From 571d91dcadfa3cef499010b4eddb9b58b0da4d24 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Wed, 25 Oct 2023 13:16:19 -0700
Subject: perf: Add branch stack counters

Currently, the additional information of a branch entry is stored in a
u64 space. With more and more information added, the space is running
out. For example, the information of occurrences of events will be added
for each branch.

Two places were suggested to append the counters.
https://lore.kernel.org/lkml/20230802215814.GH231007@hirez.programming.kicks-ass.net/
One place is right after the flags of each branch entry. It changes the
existing struct perf_branch_entry. The later ARCH specific
implementation has to be really careful to consistently pick
the right struct.
The other place is right after the entire struct perf_branch_stack.
The disadvantage is that the pointer of the extra space has to be
recorded. The common interface perf_sample_save_brstack() has to be
updated.

The latter is much straightforward, and should be easily understood and
maintained. It is implemented in the patch.

Add a new branch sample type, PERF_SAMPLE_BRANCH_COUNTERS, to indicate
the event which is recorded in the branch info.

The "u64 counters" may store the occurrences of several events. The
information regarding the number of events/counters and the width of
each counter should be exposed via sysfs as a reference for the perf
tool. Define the branch_counter_nr and branch_counter_width ABI here.
The support will be implemented later in the Intel-specific patch.

Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20231025201626.3000228-1-kan.liang@linux.intel.com
---
 include/linux/perf_event.h      | 17 ++++++++++++++++-
 include/uapi/linux/perf_event.h | 10 ++++++++++
 2 files changed, 26 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 0367d748fae0..7897ef066027 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1139,6 +1139,10 @@ static inline bool branch_sample_priv(const struct perf_event *event)
 	return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_PRIV_SAVE;
 }
 
+static inline bool branch_sample_counters(const struct perf_event *event)
+{
+	return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS;
+}
 
 struct perf_sample_data {
 	/*
@@ -1173,6 +1177,7 @@ struct perf_sample_data {
 	struct perf_callchain_entry	*callchain;
 	struct perf_raw_record		*raw;
 	struct perf_branch_stack	*br_stack;
+	u64				*br_stack_cntr;
 	union perf_sample_weight	weight;
 	union  perf_mem_data_src	data_src;
 	u64				txn;
@@ -1250,7 +1255,8 @@ static inline void perf_sample_save_raw_data(struct perf_sample_data *data,
 
 static inline void perf_sample_save_brstack(struct perf_sample_data *data,
 					    struct perf_event *event,
-					    struct perf_branch_stack *brs)
+					    struct perf_branch_stack *brs,
+					    u64 *brs_cntr)
 {
 	int size = sizeof(u64); /* nr */
 
@@ -1258,7 +1264,16 @@ static inline void perf_sample_save_brstack(struct perf_sample_data *data,
 		size += sizeof(u64);
 	size += brs->nr * sizeof(struct perf_branch_entry);
 
+	/*
+	 * The extension space for counters is appended after the
+	 * struct perf_branch_stack. It is used to store the occurrences
+	 * of events of each branch.
+	 */
+	if (brs_cntr)
+		size += brs->nr * sizeof(u64);
+
 	data->br_stack = brs;
+	data->br_stack_cntr = brs_cntr;
 	data->dyn_size += size;
 	data->sample_flags |= PERF_SAMPLE_BRANCH_STACK;
 }
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 39c6a250dd1b..4461f380425b 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -204,6 +204,8 @@ enum perf_branch_sample_type_shift {
 
 	PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT	= 18, /* save privilege mode */
 
+	PERF_SAMPLE_BRANCH_COUNTERS_SHIFT	= 19, /* save occurrences of events on a branch */
+
 	PERF_SAMPLE_BRANCH_MAX_SHIFT		/* non-ABI */
 };
 
@@ -235,6 +237,8 @@ enum perf_branch_sample_type {
 
 	PERF_SAMPLE_BRANCH_PRIV_SAVE	= 1U << PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT,
 
+	PERF_SAMPLE_BRANCH_COUNTERS	= 1U << PERF_SAMPLE_BRANCH_COUNTERS_SHIFT,
+
 	PERF_SAMPLE_BRANCH_MAX		= 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT,
 };
 
@@ -982,6 +986,12 @@ enum perf_event_type {
 	 *	{ u64                   nr;
 	 *	  { u64	hw_idx; } && PERF_SAMPLE_BRANCH_HW_INDEX
 	 *        { u64 from, to, flags } lbr[nr];
+	 *        #
+	 *        # The format of the counters is decided by the
+	 *        # "branch_counter_nr" and "branch_counter_width",
+	 *        # which are defined in the ABI.
+	 *        #
+	 *        { u64 counters; } cntr[nr] && PERF_SAMPLE_BRANCH_COUNTERS
 	 *      } && PERF_SAMPLE_BRANCH_STACK
 	 *
 	 * 	{ u64			abi; # enum perf_sample_regs_abi
-- 
cgit v1.2.3


From 1f2376cd03dd3b965d130ed46a7c92769d614ba1 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Wed, 25 Oct 2023 13:16:21 -0700
Subject: perf: Add branch_sample_call_stack

Add a helper function to check call stack sample type.

The later patch will invoke the function in several places.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20231025201626.3000228-3-kan.liang@linux.intel.com
---
 arch/x86/events/core.c     | 2 +-
 include/linux/perf_event.h | 5 +++++
 2 files changed, 6 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 40c9af124128..09050641ce5d 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -601,7 +601,7 @@ int x86_pmu_hw_config(struct perf_event *event)
 		}
 	}
 
-	if (event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK)
+	if (branch_sample_call_stack(event))
 		event->attach_state |= PERF_ATTACH_TASK_DATA;
 
 	/*
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 7897ef066027..ac1a59c1f252 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1144,6 +1144,11 @@ static inline bool branch_sample_counters(const struct perf_event *event)
 	return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS;
 }
 
+static inline bool branch_sample_call_stack(const struct perf_event *event)
+{
+	return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK;
+}
+
 struct perf_sample_data {
 	/*
 	 * Fields set by perf_sample_data_init() unconditionally,
-- 
cgit v1.2.3


From 33744916196b4ed7a50f6f47af7c3ad46b730ce6 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Wed, 25 Oct 2023 13:16:23 -0700
Subject: perf/x86/intel: Support branch counters logging

The branch counters logging (A.K.A LBR event logging) introduces a
per-counter indication of precise event occurrences in LBRs. It can
provide a means to attribute exposed retirement latency to combinations
of events across a block of instructions. It also provides a means of
attributing Timed LBR latencies to events.

The feature is first introduced on SRF/GRR. It is an enhancement of the
ARCH LBR. It adds new fields in the LBR_INFO MSRs to log the occurrences
of events on the GP counters. The information is displayed by the order
of counters.

The design proposed in this patch requires that the events which are
logged must be in a group with the event that has LBR. If there are
more than one LBR group, the counters logging information only from the
current group (overflowed) are stored for the perf tool, otherwise the
perf tool cannot know which and when other groups are scheduled
especially when multiplexing is triggered. The user can ensure it uses
the maximum number of counters that support LBR info (4 by now) by
making the group large enough.

The HW only logs events by the order of counters. The order may be
different from the order of enabling which the perf tool can understand.
When parsing the information of each branch entry, convert the counter
order to the enabled order, and store the enabled order in the extension
space.

Unconditionally reset LBRs for an LBR event group when it's deleted. The
logged counter information is only valid for the current LBR group. If
another LBR group is scheduled later, the information from the stale
LBRs would be otherwise wrongly interpreted.

Add a sanity check in intel_pmu_hw_config(). Disable the feature if other
counter filters (inv, cmask, edge, in_tx) are set or LBR call stack mode
is enabled. (For the LBR call stack mode, we cannot simply flush the
LBR, since it will break the call stack. Also, there is no obvious usage
with the call stack mode for now.)

Only applying the PERF_SAMPLE_BRANCH_COUNTERS doesn't require any branch
stack setup.

Expose the maximum number of supported counters and the width of the
counters into the sysfs. The perf tool can use the information to parse
the logged counters in each branch.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20231025201626.3000228-5-kan.liang@linux.intel.com
---
 arch/x86/events/intel/core.c       | 103 ++++++++++++++++++++++++++++++++++---
 arch/x86/events/intel/ds.c         |   2 +-
 arch/x86/events/intel/lbr.c        |  85 +++++++++++++++++++++++++++++-
 arch/x86/events/perf_event.h       |  12 +++++
 arch/x86/events/perf_event_flags.h |   1 +
 arch/x86/include/asm/msr-index.h   |   5 ++
 arch/x86/include/asm/perf_event.h  |   4 ++
 include/uapi/linux/perf_event.h    |   3 ++
 8 files changed, 207 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 584b58df7bf6..e068a96aeb54 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2792,6 +2792,7 @@ static void intel_pmu_enable_fixed(struct perf_event *event)
 
 static void intel_pmu_enable_event(struct perf_event *event)
 {
+	u64 enable_mask = ARCH_PERFMON_EVENTSEL_ENABLE;
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
@@ -2800,8 +2801,10 @@ static void intel_pmu_enable_event(struct perf_event *event)
 
 	switch (idx) {
 	case 0 ... INTEL_PMC_IDX_FIXED - 1:
+		if (branch_sample_counters(event))
+			enable_mask |= ARCH_PERFMON_EVENTSEL_BR_CNTR;
 		intel_set_masks(event, idx);
-		__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
+		__x86_pmu_enable_event(hwc, enable_mask);
 		break;
 	case INTEL_PMC_IDX_FIXED ... INTEL_PMC_IDX_FIXED_BTS - 1:
 	case INTEL_PMC_IDX_METRIC_BASE ... INTEL_PMC_IDX_METRIC_END:
@@ -3052,7 +3055,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 		perf_sample_data_init(&data, 0, event->hw.last_period);
 
 		if (has_branch_stack(event))
-			perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL);
+			intel_pmu_lbr_save_brstack(&data, cpuc, event);
 
 		if (perf_event_overflow(event, &data, regs))
 			x86_pmu_stop(event, 0);
@@ -3617,6 +3620,13 @@ intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 	if (cpuc->excl_cntrs)
 		return intel_get_excl_constraints(cpuc, event, idx, c2);
 
+	/* Not all counters support the branch counter feature. */
+	if (branch_sample_counters(event)) {
+		c2 = dyn_constraint(cpuc, c2, idx);
+		c2->idxmsk64 &= x86_pmu.lbr_counters;
+		c2->weight = hweight64(c2->idxmsk64);
+	}
+
 	return c2;
 }
 
@@ -3905,6 +3915,58 @@ static int intel_pmu_hw_config(struct perf_event *event)
 	if (needs_branch_stack(event) && is_sampling_event(event))
 		event->hw.flags  |= PERF_X86_EVENT_NEEDS_BRANCH_STACK;
 
+	if (branch_sample_counters(event)) {
+		struct perf_event *leader, *sibling;
+		int num = 0;
+
+		if (!(x86_pmu.flags & PMU_FL_BR_CNTR) ||
+		    (event->attr.config & ~INTEL_ARCH_EVENT_MASK))
+			return -EINVAL;
+
+		/*
+		 * The branch counter logging is not supported in the call stack
+		 * mode yet, since we cannot simply flush the LBR during e.g.,
+		 * multiplexing. Also, there is no obvious usage with the call
+		 * stack mode. Simply forbids it for now.
+		 *
+		 * If any events in the group enable the branch counter logging
+		 * feature, the group is treated as a branch counter logging
+		 * group, which requires the extra space to store the counters.
+		 */
+		leader = event->group_leader;
+		if (branch_sample_call_stack(leader))
+			return -EINVAL;
+		if (branch_sample_counters(leader))
+			num++;
+		leader->hw.flags |= PERF_X86_EVENT_BRANCH_COUNTERS;
+
+		for_each_sibling_event(sibling, leader) {
+			if (branch_sample_call_stack(sibling))
+				return -EINVAL;
+			if (branch_sample_counters(sibling))
+				num++;
+		}
+
+		if (num > fls(x86_pmu.lbr_counters))
+			return -EINVAL;
+		/*
+		 * Only applying the PERF_SAMPLE_BRANCH_COUNTERS doesn't
+		 * require any branch stack setup.
+		 * Clear the bit to avoid unnecessary branch stack setup.
+		 */
+		if (0 == (event->attr.branch_sample_type &
+			  ~(PERF_SAMPLE_BRANCH_PLM_ALL |
+			    PERF_SAMPLE_BRANCH_COUNTERS)))
+			event->hw.flags  &= ~PERF_X86_EVENT_NEEDS_BRANCH_STACK;
+
+		/*
+		 * Force the leader to be a LBR event. So LBRs can be reset
+		 * with the leader event. See intel_pmu_lbr_del() for details.
+		 */
+		if (!intel_pmu_needs_branch_stack(leader))
+			return -EINVAL;
+	}
+
 	if (intel_pmu_needs_branch_stack(event)) {
 		ret = intel_pmu_setup_lbr_filter(event);
 		if (ret)
@@ -4383,8 +4445,13 @@ cmt_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 	 */
 	if (event->attr.precise_ip == 3) {
 		/* Force instruction:ppp on PMC0, 1 and Fixed counter 0 */
-		if (constraint_match(&fixed0_constraint, event->hw.config))
-			return &fixed0_counter0_1_constraint;
+		if (constraint_match(&fixed0_constraint, event->hw.config)) {
+			/* The fixed counter 0 doesn't support LBR event logging. */
+			if (branch_sample_counters(event))
+				return &counter0_1_constraint;
+			else
+				return &fixed0_counter0_1_constraint;
+		}
 
 		switch (c->idxmsk64 & 0x3ull) {
 		case 0x1:
@@ -4563,7 +4630,7 @@ int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu)
 			goto err;
 	}
 
-	if (x86_pmu.flags & (PMU_FL_EXCL_CNTRS | PMU_FL_TFA)) {
+	if (x86_pmu.flags & (PMU_FL_EXCL_CNTRS | PMU_FL_TFA | PMU_FL_BR_CNTR)) {
 		size_t sz = X86_PMC_IDX_MAX * sizeof(struct event_constraint);
 
 		cpuc->constraint_list = kzalloc_node(sz, GFP_KERNEL, cpu_to_node(cpu));
@@ -5535,15 +5602,39 @@ static ssize_t branches_show(struct device *cdev,
 
 static DEVICE_ATTR_RO(branches);
 
+static ssize_t branch_counter_nr_show(struct device *cdev,
+				      struct device_attribute *attr,
+				      char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%d\n", fls(x86_pmu.lbr_counters));
+}
+
+static DEVICE_ATTR_RO(branch_counter_nr);
+
+static ssize_t branch_counter_width_show(struct device *cdev,
+					 struct device_attribute *attr,
+					 char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%d\n", LBR_INFO_BR_CNTR_BITS);
+}
+
+static DEVICE_ATTR_RO(branch_counter_width);
+
 static struct attribute *lbr_attrs[] = {
 	&dev_attr_branches.attr,
+	&dev_attr_branch_counter_nr.attr,
+	&dev_attr_branch_counter_width.attr,
 	NULL
 };
 
 static umode_t
 lbr_is_visible(struct kobject *kobj, struct attribute *attr, int i)
 {
-	return x86_pmu.lbr_nr ? attr->mode : 0;
+	/* branches */
+	if (i == 0)
+		return x86_pmu.lbr_nr ? attr->mode : 0;
+
+	return (x86_pmu.flags & PMU_FL_BR_CNTR) ? attr->mode : 0;
 }
 
 static char pmu_name_str[30];
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index cb3f329f8fa4..d49d661ec0a7 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1912,7 +1912,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 
 		if (has_branch_stack(event)) {
 			intel_pmu_store_pebs_lbrs(lbr);
-			perf_sample_save_brstack(data, event, &cpuc->lbr_stack, NULL);
+			intel_pmu_lbr_save_brstack(data, cpuc, event);
 		}
 	}
 
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index c3b0d15a9841..78cd5084104e 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -676,6 +676,25 @@ void intel_pmu_lbr_del(struct perf_event *event)
 	WARN_ON_ONCE(cpuc->lbr_users < 0);
 	WARN_ON_ONCE(cpuc->lbr_pebs_users < 0);
 	perf_sched_cb_dec(event->pmu);
+
+	/*
+	 * The logged occurrences information is only valid for the
+	 * current LBR group. If another LBR group is scheduled in
+	 * later, the information from the stale LBRs will be wrongly
+	 * interpreted. Reset the LBRs here.
+	 *
+	 * Only clear once for a branch counter group with the leader
+	 * event. Because
+	 * - Cannot simply reset the LBRs with the !cpuc->lbr_users.
+	 *   Because it's possible that the last LBR user is not in a
+	 *   branch counter group, e.g., a branch_counters group +
+	 *   several normal LBR events.
+	 * - The LBR reset can be done with any one of the events in a
+	 *   branch counter group, since they are always scheduled together.
+	 *   It's easy to force the leader event an LBR event.
+	 */
+	if (is_branch_counters_group(event) && event == event->group_leader)
+		intel_pmu_lbr_reset();
 }
 
 static inline bool vlbr_exclude_host(void)
@@ -866,6 +885,8 @@ static __always_inline u16 get_lbr_cycles(u64 info)
 	return cycles;
 }
 
+static_assert((64 - PERF_BRANCH_ENTRY_INFO_BITS_MAX) > LBR_INFO_BR_CNTR_NUM * LBR_INFO_BR_CNTR_BITS);
+
 static void intel_pmu_store_lbr(struct cpu_hw_events *cpuc,
 				struct lbr_entry *entries)
 {
@@ -898,11 +919,67 @@ static void intel_pmu_store_lbr(struct cpu_hw_events *cpuc,
 		e->abort	= !!(info & LBR_INFO_ABORT);
 		e->cycles	= get_lbr_cycles(info);
 		e->type		= get_lbr_br_type(info);
+
+		/*
+		 * Leverage the reserved field of cpuc->lbr_entries[i] to
+		 * temporarily store the branch counters information.
+		 * The later code will decide what content can be disclosed
+		 * to the perf tool. Pleae see intel_pmu_lbr_counters_reorder().
+		 */
+		e->reserved	= (info >> LBR_INFO_BR_CNTR_OFFSET) & LBR_INFO_BR_CNTR_FULL_MASK;
 	}
 
 	cpuc->lbr_stack.nr = i;
 }
 
+/*
+ * The enabled order may be different from the counter order.
+ * Update the lbr_counters with the enabled order.
+ */
+static void intel_pmu_lbr_counters_reorder(struct cpu_hw_events *cpuc,
+					   struct perf_event *event)
+{
+	int i, j, pos = 0, order[X86_PMC_IDX_MAX];
+	struct perf_event *leader, *sibling;
+	u64 src, dst, cnt;
+
+	leader = event->group_leader;
+	if (branch_sample_counters(leader))
+		order[pos++] = leader->hw.idx;
+
+	for_each_sibling_event(sibling, leader) {
+		if (!branch_sample_counters(sibling))
+			continue;
+		order[pos++] = sibling->hw.idx;
+	}
+
+	WARN_ON_ONCE(!pos);
+
+	for (i = 0; i < cpuc->lbr_stack.nr; i++) {
+		src = cpuc->lbr_entries[i].reserved;
+		dst = 0;
+		for (j = 0; j < pos; j++) {
+			cnt = (src >> (order[j] * LBR_INFO_BR_CNTR_BITS)) & LBR_INFO_BR_CNTR_MASK;
+			dst |= cnt << j * LBR_INFO_BR_CNTR_BITS;
+		}
+		cpuc->lbr_counters[i] = dst;
+		cpuc->lbr_entries[i].reserved = 0;
+	}
+}
+
+void intel_pmu_lbr_save_brstack(struct perf_sample_data *data,
+				struct cpu_hw_events *cpuc,
+				struct perf_event *event)
+{
+	if (is_branch_counters_group(event)) {
+		intel_pmu_lbr_counters_reorder(cpuc, event);
+		perf_sample_save_brstack(data, event, &cpuc->lbr_stack, cpuc->lbr_counters);
+		return;
+	}
+
+	perf_sample_save_brstack(data, event, &cpuc->lbr_stack, NULL);
+}
+
 static void intel_pmu_arch_lbr_read(struct cpu_hw_events *cpuc)
 {
 	intel_pmu_store_lbr(cpuc, NULL);
@@ -1173,8 +1250,10 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
 	for (i = 0; i < cpuc->lbr_stack.nr; ) {
 		if (!cpuc->lbr_entries[i].from) {
 			j = i;
-			while (++j < cpuc->lbr_stack.nr)
+			while (++j < cpuc->lbr_stack.nr) {
 				cpuc->lbr_entries[j-1] = cpuc->lbr_entries[j];
+				cpuc->lbr_counters[j-1] = cpuc->lbr_counters[j];
+			}
 			cpuc->lbr_stack.nr--;
 			if (!cpuc->lbr_entries[i].from)
 				continue;
@@ -1525,8 +1604,12 @@ void __init intel_pmu_arch_lbr_init(void)
 	x86_pmu.lbr_mispred = ecx.split.lbr_mispred;
 	x86_pmu.lbr_timed_lbr = ecx.split.lbr_timed_lbr;
 	x86_pmu.lbr_br_type = ecx.split.lbr_br_type;
+	x86_pmu.lbr_counters = ecx.split.lbr_counters;
 	x86_pmu.lbr_nr = lbr_nr;
 
+	if (!!x86_pmu.lbr_counters)
+		x86_pmu.flags |= PMU_FL_BR_CNTR;
+
 	if (x86_pmu.lbr_mispred)
 		static_branch_enable(&x86_lbr_mispred);
 	if (x86_pmu.lbr_timed_lbr)
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 53dd5d495ba6..fb56518356ec 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -110,6 +110,11 @@ static inline bool is_topdown_event(struct perf_event *event)
 	return is_metric_event(event) || is_slots_event(event);
 }
 
+static inline bool is_branch_counters_group(struct perf_event *event)
+{
+	return event->group_leader->hw.flags & PERF_X86_EVENT_BRANCH_COUNTERS;
+}
+
 struct amd_nb {
 	int nb_id;  /* NorthBridge id */
 	int refcnt; /* reference count */
@@ -283,6 +288,7 @@ struct cpu_hw_events {
 	int				lbr_pebs_users;
 	struct perf_branch_stack	lbr_stack;
 	struct perf_branch_entry	lbr_entries[MAX_LBR_ENTRIES];
+	u64				lbr_counters[MAX_LBR_ENTRIES]; /* branch stack extra */
 	union {
 		struct er_account		*lbr_sel;
 		struct er_account		*lbr_ctl;
@@ -888,6 +894,7 @@ struct x86_pmu {
 	unsigned int	lbr_mispred:1;
 	unsigned int	lbr_timed_lbr:1;
 	unsigned int	lbr_br_type:1;
+	unsigned int	lbr_counters:4;
 
 	void		(*lbr_reset)(void);
 	void		(*lbr_read)(struct cpu_hw_events *cpuc);
@@ -1012,6 +1019,7 @@ do {									\
 #define PMU_FL_INSTR_LATENCY	0x80 /* Support Instruction Latency in PEBS Memory Info Record */
 #define PMU_FL_MEM_LOADS_AUX	0x100 /* Require an auxiliary event for the complete memory info */
 #define PMU_FL_RETIRE_LATENCY	0x200 /* Support Retire Latency in PEBS */
+#define PMU_FL_BR_CNTR		0x400 /* Support branch counter logging */
 
 #define EVENT_VAR(_id)  event_attr_##_id
 #define EVENT_PTR(_id) &event_attr_##_id.attr.attr
@@ -1552,6 +1560,10 @@ void intel_pmu_store_pebs_lbrs(struct lbr_entry *lbr);
 
 void intel_ds_init(void);
 
+void intel_pmu_lbr_save_brstack(struct perf_sample_data *data,
+				struct cpu_hw_events *cpuc,
+				struct perf_event *event);
+
 void intel_pmu_lbr_swap_task_ctx(struct perf_event_pmu_context *prev_epc,
 				 struct perf_event_pmu_context *next_epc);
 
diff --git a/arch/x86/events/perf_event_flags.h b/arch/x86/events/perf_event_flags.h
index a1685981c520..6c977c19f2cd 100644
--- a/arch/x86/events/perf_event_flags.h
+++ b/arch/x86/events/perf_event_flags.h
@@ -21,3 +21,4 @@ PERF_ARCH(PEBS_STLAT,		0x08000) /* st+stlat data address sampling */
 PERF_ARCH(AMD_BRS,		0x10000) /* AMD Branch Sampling */
 PERF_ARCH(PEBS_LAT_HYBRID,	0x20000) /* ld and st lat for hybrid */
 PERF_ARCH(NEEDS_BRANCH_STACK,	0x40000) /* require branch stack setup */
+PERF_ARCH(BRANCH_COUNTERS,	0x80000) /* logs the counters in the extra space of each branch */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index f8b502867dd1..a5b0a19ccdf2 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -236,6 +236,11 @@
 #define LBR_INFO_CYCLES			0xffff
 #define LBR_INFO_BR_TYPE_OFFSET		56
 #define LBR_INFO_BR_TYPE		(0xfull << LBR_INFO_BR_TYPE_OFFSET)
+#define LBR_INFO_BR_CNTR_OFFSET		32
+#define LBR_INFO_BR_CNTR_NUM		4
+#define LBR_INFO_BR_CNTR_BITS		2
+#define LBR_INFO_BR_CNTR_MASK		GENMASK_ULL(LBR_INFO_BR_CNTR_BITS - 1, 0)
+#define LBR_INFO_BR_CNTR_FULL_MASK	GENMASK_ULL(LBR_INFO_BR_CNTR_NUM * LBR_INFO_BR_CNTR_BITS - 1, 0)
 
 #define MSR_ARCH_LBR_CTL		0x000014ce
 #define ARCH_LBR_CTL_LBREN		BIT(0)
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 2618ec7c3d1d..3736b8a46c04 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -31,6 +31,7 @@
 #define ARCH_PERFMON_EVENTSEL_ENABLE			(1ULL << 22)
 #define ARCH_PERFMON_EVENTSEL_INV			(1ULL << 23)
 #define ARCH_PERFMON_EVENTSEL_CMASK			0xFF000000ULL
+#define ARCH_PERFMON_EVENTSEL_BR_CNTR			(1ULL << 35)
 
 #define INTEL_FIXED_BITS_MASK				0xFULL
 #define INTEL_FIXED_BITS_STRIDE			4
@@ -223,6 +224,9 @@ union cpuid28_ecx {
 		unsigned int    lbr_timed_lbr:1;
 		/* Branch Type Field Supported */
 		unsigned int    lbr_br_type:1;
+		unsigned int	reserved:13;
+		/* Branch counters (Event Logging) Supported */
+		unsigned int	lbr_counters:4;
 	} split;
 	unsigned int            full;
 };
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 4461f380425b..3a64499b0f5d 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -1437,6 +1437,9 @@ struct perf_branch_entry {
 		reserved:31;
 };
 
+/* Size of used info bits in struct perf_branch_entry */
+#define PERF_BRANCH_ENTRY_INFO_BITS_MAX		33
+
 union perf_sample_weight {
 	__u64		full;
 #if defined(__LITTLE_ENDIAN_BITFIELD)
-- 
cgit v1.2.3


From d23b5c577715892c87533b13923306acc6243f93 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Sun, 29 Oct 2023 06:14:29 +0000
Subject: cgroup: Make operations on the cgroup root_list RCU safe

At present, when we perform operations on the cgroup root_list, we must
hold the cgroup_mutex, which is a relatively heavyweight lock. In reality,
we can make operations on this list RCU-safe, eliminating the need to hold
the cgroup_mutex during traversal. Modifications to the list only occur in
the cgroup root setup and destroy paths, which should be infrequent in a
production environment. In contrast, traversal may occur frequently.
Therefore, making it RCU-safe would be beneficial.

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/cgroup-defs.h     |  1 +
 kernel/cgroup/cgroup-internal.h |  3 ++-
 kernel/cgroup/cgroup.c          | 23 ++++++++++++++++-------
 3 files changed, 19 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 4a6b6b77ccb6..4caab0c6b361 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -563,6 +563,7 @@ struct cgroup_root {
 
 	/* A list running through the active hierarchies */
 	struct list_head root_list;
+	struct rcu_head rcu;
 
 	/* Hierarchy-specific flags */
 	unsigned int flags;
diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h
index c56071f150f2..5e17f01ced9f 100644
--- a/kernel/cgroup/cgroup-internal.h
+++ b/kernel/cgroup/cgroup-internal.h
@@ -170,7 +170,8 @@ extern struct list_head cgroup_roots;
 
 /* iterate across the hierarchies */
 #define for_each_root(root)						\
-	list_for_each_entry((root), &cgroup_roots, root_list)
+	list_for_each_entry_rcu((root), &cgroup_roots, root_list,	\
+				lockdep_is_held(&cgroup_mutex))
 
 /**
  * for_each_subsys - iterate all enabled cgroup subsystems
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 3a436e4f0da1..19784d44d615 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1315,7 +1315,7 @@ static void cgroup_exit_root_id(struct cgroup_root *root)
 
 void cgroup_free_root(struct cgroup_root *root)
 {
-	kfree(root);
+	kfree_rcu(root, rcu);
 }
 
 static void cgroup_destroy_root(struct cgroup_root *root)
@@ -1348,7 +1348,7 @@ static void cgroup_destroy_root(struct cgroup_root *root)
 	spin_unlock_irq(&css_set_lock);
 
 	WARN_ON_ONCE(list_empty(&root->root_list));
-	list_del(&root->root_list);
+	list_del_rcu(&root->root_list);
 	cgroup_root_count--;
 
 	if (!have_favordynmods)
@@ -1389,7 +1389,15 @@ static inline struct cgroup *__cset_cgroup_from_root(struct css_set *cset,
 		}
 	}
 
-	BUG_ON(!res_cgroup);
+	/*
+	 * If cgroup_mutex is not held, the cgrp_cset_link will be freed
+	 * before we remove the cgroup root from the root_list. Consequently,
+	 * when accessing a cgroup root, the cset_link may have already been
+	 * freed, resulting in a NULL res_cgroup. However, by holding the
+	 * cgroup_mutex, we ensure that res_cgroup can't be NULL.
+	 * If we don't hold cgroup_mutex in the caller, we must do the NULL
+	 * check.
+	 */
 	return res_cgroup;
 }
 
@@ -1448,7 +1456,6 @@ static struct cgroup *current_cgns_cgroup_dfl(void)
 static struct cgroup *cset_cgroup_from_root(struct css_set *cset,
 					    struct cgroup_root *root)
 {
-	lockdep_assert_held(&cgroup_mutex);
 	lockdep_assert_held(&css_set_lock);
 
 	return __cset_cgroup_from_root(cset, root);
@@ -1456,7 +1463,9 @@ static struct cgroup *cset_cgroup_from_root(struct css_set *cset,
 
 /*
  * Return the cgroup for "task" from the given hierarchy. Must be
- * called with cgroup_mutex and css_set_lock held.
+ * called with css_set_lock held to prevent task's groups from being modified.
+ * Must be called with either cgroup_mutex or rcu read lock to prevent the
+ * cgroup root from being destroyed.
  */
 struct cgroup *task_cgroup_from_root(struct task_struct *task,
 				     struct cgroup_root *root)
@@ -2031,7 +2040,7 @@ void init_cgroup_root(struct cgroup_fs_context *ctx)
 	struct cgroup_root *root = ctx->root;
 	struct cgroup *cgrp = &root->cgrp;
 
-	INIT_LIST_HEAD(&root->root_list);
+	INIT_LIST_HEAD_RCU(&root->root_list);
 	atomic_set(&root->nr_cgrps, 1);
 	cgrp->root = root;
 	init_cgroup_housekeeping(cgrp);
@@ -2114,7 +2123,7 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
 	 * care of subsystems' refcounts, which are explicitly dropped in
 	 * the failure exit path.
 	 */
-	list_add(&root->root_list, &cgroup_roots);
+	list_add_rcu(&root->root_list, &cgroup_roots);
 	cgroup_root_count++;
 
 	/*
-- 
cgit v1.2.3


From aecd408b7e50742868b3305c24325a89024e2a30 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Sun, 29 Oct 2023 06:14:32 +0000
Subject: cgroup: Add a new helper for cgroup1 hierarchy

A new helper is added for cgroup1 hierarchy:

- task_get_cgroup1
  Acquires the associated cgroup of a task within a specific cgroup1
  hierarchy. The cgroup1 hierarchy is identified by its hierarchy ID.

This helper function is added to facilitate the tracing of tasks within
a particular container or cgroup dir in BPF programs. It's important to
note that this helper is designed specifically for cgroup1 only.

tj: Use irsqsave/restore as suggested by Hou Tao <houtao@huaweicloud.com>.

Suggested-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Cc: Hou Tao <houtao@huaweicloud.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/cgroup.h          |  4 +++-
 kernel/cgroup/cgroup-internal.h |  1 -
 kernel/cgroup/cgroup-v1.c       | 34 ++++++++++++++++++++++++++++++++++
 3 files changed, 37 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 0ef0af66080e..34aaf0e87def 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -69,6 +69,7 @@ struct css_task_iter {
 extern struct file_system_type cgroup_fs_type;
 extern struct cgroup_root cgrp_dfl_root;
 extern struct css_set init_css_set;
+extern spinlock_t css_set_lock;
 
 #define SUBSYS(_x) extern struct cgroup_subsys _x ## _cgrp_subsys;
 #include <linux/cgroup_subsys.h>
@@ -386,7 +387,6 @@ static inline void cgroup_unlock(void)
  * as locks used during the cgroup_subsys::attach() methods.
  */
 #ifdef CONFIG_PROVE_RCU
-extern spinlock_t css_set_lock;
 #define task_css_set_check(task, __c)					\
 	rcu_dereference_check((task)->cgroups,				\
 		rcu_read_lock_sched_held() ||				\
@@ -853,4 +853,6 @@ static inline void cgroup_bpf_put(struct cgroup *cgrp) {}
 
 #endif /* CONFIG_CGROUP_BPF */
 
+struct cgroup *task_get_cgroup1(struct task_struct *tsk, int hierarchy_id);
+
 #endif /* _LINUX_CGROUP_H */
diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h
index 5e17f01ced9f..520b90dd97ec 100644
--- a/kernel/cgroup/cgroup-internal.h
+++ b/kernel/cgroup/cgroup-internal.h
@@ -164,7 +164,6 @@ struct cgroup_mgctx {
 #define DEFINE_CGROUP_MGCTX(name)						\
 	struct cgroup_mgctx name = CGROUP_MGCTX_INIT(name)
 
-extern spinlock_t css_set_lock;
 extern struct cgroup_subsys *cgroup_subsys[];
 extern struct list_head cgroup_roots;
 
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 76db6c67e39a..04d11a7dd95f 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -1262,6 +1262,40 @@ int cgroup1_get_tree(struct fs_context *fc)
 	return ret;
 }
 
+/**
+ * task_get_cgroup1 - Acquires the associated cgroup of a task within a
+ * specific cgroup1 hierarchy. The cgroup1 hierarchy is identified by its
+ * hierarchy ID.
+ * @tsk: The target task
+ * @hierarchy_id: The ID of a cgroup1 hierarchy
+ *
+ * On success, the cgroup is returned. On failure, ERR_PTR is returned.
+ * We limit it to cgroup1 only.
+ */
+struct cgroup *task_get_cgroup1(struct task_struct *tsk, int hierarchy_id)
+{
+	struct cgroup *cgrp = ERR_PTR(-ENOENT);
+	struct cgroup_root *root;
+	unsigned long flags;
+
+	rcu_read_lock();
+	for_each_root(root) {
+		/* cgroup1 only*/
+		if (root == &cgrp_dfl_root)
+			continue;
+		if (root->hierarchy_id != hierarchy_id)
+			continue;
+		spin_lock_irqsave(&css_set_lock, flags);
+		cgrp = task_cgroup_from_root(tsk, root);
+		if (!cgrp || !cgroup_tryget(cgrp))
+			cgrp = ERR_PTR(-ENOENT);
+		spin_unlock_irqrestore(&css_set_lock, flags);
+		break;
+	}
+	rcu_read_unlock();
+	return cgrp;
+}
+
 static int __init cgroup1_wq_init(void)
 {
 	/*
-- 
cgit v1.2.3


From 74523c06ae20b83c5508a98af62393ac34913362 Mon Sep 17 00:00:00 2001
From: Song Liu <song@kernel.org>
Date: Mon, 6 Nov 2023 20:57:23 -0800
Subject: bpf: Add __bpf_dynptr_data* for in kernel use

Different types of bpf dynptr have different internal data storage.
Specifically, SKB and XDP type of dynptr may have non-continuous data.
Therefore, it is not always safe to directly access dynptr->data.

Add __bpf_dynptr_data and __bpf_dynptr_data_rw to replace direct access to
dynptr->data.

Update bpf_verify_pkcs7_signature to use __bpf_dynptr_data instead of
dynptr->data.

Signed-off-by: Song Liu <song@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://lore.kernel.org/bpf/20231107045725.2278852-2-song@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h      |  2 ++
 kernel/bpf/helpers.c     | 19 +++++++++++++++++++
 kernel/trace/bpf_trace.c | 12 ++++++++----
 3 files changed, 29 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index b4825d3cdb29..eb84caf133df 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1222,6 +1222,8 @@ enum bpf_dynptr_type {
 
 int bpf_dynptr_check_size(u32 size);
 u32 __bpf_dynptr_size(const struct bpf_dynptr_kern *ptr);
+const void *__bpf_dynptr_data(const struct bpf_dynptr_kern *ptr, u32 len);
+void *__bpf_dynptr_data_rw(const struct bpf_dynptr_kern *ptr, u32 len);
 
 #ifdef CONFIG_BPF_JIT
 int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr);
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 56b0c1f678ee..174f02a9e703 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -2618,3 +2618,22 @@ static int __init kfunc_init(void)
 }
 
 late_initcall(kfunc_init);
+
+/* Get a pointer to dynptr data up to len bytes for read only access. If
+ * the dynptr doesn't have continuous data up to len bytes, return NULL.
+ */
+const void *__bpf_dynptr_data(const struct bpf_dynptr_kern *ptr, u32 len)
+{
+	return bpf_dynptr_slice(ptr, 0, NULL, len);
+}
+
+/* Get a pointer to dynptr data up to len bytes for read write access. If
+ * the dynptr doesn't have continuous data up to len bytes, or the dynptr
+ * is read only, return NULL.
+ */
+void *__bpf_dynptr_data_rw(const struct bpf_dynptr_kern *ptr, u32 len)
+{
+	if (__bpf_dynptr_is_rdonly(ptr))
+		return NULL;
+	return (void *)__bpf_dynptr_data(ptr, len);
+}
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 84e8a0f6e4e0..f0b8b7c29126 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1376,6 +1376,8 @@ __bpf_kfunc int bpf_verify_pkcs7_signature(struct bpf_dynptr_kern *data_ptr,
 			       struct bpf_dynptr_kern *sig_ptr,
 			       struct bpf_key *trusted_keyring)
 {
+	const void *data, *sig;
+	u32 data_len, sig_len;
 	int ret;
 
 	if (trusted_keyring->has_ref) {
@@ -1392,10 +1394,12 @@ __bpf_kfunc int bpf_verify_pkcs7_signature(struct bpf_dynptr_kern *data_ptr,
 			return ret;
 	}
 
-	return verify_pkcs7_signature(data_ptr->data,
-				      __bpf_dynptr_size(data_ptr),
-				      sig_ptr->data,
-				      __bpf_dynptr_size(sig_ptr),
+	data_len = __bpf_dynptr_size(data_ptr);
+	data = __bpf_dynptr_data(data_ptr, data_len);
+	sig_len = __bpf_dynptr_size(sig_ptr);
+	sig = __bpf_dynptr_data(sig_ptr, sig_len);
+
+	return verify_pkcs7_signature(data, data_len, sig, sig_len,
 				      trusted_keyring->key,
 				      VERIFYING_UNSPECIFIED_SIGNATURE, NULL,
 				      NULL);
-- 
cgit v1.2.3


From 790ce3cfefb1b768dccd4eee324ddef0f0ce3db4 Mon Sep 17 00:00:00 2001
From: Dave Marchevsky <davemarchevsky@fb.com>
Date: Tue, 7 Nov 2023 00:56:37 -0800
Subject: bpf: Move GRAPH_{ROOT,NODE}_MASK macros into btf_field_type enum

This refactoring patch removes the unused BPF_GRAPH_NODE_OR_ROOT
btf_field_type and moves BPF_GRAPH_{NODE,ROOT} macros into the
btf_field_type enum. Further patches in the series will use
BPF_GRAPH_NODE, so let's move this useful definition out of btf.c.

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Link: https://lore.kernel.org/r/20231107085639.3016113-5-davemarchevsky@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h |  4 ++--
 kernel/bpf/btf.c    | 11 ++++-------
 2 files changed, 6 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index eb84caf133df..4001d11be151 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -186,8 +186,8 @@ enum btf_field_type {
 	BPF_LIST_NODE  = (1 << 6),
 	BPF_RB_ROOT    = (1 << 7),
 	BPF_RB_NODE    = (1 << 8),
-	BPF_GRAPH_NODE_OR_ROOT = BPF_LIST_NODE | BPF_LIST_HEAD |
-				 BPF_RB_NODE | BPF_RB_ROOT,
+	BPF_GRAPH_NODE = BPF_RB_NODE | BPF_LIST_NODE,
+	BPF_GRAPH_ROOT = BPF_RB_ROOT | BPF_LIST_HEAD,
 	BPF_REFCOUNT   = (1 << 9),
 };
 
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 15d71d2986d3..63cf4128fc05 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3840,9 +3840,6 @@ end:
 	return ERR_PTR(ret);
 }
 
-#define GRAPH_ROOT_MASK (BPF_LIST_HEAD | BPF_RB_ROOT)
-#define GRAPH_NODE_MASK (BPF_LIST_NODE | BPF_RB_NODE)
-
 int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec)
 {
 	int i;
@@ -3855,13 +3852,13 @@ int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec)
 	 * Hence we only need to ensure that bpf_{list_head,rb_root} ownership
 	 * does not form cycles.
 	 */
-	if (IS_ERR_OR_NULL(rec) || !(rec->field_mask & GRAPH_ROOT_MASK))
+	if (IS_ERR_OR_NULL(rec) || !(rec->field_mask & BPF_GRAPH_ROOT))
 		return 0;
 	for (i = 0; i < rec->cnt; i++) {
 		struct btf_struct_meta *meta;
 		u32 btf_id;
 
-		if (!(rec->fields[i].type & GRAPH_ROOT_MASK))
+		if (!(rec->fields[i].type & BPF_GRAPH_ROOT))
 			continue;
 		btf_id = rec->fields[i].graph_root.value_btf_id;
 		meta = btf_find_struct_meta(btf, btf_id);
@@ -3873,7 +3870,7 @@ int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec)
 		 * to check ownership cycle for a type unless it's also a
 		 * node type.
 		 */
-		if (!(rec->field_mask & GRAPH_NODE_MASK))
+		if (!(rec->field_mask & BPF_GRAPH_NODE))
 			continue;
 
 		/* We need to ensure ownership acyclicity among all types. The
@@ -3909,7 +3906,7 @@ int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec)
 		 * - A is both an root and node.
 		 * - B is only an node.
 		 */
-		if (meta->record->field_mask & GRAPH_ROOT_MASK)
+		if (meta->record->field_mask & BPF_GRAPH_ROOT)
 			return -ELOOP;
 	}
 	return 0;
-- 
cgit v1.2.3


From 155addf0814a92d08fce26a11b27e3315cdba977 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Fri, 3 Nov 2023 19:49:00 -0700
Subject: bpf: Use named fields for certain bpf uapi structs

Martin and Vadim reported a verifier failure with bpf_dynptr usage.
The issue is mentioned but Vadim workarounded the issue with source
change ([1]). The below describes what is the issue and why there
is a verification failure.

  int BPF_PROG(skb_crypto_setup) {
    struct bpf_dynptr algo, key;
    ...

    bpf_dynptr_from_mem(..., ..., 0, &algo);
    ...
  }

The bpf program is using vmlinux.h, so we have the following definition in
vmlinux.h:
  struct bpf_dynptr {
        long: 64;
        long: 64;
  };
Note that in uapi header bpf.h, we have
  struct bpf_dynptr {
        long: 64;
        long: 64;
} __attribute__((aligned(8)));

So we lost alignment information for struct bpf_dynptr by using vmlinux.h.
Let us take a look at a simple program below:
  $ cat align.c
  typedef unsigned long long __u64;
  struct bpf_dynptr_no_align {
        __u64 :64;
        __u64 :64;
  };
  struct bpf_dynptr_yes_align {
        __u64 :64;
        __u64 :64;
  } __attribute__((aligned(8)));

  void bar(void *, void *);
  int foo() {
    struct bpf_dynptr_no_align a;
    struct bpf_dynptr_yes_align b;
    bar(&a, &b);
    return 0;
  }
  $ clang --target=bpf -O2 -S -emit-llvm align.c

Look at the generated IR file align.ll:
  ...
  %a = alloca %struct.bpf_dynptr_no_align, align 1
  %b = alloca %struct.bpf_dynptr_yes_align, align 8
  ...

The compiler dictates the alignment for struct bpf_dynptr_no_align is 1 and
the alignment for struct bpf_dynptr_yes_align is 8. So theoretically compiler
could allocate variable %a with alignment 1 although in reallity the compiler
may choose a different alignment by considering other local variables.

In [1], the verification failure happens because variable 'algo' is allocated
on the stack with alignment 4 (fp-28). But the verifer wants its alignment
to be 8.

To fix the issue, the RFC patch ([1]) tried to add '__attribute__((aligned(8)))'
to struct bpf_dynptr plus other similar structs. Andrii suggested that
we could directly modify uapi struct with named fields like struct 'bpf_iter_num':
  struct bpf_iter_num {
        /* opaque iterator state; having __u64 here allows to preserve correct
         * alignment requirements in vmlinux.h, generated from BTF
         */
        __u64 __opaque[1];
  } __attribute__((aligned(8)));

Indeed, adding named fields for those affected structs in this patch can preserve
alignment when bpf program references them in vmlinux.h. With this patch,
the verification failure in [1] can also be resolved.

  [1] https://lore.kernel.org/bpf/1b100f73-7625-4c1f-3ae5-50ecf84d3ff0@linux.dev/
  [2] https://lore.kernel.org/bpf/20231103055218.2395034-1-yonghong.song@linux.dev/

Cc: Vadim Fedorenko <vadfed@meta.com>
Cc: Martin KaFai Lau <martin.lau@linux.dev>
Suggested-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20231104024900.1539182-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h       | 23 +++++++----------------
 tools/include/uapi/linux/bpf.h | 23 +++++++----------------
 2 files changed, 14 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 0f6cdf52b1da..095ca7238ac2 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -7151,40 +7151,31 @@ struct bpf_spin_lock {
 };
 
 struct bpf_timer {
-	__u64 :64;
-	__u64 :64;
+	__u64 __opaque[2];
 } __attribute__((aligned(8)));
 
 struct bpf_dynptr {
-	__u64 :64;
-	__u64 :64;
+	__u64 __opaque[2];
 } __attribute__((aligned(8)));
 
 struct bpf_list_head {
-	__u64 :64;
-	__u64 :64;
+	__u64 __opaque[2];
 } __attribute__((aligned(8)));
 
 struct bpf_list_node {
-	__u64 :64;
-	__u64 :64;
-	__u64 :64;
+	__u64 __opaque[3];
 } __attribute__((aligned(8)));
 
 struct bpf_rb_root {
-	__u64 :64;
-	__u64 :64;
+	__u64 __opaque[2];
 } __attribute__((aligned(8)));
 
 struct bpf_rb_node {
-	__u64 :64;
-	__u64 :64;
-	__u64 :64;
-	__u64 :64;
+	__u64 __opaque[4];
 } __attribute__((aligned(8)));
 
 struct bpf_refcount {
-	__u32 :32;
+	__u32 __opaque[1];
 } __attribute__((aligned(4)));
 
 struct bpf_sysctl {
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 0f6cdf52b1da..095ca7238ac2 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -7151,40 +7151,31 @@ struct bpf_spin_lock {
 };
 
 struct bpf_timer {
-	__u64 :64;
-	__u64 :64;
+	__u64 __opaque[2];
 } __attribute__((aligned(8)));
 
 struct bpf_dynptr {
-	__u64 :64;
-	__u64 :64;
+	__u64 __opaque[2];
 } __attribute__((aligned(8)));
 
 struct bpf_list_head {
-	__u64 :64;
-	__u64 :64;
+	__u64 __opaque[2];
 } __attribute__((aligned(8)));
 
 struct bpf_list_node {
-	__u64 :64;
-	__u64 :64;
-	__u64 :64;
+	__u64 __opaque[3];
 } __attribute__((aligned(8)));
 
 struct bpf_rb_root {
-	__u64 :64;
-	__u64 :64;
+	__u64 __opaque[2];
 } __attribute__((aligned(8)));
 
 struct bpf_rb_node {
-	__u64 :64;
-	__u64 :64;
-	__u64 :64;
-	__u64 :64;
+	__u64 __opaque[4];
 } __attribute__((aligned(8)));
 
 struct bpf_refcount {
-	__u32 :32;
+	__u32 __opaque[1];
 } __attribute__((aligned(4)));
 
 struct bpf_sysctl {
-- 
cgit v1.2.3


From 689b097a06bafb461ec162fc3b3ecc9765cea67b Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Mon, 6 Nov 2023 03:18:02 +0000
Subject: compiler-gcc: Suppress -Wmissing-prototypes warning for all supported
 GCC

The kernel supports a minimum GCC version of 5.1.0 for building. However,
the "__diag_ignore_all" directive only suppresses the
"-Wmissing-prototypes" warning for GCC versions >= 8.0.0. As a result, when
building the kernel with older GCC versions, warnings may be triggered. The
example below illustrates the warnings reported by the kernel test robot
using GCC 7.5.0:

  compiler: gcc-7 (Ubuntu 7.5.0-6ubuntu2) 7.5.0
  All warnings (new ones prefixed by >>):

   kernel/bpf/helpers.c:1893:19: warning: no previous prototype for 'bpf_obj_new_impl' [-Wmissing-prototypes]
    __bpf_kfunc void *bpf_obj_new_impl(u64 local_type_id__k, void *meta__ign)
                      ^~~~~~~~~~~~~~~~
   kernel/bpf/helpers.c:1907:19: warning: no previous prototype for 'bpf_percpu_obj_new_impl' [-Wmissing-prototypes]
    __bpf_kfunc void *bpf_percpu_obj_new_impl(u64 local_type_id__k, void *meta__ign)
   [...]

To address this, we should also suppress the "-Wmissing-prototypes" warning
for older GCC versions. "#pragma GCC diagnostic push" is supported as
of GCC 4.6, and both "-Wmissing-prototypes" and "-Wmissing-declarations"
are supported for all the GCC versions that we currently support.
Therefore, it is reasonable to suppress these warnings for all supported
GCC versions.

With this adjustment, it's important to note that after implementing
"__diag_ignore_all", it will effectively suppress warnings for all the
supported GCC versions.

In the future, if you wish to suppress warnings that are only supported on
higher GCC versions, it is advisable to explicitly use "__diag_ignore" to
specify the GCC version you are targeting.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202311031651.A7crZEur-lkp@intel.com/
Suggested-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Cc: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20231106031802.4188-1-laoar.shao@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/compiler-gcc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index 2ceba3fe4ec1..aebb65bf95a7 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -136,7 +136,7 @@
 #endif
 
 #define __diag_ignore_all(option, comment) \
-	__diag_GCC(8, ignore, option)
+	__diag(__diag_GCC_ignore option)
 
 /*
  * Prior to 9.1, -Wno-alloc-size-larger-than (and therefore the "alloc_size"
-- 
cgit v1.2.3


From b8e3a87a627b575896e448021e5c2f8a3bc19931 Mon Sep 17 00:00:00 2001
From: Jordan Rome <jordalgo@meta.com>
Date: Wed, 8 Nov 2023 03:23:34 -0800
Subject: bpf: Add crosstask check to __bpf_get_stack

Currently get_perf_callchain only supports user stack walking for
the current task. Passing the correct *crosstask* param will return
0 frames if the task passed to __bpf_get_stack isn't the current
one instead of a single incorrect frame/address. This change
passes the correct *crosstask* param but also does a preemptive
check in __bpf_get_stack if the task is current and returns
-EOPNOTSUPP if it is not.

This issue was found using bpf_get_task_stack inside a BPF
iterator ("iter/task"), which iterates over all tasks.
bpf_get_task_stack works fine for fetching kernel stacks
but because get_perf_callchain relies on the caller to know
if the requested *task* is the current one (via *crosstask*)
it was failing in a confusing way.

It might be possible to get user stacks for all tasks utilizing
something like access_process_vm but that requires the bpf
program calling bpf_get_task_stack to be sleepable and would
therefore be a breaking change.

Fixes: fa28dcb82a38 ("bpf: Introduce helper bpf_get_task_stack()")
Signed-off-by: Jordan Rome <jordalgo@meta.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20231108112334.3433136-1-jordalgo@meta.com
---
 include/uapi/linux/bpf.h       |  3 +++
 kernel/bpf/stackmap.c          | 11 ++++++++++-
 tools/include/uapi/linux/bpf.h |  3 +++
 3 files changed, 16 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 095ca7238ac2..7cf8bcf9f6a2 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -4517,6 +4517,8 @@ union bpf_attr {
  * long bpf_get_task_stack(struct task_struct *task, void *buf, u32 size, u64 flags)
  *	Description
  *		Return a user or a kernel stack in bpf program provided buffer.
+ *		Note: the user stack will only be populated if the *task* is
+ *		the current task; all other tasks will return -EOPNOTSUPP.
  *		To achieve this, the helper needs *task*, which is a valid
  *		pointer to **struct task_struct**. To store the stacktrace, the
  *		bpf program provides *buf* with a nonnegative *size*.
@@ -4528,6 +4530,7 @@ union bpf_attr {
  *
  *		**BPF_F_USER_STACK**
  *			Collect a user space stack instead of a kernel stack.
+ *			The *task* must be the current task.
  *		**BPF_F_USER_BUILD_ID**
  *			Collect buildid+offset instead of ips for user stack,
  *			only valid if **BPF_F_USER_STACK** is also specified.
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index d6b277482085..dff7ba539701 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -388,6 +388,7 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
 {
 	u32 trace_nr, copy_len, elem_size, num_elem, max_depth;
 	bool user_build_id = flags & BPF_F_USER_BUILD_ID;
+	bool crosstask = task && task != current;
 	u32 skip = flags & BPF_F_SKIP_FIELD_MASK;
 	bool user = flags & BPF_F_USER_STACK;
 	struct perf_callchain_entry *trace;
@@ -410,6 +411,14 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
 	if (task && user && !user_mode(regs))
 		goto err_fault;
 
+	/* get_perf_callchain does not support crosstask user stack walking
+	 * but returns an empty stack instead of NULL.
+	 */
+	if (crosstask && user) {
+		err = -EOPNOTSUPP;
+		goto clear;
+	}
+
 	num_elem = size / elem_size;
 	max_depth = num_elem + skip;
 	if (sysctl_perf_event_max_stack < max_depth)
@@ -421,7 +430,7 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
 		trace = get_callchain_entry_for_task(task, max_depth);
 	else
 		trace = get_perf_callchain(regs, 0, kernel, user, max_depth,
-					   false, false);
+					   crosstask, false);
 	if (unlikely(!trace))
 		goto err_fault;
 
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 095ca7238ac2..7cf8bcf9f6a2 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4517,6 +4517,8 @@ union bpf_attr {
  * long bpf_get_task_stack(struct task_struct *task, void *buf, u32 size, u64 flags)
  *	Description
  *		Return a user or a kernel stack in bpf program provided buffer.
+ *		Note: the user stack will only be populated if the *task* is
+ *		the current task; all other tasks will return -EOPNOTSUPP.
  *		To achieve this, the helper needs *task*, which is a valid
  *		pointer to **struct task_struct**. To store the stacktrace, the
  *		bpf program provides *buf* with a nonnegative *size*.
@@ -4528,6 +4530,7 @@ union bpf_attr {
  *
  *		**BPF_F_USER_STACK**
  *			Collect a user space stack instead of a kernel stack.
+ *			The *task* must be the current task.
  *		**BPF_F_USER_BUILD_ID**
  *			Collect buildid+offset instead of ips for user stack,
  *			only valid if **BPF_F_USER_STACK** is also specified.
-- 
cgit v1.2.3


From fe28f631fa941fba583d1c4f25895284b90af671 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Wed, 25 Oct 2023 14:25:52 -0400
Subject: workqueue: Add workqueue_unbound_exclude_cpumask() to exclude CPUs
 from wq_unbound_cpumask

When the "isolcpus" boot command line option is used to add a set
of isolated CPUs, those CPUs will be excluded automatically from
wq_unbound_cpumask to avoid running work functions from unbound
workqueues.

Recently cpuset has been extended to allow the creation of partitions
of isolated CPUs dynamically. To make it closer to the "isolcpus"
in functionality, the CPUs in those isolated cpuset partitions should be
excluded from wq_unbound_cpumask as well. This can be done currently by
explicitly writing to the workqueue's cpumask sysfs file after creating
the isolated partitions. However, this process can be error prone.

Ideally, the cpuset code should be allowed to request the workqueue code
to exclude those isolated CPUs from wq_unbound_cpumask so that this
operation can be done automatically and the isolated CPUs will be returned
back to wq_unbound_cpumask after the destructions of the isolated
cpuset partitions.

This patch adds a new workqueue_unbound_exclude_cpumask() function to
enable that. This new function will exclude the specified isolated
CPUs from wq_unbound_cpumask. To be able to restore those isolated
CPUs back after the destruction of isolated cpuset partitions, a new
wq_requested_unbound_cpumask is added to store the user provided unbound
cpumask either from the boot command line options or from writing to
the cpumask sysfs file. This new cpumask provides the basis for CPU
exclusion.

To enable users to understand how the wq_unbound_cpumask is being
modified internally, this patch also exposes the newly introduced
wq_requested_unbound_cpumask as well as a wq_isolated_cpumask to
store the cpumask to be excluded from wq_unbound_cpumask as read-only
sysfs files.

Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/workqueue.h |  2 +-
 kernel/workqueue.c        | 91 ++++++++++++++++++++++++++++++++++++++++++-----
 2 files changed, 84 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 24b1e5070f4d..b0b9604b76b8 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -491,7 +491,7 @@ struct workqueue_attrs *alloc_workqueue_attrs(void);
 void free_workqueue_attrs(struct workqueue_attrs *attrs);
 int apply_workqueue_attrs(struct workqueue_struct *wq,
 			  const struct workqueue_attrs *attrs);
-int workqueue_set_unbound_cpumask(cpumask_var_t cpumask);
+extern int workqueue_unbound_exclude_cpumask(cpumask_var_t cpumask);
 
 extern bool queue_work_on(int cpu, struct workqueue_struct *wq,
 			struct work_struct *work);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 6e578f576a6f..bd9d34eacd78 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -381,6 +381,12 @@ static bool workqueue_freezing;		/* PL: have wqs started freezing? */
 /* PL&A: allowable cpus for unbound wqs and work items */
 static cpumask_var_t wq_unbound_cpumask;
 
+/* PL: user requested unbound cpumask via sysfs */
+static cpumask_var_t wq_requested_unbound_cpumask;
+
+/* PL: isolated cpumask to be excluded from unbound cpumask */
+static cpumask_var_t wq_isolated_cpumask;
+
 /* for further constrain wq_unbound_cpumask by cmdline parameter*/
 static struct cpumask wq_cmdline_cpumask __initdata;
 
@@ -5839,7 +5845,7 @@ static int workqueue_apply_unbound_cpumask(const cpumask_var_t unbound_cpumask)
  *  		-EINVAL	- Invalid @cpumask
  *  		-ENOMEM	- Failed to allocate memory for attrs or pwqs.
  */
-int workqueue_set_unbound_cpumask(cpumask_var_t cpumask)
+static int workqueue_set_unbound_cpumask(cpumask_var_t cpumask)
 {
 	int ret = -EINVAL;
 
@@ -5850,6 +5856,7 @@ int workqueue_set_unbound_cpumask(cpumask_var_t cpumask)
 	cpumask_and(cpumask, cpumask, cpu_possible_mask);
 	if (!cpumask_empty(cpumask)) {
 		apply_wqattrs_lock();
+		cpumask_copy(wq_requested_unbound_cpumask, cpumask);
 		if (cpumask_equal(cpumask, wq_unbound_cpumask)) {
 			ret = 0;
 			goto out_unlock;
@@ -5864,6 +5871,44 @@ out_unlock:
 	return ret;
 }
 
+/**
+ * workqueue_unbound_exclude_cpumask - Exclude given CPUs from unbound cpumask
+ * @exclude_cpumask: the cpumask to be excluded from wq_unbound_cpumask
+ *
+ * This function can be called from cpuset code to provide a set of isolated
+ * CPUs that should be excluded from wq_unbound_cpumask. The caller must hold
+ * either cpus_read_lock or cpus_write_lock.
+ */
+int workqueue_unbound_exclude_cpumask(cpumask_var_t exclude_cpumask)
+{
+	cpumask_var_t cpumask;
+	int ret = 0;
+
+	if (!zalloc_cpumask_var(&cpumask, GFP_KERNEL))
+		return -ENOMEM;
+
+	lockdep_assert_cpus_held();
+	mutex_lock(&wq_pool_mutex);
+
+	/* Save the current isolated cpumask & export it via sysfs */
+	cpumask_copy(wq_isolated_cpumask, exclude_cpumask);
+
+	/*
+	 * If the operation fails, it will fall back to
+	 * wq_requested_unbound_cpumask which is initially set to
+	 * (HK_TYPE_WQ ∩ HK_TYPE_DOMAIN) house keeping mask and rewritten
+	 * by any subsequent write to workqueue/cpumask sysfs file.
+	 */
+	if (!cpumask_andnot(cpumask, wq_requested_unbound_cpumask, exclude_cpumask))
+		cpumask_copy(cpumask, wq_requested_unbound_cpumask);
+	if (!cpumask_equal(cpumask, wq_unbound_cpumask))
+		ret = workqueue_apply_unbound_cpumask(cpumask);
+
+	mutex_unlock(&wq_pool_mutex);
+	free_cpumask_var(cpumask);
+	return ret;
+}
+
 static int parse_affn_scope(const char *val)
 {
 	int i;
@@ -6158,19 +6203,36 @@ static struct bus_type wq_subsys = {
 	.dev_groups			= wq_sysfs_groups,
 };
 
-static ssize_t wq_unbound_cpumask_show(struct device *dev,
-		struct device_attribute *attr, char *buf)
+static ssize_t __wq_cpumask_show(struct device *dev,
+		struct device_attribute *attr, char *buf, cpumask_var_t mask)
 {
 	int written;
 
 	mutex_lock(&wq_pool_mutex);
-	written = scnprintf(buf, PAGE_SIZE, "%*pb\n",
-			    cpumask_pr_args(wq_unbound_cpumask));
+	written = scnprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(mask));
 	mutex_unlock(&wq_pool_mutex);
 
 	return written;
 }
 
+static ssize_t wq_unbound_cpumask_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	return __wq_cpumask_show(dev, attr, buf, wq_unbound_cpumask);
+}
+
+static ssize_t wq_requested_cpumask_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	return __wq_cpumask_show(dev, attr, buf, wq_requested_unbound_cpumask);
+}
+
+static ssize_t wq_isolated_cpumask_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	return __wq_cpumask_show(dev, attr, buf, wq_isolated_cpumask);
+}
+
 static ssize_t wq_unbound_cpumask_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t count)
 {
@@ -6188,9 +6250,13 @@ static ssize_t wq_unbound_cpumask_store(struct device *dev,
 	return ret ? ret : count;
 }
 
-static struct device_attribute wq_sysfs_cpumask_attr =
+static struct device_attribute wq_sysfs_cpumask_attrs[] = {
 	__ATTR(cpumask, 0644, wq_unbound_cpumask_show,
-	       wq_unbound_cpumask_store);
+	       wq_unbound_cpumask_store),
+	__ATTR(cpumask_requested, 0444, wq_requested_cpumask_show, NULL),
+	__ATTR(cpumask_isolated, 0444, wq_isolated_cpumask_show, NULL),
+	__ATTR_NULL,
+};
 
 static int __init wq_sysfs_init(void)
 {
@@ -6203,7 +6269,13 @@ static int __init wq_sysfs_init(void)
 
 	dev_root = bus_get_dev_root(&wq_subsys);
 	if (dev_root) {
-		err = device_create_file(dev_root, &wq_sysfs_cpumask_attr);
+		struct device_attribute *attr;
+
+		for (attr = wq_sysfs_cpumask_attrs; attr->attr.name; attr++) {
+			err = device_create_file(dev_root, attr);
+			if (err)
+				break;
+		}
 		put_device(dev_root);
 	}
 	return err;
@@ -6534,11 +6606,14 @@ void __init workqueue_init_early(void)
 	BUILD_BUG_ON(__alignof__(struct pool_workqueue) < __alignof__(long long));
 
 	BUG_ON(!alloc_cpumask_var(&wq_unbound_cpumask, GFP_KERNEL));
+	BUG_ON(!alloc_cpumask_var(&wq_requested_unbound_cpumask, GFP_KERNEL));
+	BUG_ON(!zalloc_cpumask_var(&wq_isolated_cpumask, GFP_KERNEL));
 	cpumask_copy(wq_unbound_cpumask, housekeeping_cpumask(HK_TYPE_WQ));
 	cpumask_and(wq_unbound_cpumask, wq_unbound_cpumask, housekeeping_cpumask(HK_TYPE_DOMAIN));
 
 	if (!cpumask_empty(&wq_cmdline_cpumask))
 		cpumask_and(wq_unbound_cpumask, wq_unbound_cpumask, &wq_cmdline_cpumask);
+	cpumask_copy(wq_requested_unbound_cpumask, wq_unbound_cpumask);
 
 	pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC);
 
-- 
cgit v1.2.3


From e76d28bdf9ba5388b8c4835a5199dc427b603188 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Fri, 3 Nov 2023 23:13:01 -0400
Subject: cgroup/rstat: Reduce cpu_lock hold time in
 cgroup_rstat_flush_locked()

When cgroup_rstat_updated() isn't being called concurrently with
cgroup_rstat_flush_locked(), its run time is pretty short. When
both are called concurrently, the cgroup_rstat_updated() run time
can spike to a pretty high value due to high cpu_lock hold time in
cgroup_rstat_flush_locked(). This can be problematic if the task calling
cgroup_rstat_updated() is a realtime task running on an isolated CPU
with a strict latency requirement. The cgroup_rstat_updated() call can
happen when there is a page fault even though the task is running in
user space most of the time.

The percpu cpu_lock is used to protect the update tree -
updated_next and updated_children. This protection is only needed when
cgroup_rstat_cpu_pop_updated() is being called. The subsequent flushing
operation which can take a much longer time does not need that protection
as it is already protected by cgroup_rstat_lock.

To reduce the cpu_lock hold time, we need to perform all the
cgroup_rstat_cpu_pop_updated() calls up front with the lock
released afterward before doing any flushing. This patch adds a new
cgroup_rstat_updated_list() function to return a singly linked list of
cgroups to be flushed.

Some instrumentation code are added to measure the cpu_lock hold time
right after lock acquisition to after releasing the lock. Parallel
kernel build on a 2-socket x86-64 server is used as the benchmarking
tool for measuring the lock hold time.

The maximum cpu_lock hold time before and after the patch are 100us and
29us respectively. So the worst case time is reduced to about 30% of
the original. However, there may be some OS or hardware noises like NMI
or SMI in the test system that can worsen the worst case value. Those
noises are usually tuned out in a real production environment to get
a better result.

OTOH, the lock hold time frequency distribution should give a better
idea of the performance benefit of the patch.  Below were the frequency
distribution before and after the patch:

     Hold time        Before patch       After patch
     ---------        ------------       -----------
       0-01 us           804,139         13,738,708
      01-05 us         9,772,767          1,177,194
      05-10 us         4,595,028              4,984
      10-15 us           303,481              3,562
      15-20 us            78,971              1,314
      20-25 us            24,583                 18
      25-30 us             6,908                 12
      30-40 us             8,015
      40-50 us             2,192
      50-60 us               316
      60-70 us                43
      70-80 us                 7
      80-90 us                 2
        >90 us                 3

Signed-off-by: Waiman Long <longman@redhat.com>
Reviewed-by: Yosry Ahmed <yosryahmed@google.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/cgroup-defs.h |  7 +++++++
 kernel/cgroup/rstat.c       | 43 ++++++++++++++++++++++++++++---------------
 2 files changed, 35 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 4caab0c6b361..37518436cfe7 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -496,6 +496,13 @@ struct cgroup {
 	struct cgroup_rstat_cpu __percpu *rstat_cpu;
 	struct list_head rstat_css_list;
 
+	/*
+	 * A singly-linked list of cgroup structures to be rstat flushed.
+	 * This is a scratch field to be used exclusively by
+	 * cgroup_rstat_flush_locked() and protected by cgroup_rstat_lock.
+	 */
+	struct cgroup	*rstat_flush_next;
+
 	/* cgroup basic resource statistics */
 	struct cgroup_base_stat last_bstat;
 	struct cgroup_base_stat bstat;
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index d80d7a608141..1f300bf4dc40 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -145,6 +145,32 @@ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos,
 	return pos;
 }
 
+/* Return a list of updated cgroups to be flushed */
+static struct cgroup *cgroup_rstat_updated_list(struct cgroup *root, int cpu)
+{
+	raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu);
+	struct cgroup *head, *tail, *next;
+	unsigned long flags;
+
+	/*
+	 * The _irqsave() is needed because cgroup_rstat_lock is
+	 * spinlock_t which is a sleeping lock on PREEMPT_RT. Acquiring
+	 * this lock with the _irq() suffix only disables interrupts on
+	 * a non-PREEMPT_RT kernel. The raw_spinlock_t below disables
+	 * interrupts on both configurations. The _irqsave() ensures
+	 * that interrupts are always disabled and later restored.
+	 */
+	raw_spin_lock_irqsave(cpu_lock, flags);
+	head = tail = cgroup_rstat_cpu_pop_updated(NULL, root, cpu);
+	while (tail) {
+		next = cgroup_rstat_cpu_pop_updated(tail, root, cpu);
+		tail->rstat_flush_next = next;
+		tail = next;
+	}
+	raw_spin_unlock_irqrestore(cpu_lock, flags);
+	return head;
+}
+
 /*
  * A hook for bpf stat collectors to attach to and flush their stats.
  * Together with providing bpf kfuncs for cgroup_rstat_updated() and
@@ -179,21 +205,9 @@ static void cgroup_rstat_flush_locked(struct cgroup *cgrp)
 	lockdep_assert_held(&cgroup_rstat_lock);
 
 	for_each_possible_cpu(cpu) {
-		raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock,
-						       cpu);
-		struct cgroup *pos = NULL;
-		unsigned long flags;
+		struct cgroup *pos = cgroup_rstat_updated_list(cgrp, cpu);
 
-		/*
-		 * The _irqsave() is needed because cgroup_rstat_lock is
-		 * spinlock_t which is a sleeping lock on PREEMPT_RT. Acquiring
-		 * this lock with the _irq() suffix only disables interrupts on
-		 * a non-PREEMPT_RT kernel. The raw_spinlock_t below disables
-		 * interrupts on both configurations. The _irqsave() ensures
-		 * that interrupts are always disabled and later restored.
-		 */
-		raw_spin_lock_irqsave(cpu_lock, flags);
-		while ((pos = cgroup_rstat_cpu_pop_updated(pos, cgrp, cpu))) {
+		for (; pos; pos = pos->rstat_flush_next) {
 			struct cgroup_subsys_state *css;
 
 			cgroup_base_stat_flush(pos, cpu);
@@ -205,7 +219,6 @@ static void cgroup_rstat_flush_locked(struct cgroup *cgrp)
 				css->ss->css_rstat_flush(css, cpu);
 			rcu_read_unlock();
 		}
-		raw_spin_unlock_irqrestore(cpu_lock, flags);
 
 		/* play nice and yield if necessary */
 		if (need_resched() || spin_needbreak(&cgroup_rstat_lock)) {
-- 
cgit v1.2.3


From 89ef42088b3ba884a007ad10bd89ce8a81b9dedd Mon Sep 17 00:00:00 2001
From: Daniel Baluta <daniel.baluta@nxp.com>
Date: Thu, 9 Nov 2023 15:59:00 +0200
Subject: ASoC: SOF: Add support for configuring PDM interface from topology
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently we only support configuration for number of channels and
sample rate.

Reviewed-by: Péter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Iuliana Prodan <iuliana.prodan@nxp.com>
Signed-off-by: Daniel Baluta <daniel.baluta@nxp.com>
Link: https://lore.kernel.org/r/20231109135900.88310-3-daniel.baluta@oss.nxp.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/sof/dai-imx.h     |  7 +++++++
 include/sound/sof/dai.h         |  2 ++
 include/uapi/sound/sof/tokens.h |  4 ++++
 sound/soc/sof/ipc3-pcm.c        | 11 ++++++++++
 sound/soc/sof/ipc3-topology.c   | 46 +++++++++++++++++++++++++++++++++++++++++
 sound/soc/sof/sof-audio.h       |  1 +
 sound/soc/sof/topology.c        |  5 +++++
 7 files changed, 76 insertions(+)

(limited to 'include')

diff --git a/include/sound/sof/dai-imx.h b/include/sound/sof/dai-imx.h
index ca8325353d41..6bc987bd4761 100644
--- a/include/sound/sof/dai-imx.h
+++ b/include/sound/sof/dai-imx.h
@@ -51,4 +51,11 @@ struct sof_ipc_dai_sai_params {
 	uint16_t tdm_slot_width;
 	uint16_t reserved2;	/* alignment */
 } __packed;
+
+/* MICFIL Configuration Request - SOF_IPC_DAI_MICFIL_CONFIG */
+struct sof_ipc_dai_micfil_params {
+	uint32_t pdm_rate;
+	uint32_t pdm_ch;
+} __packed;
+
 #endif
diff --git a/include/sound/sof/dai.h b/include/sound/sof/dai.h
index 3041f5805b7b..4773a5f616a4 100644
--- a/include/sound/sof/dai.h
+++ b/include/sound/sof/dai.h
@@ -88,6 +88,7 @@ enum sof_ipc_dai_type {
 	SOF_DAI_AMD_HS,			/**< Amd HS */
 	SOF_DAI_AMD_SP_VIRTUAL,		/**< AMD ACP SP VIRTUAL */
 	SOF_DAI_AMD_HS_VIRTUAL,		/**< AMD ACP HS VIRTUAL */
+	SOF_DAI_IMX_MICFIL,		/** < i.MX MICFIL PDM */
 };
 
 /* general purpose DAI configuration */
@@ -117,6 +118,7 @@ struct sof_ipc_dai_config {
 		struct sof_ipc_dai_acpdmic_params acpdmic;
 		struct sof_ipc_dai_acp_params acphs;
 		struct sof_ipc_dai_mtk_afe_params afe;
+		struct sof_ipc_dai_micfil_params micfil;
 	};
 } __packed;
 
diff --git a/include/uapi/sound/sof/tokens.h b/include/uapi/sound/sof/tokens.h
index 453cab2a1209..0fb39780f9bd 100644
--- a/include/uapi/sound/sof/tokens.h
+++ b/include/uapi/sound/sof/tokens.h
@@ -213,4 +213,8 @@
 #define SOF_TKN_AMD_ACPI2S_CH			1701
 #define SOF_TKN_AMD_ACPI2S_TDM_MODE		1702
 
+/* MICFIL PDM */
+#define SOF_TKN_IMX_MICFIL_RATE			2000
+#define SOF_TKN_IMX_MICFIL_CH			2001
+
 #endif
diff --git a/sound/soc/sof/ipc3-pcm.c b/sound/soc/sof/ipc3-pcm.c
index 2d0addcbc819..330f04bcd75d 100644
--- a/sound/soc/sof/ipc3-pcm.c
+++ b/sound/soc/sof/ipc3-pcm.c
@@ -384,6 +384,17 @@ static int sof_ipc3_pcm_dai_link_fixup(struct snd_soc_pcm_runtime *rtd,
 		dev_dbg(component->dev, "AMD_DMIC channels_min: %d channels_max: %d\n",
 			channels->min, channels->max);
 		break;
+	case SOF_DAI_IMX_MICFIL:
+		rate->min = private->dai_config->micfil.pdm_rate;
+		rate->max = private->dai_config->micfil.pdm_rate;
+		channels->min = private->dai_config->micfil.pdm_ch;
+		channels->max = private->dai_config->micfil.pdm_ch;
+
+		dev_dbg(component->dev,
+			"MICFIL PDM rate_min: %d rate_max: %d\n", rate->min, rate->max);
+		dev_dbg(component->dev, "MICFIL PDM channels_min: %d channels_max: %d\n",
+			channels->min, channels->max);
+		break;
 	default:
 		dev_err(component->dev, "Invalid DAI type %d\n", private->dai_config->type);
 		break;
diff --git a/sound/soc/sof/ipc3-topology.c b/sound/soc/sof/ipc3-topology.c
index ba4ef290b634..7a4932c152a9 100644
--- a/sound/soc/sof/ipc3-topology.c
+++ b/sound/soc/sof/ipc3-topology.c
@@ -286,6 +286,16 @@ static const struct sof_topology_token acpi2s_tokens[] = {
 		offsetof(struct sof_ipc_dai_acp_params, tdm_mode)},
 };
 
+/* MICFIL PDM */
+static const struct sof_topology_token micfil_pdm_tokens[] = {
+	{SOF_TKN_IMX_MICFIL_RATE,
+		SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32,
+		offsetof(struct sof_ipc_dai_micfil_params, pdm_rate)},
+	{SOF_TKN_IMX_MICFIL_CH,
+		SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32,
+		offsetof(struct sof_ipc_dai_micfil_params, pdm_ch)},
+};
+
 /* Core tokens */
 static const struct sof_topology_token core_tokens[] = {
 	{SOF_TKN_COMP_CORE_ID, SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32,
@@ -322,6 +332,8 @@ static const struct sof_token_info ipc3_token_list[SOF_TOKEN_COUNT] = {
 	[SOF_AFE_TOKENS] = {"AFE tokens", afe_tokens, ARRAY_SIZE(afe_tokens)},
 	[SOF_ACPDMIC_TOKENS] = {"ACPDMIC tokens", acpdmic_tokens, ARRAY_SIZE(acpdmic_tokens)},
 	[SOF_ACPI2S_TOKENS]   = {"ACPI2S tokens", acpi2s_tokens, ARRAY_SIZE(acpi2s_tokens)},
+	[SOF_MICFIL_TOKENS] = {"MICFIL PDM tokens",
+		micfil_pdm_tokens, ARRAY_SIZE(micfil_pdm_tokens)},
 };
 
 /**
@@ -1136,6 +1148,37 @@ static int sof_link_esai_load(struct snd_soc_component *scomp, struct snd_sof_da
 	return 0;
 }
 
+static int sof_link_micfil_load(struct snd_soc_component *scomp, struct snd_sof_dai_link *slink,
+				struct sof_ipc_dai_config *config, struct snd_sof_dai *dai)
+{
+	struct snd_soc_tplg_hw_config *hw_config = slink->hw_configs;
+	struct sof_dai_private_data *private = dai->private;
+	u32 size = sizeof(*config);
+	int ret;
+
+       /* handle master/slave and inverted clocks */
+	sof_dai_set_format(hw_config, config);
+
+	config->hdr.size = size;
+
+	/* parse the required set of MICFIL PDM tokens based on num_hw_cfgs */
+	ret = sof_update_ipc_object(scomp, &config->micfil, SOF_MICFIL_TOKENS, slink->tuples,
+				    slink->num_tuples, size, slink->num_hw_configs);
+	if (ret < 0)
+		return ret;
+
+	dev_info(scomp->dev, "MICFIL PDM config dai_index %d channel %d rate %d\n",
+		 config->dai_index, config->micfil.pdm_ch, config->micfil.pdm_rate);
+
+	dai->number_configs = 1;
+	dai->current_config = 0;
+	private->dai_config = kmemdup(config, size, GFP_KERNEL);
+	if (!private->dai_config)
+		return -ENOMEM;
+
+	return 0;
+}
+
 static int sof_link_acp_dmic_load(struct snd_soc_component *scomp, struct snd_sof_dai_link *slink,
 				  struct sof_ipc_dai_config *config, struct snd_sof_dai *dai)
 {
@@ -1559,6 +1602,9 @@ static int sof_ipc3_widget_setup_comp_dai(struct snd_sof_widget *swidget)
 		case SOF_DAI_IMX_ESAI:
 			ret = sof_link_esai_load(scomp, slink, config, dai);
 			break;
+		case SOF_DAI_IMX_MICFIL:
+			ret = sof_link_micfil_load(scomp, slink, config, dai);
+			break;
 		case SOF_DAI_AMD_BT:
 			ret = sof_link_acp_bt_load(scomp, slink, config, dai);
 			break;
diff --git a/sound/soc/sof/sof-audio.h b/sound/soc/sof/sof-audio.h
index 5d5eeb1a1a6f..99c940b22538 100644
--- a/sound/soc/sof/sof-audio.h
+++ b/sound/soc/sof/sof-audio.h
@@ -275,6 +275,7 @@ enum sof_tokens {
 	SOF_GAIN_TOKENS,
 	SOF_ACPDMIC_TOKENS,
 	SOF_ACPI2S_TOKENS,
+	SOF_MICFIL_TOKENS,
 
 	/* this should be the last */
 	SOF_TOKEN_COUNT,
diff --git a/sound/soc/sof/topology.c b/sound/soc/sof/topology.c
index a3a3af252259..9f717366cddc 100644
--- a/sound/soc/sof/topology.c
+++ b/sound/soc/sof/topology.c
@@ -296,6 +296,7 @@ static const struct sof_dai_types sof_dais[] = {
 	{"AFE", SOF_DAI_MEDIATEK_AFE},
 	{"ACPSP_VIRTUAL", SOF_DAI_AMD_SP_VIRTUAL},
 	{"ACPHS_VIRTUAL", SOF_DAI_AMD_HS_VIRTUAL},
+	{"MICFIL", SOF_DAI_IMX_MICFIL},
 
 };
 
@@ -1960,6 +1961,10 @@ static int sof_link_load(struct snd_soc_component *scomp, int index, struct snd_
 		token_id = SOF_ACPI2S_TOKENS;
 		num_tuples += token_list[SOF_ACPI2S_TOKENS].count;
 		break;
+	case SOF_DAI_IMX_MICFIL:
+		token_id = SOF_MICFIL_TOKENS;
+		num_tuples += token_list[SOF_MICFIL_TOKENS].count;
+		break;
 	default:
 		break;
 	}
-- 
cgit v1.2.3


From 8156c7dd47b92fc4a70c9ea58e7a9e88c8bc32be Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Thu, 26 Oct 2023 16:48:21 +0200
Subject: regulator: Introduce handling for system-critical under-voltage
 events

Handle under-voltage events for crucial regulators to maintain system
stability and avoid issues during power drops.

Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://lore.kernel.org/r/20231026144824.4065145-3-o.rempel@pengutronix.de
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/core.c          | 38 ++++++++++++++++++++++++++++++++++++++
 drivers/regulator/of_regulator.c  |  2 ++
 include/linux/regulator/machine.h | 10 ++++++++++
 3 files changed, 50 insertions(+)

(limited to 'include')

diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 3137e40fcd3e..a072f721f288 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -19,6 +19,7 @@
 #include <linux/delay.h>
 #include <linux/gpio/consumer.h>
 #include <linux/of.h>
+#include <linux/reboot.h>
 #include <linux/regmap.h>
 #include <linux/regulator/of_regulator.h>
 #include <linux/regulator/consumer.h>
@@ -5061,6 +5062,41 @@ void regulator_bulk_free(int num_consumers,
 }
 EXPORT_SYMBOL_GPL(regulator_bulk_free);
 
+/**
+ * regulator_handle_critical - Handle events for system-critical regulators.
+ * @rdev: The regulator device.
+ * @event: The event being handled.
+ *
+ * This function handles critical events such as under-voltage, over-current,
+ * and unknown errors for regulators deemed system-critical. On detecting such
+ * events, it triggers a hardware protection shutdown with a defined timeout.
+ */
+static void regulator_handle_critical(struct regulator_dev *rdev,
+				      unsigned long event)
+{
+	const char *reason = NULL;
+
+	if (!rdev->constraints->system_critical)
+		return;
+
+	switch (event) {
+	case REGULATOR_EVENT_UNDER_VOLTAGE:
+		reason = "System critical regulator: voltage drop detected";
+		break;
+	case REGULATOR_EVENT_OVER_CURRENT:
+		reason = "System critical regulator: over-current detected";
+		break;
+	case REGULATOR_EVENT_FAIL:
+		reason = "System critical regulator: unknown error";
+	}
+
+	if (!reason)
+		return;
+
+	hw_protection_shutdown(reason,
+			       REGULATOR_DEF_UV_LESS_CRITICAL_WINDOW_MS);
+}
+
 /**
  * regulator_notifier_call_chain - call regulator event notifier
  * @rdev: regulator source
@@ -5073,6 +5109,8 @@ EXPORT_SYMBOL_GPL(regulator_bulk_free);
 int regulator_notifier_call_chain(struct regulator_dev *rdev,
 				  unsigned long event, void *data)
 {
+	regulator_handle_critical(rdev, event);
+
 	_notifier_call_chain(rdev, event, data);
 	return NOTIFY_DONE;
 
diff --git a/drivers/regulator/of_regulator.c b/drivers/regulator/of_regulator.c
index 1b65e5e4e40f..3bdd6f1919a4 100644
--- a/drivers/regulator/of_regulator.c
+++ b/drivers/regulator/of_regulator.c
@@ -131,6 +131,8 @@ static int of_get_regulation_constraints(struct device *dev,
 		constraints->valid_ops_mask |= REGULATOR_CHANGE_STATUS;
 
 	constraints->pull_down = of_property_read_bool(np, "regulator-pull-down");
+	constraints->system_critical = of_property_read_bool(np,
+						"system-critical-regulator");
 
 	if (of_property_read_bool(np, "regulator-allow-bypass"))
 		constraints->valid_ops_mask |= REGULATOR_CHANGE_BYPASS;
diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h
index 621b7f4a3639..e0ddfb5593c9 100644
--- a/include/linux/regulator/machine.h
+++ b/include/linux/regulator/machine.h
@@ -49,6 +49,13 @@ struct regulator;
 #define DISABLE_IN_SUSPEND	1
 #define ENABLE_IN_SUSPEND	2
 
+/*
+ * Default time window (in milliseconds) following a critical under-voltage
+ * event during which less critical actions can be safely carried out by the
+ * system.
+ */
+#define REGULATOR_DEF_UV_LESS_CRITICAL_WINDOW_MS	10
+
 /* Regulator active discharge flags */
 enum regulator_active_discharge {
 	REGULATOR_ACTIVE_DISCHARGE_DEFAULT,
@@ -127,6 +134,8 @@ struct notification_limit {
  * @ramp_disable: Disable ramp delay when initialising or when setting voltage.
  * @soft_start: Enable soft start so that voltage ramps slowly.
  * @pull_down: Enable pull down when regulator is disabled.
+ * @system_critical: Set if the regulator is critical to system stability or
+ *                   functionality.
  * @over_current_protection: Auto disable on over current event.
  *
  * @over_current_detection: Configure over current limits.
@@ -214,6 +223,7 @@ struct regulation_constraints {
 	unsigned ramp_disable:1; /* disable ramp delay */
 	unsigned soft_start:1;	/* ramp voltage slowly */
 	unsigned pull_down:1;	/* pull down resistor when regulator off */
+	unsigned system_critical:1;	/* critical to system stability */
 	unsigned over_current_protection:1; /* auto disable on over current */
 	unsigned over_current_detection:1; /* notify on over current */
 	unsigned over_voltage_detection:1; /* notify on over voltage */
-- 
cgit v1.2.3


From 1e22152aa59d793743fc53051dd7a042f362aecb Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Thu, 26 Oct 2023 16:48:24 +0200
Subject: regulator: Implement uv_survival_time for handling under-voltage
 events

Add 'uv_survival_time' field to regulation_constraints for specifying
survival time post critical under-voltage event. Update the regulator
notifier call chain and Device Tree property parsing to use this new
field, allowing a configurable timeout before emergency shutdown.

Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://lore.kernel.org/r/20231026144824.4065145-6-o.rempel@pengutronix.de
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/core.c          | 2 +-
 drivers/regulator/of_regulator.c  | 7 +++++++
 include/linux/regulator/machine.h | 8 ++++++++
 3 files changed, 16 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index a072f721f288..a6cb84af989e 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -5094,7 +5094,7 @@ static void regulator_handle_critical(struct regulator_dev *rdev,
 		return;
 
 	hw_protection_shutdown(reason,
-			       REGULATOR_DEF_UV_LESS_CRITICAL_WINDOW_MS);
+			       rdev->constraints->uv_less_critical_window_ms);
 }
 
 /**
diff --git a/drivers/regulator/of_regulator.c b/drivers/regulator/of_regulator.c
index 3bdd6f1919a4..03afc160fc72 100644
--- a/drivers/regulator/of_regulator.c
+++ b/drivers/regulator/of_regulator.c
@@ -175,6 +175,13 @@ static int of_get_regulation_constraints(struct device *dev,
 	if (!ret)
 		constraints->enable_time = pval;
 
+	ret = of_property_read_u32(np, "regulator-uv-survival-time-ms", &pval);
+	if (!ret)
+		constraints->uv_less_critical_window_ms = pval;
+	else
+		constraints->uv_less_critical_window_ms =
+				REGULATOR_DEF_UV_LESS_CRITICAL_WINDOW_MS;
+
 	constraints->soft_start = of_property_read_bool(np,
 					"regulator-soft-start");
 	ret = of_property_read_u32(np, "regulator-active-discharge", &pval);
diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h
index e0ddfb5593c9..0cd76d264727 100644
--- a/include/linux/regulator/machine.h
+++ b/include/linux/regulator/machine.h
@@ -162,6 +162,13 @@ struct notification_limit {
  *		      regulator_active_discharge values are used for
  *		      initialisation.
  * @enable_time: Turn-on time of the rails (unit: microseconds)
+ * @uv_less_critical_window_ms: Specifies the time window (in milliseconds)
+ *                              following a critical under-voltage (UV) event
+ *                              during which less critical actions can be
+ *                              safely carried out by the system (for example
+ *                              logging). After this time window more critical
+ *                              actions should be done (for example prevent
+ *                              HW damage).
  */
 struct regulation_constraints {
 
@@ -213,6 +220,7 @@ struct regulation_constraints {
 	unsigned int settling_time_up;
 	unsigned int settling_time_down;
 	unsigned int enable_time;
+	unsigned int uv_less_critical_window_ms;
 
 	unsigned int active_discharge;
 
-- 
cgit v1.2.3


From f3b8788cde61b02f1e6c202f8fac4360e6adbafc Mon Sep 17 00:00:00 2001
From: Casey Schaufler <casey@schaufler-ca.com>
Date: Tue, 12 Sep 2023 13:56:46 -0700
Subject: LSM: Identify modules by more than name

Create a struct lsm_id to contain identifying information about Linux
Security Modules (LSMs). At inception this contains the name of the
module and an identifier associated with the security module.  Change
the security_add_hooks() interface to use this structure.  Change the
individual modules to maintain their own struct lsm_id and pass it to
security_add_hooks().

The values are for LSM identifiers are defined in a new UAPI
header file linux/lsm.h. Each existing LSM has been updated to
include it's LSMID in the lsm_id.

The LSM ID values are sequential, with the oldest module
LSM_ID_CAPABILITY being the lowest value and the existing modules
numbered in the order they were included in the main line kernel.
This is an arbitrary convention for assigning the values, but
none better presents itself. The value 0 is defined as being invalid.
The values 1-99 are reserved for any special case uses which may
arise in the future. This may include attributes of the LSM
infrastructure itself, possibly related to namespacing or network
attribute management. A special range is identified for such attributes
to help reduce confusion for developers unfamiliar with LSMs.

LSM attribute values are defined for the attributes presented by
modules that are available today. As with the LSM IDs, The value 0
is defined as being invalid. The values 1-99 are reserved for any
special case uses which may arise in the future.

Cc: linux-security-module <linux-security-module@vger.kernel.org>
Signed-off-by: Casey Schaufler <casey@schaufler-ca.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Serge Hallyn <serge@hallyn.com>
Reviewed-by: Mickael Salaun <mic@digikod.net>
Reviewed-by: John Johansen <john.johansen@canonical.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Nacked-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
[PM: forward ported beyond v6.6 due merge window changes]
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 Documentation/userspace-api/index.rst |  1 +
 MAINTAINERS                           |  1 +
 include/linux/lsm_hooks.h             | 16 +++++++++--
 include/uapi/linux/lsm.h              | 54 +++++++++++++++++++++++++++++++++++
 security/apparmor/lsm.c               |  8 +++++-
 security/bpf/hooks.c                  |  9 +++++-
 security/commoncap.c                  |  8 +++++-
 security/landlock/cred.c              |  2 +-
 security/landlock/fs.c                |  2 +-
 security/landlock/net.c               |  2 +-
 security/landlock/ptrace.c            |  2 +-
 security/landlock/setup.c             |  6 ++++
 security/landlock/setup.h             |  1 +
 security/loadpin/loadpin.c            |  9 +++++-
 security/lockdown/lockdown.c          |  8 +++++-
 security/safesetid/lsm.c              |  9 +++++-
 security/security.c                   | 12 ++++----
 security/selinux/hooks.c              |  9 +++++-
 security/smack/smack_lsm.c            |  8 +++++-
 security/tomoyo/tomoyo.c              |  9 +++++-
 security/yama/yama_lsm.c              |  8 +++++-
 21 files changed, 162 insertions(+), 22 deletions(-)
 create mode 100644 include/uapi/linux/lsm.h

(limited to 'include')

diff --git a/Documentation/userspace-api/index.rst b/Documentation/userspace-api/index.rst
index 031df47a7c19..8be8b1979194 100644
--- a/Documentation/userspace-api/index.rst
+++ b/Documentation/userspace-api/index.rst
@@ -33,6 +33,7 @@ place where this information is gathered.
    sysfs-platform_profile
    vduse
    futex2
+   lsm
 
 .. only::  subproject and html
 
diff --git a/MAINTAINERS b/MAINTAINERS
index 97f51d5ec1cf..f1d41fd9159a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -19511,6 +19511,7 @@ L:	linux-security-module@vger.kernel.org (suggested Cc:)
 S:	Supported
 W:	http://kernsec.org/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/lsm.git
+F:	include/uapi/linux/lsm.h
 F:	security/
 X:	security/selinux/
 
diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index dcb5e5b5eb13..7f0adb33caaa 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -42,6 +42,18 @@ struct security_hook_heads {
 	#undef LSM_HOOK
 } __randomize_layout;
 
+/**
+ * struct lsm_id - Identify a Linux Security Module.
+ * @lsm: name of the LSM, must be approved by the LSM maintainers
+ * @id: LSM ID number from uapi/linux/lsm.h
+ *
+ * Contains the information that identifies the LSM.
+ */
+struct lsm_id {
+	const char	*name;
+	u64		id;
+};
+
 /*
  * Security module hook list structure.
  * For use with generic list macros for common operations.
@@ -50,7 +62,7 @@ struct security_hook_list {
 	struct hlist_node		list;
 	struct hlist_head		*head;
 	union security_list_options	hook;
-	const char			*lsm;
+	const struct lsm_id		*lsmid;
 } __randomize_layout;
 
 /*
@@ -104,7 +116,7 @@ extern struct security_hook_heads security_hook_heads;
 extern char *lsm_names;
 
 extern void security_add_hooks(struct security_hook_list *hooks, int count,
-				const char *lsm);
+			       const struct lsm_id *lsmid);
 
 #define LSM_FLAG_LEGACY_MAJOR	BIT(0)
 #define LSM_FLAG_EXCLUSIVE	BIT(1)
diff --git a/include/uapi/linux/lsm.h b/include/uapi/linux/lsm.h
new file mode 100644
index 000000000000..f27c9a9cc376
--- /dev/null
+++ b/include/uapi/linux/lsm.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Linux Security Modules (LSM) - User space API
+ *
+ * Copyright (C) 2022 Casey Schaufler <casey@schaufler-ca.com>
+ * Copyright (C) 2022 Intel Corporation
+ */
+
+#ifndef _UAPI_LINUX_LSM_H
+#define _UAPI_LINUX_LSM_H
+
+/*
+ * ID tokens to identify Linux Security Modules (LSMs)
+ *
+ * These token values are used to uniquely identify specific LSMs
+ * in the kernel as well as in the kernel's LSM userspace API.
+ *
+ * A value of zero/0 is considered undefined and should not be used
+ * outside the kernel. Values 1-99 are reserved for potential
+ * future use.
+ */
+#define LSM_ID_UNDEF		0
+#define LSM_ID_CAPABILITY	100
+#define LSM_ID_SELINUX		101
+#define LSM_ID_SMACK		102
+#define LSM_ID_TOMOYO		103
+#define LSM_ID_IMA		104
+#define LSM_ID_APPARMOR		105
+#define LSM_ID_YAMA		106
+#define LSM_ID_LOADPIN		107
+#define LSM_ID_SAFESETID	108
+#define LSM_ID_LOCKDOWN		109
+#define LSM_ID_BPF		110
+#define LSM_ID_LANDLOCK		111
+
+/*
+ * LSM_ATTR_XXX definitions identify different LSM attributes
+ * which are used in the kernel's LSM userspace API. Support
+ * for these attributes vary across the different LSMs. None
+ * are required.
+ *
+ * A value of zero/0 is considered undefined and should not be used
+ * outside the kernel. Values 1-99 are reserved for potential
+ * future use.
+ */
+#define LSM_ATTR_UNDEF		0
+#define LSM_ATTR_CURRENT	100
+#define LSM_ATTR_EXEC		101
+#define LSM_ATTR_FSCREATE	102
+#define LSM_ATTR_KEYCREATE	103
+#define LSM_ATTR_PREV		104
+#define LSM_ATTR_SOCKCREATE	105
+
+#endif /* _UAPI_LINUX_LSM_H */
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index 4981bdf02993..093da0a9dbd8 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -24,6 +24,7 @@
 #include <linux/zstd.h>
 #include <net/sock.h>
 #include <uapi/linux/mount.h>
+#include <uapi/linux/lsm.h>
 
 #include "include/apparmor.h"
 #include "include/apparmorfs.h"
@@ -1385,6 +1386,11 @@ struct lsm_blob_sizes apparmor_blob_sizes __ro_after_init = {
 	.lbs_task = sizeof(struct aa_task_ctx),
 };
 
+const struct lsm_id apparmor_lsmid = {
+	.name = "apparmor",
+	.id = LSM_ID_APPARMOR,
+};
+
 static struct security_hook_list apparmor_hooks[] __ro_after_init = {
 	LSM_HOOK_INIT(ptrace_access_check, apparmor_ptrace_access_check),
 	LSM_HOOK_INIT(ptrace_traceme, apparmor_ptrace_traceme),
@@ -2202,7 +2208,7 @@ static int __init apparmor_init(void)
 		goto buffers_out;
 	}
 	security_add_hooks(apparmor_hooks, ARRAY_SIZE(apparmor_hooks),
-				"apparmor");
+				&apparmor_lsmid);
 
 	/* Report that AppArmor successfully initialized */
 	apparmor_initialized = 1;
diff --git a/security/bpf/hooks.c b/security/bpf/hooks.c
index cfaf1d0e6a5f..91011e0c361a 100644
--- a/security/bpf/hooks.c
+++ b/security/bpf/hooks.c
@@ -5,6 +5,7 @@
  */
 #include <linux/lsm_hooks.h>
 #include <linux/bpf_lsm.h>
+#include <uapi/linux/lsm.h>
 
 static struct security_hook_list bpf_lsm_hooks[] __ro_after_init = {
 	#define LSM_HOOK(RET, DEFAULT, NAME, ...) \
@@ -15,9 +16,15 @@ static struct security_hook_list bpf_lsm_hooks[] __ro_after_init = {
 	LSM_HOOK_INIT(task_free, bpf_task_storage_free),
 };
 
+const struct lsm_id bpf_lsmid = {
+	.name = "bpf",
+	.id = LSM_ID_BPF,
+};
+
 static int __init bpf_lsm_init(void)
 {
-	security_add_hooks(bpf_lsm_hooks, ARRAY_SIZE(bpf_lsm_hooks), "bpf");
+	security_add_hooks(bpf_lsm_hooks, ARRAY_SIZE(bpf_lsm_hooks),
+			   &bpf_lsmid);
 	pr_info("LSM support for eBPF active\n");
 	return 0;
 }
diff --git a/security/commoncap.c b/security/commoncap.c
index 8e8c630ce204..a64c0c8592bb 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -25,6 +25,7 @@
 #include <linux/binfmts.h>
 #include <linux/personality.h>
 #include <linux/mnt_idmapping.h>
+#include <uapi/linux/lsm.h>
 
 /*
  * If a non-root user executes a setuid-root binary in
@@ -1440,6 +1441,11 @@ int cap_mmap_file(struct file *file, unsigned long reqprot,
 
 #ifdef CONFIG_SECURITY
 
+const struct lsm_id capability_lsmid = {
+	.name = "capability",
+	.id = LSM_ID_CAPABILITY,
+};
+
 static struct security_hook_list capability_hooks[] __ro_after_init = {
 	LSM_HOOK_INIT(capable, cap_capable),
 	LSM_HOOK_INIT(settime, cap_settime),
@@ -1464,7 +1470,7 @@ static struct security_hook_list capability_hooks[] __ro_after_init = {
 static int __init capability_init(void)
 {
 	security_add_hooks(capability_hooks, ARRAY_SIZE(capability_hooks),
-				"capability");
+			   &capability_lsmid);
 	return 0;
 }
 
diff --git a/security/landlock/cred.c b/security/landlock/cred.c
index 13dff2a31545..786af18c4a1c 100644
--- a/security/landlock/cred.c
+++ b/security/landlock/cred.c
@@ -42,5 +42,5 @@ static struct security_hook_list landlock_hooks[] __ro_after_init = {
 __init void landlock_add_cred_hooks(void)
 {
 	security_add_hooks(landlock_hooks, ARRAY_SIZE(landlock_hooks),
-			   LANDLOCK_NAME);
+			   &landlock_lsmid);
 }
diff --git a/security/landlock/fs.c b/security/landlock/fs.c
index bc7c126deea2..490655d09b43 100644
--- a/security/landlock/fs.c
+++ b/security/landlock/fs.c
@@ -1223,5 +1223,5 @@ static struct security_hook_list landlock_hooks[] __ro_after_init = {
 __init void landlock_add_fs_hooks(void)
 {
 	security_add_hooks(landlock_hooks, ARRAY_SIZE(landlock_hooks),
-			   LANDLOCK_NAME);
+			   &landlock_lsmid);
 }
diff --git a/security/landlock/net.c b/security/landlock/net.c
index aaa92c2b1f08..efa1b644a4af 100644
--- a/security/landlock/net.c
+++ b/security/landlock/net.c
@@ -196,5 +196,5 @@ static struct security_hook_list landlock_hooks[] __ro_after_init = {
 __init void landlock_add_net_hooks(void)
 {
 	security_add_hooks(landlock_hooks, ARRAY_SIZE(landlock_hooks),
-			   LANDLOCK_NAME);
+			   &landlock_lsmid);
 }
diff --git a/security/landlock/ptrace.c b/security/landlock/ptrace.c
index 8a06d6c492bf..2bfc533d36e4 100644
--- a/security/landlock/ptrace.c
+++ b/security/landlock/ptrace.c
@@ -116,5 +116,5 @@ static struct security_hook_list landlock_hooks[] __ro_after_init = {
 __init void landlock_add_ptrace_hooks(void)
 {
 	security_add_hooks(landlock_hooks, ARRAY_SIZE(landlock_hooks),
-			   LANDLOCK_NAME);
+			   &landlock_lsmid);
 }
diff --git a/security/landlock/setup.c b/security/landlock/setup.c
index 3e11d303542f..f6dd33143b7f 100644
--- a/security/landlock/setup.c
+++ b/security/landlock/setup.c
@@ -8,6 +8,7 @@
 
 #include <linux/init.h>
 #include <linux/lsm_hooks.h>
+#include <uapi/linux/lsm.h>
 
 #include "common.h"
 #include "cred.h"
@@ -25,6 +26,11 @@ struct lsm_blob_sizes landlock_blob_sizes __ro_after_init = {
 	.lbs_superblock = sizeof(struct landlock_superblock_security),
 };
 
+const struct lsm_id landlock_lsmid = {
+	.name = LANDLOCK_NAME,
+	.id = LSM_ID_LANDLOCK,
+};
+
 static int __init landlock_init(void)
 {
 	landlock_add_cred_hooks();
diff --git a/security/landlock/setup.h b/security/landlock/setup.h
index 1daffab1ab4b..c4252d46d49d 100644
--- a/security/landlock/setup.h
+++ b/security/landlock/setup.h
@@ -14,5 +14,6 @@
 extern bool landlock_initialized;
 
 extern struct lsm_blob_sizes landlock_blob_sizes;
+extern const struct lsm_id landlock_lsmid;
 
 #endif /* _SECURITY_LANDLOCK_SETUP_H */
diff --git a/security/loadpin/loadpin.c b/security/loadpin/loadpin.c
index a9d40456a064..d682a851de58 100644
--- a/security/loadpin/loadpin.c
+++ b/security/loadpin/loadpin.c
@@ -20,6 +20,7 @@
 #include <linux/string_helpers.h>
 #include <linux/dm-verity-loadpin.h>
 #include <uapi/linux/loadpin.h>
+#include <uapi/linux/lsm.h>
 
 #define VERITY_DIGEST_FILE_HEADER "# LOADPIN_TRUSTED_VERITY_ROOT_DIGESTS"
 
@@ -208,6 +209,11 @@ static int loadpin_load_data(enum kernel_load_data_id id, bool contents)
 	return loadpin_check(NULL, (enum kernel_read_file_id) id);
 }
 
+const struct lsm_id loadpin_lsmid = {
+	.name = "loadpin",
+	.id = LSM_ID_LOADPIN,
+};
+
 static struct security_hook_list loadpin_hooks[] __ro_after_init = {
 	LSM_HOOK_INIT(sb_free_security, loadpin_sb_free_security),
 	LSM_HOOK_INIT(kernel_read_file, loadpin_read_file),
@@ -259,7 +265,8 @@ static int __init loadpin_init(void)
 	if (!register_sysctl("kernel/loadpin", loadpin_sysctl_table))
 		pr_notice("sysctl registration failed!\n");
 #endif
-	security_add_hooks(loadpin_hooks, ARRAY_SIZE(loadpin_hooks), "loadpin");
+	security_add_hooks(loadpin_hooks, ARRAY_SIZE(loadpin_hooks),
+			   &loadpin_lsmid);
 
 	return 0;
 }
diff --git a/security/lockdown/lockdown.c b/security/lockdown/lockdown.c
index 68d19632aeb7..cd84d8ea1dfb 100644
--- a/security/lockdown/lockdown.c
+++ b/security/lockdown/lockdown.c
@@ -13,6 +13,7 @@
 #include <linux/security.h>
 #include <linux/export.h>
 #include <linux/lsm_hooks.h>
+#include <uapi/linux/lsm.h>
 
 static enum lockdown_reason kernel_locked_down;
 
@@ -75,6 +76,11 @@ static struct security_hook_list lockdown_hooks[] __ro_after_init = {
 	LSM_HOOK_INIT(locked_down, lockdown_is_locked_down),
 };
 
+const struct lsm_id lockdown_lsmid = {
+	.name = "lockdown",
+	.id = LSM_ID_LOCKDOWN,
+};
+
 static int __init lockdown_lsm_init(void)
 {
 #if defined(CONFIG_LOCK_DOWN_KERNEL_FORCE_INTEGRITY)
@@ -83,7 +89,7 @@ static int __init lockdown_lsm_init(void)
 	lock_kernel_down("Kernel configuration", LOCKDOWN_CONFIDENTIALITY_MAX);
 #endif
 	security_add_hooks(lockdown_hooks, ARRAY_SIZE(lockdown_hooks),
-			   "lockdown");
+			   &lockdown_lsmid);
 	return 0;
 }
 
diff --git a/security/safesetid/lsm.c b/security/safesetid/lsm.c
index 5be5894aa0ea..f42d5af5ffb0 100644
--- a/security/safesetid/lsm.c
+++ b/security/safesetid/lsm.c
@@ -19,6 +19,7 @@
 #include <linux/ptrace.h>
 #include <linux/sched/task_stack.h>
 #include <linux/security.h>
+#include <uapi/linux/lsm.h>
 #include "lsm.h"
 
 /* Flag indicating whether initialization completed */
@@ -261,6 +262,11 @@ static int safesetid_task_fix_setgroups(struct cred *new, const struct cred *old
 	return 0;
 }
 
+const struct lsm_id safesetid_lsmid = {
+	.name = "safesetid",
+	.id = LSM_ID_SAFESETID,
+};
+
 static struct security_hook_list safesetid_security_hooks[] = {
 	LSM_HOOK_INIT(task_fix_setuid, safesetid_task_fix_setuid),
 	LSM_HOOK_INIT(task_fix_setgid, safesetid_task_fix_setgid),
@@ -271,7 +277,8 @@ static struct security_hook_list safesetid_security_hooks[] = {
 static int __init safesetid_security_init(void)
 {
 	security_add_hooks(safesetid_security_hooks,
-			   ARRAY_SIZE(safesetid_security_hooks), "safesetid");
+			   ARRAY_SIZE(safesetid_security_hooks),
+			   &safesetid_lsmid);
 
 	/* Report that SafeSetID successfully initialized */
 	safesetid_initialized = 1;
diff --git a/security/security.c b/security/security.c
index dcb3e7014f9b..08b1bd9457a9 100644
--- a/security/security.c
+++ b/security/security.c
@@ -513,17 +513,17 @@ static int lsm_append(const char *new, char **result)
  * security_add_hooks - Add a modules hooks to the hook lists.
  * @hooks: the hooks to add
  * @count: the number of hooks to add
- * @lsm: the name of the security module
+ * @lsmid: the identification information for the security module
  *
  * Each LSM has to register its hooks with the infrastructure.
  */
 void __init security_add_hooks(struct security_hook_list *hooks, int count,
-			       const char *lsm)
+			       const struct lsm_id *lsmid)
 {
 	int i;
 
 	for (i = 0; i < count; i++) {
-		hooks[i].lsm = lsm;
+		hooks[i].lsmid = lsmid;
 		hlist_add_tail_rcu(&hooks[i].list, hooks[i].head);
 	}
 
@@ -532,7 +532,7 @@ void __init security_add_hooks(struct security_hook_list *hooks, int count,
 	 * and fix this up afterwards.
 	 */
 	if (slab_is_available()) {
-		if (lsm_append(lsm, &lsm_names) < 0)
+		if (lsm_append(lsmid->name, &lsm_names) < 0)
 			panic("%s - Cannot get early memory.\n", __func__);
 	}
 }
@@ -3817,7 +3817,7 @@ int security_getprocattr(struct task_struct *p, const char *lsm,
 	struct security_hook_list *hp;
 
 	hlist_for_each_entry(hp, &security_hook_heads.getprocattr, list) {
-		if (lsm != NULL && strcmp(lsm, hp->lsm))
+		if (lsm != NULL && strcmp(lsm, hp->lsmid->name))
 			continue;
 		return hp->hook.getprocattr(p, name, value);
 	}
@@ -3842,7 +3842,7 @@ int security_setprocattr(const char *lsm, const char *name, void *value,
 	struct security_hook_list *hp;
 
 	hlist_for_each_entry(hp, &security_hook_heads.setprocattr, list) {
-		if (lsm != NULL && strcmp(lsm, hp->lsm))
+		if (lsm != NULL && strcmp(lsm, hp->lsmid->name))
 			continue;
 		return hp->hook.setprocattr(name, value, size);
 	}
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index feda711c6b7b..f2423dfd19cd 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -92,6 +92,7 @@
 #include <linux/fsnotify.h>
 #include <linux/fanotify.h>
 #include <linux/io_uring.h>
+#include <uapi/linux/lsm.h>
 
 #include "avc.h"
 #include "objsec.h"
@@ -6950,6 +6951,11 @@ static int selinux_uring_cmd(struct io_uring_cmd *ioucmd)
 }
 #endif /* CONFIG_IO_URING */
 
+const struct lsm_id selinux_lsmid = {
+	.name = "selinux",
+	.id = LSM_ID_SELINUX,
+};
+
 /*
  * IMPORTANT NOTE: When adding new hooks, please be careful to keep this order:
  * 1. any hooks that don't belong to (2.) or (3.) below,
@@ -7270,7 +7276,8 @@ static __init int selinux_init(void)
 
 	hashtab_cache_init();
 
-	security_add_hooks(selinux_hooks, ARRAY_SIZE(selinux_hooks), "selinux");
+	security_add_hooks(selinux_hooks, ARRAY_SIZE(selinux_hooks),
+			   &selinux_lsmid);
 
 	if (avc_add_callback(selinux_netcache_avc_callback, AVC_CALLBACK_RESET))
 		panic("SELinux: Unable to register AVC netcache callback\n");
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index 65130a791f57..f73f9a2834eb 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -43,6 +43,7 @@
 #include <linux/fs_parser.h>
 #include <linux/watch_queue.h>
 #include <linux/io_uring.h>
+#include <uapi/linux/lsm.h>
 #include "smack.h"
 
 #define TRANS_TRUE	"TRUE"
@@ -4933,6 +4934,11 @@ struct lsm_blob_sizes smack_blob_sizes __ro_after_init = {
 	.lbs_xattr_count = SMACK_INODE_INIT_XATTRS,
 };
 
+const struct lsm_id smack_lsmid = {
+	.name = "smack",
+	.id = LSM_ID_SMACK,
+};
+
 static struct security_hook_list smack_hooks[] __ro_after_init = {
 	LSM_HOOK_INIT(ptrace_access_check, smack_ptrace_access_check),
 	LSM_HOOK_INIT(ptrace_traceme, smack_ptrace_traceme),
@@ -5140,7 +5146,7 @@ static __init int smack_init(void)
 	/*
 	 * Register with LSM
 	 */
-	security_add_hooks(smack_hooks, ARRAY_SIZE(smack_hooks), "smack");
+	security_add_hooks(smack_hooks, ARRAY_SIZE(smack_hooks), &smack_lsmid);
 	smack_enabled = 1;
 
 	pr_info("Smack:  Initializing.\n");
diff --git a/security/tomoyo/tomoyo.c b/security/tomoyo/tomoyo.c
index 255f1b470295..722205433105 100644
--- a/security/tomoyo/tomoyo.c
+++ b/security/tomoyo/tomoyo.c
@@ -6,6 +6,7 @@
  */
 
 #include <linux/lsm_hooks.h>
+#include <uapi/linux/lsm.h>
 #include "common.h"
 
 /**
@@ -542,6 +543,11 @@ static void tomoyo_task_free(struct task_struct *task)
 	}
 }
 
+const struct lsm_id tomoyo_lsmid = {
+	.name = "tomoyo",
+	.id = LSM_ID_TOMOYO,
+};
+
 /*
  * tomoyo_security_ops is a "struct security_operations" which is used for
  * registering TOMOYO.
@@ -595,7 +601,8 @@ static int __init tomoyo_init(void)
 	struct tomoyo_task *s = tomoyo_task(current);
 
 	/* register ourselves with the security framework */
-	security_add_hooks(tomoyo_hooks, ARRAY_SIZE(tomoyo_hooks), "tomoyo");
+	security_add_hooks(tomoyo_hooks, ARRAY_SIZE(tomoyo_hooks),
+			   &tomoyo_lsmid);
 	pr_info("TOMOYO Linux initialized\n");
 	s->domain_info = &tomoyo_kernel_domain;
 	atomic_inc(&tomoyo_kernel_domain.users);
diff --git a/security/yama/yama_lsm.c b/security/yama/yama_lsm.c
index 2503cf153d4a..5cdff292fcae 100644
--- a/security/yama/yama_lsm.c
+++ b/security/yama/yama_lsm.c
@@ -18,6 +18,7 @@
 #include <linux/task_work.h>
 #include <linux/sched.h>
 #include <linux/spinlock.h>
+#include <uapi/linux/lsm.h>
 
 #define YAMA_SCOPE_DISABLED	0
 #define YAMA_SCOPE_RELATIONAL	1
@@ -421,6 +422,11 @@ static int yama_ptrace_traceme(struct task_struct *parent)
 	return rc;
 }
 
+const struct lsm_id yama_lsmid = {
+	.name = "yama",
+	.id = LSM_ID_YAMA,
+};
+
 static struct security_hook_list yama_hooks[] __ro_after_init = {
 	LSM_HOOK_INIT(ptrace_access_check, yama_ptrace_access_check),
 	LSM_HOOK_INIT(ptrace_traceme, yama_ptrace_traceme),
@@ -471,7 +477,7 @@ static inline void yama_init_sysctl(void) { }
 static int __init yama_init(void)
 {
 	pr_info("Yama: becoming mindful.\n");
-	security_add_hooks(yama_hooks, ARRAY_SIZE(yama_hooks), "yama");
+	security_add_hooks(yama_hooks, ARRAY_SIZE(yama_hooks), &yama_lsmid);
 	yama_init_sysctl();
 	return 0;
 }
-- 
cgit v1.2.3


From 9285c5ad9d00abfe0f4e2ce4039c8127e7a09738 Mon Sep 17 00:00:00 2001
From: Casey Schaufler <casey@schaufler-ca.com>
Date: Tue, 12 Sep 2023 13:56:47 -0700
Subject: LSM: Maintain a table of LSM attribute data

As LSMs are registered add their lsm_id pointers to a table.
This will be used later for attribute reporting.

Determine the number of possible security modules based on
their respective CONFIG options. This allows the number to be
known at build time. This allows data structures and tables
to use the constant.

Signed-off-by: Casey Schaufler <casey@schaufler-ca.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Serge Hallyn <serge@hallyn.com>
Reviewed-by: Mickael Salaun <mic@digikod.net>
Reviewed-by: John Johansen <john.johansen@canonical.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 include/linux/security.h |  2 ++
 security/security.c      | 37 +++++++++++++++++++++++++++++++++++++
 2 files changed, 39 insertions(+)

(limited to 'include')

diff --git a/include/linux/security.h b/include/linux/security.h
index 1d1df326c881..50c178019a58 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -138,6 +138,8 @@ enum lockdown_reason {
 };
 
 extern const char *const lockdown_reasons[LOCKDOWN_CONFIDENTIALITY_MAX+1];
+extern u32 lsm_active_cnt;
+extern const struct lsm_id *lsm_idlist[];
 
 /* These functions are in security/commoncap.c */
 extern int cap_capable(const struct cred *cred, struct user_namespace *ns,
diff --git a/security/security.c b/security/security.c
index 08b1bd9457a9..0952d6bff4da 100644
--- a/security/security.c
+++ b/security/security.c
@@ -34,6 +34,25 @@
 /* How many LSMs were built into the kernel? */
 #define LSM_COUNT (__end_lsm_info - __start_lsm_info)
 
+/*
+ * How many LSMs are built into the kernel as determined at
+ * build time. Used to determine fixed array sizes.
+ * The capability module is accounted for by CONFIG_SECURITY
+ */
+#define LSM_CONFIG_COUNT ( \
+	(IS_ENABLED(CONFIG_SECURITY) ? 1 : 0) + \
+	(IS_ENABLED(CONFIG_SECURITY_SELINUX) ? 1 : 0) + \
+	(IS_ENABLED(CONFIG_SECURITY_SMACK) ? 1 : 0) + \
+	(IS_ENABLED(CONFIG_SECURITY_TOMOYO) ? 1 : 0) + \
+	(IS_ENABLED(CONFIG_IMA) ? 1 : 0) + \
+	(IS_ENABLED(CONFIG_SECURITY_APPARMOR) ? 1 : 0) + \
+	(IS_ENABLED(CONFIG_SECURITY_YAMA) ? 1 : 0) + \
+	(IS_ENABLED(CONFIG_SECURITY_LOADPIN) ? 1 : 0) + \
+	(IS_ENABLED(CONFIG_SECURITY_SAFESETID) ? 1 : 0) + \
+	(IS_ENABLED(CONFIG_SECURITY_LOCKDOWN_LSM) ? 1 : 0) + \
+	(IS_ENABLED(CONFIG_BPF_LSM) ? 1 : 0) + \
+	(IS_ENABLED(CONFIG_SECURITY_LANDLOCK) ? 1 : 0))
+
 /*
  * These are descriptions of the reasons that can be passed to the
  * security_locked_down() LSM hook. Placing this array here allows
@@ -245,6 +264,12 @@ static void __init initialize_lsm(struct lsm_info *lsm)
 	}
 }
 
+/*
+ * Current index to use while initializing the lsm id list.
+ */
+u32 lsm_active_cnt __ro_after_init;
+const struct lsm_id *lsm_idlist[LSM_CONFIG_COUNT];
+
 /* Populate ordered LSMs list from comma-separated LSM name list. */
 static void __init ordered_lsm_parse(const char *order, const char *origin)
 {
@@ -522,6 +547,18 @@ void __init security_add_hooks(struct security_hook_list *hooks, int count,
 {
 	int i;
 
+	/*
+	 * A security module may call security_add_hooks() more
+	 * than once during initialization, and LSM initialization
+	 * is serialized. Landlock is one such case.
+	 * Look at the previous entry, if there is one, for duplication.
+	 */
+	if (lsm_active_cnt == 0 || lsm_idlist[lsm_active_cnt - 1] != lsmid) {
+		if (lsm_active_cnt >= LSM_CONFIG_COUNT)
+			panic("%s Too many LSMs registered.\n", __func__);
+		lsm_idlist[lsm_active_cnt++] = lsmid;
+	}
+
 	for (i = 0; i < count; i++) {
 		hooks[i].lsmid = lsmid;
 		hlist_add_tail_rcu(&hooks[i].list, hooks[i].head);
-- 
cgit v1.2.3


From 267c068e5f8b81b68cc4247c94dbba90a21a634e Mon Sep 17 00:00:00 2001
From: Casey Schaufler <casey@schaufler-ca.com>
Date: Tue, 12 Sep 2023 13:56:48 -0700
Subject: proc: Use lsmids instead of lsm names for attrs

Use the LSM ID number instead of the LSM name to identify which
security module's attibute data should be shown in /proc/self/attr.
The security_[gs]etprocattr() functions have been changed to expect
the LSM ID. The change from a string comparison to an integer comparison
in these functions will provide a minor performance improvement.

Cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Casey Schaufler <casey@schaufler-ca.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Serge Hallyn <serge@hallyn.com>
Reviewed-by: Mickael Salaun <mic@digikod.net>
Reviewed-by: John Johansen <john.johansen@canonical.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 fs/proc/base.c           | 29 +++++++++++++++--------------
 fs/proc/internal.h       |  2 +-
 include/linux/security.h | 11 +++++------
 security/security.c      | 15 +++++++--------
 4 files changed, 28 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/fs/proc/base.c b/fs/proc/base.c
index dd31e3b6bf77..98a031ac2648 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -97,6 +97,7 @@
 #include <linux/resctrl.h>
 #include <linux/cn_proc.h>
 #include <linux/ksm.h>
+#include <uapi/linux/lsm.h>
 #include <trace/events/oom.h>
 #include "internal.h"
 #include "fd.h"
@@ -146,10 +147,10 @@ struct pid_entry {
 	NOD(NAME, (S_IFREG|(MODE)),			\
 		NULL, &proc_single_file_operations,	\
 		{ .proc_show = show } )
-#define ATTR(LSM, NAME, MODE)				\
+#define ATTR(LSMID, NAME, MODE)				\
 	NOD(NAME, (S_IFREG|(MODE)),			\
 		NULL, &proc_pid_attr_operations,	\
-		{ .lsm = LSM })
+		{ .lsmid = LSMID })
 
 /*
  * Count the number of hardlinks for the pid_entry table, excluding the .
@@ -2726,7 +2727,7 @@ static ssize_t proc_pid_attr_read(struct file * file, char __user * buf,
 	if (!task)
 		return -ESRCH;
 
-	length = security_getprocattr(task, PROC_I(inode)->op.lsm,
+	length = security_getprocattr(task, PROC_I(inode)->op.lsmid,
 				      file->f_path.dentry->d_name.name,
 				      &p);
 	put_task_struct(task);
@@ -2784,7 +2785,7 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
 	if (rv < 0)
 		goto out_free;
 
-	rv = security_setprocattr(PROC_I(inode)->op.lsm,
+	rv = security_setprocattr(PROC_I(inode)->op.lsmid,
 				  file->f_path.dentry->d_name.name, page,
 				  count);
 	mutex_unlock(&current->signal->cred_guard_mutex);
@@ -2833,27 +2834,27 @@ static const struct inode_operations proc_##LSM##_attr_dir_inode_ops = { \
 
 #ifdef CONFIG_SECURITY_SMACK
 static const struct pid_entry smack_attr_dir_stuff[] = {
-	ATTR("smack", "current",	0666),
+	ATTR(LSM_ID_SMACK, "current",	0666),
 };
 LSM_DIR_OPS(smack);
 #endif
 
 #ifdef CONFIG_SECURITY_APPARMOR
 static const struct pid_entry apparmor_attr_dir_stuff[] = {
-	ATTR("apparmor", "current",	0666),
-	ATTR("apparmor", "prev",	0444),
-	ATTR("apparmor", "exec",	0666),
+	ATTR(LSM_ID_APPARMOR, "current",	0666),
+	ATTR(LSM_ID_APPARMOR, "prev",		0444),
+	ATTR(LSM_ID_APPARMOR, "exec",		0666),
 };
 LSM_DIR_OPS(apparmor);
 #endif
 
 static const struct pid_entry attr_dir_stuff[] = {
-	ATTR(NULL, "current",		0666),
-	ATTR(NULL, "prev",		0444),
-	ATTR(NULL, "exec",		0666),
-	ATTR(NULL, "fscreate",		0666),
-	ATTR(NULL, "keycreate",		0666),
-	ATTR(NULL, "sockcreate",	0666),
+	ATTR(LSM_ID_UNDEF, "current",	0666),
+	ATTR(LSM_ID_UNDEF, "prev",		0444),
+	ATTR(LSM_ID_UNDEF, "exec",		0666),
+	ATTR(LSM_ID_UNDEF, "fscreate",	0666),
+	ATTR(LSM_ID_UNDEF, "keycreate",	0666),
+	ATTR(LSM_ID_UNDEF, "sockcreate",	0666),
 #ifdef CONFIG_SECURITY_SMACK
 	DIR("smack",			0555,
 	    proc_smack_attr_dir_inode_ops, proc_smack_attr_dir_ops),
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 9a8f32f21ff5..a71ac5379584 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -92,7 +92,7 @@ union proc_op {
 	int (*proc_show)(struct seq_file *m,
 		struct pid_namespace *ns, struct pid *pid,
 		struct task_struct *task);
-	const char *lsm;
+	int lsmid;
 };
 
 struct proc_inode {
diff --git a/include/linux/security.h b/include/linux/security.h
index 50c178019a58..c81bca77f4f2 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -472,10 +472,9 @@ int security_sem_semctl(struct kern_ipc_perm *sma, int cmd);
 int security_sem_semop(struct kern_ipc_perm *sma, struct sembuf *sops,
 			unsigned nsops, int alter);
 void security_d_instantiate(struct dentry *dentry, struct inode *inode);
-int security_getprocattr(struct task_struct *p, const char *lsm, const char *name,
+int security_getprocattr(struct task_struct *p, int lsmid, const char *name,
 			 char **value);
-int security_setprocattr(const char *lsm, const char *name, void *value,
-			 size_t size);
+int security_setprocattr(int lsmid, const char *name, void *value, size_t size);
 int security_netlink_send(struct sock *sk, struct sk_buff *skb);
 int security_ismaclabel(const char *name);
 int security_secid_to_secctx(u32 secid, char **secdata, u32 *seclen);
@@ -1339,14 +1338,14 @@ static inline void security_d_instantiate(struct dentry *dentry,
 					  struct inode *inode)
 { }
 
-static inline int security_getprocattr(struct task_struct *p, const char *lsm,
+static inline int security_getprocattr(struct task_struct *p, int lsmid,
 				       const char *name, char **value)
 {
 	return -EINVAL;
 }
 
-static inline int security_setprocattr(const char *lsm, char *name,
-				       void *value, size_t size)
+static inline int security_setprocattr(int lsmid, char *name, void *value,
+				       size_t size)
 {
 	return -EINVAL;
 }
diff --git a/security/security.c b/security/security.c
index 0952d6bff4da..c66f9faefa40 100644
--- a/security/security.c
+++ b/security/security.c
@@ -3840,7 +3840,7 @@ EXPORT_SYMBOL(security_d_instantiate);
 /**
  * security_getprocattr() - Read an attribute for a task
  * @p: the task
- * @lsm: LSM name
+ * @lsmid: LSM identification
  * @name: attribute name
  * @value: attribute value
  *
@@ -3848,13 +3848,13 @@ EXPORT_SYMBOL(security_d_instantiate);
  *
  * Return: Returns the length of @value on success, a negative value otherwise.
  */
-int security_getprocattr(struct task_struct *p, const char *lsm,
-			 const char *name, char **value)
+int security_getprocattr(struct task_struct *p, int lsmid, const char *name,
+			 char **value)
 {
 	struct security_hook_list *hp;
 
 	hlist_for_each_entry(hp, &security_hook_heads.getprocattr, list) {
-		if (lsm != NULL && strcmp(lsm, hp->lsmid->name))
+		if (lsmid != 0 && lsmid != hp->lsmid->id)
 			continue;
 		return hp->hook.getprocattr(p, name, value);
 	}
@@ -3863,7 +3863,7 @@ int security_getprocattr(struct task_struct *p, const char *lsm,
 
 /**
  * security_setprocattr() - Set an attribute for a task
- * @lsm: LSM name
+ * @lsmid: LSM identification
  * @name: attribute name
  * @value: attribute value
  * @size: attribute value size
@@ -3873,13 +3873,12 @@ int security_getprocattr(struct task_struct *p, const char *lsm,
  *
  * Return: Returns bytes written on success, a negative value otherwise.
  */
-int security_setprocattr(const char *lsm, const char *name, void *value,
-			 size_t size)
+int security_setprocattr(int lsmid, const char *name, void *value, size_t size)
 {
 	struct security_hook_list *hp;
 
 	hlist_for_each_entry(hp, &security_hook_heads.setprocattr, list) {
-		if (lsm != NULL && strcmp(lsm, hp->lsmid->name))
+		if (lsmid != 0 && lsmid != hp->lsmid->id)
 			continue;
 		return hp->hook.setprocattr(name, value, size);
 	}
-- 
cgit v1.2.3


From a04a1198088a1378d0389c250cc684f649bcc91e Mon Sep 17 00:00:00 2001
From: Casey Schaufler <casey@schaufler-ca.com>
Date: Tue, 12 Sep 2023 13:56:49 -0700
Subject: LSM: syscalls for current process attributes

Create a system call lsm_get_self_attr() to provide the security
module maintained attributes of the current process.
Create a system call lsm_set_self_attr() to set a security
module maintained attribute of the current process.
Historically these attributes have been exposed to user space via
entries in procfs under /proc/self/attr.

The attribute value is provided in a lsm_ctx structure. The structure
identifies the size of the attribute, and the attribute value. The format
of the attribute value is defined by the security module. A flags field
is included for LSM specific information. It is currently unused and must
be 0. The total size of the data, including the lsm_ctx structure and any
padding, is maintained as well.

struct lsm_ctx {
        __u64 id;
        __u64 flags;
        __u64 len;
        __u64 ctx_len;
        __u8 ctx[];
};

Two new LSM hooks are used to interface with the LSMs.
security_getselfattr() collects the lsm_ctx values from the
LSMs that support the hook, accounting for space requirements.
security_setselfattr() identifies which LSM the attribute is
intended for and passes it along.

Signed-off-by: Casey Schaufler <casey@schaufler-ca.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Serge Hallyn <serge@hallyn.com>
Reviewed-by: John Johansen <john.johansen@canonical.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 Documentation/userspace-api/lsm.rst |  70 +++++++++++++++++
 include/linux/lsm_hook_defs.h       |   4 +
 include/linux/lsm_hooks.h           |   1 +
 include/linux/security.h            |  19 +++++
 include/linux/syscalls.h            |   5 ++
 include/uapi/linux/lsm.h            |  36 +++++++++
 kernel/sys_ni.c                     |   2 +
 security/Makefile                   |   1 +
 security/lsm_syscalls.c             |  57 ++++++++++++++
 security/security.c                 | 152 ++++++++++++++++++++++++++++++++++++
 10 files changed, 347 insertions(+)
 create mode 100644 Documentation/userspace-api/lsm.rst
 create mode 100644 security/lsm_syscalls.c

(limited to 'include')

diff --git a/Documentation/userspace-api/lsm.rst b/Documentation/userspace-api/lsm.rst
new file mode 100644
index 000000000000..f8499f3e2826
--- /dev/null
+++ b/Documentation/userspace-api/lsm.rst
@@ -0,0 +1,70 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. Copyright (C) 2022 Casey Schaufler <casey@schaufler-ca.com>
+.. Copyright (C) 2022 Intel Corporation
+
+=====================================
+Linux Security Modules
+=====================================
+
+:Author: Casey Schaufler
+:Date: July 2023
+
+Linux security modules (LSM) provide a mechanism to implement
+additional access controls to the Linux security policies.
+
+The various security modules may support any of these attributes:
+
+``LSM_ATTR_CURRENT`` is the current, active security context of the
+process.
+The proc filesystem provides this value in ``/proc/self/attr/current``.
+This is supported by the SELinux, Smack and AppArmor security modules.
+Smack also provides this value in ``/proc/self/attr/smack/current``.
+AppArmor also provides this value in ``/proc/self/attr/apparmor/current``.
+
+``LSM_ATTR_EXEC`` is the security context of the process at the time the
+current image was executed.
+The proc filesystem provides this value in ``/proc/self/attr/exec``.
+This is supported by the SELinux and AppArmor security modules.
+AppArmor also provides this value in ``/proc/self/attr/apparmor/exec``.
+
+``LSM_ATTR_FSCREATE`` is the security context of the process used when
+creating file system objects.
+The proc filesystem provides this value in ``/proc/self/attr/fscreate``.
+This is supported by the SELinux security module.
+
+``LSM_ATTR_KEYCREATE`` is the security context of the process used when
+creating key objects.
+The proc filesystem provides this value in ``/proc/self/attr/keycreate``.
+This is supported by the SELinux security module.
+
+``LSM_ATTR_PREV`` is the security context of the process at the time the
+current security context was set.
+The proc filesystem provides this value in ``/proc/self/attr/prev``.
+This is supported by the SELinux and AppArmor security modules.
+AppArmor also provides this value in ``/proc/self/attr/apparmor/prev``.
+
+``LSM_ATTR_SOCKCREATE`` is the security context of the process used when
+creating socket objects.
+The proc filesystem provides this value in ``/proc/self/attr/sockcreate``.
+This is supported by the SELinux security module.
+
+Kernel interface
+================
+
+Set a security attribute of the current process
+-----------------------------------------------
+
+.. kernel-doc:: security/lsm_syscalls.c
+    :identifiers: sys_lsm_set_self_attr
+
+Get the specified security attributes of the current process
+------------------------------------------------------------
+
+.. kernel-doc:: security/lsm_syscalls.c
+    :identifiers: sys_lsm_get_self_attr
+
+Additional documentation
+========================
+
+* Documentation/security/lsm.rst
+* Documentation/security/lsm-development.rst
diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index ff217a5ce552..c925a0d26edf 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -262,6 +262,10 @@ LSM_HOOK(int, 0, sem_semop, struct kern_ipc_perm *perm, struct sembuf *sops,
 LSM_HOOK(int, 0, netlink_send, struct sock *sk, struct sk_buff *skb)
 LSM_HOOK(void, LSM_RET_VOID, d_instantiate, struct dentry *dentry,
 	 struct inode *inode)
+LSM_HOOK(int, -EOPNOTSUPP, getselfattr, unsigned int attr,
+	 struct lsm_ctx __user *ctx, size_t *size, u32 flags)
+LSM_HOOK(int, -EOPNOTSUPP, setselfattr, unsigned int attr,
+	 struct lsm_ctx *ctx, size_t size, u32 flags)
 LSM_HOOK(int, -EINVAL, getprocattr, struct task_struct *p, const char *name,
 	 char **value)
 LSM_HOOK(int, -EINVAL, setprocattr, const char *name, void *value, size_t size)
diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index 7f0adb33caaa..a2ade0ffe9e7 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -25,6 +25,7 @@
 #ifndef __LINUX_LSM_HOOKS_H
 #define __LINUX_LSM_HOOKS_H
 
+#include <uapi/linux/lsm.h>
 #include <linux/security.h>
 #include <linux/init.h>
 #include <linux/rculist.h>
diff --git a/include/linux/security.h b/include/linux/security.h
index c81bca77f4f2..dd1fe487385d 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -60,6 +60,7 @@ struct fs_parameter;
 enum fs_value_type;
 struct watch;
 struct watch_notification;
+struct lsm_ctx;
 
 /* Default (no) options for the capable function */
 #define CAP_OPT_NONE 0x0
@@ -472,6 +473,10 @@ int security_sem_semctl(struct kern_ipc_perm *sma, int cmd);
 int security_sem_semop(struct kern_ipc_perm *sma, struct sembuf *sops,
 			unsigned nsops, int alter);
 void security_d_instantiate(struct dentry *dentry, struct inode *inode);
+int security_getselfattr(unsigned int attr, struct lsm_ctx __user *ctx,
+			 size_t __user *size, u32 flags);
+int security_setselfattr(unsigned int attr, struct lsm_ctx __user *ctx,
+			 size_t size, u32 flags);
 int security_getprocattr(struct task_struct *p, int lsmid, const char *name,
 			 char **value);
 int security_setprocattr(int lsmid, const char *name, void *value, size_t size);
@@ -1338,6 +1343,20 @@ static inline void security_d_instantiate(struct dentry *dentry,
 					  struct inode *inode)
 { }
 
+static inline int security_getselfattr(unsigned int attr,
+				       struct lsm_ctx __user *ctx,
+				       size_t __user *size, u32 flags)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int security_setselfattr(unsigned int attr,
+				       struct lsm_ctx __user *ctx,
+				       size_t size, u32 flags)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline int security_getprocattr(struct task_struct *p, int lsmid,
 				       const char *name, char **value)
 {
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index fd9d12de7e92..4e1e56a24f1e 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -71,6 +71,7 @@ struct clone_args;
 struct open_how;
 struct mount_attr;
 struct landlock_ruleset_attr;
+struct lsm_ctx;
 enum landlock_rule_type;
 struct cachestat_range;
 struct cachestat;
@@ -949,6 +950,10 @@ asmlinkage long sys_cachestat(unsigned int fd,
 		struct cachestat_range __user *cstat_range,
 		struct cachestat __user *cstat, unsigned int flags);
 asmlinkage long sys_map_shadow_stack(unsigned long addr, unsigned long size, unsigned int flags);
+asmlinkage long sys_lsm_get_self_attr(unsigned int attr, struct lsm_ctx *ctx,
+				      size_t *size, __u32 flags);
+asmlinkage long sys_lsm_set_self_attr(unsigned int attr, struct lsm_ctx *ctx,
+				      size_t size, __u32 flags);
 
 /*
  * Architecture-specific system calls
diff --git a/include/uapi/linux/lsm.h b/include/uapi/linux/lsm.h
index f27c9a9cc376..eeda59a77c02 100644
--- a/include/uapi/linux/lsm.h
+++ b/include/uapi/linux/lsm.h
@@ -9,6 +9,36 @@
 #ifndef _UAPI_LINUX_LSM_H
 #define _UAPI_LINUX_LSM_H
 
+#include <linux/types.h>
+#include <linux/unistd.h>
+
+/**
+ * struct lsm_ctx - LSM context information
+ * @id: the LSM id number, see LSM_ID_XXX
+ * @flags: LSM specific flags
+ * @len: length of the lsm_ctx struct, @ctx and any other data or padding
+ * @ctx_len: the size of @ctx
+ * @ctx: the LSM context value
+ *
+ * The @len field MUST be equal to the size of the lsm_ctx struct
+ * plus any additional padding and/or data placed after @ctx.
+ *
+ * In all cases @ctx_len MUST be equal to the length of @ctx.
+ * If @ctx is a string value it should be nul terminated with
+ * @ctx_len equal to `strlen(@ctx) + 1`.  Binary values are
+ * supported.
+ *
+ * The @flags and @ctx fields SHOULD only be interpreted by the
+ * LSM specified by @id; they MUST be set to zero/0 when not used.
+ */
+struct lsm_ctx {
+	__u64 id;
+	__u64 flags;
+	__u64 len;
+	__u64 ctx_len;
+	__u8 ctx[];
+};
+
 /*
  * ID tokens to identify Linux Security Modules (LSMs)
  *
@@ -51,4 +81,10 @@
 #define LSM_ATTR_PREV		104
 #define LSM_ATTR_SOCKCREATE	105
 
+/*
+ * LSM_FLAG_XXX definitions identify special handling instructions
+ * for the API.
+ */
+#define LSM_FLAG_SINGLE	0x0001
+
 #endif /* _UAPI_LINUX_LSM_H */
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index e1a6e3c675c0..1f61b8452a6e 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -171,6 +171,8 @@ COND_SYSCALL(landlock_add_rule);
 COND_SYSCALL(landlock_restrict_self);
 COND_SYSCALL(fadvise64_64);
 COND_SYSCALL_COMPAT(fadvise64_64);
+COND_SYSCALL(lsm_get_self_attr);
+COND_SYSCALL(lsm_set_self_attr);
 
 /* CONFIG_MMU only */
 COND_SYSCALL(swapon);
diff --git a/security/Makefile b/security/Makefile
index 18121f8f85cd..59f238490665 100644
--- a/security/Makefile
+++ b/security/Makefile
@@ -7,6 +7,7 @@ obj-$(CONFIG_KEYS)			+= keys/
 
 # always enable default capabilities
 obj-y					+= commoncap.o
+obj-$(CONFIG_SECURITY) 			+= lsm_syscalls.o
 obj-$(CONFIG_MMU)			+= min_addr.o
 
 # Object file lists
diff --git a/security/lsm_syscalls.c b/security/lsm_syscalls.c
new file mode 100644
index 000000000000..226ae80d9683
--- /dev/null
+++ b/security/lsm_syscalls.c
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * System calls implementing the Linux Security Module API.
+ *
+ *  Copyright (C) 2022 Casey Schaufler <casey@schaufler-ca.com>
+ *  Copyright (C) 2022 Intel Corporation
+ */
+
+#include <asm/current.h>
+#include <linux/compiler_types.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/security.h>
+#include <linux/stddef.h>
+#include <linux/syscalls.h>
+#include <linux/types.h>
+#include <linux/lsm_hooks.h>
+#include <uapi/linux/lsm.h>
+
+/**
+ * sys_lsm_set_self_attr - Set current task's security module attribute
+ * @attr: which attribute to set
+ * @ctx: the LSM contexts
+ * @size: size of @ctx
+ * @flags: reserved for future use
+ *
+ * Sets the calling task's LSM context. On success this function
+ * returns 0. If the attribute specified cannot be set a negative
+ * value indicating the reason for the error is returned.
+ */
+SYSCALL_DEFINE4(lsm_set_self_attr, unsigned int, attr, struct lsm_ctx __user *,
+		ctx, size_t, size, u32, flags)
+{
+	return security_setselfattr(attr, ctx, size, flags);
+}
+
+/**
+ * sys_lsm_get_self_attr - Return current task's security module attributes
+ * @attr: which attribute to return
+ * @ctx: the user-space destination for the information, or NULL
+ * @size: pointer to the size of space available to receive the data
+ * @flags: special handling options. LSM_FLAG_SINGLE indicates that only
+ * attributes associated with the LSM identified in the passed @ctx be
+ * reported.
+ *
+ * Returns the calling task's LSM contexts. On success this
+ * function returns the number of @ctx array elements. This value
+ * may be zero if there are no LSM contexts assigned. If @size is
+ * insufficient to contain the return data -E2BIG is returned and
+ * @size is set to the minimum required size. In all other cases
+ * a negative value indicating the error is returned.
+ */
+SYSCALL_DEFINE4(lsm_get_self_attr, unsigned int, attr, struct lsm_ctx __user *,
+		ctx, size_t __user *, size, u32, flags)
+{
+	return security_getselfattr(attr, ctx, size, flags);
+}
diff --git a/security/security.c b/security/security.c
index c66f9faefa40..9757d009113f 100644
--- a/security/security.c
+++ b/security/security.c
@@ -3837,6 +3837,158 @@ void security_d_instantiate(struct dentry *dentry, struct inode *inode)
 }
 EXPORT_SYMBOL(security_d_instantiate);
 
+/*
+ * Please keep this in sync with it's counterpart in security/lsm_syscalls.c
+ */
+
+/**
+ * security_getselfattr - Read an LSM attribute of the current process.
+ * @attr: which attribute to return
+ * @uctx: the user-space destination for the information, or NULL
+ * @size: pointer to the size of space available to receive the data
+ * @flags: special handling options. LSM_FLAG_SINGLE indicates that only
+ * attributes associated with the LSM identified in the passed @ctx be
+ * reported.
+ *
+ * A NULL value for @uctx can be used to get both the number of attributes
+ * and the size of the data.
+ *
+ * Returns the number of attributes found on success, negative value
+ * on error. @size is reset to the total size of the data.
+ * If @size is insufficient to contain the data -E2BIG is returned.
+ */
+int security_getselfattr(unsigned int attr, struct lsm_ctx __user *uctx,
+			 size_t __user *size, u32 flags)
+{
+	struct security_hook_list *hp;
+	struct lsm_ctx lctx = { .id = LSM_ID_UNDEF, };
+	u8 __user *base = (u8 __user *)uctx;
+	size_t total = 0;
+	size_t entrysize;
+	size_t left;
+	bool toobig = false;
+	bool single = false;
+	int count = 0;
+	int rc;
+
+	if (attr == LSM_ATTR_UNDEF)
+		return -EINVAL;
+	if (size == NULL)
+		return -EINVAL;
+	if (get_user(left, size))
+		return -EFAULT;
+
+	if (flags) {
+		/*
+		 * Only flag supported is LSM_FLAG_SINGLE
+		 */
+		if (flags != LSM_FLAG_SINGLE)
+			return -EINVAL;
+		if (uctx && copy_from_user(&lctx, uctx, sizeof(lctx)))
+			return -EFAULT;
+		/*
+		 * If the LSM ID isn't specified it is an error.
+		 */
+		if (lctx.id == LSM_ID_UNDEF)
+			return -EINVAL;
+		single = true;
+	}
+
+	/*
+	 * In the usual case gather all the data from the LSMs.
+	 * In the single case only get the data from the LSM specified.
+	 */
+	hlist_for_each_entry(hp, &security_hook_heads.getselfattr, list) {
+		if (single && lctx.id != hp->lsmid->id)
+			continue;
+		entrysize = left;
+		if (base)
+			uctx = (struct lsm_ctx __user *)(base + total);
+		rc = hp->hook.getselfattr(attr, uctx, &entrysize, flags);
+		if (rc == -EOPNOTSUPP) {
+			rc = 0;
+			continue;
+		}
+		if (rc == -E2BIG) {
+			toobig = true;
+			left = 0;
+		} else if (rc < 0)
+			return rc;
+		else
+			left -= entrysize;
+
+		total += entrysize;
+		count += rc;
+		if (single)
+			break;
+	}
+	if (put_user(total, size))
+		return -EFAULT;
+	if (toobig)
+		return -E2BIG;
+	if (count == 0)
+		return LSM_RET_DEFAULT(getselfattr);
+	return count;
+}
+
+/*
+ * Please keep this in sync with it's counterpart in security/lsm_syscalls.c
+ */
+
+/**
+ * security_setselfattr - Set an LSM attribute on the current process.
+ * @attr: which attribute to set
+ * @uctx: the user-space source for the information
+ * @size: the size of the data
+ * @flags: reserved for future use, must be 0
+ *
+ * Set an LSM attribute for the current process. The LSM, attribute
+ * and new value are included in @uctx.
+ *
+ * Returns 0 on success, -EINVAL if the input is inconsistent, -EFAULT
+ * if the user buffer is inaccessible, E2BIG if size is too big, or an
+ * LSM specific failure.
+ */
+int security_setselfattr(unsigned int attr, struct lsm_ctx __user *uctx,
+			 size_t size, u32 flags)
+{
+	struct security_hook_list *hp;
+	struct lsm_ctx *lctx;
+	int rc = LSM_RET_DEFAULT(setselfattr);
+
+	if (flags)
+		return -EINVAL;
+	if (size < sizeof(*lctx))
+		return -EINVAL;
+	if (size > PAGE_SIZE)
+		return -E2BIG;
+
+	lctx = kmalloc(size, GFP_KERNEL);
+	if (lctx == NULL)
+		return -ENOMEM;
+
+	if (copy_from_user(lctx, uctx, size)) {
+		rc = -EFAULT;
+		goto free_out;
+	}
+
+	if (size < lctx->len || size < lctx->ctx_len + sizeof(*lctx) ||
+	    lctx->len < lctx->ctx_len + sizeof(*lctx)) {
+		rc = -EINVAL;
+		goto free_out;
+	}
+
+	hlist_for_each_entry(hp, &security_hook_heads.setselfattr, list)
+		if ((hp->lsmid->id) == lctx->id) {
+			rc = hp->hook.setselfattr(attr, lctx, size, flags);
+			break;
+		}
+
+free_out:
+	kfree(lctx);
+	return rc;
+}
+
 /**
  * security_getprocattr() - Read an attribute for a task
  * @p: the task
-- 
cgit v1.2.3


From ad4aff9ec25f400608283c10d634cc4eeda83a02 Mon Sep 17 00:00:00 2001
From: Casey Schaufler <casey@schaufler-ca.com>
Date: Tue, 12 Sep 2023 13:56:50 -0700
Subject: LSM: Create lsm_list_modules system call
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Create a system call to report the list of Linux Security Modules
that are active on the system. The list is provided as an array
of LSM ID numbers.

The calling application can use this list determine what LSM
specific actions it might take. That might include choosing an
output format, determining required privilege or bypassing
security module specific behavior.

Signed-off-by: Casey Schaufler <casey@schaufler-ca.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Serge Hallyn <serge@hallyn.com>
Reviewed-by: John Johansen <john.johansen@canonical.com>
Reviewed-by: Mickaël Salaün <mic@digikod.net>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 Documentation/userspace-api/lsm.rst |  3 +++
 include/linux/syscalls.h            |  1 +
 kernel/sys_ni.c                     |  1 +
 security/lsm_syscalls.c             | 39 +++++++++++++++++++++++++++++++++++++
 4 files changed, 44 insertions(+)

(limited to 'include')

diff --git a/Documentation/userspace-api/lsm.rst b/Documentation/userspace-api/lsm.rst
index f8499f3e2826..a76da373841b 100644
--- a/Documentation/userspace-api/lsm.rst
+++ b/Documentation/userspace-api/lsm.rst
@@ -63,6 +63,9 @@ Get the specified security attributes of the current process
 .. kernel-doc:: security/lsm_syscalls.c
     :identifiers: sys_lsm_get_self_attr
 
+.. kernel-doc:: security/lsm_syscalls.c
+    :identifiers: sys_lsm_list_modules
+
 Additional documentation
 ========================
 
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 4e1e56a24f1e..feec5719750b 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -954,6 +954,7 @@ asmlinkage long sys_lsm_get_self_attr(unsigned int attr, struct lsm_ctx *ctx,
 				      size_t *size, __u32 flags);
 asmlinkage long sys_lsm_set_self_attr(unsigned int attr, struct lsm_ctx *ctx,
 				      size_t size, __u32 flags);
+asmlinkage long sys_lsm_list_modules(u64 *ids, size_t *size, u32 flags);
 
 /*
  * Architecture-specific system calls
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 1f61b8452a6e..9fa5989bf2ce 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -173,6 +173,7 @@ COND_SYSCALL(fadvise64_64);
 COND_SYSCALL_COMPAT(fadvise64_64);
 COND_SYSCALL(lsm_get_self_attr);
 COND_SYSCALL(lsm_set_self_attr);
+COND_SYSCALL(lsm_list_modules);
 
 /* CONFIG_MMU only */
 COND_SYSCALL(swapon);
diff --git a/security/lsm_syscalls.c b/security/lsm_syscalls.c
index 226ae80d9683..329aaca5efc0 100644
--- a/security/lsm_syscalls.c
+++ b/security/lsm_syscalls.c
@@ -55,3 +55,42 @@ SYSCALL_DEFINE4(lsm_get_self_attr, unsigned int, attr, struct lsm_ctx __user *,
 {
 	return security_getselfattr(attr, ctx, size, flags);
 }
+
+/**
+ * sys_lsm_list_modules - Return a list of the active security modules
+ * @ids: the LSM module ids
+ * @size: pointer to size of @ids, updated on return
+ * @flags: reserved for future use, must be zero
+ *
+ * Returns a list of the active LSM ids. On success this function
+ * returns the number of @ids array elements. This value may be zero
+ * if there are no LSMs active. If @size is insufficient to contain
+ * the return data -E2BIG is returned and @size is set to the minimum
+ * required size. In all other cases a negative value indicating the
+ * error is returned.
+ */
+SYSCALL_DEFINE3(lsm_list_modules, u64 __user *, ids, size_t __user *, size,
+		u32, flags)
+{
+	size_t total_size = lsm_active_cnt * sizeof(*ids);
+	size_t usize;
+	int i;
+
+	if (flags)
+		return -EINVAL;
+
+	if (get_user(usize, size))
+		return -EFAULT;
+
+	if (put_user(total_size, size) != 0)
+		return -EFAULT;
+
+	if (usize < total_size)
+		return -E2BIG;
+
+	for (i = 0; i < lsm_active_cnt; i++)
+		if (put_user(lsm_idlist[i]->id, ids++))
+			return -EFAULT;
+
+	return lsm_active_cnt;
+}
-- 
cgit v1.2.3


From 5f42375904b08890f2e8e7cd955c5bf0c2c0d05a Mon Sep 17 00:00:00 2001
From: Casey Schaufler <casey@schaufler-ca.com>
Date: Tue, 12 Sep 2023 13:56:51 -0700
Subject: LSM: wireup Linux Security Module syscalls
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Wireup lsm_get_self_attr, lsm_set_self_attr and lsm_list_modules
system calls.

Signed-off-by: Casey Schaufler <casey@schaufler-ca.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Cc: linux-api@vger.kernel.org
Reviewed-by: Mickaël Salaün <mic@digikod.net>
[PM: forward ported beyond v6.6 due merge window changes]
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 arch/alpha/kernel/syscalls/syscall.tbl              | 3 +++
 arch/arm/tools/syscall.tbl                          | 3 +++
 arch/arm64/include/asm/unistd.h                     | 2 +-
 arch/arm64/include/asm/unistd32.h                   | 6 ++++++
 arch/m68k/kernel/syscalls/syscall.tbl               | 3 +++
 arch/microblaze/kernel/syscalls/syscall.tbl         | 3 +++
 arch/mips/kernel/syscalls/syscall_n32.tbl           | 3 +++
 arch/mips/kernel/syscalls/syscall_n64.tbl           | 3 +++
 arch/mips/kernel/syscalls/syscall_o32.tbl           | 3 +++
 arch/parisc/kernel/syscalls/syscall.tbl             | 3 +++
 arch/powerpc/kernel/syscalls/syscall.tbl            | 3 +++
 arch/s390/kernel/syscalls/syscall.tbl               | 3 +++
 arch/sh/kernel/syscalls/syscall.tbl                 | 3 +++
 arch/sparc/kernel/syscalls/syscall.tbl              | 3 +++
 arch/x86/entry/syscalls/syscall_32.tbl              | 3 +++
 arch/x86/entry/syscalls/syscall_64.tbl              | 3 +++
 arch/xtensa/kernel/syscalls/syscall.tbl             | 3 +++
 include/uapi/asm-generic/unistd.h                   | 9 ++++++++-
 tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl | 3 +++
 tools/perf/arch/powerpc/entry/syscalls/syscall.tbl  | 3 +++
 tools/perf/arch/s390/entry/syscalls/syscall.tbl     | 3 +++
 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl   | 3 +++
 22 files changed, 72 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index 18c842ca6c32..b04af0c9fcbc 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -496,3 +496,6 @@
 564	common	futex_wake			sys_futex_wake
 565	common	futex_wait			sys_futex_wait
 566	common	futex_requeue			sys_futex_requeue
+567	common	lsm_get_self_attr		sys_lsm_get_self_attr
+568	common	lsm_set_self_attr		sys_lsm_set_self_attr
+569	common	lsm_list_modules		sys_lsm_list_modules
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index 584f9528c996..43313beefae7 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -470,3 +470,6 @@
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
 456	common	futex_requeue			sys_futex_requeue
+457	common	lsm_get_self_attr		sys_lsm_get_self_attr
+458	common	lsm_set_self_attr		sys_lsm_set_self_attr
+459	common	lsm_list_modules		sys_lsm_list_modules
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 531effca5f1f..abe10a833fcd 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -39,7 +39,7 @@
 #define __ARM_NR_compat_set_tls		(__ARM_NR_COMPAT_BASE + 5)
 #define __ARM_NR_COMPAT_END		(__ARM_NR_COMPAT_BASE + 0x800)
 
-#define __NR_compat_syscalls		457
+#define __NR_compat_syscalls		460
 #endif
 
 #define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 9f7c1bf99526..ab1a7c2b6653 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -919,6 +919,12 @@ __SYSCALL(__NR_futex_wake, sys_futex_wake)
 __SYSCALL(__NR_futex_wait, sys_futex_wait)
 #define __NR_futex_requeue 456
 __SYSCALL(__NR_futex_requeue, sys_futex_requeue)
+#define __NR_lsm_get_self_attr 457
+__SYSCALL(__NR_lsm_get_self_attr, sys_lsm_get_self_attr)
+#define __NR_lsm_set_self_attr 458
+__SYSCALL(__NR_lsm_set_self_attr, sys_lsm_set_self_attr)
+#define __NR_lsm_list_modules 459
+__SYSCALL(__NR_lsm_list_modules, sys_lsm_list_modules)
 
 /*
  * Please add new compat syscalls above this comment and update
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index 7a4b780e82cb..90629ffc6732 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -456,3 +456,6 @@
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
 456	common	futex_requeue			sys_futex_requeue
+457	common	lsm_get_self_attr		sys_lsm_get_self_attr
+458	common	lsm_set_self_attr		sys_lsm_set_self_attr
+459	common	lsm_list_modules		sys_lsm_list_modules
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl
index 5b6a0b02b7de..c395dece73b4 100644
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -462,3 +462,6 @@
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
 456	common	futex_requeue			sys_futex_requeue
+457	common	lsm_get_self_attr		sys_lsm_get_self_attr
+458	common	lsm_set_self_attr		sys_lsm_set_self_attr
+459	common	lsm_list_modules		sys_lsm_list_modules
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index a842b41c8e06..4a876c4e77d6 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -395,3 +395,6 @@
 454	n32	futex_wake			sys_futex_wake
 455	n32	futex_wait			sys_futex_wait
 456	n32	futex_requeue			sys_futex_requeue
+457	n32	lsm_get_self_attr		sys_lsm_get_self_attr
+458	n32	lsm_set_self_attr		sys_lsm_set_self_attr
+459	n32	lsm_list_modules		sys_lsm_list_modules
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index 116ff501bf92..b74c8571f063 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -371,3 +371,6 @@
 454	n64	futex_wake			sys_futex_wake
 455	n64	futex_wait			sys_futex_wait
 456	n64	futex_requeue			sys_futex_requeue
+457	n64	lsm_get_self_attr		sys_lsm_get_self_attr
+458	n64	lsm_set_self_attr		sys_lsm_set_self_attr
+459	n64	lsm_list_modules		sys_lsm_list_modules
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index 525cc54bc63b..bf41906e1f68 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -444,3 +444,6 @@
 454	o32	futex_wake			sys_futex_wake
 455	o32	futex_wait			sys_futex_wait
 456	o32	futex_requeue			sys_futex_requeue
+457	o32	lsm_get_self_attr		sys_lsm_get_self_attr
+458	032	lsm_set_self_attr		sys_lsm_set_self_attr
+459	o32	lsm_list_modules		sys_lsm_list_modules
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index a47798fed54e..ccc0a679e774 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -455,3 +455,6 @@
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
 456	common	futex_requeue			sys_futex_requeue
+457	common	lsm_get_self_attr		sys_lsm_get_self_attr
+458	common	lsm_set_self_attr		sys_lsm_set_self_attr
+459	common	lsm_list_modules		sys_lsm_list_modules
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index 7fab411378f2..a6f37e2333cb 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -543,3 +543,6 @@
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
 456	common	futex_requeue			sys_futex_requeue
+457	common	lsm_get_self_attr		sys_lsm_get_self_attr
+458	common	lsm_set_self_attr		sys_lsm_set_self_attr
+459	common	lsm_list_modules		sys_lsm_list_modules
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index 86fec9b080f6..4b818e9ee832 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -459,3 +459,6 @@
 454  common	futex_wake		sys_futex_wake			sys_futex_wake
 455  common	futex_wait		sys_futex_wait			sys_futex_wait
 456  common	futex_requeue		sys_futex_requeue		sys_futex_requeue
+457  common	lsm_get_self_attr	sys_lsm_get_self_attr		sys_lsm_get_self_attr
+458  common	lsm_set_self_attr	sys_lsm_set_self_attr		sys_lsm_set_self_attr
+459  common	lsm_list_modules	sys_lsm_list_modules		sys_lsm_list_modules
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index 363fae0fe9bf..1a3d88d1a07f 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -459,3 +459,6 @@
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
 456	common	futex_requeue			sys_futex_requeue
+457	common	lsm_get_self_attr		sys_lsm_get_self_attr
+458	common	lsm_set_self_attr		sys_lsm_set_self_attr
+459	common	lsm_list_modules		sys_lsm_list_modules
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index 7bcaa3d5ea44..e0e8cec62358 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -502,3 +502,6 @@
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
 456	common	futex_requeue			sys_futex_requeue
+457	common	lsm_get_self_attr		sys_lsm_get_self_attr
+458	common	lsm_set_self_attr		sys_lsm_set_self_attr
+459	common	lsm_list_modules		sys_lsm_list_modules
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index c8fac5205803..6e45e693f339 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -461,3 +461,6 @@
 454	i386	futex_wake		sys_futex_wake
 455	i386	futex_wait		sys_futex_wait
 456	i386	futex_requeue		sys_futex_requeue
+457	i386	lsm_get_self_attr	sys_lsm_get_self_attr
+458	i386	lsm_set_self_attr	sys_lsm_set_self_attr
+459	i386	lsm_list_modules	sys_lsm_list_modules
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 8cb8bf68721c..d3b41d059d4d 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -378,6 +378,9 @@
 454	common	futex_wake		sys_futex_wake
 455	common	futex_wait		sys_futex_wait
 456	common	futex_requeue		sys_futex_requeue
+457	common	lsm_get_self_attr	sys_lsm_get_self_attr
+458	common	lsm_set_self_attr	sys_lsm_set_self_attr
+459	common	lsm_list_modules	sys_lsm_list_modules
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl
index 06eefa9c1458..284784ea5a46 100644
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -427,3 +427,6 @@
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
 456	common	futex_requeue			sys_futex_requeue
+457	common	lsm_get_self_attr		sys_lsm_get_self_attr
+458	common	lsm_set_self_attr		sys_lsm_set_self_attr
+459	common	lsm_list_modules		sys_lsm_list_modules
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 756b013fb832..55cc0bcfb58d 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -829,8 +829,15 @@ __SYSCALL(__NR_futex_wait, sys_futex_wait)
 #define __NR_futex_requeue 456
 __SYSCALL(__NR_futex_requeue, sys_futex_requeue)
 
+#define __NR_lsm_get_self_attr 457
+__SYSCALL(__NR_lsm_get_self_attr, sys_lsm_get_self_attr)
+#define __NR_lsm_set_self_attr 458
+__SYSCALL(__NR_lsm_set_self_attr, sys_lsm_set_self_attr)
+#define __NR_lsm_list_modules 459
+__SYSCALL(__NR_lsm_list_modules, sys_lsm_list_modules)
+
 #undef __NR_syscalls
-#define __NR_syscalls 457
+#define __NR_syscalls 460
 
 /*
  * 32 bit systems traditionally used different
diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
index 80be0e98ea0c..81c772c0f5c8 100644
--- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
+++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
@@ -367,3 +367,6 @@
 450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	n64	cachestat			sys_cachestat
 452	n64	fchmodat2			sys_fchmodat2
+453	n64	lsm_get_self_attr		sys_lsm_get_self_attr
+454	n64	lsm_set_self_attr		sys_lsm_set_self_attr
+455	n64	lsm_list_modules		sys_lsm_list_modules
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index e1412519b4ad..861c6ca0a8c3 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -539,3 +539,6 @@
 450 	nospu	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	common	cachestat			sys_cachestat
 452	common	fchmodat2			sys_fchmodat2
+453	common	lsm_get_self_attr		sys_lsm_get_self_attr
+454	common	lsm_set_self_attr		sys_lsm_set_self_attr
+455	common	lsm_list_modules		sys_lsm_list_modules
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index cc0bc144b661..5a422443cb16 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -455,3 +455,6 @@
 450  common	set_mempolicy_home_node	sys_set_mempolicy_home_node	sys_set_mempolicy_home_node
 451  common	cachestat		sys_cachestat			sys_cachestat
 452  common	fchmodat2		sys_fchmodat2			sys_fchmodat2
+453  common	lsm_get_self_attr	sys_lsm_get_self_attr	sys_lsm_get_self_attr
+454  common	lsm_set_self_attr	sys_lsm_set_self_attr	sys_lsm_set_self_attr
+455  common	lsm_list_modules	sys_lsm_list_modules	sys_lsm_list_modules
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 2a62eaf30d69..e692c88105a6 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -375,6 +375,9 @@
 451	common	cachestat		sys_cachestat
 452	common	fchmodat2		sys_fchmodat2
 453	64	map_shadow_stack	sys_map_shadow_stack
+454	common	lsm_get_self_attr	sys_lsm_get_self_attr
+455	common	lsm_set_self_attr	sys_lsm_set_self_attr
+456	common	lsm_list_modules	sys_lsm_list_modules
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
-- 
cgit v1.2.3


From e1ca7129db2c3b3c4d261702905a752e6b2710b4 Mon Sep 17 00:00:00 2001
From: Casey Schaufler <casey@schaufler-ca.com>
Date: Tue, 12 Sep 2023 13:56:52 -0700
Subject: LSM: Helpers for attribute names and filling lsm_ctx
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add lsm_name_to_attr(), which translates a text string to a
LSM_ATTR value if one is available.

Add lsm_fill_user_ctx(), which fills a struct lsm_ctx, including
the trailing attribute value.

Both are used in module specific components of LSM system calls.

Signed-off-by: Casey Schaufler <casey@schaufler-ca.com>
Reviewed-by: John Johansen <john.johansen@canonical.com>
Reviewed-by: Serge Hallyn <serge@hallyn.com>
Reviewed-by: Mickaël Salaün <mic@digikod.net>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 include/linux/security.h | 14 ++++++++++++++
 security/lsm_syscalls.c  | 24 ++++++++++++++++++++++++
 security/security.c      | 41 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 79 insertions(+)

(limited to 'include')

diff --git a/include/linux/security.h b/include/linux/security.h
index dd1fe487385d..334f75aa7289 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -32,6 +32,7 @@
 #include <linux/string.h>
 #include <linux/mm.h>
 #include <linux/sockptr.h>
+#include <uapi/linux/lsm.h>
 
 struct linux_binprm;
 struct cred;
@@ -264,6 +265,7 @@ int unregister_blocking_lsm_notifier(struct notifier_block *nb);
 /* prototypes */
 extern int security_init(void);
 extern int early_security_init(void);
+extern u64 lsm_name_to_attr(const char *name);
 
 /* Security operations */
 int security_binder_set_context_mgr(const struct cred *mgr);
@@ -490,6 +492,8 @@ int security_inode_notifysecctx(struct inode *inode, void *ctx, u32 ctxlen);
 int security_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen);
 int security_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen);
 int security_locked_down(enum lockdown_reason what);
+int lsm_fill_user_ctx(struct lsm_ctx __user *ctx, void *context,
+		      size_t context_size, u64 id, u64 flags);
 #else /* CONFIG_SECURITY */
 
 static inline int call_blocking_lsm_notifier(enum lsm_event event, void *data)
@@ -507,6 +511,11 @@ static inline  int unregister_blocking_lsm_notifier(struct notifier_block *nb)
 	return 0;
 }
 
+static inline u64 lsm_name_to_attr(const char *name)
+{
+	return LSM_ATTR_UNDEF;
+}
+
 static inline void security_free_mnt_opts(void **mnt_opts)
 {
 }
@@ -1415,6 +1424,11 @@ static inline int security_locked_down(enum lockdown_reason what)
 {
 	return 0;
 }
+static inline int lsm_fill_user_ctx(struct lsm_ctx __user *ctx, void *context,
+				    size_t context_size, u64 id, u64 flags)
+{
+	return -EOPNOTSUPP;
+}
 #endif	/* CONFIG_SECURITY */
 
 #if defined(CONFIG_SECURITY) && defined(CONFIG_WATCH_QUEUE)
diff --git a/security/lsm_syscalls.c b/security/lsm_syscalls.c
index 329aaca5efc0..5d391b1f7e69 100644
--- a/security/lsm_syscalls.c
+++ b/security/lsm_syscalls.c
@@ -17,6 +17,30 @@
 #include <linux/lsm_hooks.h>
 #include <uapi/linux/lsm.h>
 
+/**
+ * lsm_name_to_attr - map an LSM attribute name to its ID
+ * @name: name of the attribute
+ *
+ * Returns the LSM attribute value associated with @name, or 0 if
+ * there is no mapping.
+ */
+u64 lsm_name_to_attr(const char *name)
+{
+	if (!strcmp(name, "current"))
+		return LSM_ATTR_CURRENT;
+	if (!strcmp(name, "exec"))
+		return LSM_ATTR_EXEC;
+	if (!strcmp(name, "fscreate"))
+		return LSM_ATTR_FSCREATE;
+	if (!strcmp(name, "keycreate"))
+		return LSM_ATTR_KEYCREATE;
+	if (!strcmp(name, "prev"))
+		return LSM_ATTR_PREV;
+	if (!strcmp(name, "sockcreate"))
+		return LSM_ATTR_SOCKCREATE;
+	return LSM_ATTR_UNDEF;
+}
+
 /**
  * sys_lsm_set_self_attr - Set current task's security module attribute
  * @attr: which attribute to set
diff --git a/security/security.c b/security/security.c
index 9757d009113f..988483fcf153 100644
--- a/security/security.c
+++ b/security/security.c
@@ -771,6 +771,47 @@ static int lsm_superblock_alloc(struct super_block *sb)
 	return 0;
 }
 
+/**
+ * lsm_fill_user_ctx - Fill a user space lsm_ctx structure
+ * @ctx: an LSM context to be filled
+ * @context: the new context value
+ * @context_size: the size of the new context value
+ * @id: LSM id
+ * @flags: LSM defined flags
+ *
+ * Fill all of the fields in a user space lsm_ctx structure.
+ * Caller is assumed to have verified that @ctx has enough space
+ * for @context.
+ *
+ * Returns 0 on success, -EFAULT on a copyout error, -ENOMEM
+ * if memory can't be allocated.
+ */
+int lsm_fill_user_ctx(struct lsm_ctx __user *ctx, void *context,
+		      size_t context_size, u64 id, u64 flags)
+{
+	struct lsm_ctx *lctx;
+	size_t locallen = struct_size(lctx, ctx, context_size);
+	int rc = 0;
+
+	lctx = kzalloc(locallen, GFP_KERNEL);
+	if (lctx == NULL)
+		return -ENOMEM;
+
+	lctx->id = id;
+	lctx->flags = flags;
+	lctx->ctx_len = context_size;
+	lctx->len = locallen;
+
+	memcpy(lctx->ctx, context, context_size);
+
+	if (copy_to_user(ctx, lctx, locallen))
+		rc = -EFAULT;
+
+	kfree(lctx);
+
+	return rc;
+}
+
 /*
  * The default value of the LSM hook is defined in linux/lsm_hook_defs.h and
  * can be accessed with:
-- 
cgit v1.2.3


From edd71f8e266c7ba15eedfec338864e53ddde1c25 Mon Sep 17 00:00:00 2001
From: Paul Moore <paul@paul-moore.com>
Date: Wed, 18 Oct 2023 17:41:41 -0400
Subject: lsm: drop LSM_ID_IMA

When IMA becomes a proper LSM we will reintroduce an appropriate
LSM ID, but drop it from the userspace API for now in an effort
to put an end to debates around the naming of the LSM ID macro.

Reviewed-by: Roberto Sassu <roberto.sassu@huawei.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 include/uapi/linux/lsm.h | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/lsm.h b/include/uapi/linux/lsm.h
index eeda59a77c02..f0386880a78e 100644
--- a/include/uapi/linux/lsm.h
+++ b/include/uapi/linux/lsm.h
@@ -54,14 +54,13 @@ struct lsm_ctx {
 #define LSM_ID_SELINUX		101
 #define LSM_ID_SMACK		102
 #define LSM_ID_TOMOYO		103
-#define LSM_ID_IMA		104
-#define LSM_ID_APPARMOR		105
-#define LSM_ID_YAMA		106
-#define LSM_ID_LOADPIN		107
-#define LSM_ID_SAFESETID	108
-#define LSM_ID_LOCKDOWN		109
-#define LSM_ID_BPF		110
-#define LSM_ID_LANDLOCK		111
+#define LSM_ID_APPARMOR		104
+#define LSM_ID_YAMA		105
+#define LSM_ID_LOADPIN		106
+#define LSM_ID_SAFESETID	107
+#define LSM_ID_LOCKDOWN		108
+#define LSM_ID_BPF		109
+#define LSM_ID_LANDLOCK		110
 
 /*
  * LSM_ATTR_XXX definitions identify different LSM attributes
-- 
cgit v1.2.3


From d7cf3412a9f6c547e5ee443fa7644e08898aa3e2 Mon Sep 17 00:00:00 2001
From: Paul Moore <paul@paul-moore.com>
Date: Tue, 24 Oct 2023 14:44:00 -0400
Subject: lsm: consolidate buffer size handling into lsm_fill_user_ctx()

While we have a lsm_fill_user_ctx() helper function designed to make
life easier for LSMs which return lsm_ctx structs to userspace, we
didn't include all of the buffer length safety checks and buffer
padding adjustments in the helper.  This led to code duplication
across the different LSMs and the possibility for mistakes across the
different LSM subsystems.  In order to reduce code duplication and
decrease the chances of silly mistakes, we're consolidating all of
this code into the lsm_fill_user_ctx() helper.

The buffer padding is also modified from a fixed 8-byte alignment to
an alignment that matches the word length of the machine
(BITS_PER_LONG / 8).

Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 include/linux/security.h   |  9 ++++----
 security/apparmor/lsm.c    | 15 +++----------
 security/security.c        | 55 ++++++++++++++++++++++++++--------------------
 security/selinux/hooks.c   | 44 +++++++++++++++++++------------------
 security/smack/smack_lsm.c | 23 +++++--------------
 5 files changed, 68 insertions(+), 78 deletions(-)

(limited to 'include')

diff --git a/include/linux/security.h b/include/linux/security.h
index 334f75aa7289..750130a7b9dd 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -492,8 +492,8 @@ int security_inode_notifysecctx(struct inode *inode, void *ctx, u32 ctxlen);
 int security_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen);
 int security_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen);
 int security_locked_down(enum lockdown_reason what);
-int lsm_fill_user_ctx(struct lsm_ctx __user *ctx, void *context,
-		      size_t context_size, u64 id, u64 flags);
+int lsm_fill_user_ctx(struct lsm_ctx __user *uctx, size_t *uctx_len,
+		      void *val, size_t val_len, u64 id, u64 flags);
 #else /* CONFIG_SECURITY */
 
 static inline int call_blocking_lsm_notifier(enum lsm_event event, void *data)
@@ -1424,8 +1424,9 @@ static inline int security_locked_down(enum lockdown_reason what)
 {
 	return 0;
 }
-static inline int lsm_fill_user_ctx(struct lsm_ctx __user *ctx, void *context,
-				    size_t context_size, u64 id, u64 flags)
+static inline int lsm_fill_user_ctx(struct lsm_ctx __user *uctx,
+				    size_t *uctx_len, void *val, size_t val_len,
+				    u64 id, u64 flags)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index 8165f80c10ff..332198e0a017 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -782,7 +782,6 @@ static int apparmor_getselfattr(unsigned int attr, struct lsm_ctx __user *lx,
 	int error = -ENOENT;
 	struct aa_task_ctx *ctx = task_ctx(current);
 	struct aa_label *label = NULL;
-	size_t total_len = 0;
 	char *value;
 
 	switch (attr) {
@@ -804,22 +803,14 @@ static int apparmor_getselfattr(unsigned int attr, struct lsm_ctx __user *lx,
 
 	if (label) {
 		error = aa_getprocattr(label, &value, false);
-		if (error > 0) {
-			total_len = ALIGN(struct_size(lx, ctx, error), 8);
-			if (total_len > *size)
-				error = -E2BIG;
-			else if (lx)
-				error = lsm_fill_user_ctx(lx, value, error,
-							  LSM_ID_APPARMOR, 0);
-			else
-				error = 1;
-		}
+		if (error > 0)
+			error = lsm_fill_user_ctx(lx, size, value, error,
+						  LSM_ID_APPARMOR, 0);
 		kfree(value);
 	}
 
 	aa_put_label(label);
 
-	*size = total_len;
 	if (error < 0)
 		return error;
 	return 1;
diff --git a/security/security.c b/security/security.c
index 78e7ffcc9f6c..86f7a1995991 100644
--- a/security/security.c
+++ b/security/security.c
@@ -772,42 +772,49 @@ static int lsm_superblock_alloc(struct super_block *sb)
 
 /**
  * lsm_fill_user_ctx - Fill a user space lsm_ctx structure
- * @ctx: an LSM context to be filled
- * @context: the new context value
- * @context_size: the size of the new context value
+ * @uctx: a userspace LSM context to be filled
+ * @uctx_len: available uctx size (input), used uctx size (output)
+ * @val: the new LSM context value
+ * @val_len: the size of the new LSM context value
  * @id: LSM id
  * @flags: LSM defined flags
  *
- * Fill all of the fields in a user space lsm_ctx structure.
- * Caller is assumed to have verified that @ctx has enough space
- * for @context.
+ * Fill all of the fields in a userspace lsm_ctx structure.
  *
- * Returns 0 on success, -EFAULT on a copyout error, -ENOMEM
- * if memory can't be allocated.
+ * Returns 0 on success, -E2BIG if userspace buffer is not large enough,
+ * -EFAULT on a copyout error, -ENOMEM if memory can't be allocated.
  */
-int lsm_fill_user_ctx(struct lsm_ctx __user *ctx, void *context,
-		      size_t context_size, u64 id, u64 flags)
+int lsm_fill_user_ctx(struct lsm_ctx __user *uctx, size_t *uctx_len,
+		      void *val, size_t val_len,
+		      u64 id, u64 flags)
 {
-	struct lsm_ctx *lctx;
-	size_t locallen = struct_size(lctx, ctx, context_size);
+	struct lsm_ctx *nctx = NULL;
+	size_t nctx_len;
 	int rc = 0;
 
-	lctx = kzalloc(locallen, GFP_KERNEL);
-	if (lctx == NULL)
-		return -ENOMEM;
-
-	lctx->id = id;
-	lctx->flags = flags;
-	lctx->ctx_len = context_size;
-	lctx->len = locallen;
+	nctx_len = ALIGN(struct_size(nctx, ctx, val_len), BITS_PER_LONG / 8);
+	if (nctx_len > *uctx_len) {
+		rc = -E2BIG;
+		goto out;
+	}
 
-	memcpy(lctx->ctx, context, context_size);
+	nctx = kzalloc(nctx_len, GFP_KERNEL);
+	if (nctx == NULL) {
+		rc = -ENOMEM;
+		goto out;
+	}
+	nctx->id = id;
+	nctx->flags = flags;
+	nctx->len = nctx_len;
+	nctx->ctx_len = val_len;
+	memcpy(nctx->ctx, val, val_len);
 
-	if (copy_to_user(ctx, lctx, locallen))
+	if (copy_to_user(uctx, nctx, nctx_len))
 		rc = -EFAULT;
 
-	kfree(lctx);
-
+out:
+	kfree(nctx);
+	*uctx_len = nctx_len;
 	return rc;
 }
 
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index b6c7930a3ab2..942f2b8c4ebb 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -6486,30 +6486,32 @@ abort_change:
 	return error;
 }
 
+/**
+ * selinux_getselfattr - Get SELinux current task attributes
+ * @attr: the requested attribute
+ * @ctx: buffer to receive the result
+ * @size: buffer size (input), buffer size used (output)
+ * @flags: unused
+ *
+ * Fill the passed user space @ctx with the details of the requested
+ * attribute.
+ *
+ * Returns the number of attributes on success, an error code otherwise.
+ * There will only ever be one attribute.
+ */
 static int selinux_getselfattr(unsigned int attr, struct lsm_ctx __user *ctx,
 			       size_t *size, u32 flags)
 {
-	char *value;
-	size_t total_len;
-	int len;
-	int rc = 0;
-
-	len = selinux_lsm_getattr(attr, current, &value);
-	if (len < 0)
-		return len;
-
-	total_len = ALIGN(struct_size(ctx, ctx, len), 8);
-
-	if (total_len > *size)
-		rc = -E2BIG;
-	else if (ctx)
-		rc = lsm_fill_user_ctx(ctx, value, len, LSM_ID_SELINUX, 0);
-
-	kfree(value);
-	*size = total_len;
-	if (rc < 0)
-		return rc;
-	return 1;
+	int rc;
+	char *val;
+	int val_len;
+
+	val_len = selinux_lsm_getattr(attr, current, &val);
+	if (val_len < 0)
+		return val_len;
+	rc = lsm_fill_user_ctx(ctx, size, val, val_len, LSM_ID_SELINUX, 0);
+	kfree(val);
+	return (!rc ? 1 : rc);
 }
 
 static int selinux_setselfattr(unsigned int attr, struct lsm_ctx *ctx,
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index 12160d060cc1..99664c8cf867 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -3642,28 +3642,17 @@ static void smack_d_instantiate(struct dentry *opt_dentry, struct inode *inode)
 static int smack_getselfattr(unsigned int attr, struct lsm_ctx __user *ctx,
 			     size_t *size, u32 flags)
 {
-	struct smack_known *skp = smk_of_current();
-	int total;
-	int slen;
 	int rc;
+	struct smack_known *skp;
 
 	if (attr != LSM_ATTR_CURRENT)
 		return -EOPNOTSUPP;
 
-	slen = strlen(skp->smk_known) + 1;
-	total = ALIGN(slen + sizeof(*ctx), 8);
-	if (total > *size)
-		rc = -E2BIG;
-	else if (ctx)
-		rc = lsm_fill_user_ctx(ctx, skp->smk_known, slen, LSM_ID_SMACK,
-				       0);
-	else
-		rc = 1;
-
-	*size = total;
-	if (rc >= 0)
-		return 1;
-	return rc;
+	skp = smk_of_current();
+	rc = lsm_fill_user_ctx(ctx, size,
+			       skp->smk_known, strlen(skp->smk_known) + 1,
+			       LSM_ID_SMACK, 0);
+	return (!rc ? 1 : rc);
 }
 
 /**
-- 
cgit v1.2.3


From 48f996d4adf15a0a0af8b8184d3ec6042a684ea4 Mon Sep 17 00:00:00 2001
From: Chandramohan Akula <chandramohan.akula@broadcom.com>
Date: Mon, 23 Oct 2023 07:03:23 -0700
Subject: RDMA/bnxt_re: Remove roundup_pow_of_two depth for all hardware queue
 resources

Rounding up the queue depth to power of two is not a hardware requirement.
In order to optimize the per connection memory usage, removing drivers
implementation which round up to the queue depths to the power of 2.

Implements a mask to maintain backward compatibility with older
library.

Signed-off-by: Chandramohan Akula <chandramohan.akula@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://lore.kernel.org/r/1698069803-1787-3-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/bnxt_re/ib_verbs.c | 57 +++++++++++++++++++++-----------
 drivers/infiniband/hw/bnxt_re/ib_verbs.h |  7 ++++
 include/uapi/rdma/bnxt_re-abi.h          |  9 +++++
 3 files changed, 54 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index faa88d12ee86..b2467de721dc 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -1184,7 +1184,8 @@ fail:
 }
 
 static int bnxt_re_init_rq_attr(struct bnxt_re_qp *qp,
-				struct ib_qp_init_attr *init_attr)
+				struct ib_qp_init_attr *init_attr,
+				struct bnxt_re_ucontext *uctx)
 {
 	struct bnxt_qplib_dev_attr *dev_attr;
 	struct bnxt_qplib_qp *qplqp;
@@ -1213,7 +1214,7 @@ static int bnxt_re_init_rq_attr(struct bnxt_re_qp *qp,
 		/* Allocate 1 more than what's provided so posting max doesn't
 		 * mean empty.
 		 */
-		entries = roundup_pow_of_two(init_attr->cap.max_recv_wr + 1);
+		entries = bnxt_re_init_depth(init_attr->cap.max_recv_wr + 1, uctx);
 		rq->max_wqe = min_t(u32, entries, dev_attr->max_qp_wqes + 1);
 		rq->q_full_delta = 0;
 		rq->sg_info.pgsize = PAGE_SIZE;
@@ -1243,7 +1244,7 @@ static void bnxt_re_adjust_gsi_rq_attr(struct bnxt_re_qp *qp)
 
 static int bnxt_re_init_sq_attr(struct bnxt_re_qp *qp,
 				struct ib_qp_init_attr *init_attr,
-				struct ib_udata *udata)
+				struct bnxt_re_ucontext *uctx)
 {
 	struct bnxt_qplib_dev_attr *dev_attr;
 	struct bnxt_qplib_qp *qplqp;
@@ -1272,7 +1273,7 @@ static int bnxt_re_init_sq_attr(struct bnxt_re_qp *qp,
 	/* Allocate 128 + 1 more than what's provided */
 	diff = (qplqp->wqe_mode == BNXT_QPLIB_WQE_MODE_VARIABLE) ?
 		0 : BNXT_QPLIB_RESERVED_QP_WRS;
-	entries = roundup_pow_of_two(entries + diff + 1);
+	entries = bnxt_re_init_depth(entries + diff + 1, uctx);
 	sq->max_wqe = min_t(u32, entries, dev_attr->max_qp_wqes + diff + 1);
 	sq->q_full_delta = diff + 1;
 	/*
@@ -1288,7 +1289,8 @@ static int bnxt_re_init_sq_attr(struct bnxt_re_qp *qp,
 }
 
 static void bnxt_re_adjust_gsi_sq_attr(struct bnxt_re_qp *qp,
-				       struct ib_qp_init_attr *init_attr)
+				       struct ib_qp_init_attr *init_attr,
+				       struct bnxt_re_ucontext *uctx)
 {
 	struct bnxt_qplib_dev_attr *dev_attr;
 	struct bnxt_qplib_qp *qplqp;
@@ -1300,7 +1302,7 @@ static void bnxt_re_adjust_gsi_sq_attr(struct bnxt_re_qp *qp,
 	dev_attr = &rdev->dev_attr;
 
 	if (!bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx)) {
-		entries = roundup_pow_of_two(init_attr->cap.max_send_wr + 1);
+		entries = bnxt_re_init_depth(init_attr->cap.max_send_wr + 1, uctx);
 		qplqp->sq.max_wqe = min_t(u32, entries,
 					  dev_attr->max_qp_wqes + 1);
 		qplqp->sq.q_full_delta = qplqp->sq.max_wqe -
@@ -1338,6 +1340,7 @@ static int bnxt_re_init_qp_attr(struct bnxt_re_qp *qp, struct bnxt_re_pd *pd,
 				struct ib_udata *udata)
 {
 	struct bnxt_qplib_dev_attr *dev_attr;
+	struct bnxt_re_ucontext *uctx;
 	struct bnxt_qplib_qp *qplqp;
 	struct bnxt_re_dev *rdev;
 	struct bnxt_re_cq *cq;
@@ -1347,6 +1350,7 @@ static int bnxt_re_init_qp_attr(struct bnxt_re_qp *qp, struct bnxt_re_pd *pd,
 	qplqp = &qp->qplib_qp;
 	dev_attr = &rdev->dev_attr;
 
+	uctx = rdma_udata_to_drv_context(udata, struct bnxt_re_ucontext, ib_uctx);
 	/* Setup misc params */
 	ether_addr_copy(qplqp->smac, rdev->netdev->dev_addr);
 	qplqp->pd = &pd->qplib_pd;
@@ -1388,18 +1392,18 @@ static int bnxt_re_init_qp_attr(struct bnxt_re_qp *qp, struct bnxt_re_pd *pd,
 	}
 
 	/* Setup RQ/SRQ */
-	rc = bnxt_re_init_rq_attr(qp, init_attr);
+	rc = bnxt_re_init_rq_attr(qp, init_attr, uctx);
 	if (rc)
 		goto out;
 	if (init_attr->qp_type == IB_QPT_GSI)
 		bnxt_re_adjust_gsi_rq_attr(qp);
 
 	/* Setup SQ */
-	rc = bnxt_re_init_sq_attr(qp, init_attr, udata);
+	rc = bnxt_re_init_sq_attr(qp, init_attr, uctx);
 	if (rc)
 		goto out;
 	if (init_attr->qp_type == IB_QPT_GSI)
-		bnxt_re_adjust_gsi_sq_attr(qp, init_attr);
+		bnxt_re_adjust_gsi_sq_attr(qp, init_attr, uctx);
 
 	if (udata) /* This will update DPI and qp_handle */
 		rc = bnxt_re_init_user_qp(rdev, pd, qp, udata);
@@ -1715,6 +1719,7 @@ int bnxt_re_create_srq(struct ib_srq *ib_srq,
 {
 	struct bnxt_qplib_dev_attr *dev_attr;
 	struct bnxt_qplib_nq *nq = NULL;
+	struct bnxt_re_ucontext *uctx;
 	struct bnxt_re_dev *rdev;
 	struct bnxt_re_srq *srq;
 	struct bnxt_re_pd *pd;
@@ -1739,13 +1744,14 @@ int bnxt_re_create_srq(struct ib_srq *ib_srq,
 		goto exit;
 	}
 
+	uctx = rdma_udata_to_drv_context(udata, struct bnxt_re_ucontext, ib_uctx);
 	srq->rdev = rdev;
 	srq->qplib_srq.pd = &pd->qplib_pd;
 	srq->qplib_srq.dpi = &rdev->dpi_privileged;
 	/* Allocate 1 more than what's provided so posting max doesn't
 	 * mean empty
 	 */
-	entries = roundup_pow_of_two(srq_init_attr->attr.max_wr + 1);
+	entries = bnxt_re_init_depth(srq_init_attr->attr.max_wr + 1, uctx);
 	if (entries > dev_attr->max_srq_wqes + 1)
 		entries = dev_attr->max_srq_wqes + 1;
 	srq->qplib_srq.max_wqe = entries;
@@ -2103,6 +2109,9 @@ int bnxt_re_modify_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr,
 		qp->qplib_qp.max_dest_rd_atomic = qp_attr->max_dest_rd_atomic;
 	}
 	if (qp_attr_mask & IB_QP_CAP) {
+		struct bnxt_re_ucontext *uctx =
+			rdma_udata_to_drv_context(udata, struct bnxt_re_ucontext, ib_uctx);
+
 		qp->qplib_qp.modify_flags |=
 				CMDQ_MODIFY_QP_MODIFY_MASK_SQ_SIZE |
 				CMDQ_MODIFY_QP_MODIFY_MASK_RQ_SIZE |
@@ -2119,7 +2128,7 @@ int bnxt_re_modify_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr,
 				  "Create QP failed - max exceeded");
 			return -EINVAL;
 		}
-		entries = roundup_pow_of_two(qp_attr->cap.max_send_wr);
+		entries = bnxt_re_init_depth(qp_attr->cap.max_send_wr, uctx);
 		qp->qplib_qp.sq.max_wqe = min_t(u32, entries,
 						dev_attr->max_qp_wqes + 1);
 		qp->qplib_qp.sq.q_full_delta = qp->qplib_qp.sq.max_wqe -
@@ -2132,7 +2141,7 @@ int bnxt_re_modify_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr,
 		qp->qplib_qp.sq.q_full_delta -= 1;
 		qp->qplib_qp.sq.max_sge = qp_attr->cap.max_send_sge;
 		if (qp->qplib_qp.rq.max_wqe) {
-			entries = roundup_pow_of_two(qp_attr->cap.max_recv_wr);
+			entries = bnxt_re_init_depth(qp_attr->cap.max_recv_wr, uctx);
 			qp->qplib_qp.rq.max_wqe =
 				min_t(u32, entries, dev_attr->max_qp_wqes + 1);
 			qp->qplib_qp.rq.q_full_delta = qp->qplib_qp.rq.max_wqe -
@@ -2920,9 +2929,11 @@ int bnxt_re_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata)
 int bnxt_re_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 		      struct ib_udata *udata)
 {
+	struct bnxt_re_cq *cq = container_of(ibcq, struct bnxt_re_cq, ib_cq);
 	struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibcq->device, ibdev);
+	struct bnxt_re_ucontext *uctx =
+		rdma_udata_to_drv_context(udata, struct bnxt_re_ucontext, ib_uctx);
 	struct bnxt_qplib_dev_attr *dev_attr = &rdev->dev_attr;
-	struct bnxt_re_cq *cq = container_of(ibcq, struct bnxt_re_cq, ib_cq);
 	int rc, entries;
 	int cqe = attr->cqe;
 	struct bnxt_qplib_nq *nq = NULL;
@@ -2941,7 +2952,7 @@ int bnxt_re_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 	cq->rdev = rdev;
 	cq->qplib_cq.cq_handle = (u64)(unsigned long)(&cq->qplib_cq);
 
-	entries = roundup_pow_of_two(cqe + 1);
+	entries = bnxt_re_init_depth(cqe + 1, uctx);
 	if (entries > dev_attr->max_cq_wqes + 1)
 		entries = dev_attr->max_cq_wqes + 1;
 
@@ -2949,8 +2960,6 @@ int bnxt_re_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 	cq->qplib_cq.sg_info.pgshft = PAGE_SHIFT;
 	if (udata) {
 		struct bnxt_re_cq_req req;
-		struct bnxt_re_ucontext *uctx = rdma_udata_to_drv_context(
-			udata, struct bnxt_re_ucontext, ib_uctx);
 		if (ib_copy_from_udata(&req, udata, sizeof(req))) {
 			rc = -EFAULT;
 			goto fail;
@@ -3072,12 +3081,11 @@ int bnxt_re_resize_cq(struct ib_cq *ibcq, int cqe, struct ib_udata *udata)
 		return -EINVAL;
 	}
 
-	entries = roundup_pow_of_two(cqe + 1);
+	uctx = rdma_udata_to_drv_context(udata, struct bnxt_re_ucontext, ib_uctx);
+	entries = bnxt_re_init_depth(cqe + 1, uctx);
 	if (entries > dev_attr->max_cq_wqes + 1)
 		entries = dev_attr->max_cq_wqes + 1;
 
-	uctx = rdma_udata_to_drv_context(udata, struct bnxt_re_ucontext,
-					 ib_uctx);
 	/* uverbs consumer */
 	if (ib_copy_from_udata(&req, udata, sizeof(req))) {
 		rc = -EFAULT;
@@ -4108,6 +4116,7 @@ int bnxt_re_alloc_ucontext(struct ib_ucontext *ctx, struct ib_udata *udata)
 	struct bnxt_qplib_dev_attr *dev_attr = &rdev->dev_attr;
 	struct bnxt_re_user_mmap_entry *entry;
 	struct bnxt_re_uctx_resp resp = {};
+	struct bnxt_re_uctx_req ureq = {};
 	u32 chip_met_rev_num = 0;
 	int rc;
 
@@ -4157,6 +4166,16 @@ int bnxt_re_alloc_ucontext(struct ib_ucontext *ctx, struct ib_udata *udata)
 	if (rdev->pacing.dbr_pacing)
 		resp.comp_mask |= BNXT_RE_UCNTX_CMASK_DBR_PACING_ENABLED;
 
+	if (udata->inlen >= sizeof(ureq)) {
+		rc = ib_copy_from_udata(&ureq, udata, min(udata->inlen, sizeof(ureq)));
+		if (rc)
+			goto cfail;
+		if (ureq.comp_mask & BNXT_RE_COMP_MASK_REQ_UCNTX_POW2_SUPPORT) {
+			resp.comp_mask |= BNXT_RE_UCNTX_CMASK_POW2_DISABLED;
+			uctx->cmask |= BNXT_RE_UCNTX_CMASK_POW2_DISABLED;
+		}
+	}
+
 	rc = ib_copy_to_udata(udata, &resp, min(udata->outlen, sizeof(resp)));
 	if (rc) {
 		ibdev_err(ibdev, "Failed to copy user context");
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.h b/drivers/infiniband/hw/bnxt_re/ib_verbs.h
index 84715b7e7a4e..98baea98fc17 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.h
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.h
@@ -140,6 +140,7 @@ struct bnxt_re_ucontext {
 	void			*shpg;
 	spinlock_t		sh_lock;	/* protect shpg */
 	struct rdma_user_mmap_entry *shpage_mmap;
+	u64 cmask;
 };
 
 enum bnxt_re_mmap_flag {
@@ -167,6 +168,12 @@ static inline u16 bnxt_re_get_rwqe_size(int nsge)
 	return sizeof(struct rq_wqe_hdr) + (nsge * sizeof(struct sq_sge));
 }
 
+static inline u32 bnxt_re_init_depth(u32 ent, struct bnxt_re_ucontext *uctx)
+{
+	return uctx ? (uctx->cmask & BNXT_RE_UCNTX_CMASK_POW2_DISABLED) ?
+		ent : roundup_pow_of_two(ent) : ent;
+}
+
 int bnxt_re_query_device(struct ib_device *ibdev,
 			 struct ib_device_attr *ib_attr,
 			 struct ib_udata *udata);
diff --git a/include/uapi/rdma/bnxt_re-abi.h b/include/uapi/rdma/bnxt_re-abi.h
index 6e7c67a0cca3..a1b896d6d940 100644
--- a/include/uapi/rdma/bnxt_re-abi.h
+++ b/include/uapi/rdma/bnxt_re-abi.h
@@ -54,6 +54,7 @@ enum {
 	BNXT_RE_UCNTX_CMASK_HAVE_MODE = 0x02ULL,
 	BNXT_RE_UCNTX_CMASK_WC_DPI_ENABLED = 0x04ULL,
 	BNXT_RE_UCNTX_CMASK_DBR_PACING_ENABLED = 0x08ULL,
+	BNXT_RE_UCNTX_CMASK_POW2_DISABLED = 0x10ULL,
 };
 
 enum bnxt_re_wqe_mode {
@@ -62,6 +63,14 @@ enum bnxt_re_wqe_mode {
 	BNXT_QPLIB_WQE_MODE_INVALID	= 0x02,
 };
 
+enum {
+	BNXT_RE_COMP_MASK_REQ_UCNTX_POW2_SUPPORT = 0x01,
+};
+
+struct bnxt_re_uctx_req {
+	__aligned_u64 comp_mask;
+};
+
 struct bnxt_re_uctx_resp {
 	__u32 dev_id;
 	__u32 max_qp;
-- 
cgit v1.2.3


From 8569992d64b8f750e34b7858eac5d7daaf0f80fd Mon Sep 17 00:00:00 2001
From: Chao Peng <chao.p.peng@linux.intel.com>
Date: Fri, 27 Oct 2023 11:21:45 -0700
Subject: KVM: Use gfn instead of hva for mmu_notifier_retry

Currently in mmu_notifier invalidate path, hva range is recorded and then
checked against by mmu_invalidate_retry_hva() in the page fault handling
path. However, for the soon-to-be-introduced private memory, a page fault
may not have a hva associated, checking gfn(gpa) makes more sense.

For existing hva based shared memory, gfn is expected to also work. The
only downside is when aliasing multiple gfns to a single hva, the
current algorithm of checking multiple ranges could result in a much
larger range being rejected. Such aliasing should be uncommon, so the
impact is expected small.

Suggested-by: Sean Christopherson <seanjc@google.com>
Cc: Xu Yilun <yilun.xu@intel.com>
Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
[sean: convert vmx_set_apic_access_page_addr() to gfn-based API]
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Xu Yilun <yilun.xu@linux.intel.com>
Message-Id: <20231027182217.3615211-4-seanjc@google.com>
Reviewed-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c   | 10 ++++++----
 arch/x86/kvm/vmx/vmx.c   | 11 +++++------
 include/linux/kvm_host.h | 33 +++++++++++++++++++++------------
 virt/kvm/kvm_main.c      | 43 ++++++++++++++++++++++++++++++++++---------
 4 files changed, 66 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index b0f01d605617..b2d916f786ca 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3056,7 +3056,7 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep)
  *
  * There are several ways to safely use this helper:
  *
- * - Check mmu_invalidate_retry_hva() after grabbing the mapping level, before
+ * - Check mmu_invalidate_retry_gfn() after grabbing the mapping level, before
  *   consuming it.  In this case, mmu_lock doesn't need to be held during the
  *   lookup, but it does need to be held while checking the MMU notifier.
  *
@@ -4366,7 +4366,7 @@ static bool is_page_fault_stale(struct kvm_vcpu *vcpu,
 		return true;
 
 	return fault->slot &&
-	       mmu_invalidate_retry_hva(vcpu->kvm, fault->mmu_seq, fault->hva);
+	       mmu_invalidate_retry_gfn(vcpu->kvm, fault->mmu_seq, fault->gfn);
 }
 
 static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
@@ -6260,7 +6260,9 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
 
 	write_lock(&kvm->mmu_lock);
 
-	kvm_mmu_invalidate_begin(kvm, 0, -1ul);
+	kvm_mmu_invalidate_begin(kvm);
+
+	kvm_mmu_invalidate_range_add(kvm, gfn_start, gfn_end);
 
 	flush = kvm_rmap_zap_gfn_range(kvm, gfn_start, gfn_end);
 
@@ -6270,7 +6272,7 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
 	if (flush)
 		kvm_flush_remote_tlbs_range(kvm, gfn_start, gfn_end - gfn_start);
 
-	kvm_mmu_invalidate_end(kvm, 0, -1ul);
+	kvm_mmu_invalidate_end(kvm);
 
 	write_unlock(&kvm->mmu_lock);
 }
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index be20a60047b1..40e3780d73ae 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6757,10 +6757,10 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu)
 		return;
 
 	/*
-	 * Grab the memslot so that the hva lookup for the mmu_notifier retry
-	 * is guaranteed to use the same memslot as the pfn lookup, i.e. rely
-	 * on the pfn lookup's validation of the memslot to ensure a valid hva
-	 * is used for the retry check.
+	 * Explicitly grab the memslot using KVM's internal slot ID to ensure
+	 * KVM doesn't unintentionally grab a userspace memslot.  It _should_
+	 * be impossible for userspace to create a memslot for the APIC when
+	 * APICv is enabled, but paranoia won't hurt in this case.
 	 */
 	slot = id_to_memslot(slots, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT);
 	if (!slot || slot->flags & KVM_MEMSLOT_INVALID)
@@ -6785,8 +6785,7 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu)
 		return;
 
 	read_lock(&vcpu->kvm->mmu_lock);
-	if (mmu_invalidate_retry_hva(kvm, mmu_seq,
-				     gfn_to_hva_memslot(slot, gfn))) {
+	if (mmu_invalidate_retry_gfn(kvm, mmu_seq, gfn)) {
 		kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu);
 		read_unlock(&vcpu->kvm->mmu_lock);
 		goto out;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index fb6c6109fdca..11d091688346 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -787,8 +787,8 @@ struct kvm {
 	struct mmu_notifier mmu_notifier;
 	unsigned long mmu_invalidate_seq;
 	long mmu_invalidate_in_progress;
-	unsigned long mmu_invalidate_range_start;
-	unsigned long mmu_invalidate_range_end;
+	gfn_t mmu_invalidate_range_start;
+	gfn_t mmu_invalidate_range_end;
 #endif
 	struct list_head devices;
 	u64 manual_dirty_log_protect;
@@ -1392,10 +1392,9 @@ void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc);
 void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc);
 #endif
 
-void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start,
-			      unsigned long end);
-void kvm_mmu_invalidate_end(struct kvm *kvm, unsigned long start,
-			    unsigned long end);
+void kvm_mmu_invalidate_begin(struct kvm *kvm);
+void kvm_mmu_invalidate_range_add(struct kvm *kvm, gfn_t start, gfn_t end);
+void kvm_mmu_invalidate_end(struct kvm *kvm);
 
 long kvm_arch_dev_ioctl(struct file *filp,
 			unsigned int ioctl, unsigned long arg);
@@ -1970,9 +1969,9 @@ static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq)
 	return 0;
 }
 
-static inline int mmu_invalidate_retry_hva(struct kvm *kvm,
+static inline int mmu_invalidate_retry_gfn(struct kvm *kvm,
 					   unsigned long mmu_seq,
-					   unsigned long hva)
+					   gfn_t gfn)
 {
 	lockdep_assert_held(&kvm->mmu_lock);
 	/*
@@ -1981,10 +1980,20 @@ static inline int mmu_invalidate_retry_hva(struct kvm *kvm,
 	 * that might be being invalidated. Note that it may include some false
 	 * positives, due to shortcuts when handing concurrent invalidations.
 	 */
-	if (unlikely(kvm->mmu_invalidate_in_progress) &&
-	    hva >= kvm->mmu_invalidate_range_start &&
-	    hva < kvm->mmu_invalidate_range_end)
-		return 1;
+	if (unlikely(kvm->mmu_invalidate_in_progress)) {
+		/*
+		 * Dropping mmu_lock after bumping mmu_invalidate_in_progress
+		 * but before updating the range is a KVM bug.
+		 */
+		if (WARN_ON_ONCE(kvm->mmu_invalidate_range_start == INVALID_GPA ||
+				 kvm->mmu_invalidate_range_end == INVALID_GPA))
+			return 1;
+
+		if (gfn >= kvm->mmu_invalidate_range_start &&
+		    gfn < kvm->mmu_invalidate_range_end)
+			return 1;
+	}
+
 	if (kvm->mmu_invalidate_seq != mmu_seq)
 		return 1;
 	return 0;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 5a97e6c7d9c2..9cc57b23ec81 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -543,9 +543,7 @@ static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn)
 
 typedef bool (*gfn_handler_t)(struct kvm *kvm, struct kvm_gfn_range *range);
 
-typedef void (*on_lock_fn_t)(struct kvm *kvm, unsigned long start,
-			     unsigned long end);
-
+typedef void (*on_lock_fn_t)(struct kvm *kvm);
 typedef void (*on_unlock_fn_t)(struct kvm *kvm);
 
 struct kvm_mmu_notifier_range {
@@ -637,7 +635,8 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
 				locked = true;
 				KVM_MMU_LOCK(kvm);
 				if (!IS_KVM_NULL_FN(range->on_lock))
-					range->on_lock(kvm, range->start, range->end);
+					range->on_lock(kvm);
+
 				if (IS_KVM_NULL_FN(range->handler))
 					break;
 			}
@@ -742,16 +741,29 @@ static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
 	kvm_handle_hva_range(mn, address, address + 1, arg, kvm_change_spte_gfn);
 }
 
-void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start,
-			      unsigned long end)
+void kvm_mmu_invalidate_begin(struct kvm *kvm)
 {
+	lockdep_assert_held_write(&kvm->mmu_lock);
 	/*
 	 * The count increase must become visible at unlock time as no
 	 * spte can be established without taking the mmu_lock and
 	 * count is also read inside the mmu_lock critical section.
 	 */
 	kvm->mmu_invalidate_in_progress++;
+
 	if (likely(kvm->mmu_invalidate_in_progress == 1)) {
+		kvm->mmu_invalidate_range_start = INVALID_GPA;
+		kvm->mmu_invalidate_range_end = INVALID_GPA;
+	}
+}
+
+void kvm_mmu_invalidate_range_add(struct kvm *kvm, gfn_t start, gfn_t end)
+{
+	lockdep_assert_held_write(&kvm->mmu_lock);
+
+	WARN_ON_ONCE(!kvm->mmu_invalidate_in_progress);
+
+	if (likely(kvm->mmu_invalidate_range_start == INVALID_GPA)) {
 		kvm->mmu_invalidate_range_start = start;
 		kvm->mmu_invalidate_range_end = end;
 	} else {
@@ -771,6 +783,12 @@ void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start,
 	}
 }
 
+static bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
+{
+	kvm_mmu_invalidate_range_add(kvm, range->start, range->end);
+	return kvm_unmap_gfn_range(kvm, range);
+}
+
 static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 					const struct mmu_notifier_range *range)
 {
@@ -778,7 +796,7 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	const struct kvm_mmu_notifier_range hva_range = {
 		.start		= range->start,
 		.end		= range->end,
-		.handler	= kvm_unmap_gfn_range,
+		.handler	= kvm_mmu_unmap_gfn_range,
 		.on_lock	= kvm_mmu_invalidate_begin,
 		.on_unlock	= kvm_arch_guest_memory_reclaimed,
 		.flush_on_ret	= true,
@@ -817,9 +835,10 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	return 0;
 }
 
-void kvm_mmu_invalidate_end(struct kvm *kvm, unsigned long start,
-			    unsigned long end)
+void kvm_mmu_invalidate_end(struct kvm *kvm)
 {
+	lockdep_assert_held_write(&kvm->mmu_lock);
+
 	/*
 	 * This sequence increase will notify the kvm page fault that
 	 * the page that is going to be mapped in the spte could have
@@ -834,6 +853,12 @@ void kvm_mmu_invalidate_end(struct kvm *kvm, unsigned long start,
 	 */
 	kvm->mmu_invalidate_in_progress--;
 	KVM_BUG_ON(kvm->mmu_invalidate_in_progress < 0, kvm);
+
+	/*
+	 * Assert that at least one range was added between start() and end().
+	 * Not adding a range isn't fatal, but it is a KVM bug.
+	 */
+	WARN_ON_ONCE(kvm->mmu_invalidate_range_start == INVALID_GPA);
 }
 
 static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
-- 
cgit v1.2.3


From f128cf8cfbecccf95e891ae90d9c917df5117c7a Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 27 Oct 2023 11:21:49 -0700
Subject: KVM: Convert KVM_ARCH_WANT_MMU_NOTIFIER to
 CONFIG_KVM_GENERIC_MMU_NOTIFIER

Convert KVM_ARCH_WANT_MMU_NOTIFIER into a Kconfig and select it where
appropriate to effectively maintain existing behavior.  Using a proper
Kconfig will simplify building more functionality on top of KVM's
mmu_notifier infrastructure.

Add a forward declaration of kvm_gfn_range to kvm_types.h so that
including arch/powerpc/include/asm/kvm_ppc.h's with CONFIG_KVM=n doesn't
generate warnings due to kvm_gfn_range being undeclared.  PPC defines
hooks for PR vs. HV without guarding them via #ifdeffery, e.g.

  bool (*unmap_gfn_range)(struct kvm *kvm, struct kvm_gfn_range *range);
  bool (*age_gfn)(struct kvm *kvm, struct kvm_gfn_range *range);
  bool (*test_age_gfn)(struct kvm *kvm, struct kvm_gfn_range *range);
  bool (*set_spte_gfn)(struct kvm *kvm, struct kvm_gfn_range *range);

Alternatively, PPC could forward declare kvm_gfn_range, but there's no
good reason not to define it in common KVM.

Acked-by: Anup Patel <anup@brainfault.org>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Message-Id: <20231027182217.3615211-8-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/arm64/include/asm/kvm_host.h     |  2 --
 arch/arm64/kvm/Kconfig                |  2 +-
 arch/loongarch/include/asm/kvm_host.h |  1 -
 arch/loongarch/kvm/Kconfig            |  2 +-
 arch/mips/include/asm/kvm_host.h      |  2 --
 arch/mips/kvm/Kconfig                 |  2 +-
 arch/powerpc/include/asm/kvm_host.h   |  2 --
 arch/powerpc/kvm/Kconfig              |  8 ++++----
 arch/powerpc/kvm/powerpc.c            |  4 +---
 arch/riscv/include/asm/kvm_host.h     |  2 --
 arch/riscv/kvm/Kconfig                |  2 +-
 arch/x86/include/asm/kvm_host.h       |  2 --
 arch/x86/kvm/Kconfig                  |  2 +-
 include/linux/kvm_host.h              |  6 +++---
 include/linux/kvm_types.h             |  1 +
 virt/kvm/Kconfig                      |  4 ++++
 virt/kvm/kvm_main.c                   | 10 +++++-----
 17 files changed, 23 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 5653d3553e3e..9029fe09f3f6 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -954,8 +954,6 @@ int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu,
 int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu,
 			      struct kvm_vcpu_events *events);
 
-#define KVM_ARCH_WANT_MMU_NOTIFIER
-
 void kvm_arm_halt_guest(struct kvm *kvm);
 void kvm_arm_resume_guest(struct kvm *kvm);
 
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 83c1e09be42e..1a777715199f 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -22,7 +22,7 @@ menuconfig KVM
 	bool "Kernel-based Virtual Machine (KVM) support"
 	depends on HAVE_KVM
 	select KVM_GENERIC_HARDWARE_ENABLING
-	select MMU_NOTIFIER
+	select KVM_GENERIC_MMU_NOTIFIER
 	select PREEMPT_NOTIFIERS
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
 	select KVM_MMIO
diff --git a/arch/loongarch/include/asm/kvm_host.h b/arch/loongarch/include/asm/kvm_host.h
index 11328700d4fa..b108301c2e5a 100644
--- a/arch/loongarch/include/asm/kvm_host.h
+++ b/arch/loongarch/include/asm/kvm_host.h
@@ -183,7 +183,6 @@ void kvm_flush_tlb_all(void);
 void kvm_flush_tlb_gpa(struct kvm_vcpu *vcpu, unsigned long gpa);
 int kvm_handle_mm_fault(struct kvm_vcpu *vcpu, unsigned long badv, bool write);
 
-#define KVM_ARCH_WANT_MMU_NOTIFIER
 void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
 int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, bool blockable);
 int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
diff --git a/arch/loongarch/kvm/Kconfig b/arch/loongarch/kvm/Kconfig
index fda425babfb2..f22bae89b07d 100644
--- a/arch/loongarch/kvm/Kconfig
+++ b/arch/loongarch/kvm/Kconfig
@@ -26,9 +26,9 @@ config KVM
 	select HAVE_KVM_VCPU_ASYNC_IOCTL
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select KVM_GENERIC_HARDWARE_ENABLING
+	select KVM_GENERIC_MMU_NOTIFIER
 	select KVM_MMIO
 	select KVM_XFER_TO_GUEST_WORK
-	select MMU_NOTIFIER
 	select PREEMPT_NOTIFIERS
 	help
 	  Support hosting virtualized guest machines using
diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index 54a85f1d4f2c..179f320cc231 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -810,8 +810,6 @@ int kvm_mips_mkclean_gpa_pt(struct kvm *kvm, gfn_t start_gfn, gfn_t end_gfn);
 pgd_t *kvm_pgd_alloc(void);
 void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu);
 
-#define KVM_ARCH_WANT_MMU_NOTIFIER
-
 /* Emulation */
 enum emulation_result update_pc(struct kvm_vcpu *vcpu, u32 cause);
 int kvm_get_badinstr(u32 *opc, struct kvm_vcpu *vcpu, u32 *out);
diff --git a/arch/mips/kvm/Kconfig b/arch/mips/kvm/Kconfig
index a8cdba75f98d..c04987d2ed2e 100644
--- a/arch/mips/kvm/Kconfig
+++ b/arch/mips/kvm/Kconfig
@@ -25,7 +25,7 @@ config KVM
 	select HAVE_KVM_EVENTFD
 	select HAVE_KVM_VCPU_ASYNC_IOCTL
 	select KVM_MMIO
-	select MMU_NOTIFIER
+	select KVM_GENERIC_MMU_NOTIFIER
 	select INTERVAL_TREE
 	select KVM_GENERIC_HARDWARE_ENABLING
 	help
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 14ee0dece853..4b5c3f2acf78 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -62,8 +62,6 @@
 
 #include <linux/mmu_notifier.h>
 
-#define KVM_ARCH_WANT_MMU_NOTIFIER
-
 #define HPTEG_CACHE_NUM			(1 << 15)
 #define HPTEG_HASH_BITS_PTE		13
 #define HPTEG_HASH_BITS_PTE_LONG	12
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 902611954200..b33358ee6424 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -42,7 +42,7 @@ config KVM_BOOK3S_64_HANDLER
 config KVM_BOOK3S_PR_POSSIBLE
 	bool
 	select KVM_MMIO
-	select MMU_NOTIFIER
+	select KVM_GENERIC_MMU_NOTIFIER
 
 config KVM_BOOK3S_HV_POSSIBLE
 	bool
@@ -85,7 +85,7 @@ config KVM_BOOK3S_64_HV
 	tristate "KVM for POWER7 and later using hypervisor mode in host"
 	depends on KVM_BOOK3S_64 && PPC_POWERNV
 	select KVM_BOOK3S_HV_POSSIBLE
-	select MMU_NOTIFIER
+	select KVM_GENERIC_MMU_NOTIFIER
 	select CMA
 	help
 	  Support running unmodified book3s_64 guest kernels in
@@ -194,7 +194,7 @@ config KVM_E500V2
 	depends on !CONTEXT_TRACKING_USER
 	select KVM
 	select KVM_MMIO
-	select MMU_NOTIFIER
+	select KVM_GENERIC_MMU_NOTIFIER
 	help
 	  Support running unmodified E500 guest kernels in virtual machines on
 	  E500v2 host processors.
@@ -211,7 +211,7 @@ config KVM_E500MC
 	select KVM
 	select KVM_MMIO
 	select KVM_BOOKE_HV
-	select MMU_NOTIFIER
+	select KVM_GENERIC_MMU_NOTIFIER
 	help
 	  Support running unmodified E500MC/E5500/E6500 guest kernels in
 	  virtual machines on E500MC/E5500/E6500 host processors.
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 8d3ec483bc2b..aac75c98a956 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -632,9 +632,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		break;
 #endif
 	case KVM_CAP_SYNC_MMU:
-#if !defined(CONFIG_MMU_NOTIFIER) || !defined(KVM_ARCH_WANT_MMU_NOTIFIER)
-		BUILD_BUG();
-#endif
+		BUILD_BUG_ON(!IS_ENABLED(CONFIG_KVM_GENERIC_MMU_NOTIFIER));
 		r = 1;
 		break;
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h
index 0eefd9c991ae..6964dd235e97 100644
--- a/arch/riscv/include/asm/kvm_host.h
+++ b/arch/riscv/include/asm/kvm_host.h
@@ -267,8 +267,6 @@ struct kvm_vcpu_arch {
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
 
-#define KVM_ARCH_WANT_MMU_NOTIFIER
-
 #define KVM_RISCV_GSTAGE_TLB_MIN_ORDER		12
 
 void kvm_riscv_local_hfence_gvma_vmid_gpa(unsigned long vmid,
diff --git a/arch/riscv/kvm/Kconfig b/arch/riscv/kvm/Kconfig
index dfc237d7875b..ae2e05f050ec 100644
--- a/arch/riscv/kvm/Kconfig
+++ b/arch/riscv/kvm/Kconfig
@@ -30,7 +30,7 @@ config KVM
 	select KVM_GENERIC_HARDWARE_ENABLING
 	select KVM_MMIO
 	select KVM_XFER_TO_GUEST_WORK
-	select MMU_NOTIFIER
+	select KVM_GENERIC_MMU_NOTIFIER
 	select PREEMPT_NOTIFIERS
 	help
 	  Support hosting virtualized guest machines.
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index d7036982332e..6f559fb75e6d 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -2141,8 +2141,6 @@ enum {
 # define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, 0)
 #endif
 
-#define KVM_ARCH_WANT_MMU_NOTIFIER
-
 int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v);
 int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
 int kvm_cpu_has_extint(struct kvm_vcpu *v);
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 950c12868d30..e61383674c75 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -24,7 +24,7 @@ config KVM
 	depends on HIGH_RES_TIMERS
 	depends on X86_LOCAL_APIC
 	select PREEMPT_NOTIFIERS
-	select MMU_NOTIFIER
+	select KVM_GENERIC_MMU_NOTIFIER
 	select HAVE_KVM_IRQCHIP
 	select HAVE_KVM_PFNCACHE
 	select HAVE_KVM_IRQFD
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 11d091688346..5faba69403ac 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -253,7 +253,7 @@ bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
 #endif
 
-#ifdef KVM_ARCH_WANT_MMU_NOTIFIER
+#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 union kvm_mmu_notifier_arg {
 	pte_t pte;
 };
@@ -783,7 +783,7 @@ struct kvm {
 	struct hlist_head irq_ack_notifier_list;
 #endif
 
-#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 	struct mmu_notifier mmu_notifier;
 	unsigned long mmu_invalidate_seq;
 	long mmu_invalidate_in_progress;
@@ -1946,7 +1946,7 @@ extern const struct _kvm_stats_desc kvm_vm_stats_desc[];
 extern const struct kvm_stats_header kvm_vcpu_stats_header;
 extern const struct _kvm_stats_desc kvm_vcpu_stats_desc[];
 
-#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq)
 {
 	if (unlikely(kvm->mmu_invalidate_in_progress))
diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
index 6f4737d5046a..9d1f7835d8c1 100644
--- a/include/linux/kvm_types.h
+++ b/include/linux/kvm_types.h
@@ -6,6 +6,7 @@
 struct kvm;
 struct kvm_async_pf;
 struct kvm_device_ops;
+struct kvm_gfn_range;
 struct kvm_interrupt;
 struct kvm_irq_routing_table;
 struct kvm_memory_slot;
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 484d0873061c..ecae2914c97e 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -92,3 +92,7 @@ config HAVE_KVM_PM_NOTIFIER
 
 config KVM_GENERIC_HARDWARE_ENABLING
        bool
+
+config KVM_GENERIC_MMU_NOTIFIER
+       select MMU_NOTIFIER
+       bool
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 5422ce20dcba..dc81279ea385 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -535,7 +535,7 @@ void kvm_destroy_vcpus(struct kvm *kvm)
 }
 EXPORT_SYMBOL_GPL(kvm_destroy_vcpus);
 
-#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn)
 {
 	return container_of(mn, struct kvm, mmu_notifier);
@@ -962,14 +962,14 @@ static int kvm_init_mmu_notifier(struct kvm *kvm)
 	return mmu_notifier_register(&kvm->mmu_notifier, current->mm);
 }
 
-#else  /* !(CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER) */
+#else  /* !CONFIG_KVM_GENERIC_MMU_NOTIFIER */
 
 static int kvm_init_mmu_notifier(struct kvm *kvm)
 {
 	return 0;
 }
 
-#endif /* CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER */
+#endif /* CONFIG_KVM_GENERIC_MMU_NOTIFIER */
 
 #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
 static int kvm_pm_notifier_call(struct notifier_block *bl,
@@ -1289,7 +1289,7 @@ out_err:
 out_err_no_debugfs:
 	kvm_coalesced_mmio_free(kvm);
 out_no_coalesced_mmio:
-#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 	if (kvm->mmu_notifier.ops)
 		mmu_notifier_unregister(&kvm->mmu_notifier, current->mm);
 #endif
@@ -1349,7 +1349,7 @@ static void kvm_destroy_vm(struct kvm *kvm)
 		kvm->buses[i] = NULL;
 	}
 	kvm_coalesced_mmio_free(kvm);
-#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 	mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm);
 	/*
 	 * At this point, pending calls to invalidate_range_start()
-- 
cgit v1.2.3


From bb58b90b1a8f753b582055adaf448214a8e22c31 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 27 Oct 2023 11:21:50 -0700
Subject: KVM: Introduce KVM_SET_USER_MEMORY_REGION2

Introduce a "version 2" of KVM_SET_USER_MEMORY_REGION so that additional
information can be supplied without setting userspace up to fail.  The
padding in the new kvm_userspace_memory_region2 structure will be used to
pass a file descriptor in addition to the userspace_addr, i.e. allow
userspace to point at a file descriptor and map memory into a guest that
is NOT mapped into host userspace.

Alternatively, KVM could simply add "struct kvm_userspace_memory_region2"
without a new ioctl(), but as Paolo pointed out, adding a new ioctl()
makes detection of bad flags a bit more robust, e.g. if the new fd field
is guarded only by a flag and not a new ioctl(), then a userspace bug
(setting a "bad" flag) would generate out-of-bounds access instead of an
-EINVAL error.

Cc: Jarkko Sakkinen <jarkko@kernel.org>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Message-Id: <20231027182217.3615211-9-seanjc@google.com>
Acked-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virt/kvm/api.rst | 22 ++++++++++++++++
 arch/x86/kvm/x86.c             |  2 +-
 include/linux/kvm_host.h       |  4 +--
 include/uapi/linux/kvm.h       | 13 ++++++++++
 virt/kvm/kvm_main.c            | 57 ++++++++++++++++++++++++++++++++++++------
 5 files changed, 87 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 7025b3751027..9edd9e436bab 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6192,6 +6192,28 @@ to know what fields can be changed for the system register described by
 ``op0, op1, crn, crm, op2``. KVM rejects ID register values that describe a
 superset of the features supported by the system.
 
+4.140 KVM_SET_USER_MEMORY_REGION2
+---------------------------------
+
+:Capability: KVM_CAP_USER_MEMORY2
+:Architectures: all
+:Type: vm ioctl
+:Parameters: struct kvm_userspace_memory_region2 (in)
+:Returns: 0 on success, -1 on error
+
+::
+
+  struct kvm_userspace_memory_region2 {
+	__u32 slot;
+	__u32 flags;
+	__u64 guest_phys_addr;
+	__u64 memory_size; /* bytes */
+	__u64 userspace_addr; /* start of the userspace allocated memory */
+	__u64 pad[16];
+  };
+
+See KVM_SET_USER_MEMORY_REGION.
+
 5. The kvm_run structure
 ========================
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2c924075f6f1..7b389f27dffc 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -12576,7 +12576,7 @@ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa,
 	}
 
 	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
-		struct kvm_userspace_memory_region m;
+		struct kvm_userspace_memory_region2 m;
 
 		m.slot = id | (i << 16);
 		m.flags = 0;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 5faba69403ac..4e741ff27af3 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1146,9 +1146,9 @@ enum kvm_mr_change {
 };
 
 int kvm_set_memory_region(struct kvm *kvm,
-			  const struct kvm_userspace_memory_region *mem);
+			  const struct kvm_userspace_memory_region2 *mem);
 int __kvm_set_memory_region(struct kvm *kvm,
-			    const struct kvm_userspace_memory_region *mem);
+			    const struct kvm_userspace_memory_region2 *mem);
 void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot);
 void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen);
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 211b86de35ac..308cc70bd6ab 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -95,6 +95,16 @@ struct kvm_userspace_memory_region {
 	__u64 userspace_addr; /* start of the userspace allocated memory */
 };
 
+/* for KVM_SET_USER_MEMORY_REGION2 */
+struct kvm_userspace_memory_region2 {
+	__u32 slot;
+	__u32 flags;
+	__u64 guest_phys_addr;
+	__u64 memory_size;
+	__u64 userspace_addr;
+	__u64 pad[16];
+};
+
 /*
  * The bit 0 ~ bit 15 of kvm_userspace_memory_region::flags are visible for
  * userspace, other bits are reserved for kvm internal use which are defined
@@ -1201,6 +1211,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE 228
 #define KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES 229
 #define KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES 230
+#define KVM_CAP_USER_MEMORY2 231
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1483,6 +1494,8 @@ struct kvm_vfio_spapr_tce {
 					struct kvm_userspace_memory_region)
 #define KVM_SET_TSS_ADDR          _IO(KVMIO,   0x47)
 #define KVM_SET_IDENTITY_MAP_ADDR _IOW(KVMIO,  0x48, __u64)
+#define KVM_SET_USER_MEMORY_REGION2 _IOW(KVMIO, 0x49, \
+					 struct kvm_userspace_memory_region2)
 
 /* enable ucontrol for s390 */
 struct kvm_s390_ucas_mapping {
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index dc81279ea385..756b94ecd511 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1580,7 +1580,15 @@ static void kvm_replace_memslot(struct kvm *kvm,
 	}
 }
 
-static int check_memory_region_flags(const struct kvm_userspace_memory_region *mem)
+/*
+ * Flags that do not access any of the extra space of struct
+ * kvm_userspace_memory_region2.  KVM_SET_USER_MEMORY_REGION_V1_FLAGS
+ * only allows these.
+ */
+#define KVM_SET_USER_MEMORY_REGION_V1_FLAGS \
+	(KVM_MEM_LOG_DIRTY_PAGES | KVM_MEM_READONLY)
+
+static int check_memory_region_flags(const struct kvm_userspace_memory_region2 *mem)
 {
 	u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES;
 
@@ -1982,7 +1990,7 @@ static bool kvm_check_memslot_overlap(struct kvm_memslots *slots, int id,
  * Must be called holding kvm->slots_lock for write.
  */
 int __kvm_set_memory_region(struct kvm *kvm,
-			    const struct kvm_userspace_memory_region *mem)
+			    const struct kvm_userspace_memory_region2 *mem)
 {
 	struct kvm_memory_slot *old, *new;
 	struct kvm_memslots *slots;
@@ -2086,7 +2094,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 EXPORT_SYMBOL_GPL(__kvm_set_memory_region);
 
 int kvm_set_memory_region(struct kvm *kvm,
-			  const struct kvm_userspace_memory_region *mem)
+			  const struct kvm_userspace_memory_region2 *mem)
 {
 	int r;
 
@@ -2098,7 +2106,7 @@ int kvm_set_memory_region(struct kvm *kvm,
 EXPORT_SYMBOL_GPL(kvm_set_memory_region);
 
 static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
-					  struct kvm_userspace_memory_region *mem)
+					  struct kvm_userspace_memory_region2 *mem)
 {
 	if ((u16)mem->slot >= KVM_USER_MEM_SLOTS)
 		return -EINVAL;
@@ -4568,6 +4576,7 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 {
 	switch (arg) {
 	case KVM_CAP_USER_MEMORY:
+	case KVM_CAP_USER_MEMORY2:
 	case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
 	case KVM_CAP_JOIN_MEMORY_REGIONS_WORKS:
 	case KVM_CAP_INTERNAL_ERROR_DATA:
@@ -4823,6 +4832,14 @@ static int kvm_vm_ioctl_get_stats_fd(struct kvm *kvm)
 	return fd;
 }
 
+#define SANITY_CHECK_MEM_REGION_FIELD(field)					\
+do {										\
+	BUILD_BUG_ON(offsetof(struct kvm_userspace_memory_region, field) !=		\
+		     offsetof(struct kvm_userspace_memory_region2, field));	\
+	BUILD_BUG_ON(sizeof_field(struct kvm_userspace_memory_region, field) !=		\
+		     sizeof_field(struct kvm_userspace_memory_region2, field));	\
+} while (0)
+
 static long kvm_vm_ioctl(struct file *filp,
 			   unsigned int ioctl, unsigned long arg)
 {
@@ -4845,15 +4862,39 @@ static long kvm_vm_ioctl(struct file *filp,
 		r = kvm_vm_ioctl_enable_cap_generic(kvm, &cap);
 		break;
 	}
+	case KVM_SET_USER_MEMORY_REGION2:
 	case KVM_SET_USER_MEMORY_REGION: {
-		struct kvm_userspace_memory_region kvm_userspace_mem;
+		struct kvm_userspace_memory_region2 mem;
+		unsigned long size;
+
+		if (ioctl == KVM_SET_USER_MEMORY_REGION) {
+			/*
+			 * Fields beyond struct kvm_userspace_memory_region shouldn't be
+			 * accessed, but avoid leaking kernel memory in case of a bug.
+			 */
+			memset(&mem, 0, sizeof(mem));
+			size = sizeof(struct kvm_userspace_memory_region);
+		} else {
+			size = sizeof(struct kvm_userspace_memory_region2);
+		}
+
+		/* Ensure the common parts of the two structs are identical. */
+		SANITY_CHECK_MEM_REGION_FIELD(slot);
+		SANITY_CHECK_MEM_REGION_FIELD(flags);
+		SANITY_CHECK_MEM_REGION_FIELD(guest_phys_addr);
+		SANITY_CHECK_MEM_REGION_FIELD(memory_size);
+		SANITY_CHECK_MEM_REGION_FIELD(userspace_addr);
 
 		r = -EFAULT;
-		if (copy_from_user(&kvm_userspace_mem, argp,
-						sizeof(kvm_userspace_mem)))
+		if (copy_from_user(&mem, argp, size))
+			goto out;
+
+		r = -EINVAL;
+		if (ioctl == KVM_SET_USER_MEMORY_REGION &&
+		    (mem.flags & ~KVM_SET_USER_MEMORY_REGION_V1_FLAGS))
 			goto out;
 
-		r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem);
+		r = kvm_vm_ioctl_set_memory_region(kvm, &mem);
 		break;
 	}
 	case KVM_GET_DIRTY_LOG: {
-- 
cgit v1.2.3


From 16f95f3b95caded251a0440051e44a2fbe9e5f55 Mon Sep 17 00:00:00 2001
From: Chao Peng <chao.p.peng@linux.intel.com>
Date: Fri, 27 Oct 2023 11:21:51 -0700
Subject: KVM: Add KVM_EXIT_MEMORY_FAULT exit to report faults to userspace

Add a new KVM exit type to allow userspace to handle memory faults that
KVM cannot resolve, but that userspace *may* be able to handle (without
terminating the guest).

KVM will initially use KVM_EXIT_MEMORY_FAULT to report implicit
conversions between private and shared memory.  With guest private memory,
there will be two kind of memory conversions:

  - explicit conversion: happens when the guest explicitly calls into KVM
    to map a range (as private or shared)

  - implicit conversion: happens when the guest attempts to access a gfn
    that is configured in the "wrong" state (private vs. shared)

On x86 (first architecture to support guest private memory), explicit
conversions will be reported via KVM_EXIT_HYPERCALL+KVM_HC_MAP_GPA_RANGE,
but reporting KVM_EXIT_HYPERCALL for implicit conversions is undesriable
as there is (obviously) no hypercall, and there is no guarantee that the
guest actually intends to convert between private and shared, i.e. what
KVM thinks is an implicit conversion "request" could actually be the
result of a guest code bug.

KVM_EXIT_MEMORY_FAULT will be used to report memory faults that appear to
be implicit conversions.

Note!  To allow for future possibilities where KVM reports
KVM_EXIT_MEMORY_FAULT and fills run->memory_fault on _any_ unresolved
fault, KVM returns "-EFAULT" (-1 with errno == EFAULT from userspace's
perspective), not '0'!  Due to historical baggage within KVM, exiting to
userspace with '0' from deep callstacks, e.g. in emulation paths, is
infeasible as doing so would require a near-complete overhaul of KVM,
whereas KVM already propagates -errno return codes to userspace even when
the -errno originated in a low level helper.

Report the gpa+size instead of a single gfn even though the initial usage
is expected to always report single pages.  It's entirely possible, likely
even, that KVM will someday support sub-page granularity faults, e.g.
Intel's sub-page protection feature allows for additional protections at
128-byte granularity.

Link: https://lore.kernel.org/all/20230908222905.1321305-5-amoorthy@google.com
Link: https://lore.kernel.org/all/ZQ3AmLO2SYv3DszH@google.com
Cc: Anish Moorthy <amoorthy@google.com>
Cc: David Matlack <dmatlack@google.com>
Suggested-by: Sean Christopherson <seanjc@google.com>
Co-developed-by: Yu Zhang <yu.c.zhang@linux.intel.com>
Signed-off-by: Yu Zhang <yu.c.zhang@linux.intel.com>
Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20231027182217.3615211-10-seanjc@google.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virt/kvm/api.rst | 41 +++++++++++++++++++++++++++++++++++++++++
 arch/x86/kvm/x86.c             |  1 +
 include/linux/kvm_host.h       | 11 +++++++++++
 include/uapi/linux/kvm.h       |  8 ++++++++
 4 files changed, 61 insertions(+)

(limited to 'include')

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 9edd9e436bab..27d945d5b4e4 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6846,6 +6846,26 @@ array field represents return values. The userspace should update the return
 values of SBI call before resuming the VCPU. For more details on RISC-V SBI
 spec refer, https://github.com/riscv/riscv-sbi-doc.
 
+::
+
+		/* KVM_EXIT_MEMORY_FAULT */
+		struct {
+			__u64 flags;
+			__u64 gpa;
+			__u64 size;
+		} memory_fault;
+
+KVM_EXIT_MEMORY_FAULT indicates the vCPU has encountered a memory fault that
+could not be resolved by KVM.  The 'gpa' and 'size' (in bytes) describe the
+guest physical address range [gpa, gpa + size) of the fault.  The 'flags' field
+describes properties of the faulting access that are likely pertinent.
+Currently, no flags are defined.
+
+Note!  KVM_EXIT_MEMORY_FAULT is unique among all KVM exit reasons in that it
+accompanies a return code of '-1', not '0'!  errno will always be set to EFAULT
+or EHWPOISON when KVM exits with KVM_EXIT_MEMORY_FAULT, userspace should assume
+kvm_run.exit_reason is stale/undefined for all other error numbers.
+
 ::
 
     /* KVM_EXIT_NOTIFY */
@@ -7880,6 +7900,27 @@ This capability is aimed to mitigate the threat that malicious VMs can
 cause CPU stuck (due to event windows don't open up) and make the CPU
 unavailable to host or other VMs.
 
+7.34 KVM_CAP_MEMORY_FAULT_INFO
+------------------------------
+
+:Architectures: x86
+:Returns: Informational only, -EINVAL on direct KVM_ENABLE_CAP.
+
+The presence of this capability indicates that KVM_RUN will fill
+kvm_run.memory_fault if KVM cannot resolve a guest page fault VM-Exit, e.g. if
+there is a valid memslot but no backing VMA for the corresponding host virtual
+address.
+
+The information in kvm_run.memory_fault is valid if and only if KVM_RUN returns
+an error with errno=EFAULT or errno=EHWPOISON *and* kvm_run.exit_reason is set
+to KVM_EXIT_MEMORY_FAULT.
+
+Note: Userspaces which attempt to resolve memory faults so that they can retry
+KVM_RUN are encouraged to guard against repeatedly receiving the same
+error/annotated fault.
+
+See KVM_EXIT_MEMORY_FAULT for more information.
+
 8. Other capabilities.
 ======================
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 7b389f27dffc..8f9d8939b63b 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4625,6 +4625,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_ENABLE_CAP:
 	case KVM_CAP_VM_DISABLE_NX_HUGE_PAGES:
 	case KVM_CAP_IRQFD_RESAMPLE:
+	case KVM_CAP_MEMORY_FAULT_INFO:
 		r = 1;
 		break;
 	case KVM_CAP_EXIT_HYPERCALL:
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 4e741ff27af3..96aa930536b1 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2327,4 +2327,15 @@ static inline void kvm_account_pgtable_pages(void *virt, int nr)
 /* Max number of entries allowed for each kvm dirty ring */
 #define  KVM_DIRTY_RING_MAX_ENTRIES  65536
 
+static inline void kvm_prepare_memory_fault_exit(struct kvm_vcpu *vcpu,
+						 gpa_t gpa, gpa_t size)
+{
+	vcpu->run->exit_reason = KVM_EXIT_MEMORY_FAULT;
+	vcpu->run->memory_fault.gpa = gpa;
+	vcpu->run->memory_fault.size = size;
+
+	/* Flags are not (yet) defined or communicated to userspace. */
+	vcpu->run->memory_fault.flags = 0;
+}
+
 #endif
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 308cc70bd6ab..59010a685007 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -275,6 +275,7 @@ struct kvm_xen_exit {
 #define KVM_EXIT_RISCV_CSR        36
 #define KVM_EXIT_NOTIFY           37
 #define KVM_EXIT_LOONGARCH_IOCSR  38
+#define KVM_EXIT_MEMORY_FAULT     39
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -528,6 +529,12 @@ struct kvm_run {
 #define KVM_NOTIFY_CONTEXT_INVALID	(1 << 0)
 			__u32 flags;
 		} notify;
+		/* KVM_EXIT_MEMORY_FAULT */
+		struct {
+			__u64 flags;
+			__u64 gpa;
+			__u64 size;
+		} memory_fault;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -1212,6 +1219,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES 229
 #define KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES 230
 #define KVM_CAP_USER_MEMORY2 231
+#define KVM_CAP_MEMORY_FAULT_INFO 232
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
-- 
cgit v1.2.3


From 5a475554db1e476a14216e742ea2bdb77362d5d5 Mon Sep 17 00:00:00 2001
From: Chao Peng <chao.p.peng@linux.intel.com>
Date: Fri, 27 Oct 2023 11:21:55 -0700
Subject: KVM: Introduce per-page memory attributes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In confidential computing usages, whether a page is private or shared is
necessary information for KVM to perform operations like page fault
handling, page zapping etc. There are other potential use cases for
per-page memory attributes, e.g. to make memory read-only (or no-exec,
or exec-only, etc.) without having to modify memslots.

Introduce the KVM_SET_MEMORY_ATTRIBUTES ioctl, advertised by
KVM_CAP_MEMORY_ATTRIBUTES, to allow userspace to set the per-page memory
attributes to a guest memory range.

Use an xarray to store the per-page attributes internally, with a naive,
not fully optimized implementation, i.e. prioritize correctness over
performance for the initial implementation.

Use bit 3 for the PRIVATE attribute so that KVM can use bits 0-2 for RWX
attributes/protections in the future, e.g. to give userspace fine-grained
control over read, write, and execute protections for guest memory.

Provide arch hooks for handling attribute changes before and after common
code sets the new attributes, e.g. x86 will use the "pre" hook to zap all
relevant mappings, and the "post" hook to track whether or not hugepages
can be used to map the range.

To simplify the implementation wrap the entire sequence with
kvm_mmu_invalidate_{begin,end}() even though the operation isn't strictly
guaranteed to be an invalidation.  For the initial use case, x86 *will*
always invalidate memory, and preventing arch code from creating new
mappings while the attributes are in flux makes it much easier to reason
about the correctness of consuming attributes.

It's possible that future usages may not require an invalidation, e.g.
if KVM ends up supporting RWX protections and userspace grants _more_
protections, but again opt for simplicity and punt optimizations to
if/when they are needed.

Suggested-by: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/all/Y2WB48kD0J4VGynX@google.com
Cc: Fuad Tabba <tabba@google.com>
Cc: Xu Yilun <yilun.xu@intel.com>
Cc: Mickaël Salaün <mic@digikod.net>
Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20231027182217.3615211-14-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virt/kvm/api.rst |  36 +++++++
 include/linux/kvm_host.h       |  19 ++++
 include/uapi/linux/kvm.h       |  13 +++
 virt/kvm/Kconfig               |   4 +
 virt/kvm/kvm_main.c            | 216 +++++++++++++++++++++++++++++++++++++++++
 5 files changed, 288 insertions(+)

(limited to 'include')

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 27d945d5b4e4..081ef09d3148 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6214,6 +6214,42 @@ superset of the features supported by the system.
 
 See KVM_SET_USER_MEMORY_REGION.
 
+4.141 KVM_SET_MEMORY_ATTRIBUTES
+-------------------------------
+
+:Capability: KVM_CAP_MEMORY_ATTRIBUTES
+:Architectures: x86
+:Type: vm ioctl
+:Parameters: struct kvm_memory_attributes (in)
+:Returns: 0 on success, <0 on error
+
+KVM_SET_MEMORY_ATTRIBUTES allows userspace to set memory attributes for a range
+of guest physical memory.
+
+::
+
+  struct kvm_memory_attributes {
+	__u64 address;
+	__u64 size;
+	__u64 attributes;
+	__u64 flags;
+  };
+
+  #define KVM_MEMORY_ATTRIBUTE_PRIVATE           (1ULL << 3)
+
+The address and size must be page aligned.  The supported attributes can be
+retrieved via ioctl(KVM_CHECK_EXTENSION) on KVM_CAP_MEMORY_ATTRIBUTES.  If
+executed on a VM, KVM_CAP_MEMORY_ATTRIBUTES precisely returns the attributes
+supported by that VM.  If executed at system scope, KVM_CAP_MEMORY_ATTRIBUTES
+returns all attributes supported by KVM.  The only attribute defined at this
+time is KVM_MEMORY_ATTRIBUTE_PRIVATE, which marks the associated gfn as being
+guest private memory.
+
+Note, there is no "get" API.  Userspace is responsible for explicitly tracking
+the state of a gfn/page as needed.
+
+The "flags" field is reserved for future extensions and must be '0'.
+
 5. The kvm_run structure
 ========================
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 96aa930536b1..68a144cb7dbc 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -256,6 +256,7 @@ int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
 #ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 union kvm_mmu_notifier_arg {
 	pte_t pte;
+	unsigned long attributes;
 };
 
 struct kvm_gfn_range {
@@ -806,6 +807,10 @@ struct kvm {
 
 #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
 	struct notifier_block pm_notifier;
+#endif
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+	/* Protected by slots_locks (for writes) and RCU (for reads) */
+	struct xarray mem_attr_array;
 #endif
 	char stats_id[KVM_STATS_NAME_SIZE];
 };
@@ -2338,4 +2343,18 @@ static inline void kvm_prepare_memory_fault_exit(struct kvm_vcpu *vcpu,
 	vcpu->run->memory_fault.flags = 0;
 }
 
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+static inline unsigned long kvm_get_memory_attributes(struct kvm *kvm, gfn_t gfn)
+{
+	return xa_to_value(xa_load(&kvm->mem_attr_array, gfn));
+}
+
+bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
+				     unsigned long attrs);
+bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
+					struct kvm_gfn_range *range);
+bool kvm_arch_post_set_memory_attributes(struct kvm *kvm,
+					 struct kvm_gfn_range *range);
+#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */
+
 #endif
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 59010a685007..e8d167e54980 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1220,6 +1220,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES 230
 #define KVM_CAP_USER_MEMORY2 231
 #define KVM_CAP_MEMORY_FAULT_INFO 232
+#define KVM_CAP_MEMORY_ATTRIBUTES 233
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -2288,4 +2289,16 @@ struct kvm_s390_zpci_op {
 /* flags for kvm_s390_zpci_op->u.reg_aen.flags */
 #define KVM_S390_ZPCIOP_REGAEN_HOST    (1 << 0)
 
+/* Available with KVM_CAP_MEMORY_ATTRIBUTES */
+#define KVM_SET_MEMORY_ATTRIBUTES              _IOW(KVMIO,  0xd2, struct kvm_memory_attributes)
+
+struct kvm_memory_attributes {
+	__u64 address;
+	__u64 size;
+	__u64 attributes;
+	__u64 flags;
+};
+
+#define KVM_MEMORY_ATTRIBUTE_PRIVATE           (1ULL << 3)
+
 #endif /* __LINUX_KVM_H */
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index ecae2914c97e..5bd7fcaf9089 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -96,3 +96,7 @@ config KVM_GENERIC_HARDWARE_ENABLING
 config KVM_GENERIC_MMU_NOTIFIER
        select MMU_NOTIFIER
        bool
+
+config KVM_GENERIC_MEMORY_ATTRIBUTES
+       select KVM_GENERIC_MMU_NOTIFIER
+       bool
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 7f3291dec7a6..f1a575d39b3b 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1211,6 +1211,9 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 	spin_lock_init(&kvm->mn_invalidate_lock);
 	rcuwait_init(&kvm->mn_memslots_update_rcuwait);
 	xa_init(&kvm->vcpu_array);
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+	xa_init(&kvm->mem_attr_array);
+#endif
 
 	INIT_LIST_HEAD(&kvm->gpc_list);
 	spin_lock_init(&kvm->gpc_lock);
@@ -1391,6 +1394,9 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	}
 	cleanup_srcu_struct(&kvm->irq_srcu);
 	cleanup_srcu_struct(&kvm->srcu);
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+	xa_destroy(&kvm->mem_attr_array);
+#endif
 	kvm_arch_free_vm(kvm);
 	preempt_notifier_dec();
 	hardware_disable_all();
@@ -2397,6 +2403,200 @@ static int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm,
 }
 #endif /* CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */
 
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+/*
+ * Returns true if _all_ gfns in the range [@start, @end) have attributes
+ * matching @attrs.
+ */
+bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
+				     unsigned long attrs)
+{
+	XA_STATE(xas, &kvm->mem_attr_array, start);
+	unsigned long index;
+	bool has_attrs;
+	void *entry;
+
+	rcu_read_lock();
+
+	if (!attrs) {
+		has_attrs = !xas_find(&xas, end - 1);
+		goto out;
+	}
+
+	has_attrs = true;
+	for (index = start; index < end; index++) {
+		do {
+			entry = xas_next(&xas);
+		} while (xas_retry(&xas, entry));
+
+		if (xas.xa_index != index || xa_to_value(entry) != attrs) {
+			has_attrs = false;
+			break;
+		}
+	}
+
+out:
+	rcu_read_unlock();
+	return has_attrs;
+}
+
+static u64 kvm_supported_mem_attributes(struct kvm *kvm)
+{
+	if (!kvm)
+		return KVM_MEMORY_ATTRIBUTE_PRIVATE;
+
+	return 0;
+}
+
+static __always_inline void kvm_handle_gfn_range(struct kvm *kvm,
+						 struct kvm_mmu_notifier_range *range)
+{
+	struct kvm_gfn_range gfn_range;
+	struct kvm_memory_slot *slot;
+	struct kvm_memslots *slots;
+	struct kvm_memslot_iter iter;
+	bool found_memslot = false;
+	bool ret = false;
+	int i;
+
+	gfn_range.arg = range->arg;
+	gfn_range.may_block = range->may_block;
+
+	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+		slots = __kvm_memslots(kvm, i);
+
+		kvm_for_each_memslot_in_gfn_range(&iter, slots, range->start, range->end) {
+			slot = iter.slot;
+			gfn_range.slot = slot;
+
+			gfn_range.start = max(range->start, slot->base_gfn);
+			gfn_range.end = min(range->end, slot->base_gfn + slot->npages);
+			if (gfn_range.start >= gfn_range.end)
+				continue;
+
+			if (!found_memslot) {
+				found_memslot = true;
+				KVM_MMU_LOCK(kvm);
+				if (!IS_KVM_NULL_FN(range->on_lock))
+					range->on_lock(kvm);
+			}
+
+			ret |= range->handler(kvm, &gfn_range);
+		}
+	}
+
+	if (range->flush_on_ret && ret)
+		kvm_flush_remote_tlbs(kvm);
+
+	if (found_memslot)
+		KVM_MMU_UNLOCK(kvm);
+}
+
+static bool kvm_pre_set_memory_attributes(struct kvm *kvm,
+					  struct kvm_gfn_range *range)
+{
+	/*
+	 * Unconditionally add the range to the invalidation set, regardless of
+	 * whether or not the arch callback actually needs to zap SPTEs.  E.g.
+	 * if KVM supports RWX attributes in the future and the attributes are
+	 * going from R=>RW, zapping isn't strictly necessary.  Unconditionally
+	 * adding the range allows KVM to require that MMU invalidations add at
+	 * least one range between begin() and end(), e.g. allows KVM to detect
+	 * bugs where the add() is missed.  Relaxing the rule *might* be safe,
+	 * but it's not obvious that allowing new mappings while the attributes
+	 * are in flux is desirable or worth the complexity.
+	 */
+	kvm_mmu_invalidate_range_add(kvm, range->start, range->end);
+
+	return kvm_arch_pre_set_memory_attributes(kvm, range);
+}
+
+/* Set @attributes for the gfn range [@start, @end). */
+static int kvm_vm_set_mem_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
+				     unsigned long attributes)
+{
+	struct kvm_mmu_notifier_range pre_set_range = {
+		.start = start,
+		.end = end,
+		.handler = kvm_pre_set_memory_attributes,
+		.on_lock = kvm_mmu_invalidate_begin,
+		.flush_on_ret = true,
+		.may_block = true,
+	};
+	struct kvm_mmu_notifier_range post_set_range = {
+		.start = start,
+		.end = end,
+		.arg.attributes = attributes,
+		.handler = kvm_arch_post_set_memory_attributes,
+		.on_lock = kvm_mmu_invalidate_end,
+		.may_block = true,
+	};
+	unsigned long i;
+	void *entry;
+	int r = 0;
+
+	entry = attributes ? xa_mk_value(attributes) : NULL;
+
+	mutex_lock(&kvm->slots_lock);
+
+	/* Nothing to do if the entire range as the desired attributes. */
+	if (kvm_range_has_memory_attributes(kvm, start, end, attributes))
+		goto out_unlock;
+
+	/*
+	 * Reserve memory ahead of time to avoid having to deal with failures
+	 * partway through setting the new attributes.
+	 */
+	for (i = start; i < end; i++) {
+		r = xa_reserve(&kvm->mem_attr_array, i, GFP_KERNEL_ACCOUNT);
+		if (r)
+			goto out_unlock;
+	}
+
+	kvm_handle_gfn_range(kvm, &pre_set_range);
+
+	for (i = start; i < end; i++) {
+		r = xa_err(xa_store(&kvm->mem_attr_array, i, entry,
+				    GFP_KERNEL_ACCOUNT));
+		KVM_BUG_ON(r, kvm);
+	}
+
+	kvm_handle_gfn_range(kvm, &post_set_range);
+
+out_unlock:
+	mutex_unlock(&kvm->slots_lock);
+
+	return r;
+}
+static int kvm_vm_ioctl_set_mem_attributes(struct kvm *kvm,
+					   struct kvm_memory_attributes *attrs)
+{
+	gfn_t start, end;
+
+	/* flags is currently not used. */
+	if (attrs->flags)
+		return -EINVAL;
+	if (attrs->attributes & ~kvm_supported_mem_attributes(kvm))
+		return -EINVAL;
+	if (attrs->size == 0 || attrs->address + attrs->size < attrs->address)
+		return -EINVAL;
+	if (!PAGE_ALIGNED(attrs->address) || !PAGE_ALIGNED(attrs->size))
+		return -EINVAL;
+
+	start = attrs->address >> PAGE_SHIFT;
+	end = (attrs->address + attrs->size) >> PAGE_SHIFT;
+
+	/*
+	 * xarray tracks data using "unsigned long", and as a result so does
+	 * KVM.  For simplicity, supports generic attributes only on 64-bit
+	 * architectures.
+	 */
+	BUILD_BUG_ON(sizeof(attrs->attributes) != sizeof(unsigned long));
+
+	return kvm_vm_set_mem_attributes(kvm, start, end, attrs->attributes);
+}
+#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */
+
 struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn)
 {
 	return __gfn_to_memslot(kvm_memslots(kvm), gfn);
@@ -4641,6 +4841,10 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 	case KVM_CAP_BINARY_STATS_FD:
 	case KVM_CAP_SYSTEM_EVENT_DATA:
 		return 1;
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+	case KVM_CAP_MEMORY_ATTRIBUTES:
+		return kvm_supported_mem_attributes(kvm);
+#endif
 	default:
 		break;
 	}
@@ -5034,6 +5238,18 @@ static long kvm_vm_ioctl(struct file *filp,
 		break;
 	}
 #endif /* CONFIG_HAVE_KVM_IRQ_ROUTING */
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+	case KVM_SET_MEMORY_ATTRIBUTES: {
+		struct kvm_memory_attributes attrs;
+
+		r = -EFAULT;
+		if (copy_from_user(&attrs, argp, sizeof(attrs)))
+			goto out;
+
+		r = kvm_vm_ioctl_set_mem_attributes(kvm, &attrs);
+		break;
+	}
+#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */
 	case KVM_CREATE_DEVICE: {
 		struct kvm_create_device cd;
 
-- 
cgit v1.2.3


From 0003e2a414687fff6a75250d381e4abf345d663f Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 27 Oct 2023 11:21:56 -0700
Subject: mm: Add AS_UNMOVABLE to mark mapping as completely unmovable

Add an "unmovable" flag for mappings that cannot be migrated under any
circumstance.  KVM will use the flag for its upcoming GUEST_MEMFD support,
which will not support compaction/migration, at least not in the
foreseeable future.

Test AS_UNMOVABLE under folio lock as already done for the async
compaction/dirty folio case, as the mapping can be removed by truncation
while compaction is running.  To avoid having to lock every folio with a
mapping, assume/require that unmovable mappings are also unevictable, and
have mapping_set_unmovable() also set AS_UNEVICTABLE.

Cc: Matthew Wilcox <willy@infradead.org>
Co-developed-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20231027182217.3615211-15-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/pagemap.h | 19 ++++++++++++++++++-
 mm/compaction.c         | 43 +++++++++++++++++++++++++++++++------------
 mm/migrate.c            |  2 ++
 3 files changed, 51 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 351c3b7f93a1..82c9bf506b79 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -203,7 +203,8 @@ enum mapping_flags {
 	/* writeback related tags are not used */
 	AS_NO_WRITEBACK_TAGS = 5,
 	AS_LARGE_FOLIO_SUPPORT = 6,
-	AS_RELEASE_ALWAYS,	/* Call ->release_folio(), even if no private data */
+	AS_RELEASE_ALWAYS = 7,	/* Call ->release_folio(), even if no private data */
+	AS_UNMOVABLE	= 8,	/* The mapping cannot be moved, ever */
 };
 
 /**
@@ -289,6 +290,22 @@ static inline void mapping_clear_release_always(struct address_space *mapping)
 	clear_bit(AS_RELEASE_ALWAYS, &mapping->flags);
 }
 
+static inline void mapping_set_unmovable(struct address_space *mapping)
+{
+	/*
+	 * It's expected unmovable mappings are also unevictable. Compaction
+	 * migrate scanner (isolate_migratepages_block()) relies on this to
+	 * reduce page locking.
+	 */
+	set_bit(AS_UNEVICTABLE, &mapping->flags);
+	set_bit(AS_UNMOVABLE, &mapping->flags);
+}
+
+static inline bool mapping_unmovable(struct address_space *mapping)
+{
+	return test_bit(AS_UNMOVABLE, &mapping->flags);
+}
+
 static inline gfp_t mapping_gfp_mask(struct address_space * mapping)
 {
 	return mapping->gfp_mask;
diff --git a/mm/compaction.c b/mm/compaction.c
index 38c8d216c6a3..12b828aed7c8 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -883,6 +883,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 
 	/* Time to isolate some pages for migration */
 	for (; low_pfn < end_pfn; low_pfn++) {
+		bool is_dirty, is_unevictable;
 
 		if (skip_on_failure && low_pfn >= next_skip_pfn) {
 			/*
@@ -1080,8 +1081,10 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		if (!folio_test_lru(folio))
 			goto isolate_fail_put;
 
+		is_unevictable = folio_test_unevictable(folio);
+
 		/* Compaction might skip unevictable pages but CMA takes them */
-		if (!(mode & ISOLATE_UNEVICTABLE) && folio_test_unevictable(folio))
+		if (!(mode & ISOLATE_UNEVICTABLE) && is_unevictable)
 			goto isolate_fail_put;
 
 		/*
@@ -1093,26 +1096,42 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		if ((mode & ISOLATE_ASYNC_MIGRATE) && folio_test_writeback(folio))
 			goto isolate_fail_put;
 
-		if ((mode & ISOLATE_ASYNC_MIGRATE) && folio_test_dirty(folio)) {
-			bool migrate_dirty;
+		is_dirty = folio_test_dirty(folio);
+
+		if (((mode & ISOLATE_ASYNC_MIGRATE) && is_dirty) ||
+		    (mapping && is_unevictable)) {
+			bool migrate_dirty = true;
+			bool is_unmovable;
 
 			/*
 			 * Only folios without mappings or that have
-			 * a ->migrate_folio callback are possible to
-			 * migrate without blocking.  However, we may
-			 * be racing with truncation, which can free
-			 * the mapping.  Truncation holds the folio lock
-			 * until after the folio is removed from the page
-			 * cache so holding it ourselves is sufficient.
+			 * a ->migrate_folio callback are possible to migrate
+			 * without blocking.
+			 *
+			 * Folios from unmovable mappings are not migratable.
+			 *
+			 * However, we can be racing with truncation, which can
+			 * free the mapping that we need to check. Truncation
+			 * holds the folio lock until after the folio is removed
+			 * from the page so holding it ourselves is sufficient.
+			 *
+			 * To avoid locking the folio just to check unmovable,
+			 * assume every unmovable folio is also unevictable,
+			 * which is a cheaper test.  If our assumption goes
+			 * wrong, it's not a correctness bug, just potentially
+			 * wasted cycles.
 			 */
 			if (!folio_trylock(folio))
 				goto isolate_fail_put;
 
 			mapping = folio_mapping(folio);
-			migrate_dirty = !mapping ||
-					mapping->a_ops->migrate_folio;
+			if ((mode & ISOLATE_ASYNC_MIGRATE) && is_dirty) {
+				migrate_dirty = !mapping ||
+						mapping->a_ops->migrate_folio;
+			}
+			is_unmovable = mapping && mapping_unmovable(mapping);
 			folio_unlock(folio);
-			if (!migrate_dirty)
+			if (!migrate_dirty || is_unmovable)
 				goto isolate_fail_put;
 		}
 
diff --git a/mm/migrate.c b/mm/migrate.c
index 06086dc9da28..60f2ff6b36aa 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -956,6 +956,8 @@ static int move_to_new_folio(struct folio *dst, struct folio *src,
 
 		if (!mapping)
 			rc = migrate_folio(mapping, dst, src, mode);
+		else if (mapping_unmovable(mapping))
+			rc = -EOPNOTSUPP;
 		else if (mapping->a_ops->migrate_folio)
 			/*
 			 * Most folios have a mapping and most filesystems
-- 
cgit v1.2.3


From 3fad96e9b21bed214c1593d7d7fb3e40d1fbf6f4 Mon Sep 17 00:00:00 2001
From: Sudeep Holla <sudeep.holla@arm.com>
Date: Tue, 24 Oct 2023 11:57:15 +0100
Subject: firmware: arm_ffa: Declare ffa_bus_type structure in the header

smatch reports:
drivers/firmware/arm_ffa/bus.c:108:17: warning:
	symbol 'ffa_bus_type' was not declared. Should it be static?

ffa_bus_type is exported to be useful in the FF-A driver. So this
warning is not correct. However, declaring the ffa_bus_type structure
in the header like many other bus_types do already removes this warning.
So let us just do the same and get rid of the warning.

Link: https://lore.kernel.org/r/20231024105715.2369638-1-sudeep.holla@arm.com
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 include/linux/arm_ffa.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h
index 1abedb5b2e48..3d0fde57ba90 100644
--- a/include/linux/arm_ffa.h
+++ b/include/linux/arm_ffa.h
@@ -209,6 +209,8 @@ bool ffa_device_is_valid(struct ffa_device *ffa_dev) { return false; }
 #define module_ffa_driver(__ffa_driver)	\
 	module_driver(__ffa_driver, ffa_register, ffa_unregister)
 
+extern struct bus_type ffa_bus_type;
+
 /* FFA transport related */
 struct ffa_partition_info {
 	u16 id;
-- 
cgit v1.2.3


From 07afe1ba288c04280622fa002ed385f1ac0b6fe6 Mon Sep 17 00:00:00 2001
From: Linus Lüssing <linus.luessing@c0d3.blue>
Date: Thu, 7 Sep 2023 03:09:08 +0200
Subject: batman-adv: mcast: implement multicast packet reception and
 forwarding
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Implement functionality to receive and forward a new TVLV capable
multicast packet type.

The new batman-adv multicast packet type allows to contain several
originator destination addresses within a TVLV. Routers on the way will
potentially split the batman-adv multicast packet and adjust its tracker
TVLV contents.

Routing decisions are still based on the selected BATMAN IV or BATMAN V
routing algorithm. So this new batman-adv multicast packet type retains
the same loop-free properties.

Also a new OGM multicast TVLV flag is introduced to signal to other
nodes that we are capable of handling a batman-adv multicast packet and
multicast tracker TVLV. And that all of our hard interfaces have an MTU
of at least 1280 bytes (IPv6 minimum MTU), as a simple solution for now
to avoid MTU issues while forwarding.

Signed-off-by: Linus Lüssing <linus.luessing@c0d3.blue>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 include/uapi/linux/batadv_packet.h |  45 ++++++-
 net/batman-adv/Makefile            |   1 +
 net/batman-adv/fragmentation.c     |   8 +-
 net/batman-adv/main.c              |   2 +
 net/batman-adv/multicast.c         |  48 +++++++-
 net/batman-adv/multicast.h         |   5 +
 net/batman-adv/multicast_forw.c    | 239 +++++++++++++++++++++++++++++++++++++
 net/batman-adv/originator.c        |  28 +++++
 net/batman-adv/originator.h        |   3 +
 net/batman-adv/routing.c           |  70 +++++++++++
 net/batman-adv/routing.h           |  11 ++
 net/batman-adv/soft-interface.c    |  12 ++
 net/batman-adv/types.h             |  64 ++++++++++
 13 files changed, 518 insertions(+), 18 deletions(-)
 create mode 100644 net/batman-adv/multicast_forw.c

(limited to 'include')

diff --git a/include/uapi/linux/batadv_packet.h b/include/uapi/linux/batadv_packet.h
index 9204e4494b25..6e25753015df 100644
--- a/include/uapi/linux/batadv_packet.h
+++ b/include/uapi/linux/batadv_packet.h
@@ -116,6 +116,9 @@ enum batadv_icmp_packettype {
  * only need routable IPv4 multicast packets we signed up for explicitly
  * @BATADV_MCAST_WANT_NO_RTR6: we have no IPv6 multicast router and therefore
  * only need routable IPv6 multicast packets we signed up for explicitly
+ * @BATADV_MCAST_HAVE_MC_PTYPE_CAPA: we can parse, receive and forward
+ * batman-adv multicast packets with a multicast tracker TVLV. And all our
+ * hard interfaces have an MTU of at least 1280 bytes.
  */
 enum batadv_mcast_flags {
 	BATADV_MCAST_WANT_ALL_UNSNOOPABLES	= 1UL << 0,
@@ -123,6 +126,7 @@ enum batadv_mcast_flags {
 	BATADV_MCAST_WANT_ALL_IPV6		= 1UL << 2,
 	BATADV_MCAST_WANT_NO_RTR4		= 1UL << 3,
 	BATADV_MCAST_WANT_NO_RTR6		= 1UL << 4,
+	BATADV_MCAST_HAVE_MC_PTYPE_CAPA		= 1UL << 5,
 };
 
 /* tt data subtypes */
@@ -174,14 +178,16 @@ enum batadv_bla_claimframe {
  * @BATADV_TVLV_TT: translation table tvlv
  * @BATADV_TVLV_ROAM: roaming advertisement tvlv
  * @BATADV_TVLV_MCAST: multicast capability tvlv
+ * @BATADV_TVLV_MCAST_TRACKER: multicast tracker tvlv
  */
 enum batadv_tvlv_type {
-	BATADV_TVLV_GW		= 0x01,
-	BATADV_TVLV_DAT		= 0x02,
-	BATADV_TVLV_NC		= 0x03,
-	BATADV_TVLV_TT		= 0x04,
-	BATADV_TVLV_ROAM	= 0x05,
-	BATADV_TVLV_MCAST	= 0x06,
+	BATADV_TVLV_GW			= 0x01,
+	BATADV_TVLV_DAT			= 0x02,
+	BATADV_TVLV_NC			= 0x03,
+	BATADV_TVLV_TT			= 0x04,
+	BATADV_TVLV_ROAM		= 0x05,
+	BATADV_TVLV_MCAST		= 0x06,
+	BATADV_TVLV_MCAST_TRACKER	= 0x07,
 };
 
 #pragma pack(2)
@@ -487,6 +493,25 @@ struct batadv_bcast_packet {
 	 */
 };
 
+/**
+ * struct batadv_mcast_packet - multicast packet for network payload
+ * @packet_type: batman-adv packet type, part of the general header
+ * @version: batman-adv protocol version, part of the general header
+ * @ttl: time to live for this packet, part of the general header
+ * @reserved: reserved byte for alignment
+ * @tvlv_len: length of the appended tvlv buffer (in bytes)
+ */
+struct batadv_mcast_packet {
+	__u8 packet_type;
+	__u8 version;
+	__u8 ttl;
+	__u8 reserved;
+	__be16 tvlv_len;
+	/* "4 bytes boundary + 2 bytes" long to make the payload after the
+	 * following ethernet header again 4 bytes boundary aligned
+	 */
+};
+
 /**
  * struct batadv_coded_packet - network coded packet
  * @packet_type: batman-adv packet type, part of the general header
@@ -628,6 +653,14 @@ struct batadv_tvlv_mcast_data {
 	__u8 reserved[3];
 };
 
+/**
+ * struct batadv_tvlv_mcast_tracker - payload of a multicast tracker tvlv
+ * @num_dests: number of subsequent destination originator MAC addresses
+ */
+struct batadv_tvlv_mcast_tracker {
+	__be16	num_dests;
+};
+
 #pragma pack()
 
 #endif /* _UAPI_LINUX_BATADV_PACKET_H_ */
diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile
index 3bd0760c76a2..b51d8b071b56 100644
--- a/net/batman-adv/Makefile
+++ b/net/batman-adv/Makefile
@@ -20,6 +20,7 @@ batman-adv-y += hash.o
 batman-adv-$(CONFIG_BATMAN_ADV_DEBUG) += log.o
 batman-adv-y += main.o
 batman-adv-$(CONFIG_BATMAN_ADV_MCAST) += multicast.o
+batman-adv-$(CONFIG_BATMAN_ADV_MCAST) += multicast_forw.o
 batman-adv-y += netlink.o
 batman-adv-$(CONFIG_BATMAN_ADV_NC) += network-coding.o
 batman-adv-y += originator.o
diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c
index c120c7c6d25f..757c084ac2d1 100644
--- a/net/batman-adv/fragmentation.c
+++ b/net/batman-adv/fragmentation.c
@@ -25,7 +25,6 @@
 
 #include "hard-interface.h"
 #include "originator.h"
-#include "routing.h"
 #include "send.h"
 
 /**
@@ -351,18 +350,14 @@ bool batadv_frag_skb_fwd(struct sk_buff *skb,
 			 struct batadv_orig_node *orig_node_src)
 {
 	struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface);
-	struct batadv_orig_node *orig_node_dst;
 	struct batadv_neigh_node *neigh_node = NULL;
 	struct batadv_frag_packet *packet;
 	u16 total_size;
 	bool ret = false;
 
 	packet = (struct batadv_frag_packet *)skb->data;
-	orig_node_dst = batadv_orig_hash_find(bat_priv, packet->dest);
-	if (!orig_node_dst)
-		goto out;
 
-	neigh_node = batadv_find_router(bat_priv, orig_node_dst, recv_if);
+	neigh_node = batadv_orig_to_router(bat_priv, packet->dest, recv_if);
 	if (!neigh_node)
 		goto out;
 
@@ -381,7 +376,6 @@ bool batadv_frag_skb_fwd(struct sk_buff *skb,
 	}
 
 out:
-	batadv_orig_node_put(orig_node_dst);
 	batadv_neigh_node_put(neigh_node);
 	return ret;
 }
diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index e8a449915566..50b2bf2b748c 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -532,6 +532,8 @@ static void batadv_recv_handler_init(void)
 
 	/* broadcast packet */
 	batadv_rx_handler[BATADV_BCAST] = batadv_recv_bcast_packet;
+	/* multicast packet */
+	batadv_rx_handler[BATADV_MCAST] = batadv_recv_mcast_packet;
 
 	/* unicast packets ... */
 	/* unicast with 4 addresses packet */
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index 315394f12c55..dfc2c645b13f 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -235,6 +235,37 @@ static u8 batadv_mcast_mla_rtr_flags_get(struct batadv_priv *bat_priv,
 	return flags;
 }
 
+/**
+ * batadv_mcast_mla_forw_flags_get() - get multicast forwarding flags
+ * @bat_priv: the bat priv with all the soft interface information
+ *
+ * Checks if all active hard interfaces have an MTU larger or equal to 1280
+ * bytes (IPv6 minimum MTU).
+ *
+ * Return: BATADV_MCAST_HAVE_MC_PTYPE_CAPA if yes, BATADV_NO_FLAGS otherwise.
+ */
+static u8 batadv_mcast_mla_forw_flags_get(struct batadv_priv *bat_priv)
+{
+	const struct batadv_hard_iface *hard_iface;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) {
+		if (hard_iface->if_status != BATADV_IF_ACTIVE)
+			continue;
+
+		if (hard_iface->soft_iface != bat_priv->soft_iface)
+			continue;
+
+		if (hard_iface->net_dev->mtu < IPV6_MIN_MTU) {
+			rcu_read_unlock();
+			return BATADV_NO_FLAGS;
+		}
+	}
+	rcu_read_unlock();
+
+	return BATADV_MCAST_HAVE_MC_PTYPE_CAPA;
+}
+
 /**
  * batadv_mcast_mla_flags_get() - get the new multicast flags
  * @bat_priv: the bat priv with all the soft interface information
@@ -256,6 +287,7 @@ batadv_mcast_mla_flags_get(struct batadv_priv *bat_priv)
 	mla_flags.enabled = 1;
 	mla_flags.tvlv_flags |= batadv_mcast_mla_rtr_flags_get(bat_priv,
 							       bridge);
+	mla_flags.tvlv_flags |= batadv_mcast_mla_forw_flags_get(bat_priv);
 
 	if (!bridge)
 		return mla_flags;
@@ -806,23 +838,25 @@ static void batadv_mcast_flags_log(struct batadv_priv *bat_priv, u8 flags)
 {
 	bool old_enabled = bat_priv->mcast.mla_flags.enabled;
 	u8 old_flags = bat_priv->mcast.mla_flags.tvlv_flags;
-	char str_old_flags[] = "[.... . ]";
+	char str_old_flags[] = "[.... . .]";
 
-	sprintf(str_old_flags, "[%c%c%c%s%s]",
+	sprintf(str_old_flags, "[%c%c%c%s%s%c]",
 		(old_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES) ? 'U' : '.',
 		(old_flags & BATADV_MCAST_WANT_ALL_IPV4) ? '4' : '.',
 		(old_flags & BATADV_MCAST_WANT_ALL_IPV6) ? '6' : '.',
 		!(old_flags & BATADV_MCAST_WANT_NO_RTR4) ? "R4" : ". ",
-		!(old_flags & BATADV_MCAST_WANT_NO_RTR6) ? "R6" : ". ");
+		!(old_flags & BATADV_MCAST_WANT_NO_RTR6) ? "R6" : ". ",
+		!(old_flags & BATADV_MCAST_HAVE_MC_PTYPE_CAPA) ? 'P' : '.');
 
 	batadv_dbg(BATADV_DBG_MCAST, bat_priv,
-		   "Changing multicast flags from '%s' to '[%c%c%c%s%s]'\n",
+		   "Changing multicast flags from '%s' to '[%c%c%c%s%s%c]'\n",
 		   old_enabled ? str_old_flags : "<undefined>",
 		   (flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES) ? 'U' : '.',
 		   (flags & BATADV_MCAST_WANT_ALL_IPV4) ? '4' : '.',
 		   (flags & BATADV_MCAST_WANT_ALL_IPV6) ? '6' : '.',
 		   !(flags & BATADV_MCAST_WANT_NO_RTR4) ? "R4" : ". ",
-		   !(flags & BATADV_MCAST_WANT_NO_RTR6) ? "R6" : ". ");
+		   !(flags & BATADV_MCAST_WANT_NO_RTR6) ? "R6" : ". ",
+		   !(flags & BATADV_MCAST_HAVE_MC_PTYPE_CAPA) ? 'P' : '.');
 }
 
 /**
@@ -1820,6 +1854,10 @@ void batadv_mcast_init(struct batadv_priv *bat_priv)
 	batadv_tvlv_handler_register(bat_priv, batadv_mcast_tvlv_ogm_handler,
 				     NULL, NULL, BATADV_TVLV_MCAST, 2,
 				     BATADV_TVLV_HANDLER_OGM_CIFNOTFND);
+	batadv_tvlv_handler_register(bat_priv, NULL, NULL,
+				     batadv_mcast_forw_tracker_tvlv_handler,
+				     BATADV_TVLV_MCAST_TRACKER, 1,
+				     BATADV_TVLV_HANDLER_OGM_CIFNOTFND);
 
 	INIT_DELAYED_WORK(&bat_priv->mcast.work, batadv_mcast_mla_update);
 	batadv_mcast_start_timer(bat_priv);
diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h
index a9770d8d6d36..a5c0f384bb9a 100644
--- a/net/batman-adv/multicast.h
+++ b/net/batman-adv/multicast.h
@@ -52,6 +52,11 @@ void batadv_mcast_free(struct batadv_priv *bat_priv);
 
 void batadv_mcast_purge_orig(struct batadv_orig_node *orig_node);
 
+/* multicast_forw.c */
+
+int batadv_mcast_forw_tracker_tvlv_handler(struct batadv_priv *bat_priv,
+					   struct sk_buff *skb);
+
 #else
 
 static inline enum batadv_forw_mode
diff --git a/net/batman-adv/multicast_forw.c b/net/batman-adv/multicast_forw.c
new file mode 100644
index 000000000000..d17341dfb832
--- /dev/null
+++ b/net/batman-adv/multicast_forw.c
@@ -0,0 +1,239 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) B.A.T.M.A.N. contributors:
+ *
+ * Linus Lüssing
+ */
+
+#include "multicast.h"
+#include "main.h"
+
+#include <linux/byteorder/generic.h>
+#include <linux/errno.h>
+#include <linux/etherdevice.h>
+#include <linux/gfp.h>
+#include <linux/if_ether.h>
+#include <linux/netdevice.h>
+#include <linux/skbuff.h>
+#include <linux/stddef.h>
+#include <linux/types.h>
+#include <uapi/linux/batadv_packet.h>
+
+#include "originator.h"
+#include "send.h"
+
+#define batadv_mcast_forw_tracker_for_each_dest(dest, num_dests) \
+	for (; num_dests; num_dests--, (dest) += ETH_ALEN)
+
+#define batadv_mcast_forw_tracker_for_each_dest2(dest1, dest2, num_dests) \
+	for (; num_dests; num_dests--, (dest1) += ETH_ALEN, (dest2) += ETH_ALEN)
+
+/**
+ * batadv_mcast_forw_scrub_dests() - scrub destinations in a tracker TVLV
+ * @bat_priv: the bat priv with all the soft interface information
+ * @comp_neigh: next hop neighbor to scrub+collect destinations for
+ * @dest: start MAC entry in original skb's tracker TVLV
+ * @next_dest: start MAC entry in to be sent skb's tracker TVLV
+ * @num_dests: number of remaining destination MAC entries to iterate over
+ *
+ * This sorts destination entries into either the original batman-adv
+ * multicast packet or the skb (copy) that is going to be sent to comp_neigh
+ * next.
+ *
+ * In preparation for the next, to be (unicast) transmitted batman-adv multicast
+ * packet skb to be sent to the given neighbor node, tries to collect all
+ * originator MAC addresses that have the given neighbor node as their next hop
+ * in the to be transmitted skb (copy), which next_dest points into. That is we
+ * zero all destination entries in next_dest which do not have comp_neigh as
+ * their next hop. And zero all destination entries in the original skb that
+ * would have comp_neigh as their next hop (to avoid redundant transmissions and
+ * duplicated payload later).
+ */
+static void
+batadv_mcast_forw_scrub_dests(struct batadv_priv *bat_priv,
+			      struct batadv_neigh_node *comp_neigh, u8 *dest,
+			      u8 *next_dest, u16 num_dests)
+{
+	struct batadv_neigh_node *next_neigh;
+
+	/* skip first entry, this is what we are comparing with */
+	eth_zero_addr(dest);
+	dest += ETH_ALEN;
+	next_dest += ETH_ALEN;
+	num_dests--;
+
+	batadv_mcast_forw_tracker_for_each_dest2(dest, next_dest, num_dests) {
+		if (is_zero_ether_addr(next_dest))
+			continue;
+
+		/* sanity check, we expect unicast destinations */
+		if (is_multicast_ether_addr(next_dest)) {
+			eth_zero_addr(dest);
+			eth_zero_addr(next_dest);
+			continue;
+		}
+
+		next_neigh = batadv_orig_to_router(bat_priv, next_dest, NULL);
+		if (!next_neigh) {
+			eth_zero_addr(next_dest);
+			continue;
+		}
+
+		if (!batadv_compare_eth(next_neigh->addr, comp_neigh->addr)) {
+			eth_zero_addr(next_dest);
+			batadv_neigh_node_put(next_neigh);
+			continue;
+		}
+
+		/* found an entry for our next packet to transmit, so remove it
+		 * from the original packet
+		 */
+		eth_zero_addr(dest);
+		batadv_neigh_node_put(next_neigh);
+	}
+}
+
+/**
+ * batadv_mcast_forw_packet() - forward a batman-adv multicast packet
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: the received or locally generated batman-adv multicast packet
+ * @local_xmit: indicates that the packet was locally generated and not received
+ *
+ * Parses the tracker TVLV of a batman-adv multicast packet and forwards the
+ * packet as indicated in this TVLV.
+ *
+ * Caller needs to set the skb network header to the start of the multicast
+ * tracker TVLV (excluding the generic TVLV header) and the skb transport header
+ * to the next byte after this multicast tracker TVLV.
+ *
+ * Caller needs to free the skb.
+ *
+ * Return: NET_RX_SUCCESS or NET_RX_DROP on success or a negative error
+ * code on failure. NET_RX_SUCCESS if the received packet is supposed to be
+ * decapsulated and forwarded to the own soft interface, NET_RX_DROP otherwise.
+ */
+static int batadv_mcast_forw_packet(struct batadv_priv *bat_priv,
+				    struct sk_buff *skb, bool local_xmit)
+{
+	struct batadv_tvlv_mcast_tracker *mcast_tracker;
+	struct batadv_neigh_node *neigh_node;
+	unsigned long offset, num_dests_off;
+	struct sk_buff *nexthop_skb;
+	unsigned char *skb_net_hdr;
+	bool local_recv = false;
+	unsigned int tvlv_len;
+	bool xmitted = false;
+	u8 *dest, *next_dest;
+	u16 num_dests;
+	int ret;
+
+	/* (at least) TVLV part needs to be linearized */
+	SKB_LINEAR_ASSERT(skb);
+
+	/* check if num_dests is within skb length */
+	num_dests_off = offsetof(struct batadv_tvlv_mcast_tracker, num_dests);
+	if (num_dests_off > skb_network_header_len(skb))
+		return -EINVAL;
+
+	skb_net_hdr = skb_network_header(skb);
+	mcast_tracker = (struct batadv_tvlv_mcast_tracker *)skb_net_hdr;
+	num_dests = ntohs(mcast_tracker->num_dests);
+
+	dest = (u8 *)mcast_tracker + sizeof(*mcast_tracker);
+
+	/* check if full tracker tvlv is within skb length */
+	tvlv_len = sizeof(*mcast_tracker) + ETH_ALEN * num_dests;
+	if (tvlv_len > skb_network_header_len(skb))
+		return -EINVAL;
+
+	/* invalidate checksum: */
+	skb->ip_summed = CHECKSUM_NONE;
+
+	batadv_mcast_forw_tracker_for_each_dest(dest, num_dests) {
+		if (is_zero_ether_addr(dest))
+			continue;
+
+		/* only unicast originator addresses supported */
+		if (is_multicast_ether_addr(dest)) {
+			eth_zero_addr(dest);
+			continue;
+		}
+
+		if (batadv_is_my_mac(bat_priv, dest)) {
+			eth_zero_addr(dest);
+			local_recv = true;
+			continue;
+		}
+
+		neigh_node = batadv_orig_to_router(bat_priv, dest, NULL);
+		if (!neigh_node) {
+			eth_zero_addr(dest);
+			continue;
+		}
+
+		nexthop_skb = skb_copy(skb, GFP_ATOMIC);
+		if (!nexthop_skb) {
+			batadv_neigh_node_put(neigh_node);
+			return -ENOMEM;
+		}
+
+		offset = dest - skb->data;
+		next_dest = nexthop_skb->data + offset;
+
+		batadv_mcast_forw_scrub_dests(bat_priv, neigh_node, dest,
+					      next_dest, num_dests);
+
+		batadv_inc_counter(bat_priv, BATADV_CNT_MCAST_TX);
+		batadv_add_counter(bat_priv, BATADV_CNT_MCAST_TX_BYTES,
+				   nexthop_skb->len + ETH_HLEN);
+		xmitted = true;
+		ret = batadv_send_unicast_skb(nexthop_skb, neigh_node);
+
+		batadv_neigh_node_put(neigh_node);
+
+		if (ret < 0)
+			return ret;
+	}
+
+	if (xmitted) {
+		if (local_xmit) {
+			batadv_inc_counter(bat_priv, BATADV_CNT_MCAST_TX_LOCAL);
+			batadv_add_counter(bat_priv,
+					   BATADV_CNT_MCAST_TX_LOCAL_BYTES,
+					   skb->len -
+					   skb_transport_offset(skb));
+		} else {
+			batadv_inc_counter(bat_priv, BATADV_CNT_MCAST_FWD);
+			batadv_add_counter(bat_priv, BATADV_CNT_MCAST_FWD_BYTES,
+					   skb->len + ETH_HLEN);
+		}
+	}
+
+	if (local_recv)
+		return NET_RX_SUCCESS;
+	else
+		return NET_RX_DROP;
+}
+
+/**
+ * batadv_mcast_forw_tracker_tvlv_handler() - handle an mcast tracker tvlv
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: the received batman-adv multicast packet
+ *
+ * Parses the tracker TVLV of an incoming batman-adv multicast packet and
+ * forwards the packet as indicated in this TVLV.
+ *
+ * Caller needs to set the skb network header to the start of the multicast
+ * tracker TVLV (excluding the generic TVLV header) and the skb transport header
+ * to the next byte after this multicast tracker TVLV.
+ *
+ * Caller needs to free the skb.
+ *
+ * Return: NET_RX_SUCCESS or NET_RX_DROP on success or a negative error
+ * code on failure. NET_RX_SUCCESS if the received packet is supposed to be
+ * decapsulated and forwarded to the own soft interface, NET_RX_DROP otherwise.
+ */
+int batadv_mcast_forw_tracker_tvlv_handler(struct batadv_priv *bat_priv,
+					   struct sk_buff *skb)
+{
+	return batadv_mcast_forw_packet(bat_priv, skb, false);
+}
diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index 34903df4fe93..71c143d4b6d0 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -311,6 +311,33 @@ batadv_orig_router_get(struct batadv_orig_node *orig_node,
 	return router;
 }
 
+/**
+ * batadv_orig_to_router() - get next hop neighbor to an orig address
+ * @bat_priv: the bat priv with all the soft interface information
+ * @orig_addr: the originator MAC address to search the best next hop router for
+ * @if_outgoing: the interface where the payload packet has been received or
+ *  the OGM should be sent to
+ *
+ * Return: A neighbor node which is the best router towards the given originator
+ * address.
+ */
+struct batadv_neigh_node *
+batadv_orig_to_router(struct batadv_priv *bat_priv, u8 *orig_addr,
+		      struct batadv_hard_iface *if_outgoing)
+{
+	struct batadv_neigh_node *neigh_node;
+	struct batadv_orig_node *orig_node;
+
+	orig_node = batadv_orig_hash_find(bat_priv, orig_addr);
+	if (!orig_node)
+		return NULL;
+
+	neigh_node = batadv_find_router(bat_priv, orig_node, if_outgoing);
+	batadv_orig_node_put(orig_node);
+
+	return neigh_node;
+}
+
 /**
  * batadv_orig_ifinfo_get() - find the ifinfo from an orig_node
  * @orig_node: the orig node to be queried
@@ -942,6 +969,7 @@ struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv,
 #ifdef CONFIG_BATMAN_ADV_MCAST
 	orig_node->mcast_flags = BATADV_MCAST_WANT_NO_RTR4;
 	orig_node->mcast_flags |= BATADV_MCAST_WANT_NO_RTR6;
+	orig_node->mcast_flags |= BATADV_MCAST_HAVE_MC_PTYPE_CAPA;
 	INIT_HLIST_NODE(&orig_node->mcast_want_all_unsnoopables_node);
 	INIT_HLIST_NODE(&orig_node->mcast_want_all_ipv4_node);
 	INIT_HLIST_NODE(&orig_node->mcast_want_all_ipv6_node);
diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h
index ea3d69e4e670..db0c55128170 100644
--- a/net/batman-adv/originator.h
+++ b/net/batman-adv/originator.h
@@ -36,6 +36,9 @@ void batadv_neigh_node_release(struct kref *ref);
 struct batadv_neigh_node *
 batadv_orig_router_get(struct batadv_orig_node *orig_node,
 		       const struct batadv_hard_iface *if_outgoing);
+struct batadv_neigh_node *
+batadv_orig_to_router(struct batadv_priv *bat_priv, u8 *orig_addr,
+		      struct batadv_hard_iface *if_outgoing);
 struct batadv_neigh_ifinfo *
 batadv_neigh_ifinfo_new(struct batadv_neigh_node *neigh,
 			struct batadv_hard_iface *if_outgoing);
diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c
index 163cd43c4821..f1061985149f 100644
--- a/net/batman-adv/routing.c
+++ b/net/batman-adv/routing.c
@@ -1270,3 +1270,73 @@ out:
 	batadv_orig_node_put(orig_node);
 	return ret;
 }
+
+#ifdef CONFIG_BATMAN_ADV_MCAST
+/**
+ * batadv_recv_mcast_packet() - process received batman-adv multicast packet
+ * @skb: the received batman-adv multicast packet
+ * @recv_if: interface that the skb is received on
+ *
+ * Parses the given, received batman-adv multicast packet. Depending on the
+ * contents of its TVLV forwards it and/or decapsulates it to hand it to the
+ * soft interface.
+ *
+ * Return: NET_RX_DROP if the skb is not consumed, NET_RX_SUCCESS otherwise.
+ */
+int batadv_recv_mcast_packet(struct sk_buff *skb,
+			     struct batadv_hard_iface *recv_if)
+{
+	struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface);
+	struct batadv_mcast_packet *mcast_packet;
+	int hdr_size = sizeof(*mcast_packet);
+	unsigned char *tvlv_buff;
+	int ret = NET_RX_DROP;
+	u16 tvlv_buff_len;
+
+	if (batadv_check_unicast_packet(bat_priv, skb, hdr_size) < 0)
+		goto free_skb;
+
+	/* create a copy of the skb, if needed, to modify it. */
+	if (skb_cow(skb, ETH_HLEN) < 0)
+		goto free_skb;
+
+	/* packet needs to be linearized to access the tvlv content */
+	if (skb_linearize(skb) < 0)
+		goto free_skb;
+
+	mcast_packet = (struct batadv_mcast_packet *)skb->data;
+	if (mcast_packet->ttl-- < 2)
+		goto free_skb;
+
+	tvlv_buff = (unsigned char *)(skb->data + hdr_size);
+	tvlv_buff_len = ntohs(mcast_packet->tvlv_len);
+
+	if (tvlv_buff_len > skb->len - hdr_size)
+		goto free_skb;
+
+	ret = batadv_tvlv_containers_process(bat_priv, BATADV_MCAST, NULL, skb,
+					     tvlv_buff, tvlv_buff_len);
+	if (ret >= 0) {
+		batadv_inc_counter(bat_priv, BATADV_CNT_MCAST_RX);
+		batadv_add_counter(bat_priv, BATADV_CNT_MCAST_RX_BYTES,
+				   skb->len + ETH_HLEN);
+	}
+
+	hdr_size += tvlv_buff_len;
+
+	if (ret == NET_RX_SUCCESS && (skb->len - hdr_size >= ETH_HLEN)) {
+		batadv_inc_counter(bat_priv, BATADV_CNT_MCAST_RX_LOCAL);
+		batadv_add_counter(bat_priv, BATADV_CNT_MCAST_RX_LOCAL_BYTES,
+				   skb->len - hdr_size);
+
+		batadv_interface_rx(bat_priv->soft_iface, skb, hdr_size, NULL);
+		/* skb was consumed */
+		skb = NULL;
+	}
+
+free_skb:
+	kfree_skb(skb);
+
+	return ret;
+}
+#endif /* CONFIG_BATMAN_ADV_MCAST */
diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h
index afd15b3879f1..e9849f032a24 100644
--- a/net/batman-adv/routing.h
+++ b/net/batman-adv/routing.h
@@ -27,6 +27,17 @@ int batadv_recv_frag_packet(struct sk_buff *skb,
 			    struct batadv_hard_iface *iface);
 int batadv_recv_bcast_packet(struct sk_buff *skb,
 			     struct batadv_hard_iface *recv_if);
+#ifdef CONFIG_BATMAN_ADV_MCAST
+int batadv_recv_mcast_packet(struct sk_buff *skb,
+			     struct batadv_hard_iface *recv_if);
+#else
+static inline int batadv_recv_mcast_packet(struct sk_buff *skb,
+					   struct batadv_hard_iface *recv_if)
+{
+	kfree_skb(skb);
+	return NET_RX_DROP;
+}
+#endif
 int batadv_recv_unicast_tvlv(struct sk_buff *skb,
 			     struct batadv_hard_iface *recv_if);
 int batadv_recv_unhandled_unicast_packet(struct sk_buff *skb,
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 1bf1232a4f75..1b0e2c59aef2 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -925,6 +925,18 @@ static const struct {
 	{ "tt_response_rx" },
 	{ "tt_roam_adv_tx" },
 	{ "tt_roam_adv_rx" },
+#ifdef CONFIG_BATMAN_ADV_MCAST
+	{ "mcast_tx" },
+	{ "mcast_tx_bytes" },
+	{ "mcast_tx_local" },
+	{ "mcast_tx_local_bytes" },
+	{ "mcast_rx" },
+	{ "mcast_rx_bytes" },
+	{ "mcast_rx_local" },
+	{ "mcast_rx_local_bytes" },
+	{ "mcast_fwd" },
+	{ "mcast_fwd_bytes" },
+#endif
 #ifdef CONFIG_BATMAN_ADV_DAT
 	{ "dat_get_tx" },
 	{ "dat_get_rx" },
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index 17d5ea1d8e84..850b184e5b04 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -862,6 +862,70 @@ enum batadv_counters {
 	 */
 	BATADV_CNT_TT_ROAM_ADV_RX,
 
+#ifdef CONFIG_BATMAN_ADV_MCAST
+	/**
+	 * @BATADV_CNT_MCAST_TX: transmitted batman-adv multicast packets
+	 *  counter
+	 */
+	BATADV_CNT_MCAST_TX,
+
+	/**
+	 * @BATADV_CNT_MCAST_TX_BYTES: transmitted batman-adv multicast packets
+	 *  bytes counter
+	 */
+	BATADV_CNT_MCAST_TX_BYTES,
+
+	/**
+	 * @BATADV_CNT_MCAST_TX_LOCAL: counter for multicast packets which
+	 *  were locally encapsulated and transmitted as batman-adv multicast
+	 *  packets
+	 */
+	BATADV_CNT_MCAST_TX_LOCAL,
+
+	/**
+	 * @BATADV_CNT_MCAST_TX_LOCAL_BYTES: bytes counter for multicast packets
+	 *  which were locally encapsulated and transmitted as batman-adv
+	 *  multicast packets
+	 */
+	BATADV_CNT_MCAST_TX_LOCAL_BYTES,
+
+	/**
+	 * @BATADV_CNT_MCAST_RX: received batman-adv multicast packet counter
+	 */
+	BATADV_CNT_MCAST_RX,
+
+	/**
+	 * @BATADV_CNT_MCAST_RX_BYTES: received batman-adv multicast packet
+	 *  bytes counter
+	 */
+	BATADV_CNT_MCAST_RX_BYTES,
+
+	/**
+	 * @BATADV_CNT_MCAST_RX_LOCAL: counter for received batman-adv multicast
+	 *  packets which were forwarded to the local soft interface
+	 */
+	BATADV_CNT_MCAST_RX_LOCAL,
+
+	/**
+	 * @BATADV_CNT_MCAST_RX_LOCAL_BYTES: bytes counter for received
+	 *  batman-adv multicast packets which were forwarded to the local soft
+	 *  interface
+	 */
+	BATADV_CNT_MCAST_RX_LOCAL_BYTES,
+
+	/**
+	 * @BATADV_CNT_MCAST_FWD: counter for received batman-adv multicast
+	 *  packets which were forwarded to other, neighboring nodes
+	 */
+	BATADV_CNT_MCAST_FWD,
+
+	/**
+	 * @BATADV_CNT_MCAST_FWD_BYTES: bytes counter for received batman-adv
+	 *  multicast packets which were forwarded to other, neighboring nodes
+	 */
+	BATADV_CNT_MCAST_FWD_BYTES,
+#endif
+
 #ifdef CONFIG_BATMAN_ADV_DAT
 	/**
 	 * @BATADV_CNT_DAT_GET_TX: transmitted dht GET traffic packet counter
-- 
cgit v1.2.3


From 4f0b9194bc119a9850a99e5e824808e2f468c348 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Fri, 3 Nov 2023 06:47:51 -0400
Subject: fs: Rename anon_inode_getfile_secure() and anon_inode_getfd_secure()

The call to the inode_init_security_anon() LSM hook is not the sole
reason to use anon_inode_getfile_secure() or anon_inode_getfd_secure().
For example, the functions also allow one to create a file with non-zero
size, without needing a full-blown filesystem.  In this case, you don't
need a "secure" version, just unique inodes; the current name of the
functions is confusing and does not explain well the difference with
the more "standard" anon_inode_getfile() and anon_inode_getfd().

Of course, there is another side of the coin; neither io_uring nor
userfaultfd strictly speaking need distinct inodes, and it is not
that clear anymore that anon_inode_create_get{file,fd}() allow the LSM
to intercept and block the inode's creation.  If one was so inclined,
anon_inode_getfile_secure() and anon_inode_getfd_secure() could be kept,
using the shared inode or a new one depending on CONFIG_SECURITY.
However, this is probably overkill, and potentially a cause of bugs in
different configurations.  Therefore, just add a comment to io_uring
and userfaultfd explaining the choice of the function.

While at it, remove the export for what is now anon_inode_create_getfd().
There is no in-tree module that uses it, and the old name is gone anyway.
If anybody actually needs the symbol, they can ask or they can just use
anon_inode_create_getfile(), which will be exported very soon for use
in KVM.

Suggested-by: Christian Brauner <brauner@kernel.org>
Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 fs/anon_inodes.c            | 50 ++++++++++++++++++++++++++++++---------------
 fs/userfaultfd.c            |  5 +++--
 include/linux/anon_inodes.h |  4 ++--
 io_uring/io_uring.c         |  3 ++-
 4 files changed, 40 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
index 24192a7667ed..42b02dc36474 100644
--- a/fs/anon_inodes.c
+++ b/fs/anon_inodes.c
@@ -79,7 +79,7 @@ static struct file *__anon_inode_getfile(const char *name,
 					 const struct file_operations *fops,
 					 void *priv, int flags,
 					 const struct inode *context_inode,
-					 bool secure)
+					 bool make_inode)
 {
 	struct inode *inode;
 	struct file *file;
@@ -87,7 +87,7 @@ static struct file *__anon_inode_getfile(const char *name,
 	if (fops->owner && !try_module_get(fops->owner))
 		return ERR_PTR(-ENOENT);
 
-	if (secure) {
+	if (make_inode) {
 		inode =	anon_inode_make_secure_inode(name, context_inode);
 		if (IS_ERR(inode)) {
 			file = ERR_CAST(inode);
@@ -149,13 +149,10 @@ struct file *anon_inode_getfile(const char *name,
 EXPORT_SYMBOL_GPL(anon_inode_getfile);
 
 /**
- * anon_inode_getfile_secure - Like anon_inode_getfile(), but creates a new
+ * anon_inode_create_getfile - Like anon_inode_getfile(), but creates a new
  *                             !S_PRIVATE anon inode rather than reuse the
  *                             singleton anon inode and calls the
- *                             inode_init_security_anon() LSM hook.  This
- *                             allows for both the inode to have its own
- *                             security context and for the LSM to enforce
- *                             policy on the inode's creation.
+ *                             inode_init_security_anon() LSM hook.
  *
  * @name:    [in]    name of the "class" of the new file
  * @fops:    [in]    file operations for the new file
@@ -164,11 +161,21 @@ EXPORT_SYMBOL_GPL(anon_inode_getfile);
  * @context_inode:
  *           [in]    the logical relationship with the new inode (optional)
  *
+ * Create a new anonymous inode and file pair.  This can be done for two
+ * reasons:
+ *
+ * - for the inode to have its own security context, so that LSMs can enforce
+ *   policy on the inode's creation;
+ *
+ * - if the caller needs a unique inode, for example in order to customize
+ *   the size returned by fstat()
+ *
  * The LSM may use @context_inode in inode_init_security_anon(), but a
- * reference to it is not held.  Returns the newly created file* or an error
- * pointer.  See the anon_inode_getfile() documentation for more information.
+ * reference to it is not held.
+ *
+ * Returns the newly created file* or an error pointer.
  */
-struct file *anon_inode_getfile_secure(const char *name,
+struct file *anon_inode_create_getfile(const char *name,
 				       const struct file_operations *fops,
 				       void *priv, int flags,
 				       const struct inode *context_inode)
@@ -181,7 +188,7 @@ static int __anon_inode_getfd(const char *name,
 			      const struct file_operations *fops,
 			      void *priv, int flags,
 			      const struct inode *context_inode,
-			      bool secure)
+			      bool make_inode)
 {
 	int error, fd;
 	struct file *file;
@@ -192,7 +199,7 @@ static int __anon_inode_getfd(const char *name,
 	fd = error;
 
 	file = __anon_inode_getfile(name, fops, priv, flags, context_inode,
-				    secure);
+				    make_inode);
 	if (IS_ERR(file)) {
 		error = PTR_ERR(file);
 		goto err_put_unused_fd;
@@ -231,10 +238,9 @@ int anon_inode_getfd(const char *name, const struct file_operations *fops,
 EXPORT_SYMBOL_GPL(anon_inode_getfd);
 
 /**
- * anon_inode_getfd_secure - Like anon_inode_getfd(), but creates a new
+ * anon_inode_create_getfd - Like anon_inode_getfd(), but creates a new
  * !S_PRIVATE anon inode rather than reuse the singleton anon inode, and calls
- * the inode_init_security_anon() LSM hook. This allows the inode to have its
- * own security context and for a LSM to reject creation of the inode.
+ * the inode_init_security_anon() LSM hook.
  *
  * @name:    [in]    name of the "class" of the new file
  * @fops:    [in]    file operations for the new file
@@ -243,16 +249,26 @@ EXPORT_SYMBOL_GPL(anon_inode_getfd);
  * @context_inode:
  *           [in]    the logical relationship with the new inode (optional)
  *
+ * Create a new anonymous inode and file pair.  This can be done for two
+ * reasons:
+ *
+ * - for the inode to have its own security context, so that LSMs can enforce
+ *   policy on the inode's creation;
+ *
+ * - if the caller needs a unique inode, for example in order to customize
+ *   the size returned by fstat()
+ *
  * The LSM may use @context_inode in inode_init_security_anon(), but a
  * reference to it is not held.
+ *
+ * Returns a newly created file descriptor or an error code.
  */
-int anon_inode_getfd_secure(const char *name, const struct file_operations *fops,
+int anon_inode_create_getfd(const char *name, const struct file_operations *fops,
 			    void *priv, int flags,
 			    const struct inode *context_inode)
 {
 	return __anon_inode_getfd(name, fops, priv, flags, context_inode, true);
 }
-EXPORT_SYMBOL_GPL(anon_inode_getfd_secure);
 
 static int __init anon_inode_init(void)
 {
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 56eaae9dac1a..7a1cf8bab5eb 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1033,7 +1033,7 @@ static int resolve_userfault_fork(struct userfaultfd_ctx *new,
 {
 	int fd;
 
-	fd = anon_inode_getfd_secure("[userfaultfd]", &userfaultfd_fops, new,
+	fd = anon_inode_create_getfd("[userfaultfd]", &userfaultfd_fops, new,
 			O_RDONLY | (new->flags & UFFD_SHARED_FCNTL_FLAGS), inode);
 	if (fd < 0)
 		return fd;
@@ -2205,7 +2205,8 @@ static int new_userfaultfd(int flags)
 	/* prevent the mm struct to be freed */
 	mmgrab(ctx->mm);
 
-	fd = anon_inode_getfd_secure("[userfaultfd]", &userfaultfd_fops, ctx,
+	/* Create a new inode so that the LSM can block the creation.  */
+	fd = anon_inode_create_getfd("[userfaultfd]", &userfaultfd_fops, ctx,
 			O_RDONLY | (flags & UFFD_SHARED_FCNTL_FLAGS), NULL);
 	if (fd < 0) {
 		mmdrop(ctx->mm);
diff --git a/include/linux/anon_inodes.h b/include/linux/anon_inodes.h
index 5deaddbd7927..93a5f16d03f3 100644
--- a/include/linux/anon_inodes.h
+++ b/include/linux/anon_inodes.h
@@ -15,13 +15,13 @@ struct inode;
 struct file *anon_inode_getfile(const char *name,
 				const struct file_operations *fops,
 				void *priv, int flags);
-struct file *anon_inode_getfile_secure(const char *name,
+struct file *anon_inode_create_getfile(const char *name,
 				       const struct file_operations *fops,
 				       void *priv, int flags,
 				       const struct inode *context_inode);
 int anon_inode_getfd(const char *name, const struct file_operations *fops,
 		     void *priv, int flags);
-int anon_inode_getfd_secure(const char *name,
+int anon_inode_create_getfd(const char *name,
 			    const struct file_operations *fops,
 			    void *priv, int flags,
 			    const struct inode *context_inode);
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 8d1bc6cdfe71..22b98f47bb28 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -3835,7 +3835,8 @@ static struct file *io_uring_get_file(struct io_ring_ctx *ctx)
 		return ERR_PTR(ret);
 #endif
 
-	file = anon_inode_getfile_secure("[io_uring]", &io_uring_fops, ctx,
+	/* Create a new inode so that the LSM can block the creation.  */
+	file = anon_inode_create_getfile("[io_uring]", &io_uring_fops, ctx,
 					 O_RDWR | O_CLOEXEC, NULL);
 #if defined(CONFIG_UNIX)
 	if (IS_ERR(file)) {
-- 
cgit v1.2.3


From a7800aa80ea4d5356b8474c2302812e9d4926fa6 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Mon, 13 Nov 2023 05:42:34 -0500
Subject: KVM: Add KVM_CREATE_GUEST_MEMFD ioctl() for guest-specific backing
 memory
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Introduce an ioctl(), KVM_CREATE_GUEST_MEMFD, to allow creating file-based
memory that is tied to a specific KVM virtual machine and whose primary
purpose is to serve guest memory.

A guest-first memory subsystem allows for optimizations and enhancements
that are kludgy or outright infeasible to implement/support in a generic
memory subsystem.  With guest_memfd, guest protections and mapping sizes
are fully decoupled from host userspace mappings.   E.g. KVM currently
doesn't support mapping memory as writable in the guest without it also
being writable in host userspace, as KVM's ABI uses VMA protections to
define the allow guest protection.  Userspace can fudge this by
establishing two mappings, a writable mapping for the guest and readable
one for itself, but that’s suboptimal on multiple fronts.

Similarly, KVM currently requires the guest mapping size to be a strict
subset of the host userspace mapping size, e.g. KVM doesn’t support
creating a 1GiB guest mapping unless userspace also has a 1GiB guest
mapping.  Decoupling the mappings sizes would allow userspace to precisely
map only what is needed without impacting guest performance, e.g. to
harden against unintentional accesses to guest memory.

Decoupling guest and userspace mappings may also allow for a cleaner
alternative to high-granularity mappings for HugeTLB, which has reached a
bit of an impasse and is unlikely to ever be merged.

A guest-first memory subsystem also provides clearer line of sight to
things like a dedicated memory pool (for slice-of-hardware VMs) and
elimination of "struct page" (for offload setups where userspace _never_
needs to mmap() guest memory).

More immediately, being able to map memory into KVM guests without mapping
said memory into the host is critical for Confidential VMs (CoCo VMs), the
initial use case for guest_memfd.  While AMD's SEV and Intel's TDX prevent
untrusted software from reading guest private data by encrypting guest
memory with a key that isn't usable by the untrusted host, projects such
as Protected KVM (pKVM) provide confidentiality and integrity *without*
relying on memory encryption.  And with SEV-SNP and TDX, accessing guest
private memory can be fatal to the host, i.e. KVM must be prevent host
userspace from accessing guest memory irrespective of hardware behavior.

Attempt #1 to support CoCo VMs was to add a VMA flag to mark memory as
being mappable only by KVM (or a similarly enlightened kernel subsystem).
That approach was abandoned largely due to it needing to play games with
PROT_NONE to prevent userspace from accessing guest memory.

Attempt #2 to was to usurp PG_hwpoison to prevent the host from mapping
guest private memory into userspace, but that approach failed to meet
several requirements for software-based CoCo VMs, e.g. pKVM, as the kernel
wouldn't easily be able to enforce a 1:1 page:guest association, let alone
a 1:1 pfn:gfn mapping.  And using PG_hwpoison does not work for memory
that isn't backed by 'struct page', e.g. if devices gain support for
exposing encrypted memory regions to guests.

Attempt #3 was to extend the memfd() syscall and wrap shmem to provide
dedicated file-based guest memory.  That approach made it as far as v10
before feedback from Hugh Dickins and Christian Brauner (and others) led
to it demise.

Hugh's objection was that piggybacking shmem made no sense for KVM's use
case as KVM didn't actually *want* the features provided by shmem.  I.e.
KVM was using memfd() and shmem to avoid having to manage memory directly,
not because memfd() and shmem were the optimal solution, e.g. things like
read/write/mmap in shmem were dead weight.

Christian pointed out flaws with implementing a partial overlay (wrapping
only _some_ of shmem), e.g. poking at inode_operations or super_operations
would show shmem stuff, but address_space_operations and file_operations
would show KVM's overlay.  Paraphrashing heavily, Christian suggested KVM
stop being lazy and create a proper API.

Link: https://lore.kernel.org/all/20201020061859.18385-1-kirill.shutemov@linux.intel.com
Link: https://lore.kernel.org/all/20210416154106.23721-1-kirill.shutemov@linux.intel.com
Link: https://lore.kernel.org/all/20210824005248.200037-1-seanjc@google.com
Link: https://lore.kernel.org/all/20211111141352.26311-1-chao.p.peng@linux.intel.com
Link: https://lore.kernel.org/all/20221202061347.1070246-1-chao.p.peng@linux.intel.com
Link: https://lore.kernel.org/all/ff5c5b97-acdf-9745-ebe5-c6609dd6322e@google.com
Link: https://lore.kernel.org/all/20230418-anfallen-irdisch-6993a61be10b@brauner
Link: https://lore.kernel.org/all/ZEM5Zq8oo+xnApW9@google.com
Link: https://lore.kernel.org/linux-mm/20230306191944.GA15773@monkey
Link: https://lore.kernel.org/linux-mm/ZII1p8ZHlHaQ3dDl@casper.infradead.org
Cc: Fuad Tabba <tabba@google.com>
Cc: Vishal Annapurve <vannapurve@google.com>
Cc: Ackerley Tng <ackerleytng@google.com>
Cc: Jarkko Sakkinen <jarkko@kernel.org>
Cc: Maciej Szmigiero <mail@maciej.szmigiero.name>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: David Hildenbrand <david@redhat.com>
Cc: Quentin Perret <qperret@google.com>
Cc: Michael Roth <michael.roth@amd.com>
Cc: Wang <wei.w.wang@intel.com>
Cc: Liam Merwick <liam.merwick@oracle.com>
Cc: Isaku Yamahata <isaku.yamahata@gmail.com>
Co-developed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Co-developed-by: Yu Zhang <yu.c.zhang@linux.intel.com>
Signed-off-by: Yu Zhang <yu.c.zhang@linux.intel.com>
Co-developed-by: Chao Peng <chao.p.peng@linux.intel.com>
Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
Co-developed-by: Ackerley Tng <ackerleytng@google.com>
Signed-off-by: Ackerley Tng <ackerleytng@google.com>
Co-developed-by: Isaku Yamahata <isaku.yamahata@intel.com>
Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
Co-developed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Co-developed-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20231027182217.3615211-17-seanjc@google.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virt/kvm/api.rst |  70 +++++-
 fs/anon_inodes.c               |   1 +
 include/linux/kvm_host.h       |  48 ++++
 include/uapi/linux/kvm.h       |  15 +-
 virt/kvm/Kconfig               |   4 +
 virt/kvm/Makefile.kvm          |   1 +
 virt/kvm/guest_memfd.c         | 538 +++++++++++++++++++++++++++++++++++++++++
 virt/kvm/kvm_main.c            |  59 ++++-
 virt/kvm/kvm_mm.h              |  26 ++
 9 files changed, 754 insertions(+), 8 deletions(-)
 create mode 100644 virt/kvm/guest_memfd.c

(limited to 'include')

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 081ef09d3148..1e61faf02b2a 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6201,6 +6201,15 @@ superset of the features supported by the system.
 :Parameters: struct kvm_userspace_memory_region2 (in)
 :Returns: 0 on success, -1 on error
 
+KVM_SET_USER_MEMORY_REGION2 is an extension to KVM_SET_USER_MEMORY_REGION that
+allows mapping guest_memfd memory into a guest.  All fields shared with
+KVM_SET_USER_MEMORY_REGION identically.  Userspace can set KVM_MEM_GUEST_MEMFD
+in flags to have KVM bind the memory region to a given guest_memfd range of
+[guest_memfd_offset, guest_memfd_offset + memory_size].  The target guest_memfd
+must point at a file created via KVM_CREATE_GUEST_MEMFD on the current VM, and
+the target range must not be bound to any other memory region.  All standard
+bounds checks apply (use common sense).
+
 ::
 
   struct kvm_userspace_memory_region2 {
@@ -6209,10 +6218,24 @@ superset of the features supported by the system.
 	__u64 guest_phys_addr;
 	__u64 memory_size; /* bytes */
 	__u64 userspace_addr; /* start of the userspace allocated memory */
-	__u64 pad[16];
+	__u64 guest_memfd_offset;
+	__u32 guest_memfd;
+	__u32 pad1;
+	__u64 pad2[14];
   };
 
-See KVM_SET_USER_MEMORY_REGION.
+A KVM_MEM_GUEST_MEMFD region _must_ have a valid guest_memfd (private memory) and
+userspace_addr (shared memory).  However, "valid" for userspace_addr simply
+means that the address itself must be a legal userspace address.  The backing
+mapping for userspace_addr is not required to be valid/populated at the time of
+KVM_SET_USER_MEMORY_REGION2, e.g. shared memory can be lazily mapped/allocated
+on-demand.
+
+When mapping a gfn into the guest, KVM selects shared vs. private, i.e consumes
+userspace_addr vs. guest_memfd, based on the gfn's KVM_MEMORY_ATTRIBUTE_PRIVATE
+state.  At VM creation time, all memory is shared, i.e. the PRIVATE attribute
+is '0' for all gfns.  Userspace can control whether memory is shared/private by
+toggling KVM_MEMORY_ATTRIBUTE_PRIVATE via KVM_SET_MEMORY_ATTRIBUTES as needed.
 
 4.141 KVM_SET_MEMORY_ATTRIBUTES
 -------------------------------
@@ -6250,6 +6273,49 @@ the state of a gfn/page as needed.
 
 The "flags" field is reserved for future extensions and must be '0'.
 
+4.142 KVM_CREATE_GUEST_MEMFD
+----------------------------
+
+:Capability: KVM_CAP_GUEST_MEMFD
+:Architectures: none
+:Type: vm ioctl
+:Parameters: struct kvm_create_guest_memfd(in)
+:Returns: 0 on success, <0 on error
+
+KVM_CREATE_GUEST_MEMFD creates an anonymous file and returns a file descriptor
+that refers to it.  guest_memfd files are roughly analogous to files created
+via memfd_create(), e.g. guest_memfd files live in RAM, have volatile storage,
+and are automatically released when the last reference is dropped.  Unlike
+"regular" memfd_create() files, guest_memfd files are bound to their owning
+virtual machine (see below), cannot be mapped, read, or written by userspace,
+and cannot be resized  (guest_memfd files do however support PUNCH_HOLE).
+
+::
+
+  struct kvm_create_guest_memfd {
+	__u64 size;
+	__u64 flags;
+	__u64 reserved[6];
+  };
+
+Conceptually, the inode backing a guest_memfd file represents physical memory,
+i.e. is coupled to the virtual machine as a thing, not to a "struct kvm".  The
+file itself, which is bound to a "struct kvm", is that instance's view of the
+underlying memory, e.g. effectively provides the translation of guest addresses
+to host memory.  This allows for use cases where multiple KVM structures are
+used to manage a single virtual machine, e.g. when performing intrahost
+migration of a virtual machine.
+
+KVM currently only supports mapping guest_memfd via KVM_SET_USER_MEMORY_REGION2,
+and more specifically via the guest_memfd and guest_memfd_offset fields in
+"struct kvm_userspace_memory_region2", where guest_memfd_offset is the offset
+into the guest_memfd instance.  For a given guest_memfd file, there can be at
+most one mapping per page, i.e. binding multiple memory regions to a single
+guest_memfd range is not allowed (any number of memory regions can be bound to
+a single guest_memfd file, but the bound ranges must not overlap).
+
+See KVM_SET_USER_MEMORY_REGION2 for additional details.
+
 5. The kvm_run structure
 ========================
 
diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
index 42b02dc36474..8dd436ee985b 100644
--- a/fs/anon_inodes.c
+++ b/fs/anon_inodes.c
@@ -183,6 +183,7 @@ struct file *anon_inode_create_getfile(const char *name,
 	return __anon_inode_getfile(name, fops, priv, flags,
 				    context_inode, true);
 }
+EXPORT_SYMBOL_GPL(anon_inode_create_getfile);
 
 static int __anon_inode_getfd(const char *name,
 			      const struct file_operations *fops,
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 68a144cb7dbc..a6de526c0426 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -589,8 +589,20 @@ struct kvm_memory_slot {
 	u32 flags;
 	short id;
 	u16 as_id;
+
+#ifdef CONFIG_KVM_PRIVATE_MEM
+	struct {
+		struct file __rcu *file;
+		pgoff_t pgoff;
+	} gmem;
+#endif
 };
 
+static inline bool kvm_slot_can_be_private(const struct kvm_memory_slot *slot)
+{
+	return slot && (slot->flags & KVM_MEM_GUEST_MEMFD);
+}
+
 static inline bool kvm_slot_dirty_track_enabled(const struct kvm_memory_slot *slot)
 {
 	return slot->flags & KVM_MEM_LOG_DIRTY_PAGES;
@@ -685,6 +697,17 @@ static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu)
 }
 #endif
 
+/*
+ * Arch code must define kvm_arch_has_private_mem if support for private memory
+ * is enabled.
+ */
+#if !defined(kvm_arch_has_private_mem) && !IS_ENABLED(CONFIG_KVM_PRIVATE_MEM)
+static inline bool kvm_arch_has_private_mem(struct kvm *kvm)
+{
+	return false;
+}
+#endif
+
 struct kvm_memslots {
 	u64 generation;
 	atomic_long_t last_used_slot;
@@ -1400,6 +1423,7 @@ void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc);
 void kvm_mmu_invalidate_begin(struct kvm *kvm);
 void kvm_mmu_invalidate_range_add(struct kvm *kvm, gfn_t start, gfn_t end);
 void kvm_mmu_invalidate_end(struct kvm *kvm);
+bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range);
 
 long kvm_arch_dev_ioctl(struct file *filp,
 			unsigned int ioctl, unsigned long arg);
@@ -2355,6 +2379,30 @@ bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
 					struct kvm_gfn_range *range);
 bool kvm_arch_post_set_memory_attributes(struct kvm *kvm,
 					 struct kvm_gfn_range *range);
+
+static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
+{
+	return IS_ENABLED(CONFIG_KVM_PRIVATE_MEM) &&
+	       kvm_get_memory_attributes(kvm, gfn) & KVM_MEMORY_ATTRIBUTE_PRIVATE;
+}
+#else
+static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
+{
+	return false;
+}
 #endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */
 
+#ifdef CONFIG_KVM_PRIVATE_MEM
+int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
+		     gfn_t gfn, kvm_pfn_t *pfn, int *max_order);
+#else
+static inline int kvm_gmem_get_pfn(struct kvm *kvm,
+				   struct kvm_memory_slot *slot, gfn_t gfn,
+				   kvm_pfn_t *pfn, int *max_order)
+{
+	KVM_BUG_ON(1, kvm);
+	return -EIO;
+}
+#endif /* CONFIG_KVM_PRIVATE_MEM */
+
 #endif
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index e8d167e54980..2802d10aa88c 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -102,7 +102,10 @@ struct kvm_userspace_memory_region2 {
 	__u64 guest_phys_addr;
 	__u64 memory_size;
 	__u64 userspace_addr;
-	__u64 pad[16];
+	__u64 guest_memfd_offset;
+	__u32 guest_memfd;
+	__u32 pad1;
+	__u64 pad2[14];
 };
 
 /*
@@ -112,6 +115,7 @@ struct kvm_userspace_memory_region2 {
  */
 #define KVM_MEM_LOG_DIRTY_PAGES	(1UL << 0)
 #define KVM_MEM_READONLY	(1UL << 1)
+#define KVM_MEM_GUEST_MEMFD	(1UL << 2)
 
 /* for KVM_IRQ_LINE */
 struct kvm_irq_level {
@@ -1221,6 +1225,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_USER_MEMORY2 231
 #define KVM_CAP_MEMORY_FAULT_INFO 232
 #define KVM_CAP_MEMORY_ATTRIBUTES 233
+#define KVM_CAP_GUEST_MEMFD 234
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -2301,4 +2306,12 @@ struct kvm_memory_attributes {
 
 #define KVM_MEMORY_ATTRIBUTE_PRIVATE           (1ULL << 3)
 
+#define KVM_CREATE_GUEST_MEMFD	_IOWR(KVMIO,  0xd4, struct kvm_create_guest_memfd)
+
+struct kvm_create_guest_memfd {
+	__u64 size;
+	__u64 flags;
+	__u64 reserved[6];
+};
+
 #endif /* __LINUX_KVM_H */
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 5bd7fcaf9089..08afef022db9 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -100,3 +100,7 @@ config KVM_GENERIC_MMU_NOTIFIER
 config KVM_GENERIC_MEMORY_ATTRIBUTES
        select KVM_GENERIC_MMU_NOTIFIER
        bool
+
+config KVM_PRIVATE_MEM
+       select XARRAY_MULTI
+       bool
diff --git a/virt/kvm/Makefile.kvm b/virt/kvm/Makefile.kvm
index 2c27d5d0c367..724c89af78af 100644
--- a/virt/kvm/Makefile.kvm
+++ b/virt/kvm/Makefile.kvm
@@ -12,3 +12,4 @@ kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o
 kvm-$(CONFIG_HAVE_KVM_IRQ_ROUTING) += $(KVM)/irqchip.o
 kvm-$(CONFIG_HAVE_KVM_DIRTY_RING) += $(KVM)/dirty_ring.o
 kvm-$(CONFIG_HAVE_KVM_PFNCACHE) += $(KVM)/pfncache.o
+kvm-$(CONFIG_KVM_PRIVATE_MEM) += $(KVM)/guest_memfd.o
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
new file mode 100644
index 000000000000..e65f4170425c
--- /dev/null
+++ b/virt/kvm/guest_memfd.c
@@ -0,0 +1,538 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/backing-dev.h>
+#include <linux/falloc.h>
+#include <linux/kvm_host.h>
+#include <linux/pagemap.h>
+#include <linux/anon_inodes.h>
+
+#include "kvm_mm.h"
+
+struct kvm_gmem {
+	struct kvm *kvm;
+	struct xarray bindings;
+	struct list_head entry;
+};
+
+static struct folio *kvm_gmem_get_folio(struct inode *inode, pgoff_t index)
+{
+	struct folio *folio;
+
+	/* TODO: Support huge pages. */
+	folio = filemap_grab_folio(inode->i_mapping, index);
+	if (IS_ERR_OR_NULL(folio))
+		return NULL;
+
+	/*
+	 * Use the up-to-date flag to track whether or not the memory has been
+	 * zeroed before being handed off to the guest.  There is no backing
+	 * storage for the memory, so the folio will remain up-to-date until
+	 * it's removed.
+	 *
+	 * TODO: Skip clearing pages when trusted firmware will do it when
+	 * assigning memory to the guest.
+	 */
+	if (!folio_test_uptodate(folio)) {
+		unsigned long nr_pages = folio_nr_pages(folio);
+		unsigned long i;
+
+		for (i = 0; i < nr_pages; i++)
+			clear_highpage(folio_page(folio, i));
+
+		folio_mark_uptodate(folio);
+	}
+
+	/*
+	 * Ignore accessed, referenced, and dirty flags.  The memory is
+	 * unevictable and there is no storage to write back to.
+	 */
+	return folio;
+}
+
+static void kvm_gmem_invalidate_begin(struct kvm_gmem *gmem, pgoff_t start,
+				      pgoff_t end)
+{
+	bool flush = false, found_memslot = false;
+	struct kvm_memory_slot *slot;
+	struct kvm *kvm = gmem->kvm;
+	unsigned long index;
+
+	xa_for_each_range(&gmem->bindings, index, slot, start, end - 1) {
+		pgoff_t pgoff = slot->gmem.pgoff;
+
+		struct kvm_gfn_range gfn_range = {
+			.start = slot->base_gfn + max(pgoff, start) - pgoff,
+			.end = slot->base_gfn + min(pgoff + slot->npages, end) - pgoff,
+			.slot = slot,
+			.may_block = true,
+		};
+
+		if (!found_memslot) {
+			found_memslot = true;
+
+			KVM_MMU_LOCK(kvm);
+			kvm_mmu_invalidate_begin(kvm);
+		}
+
+		flush |= kvm_mmu_unmap_gfn_range(kvm, &gfn_range);
+	}
+
+	if (flush)
+		kvm_flush_remote_tlbs(kvm);
+
+	if (found_memslot)
+		KVM_MMU_UNLOCK(kvm);
+}
+
+static void kvm_gmem_invalidate_end(struct kvm_gmem *gmem, pgoff_t start,
+				    pgoff_t end)
+{
+	struct kvm *kvm = gmem->kvm;
+
+	if (xa_find(&gmem->bindings, &start, end - 1, XA_PRESENT)) {
+		KVM_MMU_LOCK(kvm);
+		kvm_mmu_invalidate_end(kvm);
+		KVM_MMU_UNLOCK(kvm);
+	}
+}
+
+static long kvm_gmem_punch_hole(struct inode *inode, loff_t offset, loff_t len)
+{
+	struct list_head *gmem_list = &inode->i_mapping->private_list;
+	pgoff_t start = offset >> PAGE_SHIFT;
+	pgoff_t end = (offset + len) >> PAGE_SHIFT;
+	struct kvm_gmem *gmem;
+
+	/*
+	 * Bindings must be stable across invalidation to ensure the start+end
+	 * are balanced.
+	 */
+	filemap_invalidate_lock(inode->i_mapping);
+
+	list_for_each_entry(gmem, gmem_list, entry)
+		kvm_gmem_invalidate_begin(gmem, start, end);
+
+	truncate_inode_pages_range(inode->i_mapping, offset, offset + len - 1);
+
+	list_for_each_entry(gmem, gmem_list, entry)
+		kvm_gmem_invalidate_end(gmem, start, end);
+
+	filemap_invalidate_unlock(inode->i_mapping);
+
+	return 0;
+}
+
+static long kvm_gmem_allocate(struct inode *inode, loff_t offset, loff_t len)
+{
+	struct address_space *mapping = inode->i_mapping;
+	pgoff_t start, index, end;
+	int r;
+
+	/* Dedicated guest is immutable by default. */
+	if (offset + len > i_size_read(inode))
+		return -EINVAL;
+
+	filemap_invalidate_lock_shared(mapping);
+
+	start = offset >> PAGE_SHIFT;
+	end = (offset + len) >> PAGE_SHIFT;
+
+	r = 0;
+	for (index = start; index < end; ) {
+		struct folio *folio;
+
+		if (signal_pending(current)) {
+			r = -EINTR;
+			break;
+		}
+
+		folio = kvm_gmem_get_folio(inode, index);
+		if (!folio) {
+			r = -ENOMEM;
+			break;
+		}
+
+		index = folio_next_index(folio);
+
+		folio_unlock(folio);
+		folio_put(folio);
+
+		/* 64-bit only, wrapping the index should be impossible. */
+		if (WARN_ON_ONCE(!index))
+			break;
+
+		cond_resched();
+	}
+
+	filemap_invalidate_unlock_shared(mapping);
+
+	return r;
+}
+
+static long kvm_gmem_fallocate(struct file *file, int mode, loff_t offset,
+			       loff_t len)
+{
+	int ret;
+
+	if (!(mode & FALLOC_FL_KEEP_SIZE))
+		return -EOPNOTSUPP;
+
+	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
+		return -EOPNOTSUPP;
+
+	if (!PAGE_ALIGNED(offset) || !PAGE_ALIGNED(len))
+		return -EINVAL;
+
+	if (mode & FALLOC_FL_PUNCH_HOLE)
+		ret = kvm_gmem_punch_hole(file_inode(file), offset, len);
+	else
+		ret = kvm_gmem_allocate(file_inode(file), offset, len);
+
+	if (!ret)
+		file_modified(file);
+	return ret;
+}
+
+static int kvm_gmem_release(struct inode *inode, struct file *file)
+{
+	struct kvm_gmem *gmem = file->private_data;
+	struct kvm_memory_slot *slot;
+	struct kvm *kvm = gmem->kvm;
+	unsigned long index;
+
+	/*
+	 * Prevent concurrent attempts to *unbind* a memslot.  This is the last
+	 * reference to the file and thus no new bindings can be created, but
+	 * dereferencing the slot for existing bindings needs to be protected
+	 * against memslot updates, specifically so that unbind doesn't race
+	 * and free the memslot (kvm_gmem_get_file() will return NULL).
+	 */
+	mutex_lock(&kvm->slots_lock);
+
+	filemap_invalidate_lock(inode->i_mapping);
+
+	xa_for_each(&gmem->bindings, index, slot)
+		rcu_assign_pointer(slot->gmem.file, NULL);
+
+	synchronize_rcu();
+
+	/*
+	 * All in-flight operations are gone and new bindings can be created.
+	 * Zap all SPTEs pointed at by this file.  Do not free the backing
+	 * memory, as its lifetime is associated with the inode, not the file.
+	 */
+	kvm_gmem_invalidate_begin(gmem, 0, -1ul);
+	kvm_gmem_invalidate_end(gmem, 0, -1ul);
+
+	list_del(&gmem->entry);
+
+	filemap_invalidate_unlock(inode->i_mapping);
+
+	mutex_unlock(&kvm->slots_lock);
+
+	xa_destroy(&gmem->bindings);
+	kfree(gmem);
+
+	kvm_put_kvm(kvm);
+
+	return 0;
+}
+
+static struct file *kvm_gmem_get_file(struct kvm_memory_slot *slot)
+{
+	struct file *file;
+
+	rcu_read_lock();
+
+	file = rcu_dereference(slot->gmem.file);
+	if (file && !get_file_rcu(file))
+		file = NULL;
+
+	rcu_read_unlock();
+
+	return file;
+}
+
+static struct file_operations kvm_gmem_fops = {
+	.open		= generic_file_open,
+	.release	= kvm_gmem_release,
+	.fallocate	= kvm_gmem_fallocate,
+};
+
+void kvm_gmem_init(struct module *module)
+{
+	kvm_gmem_fops.owner = module;
+}
+
+static int kvm_gmem_migrate_folio(struct address_space *mapping,
+				  struct folio *dst, struct folio *src,
+				  enum migrate_mode mode)
+{
+	WARN_ON_ONCE(1);
+	return -EINVAL;
+}
+
+static int kvm_gmem_error_page(struct address_space *mapping, struct page *page)
+{
+	struct list_head *gmem_list = &mapping->private_list;
+	struct kvm_gmem *gmem;
+	pgoff_t start, end;
+
+	filemap_invalidate_lock_shared(mapping);
+
+	start = page->index;
+	end = start + thp_nr_pages(page);
+
+	list_for_each_entry(gmem, gmem_list, entry)
+		kvm_gmem_invalidate_begin(gmem, start, end);
+
+	/*
+	 * Do not truncate the range, what action is taken in response to the
+	 * error is userspace's decision (assuming the architecture supports
+	 * gracefully handling memory errors).  If/when the guest attempts to
+	 * access a poisoned page, kvm_gmem_get_pfn() will return -EHWPOISON,
+	 * at which point KVM can either terminate the VM or propagate the
+	 * error to userspace.
+	 */
+
+	list_for_each_entry(gmem, gmem_list, entry)
+		kvm_gmem_invalidate_end(gmem, start, end);
+
+	filemap_invalidate_unlock_shared(mapping);
+
+	return MF_DELAYED;
+}
+
+static const struct address_space_operations kvm_gmem_aops = {
+	.dirty_folio = noop_dirty_folio,
+#ifdef CONFIG_MIGRATION
+	.migrate_folio	= kvm_gmem_migrate_folio,
+#endif
+	.error_remove_page = kvm_gmem_error_page,
+};
+
+static int kvm_gmem_getattr(struct mnt_idmap *idmap, const struct path *path,
+			    struct kstat *stat, u32 request_mask,
+			    unsigned int query_flags)
+{
+	struct inode *inode = path->dentry->d_inode;
+
+	generic_fillattr(idmap, request_mask, inode, stat);
+	return 0;
+}
+
+static int kvm_gmem_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
+			    struct iattr *attr)
+{
+	return -EINVAL;
+}
+static const struct inode_operations kvm_gmem_iops = {
+	.getattr	= kvm_gmem_getattr,
+	.setattr	= kvm_gmem_setattr,
+};
+
+static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags)
+{
+	const char *anon_name = "[kvm-gmem]";
+	struct kvm_gmem *gmem;
+	struct inode *inode;
+	struct file *file;
+	int fd, err;
+
+	fd = get_unused_fd_flags(0);
+	if (fd < 0)
+		return fd;
+
+	gmem = kzalloc(sizeof(*gmem), GFP_KERNEL);
+	if (!gmem) {
+		err = -ENOMEM;
+		goto err_fd;
+	}
+
+	file = anon_inode_create_getfile(anon_name, &kvm_gmem_fops, gmem,
+					 O_RDWR, NULL);
+	if (IS_ERR(file)) {
+		err = PTR_ERR(file);
+		goto err_gmem;
+	}
+
+	file->f_flags |= O_LARGEFILE;
+
+	inode = file->f_inode;
+	WARN_ON(file->f_mapping != inode->i_mapping);
+
+	inode->i_private = (void *)(unsigned long)flags;
+	inode->i_op = &kvm_gmem_iops;
+	inode->i_mapping->a_ops = &kvm_gmem_aops;
+	inode->i_mode |= S_IFREG;
+	inode->i_size = size;
+	mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER);
+	mapping_set_unmovable(inode->i_mapping);
+	/* Unmovable mappings are supposed to be marked unevictable as well. */
+	WARN_ON_ONCE(!mapping_unevictable(inode->i_mapping));
+
+	kvm_get_kvm(kvm);
+	gmem->kvm = kvm;
+	xa_init(&gmem->bindings);
+	list_add(&gmem->entry, &inode->i_mapping->private_list);
+
+	fd_install(fd, file);
+	return fd;
+
+err_gmem:
+	kfree(gmem);
+err_fd:
+	put_unused_fd(fd);
+	return err;
+}
+
+int kvm_gmem_create(struct kvm *kvm, struct kvm_create_guest_memfd *args)
+{
+	loff_t size = args->size;
+	u64 flags = args->flags;
+	u64 valid_flags = 0;
+
+	if (flags & ~valid_flags)
+		return -EINVAL;
+
+	if (size <= 0 || !PAGE_ALIGNED(size))
+		return -EINVAL;
+
+	return __kvm_gmem_create(kvm, size, flags);
+}
+
+int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot,
+		  unsigned int fd, loff_t offset)
+{
+	loff_t size = slot->npages << PAGE_SHIFT;
+	unsigned long start, end;
+	struct kvm_gmem *gmem;
+	struct inode *inode;
+	struct file *file;
+	int r = -EINVAL;
+
+	BUILD_BUG_ON(sizeof(gfn_t) != sizeof(slot->gmem.pgoff));
+
+	file = fget(fd);
+	if (!file)
+		return -EBADF;
+
+	if (file->f_op != &kvm_gmem_fops)
+		goto err;
+
+	gmem = file->private_data;
+	if (gmem->kvm != kvm)
+		goto err;
+
+	inode = file_inode(file);
+
+	if (offset < 0 || !PAGE_ALIGNED(offset) ||
+	    offset + size > i_size_read(inode))
+		goto err;
+
+	filemap_invalidate_lock(inode->i_mapping);
+
+	start = offset >> PAGE_SHIFT;
+	end = start + slot->npages;
+
+	if (!xa_empty(&gmem->bindings) &&
+	    xa_find(&gmem->bindings, &start, end - 1, XA_PRESENT)) {
+		filemap_invalidate_unlock(inode->i_mapping);
+		goto err;
+	}
+
+	/*
+	 * No synchronize_rcu() needed, any in-flight readers are guaranteed to
+	 * be see either a NULL file or this new file, no need for them to go
+	 * away.
+	 */
+	rcu_assign_pointer(slot->gmem.file, file);
+	slot->gmem.pgoff = start;
+
+	xa_store_range(&gmem->bindings, start, end - 1, slot, GFP_KERNEL);
+	filemap_invalidate_unlock(inode->i_mapping);
+
+	/*
+	 * Drop the reference to the file, even on success.  The file pins KVM,
+	 * not the other way 'round.  Active bindings are invalidated if the
+	 * file is closed before memslots are destroyed.
+	 */
+	r = 0;
+err:
+	fput(file);
+	return r;
+}
+
+void kvm_gmem_unbind(struct kvm_memory_slot *slot)
+{
+	unsigned long start = slot->gmem.pgoff;
+	unsigned long end = start + slot->npages;
+	struct kvm_gmem *gmem;
+	struct file *file;
+
+	/*
+	 * Nothing to do if the underlying file was already closed (or is being
+	 * closed right now), kvm_gmem_release() invalidates all bindings.
+	 */
+	file = kvm_gmem_get_file(slot);
+	if (!file)
+		return;
+
+	gmem = file->private_data;
+
+	filemap_invalidate_lock(file->f_mapping);
+	xa_store_range(&gmem->bindings, start, end - 1, NULL, GFP_KERNEL);
+	rcu_assign_pointer(slot->gmem.file, NULL);
+	synchronize_rcu();
+	filemap_invalidate_unlock(file->f_mapping);
+
+	fput(file);
+}
+
+int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
+		     gfn_t gfn, kvm_pfn_t *pfn, int *max_order)
+{
+	pgoff_t index = gfn - slot->base_gfn + slot->gmem.pgoff;
+	struct kvm_gmem *gmem;
+	struct folio *folio;
+	struct page *page;
+	struct file *file;
+	int r;
+
+	file = kvm_gmem_get_file(slot);
+	if (!file)
+		return -EFAULT;
+
+	gmem = file->private_data;
+
+	if (WARN_ON_ONCE(xa_load(&gmem->bindings, index) != slot)) {
+		r = -EIO;
+		goto out_fput;
+	}
+
+	folio = kvm_gmem_get_folio(file_inode(file), index);
+	if (!folio) {
+		r = -ENOMEM;
+		goto out_fput;
+	}
+
+	if (folio_test_hwpoison(folio)) {
+		r = -EHWPOISON;
+		goto out_unlock;
+	}
+
+	page = folio_file_page(folio, index);
+
+	*pfn = page_to_pfn(page);
+	if (max_order)
+		*max_order = 0;
+
+	r = 0;
+
+out_unlock:
+	folio_unlock(folio);
+out_fput:
+	fput(file);
+
+	return r;
+}
+EXPORT_SYMBOL_GPL(kvm_gmem_get_pfn);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index f1a575d39b3b..8f46d757a2c5 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -791,7 +791,7 @@ void kvm_mmu_invalidate_range_add(struct kvm *kvm, gfn_t start, gfn_t end)
 	}
 }
 
-static bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
+bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
 {
 	kvm_mmu_invalidate_range_add(kvm, range->start, range->end);
 	return kvm_unmap_gfn_range(kvm, range);
@@ -1027,6 +1027,9 @@ static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot)
 /* This does not remove the slot from struct kvm_memslots data structures */
 static void kvm_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot)
 {
+	if (slot->flags & KVM_MEM_GUEST_MEMFD)
+		kvm_gmem_unbind(slot);
+
 	kvm_destroy_dirty_bitmap(slot);
 
 	kvm_arch_free_memslot(kvm, slot);
@@ -1606,10 +1609,18 @@ static void kvm_replace_memslot(struct kvm *kvm,
 #define KVM_SET_USER_MEMORY_REGION_V1_FLAGS \
 	(KVM_MEM_LOG_DIRTY_PAGES | KVM_MEM_READONLY)
 
-static int check_memory_region_flags(const struct kvm_userspace_memory_region2 *mem)
+static int check_memory_region_flags(struct kvm *kvm,
+				     const struct kvm_userspace_memory_region2 *mem)
 {
 	u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES;
 
+	if (kvm_arch_has_private_mem(kvm))
+		valid_flags |= KVM_MEM_GUEST_MEMFD;
+
+	/* Dirty logging private memory is not currently supported. */
+	if (mem->flags & KVM_MEM_GUEST_MEMFD)
+		valid_flags &= ~KVM_MEM_LOG_DIRTY_PAGES;
+
 #ifdef __KVM_HAVE_READONLY_MEM
 	valid_flags |= KVM_MEM_READONLY;
 #endif
@@ -2018,7 +2029,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	int as_id, id;
 	int r;
 
-	r = check_memory_region_flags(mem);
+	r = check_memory_region_flags(kvm, mem);
 	if (r)
 		return r;
 
@@ -2037,6 +2048,10 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	     !access_ok((void __user *)(unsigned long)mem->userspace_addr,
 			mem->memory_size))
 		return -EINVAL;
+	if (mem->flags & KVM_MEM_GUEST_MEMFD &&
+	    (mem->guest_memfd_offset & (PAGE_SIZE - 1) ||
+	     mem->guest_memfd_offset + mem->memory_size < mem->guest_memfd_offset))
+		return -EINVAL;
 	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_MEM_SLOTS_NUM)
 		return -EINVAL;
 	if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr)
@@ -2075,6 +2090,9 @@ int __kvm_set_memory_region(struct kvm *kvm,
 		if ((kvm->nr_memslot_pages + npages) < kvm->nr_memslot_pages)
 			return -EINVAL;
 	} else { /* Modify an existing slot. */
+		/* Private memslots are immutable, they can only be deleted. */
+		if (mem->flags & KVM_MEM_GUEST_MEMFD)
+			return -EINVAL;
 		if ((mem->userspace_addr != old->userspace_addr) ||
 		    (npages != old->npages) ||
 		    ((mem->flags ^ old->flags) & KVM_MEM_READONLY))
@@ -2103,10 +2121,23 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	new->npages = npages;
 	new->flags = mem->flags;
 	new->userspace_addr = mem->userspace_addr;
+	if (mem->flags & KVM_MEM_GUEST_MEMFD) {
+		r = kvm_gmem_bind(kvm, new, mem->guest_memfd, mem->guest_memfd_offset);
+		if (r)
+			goto out;
+	}
 
 	r = kvm_set_memslot(kvm, old, new, change);
 	if (r)
-		kfree(new);
+		goto out_unbind;
+
+	return 0;
+
+out_unbind:
+	if (mem->flags & KVM_MEM_GUEST_MEMFD)
+		kvm_gmem_unbind(new);
+out:
+	kfree(new);
 	return r;
 }
 EXPORT_SYMBOL_GPL(__kvm_set_memory_region);
@@ -2442,7 +2473,7 @@ out:
 
 static u64 kvm_supported_mem_attributes(struct kvm *kvm)
 {
-	if (!kvm)
+	if (!kvm || kvm_arch_has_private_mem(kvm))
 		return KVM_MEMORY_ATTRIBUTE_PRIVATE;
 
 	return 0;
@@ -4844,6 +4875,10 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
 	case KVM_CAP_MEMORY_ATTRIBUTES:
 		return kvm_supported_mem_attributes(kvm);
+#endif
+#ifdef CONFIG_KVM_PRIVATE_MEM
+	case KVM_CAP_GUEST_MEMFD:
+		return !kvm || kvm_arch_has_private_mem(kvm);
 #endif
 	default:
 		break;
@@ -5277,6 +5312,18 @@ static long kvm_vm_ioctl(struct file *filp,
 	case KVM_GET_STATS_FD:
 		r = kvm_vm_ioctl_get_stats_fd(kvm);
 		break;
+#ifdef CONFIG_KVM_PRIVATE_MEM
+	case KVM_CREATE_GUEST_MEMFD: {
+		struct kvm_create_guest_memfd guest_memfd;
+
+		r = -EFAULT;
+		if (copy_from_user(&guest_memfd, argp, sizeof(guest_memfd)))
+			goto out;
+
+		r = kvm_gmem_create(kvm, &guest_memfd);
+		break;
+	}
+#endif
 	default:
 		r = kvm_arch_vm_ioctl(filp, ioctl, arg);
 	}
@@ -6409,6 +6456,8 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module)
 	if (WARN_ON_ONCE(r))
 		goto err_vfio;
 
+	kvm_gmem_init(module);
+
 	/*
 	 * Registration _must_ be the very last thing done, as this exposes
 	 * /dev/kvm to userspace, i.e. all infrastructure must be setup!
diff --git a/virt/kvm/kvm_mm.h b/virt/kvm/kvm_mm.h
index 180f1a09e6ba..ecefc7ec51af 100644
--- a/virt/kvm/kvm_mm.h
+++ b/virt/kvm/kvm_mm.h
@@ -37,4 +37,30 @@ static inline void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm,
 }
 #endif /* HAVE_KVM_PFNCACHE */
 
+#ifdef CONFIG_KVM_PRIVATE_MEM
+void kvm_gmem_init(struct module *module);
+int kvm_gmem_create(struct kvm *kvm, struct kvm_create_guest_memfd *args);
+int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot,
+		  unsigned int fd, loff_t offset);
+void kvm_gmem_unbind(struct kvm_memory_slot *slot);
+#else
+static inline void kvm_gmem_init(struct module *module)
+{
+
+}
+
+static inline int kvm_gmem_bind(struct kvm *kvm,
+					 struct kvm_memory_slot *slot,
+					 unsigned int fd, loff_t offset)
+{
+	WARN_ON_ONCE(1);
+	return -EIO;
+}
+
+static inline void kvm_gmem_unbind(struct kvm_memory_slot *slot)
+{
+	WARN_ON_ONCE(1);
+}
+#endif /* CONFIG_KVM_PRIVATE_MEM */
+
 #endif /* __KVM_MM_H__ */
-- 
cgit v1.2.3


From 8dd2eee9d526c30fccfe75da7ec5365c6476e510 Mon Sep 17 00:00:00 2001
From: Chao Peng <chao.p.peng@linux.intel.com>
Date: Fri, 27 Oct 2023 11:22:02 -0700
Subject: KVM: x86/mmu: Handle page fault for private memory

Add support for resolving page faults on guest private memory for VMs
that differentiate between "shared" and "private" memory.  For such VMs,
KVM_MEM_GUEST_MEMFD memslots can include both fd-based private memory and
hva-based shared memory, and KVM needs to map in the "correct" variant,
i.e. KVM needs to map the gfn shared/private as appropriate based on the
current state of the gfn's KVM_MEMORY_ATTRIBUTE_PRIVATE flag.

For AMD's SEV-SNP and Intel's TDX, the guest effectively gets to request
shared vs. private via a bit in the guest page tables, i.e. what the guest
wants may conflict with the current memory attributes.  To support such
"implicit" conversion requests, exit to user with KVM_EXIT_MEMORY_FAULT
to forward the request to userspace.  Add a new flag for memory faults,
KVM_MEMORY_EXIT_FLAG_PRIVATE, to communicate whether the guest wants to
map memory as shared vs. private.

Like KVM_MEMORY_ATTRIBUTE_PRIVATE, use bit 3 for flagging private memory
so that KVM can use bits 0-2 for capturing RWX behavior if/when userspace
needs such information, e.g. a likely user of KVM_EXIT_MEMORY_FAULT is to
exit on missing mappings when handling guest page fault VM-Exits.  In
that case, userspace will want to know RWX information in order to
correctly/precisely resolve the fault.

Note, private memory *must* be backed by guest_memfd, i.e. shared mappings
always come from the host userspace page tables, and private mappings
always come from a guest_memfd instance.

Co-developed-by: Yu Zhang <yu.c.zhang@linux.intel.com>
Signed-off-by: Yu Zhang <yu.c.zhang@linux.intel.com>
Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Message-Id: <20231027182217.3615211-21-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virt/kvm/api.rst  |   8 +++-
 arch/x86/kvm/mmu/mmu.c          | 101 ++++++++++++++++++++++++++++++++++++++--
 arch/x86/kvm/mmu/mmu_internal.h |   1 +
 include/linux/kvm_host.h        |   8 +++-
 include/uapi/linux/kvm.h        |   1 +
 5 files changed, 110 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 1e61faf02b2a..726c87c35d57 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6952,6 +6952,7 @@ spec refer, https://github.com/riscv/riscv-sbi-doc.
 
 		/* KVM_EXIT_MEMORY_FAULT */
 		struct {
+  #define KVM_MEMORY_EXIT_FLAG_PRIVATE	(1ULL << 3)
 			__u64 flags;
 			__u64 gpa;
 			__u64 size;
@@ -6960,8 +6961,11 @@ spec refer, https://github.com/riscv/riscv-sbi-doc.
 KVM_EXIT_MEMORY_FAULT indicates the vCPU has encountered a memory fault that
 could not be resolved by KVM.  The 'gpa' and 'size' (in bytes) describe the
 guest physical address range [gpa, gpa + size) of the fault.  The 'flags' field
-describes properties of the faulting access that are likely pertinent.
-Currently, no flags are defined.
+describes properties of the faulting access that are likely pertinent:
+
+ - KVM_MEMORY_EXIT_FLAG_PRIVATE - When set, indicates the memory fault occurred
+   on a private memory access.  When clear, indicates the fault occurred on a
+   shared access.
 
 Note!  KVM_EXIT_MEMORY_FAULT is unique among all KVM exit reasons in that it
 accompanies a return code of '-1', not '0'!  errno will always be set to EFAULT
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index f5c6b0643645..754a5aaebee5 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3147,9 +3147,9 @@ out:
 	return level;
 }
 
-int kvm_mmu_max_mapping_level(struct kvm *kvm,
-			      const struct kvm_memory_slot *slot, gfn_t gfn,
-			      int max_level)
+static int __kvm_mmu_max_mapping_level(struct kvm *kvm,
+				       const struct kvm_memory_slot *slot,
+				       gfn_t gfn, int max_level, bool is_private)
 {
 	struct kvm_lpage_info *linfo;
 	int host_level;
@@ -3161,6 +3161,9 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm,
 			break;
 	}
 
+	if (is_private)
+		return max_level;
+
 	if (max_level == PG_LEVEL_4K)
 		return PG_LEVEL_4K;
 
@@ -3168,6 +3171,16 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm,
 	return min(host_level, max_level);
 }
 
+int kvm_mmu_max_mapping_level(struct kvm *kvm,
+			      const struct kvm_memory_slot *slot, gfn_t gfn,
+			      int max_level)
+{
+	bool is_private = kvm_slot_can_be_private(slot) &&
+			  kvm_mem_is_private(kvm, gfn);
+
+	return __kvm_mmu_max_mapping_level(kvm, slot, gfn, max_level, is_private);
+}
+
 void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 {
 	struct kvm_memory_slot *slot = fault->slot;
@@ -3188,8 +3201,9 @@ void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	 * Enforce the iTLB multihit workaround after capturing the requested
 	 * level, which will be used to do precise, accurate accounting.
 	 */
-	fault->req_level = kvm_mmu_max_mapping_level(vcpu->kvm, slot,
-						     fault->gfn, fault->max_level);
+	fault->req_level = __kvm_mmu_max_mapping_level(vcpu->kvm, slot,
+						       fault->gfn, fault->max_level,
+						       fault->is_private);
 	if (fault->req_level == PG_LEVEL_4K || fault->huge_page_disallowed)
 		return;
 
@@ -4269,6 +4283,55 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
 	kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true, NULL);
 }
 
+static inline u8 kvm_max_level_for_order(int order)
+{
+	BUILD_BUG_ON(KVM_MAX_HUGEPAGE_LEVEL > PG_LEVEL_1G);
+
+	KVM_MMU_WARN_ON(order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G) &&
+			order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M) &&
+			order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_4K));
+
+	if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G))
+		return PG_LEVEL_1G;
+
+	if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M))
+		return PG_LEVEL_2M;
+
+	return PG_LEVEL_4K;
+}
+
+static void kvm_mmu_prepare_memory_fault_exit(struct kvm_vcpu *vcpu,
+					      struct kvm_page_fault *fault)
+{
+	kvm_prepare_memory_fault_exit(vcpu, fault->gfn << PAGE_SHIFT,
+				      PAGE_SIZE, fault->write, fault->exec,
+				      fault->is_private);
+}
+
+static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu,
+				   struct kvm_page_fault *fault)
+{
+	int max_order, r;
+
+	if (!kvm_slot_can_be_private(fault->slot)) {
+		kvm_mmu_prepare_memory_fault_exit(vcpu, fault);
+		return -EFAULT;
+	}
+
+	r = kvm_gmem_get_pfn(vcpu->kvm, fault->slot, fault->gfn, &fault->pfn,
+			     &max_order);
+	if (r) {
+		kvm_mmu_prepare_memory_fault_exit(vcpu, fault);
+		return r;
+	}
+
+	fault->max_level = min(kvm_max_level_for_order(max_order),
+			       fault->max_level);
+	fault->map_writable = !(fault->slot->flags & KVM_MEM_READONLY);
+
+	return RET_PF_CONTINUE;
+}
+
 static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 {
 	struct kvm_memory_slot *slot = fault->slot;
@@ -4301,6 +4364,14 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 			return RET_PF_EMULATE;
 	}
 
+	if (fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) {
+		kvm_mmu_prepare_memory_fault_exit(vcpu, fault);
+		return -EFAULT;
+	}
+
+	if (fault->is_private)
+		return kvm_faultin_pfn_private(vcpu, fault);
+
 	async = false;
 	fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, false, &async,
 					  fault->write, &fault->map_writable,
@@ -7188,6 +7259,26 @@ void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
 }
 
 #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
+					struct kvm_gfn_range *range)
+{
+	/*
+	 * Zap SPTEs even if the slot can't be mapped PRIVATE.  KVM x86 only
+	 * supports KVM_MEMORY_ATTRIBUTE_PRIVATE, and so it *seems* like KVM
+	 * can simply ignore such slots.  But if userspace is making memory
+	 * PRIVATE, then KVM must prevent the guest from accessing the memory
+	 * as shared.  And if userspace is making memory SHARED and this point
+	 * is reached, then at least one page within the range was previously
+	 * PRIVATE, i.e. the slot's possible hugepage ranges are changing.
+	 * Zapping SPTEs in this case ensures KVM will reassess whether or not
+	 * a hugepage can be used for affected ranges.
+	 */
+	if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm)))
+		return false;
+
+	return kvm_unmap_gfn_range(kvm, range);
+}
+
 static bool hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
 				int level)
 {
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index decc1f153669..86c7cb692786 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -201,6 +201,7 @@ struct kvm_page_fault {
 
 	/* Derived from mmu and global state.  */
 	const bool is_tdp;
+	const bool is_private;
 	const bool nx_huge_page_workaround_enabled;
 
 	/*
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index a6de526c0426..67dfd4d79529 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2357,14 +2357,18 @@ static inline void kvm_account_pgtable_pages(void *virt, int nr)
 #define  KVM_DIRTY_RING_MAX_ENTRIES  65536
 
 static inline void kvm_prepare_memory_fault_exit(struct kvm_vcpu *vcpu,
-						 gpa_t gpa, gpa_t size)
+						 gpa_t gpa, gpa_t size,
+						 bool is_write, bool is_exec,
+						 bool is_private)
 {
 	vcpu->run->exit_reason = KVM_EXIT_MEMORY_FAULT;
 	vcpu->run->memory_fault.gpa = gpa;
 	vcpu->run->memory_fault.size = size;
 
-	/* Flags are not (yet) defined or communicated to userspace. */
+	/* RWX flags are not (yet) defined or communicated to userspace. */
 	vcpu->run->memory_fault.flags = 0;
+	if (is_private)
+		vcpu->run->memory_fault.flags |= KVM_MEMORY_EXIT_FLAG_PRIVATE;
 }
 
 #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 2802d10aa88c..8eb10f560c69 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -535,6 +535,7 @@ struct kvm_run {
 		} notify;
 		/* KVM_EXIT_MEMORY_FAULT */
 		struct {
+#define KVM_MEMORY_EXIT_FLAG_PRIVATE	(1ULL << 3)
 			__u64 flags;
 			__u64 gpa;
 			__u64 size;
-- 
cgit v1.2.3


From 2333afa17af0f4b6651214ee17cfd5ae5f47787a Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 27 Oct 2023 11:22:03 -0700
Subject: KVM: Drop superfluous __KVM_VCPU_MULTIPLE_ADDRESS_SPACE macro

Drop __KVM_VCPU_MULTIPLE_ADDRESS_SPACE and instead check the value of
KVM_ADDRESS_SPACE_NUM.

No functional change intended.

Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Message-Id: <20231027182217.3615211-22-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_host.h | 1 -
 include/linux/kvm_host.h        | 2 +-
 2 files changed, 1 insertion(+), 2 deletions(-)

(limited to 'include')

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index fa0d42202405..061eec231299 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -2136,7 +2136,6 @@ enum {
 #define HF_SMM_MASK		(1 << 1)
 #define HF_SMM_INSIDE_NMI_MASK	(1 << 2)
 
-# define __KVM_VCPU_MULTIPLE_ADDRESS_SPACE
 # define KVM_ADDRESS_SPACE_NUM 2
 # define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0)
 # define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 67dfd4d79529..db423ea9e3a4 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -690,7 +690,7 @@ bool kvm_arch_irqchip_in_kernel(struct kvm *kvm);
 #define KVM_MEM_SLOTS_NUM SHRT_MAX
 #define KVM_USER_MEM_SLOTS (KVM_MEM_SLOTS_NUM - KVM_INTERNAL_MEM_SLOTS)
 
-#ifndef __KVM_VCPU_MULTIPLE_ADDRESS_SPACE
+#if KVM_ADDRESS_SPACE_NUM == 1
 static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu)
 {
 	return 0;
-- 
cgit v1.2.3


From eed52e434bc33603ddb0af62b6c4ef818948489d Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 27 Oct 2023 11:22:04 -0700
Subject: KVM: Allow arch code to track number of memslot address spaces per VM

Let x86 track the number of address spaces on a per-VM basis so that KVM
can disallow SMM memslots for confidential VMs.  Confidentials VMs are
fundamentally incompatible with emulating SMM, which as the name suggests
requires being able to read and write guest memory and register state.

Disallowing SMM will simplify support for guest private memory, as KVM
will not need to worry about tracking memory attributes for multiple
address spaces (SMM is the only "non-default" address space across all
architectures).

Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Message-Id: <20231027182217.3615211-23-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/powerpc/kvm/book3s_hv.c    |  2 +-
 arch/x86/include/asm/kvm_host.h |  8 +++++++-
 arch/x86/kvm/debugfs.c          |  2 +-
 arch/x86/kvm/mmu/mmu.c          |  6 +++---
 arch/x86/kvm/x86.c              |  2 +-
 include/linux/kvm_host.h        | 17 +++++++++++------
 virt/kvm/dirty_ring.c           |  2 +-
 virt/kvm/kvm_main.c             | 26 ++++++++++++++------------
 8 files changed, 39 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 130bafdb1430..9b0eaa17275a 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -6084,7 +6084,7 @@ static int kvmhv_svm_off(struct kvm *kvm)
 	}
 
 	srcu_idx = srcu_read_lock(&kvm->srcu);
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		struct kvm_memory_slot *memslot;
 		struct kvm_memslots *slots = __kvm_memslots(kvm, i);
 		int bkt;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 061eec231299..75ab0da06e64 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -2136,9 +2136,15 @@ enum {
 #define HF_SMM_MASK		(1 << 1)
 #define HF_SMM_INSIDE_NMI_MASK	(1 << 2)
 
-# define KVM_ADDRESS_SPACE_NUM 2
+# define KVM_MAX_NR_ADDRESS_SPACES	2
 # define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0)
 # define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm)
+
+static inline int kvm_arch_nr_memslot_as_ids(struct kvm *kvm)
+{
+	return KVM_MAX_NR_ADDRESS_SPACES;
+}
+
 #else
 # define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, 0)
 #endif
diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c
index ee8c4c3496ed..42026b3f3ff3 100644
--- a/arch/x86/kvm/debugfs.c
+++ b/arch/x86/kvm/debugfs.c
@@ -111,7 +111,7 @@ static int kvm_mmu_rmaps_stat_show(struct seq_file *m, void *v)
 	mutex_lock(&kvm->slots_lock);
 	write_lock(&kvm->mmu_lock);
 
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		int bkt;
 
 		slots = __kvm_memslots(kvm, i);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 754a5aaebee5..4de7670d5976 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3763,7 +3763,7 @@ static int mmu_first_shadow_root_alloc(struct kvm *kvm)
 	    kvm_page_track_write_tracking_enabled(kvm))
 		goto out_success;
 
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		slots = __kvm_memslots(kvm, i);
 		kvm_for_each_memslot(slot, bkt, slots) {
 			/*
@@ -6309,7 +6309,7 @@ static bool kvm_rmap_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_e
 	if (!kvm_memslots_have_rmaps(kvm))
 		return flush;
 
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		slots = __kvm_memslots(kvm, i);
 
 		kvm_for_each_memslot_in_gfn_range(&iter, slots, gfn_start, gfn_end) {
@@ -6806,7 +6806,7 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen)
 	 * modifier prior to checking for a wrap of the MMIO generation so
 	 * that a wrap in any address space is detected.
 	 */
-	gen &= ~((u64)KVM_ADDRESS_SPACE_NUM - 1);
+	gen &= ~((u64)kvm_arch_nr_memslot_as_ids(kvm) - 1);
 
 	/*
 	 * The very rare case: if the MMIO generation number has wrapped,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e1aad0c81f6f..f521c97f5c64 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -12577,7 +12577,7 @@ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa,
 		hva = slot->userspace_addr;
 	}
 
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		struct kvm_userspace_memory_region2 m;
 
 		m.slot = id | (i << 16);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index db423ea9e3a4..3ebc6912c54a 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -80,8 +80,8 @@
 /* Two fragments for cross MMIO pages. */
 #define KVM_MAX_MMIO_FRAGMENTS	2
 
-#ifndef KVM_ADDRESS_SPACE_NUM
-#define KVM_ADDRESS_SPACE_NUM	1
+#ifndef KVM_MAX_NR_ADDRESS_SPACES
+#define KVM_MAX_NR_ADDRESS_SPACES	1
 #endif
 
 /*
@@ -690,7 +690,12 @@ bool kvm_arch_irqchip_in_kernel(struct kvm *kvm);
 #define KVM_MEM_SLOTS_NUM SHRT_MAX
 #define KVM_USER_MEM_SLOTS (KVM_MEM_SLOTS_NUM - KVM_INTERNAL_MEM_SLOTS)
 
-#if KVM_ADDRESS_SPACE_NUM == 1
+#if KVM_MAX_NR_ADDRESS_SPACES == 1
+static inline int kvm_arch_nr_memslot_as_ids(struct kvm *kvm)
+{
+	return KVM_MAX_NR_ADDRESS_SPACES;
+}
+
 static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu)
 {
 	return 0;
@@ -745,9 +750,9 @@ struct kvm {
 	struct mm_struct *mm; /* userspace tied to this vm */
 	unsigned long nr_memslot_pages;
 	/* The two memslot sets - active and inactive (per address space) */
-	struct kvm_memslots __memslots[KVM_ADDRESS_SPACE_NUM][2];
+	struct kvm_memslots __memslots[KVM_MAX_NR_ADDRESS_SPACES][2];
 	/* The current active memslot set for each address space */
-	struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM];
+	struct kvm_memslots __rcu *memslots[KVM_MAX_NR_ADDRESS_SPACES];
 	struct xarray vcpu_array;
 	/*
 	 * Protected by slots_lock, but can be read outside if an
@@ -1017,7 +1022,7 @@ void kvm_put_kvm_no_destroy(struct kvm *kvm);
 
 static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id)
 {
-	as_id = array_index_nospec(as_id, KVM_ADDRESS_SPACE_NUM);
+	as_id = array_index_nospec(as_id, KVM_MAX_NR_ADDRESS_SPACES);
 	return srcu_dereference_check(kvm->memslots[as_id], &kvm->srcu,
 			lockdep_is_held(&kvm->slots_lock) ||
 			!refcount_read(&kvm->users_count));
diff --git a/virt/kvm/dirty_ring.c b/virt/kvm/dirty_ring.c
index c1cd7dfe4a90..86d267db87bb 100644
--- a/virt/kvm/dirty_ring.c
+++ b/virt/kvm/dirty_ring.c
@@ -58,7 +58,7 @@ static void kvm_reset_dirty_gfn(struct kvm *kvm, u32 slot, u64 offset, u64 mask)
 	as_id = slot >> 16;
 	id = (u16)slot;
 
-	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
+	if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS)
 		return;
 
 	memslot = id_to_memslot(__kvm_memslots(kvm, as_id), id);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 8f46d757a2c5..8758cb799e18 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -615,7 +615,7 @@ static __always_inline kvm_mn_ret_t __kvm_handle_hva_range(struct kvm *kvm,
 
 	idx = srcu_read_lock(&kvm->srcu);
 
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		struct interval_tree_node *node;
 
 		slots = __kvm_memslots(kvm, i);
@@ -1241,7 +1241,7 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 		goto out_err_no_irq_srcu;
 
 	refcount_set(&kvm->users_count, 1);
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		for (j = 0; j < 2; j++) {
 			slots = &kvm->__memslots[i][j];
 
@@ -1391,7 +1391,7 @@ static void kvm_destroy_vm(struct kvm *kvm)
 #endif
 	kvm_arch_destroy_vm(kvm);
 	kvm_destroy_devices(kvm);
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		kvm_free_memslots(kvm, &kvm->__memslots[i][0]);
 		kvm_free_memslots(kvm, &kvm->__memslots[i][1]);
 	}
@@ -1682,7 +1682,7 @@ static void kvm_swap_active_memslots(struct kvm *kvm, int as_id)
 	 * space 0 will use generations 0, 2, 4, ... while address space 1 will
 	 * use generations 1, 3, 5, ...
 	 */
-	gen += KVM_ADDRESS_SPACE_NUM;
+	gen += kvm_arch_nr_memslot_as_ids(kvm);
 
 	kvm_arch_memslots_updated(kvm, gen);
 
@@ -2052,7 +2052,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	    (mem->guest_memfd_offset & (PAGE_SIZE - 1) ||
 	     mem->guest_memfd_offset + mem->memory_size < mem->guest_memfd_offset))
 		return -EINVAL;
-	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_MEM_SLOTS_NUM)
+	if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_MEM_SLOTS_NUM)
 		return -EINVAL;
 	if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr)
 		return -EINVAL;
@@ -2188,7 +2188,7 @@ int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log,
 
 	as_id = log->slot >> 16;
 	id = (u16)log->slot;
-	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
+	if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS)
 		return -EINVAL;
 
 	slots = __kvm_memslots(kvm, as_id);
@@ -2250,7 +2250,7 @@ static int kvm_get_dirty_log_protect(struct kvm *kvm, struct kvm_dirty_log *log)
 
 	as_id = log->slot >> 16;
 	id = (u16)log->slot;
-	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
+	if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS)
 		return -EINVAL;
 
 	slots = __kvm_memslots(kvm, as_id);
@@ -2362,7 +2362,7 @@ static int kvm_clear_dirty_log_protect(struct kvm *kvm,
 
 	as_id = log->slot >> 16;
 	id = (u16)log->slot;
-	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
+	if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS)
 		return -EINVAL;
 
 	if (log->first_page & 63)
@@ -2493,7 +2493,7 @@ static __always_inline void kvm_handle_gfn_range(struct kvm *kvm,
 	gfn_range.arg = range->arg;
 	gfn_range.may_block = range->may_block;
 
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		slots = __kvm_memslots(kvm, i);
 
 		kvm_for_each_memslot_in_gfn_range(&iter, slots, range->start, range->end) {
@@ -4848,9 +4848,11 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 	case KVM_CAP_IRQ_ROUTING:
 		return KVM_MAX_IRQ_ROUTES;
 #endif
-#if KVM_ADDRESS_SPACE_NUM > 1
+#if KVM_MAX_NR_ADDRESS_SPACES > 1
 	case KVM_CAP_MULTI_ADDRESS_SPACE:
-		return KVM_ADDRESS_SPACE_NUM;
+		if (kvm)
+			return kvm_arch_nr_memslot_as_ids(kvm);
+		return KVM_MAX_NR_ADDRESS_SPACES;
 #endif
 	case KVM_CAP_NR_MEMSLOTS:
 		return KVM_USER_MEM_SLOTS;
@@ -4958,7 +4960,7 @@ bool kvm_are_all_memslots_empty(struct kvm *kvm)
 
 	lockdep_assert_held(&kvm->slots_lock);
 
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		if (!kvm_memslots_empty(__kvm_memslots(kvm, i)))
 			return false;
 	}
-- 
cgit v1.2.3


From 89ea60c2c7b5838bf192c50062d5720cd6ab8662 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 27 Oct 2023 11:22:05 -0700
Subject: KVM: x86: Add support for "protected VMs" that can utilize private
 memory

Add a new x86 VM type, KVM_X86_SW_PROTECTED_VM, to serve as a development
and testing vehicle for Confidential (CoCo) VMs, and potentially to even
become a "real" product in the distant future, e.g. a la pKVM.

The private memory support in KVM x86 is aimed at AMD's SEV-SNP and
Intel's TDX, but those technologies are extremely complex (understatement),
difficult to debug, don't support running as nested guests, and require
hardware that's isn't universally accessible.  I.e. relying SEV-SNP or TDX
for maintaining guest private memory isn't a realistic option.

At the very least, KVM_X86_SW_PROTECTED_VM will enable a variety of
selftests for guest_memfd and private memory support without requiring
unique hardware.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20231027182217.3615211-24-seanjc@google.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virt/kvm/api.rst  | 32 ++++++++++++++++++++++++++++++++
 arch/x86/include/asm/kvm_host.h | 15 +++++++++------
 arch/x86/include/uapi/asm/kvm.h |  3 +++
 arch/x86/kvm/Kconfig            | 12 ++++++++++++
 arch/x86/kvm/mmu/mmu_internal.h |  1 +
 arch/x86/kvm/x86.c              | 16 +++++++++++++++-
 include/uapi/linux/kvm.h        |  1 +
 virt/kvm/Kconfig                |  5 +++++
 8 files changed, 78 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 726c87c35d57..926241e23aeb 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -147,10 +147,29 @@ described as 'basic' will be available.
 The new VM has no virtual cpus and no memory.
 You probably want to use 0 as machine type.
 
+X86:
+^^^^
+
+Supported X86 VM types can be queried via KVM_CAP_VM_TYPES.
+
+S390:
+^^^^^
+
 In order to create user controlled virtual machines on S390, check
 KVM_CAP_S390_UCONTROL and use the flag KVM_VM_S390_UCONTROL as
 privileged user (CAP_SYS_ADMIN).
 
+MIPS:
+^^^^^
+
+To use hardware assisted virtualization on MIPS (VZ ASE) rather than
+the default trap & emulate implementation (which changes the virtual
+memory layout to fit in user mode), check KVM_CAP_MIPS_VZ and use the
+flag KVM_VM_MIPS_VZ.
+
+ARM64:
+^^^^^^
+
 On arm64, the physical address size for a VM (IPA Size limit) is limited
 to 40bits by default. The limit can be configured if the host supports the
 extension KVM_CAP_ARM_VM_IPA_SIZE. When supported, use
@@ -8765,6 +8784,19 @@ block sizes is exposed in KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES as a
 64-bit bitmap (each bit describing a block size). The default value is
 0, to disable the eager page splitting.
 
+8.41 KVM_CAP_VM_TYPES
+---------------------
+
+:Capability: KVM_CAP_MEMORY_ATTRIBUTES
+:Architectures: x86
+:Type: system ioctl
+
+This capability returns a bitmap of support VM types.  The 1-setting of bit @n
+means the VM type with value @n is supported.  Possible values of @n are::
+
+  #define KVM_X86_DEFAULT_VM	0
+  #define KVM_X86_SW_PROTECTED_VM	1
+
 9. Known KVM API problems
 =========================
 
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 75ab0da06e64..a565a2e70f30 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1255,6 +1255,7 @@ enum kvm_apicv_inhibit {
 };
 
 struct kvm_arch {
+	unsigned long vm_type;
 	unsigned long n_used_mmu_pages;
 	unsigned long n_requested_mmu_pages;
 	unsigned long n_max_mmu_pages;
@@ -2089,6 +2090,12 @@ void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd);
 void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level,
 		       int tdp_max_root_level, int tdp_huge_page_level);
 
+#ifdef CONFIG_KVM_PRIVATE_MEM
+#define kvm_arch_has_private_mem(kvm) ((kvm)->arch.vm_type != KVM_X86_DEFAULT_VM)
+#else
+#define kvm_arch_has_private_mem(kvm) false
+#endif
+
 static inline u16 kvm_read_ldt(void)
 {
 	u16 ldt;
@@ -2137,14 +2144,10 @@ enum {
 #define HF_SMM_INSIDE_NMI_MASK	(1 << 2)
 
 # define KVM_MAX_NR_ADDRESS_SPACES	2
+/* SMM is currently unsupported for guests with private memory. */
+# define kvm_arch_nr_memslot_as_ids(kvm) (kvm_arch_has_private_mem(kvm) ? 1 : 2)
 # define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0)
 # define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm)
-
-static inline int kvm_arch_nr_memslot_as_ids(struct kvm *kvm)
-{
-	return KVM_MAX_NR_ADDRESS_SPACES;
-}
-
 #else
 # define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, 0)
 #endif
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 1a6a1f987949..a448d0964fc0 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -562,4 +562,7 @@ struct kvm_pmu_event_filter {
 /* x86-specific KVM_EXIT_HYPERCALL flags. */
 #define KVM_EXIT_HYPERCALL_LONG_MODE	BIT(0)
 
+#define KVM_X86_DEFAULT_VM	0
+#define KVM_X86_SW_PROTECTED_VM	1
+
 #endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index e61383674c75..c1716e83d176 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -77,6 +77,18 @@ config KVM_WERROR
 
 	  If in doubt, say "N".
 
+config KVM_SW_PROTECTED_VM
+	bool "Enable support for KVM software-protected VMs"
+	depends on EXPERT
+	depends on X86_64
+	select KVM_GENERIC_PRIVATE_MEM
+	help
+	  Enable support for KVM software-protected VMs.  Currently "protected"
+	  means the VM can be backed with memory provided by
+	  KVM_CREATE_GUEST_MEMFD.
+
+	  If unsure, say "N".
+
 config KVM_INTEL
 	tristate "KVM for Intel (and compatible) processors support"
 	depends on KVM && IA32_FEAT_CTL
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 86c7cb692786..b66a7d47e0e4 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -297,6 +297,7 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 		.max_level = KVM_MAX_HUGEPAGE_LEVEL,
 		.req_level = PG_LEVEL_4K,
 		.goal_level = PG_LEVEL_4K,
+		.is_private = kvm_mem_is_private(vcpu->kvm, cr2_or_gpa >> PAGE_SHIFT),
 	};
 	int r;
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f521c97f5c64..6d0772b47041 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4548,6 +4548,13 @@ static int kvm_ioctl_get_supported_hv_cpuid(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+static bool kvm_is_vm_type_supported(unsigned long type)
+{
+	return type == KVM_X86_DEFAULT_VM ||
+	       (type == KVM_X86_SW_PROTECTED_VM &&
+		IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) && tdp_enabled);
+}
+
 int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 {
 	int r = 0;
@@ -4739,6 +4746,11 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_X86_NOTIFY_VMEXIT:
 		r = kvm_caps.has_notify_vmexit;
 		break;
+	case KVM_CAP_VM_TYPES:
+		r = BIT(KVM_X86_DEFAULT_VM);
+		if (kvm_is_vm_type_supported(KVM_X86_SW_PROTECTED_VM))
+			r |= BIT(KVM_X86_SW_PROTECTED_VM);
+		break;
 	default:
 		break;
 	}
@@ -12436,9 +12448,11 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	int ret;
 	unsigned long flags;
 
-	if (type)
+	if (!kvm_is_vm_type_supported(type))
 		return -EINVAL;
 
+	kvm->arch.vm_type = type;
+
 	ret = kvm_page_track_init(kvm);
 	if (ret)
 		goto out;
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 8eb10f560c69..e9cb2df67a1d 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1227,6 +1227,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_MEMORY_FAULT_INFO 232
 #define KVM_CAP_MEMORY_ATTRIBUTES 233
 #define KVM_CAP_GUEST_MEMFD 234
+#define KVM_CAP_VM_TYPES 235
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 08afef022db9..2c964586aa14 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -104,3 +104,8 @@ config KVM_GENERIC_MEMORY_ATTRIBUTES
 config KVM_PRIVATE_MEM
        select XARRAY_MULTI
        bool
+
+config KVM_GENERIC_PRIVATE_MEM
+       select KVM_GENERIC_MEMORY_ATTRIBUTES
+       select KVM_PRIVATE_MEM
+       bool
-- 
cgit v1.2.3


From 577d71544871b075a25a09e4c5aa31008850c0a8 Mon Sep 17 00:00:00 2001
From: Jack Yu <jack.yu@realtek.com>
Date: Mon, 13 Nov 2023 10:37:15 +0000
Subject: ASoC: rt5682s: Add LDO output selection for dacref

Add LDO output selection for dacref.

Signed-off-by: Jack Yu <jack.yu@realtek.com>
Link: https://lore.kernel.org/r/62cad4e51c044108bad872ab349e36f8@realtek.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/rt5682s.h    |  8 ++++++++
 sound/soc/codecs/rt5682s.c | 23 +++++++++++++++++++++++
 sound/soc/codecs/rt5682s.h |  7 +++++++
 3 files changed, 38 insertions(+)

(limited to 'include')

diff --git a/include/sound/rt5682s.h b/include/sound/rt5682s.h
index 66ca0c75b914..006e6003d11c 100644
--- a/include/sound/rt5682s.h
+++ b/include/sound/rt5682s.h
@@ -31,6 +31,13 @@ enum rt5682s_dai_clks {
 	RT5682S_DAI_NUM_CLKS,
 };
 
+enum {
+	RT5682S_LDO_1_607V,
+	RT5682S_LDO_1_5V,
+	RT5682S_LDO_1_406V,
+	RT5682S_LDO_1_731V,
+};
+
 struct rt5682s_platform_data {
 	enum rt5682s_dmic1_data_pin dmic1_data_pin;
 	enum rt5682s_dmic1_clk_pin dmic1_clk_pin;
@@ -38,6 +45,7 @@ struct rt5682s_platform_data {
 	unsigned int dmic_clk_rate;
 	unsigned int dmic_delay;
 	unsigned int amic_delay;
+	unsigned int ldo_dacref;
 	bool dmic_clk_driving_high;
 
 	const char *dai_clk_names[RT5682S_DAI_NUM_CLKS];
diff --git a/sound/soc/codecs/rt5682s.c b/sound/soc/codecs/rt5682s.c
index c261c33c4be7..3322056bbb3b 100644
--- a/sound/soc/codecs/rt5682s.c
+++ b/sound/soc/codecs/rt5682s.c
@@ -2971,6 +2971,8 @@ static int rt5682s_parse_dt(struct rt5682s_priv *rt5682s, struct device *dev)
 		&rt5682s->pdata.dmic_delay);
 	device_property_read_u32(dev, "realtek,amic-delay-ms",
 		&rt5682s->pdata.amic_delay);
+	device_property_read_u32(dev, "realtek,ldo-sel",
+		&rt5682s->pdata.ldo_dacref);
 
 	if (device_property_read_string_array(dev, "clock-output-names",
 					      rt5682s->pdata.dai_clk_names,
@@ -3250,6 +3252,27 @@ static int rt5682s_i2c_probe(struct i2c_client *i2c)
 		break;
 	}
 
+	/* LDO output voltage control */
+	switch (rt5682s->pdata.ldo_dacref) {
+	case RT5682S_LDO_1_607V:
+		break;
+	case RT5682S_LDO_1_5V:
+		regmap_update_bits(rt5682s->regmap, RT5682S_BIAS_CUR_CTRL_7,
+			RT5682S_LDO_DACREF_MASK, RT5682S_LDO_DACREF_1_5V);
+		break;
+	case RT5682S_LDO_1_406V:
+		regmap_update_bits(rt5682s->regmap, RT5682S_BIAS_CUR_CTRL_7,
+			RT5682S_LDO_DACREF_MASK, RT5682S_LDO_DACREF_1_406V);
+		break;
+	case RT5682S_LDO_1_731V:
+		regmap_update_bits(rt5682s->regmap, RT5682S_BIAS_CUR_CTRL_7,
+			RT5682S_LDO_DACREF_MASK, RT5682S_LDO_DACREF_1_731V);
+		break;
+	default:
+		dev_warn(&i2c->dev, "invalid LDO output setting.\n");
+		break;
+	}
+
 	INIT_DELAYED_WORK(&rt5682s->jack_detect_work, rt5682s_jack_detect_handler);
 	INIT_DELAYED_WORK(&rt5682s->jd_check_work, rt5682s_jd_check_handler);
 
diff --git a/sound/soc/codecs/rt5682s.h b/sound/soc/codecs/rt5682s.h
index 1d79d432d0d8..67f42898de96 100644
--- a/sound/soc/codecs/rt5682s.h
+++ b/sound/soc/codecs/rt5682s.h
@@ -1263,6 +1263,13 @@
 #define RT5682S_JDH_NO_PLUG			(0x1 << 4)
 #define RT5682S_JDH_PLUG			(0x0 << 4)
 
+/* Bias current control 7  (0x0110) */
+#define RT5682S_LDO_DACREF_MASK			(0x3 << 4)
+#define RT5682S_LDO_DACREF_1_607V		(0x0 << 4)
+#define RT5682S_LDO_DACREF_1_5V			(0x1 << 4)
+#define RT5682S_LDO_DACREF_1_406V		(0x2 << 4)
+#define RT5682S_LDO_DACREF_1_731V		(0x3 << 4)
+
 /* Charge Pump Internal Register1 (0x0125) */
 #define RT5682S_CP_CLK_HP_MASK			(0x3 << 4)
 #define RT5682S_CP_CLK_HP_100KHZ		(0x0 << 4)
-- 
cgit v1.2.3


From 84db47ca7146d7bd00eb5cf2b93989a971c84650 Mon Sep 17 00:00:00 2001
From: Raghavendra K T <raghavendra.kt@amd.com>
Date: Fri, 20 Oct 2023 21:27:46 +0530
Subject: sched/numa: Fix mm numa_scan_seq based unconditional scan

Since commit fc137c0ddab2 ("sched/numa: enhance vma scanning logic")

NUMA Balancing allows updating PTEs to trap NUMA hinting faults if the
task had previously accessed VMA. However unconditional scan of VMAs are
allowed during initial phase of VMA creation until process's
mm numa_scan_seq reaches 2 even though current task had not accessed VMA.

Rationale:
 - Without initial scan subsequent PTE update may never happen.
 - Give fair opportunity to all the VMAs to be scanned and subsequently
understand the access pattern of all the VMAs.

But it has a corner case where, if a VMA is created after some time,
process's mm numa_scan_seq could be already greater than 2.

For e.g., values of mm numa_scan_seq when VMAs are created by running
mmtest autonuma benchmark briefly looks like:
start_seq=0 : 459
start_seq=2 : 138
start_seq=3 : 144
start_seq=4 : 8
start_seq=8 : 1
start_seq=9 : 1
This results in no unconditional PTE updates for those VMAs created after
some time.

Fix:
 - Note down the initial value of mm numa_scan_seq in per VMA start_seq.
 - Allow unconditional scan till start_seq + 2.

Result:
SUT: AMD EPYC Milan with 2 NUMA nodes 256 cpus.
base kernel: upstream 6.6-rc6 with Mels patches [1] applied.

kernbench
==========		base                  patched %gain
Amean    elsp-128      165.09 ( 0.00%)      164.78 *   0.19%*

Duration User       41404.28    41375.08
Duration System      9862.22     9768.48
Duration Elapsed      519.87      518.72

Ops NUMA PTE updates           1041416.00      831536.00
Ops NUMA hint faults            263296.00      220966.00
Ops NUMA pages migrated         258021.00      212769.00
Ops AutoNUMA cost                 1328.67        1114.69

autonumabench

NUMA01_THREADLOCAL
==================
Amean  elsp-NUMA01_THREADLOCAL   81.79 (0.00%)  67.74 *  17.18%*

Duration User       54832.73    47379.67
Duration System        75.00      185.75
Duration Elapsed      576.72      476.09

Ops NUMA PTE updates                  394429.00    11121044.00
Ops NUMA hint faults                    1001.00     8906404.00
Ops NUMA pages migrated                  288.00     2998694.00
Ops AutoNUMA cost                          7.77       44666.84

Signed-off-by: Raghavendra K T <raghavendra.kt@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Link: https://lore.kernel.org/r/2ea7cbce80ac7c62e90cbfb9653a7972f902439f.1697816692.git.raghavendra.kt@amd.com
---
 include/linux/mm_types.h | 3 +++
 kernel/sched/fair.c      | 4 +++-
 2 files changed, 6 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 957ce38768b2..950df415d7de 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -600,6 +600,9 @@ struct vma_numab_state {
 	 */
 	unsigned long pids_active[2];
 
+	/* MM scan sequence ID when scan first started after VMA creation */
+	int start_scan_seq;
+
 	/*
 	 * MM scan sequence ID when the VMA was last completely scanned.
 	 * A VMA is not eligible for scanning if prev_scan_seq == numa_scan_seq
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d7a3c63a2171..44b5262b6657 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3164,7 +3164,7 @@ static bool vma_is_accessed(struct mm_struct *mm, struct vm_area_struct *vma)
 	 * This is also done to avoid any side effect of task scanning
 	 * amplifying the unfairness of disjoint set of VMAs' access.
 	 */
-	if (READ_ONCE(current->mm->numa_scan_seq) < 2)
+	if ((READ_ONCE(current->mm->numa_scan_seq) - vma->numab_state->start_scan_seq) < 2)
 		return true;
 
 	pids = vma->numab_state->pids_active[0] | vma->numab_state->pids_active[1];
@@ -3307,6 +3307,8 @@ retry_pids:
 			if (!vma->numab_state)
 				continue;
 
+			vma->numab_state->start_scan_seq = mm->numa_scan_seq;
+
 			vma->numab_state->next_scan = now +
 				msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
 
-- 
cgit v1.2.3


From 2227a957e1d5b1941be4e4207879ec74f4bb37f8 Mon Sep 17 00:00:00 2001
From: Abel Wu <wuyun.abel@bytedance.com>
Date: Wed, 15 Nov 2023 11:36:45 +0800
Subject: sched/eevdf: Sort the rbtree by virtual deadline

Sort the task timeline by virtual deadline and keep the min_vruntime
in the augmented tree, so we can avoid doubling the worst case cost
and make full use of the cached leftmost node to enable O(1) fastpath
picking in next patch.

Signed-off-by: Abel Wu <wuyun.abel@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20231115033647.80785-3-wuyun.abel@bytedance.com
---
 include/linux/sched.h |   2 +-
 kernel/sched/debug.c  |  11 +++-
 kernel/sched/fair.c   | 168 ++++++++++++++++++++------------------------------
 kernel/sched/sched.h  |   1 +
 4 files changed, 77 insertions(+), 105 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 292c31697248..cd56d4018527 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -553,7 +553,7 @@ struct sched_entity {
 	struct load_weight		load;
 	struct rb_node			run_node;
 	u64				deadline;
-	u64				min_deadline;
+	u64				min_vruntime;
 
 	struct list_head		group_node;
 	unsigned int			on_rq;
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 4580a450700e..168eecc209b4 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -628,8 +628,8 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu)
 
 void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 {
-	s64 left_vruntime = -1, min_vruntime, right_vruntime = -1, spread;
-	struct sched_entity *last, *first;
+	s64 left_vruntime = -1, min_vruntime, right_vruntime = -1, left_deadline = -1, spread;
+	struct sched_entity *last, *first, *root;
 	struct rq *rq = cpu_rq(cpu);
 	unsigned long flags;
 
@@ -644,15 +644,20 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 			SPLIT_NS(cfs_rq->exec_clock));
 
 	raw_spin_rq_lock_irqsave(rq, flags);
+	root = __pick_root_entity(cfs_rq);
+	if (root)
+		left_vruntime = root->min_vruntime;
 	first = __pick_first_entity(cfs_rq);
 	if (first)
-		left_vruntime = first->vruntime;
+		left_deadline = first->deadline;
 	last = __pick_last_entity(cfs_rq);
 	if (last)
 		right_vruntime = last->vruntime;
 	min_vruntime = cfs_rq->min_vruntime;
 	raw_spin_rq_unlock_irqrestore(rq, flags);
 
+	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "left_deadline",
+			SPLIT_NS(left_deadline));
 	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "left_vruntime",
 			SPLIT_NS(left_vruntime));
 	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "min_vruntime",
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 44b5262b6657..31bca05c3612 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -551,7 +551,11 @@ static inline u64 min_vruntime(u64 min_vruntime, u64 vruntime)
 static inline bool entity_before(const struct sched_entity *a,
 				 const struct sched_entity *b)
 {
-	return (s64)(a->vruntime - b->vruntime) < 0;
+	/*
+	 * Tiebreak on vruntime seems unnecessary since it can
+	 * hardly happen.
+	 */
+	return (s64)(a->deadline - b->deadline) < 0;
 }
 
 static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se)
@@ -720,7 +724,7 @@ static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se)
  * Note: using 'avg_vruntime() > se->vruntime' is inacurate due
  *       to the loss in precision caused by the division.
  */
-int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static int vruntime_eligible(struct cfs_rq *cfs_rq, u64 vruntime)
 {
 	struct sched_entity *curr = cfs_rq->curr;
 	s64 avg = cfs_rq->avg_vruntime;
@@ -733,7 +737,12 @@ int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		load += weight;
 	}
 
-	return avg >= entity_key(cfs_rq, se) * load;
+	return avg >= (s64)(vruntime - cfs_rq->min_vruntime) * load;
+}
+
+int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	return vruntime_eligible(cfs_rq, se->vruntime);
 }
 
 static u64 __update_min_vruntime(struct cfs_rq *cfs_rq, u64 vruntime)
@@ -752,9 +761,8 @@ static u64 __update_min_vruntime(struct cfs_rq *cfs_rq, u64 vruntime)
 
 static void update_min_vruntime(struct cfs_rq *cfs_rq)
 {
-	struct sched_entity *se = __pick_first_entity(cfs_rq);
+	struct sched_entity *se = __pick_root_entity(cfs_rq);
 	struct sched_entity *curr = cfs_rq->curr;
-
 	u64 vruntime = cfs_rq->min_vruntime;
 
 	if (curr) {
@@ -766,9 +774,9 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq)
 
 	if (se) {
 		if (!curr)
-			vruntime = se->vruntime;
+			vruntime = se->min_vruntime;
 		else
-			vruntime = min_vruntime(vruntime, se->vruntime);
+			vruntime = min_vruntime(vruntime, se->min_vruntime);
 	}
 
 	/* ensure we never gain time by being placed backwards. */
@@ -781,34 +789,34 @@ static inline bool __entity_less(struct rb_node *a, const struct rb_node *b)
 	return entity_before(__node_2_se(a), __node_2_se(b));
 }
 
-#define deadline_gt(field, lse, rse) ({ (s64)((lse)->field - (rse)->field) > 0; })
+#define vruntime_gt(field, lse, rse) ({ (s64)((lse)->field - (rse)->field) > 0; })
 
-static inline void __update_min_deadline(struct sched_entity *se, struct rb_node *node)
+static inline void __min_vruntime_update(struct sched_entity *se, struct rb_node *node)
 {
 	if (node) {
 		struct sched_entity *rse = __node_2_se(node);
-		if (deadline_gt(min_deadline, se, rse))
-			se->min_deadline = rse->min_deadline;
+		if (vruntime_gt(min_vruntime, se, rse))
+			se->min_vruntime = rse->min_vruntime;
 	}
 }
 
 /*
- * se->min_deadline = min(se->deadline, left->min_deadline, right->min_deadline)
+ * se->min_vruntime = min(se->vruntime, {left,right}->min_vruntime)
  */
-static inline bool min_deadline_update(struct sched_entity *se, bool exit)
+static inline bool min_vruntime_update(struct sched_entity *se, bool exit)
 {
-	u64 old_min_deadline = se->min_deadline;
+	u64 old_min_vruntime = se->min_vruntime;
 	struct rb_node *node = &se->run_node;
 
-	se->min_deadline = se->deadline;
-	__update_min_deadline(se, node->rb_right);
-	__update_min_deadline(se, node->rb_left);
+	se->min_vruntime = se->vruntime;
+	__min_vruntime_update(se, node->rb_right);
+	__min_vruntime_update(se, node->rb_left);
 
-	return se->min_deadline == old_min_deadline;
+	return se->min_vruntime == old_min_vruntime;
 }
 
-RB_DECLARE_CALLBACKS(static, min_deadline_cb, struct sched_entity,
-		     run_node, min_deadline, min_deadline_update);
+RB_DECLARE_CALLBACKS(static, min_vruntime_cb, struct sched_entity,
+		     run_node, min_vruntime, min_vruntime_update);
 
 /*
  * Enqueue an entity into the rb-tree:
@@ -816,18 +824,28 @@ RB_DECLARE_CALLBACKS(static, min_deadline_cb, struct sched_entity,
 static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	avg_vruntime_add(cfs_rq, se);
-	se->min_deadline = se->deadline;
+	se->min_vruntime = se->vruntime;
 	rb_add_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline,
-				__entity_less, &min_deadline_cb);
+				__entity_less, &min_vruntime_cb);
 }
 
 static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	rb_erase_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline,
-				  &min_deadline_cb);
+				  &min_vruntime_cb);
 	avg_vruntime_sub(cfs_rq, se);
 }
 
+struct sched_entity *__pick_root_entity(struct cfs_rq *cfs_rq)
+{
+	struct rb_node *root = cfs_rq->tasks_timeline.rb_root.rb_node;
+
+	if (!root)
+		return NULL;
+
+	return __node_2_se(root);
+}
+
 struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
 {
 	struct rb_node *left = rb_first_cached(&cfs_rq->tasks_timeline);
@@ -850,23 +868,28 @@ struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
  *     with the earliest virtual deadline.
  *
  * We can do this in O(log n) time due to an augmented RB-tree. The
- * tree keeps the entries sorted on service, but also functions as a
- * heap based on the deadline by keeping:
+ * tree keeps the entries sorted on deadline, but also functions as a
+ * heap based on the vruntime by keeping:
  *
- *  se->min_deadline = min(se->deadline, se->{left,right}->min_deadline)
+ *  se->min_vruntime = min(se->vruntime, se->{left,right}->min_vruntime)
  *
- * Which allows an EDF like search on (sub)trees.
+ * Which allows tree pruning through eligibility.
  */
-static struct sched_entity *__pick_eevdf(struct cfs_rq *cfs_rq)
+static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
 {
 	struct rb_node *node = cfs_rq->tasks_timeline.rb_root.rb_node;
 	struct sched_entity *curr = cfs_rq->curr;
 	struct sched_entity *best = NULL;
-	struct sched_entity *best_left = NULL;
+
+	/*
+	 * We can safely skip eligibility check if there is only one entity
+	 * in this cfs_rq, saving some cycles.
+	 */
+	if (cfs_rq->nr_running == 1)
+		return curr && curr->on_rq ? curr : __node_2_se(node);
 
 	if (curr && (!curr->on_rq || !entity_eligible(cfs_rq, curr)))
 		curr = NULL;
-	best = curr;
 
 	/*
 	 * Once selected, run a task until it either becomes non-eligible or
@@ -875,95 +898,38 @@ static struct sched_entity *__pick_eevdf(struct cfs_rq *cfs_rq)
 	if (sched_feat(RUN_TO_PARITY) && curr && curr->vlag == curr->deadline)
 		return curr;
 
+	/* Heap search for the EEVD entity */
 	while (node) {
 		struct sched_entity *se = __node_2_se(node);
+		struct rb_node *left = node->rb_left;
 
 		/*
-		 * If this entity is not eligible, try the left subtree.
+		 * Eligible entities in left subtree are always better
+		 * choices, since they have earlier deadlines.
 		 */
-		if (!entity_eligible(cfs_rq, se)) {
-			node = node->rb_left;
+		if (left && vruntime_eligible(cfs_rq,
+					__node_2_se(left)->min_vruntime)) {
+			node = left;
 			continue;
 		}
 
 		/*
-		 * Now we heap search eligible trees for the best (min_)deadline
+		 * The left subtree either is empty or has no eligible
+		 * entity, so check the current node since it is the one
+		 * with earliest deadline that might be eligible.
 		 */
-		if (!best || deadline_gt(deadline, best, se))
+		if (entity_eligible(cfs_rq, se)) {
 			best = se;
-
-		/*
-		 * Every se in a left branch is eligible, keep track of the
-		 * branch with the best min_deadline
-		 */
-		if (node->rb_left) {
-			struct sched_entity *left = __node_2_se(node->rb_left);
-
-			if (!best_left || deadline_gt(min_deadline, best_left, left))
-				best_left = left;
-
-			/*
-			 * min_deadline is in the left branch. rb_left and all
-			 * descendants are eligible, so immediately switch to the second
-			 * loop.
-			 */
-			if (left->min_deadline == se->min_deadline)
-				break;
-		}
-
-		/* min_deadline is at this node, no need to look right */
-		if (se->deadline == se->min_deadline)
 			break;
-
-		/* else min_deadline is in the right branch. */
-		node = node->rb_right;
-	}
-
-	/*
-	 * We ran into an eligible node which is itself the best.
-	 * (Or nr_running == 0 and both are NULL)
-	 */
-	if (!best_left || (s64)(best_left->min_deadline - best->deadline) > 0)
-		return best;
-
-	/*
-	 * Now best_left and all of its children are eligible, and we are just
-	 * looking for deadline == min_deadline
-	 */
-	node = &best_left->run_node;
-	while (node) {
-		struct sched_entity *se = __node_2_se(node);
-
-		/* min_deadline is the current node */
-		if (se->deadline == se->min_deadline)
-			return se;
-
-		/* min_deadline is in the left branch */
-		if (node->rb_left &&
-		    __node_2_se(node->rb_left)->min_deadline == se->min_deadline) {
-			node = node->rb_left;
-			continue;
 		}
 
-		/* else min_deadline is in the right branch */
 		node = node->rb_right;
 	}
-	return NULL;
-}
 
-static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
-{
-	struct sched_entity *se = __pick_eevdf(cfs_rq);
-
-	if (!se) {
-		struct sched_entity *left = __pick_first_entity(cfs_rq);
-		if (left) {
-			pr_err("EEVDF scheduling fail, picking leftmost\n");
-			return left;
-		}
-	}
+	if (!best || (curr && entity_before(curr, best)))
+		best = curr;
 
-	return se;
+	return best;
 }
 
 #ifdef CONFIG_SCHED_DEBUG
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 2e5a95486a42..539c7e763f15 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2822,6 +2822,7 @@ DEFINE_LOCK_GUARD_2(double_rq_lock, struct rq,
 		    double_rq_lock(_T->lock, _T->lock2),
 		    double_rq_unlock(_T->lock, _T->lock2))
 
+extern struct sched_entity *__pick_root_entity(struct cfs_rq *cfs_rq);
 extern struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq);
 extern struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq);
 
-- 
cgit v1.2.3


From 5d69eca542ee17c618f9a55da52191d5e28b435f Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Sat, 4 Nov 2023 11:59:18 +0100
Subject: sched: Unify runtime accounting across classes

All classes use sched_entity::exec_start to track runtime and have
copies of the exact same code around to compute runtime.

Collapse all that.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Phil Auld <pauld@redhat.com>
Reviewed-by: Valentin Schneider <vschneid@redhat.com>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Link: https://lkml.kernel.org/r/54d148a144f26d9559698c4dd82d8859038a7380.1699095159.git.bristot@kernel.org
---
 include/linux/sched.h    |  2 +-
 kernel/sched/deadline.c  | 15 +++----------
 kernel/sched/fair.c      | 57 ++++++++++++++++++++++++++++++++++++------------
 kernel/sched/rt.c        | 15 +++----------
 kernel/sched/sched.h     | 12 ++--------
 kernel/sched/stop_task.c | 13 +----------
 6 files changed, 53 insertions(+), 61 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index cd56d4018527..44b46d9743bf 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -523,7 +523,7 @@ struct sched_statistics {
 	u64				block_max;
 	s64				sum_block_runtime;
 
-	u64				exec_max;
+	s64				exec_max;
 	u64				slice_max;
 
 	u64				nr_migrations_cold;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index b28114478b82..de79719c63c0 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1275,9 +1275,8 @@ static void update_curr_dl(struct rq *rq)
 {
 	struct task_struct *curr = rq->curr;
 	struct sched_dl_entity *dl_se = &curr->dl;
-	u64 delta_exec, scaled_delta_exec;
+	s64 delta_exec, scaled_delta_exec;
 	int cpu = cpu_of(rq);
-	u64 now;
 
 	if (!dl_task(curr) || !on_dl_rq(dl_se))
 		return;
@@ -1290,21 +1289,13 @@ static void update_curr_dl(struct rq *rq)
 	 * natural solution, but the full ramifications of this
 	 * approach need further study.
 	 */
-	now = rq_clock_task(rq);
-	delta_exec = now - curr->se.exec_start;
-	if (unlikely((s64)delta_exec <= 0)) {
+	delta_exec = update_curr_common(rq);
+	if (unlikely(delta_exec <= 0)) {
 		if (unlikely(dl_se->dl_yielded))
 			goto throttle;
 		return;
 	}
 
-	schedstat_set(curr->stats.exec_max,
-		      max(curr->stats.exec_max, delta_exec));
-
-	trace_sched_stat_runtime(curr, delta_exec, 0);
-
-	update_current_exec_runtime(curr, now, delta_exec);
-
 	if (dl_entity_is_special(dl_se))
 		return;
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d3e045d80cab..11073cf00134 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1103,23 +1103,17 @@ static void update_tg_load_avg(struct cfs_rq *cfs_rq)
 }
 #endif /* CONFIG_SMP */
 
-/*
- * Update the current task's runtime statistics.
- */
-static void update_curr(struct cfs_rq *cfs_rq)
+static s64 update_curr_se(struct rq *rq, struct sched_entity *curr)
 {
-	struct sched_entity *curr = cfs_rq->curr;
-	u64 now = rq_clock_task(rq_of(cfs_rq));
-	u64 delta_exec;
-
-	if (unlikely(!curr))
-		return;
+	u64 now = rq_clock_task(rq);
+	s64 delta_exec;
 
 	delta_exec = now - curr->exec_start;
-	if (unlikely((s64)delta_exec <= 0))
-		return;
+	if (unlikely(delta_exec <= 0))
+		return delta_exec;
 
 	curr->exec_start = now;
+	curr->sum_exec_runtime += delta_exec;
 
 	if (schedstat_enabled()) {
 		struct sched_statistics *stats;
@@ -1129,8 +1123,43 @@ static void update_curr(struct cfs_rq *cfs_rq)
 				max(delta_exec, stats->exec_max));
 	}
 
-	curr->sum_exec_runtime += delta_exec;
-	schedstat_add(cfs_rq->exec_clock, delta_exec);
+	return delta_exec;
+}
+
+/*
+ * Used by other classes to account runtime.
+ */
+s64 update_curr_common(struct rq *rq)
+{
+	struct task_struct *curr = rq->curr;
+	s64 delta_exec;
+
+	delta_exec = update_curr_se(rq, &curr->se);
+	if (unlikely(delta_exec <= 0))
+		return delta_exec;
+
+	trace_sched_stat_runtime(curr, delta_exec, 0);
+
+	account_group_exec_runtime(curr, delta_exec);
+	cgroup_account_cputime(curr, delta_exec);
+
+	return delta_exec;
+}
+
+/*
+ * Update the current task's runtime statistics.
+ */
+static void update_curr(struct cfs_rq *cfs_rq)
+{
+	struct sched_entity *curr = cfs_rq->curr;
+	s64 delta_exec;
+
+	if (unlikely(!curr))
+		return;
+
+	delta_exec = update_curr_se(rq_of(cfs_rq), curr);
+	if (unlikely(delta_exec <= 0))
+		return;
 
 	curr->vruntime += calc_delta_fair(delta_exec, curr);
 	update_deadline(cfs_rq, curr);
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 6aaf0a3d6081..3261b067b67e 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1002,24 +1002,15 @@ static void update_curr_rt(struct rq *rq)
 {
 	struct task_struct *curr = rq->curr;
 	struct sched_rt_entity *rt_se = &curr->rt;
-	u64 delta_exec;
-	u64 now;
+	s64 delta_exec;
 
 	if (curr->sched_class != &rt_sched_class)
 		return;
 
-	now = rq_clock_task(rq);
-	delta_exec = now - curr->se.exec_start;
-	if (unlikely((s64)delta_exec <= 0))
+	delta_exec = update_curr_common(rq);
+	if (unlikely(delta_exec <= 0))
 		return;
 
-	schedstat_set(curr->stats.exec_max,
-		      max(curr->stats.exec_max, delta_exec));
-
-	trace_sched_stat_runtime(curr, delta_exec, 0);
-
-	update_current_exec_runtime(curr, now, delta_exec);
-
 	if (!rt_bandwidth_enabled())
 		return;
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 539c7e763f15..6703e9e81b1d 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2212,6 +2212,8 @@ struct affinity_context {
 	unsigned int flags;
 };
 
+extern s64 update_curr_common(struct rq *rq);
+
 struct sched_class {
 
 #ifdef CONFIG_UCLAMP_TASK
@@ -3262,16 +3264,6 @@ extern int sched_dynamic_mode(const char *str);
 extern void sched_dynamic_update(int mode);
 #endif
 
-static inline void update_current_exec_runtime(struct task_struct *curr,
-						u64 now, u64 delta_exec)
-{
-	curr->se.sum_exec_runtime += delta_exec;
-	account_group_exec_runtime(curr, delta_exec);
-
-	curr->se.exec_start = now;
-	cgroup_account_cputime(curr, delta_exec);
-}
-
 #ifdef CONFIG_SCHED_MM_CID
 
 #define SCHED_MM_CID_PERIOD_NS	(100ULL * 1000000)	/* 100ms */
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 6cf7304e6449..b1b8fe61c532 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -70,18 +70,7 @@ static void yield_task_stop(struct rq *rq)
 
 static void put_prev_task_stop(struct rq *rq, struct task_struct *prev)
 {
-	struct task_struct *curr = rq->curr;
-	u64 now, delta_exec;
-
-	now = rq_clock_task(rq);
-	delta_exec = now - curr->se.exec_start;
-	if (unlikely((s64)delta_exec < 0))
-		delta_exec = 0;
-
-	schedstat_set(curr->stats.exec_max,
-		      max(curr->stats.exec_max, delta_exec));
-
-	update_current_exec_runtime(curr, now, delta_exec);
+	update_curr_common(rq);
 }
 
 /*
-- 
cgit v1.2.3


From 5fe6ec8f6ab549b6422e41551abb51802bd48bc7 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 6 Nov 2023 13:41:43 +0100
Subject: sched: Remove vruntime from trace_sched_stat_runtime()

Tracing the runtime delta makes sense, observer can sum over time.
Tracing the absolute vruntime makes less sense, inconsistent:
absolute-vs-delta, but also vruntime delta can be computed from
runtime delta.

Removing the vruntime thing also makes the two tracepoint sites
identical, allowing to unify the code in a later patch.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 include/trace/events/sched.h | 15 ++++++---------
 kernel/sched/fair.c          |  5 ++---
 2 files changed, 8 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 6188ad0d9e0d..dbb01b4b7451 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -493,33 +493,30 @@ DEFINE_EVENT_SCHEDSTAT(sched_stat_template, sched_stat_blocked,
  */
 DECLARE_EVENT_CLASS(sched_stat_runtime,
 
-	TP_PROTO(struct task_struct *tsk, u64 runtime, u64 vruntime),
+	TP_PROTO(struct task_struct *tsk, u64 runtime),
 
-	TP_ARGS(tsk, __perf_count(runtime), vruntime),
+	TP_ARGS(tsk, __perf_count(runtime)),
 
 	TP_STRUCT__entry(
 		__array( char,	comm,	TASK_COMM_LEN	)
 		__field( pid_t,	pid			)
 		__field( u64,	runtime			)
-		__field( u64,	vruntime			)
 	),
 
 	TP_fast_assign(
 		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
 		__entry->pid		= tsk->pid;
 		__entry->runtime	= runtime;
-		__entry->vruntime	= vruntime;
 	),
 
-	TP_printk("comm=%s pid=%d runtime=%Lu [ns] vruntime=%Lu [ns]",
+	TP_printk("comm=%s pid=%d runtime=%Lu [ns]",
 			__entry->comm, __entry->pid,
-			(unsigned long long)__entry->runtime,
-			(unsigned long long)__entry->vruntime)
+			(unsigned long long)__entry->runtime)
 );
 
 DEFINE_EVENT(sched_stat_runtime, sched_stat_runtime,
-	     TP_PROTO(struct task_struct *tsk, u64 runtime, u64 vruntime),
-	     TP_ARGS(tsk, runtime, vruntime));
+	     TP_PROTO(struct task_struct *tsk, u64 runtime),
+	     TP_ARGS(tsk, runtime));
 
 /*
  * Tracepoint for showing priority inheritance modifying a tasks
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 11073cf00134..33db70c6b582 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1138,8 +1138,7 @@ s64 update_curr_common(struct rq *rq)
 	if (unlikely(delta_exec <= 0))
 		return delta_exec;
 
-	trace_sched_stat_runtime(curr, delta_exec, 0);
-
+	trace_sched_stat_runtime(curr, delta_exec);
 	account_group_exec_runtime(curr, delta_exec);
 	cgroup_account_cputime(curr, delta_exec);
 
@@ -1168,7 +1167,7 @@ static void update_curr(struct cfs_rq *cfs_rq)
 	if (entity_is_task(curr)) {
 		struct task_struct *curtask = task_of(curr);
 
-		trace_sched_stat_runtime(curtask, delta_exec, curr->vruntime);
+		trace_sched_stat_runtime(curtask, delta_exec);
 		cgroup_account_cputime(curtask, delta_exec);
 		account_group_exec_runtime(curtask, delta_exec);
 	}
-- 
cgit v1.2.3


From 63ba8422f876e32ee564ea95da9a7313b13ff0a1 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Sat, 4 Nov 2023 11:59:21 +0100
Subject: sched/deadline: Introduce deadline servers

Low priority tasks (e.g., SCHED_OTHER) can suffer starvation if tasks
with higher priority (e.g., SCHED_FIFO) monopolize CPU(s).

RT Throttling has been introduced a while ago as a (mostly debug)
countermeasure one can utilize to reserve some CPU time for low priority
tasks (usually background type of work, e.g. workqueues, timers, etc.).
It however has its own problems (see documentation) and the undesired
effect of unconditionally throttling FIFO tasks even when no lower
priority activity needs to run (there are mechanisms to fix this issue
as well, but, again, with their own problems).

Introduce deadline servers to service low priority tasks needs under
starvation conditions. Deadline servers are built extending SCHED_DEADLINE
implementation to allow 2-level scheduling (a sched_deadline entity
becomes a container for lower priority scheduling entities).

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/4968601859d920335cf85822eb573a5f179f04b8.1699095159.git.bristot@kernel.org
---
 include/linux/sched.h   |  22 +++-
 kernel/sched/core.c     |  17 +++
 kernel/sched/deadline.c | 332 ++++++++++++++++++++++++++++++++----------------
 kernel/sched/fair.c     |   2 +
 kernel/sched/sched.h    |  27 ++++
 5 files changed, 292 insertions(+), 108 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 44b46d9743bf..8d258162deb0 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -63,11 +63,13 @@ struct robust_list_head;
 struct root_domain;
 struct rq;
 struct sched_attr;
+struct sched_dl_entity;
 struct seq_file;
 struct sighand_struct;
 struct signal_struct;
 struct task_delay_info;
 struct task_group;
+struct task_struct;
 struct user_event_mm;
 
 /*
@@ -607,6 +609,9 @@ struct sched_rt_entity {
 #endif
 } __randomize_layout;
 
+typedef bool (*dl_server_has_tasks_f)(struct sched_dl_entity *);
+typedef struct task_struct *(*dl_server_pick_f)(struct sched_dl_entity *);
+
 struct sched_dl_entity {
 	struct rb_node			rb_node;
 
@@ -654,6 +659,7 @@ struct sched_dl_entity {
 	unsigned int			dl_yielded        : 1;
 	unsigned int			dl_non_contending : 1;
 	unsigned int			dl_overrun	  : 1;
+	unsigned int			dl_server         : 1;
 
 	/*
 	 * Bandwidth enforcement timer. Each -deadline task has its
@@ -668,7 +674,20 @@ struct sched_dl_entity {
 	 * timer is needed to decrease the active utilization at the correct
 	 * time.
 	 */
-	struct hrtimer inactive_timer;
+	struct hrtimer			inactive_timer;
+
+	/*
+	 * Bits for DL-server functionality. Also see the comment near
+	 * dl_server_update().
+	 *
+	 * @rq the runqueue this server is for
+	 *
+	 * @server_has_tasks() returns true if @server_pick return a
+	 * runnable task.
+	 */
+	struct rq			*rq;
+	dl_server_has_tasks_f		server_has_tasks;
+	dl_server_pick_f		server_pick;
 
 #ifdef CONFIG_RT_MUTEXES
 	/*
@@ -795,6 +814,7 @@ struct task_struct {
 	struct sched_entity		se;
 	struct sched_rt_entity		rt;
 	struct sched_dl_entity		dl;
+	struct sched_dl_entity		*dl_server;
 	const struct sched_class	*sched_class;
 
 #ifdef CONFIG_SCHED_CORE
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 966631f05d71..f5f4495d1768 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3797,6 +3797,8 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 		rq->idle_stamp = 0;
 	}
 #endif
+
+	p->dl_server = NULL;
 }
 
 /*
@@ -6003,12 +6005,27 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 			p = pick_next_task_idle(rq);
 		}
 
+		/*
+		 * This is the fast path; it cannot be a DL server pick;
+		 * therefore even if @p == @prev, ->dl_server must be NULL.
+		 */
+		if (p->dl_server)
+			p->dl_server = NULL;
+
 		return p;
 	}
 
 restart:
 	put_prev_task_balance(rq, prev, rf);
 
+	/*
+	 * We've updated @prev and no longer need the server link, clear it.
+	 * Must be done before ->pick_next_task() because that can (re)set
+	 * ->dl_server.
+	 */
+	if (prev->dl_server)
+		prev->dl_server = NULL;
+
 	for_each_class(class) {
 		p = class->pick_next_task(rq);
 		if (p)
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 81810f67df7a..a04a436af8cc 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -54,8 +54,14 @@ static int __init sched_dl_sysctl_init(void)
 late_initcall(sched_dl_sysctl_init);
 #endif
 
+static bool dl_server(struct sched_dl_entity *dl_se)
+{
+	return dl_se->dl_server;
+}
+
 static inline struct task_struct *dl_task_of(struct sched_dl_entity *dl_se)
 {
+	BUG_ON(dl_server(dl_se));
 	return container_of(dl_se, struct task_struct, dl);
 }
 
@@ -64,12 +70,19 @@ static inline struct rq *rq_of_dl_rq(struct dl_rq *dl_rq)
 	return container_of(dl_rq, struct rq, dl);
 }
 
-static inline struct dl_rq *dl_rq_of_se(struct sched_dl_entity *dl_se)
+static inline struct rq *rq_of_dl_se(struct sched_dl_entity *dl_se)
 {
-	struct task_struct *p = dl_task_of(dl_se);
-	struct rq *rq = task_rq(p);
+	struct rq *rq = dl_se->rq;
+
+	if (!dl_server(dl_se))
+		rq = task_rq(dl_task_of(dl_se));
 
-	return &rq->dl;
+	return rq;
+}
+
+static inline struct dl_rq *dl_rq_of_se(struct sched_dl_entity *dl_se)
+{
+	return &rq_of_dl_se(dl_se)->dl;
 }
 
 static inline int on_dl_rq(struct sched_dl_entity *dl_se)
@@ -394,9 +407,8 @@ static void __dl_clear_params(struct sched_dl_entity *dl_se);
 static void task_non_contending(struct sched_dl_entity *dl_se)
 {
 	struct hrtimer *timer = &dl_se->inactive_timer;
-	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
-	struct rq *rq = rq_of_dl_rq(dl_rq);
-	struct task_struct *p = dl_task_of(dl_se);
+	struct rq *rq = rq_of_dl_se(dl_se);
+	struct dl_rq *dl_rq = &rq->dl;
 	s64 zerolag_time;
 
 	/*
@@ -426,25 +438,33 @@ static void task_non_contending(struct sched_dl_entity *dl_se)
 	 * utilization now, instead of starting a timer
 	 */
 	if ((zerolag_time < 0) || hrtimer_active(&dl_se->inactive_timer)) {
-		if (dl_task(p))
+		if (dl_server(dl_se)) {
 			sub_running_bw(dl_se, dl_rq);
+		} else {
+			struct task_struct *p = dl_task_of(dl_se);
 
-		if (!dl_task(p) || READ_ONCE(p->__state) == TASK_DEAD) {
-			struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
+			if (dl_task(p))
+				sub_running_bw(dl_se, dl_rq);
 
-			if (READ_ONCE(p->__state) == TASK_DEAD)
-				sub_rq_bw(dl_se, &rq->dl);
-			raw_spin_lock(&dl_b->lock);
-			__dl_sub(dl_b, dl_se->dl_bw, dl_bw_cpus(task_cpu(p)));
-			raw_spin_unlock(&dl_b->lock);
-			__dl_clear_params(dl_se);
+			if (!dl_task(p) || READ_ONCE(p->__state) == TASK_DEAD) {
+				struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
+
+				if (READ_ONCE(p->__state) == TASK_DEAD)
+					sub_rq_bw(dl_se, &rq->dl);
+				raw_spin_lock(&dl_b->lock);
+				__dl_sub(dl_b, dl_se->dl_bw, dl_bw_cpus(task_cpu(p)));
+				raw_spin_unlock(&dl_b->lock);
+				__dl_clear_params(dl_se);
+			}
 		}
 
 		return;
 	}
 
 	dl_se->dl_non_contending = 1;
-	get_task_struct(p);
+	if (!dl_server(dl_se))
+		get_task_struct(dl_task_of(dl_se));
+
 	hrtimer_start(timer, ns_to_ktime(zerolag_time), HRTIMER_MODE_REL_HARD);
 }
 
@@ -471,8 +491,10 @@ static void task_contending(struct sched_dl_entity *dl_se, int flags)
 		 * will not touch the rq's active utilization,
 		 * so we are still safe.
 		 */
-		if (hrtimer_try_to_cancel(&dl_se->inactive_timer) == 1)
-			put_task_struct(dl_task_of(dl_se));
+		if (hrtimer_try_to_cancel(&dl_se->inactive_timer) == 1) {
+			if (!dl_server(dl_se))
+				put_task_struct(dl_task_of(dl_se));
+		}
 	} else {
 		/*
 		 * Since "dl_non_contending" is not set, the
@@ -485,10 +507,8 @@ static void task_contending(struct sched_dl_entity *dl_se, int flags)
 	}
 }
 
-static inline int is_leftmost(struct task_struct *p, struct dl_rq *dl_rq)
+static inline int is_leftmost(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 {
-	struct sched_dl_entity *dl_se = &p->dl;
-
 	return rb_first_cached(&dl_rq->root) == &dl_se->rb_node;
 }
 
@@ -740,8 +760,10 @@ static inline void deadline_queue_pull_task(struct rq *rq)
 }
 #endif /* CONFIG_SMP */
 
+static void
+enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags);
 static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags);
-static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags);
+static void dequeue_dl_entity(struct sched_dl_entity *dl_se, int flags);
 static void wakeup_preempt_dl(struct rq *rq, struct task_struct *p, int flags);
 
 static inline void replenish_dl_new_period(struct sched_dl_entity *dl_se,
@@ -989,8 +1011,7 @@ static inline bool dl_is_implicit(struct sched_dl_entity *dl_se)
  */
 static void update_dl_entity(struct sched_dl_entity *dl_se)
 {
-	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
-	struct rq *rq = rq_of_dl_rq(dl_rq);
+	struct rq *rq = rq_of_dl_se(dl_se);
 
 	if (dl_time_before(dl_se->deadline, rq_clock(rq)) ||
 	    dl_entity_overflow(dl_se, rq_clock(rq))) {
@@ -1021,11 +1042,11 @@ static inline u64 dl_next_period(struct sched_dl_entity *dl_se)
  * actually started or not (i.e., the replenishment instant is in
  * the future or in the past).
  */
-static int start_dl_timer(struct task_struct *p)
+static int start_dl_timer(struct sched_dl_entity *dl_se)
 {
-	struct sched_dl_entity *dl_se = &p->dl;
 	struct hrtimer *timer = &dl_se->dl_timer;
-	struct rq *rq = task_rq(p);
+	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+	struct rq *rq = rq_of_dl_rq(dl_rq);
 	ktime_t now, act;
 	s64 delta;
 
@@ -1059,13 +1080,33 @@ static int start_dl_timer(struct task_struct *p)
 	 * and observe our state.
 	 */
 	if (!hrtimer_is_queued(timer)) {
-		get_task_struct(p);
+		if (!dl_server(dl_se))
+			get_task_struct(dl_task_of(dl_se));
 		hrtimer_start(timer, act, HRTIMER_MODE_ABS_HARD);
 	}
 
 	return 1;
 }
 
+static void __push_dl_task(struct rq *rq, struct rq_flags *rf)
+{
+#ifdef CONFIG_SMP
+	/*
+	 * Queueing this task back might have overloaded rq, check if we need
+	 * to kick someone away.
+	 */
+	if (has_pushable_dl_tasks(rq)) {
+		/*
+		 * Nothing relies on rq->lock after this, so its safe to drop
+		 * rq->lock.
+		 */
+		rq_unpin_lock(rq, rf);
+		push_dl_task(rq);
+		rq_repin_lock(rq, rf);
+	}
+#endif
+}
+
 /*
  * This is the bandwidth enforcement timer callback. If here, we know
  * a task is not on its dl_rq, since the fact that the timer was running
@@ -1084,10 +1125,34 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 	struct sched_dl_entity *dl_se = container_of(timer,
 						     struct sched_dl_entity,
 						     dl_timer);
-	struct task_struct *p = dl_task_of(dl_se);
+	struct task_struct *p;
 	struct rq_flags rf;
 	struct rq *rq;
 
+	if (dl_server(dl_se)) {
+		struct rq *rq = rq_of_dl_se(dl_se);
+		struct rq_flags rf;
+
+		rq_lock(rq, &rf);
+		if (dl_se->dl_throttled) {
+			sched_clock_tick();
+			update_rq_clock(rq);
+
+			if (dl_se->server_has_tasks(dl_se)) {
+				enqueue_dl_entity(dl_se, ENQUEUE_REPLENISH);
+				resched_curr(rq);
+				__push_dl_task(rq, &rf);
+			} else {
+				replenish_dl_entity(dl_se);
+			}
+
+		}
+		rq_unlock(rq, &rf);
+
+		return HRTIMER_NORESTART;
+	}
+
+	p = dl_task_of(dl_se);
 	rq = task_rq_lock(p, &rf);
 
 	/*
@@ -1158,21 +1223,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 	else
 		resched_curr(rq);
 
-#ifdef CONFIG_SMP
-	/*
-	 * Queueing this task back might have overloaded rq, check if we need
-	 * to kick someone away.
-	 */
-	if (has_pushable_dl_tasks(rq)) {
-		/*
-		 * Nothing relies on rq->lock after this, so its safe to drop
-		 * rq->lock.
-		 */
-		rq_unpin_lock(rq, &rf);
-		push_dl_task(rq);
-		rq_repin_lock(rq, &rf);
-	}
-#endif
+	__push_dl_task(rq, &rf);
 
 unlock:
 	task_rq_unlock(rq, p, &rf);
@@ -1214,12 +1265,11 @@ static void init_dl_task_timer(struct sched_dl_entity *dl_se)
  */
 static inline void dl_check_constrained_dl(struct sched_dl_entity *dl_se)
 {
-	struct task_struct *p = dl_task_of(dl_se);
-	struct rq *rq = rq_of_dl_rq(dl_rq_of_se(dl_se));
+	struct rq *rq = rq_of_dl_se(dl_se);
 
 	if (dl_time_before(dl_se->deadline, rq_clock(rq)) &&
 	    dl_time_before(rq_clock(rq), dl_next_period(dl_se))) {
-		if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(p)))
+		if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(dl_se)))
 			return;
 		dl_se->dl_throttled = 1;
 		if (dl_se->runtime > 0)
@@ -1270,29 +1320,13 @@ static u64 grub_reclaim(u64 delta, struct rq *rq, struct sched_dl_entity *dl_se)
 	return (delta * u_act) >> BW_SHIFT;
 }
 
-/*
- * Update the current task's runtime statistics (provided it is still
- * a -deadline task and has not been removed from the dl_rq).
- */
-static void update_curr_dl(struct rq *rq)
+static inline void
+update_stats_dequeue_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se,
+                        int flags);
+static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64 delta_exec)
 {
-	struct task_struct *curr = rq->curr;
-	struct sched_dl_entity *dl_se = &curr->dl;
-	s64 delta_exec, scaled_delta_exec;
-	int cpu = cpu_of(rq);
-
-	if (!dl_task(curr) || !on_dl_rq(dl_se))
-		return;
+	s64 scaled_delta_exec;
 
-	/*
-	 * Consumed budget is computed considering the time as
-	 * observed by schedulable tasks (excluding time spent
-	 * in hardirq context, etc.). Deadlines are instead
-	 * computed using hard walltime. This seems to be the more
-	 * natural solution, but the full ramifications of this
-	 * approach need further study.
-	 */
-	delta_exec = update_curr_common(rq);
 	if (unlikely(delta_exec <= 0)) {
 		if (unlikely(dl_se->dl_yielded))
 			goto throttle;
@@ -1310,10 +1344,9 @@ static void update_curr_dl(struct rq *rq)
 	 * according to current frequency and CPU maximum capacity.
 	 */
 	if (unlikely(dl_se->flags & SCHED_FLAG_RECLAIM)) {
-		scaled_delta_exec = grub_reclaim(delta_exec,
-						 rq,
-						 &curr->dl);
+		scaled_delta_exec = grub_reclaim(delta_exec, rq, dl_se);
 	} else {
+		int cpu = cpu_of(rq);
 		unsigned long scale_freq = arch_scale_freq_capacity(cpu);
 		unsigned long scale_cpu = arch_scale_cpu_capacity(cpu);
 
@@ -1332,11 +1365,20 @@ throttle:
 		    (dl_se->flags & SCHED_FLAG_DL_OVERRUN))
 			dl_se->dl_overrun = 1;
 
-		__dequeue_task_dl(rq, curr, 0);
-		if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(curr)))
-			enqueue_task_dl(rq, curr, ENQUEUE_REPLENISH);
+		dequeue_dl_entity(dl_se, 0);
+		if (!dl_server(dl_se)) {
+			update_stats_dequeue_dl(&rq->dl, dl_se, 0);
+			dequeue_pushable_dl_task(rq, dl_task_of(dl_se));
+		}
 
-		if (!is_leftmost(curr, &rq->dl))
+		if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(dl_se))) {
+			if (dl_server(dl_se))
+				enqueue_dl_entity(dl_se, ENQUEUE_REPLENISH);
+			else
+				enqueue_task_dl(rq, dl_task_of(dl_se), ENQUEUE_REPLENISH);
+		}
+
+		if (!is_leftmost(dl_se, &rq->dl))
 			resched_curr(rq);
 	}
 
@@ -1366,20 +1408,82 @@ throttle:
 	}
 }
 
+void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec)
+{
+	update_curr_dl_se(dl_se->rq, dl_se, delta_exec);
+}
+
+void dl_server_start(struct sched_dl_entity *dl_se)
+{
+	if (!dl_server(dl_se)) {
+		dl_se->dl_server = 1;
+		setup_new_dl_entity(dl_se);
+	}
+	enqueue_dl_entity(dl_se, ENQUEUE_WAKEUP);
+}
+
+void dl_server_stop(struct sched_dl_entity *dl_se)
+{
+	dequeue_dl_entity(dl_se, DEQUEUE_SLEEP);
+}
+
+void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq,
+		    dl_server_has_tasks_f has_tasks,
+		    dl_server_pick_f pick)
+{
+	dl_se->rq = rq;
+	dl_se->server_has_tasks = has_tasks;
+	dl_se->server_pick = pick;
+}
+
+/*
+ * Update the current task's runtime statistics (provided it is still
+ * a -deadline task and has not been removed from the dl_rq).
+ */
+static void update_curr_dl(struct rq *rq)
+{
+	struct task_struct *curr = rq->curr;
+	struct sched_dl_entity *dl_se = &curr->dl;
+	s64 delta_exec;
+
+	if (!dl_task(curr) || !on_dl_rq(dl_se))
+		return;
+
+	/*
+	 * Consumed budget is computed considering the time as
+	 * observed by schedulable tasks (excluding time spent
+	 * in hardirq context, etc.). Deadlines are instead
+	 * computed using hard walltime. This seems to be the more
+	 * natural solution, but the full ramifications of this
+	 * approach need further study.
+	 */
+	delta_exec = update_curr_common(rq);
+	update_curr_dl_se(rq, dl_se, delta_exec);
+}
+
 static enum hrtimer_restart inactive_task_timer(struct hrtimer *timer)
 {
 	struct sched_dl_entity *dl_se = container_of(timer,
 						     struct sched_dl_entity,
 						     inactive_timer);
-	struct task_struct *p = dl_task_of(dl_se);
+	struct task_struct *p = NULL;
 	struct rq_flags rf;
 	struct rq *rq;
 
-	rq = task_rq_lock(p, &rf);
+	if (!dl_server(dl_se)) {
+		p = dl_task_of(dl_se);
+		rq = task_rq_lock(p, &rf);
+	} else {
+		rq = dl_se->rq;
+		rq_lock(rq, &rf);
+	}
 
 	sched_clock_tick();
 	update_rq_clock(rq);
 
+	if (dl_server(dl_se))
+		goto no_task;
+
 	if (!dl_task(p) || READ_ONCE(p->__state) == TASK_DEAD) {
 		struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
 
@@ -1396,14 +1500,21 @@ static enum hrtimer_restart inactive_task_timer(struct hrtimer *timer)
 
 		goto unlock;
 	}
+
+no_task:
 	if (dl_se->dl_non_contending == 0)
 		goto unlock;
 
 	sub_running_bw(dl_se, &rq->dl);
 	dl_se->dl_non_contending = 0;
 unlock:
-	task_rq_unlock(rq, p, &rf);
-	put_task_struct(p);
+
+	if (!dl_server(dl_se)) {
+		task_rq_unlock(rq, p, &rf);
+		put_task_struct(p);
+	} else {
+		rq_unlock(rq, &rf);
+	}
 
 	return HRTIMER_NORESTART;
 }
@@ -1466,10 +1577,8 @@ static inline void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline) {}
 static inline
 void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 {
-	int prio = dl_task_of(dl_se)->prio;
 	u64 deadline = dl_se->deadline;
 
-	WARN_ON(!dl_prio(prio));
 	dl_rq->dl_nr_running++;
 	add_nr_running(rq_of_dl_rq(dl_rq), 1);
 
@@ -1479,9 +1588,6 @@ void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 static inline
 void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 {
-	int prio = dl_task_of(dl_se)->prio;
-
-	WARN_ON(!dl_prio(prio));
 	WARN_ON(!dl_rq->dl_nr_running);
 	dl_rq->dl_nr_running--;
 	sub_nr_running(rq_of_dl_rq(dl_rq), 1);
@@ -1648,8 +1754,7 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags)
 	} else if (flags & ENQUEUE_REPLENISH) {
 		replenish_dl_entity(dl_se);
 	} else if ((flags & ENQUEUE_RESTORE) &&
-		  dl_time_before(dl_se->deadline,
-				 rq_clock(rq_of_dl_rq(dl_rq_of_se(dl_se))))) {
+		   dl_time_before(dl_se->deadline, rq_clock(rq_of_dl_se(dl_se)))) {
 		setup_new_dl_entity(dl_se);
 	}
 
@@ -1730,19 +1835,13 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 
 	enqueue_dl_entity(&p->dl, flags);
 
+	if (dl_server(&p->dl))
+		return;
+
 	if (!task_current(rq, p) && !p->dl.dl_throttled && p->nr_cpus_allowed > 1)
 		enqueue_pushable_dl_task(rq, p);
 }
 
-static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
-{
-	update_stats_dequeue_dl(&rq->dl, &p->dl, flags);
-	dequeue_dl_entity(&p->dl, flags);
-
-	if (!p->dl.dl_throttled)
-		dequeue_pushable_dl_task(rq, p);
-}
-
 static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 {
 	update_curr_dl(rq);
@@ -1750,7 +1849,9 @@ static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 	if (p->on_rq == TASK_ON_RQ_MIGRATING)
 		flags |= DEQUEUE_MIGRATING;
 
-	__dequeue_task_dl(rq, p, flags);
+	dequeue_dl_entity(&p->dl, flags);
+	if (!p->dl.dl_throttled && !dl_server(&p->dl))
+		dequeue_pushable_dl_task(rq, p);
 }
 
 /*
@@ -1940,12 +2041,12 @@ static void wakeup_preempt_dl(struct rq *rq, struct task_struct *p,
 }
 
 #ifdef CONFIG_SCHED_HRTICK
-static void start_hrtick_dl(struct rq *rq, struct task_struct *p)
+static void start_hrtick_dl(struct rq *rq, struct sched_dl_entity *dl_se)
 {
-	hrtick_start(rq, p->dl.runtime);
+	hrtick_start(rq, dl_se->runtime);
 }
 #else /* !CONFIG_SCHED_HRTICK */
-static void start_hrtick_dl(struct rq *rq, struct task_struct *p)
+static void start_hrtick_dl(struct rq *rq, struct sched_dl_entity *dl_se)
 {
 }
 #endif
@@ -1965,9 +2066,6 @@ static void set_next_task_dl(struct rq *rq, struct task_struct *p, bool first)
 	if (!first)
 		return;
 
-	if (hrtick_enabled_dl(rq))
-		start_hrtick_dl(rq, p);
-
 	if (rq->curr->sched_class != &dl_sched_class)
 		update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 0);
 
@@ -1990,12 +2088,25 @@ static struct task_struct *pick_task_dl(struct rq *rq)
 	struct dl_rq *dl_rq = &rq->dl;
 	struct task_struct *p;
 
+again:
 	if (!sched_dl_runnable(rq))
 		return NULL;
 
 	dl_se = pick_next_dl_entity(dl_rq);
 	WARN_ON_ONCE(!dl_se);
-	p = dl_task_of(dl_se);
+
+	if (dl_server(dl_se)) {
+		p = dl_se->server_pick(dl_se);
+		if (!p) {
+			WARN_ON_ONCE(1);
+			dl_se->dl_yielded = 1;
+			update_curr_dl_se(rq, dl_se, 0);
+			goto again;
+		}
+		p->dl_server = dl_se;
+	} else {
+		p = dl_task_of(dl_se);
+	}
 
 	return p;
 }
@@ -2005,9 +2116,15 @@ static struct task_struct *pick_next_task_dl(struct rq *rq)
 	struct task_struct *p;
 
 	p = pick_task_dl(rq);
-	if (p)
+	if (!p)
+		return p;
+
+	if (!p->dl_server)
 		set_next_task_dl(rq, p, true);
 
+	if (hrtick_enabled(rq))
+		start_hrtick_dl(rq, &p->dl);
+
 	return p;
 }
 
@@ -2045,8 +2162,8 @@ static void task_tick_dl(struct rq *rq, struct task_struct *p, int queued)
 	 * be set and schedule() will start a new hrtick for the next task.
 	 */
 	if (hrtick_enabled_dl(rq) && queued && p->dl.runtime > 0 &&
-	    is_leftmost(p, &rq->dl))
-		start_hrtick_dl(rq, p);
+	    is_leftmost(&p->dl, &rq->dl))
+		start_hrtick_dl(rq, &p->dl);
 }
 
 static void task_fork_dl(struct task_struct *p)
@@ -2986,6 +3103,7 @@ static void __dl_clear_params(struct sched_dl_entity *dl_se)
 	dl_se->dl_yielded		= 0;
 	dl_se->dl_non_contending	= 0;
 	dl_se->dl_overrun		= 0;
+	dl_se->dl_server		= 0;
 
 #ifdef CONFIG_RT_MUTEXES
 	dl_se->pi_se			= dl_se;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1cd92b11b289..07f555857698 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1131,6 +1131,8 @@ static inline void update_curr_task(struct task_struct *p, s64 delta_exec)
 	trace_sched_stat_runtime(p, delta_exec);
 	account_group_exec_runtime(p, delta_exec);
 	cgroup_account_cputime(p, delta_exec);
+	if (p->dl_server)
+		dl_server_update(p->dl_server, delta_exec);
 }
 
 /*
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 1cda787172f0..8a70d51ffa33 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -313,6 +313,33 @@ extern bool dl_param_changed(struct task_struct *p, const struct sched_attr *att
 extern int  dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial);
 extern int  dl_bw_check_overflow(int cpu);
 
+/*
+ * SCHED_DEADLINE supports servers (nested scheduling) with the following
+ * interface:
+ *
+ *   dl_se::rq -- runqueue we belong to.
+ *
+ *   dl_se::server_has_tasks() -- used on bandwidth enforcement; we 'stop' the
+ *                                server when it runs out of tasks to run.
+ *
+ *   dl_se::server_pick() -- nested pick_next_task(); we yield the period if this
+ *                           returns NULL.
+ *
+ *   dl_server_update() -- called from update_curr_common(), propagates runtime
+ *                         to the server.
+ *
+ *   dl_server_start()
+ *   dl_server_stop()  -- start/stop the server when it has (no) tasks.
+ *
+ *   dl_server_init() -- initializes the server.
+ */
+extern void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec);
+extern void dl_server_start(struct sched_dl_entity *dl_se);
+extern void dl_server_stop(struct sched_dl_entity *dl_se);
+extern void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq,
+		    dl_server_has_tasks_f has_tasks,
+		    dl_server_pick_f pick);
+
 #ifdef CONFIG_CGROUP_SCHED
 
 struct cfs_rq;
-- 
cgit v1.2.3


From e4ab322fbaaaf84b23d6cb0e3317a7f68baf36dc Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Sun, 17 Sep 2023 13:22:17 +0200
Subject: cleanup: Add conditional guard support

Adds:

 - DEFINE_GUARD_COND() / DEFINE_LOCK_GUARD_1_COND() to extend existing
   guards with conditional lock primitives, eg. mutex_trylock(),
   mutex_lock_interruptible().

   nb. both primitives allow NULL 'locks', which cause the lock to
       fail (obviously).

 - extends scoped_guard() to not take the body when the the
   conditional guard 'fails'. eg.

     scoped_guard (mutex_intr, &task->signal_cred_guard_mutex) {
	...
     }

   will only execute the body when the mutex is held.

 - provides scoped_cond_guard(name, fail, args...); which extends
   scoped_guard() to do fail when the lock-acquire fails.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20231102110706.460851167%40infradead.org
---
 include/linux/cleanup.h  | 52 +++++++++++++++++++++++++++++++++++++++++++++---
 include/linux/mutex.h    |  3 ++-
 include/linux/rwsem.h    |  8 ++++----
 include/linux/spinlock.h | 15 ++++++++++++++
 4 files changed, 70 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h
index 9f1a9c455b68..c2d09bc4f976 100644
--- a/include/linux/cleanup.h
+++ b/include/linux/cleanup.h
@@ -125,25 +125,55 @@ static inline class_##_name##_t class_##_name##ext##_constructor(_init_args) \
  *	trivial wrapper around DEFINE_CLASS() above specifically
  *	for locks.
  *
+ * DEFINE_GUARD_COND(name, ext, condlock)
+ *	wrapper around EXTEND_CLASS above to add conditional lock
+ *	variants to a base class, eg. mutex_trylock() or
+ *	mutex_lock_interruptible().
+ *
  * guard(name):
- *	an anonymous instance of the (guard) class
+ *	an anonymous instance of the (guard) class, not recommended for
+ *	conditional locks.
  *
  * scoped_guard (name, args...) { }:
  *	similar to CLASS(name, scope)(args), except the variable (with the
  *	explicit name 'scope') is declard in a for-loop such that its scope is
  *	bound to the next (compound) statement.
  *
+ *	for conditional locks the loop body is skipped when the lock is not
+ *	acquired.
+ *
+ * scoped_cond_guard (name, fail, args...) { }:
+ *      similar to scoped_guard(), except it does fail when the lock
+ *      acquire fails.
+ *
  */
 
 #define DEFINE_GUARD(_name, _type, _lock, _unlock) \
-	DEFINE_CLASS(_name, _type, _unlock, ({ _lock; _T; }), _type _T)
+	DEFINE_CLASS(_name, _type, if (_T) { _unlock; }, ({ _lock; _T; }), _type _T); \
+	static inline void * class_##_name##_lock_ptr(class_##_name##_t *_T) \
+	{ return *_T; }
+
+#define DEFINE_GUARD_COND(_name, _ext, _condlock) \
+	EXTEND_CLASS(_name, _ext, \
+		     ({ void *_t = _T; if (_T && !(_condlock)) _t = NULL; _t; }), \
+		     class_##_name##_t _T) \
+	static inline void * class_##_name##_ext##_lock_ptr(class_##_name##_t *_T) \
+	{ return class_##_name##_lock_ptr(_T); }
 
 #define guard(_name) \
 	CLASS(_name, __UNIQUE_ID(guard))
 
+#define __guard_ptr(_name) class_##_name##_lock_ptr
+
 #define scoped_guard(_name, args...)					\
 	for (CLASS(_name, scope)(args),					\
-	     *done = NULL; !done; done = (void *)1)
+	     *done = NULL; __guard_ptr(_name)(&scope) && !done; done = (void *)1)
+
+#define scoped_cond_guard(_name, _fail, args...) \
+	for (CLASS(_name, scope)(args), \
+	     *done = NULL; !done; done = (void *)1) \
+		if (!__guard_ptr(_name)(&scope)) _fail; \
+		else
 
 /*
  * Additional helper macros for generating lock guards with types, either for
@@ -152,6 +182,7 @@ static inline class_##_name##_t class_##_name##ext##_constructor(_init_args) \
  *
  * DEFINE_LOCK_GUARD_0(name, lock, unlock, ...)
  * DEFINE_LOCK_GUARD_1(name, type, lock, unlock, ...)
+ * DEFINE_LOCK_GUARD_1_COND(name, ext, condlock)
  *
  * will result in the following type:
  *
@@ -173,6 +204,11 @@ typedef struct {							\
 static inline void class_##_name##_destructor(class_##_name##_t *_T)	\
 {									\
 	if (_T->lock) { _unlock; }					\
+}									\
+									\
+static inline void *class_##_name##_lock_ptr(class_##_name##_t *_T)	\
+{									\
+	return _T->lock;						\
 }
 
 
@@ -201,4 +237,14 @@ __DEFINE_LOCK_GUARD_1(_name, _type, _lock)
 __DEFINE_UNLOCK_GUARD(_name, void, _unlock, __VA_ARGS__)		\
 __DEFINE_LOCK_GUARD_0(_name, _lock)
 
+#define DEFINE_LOCK_GUARD_1_COND(_name, _ext, _condlock)		\
+	EXTEND_CLASS(_name, _ext,					\
+		     ({ class_##_name##_t _t = { .lock = l }, *_T = &_t;\
+		        if (_T->lock && !(_condlock)) _T->lock = NULL;	\
+			_t; }),						\
+		     typeof_member(class_##_name##_t, lock) l)		\
+	static inline void * class_##_name##_ext##_lock_ptr(class_##_name##_t *_T) \
+	{ return class_##_name##_lock_ptr(_T); }
+
+
 #endif /* __LINUX_GUARDS_H */
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index a33aa9eb9fc3..95d11308f995 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -221,6 +221,7 @@ extern void mutex_unlock(struct mutex *lock);
 extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock);
 
 DEFINE_GUARD(mutex, struct mutex *, mutex_lock(_T), mutex_unlock(_T))
-DEFINE_FREE(mutex, struct mutex *, if (_T) mutex_unlock(_T))
+DEFINE_GUARD_COND(mutex, _try, mutex_trylock(_T))
+DEFINE_GUARD_COND(mutex, _intr, mutex_lock_interruptible(_T) == 0)
 
 #endif /* __LINUX_MUTEX_H */
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index 1dd530ce8b45..9c29689ff505 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -203,11 +203,11 @@ extern void up_read(struct rw_semaphore *sem);
 extern void up_write(struct rw_semaphore *sem);
 
 DEFINE_GUARD(rwsem_read, struct rw_semaphore *, down_read(_T), up_read(_T))
-DEFINE_GUARD(rwsem_write, struct rw_semaphore *, down_write(_T), up_write(_T))
-
-DEFINE_FREE(up_read, struct rw_semaphore *, if (_T) up_read(_T))
-DEFINE_FREE(up_write, struct rw_semaphore *, if (_T) up_write(_T))
+DEFINE_GUARD_COND(rwsem_read, _try, down_read_trylock(_T))
+DEFINE_GUARD_COND(rwsem_read, _intr, down_read_interruptible(_T) == 0)
 
+DEFINE_GUARD(rwsem_write, struct rw_semaphore *, down_write(_T), up_write(_T))
+DEFINE_GUARD_COND(rwsem_write, _try, down_write_trylock(_T))
 
 /*
  * downgrade write lock to read lock
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 31d3d747a9db..ceb56b39c70f 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -507,6 +507,8 @@ DEFINE_LOCK_GUARD_1(raw_spinlock, raw_spinlock_t,
 		    raw_spin_lock(_T->lock),
 		    raw_spin_unlock(_T->lock))
 
+DEFINE_LOCK_GUARD_1_COND(raw_spinlock, _try, raw_spin_trylock(_T->lock))
+
 DEFINE_LOCK_GUARD_1(raw_spinlock_nested, raw_spinlock_t,
 		    raw_spin_lock_nested(_T->lock, SINGLE_DEPTH_NESTING),
 		    raw_spin_unlock(_T->lock))
@@ -515,23 +517,36 @@ DEFINE_LOCK_GUARD_1(raw_spinlock_irq, raw_spinlock_t,
 		    raw_spin_lock_irq(_T->lock),
 		    raw_spin_unlock_irq(_T->lock))
 
+DEFINE_LOCK_GUARD_1_COND(raw_spinlock_irq, _try, raw_spin_trylock_irq(_T->lock))
+
 DEFINE_LOCK_GUARD_1(raw_spinlock_irqsave, raw_spinlock_t,
 		    raw_spin_lock_irqsave(_T->lock, _T->flags),
 		    raw_spin_unlock_irqrestore(_T->lock, _T->flags),
 		    unsigned long flags)
 
+DEFINE_LOCK_GUARD_1_COND(raw_spinlock_irqsave, _try,
+			 raw_spin_trylock_irqsave(_T->lock, _T->flags))
+
 DEFINE_LOCK_GUARD_1(spinlock, spinlock_t,
 		    spin_lock(_T->lock),
 		    spin_unlock(_T->lock))
 
+DEFINE_LOCK_GUARD_1_COND(spinlock, _try, spin_trylock(_T->lock))
+
 DEFINE_LOCK_GUARD_1(spinlock_irq, spinlock_t,
 		    spin_lock_irq(_T->lock),
 		    spin_unlock_irq(_T->lock))
 
+DEFINE_LOCK_GUARD_1_COND(spinlock_irq, _try,
+			 spin_trylock_irq(_T->lock))
+
 DEFINE_LOCK_GUARD_1(spinlock_irqsave, spinlock_t,
 		    spin_lock_irqsave(_T->lock, _T->flags),
 		    spin_unlock_irqrestore(_T->lock, _T->flags),
 		    unsigned long flags)
 
+DEFINE_LOCK_GUARD_1_COND(spinlock_irqsave, _try,
+			 spin_trylock_irqsave(_T->lock, _T->flags))
+
 #undef __LINUX_INSIDE_SPINLOCK_H
 #endif /* __LINUX_SPINLOCK_H */
-- 
cgit v1.2.3


From 4f6dd2a4bf378bc4d169296739ea7d6972c0d858 Mon Sep 17 00:00:00 2001
From: Can Guo <quic_cang@quicinc.com>
Date: Wed, 1 Nov 2023 18:58:36 -0700
Subject: scsi: ufs: ufs-sysfs: Expose UFS power info

Having UFS power info available in sysfs makes it easier to tell the state
of the link during runtime considering we have a bunch of power saving
features and various combinations for backward compatibility.

Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Reviewed-by: Bean Huo <beanhuo@micron.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Can Guo <quic_cang@quicinc.com>
Link: https://lore.kernel.org/r/1698890324-7374-1-git-send-email-quic_cang@quicinc.com
Reviewed-by: Avri Altman <avri.altman@wdc.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 Documentation/ABI/testing/sysfs-driver-ufs |  49 ++++++++++++
 drivers/ufs/core/ufs-sysfs.c               | 120 +++++++++++++++++++++++++++++
 include/ufs/unipro.h                       |   4 +-
 3 files changed, 171 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/Documentation/ABI/testing/sysfs-driver-ufs b/Documentation/ABI/testing/sysfs-driver-ufs
index 0c7efaf62de0..b73067bb5ea2 100644
--- a/Documentation/ABI/testing/sysfs-driver-ufs
+++ b/Documentation/ABI/testing/sysfs-driver-ufs
@@ -1223,6 +1223,55 @@ Description:	This file shows the total latency (in micro seconds) of write
 
 		The file is read only.
 
+What:		/sys/bus/platform/drivers/ufshcd/*/power_info/lane
+What:		/sys/bus/platform/devices/*.ufs/power_info/lane
+Date:		September 2023
+Contact:	Can Guo <quic_cang@quicinc.com>
+Description:	This file shows how many lanes are enabled on the UFS link,
+		i.e., an output 2 means UFS link is operating with 2 lanes.
+
+		The file is read only.
+
+What:		/sys/bus/platform/drivers/ufshcd/*/power_info/mode
+What:		/sys/bus/platform/devices/*.ufs/power_info/mode
+Date:		September 2023
+Contact:	Can Guo <quic_cang@quicinc.com>
+Description:	This file shows the PA power mode of UFS.
+
+		The file is read only.
+
+What:		/sys/bus/platform/drivers/ufshcd/*/power_info/rate
+What:		/sys/bus/platform/devices/*.ufs/power_info/rate
+Date:		September 2023
+Contact:	Can Guo <quic_cang@quicinc.com>
+Description:	This file shows the speed rate of UFS link.
+
+		The file is read only.
+
+What:		/sys/bus/platform/drivers/ufshcd/*/power_info/gear
+What:		/sys/bus/platform/devices/*.ufs/power_info/gear
+Date:		September 2023
+Contact:	Can Guo <quic_cang@quicinc.com>
+Description:	This file shows the gear of UFS link.
+
+		The file is read only.
+
+What:		/sys/bus/platform/drivers/ufshcd/*/power_info/dev_pm
+What:		/sys/bus/platform/devices/*.ufs/power_info/dev_pm
+Date:		September 2023
+Contact:	Can Guo <quic_cang@quicinc.com>
+Description:	This file shows the UFS device power mode.
+
+		The file is read only.
+
+What:		/sys/bus/platform/drivers/ufshcd/*/power_info/link_state
+What:		/sys/bus/platform/devices/*.ufs/power_info/link_state
+Date:		September 2023
+Contact:	Can Guo <quic_cang@quicinc.com>
+Description:	This file shows the state of UFS link.
+
+		The file is read only.
+
 What:		/sys/bus/platform/drivers/ufshcd/*/device_descriptor/wb_presv_us_en
 What:		/sys/bus/platform/devices/*.ufs/device_descriptor/wb_presv_us_en
 Date:		June 2020
diff --git a/drivers/ufs/core/ufs-sysfs.c b/drivers/ufs/core/ufs-sysfs.c
index c95906443d5f..05b10ca90b50 100644
--- a/drivers/ufs/core/ufs-sysfs.c
+++ b/drivers/ufs/core/ufs-sysfs.c
@@ -7,9 +7,56 @@
 #include <asm/unaligned.h>
 
 #include <ufs/ufs.h>
+#include <ufs/unipro.h>
 #include "ufs-sysfs.h"
 #include "ufshcd-priv.h"
 
+static const char *ufs_pa_pwr_mode_to_string(enum ufs_pa_pwr_mode mode)
+{
+	switch (mode) {
+	case FAST_MODE:		return "FAST_MODE";
+	case SLOW_MODE:		return "SLOW_MODE";
+	case FASTAUTO_MODE:	return "FASTAUTO_MODE";
+	case SLOWAUTO_MODE:	return "SLOWAUTO_MODE";
+	default:		return "UNKNOWN";
+	}
+}
+
+static const char *ufs_hs_gear_rate_to_string(enum ufs_hs_gear_rate rate)
+{
+	switch (rate) {
+	case PA_HS_MODE_A:	return "HS_RATE_A";
+	case PA_HS_MODE_B:	return "HS_RATE_B";
+	default:		return "UNKNOWN";
+	}
+}
+
+static const char *ufs_pwm_gear_to_string(enum ufs_pwm_gear_tag gear)
+{
+	switch (gear) {
+	case UFS_PWM_G1:	return "PWM_GEAR1";
+	case UFS_PWM_G2:	return "PWM_GEAR2";
+	case UFS_PWM_G3:	return "PWM_GEAR3";
+	case UFS_PWM_G4:	return "PWM_GEAR4";
+	case UFS_PWM_G5:	return "PWM_GEAR5";
+	case UFS_PWM_G6:	return "PWM_GEAR6";
+	case UFS_PWM_G7:	return "PWM_GEAR7";
+	default:		return "UNKNOWN";
+	}
+}
+
+static const char *ufs_hs_gear_to_string(enum ufs_hs_gear_tag gear)
+{
+	switch (gear) {
+	case UFS_HS_G1:	return "HS_GEAR1";
+	case UFS_HS_G2:	return "HS_GEAR2";
+	case UFS_HS_G3:	return "HS_GEAR3";
+	case UFS_HS_G4:	return "HS_GEAR4";
+	case UFS_HS_G5:	return "HS_GEAR5";
+	default:	return "UNKNOWN";
+	}
+}
+
 static const char *ufshcd_uic_link_state_to_string(
 			enum uic_link_state state)
 {
@@ -628,6 +675,78 @@ static const struct attribute_group ufs_sysfs_monitor_group = {
 	.attrs = ufs_sysfs_monitor_attrs,
 };
 
+static ssize_t lane_show(struct device *dev, struct device_attribute *attr,
+			 char *buf)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "%u\n", hba->pwr_info.lane_rx);
+}
+
+static ssize_t mode_show(struct device *dev, struct device_attribute *attr,
+			 char *buf)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "%s\n", ufs_pa_pwr_mode_to_string(hba->pwr_info.pwr_rx));
+}
+
+static ssize_t rate_show(struct device *dev, struct device_attribute *attr,
+			 char *buf)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "%s\n", ufs_hs_gear_rate_to_string(hba->pwr_info.hs_rate));
+}
+
+static ssize_t gear_show(struct device *dev, struct device_attribute *attr,
+			 char *buf)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "%s\n", hba->pwr_info.hs_rate ?
+			  ufs_hs_gear_to_string(hba->pwr_info.gear_rx) :
+			  ufs_pwm_gear_to_string(hba->pwr_info.gear_rx));
+}
+
+static ssize_t dev_pm_show(struct device *dev, struct device_attribute *attr,
+			   char *buf)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "%s\n", ufshcd_ufs_dev_pwr_mode_to_string(hba->curr_dev_pwr_mode));
+}
+
+static ssize_t link_state_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "%s\n", ufshcd_uic_link_state_to_string(hba->uic_link_state));
+}
+
+static DEVICE_ATTR_RO(lane);
+static DEVICE_ATTR_RO(mode);
+static DEVICE_ATTR_RO(rate);
+static DEVICE_ATTR_RO(gear);
+static DEVICE_ATTR_RO(dev_pm);
+static DEVICE_ATTR_RO(link_state);
+
+static struct attribute *ufs_power_info_attrs[] = {
+	&dev_attr_lane.attr,
+	&dev_attr_mode.attr,
+	&dev_attr_rate.attr,
+	&dev_attr_gear.attr,
+	&dev_attr_dev_pm.attr,
+	&dev_attr_link_state.attr,
+	NULL
+};
+
+static const struct attribute_group ufs_sysfs_power_info_group = {
+	.name = "power_info",
+	.attrs = ufs_power_info_attrs,
+};
+
 static ssize_t ufs_sysfs_read_desc_param(struct ufs_hba *hba,
 				  enum desc_idn desc_id,
 				  u8 desc_index,
@@ -1233,6 +1352,7 @@ static const struct attribute_group *ufs_sysfs_groups[] = {
 	&ufs_sysfs_default_group,
 	&ufs_sysfs_capabilities_group,
 	&ufs_sysfs_monitor_group,
+	&ufs_sysfs_power_info_group,
 	&ufs_sysfs_device_descriptor_group,
 	&ufs_sysfs_interconnect_descriptor_group,
 	&ufs_sysfs_geometry_descriptor_group,
diff --git a/include/ufs/unipro.h b/include/ufs/unipro.h
index 256eb3a43f54..360e1245fb40 100644
--- a/include/ufs/unipro.h
+++ b/include/ufs/unipro.h
@@ -193,7 +193,7 @@
 #define DME_LocalAFC0ReqTimeOutVal		0xD043
 
 /* PA power modes */
-enum {
+enum ufs_pa_pwr_mode {
 	FAST_MODE	= 1,
 	SLOW_MODE	= 2,
 	FASTAUTO_MODE	= 4,
@@ -205,7 +205,7 @@ enum {
 #define PWRMODE_RX_OFFSET	4
 
 /* PA TX/RX Frequency Series */
-enum {
+enum ufs_hs_gear_rate {
 	PA_HS_MODE_A	= 1,
 	PA_HS_MODE_B	= 2,
 };
-- 
cgit v1.2.3


From 4aea6a6d61cd6e3df9ed98345638abad1b1e5276 Mon Sep 17 00:00:00 2001
From: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Date: Thu, 30 Mar 2023 15:05:38 -0700
Subject: net/mlx5: Query maximum frequency adjustment of the PTP hardware
 clock

Some mlx5 devices do not support the default advertised maximum frequency
adjustment value for the PTP hardware clock that is set by the driver.
These devices need to be queried when initializing the clock functionality
in order to get the maximum supported frequency adjustment value. This
value can be greater than the minimum supported frequency adjustment across
mlx5 devices (50 million ppb).

Signed-off-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/lib/clock.c    | 22 ++++++++++++++++++++++
 include/linux/mlx5/mlx5_ifc.h                      |  5 ++++-
 2 files changed, 26 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index 1daa4b019513..cac60a841e1d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -1000,6 +1000,25 @@ static void mlx5_init_clock_info(struct mlx5_core_dev *mdev)
 	info->frac = timer->tc.frac;
 }
 
+static void mlx5_init_timer_max_freq_adjustment(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_clock *clock = &mdev->clock;
+	u32 out[MLX5_ST_SZ_DW(mtutc_reg)] = {};
+	u32 in[MLX5_ST_SZ_DW(mtutc_reg)] = {};
+	u8 log_max_freq_adjustment = 0;
+	int err;
+
+	err = mlx5_core_access_reg(mdev, in, sizeof(in), out, sizeof(out),
+				   MLX5_REG_MTUTC, 0, 0);
+	if (!err)
+		log_max_freq_adjustment =
+			MLX5_GET(mtutc_reg, out, log_max_freq_adjustment);
+
+	if (log_max_freq_adjustment)
+		clock->ptp_info.max_adj =
+			min(S32_MAX, 1 << log_max_freq_adjustment);
+}
+
 static void mlx5_init_timer_clock(struct mlx5_core_dev *mdev)
 {
 	struct mlx5_clock *clock = &mdev->clock;
@@ -1007,6 +1026,9 @@ static void mlx5_init_timer_clock(struct mlx5_core_dev *mdev)
 	/* Configure the PHC */
 	clock->ptp_info = mlx5_ptp_clock_info;
 
+	if (MLX5_CAP_MCAM_REG(mdev, mtutc))
+		mlx5_init_timer_max_freq_adjustment(mdev);
+
 	mlx5_timecounter_init(mdev);
 	mlx5_init_clock_info(mdev);
 	mlx5_init_overflow_period(clock);
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 6f3631425f38..ce2e71cd6d2a 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -10103,7 +10103,10 @@ enum {
 struct mlx5_ifc_mtutc_reg_bits {
 	u8         reserved_at_0[0x5];
 	u8         freq_adj_units[0x3];
-	u8         reserved_at_8[0x14];
+	u8         reserved_at_8[0x3];
+	u8         log_max_freq_adjustment[0x5];
+
+	u8         reserved_at_10[0xc];
 	u8         operation[0x4];
 
 	u8         freq_adjustment[0x20];
-- 
cgit v1.2.3


From 67420501e8681ae18f9f0ea0a69cd2f432100e70 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Sat, 11 Nov 2023 17:05:57 -0800
Subject: bpf: generalize reg_set_min_max() to handle non-const register
 comparisons

Generalize bounds adjustment logic of reg_set_min_max() to handle not
just register vs constant case, but in general any register vs any
register cases. For most of the operations it's trivial extension based
on range vs range comparison logic, we just need to properly pick
min/max of a range to compare against min/max of the other range.

For BPF_JSET we keep the original capabilities, just make sure JSET is
integrated in the common framework. This is manifested in the
internal-only BPF_JSET + BPF_X "opcode" to allow for simpler and more
uniform rev_opcode() handling. See the code for details. This allows to
reuse the same code exactly both for TRUE and FALSE branches without
explicitly handling both conditions with custom code.

Note also that now we don't need a special handling of BPF_JEQ/BPF_JNE
case none of the registers are constants. This is now just a normal
generic case handled by reg_set_min_max().

To make tnum handling cleaner, tnum_with_subreg() helper is added, as
that's a common operator when dealing with 32-bit subregister bounds.
This keeps the overall logic much less noisy when it comes to tnums.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Shung-Hsi Yu <shung-hsi.yu@suse.com>
Link: https://lore.kernel.org/r/20231112010609.848406-2-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/tnum.h  |   4 +
 kernel/bpf/tnum.c     |   7 +-
 kernel/bpf/verifier.c | 314 ++++++++++++++++++++++----------------------------
 3 files changed, 146 insertions(+), 179 deletions(-)

(limited to 'include')

diff --git a/include/linux/tnum.h b/include/linux/tnum.h
index 1c3948a1d6ad..3c13240077b8 100644
--- a/include/linux/tnum.h
+++ b/include/linux/tnum.h
@@ -106,6 +106,10 @@ int tnum_sbin(char *str, size_t size, struct tnum a);
 struct tnum tnum_subreg(struct tnum a);
 /* Returns the tnum with the lower 32-bit subreg cleared */
 struct tnum tnum_clear_subreg(struct tnum a);
+/* Returns the tnum with the lower 32-bit subreg in *reg* set to the lower
+ * 32-bit subreg in *subreg*
+ */
+struct tnum tnum_with_subreg(struct tnum reg, struct tnum subreg);
 /* Returns the tnum with the lower 32-bit subreg set to value */
 struct tnum tnum_const_subreg(struct tnum a, u32 value);
 /* Returns true if 32-bit subreg @a is a known constant*/
diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c
index 3d7127f439a1..f4c91c9b27d7 100644
--- a/kernel/bpf/tnum.c
+++ b/kernel/bpf/tnum.c
@@ -208,7 +208,12 @@ struct tnum tnum_clear_subreg(struct tnum a)
 	return tnum_lshift(tnum_rshift(a, 32), 32);
 }
 
+struct tnum tnum_with_subreg(struct tnum reg, struct tnum subreg)
+{
+	return tnum_or(tnum_clear_subreg(reg), tnum_subreg(subreg));
+}
+
 struct tnum tnum_const_subreg(struct tnum a, u32 value)
 {
-	return tnum_or(tnum_clear_subreg(a), tnum_const(value));
+	return tnum_with_subreg(a, tnum_const(value));
 }
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 9ae6eae13471..39ce141c55d3 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -14453,218 +14453,186 @@ static int is_branch_taken(struct bpf_reg_state *reg1, struct bpf_reg_state *reg
 	return is_scalar_branch_taken(reg1, reg2, opcode, is_jmp32);
 }
 
-/* Adjusts the register min/max values in the case that the dst_reg and
- * src_reg are both SCALAR_VALUE registers (or we are simply doing a BPF_K
- * check, in which case we havea fake SCALAR_VALUE representing insn->imm).
- * Technically we can do similar adjustments for pointers to the same object,
- * but we don't support that right now.
+/* Opcode that corresponds to a *false* branch condition.
+ * E.g., if r1 < r2, then reverse (false) condition is r1 >= r2
  */
-static void reg_set_min_max(struct bpf_reg_state *true_reg1,
-			    struct bpf_reg_state *true_reg2,
-			    struct bpf_reg_state *false_reg1,
-			    struct bpf_reg_state *false_reg2,
-			    u8 opcode, bool is_jmp32)
+static u8 rev_opcode(u8 opcode)
 {
-	struct tnum false_32off, false_64off;
-	struct tnum true_32off, true_64off;
-	u64 uval;
-	u32 uval32;
-	s64 sval;
-	s32 sval32;
-
-	/* If either register is a pointer, we can't learn anything about its
-	 * variable offset from the compare (unless they were a pointer into
-	 * the same object, but we don't bother with that).
+	switch (opcode) {
+	case BPF_JEQ:		return BPF_JNE;
+	case BPF_JNE:		return BPF_JEQ;
+	/* JSET doesn't have it's reverse opcode in BPF, so add
+	 * BPF_X flag to denote the reverse of that operation
 	 */
-	if (false_reg1->type != SCALAR_VALUE || false_reg2->type != SCALAR_VALUE)
-		return;
-
-	/* we expect right-hand registers (src ones) to be constants, for now */
-	if (!is_reg_const(false_reg2, is_jmp32)) {
-		opcode = flip_opcode(opcode);
-		swap(true_reg1, true_reg2);
-		swap(false_reg1, false_reg2);
+	case BPF_JSET:		return BPF_JSET | BPF_X;
+	case BPF_JSET | BPF_X:	return BPF_JSET;
+	case BPF_JGE:		return BPF_JLT;
+	case BPF_JGT:		return BPF_JLE;
+	case BPF_JLE:		return BPF_JGT;
+	case BPF_JLT:		return BPF_JGE;
+	case BPF_JSGE:		return BPF_JSLT;
+	case BPF_JSGT:		return BPF_JSLE;
+	case BPF_JSLE:		return BPF_JSGT;
+	case BPF_JSLT:		return BPF_JSGE;
+	default:		return 0;
 	}
-	if (!is_reg_const(false_reg2, is_jmp32))
-		return;
+}
 
-	false_32off = tnum_subreg(false_reg1->var_off);
-	false_64off = false_reg1->var_off;
-	true_32off = tnum_subreg(true_reg1->var_off);
-	true_64off = true_reg1->var_off;
-	uval = false_reg2->var_off.value;
-	uval32 = (u32)tnum_subreg(false_reg2->var_off).value;
-	sval = (s64)uval;
-	sval32 = (s32)uval32;
+/* Refine range knowledge for <reg1> <op> <reg>2 conditional operation. */
+static void regs_refine_cond_op(struct bpf_reg_state *reg1, struct bpf_reg_state *reg2,
+				u8 opcode, bool is_jmp32)
+{
+	struct tnum t;
+	u64 val;
 
+again:
 	switch (opcode) {
-	/* JEQ/JNE comparison doesn't change the register equivalence.
-	 *
-	 * r1 = r2;
-	 * if (r1 == 42) goto label;
-	 * ...
-	 * label: // here both r1 and r2 are known to be 42.
-	 *
-	 * Hence when marking register as known preserve it's ID.
-	 */
 	case BPF_JEQ:
 		if (is_jmp32) {
-			__mark_reg32_known(true_reg1, uval32);
-			true_32off = tnum_subreg(true_reg1->var_off);
+			reg1->u32_min_value = max(reg1->u32_min_value, reg2->u32_min_value);
+			reg1->u32_max_value = min(reg1->u32_max_value, reg2->u32_max_value);
+			reg1->s32_min_value = max(reg1->s32_min_value, reg2->s32_min_value);
+			reg1->s32_max_value = min(reg1->s32_max_value, reg2->s32_max_value);
+			reg2->u32_min_value = reg1->u32_min_value;
+			reg2->u32_max_value = reg1->u32_max_value;
+			reg2->s32_min_value = reg1->s32_min_value;
+			reg2->s32_max_value = reg1->s32_max_value;
+
+			t = tnum_intersect(tnum_subreg(reg1->var_off), tnum_subreg(reg2->var_off));
+			reg1->var_off = tnum_with_subreg(reg1->var_off, t);
+			reg2->var_off = tnum_with_subreg(reg2->var_off, t);
 		} else {
-			___mark_reg_known(true_reg1, uval);
-			true_64off = true_reg1->var_off;
+			reg1->umin_value = max(reg1->umin_value, reg2->umin_value);
+			reg1->umax_value = min(reg1->umax_value, reg2->umax_value);
+			reg1->smin_value = max(reg1->smin_value, reg2->smin_value);
+			reg1->smax_value = min(reg1->smax_value, reg2->smax_value);
+			reg2->umin_value = reg1->umin_value;
+			reg2->umax_value = reg1->umax_value;
+			reg2->smin_value = reg1->smin_value;
+			reg2->smax_value = reg1->smax_value;
+
+			reg1->var_off = tnum_intersect(reg1->var_off, reg2->var_off);
+			reg2->var_off = reg1->var_off;
 		}
 		break;
 	case BPF_JNE:
-		if (is_jmp32) {
-			__mark_reg32_known(false_reg1, uval32);
-			false_32off = tnum_subreg(false_reg1->var_off);
-		} else {
-			___mark_reg_known(false_reg1, uval);
-			false_64off = false_reg1->var_off;
-		}
+		/* we don't derive any new information for inequality yet */
 		break;
 	case BPF_JSET:
+		if (!is_reg_const(reg2, is_jmp32))
+			swap(reg1, reg2);
+		if (!is_reg_const(reg2, is_jmp32))
+			break;
+		val = reg_const_value(reg2, is_jmp32);
+		/* BPF_JSET (i.e., TRUE branch, *not* BPF_JSET | BPF_X)
+		 * requires single bit to learn something useful. E.g., if we
+		 * know that `r1 & 0x3` is true, then which bits (0, 1, or both)
+		 * are actually set? We can learn something definite only if
+		 * it's a single-bit value to begin with.
+		 *
+		 * BPF_JSET | BPF_X (i.e., negation of BPF_JSET) doesn't have
+		 * this restriction. I.e., !(r1 & 0x3) means neither bit 0 nor
+		 * bit 1 is set, which we can readily use in adjustments.
+		 */
+		if (!is_power_of_2(val))
+			break;
 		if (is_jmp32) {
-			false_32off = tnum_and(false_32off, tnum_const(~uval32));
-			if (is_power_of_2(uval32))
-				true_32off = tnum_or(true_32off,
-						     tnum_const(uval32));
+			t = tnum_or(tnum_subreg(reg1->var_off), tnum_const(val));
+			reg1->var_off = tnum_with_subreg(reg1->var_off, t);
 		} else {
-			false_64off = tnum_and(false_64off, tnum_const(~uval));
-			if (is_power_of_2(uval))
-				true_64off = tnum_or(true_64off,
-						     tnum_const(uval));
+			reg1->var_off = tnum_or(reg1->var_off, tnum_const(val));
 		}
 		break;
-	case BPF_JGE:
-	case BPF_JGT:
-	{
+	case BPF_JSET | BPF_X: /* reverse of BPF_JSET, see rev_opcode() */
+		if (!is_reg_const(reg2, is_jmp32))
+			swap(reg1, reg2);
+		if (!is_reg_const(reg2, is_jmp32))
+			break;
+		val = reg_const_value(reg2, is_jmp32);
 		if (is_jmp32) {
-			u32 false_umax = opcode == BPF_JGT ? uval32  : uval32 - 1;
-			u32 true_umin = opcode == BPF_JGT ? uval32 + 1 : uval32;
-
-			false_reg1->u32_max_value = min(false_reg1->u32_max_value,
-						       false_umax);
-			true_reg1->u32_min_value = max(true_reg1->u32_min_value,
-						      true_umin);
+			t = tnum_and(tnum_subreg(reg1->var_off), tnum_const(~val));
+			reg1->var_off = tnum_with_subreg(reg1->var_off, t);
 		} else {
-			u64 false_umax = opcode == BPF_JGT ? uval    : uval - 1;
-			u64 true_umin = opcode == BPF_JGT ? uval + 1 : uval;
-
-			false_reg1->umax_value = min(false_reg1->umax_value, false_umax);
-			true_reg1->umin_value = max(true_reg1->umin_value, true_umin);
+			reg1->var_off = tnum_and(reg1->var_off, tnum_const(~val));
 		}
 		break;
-	}
-	case BPF_JSGE:
-	case BPF_JSGT:
-	{
+	case BPF_JLE:
 		if (is_jmp32) {
-			s32 false_smax = opcode == BPF_JSGT ? sval32    : sval32 - 1;
-			s32 true_smin = opcode == BPF_JSGT ? sval32 + 1 : sval32;
-
-			false_reg1->s32_max_value = min(false_reg1->s32_max_value, false_smax);
-			true_reg1->s32_min_value = max(true_reg1->s32_min_value, true_smin);
+			reg1->u32_max_value = min(reg1->u32_max_value, reg2->u32_max_value);
+			reg2->u32_min_value = max(reg1->u32_min_value, reg2->u32_min_value);
 		} else {
-			s64 false_smax = opcode == BPF_JSGT ? sval    : sval - 1;
-			s64 true_smin = opcode == BPF_JSGT ? sval + 1 : sval;
-
-			false_reg1->smax_value = min(false_reg1->smax_value, false_smax);
-			true_reg1->smin_value = max(true_reg1->smin_value, true_smin);
+			reg1->umax_value = min(reg1->umax_value, reg2->umax_value);
+			reg2->umin_value = max(reg1->umin_value, reg2->umin_value);
 		}
 		break;
-	}
-	case BPF_JLE:
 	case BPF_JLT:
-	{
 		if (is_jmp32) {
-			u32 false_umin = opcode == BPF_JLT ? uval32  : uval32 + 1;
-			u32 true_umax = opcode == BPF_JLT ? uval32 - 1 : uval32;
-
-			false_reg1->u32_min_value = max(false_reg1->u32_min_value,
-						       false_umin);
-			true_reg1->u32_max_value = min(true_reg1->u32_max_value,
-						      true_umax);
+			reg1->u32_max_value = min(reg1->u32_max_value, reg2->u32_max_value - 1);
+			reg2->u32_min_value = max(reg1->u32_min_value + 1, reg2->u32_min_value);
 		} else {
-			u64 false_umin = opcode == BPF_JLT ? uval    : uval + 1;
-			u64 true_umax = opcode == BPF_JLT ? uval - 1 : uval;
-
-			false_reg1->umin_value = max(false_reg1->umin_value, false_umin);
-			true_reg1->umax_value = min(true_reg1->umax_value, true_umax);
+			reg1->umax_value = min(reg1->umax_value, reg2->umax_value - 1);
+			reg2->umin_value = max(reg1->umin_value + 1, reg2->umin_value);
 		}
 		break;
-	}
 	case BPF_JSLE:
+		if (is_jmp32) {
+			reg1->s32_max_value = min(reg1->s32_max_value, reg2->s32_max_value);
+			reg2->s32_min_value = max(reg1->s32_min_value, reg2->s32_min_value);
+		} else {
+			reg1->smax_value = min(reg1->smax_value, reg2->smax_value);
+			reg2->smin_value = max(reg1->smin_value, reg2->smin_value);
+		}
+		break;
 	case BPF_JSLT:
-	{
 		if (is_jmp32) {
-			s32 false_smin = opcode == BPF_JSLT ? sval32    : sval32 + 1;
-			s32 true_smax = opcode == BPF_JSLT ? sval32 - 1 : sval32;
-
-			false_reg1->s32_min_value = max(false_reg1->s32_min_value, false_smin);
-			true_reg1->s32_max_value = min(true_reg1->s32_max_value, true_smax);
+			reg1->s32_max_value = min(reg1->s32_max_value, reg2->s32_max_value - 1);
+			reg2->s32_min_value = max(reg1->s32_min_value + 1, reg2->s32_min_value);
 		} else {
-			s64 false_smin = opcode == BPF_JSLT ? sval    : sval + 1;
-			s64 true_smax = opcode == BPF_JSLT ? sval - 1 : sval;
-
-			false_reg1->smin_value = max(false_reg1->smin_value, false_smin);
-			true_reg1->smax_value = min(true_reg1->smax_value, true_smax);
+			reg1->smax_value = min(reg1->smax_value, reg2->smax_value - 1);
+			reg2->smin_value = max(reg1->smin_value + 1, reg2->smin_value);
 		}
 		break;
-	}
+	case BPF_JGE:
+	case BPF_JGT:
+	case BPF_JSGE:
+	case BPF_JSGT:
+		/* just reuse LE/LT logic above */
+		opcode = flip_opcode(opcode);
+		swap(reg1, reg2);
+		goto again;
 	default:
 		return;
 	}
-
-	if (is_jmp32) {
-		false_reg1->var_off = tnum_or(tnum_clear_subreg(false_64off),
-					     tnum_subreg(false_32off));
-		true_reg1->var_off = tnum_or(tnum_clear_subreg(true_64off),
-					    tnum_subreg(true_32off));
-		reg_bounds_sync(false_reg1);
-		reg_bounds_sync(true_reg1);
-	} else {
-		false_reg1->var_off = false_64off;
-		true_reg1->var_off = true_64off;
-		reg_bounds_sync(false_reg1);
-		reg_bounds_sync(true_reg1);
-	}
-}
-
-/* Regs are known to be equal, so intersect their min/max/var_off */
-static void __reg_combine_min_max(struct bpf_reg_state *src_reg,
-				  struct bpf_reg_state *dst_reg)
-{
-	src_reg->umin_value = dst_reg->umin_value = max(src_reg->umin_value,
-							dst_reg->umin_value);
-	src_reg->umax_value = dst_reg->umax_value = min(src_reg->umax_value,
-							dst_reg->umax_value);
-	src_reg->smin_value = dst_reg->smin_value = max(src_reg->smin_value,
-							dst_reg->smin_value);
-	src_reg->smax_value = dst_reg->smax_value = min(src_reg->smax_value,
-							dst_reg->smax_value);
-	src_reg->var_off = dst_reg->var_off = tnum_intersect(src_reg->var_off,
-							     dst_reg->var_off);
-	reg_bounds_sync(src_reg);
-	reg_bounds_sync(dst_reg);
 }
 
-static void reg_combine_min_max(struct bpf_reg_state *true_src,
-				struct bpf_reg_state *true_dst,
-				struct bpf_reg_state *false_src,
-				struct bpf_reg_state *false_dst,
-				u8 opcode)
+/* Adjusts the register min/max values in the case that the dst_reg and
+ * src_reg are both SCALAR_VALUE registers (or we are simply doing a BPF_K
+ * check, in which case we havea fake SCALAR_VALUE representing insn->imm).
+ * Technically we can do similar adjustments for pointers to the same object,
+ * but we don't support that right now.
+ */
+static void reg_set_min_max(struct bpf_reg_state *true_reg1,
+			    struct bpf_reg_state *true_reg2,
+			    struct bpf_reg_state *false_reg1,
+			    struct bpf_reg_state *false_reg2,
+			    u8 opcode, bool is_jmp32)
 {
-	switch (opcode) {
-	case BPF_JEQ:
-		__reg_combine_min_max(true_src, true_dst);
-		break;
-	case BPF_JNE:
-		__reg_combine_min_max(false_src, false_dst);
-		break;
-	}
+	/* If either register is a pointer, we can't learn anything about its
+	 * variable offset from the compare (unless they were a pointer into
+	 * the same object, but we don't bother with that).
+	 */
+	if (false_reg1->type != SCALAR_VALUE || false_reg2->type != SCALAR_VALUE)
+		return;
+
+	/* fallthrough (FALSE) branch */
+	regs_refine_cond_op(false_reg1, false_reg2, rev_opcode(opcode), is_jmp32);
+	reg_bounds_sync(false_reg1);
+	reg_bounds_sync(false_reg2);
+
+	/* jump (TRUE) branch */
+	regs_refine_cond_op(true_reg1, true_reg2, opcode, is_jmp32);
+	reg_bounds_sync(true_reg1);
+	reg_bounds_sync(true_reg2);
 }
 
 static void mark_ptr_or_null_reg(struct bpf_func_state *state,
@@ -14961,22 +14929,12 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 		reg_set_min_max(&other_branch_regs[insn->dst_reg],
 				&other_branch_regs[insn->src_reg],
 				dst_reg, src_reg, opcode, is_jmp32);
-
-		if (dst_reg->type == SCALAR_VALUE &&
-		    src_reg->type == SCALAR_VALUE &&
-		    !is_jmp32 && (opcode == BPF_JEQ || opcode == BPF_JNE)) {
-			/* Comparing for equality, we can combine knowledge */
-			reg_combine_min_max(&other_branch_regs[insn->src_reg],
-					    &other_branch_regs[insn->dst_reg],
-					    src_reg, dst_reg, opcode);
-		}
 	} else /* BPF_SRC(insn->code) == BPF_K */ {
 		reg_set_min_max(&other_branch_regs[insn->dst_reg],
 				src_reg /* fake one */,
 				dst_reg, src_reg /* same fake one */,
 				opcode, is_jmp32);
 	}
-
 	if (BPF_SRC(insn->code) == BPF_X &&
 	    src_reg->type == SCALAR_VALUE && src_reg->id &&
 	    !WARN_ON_ONCE(src_reg->id != other_branch_regs[insn->src_reg].id)) {
-- 
cgit v1.2.3


From 5f99f312bd3bedb3b266b0d26376a8c500cdc97f Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Sat, 11 Nov 2023 17:06:00 -0800
Subject: bpf: add register bounds sanity checks and sanitization

Add simple sanity checks that validate well-formed ranges (min <= max)
across u64, s64, u32, and s32 ranges. Also for cases when the value is
constant (either 64-bit or 32-bit), we validate that ranges and tnums
are in agreement.

These bounds checks are performed at the end of BPF_ALU/BPF_ALU64
operations, on conditional jumps, and for LDX instructions (where subreg
zero/sign extension is probably the most important to check). This
covers most of the interesting cases.

Also, we validate the sanity of the return register when manually
adjusting it for some special helpers.

By default, sanity violation will trigger a warning in verifier log and
resetting register bounds to "unbounded" ones. But to aid development
and debugging, BPF_F_TEST_SANITY_STRICT flag is added, which will
trigger hard failure of verification with -EFAULT on register bounds
violations. This allows selftests to catch such issues. veristat will
also gain a CLI option to enable this behavior.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Shung-Hsi Yu <shung-hsi.yu@suse.com>
Link: https://lore.kernel.org/r/20231112010609.848406-5-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf_verifier.h   |   1 +
 include/uapi/linux/bpf.h       |   3 ++
 kernel/bpf/syscall.c           |   3 +-
 kernel/bpf/verifier.c          | 117 ++++++++++++++++++++++++++++++++---------
 tools/include/uapi/linux/bpf.h |   3 ++
 5 files changed, 101 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 24213a99cc79..402b6bc44a1b 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -602,6 +602,7 @@ struct bpf_verifier_env {
 	int stack_size;			/* number of states to be processed */
 	bool strict_alignment;		/* perform strict pointer alignment checks */
 	bool test_state_freq;		/* test verifier with different pruning frequency */
+	bool test_sanity_strict;	/* fail verification on sanity violations */
 	struct bpf_verifier_state *cur_state; /* current verifier state */
 	struct bpf_verifier_state_list **explored_states; /* search pruning optimization */
 	struct bpf_verifier_state_list *free_list;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 7cf8bcf9f6a2..8a5855fcee69 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1200,6 +1200,9 @@ enum bpf_perf_event_type {
  */
 #define BPF_F_XDP_DEV_BOUND_ONLY	(1U << 6)
 
+/* The verifier internal test flag. Behavior is undefined */
+#define BPF_F_TEST_SANITY_STRICT	(1U << 7)
+
 /* link_create.kprobe_multi.flags used in LINK_CREATE command for
  * BPF_TRACE_KPROBE_MULTI attach type to create return probe.
  */
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 0ed286b8a0f0..f266e03ba342 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2573,7 +2573,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
 				 BPF_F_SLEEPABLE |
 				 BPF_F_TEST_RND_HI32 |
 				 BPF_F_XDP_HAS_FRAGS |
-				 BPF_F_XDP_DEV_BOUND_ONLY))
+				 BPF_F_XDP_DEV_BOUND_ONLY |
+				 BPF_F_TEST_SANITY_STRICT))
 		return -EINVAL;
 
 	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) &&
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 65570eedfe88..e7edacf86e0f 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2615,6 +2615,56 @@ static void reg_bounds_sync(struct bpf_reg_state *reg)
 	__update_reg_bounds(reg);
 }
 
+static int reg_bounds_sanity_check(struct bpf_verifier_env *env,
+				   struct bpf_reg_state *reg, const char *ctx)
+{
+	const char *msg;
+
+	if (reg->umin_value > reg->umax_value ||
+	    reg->smin_value > reg->smax_value ||
+	    reg->u32_min_value > reg->u32_max_value ||
+	    reg->s32_min_value > reg->s32_max_value) {
+		    msg = "range bounds violation";
+		    goto out;
+	}
+
+	if (tnum_is_const(reg->var_off)) {
+		u64 uval = reg->var_off.value;
+		s64 sval = (s64)uval;
+
+		if (reg->umin_value != uval || reg->umax_value != uval ||
+		    reg->smin_value != sval || reg->smax_value != sval) {
+			msg = "const tnum out of sync with range bounds";
+			goto out;
+		}
+	}
+
+	if (tnum_subreg_is_const(reg->var_off)) {
+		u32 uval32 = tnum_subreg(reg->var_off).value;
+		s32 sval32 = (s32)uval32;
+
+		if (reg->u32_min_value != uval32 || reg->u32_max_value != uval32 ||
+		    reg->s32_min_value != sval32 || reg->s32_max_value != sval32) {
+			msg = "const subreg tnum out of sync with range bounds";
+			goto out;
+		}
+	}
+
+	return 0;
+out:
+	verbose(env, "REG SANITY VIOLATION (%s): %s u64=[%#llx, %#llx] "
+		"s64=[%#llx, %#llx] u32=[%#x, %#x] s32=[%#x, %#x] var_off=(%#llx, %#llx)\n",
+		ctx, msg, reg->umin_value, reg->umax_value,
+		reg->smin_value, reg->smax_value,
+		reg->u32_min_value, reg->u32_max_value,
+		reg->s32_min_value, reg->s32_max_value,
+		reg->var_off.value, reg->var_off.mask);
+	if (env->test_sanity_strict)
+		return -EFAULT;
+	__mark_reg_unbounded(reg);
+	return 0;
+}
+
 static bool __reg32_bound_s64(s32 a)
 {
 	return a >= 0 && a <= S32_MAX;
@@ -9982,14 +10032,15 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 	return 0;
 }
 
-static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type,
-				   int func_id,
-				   struct bpf_call_arg_meta *meta)
+static int do_refine_retval_range(struct bpf_verifier_env *env,
+				  struct bpf_reg_state *regs, int ret_type,
+				  int func_id,
+				  struct bpf_call_arg_meta *meta)
 {
 	struct bpf_reg_state *ret_reg = &regs[BPF_REG_0];
 
 	if (ret_type != RET_INTEGER)
-		return;
+		return 0;
 
 	switch (func_id) {
 	case BPF_FUNC_get_stack:
@@ -10015,6 +10066,8 @@ static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type,
 		reg_bounds_sync(ret_reg);
 		break;
 	}
+
+	return reg_bounds_sanity_check(env, ret_reg, "retval");
 }
 
 static int
@@ -10666,7 +10719,9 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		regs[BPF_REG_0].ref_obj_id = id;
 	}
 
-	do_refine_retval_range(regs, fn->ret_type, func_id, &meta);
+	err = do_refine_retval_range(env, regs, fn->ret_type, func_id, &meta);
+	if (err)
+		return err;
 
 	err = check_map_func_compatibility(env, meta.map_ptr, func_id);
 	if (err)
@@ -14166,13 +14221,12 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 
 		/* check dest operand */
 		err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK);
+		err = err ?: adjust_reg_min_max_vals(env, insn);
 		if (err)
 			return err;
-
-		return adjust_reg_min_max_vals(env, insn);
 	}
 
-	return 0;
+	return reg_bounds_sanity_check(env, &regs[insn->dst_reg], "alu");
 }
 
 static void find_good_pkt_pointers(struct bpf_verifier_state *vstate,
@@ -14653,18 +14707,21 @@ again:
  * Technically we can do similar adjustments for pointers to the same object,
  * but we don't support that right now.
  */
-static void reg_set_min_max(struct bpf_reg_state *true_reg1,
-			    struct bpf_reg_state *true_reg2,
-			    struct bpf_reg_state *false_reg1,
-			    struct bpf_reg_state *false_reg2,
-			    u8 opcode, bool is_jmp32)
+static int reg_set_min_max(struct bpf_verifier_env *env,
+			   struct bpf_reg_state *true_reg1,
+			   struct bpf_reg_state *true_reg2,
+			   struct bpf_reg_state *false_reg1,
+			   struct bpf_reg_state *false_reg2,
+			   u8 opcode, bool is_jmp32)
 {
+	int err;
+
 	/* If either register is a pointer, we can't learn anything about its
 	 * variable offset from the compare (unless they were a pointer into
 	 * the same object, but we don't bother with that).
 	 */
 	if (false_reg1->type != SCALAR_VALUE || false_reg2->type != SCALAR_VALUE)
-		return;
+		return 0;
 
 	/* fallthrough (FALSE) branch */
 	regs_refine_cond_op(false_reg1, false_reg2, rev_opcode(opcode), is_jmp32);
@@ -14675,6 +14732,12 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg1,
 	regs_refine_cond_op(true_reg1, true_reg2, opcode, is_jmp32);
 	reg_bounds_sync(true_reg1);
 	reg_bounds_sync(true_reg2);
+
+	err = reg_bounds_sanity_check(env, true_reg1, "true_reg1");
+	err = err ?: reg_bounds_sanity_check(env, true_reg2, "true_reg2");
+	err = err ?: reg_bounds_sanity_check(env, false_reg1, "false_reg1");
+	err = err ?: reg_bounds_sanity_check(env, false_reg2, "false_reg2");
+	return err;
 }
 
 static void mark_ptr_or_null_reg(struct bpf_func_state *state,
@@ -14968,15 +15031,20 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 	other_branch_regs = other_branch->frame[other_branch->curframe]->regs;
 
 	if (BPF_SRC(insn->code) == BPF_X) {
-		reg_set_min_max(&other_branch_regs[insn->dst_reg],
-				&other_branch_regs[insn->src_reg],
-				dst_reg, src_reg, opcode, is_jmp32);
+		err = reg_set_min_max(env,
+				      &other_branch_regs[insn->dst_reg],
+				      &other_branch_regs[insn->src_reg],
+				      dst_reg, src_reg, opcode, is_jmp32);
 	} else /* BPF_SRC(insn->code) == BPF_K */ {
-		reg_set_min_max(&other_branch_regs[insn->dst_reg],
-				src_reg /* fake one */,
-				dst_reg, src_reg /* same fake one */,
-				opcode, is_jmp32);
+		err = reg_set_min_max(env,
+				      &other_branch_regs[insn->dst_reg],
+				      src_reg /* fake one */,
+				      dst_reg, src_reg /* same fake one */,
+				      opcode, is_jmp32);
 	}
+	if (err)
+		return err;
+
 	if (BPF_SRC(insn->code) == BPF_X &&
 	    src_reg->type == SCALAR_VALUE && src_reg->id &&
 	    !WARN_ON_ONCE(src_reg->id != other_branch_regs[insn->src_reg].id)) {
@@ -17479,10 +17547,8 @@ static int do_check(struct bpf_verifier_env *env)
 					       insn->off, BPF_SIZE(insn->code),
 					       BPF_READ, insn->dst_reg, false,
 					       BPF_MODE(insn->code) == BPF_MEMSX);
-			if (err)
-				return err;
-
-			err = save_aux_ptr_type(env, src_reg_type, true);
+			err = err ?: save_aux_ptr_type(env, src_reg_type, true);
+			err = err ?: reg_bounds_sanity_check(env, &regs[insn->dst_reg], "ldx");
 			if (err)
 				return err;
 		} else if (class == BPF_STX) {
@@ -20769,6 +20835,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
 
 	if (is_priv)
 		env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ;
+	env->test_sanity_strict = attr->prog_flags & BPF_F_TEST_SANITY_STRICT;
 
 	env->explored_states = kvcalloc(state_htab_size(env),
 				       sizeof(struct bpf_verifier_state_list *),
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 7cf8bcf9f6a2..8a5855fcee69 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1200,6 +1200,9 @@ enum bpf_perf_event_type {
  */
 #define BPF_F_XDP_DEV_BOUND_ONLY	(1U << 6)
 
+/* The verifier internal test flag. Behavior is undefined */
+#define BPF_F_TEST_SANITY_STRICT	(1U << 7)
+
 /* link_create.kprobe_multi.flags used in LINK_CREATE command for
  * BPF_TRACE_KPROBE_MULTI attach type to create return probe.
  */
-- 
cgit v1.2.3


From dfcb264a01a9199e8338a548731baf5bbe77ef19 Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Sat, 4 Nov 2023 16:49:06 +0100
Subject: power: supply: bq27xxx: Stop and start delayed work in suspend and
 resume

This driver uses delayed work to perform periodic battery state read out.
This delayed work is not stopped across suspend and resume cycle. The
read out can occur early in the resume cycle. In case of an I2C variant
of this hardware, that read out triggers I2C transfer. That I2C transfer
may happen while the I2C controller is still suspended, which produces a
WARNING in the kernel log.

Fix this by introducing trivial PM ops, which stop the delayed work before
the system enters suspend, and schedule the delayed work right after the
system resumes.

Signed-off-by: Marek Vasut <marex@denx.de>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20231104154920.68585-1-marex@denx.de
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/bq27xxx_battery.c     | 22 ++++++++++++++++++++++
 drivers/power/supply/bq27xxx_battery_i2c.c |  1 +
 include/linux/power/bq27xxx_battery.h      |  1 +
 3 files changed, 24 insertions(+)

(limited to 'include')

diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c
index 4296600e8912..1c4a9d137744 100644
--- a/drivers/power/supply/bq27xxx_battery.c
+++ b/drivers/power/supply/bq27xxx_battery.c
@@ -2162,6 +2162,28 @@ void bq27xxx_battery_teardown(struct bq27xxx_device_info *di)
 }
 EXPORT_SYMBOL_GPL(bq27xxx_battery_teardown);
 
+#ifdef CONFIG_PM_SLEEP
+static int bq27xxx_battery_suspend(struct device *dev)
+{
+	struct bq27xxx_device_info *di = dev_get_drvdata(dev);
+
+	cancel_delayed_work(&di->work);
+	return 0;
+}
+
+static int bq27xxx_battery_resume(struct device *dev)
+{
+	struct bq27xxx_device_info *di = dev_get_drvdata(dev);
+
+	schedule_delayed_work(&di->work, 0);
+	return 0;
+}
+#endif /* CONFIG_PM_SLEEP */
+
+SIMPLE_DEV_PM_OPS(bq27xxx_battery_battery_pm_ops,
+		  bq27xxx_battery_suspend, bq27xxx_battery_resume);
+EXPORT_SYMBOL_GPL(bq27xxx_battery_battery_pm_ops);
+
 MODULE_AUTHOR("Rodolfo Giometti <giometti@linux.it>");
 MODULE_DESCRIPTION("BQ27xxx battery monitor driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/power/supply/bq27xxx_battery_i2c.c b/drivers/power/supply/bq27xxx_battery_i2c.c
index 9b5475590518..3a1798b0c1a7 100644
--- a/drivers/power/supply/bq27xxx_battery_i2c.c
+++ b/drivers/power/supply/bq27xxx_battery_i2c.c
@@ -295,6 +295,7 @@ static struct i2c_driver bq27xxx_battery_i2c_driver = {
 	.driver = {
 		.name = "bq27xxx-battery",
 		.of_match_table = of_match_ptr(bq27xxx_battery_i2c_of_match_table),
+		.pm = &bq27xxx_battery_battery_pm_ops,
 	},
 	.probe = bq27xxx_battery_i2c_probe,
 	.remove = bq27xxx_battery_i2c_remove,
diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h
index 7c8d65414a70..7d8025fb74b7 100644
--- a/include/linux/power/bq27xxx_battery.h
+++ b/include/linux/power/bq27xxx_battery.h
@@ -83,5 +83,6 @@ struct bq27xxx_device_info {
 void bq27xxx_battery_update(struct bq27xxx_device_info *di);
 int bq27xxx_battery_setup(struct bq27xxx_device_info *di);
 void bq27xxx_battery_teardown(struct bq27xxx_device_info *di);
+extern const struct dev_pm_ops bq27xxx_battery_battery_pm_ops;
 
 #endif
-- 
cgit v1.2.3


From 74d016ecc1a7974664e98d1afbf649cd4e0e0423 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 15 Nov 2023 22:41:27 -0500
Subject: new helper: user_path_locked_at()

Equivalent of kern_path_locked() taking dfd/userland name.
User introduced in the next commit.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namei.c            | 16 +++++++++++++---
 include/linux/namei.h |  1 +
 2 files changed, 14 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/fs/namei.c b/fs/namei.c
index 71c13b2990b4..3ffbe268d52c 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2573,13 +2573,13 @@ static int filename_parentat(int dfd, struct filename *name,
 }
 
 /* does lookup, returns the object with parent locked */
-static struct dentry *__kern_path_locked(struct filename *name, struct path *path)
+static struct dentry *__kern_path_locked(int dfd, struct filename *name, struct path *path)
 {
 	struct dentry *d;
 	struct qstr last;
 	int type, error;
 
-	error = filename_parentat(AT_FDCWD, name, 0, path, &last, &type);
+	error = filename_parentat(dfd, name, 0, path, &last, &type);
 	if (error)
 		return ERR_PTR(error);
 	if (unlikely(type != LAST_NORM)) {
@@ -2598,12 +2598,22 @@ static struct dentry *__kern_path_locked(struct filename *name, struct path *pat
 struct dentry *kern_path_locked(const char *name, struct path *path)
 {
 	struct filename *filename = getname_kernel(name);
-	struct dentry *res = __kern_path_locked(filename, path);
+	struct dentry *res = __kern_path_locked(AT_FDCWD, filename, path);
 
 	putname(filename);
 	return res;
 }
 
+struct dentry *user_path_locked_at(int dfd, const char __user *name, struct path *path)
+{
+	struct filename *filename = getname(name);
+	struct dentry *res = __kern_path_locked(dfd, filename, path);
+
+	putname(filename);
+	return res;
+}
+EXPORT_SYMBOL(user_path_locked_at);
+
 int kern_path(const char *name, unsigned int flags, struct path *path)
 {
 	struct filename *filename = getname_kernel(name);
diff --git a/include/linux/namei.h b/include/linux/namei.h
index 3100371b5e32..74e0cc14ebf8 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -66,6 +66,7 @@ extern struct dentry *kern_path_create(int, const char *, struct path *, unsigne
 extern struct dentry *user_path_create(int, const char __user *, struct path *, unsigned int);
 extern void done_path_create(struct path *, struct dentry *);
 extern struct dentry *kern_path_locked(const char *, struct path *);
+extern struct dentry *user_path_locked_at(int , const char __user *, struct path *);
 int vfs_path_parent_lookup(struct filename *filename, unsigned int flags,
 			   struct path *parent, struct qstr *last, int *type,
 			   const struct path *root);
-- 
cgit v1.2.3


From 3185d57cfcd34fadbe28f4ed57a6cb5122277ece Mon Sep 17 00:00:00 2001
From: Tobias Klauser <tklauser@distanz.ch>
Date: Tue, 14 Nov 2023 11:42:02 +0100
Subject: indirect_call_wrapper: Fix typo in INDIRECT_CALL_$NR kerneldoc

Fix a small typo in the kerneldoc comment of the INDIRECT_CALL_$NR
macro.

Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20231114104202.4680-1-tklauser@distanz.ch
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/linux/indirect_call_wrapper.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/indirect_call_wrapper.h b/include/linux/indirect_call_wrapper.h
index c1c76a70a6ce..adb83a42a6b9 100644
--- a/include/linux/indirect_call_wrapper.h
+++ b/include/linux/indirect_call_wrapper.h
@@ -11,7 +11,7 @@
  *  @__VA_ARGS__: arguments for @f
  *
  * Avoid retpoline overhead for known builtin, checking @f vs each of them and
- * eventually invoking directly the builtin function. The functions are check
+ * eventually invoking directly the builtin function. The functions are checked
  * in the given order. Fallback to the indirect call.
  */
 #define INDIRECT_CALL_1(f, f1, ...)					\
-- 
cgit v1.2.3


From f7f965c982f7954b46db910146a7ffe0fe1eb5e1 Mon Sep 17 00:00:00 2001
From: Tao Zhang <quic_taozha@quicinc.com>
Date: Thu, 28 Sep 2023 14:29:36 +0800
Subject: coresight-tpdm: Introduce TPDM subtype to TPDM driver

Introduce the new subtype of "CORESIGHT_DEV_SUBTYPE_SOURCE_TPDM"
for TPDM components in driver.

Signed-off-by: Tao Zhang <quic_taozha@quicinc.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Link: https://lore.kernel.org/r/1695882586-10306-4-git-send-email-quic_taozha@quicinc.com
---
 drivers/hwtracing/coresight/coresight-core.c | 3 +++
 drivers/hwtracing/coresight/coresight-tpdm.c | 2 +-
 include/linux/coresight.h                    | 1 +
 3 files changed, 5 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/hwtracing/coresight/coresight-core.c b/drivers/hwtracing/coresight/coresight-core.c
index 9fabe00a40d6..d7f0e231feb9 100644
--- a/drivers/hwtracing/coresight/coresight-core.c
+++ b/drivers/hwtracing/coresight/coresight-core.c
@@ -1093,6 +1093,7 @@ static int coresight_validate_source(struct coresight_device *csdev,
 
 	if (subtype != CORESIGHT_DEV_SUBTYPE_SOURCE_PROC &&
 	    subtype != CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE &&
+	    subtype != CORESIGHT_DEV_SUBTYPE_SOURCE_TPDM &&
 	    subtype != CORESIGHT_DEV_SUBTYPE_SOURCE_OTHERS) {
 		dev_err(&csdev->dev, "wrong device subtype in %s\n", function);
 		return -EINVAL;
@@ -1162,6 +1163,7 @@ int coresight_enable(struct coresight_device *csdev)
 		per_cpu(tracer_path, cpu) = path;
 		break;
 	case CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE:
+	case CORESIGHT_DEV_SUBTYPE_SOURCE_TPDM:
 	case CORESIGHT_DEV_SUBTYPE_SOURCE_OTHERS:
 		/*
 		 * Use the hash of source's device name as ID
@@ -1212,6 +1214,7 @@ void coresight_disable(struct coresight_device *csdev)
 		per_cpu(tracer_path, cpu) = NULL;
 		break;
 	case CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE:
+	case CORESIGHT_DEV_SUBTYPE_SOURCE_TPDM:
 	case CORESIGHT_DEV_SUBTYPE_SOURCE_OTHERS:
 		hash = hashlen_hash(hashlen_string(NULL, dev_name(&csdev->dev)));
 		/* Find the path by the hash. */
diff --git a/drivers/hwtracing/coresight/coresight-tpdm.c b/drivers/hwtracing/coresight/coresight-tpdm.c
index b6456120b76a..abaff0b934db 100644
--- a/drivers/hwtracing/coresight/coresight-tpdm.c
+++ b/drivers/hwtracing/coresight/coresight-tpdm.c
@@ -203,7 +203,7 @@ static int tpdm_probe(struct amba_device *adev, const struct amba_id *id)
 	if (!desc.name)
 		return -ENOMEM;
 	desc.type = CORESIGHT_DEV_TYPE_SOURCE;
-	desc.subtype.source_subtype = CORESIGHT_DEV_SUBTYPE_SOURCE_OTHERS;
+	desc.subtype.source_subtype = CORESIGHT_DEV_SUBTYPE_SOURCE_TPDM;
 	desc.ops = &tpdm_cs_ops;
 	desc.pdata = adev->dev.platform_data;
 	desc.dev = &adev->dev;
diff --git a/include/linux/coresight.h b/include/linux/coresight.h
index a269fffaf991..a4cb7dd6ca23 100644
--- a/include/linux/coresight.h
+++ b/include/linux/coresight.h
@@ -64,6 +64,7 @@ enum coresight_dev_subtype_source {
 	CORESIGHT_DEV_SUBTYPE_SOURCE_PROC,
 	CORESIGHT_DEV_SUBTYPE_SOURCE_BUS,
 	CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE,
+	CORESIGHT_DEV_SUBTYPE_SOURCE_TPDM,
 	CORESIGHT_DEV_SUBTYPE_SOURCE_OTHERS,
 };
 
-- 
cgit v1.2.3


From 3fc6350fc8470d42f5e700ecd1c3d90f9dd9fd2d Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 13 Nov 2023 13:12:49 +0200
Subject: treewide, spi: Get rid of SPI_MASTER_HALF_DUPLEX

The SPI_MASTER_HALF_DUPLEX is the legacy name of a definition
for a half duplex flag. Since all others had been replaced with
the respective SPI_CONTROLLER prefix get rid of the last one
as well. There is no functional change intended.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Ulf Hansson <ulf.hansson@linaro.org> # For MMC
Acked-by: Dmitry Torokhov <dmitry.torokhov@gmail.com> # for input
Acked-by: Paolo Abeni <pabeni@redhat.com>
Link: https://lore.kernel.org/r/20231113111249.3982461-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/input/rmi4/rmi_spi.c             | 2 +-
 drivers/mmc/host/mmc_spi.c               | 2 +-
 drivers/net/ethernet/micrel/ks8851_spi.c | 4 ++--
 drivers/usb/gadget/udc/max3420_udc.c     | 2 +-
 include/linux/spi/spi.h                  | 2 --
 5 files changed, 5 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/input/rmi4/rmi_spi.c b/drivers/input/rmi4/rmi_spi.c
index 852aeb0b2c07..07c866f42296 100644
--- a/drivers/input/rmi4/rmi_spi.c
+++ b/drivers/input/rmi4/rmi_spi.c
@@ -375,7 +375,7 @@ static int rmi_spi_probe(struct spi_device *spi)
 	struct rmi_device_platform_data *spi_pdata = spi->dev.platform_data;
 	int error;
 
-	if (spi->master->flags & SPI_MASTER_HALF_DUPLEX)
+	if (spi->master->flags & SPI_CONTROLLER_HALF_DUPLEX)
 		return -EINVAL;
 
 	rmi_spi = devm_kzalloc(&spi->dev, sizeof(struct rmi_spi_xport),
diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c
index cc333ad67cac..b0cccef4cfbf 100644
--- a/drivers/mmc/host/mmc_spi.c
+++ b/drivers/mmc/host/mmc_spi.c
@@ -1322,7 +1322,7 @@ static int mmc_spi_probe(struct spi_device *spi)
 	/* We rely on full duplex transfers, mostly to reduce
 	 * per-transfer overheads (by making fewer transfers).
 	 */
-	if (spi->master->flags & SPI_MASTER_HALF_DUPLEX)
+	if (spi->master->flags & SPI_CONTROLLER_HALF_DUPLEX)
 		return -EINVAL;
 
 	/* MMC and SD specs only seem to care that sampling is on the
diff --git a/drivers/net/ethernet/micrel/ks8851_spi.c b/drivers/net/ethernet/micrel/ks8851_spi.c
index 70bc7253454f..7c41623dac90 100644
--- a/drivers/net/ethernet/micrel/ks8851_spi.c
+++ b/drivers/net/ethernet/micrel/ks8851_spi.c
@@ -156,7 +156,7 @@ static void ks8851_rdreg(struct ks8851_net *ks, unsigned int op,
 
 	txb[0] = cpu_to_le16(op | KS_SPIOP_RD);
 
-	if (kss->spidev->master->flags & SPI_MASTER_HALF_DUPLEX) {
+	if (kss->spidev->master->flags & SPI_CONTROLLER_HALF_DUPLEX) {
 		msg = &kss->spi_msg2;
 		xfer = kss->spi_xfer2;
 
@@ -180,7 +180,7 @@ static void ks8851_rdreg(struct ks8851_net *ks, unsigned int op,
 	ret = spi_sync(kss->spidev, msg);
 	if (ret < 0)
 		netdev_err(ks->netdev, "read: spi_sync() failed\n");
-	else if (kss->spidev->master->flags & SPI_MASTER_HALF_DUPLEX)
+	else if (kss->spidev->master->flags & SPI_CONTROLLER_HALF_DUPLEX)
 		memcpy(rxb, trx, rxl);
 	else
 		memcpy(rxb, trx + 2, rxl);
diff --git a/drivers/usb/gadget/udc/max3420_udc.c b/drivers/usb/gadget/udc/max3420_udc.c
index 2d57786d3db7..89e8cf2a2a7d 100644
--- a/drivers/usb/gadget/udc/max3420_udc.c
+++ b/drivers/usb/gadget/udc/max3420_udc.c
@@ -1201,7 +1201,7 @@ static int max3420_probe(struct spi_device *spi)
 	int err, irq;
 	u8 reg[8];
 
-	if (spi->master->flags & SPI_MASTER_HALF_DUPLEX) {
+	if (spi->master->flags & SPI_CONTROLLER_HALF_DUPLEX) {
 		dev_err(&spi->dev, "UDC needs full duplex to work\n");
 		return -EINVAL;
 	}
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 255a0562aea5..7b4baff63c5c 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -1638,8 +1638,6 @@ spi_transfer_is_last(struct spi_controller *ctlr, struct spi_transfer *xfer)
 /* Compatibility layer */
 #define spi_master			spi_controller
 
-#define SPI_MASTER_HALF_DUPLEX		SPI_CONTROLLER_HALF_DUPLEX
-
 #define spi_master_get_devdata(_ctlr)	spi_controller_get_devdata(_ctlr)
 #define spi_master_set_devdata(_ctlr, _data)	\
 	spi_controller_set_devdata(_ctlr, _data)
-- 
cgit v1.2.3


From 103d15bc20086820ce2c2af40a651529a87c9e3c Mon Sep 17 00:00:00 2001
From: Sebastian Fricke <sebastian.fricke@collabora.com>
Date: Wed, 8 Nov 2023 20:29:20 +0100
Subject: media: v4l2: Add ignore_streaming flag

Add a new flag to the `struct v4l2_m2m_dev` to toggle whether a queue
must be streaming in order to allow queuing jobs to the ready queue.
Currently, both queues (CAPTURE & OUTPUT) must be streaming in order to
allow adding new jobs. This behavior limits the usability of M2M for
some drivers, as these have to be able, to perform analysis of the
sequence to ensure, that userspace prepares the CAPTURE queue correctly.

Signed-off-by: Sebastian Fricke <sebastian.fricke@collabora.com>
Signed-off-by: Nicolas Dufresne <nicolas.dufresne@collabora.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
---
 include/media/v4l2-mem2mem.h | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/media/v4l2-mem2mem.h b/include/media/v4l2-mem2mem.h
index d6c8eb2b5201..1288fe364fab 100644
--- a/include/media/v4l2-mem2mem.h
+++ b/include/media/v4l2-mem2mem.h
@@ -84,6 +84,12 @@ struct v4l2_m2m_queue_ctx {
  * @last_src_buf: indicate the last source buffer for draining
  * @next_buf_last: next capture queud buffer will be tagged as last
  * @has_stopped: indicate the device has been stopped
+ * @ignore_cap_streaming: If true, job_ready can be called even if the CAPTURE
+ *			  queue is not streaming. This allows firmware to
+ *			  analyze the bitstream header which arrives on the
+ *			  OUTPUT queue. The driver must implement the job_ready
+ *			  callback correctly to make sure that the requirements
+ *			  for actual decoding are met.
  * @m2m_dev: opaque pointer to the internal data to handle M2M context
  * @cap_q_ctx: Capture (output to memory) queue context
  * @out_q_ctx: Output (input from memory) queue context
@@ -106,6 +112,7 @@ struct v4l2_m2m_ctx {
 	struct vb2_v4l2_buffer		*last_src_buf;
 	bool				next_buf_last;
 	bool				has_stopped;
+	bool				ignore_cap_streaming;
 
 	/* internal use only */
 	struct v4l2_m2m_dev		*m2m_dev;
-- 
cgit v1.2.3


From 5d33213fac5929a2e7766c88d78779fd443b0fe8 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Fri, 3 Nov 2023 10:39:24 +0300
Subject: media: v4l2-subdev: Fix a 64bit bug

The problem is this line here from subdev_do_ioctl().

        client_cap->capabilities &= ~V4L2_SUBDEV_CLIENT_CAP_STREAMS;

The "client_cap->capabilities" variable is a u64.  The AND operation
is supposed to clear out the V4L2_SUBDEV_CLIENT_CAP_STREAMS flag.  But
because it's a 32 bit variable it accidentally clears out the high 32
bits as well.

Currently we only use the first bit and none of the upper bits so this
doesn't affect runtime behavior.

Fixes: f57fa2959244 ("media: v4l2-subdev: Add new ioctl for client capabilities")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Tomi Valkeinen <tomi.valkeinen@ideasonboard.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
---
 include/uapi/linux/v4l2-subdev.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/v4l2-subdev.h b/include/uapi/linux/v4l2-subdev.h
index 4a195b68f28f..b383c2fe0cf3 100644
--- a/include/uapi/linux/v4l2-subdev.h
+++ b/include/uapi/linux/v4l2-subdev.h
@@ -239,7 +239,7 @@ struct v4l2_subdev_routing {
  * set (which is the default), the 'stream' fields will be forced to 0 by the
  * kernel.
  */
- #define V4L2_SUBDEV_CLIENT_CAP_STREAMS		(1U << 0)
+ #define V4L2_SUBDEV_CLIENT_CAP_STREAMS		(1ULL << 0)
 
 /**
  * struct v4l2_subdev_client_capability - Capabilities of the client accessing
-- 
cgit v1.2.3


From fac4a535758851215d23d7d92879aeee5035f51d Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 8 Aug 2023 19:27:56 +0300
Subject: device property: Add fwnode_property_match_property_string()

Sometimes the users want to match the single value string property
against an array of predefined strings. Create a helper for them.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Rafael J. Wysocki <rafael@kernel.org>
Link: https://lore.kernel.org/r/20230808162800.61651-3-andriy.shevchenko@linux.intel.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/base/property.c  | 35 +++++++++++++++++++++++++++++++++++
 include/linux/property.h | 12 ++++++++++++
 2 files changed, 47 insertions(+)

(limited to 'include')

diff --git a/drivers/base/property.c b/drivers/base/property.c
index 3bb9505f1631..8f8e2a6816bc 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -498,6 +498,41 @@ out_free:
 }
 EXPORT_SYMBOL_GPL(fwnode_property_match_string);
 
+/**
+ * fwnode_property_match_property_string - find a property string value in an array and return index
+ * @fwnode: Firmware node to get the property of
+ * @propname: Name of the property holding the string value
+ * @array: String array to search in
+ * @n: Size of the @array
+ *
+ * Find a property string value in a given @array and if it is found return
+ * the index back.
+ *
+ * Return: index, starting from %0, if the string value was found in the @array (success),
+ *	   %-ENOENT when the string value was not found in the @array,
+ *	   %-EINVAL if given arguments are not valid,
+ *	   %-ENODATA if the property does not have a value,
+ *	   %-EPROTO or %-EILSEQ if the property is not a string,
+ *	   %-ENXIO if no suitable firmware interface is present.
+ */
+int fwnode_property_match_property_string(const struct fwnode_handle *fwnode,
+	const char *propname, const char * const *array, size_t n)
+{
+	const char *string;
+	int ret;
+
+	ret = fwnode_property_read_string(fwnode, propname, &string);
+	if (ret)
+		return ret;
+
+	ret = match_string(array, n, string);
+	if (ret < 0)
+		ret = -ENOENT;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(fwnode_property_match_property_string);
+
 /**
  * fwnode_property_get_reference_args() - Find a reference with arguments
  * @fwnode:	Firmware node where to look for the reference
diff --git a/include/linux/property.h b/include/linux/property.h
index 9f2585d705a8..2b8f07fc68a9 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -98,6 +98,18 @@ static inline bool device_is_compatible(const struct device *dev, const char *co
 	return fwnode_device_is_compatible(dev_fwnode(dev), compat);
 }
 
+int fwnode_property_match_property_string(const struct fwnode_handle *fwnode,
+					  const char *propname,
+					  const char * const *array, size_t n);
+
+static inline
+int device_property_match_property_string(const struct device *dev,
+					  const char *propname,
+					  const char * const *array, size_t n)
+{
+	return fwnode_property_match_property_string(dev_fwnode(dev), propname, array, n);
+}
+
 int fwnode_property_get_reference_args(const struct fwnode_handle *fwnode,
 				       const char *prop, const char *nargs_prop,
 				       unsigned int nargs, unsigned int index,
-- 
cgit v1.2.3


From c6e9dba3be5ef3b701b29b143609561915e5d0e9 Mon Sep 17 00:00:00 2001
From: Alce Lafranque <alce@lafranque.net>
Date: Tue, 14 Nov 2023 11:36:57 -0600
Subject: vxlan: add support for flowlabel inherit

By default, VXLAN encapsulation over IPv6 sets the flow label to 0, with
an option for a fixed value. This commits add the ability to inherit the
flow label from the inner packet, like for other tunnel implementations.
This enables devices using only L3 headers for ECMP to correctly balance
VXLAN-encapsulated IPv6 packets.

```
$ ./ip/ip link add dummy1 type dummy
$ ./ip/ip addr add 2001:db8::2/64 dev dummy1
$ ./ip/ip link set up dev dummy1
$ ./ip/ip link add vxlan1 type vxlan id 100 flowlabel inherit remote 2001:db8::1 local 2001:db8::2
$ ./ip/ip link set up dev vxlan1
$ ./ip/ip addr add 2001:db8:1::2/64 dev vxlan1
$ ./ip/ip link set arp off dev vxlan1
$ ping -q 2001:db8:1::1 &
$ tshark -d udp.port==8472,vxlan -Vpni dummy1 -c1
[...]
Internet Protocol Version 6, Src: 2001:db8::2, Dst: 2001:db8::1
    0110 .... = Version: 6
    .... 0000 0000 .... .... .... .... .... = Traffic Class: 0x00 (DSCP: CS0, ECN: Not-ECT)
        .... 0000 00.. .... .... .... .... .... = Differentiated Services Codepoint: Default (0)
        .... .... ..00 .... .... .... .... .... = Explicit Congestion Notification: Not ECN-Capable Transport (0)
    .... 1011 0001 1010 1111 1011 = Flow Label: 0xb1afb
[...]
Virtual eXtensible Local Area Network
    Flags: 0x0800, VXLAN Network ID (VNI)
    Group Policy ID: 0
    VXLAN Network Identifier (VNI): 100
[...]
Internet Protocol Version 6, Src: 2001:db8:1::2, Dst: 2001:db8:1::1
    0110 .... = Version: 6
    .... 0000 0000 .... .... .... .... .... = Traffic Class: 0x00 (DSCP: CS0, ECN: Not-ECT)
        .... 0000 00.. .... .... .... .... .... = Differentiated Services Codepoint: Default (0)
        .... .... ..00 .... .... .... .... .... = Explicit Congestion Notification: Not ECN-Capable Transport (0)
    .... 1011 0001 1010 1111 1011 = Flow Label: 0xb1afb
```

Signed-off-by: Alce Lafranque <alce@lafranque.net>
Co-developed-by: Vincent Bernat <vincent@bernat.ch>
Signed-off-by: Vincent Bernat <vincent@bernat.ch>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan/vxlan_core.c | 23 ++++++++++++++++++++++-
 include/net/ip_tunnels.h       | 11 +++++++++++
 include/net/vxlan.h            | 33 +++++++++++++++++----------------
 include/uapi/linux/if_link.h   |  8 ++++++++
 4 files changed, 58 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index 412c3c0b6990..764ea02ff911 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -2379,7 +2379,17 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		else
 			udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM6_TX);
 #if IS_ENABLED(CONFIG_IPV6)
-		key.label = vxlan->cfg.label;
+		switch (vxlan->cfg.label_policy) {
+		case VXLAN_LABEL_FIXED:
+			key.label = vxlan->cfg.label;
+			break;
+		case VXLAN_LABEL_INHERIT:
+			key.label = ip_tunnel_get_flowlabel(old_iph, skb);
+			break;
+		default:
+			DEBUG_NET_WARN_ON_ONCE(1);
+			goto drop;
+		}
 #endif
 	} else {
 		if (!info) {
@@ -3366,6 +3376,7 @@ static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = {
 	[IFLA_VXLAN_DF]		= { .type = NLA_U8 },
 	[IFLA_VXLAN_VNIFILTER]	= { .type = NLA_U8 },
 	[IFLA_VXLAN_LOCALBYPASS]	= NLA_POLICY_MAX(NLA_U8, 1),
+	[IFLA_VXLAN_LABEL_POLICY]       = NLA_POLICY_MAX(NLA_U32, VXLAN_LABEL_MAX),
 };
 
 static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[],
@@ -3740,6 +3751,12 @@ static int vxlan_config_validate(struct net *src_net, struct vxlan_config *conf,
 		return -EINVAL;
 	}
 
+	if (conf->label_policy && !use_ipv6) {
+		NL_SET_ERR_MSG(extack,
+			       "Label policy only applies to IPv6 VXLAN devices");
+		return -EINVAL;
+	}
+
 	if (conf->remote_ifindex) {
 		struct net_device *lowerdev;
 
@@ -4082,6 +4099,8 @@ static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[],
 	if (data[IFLA_VXLAN_LABEL])
 		conf->label = nla_get_be32(data[IFLA_VXLAN_LABEL]) &
 			     IPV6_FLOWLABEL_MASK;
+	if (data[IFLA_VXLAN_LABEL_POLICY])
+		conf->label_policy = nla_get_u32(data[IFLA_VXLAN_LABEL_POLICY]);
 
 	if (data[IFLA_VXLAN_LEARNING]) {
 		err = vxlan_nl2flag(conf, data, IFLA_VXLAN_LEARNING,
@@ -4398,6 +4417,7 @@ static size_t vxlan_get_size(const struct net_device *dev)
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_TOS */
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_DF */
 		nla_total_size(sizeof(__be32)) + /* IFLA_VXLAN_LABEL */
+		nla_total_size(sizeof(__u32)) +  /* IFLA_VXLAN_LABEL_POLICY */
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_LEARNING */
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_PROXY */
 		nla_total_size(sizeof(__u8)) +	/* IFLA_VXLAN_RSC */
@@ -4471,6 +4491,7 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	    nla_put_u8(skb, IFLA_VXLAN_TOS, vxlan->cfg.tos) ||
 	    nla_put_u8(skb, IFLA_VXLAN_DF, vxlan->cfg.df) ||
 	    nla_put_be32(skb, IFLA_VXLAN_LABEL, vxlan->cfg.label) ||
+	    nla_put_u32(skb, IFLA_VXLAN_LABEL_POLICY, vxlan->cfg.label_policy) ||
 	    nla_put_u8(skb, IFLA_VXLAN_LEARNING,
 		       !!(vxlan->cfg.flags & VXLAN_F_LEARN)) ||
 	    nla_put_u8(skb, IFLA_VXLAN_PROXY,
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index f346b4efbc30..2d746f4c9a0a 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -416,6 +416,17 @@ static inline u8 ip_tunnel_get_dsfield(const struct iphdr *iph,
 		return 0;
 }
 
+static inline __be32 ip_tunnel_get_flowlabel(const struct iphdr *iph,
+					     const struct sk_buff *skb)
+{
+	__be16 payload_protocol = skb_protocol(skb, true);
+
+	if (payload_protocol == htons(ETH_P_IPV6))
+		return ip6_flowlabel((const struct ipv6hdr *)iph);
+	else
+		return 0;
+}
+
 static inline u8 ip_tunnel_get_ttl(const struct iphdr *iph,
 				       const struct sk_buff *skb)
 {
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 6a9f8a5f387c..33ba6fc151cf 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -210,22 +210,23 @@ struct vxlan_rdst {
 };
 
 struct vxlan_config {
-	union vxlan_addr	remote_ip;
-	union vxlan_addr	saddr;
-	__be32			vni;
-	int			remote_ifindex;
-	int			mtu;
-	__be16			dst_port;
-	u16			port_min;
-	u16			port_max;
-	u8			tos;
-	u8			ttl;
-	__be32			label;
-	u32			flags;
-	unsigned long		age_interval;
-	unsigned int		addrmax;
-	bool			no_share;
-	enum ifla_vxlan_df	df;
+	union vxlan_addr		remote_ip;
+	union vxlan_addr		saddr;
+	__be32				vni;
+	int				remote_ifindex;
+	int				mtu;
+	__be16				dst_port;
+	u16				port_min;
+	u16				port_max;
+	u8				tos;
+	u8				ttl;
+	__be32				label;
+	enum ifla_vxlan_label_policy	label_policy;
+	u32				flags;
+	unsigned long			age_interval;
+	unsigned int			addrmax;
+	bool				no_share;
+	enum ifla_vxlan_df		df;
 };
 
 enum {
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 29ff80da2775..8181ef23a7a2 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -856,6 +856,7 @@ enum {
 	IFLA_VXLAN_DF,
 	IFLA_VXLAN_VNIFILTER, /* only applicable with COLLECT_METADATA mode */
 	IFLA_VXLAN_LOCALBYPASS,
+	IFLA_VXLAN_LABEL_POLICY, /* IPv6 flow label policy; ifla_vxlan_label_policy */
 	__IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)
@@ -873,6 +874,13 @@ enum ifla_vxlan_df {
 	VXLAN_DF_MAX = __VXLAN_DF_END - 1,
 };
 
+enum ifla_vxlan_label_policy {
+	VXLAN_LABEL_FIXED = 0,
+	VXLAN_LABEL_INHERIT = 1,
+	__VXLAN_LABEL_END,
+	VXLAN_LABEL_MAX = __VXLAN_LABEL_END - 1,
+};
+
 /* GENEVE section */
 enum {
 	IFLA_GENEVE_UNSPEC,
-- 
cgit v1.2.3


From 96fa96e198f9707285003075fbbce7db6a485112 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 15 Nov 2023 11:39:18 +0000
Subject: net: linkmode: add linkmode_fill() helper

Add a linkmode_fill() helper, which will allow us to convert phylink's
open coded bitmap_fill() operations.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/linkmode.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h
index 7303b4bc2ce0..287f590ed56b 100644
--- a/include/linux/linkmode.h
+++ b/include/linux/linkmode.h
@@ -10,6 +10,11 @@ static inline void linkmode_zero(unsigned long *dst)
 	bitmap_zero(dst, __ETHTOOL_LINK_MODE_MASK_NBITS);
 }
 
+static inline void linkmode_fill(unsigned long *dst)
+{
+	bitmap_fill(dst, __ETHTOOL_LINK_MODE_MASK_NBITS);
+}
+
 static inline void linkmode_copy(unsigned long *dst, const unsigned long *src)
 {
 	bitmap_copy(dst, src, __ETHTOOL_LINK_MODE_MASK_NBITS);
-- 
cgit v1.2.3


From a9214a8883ceb82df55aa90d1c49ddb85fc1e3d5 Mon Sep 17 00:00:00 2001
From: Etienne Carriere <etienne.carriere@foss.st.com>
Date: Mon, 30 Oct 2023 09:48:10 +0100
Subject: tee: system session

Adds kernel client API function tee_client_system_session() for a client
to request a system service entry in TEE context.

This feature is needed to prevent a system deadlock when several TEE
client applications invoke TEE, consuming all TEE thread contexts
available in the secure world. The deadlock can happen in the OP-TEE
driver for example if all these TEE threads issue an RPC call from TEE
to Linux OS to access an eMMC RPMB partition (TEE secure storage) which
device clock or regulator controller is accessed through an OP-TEE SCMI
services. In that case, Linux SCMI driver must reach OP-TEE SCMI service
without waiting until one of the consumed TEE threads is freed.

Reviewed-by: Sumit Garg <sumit.garg@linaro.org>
Co-developed-by: Jens Wiklander <jens.wiklander@linaro.org>
Signed-off-by: Etienne Carriere <etienne.carriere@foss.st.com>
Signed-off-by: Jens Wiklander <jens.wiklander@linaro.org>
---
 drivers/tee/tee_core.c  |  8 ++++++++
 include/linux/tee_drv.h | 16 ++++++++++++++++
 2 files changed, 24 insertions(+)

(limited to 'include')

diff --git a/drivers/tee/tee_core.c b/drivers/tee/tee_core.c
index 5ddfd5d9ac7f..792d6fae4354 100644
--- a/drivers/tee/tee_core.c
+++ b/drivers/tee/tee_core.c
@@ -1173,6 +1173,14 @@ int tee_client_close_session(struct tee_context *ctx, u32 session)
 }
 EXPORT_SYMBOL_GPL(tee_client_close_session);
 
+int tee_client_system_session(struct tee_context *ctx, u32 session)
+{
+	if (!ctx->teedev->desc->ops->system_session)
+		return -EINVAL;
+	return ctx->teedev->desc->ops->system_session(ctx, session);
+}
+EXPORT_SYMBOL_GPL(tee_client_system_session);
+
 int tee_client_invoke_func(struct tee_context *ctx,
 			   struct tee_ioctl_invoke_arg *arg,
 			   struct tee_param *param)
diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h
index 17eb1c5205d3..911ddf92dcee 100644
--- a/include/linux/tee_drv.h
+++ b/include/linux/tee_drv.h
@@ -84,6 +84,7 @@ struct tee_param {
  * @release:		release this open file
  * @open_session:	open a new session
  * @close_session:	close a session
+ * @system_session:	declare session as a system session
  * @invoke_func:	invoke a trusted function
  * @cancel_req:		request cancel of an ongoing invoke or open
  * @supp_recv:		called for supplicant to get a command
@@ -100,6 +101,7 @@ struct tee_driver_ops {
 			    struct tee_ioctl_open_session_arg *arg,
 			    struct tee_param *param);
 	int (*close_session)(struct tee_context *ctx, u32 session);
+	int (*system_session)(struct tee_context *ctx, u32 session);
 	int (*invoke_func)(struct tee_context *ctx,
 			   struct tee_ioctl_invoke_arg *arg,
 			   struct tee_param *param);
@@ -429,6 +431,20 @@ int tee_client_open_session(struct tee_context *ctx,
  */
 int tee_client_close_session(struct tee_context *ctx, u32 session);
 
+/**
+ * tee_client_system_session() - Declare session as a system session
+ * @ctx:	TEE Context
+ * @session:	Session id
+ *
+ * This function requests TEE to provision an entry context ready to use for
+ * that session only. The provisioned entry context is used for command
+ * invocation and session closure, not for command cancelling requests.
+ * TEE releases the provisioned context upon session closure.
+ *
+ * Return < 0 on error else 0 if an entry context has been provisioned.
+ */
+int tee_client_system_session(struct tee_context *ctx, u32 session);
+
 /**
  * tee_client_invoke_func() - Invoke a function in a Trusted Application
  * @ctx:	TEE Context
-- 
cgit v1.2.3


From 5e4166461cf66a26f925011d90017da74e410747 Mon Sep 17 00:00:00 2001
From: Yang Hubin <yanghb2019@lzu.edu.cn>
Date: Sat, 4 Nov 2023 00:45:01 -0700
Subject: f2fs: the name of a struct is wrong in a comment.

The macro SUMMARY_SIZE represents the size of the struct f2fs_summary,

instead of the size of the struct summary.

Signed-off-by: Yang Hubin <yanghb2019@lzu.edu.cn>
Signed-off-by: Qian Haolai <qianhl2023@lzu.edu.cn>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 include/linux/f2fs_fs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index 039fe0ce8d83..053137a0fe45 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -441,7 +441,7 @@ struct f2fs_sit_block {
  * ex) data_blkaddr = (block_t)(nodepage_start_address + ofs_in_node)
  */
 #define ENTRIES_IN_SUM		(F2FS_BLKSIZE / 8)
-#define	SUMMARY_SIZE		(7)	/* sizeof(struct summary) */
+#define	SUMMARY_SIZE		(7)	/* sizeof(struct f2fs_summary) */
 #define	SUM_FOOTER_SIZE		(5)	/* sizeof(struct summary_footer) */
 #define SUM_ENTRY_SIZE		(SUMMARY_SIZE * ENTRIES_IN_SUM)
 
-- 
cgit v1.2.3


From ff8867af01daa7ea770bebf5f91199b7434b74e5 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Fri, 17 Nov 2023 09:14:04 -0800
Subject: bpf: rename BPF_F_TEST_SANITY_STRICT to BPF_F_TEST_REG_INVARIANTS

Rename verifier internal flag BPF_F_TEST_SANITY_STRICT to more neutral
BPF_F_TEST_REG_INVARIANTS. This is a follow up to [0].

A few selftests and veristat need to be adjusted in the same patch as
well.

  [0] https://patchwork.kernel.org/project/netdevbpf/patch/20231112010609.848406-5-andrii@kernel.org/

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20231117171404.225508-1-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf_verifier.h                             |  2 +-
 include/uapi/linux/bpf.h                                 |  2 +-
 kernel/bpf/syscall.c                                     |  2 +-
 kernel/bpf/verifier.c                                    |  6 +++---
 tools/include/uapi/linux/bpf.h                           |  2 +-
 tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c |  2 +-
 tools/testing/selftests/bpf/prog_tests/reg_bounds.c      |  2 +-
 tools/testing/selftests/bpf/progs/verifier_bounds.c      |  4 ++--
 tools/testing/selftests/bpf/test_loader.c                |  6 +++---
 tools/testing/selftests/bpf/test_sock_addr.c             |  3 +--
 tools/testing/selftests/bpf/test_verifier.c              |  2 +-
 tools/testing/selftests/bpf/testing_helpers.c            |  4 ++--
 tools/testing/selftests/bpf/veristat.c                   | 12 ++++++------
 13 files changed, 24 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 402b6bc44a1b..52a4012b8255 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -602,7 +602,7 @@ struct bpf_verifier_env {
 	int stack_size;			/* number of states to be processed */
 	bool strict_alignment;		/* perform strict pointer alignment checks */
 	bool test_state_freq;		/* test verifier with different pruning frequency */
-	bool test_sanity_strict;	/* fail verification on sanity violations */
+	bool test_reg_invariants;	/* fail verification on register invariants violations */
 	struct bpf_verifier_state *cur_state; /* current verifier state */
 	struct bpf_verifier_state_list **explored_states; /* search pruning optimization */
 	struct bpf_verifier_state_list *free_list;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 8a5855fcee69..7a5498242eaa 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1201,7 +1201,7 @@ enum bpf_perf_event_type {
 #define BPF_F_XDP_DEV_BOUND_ONLY	(1U << 6)
 
 /* The verifier internal test flag. Behavior is undefined */
-#define BPF_F_TEST_SANITY_STRICT	(1U << 7)
+#define BPF_F_TEST_REG_INVARIANTS	(1U << 7)
 
 /* link_create.kprobe_multi.flags used in LINK_CREATE command for
  * BPF_TRACE_KPROBE_MULTI attach type to create return probe.
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index f266e03ba342..5e43ddd1b83f 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2574,7 +2574,7 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
 				 BPF_F_TEST_RND_HI32 |
 				 BPF_F_XDP_HAS_FRAGS |
 				 BPF_F_XDP_DEV_BOUND_ONLY |
-				 BPF_F_TEST_SANITY_STRICT))
+				 BPF_F_TEST_REG_INVARIANTS))
 		return -EINVAL;
 
 	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) &&
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 59505881e7a7..7c3461b89513 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2608,14 +2608,14 @@ static int reg_bounds_sanity_check(struct bpf_verifier_env *env,
 
 	return 0;
 out:
-	verbose(env, "REG SANITY VIOLATION (%s): %s u64=[%#llx, %#llx] "
+	verbose(env, "REG INVARIANTS VIOLATION (%s): %s u64=[%#llx, %#llx] "
 		"s64=[%#llx, %#llx] u32=[%#x, %#x] s32=[%#x, %#x] var_off=(%#llx, %#llx)\n",
 		ctx, msg, reg->umin_value, reg->umax_value,
 		reg->smin_value, reg->smax_value,
 		reg->u32_min_value, reg->u32_max_value,
 		reg->s32_min_value, reg->s32_max_value,
 		reg->var_off.value, reg->var_off.mask);
-	if (env->test_sanity_strict)
+	if (env->test_reg_invariants)
 		return -EFAULT;
 	__mark_reg_unbounded(reg);
 	return 0;
@@ -20791,7 +20791,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
 
 	if (is_priv)
 		env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ;
-	env->test_sanity_strict = attr->prog_flags & BPF_F_TEST_SANITY_STRICT;
+	env->test_reg_invariants = attr->prog_flags & BPF_F_TEST_REG_INVARIANTS;
 
 	env->explored_states = kvcalloc(state_htab_size(env),
 				       sizeof(struct bpf_verifier_state_list *),
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 8a5855fcee69..7a5498242eaa 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1201,7 +1201,7 @@ enum bpf_perf_event_type {
 #define BPF_F_XDP_DEV_BOUND_ONLY	(1U << 6)
 
 /* The verifier internal test flag. Behavior is undefined */
-#define BPF_F_TEST_SANITY_STRICT	(1U << 7)
+#define BPF_F_TEST_REG_INVARIANTS	(1U << 7)
 
 /* link_create.kprobe_multi.flags used in LINK_CREATE command for
  * BPF_TRACE_KPROBE_MULTI attach type to create return probe.
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
index 3f2d70831873..e770912fc1d2 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
@@ -35,7 +35,7 @@ static int check_load(const char *file, enum bpf_prog_type type)
 	}
 
 	bpf_program__set_type(prog, type);
-	bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32 | BPF_F_TEST_SANITY_STRICT);
+	bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32 | BPF_F_TEST_REG_INVARIANTS);
 	bpf_program__set_log_level(prog, 4 | extra_prog_load_log_flags);
 
 	err = bpf_object__load(obj);
diff --git a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
index fe0cb906644b..7a8b0bf0a7f8 100644
--- a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
+++ b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
@@ -838,7 +838,7 @@ static int load_range_cmp_prog(struct range x, struct range y, enum op op,
 		.log_level = 2,
 		.log_buf = log_buf,
 		.log_size = log_sz,
-		.prog_flags = BPF_F_TEST_SANITY_STRICT,
+		.prog_flags = BPF_F_TEST_REG_INVARIANTS,
 	);
 
 	/* ; skip exit block below
diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds.c b/tools/testing/selftests/bpf/progs/verifier_bounds.c
index 0c1460936373..ec430b71730b 100644
--- a/tools/testing/selftests/bpf/progs/verifier_bounds.c
+++ b/tools/testing/selftests/bpf/progs/verifier_bounds.c
@@ -965,7 +965,7 @@ l0_%=:	r0 = 0;						\
 SEC("xdp")
 __description("bound check with JMP_JSLT for crossing 64-bit signed boundary")
 __success __retval(0)
-__flag(!BPF_F_TEST_SANITY_STRICT) /* known sanity violation */
+__flag(!BPF_F_TEST_REG_INVARIANTS) /* known invariants violation */
 __naked void crossing_64_bit_signed_boundary_2(void)
 {
 	asm volatile ("					\
@@ -1047,7 +1047,7 @@ l0_%=:	r0 = 0;						\
 SEC("xdp")
 __description("bound check with JMP32_JSLT for crossing 32-bit signed boundary")
 __success __retval(0)
-__flag(!BPF_F_TEST_SANITY_STRICT) /* known sanity violation */
+__flag(!BPF_F_TEST_REG_INVARIANTS) /* known invariants violation */
 __naked void crossing_32_bit_signed_boundary_2(void)
 {
 	asm volatile ("					\
diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c
index 57e27b1a73a6..a350ecdfba4a 100644
--- a/tools/testing/selftests/bpf/test_loader.c
+++ b/tools/testing/selftests/bpf/test_loader.c
@@ -179,7 +179,7 @@ static int parse_test_spec(struct test_loader *tester,
 	memset(spec, 0, sizeof(*spec));
 
 	spec->prog_name = bpf_program__name(prog);
-	spec->prog_flags = BPF_F_TEST_SANITY_STRICT; /* by default be strict */
+	spec->prog_flags = BPF_F_TEST_REG_INVARIANTS; /* by default be strict */
 
 	btf = bpf_object__btf(obj);
 	if (!btf) {
@@ -280,8 +280,8 @@ static int parse_test_spec(struct test_loader *tester,
 				update_flags(&spec->prog_flags, BPF_F_SLEEPABLE, clear);
 			} else if (strcmp(val, "BPF_F_XDP_HAS_FRAGS") == 0) {
 				update_flags(&spec->prog_flags, BPF_F_XDP_HAS_FRAGS, clear);
-			} else if (strcmp(val, "BPF_F_TEST_SANITY_STRICT") == 0) {
-				update_flags(&spec->prog_flags, BPF_F_TEST_SANITY_STRICT, clear);
+			} else if (strcmp(val, "BPF_F_TEST_REG_INVARIANTS") == 0) {
+				update_flags(&spec->prog_flags, BPF_F_TEST_REG_INVARIANTS, clear);
 			} else /* assume numeric value */ {
 				err = parse_int(val, &flags, "test prog flags");
 				if (err)
diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c
index 878c077e0fa7..b0068a9d2cfe 100644
--- a/tools/testing/selftests/bpf/test_sock_addr.c
+++ b/tools/testing/selftests/bpf/test_sock_addr.c
@@ -679,8 +679,7 @@ static int load_path(const struct sock_addr_test *test, const char *path)
 
 	bpf_program__set_type(prog, BPF_PROG_TYPE_CGROUP_SOCK_ADDR);
 	bpf_program__set_expected_attach_type(prog, test->expected_attach_type);
-	bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32);
-	bpf_program__set_flags(prog, BPF_F_TEST_SANITY_STRICT);
+	bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32 | BPF_F_TEST_REG_INVARIANTS);
 
 	err = bpf_object__load(obj);
 	if (err) {
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 4992022f3137..f36e41435be7 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -1588,7 +1588,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 	if (fixup_skips != skips)
 		return;
 
-	pflags = BPF_F_TEST_RND_HI32 | BPF_F_TEST_SANITY_STRICT;
+	pflags = BPF_F_TEST_RND_HI32 | BPF_F_TEST_REG_INVARIANTS;
 	if (test->flags & F_LOAD_WITH_STRICT_ALIGNMENT)
 		pflags |= BPF_F_STRICT_ALIGNMENT;
 	if (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS)
diff --git a/tools/testing/selftests/bpf/testing_helpers.c b/tools/testing/selftests/bpf/testing_helpers.c
index 9786a94a666c..d2458c1b1671 100644
--- a/tools/testing/selftests/bpf/testing_helpers.c
+++ b/tools/testing/selftests/bpf/testing_helpers.c
@@ -276,7 +276,7 @@ int bpf_prog_test_load(const char *file, enum bpf_prog_type type,
 	if (type != BPF_PROG_TYPE_UNSPEC && bpf_program__type(prog) != type)
 		bpf_program__set_type(prog, type);
 
-	flags = bpf_program__flags(prog) | BPF_F_TEST_RND_HI32 | BPF_F_TEST_SANITY_STRICT;
+	flags = bpf_program__flags(prog) | BPF_F_TEST_RND_HI32 | BPF_F_TEST_REG_INVARIANTS;
 	bpf_program__set_flags(prog, flags);
 
 	err = bpf_object__load(obj);
@@ -299,7 +299,7 @@ int bpf_test_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
 {
 	LIBBPF_OPTS(bpf_prog_load_opts, opts,
 		.kern_version = kern_version,
-		.prog_flags = BPF_F_TEST_RND_HI32 | BPF_F_TEST_SANITY_STRICT,
+		.prog_flags = BPF_F_TEST_RND_HI32 | BPF_F_TEST_REG_INVARIANTS,
 		.log_level = extra_prog_load_log_flags,
 		.log_buf = log_buf,
 		.log_size = log_buf_sz,
diff --git a/tools/testing/selftests/bpf/veristat.c b/tools/testing/selftests/bpf/veristat.c
index 609fd9753af0..1d418d66e375 100644
--- a/tools/testing/selftests/bpf/veristat.c
+++ b/tools/testing/selftests/bpf/veristat.c
@@ -145,7 +145,7 @@ static struct env {
 	bool debug;
 	bool quiet;
 	bool force_checkpoints;
-	bool strict_range_sanity;
+	bool force_reg_invariants;
 	enum resfmt out_fmt;
 	bool show_version;
 	bool comparison_mode;
@@ -225,8 +225,8 @@ static const struct argp_option opts[] = {
 	{ "filter", 'f', "FILTER", 0, "Filter expressions (or @filename for file with expressions)." },
 	{ "test-states", 't', NULL, 0,
 	  "Force frequent BPF verifier state checkpointing (set BPF_F_TEST_STATE_FREQ program flag)" },
-	{ "test-sanity", 'r', NULL, 0,
-	  "Force strict BPF verifier register sanity behavior (BPF_F_TEST_SANITY_STRICT program flag)" },
+	{ "test-reg-invariants", 'r', NULL, 0,
+	  "Force BPF verifier failure on register invariant violation (BPF_F_TEST_REG_INVARIANTS program flag)" },
 	{},
 };
 
@@ -299,7 +299,7 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
 		env.force_checkpoints = true;
 		break;
 	case 'r':
-		env.strict_range_sanity = true;
+		env.force_reg_invariants = true;
 		break;
 	case 'n':
 		errno = 0;
@@ -1028,8 +1028,8 @@ static int process_prog(const char *filename, struct bpf_object *obj, struct bpf
 
 	if (env.force_checkpoints)
 		bpf_program__set_flags(prog, bpf_program__flags(prog) | BPF_F_TEST_STATE_FREQ);
-	if (env.strict_range_sanity)
-		bpf_program__set_flags(prog, bpf_program__flags(prog) | BPF_F_TEST_SANITY_STRICT);
+	if (env.force_reg_invariants)
+		bpf_program__set_flags(prog, bpf_program__flags(prog) | BPF_F_TEST_REG_INVARIANTS);
 
 	err = bpf_object__load(obj);
 	env.progs_processed++;
-- 
cgit v1.2.3


From 98d2b43081972abeb5bb5a087bc3e3197531c46e Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@redhat.com>
Date: Wed, 25 Oct 2023 16:01:59 +0200
Subject: add unique mount ID

If a mount is released then its mnt_id can immediately be reused.  This is
bad news for user interfaces that want to uniquely identify a mount.

Implementing a unique mount ID is trivial (use a 64bit counter).
Unfortunately userspace assumes 32bit size and would overflow after the
counter reaches 2^32.

Introduce a new 64bit ID alongside the old one.  Initialize the counter to
2^32, this guarantees that the old and new IDs are never mixed up.

Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Link: https://lore.kernel.org/r/20231025140205.3586473-2-mszeredi@redhat.com
Reviewed-by: Ian Kent <raven@themaw.net>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/mount.h                | 3 ++-
 fs/namespace.c            | 4 ++++
 fs/stat.c                 | 9 +++++++--
 include/uapi/linux/stat.h | 1 +
 4 files changed, 14 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/fs/mount.h b/fs/mount.h
index 130c07c2f8d2..a14f762b3f29 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -72,7 +72,8 @@ struct mount {
 	struct fsnotify_mark_connector __rcu *mnt_fsnotify_marks;
 	__u32 mnt_fsnotify_mask;
 #endif
-	int mnt_id;			/* mount identifier */
+	int mnt_id;			/* mount identifier, reused */
+	u64 mnt_id_unique;		/* mount ID unique until reboot */
 	int mnt_group_id;		/* peer group identifier */
 	int mnt_expiry_mark;		/* true if marked for expiry */
 	struct hlist_head mnt_pins;
diff --git a/fs/namespace.c b/fs/namespace.c
index fbf0e596fcd3..0bcba81402b5 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -68,6 +68,9 @@ static u64 event;
 static DEFINE_IDA(mnt_id_ida);
 static DEFINE_IDA(mnt_group_ida);
 
+/* Don't allow confusion with old 32bit mount ID */
+static atomic64_t mnt_id_ctr = ATOMIC64_INIT(1ULL << 32);
+
 static struct hlist_head *mount_hashtable __ro_after_init;
 static struct hlist_head *mountpoint_hashtable __ro_after_init;
 static struct kmem_cache *mnt_cache __ro_after_init;
@@ -131,6 +134,7 @@ static int mnt_alloc_id(struct mount *mnt)
 	if (res < 0)
 		return res;
 	mnt->mnt_id = res;
+	mnt->mnt_id_unique = atomic64_inc_return(&mnt_id_ctr);
 	return 0;
 }
 
diff --git a/fs/stat.c b/fs/stat.c
index 24bb0209e459..e44f0625c24f 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -243,8 +243,13 @@ retry:
 
 	error = vfs_getattr(&path, stat, request_mask, flags);
 
-	stat->mnt_id = real_mount(path.mnt)->mnt_id;
-	stat->result_mask |= STATX_MNT_ID;
+	if (request_mask & STATX_MNT_ID_UNIQUE) {
+		stat->mnt_id = real_mount(path.mnt)->mnt_id_unique;
+		stat->result_mask |= STATX_MNT_ID_UNIQUE;
+	} else {
+		stat->mnt_id = real_mount(path.mnt)->mnt_id;
+		stat->result_mask |= STATX_MNT_ID;
+	}
 
 	if (path.mnt->mnt_root == path.dentry)
 		stat->attributes |= STATX_ATTR_MOUNT_ROOT;
diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h
index 7cab2c65d3d7..2f2ee82d5517 100644
--- a/include/uapi/linux/stat.h
+++ b/include/uapi/linux/stat.h
@@ -154,6 +154,7 @@ struct statx {
 #define STATX_BTIME		0x00000800U	/* Want/got stx_btime */
 #define STATX_MNT_ID		0x00001000U	/* Got stx_mnt_id */
 #define STATX_DIOALIGN		0x00002000U	/* Want/got direct I/O alignment info */
+#define STATX_MNT_ID_UNIQUE	0x00004000U	/* Want/got extended stx_mount_id */
 
 #define STATX__RESERVED		0x80000000U	/* Reserved for future struct statx expansion */
 
-- 
cgit v1.2.3


From 2eea9ce4310d8c0f8ef1dbe7b0e7d9219ff02b97 Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@redhat.com>
Date: Wed, 25 Oct 2023 16:02:00 +0200
Subject: mounts: keep list of mounts in an rbtree

When adding a mount to a namespace insert it into an rbtree rooted in the
mnt_namespace instead of a linear list.

The mnt.mnt_list is still used to set up the mount tree and for
propagation, but not after the mount has been added to a namespace.  Hence
mnt_list can live in union with rb_node.  Use MNT_ONRB mount flag to
validate that the mount is on the correct list.

This allows removing the cursor used for reading /proc/$PID/mountinfo.  The
mnt_id_unique of the next mount can be used as an index into the seq file.

Tested by inserting 100k bind mounts, unsharing the mount namespace, and
unmounting.  No performance regressions have been observed.

For the last mount in the 100k list the statmount() call was more than 100x
faster due to the mount ID lookup not having to do a linear search.  This
patch makes the overhead of mount ID lookup non-observable in this range.

Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Link: https://lore.kernel.org/r/20231025140205.3586473-3-mszeredi@redhat.com
Reviewed-by: Ian Kent <raven@themaw.net>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/mount.h            |  24 ++++---
 fs/namespace.c        | 190 +++++++++++++++++++++++---------------------------
 fs/pnode.c            |   2 +-
 fs/proc_namespace.c   |   3 -
 include/linux/mount.h |   5 +-
 5 files changed, 106 insertions(+), 118 deletions(-)

(limited to 'include')

diff --git a/fs/mount.h b/fs/mount.h
index a14f762b3f29..4a42fc68f4cc 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -8,19 +8,13 @@
 struct mnt_namespace {
 	struct ns_common	ns;
 	struct mount *	root;
-	/*
-	 * Traversal and modification of .list is protected by either
-	 * - taking namespace_sem for write, OR
-	 * - taking namespace_sem for read AND taking .ns_lock.
-	 */
-	struct list_head	list;
-	spinlock_t		ns_lock;
+	struct rb_root		mounts; /* Protected by namespace_sem */
 	struct user_namespace	*user_ns;
 	struct ucounts		*ucounts;
 	u64			seq;	/* Sequence number to prevent loops */
 	wait_queue_head_t poll;
 	u64 event;
-	unsigned int		mounts; /* # of mounts in the namespace */
+	unsigned int		nr_mounts; /* # of mounts in the namespace */
 	unsigned int		pending_mounts;
 } __randomize_layout;
 
@@ -55,7 +49,10 @@ struct mount {
 	struct list_head mnt_child;	/* and going through their mnt_child */
 	struct list_head mnt_instance;	/* mount instance on sb->s_mounts */
 	const char *mnt_devname;	/* Name of device e.g. /dev/dsk/hda1 */
-	struct list_head mnt_list;
+	union {
+		struct rb_node mnt_node;	/* Under ns->mounts */
+		struct list_head mnt_list;
+	};
 	struct list_head mnt_expire;	/* link in fs-specific expiry list */
 	struct list_head mnt_share;	/* circular list of shared mounts */
 	struct list_head mnt_slave_list;/* list of slave mounts */
@@ -128,7 +125,6 @@ struct proc_mounts {
 	struct mnt_namespace *ns;
 	struct path root;
 	int (*show)(struct seq_file *, struct vfsmount *);
-	struct mount cursor;
 };
 
 extern const struct seq_operations mounts_op;
@@ -147,4 +143,12 @@ static inline bool is_anon_ns(struct mnt_namespace *ns)
 	return ns->seq == 0;
 }
 
+static inline void move_from_ns(struct mount *mnt, struct list_head *dt_list)
+{
+	WARN_ON(!(mnt->mnt.mnt_flags & MNT_ONRB));
+	mnt->mnt.mnt_flags &= ~MNT_ONRB;
+	rb_erase(&mnt->mnt_node, &mnt->mnt_ns->mounts);
+	list_add_tail(&mnt->mnt_list, dt_list);
+}
+
 extern void mnt_cursor_del(struct mnt_namespace *ns, struct mount *cursor);
diff --git a/fs/namespace.c b/fs/namespace.c
index 0bcba81402b5..bbe94096e262 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -734,21 +734,6 @@ struct vfsmount *lookup_mnt(const struct path *path)
 	return m;
 }
 
-static inline void lock_ns_list(struct mnt_namespace *ns)
-{
-	spin_lock(&ns->ns_lock);
-}
-
-static inline void unlock_ns_list(struct mnt_namespace *ns)
-{
-	spin_unlock(&ns->ns_lock);
-}
-
-static inline bool mnt_is_cursor(struct mount *mnt)
-{
-	return mnt->mnt.mnt_flags & MNT_CURSOR;
-}
-
 /*
  * __is_local_mountpoint - Test to see if dentry is a mountpoint in the
  *                         current mount namespace.
@@ -767,19 +752,15 @@ static inline bool mnt_is_cursor(struct mount *mnt)
 bool __is_local_mountpoint(struct dentry *dentry)
 {
 	struct mnt_namespace *ns = current->nsproxy->mnt_ns;
-	struct mount *mnt;
+	struct mount *mnt, *n;
 	bool is_covered = false;
 
 	down_read(&namespace_sem);
-	lock_ns_list(ns);
-	list_for_each_entry(mnt, &ns->list, mnt_list) {
-		if (mnt_is_cursor(mnt))
-			continue;
+	rbtree_postorder_for_each_entry_safe(mnt, n, &ns->mounts, mnt_node) {
 		is_covered = (mnt->mnt_mountpoint == dentry);
 		if (is_covered)
 			break;
 	}
-	unlock_ns_list(ns);
 	up_read(&namespace_sem);
 
 	return is_covered;
@@ -1026,6 +1007,30 @@ void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct m
 	mnt_add_count(old_parent, -1);
 }
 
+static inline struct mount *node_to_mount(struct rb_node *node)
+{
+	return rb_entry(node, struct mount, mnt_node);
+}
+
+static void mnt_add_to_ns(struct mnt_namespace *ns, struct mount *mnt)
+{
+	struct rb_node **link = &ns->mounts.rb_node;
+	struct rb_node *parent = NULL;
+
+	WARN_ON(mnt->mnt.mnt_flags & MNT_ONRB);
+	mnt->mnt_ns = ns;
+	while (*link) {
+		parent = *link;
+		if (mnt->mnt_id_unique < node_to_mount(parent)->mnt_id_unique)
+			link = &parent->rb_left;
+		else
+			link = &parent->rb_right;
+	}
+	rb_link_node(&mnt->mnt_node, parent, link);
+	rb_insert_color(&mnt->mnt_node, &ns->mounts);
+	mnt->mnt.mnt_flags |= MNT_ONRB;
+}
+
 /*
  * vfsmount lock must be held for write
  */
@@ -1039,12 +1044,13 @@ static void commit_tree(struct mount *mnt)
 	BUG_ON(parent == mnt);
 
 	list_add_tail(&head, &mnt->mnt_list);
-	list_for_each_entry(m, &head, mnt_list)
-		m->mnt_ns = n;
+	while (!list_empty(&head)) {
+		m = list_first_entry(&head, typeof(*m), mnt_list);
+		list_del(&m->mnt_list);
 
-	list_splice(&head, n->list.prev);
-
-	n->mounts += n->pending_mounts;
+		mnt_add_to_ns(n, m);
+	}
+	n->nr_mounts += n->pending_mounts;
 	n->pending_mounts = 0;
 
 	__attach_mnt(mnt, parent);
@@ -1192,7 +1198,7 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 	}
 
 	mnt->mnt.mnt_flags = old->mnt.mnt_flags;
-	mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL);
+	mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL|MNT_ONRB);
 
 	atomic_inc(&sb->s_active);
 	mnt->mnt.mnt_idmap = mnt_idmap_get(mnt_idmap(&old->mnt));
@@ -1417,65 +1423,57 @@ struct vfsmount *mnt_clone_internal(const struct path *path)
 	return &p->mnt;
 }
 
-#ifdef CONFIG_PROC_FS
-static struct mount *mnt_list_next(struct mnt_namespace *ns,
-				   struct list_head *p)
+/*
+ * Returns the mount which either has the specified mnt_id, or has the next
+ * smallest id afer the specified one.
+ */
+static struct mount *mnt_find_id_at(struct mnt_namespace *ns, u64 mnt_id)
 {
-	struct mount *mnt, *ret = NULL;
+	struct rb_node *node = ns->mounts.rb_node;
+	struct mount *ret = NULL;
 
-	lock_ns_list(ns);
-	list_for_each_continue(p, &ns->list) {
-		mnt = list_entry(p, typeof(*mnt), mnt_list);
-		if (!mnt_is_cursor(mnt)) {
-			ret = mnt;
-			break;
+	while (node) {
+		struct mount *m = node_to_mount(node);
+
+		if (mnt_id <= m->mnt_id_unique) {
+			ret = node_to_mount(node);
+			if (mnt_id == m->mnt_id_unique)
+				break;
+			node = node->rb_left;
+		} else {
+			node = node->rb_right;
 		}
 	}
-	unlock_ns_list(ns);
-
 	return ret;
 }
 
+#ifdef CONFIG_PROC_FS
+
 /* iterator; we want it to have access to namespace_sem, thus here... */
 static void *m_start(struct seq_file *m, loff_t *pos)
 {
 	struct proc_mounts *p = m->private;
-	struct list_head *prev;
 
 	down_read(&namespace_sem);
-	if (!*pos) {
-		prev = &p->ns->list;
-	} else {
-		prev = &p->cursor.mnt_list;
 
-		/* Read after we'd reached the end? */
-		if (list_empty(prev))
-			return NULL;
-	}
-
-	return mnt_list_next(p->ns, prev);
+	return mnt_find_id_at(p->ns, *pos);
 }
 
 static void *m_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	struct proc_mounts *p = m->private;
-	struct mount *mnt = v;
+	struct mount *next = NULL, *mnt = v;
+	struct rb_node *node = rb_next(&mnt->mnt_node);
 
 	++*pos;
-	return mnt_list_next(p->ns, &mnt->mnt_list);
+	if (node) {
+		next = node_to_mount(node);
+		*pos = next->mnt_id_unique;
+	}
+	return next;
 }
 
 static void m_stop(struct seq_file *m, void *v)
 {
-	struct proc_mounts *p = m->private;
-	struct mount *mnt = v;
-
-	lock_ns_list(p->ns);
-	if (mnt)
-		list_move_tail(&p->cursor.mnt_list, &mnt->mnt_list);
-	else
-		list_del_init(&p->cursor.mnt_list);
-	unlock_ns_list(p->ns);
 	up_read(&namespace_sem);
 }
 
@@ -1493,14 +1491,6 @@ const struct seq_operations mounts_op = {
 	.show	= m_show,
 };
 
-void mnt_cursor_del(struct mnt_namespace *ns, struct mount *cursor)
-{
-	down_read(&namespace_sem);
-	lock_ns_list(ns);
-	list_del(&cursor->mnt_list);
-	unlock_ns_list(ns);
-	up_read(&namespace_sem);
-}
 #endif  /* CONFIG_PROC_FS */
 
 /**
@@ -1642,7 +1632,10 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how)
 	/* Gather the mounts to umount */
 	for (p = mnt; p; p = next_mnt(p, mnt)) {
 		p->mnt.mnt_flags |= MNT_UMOUNT;
-		list_move(&p->mnt_list, &tmp_list);
+		if (p->mnt.mnt_flags & MNT_ONRB)
+			move_from_ns(p, &tmp_list);
+		else
+			list_move(&p->mnt_list, &tmp_list);
 	}
 
 	/* Hide the mounts from mnt_mounts */
@@ -1662,7 +1655,7 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how)
 		list_del_init(&p->mnt_list);
 		ns = p->mnt_ns;
 		if (ns) {
-			ns->mounts--;
+			ns->nr_mounts--;
 			__touch_mnt_namespace(ns);
 		}
 		p->mnt_ns = NULL;
@@ -1788,14 +1781,16 @@ static int do_umount(struct mount *mnt, int flags)
 
 	event++;
 	if (flags & MNT_DETACH) {
-		if (!list_empty(&mnt->mnt_list))
+		if (mnt->mnt.mnt_flags & MNT_ONRB ||
+		    !list_empty(&mnt->mnt_list))
 			umount_tree(mnt, UMOUNT_PROPAGATE);
 		retval = 0;
 	} else {
 		shrink_submounts(mnt);
 		retval = -EBUSY;
 		if (!propagate_mount_busy(mnt, 2)) {
-			if (!list_empty(&mnt->mnt_list))
+			if (mnt->mnt.mnt_flags & MNT_ONRB ||
+			    !list_empty(&mnt->mnt_list))
 				umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC);
 			retval = 0;
 		}
@@ -2213,9 +2208,9 @@ int count_mounts(struct mnt_namespace *ns, struct mount *mnt)
 	unsigned int mounts = 0;
 	struct mount *p;
 
-	if (ns->mounts >= max)
+	if (ns->nr_mounts >= max)
 		return -ENOSPC;
-	max -= ns->mounts;
+	max -= ns->nr_mounts;
 	if (ns->pending_mounts >= max)
 		return -ENOSPC;
 	max -= ns->pending_mounts;
@@ -2359,8 +2354,12 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 		touch_mnt_namespace(source_mnt->mnt_ns);
 	} else {
 		if (source_mnt->mnt_ns) {
+			LIST_HEAD(head);
+
 			/* move from anon - the caller will destroy */
-			list_del_init(&source_mnt->mnt_ns->list);
+			for (p = source_mnt; p; p = next_mnt(p, source_mnt))
+				move_from_ns(p, &head);
+			list_del_init(&head);
 		}
 		if (beneath)
 			mnt_set_mountpoint_beneath(source_mnt, top_mnt, smp);
@@ -2671,11 +2670,10 @@ static struct file *open_detached_copy(struct path *path, bool recursive)
 
 	lock_mount_hash();
 	for (p = mnt; p; p = next_mnt(p, mnt)) {
-		p->mnt_ns = ns;
-		ns->mounts++;
+		mnt_add_to_ns(ns, p);
+		ns->nr_mounts++;
 	}
 	ns->root = mnt;
-	list_add_tail(&ns->list, &mnt->mnt_list);
 	mntget(&mnt->mnt);
 	unlock_mount_hash();
 	namespace_unlock();
@@ -3738,9 +3736,8 @@ static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns, bool a
 	if (!anon)
 		new_ns->seq = atomic64_add_return(1, &mnt_ns_seq);
 	refcount_set(&new_ns->ns.count, 1);
-	INIT_LIST_HEAD(&new_ns->list);
+	new_ns->mounts = RB_ROOT;
 	init_waitqueue_head(&new_ns->poll);
-	spin_lock_init(&new_ns->ns_lock);
 	new_ns->user_ns = get_user_ns(user_ns);
 	new_ns->ucounts = ucounts;
 	return new_ns;
@@ -3787,7 +3784,6 @@ struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns,
 		unlock_mount_hash();
 	}
 	new_ns->root = new;
-	list_add_tail(&new_ns->list, &new->mnt_list);
 
 	/*
 	 * Second pass: switch the tsk->fs->* elements and mark new vfsmounts
@@ -3797,8 +3793,8 @@ struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns,
 	p = old;
 	q = new;
 	while (p) {
-		q->mnt_ns = new_ns;
-		new_ns->mounts++;
+		mnt_add_to_ns(new_ns, q);
+		new_ns->nr_mounts++;
 		if (new_fs) {
 			if (&p->mnt == new_fs->root.mnt) {
 				new_fs->root.mnt = mntget(&q->mnt);
@@ -3840,10 +3836,9 @@ struct dentry *mount_subtree(struct vfsmount *m, const char *name)
 		mntput(m);
 		return ERR_CAST(ns);
 	}
-	mnt->mnt_ns = ns;
 	ns->root = mnt;
-	ns->mounts++;
-	list_add(&mnt->mnt_list, &ns->list);
+	ns->nr_mounts++;
+	mnt_add_to_ns(ns, mnt);
 
 	err = vfs_path_lookup(m->mnt_root, m,
 			name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path);
@@ -4021,10 +4016,9 @@ SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags,
 		goto err_path;
 	}
 	mnt = real_mount(newmount.mnt);
-	mnt->mnt_ns = ns;
 	ns->root = mnt;
-	ns->mounts = 1;
-	list_add(&mnt->mnt_list, &ns->list);
+	ns->nr_mounts = 1;
+	mnt_add_to_ns(ns, mnt);
 	mntget(newmount.mnt);
 
 	/* Attach to an apparent O_PATH fd with a note that we need to unmount
@@ -4695,10 +4689,9 @@ static void __init init_mount_tree(void)
 	if (IS_ERR(ns))
 		panic("Can't allocate initial namespace");
 	m = real_mount(mnt);
-	m->mnt_ns = ns;
 	ns->root = m;
-	ns->mounts = 1;
-	list_add(&m->mnt_list, &ns->list);
+	ns->nr_mounts = 1;
+	mnt_add_to_ns(ns, m);
 	init_task.nsproxy->mnt_ns = ns;
 	get_mnt_ns(ns);
 
@@ -4825,18 +4818,14 @@ static bool mnt_already_visible(struct mnt_namespace *ns,
 				int *new_mnt_flags)
 {
 	int new_flags = *new_mnt_flags;
-	struct mount *mnt;
+	struct mount *mnt, *n;
 	bool visible = false;
 
 	down_read(&namespace_sem);
-	lock_ns_list(ns);
-	list_for_each_entry(mnt, &ns->list, mnt_list) {
+	rbtree_postorder_for_each_entry_safe(mnt, n, &ns->mounts, mnt_node) {
 		struct mount *child;
 		int mnt_flags;
 
-		if (mnt_is_cursor(mnt))
-			continue;
-
 		if (mnt->mnt.mnt_sb->s_type != sb->s_type)
 			continue;
 
@@ -4884,7 +4873,6 @@ static bool mnt_already_visible(struct mnt_namespace *ns,
 	next:	;
 	}
 found:
-	unlock_ns_list(ns);
 	up_read(&namespace_sem);
 	return visible;
 }
diff --git a/fs/pnode.c b/fs/pnode.c
index e4d0340393d5..a799e0315cc9 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -468,7 +468,7 @@ static void umount_one(struct mount *mnt, struct list_head *to_umount)
 	mnt->mnt.mnt_flags |= MNT_UMOUNT;
 	list_del_init(&mnt->mnt_child);
 	list_del_init(&mnt->mnt_umounting);
-	list_move_tail(&mnt->mnt_list, to_umount);
+	move_from_ns(mnt, to_umount);
 }
 
 /*
diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c
index 250eb5bf7b52..73d2274d5f59 100644
--- a/fs/proc_namespace.c
+++ b/fs/proc_namespace.c
@@ -283,8 +283,6 @@ static int mounts_open_common(struct inode *inode, struct file *file,
 	p->ns = ns;
 	p->root = root;
 	p->show = show;
-	INIT_LIST_HEAD(&p->cursor.mnt_list);
-	p->cursor.mnt.mnt_flags = MNT_CURSOR;
 
 	return 0;
 
@@ -301,7 +299,6 @@ static int mounts_release(struct inode *inode, struct file *file)
 	struct seq_file *m = file->private_data;
 	struct proc_mounts *p = m->private;
 	path_put(&p->root);
-	mnt_cursor_del(p->ns, &p->cursor);
 	put_mnt_ns(p->ns);
 	return seq_release_private(inode, file);
 }
diff --git a/include/linux/mount.h b/include/linux/mount.h
index ac3dd2876197..c34c18b4e8f3 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -50,8 +50,7 @@ struct path;
 #define MNT_ATIME_MASK (MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME )
 
 #define MNT_INTERNAL_FLAGS (MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | \
-			    MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED | \
-			    MNT_CURSOR)
+			    MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED | MNT_ONRB)
 
 #define MNT_INTERNAL	0x4000
 
@@ -65,7 +64,7 @@ struct path;
 #define MNT_SYNC_UMOUNT		0x2000000
 #define MNT_MARKED		0x4000000
 #define MNT_UMOUNT		0x8000000
-#define MNT_CURSOR		0x10000000
+#define MNT_ONRB		0x10000000
 
 struct vfsmount {
 	struct dentry *mnt_root;	/* root of the mounted tree */
-- 
cgit v1.2.3


From 982c3b3058433f20aba9fb032599cee5dfc17328 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Tue, 24 Oct 2023 15:01:08 +0200
Subject: bdev: rename freeze and thaw helpers

We have bdev_mark_dead() etc and we're going to move block device
freezing to holder ops in the next patch. Make the naming consistent:

* freeze_bdev() -> bdev_freeze()
* thaw_bdev()   -> bdev_thaw()

Also document the return code.

Link: https://lore.kernel.org/r/20231024-vfs-super-freeze-v2-2-599c19f4faac@kernel.org
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 block/bdev.c           | 22 +++++++++++++---------
 drivers/md/dm.c        |  4 ++--
 fs/bcachefs/fs-ioctl.c |  4 ++--
 fs/ext4/ioctl.c        |  4 ++--
 fs/f2fs/file.c         |  4 ++--
 fs/super.c             |  4 ++--
 fs/xfs/xfs_fsops.c     |  4 ++--
 include/linux/blkdev.h |  4 ++--
 8 files changed, 27 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/block/bdev.c b/block/bdev.c
index e4cfb7adb645..a890da1b3adf 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -207,18 +207,20 @@ int sync_blockdev_range(struct block_device *bdev, loff_t lstart, loff_t lend)
 EXPORT_SYMBOL(sync_blockdev_range);
 
 /**
- * freeze_bdev - lock a filesystem and force it into a consistent state
+ * bdev_freeze - lock a filesystem and force it into a consistent state
  * @bdev:	blockdevice to lock
  *
  * If a superblock is found on this device, we take the s_umount semaphore
  * on it to make sure nobody unmounts until the snapshot creation is done.
  * The reference counter (bd_fsfreeze_count) guarantees that only the last
  * unfreeze process can unfreeze the frozen filesystem actually when multiple
- * freeze requests arrive simultaneously. It counts up in freeze_bdev() and
- * count down in thaw_bdev(). When it becomes 0, thaw_bdev() will unfreeze
+ * freeze requests arrive simultaneously. It counts up in bdev_freeze() and
+ * count down in bdev_thaw(). When it becomes 0, thaw_bdev() will unfreeze
  * actually.
+ *
+ * Return: On success zero is returned, negative error code on failure.
  */
-int freeze_bdev(struct block_device *bdev)
+int bdev_freeze(struct block_device *bdev)
 {
 	struct super_block *sb;
 	int error = 0;
@@ -248,15 +250,17 @@ done:
 	mutex_unlock(&bdev->bd_fsfreeze_mutex);
 	return error;
 }
-EXPORT_SYMBOL(freeze_bdev);
+EXPORT_SYMBOL(bdev_freeze);
 
 /**
- * thaw_bdev - unlock filesystem
+ * bdev_thaw - unlock filesystem
  * @bdev:	blockdevice to unlock
  *
- * Unlocks the filesystem and marks it writeable again after freeze_bdev().
+ * Unlocks the filesystem and marks it writeable again after bdev_freeze().
+ *
+ * Return: On success zero is returned, negative error code on failure.
  */
-int thaw_bdev(struct block_device *bdev)
+int bdev_thaw(struct block_device *bdev)
 {
 	struct super_block *sb;
 	int error = -EINVAL;
@@ -285,7 +289,7 @@ out:
 	mutex_unlock(&bdev->bd_fsfreeze_mutex);
 	return error;
 }
-EXPORT_SYMBOL(thaw_bdev);
+EXPORT_SYMBOL(bdev_thaw);
 
 /*
  * pseudo-fs
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 23c32cd1f1d8..8dcabf84d866 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -2675,7 +2675,7 @@ static int lock_fs(struct mapped_device *md)
 
 	WARN_ON(test_bit(DMF_FROZEN, &md->flags));
 
-	r = freeze_bdev(md->disk->part0);
+	r = bdev_freeze(md->disk->part0);
 	if (!r)
 		set_bit(DMF_FROZEN, &md->flags);
 	return r;
@@ -2685,7 +2685,7 @@ static void unlock_fs(struct mapped_device *md)
 {
 	if (!test_bit(DMF_FROZEN, &md->flags))
 		return;
-	thaw_bdev(md->disk->part0);
+	bdev_thaw(md->disk->part0);
 	clear_bit(DMF_FROZEN, &md->flags);
 }
 
diff --git a/fs/bcachefs/fs-ioctl.c b/fs/bcachefs/fs-ioctl.c
index 5a39bcb597a3..45e663342e38 100644
--- a/fs/bcachefs/fs-ioctl.c
+++ b/fs/bcachefs/fs-ioctl.c
@@ -291,14 +291,14 @@ static int bch2_ioc_goingdown(struct bch_fs *c, u32 __user *arg)
 
 	switch (flags) {
 	case FSOP_GOING_FLAGS_DEFAULT:
-		ret = freeze_bdev(c->vfs_sb->s_bdev);
+		ret = bdev_freeze(c->vfs_sb->s_bdev);
 		if (ret)
 			goto err;
 
 		bch2_journal_flush(&c->journal);
 		c->vfs_sb->s_flags |= SB_RDONLY;
 		bch2_fs_emergency_read_only(c);
-		thaw_bdev(c->vfs_sb->s_bdev);
+		bdev_thaw(c->vfs_sb->s_bdev);
 		break;
 
 	case FSOP_GOING_FLAGS_LOGFLUSH:
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 4f931f80cb34..aa6be510eb8f 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -819,11 +819,11 @@ int ext4_force_shutdown(struct super_block *sb, u32 flags)
 
 	switch (flags) {
 	case EXT4_GOING_FLAGS_DEFAULT:
-		ret = freeze_bdev(sb->s_bdev);
+		ret = bdev_freeze(sb->s_bdev);
 		if (ret)
 			return ret;
 		set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
-		thaw_bdev(sb->s_bdev);
+		bdev_thaw(sb->s_bdev);
 		break;
 	case EXT4_GOING_FLAGS_LOGFLUSH:
 		set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index e50363583f01..4580dfefd5e9 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -2239,11 +2239,11 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
 
 	switch (in) {
 	case F2FS_GOING_DOWN_FULLSYNC:
-		ret = freeze_bdev(sb->s_bdev);
+		ret = bdev_freeze(sb->s_bdev);
 		if (ret)
 			goto out;
 		f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_SHUTDOWN);
-		thaw_bdev(sb->s_bdev);
+		bdev_thaw(sb->s_bdev);
 		break;
 	case F2FS_GOING_DOWN_METASYNC:
 		/* do checkpoint only */
diff --git a/fs/super.c b/fs/super.c
index aa43090ea52d..8333aaa878cf 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1224,7 +1224,7 @@ static void do_thaw_all_callback(struct super_block *sb)
 
 	if (locked && sb->s_root) {
 		if (IS_ENABLED(CONFIG_BLOCK))
-			while (sb->s_bdev && !thaw_bdev(sb->s_bdev))
+			while (sb->s_bdev && !bdev_thaw(sb->s_bdev))
 				pr_warn("Emergency Thaw on %pg\n", sb->s_bdev);
 		thaw_super_locked(sb, FREEZE_HOLDER_USERSPACE);
 		return;
@@ -1532,7 +1532,7 @@ int setup_bdev_super(struct super_block *sb, int sb_flags,
 	/*
 	 * Until SB_BORN flag is set, there can be no active superblock
 	 * references and thus no filesystem freezing. get_active_super() will
-	 * just loop waiting for SB_BORN so even freeze_bdev() cannot proceed.
+	 * just loop waiting for SB_BORN so even bdev_freeze() cannot proceed.
 	 *
 	 * It is enough to check bdev was not frozen before we set s_bdev.
 	 */
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 7cb75cb6b8e9..57076a25f17d 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -482,9 +482,9 @@ xfs_fs_goingdown(
 {
 	switch (inflags) {
 	case XFS_FSOP_GOING_FLAGS_DEFAULT: {
-		if (!freeze_bdev(mp->m_super->s_bdev)) {
+		if (!bdev_freeze(mp->m_super->s_bdev)) {
 			xfs_force_shutdown(mp, SHUTDOWN_FORCE_UMOUNT);
-			thaw_bdev(mp->m_super->s_bdev);
+			bdev_thaw(mp->m_super->s_bdev);
 		}
 		break;
 	}
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 51fa7ffdee83..7a3da7f44afb 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1541,8 +1541,8 @@ static inline int early_lookup_bdev(const char *pathname, dev_t *dev)
 }
 #endif /* CONFIG_BLOCK */
 
-int freeze_bdev(struct block_device *bdev);
-int thaw_bdev(struct block_device *bdev);
+int bdev_freeze(struct block_device *bdev);
+int bdev_thaw(struct block_device *bdev);
 
 struct io_comp_batch {
 	struct request *req_list;
-- 
cgit v1.2.3


From a30561a9be69d446d8d542a4f9735fe5ca9573df Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Tue, 24 Oct 2023 15:01:10 +0200
Subject: bdev: add freeze and thaw holder operations

Add block device freeze and thaw holder operations. Follow-up patches
will implement block device freeze and thaw based on stuct
blk_holder_ops.

Link: https://lore.kernel.org/r/20231024-vfs-super-freeze-v2-4-599c19f4faac@kernel.org
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/blkdev.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'include')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 7a3da7f44afb..1bc776335ff8 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1468,6 +1468,16 @@ struct blk_holder_ops {
 	 * Sync the file system mounted on the block device.
 	 */
 	void (*sync)(struct block_device *bdev);
+
+	/*
+	 * Freeze the file system mounted on the block device.
+	 */
+	int (*freeze)(struct block_device *bdev);
+
+	/*
+	 * Thaw the file system mounted on the block device.
+	 */
+	int (*thaw)(struct block_device *bdev);
 };
 
 extern const struct blk_holder_ops fs_holder_ops;
-- 
cgit v1.2.3


From 49ef8832fb1a9e0da0020eb17480fd286433bc13 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Wed, 27 Sep 2023 15:21:16 +0200
Subject: bdev: implement freeze and thaw holder operations

The old method of implementing block device freeze and thaw operations
required us to rely on get_active_super() to walk the list of all
superblocks on the system to find any superblock that might use the
block device. This is wasteful and not very pleasant overall.

Now that we can finally go straight from block device to owning
superblock things become way simpler.

Link: https://lore.kernel.org/r/20231024-vfs-super-freeze-v2-5-599c19f4faac@kernel.org
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 block/bdev.c              | 65 +++++++++++++++----------------
 fs/super.c                | 99 +++++++++++++++++++++++++++++++++++++----------
 include/linux/blk_types.h |  2 +-
 3 files changed, 112 insertions(+), 54 deletions(-)

(limited to 'include')

diff --git a/block/bdev.c b/block/bdev.c
index f27f1a7db2bd..53a2c653a259 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -222,31 +222,27 @@ EXPORT_SYMBOL(sync_blockdev_range);
  */
 int bdev_freeze(struct block_device *bdev)
 {
-	struct super_block *sb;
 	int error = 0;
 
 	mutex_lock(&bdev->bd_fsfreeze_mutex);
-	if (++bdev->bd_fsfreeze_count > 1)
-		goto done;
-
-	sb = get_active_super(bdev);
-	if (!sb)
-		goto sync;
-	if (sb->s_op->freeze_super)
-		error = sb->s_op->freeze_super(sb, FREEZE_HOLDER_USERSPACE);
-	else
-		error = freeze_super(sb, FREEZE_HOLDER_USERSPACE);
-	deactivate_super(sb);
 
-	if (error) {
-		bdev->bd_fsfreeze_count--;
-		goto done;
+	if (atomic_inc_return(&bdev->bd_fsfreeze_count) > 1) {
+		mutex_unlock(&bdev->bd_fsfreeze_mutex);
+		return 0;
+	}
+
+	mutex_lock(&bdev->bd_holder_lock);
+	if (bdev->bd_holder_ops && bdev->bd_holder_ops->freeze) {
+		error = bdev->bd_holder_ops->freeze(bdev);
+		lockdep_assert_not_held(&bdev->bd_holder_lock);
+	} else {
+		mutex_unlock(&bdev->bd_holder_lock);
+		error = sync_blockdev(bdev);
 	}
-	bdev->bd_fsfreeze_sb = sb;
 
-sync:
-	error = sync_blockdev(bdev);
-done:
+	if (error)
+		atomic_dec(&bdev->bd_fsfreeze_count);
+
 	mutex_unlock(&bdev->bd_fsfreeze_mutex);
 	return error;
 }
@@ -262,29 +258,32 @@ EXPORT_SYMBOL(bdev_freeze);
  */
 int bdev_thaw(struct block_device *bdev)
 {
-	struct super_block *sb;
-	int error = -EINVAL;
+	int error = -EINVAL, nr_freeze;
 
 	mutex_lock(&bdev->bd_fsfreeze_mutex);
-	if (!bdev->bd_fsfreeze_count)
+
+	/*
+	 * If this returns < 0 it means that @bd_fsfreeze_count was
+	 * already 0 and no decrement was performed.
+	 */
+	nr_freeze = atomic_dec_if_positive(&bdev->bd_fsfreeze_count);
+	if (nr_freeze < 0)
 		goto out;
 
 	error = 0;
-	if (--bdev->bd_fsfreeze_count > 0)
+	if (nr_freeze > 0)
 		goto out;
 
-	sb = bdev->bd_fsfreeze_sb;
-	if (!sb)
-		goto out;
+	mutex_lock(&bdev->bd_holder_lock);
+	if (bdev->bd_holder_ops && bdev->bd_holder_ops->thaw) {
+		error = bdev->bd_holder_ops->thaw(bdev);
+		lockdep_assert_not_held(&bdev->bd_holder_lock);
+	} else {
+		mutex_unlock(&bdev->bd_holder_lock);
+	}
 
-	if (sb->s_op->thaw_super)
-		error = sb->s_op->thaw_super(sb, FREEZE_HOLDER_USERSPACE);
-	else
-		error = thaw_super(sb, FREEZE_HOLDER_USERSPACE);
 	if (error)
-		bdev->bd_fsfreeze_count++;
-	else
-		bdev->bd_fsfreeze_sb = NULL;
+		atomic_inc(&bdev->bd_fsfreeze_count);
 out:
 	mutex_unlock(&bdev->bd_fsfreeze_mutex);
 	return error;
diff --git a/fs/super.c b/fs/super.c
index 8333aaa878cf..8c943ab1f424 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1440,7 +1440,7 @@ EXPORT_SYMBOL(sget_dev);
  *
  * The function must be called with bdev->bd_holder_lock and releases it.
  */
-static struct super_block *bdev_super_lock_shared(struct block_device *bdev)
+static struct super_block *bdev_super_lock(struct block_device *bdev, bool excl)
 	__releases(&bdev->bd_holder_lock)
 {
 	struct super_block *sb = bdev->bd_holder;
@@ -1454,18 +1454,25 @@ static struct super_block *bdev_super_lock_shared(struct block_device *bdev)
 	spin_lock(&sb_lock);
 	sb->s_count++;
 	spin_unlock(&sb_lock);
+
 	mutex_unlock(&bdev->bd_holder_lock);
 
-	locked = super_lock_shared(sb);
-	if (!locked || !sb->s_root || !(sb->s_flags & SB_ACTIVE)) {
-		put_super(sb);
-		return NULL;
-	}
+	locked = super_lock(sb, excl);
+
 	/*
-	 * The superblock is active and we hold s_umount, we can drop our
-	 * temporary reference now.
-	 */
+	 * If the superblock wasn't already SB_DYING then we hold
+	 * s_umount and can safely drop our temporary reference.
+         */
 	put_super(sb);
+
+	if (!locked)
+		return NULL;
+
+	if (!sb->s_root || !(sb->s_flags & SB_ACTIVE)) {
+		super_unlock(sb, excl);
+		return NULL;
+	}
+
 	return sb;
 }
 
@@ -1473,7 +1480,7 @@ static void fs_bdev_mark_dead(struct block_device *bdev, bool surprise)
 {
 	struct super_block *sb;
 
-	sb = bdev_super_lock_shared(bdev);
+	sb = bdev_super_lock(bdev, false);
 	if (!sb)
 		return;
 
@@ -1491,16 +1498,74 @@ static void fs_bdev_sync(struct block_device *bdev)
 {
 	struct super_block *sb;
 
-	sb = bdev_super_lock_shared(bdev);
+	sb = bdev_super_lock(bdev, false);
 	if (!sb)
 		return;
+
 	sync_filesystem(sb);
 	super_unlock_shared(sb);
 }
 
+static struct super_block *get_bdev_super(struct block_device *bdev)
+{
+	bool active = false;
+	struct super_block *sb;
+
+	sb = bdev_super_lock(bdev, true);
+	if (sb) {
+		active = atomic_inc_not_zero(&sb->s_active);
+		super_unlock_excl(sb);
+	}
+	if (!active)
+		return NULL;
+	return sb;
+}
+
+static int fs_bdev_freeze(struct block_device *bdev)
+{
+	struct super_block *sb;
+	int error = 0;
+
+	lockdep_assert_held(&bdev->bd_fsfreeze_mutex);
+
+	sb = get_bdev_super(bdev);
+	if (!sb)
+		return -EINVAL;
+
+	if (sb->s_op->freeze_super)
+		error = sb->s_op->freeze_super(sb, FREEZE_HOLDER_USERSPACE);
+	else
+		error = freeze_super(sb, FREEZE_HOLDER_USERSPACE);
+	if (!error)
+		error = sync_blockdev(bdev);
+	deactivate_super(sb);
+	return error;
+}
+
+static int fs_bdev_thaw(struct block_device *bdev)
+{
+	struct super_block *sb;
+	int error;
+
+	lockdep_assert_held(&bdev->bd_fsfreeze_mutex);
+
+	sb = get_bdev_super(bdev);
+	if (WARN_ON_ONCE(!sb))
+		return -EINVAL;
+
+	if (sb->s_op->thaw_super)
+		error = sb->s_op->thaw_super(sb, FREEZE_HOLDER_USERSPACE);
+	else
+		error = thaw_super(sb, FREEZE_HOLDER_USERSPACE);
+	deactivate_super(sb);
+	return error;
+}
+
 const struct blk_holder_ops fs_holder_ops = {
 	.mark_dead		= fs_bdev_mark_dead,
 	.sync			= fs_bdev_sync,
+	.freeze			= fs_bdev_freeze,
+	.thaw			= fs_bdev_thaw,
 };
 EXPORT_SYMBOL_GPL(fs_holder_ops);
 
@@ -1530,15 +1595,10 @@ int setup_bdev_super(struct super_block *sb, int sb_flags,
 	}
 
 	/*
-	 * Until SB_BORN flag is set, there can be no active superblock
-	 * references and thus no filesystem freezing. get_active_super() will
-	 * just loop waiting for SB_BORN so even bdev_freeze() cannot proceed.
-	 *
-	 * It is enough to check bdev was not frozen before we set s_bdev.
+	 * It is enough to check bdev was not frozen before we set
+	 * s_bdev as freezing will wait until SB_BORN is set.
 	 */
-	mutex_lock(&bdev->bd_fsfreeze_mutex);
-	if (bdev->bd_fsfreeze_count > 0) {
-		mutex_unlock(&bdev->bd_fsfreeze_mutex);
+	if (atomic_read(&bdev->bd_fsfreeze_count) > 0) {
 		if (fc)
 			warnf(fc, "%pg: Can't mount, blockdev is frozen", bdev);
 		bdev_release(bdev_handle);
@@ -1551,7 +1611,6 @@ int setup_bdev_super(struct super_block *sb, int sb_flags,
 	if (bdev_stable_writes(bdev))
 		sb->s_iflags |= SB_I_STABLE_WRITES;
 	spin_unlock(&sb_lock);
-	mutex_unlock(&bdev->bd_fsfreeze_mutex);
 
 	snprintf(sb->s_id, sizeof(sb->s_id), "%pg", bdev);
 	shrinker_debugfs_rename(sb->s_shrink, "sb-%s:%s", sb->s_type->name,
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index d5c5e59ddbd2..88e1848b0869 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -57,7 +57,7 @@ struct block_device {
 	const struct blk_holder_ops *bd_holder_ops;
 	struct mutex		bd_holder_lock;
 	/* The counter of freeze processes */
-	int			bd_fsfreeze_count;
+	atomic_t		bd_fsfreeze_count;
 	int			bd_holders;
 	struct kobject		*bd_holder_dir;
 
-- 
cgit v1.2.3


From 434f8d8299f2a0c97578f77ab23a70cd0ae56544 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Tue, 24 Oct 2023 15:01:12 +0200
Subject: fs: remove get_active_super()

This function is now unused so remove it. One less function that uses
the global superblock list.

Link: https://lore.kernel.org/r/20231024-vfs-super-freeze-v2-6-599c19f4faac@kernel.org
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/super.c         | 28 ----------------------------
 include/linux/fs.h |  1 -
 2 files changed, 29 deletions(-)

(limited to 'include')

diff --git a/fs/super.c b/fs/super.c
index 8c943ab1f424..b49a49d70450 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1027,34 +1027,6 @@ void iterate_supers_type(struct file_system_type *type,
 
 EXPORT_SYMBOL(iterate_supers_type);
 
-/**
- * get_active_super - get an active reference to the superblock of a device
- * @bdev: device to get the superblock for
- *
- * Scans the superblock list and finds the superblock of the file system
- * mounted on the device given.  Returns the superblock with an active
- * reference or %NULL if none was found.
- */
-struct super_block *get_active_super(struct block_device *bdev)
-{
-	struct super_block *sb;
-
-	if (!bdev)
-		return NULL;
-
-	spin_lock(&sb_lock);
-	list_for_each_entry(sb, &super_blocks, s_list) {
-		if (sb->s_bdev == bdev) {
-			if (!grab_super(sb))
-				return NULL;
-			super_unlock_excl(sb);
-			return sb;
-		}
-	}
-	spin_unlock(&sb_lock);
-	return NULL;
-}
-
 struct super_block *user_get_super(dev_t dev, bool excl)
 {
 	struct super_block *sb;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 98b7a7a8c42e..7dc6c1bf5f55 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3121,7 +3121,6 @@ extern int vfs_readlink(struct dentry *, char __user *, int);
 extern struct file_system_type *get_filesystem(struct file_system_type *fs);
 extern void put_filesystem(struct file_system_type *fs);
 extern struct file_system_type *get_fs_type(const char *name);
-extern struct super_block *get_active_super(struct block_device *bdev);
 extern void drop_super(struct super_block *sb);
 extern void drop_super_exclusive(struct super_block *sb);
 extern void iterate_supers(void (*)(struct super_block *, void *), void *);
-- 
cgit v1.2.3


From 90f95dc415de23267b888f8238c4a19fa0f66b89 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Tue, 24 Oct 2023 15:01:13 +0200
Subject: super: remove bd_fsfreeze_sb

Remove bd_fsfreeze_sb as it's now unused and can be removed. Also move
bd_fsfreeze_count down to not have it weirdly placed in the middle of
the holder fields.

Link: https://lore.kernel.org/r/20231024-vfs-super-freeze-v2-7-599c19f4faac@kernel.org
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Suggested-by: Jan Kara <jack@suse.cz>
Suggested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/blk_types.h | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 88e1848b0869..749203277fee 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -56,14 +56,11 @@ struct block_device {
 	void *			bd_holder;
 	const struct blk_holder_ops *bd_holder_ops;
 	struct mutex		bd_holder_lock;
-	/* The counter of freeze processes */
-	atomic_t		bd_fsfreeze_count;
 	int			bd_holders;
 	struct kobject		*bd_holder_dir;
 
-	/* Mutex for freeze */
-	struct mutex		bd_fsfreeze_mutex;
-	struct super_block	*bd_fsfreeze_sb;
+	atomic_t		bd_fsfreeze_count; /* number of freeze requests */
+	struct mutex		bd_fsfreeze_mutex; /* serialize freeze/thaw */
 
 	struct partition_meta_info *bd_meta_info;
 #ifdef CONFIG_FAIL_MAKE_REQUEST
-- 
cgit v1.2.3


From e419cf3ebaee694a826ddcfb350f1b1ebaf1e599 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Tue, 24 Oct 2023 15:01:16 +0200
Subject: blkdev: comment fs_holder_ops

Add a comment to @fs_holder_ops that @holder must point to a superblock.

Link: https://lore.kernel.org/r/20231024-vfs-super-freeze-v2-10-599c19f4faac@kernel.org
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/blkdev.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 1bc776335ff8..abf71cce785c 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1480,6 +1480,11 @@ struct blk_holder_ops {
 	int (*thaw)(struct block_device *bdev);
 };
 
+/*
+ * For filesystems using @fs_holder_ops, the @holder argument passed to
+ * helpers used to open and claim block devices via
+ * bd_prepare_to_claim() must point to a superblock.
+ */
 extern const struct blk_holder_ops fs_holder_ops;
 
 /*
-- 
cgit v1.2.3


From 7366f8b6fc6aa21c4199cb5d337b023df69745b0 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Sat, 4 Nov 2023 15:00:13 +0100
Subject: fs: handle freezing from multiple devices

Before [1] freezing a filesystems through the block layer only worked
for the main block device as the owning superblock of additional block
devices could not be found. Any filesystem that made use of multiple
block devices would only be freezable via it's main block device.

For example, consider xfs over device mapper with /dev/dm-0 as main
block device and /dev/dm-1 as external log device. Two freeze requests
before [1]:

(1) dmsetup suspend /dev/dm-0 on the main block device

    bdev_freeze(dm-0)
    -> dm-0->bd_fsfreeze_count++
    -> freeze_super(xfs-sb)

    The owning superblock is found and the filesystem gets frozen.
    Returns 0.

(2) dmsetup suspend /dev/dm-1 on the log device

    bdev_freeze(dm-1)
    -> dm-1->bd_fsfreeze_count++

    The owning superblock isn't found and only the block device freeze
    count is incremented. Returns 0.

Two freeze requests after [1]:

(1') dmsetup suspend /dev/dm-0 on the main block device

    bdev_freeze(dm-0)
    -> dm-0->bd_fsfreeze_count++
    -> freeze_super(xfs-sb)

    The owning superblock is found and the filesystem gets frozen.
    Returns 0.

(2') dmsetup suspend /dev/dm-1 on the log device

    bdev_freeze(dm-0)
    -> dm-0->bd_fsfreeze_count++
    -> freeze_super(xfs-sb)

    The owning superblock is found and the filesystem gets frozen.
    Returns -EBUSY.

When (2') is called we initiate a freeze from another block device of
the same superblock. So we increment the bd_fsfreeze_count for that
additional block device. But we now also find the owning superblock for
additional block devices and call freeze_super() again which reports
-EBUSY.

This can be reproduced through xfstests via:

    mkfs.xfs -f -m crc=1,reflink=1,rmapbt=1, -i sparse=1 -lsize=1g,logdev=/dev/nvme1n1p4 /dev/nvme1n1p3
    mkfs.xfs -f -m crc=1,reflink=1,rmapbt=1, -i sparse=1 -lsize=1g,logdev=/dev/nvme1n1p6 /dev/nvme1n1p5

    FSTYP=xfs
    export TEST_DEV=/dev/nvme1n1p3
    export TEST_DIR=/mnt/test
    export TEST_LOGDEV=/dev/nvme1n1p4
    export SCRATCH_DEV=/dev/nvme1n1p5
    export SCRATCH_MNT=/mnt/scratch
    export SCRATCH_LOGDEV=/dev/nvme1n1p6
    export USE_EXTERNAL=yes

    sudo ./check generic/311

Current semantics allow two concurrent freezers: one initiated from
userspace via FREEZE_HOLDER_USERSPACE and one initiated from the kernel
via FREEZE_HOLDER_KERNEL. If there are multiple concurrent freeze
requests from either FREEZE_HOLDER_USERSPACE or FREEZE_HOLDER_KERNEL
-EBUSY is returned.

We need to preserve these semantics because as they are uapi via
FIFREEZE and FITHAW ioctl()s. IOW, freezes don't nest for FIFREEZE and
FITHAW. Other kernels consumers rely on non-nesting freezes as well.

With freezes initiated from the block layer freezes need to nest if the
same superblock is frozen via multiple devices. So we need to start
counting the number of freeze requests.

If FREEZE_MAY_NEST is passed alongside FREEZE_HOLDER_KERNEL or
FREEZE_HOLDER_USERSPACE we allow the caller to nest freeze calls.

To accommodate the old semantics we split the freeze counter into two
counting kernel initiated and userspace initiated freezes separately. We
can then also stop recording FREEZE_HOLDER_* in struct sb_writers.

We also simplify freezing by making all concurrent freezers share a
single active superblock reference count instead of having separate
references for kernel and userspace. I don't see why we would need two
active reference counts. Neither FREEZE_HOLDER_KERNEL nor
FREEZE_HOLDER_USERSPACE can put the active reference as long as they are
concurrent freezers anwyay. That was already true before we allowed
nesting freezes.

Survives various fstests runs with different options including the
reproducer, online scrub, and online repair, fsfreze, and so on. Also
survives blktests.

Link: https://lore.kernel.org/linux-block/87bkccnwxc.fsf@debian-BULLSEYE-live-builder-AMD64
Link: https://lore.kernel.org/r/20231104-vfs-multi-device-freeze-v2-2-5b5b69626eac@kernel.org
Fixes: 288d8706abfc ("bdev: implement freeze and thaw holder operations") [1] # no backport needed
Tested-by: Chandan Babu R <chandanbabu@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reported-by: Chandan Babu R <chandanbabu@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/super.c         | 144 +++++++++++++++++++++++++++++++++++++++++------------
 include/linux/fs.h |  18 ++++++-
 2 files changed, 129 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/fs/super.c b/fs/super.c
index d2b026566dea..aa4e5c11ee32 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1467,6 +1467,21 @@ static struct super_block *get_bdev_super(struct block_device *bdev)
 	return sb;
 }
 
+/**
+ * fs_bdev_freeze - freeze owning filesystem of block device
+ * @bdev: block device
+ *
+ * Freeze the filesystem that owns this block device if it is still
+ * active.
+ *
+ * A filesystem that owns multiple block devices may be frozen from each
+ * block device and won't be unfrozen until all block devices are
+ * unfrozen. Each block device can only freeze the filesystem once as we
+ * nest freezes for block devices in the block layer.
+ *
+ * Return: If the freeze was successful zero is returned. If the freeze
+ *         failed a negative error code is returned.
+ */
 static int fs_bdev_freeze(struct block_device *bdev)
 {
 	struct super_block *sb;
@@ -1479,15 +1494,34 @@ static int fs_bdev_freeze(struct block_device *bdev)
 		return -EINVAL;
 
 	if (sb->s_op->freeze_super)
-		error = sb->s_op->freeze_super(sb, FREEZE_HOLDER_USERSPACE);
+		error = sb->s_op->freeze_super(sb,
+				FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE);
 	else
-		error = freeze_super(sb, FREEZE_HOLDER_USERSPACE);
+		error = freeze_super(sb,
+				FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE);
 	if (!error)
 		error = sync_blockdev(bdev);
 	deactivate_super(sb);
 	return error;
 }
 
+/**
+ * fs_bdev_thaw - thaw owning filesystem of block device
+ * @bdev: block device
+ *
+ * Thaw the filesystem that owns this block device.
+ *
+ * A filesystem that owns multiple block devices may be frozen from each
+ * block device and won't be unfrozen until all block devices are
+ * unfrozen. Each block device can only freeze the filesystem once as we
+ * nest freezes for block devices in the block layer.
+ *
+ * Return: If the thaw was successful zero is returned. If the thaw
+ *         failed a negative error code is returned. If this function
+ *         returns zero it doesn't mean that the filesystem is unfrozen
+ *         as it may have been frozen multiple times (kernel may hold a
+ *         freeze or might be frozen from other block devices).
+ */
 static int fs_bdev_thaw(struct block_device *bdev)
 {
 	struct super_block *sb;
@@ -1500,9 +1534,11 @@ static int fs_bdev_thaw(struct block_device *bdev)
 		return -EINVAL;
 
 	if (sb->s_op->thaw_super)
-		error = sb->s_op->thaw_super(sb, FREEZE_HOLDER_USERSPACE);
+		error = sb->s_op->thaw_super(sb,
+				FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE);
 	else
-		error = thaw_super(sb, FREEZE_HOLDER_USERSPACE);
+		error = thaw_super(sb,
+				FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE);
 	deactivate_super(sb);
 	return error;
 }
@@ -1914,6 +1950,47 @@ static int wait_for_partially_frozen(struct super_block *sb)
 	return ret;
 }
 
+#define FREEZE_HOLDERS (FREEZE_HOLDER_KERNEL | FREEZE_HOLDER_USERSPACE)
+#define FREEZE_FLAGS (FREEZE_HOLDERS | FREEZE_MAY_NEST)
+
+static inline int freeze_inc(struct super_block *sb, enum freeze_holder who)
+{
+	WARN_ON_ONCE((who & ~FREEZE_FLAGS));
+	WARN_ON_ONCE(hweight32(who & FREEZE_HOLDERS) > 1);
+
+	if (who & FREEZE_HOLDER_KERNEL)
+		++sb->s_writers.freeze_kcount;
+	if (who & FREEZE_HOLDER_USERSPACE)
+		++sb->s_writers.freeze_ucount;
+	return sb->s_writers.freeze_kcount + sb->s_writers.freeze_ucount;
+}
+
+static inline int freeze_dec(struct super_block *sb, enum freeze_holder who)
+{
+	WARN_ON_ONCE((who & ~FREEZE_FLAGS));
+	WARN_ON_ONCE(hweight32(who & FREEZE_HOLDERS) > 1);
+
+	if ((who & FREEZE_HOLDER_KERNEL) && sb->s_writers.freeze_kcount)
+		--sb->s_writers.freeze_kcount;
+	if ((who & FREEZE_HOLDER_USERSPACE) && sb->s_writers.freeze_ucount)
+		--sb->s_writers.freeze_ucount;
+	return sb->s_writers.freeze_kcount + sb->s_writers.freeze_ucount;
+}
+
+static inline bool may_freeze(struct super_block *sb, enum freeze_holder who)
+{
+	WARN_ON_ONCE((who & ~FREEZE_FLAGS));
+	WARN_ON_ONCE(hweight32(who & FREEZE_HOLDERS) > 1);
+
+	if (who & FREEZE_HOLDER_KERNEL)
+		return (who & FREEZE_MAY_NEST) ||
+		       sb->s_writers.freeze_kcount == 0;
+	if (who & FREEZE_HOLDER_USERSPACE)
+		return (who & FREEZE_MAY_NEST) ||
+		       sb->s_writers.freeze_ucount == 0;
+	return false;
+}
+
 /**
  * freeze_super - lock the filesystem and force it into a consistent state
  * @sb: the super to lock
@@ -1926,6 +2003,7 @@ static int wait_for_partially_frozen(struct super_block *sb)
  * @who should be:
  * * %FREEZE_HOLDER_USERSPACE if userspace wants to freeze the fs;
  * * %FREEZE_HOLDER_KERNEL if the kernel wants to freeze the fs.
+ * * %FREEZE_MAY_NEST whether nesting freeze and thaw requests is allowed.
  *
  * The @who argument distinguishes between the kernel and userspace trying to
  * freeze the filesystem.  Although there cannot be multiple kernel freezes or
@@ -1933,6 +2011,13 @@ static int wait_for_partially_frozen(struct super_block *sb)
  * userspace can both hold a filesystem frozen.  The filesystem remains frozen
  * until there are no kernel or userspace freezes in effect.
  *
+ * A filesystem may hold multiple devices and thus a filesystems may be
+ * frozen through the block layer via multiple block devices. In this
+ * case the request is marked as being allowed to nest by passing
+ * FREEZE_MAY_NEST. The filesystem remains frozen until all block
+ * devices are unfrozen. If multiple freezes are attempted without
+ * FREEZE_MAY_NEST -EBUSY will be returned.
+ *
  * During this function, sb->s_writers.frozen goes through these values:
  *
  * SB_UNFROZEN: File system is normal, all writes progress as usual.
@@ -1957,6 +2042,9 @@ static int wait_for_partially_frozen(struct super_block *sb)
  * mostly auxiliary for filesystems to verify they do not modify frozen fs.
  *
  * sb->s_writers.frozen is protected by sb->s_umount.
+ *
+ * Return: If the freeze was successful zero is returned. If the freeze
+ *         failed a negative error code is returned.
  */
 int freeze_super(struct super_block *sb, enum freeze_holder who)
 {
@@ -1970,20 +2058,13 @@ int freeze_super(struct super_block *sb, enum freeze_holder who)
 
 retry:
 	if (sb->s_writers.frozen == SB_FREEZE_COMPLETE) {
-		if (sb->s_writers.freeze_holders & who) {
-			deactivate_locked_super(sb);
-			return -EBUSY;
-		}
-
-		WARN_ON(sb->s_writers.freeze_holders == 0);
-
-		/*
-		 * Someone else already holds this type of freeze; share the
-		 * freeze and assign the active ref to the freeze.
-		 */
-		sb->s_writers.freeze_holders |= who;
-		super_unlock_excl(sb);
-		return 0;
+		if (may_freeze(sb, who))
+			ret = !!WARN_ON_ONCE(freeze_inc(sb, who) == 1);
+		else
+			ret = -EBUSY;
+		/* All freezers share a single active reference. */
+		deactivate_locked_super(sb);
+		return ret;
 	}
 
 	if (sb->s_writers.frozen != SB_UNFROZEN) {
@@ -1998,7 +2079,7 @@ retry:
 
 	if (sb_rdonly(sb)) {
 		/* Nothing to do really... */
-		sb->s_writers.freeze_holders |= who;
+		WARN_ON_ONCE(freeze_inc(sb, who) > 1);
 		sb->s_writers.frozen = SB_FREEZE_COMPLETE;
 		wake_up_var(&sb->s_writers.frozen);
 		super_unlock_excl(sb);
@@ -2048,7 +2129,7 @@ retry:
 	 * For debugging purposes so that fs can warn if it sees write activity
 	 * when frozen is set to SB_FREEZE_COMPLETE, and for thaw_super().
 	 */
-	sb->s_writers.freeze_holders |= who;
+	WARN_ON_ONCE(freeze_inc(sb, who) > 1);
 	sb->s_writers.frozen = SB_FREEZE_COMPLETE;
 	wake_up_var(&sb->s_writers.frozen);
 	lockdep_sb_freeze_release(sb);
@@ -2069,21 +2150,15 @@ static int thaw_super_locked(struct super_block *sb, enum freeze_holder who)
 
 	if (sb->s_writers.frozen != SB_FREEZE_COMPLETE)
 		goto out_unlock;
-	if (!(sb->s_writers.freeze_holders & who))
-		goto out_unlock;
 
 	/*
-	 * Freeze is shared with someone else.  Release our hold and drop the
-	 * active ref that freeze_super assigned to the freezer.
+	 * All freezers share a single active reference.
+	 * So just unlock in case there are any left.
 	 */
-	error = 0;
-	if (sb->s_writers.freeze_holders & ~who) {
-		sb->s_writers.freeze_holders &= ~who;
-		goto out_deactivate;
-	}
+	if (freeze_dec(sb, who))
+		goto out_unlock;
 
 	if (sb_rdonly(sb)) {
-		sb->s_writers.freeze_holders &= ~who;
 		sb->s_writers.frozen = SB_UNFROZEN;
 		wake_up_var(&sb->s_writers.frozen);
 		goto out_deactivate;
@@ -2094,13 +2169,13 @@ static int thaw_super_locked(struct super_block *sb, enum freeze_holder who)
 	if (sb->s_op->unfreeze_fs) {
 		error = sb->s_op->unfreeze_fs(sb);
 		if (error) {
-			printk(KERN_ERR "VFS:Filesystem thaw failed\n");
+			pr_err("VFS: Filesystem thaw failed\n");
+			freeze_inc(sb, who);
 			lockdep_sb_freeze_release(sb);
 			goto out_unlock;
 		}
 	}
 
-	sb->s_writers.freeze_holders &= ~who;
 	sb->s_writers.frozen = SB_UNFROZEN;
 	wake_up_var(&sb->s_writers.frozen);
 	sb_freeze_unlock(sb, SB_FREEZE_FS);
@@ -2124,6 +2199,11 @@ out_unlock:
  * @who should be:
  * * %FREEZE_HOLDER_USERSPACE if userspace wants to thaw the fs;
  * * %FREEZE_HOLDER_KERNEL if the kernel wants to thaw the fs.
+ * * %FREEZE_MAY_NEST whether nesting freeze and thaw requests is allowed
+ *
+ * A filesystem may hold multiple devices and thus a filesystems may
+ * have been frozen through the block layer via multiple block devices.
+ * The filesystem remains frozen until all block devices are unfrozen.
  */
 int thaw_super(struct super_block *sb, enum freeze_holder who)
 {
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 7dc6c1bf5f55..b2a3f1c61c19 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1185,7 +1185,8 @@ enum {
 
 struct sb_writers {
 	unsigned short			frozen;		/* Is sb frozen? */
-	unsigned short			freeze_holders;	/* Who froze fs? */
+	int				freeze_kcount;	/* How many kernel freeze requests? */
+	int				freeze_ucount;	/* How many userspace freeze requests? */
 	struct percpu_rw_semaphore	rw_sem[SB_FREEZE_LEVELS];
 };
 
@@ -2051,9 +2052,24 @@ extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
 					struct file *dst_file, loff_t dst_pos,
 					loff_t len, unsigned int remap_flags);
 
+/**
+ * enum freeze_holder - holder of the freeze
+ * @FREEZE_HOLDER_KERNEL: kernel wants to freeze or thaw filesystem
+ * @FREEZE_HOLDER_USERSPACE: userspace wants to freeze or thaw filesystem
+ * @FREEZE_MAY_NEST: whether nesting freeze and thaw requests is allowed
+ *
+ * Indicate who the owner of the freeze or thaw request is and whether
+ * the freeze needs to be exclusive or can nest.
+ * Without @FREEZE_MAY_NEST, multiple freeze and thaw requests from the
+ * same holder aren't allowed. It is however allowed to hold a single
+ * @FREEZE_HOLDER_USERSPACE and a single @FREEZE_HOLDER_KERNEL freeze at
+ * the same time. This is relied upon by some filesystems during online
+ * repair or similar.
+ */
 enum freeze_holder {
 	FREEZE_HOLDER_KERNEL	= (1U << 0),
 	FREEZE_HOLDER_USERSPACE	= (1U << 1),
+	FREEZE_MAY_NEST		= (1U << 2),
 };
 
 struct super_operations {
-- 
cgit v1.2.3


From cd34758c5238ae6976b10fe15bba7031b409c969 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Wed, 1 Nov 2023 18:43:07 +0100
Subject: block: Remove blkdev_get_by_*() functions

blkdev_get_by_*() and blkdev_put() functions are now unused. Remove
them.

Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20231101174325.10596-2-jack@suse.cz
Reviewed-by: Christian Brauner <brauner@kernel.org>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 block/bdev.c           | 94 ++++++++++++++++----------------------------------
 include/linux/blkdev.h |  5 ---
 2 files changed, 30 insertions(+), 69 deletions(-)

(limited to 'include')

diff --git a/block/bdev.c b/block/bdev.c
index 53a2c653a259..0daf14e50dd0 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -732,7 +732,7 @@ void blkdev_put_no_open(struct block_device *bdev)
 }
 	
 /**
- * blkdev_get_by_dev - open a block device by device number
+ * bdev_open_by_dev - open a block device by device number
  * @dev: device number of block device to open
  * @mode: open mode (BLK_OPEN_*)
  * @holder: exclusive holder identifier
@@ -744,32 +744,40 @@ void blkdev_put_no_open(struct block_device *bdev)
  *
  * Use this interface ONLY if you really do not have anything better - i.e. when
  * you are behind a truly sucky interface and all you are given is a device
- * number.  Everything else should use blkdev_get_by_path().
+ * number.  Everything else should use bdev_open_by_path().
  *
  * CONTEXT:
  * Might sleep.
  *
  * RETURNS:
- * Reference to the block_device on success, ERR_PTR(-errno) on failure.
+ * Handle with a reference to the block_device on success, ERR_PTR(-errno) on
+ * failure.
  */
-struct block_device *blkdev_get_by_dev(dev_t dev, blk_mode_t mode, void *holder,
-		const struct blk_holder_ops *hops)
+struct bdev_handle *bdev_open_by_dev(dev_t dev, blk_mode_t mode, void *holder,
+				     const struct blk_holder_ops *hops)
 {
-	bool unblock_events = true;
+	struct bdev_handle *handle = kmalloc(sizeof(struct bdev_handle),
+					     GFP_KERNEL);
 	struct block_device *bdev;
+	bool unblock_events = true;
 	struct gendisk *disk;
 	int ret;
 
+	if (!handle)
+		return ERR_PTR(-ENOMEM);
+
 	ret = devcgroup_check_permission(DEVCG_DEV_BLOCK,
 			MAJOR(dev), MINOR(dev),
 			((mode & BLK_OPEN_READ) ? DEVCG_ACC_READ : 0) |
 			((mode & BLK_OPEN_WRITE) ? DEVCG_ACC_WRITE : 0));
 	if (ret)
-		return ERR_PTR(ret);
+		goto free_handle;
 
 	bdev = blkdev_get_no_open(dev);
-	if (!bdev)
-		return ERR_PTR(-ENXIO);
+	if (!bdev) {
+		ret = -ENXIO;
+		goto free_handle;
+	}
 	disk = bdev->bd_disk;
 
 	if (holder) {
@@ -818,7 +826,10 @@ struct block_device *blkdev_get_by_dev(dev_t dev, blk_mode_t mode, void *holder,
 
 	if (unblock_events)
 		disk_unblock_events(disk);
-	return bdev;
+	handle->bdev = bdev;
+	handle->holder = holder;
+	handle->mode = mode;
+	return handle;
 put_module:
 	module_put(disk->fops->owner);
 abort_claiming:
@@ -828,34 +839,14 @@ abort_claiming:
 	disk_unblock_events(disk);
 put_blkdev:
 	blkdev_put_no_open(bdev);
+free_handle:
+	kfree(handle);
 	return ERR_PTR(ret);
 }
-EXPORT_SYMBOL(blkdev_get_by_dev);
-
-struct bdev_handle *bdev_open_by_dev(dev_t dev, blk_mode_t mode, void *holder,
-				     const struct blk_holder_ops *hops)
-{
-	struct bdev_handle *handle = kmalloc(sizeof(*handle), GFP_KERNEL);
-	struct block_device *bdev;
-
-	if (!handle)
-		return ERR_PTR(-ENOMEM);
-	bdev = blkdev_get_by_dev(dev, mode, holder, hops);
-	if (IS_ERR(bdev)) {
-		kfree(handle);
-		return ERR_CAST(bdev);
-	}
-	handle->bdev = bdev;
-	handle->holder = holder;
-	if (holder)
-		mode |= BLK_OPEN_EXCL;
-	handle->mode = mode;
-	return handle;
-}
 EXPORT_SYMBOL(bdev_open_by_dev);
 
 /**
- * blkdev_get_by_path - open a block device by name
+ * bdev_open_by_path - open a block device by name
  * @path: path to the block device to open
  * @mode: open mode (BLK_OPEN_*)
  * @holder: exclusive holder identifier
@@ -869,29 +860,9 @@ EXPORT_SYMBOL(bdev_open_by_dev);
  * Might sleep.
  *
  * RETURNS:
- * Reference to the block_device on success, ERR_PTR(-errno) on failure.
+ * Handle with a reference to the block_device on success, ERR_PTR(-errno) on
+ * failure.
  */
-struct block_device *blkdev_get_by_path(const char *path, blk_mode_t mode,
-		void *holder, const struct blk_holder_ops *hops)
-{
-	struct block_device *bdev;
-	dev_t dev;
-	int error;
-
-	error = lookup_bdev(path, &dev);
-	if (error)
-		return ERR_PTR(error);
-
-	bdev = blkdev_get_by_dev(dev, mode, holder, hops);
-	if (!IS_ERR(bdev) && (mode & BLK_OPEN_WRITE) && bdev_read_only(bdev)) {
-		blkdev_put(bdev, holder);
-		return ERR_PTR(-EACCES);
-	}
-
-	return bdev;
-}
-EXPORT_SYMBOL(blkdev_get_by_path);
-
 struct bdev_handle *bdev_open_by_path(const char *path, blk_mode_t mode,
 		void *holder, const struct blk_holder_ops *hops)
 {
@@ -914,8 +885,9 @@ struct bdev_handle *bdev_open_by_path(const char *path, blk_mode_t mode,
 }
 EXPORT_SYMBOL(bdev_open_by_path);
 
-void blkdev_put(struct block_device *bdev, void *holder)
+void bdev_release(struct bdev_handle *handle)
 {
+	struct block_device *bdev = handle->bdev;
 	struct gendisk *disk = bdev->bd_disk;
 
 	/*
@@ -929,8 +901,8 @@ void blkdev_put(struct block_device *bdev, void *holder)
 		sync_blockdev(bdev);
 
 	mutex_lock(&disk->open_mutex);
-	if (holder)
-		bd_end_claim(bdev, holder);
+	if (handle->holder)
+		bd_end_claim(bdev, handle->holder);
 
 	/*
 	 * Trigger event checking and tell drivers to flush MEDIA_CHANGE
@@ -947,12 +919,6 @@ void blkdev_put(struct block_device *bdev, void *holder)
 
 	module_put(disk->fops->owner);
 	blkdev_put_no_open(bdev);
-}
-EXPORT_SYMBOL(blkdev_put);
-
-void bdev_release(struct bdev_handle *handle)
-{
-	blkdev_put(handle->bdev, handle->holder);
 	kfree(handle);
 }
 EXPORT_SYMBOL(bdev_release);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index abf71cce785c..7afc10315dd5 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1500,10 +1500,6 @@ struct bdev_handle {
 	blk_mode_t mode;
 };
 
-struct block_device *blkdev_get_by_dev(dev_t dev, blk_mode_t mode, void *holder,
-		const struct blk_holder_ops *hops);
-struct block_device *blkdev_get_by_path(const char *path, blk_mode_t mode,
-		void *holder, const struct blk_holder_ops *hops);
 struct bdev_handle *bdev_open_by_dev(dev_t dev, blk_mode_t mode, void *holder,
 		const struct blk_holder_ops *hops);
 struct bdev_handle *bdev_open_by_path(const char *path, blk_mode_t mode,
@@ -1511,7 +1507,6 @@ struct bdev_handle *bdev_open_by_path(const char *path, blk_mode_t mode,
 int bd_prepare_to_claim(struct block_device *bdev, void *holder,
 		const struct blk_holder_ops *hops);
 void bd_abort_claiming(struct block_device *bdev, void *holder);
-void blkdev_put(struct block_device *bdev, void *holder);
 void bdev_release(struct bdev_handle *handle);
 
 /* just for blk-cgroup, don't use elsewhere */
-- 
cgit v1.2.3


From ed5cc702d311c14b653323d76062b0294effa66e Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Wed, 1 Nov 2023 18:43:08 +0100
Subject: block: Add config option to not allow writing to mounted devices

Writing to mounted devices is dangerous and can lead to filesystem
corruption as well as crashes. Furthermore syzbot comes with more and
more involved examples how to corrupt block device under a mounted
filesystem leading to kernel crashes and reports we can do nothing
about. Add tracking of writers to each block device and a kernel cmdline
argument which controls whether other writeable opens to block devices
open with BLK_OPEN_RESTRICT_WRITES flag are allowed. We will make
filesystems use this flag for used devices.

Note that this effectively only prevents modification of the particular
block device's page cache by other writers. The actual device content
can still be modified by other means - e.g. by issuing direct scsi
commands, by doing writes through devices lower in the storage stack
(e.g. in case loop devices, DM, or MD are involved) etc. But blocking
direct modifications of the block device page cache is enough to give
filesystems a chance to perform data validation when loading data from
the underlying storage and thus prevent kernel crashes.

Syzbot can use this cmdline argument option to avoid uninteresting
crashes. Also users whose userspace setup does not need writing to
mounted block devices can set this option for hardening.

Link: https://lore.kernel.org/all/60788e5d-5c7c-1142-e554-c21d709acfd9@linaro.org
Signed-off-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20231101174325.10596-3-jack@suse.cz
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 block/Kconfig             | 20 +++++++++++++
 block/bdev.c              | 75 ++++++++++++++++++++++++++++++++++++++++++++++-
 include/linux/blk_types.h |  1 +
 include/linux/blkdev.h    |  2 ++
 4 files changed, 97 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/block/Kconfig b/block/Kconfig
index 55ae2286a4de..1de4682d48cc 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -78,6 +78,26 @@ config BLK_DEV_INTEGRITY_T10
 	select CRC_T10DIF
 	select CRC64_ROCKSOFT
 
+config BLK_DEV_WRITE_MOUNTED
+	bool "Allow writing to mounted block devices"
+	default y
+	help
+	When a block device is mounted, writing to its buffer cache is very
+	likely going to cause filesystem corruption. It is also rather easy to
+	crash the kernel in this way since the filesystem has no practical way
+	of detecting these writes to buffer cache and verifying its metadata
+	integrity. However there are some setups that need this capability
+	like running fsck on read-only mounted root device, modifying some
+	features on mounted ext4 filesystem, and similar. If you say N, the
+	kernel will prevent processes from writing to block devices that are
+	mounted by filesystems which provides some more protection from runaway
+	privileged processes and generally makes it much harder to crash
+	filesystem drivers. Note however that this does not prevent
+	underlying device(s) from being modified by other means, e.g. by
+	directly submitting SCSI commands or through access to lower layers of
+	storage stack. If in doubt, say Y. The configuration can be overridden
+	with the bdev_allow_write_mounted boot option.
+
 config BLK_DEV_ZONED
 	bool "Zoned block device support"
 	select MQ_IOSCHED_DEADLINE
diff --git a/block/bdev.c b/block/bdev.c
index 0daf14e50dd0..fc8d28d77495 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -30,6 +30,9 @@
 #include "../fs/internal.h"
 #include "blk.h"
 
+/* Should we allow writing to mounted block devices? */
+static bool bdev_allow_write_mounted = IS_ENABLED(CONFIG_BLK_DEV_WRITE_MOUNTED);
+
 struct bdev_inode {
 	struct block_device bdev;
 	struct inode vfs_inode;
@@ -730,7 +733,58 @@ void blkdev_put_no_open(struct block_device *bdev)
 {
 	put_device(&bdev->bd_device);
 }
-	
+
+static bool bdev_writes_blocked(struct block_device *bdev)
+{
+	return bdev->bd_writers == -1;
+}
+
+static void bdev_block_writes(struct block_device *bdev)
+{
+	bdev->bd_writers = -1;
+}
+
+static void bdev_unblock_writes(struct block_device *bdev)
+{
+	bdev->bd_writers = 0;
+}
+
+static bool bdev_may_open(struct block_device *bdev, blk_mode_t mode)
+{
+	if (bdev_allow_write_mounted)
+		return true;
+	/* Writes blocked? */
+	if (mode & BLK_OPEN_WRITE && bdev_writes_blocked(bdev))
+		return false;
+	if (mode & BLK_OPEN_RESTRICT_WRITES && bdev->bd_writers > 0)
+		return false;
+	return true;
+}
+
+static void bdev_claim_write_access(struct block_device *bdev, blk_mode_t mode)
+{
+	if (bdev_allow_write_mounted)
+		return;
+
+	/* Claim exclusive or shared write access. */
+	if (mode & BLK_OPEN_RESTRICT_WRITES)
+		bdev_block_writes(bdev);
+	else if (mode & BLK_OPEN_WRITE)
+		bdev->bd_writers++;
+}
+
+static void bdev_yield_write_access(struct block_device *bdev, blk_mode_t mode)
+{
+	if (bdev_allow_write_mounted)
+		return;
+
+	/* Yield exclusive or shared write access. */
+	if (mode & BLK_OPEN_RESTRICT_WRITES)
+		bdev_unblock_writes(bdev);
+	else if (mode & BLK_OPEN_WRITE)
+		bdev->bd_writers--;
+}
+
 /**
  * bdev_open_by_dev - open a block device by device number
  * @dev: device number of block device to open
@@ -773,6 +827,10 @@ struct bdev_handle *bdev_open_by_dev(dev_t dev, blk_mode_t mode, void *holder,
 	if (ret)
 		goto free_handle;
 
+	/* Blocking writes requires exclusive opener */
+	if (mode & BLK_OPEN_RESTRICT_WRITES && !holder)
+		return ERR_PTR(-EINVAL);
+
 	bdev = blkdev_get_no_open(dev);
 	if (!bdev) {
 		ret = -ENXIO;
@@ -800,12 +858,16 @@ struct bdev_handle *bdev_open_by_dev(dev_t dev, blk_mode_t mode, void *holder,
 		goto abort_claiming;
 	if (!try_module_get(disk->fops->owner))
 		goto abort_claiming;
+	ret = -EBUSY;
+	if (!bdev_may_open(bdev, mode))
+		goto abort_claiming;
 	if (bdev_is_partition(bdev))
 		ret = blkdev_get_part(bdev, mode);
 	else
 		ret = blkdev_get_whole(bdev, mode);
 	if (ret)
 		goto put_module;
+	bdev_claim_write_access(bdev, mode);
 	if (holder) {
 		bd_finish_claiming(bdev, holder, hops);
 
@@ -901,6 +963,8 @@ void bdev_release(struct bdev_handle *handle)
 		sync_blockdev(bdev);
 
 	mutex_lock(&disk->open_mutex);
+	bdev_yield_write_access(bdev, handle->mode);
+
 	if (handle->holder)
 		bd_end_claim(bdev, handle->holder);
 
@@ -1069,3 +1133,12 @@ void bdev_statx_dioalign(struct inode *inode, struct kstat *stat)
 
 	blkdev_put_no_open(bdev);
 }
+
+static int __init setup_bdev_allow_write_mounted(char *str)
+{
+	if (kstrtobool(str, &bdev_allow_write_mounted))
+		pr_warn("Invalid option string for bdev_allow_write_mounted:"
+			" '%s'\n", str);
+	return 1;
+}
+__setup("bdev_allow_write_mounted=", setup_bdev_allow_write_mounted);
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 749203277fee..52e264d5a830 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -66,6 +66,7 @@ struct block_device {
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 	bool			bd_make_it_fail;
 #endif
+	int			bd_writers;
 	/*
 	 * keep this out-of-line as it's both big and not needed in the fast
 	 * path
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 7afc10315dd5..0e0c0186aa32 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -124,6 +124,8 @@ typedef unsigned int __bitwise blk_mode_t;
 #define BLK_OPEN_NDELAY		((__force blk_mode_t)(1 << 3))
 /* open for "writes" only for ioctls (specialy hack for floppy.c) */
 #define BLK_OPEN_WRITE_IOCTL	((__force blk_mode_t)(1 << 4))
+/* open is exclusive wrt all other BLK_OPEN_WRITE opens to the device */
+#define BLK_OPEN_RESTRICT_WRITES	((__force blk_mode_t)(1 << 5))
 
 struct gendisk {
 	/*
-- 
cgit v1.2.3


From 6f861765464f43a71462d52026fbddfc858239a5 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Wed, 1 Nov 2023 18:43:10 +0100
Subject: fs: Block writes to mounted block devices

Ask block layer to block writes to block devices mounted by filesystems.

Signed-off-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20231101174325.10596-5-jack@suse.cz
Reviewed-by: Christian Brauner <brauner@kernel.org>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/blkdev.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 0e0c0186aa32..9f6c3373f9fc 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1494,7 +1494,8 @@ extern const struct blk_holder_ops fs_holder_ops;
  * as stored in sb->s_flags.
  */
 #define sb_open_mode(flags) \
-	(BLK_OPEN_READ | (((flags) & SB_RDONLY) ? 0 : BLK_OPEN_WRITE))
+	(BLK_OPEN_READ | BLK_OPEN_RESTRICT_WRITES | \
+	 (((flags) & SB_RDONLY) ? 0 : BLK_OPEN_WRITE))
 
 struct bdev_handle {
 	struct block_device *bdev;
-- 
cgit v1.2.3


From db3db63b1d17c98f69e894edaa2b0b364ecde7a9 Mon Sep 17 00:00:00 2001
From: Mateusz Guzik <mjguzik@gmail.com>
Date: Sat, 4 Nov 2023 23:11:17 +0100
Subject: vfs: remove a redundant might_sleep in wait_on_inode

wait_on_bit already does it.

Signed-off-by: Mateusz Guzik <mjguzik@gmail.com>
Link: https://lore.kernel.org/r/20231104221117.2584708-1-mjguzik@gmail.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/writeback.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 083387c00f0c..6d0a14f7019d 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -193,7 +193,6 @@ void inode_io_list_del(struct inode *inode);
 /* writeback.h requires fs.h; it, too, is not included from here. */
 static inline void wait_on_inode(struct inode *inode)
 {
-	might_sleep();
 	wait_on_bit(&inode->i_state, __I_NEW, TASK_UNINTERRUPTIBLE);
 }
 
-- 
cgit v1.2.3


From 446e2305827b76e8081057ce56bbd2703b4da8a9 Mon Sep 17 00:00:00 2001
From: Kory Maincent <kory.maincent@bootlin.com>
Date: Tue, 14 Nov 2023 12:28:29 +0100
Subject: net: Convert PHYs hwtstamp callback to use kernel_hwtstamp_config

The PHYs hwtstamp callback are still getting the timestamp config from
ifreq and using copy_from/to_user.
Get rid of these functions by using timestamp configuration in parameter.
This also allow to move on to kernel_hwtstamp_config and be similar to
net devices using the new ndo_hwstamp_get/set.

This adds the possibility to manipulate the timestamp configuration
from the kernel which was not possible with the copy_from/to_user.

Signed-off-by: Kory Maincent <kory.maincent@bootlin.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/bcm-phy-ptp.c     | 15 ++++++---------
 drivers/net/phy/dp83640.c         | 24 +++++++++++-------------
 drivers/net/phy/micrel.c          | 38 +++++++++++++++++---------------------
 drivers/net/phy/mscc/mscc_ptp.c   | 18 ++++++++----------
 drivers/net/phy/nxp-c45-tja11xx.c | 17 +++++++----------
 drivers/net/phy/phy.c             | 21 +++++++++++++++++++--
 drivers/ptp/ptp_ines.c            | 16 +++++++---------
 include/linux/mii_timestamper.h   |  4 +++-
 include/linux/phy.h               |  6 ++++--
 9 files changed, 82 insertions(+), 77 deletions(-)

(limited to 'include')

diff --git a/drivers/net/phy/bcm-phy-ptp.c b/drivers/net/phy/bcm-phy-ptp.c
index cb4b91af5e17..617d384d4551 100644
--- a/drivers/net/phy/bcm-phy-ptp.c
+++ b/drivers/net/phy/bcm-phy-ptp.c
@@ -782,16 +782,13 @@ out:
 }
 
 static int bcm_ptp_hwtstamp(struct mii_timestamper *mii_ts,
-			    struct ifreq *ifr)
+			    struct kernel_hwtstamp_config *cfg,
+			    struct netlink_ext_ack *extack)
 {
 	struct bcm_ptp_private *priv = mii2priv(mii_ts);
-	struct hwtstamp_config cfg;
 	u16 mode, ctrl;
 
-	if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
-		return -EFAULT;
-
-	switch (cfg.rx_filter) {
+	switch (cfg->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		priv->hwts_rx = false;
 		break;
@@ -804,14 +801,14 @@ static int bcm_ptp_hwtstamp(struct mii_timestamper *mii_ts,
 	case HWTSTAMP_FILTER_PTP_V2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
-		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
+		cfg->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
 		priv->hwts_rx = true;
 		break;
 	default:
 		return -ERANGE;
 	}
 
-	priv->tx_type = cfg.tx_type;
+	priv->tx_type = cfg->tx_type;
 
 	ctrl  = priv->hwts_rx ? SLICE_RX_EN : 0;
 	ctrl |= priv->tx_type != HWTSTAMP_TX_OFF ? SLICE_TX_EN : 0;
@@ -840,7 +837,7 @@ static int bcm_ptp_hwtstamp(struct mii_timestamper *mii_ts,
 	/* purge existing data */
 	skb_queue_purge(&priv->tx_queue);
 
-	return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
+	return 0;
 }
 
 static int bcm_ptp_ts_info(struct mii_timestamper *mii_ts,
diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index 2657be7cc049..5c42c47dc564 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -1207,22 +1207,20 @@ static irqreturn_t dp83640_handle_interrupt(struct phy_device *phydev)
 	return IRQ_HANDLED;
 }
 
-static int dp83640_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
+static int dp83640_hwtstamp(struct mii_timestamper *mii_ts,
+			    struct kernel_hwtstamp_config *cfg,
+			    struct netlink_ext_ack *extack)
 {
 	struct dp83640_private *dp83640 =
 		container_of(mii_ts, struct dp83640_private, mii_ts);
-	struct hwtstamp_config cfg;
 	u16 txcfg0, rxcfg0;
 
-	if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
-		return -EFAULT;
-
-	if (cfg.tx_type < 0 || cfg.tx_type > HWTSTAMP_TX_ONESTEP_SYNC)
+	if (cfg->tx_type < 0 || cfg->tx_type > HWTSTAMP_TX_ONESTEP_SYNC)
 		return -ERANGE;
 
-	dp83640->hwts_tx_en = cfg.tx_type;
+	dp83640->hwts_tx_en = cfg->tx_type;
 
-	switch (cfg.rx_filter) {
+	switch (cfg->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		dp83640->hwts_rx_en = 0;
 		dp83640->layer = 0;
@@ -1234,7 +1232,7 @@ static int dp83640_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
 		dp83640->hwts_rx_en = 1;
 		dp83640->layer = PTP_CLASS_L4;
 		dp83640->version = PTP_CLASS_V1;
-		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
+		cfg->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
@@ -1242,7 +1240,7 @@ static int dp83640_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
 		dp83640->hwts_rx_en = 1;
 		dp83640->layer = PTP_CLASS_L4;
 		dp83640->version = PTP_CLASS_V2;
-		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT;
+		cfg->rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT;
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
@@ -1250,7 +1248,7 @@ static int dp83640_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
 		dp83640->hwts_rx_en = 1;
 		dp83640->layer = PTP_CLASS_L2;
 		dp83640->version = PTP_CLASS_V2;
-		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT;
+		cfg->rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT;
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
@@ -1258,7 +1256,7 @@ static int dp83640_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
 		dp83640->hwts_rx_en = 1;
 		dp83640->layer = PTP_CLASS_L4 | PTP_CLASS_L2;
 		dp83640->version = PTP_CLASS_V2;
-		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
+		cfg->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
 		break;
 	default:
 		return -ERANGE;
@@ -1292,7 +1290,7 @@ static int dp83640_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
 
 	mutex_unlock(&dp83640->clock->extreg_lock);
 
-	return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
+	return 0;
 }
 
 static void rx_timestamp_work(struct work_struct *work)
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 08e3915001c3..99af1e500c6c 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -2395,24 +2395,22 @@ static void lan8814_flush_fifo(struct phy_device *phydev, bool egress)
 	lanphy_read_page_reg(phydev, 5, PTP_TSU_INT_STS);
 }
 
-static int lan8814_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
+static int lan8814_hwtstamp(struct mii_timestamper *mii_ts,
+			    struct kernel_hwtstamp_config *config,
+			    struct netlink_ext_ack *extack)
 {
 	struct kszphy_ptp_priv *ptp_priv =
 			  container_of(mii_ts, struct kszphy_ptp_priv, mii_ts);
 	struct phy_device *phydev = ptp_priv->phydev;
 	struct lan8814_shared_priv *shared = phydev->shared->priv;
 	struct lan8814_ptp_rx_ts *rx_ts, *tmp;
-	struct hwtstamp_config config;
 	int txcfg = 0, rxcfg = 0;
 	int pkt_ts_enable;
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
+	ptp_priv->hwts_tx_type = config->tx_type;
+	ptp_priv->rx_filter = config->rx_filter;
 
-	ptp_priv->hwts_tx_type = config.tx_type;
-	ptp_priv->rx_filter = config.rx_filter;
-
-	switch (config.rx_filter) {
+	switch (config->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		ptp_priv->layer = 0;
 		ptp_priv->version = 0;
@@ -2458,13 +2456,13 @@ static int lan8814_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
 		lanphy_write_page_reg(ptp_priv->phydev, 5, PTP_TX_MOD,
 				      PTP_TX_MOD_TX_PTP_SYNC_TS_INSERT_);
 
-	if (config.rx_filter != HWTSTAMP_FILTER_NONE)
+	if (config->rx_filter != HWTSTAMP_FILTER_NONE)
 		lan8814_config_ts_intr(ptp_priv->phydev, true);
 	else
 		lan8814_config_ts_intr(ptp_priv->phydev, false);
 
 	mutex_lock(&shared->shared_lock);
-	if (config.rx_filter != HWTSTAMP_FILTER_NONE)
+	if (config->rx_filter != HWTSTAMP_FILTER_NONE)
 		shared->ref++;
 	else
 		shared->ref--;
@@ -2488,7 +2486,7 @@ static int lan8814_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
 	lan8814_flush_fifo(ptp_priv->phydev, false);
 	lan8814_flush_fifo(ptp_priv->phydev, true);
 
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? -EFAULT : 0;
+	return 0;
 }
 
 static void lan8814_txtstamp(struct mii_timestamper *mii_ts,
@@ -3703,21 +3701,19 @@ static void lan8841_ptp_enable_processing(struct kszphy_ptp_priv *ptp_priv,
 #define LAN8841_PTP_TX_TIMESTAMP_EN		443
 #define LAN8841_PTP_TX_MOD			445
 
-static int lan8841_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
+static int lan8841_hwtstamp(struct mii_timestamper *mii_ts,
+			    struct kernel_hwtstamp_config *config,
+			    struct netlink_ext_ack *extack)
 {
 	struct kszphy_ptp_priv *ptp_priv = container_of(mii_ts, struct kszphy_ptp_priv, mii_ts);
 	struct phy_device *phydev = ptp_priv->phydev;
-	struct hwtstamp_config config;
 	int txcfg = 0, rxcfg = 0;
 	int pkt_ts_enable;
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
+	ptp_priv->hwts_tx_type = config->tx_type;
+	ptp_priv->rx_filter = config->rx_filter;
 
-	ptp_priv->hwts_tx_type = config.tx_type;
-	ptp_priv->rx_filter = config.rx_filter;
-
-	switch (config.rx_filter) {
+	switch (config->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		ptp_priv->layer = 0;
 		ptp_priv->version = 0;
@@ -3771,13 +3767,13 @@ static int lan8841_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
 
 	/* Now enable/disable the timestamping */
 	lan8841_ptp_enable_processing(ptp_priv,
-				      config.rx_filter != HWTSTAMP_FILTER_NONE);
+				      config->rx_filter != HWTSTAMP_FILTER_NONE);
 
 	skb_queue_purge(&ptp_priv->tx_queue);
 
 	lan8841_ptp_flush_fifo(ptp_priv);
 
-	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? -EFAULT : 0;
+	return 0;
 }
 
 static bool lan8841_rxtstamp(struct mii_timestamper *mii_ts,
diff --git a/drivers/net/phy/mscc/mscc_ptp.c b/drivers/net/phy/mscc/mscc_ptp.c
index cf728bfd83e2..eb0b032cb613 100644
--- a/drivers/net/phy/mscc/mscc_ptp.c
+++ b/drivers/net/phy/mscc/mscc_ptp.c
@@ -1045,19 +1045,17 @@ static void vsc85xx_ts_reset_fifo(struct phy_device *phydev)
 			     val);
 }
 
-static int vsc85xx_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
+static int vsc85xx_hwtstamp(struct mii_timestamper *mii_ts,
+			    struct kernel_hwtstamp_config *cfg,
+			    struct netlink_ext_ack *extack)
 {
 	struct vsc8531_private *vsc8531 =
 		container_of(mii_ts, struct vsc8531_private, mii_ts);
 	struct phy_device *phydev = vsc8531->ptp->phydev;
-	struct hwtstamp_config cfg;
 	bool one_step = false;
 	u32 val;
 
-	if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
-		return -EFAULT;
-
-	switch (cfg.tx_type) {
+	switch (cfg->tx_type) {
 	case HWTSTAMP_TX_ONESTEP_SYNC:
 		one_step = true;
 		break;
@@ -1069,9 +1067,9 @@ static int vsc85xx_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
 		return -ERANGE;
 	}
 
-	vsc8531->ptp->tx_type = cfg.tx_type;
+	vsc8531->ptp->tx_type = cfg->tx_type;
 
-	switch (cfg.rx_filter) {
+	switch (cfg->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
@@ -1084,7 +1082,7 @@ static int vsc85xx_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
 		return -ERANGE;
 	}
 
-	vsc8531->ptp->rx_filter = cfg.rx_filter;
+	vsc8531->ptp->rx_filter = cfg->rx_filter;
 
 	mutex_lock(&vsc8531->ts_lock);
 
@@ -1132,7 +1130,7 @@ static int vsc85xx_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
 	vsc8531->ptp->configured = 1;
 	mutex_unlock(&vsc8531->ts_lock);
 
-	return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
+	return 0;
 }
 
 static int vsc85xx_ts_info(struct mii_timestamper *mii_ts,
diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c
index 7ab080ff02df..780ad353cf55 100644
--- a/drivers/net/phy/nxp-c45-tja11xx.c
+++ b/drivers/net/phy/nxp-c45-tja11xx.c
@@ -1022,24 +1022,21 @@ static bool nxp_c45_rxtstamp(struct mii_timestamper *mii_ts,
 }
 
 static int nxp_c45_hwtstamp(struct mii_timestamper *mii_ts,
-			    struct ifreq *ifreq)
+			    struct kernel_hwtstamp_config *cfg,
+			    struct netlink_ext_ack *extack)
 {
 	struct nxp_c45_phy *priv = container_of(mii_ts, struct nxp_c45_phy,
 						mii_ts);
 	struct phy_device *phydev = priv->phydev;
 	const struct nxp_c45_phy_data *data;
-	struct hwtstamp_config cfg;
 
-	if (copy_from_user(&cfg, ifreq->ifr_data, sizeof(cfg)))
-		return -EFAULT;
-
-	if (cfg.tx_type < 0 || cfg.tx_type > HWTSTAMP_TX_ON)
+	if (cfg->tx_type < 0 || cfg->tx_type > HWTSTAMP_TX_ON)
 		return -ERANGE;
 
 	data = nxp_c45_get_data(phydev);
-	priv->hwts_tx = cfg.tx_type;
+	priv->hwts_tx = cfg->tx_type;
 
-	switch (cfg.rx_filter) {
+	switch (cfg->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		priv->hwts_rx = 0;
 		break;
@@ -1047,7 +1044,7 @@ static int nxp_c45_hwtstamp(struct mii_timestamper *mii_ts,
 	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
 		priv->hwts_rx = 1;
-		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT;
+		cfg->rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT;
 		break;
 	default:
 		return -ERANGE;
@@ -1074,7 +1071,7 @@ static int nxp_c45_hwtstamp(struct mii_timestamper *mii_ts,
 		nxp_c45_clear_reg_field(phydev, &data->regmap->irq_egr_ts_en);
 
 nxp_c45_no_ptp_irq:
-	return copy_to_user(ifreq->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
+	return 0;
 }
 
 static int nxp_c45_ts_info(struct mii_timestamper *mii_ts,
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index a5fa077650e8..d058316666ba 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -325,9 +325,13 @@ EXPORT_SYMBOL(phy_ethtool_ksettings_get);
 int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd)
 {
 	struct mii_ioctl_data *mii_data = if_mii(ifr);
+	struct kernel_hwtstamp_config kernel_cfg;
+	struct netlink_ext_ack extack = {};
 	u16 val = mii_data->val_in;
 	bool change_autoneg = false;
+	struct hwtstamp_config cfg;
 	int prtad, devad;
+	int ret;
 
 	switch (cmd) {
 	case SIOCGMIIPHY:
@@ -411,8 +415,21 @@ int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd)
 		return 0;
 
 	case SIOCSHWTSTAMP:
-		if (phydev->mii_ts && phydev->mii_ts->hwtstamp)
-			return phydev->mii_ts->hwtstamp(phydev->mii_ts, ifr);
+		if (phydev->mii_ts && phydev->mii_ts->hwtstamp) {
+			if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
+				return -EFAULT;
+
+			hwtstamp_config_to_kernel(&kernel_cfg, &cfg);
+			ret = phydev->mii_ts->hwtstamp(phydev->mii_ts, &kernel_cfg, &extack);
+			if (ret)
+				return ret;
+
+			hwtstamp_config_from_kernel(&cfg, &kernel_cfg);
+			if (copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)))
+				return -EFAULT;
+
+			return 0;
+		}
 		fallthrough;
 
 	default:
diff --git a/drivers/ptp/ptp_ines.c b/drivers/ptp/ptp_ines.c
index ed215b458183..1d2940a78455 100644
--- a/drivers/ptp/ptp_ines.c
+++ b/drivers/ptp/ptp_ines.c
@@ -328,17 +328,15 @@ static u64 ines_find_txts(struct ines_port *port, struct sk_buff *skb)
 	return ns;
 }
 
-static int ines_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
+static int ines_hwtstamp(struct mii_timestamper *mii_ts,
+			 struct kernel_hwtstamp_config *cfg,
+			 struct netlink_ext_ack *extack)
 {
 	struct ines_port *port = container_of(mii_ts, struct ines_port, mii_ts);
 	u32 cm_one_step = 0, port_conf, ts_stat_rx, ts_stat_tx;
-	struct hwtstamp_config cfg;
 	unsigned long flags;
 
-	if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
-		return -EFAULT;
-
-	switch (cfg.tx_type) {
+	switch (cfg->tx_type) {
 	case HWTSTAMP_TX_OFF:
 		ts_stat_tx = 0;
 		break;
@@ -353,7 +351,7 @@ static int ines_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
 		return -ERANGE;
 	}
 
-	switch (cfg.rx_filter) {
+	switch (cfg->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		ts_stat_rx = 0;
 		break;
@@ -372,7 +370,7 @@ static int ines_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
 		ts_stat_rx = TS_ENABLE;
-		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
+		cfg->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
 		break;
 	default:
 		return -ERANGE;
@@ -393,7 +391,7 @@ static int ines_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr)
 
 	spin_unlock_irqrestore(&port->lock, flags);
 
-	return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
+	return 0;
 }
 
 static void ines_link_state(struct mii_timestamper *mii_ts,
diff --git a/include/linux/mii_timestamper.h b/include/linux/mii_timestamper.h
index fa940bbaf8ae..26b04f73f214 100644
--- a/include/linux/mii_timestamper.h
+++ b/include/linux/mii_timestamper.h
@@ -9,6 +9,7 @@
 #include <linux/device.h>
 #include <linux/ethtool.h>
 #include <linux/skbuff.h>
+#include <linux/net_tstamp.h>
 
 struct phy_device;
 
@@ -51,7 +52,8 @@ struct mii_timestamper {
 			 struct sk_buff *skb, int type);
 
 	int  (*hwtstamp)(struct mii_timestamper *mii_ts,
-			 struct ifreq *ifreq);
+			 struct kernel_hwtstamp_config *kernel_config,
+			 struct netlink_ext_ack *extack);
 
 	void (*link_state)(struct mii_timestamper *mii_ts,
 			   struct phy_device *phydev);
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 3cc52826f18e..e5f1f41e399c 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1560,9 +1560,11 @@ static inline bool phy_has_txtstamp(struct phy_device *phydev)
 	return phydev && phydev->mii_ts && phydev->mii_ts->txtstamp;
 }
 
-static inline int phy_hwtstamp(struct phy_device *phydev, struct ifreq *ifr)
+static inline int phy_hwtstamp(struct phy_device *phydev,
+			       struct kernel_hwtstamp_config *cfg,
+			       struct netlink_ext_ack *extack)
 {
-	return phydev->mii_ts->hwtstamp(phydev->mii_ts, ifr);
+	return phydev->mii_ts->hwtstamp(phydev->mii_ts, cfg, extack);
 }
 
 static inline bool phy_rxtstamp(struct phy_device *phydev, struct sk_buff *skb,
-- 
cgit v1.2.3


From b8768dc4077712915f045ba1b198f521493c7914 Mon Sep 17 00:00:00 2001
From: Richard Cochran <richardcochran@gmail.com>
Date: Tue, 14 Nov 2023 12:28:31 +0100
Subject: net: ethtool: Refactor identical get_ts_info implementations.

The vlan, macvlan and the bonding drivers call their "real" device driver
in order to report the time stamping capabilities.  Provide a core
ethtool helper function to avoid copy/paste in the stack.

Signed-off-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: Kory Maincent <kory.maincent@bootlin.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Reviewed-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 29 ++---------------------------
 drivers/net/macvlan.c           | 14 +-------------
 include/linux/ethtool.h         |  8 ++++++++
 net/8021q/vlan_dev.c            | 15 +--------------
 net/ethtool/common.c            |  6 ++++++
 5 files changed, 18 insertions(+), 54 deletions(-)

(limited to 'include')

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 8e6cc0e133b7..4e0600c7b050 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -5755,10 +5755,8 @@ static int bond_ethtool_get_ts_info(struct net_device *bond_dev,
 {
 	struct bonding *bond = netdev_priv(bond_dev);
 	struct ethtool_ts_info ts_info;
-	const struct ethtool_ops *ops;
 	struct net_device *real_dev;
 	bool sw_tx_support = false;
-	struct phy_device *phydev;
 	struct list_head *iter;
 	struct slave *slave;
 	int ret = 0;
@@ -5769,29 +5767,12 @@ static int bond_ethtool_get_ts_info(struct net_device *bond_dev,
 	rcu_read_unlock();
 
 	if (real_dev) {
-		ops = real_dev->ethtool_ops;
-		phydev = real_dev->phydev;
-
-		if (phy_has_tsinfo(phydev)) {
-			ret = phy_ts_info(phydev, info);
-			goto out;
-		} else if (ops->get_ts_info) {
-			ret = ops->get_ts_info(real_dev, info);
-			goto out;
-		}
+		ret = ethtool_get_ts_info_by_layer(real_dev, info);
 	} else {
 		/* Check if all slaves support software tx timestamping */
 		rcu_read_lock();
 		bond_for_each_slave_rcu(bond, slave, iter) {
-			ret = -1;
-			ops = slave->dev->ethtool_ops;
-			phydev = slave->dev->phydev;
-
-			if (phy_has_tsinfo(phydev))
-				ret = phy_ts_info(phydev, &ts_info);
-			else if (ops->get_ts_info)
-				ret = ops->get_ts_info(slave->dev, &ts_info);
-
+			ret = ethtool_get_ts_info_by_layer(slave->dev, &ts_info);
 			if (!ret && (ts_info.so_timestamping & SOF_TIMESTAMPING_TX_SOFTWARE)) {
 				sw_tx_support = true;
 				continue;
@@ -5803,15 +5784,9 @@ static int bond_ethtool_get_ts_info(struct net_device *bond_dev,
 		rcu_read_unlock();
 	}
 
-	ret = 0;
-	info->so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE |
-				SOF_TIMESTAMPING_SOFTWARE;
 	if (sw_tx_support)
 		info->so_timestamping |= SOF_TIMESTAMPING_TX_SOFTWARE;
 
-	info->phc_index = -1;
-
-out:
 	dev_put(real_dev);
 	return ret;
 }
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index c8da94af4161..88dd8a2245b0 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -1086,20 +1086,8 @@ static int macvlan_ethtool_get_ts_info(struct net_device *dev,
 				       struct ethtool_ts_info *info)
 {
 	struct net_device *real_dev = macvlan_dev_real_dev(dev);
-	const struct ethtool_ops *ops = real_dev->ethtool_ops;
-	struct phy_device *phydev = real_dev->phydev;
 
-	if (phy_has_tsinfo(phydev)) {
-		return phy_ts_info(phydev, info);
-	} else if (ops->get_ts_info) {
-		return ops->get_ts_info(real_dev, info);
-	} else {
-		info->so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE |
-			SOF_TIMESTAMPING_SOFTWARE;
-		info->phc_index = -1;
-	}
-
-	return 0;
+	return ethtool_get_ts_info_by_layer(real_dev, info);
 }
 
 static netdev_features_t macvlan_fix_features(struct net_device *dev,
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 689028257fcc..c2bb74143eda 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -1043,6 +1043,14 @@ static inline int ethtool_mm_frag_size_min_to_add(u32 val_min, u32 *val_add,
 	return -EINVAL;
 }
 
+/**
+ * ethtool_get_ts_info_by_layer - Obtains time stamping capabilities from the MAC or PHY layer.
+ * @dev: pointer to net_device structure
+ * @info: buffer to hold the result
+ * Returns zero on success, non-zero otherwise.
+ */
+int ethtool_get_ts_info_by_layer(struct net_device *dev, struct ethtool_ts_info *info);
+
 /**
  * ethtool_sprintf - Write formatted string to ethtool string data
  * @data: Pointer to a pointer to the start of string to update
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 2a7f1b15714a..407b2335f091 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -702,20 +702,7 @@ static int vlan_ethtool_get_ts_info(struct net_device *dev,
 				    struct ethtool_ts_info *info)
 {
 	const struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
-	const struct ethtool_ops *ops = vlan->real_dev->ethtool_ops;
-	struct phy_device *phydev = vlan->real_dev->phydev;
-
-	if (phy_has_tsinfo(phydev)) {
-		return phy_ts_info(phydev, info);
-	} else if (ops->get_ts_info) {
-		return ops->get_ts_info(vlan->real_dev, info);
-	} else {
-		info->so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE |
-			SOF_TIMESTAMPING_SOFTWARE;
-		info->phc_index = -1;
-	}
-
-	return 0;
+	return ethtool_get_ts_info_by_layer(vlan->real_dev, info);
 }
 
 static void vlan_dev_get_stats64(struct net_device *dev,
diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index b4419fb6df6a..11d8797f63f6 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -661,6 +661,12 @@ int ethtool_get_phc_vclocks(struct net_device *dev, int **vclock_index)
 }
 EXPORT_SYMBOL(ethtool_get_phc_vclocks);
 
+int ethtool_get_ts_info_by_layer(struct net_device *dev, struct ethtool_ts_info *info)
+{
+	return __ethtool_get_ts_info(dev, info);
+}
+EXPORT_SYMBOL(ethtool_get_ts_info_by_layer);
+
 const struct ethtool_phy_ops *ethtool_phy_ops;
 
 void ethtool_set_ethtool_phy_ops(const struct ethtool_phy_ops *ops)
-- 
cgit v1.2.3


From 011dd3b3f83f9c89605c640424e05845b84f2dad Mon Sep 17 00:00:00 2001
From: Kory Maincent <kory.maincent@bootlin.com>
Date: Tue, 14 Nov 2023 12:28:33 +0100
Subject: net: Make dev_set_hwtstamp_phylib accessible

Make the dev_set_hwtstamp_phylib function accessible in prevision to use
it from ethtool to reset the tstamp current configuration.

Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: Kory Maincent <kory.maincent@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 3 +++
 net/core/dev_ioctl.c      | 7 ++++---
 2 files changed, 7 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index a16c9cc063fe..2d840d7056f2 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3942,6 +3942,9 @@ int generic_hwtstamp_get_lower(struct net_device *dev,
 int generic_hwtstamp_set_lower(struct net_device *dev,
 			       struct kernel_hwtstamp_config *kernel_cfg,
 			       struct netlink_ext_ack *extack);
+int dev_set_hwtstamp_phylib(struct net_device *dev,
+			    struct kernel_hwtstamp_config *cfg,
+			    struct netlink_ext_ack *extack);
 int dev_ethtool(struct net *net, struct ifreq *ifr, void __user *userdata);
 unsigned int dev_get_flags(const struct net_device *);
 int __dev_change_flags(struct net_device *dev, unsigned int flags,
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index feeddf95f450..9a66cf5015f2 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -322,9 +322,9 @@ static int dev_get_hwtstamp(struct net_device *dev, struct ifreq *ifr)
  * frames and not forward them), it must set IFF_SEE_ALL_HWTSTAMP_REQUESTS in
  * dev->priv_flags.
  */
-static int dev_set_hwtstamp_phylib(struct net_device *dev,
-				   struct kernel_hwtstamp_config *cfg,
-				   struct netlink_ext_ack *extack)
+int dev_set_hwtstamp_phylib(struct net_device *dev,
+			    struct kernel_hwtstamp_config *cfg,
+			    struct netlink_ext_ack *extack)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
 	bool phy_ts = phy_has_hwtstamp(dev->phydev);
@@ -363,6 +363,7 @@ static int dev_set_hwtstamp_phylib(struct net_device *dev,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(dev_set_hwtstamp_phylib);
 
 static int dev_set_hwtstamp(struct net_device *dev, struct ifreq *ifr)
 {
-- 
cgit v1.2.3


From acec05fb78abb74fdab2195bfca9a6d38a732643 Mon Sep 17 00:00:00 2001
From: Kory Maincent <kory.maincent@bootlin.com>
Date: Tue, 14 Nov 2023 12:28:35 +0100
Subject: net_tstamp: Add TIMESTAMPING SOFTWARE and HARDWARE mask

Timestamping software or hardware flags are often used as a group,
therefore adding these masks will easier future use.

I did not use SOF_TIMESTAMPING_SYS_HARDWARE flag as it is deprecated and
not use at all.

Signed-off-by: Kory Maincent <kory.maincent@bootlin.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/net_tstamp.h | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h
index a2c66b3d7f0f..df8091998c8d 100644
--- a/include/uapi/linux/net_tstamp.h
+++ b/include/uapi/linux/net_tstamp.h
@@ -48,6 +48,14 @@ enum {
 					 SOF_TIMESTAMPING_TX_SCHED | \
 					 SOF_TIMESTAMPING_TX_ACK)
 
+#define SOF_TIMESTAMPING_SOFTWARE_MASK	(SOF_TIMESTAMPING_RX_SOFTWARE | \
+					 SOF_TIMESTAMPING_TX_SOFTWARE | \
+					 SOF_TIMESTAMPING_SOFTWARE)
+
+#define SOF_TIMESTAMPING_HARDWARE_MASK	(SOF_TIMESTAMPING_RX_HARDWARE | \
+					 SOF_TIMESTAMPING_TX_HARDWARE | \
+					 SOF_TIMESTAMPING_RAW_HARDWARE)
+
 /**
  * struct so_timestamping - SO_TIMESTAMPING parameter
  *
-- 
cgit v1.2.3


From 11d55be06df0aedf19b05ab61c2d26b31a3c7e64 Mon Sep 17 00:00:00 2001
From: Kory Maincent <kory.maincent@bootlin.com>
Date: Tue, 14 Nov 2023 12:28:36 +0100
Subject: net: ethtool: Add a command to expose current time stamping layer

Time stamping on network packets may happen either in the MAC or in
the PHY, but not both.  In preparation for making the choice
selectable, expose both the current layers via ethtool.

In accordance with the kernel implementation as it stands, the current
layer will always read as "phy" when a PHY time stamping device is
present. Future patches will allow changing the current layer
administratively.

Signed-off-by: Kory Maincent <kory.maincent@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ethtool-netlink.rst | 23 ++++++++
 include/uapi/linux/ethtool_netlink.h         | 14 +++++
 include/uapi/linux/net_tstamp.h              | 10 ++++
 net/ethtool/Makefile                         |  2 +-
 net/ethtool/common.h                         |  1 +
 net/ethtool/netlink.c                        | 10 ++++
 net/ethtool/netlink.h                        |  2 +
 net/ethtool/ts.c                             | 88 ++++++++++++++++++++++++++++
 8 files changed, 149 insertions(+), 1 deletion(-)
 create mode 100644 net/ethtool/ts.c

(limited to 'include')

diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst
index 2540c70952ff..644b3b764044 100644
--- a/Documentation/networking/ethtool-netlink.rst
+++ b/Documentation/networking/ethtool-netlink.rst
@@ -225,6 +225,7 @@ Userspace to kernel:
   ``ETHTOOL_MSG_RSS_GET``               get RSS settings
   ``ETHTOOL_MSG_MM_GET``                get MAC merge layer state
   ``ETHTOOL_MSG_MM_SET``                set MAC merge layer parameters
+  ``ETHTOOL_MSG_TS_GET``                get current timestamping
   ===================================== =================================
 
 Kernel to userspace:
@@ -268,6 +269,7 @@ Kernel to userspace:
   ``ETHTOOL_MSG_PSE_GET_REPLY``            PSE parameters
   ``ETHTOOL_MSG_RSS_GET_REPLY``            RSS settings
   ``ETHTOOL_MSG_MM_GET_REPLY``             MAC merge layer status
+  ``ETHTOOL_MSG_TS_GET_REPLY``             current timestamping
   ======================================== =================================
 
 ``GET`` requests are sent by userspace applications to retrieve device
@@ -1994,6 +1996,26 @@ The attributes are propagated to the driver through the following structure:
 .. kernel-doc:: include/linux/ethtool.h
     :identifiers: ethtool_mm_cfg
 
+TS_GET
+======
+
+Gets current timestamping.
+
+Request contents:
+
+  =================================  ======  ====================
+  ``ETHTOOL_A_TS_HEADER``            nested  request header
+  =================================  ======  ====================
+
+Kernel response contents:
+
+  =======================  ======  ==============================
+  ``ETHTOOL_A_TS_HEADER``  nested  reply header
+  ``ETHTOOL_A_TS_LAYER``   u32     current timestamping
+  =======================  ======  ==============================
+
+This command get the current timestamp layer.
+
 Request translation
 ===================
 
@@ -2100,4 +2122,5 @@ are netlink only.
   n/a                                 ``ETHTOOL_MSG_PLCA_GET_STATUS``
   n/a                                 ``ETHTOOL_MSG_MM_GET``
   n/a                                 ``ETHTOOL_MSG_MM_SET``
+  n/a                                 ``ETHTOOL_MSG_TS_GET``
   =================================== =====================================
diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h
index 73e2c10dc2cc..cb51136328cf 100644
--- a/include/uapi/linux/ethtool_netlink.h
+++ b/include/uapi/linux/ethtool_netlink.h
@@ -57,6 +57,7 @@ enum {
 	ETHTOOL_MSG_PLCA_GET_STATUS,
 	ETHTOOL_MSG_MM_GET,
 	ETHTOOL_MSG_MM_SET,
+	ETHTOOL_MSG_TS_GET,
 
 	/* add new constants above here */
 	__ETHTOOL_MSG_USER_CNT,
@@ -109,6 +110,7 @@ enum {
 	ETHTOOL_MSG_PLCA_NTF,
 	ETHTOOL_MSG_MM_GET_REPLY,
 	ETHTOOL_MSG_MM_NTF,
+	ETHTOOL_MSG_TS_GET_REPLY,
 
 	/* add new constants above here */
 	__ETHTOOL_MSG_KERNEL_CNT,
@@ -975,6 +977,18 @@ enum {
 	ETHTOOL_A_MM_MAX = (__ETHTOOL_A_MM_CNT - 1)
 };
 
+/* TS LAYER */
+
+enum {
+	ETHTOOL_A_TS_UNSPEC,
+	ETHTOOL_A_TS_HEADER,			/* nest - _A_HEADER_* */
+	ETHTOOL_A_TS_LAYER,			/* u32 */
+
+	/* add new constants above here */
+	__ETHTOOL_A_TS_CNT,
+	ETHTOOL_A_TS_MAX = (__ETHTOOL_A_TS_CNT - 1)
+};
+
 /* generic netlink info */
 #define ETHTOOL_GENL_NAME "ethtool"
 #define ETHTOOL_GENL_VERSION 1
diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h
index df8091998c8d..4551fb3d7720 100644
--- a/include/uapi/linux/net_tstamp.h
+++ b/include/uapi/linux/net_tstamp.h
@@ -13,6 +13,16 @@
 #include <linux/types.h>
 #include <linux/socket.h>   /* for SO_TIMESTAMPING */
 
+/* Layer of the TIMESTAMPING provider */
+enum timestamping_layer {
+	NO_TIMESTAMPING,
+	SOFTWARE_TIMESTAMPING,
+	MAC_TIMESTAMPING,
+	PHY_TIMESTAMPING,
+
+	__TIMESTAMPING_COUNT,
+};
+
 /* SO_TIMESTAMPING flags */
 enum {
 	SOF_TIMESTAMPING_TX_HARDWARE = (1<<0),
diff --git a/net/ethtool/Makefile b/net/ethtool/Makefile
index 504f954a1b28..4ea64c080639 100644
--- a/net/ethtool/Makefile
+++ b/net/ethtool/Makefile
@@ -8,4 +8,4 @@ ethtool_nl-y	:= netlink.o bitset.o strset.o linkinfo.o linkmodes.o rss.o \
 		   linkstate.o debug.o wol.o features.o privflags.o rings.o \
 		   channels.o coalesce.o pause.o eee.o tsinfo.o cabletest.o \
 		   tunnels.o fec.o eeprom.o stats.o phc_vclocks.o mm.o \
-		   module.o pse-pd.o plca.o mm.o
+		   module.o pse-pd.o plca.o mm.o ts.o
diff --git a/net/ethtool/common.h b/net/ethtool/common.h
index 28b8aaaf9bcb..a264b635f7d3 100644
--- a/net/ethtool/common.h
+++ b/net/ethtool/common.h
@@ -35,6 +35,7 @@ extern const char wol_mode_names[][ETH_GSTRING_LEN];
 extern const char sof_timestamping_names[][ETH_GSTRING_LEN];
 extern const char ts_tx_type_names[][ETH_GSTRING_LEN];
 extern const char ts_rx_filter_names[][ETH_GSTRING_LEN];
+extern const char ts_layer_names[][ETH_GSTRING_LEN];
 extern const char udp_tunnel_type_names[][ETH_GSTRING_LEN];
 
 int __ethtool_get_link(struct net_device *dev);
diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index 3bbd5afb7b31..561c0931d055 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -306,6 +306,7 @@ ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = {
 	[ETHTOOL_MSG_PLCA_GET_STATUS]	= &ethnl_plca_status_request_ops,
 	[ETHTOOL_MSG_MM_GET]		= &ethnl_mm_request_ops,
 	[ETHTOOL_MSG_MM_SET]		= &ethnl_mm_request_ops,
+	[ETHTOOL_MSG_TS_GET]		= &ethnl_ts_request_ops,
 };
 
 static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb)
@@ -1128,6 +1129,15 @@ static const struct genl_ops ethtool_genl_ops[] = {
 		.policy = ethnl_mm_set_policy,
 		.maxattr = ARRAY_SIZE(ethnl_mm_set_policy) - 1,
 	},
+	{
+		.cmd	= ETHTOOL_MSG_TS_GET,
+		.doit	= ethnl_default_doit,
+		.start	= ethnl_default_start,
+		.dumpit	= ethnl_default_dumpit,
+		.done	= ethnl_default_done,
+		.policy = ethnl_ts_get_policy,
+		.maxattr = ARRAY_SIZE(ethnl_ts_get_policy) - 1,
+	},
 };
 
 static const struct genl_multicast_group ethtool_nl_mcgrps[] = {
diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h
index 9a333a8d04c1..1e6085198acc 100644
--- a/net/ethtool/netlink.h
+++ b/net/ethtool/netlink.h
@@ -395,6 +395,7 @@ extern const struct ethnl_request_ops ethnl_rss_request_ops;
 extern const struct ethnl_request_ops ethnl_plca_cfg_request_ops;
 extern const struct ethnl_request_ops ethnl_plca_status_request_ops;
 extern const struct ethnl_request_ops ethnl_mm_request_ops;
+extern const struct ethnl_request_ops ethnl_ts_request_ops;
 
 extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1];
 extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1];
@@ -441,6 +442,7 @@ extern const struct nla_policy ethnl_plca_set_cfg_policy[ETHTOOL_A_PLCA_MAX + 1]
 extern const struct nla_policy ethnl_plca_get_status_policy[ETHTOOL_A_PLCA_HEADER + 1];
 extern const struct nla_policy ethnl_mm_get_policy[ETHTOOL_A_MM_HEADER + 1];
 extern const struct nla_policy ethnl_mm_set_policy[ETHTOOL_A_MM_MAX + 1];
+extern const struct nla_policy ethnl_ts_get_policy[ETHTOOL_A_TS_HEADER + 1];
 
 int ethnl_set_features(struct sk_buff *skb, struct genl_info *info);
 int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info);
diff --git a/net/ethtool/ts.c b/net/ethtool/ts.c
new file mode 100644
index 000000000000..066cb06f4d0b
--- /dev/null
+++ b/net/ethtool/ts.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/net_tstamp.h>
+#include <linux/phy.h>
+
+#include "netlink.h"
+#include "common.h"
+#include "bitset.h"
+
+struct ts_req_info {
+	struct ethnl_req_info		base;
+};
+
+struct ts_reply_data {
+	struct ethnl_reply_data		base;
+	enum timestamping_layer		ts_layer;
+};
+
+#define TS_REPDATA(__reply_base) \
+	container_of(__reply_base, struct ts_reply_data, base)
+
+/* TS_GET */
+const struct nla_policy ethnl_ts_get_policy[] = {
+	[ETHTOOL_A_TS_HEADER]		=
+		NLA_POLICY_NESTED(ethnl_header_policy),
+};
+
+static int ts_prepare_data(const struct ethnl_req_info *req_base,
+			   struct ethnl_reply_data *reply_base,
+			   const struct genl_info *info)
+{
+	struct ts_reply_data *data = TS_REPDATA(reply_base);
+	struct net_device *dev = reply_base->dev;
+	const struct ethtool_ops *ops = dev->ethtool_ops;
+	int ret;
+
+	ret = ethnl_ops_begin(dev);
+	if (ret < 0)
+		return ret;
+
+	if (phy_has_tsinfo(dev->phydev)) {
+		data->ts_layer = PHY_TIMESTAMPING;
+	} else if (ops->get_ts_info) {
+		struct ethtool_ts_info ts_info = {0};
+
+		ops->get_ts_info(dev, &ts_info);
+		if (ts_info.so_timestamping &
+		    SOF_TIMESTAMPING_HARDWARE_MASK)
+			data->ts_layer = MAC_TIMESTAMPING;
+
+		if (ts_info.so_timestamping &
+		    SOF_TIMESTAMPING_SOFTWARE_MASK)
+			data->ts_layer = SOFTWARE_TIMESTAMPING;
+	} else {
+		data->ts_layer = NO_TIMESTAMPING;
+	}
+
+	ethnl_ops_complete(dev);
+
+	return ret;
+}
+
+static int ts_reply_size(const struct ethnl_req_info *req_base,
+			 const struct ethnl_reply_data *reply_base)
+{
+	return nla_total_size(sizeof(u32));
+}
+
+static int ts_fill_reply(struct sk_buff *skb,
+			 const struct ethnl_req_info *req_base,
+			 const struct ethnl_reply_data *reply_base)
+{
+	struct ts_reply_data *data = TS_REPDATA(reply_base);
+
+	return nla_put_u32(skb, ETHTOOL_A_TS_LAYER, data->ts_layer);
+}
+
+const struct ethnl_request_ops ethnl_ts_request_ops = {
+	.request_cmd		= ETHTOOL_MSG_TS_GET,
+	.reply_cmd		= ETHTOOL_MSG_TS_GET_REPLY,
+	.hdr_attr		= ETHTOOL_A_TS_HEADER,
+	.req_info_size		= sizeof(struct ts_req_info),
+	.reply_data_size	= sizeof(struct ts_reply_data),
+
+	.prepare_data		= ts_prepare_data,
+	.reply_size		= ts_reply_size,
+	.fill_reply		= ts_fill_reply,
+};
-- 
cgit v1.2.3


From d905f9c753295ee5a30af265f4b724f10050e7d3 Mon Sep 17 00:00:00 2001
From: Kory Maincent <kory.maincent@bootlin.com>
Date: Tue, 14 Nov 2023 12:28:38 +0100
Subject: net: ethtool: Add a command to list available time stamping layers

Introduce a new netlink message that lists all available time stamping
layers on a given interface.

Signed-off-by: Kory Maincent <kory.maincent@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ethtool-netlink.rst | 23 +++++++++
 include/uapi/linux/ethtool_netlink.h         | 14 ++++++
 net/ethtool/netlink.c                        | 10 ++++
 net/ethtool/netlink.h                        |  1 +
 net/ethtool/ts.c                             | 73 ++++++++++++++++++++++++++++
 5 files changed, 121 insertions(+)

(limited to 'include')

diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst
index 644b3b764044..b8d00676ed82 100644
--- a/Documentation/networking/ethtool-netlink.rst
+++ b/Documentation/networking/ethtool-netlink.rst
@@ -226,6 +226,7 @@ Userspace to kernel:
   ``ETHTOOL_MSG_MM_GET``                get MAC merge layer state
   ``ETHTOOL_MSG_MM_SET``                set MAC merge layer parameters
   ``ETHTOOL_MSG_TS_GET``                get current timestamping
+  ``ETHTOOL_MSG_TS_LIST_GET``           list available timestampings
   ===================================== =================================
 
 Kernel to userspace:
@@ -270,6 +271,7 @@ Kernel to userspace:
   ``ETHTOOL_MSG_RSS_GET_REPLY``            RSS settings
   ``ETHTOOL_MSG_MM_GET_REPLY``             MAC merge layer status
   ``ETHTOOL_MSG_TS_GET_REPLY``             current timestamping
+  ``ETHTOOL_MSG_TS_LIST_GET_REPLY``        available timestampings
   ======================================== =================================
 
 ``GET`` requests are sent by userspace applications to retrieve device
@@ -2016,6 +2018,26 @@ Kernel response contents:
 
 This command get the current timestamp layer.
 
+TS_LIST_GET
+===========
+
+Get the list of available timestampings.
+
+Request contents:
+
+  =================================  ======  ====================
+  ``ETHTOOL_A_TS_HEADER``            nested  request header
+  =================================  ======  ====================
+
+Kernel response contents:
+
+  ===========================  ======  ==============================
+  ``ETHTOOL_A_TS_HEADER``      nested  reply header
+  ``ETHTOOL_A_TS_LIST_LAYER``  binary  available timestampings
+  ===========================  ======  ==============================
+
+This command lists all the possible timestamp layer available.
+
 Request translation
 ===================
 
@@ -2123,4 +2145,5 @@ are netlink only.
   n/a                                 ``ETHTOOL_MSG_MM_GET``
   n/a                                 ``ETHTOOL_MSG_MM_SET``
   n/a                                 ``ETHTOOL_MSG_TS_GET``
+  n/a                                 ``ETHTOOL_MSG_TS_LIST_GET``
   =================================== =====================================
diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h
index cb51136328cf..62b885d44d06 100644
--- a/include/uapi/linux/ethtool_netlink.h
+++ b/include/uapi/linux/ethtool_netlink.h
@@ -58,6 +58,7 @@ enum {
 	ETHTOOL_MSG_MM_GET,
 	ETHTOOL_MSG_MM_SET,
 	ETHTOOL_MSG_TS_GET,
+	ETHTOOL_MSG_TS_LIST_GET,
 
 	/* add new constants above here */
 	__ETHTOOL_MSG_USER_CNT,
@@ -111,6 +112,7 @@ enum {
 	ETHTOOL_MSG_MM_GET_REPLY,
 	ETHTOOL_MSG_MM_NTF,
 	ETHTOOL_MSG_TS_GET_REPLY,
+	ETHTOOL_MSG_TS_LIST_GET_REPLY,
 
 	/* add new constants above here */
 	__ETHTOOL_MSG_KERNEL_CNT,
@@ -989,6 +991,18 @@ enum {
 	ETHTOOL_A_TS_MAX = (__ETHTOOL_A_TS_CNT - 1)
 };
 
+/* TS LIST LAYER */
+
+enum {
+	ETHTOOL_A_TS_LIST_UNSPEC,
+	ETHTOOL_A_TS_LIST_HEADER,			/* nest - _A_HEADER_* */
+	ETHTOOL_A_TS_LIST_LAYER,		/* array, u32 */
+
+	/* add new constants above here */
+	__ETHTOOL_A_TS_LIST_CNT,
+	ETHTOOL_A_TS_LIST_MAX = (__ETHTOOL_A_TS_LIST_CNT - 1)
+};
+
 /* generic netlink info */
 #define ETHTOOL_GENL_NAME "ethtool"
 #define ETHTOOL_GENL_VERSION 1
diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index 561c0931d055..842c9db1531f 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -307,6 +307,7 @@ ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = {
 	[ETHTOOL_MSG_MM_GET]		= &ethnl_mm_request_ops,
 	[ETHTOOL_MSG_MM_SET]		= &ethnl_mm_request_ops,
 	[ETHTOOL_MSG_TS_GET]		= &ethnl_ts_request_ops,
+	[ETHTOOL_MSG_TS_LIST_GET]	= &ethnl_ts_list_request_ops,
 };
 
 static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb)
@@ -1138,6 +1139,15 @@ static const struct genl_ops ethtool_genl_ops[] = {
 		.policy = ethnl_ts_get_policy,
 		.maxattr = ARRAY_SIZE(ethnl_ts_get_policy) - 1,
 	},
+	{
+		.cmd	= ETHTOOL_MSG_TS_LIST_GET,
+		.doit	= ethnl_default_doit,
+		.start	= ethnl_default_start,
+		.dumpit	= ethnl_default_dumpit,
+		.done	= ethnl_default_done,
+		.policy = ethnl_ts_get_policy,
+		.maxattr = ARRAY_SIZE(ethnl_ts_get_policy) - 1,
+	},
 };
 
 static const struct genl_multicast_group ethtool_nl_mcgrps[] = {
diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h
index 1e6085198acc..ea8c312db3af 100644
--- a/net/ethtool/netlink.h
+++ b/net/ethtool/netlink.h
@@ -396,6 +396,7 @@ extern const struct ethnl_request_ops ethnl_plca_cfg_request_ops;
 extern const struct ethnl_request_ops ethnl_plca_status_request_ops;
 extern const struct ethnl_request_ops ethnl_mm_request_ops;
 extern const struct ethnl_request_ops ethnl_ts_request_ops;
+extern const struct ethnl_request_ops ethnl_ts_list_request_ops;
 
 extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1];
 extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1];
diff --git a/net/ethtool/ts.c b/net/ethtool/ts.c
index 066cb06f4d0b..f2dd65a2e69c 100644
--- a/net/ethtool/ts.c
+++ b/net/ethtool/ts.c
@@ -86,3 +86,76 @@ const struct ethnl_request_ops ethnl_ts_request_ops = {
 	.reply_size		= ts_reply_size,
 	.fill_reply		= ts_fill_reply,
 };
+
+/* TS_LIST_GET */
+struct ts_list_reply_data {
+	struct ethnl_reply_data		base;
+	enum timestamping_layer		ts_layer[__TIMESTAMPING_COUNT];
+	u8				num_ts;
+};
+
+#define TS_LIST_REPDATA(__reply_base) \
+	container_of(__reply_base, struct ts_list_reply_data, base)
+
+static int ts_list_prepare_data(const struct ethnl_req_info *req_base,
+				struct ethnl_reply_data *reply_base,
+				const struct genl_info *info)
+{
+	struct ts_list_reply_data *data = TS_LIST_REPDATA(reply_base);
+	struct net_device *dev = reply_base->dev;
+	const struct ethtool_ops *ops = dev->ethtool_ops;
+	int ret, i = 0;
+
+	ret = ethnl_ops_begin(dev);
+	if (ret < 0)
+		return ret;
+
+	if (phy_has_tsinfo(dev->phydev))
+		data->ts_layer[i++] = PHY_TIMESTAMPING;
+	if (ops->get_ts_info) {
+		struct ethtool_ts_info ts_info = {0};
+
+		ops->get_ts_info(dev, &ts_info);
+		if (ts_info.so_timestamping &
+		    SOF_TIMESTAMPING_HARDWARE_MASK)
+			data->ts_layer[i++] = MAC_TIMESTAMPING;
+
+		if (ts_info.so_timestamping &
+		    SOF_TIMESTAMPING_SOFTWARE_MASK)
+			data->ts_layer[i++] = SOFTWARE_TIMESTAMPING;
+	}
+
+	data->num_ts = i;
+	ethnl_ops_complete(dev);
+
+	return ret;
+}
+
+static int ts_list_reply_size(const struct ethnl_req_info *req_base,
+			      const struct ethnl_reply_data *reply_base)
+{
+	struct ts_list_reply_data *data = TS_LIST_REPDATA(reply_base);
+
+	return nla_total_size(sizeof(u32)) * data->num_ts;
+}
+
+static int ts_list_fill_reply(struct sk_buff *skb,
+			      const struct ethnl_req_info *req_base,
+			 const struct ethnl_reply_data *reply_base)
+{
+	struct ts_list_reply_data *data = TS_LIST_REPDATA(reply_base);
+
+	return nla_put(skb, ETHTOOL_A_TS_LIST_LAYER, sizeof(u32) * data->num_ts, data->ts_layer);
+}
+
+const struct ethnl_request_ops ethnl_ts_list_request_ops = {
+	.request_cmd		= ETHTOOL_MSG_TS_LIST_GET,
+	.reply_cmd		= ETHTOOL_MSG_TS_LIST_GET_REPLY,
+	.hdr_attr		= ETHTOOL_A_TS_HEADER,
+	.req_info_size		= sizeof(struct ts_req_info),
+	.reply_data_size	= sizeof(struct ts_list_reply_data),
+
+	.prepare_data		= ts_list_prepare_data,
+	.reply_size		= ts_list_reply_size,
+	.fill_reply		= ts_list_fill_reply,
+};
-- 
cgit v1.2.3


From 51bdf3165f012827644c474a6d905baa3de3f1ea Mon Sep 17 00:00:00 2001
From: Kory Maincent <kory.maincent@bootlin.com>
Date: Tue, 14 Nov 2023 12:28:40 +0100
Subject: net: Replace hwtstamp_source by timestamping layer

Replace hwtstamp_source which is only used by the kernel_hwtstamp_config
structure by the more widely use timestamp_layer structure. This is done
to prepare the support of selectable timestamping source.

Signed-off-by: Kory Maincent <kory.maincent@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/lan966x/lan966x_main.c |  6 +++---
 include/linux/net_tstamp.h                            | 11 +++--------
 net/core/dev_ioctl.c                                  |  2 +-
 3 files changed, 7 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
index 2635ef8958c8..fbe56b1bb386 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
@@ -470,15 +470,15 @@ static int lan966x_port_hwtstamp_set(struct net_device *dev,
 	struct lan966x_port *port = netdev_priv(dev);
 	int err;
 
-	if (cfg->source != HWTSTAMP_SOURCE_NETDEV &&
-	    cfg->source != HWTSTAMP_SOURCE_PHYLIB)
+	if (cfg->source != MAC_TIMESTAMPING &&
+	    cfg->source != PHY_TIMESTAMPING)
 		return -EOPNOTSUPP;
 
 	err = lan966x_ptp_setup_traps(port, cfg);
 	if (err)
 		return err;
 
-	if (cfg->source == HWTSTAMP_SOURCE_NETDEV) {
+	if (cfg->source == MAC_TIMESTAMPING) {
 		if (!port->lan966x->ptp)
 			return -EOPNOTSUPP;
 
diff --git a/include/linux/net_tstamp.h b/include/linux/net_tstamp.h
index eb01c37e71e0..bb289c2ad376 100644
--- a/include/linux/net_tstamp.h
+++ b/include/linux/net_tstamp.h
@@ -5,11 +5,6 @@
 
 #include <uapi/linux/net_tstamp.h>
 
-enum hwtstamp_source {
-	HWTSTAMP_SOURCE_NETDEV,
-	HWTSTAMP_SOURCE_PHYLIB,
-};
-
 /**
  * struct kernel_hwtstamp_config - Kernel copy of struct hwtstamp_config
  *
@@ -20,8 +15,8 @@ enum hwtstamp_source {
  *	a legacy implementation of a lower driver
  * @copied_to_user: request was passed to a legacy implementation which already
  *	copied the ioctl request back to user space
- * @source: indication whether timestamps should come from the netdev or from
- *	an attached phylib PHY
+ * @source: indication whether timestamps should come from software, the netdev
+ *	or from an attached phylib PHY
  *
  * Prefer using this structure for in-kernel processing of hardware
  * timestamping configuration, over the inextensible struct hwtstamp_config
@@ -33,7 +28,7 @@ struct kernel_hwtstamp_config {
 	int rx_filter;
 	struct ifreq *ifr;
 	bool copied_to_user;
-	enum hwtstamp_source source;
+	enum timestamping_layer source;
 };
 
 static inline void hwtstamp_config_to_kernel(struct kernel_hwtstamp_config *kernel_cfg,
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index 9a66cf5015f2..267cd00269d0 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -332,7 +332,7 @@ int dev_set_hwtstamp_phylib(struct net_device *dev,
 	bool changed = false;
 	int err;
 
-	cfg->source = phy_ts ? HWTSTAMP_SOURCE_PHYLIB : HWTSTAMP_SOURCE_NETDEV;
+	cfg->source = phy_ts ? PHY_TIMESTAMPING : MAC_TIMESTAMPING;
 
 	if (phy_ts && (dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS)) {
 		err = ops->ndo_hwtstamp_get(dev, &old_cfg);
-- 
cgit v1.2.3


From 0f7f463d4821a4f52fa5c0a961389e651d50c384 Mon Sep 17 00:00:00 2001
From: Kory Maincent <kory.maincent@bootlin.com>
Date: Tue, 14 Nov 2023 12:28:41 +0100
Subject: net: Change the API of PHY default timestamp to MAC

Change the API to select MAC default time stamping instead of the PHY.
Indeed the PHY is closer to the wire therefore theoretically it has less
delay than the MAC timestamping but the reality is different. Due to lower
time stamping clock frequency, latency in the MDIO bus and no PHC hardware
synchronization between different PHY, the PHY PTP is often less precise
than the MAC. The exception is for PHY designed specially for PTP case but
these devices are not very widespread. For not breaking the compatibility I
introduce a default_timestamp flag in phy_device that is set by the phy
driver to know we are using the old API behavior.

The phy_set_timestamp function is called at each call of phy_attach_direct.
In case of MAC driver using phylink this function is called when the
interface is turned up. Then if the interface goes down and up again the
last choice of timestamp will be overwritten by the default choice.
A solution could be to cache the timestamp status but it can bring other
issues. In case of SFP, if we change the module, it doesn't make sense to
blindly re-set the timestamp back to PHY, if the new module has a PHY with
mediocre timestamping capabilities.

Signed-off-by: Kory Maincent <kory.maincent@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/bcm-phy-ptp.c     |  3 +++
 drivers/net/phy/dp83640.c         |  3 +++
 drivers/net/phy/micrel.c          |  6 ++++++
 drivers/net/phy/mscc/mscc_ptp.c   |  2 ++
 drivers/net/phy/nxp-c45-tja11xx.c |  3 +++
 drivers/net/phy/phy_device.c      | 37 +++++++++++++++++++++++++++++++++++++
 include/linux/netdevice.h         |  5 +++++
 include/linux/phy.h               |  4 ++++
 net/core/dev.c                    |  3 +++
 net/core/dev_ioctl.c              | 36 ++++++++++++++++++++++--------------
 net/core/timestamping.c           | 10 ++++++++++
 net/ethtool/common.c              | 19 +++++++++++++++++--
 12 files changed, 115 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/net/phy/bcm-phy-ptp.c b/drivers/net/phy/bcm-phy-ptp.c
index 617d384d4551..d3e825c951ee 100644
--- a/drivers/net/phy/bcm-phy-ptp.c
+++ b/drivers/net/phy/bcm-phy-ptp.c
@@ -931,6 +931,9 @@ struct bcm_ptp_private *bcm_ptp_probe(struct phy_device *phydev)
 		return ERR_CAST(clock);
 	priv->ptp_clock = clock;
 
+	/* Timestamp selected by default to keep legacy API */
+	phydev->default_timestamp = true;
+
 	priv->phydev = phydev;
 	bcm_ptp_init(priv);
 
diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index 5c42c47dc564..64fd1a109c0f 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -1450,6 +1450,9 @@ static int dp83640_probe(struct phy_device *phydev)
 	phydev->mii_ts = &dp83640->mii_ts;
 	phydev->priv = dp83640;
 
+	/* Timestamp selected by default to keep legacy API */
+	phydev->default_timestamp = true;
+
 	spin_lock_init(&dp83640->rx_lock);
 	skb_queue_head_init(&dp83640->rx_queue);
 	skb_queue_head_init(&dp83640->tx_queue);
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index bd4cd082662f..2b8dd0131926 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -3158,6 +3158,9 @@ static void lan8814_ptp_init(struct phy_device *phydev)
 	ptp_priv->mii_ts.ts_info  = lan8814_ts_info;
 
 	phydev->mii_ts = &ptp_priv->mii_ts;
+
+	/* Timestamp selected by default to keep legacy API */
+	phydev->default_timestamp = true;
 }
 
 static int lan8814_ptp_probe_once(struct phy_device *phydev)
@@ -4586,6 +4589,9 @@ static int lan8841_probe(struct phy_device *phydev)
 
 	phydev->mii_ts = &ptp_priv->mii_ts;
 
+	/* Timestamp selected by default to keep legacy API */
+	phydev->default_timestamp = true;
+
 	return 0;
 }
 
diff --git a/drivers/net/phy/mscc/mscc_ptp.c b/drivers/net/phy/mscc/mscc_ptp.c
index eb0b032cb613..fd174eb06d4a 100644
--- a/drivers/net/phy/mscc/mscc_ptp.c
+++ b/drivers/net/phy/mscc/mscc_ptp.c
@@ -1570,6 +1570,8 @@ int vsc8584_ptp_probe(struct phy_device *phydev)
 		return PTR_ERR(vsc8531->load_save);
 	}
 
+	/* Timestamp selected by default to keep legacy API */
+	phydev->default_timestamp = true;
 	vsc8531->ptp->phydev = phydev;
 
 	return 0;
diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c
index 780ad353cf55..0515c7b979db 100644
--- a/drivers/net/phy/nxp-c45-tja11xx.c
+++ b/drivers/net/phy/nxp-c45-tja11xx.c
@@ -1658,6 +1658,9 @@ static int nxp_c45_probe(struct phy_device *phydev)
 		priv->mii_ts.ts_info = nxp_c45_ts_info;
 		phydev->mii_ts = &priv->mii_ts;
 		ret = nxp_c45_init_ptp_clock(priv);
+
+		/* Timestamp selected by default to keep legacy API */
+		phydev->default_timestamp = true;
 	} else {
 		phydev_dbg(phydev, "PTP support not enabled even if the phy supports it");
 	}
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 2ce74593d6e4..8c4794631daa 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1411,6 +1411,26 @@ int phy_sfp_probe(struct phy_device *phydev,
 }
 EXPORT_SYMBOL(phy_sfp_probe);
 
+/**
+ * phy_set_timestamp - set the default selected timestamping device
+ * @dev: Pointer to net_device
+ * @phydev: Pointer to phy_device
+ *
+ * This is used to set default timestamping device taking into account
+ * the new API choice, which is selecting the timestamping from MAC by
+ * default if the phydev does not have default_timestamp flag enabled.
+ */
+static void phy_set_timestamp(struct net_device *dev, struct phy_device *phydev)
+{
+	const struct ethtool_ops *ops = dev->ethtool_ops;
+
+	if (!phy_has_tsinfo(phydev))
+		return;
+
+	if (!ops->get_ts_info || phydev->default_timestamp)
+		dev->ts_layer = PHY_TIMESTAMPING;
+}
+
 /**
  * phy_attach_direct - attach a network device to a given PHY device pointer
  * @dev: network device to attach
@@ -1484,6 +1504,7 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
 
 	phydev->phy_link_change = phy_link_change;
 	if (dev) {
+		phy_set_timestamp(dev, phydev);
 		phydev->attached_dev = dev;
 		dev->phydev = phydev;
 
@@ -1812,6 +1833,22 @@ void phy_detach(struct phy_device *phydev)
 
 	phy_suspend(phydev);
 	if (dev) {
+		const struct ethtool_ops *ops = dev->ethtool_ops;
+		struct ethtool_ts_info ts_info = {0};
+
+		if (ops->get_ts_info) {
+			ops->get_ts_info(dev, &ts_info);
+			if ((ts_info.so_timestamping &
+			    SOF_TIMESTAMPING_HARDWARE_MASK) ==
+			    SOF_TIMESTAMPING_HARDWARE_MASK)
+				dev->ts_layer = MAC_TIMESTAMPING;
+			else if ((ts_info.so_timestamping &
+				 SOF_TIMESTAMPING_SOFTWARE_MASK) ==
+				 SOF_TIMESTAMPING_SOFTWARE_MASK)
+				dev->ts_layer = SOFTWARE_TIMESTAMPING;
+		} else {
+			dev->ts_layer = NO_TIMESTAMPING;
+		}
 		phydev->attached_dev->phydev = NULL;
 		phydev->attached_dev = NULL;
 	}
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 2d840d7056f2..f020d2790c12 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -47,6 +47,7 @@
 #include <uapi/linux/if_bonding.h>
 #include <uapi/linux/pkt_cls.h>
 #include <uapi/linux/netdev.h>
+#include <uapi/linux/net_tstamp.h>
 #include <linux/hashtable.h>
 #include <linux/rbtree.h>
 #include <net/net_trackers.h>
@@ -2074,6 +2075,8 @@ enum netdev_ml_priv_type {
  *
  *	@dpll_pin: Pointer to the SyncE source pin of a DPLL subsystem,
  *		   where the clock is recovered.
+ *	@ts_layer:	Tracks which network device
+ *			performs packet	time stamping.
  *
  *	FIXME: cleanup struct net_device such that network protocol info
  *	moves out.
@@ -2435,6 +2438,8 @@ struct net_device {
 #if IS_ENABLED(CONFIG_DPLL)
 	struct dpll_pin		*dpll_pin;
 #endif
+
+	enum timestamping_layer	ts_layer;
 };
 #define to_net_dev(d) container_of(d, struct net_device, dev)
 
diff --git a/include/linux/phy.h b/include/linux/phy.h
index e5f1f41e399c..317def2a7843 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -604,6 +604,8 @@ struct macsec_ops;
  *                 handling shall be postponed until PHY has resumed
  * @irq_rerun: Flag indicating interrupts occurred while PHY was suspended,
  *             requiring a rerun of the interrupt handler after resume
+ * @default_timestamp: Flag indicating whether we are using the phy
+ *		       timestamp as the default one
  * @interface: enum phy_interface_t value
  * @skb: Netlink message for cable diagnostics
  * @nest: Netlink nest used for cable diagnostics
@@ -667,6 +669,8 @@ struct phy_device {
 	unsigned irq_suspended:1;
 	unsigned irq_rerun:1;
 
+	unsigned default_timestamp:1;
+
 	int rate_matching;
 
 	enum phy_state state;
diff --git a/net/core/dev.c b/net/core/dev.c
index af53f6d838ce..05ce00632892 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -10212,6 +10212,9 @@ int register_netdevice(struct net_device *dev)
 	    dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
 		rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL, 0, NULL);
 
+	if (dev->ethtool_ops->get_ts_info)
+		dev->ts_layer = MAC_TIMESTAMPING;
+
 out:
 	return ret;
 
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index 267cd00269d0..bc8be9749376 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -259,9 +259,7 @@ static int dev_eth_ioctl(struct net_device *dev,
  * @dev: Network device
  * @cfg: Timestamping configuration structure
  *
- * Helper for enforcing a common policy that phylib timestamping, if available,
- * should take precedence in front of hardware timestamping provided by the
- * netdev.
+ * Helper for calling the selected hardware provider timestamping.
  *
  * Note: phy_mii_ioctl() only handles SIOCSHWTSTAMP (not SIOCGHWTSTAMP), and
  * there only exists a phydev->mii_ts->hwtstamp() method. So this will return
@@ -271,10 +269,14 @@ static int dev_eth_ioctl(struct net_device *dev,
 static int dev_get_hwtstamp_phylib(struct net_device *dev,
 				   struct kernel_hwtstamp_config *cfg)
 {
-	if (phy_has_hwtstamp(dev->phydev))
+	enum timestamping_layer ts_layer = dev->ts_layer;
+
+	if (ts_layer == PHY_TIMESTAMPING)
 		return phy_hwtstamp_get(dev->phydev, cfg);
+	else if (ts_layer == MAC_TIMESTAMPING)
+		return dev->netdev_ops->ndo_hwtstamp_get(dev, cfg);
 
-	return dev->netdev_ops->ndo_hwtstamp_get(dev, cfg);
+	return -EOPNOTSUPP;
 }
 
 static int dev_get_hwtstamp(struct net_device *dev, struct ifreq *ifr)
@@ -315,9 +317,8 @@ static int dev_get_hwtstamp(struct net_device *dev, struct ifreq *ifr)
  * @cfg: Timestamping configuration structure
  * @extack: Netlink extended ack message structure, for error reporting
  *
- * Helper for enforcing a common policy that phylib timestamping, if available,
- * should take precedence in front of hardware timestamping provided by the
- * netdev. If the netdev driver needs to perform specific actions even for PHY
+ * Helper for calling the selected hardware provider timestamping.
+ * If the netdev driver needs to perform specific actions even for PHY
  * timestamping to work properly (a switch port must trap the timestamped
  * frames and not forward them), it must set IFF_SEE_ALL_HWTSTAMP_REQUESTS in
  * dev->priv_flags.
@@ -327,20 +328,26 @@ int dev_set_hwtstamp_phylib(struct net_device *dev,
 			    struct netlink_ext_ack *extack)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
-	bool phy_ts = phy_has_hwtstamp(dev->phydev);
+	enum timestamping_layer ts_layer = dev->ts_layer;
 	struct kernel_hwtstamp_config old_cfg = {};
 	bool changed = false;
 	int err;
 
-	cfg->source = phy_ts ? PHY_TIMESTAMPING : MAC_TIMESTAMPING;
+	cfg->source = ts_layer;
+
+	if (ts_layer != PHY_TIMESTAMPING &&
+	    ts_layer != MAC_TIMESTAMPING)
+		return -EOPNOTSUPP;
 
-	if (phy_ts && (dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS)) {
+	if (ts_layer == PHY_TIMESTAMPING &&
+	    dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS) {
 		err = ops->ndo_hwtstamp_get(dev, &old_cfg);
 		if (err)
 			return err;
 	}
 
-	if (!phy_ts || (dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS)) {
+	if (ts_layer == MAC_TIMESTAMPING ||
+	    dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS) {
 		err = ops->ndo_hwtstamp_set(dev, cfg, extack);
 		if (err) {
 			if (extack->_msg)
@@ -349,10 +356,11 @@ int dev_set_hwtstamp_phylib(struct net_device *dev,
 		}
 	}
 
-	if (phy_ts && (dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS))
+	if (ts_layer == PHY_TIMESTAMPING &&
+	    dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS)
 		changed = kernel_hwtstamp_config_changed(&old_cfg, cfg);
 
-	if (phy_ts) {
+	if (ts_layer == PHY_TIMESTAMPING) {
 		err = phy_hwtstamp_set(dev->phydev, cfg, extack);
 		if (err) {
 			if (changed)
diff --git a/net/core/timestamping.c b/net/core/timestamping.c
index 04840697fe79..5cf51a523fb3 100644
--- a/net/core/timestamping.c
+++ b/net/core/timestamping.c
@@ -21,6 +21,7 @@ static unsigned int classify(const struct sk_buff *skb)
 
 void skb_clone_tx_timestamp(struct sk_buff *skb)
 {
+	enum timestamping_layer ts_layer;
 	struct mii_timestamper *mii_ts;
 	struct sk_buff *clone;
 	unsigned int type;
@@ -28,6 +29,10 @@ void skb_clone_tx_timestamp(struct sk_buff *skb)
 	if (!skb->sk)
 		return;
 
+	ts_layer = skb->dev->ts_layer;
+	if (ts_layer != PHY_TIMESTAMPING)
+		return;
+
 	type = classify(skb);
 	if (type == PTP_CLASS_NONE)
 		return;
@@ -44,12 +49,17 @@ EXPORT_SYMBOL_GPL(skb_clone_tx_timestamp);
 
 bool skb_defer_rx_timestamp(struct sk_buff *skb)
 {
+	enum timestamping_layer ts_layer;
 	struct mii_timestamper *mii_ts;
 	unsigned int type;
 
 	if (!skb->dev || !skb->dev->phydev || !skb->dev->phydev->mii_ts)
 		return false;
 
+	ts_layer = skb->dev->ts_layer;
+	if (ts_layer != PHY_TIMESTAMPING)
+		return false;
+
 	if (skb_headroom(skb) < ETH_HLEN)
 		return false;
 
diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index 11d8797f63f6..9f6e3b2c74e2 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -633,13 +633,28 @@ int __ethtool_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info)
 {
 	const struct ethtool_ops *ops = dev->ethtool_ops;
 	struct phy_device *phydev = dev->phydev;
+	enum timestamping_layer ts_layer;
+	int ret;
 
 	memset(info, 0, sizeof(*info));
 	info->cmd = ETHTOOL_GET_TS_INFO;
 
-	if (phy_has_tsinfo(phydev))
+	ts_layer = dev->ts_layer;
+	if (ts_layer == SOFTWARE_TIMESTAMPING) {
+		ret = ops->get_ts_info(dev, info);
+		if (ret)
+			return ret;
+		info->so_timestamping &= ~SOF_TIMESTAMPING_HARDWARE_MASK;
+		info->phc_index = -1;
+		info->rx_filters = 0;
+		info->tx_types = 0;
+		return 0;
+	}
+
+	if (ts_layer == PHY_TIMESTAMPING)
 		return phy_ts_info(phydev, info);
-	if (ops->get_ts_info)
+
+	if (ts_layer == MAC_TIMESTAMPING)
 		return ops->get_ts_info(dev, info);
 
 	info->so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE |
-- 
cgit v1.2.3


From 152c75e1d00200edc4da1beb67dd099a462ea86b Mon Sep 17 00:00:00 2001
From: Kory Maincent <kory.maincent@bootlin.com>
Date: Tue, 14 Nov 2023 12:28:43 +0100
Subject: net: ethtool: ts: Let the active time stamping layer be selectable

Now that the current timestamp is saved in a variable lets add the
ETHTOOL_MSG_TS_SET ethtool netlink socket to make it selectable.

Signed-off-by: Kory Maincent <kory.maincent@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ethtool-netlink.rst | 17 +++++
 include/uapi/linux/ethtool_netlink.h         |  1 +
 net/ethtool/netlink.c                        |  8 +++
 net/ethtool/netlink.h                        |  1 +
 net/ethtool/ts.c                             | 99 ++++++++++++++++++++++++++++
 5 files changed, 126 insertions(+)

(limited to 'include')

diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst
index b8d00676ed82..530c1775e5f4 100644
--- a/Documentation/networking/ethtool-netlink.rst
+++ b/Documentation/networking/ethtool-netlink.rst
@@ -227,6 +227,7 @@ Userspace to kernel:
   ``ETHTOOL_MSG_MM_SET``                set MAC merge layer parameters
   ``ETHTOOL_MSG_TS_GET``                get current timestamping
   ``ETHTOOL_MSG_TS_LIST_GET``           list available timestampings
+  ``ETHTOOL_MSG_TS_SET``                set current timestamping
   ===================================== =================================
 
 Kernel to userspace:
@@ -2038,6 +2039,21 @@ Kernel response contents:
 
 This command lists all the possible timestamp layer available.
 
+TS_SET
+======
+
+Modify the selected timestamping.
+
+Request contents:
+
+  =======================  ======  ===================
+  ``ETHTOOL_A_TS_HEADER``  nested  reply header
+  ``ETHTOOL_A_TS_LAYER``   u32     timestamping
+  =======================  ======  ===================
+
+This command set the timestamping with one that should be listed by the
+TSLIST_GET command.
+
 Request translation
 ===================
 
@@ -2146,4 +2162,5 @@ are netlink only.
   n/a                                 ``ETHTOOL_MSG_MM_SET``
   n/a                                 ``ETHTOOL_MSG_TS_GET``
   n/a                                 ``ETHTOOL_MSG_TS_LIST_GET``
+  n/a                                 ``ETHTOOL_MSG_TS_SET``
   =================================== =====================================
diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h
index 62b885d44d06..df6c4fcc62c1 100644
--- a/include/uapi/linux/ethtool_netlink.h
+++ b/include/uapi/linux/ethtool_netlink.h
@@ -59,6 +59,7 @@ enum {
 	ETHTOOL_MSG_MM_SET,
 	ETHTOOL_MSG_TS_GET,
 	ETHTOOL_MSG_TS_LIST_GET,
+	ETHTOOL_MSG_TS_SET,
 
 	/* add new constants above here */
 	__ETHTOOL_MSG_USER_CNT,
diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index 842c9db1531f..8322bf71f80d 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -308,6 +308,7 @@ ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = {
 	[ETHTOOL_MSG_MM_SET]		= &ethnl_mm_request_ops,
 	[ETHTOOL_MSG_TS_GET]		= &ethnl_ts_request_ops,
 	[ETHTOOL_MSG_TS_LIST_GET]	= &ethnl_ts_list_request_ops,
+	[ETHTOOL_MSG_TS_SET]		= &ethnl_ts_request_ops,
 };
 
 static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb)
@@ -1148,6 +1149,13 @@ static const struct genl_ops ethtool_genl_ops[] = {
 		.policy = ethnl_ts_get_policy,
 		.maxattr = ARRAY_SIZE(ethnl_ts_get_policy) - 1,
 	},
+	{
+		.cmd	= ETHTOOL_MSG_TS_SET,
+		.flags	= GENL_UNS_ADMIN_PERM,
+		.doit	= ethnl_default_set_doit,
+		.policy = ethnl_ts_set_policy,
+		.maxattr = ARRAY_SIZE(ethnl_ts_set_policy) - 1,
+	},
 };
 
 static const struct genl_multicast_group ethtool_nl_mcgrps[] = {
diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h
index ea8c312db3af..8fedf234b824 100644
--- a/net/ethtool/netlink.h
+++ b/net/ethtool/netlink.h
@@ -444,6 +444,7 @@ extern const struct nla_policy ethnl_plca_get_status_policy[ETHTOOL_A_PLCA_HEADE
 extern const struct nla_policy ethnl_mm_get_policy[ETHTOOL_A_MM_HEADER + 1];
 extern const struct nla_policy ethnl_mm_set_policy[ETHTOOL_A_MM_MAX + 1];
 extern const struct nla_policy ethnl_ts_get_policy[ETHTOOL_A_TS_HEADER + 1];
+extern const struct nla_policy ethnl_ts_set_policy[ETHTOOL_A_TS_MAX + 1];
 
 int ethnl_set_features(struct sk_buff *skb, struct genl_info *info);
 int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info);
diff --git a/net/ethtool/ts.c b/net/ethtool/ts.c
index bd219512b8de..357265e74e08 100644
--- a/net/ethtool/ts.c
+++ b/net/ethtool/ts.c
@@ -59,6 +59,102 @@ static int ts_fill_reply(struct sk_buff *skb,
 	return nla_put_u32(skb, ETHTOOL_A_TS_LAYER, data->ts_layer);
 }
 
+/* TS_SET */
+const struct nla_policy ethnl_ts_set_policy[] = {
+	[ETHTOOL_A_TS_HEADER]	= NLA_POLICY_NESTED(ethnl_header_policy),
+	[ETHTOOL_A_TS_LAYER]	= NLA_POLICY_RANGE(NLA_U32, 0,
+						   __TIMESTAMPING_COUNT - 1)
+};
+
+static int ethnl_set_ts_validate(struct ethnl_req_info *req_info,
+				 struct genl_info *info)
+{
+	struct nlattr **tb = info->attrs;
+	const struct net_device_ops *ops = req_info->dev->netdev_ops;
+
+	if (!ops->ndo_hwtstamp_set)
+		return -EOPNOTSUPP;
+
+	if (!tb[ETHTOOL_A_TS_LAYER])
+		return 0;
+
+	return 1;
+}
+
+static int ethnl_set_ts(struct ethnl_req_info *req_info, struct genl_info *info)
+{
+	struct net_device *dev = req_info->dev;
+	const struct ethtool_ops *ops = dev->ethtool_ops;
+	struct kernel_hwtstamp_config config = {0};
+	struct nlattr **tb = info->attrs;
+	enum timestamping_layer ts_layer;
+	bool mod = false;
+	int ret;
+
+	ts_layer = dev->ts_layer;
+	ethnl_update_u32(&ts_layer, tb[ETHTOOL_A_TS_LAYER], &mod);
+
+	if (!mod)
+		return 0;
+
+	if (ts_layer == SOFTWARE_TIMESTAMPING) {
+		struct ethtool_ts_info ts_info = {0};
+
+		if (!ops->get_ts_info) {
+			NL_SET_ERR_MSG_ATTR(info->extack,
+					    tb[ETHTOOL_A_TS_LAYER],
+					    "this net device cannot support timestamping");
+			return -EINVAL;
+		}
+
+		ops->get_ts_info(dev, &ts_info);
+		if ((ts_info.so_timestamping &
+		    SOF_TIMESTAMPING_SOFTWARE_MASK) !=
+		    SOF_TIMESTAMPING_SOFTWARE_MASK) {
+			NL_SET_ERR_MSG_ATTR(info->extack,
+					    tb[ETHTOOL_A_TS_LAYER],
+					    "this net device cannot support software timestamping");
+			return -EINVAL;
+		}
+	} else if (ts_layer == MAC_TIMESTAMPING) {
+		struct ethtool_ts_info ts_info = {0};
+
+		if (!ops->get_ts_info) {
+			NL_SET_ERR_MSG_ATTR(info->extack,
+					    tb[ETHTOOL_A_TS_LAYER],
+					    "this net device cannot support timestamping");
+			return -EINVAL;
+		}
+
+		ops->get_ts_info(dev, &ts_info);
+		if ((ts_info.so_timestamping &
+		    SOF_TIMESTAMPING_HARDWARE_MASK) !=
+		    SOF_TIMESTAMPING_HARDWARE_MASK) {
+			NL_SET_ERR_MSG_ATTR(info->extack,
+					    tb[ETHTOOL_A_TS_LAYER],
+					    "this net device cannot support hardware timestamping");
+			return -EINVAL;
+		}
+	} else if (ts_layer == PHY_TIMESTAMPING && !phy_has_tsinfo(dev->phydev)) {
+		NL_SET_ERR_MSG_ATTR(info->extack, tb[ETHTOOL_A_TS_LAYER],
+				    "this phy device cannot support timestamping");
+		return -EINVAL;
+	}
+
+	/* Disable time stamping in the current layer. */
+	if (netif_device_present(dev) &&
+	    (dev->ts_layer == PHY_TIMESTAMPING ||
+	    dev->ts_layer == MAC_TIMESTAMPING)) {
+		ret = dev_set_hwtstamp_phylib(dev, &config, info->extack);
+		if (ret < 0)
+			return ret;
+	}
+
+	dev->ts_layer = ts_layer;
+
+	return 1;
+}
+
 const struct ethnl_request_ops ethnl_ts_request_ops = {
 	.request_cmd		= ETHTOOL_MSG_TS_GET,
 	.reply_cmd		= ETHTOOL_MSG_TS_GET_REPLY,
@@ -69,6 +165,9 @@ const struct ethnl_request_ops ethnl_ts_request_ops = {
 	.prepare_data		= ts_prepare_data,
 	.reply_size		= ts_reply_size,
 	.fill_reply		= ts_fill_reply,
+
+	.set_validate		= ethnl_set_ts_validate,
+	.set			= ethnl_set_ts,
 };
 
 /* TS_LIST_GET */
-- 
cgit v1.2.3


From db840d389bad60ce6f3aadc1079da13e7e993a16 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Fri, 17 Nov 2023 19:46:16 -0800
Subject: bpf: move verbose_linfo() into kernel/bpf/log.c

verifier.c is huge. Let's try to move out parts that are logging-related
into log.c, as we previously did with bpf_log() and other related stuff.
This patch moves line info verbose output routines: it's pretty
self-contained and isolated code, so there is no problem with this.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20231118034623.3320920-2-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf_verifier.h |  4 +++
 kernel/bpf/log.c             | 59 ++++++++++++++++++++++++++++++++++++++++++++
 kernel/bpf/verifier.c        | 57 ------------------------------------------
 3 files changed, 63 insertions(+), 57 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 52a4012b8255..d896f3db6a22 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -680,6 +680,10 @@ int bpf_vlog_init(struct bpf_verifier_log *log, u32 log_level,
 void bpf_vlog_reset(struct bpf_verifier_log *log, u64 new_pos);
 int bpf_vlog_finalize(struct bpf_verifier_log *log, u32 *log_size_actual);
 
+__printf(3, 4) void verbose_linfo(struct bpf_verifier_env *env,
+				  u32 insn_off,
+				  const char *prefix_fmt, ...);
+
 static inline struct bpf_func_state *cur_func(struct bpf_verifier_env *env)
 {
 	struct bpf_verifier_state *cur = env->cur_state;
diff --git a/kernel/bpf/log.c b/kernel/bpf/log.c
index 850494423530..f20e1449c882 100644
--- a/kernel/bpf/log.c
+++ b/kernel/bpf/log.c
@@ -10,6 +10,8 @@
 #include <linux/bpf_verifier.h>
 #include <linux/math64.h>
 
+#define verbose(env, fmt, args...) bpf_verifier_log_write(env, fmt, ##args)
+
 static bool bpf_verifier_log_attr_valid(const struct bpf_verifier_log *log)
 {
 	/* ubuf and len_total should both be specified (or not) together */
@@ -325,3 +327,60 @@ __printf(2, 3) void bpf_log(struct bpf_verifier_log *log,
 	va_end(args);
 }
 EXPORT_SYMBOL_GPL(bpf_log);
+
+static const struct bpf_line_info *
+find_linfo(const struct bpf_verifier_env *env, u32 insn_off)
+{
+	const struct bpf_line_info *linfo;
+	const struct bpf_prog *prog;
+	u32 i, nr_linfo;
+
+	prog = env->prog;
+	nr_linfo = prog->aux->nr_linfo;
+
+	if (!nr_linfo || insn_off >= prog->len)
+		return NULL;
+
+	linfo = prog->aux->linfo;
+	for (i = 1; i < nr_linfo; i++)
+		if (insn_off < linfo[i].insn_off)
+			break;
+
+	return &linfo[i - 1];
+}
+
+static const char *ltrim(const char *s)
+{
+	while (isspace(*s))
+		s++;
+
+	return s;
+}
+
+__printf(3, 4) void verbose_linfo(struct bpf_verifier_env *env,
+				  u32 insn_off,
+				  const char *prefix_fmt, ...)
+{
+	const struct bpf_line_info *linfo;
+
+	if (!bpf_verifier_log_needed(&env->log))
+		return;
+
+	linfo = find_linfo(env, insn_off);
+	if (!linfo || linfo == env->prev_linfo)
+		return;
+
+	if (prefix_fmt) {
+		va_list args;
+
+		va_start(args, prefix_fmt);
+		bpf_verifier_vlog(&env->log, prefix_fmt, args);
+		va_end(args);
+	}
+
+	verbose(env, "%s\n",
+		ltrim(btf_name_by_offset(env->prog->aux->btf,
+					 linfo->line_off)));
+
+	env->prev_linfo = linfo;
+}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 7c3461b89513..683fdda25c13 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -337,27 +337,6 @@ struct btf *btf_vmlinux;
 
 static DEFINE_MUTEX(bpf_verifier_lock);
 
-static const struct bpf_line_info *
-find_linfo(const struct bpf_verifier_env *env, u32 insn_off)
-{
-	const struct bpf_line_info *linfo;
-	const struct bpf_prog *prog;
-	u32 i, nr_linfo;
-
-	prog = env->prog;
-	nr_linfo = prog->aux->nr_linfo;
-
-	if (!nr_linfo || insn_off >= prog->len)
-		return NULL;
-
-	linfo = prog->aux->linfo;
-	for (i = 1; i < nr_linfo; i++)
-		if (insn_off < linfo[i].insn_off)
-			break;
-
-	return &linfo[i - 1];
-}
-
 __printf(2, 3) static void verbose(void *private_data, const char *fmt, ...)
 {
 	struct bpf_verifier_env *env = private_data;
@@ -371,42 +350,6 @@ __printf(2, 3) static void verbose(void *private_data, const char *fmt, ...)
 	va_end(args);
 }
 
-static const char *ltrim(const char *s)
-{
-	while (isspace(*s))
-		s++;
-
-	return s;
-}
-
-__printf(3, 4) static void verbose_linfo(struct bpf_verifier_env *env,
-					 u32 insn_off,
-					 const char *prefix_fmt, ...)
-{
-	const struct bpf_line_info *linfo;
-
-	if (!bpf_verifier_log_needed(&env->log))
-		return;
-
-	linfo = find_linfo(env, insn_off);
-	if (!linfo || linfo == env->prev_linfo)
-		return;
-
-	if (prefix_fmt) {
-		va_list args;
-
-		va_start(args, prefix_fmt);
-		bpf_verifier_vlog(&env->log, prefix_fmt, args);
-		va_end(args);
-	}
-
-	verbose(env, "%s\n",
-		ltrim(btf_name_by_offset(env->prog->aux->btf,
-					 linfo->line_off)));
-
-	env->prev_linfo = linfo;
-}
-
 static void verbose_invalid_scalar(struct bpf_verifier_env *env,
 				   struct bpf_reg_state *reg,
 				   struct tnum *range, const char *ctx,
-- 
cgit v1.2.3


From 42feb6620accded89cad5f455665e21281813d79 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Fri, 17 Nov 2023 19:46:17 -0800
Subject: bpf: move verifier state printing code to kernel/bpf/log.c

Move a good chunk of code from verifier.c to log.c: verifier state
verbose printing logic. This is an important and very much
logging/debugging oriented code. It fits the overlall log.c's focus on
verifier logging, and moving it allows to keep growing it without
unnecessarily adding to verifier.c code that otherwise contains a core
verification logic.

There are not many shared dependencies between this code and the rest of
verifier.c code, except a few single-line helpers for various register
type checks and a bit of state "scratching" helpers. We move all such
trivial helpers into include/bpf/bpf_verifier.h as static inlines.

No functional changes in this patch.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20231118034623.3320920-3-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf_verifier.h |  72 ++++++++
 kernel/bpf/log.c             | 342 ++++++++++++++++++++++++++++++++++++
 kernel/bpf/verifier.c        | 403 -------------------------------------------
 3 files changed, 414 insertions(+), 403 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index d896f3db6a22..39edc76f436e 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -783,4 +783,76 @@ static inline bool bpf_type_has_unsafe_modifiers(u32 type)
 	return type_flag(type) & ~BPF_REG_TRUSTED_MODIFIERS;
 }
 
+static inline bool type_is_ptr_alloc_obj(u32 type)
+{
+	return base_type(type) == PTR_TO_BTF_ID && type_flag(type) & MEM_ALLOC;
+}
+
+static inline bool type_is_non_owning_ref(u32 type)
+{
+	return type_is_ptr_alloc_obj(type) && type_flag(type) & NON_OWN_REF;
+}
+
+static inline bool type_is_pkt_pointer(enum bpf_reg_type type)
+{
+	type = base_type(type);
+	return type == PTR_TO_PACKET ||
+	       type == PTR_TO_PACKET_META;
+}
+
+static inline bool type_is_sk_pointer(enum bpf_reg_type type)
+{
+	return type == PTR_TO_SOCKET ||
+		type == PTR_TO_SOCK_COMMON ||
+		type == PTR_TO_TCP_SOCK ||
+		type == PTR_TO_XDP_SOCK;
+}
+
+static inline void mark_reg_scratched(struct bpf_verifier_env *env, u32 regno)
+{
+	env->scratched_regs |= 1U << regno;
+}
+
+static inline void mark_stack_slot_scratched(struct bpf_verifier_env *env, u32 spi)
+{
+	env->scratched_stack_slots |= 1ULL << spi;
+}
+
+static inline bool reg_scratched(const struct bpf_verifier_env *env, u32 regno)
+{
+	return (env->scratched_regs >> regno) & 1;
+}
+
+static inline bool stack_slot_scratched(const struct bpf_verifier_env *env, u64 regno)
+{
+	return (env->scratched_stack_slots >> regno) & 1;
+}
+
+static inline bool verifier_state_scratched(const struct bpf_verifier_env *env)
+{
+	return env->scratched_regs || env->scratched_stack_slots;
+}
+
+static inline void mark_verifier_state_clean(struct bpf_verifier_env *env)
+{
+	env->scratched_regs = 0U;
+	env->scratched_stack_slots = 0ULL;
+}
+
+/* Used for printing the entire verifier state. */
+static inline void mark_verifier_state_scratched(struct bpf_verifier_env *env)
+{
+	env->scratched_regs = ~0U;
+	env->scratched_stack_slots = ~0ULL;
+}
+
+const char *reg_type_str(struct bpf_verifier_env *env, enum bpf_reg_type type);
+const char *dynptr_type_str(enum bpf_dynptr_type type);
+const char *iter_type_str(const struct btf *btf, u32 btf_id);
+const char *iter_state_str(enum bpf_iter_state state);
+
+void print_verifier_state(struct bpf_verifier_env *env,
+			  const struct bpf_func_state *state, bool print_all);
+void print_insn_state(struct bpf_verifier_env *env, const struct bpf_func_state *state);
+
 #endif /* _LINUX_BPF_VERIFIER_H */
diff --git a/kernel/bpf/log.c b/kernel/bpf/log.c
index f20e1449c882..c1b257eac21b 100644
--- a/kernel/bpf/log.c
+++ b/kernel/bpf/log.c
@@ -384,3 +384,345 @@ __printf(3, 4) void verbose_linfo(struct bpf_verifier_env *env,
 
 	env->prev_linfo = linfo;
 }
+
+static const char *btf_type_name(const struct btf *btf, u32 id)
+{
+	return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off);
+}
+
+/* string representation of 'enum bpf_reg_type'
+ *
+ * Note that reg_type_str() can not appear more than once in a single verbose()
+ * statement.
+ */
+const char *reg_type_str(struct bpf_verifier_env *env, enum bpf_reg_type type)
+{
+	char postfix[16] = {0}, prefix[64] = {0};
+	static const char * const str[] = {
+		[NOT_INIT]		= "?",
+		[SCALAR_VALUE]		= "scalar",
+		[PTR_TO_CTX]		= "ctx",
+		[CONST_PTR_TO_MAP]	= "map_ptr",
+		[PTR_TO_MAP_VALUE]	= "map_value",
+		[PTR_TO_STACK]		= "fp",
+		[PTR_TO_PACKET]		= "pkt",
+		[PTR_TO_PACKET_META]	= "pkt_meta",
+		[PTR_TO_PACKET_END]	= "pkt_end",
+		[PTR_TO_FLOW_KEYS]	= "flow_keys",
+		[PTR_TO_SOCKET]		= "sock",
+		[PTR_TO_SOCK_COMMON]	= "sock_common",
+		[PTR_TO_TCP_SOCK]	= "tcp_sock",
+		[PTR_TO_TP_BUFFER]	= "tp_buffer",
+		[PTR_TO_XDP_SOCK]	= "xdp_sock",
+		[PTR_TO_BTF_ID]		= "ptr_",
+		[PTR_TO_MEM]		= "mem",
+		[PTR_TO_BUF]		= "buf",
+		[PTR_TO_FUNC]		= "func",
+		[PTR_TO_MAP_KEY]	= "map_key",
+		[CONST_PTR_TO_DYNPTR]	= "dynptr_ptr",
+	};
+
+	if (type & PTR_MAYBE_NULL) {
+		if (base_type(type) == PTR_TO_BTF_ID)
+			strncpy(postfix, "or_null_", 16);
+		else
+			strncpy(postfix, "_or_null", 16);
+	}
+
+	snprintf(prefix, sizeof(prefix), "%s%s%s%s%s%s%s",
+		 type & MEM_RDONLY ? "rdonly_" : "",
+		 type & MEM_RINGBUF ? "ringbuf_" : "",
+		 type & MEM_USER ? "user_" : "",
+		 type & MEM_PERCPU ? "percpu_" : "",
+		 type & MEM_RCU ? "rcu_" : "",
+		 type & PTR_UNTRUSTED ? "untrusted_" : "",
+		 type & PTR_TRUSTED ? "trusted_" : ""
+	);
+
+	snprintf(env->tmp_str_buf, TMP_STR_BUF_LEN, "%s%s%s",
+		 prefix, str[base_type(type)], postfix);
+	return env->tmp_str_buf;
+}
+
+const char *dynptr_type_str(enum bpf_dynptr_type type)
+{
+	switch (type) {
+	case BPF_DYNPTR_TYPE_LOCAL:
+		return "local";
+	case BPF_DYNPTR_TYPE_RINGBUF:
+		return "ringbuf";
+	case BPF_DYNPTR_TYPE_SKB:
+		return "skb";
+	case BPF_DYNPTR_TYPE_XDP:
+		return "xdp";
+	case BPF_DYNPTR_TYPE_INVALID:
+		return "<invalid>";
+	default:
+		WARN_ONCE(1, "unknown dynptr type %d\n", type);
+		return "<unknown>";
+	}
+}
+
+const char *iter_type_str(const struct btf *btf, u32 btf_id)
+{
+	if (!btf || btf_id == 0)
+		return "<invalid>";
+
+	/* we already validated that type is valid and has conforming name */
+	return btf_type_name(btf, btf_id) + sizeof(ITER_PREFIX) - 1;
+}
+
+const char *iter_state_str(enum bpf_iter_state state)
+{
+	switch (state) {
+	case BPF_ITER_STATE_ACTIVE:
+		return "active";
+	case BPF_ITER_STATE_DRAINED:
+		return "drained";
+	case BPF_ITER_STATE_INVALID:
+		return "<invalid>";
+	default:
+		WARN_ONCE(1, "unknown iter state %d\n", state);
+		return "<unknown>";
+	}
+}
+
+static char slot_type_char[] = {
+	[STACK_INVALID]	= '?',
+	[STACK_SPILL]	= 'r',
+	[STACK_MISC]	= 'm',
+	[STACK_ZERO]	= '0',
+	[STACK_DYNPTR]	= 'd',
+	[STACK_ITER]	= 'i',
+};
+
+static void print_liveness(struct bpf_verifier_env *env,
+			   enum bpf_reg_liveness live)
+{
+	if (live & (REG_LIVE_READ | REG_LIVE_WRITTEN | REG_LIVE_DONE))
+	    verbose(env, "_");
+	if (live & REG_LIVE_READ)
+		verbose(env, "r");
+	if (live & REG_LIVE_WRITTEN)
+		verbose(env, "w");
+	if (live & REG_LIVE_DONE)
+		verbose(env, "D");
+}
+
+static void print_scalar_ranges(struct bpf_verifier_env *env,
+				const struct bpf_reg_state *reg,
+				const char **sep)
+{
+	struct {
+		const char *name;
+		u64 val;
+		bool omit;
+	} minmaxs[] = {
+		{"smin",   reg->smin_value,         reg->smin_value == S64_MIN},
+		{"smax",   reg->smax_value,         reg->smax_value == S64_MAX},
+		{"umin",   reg->umin_value,         reg->umin_value == 0},
+		{"umax",   reg->umax_value,         reg->umax_value == U64_MAX},
+		{"smin32", (s64)reg->s32_min_value, reg->s32_min_value == S32_MIN},
+		{"smax32", (s64)reg->s32_max_value, reg->s32_max_value == S32_MAX},
+		{"umin32", reg->u32_min_value,      reg->u32_min_value == 0},
+		{"umax32", reg->u32_max_value,      reg->u32_max_value == U32_MAX},
+	}, *m1, *m2, *mend = &minmaxs[ARRAY_SIZE(minmaxs)];
+	bool neg1, neg2;
+
+	for (m1 = &minmaxs[0]; m1 < mend; m1++) {
+		if (m1->omit)
+			continue;
+
+		neg1 = m1->name[0] == 's' && (s64)m1->val < 0;
+
+		verbose(env, "%s%s=", *sep, m1->name);
+		*sep = ",";
+
+		for (m2 = m1 + 2; m2 < mend; m2 += 2) {
+			if (m2->omit || m2->val != m1->val)
+				continue;
+			/* don't mix negatives with positives */
+			neg2 = m2->name[0] == 's' && (s64)m2->val < 0;
+			if (neg2 != neg1)
+				continue;
+			m2->omit = true;
+			verbose(env, "%s=", m2->name);
+		}
+
+		verbose(env, m1->name[0] == 's' ? "%lld" : "%llu", m1->val);
+	}
+}
+
+void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_func_state *state,
+			  bool print_all)
+{
+	const struct bpf_reg_state *reg;
+	enum bpf_reg_type t;
+	int i;
+
+	if (state->frameno)
+		verbose(env, " frame%d:", state->frameno);
+	for (i = 0; i < MAX_BPF_REG; i++) {
+		reg = &state->regs[i];
+		t = reg->type;
+		if (t == NOT_INIT)
+			continue;
+		if (!print_all && !reg_scratched(env, i))
+			continue;
+		verbose(env, " R%d", i);
+		print_liveness(env, reg->live);
+		verbose(env, "=");
+		if (t == SCALAR_VALUE && reg->precise)
+			verbose(env, "P");
+		if ((t == SCALAR_VALUE || t == PTR_TO_STACK) &&
+		    tnum_is_const(reg->var_off)) {
+			/* reg->off should be 0 for SCALAR_VALUE */
+			verbose(env, "%s", t == SCALAR_VALUE ? "" : reg_type_str(env, t));
+			verbose(env, "%lld", reg->var_off.value + reg->off);
+		} else {
+			const char *sep = "";
+
+			verbose(env, "%s", reg_type_str(env, t));
+			if (base_type(t) == PTR_TO_BTF_ID)
+				verbose(env, "%s", btf_type_name(reg->btf, reg->btf_id));
+			verbose(env, "(");
+/*
+ * _a stands for append, was shortened to avoid multiline statements below.
+ * This macro is used to output a comma separated list of attributes.
+ */
+#define verbose_a(fmt, ...) ({ verbose(env, "%s" fmt, sep, __VA_ARGS__); sep = ","; })
+
+			if (reg->id)
+				verbose_a("id=%d", reg->id);
+			if (reg->ref_obj_id)
+				verbose_a("ref_obj_id=%d", reg->ref_obj_id);
+			if (type_is_non_owning_ref(reg->type))
+				verbose_a("%s", "non_own_ref");
+			if (t != SCALAR_VALUE)
+				verbose_a("off=%d", reg->off);
+			if (type_is_pkt_pointer(t))
+				verbose_a("r=%d", reg->range);
+			else if (base_type(t) == CONST_PTR_TO_MAP ||
+				 base_type(t) == PTR_TO_MAP_KEY ||
+				 base_type(t) == PTR_TO_MAP_VALUE)
+				verbose_a("ks=%d,vs=%d",
+					  reg->map_ptr->key_size,
+					  reg->map_ptr->value_size);
+			if (tnum_is_const(reg->var_off)) {
+				/* Typically an immediate SCALAR_VALUE, but
+				 * could be a pointer whose offset is too big
+				 * for reg->off
+				 */
+				verbose_a("imm=%llx", reg->var_off.value);
+			} else {
+				print_scalar_ranges(env, reg, &sep);
+				if (!tnum_is_unknown(reg->var_off)) {
+					char tn_buf[48];
+
+					tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+					verbose_a("var_off=%s", tn_buf);
+				}
+			}
+#undef verbose_a
+
+			verbose(env, ")");
+		}
+	}
+	for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
+		char types_buf[BPF_REG_SIZE + 1];
+		bool valid = false;
+		int j;
+
+		for (j = 0; j < BPF_REG_SIZE; j++) {
+			if (state->stack[i].slot_type[j] != STACK_INVALID)
+				valid = true;
+			types_buf[j] = slot_type_char[state->stack[i].slot_type[j]];
+		}
+		types_buf[BPF_REG_SIZE] = 0;
+		if (!valid)
+			continue;
+		if (!print_all && !stack_slot_scratched(env, i))
+			continue;
+		switch (state->stack[i].slot_type[BPF_REG_SIZE - 1]) {
+		case STACK_SPILL:
+			reg = &state->stack[i].spilled_ptr;
+			t = reg->type;
+
+			verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
+			print_liveness(env, reg->live);
+			verbose(env, "=%s", t == SCALAR_VALUE ? "" : reg_type_str(env, t));
+			if (t == SCALAR_VALUE && reg->precise)
+				verbose(env, "P");
+			if (t == SCALAR_VALUE && tnum_is_const(reg->var_off))
+				verbose(env, "%lld", reg->var_off.value + reg->off);
+			break;
+		case STACK_DYNPTR:
+			i += BPF_DYNPTR_NR_SLOTS - 1;
+			reg = &state->stack[i].spilled_ptr;
+
+			verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
+			print_liveness(env, reg->live);
+			verbose(env, "=dynptr_%s", dynptr_type_str(reg->dynptr.type));
+			if (reg->ref_obj_id)
+				verbose(env, "(ref_id=%d)", reg->ref_obj_id);
+			break;
+		case STACK_ITER:
+			/* only main slot has ref_obj_id set; skip others */
+			reg = &state->stack[i].spilled_ptr;
+			if (!reg->ref_obj_id)
+				continue;
+
+			verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
+			print_liveness(env, reg->live);
+			verbose(env, "=iter_%s(ref_id=%d,state=%s,depth=%u)",
+				iter_type_str(reg->iter.btf, reg->iter.btf_id),
+				reg->ref_obj_id, iter_state_str(reg->iter.state),
+				reg->iter.depth);
+			break;
+		case STACK_MISC:
+		case STACK_ZERO:
+		default:
+			reg = &state->stack[i].spilled_ptr;
+
+			for (j = 0; j < BPF_REG_SIZE; j++)
+				types_buf[j] = slot_type_char[state->stack[i].slot_type[j]];
+			types_buf[BPF_REG_SIZE] = 0;
+
+			verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
+			print_liveness(env, reg->live);
+			verbose(env, "=%s", types_buf);
+			break;
+		}
+	}
+	if (state->acquired_refs && state->refs[0].id) {
+		verbose(env, " refs=%d", state->refs[0].id);
+		for (i = 1; i < state->acquired_refs; i++)
+			if (state->refs[i].id)
+				verbose(env, ",%d", state->refs[i].id);
+	}
+	if (state->in_callback_fn)
+		verbose(env, " cb");
+	if (state->in_async_callback_fn)
+		verbose(env, " async_cb");
+	verbose(env, "\n");
+	if (!print_all)
+		mark_verifier_state_clean(env);
+}
+
+static inline u32 vlog_alignment(u32 pos)
+{
+	return round_up(max(pos + BPF_LOG_MIN_ALIGNMENT / 2, BPF_LOG_ALIGNMENT),
+			BPF_LOG_MIN_ALIGNMENT) - pos - 1;
+}
+
+void print_insn_state(struct bpf_verifier_env *env, const struct bpf_func_state *state)
+{
+	if (env->prev_log_pos && env->prev_log_pos == env->log.end_pos) {
+		/* remove new line character */
+		bpf_vlog_reset(&env->log, env->prev_log_pos - 1);
+		verbose(env, "%*c;", vlog_alignment(env->prev_insn_print_pos), ' ');
+	} else {
+		verbose(env, "%d:", env->insn_idx);
+	}
+	print_verifier_state(env, state, false);
+}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 683fdda25c13..8c2d31aa3d31 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -368,21 +368,6 @@ static void verbose_invalid_scalar(struct bpf_verifier_env *env,
 	verbose(env, " should have been in %s\n", tn_buf);
 }
 
-static bool type_is_pkt_pointer(enum bpf_reg_type type)
-{
-	type = base_type(type);
-	return type == PTR_TO_PACKET ||
-	       type == PTR_TO_PACKET_META;
-}
-
-static bool type_is_sk_pointer(enum bpf_reg_type type)
-{
-	return type == PTR_TO_SOCKET ||
-		type == PTR_TO_SOCK_COMMON ||
-		type == PTR_TO_TCP_SOCK ||
-		type == PTR_TO_XDP_SOCK;
-}
-
 static bool type_may_be_null(u32 type)
 {
 	return type & PTR_MAYBE_NULL;
@@ -406,16 +391,6 @@ static bool reg_not_null(const struct bpf_reg_state *reg)
 		type == PTR_TO_MEM;
 }
 
-static bool type_is_ptr_alloc_obj(u32 type)
-{
-	return base_type(type) == PTR_TO_BTF_ID && type_flag(type) & MEM_ALLOC;
-}
-
-static bool type_is_non_owning_ref(u32 type)
-{
-	return type_is_ptr_alloc_obj(type) && type_flag(type) & NON_OWN_REF;
-}
-
 static struct btf_record *reg_btf_record(const struct bpf_reg_state *reg)
 {
 	struct btf_record *rec = NULL;
@@ -532,83 +507,6 @@ static bool is_cmpxchg_insn(const struct bpf_insn *insn)
 	       insn->imm == BPF_CMPXCHG;
 }
 
-/* string representation of 'enum bpf_reg_type'
- *
- * Note that reg_type_str() can not appear more than once in a single verbose()
- * statement.
- */
-static const char *reg_type_str(struct bpf_verifier_env *env,
-				enum bpf_reg_type type)
-{
-	char postfix[16] = {0}, prefix[64] = {0};
-	static const char * const str[] = {
-		[NOT_INIT]		= "?",
-		[SCALAR_VALUE]		= "scalar",
-		[PTR_TO_CTX]		= "ctx",
-		[CONST_PTR_TO_MAP]	= "map_ptr",
-		[PTR_TO_MAP_VALUE]	= "map_value",
-		[PTR_TO_STACK]		= "fp",
-		[PTR_TO_PACKET]		= "pkt",
-		[PTR_TO_PACKET_META]	= "pkt_meta",
-		[PTR_TO_PACKET_END]	= "pkt_end",
-		[PTR_TO_FLOW_KEYS]	= "flow_keys",
-		[PTR_TO_SOCKET]		= "sock",
-		[PTR_TO_SOCK_COMMON]	= "sock_common",
-		[PTR_TO_TCP_SOCK]	= "tcp_sock",
-		[PTR_TO_TP_BUFFER]	= "tp_buffer",
-		[PTR_TO_XDP_SOCK]	= "xdp_sock",
-		[PTR_TO_BTF_ID]		= "ptr_",
-		[PTR_TO_MEM]		= "mem",
-		[PTR_TO_BUF]		= "buf",
-		[PTR_TO_FUNC]		= "func",
-		[PTR_TO_MAP_KEY]	= "map_key",
-		[CONST_PTR_TO_DYNPTR]	= "dynptr_ptr",
-	};
-
-	if (type & PTR_MAYBE_NULL) {
-		if (base_type(type) == PTR_TO_BTF_ID)
-			strncpy(postfix, "or_null_", 16);
-		else
-			strncpy(postfix, "_or_null", 16);
-	}
-
-	snprintf(prefix, sizeof(prefix), "%s%s%s%s%s%s%s",
-		 type & MEM_RDONLY ? "rdonly_" : "",
-		 type & MEM_RINGBUF ? "ringbuf_" : "",
-		 type & MEM_USER ? "user_" : "",
-		 type & MEM_PERCPU ? "percpu_" : "",
-		 type & MEM_RCU ? "rcu_" : "",
-		 type & PTR_UNTRUSTED ? "untrusted_" : "",
-		 type & PTR_TRUSTED ? "trusted_" : ""
-	);
-
-	snprintf(env->tmp_str_buf, TMP_STR_BUF_LEN, "%s%s%s",
-		 prefix, str[base_type(type)], postfix);
-	return env->tmp_str_buf;
-}
-
-static char slot_type_char[] = {
-	[STACK_INVALID]	= '?',
-	[STACK_SPILL]	= 'r',
-	[STACK_MISC]	= 'm',
-	[STACK_ZERO]	= '0',
-	[STACK_DYNPTR]	= 'd',
-	[STACK_ITER]	= 'i',
-};
-
-static void print_liveness(struct bpf_verifier_env *env,
-			   enum bpf_reg_liveness live)
-{
-	if (live & (REG_LIVE_READ | REG_LIVE_WRITTEN | REG_LIVE_DONE))
-	    verbose(env, "_");
-	if (live & REG_LIVE_READ)
-		verbose(env, "r");
-	if (live & REG_LIVE_WRITTEN)
-		verbose(env, "w");
-	if (live & REG_LIVE_DONE)
-		verbose(env, "D");
-}
-
 static int __get_spi(s32 off)
 {
 	return (-off - 1) / BPF_REG_SIZE;
@@ -678,87 +576,6 @@ static const char *btf_type_name(const struct btf *btf, u32 id)
 	return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off);
 }
 
-static const char *dynptr_type_str(enum bpf_dynptr_type type)
-{
-	switch (type) {
-	case BPF_DYNPTR_TYPE_LOCAL:
-		return "local";
-	case BPF_DYNPTR_TYPE_RINGBUF:
-		return "ringbuf";
-	case BPF_DYNPTR_TYPE_SKB:
-		return "skb";
-	case BPF_DYNPTR_TYPE_XDP:
-		return "xdp";
-	case BPF_DYNPTR_TYPE_INVALID:
-		return "<invalid>";
-	default:
-		WARN_ONCE(1, "unknown dynptr type %d\n", type);
-		return "<unknown>";
-	}
-}
-
-static const char *iter_type_str(const struct btf *btf, u32 btf_id)
-{
-	if (!btf || btf_id == 0)
-		return "<invalid>";
-
-	/* we already validated that type is valid and has conforming name */
-	return btf_type_name(btf, btf_id) + sizeof(ITER_PREFIX) - 1;
-}
-
-static const char *iter_state_str(enum bpf_iter_state state)
-{
-	switch (state) {
-	case BPF_ITER_STATE_ACTIVE:
-		return "active";
-	case BPF_ITER_STATE_DRAINED:
-		return "drained";
-	case BPF_ITER_STATE_INVALID:
-		return "<invalid>";
-	default:
-		WARN_ONCE(1, "unknown iter state %d\n", state);
-		return "<unknown>";
-	}
-}
-
-static void mark_reg_scratched(struct bpf_verifier_env *env, u32 regno)
-{
-	env->scratched_regs |= 1U << regno;
-}
-
-static void mark_stack_slot_scratched(struct bpf_verifier_env *env, u32 spi)
-{
-	env->scratched_stack_slots |= 1ULL << spi;
-}
-
-static bool reg_scratched(const struct bpf_verifier_env *env, u32 regno)
-{
-	return (env->scratched_regs >> regno) & 1;
-}
-
-static bool stack_slot_scratched(const struct bpf_verifier_env *env, u64 regno)
-{
-	return (env->scratched_stack_slots >> regno) & 1;
-}
-
-static bool verifier_state_scratched(const struct bpf_verifier_env *env)
-{
-	return env->scratched_regs || env->scratched_stack_slots;
-}
-
-static void mark_verifier_state_clean(struct bpf_verifier_env *env)
-{
-	env->scratched_regs = 0U;
-	env->scratched_stack_slots = 0ULL;
-}
-
-/* Used for printing the entire verifier state. */
-static void mark_verifier_state_scratched(struct bpf_verifier_env *env)
-{
-	env->scratched_regs = ~0U;
-	env->scratched_stack_slots = ~0ULL;
-}
-
 static enum bpf_dynptr_type arg_to_dynptr_type(enum bpf_arg_type arg_type)
 {
 	switch (arg_type & DYNPTR_TYPE_FLAG_MASK) {
@@ -1298,226 +1115,6 @@ static void scrub_spilled_slot(u8 *stype)
 		*stype = STACK_MISC;
 }
 
-static void print_scalar_ranges(struct bpf_verifier_env *env,
-				const struct bpf_reg_state *reg,
-				const char **sep)
-{
-	struct {
-		const char *name;
-		u64 val;
-		bool omit;
-	} minmaxs[] = {
-		{"smin",   reg->smin_value,         reg->smin_value == S64_MIN},
-		{"smax",   reg->smax_value,         reg->smax_value == S64_MAX},
-		{"umin",   reg->umin_value,         reg->umin_value == 0},
-		{"umax",   reg->umax_value,         reg->umax_value == U64_MAX},
-		{"smin32", (s64)reg->s32_min_value, reg->s32_min_value == S32_MIN},
-		{"smax32", (s64)reg->s32_max_value, reg->s32_max_value == S32_MAX},
-		{"umin32", reg->u32_min_value,      reg->u32_min_value == 0},
-		{"umax32", reg->u32_max_value,      reg->u32_max_value == U32_MAX},
-	}, *m1, *m2, *mend = &minmaxs[ARRAY_SIZE(minmaxs)];
-	bool neg1, neg2;
-
-	for (m1 = &minmaxs[0]; m1 < mend; m1++) {
-		if (m1->omit)
-			continue;
-
-		neg1 = m1->name[0] == 's' && (s64)m1->val < 0;
-
-		verbose(env, "%s%s=", *sep, m1->name);
-		*sep = ",";
-
-		for (m2 = m1 + 2; m2 < mend; m2 += 2) {
-			if (m2->omit || m2->val != m1->val)
-				continue;
-			/* don't mix negatives with positives */
-			neg2 = m2->name[0] == 's' && (s64)m2->val < 0;
-			if (neg2 != neg1)
-				continue;
-			m2->omit = true;
-			verbose(env, "%s=", m2->name);
-		}
-
-		verbose(env, m1->name[0] == 's' ? "%lld" : "%llu", m1->val);
-	}
-}
-
-static void print_verifier_state(struct bpf_verifier_env *env,
-				 const struct bpf_func_state *state,
-				 bool print_all)
-{
-	const struct bpf_reg_state *reg;
-	enum bpf_reg_type t;
-	int i;
-
-	if (state->frameno)
-		verbose(env, " frame%d:", state->frameno);
-	for (i = 0; i < MAX_BPF_REG; i++) {
-		reg = &state->regs[i];
-		t = reg->type;
-		if (t == NOT_INIT)
-			continue;
-		if (!print_all && !reg_scratched(env, i))
-			continue;
-		verbose(env, " R%d", i);
-		print_liveness(env, reg->live);
-		verbose(env, "=");
-		if (t == SCALAR_VALUE && reg->precise)
-			verbose(env, "P");
-		if ((t == SCALAR_VALUE || t == PTR_TO_STACK) &&
-		    tnum_is_const(reg->var_off)) {
-			/* reg->off should be 0 for SCALAR_VALUE */
-			verbose(env, "%s", t == SCALAR_VALUE ? "" : reg_type_str(env, t));
-			verbose(env, "%lld", reg->var_off.value + reg->off);
-		} else {
-			const char *sep = "";
-
-			verbose(env, "%s", reg_type_str(env, t));
-			if (base_type(t) == PTR_TO_BTF_ID)
-				verbose(env, "%s", btf_type_name(reg->btf, reg->btf_id));
-			verbose(env, "(");
-/*
- * _a stands for append, was shortened to avoid multiline statements below.
- * This macro is used to output a comma separated list of attributes.
- */
-#define verbose_a(fmt, ...) ({ verbose(env, "%s" fmt, sep, __VA_ARGS__); sep = ","; })
-
-			if (reg->id)
-				verbose_a("id=%d", reg->id);
-			if (reg->ref_obj_id)
-				verbose_a("ref_obj_id=%d", reg->ref_obj_id);
-			if (type_is_non_owning_ref(reg->type))
-				verbose_a("%s", "non_own_ref");
-			if (t != SCALAR_VALUE)
-				verbose_a("off=%d", reg->off);
-			if (type_is_pkt_pointer(t))
-				verbose_a("r=%d", reg->range);
-			else if (base_type(t) == CONST_PTR_TO_MAP ||
-				 base_type(t) == PTR_TO_MAP_KEY ||
-				 base_type(t) == PTR_TO_MAP_VALUE)
-				verbose_a("ks=%d,vs=%d",
-					  reg->map_ptr->key_size,
-					  reg->map_ptr->value_size);
-			if (tnum_is_const(reg->var_off)) {
-				/* Typically an immediate SCALAR_VALUE, but
-				 * could be a pointer whose offset is too big
-				 * for reg->off
-				 */
-				verbose_a("imm=%llx", reg->var_off.value);
-			} else {
-				print_scalar_ranges(env, reg, &sep);
-				if (!tnum_is_unknown(reg->var_off)) {
-					char tn_buf[48];
-
-					tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
-					verbose_a("var_off=%s", tn_buf);
-				}
-			}
-#undef verbose_a
-
-			verbose(env, ")");
-		}
-	}
-	for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
-		char types_buf[BPF_REG_SIZE + 1];
-		bool valid = false;
-		int j;
-
-		for (j = 0; j < BPF_REG_SIZE; j++) {
-			if (state->stack[i].slot_type[j] != STACK_INVALID)
-				valid = true;
-			types_buf[j] = slot_type_char[state->stack[i].slot_type[j]];
-		}
-		types_buf[BPF_REG_SIZE] = 0;
-		if (!valid)
-			continue;
-		if (!print_all && !stack_slot_scratched(env, i))
-			continue;
-		switch (state->stack[i].slot_type[BPF_REG_SIZE - 1]) {
-		case STACK_SPILL:
-			reg = &state->stack[i].spilled_ptr;
-			t = reg->type;
-
-			verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
-			print_liveness(env, reg->live);
-			verbose(env, "=%s", t == SCALAR_VALUE ? "" : reg_type_str(env, t));
-			if (t == SCALAR_VALUE && reg->precise)
-				verbose(env, "P");
-			if (t == SCALAR_VALUE && tnum_is_const(reg->var_off))
-				verbose(env, "%lld", reg->var_off.value + reg->off);
-			break;
-		case STACK_DYNPTR:
-			i += BPF_DYNPTR_NR_SLOTS - 1;
-			reg = &state->stack[i].spilled_ptr;
-
-			verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
-			print_liveness(env, reg->live);
-			verbose(env, "=dynptr_%s", dynptr_type_str(reg->dynptr.type));
-			if (reg->ref_obj_id)
-				verbose(env, "(ref_id=%d)", reg->ref_obj_id);
-			break;
-		case STACK_ITER:
-			/* only main slot has ref_obj_id set; skip others */
-			reg = &state->stack[i].spilled_ptr;
-			if (!reg->ref_obj_id)
-				continue;
-
-			verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
-			print_liveness(env, reg->live);
-			verbose(env, "=iter_%s(ref_id=%d,state=%s,depth=%u)",
-				iter_type_str(reg->iter.btf, reg->iter.btf_id),
-				reg->ref_obj_id, iter_state_str(reg->iter.state),
-				reg->iter.depth);
-			break;
-		case STACK_MISC:
-		case STACK_ZERO:
-		default:
-			reg = &state->stack[i].spilled_ptr;
-
-			for (j = 0; j < BPF_REG_SIZE; j++)
-				types_buf[j] = slot_type_char[state->stack[i].slot_type[j]];
-			types_buf[BPF_REG_SIZE] = 0;
-
-			verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
-			print_liveness(env, reg->live);
-			verbose(env, "=%s", types_buf);
-			break;
-		}
-	}
-	if (state->acquired_refs && state->refs[0].id) {
-		verbose(env, " refs=%d", state->refs[0].id);
-		for (i = 1; i < state->acquired_refs; i++)
-			if (state->refs[i].id)
-				verbose(env, ",%d", state->refs[i].id);
-	}
-	if (state->in_callback_fn)
-		verbose(env, " cb");
-	if (state->in_async_callback_fn)
-		verbose(env, " async_cb");
-	verbose(env, "\n");
-	if (!print_all)
-		mark_verifier_state_clean(env);
-}
-
-static inline u32 vlog_alignment(u32 pos)
-{
-	return round_up(max(pos + BPF_LOG_MIN_ALIGNMENT / 2, BPF_LOG_ALIGNMENT),
-			BPF_LOG_MIN_ALIGNMENT) - pos - 1;
-}
-
-static void print_insn_state(struct bpf_verifier_env *env,
-			     const struct bpf_func_state *state)
-{
-	if (env->prev_log_pos && env->prev_log_pos == env->log.end_pos) {
-		/* remove new line character */
-		bpf_vlog_reset(&env->log, env->prev_log_pos - 1);
-		verbose(env, "%*c;", vlog_alignment(env->prev_insn_print_pos), ' ');
-	} else {
-		verbose(env, "%d:", env->insn_idx);
-	}
-	print_verifier_state(env, state, false);
-}
-
 /* copy array src of length n * size bytes to dst. dst is reallocated if it's too
  * small to hold src. This is different from krealloc since we don't want to preserve
  * the contents of dst.
-- 
cgit v1.2.3


From acfde6e8abee6b23e53b08606f861d9124288030 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 4 Nov 2023 00:10:18 -0400
Subject: struct dentry: get rid of randomize_layout idiocy

This is beyond ridiculous.  There is a reason why that thing is
cacheline-aligned...

Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/dcache.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 3da2f0545d5d..1d9f7f132055 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -111,7 +111,7 @@ struct dentry {
 		struct hlist_bl_node d_in_lookup_hash;	/* only for in-lookup ones */
 	 	struct rcu_head d_rcu;
 	} d_u;
-} __randomize_layout;
+};
 
 /*
  * dentry->d_lock spinlock nesting subclasses:
-- 
cgit v1.2.3


From 641c3ef5cb68a1426d42e6d3aba16db9bdfbe94f Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 10 Nov 2023 12:46:30 -0500
Subject: DCACHE_... ->d_flags bits: switch to BIT()

For bits 20..22 (inode type cached in ->d_flags) turn the definitions into
expressions like (5 << 20); everything else turns into straight use of
BIT()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/dcache.h | 76 +++++++++++++++++++++++++-------------------------
 1 file changed, 38 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 1d9f7f132055..d9c314cc93b8 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -151,13 +151,13 @@ struct dentry_operations {
  */
 
 /* d_flags entries */
-#define DCACHE_OP_HASH			0x00000001
-#define DCACHE_OP_COMPARE		0x00000002
-#define DCACHE_OP_REVALIDATE		0x00000004
-#define DCACHE_OP_DELETE		0x00000008
-#define DCACHE_OP_PRUNE			0x00000010
+#define DCACHE_OP_HASH			BIT(0)
+#define DCACHE_OP_COMPARE		BIT(1)
+#define DCACHE_OP_REVALIDATE		BIT(2)
+#define DCACHE_OP_DELETE		BIT(3)
+#define DCACHE_OP_PRUNE			BIT(4)
 
-#define	DCACHE_DISCONNECTED		0x00000020
+#define	DCACHE_DISCONNECTED		BIT(5)
      /* This dentry is possibly not currently connected to the dcache tree, in
       * which case its parent will either be itself, or will have this flag as
       * well.  nfsd will not use a dentry with this bit set, but will first
@@ -168,50 +168,50 @@ struct dentry_operations {
       * dentry into place and return that dentry rather than the passed one,
       * typically using d_splice_alias. */
 
-#define DCACHE_REFERENCED		0x00000040 /* Recently used, don't discard. */
+#define DCACHE_REFERENCED		BIT(6) /* Recently used, don't discard. */
 
-#define DCACHE_DONTCACHE		0x00000080 /* Purge from memory on final dput() */
+#define DCACHE_DONTCACHE		BIT(7) /* Purge from memory on final dput() */
 
-#define DCACHE_CANT_MOUNT		0x00000100
-#define DCACHE_GENOCIDE			0x00000200
-#define DCACHE_SHRINK_LIST		0x00000400
+#define DCACHE_CANT_MOUNT		BIT(8)
+#define DCACHE_GENOCIDE			BIT(9)
+#define DCACHE_SHRINK_LIST		BIT(10)
 
-#define DCACHE_OP_WEAK_REVALIDATE	0x00000800
+#define DCACHE_OP_WEAK_REVALIDATE	BIT(11)
 
-#define DCACHE_NFSFS_RENAMED		0x00001000
+#define DCACHE_NFSFS_RENAMED		BIT(12)
      /* this dentry has been "silly renamed" and has to be deleted on the last
       * dput() */
-#define DCACHE_COOKIE			0x00002000 /* For use by dcookie subsystem */
-#define DCACHE_FSNOTIFY_PARENT_WATCHED	0x00004000
+#define DCACHE_COOKIE			BIT(13) /* For use by dcookie subsystem */
+#define DCACHE_FSNOTIFY_PARENT_WATCHED	BIT(14)
      /* Parent inode is watched by some fsnotify listener */
 
-#define DCACHE_DENTRY_KILLED		0x00008000
+#define DCACHE_DENTRY_KILLED		BIT(15)
 
-#define DCACHE_MOUNTED			0x00010000 /* is a mountpoint */
-#define DCACHE_NEED_AUTOMOUNT		0x00020000 /* handle automount on this dir */
-#define DCACHE_MANAGE_TRANSIT		0x00040000 /* manage transit from this dirent */
+#define DCACHE_MOUNTED			BIT(16) /* is a mountpoint */
+#define DCACHE_NEED_AUTOMOUNT		BIT(17) /* handle automount on this dir */
+#define DCACHE_MANAGE_TRANSIT		BIT(18) /* manage transit from this dirent */
 #define DCACHE_MANAGED_DENTRY \
 	(DCACHE_MOUNTED|DCACHE_NEED_AUTOMOUNT|DCACHE_MANAGE_TRANSIT)
 
-#define DCACHE_LRU_LIST			0x00080000
-
-#define DCACHE_ENTRY_TYPE		0x00700000
-#define DCACHE_MISS_TYPE		0x00000000 /* Negative dentry (maybe fallthru to nowhere) */
-#define DCACHE_WHITEOUT_TYPE		0x00100000 /* Whiteout dentry (stop pathwalk) */
-#define DCACHE_DIRECTORY_TYPE		0x00200000 /* Normal directory */
-#define DCACHE_AUTODIR_TYPE		0x00300000 /* Lookupless directory (presumed automount) */
-#define DCACHE_REGULAR_TYPE		0x00400000 /* Regular file type (or fallthru to such) */
-#define DCACHE_SPECIAL_TYPE		0x00500000 /* Other file type (or fallthru to such) */
-#define DCACHE_SYMLINK_TYPE		0x00600000 /* Symlink (or fallthru to such) */
-
-#define DCACHE_MAY_FREE			0x00800000
-#define DCACHE_FALLTHRU			0x01000000 /* Fall through to lower layer */
-#define DCACHE_NOKEY_NAME		0x02000000 /* Encrypted name encoded without key */
-#define DCACHE_OP_REAL			0x04000000
-
-#define DCACHE_PAR_LOOKUP		0x10000000 /* being looked up (with parent locked shared) */
-#define DCACHE_DENTRY_CURSOR		0x20000000
-#define DCACHE_NORCU			0x40000000 /* No RCU delay for freeing */
+#define DCACHE_LRU_LIST			BIT(19)
+
+#define DCACHE_ENTRY_TYPE		(7 << 20) /* bits 20..22 are for storing type: */
+#define DCACHE_MISS_TYPE		(0 << 20) /* Negative dentry (maybe fallthru to nowhere) */
+#define DCACHE_WHITEOUT_TYPE		(1 << 20) /* Whiteout dentry (stop pathwalk) */
+#define DCACHE_DIRECTORY_TYPE		(2 << 20) /* Normal directory */
+#define DCACHE_AUTODIR_TYPE		(3 << 20) /* Lookupless directory (presumed automount) */
+#define DCACHE_REGULAR_TYPE		(4 << 20) /* Regular file type (or fallthru to such) */
+#define DCACHE_SPECIAL_TYPE		(5 << 20) /* Other file type (or fallthru to such) */
+#define DCACHE_SYMLINK_TYPE		(6 << 20) /* Symlink (or fallthru to such) */
+
+#define DCACHE_MAY_FREE			BIT(23)
+#define DCACHE_FALLTHRU			BIT(24) /* Fall through to lower layer */
+#define DCACHE_NOKEY_NAME		BIT(25) /* Encrypted name encoded without key */
+#define DCACHE_OP_REAL			BIT(26)
+
+#define DCACHE_PAR_LOOKUP		BIT(28) /* being looked up (with parent locked shared) */
+#define DCACHE_DENTRY_CURSOR		BIT(29)
+#define DCACHE_NORCU			BIT(30) /* No RCU delay for freeing */
 
 extern seqlock_t rename_lock;
 
-- 
cgit v1.2.3


From 0bec65a80f1b1ebcda05286e539a204713b70353 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 10 Nov 2023 12:50:29 -0500
Subject: DCACHE_COOKIE: RIP

the last user gone in 2021...

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/dcache.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index d9c314cc93b8..92c0b2a1ae2e 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -181,7 +181,6 @@ struct dentry_operations {
 #define DCACHE_NFSFS_RENAMED		BIT(12)
      /* this dentry has been "silly renamed" and has to be deleted on the last
       * dput() */
-#define DCACHE_COOKIE			BIT(13) /* For use by dcookie subsystem */
 #define DCACHE_FSNOTIFY_PARENT_WATCHED	BIT(14)
      /* Parent inode is watched by some fsnotify listener */
 
-- 
cgit v1.2.3


From 8219cb58feddcf28909072015f4e17e29f68c41a Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 10 Nov 2023 14:32:05 -0500
Subject: kill d_{is,set}_fallthru()

Introduced in 2015 and never had any in-tree users...

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/dcache.c            | 20 ++------------------
 include/linux/dcache.h | 17 ++++-------------
 2 files changed, 6 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/fs/dcache.c b/fs/dcache.c
index b8f1b54a1492..9f5b2b5c1e6d 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -344,7 +344,7 @@ static inline void __d_set_inode_and_type(struct dentry *dentry,
 
 	dentry->d_inode = inode;
 	flags = READ_ONCE(dentry->d_flags);
-	flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU);
+	flags &= ~DCACHE_ENTRY_TYPE;
 	flags |= type_flags;
 	smp_store_release(&dentry->d_flags, flags);
 }
@@ -353,7 +353,7 @@ static inline void __d_clear_type_and_inode(struct dentry *dentry)
 {
 	unsigned flags = READ_ONCE(dentry->d_flags);
 
-	flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU);
+	flags &= ~DCACHE_ENTRY_TYPE;
 	WRITE_ONCE(dentry->d_flags, flags);
 	dentry->d_inode = NULL;
 	if (dentry->d_flags & DCACHE_LRU_LIST)
@@ -1936,22 +1936,6 @@ void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op)
 }
 EXPORT_SYMBOL(d_set_d_op);
 
-
-/*
- * d_set_fallthru - Mark a dentry as falling through to a lower layer
- * @dentry - The dentry to mark
- *
- * Mark a dentry as falling through to the lower layer (as set with
- * d_pin_lower()).  This flag may be recorded on the medium.
- */
-void d_set_fallthru(struct dentry *dentry)
-{
-	spin_lock(&dentry->d_lock);
-	dentry->d_flags |= DCACHE_FALLTHRU;
-	spin_unlock(&dentry->d_lock);
-}
-EXPORT_SYMBOL(d_set_fallthru);
-
 static unsigned d_flags_for_inode(struct inode *inode)
 {
 	unsigned add_flags = DCACHE_REGULAR_TYPE;
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 92c0b2a1ae2e..8cd937bb2292 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -195,16 +195,15 @@ struct dentry_operations {
 #define DCACHE_LRU_LIST			BIT(19)
 
 #define DCACHE_ENTRY_TYPE		(7 << 20) /* bits 20..22 are for storing type: */
-#define DCACHE_MISS_TYPE		(0 << 20) /* Negative dentry (maybe fallthru to nowhere) */
+#define DCACHE_MISS_TYPE		(0 << 20) /* Negative dentry */
 #define DCACHE_WHITEOUT_TYPE		(1 << 20) /* Whiteout dentry (stop pathwalk) */
 #define DCACHE_DIRECTORY_TYPE		(2 << 20) /* Normal directory */
 #define DCACHE_AUTODIR_TYPE		(3 << 20) /* Lookupless directory (presumed automount) */
-#define DCACHE_REGULAR_TYPE		(4 << 20) /* Regular file type (or fallthru to such) */
-#define DCACHE_SPECIAL_TYPE		(5 << 20) /* Other file type (or fallthru to such) */
-#define DCACHE_SYMLINK_TYPE		(6 << 20) /* Symlink (or fallthru to such) */
+#define DCACHE_REGULAR_TYPE		(4 << 20) /* Regular file type */
+#define DCACHE_SPECIAL_TYPE		(5 << 20) /* Other file type */
+#define DCACHE_SYMLINK_TYPE		(6 << 20) /* Symlink */
 
 #define DCACHE_MAY_FREE			BIT(23)
-#define DCACHE_FALLTHRU			BIT(24) /* Fall through to lower layer */
 #define DCACHE_NOKEY_NAME		BIT(25) /* Encrypted name encoded without key */
 #define DCACHE_OP_REAL			BIT(26)
 
@@ -489,14 +488,6 @@ static inline int simple_positive(const struct dentry *dentry)
 	return d_really_is_positive(dentry) && !d_unhashed(dentry);
 }
 
-extern void d_set_fallthru(struct dentry *dentry);
-
-static inline bool d_is_fallthru(const struct dentry *dentry)
-{
-	return dentry->d_flags & DCACHE_FALLTHRU;
-}
-
-
 extern int sysctl_vfs_cache_pressure;
 
 static inline unsigned long vfs_pressure_ratio(unsigned long val)
-- 
cgit v1.2.3


From 0d486510f86eb8162022ed61e6dc424a10909a10 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 10 Nov 2023 15:22:40 -0500
Subject: dentry.h: trim externs

d_instantiate_unique() had been gone for 7 years; __d_lookup...()
and shrink_dcache_for_umount() are fs/internal.h fodder.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/internal.h          | 4 ++++
 include/linux/dcache.h | 5 -----
 2 files changed, 4 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/fs/internal.h b/fs/internal.h
index 58e43341aebf..9e9fc629f935 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -215,6 +215,10 @@ extern struct dentry * d_alloc_pseudo(struct super_block *, const struct qstr *)
 extern char *simple_dname(struct dentry *, char *, int);
 extern void dput_to_list(struct dentry *, struct list_head *);
 extern void shrink_dentry_list(struct list_head *);
+extern void shrink_dcache_for_umount(struct super_block *);
+extern struct dentry *__d_lookup(const struct dentry *, const struct qstr *);
+extern struct dentry *__d_lookup_rcu(const struct dentry *parent,
+				const struct qstr *name, unsigned *seq);
 
 /*
  * pipe.c
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 8cd937bb2292..9706bf1dc5de 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -218,7 +218,6 @@ extern seqlock_t rename_lock;
  */
 extern void d_instantiate(struct dentry *, struct inode *);
 extern void d_instantiate_new(struct dentry *, struct inode *);
-extern struct dentry * d_instantiate_unique(struct dentry *, struct inode *);
 extern struct dentry * d_instantiate_anon(struct dentry *, struct inode *);
 extern void __d_drop(struct dentry *dentry);
 extern void d_drop(struct dentry *dentry);
@@ -240,7 +239,6 @@ extern struct dentry * d_obtain_alias(struct inode *);
 extern struct dentry * d_obtain_root(struct inode *);
 extern void shrink_dcache_sb(struct super_block *);
 extern void shrink_dcache_parent(struct dentry *);
-extern void shrink_dcache_for_umount(struct super_block *);
 extern void d_invalidate(struct dentry *);
 
 /* only used at mount-time */
@@ -275,9 +273,6 @@ extern struct dentry *d_ancestor(struct dentry *, struct dentry *);
 /* appendix may either be NULL or be used for transname suffixes */
 extern struct dentry *d_lookup(const struct dentry *, const struct qstr *);
 extern struct dentry *d_hash_and_lookup(struct dentry *, struct qstr *);
-extern struct dentry *__d_lookup(const struct dentry *, const struct qstr *);
-extern struct dentry *__d_lookup_rcu(const struct dentry *parent,
-				const struct qstr *name, unsigned *seq);
 
 static inline unsigned d_count(const struct dentry *dentry)
 {
-- 
cgit v1.2.3


From 2fcd38f4de7256e2b5cb23ad22a6e3ebfea7dd18 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 10 Nov 2023 15:24:45 -0500
Subject: [software coproarchaeology] dentry.h: kill a mysterious comment

there's a strange comment in front of d_lookup() declaration:

/* appendix may either be NULL or be used for transname suffixes */

Looks like nobody had been curious enough to track its history;
it predates git, it predates bitkeeper and if you look through
the pre-BK trees, you finally arrive at this in 2.1.44-for-davem:
  /* appendix may either be NULL or be used for transname suffixes */
 -extern struct dentry * d_lookup(struct inode * dir, struct qstr * name,
 -                               struct qstr * appendix);
 +extern struct dentry * d_lookup(struct dentry * dir, struct qstr * name);
In other words, it refers to the third argument d_lookup() used to have
back then.  It had been introduced in 2.1.43-pre, on June 12 1997,
along with d_lookup(), only to be removed by July 4 1997, presumably
when the Cthulhu-awful thing it used to be used for (look for
CONFIG_TRANS_NAMES in 2.1.43-pre, and keep a heavy-duty barfbag
ready) had been, er, noticed and recognized for what it had been.

Despite the appendectomy, the comment remained.  Some things really
need to be put out of their misery...

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/dcache.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 9706bf1dc5de..a5e5e274eee0 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -270,7 +270,6 @@ extern void d_move(struct dentry *, struct dentry *);
 extern void d_exchange(struct dentry *, struct dentry *);
 extern struct dentry *d_ancestor(struct dentry *, struct dentry *);
 
-/* appendix may either be NULL or be used for transname suffixes */
 extern struct dentry *d_lookup(const struct dentry *, const struct qstr *);
 extern struct dentry *d_hash_and_lookup(struct dentry *, struct qstr *);
 
-- 
cgit v1.2.3


From 698f1e2b71736977b04f951e2e2ef1c9a80696ff Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 10 Nov 2023 16:19:59 -0500
Subject: kill d_backing_dentry()

no users left

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/dcache.h | 15 ---------------
 1 file changed, 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index a5e5e274eee0..fa0414cff85c 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -530,21 +530,6 @@ static inline struct inode *d_backing_inode(const struct dentry *upper)
 	return inode;
 }
 
-/**
- * d_backing_dentry - Get upper or lower dentry we should be using
- * @upper: The upper layer
- *
- * This is the helper that should be used to get the dentry of the inode that
- * will be used if this dentry were opened as a file.  It may be the upper
- * dentry or it may be a lower dentry pinned by the upper.
- *
- * Normal filesystems should not use this to access their own dentries.
- */
-static inline struct dentry *d_backing_dentry(struct dentry *upper)
-{
-	return upper;
-}
-
 /**
  * d_real - Return the real dentry
  * @dentry: the dentry to query
-- 
cgit v1.2.3


From 289354f21b2c3fac93e956efd45f256a88a4d997 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Sat, 18 Nov 2023 18:38:05 -0800
Subject: net: partial revert of the "Make timestamping selectable: series

Revert following commits:

commit acec05fb78ab ("net_tstamp: Add TIMESTAMPING SOFTWARE and HARDWARE mask")
commit 11d55be06df0 ("net: ethtool: Add a command to expose current time stamping layer")
commit bb8645b00ced ("netlink: specs: Introduce new netlink command to get current timestamp")
commit d905f9c75329 ("net: ethtool: Add a command to list available time stamping layers")
commit aed5004ee7a0 ("netlink: specs: Introduce new netlink command to list available time stamping layers")
commit 51bdf3165f01 ("net: Replace hwtstamp_source by timestamping layer")
commit 0f7f463d4821 ("net: Change the API of PHY default timestamp to MAC")
commit 091fab122869 ("net: ethtool: ts: Update GET_TS to reply the current selected timestamp")
commit 152c75e1d002 ("net: ethtool: ts: Let the active time stamping layer be selectable")
commit ee60ea6be0d3 ("netlink: specs: Introduce time stamping set command")

They need more time for reviews.

Link: https://lore.kernel.org/all/20231118183529.6e67100c@kernel.org/
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/ethtool.yaml           |  57 -----
 Documentation/networking/ethtool-netlink.rst       |  63 ------
 .../net/ethernet/microchip/lan966x/lan966x_main.c  |   6 +-
 drivers/net/phy/bcm-phy-ptp.c                      |   3 -
 drivers/net/phy/dp83640.c                          |   3 -
 drivers/net/phy/micrel.c                           |   6 -
 drivers/net/phy/mscc/mscc_ptp.c                    |   2 -
 drivers/net/phy/nxp-c45-tja11xx.c                  |   3 -
 drivers/net/phy/phy_device.c                       |  37 ----
 include/linux/net_tstamp.h                         |  11 +-
 include/linux/netdevice.h                          |   5 -
 include/linux/phy.h                                |   4 -
 include/uapi/linux/ethtool_netlink.h               |  29 ---
 include/uapi/linux/net_tstamp.h                    |  18 --
 net/core/dev.c                                     |   3 -
 net/core/dev_ioctl.c                               |  36 ++-
 net/core/timestamping.c                            |  10 -
 net/ethtool/Makefile                               |   2 +-
 net/ethtool/common.c                               |  19 +-
 net/ethtool/common.h                               |   1 -
 net/ethtool/netlink.c                              |  28 ---
 net/ethtool/netlink.h                              |   4 -
 net/ethtool/ts.c                                   | 244 ---------------------
 23 files changed, 28 insertions(+), 566 deletions(-)
 delete mode 100644 net/ethtool/ts.c

(limited to 'include')

diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml
index 06d9120543d3..5c7a65b009b4 100644
--- a/Documentation/netlink/specs/ethtool.yaml
+++ b/Documentation/netlink/specs/ethtool.yaml
@@ -939,26 +939,6 @@ attribute-sets:
       -
         name: burst-tmr
         type: u32
-  -
-    name: ts
-    attributes:
-      -
-        name: header
-        type: nest
-        nested-attributes: header
-      -
-        name: ts-layer
-        type: u32
-  -
-    name: ts-list
-    attributes:
-      -
-        name: header
-        type: nest
-        nested-attributes: header
-      -
-        name: ts-list-layer
-        type: binary
 
 operations:
   enum-model: directional
@@ -1709,40 +1689,3 @@ operations:
       name: mm-ntf
       doc: Notification for change in MAC Merge configuration.
       notify: mm-get
-    -
-      name: ts-get
-      doc: Get current timestamp
-
-      attribute-set: ts
-
-      do:
-        request:
-          attributes:
-            - header
-        reply:
-          attributes: &ts
-            - header
-            - ts-layer
-    -
-      name: ts-list-get
-      doc: Get list of timestamp devices available on an interface
-
-      attribute-set: ts-list
-
-      do:
-        request:
-          attributes:
-            - header
-        reply:
-          attributes:
-            - header
-            - ts-list-layer
-    -
-      name: ts-set
-      doc: Set the timestamp device
-
-      attribute-set: ts
-
-      do:
-        request:
-          attributes: *ts
diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst
index 530c1775e5f4..2540c70952ff 100644
--- a/Documentation/networking/ethtool-netlink.rst
+++ b/Documentation/networking/ethtool-netlink.rst
@@ -225,9 +225,6 @@ Userspace to kernel:
   ``ETHTOOL_MSG_RSS_GET``               get RSS settings
   ``ETHTOOL_MSG_MM_GET``                get MAC merge layer state
   ``ETHTOOL_MSG_MM_SET``                set MAC merge layer parameters
-  ``ETHTOOL_MSG_TS_GET``                get current timestamping
-  ``ETHTOOL_MSG_TS_LIST_GET``           list available timestampings
-  ``ETHTOOL_MSG_TS_SET``                set current timestamping
   ===================================== =================================
 
 Kernel to userspace:
@@ -271,8 +268,6 @@ Kernel to userspace:
   ``ETHTOOL_MSG_PSE_GET_REPLY``            PSE parameters
   ``ETHTOOL_MSG_RSS_GET_REPLY``            RSS settings
   ``ETHTOOL_MSG_MM_GET_REPLY``             MAC merge layer status
-  ``ETHTOOL_MSG_TS_GET_REPLY``             current timestamping
-  ``ETHTOOL_MSG_TS_LIST_GET_REPLY``        available timestampings
   ======================================== =================================
 
 ``GET`` requests are sent by userspace applications to retrieve device
@@ -1999,61 +1994,6 @@ The attributes are propagated to the driver through the following structure:
 .. kernel-doc:: include/linux/ethtool.h
     :identifiers: ethtool_mm_cfg
 
-TS_GET
-======
-
-Gets current timestamping.
-
-Request contents:
-
-  =================================  ======  ====================
-  ``ETHTOOL_A_TS_HEADER``            nested  request header
-  =================================  ======  ====================
-
-Kernel response contents:
-
-  =======================  ======  ==============================
-  ``ETHTOOL_A_TS_HEADER``  nested  reply header
-  ``ETHTOOL_A_TS_LAYER``   u32     current timestamping
-  =======================  ======  ==============================
-
-This command get the current timestamp layer.
-
-TS_LIST_GET
-===========
-
-Get the list of available timestampings.
-
-Request contents:
-
-  =================================  ======  ====================
-  ``ETHTOOL_A_TS_HEADER``            nested  request header
-  =================================  ======  ====================
-
-Kernel response contents:
-
-  ===========================  ======  ==============================
-  ``ETHTOOL_A_TS_HEADER``      nested  reply header
-  ``ETHTOOL_A_TS_LIST_LAYER``  binary  available timestampings
-  ===========================  ======  ==============================
-
-This command lists all the possible timestamp layer available.
-
-TS_SET
-======
-
-Modify the selected timestamping.
-
-Request contents:
-
-  =======================  ======  ===================
-  ``ETHTOOL_A_TS_HEADER``  nested  reply header
-  ``ETHTOOL_A_TS_LAYER``   u32     timestamping
-  =======================  ======  ===================
-
-This command set the timestamping with one that should be listed by the
-TSLIST_GET command.
-
 Request translation
 ===================
 
@@ -2160,7 +2100,4 @@ are netlink only.
   n/a                                 ``ETHTOOL_MSG_PLCA_GET_STATUS``
   n/a                                 ``ETHTOOL_MSG_MM_GET``
   n/a                                 ``ETHTOOL_MSG_MM_SET``
-  n/a                                 ``ETHTOOL_MSG_TS_GET``
-  n/a                                 ``ETHTOOL_MSG_TS_LIST_GET``
-  n/a                                 ``ETHTOOL_MSG_TS_SET``
   =================================== =====================================
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
index fbe56b1bb386..2635ef8958c8 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
@@ -470,15 +470,15 @@ static int lan966x_port_hwtstamp_set(struct net_device *dev,
 	struct lan966x_port *port = netdev_priv(dev);
 	int err;
 
-	if (cfg->source != MAC_TIMESTAMPING &&
-	    cfg->source != PHY_TIMESTAMPING)
+	if (cfg->source != HWTSTAMP_SOURCE_NETDEV &&
+	    cfg->source != HWTSTAMP_SOURCE_PHYLIB)
 		return -EOPNOTSUPP;
 
 	err = lan966x_ptp_setup_traps(port, cfg);
 	if (err)
 		return err;
 
-	if (cfg->source == MAC_TIMESTAMPING) {
+	if (cfg->source == HWTSTAMP_SOURCE_NETDEV) {
 		if (!port->lan966x->ptp)
 			return -EOPNOTSUPP;
 
diff --git a/drivers/net/phy/bcm-phy-ptp.c b/drivers/net/phy/bcm-phy-ptp.c
index d3e825c951ee..617d384d4551 100644
--- a/drivers/net/phy/bcm-phy-ptp.c
+++ b/drivers/net/phy/bcm-phy-ptp.c
@@ -931,9 +931,6 @@ struct bcm_ptp_private *bcm_ptp_probe(struct phy_device *phydev)
 		return ERR_CAST(clock);
 	priv->ptp_clock = clock;
 
-	/* Timestamp selected by default to keep legacy API */
-	phydev->default_timestamp = true;
-
 	priv->phydev = phydev;
 	bcm_ptp_init(priv);
 
diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index 64fd1a109c0f..5c42c47dc564 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -1450,9 +1450,6 @@ static int dp83640_probe(struct phy_device *phydev)
 	phydev->mii_ts = &dp83640->mii_ts;
 	phydev->priv = dp83640;
 
-	/* Timestamp selected by default to keep legacy API */
-	phydev->default_timestamp = true;
-
 	spin_lock_init(&dp83640->rx_lock);
 	skb_queue_head_init(&dp83640->rx_queue);
 	skb_queue_head_init(&dp83640->tx_queue);
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 2b8dd0131926..bd4cd082662f 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -3158,9 +3158,6 @@ static void lan8814_ptp_init(struct phy_device *phydev)
 	ptp_priv->mii_ts.ts_info  = lan8814_ts_info;
 
 	phydev->mii_ts = &ptp_priv->mii_ts;
-
-	/* Timestamp selected by default to keep legacy API */
-	phydev->default_timestamp = true;
 }
 
 static int lan8814_ptp_probe_once(struct phy_device *phydev)
@@ -4589,9 +4586,6 @@ static int lan8841_probe(struct phy_device *phydev)
 
 	phydev->mii_ts = &ptp_priv->mii_ts;
 
-	/* Timestamp selected by default to keep legacy API */
-	phydev->default_timestamp = true;
-
 	return 0;
 }
 
diff --git a/drivers/net/phy/mscc/mscc_ptp.c b/drivers/net/phy/mscc/mscc_ptp.c
index fd174eb06d4a..eb0b032cb613 100644
--- a/drivers/net/phy/mscc/mscc_ptp.c
+++ b/drivers/net/phy/mscc/mscc_ptp.c
@@ -1570,8 +1570,6 @@ int vsc8584_ptp_probe(struct phy_device *phydev)
 		return PTR_ERR(vsc8531->load_save);
 	}
 
-	/* Timestamp selected by default to keep legacy API */
-	phydev->default_timestamp = true;
 	vsc8531->ptp->phydev = phydev;
 
 	return 0;
diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c
index 0515c7b979db..780ad353cf55 100644
--- a/drivers/net/phy/nxp-c45-tja11xx.c
+++ b/drivers/net/phy/nxp-c45-tja11xx.c
@@ -1658,9 +1658,6 @@ static int nxp_c45_probe(struct phy_device *phydev)
 		priv->mii_ts.ts_info = nxp_c45_ts_info;
 		phydev->mii_ts = &priv->mii_ts;
 		ret = nxp_c45_init_ptp_clock(priv);
-
-		/* Timestamp selected by default to keep legacy API */
-		phydev->default_timestamp = true;
 	} else {
 		phydev_dbg(phydev, "PTP support not enabled even if the phy supports it");
 	}
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 8c4794631daa..2ce74593d6e4 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1411,26 +1411,6 @@ int phy_sfp_probe(struct phy_device *phydev,
 }
 EXPORT_SYMBOL(phy_sfp_probe);
 
-/**
- * phy_set_timestamp - set the default selected timestamping device
- * @dev: Pointer to net_device
- * @phydev: Pointer to phy_device
- *
- * This is used to set default timestamping device taking into account
- * the new API choice, which is selecting the timestamping from MAC by
- * default if the phydev does not have default_timestamp flag enabled.
- */
-static void phy_set_timestamp(struct net_device *dev, struct phy_device *phydev)
-{
-	const struct ethtool_ops *ops = dev->ethtool_ops;
-
-	if (!phy_has_tsinfo(phydev))
-		return;
-
-	if (!ops->get_ts_info || phydev->default_timestamp)
-		dev->ts_layer = PHY_TIMESTAMPING;
-}
-
 /**
  * phy_attach_direct - attach a network device to a given PHY device pointer
  * @dev: network device to attach
@@ -1504,7 +1484,6 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
 
 	phydev->phy_link_change = phy_link_change;
 	if (dev) {
-		phy_set_timestamp(dev, phydev);
 		phydev->attached_dev = dev;
 		dev->phydev = phydev;
 
@@ -1833,22 +1812,6 @@ void phy_detach(struct phy_device *phydev)
 
 	phy_suspend(phydev);
 	if (dev) {
-		const struct ethtool_ops *ops = dev->ethtool_ops;
-		struct ethtool_ts_info ts_info = {0};
-
-		if (ops->get_ts_info) {
-			ops->get_ts_info(dev, &ts_info);
-			if ((ts_info.so_timestamping &
-			    SOF_TIMESTAMPING_HARDWARE_MASK) ==
-			    SOF_TIMESTAMPING_HARDWARE_MASK)
-				dev->ts_layer = MAC_TIMESTAMPING;
-			else if ((ts_info.so_timestamping &
-				 SOF_TIMESTAMPING_SOFTWARE_MASK) ==
-				 SOF_TIMESTAMPING_SOFTWARE_MASK)
-				dev->ts_layer = SOFTWARE_TIMESTAMPING;
-		} else {
-			dev->ts_layer = NO_TIMESTAMPING;
-		}
 		phydev->attached_dev->phydev = NULL;
 		phydev->attached_dev = NULL;
 	}
diff --git a/include/linux/net_tstamp.h b/include/linux/net_tstamp.h
index bb289c2ad376..eb01c37e71e0 100644
--- a/include/linux/net_tstamp.h
+++ b/include/linux/net_tstamp.h
@@ -5,6 +5,11 @@
 
 #include <uapi/linux/net_tstamp.h>
 
+enum hwtstamp_source {
+	HWTSTAMP_SOURCE_NETDEV,
+	HWTSTAMP_SOURCE_PHYLIB,
+};
+
 /**
  * struct kernel_hwtstamp_config - Kernel copy of struct hwtstamp_config
  *
@@ -15,8 +20,8 @@
  *	a legacy implementation of a lower driver
  * @copied_to_user: request was passed to a legacy implementation which already
  *	copied the ioctl request back to user space
- * @source: indication whether timestamps should come from software, the netdev
- *	or from an attached phylib PHY
+ * @source: indication whether timestamps should come from the netdev or from
+ *	an attached phylib PHY
  *
  * Prefer using this structure for in-kernel processing of hardware
  * timestamping configuration, over the inextensible struct hwtstamp_config
@@ -28,7 +33,7 @@ struct kernel_hwtstamp_config {
 	int rx_filter;
 	struct ifreq *ifr;
 	bool copied_to_user;
-	enum timestamping_layer source;
+	enum hwtstamp_source source;
 };
 
 static inline void hwtstamp_config_to_kernel(struct kernel_hwtstamp_config *kernel_cfg,
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index f020d2790c12..2d840d7056f2 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -47,7 +47,6 @@
 #include <uapi/linux/if_bonding.h>
 #include <uapi/linux/pkt_cls.h>
 #include <uapi/linux/netdev.h>
-#include <uapi/linux/net_tstamp.h>
 #include <linux/hashtable.h>
 #include <linux/rbtree.h>
 #include <net/net_trackers.h>
@@ -2075,8 +2074,6 @@ enum netdev_ml_priv_type {
  *
  *	@dpll_pin: Pointer to the SyncE source pin of a DPLL subsystem,
  *		   where the clock is recovered.
- *	@ts_layer:	Tracks which network device
- *			performs packet	time stamping.
  *
  *	FIXME: cleanup struct net_device such that network protocol info
  *	moves out.
@@ -2438,8 +2435,6 @@ struct net_device {
 #if IS_ENABLED(CONFIG_DPLL)
 	struct dpll_pin		*dpll_pin;
 #endif
-
-	enum timestamping_layer	ts_layer;
 };
 #define to_net_dev(d) container_of(d, struct net_device, dev)
 
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 317def2a7843..e5f1f41e399c 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -604,8 +604,6 @@ struct macsec_ops;
  *                 handling shall be postponed until PHY has resumed
  * @irq_rerun: Flag indicating interrupts occurred while PHY was suspended,
  *             requiring a rerun of the interrupt handler after resume
- * @default_timestamp: Flag indicating whether we are using the phy
- *		       timestamp as the default one
  * @interface: enum phy_interface_t value
  * @skb: Netlink message for cable diagnostics
  * @nest: Netlink nest used for cable diagnostics
@@ -669,8 +667,6 @@ struct phy_device {
 	unsigned irq_suspended:1;
 	unsigned irq_rerun:1;
 
-	unsigned default_timestamp:1;
-
 	int rate_matching;
 
 	enum phy_state state;
diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h
index df6c4fcc62c1..73e2c10dc2cc 100644
--- a/include/uapi/linux/ethtool_netlink.h
+++ b/include/uapi/linux/ethtool_netlink.h
@@ -57,9 +57,6 @@ enum {
 	ETHTOOL_MSG_PLCA_GET_STATUS,
 	ETHTOOL_MSG_MM_GET,
 	ETHTOOL_MSG_MM_SET,
-	ETHTOOL_MSG_TS_GET,
-	ETHTOOL_MSG_TS_LIST_GET,
-	ETHTOOL_MSG_TS_SET,
 
 	/* add new constants above here */
 	__ETHTOOL_MSG_USER_CNT,
@@ -112,8 +109,6 @@ enum {
 	ETHTOOL_MSG_PLCA_NTF,
 	ETHTOOL_MSG_MM_GET_REPLY,
 	ETHTOOL_MSG_MM_NTF,
-	ETHTOOL_MSG_TS_GET_REPLY,
-	ETHTOOL_MSG_TS_LIST_GET_REPLY,
 
 	/* add new constants above here */
 	__ETHTOOL_MSG_KERNEL_CNT,
@@ -980,30 +975,6 @@ enum {
 	ETHTOOL_A_MM_MAX = (__ETHTOOL_A_MM_CNT - 1)
 };
 
-/* TS LAYER */
-
-enum {
-	ETHTOOL_A_TS_UNSPEC,
-	ETHTOOL_A_TS_HEADER,			/* nest - _A_HEADER_* */
-	ETHTOOL_A_TS_LAYER,			/* u32 */
-
-	/* add new constants above here */
-	__ETHTOOL_A_TS_CNT,
-	ETHTOOL_A_TS_MAX = (__ETHTOOL_A_TS_CNT - 1)
-};
-
-/* TS LIST LAYER */
-
-enum {
-	ETHTOOL_A_TS_LIST_UNSPEC,
-	ETHTOOL_A_TS_LIST_HEADER,			/* nest - _A_HEADER_* */
-	ETHTOOL_A_TS_LIST_LAYER,		/* array, u32 */
-
-	/* add new constants above here */
-	__ETHTOOL_A_TS_LIST_CNT,
-	ETHTOOL_A_TS_LIST_MAX = (__ETHTOOL_A_TS_LIST_CNT - 1)
-};
-
 /* generic netlink info */
 #define ETHTOOL_GENL_NAME "ethtool"
 #define ETHTOOL_GENL_VERSION 1
diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h
index 4551fb3d7720..a2c66b3d7f0f 100644
--- a/include/uapi/linux/net_tstamp.h
+++ b/include/uapi/linux/net_tstamp.h
@@ -13,16 +13,6 @@
 #include <linux/types.h>
 #include <linux/socket.h>   /* for SO_TIMESTAMPING */
 
-/* Layer of the TIMESTAMPING provider */
-enum timestamping_layer {
-	NO_TIMESTAMPING,
-	SOFTWARE_TIMESTAMPING,
-	MAC_TIMESTAMPING,
-	PHY_TIMESTAMPING,
-
-	__TIMESTAMPING_COUNT,
-};
-
 /* SO_TIMESTAMPING flags */
 enum {
 	SOF_TIMESTAMPING_TX_HARDWARE = (1<<0),
@@ -58,14 +48,6 @@ enum {
 					 SOF_TIMESTAMPING_TX_SCHED | \
 					 SOF_TIMESTAMPING_TX_ACK)
 
-#define SOF_TIMESTAMPING_SOFTWARE_MASK	(SOF_TIMESTAMPING_RX_SOFTWARE | \
-					 SOF_TIMESTAMPING_TX_SOFTWARE | \
-					 SOF_TIMESTAMPING_SOFTWARE)
-
-#define SOF_TIMESTAMPING_HARDWARE_MASK	(SOF_TIMESTAMPING_RX_HARDWARE | \
-					 SOF_TIMESTAMPING_TX_HARDWARE | \
-					 SOF_TIMESTAMPING_RAW_HARDWARE)
-
 /**
  * struct so_timestamping - SO_TIMESTAMPING parameter
  *
diff --git a/net/core/dev.c b/net/core/dev.c
index 05ce00632892..af53f6d838ce 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -10212,9 +10212,6 @@ int register_netdevice(struct net_device *dev)
 	    dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
 		rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL, 0, NULL);
 
-	if (dev->ethtool_ops->get_ts_info)
-		dev->ts_layer = MAC_TIMESTAMPING;
-
 out:
 	return ret;
 
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index bc8be9749376..9a66cf5015f2 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -259,7 +259,9 @@ static int dev_eth_ioctl(struct net_device *dev,
  * @dev: Network device
  * @cfg: Timestamping configuration structure
  *
- * Helper for calling the selected hardware provider timestamping.
+ * Helper for enforcing a common policy that phylib timestamping, if available,
+ * should take precedence in front of hardware timestamping provided by the
+ * netdev.
  *
  * Note: phy_mii_ioctl() only handles SIOCSHWTSTAMP (not SIOCGHWTSTAMP), and
  * there only exists a phydev->mii_ts->hwtstamp() method. So this will return
@@ -269,14 +271,10 @@ static int dev_eth_ioctl(struct net_device *dev,
 static int dev_get_hwtstamp_phylib(struct net_device *dev,
 				   struct kernel_hwtstamp_config *cfg)
 {
-	enum timestamping_layer ts_layer = dev->ts_layer;
-
-	if (ts_layer == PHY_TIMESTAMPING)
+	if (phy_has_hwtstamp(dev->phydev))
 		return phy_hwtstamp_get(dev->phydev, cfg);
-	else if (ts_layer == MAC_TIMESTAMPING)
-		return dev->netdev_ops->ndo_hwtstamp_get(dev, cfg);
 
-	return -EOPNOTSUPP;
+	return dev->netdev_ops->ndo_hwtstamp_get(dev, cfg);
 }
 
 static int dev_get_hwtstamp(struct net_device *dev, struct ifreq *ifr)
@@ -317,8 +315,9 @@ static int dev_get_hwtstamp(struct net_device *dev, struct ifreq *ifr)
  * @cfg: Timestamping configuration structure
  * @extack: Netlink extended ack message structure, for error reporting
  *
- * Helper for calling the selected hardware provider timestamping.
- * If the netdev driver needs to perform specific actions even for PHY
+ * Helper for enforcing a common policy that phylib timestamping, if available,
+ * should take precedence in front of hardware timestamping provided by the
+ * netdev. If the netdev driver needs to perform specific actions even for PHY
  * timestamping to work properly (a switch port must trap the timestamped
  * frames and not forward them), it must set IFF_SEE_ALL_HWTSTAMP_REQUESTS in
  * dev->priv_flags.
@@ -328,26 +327,20 @@ int dev_set_hwtstamp_phylib(struct net_device *dev,
 			    struct netlink_ext_ack *extack)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
-	enum timestamping_layer ts_layer = dev->ts_layer;
+	bool phy_ts = phy_has_hwtstamp(dev->phydev);
 	struct kernel_hwtstamp_config old_cfg = {};
 	bool changed = false;
 	int err;
 
-	cfg->source = ts_layer;
-
-	if (ts_layer != PHY_TIMESTAMPING &&
-	    ts_layer != MAC_TIMESTAMPING)
-		return -EOPNOTSUPP;
+	cfg->source = phy_ts ? HWTSTAMP_SOURCE_PHYLIB : HWTSTAMP_SOURCE_NETDEV;
 
-	if (ts_layer == PHY_TIMESTAMPING &&
-	    dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS) {
+	if (phy_ts && (dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS)) {
 		err = ops->ndo_hwtstamp_get(dev, &old_cfg);
 		if (err)
 			return err;
 	}
 
-	if (ts_layer == MAC_TIMESTAMPING ||
-	    dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS) {
+	if (!phy_ts || (dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS)) {
 		err = ops->ndo_hwtstamp_set(dev, cfg, extack);
 		if (err) {
 			if (extack->_msg)
@@ -356,11 +349,10 @@ int dev_set_hwtstamp_phylib(struct net_device *dev,
 		}
 	}
 
-	if (ts_layer == PHY_TIMESTAMPING &&
-	    dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS)
+	if (phy_ts && (dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS))
 		changed = kernel_hwtstamp_config_changed(&old_cfg, cfg);
 
-	if (ts_layer == PHY_TIMESTAMPING) {
+	if (phy_ts) {
 		err = phy_hwtstamp_set(dev->phydev, cfg, extack);
 		if (err) {
 			if (changed)
diff --git a/net/core/timestamping.c b/net/core/timestamping.c
index 5cf51a523fb3..04840697fe79 100644
--- a/net/core/timestamping.c
+++ b/net/core/timestamping.c
@@ -21,7 +21,6 @@ static unsigned int classify(const struct sk_buff *skb)
 
 void skb_clone_tx_timestamp(struct sk_buff *skb)
 {
-	enum timestamping_layer ts_layer;
 	struct mii_timestamper *mii_ts;
 	struct sk_buff *clone;
 	unsigned int type;
@@ -29,10 +28,6 @@ void skb_clone_tx_timestamp(struct sk_buff *skb)
 	if (!skb->sk)
 		return;
 
-	ts_layer = skb->dev->ts_layer;
-	if (ts_layer != PHY_TIMESTAMPING)
-		return;
-
 	type = classify(skb);
 	if (type == PTP_CLASS_NONE)
 		return;
@@ -49,17 +44,12 @@ EXPORT_SYMBOL_GPL(skb_clone_tx_timestamp);
 
 bool skb_defer_rx_timestamp(struct sk_buff *skb)
 {
-	enum timestamping_layer ts_layer;
 	struct mii_timestamper *mii_ts;
 	unsigned int type;
 
 	if (!skb->dev || !skb->dev->phydev || !skb->dev->phydev->mii_ts)
 		return false;
 
-	ts_layer = skb->dev->ts_layer;
-	if (ts_layer != PHY_TIMESTAMPING)
-		return false;
-
 	if (skb_headroom(skb) < ETH_HLEN)
 		return false;
 
diff --git a/net/ethtool/Makefile b/net/ethtool/Makefile
index 4ea64c080639..504f954a1b28 100644
--- a/net/ethtool/Makefile
+++ b/net/ethtool/Makefile
@@ -8,4 +8,4 @@ ethtool_nl-y	:= netlink.o bitset.o strset.o linkinfo.o linkmodes.o rss.o \
 		   linkstate.o debug.o wol.o features.o privflags.o rings.o \
 		   channels.o coalesce.o pause.o eee.o tsinfo.o cabletest.o \
 		   tunnels.o fec.o eeprom.o stats.o phc_vclocks.o mm.o \
-		   module.o pse-pd.o plca.o mm.o ts.o
+		   module.o pse-pd.o plca.o mm.o
diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index 9f6e3b2c74e2..11d8797f63f6 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -633,28 +633,13 @@ int __ethtool_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info)
 {
 	const struct ethtool_ops *ops = dev->ethtool_ops;
 	struct phy_device *phydev = dev->phydev;
-	enum timestamping_layer ts_layer;
-	int ret;
 
 	memset(info, 0, sizeof(*info));
 	info->cmd = ETHTOOL_GET_TS_INFO;
 
-	ts_layer = dev->ts_layer;
-	if (ts_layer == SOFTWARE_TIMESTAMPING) {
-		ret = ops->get_ts_info(dev, info);
-		if (ret)
-			return ret;
-		info->so_timestamping &= ~SOF_TIMESTAMPING_HARDWARE_MASK;
-		info->phc_index = -1;
-		info->rx_filters = 0;
-		info->tx_types = 0;
-		return 0;
-	}
-
-	if (ts_layer == PHY_TIMESTAMPING)
+	if (phy_has_tsinfo(phydev))
 		return phy_ts_info(phydev, info);
-
-	if (ts_layer == MAC_TIMESTAMPING)
+	if (ops->get_ts_info)
 		return ops->get_ts_info(dev, info);
 
 	info->so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE |
diff --git a/net/ethtool/common.h b/net/ethtool/common.h
index a264b635f7d3..28b8aaaf9bcb 100644
--- a/net/ethtool/common.h
+++ b/net/ethtool/common.h
@@ -35,7 +35,6 @@ extern const char wol_mode_names[][ETH_GSTRING_LEN];
 extern const char sof_timestamping_names[][ETH_GSTRING_LEN];
 extern const char ts_tx_type_names[][ETH_GSTRING_LEN];
 extern const char ts_rx_filter_names[][ETH_GSTRING_LEN];
-extern const char ts_layer_names[][ETH_GSTRING_LEN];
 extern const char udp_tunnel_type_names[][ETH_GSTRING_LEN];
 
 int __ethtool_get_link(struct net_device *dev);
diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index 8322bf71f80d..3bbd5afb7b31 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -306,9 +306,6 @@ ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = {
 	[ETHTOOL_MSG_PLCA_GET_STATUS]	= &ethnl_plca_status_request_ops,
 	[ETHTOOL_MSG_MM_GET]		= &ethnl_mm_request_ops,
 	[ETHTOOL_MSG_MM_SET]		= &ethnl_mm_request_ops,
-	[ETHTOOL_MSG_TS_GET]		= &ethnl_ts_request_ops,
-	[ETHTOOL_MSG_TS_LIST_GET]	= &ethnl_ts_list_request_ops,
-	[ETHTOOL_MSG_TS_SET]		= &ethnl_ts_request_ops,
 };
 
 static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb)
@@ -1131,31 +1128,6 @@ static const struct genl_ops ethtool_genl_ops[] = {
 		.policy = ethnl_mm_set_policy,
 		.maxattr = ARRAY_SIZE(ethnl_mm_set_policy) - 1,
 	},
-	{
-		.cmd	= ETHTOOL_MSG_TS_GET,
-		.doit	= ethnl_default_doit,
-		.start	= ethnl_default_start,
-		.dumpit	= ethnl_default_dumpit,
-		.done	= ethnl_default_done,
-		.policy = ethnl_ts_get_policy,
-		.maxattr = ARRAY_SIZE(ethnl_ts_get_policy) - 1,
-	},
-	{
-		.cmd	= ETHTOOL_MSG_TS_LIST_GET,
-		.doit	= ethnl_default_doit,
-		.start	= ethnl_default_start,
-		.dumpit	= ethnl_default_dumpit,
-		.done	= ethnl_default_done,
-		.policy = ethnl_ts_get_policy,
-		.maxattr = ARRAY_SIZE(ethnl_ts_get_policy) - 1,
-	},
-	{
-		.cmd	= ETHTOOL_MSG_TS_SET,
-		.flags	= GENL_UNS_ADMIN_PERM,
-		.doit	= ethnl_default_set_doit,
-		.policy = ethnl_ts_set_policy,
-		.maxattr = ARRAY_SIZE(ethnl_ts_set_policy) - 1,
-	},
 };
 
 static const struct genl_multicast_group ethtool_nl_mcgrps[] = {
diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h
index 8fedf234b824..9a333a8d04c1 100644
--- a/net/ethtool/netlink.h
+++ b/net/ethtool/netlink.h
@@ -395,8 +395,6 @@ extern const struct ethnl_request_ops ethnl_rss_request_ops;
 extern const struct ethnl_request_ops ethnl_plca_cfg_request_ops;
 extern const struct ethnl_request_ops ethnl_plca_status_request_ops;
 extern const struct ethnl_request_ops ethnl_mm_request_ops;
-extern const struct ethnl_request_ops ethnl_ts_request_ops;
-extern const struct ethnl_request_ops ethnl_ts_list_request_ops;
 
 extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1];
 extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1];
@@ -443,8 +441,6 @@ extern const struct nla_policy ethnl_plca_set_cfg_policy[ETHTOOL_A_PLCA_MAX + 1]
 extern const struct nla_policy ethnl_plca_get_status_policy[ETHTOOL_A_PLCA_HEADER + 1];
 extern const struct nla_policy ethnl_mm_get_policy[ETHTOOL_A_MM_HEADER + 1];
 extern const struct nla_policy ethnl_mm_set_policy[ETHTOOL_A_MM_MAX + 1];
-extern const struct nla_policy ethnl_ts_get_policy[ETHTOOL_A_TS_HEADER + 1];
-extern const struct nla_policy ethnl_ts_set_policy[ETHTOOL_A_TS_MAX + 1];
 
 int ethnl_set_features(struct sk_buff *skb, struct genl_info *info);
 int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info);
diff --git a/net/ethtool/ts.c b/net/ethtool/ts.c
deleted file mode 100644
index 357265e74e08..000000000000
--- a/net/ethtool/ts.c
+++ /dev/null
@@ -1,244 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-
-#include <linux/net_tstamp.h>
-#include <linux/phy.h>
-
-#include "netlink.h"
-#include "common.h"
-#include "bitset.h"
-
-struct ts_req_info {
-	struct ethnl_req_info		base;
-};
-
-struct ts_reply_data {
-	struct ethnl_reply_data		base;
-	enum timestamping_layer		ts_layer;
-};
-
-#define TS_REPDATA(__reply_base) \
-	container_of(__reply_base, struct ts_reply_data, base)
-
-/* TS_GET */
-const struct nla_policy ethnl_ts_get_policy[] = {
-	[ETHTOOL_A_TS_HEADER]		=
-		NLA_POLICY_NESTED(ethnl_header_policy),
-};
-
-static int ts_prepare_data(const struct ethnl_req_info *req_base,
-			   struct ethnl_reply_data *reply_base,
-			   const struct genl_info *info)
-{
-	struct ts_reply_data *data = TS_REPDATA(reply_base);
-	struct net_device *dev = reply_base->dev;
-	int ret;
-
-	ret = ethnl_ops_begin(dev);
-	if (ret < 0)
-		return ret;
-
-	data->ts_layer = dev->ts_layer;
-
-	ethnl_ops_complete(dev);
-
-	return ret;
-}
-
-static int ts_reply_size(const struct ethnl_req_info *req_base,
-			 const struct ethnl_reply_data *reply_base)
-{
-	return nla_total_size(sizeof(u32));
-}
-
-static int ts_fill_reply(struct sk_buff *skb,
-			 const struct ethnl_req_info *req_base,
-			 const struct ethnl_reply_data *reply_base)
-{
-	struct ts_reply_data *data = TS_REPDATA(reply_base);
-
-	return nla_put_u32(skb, ETHTOOL_A_TS_LAYER, data->ts_layer);
-}
-
-/* TS_SET */
-const struct nla_policy ethnl_ts_set_policy[] = {
-	[ETHTOOL_A_TS_HEADER]	= NLA_POLICY_NESTED(ethnl_header_policy),
-	[ETHTOOL_A_TS_LAYER]	= NLA_POLICY_RANGE(NLA_U32, 0,
-						   __TIMESTAMPING_COUNT - 1)
-};
-
-static int ethnl_set_ts_validate(struct ethnl_req_info *req_info,
-				 struct genl_info *info)
-{
-	struct nlattr **tb = info->attrs;
-	const struct net_device_ops *ops = req_info->dev->netdev_ops;
-
-	if (!ops->ndo_hwtstamp_set)
-		return -EOPNOTSUPP;
-
-	if (!tb[ETHTOOL_A_TS_LAYER])
-		return 0;
-
-	return 1;
-}
-
-static int ethnl_set_ts(struct ethnl_req_info *req_info, struct genl_info *info)
-{
-	struct net_device *dev = req_info->dev;
-	const struct ethtool_ops *ops = dev->ethtool_ops;
-	struct kernel_hwtstamp_config config = {0};
-	struct nlattr **tb = info->attrs;
-	enum timestamping_layer ts_layer;
-	bool mod = false;
-	int ret;
-
-	ts_layer = dev->ts_layer;
-	ethnl_update_u32(&ts_layer, tb[ETHTOOL_A_TS_LAYER], &mod);
-
-	if (!mod)
-		return 0;
-
-	if (ts_layer == SOFTWARE_TIMESTAMPING) {
-		struct ethtool_ts_info ts_info = {0};
-
-		if (!ops->get_ts_info) {
-			NL_SET_ERR_MSG_ATTR(info->extack,
-					    tb[ETHTOOL_A_TS_LAYER],
-					    "this net device cannot support timestamping");
-			return -EINVAL;
-		}
-
-		ops->get_ts_info(dev, &ts_info);
-		if ((ts_info.so_timestamping &
-		    SOF_TIMESTAMPING_SOFTWARE_MASK) !=
-		    SOF_TIMESTAMPING_SOFTWARE_MASK) {
-			NL_SET_ERR_MSG_ATTR(info->extack,
-					    tb[ETHTOOL_A_TS_LAYER],
-					    "this net device cannot support software timestamping");
-			return -EINVAL;
-		}
-	} else if (ts_layer == MAC_TIMESTAMPING) {
-		struct ethtool_ts_info ts_info = {0};
-
-		if (!ops->get_ts_info) {
-			NL_SET_ERR_MSG_ATTR(info->extack,
-					    tb[ETHTOOL_A_TS_LAYER],
-					    "this net device cannot support timestamping");
-			return -EINVAL;
-		}
-
-		ops->get_ts_info(dev, &ts_info);
-		if ((ts_info.so_timestamping &
-		    SOF_TIMESTAMPING_HARDWARE_MASK) !=
-		    SOF_TIMESTAMPING_HARDWARE_MASK) {
-			NL_SET_ERR_MSG_ATTR(info->extack,
-					    tb[ETHTOOL_A_TS_LAYER],
-					    "this net device cannot support hardware timestamping");
-			return -EINVAL;
-		}
-	} else if (ts_layer == PHY_TIMESTAMPING && !phy_has_tsinfo(dev->phydev)) {
-		NL_SET_ERR_MSG_ATTR(info->extack, tb[ETHTOOL_A_TS_LAYER],
-				    "this phy device cannot support timestamping");
-		return -EINVAL;
-	}
-
-	/* Disable time stamping in the current layer. */
-	if (netif_device_present(dev) &&
-	    (dev->ts_layer == PHY_TIMESTAMPING ||
-	    dev->ts_layer == MAC_TIMESTAMPING)) {
-		ret = dev_set_hwtstamp_phylib(dev, &config, info->extack);
-		if (ret < 0)
-			return ret;
-	}
-
-	dev->ts_layer = ts_layer;
-
-	return 1;
-}
-
-const struct ethnl_request_ops ethnl_ts_request_ops = {
-	.request_cmd		= ETHTOOL_MSG_TS_GET,
-	.reply_cmd		= ETHTOOL_MSG_TS_GET_REPLY,
-	.hdr_attr		= ETHTOOL_A_TS_HEADER,
-	.req_info_size		= sizeof(struct ts_req_info),
-	.reply_data_size	= sizeof(struct ts_reply_data),
-
-	.prepare_data		= ts_prepare_data,
-	.reply_size		= ts_reply_size,
-	.fill_reply		= ts_fill_reply,
-
-	.set_validate		= ethnl_set_ts_validate,
-	.set			= ethnl_set_ts,
-};
-
-/* TS_LIST_GET */
-struct ts_list_reply_data {
-	struct ethnl_reply_data		base;
-	enum timestamping_layer		ts_layer[__TIMESTAMPING_COUNT];
-	u8				num_ts;
-};
-
-#define TS_LIST_REPDATA(__reply_base) \
-	container_of(__reply_base, struct ts_list_reply_data, base)
-
-static int ts_list_prepare_data(const struct ethnl_req_info *req_base,
-				struct ethnl_reply_data *reply_base,
-				const struct genl_info *info)
-{
-	struct ts_list_reply_data *data = TS_LIST_REPDATA(reply_base);
-	struct net_device *dev = reply_base->dev;
-	const struct ethtool_ops *ops = dev->ethtool_ops;
-	int ret, i = 0;
-
-	ret = ethnl_ops_begin(dev);
-	if (ret < 0)
-		return ret;
-
-	if (phy_has_tsinfo(dev->phydev))
-		data->ts_layer[i++] = PHY_TIMESTAMPING;
-	if (ops->get_ts_info) {
-		struct ethtool_ts_info ts_info = {0};
-
-		ops->get_ts_info(dev, &ts_info);
-		if (ts_info.so_timestamping &
-		    SOF_TIMESTAMPING_HARDWARE_MASK)
-			data->ts_layer[i++] = MAC_TIMESTAMPING;
-
-		if (ts_info.so_timestamping &
-		    SOF_TIMESTAMPING_SOFTWARE_MASK)
-			data->ts_layer[i++] = SOFTWARE_TIMESTAMPING;
-	}
-
-	data->num_ts = i;
-	ethnl_ops_complete(dev);
-
-	return ret;
-}
-
-static int ts_list_reply_size(const struct ethnl_req_info *req_base,
-			      const struct ethnl_reply_data *reply_base)
-{
-	struct ts_list_reply_data *data = TS_LIST_REPDATA(reply_base);
-
-	return nla_total_size(sizeof(u32)) * data->num_ts;
-}
-
-static int ts_list_fill_reply(struct sk_buff *skb,
-			      const struct ethnl_req_info *req_base,
-			 const struct ethnl_reply_data *reply_base)
-{
-	struct ts_list_reply_data *data = TS_LIST_REPDATA(reply_base);
-
-	return nla_put(skb, ETHTOOL_A_TS_LIST_LAYER, sizeof(u32) * data->num_ts, data->ts_layer);
-}
-
-const struct ethnl_request_ops ethnl_ts_list_request_ops = {
-	.request_cmd		= ETHTOOL_MSG_TS_LIST_GET,
-	.reply_cmd		= ETHTOOL_MSG_TS_LIST_GET_REPLY,
-	.hdr_attr		= ETHTOOL_A_TS_HEADER,
-	.req_info_size		= sizeof(struct ts_req_info),
-	.reply_data_size	= sizeof(struct ts_list_reply_data),
-
-	.prepare_data		= ts_list_prepare_data,
-	.reply_size		= ts_list_reply_size,
-	.fill_reply		= ts_list_fill_reply,
-};
-- 
cgit v1.2.3


From ac40916a3f7243efbe6e129ebf495b5c33a3adfe Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Wed, 15 Nov 2023 20:01:08 +0800
Subject: rtnetlink: introduce nlmsg_new_large and use it in rtnl_getlink

if a PF has 256 or more VFs, ip link command will allocate an order 3
memory or more, and maybe trigger OOM due to memory fragment,
the VFs needed memory size is computed in rtnl_vfinfo_size.

so introduce nlmsg_new_large which calls netlink_alloc_large_skb in
which vmalloc is used for large memory, to avoid the failure of
allocating memory

    ip invoked oom-killer: gfp_mask=0xc2cc0(GFP_KERNEL|__GFP_NOWARN|\
	__GFP_COMP|__GFP_NOMEMALLOC), order=3, oom_score_adj=0
    CPU: 74 PID: 204414 Comm: ip Kdump: loaded Tainted: P           OE
    Call Trace:
    dump_stack+0x57/0x6a
    dump_header+0x4a/0x210
    oom_kill_process+0xe4/0x140
    out_of_memory+0x3e8/0x790
    __alloc_pages_slowpath.constprop.116+0x953/0xc50
    __alloc_pages_nodemask+0x2af/0x310
    kmalloc_large_node+0x38/0xf0
    __kmalloc_node_track_caller+0x417/0x4d0
    __kmalloc_reserve.isra.61+0x2e/0x80
    __alloc_skb+0x82/0x1c0
    rtnl_getlink+0x24f/0x370
    rtnetlink_rcv_msg+0x12c/0x350
    netlink_rcv_skb+0x50/0x100
    netlink_unicast+0x1b2/0x280
    netlink_sendmsg+0x355/0x4a0
    sock_sendmsg+0x5b/0x60
    ____sys_sendmsg+0x1ea/0x250
    ___sys_sendmsg+0x88/0xd0
    __sys_sendmsg+0x5e/0xa0
    do_syscall_64+0x33/0x40
    entry_SYSCALL_64_after_hwframe+0x44/0xa9
    RIP: 0033:0x7f95a65a5b70

Cc: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Link: https://lore.kernel.org/r/20231115120108.3711-1-lirongqing@baidu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netlink.h  |  1 +
 include/net/netlink.h    | 14 ++++++++++++++
 net/core/rtnetlink.c     |  2 +-
 net/netlink/af_netlink.c |  3 +--
 4 files changed, 17 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index 75d7de34c908..abe91ed6b9aa 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -351,5 +351,6 @@ bool netlink_ns_capable(const struct sk_buff *skb,
 			struct user_namespace *ns, int cap);
 bool netlink_capable(const struct sk_buff *skb, int cap);
 bool netlink_net_capable(const struct sk_buff *skb, int cap);
+struct sk_buff *netlink_alloc_large_skb(unsigned int size, int broadcast);
 
 #endif	/* __LINUX_NETLINK_H */
diff --git a/include/net/netlink.h b/include/net/netlink.h
index 83bdf787aeee..167b91348e57 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -1010,6 +1010,20 @@ static inline struct sk_buff *nlmsg_new(size_t payload, gfp_t flags)
 	return alloc_skb(nlmsg_total_size(payload), flags);
 }
 
+/**
+ * nlmsg_new_large - Allocate a new netlink message with non-contiguous
+ * physical memory
+ * @payload: size of the message payload
+ *
+ * The allocated skb is unable to have frag page for shinfo->frags*,
+ * as the NULL setting for skb->head in netlink_skb_destructor() will
+ * bypass most of the handling in skb_release_data()
+ */
+static inline struct sk_buff *nlmsg_new_large(size_t payload)
+{
+	return netlink_alloc_large_skb(nlmsg_total_size(payload), 0);
+}
+
 /**
  * nlmsg_end - Finalize a netlink message
  * @skb: socket buffer the message is stored in
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index e8431c6c8490..592164c2a540 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3849,7 +3849,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 		goto out;
 
 	err = -ENOBUFS;
-	nskb = nlmsg_new(if_nlmsg_size(dev, ext_filter_mask), GFP_KERNEL);
+	nskb = nlmsg_new_large(if_nlmsg_size(dev, ext_filter_mask));
 	if (nskb == NULL)
 		goto out;
 
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index eb086b06d60d..177126fb0484 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1204,8 +1204,7 @@ struct sock *netlink_getsockbyfilp(struct file *filp)
 	return sock;
 }
 
-static struct sk_buff *netlink_alloc_large_skb(unsigned int size,
-					       int broadcast)
+struct sk_buff *netlink_alloc_large_skb(unsigned int size, int broadcast)
 {
 	struct sk_buff *skb;
 	void *data;
-- 
cgit v1.2.3


From 2e7ed75e92fc493ff5484f61aed6489262c78f3e Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 27 Sep 2023 20:12:05 +0200
Subject: ieee802154: Internal PAN management

Introduce structures to describe peer devices in a PAN as well as a few
related helpers. We basically care about:
- Our unique parent after associating with a coordinator.
- Peer devices, children, which successfully associated with us.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Acked-by: Stefan Schmidt <stefan@datenfreihafen.org>
Acked-by: Alexander Aring <aahringo@redhat.com>
Link: https://lore.kernel.org/linux-wpan/20230927181214.129346-3-miquel.raynal@bootlin.com
---
 include/net/cfg802154.h | 47 ++++++++++++++++++++++++++++++++++++
 net/ieee802154/Makefile |  2 +-
 net/ieee802154/core.c   |  2 ++
 net/ieee802154/pan.c    | 63 +++++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 113 insertions(+), 1 deletion(-)
 create mode 100644 net/ieee802154/pan.c

(limited to 'include')

diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index f79ce133e51a..a89f1c9cea3f 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -303,6 +303,22 @@ struct ieee802154_coord_desc {
 	bool gts_permit;
 };
 
+/**
+ * struct ieee802154_pan_device - PAN device information
+ * @pan_id: the PAN ID of this device
+ * @mode: the preferred mode to reach the device
+ * @short_addr: the short address of this device
+ * @extended_addr: the extended address of this device
+ * @node: the list node
+ */
+struct ieee802154_pan_device {
+	__le16 pan_id;
+	u8 mode;
+	__le16 short_addr;
+	__le64 extended_addr;
+	struct list_head node;
+};
+
 /**
  * struct cfg802154_scan_request - Scan request
  *
@@ -478,6 +494,11 @@ struct wpan_dev {
 
 	/* fallback for acknowledgment bit setting */
 	bool ackreq;
+
+	/* Associations */
+	struct mutex association_lock;
+	struct ieee802154_pan_device *parent;
+	struct list_head children;
 };
 
 #define to_phy(_dev)	container_of(_dev, struct wpan_phy, dev)
@@ -529,4 +550,30 @@ static inline const char *wpan_phy_name(struct wpan_phy *phy)
 void ieee802154_configure_durations(struct wpan_phy *phy,
 				    unsigned int page, unsigned int channel);
 
+/**
+ * cfg802154_device_is_associated - Checks whether we are associated to any device
+ * @wpan_dev: the wpan device
+ * @return: true if we are associated
+ */
+bool cfg802154_device_is_associated(struct wpan_dev *wpan_dev);
+
+/**
+ * cfg802154_device_is_parent - Checks if a device is our coordinator
+ * @wpan_dev: the wpan device
+ * @target: the expected parent
+ * @return: true if @target is our coordinator
+ */
+bool cfg802154_device_is_parent(struct wpan_dev *wpan_dev,
+				struct ieee802154_addr *target);
+
+/**
+ * cfg802154_device_is_child - Checks whether a device is associated to us
+ * @wpan_dev: the wpan device
+ * @target: the expected child
+ * @return: the PAN device
+ */
+struct ieee802154_pan_device *
+cfg802154_device_is_child(struct wpan_dev *wpan_dev,
+			  struct ieee802154_addr *target);
+
 #endif /* __NET_CFG802154_H */
diff --git a/net/ieee802154/Makefile b/net/ieee802154/Makefile
index f05b7bdae2aa..7bce67673e83 100644
--- a/net/ieee802154/Makefile
+++ b/net/ieee802154/Makefile
@@ -4,7 +4,7 @@ obj-$(CONFIG_IEEE802154_SOCKET) += ieee802154_socket.o
 obj-y += 6lowpan/
 
 ieee802154-y := netlink.o nl-mac.o nl-phy.o nl_policy.o core.o \
-                header_ops.o sysfs.o nl802154.o trace.o
+                header_ops.o sysfs.o nl802154.o trace.o pan.o
 ieee802154_socket-y := socket.o
 
 CFLAGS_trace.o := -I$(src)
diff --git a/net/ieee802154/core.c b/net/ieee802154/core.c
index 57546e07e06a..cd69bdbfd59f 100644
--- a/net/ieee802154/core.c
+++ b/net/ieee802154/core.c
@@ -276,6 +276,8 @@ static int cfg802154_netdev_notifier_call(struct notifier_block *nb,
 		wpan_dev->identifier = ++rdev->wpan_dev_id;
 		list_add_rcu(&wpan_dev->list, &rdev->wpan_dev_list);
 		rdev->devlist_generation++;
+		mutex_init(&wpan_dev->association_lock);
+		INIT_LIST_HEAD(&wpan_dev->children);
 
 		wpan_dev->netdev = dev;
 		break;
diff --git a/net/ieee802154/pan.c b/net/ieee802154/pan.c
new file mode 100644
index 000000000000..2b30e7b19ac3
--- /dev/null
+++ b/net/ieee802154/pan.c
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * IEEE 802.15.4 PAN management
+ *
+ * Copyright (C) 2023 Qorvo US, Inc
+ * Authors:
+ *   - David Girault <david.girault@qorvo.com>
+ *   - Miquel Raynal <miquel.raynal@bootlin.com>
+ */
+
+#include <linux/kernel.h>
+#include <net/cfg802154.h>
+#include <net/af_ieee802154.h>
+
+/* Checks whether a device address matches one from the PAN list.
+ * This helper is meant to be used only during PAN management, when we expect
+ * extended addresses to be used.
+ */
+static bool cfg802154_pan_device_is_matching(struct ieee802154_pan_device *pan_dev,
+					     struct ieee802154_addr *ext_dev)
+{
+	if (!pan_dev || !ext_dev)
+		return false;
+
+	if (ext_dev->mode == IEEE802154_ADDR_SHORT)
+		return false;
+
+	return pan_dev->extended_addr == ext_dev->extended_addr;
+}
+
+bool cfg802154_device_is_associated(struct wpan_dev *wpan_dev)
+{
+	bool is_assoc;
+
+	mutex_lock(&wpan_dev->association_lock);
+	is_assoc = !list_empty(&wpan_dev->children) || wpan_dev->parent;
+	mutex_unlock(&wpan_dev->association_lock);
+
+	return is_assoc;
+}
+
+bool cfg802154_device_is_parent(struct wpan_dev *wpan_dev,
+				struct ieee802154_addr *target)
+{
+	lockdep_assert_held(&wpan_dev->association_lock);
+
+	return cfg802154_pan_device_is_matching(wpan_dev->parent, target);
+}
+
+struct ieee802154_pan_device *
+cfg802154_device_is_child(struct wpan_dev *wpan_dev,
+			  struct ieee802154_addr *target)
+{
+	struct ieee802154_pan_device *child;
+
+	lockdep_assert_held(&wpan_dev->association_lock);
+
+	list_for_each_entry(child, &wpan_dev->children, node)
+		if (cfg802154_pan_device_is_matching(child, target))
+			return child;
+
+	return NULL;
+}
-- 
cgit v1.2.3


From 05db59a0619969a47ab87050985344177c662cab Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 27 Sep 2023 20:12:06 +0200
Subject: ieee802154: Add support for user association requests

Users may decide to associate with a peer, which becomes our parent
coordinator. Let's add the necessary netlink support for this.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Acked-by: Stefan Schmidt <stefan@datenfreihafen.org>
Acked-by: Alexander Aring <aahringo@redhat.com>
Link: https://lore.kernel.org/linux-wpan/20230927181214.129346-4-miquel.raynal@bootlin.com
---
 include/net/cfg802154.h         |  4 ++++
 include/net/ieee802154_netdev.h | 38 ++++++++++++++++++++++++++++++++++++
 include/net/nl802154.h          |  1 +
 net/ieee802154/nl802154.c       | 43 +++++++++++++++++++++++++++++++++++++++++
 net/ieee802154/rdev-ops.h       | 15 ++++++++++++++
 net/ieee802154/trace.h          | 19 ++++++++++++++++++
 6 files changed, 120 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index a89f1c9cea3f..d0c033176220 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -20,6 +20,7 @@ struct wpan_phy;
 struct wpan_phy_cca;
 struct cfg802154_scan_request;
 struct cfg802154_beacon_request;
+struct ieee802154_addr;
 
 #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
 struct ieee802154_llsec_device_key;
@@ -77,6 +78,9 @@ struct cfg802154_ops {
 				struct cfg802154_beacon_request *request);
 	int	(*stop_beacons)(struct wpan_phy *wpan_phy,
 				struct wpan_dev *wpan_dev);
+	int	(*associate)(struct wpan_phy *wpan_phy,
+			     struct wpan_dev *wpan_dev,
+			     struct ieee802154_addr *coord);
 #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
 	void	(*get_llsec_table)(struct wpan_phy *wpan_phy,
 				   struct wpan_dev *wpan_dev,
diff --git a/include/net/ieee802154_netdev.h b/include/net/ieee802154_netdev.h
index 063313df447d..ca8c827d0d7f 100644
--- a/include/net/ieee802154_netdev.h
+++ b/include/net/ieee802154_netdev.h
@@ -125,6 +125,30 @@ struct ieee802154_hdr_fc {
 #endif
 };
 
+struct ieee802154_assoc_req_pl {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+	u8 reserved1:1,
+	   device_type:1,
+	   power_source:1,
+	   rx_on_when_idle:1,
+	   assoc_type:1,
+	   reserved2:1,
+	   security_cap:1,
+	   alloc_addr:1;
+#elif defined(__BIG_ENDIAN_BITFIELD)
+	u8 alloc_addr:1,
+	   security_cap:1,
+	   reserved2:1,
+	   assoc_type:1,
+	   rx_on_when_idle:1,
+	   power_source:1,
+	   device_type:1,
+	   reserved1:1;
+#else
+#error	"Please fix <asm/byteorder.h>"
+#endif
+} __packed;
+
 enum ieee802154_frame_version {
 	IEEE802154_2003_STD,
 	IEEE802154_2006_STD,
@@ -140,6 +164,14 @@ enum ieee802154_addressing_mode {
 	IEEE802154_EXTENDED_ADDRESSING,
 };
 
+enum ieee802154_association_status {
+	IEEE802154_ASSOCIATION_SUCCESSFUL = 0x00,
+	IEEE802154_PAN_AT_CAPACITY = 0x01,
+	IEEE802154_PAN_ACCESS_DENIED = 0x02,
+	IEEE802154_HOPPING_SEQUENCE_OFFSET_DUP = 0x03,
+	IEEE802154_FAST_ASSOCIATION_SUCCESSFUL = 0x80,
+};
+
 struct ieee802154_hdr {
 	struct ieee802154_hdr_fc fc;
 	u8 seq;
@@ -163,6 +195,12 @@ struct ieee802154_beacon_req_frame {
 	struct ieee802154_mac_cmd_pl mac_pl;
 };
 
+struct ieee802154_association_req_frame {
+	struct ieee802154_hdr mhr;
+	struct ieee802154_mac_cmd_pl mac_pl;
+	struct ieee802154_assoc_req_pl assoc_req_pl;
+};
+
 /* pushes hdr onto the skb. fields of hdr->fc that can be calculated from
  * the contents of hdr will be, and the actual value of those bits in
  * hdr->fc will be ignored. this includes the INTRA_PAN bit and the frame
diff --git a/include/net/nl802154.h b/include/net/nl802154.h
index 8cd9d141f5af..830e1c51d3df 100644
--- a/include/net/nl802154.h
+++ b/include/net/nl802154.h
@@ -78,6 +78,7 @@ enum nl802154_commands {
 	NL802154_CMD_SCAN_DONE,
 	NL802154_CMD_SEND_BEACONS,
 	NL802154_CMD_STOP_BEACONS,
+	NL802154_CMD_ASSOCIATE,
 
 	/* add new commands above here */
 
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index 1b6a9f27a6e4..e430dbf66d00 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -1628,6 +1628,41 @@ nl802154_stop_beacons(struct sk_buff *skb, struct genl_info *info)
 	return rdev_stop_beacons(rdev, wpan_dev);
 }
 
+static int nl802154_associate(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg802154_registered_device *rdev = info->user_ptr[0];
+	struct net_device *dev = info->user_ptr[1];
+	struct wpan_dev *wpan_dev;
+	struct wpan_phy *wpan_phy;
+	struct ieee802154_addr coord;
+	int err;
+
+	wpan_dev = dev->ieee802154_ptr;
+	wpan_phy = &rdev->wpan_phy;
+
+	if (wpan_phy->flags & WPAN_PHY_FLAG_DATAGRAMS_ONLY) {
+		NL_SET_ERR_MSG(info->extack, "PHY only supports datagrams");
+		return -EOPNOTSUPP;
+	}
+
+	if (!info->attrs[NL802154_ATTR_PAN_ID] ||
+	    !info->attrs[NL802154_ATTR_EXTENDED_ADDR])
+		return -EINVAL;
+
+	coord.pan_id = nla_get_le16(info->attrs[NL802154_ATTR_PAN_ID]);
+	coord.mode = IEEE802154_ADDR_LONG;
+	coord.extended_addr = nla_get_le64(info->attrs[NL802154_ATTR_EXTENDED_ADDR]);
+
+	mutex_lock(&wpan_dev->association_lock);
+	err = rdev_associate(rdev, wpan_dev, &coord);
+	mutex_unlock(&wpan_dev->association_lock);
+	if (err)
+		pr_err("Association with PAN ID 0x%x failed (%d)\n",
+		       le16_to_cpu(coord.pan_id), err);
+
+	return err;
+}
+
 #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
 static const struct nla_policy nl802154_dev_addr_policy[NL802154_DEV_ADDR_ATTR_MAX + 1] = {
 	[NL802154_DEV_ADDR_ATTR_PAN_ID] = { .type = NLA_U16 },
@@ -2749,6 +2784,14 @@ static const struct genl_ops nl802154_ops[] = {
 				  NL802154_FLAG_CHECK_NETDEV_UP |
 				  NL802154_FLAG_NEED_RTNL,
 	},
+	{
+		.cmd = NL802154_CMD_ASSOCIATE,
+		.doit = nl802154_associate,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL802154_FLAG_NEED_NETDEV |
+				  NL802154_FLAG_CHECK_NETDEV_UP |
+				  NL802154_FLAG_NEED_RTNL,
+	},
 #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
 	{
 		.cmd = NL802154_CMD_SET_SEC_PARAMS,
diff --git a/net/ieee802154/rdev-ops.h b/net/ieee802154/rdev-ops.h
index 5eaae15c610e..4843d52f1ee0 100644
--- a/net/ieee802154/rdev-ops.h
+++ b/net/ieee802154/rdev-ops.h
@@ -265,6 +265,21 @@ static inline int rdev_stop_beacons(struct cfg802154_registered_device *rdev,
 	return ret;
 }
 
+static inline int rdev_associate(struct cfg802154_registered_device *rdev,
+				 struct wpan_dev *wpan_dev,
+				 struct ieee802154_addr *coord)
+{
+	int ret;
+
+	if (!rdev->ops->associate)
+		return -EOPNOTSUPP;
+
+	trace_802154_rdev_associate(&rdev->wpan_phy, wpan_dev, coord);
+	ret = rdev->ops->associate(&rdev->wpan_phy, wpan_dev, coord);
+	trace_802154_rdev_return_int(&rdev->wpan_phy, ret);
+	return ret;
+}
+
 #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
 /* TODO this is already a nl802154, so move into ieee802154 */
 static inline void
diff --git a/net/ieee802154/trace.h b/net/ieee802154/trace.h
index c16db0b326fa..2e1d4f456316 100644
--- a/net/ieee802154/trace.h
+++ b/net/ieee802154/trace.h
@@ -356,6 +356,25 @@ DEFINE_EVENT(802154_wdev_template, 802154_rdev_stop_beacons,
 	TP_ARGS(wpan_phy, wpan_dev)
 );
 
+TRACE_EVENT(802154_rdev_associate,
+	TP_PROTO(struct wpan_phy *wpan_phy,
+		 struct wpan_dev *wpan_dev,
+		 struct ieee802154_addr *coord),
+	TP_ARGS(wpan_phy, wpan_dev, coord),
+	TP_STRUCT__entry(
+		WPAN_PHY_ENTRY
+		WPAN_DEV_ENTRY
+		__field(__le64, addr)
+	),
+	TP_fast_assign(
+		WPAN_PHY_ASSIGN;
+		WPAN_DEV_ASSIGN;
+		__entry->addr = coord->extended_addr;
+	),
+	TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT ", associating with: 0x%llx",
+		  WPAN_PHY_PR_ARG, WPAN_DEV_PR_ARG, __entry->addr)
+);
+
 TRACE_EVENT(802154_rdev_return_int,
 	TP_PROTO(struct wpan_phy *wpan_phy, int ret),
 	TP_ARGS(wpan_phy, ret),
-- 
cgit v1.2.3


From fefd19807fe9c65002366c749e809996a1ca4e68 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 27 Sep 2023 20:12:07 +0200
Subject: mac802154: Handle associating

Joining a PAN officially goes by associating with a coordinator. This
coordinator may have been discovered thanks to the beacons it sent in
the past. Add support to the MAC layer for these associations, which
require:
- Sending an association request
- Receiving an association response

The association response contains the association status, eventually a
reason if the association was unsuccessful, and finally a short address
that we should use for intra-PAN communication from now on, if we
required one (which is the default, and not yet configurable).

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Acked-by: Stefan Schmidt <stefan@datenfreihafen.org>
Acked-by: Alexander Aring <aahringo@redhat.com>
Link: https://lore.kernel.org/linux-wpan/20230927181214.129346-5-miquel.raynal@bootlin.com
---
 include/net/ieee802154_netdev.h |   5 ++
 net/ieee802154/core.c           |  12 ++++
 net/mac802154/cfg.c             |  69 ++++++++++++++++++++++
 net/mac802154/ieee802154_i.h    |  19 ++++++
 net/mac802154/main.c            |   2 +
 net/mac802154/rx.c              |   9 +++
 net/mac802154/scan.c            | 127 ++++++++++++++++++++++++++++++++++++++++
 7 files changed, 243 insertions(+)

(limited to 'include')

diff --git a/include/net/ieee802154_netdev.h b/include/net/ieee802154_netdev.h
index ca8c827d0d7f..e26ffd079556 100644
--- a/include/net/ieee802154_netdev.h
+++ b/include/net/ieee802154_netdev.h
@@ -149,6 +149,11 @@ struct ieee802154_assoc_req_pl {
 #endif
 } __packed;
 
+struct ieee802154_assoc_resp_pl {
+	__le16 short_addr;
+	u8 status;
+} __packed;
+
 enum ieee802154_frame_version {
 	IEEE802154_2003_STD,
 	IEEE802154_2006_STD,
diff --git a/net/ieee802154/core.c b/net/ieee802154/core.c
index cd69bdbfd59f..a08d75dd56ad 100644
--- a/net/ieee802154/core.c
+++ b/net/ieee802154/core.c
@@ -198,6 +198,16 @@ void wpan_phy_free(struct wpan_phy *phy)
 }
 EXPORT_SYMBOL(wpan_phy_free);
 
+static void cfg802154_free_peer_structures(struct wpan_dev *wpan_dev)
+{
+	mutex_lock(&wpan_dev->association_lock);
+
+	kfree(wpan_dev->parent);
+	wpan_dev->parent = NULL;
+
+	mutex_unlock(&wpan_dev->association_lock);
+}
+
 int cfg802154_switch_netns(struct cfg802154_registered_device *rdev,
 			   struct net *net)
 {
@@ -293,6 +303,8 @@ static int cfg802154_netdev_notifier_call(struct notifier_block *nb,
 		rdev->opencount++;
 		break;
 	case NETDEV_UNREGISTER:
+		cfg802154_free_peer_structures(wpan_dev);
+
 		/* It is possible to get NETDEV_UNREGISTER
 		 * multiple times. To detect that, check
 		 * that the interface is still on the list
diff --git a/net/mac802154/cfg.c b/net/mac802154/cfg.c
index 5c3cb019f751..0e8bb1486430 100644
--- a/net/mac802154/cfg.c
+++ b/net/mac802154/cfg.c
@@ -315,6 +315,74 @@ static int mac802154_stop_beacons(struct wpan_phy *wpan_phy,
 	return mac802154_stop_beacons_locked(local, sdata);
 }
 
+static int mac802154_associate(struct wpan_phy *wpan_phy,
+			       struct wpan_dev *wpan_dev,
+			       struct ieee802154_addr *coord)
+{
+	struct ieee802154_local *local = wpan_phy_priv(wpan_phy);
+	u64 ceaddr = swab64((__force u64)coord->extended_addr);
+	struct ieee802154_sub_if_data *sdata;
+	struct ieee802154_pan_device *parent;
+	__le16 short_addr;
+	int ret;
+
+	ASSERT_RTNL();
+
+	sdata = IEEE802154_WPAN_DEV_TO_SUB_IF(wpan_dev);
+
+	if (wpan_dev->parent) {
+		dev_err(&sdata->dev->dev,
+			"Device %8phC is already associated\n", &ceaddr);
+		return -EPERM;
+	}
+
+	if (coord->mode == IEEE802154_SHORT_ADDRESSING)
+		return -EINVAL;
+
+	parent = kzalloc(sizeof(*parent), GFP_KERNEL);
+	if (!parent)
+		return -ENOMEM;
+
+	parent->pan_id = coord->pan_id;
+	parent->mode = coord->mode;
+	parent->extended_addr = coord->extended_addr;
+	parent->short_addr = cpu_to_le16(IEEE802154_ADDR_SHORT_BROADCAST);
+
+	/* Set the PAN ID hardware address filter beforehand to avoid dropping
+	 * the association response with a destination PAN ID field set to the
+	 * "new" PAN ID.
+	 */
+	if (local->hw.flags & IEEE802154_HW_AFILT) {
+		ret = drv_set_pan_id(local, coord->pan_id);
+		if (ret < 0)
+			goto free_parent;
+	}
+
+	ret = mac802154_perform_association(sdata, parent, &short_addr);
+	if (ret)
+		goto reset_panid;
+
+	if (local->hw.flags & IEEE802154_HW_AFILT) {
+		ret = drv_set_short_addr(local, short_addr);
+		if (ret < 0)
+			goto reset_panid;
+	}
+
+	wpan_dev->pan_id = coord->pan_id;
+	wpan_dev->short_addr = short_addr;
+	wpan_dev->parent = parent;
+
+	return 0;
+
+reset_panid:
+	if (local->hw.flags & IEEE802154_HW_AFILT)
+		drv_set_pan_id(local, cpu_to_le16(IEEE802154_PAN_ID_BROADCAST));
+
+free_parent:
+	kfree(parent);
+	return ret;
+}
+
 #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
 static void
 ieee802154_get_llsec_table(struct wpan_phy *wpan_phy,
@@ -526,6 +594,7 @@ const struct cfg802154_ops mac802154_config_ops = {
 	.abort_scan = mac802154_abort_scan,
 	.send_beacons = mac802154_send_beacons,
 	.stop_beacons = mac802154_stop_beacons,
+	.associate = mac802154_associate,
 #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
 	.get_llsec_table = ieee802154_get_llsec_table,
 	.lock_llsec_table = ieee802154_lock_llsec_table,
diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h
index c347ec9ff8c9..fff67676b400 100644
--- a/net/mac802154/ieee802154_i.h
+++ b/net/mac802154/ieee802154_i.h
@@ -24,6 +24,7 @@
 enum ieee802154_ongoing {
 	IEEE802154_IS_SCANNING = BIT(0),
 	IEEE802154_IS_BEACONING = BIT(1),
+	IEEE802154_IS_ASSOCIATING = BIT(2),
 };
 
 /* mac802154 device private data */
@@ -74,6 +75,13 @@ struct ieee802154_local {
 	struct list_head rx_mac_cmd_list;
 	struct work_struct rx_mac_cmd_work;
 
+	/* Association */
+	struct ieee802154_pan_device *assoc_dev;
+	struct completion assoc_done;
+	__le16 assoc_addr;
+	u8 assoc_status;
+	struct work_struct assoc_work;
+
 	bool started;
 	bool suspended;
 	unsigned long ongoing;
@@ -296,6 +304,17 @@ static inline bool mac802154_is_beaconing(struct ieee802154_local *local)
 
 void mac802154_rx_mac_cmd_worker(struct work_struct *work);
 
+int mac802154_perform_association(struct ieee802154_sub_if_data *sdata,
+				  struct ieee802154_pan_device *coord,
+				  __le16 *short_addr);
+int mac802154_process_association_resp(struct ieee802154_sub_if_data *sdata,
+				       struct sk_buff *skb);
+
+static inline bool mac802154_is_associating(struct ieee802154_local *local)
+{
+	return test_bit(IEEE802154_IS_ASSOCIATING, &local->ongoing);
+}
+
 /* interface handling */
 int ieee802154_iface_init(void);
 void ieee802154_iface_exit(void);
diff --git a/net/mac802154/main.c b/net/mac802154/main.c
index 357ece67432b..9ab7396668d2 100644
--- a/net/mac802154/main.c
+++ b/net/mac802154/main.c
@@ -103,6 +103,8 @@ ieee802154_alloc_hw(size_t priv_data_len, const struct ieee802154_ops *ops)
 	INIT_DELAYED_WORK(&local->beacon_work, mac802154_beacon_worker);
 	INIT_WORK(&local->rx_mac_cmd_work, mac802154_rx_mac_cmd_worker);
 
+	init_completion(&local->assoc_done);
+
 	/* init supported flags with 802.15.4 default ranges */
 	phy->supported.max_minbe = 8;
 	phy->supported.min_maxbe = 3;
diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c
index e2434b4fe514..d0e08613a36b 100644
--- a/net/mac802154/rx.c
+++ b/net/mac802154/rx.c
@@ -93,6 +93,15 @@ void mac802154_rx_mac_cmd_worker(struct work_struct *work)
 
 		queue_delayed_work(local->mac_wq, &local->beacon_work, 0);
 		break;
+
+	case IEEE802154_CMD_ASSOCIATION_RESP:
+		dev_dbg(&mac_pkt->sdata->dev->dev, "processing ASSOC RESP\n");
+		if (!mac802154_is_associating(local))
+			break;
+
+		mac802154_process_association_resp(mac_pkt->sdata, mac_pkt->skb);
+		break;
+
 	default:
 		break;
 	}
diff --git a/net/mac802154/scan.c b/net/mac802154/scan.c
index d9658f2c4ae6..5dd50e1ce329 100644
--- a/net/mac802154/scan.c
+++ b/net/mac802154/scan.c
@@ -510,3 +510,130 @@ int mac802154_send_beacons_locked(struct ieee802154_sub_if_data *sdata,
 
 	return 0;
 }
+
+int mac802154_perform_association(struct ieee802154_sub_if_data *sdata,
+				  struct ieee802154_pan_device *coord,
+				  __le16 *short_addr)
+{
+	u64 ceaddr = swab64((__force u64)coord->extended_addr);
+	struct ieee802154_association_req_frame frame = {};
+	struct ieee802154_local *local = sdata->local;
+	struct wpan_dev *wpan_dev = &sdata->wpan_dev;
+	struct sk_buff *skb;
+	int ret;
+
+	frame.mhr.fc.type = IEEE802154_FC_TYPE_MAC_CMD;
+	frame.mhr.fc.security_enabled = 0;
+	frame.mhr.fc.frame_pending = 0;
+	frame.mhr.fc.ack_request = 1; /* We always expect an ack here */
+	frame.mhr.fc.intra_pan = 0;
+	frame.mhr.fc.dest_addr_mode = (coord->mode == IEEE802154_ADDR_LONG) ?
+		IEEE802154_EXTENDED_ADDRESSING : IEEE802154_SHORT_ADDRESSING;
+	frame.mhr.fc.version = IEEE802154_2003_STD;
+	frame.mhr.fc.source_addr_mode = IEEE802154_EXTENDED_ADDRESSING;
+	frame.mhr.source.mode = IEEE802154_ADDR_LONG;
+	frame.mhr.source.pan_id = cpu_to_le16(IEEE802154_PANID_BROADCAST);
+	frame.mhr.source.extended_addr = wpan_dev->extended_addr;
+	frame.mhr.dest.mode = coord->mode;
+	frame.mhr.dest.pan_id = coord->pan_id;
+	if (coord->mode == IEEE802154_ADDR_LONG)
+		frame.mhr.dest.extended_addr = coord->extended_addr;
+	else
+		frame.mhr.dest.short_addr = coord->short_addr;
+	frame.mhr.seq = atomic_inc_return(&wpan_dev->dsn) & 0xFF;
+	frame.mac_pl.cmd_id = IEEE802154_CMD_ASSOCIATION_REQ;
+	frame.assoc_req_pl.device_type = 1;
+	frame.assoc_req_pl.power_source = 1;
+	frame.assoc_req_pl.rx_on_when_idle = 1;
+	frame.assoc_req_pl.alloc_addr = 1;
+
+	skb = alloc_skb(IEEE802154_MAC_CMD_SKB_SZ + sizeof(frame.assoc_req_pl),
+			GFP_KERNEL);
+	if (!skb)
+		return -ENOBUFS;
+
+	skb->dev = sdata->dev;
+
+	ret = ieee802154_mac_cmd_push(skb, &frame, &frame.assoc_req_pl,
+				      sizeof(frame.assoc_req_pl));
+	if (ret) {
+		kfree_skb(skb);
+		return ret;
+	}
+
+	local->assoc_dev = coord;
+	reinit_completion(&local->assoc_done);
+	set_bit(IEEE802154_IS_ASSOCIATING, &local->ongoing);
+
+	ret = ieee802154_mlme_tx_one_locked(local, sdata, skb);
+	if (ret) {
+		if (ret > 0)
+			ret = (ret == IEEE802154_NO_ACK) ? -EREMOTEIO : -EIO;
+		dev_warn(&sdata->dev->dev,
+			 "No ASSOC REQ ACK received from %8phC\n", &ceaddr);
+		goto clear_assoc;
+	}
+
+	ret = wait_for_completion_killable_timeout(&local->assoc_done, 10 * HZ);
+	if (ret <= 0) {
+		dev_warn(&sdata->dev->dev,
+			 "No ASSOC RESP received from %8phC\n", &ceaddr);
+		ret = -ETIMEDOUT;
+		goto clear_assoc;
+	}
+
+	if (local->assoc_status != IEEE802154_ASSOCIATION_SUCCESSFUL) {
+		if (local->assoc_status == IEEE802154_PAN_AT_CAPACITY)
+			ret = -ERANGE;
+		else
+			ret = -EPERM;
+
+		dev_warn(&sdata->dev->dev,
+			 "Negative ASSOC RESP received from %8phC: %s\n", &ceaddr,
+			 local->assoc_status == IEEE802154_PAN_AT_CAPACITY ?
+			 "PAN at capacity" : "access denied");
+	}
+
+	ret = 0;
+	*short_addr = local->assoc_addr;
+
+clear_assoc:
+	clear_bit(IEEE802154_IS_ASSOCIATING, &local->ongoing);
+	local->assoc_dev = NULL;
+
+	return ret;
+}
+
+int mac802154_process_association_resp(struct ieee802154_sub_if_data *sdata,
+				       struct sk_buff *skb)
+{
+	struct ieee802154_addr *src = &mac_cb(skb)->source;
+	struct ieee802154_addr *dest = &mac_cb(skb)->dest;
+	u64 deaddr = swab64((__force u64)dest->extended_addr);
+	struct ieee802154_local *local = sdata->local;
+	struct wpan_dev *wpan_dev = &sdata->wpan_dev;
+	struct ieee802154_assoc_resp_pl resp_pl = {};
+
+	if (skb->len != sizeof(resp_pl))
+		return -EINVAL;
+
+	if (unlikely(src->mode != IEEE802154_EXTENDED_ADDRESSING ||
+		     dest->mode != IEEE802154_EXTENDED_ADDRESSING))
+		return -EINVAL;
+
+	if (unlikely(dest->extended_addr != wpan_dev->extended_addr ||
+		     src->extended_addr != local->assoc_dev->extended_addr))
+		return -ENODEV;
+
+	memcpy(&resp_pl, skb->data, sizeof(resp_pl));
+	local->assoc_addr = resp_pl.short_addr;
+	local->assoc_status = resp_pl.status;
+
+	dev_dbg(&skb->dev->dev,
+		"ASSOC RESP 0x%x received from %8phC, getting short address %04x\n",
+		local->assoc_status, &deaddr, local->assoc_addr);
+
+	complete(&local->assoc_done);
+
+	return 0;
+}
-- 
cgit v1.2.3


From 7b18313e84eb62c3e4071f9679480159d8da5107 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 27 Sep 2023 20:12:08 +0200
Subject: ieee802154: Add support for user disassociation requests

A device may decide at some point to disassociate from a PAN, let's
introduce a netlink command for this purpose.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Acked-by: Stefan Schmidt <stefan@datenfreihafen.org>
Acked-by: Alexander Aring <aahringo@redhat.com>
Link: https://lore.kernel.org/linux-wpan/20230927181214.129346-6-miquel.raynal@bootlin.com
---
 include/net/cfg802154.h         |  3 +++
 include/net/ieee802154_netdev.h | 11 +++++++++++
 include/net/nl802154.h          |  1 +
 net/ieee802154/nl802154.c       | 41 +++++++++++++++++++++++++++++++++++++++++
 net/ieee802154/rdev-ops.h       | 15 +++++++++++++++
 net/ieee802154/trace.h          | 19 +++++++++++++++++++
 6 files changed, 90 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index d0c033176220..9b036ab20079 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -81,6 +81,9 @@ struct cfg802154_ops {
 	int	(*associate)(struct wpan_phy *wpan_phy,
 			     struct wpan_dev *wpan_dev,
 			     struct ieee802154_addr *coord);
+	int	(*disassociate)(struct wpan_phy *wpan_phy,
+				struct wpan_dev *wpan_dev,
+				struct ieee802154_addr *target);
 #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
 	void	(*get_llsec_table)(struct wpan_phy *wpan_phy,
 				   struct wpan_dev *wpan_dev,
diff --git a/include/net/ieee802154_netdev.h b/include/net/ieee802154_netdev.h
index e26ffd079556..16194356cfe7 100644
--- a/include/net/ieee802154_netdev.h
+++ b/include/net/ieee802154_netdev.h
@@ -177,6 +177,11 @@ enum ieee802154_association_status {
 	IEEE802154_FAST_ASSOCIATION_SUCCESSFUL = 0x80,
 };
 
+enum ieee802154_disassociation_reason {
+	IEEE802154_COORD_WISHES_DEVICE_TO_LEAVE = 0x1,
+	IEEE802154_DEVICE_WISHES_TO_LEAVE = 0x2,
+};
+
 struct ieee802154_hdr {
 	struct ieee802154_hdr_fc fc;
 	u8 seq;
@@ -206,6 +211,12 @@ struct ieee802154_association_req_frame {
 	struct ieee802154_assoc_req_pl assoc_req_pl;
 };
 
+struct ieee802154_disassociation_notif_frame {
+	struct ieee802154_hdr mhr;
+	struct ieee802154_mac_cmd_pl mac_pl;
+	u8 disassoc_pl;
+};
+
 /* pushes hdr onto the skb. fields of hdr->fc that can be calculated from
  * the contents of hdr will be, and the actual value of those bits in
  * hdr->fc will be ignored. this includes the INTRA_PAN bit and the frame
diff --git a/include/net/nl802154.h b/include/net/nl802154.h
index 830e1c51d3df..8a47c14c72f0 100644
--- a/include/net/nl802154.h
+++ b/include/net/nl802154.h
@@ -79,6 +79,7 @@ enum nl802154_commands {
 	NL802154_CMD_SEND_BEACONS,
 	NL802154_CMD_STOP_BEACONS,
 	NL802154_CMD_ASSOCIATE,
+	NL802154_CMD_DISASSOCIATE,
 
 	/* add new commands above here */
 
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index e430dbf66d00..dd86ecd7b193 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -1663,6 +1663,39 @@ static int nl802154_associate(struct sk_buff *skb, struct genl_info *info)
 	return err;
 }
 
+static int nl802154_disassociate(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg802154_registered_device *rdev = info->user_ptr[0];
+	struct net_device *dev = info->user_ptr[1];
+	struct wpan_dev *wpan_dev = dev->ieee802154_ptr;
+	struct wpan_phy *wpan_phy = &rdev->wpan_phy;
+	struct ieee802154_addr target;
+
+	if (wpan_phy->flags & WPAN_PHY_FLAG_DATAGRAMS_ONLY) {
+		NL_SET_ERR_MSG(info->extack, "PHY only supports datagrams");
+		return -EOPNOTSUPP;
+	}
+
+	target.pan_id = wpan_dev->pan_id;
+
+	if (info->attrs[NL802154_ATTR_EXTENDED_ADDR]) {
+		target.mode = IEEE802154_ADDR_LONG;
+		target.extended_addr = nla_get_le64(info->attrs[NL802154_ATTR_EXTENDED_ADDR]);
+	} else if (info->attrs[NL802154_ATTR_SHORT_ADDR]) {
+		target.mode = IEEE802154_ADDR_SHORT;
+		target.short_addr = nla_get_le16(info->attrs[NL802154_ATTR_SHORT_ADDR]);
+	} else {
+		NL_SET_ERR_MSG(info->extack, "Device address is missing");
+		return -EINVAL;
+	}
+
+	mutex_lock(&wpan_dev->association_lock);
+	rdev_disassociate(rdev, wpan_dev, &target);
+	mutex_unlock(&wpan_dev->association_lock);
+
+	return 0;
+}
+
 #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
 static const struct nla_policy nl802154_dev_addr_policy[NL802154_DEV_ADDR_ATTR_MAX + 1] = {
 	[NL802154_DEV_ADDR_ATTR_PAN_ID] = { .type = NLA_U16 },
@@ -2792,6 +2825,14 @@ static const struct genl_ops nl802154_ops[] = {
 				  NL802154_FLAG_CHECK_NETDEV_UP |
 				  NL802154_FLAG_NEED_RTNL,
 	},
+	{
+		.cmd = NL802154_CMD_DISASSOCIATE,
+		.doit = nl802154_disassociate,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL802154_FLAG_NEED_NETDEV |
+				  NL802154_FLAG_CHECK_NETDEV_UP |
+				  NL802154_FLAG_NEED_RTNL,
+	},
 #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
 	{
 		.cmd = NL802154_CMD_SET_SEC_PARAMS,
diff --git a/net/ieee802154/rdev-ops.h b/net/ieee802154/rdev-ops.h
index 4843d52f1ee0..64071ef6f57b 100644
--- a/net/ieee802154/rdev-ops.h
+++ b/net/ieee802154/rdev-ops.h
@@ -280,6 +280,21 @@ static inline int rdev_associate(struct cfg802154_registered_device *rdev,
 	return ret;
 }
 
+static inline int rdev_disassociate(struct cfg802154_registered_device *rdev,
+				    struct wpan_dev *wpan_dev,
+				    struct ieee802154_addr *target)
+{
+	int ret;
+
+	if (!rdev->ops->disassociate)
+		return -EOPNOTSUPP;
+
+	trace_802154_rdev_disassociate(&rdev->wpan_phy, wpan_dev, target);
+	ret = rdev->ops->disassociate(&rdev->wpan_phy, wpan_dev, target);
+	trace_802154_rdev_return_int(&rdev->wpan_phy, ret);
+	return ret;
+}
+
 #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
 /* TODO this is already a nl802154, so move into ieee802154 */
 static inline void
diff --git a/net/ieee802154/trace.h b/net/ieee802154/trace.h
index 2e1d4f456316..62aa6465253a 100644
--- a/net/ieee802154/trace.h
+++ b/net/ieee802154/trace.h
@@ -375,6 +375,25 @@ TRACE_EVENT(802154_rdev_associate,
 		  WPAN_PHY_PR_ARG, WPAN_DEV_PR_ARG, __entry->addr)
 );
 
+TRACE_EVENT(802154_rdev_disassociate,
+	TP_PROTO(struct wpan_phy *wpan_phy,
+		 struct wpan_dev *wpan_dev,
+		 struct ieee802154_addr *target),
+	TP_ARGS(wpan_phy, wpan_dev, target),
+	TP_STRUCT__entry(
+		WPAN_PHY_ENTRY
+		WPAN_DEV_ENTRY
+		__field(__le64, addr)
+	),
+	TP_fast_assign(
+		WPAN_PHY_ASSIGN;
+		WPAN_DEV_ASSIGN;
+		__entry->addr = target->extended_addr;
+	),
+	TP_printk(WPAN_PHY_PR_FMT ", " WPAN_DEV_PR_FMT ", disassociating with: 0x%llx",
+		  WPAN_PHY_PR_ARG, WPAN_DEV_PR_ARG, __entry->addr)
+);
+
 TRACE_EVENT(802154_rdev_return_int,
 	TP_PROTO(struct wpan_phy *wpan_phy, int ret),
 	TP_ARGS(wpan_phy, ret),
-- 
cgit v1.2.3


From 601f160b61b2152ef84a663f856350d5dd9e752a Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 27 Sep 2023 20:12:10 +0200
Subject: mac802154: Handle association requests from peers

Coordinators may have to handle association requests from peers which
want to join the PAN. The logic involves:
- Acknowledging the request (done by hardware)
- If requested, a random short address that is free on this PAN should
  be chosen for the device.
- Sending an association response with the short address allocated for
  the peer and expecting it to be ack'ed.

If anything fails during this procedure, the peer is considered not
associated.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Acked-by: Stefan Schmidt <stefan@datenfreihafen.org>
Acked-by: Alexander Aring <aahringo@redhat.com>
Link: https://lore.kernel.org/linux-wpan/20230927181214.129346-8-miquel.raynal@bootlin.com
---
 include/net/cfg802154.h         |   7 ++
 include/net/ieee802154_netdev.h |   6 ++
 net/ieee802154/core.c           |   7 ++
 net/ieee802154/pan.c            |  30 +++++++++
 net/mac802154/ieee802154_i.h    |   2 +
 net/mac802154/rx.c              |   8 +++
 net/mac802154/scan.c            | 142 ++++++++++++++++++++++++++++++++++++++++
 7 files changed, 202 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index 9b036ab20079..c844ae63bc04 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -583,4 +583,11 @@ struct ieee802154_pan_device *
 cfg802154_device_is_child(struct wpan_dev *wpan_dev,
 			  struct ieee802154_addr *target);
 
+/**
+ * cfg802154_get_free_short_addr - Get a free address among the known devices
+ * @wpan_dev: the wpan device
+ * @return: a random short address expectedly unused on our PAN
+ */
+__le16 cfg802154_get_free_short_addr(struct wpan_dev *wpan_dev);
+
 #endif /* __NET_CFG802154_H */
diff --git a/include/net/ieee802154_netdev.h b/include/net/ieee802154_netdev.h
index 16194356cfe7..4de858f9929e 100644
--- a/include/net/ieee802154_netdev.h
+++ b/include/net/ieee802154_netdev.h
@@ -211,6 +211,12 @@ struct ieee802154_association_req_frame {
 	struct ieee802154_assoc_req_pl assoc_req_pl;
 };
 
+struct ieee802154_association_resp_frame {
+	struct ieee802154_hdr mhr;
+	struct ieee802154_mac_cmd_pl mac_pl;
+	struct ieee802154_assoc_resp_pl assoc_resp_pl;
+};
+
 struct ieee802154_disassociation_notif_frame {
 	struct ieee802154_hdr mhr;
 	struct ieee802154_mac_cmd_pl mac_pl;
diff --git a/net/ieee802154/core.c b/net/ieee802154/core.c
index a08d75dd56ad..1670a71327a7 100644
--- a/net/ieee802154/core.c
+++ b/net/ieee802154/core.c
@@ -200,11 +200,18 @@ EXPORT_SYMBOL(wpan_phy_free);
 
 static void cfg802154_free_peer_structures(struct wpan_dev *wpan_dev)
 {
+	struct ieee802154_pan_device *child, *tmp;
+
 	mutex_lock(&wpan_dev->association_lock);
 
 	kfree(wpan_dev->parent);
 	wpan_dev->parent = NULL;
 
+	list_for_each_entry_safe(child, tmp, &wpan_dev->children, node) {
+		list_del(&child->node);
+		kfree(child);
+	}
+
 	mutex_unlock(&wpan_dev->association_lock);
 }
 
diff --git a/net/ieee802154/pan.c b/net/ieee802154/pan.c
index 43b8d2df2186..545461069197 100644
--- a/net/ieee802154/pan.c
+++ b/net/ieee802154/pan.c
@@ -63,3 +63,33 @@ cfg802154_device_is_child(struct wpan_dev *wpan_dev,
 	return NULL;
 }
 EXPORT_SYMBOL_GPL(cfg802154_device_is_child);
+
+__le16 cfg802154_get_free_short_addr(struct wpan_dev *wpan_dev)
+{
+	struct ieee802154_pan_device *child;
+	__le16 addr;
+
+	lockdep_assert_held(&wpan_dev->association_lock);
+
+	do {
+		get_random_bytes(&addr, 2);
+		if (addr == cpu_to_le16(IEEE802154_ADDR_SHORT_BROADCAST) ||
+		    addr == cpu_to_le16(IEEE802154_ADDR_SHORT_UNSPEC))
+			continue;
+
+		if (wpan_dev->short_addr == addr)
+			continue;
+
+		if (wpan_dev->parent && wpan_dev->parent->short_addr == addr)
+			continue;
+
+		list_for_each_entry(child, &wpan_dev->children, node)
+			if (child->short_addr == addr)
+				continue;
+
+		break;
+	} while (1);
+
+	return addr;
+}
+EXPORT_SYMBOL_GPL(cfg802154_get_free_short_addr);
diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h
index 92252f86c69c..432bfa87249e 100644
--- a/net/mac802154/ieee802154_i.h
+++ b/net/mac802154/ieee802154_i.h
@@ -318,6 +318,8 @@ static inline bool mac802154_is_associating(struct ieee802154_local *local)
 int mac802154_send_disassociation_notif(struct ieee802154_sub_if_data *sdata,
 					struct ieee802154_pan_device *target,
 					u8 reason);
+int mac802154_process_association_req(struct ieee802154_sub_if_data *sdata,
+				      struct sk_buff *skb);
 
 /* interface handling */
 int ieee802154_iface_init(void);
diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c
index d0e08613a36b..96040b63a4fc 100644
--- a/net/mac802154/rx.c
+++ b/net/mac802154/rx.c
@@ -102,6 +102,14 @@ void mac802154_rx_mac_cmd_worker(struct work_struct *work)
 		mac802154_process_association_resp(mac_pkt->sdata, mac_pkt->skb);
 		break;
 
+	case IEEE802154_CMD_ASSOCIATION_REQ:
+		dev_dbg(&mac_pkt->sdata->dev->dev, "processing ASSOC REQ\n");
+		if (mac_pkt->sdata->wpan_dev.iftype != NL802154_IFTYPE_COORD)
+			break;
+
+		mac802154_process_association_req(mac_pkt->sdata, mac_pkt->skb);
+		break;
+
 	default:
 		break;
 	}
diff --git a/net/mac802154/scan.c b/net/mac802154/scan.c
index e2f2e1235ec6..d5f66c204bc5 100644
--- a/net/mac802154/scan.c
+++ b/net/mac802154/scan.c
@@ -697,3 +697,145 @@ int mac802154_send_disassociation_notif(struct ieee802154_sub_if_data *sdata,
 	dev_dbg(&sdata->dev->dev, "DISASSOC ACK received from %8phC\n", &teaddr);
 	return 0;
 }
+
+static int
+mac802154_send_association_resp_locked(struct ieee802154_sub_if_data *sdata,
+				       struct ieee802154_pan_device *target,
+				       struct ieee802154_assoc_resp_pl *assoc_resp_pl)
+{
+	u64 teaddr = swab64((__force u64)target->extended_addr);
+	struct ieee802154_association_resp_frame frame = {};
+	struct ieee802154_local *local = sdata->local;
+	struct wpan_dev *wpan_dev = &sdata->wpan_dev;
+	struct sk_buff *skb;
+	int ret;
+
+	frame.mhr.fc.type = IEEE802154_FC_TYPE_MAC_CMD;
+	frame.mhr.fc.security_enabled = 0;
+	frame.mhr.fc.frame_pending = 0;
+	frame.mhr.fc.ack_request = 1; /* We always expect an ack here */
+	frame.mhr.fc.intra_pan = 1;
+	frame.mhr.fc.dest_addr_mode = IEEE802154_EXTENDED_ADDRESSING;
+	frame.mhr.fc.version = IEEE802154_2003_STD;
+	frame.mhr.fc.source_addr_mode = IEEE802154_EXTENDED_ADDRESSING;
+	frame.mhr.source.mode = IEEE802154_ADDR_LONG;
+	frame.mhr.source.extended_addr = wpan_dev->extended_addr;
+	frame.mhr.dest.mode = IEEE802154_ADDR_LONG;
+	frame.mhr.dest.pan_id = wpan_dev->pan_id;
+	frame.mhr.dest.extended_addr = target->extended_addr;
+	frame.mhr.seq = atomic_inc_return(&wpan_dev->dsn) & 0xFF;
+	frame.mac_pl.cmd_id = IEEE802154_CMD_ASSOCIATION_RESP;
+
+	skb = alloc_skb(IEEE802154_MAC_CMD_SKB_SZ + sizeof(*assoc_resp_pl),
+			GFP_KERNEL);
+	if (!skb)
+		return -ENOBUFS;
+
+	skb->dev = sdata->dev;
+
+	ret = ieee802154_mac_cmd_push(skb, &frame, assoc_resp_pl,
+				      sizeof(*assoc_resp_pl));
+	if (ret) {
+		kfree_skb(skb);
+		return ret;
+	}
+
+	ret = ieee802154_mlme_tx_locked(local, sdata, skb);
+	if (ret) {
+		dev_warn(&sdata->dev->dev,
+			 "No ASSOC RESP ACK received from %8phC\n", &teaddr);
+		if (ret > 0)
+			ret = (ret == IEEE802154_NO_ACK) ? -EREMOTEIO : -EIO;
+		return ret;
+	}
+
+	return 0;
+}
+
+int mac802154_process_association_req(struct ieee802154_sub_if_data *sdata,
+				      struct sk_buff *skb)
+{
+	struct wpan_dev *wpan_dev = &sdata->wpan_dev;
+	struct ieee802154_addr *src = &mac_cb(skb)->source;
+	struct ieee802154_addr *dest = &mac_cb(skb)->dest;
+	struct ieee802154_assoc_resp_pl assoc_resp_pl = {};
+	struct ieee802154_assoc_req_pl assoc_req_pl;
+	struct ieee802154_pan_device *child, *exchild;
+	struct ieee802154_addr tmp = {};
+	u64 ceaddr;
+	int ret;
+
+	if (skb->len != sizeof(assoc_req_pl))
+		return -EINVAL;
+
+	if (unlikely(src->mode != IEEE802154_EXTENDED_ADDRESSING))
+		return -EINVAL;
+
+	if (unlikely(dest->pan_id != wpan_dev->pan_id))
+		return -ENODEV;
+
+	if (dest->mode == IEEE802154_EXTENDED_ADDRESSING &&
+	    unlikely(dest->extended_addr != wpan_dev->extended_addr))
+		return -ENODEV;
+	else if (dest->mode == IEEE802154_SHORT_ADDRESSING &&
+		 unlikely(dest->short_addr != wpan_dev->short_addr))
+		return -ENODEV;
+
+	mutex_lock(&wpan_dev->association_lock);
+
+	memcpy(&assoc_req_pl, skb->data, sizeof(assoc_req_pl));
+	if (assoc_req_pl.assoc_type) {
+		dev_err(&skb->dev->dev, "Fast associations not supported yet\n");
+		ret = -EOPNOTSUPP;
+		goto unlock;
+	}
+
+	child = kzalloc(sizeof(*child), GFP_KERNEL);
+	if (!child) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
+
+	child->extended_addr = src->extended_addr;
+	child->mode = IEEE802154_EXTENDED_ADDRESSING;
+	ceaddr = swab64((__force u64)child->extended_addr);
+
+	assoc_resp_pl.status = IEEE802154_ASSOCIATION_SUCCESSFUL;
+	if (assoc_req_pl.alloc_addr) {
+		assoc_resp_pl.short_addr = cfg802154_get_free_short_addr(wpan_dev);
+		child->mode = IEEE802154_SHORT_ADDRESSING;
+	} else {
+		assoc_resp_pl.short_addr = cpu_to_le16(IEEE802154_ADDR_SHORT_UNSPEC);
+	}
+	child->short_addr = assoc_resp_pl.short_addr;
+	dev_dbg(&sdata->dev->dev,
+		"Accepting ASSOC REQ from child %8phC, providing short address 0x%04x\n",
+		&ceaddr, le16_to_cpu(child->short_addr));
+
+	ret = mac802154_send_association_resp_locked(sdata, child, &assoc_resp_pl);
+	if (ret) {
+		kfree(child);
+		goto unlock;
+	}
+
+	dev_dbg(&sdata->dev->dev,
+		"Successful association with new child %8phC\n", &ceaddr);
+
+	/* Ensure this child is not already associated (might happen due to
+	 * retransmissions), in this case drop the ex structure.
+	 */
+	tmp.mode = child->mode;
+	tmp.extended_addr = child->extended_addr;
+	exchild = cfg802154_device_is_child(wpan_dev, &tmp);
+	if (exchild) {
+		dev_dbg(&sdata->dev->dev,
+			"Child %8phC was already known\n", &ceaddr);
+		list_del(&exchild->node);
+	}
+
+	list_add(&child->node, &wpan_dev->children);
+
+unlock:
+	mutex_unlock(&wpan_dev->association_lock);
+	return ret;
+}
-- 
cgit v1.2.3


From ce93b9378c306e6bcc4e0bd817acf4195b4a0288 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 27 Sep 2023 20:12:11 +0200
Subject: ieee802154: Add support for limiting the number of associated devices

Coordinators may refuse associations. We need a user input for
that. Let's add a new netlink command which can provide a maximum number
of devices we accept to associate with as a first step. Later, we could
also forward the request to userspace and check whether the association
should be accepted or not.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Acked-by: Stefan Schmidt <stefan@datenfreihafen.org>
Acked-by: Alexander Aring <aahringo@redhat.com>
Link: https://lore.kernel.org/linux-wpan/20230927181214.129346-9-miquel.raynal@bootlin.com
---
 include/net/cfg802154.h   |  8 ++++++++
 include/net/nl802154.h    |  2 ++
 net/ieee802154/core.c     |  1 +
 net/ieee802154/nl802154.c | 28 ++++++++++++++++++++++++++++
 net/ieee802154/pan.c      |  8 ++++++++
 5 files changed, 47 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index c844ae63bc04..0d3e9af00198 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -506,6 +506,7 @@ struct wpan_dev {
 	struct mutex association_lock;
 	struct ieee802154_pan_device *parent;
 	struct list_head children;
+	unsigned int max_associations;
 };
 
 #define to_phy(_dev)	container_of(_dev, struct wpan_phy, dev)
@@ -583,6 +584,13 @@ struct ieee802154_pan_device *
 cfg802154_device_is_child(struct wpan_dev *wpan_dev,
 			  struct ieee802154_addr *target);
 
+/**
+ * cfg802154_set_max_associations - Limit the number of future associations
+ * @wpan_dev: the wpan device
+ * @max: the maximum number of devices we accept to associate
+ */
+void cfg802154_set_max_associations(struct wpan_dev *wpan_dev, unsigned int max);
+
 /**
  * cfg802154_get_free_short_addr - Get a free address among the known devices
  * @wpan_dev: the wpan device
diff --git a/include/net/nl802154.h b/include/net/nl802154.h
index 8a47c14c72f0..8b26faae49e8 100644
--- a/include/net/nl802154.h
+++ b/include/net/nl802154.h
@@ -80,6 +80,7 @@ enum nl802154_commands {
 	NL802154_CMD_STOP_BEACONS,
 	NL802154_CMD_ASSOCIATE,
 	NL802154_CMD_DISASSOCIATE,
+	NL802154_CMD_SET_MAX_ASSOCIATIONS,
 
 	/* add new commands above here */
 
@@ -149,6 +150,7 @@ enum nl802154_attrs {
 	NL802154_ATTR_SCAN_DURATION,
 	NL802154_ATTR_SCAN_DONE_REASON,
 	NL802154_ATTR_BEACON_INTERVAL,
+	NL802154_ATTR_MAX_ASSOCIATIONS,
 
 	/* add attributes here, update the policy in nl802154.c */
 
diff --git a/net/ieee802154/core.c b/net/ieee802154/core.c
index 1670a71327a7..2d6fe45efa05 100644
--- a/net/ieee802154/core.c
+++ b/net/ieee802154/core.c
@@ -295,6 +295,7 @@ static int cfg802154_netdev_notifier_call(struct notifier_block *nb,
 		rdev->devlist_generation++;
 		mutex_init(&wpan_dev->association_lock);
 		INIT_LIST_HEAD(&wpan_dev->children);
+		wpan_dev->max_associations = SZ_16K;
 
 		wpan_dev->netdev = dev;
 		break;
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index dd86ecd7b193..06e0bd6ffcca 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -234,6 +234,7 @@ static const struct nla_policy nl802154_policy[NL802154_ATTR_MAX+1] = {
 				 NL802154_SCAN_DONE_REASON_ABORTED),
 	[NL802154_ATTR_BEACON_INTERVAL] =
 		NLA_POLICY_MAX(NLA_U8, IEEE802154_ACTIVE_SCAN_DURATION),
+	[NL802154_ATTR_MAX_ASSOCIATIONS] = { .type = NLA_U32 },
 
 #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
 	[NL802154_ATTR_SEC_ENABLED] = { .type = NLA_U8, },
@@ -1696,6 +1697,26 @@ static int nl802154_disassociate(struct sk_buff *skb, struct genl_info *info)
 	return 0;
 }
 
+static int nl802154_set_max_associations(struct sk_buff *skb, struct genl_info *info)
+{
+	struct net_device *dev = info->user_ptr[1];
+	struct wpan_dev *wpan_dev = dev->ieee802154_ptr;
+	unsigned int max_assoc;
+
+	if (!info->attrs[NL802154_ATTR_MAX_ASSOCIATIONS]) {
+		NL_SET_ERR_MSG(info->extack, "No maximum number of association given");
+		return -EINVAL;
+	}
+
+	max_assoc = nla_get_u32(info->attrs[NL802154_ATTR_MAX_ASSOCIATIONS]);
+
+	mutex_lock(&wpan_dev->association_lock);
+	cfg802154_set_max_associations(wpan_dev, max_assoc);
+	mutex_unlock(&wpan_dev->association_lock);
+
+	return 0;
+}
+
 #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
 static const struct nla_policy nl802154_dev_addr_policy[NL802154_DEV_ADDR_ATTR_MAX + 1] = {
 	[NL802154_DEV_ADDR_ATTR_PAN_ID] = { .type = NLA_U16 },
@@ -2833,6 +2854,13 @@ static const struct genl_ops nl802154_ops[] = {
 				  NL802154_FLAG_CHECK_NETDEV_UP |
 				  NL802154_FLAG_NEED_RTNL,
 	},
+	{
+		.cmd = NL802154_CMD_SET_MAX_ASSOCIATIONS,
+		.doit = nl802154_set_max_associations,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL802154_FLAG_NEED_NETDEV |
+				  NL802154_FLAG_NEED_RTNL,
+	},
 #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
 	{
 		.cmd = NL802154_CMD_SET_SEC_PARAMS,
diff --git a/net/ieee802154/pan.c b/net/ieee802154/pan.c
index 545461069197..fb5b0af2ef68 100644
--- a/net/ieee802154/pan.c
+++ b/net/ieee802154/pan.c
@@ -93,3 +93,11 @@ __le16 cfg802154_get_free_short_addr(struct wpan_dev *wpan_dev)
 	return addr;
 }
 EXPORT_SYMBOL_GPL(cfg802154_get_free_short_addr);
+
+void cfg802154_set_max_associations(struct wpan_dev *wpan_dev, unsigned int max)
+{
+	lockdep_assert_held(&wpan_dev->association_lock);
+
+	wpan_dev->max_associations = max;
+}
+EXPORT_SYMBOL_GPL(cfg802154_set_max_associations);
-- 
cgit v1.2.3


From 80f8bf9a2a7f603662e08f7663643a58087a2cd4 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 27 Sep 2023 20:12:12 +0200
Subject: mac802154: Follow the number of associated devices

Track the count of associated devices. Limit the number of associations
using the value provided by the user if any. If we reach the maximum
number of associations, we tell the device we are at capacity. If the
user do not want to accept any more associations, it may specify the
value 0 to the maximum number of associations, which will lead to an
access denied error status returned to the peers trying to associate.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Acked-by: Stefan Schmidt <stefan@datenfreihafen.org>
Acked-by: Alexander Aring <aahringo@redhat.com>
Link: https://lore.kernel.org/linux-wpan/20230927181214.129346-10-miquel.raynal@bootlin.com
---
 include/net/cfg802154.h |  1 +
 net/ieee802154/core.c   |  2 ++
 net/mac802154/cfg.c     |  1 +
 net/mac802154/scan.c    | 33 +++++++++++++++++++++++----------
 4 files changed, 27 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index 0d3e9af00198..a64bbcd71f10 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -507,6 +507,7 @@ struct wpan_dev {
 	struct ieee802154_pan_device *parent;
 	struct list_head children;
 	unsigned int max_associations;
+	unsigned int nchildren;
 };
 
 #define to_phy(_dev)	container_of(_dev, struct wpan_phy, dev)
diff --git a/net/ieee802154/core.c b/net/ieee802154/core.c
index 2d6fe45efa05..60e8fff1347e 100644
--- a/net/ieee802154/core.c
+++ b/net/ieee802154/core.c
@@ -212,6 +212,8 @@ static void cfg802154_free_peer_structures(struct wpan_dev *wpan_dev)
 		kfree(child);
 	}
 
+	wpan_dev->nchildren = 0;
+
 	mutex_unlock(&wpan_dev->association_lock);
 }
 
diff --git a/net/mac802154/cfg.c b/net/mac802154/cfg.c
index 083de2d3fe37..17e2032fac24 100644
--- a/net/mac802154/cfg.c
+++ b/net/mac802154/cfg.c
@@ -454,6 +454,7 @@ static int mac802154_disassociate_child(struct wpan_phy *wpan_phy,
 		return ret;
 
 	list_del(&child->node);
+	wpan_dev->nchildren--;
 	kfree(child);
 
 	return 0;
diff --git a/net/mac802154/scan.c b/net/mac802154/scan.c
index d5f66c204bc5..81d2c2bb1f09 100644
--- a/net/mac802154/scan.c
+++ b/net/mac802154/scan.c
@@ -800,20 +800,32 @@ int mac802154_process_association_req(struct ieee802154_sub_if_data *sdata,
 	child->mode = IEEE802154_EXTENDED_ADDRESSING;
 	ceaddr = swab64((__force u64)child->extended_addr);
 
-	assoc_resp_pl.status = IEEE802154_ASSOCIATION_SUCCESSFUL;
-	if (assoc_req_pl.alloc_addr) {
-		assoc_resp_pl.short_addr = cfg802154_get_free_short_addr(wpan_dev);
-		child->mode = IEEE802154_SHORT_ADDRESSING;
+	if (wpan_dev->nchildren >= wpan_dev->max_associations) {
+		if (!wpan_dev->max_associations)
+			assoc_resp_pl.status = IEEE802154_PAN_ACCESS_DENIED;
+		else
+			assoc_resp_pl.status = IEEE802154_PAN_AT_CAPACITY;
+		assoc_resp_pl.short_addr = cpu_to_le16(IEEE802154_ADDR_SHORT_BROADCAST);
+		dev_dbg(&sdata->dev->dev,
+			"Refusing ASSOC REQ from child %8phC, %s\n", &ceaddr,
+			assoc_resp_pl.status == IEEE802154_PAN_ACCESS_DENIED ?
+			"access denied" : "too many children");
 	} else {
-		assoc_resp_pl.short_addr = cpu_to_le16(IEEE802154_ADDR_SHORT_UNSPEC);
+		assoc_resp_pl.status = IEEE802154_ASSOCIATION_SUCCESSFUL;
+		if (assoc_req_pl.alloc_addr) {
+			assoc_resp_pl.short_addr = cfg802154_get_free_short_addr(wpan_dev);
+			child->mode = IEEE802154_SHORT_ADDRESSING;
+		} else {
+			assoc_resp_pl.short_addr = cpu_to_le16(IEEE802154_ADDR_SHORT_UNSPEC);
+		}
+		child->short_addr = assoc_resp_pl.short_addr;
+		dev_dbg(&sdata->dev->dev,
+			"Accepting ASSOC REQ from child %8phC, providing short address 0x%04x\n",
+			&ceaddr, le16_to_cpu(child->short_addr));
 	}
-	child->short_addr = assoc_resp_pl.short_addr;
-	dev_dbg(&sdata->dev->dev,
-		"Accepting ASSOC REQ from child %8phC, providing short address 0x%04x\n",
-		&ceaddr, le16_to_cpu(child->short_addr));
 
 	ret = mac802154_send_association_resp_locked(sdata, child, &assoc_resp_pl);
-	if (ret) {
+	if (ret || assoc_resp_pl.status != IEEE802154_ASSOCIATION_SUCCESSFUL) {
 		kfree(child);
 		goto unlock;
 	}
@@ -834,6 +846,7 @@ int mac802154_process_association_req(struct ieee802154_sub_if_data *sdata,
 	}
 
 	list_add(&child->node, &wpan_dev->children);
+	wpan_dev->nchildren++;
 
 unlock:
 	mutex_unlock(&wpan_dev->association_lock);
-- 
cgit v1.2.3


From 83fcf26b00d77e4a0ec920524fe85350a27e9c05 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 27 Sep 2023 20:12:14 +0200
Subject: ieee802154: Give the user the association list

Upon request, we must be able to provide to the user the list of
associations currently in place. Let's add a new netlink command and
attribute for this purpose.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Acked-by: Stefan Schmidt <stefan@datenfreihafen.org>
Acked-by: Alexander Aring <aahringo@redhat.com>
Link: https://lore.kernel.org/linux-wpan/20230927181214.129346-12-miquel.raynal@bootlin.com
---
 include/net/nl802154.h    |  18 +++++++-
 net/ieee802154/nl802154.c | 103 +++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 117 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/nl802154.h b/include/net/nl802154.h
index 8b26faae49e8..4c752f799957 100644
--- a/include/net/nl802154.h
+++ b/include/net/nl802154.h
@@ -81,6 +81,7 @@ enum nl802154_commands {
 	NL802154_CMD_ASSOCIATE,
 	NL802154_CMD_DISASSOCIATE,
 	NL802154_CMD_SET_MAX_ASSOCIATIONS,
+	NL802154_CMD_LIST_ASSOCIATIONS,
 
 	/* add new commands above here */
 
@@ -151,6 +152,7 @@ enum nl802154_attrs {
 	NL802154_ATTR_SCAN_DONE_REASON,
 	NL802154_ATTR_BEACON_INTERVAL,
 	NL802154_ATTR_MAX_ASSOCIATIONS,
+	NL802154_ATTR_PEER,
 
 	/* add attributes here, update the policy in nl802154.c */
 
@@ -389,8 +391,6 @@ enum nl802154_supported_bool_states {
 	NL802154_SUPPORTED_BOOL_MAX = __NL802154_SUPPORTED_BOOL_AFTER_LAST - 1
 };
 
-#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
-
 enum nl802154_dev_addr_modes {
 	NL802154_DEV_ADDR_NONE,
 	__NL802154_DEV_ADDR_INVALID,
@@ -410,12 +410,26 @@ enum nl802154_dev_addr_attrs {
 	NL802154_DEV_ADDR_ATTR_SHORT,
 	NL802154_DEV_ADDR_ATTR_EXTENDED,
 	NL802154_DEV_ADDR_ATTR_PAD,
+	NL802154_DEV_ADDR_ATTR_PEER_TYPE,
 
 	/* keep last */
 	__NL802154_DEV_ADDR_ATTR_AFTER_LAST,
 	NL802154_DEV_ADDR_ATTR_MAX = __NL802154_DEV_ADDR_ATTR_AFTER_LAST - 1
 };
 
+enum nl802154_peer_type {
+	NL802154_PEER_TYPE_UNSPEC,
+
+	NL802154_PEER_TYPE_PARENT,
+	NL802154_PEER_TYPE_CHILD,
+
+	/* keep last */
+	__NL802154_PEER_TYPE_AFTER_LAST,
+	NL802154_PEER_TYPE_MAX = __NL802154_PEER_TYPE_AFTER_LAST - 1
+};
+
+#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
+
 enum nl802154_key_id_modes {
 	NL802154_KEY_ID_MODE_IMPLICIT,
 	NL802154_KEY_ID_MODE_INDEX,
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index 06e0bd6ffcca..822cf025120a 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -235,6 +235,7 @@ static const struct nla_policy nl802154_policy[NL802154_ATTR_MAX+1] = {
 	[NL802154_ATTR_BEACON_INTERVAL] =
 		NLA_POLICY_MAX(NLA_U8, IEEE802154_ACTIVE_SCAN_DURATION),
 	[NL802154_ATTR_MAX_ASSOCIATIONS] = { .type = NLA_U32 },
+	[NL802154_ATTR_PEER] = { .type = NLA_NESTED },
 
 #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
 	[NL802154_ATTR_SEC_ENABLED] = { .type = NLA_U8, },
@@ -249,7 +250,6 @@ static const struct nla_policy nl802154_policy[NL802154_ATTR_MAX+1] = {
 #endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */
 };
 
-#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
 static int
 nl802154_prepare_wpan_dev_dump(struct sk_buff *skb,
 			       struct netlink_callback *cb,
@@ -308,7 +308,6 @@ nl802154_finish_wpan_dev_dump(struct cfg802154_registered_device *rdev)
 {
 	rtnl_unlock();
 }
-#endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */
 
 /* message building helper */
 static inline void *nl802154hdr_put(struct sk_buff *skb, u32 portid, u32 seq,
@@ -1717,6 +1716,101 @@ static int nl802154_set_max_associations(struct sk_buff *skb, struct genl_info *
 	return 0;
 }
 
+static int nl802154_send_peer_info(struct sk_buff *msg,
+				   struct netlink_callback *cb,
+				   u32 seq, int flags,
+				   struct cfg802154_registered_device *rdev,
+				   struct wpan_dev *wpan_dev,
+				   struct ieee802154_pan_device *peer,
+				   enum nl802154_peer_type type)
+{
+	struct nlattr *nla;
+	void *hdr;
+
+	ASSERT_RTNL();
+
+	hdr = nl802154hdr_put(msg, NETLINK_CB(cb->skb).portid, seq, flags,
+			      NL802154_CMD_LIST_ASSOCIATIONS);
+	if (!hdr)
+		return -ENOBUFS;
+
+	genl_dump_check_consistent(cb, hdr);
+
+	nla = nla_nest_start_noflag(msg, NL802154_ATTR_PEER);
+	if (!nla)
+		goto nla_put_failure;
+
+	if (nla_put_u8(msg, NL802154_DEV_ADDR_ATTR_PEER_TYPE, type))
+		goto nla_put_failure;
+
+	if (nla_put_u8(msg, NL802154_DEV_ADDR_ATTR_MODE, peer->mode))
+		goto nla_put_failure;
+
+	if (nla_put(msg, NL802154_DEV_ADDR_ATTR_SHORT,
+		    IEEE802154_SHORT_ADDR_LEN, &peer->short_addr))
+		goto nla_put_failure;
+
+	if (nla_put(msg, NL802154_DEV_ADDR_ATTR_EXTENDED,
+		    IEEE802154_EXTENDED_ADDR_LEN, &peer->extended_addr))
+		goto nla_put_failure;
+
+	nla_nest_end(msg, nla);
+
+	genlmsg_end(msg, hdr);
+
+	return 0;
+
+ nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+	return -EMSGSIZE;
+}
+
+static int nl802154_list_associations(struct sk_buff *skb,
+				      struct netlink_callback *cb)
+{
+	struct cfg802154_registered_device *rdev;
+	struct ieee802154_pan_device *child;
+	struct wpan_dev *wpan_dev;
+	int err;
+
+	err = nl802154_prepare_wpan_dev_dump(skb, cb, &rdev, &wpan_dev);
+	if (err)
+		return err;
+
+	mutex_lock(&wpan_dev->association_lock);
+
+	if (cb->args[2])
+		goto out;
+
+	if (wpan_dev->parent) {
+		err = nl802154_send_peer_info(skb, cb, cb->nlh->nlmsg_seq,
+					      NLM_F_MULTI, rdev, wpan_dev,
+					      wpan_dev->parent,
+					      NL802154_PEER_TYPE_PARENT);
+		if (err < 0)
+			goto out_err;
+	}
+
+	list_for_each_entry(child, &wpan_dev->children, node) {
+		err = nl802154_send_peer_info(skb, cb, cb->nlh->nlmsg_seq,
+					      NLM_F_MULTI, rdev, wpan_dev,
+					      child,
+					      NL802154_PEER_TYPE_CHILD);
+		if (err < 0)
+			goto out_err;
+	}
+
+	cb->args[2] = 1;
+out:
+	err = skb->len;
+out_err:
+	mutex_unlock(&wpan_dev->association_lock);
+
+	nl802154_finish_wpan_dev_dump(rdev);
+
+	return err;
+}
+
 #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
 static const struct nla_policy nl802154_dev_addr_policy[NL802154_DEV_ADDR_ATTR_MAX + 1] = {
 	[NL802154_DEV_ADDR_ATTR_PAN_ID] = { .type = NLA_U16 },
@@ -2861,6 +2955,11 @@ static const struct genl_ops nl802154_ops[] = {
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
 				  NL802154_FLAG_NEED_RTNL,
 	},
+	{
+		.cmd = NL802154_CMD_LIST_ASSOCIATIONS,
+		.dumpit = nl802154_list_associations,
+		/* can be retrieved by unprivileged users */
+	},
 #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
 	{
 		.cmd = NL802154_CMD_SET_SEC_PARAMS,
-- 
cgit v1.2.3


From d04ce4113cb4e5c2deddcb161db42a25917f285f Mon Sep 17 00:00:00 2001
From: Stefan Binding <sbinding@opensource.cirrus.com>
Date: Fri, 17 Nov 2023 16:36:09 +0000
Subject: ALSA: cs35l41: Fix for old systems which do not support command

Some older laptops using cs35l41 use firmware which does not support
the CSPL_MBOX_CMD_SPK_OUT_ENABLE command.
Firmware versions v0.28.0 and older do not support this command.

Fixes: fa3efcc36aac ("ALSA: cs35l41: Use mbox command to enable speaker output for external boost")
Signed-off-by: Stefan Binding <sbinding@opensource.cirrus.com>
Link: https://lore.kernel.org/r/20231117163609.823627-3-sbinding@opensource.cirrus.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/cs35l41.h        | 2 +-
 sound/pci/hda/cs35l41_hda.c    | 4 ++--
 sound/soc/codecs/cs35l41-lib.c | 6 ++++--
 sound/soc/codecs/cs35l41.c     | 4 ++--
 4 files changed, 9 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/sound/cs35l41.h b/include/sound/cs35l41.h
index 043f8ac65dbf..68e053fe7340 100644
--- a/include/sound/cs35l41.h
+++ b/include/sound/cs35l41.h
@@ -906,6 +906,6 @@ int cs35l41_init_boost(struct device *dev, struct regmap *regmap,
 bool cs35l41_safe_reset(struct regmap *regmap, enum cs35l41_boost_type b_type);
 int cs35l41_mdsync_up(struct regmap *regmap);
 int cs35l41_global_enable(struct device *dev, struct regmap *regmap, enum cs35l41_boost_type b_type,
-			  int enable, bool firmware_running);
+			  int enable, struct cs_dsp *dsp);
 
 #endif /* __CS35L41_H */
diff --git a/sound/pci/hda/cs35l41_hda.c b/sound/pci/hda/cs35l41_hda.c
index b7d2aa18c566..cbd7d8badf91 100644
--- a/sound/pci/hda/cs35l41_hda.c
+++ b/sound/pci/hda/cs35l41_hda.c
@@ -598,7 +598,7 @@ static void cs35l41_hda_play_done(struct device *dev)
 	dev_dbg(dev, "Play (Complete)\n");
 
 	cs35l41_global_enable(dev, reg, cs35l41->hw_cfg.bst_type, 1,
-			      cs35l41->cs_dsp.running);
+			      &cs35l41->cs_dsp);
 	cs35l41_mute(dev, false);
 }
 
@@ -611,7 +611,7 @@ static void cs35l41_hda_pause_start(struct device *dev)
 
 	cs35l41_mute(dev, true);
 	cs35l41_global_enable(dev, reg, cs35l41->hw_cfg.bst_type, 0,
-			      cs35l41->cs_dsp.running);
+			      &cs35l41->cs_dsp);
 }
 
 static void cs35l41_hda_pause_done(struct device *dev)
diff --git a/sound/soc/codecs/cs35l41-lib.c b/sound/soc/codecs/cs35l41-lib.c
index 4569e4f7cf7e..e9993a39f7d0 100644
--- a/sound/soc/codecs/cs35l41-lib.c
+++ b/sound/soc/codecs/cs35l41-lib.c
@@ -16,6 +16,8 @@
 
 #include <sound/cs35l41.h>
 
+#define CS35L41_FIRMWARE_OLD_VERSION 0x001C00 /* v0.28.0 */
+
 static const struct reg_default cs35l41_reg[] = {
 	{ CS35L41_PWR_CTRL1,			0x00000000 },
 	{ CS35L41_PWR_CTRL2,			0x00000000 },
@@ -1214,7 +1216,7 @@ EXPORT_SYMBOL_GPL(cs35l41_safe_reset);
  * the PLL Lock interrupt, in the IRQ handler.
  */
 int cs35l41_global_enable(struct device *dev, struct regmap *regmap, enum cs35l41_boost_type b_type,
-			  int enable, bool firmware_running)
+			  int enable, struct cs_dsp *dsp)
 {
 	int ret;
 	unsigned int gpio1_func, pad_control, pwr_ctrl1, pwr_ctrl3, int_status, pup_pdn_mask;
@@ -1309,7 +1311,7 @@ int cs35l41_global_enable(struct device *dev, struct regmap *regmap, enum cs35l4
 			}
 			regmap_write(regmap, CS35L41_IRQ1_STATUS1, CS35L41_PUP_DONE_MASK);
 
-			if (firmware_running)
+			if (dsp->running && dsp->fw_id_version > CS35L41_FIRMWARE_OLD_VERSION)
 				ret = cs35l41_set_cspl_mbox_cmd(dev, regmap,
 								CSPL_MBOX_CMD_SPK_OUT_ENABLE);
 			else
diff --git a/sound/soc/codecs/cs35l41.c b/sound/soc/codecs/cs35l41.c
index d0e9128ac6d0..dfb4ce53491b 100644
--- a/sound/soc/codecs/cs35l41.c
+++ b/sound/soc/codecs/cs35l41.c
@@ -519,11 +519,11 @@ static int cs35l41_main_amp_event(struct snd_soc_dapm_widget *w,
 						ARRAY_SIZE(cs35l41_pup_patch));
 
 		ret = cs35l41_global_enable(cs35l41->dev, cs35l41->regmap, cs35l41->hw_cfg.bst_type,
-					    1, cs35l41->dsp.cs_dsp.running);
+					    1, &cs35l41->dsp.cs_dsp);
 		break;
 	case SND_SOC_DAPM_POST_PMD:
 		ret = cs35l41_global_enable(cs35l41->dev, cs35l41->regmap, cs35l41->hw_cfg.bst_type,
-					    0, cs35l41->dsp.cs_dsp.running);
+					    0, &cs35l41->dsp.cs_dsp);
 
 		regmap_multi_reg_write_bypassed(cs35l41->regmap,
 						cs35l41_pdn_patch,
-- 
cgit v1.2.3


From f25d34646bd01505a0989ca67bc9a37390cae755 Mon Sep 17 00:00:00 2001
From: Armin Wolf <W_Armin@gmx.de>
Date: Fri, 3 Nov 2023 19:25:23 +0100
Subject: platform/x86: wmi: Add wmidev_block_set()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently, WMI drivers have to use the deprecated GUID-based
interface when setting data blocks. This prevents those
drivers from fully moving away from this interface.

Provide wmidev_block_set() so drivers using wmi_set_block() can
fully migrate to the modern bus-based interface.

Tested with a custom SSDT from the Intel Slim Bootloader project.

Signed-off-by: Armin Wolf <W_Armin@gmx.de>
Link: https://lore.kernel.org/r/20231103182526.3524-1-W_Armin@gmx.de
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 drivers/platform/x86/wmi.c | 64 ++++++++++++++++++++++++----------------------
 include/linux/wmi.h        |  2 ++
 2 files changed, 36 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c
index 5c27b4aa9690..9d9a050e7086 100644
--- a/drivers/platform/x86/wmi.c
+++ b/drivers/platform/x86/wmi.c
@@ -536,41 +536,50 @@ EXPORT_SYMBOL_GPL(wmidev_block_query);
  *
  * Return: acpi_status signaling success or error.
  */
-acpi_status wmi_set_block(const char *guid_string, u8 instance,
-			  const struct acpi_buffer *in)
+acpi_status wmi_set_block(const char *guid_string, u8 instance, const struct acpi_buffer *in)
 {
-	struct wmi_block *wblock;
-	struct guid_block *block;
 	struct wmi_device *wdev;
-	acpi_handle handle;
-	struct acpi_object_list input;
-	union acpi_object params[2];
-	char method[WMI_ACPI_METHOD_NAME_SIZE];
 	acpi_status status;
 
-	if (!in)
-		return AE_BAD_DATA;
-
 	wdev = wmi_find_device_by_guid(guid_string);
 	if (IS_ERR(wdev))
 		return AE_ERROR;
 
-	wblock = container_of(wdev, struct wmi_block, dev);
-	block = &wblock->gblock;
-	handle = wblock->acpi_device->handle;
+	status =  wmidev_block_set(wdev, instance, in);
+	wmi_device_put(wdev);
 
-	if (block->instance_count <= instance) {
-		status = AE_BAD_PARAMETER;
+	return status;
+}
+EXPORT_SYMBOL_GPL(wmi_set_block);
 
-		goto err_wdev_put;
-	}
+/**
+ * wmidev_block_set - Write to a WMI block
+ * @wdev: A wmi bus device from a driver
+ * @instance: Instance index
+ * @in: Buffer containing new values for the data block
+ *
+ * Write contents of the input buffer to an ACPI-WMI data block.
+ *
+ * Return: acpi_status signaling success or error.
+ */
+acpi_status wmidev_block_set(struct wmi_device *wdev, u8 instance, const struct acpi_buffer *in)
+{
+	struct wmi_block *wblock = container_of(wdev, struct wmi_block, dev);
+	acpi_handle handle = wblock->acpi_device->handle;
+	struct guid_block *block = &wblock->gblock;
+	char method[WMI_ACPI_METHOD_NAME_SIZE];
+	struct acpi_object_list input;
+	union acpi_object params[2];
 
-	/* Check GUID is a data block */
-	if (block->flags & (ACPI_WMI_EVENT | ACPI_WMI_METHOD)) {
-		status = AE_ERROR;
+	if (!in)
+		return AE_BAD_DATA;
 
-		goto err_wdev_put;
-	}
+	if (block->instance_count <= instance)
+		return AE_BAD_PARAMETER;
+
+	/* Check GUID is a data block */
+	if (block->flags & (ACPI_WMI_EVENT | ACPI_WMI_METHOD))
+		return AE_ERROR;
 
 	input.count = 2;
 	input.pointer = params;
@@ -582,14 +591,9 @@ acpi_status wmi_set_block(const char *guid_string, u8 instance,
 
 	get_acpi_method_name(wblock, 'S', method);
 
-	status = acpi_evaluate_object(handle, method, &input, NULL);
-
-err_wdev_put:
-	wmi_device_put(wdev);
-
-	return status;
+	return acpi_evaluate_object(handle, method, &input, NULL);
 }
-EXPORT_SYMBOL_GPL(wmi_set_block);
+EXPORT_SYMBOL_GPL(wmidev_block_set);
 
 static void wmi_dump_wdg(const struct guid_block *g)
 {
diff --git a/include/linux/wmi.h b/include/linux/wmi.h
index 763bd382cf2d..207544968268 100644
--- a/include/linux/wmi.h
+++ b/include/linux/wmi.h
@@ -35,6 +35,8 @@ extern acpi_status wmidev_evaluate_method(struct wmi_device *wdev,
 extern union acpi_object *wmidev_block_query(struct wmi_device *wdev,
 					     u8 instance);
 
+acpi_status wmidev_block_set(struct wmi_device *wdev, u8 instance, const struct acpi_buffer *in);
+
 u8 wmidev_instance_count(struct wmi_device *wdev);
 
 extern int set_required_buffer_size(struct wmi_device *wdev, u64 length);
-- 
cgit v1.2.3


From 7275bf3e09578e1761157e7683f2e898c5c235a6 Mon Sep 17 00:00:00 2001
From: Armin Wolf <W_Armin@gmx.de>
Date: Fri, 3 Nov 2023 19:25:24 +0100
Subject: platform/x86: wmi: Add to_wmi_device() helper macro
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add a helper macro for WMI drivers to cast a device to
the corresponding WMI device. This should replace some
boilerplate code.

Signed-off-by: Armin Wolf <W_Armin@gmx.de>
Link: https://lore.kernel.org/r/20231103182526.3524-2-W_Armin@gmx.de
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 include/linux/wmi.h | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'include')

diff --git a/include/linux/wmi.h b/include/linux/wmi.h
index 207544968268..8a643c39fcce 100644
--- a/include/linux/wmi.h
+++ b/include/linux/wmi.h
@@ -27,6 +27,14 @@ struct wmi_device {
 	bool setable;
 };
 
+/**
+ * to_wmi_device() - Helper macro to cast a device to a wmi_device
+ * @device: device struct
+ *
+ * Cast a struct device to a struct wmi_device.
+ */
+#define to_wmi_device(device)	container_of(device, struct wmi_device, dev)
+
 extern acpi_status wmidev_evaluate_method(struct wmi_device *wdev,
 					  u8 instance, u32 method_id,
 					  const struct acpi_buffer *in,
-- 
cgit v1.2.3


From bd721b934323e4dcde892013a97e0e5674f4c884 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Mon, 6 Nov 2023 17:09:01 +0100
Subject: ACPI: scan: Extract CSI-2 connection graph from _CRS

Find ACPI CSI-2 resource descriptors defined since ACPI 6.4 (for
CSI-2 and camera configuration) in _CRS for all device objects in
the given scope of the ACPI namespace that have them, identify the
corresponding "remote endpoint" device objects for them and
allocate memory for software nodes needed to create a DT-like data
structure representing the CSI-2 connection graph for drivers.

The code needed to populate these software nodes will be added by
subsequent change sets.

Link: https://uefi.org/specs/ACPI/6.5/06_Device_Configuration.html#camera-serial-interface-csi-2-connection-resource-descriptor
Co-developed-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Tested-by: Sakari Ailus <sakari.ailus@linux.intel.com>
---
 drivers/acpi/Makefile         |   2 +-
 drivers/acpi/internal.h       |   8 ++
 drivers/acpi/mipi-disco-img.c | 292 ++++++++++++++++++++++++++++++++++++++++++
 drivers/acpi/scan.c           |  48 +++++--
 include/acpi/acpi_bus.h       |  18 +++
 5 files changed, 358 insertions(+), 10 deletions(-)
 create mode 100644 drivers/acpi/mipi-disco-img.c

(limited to 'include')

diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index eaa09bf52f17..d367e649714f 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -37,7 +37,7 @@ acpi-$(CONFIG_ACPI_SLEEP)	+= proc.o
 # ACPI Bus and Device Drivers
 #
 acpi-y				+= bus.o glue.o
-acpi-y				+= scan.o
+acpi-y				+= scan.o mipi-disco-img.o
 acpi-y				+= resource.o
 acpi-y				+= acpi_processor.o
 acpi-y				+= processor_core.o
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 866c7c4ed233..959a2bc61916 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -276,4 +276,12 @@ void acpi_init_lpit(void);
 static inline void acpi_init_lpit(void) { }
 #endif
 
+/*--------------------------------------------------------------------------
+		ACPI _CRS CSI-2 and MIPI DisCo for Imaging
+  -------------------------------------------------------------------------- */
+
+void acpi_mipi_check_crs_csi2(acpi_handle handle);
+void acpi_mipi_scan_crs_csi2(void);
+void acpi_mipi_crs_csi2_cleanup(void);
+
 #endif /* _ACPI_INTERNAL_H_ */
diff --git a/drivers/acpi/mipi-disco-img.c b/drivers/acpi/mipi-disco-img.c
new file mode 100644
index 000000000000..91281c8cb4f2
--- /dev/null
+++ b/drivers/acpi/mipi-disco-img.c
@@ -0,0 +1,292 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * MIPI DisCo for Imaging support.
+ *
+ * Copyright (C) 2023 Intel Corporation
+ *
+ * Support MIPI DisCo for Imaging by parsing ACPI _CRS CSI-2 records defined in
+ * Section 6.4.3.8.2.4 "Camera Serial Interface (CSI-2) Connection Resource
+ * Descriptor" of ACPI 6.5.
+ *
+ * The implementation looks for the information in the ACPI namespace (CSI-2
+ * resource descriptors in _CRS) and constructs software nodes compatible with
+ * Documentation/firmware-guide/acpi/dsd/graph.rst to represent the CSI-2
+ * connection graph.
+ */
+
+#include <linux/acpi.h>
+#include <linux/limits.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/overflow.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+
+#include "internal.h"
+
+static LIST_HEAD(acpi_mipi_crs_csi2_list);
+
+static void acpi_mipi_data_tag(acpi_handle handle, void *context)
+{
+}
+
+/* Connection data extracted from one _CRS CSI-2 resource descriptor. */
+struct crs_csi2_connection {
+	struct list_head entry;
+	struct acpi_resource_csi2_serialbus csi2_data;
+	acpi_handle remote_handle;
+	char remote_name[];
+};
+
+/* Data extracted from _CRS CSI-2 resource descriptors for one device. */
+struct crs_csi2 {
+	struct list_head entry;
+	acpi_handle handle;
+	struct acpi_device_software_nodes *swnodes;
+	struct list_head connections;
+	u32 port_count;
+};
+
+struct csi2_resources_walk_data {
+	acpi_handle handle;
+	struct list_head connections;
+};
+
+static acpi_status parse_csi2_resource(struct acpi_resource *res, void *context)
+{
+	struct csi2_resources_walk_data *crwd = context;
+	struct acpi_resource_csi2_serialbus *csi2_res;
+	struct acpi_resource_source *csi2_res_src;
+	u16 csi2_res_src_length;
+	struct crs_csi2_connection *conn;
+	acpi_handle remote_handle;
+
+	if (res->type != ACPI_RESOURCE_TYPE_SERIAL_BUS)
+		return AE_OK;
+
+	csi2_res = &res->data.csi2_serial_bus;
+
+	if (csi2_res->type != ACPI_RESOURCE_SERIAL_TYPE_CSI2)
+		return AE_OK;
+
+	csi2_res_src = &csi2_res->resource_source;
+	if (ACPI_FAILURE(acpi_get_handle(NULL, csi2_res_src->string_ptr,
+					 &remote_handle))) {
+		acpi_handle_debug(crwd->handle,
+				  "unable to find resource source\n");
+		return AE_OK;
+	}
+	csi2_res_src_length = csi2_res_src->string_length;
+	if (!csi2_res_src_length) {
+		acpi_handle_debug(crwd->handle,
+				  "invalid resource source string length\n");
+		return AE_OK;
+	}
+
+	conn = kmalloc(struct_size(conn, remote_name, csi2_res_src_length + 1),
+		       GFP_KERNEL);
+	if (!conn)
+		return AE_OK;
+
+	conn->csi2_data = *csi2_res;
+	strscpy(conn->remote_name, csi2_res_src->string_ptr, csi2_res_src_length);
+	conn->csi2_data.resource_source.string_ptr = conn->remote_name;
+	conn->remote_handle = remote_handle;
+
+	list_add(&conn->entry, &crwd->connections);
+
+	return AE_OK;
+}
+
+static struct crs_csi2 *acpi_mipi_add_crs_csi2(acpi_handle handle,
+					       struct list_head *list)
+{
+	struct crs_csi2 *csi2;
+
+	csi2 = kzalloc(sizeof(*csi2), GFP_KERNEL);
+	if (!csi2)
+		return NULL;
+
+	csi2->handle = handle;
+	INIT_LIST_HEAD(&csi2->connections);
+	csi2->port_count = 1;
+
+	if (ACPI_FAILURE(acpi_attach_data(handle, acpi_mipi_data_tag, csi2))) {
+		kfree(csi2);
+		return NULL;
+	}
+
+	list_add(&csi2->entry, list);
+
+	return csi2;
+}
+
+static struct crs_csi2 *acpi_mipi_get_crs_csi2(acpi_handle handle)
+{
+	struct crs_csi2 *csi2;
+
+	if (ACPI_FAILURE(acpi_get_data_full(handle, acpi_mipi_data_tag,
+					    (void **)&csi2, NULL)))
+		return NULL;
+
+	return csi2;
+}
+
+static void csi_csr2_release_connections(struct list_head *list)
+{
+	struct crs_csi2_connection *conn, *conn_tmp;
+
+	list_for_each_entry_safe(conn, conn_tmp, list, entry) {
+		list_del(&conn->entry);
+		kfree(conn);
+	}
+}
+
+static void acpi_mipi_del_crs_csi2(struct crs_csi2 *csi2)
+{
+	list_del(&csi2->entry);
+	acpi_detach_data(csi2->handle, acpi_mipi_data_tag);
+	kfree(csi2->swnodes);
+	csi_csr2_release_connections(&csi2->connections);
+	kfree(csi2);
+}
+
+/**
+ * acpi_mipi_check_crs_csi2 - Look for CSI-2 resources in _CRS
+ * @handle: Device object handle to evaluate _CRS for.
+ *
+ * Find all CSI-2 resource descriptors in the given device's _CRS
+ * and collect them into a list.
+ */
+void acpi_mipi_check_crs_csi2(acpi_handle handle)
+{
+	struct csi2_resources_walk_data crwd = {
+		.handle = handle,
+		.connections = LIST_HEAD_INIT(crwd.connections),
+	};
+	struct crs_csi2 *csi2;
+
+	/*
+	 * Avoid allocating _CRS CSI-2 objects for devices without any CSI-2
+	 * resource descriptions in _CRS to reduce overhead.
+	 */
+	acpi_walk_resources(handle, METHOD_NAME__CRS, parse_csi2_resource, &crwd);
+	if (list_empty(&crwd.connections))
+		return;
+
+	/*
+	 * Create a _CRS CSI-2 entry to store the extracted connection
+	 * information and add it to the global list.
+	 */
+	csi2 = acpi_mipi_add_crs_csi2(handle, &acpi_mipi_crs_csi2_list);
+	if (!csi2) {
+		csi_csr2_release_connections(&crwd.connections);
+		return; /* Nothing really can be done about this. */
+	}
+
+	list_replace(&crwd.connections, &csi2->connections);
+}
+
+#define NO_CSI2_PORT (UINT_MAX - 1)
+
+static void alloc_crs_csi2_swnodes(struct crs_csi2 *csi2)
+{
+	size_t port_count = csi2->port_count;
+	struct acpi_device_software_nodes *swnodes;
+	size_t alloc_size;
+	unsigned int i;
+
+	/*
+	 * Allocate memory for ports, node pointers (number of nodes +
+	 * 1 (guardian), nodes (root + number of ports * 2 (because for
+	 * every port there is an endpoint)).
+	 */
+	if (check_mul_overflow(sizeof(*swnodes->ports) +
+			       sizeof(*swnodes->nodes) * 2 +
+			       sizeof(*swnodes->nodeptrs) * 2,
+			       port_count, &alloc_size) ||
+	    check_add_overflow(sizeof(*swnodes) +
+			       sizeof(*swnodes->nodes) +
+			       sizeof(*swnodes->nodeptrs) * 2,
+			       alloc_size, &alloc_size)) {
+		acpi_handle_info(csi2->handle,
+				 "too many _CRS CSI-2 resource handles (%zu)",
+				 port_count);
+		return;
+	}
+
+	swnodes = kmalloc(alloc_size, GFP_KERNEL);
+	if (!swnodes)
+		return;
+
+	swnodes->ports = (struct acpi_device_software_node_port *)(swnodes + 1);
+	swnodes->nodes = (struct software_node *)(swnodes->ports + port_count);
+	swnodes->nodeptrs = (const struct software_node **)(swnodes->nodes + 1 +
+				2 * port_count);
+	swnodes->num_ports = port_count;
+
+	for (i = 0; i < 2 * port_count + 1; i++)
+		swnodes->nodeptrs[i] = &swnodes->nodes[i];
+
+	swnodes->nodeptrs[i] = NULL;
+
+	for (i = 0; i < port_count; i++)
+		swnodes->ports[i].port_nr = NO_CSI2_PORT;
+
+	csi2->swnodes = swnodes;
+}
+
+/**
+ * acpi_mipi_scan_crs_csi2 - Create ACPI _CRS CSI-2 software nodes
+ *
+ * Note that this function must be called before any struct acpi_device objects
+ * are bound to any ACPI drivers or scan handlers, so it cannot assume the
+ * existence of struct acpi_device objects for every device present in the ACPI
+ * namespace.
+ *
+ * acpi_scan_lock in scan.c must be held when calling this function.
+ */
+void acpi_mipi_scan_crs_csi2(void)
+{
+	struct crs_csi2 *csi2;
+	LIST_HEAD(aux_list);
+
+	/* Count references to each ACPI handle in the CSI-2 connection graph. */
+	list_for_each_entry(csi2, &acpi_mipi_crs_csi2_list, entry) {
+		struct crs_csi2_connection *conn;
+
+		list_for_each_entry(conn, &csi2->connections, entry) {
+			struct crs_csi2 *remote_csi2;
+
+			csi2->port_count++;
+
+			remote_csi2 = acpi_mipi_get_crs_csi2(conn->remote_handle);
+			if (remote_csi2) {
+				remote_csi2->port_count++;
+				continue;
+			}
+			/*
+			 * The remote endpoint has no _CRS CSI-2 list entry yet,
+			 * so create one for it and add it to the list.
+			 */
+			acpi_mipi_add_crs_csi2(conn->remote_handle, &aux_list);
+		}
+	}
+	list_splice(&aux_list, &acpi_mipi_crs_csi2_list);
+
+	/* Allocate software nodes for representing the CSI-2 information. */
+	list_for_each_entry(csi2, &acpi_mipi_crs_csi2_list, entry)
+		alloc_crs_csi2_swnodes(csi2);
+}
+
+/**
+ * acpi_mipi_crs_csi2_cleanup - Free _CRS CSI-2 temporary data
+ */
+void acpi_mipi_crs_csi2_cleanup(void)
+{
+	struct crs_csi2 *csi2, *csi2_tmp;
+
+	list_for_each_entry_safe(csi2, csi2_tmp, &acpi_mipi_crs_csi2_list, entry)
+		acpi_mipi_del_crs_csi2(csi2);
+}
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index fa5dd71a80fa..8e12c558b8db 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1976,7 +1976,7 @@ static void acpi_scan_init_hotplug(struct acpi_device *adev)
 	}
 }
 
-static u32 acpi_scan_check_dep(acpi_handle handle, bool check_dep)
+static u32 acpi_scan_check_dep(acpi_handle handle)
 {
 	struct acpi_handle_list dep_devices;
 	acpi_status status;
@@ -1989,8 +1989,7 @@ static u32 acpi_scan_check_dep(acpi_handle handle, bool check_dep)
 	 * 2. ACPI nodes describing USB ports.
 	 * Still, checking for _HID catches more then just these cases ...
 	 */
-	if (!check_dep || !acpi_has_method(handle, "_DEP") ||
-	    !acpi_has_method(handle, "_HID"))
+	if (!acpi_has_method(handle, "_DEP") || !acpi_has_method(handle, "_HID"))
 		return 0;
 
 	status = acpi_evaluate_reference(handle, "_DEP", NULL, &dep_devices);
@@ -2036,7 +2035,13 @@ static u32 acpi_scan_check_dep(acpi_handle handle, bool check_dep)
 	return count;
 }
 
-static acpi_status acpi_bus_check_add(acpi_handle handle, bool check_dep,
+static acpi_status acpi_scan_check_crs_csi2_cb(acpi_handle handle, u32 a, void *b, void **c)
+{
+	acpi_mipi_check_crs_csi2(handle);
+	return AE_OK;
+}
+
+static acpi_status acpi_bus_check_add(acpi_handle handle, bool first_pass,
 				      struct acpi_device **adev_p)
 {
 	struct acpi_device *device = acpi_fetch_acpi_dev(handle);
@@ -2054,9 +2059,25 @@ static acpi_status acpi_bus_check_add(acpi_handle handle, bool check_dep,
 		if (acpi_device_should_be_hidden(handle))
 			return AE_OK;
 
-		/* Bail out if there are dependencies. */
-		if (acpi_scan_check_dep(handle, check_dep) > 0)
-			return AE_CTRL_DEPTH;
+		if (first_pass) {
+			acpi_mipi_check_crs_csi2(handle);
+
+			/* Bail out if there are dependencies. */
+			if (acpi_scan_check_dep(handle) > 0) {
+				/*
+				 * The entire CSI-2 connection graph needs to be
+				 * extracted before any drivers or scan handlers
+				 * are bound to struct device objects, so scan
+				 * _CRS CSI-2 resource descriptors for all
+				 * devices below the current handle.
+				 */
+				acpi_walk_namespace(ACPI_TYPE_DEVICE, handle,
+						    ACPI_UINT32_MAX,
+						    acpi_scan_check_crs_csi2_cb,
+						    NULL, NULL, NULL);
+				return AE_CTRL_DEPTH;
+			}
+		}
 
 		fallthrough;
 	case ACPI_TYPE_ANY:	/* for ACPI_ROOT_OBJECT */
@@ -2079,10 +2100,10 @@ static acpi_status acpi_bus_check_add(acpi_handle handle, bool check_dep,
 	}
 
 	/*
-	 * If check_dep is true at this point, the device has no dependencies,
+	 * If first_pass is true at this point, the device has no dependencies,
 	 * or the creation of the device object would have been postponed above.
 	 */
-	acpi_add_single_object(&device, handle, type, !check_dep);
+	acpi_add_single_object(&device, handle, type, !first_pass);
 	if (!device)
 		return AE_CTRL_DEPTH;
 
@@ -2494,12 +2515,21 @@ int acpi_bus_scan(acpi_handle handle)
 	if (!device)
 		return -ENODEV;
 
+	/*
+	 * Allocate ACPI _CRS CSI-2 software nodes using information extracted
+	 * from the _CRS CSI-2 resource descriptors during the ACPI namespace
+	 * walk above.
+	 */
+	acpi_mipi_scan_crs_csi2();
+
 	acpi_bus_attach(device, (void *)true);
 
 	/* Pass 2: Enumerate all of the remaining devices. */
 
 	acpi_scan_postponed();
 
+	acpi_mipi_crs_csi2_cleanup();
+
 	return 0;
 }
 EXPORT_SYMBOL(acpi_bus_scan);
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index afeed6e72049..f122fa1c10a8 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -366,6 +366,24 @@ struct acpi_device_data {
 
 struct acpi_gpio_mapping;
 
+struct acpi_device_software_node_port {
+	unsigned int port_nr;
+};
+
+/**
+ * struct acpi_device_software_nodes - Software nodes for an ACPI device
+ * @nodes: Software nodes for root as well as ports and endpoints.
+ * @nodeprts: Array of software node pointers, for (un)registering them.
+ * @ports: Information related to each port and endpoint within a port.
+ * @num_ports: The number of ports.
+ */
+struct acpi_device_software_nodes {
+	struct software_node *nodes;
+	const struct software_node **nodeptrs;
+	struct acpi_device_software_node_port *ports;
+	unsigned int num_ports;
+};
+
 /* Device */
 struct acpi_device {
 	u32 pld_crc;
-- 
cgit v1.2.3


From 693c667b32ee1dd312000d4656b3383fffb3af2d Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Mon, 6 Nov 2023 17:16:26 +0100
Subject: ACPI: scan: Extract _CRS CSI-2 connection information into swnodes

Use the connection information extracted from the _CRS CSI-2 resource
descriptors for all devices that have them to populate port names and the
"reg", "bus-type" and "remote-endpoint" properties in the software nodes
representing the CSI-2 connection graph.

Link: https://uefi.org/specs/ACPI/6.5/06_Device_Configuration.html#camera-serial-interface-csi-2-connection-resource-descriptor
Co-developed-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Tested-by: Sakari Ailus <sakari.ailus@linux.intel.com>
---
 drivers/acpi/mipi-disco-img.c | 153 +++++++++++++++++++++++++++++++++++++++++-
 include/acpi/acpi_bus.h       |  53 +++++++++++++++
 2 files changed, 205 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/acpi/mipi-disco-img.c b/drivers/acpi/mipi-disco-img.c
index 91281c8cb4f2..5ff72d83fad2 100644
--- a/drivers/acpi/mipi-disco-img.c
+++ b/drivers/acpi/mipi-disco-img.c
@@ -23,6 +23,8 @@
 #include <linux/slab.h>
 #include <linux/string.h>
 
+#include <media/v4l2-fwnode.h>
+
 #include "internal.h"
 
 static LIST_HEAD(acpi_mipi_crs_csi2_list);
@@ -237,6 +239,142 @@ static void alloc_crs_csi2_swnodes(struct crs_csi2 *csi2)
 	csi2->swnodes = swnodes;
 }
 
+#define ACPI_CRS_CSI2_PHY_TYPE_C	0
+#define ACPI_CRS_CSI2_PHY_TYPE_D	1
+
+static unsigned int next_csi2_port_index(struct acpi_device_software_nodes *swnodes,
+					 unsigned int port_nr)
+{
+	unsigned int i;
+
+	for (i = 0; i < swnodes->num_ports; i++) {
+		struct acpi_device_software_node_port *port = &swnodes->ports[i];
+
+		if (port->port_nr == port_nr)
+			return i;
+
+		if (port->port_nr == NO_CSI2_PORT) {
+			port->port_nr = port_nr;
+			return i;
+		}
+	}
+
+	return NO_CSI2_PORT;
+}
+
+/* Print graph port name into a buffer, return non-zero on failure. */
+#define GRAPH_PORT_NAME(var, num)					    \
+	(snprintf((var), sizeof(var), SWNODE_GRAPH_PORT_NAME_FMT, (num)) >= \
+	 sizeof(var))
+
+static void extract_crs_csi2_conn_info(acpi_handle local_handle,
+				       struct acpi_device_software_nodes *local_swnodes,
+				       struct crs_csi2_connection *conn)
+{
+	struct crs_csi2 *remote_csi2 = acpi_mipi_get_crs_csi2(conn->remote_handle);
+	struct acpi_device_software_nodes *remote_swnodes;
+	struct acpi_device_software_node_port *local_port, *remote_port;
+	struct software_node *local_node, *remote_node;
+	unsigned int local_index, remote_index;
+	unsigned int bus_type;
+
+	/*
+	 * If the previous steps have failed to make room for a _CRS CSI-2
+	 * representation for the remote end of the given connection, skip it.
+	 */
+	if (!remote_csi2)
+		return;
+
+	remote_swnodes = remote_csi2->swnodes;
+	if (!remote_swnodes)
+		return;
+
+	switch (conn->csi2_data.phy_type) {
+	case ACPI_CRS_CSI2_PHY_TYPE_C:
+		bus_type = V4L2_FWNODE_BUS_TYPE_CSI2_CPHY;
+		break;
+
+	case ACPI_CRS_CSI2_PHY_TYPE_D:
+		bus_type = V4L2_FWNODE_BUS_TYPE_CSI2_DPHY;
+		break;
+
+	default:
+		acpi_handle_info(local_handle, "unknown CSI-2 PHY type %u\n",
+				 conn->csi2_data.phy_type);
+		return;
+	}
+
+	local_index = next_csi2_port_index(local_swnodes,
+					   conn->csi2_data.local_port_instance);
+	if (WARN_ON_ONCE(local_index >= local_swnodes->num_ports))
+		return;
+
+	remote_index = next_csi2_port_index(remote_swnodes,
+					    conn->csi2_data.resource_source.index);
+	if (WARN_ON_ONCE(remote_index >= remote_swnodes->num_ports))
+		return;
+
+	local_port = &local_swnodes->ports[local_index];
+	local_node = &local_swnodes->nodes[ACPI_DEVICE_SWNODE_EP(local_index)];
+	local_port->crs_csi2_local = true;
+
+	remote_port = &remote_swnodes->ports[remote_index];
+	remote_node = &remote_swnodes->nodes[ACPI_DEVICE_SWNODE_EP(remote_index)];
+
+	local_port->remote_ep[0] = SOFTWARE_NODE_REFERENCE(remote_node);
+	remote_port->remote_ep[0] = SOFTWARE_NODE_REFERENCE(local_node);
+
+	local_port->ep_props[ACPI_DEVICE_SWNODE_EP_REMOTE_EP] =
+			PROPERTY_ENTRY_REF_ARRAY("remote-endpoint",
+						 local_port->remote_ep);
+
+	local_port->ep_props[ACPI_DEVICE_SWNODE_EP_BUS_TYPE] =
+			PROPERTY_ENTRY_U32("bus-type", bus_type);
+
+	local_port->ep_props[ACPI_DEVICE_SWNODE_EP_REG] =
+			PROPERTY_ENTRY_U32("reg", 0);
+
+	local_port->port_props[ACPI_DEVICE_SWNODE_PORT_REG] =
+			PROPERTY_ENTRY_U32("reg", conn->csi2_data.local_port_instance);
+
+	if (GRAPH_PORT_NAME(local_port->port_name,
+			    conn->csi2_data.local_port_instance))
+		acpi_handle_info(local_handle, "local port %u name too long",
+				 conn->csi2_data.local_port_instance);
+
+	remote_port->ep_props[ACPI_DEVICE_SWNODE_EP_REMOTE_EP] =
+			PROPERTY_ENTRY_REF_ARRAY("remote-endpoint",
+						 remote_port->remote_ep);
+
+	remote_port->ep_props[ACPI_DEVICE_SWNODE_EP_BUS_TYPE] =
+			PROPERTY_ENTRY_U32("bus-type", bus_type);
+
+	remote_port->ep_props[ACPI_DEVICE_SWNODE_EP_REG] =
+			PROPERTY_ENTRY_U32("reg", 0);
+
+	remote_port->port_props[ACPI_DEVICE_SWNODE_PORT_REG] =
+			PROPERTY_ENTRY_U32("reg", conn->csi2_data.resource_source.index);
+
+	if (GRAPH_PORT_NAME(remote_port->port_name,
+			    conn->csi2_data.resource_source.index))
+		acpi_handle_info(local_handle, "remote port %u name too long",
+				 conn->csi2_data.resource_source.index);
+}
+
+static void prepare_crs_csi2_swnodes(struct crs_csi2 *csi2)
+{
+	struct acpi_device_software_nodes *local_swnodes = csi2->swnodes;
+	acpi_handle local_handle = csi2->handle;
+	struct crs_csi2_connection *conn;
+
+	/* Bail out if the allocation of swnodes has failed. */
+	if (!local_swnodes)
+		return;
+
+	list_for_each_entry(conn, &csi2->connections, entry)
+		extract_crs_csi2_conn_info(local_handle, local_swnodes, conn);
+}
+
 /**
  * acpi_mipi_scan_crs_csi2 - Create ACPI _CRS CSI-2 software nodes
  *
@@ -275,9 +413,22 @@ void acpi_mipi_scan_crs_csi2(void)
 	}
 	list_splice(&aux_list, &acpi_mipi_crs_csi2_list);
 
-	/* Allocate software nodes for representing the CSI-2 information. */
+	/*
+	 * Allocate software nodes for representing the CSI-2 information.
+	 *
+	 * This needs to be done for all of the list entries in one go, because
+	 * they may point to each other without restrictions and the next step
+	 * relies on the availability of swnodes memory for each list entry.
+	 */
 	list_for_each_entry(csi2, &acpi_mipi_crs_csi2_list, entry)
 		alloc_crs_csi2_swnodes(csi2);
+
+	/*
+	 * Set up software node properties using data from _CRS CSI-2 resource
+	 * descriptors.
+	 */
+	list_for_each_entry(csi2, &acpi_mipi_crs_csi2_list, entry)
+		prepare_crs_csi2_swnodes(csi2);
 }
 
 /**
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index f122fa1c10a8..a7fa24f1af46 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -366,8 +366,61 @@ struct acpi_device_data {
 
 struct acpi_gpio_mapping;
 
+#define ACPI_DEVICE_CSI2_DATA_LANES		8
+
+#define ACPI_DEVICE_SWNODE_PORT_NAME_LENGTH	8
+
+enum acpi_device_swnode_port_props {
+	ACPI_DEVICE_SWNODE_PORT_REG,
+	ACPI_DEVICE_SWNODE_PORT_NUM_OF,
+	ACPI_DEVICE_SWNODE_PORT_NUM_ENTRIES
+};
+
+enum acpi_device_swnode_ep_props {
+	ACPI_DEVICE_SWNODE_EP_REMOTE_EP,
+	ACPI_DEVICE_SWNODE_EP_BUS_TYPE,
+	ACPI_DEVICE_SWNODE_EP_REG,
+	ACPI_DEVICE_SWNODE_EP_CLOCK_LANES,
+	ACPI_DEVICE_SWNODE_EP_DATA_LANES,
+	ACPI_DEVICE_SWNODE_EP_LANE_POLARITIES,
+	/* TX only */
+	ACPI_DEVICE_SWNODE_EP_LINK_FREQUENCIES,
+	ACPI_DEVICE_SWNODE_EP_NUM_OF,
+	ACPI_DEVICE_SWNODE_EP_NUM_ENTRIES
+};
+
+/*
+ * Each device has a root software node plus two times as many nodes as the
+ * number of CSI-2 ports.
+ */
+#define ACPI_DEVICE_SWNODE_PORT(port)	(2 * (port) + 1)
+#define ACPI_DEVICE_SWNODE_EP(endpoint)	\
+		(ACPI_DEVICE_SWNODE_PORT(endpoint) + 1)
+
+/**
+ * struct acpi_device_software_node_port - MIPI DisCo for Imaging CSI-2 port
+ * @port_name: Port name.
+ * @data_lanes: "data-lanes" property values.
+ * @lane_polarities: "lane-polarities" property values.
+ * @link_frequencies: "link_frequencies" property values.
+ * @port_nr: Port number.
+ * @crs_crs2_local: _CRS CSI2 record present (i.e. this is a transmitter one).
+ * @port_props: Port properties.
+ * @ep_props: Endpoint properties.
+ * @remote_ep: Reference to the remote endpoint.
+ */
 struct acpi_device_software_node_port {
+	char port_name[ACPI_DEVICE_SWNODE_PORT_NAME_LENGTH + 1];
+	u32 data_lanes[ACPI_DEVICE_CSI2_DATA_LANES];
+	u32 lane_polarities[ACPI_DEVICE_CSI2_DATA_LANES + 1 /* clock lane */];
+	u64 link_frequencies[ACPI_DEVICE_CSI2_DATA_LANES];
 	unsigned int port_nr;
+	bool crs_csi2_local;
+
+	struct property_entry port_props[ACPI_DEVICE_SWNODE_PORT_NUM_ENTRIES];
+	struct property_entry ep_props[ACPI_DEVICE_SWNODE_EP_NUM_ENTRIES];
+
+	struct software_node_ref_args remote_ep[1];
 };
 
 /**
-- 
cgit v1.2.3


From 48c9996f1dfe92bd7318472651c9ad538d6d53b5 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Mon, 6 Nov 2023 17:16:37 +0100
Subject: device property: Add SOFTWARE_NODE() macro for defining software
 nodes

Add SOFTWARE_NODE() macro in order to make defining software nodes look
nicer. This is analogous to different PROPERTY_ENTRY_*() macros for
defining properties.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Tested-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/property.h | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/linux/property.h b/include/linux/property.h
index 9f2585d705a8..97f901c0914e 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -489,6 +489,13 @@ struct software_node {
 	const struct property_entry *properties;
 };
 
+#define SOFTWARE_NODE(_name_, _properties_, _parent_)	\
+	(struct software_node) {			\
+		.name = _name_,				\
+		.properties = _properties_,		\
+		.parent = _parent_,			\
+	}
+
 bool is_software_node(const struct fwnode_handle *fwnode);
 const struct software_node *
 to_software_node(const struct fwnode_handle *fwnode);
-- 
cgit v1.2.3


From a6cb0a611273767683d50fb908173b6f88052ce5 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Tue, 7 Nov 2023 20:19:42 +0100
Subject: ACPI: scan: Extract MIPI DisCo for Imaging data into swnodes

Add information extracted from the MIPI DisCo for Imaging device
properties to software nodes created during the CSI-2 connection graph
discovery.

Link: https://www.mipi.org/specifications/mipi-disco-imaging
Co-developed-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Tested-by: Sakari Ailus <sakari.ailus@linux.intel.com>
---
 drivers/acpi/internal.h       |   1 +
 drivers/acpi/mipi-disco-img.c | 252 +++++++++++++++++++++++++++++++++++++++++-
 drivers/acpi/scan.c           |  12 +-
 include/acpi/acpi_bus.h       |  17 +++
 4 files changed, 278 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 959a2bc61916..86b670637f2f 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -282,6 +282,7 @@ static inline void acpi_init_lpit(void) { }
 
 void acpi_mipi_check_crs_csi2(acpi_handle handle);
 void acpi_mipi_scan_crs_csi2(void);
+void acpi_mipi_init_crs_csi2_swnodes(void);
 void acpi_mipi_crs_csi2_cleanup(void);
 
 #endif /* _ACPI_INTERNAL_H_ */
diff --git a/drivers/acpi/mipi-disco-img.c b/drivers/acpi/mipi-disco-img.c
index 5ff72d83fad2..dcbaba91d4fe 100644
--- a/drivers/acpi/mipi-disco-img.c
+++ b/drivers/acpi/mipi-disco-img.c
@@ -6,12 +6,16 @@
  *
  * Support MIPI DisCo for Imaging by parsing ACPI _CRS CSI-2 records defined in
  * Section 6.4.3.8.2.4 "Camera Serial Interface (CSI-2) Connection Resource
- * Descriptor" of ACPI 6.5.
+ * Descriptor" of ACPI 6.5 and using device properties defined by the MIPI DisCo
+ * for Imaging specification.
  *
  * The implementation looks for the information in the ACPI namespace (CSI-2
  * resource descriptors in _CRS) and constructs software nodes compatible with
  * Documentation/firmware-guide/acpi/dsd/graph.rst to represent the CSI-2
- * connection graph.
+ * connection graph.  The software nodes are then populated with the data
+ * extracted from the _CRS CSI-2 resource descriptors and the MIPI DisCo
+ * for Imaging device properties present in _DSD for the ACPI device objects
+ * with CSI-2 connections.
  */
 
 #include <linux/acpi.h>
@@ -431,6 +435,250 @@ void acpi_mipi_scan_crs_csi2(void)
 		prepare_crs_csi2_swnodes(csi2);
 }
 
+/*
+ * Get the index of the next property in the property array, with a given
+ * maximum value.
+ */
+#define NEXT_PROPERTY(index, max)			\
+	(WARN_ON((index) > ACPI_DEVICE_SWNODE_##max) ?	\
+	 ACPI_DEVICE_SWNODE_##max : (index)++)
+
+static void init_csi2_port_local(struct acpi_device *adev,
+				 struct acpi_device_software_node_port *port,
+				 struct fwnode_handle *port_fwnode,
+				 unsigned int index)
+{
+	acpi_handle handle = acpi_device_handle(adev);
+	unsigned int num_link_freqs;
+	int ret;
+
+	ret = fwnode_property_count_u64(port_fwnode, "mipi-img-link-frequencies");
+	if (ret <= 0)
+		return;
+
+	num_link_freqs = ret;
+	if (num_link_freqs > ACPI_DEVICE_CSI2_DATA_LANES) {
+		acpi_handle_info(handle, "Too many link frequencies: %u\n",
+				 num_link_freqs);
+		num_link_freqs = ACPI_DEVICE_CSI2_DATA_LANES;
+	}
+
+	ret = fwnode_property_read_u64_array(port_fwnode,
+					     "mipi-img-link-frequencies",
+					     port->link_frequencies,
+					     num_link_freqs);
+	if (ret) {
+		acpi_handle_info(handle, "Unable to get link frequencies (%d)\n",
+				 ret);
+		return;
+	}
+
+	port->ep_props[NEXT_PROPERTY(index, EP_LINK_FREQUENCIES)] =
+				PROPERTY_ENTRY_U64_ARRAY_LEN("link-frequencies",
+							     port->link_frequencies,
+							     num_link_freqs);
+}
+
+static void init_csi2_port(struct acpi_device *adev,
+			   struct acpi_device_software_nodes *swnodes,
+			   struct acpi_device_software_node_port *port,
+			   struct fwnode_handle *port_fwnode,
+			   unsigned int port_index)
+{
+	unsigned int ep_prop_index = ACPI_DEVICE_SWNODE_EP_CLOCK_LANES;
+	acpi_handle handle = acpi_device_handle(adev);
+	u8 val[ACPI_DEVICE_CSI2_DATA_LANES];
+	int num_lanes = 0;
+	int ret;
+
+	if (GRAPH_PORT_NAME(port->port_name, port->port_nr))
+		return;
+
+	swnodes->nodes[ACPI_DEVICE_SWNODE_PORT(port_index)] =
+			SOFTWARE_NODE(port->port_name, port->port_props,
+				      &swnodes->nodes[ACPI_DEVICE_SWNODE_ROOT]);
+
+	ret = fwnode_property_read_u8(port_fwnode, "mipi-img-clock-lane", val);
+	if (!ret)
+		port->ep_props[NEXT_PROPERTY(ep_prop_index, EP_CLOCK_LANES)] =
+			PROPERTY_ENTRY_U32("clock-lanes", val[0]);
+
+	ret = fwnode_property_count_u8(port_fwnode, "mipi-img-data-lanes");
+	if (ret > 0) {
+		num_lanes = ret;
+
+		if (num_lanes > ACPI_DEVICE_CSI2_DATA_LANES) {
+			acpi_handle_info(handle, "Too many data lanes: %u\n",
+					 num_lanes);
+			num_lanes = ACPI_DEVICE_CSI2_DATA_LANES;
+		}
+
+		ret = fwnode_property_read_u8_array(port_fwnode,
+						    "mipi-img-data-lanes",
+						    val, num_lanes);
+		if (!ret) {
+			unsigned int i;
+
+			for (i = 0; i < num_lanes; i++)
+				port->data_lanes[i] = val[i];
+
+			port->ep_props[NEXT_PROPERTY(ep_prop_index, EP_DATA_LANES)] =
+				PROPERTY_ENTRY_U32_ARRAY_LEN("data-lanes",
+							     port->data_lanes,
+							     num_lanes);
+		}
+	}
+
+	ret = fwnode_property_count_u8(port_fwnode, "mipi-img-lane-polarities");
+	if (ret < 0) {
+		acpi_handle_debug(handle, "Lane polarity bytes missing\n");
+	} else if (ret * BITS_PER_TYPE(u8) < num_lanes + 1) {
+		acpi_handle_info(handle, "Too few lane polarity bytes (%lu vs. %d)\n",
+				 ret * BITS_PER_TYPE(u8), num_lanes + 1);
+	} else {
+		unsigned long mask = 0;
+		int byte_count = ret;
+		unsigned int i;
+
+		/*
+		 * The total number of lanes is ACPI_DEVICE_CSI2_DATA_LANES + 1
+		 * (data lanes + clock lane).  It is not expected to ever be
+		 * greater than the number of bits in an unsigned long
+		 * variable, but ensure that this is the case.
+		 */
+		BUILD_BUG_ON(BITS_PER_TYPE(unsigned long) <= ACPI_DEVICE_CSI2_DATA_LANES);
+
+		if (byte_count > sizeof(mask)) {
+			acpi_handle_info(handle, "Too many lane polarities: %d\n",
+					 byte_count);
+			byte_count = sizeof(mask);
+		}
+		fwnode_property_read_u8_array(port_fwnode, "mipi-img-lane-polarities",
+					      val, byte_count);
+
+		for (i = 0; i < byte_count; i++)
+			mask |= (unsigned long)val[i] << BITS_PER_TYPE(u8) * i;
+
+		for (i = 0; i <= num_lanes; i++)
+			port->lane_polarities[i] = test_bit(i, &mask);
+
+		port->ep_props[NEXT_PROPERTY(ep_prop_index, EP_LANE_POLARITIES)] =
+				PROPERTY_ENTRY_U32_ARRAY_LEN("lane-polarities",
+							     port->lane_polarities,
+							     num_lanes + 1);
+	}
+
+	swnodes->nodes[ACPI_DEVICE_SWNODE_EP(port_index)] =
+		SOFTWARE_NODE("endpoint@0", swnodes->ports[port_index].ep_props,
+			      &swnodes->nodes[ACPI_DEVICE_SWNODE_PORT(port_index)]);
+
+	if (port->crs_csi2_local)
+		init_csi2_port_local(adev, port, port_fwnode, ep_prop_index);
+}
+
+#define MIPI_IMG_PORT_PREFIX "mipi-img-port-"
+
+static struct fwnode_handle *get_mipi_port_handle(struct fwnode_handle *adev_fwnode,
+						  unsigned int port_nr)
+{
+	char port_name[sizeof(MIPI_IMG_PORT_PREFIX) + 2];
+
+	if (snprintf(port_name, sizeof(port_name), "%s%u",
+		     MIPI_IMG_PORT_PREFIX, port_nr) >= sizeof(port_name))
+		return NULL;
+
+	return fwnode_get_named_child_node(adev_fwnode, port_name);
+}
+
+static void init_crs_csi2_swnodes(struct crs_csi2 *csi2)
+{
+	struct acpi_buffer buffer = { .length = ACPI_ALLOCATE_BUFFER };
+	struct acpi_device_software_nodes *swnodes = csi2->swnodes;
+	acpi_handle handle = csi2->handle;
+	struct fwnode_handle *adev_fwnode;
+	struct acpi_device *adev;
+	acpi_status status;
+	unsigned int i;
+	int ret;
+
+	/*
+	 * Bail out if the swnodes are not available (either they have not been
+	 * allocated or they have been assigned to the device already).
+	 */
+	if (!swnodes)
+		return;
+
+	adev = acpi_fetch_acpi_dev(handle);
+	if (!adev)
+		return;
+
+	adev_fwnode = acpi_fwnode_handle(adev);
+
+	status = acpi_get_name(handle, ACPI_FULL_PATHNAME, &buffer);
+	if (ACPI_FAILURE(status)) {
+		acpi_handle_info(handle, "Unable to get the path name\n");
+		return;
+	}
+
+	swnodes->nodes[ACPI_DEVICE_SWNODE_ROOT] =
+			SOFTWARE_NODE(buffer.pointer, swnodes->dev_props, NULL);
+
+	for (i = 0; i < swnodes->num_ports; i++) {
+		struct acpi_device_software_node_port *port = &swnodes->ports[i];
+		struct fwnode_handle *port_fwnode;
+
+		/*
+		 * The MIPI DisCo for Imaging specification defines _DSD device
+		 * properties for providing CSI-2 port parameters that can be
+		 * accessed through the generic device properties framework.  To
+		 * access them, it is first necessary to find the data node
+		 * representing the port under the given ACPI device object.
+		 */
+		port_fwnode = get_mipi_port_handle(adev_fwnode, port->port_nr);
+		if (!port_fwnode) {
+			acpi_handle_info(handle,
+					 "MIPI port name too long for port %u\n",
+					 port->port_nr);
+			continue;
+		}
+
+		init_csi2_port(adev, swnodes, port, port_fwnode, i);
+
+		fwnode_handle_put(port_fwnode);
+	}
+
+	ret = software_node_register_node_group(swnodes->nodeptrs);
+	if (ret < 0) {
+		acpi_handle_info(handle,
+				 "Unable to register software nodes (%d)\n", ret);
+		return;
+	}
+
+	adev->swnodes = swnodes;
+	adev_fwnode->secondary = software_node_fwnode(swnodes->nodes);
+
+	/*
+	 * Prevents the swnodes from this csi2 entry from being assigned again
+	 * or freed prematurely.
+	 */
+	csi2->swnodes = NULL;
+}
+
+/**
+ * acpi_mipi_init_crs_csi2_swnodes - Initialize _CRS CSI-2 software nodes
+ *
+ * Use MIPI DisCo for Imaging device properties to finalize the initialization
+ * of CSI-2 software nodes for all ACPI device objects that have been already
+ * enumerated.
+ */
+void acpi_mipi_init_crs_csi2_swnodes(void)
+{
+	struct crs_csi2 *csi2, *csi2_tmp;
+
+	list_for_each_entry_safe(csi2, csi2_tmp, &acpi_mipi_crs_csi2_list, entry)
+		init_crs_csi2_swnodes(csi2);
+}
+
 /**
  * acpi_mipi_crs_csi2_cleanup - Free _CRS CSI-2 temporary data
  */
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 8e12c558b8db..b8df04779904 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -2447,6 +2447,13 @@ static void acpi_scan_postponed_branch(acpi_handle handle)
 
 	acpi_walk_namespace(ACPI_TYPE_ANY, handle, ACPI_UINT32_MAX,
 			    acpi_bus_check_add_2, NULL, NULL, (void **)&adev);
+
+	/*
+	 * Populate the ACPI _CRS CSI-2 software nodes for the ACPI devices that
+	 * have been added above.
+	 */
+	acpi_mipi_init_crs_csi2_swnodes();
+
 	acpi_bus_attach(adev, NULL);
 }
 
@@ -2516,11 +2523,12 @@ int acpi_bus_scan(acpi_handle handle)
 		return -ENODEV;
 
 	/*
-	 * Allocate ACPI _CRS CSI-2 software nodes using information extracted
+	 * Set up ACPI _CRS CSI-2 software nodes using information extracted
 	 * from the _CRS CSI-2 resource descriptors during the ACPI namespace
-	 * walk above.
+	 * walk above and MIPI DisCo for Imaging device properties.
 	 */
 	acpi_mipi_scan_crs_csi2();
+	acpi_mipi_init_crs_csi2_swnodes();
 
 	acpi_bus_attach(device, (void *)true);
 
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index a7fa24f1af46..c299fb974e49 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -366,10 +366,24 @@ struct acpi_device_data {
 
 struct acpi_gpio_mapping;
 
+#define ACPI_DEVICE_SWNODE_ROOT			0
+
+/*
+ * The maximum expected number of CSI-2 data lanes.
+ *
+ * This number is not expected to ever have to be equal to or greater than the
+ * number of bits in an unsigned long variable, but if it needs to be increased
+ * above that limit, code will need to be adjusted accordingly.
+ */
 #define ACPI_DEVICE_CSI2_DATA_LANES		8
 
 #define ACPI_DEVICE_SWNODE_PORT_NAME_LENGTH	8
 
+enum acpi_device_swnode_dev_props {
+	ACPI_DEVICE_SWNODE_DEV_NUM_OF,
+	ACPI_DEVICE_SWNODE_DEV_NUM_ENTRIES
+};
+
 enum acpi_device_swnode_port_props {
 	ACPI_DEVICE_SWNODE_PORT_REG,
 	ACPI_DEVICE_SWNODE_PORT_NUM_OF,
@@ -425,12 +439,14 @@ struct acpi_device_software_node_port {
 
 /**
  * struct acpi_device_software_nodes - Software nodes for an ACPI device
+ * @dev_props: Device properties.
  * @nodes: Software nodes for root as well as ports and endpoints.
  * @nodeprts: Array of software node pointers, for (un)registering them.
  * @ports: Information related to each port and endpoint within a port.
  * @num_ports: The number of ports.
  */
 struct acpi_device_software_nodes {
+	struct property_entry dev_props[ACPI_DEVICE_SWNODE_DEV_NUM_ENTRIES];
 	struct software_node *nodes;
 	const struct software_node **nodeptrs;
 	struct acpi_device_software_node_port *ports;
@@ -455,6 +471,7 @@ struct acpi_device {
 	struct acpi_device_data data;
 	struct acpi_scan_handler *handler;
 	struct acpi_hotplug_context *hp;
+	struct acpi_device_software_nodes *swnodes;
 	const struct acpi_gpio_mapping *driver_gpios;
 	void *driver_data;
 	struct device dev;
-- 
cgit v1.2.3


From f533e43a2a3117cc59886cbcd66ca32e42cf1ea9 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Mon, 6 Nov 2023 17:28:40 +0100
Subject: ACPI: property: Dig "rotation" property for devices with CSI2 _CRS

Find the "rotation" property value for devices with _CRS CSI-2 resource
descriptors and use it to add the "rotation" property to the software
nodes representing the CSI-2 connection graph.  That value typically
comes from the _PLD (Physical Location of Device) object if it is
present for the given device.

This way, camera sensor drivers that know the "rotation" property do not
need to care about _PLD on systems using ACPI.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
[ rjw: Changelog edits, file rename ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Tested-by: Sakari Ailus <sakari.ailus@linux.intel.com>
---
 drivers/acpi/mipi-disco-img.c | 17 +++++++++++++++++
 include/acpi/acpi_bus.h       |  1 +
 2 files changed, 18 insertions(+)

(limited to 'include')

diff --git a/drivers/acpi/mipi-disco-img.c b/drivers/acpi/mipi-disco-img.c
index dcbaba91d4fe..b2c7a4922804 100644
--- a/drivers/acpi/mipi-disco-img.c
+++ b/drivers/acpi/mipi-disco-img.c
@@ -595,6 +595,7 @@ static void init_crs_csi2_swnodes(struct crs_csi2 *csi2)
 	struct acpi_buffer buffer = { .length = ACPI_ALLOCATE_BUFFER };
 	struct acpi_device_software_nodes *swnodes = csi2->swnodes;
 	acpi_handle handle = csi2->handle;
+	unsigned int prop_index = 0;
 	struct fwnode_handle *adev_fwnode;
 	struct acpi_device *adev;
 	acpi_status status;
@@ -614,6 +615,22 @@ static void init_crs_csi2_swnodes(struct crs_csi2 *csi2)
 
 	adev_fwnode = acpi_fwnode_handle(adev);
 
+	/*
+	 * If the "rotation" property is not present, but _PLD is there,
+	 * evaluate it to get the "rotation" value.
+	 */
+	if (!fwnode_property_present(adev_fwnode, "rotation")) {
+		struct acpi_pld_info *pld;
+
+		status = acpi_get_physical_device_location(handle, &pld);
+		if (ACPI_SUCCESS(status)) {
+			swnodes->dev_props[NEXT_PROPERTY(prop_index, DEV_ROTATION)] =
+					PROPERTY_ENTRY_U32("rotation",
+							   pld->rotation * 45U);
+			kfree(pld);
+		}
+	}
+
 	status = acpi_get_name(handle, ACPI_FULL_PATHNAME, &buffer);
 	if (ACPI_FAILURE(status)) {
 		acpi_handle_info(handle, "Unable to get the path name\n");
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index c299fb974e49..1e5d2e2c3444 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -380,6 +380,7 @@ struct acpi_gpio_mapping;
 #define ACPI_DEVICE_SWNODE_PORT_NAME_LENGTH	8
 
 enum acpi_device_swnode_dev_props {
+	ACPI_DEVICE_SWNODE_DEV_ROTATION,
 	ACPI_DEVICE_SWNODE_DEV_NUM_OF,
 	ACPI_DEVICE_SWNODE_DEV_NUM_ENTRIES
 };
-- 
cgit v1.2.3


From 4cd57d6d527c3570827a6eb8bd790ae216a78ed9 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Mon, 6 Nov 2023 17:31:18 +0100
Subject: ACPI: property: Replicate DT-aligned u32 properties from DisCo for
 Imaging

MIPI DisCo for Imaging defines properties for camera sensors that
functionally align with DT equivalents.

Replicate these properties in the ACPI device swnodes so the code
using the corresponding DT properties already does not need to be
updated to deal with their MIPI counterparts directly.

The replicated properties are:

	"mipi-img-clock-frequency" -> "clock-frequency"
	"mipi-img-led-max-current" -> "led-max-microamp"
	"mipi-img-flash-max-current" -> "flash-max-microamp"
	"mipi-img-flash-max-timeout" -> "flash-max-timeout-us"

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
[ rjw: Changelog edits, removal of redundant braces ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Tested-by: Sakari Ailus <sakari.ailus@linux.intel.com>
---
 drivers/acpi/mipi-disco-img.c | 17 +++++++++++++++++
 include/acpi/acpi_bus.h       |  4 ++++
 2 files changed, 21 insertions(+)

(limited to 'include')

diff --git a/drivers/acpi/mipi-disco-img.c b/drivers/acpi/mipi-disco-img.c
index b2c7a4922804..cad72d1fc127 100644
--- a/drivers/acpi/mipi-disco-img.c
+++ b/drivers/acpi/mipi-disco-img.c
@@ -600,6 +600,7 @@ static void init_crs_csi2_swnodes(struct crs_csi2 *csi2)
 	struct acpi_device *adev;
 	acpi_status status;
 	unsigned int i;
+	u32 val;
 	int ret;
 
 	/*
@@ -631,6 +632,22 @@ static void init_crs_csi2_swnodes(struct crs_csi2 *csi2)
 		}
 	}
 
+	if (!fwnode_property_read_u32(adev_fwnode, "mipi-img-clock-frequency", &val))
+		swnodes->dev_props[NEXT_PROPERTY(prop_index, DEV_CLOCK_FREQUENCY)] =
+			PROPERTY_ENTRY_U32("clock-frequency", val);
+
+	if (!fwnode_property_read_u32(adev_fwnode, "mipi-img-led-max-current", &val))
+		swnodes->dev_props[NEXT_PROPERTY(prop_index, DEV_LED_MAX_MICROAMP)] =
+			PROPERTY_ENTRY_U32("led-max-microamp", val);
+
+	if (!fwnode_property_read_u32(adev_fwnode, "mipi-img-flash-max-current", &val))
+		swnodes->dev_props[NEXT_PROPERTY(prop_index, DEV_FLASH_MAX_MICROAMP)] =
+			PROPERTY_ENTRY_U32("flash-max-microamp", val);
+
+	if (!fwnode_property_read_u32(adev_fwnode, "mipi-img-flash-max-timeout-us", &val))
+		swnodes->dev_props[NEXT_PROPERTY(prop_index, DEV_FLASH_MAX_TIMEOUT_US)] =
+			PROPERTY_ENTRY_U32("flash-max-timeout-us", val);
+
 	status = acpi_get_name(handle, ACPI_FULL_PATHNAME, &buffer);
 	if (ACPI_FAILURE(status)) {
 		acpi_handle_info(handle, "Unable to get the path name\n");
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 1e5d2e2c3444..989ea623b1c2 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -381,6 +381,10 @@ struct acpi_gpio_mapping;
 
 enum acpi_device_swnode_dev_props {
 	ACPI_DEVICE_SWNODE_DEV_ROTATION,
+	ACPI_DEVICE_SWNODE_DEV_CLOCK_FREQUENCY,
+	ACPI_DEVICE_SWNODE_DEV_LED_MAX_MICROAMP,
+	ACPI_DEVICE_SWNODE_DEV_FLASH_MAX_MICROAMP,
+	ACPI_DEVICE_SWNODE_DEV_FLASH_MAX_TIMEOUT_US,
 	ACPI_DEVICE_SWNODE_DEV_NUM_OF,
 	ACPI_DEVICE_SWNODE_DEV_NUM_ENTRIES
 };
-- 
cgit v1.2.3


From 44844db91397d3d94589f3c0c855be02daeebdb3 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Thu, 9 Nov 2023 16:01:48 +0100
Subject: thermal: core: Add trip thresholds for trip crossing detection

The trip crossing detection in handle_thermal_trip() does not work
correctly in the cases when a trip point is crossed on the way up and
then the zone temperature stays above its low temperature (that is, its
temperature decreased by its hysteresis).  The trip temperature may
be passed by the zone temperature subsequently in that case, even
multiple times, but that does not count as the trip crossing as long as
the zone temperature does not fall below the trip's low temperature or,
in other words, until the trip is crossed on the way down.

|-----------low--------high------------|
             |<--------->|
             |    hyst   |
             |           |
             |          -|--> crossed on the way up
             |
         <---|-- crossed on the way down

However, handle_thermal_trip() will invoke thermal_notify_tz_trip_up()
every time the trip temperature is passed by the zone temperature on
the way up regardless of whether or not the trip has been crossed on
the way down yet.  Moreover, it will not call thermal_notify_tz_trip_down()
if the last zone temperature was between the trip's temperature and its
low temperature, so some "trip crossed on the way down" events may not
be reported.

To address this issue, introduce trip thresholds equal to either the
temperature of the given trip, or its low temperature, such that if
the trip's threshold is passed by the zone temperature on the way up,
its value will be set to the trip's low temperature and
thermal_notify_tz_trip_up() will be called, and if the trip's threshold
is passed by the zone temperature on the way down, its value will be set
to the trip's temperature (high) and thermal_notify_tz_trip_down() will
be called.  Accordingly, if the threshold is passed on the way up, it
cannot be passed on the way up again until its passed on the way down
and if it is passed on the way down, it cannot be passed on the way down
again until it is passed on the way up which guarantees correct
triggering of trip crossing notifications.

If the last temperature of the zone is invalid, the trip's threshold
will be set depending of the zone's current temperature: If that
temperature is above the trip's temperature, its threshold will be
set to its low temperature or otherwise its threshold will be set to
its (high) temperature.  Because the zone temperature is initially
set to invalid and tz->last_temperature is only updated by
update_temperature(), this is sufficient to set the correct initial
threshold values for all trips.

Link: https://lore.kernel.org/all/20220718145038.1114379-4-daniel.lezcano@linaro.org
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/thermal/thermal_core.c | 43 +++++++++++++++++++++++++++++++++++-------
 include/linux/thermal.h        |  2 ++
 2 files changed, 38 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 9c17d35ccbbd..625ba07cbe2f 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -345,22 +345,51 @@ static void handle_critical_trips(struct thermal_zone_device *tz,
 }
 
 static void handle_thermal_trip(struct thermal_zone_device *tz,
-				const struct thermal_trip *trip)
+				struct thermal_trip *trip)
 {
 	if (trip->temperature == THERMAL_TEMP_INVALID)
 		return;
 
-	if (tz->last_temperature != THERMAL_TEMP_INVALID) {
-		if (tz->last_temperature < trip->temperature &&
-		    tz->temperature >= trip->temperature)
+	if (tz->last_temperature == THERMAL_TEMP_INVALID) {
+		/* Initialization. */
+		trip->threshold = trip->temperature;
+		if (tz->temperature >= trip->threshold)
+			trip->threshold -= trip->hysteresis;
+	} else if (tz->last_temperature < trip->threshold) {
+		/*
+		 * The trip threshold is equal to the trip temperature, unless
+		 * the latter has changed in the meantime.  In either case,
+		 * the trip is crossed if the current zone temperature is at
+		 * least equal to its temperature, but otherwise ensure that
+		 * the threshold and the trip temperature will be equal.
+		 */
+		if (tz->temperature >= trip->temperature) {
 			thermal_notify_tz_trip_up(tz->id,
 						  thermal_zone_trip_id(tz, trip),
 						  tz->temperature);
-		if (tz->last_temperature >= trip->temperature &&
-		    tz->temperature < trip->temperature - trip->hysteresis)
+			trip->threshold = trip->temperature - trip->hysteresis;
+		} else {
+			trip->threshold = trip->temperature;
+		}
+	} else {
+		/*
+		 * The previous zone temperature was above or equal to the trip
+		 * threshold, which would be equal to the "low temperature" of
+		 * the trip (its temperature minus its hysteresis), unless the
+		 * trip temperature or hysteresis had changed.  In either case,
+		 * the trip is crossed if the current zone temperature is below
+		 * the low temperature of the trip, but otherwise ensure that
+		 * the trip threshold will be equal to the low temperature of
+		 * the trip.
+		 */
+		if (tz->temperature < trip->temperature - trip->hysteresis) {
 			thermal_notify_tz_trip_down(tz->id,
 						    thermal_zone_trip_id(tz, trip),
 						    tz->temperature);
+			trip->threshold = trip->temperature;
+		} else {
+			trip->threshold = trip->temperature - trip->hysteresis;
+		}
 	}
 
 	if (trip->type == THERMAL_TRIP_CRITICAL || trip->type == THERMAL_TRIP_HOT)
@@ -403,7 +432,7 @@ static void thermal_zone_device_init(struct thermal_zone_device *tz)
 void __thermal_zone_device_update(struct thermal_zone_device *tz,
 				  enum thermal_notify_event event)
 {
-	const struct thermal_trip *trip;
+	struct thermal_trip *trip;
 
 	if (atomic_read(&in_suspend))
 		return;
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index cee814d5d1ac..1f9ee869f9f9 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -57,12 +57,14 @@ enum thermal_notify_event {
  * struct thermal_trip - representation of a point in temperature domain
  * @temperature: temperature value in miliCelsius
  * @hysteresis: relative hysteresis in miliCelsius
+ * @threshold: trip crossing notification threshold miliCelsius
  * @type: trip point type
  * @priv: pointer to driver data associated with this trip
  */
 struct thermal_trip {
 	int temperature;
 	int hysteresis;
+	int threshold;
 	enum thermal_trip_type type;
 	void *priv;
 };
-- 
cgit v1.2.3


From 52304886ea49ee662589aff05925ef226c17a6a6 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 26 Oct 2023 15:53:03 +0200
Subject: ACPI: video: Add comment about acpi_video_backlight_use_native()
 usage

Add a comment explaining that acpi_video_backlight_use_native() MUST
only be used by GPU drivers and that it must NOT be used on other places.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/video.h | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'include')

diff --git a/include/acpi/video.h b/include/acpi/video.h
index 4230392b5b0b..3d538d4178ab 100644
--- a/include/acpi/video.h
+++ b/include/acpi/video.h
@@ -75,6 +75,15 @@ static inline enum acpi_backlight_type acpi_video_get_backlight_type(void)
 	return __acpi_video_get_backlight_type(false, NULL);
 }
 
+/*
+ * This function MUST only be called by GPU drivers to check if the driver
+ * should register a backlight class device. This function not only checks
+ * if a GPU native backlight device should be registered it *also* tells
+ * the ACPI video-detect code that native GPU backlight control is available.
+ * Therefor calling this from any place other then the GPU driver is wrong!
+ * To check if GPU native backlight control is used in other places instead use:
+ *   if (acpi_video_get_backlight_type() == acpi_backlight_native) { ... }
+ */
 static inline bool acpi_video_backlight_use_native(void)
 {
 	return __acpi_video_get_backlight_type(true, NULL) == acpi_backlight_native;
-- 
cgit v1.2.3


From d9dcdb4531fe39ce48919ef8c2c9369ee49f3ad2 Mon Sep 17 00:00:00 2001
From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Date: Fri, 20 Oct 2023 11:21:07 +0200
Subject: PCI: host-generic: Convert to platform remove callback returning void
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code.  However the value returned is (mostly) ignored
and this typically results in resource leaks. To improve here there is a
quest to make the remove callback return void. In the first step of this
quest all drivers are converted to .remove_new() which already returns
void.

pci_host_common_remove() returned zero unconditionally. With that converted
to return void instead, the generic pci host driver can be switched to
.remove_new() trivially.

Link: https://lore.kernel.org/r/20231020092107.2148311-1-u.kleine-koenig@pengutronix.de
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Will Deacon <will@kernel.org>
---
 drivers/pci/controller/pci-host-common.c  | 4 +---
 drivers/pci/controller/pci-host-generic.c | 2 +-
 include/linux/pci-ecam.h                  | 2 +-
 3 files changed, 3 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/controller/pci-host-common.c b/drivers/pci/controller/pci-host-common.c
index 6be3266cd7b5..45b71806182d 100644
--- a/drivers/pci/controller/pci-host-common.c
+++ b/drivers/pci/controller/pci-host-common.c
@@ -85,7 +85,7 @@ int pci_host_common_probe(struct platform_device *pdev)
 }
 EXPORT_SYMBOL_GPL(pci_host_common_probe);
 
-int pci_host_common_remove(struct platform_device *pdev)
+void pci_host_common_remove(struct platform_device *pdev)
 {
 	struct pci_host_bridge *bridge = platform_get_drvdata(pdev);
 
@@ -93,8 +93,6 @@ int pci_host_common_remove(struct platform_device *pdev)
 	pci_stop_root_bus(bridge->bus);
 	pci_remove_root_bus(bridge->bus);
 	pci_unlock_rescan_remove();
-
-	return 0;
 }
 EXPORT_SYMBOL_GPL(pci_host_common_remove);
 
diff --git a/drivers/pci/controller/pci-host-generic.c b/drivers/pci/controller/pci-host-generic.c
index 63865aeb636b..41cb6a057f6e 100644
--- a/drivers/pci/controller/pci-host-generic.c
+++ b/drivers/pci/controller/pci-host-generic.c
@@ -82,7 +82,7 @@ static struct platform_driver gen_pci_driver = {
 		.of_match_table = gen_pci_of_match,
 	},
 	.probe = pci_host_common_probe,
-	.remove = pci_host_common_remove,
+	.remove_new = pci_host_common_remove,
 };
 module_platform_driver(gen_pci_driver);
 
diff --git a/include/linux/pci-ecam.h b/include/linux/pci-ecam.h
index 6b1301e2498e..3a4860bd2758 100644
--- a/include/linux/pci-ecam.h
+++ b/include/linux/pci-ecam.h
@@ -93,6 +93,6 @@ extern const struct pci_ecam_ops loongson_pci_ecam_ops; /* Loongson PCIe */
 #if IS_ENABLED(CONFIG_PCI_HOST_COMMON)
 /* for DT-based PCI controllers that support ECAM */
 int pci_host_common_probe(struct platform_device *pdev);
-int pci_host_common_remove(struct platform_device *pdev);
+void pci_host_common_remove(struct platform_device *pdev);
 #endif
 #endif
-- 
cgit v1.2.3


From 3171e46d677a668eed3086da78671f1e4f5b8405 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 30 Oct 2023 13:42:18 +0200
Subject: PCI: Avoid potential out-of-bounds read in
 pci_dev_for_each_resource()

Coverity complains that pointer in the pci_dev_for_each_resource() may be
wrong, i.e., might be used for the out-of-bounds read.

There is no actual issue right now because we have another check afterwards
and the out-of-bounds read is not being performed. In any case it's better
code with this fixed, hence the proposed change.

As Jonas pointed out "It probably makes the code slightly less performant
as res will now be checked for being not NULL (which will always be true),
but I doubt it will be significant (or in any hot paths)."

Fixes: 09cc90063240 ("PCI: Introduce pci_dev_for_each_resource()")
Reported-by: Bjorn Helgaas <bhelgaas@google.com>
Closes: https://lore.kernel.org/r/20230509182122.GA1259567@bhelgaas
Suggested-by: Jonas Gorski <jonas.gorski@gmail.com>
Link: https://lore.kernel.org/r/20231030114218.2752236-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 include/linux/pci.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/pci.h b/include/linux/pci.h
index 60ca768bc867..4ebecc7896ef 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -2127,14 +2127,14 @@ int pci_iobar_pfn(struct pci_dev *pdev, int bar, struct vm_area_struct *vma);
 	(pci_resource_end((dev), (bar)) ? 				\
 	 resource_size(pci_resource_n((dev), (bar))) : 0)
 
-#define __pci_dev_for_each_res0(dev, res, ...)				\
-	for (unsigned int __b = 0;					\
-	     res = pci_resource_n(dev, __b), __b < PCI_NUM_RESOURCES;	\
+#define __pci_dev_for_each_res0(dev, res, ...)				  \
+	for (unsigned int __b = 0;					  \
+	     __b < PCI_NUM_RESOURCES && (res = pci_resource_n(dev, __b)); \
 	     __b++)
 
-#define __pci_dev_for_each_res1(dev, res, __b)				\
-	for (__b = 0;							\
-	     res = pci_resource_n(dev, __b), __b < PCI_NUM_RESOURCES;	\
+#define __pci_dev_for_each_res1(dev, res, __b)				  \
+	for (__b = 0;							  \
+	     __b < PCI_NUM_RESOURCES && (res = pci_resource_n(dev, __b)); \
 	     __b++)
 
 #define pci_dev_for_each_resource(dev, res, ...)			\
-- 
cgit v1.2.3


From 9902cb999e4e913d98e8afe4b36c08e4a793e1ce Mon Sep 17 00:00:00 2001
From: Rob Clark <robdclark@chromium.org>
Date: Mon, 6 Nov 2023 10:50:26 -0800
Subject: drm/msm/gem: Add metadata

The EXT_external_objects extension is a bit awkward as it doesn't pass
explicit modifiers, leaving the importer to guess with incomplete
information.  In the case of vk (turnip) exporting and gl (freedreno)
importing, the "OPTIMAL_TILING_EXT" layout depends on VkImageCreateInfo
flags (among other things), which the importer does not know.  Which
unfortunately leaves us with the need for a metadata back-channel.

The contents of the metadata are defined by userspace.  The
EXT_external_objects extension is only required to work between
compatible versions of gl and vk drivers, as defined by device and
driver UUIDs.

v2: add missing metadata kfree
v3: Rework to move copy_from/to_user out from under gem obj lock
    to avoid angering lockdep about deadlocks against fs-reclaim

Signed-off-by: Rob Clark <robdclark@chromium.org>
Patchwork: https://patchwork.freedesktop.org/patch/566157/
---
 drivers/gpu/drm/msm/msm_drv.c | 92 ++++++++++++++++++++++++++++++++++++++++++-
 drivers/gpu/drm/msm/msm_gem.c |  1 +
 drivers/gpu/drm/msm/msm_gem.h |  4 ++
 include/uapi/drm/msm_drm.h    |  2 +
 4 files changed, 98 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index d751d2023f84..75d60aab5780 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -37,9 +37,10 @@
  * - 1.9.0 - Add MSM_SUBMIT_FENCE_SN_IN
  * - 1.10.0 - Add MSM_SUBMIT_BO_NO_IMPLICIT
  * - 1.11.0 - Add wait boost (MSM_WAIT_FENCE_BOOST, MSM_PREP_BOOST)
+ * - 1.12.0 - Add MSM_INFO_SET_METADATA and MSM_INFO_GET_METADATA
  */
 #define MSM_VERSION_MAJOR	1
-#define MSM_VERSION_MINOR	11
+#define MSM_VERSION_MINOR	12
 #define MSM_VERSION_PATCHLEVEL	0
 
 static void msm_deinit_vram(struct drm_device *ddev);
@@ -546,6 +547,85 @@ static int msm_ioctl_gem_info_set_iova(struct drm_device *dev,
 	return msm_gem_set_iova(obj, ctx->aspace, iova);
 }
 
+static int msm_ioctl_gem_info_set_metadata(struct drm_gem_object *obj,
+					   __user void *metadata,
+					   u32 metadata_size)
+{
+	struct msm_gem_object *msm_obj = to_msm_bo(obj);
+	void *buf;
+	int ret;
+
+	/* Impose a moderate upper bound on metadata size: */
+	if (metadata_size > 128) {
+		return -EOVERFLOW;
+	}
+
+	/* Use a temporary buf to keep copy_from_user() outside of gem obj lock: */
+	buf = memdup_user(metadata, metadata_size);
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
+
+	ret = msm_gem_lock_interruptible(obj);
+	if (ret)
+		goto out;
+
+	msm_obj->metadata =
+		krealloc(msm_obj->metadata, metadata_size, GFP_KERNEL);
+	msm_obj->metadata_size = metadata_size;
+	memcpy(msm_obj->metadata, buf, metadata_size);
+
+	msm_gem_unlock(obj);
+
+out:
+	kfree(buf);
+
+	return ret;
+}
+
+static int msm_ioctl_gem_info_get_metadata(struct drm_gem_object *obj,
+					   __user void *metadata,
+					   u32 *metadata_size)
+{
+	struct msm_gem_object *msm_obj = to_msm_bo(obj);
+	void *buf;
+	int ret, len;
+
+	if (!metadata) {
+		/*
+		 * Querying the size is inherently racey, but
+		 * EXT_external_objects expects the app to confirm
+		 * via device and driver UUIDs that the exporter and
+		 * importer versions match.  All we can do from the
+		 * kernel side is check the length under obj lock
+		 * when userspace tries to retrieve the metadata
+		 */
+		*metadata_size = msm_obj->metadata_size;
+		return 0;
+	}
+
+	ret = msm_gem_lock_interruptible(obj);
+	if (ret)
+		return ret;
+
+	/* Avoid copy_to_user() under gem obj lock: */
+	len = msm_obj->metadata_size;
+	buf = kmemdup(msm_obj->metadata, len, GFP_KERNEL);
+
+	msm_gem_unlock(obj);
+
+	if (*metadata_size < len) {
+		ret = -ETOOSMALL;
+	} else if (copy_to_user(metadata, buf, len)) {
+		ret = -EFAULT;
+	} else {
+		*metadata_size = len;
+	}
+
+	kfree(buf);
+
+	return 0;
+}
+
 static int msm_ioctl_gem_info(struct drm_device *dev, void *data,
 		struct drm_file *file)
 {
@@ -568,6 +648,8 @@ static int msm_ioctl_gem_info(struct drm_device *dev, void *data,
 		break;
 	case MSM_INFO_SET_NAME:
 	case MSM_INFO_GET_NAME:
+	case MSM_INFO_SET_METADATA:
+	case MSM_INFO_GET_METADATA:
 		break;
 	default:
 		return -EINVAL;
@@ -630,6 +712,14 @@ static int msm_ioctl_gem_info(struct drm_device *dev, void *data,
 				ret = -EFAULT;
 		}
 		break;
+	case MSM_INFO_SET_METADATA:
+		ret = msm_ioctl_gem_info_set_metadata(
+			obj, u64_to_user_ptr(args->value), args->len);
+		break;
+	case MSM_INFO_GET_METADATA:
+		ret = msm_ioctl_gem_info_get_metadata(
+			obj, u64_to_user_ptr(args->value), &args->len);
+		break;
 	}
 
 	drm_gem_object_put(obj);
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index db1e748daa75..32303cc8e646 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -1058,6 +1058,7 @@ static void msm_gem_free_object(struct drm_gem_object *obj)
 
 	drm_gem_object_release(obj);
 
+	kfree(msm_obj->metadata);
 	kfree(msm_obj);
 }
 
diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h
index 8ddef5443140..6352bd3cc5ed 100644
--- a/drivers/gpu/drm/msm/msm_gem.h
+++ b/drivers/gpu/drm/msm/msm_gem.h
@@ -108,6 +108,10 @@ struct msm_gem_object {
 
 	char name[32]; /* Identifier to print for the debugfs files */
 
+	/* userspace metadata backchannel */
+	void *metadata;
+	u32 metadata_size;
+
 	/**
 	 * pin_count: Number of times the pages are pinned
 	 *
diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h
index 6c34272a13fd..6f2a7ad04aa4 100644
--- a/include/uapi/drm/msm_drm.h
+++ b/include/uapi/drm/msm_drm.h
@@ -139,6 +139,8 @@ struct drm_msm_gem_new {
 #define MSM_INFO_GET_NAME	0x03   /* get debug name, returned by pointer */
 #define MSM_INFO_SET_IOVA	0x04   /* set the iova, passed by value */
 #define MSM_INFO_GET_FLAGS	0x05   /* get the MSM_BO_x flags */
+#define MSM_INFO_SET_METADATA	0x06   /* set userspace metadata */
+#define MSM_INFO_GET_METADATA	0x07   /* get userspace metadata */
 
 struct drm_msm_gem_info {
 	__u32 handle;         /* in */
-- 
cgit v1.2.3


From fe3b082a6eb8b1526ed7397c849d6b2a6baeb6a1 Mon Sep 17 00:00:00 2001
From: Ashish Mhetre <amhetre@nvidia.com>
Date: Tue, 7 Nov 2023 16:57:12 +0530
Subject: memory: tegra: Add SID override programming for MC clients

For some devices the bootloader/firmware may set up the device in
bypass. Memory clients like display needs kernel to program SID after
resume because bootloader/firmware programs the SID of display device to
bypass. In order to make sure that kernel IOMMU mappings for these
devices work after resume, add SID override programming support for all
memory clients on memory controller resume.

This partially reverts 'commit ef86b2c2807f ("memory: tegra: Remove
clients SID override programming")'

Signed-off-by: Ashish Mhetre <amhetre@nvidia.com>
Link: https://lore.kernel.org/r/20231107112713.21399-1-amhetre@nvidia.com
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 drivers/memory/tegra/tegra186.c | 14 ++++++++++++++
 include/soc/tegra/mc.h          |  1 +
 2 files changed, 15 insertions(+)

(limited to 'include')

diff --git a/drivers/memory/tegra/tegra186.c b/drivers/memory/tegra/tegra186.c
index 533f85a4b2bd..8203f0db1350 100644
--- a/drivers/memory/tegra/tegra186.c
+++ b/drivers/memory/tegra/tegra186.c
@@ -136,9 +136,23 @@ static int tegra186_mc_probe_device(struct tegra_mc *mc, struct device *dev)
 	return 0;
 }
 
+static int tegra186_mc_resume(struct tegra_mc *mc)
+{
+	unsigned int i;
+
+	for (i = 0; i < mc->soc->num_clients; i++) {
+		const struct tegra_mc_client *client = &mc->soc->clients[i];
+
+		tegra186_mc_client_sid_override(mc, client, client->sid);
+	}
+
+	return 0;
+}
+
 const struct tegra_mc_ops tegra186_mc_ops = {
 	.probe = tegra186_mc_probe,
 	.remove = tegra186_mc_remove,
+	.resume = tegra186_mc_resume,
 	.probe_device = tegra186_mc_probe_device,
 	.handle_irq = tegra30_mc_handle_irq,
 };
diff --git a/include/soc/tegra/mc.h b/include/soc/tegra/mc.h
index 71ae37d3bedd..af1d73a7f0cd 100644
--- a/include/soc/tegra/mc.h
+++ b/include/soc/tegra/mc.h
@@ -162,6 +162,7 @@ struct tegra_mc_ops {
 	 */
 	int (*probe)(struct tegra_mc *mc);
 	void (*remove)(struct tegra_mc *mc);
+	int (*resume)(struct tegra_mc *mc);
 	irqreturn_t (*handle_irq)(int irq, void *data);
 	int (*probe_device)(struct tegra_mc *mc, struct device *dev);
 };
-- 
cgit v1.2.3


From 600f111ef51dc2cbdb330b09d09f1856efa64912 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Fri, 17 Nov 2023 21:58:23 +0000
Subject: fs: Rename mapping private members

It is hard to find where mapping->private_lock, mapping->private_list and
mapping->private_data are used, due to private_XXX being a relatively
common name for variables and structure members in the kernel.  To fit
with other members of struct address_space, rename them all to have an
i_ prefix.  Tested with an allmodconfig build.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Link: https://lore.kernel.org/r/20231117215823.2821906-1-willy@infradead.org
Acked-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/aio.c             |  16 ++++----
 fs/btrfs/extent_io.c |  52 ++++++++++++-------------
 fs/btrfs/subpage.c   |   4 +-
 fs/buffer.c          | 108 +++++++++++++++++++++++++--------------------------
 fs/ext4/inode.c      |   4 +-
 fs/gfs2/glock.c      |   2 +-
 fs/gfs2/ops_fstype.c |   2 +-
 fs/hugetlbfs/inode.c |   4 +-
 fs/inode.c           |   8 ++--
 fs/nfs/write.c       |  12 +++---
 fs/nilfs2/inode.c    |   4 +-
 fs/ntfs/aops.c       |  10 ++---
 include/linux/fs.h   |  12 +++---
 mm/hugetlb.c         |   2 +-
 mm/migrate.c         |   6 +--
 15 files changed, 123 insertions(+), 123 deletions(-)

(limited to 'include')

diff --git a/fs/aio.c b/fs/aio.c
index f8589caef9c1..d02842156b35 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -266,7 +266,7 @@ static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
 		return ERR_CAST(inode);
 
 	inode->i_mapping->a_ops = &aio_ctx_aops;
-	inode->i_mapping->private_data = ctx;
+	inode->i_mapping->i_private_data = ctx;
 	inode->i_size = PAGE_SIZE * nr_pages;
 
 	file = alloc_file_pseudo(inode, aio_mnt, "[aio]",
@@ -316,10 +316,10 @@ static void put_aio_ring_file(struct kioctx *ctx)
 
 		/* Prevent further access to the kioctx from migratepages */
 		i_mapping = aio_ring_file->f_mapping;
-		spin_lock(&i_mapping->private_lock);
-		i_mapping->private_data = NULL;
+		spin_lock(&i_mapping->i_private_lock);
+		i_mapping->i_private_data = NULL;
 		ctx->aio_ring_file = NULL;
-		spin_unlock(&i_mapping->private_lock);
+		spin_unlock(&i_mapping->i_private_lock);
 
 		fput(aio_ring_file);
 	}
@@ -422,9 +422,9 @@ static int aio_migrate_folio(struct address_space *mapping, struct folio *dst,
 
 	rc = 0;
 
-	/* mapping->private_lock here protects against the kioctx teardown.  */
-	spin_lock(&mapping->private_lock);
-	ctx = mapping->private_data;
+	/* mapping->i_private_lock here protects against the kioctx teardown.  */
+	spin_lock(&mapping->i_private_lock);
+	ctx = mapping->i_private_data;
 	if (!ctx) {
 		rc = -EINVAL;
 		goto out;
@@ -476,7 +476,7 @@ static int aio_migrate_folio(struct address_space *mapping, struct folio *dst,
 out_unlock:
 	mutex_unlock(&ctx->ring_lock);
 out:
-	spin_unlock(&mapping->private_lock);
+	spin_unlock(&mapping->i_private_lock);
 	return rc;
 }
 #else
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 03cef28d9e37..3431a53bf3fd 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -870,7 +870,7 @@ static int attach_extent_buffer_page(struct extent_buffer *eb,
 	 * will not race with any other ebs.
 	 */
 	if (page->mapping)
-		lockdep_assert_held(&page->mapping->private_lock);
+		lockdep_assert_held(&page->mapping->i_private_lock);
 
 	if (fs_info->nodesize >= PAGE_SIZE) {
 		if (!PagePrivate(page))
@@ -1736,16 +1736,16 @@ static int submit_eb_subpage(struct page *page, struct writeback_control *wbc)
 		 * Take private lock to ensure the subpage won't be detached
 		 * in the meantime.
 		 */
-		spin_lock(&page->mapping->private_lock);
+		spin_lock(&page->mapping->i_private_lock);
 		if (!PagePrivate(page)) {
-			spin_unlock(&page->mapping->private_lock);
+			spin_unlock(&page->mapping->i_private_lock);
 			break;
 		}
 		spin_lock_irqsave(&subpage->lock, flags);
 		if (!test_bit(bit_start + fs_info->subpage_info->dirty_offset,
 			      subpage->bitmaps)) {
 			spin_unlock_irqrestore(&subpage->lock, flags);
-			spin_unlock(&page->mapping->private_lock);
+			spin_unlock(&page->mapping->i_private_lock);
 			bit_start++;
 			continue;
 		}
@@ -1759,7 +1759,7 @@ static int submit_eb_subpage(struct page *page, struct writeback_control *wbc)
 		 */
 		eb = find_extent_buffer_nolock(fs_info, start);
 		spin_unlock_irqrestore(&subpage->lock, flags);
-		spin_unlock(&page->mapping->private_lock);
+		spin_unlock(&page->mapping->i_private_lock);
 
 		/*
 		 * The eb has already reached 0 refs thus find_extent_buffer()
@@ -1811,9 +1811,9 @@ static int submit_eb_page(struct page *page, struct btrfs_eb_write_context *ctx)
 	if (btrfs_sb(page->mapping->host->i_sb)->nodesize < PAGE_SIZE)
 		return submit_eb_subpage(page, wbc);
 
-	spin_lock(&mapping->private_lock);
+	spin_lock(&mapping->i_private_lock);
 	if (!PagePrivate(page)) {
-		spin_unlock(&mapping->private_lock);
+		spin_unlock(&mapping->i_private_lock);
 		return 0;
 	}
 
@@ -1824,16 +1824,16 @@ static int submit_eb_page(struct page *page, struct btrfs_eb_write_context *ctx)
 	 * crashing the machine for something we can survive anyway.
 	 */
 	if (WARN_ON(!eb)) {
-		spin_unlock(&mapping->private_lock);
+		spin_unlock(&mapping->i_private_lock);
 		return 0;
 	}
 
 	if (eb == ctx->eb) {
-		spin_unlock(&mapping->private_lock);
+		spin_unlock(&mapping->i_private_lock);
 		return 0;
 	}
 	ret = atomic_inc_not_zero(&eb->refs);
-	spin_unlock(&mapping->private_lock);
+	spin_unlock(&mapping->i_private_lock);
 	if (!ret)
 		return 0;
 
@@ -3056,7 +3056,7 @@ static bool page_range_has_eb(struct btrfs_fs_info *fs_info, struct page *page)
 {
 	struct btrfs_subpage *subpage;
 
-	lockdep_assert_held(&page->mapping->private_lock);
+	lockdep_assert_held(&page->mapping->i_private_lock);
 
 	if (PagePrivate(page)) {
 		subpage = (struct btrfs_subpage *)page->private;
@@ -3079,14 +3079,14 @@ static void detach_extent_buffer_page(struct extent_buffer *eb, struct page *pag
 
 	/*
 	 * For mapped eb, we're going to change the page private, which should
-	 * be done under the private_lock.
+	 * be done under the i_private_lock.
 	 */
 	if (mapped)
-		spin_lock(&page->mapping->private_lock);
+		spin_lock(&page->mapping->i_private_lock);
 
 	if (!PagePrivate(page)) {
 		if (mapped)
-			spin_unlock(&page->mapping->private_lock);
+			spin_unlock(&page->mapping->i_private_lock);
 		return;
 	}
 
@@ -3110,7 +3110,7 @@ static void detach_extent_buffer_page(struct extent_buffer *eb, struct page *pag
 			detach_page_private(page);
 		}
 		if (mapped)
-			spin_unlock(&page->mapping->private_lock);
+			spin_unlock(&page->mapping->i_private_lock);
 		return;
 	}
 
@@ -3133,7 +3133,7 @@ static void detach_extent_buffer_page(struct extent_buffer *eb, struct page *pag
 	if (!page_range_has_eb(fs_info, page))
 		btrfs_detach_subpage(fs_info, page);
 
-	spin_unlock(&page->mapping->private_lock);
+	spin_unlock(&page->mapping->i_private_lock);
 }
 
 /* Release all pages attached to the extent buffer */
@@ -3514,7 +3514,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 
 	/*
 	 * Preallocate page->private for subpage case, so that we won't
-	 * allocate memory with private_lock nor page lock hold.
+	 * allocate memory with i_private_lock nor page lock hold.
 	 *
 	 * The memory will be freed by attach_extent_buffer_page() or freed
 	 * manually if we exit earlier.
@@ -3535,10 +3535,10 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 			goto free_eb;
 		}
 
-		spin_lock(&mapping->private_lock);
+		spin_lock(&mapping->i_private_lock);
 		exists = grab_extent_buffer(fs_info, p);
 		if (exists) {
-			spin_unlock(&mapping->private_lock);
+			spin_unlock(&mapping->i_private_lock);
 			unlock_page(p);
 			put_page(p);
 			mark_extent_buffer_accessed(exists, p);
@@ -3558,7 +3558,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 		 * Thus needs no special handling in error path.
 		 */
 		btrfs_page_inc_eb_refs(fs_info, p);
-		spin_unlock(&mapping->private_lock);
+		spin_unlock(&mapping->i_private_lock);
 
 		WARN_ON(btrfs_page_test_dirty(fs_info, p, eb->start, eb->len));
 		eb->pages[i] = p;
@@ -4563,12 +4563,12 @@ static int try_release_subpage_extent_buffer(struct page *page)
 	 * Finally to check if we have cleared page private, as if we have
 	 * released all ebs in the page, the page private should be cleared now.
 	 */
-	spin_lock(&page->mapping->private_lock);
+	spin_lock(&page->mapping->i_private_lock);
 	if (!PagePrivate(page))
 		ret = 1;
 	else
 		ret = 0;
-	spin_unlock(&page->mapping->private_lock);
+	spin_unlock(&page->mapping->i_private_lock);
 	return ret;
 
 }
@@ -4584,9 +4584,9 @@ int try_release_extent_buffer(struct page *page)
 	 * We need to make sure nobody is changing page->private, as we rely on
 	 * page->private as the pointer to extent buffer.
 	 */
-	spin_lock(&page->mapping->private_lock);
+	spin_lock(&page->mapping->i_private_lock);
 	if (!PagePrivate(page)) {
-		spin_unlock(&page->mapping->private_lock);
+		spin_unlock(&page->mapping->i_private_lock);
 		return 1;
 	}
 
@@ -4601,10 +4601,10 @@ int try_release_extent_buffer(struct page *page)
 	spin_lock(&eb->refs_lock);
 	if (atomic_read(&eb->refs) != 1 || extent_buffer_under_io(eb)) {
 		spin_unlock(&eb->refs_lock);
-		spin_unlock(&page->mapping->private_lock);
+		spin_unlock(&page->mapping->i_private_lock);
 		return 0;
 	}
-	spin_unlock(&page->mapping->private_lock);
+	spin_unlock(&page->mapping->i_private_lock);
 
 	/*
 	 * If tree ref isn't set then we know the ref on this eb is a real ref,
diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c
index 1b999c6e4193..2347cf15278b 100644
--- a/fs/btrfs/subpage.c
+++ b/fs/btrfs/subpage.c
@@ -200,7 +200,7 @@ void btrfs_page_inc_eb_refs(const struct btrfs_fs_info *fs_info,
 		return;
 
 	ASSERT(PagePrivate(page) && page->mapping);
-	lockdep_assert_held(&page->mapping->private_lock);
+	lockdep_assert_held(&page->mapping->i_private_lock);
 
 	subpage = (struct btrfs_subpage *)page->private;
 	atomic_inc(&subpage->eb_refs);
@@ -215,7 +215,7 @@ void btrfs_page_dec_eb_refs(const struct btrfs_fs_info *fs_info,
 		return;
 
 	ASSERT(PagePrivate(page) && page->mapping);
-	lockdep_assert_held(&page->mapping->private_lock);
+	lockdep_assert_held(&page->mapping->i_private_lock);
 
 	subpage = (struct btrfs_subpage *)page->private;
 	ASSERT(atomic_read(&subpage->eb_refs));
diff --git a/fs/buffer.c b/fs/buffer.c
index 967f34b70aa8..5ffc44ab4854 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -180,11 +180,11 @@ EXPORT_SYMBOL(end_buffer_write_sync);
  * Various filesystems appear to want __find_get_block to be non-blocking.
  * But it's the page lock which protects the buffers.  To get around this,
  * we get exclusion from try_to_free_buffers with the blockdev mapping's
- * private_lock.
+ * i_private_lock.
  *
- * Hack idea: for the blockdev mapping, private_lock contention
+ * Hack idea: for the blockdev mapping, i_private_lock contention
  * may be quite high.  This code could TryLock the page, and if that
- * succeeds, there is no need to take private_lock.
+ * succeeds, there is no need to take i_private_lock.
  */
 static struct buffer_head *
 __find_get_block_slow(struct block_device *bdev, sector_t block)
@@ -204,7 +204,7 @@ __find_get_block_slow(struct block_device *bdev, sector_t block)
 	if (IS_ERR(folio))
 		goto out;
 
-	spin_lock(&bd_mapping->private_lock);
+	spin_lock(&bd_mapping->i_private_lock);
 	head = folio_buffers(folio);
 	if (!head)
 		goto out_unlock;
@@ -236,7 +236,7 @@ __find_get_block_slow(struct block_device *bdev, sector_t block)
 		       1 << bd_inode->i_blkbits);
 	}
 out_unlock:
-	spin_unlock(&bd_mapping->private_lock);
+	spin_unlock(&bd_mapping->i_private_lock);
 	folio_put(folio);
 out:
 	return ret;
@@ -467,25 +467,25 @@ EXPORT_SYMBOL(mark_buffer_async_write);
  *
  * The functions mark_buffer_inode_dirty(), fsync_inode_buffers(),
  * inode_has_buffers() and invalidate_inode_buffers() are provided for the
- * management of a list of dependent buffers at ->i_mapping->private_list.
+ * management of a list of dependent buffers at ->i_mapping->i_private_list.
  *
  * Locking is a little subtle: try_to_free_buffers() will remove buffers
  * from their controlling inode's queue when they are being freed.  But
  * try_to_free_buffers() will be operating against the *blockdev* mapping
  * at the time, not against the S_ISREG file which depends on those buffers.
- * So the locking for private_list is via the private_lock in the address_space
+ * So the locking for i_private_list is via the i_private_lock in the address_space
  * which backs the buffers.  Which is different from the address_space 
  * against which the buffers are listed.  So for a particular address_space,
- * mapping->private_lock does *not* protect mapping->private_list!  In fact,
- * mapping->private_list will always be protected by the backing blockdev's
- * ->private_lock.
+ * mapping->i_private_lock does *not* protect mapping->i_private_list!  In fact,
+ * mapping->i_private_list will always be protected by the backing blockdev's
+ * ->i_private_lock.
  *
  * Which introduces a requirement: all buffers on an address_space's
- * ->private_list must be from the same address_space: the blockdev's.
+ * ->i_private_list must be from the same address_space: the blockdev's.
  *
- * address_spaces which do not place buffers at ->private_list via these
- * utility functions are free to use private_lock and private_list for
- * whatever they want.  The only requirement is that list_empty(private_list)
+ * address_spaces which do not place buffers at ->i_private_list via these
+ * utility functions are free to use i_private_lock and i_private_list for
+ * whatever they want.  The only requirement is that list_empty(i_private_list)
  * be true at clear_inode() time.
  *
  * FIXME: clear_inode should not call invalidate_inode_buffers().  The
@@ -508,7 +508,7 @@ EXPORT_SYMBOL(mark_buffer_async_write);
  */
 
 /*
- * The buffer's backing address_space's private_lock must be held
+ * The buffer's backing address_space's i_private_lock must be held
  */
 static void __remove_assoc_queue(struct buffer_head *bh)
 {
@@ -519,7 +519,7 @@ static void __remove_assoc_queue(struct buffer_head *bh)
 
 int inode_has_buffers(struct inode *inode)
 {
-	return !list_empty(&inode->i_data.private_list);
+	return !list_empty(&inode->i_data.i_private_list);
 }
 
 /*
@@ -561,7 +561,7 @@ repeat:
  * sync_mapping_buffers - write out & wait upon a mapping's "associated" buffers
  * @mapping: the mapping which wants those buffers written
  *
- * Starts I/O against the buffers at mapping->private_list, and waits upon
+ * Starts I/O against the buffers at mapping->i_private_list, and waits upon
  * that I/O.
  *
  * Basically, this is a convenience function for fsync().
@@ -570,13 +570,13 @@ repeat:
  */
 int sync_mapping_buffers(struct address_space *mapping)
 {
-	struct address_space *buffer_mapping = mapping->private_data;
+	struct address_space *buffer_mapping = mapping->i_private_data;
 
-	if (buffer_mapping == NULL || list_empty(&mapping->private_list))
+	if (buffer_mapping == NULL || list_empty(&mapping->i_private_list))
 		return 0;
 
-	return fsync_buffers_list(&buffer_mapping->private_lock,
-					&mapping->private_list);
+	return fsync_buffers_list(&buffer_mapping->i_private_lock,
+					&mapping->i_private_list);
 }
 EXPORT_SYMBOL(sync_mapping_buffers);
 
@@ -673,17 +673,17 @@ void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode)
 	struct address_space *buffer_mapping = bh->b_folio->mapping;
 
 	mark_buffer_dirty(bh);
-	if (!mapping->private_data) {
-		mapping->private_data = buffer_mapping;
+	if (!mapping->i_private_data) {
+		mapping->i_private_data = buffer_mapping;
 	} else {
-		BUG_ON(mapping->private_data != buffer_mapping);
+		BUG_ON(mapping->i_private_data != buffer_mapping);
 	}
 	if (!bh->b_assoc_map) {
-		spin_lock(&buffer_mapping->private_lock);
+		spin_lock(&buffer_mapping->i_private_lock);
 		list_move_tail(&bh->b_assoc_buffers,
-				&mapping->private_list);
+				&mapping->i_private_list);
 		bh->b_assoc_map = mapping;
-		spin_unlock(&buffer_mapping->private_lock);
+		spin_unlock(&buffer_mapping->i_private_lock);
 	}
 }
 EXPORT_SYMBOL(mark_buffer_dirty_inode);
@@ -706,7 +706,7 @@ EXPORT_SYMBOL(mark_buffer_dirty_inode);
  * bit, see a bunch of clean buffers and we'd end up with dirty buffers/clean
  * page on the dirty page list.
  *
- * We use private_lock to lock against try_to_free_buffers while using the
+ * We use i_private_lock to lock against try_to_free_buffers while using the
  * page's buffer list.  Also use this to protect against clean buffers being
  * added to the page after it was set dirty.
  *
@@ -718,7 +718,7 @@ bool block_dirty_folio(struct address_space *mapping, struct folio *folio)
 	struct buffer_head *head;
 	bool newly_dirty;
 
-	spin_lock(&mapping->private_lock);
+	spin_lock(&mapping->i_private_lock);
 	head = folio_buffers(folio);
 	if (head) {
 		struct buffer_head *bh = head;
@@ -734,7 +734,7 @@ bool block_dirty_folio(struct address_space *mapping, struct folio *folio)
 	 */
 	folio_memcg_lock(folio);
 	newly_dirty = !folio_test_set_dirty(folio);
-	spin_unlock(&mapping->private_lock);
+	spin_unlock(&mapping->i_private_lock);
 
 	if (newly_dirty)
 		__folio_mark_dirty(folio, mapping, 1);
@@ -827,7 +827,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list)
 		smp_mb();
 		if (buffer_dirty(bh)) {
 			list_add(&bh->b_assoc_buffers,
-				 &mapping->private_list);
+				 &mapping->i_private_list);
 			bh->b_assoc_map = mapping;
 		}
 		spin_unlock(lock);
@@ -851,7 +851,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list)
  * probably unmounting the fs, but that doesn't mean we have already
  * done a sync().  Just drop the buffers from the inode list.
  *
- * NOTE: we take the inode's blockdev's mapping's private_lock.  Which
+ * NOTE: we take the inode's blockdev's mapping's i_private_lock.  Which
  * assumes that all the buffers are against the blockdev.  Not true
  * for reiserfs.
  */
@@ -859,13 +859,13 @@ void invalidate_inode_buffers(struct inode *inode)
 {
 	if (inode_has_buffers(inode)) {
 		struct address_space *mapping = &inode->i_data;
-		struct list_head *list = &mapping->private_list;
-		struct address_space *buffer_mapping = mapping->private_data;
+		struct list_head *list = &mapping->i_private_list;
+		struct address_space *buffer_mapping = mapping->i_private_data;
 
-		spin_lock(&buffer_mapping->private_lock);
+		spin_lock(&buffer_mapping->i_private_lock);
 		while (!list_empty(list))
 			__remove_assoc_queue(BH_ENTRY(list->next));
-		spin_unlock(&buffer_mapping->private_lock);
+		spin_unlock(&buffer_mapping->i_private_lock);
 	}
 }
 EXPORT_SYMBOL(invalidate_inode_buffers);
@@ -882,10 +882,10 @@ int remove_inode_buffers(struct inode *inode)
 
 	if (inode_has_buffers(inode)) {
 		struct address_space *mapping = &inode->i_data;
-		struct list_head *list = &mapping->private_list;
-		struct address_space *buffer_mapping = mapping->private_data;
+		struct list_head *list = &mapping->i_private_list;
+		struct address_space *buffer_mapping = mapping->i_private_data;
 
-		spin_lock(&buffer_mapping->private_lock);
+		spin_lock(&buffer_mapping->i_private_lock);
 		while (!list_empty(list)) {
 			struct buffer_head *bh = BH_ENTRY(list->next);
 			if (buffer_dirty(bh)) {
@@ -894,7 +894,7 @@ int remove_inode_buffers(struct inode *inode)
 			}
 			__remove_assoc_queue(bh);
 		}
-		spin_unlock(&buffer_mapping->private_lock);
+		spin_unlock(&buffer_mapping->i_private_lock);
 	}
 	return ret;
 }
@@ -1064,11 +1064,11 @@ grow_dev_page(struct block_device *bdev, sector_t block,
 	 * lock to be atomic wrt __find_get_block(), which does not
 	 * run under the folio lock.
 	 */
-	spin_lock(&inode->i_mapping->private_lock);
+	spin_lock(&inode->i_mapping->i_private_lock);
 	link_dev_buffers(folio, bh);
 	end_block = folio_init_buffers(folio, bdev,
 			(sector_t)index << sizebits, size);
-	spin_unlock(&inode->i_mapping->private_lock);
+	spin_unlock(&inode->i_mapping->i_private_lock);
 done:
 	ret = (block < end_block) ? 1 : -ENXIO;
 failed:
@@ -1168,7 +1168,7 @@ __getblk_slow(struct block_device *bdev, sector_t block,
  * and then attach the address_space's inode to its superblock's dirty
  * inode list.
  *
- * mark_buffer_dirty() is atomic.  It takes bh->b_folio->mapping->private_lock,
+ * mark_buffer_dirty() is atomic.  It takes bh->b_folio->mapping->i_private_lock,
  * i_pages lock and mapping->host->i_lock.
  */
 void mark_buffer_dirty(struct buffer_head *bh)
@@ -1246,10 +1246,10 @@ void __bforget(struct buffer_head *bh)
 	if (bh->b_assoc_map) {
 		struct address_space *buffer_mapping = bh->b_folio->mapping;
 
-		spin_lock(&buffer_mapping->private_lock);
+		spin_lock(&buffer_mapping->i_private_lock);
 		list_del_init(&bh->b_assoc_buffers);
 		bh->b_assoc_map = NULL;
-		spin_unlock(&buffer_mapping->private_lock);
+		spin_unlock(&buffer_mapping->i_private_lock);
 	}
 	__brelse(bh);
 }
@@ -1638,7 +1638,7 @@ EXPORT_SYMBOL(block_invalidate_folio);
 
 /*
  * We attach and possibly dirty the buffers atomically wrt
- * block_dirty_folio() via private_lock.  try_to_free_buffers
+ * block_dirty_folio() via i_private_lock.  try_to_free_buffers
  * is already excluded via the folio lock.
  */
 struct buffer_head *create_empty_buffers(struct folio *folio,
@@ -1656,7 +1656,7 @@ struct buffer_head *create_empty_buffers(struct folio *folio,
 	} while (bh);
 	tail->b_this_page = head;
 
-	spin_lock(&folio->mapping->private_lock);
+	spin_lock(&folio->mapping->i_private_lock);
 	if (folio_test_uptodate(folio) || folio_test_dirty(folio)) {
 		bh = head;
 		do {
@@ -1668,7 +1668,7 @@ struct buffer_head *create_empty_buffers(struct folio *folio,
 		} while (bh != head);
 	}
 	folio_attach_private(folio, head);
-	spin_unlock(&folio->mapping->private_lock);
+	spin_unlock(&folio->mapping->i_private_lock);
 
 	return head;
 }
@@ -1715,7 +1715,7 @@ void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len)
 			if (!folio_buffers(folio))
 				continue;
 			/*
-			 * We use folio lock instead of bd_mapping->private_lock
+			 * We use folio lock instead of bd_mapping->i_private_lock
 			 * to pin buffers here since we can afford to sleep and
 			 * it scales better than a global spinlock lock.
 			 */
@@ -2883,7 +2883,7 @@ EXPORT_SYMBOL(sync_dirty_buffer);
  * are unused, and releases them if so.
  *
  * Exclusion against try_to_free_buffers may be obtained by either
- * locking the folio or by holding its mapping's private_lock.
+ * locking the folio or by holding its mapping's i_private_lock.
  *
  * If the folio is dirty but all the buffers are clean then we need to
  * be sure to mark the folio clean as well.  This is because the folio
@@ -2894,7 +2894,7 @@ EXPORT_SYMBOL(sync_dirty_buffer);
  * The same applies to regular filesystem folios: if all the buffers are
  * clean then we set the folio clean and proceed.  To do that, we require
  * total exclusion from block_dirty_folio().  That is obtained with
- * private_lock.
+ * i_private_lock.
  *
  * try_to_free_buffers() is non-blocking.
  */
@@ -2946,7 +2946,7 @@ bool try_to_free_buffers(struct folio *folio)
 		goto out;
 	}
 
-	spin_lock(&mapping->private_lock);
+	spin_lock(&mapping->i_private_lock);
 	ret = drop_buffers(folio, &buffers_to_free);
 
 	/*
@@ -2959,13 +2959,13 @@ bool try_to_free_buffers(struct folio *folio)
 	 * the folio's buffers clean.  We discover that here and clean
 	 * the folio also.
 	 *
-	 * private_lock must be held over this entire operation in order
+	 * i_private_lock must be held over this entire operation in order
 	 * to synchronise against block_dirty_folio and prevent the
 	 * dirty bit from being lost.
 	 */
 	if (ret)
 		folio_cancel_dirty(folio);
-	spin_unlock(&mapping->private_lock);
+	spin_unlock(&mapping->i_private_lock);
 out:
 	if (buffers_to_free) {
 		struct buffer_head *bh = buffers_to_free;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 61277f7f8722..0558c8c986d4 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1261,7 +1261,7 @@ static int write_end_fn(handle_t *handle, struct inode *inode,
  * We need to pick up the new inode size which generic_commit_write gave us
  * `file' can be NULL - eg, when called from page_symlink().
  *
- * ext4 never places buffers on inode->i_mapping->private_list.  metadata
+ * ext4 never places buffers on inode->i_mapping->i_private_list.  metadata
  * buffers are managed internally.
  */
 static int ext4_write_end(struct file *file,
@@ -3213,7 +3213,7 @@ static bool ext4_inode_datasync_dirty(struct inode *inode)
 	}
 
 	/* Any metadata buffers to write? */
-	if (!list_empty(&inode->i_mapping->private_list))
+	if (!list_empty(&inode->i_mapping->i_private_list))
 		return true;
 	return inode->i_state & I_DIRTY_DATASYNC;
 }
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index d6bf1f8c25dc..d8b619ed2f1e 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1213,7 +1213,7 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 		mapping->host = s->s_bdev->bd_inode;
 		mapping->flags = 0;
 		mapping_set_gfp_mask(mapping, GFP_NOFS);
-		mapping->private_data = NULL;
+		mapping->i_private_data = NULL;
 		mapping->writeback_index = 0;
 	}
 
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index b108c5d26839..00ce89bdf32c 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -117,7 +117,7 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
 	mapping->host = sb->s_bdev->bd_inode;
 	mapping->flags = 0;
 	mapping_set_gfp_mask(mapping, GFP_NOFS);
-	mapping->private_data = NULL;
+	mapping->i_private_data = NULL;
 	mapping->writeback_index = 0;
 
 	spin_lock_init(&sdp->sd_log_lock);
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index f757d4f7ad98..05609ab15cbc 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -686,7 +686,7 @@ static void hugetlbfs_evict_inode(struct inode *inode)
 	 * at inode creation time.  If this is a device special inode,
 	 * i_mapping may not point to the original address space.
 	 */
-	resv_map = (struct resv_map *)(&inode->i_data)->private_data;
+	resv_map = (struct resv_map *)(&inode->i_data)->i_private_data;
 	/* Only regular and link inodes have associated reserve maps */
 	if (resv_map)
 		resv_map_release(&resv_map->refs);
@@ -1000,7 +1000,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 				&hugetlbfs_i_mmap_rwsem_key);
 		inode->i_mapping->a_ops = &hugetlbfs_aops;
 		simple_inode_init_ts(inode);
-		inode->i_mapping->private_data = resv_map;
+		inode->i_mapping->i_private_data = resv_map;
 		info->seals = F_SEAL_SEAL;
 		switch (mode & S_IFMT) {
 		default:
diff --git a/fs/inode.c b/fs/inode.c
index edcd8a61975f..788aa0aa542b 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -209,7 +209,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 	atomic_set(&mapping->nr_thps, 0);
 #endif
 	mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE);
-	mapping->private_data = NULL;
+	mapping->i_private_data = NULL;
 	mapping->writeback_index = 0;
 	init_rwsem(&mapping->invalidate_lock);
 	lockdep_set_class_and_name(&mapping->invalidate_lock,
@@ -396,8 +396,8 @@ static void __address_space_init_once(struct address_space *mapping)
 {
 	xa_init_flags(&mapping->i_pages, XA_FLAGS_LOCK_IRQ | XA_FLAGS_ACCOUNT);
 	init_rwsem(&mapping->i_mmap_rwsem);
-	INIT_LIST_HEAD(&mapping->private_list);
-	spin_lock_init(&mapping->private_lock);
+	INIT_LIST_HEAD(&mapping->i_private_list);
+	spin_lock_init(&mapping->i_private_lock);
 	mapping->i_mmap = RB_ROOT_CACHED;
 }
 
@@ -618,7 +618,7 @@ void clear_inode(struct inode *inode)
 	 * nor even WARN_ON(!mapping_empty).
 	 */
 	xa_unlock_irq(&inode->i_data.i_pages);
-	BUG_ON(!list_empty(&inode->i_data.private_list));
+	BUG_ON(!list_empty(&inode->i_data.i_private_list));
 	BUG_ON(!(inode->i_state & I_FREEING));
 	BUG_ON(inode->i_state & I_CLEAR);
 	BUG_ON(!list_empty(&inode->i_wb_list));
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index b664caea8b4e..7248705faef4 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -192,13 +192,13 @@ static struct nfs_page *nfs_folio_find_private_request(struct folio *folio)
 
 	if (!folio_test_private(folio))
 		return NULL;
-	spin_lock(&mapping->private_lock);
+	spin_lock(&mapping->i_private_lock);
 	req = nfs_folio_private_request(folio);
 	if (req) {
 		WARN_ON_ONCE(req->wb_head != req);
 		kref_get(&req->wb_kref);
 	}
-	spin_unlock(&mapping->private_lock);
+	spin_unlock(&mapping->i_private_lock);
 	return req;
 }
 
@@ -769,13 +769,13 @@ static void nfs_inode_add_request(struct nfs_page *req)
 	 * Swap-space should not get truncated. Hence no need to plug the race
 	 * with invalidate/truncate.
 	 */
-	spin_lock(&mapping->private_lock);
+	spin_lock(&mapping->i_private_lock);
 	if (likely(!folio_test_swapcache(folio))) {
 		set_bit(PG_MAPPED, &req->wb_flags);
 		folio_set_private(folio);
 		folio->private = req;
 	}
-	spin_unlock(&mapping->private_lock);
+	spin_unlock(&mapping->i_private_lock);
 	atomic_long_inc(&nfsi->nrequests);
 	/* this a head request for a page group - mark it as having an
 	 * extra reference so sub groups can follow suit.
@@ -796,13 +796,13 @@ static void nfs_inode_remove_request(struct nfs_page *req)
 		struct folio *folio = nfs_page_to_folio(req->wb_head);
 		struct address_space *mapping = folio_file_mapping(folio);
 
-		spin_lock(&mapping->private_lock);
+		spin_lock(&mapping->i_private_lock);
 		if (likely(folio && !folio_test_swapcache(folio))) {
 			folio->private = NULL;
 			folio_clear_private(folio);
 			clear_bit(PG_MAPPED, &req->wb_head->wb_flags);
 		}
-		spin_unlock(&mapping->private_lock);
+		spin_unlock(&mapping->i_private_lock);
 	}
 
 	if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags)) {
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index f861f3a0bf5c..2ead36dfa2a3 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -214,7 +214,7 @@ static bool nilfs_dirty_folio(struct address_space *mapping,
 	/*
 	 * The page may not be locked, eg if called from try_to_unmap_one()
 	 */
-	spin_lock(&mapping->private_lock);
+	spin_lock(&mapping->i_private_lock);
 	head = folio_buffers(folio);
 	if (head) {
 		struct buffer_head *bh = head;
@@ -230,7 +230,7 @@ static bool nilfs_dirty_folio(struct address_space *mapping,
 	} else if (ret) {
 		nr_dirty = 1 << (folio_shift(folio) - inode->i_blkbits);
 	}
-	spin_unlock(&mapping->private_lock);
+	spin_unlock(&mapping->i_private_lock);
 
 	if (nr_dirty)
 		nilfs_set_file_dirty(inode, nr_dirty);
diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c
index 71e31e789b29..548f3b51aa5f 100644
--- a/fs/ntfs/aops.c
+++ b/fs/ntfs/aops.c
@@ -1690,7 +1690,7 @@ const struct address_space_operations ntfs_mst_aops = {
  *
  * If the page does not have buffers, we create them and set them uptodate.
  * The page may not be locked which is why we need to handle the buffers under
- * the mapping->private_lock.  Once the buffers are marked dirty we no longer
+ * the mapping->i_private_lock.  Once the buffers are marked dirty we no longer
  * need the lock since try_to_free_buffers() does not free dirty buffers.
  */
 void mark_ntfs_record_dirty(struct page *page, const unsigned int ofs) {
@@ -1702,11 +1702,11 @@ void mark_ntfs_record_dirty(struct page *page, const unsigned int ofs) {
 	BUG_ON(!PageUptodate(page));
 	end = ofs + ni->itype.index.block_size;
 	bh_size = VFS_I(ni)->i_sb->s_blocksize;
-	spin_lock(&mapping->private_lock);
+	spin_lock(&mapping->i_private_lock);
 	if (unlikely(!page_has_buffers(page))) {
-		spin_unlock(&mapping->private_lock);
+		spin_unlock(&mapping->i_private_lock);
 		bh = head = alloc_page_buffers(page, bh_size, true);
-		spin_lock(&mapping->private_lock);
+		spin_lock(&mapping->i_private_lock);
 		if (likely(!page_has_buffers(page))) {
 			struct buffer_head *tail;
 
@@ -1730,7 +1730,7 @@ void mark_ntfs_record_dirty(struct page *page, const unsigned int ofs) {
 			break;
 		set_buffer_dirty(bh);
 	} while ((bh = bh->b_this_page) != head);
-	spin_unlock(&mapping->private_lock);
+	spin_unlock(&mapping->i_private_lock);
 	filemap_dirty_folio(mapping, page_folio(page));
 	if (unlikely(buffers_to_free)) {
 		do {
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 98b7a7a8c42e..f171505940ff 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -463,9 +463,9 @@ extern const struct address_space_operations empty_aops;
  * @a_ops: Methods.
  * @flags: Error bits and flags (AS_*).
  * @wb_err: The most recent error which has occurred.
- * @private_lock: For use by the owner of the address_space.
- * @private_list: For use by the owner of the address_space.
- * @private_data: For use by the owner of the address_space.
+ * @i_private_lock: For use by the owner of the address_space.
+ * @i_private_list: For use by the owner of the address_space.
+ * @i_private_data: For use by the owner of the address_space.
  */
 struct address_space {
 	struct inode		*host;
@@ -484,9 +484,9 @@ struct address_space {
 	unsigned long		flags;
 	struct rw_semaphore	i_mmap_rwsem;
 	errseq_t		wb_err;
-	spinlock_t		private_lock;
-	struct list_head	private_list;
-	void			*private_data;
+	spinlock_t		i_private_lock;
+	struct list_head	i_private_list;
+	void *			i_private_data;
 } __attribute__((aligned(sizeof(long)))) __randomize_layout;
 	/*
 	 * On most architectures that alignment is already the case; but
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 1169ef2f2176..38c4477fda6a 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1141,7 +1141,7 @@ static inline struct resv_map *inode_resv_map(struct inode *inode)
 	 * The VERY common case is inode->mapping == &inode->i_data but,
 	 * this may not be true for device special inodes.
 	 */
-	return (struct resv_map *)(&inode->i_data)->private_data;
+	return (struct resv_map *)(&inode->i_data)->i_private_data;
 }
 
 static struct resv_map *vma_resv_map(struct vm_area_struct *vma)
diff --git a/mm/migrate.c b/mm/migrate.c
index 35a88334bb3c..377f55ebf7f4 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -746,7 +746,7 @@ static int __buffer_migrate_folio(struct address_space *mapping,
 
 recheck_buffers:
 		busy = false;
-		spin_lock(&mapping->private_lock);
+		spin_lock(&mapping->i_private_lock);
 		bh = head;
 		do {
 			if (atomic_read(&bh->b_count)) {
@@ -760,7 +760,7 @@ recheck_buffers:
 				rc = -EAGAIN;
 				goto unlock_buffers;
 			}
-			spin_unlock(&mapping->private_lock);
+			spin_unlock(&mapping->i_private_lock);
 			invalidate_bh_lrus();
 			invalidated = true;
 			goto recheck_buffers;
@@ -787,7 +787,7 @@ recheck_buffers:
 	rc = MIGRATEPAGE_SUCCESS;
 unlock_buffers:
 	if (check_refs)
-		spin_unlock(&mapping->private_lock);
+		spin_unlock(&mapping->i_private_lock);
 	bh = head;
 	do {
 		unlock_buffer(bh);
-- 
cgit v1.2.3


From f47507988145185aef5d0e7a0e28dbf6e7776f29 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Tue, 17 Oct 2023 22:05:23 +0200
Subject: thermal: ACPI: Move the ACPI thermal library to drivers/acpi/

The ACPI thermal library contains functions that can be used to
retrieve trip point temperature values through the platform firmware
for various types of trip points.  Each of these functions basically
evaluates a specific ACPI object, checks if the value produced by it
is reasonable and returns it (or THERMAL_TEMP_INVALID if anything
fails).

It made sense to hold it in drivers/thermal/ so long as it was only used
by the code in that directory, but since it is also going to be used by
the ACPI thermal driver located in drivers/acpi/, move it to the latter
in order to keep the code related to evaluating ACPI objects defined in
the specification proper together.

No intentional functional impact.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/Kconfig                          |   5 ++
 drivers/acpi/Makefile                         |   1 +
 drivers/acpi/thermal_lib.c                    | 116 ++++++++++++++++++++++++++
 drivers/thermal/Kconfig                       |   4 -
 drivers/thermal/Makefile                      |   1 -
 drivers/thermal/intel/Kconfig                 |   2 +-
 drivers/thermal/intel/int340x_thermal/Kconfig |   2 +-
 drivers/thermal/thermal_acpi.c                | 116 --------------------------
 include/linux/acpi.h                          |   7 ++
 include/linux/thermal.h                       |   7 --
 10 files changed, 131 insertions(+), 130 deletions(-)
 create mode 100644 drivers/acpi/thermal_lib.c
 delete mode 100644 drivers/thermal/thermal_acpi.c

(limited to 'include')

diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index f819e760ff19..6f2bfcf7645c 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -61,6 +61,10 @@ config ACPI_CCA_REQUIRED
 config ACPI_TABLE_LIB
 	bool
 
+config ACPI_THERMAL_LIB
+       depends on THERMAL
+       bool
+
 config ACPI_DEBUGGER
 	bool "AML debugger interface"
 	select ACPI_DEBUG
@@ -327,6 +331,7 @@ config ACPI_THERMAL
 	tristate "Thermal Zone"
 	depends on ACPI_PROCESSOR
 	select THERMAL
+	select ACPI_THERMAL_LIB
 	default y
 	help
 	  This driver supports ACPI thermal zones.  Most mobile and
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index eaa09bf52f17..2a52083704e6 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -89,6 +89,7 @@ obj-$(CONFIG_ACPI_TAD)		+= acpi_tad.o
 obj-$(CONFIG_ACPI_PCI_SLOT)	+= pci_slot.o
 obj-$(CONFIG_ACPI_PROCESSOR)	+= processor.o
 obj-$(CONFIG_ACPI)		+= container.o
+obj-$(CONFIG_ACPI_THERMAL_LIB)	+= thermal_lib.o
 obj-$(CONFIG_ACPI_THERMAL)	+= thermal.o
 obj-$(CONFIG_ACPI_PLATFORM_PROFILE) 	+= platform_profile.o
 obj-$(CONFIG_ACPI_NFIT)		+= nfit/
diff --git a/drivers/acpi/thermal_lib.c b/drivers/acpi/thermal_lib.c
new file mode 100644
index 000000000000..43eaf0f2ff49
--- /dev/null
+++ b/drivers/acpi/thermal_lib.c
@@ -0,0 +1,116 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2023 Linaro Limited
+ * Copyright 2023 Intel Corporation
+ *
+ * Library routines for populating a generic thermal trip point structure
+ * with data obtained by evaluating a specific object in the ACPI Namespace.
+ */
+#include <linux/acpi.h>
+#include <linux/units.h>
+#include <linux/thermal.h>
+
+/*
+ * Minimum temperature for full military grade is 218°K (-55°C) and
+ * max temperature is 448°K (175°C). We can consider those values as
+ * the boundaries for the [trips] temperature returned by the
+ * firmware. Any values out of these boundaries may be considered
+ * bogus and we can assume the firmware has no data to provide.
+ */
+#define TEMP_MIN_DECIK	2180
+#define TEMP_MAX_DECIK	4480
+
+static int thermal_acpi_trip_temp(struct acpi_device *adev, char *obj_name,
+				  int *ret_temp)
+{
+	unsigned long long temp;
+	acpi_status status;
+
+	status = acpi_evaluate_integer(adev->handle, obj_name, NULL, &temp);
+	if (ACPI_FAILURE(status)) {
+		acpi_handle_debug(adev->handle, "%s evaluation failed\n", obj_name);
+		return -ENODATA;
+	}
+
+	if (temp >= TEMP_MIN_DECIK && temp <= TEMP_MAX_DECIK) {
+		*ret_temp = deci_kelvin_to_millicelsius(temp);
+	} else {
+		acpi_handle_debug(adev->handle, "%s result %llu out of range\n",
+				  obj_name, temp);
+		*ret_temp = THERMAL_TEMP_INVALID;
+	}
+
+	return 0;
+}
+
+/**
+ * thermal_acpi_active_trip_temp - Retrieve active trip point temperature
+ * @adev: Target thermal zone ACPI device object.
+ * @id: Active cooling level (0 - 9).
+ * @ret_temp: Address to store the retrieved temperature value on success.
+ *
+ * Evaluate the _ACx object for the thermal zone represented by @adev to obtain
+ * the temperature of the active cooling trip point corresponding to the active
+ * cooling level given by @id.
+ *
+ * Return 0 on success or a negative error value on failure.
+ */
+int thermal_acpi_active_trip_temp(struct acpi_device *adev, int id, int *ret_temp)
+{
+	char obj_name[] = {'_', 'A', 'C', '0' + id, '\0'};
+
+	if (id < 0 || id > 9)
+		return -EINVAL;
+
+	return thermal_acpi_trip_temp(adev, obj_name, ret_temp);
+}
+EXPORT_SYMBOL_GPL(thermal_acpi_active_trip_temp);
+
+/**
+ * thermal_acpi_passive_trip_temp - Retrieve passive trip point temperature
+ * @adev: Target thermal zone ACPI device object.
+ * @ret_temp: Address to store the retrieved temperature value on success.
+ *
+ * Evaluate the _PSV object for the thermal zone represented by @adev to obtain
+ * the temperature of the passive cooling trip point.
+ *
+ * Return 0 on success or -ENODATA on failure.
+ */
+int thermal_acpi_passive_trip_temp(struct acpi_device *adev, int *ret_temp)
+{
+	return thermal_acpi_trip_temp(adev, "_PSV", ret_temp);
+}
+EXPORT_SYMBOL_GPL(thermal_acpi_passive_trip_temp);
+
+/**
+ * thermal_acpi_hot_trip_temp - Retrieve hot trip point temperature
+ * @adev: Target thermal zone ACPI device object.
+ * @ret_temp: Address to store the retrieved temperature value on success.
+ *
+ * Evaluate the _HOT object for the thermal zone represented by @adev to obtain
+ * the temperature of the trip point at which the system is expected to be put
+ * into the S4 sleep state.
+ *
+ * Return 0 on success or -ENODATA on failure.
+ */
+int thermal_acpi_hot_trip_temp(struct acpi_device *adev, int *ret_temp)
+{
+	return thermal_acpi_trip_temp(adev, "_HOT", ret_temp);
+}
+EXPORT_SYMBOL_GPL(thermal_acpi_hot_trip_temp);
+
+/**
+ * thermal_acpi_critical_trip_temp - Retrieve critical trip point temperature
+ * @adev: Target thermal zone ACPI device object.
+ * @ret_temp: Address to store the retrieved temperature value on success.
+ *
+ * Evaluate the _CRT object for the thermal zone represented by @adev to obtain
+ * the temperature of the critical cooling trip point.
+ *
+ * Return 0 on success or -ENODATA on failure.
+ */
+int thermal_acpi_critical_trip_temp(struct acpi_device *adev, int *ret_temp)
+{
+	return thermal_acpi_trip_temp(adev, "_CRT", ret_temp);
+}
+EXPORT_SYMBOL_GPL(thermal_acpi_critical_trip_temp);
diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index c81a00fbca7d..59883502eff4 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -76,10 +76,6 @@ config THERMAL_OF
 	  Say 'Y' here if you need to build thermal infrastructure
 	  based on device tree.
 
-config THERMAL_ACPI
-       depends on ACPI
-       bool
-
 config THERMAL_WRITABLE_TRIPS
 	bool "Enable writable trip points"
 	help
diff --git a/drivers/thermal/Makefile b/drivers/thermal/Makefile
index c934cab309ae..a8318d671036 100644
--- a/drivers/thermal/Makefile
+++ b/drivers/thermal/Makefile
@@ -13,7 +13,6 @@ thermal_sys-$(CONFIG_THERMAL_NETLINK)		+= thermal_netlink.o
 # interface to/from other layers providing sensors
 thermal_sys-$(CONFIG_THERMAL_HWMON)		+= thermal_hwmon.o
 thermal_sys-$(CONFIG_THERMAL_OF)		+= thermal_of.o
-thermal_sys-$(CONFIG_THERMAL_ACPI)		+= thermal_acpi.o
 
 # governors
 CFLAGS_gov_power_allocator.o			:= -I$(src)
diff --git a/drivers/thermal/intel/Kconfig b/drivers/thermal/intel/Kconfig
index ecd7e07eece0..b43953b5539f 100644
--- a/drivers/thermal/intel/Kconfig
+++ b/drivers/thermal/intel/Kconfig
@@ -85,7 +85,7 @@ config INTEL_BXT_PMIC_THERMAL
 config INTEL_PCH_THERMAL
 	tristate "Intel PCH Thermal Reporting Driver"
 	depends on X86 && PCI
-	select THERMAL_ACPI if ACPI
+	select ACPI_THERMAL_LIB if ACPI
 	help
 	  Enable this to support thermal reporting on certain intel PCHs.
 	  Thermal reporting device will provide temperature reading,
diff --git a/drivers/thermal/intel/int340x_thermal/Kconfig b/drivers/thermal/intel/int340x_thermal/Kconfig
index 300ea53e9b33..e76b13e44d03 100644
--- a/drivers/thermal/intel/int340x_thermal/Kconfig
+++ b/drivers/thermal/intel/int340x_thermal/Kconfig
@@ -9,7 +9,7 @@ config INT340X_THERMAL
 	select THERMAL_GOV_USER_SPACE
 	select ACPI_THERMAL_REL
 	select ACPI_FAN
-	select THERMAL_ACPI
+	select ACPI_THERMAL_LIB
 	select INTEL_SOC_DTS_IOSF_CORE
 	select INTEL_TCC
 	select PROC_THERMAL_MMIO_RAPL if POWERCAP
diff --git a/drivers/thermal/thermal_acpi.c b/drivers/thermal/thermal_acpi.c
deleted file mode 100644
index 43eaf0f2ff49..000000000000
--- a/drivers/thermal/thermal_acpi.c
+++ /dev/null
@@ -1,116 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright 2023 Linaro Limited
- * Copyright 2023 Intel Corporation
- *
- * Library routines for populating a generic thermal trip point structure
- * with data obtained by evaluating a specific object in the ACPI Namespace.
- */
-#include <linux/acpi.h>
-#include <linux/units.h>
-#include <linux/thermal.h>
-
-/*
- * Minimum temperature for full military grade is 218°K (-55°C) and
- * max temperature is 448°K (175°C). We can consider those values as
- * the boundaries for the [trips] temperature returned by the
- * firmware. Any values out of these boundaries may be considered
- * bogus and we can assume the firmware has no data to provide.
- */
-#define TEMP_MIN_DECIK	2180
-#define TEMP_MAX_DECIK	4480
-
-static int thermal_acpi_trip_temp(struct acpi_device *adev, char *obj_name,
-				  int *ret_temp)
-{
-	unsigned long long temp;
-	acpi_status status;
-
-	status = acpi_evaluate_integer(adev->handle, obj_name, NULL, &temp);
-	if (ACPI_FAILURE(status)) {
-		acpi_handle_debug(adev->handle, "%s evaluation failed\n", obj_name);
-		return -ENODATA;
-	}
-
-	if (temp >= TEMP_MIN_DECIK && temp <= TEMP_MAX_DECIK) {
-		*ret_temp = deci_kelvin_to_millicelsius(temp);
-	} else {
-		acpi_handle_debug(adev->handle, "%s result %llu out of range\n",
-				  obj_name, temp);
-		*ret_temp = THERMAL_TEMP_INVALID;
-	}
-
-	return 0;
-}
-
-/**
- * thermal_acpi_active_trip_temp - Retrieve active trip point temperature
- * @adev: Target thermal zone ACPI device object.
- * @id: Active cooling level (0 - 9).
- * @ret_temp: Address to store the retrieved temperature value on success.
- *
- * Evaluate the _ACx object for the thermal zone represented by @adev to obtain
- * the temperature of the active cooling trip point corresponding to the active
- * cooling level given by @id.
- *
- * Return 0 on success or a negative error value on failure.
- */
-int thermal_acpi_active_trip_temp(struct acpi_device *adev, int id, int *ret_temp)
-{
-	char obj_name[] = {'_', 'A', 'C', '0' + id, '\0'};
-
-	if (id < 0 || id > 9)
-		return -EINVAL;
-
-	return thermal_acpi_trip_temp(adev, obj_name, ret_temp);
-}
-EXPORT_SYMBOL_GPL(thermal_acpi_active_trip_temp);
-
-/**
- * thermal_acpi_passive_trip_temp - Retrieve passive trip point temperature
- * @adev: Target thermal zone ACPI device object.
- * @ret_temp: Address to store the retrieved temperature value on success.
- *
- * Evaluate the _PSV object for the thermal zone represented by @adev to obtain
- * the temperature of the passive cooling trip point.
- *
- * Return 0 on success or -ENODATA on failure.
- */
-int thermal_acpi_passive_trip_temp(struct acpi_device *adev, int *ret_temp)
-{
-	return thermal_acpi_trip_temp(adev, "_PSV", ret_temp);
-}
-EXPORT_SYMBOL_GPL(thermal_acpi_passive_trip_temp);
-
-/**
- * thermal_acpi_hot_trip_temp - Retrieve hot trip point temperature
- * @adev: Target thermal zone ACPI device object.
- * @ret_temp: Address to store the retrieved temperature value on success.
- *
- * Evaluate the _HOT object for the thermal zone represented by @adev to obtain
- * the temperature of the trip point at which the system is expected to be put
- * into the S4 sleep state.
- *
- * Return 0 on success or -ENODATA on failure.
- */
-int thermal_acpi_hot_trip_temp(struct acpi_device *adev, int *ret_temp)
-{
-	return thermal_acpi_trip_temp(adev, "_HOT", ret_temp);
-}
-EXPORT_SYMBOL_GPL(thermal_acpi_hot_trip_temp);
-
-/**
- * thermal_acpi_critical_trip_temp - Retrieve critical trip point temperature
- * @adev: Target thermal zone ACPI device object.
- * @ret_temp: Address to store the retrieved temperature value on success.
- *
- * Evaluate the _CRT object for the thermal zone represented by @adev to obtain
- * the temperature of the critical cooling trip point.
- *
- * Return 0 on success or -ENODATA on failure.
- */
-int thermal_acpi_critical_trip_temp(struct acpi_device *adev, int *ret_temp)
-{
-	return thermal_acpi_trip_temp(adev, "_CRT", ret_temp);
-}
-EXPORT_SYMBOL_GPL(thermal_acpi_critical_trip_temp);
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 54189e0e5f41..b63d7811c728 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -424,6 +424,13 @@ extern int acpi_blacklisted(void);
 extern void acpi_osi_setup(char *str);
 extern bool acpi_osi_is_win8(void);
 
+#ifdef CONFIG_ACPI_THERMAL_LIB
+int thermal_acpi_active_trip_temp(struct acpi_device *adev, int id, int *ret_temp);
+int thermal_acpi_passive_trip_temp(struct acpi_device *adev, int *ret_temp);
+int thermal_acpi_hot_trip_temp(struct acpi_device *adev, int *ret_temp);
+int thermal_acpi_critical_trip_temp(struct acpi_device *adev, int *ret_temp);
+#endif
+
 #ifdef CONFIG_ACPI_NUMA
 int acpi_map_pxm_to_node(int pxm);
 int acpi_get_node(acpi_handle handle);
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index cee814d5d1ac..35f620059456 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -294,13 +294,6 @@ int thermal_zone_get_num_trips(struct thermal_zone_device *tz);
 
 int thermal_zone_get_crit_temp(struct thermal_zone_device *tz, int *temp);
 
-#ifdef CONFIG_THERMAL_ACPI
-int thermal_acpi_active_trip_temp(struct acpi_device *adev, int id, int *ret_temp);
-int thermal_acpi_passive_trip_temp(struct acpi_device *adev, int *ret_temp);
-int thermal_acpi_hot_trip_temp(struct acpi_device *adev, int *ret_temp);
-int thermal_acpi_critical_trip_temp(struct acpi_device *adev, int *ret_temp);
-#endif
-
 #ifdef CONFIG_THERMAL
 struct thermal_zone_device *thermal_zone_device_register_with_trips(
 					const char *type,
-- 
cgit v1.2.3


From 5032c607e886e0c40749a05d37b835c1757d38ff Mon Sep 17 00:00:00 2001
From: Haridhar Kalvala <haridhar.kalvala@intel.com>
Date: Mon, 20 Nov 2023 17:07:31 +0530
Subject: drm/i915: ATS-M device ID update

ATS-M device ID update.

BSpec: 44477

Signed-off-by: Haridhar Kalvala <haridhar.kalvala@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231120113731.1570589-1-haridhar.kalvala@intel.com
---
 include/drm/i915_pciids.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h
index 1c9ea6ab3eb9..fcf1849aa47c 100644
--- a/include/drm/i915_pciids.h
+++ b/include/drm/i915_pciids.h
@@ -738,7 +738,8 @@
 	INTEL_DG2_G12_IDS(info)
 
 #define INTEL_ATS_M150_IDS(info) \
-	INTEL_VGA_DEVICE(0x56C0, info)
+	INTEL_VGA_DEVICE(0x56C0, info), \
+	INTEL_VGA_DEVICE(0x56C2, info)
 
 #define INTEL_ATS_M75_IDS(info) \
 	INTEL_VGA_DEVICE(0x56C1, info)
-- 
cgit v1.2.3


From 5027ec19f1049a07df5b0a37b1f462514cf2724b Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 20 Nov 2023 16:00:34 -0800
Subject: net: page_pool: split the page_pool_params into fast and slow

struct page_pool is rather performance critical and we use
16B of the first cache line to store 2 pointers used only
by test code. Future patches will add more informational
(non-fast path) attributes.

It's convenient for the user of the API to not have to worry
which fields are fast and which are slow path. Use struct
groups to split the params into the two categories internally.

Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Reviewed-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Link: https://lore.kernel.org/r/20231121000048.789613-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/page_pool/types.h | 31 +++++++++++++++++++------------
 net/core/page_pool.c          |  7 ++++---
 2 files changed, 23 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index 6fc5134095ed..23950fcc4eca 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -54,18 +54,22 @@ struct pp_alloc_cache {
  * @offset:	DMA sync address offset for PP_FLAG_DMA_SYNC_DEV
  */
 struct page_pool_params {
-	unsigned int	flags;
-	unsigned int	order;
-	unsigned int	pool_size;
-	int		nid;
-	struct device	*dev;
-	struct napi_struct *napi;
-	enum dma_data_direction dma_dir;
-	unsigned int	max_len;
-	unsigned int	offset;
+	struct_group_tagged(page_pool_params_fast, fast,
+		unsigned int	flags;
+		unsigned int	order;
+		unsigned int	pool_size;
+		int		nid;
+		struct device	*dev;
+		struct napi_struct *napi;
+		enum dma_data_direction dma_dir;
+		unsigned int	max_len;
+		unsigned int	offset;
+	);
+	struct_group_tagged(page_pool_params_slow, slow,
 /* private: used by test code only */
-	void (*init_callback)(struct page *page, void *arg);
-	void *init_arg;
+		void (*init_callback)(struct page *page, void *arg);
+		void *init_arg;
+	);
 };
 
 #ifdef CONFIG_PAGE_POOL_STATS
@@ -119,7 +123,7 @@ struct page_pool_stats {
 #endif
 
 struct page_pool {
-	struct page_pool_params p;
+	struct page_pool_params_fast p;
 
 	long frag_users;
 	struct page *frag_page;
@@ -178,6 +182,9 @@ struct page_pool {
 	refcount_t user_cnt;
 
 	u64 destroy_cnt;
+
+	/* Slow/Control-path information follows */
+	struct page_pool_params_slow slow;
 };
 
 struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp);
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index dec544337236..ab22a2fdae57 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -173,7 +173,8 @@ static int page_pool_init(struct page_pool *pool,
 {
 	unsigned int ring_qsize = 1024; /* Default */
 
-	memcpy(&pool->p, params, sizeof(pool->p));
+	memcpy(&pool->p, &params->fast, sizeof(pool->p));
+	memcpy(&pool->slow, &params->slow, sizeof(pool->slow));
 
 	/* Validate only known flags were used */
 	if (pool->p.flags & ~(PP_FLAG_ALL))
@@ -388,8 +389,8 @@ static void page_pool_set_pp_info(struct page_pool *pool,
 	 * the overhead is negligible.
 	 */
 	page_pool_fragment_page(page, 1);
-	if (pool->p.init_callback)
-		pool->p.init_callback(page, pool->p.init_arg);
+	if (pool->slow.init_callback)
+		pool->slow.init_callback(page, pool->slow.init_arg);
 }
 
 static void page_pool_clear_pp_info(struct page *page)
-- 
cgit v1.2.3


From 2da0cac1e9494f34c5a3438e5c4c7e662e1b7445 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 20 Nov 2023 16:00:35 -0800
Subject: net: page_pool: avoid touching slow on the fastpath

To fully benefit from previous commit add one byte of state
in the first cache line recording if we need to look at
the slow part.

The packing isn't all that impressive right now, we create
a 7B hole. I'm expecting Olek's rework will reshuffle this,
anyway.

Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Reviewed-by: Mina Almasry <almasrymina@google.com>
Link: https://lore.kernel.org/r/20231121000048.789613-3-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/page_pool/types.h | 2 ++
 net/core/page_pool.c          | 4 +++-
 2 files changed, 5 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index 23950fcc4eca..e1bb92c192de 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -125,6 +125,8 @@ struct page_pool_stats {
 struct page_pool {
 	struct page_pool_params_fast p;
 
+	bool has_init_callback;
+
 	long frag_users;
 	struct page *frag_page;
 	unsigned int frag_offset;
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index ab22a2fdae57..df2a06d7da52 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -212,6 +212,8 @@ static int page_pool_init(struct page_pool *pool,
 		 */
 	}
 
+	pool->has_init_callback = !!pool->slow.init_callback;
+
 #ifdef CONFIG_PAGE_POOL_STATS
 	pool->recycle_stats = alloc_percpu(struct page_pool_recycle_stats);
 	if (!pool->recycle_stats)
@@ -389,7 +391,7 @@ static void page_pool_set_pp_info(struct page_pool *pool,
 	 * the overhead is negligible.
 	 */
 	page_pool_fragment_page(page, 1);
-	if (pool->slow.init_callback)
+	if (pool->has_init_callback)
 		pool->slow.init_callback(page, pool->slow.init_arg);
 }
 
-- 
cgit v1.2.3


From 35732699f5d2922ff674e711e566cf44a4bd86d2 Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Wed, 22 Nov 2023 08:33:53 -0700
Subject: ACPI: Fix ARM32 platforms compile issue introduced by fw_table
 changes

Linus reported that:
After commit a103f46633fd the kernel stopped compiling for
several ARM32 platforms that I am building with a bare metal
compiler. Bare metal compilers (arm-none-eabi-) don't
define __linux__.

This is because the header <acpi/platform/acenv.h> is now
in the include path for <linux/irq.h>:

  CC      arch/arm/kernel/irq.o
  CC      kernel/sysctl.o
  CC      crypto/api.o
In file included from ../include/acpi/acpi.h:22,
                 from ../include/linux/fw_table.h:29,
                 from ../include/linux/acpi.h:18,
                 from ../include/linux/irqchip.h:14,
                 from ../arch/arm/kernel/irq.c:25:
../include/acpi/platform/acenv.h:218:2: error: #error Unknown target environment
  218 | #error Unknown target environment
      |  ^~~~~

The issue is caused by the introducing of splitting out the ACPI code to
support the new generic fw_table code.

Rafael suggested [1] moving the fw_table.h include in linux/acpi.h to below
the linux/mutex.h. Remove the two includes in fw_table.h. Replace
linux/fw_table.h include in fw_table.c with linux/acpi.h.

Link: https://lore.kernel.org/linux-acpi/CAJZ5v0idWdJq3JSqQWLG5q+b+b=zkEdWR55rGYEoxh7R6N8kFQ@mail.gmail.com/
Fixes: a103f46633fd ("acpi: Move common tables helper functions to common lib")
Closes: https://lore.kernel.org/linux-acpi/20231114-arm-build-bug-v1-1-458745fe32a4@linaro.org/
Reported-by: Linus Walleij <linus.walleij@linaro.org>
Suggested-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Tested-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/acpi.h     | 22 +++++++++++-----------
 include/linux/fw_table.h |  3 ---
 lib/fw_table.c           |  2 +-
 3 files changed, 12 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 54189e0e5f41..4db54e928b36 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -15,7 +15,6 @@
 #include <linux/mod_devicetable.h>
 #include <linux/property.h>
 #include <linux/uuid.h>
-#include <linux/fw_table.h>
 
 struct irq_domain;
 struct irq_domain_ops;
@@ -25,22 +24,13 @@ struct irq_domain_ops;
 #endif
 #include <acpi/acpi.h>
 
-#ifdef CONFIG_ACPI_TABLE_LIB
-#define EXPORT_SYMBOL_ACPI_LIB(x) EXPORT_SYMBOL_NS_GPL(x, ACPI)
-#define __init_or_acpilib
-#define __initdata_or_acpilib
-#else
-#define EXPORT_SYMBOL_ACPI_LIB(x)
-#define __init_or_acpilib __init
-#define __initdata_or_acpilib __initdata
-#endif
-
 #ifdef	CONFIG_ACPI
 
 #include <linux/list.h>
 #include <linux/dynamic_debug.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/fw_table.h>
 
 #include <acpi/acpi_bus.h>
 #include <acpi/acpi_drivers.h>
@@ -48,6 +38,16 @@ struct irq_domain_ops;
 #include <acpi/acpi_io.h>
 #include <asm/acpi.h>
 
+#ifdef CONFIG_ACPI_TABLE_LIB
+#define EXPORT_SYMBOL_ACPI_LIB(x) EXPORT_SYMBOL_NS_GPL(x, ACPI)
+#define __init_or_acpilib
+#define __initdata_or_acpilib
+#else
+#define EXPORT_SYMBOL_ACPI_LIB(x)
+#define __init_or_acpilib __init
+#define __initdata_or_acpilib __initdata
+#endif
+
 static inline acpi_handle acpi_device_handle(struct acpi_device *adev)
 {
 	return adev ? adev->handle : NULL;
diff --git a/include/linux/fw_table.h b/include/linux/fw_table.h
index ff8fa58d5818..ca49947f0a77 100644
--- a/include/linux/fw_table.h
+++ b/include/linux/fw_table.h
@@ -25,9 +25,6 @@ struct acpi_subtable_proc {
 	int count;
 };
 
-#include <linux/acpi.h>
-#include <acpi/acpi.h>
-
 union acpi_subtable_headers {
 	struct acpi_subtable_header common;
 	struct acpi_hmat_structure hmat;
diff --git a/lib/fw_table.c b/lib/fw_table.c
index b51f30a28e47..294df54e33b6 100644
--- a/lib/fw_table.c
+++ b/lib/fw_table.c
@@ -7,7 +7,7 @@
  *  Copyright (C) 2023 Intel Corp.
  */
 #include <linux/errno.h>
-#include <linux/fw_table.h>
+#include <linux/acpi.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
-- 
cgit v1.2.3


From 21f4c443731fdb064c0dd31a743aafd0b075156c Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Mon, 20 Nov 2023 18:47:20 +0100
Subject: soundwire: stream: constify sdw_port_config when adding devices

sdw_stream_add_master() and sdw_stream_add_slave() do not modify
contents of passed sdw_port_config, so it can be made const for code
safety and as documentation of expected usage.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Link: https://lore.kernel.org/r/20231120174720.239610-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/stream.c    | 10 +++++-----
 include/linux/soundwire/sdw.h |  6 +++---
 2 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c
index 69719b335bcb..9dc6399f206a 100644
--- a/drivers/soundwire/stream.c
+++ b/drivers/soundwire/stream.c
@@ -897,7 +897,7 @@ static struct sdw_port_runtime *sdw_port_alloc(struct list_head *port_list)
 }
 
 static int sdw_port_config(struct sdw_port_runtime *p_rt,
-			   struct sdw_port_config *port_config,
+			   const struct sdw_port_config *port_config,
 			   int port_index)
 {
 	p_rt->ch_mask = port_config[port_index].ch_mask;
@@ -970,7 +970,7 @@ static int sdw_slave_port_is_valid_range(struct device *dev, int num)
 
 static int sdw_slave_port_config(struct sdw_slave *slave,
 				 struct sdw_slave_runtime *s_rt,
-				 struct sdw_port_config *port_config)
+				 const struct sdw_port_config *port_config)
 {
 	struct sdw_port_runtime *p_rt;
 	int ret;
@@ -1026,7 +1026,7 @@ static int sdw_master_port_alloc(struct sdw_master_runtime *m_rt,
 }
 
 static int sdw_master_port_config(struct sdw_master_runtime *m_rt,
-				  struct sdw_port_config *port_config)
+				  const struct sdw_port_config *port_config)
 {
 	struct sdw_port_runtime *p_rt;
 	int ret;
@@ -1861,7 +1861,7 @@ EXPORT_SYMBOL(sdw_release_stream);
  */
 int sdw_stream_add_master(struct sdw_bus *bus,
 			  struct sdw_stream_config *stream_config,
-			  struct sdw_port_config *port_config,
+			  const struct sdw_port_config *port_config,
 			  unsigned int num_ports,
 			  struct sdw_stream_runtime *stream)
 {
@@ -1981,7 +1981,7 @@ EXPORT_SYMBOL(sdw_stream_remove_master);
  */
 int sdw_stream_add_slave(struct sdw_slave *slave,
 			 struct sdw_stream_config *stream_config,
-			 struct sdw_port_config *port_config,
+			 const struct sdw_port_config *port_config,
 			 unsigned int num_ports,
 			 struct sdw_stream_runtime *stream)
 {
diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 4f3d14bb1538..904004d8b562 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -1040,7 +1040,7 @@ int sdw_compute_params(struct sdw_bus *bus);
 
 int sdw_stream_add_master(struct sdw_bus *bus,
 		struct sdw_stream_config *stream_config,
-		struct sdw_port_config *port_config,
+		const struct sdw_port_config *port_config,
 		unsigned int num_ports,
 		struct sdw_stream_runtime *stream);
 int sdw_stream_remove_master(struct sdw_bus *bus,
@@ -1062,7 +1062,7 @@ void sdw_extract_slave_id(struct sdw_bus *bus, u64 addr, struct sdw_slave_id *id
 
 int sdw_stream_add_slave(struct sdw_slave *slave,
 			 struct sdw_stream_config *stream_config,
-			 struct sdw_port_config *port_config,
+			 const struct sdw_port_config *port_config,
 			 unsigned int num_ports,
 			 struct sdw_stream_runtime *stream);
 int sdw_stream_remove_slave(struct sdw_slave *slave,
@@ -1084,7 +1084,7 @@ int sdw_update_no_pm(struct sdw_slave *slave, u32 addr, u8 mask, u8 val);
 
 static inline int sdw_stream_add_slave(struct sdw_slave *slave,
 				       struct sdw_stream_config *stream_config,
-				       struct sdw_port_config *port_config,
+				       const struct sdw_port_config *port_config,
 				       unsigned int num_ports,
 				       struct sdw_stream_runtime *stream)
 {
-- 
cgit v1.2.3


From 57b79ac9f43dc71fc8b55af51d1c9f469cb7a0de Mon Sep 17 00:00:00 2001
From: Hector Martin <marcan@marcan.st>
Date: Thu, 5 May 2022 01:25:16 +0900
Subject: soc: apple: rtkit: Get rid of apple_rtkit_send_message_wait

It is fundamentally broken and has no users. Just remove it.

Acked-by: Eric Curtin <ecurtin@redhat.com>
Acked-by: Neal Gompa <neal@gompa.dev>
Acked-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Signed-off-by: Hector Martin <marcan@marcan.st>
---
 drivers/soc/apple/rtkit.c       | 32 --------------------------------
 include/linux/soc/apple/rtkit.h | 18 ------------------
 2 files changed, 50 deletions(-)

(limited to 'include')

diff --git a/drivers/soc/apple/rtkit.c b/drivers/soc/apple/rtkit.c
index d9f19dc99da5..7c9b9f25bbc1 100644
--- a/drivers/soc/apple/rtkit.c
+++ b/drivers/soc/apple/rtkit.c
@@ -641,38 +641,6 @@ int apple_rtkit_send_message(struct apple_rtkit *rtk, u8 ep, u64 message,
 }
 EXPORT_SYMBOL_GPL(apple_rtkit_send_message);
 
-int apple_rtkit_send_message_wait(struct apple_rtkit *rtk, u8 ep, u64 message,
-				  unsigned long timeout, bool atomic)
-{
-	DECLARE_COMPLETION_ONSTACK(completion);
-	int ret;
-	long t;
-
-	ret = apple_rtkit_send_message(rtk, ep, message, &completion, atomic);
-	if (ret < 0)
-		return ret;
-
-	if (atomic) {
-		ret = mbox_flush(rtk->mbox_chan, timeout);
-		if (ret < 0)
-			return ret;
-
-		if (try_wait_for_completion(&completion))
-			return 0;
-
-		return -ETIME;
-	} else {
-		t = wait_for_completion_interruptible_timeout(
-			&completion, msecs_to_jiffies(timeout));
-		if (t < 0)
-			return t;
-		else if (t == 0)
-			return -ETIME;
-		return 0;
-	}
-}
-EXPORT_SYMBOL_GPL(apple_rtkit_send_message_wait);
-
 int apple_rtkit_poll(struct apple_rtkit *rtk)
 {
 	return mbox_client_peek_data(rtk->mbox_chan);
diff --git a/include/linux/soc/apple/rtkit.h b/include/linux/soc/apple/rtkit.h
index fc456f75c131..8c9ca857ccf6 100644
--- a/include/linux/soc/apple/rtkit.h
+++ b/include/linux/soc/apple/rtkit.h
@@ -160,24 +160,6 @@ int apple_rtkit_start_ep(struct apple_rtkit *rtk, u8 endpoint);
 int apple_rtkit_send_message(struct apple_rtkit *rtk, u8 ep, u64 message,
 			     struct completion *completion, bool atomic);
 
-/*
- * Send a message to the given endpoint and wait until it has been submitted
- * to the hardware FIFO.
- * Will return zero on success and a negative error code on failure
- * (e.g. -ETIME when the message couldn't be written within the given
- * timeout)
- *
- * @rtk:            RTKit reference
- * @ep:             target endpoint
- * @message:        message to be sent
- * @timeout:        timeout in milliseconds to allow the message transmission
- *                  to be completed
- * @atomic:         if set to true this function can be called from atomic
- *                  context.
- */
-int apple_rtkit_send_message_wait(struct apple_rtkit *rtk, u8 ep, u64 message,
-				  unsigned long timeout, bool atomic);
-
 /*
  * Process incoming messages in atomic context.
  * This only guarantees that messages arrive as far as the recv_message_early
-- 
cgit v1.2.3


From 143897c4fa976d02bfafe5ae32b9ffc60dc6145a Mon Sep 17 00:00:00 2001
From: Hector Martin <marcan@marcan.st>
Date: Tue, 14 Mar 2023 19:47:32 +0900
Subject: mailbox: apple: Delete driver

This driver is now orphaned and superseded by
drivers/soc/apple/mailbox.c.

Acked-by: Eric Curtin <ecurtin@redhat.com>
Acked-by: Neal Gompa <neal@gompa.dev>
Acked-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Signed-off-by: Hector Martin <marcan@marcan.st>
---
 MAINTAINERS                     |   2 -
 drivers/mailbox/Kconfig         |  12 --
 drivers/mailbox/Makefile        |   2 -
 drivers/mailbox/apple-mailbox.c | 441 ----------------------------------------
 include/linux/apple-mailbox.h   |  19 --
 5 files changed, 476 deletions(-)
 delete mode 100644 drivers/mailbox/apple-mailbox.c
 delete mode 100644 include/linux/apple-mailbox.h

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index 97f51d5ec1cf..c57c011dbd8c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1943,7 +1943,6 @@ F:	drivers/i2c/busses/i2c-pasemi-platform.c
 F:	drivers/iommu/apple-dart.c
 F:	drivers/iommu/io-pgtable-dart.c
 F:	drivers/irqchip/irq-apple-aic.c
-F:	drivers/mailbox/apple-mailbox.c
 F:	drivers/nvme/host/apple.c
 F:	drivers/nvmem/apple-efuses.c
 F:	drivers/pinctrl/pinctrl-apple-gpio.c
@@ -1952,7 +1951,6 @@ F:	drivers/soc/apple/*
 F:	drivers/watchdog/apple_wdt.c
 F:	include/dt-bindings/interrupt-controller/apple-aic.h
 F:	include/dt-bindings/pinctrl/apple.h
-F:	include/linux/apple-mailbox.h
 F:	include/linux/soc/apple/*
 
 ARM/ARTPEC MACHINE SUPPORT
diff --git a/drivers/mailbox/Kconfig b/drivers/mailbox/Kconfig
index bc2e265cb02d..42940108a187 100644
--- a/drivers/mailbox/Kconfig
+++ b/drivers/mailbox/Kconfig
@@ -8,18 +8,6 @@ menuconfig MAILBOX
 
 if MAILBOX
 
-config APPLE_MAILBOX
-	tristate "Apple Mailbox driver"
-	depends on ARCH_APPLE || (ARM64 && COMPILE_TEST)
-	default ARCH_APPLE
-	help
-	  Apple SoCs have various co-processors required for certain
-	  peripherals to work (NVMe, display controller, etc.). This
-	  driver adds support for the mailbox controller used to
-	  communicate with those.
-
-	  Say Y here if you have a Apple SoC.
-
 config ARM_MHU
 	tristate "ARM MHU Mailbox"
 	depends on ARM_AMBA
diff --git a/drivers/mailbox/Makefile b/drivers/mailbox/Makefile
index fc9376117111..18793e6caa2f 100644
--- a/drivers/mailbox/Makefile
+++ b/drivers/mailbox/Makefile
@@ -60,5 +60,3 @@ obj-$(CONFIG_SUN6I_MSGBOX)	+= sun6i-msgbox.o
 obj-$(CONFIG_SPRD_MBOX)		+= sprd-mailbox.o
 
 obj-$(CONFIG_QCOM_IPCC)		+= qcom-ipcc.o
-
-obj-$(CONFIG_APPLE_MAILBOX)	+= apple-mailbox.o
diff --git a/drivers/mailbox/apple-mailbox.c b/drivers/mailbox/apple-mailbox.c
deleted file mode 100644
index 2a3e8d8ff8b5..000000000000
--- a/drivers/mailbox/apple-mailbox.c
+++ /dev/null
@@ -1,441 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only OR MIT
-/*
- * Apple mailbox driver
- *
- * Copyright (C) 2021 The Asahi Linux Contributors
- *
- * This driver adds support for two mailbox variants (called ASC and M3 by
- * Apple) found in Apple SoCs such as the M1. It consists of two FIFOs used to
- * exchange 64+32 bit messages between the main CPU and a co-processor.
- * Various coprocessors implement different IPC protocols based on these simple
- * messages and shared memory buffers.
- *
- * Both the main CPU and the co-processor see the same set of registers but
- * the first FIFO (A2I) is always used to transfer messages from the application
- * processor (us) to the I/O processor and the second one (I2A) for the
- * other direction.
- */
-
-#include <linux/apple-mailbox.h>
-#include <linux/delay.h>
-#include <linux/device.h>
-#include <linux/gfp.h>
-#include <linux/interrupt.h>
-#include <linux/io.h>
-#include <linux/mailbox_controller.h>
-#include <linux/module.h>
-#include <linux/of.h>
-#include <linux/platform_device.h>
-#include <linux/spinlock.h>
-#include <linux/types.h>
-
-#define APPLE_ASC_MBOX_CONTROL_FULL  BIT(16)
-#define APPLE_ASC_MBOX_CONTROL_EMPTY BIT(17)
-
-#define APPLE_ASC_MBOX_A2I_CONTROL 0x110
-#define APPLE_ASC_MBOX_A2I_SEND0   0x800
-#define APPLE_ASC_MBOX_A2I_SEND1   0x808
-#define APPLE_ASC_MBOX_A2I_RECV0   0x810
-#define APPLE_ASC_MBOX_A2I_RECV1   0x818
-
-#define APPLE_ASC_MBOX_I2A_CONTROL 0x114
-#define APPLE_ASC_MBOX_I2A_SEND0   0x820
-#define APPLE_ASC_MBOX_I2A_SEND1   0x828
-#define APPLE_ASC_MBOX_I2A_RECV0   0x830
-#define APPLE_ASC_MBOX_I2A_RECV1   0x838
-
-#define APPLE_M3_MBOX_CONTROL_FULL  BIT(16)
-#define APPLE_M3_MBOX_CONTROL_EMPTY BIT(17)
-
-#define APPLE_M3_MBOX_A2I_CONTROL 0x50
-#define APPLE_M3_MBOX_A2I_SEND0	  0x60
-#define APPLE_M3_MBOX_A2I_SEND1	  0x68
-#define APPLE_M3_MBOX_A2I_RECV0	  0x70
-#define APPLE_M3_MBOX_A2I_RECV1	  0x78
-
-#define APPLE_M3_MBOX_I2A_CONTROL 0x80
-#define APPLE_M3_MBOX_I2A_SEND0	  0x90
-#define APPLE_M3_MBOX_I2A_SEND1	  0x98
-#define APPLE_M3_MBOX_I2A_RECV0	  0xa0
-#define APPLE_M3_MBOX_I2A_RECV1	  0xa8
-
-#define APPLE_M3_MBOX_IRQ_ENABLE	0x48
-#define APPLE_M3_MBOX_IRQ_ACK		0x4c
-#define APPLE_M3_MBOX_IRQ_A2I_EMPTY	BIT(0)
-#define APPLE_M3_MBOX_IRQ_A2I_NOT_EMPTY BIT(1)
-#define APPLE_M3_MBOX_IRQ_I2A_EMPTY	BIT(2)
-#define APPLE_M3_MBOX_IRQ_I2A_NOT_EMPTY BIT(3)
-
-#define APPLE_MBOX_MSG1_OUTCNT GENMASK(56, 52)
-#define APPLE_MBOX_MSG1_INCNT  GENMASK(51, 48)
-#define APPLE_MBOX_MSG1_OUTPTR GENMASK(47, 44)
-#define APPLE_MBOX_MSG1_INPTR  GENMASK(43, 40)
-#define APPLE_MBOX_MSG1_MSG    GENMASK(31, 0)
-
-struct apple_mbox_hw {
-	unsigned int control_full;
-	unsigned int control_empty;
-
-	unsigned int a2i_control;
-	unsigned int a2i_send0;
-	unsigned int a2i_send1;
-
-	unsigned int i2a_control;
-	unsigned int i2a_recv0;
-	unsigned int i2a_recv1;
-
-	bool has_irq_controls;
-	unsigned int irq_enable;
-	unsigned int irq_ack;
-	unsigned int irq_bit_recv_not_empty;
-	unsigned int irq_bit_send_empty;
-};
-
-struct apple_mbox {
-	void __iomem *regs;
-	const struct apple_mbox_hw *hw;
-
-	int irq_recv_not_empty;
-	int irq_send_empty;
-
-	struct mbox_chan chan;
-
-	struct device *dev;
-	struct mbox_controller controller;
-	spinlock_t rx_lock;
-};
-
-static const struct of_device_id apple_mbox_of_match[];
-
-static bool apple_mbox_hw_can_send(struct apple_mbox *apple_mbox)
-{
-	u32 mbox_ctrl =
-		readl_relaxed(apple_mbox->regs + apple_mbox->hw->a2i_control);
-
-	return !(mbox_ctrl & apple_mbox->hw->control_full);
-}
-
-static bool apple_mbox_hw_send_empty(struct apple_mbox *apple_mbox)
-{
-	u32 mbox_ctrl =
-		readl_relaxed(apple_mbox->regs + apple_mbox->hw->a2i_control);
-
-	return mbox_ctrl & apple_mbox->hw->control_empty;
-}
-
-static int apple_mbox_hw_send(struct apple_mbox *apple_mbox,
-			      struct apple_mbox_msg *msg)
-{
-	if (!apple_mbox_hw_can_send(apple_mbox))
-		return -EBUSY;
-
-	dev_dbg(apple_mbox->dev, "> TX %016llx %08x\n", msg->msg0, msg->msg1);
-
-	writeq_relaxed(msg->msg0, apple_mbox->regs + apple_mbox->hw->a2i_send0);
-	writeq_relaxed(FIELD_PREP(APPLE_MBOX_MSG1_MSG, msg->msg1),
-		       apple_mbox->regs + apple_mbox->hw->a2i_send1);
-
-	return 0;
-}
-
-static bool apple_mbox_hw_can_recv(struct apple_mbox *apple_mbox)
-{
-	u32 mbox_ctrl =
-		readl_relaxed(apple_mbox->regs + apple_mbox->hw->i2a_control);
-
-	return !(mbox_ctrl & apple_mbox->hw->control_empty);
-}
-
-static int apple_mbox_hw_recv(struct apple_mbox *apple_mbox,
-			      struct apple_mbox_msg *msg)
-{
-	if (!apple_mbox_hw_can_recv(apple_mbox))
-		return -ENOMSG;
-
-	msg->msg0 = readq_relaxed(apple_mbox->regs + apple_mbox->hw->i2a_recv0);
-	msg->msg1 = FIELD_GET(
-		APPLE_MBOX_MSG1_MSG,
-		readq_relaxed(apple_mbox->regs + apple_mbox->hw->i2a_recv1));
-
-	dev_dbg(apple_mbox->dev, "< RX %016llx %08x\n", msg->msg0, msg->msg1);
-
-	return 0;
-}
-
-static int apple_mbox_chan_send_data(struct mbox_chan *chan, void *data)
-{
-	struct apple_mbox *apple_mbox = chan->con_priv;
-	struct apple_mbox_msg *msg = data;
-	int ret;
-
-	ret = apple_mbox_hw_send(apple_mbox, msg);
-	if (ret)
-		return ret;
-
-	/*
-	 * The interrupt is level triggered and will keep firing as long as the
-	 * FIFO is empty. It will also keep firing if the FIFO was empty
-	 * at any point in the past until it has been acknowledged at the
-	 * mailbox level. By acknowledging it here we can ensure that we will
-	 * only get the interrupt once the FIFO has been cleared again.
-	 * If the FIFO is already empty before the ack it will fire again
-	 * immediately after the ack.
-	 */
-	if (apple_mbox->hw->has_irq_controls) {
-		writel_relaxed(apple_mbox->hw->irq_bit_send_empty,
-			       apple_mbox->regs + apple_mbox->hw->irq_ack);
-	}
-	enable_irq(apple_mbox->irq_send_empty);
-
-	return 0;
-}
-
-static irqreturn_t apple_mbox_send_empty_irq(int irq, void *data)
-{
-	struct apple_mbox *apple_mbox = data;
-
-	/*
-	 * We don't need to acknowledge the interrupt at the mailbox level
-	 * here even if supported by the hardware. It will keep firing but that
-	 * doesn't matter since it's disabled at the main interrupt controller.
-	 * apple_mbox_chan_send_data will acknowledge it before enabling
-	 * it at the main controller again.
-	 */
-	disable_irq_nosync(apple_mbox->irq_send_empty);
-	mbox_chan_txdone(&apple_mbox->chan, 0);
-	return IRQ_HANDLED;
-}
-
-static int apple_mbox_poll(struct apple_mbox *apple_mbox)
-{
-	struct apple_mbox_msg msg;
-	int ret = 0;
-
-	while (apple_mbox_hw_recv(apple_mbox, &msg) == 0) {
-		mbox_chan_received_data(&apple_mbox->chan, (void *)&msg);
-		ret++;
-	}
-
-	/*
-	 * The interrupt will keep firing even if there are no more messages
-	 * unless we also acknowledge it at the mailbox level here.
-	 * There's no race if a message comes in between the check in the while
-	 * loop above and the ack below: If a new messages arrives inbetween
-	 * those two the interrupt will just fire again immediately after the
-	 * ack since it's level triggered.
-	 */
-	if (apple_mbox->hw->has_irq_controls) {
-		writel_relaxed(apple_mbox->hw->irq_bit_recv_not_empty,
-			       apple_mbox->regs + apple_mbox->hw->irq_ack);
-	}
-
-	return ret;
-}
-
-static irqreturn_t apple_mbox_recv_irq(int irq, void *data)
-{
-	struct apple_mbox *apple_mbox = data;
-
-	spin_lock(&apple_mbox->rx_lock);
-	apple_mbox_poll(apple_mbox);
-	spin_unlock(&apple_mbox->rx_lock);
-
-	return IRQ_HANDLED;
-}
-
-static bool apple_mbox_chan_peek_data(struct mbox_chan *chan)
-{
-	struct apple_mbox *apple_mbox = chan->con_priv;
-	unsigned long flags;
-	int ret;
-
-	spin_lock_irqsave(&apple_mbox->rx_lock, flags);
-	ret = apple_mbox_poll(apple_mbox);
-	spin_unlock_irqrestore(&apple_mbox->rx_lock, flags);
-
-	return ret > 0;
-}
-
-static int apple_mbox_chan_flush(struct mbox_chan *chan, unsigned long timeout)
-{
-	struct apple_mbox *apple_mbox = chan->con_priv;
-	unsigned long deadline = jiffies + msecs_to_jiffies(timeout);
-
-	while (time_before(jiffies, deadline)) {
-		if (apple_mbox_hw_send_empty(apple_mbox)) {
-			mbox_chan_txdone(&apple_mbox->chan, 0);
-			return 0;
-		}
-
-		udelay(1);
-	}
-
-	return -ETIME;
-}
-
-static int apple_mbox_chan_startup(struct mbox_chan *chan)
-{
-	struct apple_mbox *apple_mbox = chan->con_priv;
-
-	/*
-	 * Only some variants of this mailbox HW provide interrupt control
-	 * at the mailbox level. We therefore need to handle enabling/disabling
-	 * interrupts at the main interrupt controller anyway for hardware that
-	 * doesn't. Just always keep the interrupts we care about enabled at
-	 * the mailbox level so that both hardware revisions behave almost
-	 * the same.
-	 */
-	if (apple_mbox->hw->has_irq_controls) {
-		writel_relaxed(apple_mbox->hw->irq_bit_recv_not_empty |
-				       apple_mbox->hw->irq_bit_send_empty,
-			       apple_mbox->regs + apple_mbox->hw->irq_enable);
-	}
-
-	enable_irq(apple_mbox->irq_recv_not_empty);
-	return 0;
-}
-
-static void apple_mbox_chan_shutdown(struct mbox_chan *chan)
-{
-	struct apple_mbox *apple_mbox = chan->con_priv;
-
-	disable_irq(apple_mbox->irq_recv_not_empty);
-}
-
-static const struct mbox_chan_ops apple_mbox_ops = {
-	.send_data = apple_mbox_chan_send_data,
-	.peek_data = apple_mbox_chan_peek_data,
-	.flush = apple_mbox_chan_flush,
-	.startup = apple_mbox_chan_startup,
-	.shutdown = apple_mbox_chan_shutdown,
-};
-
-static struct mbox_chan *apple_mbox_of_xlate(struct mbox_controller *mbox,
-					     const struct of_phandle_args *args)
-{
-	if (args->args_count != 0)
-		return ERR_PTR(-EINVAL);
-
-	return &mbox->chans[0];
-}
-
-static int apple_mbox_probe(struct platform_device *pdev)
-{
-	int ret;
-	const struct of_device_id *match;
-	char *irqname;
-	struct apple_mbox *mbox;
-	struct device *dev = &pdev->dev;
-
-	match = of_match_node(apple_mbox_of_match, pdev->dev.of_node);
-	if (!match)
-		return -EINVAL;
-	if (!match->data)
-		return -EINVAL;
-
-	mbox = devm_kzalloc(dev, sizeof(*mbox), GFP_KERNEL);
-	if (!mbox)
-		return -ENOMEM;
-	platform_set_drvdata(pdev, mbox);
-
-	mbox->dev = dev;
-	mbox->regs = devm_platform_ioremap_resource(pdev, 0);
-	if (IS_ERR(mbox->regs))
-		return PTR_ERR(mbox->regs);
-
-	mbox->hw = match->data;
-	mbox->irq_recv_not_empty =
-		platform_get_irq_byname(pdev, "recv-not-empty");
-	if (mbox->irq_recv_not_empty < 0)
-		return -ENODEV;
-
-	mbox->irq_send_empty = platform_get_irq_byname(pdev, "send-empty");
-	if (mbox->irq_send_empty < 0)
-		return -ENODEV;
-
-	mbox->controller.dev = mbox->dev;
-	mbox->controller.num_chans = 1;
-	mbox->controller.chans = &mbox->chan;
-	mbox->controller.ops = &apple_mbox_ops;
-	mbox->controller.txdone_irq = true;
-	mbox->controller.of_xlate = apple_mbox_of_xlate;
-	mbox->chan.con_priv = mbox;
-	spin_lock_init(&mbox->rx_lock);
-
-	irqname = devm_kasprintf(dev, GFP_KERNEL, "%s-recv", dev_name(dev));
-	if (!irqname)
-		return -ENOMEM;
-
-	ret = devm_request_threaded_irq(dev, mbox->irq_recv_not_empty, NULL,
-					apple_mbox_recv_irq,
-					IRQF_NO_AUTOEN | IRQF_ONESHOT, irqname,
-					mbox);
-	if (ret)
-		return ret;
-
-	irqname = devm_kasprintf(dev, GFP_KERNEL, "%s-send", dev_name(dev));
-	if (!irqname)
-		return -ENOMEM;
-
-	ret = devm_request_irq(dev, mbox->irq_send_empty,
-			       apple_mbox_send_empty_irq, IRQF_NO_AUTOEN,
-			       irqname, mbox);
-	if (ret)
-		return ret;
-
-	return devm_mbox_controller_register(dev, &mbox->controller);
-}
-
-static const struct apple_mbox_hw apple_mbox_asc_hw = {
-	.control_full = APPLE_ASC_MBOX_CONTROL_FULL,
-	.control_empty = APPLE_ASC_MBOX_CONTROL_EMPTY,
-
-	.a2i_control = APPLE_ASC_MBOX_A2I_CONTROL,
-	.a2i_send0 = APPLE_ASC_MBOX_A2I_SEND0,
-	.a2i_send1 = APPLE_ASC_MBOX_A2I_SEND1,
-
-	.i2a_control = APPLE_ASC_MBOX_I2A_CONTROL,
-	.i2a_recv0 = APPLE_ASC_MBOX_I2A_RECV0,
-	.i2a_recv1 = APPLE_ASC_MBOX_I2A_RECV1,
-
-	.has_irq_controls = false,
-};
-
-static const struct apple_mbox_hw apple_mbox_m3_hw = {
-	.control_full = APPLE_M3_MBOX_CONTROL_FULL,
-	.control_empty = APPLE_M3_MBOX_CONTROL_EMPTY,
-
-	.a2i_control = APPLE_M3_MBOX_A2I_CONTROL,
-	.a2i_send0 = APPLE_M3_MBOX_A2I_SEND0,
-	.a2i_send1 = APPLE_M3_MBOX_A2I_SEND1,
-
-	.i2a_control = APPLE_M3_MBOX_I2A_CONTROL,
-	.i2a_recv0 = APPLE_M3_MBOX_I2A_RECV0,
-	.i2a_recv1 = APPLE_M3_MBOX_I2A_RECV1,
-
-	.has_irq_controls = true,
-	.irq_enable = APPLE_M3_MBOX_IRQ_ENABLE,
-	.irq_ack = APPLE_M3_MBOX_IRQ_ACK,
-	.irq_bit_recv_not_empty = APPLE_M3_MBOX_IRQ_I2A_NOT_EMPTY,
-	.irq_bit_send_empty = APPLE_M3_MBOX_IRQ_A2I_EMPTY,
-};
-
-static const struct of_device_id apple_mbox_of_match[] = {
-	{ .compatible = "apple,asc-mailbox-v4", .data = &apple_mbox_asc_hw },
-	{ .compatible = "apple,m3-mailbox-v2", .data = &apple_mbox_m3_hw },
-	{}
-};
-MODULE_DEVICE_TABLE(of, apple_mbox_of_match);
-
-static struct platform_driver apple_mbox_driver = {
-	.driver = {
-		.name = "apple-mailbox",
-		.of_match_table = apple_mbox_of_match,
-	},
-	.probe = apple_mbox_probe,
-};
-module_platform_driver(apple_mbox_driver);
-
-MODULE_LICENSE("Dual MIT/GPL");
-MODULE_AUTHOR("Sven Peter <sven@svenpeter.dev>");
-MODULE_DESCRIPTION("Apple Mailbox driver");
diff --git a/include/linux/apple-mailbox.h b/include/linux/apple-mailbox.h
deleted file mode 100644
index 720fbb70294a..000000000000
--- a/include/linux/apple-mailbox.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only OR MIT */
-/*
- * Apple mailbox message format
- *
- * Copyright (C) 2021 The Asahi Linux Contributors
- */
-
-#ifndef _LINUX_APPLE_MAILBOX_H_
-#define _LINUX_APPLE_MAILBOX_H_
-
-#include <linux/types.h>
-
-/* encodes a single 96bit message sent over the single channel */
-struct apple_mbox_msg {
-	u64 msg0;
-	u32 msg1;
-};
-
-#endif
-- 
cgit v1.2.3


From 9c0b4bb7f6303c9c4e2e34984c46f5a86478f84d Mon Sep 17 00:00:00 2001
From: Vincent Guittot <vincent.guittot@linaro.org>
Date: Wed, 22 Nov 2023 14:39:03 +0100
Subject: sched/cpufreq: Rework schedutil governor performance estimation

The current method to take into account uclamp hints when estimating the
target frequency can end in a situation where the selected target
frequency is finally higher than uclamp hints, whereas there are no real
needs. Such cases mainly happen because we are currently mixing the
traditional scheduler utilization signal with the uclamp performance
hints. By adding these 2 metrics, we loose an important information when
it comes to select the target frequency, and we have to make some
assumptions which can't fit all cases.

Rework the interface between the scheduler and schedutil governor in order
to propagate all information down to the cpufreq governor.

effective_cpu_util() interface changes and now returns the actual
utilization of the CPU with 2 optional inputs:

- The minimum performance for this CPU; typically the capacity to handle
  the deadline task and the interrupt pressure. But also uclamp_min
  request when available.

- The maximum targeting performance for this CPU which reflects the
  maximum level that we would like to not exceed. By default it will be
  the CPU capacity but can be reduced because of some performance hints
  set with uclamp. The value can be lower than actual utilization and/or
  min performance level.

A new sugov_effective_cpu_perf() interface is also available to compute
the final performance level that is targeted for the CPU, after applying
some cpufreq headroom and taking into account all inputs.

With these 2 functions, schedutil is now able to decide when it must go
above uclamp hints. It now also has a generic way to get the min
performance level.

The dependency between energy model and cpufreq governor and its headroom
policy doesn't exist anymore.

eenv_pd_max_util() asks schedutil for the targeted performance after
applying the impact of the waking task.

[ mingo: Refined the changelog & C comments. ]

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Rafael J. Wysocki <rafael@kernel.org>
Link: https://lore.kernel.org/r/20231122133904.446032-2-vincent.guittot@linaro.org
---
 include/linux/energy_model.h     |  1 -
 kernel/sched/core.c              | 90 +++++++++++++++++-----------------------
 kernel/sched/cpufreq_schedutil.c | 35 +++++++++++-----
 kernel/sched/fair.c              | 22 ++++++++--
 kernel/sched/sched.h             | 24 ++++-------
 5 files changed, 89 insertions(+), 83 deletions(-)

(limited to 'include')

diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h
index b9caa01dfac4..adec808b371a 100644
--- a/include/linux/energy_model.h
+++ b/include/linux/energy_model.h
@@ -243,7 +243,6 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd,
 	scale_cpu = arch_scale_cpu_capacity(cpu);
 	ps = &pd->table[pd->nr_perf_states - 1];
 
-	max_util = map_util_perf(max_util);
 	max_util = min(max_util, allowed_cpu_cap);
 	freq = map_util_freq(max_util, ps->frequency, scale_cpu);
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2de77a6d5ef8..db4be4921e7f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7467,18 +7467,13 @@ int sched_core_idle_cpu(int cpu)
  * required to meet deadlines.
  */
 unsigned long effective_cpu_util(int cpu, unsigned long util_cfs,
-				 enum cpu_util_type type,
-				 struct task_struct *p)
+				 unsigned long *min,
+				 unsigned long *max)
 {
-	unsigned long dl_util, util, irq, max;
+	unsigned long util, irq, scale;
 	struct rq *rq = cpu_rq(cpu);
 
-	max = arch_scale_cpu_capacity(cpu);
-
-	if (!uclamp_is_used() &&
-	    type == FREQUENCY_UTIL && rt_rq_is_runnable(&rq->rt)) {
-		return max;
-	}
+	scale = arch_scale_cpu_capacity(cpu);
 
 	/*
 	 * Early check to see if IRQ/steal time saturates the CPU, can be
@@ -7486,45 +7481,49 @@ unsigned long effective_cpu_util(int cpu, unsigned long util_cfs,
 	 * update_irq_load_avg().
 	 */
 	irq = cpu_util_irq(rq);
-	if (unlikely(irq >= max))
-		return max;
+	if (unlikely(irq >= scale)) {
+		if (min)
+			*min = scale;
+		if (max)
+			*max = scale;
+		return scale;
+	}
+
+	if (min) {
+		/*
+		 * The minimum utilization returns the highest level between:
+		 * - the computed DL bandwidth needed with the IRQ pressure which
+		 *   steals time to the deadline task.
+		 * - The minimum performance requirement for CFS and/or RT.
+		 */
+		*min = max(irq + cpu_bw_dl(rq), uclamp_rq_get(rq, UCLAMP_MIN));
+
+		/*
+		 * When an RT task is runnable and uclamp is not used, we must
+		 * ensure that the task will run at maximum compute capacity.
+		 */
+		if (!uclamp_is_used() && rt_rq_is_runnable(&rq->rt))
+			*min = max(*min, scale);
+	}
 
 	/*
 	 * Because the time spend on RT/DL tasks is visible as 'lost' time to
 	 * CFS tasks and we use the same metric to track the effective
 	 * utilization (PELT windows are synchronized) we can directly add them
 	 * to obtain the CPU's actual utilization.
-	 *
-	 * CFS and RT utilization can be boosted or capped, depending on
-	 * utilization clamp constraints requested by currently RUNNABLE
-	 * tasks.
-	 * When there are no CFS RUNNABLE tasks, clamps are released and
-	 * frequency will be gracefully reduced with the utilization decay.
 	 */
 	util = util_cfs + cpu_util_rt(rq);
-	if (type == FREQUENCY_UTIL)
-		util = uclamp_rq_util_with(rq, util, p);
-
-	dl_util = cpu_util_dl(rq);
+	util += cpu_util_dl(rq);
 
 	/*
-	 * For frequency selection we do not make cpu_util_dl() a permanent part
-	 * of this sum because we want to use cpu_bw_dl() later on, but we need
-	 * to check if the CFS+RT+DL sum is saturated (ie. no idle time) such
-	 * that we select f_max when there is no idle time.
-	 *
-	 * NOTE: numerical errors or stop class might cause us to not quite hit
-	 * saturation when we should -- something for later.
+	 * The maximum hint is a soft bandwidth requirement, which can be lower
+	 * than the actual utilization because of uclamp_max requirements.
 	 */
-	if (util + dl_util >= max)
-		return max;
+	if (max)
+		*max = min(scale, uclamp_rq_get(rq, UCLAMP_MAX));
 
-	/*
-	 * OTOH, for energy computation we need the estimated running time, so
-	 * include util_dl and ignore dl_bw.
-	 */
-	if (type == ENERGY_UTIL)
-		util += dl_util;
+	if (util >= scale)
+		return scale;
 
 	/*
 	 * There is still idle time; further improve the number by using the
@@ -7535,28 +7534,15 @@ unsigned long effective_cpu_util(int cpu, unsigned long util_cfs,
 	 *   U' = irq + --------- * U
 	 *                 max
 	 */
-	util = scale_irq_capacity(util, irq, max);
+	util = scale_irq_capacity(util, irq, scale);
 	util += irq;
 
-	/*
-	 * Bandwidth required by DEADLINE must always be granted while, for
-	 * FAIR and RT, we use blocked utilization of IDLE CPUs as a mechanism
-	 * to gracefully reduce the frequency when no tasks show up for longer
-	 * periods of time.
-	 *
-	 * Ideally we would like to set bw_dl as min/guaranteed freq and util +
-	 * bw_dl as requested freq. However, cpufreq is not yet ready for such
-	 * an interface. So, we only do the latter for now.
-	 */
-	if (type == FREQUENCY_UTIL)
-		util += cpu_bw_dl(rq);
-
-	return min(max, util);
+	return min(scale, util);
 }
 
 unsigned long sched_cpu_util(int cpu)
 {
-	return effective_cpu_util(cpu, cpu_util_cfs(cpu), ENERGY_UTIL, NULL);
+	return effective_cpu_util(cpu, cpu_util_cfs(cpu), NULL, NULL);
 }
 #endif /* CONFIG_SMP */
 
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 5888176354e2..f3acf2cf26ed 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -47,7 +47,7 @@ struct sugov_cpu {
 	u64			last_update;
 
 	unsigned long		util;
-	unsigned long		bw_dl;
+	unsigned long		bw_min;
 
 	/* The field below is for single-CPU policies only: */
 #ifdef CONFIG_NO_HZ_COMMON
@@ -143,7 +143,6 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy,
 	unsigned int freq = arch_scale_freq_invariant() ?
 				policy->cpuinfo.max_freq : policy->cur;
 
-	util = map_util_perf(util);
 	freq = map_util_freq(util, freq, max);
 
 	if (freq == sg_policy->cached_raw_freq && !sg_policy->need_freq_update)
@@ -153,14 +152,30 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy,
 	return cpufreq_driver_resolve_freq(policy, freq);
 }
 
+unsigned long sugov_effective_cpu_perf(int cpu, unsigned long actual,
+				 unsigned long min,
+				 unsigned long max)
+{
+	/* Add dvfs headroom to actual utilization */
+	actual = map_util_perf(actual);
+	/* Actually we don't need to target the max performance */
+	if (actual < max)
+		max = actual;
+
+	/*
+	 * Ensure at least minimum performance while providing more compute
+	 * capacity when possible.
+	 */
+	return max(min, max);
+}
+
 static void sugov_get_util(struct sugov_cpu *sg_cpu)
 {
-	unsigned long util = cpu_util_cfs_boost(sg_cpu->cpu);
-	struct rq *rq = cpu_rq(sg_cpu->cpu);
+	unsigned long min, max, util = cpu_util_cfs_boost(sg_cpu->cpu);
 
-	sg_cpu->bw_dl = cpu_bw_dl(rq);
-	sg_cpu->util = effective_cpu_util(sg_cpu->cpu, util,
-					  FREQUENCY_UTIL, NULL);
+	util = effective_cpu_util(sg_cpu->cpu, util, &min, &max);
+	sg_cpu->bw_min = min;
+	sg_cpu->util = sugov_effective_cpu_perf(sg_cpu->cpu, util, min, max);
 }
 
 /**
@@ -306,7 +321,7 @@ static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; }
  */
 static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu)
 {
-	if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_dl)
+	if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_min)
 		sg_cpu->sg_policy->limits_changed = true;
 }
 
@@ -407,8 +422,8 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time,
 	    sugov_cpu_is_busy(sg_cpu) && sg_cpu->util < prev_util)
 		sg_cpu->util = prev_util;
 
-	cpufreq_driver_adjust_perf(sg_cpu->cpu, map_util_perf(sg_cpu->bw_dl),
-				   map_util_perf(sg_cpu->util), max_cap);
+	cpufreq_driver_adjust_perf(sg_cpu->cpu, sg_cpu->bw_min,
+				   sg_cpu->util, max_cap);
 
 	sg_cpu->sg_policy->last_freq_update_time = time;
 }
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 53dea95ad8c9..34fe6e9490c2 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7793,7 +7793,7 @@ static inline void eenv_pd_busy_time(struct energy_env *eenv,
 	for_each_cpu(cpu, pd_cpus) {
 		unsigned long util = cpu_util(cpu, p, -1, 0);
 
-		busy_time += effective_cpu_util(cpu, util, ENERGY_UTIL, NULL);
+		busy_time += effective_cpu_util(cpu, util, NULL, NULL);
 	}
 
 	eenv->pd_busy_time = min(eenv->pd_cap, busy_time);
@@ -7816,7 +7816,7 @@ eenv_pd_max_util(struct energy_env *eenv, struct cpumask *pd_cpus,
 	for_each_cpu(cpu, pd_cpus) {
 		struct task_struct *tsk = (cpu == dst_cpu) ? p : NULL;
 		unsigned long util = cpu_util(cpu, p, dst_cpu, 1);
-		unsigned long eff_util;
+		unsigned long eff_util, min, max;
 
 		/*
 		 * Performance domain frequency: utilization clamping
@@ -7825,7 +7825,23 @@ eenv_pd_max_util(struct energy_env *eenv, struct cpumask *pd_cpus,
 		 * NOTE: in case RT tasks are running, by default the
 		 * FREQUENCY_UTIL's utilization can be max OPP.
 		 */
-		eff_util = effective_cpu_util(cpu, util, FREQUENCY_UTIL, tsk);
+		eff_util = effective_cpu_util(cpu, util, &min, &max);
+
+		/* Task's uclamp can modify min and max value */
+		if (tsk && uclamp_is_used()) {
+			min = max(min, uclamp_eff_value(p, UCLAMP_MIN));
+
+			/*
+			 * If there is no active max uclamp constraint,
+			 * directly use task's one, otherwise keep max.
+			 */
+			if (uclamp_rq_is_idle(cpu_rq(cpu)))
+				max = uclamp_eff_value(p, UCLAMP_MAX);
+			else
+				max = max(max, uclamp_eff_value(p, UCLAMP_MAX));
+		}
+
+		eff_util = sugov_effective_cpu_perf(cpu, eff_util, min, max);
 		max_util = max(max_util, eff_util);
 	}
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 8a70d51ffa33..c1574cd388e7 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2994,24 +2994,14 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
 #endif
 
 #ifdef CONFIG_SMP
-/**
- * enum cpu_util_type - CPU utilization type
- * @FREQUENCY_UTIL:	Utilization used to select frequency
- * @ENERGY_UTIL:	Utilization used during energy calculation
- *
- * The utilization signals of all scheduling classes (CFS/RT/DL) and IRQ time
- * need to be aggregated differently depending on the usage made of them. This
- * enum is used within effective_cpu_util() to differentiate the types of
- * utilization expected by the callers, and adjust the aggregation accordingly.
- */
-enum cpu_util_type {
-	FREQUENCY_UTIL,
-	ENERGY_UTIL,
-};
-
 unsigned long effective_cpu_util(int cpu, unsigned long util_cfs,
-				 enum cpu_util_type type,
-				 struct task_struct *p);
+				 unsigned long *min,
+				 unsigned long *max);
+
+unsigned long sugov_effective_cpu_perf(int cpu, unsigned long actual,
+				 unsigned long min,
+				 unsigned long max);
+
 
 /*
  * Verify the fitness of task @p to run on @cpu taking into account the
-- 
cgit v1.2.3


From 64bac5ea17d527872121adddfee869c7a0618f8f Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 8 Nov 2023 13:58:29 +0100
Subject: arch: consolidate arch_irq_work_raise prototypes

The prototype was hidden in an #ifdef on x86, which causes a warning:

kernel/irq_work.c:72:13: error: no previous prototype for 'arch_irq_work_raise' [-Werror=missing-prototypes]

Some architectures have a working prototype, while others don't.
Fix this by providing it in only one place that is always visible.

Reviewed-by: Alexander Gordeev <agordeev@linux.ibm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Palmer Dabbelt <palmer@rivosinc.com>
Acked-by: Guo Ren <guoren@kernel.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arm/include/asm/irq_work.h     | 2 --
 arch/arm64/include/asm/irq_work.h   | 2 --
 arch/csky/include/asm/irq_work.h    | 2 +-
 arch/powerpc/include/asm/irq_work.h | 1 -
 arch/riscv/include/asm/irq_work.h   | 2 +-
 arch/s390/include/asm/irq_work.h    | 2 --
 arch/x86/include/asm/irq_work.h     | 1 -
 include/linux/irq_work.h            | 3 +++
 8 files changed, 5 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/arch/arm/include/asm/irq_work.h b/arch/arm/include/asm/irq_work.h
index 3149e4dc1b54..8895999834cc 100644
--- a/arch/arm/include/asm/irq_work.h
+++ b/arch/arm/include/asm/irq_work.h
@@ -9,6 +9,4 @@ static inline bool arch_irq_work_has_interrupt(void)
 	return is_smp();
 }
 
-extern void arch_irq_work_raise(void);
-
 #endif /* _ASM_ARM_IRQ_WORK_H */
diff --git a/arch/arm64/include/asm/irq_work.h b/arch/arm64/include/asm/irq_work.h
index 81bbfa3a035b..a1020285ea75 100644
--- a/arch/arm64/include/asm/irq_work.h
+++ b/arch/arm64/include/asm/irq_work.h
@@ -2,8 +2,6 @@
 #ifndef __ASM_IRQ_WORK_H
 #define __ASM_IRQ_WORK_H
 
-extern void arch_irq_work_raise(void);
-
 static inline bool arch_irq_work_has_interrupt(void)
 {
 	return true;
diff --git a/arch/csky/include/asm/irq_work.h b/arch/csky/include/asm/irq_work.h
index 33aaf39d6f94..d39fcc1f5395 100644
--- a/arch/csky/include/asm/irq_work.h
+++ b/arch/csky/include/asm/irq_work.h
@@ -7,5 +7,5 @@ static inline bool arch_irq_work_has_interrupt(void)
 {
 	return true;
 }
-extern void arch_irq_work_raise(void);
+
 #endif /* __ASM_CSKY_IRQ_WORK_H */
diff --git a/arch/powerpc/include/asm/irq_work.h b/arch/powerpc/include/asm/irq_work.h
index b8b0be8f1a07..c6d3078bd8c3 100644
--- a/arch/powerpc/include/asm/irq_work.h
+++ b/arch/powerpc/include/asm/irq_work.h
@@ -6,6 +6,5 @@ static inline bool arch_irq_work_has_interrupt(void)
 {
 	return true;
 }
-extern void arch_irq_work_raise(void);
 
 #endif /* _ASM_POWERPC_IRQ_WORK_H */
diff --git a/arch/riscv/include/asm/irq_work.h b/arch/riscv/include/asm/irq_work.h
index b53891964ae0..b27a4d64fc6a 100644
--- a/arch/riscv/include/asm/irq_work.h
+++ b/arch/riscv/include/asm/irq_work.h
@@ -6,5 +6,5 @@ static inline bool arch_irq_work_has_interrupt(void)
 {
 	return IS_ENABLED(CONFIG_SMP);
 }
-extern void arch_irq_work_raise(void);
+
 #endif /* _ASM_RISCV_IRQ_WORK_H */
diff --git a/arch/s390/include/asm/irq_work.h b/arch/s390/include/asm/irq_work.h
index 603783766d0a..f00c9f610d5a 100644
--- a/arch/s390/include/asm/irq_work.h
+++ b/arch/s390/include/asm/irq_work.h
@@ -7,6 +7,4 @@ static inline bool arch_irq_work_has_interrupt(void)
 	return true;
 }
 
-void arch_irq_work_raise(void);
-
 #endif /* _ASM_S390_IRQ_WORK_H */
diff --git a/arch/x86/include/asm/irq_work.h b/arch/x86/include/asm/irq_work.h
index 800ffce0db29..6b4d36c95165 100644
--- a/arch/x86/include/asm/irq_work.h
+++ b/arch/x86/include/asm/irq_work.h
@@ -9,7 +9,6 @@ static inline bool arch_irq_work_has_interrupt(void)
 {
 	return boot_cpu_has(X86_FEATURE_APIC);
 }
-extern void arch_irq_work_raise(void);
 #else
 static inline bool arch_irq_work_has_interrupt(void)
 {
diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h
index 8cd11a223260..136f2980cba3 100644
--- a/include/linux/irq_work.h
+++ b/include/linux/irq_work.h
@@ -66,6 +66,9 @@ void irq_work_sync(struct irq_work *work);
 void irq_work_run(void);
 bool irq_work_needs_cpu(void);
 void irq_work_single(void *arg);
+
+void arch_irq_work_raise(void);
+
 #else
 static inline bool irq_work_needs_cpu(void) { return false; }
 static inline void irq_work_run(void) { }
-- 
cgit v1.2.3


From 42874e4eb35bdfc54f8514685e50434098ba4f6c Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 8 Nov 2023 13:58:36 +0100
Subject: arch: vdso: consolidate gettime prototypes

The VDSO functions are defined as globals in the kernel sources but intended
to be called from userspace, so there is no need to declare them in a kernel
side header.

Without a prototype, this now causes warnings such as

arch/mips/vdso/vgettimeofday.c:14:5: error: no previous prototype for '__vdso_clock_gettime' [-Werror=missing-prototypes]
arch/mips/vdso/vgettimeofday.c:28:5: error: no previous prototype for '__vdso_gettimeofday' [-Werror=missing-prototypes]
arch/mips/vdso/vgettimeofday.c:36:5: error: no previous prototype for '__vdso_clock_getres' [-Werror=missing-prototypes]
arch/mips/vdso/vgettimeofday.c:42:5: error: no previous prototype for '__vdso_clock_gettime64' [-Werror=missing-prototypes]
arch/sparc/vdso/vclock_gettime.c:254:1: error: no previous prototype for '__vdso_clock_gettime' [-Werror=missing-prototypes]
arch/sparc/vdso/vclock_gettime.c:282:1: error: no previous prototype for '__vdso_clock_gettime_stick' [-Werror=missing-prototypes]
arch/sparc/vdso/vclock_gettime.c:307:1: error: no previous prototype for '__vdso_gettimeofday' [-Werror=missing-prototypes]
arch/sparc/vdso/vclock_gettime.c:343:1: error: no previous prototype for '__vdso_gettimeofday_stick' [-Werror=missing-prototypes]

Most architectures have already added workarounds for these by adding
declarations somewhere, but since these are all compatible, we should
really just have one copy, with an #ifdef check for the 32-bit vs
64-bit variant and use that everywhere.

Unfortunately, the sparc an um versions are currently incompatible
since they never added support for __vdso_clock_gettime64() in 32-bit
userland. For the moment, I'm leaving this one out, as I can't
easily test it and it requires a larger rework.

Reviewed-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arm/include/asm/vdso.h              |  5 -----
 arch/arm/vdso/vgettimeofday.c            |  1 +
 arch/arm64/kernel/vdso32/vgettimeofday.c |  1 +
 arch/csky/kernel/vdso/vgettimeofday.c    | 11 +----------
 arch/loongarch/vdso/vgettimeofday.c      |  7 +------
 arch/mips/vdso/vgettimeofday.c           |  1 +
 arch/riscv/kernel/vdso/vgettimeofday.c   |  7 +------
 arch/x86/entry/vdso/vclock_gettime.c     | 10 +---------
 arch/x86/include/asm/vdso/gettimeofday.h |  2 --
 include/vdso/gettime.h                   | 23 +++++++++++++++++++++++
 10 files changed, 30 insertions(+), 38 deletions(-)
 create mode 100644 include/vdso/gettime.h

(limited to 'include')

diff --git a/arch/arm/include/asm/vdso.h b/arch/arm/include/asm/vdso.h
index 422c3afa806a..5b85889f82ee 100644
--- a/arch/arm/include/asm/vdso.h
+++ b/arch/arm/include/asm/vdso.h
@@ -24,11 +24,6 @@ static inline void arm_install_vdso(struct mm_struct *mm, unsigned long addr)
 
 #endif /* CONFIG_VDSO */
 
-int __vdso_clock_gettime(clockid_t clock, struct old_timespec32 *ts);
-int __vdso_clock_gettime64(clockid_t clock, struct __kernel_timespec *ts);
-int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz);
-int __vdso_clock_getres(clockid_t clock_id, struct old_timespec32 *res);
-
 #endif /* __ASSEMBLY__ */
 
 #endif /* __KERNEL__ */
diff --git a/arch/arm/vdso/vgettimeofday.c b/arch/arm/vdso/vgettimeofday.c
index a003beacac76..3554aa35f1ba 100644
--- a/arch/arm/vdso/vgettimeofday.c
+++ b/arch/arm/vdso/vgettimeofday.c
@@ -8,6 +8,7 @@
 #include <linux/types.h>
 #include <asm/vdso.h>
 #include <asm/unwind.h>
+#include <vdso/gettime.h>
 
 int __vdso_clock_gettime(clockid_t clock,
 			 struct old_timespec32 *ts)
diff --git a/arch/arm64/kernel/vdso32/vgettimeofday.c b/arch/arm64/kernel/vdso32/vgettimeofday.c
index 5acff29c5991..e23c7f4ef26b 100644
--- a/arch/arm64/kernel/vdso32/vgettimeofday.c
+++ b/arch/arm64/kernel/vdso32/vgettimeofday.c
@@ -5,6 +5,7 @@
  * Copyright (C) 2018 ARM Limited
  *
  */
+#include <vdso/gettime.h>
 
 int __vdso_clock_gettime(clockid_t clock,
 			 struct old_timespec32 *ts)
diff --git a/arch/csky/kernel/vdso/vgettimeofday.c b/arch/csky/kernel/vdso/vgettimeofday.c
index c4831145eed5..55af30e83752 100644
--- a/arch/csky/kernel/vdso/vgettimeofday.c
+++ b/arch/csky/kernel/vdso/vgettimeofday.c
@@ -2,36 +2,27 @@
 
 #include <linux/time.h>
 #include <linux/types.h>
+#include <vdso/gettime.h>
 
 extern
-int __vdso_clock_gettime(clockid_t clock,
-			 struct old_timespec32 *ts);
 int __vdso_clock_gettime(clockid_t clock,
 			 struct old_timespec32 *ts)
 {
 	return __cvdso_clock_gettime32(clock, ts);
 }
 
-int __vdso_clock_gettime64(clockid_t clock,
-			   struct __kernel_timespec *ts);
 int __vdso_clock_gettime64(clockid_t clock,
 			   struct __kernel_timespec *ts)
 {
 	return __cvdso_clock_gettime(clock, ts);
 }
 
-extern
-int __vdso_gettimeofday(struct __kernel_old_timeval *tv,
-			struct timezone *tz);
 int __vdso_gettimeofday(struct __kernel_old_timeval *tv,
 			struct timezone *tz)
 {
 	return __cvdso_gettimeofday(tv, tz);
 }
 
-extern
-int __vdso_clock_getres(clockid_t clock_id,
-			struct old_timespec32 *res);
 int __vdso_clock_getres(clockid_t clock_id,
 			struct old_timespec32 *res)
 {
diff --git a/arch/loongarch/vdso/vgettimeofday.c b/arch/loongarch/vdso/vgettimeofday.c
index 8f22863bd7ea..0885c1f3a89d 100644
--- a/arch/loongarch/vdso/vgettimeofday.c
+++ b/arch/loongarch/vdso/vgettimeofday.c
@@ -5,23 +5,18 @@
  * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
  */
 #include <linux/types.h>
+#include <vdso/gettime.h>
 
-extern
-int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts);
 int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts)
 {
 	return __cvdso_clock_gettime(clock, ts);
 }
 
-extern
-int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz);
 int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
 {
 	return __cvdso_gettimeofday(tv, tz);
 }
 
-extern
-int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res);
 int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res)
 {
 	return __cvdso_clock_getres(clock_id, res);
diff --git a/arch/mips/vdso/vgettimeofday.c b/arch/mips/vdso/vgettimeofday.c
index 6b83b6376a4b..604afea3f336 100644
--- a/arch/mips/vdso/vgettimeofday.c
+++ b/arch/mips/vdso/vgettimeofday.c
@@ -9,6 +9,7 @@
  */
 #include <linux/time.h>
 #include <linux/types.h>
+#include <vdso/gettime.h>
 
 #if _MIPS_SIM != _MIPS_SIM_ABI64
 int __vdso_clock_gettime(clockid_t clock,
diff --git a/arch/riscv/kernel/vdso/vgettimeofday.c b/arch/riscv/kernel/vdso/vgettimeofday.c
index cc0d80699c31..b35057802584 100644
--- a/arch/riscv/kernel/vdso/vgettimeofday.c
+++ b/arch/riscv/kernel/vdso/vgettimeofday.c
@@ -8,23 +8,18 @@
 
 #include <linux/time.h>
 #include <linux/types.h>
+#include <vdso/gettime.h>
 
-extern
-int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts);
 int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts)
 {
 	return __cvdso_clock_gettime(clock, ts);
 }
 
-extern
-int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz);
 int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
 {
 	return __cvdso_gettimeofday(tv, tz);
 }
 
-extern
-int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res);
 int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res)
 {
 	return __cvdso_clock_getres(clock_id, res);
diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index 7d70935b6758..0debc194bd78 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -11,12 +11,10 @@
 #include <linux/time.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
+#include <vdso/gettime.h>
 
 #include "../../../../lib/vdso/gettimeofday.c"
 
-extern int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz);
-extern __kernel_old_time_t __vdso_time(__kernel_old_time_t *t);
-
 int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
 {
 	return __cvdso_gettimeofday(tv, tz);
@@ -35,9 +33,6 @@ __kernel_old_time_t time(__kernel_old_time_t *t)	__attribute__((weak, alias("__v
 
 #if defined(CONFIG_X86_64) && !defined(BUILD_VDSO32_64)
 /* both 64-bit and x32 use these */
-extern int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts);
-extern int __vdso_clock_getres(clockid_t clock, struct __kernel_timespec *res);
-
 int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts)
 {
 	return __cvdso_clock_gettime(clock, ts);
@@ -56,9 +51,6 @@ int clock_getres(clockid_t, struct __kernel_timespec *)
 
 #else
 /* i386 only */
-extern int __vdso_clock_gettime(clockid_t clock, struct old_timespec32 *ts);
-extern int __vdso_clock_getres(clockid_t clock, struct old_timespec32 *res);
-
 int __vdso_clock_gettime(clockid_t clock, struct old_timespec32 *ts)
 {
 	return __cvdso_clock_gettime32(clock, ts);
diff --git a/arch/x86/include/asm/vdso/gettimeofday.h b/arch/x86/include/asm/vdso/gettimeofday.h
index c81858d903dc..a46edb0e0cf7 100644
--- a/arch/x86/include/asm/vdso/gettimeofday.h
+++ b/arch/x86/include/asm/vdso/gettimeofday.h
@@ -337,8 +337,6 @@ u64 vdso_calc_delta(u64 cycles, u64 last, u64 mask, u32 mult)
 }
 #define vdso_calc_delta vdso_calc_delta
 
-int __vdso_clock_gettime64(clockid_t clock, struct __kernel_timespec *ts);
-
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_VDSO_GETTIMEOFDAY_H */
diff --git a/include/vdso/gettime.h b/include/vdso/gettime.h
new file mode 100644
index 000000000000..c50d152e7b3e
--- /dev/null
+++ b/include/vdso/gettime.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _VDSO_GETTIME_H
+#define _VDSO_GETTIME_H
+
+#include <linux/types.h>
+
+struct __kernel_timespec;
+struct timezone;
+
+#if !defined(CONFIG_64BIT) || defined(BUILD_VDSO32_64)
+struct old_timespec32;
+int __vdso_clock_getres(clockid_t clock, struct old_timespec32 *res);
+int __vdso_clock_gettime(clockid_t clock, struct old_timespec32 *ts);
+#else
+int __vdso_clock_getres(clockid_t clock, struct __kernel_timespec *res);
+int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts);
+#endif
+
+__kernel_old_time_t __vdso_time(__kernel_old_time_t *t);
+int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz);
+int __vdso_clock_gettime64(clockid_t clock, struct __kernel_timespec *ts);
+
+#endif
-- 
cgit v1.2.3


From 3c147c29310b838fb79a84f01448e34fbcbf0334 Mon Sep 17 00:00:00 2001
From: Benjamin Gaignard <benjamin.gaignard@collabora.com>
Date: Thu, 9 Nov 2023 17:29:16 +0100
Subject: media: videobuf2: Use vb2_buffer instead of index

Directly use vb2_buffer pointer instead of index inside queue array.

Signed-off-by: Benjamin Gaignard <benjamin.gaignard@collabora.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
---
 drivers/media/common/videobuf2/videobuf2-core.c | 40 ++++++-------------
 drivers/media/common/videobuf2/videobuf2-v4l2.c | 51 +++++++++++++++----------
 drivers/media/dvb-core/dvb_vb2.c                |  6 +--
 include/media/videobuf2-core.h                  | 16 ++++----
 4 files changed, 53 insertions(+), 60 deletions(-)

(limited to 'include')

diff --git a/drivers/media/common/videobuf2/videobuf2-core.c b/drivers/media/common/videobuf2/videobuf2-core.c
index 009ae53dbe3b..df515134bb0c 100644
--- a/drivers/media/common/videobuf2/videobuf2-core.c
+++ b/drivers/media/common/videobuf2/videobuf2-core.c
@@ -659,9 +659,9 @@ static bool __buffers_in_use(struct vb2_queue *q)
 	return false;
 }
 
-void vb2_core_querybuf(struct vb2_queue *q, unsigned int index, void *pb)
+void vb2_core_querybuf(struct vb2_queue *q, struct vb2_buffer *vb, void *pb)
 {
-	call_void_bufop(q, fill_user_buffer, q->bufs[index], pb);
+	call_void_bufop(q, fill_user_buffer, vb, pb);
 }
 EXPORT_SYMBOL_GPL(vb2_core_querybuf);
 
@@ -1495,9 +1495,6 @@ static void vb2_req_unprepare(struct media_request_object *obj)
 	WARN_ON(!vb->req_obj.req);
 }
 
-int vb2_core_qbuf(struct vb2_queue *q, unsigned int index, void *pb,
-		  struct media_request *req);
-
 static void vb2_req_queue(struct media_request_object *obj)
 {
 	struct vb2_buffer *vb = container_of(obj, struct vb2_buffer, req_obj);
@@ -1512,7 +1509,7 @@ static void vb2_req_queue(struct media_request_object *obj)
 	 * set. We just ignore that, and expect this will be caught the
 	 * next time vb2_req_prepare() is called.
 	 */
-	err = vb2_core_qbuf(vb->vb2_queue, vb->index, NULL, NULL);
+	err = vb2_core_qbuf(vb->vb2_queue, vb, NULL, NULL);
 	WARN_ON_ONCE(err && err != -EIO);
 	mutex_unlock(vb->vb2_queue->lock);
 }
@@ -1567,12 +1564,10 @@ unsigned int vb2_request_buffer_cnt(struct media_request *req)
 }
 EXPORT_SYMBOL_GPL(vb2_request_buffer_cnt);
 
-int vb2_core_prepare_buf(struct vb2_queue *q, unsigned int index, void *pb)
+int vb2_core_prepare_buf(struct vb2_queue *q, struct vb2_buffer *vb, void *pb)
 {
-	struct vb2_buffer *vb;
 	int ret;
 
-	vb = q->bufs[index];
 	if (vb->state != VB2_BUF_STATE_DEQUEUED) {
 		dprintk(q, 1, "invalid buffer state %s\n",
 			vb2_state_name(vb->state));
@@ -1659,10 +1654,9 @@ static int vb2_start_streaming(struct vb2_queue *q)
 	return ret;
 }
 
-int vb2_core_qbuf(struct vb2_queue *q, unsigned int index, void *pb,
+int vb2_core_qbuf(struct vb2_queue *q, struct vb2_buffer *vb, void *pb,
 		  struct media_request *req)
 {
-	struct vb2_buffer *vb;
 	enum vb2_buffer_state orig_state;
 	int ret;
 
@@ -1671,8 +1665,6 @@ int vb2_core_qbuf(struct vb2_queue *q, unsigned int index, void *pb,
 		return -EIO;
 	}
 
-	vb = q->bufs[index];
-
 	if (!req && vb->state != VB2_BUF_STATE_IN_REQUEST &&
 	    q->requires_requests) {
 		dprintk(q, 1, "qbuf requires a request\n");
@@ -2245,9 +2237,8 @@ static int __find_plane_by_offset(struct vb2_queue *q, unsigned long offset,
 }
 
 int vb2_core_expbuf(struct vb2_queue *q, int *fd, unsigned int type,
-		unsigned int index, unsigned int plane, unsigned int flags)
+		    struct vb2_buffer *vb, unsigned int plane, unsigned int flags)
 {
-	struct vb2_buffer *vb = NULL;
 	struct vb2_plane *vb_plane;
 	int ret;
 	struct dma_buf *dbuf;
@@ -2272,13 +2263,6 @@ int vb2_core_expbuf(struct vb2_queue *q, int *fd, unsigned int type,
 		return -EINVAL;
 	}
 
-	if (index >= q->num_buffers) {
-		dprintk(q, 1, "buffer index out of range\n");
-		return -EINVAL;
-	}
-
-	vb = q->bufs[index];
-
 	if (plane >= vb->num_planes) {
 		dprintk(q, 1, "buffer plane out of range\n");
 		return -EINVAL;
@@ -2297,20 +2281,20 @@ int vb2_core_expbuf(struct vb2_queue *q, int *fd, unsigned int type,
 			      flags & O_ACCMODE);
 	if (IS_ERR_OR_NULL(dbuf)) {
 		dprintk(q, 1, "failed to export buffer %d, plane %d\n",
-			index, plane);
+			vb->index, plane);
 		return -EINVAL;
 	}
 
 	ret = dma_buf_fd(dbuf, flags & ~O_ACCMODE);
 	if (ret < 0) {
 		dprintk(q, 3, "buffer %d, plane %d failed to export (%d)\n",
-			index, plane, ret);
+			vb->index, plane, ret);
 		dma_buf_put(dbuf);
 		return ret;
 	}
 
 	dprintk(q, 3, "buffer %d, plane %d exported as %d descriptor\n",
-		index, plane, ret);
+		vb->index, plane, ret);
 	*fd = ret;
 
 	return 0;
@@ -2715,7 +2699,7 @@ static int __vb2_init_fileio(struct vb2_queue *q, int read)
 		 * Queue all buffers.
 		 */
 		for (i = 0; i < q->num_buffers; i++) {
-			ret = vb2_core_qbuf(q, i, NULL, NULL);
+			ret = vb2_core_qbuf(q, q->bufs[i], NULL, NULL);
 			if (ret)
 				goto err_reqbufs;
 			fileio->bufs[i].queued = 1;
@@ -2900,7 +2884,7 @@ static size_t __vb2_perform_fileio(struct vb2_queue *q, char __user *data, size_
 
 		if (copy_timestamp)
 			b->timestamp = ktime_get_ns();
-		ret = vb2_core_qbuf(q, index, NULL, NULL);
+		ret = vb2_core_qbuf(q, b, NULL, NULL);
 		dprintk(q, 5, "vb2_qbuf result: %d\n", ret);
 		if (ret)
 			return ret;
@@ -3003,7 +2987,7 @@ static int vb2_thread(void *data)
 		if (copy_timestamp)
 			vb->timestamp = ktime_get_ns();
 		if (!threadio->stop)
-			ret = vb2_core_qbuf(q, vb->index, NULL, NULL);
+			ret = vb2_core_qbuf(q, vb, NULL, NULL);
 		call_void_qop(q, wait_prepare, q);
 		if (ret || threadio->stop)
 			break;
diff --git a/drivers/media/common/videobuf2/videobuf2-v4l2.c b/drivers/media/common/videobuf2/videobuf2-v4l2.c
index c7a54d82a55e..d19d82a75ac6 100644
--- a/drivers/media/common/videobuf2/videobuf2-v4l2.c
+++ b/drivers/media/common/videobuf2/videobuf2-v4l2.c
@@ -364,13 +364,12 @@ static void set_buffer_cache_hints(struct vb2_queue *q,
 }
 
 static int vb2_queue_or_prepare_buf(struct vb2_queue *q, struct media_device *mdev,
-				    struct v4l2_buffer *b, bool is_prepare,
-				    struct media_request **p_req)
+				    struct vb2_buffer *vb, struct v4l2_buffer *b,
+				    bool is_prepare, struct media_request **p_req)
 {
 	const char *opname = is_prepare ? "prepare_buf" : "qbuf";
 	struct media_request *req;
 	struct vb2_v4l2_buffer *vbuf;
-	struct vb2_buffer *vb;
 	int ret;
 
 	if (b->type != q->type) {
@@ -378,23 +377,11 @@ static int vb2_queue_or_prepare_buf(struct vb2_queue *q, struct media_device *md
 		return -EINVAL;
 	}
 
-	if (b->index >= q->num_buffers) {
-		dprintk(q, 1, "%s: buffer index out of range\n", opname);
-		return -EINVAL;
-	}
-
-	if (q->bufs[b->index] == NULL) {
-		/* Should never happen */
-		dprintk(q, 1, "%s: buffer is NULL\n", opname);
-		return -EINVAL;
-	}
-
 	if (b->memory != q->memory) {
 		dprintk(q, 1, "%s: invalid memory type\n", opname);
 		return -EINVAL;
 	}
 
-	vb = q->bufs[b->index];
 	vbuf = to_vb2_v4l2_buffer(vb);
 	ret = __verify_planes_array(vb, b);
 	if (ret)
@@ -667,7 +654,7 @@ int vb2_querybuf(struct vb2_queue *q, struct v4l2_buffer *b)
 	vb = q->bufs[b->index];
 	ret = __verify_planes_array(vb, b);
 	if (!ret)
-		vb2_core_querybuf(q, b->index, b);
+		vb2_core_querybuf(q, vb, b);
 	return ret;
 }
 EXPORT_SYMBOL(vb2_querybuf);
@@ -723,6 +710,7 @@ EXPORT_SYMBOL_GPL(vb2_reqbufs);
 int vb2_prepare_buf(struct vb2_queue *q, struct media_device *mdev,
 		    struct v4l2_buffer *b)
 {
+	struct vb2_buffer *vb;
 	int ret;
 
 	if (vb2_fileio_is_active(q)) {
@@ -733,9 +721,15 @@ int vb2_prepare_buf(struct vb2_queue *q, struct media_device *mdev,
 	if (b->flags & V4L2_BUF_FLAG_REQUEST_FD)
 		return -EINVAL;
 
-	ret = vb2_queue_or_prepare_buf(q, mdev, b, true, NULL);
+	if (b->index >= q->num_buffers) {
+		dprintk(q, 1, "buffer index out of range\n");
+		return -EINVAL;
+	}
+	vb = q->bufs[b->index];
 
-	return ret ? ret : vb2_core_prepare_buf(q, b->index, b);
+	ret = vb2_queue_or_prepare_buf(q, mdev, vb, b, true, NULL);
+
+	return ret ? ret : vb2_core_prepare_buf(q, vb, b);
 }
 EXPORT_SYMBOL_GPL(vb2_prepare_buf);
 
@@ -803,6 +797,7 @@ int vb2_qbuf(struct vb2_queue *q, struct media_device *mdev,
 	     struct v4l2_buffer *b)
 {
 	struct media_request *req = NULL;
+	struct vb2_buffer *vb;
 	int ret;
 
 	if (vb2_fileio_is_active(q)) {
@@ -810,10 +805,16 @@ int vb2_qbuf(struct vb2_queue *q, struct media_device *mdev,
 		return -EBUSY;
 	}
 
-	ret = vb2_queue_or_prepare_buf(q, mdev, b, false, &req);
+	if (b->index >= q->num_buffers) {
+		dprintk(q, 1, "buffer index out of range\n");
+		return -EINVAL;
+	}
+	vb = q->bufs[b->index];
+
+	ret = vb2_queue_or_prepare_buf(q, mdev, vb, b, false, &req);
 	if (ret)
 		return ret;
-	ret = vb2_core_qbuf(q, b->index, b, req);
+	ret = vb2_core_qbuf(q, vb, b, req);
 	if (req)
 		media_request_put(req);
 	return ret;
@@ -873,7 +874,15 @@ EXPORT_SYMBOL_GPL(vb2_streamoff);
 
 int vb2_expbuf(struct vb2_queue *q, struct v4l2_exportbuffer *eb)
 {
-	return vb2_core_expbuf(q, &eb->fd, eb->type, eb->index,
+	struct vb2_buffer *vb;
+
+	if (eb->index >= q->num_buffers) {
+		dprintk(q, 1, "buffer index out of range\n");
+		return -EINVAL;
+	}
+	vb = q->bufs[eb->index];
+
+	return vb2_core_expbuf(q, &eb->fd, eb->type, vb,
 				eb->plane, eb->flags);
 }
 EXPORT_SYMBOL_GPL(vb2_expbuf);
diff --git a/drivers/media/dvb-core/dvb_vb2.c b/drivers/media/dvb-core/dvb_vb2.c
index 909df82fed33..b322ef179f05 100644
--- a/drivers/media/dvb-core/dvb_vb2.c
+++ b/drivers/media/dvb-core/dvb_vb2.c
@@ -360,7 +360,7 @@ int dvb_vb2_querybuf(struct dvb_vb2_ctx *ctx, struct dmx_buffer *b)
 		dprintk(1, "[%s] buffer index out of range\n", ctx->name);
 		return -EINVAL;
 	}
-	vb2_core_querybuf(&ctx->vb_q, b->index, b);
+	vb2_core_querybuf(&ctx->vb_q, q->bufs[b->index], b);
 	dprintk(3, "[%s] index=%d\n", ctx->name, b->index);
 	return 0;
 }
@@ -370,7 +370,7 @@ int dvb_vb2_expbuf(struct dvb_vb2_ctx *ctx, struct dmx_exportbuffer *exp)
 	struct vb2_queue *q = &ctx->vb_q;
 	int ret;
 
-	ret = vb2_core_expbuf(&ctx->vb_q, &exp->fd, q->type, exp->index,
+	ret = vb2_core_expbuf(&ctx->vb_q, &exp->fd, q->type, q->bufs[exp->index],
 			      0, exp->flags);
 	if (ret) {
 		dprintk(1, "[%s] index=%d errno=%d\n", ctx->name,
@@ -391,7 +391,7 @@ int dvb_vb2_qbuf(struct dvb_vb2_ctx *ctx, struct dmx_buffer *b)
 		dprintk(1, "[%s] buffer index out of range\n", ctx->name);
 		return -EINVAL;
 	}
-	ret = vb2_core_qbuf(&ctx->vb_q, b->index, b, NULL);
+	ret = vb2_core_qbuf(&ctx->vb_q, q->bufs[b->index], b, NULL);
 	if (ret) {
 		dprintk(1, "[%s] index=%d errno=%d\n", ctx->name,
 			b->index, ret);
diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h
index 4b6a9d2ea372..cd3ff1cd759d 100644
--- a/include/media/videobuf2-core.h
+++ b/include/media/videobuf2-core.h
@@ -747,7 +747,7 @@ int vb2_wait_for_all_buffers(struct vb2_queue *q);
 /**
  * vb2_core_querybuf() - query video buffer information.
  * @q:		pointer to &struct vb2_queue with videobuf2 queue.
- * @index:	id number of the buffer.
+ * @vb:		pointer to struct &vb2_buffer.
  * @pb:		buffer struct passed from userspace.
  *
  * Videobuf2 core helper to implement VIDIOC_QUERYBUF() operation. It is called
@@ -759,7 +759,7 @@ int vb2_wait_for_all_buffers(struct vb2_queue *q);
  *
  * Return: returns zero on success; an error code otherwise.
  */
-void vb2_core_querybuf(struct vb2_queue *q, unsigned int index, void *pb);
+void vb2_core_querybuf(struct vb2_queue *q, struct vb2_buffer *vb, void *pb);
 
 /**
  * vb2_core_reqbufs() - Initiate streaming.
@@ -823,7 +823,7 @@ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory,
  * vb2_core_prepare_buf() - Pass ownership of a buffer from userspace
  *			to the kernel.
  * @q:		pointer to &struct vb2_queue with videobuf2 queue.
- * @index:	id number of the buffer.
+ * @vb:		pointer to struct &vb2_buffer.
  * @pb:		buffer structure passed from userspace to
  *		&v4l2_ioctl_ops->vidioc_prepare_buf handler in driver.
  *
@@ -839,13 +839,13 @@ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory,
  *
  * Return: returns zero on success; an error code otherwise.
  */
-int vb2_core_prepare_buf(struct vb2_queue *q, unsigned int index, void *pb);
+int vb2_core_prepare_buf(struct vb2_queue *q, struct vb2_buffer *vb, void *pb);
 
 /**
  * vb2_core_qbuf() - Queue a buffer from userspace
  *
  * @q:		pointer to &struct vb2_queue with videobuf2 queue.
- * @index:	id number of the buffer
+ * @vb:		pointer to struct &vb2_buffer.
  * @pb:		buffer structure passed from userspace to
  *		v4l2_ioctl_ops->vidioc_qbuf handler in driver
  * @req:	pointer to &struct media_request, may be NULL.
@@ -867,7 +867,7 @@ int vb2_core_prepare_buf(struct vb2_queue *q, unsigned int index, void *pb);
  *
  * Return: returns zero on success; an error code otherwise.
  */
-int vb2_core_qbuf(struct vb2_queue *q, unsigned int index, void *pb,
+int vb2_core_qbuf(struct vb2_queue *q, struct vb2_buffer *vb, void *pb,
 		  struct media_request *req);
 
 /**
@@ -931,7 +931,7 @@ int vb2_core_streamoff(struct vb2_queue *q, unsigned int type);
  * @fd:		pointer to the file descriptor associated with DMABUF
  *		(set by driver).
  * @type:	buffer type.
- * @index:	id number of the buffer.
+ * @vb:		pointer to struct &vb2_buffer.
  * @plane:	index of the plane to be exported, 0 for single plane queues
  * @flags:	file flags for newly created file, as defined at
  *		include/uapi/asm-generic/fcntl.h.
@@ -945,7 +945,7 @@ int vb2_core_streamoff(struct vb2_queue *q, unsigned int type);
  * Return: returns zero on success; an error code otherwise.
  */
 int vb2_core_expbuf(struct vb2_queue *q, int *fd, unsigned int type,
-		unsigned int index, unsigned int plane, unsigned int flags);
+		    struct vb2_buffer *vb, unsigned int plane, unsigned int flags);
 
 /**
  * vb2_core_queue_init() - initialize a videobuf2 queue
-- 
cgit v1.2.3


From 741d0f6b51032a35446ac72ee8a04fcfa938ee2e Mon Sep 17 00:00:00 2001
From: Benjamin Gaignard <benjamin.gaignard@collabora.com>
Date: Thu, 9 Nov 2023 17:29:19 +0100
Subject: media: videobuf2: Add helper to get queue number of buffers

In the future a side effect of introducing DELETE_BUFS ioctl is
the create of 'holes' (i.e. unused buffers) in bufs arrays.
To know which entries of the bufs arrays are used a bitmap will
be added in struct vb2_queue. That will also mean that the number
of buffers will be computed given the number of bit set in this bitmap.
To smoothly allow this evolution all drives must stop using
directly num_buffers field from struct vb2_queue.

Signed-off-by: Benjamin Gaignard <benjamin.gaignard@collabora.com>
Reviewed-by: Andrzej Pietrasiewicz <andrzej.p@collabora.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
---
 include/media/videobuf2-core.h | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h
index cd3ff1cd759d..8f9d9e4af5b1 100644
--- a/include/media/videobuf2-core.h
+++ b/include/media/videobuf2-core.h
@@ -1139,6 +1139,15 @@ static inline bool vb2_fileio_is_active(struct vb2_queue *q)
 	return q->fileio;
 }
 
+/**
+ * vb2_get_num_buffers() - get the number of buffer in a queue
+ * @q:		pointer to &struct vb2_queue with videobuf2 queue.
+ */
+static inline unsigned int vb2_get_num_buffers(struct vb2_queue *q)
+{
+	return q->num_buffers;
+}
+
 /**
  * vb2_is_busy() - return busy status of the queue.
  * @q:		pointer to &struct vb2_queue with videobuf2 queue.
@@ -1147,7 +1156,7 @@ static inline bool vb2_fileio_is_active(struct vb2_queue *q)
  */
 static inline bool vb2_is_busy(struct vb2_queue *q)
 {
-	return (q->num_buffers > 0);
+	return vb2_get_num_buffers(q) > 0;
 }
 
 /**
-- 
cgit v1.2.3


From c838530d230bc638d79b78737fc4488ffc28c1ee Mon Sep 17 00:00:00 2001
From: Benjamin Gaignard <benjamin.gaignard@collabora.com>
Date: Thu, 9 Nov 2023 17:34:59 +0100
Subject: media: media videobuf2: Be more flexible on the number of queue
 stored buffers

Add 'max_num_buffers' field in vb2_queue struct to let drivers decide
how many buffers could be stored in a queue.
This require 'bufs' array to be allocated at queue init time and freed
when releasing the queue.
By default VB2_MAX_FRAME remains the limit.

Signed-off-by: Benjamin Gaignard <benjamin.gaignard@collabora.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
---
 drivers/media/common/videobuf2/videobuf2-core.c | 46 ++++++++++++++++++++-----
 drivers/media/common/videobuf2/videobuf2-v4l2.c |  6 ++--
 include/media/videobuf2-core.h                  | 12 ++++++-
 3 files changed, 52 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/drivers/media/common/videobuf2/videobuf2-core.c b/drivers/media/common/videobuf2/videobuf2-core.c
index ce5b84b9bcd4..8c1df829745b 100644
--- a/drivers/media/common/videobuf2/videobuf2-core.c
+++ b/drivers/media/common/videobuf2/videobuf2-core.c
@@ -421,7 +421,7 @@ static void init_buffer_cache_hints(struct vb2_queue *q, struct vb2_buffer *vb)
  */
 static void vb2_queue_add_buffer(struct vb2_queue *q, struct vb2_buffer *vb, unsigned int index)
 {
-	WARN_ON(index >= VB2_MAX_FRAME || q->bufs[index] || vb->vb2_queue);
+	WARN_ON(index >= q->max_num_buffers || q->bufs[index] || vb->vb2_queue);
 
 	q->bufs[index] = vb;
 	vb->index = index;
@@ -454,9 +454,12 @@ static int __vb2_queue_alloc(struct vb2_queue *q, enum vb2_memory memory,
 	struct vb2_buffer *vb;
 	int ret;
 
-	/* Ensure that q->num_buffers+num_buffers is below VB2_MAX_FRAME */
+	/*
+	 * Ensure that the number of already queue + the number of buffers already
+	 * in the queue is below q->max_num_buffers
+	 */
 	num_buffers = min_t(unsigned int, num_buffers,
-			    VB2_MAX_FRAME - q_num_buffers);
+			    q->max_num_buffers - q_num_buffers);
 
 	for (buffer = 0; buffer < num_buffers; ++buffer) {
 		/* Allocate vb2 buffer structures */
@@ -818,7 +821,7 @@ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory,
 	unsigned plane_sizes[VB2_MAX_PLANES] = { };
 	bool non_coherent_mem = flags & V4L2_MEMORY_FLAG_NON_COHERENT;
 	unsigned int i;
-	int ret;
+	int ret = 0;
 
 	if (q->streaming) {
 		dprintk(q, 1, "streaming active\n");
@@ -862,17 +865,22 @@ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory,
 	/*
 	 * Make sure the requested values and current defaults are sane.
 	 */
-	WARN_ON(q->min_buffers_needed > VB2_MAX_FRAME);
 	num_buffers = max_t(unsigned int, *count, q->min_buffers_needed);
-	num_buffers = min_t(unsigned int, num_buffers, VB2_MAX_FRAME);
+	num_buffers = min_t(unsigned int, num_buffers, q->max_num_buffers);
 	memset(q->alloc_devs, 0, sizeof(q->alloc_devs));
 	/*
 	 * Set this now to ensure that drivers see the correct q->memory value
 	 * in the queue_setup op.
 	 */
 	mutex_lock(&q->mmap_lock);
+	if (!q->bufs)
+		q->bufs = kcalloc(q->max_num_buffers, sizeof(*q->bufs), GFP_KERNEL);
+	if (!q->bufs)
+		ret = -ENOMEM;
 	q->memory = memory;
 	mutex_unlock(&q->mmap_lock);
+	if (ret)
+		return ret;
 	set_queue_coherency(q, non_coherent_mem);
 
 	/*
@@ -981,7 +989,7 @@ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory,
 	bool no_previous_buffers = !q_num_bufs;
 	int ret = 0;
 
-	if (q_num_bufs == VB2_MAX_FRAME) {
+	if (q->num_buffers == q->max_num_buffers) {
 		dprintk(q, 1, "maximum number of buffers already allocated\n");
 		return -ENOBUFS;
 	}
@@ -998,7 +1006,13 @@ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory,
 		 */
 		mutex_lock(&q->mmap_lock);
 		q->memory = memory;
+		if (!q->bufs)
+			q->bufs = kcalloc(q->max_num_buffers, sizeof(*q->bufs), GFP_KERNEL);
+		if (!q->bufs)
+			ret = -ENOMEM;
 		mutex_unlock(&q->mmap_lock);
+		if (ret)
+			return ret;
 		q->waiting_for_buffers = !q->is_output;
 		set_queue_coherency(q, non_coherent_mem);
 	} else {
@@ -1010,7 +1024,7 @@ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory,
 			return -EINVAL;
 	}
 
-	num_buffers = min(*count, VB2_MAX_FRAME - q_num_bufs);
+	num_buffers = min(*count, q->max_num_buffers - q_num_bufs);
 
 	if (requested_planes && requested_sizes) {
 		num_planes = requested_planes;
@@ -2470,6 +2484,16 @@ int vb2_core_queue_init(struct vb2_queue *q)
 	/*
 	 * Sanity check
 	 */
+	/*
+	 * For drivers who don't support max_num_buffers ensure
+	 * a backward compatibility.
+	 */
+	if (!q->max_num_buffers)
+		q->max_num_buffers = VB2_MAX_FRAME;
+
+	/* The maximum is limited by offset cookie encoding pattern */
+	q->max_num_buffers = min_t(unsigned int, q->max_num_buffers, MAX_BUFFER_INDEX);
+
 	if (WARN_ON(!q)			  ||
 	    WARN_ON(!q->ops)		  ||
 	    WARN_ON(!q->mem_ops)	  ||
@@ -2479,6 +2503,10 @@ int vb2_core_queue_init(struct vb2_queue *q)
 	    WARN_ON(!q->ops->buf_queue))
 		return -EINVAL;
 
+	if (WARN_ON(q->max_num_buffers > MAX_BUFFER_INDEX) ||
+	    WARN_ON(q->min_buffers_needed > q->max_num_buffers))
+		return -EINVAL;
+
 	if (WARN_ON(q->requires_requests && !q->supports_requests))
 		return -EINVAL;
 
@@ -2525,6 +2553,8 @@ void vb2_core_queue_release(struct vb2_queue *q)
 	__vb2_queue_cancel(q);
 	mutex_lock(&q->mmap_lock);
 	__vb2_queue_free(q, vb2_get_num_buffers(q));
+	kfree(q->bufs);
+	q->bufs = NULL;
 	mutex_unlock(&q->mmap_lock);
 }
 EXPORT_SYMBOL_GPL(vb2_core_queue_release);
diff --git a/drivers/media/common/videobuf2/videobuf2-v4l2.c b/drivers/media/common/videobuf2/videobuf2-v4l2.c
index 9d3b828cc804..3d71c205406d 100644
--- a/drivers/media/common/videobuf2/videobuf2-v4l2.c
+++ b/drivers/media/common/videobuf2/videobuf2-v4l2.c
@@ -621,7 +621,7 @@ struct vb2_buffer *vb2_find_buffer(struct vb2_queue *q, u64 timestamp)
 	 * This loop doesn't scale if there is a really large number of buffers.
 	 * Maybe something more efficient will be needed in this case.
 	 */
-	for (i = 0; i < vb2_get_num_buffers(q); i++) {
+	for (i = 0; i < q->max_num_buffers; i++) {
 		vb2 = vb2_get_buffer(q, i);
 
 		if (!vb2)
@@ -1136,7 +1136,7 @@ int _vb2_fop_release(struct file *file, struct mutex *lock)
 
 	if (lock)
 		mutex_lock(lock);
-	if (file->private_data == vdev->queue->owner) {
+	if (!vdev->queue->owner || file->private_data == vdev->queue->owner) {
 		vb2_queue_release(vdev->queue);
 		vdev->queue->owner = NULL;
 	}
@@ -1264,7 +1264,7 @@ void vb2_video_unregister_device(struct video_device *vdev)
 	 */
 	get_device(&vdev->dev);
 	video_unregister_device(vdev);
-	if (vdev->queue && vdev->queue->owner) {
+	if (vdev->queue) {
 		struct mutex *lock = vdev->queue->lock ?
 			vdev->queue->lock : vdev->lock;
 
diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h
index 8f9d9e4af5b1..5557d78b6f20 100644
--- a/include/media/videobuf2-core.h
+++ b/include/media/videobuf2-core.h
@@ -558,6 +558,9 @@ struct vb2_buf_ops {
  * @dma_dir:	DMA mapping direction.
  * @bufs:	videobuf2 buffer structures
  * @num_buffers: number of allocated/used buffers
+ * @max_num_buffers: upper limit of number of allocated/used buffers.
+ *		     If set to 0 v4l2 core will change it VB2_MAX_FRAME
+ *		     for backward compatibility.
  * @queued_list: list of buffers currently queued from userspace
  * @queued_count: number of buffers queued and ready for streaming.
  * @owned_by_drv_count: number of buffers owned by the driver
@@ -619,8 +622,9 @@ struct vb2_queue {
 	struct mutex			mmap_lock;
 	unsigned int			memory;
 	enum dma_data_direction		dma_dir;
-	struct vb2_buffer		*bufs[VB2_MAX_FRAME];
+	struct vb2_buffer		**bufs;
 	unsigned int			num_buffers;
+	unsigned int			max_num_buffers;
 
 	struct list_head		queued_list;
 	unsigned int			queued_count;
@@ -1248,6 +1252,12 @@ static inline void vb2_clear_last_buffer_dequeued(struct vb2_queue *q)
 static inline struct vb2_buffer *vb2_get_buffer(struct vb2_queue *q,
 						unsigned int index)
 {
+	if (!q->bufs)
+		return NULL;
+
+	if (index >= q->max_num_buffers)
+		return NULL;
+
 	if (index < q->num_buffers)
 		return q->bufs[index];
 	return NULL;
-- 
cgit v1.2.3


From d055a76c006540defd4eb80dcdea217cee0a141a Mon Sep 17 00:00:00 2001
From: Benjamin Gaignard <benjamin.gaignard@collabora.com>
Date: Thu, 9 Nov 2023 17:35:00 +0100
Subject: media: core: Report the maximum possible number of buffers for the
 queue

Use one of the struct v4l2_create_buffers reserved bytes to report
the maximum possible number of buffers for the queue.
V4l2 framework set V4L2_BUF_CAP_SUPPORTS_MAX_NUM_BUFFERS flags in queue
capabilities so userland can know when the field is valid.
Does the same change in v4l2_create_buffers32 structure.

Signed-off-by: Benjamin Gaignard <benjamin.gaignard@collabora.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
---
 Documentation/userspace-api/media/v4l/vidioc-create-bufs.rst |  8 ++++++--
 Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst     |  1 +
 drivers/media/common/videobuf2/videobuf2-v4l2.c              |  2 ++
 drivers/media/v4l2-core/v4l2-compat-ioctl32.c                | 10 +++++++++-
 drivers/media/v4l2-core/v4l2-ioctl.c                         |  4 ++--
 include/uapi/linux/videodev2.h                               |  7 ++++++-
 6 files changed, 26 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/Documentation/userspace-api/media/v4l/vidioc-create-bufs.rst b/Documentation/userspace-api/media/v4l/vidioc-create-bufs.rst
index a048a9f6b7b6..49232c9006c2 100644
--- a/Documentation/userspace-api/media/v4l/vidioc-create-bufs.rst
+++ b/Documentation/userspace-api/media/v4l/vidioc-create-bufs.rst
@@ -116,9 +116,13 @@ than the number requested.
       - ``flags``
       - Specifies additional buffer management attributes.
 	See :ref:`memory-flags`.
-
     * - __u32
-      - ``reserved``\ [6]
+      - ``max_num_buffers``
+      - If the V4L2_BUF_CAP_SUPPORTS_MAX_NUM_BUFFERS capability flag is set
+        this field indicates the maximum possible number of buffers
+        for this queue.
+    * - __u32
+      - ``reserved``\ [5]
       - A place holder for future extensions. Drivers and applications
 	must set the array to zero.
 
diff --git a/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst b/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst
index 099fa6695167..0b3a41a45d05 100644
--- a/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst
+++ b/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst
@@ -120,6 +120,7 @@ aborting or finishing any DMA in progress, an implicit
 .. _V4L2-BUF-CAP-SUPPORTS-ORPHANED-BUFS:
 .. _V4L2-BUF-CAP-SUPPORTS-M2M-HOLD-CAPTURE-BUF:
 .. _V4L2-BUF-CAP-SUPPORTS-MMAP-CACHE-HINTS:
+.. _V4L2-BUF-CAP-SUPPORTS-MAX-NUM-BUFFERS:
 
 .. raw:: latex
 
diff --git a/drivers/media/common/videobuf2/videobuf2-v4l2.c b/drivers/media/common/videobuf2/videobuf2-v4l2.c
index 3d71c205406d..440c3b1c18ec 100644
--- a/drivers/media/common/videobuf2/videobuf2-v4l2.c
+++ b/drivers/media/common/videobuf2/videobuf2-v4l2.c
@@ -756,6 +756,8 @@ int vb2_create_bufs(struct vb2_queue *q, struct v4l2_create_buffers *create)
 	fill_buf_caps(q, &create->capabilities);
 	validate_memory_flags(q, create->memory, &create->flags);
 	create->index = vb2_get_num_buffers(q);
+	create->max_num_buffers = q->max_num_buffers;
+	create->capabilities |= V4L2_BUF_CAP_SUPPORTS_MAX_NUM_BUFFERS;
 	if (create->count == 0)
 		return ret != -EBUSY ? ret : 0;
 
diff --git a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
index f3bed37859a2..8c07400bd280 100644
--- a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
+++ b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
@@ -116,6 +116,9 @@ struct v4l2_format32 {
  * @flags:	additional buffer management attributes (ignored unless the
  *		queue has V4L2_BUF_CAP_SUPPORTS_MMAP_CACHE_HINTS capability and
  *		configured for MMAP streaming I/O).
+ * @max_num_buffers: if V4L2_BUF_CAP_SUPPORTS_MAX_NUM_BUFFERS capability flag is set
+ *		this field indicate the maximum possible number of buffers
+ *		for this queue.
  * @reserved:	future extensions
  */
 struct v4l2_create_buffers32 {
@@ -125,7 +128,8 @@ struct v4l2_create_buffers32 {
 	struct v4l2_format32	format;
 	__u32			capabilities;
 	__u32			flags;
-	__u32			reserved[6];
+	__u32			max_num_buffers;
+	__u32			reserved[5];
 };
 
 static int get_v4l2_format32(struct v4l2_format *p64,
@@ -175,6 +179,9 @@ static int get_v4l2_create32(struct v4l2_create_buffers *p64,
 		return -EFAULT;
 	if (copy_from_user(&p64->flags, &p32->flags, sizeof(p32->flags)))
 		return -EFAULT;
+	if (copy_from_user(&p64->max_num_buffers, &p32->max_num_buffers,
+			   sizeof(p32->max_num_buffers)))
+		return -EFAULT;
 	return get_v4l2_format32(&p64->format, &p32->format);
 }
 
@@ -221,6 +228,7 @@ static int put_v4l2_create32(struct v4l2_create_buffers *p64,
 			 offsetof(struct v4l2_create_buffers32, format)) ||
 	    put_user(p64->capabilities, &p32->capabilities) ||
 	    put_user(p64->flags, &p32->flags) ||
+	    put_user(p64->max_num_buffers, &p32->max_num_buffers) ||
 	    copy_to_user(p32->reserved, p64->reserved, sizeof(p64->reserved)))
 		return -EFAULT;
 	return put_v4l2_format32(&p64->format, &p32->format);
diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c
index 9b1de54ce379..4d90424cbfc4 100644
--- a/drivers/media/v4l2-core/v4l2-ioctl.c
+++ b/drivers/media/v4l2-core/v4l2-ioctl.c
@@ -483,9 +483,9 @@ static void v4l_print_create_buffers(const void *arg, bool write_only)
 {
 	const struct v4l2_create_buffers *p = arg;
 
-	pr_cont("index=%d, count=%d, memory=%s, capabilities=0x%08x, ",
+	pr_cont("index=%d, count=%d, memory=%s, capabilities=0x%08x, max num buffers=%u",
 		p->index, p->count, prt_names(p->memory, v4l2_memory_names),
-		p->capabilities);
+		p->capabilities, p->max_num_buffers);
 	v4l_print_format(&p->format, write_only);
 }
 
diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index c3d4e490ce7c..13ddb5abf584 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -1035,6 +1035,7 @@ struct v4l2_requestbuffers {
 #define V4L2_BUF_CAP_SUPPORTS_ORPHANED_BUFS		(1 << 4)
 #define V4L2_BUF_CAP_SUPPORTS_M2M_HOLD_CAPTURE_BUF	(1 << 5)
 #define V4L2_BUF_CAP_SUPPORTS_MMAP_CACHE_HINTS		(1 << 6)
+#define V4L2_BUF_CAP_SUPPORTS_MAX_NUM_BUFFERS		(1 << 7)
 
 /**
  * struct v4l2_plane - plane info for multi-planar buffers
@@ -2605,6 +2606,9 @@ struct v4l2_dbg_chip_info {
  * @flags:	additional buffer management attributes (ignored unless the
  *		queue has V4L2_BUF_CAP_SUPPORTS_MMAP_CACHE_HINTS capability
  *		and configured for MMAP streaming I/O).
+ * @max_num_buffers: if V4L2_BUF_CAP_SUPPORTS_MAX_NUM_BUFFERS capability flag is set
+ *		this field indicate the maximum possible number of buffers
+ *		for this queue.
  * @reserved:	future extensions
  */
 struct v4l2_create_buffers {
@@ -2614,7 +2618,8 @@ struct v4l2_create_buffers {
 	struct v4l2_format	format;
 	__u32			capabilities;
 	__u32			flags;
-	__u32			reserved[6];
+	__u32			max_num_buffers;
+	__u32			reserved[5];
 };
 
 /*
-- 
cgit v1.2.3


From 632b8b044a940e415c6d9bd5235778b0db28add1 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Date: Wed, 11 Oct 2023 10:17:59 +0200
Subject: media: cec: core: count low-drive, error and arb-lost conditions

Count how many Low Drive, Error and Arbitration Lost transmit
status errors occurred, and expose that in debugfs.

Also log the first 8 transmits that result in Low Drive or Error
conditions. That really should not happen with well-behaved CEC devices
and good HDMI cables.

This is useful to detect and debug HDMI cable issues.

Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
---
 drivers/media/cec/core/cec-adap.c | 54 +++++++++++++++++++++++++++++++++++----
 include/media/cec.h               | 22 ++++++++++++++--
 2 files changed, 69 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/media/cec/core/cec-adap.c b/drivers/media/cec/core/cec-adap.c
index 6bb49bb3f98c..5741adf09a2e 100644
--- a/drivers/media/cec/core/cec-adap.c
+++ b/drivers/media/cec/core/cec-adap.c
@@ -511,7 +511,7 @@ int cec_thread_func(void *_adap)
 				pr_warn("cec-%s: transmit timed out\n", adap->name);
 			}
 			adap->transmit_in_progress = false;
-			adap->tx_timeouts++;
+			adap->tx_timeout_cnt++;
 			goto unlock;
 		}
 
@@ -625,6 +625,33 @@ void cec_transmit_done_ts(struct cec_adapter *adap, u8 status,
 	msg->tx_low_drive_cnt += low_drive_cnt;
 	msg->tx_error_cnt += error_cnt;
 
+	adap->tx_arb_lost_cnt += arb_lost_cnt;
+	adap->tx_low_drive_cnt += low_drive_cnt;
+	adap->tx_error_cnt += error_cnt;
+
+	/*
+	 * Low Drive transmission errors should really not happen for
+	 * well-behaved CEC devices and proper HDMI cables.
+	 *
+	 * Ditto for the 'Error' status.
+	 *
+	 * For the first few times that this happens, log this.
+	 * Stop logging after that, since that will not add any more
+	 * useful information and instead it will just flood the kernel log.
+	 */
+	if (done && adap->tx_low_drive_log_cnt < 8 && msg->tx_low_drive_cnt) {
+		adap->tx_low_drive_log_cnt++;
+		dprintk(0, "low drive counter: %u (seq %u: %*ph)\n",
+			msg->tx_low_drive_cnt, msg->sequence,
+			msg->len, msg->msg);
+	}
+	if (done && adap->tx_error_log_cnt < 8 && msg->tx_error_cnt) {
+		adap->tx_error_log_cnt++;
+		dprintk(0, "error counter: %u (seq %u: %*ph)\n",
+			msg->tx_error_cnt, msg->sequence,
+			msg->len, msg->msg);
+	}
+
 	/* Mark that we're done with this transmit */
 	adap->transmitting = NULL;
 
@@ -1607,6 +1634,8 @@ int cec_adap_enable(struct cec_adapter *adap)
 	if (enable) {
 		adap->last_initiator = 0xff;
 		adap->transmit_in_progress = false;
+		adap->tx_low_drive_log_cnt = 0;
+		adap->tx_error_log_cnt = 0;
 		ret = adap->ops->adap_enable(adap, true);
 		if (!ret) {
 			/*
@@ -2265,10 +2294,25 @@ int cec_adap_status(struct seq_file *file, void *priv)
 	if (adap->monitor_pin_cnt)
 		seq_printf(file, "file handles in Monitor Pin mode: %u\n",
 			   adap->monitor_pin_cnt);
-	if (adap->tx_timeouts) {
-		seq_printf(file, "transmit timeouts: %u\n",
-			   adap->tx_timeouts);
-		adap->tx_timeouts = 0;
+	if (adap->tx_timeout_cnt) {
+		seq_printf(file, "transmit timeout count: %u\n",
+			   adap->tx_timeout_cnt);
+		adap->tx_timeout_cnt = 0;
+	}
+	if (adap->tx_low_drive_cnt) {
+		seq_printf(file, "transmit low drive count: %u\n",
+			   adap->tx_low_drive_cnt);
+		adap->tx_low_drive_cnt = 0;
+	}
+	if (adap->tx_arb_lost_cnt) {
+		seq_printf(file, "transmit arbitration lost count: %u\n",
+			   adap->tx_arb_lost_cnt);
+		adap->tx_arb_lost_cnt = 0;
+	}
+	if (adap->tx_error_cnt) {
+		seq_printf(file, "transmit error count: %u\n",
+			   adap->tx_error_cnt);
+		adap->tx_error_cnt = 0;
 	}
 	data = adap->transmitting;
 	if (data)
diff --git a/include/media/cec.h b/include/media/cec.h
index 53e4b2eb2b26..d77982685116 100644
--- a/include/media/cec.h
+++ b/include/media/cec.h
@@ -207,7 +207,20 @@ struct cec_adap_ops {
  *	passthrough mode.
  * @log_addrs:		current logical addresses
  * @conn_info:		current connector info
- * @tx_timeouts:	number of transmit timeouts
+ * @tx_timeout_cnt:	count the number of Timed Out transmits.
+ *			Reset to 0 when this is reported in cec_adap_status().
+ * @tx_low_drive_cnt:	count the number of Low Drive transmits.
+ *			Reset to 0 when this is reported in cec_adap_status().
+ * @tx_error_cnt:	count the number of Error transmits.
+ *			Reset to 0 when this is reported in cec_adap_status().
+ * @tx_arb_lost_cnt:	count the number of Arb Lost transmits.
+ *			Reset to 0 when this is reported in cec_adap_status().
+ * @tx_low_drive_log_cnt: number of logged Low Drive transmits since the
+ *			adapter was enabled. Used to avoid flooding the kernel
+ *			log if this happens a lot.
+ * @tx_error_log_cnt:	number of logged Error transmits since the adapter was
+ *                      enabled. Used to avoid flooding the kernel log if this
+ *                      happens a lot.
  * @notifier:		CEC notifier
  * @pin:		CEC pin status struct
  * @cec_dir:		debugfs cec directory
@@ -262,7 +275,12 @@ struct cec_adapter {
 	struct cec_log_addrs log_addrs;
 	struct cec_connector_info conn_info;
 
-	u32 tx_timeouts;
+	u32 tx_timeout_cnt;
+	u32 tx_low_drive_cnt;
+	u32 tx_error_cnt;
+	u32 tx_arb_lost_cnt;
+	u32 tx_low_drive_log_cnt;
+	u32 tx_error_log_cnt;
 
 #ifdef CONFIG_CEC_NOTIFIER
 	struct cec_notifier *notifier;
-- 
cgit v1.2.3


From ed5000fe5ac48980bf0b2a707c64bba184dd83d2 Mon Sep 17 00:00:00 2001
From: Deborah Brouwer <deborah.brouwer@collabora.com>
Date: Thu, 9 Nov 2023 20:16:43 +0100
Subject: media: v4l2-mem2mem.h: fix typo in comment

The comment describing the function v4l2_m2m_last_src_buf() says that this
function returns the last destination buffer when it actually returns the
last source buffer. Fix the comment so that it is accurate.

Signed-off-by: Deborah Brouwer <deborah.brouwer@collabora.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
---
 include/media/v4l2-mem2mem.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/media/v4l2-mem2mem.h b/include/media/v4l2-mem2mem.h
index 1288fe364fab..7f1af1f7f912 100644
--- a/include/media/v4l2-mem2mem.h
+++ b/include/media/v4l2-mem2mem.h
@@ -668,7 +668,7 @@ v4l2_m2m_next_dst_buf(struct v4l2_m2m_ctx *m2m_ctx)
 struct vb2_v4l2_buffer *v4l2_m2m_last_buf(struct v4l2_m2m_queue_ctx *q_ctx);
 
 /**
- * v4l2_m2m_last_src_buf() - return last destination buffer from the list of
+ * v4l2_m2m_last_src_buf() - return last source buffer from the list of
  * ready buffers
  *
  * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx
-- 
cgit v1.2.3


From 70be8a84017a4454429abc40dec40a1f845c7827 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Date: Tue, 14 Nov 2023 11:39:44 +0100
Subject: media: videodev2.h: add missing __user to p_h264_pps

The p_h264_pps pointer in struct v4l2_ext_control was missing the
__user annotation. Add this.

Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
---
 include/uapi/linux/videodev2.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index 13ddb5abf584..c3fc710ef9a7 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -1817,7 +1817,7 @@ struct v4l2_ext_control {
 		__s64 __user *p_s64;
 		struct v4l2_area __user *p_area;
 		struct v4l2_ctrl_h264_sps __user *p_h264_sps;
-		struct v4l2_ctrl_h264_pps *p_h264_pps;
+		struct v4l2_ctrl_h264_pps __user *p_h264_pps;
 		struct v4l2_ctrl_h264_scaling_matrix __user *p_h264_scaling_matrix;
 		struct v4l2_ctrl_h264_pred_weights __user *p_h264_pred_weights;
 		struct v4l2_ctrl_h264_slice_params __user *p_h264_slice_params;
-- 
cgit v1.2.3


From 26846dda3eca07cbb8dd481421ae52b31ef232d5 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Date: Tue, 14 Nov 2023 11:50:36 +0100
Subject: media: videodev.h: add missing p_hdr10_* pointers

The HDR10 standard compound controls were missing the corresponding
pointers in videodev2.h. Add these and document them.

Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
---
 Documentation/userspace-api/media/v4l/vidioc-g-ext-ctrls.rst | 8 ++++++++
 include/uapi/linux/videodev2.h                               | 2 ++
 2 files changed, 10 insertions(+)

(limited to 'include')

diff --git a/Documentation/userspace-api/media/v4l/vidioc-g-ext-ctrls.rst b/Documentation/userspace-api/media/v4l/vidioc-g-ext-ctrls.rst
index f9f73530a6be..4d56c0528ad7 100644
--- a/Documentation/userspace-api/media/v4l/vidioc-g-ext-ctrls.rst
+++ b/Documentation/userspace-api/media/v4l/vidioc-g-ext-ctrls.rst
@@ -295,6 +295,14 @@ still cause this situation.
       - ``p_av1_film_grain``
       - A pointer to a struct :c:type:`v4l2_ctrl_av1_film_grain`. Valid if this control is
         of type ``V4L2_CTRL_TYPE_AV1_FILM_GRAIN``.
+    * - struct :c:type:`v4l2_ctrl_hdr10_cll_info` *
+      - ``p_hdr10_cll_info``
+      - A pointer to a struct :c:type:`v4l2_ctrl_hdr10_cll_info`. Valid if this control is
+        of type ``V4L2_CTRL_TYPE_HDR10_CLL_INFO``.
+    * - struct :c:type:`v4l2_ctrl_hdr10_mastering_display` *
+      - ``p_hdr10_mastering_display``
+      - A pointer to a struct :c:type:`v4l2_ctrl_hdr10_mastering_display`. Valid if this control is
+        of type ``V4L2_CTRL_TYPE_HDR10_MASTERING_DISPLAY``.
     * - void *
       - ``ptr``
       - A pointer to a compound type which can be an N-dimensional array
diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index c3fc710ef9a7..68e7ac178cc2 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -1838,6 +1838,8 @@ struct v4l2_ext_control {
 		struct v4l2_ctrl_av1_tile_group_entry __user *p_av1_tile_group_entry;
 		struct v4l2_ctrl_av1_frame __user *p_av1_frame;
 		struct v4l2_ctrl_av1_film_grain __user *p_av1_film_grain;
+		struct v4l2_ctrl_hdr10_cll_info __user *p_hdr10_cll_info;
+		struct v4l2_ctrl_hdr10_mastering_display __user *p_hdr10_mastering_display;
 		void __user *ptr;
 	};
 } __attribute__ ((packed));
-- 
cgit v1.2.3


From a769154c7cac037914ba375ae88aae55b2c853e0 Mon Sep 17 00:00:00 2001
From: Hardik Gajjar <hgajjar@de.adit-jv.com>
Date: Fri, 27 Oct 2023 17:20:28 +0200
Subject: usb: xhci: Add timeout argument in address_device USB HCD callback

- The HCD address_device callback now accepts a user-defined timeout value
  in milliseconds, providing better control over command execution times.
- The default timeout value for the address_device command has been set
  to 5000 ms, aligning with the USB 3.2 specification. However, this
  timeout can be adjusted as needed.
- The xhci_setup_device function has been updated to accept the timeout
  value, allowing it to specify the maximum wait time for the command
  operation to complete.
- The hub driver has also been updated to accommodate the newly added
  timeout parameter during the SET_ADDRESS request.

Signed-off-by: Hardik Gajjar <hgajjar@de.adit-jv.com>
Reviewed-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20231027152029.104363-1-hgajjar@de.adit-jv.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/hub.c       |  2 +-
 drivers/usb/host/xhci-mem.c  |  2 ++
 drivers/usb/host/xhci-ring.c | 11 ++++++-----
 drivers/usb/host/xhci.c      | 23 ++++++++++++++++-------
 drivers/usb/host/xhci.h      |  9 +++++++--
 include/linux/usb/hcd.h      |  5 +++--
 6 files changed, 35 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index b4584a0cd484..049058264367 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -4662,7 +4662,7 @@ static int hub_set_address(struct usb_device *udev, int devnum)
 	if (udev->state != USB_STATE_DEFAULT)
 		return -EINVAL;
 	if (hcd->driver->address_device)
-		retval = hcd->driver->address_device(hcd, udev);
+		retval = hcd->driver->address_device(hcd, udev, USB_CTRL_SET_TIMEOUT);
 	else
 		retval = usb_control_msg(udev, usb_sndaddr0pipe(),
 				USB_REQ_SET_ADDRESS, 0, devnum, 0,
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index 62116586848b..6faa854152ef 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -1739,6 +1739,8 @@ struct xhci_command *xhci_alloc_command(struct xhci_hcd *xhci,
 	}
 
 	command->status = 0;
+	/* set default timeout to 5000 ms */
+	command->timeout_ms = XHCI_CMD_DEFAULT_TIMEOUT;
 	INIT_LIST_HEAD(&command->cmd_list);
 	return command;
 }
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index f3b5e6345858..2c1d614b3b0f 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -366,9 +366,10 @@ void xhci_ring_cmd_db(struct xhci_hcd *xhci)
 	readl(&xhci->dba->doorbell[0]);
 }
 
-static bool xhci_mod_cmd_timer(struct xhci_hcd *xhci, unsigned long delay)
+static bool xhci_mod_cmd_timer(struct xhci_hcd *xhci)
 {
-	return mod_delayed_work(system_wq, &xhci->cmd_timer, delay);
+	return mod_delayed_work(system_wq, &xhci->cmd_timer,
+			msecs_to_jiffies(xhci->current_cmd->timeout_ms));
 }
 
 static struct xhci_command *xhci_next_queued_cmd(struct xhci_hcd *xhci)
@@ -412,7 +413,7 @@ static void xhci_handle_stopped_cmd_ring(struct xhci_hcd *xhci,
 	if ((xhci->cmd_ring->dequeue != xhci->cmd_ring->enqueue) &&
 	    !(xhci->xhc_state & XHCI_STATE_DYING)) {
 		xhci->current_cmd = cur_cmd;
-		xhci_mod_cmd_timer(xhci, XHCI_CMD_DEFAULT_TIMEOUT);
+		xhci_mod_cmd_timer(xhci);
 		xhci_ring_cmd_db(xhci);
 	}
 }
@@ -1787,7 +1788,7 @@ static void handle_cmd_completion(struct xhci_hcd *xhci,
 	if (!list_is_singular(&xhci->cmd_list)) {
 		xhci->current_cmd = list_first_entry(&cmd->cmd_list,
 						struct xhci_command, cmd_list);
-		xhci_mod_cmd_timer(xhci, XHCI_CMD_DEFAULT_TIMEOUT);
+		xhci_mod_cmd_timer(xhci);
 	} else if (xhci->current_cmd == cmd) {
 		xhci->current_cmd = NULL;
 	}
@@ -4287,7 +4288,7 @@ static int queue_command(struct xhci_hcd *xhci, struct xhci_command *cmd,
 	/* if there are no other commands queued we start the timeout timer */
 	if (list_empty(&xhci->cmd_list)) {
 		xhci->current_cmd = cmd;
-		xhci_mod_cmd_timer(xhci, XHCI_CMD_DEFAULT_TIMEOUT);
+		xhci_mod_cmd_timer(xhci);
 	}
 
 	list_add_tail(&cmd->cmd_list, &xhci->cmd_list);
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 884b0898d9c9..cb885ddc2032 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -4029,12 +4029,18 @@ disable_slot:
 	return 0;
 }
 
-/*
- * Issue an Address Device command and optionally send a corresponding
- * SetAddress request to the device.
+/**
+ * xhci_setup_device - issues an Address Device command to assign a unique
+ *			USB bus address.
+ * @hcd: USB host controller data structure.
+ * @udev: USB dev structure representing the connected device.
+ * @setup: Enum specifying setup mode: address only or with context.
+ * @timeout_ms: Max wait time (ms) for the command operation to complete.
+ *
+ * Return: 0 if successful; otherwise, negative error code.
  */
 static int xhci_setup_device(struct usb_hcd *hcd, struct usb_device *udev,
-			     enum xhci_setup_dev setup)
+			     enum xhci_setup_dev setup, unsigned int timeout_ms)
 {
 	const char *act = setup == SETUP_CONTEXT_ONLY ? "context" : "address";
 	unsigned long flags;
@@ -4091,6 +4097,7 @@ static int xhci_setup_device(struct usb_hcd *hcd, struct usb_device *udev,
 	}
 
 	command->in_ctx = virt_dev->in_ctx;
+	command->timeout_ms = timeout_ms;
 
 	slot_ctx = xhci_get_slot_ctx(xhci, virt_dev->in_ctx);
 	ctrl_ctx = xhci_get_input_control_ctx(virt_dev->in_ctx);
@@ -4217,14 +4224,16 @@ out:
 	return ret;
 }
 
-static int xhci_address_device(struct usb_hcd *hcd, struct usb_device *udev)
+static int xhci_address_device(struct usb_hcd *hcd, struct usb_device *udev,
+			       unsigned int timeout_ms)
 {
-	return xhci_setup_device(hcd, udev, SETUP_CONTEXT_ADDRESS);
+	return xhci_setup_device(hcd, udev, SETUP_CONTEXT_ADDRESS, timeout_ms);
 }
 
 static int xhci_enable_device(struct usb_hcd *hcd, struct usb_device *udev)
 {
-	return xhci_setup_device(hcd, udev, SETUP_CONTEXT_ONLY);
+	return xhci_setup_device(hcd, udev, SETUP_CONTEXT_ONLY,
+				 XHCI_CMD_DEFAULT_TIMEOUT);
 }
 
 /*
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 3ea5c092bba7..62b610f00754 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -791,6 +791,8 @@ struct xhci_command {
 	struct completion		*completion;
 	union xhci_trb			*command_trb;
 	struct list_head		cmd_list;
+	/* xHCI command response timeout in milliseconds */
+	unsigned int			timeout_ms;
 };
 
 /* drop context bitmasks */
@@ -1550,8 +1552,11 @@ struct xhci_td {
 	unsigned int		num_trbs;
 };
 
-/* xHCI command default timeout value */
-#define XHCI_CMD_DEFAULT_TIMEOUT	(5 * HZ)
+/*
+ * xHCI command default timeout value in milliseconds.
+ * USB 3.2 spec, section 9.2.6.1
+ */
+#define XHCI_CMD_DEFAULT_TIMEOUT	5000
 
 /* command descriptor */
 struct xhci_cd {
diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index 00724b4f6e12..cd77fc6095a1 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -372,8 +372,9 @@ struct hc_driver {
 		 * or bandwidth constraints.
 		 */
 	void	(*reset_bandwidth)(struct usb_hcd *, struct usb_device *);
-		/* Returns the hardware-chosen device address */
-	int	(*address_device)(struct usb_hcd *, struct usb_device *udev);
+		/* Set the hardware-chosen device address */
+	int	(*address_device)(struct usb_hcd *, struct usb_device *udev,
+				  unsigned int timeout_ms);
 		/* prepares the hardware to send commands to the device */
 	int	(*enable_device)(struct usb_hcd *, struct usb_device *udev);
 		/* Notifies the HCD after a hub descriptor is fetched.
-- 
cgit v1.2.3


From 5a1ccf0c72cf917ff3ccc131d1bb8d19338ffe52 Mon Sep 17 00:00:00 2001
From: Hardik Gajjar <hgajjar@de.adit-jv.com>
Date: Fri, 27 Oct 2023 17:20:29 +0200
Subject: usb: new quirk to reduce the SET_ADDRESS request timeout

This patch introduces a new USB quirk,
USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT, which modifies the timeout value
for the SET_ADDRESS request. The standard timeout for USB request/command
is 5000 ms, as recommended in the USB 3.2 specification (section 9.2.6.1).

However, certain scenarios, such as connecting devices through an APTIV
hub, can lead to timeout errors when the device enumerates as full speed
initially and later switches to high speed during chirp negotiation.

In such cases, USB analyzer logs reveal that the bus suspends for
5 seconds due to incorrect chirp parsing and resumes only after two
consecutive timeout errors trigger a hub driver reset.

Packet(54) Dir(?) Full Speed J(997.100 us) Idle(  2.850 us)
_______| Time Stamp(28 . 105 910 682)
_______|_____________________________________________________________Ch0
Packet(55) Dir(?) Full Speed J(997.118 us) Idle(  2.850 us)
_______| Time Stamp(28 . 106 910 632)
_______|_____________________________________________________________Ch0
Packet(56) Dir(?) Full Speed J(399.650 us) Idle(222.582 us)
_______| Time Stamp(28 . 107 910 600)
_______|_____________________________________________________________Ch0
Packet(57) Dir Chirp J( 23.955 ms) Idle(115.169 ms)
_______| Time Stamp(28 . 108 532 832)
_______|_____________________________________________________________Ch0
Packet(58) Dir(?) Full Speed J (Suspend)( 5.347 sec) Idle(  5.366 us)
_______| Time Stamp(28 . 247 657 600)
_______|_____________________________________________________________Ch0

This 5-second delay in device enumeration is undesirable, particularly
in automotive applications where quick enumeration is crucial
(ideally within 3 seconds).

The newly introduced quirks provide the flexibility to align with a
3-second time limit, as required in specific contexts like automotive
applications.

By reducing the SET_ADDRESS request timeout to 500 ms, the
system can respond more swiftly to errors, initiate rapid recovery, and
ensure efficient device enumeration. This change is vital for scenarios
where rapid smartphone enumeration and screen projection are essential.

To use the quirk, please write "vendor_id:product_id:p" to
/sys/bus/usb/drivers/hub/module/parameter/quirks

For example,
echo "0x2c48:0x0132:p" > /sys/bus/usb/drivers/hub/module/parameters/quirks"

Signed-off-by: Hardik Gajjar <hgajjar@de.adit-jv.com>
Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
Link: https://lore.kernel.org/r/20231027152029.104363-2-hgajjar@de.adit-jv.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/admin-guide/kernel-parameters.txt |  3 +++
 drivers/usb/core/hub.c                          | 15 +++++++++++++--
 drivers/usb/core/quirks.c                       |  7 +++++++
 include/linux/usb/quirks.h                      |  3 +++
 4 files changed, 26 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 65731b060e3f..0a6a4b7f7a3b 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -6908,6 +6908,9 @@
 					pause after every control message);
 				o = USB_QUIRK_HUB_SLOW_RESET (Hub needs extra
 					delay after resetting its port);
+				p = USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT
+					(Reduce timeout of the SET_ADDRESS
+					request from 5000 ms to 500 ms);
 			Example: quirks=0781:5580:bk,0a5c:5834:gij
 
 	usbhid.mousepoll=
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 049058264367..756fbd7cac43 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -54,6 +54,12 @@
 #define USB_TP_TRANSMISSION_DELAY_MAX	65535	/* ns */
 #define USB_PING_RESPONSE_TIME		400	/* ns */
 
+/*
+ * The SET_ADDRESS request timeout will be 500 ms when
+ * USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT quirk flag is set.
+ */
+#define USB_SHORT_SET_ADDRESS_REQ_TIMEOUT	500  /* ms */
+
 /* Protect struct usb_device->state and ->children members
  * Note: Both are also protected by ->dev.sem, except that ->state can
  * change to USB_STATE_NOTATTACHED even when the semaphore isn't held. */
@@ -4649,7 +4655,12 @@ EXPORT_SYMBOL_GPL(usb_ep0_reinit);
 static int hub_set_address(struct usb_device *udev, int devnum)
 {
 	int retval;
+	unsigned int timeout_ms = USB_CTRL_SET_TIMEOUT;
 	struct usb_hcd *hcd = bus_to_hcd(udev->bus);
+	struct usb_hub *hub = usb_hub_to_struct_hub(udev->parent);
+
+	if (hub->hdev->quirks & USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT)
+		timeout_ms = USB_SHORT_SET_ADDRESS_REQ_TIMEOUT;
 
 	/*
 	 * The host controller will choose the device address,
@@ -4662,11 +4673,11 @@ static int hub_set_address(struct usb_device *udev, int devnum)
 	if (udev->state != USB_STATE_DEFAULT)
 		return -EINVAL;
 	if (hcd->driver->address_device)
-		retval = hcd->driver->address_device(hcd, udev, USB_CTRL_SET_TIMEOUT);
+		retval = hcd->driver->address_device(hcd, udev, timeout_ms);
 	else
 		retval = usb_control_msg(udev, usb_sndaddr0pipe(),
 				USB_REQ_SET_ADDRESS, 0, devnum, 0,
-				NULL, 0, USB_CTRL_SET_TIMEOUT);
+				NULL, 0, timeout_ms);
 	if (retval == 0) {
 		update_devnum(udev, devnum);
 		/* Device now using proper address. */
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 15e9bd180a1d..b4783574b8e6 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -138,6 +138,9 @@ static int quirks_param_set(const char *value, const struct kernel_param *kp)
 			case 'o':
 				flags |= USB_QUIRK_HUB_SLOW_RESET;
 				break;
+			case 'p':
+				flags |= USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT;
+				break;
 			/* Ignore unrecognized flag characters */
 			}
 		}
@@ -527,6 +530,10 @@ static const struct usb_device_id usb_quirk_list[] = {
 
 	{ USB_DEVICE(0x2386, 0x350e), .driver_info = USB_QUIRK_NO_LPM },
 
+	/* APTIV AUTOMOTIVE HUB */
+	{ USB_DEVICE(0x2c48, 0x0132), .driver_info =
+			USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT },
+
 	/* DJI CineSSD */
 	{ USB_DEVICE(0x2ca3, 0x0031), .driver_info = USB_QUIRK_NO_LPM },
 
diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h
index eeb7c2157c72..59409c1fc3de 100644
--- a/include/linux/usb/quirks.h
+++ b/include/linux/usb/quirks.h
@@ -72,4 +72,7 @@
 /* device has endpoints that should be ignored */
 #define USB_QUIRK_ENDPOINT_IGNORE		BIT(15)
 
+/* short SET_ADDRESS request timeout */
+#define USB_QUIRK_SHORT_SET_ADDRESS_REQ_TIMEOUT	BIT(16)
+
 #endif /* __LINUX_USB_QUIRKS_H */
-- 
cgit v1.2.3


From 36f2cd3bd496348a4ff8e1de9b23955bd641ce42 Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Date: Mon, 23 Oct 2023 23:40:11 +0200
Subject: media: v4l2-subdev: Rename pad config 'try_*' fields

The try_fmt, try_crop and try_compose fields of the
v4l2_subdev_pad_config structure are misnamed (for historical reason) as
they also store data for the subdev active configuration. Rename them to
format, crop and compose respectively and update the accessor helpers.

Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
---
 include/media/v4l2-subdev.h | 33 +++++++++++++++------------------
 1 file changed, 15 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h
index c1f90c1223a7..bb1aad264756 100644
--- a/include/media/v4l2-subdev.h
+++ b/include/media/v4l2-subdev.h
@@ -688,21 +688,18 @@ struct v4l2_subdev_ir_ops {
 /**
  * struct v4l2_subdev_pad_config - Used for storing subdev pad information.
  *
- * @try_fmt: &struct v4l2_mbus_framefmt
- * @try_crop: &struct v4l2_rect to be used for crop
- * @try_compose: &struct v4l2_rect to be used for compose
+ * @format: &struct v4l2_mbus_framefmt
+ * @crop: &struct v4l2_rect to be used for crop
+ * @compose: &struct v4l2_rect to be used for compose
  *
  * This structure only needs to be passed to the pad op if the 'which' field
  * of the main argument is set to %V4L2_SUBDEV_FORMAT_TRY. For
  * %V4L2_SUBDEV_FORMAT_ACTIVE it is safe to pass %NULL.
- *
- * Note: This struct is also used in active state, and the 'try' prefix is
- * historical and to be removed.
  */
 struct v4l2_subdev_pad_config {
-	struct v4l2_mbus_framefmt try_fmt;
-	struct v4l2_rect try_crop;
-	struct v4l2_rect try_compose;
+	struct v4l2_mbus_framefmt format;
+	struct v4l2_rect crop;
+	struct v4l2_rect compose;
 };
 
 /**
@@ -1145,8 +1142,8 @@ struct v4l2_subdev_fh {
 #if defined(CONFIG_VIDEO_V4L2_SUBDEV_API)
 
 /**
- * v4l2_subdev_get_pad_format - ancillary routine to call
- *	&struct v4l2_subdev_pad_config->try_fmt
+ * v4l2_subdev_get_pad_format - ancillary routine to get
+ *	&struct v4l2_subdev_pad_config->format
  *
  * @sd: pointer to &struct v4l2_subdev
  * @state: pointer to &struct v4l2_subdev_state
@@ -1161,12 +1158,12 @@ v4l2_subdev_get_pad_format(struct v4l2_subdev *sd,
 		return NULL;
 	if (WARN_ON(pad >= sd->entity.num_pads))
 		pad = 0;
-	return &state->pads[pad].try_fmt;
+	return &state->pads[pad].format;
 }
 
 /**
- * v4l2_subdev_get_pad_crop - ancillary routine to call
- *	&struct v4l2_subdev_pad_config->try_crop
+ * v4l2_subdev_get_pad_crop - ancillary routine to get
+ *	&struct v4l2_subdev_pad_config->crop
  *
  * @sd: pointer to &struct v4l2_subdev
  * @state: pointer to &struct v4l2_subdev_state.
@@ -1181,12 +1178,12 @@ v4l2_subdev_get_pad_crop(struct v4l2_subdev *sd,
 		return NULL;
 	if (WARN_ON(pad >= sd->entity.num_pads))
 		pad = 0;
-	return &state->pads[pad].try_crop;
+	return &state->pads[pad].crop;
 }
 
 /**
- * v4l2_subdev_get_pad_compose - ancillary routine to call
- *	&struct v4l2_subdev_pad_config->try_compose
+ * v4l2_subdev_get_pad_compose - ancillary routine to get
+ *	&struct v4l2_subdev_pad_config->compose
  *
  * @sd: pointer to &struct v4l2_subdev
  * @state: pointer to &struct v4l2_subdev_state.
@@ -1201,7 +1198,7 @@ v4l2_subdev_get_pad_compose(struct v4l2_subdev *sd,
 		return NULL;
 	if (WARN_ON(pad >= sd->entity.num_pads))
 		pad = 0;
-	return &state->pads[pad].try_compose;
+	return &state->pads[pad].compose;
 }
 
 /*
-- 
cgit v1.2.3


From 6078b2b803dba5f3fa62f652d931120fc1f0137d Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Date: Tue, 24 Oct 2023 00:17:12 +0200
Subject: media: v4l2-subdev: Drop outdated comment for v4l2_subdev_pad_config

The v4l2_subdev_pad_config structure is not passed to subdev operations
anymore. Drop an outdated comment to refers to that old mechanism.

Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Reviewed-by: Tomi Valkeinen <tomi.valkeinen@ideasonboard.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
---
 include/media/v4l2-subdev.h | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'include')

diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h
index bb1aad264756..bbcee4f3da1e 100644
--- a/include/media/v4l2-subdev.h
+++ b/include/media/v4l2-subdev.h
@@ -691,10 +691,6 @@ struct v4l2_subdev_ir_ops {
  * @format: &struct v4l2_mbus_framefmt
  * @crop: &struct v4l2_rect to be used for crop
  * @compose: &struct v4l2_rect to be used for compose
- *
- * This structure only needs to be passed to the pad op if the 'which' field
- * of the main argument is set to %V4L2_SUBDEV_FORMAT_TRY. For
- * %V4L2_SUBDEV_FORMAT_ACTIVE it is safe to pass %NULL.
  */
 struct v4l2_subdev_pad_config {
 	struct v4l2_mbus_framefmt format;
-- 
cgit v1.2.3


From c1ac5298867b955e8551bc4a93fcd739ea5db85a Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Date: Fri, 27 Oct 2023 11:58:47 +0200
Subject: media: v4l2-subdev: Fix references to pad config

V4L2 subdev operations have moved from operating on a
v4l2_subdev_pad_config to a v4l2_subdev_state a long time ago. Fix the
few remaining incorrect references to pad config in the documentation.

Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
---
 Documentation/driver-api/media/v4l2-subdev.rst | 4 ++--
 include/media/v4l2-subdev.h                    | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/Documentation/driver-api/media/v4l2-subdev.rst b/Documentation/driver-api/media/v4l2-subdev.rst
index e56b50b3f203..a62e4aff31be 100644
--- a/Documentation/driver-api/media/v4l2-subdev.rst
+++ b/Documentation/driver-api/media/v4l2-subdev.rst
@@ -562,8 +562,8 @@ device configuration. This is often implemented as e.g. an array of struct
 v4l2_mbus_framefmt, one entry for each pad, and similarly for crop and compose
 rectangles.
 
-In addition to the active configuration, each subdev file handle has an array of
-struct v4l2_subdev_pad_config, managed by the V4L2 core, which contains the try
+In addition to the active configuration, each subdev file handle has a struct
+v4l2_subdev_state, managed by the V4L2 core, which contains the try
 configuration.
 
 To simplify the subdev drivers the V4L2 subdev API now optionally supports a
diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h
index bbcee4f3da1e..8a345b5fa39d 100644
--- a/include/media/v4l2-subdev.h
+++ b/include/media/v4l2-subdev.h
@@ -769,7 +769,7 @@ struct v4l2_subdev_state {
 /**
  * struct v4l2_subdev_pad_ops - v4l2-subdev pad level operations
  *
- * @init_cfg: initialize the pad config to default values
+ * @init_cfg: initialize the subdev state to default values
  * @enum_mbus_code: callback for VIDIOC_SUBDEV_ENUM_MBUS_CODE() ioctl handler
  *		    code.
  * @enum_frame_size: callback for VIDIOC_SUBDEV_ENUM_FRAME_SIZE() ioctl handler
-- 
cgit v1.2.3


From 52c2575db8faa1d93227a92a32deb2cd66b96614 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Fri, 13 Oct 2023 09:15:48 +0200
Subject: media: v4l: subdev: Store the sub-device in the sub-device state

Store the sub-device in the sub-device state. This will be needed in e.g.
validating pad number when retrieving information for non-stream-aware
users. There are expected to be more needs for this in the future.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Reviewed-by: Tomi Valkeinen <tomi.valkeinen@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
---
 drivers/media/v4l2-core/v4l2-subdev.c | 2 ++
 include/media/v4l2-subdev.h           | 2 ++
 2 files changed, 4 insertions(+)

(limited to 'include')

diff --git a/drivers/media/v4l2-core/v4l2-subdev.c b/drivers/media/v4l2-core/v4l2-subdev.c
index be86b906c985..cd3ff5b19d0c 100644
--- a/drivers/media/v4l2-core/v4l2-subdev.c
+++ b/drivers/media/v4l2-core/v4l2-subdev.c
@@ -1448,6 +1448,8 @@ __v4l2_subdev_state_alloc(struct v4l2_subdev *sd, const char *lock_name,
 	else
 		state->lock = &state->_lock;
 
+	state->sd = sd;
+
 	/* Drivers that support streams do not need the legacy pad config */
 	if (!(sd->flags & V4L2_SUBDEV_FL_STREAMS) && sd->entity.num_pads) {
 		state->pads = kvcalloc(sd->entity.num_pads,
diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h
index 8a345b5fa39d..46296852cb5b 100644
--- a/include/media/v4l2-subdev.h
+++ b/include/media/v4l2-subdev.h
@@ -749,6 +749,7 @@ struct v4l2_subdev_krouting {
  *
  * @_lock: default for 'lock'
  * @lock: mutex for the state. May be replaced by the user.
+ * @sd: the sub-device which the state is related to
  * @pads: &struct v4l2_subdev_pad_config array
  * @routing: routing table for the subdev
  * @stream_configs: stream configurations (only for V4L2_SUBDEV_FL_STREAMS)
@@ -761,6 +762,7 @@ struct v4l2_subdev_state {
 	/* lock for the struct v4l2_subdev_state fields */
 	struct mutex _lock;
 	struct mutex *lock;
+	struct v4l2_subdev *sd;
 	struct v4l2_subdev_pad_config *pads;
 	struct v4l2_subdev_krouting routing;
 	struct v4l2_subdev_stream_configs stream_configs;
-- 
cgit v1.2.3


From 049fa16b81c276f25a09abaa4e8f743470c3cdc8 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Fri, 13 Oct 2023 09:31:37 +0200
Subject: media: v4l: subdev: Also return pads array information on stream
 functions

There are two sets of functions that return information from sub-device
state, one for stream-unaware users and another for stream-aware users.
Add support for stream-aware functions to return format, crop and compose
information from pad-based array that are functionally equivalent to the
old, stream-unaware ones.

Also check state is non-NULL, in order to guard against old drivers
potentially calling this with NULL state for active formats or selection
rectangles.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Reviewed-by: Tomi Valkeinen <tomi.valkeinen@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
---
 drivers/media/v4l2-core/v4l2-subdev.c | 63 +++++++++++++++++++++++++++++++++++
 include/media/v4l2-subdev.h           |  9 +++--
 2 files changed, 69 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/media/v4l2-core/v4l2-subdev.c b/drivers/media/v4l2-core/v4l2-subdev.c
index cd3ff5b19d0c..554d0c128ee9 100644
--- a/drivers/media/v4l2-core/v4l2-subdev.c
+++ b/drivers/media/v4l2-core/v4l2-subdev.c
@@ -1691,6 +1691,27 @@ v4l2_subdev_state_get_stream_format(struct v4l2_subdev_state *state,
 	struct v4l2_subdev_stream_configs *stream_configs;
 	unsigned int i;
 
+	if (WARN_ON_ONCE(!state))
+		return NULL;
+
+	if (state->pads) {
+		if (stream)
+			return NULL;
+
+		/*
+		 * Set the pad to 0 on error as this is aligned with the
+		 * behaviour of the pad state information access functions. The
+		 * purpose of setting pad to 0 here is to avoid accessing memory
+		 * outside the pads array, but still issuing warning of the
+		 * invalid access while making the caller's error handling
+		 * easier.
+		 */
+		if (WARN_ON_ONCE(pad >= state->sd->entity.num_pads))
+			pad = 0;
+
+		return &state->pads[pad].format;
+	}
+
 	lockdep_assert_held(state->lock);
 
 	stream_configs = &state->stream_configs;
@@ -1712,6 +1733,27 @@ v4l2_subdev_state_get_stream_crop(struct v4l2_subdev_state *state,
 	struct v4l2_subdev_stream_configs *stream_configs;
 	unsigned int i;
 
+	if (WARN_ON_ONCE(!state))
+		return NULL;
+
+	if (state->pads) {
+		if (stream)
+			return NULL;
+
+		/*
+		 * Set the pad to 0 on error as this is aligned with the
+		 * behaviour of the pad state information access functions. The
+		 * purpose of setting pad to 0 here is to avoid accessing memory
+		 * outside the pads array, but still issuing warning of the
+		 * invalid access while making the caller's error handling
+		 * easier.
+		 */
+		if (WARN_ON_ONCE(pad >= state->sd->entity.num_pads))
+			pad = 0;
+
+		return &state->pads[pad].crop;
+	}
+
 	lockdep_assert_held(state->lock);
 
 	stream_configs = &state->stream_configs;
@@ -1733,6 +1775,27 @@ v4l2_subdev_state_get_stream_compose(struct v4l2_subdev_state *state,
 	struct v4l2_subdev_stream_configs *stream_configs;
 	unsigned int i;
 
+	if (WARN_ON_ONCE(!state))
+		return NULL;
+
+	if (state->pads) {
+		if (stream)
+			return NULL;
+
+		/*
+		 * Set the pad to 0 on error as this is aligned with the
+		 * behaviour of the pad state information access functions. The
+		 * purpose of setting pad to 0 here is to avoid accessing memory
+		 * outside the pads array, but still issuing warning of the
+		 * invalid access while making the caller's error handling
+		 * easier.
+		 */
+		if (WARN_ON_ONCE(pad >= state->sd->entity.num_pads))
+			pad = 0;
+
+		return &state->pads[pad].compose;
+	}
+
 	lockdep_assert_held(state->lock);
 
 	stream_configs = &state->stream_configs;
diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h
index 46296852cb5b..6b242ec58cb7 100644
--- a/include/media/v4l2-subdev.h
+++ b/include/media/v4l2-subdev.h
@@ -1543,7 +1543,8 @@ int v4l2_subdev_set_routing_with_fmt(struct v4l2_subdev *sd,
  * This returns a pointer to &struct v4l2_mbus_framefmt for the given pad +
  * stream in the subdev state.
  *
- * If the state does not contain the given pad + stream, NULL is returned.
+ * For stream-unaware drivers the format for the corresponding pad is returned.
+ * If the pad does not exist, NULL is returned.
  */
 struct v4l2_mbus_framefmt *
 v4l2_subdev_state_get_stream_format(struct v4l2_subdev_state *state,
@@ -1558,7 +1559,8 @@ v4l2_subdev_state_get_stream_format(struct v4l2_subdev_state *state,
  * This returns a pointer to crop rectangle for the given pad + stream in the
  * subdev state.
  *
- * If the state does not contain the given pad + stream, NULL is returned.
+ * For stream-unaware drivers the crop rectangle for the corresponding pad is
+ * returned. If the pad does not exist, NULL is returned.
  */
 struct v4l2_rect *
 v4l2_subdev_state_get_stream_crop(struct v4l2_subdev_state *state,
@@ -1574,7 +1576,8 @@ v4l2_subdev_state_get_stream_crop(struct v4l2_subdev_state *state,
  * This returns a pointer to compose rectangle for the given pad + stream in the
  * subdev state.
  *
- * If the state does not contain the given pad + stream, NULL is returned.
+ * For stream-unaware drivers the compose rectangle for the corresponding pad is
+ * returned. If the pad does not exist, NULL is returned.
  */
 struct v4l2_rect *
 v4l2_subdev_state_get_stream_compose(struct v4l2_subdev_state *state,
-- 
cgit v1.2.3


From d0fde6aae2bacdc024fff43461ba0f325375fa97 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Fri, 13 Oct 2023 10:16:06 +0200
Subject: media: v4l: subdev: Rename sub-device state information access
 functions

Rename the sub-devices state information access functions, removing
"_stream" from them and replacing "format" by "ffmt". This makes them
shorter and so more convenient to use. No other sets of functions will be
needed to access this information.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Reviewed-by: Tomi Valkeinen <tomi.valkeinen@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
---
 drivers/media/i2c/ds90ub913.c                      |  3 +--
 drivers/media/i2c/ds90ub953.c                      |  3 +--
 drivers/media/i2c/ds90ub960.c                      | 12 ++++------
 .../platform/nxp/imx8-isi/imx8-isi-crossbar.c      | 10 ++++----
 drivers/media/v4l2-core/v4l2-subdev.c              | 27 +++++++++++-----------
 include/media/v4l2-subdev.h                        | 19 ++++++++-------
 6 files changed, 34 insertions(+), 40 deletions(-)

(limited to 'include')

diff --git a/drivers/media/i2c/ds90ub913.c b/drivers/media/i2c/ds90ub913.c
index 8e9ebed09f64..8bb6be956780 100644
--- a/drivers/media/i2c/ds90ub913.c
+++ b/drivers/media/i2c/ds90ub913.c
@@ -424,8 +424,7 @@ static int ub913_set_fmt(struct v4l2_subdev *sd,
 	}
 
 	/* Set sink format */
-	fmt = v4l2_subdev_state_get_stream_format(state, format->pad,
-						  format->stream);
+	fmt = v4l2_subdev_state_get_format(state, format->pad, format->stream);
 	if (!fmt)
 		return -EINVAL;
 
diff --git a/drivers/media/i2c/ds90ub953.c b/drivers/media/i2c/ds90ub953.c
index 644022312833..4eb08e3a31c7 100644
--- a/drivers/media/i2c/ds90ub953.c
+++ b/drivers/media/i2c/ds90ub953.c
@@ -558,8 +558,7 @@ static int ub953_set_fmt(struct v4l2_subdev *sd,
 		return v4l2_subdev_get_fmt(sd, state, format);
 
 	/* Set sink format */
-	fmt = v4l2_subdev_state_get_stream_format(state, format->pad,
-						  format->stream);
+	fmt = v4l2_subdev_state_get_format(state, format->pad, format->stream);
 	if (!fmt)
 		return -EINVAL;
 
diff --git a/drivers/media/i2c/ds90ub960.c b/drivers/media/i2c/ds90ub960.c
index b8f3e5ca03ef..1d1476098c92 100644
--- a/drivers/media/i2c/ds90ub960.c
+++ b/drivers/media/i2c/ds90ub960.c
@@ -2451,9 +2451,8 @@ static int ub960_configure_ports_for_streaming(struct ub960_data *priv,
 		if (rx_data[nport].num_streams > 2)
 			return -EPIPE;
 
-		fmt = v4l2_subdev_state_get_stream_format(state,
-							  route->sink_pad,
-							  route->sink_stream);
+		fmt = v4l2_subdev_state_get_format(state, route->sink_pad,
+						   route->sink_stream);
 		if (!fmt)
 			return -EPIPE;
 
@@ -2842,8 +2841,8 @@ static int ub960_get_frame_desc(struct v4l2_subdev *sd, unsigned int pad,
 			const struct ub960_format_info *ub960_fmt;
 			struct v4l2_mbus_framefmt *fmt;
 
-			fmt = v4l2_subdev_state_get_stream_format(state, pad,
-								  route->source_stream);
+			fmt = v4l2_subdev_state_get_format(state, pad,
+							   route->source_stream);
 
 			if (!fmt) {
 				ret = -EINVAL;
@@ -2891,8 +2890,7 @@ static int ub960_set_fmt(struct v4l2_subdev *sd,
 	if (!ub960_find_format(format->format.code))
 		format->format.code = ub960_formats[0].code;
 
-	fmt = v4l2_subdev_state_get_stream_format(state, format->pad,
-						  format->stream);
+	fmt = v4l2_subdev_state_get_format(state, format->pad, format->stream);
 	if (!fmt)
 		return -EINVAL;
 
diff --git a/drivers/media/platform/nxp/imx8-isi/imx8-isi-crossbar.c b/drivers/media/platform/nxp/imx8-isi/imx8-isi-crossbar.c
index 792f031e032a..9401261eb239 100644
--- a/drivers/media/platform/nxp/imx8-isi/imx8-isi-crossbar.c
+++ b/drivers/media/platform/nxp/imx8-isi/imx8-isi-crossbar.c
@@ -58,7 +58,7 @@ static int mxc_isi_crossbar_gasket_enable(struct mxc_isi_crossbar *xbar,
 		return -EINVAL;
 	}
 
-	fmt = v4l2_subdev_state_get_stream_format(state, port, 0);
+	fmt = v4l2_subdev_state_get_format(state, port, 0);
 	if (!fmt)
 		return -EINVAL;
 
@@ -281,8 +281,7 @@ static int mxc_isi_crossbar_set_fmt(struct v4l2_subdev *sd,
 	 * Set the format on the sink stream and propagate it to the source
 	 * streams.
 	 */
-	sink_fmt = v4l2_subdev_state_get_stream_format(state, fmt->pad,
-						       fmt->stream);
+	sink_fmt = v4l2_subdev_state_get_format(state, fmt->pad, fmt->stream);
 	if (!sink_fmt)
 		return -EINVAL;
 
@@ -296,8 +295,9 @@ static int mxc_isi_crossbar_set_fmt(struct v4l2_subdev *sd,
 		    route->sink_stream != fmt->stream)
 			continue;
 
-		source_fmt = v4l2_subdev_state_get_stream_format(state, route->source_pad,
-								 route->source_stream);
+		source_fmt = v4l2_subdev_state_get_format(state,
+							  route->source_pad,
+							  route->source_stream);
 		if (!source_fmt)
 			return -EINVAL;
 
diff --git a/drivers/media/v4l2-core/v4l2-subdev.c b/drivers/media/v4l2-core/v4l2-subdev.c
index 554d0c128ee9..a6f480ef7881 100644
--- a/drivers/media/v4l2-core/v4l2-subdev.c
+++ b/drivers/media/v4l2-core/v4l2-subdev.c
@@ -177,7 +177,7 @@ static int check_state(struct v4l2_subdev *sd, struct v4l2_subdev_state *state,
 {
 	if (sd->flags & V4L2_SUBDEV_FL_STREAMS) {
 #if defined(CONFIG_VIDEO_V4L2_SUBDEV_API)
-		if (!v4l2_subdev_state_get_stream_format(state, pad, stream))
+		if (!v4l2_subdev_state_get_format(state, pad, stream))
 			return -EINVAL;
 		return 0;
 #else
@@ -1588,8 +1588,8 @@ int v4l2_subdev_get_fmt(struct v4l2_subdev *sd, struct v4l2_subdev_state *state,
 	struct v4l2_mbus_framefmt *fmt;
 
 	if (sd->flags & V4L2_SUBDEV_FL_STREAMS)
-		fmt = v4l2_subdev_state_get_stream_format(state, format->pad,
-							  format->stream);
+		fmt = v4l2_subdev_state_get_format(state, format->pad,
+						   format->stream);
 	else if (format->pad < sd->entity.num_pads && format->stream == 0)
 		fmt = v4l2_subdev_get_pad_format(sd, state, format->pad);
 	else
@@ -1685,8 +1685,8 @@ int v4l2_subdev_set_routing_with_fmt(struct v4l2_subdev *sd,
 EXPORT_SYMBOL_GPL(v4l2_subdev_set_routing_with_fmt);
 
 struct v4l2_mbus_framefmt *
-v4l2_subdev_state_get_stream_format(struct v4l2_subdev_state *state,
-				    unsigned int pad, u32 stream)
+v4l2_subdev_state_get_format(struct v4l2_subdev_state *state, unsigned int pad,
+			     u32 stream)
 {
 	struct v4l2_subdev_stream_configs *stream_configs;
 	unsigned int i;
@@ -1724,11 +1724,11 @@ v4l2_subdev_state_get_stream_format(struct v4l2_subdev_state *state,
 
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(v4l2_subdev_state_get_stream_format);
+EXPORT_SYMBOL_GPL(v4l2_subdev_state_get_format);
 
 struct v4l2_rect *
-v4l2_subdev_state_get_stream_crop(struct v4l2_subdev_state *state,
-				  unsigned int pad, u32 stream)
+v4l2_subdev_state_get_crop(struct v4l2_subdev_state *state, unsigned int pad,
+			   u32 stream)
 {
 	struct v4l2_subdev_stream_configs *stream_configs;
 	unsigned int i;
@@ -1766,11 +1766,11 @@ v4l2_subdev_state_get_stream_crop(struct v4l2_subdev_state *state,
 
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(v4l2_subdev_state_get_stream_crop);
+EXPORT_SYMBOL_GPL(v4l2_subdev_state_get_crop);
 
 struct v4l2_rect *
-v4l2_subdev_state_get_stream_compose(struct v4l2_subdev_state *state,
-				     unsigned int pad, u32 stream)
+v4l2_subdev_state_get_compose(struct v4l2_subdev_state *state, unsigned int pad,
+			      u32 stream)
 {
 	struct v4l2_subdev_stream_configs *stream_configs;
 	unsigned int i;
@@ -1808,7 +1808,7 @@ v4l2_subdev_state_get_stream_compose(struct v4l2_subdev_state *state,
 
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(v4l2_subdev_state_get_stream_compose);
+EXPORT_SYMBOL_GPL(v4l2_subdev_state_get_compose);
 
 int v4l2_subdev_routing_find_opposite_end(const struct v4l2_subdev_krouting *routing,
 					  u32 pad, u32 stream, u32 *other_pad,
@@ -1854,8 +1854,7 @@ v4l2_subdev_state_get_opposite_stream_format(struct v4l2_subdev_state *state,
 	if (ret)
 		return NULL;
 
-	return v4l2_subdev_state_get_stream_format(state, other_pad,
-						   other_stream);
+	return v4l2_subdev_state_get_format(state, other_pad, other_stream);
 }
 EXPORT_SYMBOL_GPL(v4l2_subdev_state_get_opposite_stream_format);
 
diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h
index 6b242ec58cb7..f144d49a825c 100644
--- a/include/media/v4l2-subdev.h
+++ b/include/media/v4l2-subdev.h
@@ -1535,7 +1535,7 @@ int v4l2_subdev_set_routing_with_fmt(struct v4l2_subdev *sd,
 				     const struct v4l2_mbus_framefmt *fmt);
 
 /**
- * v4l2_subdev_state_get_stream_format() - Get pointer to a stream format
+ * v4l2_subdev_state_get_format() - Get pointer to a stream format
  * @state: subdevice state
  * @pad: pad id
  * @stream: stream id
@@ -1547,11 +1547,11 @@ int v4l2_subdev_set_routing_with_fmt(struct v4l2_subdev *sd,
  * If the pad does not exist, NULL is returned.
  */
 struct v4l2_mbus_framefmt *
-v4l2_subdev_state_get_stream_format(struct v4l2_subdev_state *state,
-				    unsigned int pad, u32 stream);
+v4l2_subdev_state_get_format(struct v4l2_subdev_state *state, unsigned int pad,
+			     u32 stream);
 
 /**
- * v4l2_subdev_state_get_stream_crop() - Get pointer to a stream crop rectangle
+ * v4l2_subdev_state_get_crop() - Get pointer to a stream crop rectangle
  * @state: subdevice state
  * @pad: pad id
  * @stream: stream id
@@ -1563,12 +1563,11 @@ v4l2_subdev_state_get_stream_format(struct v4l2_subdev_state *state,
  * returned. If the pad does not exist, NULL is returned.
  */
 struct v4l2_rect *
-v4l2_subdev_state_get_stream_crop(struct v4l2_subdev_state *state,
-				  unsigned int pad, u32 stream);
+v4l2_subdev_state_get_crop(struct v4l2_subdev_state *state, unsigned int pad,
+			   u32 stream);
 
 /**
- * v4l2_subdev_state_get_stream_compose() - Get pointer to a stream compose
- *					    rectangle
+ * v4l2_subdev_state_get_compose() - Get pointer to a stream compose rectangle
  * @state: subdevice state
  * @pad: pad id
  * @stream: stream id
@@ -1580,8 +1579,8 @@ v4l2_subdev_state_get_stream_crop(struct v4l2_subdev_state *state,
  * returned. If the pad does not exist, NULL is returned.
  */
 struct v4l2_rect *
-v4l2_subdev_state_get_stream_compose(struct v4l2_subdev_state *state,
-				     unsigned int pad, u32 stream);
+v4l2_subdev_state_get_compose(struct v4l2_subdev_state *state, unsigned int pad,
+			      u32 stream);
 
 /**
  * v4l2_subdev_routing_find_opposite_end() - Find the opposite stream
-- 
cgit v1.2.3


From 791765b426df4d2a1b1be0617c2c0bf2248bfaba Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Mon, 23 Oct 2023 12:26:34 +0200
Subject: media: v4l: subdev: Make stream argument optional in state access
 functions

The sub-device state access functions take three arguments: sub-device
state, pad and stream. The stream is not relevant for the majority of
drivers and having to specify 0 for the stream is considered a nuisance.

Provide a two-argument macros for these state access functions to cover
the needs of stream-unaware users.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
---
 drivers/media/v4l2-core/v4l2-subdev.c | 18 ++++++-------
 include/media/v4l2-subdev.h           | 49 ++++++++++++++++++++++++++++-------
 2 files changed, 49 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/drivers/media/v4l2-core/v4l2-subdev.c b/drivers/media/v4l2-core/v4l2-subdev.c
index 9eef170934c5..06988e3a6f10 100644
--- a/drivers/media/v4l2-core/v4l2-subdev.c
+++ b/drivers/media/v4l2-core/v4l2-subdev.c
@@ -1678,8 +1678,8 @@ int v4l2_subdev_set_routing_with_fmt(struct v4l2_subdev *sd,
 EXPORT_SYMBOL_GPL(v4l2_subdev_set_routing_with_fmt);
 
 struct v4l2_mbus_framefmt *
-v4l2_subdev_state_get_format(struct v4l2_subdev_state *state, unsigned int pad,
-			     u32 stream)
+__v4l2_subdev_state_get_format(struct v4l2_subdev_state *state,
+			       unsigned int pad, u32 stream)
 {
 	struct v4l2_subdev_stream_configs *stream_configs;
 	unsigned int i;
@@ -1717,11 +1717,11 @@ v4l2_subdev_state_get_format(struct v4l2_subdev_state *state, unsigned int pad,
 
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(v4l2_subdev_state_get_format);
+EXPORT_SYMBOL_GPL(__v4l2_subdev_state_get_format);
 
 struct v4l2_rect *
-v4l2_subdev_state_get_crop(struct v4l2_subdev_state *state, unsigned int pad,
-			   u32 stream)
+__v4l2_subdev_state_get_crop(struct v4l2_subdev_state *state, unsigned int pad,
+			     u32 stream)
 {
 	struct v4l2_subdev_stream_configs *stream_configs;
 	unsigned int i;
@@ -1759,11 +1759,11 @@ v4l2_subdev_state_get_crop(struct v4l2_subdev_state *state, unsigned int pad,
 
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(v4l2_subdev_state_get_crop);
+EXPORT_SYMBOL_GPL(__v4l2_subdev_state_get_crop);
 
 struct v4l2_rect *
-v4l2_subdev_state_get_compose(struct v4l2_subdev_state *state, unsigned int pad,
-			      u32 stream)
+__v4l2_subdev_state_get_compose(struct v4l2_subdev_state *state,
+				unsigned int pad, u32 stream)
 {
 	struct v4l2_subdev_stream_configs *stream_configs;
 	unsigned int i;
@@ -1801,7 +1801,7 @@ v4l2_subdev_state_get_compose(struct v4l2_subdev_state *state, unsigned int pad,
 
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(v4l2_subdev_state_get_compose);
+EXPORT_SYMBOL_GPL(__v4l2_subdev_state_get_compose);
 
 int v4l2_subdev_routing_find_opposite_end(const struct v4l2_subdev_krouting *routing,
 					  u32 pad, u32 stream, u32 *other_pad,
diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h
index f144d49a825c..c8ac91a2cdb8 100644
--- a/include/media/v4l2-subdev.h
+++ b/include/media/v4l2-subdev.h
@@ -1534,11 +1534,18 @@ int v4l2_subdev_set_routing_with_fmt(struct v4l2_subdev *sd,
 				     const struct v4l2_subdev_krouting *routing,
 				     const struct v4l2_mbus_framefmt *fmt);
 
+/*
+ * A macro to generate the macro or function name for sub-devices state access
+ * wrapper macros below.
+ */
+#define __v4l2_subdev_state_gen_call(NAME, _1, ARG, ...)	\
+	__v4l2_subdev_state_get_ ## NAME ## ARG
+
 /**
  * v4l2_subdev_state_get_format() - Get pointer to a stream format
  * @state: subdevice state
  * @pad: pad id
- * @stream: stream id
+ * @...: stream id (optional argument)
  *
  * This returns a pointer to &struct v4l2_mbus_framefmt for the given pad +
  * stream in the subdev state.
@@ -1546,15 +1553,29 @@ int v4l2_subdev_set_routing_with_fmt(struct v4l2_subdev *sd,
  * For stream-unaware drivers the format for the corresponding pad is returned.
  * If the pad does not exist, NULL is returned.
  */
+/*
+ * Wrap v4l2_subdev_state_get_format(), allowing the function to be called with
+ * two or three arguments. The purpose of the __v4l2_subdev_state_get_format()
+ * macro below is to come up with the name of the function or macro to call,
+ * using the last two arguments (_stream and _pad). The selected function or
+ * macro is then called using the arguments specified by the caller. A similar
+ * arrangement is used for v4l2_subdev_state_crop() and
+ * v4l2_subdev_state_compose() below.
+ */
+#define v4l2_subdev_state_get_format(state, pad, ...)			\
+	__v4l2_subdev_state_gen_call(format, ##__VA_ARGS__, , _pad)	\
+		(state, pad, ##__VA_ARGS__)
+#define __v4l2_subdev_state_get_format_pad(state, pad)	\
+	__v4l2_subdev_state_get_format(state, pad, 0)
 struct v4l2_mbus_framefmt *
-v4l2_subdev_state_get_format(struct v4l2_subdev_state *state, unsigned int pad,
-			     u32 stream);
+__v4l2_subdev_state_get_format(struct v4l2_subdev_state *state,
+			       unsigned int pad, u32 stream);
 
 /**
  * v4l2_subdev_state_get_crop() - Get pointer to a stream crop rectangle
  * @state: subdevice state
  * @pad: pad id
- * @stream: stream id
+ * @...: stream id (optional argument)
  *
  * This returns a pointer to crop rectangle for the given pad + stream in the
  * subdev state.
@@ -1562,15 +1583,20 @@ v4l2_subdev_state_get_format(struct v4l2_subdev_state *state, unsigned int pad,
  * For stream-unaware drivers the crop rectangle for the corresponding pad is
  * returned. If the pad does not exist, NULL is returned.
  */
+#define v4l2_subdev_state_get_crop(state, pad, ...)			\
+	__v4l2_subdev_state_gen_call(crop, ##__VA_ARGS__, , _pad)	\
+		(state, pad, ##__VA_ARGS__)
+#define __v4l2_subdev_state_get_crop_pad(state, pad)	\
+	__v4l2_subdev_state_get_crop(state, pad, 0)
 struct v4l2_rect *
-v4l2_subdev_state_get_crop(struct v4l2_subdev_state *state, unsigned int pad,
-			   u32 stream);
+__v4l2_subdev_state_get_crop(struct v4l2_subdev_state *state, unsigned int pad,
+			     u32 stream);
 
 /**
  * v4l2_subdev_state_get_compose() - Get pointer to a stream compose rectangle
  * @state: subdevice state
  * @pad: pad id
- * @stream: stream id
+ * @...: stream id (optional argument)
  *
  * This returns a pointer to compose rectangle for the given pad + stream in the
  * subdev state.
@@ -1578,9 +1604,14 @@ v4l2_subdev_state_get_crop(struct v4l2_subdev_state *state, unsigned int pad,
  * For stream-unaware drivers the compose rectangle for the corresponding pad is
  * returned. If the pad does not exist, NULL is returned.
  */
+#define v4l2_subdev_state_get_compose(state, pad, ...)			\
+	__v4l2_subdev_state_gen_call(compose, ##__VA_ARGS__, , _pad)	\
+		(state, pad, ##__VA_ARGS__)
+#define __v4l2_subdev_state_get_compose_pad(state, pad)	\
+	__v4l2_subdev_state_get_compose(state, pad, 0)
 struct v4l2_rect *
-v4l2_subdev_state_get_compose(struct v4l2_subdev_state *state, unsigned int pad,
-			      u32 stream);
+__v4l2_subdev_state_get_compose(struct v4l2_subdev_state *state,
+				unsigned int pad, u32 stream);
 
 /**
  * v4l2_subdev_routing_find_opposite_end() - Find the opposite stream
-- 
cgit v1.2.3


From 981e0d4c724fae1fbc281b3b25b18b041b793f4d Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Fri, 10 Nov 2023 08:10:26 +0100
Subject: media: v4l: subdev: Always compile sub-device state access functions

Compile sub-device state information access functions
v4l2_subdev_state_get_{format,crop,compose} unconditionally as they are
now also used by plain V4L2 drivers.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
---
 drivers/media/v4l2-core/v4l2-subdev.c | 252 +++++++++++++++++-----------------
 include/media/v4l2-subdev.h           | 128 ++++++++---------
 2 files changed, 190 insertions(+), 190 deletions(-)

(limited to 'include')

diff --git a/drivers/media/v4l2-core/v4l2-subdev.c b/drivers/media/v4l2-core/v4l2-subdev.c
index 06988e3a6f10..41fe9fa5c21a 100644
--- a/drivers/media/v4l2-core/v4l2-subdev.c
+++ b/drivers/media/v4l2-core/v4l2-subdev.c
@@ -1531,6 +1531,132 @@ void v4l2_subdev_cleanup(struct v4l2_subdev *sd)
 }
 EXPORT_SYMBOL_GPL(v4l2_subdev_cleanup);
 
+struct v4l2_mbus_framefmt *
+__v4l2_subdev_state_get_format(struct v4l2_subdev_state *state,
+			       unsigned int pad, u32 stream)
+{
+	struct v4l2_subdev_stream_configs *stream_configs;
+	unsigned int i;
+
+	if (WARN_ON_ONCE(!state))
+		return NULL;
+
+	if (state->pads) {
+		if (stream)
+			return NULL;
+
+		/*
+		 * Set the pad to 0 on error as this is aligned with the
+		 * behaviour of the pad state information access functions. The
+		 * purpose of setting pad to 0 here is to avoid accessing memory
+		 * outside the pads array, but still issuing warning of the
+		 * invalid access while making the caller's error handling
+		 * easier.
+		 */
+		if (WARN_ON_ONCE(pad >= state->sd->entity.num_pads))
+			pad = 0;
+
+		return &state->pads[pad].format;
+	}
+
+	lockdep_assert_held(state->lock);
+
+	stream_configs = &state->stream_configs;
+
+	for (i = 0; i < stream_configs->num_configs; ++i) {
+		if (stream_configs->configs[i].pad == pad &&
+		    stream_configs->configs[i].stream == stream)
+			return &stream_configs->configs[i].fmt;
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(__v4l2_subdev_state_get_format);
+
+struct v4l2_rect *
+__v4l2_subdev_state_get_crop(struct v4l2_subdev_state *state, unsigned int pad,
+			     u32 stream)
+{
+	struct v4l2_subdev_stream_configs *stream_configs;
+	unsigned int i;
+
+	if (WARN_ON_ONCE(!state))
+		return NULL;
+
+	if (state->pads) {
+		if (stream)
+			return NULL;
+
+		/*
+		 * Set the pad to 0 on error as this is aligned with the
+		 * behaviour of the pad state information access functions. The
+		 * purpose of setting pad to 0 here is to avoid accessing memory
+		 * outside the pads array, but still issuing warning of the
+		 * invalid access while making the caller's error handling
+		 * easier.
+		 */
+		if (WARN_ON_ONCE(pad >= state->sd->entity.num_pads))
+			pad = 0;
+
+		return &state->pads[pad].crop;
+	}
+
+	lockdep_assert_held(state->lock);
+
+	stream_configs = &state->stream_configs;
+
+	for (i = 0; i < stream_configs->num_configs; ++i) {
+		if (stream_configs->configs[i].pad == pad &&
+		    stream_configs->configs[i].stream == stream)
+			return &stream_configs->configs[i].crop;
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(__v4l2_subdev_state_get_crop);
+
+struct v4l2_rect *
+__v4l2_subdev_state_get_compose(struct v4l2_subdev_state *state,
+				unsigned int pad, u32 stream)
+{
+	struct v4l2_subdev_stream_configs *stream_configs;
+	unsigned int i;
+
+	if (WARN_ON_ONCE(!state))
+		return NULL;
+
+	if (state->pads) {
+		if (stream)
+			return NULL;
+
+		/*
+		 * Set the pad to 0 on error as this is aligned with the
+		 * behaviour of the pad state information access functions. The
+		 * purpose of setting pad to 0 here is to avoid accessing memory
+		 * outside the pads array, but still issuing warning of the
+		 * invalid access while making the caller's error handling
+		 * easier.
+		 */
+		if (WARN_ON_ONCE(pad >= state->sd->entity.num_pads))
+			pad = 0;
+
+		return &state->pads[pad].compose;
+	}
+
+	lockdep_assert_held(state->lock);
+
+	stream_configs = &state->stream_configs;
+
+	for (i = 0; i < stream_configs->num_configs; ++i) {
+		if (stream_configs->configs[i].pad == pad &&
+		    stream_configs->configs[i].stream == stream)
+			return &stream_configs->configs[i].compose;
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(__v4l2_subdev_state_get_compose);
+
 #if defined(CONFIG_VIDEO_V4L2_SUBDEV_API)
 
 static int
@@ -1677,132 +1803,6 @@ int v4l2_subdev_set_routing_with_fmt(struct v4l2_subdev *sd,
 }
 EXPORT_SYMBOL_GPL(v4l2_subdev_set_routing_with_fmt);
 
-struct v4l2_mbus_framefmt *
-__v4l2_subdev_state_get_format(struct v4l2_subdev_state *state,
-			       unsigned int pad, u32 stream)
-{
-	struct v4l2_subdev_stream_configs *stream_configs;
-	unsigned int i;
-
-	if (WARN_ON_ONCE(!state))
-		return NULL;
-
-	if (state->pads) {
-		if (stream)
-			return NULL;
-
-		/*
-		 * Set the pad to 0 on error as this is aligned with the
-		 * behaviour of the pad state information access functions. The
-		 * purpose of setting pad to 0 here is to avoid accessing memory
-		 * outside the pads array, but still issuing warning of the
-		 * invalid access while making the caller's error handling
-		 * easier.
-		 */
-		if (WARN_ON_ONCE(pad >= state->sd->entity.num_pads))
-			pad = 0;
-
-		return &state->pads[pad].format;
-	}
-
-	lockdep_assert_held(state->lock);
-
-	stream_configs = &state->stream_configs;
-
-	for (i = 0; i < stream_configs->num_configs; ++i) {
-		if (stream_configs->configs[i].pad == pad &&
-		    stream_configs->configs[i].stream == stream)
-			return &stream_configs->configs[i].fmt;
-	}
-
-	return NULL;
-}
-EXPORT_SYMBOL_GPL(__v4l2_subdev_state_get_format);
-
-struct v4l2_rect *
-__v4l2_subdev_state_get_crop(struct v4l2_subdev_state *state, unsigned int pad,
-			     u32 stream)
-{
-	struct v4l2_subdev_stream_configs *stream_configs;
-	unsigned int i;
-
-	if (WARN_ON_ONCE(!state))
-		return NULL;
-
-	if (state->pads) {
-		if (stream)
-			return NULL;
-
-		/*
-		 * Set the pad to 0 on error as this is aligned with the
-		 * behaviour of the pad state information access functions. The
-		 * purpose of setting pad to 0 here is to avoid accessing memory
-		 * outside the pads array, but still issuing warning of the
-		 * invalid access while making the caller's error handling
-		 * easier.
-		 */
-		if (WARN_ON_ONCE(pad >= state->sd->entity.num_pads))
-			pad = 0;
-
-		return &state->pads[pad].crop;
-	}
-
-	lockdep_assert_held(state->lock);
-
-	stream_configs = &state->stream_configs;
-
-	for (i = 0; i < stream_configs->num_configs; ++i) {
-		if (stream_configs->configs[i].pad == pad &&
-		    stream_configs->configs[i].stream == stream)
-			return &stream_configs->configs[i].crop;
-	}
-
-	return NULL;
-}
-EXPORT_SYMBOL_GPL(__v4l2_subdev_state_get_crop);
-
-struct v4l2_rect *
-__v4l2_subdev_state_get_compose(struct v4l2_subdev_state *state,
-				unsigned int pad, u32 stream)
-{
-	struct v4l2_subdev_stream_configs *stream_configs;
-	unsigned int i;
-
-	if (WARN_ON_ONCE(!state))
-		return NULL;
-
-	if (state->pads) {
-		if (stream)
-			return NULL;
-
-		/*
-		 * Set the pad to 0 on error as this is aligned with the
-		 * behaviour of the pad state information access functions. The
-		 * purpose of setting pad to 0 here is to avoid accessing memory
-		 * outside the pads array, but still issuing warning of the
-		 * invalid access while making the caller's error handling
-		 * easier.
-		 */
-		if (WARN_ON_ONCE(pad >= state->sd->entity.num_pads))
-			pad = 0;
-
-		return &state->pads[pad].compose;
-	}
-
-	lockdep_assert_held(state->lock);
-
-	stream_configs = &state->stream_configs;
-
-	for (i = 0; i < stream_configs->num_configs; ++i) {
-		if (stream_configs->configs[i].pad == pad &&
-		    stream_configs->configs[i].stream == stream)
-			return &stream_configs->configs[i].compose;
-	}
-
-	return NULL;
-}
-EXPORT_SYMBOL_GPL(__v4l2_subdev_state_get_compose);
-
 int v4l2_subdev_routing_find_opposite_end(const struct v4l2_subdev_krouting *routing,
 					  u32 pad, u32 stream, u32 *other_pad,
 					  u32 *other_stream)
diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h
index c8ac91a2cdb8..80744d87bae4 100644
--- a/include/media/v4l2-subdev.h
+++ b/include/media/v4l2-subdev.h
@@ -1470,70 +1470,6 @@ v4l2_subdev_lock_and_get_active_state(struct v4l2_subdev *sd)
 	return sd->active_state;
 }
 
-#if defined(CONFIG_VIDEO_V4L2_SUBDEV_API)
-
-/**
- * v4l2_subdev_get_fmt() - Fill format based on state
- * @sd: subdevice
- * @state: subdevice state
- * @format: pointer to &struct v4l2_subdev_format
- *
- * Fill @format->format field based on the information in the @format struct.
- *
- * This function can be used by the subdev drivers which support active state to
- * implement v4l2_subdev_pad_ops.get_fmt if the subdev driver does not need to
- * do anything special in their get_fmt op.
- *
- * Returns 0 on success, error value otherwise.
- */
-int v4l2_subdev_get_fmt(struct v4l2_subdev *sd, struct v4l2_subdev_state *state,
-			struct v4l2_subdev_format *format);
-
-/**
- * v4l2_subdev_set_routing() - Set given routing to subdev state
- * @sd: The subdevice
- * @state: The subdevice state
- * @routing: Routing that will be copied to subdev state
- *
- * This will release old routing table (if any) from the state, allocate
- * enough space for the given routing, and copy the routing.
- *
- * This can be used from the subdev driver's set_routing op, after validating
- * the routing.
- */
-int v4l2_subdev_set_routing(struct v4l2_subdev *sd,
-			    struct v4l2_subdev_state *state,
-			    const struct v4l2_subdev_krouting *routing);
-
-struct v4l2_subdev_route *
-__v4l2_subdev_next_active_route(const struct v4l2_subdev_krouting *routing,
-				struct v4l2_subdev_route *route);
-
-/**
- * for_each_active_route - iterate on all active routes of a routing table
- * @routing: The routing table
- * @route: The route iterator
- */
-#define for_each_active_route(routing, route) \
-	for ((route) = NULL;                  \
-	     ((route) = __v4l2_subdev_next_active_route((routing), (route)));)
-
-/**
- * v4l2_subdev_set_routing_with_fmt() - Set given routing and format to subdev
- *					state
- * @sd: The subdevice
- * @state: The subdevice state
- * @routing: Routing that will be copied to subdev state
- * @fmt: Format used to initialize all the streams
- *
- * This is the same as v4l2_subdev_set_routing, but additionally initializes
- * all the streams using the given format.
- */
-int v4l2_subdev_set_routing_with_fmt(struct v4l2_subdev *sd,
-				     struct v4l2_subdev_state *state,
-				     const struct v4l2_subdev_krouting *routing,
-				     const struct v4l2_mbus_framefmt *fmt);
-
 /*
  * A macro to generate the macro or function name for sub-devices state access
  * wrapper macros below.
@@ -1613,6 +1549,70 @@ struct v4l2_rect *
 __v4l2_subdev_state_get_compose(struct v4l2_subdev_state *state,
 				unsigned int pad, u32 stream);
 
+#if defined(CONFIG_VIDEO_V4L2_SUBDEV_API)
+
+/**
+ * v4l2_subdev_get_fmt() - Fill format based on state
+ * @sd: subdevice
+ * @state: subdevice state
+ * @format: pointer to &struct v4l2_subdev_format
+ *
+ * Fill @format->format field based on the information in the @format struct.
+ *
+ * This function can be used by the subdev drivers which support active state to
+ * implement v4l2_subdev_pad_ops.get_fmt if the subdev driver does not need to
+ * do anything special in their get_fmt op.
+ *
+ * Returns 0 on success, error value otherwise.
+ */
+int v4l2_subdev_get_fmt(struct v4l2_subdev *sd, struct v4l2_subdev_state *state,
+			struct v4l2_subdev_format *format);
+
+/**
+ * v4l2_subdev_set_routing() - Set given routing to subdev state
+ * @sd: The subdevice
+ * @state: The subdevice state
+ * @routing: Routing that will be copied to subdev state
+ *
+ * This will release old routing table (if any) from the state, allocate
+ * enough space for the given routing, and copy the routing.
+ *
+ * This can be used from the subdev driver's set_routing op, after validating
+ * the routing.
+ */
+int v4l2_subdev_set_routing(struct v4l2_subdev *sd,
+			    struct v4l2_subdev_state *state,
+			    const struct v4l2_subdev_krouting *routing);
+
+struct v4l2_subdev_route *
+__v4l2_subdev_next_active_route(const struct v4l2_subdev_krouting *routing,
+				struct v4l2_subdev_route *route);
+
+/**
+ * for_each_active_route - iterate on all active routes of a routing table
+ * @routing: The routing table
+ * @route: The route iterator
+ */
+#define for_each_active_route(routing, route) \
+	for ((route) = NULL;                  \
+	     ((route) = __v4l2_subdev_next_active_route((routing), (route)));)
+
+/**
+ * v4l2_subdev_set_routing_with_fmt() - Set given routing and format to subdev
+ *					state
+ * @sd: The subdevice
+ * @state: The subdevice state
+ * @routing: Routing that will be copied to subdev state
+ * @fmt: Format used to initialize all the streams
+ *
+ * This is the same as v4l2_subdev_set_routing, but additionally initializes
+ * all the streams using the given format.
+ */
+int v4l2_subdev_set_routing_with_fmt(struct v4l2_subdev *sd,
+				     struct v4l2_subdev_state *state,
+				     const struct v4l2_subdev_krouting *routing,
+				     const struct v4l2_mbus_framefmt *fmt);
+
 /**
  * v4l2_subdev_routing_find_opposite_end() - Find the opposite stream
  * @routing: routing used to find the opposite side
-- 
cgit v1.2.3


From 34dfd1dd52660dc85d43c92c2cb8029efb2bb8f3 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Fri, 13 Oct 2023 10:09:21 +0200
Subject: media: v4l: subdev: Remove stream-unaware sub-device state access

Remove stream-unaware sub-device state access functions and macros. These
are no longer used.

[Sakari Ailus: Resolve a minor conflict in removed code.]

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
---
 include/media/v4l2-subdev.h | 77 ---------------------------------------------
 1 file changed, 77 deletions(-)

(limited to 'include')

diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h
index 80744d87bae4..2a438e516095 100644
--- a/include/media/v4l2-subdev.h
+++ b/include/media/v4l2-subdev.h
@@ -1137,83 +1137,6 @@ struct v4l2_subdev_fh {
 #define to_v4l2_subdev_fh(fh)	\
 	container_of(fh, struct v4l2_subdev_fh, vfh)
 
-#if defined(CONFIG_VIDEO_V4L2_SUBDEV_API)
-
-/**
- * v4l2_subdev_get_pad_format - ancillary routine to get
- *	&struct v4l2_subdev_pad_config->format
- *
- * @sd: pointer to &struct v4l2_subdev
- * @state: pointer to &struct v4l2_subdev_state
- * @pad: index of the pad in the &struct v4l2_subdev_state->pads array
- */
-static inline struct v4l2_mbus_framefmt *
-v4l2_subdev_get_pad_format(struct v4l2_subdev *sd,
-			   struct v4l2_subdev_state *state,
-			   unsigned int pad)
-{
-	if (WARN_ON(!state))
-		return NULL;
-	if (WARN_ON(pad >= sd->entity.num_pads))
-		pad = 0;
-	return &state->pads[pad].format;
-}
-
-/**
- * v4l2_subdev_get_pad_crop - ancillary routine to get
- *	&struct v4l2_subdev_pad_config->crop
- *
- * @sd: pointer to &struct v4l2_subdev
- * @state: pointer to &struct v4l2_subdev_state.
- * @pad: index of the pad in the &struct v4l2_subdev_state->pads array.
- */
-static inline struct v4l2_rect *
-v4l2_subdev_get_pad_crop(struct v4l2_subdev *sd,
-			 struct v4l2_subdev_state *state,
-			 unsigned int pad)
-{
-	if (WARN_ON(!state))
-		return NULL;
-	if (WARN_ON(pad >= sd->entity.num_pads))
-		pad = 0;
-	return &state->pads[pad].crop;
-}
-
-/**
- * v4l2_subdev_get_pad_compose - ancillary routine to get
- *	&struct v4l2_subdev_pad_config->compose
- *
- * @sd: pointer to &struct v4l2_subdev
- * @state: pointer to &struct v4l2_subdev_state.
- * @pad: index of the pad in the &struct v4l2_subdev_state->pads array.
- */
-static inline struct v4l2_rect *
-v4l2_subdev_get_pad_compose(struct v4l2_subdev *sd,
-			    struct v4l2_subdev_state *state,
-			    unsigned int pad)
-{
-	if (WARN_ON(!state))
-		return NULL;
-	if (WARN_ON(pad >= sd->entity.num_pads))
-		pad = 0;
-	return &state->pads[pad].compose;
-}
-
-/*
- * Temprary helpers until uses of v4l2_subdev_get_try_* functions have been
- * renamed
- */
-#define v4l2_subdev_get_try_format(sd, state, pad) \
-	v4l2_subdev_get_pad_format(sd, state, pad)
-
-#define v4l2_subdev_get_try_crop(sd, state, pad) \
-	v4l2_subdev_get_pad_crop(sd, state, pad)
-
-#define v4l2_subdev_get_try_compose(sd, state, pad) \
-	v4l2_subdev_get_pad_compose(sd, state, pad)
-
-#endif /* CONFIG_VIDEO_V4L2_SUBDEV_API */
-
 extern const struct v4l2_file_operations v4l2_subdev_fops;
 
 /**
-- 
cgit v1.2.3


From 80abebd9bf72516a3a6ed50f69908b9dbbf72a93 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Thu, 23 Nov 2023 14:32:12 +0100
Subject: dt-bindings: interconnect: document the RPMh Network-On-Chip
 Interconnect in Qualcomm SM8650 SoC

Document the RPMh Network-On-Chip Interconnect of the SM8650 platform.

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20231123-topic-sm8650-upstream-interconnect-v2-1-7e050874f59b@linaro.org
Signed-off-by: Georgi Djakov <djakov@kernel.org>
---
 .../bindings/interconnect/qcom,sm8650-rpmh.yaml    | 136 ++++++++++++++++++
 .../dt-bindings/interconnect/qcom,sm8650-rpmh.h    | 154 +++++++++++++++++++++
 2 files changed, 290 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/interconnect/qcom,sm8650-rpmh.yaml
 create mode 100644 include/dt-bindings/interconnect/qcom,sm8650-rpmh.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/interconnect/qcom,sm8650-rpmh.yaml b/Documentation/devicetree/bindings/interconnect/qcom,sm8650-rpmh.yaml
new file mode 100644
index 000000000000..f9322de7cd61
--- /dev/null
+++ b/Documentation/devicetree/bindings/interconnect/qcom,sm8650-rpmh.yaml
@@ -0,0 +1,136 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/interconnect/qcom,sm8650-rpmh.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm RPMh Network-On-Chip Interconnect on SM8650
+
+maintainers:
+  - Abel Vesa <abel.vesa@linaro.org>
+  - Neil Armstrong <neil.armstrong@linaro.org>
+
+description: |
+  RPMh interconnect providers support system bandwidth requirements through
+  RPMh hardware accelerators known as Bus Clock Manager (BCM). The provider is
+  able to communicate with the BCM through the Resource State Coordinator (RSC)
+  associated with each execution environment. Provider nodes must point to at
+  least one RPMh device child node pertaining to their RSC and each provider
+  can map to multiple RPMh resources.
+
+  See also:: include/dt-bindings/interconnect/qcom,sm8650-rpmh.h
+
+properties:
+  compatible:
+    enum:
+      - qcom,sm8650-aggre1-noc
+      - qcom,sm8650-aggre2-noc
+      - qcom,sm8650-clk-virt
+      - qcom,sm8650-cnoc-main
+      - qcom,sm8650-config-noc
+      - qcom,sm8650-gem-noc
+      - qcom,sm8650-lpass-ag-noc
+      - qcom,sm8650-lpass-lpiaon-noc
+      - qcom,sm8650-lpass-lpicx-noc
+      - qcom,sm8650-mc-virt
+      - qcom,sm8650-mmss-noc
+      - qcom,sm8650-nsp-noc
+      - qcom,sm8650-pcie-anoc
+      - qcom,sm8650-system-noc
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    minItems: 1
+    maxItems: 2
+
+required:
+  - compatible
+
+allOf:
+  - $ref: qcom,rpmh-common.yaml#
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - qcom,sm8650-clk-virt
+              - qcom,sm8650-mc-virt
+    then:
+      properties:
+        reg: false
+    else:
+      required:
+        - reg
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - qcom,sm8650-pcie-anoc
+    then:
+      properties:
+        clocks:
+          items:
+            - description: aggre-NOC PCIe AXI clock
+            - description: cfg-NOC PCIe a-NOC AHB clock
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - qcom,sm8650-aggre1-noc
+    then:
+      properties:
+        clocks:
+          items:
+            - description: aggre UFS PHY AXI clock
+            - description: aggre USB3 PRIM AXI clock
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - qcom,sm8650-aggre2-noc
+    then:
+      properties:
+        clocks:
+          items:
+            - description: RPMH CC IPA clock
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - qcom,sm8650-aggre1-noc
+              - qcom,sm8650-aggre2-noc
+              - qcom,sm8650-pcie-anoc
+    then:
+      required:
+        - clocks
+    else:
+      properties:
+        clocks: false
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    clk_virt: interconnect-0 {
+      compatible = "qcom,sm8650-clk-virt";
+      #interconnect-cells = <2>;
+      qcom,bcm-voters = <&apps_bcm_voter>;
+    };
+
+    aggre1_noc: interconnect@16e0000 {
+      compatible = "qcom,sm8650-aggre1-noc";
+      reg = <0x016e0000 0x14400>;
+      #interconnect-cells = <2>;
+      clocks = <&gcc_phy_axi_clk>, <&gcc_prim_axi_clk>;
+      qcom,bcm-voters = <&apps_bcm_voter>;
+    };
diff --git a/include/dt-bindings/interconnect/qcom,sm8650-rpmh.h b/include/dt-bindings/interconnect/qcom,sm8650-rpmh.h
new file mode 100644
index 000000000000..6c1eaf04e241
--- /dev/null
+++ b/include/dt-bindings/interconnect/qcom,sm8650-rpmh.h
@@ -0,0 +1,154 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/*
+ * Copyright (c) 2021, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#ifndef __DT_BINDINGS_INTERCONNECT_QCOM_SM8650_H
+#define __DT_BINDINGS_INTERCONNECT_QCOM_SM8650_H
+
+#define MASTER_QSPI_0				0
+#define MASTER_QUP_1				1
+#define MASTER_QUP_3				2
+#define MASTER_SDCC_4				3
+#define MASTER_UFS_MEM				4
+#define MASTER_USB3_0				5
+#define SLAVE_A1NOC_SNOC			6
+
+#define MASTER_QDSS_BAM				0
+#define MASTER_QUP_2				1
+#define MASTER_CRYPTO				2
+#define MASTER_IPA				3
+#define MASTER_SP				4
+#define MASTER_QDSS_ETR				5
+#define MASTER_QDSS_ETR_1			6
+#define MASTER_SDCC_2				7
+#define SLAVE_A2NOC_SNOC			8
+
+#define MASTER_QUP_CORE_0			0
+#define MASTER_QUP_CORE_1			1
+#define MASTER_QUP_CORE_2			2
+#define SLAVE_QUP_CORE_0			3
+#define SLAVE_QUP_CORE_1			4
+#define SLAVE_QUP_CORE_2			5
+
+#define MASTER_CNOC_CFG				0
+#define SLAVE_AHB2PHY_SOUTH			1
+#define SLAVE_AHB2PHY_NORTH			2
+#define SLAVE_CAMERA_CFG			3
+#define SLAVE_CLK_CTL				4
+#define SLAVE_RBCPR_CX_CFG			5
+#define SLAVE_CPR_HMX				6
+#define SLAVE_RBCPR_MMCX_CFG			7
+#define SLAVE_RBCPR_MXA_CFG			8
+#define SLAVE_RBCPR_MXC_CFG			9
+#define SLAVE_CPR_NSPCX				10
+#define SLAVE_CRYPTO_0_CFG			11
+#define SLAVE_CX_RDPM				12
+#define SLAVE_DISPLAY_CFG			13
+#define SLAVE_GFX3D_CFG				14
+#define SLAVE_I2C				15
+#define SLAVE_I3C_IBI0_CFG			16
+#define SLAVE_I3C_IBI1_CFG			17
+#define SLAVE_IMEM_CFG				18
+#define SLAVE_CNOC_MSS				19
+#define SLAVE_MX_2_RDPM				20
+#define SLAVE_MX_RDPM				21
+#define SLAVE_PCIE_0_CFG			22
+#define SLAVE_PCIE_1_CFG			23
+#define SLAVE_PCIE_RSCC				24
+#define SLAVE_PDM				25
+#define SLAVE_PRNG				26
+#define SLAVE_QDSS_CFG				27
+#define SLAVE_QSPI_0				28
+#define SLAVE_QUP_3				29
+#define SLAVE_QUP_1				30
+#define SLAVE_QUP_2				31
+#define SLAVE_SDCC_2				32
+#define SLAVE_SDCC_4				33
+#define SLAVE_SPSS_CFG				34
+#define SLAVE_TCSR				35
+#define SLAVE_TLMM				36
+#define SLAVE_UFS_MEM_CFG			37
+#define SLAVE_USB3_0				38
+#define SLAVE_VENUS_CFG				39
+#define SLAVE_VSENSE_CTRL_CFG			40
+#define SLAVE_CNOC_MNOC_CFG			41
+#define SLAVE_NSP_QTB_CFG			42
+#define SLAVE_PCIE_ANOC_CFG			43
+#define SLAVE_SERVICE_CNOC_CFG			44
+#define SLAVE_QDSS_STM				45
+#define SLAVE_TCU				46
+
+#define MASTER_GEM_NOC_CNOC			0
+#define MASTER_GEM_NOC_PCIE_SNOC		1
+#define SLAVE_AOSS				2
+#define SLAVE_IPA_CFG				3
+#define SLAVE_IPC_ROUTER_CFG			4
+#define SLAVE_TME_CFG				5
+#define SLAVE_APPSS				6
+#define SLAVE_CNOC_CFG				7
+#define SLAVE_DDRSS_CFG				8
+#define SLAVE_IMEM				9
+#define SLAVE_SERVICE_CNOC			10
+#define SLAVE_PCIE_0				11
+#define SLAVE_PCIE_1				12
+
+#define MASTER_GPU_TCU				0
+#define MASTER_SYS_TCU				1
+#define MASTER_UBWC_P_TCU			2
+#define MASTER_APPSS_PROC			3
+#define MASTER_GFX3D				4
+#define MASTER_LPASS_GEM_NOC			5
+#define MASTER_MSS_PROC				6
+#define MASTER_MNOC_HF_MEM_NOC			7
+#define MASTER_MNOC_SF_MEM_NOC			8
+#define MASTER_COMPUTE_NOC			9
+#define MASTER_ANOC_PCIE_GEM_NOC		10
+#define MASTER_SNOC_SF_MEM_NOC			11
+#define MASTER_UBWC_P				12
+#define MASTER_GIC				13
+#define SLAVE_GEM_NOC_CNOC			14
+#define SLAVE_LLCC				15
+#define SLAVE_MEM_NOC_PCIE_SNOC			16
+
+#define MASTER_LPIAON_NOC			0
+#define SLAVE_LPASS_GEM_NOC			1
+
+#define MASTER_LPASS_LPINOC			0
+#define SLAVE_LPIAON_NOC_LPASS_AG_NOC		1
+
+#define MASTER_LPASS_PROC			0
+#define SLAVE_LPICX_NOC_LPIAON_NOC		1
+
+#define MASTER_LLCC				0
+#define SLAVE_EBI1				1
+
+#define MASTER_CAMNOC_HF			0
+#define MASTER_CAMNOC_ICP			1
+#define MASTER_CAMNOC_SF			2
+#define MASTER_MDP				3
+#define MASTER_CDSP_HCP				4
+#define MASTER_VIDEO				5
+#define MASTER_VIDEO_CV_PROC			6
+#define MASTER_VIDEO_PROC			7
+#define MASTER_VIDEO_V_PROC			8
+#define MASTER_CNOC_MNOC_CFG			9
+#define SLAVE_MNOC_HF_MEM_NOC			10
+#define SLAVE_MNOC_SF_MEM_NOC			11
+#define SLAVE_SERVICE_MNOC			12
+
+#define MASTER_CDSP_PROC			0
+#define SLAVE_CDSP_MEM_NOC			1
+
+#define MASTER_PCIE_ANOC_CFG			0
+#define MASTER_PCIE_0				1
+#define MASTER_PCIE_1				2
+#define SLAVE_ANOC_PCIE_GEM_NOC			3
+#define SLAVE_SERVICE_PCIE_ANOC			4
+
+#define MASTER_A1NOC_SNOC			0
+#define MASTER_A2NOC_SNOC			1
+#define SLAVE_SNOC_GEM_NOC_SF			2
+
+#endif
-- 
cgit v1.2.3


From dc84a76f054c01cc1d769a86ffa3a7e13867915a Mon Sep 17 00:00:00 2001
From: Rajendra Nayak <quic_rjendra@quicinc.com>
Date: Thu, 23 Nov 2023 19:20:27 +0530
Subject: dt-bindings: interconnect: Add Qualcomm X1E80100 SoC

The Qualcomm X1E80100 SoC has several bus fabrics that could be controlled
and tuned dynamically according to the bandwidth demand.

Co-developed-by: Abel Vesa <abel.vesa@linaro.org>
Signed-off-by: Abel Vesa <abel.vesa@linaro.org>
Signed-off-by: Rajendra Nayak <quic_rjendra@quicinc.com>
Co-developed-by: Sibi Sankar <quic_sibis@quicinc.com>
Signed-off-by: Sibi Sankar <quic_sibis@quicinc.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231123135028.29433-2-quic_sibis@quicinc.com
Signed-off-by: Georgi Djakov <djakov@kernel.org>
---
 .../bindings/interconnect/qcom,x1e80100-rpmh.yaml  |  83 +++++++++
 .../dt-bindings/interconnect/qcom,x1e80100-rpmh.h  | 207 +++++++++++++++++++++
 2 files changed, 290 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/interconnect/qcom,x1e80100-rpmh.yaml
 create mode 100644 include/dt-bindings/interconnect/qcom,x1e80100-rpmh.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/interconnect/qcom,x1e80100-rpmh.yaml b/Documentation/devicetree/bindings/interconnect/qcom,x1e80100-rpmh.yaml
new file mode 100644
index 000000000000..08b0210e0e59
--- /dev/null
+++ b/Documentation/devicetree/bindings/interconnect/qcom,x1e80100-rpmh.yaml
@@ -0,0 +1,83 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/interconnect/qcom,x1e80100-rpmh.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm RPMh Network-On-Chip Interconnect on X1E80100
+
+maintainers:
+  - Rajendra Nayak <quic_rjendra@quicinc.com>
+  - Abel Vesa <abel.vesa@linaro.org>
+
+description: |
+  RPMh interconnect providers support system bandwidth requirements through
+  RPMh hardware accelerators known as Bus Clock Manager (BCM). The provider is
+  able to communicate with the BCM through the Resource State Coordinator (RSC)
+  associated with each execution environment. Provider nodes must point to at
+  least one RPMh device child node pertaining to their RSC and each provider
+  can map to multiple RPMh resources.
+
+  See also:: include/dt-bindings/interconnect/qcom,x1e80100-rpmh.h
+
+properties:
+  compatible:
+    enum:
+      - qcom,x1e80100-aggre1-noc
+      - qcom,x1e80100-aggre2-noc
+      - qcom,x1e80100-clk-virt
+      - qcom,x1e80100-cnoc-cfg
+      - qcom,x1e80100-cnoc-main
+      - qcom,x1e80100-gem-noc
+      - qcom,x1e80100-lpass-ag-noc
+      - qcom,x1e80100-lpass-lpiaon-noc
+      - qcom,x1e80100-lpass-lpicx-noc
+      - qcom,x1e80100-mc-virt
+      - qcom,x1e80100-mmss-noc
+      - qcom,x1e80100-nsp-noc
+      - qcom,x1e80100-pcie-center-anoc
+      - qcom,x1e80100-pcie-north-anoc
+      - qcom,x1e80100-pcie-south-anoc
+      - qcom,x1e80100-system-noc
+      - qcom,x1e80100-usb-center-anoc
+      - qcom,x1e80100-usb-north-anoc
+      - qcom,x1e80100-usb-south-anoc
+
+  reg:
+    maxItems: 1
+
+required:
+  - compatible
+
+allOf:
+  - $ref: qcom,rpmh-common.yaml#
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - qcom,x1e80100-clk-virt
+              - qcom,x1e80100-mc-virt
+    then:
+      properties:
+        reg: false
+    else:
+      required:
+        - reg
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    clk_virt: interconnect-0 {
+      compatible = "qcom,x1e80100-clk-virt";
+      #interconnect-cells = <2>;
+      qcom,bcm-voters = <&apps_bcm_voter>;
+    };
+
+    aggre1_noc: interconnect@16e0000 {
+      compatible = "qcom,x1e80100-aggre1-noc";
+      reg = <0x016e0000 0x14400>;
+      #interconnect-cells = <2>;
+      qcom,bcm-voters = <&apps_bcm_voter>;
+    };
diff --git a/include/dt-bindings/interconnect/qcom,x1e80100-rpmh.h b/include/dt-bindings/interconnect/qcom,x1e80100-rpmh.h
new file mode 100644
index 000000000000..a38c3472698a
--- /dev/null
+++ b/include/dt-bindings/interconnect/qcom,x1e80100-rpmh.h
@@ -0,0 +1,207 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/*
+ * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#ifndef __DT_BINDINGS_INTERCONNECT_QCOM_X1E80100_H
+#define __DT_BINDINGS_INTERCONNECT_QCOM_X1E80100_H
+
+#define MASTER_QSPI_0				0
+#define MASTER_QUP_1				1
+#define MASTER_SDCC_4				2
+#define MASTER_UFS_MEM				3
+#define SLAVE_A1NOC_SNOC			4
+
+#define MASTER_QUP_0				0
+#define MASTER_QUP_2				1
+#define MASTER_CRYPTO				2
+#define MASTER_SP				3
+#define MASTER_QDSS_ETR				4
+#define MASTER_QDSS_ETR_1			5
+#define MASTER_SDCC_2				6
+#define SLAVE_A2NOC_SNOC			7
+
+#define MASTER_DDR_PERF_MODE			0
+#define MASTER_QUP_CORE_0			1
+#define MASTER_QUP_CORE_1			2
+#define MASTER_QUP_CORE_2			3
+#define SLAVE_DDR_PERF_MODE			4
+#define SLAVE_QUP_CORE_0			5
+#define SLAVE_QUP_CORE_1			6
+#define SLAVE_QUP_CORE_2			7
+
+#define MASTER_CNOC_CFG				0
+#define SLAVE_AHB2PHY_SOUTH			1
+#define SLAVE_AHB2PHY_NORTH			2
+#define SLAVE_AHB2PHY_2				3
+#define SLAVE_AV1_ENC_CFG			4
+#define SLAVE_CAMERA_CFG			5
+#define SLAVE_CLK_CTL				6
+#define SLAVE_CRYPTO_0_CFG			7
+#define SLAVE_DISPLAY_CFG			8
+#define SLAVE_GFX3D_CFG				9
+#define SLAVE_IMEM_CFG				10
+#define SLAVE_IPC_ROUTER_CFG			11
+#define SLAVE_PCIE_0_CFG			12
+#define SLAVE_PCIE_1_CFG			13
+#define SLAVE_PCIE_2_CFG			14
+#define SLAVE_PCIE_3_CFG			15
+#define SLAVE_PCIE_4_CFG			16
+#define SLAVE_PCIE_5_CFG			17
+#define SLAVE_PCIE_6A_CFG			18
+#define SLAVE_PCIE_6B_CFG			19
+#define SLAVE_PCIE_RSC_CFG			20
+#define SLAVE_PDM				21
+#define SLAVE_PRNG				22
+#define SLAVE_QDSS_CFG				23
+#define SLAVE_QSPI_0				24
+#define SLAVE_QUP_0				25
+#define SLAVE_QUP_1				26
+#define SLAVE_QUP_2				27
+#define SLAVE_SDCC_2				28
+#define SLAVE_SDCC_4				29
+#define SLAVE_SMMUV3_CFG			30
+#define SLAVE_TCSR				31
+#define SLAVE_TLMM				32
+#define SLAVE_UFS_MEM_CFG			33
+#define SLAVE_USB2				34
+#define SLAVE_USB3_0				35
+#define SLAVE_USB3_1				36
+#define SLAVE_USB3_2				37
+#define SLAVE_USB3_MP				38
+#define SLAVE_USB4_0				39
+#define SLAVE_USB4_1				40
+#define SLAVE_USB4_2				41
+#define SLAVE_VENUS_CFG				42
+#define SLAVE_LPASS_QTB_CFG			43
+#define SLAVE_CNOC_MNOC_CFG			44
+#define SLAVE_NSP_QTB_CFG			45
+#define SLAVE_QDSS_STM				46
+#define SLAVE_TCU				47
+
+#define MASTER_GEM_NOC_CNOC			0
+#define MASTER_GEM_NOC_PCIE_SNOC		1
+#define SLAVE_AOSS				2
+#define SLAVE_TME_CFG				3
+#define SLAVE_APPSS				4
+#define SLAVE_CNOC_CFG				5
+#define SLAVE_BOOT_IMEM				6
+#define SLAVE_IMEM				7
+#define SLAVE_PCIE_0				8
+#define SLAVE_PCIE_1				9
+#define SLAVE_PCIE_2				10
+#define SLAVE_PCIE_3				11
+#define SLAVE_PCIE_4				12
+#define SLAVE_PCIE_5				13
+#define SLAVE_PCIE_6A				14
+#define SLAVE_PCIE_6B				15
+
+#define MASTER_GPU_TCU				0
+#define MASTER_PCIE_TCU				1
+#define MASTER_SYS_TCU				2
+#define MASTER_APPSS_PROC			3
+#define MASTER_GFX3D				4
+#define MASTER_LPASS_GEM_NOC			5
+#define MASTER_MNOC_HF_MEM_NOC			6
+#define MASTER_MNOC_SF_MEM_NOC			7
+#define MASTER_COMPUTE_NOC			8
+#define MASTER_ANOC_PCIE_GEM_NOC		9
+#define MASTER_SNOC_SF_MEM_NOC			10
+#define MASTER_GIC2				11
+#define SLAVE_GEM_NOC_CNOC			12
+#define SLAVE_LLCC				13
+#define SLAVE_MEM_NOC_PCIE_SNOC			14
+#define MASTER_MNOC_HF_MEM_NOC_DISP		15
+#define MASTER_ANOC_PCIE_GEM_NOC_DISP		16
+#define SLAVE_LLCC_DISP				17
+#define MASTER_ANOC_PCIE_GEM_NOC_PCIE		18
+#define SLAVE_LLCC_PCIE				19
+
+#define MASTER_LPIAON_NOC			0
+#define SLAVE_LPASS_GEM_NOC			1
+
+#define MASTER_LPASS_LPINOC			0
+#define SLAVE_LPIAON_NOC_LPASS_AG_NOC		1
+
+#define MASTER_LPASS_PROC			0
+#define SLAVE_LPICX_NOC_LPIAON_NOC		1
+
+#define MASTER_LLCC				0
+#define SLAVE_EBI1				1
+#define MASTER_LLCC_DISP			2
+#define SLAVE_EBI1_DISP				3
+#define MASTER_LLCC_PCIE			4
+#define SLAVE_EBI1_PCIE				5
+
+#define MASTER_AV1_ENC				0
+#define MASTER_CAMNOC_HF			1
+#define MASTER_CAMNOC_ICP			2
+#define MASTER_CAMNOC_SF			3
+#define MASTER_EVA				4
+#define MASTER_MDP				5
+#define MASTER_VIDEO				6
+#define MASTER_VIDEO_CV_PROC			7
+#define MASTER_VIDEO_V_PROC			8
+#define MASTER_CNOC_MNOC_CFG			9
+#define SLAVE_MNOC_HF_MEM_NOC			10
+#define SLAVE_MNOC_SF_MEM_NOC			11
+#define SLAVE_SERVICE_MNOC			12
+#define MASTER_MDP_DISP				13
+#define SLAVE_MNOC_HF_MEM_NOC_DISP		14
+
+#define MASTER_CDSP_PROC			0
+#define SLAVE_CDSP_MEM_NOC			1
+
+#define MASTER_PCIE_NORTH			0
+#define MASTER_PCIE_SOUTH			1
+#define SLAVE_ANOC_PCIE_GEM_NOC			2
+#define MASTER_PCIE_NORTH_PCIE			3
+#define MASTER_PCIE_SOUTH_PCIE			4
+#define SLAVE_ANOC_PCIE_GEM_NOC_PCIE		5
+
+#define MASTER_PCIE_3				0
+#define MASTER_PCIE_4				1
+#define MASTER_PCIE_5				2
+#define SLAVE_PCIE_NORTH			3
+#define MASTER_PCIE_3_PCIE			4
+#define MASTER_PCIE_4_PCIE			5
+#define MASTER_PCIE_5_PCIE			6
+#define SLAVE_PCIE_NORTH_PCIE			7
+
+#define MASTER_PCIE_0				0
+#define MASTER_PCIE_1				1
+#define MASTER_PCIE_2				2
+#define MASTER_PCIE_6A				3
+#define MASTER_PCIE_6B				4
+#define SLAVE_PCIE_SOUTH			5
+#define MASTER_PCIE_0_PCIE			6
+#define MASTER_PCIE_1_PCIE			7
+#define MASTER_PCIE_2_PCIE			8
+#define MASTER_PCIE_6A_PCIE			9
+#define MASTER_PCIE_6B_PCIE			10
+#define SLAVE_PCIE_SOUTH_PCIE			11
+
+#define MASTER_A1NOC_SNOC			0
+#define MASTER_A2NOC_SNOC			1
+#define MASTER_GIC1				2
+#define MASTER_USB_NOC_SNOC			3
+#define SLAVE_SNOC_GEM_NOC_SF			4
+
+#define MASTER_AGGRE_USB_NORTH			0
+#define MASTER_AGGRE_USB_SOUTH			1
+#define SLAVE_USB_NOC_SNOC			2
+
+#define MASTER_USB2				0
+#define MASTER_USB3_MP				1
+#define SLAVE_AGGRE_USB_NORTH			2
+
+#define MASTER_USB3_0				0
+#define MASTER_USB3_1				1
+#define MASTER_USB3_2				2
+#define MASTER_USB4_0				3
+#define MASTER_USB4_1				4
+#define MASTER_USB4_2				5
+#define SLAVE_AGGRE_USB_SOUTH			6
+
+#endif
-- 
cgit v1.2.3


From d4e3b928ab487a8aecd1f6a140b40ac365116cfb Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Fri, 17 Nov 2023 19:13:27 -0500
Subject: closures: CLOSURE_CALLBACK() to fix type punning

Control flow integrity is now checking that type signatures match on
indirect function calls. That breaks closures, which embed a work_struct
in a closure in such a way that a closure_fn may also be used as a
workqueue fn by the underlying closure code.

So we have to change closure fns to take a work_struct as their
argument - but that results in a loss of clarity, as closure fns have
different semantics from normal workqueue functions (they run owning a
ref on the closure, which must be released with continue_at() or
closure_return()).

Thus, this patc introduces CLOSURE_CALLBACK() and closure_type() macros
as suggested by Kees, to smooth things over a bit.

Suggested-by: Kees Cook <keescook@chromium.org>
Cc: Coly Li <colyli@suse.de>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 drivers/md/bcache/btree.c           | 14 +++----
 drivers/md/bcache/journal.c         | 20 +++++-----
 drivers/md/bcache/movinggc.c        | 16 ++++----
 drivers/md/bcache/request.c         | 74 ++++++++++++++++++-------------------
 drivers/md/bcache/request.h         |  2 +-
 drivers/md/bcache/super.c           | 40 ++++++++++----------
 drivers/md/bcache/writeback.c       | 16 ++++----
 fs/bcachefs/btree_io.c              |  7 ++--
 fs/bcachefs/btree_update_interior.c |  4 +-
 fs/bcachefs/fs-io-direct.c          |  8 ++--
 fs/bcachefs/io_write.c              | 14 +++----
 fs/bcachefs/io_write.h              |  3 +-
 fs/bcachefs/journal_io.c            | 17 ++++-----
 fs/bcachefs/journal_io.h            |  2 +-
 include/linux/closure.h             |  9 ++++-
 lib/closure.c                       |  5 ++-
 16 files changed, 127 insertions(+), 124 deletions(-)

(limited to 'include')

diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index ae5cbb55861f..9441eac3d546 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -293,16 +293,16 @@ static void btree_complete_write(struct btree *b, struct btree_write *w)
 	w->journal	= NULL;
 }
 
-static void btree_node_write_unlock(struct closure *cl)
+static CLOSURE_CALLBACK(btree_node_write_unlock)
 {
-	struct btree *b = container_of(cl, struct btree, io);
+	closure_type(b, struct btree, io);
 
 	up(&b->io_mutex);
 }
 
-static void __btree_node_write_done(struct closure *cl)
+static CLOSURE_CALLBACK(__btree_node_write_done)
 {
-	struct btree *b = container_of(cl, struct btree, io);
+	closure_type(b, struct btree, io);
 	struct btree_write *w = btree_prev_write(b);
 
 	bch_bbio_free(b->bio, b->c);
@@ -315,12 +315,12 @@ static void __btree_node_write_done(struct closure *cl)
 	closure_return_with_destructor(cl, btree_node_write_unlock);
 }
 
-static void btree_node_write_done(struct closure *cl)
+static CLOSURE_CALLBACK(btree_node_write_done)
 {
-	struct btree *b = container_of(cl, struct btree, io);
+	closure_type(b, struct btree, io);
 
 	bio_free_pages(b->bio);
-	__btree_node_write_done(cl);
+	__btree_node_write_done(&cl->work);
 }
 
 static void btree_node_write_endio(struct bio *bio)
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index c182c21de2e8..7ff14bd2feb8 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -723,11 +723,11 @@ static void journal_write_endio(struct bio *bio)
 	closure_put(&w->c->journal.io);
 }
 
-static void journal_write(struct closure *cl);
+static CLOSURE_CALLBACK(journal_write);
 
-static void journal_write_done(struct closure *cl)
+static CLOSURE_CALLBACK(journal_write_done)
 {
-	struct journal *j = container_of(cl, struct journal, io);
+	closure_type(j, struct journal, io);
 	struct journal_write *w = (j->cur == j->w)
 		? &j->w[1]
 		: &j->w[0];
@@ -736,19 +736,19 @@ static void journal_write_done(struct closure *cl)
 	continue_at_nobarrier(cl, journal_write, bch_journal_wq);
 }
 
-static void journal_write_unlock(struct closure *cl)
+static CLOSURE_CALLBACK(journal_write_unlock)
 	__releases(&c->journal.lock)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, journal.io);
+	closure_type(c, struct cache_set, journal.io);
 
 	c->journal.io_in_flight = 0;
 	spin_unlock(&c->journal.lock);
 }
 
-static void journal_write_unlocked(struct closure *cl)
+static CLOSURE_CALLBACK(journal_write_unlocked)
 	__releases(c->journal.lock)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, journal.io);
+	closure_type(c, struct cache_set, journal.io);
 	struct cache *ca = c->cache;
 	struct journal_write *w = c->journal.cur;
 	struct bkey *k = &c->journal.key;
@@ -823,12 +823,12 @@ static void journal_write_unlocked(struct closure *cl)
 	continue_at(cl, journal_write_done, NULL);
 }
 
-static void journal_write(struct closure *cl)
+static CLOSURE_CALLBACK(journal_write)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, journal.io);
+	closure_type(c, struct cache_set, journal.io);
 
 	spin_lock(&c->journal.lock);
-	journal_write_unlocked(cl);
+	journal_write_unlocked(&cl->work);
 }
 
 static void journal_try_write(struct cache_set *c)
diff --git a/drivers/md/bcache/movinggc.c b/drivers/md/bcache/movinggc.c
index 9f32901fdad1..ebd500bdf0b2 100644
--- a/drivers/md/bcache/movinggc.c
+++ b/drivers/md/bcache/movinggc.c
@@ -35,16 +35,16 @@ static bool moving_pred(struct keybuf *buf, struct bkey *k)
 
 /* Moving GC - IO loop */
 
-static void moving_io_destructor(struct closure *cl)
+static CLOSURE_CALLBACK(moving_io_destructor)
 {
-	struct moving_io *io = container_of(cl, struct moving_io, cl);
+	closure_type(io, struct moving_io, cl);
 
 	kfree(io);
 }
 
-static void write_moving_finish(struct closure *cl)
+static CLOSURE_CALLBACK(write_moving_finish)
 {
-	struct moving_io *io = container_of(cl, struct moving_io, cl);
+	closure_type(io, struct moving_io, cl);
 	struct bio *bio = &io->bio.bio;
 
 	bio_free_pages(bio);
@@ -89,9 +89,9 @@ static void moving_init(struct moving_io *io)
 	bch_bio_map(bio, NULL);
 }
 
-static void write_moving(struct closure *cl)
+static CLOSURE_CALLBACK(write_moving)
 {
-	struct moving_io *io = container_of(cl, struct moving_io, cl);
+	closure_type(io, struct moving_io, cl);
 	struct data_insert_op *op = &io->op;
 
 	if (!op->status) {
@@ -113,9 +113,9 @@ static void write_moving(struct closure *cl)
 	continue_at(cl, write_moving_finish, op->wq);
 }
 
-static void read_moving_submit(struct closure *cl)
+static CLOSURE_CALLBACK(read_moving_submit)
 {
-	struct moving_io *io = container_of(cl, struct moving_io, cl);
+	closure_type(io, struct moving_io, cl);
 	struct bio *bio = &io->bio.bio;
 
 	bch_submit_bbio(bio, io->op.c, &io->w->key, 0);
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index a9b1f3896249..83d112bd2b1c 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -25,7 +25,7 @@
 
 struct kmem_cache *bch_search_cache;
 
-static void bch_data_insert_start(struct closure *cl);
+static CLOSURE_CALLBACK(bch_data_insert_start);
 
 static unsigned int cache_mode(struct cached_dev *dc)
 {
@@ -55,9 +55,9 @@ static void bio_csum(struct bio *bio, struct bkey *k)
 
 /* Insert data into cache */
 
-static void bch_data_insert_keys(struct closure *cl)
+static CLOSURE_CALLBACK(bch_data_insert_keys)
 {
-	struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
+	closure_type(op, struct data_insert_op, cl);
 	atomic_t *journal_ref = NULL;
 	struct bkey *replace_key = op->replace ? &op->replace_key : NULL;
 	int ret;
@@ -136,9 +136,9 @@ out:
 	continue_at(cl, bch_data_insert_keys, op->wq);
 }
 
-static void bch_data_insert_error(struct closure *cl)
+static CLOSURE_CALLBACK(bch_data_insert_error)
 {
-	struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
+	closure_type(op, struct data_insert_op, cl);
 
 	/*
 	 * Our data write just errored, which means we've got a bunch of keys to
@@ -163,7 +163,7 @@ static void bch_data_insert_error(struct closure *cl)
 
 	op->insert_keys.top = dst;
 
-	bch_data_insert_keys(cl);
+	bch_data_insert_keys(&cl->work);
 }
 
 static void bch_data_insert_endio(struct bio *bio)
@@ -184,9 +184,9 @@ static void bch_data_insert_endio(struct bio *bio)
 	bch_bbio_endio(op->c, bio, bio->bi_status, "writing data to cache");
 }
 
-static void bch_data_insert_start(struct closure *cl)
+static CLOSURE_CALLBACK(bch_data_insert_start)
 {
-	struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
+	closure_type(op, struct data_insert_op, cl);
 	struct bio *bio = op->bio, *n;
 
 	if (op->bypass)
@@ -305,16 +305,16 @@ err:
  * If op->bypass is true, instead of inserting the data it invalidates the
  * region of the cache represented by op->bio and op->inode.
  */
-void bch_data_insert(struct closure *cl)
+CLOSURE_CALLBACK(bch_data_insert)
 {
-	struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
+	closure_type(op, struct data_insert_op, cl);
 
 	trace_bcache_write(op->c, op->inode, op->bio,
 			   op->writeback, op->bypass);
 
 	bch_keylist_init(&op->insert_keys);
 	bio_get(op->bio);
-	bch_data_insert_start(cl);
+	bch_data_insert_start(&cl->work);
 }
 
 /*
@@ -575,9 +575,9 @@ static int cache_lookup_fn(struct btree_op *op, struct btree *b, struct bkey *k)
 	return n == bio ? MAP_DONE : MAP_CONTINUE;
 }
 
-static void cache_lookup(struct closure *cl)
+static CLOSURE_CALLBACK(cache_lookup)
 {
-	struct search *s = container_of(cl, struct search, iop.cl);
+	closure_type(s, struct search, iop.cl);
 	struct bio *bio = &s->bio.bio;
 	struct cached_dev *dc;
 	int ret;
@@ -698,9 +698,9 @@ static void do_bio_hook(struct search *s,
 	bio_cnt_set(bio, 3);
 }
 
-static void search_free(struct closure *cl)
+static CLOSURE_CALLBACK(search_free)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 
 	atomic_dec(&s->iop.c->search_inflight);
 
@@ -749,20 +749,20 @@ static inline struct search *search_alloc(struct bio *bio,
 
 /* Cached devices */
 
-static void cached_dev_bio_complete(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_bio_complete)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
 
 	cached_dev_put(dc);
-	search_free(cl);
+	search_free(&cl->work);
 }
 
 /* Process reads */
 
-static void cached_dev_read_error_done(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_read_error_done)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 
 	if (s->iop.replace_collision)
 		bch_mark_cache_miss_collision(s->iop.c, s->d);
@@ -770,12 +770,12 @@ static void cached_dev_read_error_done(struct closure *cl)
 	if (s->iop.bio)
 		bio_free_pages(s->iop.bio);
 
-	cached_dev_bio_complete(cl);
+	cached_dev_bio_complete(&cl->work);
 }
 
-static void cached_dev_read_error(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_read_error)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 	struct bio *bio = &s->bio.bio;
 
 	/*
@@ -801,9 +801,9 @@ static void cached_dev_read_error(struct closure *cl)
 	continue_at(cl, cached_dev_read_error_done, NULL);
 }
 
-static void cached_dev_cache_miss_done(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_cache_miss_done)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 	struct bcache_device *d = s->d;
 
 	if (s->iop.replace_collision)
@@ -812,13 +812,13 @@ static void cached_dev_cache_miss_done(struct closure *cl)
 	if (s->iop.bio)
 		bio_free_pages(s->iop.bio);
 
-	cached_dev_bio_complete(cl);
+	cached_dev_bio_complete(&cl->work);
 	closure_put(&d->cl);
 }
 
-static void cached_dev_read_done(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_read_done)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
 
 	/*
@@ -858,9 +858,9 @@ static void cached_dev_read_done(struct closure *cl)
 	continue_at(cl, cached_dev_cache_miss_done, NULL);
 }
 
-static void cached_dev_read_done_bh(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_read_done_bh)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
 
 	bch_mark_cache_accounting(s->iop.c, s->d,
@@ -955,13 +955,13 @@ static void cached_dev_read(struct cached_dev *dc, struct search *s)
 
 /* Process writes */
 
-static void cached_dev_write_complete(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_write_complete)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
 
 	up_read_non_owner(&dc->writeback_lock);
-	cached_dev_bio_complete(cl);
+	cached_dev_bio_complete(&cl->work);
 }
 
 static void cached_dev_write(struct cached_dev *dc, struct search *s)
@@ -1048,9 +1048,9 @@ insert_data:
 	continue_at(cl, cached_dev_write_complete, NULL);
 }
 
-static void cached_dev_nodata(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_nodata)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 	struct bio *bio = &s->bio.bio;
 
 	if (s->iop.flush_journal)
@@ -1265,9 +1265,9 @@ static int flash_dev_cache_miss(struct btree *b, struct search *s,
 	return MAP_CONTINUE;
 }
 
-static void flash_dev_nodata(struct closure *cl)
+static CLOSURE_CALLBACK(flash_dev_nodata)
 {
-	struct search *s = container_of(cl, struct search, cl);
+	closure_type(s, struct search, cl);
 
 	if (s->iop.flush_journal)
 		bch_journal_meta(s->iop.c, cl);
diff --git a/drivers/md/bcache/request.h b/drivers/md/bcache/request.h
index 38ab4856eaab..46bbef00aebb 100644
--- a/drivers/md/bcache/request.h
+++ b/drivers/md/bcache/request.h
@@ -34,7 +34,7 @@ struct data_insert_op {
 };
 
 unsigned int bch_get_congested(const struct cache_set *c);
-void bch_data_insert(struct closure *cl);
+CLOSURE_CALLBACK(bch_data_insert);
 
 void bch_cached_dev_request_init(struct cached_dev *dc);
 void cached_dev_submit_bio(struct bio *bio);
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 8bd899766372..e0db905c1ca0 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -327,9 +327,9 @@ static void __write_super(struct cache_sb *sb, struct cache_sb_disk *out,
 	submit_bio(bio);
 }
 
-static void bch_write_bdev_super_unlock(struct closure *cl)
+static CLOSURE_CALLBACK(bch_write_bdev_super_unlock)
 {
-	struct cached_dev *dc = container_of(cl, struct cached_dev, sb_write);
+	closure_type(dc, struct cached_dev, sb_write);
 
 	up(&dc->sb_write_mutex);
 }
@@ -363,9 +363,9 @@ static void write_super_endio(struct bio *bio)
 	closure_put(&ca->set->sb_write);
 }
 
-static void bcache_write_super_unlock(struct closure *cl)
+static CLOSURE_CALLBACK(bcache_write_super_unlock)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, sb_write);
+	closure_type(c, struct cache_set, sb_write);
 
 	up(&c->sb_write_mutex);
 }
@@ -407,9 +407,9 @@ static void uuid_endio(struct bio *bio)
 	closure_put(cl);
 }
 
-static void uuid_io_unlock(struct closure *cl)
+static CLOSURE_CALLBACK(uuid_io_unlock)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, uuid_write);
+	closure_type(c, struct cache_set, uuid_write);
 
 	up(&c->uuid_write_mutex);
 }
@@ -1342,9 +1342,9 @@ void bch_cached_dev_release(struct kobject *kobj)
 	module_put(THIS_MODULE);
 }
 
-static void cached_dev_free(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_free)
 {
-	struct cached_dev *dc = container_of(cl, struct cached_dev, disk.cl);
+	closure_type(dc, struct cached_dev, disk.cl);
 
 	if (test_and_clear_bit(BCACHE_DEV_WB_RUNNING, &dc->disk.flags))
 		cancel_writeback_rate_update_dwork(dc);
@@ -1376,9 +1376,9 @@ static void cached_dev_free(struct closure *cl)
 	kobject_put(&dc->disk.kobj);
 }
 
-static void cached_dev_flush(struct closure *cl)
+static CLOSURE_CALLBACK(cached_dev_flush)
 {
-	struct cached_dev *dc = container_of(cl, struct cached_dev, disk.cl);
+	closure_type(dc, struct cached_dev, disk.cl);
 	struct bcache_device *d = &dc->disk;
 
 	mutex_lock(&bch_register_lock);
@@ -1497,9 +1497,9 @@ void bch_flash_dev_release(struct kobject *kobj)
 	kfree(d);
 }
 
-static void flash_dev_free(struct closure *cl)
+static CLOSURE_CALLBACK(flash_dev_free)
 {
-	struct bcache_device *d = container_of(cl, struct bcache_device, cl);
+	closure_type(d, struct bcache_device, cl);
 
 	mutex_lock(&bch_register_lock);
 	atomic_long_sub(bcache_dev_sectors_dirty(d),
@@ -1510,9 +1510,9 @@ static void flash_dev_free(struct closure *cl)
 	kobject_put(&d->kobj);
 }
 
-static void flash_dev_flush(struct closure *cl)
+static CLOSURE_CALLBACK(flash_dev_flush)
 {
-	struct bcache_device *d = container_of(cl, struct bcache_device, cl);
+	closure_type(d, struct bcache_device, cl);
 
 	mutex_lock(&bch_register_lock);
 	bcache_device_unlink(d);
@@ -1668,9 +1668,9 @@ void bch_cache_set_release(struct kobject *kobj)
 	module_put(THIS_MODULE);
 }
 
-static void cache_set_free(struct closure *cl)
+static CLOSURE_CALLBACK(cache_set_free)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, cl);
+	closure_type(c, struct cache_set, cl);
 	struct cache *ca;
 
 	debugfs_remove(c->debug);
@@ -1709,9 +1709,9 @@ static void cache_set_free(struct closure *cl)
 	kobject_put(&c->kobj);
 }
 
-static void cache_set_flush(struct closure *cl)
+static CLOSURE_CALLBACK(cache_set_flush)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, caching);
+	closure_type(c, struct cache_set, caching);
 	struct cache *ca = c->cache;
 	struct btree *b;
 
@@ -1806,9 +1806,9 @@ static void conditional_stop_bcache_device(struct cache_set *c,
 	}
 }
 
-static void __cache_set_unregister(struct closure *cl)
+static CLOSURE_CALLBACK(__cache_set_unregister)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, caching);
+	closure_type(c, struct cache_set, caching);
 	struct cached_dev *dc;
 	struct bcache_device *d;
 	size_t i;
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 24c049067f61..77427e355613 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -341,16 +341,16 @@ static void dirty_init(struct keybuf_key *w)
 	bch_bio_map(bio, NULL);
 }
 
-static void dirty_io_destructor(struct closure *cl)
+static CLOSURE_CALLBACK(dirty_io_destructor)
 {
-	struct dirty_io *io = container_of(cl, struct dirty_io, cl);
+	closure_type(io, struct dirty_io, cl);
 
 	kfree(io);
 }
 
-static void write_dirty_finish(struct closure *cl)
+static CLOSURE_CALLBACK(write_dirty_finish)
 {
-	struct dirty_io *io = container_of(cl, struct dirty_io, cl);
+	closure_type(io, struct dirty_io, cl);
 	struct keybuf_key *w = io->bio.bi_private;
 	struct cached_dev *dc = io->dc;
 
@@ -400,9 +400,9 @@ static void dirty_endio(struct bio *bio)
 	closure_put(&io->cl);
 }
 
-static void write_dirty(struct closure *cl)
+static CLOSURE_CALLBACK(write_dirty)
 {
-	struct dirty_io *io = container_of(cl, struct dirty_io, cl);
+	closure_type(io, struct dirty_io, cl);
 	struct keybuf_key *w = io->bio.bi_private;
 	struct cached_dev *dc = io->dc;
 
@@ -462,9 +462,9 @@ static void read_dirty_endio(struct bio *bio)
 	dirty_endio(bio);
 }
 
-static void read_dirty_submit(struct closure *cl)
+static CLOSURE_CALLBACK(read_dirty_submit)
 {
-	struct dirty_io *io = container_of(cl, struct dirty_io, cl);
+	closure_type(io, struct dirty_io, cl);
 
 	closure_bio_submit(io->dc->disk.c, &io->bio, cl);
 
diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c
index 37d896edb06e..57c20390e10e 100644
--- a/fs/bcachefs/btree_io.c
+++ b/fs/bcachefs/btree_io.c
@@ -1358,10 +1358,9 @@ static bool btree_node_has_extra_bsets(struct bch_fs *c, unsigned offset, void *
 	return offset;
 }
 
-static void btree_node_read_all_replicas_done(struct closure *cl)
+static CLOSURE_CALLBACK(btree_node_read_all_replicas_done)
 {
-	struct btree_node_read_all *ra =
-		container_of(cl, struct btree_node_read_all, cl);
+	closure_type(ra, struct btree_node_read_all, cl);
 	struct bch_fs *c = ra->c;
 	struct btree *b = ra->b;
 	struct printbuf buf = PRINTBUF;
@@ -1567,7 +1566,7 @@ static int btree_node_read_all_replicas(struct bch_fs *c, struct btree *b, bool
 
 	if (sync) {
 		closure_sync(&ra->cl);
-		btree_node_read_all_replicas_done(&ra->cl);
+		btree_node_read_all_replicas_done(&ra->cl.work);
 	} else {
 		continue_at(&ra->cl, btree_node_read_all_replicas_done,
 			    c->io_complete_wq);
diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c
index 76f27bc9fa24..d08efd6d958e 100644
--- a/fs/bcachefs/btree_update_interior.c
+++ b/fs/bcachefs/btree_update_interior.c
@@ -778,9 +778,9 @@ static void btree_interior_update_work(struct work_struct *work)
 	}
 }
 
-static void btree_update_set_nodes_written(struct closure *cl)
+static CLOSURE_CALLBACK(btree_update_set_nodes_written)
 {
-	struct btree_update *as = container_of(cl, struct btree_update, cl);
+	closure_type(as, struct btree_update, cl);
 	struct bch_fs *c = as->c;
 
 	mutex_lock(&c->btree_interior_update_lock);
diff --git a/fs/bcachefs/fs-io-direct.c b/fs/bcachefs/fs-io-direct.c
index 5b42a76c4796..9a479e4de6b3 100644
--- a/fs/bcachefs/fs-io-direct.c
+++ b/fs/bcachefs/fs-io-direct.c
@@ -35,9 +35,9 @@ static void bio_check_or_release(struct bio *bio, bool check_dirty)
 	}
 }
 
-static void bch2_dio_read_complete(struct closure *cl)
+static CLOSURE_CALLBACK(bch2_dio_read_complete)
 {
-	struct dio_read *dio = container_of(cl, struct dio_read, cl);
+	closure_type(dio, struct dio_read, cl);
 
 	dio->req->ki_complete(dio->req, dio->ret);
 	bio_check_or_release(&dio->rbio.bio, dio->should_dirty);
@@ -325,9 +325,9 @@ static noinline int bch2_dio_write_copy_iov(struct dio_write *dio)
 	return 0;
 }
 
-static void bch2_dio_write_flush_done(struct closure *cl)
+static CLOSURE_CALLBACK(bch2_dio_write_flush_done)
 {
-	struct dio_write *dio = container_of(cl, struct dio_write, op.cl);
+	closure_type(dio, struct dio_write, op.cl);
 	struct bch_fs *c = dio->op.c;
 
 	closure_debug_destroy(cl);
diff --git a/fs/bcachefs/io_write.c b/fs/bcachefs/io_write.c
index d704a8f829c8..8ede46b1e354 100644
--- a/fs/bcachefs/io_write.c
+++ b/fs/bcachefs/io_write.c
@@ -580,9 +580,9 @@ static inline void wp_update_state(struct write_point *wp, bool running)
 	__wp_update_state(wp, state);
 }
 
-static void bch2_write_index(struct closure *cl)
+static CLOSURE_CALLBACK(bch2_write_index)
 {
-	struct bch_write_op *op = container_of(cl, struct bch_write_op, cl);
+	closure_type(op, struct bch_write_op, cl);
 	struct write_point *wp = op->wp;
 	struct workqueue_struct *wq = index_update_wq(op);
 	unsigned long flags;
@@ -1208,9 +1208,9 @@ static void __bch2_nocow_write_done(struct bch_write_op *op)
 		bch2_nocow_write_convert_unwritten(op);
 }
 
-static void bch2_nocow_write_done(struct closure *cl)
+static CLOSURE_CALLBACK(bch2_nocow_write_done)
 {
-	struct bch_write_op *op = container_of(cl, struct bch_write_op, cl);
+	closure_type(op, struct bch_write_op, cl);
 
 	__bch2_nocow_write_done(op);
 	bch2_write_done(cl);
@@ -1363,7 +1363,7 @@ err:
 		op->insert_keys.top = op->insert_keys.keys;
 	} else if (op->flags & BCH_WRITE_SYNC) {
 		closure_sync(&op->cl);
-		bch2_nocow_write_done(&op->cl);
+		bch2_nocow_write_done(&op->cl.work);
 	} else {
 		/*
 		 * XXX
@@ -1566,9 +1566,9 @@ err:
  * If op->discard is true, instead of inserting the data it invalidates the
  * region of the cache represented by op->bio and op->inode.
  */
-void bch2_write(struct closure *cl)
+CLOSURE_CALLBACK(bch2_write)
 {
-	struct bch_write_op *op = container_of(cl, struct bch_write_op, cl);
+	closure_type(op, struct bch_write_op, cl);
 	struct bio *bio = &op->wbio.bio;
 	struct bch_fs *c = op->c;
 	unsigned data_len;
diff --git a/fs/bcachefs/io_write.h b/fs/bcachefs/io_write.h
index 9323167229ee..6c276a48f95d 100644
--- a/fs/bcachefs/io_write.h
+++ b/fs/bcachefs/io_write.h
@@ -90,8 +90,7 @@ static inline void bch2_write_op_init(struct bch_write_op *op, struct bch_fs *c,
 	op->devs_need_flush	= NULL;
 }
 
-void bch2_write(struct closure *);
-
+CLOSURE_CALLBACK(bch2_write);
 void bch2_write_point_do_index_updates(struct work_struct *);
 
 static inline struct bch_write_bio *wbio_init(struct bio *bio)
diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c
index 786a09285509..02e6484f9953 100644
--- a/fs/bcachefs/journal_io.c
+++ b/fs/bcachefs/journal_io.c
@@ -1025,10 +1025,9 @@ next_block:
 	return 0;
 }
 
-static void bch2_journal_read_device(struct closure *cl)
+static CLOSURE_CALLBACK(bch2_journal_read_device)
 {
-	struct journal_device *ja =
-		container_of(cl, struct journal_device, read);
+	closure_type(ja, struct journal_device, read);
 	struct bch_dev *ca = container_of(ja, struct bch_dev, journal);
 	struct bch_fs *c = ca->fs;
 	struct journal_list *jlist =
@@ -1520,9 +1519,9 @@ static inline struct journal_buf *journal_last_unwritten_buf(struct journal *j)
 	return j->buf + (journal_last_unwritten_seq(j) & JOURNAL_BUF_MASK);
 }
 
-static void journal_write_done(struct closure *cl)
+static CLOSURE_CALLBACK(journal_write_done)
 {
-	struct journal *j = container_of(cl, struct journal, io);
+	closure_type(j, struct journal, io);
 	struct bch_fs *c = container_of(j, struct bch_fs, journal);
 	struct journal_buf *w = journal_last_unwritten_buf(j);
 	struct bch_replicas_padded replicas;
@@ -1638,9 +1637,9 @@ static void journal_write_endio(struct bio *bio)
 	percpu_ref_put(&ca->io_ref);
 }
 
-static void do_journal_write(struct closure *cl)
+static CLOSURE_CALLBACK(do_journal_write)
 {
-	struct journal *j = container_of(cl, struct journal, io);
+	closure_type(j, struct journal, io);
 	struct bch_fs *c = container_of(j, struct bch_fs, journal);
 	struct bch_dev *ca;
 	struct journal_buf *w = journal_last_unwritten_buf(j);
@@ -1850,9 +1849,9 @@ static int bch2_journal_write_pick_flush(struct journal *j, struct journal_buf *
 	return 0;
 }
 
-void bch2_journal_write(struct closure *cl)
+CLOSURE_CALLBACK(bch2_journal_write)
 {
-	struct journal *j = container_of(cl, struct journal, io);
+	closure_type(j, struct journal, io);
 	struct bch_fs *c = container_of(j, struct bch_fs, journal);
 	struct bch_dev *ca;
 	struct journal_buf *w = journal_last_unwritten_buf(j);
diff --git a/fs/bcachefs/journal_io.h b/fs/bcachefs/journal_io.h
index a88d097b13f1..c035e7c108e1 100644
--- a/fs/bcachefs/journal_io.h
+++ b/fs/bcachefs/journal_io.h
@@ -60,6 +60,6 @@ void bch2_journal_ptrs_to_text(struct printbuf *, struct bch_fs *,
 
 int bch2_journal_read(struct bch_fs *, u64 *, u64 *, u64 *);
 
-void bch2_journal_write(struct closure *);
+CLOSURE_CALLBACK(bch2_journal_write);
 
 #endif /* _BCACHEFS_JOURNAL_IO_H */
diff --git a/include/linux/closure.h b/include/linux/closure.h
index de7bb47d8a46..c554c6a08768 100644
--- a/include/linux/closure.h
+++ b/include/linux/closure.h
@@ -104,7 +104,7 @@
 
 struct closure;
 struct closure_syncer;
-typedef void (closure_fn) (struct closure *);
+typedef void (closure_fn) (struct work_struct *);
 extern struct dentry *bcache_debug;
 
 struct closure_waitlist {
@@ -254,7 +254,7 @@ static inline void closure_queue(struct closure *cl)
 		INIT_WORK(&cl->work, cl->work.func);
 		BUG_ON(!queue_work(wq, &cl->work));
 	} else
-		cl->fn(cl);
+		cl->fn(&cl->work);
 }
 
 /**
@@ -309,6 +309,11 @@ static inline void closure_wake_up(struct closure_waitlist *list)
 	__closure_wake_up(list);
 }
 
+#define CLOSURE_CALLBACK(name)	void name(struct work_struct *ws)
+#define closure_type(name, type, member)				\
+	struct closure *cl = container_of(ws, struct closure, work);	\
+	type *name = container_of(cl, type, member)
+
 /**
  * continue_at - jump to another function with barrier
  *
diff --git a/lib/closure.c b/lib/closure.c
index f86c9eeafb35..c16540552d61 100644
--- a/lib/closure.c
+++ b/lib/closure.c
@@ -36,7 +36,7 @@ static inline void closure_put_after_sub(struct closure *cl, int flags)
 			closure_debug_destroy(cl);
 
 			if (destructor)
-				destructor(cl);
+				destructor(&cl->work);
 
 			if (parent)
 				closure_put(parent);
@@ -108,8 +108,9 @@ struct closure_syncer {
 	int			done;
 };
 
-static void closure_sync_fn(struct closure *cl)
+static CLOSURE_CALLBACK(closure_sync_fn)
 {
+	struct closure *cl = container_of(ws, struct closure, work);
 	struct closure_syncer *s = cl->s;
 	struct task_struct *p;
 
-- 
cgit v1.2.3


From 6543ac13c623f906200dfd3f1c407d8d333b6995 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Tue, 17 Oct 2023 11:09:32 -0500
Subject: soundwire: bus: introduce controller_id

The existing SoundWire support misses a clear Controller/Manager
hiearchical definition to deal with all variants across SOC vendors.

a) Intel platforms have one controller with 4 or more Managers.
b) AMD platforms have two controllers with one Manager each, but due
to BIOS issues use two different link_id values within the scope of a
single controller.
c) QCOM platforms have one or more controller with one Manager each.

This patch adds a 'controller_id' which can be set by higher
levels. If assigned to -1, the controller_id will be set to the
system-unique IDA-assigned bus->id.

The main change is that the bus->id is no longer used for any device
name, which makes the definition completely predictable and not
dependent on any enumeration order. The bus->id is only used to insert
the Managers in the stream rt context.

Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Vijendar Mukunda <Vijendar.Mukunda@amd.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Tested-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/stable/20231017160933.12624-2-pierre-louis.bossart%40linux.intel.com
Tested-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/20231017160933.12624-2-pierre-louis.bossart@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/amd_manager.c     | 8 ++++++++
 drivers/soundwire/bus.c             | 4 ++++
 drivers/soundwire/debugfs.c         | 2 +-
 drivers/soundwire/intel_auxdevice.c | 3 +++
 drivers/soundwire/master.c          | 2 +-
 drivers/soundwire/qcom.c            | 3 +++
 include/linux/soundwire/sdw.h       | 4 +++-
 7 files changed, 23 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/soundwire/amd_manager.c b/drivers/soundwire/amd_manager.c
index 3a99f6dcdfaf..a3b1f4e6f0f9 100644
--- a/drivers/soundwire/amd_manager.c
+++ b/drivers/soundwire/amd_manager.c
@@ -927,6 +927,14 @@ static int amd_sdw_manager_probe(struct platform_device *pdev)
 	amd_manager->bus.clk_stop_timeout = 200;
 	amd_manager->bus.link_id = amd_manager->instance;
 
+	/*
+	 * Due to BIOS compatibility, the two links are exposed within
+	 * the scope of a single controller. If this changes, the
+	 * controller_id will have to be updated with drv_data
+	 * information.
+	 */
+	amd_manager->bus.controller_id = 0;
+
 	switch (amd_manager->instance) {
 	case ACP_SDW0:
 		amd_manager->num_dout_ports = AMD_SDW0_MAX_TX_PORTS;
diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c
index 41b0d9adf68e..f3fec15c3112 100644
--- a/drivers/soundwire/bus.c
+++ b/drivers/soundwire/bus.c
@@ -22,6 +22,10 @@ static int sdw_get_id(struct sdw_bus *bus)
 		return rc;
 
 	bus->id = rc;
+
+	if (bus->controller_id == -1)
+		bus->controller_id = rc;
+
 	return 0;
 }
 
diff --git a/drivers/soundwire/debugfs.c b/drivers/soundwire/debugfs.c
index d1553cb77187..67abd7e52f09 100644
--- a/drivers/soundwire/debugfs.c
+++ b/drivers/soundwire/debugfs.c
@@ -20,7 +20,7 @@ void sdw_bus_debugfs_init(struct sdw_bus *bus)
 		return;
 
 	/* create the debugfs master-N */
-	snprintf(name, sizeof(name), "master-%d-%d", bus->id, bus->link_id);
+	snprintf(name, sizeof(name), "master-%d-%d", bus->controller_id, bus->link_id);
 	bus->debugfs = debugfs_create_dir(name, sdw_debugfs_root);
 }
 
diff --git a/drivers/soundwire/intel_auxdevice.c b/drivers/soundwire/intel_auxdevice.c
index 7f15e3549e53..93698532deac 100644
--- a/drivers/soundwire/intel_auxdevice.c
+++ b/drivers/soundwire/intel_auxdevice.c
@@ -234,6 +234,9 @@ static int intel_link_probe(struct auxiliary_device *auxdev,
 	cdns->instance = sdw->instance;
 	cdns->msg_count = 0;
 
+	/* single controller for all SoundWire links */
+	bus->controller_id = 0;
+
 	bus->link_id = auxdev->id;
 	bus->clk_stop_timeout = 1;
 
diff --git a/drivers/soundwire/master.c b/drivers/soundwire/master.c
index 9b05c9e25ebe..51abedbbaa66 100644
--- a/drivers/soundwire/master.c
+++ b/drivers/soundwire/master.c
@@ -145,7 +145,7 @@ int sdw_master_device_add(struct sdw_bus *bus, struct device *parent,
 	md->dev.fwnode = fwnode;
 	md->dev.dma_mask = parent->dma_mask;
 
-	dev_set_name(&md->dev, "sdw-master-%d", bus->id);
+	dev_set_name(&md->dev, "sdw-master-%d-%d", bus->controller_id, bus->link_id);
 
 	ret = device_register(&md->dev);
 	if (ret) {
diff --git a/drivers/soundwire/qcom.c b/drivers/soundwire/qcom.c
index e9a52c1bd359..7f8549aab42f 100644
--- a/drivers/soundwire/qcom.c
+++ b/drivers/soundwire/qcom.c
@@ -1620,6 +1620,9 @@ static int qcom_swrm_probe(struct platform_device *pdev)
 		}
 	}
 
+	/* FIXME: is there a DT-defined value to use ? */
+	ctrl->bus.controller_id = -1;
+
 	ret = sdw_bus_master_add(&ctrl->bus, dev, dev->fwnode);
 	if (ret) {
 		dev_err(dev, "Failed to register Soundwire controller (%d)\n",
diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 904004d8b562..66f814b63a43 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -886,7 +886,8 @@ struct sdw_master_ops {
  * struct sdw_bus - SoundWire bus
  * @dev: Shortcut to &bus->md->dev to avoid changing the entire code.
  * @md: Master device
- * @link_id: Link id number, can be 0 to N, unique for each Master
+ * @controller_id: system-unique controller ID. If set to -1, the bus @id will be used.
+ * @link_id: Link id number, can be 0 to N, unique for each Controller
  * @id: bus system-wide unique id
  * @slaves: list of Slaves on this bus
  * @assigned: Bitmap for Slave device numbers.
@@ -918,6 +919,7 @@ struct sdw_master_ops {
 struct sdw_bus {
 	struct device *dev;
 	struct sdw_master_device *md;
+	int controller_id;
 	unsigned int link_id;
 	int id;
 	struct list_head slaves;
-- 
cgit v1.2.3


From 8802e580ee643e3f63c6b39ff64e7c7baa4a55ba Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Wed, 22 Nov 2023 14:27:13 +0200
Subject: fs: create __sb_write_started() helper

Similar to sb_write_started() for use by other sb freeze levels.

Unlike the boolean sb_write_started(), this helper returns a tristate
to distiguish the cases of lockdep disabled or unknown lock state.

This is needed for fanotify "pre content" events.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Link: https://lore.kernel.org/r/20231122122715.2561213-15-amir73il@gmail.com
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/fs.h | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 98b7a7a8c42e..ac8b5a9b467b 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1645,9 +1645,23 @@ static inline bool __sb_start_write_trylock(struct super_block *sb, int level)
 #define __sb_writers_release(sb, lev)	\
 	percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_)
 
+/**
+ * __sb_write_started - check if sb freeze level is held
+ * @sb: the super we write to
+ * @level: the freeze level
+ *
+ * > 0 sb freeze level is held
+ *   0 sb freeze level is not held
+ * < 0 !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN
+ */
+static inline int __sb_write_started(const struct super_block *sb, int level)
+{
+	return lockdep_is_held_type(sb->s_writers.rw_sem + level - 1, 1);
+}
+
 static inline bool sb_write_started(const struct super_block *sb)
 {
-	return lockdep_is_held_type(sb->s_writers.rw_sem + SB_FREEZE_WRITE - 1, 1);
+	return __sb_write_started(sb, SB_FREEZE_WRITE);
 }
 
 /**
-- 
cgit v1.2.3


From 3d5cd4911e04683df8f4439fddd788e00a2510a8 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Wed, 22 Nov 2023 14:27:14 +0200
Subject: fs: create file_write_started() helper

Convenience wrapper for sb_write_started(file_inode(inode)->i_sb)), which
has a single occurrence in the code right now.

Document the false negatives of those helpers, which makes them unusable
to assert that sb_start_write() is not held.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Link: https://lore.kernel.org/r/20231122122715.2561213-16-amir73il@gmail.com
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/read_write.c    |  2 +-
 include/linux/fs.h | 21 +++++++++++++++++++++
 2 files changed, 22 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/fs/read_write.c b/fs/read_write.c
index 92c68ab4f221..f791555fa246 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1423,7 +1423,7 @@ ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in,
 				struct file *file_out, loff_t pos_out,
 				size_t len, unsigned int flags)
 {
-	lockdep_assert(sb_write_started(file_inode(file_out)->i_sb));
+	lockdep_assert(file_write_started(file_out));
 
 	return do_splice_direct(file_in, &pos_in, file_out, &pos_out,
 				len > MAX_RW_COUNT ? MAX_RW_COUNT : len, 0);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ac8b5a9b467b..75a10b632edd 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1659,11 +1659,32 @@ static inline int __sb_write_started(const struct super_block *sb, int level)
 	return lockdep_is_held_type(sb->s_writers.rw_sem + level - 1, 1);
 }
 
+/**
+ * sb_write_started - check if SB_FREEZE_WRITE is held
+ * @sb: the super we write to
+ *
+ * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN.
+ */
 static inline bool sb_write_started(const struct super_block *sb)
 {
 	return __sb_write_started(sb, SB_FREEZE_WRITE);
 }
 
+/**
+ * file_write_started - check if SB_FREEZE_WRITE is held
+ * @file: the file we write to
+ *
+ * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN.
+ * May be false positive with !S_ISREG, because file_start_write() has
+ * no effect on !S_ISREG.
+ */
+static inline bool file_write_started(const struct file *file)
+{
+	if (!S_ISREG(file_inode(file)->i_mode))
+		return true;
+	return sb_write_started(file_inode(file)->i_sb);
+}
+
 /**
  * sb_end_write - drop write access to a superblock
  * @sb: the super we wrote to
-- 
cgit v1.2.3


From 21b32e6a0ab5b174fa1ca2fb4c212577cf405d83 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Wed, 22 Nov 2023 14:27:15 +0200
Subject: fs: create {sb,file}_write_not_started() helpers

Create new helpers {sb,file}_write_not_started() that can be used
to assert that sb_start_write() is not held.

This is needed for fanotify "pre content" events.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Link: https://lore.kernel.org/r/20231122122715.2561213-17-amir73il@gmail.com
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/fs.h | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

(limited to 'include')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 75a10b632edd..ae0e2fb7bcea 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1670,6 +1670,17 @@ static inline bool sb_write_started(const struct super_block *sb)
 	return __sb_write_started(sb, SB_FREEZE_WRITE);
 }
 
+/**
+ * sb_write_not_started - check if SB_FREEZE_WRITE is not held
+ * @sb: the super we write to
+ *
+ * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN.
+ */
+static inline bool sb_write_not_started(const struct super_block *sb)
+{
+	return __sb_write_started(sb, SB_FREEZE_WRITE) <= 0;
+}
+
 /**
  * file_write_started - check if SB_FREEZE_WRITE is held
  * @file: the file we write to
@@ -1685,6 +1696,21 @@ static inline bool file_write_started(const struct file *file)
 	return sb_write_started(file_inode(file)->i_sb);
 }
 
+/**
+ * file_write_not_started - check if SB_FREEZE_WRITE is not held
+ * @file: the file we write to
+ *
+ * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN.
+ * May be false positive with !S_ISREG, because file_start_write() has
+ * no effect on !S_ISREG.
+ */
+static inline bool file_write_not_started(const struct file *file)
+{
+	if (!S_ISREG(file_inode(file)->i_mode))
+		return true;
+	return sb_write_not_started(file_inode(file)->i_sb);
+}
+
 /**
  * sb_end_write - drop write access to a superblock
  * @sb: the super we wrote to
-- 
cgit v1.2.3


From 2afae08c9dcb8ac648414277cec70c2fe6a34d9e Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Thu, 23 Nov 2023 19:59:36 -0800
Subject: bpf: Validate global subprogs lazily

Slightly change BPF verifier logic around eagerness and order of global
subprog validation. Instead of going over every global subprog eagerly
and validating it before main (entry) BPF program is verified, turn it
around. Validate main program first, mark subprogs that were called from
main program for later verification, but otherwise assume it is valid.
Afterwards, go over marked global subprogs and validate those,
potentially marking some more global functions as being called. Continue
this process until all (transitively) callable global subprogs are
validated. It's a BFS traversal at its heart and will always converge.

This is an important change because it allows to feature-gate some
subprograms that might not be verifiable on some older kernel, depending
on supported set of features.

E.g., at some point, global functions were allowed to accept a pointer
to memory, which size is identified by user-provided type.
Unfortunately, older kernels don't support this feature. With BPF CO-RE
approach, the natural way would be to still compile BPF object file once
and guard calls to this global subprog with some CO-RE check or using
.rodata variables. That's what people do to guard usage of new helpers
or kfuncs, and any other new BPF-side feature that might be missing on
old kernels.

That's currently impossible to do with global subprogs, unfortunately,
because they are eagerly and unconditionally validated. This patch set
aims to change this, so that in the future when global funcs gain new
features, those can be guarded using BPF CO-RE techniques in the same
fashion as any other new kernel feature.

Two selftests had to be adjusted in sync with these changes.

test_global_func12 relied on eager global subprog validation failing
before main program failure is detected (unknown return value). Fix by
making sure that main program is always valid.

verifier_subprog_precision's parent_stack_slot_precise subtest relied on
verifier checkpointing heuristic to do a checkpoint at instruction #5,
but that's no longer true because we don't have enough jumps validated
before reaching insn #5 due to global subprogs being validated later.

Other than that, no changes, as one would expect.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20231124035937.403208-3-andrii@kernel.org
---
 include/linux/bpf.h                                |  2 +
 kernel/bpf/verifier.c                              | 48 +++++++++++++++++++---
 .../selftests/bpf/progs/test_global_func12.c       |  4 +-
 .../bpf/progs/verifier_subprog_precision.c         |  4 +-
 4 files changed, 48 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 258ba232e302..eb447b0a9423 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1347,6 +1347,8 @@ static inline bool bpf_prog_has_trampoline(const struct bpf_prog *prog)
 struct bpf_func_info_aux {
 	u16 linkage;
 	bool unreliable;
+	bool called : 1;
+	bool verified : 1;
 };
 
 enum bpf_jit_poke_reason {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index a2939ebf2638..8e7b6072e3f4 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -434,6 +434,11 @@ static const char *subprog_name(const struct bpf_verifier_env *env, int subprog)
 	return btf_type_name(env->prog->aux->btf, info->type_id);
 }
 
+static struct bpf_func_info_aux *subprog_aux(const struct bpf_verifier_env *env, int subprog)
+{
+	return &env->prog->aux->func_info_aux[subprog];
+}
+
 static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg)
 {
 	return btf_record_has_field(reg_btf_record(reg), BPF_SPIN_LOCK);
@@ -9290,6 +9295,8 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 
 		verbose(env, "Func#%d ('%s') is global and assumed valid.\n",
 			subprog, sub_name);
+		/* mark global subprog for verifying after main prog */
+		subprog_aux(env, subprog)->called = true;
 		clear_caller_saved_regs(env, caller->regs);
 
 		/* All global functions return a 64-bit SCALAR_VALUE */
@@ -19873,8 +19880,11 @@ out:
 	return ret;
 }
 
-/* Verify all global functions in a BPF program one by one based on their BTF.
- * All global functions must pass verification. Otherwise the whole program is rejected.
+/* Lazily verify all global functions based on their BTF, if they are called
+ * from main BPF program or any of subprograms transitively.
+ * BPF global subprogs called from dead code are not validated.
+ * All callable global functions must pass verification.
+ * Otherwise the whole program is rejected.
  * Consider:
  * int bar(int);
  * int foo(int f)
@@ -19893,14 +19903,26 @@ out:
 static int do_check_subprogs(struct bpf_verifier_env *env)
 {
 	struct bpf_prog_aux *aux = env->prog->aux;
-	int i, ret;
+	struct bpf_func_info_aux *sub_aux;
+	int i, ret, new_cnt;
 
 	if (!aux->func_info)
 		return 0;
 
+	/* exception callback is presumed to be always called */
+	if (env->exception_callback_subprog)
+		subprog_aux(env, env->exception_callback_subprog)->called = true;
+
+again:
+	new_cnt = 0;
 	for (i = 1; i < env->subprog_cnt; i++) {
-		if (aux->func_info_aux[i].linkage != BTF_FUNC_GLOBAL)
+		if (!subprog_is_global(env, i))
+			continue;
+
+		sub_aux = subprog_aux(env, i);
+		if (!sub_aux->called || sub_aux->verified)
 			continue;
+
 		env->insn_idx = env->subprog_info[i].start;
 		WARN_ON_ONCE(env->insn_idx == 0);
 		ret = do_check_common(env, i, env->exception_callback_subprog == i);
@@ -19910,7 +19932,21 @@ static int do_check_subprogs(struct bpf_verifier_env *env)
 			verbose(env, "Func#%d ('%s') is safe for any args that match its prototype\n",
 				i, subprog_name(env, i));
 		}
+
+		/* We verified new global subprog, it might have called some
+		 * more global subprogs that we haven't verified yet, so we
+		 * need to do another pass over subprogs to verify those.
+		 */
+		sub_aux->verified = true;
+		new_cnt++;
 	}
+
+	/* We can't loop forever as we verify at least one global subprog on
+	 * each pass.
+	 */
+	if (new_cnt)
+		goto again;
+
 	return 0;
 }
 
@@ -20556,8 +20592,8 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
 	if (ret < 0)
 		goto skip_full_check;
 
-	ret = do_check_subprogs(env);
-	ret = ret ?: do_check_main(env);
+	ret = do_check_main(env);
+	ret = ret ?: do_check_subprogs(env);
 
 	if (ret == 0 && bpf_prog_is_offloaded(env->prog->aux))
 		ret = bpf_prog_offload_finalize(env);
diff --git a/tools/testing/selftests/bpf/progs/test_global_func12.c b/tools/testing/selftests/bpf/progs/test_global_func12.c
index 7f159d83c6f6..6e03d42519a6 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func12.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func12.c
@@ -19,5 +19,7 @@ int global_func12(struct __sk_buff *skb)
 {
 	const struct S s = {.x = skb->len };
 
-	return foo(&s);
+	foo(&s);
+
+	return 1;
 }
diff --git a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c
index f61d623b1ce8..b5efcaeaa1ae 100644
--- a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c
+++ b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c
@@ -370,12 +370,10 @@ __naked int parent_stack_slot_precise(void)
 SEC("?raw_tp")
 __success __log_level(2)
 __msg("9: (0f) r1 += r6")
-__msg("mark_precise: frame0: last_idx 9 first_idx 6")
+__msg("mark_precise: frame0: last_idx 9 first_idx 0")
 __msg("mark_precise: frame0: regs=r6 stack= before 8: (bf) r1 = r7")
 __msg("mark_precise: frame0: regs=r6 stack= before 7: (27) r6 *= 4")
 __msg("mark_precise: frame0: regs=r6 stack= before 6: (79) r6 = *(u64 *)(r10 -8)")
-__msg("mark_precise: frame0: parent state regs= stack=-8:")
-__msg("mark_precise: frame0: last_idx 5 first_idx 0")
 __msg("mark_precise: frame0: regs= stack=-8 before 5: (85) call pc+6")
 __msg("mark_precise: frame0: regs= stack=-8 before 4: (b7) r1 = 0")
 __msg("mark_precise: frame0: regs= stack=-8 before 3: (7b) *(u64 *)(r10 -8) = r6")
-- 
cgit v1.2.3


From f8e80fc4acebab0447567e77d6abc30fb44250cc Mon Sep 17 00:00:00 2001
From: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Date: Wed, 22 Nov 2023 21:52:57 +0800
Subject: net/smc: add sysctl for max links per lgr for SMC-R v2.1

Add a new sysctl: net.smc.smcr_max_links_per_lgr, which is
used to control the preferred max links per lgr for SMC-R
v2.1. The default value of this sysctl is 2, and the acceptable
value ranges from 1 to 2.

Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Reviewed-by: Dust Li <dust.li@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/smc-sysctl.rst |  8 ++++++++
 include/net/netns/smc.h                 |  1 +
 net/smc/af_smc.c                        |  2 +-
 net/smc/smc_clc.c                       | 10 +++++++---
 net/smc/smc_clc.h                       |  3 ++-
 net/smc/smc_sysctl.c                    | 12 ++++++++++++
 net/smc/smc_sysctl.h                    |  1 +
 7 files changed, 32 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/Documentation/networking/smc-sysctl.rst b/Documentation/networking/smc-sysctl.rst
index 769149d98773..c6ef86ef4c4f 100644
--- a/Documentation/networking/smc-sysctl.rst
+++ b/Documentation/networking/smc-sysctl.rst
@@ -57,3 +57,11 @@ rmem - INTEGER
 	only allowed 512KiB for SMC-R and 1MiB for SMC-D.
 
 	Default: 64KiB
+
+smcr_max_links_per_lgr - INTEGER
+	Controls the max number of links can be added to a SMC-R link group. Notice that
+	the actual number of the links added to a SMC-R link group depends on the number
+	of RDMA devices exist in the system. The acceptable value ranges from 1 to 2. Only
+	for SMC-R v2.1 and later.
+
+	Default: 2
diff --git a/include/net/netns/smc.h b/include/net/netns/smc.h
index 582212ada3ba..da7023587824 100644
--- a/include/net/netns/smc.h
+++ b/include/net/netns/smc.h
@@ -22,5 +22,6 @@ struct netns_smc {
 	int				sysctl_smcr_testlink_time;
 	int				sysctl_wmem;
 	int				sysctl_rmem;
+	int				sysctl_max_links_per_lgr;
 };
 #endif
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 2a1388841951..c61666e5beed 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -2461,7 +2461,7 @@ static void smc_listen_work(struct work_struct *work)
 	if (rc)
 		goto out_decl;
 
-	rc = smc_clc_srv_v2x_features_validate(pclc, ini);
+	rc = smc_clc_srv_v2x_features_validate(new_smc, pclc, ini);
 	if (rc)
 		goto out_decl;
 
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index 8deb46c28f1d..1f87c8895a27 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -824,6 +824,7 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini)
 	struct smc_clc_smcd_gid_chid *gidchids;
 	struct smc_clc_msg_proposal_area *pclc;
 	struct smc_clc_ipv6_prefix *ipv6_prfx;
+	struct net *net = sock_net(&smc->sk);
 	struct smc_clc_v2_extension *v2_ext;
 	struct smc_clc_msg_smcd *pclc_smcd;
 	struct smc_clc_msg_trail *trl;
@@ -944,7 +945,7 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini)
 	if (smcr_indicated(ini->smc_type_v2)) {
 		memcpy(v2_ext->roce, ini->smcrv2.ib_gid_v2, SMC_GID_SIZE);
 		v2_ext->max_conns = SMC_CONN_PER_LGR_PREFER;
-		v2_ext->max_links = SMC_LINKS_PER_LGR_MAX_PREFER;
+		v2_ext->max_links = net->smc.sysctl_max_links_per_lgr;
 	}
 
 	pclc_base->hdr.length = htons(plen);
@@ -1171,10 +1172,12 @@ int smc_clc_send_accept(struct smc_sock *new_smc, bool srv_first_contact,
 	return len > 0 ? 0 : len;
 }
 
-int smc_clc_srv_v2x_features_validate(struct smc_clc_msg_proposal *pclc,
+int smc_clc_srv_v2x_features_validate(struct smc_sock *smc,
+				      struct smc_clc_msg_proposal *pclc,
 				      struct smc_init_info *ini)
 {
 	struct smc_clc_v2_extension *pclc_v2_ext;
+	struct net *net = sock_net(&smc->sk);
 
 	ini->max_conns = SMC_CONN_PER_LGR_MAX;
 	ini->max_links = SMC_LINKS_ADD_LNK_MAX;
@@ -1192,7 +1195,8 @@ int smc_clc_srv_v2x_features_validate(struct smc_clc_msg_proposal *pclc,
 		if (ini->max_conns < SMC_CONN_PER_LGR_MIN)
 			return SMC_CLC_DECL_MAXCONNERR;
 
-		ini->max_links = min_t(u8, pclc_v2_ext->max_links, SMC_LINKS_PER_LGR_MAX_PREFER);
+		ini->max_links = min_t(u8, pclc_v2_ext->max_links,
+				       net->smc.sysctl_max_links_per_lgr);
 		if (ini->max_links < SMC_LINKS_ADD_LNK_MIN)
 			return SMC_CLC_DECL_MAXLINKERR;
 	}
diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h
index c5c8e7db775a..89b258cedffe 100644
--- a/net/smc/smc_clc.h
+++ b/net/smc/smc_clc.h
@@ -422,7 +422,8 @@ int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact,
 			 u8 version, u8 *eid, struct smc_init_info *ini);
 int smc_clc_send_accept(struct smc_sock *smc, bool srv_first_contact,
 			u8 version, u8 *negotiated_eid, struct smc_init_info *ini);
-int smc_clc_srv_v2x_features_validate(struct smc_clc_msg_proposal *pclc,
+int smc_clc_srv_v2x_features_validate(struct smc_sock *smc,
+				      struct smc_clc_msg_proposal *pclc,
 				      struct smc_init_info *ini);
 int smc_clc_clnt_v2x_features_validate(struct smc_clc_first_contact_ext *fce,
 				       struct smc_init_info *ini);
diff --git a/net/smc/smc_sysctl.c b/net/smc/smc_sysctl.c
index 5cbc18c6e62b..3e9bb921e40a 100644
--- a/net/smc/smc_sysctl.c
+++ b/net/smc/smc_sysctl.c
@@ -25,6 +25,8 @@ static int max_sndbuf = INT_MAX / 2;
 static int max_rcvbuf = INT_MAX / 2;
 static const int net_smc_wmem_init = (64 * 1024);
 static const int net_smc_rmem_init = (64 * 1024);
+static int links_per_lgr_min = SMC_LINKS_ADD_LNK_MIN;
+static int links_per_lgr_max = SMC_LINKS_ADD_LNK_MAX;
 
 static struct ctl_table smc_table[] = {
 	{
@@ -68,6 +70,15 @@ static struct ctl_table smc_table[] = {
 		.extra1		= &min_rcvbuf,
 		.extra2		= &max_rcvbuf,
 	},
+	{
+		.procname	= "smcr_max_links_per_lgr",
+		.data		= &init_net.smc.sysctl_max_links_per_lgr,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &links_per_lgr_min,
+		.extra2		= &links_per_lgr_max,
+	},
 	{  }
 };
 
@@ -97,6 +108,7 @@ int __net_init smc_sysctl_net_init(struct net *net)
 	net->smc.sysctl_smcr_testlink_time = SMC_LLC_TESTLINK_DEFAULT_TIME;
 	WRITE_ONCE(net->smc.sysctl_wmem, net_smc_wmem_init);
 	WRITE_ONCE(net->smc.sysctl_rmem, net_smc_rmem_init);
+	net->smc.sysctl_max_links_per_lgr = SMC_LINKS_PER_LGR_MAX_PREFER;
 
 	return 0;
 
diff --git a/net/smc/smc_sysctl.h b/net/smc/smc_sysctl.h
index 0becc11bd2f4..5783dd7575dd 100644
--- a/net/smc/smc_sysctl.h
+++ b/net/smc/smc_sysctl.h
@@ -23,6 +23,7 @@ void __net_exit smc_sysctl_net_exit(struct net *net);
 static inline int smc_sysctl_net_init(struct net *net)
 {
 	net->smc.sysctl_autocorking_size = SMC_AUTOCORKING_DEFAULT_SIZE;
+	net->smc.sysctl_max_links_per_lgr = SMC_LINKS_PER_LGR_MAX_PREFER;
 	return 0;
 }
 
-- 
cgit v1.2.3


From 1f2c9dd73f0a279214f9b3c382b3f1df272b3253 Mon Sep 17 00:00:00 2001
From: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Date: Wed, 22 Nov 2023 21:52:58 +0800
Subject: net/smc: add sysctl for max conns per lgr for SMC-R v2.1

Add a new sysctl: net.smc.smcr_max_conns_per_lgr, which is
used to control the preferred max connections per lgr for
SMC-R v2.1. The default value of this sysctl is 255, and
the acceptable value ranges from 16 to 255.

Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Reviewed-by: Dust Li <dust.li@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/smc-sysctl.rst |  6 ++++++
 include/net/netns/smc.h                 |  1 +
 net/smc/smc_clc.c                       |  5 +++--
 net/smc/smc_sysctl.c                    | 12 ++++++++++++
 net/smc/smc_sysctl.h                    |  1 +
 5 files changed, 23 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/Documentation/networking/smc-sysctl.rst b/Documentation/networking/smc-sysctl.rst
index c6ef86ef4c4f..a874d007f2db 100644
--- a/Documentation/networking/smc-sysctl.rst
+++ b/Documentation/networking/smc-sysctl.rst
@@ -65,3 +65,9 @@ smcr_max_links_per_lgr - INTEGER
 	for SMC-R v2.1 and later.
 
 	Default: 2
+
+smcr_max_conns_per_lgr - INTEGER
+	Controls the max number of connections can be added to a SMC-R link group. The
+	acceptable value ranges from 16 to 255. Only for SMC-R v2.1 and later.
+
+	Default: 255
diff --git a/include/net/netns/smc.h b/include/net/netns/smc.h
index da7023587824..fc752a50f91b 100644
--- a/include/net/netns/smc.h
+++ b/include/net/netns/smc.h
@@ -23,5 +23,6 @@ struct netns_smc {
 	int				sysctl_wmem;
 	int				sysctl_rmem;
 	int				sysctl_max_links_per_lgr;
+	int				sysctl_max_conns_per_lgr;
 };
 #endif
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index 1f87c8895a27..0fda5156eef0 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -944,7 +944,7 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini)
 	}
 	if (smcr_indicated(ini->smc_type_v2)) {
 		memcpy(v2_ext->roce, ini->smcrv2.ib_gid_v2, SMC_GID_SIZE);
-		v2_ext->max_conns = SMC_CONN_PER_LGR_PREFER;
+		v2_ext->max_conns = net->smc.sysctl_max_conns_per_lgr;
 		v2_ext->max_links = net->smc.sysctl_max_links_per_lgr;
 	}
 
@@ -1191,7 +1191,8 @@ int smc_clc_srv_v2x_features_validate(struct smc_sock *smc,
 		return SMC_CLC_DECL_NOV2EXT;
 
 	if (ini->smcr_version & SMC_V2) {
-		ini->max_conns = min_t(u8, pclc_v2_ext->max_conns, SMC_CONN_PER_LGR_PREFER);
+		ini->max_conns = min_t(u8, pclc_v2_ext->max_conns,
+				       net->smc.sysctl_max_conns_per_lgr);
 		if (ini->max_conns < SMC_CONN_PER_LGR_MIN)
 			return SMC_CLC_DECL_MAXCONNERR;
 
diff --git a/net/smc/smc_sysctl.c b/net/smc/smc_sysctl.c
index 3e9bb921e40a..a5946d1b9d60 100644
--- a/net/smc/smc_sysctl.c
+++ b/net/smc/smc_sysctl.c
@@ -27,6 +27,8 @@ static const int net_smc_wmem_init = (64 * 1024);
 static const int net_smc_rmem_init = (64 * 1024);
 static int links_per_lgr_min = SMC_LINKS_ADD_LNK_MIN;
 static int links_per_lgr_max = SMC_LINKS_ADD_LNK_MAX;
+static int conns_per_lgr_min = SMC_CONN_PER_LGR_MIN;
+static int conns_per_lgr_max = SMC_CONN_PER_LGR_MAX;
 
 static struct ctl_table smc_table[] = {
 	{
@@ -79,6 +81,15 @@ static struct ctl_table smc_table[] = {
 		.extra1		= &links_per_lgr_min,
 		.extra2		= &links_per_lgr_max,
 	},
+	{
+		.procname	= "smcr_max_conns_per_lgr",
+		.data		= &init_net.smc.sysctl_max_conns_per_lgr,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &conns_per_lgr_min,
+		.extra2		= &conns_per_lgr_max,
+	},
 	{  }
 };
 
@@ -109,6 +120,7 @@ int __net_init smc_sysctl_net_init(struct net *net)
 	WRITE_ONCE(net->smc.sysctl_wmem, net_smc_wmem_init);
 	WRITE_ONCE(net->smc.sysctl_rmem, net_smc_rmem_init);
 	net->smc.sysctl_max_links_per_lgr = SMC_LINKS_PER_LGR_MAX_PREFER;
+	net->smc.sysctl_max_conns_per_lgr = SMC_CONN_PER_LGR_PREFER;
 
 	return 0;
 
diff --git a/net/smc/smc_sysctl.h b/net/smc/smc_sysctl.h
index 5783dd7575dd..eb2465ae1e15 100644
--- a/net/smc/smc_sysctl.h
+++ b/net/smc/smc_sysctl.h
@@ -24,6 +24,7 @@ static inline int smc_sysctl_net_init(struct net *net)
 {
 	net->smc.sysctl_autocorking_size = SMC_AUTOCORKING_DEFAULT_SIZE;
 	net->smc.sysctl_max_links_per_lgr = SMC_LINKS_PER_LGR_MAX_PREFER;
+	net->smc.sysctl_max_conns_per_lgr = SMC_CONN_PER_LGR_PREFER;
 	return 0;
 }
 
-- 
cgit v1.2.3


From 1a307538c9cc274b3191b9a1380bbceece262626 Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Date: Fri, 24 Nov 2023 17:08:51 +0200
Subject: ASoC: SOF: ipc4: Add data struct for module notification message from
 firmware

With the module notification message the information about the notification
is provided via the mailbox with the sof_ipc4_notify_module_data struct.

It contains the module and instance id of the sender of the notification,
the event_id and optionally additional data which is module and event
specific.

At the same time add definitions to identify ALSA kcontrol change
notification.
These notifications use standardized event_id, modules must follow this if
they support such notifications:
upper 16 bit: 0xA15A as a magic identification value
lower 16 bit: param_id of the changed control

Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Link: https://lore.kernel.org/r/20231124150853.18648-3-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/sof/ipc4/header.h | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

(limited to 'include')

diff --git a/include/sound/sof/ipc4/header.h b/include/sound/sof/ipc4/header.h
index 574a9d581f88..2c81d6dde577 100644
--- a/include/sound/sof/ipc4/header.h
+++ b/include/sound/sof/ipc4/header.h
@@ -532,6 +532,35 @@ struct sof_ipc4_notify_resource_data {
 #define SOF_IPC4_DEBUG_SLOT_TELEMETRY		0x4c455400
 #define SOF_IPC4_DEBUG_SLOT_BROKEN		0x44414544
 
+/**
+ * struct sof_ipc4_notify_module_data - payload for module notification
+ * @instance_id: instance ID of the originator module of the notification
+ * @module_id: module ID of the originator of the notification
+ * @event_id: module specific event id
+ * @event_data_size: Size of the @event_data (if any) in bytes
+ * @event_data: Optional notification data, module and notification dependent
+ */
+struct sof_ipc4_notify_module_data {
+	uint16_t instance_id;
+	uint16_t module_id;
+	uint32_t event_id;
+	uint32_t event_data_size;
+	uint8_t event_data[];
+} __packed __aligned(4);
+
+/*
+ * ALSA kcontrol change notification
+ *
+ * The event_id of struct sof_ipc4_notify_module_data is divided into two u16:
+ *  upper u16: magic number for ALSA kcontrol types: 0xA15A
+ *  lower u16: param_id of the control, which is the type of the control
+ * The event_data contains the struct sof_ipc4_control_msg_payload of the control
+ * which sent the notification.
+ */
+#define SOF_IPC4_NOTIFY_MODULE_EVENTID_ALSA_MAGIC_MASK		GENMASK(31, 16)
+#define SOF_IPC4_NOTIFY_MODULE_EVENTID_ALSA_MAGIC_VAL		0xA15A0000
+#define SOF_IPC4_NOTIFY_MODULE_EVENTID_ALSA_PARAMID_MASK	GENMASK(15, 0)
+
 /** @}*/
 
 #endif
-- 
cgit v1.2.3


From bd5ef3f21d17a80d4e5b9c8e18bad20c8fb53c95 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Fri, 24 Nov 2023 09:41:12 +0100
Subject: dt-bindings: clk: g12a-clkc: add CTS_ENCL clock ids

Add new CLK ids for the CTS_ENCL and CTS_ENCL_SEL clocks
on G12A compatible SoCs.

Acked-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20231124-amlogic-v6-4-upstream-dsi-ccf-vim3-v9-1-95256ed139e6@linaro.org
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
---
 include/dt-bindings/clock/g12a-clkc.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/dt-bindings/clock/g12a-clkc.h b/include/dt-bindings/clock/g12a-clkc.h
index 387767f4e298..636d713f95ff 100644
--- a/include/dt-bindings/clock/g12a-clkc.h
+++ b/include/dt-bindings/clock/g12a-clkc.h
@@ -279,5 +279,7 @@
 #define CLKID_MIPI_DSI_PXCLK_DIV		268
 #define CLKID_MIPI_DSI_PXCLK_SEL		269
 #define CLKID_MIPI_DSI_PXCLK			270
+#define CLKID_CTS_ENCL				271
+#define CLKID_CTS_ENCL_SEL			272
 
 #endif /* __G12A_CLKC_H */
-- 
cgit v1.2.3


From 439d3404addf1a1ee8ba6dc6becd555bce7faf98 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Tue, 14 Nov 2023 11:14:43 +0100
Subject: dt-bindings: clock: g12a-clkc: add MIPI ISP & CSI PHY clock ids

Add MIPI ISP & CSI PHY clock ids to G12A clock bindings header

Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Daniel Scally <dan.scally@ideasonboard.com>
Tested-by: Daniel Scally <dan.scally@ideasonboard.com>
Link: https://lore.kernel.org/r/20231114-topic-amlogic-upstream-isp-clocks-v1-1-223958791501@linaro.org
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
---
 include/dt-bindings/clock/g12a-clkc.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'include')

diff --git a/include/dt-bindings/clock/g12a-clkc.h b/include/dt-bindings/clock/g12a-clkc.h
index 636d713f95ff..fd09819da2ec 100644
--- a/include/dt-bindings/clock/g12a-clkc.h
+++ b/include/dt-bindings/clock/g12a-clkc.h
@@ -281,5 +281,11 @@
 #define CLKID_MIPI_DSI_PXCLK			270
 #define CLKID_CTS_ENCL				271
 #define CLKID_CTS_ENCL_SEL			272
+#define CLKID_MIPI_ISP_DIV			273
+#define CLKID_MIPI_ISP_SEL			274
+#define CLKID_MIPI_ISP				275
+#define CLKID_MIPI_ISP_GATE			276
+#define CLKID_MIPI_ISP_CSI_PHY0			277
+#define CLKID_MIPI_ISP_CSI_PHY1			278
 
 #endif /* __G12A_CLKC_H */
-- 
cgit v1.2.3


From ef5828805842204dd0259ecfc132b5916c8a77ae Mon Sep 17 00:00:00 2001
From: Michael-CY Lee <michael-cy.lee@mediatek.com>
Date: Wed, 22 Nov 2023 11:02:37 +0800
Subject: wifi: avoid offset calculation on NULL pointer

ieee80211_he_6ghz_oper() can be passed a NULL pointer
and checks for that, but already did the calculation
to inside of it before. Move it after the check.

Signed-off-by: Michael-CY Lee <michael-cy.lee@mediatek.com>
Link: https://lore.kernel.org/r/20231122030237.31276-1-michael-cy.lee@mediatek.com
[rewrite commit message]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 958771bac9c0..c2ac9e9e7ee9 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -2830,12 +2830,14 @@ ieee80211_he_oper_size(const u8 *he_oper_ie)
 static inline const struct ieee80211_he_6ghz_oper *
 ieee80211_he_6ghz_oper(const struct ieee80211_he_operation *he_oper)
 {
-	const u8 *ret = (const void *)&he_oper->optional;
+	const u8 *ret;
 	u32 he_oper_params;
 
 	if (!he_oper)
 		return NULL;
 
+	ret = (const void *)&he_oper->optional;
+
 	he_oper_params = le32_to_cpu(he_oper->he_oper_params);
 
 	if (!(he_oper_params & IEEE80211_HE_OPERATION_6GHZ_OP_INFO))
-- 
cgit v1.2.3


From d3ca4ab4f16eb81dc3e7721251adcba49b229d54 Mon Sep 17 00:00:00 2001
From: Liam Kearney <liam.kearney@morsemicro.com>
Date: Wed, 25 Oct 2023 11:27:55 +1100
Subject: wifi: ieee80211: fix PV1 frame control field name

Update PV1 frame control field TODS to FROMDS to match 802.11 standard

Signed-off-by: Liam Kearney <liam.kearney@morsemicro.com>
Reviewed-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Link: https://lore.kernel.org/r/20231025002755.1752983-1-liam.kearney@morsemicro.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 958771bac9c0..5e5ea216f341 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -172,11 +172,11 @@
 #define IEEE80211_SN_MODULO		(IEEE80211_MAX_SN + 1)
 
 
-/* PV1 Layout 11ah 9.8.3.1 */
+/* PV1 Layout IEEE 802.11-2020 9.8.3.1 */
 #define IEEE80211_PV1_FCTL_VERS		0x0003
 #define IEEE80211_PV1_FCTL_FTYPE	0x001c
 #define IEEE80211_PV1_FCTL_STYPE	0x00e0
-#define IEEE80211_PV1_FCTL_TODS		0x0100
+#define IEEE80211_PV1_FCTL_FROMDS		0x0100
 #define IEEE80211_PV1_FCTL_MOREFRAGS	0x0200
 #define IEEE80211_PV1_FCTL_PM		0x0400
 #define IEEE80211_PV1_FCTL_MOREDATA	0x0800
-- 
cgit v1.2.3


From 6285ee30caa1a0fbd9537496578085c143127eee Mon Sep 17 00:00:00 2001
From: Ilan Peer <ilan.peer@intel.com>
Date: Mon, 13 Nov 2023 11:35:00 +0200
Subject: wifi: cfg80211: Extend support for scanning while MLO connected

To extend the support of TSF accounting in scan results for MLO
connections, allow to indicate in the scan request the link ID
corresponding to the BSS whose TSF should be used for the TSF
accounting.

Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Gregory Greenman <gregory.greenman@intel.com>
Link: https://lore.kernel.org/r/20231113112844.d4490bcdefb1.I8fcd158b810adddef4963727e9153096416b30ce@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       | 3 +++
 include/uapi/linux/nl80211.h | 8 +++++---
 net/wireless/nl80211.c       | 1 +
 3 files changed, 9 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index b137a33a1b68..d36ad4cedf3b 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -2608,6 +2608,8 @@ struct cfg80211_scan_6ghz_params {
  * @n_6ghz_params: number of 6 GHz params
  * @scan_6ghz_params: 6 GHz params
  * @bssid: BSSID to scan for (most commonly, the wildcard BSSID)
+ * @tsf_report_link_id: for MLO, indicates the link ID of the BSS that should be
+ *      used for TSF reporting. Can be set to -1 to indicate no preference.
  */
 struct cfg80211_scan_request {
 	struct cfg80211_ssid *ssids;
@@ -2636,6 +2638,7 @@ struct cfg80211_scan_request {
 	bool scan_6ghz;
 	u32 n_6ghz_params;
 	struct cfg80211_scan_6ghz_params *scan_6ghz_params;
+	s8 tsf_report_link_id;
 
 	/* keep last */
 	struct ieee80211_channel *channels[] __counted_by(n_channels);
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index dced2c49daec..03e44823355e 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -6241,9 +6241,11 @@ enum nl80211_feature_flags {
  *	the BSS that the interface that requested the scan is connected to
  *	(if available).
  * @NL80211_EXT_FEATURE_BSS_PARENT_TSF: Per BSS, this driver reports the
- *	time the last beacon/probe was received. The time is the TSF of the
- *	BSS that the interface that requested the scan is connected to
- *	(if available).
+ *	time the last beacon/probe was received. For a non MLO connection, the
+ *	time is the TSF of the BSS that the interface that requested the scan is
+ *	connected to (if available). For an MLO connection, the time is the TSF
+ *	of the BSS corresponding with link ID specified in the scan request (if
+ *	specified).
  * @NL80211_EXT_FEATURE_SET_SCAN_DWELL: This driver supports configuration of
  *	channel dwell time.
  * @NL80211_EXT_FEATURE_BEACON_RATE_LEGACY: Driver supports beacon rate
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 569234bc2be6..12b7bd92bb86 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -9337,6 +9337,7 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info)
 	else
 		eth_broadcast_addr(request->bssid);
 
+	request->tsf_report_link_id = nl80211_link_id_or_invalid(info->attrs);
 	request->wdev = wdev;
 	request->wiphy = &rdev->wiphy;
 	request->scan_start = jiffies;
-- 
cgit v1.2.3


From d1f7728259ef02ac20b7afb6e7eb5a9eb1696c25 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Wed, 15 Nov 2023 17:49:59 +0100
Subject: gpiolib: provide gpio_device_get_label()

Provide a getter for the GPIO device label string so that users don't
have to dereference struct gpio_chip directly.

Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpiolib.c      | 14 ++++++++++++++
 include/linux/gpio/driver.h |  1 +
 2 files changed, 15 insertions(+)

(limited to 'include')

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 95d2a7b2ea3e..a5faaea6915d 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -254,6 +254,20 @@ int gpio_device_get_base(struct gpio_device *gdev)
 }
 EXPORT_SYMBOL_GPL(gpio_device_get_base);
 
+/**
+ * gpio_device_get_label() - Get the label of this GPIO device
+ * @gdev: GPIO device
+ *
+ * Returns:
+ * Pointer to the string containing the GPIO device label. The string's
+ * lifetime is tied to that of the underlying GPIO device.
+ */
+const char *gpio_device_get_label(struct gpio_device *gdev)
+{
+	return gdev->label;
+}
+EXPORT_SYMBOL(gpio_device_get_label);
+
 /**
  * gpio_device_get_chip() - Get the gpio_chip implementation of this GPIO device
  * @gdev: GPIO device
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index 0aed62f0c633..100c329dc986 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -786,6 +786,7 @@ struct gpio_device *gpiod_to_gpio_device(struct gpio_desc *desc);
 
 /* struct gpio_device getters */
 int gpio_device_get_base(struct gpio_device *gdev);
+const char *gpio_device_get_label(struct gpio_device *gdev);
 
 #else /* CONFIG_GPIOLIB */
 
-- 
cgit v1.2.3


From 0cc3f50f42d262d6175ee2834aeb56e98934cfcc Mon Sep 17 00:00:00 2001
From: Vinayak Yadawad <vinayak.yadawad@broadcom.com>
Date: Thu, 9 Nov 2023 12:03:44 +0530
Subject: wifi: nl80211: Documentation update for NL80211_CMD_PORT_AUTHORIZED
 event

Drivers supporting 4-way handshake offload for AP/P2p-GO and
STA/P2P-client should use this event to indicate that port has
been authorized and open for regular data traffic, sending
this event on completion of successful 4-way handshake.

Signed-off-by: Vinayak Yadawad <vinayak.yadawad@broadcom.com>
Link: https://lore.kernel.org/r/f746b59f41436e9df29c24688035fbc6eb91ab06.1699510229.git.vinayak.yadawad@broadcom.com
[rewrite it all to not use the term 'GC' that we don't use
 in place of P2P-client]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/uapi/linux/nl80211.h | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 03e44823355e..0cd1da2c2902 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -1135,11 +1135,15 @@
  * @NL80211_CMD_DEL_PMK: For offloaded 4-Way handshake, delete the previously
  *	configured PMK for the authenticator address identified by
  *	%NL80211_ATTR_MAC.
- * @NL80211_CMD_PORT_AUTHORIZED: An event that indicates an 802.1X FT roam was
- *	completed successfully. Drivers that support 4 way handshake offload
- *	should send this event after indicating 802.1X FT assocation with
- *	%NL80211_CMD_ROAM. If the 4 way handshake failed %NL80211_CMD_DISCONNECT
- *	should be indicated instead.
+ * @NL80211_CMD_PORT_AUTHORIZED: An event that indicates port is authorized and
+ *	open for regular data traffic. For STA/P2P-client, this event is sent
+ *	with AP MAC address and for AP/P2P-GO, the event carries the STA/P2P-
+ *	client MAC address.
+ *	Drivers that support 4 way handshake offload should send this event for
+ *	STA/P2P-client after successful 4-way HS or after 802.1X FT following
+ *	NL80211_CMD_CONNECT or NL80211_CMD_ROAM. Drivers using AP/P2P-GO 4-way
+ *	handshake offload should send this event on successful completion of
+ *	4-way handshake with the peer (STA/P2P-client).
  * @NL80211_CMD_CONTROL_PORT_FRAME: Control Port (e.g. PAE) frame TX request
  *	and RX notification.  This command is used both as a request to transmit
  *	a control port frame and as a notification that a control port frame
-- 
cgit v1.2.3


From 045da3077bc57e587d0ab4cfc8945b76af03d72d Mon Sep 17 00:00:00 2001
From: Akinobu Mita <akinobu.mita@gmail.com>
Date: Sat, 18 Nov 2023 21:44:43 +0900
Subject: scsi: ufs: core: Make fault injection dynamically configurable per
 HBA

The UFS driver has two driver-specific fault injection mechanisms
(trigger_eh and timeout). Each fault injection configuration can only be
specified by a module parameter and cannot be reconfigured without
reloading the driver. Also, each configuration is common to all HBAs.

This change adds the following subdirectories for each UFS HBA when
debugfs is enabled:

  /sys/kernel/debug/ufshcd/<HBA>/timeout_inject
  /sys/kernel/debug/ufshcd/<HBA>/trigger_eh_inject

Each fault injection attribute can be dynamically set per HBA by a
corresponding file in these directories.

This is tested with QEMU UFS devices.

Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Link: https://lore.kernel.org/r/20231118124443.1007116-1-akinobu.mita@gmail.com
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufs-fault-injection.c | 19 +++++++++++++++----
 drivers/ufs/core/ufs-fault-injection.h | 13 +++++++++----
 drivers/ufs/core/ufshcd.c              |  5 +++--
 include/ufs/ufshcd.h                   |  5 +++++
 4 files changed, 32 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/ufs/core/ufs-fault-injection.c b/drivers/ufs/core/ufs-fault-injection.c
index 5b1184aac585..169540417079 100644
--- a/drivers/ufs/core/ufs-fault-injection.c
+++ b/drivers/ufs/core/ufs-fault-injection.c
@@ -4,6 +4,7 @@
 #include <linux/types.h>
 #include <linux/fault-inject.h>
 #include <linux/module.h>
+#include <ufs/ufshcd.h>
 #include "ufs-fault-injection.h"
 
 static int ufs_fault_get(char *buffer, const struct kernel_param *kp);
@@ -59,12 +60,22 @@ static int ufs_fault_set(const char *val, const struct kernel_param *kp)
 	return 0;
 }
 
-bool ufs_trigger_eh(void)
+void ufs_fault_inject_hba_init(struct ufs_hba *hba)
 {
-	return should_fail(&ufs_trigger_eh_attr, 1);
+	hba->trigger_eh_attr = ufs_trigger_eh_attr;
+	hba->timeout_attr = ufs_timeout_attr;
+#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
+	fault_create_debugfs_attr("trigger_eh_inject", hba->debugfs_root, &hba->trigger_eh_attr);
+	fault_create_debugfs_attr("timeout_inject", hba->debugfs_root, &hba->timeout_attr);
+#endif
 }
 
-bool ufs_fail_completion(void)
+bool ufs_trigger_eh(struct ufs_hba *hba)
 {
-	return should_fail(&ufs_timeout_attr, 1);
+	return should_fail(&hba->trigger_eh_attr, 1);
+}
+
+bool ufs_fail_completion(struct ufs_hba *hba)
+{
+	return should_fail(&hba->timeout_attr, 1);
 }
diff --git a/drivers/ufs/core/ufs-fault-injection.h b/drivers/ufs/core/ufs-fault-injection.h
index 6d0cd8e10c87..996a35769781 100644
--- a/drivers/ufs/core/ufs-fault-injection.h
+++ b/drivers/ufs/core/ufs-fault-injection.h
@@ -7,15 +7,20 @@
 #include <linux/types.h>
 
 #ifdef CONFIG_SCSI_UFS_FAULT_INJECTION
-bool ufs_trigger_eh(void);
-bool ufs_fail_completion(void);
+void ufs_fault_inject_hba_init(struct ufs_hba *hba);
+bool ufs_trigger_eh(struct ufs_hba *hba);
+bool ufs_fail_completion(struct ufs_hba *hba);
 #else
-static inline bool ufs_trigger_eh(void)
+static inline void ufs_fault_inject_hba_init(struct ufs_hba *hba)
+{
+}
+
+static inline bool ufs_trigger_eh(struct ufs_hba *hba)
 {
 	return false;
 }
 
-static inline bool ufs_fail_completion(void)
+static inline bool ufs_fail_completion(struct ufs_hba *hba)
 {
 	return false;
 }
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 8b1031fb0a44..63f0ee117399 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -2992,7 +2992,7 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 	ufshcd_send_command(hba, tag, hwq);
 
 out:
-	if (ufs_trigger_eh()) {
+	if (ufs_trigger_eh(hba)) {
 		unsigned long flags;
 
 		spin_lock_irqsave(hba->host->host_lock, flags);
@@ -5649,7 +5649,7 @@ static irqreturn_t ufshcd_transfer_req_compl(struct ufs_hba *hba)
 	    !(hba->quirks & UFSHCI_QUIRK_SKIP_RESET_INTR_AGGR))
 		ufshcd_reset_intr_aggr(hba);
 
-	if (ufs_fail_completion())
+	if (ufs_fail_completion(hba))
 		return IRQ_HANDLED;
 
 	/*
@@ -9348,6 +9348,7 @@ static int ufshcd_hba_init(struct ufs_hba *hba)
 		goto out_disable_vreg;
 
 	ufs_debugfs_hba_init(hba);
+	ufs_fault_inject_hba_init(hba);
 
 	hba->is_powered = true;
 	goto out;
diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h
index 7f0b2c5599cd..d862c8ddce03 100644
--- a/include/ufs/ufshcd.h
+++ b/include/ufs/ufshcd.h
@@ -16,6 +16,7 @@
 #include <linux/blk-crypto-profile.h>
 #include <linux/blk-mq.h>
 #include <linux/devfreq.h>
+#include <linux/fault-inject.h>
 #include <linux/msi.h>
 #include <linux/pm_runtime.h>
 #include <linux/dma-direction.h>
@@ -1057,6 +1058,10 @@ struct ufs_hba {
 	struct dentry *debugfs_root;
 	struct delayed_work debugfs_ee_work;
 	u32 debugfs_ee_rate_limit_ms;
+#endif
+#ifdef CONFIG_SCSI_UFS_FAULT_INJECTION
+	struct fault_attr trigger_eh_attr;
+	struct fault_attr timeout_attr;
 #endif
 	u32 luns_avail;
 	unsigned int nr_hw_queues;
-- 
cgit v1.2.3


From 6371be7aeb986905bb60ec73d002fc02343393b4 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Tue, 21 Nov 2023 07:56:30 +0900
Subject: scsi: Change SCSI device boolean fields to single bit flags

Commit 3cc2ffe5c16d ("scsi: sd: Differentiate system and runtime start/stop
management") changed the single bit manage_start_stop flag into 2 boolean
fields of the SCSI device structure. Commit 24eca2dce0f8 ("scsi: sd:
Introduce manage_shutdown device flag") introduced the manage_shutdown
boolean field for the same structure. Together, these 2 commits increase
the size of struct scsi_device by 8 bytes by using booleans instead of
defining the manage_xxx fields as single bit flags, similarly to other
flags of this structure.

Avoid this unnecessary structure size increase and be consistent with the
definition of other flags by reverting the definitions of the manage_xxx
fields as single bit flags.

Fixes: 3cc2ffe5c16d ("scsi: sd: Differentiate system and runtime start/stop management")
Fixes: 24eca2dce0f8 ("scsi: sd: Introduce manage_shutdown device flag")
Cc: <stable@vger.kernel.org>
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Link: https://lore.kernel.org/r/20231120225631.37938-2-dlemoal@kernel.org
Reviewed-by: Niklas Cassel <niklas.cassel@wdc.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ata/libata-scsi.c  | 4 ++--
 drivers/firewire/sbp2.c    | 6 +++---
 include/scsi/scsi_device.h | 6 +++---
 3 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index c10ff8985203..63317449f6ea 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -1056,8 +1056,8 @@ int ata_scsi_dev_config(struct scsi_device *sdev, struct ata_device *dev)
 		 * and resume and shutdown only. For system level suspend/resume,
 		 * devices power state is handled directly by libata EH.
 		 */
-		sdev->manage_runtime_start_stop = true;
-		sdev->manage_shutdown = true;
+		sdev->manage_runtime_start_stop = 1;
+		sdev->manage_shutdown = 1;
 	}
 
 	/*
diff --git a/drivers/firewire/sbp2.c b/drivers/firewire/sbp2.c
index 7edf2c95282f..e779d866022b 100644
--- a/drivers/firewire/sbp2.c
+++ b/drivers/firewire/sbp2.c
@@ -1519,9 +1519,9 @@ static int sbp2_scsi_slave_configure(struct scsi_device *sdev)
 	sdev->use_10_for_rw = 1;
 
 	if (sbp2_param_exclusive_login) {
-		sdev->manage_system_start_stop = true;
-		sdev->manage_runtime_start_stop = true;
-		sdev->manage_shutdown = true;
+		sdev->manage_system_start_stop = 1;
+		sdev->manage_runtime_start_stop = 1;
+		sdev->manage_shutdown = 1;
 	}
 
 	if (sdev->type == TYPE_ROM)
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 10480eb582b2..1fb460dfca0c 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -167,19 +167,19 @@ struct scsi_device {
 	 * power state for system suspend/resume (suspend to RAM and
 	 * hibernation) operations.
 	 */
-	bool manage_system_start_stop;
+	unsigned manage_system_start_stop:1;
 
 	/*
 	 * If true, let the high-level device driver (sd) manage the device
 	 * power state for runtime device suspand and resume operations.
 	 */
-	bool manage_runtime_start_stop;
+	unsigned manage_runtime_start_stop:1;
 
 	/*
 	 * If true, let the high-level device driver (sd) manage the device
 	 * power state for system shutdown (power off) operations.
 	 */
-	bool manage_shutdown;
+	unsigned manage_shutdown:1;
 
 	unsigned removable:1;
 	unsigned changed:1;	/* Data invalid due to media change */
-- 
cgit v1.2.3


From b09d7f8fd50f6e93cbadd8d27fde178f745b42a1 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Tue, 21 Nov 2023 07:56:31 +0900
Subject: scsi: sd: Fix system start for ATA devices

It is not always possible to keep a device in the runtime suspended state
when a system level suspend/resume cycle is executed. E.g. for ATA devices
connected to AHCI adapters, system resume resets the ATA ports, which
causes connected devices to spin up. In such case, a runtime suspended disk
will incorrectly be seen with a suspended runtime state because the device
is not resumed by sd_resume_system(). The power state seen by the user is
different than the actual device physical power state.

Fix this issue by introducing the struct scsi_device flag
force_runtime_start_on_system_start. When set, this flag causes
sd_resume_system() to request a runtime resume operation for runtime
suspended devices. This results in the user seeing the device runtime_state
as active after a system resume, thus correctly reflecting the device
physical power state.

Fixes: 9131bff6a9f1 ("scsi: core: pm: Only runtime resume if necessary")
Cc: <stable@vger.kernel.org>
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Link: https://lore.kernel.org/r/20231120225631.37938-3-dlemoal@kernel.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ata/libata-scsi.c  | 5 +++++
 drivers/scsi/sd.c          | 9 ++++++++-
 include/scsi/scsi_device.h | 6 ++++++
 3 files changed, 19 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 63317449f6ea..0a0f483124c3 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -1055,9 +1055,14 @@ int ata_scsi_dev_config(struct scsi_device *sdev, struct ata_device *dev)
 		 * Ask the sd driver to issue START STOP UNIT on runtime suspend
 		 * and resume and shutdown only. For system level suspend/resume,
 		 * devices power state is handled directly by libata EH.
+		 * Given that disks are always spun up on system resume, also
+		 * make sure that the sd driver forces runtime suspended disks
+		 * to be resumed to correctly reflect the power state of the
+		 * device.
 		 */
 		sdev->manage_runtime_start_stop = 1;
 		sdev->manage_shutdown = 1;
+		sdev->force_runtime_start_on_system_start = 1;
 	}
 
 	/*
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index fa00dd503cbf..542a4bbb21bc 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -3949,8 +3949,15 @@ static int sd_resume(struct device *dev, bool runtime)
 
 static int sd_resume_system(struct device *dev)
 {
-	if (pm_runtime_suspended(dev))
+	if (pm_runtime_suspended(dev)) {
+		struct scsi_disk *sdkp = dev_get_drvdata(dev);
+		struct scsi_device *sdp = sdkp ? sdkp->device : NULL;
+
+		if (sdp && sdp->force_runtime_start_on_system_start)
+			pm_request_resume(dev);
+
 		return 0;
+	}
 
 	return sd_resume(dev, false);
 }
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 1fb460dfca0c..5ec1e71a09de 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -181,6 +181,12 @@ struct scsi_device {
 	 */
 	unsigned manage_shutdown:1;
 
+	/*
+	 * If set and if the device is runtime suspended, ask the high-level
+	 * device driver (sd) to force a runtime resume of the device.
+	 */
+	unsigned force_runtime_start_on_system_start:1;
+
 	unsigned removable:1;
 	unsigned changed:1;	/* Data invalid due to media change */
 	unsigned busy:1;	/* Used to prevent races */
-- 
cgit v1.2.3


From a066f906ba396ab00d4af19fc5fad42b2605582a Mon Sep 17 00:00:00 2001
From: Kory Maincent <kory.maincent@bootlin.com>
Date: Wed, 22 Nov 2023 14:52:43 +0100
Subject: firmware_loader: Expand Firmware upload error codes with firmware
 invalid error

No error code are available to signal an invalid firmware content.
Drivers that can check the firmware content validity can not return this
specific failure to the user-space

Expand the firmware error code with an additional code:
- "firmware invalid" code which can be used when the provided firmware
  is invalid

Sync lib/test_firmware.c file accordingly.

Acked-by: Luis Chamberlain <mcgrof@kernel.org>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Kory Maincent <kory.maincent@bootlin.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20231122-feature_firmware_error_code-v3-1-04ec753afb71@bootlin.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/base/firmware_loader/sysfs_upload.c | 1 +
 include/linux/firmware.h                    | 2 ++
 lib/test_firmware.c                         | 1 +
 3 files changed, 4 insertions(+)

(limited to 'include')

diff --git a/drivers/base/firmware_loader/sysfs_upload.c b/drivers/base/firmware_loader/sysfs_upload.c
index a0af8f5f13d8..829270067d16 100644
--- a/drivers/base/firmware_loader/sysfs_upload.c
+++ b/drivers/base/firmware_loader/sysfs_upload.c
@@ -27,6 +27,7 @@ static const char * const fw_upload_err_str[] = {
 	[FW_UPLOAD_ERR_INVALID_SIZE] = "invalid-file-size",
 	[FW_UPLOAD_ERR_RW_ERROR]     = "read-write-error",
 	[FW_UPLOAD_ERR_WEAROUT]	     = "flash-wearout",
+	[FW_UPLOAD_ERR_FW_INVALID]   = "firmware-invalid",
 };
 
 static const char *fw_upload_progress(struct device *dev,
diff --git a/include/linux/firmware.h b/include/linux/firmware.h
index de7fea3bca51..0311858b46ce 100644
--- a/include/linux/firmware.h
+++ b/include/linux/firmware.h
@@ -27,6 +27,7 @@ struct firmware {
  * @FW_UPLOAD_ERR_INVALID_SIZE: invalid firmware image size
  * @FW_UPLOAD_ERR_RW_ERROR: read or write to HW failed, see kernel log
  * @FW_UPLOAD_ERR_WEAROUT: FLASH device is approaching wear-out, wait & retry
+ * @FW_UPLOAD_ERR_FW_INVALID: invalid firmware file
  * @FW_UPLOAD_ERR_MAX: Maximum error code marker
  */
 enum fw_upload_err {
@@ -38,6 +39,7 @@ enum fw_upload_err {
 	FW_UPLOAD_ERR_INVALID_SIZE,
 	FW_UPLOAD_ERR_RW_ERROR,
 	FW_UPLOAD_ERR_WEAROUT,
+	FW_UPLOAD_ERR_FW_INVALID,
 	FW_UPLOAD_ERR_MAX
 };
 
diff --git a/lib/test_firmware.c b/lib/test_firmware.c
index add4699fc6cd..9cfdcd6d21db 100644
--- a/lib/test_firmware.c
+++ b/lib/test_firmware.c
@@ -1132,6 +1132,7 @@ static const char * const fw_upload_err_str[] = {
 	[FW_UPLOAD_ERR_INVALID_SIZE] = "invalid-file-size",
 	[FW_UPLOAD_ERR_RW_ERROR]     = "read-write-error",
 	[FW_UPLOAD_ERR_WEAROUT]	     = "flash-wearout",
+	[FW_UPLOAD_ERR_FW_INVALID]   = "firmware-invalid",
 };
 
 static void upload_err_inject_error(struct test_firmware_upload *tst,
-- 
cgit v1.2.3


From b286f4e87e325b76789f30337c98ba72e00532e2 Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Mon, 13 Nov 2023 10:07:52 +0200
Subject: serial: core: Move tty and serdev to be children of serial core port
 device

Let's move tty and serdev controller to be children of the serial core port
device. This way the runtime PM usage count of a child device propagates
to the serial hardware device.

The tty and serdev devices are associated with a specific serial port of
a serial hardware controller device, and we now have serial core hierarchy
of controllers and ports.

The tty device moves happily with just a change of the parent device and
update of device_find_child() handling. The serdev device init needs some
changes to separate the serial hardware controller device from the parent
device.

With this change the tty devices move under sysfs similar to this x86_64
qemu example of a diff of "find /sys -name ttyS*":

 /sys/class/tty/ttyS0
 /sys/class/tty/ttyS3
 /sys/class/tty/ttyS1
-/sys/devices/pnp0/00:04/tty/ttyS0
-/sys/devices/platform/serial8250/tty/ttyS2
-/sys/devices/platform/serial8250/tty/ttyS3
-/sys/devices/platform/serial8250/tty/ttyS1
+/sys/devices/pnp0/00:04/00:04:0/00:04:0.0/tty/ttyS0
+/sys/devices/platform/serial8250/serial8250:0/serial8250:0.3/tty/ttyS3
+/sys/devices/platform/serial8250/serial8250:0/serial8250:0.1/tty/ttyS1
+/sys/devices/platform/serial8250/serial8250:0/serial8250:0.2/tty/ttyS2

If a serdev device is used instead of a tty, it moves in a similar way.

Suggested-by: Johan Hovold <johan@kernel.org>
Cc: Maximilian Luz <luzmaximilian@gmail.com>
Cc: Rob Herring <robh@kernel.org>
Signed-off-by: Tony Lindgren <tony@atomide.com>
Link: https://lore.kernel.org/r/20231113080758.30346-1-tony@atomide.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serdev/core.c           | 15 +++++++++------
 drivers/tty/serdev/serdev-ttyport.c |  3 ++-
 drivers/tty/serial/serial_core.c    |  7 ++++---
 drivers/tty/tty_port.c              | 16 +++++++++-------
 include/linux/serdev.h              |  8 +++++++-
 include/linux/tty_port.h            |  4 ++--
 6 files changed, 33 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/serdev/core.c b/drivers/tty/serdev/core.c
index a5fdaf5e148e..3090e3454c44 100644
--- a/drivers/tty/serdev/core.c
+++ b/drivers/tty/serdev/core.c
@@ -468,6 +468,7 @@ EXPORT_SYMBOL_GPL(serdev_device_alloc);
 
 /**
  * serdev_controller_alloc() - Allocate a new serdev controller
+ * @host:	serial port hardware controller device
  * @parent:	parent device
  * @size:	size of private data
  *
@@ -476,8 +477,9 @@ EXPORT_SYMBOL_GPL(serdev_device_alloc);
  * The allocated private data region may be accessed via
  * serdev_controller_get_drvdata()
  */
-struct serdev_controller *serdev_controller_alloc(struct device *parent,
-					      size_t size)
+struct serdev_controller *serdev_controller_alloc(struct device *host,
+						  struct device *parent,
+						  size_t size)
 {
 	struct serdev_controller *ctrl;
 	int id;
@@ -502,7 +504,8 @@ struct serdev_controller *serdev_controller_alloc(struct device *parent,
 	ctrl->dev.type = &serdev_ctrl_type;
 	ctrl->dev.bus = &serdev_bus_type;
 	ctrl->dev.parent = parent;
-	device_set_node(&ctrl->dev, dev_fwnode(parent));
+	ctrl->host = host;
+	device_set_node(&ctrl->dev, dev_fwnode(host));
 	serdev_controller_set_drvdata(ctrl, &ctrl[1]);
 
 	dev_set_name(&ctrl->dev, "serial%d", id);
@@ -665,7 +668,7 @@ static int acpi_serdev_check_resources(struct serdev_controller *ctrl,
 		acpi_get_parent(adev->handle, &lookup.controller_handle);
 
 	/* Make sure controller and ResourceSource handle match */
-	if (!device_match_acpi_handle(ctrl->dev.parent, lookup.controller_handle))
+	if (!device_match_acpi_handle(ctrl->host, lookup.controller_handle))
 		return -ENODEV;
 
 	return 0;
@@ -730,7 +733,7 @@ static int acpi_serdev_register_devices(struct serdev_controller *ctrl)
 	bool skip;
 	int ret;
 
-	if (!has_acpi_companion(ctrl->dev.parent))
+	if (!has_acpi_companion(ctrl->host))
 		return -ENODEV;
 
 	/*
@@ -739,7 +742,7 @@ static int acpi_serdev_register_devices(struct serdev_controller *ctrl)
 	 * succeed in this case, so that the proper serdev devices can be
 	 * added "manually" later.
 	 */
-	ret = acpi_quirk_skip_serdev_enumeration(ctrl->dev.parent, &skip);
+	ret = acpi_quirk_skip_serdev_enumeration(ctrl->host, &skip);
 	if (ret)
 		return ret;
 	if (skip)
diff --git a/drivers/tty/serdev/serdev-ttyport.c b/drivers/tty/serdev/serdev-ttyport.c
index e3856814ce77..c5381fe15e1c 100644
--- a/drivers/tty/serdev/serdev-ttyport.c
+++ b/drivers/tty/serdev/serdev-ttyport.c
@@ -274,6 +274,7 @@ static const struct serdev_controller_ops ctrl_ops = {
 };
 
 struct device *serdev_tty_port_register(struct tty_port *port,
+					struct device *host,
 					struct device *parent,
 					struct tty_driver *drv, int idx)
 {
@@ -284,7 +285,7 @@ struct device *serdev_tty_port_register(struct tty_port *port,
 	if (!port || !drv || !parent)
 		return ERR_PTR(-ENODEV);
 
-	ctrl = serdev_controller_alloc(parent, sizeof(struct serport));
+	ctrl = serdev_controller_alloc(host, parent, sizeof(struct serport));
 	if (!ctrl)
 		return ERR_PTR(-ENOMEM);
 	serport = serdev_controller_get_drvdata(ctrl);
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index f1348a509552..f36ea953e2c9 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -2342,7 +2342,7 @@ int uart_suspend_port(struct uart_driver *drv, struct uart_port *uport)
 
 	mutex_lock(&port->mutex);
 
-	tty_dev = device_find_child(uport->dev, &match, serial_match_port);
+	tty_dev = device_find_child(&uport->port_dev->dev, &match, serial_match_port);
 	if (tty_dev && device_may_wakeup(tty_dev)) {
 		enable_irq_wake(uport->irq);
 		put_device(tty_dev);
@@ -2423,7 +2423,7 @@ int uart_resume_port(struct uart_driver *drv, struct uart_port *uport)
 
 	mutex_lock(&port->mutex);
 
-	tty_dev = device_find_child(uport->dev, &match, serial_match_port);
+	tty_dev = device_find_child(&uport->port_dev->dev, &match, serial_match_port);
 	if (!uport->suspended && device_may_wakeup(tty_dev)) {
 		if (irqd_is_wakeup_set(irq_get_irq_data((uport->irq))))
 			disable_irq_wake(uport->irq);
@@ -3153,7 +3153,8 @@ static int serial_core_add_one_port(struct uart_driver *drv, struct uart_port *u
 	 * setserial to be used to alter this port's parameters.
 	 */
 	tty_dev = tty_port_register_device_attr_serdev(port, drv->tty_driver,
-			uport->line, uport->dev, port, uport->tty_groups);
+			uport->line, uport->dev, &uport->port_dev->dev, port,
+			uport->tty_groups);
 	if (!IS_ERR(tty_dev)) {
 		device_set_wakeup_capable(tty_dev, 1);
 	} else {
diff --git a/drivers/tty/tty_port.c b/drivers/tty/tty_port.c
index 63c125250961..ef72d2e4b928 100644
--- a/drivers/tty/tty_port.c
+++ b/drivers/tty/tty_port.c
@@ -171,7 +171,8 @@ EXPORT_SYMBOL_GPL(tty_port_register_device_attr);
  * @port: tty_port of the device
  * @driver: tty_driver for this device
  * @index: index of the tty
- * @device: parent if exists, otherwise NULL
+ * @host: serial port hardware device
+ * @parent: parent if exists, otherwise NULL
  * @drvdata: driver data for the device
  * @attr_grp: attribute group for the device
  *
@@ -180,20 +181,20 @@ EXPORT_SYMBOL_GPL(tty_port_register_device_attr);
  */
 struct device *tty_port_register_device_attr_serdev(struct tty_port *port,
 		struct tty_driver *driver, unsigned index,
-		struct device *device, void *drvdata,
+		struct device *host, struct device *parent, void *drvdata,
 		const struct attribute_group **attr_grp)
 {
 	struct device *dev;
 
 	tty_port_link_device(port, driver, index);
 
-	dev = serdev_tty_port_register(port, device, driver, index);
+	dev = serdev_tty_port_register(port, host, parent, driver, index);
 	if (PTR_ERR(dev) != -ENODEV) {
 		/* Skip creating cdev if we registered a serdev device */
 		return dev;
 	}
 
-	return tty_register_device_attr(driver, index, device, drvdata,
+	return tty_register_device_attr(driver, index, parent, drvdata,
 			attr_grp);
 }
 EXPORT_SYMBOL_GPL(tty_port_register_device_attr_serdev);
@@ -203,17 +204,18 @@ EXPORT_SYMBOL_GPL(tty_port_register_device_attr_serdev);
  * @port: tty_port of the device
  * @driver: tty_driver for this device
  * @index: index of the tty
- * @device: parent if exists, otherwise NULL
+ * @host: serial port hardware controller device
+ * @parent: parent if exists, otherwise NULL
  *
  * Register a serdev or tty device depending on if the parent device has any
  * defined serdev clients or not.
  */
 struct device *tty_port_register_device_serdev(struct tty_port *port,
 		struct tty_driver *driver, unsigned index,
-		struct device *device)
+		struct device *host, struct device *parent)
 {
 	return tty_port_register_device_attr_serdev(port, driver, index,
-			device, NULL, NULL);
+			host, parent, NULL, NULL);
 }
 EXPORT_SYMBOL_GPL(tty_port_register_device_serdev);
 
diff --git a/include/linux/serdev.h b/include/linux/serdev.h
index f5f97fa25e8a..0ebf53bb254f 100644
--- a/include/linux/serdev.h
+++ b/include/linux/serdev.h
@@ -99,12 +99,14 @@ struct serdev_controller_ops {
 /**
  * struct serdev_controller - interface to the serdev controller
  * @dev:	Driver model representation of the device.
+ * @host:	Serial port hardware controller device
  * @nr:		number identifier for this controller/bus.
  * @serdev:	Pointer to slave device for this controller.
  * @ops:	Controller operations.
  */
 struct serdev_controller {
 	struct device		dev;
+	struct device		*host;
 	unsigned int		nr;
 	struct serdev_device	*serdev;
 	const struct serdev_controller_ops *ops;
@@ -167,7 +169,9 @@ struct serdev_device *serdev_device_alloc(struct serdev_controller *);
 int serdev_device_add(struct serdev_device *);
 void serdev_device_remove(struct serdev_device *);
 
-struct serdev_controller *serdev_controller_alloc(struct device *, size_t);
+struct serdev_controller *serdev_controller_alloc(struct device *host,
+						  struct device *parent,
+						  size_t size);
 int serdev_controller_add(struct serdev_controller *);
 void serdev_controller_remove(struct serdev_controller *);
 
@@ -311,11 +315,13 @@ struct tty_driver;
 
 #ifdef CONFIG_SERIAL_DEV_CTRL_TTYPORT
 struct device *serdev_tty_port_register(struct tty_port *port,
+					struct device *host,
 					struct device *parent,
 					struct tty_driver *drv, int idx);
 int serdev_tty_port_unregister(struct tty_port *port);
 #else
 static inline struct device *serdev_tty_port_register(struct tty_port *port,
+					   struct device *host,
 					   struct device *parent,
 					   struct tty_driver *drv, int idx)
 {
diff --git a/include/linux/tty_port.h b/include/linux/tty_port.h
index 6b367eb17979..3276311a7f38 100644
--- a/include/linux/tty_port.h
+++ b/include/linux/tty_port.h
@@ -149,10 +149,10 @@ struct device *tty_port_register_device_attr(struct tty_port *port,
 		const struct attribute_group **attr_grp);
 struct device *tty_port_register_device_serdev(struct tty_port *port,
 		struct tty_driver *driver, unsigned index,
-		struct device *device);
+		struct device *host, struct device *parent);
 struct device *tty_port_register_device_attr_serdev(struct tty_port *port,
 		struct tty_driver *driver, unsigned index,
-		struct device *device, void *drvdata,
+		struct device *host, struct device *parent, void *drvdata,
 		const struct attribute_group **attr_grp);
 void tty_port_unregister_device(struct tty_port *port,
 		struct tty_driver *driver, unsigned index);
-- 
cgit v1.2.3


From 358779dd18c1e8531bd6d78c19ed802958d7c677 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Tue, 21 Nov 2023 10:22:44 +0100
Subject: tty: fix tty_operations types in documentation

Commits 95713967ba52 ("tty: make tty_operations::write()'s count
size_t") and dcaafbe6ee3b ("tty: propagate u8 data to
tty_operations::put_char()") changed types of characters to u8, but
omitted to fix the documentation.

Fix the latter now.

Signed-off-by: Jiri Slaby (SUSE) <jirislaby@kernel.org>
Link: https://lore.kernel.org/r/20231121092258.9334-4-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/tty_driver.h | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h
index 18beff0cec1a..f428c1b784a2 100644
--- a/include/linux/tty_driver.h
+++ b/include/linux/tty_driver.h
@@ -72,8 +72,7 @@ struct serial_struct;
  *	is closed for the last time freeing up the resources. This is
  *	actually the second part of shutdown for routines that might sleep.
  *
- * @write: ``ssize_t ()(struct tty_struct *tty, const unsigned char *buf,
- *		    size_t count)``
+ * @write: ``ssize_t ()(struct tty_struct *tty, const u8 *buf, size_t count)``
  *
  *	This routine is called by the kernel to write a series (@count) of
  *	characters (@buf) to the @tty device. The characters may come from
@@ -85,7 +84,7 @@ struct serial_struct;
  *
  *	Optional: Required for writable devices. May not sleep.
  *
- * @put_char: ``int ()(struct tty_struct *tty, unsigned char ch)``
+ * @put_char: ``int ()(struct tty_struct *tty, u8 ch)``
  *
  *	This routine is called by the kernel to write a single character @ch to
  *	the @tty device. If the kernel uses this routine, it must call the
-- 
cgit v1.2.3


From 239123e7e8ec4d35c8591c48f5de44925a88391d Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Tue, 21 Nov 2023 10:22:45 +0100
Subject: tty: move locking docs out of Returns for functions in tty.h
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Both tty_kref_get() and tty_get_baud_rate() note about locking in their
Return kernel-doc clause. Extract this info into a separate "Locking"
paragraph -- the same as we do for other tty functions.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Suggested-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://lore.kernel.org/r/20231121092258.9334-5-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/tty.h | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/tty.h b/include/linux/tty.h
index 4b6340ac2af2..7625fc98fef3 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -393,8 +393,10 @@ extern const struct class tty_class;
  * tty_kref_get - get a tty reference
  * @tty: tty device
  *
- * Returns: a new reference to a tty object. The caller must hold sufficient
- * locks/counts to ensure that their existing reference cannot go away
+ * Returns: a new reference to a tty object
+ *
+ * Locking: The caller must hold sufficient locks/counts to ensure that their
+ * existing reference cannot go away.
  */
 static inline struct tty_struct *tty_kref_get(struct tty_struct *tty)
 {
@@ -436,10 +438,10 @@ void tty_encode_baud_rate(struct tty_struct *tty, speed_t ibaud,
  * tty_get_baud_rate - get tty bit rates
  * @tty: tty to query
  *
- * Returns: the baud rate as an integer for this terminal. The termios lock
- * must be held by the caller and the terminal bit flags may be updated.
+ * Returns: the baud rate as an integer for this terminal
  *
- * Locking: none
+ * Locking: The termios lock must be held by the caller and the terminal bit
+ * flags may be updated.
  */
 static inline speed_t tty_get_baud_rate(struct tty_struct *tty)
 {
-- 
cgit v1.2.3


From da549bdd15c295c24b2ee7ffe7ad0f3877fa8a87 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 7 Nov 2023 02:00:39 -0500
Subject: dentry: switch the lists of children to hlist

Saves a pointer per struct dentry and actually makes the things less
clumsy.  Cleaned the d_walk() and dcache_readdir() a bit by use
of hlist_for_... iterators.

A couple of new helpers - d_first_child() and d_next_sibling(),
to make the expressions less awful.

Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 Documentation/filesystems/porting.rst     |  9 ++++
 arch/powerpc/platforms/cell/spufs/inode.c |  5 +-
 fs/afs/dynroot.c                          |  5 +-
 fs/autofs/expire.c                        |  7 +--
 fs/ceph/dir.c                             |  2 +-
 fs/ceph/mds_client.c                      |  2 +-
 fs/coda/cache.c                           |  2 +-
 fs/dcache.c                               | 76 +++++++++++++++----------------
 fs/libfs.c                                | 45 +++++++++---------
 fs/notify/fsnotify.c                      |  2 +-
 fs/tracefs/inode.c                        | 34 ++++++--------
 include/linux/dcache.h                    | 20 ++++++--
 12 files changed, 108 insertions(+), 101 deletions(-)

(limited to 'include')

diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst
index 878e72b2f8b7..331405f4b29f 100644
--- a/Documentation/filesystems/porting.rst
+++ b/Documentation/filesystems/porting.rst
@@ -1061,3 +1061,12 @@ export_operations ->encode_fh() no longer has a default implementation to
 encode FILEID_INO32_GEN* file handles.
 Filesystems that used the default implementation may use the generic helper
 generic_encode_ino32_fh() explicitly.
+
+---
+
+**mandatory**
+
+The list of children anchored in parent dentry got turned into hlist now.
+Field names got changed (->d_children/->d_sib instead of ->d_subdirs/->d_child
+for anchor/entries resp.), so any affected places will be immediately caught
+by compiler.
diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c
index 10c1320adfd0..030de2b8c145 100644
--- a/arch/powerpc/platforms/cell/spufs/inode.c
+++ b/arch/powerpc/platforms/cell/spufs/inode.c
@@ -145,10 +145,11 @@ spufs_evict_inode(struct inode *inode)
 
 static void spufs_prune_dir(struct dentry *dir)
 {
-	struct dentry *dentry, *tmp;
+	struct dentry *dentry;
+	struct hlist_node *n;
 
 	inode_lock(d_inode(dir));
-	list_for_each_entry_safe(dentry, tmp, &dir->d_subdirs, d_child) {
+	hlist_for_each_entry_safe(dentry, n, &dir->d_children, d_sib) {
 		spin_lock(&dentry->d_lock);
 		if (simple_positive(dentry)) {
 			dget_dlock(dentry);
diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c
index 4d04ef2d3ae7..fe45462834cc 100644
--- a/fs/afs/dynroot.c
+++ b/fs/afs/dynroot.c
@@ -370,7 +370,7 @@ error:
 void afs_dynroot_depopulate(struct super_block *sb)
 {
 	struct afs_net *net = afs_sb2net(sb);
-	struct dentry *root = sb->s_root, *subdir, *tmp;
+	struct dentry *root = sb->s_root, *subdir;
 
 	/* Prevent more subdirs from being created */
 	mutex_lock(&net->proc_cells_lock);
@@ -379,10 +379,11 @@ void afs_dynroot_depopulate(struct super_block *sb)
 	mutex_unlock(&net->proc_cells_lock);
 
 	if (root) {
+		struct hlist_node *n;
 		inode_lock(root->d_inode);
 
 		/* Remove all the pins for dirs created for manually added cells */
-		list_for_each_entry_safe(subdir, tmp, &root->d_subdirs, d_child) {
+		hlist_for_each_entry_safe(subdir, n, &root->d_children, d_sib) {
 			if (subdir->d_fsdata) {
 				subdir->d_fsdata = NULL;
 				dput(subdir);
diff --git a/fs/autofs/expire.c b/fs/autofs/expire.c
index 038b3d2d9f57..39d8c84c16f4 100644
--- a/fs/autofs/expire.c
+++ b/fs/autofs/expire.c
@@ -73,12 +73,9 @@ done:
 /* p->d_lock held */
 static struct dentry *positive_after(struct dentry *p, struct dentry *child)
 {
-	if (child)
-		child = list_next_entry(child, d_child);
-	else
-		child = list_first_entry(&p->d_subdirs, struct dentry, d_child);
+	child = child ? d_next_sibling(child) : d_first_child(p);
 
-	list_for_each_entry_from(child, &p->d_subdirs, d_child) {
+	hlist_for_each_entry_from(child, d_sib) {
 		spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED);
 		if (simple_positive(child)) {
 			dget_dlock(child);
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 91709934c8b1..678596684596 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -174,7 +174,7 @@ __dcache_find_get_entry(struct dentry *parent, u64 idx,
 /*
  * When possible, we try to satisfy a readdir by peeking at the
  * dcache.  We make this work by carefully ordering dentries on
- * d_child when we initially get results back from the MDS, and
+ * d_children when we initially get results back from the MDS, and
  * falling back to a "normal" sync readdir if any dentries in the dir
  * are dropped.
  *
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index d95eb525519a..02ebfabfc8ee 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -2128,7 +2128,7 @@ static bool drop_negative_children(struct dentry *dentry)
 		goto out;
 
 	spin_lock(&dentry->d_lock);
-	list_for_each_entry(child, &dentry->d_subdirs, d_child) {
+	hlist_for_each_entry(child, &dentry->d_children, d_sib) {
 		if (d_really_is_positive(child)) {
 			all_negative = false;
 			break;
diff --git a/fs/coda/cache.c b/fs/coda/cache.c
index d6254cf9f397..970f0022ec52 100644
--- a/fs/coda/cache.c
+++ b/fs/coda/cache.c
@@ -93,7 +93,7 @@ static void coda_flag_children(struct dentry *parent, int flag)
 	struct dentry *de;
 
 	spin_lock(&parent->d_lock);
-	list_for_each_entry(de, &parent->d_subdirs, d_child) {
+	hlist_for_each_entry(de, &parent->d_children, d_sib) {
 		struct inode *inode = d_inode_rcu(de);
 		/* don't know what to do with negative dentries */
 		if (inode)
diff --git a/fs/dcache.c b/fs/dcache.c
index c82ae731df9a..59f76c9a15d1 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -51,8 +51,8 @@
  *   - d_lru
  *   - d_count
  *   - d_unhashed()
- *   - d_parent and d_subdirs
- *   - childrens' d_child and d_parent
+ *   - d_parent and d_chilren
+ *   - childrens' d_sib and d_parent
  *   - d_u.d_alias, d_inode
  *
  * Ordering:
@@ -537,7 +537,7 @@ void d_drop(struct dentry *dentry)
 }
 EXPORT_SYMBOL(d_drop);
 
-static inline void dentry_unlist(struct dentry *dentry, struct dentry *parent)
+static inline void dentry_unlist(struct dentry *dentry)
 {
 	struct dentry *next;
 	/*
@@ -545,12 +545,12 @@ static inline void dentry_unlist(struct dentry *dentry, struct dentry *parent)
 	 * attached to the dentry tree
 	 */
 	dentry->d_flags |= DCACHE_DENTRY_KILLED;
-	if (unlikely(list_empty(&dentry->d_child)))
+	if (unlikely(hlist_unhashed(&dentry->d_sib)))
 		return;
-	__list_del_entry(&dentry->d_child);
+	__hlist_del(&dentry->d_sib);
 	/*
 	 * Cursors can move around the list of children.  While we'd been
-	 * a normal list member, it didn't matter - ->d_child.next would've
+	 * a normal list member, it didn't matter - ->d_sib.next would've
 	 * been updated.  However, from now on it won't be and for the
 	 * things like d_walk() it might end up with a nasty surprise.
 	 * Normally d_walk() doesn't care about cursors moving around -
@@ -558,20 +558,20 @@ static inline void dentry_unlist(struct dentry *dentry, struct dentry *parent)
 	 * of its own, we get through it without ever unlocking the parent.
 	 * There is one exception, though - if we ascend from a child that
 	 * gets killed as soon as we unlock it, the next sibling is found
-	 * using the value left in its ->d_child.next.  And if _that_
+	 * using the value left in its ->d_sib.next.  And if _that_
 	 * pointed to a cursor, and cursor got moved (e.g. by lseek())
 	 * before d_walk() regains parent->d_lock, we'll end up skipping
 	 * everything the cursor had been moved past.
 	 *
-	 * Solution: make sure that the pointer left behind in ->d_child.next
+	 * Solution: make sure that the pointer left behind in ->d_sib.next
 	 * points to something that won't be moving around.  I.e. skip the
 	 * cursors.
 	 */
-	while (dentry->d_child.next != &parent->d_subdirs) {
-		next = list_entry(dentry->d_child.next, struct dentry, d_child);
+	while (dentry->d_sib.next) {
+		next = hlist_entry(dentry->d_sib.next, struct dentry, d_sib);
 		if (likely(!(next->d_flags & DCACHE_DENTRY_CURSOR)))
 			break;
-		dentry->d_child.next = next->d_child.next;
+		dentry->d_sib.next = next->d_sib.next;
 	}
 }
 
@@ -600,7 +600,7 @@ static void __dentry_kill(struct dentry *dentry)
 	}
 	/* if it was on the hash then remove it */
 	__d_drop(dentry);
-	dentry_unlist(dentry, parent);
+	dentry_unlist(dentry);
 	if (parent)
 		spin_unlock(&parent->d_lock);
 	if (dentry->d_inode)
@@ -1348,8 +1348,7 @@ enum d_walk_ret {
 static void d_walk(struct dentry *parent, void *data,
 		   enum d_walk_ret (*enter)(void *, struct dentry *))
 {
-	struct dentry *this_parent;
-	struct list_head *next;
+	struct dentry *this_parent, *dentry;
 	unsigned seq = 0;
 	enum d_walk_ret ret;
 	bool retry = true;
@@ -1371,13 +1370,9 @@ again:
 		break;
 	}
 repeat:
-	next = this_parent->d_subdirs.next;
+	dentry = d_first_child(this_parent);
 resume:
-	while (next != &this_parent->d_subdirs) {
-		struct list_head *tmp = next;
-		struct dentry *dentry = list_entry(tmp, struct dentry, d_child);
-		next = tmp->next;
-
+	hlist_for_each_entry_from(dentry, d_sib) {
 		if (unlikely(dentry->d_flags & DCACHE_DENTRY_CURSOR))
 			continue;
 
@@ -1398,7 +1393,7 @@ resume:
 			continue;
 		}
 
-		if (!list_empty(&dentry->d_subdirs)) {
+		if (!hlist_empty(&dentry->d_children)) {
 			spin_unlock(&this_parent->d_lock);
 			spin_release(&dentry->d_lock.dep_map, _RET_IP_);
 			this_parent = dentry;
@@ -1413,24 +1408,23 @@ resume:
 	rcu_read_lock();
 ascend:
 	if (this_parent != parent) {
-		struct dentry *child = this_parent;
-		this_parent = child->d_parent;
+		dentry = this_parent;
+		this_parent = dentry->d_parent;
 
-		spin_unlock(&child->d_lock);
+		spin_unlock(&dentry->d_lock);
 		spin_lock(&this_parent->d_lock);
 
 		/* might go back up the wrong parent if we have had a rename. */
 		if (need_seqretry(&rename_lock, seq))
 			goto rename_retry;
 		/* go into the first sibling still alive */
-		do {
-			next = child->d_child.next;
-			if (next == &this_parent->d_subdirs)
-				goto ascend;
-			child = list_entry(next, struct dentry, d_child);
-		} while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED));
-		rcu_read_unlock();
-		goto resume;
+		hlist_for_each_entry_continue(dentry, d_sib) {
+			if (likely(!(dentry->d_flags & DCACHE_DENTRY_KILLED))) {
+				rcu_read_unlock();
+				goto resume;
+			}
+		}
+		goto ascend;
 	}
 	if (need_seqretry(&rename_lock, seq))
 		goto rename_retry;
@@ -1530,7 +1524,7 @@ out:
  * Search the dentry child list of the specified parent,
  * and move any unused dentries to the end of the unused
  * list for prune_dcache(). We descend to the next level
- * whenever the d_subdirs list is non-empty and continue
+ * whenever the d_children list is non-empty and continue
  * searching.
  *
  * It returns zero iff there are no unused children,
@@ -1657,7 +1651,7 @@ EXPORT_SYMBOL(shrink_dcache_parent);
 static enum d_walk_ret umount_check(void *_data, struct dentry *dentry)
 {
 	/* it has busy descendents; complain about those instead */
-	if (!list_empty(&dentry->d_subdirs))
+	if (!hlist_empty(&dentry->d_children))
 		return D_WALK_CONTINUE;
 
 	/* root with refcount 1 is fine */
@@ -1814,9 +1808,9 @@ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
 	dentry->d_fsdata = NULL;
 	INIT_HLIST_BL_NODE(&dentry->d_hash);
 	INIT_LIST_HEAD(&dentry->d_lru);
-	INIT_LIST_HEAD(&dentry->d_subdirs);
+	INIT_HLIST_HEAD(&dentry->d_children);
 	INIT_HLIST_NODE(&dentry->d_u.d_alias);
-	INIT_LIST_HEAD(&dentry->d_child);
+	INIT_HLIST_NODE(&dentry->d_sib);
 	d_set_d_op(dentry, dentry->d_sb->s_d_op);
 
 	if (dentry->d_op && dentry->d_op->d_init) {
@@ -1855,7 +1849,7 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name)
 	 */
 	__dget_dlock(parent);
 	dentry->d_parent = parent;
-	list_add(&dentry->d_child, &parent->d_subdirs);
+	hlist_add_head(&dentry->d_sib, &parent->d_children);
 	spin_unlock(&parent->d_lock);
 
 	return dentry;
@@ -2993,11 +2987,15 @@ static void __d_move(struct dentry *dentry, struct dentry *target,
 	} else {
 		target->d_parent = old_parent;
 		swap_names(dentry, target);
-		list_move(&target->d_child, &target->d_parent->d_subdirs);
+		if (!hlist_unhashed(&target->d_sib))
+			__hlist_del(&target->d_sib);
+		hlist_add_head(&target->d_sib, &target->d_parent->d_children);
 		__d_rehash(target);
 		fsnotify_update_flags(target);
 	}
-	list_move(&dentry->d_child, &dentry->d_parent->d_subdirs);
+	if (!hlist_unhashed(&dentry->d_sib))
+		__hlist_del(&dentry->d_sib);
+	hlist_add_head(&dentry->d_sib, &dentry->d_parent->d_children);
 	__d_rehash(dentry);
 	fsnotify_update_flags(dentry);
 	fscrypt_handle_d_move(dentry);
diff --git a/fs/libfs.c b/fs/libfs.c
index e9440d55073c..46c9177769c1 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -104,15 +104,16 @@ EXPORT_SYMBOL(dcache_dir_close);
  * If no such element exists, NULL is returned.
  */
 static struct dentry *scan_positives(struct dentry *cursor,
-					struct list_head *p,
+					struct hlist_node **p,
 					loff_t count,
 					struct dentry *last)
 {
 	struct dentry *dentry = cursor->d_parent, *found = NULL;
 
 	spin_lock(&dentry->d_lock);
-	while ((p = p->next) != &dentry->d_subdirs) {
-		struct dentry *d = list_entry(p, struct dentry, d_child);
+	while (*p) {
+		struct dentry *d = hlist_entry(*p, struct dentry, d_sib);
+		p = &d->d_sib.next;
 		// we must at least skip cursors, to avoid livelocks
 		if (d->d_flags & DCACHE_DENTRY_CURSOR)
 			continue;
@@ -126,8 +127,10 @@ static struct dentry *scan_positives(struct dentry *cursor,
 			count = 1;
 		}
 		if (need_resched()) {
-			list_move(&cursor->d_child, p);
-			p = &cursor->d_child;
+			if (!hlist_unhashed(&cursor->d_sib))
+				__hlist_del(&cursor->d_sib);
+			hlist_add_behind(&cursor->d_sib, &d->d_sib);
+			p = &cursor->d_sib.next;
 			spin_unlock(&dentry->d_lock);
 			cond_resched();
 			spin_lock(&dentry->d_lock);
@@ -159,13 +162,12 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence)
 		inode_lock_shared(dentry->d_inode);
 
 		if (offset > 2)
-			to = scan_positives(cursor, &dentry->d_subdirs,
+			to = scan_positives(cursor, &dentry->d_children.first,
 					    offset - 2, NULL);
 		spin_lock(&dentry->d_lock);
+		hlist_del_init(&cursor->d_sib);
 		if (to)
-			list_move(&cursor->d_child, &to->d_child);
-		else
-			list_del_init(&cursor->d_child);
+			hlist_add_behind(&cursor->d_sib, &to->d_sib);
 		spin_unlock(&dentry->d_lock);
 		dput(to);
 
@@ -187,19 +189,16 @@ int dcache_readdir(struct file *file, struct dir_context *ctx)
 {
 	struct dentry *dentry = file->f_path.dentry;
 	struct dentry *cursor = file->private_data;
-	struct list_head *anchor = &dentry->d_subdirs;
 	struct dentry *next = NULL;
-	struct list_head *p;
+	struct hlist_node **p;
 
 	if (!dir_emit_dots(file, ctx))
 		return 0;
 
 	if (ctx->pos == 2)
-		p = anchor;
-	else if (!list_empty(&cursor->d_child))
-		p = &cursor->d_child;
+		p = &dentry->d_children.first;
 	else
-		return 0;
+		p = &cursor->d_sib.next;
 
 	while ((next = scan_positives(cursor, p, 1, next)) != NULL) {
 		if (!dir_emit(ctx, next->d_name.name, next->d_name.len,
@@ -207,13 +206,12 @@ int dcache_readdir(struct file *file, struct dir_context *ctx)
 			      fs_umode_to_dtype(d_inode(next)->i_mode)))
 			break;
 		ctx->pos++;
-		p = &next->d_child;
+		p = &next->d_sib.next;
 	}
 	spin_lock(&dentry->d_lock);
+	hlist_del_init(&cursor->d_sib);
 	if (next)
-		list_move_tail(&cursor->d_child, &next->d_child);
-	else
-		list_del_init(&cursor->d_child);
+		hlist_add_before(&cursor->d_sib, &next->d_sib);
 	spin_unlock(&dentry->d_lock);
 	dput(next);
 
@@ -492,12 +490,11 @@ const struct file_operations simple_offset_dir_operations = {
 
 static struct dentry *find_next_child(struct dentry *parent, struct dentry *prev)
 {
-	struct dentry *child = NULL;
-	struct list_head *p = prev ? &prev->d_child : &parent->d_subdirs;
+	struct dentry *child = NULL, *d;
 
 	spin_lock(&parent->d_lock);
-	while ((p = p->next) != &parent->d_subdirs) {
-		struct dentry *d = container_of(p, struct dentry, d_child);
+	d = prev ? d_next_sibling(prev) : d_first_child(parent);
+	hlist_for_each_entry_from(d, d_sib) {
 		if (simple_positive(d)) {
 			spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED);
 			if (simple_positive(d))
@@ -658,7 +655,7 @@ int simple_empty(struct dentry *dentry)
 	int ret = 0;
 
 	spin_lock(&dentry->d_lock);
-	list_for_each_entry(child, &dentry->d_subdirs, d_child) {
+	hlist_for_each_entry(child, &dentry->d_children, d_sib) {
 		spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED);
 		if (simple_positive(child)) {
 			spin_unlock(&child->d_lock);
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 7974e91ffe13..8bfd690e9f10 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -124,7 +124,7 @@ void __fsnotify_update_child_dentry_flags(struct inode *inode)
 		 * d_flags to indicate parental interest (their parent is the
 		 * original inode) */
 		spin_lock(&alias->d_lock);
-		list_for_each_entry(child, &alias->d_subdirs, d_child) {
+		hlist_for_each_entry(child, &alias->d_children, d_sib) {
 			if (!child->d_inode)
 				continue;
 
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index 5b54948514fe..61ca5fcf10f9 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -199,26 +199,21 @@ static void change_gid(struct dentry *dentry, kgid_t gid)
  */
 static void set_gid(struct dentry *parent, kgid_t gid)
 {
-	struct dentry *this_parent;
-	struct list_head *next;
+	struct dentry *this_parent, *dentry;
 
 	this_parent = parent;
 	spin_lock(&this_parent->d_lock);
 
 	change_gid(this_parent, gid);
 repeat:
-	next = this_parent->d_subdirs.next;
+	dentry = d_first_child(this_parent);
 resume:
-	while (next != &this_parent->d_subdirs) {
-		struct list_head *tmp = next;
-		struct dentry *dentry = list_entry(tmp, struct dentry, d_child);
-		next = tmp->next;
-
+	hlist_for_each_entry_from(dentry, d_sib) {
 		spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
 
 		change_gid(dentry, gid);
 
-		if (!list_empty(&dentry->d_subdirs)) {
+		if (!hlist_empty(&dentry->d_children)) {
 			spin_unlock(&this_parent->d_lock);
 			spin_release(&dentry->d_lock.dep_map, _RET_IP_);
 			this_parent = dentry;
@@ -233,21 +228,20 @@ resume:
 	rcu_read_lock();
 ascend:
 	if (this_parent != parent) {
-		struct dentry *child = this_parent;
-		this_parent = child->d_parent;
+		dentry = this_parent;
+		this_parent = dentry->d_parent;
 
-		spin_unlock(&child->d_lock);
+		spin_unlock(&dentry->d_lock);
 		spin_lock(&this_parent->d_lock);
 
 		/* go into the first sibling still alive */
-		do {
-			next = child->d_child.next;
-			if (next == &this_parent->d_subdirs)
-				goto ascend;
-			child = list_entry(next, struct dentry, d_child);
-		} while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED));
-		rcu_read_unlock();
-		goto resume;
+		hlist_for_each_entry_continue(dentry, d_sib) {
+			if (likely(!(dentry->d_flags & DCACHE_DENTRY_KILLED))) {
+				rcu_read_unlock();
+				goto resume;
+			}
+		}
+		goto ascend;
 	}
 	rcu_read_unlock();
 	spin_unlock(&this_parent->d_lock);
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 3da2f0545d5d..0e397a0c519c 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -68,12 +68,12 @@ extern const struct qstr dotdot_name;
  * large memory footprint increase).
  */
 #ifdef CONFIG_64BIT
-# define DNAME_INLINE_LEN 32 /* 192 bytes */
+# define DNAME_INLINE_LEN 40 /* 192 bytes */
 #else
 # ifdef CONFIG_SMP
-#  define DNAME_INLINE_LEN 36 /* 128 bytes */
-# else
 #  define DNAME_INLINE_LEN 40 /* 128 bytes */
+# else
+#  define DNAME_INLINE_LEN 44 /* 128 bytes */
 # endif
 #endif
 
@@ -101,8 +101,8 @@ struct dentry {
 		struct list_head d_lru;		/* LRU list */
 		wait_queue_head_t *d_wait;	/* in-lookup ones only */
 	};
-	struct list_head d_child;	/* child of parent list */
-	struct list_head d_subdirs;	/* our children */
+	struct hlist_node d_sib;	/* child of parent list */
+	struct hlist_head d_children;	/* our children */
 	/*
 	 * d_alias and d_rcu can share memory
 	 */
@@ -600,4 +600,14 @@ struct name_snapshot {
 void take_dentry_name_snapshot(struct name_snapshot *, struct dentry *);
 void release_dentry_name_snapshot(struct name_snapshot *);
 
+static inline struct dentry *d_first_child(const struct dentry *dentry)
+{
+	return hlist_entry_safe(dentry->d_children.first, struct dentry, d_sib);
+}
+
+static inline struct dentry *d_next_sibling(const struct dentry *dentry)
+{
+	return hlist_entry_safe(dentry->d_sib.next, struct dentry, d_sib);
+}
+
 #endif	/* __LINUX_DCACHE_H */
-- 
cgit v1.2.3


From f2824db1b49f947ba6e208ddf02edf4b1391480a Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 18 Nov 2023 16:42:43 -0500
Subject: kill d_instantate_anon(), fold __d_instantiate_anon() into remaining
 caller

now that the only user of d_instantiate_anon() is gone...
[braino fix folded - kudos to Dan Carpenter]

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/dcache.c            | 90 ++++++++++++++++++++------------------------------
 include/linux/dcache.h |  1 -
 2 files changed, 35 insertions(+), 56 deletions(-)

(limited to 'include')

diff --git a/fs/dcache.c b/fs/dcache.c
index 9f5b2b5c1e6d..6c520eda131f 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2054,75 +2054,55 @@ struct dentry *d_make_root(struct inode *root_inode)
 }
 EXPORT_SYMBOL(d_make_root);
 
-static struct dentry *__d_instantiate_anon(struct dentry *dentry,
-					   struct inode *inode,
-					   bool disconnected)
-{
-	struct dentry *res;
-	unsigned add_flags;
-
-	security_d_instantiate(dentry, inode);
-	spin_lock(&inode->i_lock);
-	res = __d_find_any_alias(inode);
-	if (res) {
-		spin_unlock(&inode->i_lock);
-		dput(dentry);
-		goto out_iput;
-	}
-
-	/* attach a disconnected dentry */
-	add_flags = d_flags_for_inode(inode);
-
-	if (disconnected)
-		add_flags |= DCACHE_DISCONNECTED;
-
-	spin_lock(&dentry->d_lock);
-	__d_set_inode_and_type(dentry, inode, add_flags);
-	hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry);
-	if (!disconnected) {
-		hlist_bl_lock(&dentry->d_sb->s_roots);
-		hlist_bl_add_head(&dentry->d_hash, &dentry->d_sb->s_roots);
-		hlist_bl_unlock(&dentry->d_sb->s_roots);
-	}
-	spin_unlock(&dentry->d_lock);
-	spin_unlock(&inode->i_lock);
-
-	return dentry;
-
- out_iput:
-	iput(inode);
-	return res;
-}
-
-struct dentry *d_instantiate_anon(struct dentry *dentry, struct inode *inode)
-{
-	return __d_instantiate_anon(dentry, inode, true);
-}
-EXPORT_SYMBOL(d_instantiate_anon);
-
 static struct dentry *__d_obtain_alias(struct inode *inode, bool disconnected)
 {
-	struct dentry *tmp;
-	struct dentry *res;
+	struct super_block *sb;
+	struct dentry *new, *res;
 
 	if (!inode)
 		return ERR_PTR(-ESTALE);
 	if (IS_ERR(inode))
 		return ERR_CAST(inode);
 
-	res = d_find_any_alias(inode);
+	sb = inode->i_sb;
+
+	res = d_find_any_alias(inode); /* existing alias? */
 	if (res)
-		goto out_iput;
+		goto out;
 
-	tmp = d_alloc_anon(inode->i_sb);
-	if (!tmp) {
+	new = d_alloc_anon(sb);
+	if (!new) {
 		res = ERR_PTR(-ENOMEM);
-		goto out_iput;
+		goto out;
 	}
 
-	return __d_instantiate_anon(tmp, inode, disconnected);
+	security_d_instantiate(new, inode);
+	spin_lock(&inode->i_lock);
+	res = __d_find_any_alias(inode); /* recheck under lock */
+	if (likely(!res)) { /* still no alias, attach a disconnected dentry */
+		unsigned add_flags = d_flags_for_inode(inode);
+
+		if (disconnected)
+			add_flags |= DCACHE_DISCONNECTED;
+
+		spin_lock(&new->d_lock);
+		__d_set_inode_and_type(new, inode, add_flags);
+		hlist_add_head(&new->d_u.d_alias, &inode->i_dentry);
+		if (!disconnected) {
+			hlist_bl_lock(&sb->s_roots);
+			hlist_bl_add_head(&new->d_hash, &sb->s_roots);
+			hlist_bl_unlock(&sb->s_roots);
+		}
+		spin_unlock(&new->d_lock);
+		spin_unlock(&inode->i_lock);
+		inode = NULL; /* consumed by new->d_inode */
+		res = new;
+	} else {
+		spin_unlock(&inode->i_lock);
+		dput(new);
+	}
 
-out_iput:
+ out:
 	iput(inode);
 	return res;
 }
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index fa0414cff85c..8c5e3bdf1147 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -218,7 +218,6 @@ extern seqlock_t rename_lock;
  */
 extern void d_instantiate(struct dentry *, struct inode *);
 extern void d_instantiate_new(struct dentry *, struct inode *);
-extern struct dentry * d_instantiate_anon(struct dentry *, struct inode *);
 extern void __d_drop(struct dentry *dentry);
 extern void d_drop(struct dentry *dentry);
 extern void d_delete(struct dentry *);
-- 
cgit v1.2.3


From 8a54b38f3e5ced6cc4b246b8e54bd0f50deceaa8 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 11 Nov 2023 16:01:27 -0500
Subject: d_genocide(): move the extern into fs/internal.h

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/internal.h          | 1 +
 include/linux/dcache.h | 3 ---
 2 files changed, 1 insertion(+), 3 deletions(-)

(limited to 'include')

diff --git a/fs/internal.h b/fs/internal.h
index 9e9fc629f935..d9a920e2636e 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -219,6 +219,7 @@ extern void shrink_dcache_for_umount(struct super_block *);
 extern struct dentry *__d_lookup(const struct dentry *, const struct qstr *);
 extern struct dentry *__d_lookup_rcu(const struct dentry *parent,
 				const struct qstr *name, unsigned *seq);
+extern void d_genocide(struct dentry *);
 
 /*
  * pipe.c
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 8c5e3bdf1147..b4324d47f249 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -243,9 +243,6 @@ extern void d_invalidate(struct dentry *);
 /* only used at mount-time */
 extern struct dentry * d_make_root(struct inode *);
 
-/* <clickety>-<click> the ramfs-type tree */
-extern void d_genocide(struct dentry *);
-
 extern void d_mark_tmpfile(struct file *, struct inode *);
 extern void d_tmpfile(struct file *, struct inode *);
 
-- 
cgit v1.2.3


From 57851607326a2beef21e67f83f4f53a90df8445a Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 12 Nov 2023 21:38:48 -0500
Subject: get rid of DCACHE_GENOCIDE

... now that we never call d_genocide() other than from kill_litter_super()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/dcache.c            | 5 +----
 include/linux/dcache.h | 1 -
 2 files changed, 1 insertion(+), 5 deletions(-)

(limited to 'include')

diff --git a/fs/dcache.c b/fs/dcache.c
index 5947556b6e90..8473c8f0ce22 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -3198,10 +3198,7 @@ static enum d_walk_ret d_genocide_kill(void *data, struct dentry *dentry)
 		if (d_unhashed(dentry) || !dentry->d_inode)
 			return D_WALK_SKIP;
 
-		if (!(dentry->d_flags & DCACHE_GENOCIDE)) {
-			dentry->d_flags |= DCACHE_GENOCIDE;
-			dentry->d_lockref.count--;
-		}
+		dentry->d_lockref.count--;
 	}
 	return D_WALK_CONTINUE;
 }
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index b4324d47f249..981f529c6cb5 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -173,7 +173,6 @@ struct dentry_operations {
 #define DCACHE_DONTCACHE		BIT(7) /* Purge from memory on final dput() */
 
 #define DCACHE_CANT_MOUNT		BIT(8)
-#define DCACHE_GENOCIDE			BIT(9)
 #define DCACHE_SHRINK_LIST		BIT(10)
 
 #define DCACHE_OP_WEAK_REVALIDATE	BIT(11)
-- 
cgit v1.2.3


From 1b327b5ac57cf83e3d015de45d0142852f475375 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 10 Nov 2023 14:07:43 -0500
Subject: kill DCACHE_MAY_FREE

With the new ordering in __dentry_kill() it has become redundant -
it's set if and only if both DCACHE_DENTRY_KILLED and DCACHE_SHRINK_LIST
are set.

We set it in __dentry_kill(), after having set DCACHE_DENTRY_KILLED
with the only condition being that DCACHE_SHRINK_LIST is there;
all of that is done without dropping ->d_lock and the only place
that checks that flag (shrink_dentry_list()) does so under ->d_lock,
after having found the victim on its shrink list.  Since DCACHE_SHRINK_LIST
is set only when placing dentry into shrink list and removed only by
shrink_dentry_list() itself, a check for DCACHE_DENTRY_KILLED in
there would be equivalent to check for DCACHE_MAY_FREE.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/dcache.c            | 6 ++----
 include/linux/dcache.h | 1 -
 2 files changed, 2 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/fs/dcache.c b/fs/dcache.c
index 475ef1edba03..523cbf0780f0 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -614,10 +614,8 @@ static struct dentry *__dentry_kill(struct dentry *dentry)
 	}
 	spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
 	dentry_unlist(dentry);
-	if (dentry->d_flags & DCACHE_SHRINK_LIST) {
-		dentry->d_flags |= DCACHE_MAY_FREE;
+	if (dentry->d_flags & DCACHE_SHRINK_LIST)
 		can_free = false;
-	}
 	spin_unlock(&dentry->d_lock);
 	if (likely(can_free))
 		dentry_free(dentry);
@@ -1072,7 +1070,7 @@ void shrink_dentry_list(struct list_head *list)
 			bool can_free;
 			rcu_read_unlock();
 			d_shrink_del(dentry);
-			can_free = dentry->d_flags & DCACHE_MAY_FREE;
+			can_free = dentry->d_flags & DCACHE_DENTRY_KILLED;
 			spin_unlock(&dentry->d_lock);
 			if (can_free)
 				dentry_free(dentry);
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index b4449a1a47ff..48b393545ec2 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -202,7 +202,6 @@ struct dentry_operations {
 #define DCACHE_SPECIAL_TYPE		(5 << 20) /* Other file type */
 #define DCACHE_SYMLINK_TYPE		(6 << 20) /* Symlink */
 
-#define DCACHE_MAY_FREE			BIT(23)
 #define DCACHE_NOKEY_NAME		BIT(25) /* Encrypted name encoded without key */
 #define DCACHE_OP_REAL			BIT(26)
 
-- 
cgit v1.2.3


From 1b6ae9f6e6c3e3c35aad0f11b116a81780b8aa03 Mon Sep 17 00:00:00 2001
From: Vegard Nossum <vegard.nossum@oracle.com>
Date: Mon, 6 Nov 2023 14:44:17 +0100
Subject: dcache: remove unnecessary NULL check in dget_dlock()

dget_dlock() requires dentry->d_lock to be held when called, yet
contains a NULL check for dentry.

An audit of all calls to dget_dlock() shows that it is never called
with a NULL pointer (as spin_lock()/spin_unlock() would crash in these
cases):

  $ git grep -W '\<dget_dlock\>'

  arch/powerpc/platforms/cell/spufs/inode.c-              spin_lock(&dentry->d_lock);
  arch/powerpc/platforms/cell/spufs/inode.c-              if (simple_positive(dentry)) {
  arch/powerpc/platforms/cell/spufs/inode.c:                      dget_dlock(dentry);

  fs/autofs/expire.c-             spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED);
  fs/autofs/expire.c-             if (simple_positive(child)) {
  fs/autofs/expire.c:                     dget_dlock(child);

  fs/autofs/root.c:                       dget_dlock(active);
  fs/autofs/root.c-                       spin_unlock(&active->d_lock);

  fs/autofs/root.c:                       dget_dlock(expiring);
  fs/autofs/root.c-                       spin_unlock(&expiring->d_lock);

  fs/ceph/dir.c-          if (!spin_trylock(&dentry->d_lock))
  fs/ceph/dir.c-                  continue;
  [...]
  fs/ceph/dir.c:                          dget_dlock(dentry);

  fs/ceph/mds_client.c-           spin_lock(&alias->d_lock);
  [...]
  fs/ceph/mds_client.c:                   dn = dget_dlock(alias);

  fs/configfs/inode.c-            spin_lock(&dentry->d_lock);
  fs/configfs/inode.c-            if (simple_positive(dentry)) {
  fs/configfs/inode.c:                    dget_dlock(dentry);

  fs/libfs.c:                             found = dget_dlock(d);
  fs/libfs.c-                     spin_unlock(&d->d_lock);

  fs/libfs.c:             found = dget_dlock(child);
  fs/libfs.c-     spin_unlock(&child->d_lock);

  fs/libfs.c:                             child = dget_dlock(d);
  fs/libfs.c-                     spin_unlock(&d->d_lock);

  fs/ocfs2/dcache.c:                      dget_dlock(dentry);
  fs/ocfs2/dcache.c-                      spin_unlock(&dentry->d_lock);

  include/linux/dcache.h:static inline struct dentry *dget_dlock(struct dentry *dentry)

After taking out the NULL check, dget_dlock() becomes almost identical
to __dget_dlock(); the only difference is that dget_dlock() returns the
dentry that was passed in. These are static inline helpers, so we can
rely on the compiler to discard unused return values. We can therefore
also remove __dget_dlock() and replace calls to it by dget_dlock().

Also fix up and improve the kerneldoc comments while we're at it.

Al Viro pointed out that we can also clean up some of the callers to
make use of the returned value and provided a bit more info for the
kerneldoc.

While preparing v2 I also noticed that the tabs used in the kerneldoc
comments were causing the kerneldoc to get parsed incorrectly so I also
fixed this up (including for d_unhashed, which is otherwise unrelated).

Testing: x86 defconfig build + boot; make htmldocs for the kerneldoc
warning. objdump shows there are code generation changes.

Link: https://lore.kernel.org/all/20231022164520.915013-1-vegard.nossum@oracle.com/
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: linux-fsdevel@vger.kernel.org
Cc: Nick Piggin <npiggin@kernel.dk>
Cc: Waiman Long <Waiman.Long@hp.com>
Cc: linux-doc@vger.kernel.org
Signed-off-by: Vegard Nossum <vegard.nossum@oracle.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/dcache.c            | 16 ++++------------
 include/linux/dcache.h | 41 ++++++++++++++++++++++++++++++-----------
 2 files changed, 34 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/fs/dcache.c b/fs/dcache.c
index 523cbf0780f0..bb18ea91d717 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -877,12 +877,6 @@ void dput_to_list(struct dentry *dentry, struct list_head *list)
 	spin_unlock(&dentry->d_lock);
 }
 
-/* This must be called with d_lock held */
-static inline void __dget_dlock(struct dentry *dentry)
-{
-	dentry->d_lockref.count++;
-}
-
 struct dentry *dget_parent(struct dentry *dentry)
 {
 	int gotref;
@@ -964,7 +958,7 @@ static struct dentry *__d_find_alias(struct inode *inode)
 	hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
 		spin_lock(&alias->d_lock);
  		if (!d_unhashed(alias)) {
-			__dget_dlock(alias);
+			dget_dlock(alias);
 			spin_unlock(&alias->d_lock);
 			return alias;
 		}
@@ -1569,8 +1563,7 @@ static enum d_walk_ret find_submount(void *_data, struct dentry *dentry)
 {
 	struct dentry **victim = _data;
 	if (d_mountpoint(dentry)) {
-		__dget_dlock(dentry);
-		*victim = dentry;
+		*victim = dget_dlock(dentry);
 		return D_WALK_QUIT;
 	}
 	return D_WALK_CONTINUE;
@@ -1715,8 +1708,7 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name)
 	 * don't need child lock because it is not subject
 	 * to concurrency here
 	 */
-	__dget_dlock(parent);
-	dentry->d_parent = parent;
+	dentry->d_parent = dget_dlock(parent);
 	hlist_add_head(&dentry->d_sib, &parent->d_children);
 	spin_unlock(&parent->d_lock);
 
@@ -2683,7 +2675,7 @@ struct dentry *d_exact_alias(struct dentry *entry, struct inode *inode)
 			spin_unlock(&alias->d_lock);
 			alias = NULL;
 		} else {
-			__dget_dlock(alias);
+			dget_dlock(alias);
 			__d_rehash(alias);
 			spin_unlock(&alias->d_lock);
 		}
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 48b393545ec2..1666c387861f 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -287,20 +287,40 @@ extern char *dentry_path(const struct dentry *, char *, int);
 /* Allocation counts.. */
 
 /**
- *	dget, dget_dlock -	get a reference to a dentry
- *	@dentry: dentry to get a reference to
+ * dget_dlock -	get a reference to a dentry
+ * @dentry: dentry to get a reference to
  *
- *	Given a dentry or %NULL pointer increment the reference count
- *	if appropriate and return the dentry. A dentry will not be 
- *	destroyed when it has references.
+ * Given a live dentry, increment the reference count and return the dentry.
+ * Caller must hold @dentry->d_lock.  Making sure that dentry is alive is
+ * caller's resonsibility.  There are many conditions sufficient to guarantee
+ * that; e.g. anything with non-negative refcount is alive, so's anything
+ * hashed, anything positive, anyone's parent, etc.
  */
 static inline struct dentry *dget_dlock(struct dentry *dentry)
 {
-	if (dentry)
-		dentry->d_lockref.count++;
+	dentry->d_lockref.count++;
 	return dentry;
 }
 
+
+/**
+ * dget - get a reference to a dentry
+ * @dentry: dentry to get a reference to
+ *
+ * Given a dentry or %NULL pointer increment the reference count
+ * if appropriate and return the dentry.  A dentry will not be
+ * destroyed when it has references.  Conversely, a dentry with
+ * no references can disappear for any number of reasons, starting
+ * with memory pressure.  In other words, that primitive is
+ * used to clone an existing reference; using it on something with
+ * zero refcount is a bug.
+ *
+ * NOTE: it will spin if @dentry->d_lock is held.  From the deadlock
+ * avoidance point of view it is equivalent to spin_lock()/increment
+ * refcount/spin_unlock(), so calling it under @dentry->d_lock is
+ * always a bug; so's calling it under ->d_lock on any of its descendents.
+ *
+ */
 static inline struct dentry *dget(struct dentry *dentry)
 {
 	if (dentry)
@@ -311,12 +331,11 @@ static inline struct dentry *dget(struct dentry *dentry)
 extern struct dentry *dget_parent(struct dentry *dentry);
 
 /**
- *	d_unhashed -	is dentry hashed
- *	@dentry: entry to check
+ * d_unhashed - is dentry hashed
+ * @dentry: entry to check
  *
- *	Returns true if the dentry passed is not currently hashed.
+ * Returns true if the dentry passed is not currently hashed.
  */
- 
 static inline int d_unhashed(const struct dentry *dentry)
 {
 	return hlist_bl_unhashed(&dentry->d_hash);
-- 
cgit v1.2.3


From 18caaedaf4c3712ab6821f292598a8f86e6d7972 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sun, 26 Nov 2023 09:56:29 +0100
Subject: locking/lockdep: Slightly reorder 'struct lock_class' to save some
 memory

Based on pahole, 2 holes can be combined in the 'struct lock_class'. This
saves 8 bytes in the structure on my x86_64.

On a x86_64 configured with allmodconfig, this saves ~64kb of memory in
'kernel/locking/lockdep.o':

                text         data           bss           dec     filename
  Before:    102,501    1,912,490    11,531,636    13,546,627     kernel/locking/lockdep.o
  After:     102,181    1,912,490    11,466,100    13,480,771     kernel/locking/lockdep.o

because of:

  struct lock_class lock_classes[MAX_LOCKDEP_KEYS];

After the reorder, pahole gives:

  struct lock_class {
          struct hlist_node          hash_entry;           /*     0    16 */
          struct list_head           lock_entry;           /*    16    16 */
          struct list_head           locks_after;          /*    32    16 */
          struct list_head           locks_before;         /*    48    16 */
          /* --- cacheline 1 boundary (64 bytes) --- */
          const struct lockdep_subclass_key  * key;        /*    64     8 */
          lock_cmp_fn                cmp_fn;               /*    72     8 */
          lock_print_fn              print_fn;             /*    80     8 */
          unsigned int               subclass;             /*    88     4 */
          unsigned int               dep_gen_id;           /*    92     4 */
          long unsigned int          usage_mask;           /*    96     8 */
          const struct lock_trace  * usage_traces[10];     /*   104    80 */
          /* --- cacheline 2 boundary (128 bytes) was 56 bytes ago --- */
          const char  *              name;                 /*   184     8 */
          /* --- cacheline 3 boundary (192 bytes) --- */
          int                        name_version;         /*   192     4 */
          u8                         wait_type_inner;      /*   196     1 */
          u8                         wait_type_outer;      /*   197     1 */
          u8                         lock_type;            /*   198     1 */

          /* XXX 1 byte hole, try to pack */

          long unsigned int          contention_point[4];  /*   200    32 */
          long unsigned int          contending_point[4];  /*   232    32 */

          /* size: 264, cachelines: 5, members: 18 */
          /* sum members: 263, holes: 1, sum holes: 1 */
          /* last cacheline: 8 bytes */
  };

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Waiman Long <longman@redhat.com>
Link: https://lore.kernel.org/r/801258371fc4101f96495a5aaecef638d6cbd8d3.1700988869.git.christophe.jaillet@wanadoo.fr
---
 include/linux/lockdep_types.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h
index 2ebc323d345a..857d785e89e6 100644
--- a/include/linux/lockdep_types.h
+++ b/include/linux/lockdep_types.h
@@ -127,12 +127,12 @@ struct lock_class {
 	unsigned long			usage_mask;
 	const struct lock_trace		*usage_traces[LOCK_TRACE_STATES];
 
+	const char			*name;
 	/*
 	 * Generation counter, when doing certain classes of graph walking,
 	 * to ensure that we check one node only once:
 	 */
 	int				name_version;
-	const char			*name;
 
 	u8				wait_type_inner;
 	u8				wait_type_outer;
-- 
cgit v1.2.3


From a2e7e59a94269484a83386972ca07c22fd188854 Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Wed, 15 Nov 2023 18:25:44 +0000
Subject: iommu: Avoid more races around device probe
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It turns out there are more subtle races beyond just the main part of
__iommu_probe_device() itself running in parallel - the dev_iommu_free()
on the way out of an unsuccessful probe can still manage to trip up
concurrent accesses to a device's fwspec. Thus, extend the scope of
iommu_probe_device_lock() to also serialise fwspec creation and initial
retrieval.

Reported-by: Zhenhua Huang <quic_zhenhuah@quicinc.com>
Link: https://lore.kernel.org/linux-iommu/e2e20e1c-6450-4ac5-9804-b0000acdf7de@quicinc.com/
Fixes: 01657bc14a39 ("iommu: Avoid races around device probe")
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: André Draszik <andre.draszik@linaro.org>
Tested-by: André Draszik <andre.draszik@linaro.org>
Link: https://lore.kernel.org/r/16f433658661d7cadfea51e7c65da95826112a2b.1700071477.git.robin.murphy@arm.com
Cc: stable@vger.kernel.org
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/acpi/scan.c      |  7 ++++++-
 drivers/iommu/iommu.c    | 20 ++++++++++----------
 drivers/iommu/of_iommu.c | 12 +++++++++---
 include/linux/iommu.h    |  1 +
 4 files changed, 26 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index fa5dd71a80fa..02bb2cce423f 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1568,17 +1568,22 @@ static const struct iommu_ops *acpi_iommu_configure_id(struct device *dev,
 	int err;
 	const struct iommu_ops *ops;
 
+	/* Serialise to make dev->iommu stable under our potential fwspec */
+	mutex_lock(&iommu_probe_device_lock);
 	/*
 	 * If we already translated the fwspec there is nothing left to do,
 	 * return the iommu_ops.
 	 */
 	ops = acpi_iommu_fwspec_ops(dev);
-	if (ops)
+	if (ops) {
+		mutex_unlock(&iommu_probe_device_lock);
 		return ops;
+	}
 
 	err = iort_iommu_configure_id(dev, id_in);
 	if (err && err != -EPROBE_DEFER)
 		err = viot_iommu_configure(dev);
+	mutex_unlock(&iommu_probe_device_lock);
 
 	/*
 	 * If we have reason to believe the IOMMU driver missed the initial
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index c9a05bb49bfa..33e2a9b5d339 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -485,11 +485,12 @@ static void iommu_deinit_device(struct device *dev)
 	dev_iommu_free(dev);
 }
 
+DEFINE_MUTEX(iommu_probe_device_lock);
+
 static int __iommu_probe_device(struct device *dev, struct list_head *group_list)
 {
 	const struct iommu_ops *ops = dev->bus->iommu_ops;
 	struct iommu_group *group;
-	static DEFINE_MUTEX(iommu_probe_device_lock);
 	struct group_device *gdev;
 	int ret;
 
@@ -502,17 +503,15 @@ static int __iommu_probe_device(struct device *dev, struct list_head *group_list
 	 * probably be able to use device_lock() here to minimise the scope,
 	 * but for now enforcing a simple global ordering is fine.
 	 */
-	mutex_lock(&iommu_probe_device_lock);
+	lockdep_assert_held(&iommu_probe_device_lock);
 
 	/* Device is probed already if in a group */
-	if (dev->iommu_group) {
-		ret = 0;
-		goto out_unlock;
-	}
+	if (dev->iommu_group)
+		return 0;
 
 	ret = iommu_init_device(dev, ops);
 	if (ret)
-		goto out_unlock;
+		return ret;
 
 	group = dev->iommu_group;
 	gdev = iommu_group_alloc_device(group, dev);
@@ -548,7 +547,6 @@ static int __iommu_probe_device(struct device *dev, struct list_head *group_list
 			list_add_tail(&group->entry, group_list);
 	}
 	mutex_unlock(&group->mutex);
-	mutex_unlock(&iommu_probe_device_lock);
 
 	if (dev_is_pci(dev))
 		iommu_dma_set_pci_32bit_workaround(dev);
@@ -562,8 +560,6 @@ err_put_group:
 	iommu_deinit_device(dev);
 	mutex_unlock(&group->mutex);
 	iommu_group_put(group);
-out_unlock:
-	mutex_unlock(&iommu_probe_device_lock);
 
 	return ret;
 }
@@ -573,7 +569,9 @@ int iommu_probe_device(struct device *dev)
 	const struct iommu_ops *ops;
 	int ret;
 
+	mutex_lock(&iommu_probe_device_lock);
 	ret = __iommu_probe_device(dev, NULL);
+	mutex_unlock(&iommu_probe_device_lock);
 	if (ret)
 		return ret;
 
@@ -1822,7 +1820,9 @@ static int probe_iommu_group(struct device *dev, void *data)
 	struct list_head *group_list = data;
 	int ret;
 
+	mutex_lock(&iommu_probe_device_lock);
 	ret = __iommu_probe_device(dev, group_list);
+	mutex_unlock(&iommu_probe_device_lock);
 	if (ret == -ENODEV)
 		ret = 0;
 
diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c
index 157b286e36bf..c25b4ae6aeee 100644
--- a/drivers/iommu/of_iommu.c
+++ b/drivers/iommu/of_iommu.c
@@ -112,16 +112,20 @@ const struct iommu_ops *of_iommu_configure(struct device *dev,
 					   const u32 *id)
 {
 	const struct iommu_ops *ops = NULL;
-	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	struct iommu_fwspec *fwspec;
 	int err = NO_IOMMU;
 
 	if (!master_np)
 		return NULL;
 
+	/* Serialise to make dev->iommu stable under our potential fwspec */
+	mutex_lock(&iommu_probe_device_lock);
+	fwspec = dev_iommu_fwspec_get(dev);
 	if (fwspec) {
-		if (fwspec->ops)
+		if (fwspec->ops) {
+			mutex_unlock(&iommu_probe_device_lock);
 			return fwspec->ops;
-
+		}
 		/* In the deferred case, start again from scratch */
 		iommu_fwspec_free(dev);
 	}
@@ -155,6 +159,8 @@ const struct iommu_ops *of_iommu_configure(struct device *dev,
 		fwspec = dev_iommu_fwspec_get(dev);
 		ops    = fwspec->ops;
 	}
+	mutex_unlock(&iommu_probe_device_lock);
+
 	/*
 	 * If we have reason to believe the IOMMU driver missed the initial
 	 * probe for dev, replay it to get things in order.
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index ec289c1016f5..6291aa7b079b 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -845,6 +845,7 @@ static inline void dev_iommu_priv_set(struct device *dev, void *priv)
 	dev->iommu->priv = priv;
 }
 
+extern struct mutex iommu_probe_device_lock;
 int iommu_probe_device(struct device *dev);
 
 int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features f);
-- 
cgit v1.2.3


From a9c362db39207c4934c9125e56ed730c5297c37c Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Tue, 21 Nov 2023 18:03:59 +0000
Subject: iommu: Validate that devices match domains

Before we can allow drivers to coexist, we need to make sure that one
driver's domain ops can't misinterpret another driver's dev_iommu_priv
data. To that end, add a token to the domain so we can remember how it
was allocated - for now this may as well be the device ops, since they
still correlate 1:1 with drivers. We can trust ourselves for internal
default domain attachment, so add checks to cover all the public attach
interfaces.

Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Jerry Snitselaar <jsnitsel@redhat.com>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/097c6f30480e4efe12195d00ba0e84ea4837fb4c.1700589539.git.robin.murphy@arm.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/iommu.c                | 10 ++++++++++
 drivers/iommu/iommufd/hw_pagetable.c |  2 ++
 include/linux/iommu.h                |  2 +-
 3 files changed, 13 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 7fafd073c33e..8e4436c606d3 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -2117,6 +2117,7 @@ static struct iommu_domain *__iommu_domain_alloc(const struct iommu_ops *ops,
 		return NULL;
 
 	domain->type = type;
+	domain->owner = ops;
 	/*
 	 * If not already set, assume all sizes by default; the driver
 	 * may override this later
@@ -2282,10 +2283,16 @@ struct iommu_domain *iommu_get_dma_domain(struct device *dev)
 static int __iommu_attach_group(struct iommu_domain *domain,
 				struct iommu_group *group)
 {
+	struct device *dev;
+
 	if (group->domain && group->domain != group->default_domain &&
 	    group->domain != group->blocking_domain)
 		return -EBUSY;
 
+	dev = iommu_group_first_dev(group);
+	if (!dev_has_iommu(dev) || dev_iommu_ops(dev) != domain->owner)
+		return -EINVAL;
+
 	return __iommu_group_set_domain(group, domain);
 }
 
@@ -3477,6 +3484,9 @@ int iommu_attach_device_pasid(struct iommu_domain *domain,
 	if (!group)
 		return -ENODEV;
 
+	if (!dev_has_iommu(dev) || dev_iommu_ops(dev) != domain->owner)
+		return -EINVAL;
+
 	mutex_lock(&group->mutex);
 	curr = xa_cmpxchg(&group->pasid_array, pasid, NULL, domain, GFP_KERNEL);
 	if (curr) {
diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c
index 2abbeafdbd22..5be7f513b622 100644
--- a/drivers/iommu/iommufd/hw_pagetable.c
+++ b/drivers/iommu/iommufd/hw_pagetable.c
@@ -135,6 +135,7 @@ iommufd_hwpt_paging_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas,
 			hwpt->domain = NULL;
 			goto out_abort;
 		}
+		hwpt->domain->owner = ops;
 	} else {
 		hwpt->domain = iommu_domain_alloc(idev->dev->bus);
 		if (!hwpt->domain) {
@@ -233,6 +234,7 @@ iommufd_hwpt_nested_alloc(struct iommufd_ctx *ictx,
 		hwpt->domain = NULL;
 		goto out_abort;
 	}
+	hwpt->domain->owner = ops;
 
 	if (WARN_ON_ONCE(hwpt->domain->type != IOMMU_DOMAIN_NESTED)) {
 		rc = -EINVAL;
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index ec289c1016f5..077bf8cae2f7 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -106,7 +106,7 @@ struct iommu_domain {
 	unsigned type;
 	const struct iommu_domain_ops *ops;
 	const struct iommu_dirty_ops *dirty_ops;
-
+	const struct iommu_ops *owner; /* Whose domain_alloc we came from */
 	unsigned long pgsize_bitmap;	/* Bitmap of page sizes in use */
 	struct iommu_domain_geometry geometry;
 	struct iommu_dma_cookie *iova_cookie;
-- 
cgit v1.2.3


From 17de3f5fdd35676b0e3d41c7c9bf4e3032eb3673 Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Tue, 21 Nov 2023 18:04:02 +0000
Subject: iommu: Retire bus ops

With the rest of the API internals converted, it's time to finally
tackle probe_device and how we bootstrap the per-device ops association
to begin with. This ends up being disappointingly straightforward, since
fwspec users are already doing it in order to find their of_xlate
callback, and it works out that we can easily do the equivalent for
other drivers too. Then shuffle the remaining awareness of iommu_ops
into the couple of core headers that still need it, and breathe a sigh
of relief.

Ding dong the bus ops are gone!

CC: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Christoph Hellwig <hch@lst.de>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Jerry Snitselaar <jsnitsel@redhat.com>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/a59011ef65b4b6657cb0b7a388d786b779b61305.1700589539.git.robin.murphy@arm.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/iommu.c       | 31 ++++++++++++++++++-------------
 include/acpi/acpi_bus.h     |  2 ++
 include/linux/device.h      |  1 -
 include/linux/device/bus.h  |  5 -----
 include/linux/dma-map-ops.h |  1 +
 5 files changed, 21 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 88aeae0acd9b..254f42b4220b 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -148,7 +148,7 @@ struct iommu_group_attribute iommu_group_attr_##_name =		\
 static LIST_HEAD(iommu_device_list);
 static DEFINE_SPINLOCK(iommu_device_lock);
 
-static struct bus_type * const iommu_buses[] = {
+static const struct bus_type * const iommu_buses[] = {
 	&platform_bus_type,
 #ifdef CONFIG_PCI
 	&pci_bus_type,
@@ -257,13 +257,6 @@ int iommu_device_register(struct iommu_device *iommu,
 	/* We need to be able to take module references appropriately */
 	if (WARN_ON(is_module_address((unsigned long)ops) && !ops->owner))
 		return -EINVAL;
-	/*
-	 * Temporarily enforce global restriction to a single driver. This was
-	 * already the de-facto behaviour, since any possible combination of
-	 * existing drivers would compete for at least the PCI or platform bus.
-	 */
-	if (iommu_buses[0]->iommu_ops && iommu_buses[0]->iommu_ops != ops)
-		return -EBUSY;
 
 	iommu->ops = ops;
 	if (hwdev)
@@ -273,10 +266,8 @@ int iommu_device_register(struct iommu_device *iommu,
 	list_add_tail(&iommu->list, &iommu_device_list);
 	spin_unlock(&iommu_device_lock);
 
-	for (int i = 0; i < ARRAY_SIZE(iommu_buses) && !err; i++) {
-		iommu_buses[i]->iommu_ops = ops;
+	for (int i = 0; i < ARRAY_SIZE(iommu_buses) && !err; i++)
 		err = bus_iommu_probe(iommu_buses[i]);
-	}
 	if (err)
 		iommu_device_unregister(iommu);
 	return err;
@@ -329,7 +320,6 @@ int iommu_device_register_bus(struct iommu_device *iommu,
 	list_add_tail(&iommu->list, &iommu_device_list);
 	spin_unlock(&iommu_device_lock);
 
-	bus->iommu_ops = ops;
 	err = bus_iommu_probe(bus);
 	if (err) {
 		iommu_device_unregister_bus(iommu, bus, nb);
@@ -496,12 +486,27 @@ static void iommu_deinit_device(struct device *dev)
 
 static int __iommu_probe_device(struct device *dev, struct list_head *group_list)
 {
-	const struct iommu_ops *ops = dev->bus->iommu_ops;
+	const struct iommu_ops *ops;
+	struct iommu_fwspec *fwspec;
 	struct iommu_group *group;
 	static DEFINE_MUTEX(iommu_probe_device_lock);
 	struct group_device *gdev;
 	int ret;
 
+	/*
+	 * For FDT-based systems and ACPI IORT/VIOT, drivers register IOMMU
+	 * instances with non-NULL fwnodes, and client devices should have been
+	 * identified with a fwspec by this point. Otherwise, we can currently
+	 * assume that only one of Intel, AMD, s390, PAMU or legacy SMMUv2 can
+	 * be present, and that any of their registered instances has suitable
+	 * ops for probing, and thus cheekily co-opt the same mechanism.
+	 */
+	fwspec = dev_iommu_fwspec_get(dev);
+	if (fwspec && fwspec->ops)
+		ops = fwspec->ops;
+	else
+		ops = iommu_ops_from_fwnode(NULL);
+
 	if (!ops)
 		return -ENODEV;
 	/*
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 1216d72c650f..89079787905d 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -627,6 +627,8 @@ struct acpi_pci_root {
 
 /* helper */
 
+struct iommu_ops;
+
 bool acpi_dma_supported(const struct acpi_device *adev);
 enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev);
 int acpi_iommu_fwspec_init(struct device *dev, u32 id,
diff --git a/include/linux/device.h b/include/linux/device.h
index d7a72a8749ea..0314dbbdb534 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -42,7 +42,6 @@ struct class;
 struct subsys_private;
 struct device_node;
 struct fwnode_handle;
-struct iommu_ops;
 struct iommu_group;
 struct dev_pin_info;
 struct dev_iommu;
diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h
index ae10c4322754..e25aab08f873 100644
--- a/include/linux/device/bus.h
+++ b/include/linux/device/bus.h
@@ -62,9 +62,6 @@ struct fwnode_handle;
  *			this bus.
  * @pm:		Power management operations of this bus, callback the specific
  *		device driver's pm-ops.
- * @iommu_ops:  IOMMU specific operations for this bus, used to attach IOMMU
- *              driver implementations to a bus and allow the driver to do
- *              bus-specific setup
  * @need_parent_lock:	When probing or removing a device on this bus, the
  *			device core should lock the device's parent.
  *
@@ -104,8 +101,6 @@ struct bus_type {
 
 	const struct dev_pm_ops *pm;
 
-	const struct iommu_ops *iommu_ops;
-
 	bool need_parent_lock;
 };
 
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index f2fc203fb8a1..a52e508d1869 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -11,6 +11,7 @@
 #include <linux/slab.h>
 
 struct cma;
+struct iommu_ops;
 
 /*
  * Values for struct dma_map_ops.flags:
-- 
cgit v1.2.3


From 17b226dcf80ce79d02f4f0b08813d8848885b986 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@collabora.com>
Date: Fri, 24 Nov 2023 15:24:33 +0100
Subject: iommu: Allow passing custom allocators to pgtable drivers

This will be useful for GPU drivers who want to keep page tables in a
pool so they can:

- keep freed page tables in a free pool and speed-up upcoming page
  table allocations
- batch page table allocation instead of allocating one page at a time
- pre-reserve pages for page tables needed for map/unmap operations,
  to ensure map/unmap operations don't try to allocate memory in paths
  they're allowed to block or fail

It might also be valuable for other aspects of GPU and similar
use-cases, like fine-grained memory accounting and resource limiting.

We will extend the Arm LPAE format to support custom allocators in a
separate commit.

Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Steven Price <steven.price@arm.com>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/20231124142434.1577550-2-boris.brezillon@collabora.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/io-pgtable.c | 23 +++++++++++++++++++++++
 include/linux/io-pgtable.h | 34 ++++++++++++++++++++++++++++++++++
 2 files changed, 57 insertions(+)

(limited to 'include')

diff --git a/drivers/iommu/io-pgtable.c b/drivers/iommu/io-pgtable.c
index b843fcd365d2..8841c1487f00 100644
--- a/drivers/iommu/io-pgtable.c
+++ b/drivers/iommu/io-pgtable.c
@@ -34,6 +34,26 @@ io_pgtable_init_table[IO_PGTABLE_NUM_FMTS] = {
 #endif
 };
 
+static int check_custom_allocator(enum io_pgtable_fmt fmt,
+				  struct io_pgtable_cfg *cfg)
+{
+	/* No custom allocator, no need to check the format. */
+	if (!cfg->alloc && !cfg->free)
+		return 0;
+
+	/* When passing a custom allocator, both the alloc and free
+	 * functions should be provided.
+	 */
+	if (!cfg->alloc || !cfg->free)
+		return -EINVAL;
+
+	/* Make sure the format supports custom allocators. */
+	if (io_pgtable_init_table[fmt]->caps & IO_PGTABLE_CAP_CUSTOM_ALLOCATOR)
+		return 0;
+
+	return -EINVAL;
+}
+
 struct io_pgtable_ops *alloc_io_pgtable_ops(enum io_pgtable_fmt fmt,
 					    struct io_pgtable_cfg *cfg,
 					    void *cookie)
@@ -44,6 +64,9 @@ struct io_pgtable_ops *alloc_io_pgtable_ops(enum io_pgtable_fmt fmt,
 	if (fmt >= IO_PGTABLE_NUM_FMTS)
 		return NULL;
 
+	if (check_custom_allocator(fmt, cfg))
+		return NULL;
+
 	fns = io_pgtable_init_table[fmt];
 	if (!fns)
 		return NULL;
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 25142a0e2fc2..86cf1f7ae389 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -100,6 +100,30 @@ struct io_pgtable_cfg {
 	const struct iommu_flush_ops	*tlb;
 	struct device			*iommu_dev;
 
+	/**
+	 * @alloc: Custom page allocator.
+	 *
+	 * Optional hook used to allocate page tables. If this function is NULL,
+	 * @free must be NULL too.
+	 *
+	 * Memory returned should be zeroed and suitable for dma_map_single() and
+	 * virt_to_phys().
+	 *
+	 * Not all formats support custom page allocators. Before considering
+	 * passing a non-NULL value, make sure the chosen page format supports
+	 * this feature.
+	 */
+	void *(*alloc)(void *cookie, size_t size, gfp_t gfp);
+
+	/**
+	 * @free: Custom page de-allocator.
+	 *
+	 * Optional hook used to free page tables allocated with the @alloc
+	 * hook. Must be non-NULL if @alloc is not NULL, must be NULL
+	 * otherwise.
+	 */
+	void (*free)(void *cookie, void *pages, size_t size);
+
 	/* Low-level data specific to the table format */
 	union {
 		struct {
@@ -241,16 +265,26 @@ io_pgtable_tlb_add_page(struct io_pgtable *iop,
 		iop->cfg.tlb->tlb_add_page(gather, iova, granule, iop->cookie);
 }
 
+/**
+ * enum io_pgtable_caps - IO page table backend capabilities.
+ */
+enum io_pgtable_caps {
+	/** @IO_PGTABLE_CAP_CUSTOM_ALLOCATOR: Backend accepts custom page table allocators. */
+	IO_PGTABLE_CAP_CUSTOM_ALLOCATOR = BIT(0),
+};
+
 /**
  * struct io_pgtable_init_fns - Alloc/free a set of page tables for a
  *                              particular format.
  *
  * @alloc: Allocate a set of page tables described by cfg.
  * @free:  Free the page tables associated with iop.
+ * @caps:  Combination of @io_pgtable_caps flags encoding the backend capabilities.
  */
 struct io_pgtable_init_fns {
 	struct io_pgtable *(*alloc)(struct io_pgtable_cfg *cfg, void *cookie);
 	void (*free)(struct io_pgtable *iop);
+	u32 caps;
 };
 
 extern struct io_pgtable_init_fns io_pgtable_arm_32_lpae_s1_init_fns;
-- 
cgit v1.2.3


From 8c88a474357ead632b07c70bf7f119ace8c3b39e Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 24 Nov 2023 17:25:26 +0100
Subject: debugfs: add API to allow debugfs operations cancellation

In some cases there might be longer-running hardware accesses
in debugfs files, or attempts to acquire locks, and we want
to still be able to quickly remove the files.

Introduce a cancellations API to use inside the debugfs handler
functions to be able to cancel such operations on a per-file
basis.

Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 fs/debugfs/file.c       | 82 +++++++++++++++++++++++++++++++++++++++++++++++++
 fs/debugfs/inode.c      | 32 ++++++++++++++++++-
 fs/debugfs/internal.h   |  5 +++
 include/linux/debugfs.h | 19 ++++++++++++
 4 files changed, 137 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index 3eff92450fd5..5568cdea3490 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -114,6 +114,8 @@ int debugfs_file_get(struct dentry *dentry)
 		lockdep_init_map(&fsd->lockdep_map, fsd->lock_name ?: "debugfs",
 				 &fsd->key, 0);
 #endif
+		INIT_LIST_HEAD(&fsd->cancellations);
+		mutex_init(&fsd->cancellations_mtx);
 	}
 
 	/*
@@ -156,6 +158,86 @@ void debugfs_file_put(struct dentry *dentry)
 }
 EXPORT_SYMBOL_GPL(debugfs_file_put);
 
+/**
+ * debugfs_enter_cancellation - enter a debugfs cancellation
+ * @file: the file being accessed
+ * @cancellation: the cancellation object, the cancel callback
+ *	inside of it must be initialized
+ *
+ * When a debugfs file is removed it needs to wait for all active
+ * operations to complete. However, the operation itself may need
+ * to wait for hardware or completion of some asynchronous process
+ * or similar. As such, it may need to be cancelled to avoid long
+ * waits or even deadlocks.
+ *
+ * This function can be used inside a debugfs handler that may
+ * need to be cancelled. As soon as this function is called, the
+ * cancellation's 'cancel' callback may be called, at which point
+ * the caller should proceed to call debugfs_leave_cancellation()
+ * and leave the debugfs handler function as soon as possible.
+ * Note that the 'cancel' callback is only ever called in the
+ * context of some kind of debugfs_remove().
+ *
+ * This function must be paired with debugfs_leave_cancellation().
+ */
+void debugfs_enter_cancellation(struct file *file,
+				struct debugfs_cancellation *cancellation)
+{
+	struct debugfs_fsdata *fsd;
+	struct dentry *dentry = F_DENTRY(file);
+
+	INIT_LIST_HEAD(&cancellation->list);
+
+	if (WARN_ON(!d_is_reg(dentry)))
+		return;
+
+	if (WARN_ON(!cancellation->cancel))
+		return;
+
+	fsd = READ_ONCE(dentry->d_fsdata);
+	if (WARN_ON(!fsd ||
+		    ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)))
+		return;
+
+	mutex_lock(&fsd->cancellations_mtx);
+	list_add(&cancellation->list, &fsd->cancellations);
+	mutex_unlock(&fsd->cancellations_mtx);
+
+	/* if we're already removing wake it up to cancel */
+	if (d_unlinked(dentry))
+		complete(&fsd->active_users_drained);
+}
+EXPORT_SYMBOL_GPL(debugfs_enter_cancellation);
+
+/**
+ * debugfs_leave_cancellation - leave cancellation section
+ * @file: the file being accessed
+ * @cancellation: the cancellation previously registered with
+ *	debugfs_enter_cancellation()
+ *
+ * See the documentation of debugfs_enter_cancellation().
+ */
+void debugfs_leave_cancellation(struct file *file,
+				struct debugfs_cancellation *cancellation)
+{
+	struct debugfs_fsdata *fsd;
+	struct dentry *dentry = F_DENTRY(file);
+
+	if (WARN_ON(!d_is_reg(dentry)))
+		return;
+
+	fsd = READ_ONCE(dentry->d_fsdata);
+	if (WARN_ON(!fsd ||
+		    ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)))
+		return;
+
+	mutex_lock(&fsd->cancellations_mtx);
+	if (!list_empty(&cancellation->list))
+		list_del(&cancellation->list);
+	mutex_unlock(&fsd->cancellations_mtx);
+}
+EXPORT_SYMBOL_GPL(debugfs_leave_cancellation);
+
 /*
  * Only permit access to world-readable files when the kernel is locked down.
  * We also need to exclude any file that has ways to write or alter it as root
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 80f4f000dcc1..d53c2860b03c 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -247,6 +247,8 @@ static void debugfs_release_dentry(struct dentry *dentry)
 		lockdep_unregister_key(&fsd->key);
 		kfree(fsd->lock_name);
 #endif
+		WARN_ON(!list_empty(&fsd->cancellations));
+		mutex_destroy(&fsd->cancellations_mtx);
 	}
 
 	kfree(fsd);
@@ -756,8 +758,36 @@ static void __debugfs_file_removed(struct dentry *dentry)
 	lock_map_acquire(&fsd->lockdep_map);
 	lock_map_release(&fsd->lockdep_map);
 
-	if (!refcount_dec_and_test(&fsd->active_users))
+	/* if we hit zero, just wait for all to finish */
+	if (!refcount_dec_and_test(&fsd->active_users)) {
 		wait_for_completion(&fsd->active_users_drained);
+		return;
+	}
+
+	/* if we didn't hit zero, try to cancel any we can */
+	while (refcount_read(&fsd->active_users)) {
+		struct debugfs_cancellation *c;
+
+		/*
+		 * Lock the cancellations. Note that the cancellations
+		 * structs are meant to be on the stack, so we need to
+		 * ensure we either use them here or don't touch them,
+		 * and debugfs_leave_cancellation() will wait for this
+		 * to be finished processing before exiting one. It may
+		 * of course win and remove the cancellation, but then
+		 * chances are we never even got into this bit, we only
+		 * do if the refcount isn't zero already.
+		 */
+		mutex_lock(&fsd->cancellations_mtx);
+		while ((c = list_first_entry_or_null(&fsd->cancellations,
+						     typeof(*c), list))) {
+			list_del_init(&c->list);
+			c->cancel(dentry, c->cancel_data);
+		}
+		mutex_unlock(&fsd->cancellations_mtx);
+
+		wait_for_completion(&fsd->active_users_drained);
+	}
 }
 
 static void remove_one(struct dentry *victim)
diff --git a/fs/debugfs/internal.h b/fs/debugfs/internal.h
index c7d61cfc97d2..0c4c68cf161f 100644
--- a/fs/debugfs/internal.h
+++ b/fs/debugfs/internal.h
@@ -8,6 +8,7 @@
 #ifndef _DEBUGFS_INTERNAL_H_
 #define _DEBUGFS_INTERNAL_H_
 #include <linux/lockdep.h>
+#include <linux/list.h>
 
 struct file_operations;
 
@@ -29,6 +30,10 @@ struct debugfs_fsdata {
 			struct lock_class_key key;
 			char *lock_name;
 #endif
+
+			/* protect cancellations */
+			struct mutex cancellations_mtx;
+			struct list_head cancellations;
 		};
 	};
 };
diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h
index ea2d919fd9c7..c9c65b132c0f 100644
--- a/include/linux/debugfs.h
+++ b/include/linux/debugfs.h
@@ -171,6 +171,25 @@ ssize_t debugfs_write_file_bool(struct file *file, const char __user *user_buf,
 ssize_t debugfs_read_file_str(struct file *file, char __user *user_buf,
 			      size_t count, loff_t *ppos);
 
+/**
+ * struct debugfs_cancellation - cancellation data
+ * @list: internal, for keeping track
+ * @cancel: callback to call
+ * @cancel_data: extra data for the callback to call
+ */
+struct debugfs_cancellation {
+	struct list_head list;
+	void (*cancel)(struct dentry *, void *);
+	void *cancel_data;
+};
+
+void __acquires(cancellation)
+debugfs_enter_cancellation(struct file *file,
+			   struct debugfs_cancellation *cancellation);
+void __releases(cancellation)
+debugfs_leave_cancellation(struct file *file,
+			   struct debugfs_cancellation *cancellation);
+
 #else
 
 #include <linux/err.h>
-- 
cgit v1.2.3


From b590b9ae1efc30e52f81d95cdb2519a4c248b965 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 24 Nov 2023 17:25:27 +0100
Subject: wifi: cfg80211: add locked debugfs wrappers

Add wrappers for debugfs files that should be called with
the wiphy mutex held, while the file is also to be removed
under the wiphy mutex. This could otherwise deadlock when
a file is trying to acquire the wiphy mutex while the code
removing it holds the mutex but waits for the removal.

This actually works by pushing the execution of the read
or write handler to a wiphy work that can be cancelled
using the debugfs cancellation API.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h |  46 ++++++++++++++
 net/wireless/debugfs.c | 160 +++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 206 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index b137a33a1b68..4ecfb06c413d 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -9299,4 +9299,50 @@ bool cfg80211_valid_disable_subchannel_bitmap(u16 *bitmap,
  */
 void cfg80211_links_removed(struct net_device *dev, u16 link_mask);
 
+#ifdef CONFIG_CFG80211_DEBUGFS
+/**
+ * wiphy_locked_debugfs_read - do a locked read in debugfs
+ * @wiphy: the wiphy to use
+ * @file: the file being read
+ * @buf: the buffer to fill and then read from
+ * @bufsize: size of the buffer
+ * @userbuf: the user buffer to copy to
+ * @count: read count
+ * @ppos: read position
+ * @handler: the read handler to call (under wiphy lock)
+ * @data: additional data to pass to the read handler
+ */
+ssize_t wiphy_locked_debugfs_read(struct wiphy *wiphy, struct file *file,
+				  char *buf, size_t bufsize,
+				  char __user *userbuf, size_t count,
+				  loff_t *ppos,
+				  ssize_t (*handler)(struct wiphy *wiphy,
+						     struct file *file,
+						     char *buf,
+						     size_t bufsize,
+						     void *data),
+				  void *data);
+
+/**
+ * wiphy_locked_debugfs_write - do a locked write in debugfs
+ * @wiphy: the wiphy to use
+ * @file: the file being written to
+ * @buf: the buffer to copy the user data to
+ * @bufsize: size of the buffer
+ * @userbuf: the user buffer to copy from
+ * @count: read count
+ * @handler: the write handler to call (under wiphy lock)
+ * @data: additional data to pass to the write handler
+ */
+ssize_t wiphy_locked_debugfs_write(struct wiphy *wiphy, struct file *file,
+				   char *buf, size_t bufsize,
+				   const char __user *userbuf, size_t count,
+				   ssize_t (*handler)(struct wiphy *wiphy,
+						      struct file *file,
+						      char *buf,
+						      size_t count,
+						      void *data),
+				   void *data);
+#endif
+
 #endif /* __NET_CFG80211_H */
diff --git a/net/wireless/debugfs.c b/net/wireless/debugfs.c
index 0878b162890a..40e49074e2ee 100644
--- a/net/wireless/debugfs.c
+++ b/net/wireless/debugfs.c
@@ -4,6 +4,7 @@
  *
  * Copyright 2009	Luis R. Rodriguez <lrodriguez@atheros.com>
  * Copyright 2007	Johannes Berg <johannes@sipsolutions.net>
+ * Copyright (C) 2023 Intel Corporation
  */
 
 #include <linux/slab.h>
@@ -109,3 +110,162 @@ void cfg80211_debugfs_rdev_add(struct cfg80211_registered_device *rdev)
 	DEBUGFS_ADD(long_retry_limit);
 	DEBUGFS_ADD(ht40allow_map);
 }
+
+struct debugfs_read_work {
+	struct wiphy_work work;
+	ssize_t (*handler)(struct wiphy *wiphy,
+			   struct file *file,
+			   char *buf,
+			   size_t count,
+			   void *data);
+	struct wiphy *wiphy;
+	struct file *file;
+	char *buf;
+	size_t bufsize;
+	void *data;
+	ssize_t ret;
+	struct completion completion;
+};
+
+static void wiphy_locked_debugfs_read_work(struct wiphy *wiphy,
+					   struct wiphy_work *work)
+{
+	struct debugfs_read_work *w = container_of(work, typeof(*w), work);
+
+	w->ret = w->handler(w->wiphy, w->file, w->buf, w->bufsize, w->data);
+	complete(&w->completion);
+}
+
+static void wiphy_locked_debugfs_read_cancel(struct dentry *dentry,
+					     void *data)
+{
+	struct debugfs_read_work *w = data;
+
+	wiphy_work_cancel(w->wiphy, &w->work);
+	complete(&w->completion);
+}
+
+ssize_t wiphy_locked_debugfs_read(struct wiphy *wiphy, struct file *file,
+				  char *buf, size_t bufsize,
+				  char __user *userbuf, size_t count,
+				  loff_t *ppos,
+				  ssize_t (*handler)(struct wiphy *wiphy,
+						     struct file *file,
+						     char *buf,
+						     size_t bufsize,
+						     void *data),
+				  void *data)
+{
+	struct debugfs_read_work work = {
+		.handler = handler,
+		.wiphy = wiphy,
+		.file = file,
+		.buf = buf,
+		.bufsize = bufsize,
+		.data = data,
+		.ret = -ENODEV,
+		.completion = COMPLETION_INITIALIZER_ONSTACK(work.completion),
+	};
+	struct debugfs_cancellation cancellation = {
+		.cancel = wiphy_locked_debugfs_read_cancel,
+		.cancel_data = &work,
+	};
+
+	/* don't leak stack data or whatever */
+	memset(buf, 0, bufsize);
+
+	wiphy_work_init(&work.work, wiphy_locked_debugfs_read_work);
+	wiphy_work_queue(wiphy, &work.work);
+
+	debugfs_enter_cancellation(file, &cancellation);
+	wait_for_completion(&work.completion);
+	debugfs_leave_cancellation(file, &cancellation);
+
+	if (work.ret < 0)
+		return work.ret;
+
+	if (WARN_ON(work.ret > bufsize))
+		return -EINVAL;
+
+	return simple_read_from_buffer(userbuf, count, ppos, buf, work.ret);
+}
+EXPORT_SYMBOL_GPL(wiphy_locked_debugfs_read);
+
+struct debugfs_write_work {
+	struct wiphy_work work;
+	ssize_t (*handler)(struct wiphy *wiphy,
+			   struct file *file,
+			   char *buf,
+			   size_t count,
+			   void *data);
+	struct wiphy *wiphy;
+	struct file *file;
+	char *buf;
+	size_t count;
+	void *data;
+	ssize_t ret;
+	struct completion completion;
+};
+
+static void wiphy_locked_debugfs_write_work(struct wiphy *wiphy,
+					    struct wiphy_work *work)
+{
+	struct debugfs_write_work *w = container_of(work, typeof(*w), work);
+
+	w->ret = w->handler(w->wiphy, w->file, w->buf, w->count, w->data);
+	complete(&w->completion);
+}
+
+static void wiphy_locked_debugfs_write_cancel(struct dentry *dentry,
+					      void *data)
+{
+	struct debugfs_write_work *w = data;
+
+	wiphy_work_cancel(w->wiphy, &w->work);
+	complete(&w->completion);
+}
+
+ssize_t wiphy_locked_debugfs_write(struct wiphy *wiphy,
+				   struct file *file, char *buf, size_t bufsize,
+				   const char __user *userbuf, size_t count,
+				   ssize_t (*handler)(struct wiphy *wiphy,
+						      struct file *file,
+						      char *buf,
+						      size_t count,
+						      void *data),
+				   void *data)
+{
+	struct debugfs_write_work work = {
+		.handler = handler,
+		.wiphy = wiphy,
+		.file = file,
+		.buf = buf,
+		.count = count,
+		.data = data,
+		.ret = -ENODEV,
+		.completion = COMPLETION_INITIALIZER_ONSTACK(work.completion),
+	};
+	struct debugfs_cancellation cancellation = {
+		.cancel = wiphy_locked_debugfs_write_cancel,
+		.cancel_data = &work,
+	};
+
+	/* mostly used for strings so enforce NUL-termination for safety */
+	if (count >= bufsize)
+		return -EINVAL;
+
+	memset(buf, 0, bufsize);
+
+	if (copy_from_user(buf, userbuf, count))
+		return -EFAULT;
+
+	wiphy_work_init(&work.work, wiphy_locked_debugfs_write_work);
+	wiphy_work_queue(wiphy, &work.work);
+
+	debugfs_enter_cancellation(file, &cancellation);
+	wait_for_completion(&work.completion);
+	debugfs_leave_cancellation(file, &cancellation);
+
+	return work.ret;
+}
+EXPORT_SYMBOL_GPL(wiphy_locked_debugfs_write);
-- 
cgit v1.2.3


From e1df5202e879bce09845ac62bae30206e1edfb80 Mon Sep 17 00:00:00 2001
From: Shradha Gupta <shradhagupta@linux.microsoft.com>
Date: Fri, 24 Nov 2023 05:02:30 -0800
Subject: net :mana :Add remaining GDMA stats for MANA to ethtool

Extend performance counter stats in 'ethtool -S <interface>'
for MANA VF to include all GDMA stat counter.

Tested-on: Ubuntu22
Testcases:
1. LISA testcase:
PERF-NETWORK-TCP-THROUGHPUT-MULTICONNECTION-NTTTCP-Synthetic
2. LISA testcase:
PERF-NETWORK-TCP-THROUGHPUT-MULTICONNECTION-NTTTCP-SRIOV

Signed-off-by: Shradha Gupta <shradhagupta@linux.microsoft.com>
Link: https://lore.kernel.org/r/1700830950-803-1-git-send-email-shradhagupta@linux.microsoft.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/microsoft/mana/mana_en.c      | 49 +++++++++++++++++++++-
 drivers/net/ethernet/microsoft/mana/mana_ethtool.c | 40 ++++++++++++++++++
 include/net/mana/mana.h                            | 46 ++++++++++++++------
 3 files changed, 120 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index fc3d2903a80f..6b857188b9da 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -2385,13 +2385,33 @@ void mana_query_gf_stats(struct mana_port_context *apc)
 
 	mana_gd_init_req_hdr(&req.hdr, MANA_QUERY_GF_STAT,
 			     sizeof(req), sizeof(resp));
-	req.req_stats = STATISTICS_FLAGS_HC_TX_BYTES |
+	req.req_stats = STATISTICS_FLAGS_RX_DISCARDS_NO_WQE |
+			STATISTICS_FLAGS_RX_ERRORS_VPORT_DISABLED |
+			STATISTICS_FLAGS_HC_RX_BYTES |
+			STATISTICS_FLAGS_HC_RX_UCAST_PACKETS |
+			STATISTICS_FLAGS_HC_RX_UCAST_BYTES |
+			STATISTICS_FLAGS_HC_RX_MCAST_PACKETS |
+			STATISTICS_FLAGS_HC_RX_MCAST_BYTES |
+			STATISTICS_FLAGS_HC_RX_BCAST_PACKETS |
+			STATISTICS_FLAGS_HC_RX_BCAST_BYTES |
+			STATISTICS_FLAGS_TX_ERRORS_GF_DISABLED |
+			STATISTICS_FLAGS_TX_ERRORS_VPORT_DISABLED |
+			STATISTICS_FLAGS_TX_ERRORS_INVAL_VPORT_OFFSET_PACKETS |
+			STATISTICS_FLAGS_TX_ERRORS_VLAN_ENFORCEMENT |
+			STATISTICS_FLAGS_TX_ERRORS_ETH_TYPE_ENFORCEMENT |
+			STATISTICS_FLAGS_TX_ERRORS_SA_ENFORCEMENT |
+			STATISTICS_FLAGS_TX_ERRORS_SQPDID_ENFORCEMENT |
+			STATISTICS_FLAGS_TX_ERRORS_CQPDID_ENFORCEMENT |
+			STATISTICS_FLAGS_TX_ERRORS_MTU_VIOLATION |
+			STATISTICS_FLAGS_TX_ERRORS_INVALID_OOB |
+			STATISTICS_FLAGS_HC_TX_BYTES |
 			STATISTICS_FLAGS_HC_TX_UCAST_PACKETS |
 			STATISTICS_FLAGS_HC_TX_UCAST_BYTES |
 			STATISTICS_FLAGS_HC_TX_MCAST_PACKETS |
 			STATISTICS_FLAGS_HC_TX_MCAST_BYTES |
 			STATISTICS_FLAGS_HC_TX_BCAST_PACKETS |
-			STATISTICS_FLAGS_HC_TX_BCAST_BYTES;
+			STATISTICS_FLAGS_HC_TX_BCAST_BYTES |
+			STATISTICS_FLAGS_TX_ERRORS_GDMA_ERROR;
 
 	err = mana_send_request(apc->ac, &req, sizeof(req), &resp,
 				sizeof(resp));
@@ -2407,6 +2427,30 @@ void mana_query_gf_stats(struct mana_port_context *apc)
 		return;
 	}
 
+	apc->eth_stats.hc_rx_discards_no_wqe = resp.rx_discards_nowqe;
+	apc->eth_stats.hc_rx_err_vport_disabled = resp.rx_err_vport_disabled;
+	apc->eth_stats.hc_rx_bytes = resp.hc_rx_bytes;
+	apc->eth_stats.hc_rx_ucast_pkts = resp.hc_rx_ucast_pkts;
+	apc->eth_stats.hc_rx_ucast_bytes = resp.hc_rx_ucast_bytes;
+	apc->eth_stats.hc_rx_bcast_pkts = resp.hc_rx_bcast_pkts;
+	apc->eth_stats.hc_rx_bcast_bytes = resp.hc_rx_bcast_bytes;
+	apc->eth_stats.hc_rx_mcast_pkts = resp.hc_rx_mcast_pkts;
+	apc->eth_stats.hc_rx_mcast_bytes = resp.hc_rx_mcast_bytes;
+	apc->eth_stats.hc_tx_err_gf_disabled = resp.tx_err_gf_disabled;
+	apc->eth_stats.hc_tx_err_vport_disabled = resp.tx_err_vport_disabled;
+	apc->eth_stats.hc_tx_err_inval_vportoffset_pkt =
+					     resp.tx_err_inval_vport_offset_pkt;
+	apc->eth_stats.hc_tx_err_vlan_enforcement =
+					     resp.tx_err_vlan_enforcement;
+	apc->eth_stats.hc_tx_err_eth_type_enforcement =
+					     resp.tx_err_ethtype_enforcement;
+	apc->eth_stats.hc_tx_err_sa_enforcement = resp.tx_err_SA_enforcement;
+	apc->eth_stats.hc_tx_err_sqpdid_enforecement =
+					     resp.tx_err_SQPDID_enforcement;
+	apc->eth_stats.hc_tx_err_cqpdid_enforcement =
+					     resp.tx_err_CQPDID_enforcement;
+	apc->eth_stats.hc_tx_err_mtu_violation = resp.tx_err_mtu_violation;
+	apc->eth_stats.hc_tx_err_inval_oob = resp.tx_err_inval_oob;
 	apc->eth_stats.hc_tx_bytes = resp.hc_tx_bytes;
 	apc->eth_stats.hc_tx_ucast_pkts = resp.hc_tx_ucast_pkts;
 	apc->eth_stats.hc_tx_ucast_bytes = resp.hc_tx_ucast_bytes;
@@ -2414,6 +2458,7 @@ void mana_query_gf_stats(struct mana_port_context *apc)
 	apc->eth_stats.hc_tx_bcast_bytes = resp.hc_tx_bcast_bytes;
 	apc->eth_stats.hc_tx_mcast_pkts = resp.hc_tx_mcast_pkts;
 	apc->eth_stats.hc_tx_mcast_bytes = resp.hc_tx_mcast_bytes;
+	apc->eth_stats.hc_tx_err_gdma = resp.tx_err_gdma;
 }
 
 static int mana_init_port(struct net_device *ndev)
diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
index 607150165ab4..7077d647d99a 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
@@ -13,6 +13,46 @@ static const struct {
 } mana_eth_stats[] = {
 	{"stop_queue", offsetof(struct mana_ethtool_stats, stop_queue)},
 	{"wake_queue", offsetof(struct mana_ethtool_stats, wake_queue)},
+	{"hc_rx_discards_no_wqe", offsetof(struct mana_ethtool_stats,
+					   hc_rx_discards_no_wqe)},
+	{"hc_rx_err_vport_disabled", offsetof(struct mana_ethtool_stats,
+					      hc_rx_err_vport_disabled)},
+	{"hc_rx_bytes", offsetof(struct mana_ethtool_stats, hc_rx_bytes)},
+	{"hc_rx_ucast_pkts", offsetof(struct mana_ethtool_stats,
+				      hc_rx_ucast_pkts)},
+	{"hc_rx_ucast_bytes", offsetof(struct mana_ethtool_stats,
+				       hc_rx_ucast_bytes)},
+	{"hc_rx_bcast_pkts", offsetof(struct mana_ethtool_stats,
+				      hc_rx_bcast_pkts)},
+	{"hc_rx_bcast_bytes", offsetof(struct mana_ethtool_stats,
+				       hc_rx_bcast_bytes)},
+	{"hc_rx_mcast_pkts", offsetof(struct mana_ethtool_stats,
+			hc_rx_mcast_pkts)},
+	{"hc_rx_mcast_bytes", offsetof(struct mana_ethtool_stats,
+				       hc_rx_mcast_bytes)},
+	{"hc_tx_err_gf_disabled", offsetof(struct mana_ethtool_stats,
+					   hc_tx_err_gf_disabled)},
+	{"hc_tx_err_vport_disabled", offsetof(struct mana_ethtool_stats,
+					      hc_tx_err_vport_disabled)},
+	{"hc_tx_err_inval_vportoffset_pkt",
+	 offsetof(struct mana_ethtool_stats,
+		  hc_tx_err_inval_vportoffset_pkt)},
+	{"hc_tx_err_vlan_enforcement", offsetof(struct mana_ethtool_stats,
+						hc_tx_err_vlan_enforcement)},
+	{"hc_tx_err_eth_type_enforcement",
+	 offsetof(struct mana_ethtool_stats, hc_tx_err_eth_type_enforcement)},
+	{"hc_tx_err_sa_enforcement", offsetof(struct mana_ethtool_stats,
+					      hc_tx_err_sa_enforcement)},
+	{"hc_tx_err_sqpdid_enforecement",
+	 offsetof(struct mana_ethtool_stats, hc_tx_err_sqpdid_enforecement)},
+	{"hc_tx_err_cqpdid_enforcement",
+	 offsetof(struct mana_ethtool_stats, hc_tx_err_cqpdid_enforcement)},
+	{"hc_tx_err_mtu_violation", offsetof(struct mana_ethtool_stats,
+					     hc_tx_err_mtu_violation)},
+	{"hc_tx_err_inval_oob", offsetof(struct mana_ethtool_stats,
+					 hc_tx_err_inval_oob)},
+	{"hc_tx_err_gdma", offsetof(struct mana_ethtool_stats,
+				    hc_tx_err_gdma)},
 	{"hc_tx_bytes", offsetof(struct mana_ethtool_stats, hc_tx_bytes)},
 	{"hc_tx_ucast_pkts", offsetof(struct mana_ethtool_stats,
 					hc_tx_ucast_pkts)},
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index 6e3e9c1363db..5567f5bc8eb6 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -353,6 +353,25 @@ struct mana_tx_qp {
 struct mana_ethtool_stats {
 	u64 stop_queue;
 	u64 wake_queue;
+	u64 hc_rx_discards_no_wqe;
+	u64 hc_rx_err_vport_disabled;
+	u64 hc_rx_bytes;
+	u64 hc_rx_ucast_pkts;
+	u64 hc_rx_ucast_bytes;
+	u64 hc_rx_bcast_pkts;
+	u64 hc_rx_bcast_bytes;
+	u64 hc_rx_mcast_pkts;
+	u64 hc_rx_mcast_bytes;
+	u64 hc_tx_err_gf_disabled;
+	u64 hc_tx_err_vport_disabled;
+	u64 hc_tx_err_inval_vportoffset_pkt;
+	u64 hc_tx_err_vlan_enforcement;
+	u64 hc_tx_err_eth_type_enforcement;
+	u64 hc_tx_err_sa_enforcement;
+	u64 hc_tx_err_sqpdid_enforecement;
+	u64 hc_tx_err_cqpdid_enforcement;
+	u64 hc_tx_err_mtu_violation;
+	u64 hc_tx_err_inval_oob;
 	u64 hc_tx_bytes;
 	u64 hc_tx_ucast_pkts;
 	u64 hc_tx_ucast_bytes;
@@ -360,6 +379,7 @@ struct mana_ethtool_stats {
 	u64 hc_tx_bcast_bytes;
 	u64 hc_tx_mcast_pkts;
 	u64 hc_tx_mcast_bytes;
+	u64 hc_tx_err_gdma;
 	u64 tx_cqe_err;
 	u64 tx_cqe_unknown_type;
 	u64 rx_coalesced_err;
@@ -602,8 +622,8 @@ struct mana_query_gf_stat_resp {
 	struct gdma_resp_hdr hdr;
 	u64 reported_stats;
 	/* rx errors/discards */
-	u64 discard_rx_nowqe;
-	u64 err_rx_vport_disabled;
+	u64 rx_discards_nowqe;
+	u64 rx_err_vport_disabled;
 	/* rx bytes/packets */
 	u64 hc_rx_bytes;
 	u64 hc_rx_ucast_pkts;
@@ -613,16 +633,16 @@ struct mana_query_gf_stat_resp {
 	u64 hc_rx_mcast_pkts;
 	u64 hc_rx_mcast_bytes;
 	/* tx errors */
-	u64 err_tx_gf_disabled;
-	u64 err_tx_vport_disabled;
-	u64 err_tx_inval_vport_offset_pkt;
-	u64 err_tx_vlan_enforcement;
-	u64 err_tx_ethtype_enforcement;
-	u64 err_tx_SA_enforecement;
-	u64 err_tx_SQPDID_enforcement;
-	u64 err_tx_CQPDID_enforcement;
-	u64 err_tx_mtu_violation;
-	u64 err_tx_inval_oob;
+	u64 tx_err_gf_disabled;
+	u64 tx_err_vport_disabled;
+	u64 tx_err_inval_vport_offset_pkt;
+	u64 tx_err_vlan_enforcement;
+	u64 tx_err_ethtype_enforcement;
+	u64 tx_err_SA_enforcement;
+	u64 tx_err_SQPDID_enforcement;
+	u64 tx_err_CQPDID_enforcement;
+	u64 tx_err_mtu_violation;
+	u64 tx_err_inval_oob;
 	/* tx bytes/packets */
 	u64 hc_tx_bytes;
 	u64 hc_tx_ucast_pkts;
@@ -632,7 +652,7 @@ struct mana_query_gf_stat_resp {
 	u64 hc_tx_mcast_pkts;
 	u64 hc_tx_mcast_bytes;
 	/* tx error */
-	u64 err_tx_gdma;
+	u64 tx_err_gdma;
 }; /* HW DATA */
 
 /* Configure vPort Rx Steering */
-- 
cgit v1.2.3


From 45cc50d13433a62f23b7b4af380497aae5e8ddc7 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 13 Nov 2023 01:28:27 +0000
Subject: ASoC: makes CPU/Codec channel connection map more generic

Current ASoC CPU:Codec = N:M connection is using connection mapping idea,
but it is used for N < M case only. We want to use it for any case.

By this patch, not only N:M connection, but all existing connection
(1:1, 1:N, N:N) will use same connection mapping. Then, because it will
use default mapping, no conversion patch is needed to exising drivers.

More over, CPU:Codec = N:M (N > M) also supported in the same time.

ch_maps array will has CPU/Codec index by this patch.

Image
	CPU0 <---> Codec0
	CPU1 <-+-> Codec1
	CPU2 <-/

ch_map
	ch_map[0].cpu = 0	ch_map[0].codec = 0
	ch_map[1].cpu = 1	ch_map[1].codec = 1
	ch_map[2].cpu = 2	ch_map[2].codec = 1

Link: https://lore.kernel.org/r/87fs6wuszr.wl-kuninori.morimoto.gx@renesas.com
Link: https://lore.kernel.org/r/878r7yqeo4.wl-kuninori.morimoto.gx@renesas.com
Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Tested-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Tested-by: Jerome Brunet <jbrunet@baylibre.com>
Link: https://lore.kernel.org/r/87ttpq4f2c.wl-kuninori.morimoto.gx@renesas.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc.h              | 56 +++++++++++++++++++++--
 sound/soc/intel/boards/sof_sdw.c | 28 +++++-------
 sound/soc/soc-core.c             | 95 +++++++++++++++++++++++++++++++++++++++-
 sound/soc/soc-dapm.c             | 45 +++++--------------
 sound/soc/soc-pcm.c              | 44 ++++++-------------
 5 files changed, 185 insertions(+), 83 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc.h b/include/sound/soc.h
index 7792c393e238..f3803c2dc349 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -655,8 +655,45 @@ struct snd_soc_dai_link_component {
 	struct of_phandle_args *dai_args;
 };
 
-struct snd_soc_dai_link_codec_ch_map {
-	unsigned int connected_cpu_id;
+/*
+ * [dai_link->ch_maps Image sample]
+ *
+ *-------------------------
+ * CPU0 <---> Codec0
+ *
+ * ch-map[0].cpu = 0	ch-map[0].codec = 0
+ *
+ *-------------------------
+ * CPU0 <---> Codec0
+ * CPU1 <---> Codec1
+ * CPU2 <---> Codec2
+ *
+ * ch-map[0].cpu = 0	ch-map[0].codec = 0
+ * ch-map[1].cpu = 1	ch-map[1].codec = 1
+ * ch-map[2].cpu = 2	ch-map[2].codec = 2
+ *
+ *-------------------------
+ * CPU0 <---> Codec0
+ * CPU1 <-+-> Codec1
+ * CPU2 <-/
+ *
+ * ch-map[0].cpu = 0	ch-map[0].codec = 0
+ * ch-map[1].cpu = 1	ch-map[1].codec = 1
+ * ch-map[2].cpu = 2	ch-map[2].codec = 1
+ *
+ *-------------------------
+ * CPU0 <---> Codec0
+ * CPU1 <-+-> Codec1
+ *	  \-> Codec2
+ *
+ * ch-map[0].cpu = 0	ch-map[0].codec = 0
+ * ch-map[1].cpu = 1	ch-map[1].codec = 1
+ * ch-map[2].cpu = 1	ch-map[2].codec = 2
+ *
+ */
+struct snd_soc_dai_link_ch_map {
+	unsigned int cpu;
+	unsigned int codec;
 	unsigned int ch_mask;
 };
 
@@ -688,7 +725,9 @@ struct snd_soc_dai_link {
 	struct snd_soc_dai_link_component *codecs;
 	unsigned int num_codecs;
 
-	struct snd_soc_dai_link_codec_ch_map *codec_ch_maps;
+	/* num_ch_maps = max(num_cpu, num_codecs) */
+	struct snd_soc_dai_link_ch_map *ch_maps;
+
 	/*
 	 * You MAY specify the link's platform/PCM/DMA driver, either by
 	 * device name, or by DT/OF node, but not both. Some forms of link
@@ -775,6 +814,10 @@ struct snd_soc_dai_link {
 #endif
 };
 
+static inline int snd_soc_link_num_ch_map(struct snd_soc_dai_link *link) {
+	return max(link->num_cpus, link->num_codecs);
+}
+
 static inline struct snd_soc_dai_link_component*
 snd_soc_link_to_cpu(struct snd_soc_dai_link *link, int n) {
 	return &(link)->cpus[n];
@@ -808,6 +851,12 @@ snd_soc_link_to_platform(struct snd_soc_dai_link *link, int n) {
 		     ((cpu) = snd_soc_link_to_cpu(link, i));		\
 	     (i)++)
 
+#define for_each_link_ch_maps(link, i, ch_map)			\
+	for ((i) = 0;						\
+	     ((i) < snd_soc_link_num_ch_map(link) &&		\
+		      ((ch_map) = link->ch_maps + i));		\
+	     (i)++)
+
 /*
  * Sample 1 : Single CPU/Codec/Platform
  *
@@ -1163,6 +1212,7 @@ struct snd_soc_pcm_runtime {
 	     ((i) < (rtd)->dai_link->num_cpus + (rtd)->dai_link->num_codecs) &&	\
 		     ((dai) = (rtd)->dais[i]);				\
 	     (i)++)
+#define for_each_rtd_ch_maps(rtd, i, ch_maps) for_each_link_ch_maps(rtd->dai_link, i, ch_maps)
 
 void snd_soc_close_delayed_work(struct snd_soc_pcm_runtime *rtd);
 
diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c
index 3312ad8a563b..2faf7372bad0 100644
--- a/sound/soc/intel/boards/sof_sdw.c
+++ b/sound/soc/intel/boards/sof_sdw.c
@@ -570,16 +570,14 @@ int sdw_hw_params(struct snd_pcm_substream *substream,
 		  struct snd_pcm_hw_params *params)
 {
 	struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream);
+	struct snd_soc_dai_link_ch_map *ch_maps;
 	int ch = params_channels(params);
-	struct snd_soc_dai *codec_dai;
-	struct snd_soc_dai *cpu_dai;
 	unsigned int ch_mask;
 	int num_codecs;
 	int step;
 	int i;
-	int j;
 
-	if (!rtd->dai_link->codec_ch_maps)
+	if (!rtd->dai_link->ch_maps)
 		return 0;
 
 	/* Identical data will be sent to all codecs in playback */
@@ -605,13 +603,9 @@ int sdw_hw_params(struct snd_pcm_substream *substream,
 	 * link has more than one codec DAIs. Set codec channel mask and
 	 * ASoC will set the corresponding channel numbers for each cpu dai.
 	 */
-	for_each_rtd_cpu_dais(rtd, i, cpu_dai) {
-		for_each_rtd_codec_dais(rtd, j, codec_dai) {
-			if (rtd->dai_link->codec_ch_maps[j].connected_cpu_id != i)
-				continue;
-			rtd->dai_link->codec_ch_maps[j].ch_mask = ch_mask << (j * step);
-		}
-	}
+	for_each_link_ch_maps(rtd->dai_link, i, ch_maps)
+		ch_maps->ch_mask = ch_mask << (i * step);
+
 	return 0;
 }
 
@@ -1350,15 +1344,17 @@ static int get_slave_info(const struct snd_soc_acpi_link_adr *adr_link,
 	return 0;
 }
 
-static void set_dailink_map(struct snd_soc_dai_link_codec_ch_map *sdw_codec_ch_maps,
+static void set_dailink_map(struct snd_soc_dai_link_ch_map *sdw_codec_ch_maps,
 			    int codec_num, int cpu_num)
 {
 	int step;
 	int i;
 
 	step = codec_num / cpu_num;
-	for (i = 0; i < codec_num; i++)
-		sdw_codec_ch_maps[i].connected_cpu_id = i / step;
+	for (i = 0; i < codec_num; i++) {
+		sdw_codec_ch_maps[i].cpu	= i / step;
+		sdw_codec_ch_maps[i].codec	= i;
+	}
 }
 
 static const char * const type_strings[] = {"SimpleJack", "SmartAmp", "SmartMic"};
@@ -1453,7 +1449,7 @@ static int create_sdw_dailink(struct snd_soc_card *card, int *link_index,
 		*ignore_pch_dmic = true;
 
 	for_each_pcm_streams(stream) {
-		struct snd_soc_dai_link_codec_ch_map *sdw_codec_ch_maps;
+		struct snd_soc_dai_link_ch_map *sdw_codec_ch_maps;
 		char *name, *cpu_name;
 		int playback, capture;
 		static const char * const sdw_stream_name[] = {
@@ -1530,7 +1526,7 @@ static int create_sdw_dailink(struct snd_soc_card *card, int *link_index,
 		dai_links[*link_index].nonatomic = true;
 
 		set_dailink_map(sdw_codec_ch_maps, codec_num, cpu_dai_num);
-		dai_links[*link_index].codec_ch_maps = sdw_codec_ch_maps;
+		dai_links[*link_index].ch_maps = sdw_codec_ch_maps;
 		ret = set_codec_init_func(card, adr_link, dai_links + (*link_index)++,
 					  playback, group_id, adr_index, dai_index);
 		if (ret < 0) {
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index b2bd45e87bc3..4ca3319a8e19 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -1015,6 +1015,94 @@ component_dai_empty:
 	return -EINVAL;
 }
 
+#define MAX_DEFAULT_CH_MAP_SIZE 7
+static struct snd_soc_dai_link_ch_map default_ch_map_sync[MAX_DEFAULT_CH_MAP_SIZE] = {
+	{ .cpu = 0, .codec = 0 },
+	{ .cpu = 1, .codec = 1 },
+	{ .cpu = 2, .codec = 2 },
+	{ .cpu = 3, .codec = 3 },
+	{ .cpu = 4, .codec = 4 },
+	{ .cpu = 5, .codec = 5 },
+	{ .cpu = 6, .codec = 6 },
+};
+static struct snd_soc_dai_link_ch_map default_ch_map_1cpu[MAX_DEFAULT_CH_MAP_SIZE] = {
+	{ .cpu = 0, .codec = 0 },
+	{ .cpu = 0, .codec = 1 },
+	{ .cpu = 0, .codec = 2 },
+	{ .cpu = 0, .codec = 3 },
+	{ .cpu = 0, .codec = 4 },
+	{ .cpu = 0, .codec = 5 },
+	{ .cpu = 0, .codec = 6 },
+};
+static struct snd_soc_dai_link_ch_map default_ch_map_1codec[MAX_DEFAULT_CH_MAP_SIZE] = {
+	{ .cpu = 0, .codec = 0 },
+	{ .cpu = 1, .codec = 0 },
+	{ .cpu = 2, .codec = 0 },
+	{ .cpu = 3, .codec = 0 },
+	{ .cpu = 4, .codec = 0 },
+	{ .cpu = 5, .codec = 0 },
+	{ .cpu = 6, .codec = 0 },
+};
+static int snd_soc_compensate_channel_connection_map(struct snd_soc_card *card,
+						     struct snd_soc_dai_link *dai_link)
+{
+	struct snd_soc_dai_link_ch_map *ch_maps;
+	int i;
+
+	/*
+	 * dai_link->ch_maps indicates how CPU/Codec are connected.
+	 * It will be a map seen from a larger number of DAI.
+	 * see
+	 *	soc.h :: [dai_link->ch_maps Image sample]
+	 */
+
+	/* it should have ch_maps if connection was N:M */
+	if (dai_link->num_cpus > 1 && dai_link->num_codecs > 1 &&
+	    dai_link->num_cpus != dai_link->num_codecs && !dai_link->ch_maps) {
+		dev_err(card->dev, "need to have ch_maps when N:M connction (%s)",
+			dai_link->name);
+		return -EINVAL;
+	}
+
+	/* do nothing if it has own maps */
+	if (dai_link->ch_maps)
+		goto sanity_check;
+
+	/* check default map size */
+	if (dai_link->num_cpus   > MAX_DEFAULT_CH_MAP_SIZE ||
+	    dai_link->num_codecs > MAX_DEFAULT_CH_MAP_SIZE) {
+		dev_err(card->dev, "soc-core.c needs update default_connection_maps");
+		return -EINVAL;
+	}
+
+	/* Compensate missing map for ... */
+	if (dai_link->num_cpus == dai_link->num_codecs)
+		dai_link->ch_maps = default_ch_map_sync;	/* for 1:1 or N:N */
+	else if (dai_link->num_cpus <  dai_link->num_codecs)
+		dai_link->ch_maps = default_ch_map_1cpu;	/* for 1:N */
+	else
+		dai_link->ch_maps = default_ch_map_1codec;	/* for N:1 */
+
+sanity_check:
+	dev_dbg(card->dev, "dai_link %s\n", dai_link->stream_name);
+	for_each_link_ch_maps(dai_link, i, ch_maps) {
+		if ((ch_maps->cpu   >= dai_link->num_cpus) ||
+		    (ch_maps->codec >= dai_link->num_codecs)) {
+			dev_err(card->dev,
+				"unexpected dai_link->ch_maps[%d] index (cpu(%d/%d) codec(%d/%d))",
+				i,
+				ch_maps->cpu,	dai_link->num_cpus,
+				ch_maps->codec,	dai_link->num_codecs);
+			return -EINVAL;
+		}
+
+		dev_dbg(card->dev, "  [%d] cpu%d <-> codec%d\n",
+			i, ch_maps->cpu, ch_maps->codec);
+	}
+
+	return 0;
+}
+
 /**
  * snd_soc_remove_pcm_runtime - Remove a pcm_runtime from card
  * @card: The ASoC card to which the pcm_runtime has
@@ -1121,8 +1209,13 @@ int snd_soc_add_pcm_runtimes(struct snd_soc_card *card,
 			     int num_dai_link)
 {
 	for (int i = 0; i < num_dai_link; i++) {
-		int ret = snd_soc_add_pcm_runtime(card, dai_link + i);
+		int ret;
+
+		ret = snd_soc_compensate_channel_connection_map(card, dai_link + i);
+		if (ret < 0)
+			return ret;
 
+		ret = snd_soc_add_pcm_runtime(card, dai_link + i);
 		if (ret < 0)
 			return ret;
 	}
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 407a26af3eaf..bffeea80277f 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -4436,11 +4436,14 @@ static void soc_dapm_dai_stream_event(struct snd_soc_dai *dai, int stream,
 void snd_soc_dapm_connect_dai_link_widgets(struct snd_soc_card *card)
 {
 	struct snd_soc_pcm_runtime *rtd;
+	struct snd_soc_dai *cpu_dai;
 	struct snd_soc_dai *codec_dai;
-	int i;
 
 	/* for each BE DAI link... */
 	for_each_card_rtds(card, rtd)  {
+		struct snd_soc_dai_link_ch_map *ch_maps;
+		int i;
+
 		/*
 		 * dynamic FE links have no fixed DAI mapping.
 		 * CODEC<->CODEC links have no direct connection.
@@ -4448,39 +4451,15 @@ void snd_soc_dapm_connect_dai_link_widgets(struct snd_soc_card *card)
 		if (rtd->dai_link->dynamic)
 			continue;
 
-		if (rtd->dai_link->num_cpus == 1) {
-			for_each_rtd_codec_dais(rtd, i, codec_dai)
-				dapm_connect_dai_pair(card, rtd, codec_dai,
-						      snd_soc_rtd_to_cpu(rtd, 0));
-		} else if (rtd->dai_link->num_codecs == rtd->dai_link->num_cpus) {
-			for_each_rtd_codec_dais(rtd, i, codec_dai)
-				dapm_connect_dai_pair(card, rtd, codec_dai,
-						      snd_soc_rtd_to_cpu(rtd, i));
-		} else if (rtd->dai_link->num_codecs > rtd->dai_link->num_cpus) {
-			int cpu_id;
-
-			if (!rtd->dai_link->codec_ch_maps) {
-				dev_err(card->dev, "%s: no codec channel mapping table provided\n",
-					__func__);
-				continue;
-			}
+		/*
+		 * see
+		 *	soc.h :: [dai_link->ch_maps Image sample]
+		 */
+		for_each_rtd_ch_maps(rtd, i, ch_maps) {
+			cpu_dai   = snd_soc_rtd_to_cpu(rtd,   ch_maps->cpu);
+			codec_dai = snd_soc_rtd_to_codec(rtd, ch_maps->codec);
 
-			for_each_rtd_codec_dais(rtd, i, codec_dai) {
-				cpu_id = rtd->dai_link->codec_ch_maps[i].connected_cpu_id;
-				if (cpu_id >= rtd->dai_link->num_cpus) {
-					dev_err(card->dev,
-						"%s: dai_link %s cpu_id %d too large, num_cpus is %d\n",
-						__func__, rtd->dai_link->name, cpu_id,
-						rtd->dai_link->num_cpus);
-					continue;
-				}
-				dapm_connect_dai_pair(card, rtd, codec_dai,
-						      snd_soc_rtd_to_cpu(rtd, cpu_id));
-			}
-		} else {
-			dev_err(card->dev,
-				"%s: codec number %d < cpu number %d is not supported\n",
-				__func__, rtd->dai_link->num_codecs, rtd->dai_link->num_cpus);
+			dapm_connect_dai_pair(card, rtd, codec_dai, cpu_dai);
 		}
 	}
 }
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 323e4d7b6adf..c20573aeb756 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -1050,6 +1050,7 @@ static int __soc_pcm_hw_params(struct snd_soc_pcm_runtime *rtd,
 	}
 
 	for_each_rtd_cpu_dais(rtd, i, cpu_dai) {
+		struct snd_soc_dai_link_ch_map *ch_maps;
 		unsigned int ch_mask = 0;
 		int j;
 
@@ -1063,22 +1064,20 @@ static int __soc_pcm_hw_params(struct snd_soc_pcm_runtime *rtd,
 		/* copy params for each cpu */
 		tmp_params = *params;
 
-		if (!rtd->dai_link->codec_ch_maps)
-			goto hw_params;
 		/*
 		 * construct cpu channel mask by combining ch_mask of each
 		 * codec which maps to the cpu.
+		 * see
+		 *	soc.h :: [dai_link->ch_maps Image sample]
 		 */
-		for_each_rtd_codec_dais(rtd, j, codec_dai) {
-			if (rtd->dai_link->codec_ch_maps[j].connected_cpu_id == i)
-				ch_mask |= rtd->dai_link->codec_ch_maps[j].ch_mask;
-		}
+		for_each_rtd_ch_maps(rtd, j, ch_maps)
+			if (ch_maps->cpu == i)
+				ch_mask |= ch_maps->ch_mask;
 
 		/* fixup cpu channel number */
 		if (ch_mask)
 			soc_pcm_codec_params_fixup(&tmp_params, ch_mask);
 
-hw_params:
 		ret = snd_soc_dai_hw_params(cpu_dai, substream, &tmp_params);
 		if (ret < 0)
 			goto out;
@@ -2826,35 +2825,20 @@ static int soc_get_playback_capture(struct snd_soc_pcm_runtime *rtd,
 			}
 		}
 	} else {
+		struct snd_soc_dai_link_ch_map *ch_maps;
 		struct snd_soc_dai *codec_dai;
 
 		/* Adapt stream for codec2codec links */
 		int cpu_capture  = snd_soc_get_stream_cpu(dai_link, SNDRV_PCM_STREAM_CAPTURE);
 		int cpu_playback = snd_soc_get_stream_cpu(dai_link, SNDRV_PCM_STREAM_PLAYBACK);
 
-		for_each_rtd_codec_dais(rtd, i, codec_dai) {
-			if (dai_link->num_cpus == 1) {
-				cpu_dai = snd_soc_rtd_to_cpu(rtd, 0);
-			} else if (dai_link->num_cpus == dai_link->num_codecs) {
-				cpu_dai = snd_soc_rtd_to_cpu(rtd, i);
-			} else if (rtd->dai_link->num_codecs > rtd->dai_link->num_cpus) {
-				int cpu_id;
-
-				if (!rtd->dai_link->codec_ch_maps) {
-					dev_err(rtd->card->dev, "%s: no codec channel mapping table provided\n",
-						__func__);
-					return -EINVAL;
-				}
-
-				cpu_id = rtd->dai_link->codec_ch_maps[i].connected_cpu_id;
-				cpu_dai = snd_soc_rtd_to_cpu(rtd, cpu_id);
-			} else {
-				dev_err(rtd->card->dev,
-					"%s codec number %d < cpu number %d is not supported\n",
-					__func__, rtd->dai_link->num_codecs,
-					rtd->dai_link->num_cpus);
-				return -EINVAL;
-			}
+		/*
+		 * see
+		 *	soc.h :: [dai_link->ch_maps Image sample]
+		 */
+		for_each_rtd_ch_maps(rtd, i, ch_maps) {
+			cpu_dai	  = snd_soc_rtd_to_cpu(rtd,   ch_maps->cpu);
+			codec_dai = snd_soc_rtd_to_codec(rtd, ch_maps->codec);
 
 			if (snd_soc_dai_stream_valid(codec_dai, SNDRV_PCM_STREAM_PLAYBACK) &&
 			    snd_soc_dai_stream_valid(cpu_dai,   cpu_playback))
-- 
cgit v1.2.3


From 668bfeeabb5e402e3b36992f7859c284cc6e594d Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 27 Nov 2023 08:20:02 +0100
Subject: block: move a few definitions out of CONFIG_BLK_DEV_ZONED

Allow using a few symbols with IS_ENABLED instead of #idef by moving
the declarations out of #idef CONFIG_BLK_DEV_ZONED, and move
bdev_nr_zones into the remaining  #idef CONFIG_BLK_DEV_ZONED, #else
block below.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20231127072002.1332685-1-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blkdev.h | 24 +++++++++++-------------
 1 file changed, 11 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 51fa7ffdee83..17c0a7d0d319 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -331,22 +331,13 @@ typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx,
 
 void disk_set_zoned(struct gendisk *disk, enum blk_zoned_model model);
 
-#ifdef CONFIG_BLK_DEV_ZONED
 #define BLK_ALL_ZONES  ((unsigned int)-1)
 int blkdev_report_zones(struct block_device *bdev, sector_t sector,
-			unsigned int nr_zones, report_zones_cb cb, void *data);
-unsigned int bdev_nr_zones(struct block_device *bdev);
-extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op,
-			    sector_t sectors, sector_t nr_sectors,
-			    gfp_t gfp_mask);
+		unsigned int nr_zones, report_zones_cb cb, void *data);
+int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op,
+		sector_t sectors, sector_t nr_sectors, gfp_t gfp_mask);
 int blk_revalidate_disk_zones(struct gendisk *disk,
-			      void (*update_driver_data)(struct gendisk *disk));
-#else /* CONFIG_BLK_DEV_ZONED */
-static inline unsigned int bdev_nr_zones(struct block_device *bdev)
-{
-	return 0;
-}
-#endif /* CONFIG_BLK_DEV_ZONED */
+		void (*update_driver_data)(struct gendisk *disk));
 
 /*
  * Independent access ranges: struct blk_independent_access_range describes
@@ -643,6 +634,8 @@ static inline bool blk_queue_is_zoned(struct request_queue *q)
 }
 
 #ifdef CONFIG_BLK_DEV_ZONED
+unsigned int bdev_nr_zones(struct block_device *bdev);
+
 static inline unsigned int disk_nr_zones(struct gendisk *disk)
 {
 	return blk_queue_is_zoned(disk->queue) ? disk->nr_zones : 0;
@@ -687,6 +680,11 @@ static inline unsigned int bdev_max_active_zones(struct block_device *bdev)
 }
 
 #else /* CONFIG_BLK_DEV_ZONED */
+static inline unsigned int bdev_nr_zones(struct block_device *bdev)
+{
+	return 0;
+}
+
 static inline unsigned int disk_nr_zones(struct gendisk *disk)
 {
 	return 0;
-- 
cgit v1.2.3


From 2112aa034907c428785e1a5730927181276ee45b Mon Sep 17 00:00:00 2001
From: Jaroslav Kysela <perex@perex.cz>
Date: Fri, 17 Nov 2023 13:05:55 +0100
Subject: ALSA: pcm: Introduce MSBITS subformat interface

Improve granularity of format selection for S32/U32 formats by adding
constants representing 20, 24 and MAX most significant bits.

The MAX means the maximum number of significant bits which can
the physical format hold. For 32-bit formats, MAX is related
to 32 bits. For 8-bit formats, MAX is related to 8 bits etc.

As there is only one user currently (format S32_LE), subformat is
represented by a simple u32 and stores flags only for that one user
alone. The approach of subformat being part of struct snd_pcm_hardware
is a compromise between ALSA and ASoC allowing for
hw_params-intersection code to be alloc/free-less while not adding any
new responsibilities to ASoC runtime structures.

Acked-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Jaroslav Kysela <perex@perex.cz>
Co-developed-by: Cezary Rojewski <cezary.rojewski@intel.com>
Signed-off-by: Cezary Rojewski <cezary.rojewski@intel.com>
Link: https://lore.kernel.org/r/20231117120610.1755254-2-cezary.rojewski@intel.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/pcm.h               |  7 +++++
 include/uapi/sound/asound.h       |  7 +++--
 sound/core/pcm.c                  |  3 +++
 sound/core/pcm_native.c           | 55 +++++++++++++++++++++++++++++++++++++--
 tools/include/uapi/sound/asound.h |  7 +++--
 5 files changed, 73 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/sound/pcm.h b/include/sound/pcm.h
index 2a815373dac1..cc175c623dac 100644
--- a/include/sound/pcm.h
+++ b/include/sound/pcm.h
@@ -32,6 +32,7 @@
 struct snd_pcm_hardware {
 	unsigned int info;		/* SNDRV_PCM_INFO_* */
 	u64 formats;			/* SNDRV_PCM_FMTBIT_* */
+	u32 subformats;			/* for S32_LE, SNDRV_PCM_SUBFMTBIT_* */
 	unsigned int rates;		/* SNDRV_PCM_RATE_* */
 	unsigned int rate_min;		/* min rate */
 	unsigned int rate_max;		/* max rate */
@@ -217,6 +218,12 @@ struct snd_pcm_ops {
 #define SNDRV_PCM_FMTBIT_U20		SNDRV_PCM_FMTBIT_U20_BE
 #endif
 
+#define _SNDRV_PCM_SUBFMTBIT(fmt)	BIT((__force int)SNDRV_PCM_SUBFORMAT_##fmt)
+#define SNDRV_PCM_SUBFMTBIT_STD		_SNDRV_PCM_SUBFMTBIT(STD)
+#define SNDRV_PCM_SUBFMTBIT_MSBITS_MAX	_SNDRV_PCM_SUBFMTBIT(MSBITS_MAX)
+#define SNDRV_PCM_SUBFMTBIT_MSBITS_20	_SNDRV_PCM_SUBFMTBIT(MSBITS_20)
+#define SNDRV_PCM_SUBFMTBIT_MSBITS_24	_SNDRV_PCM_SUBFMTBIT(MSBITS_24)
+
 struct snd_pcm_file {
 	struct snd_pcm_substream *substream;
 	int no_compat_mmap;
diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h
index f9939da41122..d5b9cfbd9cea 100644
--- a/include/uapi/sound/asound.h
+++ b/include/uapi/sound/asound.h
@@ -142,7 +142,7 @@ struct snd_hwdep_dsp_image {
  *                                                                           *
  *****************************************************************************/
 
-#define SNDRV_PCM_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 15)
+#define SNDRV_PCM_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 16)
 
 typedef unsigned long snd_pcm_uframes_t;
 typedef signed long snd_pcm_sframes_t;
@@ -267,7 +267,10 @@ typedef int __bitwise snd_pcm_format_t;
 
 typedef int __bitwise snd_pcm_subformat_t;
 #define	SNDRV_PCM_SUBFORMAT_STD		((__force snd_pcm_subformat_t) 0)
-#define	SNDRV_PCM_SUBFORMAT_LAST	SNDRV_PCM_SUBFORMAT_STD
+#define	SNDRV_PCM_SUBFORMAT_MSBITS_MAX	((__force snd_pcm_subformat_t) 1)
+#define	SNDRV_PCM_SUBFORMAT_MSBITS_20	((__force snd_pcm_subformat_t) 2)
+#define	SNDRV_PCM_SUBFORMAT_MSBITS_24	((__force snd_pcm_subformat_t) 3)
+#define	SNDRV_PCM_SUBFORMAT_LAST	SNDRV_PCM_SUBFORMAT_MSBITS_24
 
 #define SNDRV_PCM_INFO_MMAP		0x00000001	/* hardware supports mmap */
 #define SNDRV_PCM_INFO_MMAP_VALID	0x00000002	/* period data are valid during transfer */
diff --git a/sound/core/pcm.c b/sound/core/pcm.c
index 20bb2d7c8d4b..c4bc15f048b6 100644
--- a/sound/core/pcm.c
+++ b/sound/core/pcm.c
@@ -265,6 +265,9 @@ static const char * const snd_pcm_access_names[] = {
 
 static const char * const snd_pcm_subformat_names[] = {
 	SUBFORMAT(STD), 
+	SUBFORMAT(MSBITS_MAX),
+	SUBFORMAT(MSBITS_20),
+	SUBFORMAT(MSBITS_24),
 };
 
 static const char * const snd_pcm_tstamp_mode_names[] = {
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index f610b08f5a2b..f5ff00f99788 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -479,6 +479,7 @@ static int fixup_unreferenced_params(struct snd_pcm_substream *substream,
 {
 	const struct snd_interval *i;
 	const struct snd_mask *m;
+	struct snd_mask *m_rw;
 	int err;
 
 	if (!params->msbits) {
@@ -487,6 +488,22 @@ static int fixup_unreferenced_params(struct snd_pcm_substream *substream,
 			params->msbits = snd_interval_value(i);
 	}
 
+	if (params->msbits) {
+		m = hw_param_mask_c(params, SNDRV_PCM_HW_PARAM_FORMAT);
+		if (snd_mask_single(m)) {
+			snd_pcm_format_t format = (__force snd_pcm_format_t)snd_mask_min(m);
+
+			if (snd_pcm_format_linear(format) &&
+			    snd_pcm_format_width(format) != params->msbits) {
+				m_rw = hw_param_mask(params, SNDRV_PCM_HW_PARAM_SUBFORMAT);
+				snd_mask_reset(m_rw,
+					       (__force unsigned)SNDRV_PCM_SUBFORMAT_MSBITS_MAX);
+				if (snd_mask_empty(m_rw))
+					return -EINVAL;
+			}
+		}
+	}
+
 	if (!params->rate_den) {
 		i = hw_param_interval_c(params, SNDRV_PCM_HW_PARAM_RATE);
 		if (snd_interval_single(i)) {
@@ -2483,6 +2500,41 @@ static int snd_pcm_hw_rule_buffer_bytes_max(struct snd_pcm_hw_params *params,
 	return snd_interval_refine(hw_param_interval(params, rule->var), &t);
 }		
 
+static int snd_pcm_hw_rule_subformats(struct snd_pcm_hw_params *params,
+				      struct snd_pcm_hw_rule *rule)
+{
+	struct snd_mask *sfmask = hw_param_mask(params, SNDRV_PCM_HW_PARAM_SUBFORMAT);
+	struct snd_mask *fmask = hw_param_mask(params, SNDRV_PCM_HW_PARAM_FORMAT);
+	u32 *subformats = rule->private;
+	snd_pcm_format_t f;
+	struct snd_mask m;
+
+	snd_mask_none(&m);
+	/* All PCMs support at least the default STD subformat. */
+	snd_mask_set(&m, (__force unsigned)SNDRV_PCM_SUBFORMAT_STD);
+
+	pcm_for_each_format(f) {
+		if (!snd_mask_test(fmask, (__force unsigned)f))
+			continue;
+
+		if (f == SNDRV_PCM_FORMAT_S32_LE && *subformats)
+			m.bits[0] |= *subformats;
+		else if (snd_pcm_format_linear(f))
+			snd_mask_set(&m, (__force unsigned)SNDRV_PCM_SUBFORMAT_MSBITS_MAX);
+	}
+
+	return snd_mask_refine(sfmask, &m);
+}
+
+static int snd_pcm_hw_constraint_subformats(struct snd_pcm_runtime *runtime,
+					   unsigned int cond, u32 *subformats)
+{
+	return snd_pcm_hw_rule_add(runtime, cond, -1,
+				   snd_pcm_hw_rule_subformats, (void *)subformats,
+				   SNDRV_PCM_HW_PARAM_SUBFORMAT,
+				   SNDRV_PCM_HW_PARAM_FORMAT, -1);
+}
+
 static int snd_pcm_hw_constraints_init(struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
@@ -2634,8 +2686,7 @@ static int snd_pcm_hw_constraints_complete(struct snd_pcm_substream *substream)
 	if (err < 0)
 		return err;
 
-	err = snd_pcm_hw_constraint_mask(runtime, SNDRV_PCM_HW_PARAM_SUBFORMAT,
-					 PARAM_MASK_BIT(SNDRV_PCM_SUBFORMAT_STD));
+	err = snd_pcm_hw_constraint_subformats(runtime, 0, &hw->subformats);
 	if (err < 0)
 		return err;
 
diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h
index f9939da41122..d5b9cfbd9cea 100644
--- a/tools/include/uapi/sound/asound.h
+++ b/tools/include/uapi/sound/asound.h
@@ -142,7 +142,7 @@ struct snd_hwdep_dsp_image {
  *                                                                           *
  *****************************************************************************/
 
-#define SNDRV_PCM_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 15)
+#define SNDRV_PCM_VERSION		SNDRV_PROTOCOL_VERSION(2, 0, 16)
 
 typedef unsigned long snd_pcm_uframes_t;
 typedef signed long snd_pcm_sframes_t;
@@ -267,7 +267,10 @@ typedef int __bitwise snd_pcm_format_t;
 
 typedef int __bitwise snd_pcm_subformat_t;
 #define	SNDRV_PCM_SUBFORMAT_STD		((__force snd_pcm_subformat_t) 0)
-#define	SNDRV_PCM_SUBFORMAT_LAST	SNDRV_PCM_SUBFORMAT_STD
+#define	SNDRV_PCM_SUBFORMAT_MSBITS_MAX	((__force snd_pcm_subformat_t) 1)
+#define	SNDRV_PCM_SUBFORMAT_MSBITS_20	((__force snd_pcm_subformat_t) 2)
+#define	SNDRV_PCM_SUBFORMAT_MSBITS_24	((__force snd_pcm_subformat_t) 3)
+#define	SNDRV_PCM_SUBFORMAT_LAST	SNDRV_PCM_SUBFORMAT_MSBITS_24
 
 #define SNDRV_PCM_INFO_MMAP		0x00000001	/* hardware supports mmap */
 #define SNDRV_PCM_INFO_MMAP_VALID	0x00000002	/* period data are valid during transfer */
-- 
cgit v1.2.3


From a7fc8b862fd5952be791a870ef8ef56016e83ff4 Mon Sep 17 00:00:00 2001
From: Cezary Rojewski <cezary.rojewski@intel.com>
Date: Fri, 17 Nov 2023 13:05:56 +0100
Subject: ALSA: hda: Honor subformat when querying PCMs

Update mechanism for querying supported PCMs to allow for granular
format selection when container size is 32 bits. Currently always the
highest bit depth is selected, regardless of how many actual formats
codec in question supports.

Acked-by: Mark Brown <broonie@kernel.org>
Co-developed-by: Jaroslav Kysela <perex@perex.cz>
Signed-off-by: Jaroslav Kysela <perex@perex.cz>
Signed-off-by: Cezary Rojewski <cezary.rojewski@intel.com>
Link: https://lore.kernel.org/r/20231117120610.1755254-3-cezary.rojewski@intel.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/hda_codec.h    |  5 +++--
 include/sound/hdaudio.h      |  3 ++-
 sound/hda/hdac_device.c      | 45 ++++++++++++++++++++++++--------------------
 sound/pci/hda/hda_codec.c    |  2 ++
 sound/pci/hda/patch_hdmi.c   |  1 +
 sound/soc/codecs/hdac_hdmi.c |  3 ++-
 6 files changed, 35 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/include/sound/hda_codec.h b/include/sound/hda_codec.h
index 5497dc9c396a..9c94ba7c183d 100644
--- a/include/sound/hda_codec.h
+++ b/include/sound/hda_codec.h
@@ -141,6 +141,7 @@ struct hda_pcm_stream {
 	hda_nid_t nid;	/* default NID to query rates/formats/bps, or set up */
 	u32 rates;	/* supported rates */
 	u64 formats;	/* supported formats (SNDRV_PCM_FMTBIT_) */
+	u32 subformats;	/* for S32_LE format, SNDRV_PCM_SUBFMTBIT_* */
 	unsigned int maxbps;	/* supported max. bit per sample */
 	const struct snd_pcm_chmap_elem *chmap; /* chmap to override */
 	struct hda_pcm_ops ops;
@@ -448,8 +449,8 @@ void __snd_hda_codec_cleanup_stream(struct hda_codec *codec, hda_nid_t nid,
 #define snd_hda_codec_cleanup_stream(codec, nid) \
 	__snd_hda_codec_cleanup_stream(codec, nid, 0)
 
-#define snd_hda_query_supported_pcm(codec, nid, ratesp, fmtsp, bpsp) \
-	snd_hdac_query_supported_pcm(&(codec)->core, nid, ratesp, fmtsp, bpsp)
+#define snd_hda_query_supported_pcm(codec, nid, ratesp, fmtsp, subfmtp, bpsp) \
+	snd_hdac_query_supported_pcm(&(codec)->core, nid, ratesp, fmtsp, subfmtp, bpsp)
 #define snd_hda_is_supported_format(codec, nid, fmt) \
 	snd_hdac_is_supported_format(&(codec)->core, nid, fmt)
 
diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h
index dd7c87bbc613..7cfea9e7f6e4 100644
--- a/include/sound/hdaudio.h
+++ b/include/sound/hdaudio.h
@@ -146,7 +146,8 @@ unsigned int snd_hdac_calc_stream_format(unsigned int rate,
 					 unsigned int maxbps,
 					 unsigned short spdif_ctls);
 int snd_hdac_query_supported_pcm(struct hdac_device *codec, hda_nid_t nid,
-				u32 *ratesp, u64 *formatsp, unsigned int *bpsp);
+				 u32 *ratesp, u64 *formatsp, u32 *subformatsp,
+				 unsigned int *bpsp);
 bool snd_hdac_is_supported_format(struct hdac_device *codec, hda_nid_t nid,
 				  unsigned int format);
 
diff --git a/sound/hda/hdac_device.c b/sound/hda/hdac_device.c
index bbf7bcdb449a..cde4d5c33771 100644
--- a/sound/hda/hdac_device.c
+++ b/sound/hda/hdac_device.c
@@ -817,15 +817,17 @@ static unsigned int query_stream_param(struct hdac_device *codec, hda_nid_t nid)
  * @nid: NID to query
  * @ratesp: the pointer to store the detected rate bitflags
  * @formatsp: the pointer to store the detected formats
+ * @subformatsp: the pointer to store the detected subformats for S32_LE format
  * @bpsp: the pointer to store the detected format widths
  *
- * Queries the supported PCM rates and formats.  The NULL @ratesp, @formatsp
- * or @bsps argument is ignored.
+ * Queries the supported PCM rates and formats.  The NULL @ratesp, @formatsp,
+ * @subformatsp or @bpsp argument is ignored.
  *
  * Returns 0 if successful, otherwise a negative error code.
  */
 int snd_hdac_query_supported_pcm(struct hdac_device *codec, hda_nid_t nid,
-				 u32 *ratesp, u64 *formatsp, unsigned int *bpsp)
+				 u32 *ratesp, u64 *formatsp, u32 *subformatsp,
+				 unsigned int *bpsp)
 {
 	unsigned int i, val, wcaps;
 
@@ -848,9 +850,10 @@ int snd_hdac_query_supported_pcm(struct hdac_device *codec, hda_nid_t nid,
 		*ratesp = rates;
 	}
 
-	if (formatsp || bpsp) {
-		u64 formats = 0;
+	if (formatsp || subformatsp || bpsp) {
 		unsigned int streams, bps;
+		u32 subformats = 0;
+		u64 formats = 0;
 
 		streams = query_stream_param(codec, nid);
 		if (!streams)
@@ -866,24 +869,24 @@ int snd_hdac_query_supported_pcm(struct hdac_device *codec, hda_nid_t nid,
 				formats |= SNDRV_PCM_FMTBIT_S16_LE;
 				bps = 16;
 			}
-			if (wcaps & AC_WCAP_DIGITAL) {
-				if (val & AC_SUPPCM_BITS_32)
+			if (val & AC_SUPPCM_BITS_20) {
+				formats |= SNDRV_PCM_FMTBIT_S32_LE;
+				subformats |= SNDRV_PCM_SUBFMTBIT_MSBITS_20;
+				bps = 20;
+			}
+			if (val & AC_SUPPCM_BITS_24) {
+				formats |= SNDRV_PCM_FMTBIT_S32_LE;
+				subformats |= SNDRV_PCM_SUBFMTBIT_MSBITS_24;
+				bps = 24;
+			}
+			if (val & AC_SUPPCM_BITS_32) {
+				if (wcaps & AC_WCAP_DIGITAL) {
 					formats |= SNDRV_PCM_FMTBIT_IEC958_SUBFRAME_LE;
-				if (val & (AC_SUPPCM_BITS_20|AC_SUPPCM_BITS_24))
+				} else {
 					formats |= SNDRV_PCM_FMTBIT_S32_LE;
-				if (val & AC_SUPPCM_BITS_24)
-					bps = 24;
-				else if (val & AC_SUPPCM_BITS_20)
-					bps = 20;
-			} else if (val & (AC_SUPPCM_BITS_20|AC_SUPPCM_BITS_24|
-					  AC_SUPPCM_BITS_32)) {
-				formats |= SNDRV_PCM_FMTBIT_S32_LE;
-				if (val & AC_SUPPCM_BITS_32)
+					subformats |= SNDRV_PCM_SUBFMTBIT_MSBITS_MAX;
 					bps = 32;
-				else if (val & AC_SUPPCM_BITS_24)
-					bps = 24;
-				else if (val & AC_SUPPCM_BITS_20)
-					bps = 20;
+				}
 			}
 		}
 #if 0 /* FIXME: CS4206 doesn't work, which is the only codec supporting float */
@@ -911,6 +914,8 @@ int snd_hdac_query_supported_pcm(struct hdac_device *codec, hda_nid_t nid,
 		}
 		if (formatsp)
 			*formatsp = formats;
+		if (subformatsp)
+			*subformatsp = subformats;
 		if (bpsp)
 			*bpsp = bps;
 	}
diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c
index 01718b1fc9a7..12f02cdc9659 100644
--- a/sound/pci/hda/hda_codec.c
+++ b/sound/pci/hda/hda_codec.c
@@ -3163,6 +3163,7 @@ static int set_pcm_default_values(struct hda_codec *codec,
 		err = snd_hda_query_supported_pcm(codec, info->nid,
 				info->rates ? NULL : &info->rates,
 				info->formats ? NULL : &info->formats,
+				info->subformats ? NULL : &info->subformats,
 				info->maxbps ? NULL : &info->maxbps);
 		if (err < 0)
 			return err;
@@ -3757,6 +3758,7 @@ int snd_hda_multi_out_analog_open(struct hda_codec *codec,
 			snd_hda_query_supported_pcm(codec, mout->dig_out_nid,
 						    &mout->spdif_rates,
 						    &mout->spdif_formats,
+						    NULL,
 						    &mout->spdif_maxbps);
 		}
 		mutex_lock(&codec->spdif_mutex);
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 1cde2a69bdb4..687b8b8fd7ac 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -1977,6 +1977,7 @@ static int hdmi_add_cvt(struct hda_codec *codec, hda_nid_t cvt_nid)
 	err = snd_hda_query_supported_pcm(codec, cvt_nid,
 					  &per_cvt->rates,
 					  &per_cvt->formats,
+					  NULL,
 					  &per_cvt->maxbps);
 	if (err < 0)
 		return err;
diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c
index b9c5ffbfb5ba..3e4f632d8665 100644
--- a/sound/soc/codecs/hdac_hdmi.c
+++ b/sound/soc/codecs/hdac_hdmi.c
@@ -670,6 +670,7 @@ hdac_hdmi_query_cvt_params(struct hdac_device *hdev, struct hdac_hdmi_cvt *cvt)
 	err = snd_hdac_query_supported_pcm(hdev, cvt->nid,
 			&cvt->params.rates,
 			&cvt->params.formats,
+			NULL,
 			&cvt->params.maxbps);
 	if (err < 0)
 		dev_err(&hdev->dev,
@@ -1577,7 +1578,7 @@ static int hdac_hdmi_create_dais(struct hdac_device *hdev,
 
 	list_for_each_entry(cvt, &hdmi->cvt_list, head) {
 		ret = snd_hdac_query_supported_pcm(hdev, cvt->nid,
-					&rates,	&formats, &bps);
+					&rates,	&formats, NULL, &bps);
 		if (ret)
 			return ret;
 
-- 
cgit v1.2.3


From 4a6ba09e892aab49fda8464e4f9b244a17fd75b2 Mon Sep 17 00:00:00 2001
From: Cezary Rojewski <cezary.rojewski@intel.com>
Date: Fri, 17 Nov 2023 13:05:57 +0100
Subject: ASoC: pcm: Honor subformat when configuring runtime

Subformat options are ignored when setting up hardware parameters and
assigning PCM stream capabilities. Account for them to allow for
granular format selection.

As there is only one user currently (format S32_LE), subformat is
represented by a simple u32 and stores flags only for that one user
alone. Such approach allows for alloc/free-less code until there are
more users on the horizon.

Acked-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Cezary Rojewski <cezary.rojewski@intel.com>
Acked-by: Jaroslav Kysela <perex@perex.cz>
Link: https://lore.kernel.org/r/20231117120610.1755254-4-cezary.rojewski@intel.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/soc.h |  1 +
 sound/soc/soc-pcm.c | 10 ++++++++++
 2 files changed, 11 insertions(+)

(limited to 'include')

diff --git a/include/sound/soc.h b/include/sound/soc.h
index 7792c393e238..ccc31bc41e92 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -620,6 +620,7 @@ enum snd_soc_trigger_order {
 struct snd_soc_pcm_stream {
 	const char *stream_name;
 	u64 formats;			/* SNDRV_PCM_FMTBIT_* */
+	u32 subformats;			/* for S32_LE format, SNDRV_PCM_SUBFMTBIT_* */
 	unsigned int rates;		/* SNDRV_PCM_RATE_* */
 	unsigned int rate_min;		/* min rate */
 	unsigned int rate_max;		/* max rate */
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 323e4d7b6adf..9d688917cce2 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -554,6 +554,12 @@ static void soc_pcm_hw_update_format(struct snd_pcm_hardware *hw,
 	hw->formats &= p->formats;
 }
 
+static void soc_pcm_hw_update_subformat(struct snd_pcm_hardware *hw,
+					struct snd_soc_pcm_stream *p)
+{
+	hw->subformats &= p->subformats;
+}
+
 /**
  * snd_soc_runtime_calc_hw() - Calculate hw limits for a PCM stream
  * @rtd: ASoC PCM runtime
@@ -592,6 +598,7 @@ int snd_soc_runtime_calc_hw(struct snd_soc_pcm_runtime *rtd,
 		soc_pcm_hw_update_chan(hw, cpu_stream);
 		soc_pcm_hw_update_rate(hw, cpu_stream);
 		soc_pcm_hw_update_format(hw, cpu_stream);
+		soc_pcm_hw_update_subformat(hw, cpu_stream);
 	}
 	cpu_chan_min = hw->channels_min;
 	cpu_chan_max = hw->channels_max;
@@ -613,6 +620,7 @@ int snd_soc_runtime_calc_hw(struct snd_soc_pcm_runtime *rtd,
 		soc_pcm_hw_update_chan(hw, codec_stream);
 		soc_pcm_hw_update_rate(hw, codec_stream);
 		soc_pcm_hw_update_format(hw, codec_stream);
+		soc_pcm_hw_update_subformat(hw, codec_stream);
 	}
 
 	/* Verify both a valid CPU DAI and a valid CODEC DAI were found */
@@ -1713,6 +1721,7 @@ static void dpcm_runtime_setup_fe(struct snd_pcm_substream *substream)
 		soc_pcm_hw_update_rate(hw, cpu_stream);
 		soc_pcm_hw_update_chan(hw, cpu_stream);
 		soc_pcm_hw_update_format(hw, cpu_stream);
+		soc_pcm_hw_update_subformat(hw, cpu_stream);
 	}
 
 }
@@ -1750,6 +1759,7 @@ static void dpcm_runtime_setup_be_format(struct snd_pcm_substream *substream)
 			codec_stream = snd_soc_dai_get_pcm_stream(dai, stream);
 
 			soc_pcm_hw_update_format(hw, codec_stream);
+			soc_pcm_hw_update_subformat(hw, codec_stream);
 		}
 	}
 }
-- 
cgit v1.2.3


From d24f1a090d3f2a5c86a8782afeda71c2d2539966 Mon Sep 17 00:00:00 2001
From: Cezary Rojewski <cezary.rojewski@intel.com>
Date: Fri, 17 Nov 2023 13:05:58 +0100
Subject: ALSA: hda: Upgrade stream-format infrastructure

Introduce a set of functions that ultimately facilite SDxFMT-related
calculations in atomic manner:

First, introduce snd_pcm_subformat_width() and snd_pcm_hw_params_bits()
helpers that separate the base functionality from the HDAudio-specific
one.

snd_hdac_format_normalize() - format converter. S20_LE, S24_LE and their
unsigned and BE friends are invalid from HDAudio perspective but still
can be specified as function argument due to compatibility reasons.

snd_hdac_stream_format_bits() - obtain just the bits-per-sample value.
Does not ignore subformat and msbits parameters.

snd_hdac_stream_format() and snd_hdac_spdif_stream_format() - obtain the
SDxFMT value given the audio format parameters. The former is stripped
away of spdif-related information. Useful for users that do not care
about them.

Acked-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Cezary Rojewski <cezary.rojewski@intel.com>
Acked-by: Jaroslav Kysela <perex@perex.cz>
Link: https://lore.kernel.org/r/20231117120610.1755254-5-cezary.rojewski@intel.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/hdaudio.h    |   5 ++
 include/sound/pcm_params.h |   2 +
 sound/core/pcm_lib.c       |  34 +++++++++++++
 sound/hda/hdac_device.c    | 124 +++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 165 insertions(+)

(limited to 'include')

diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h
index 7cfea9e7f6e4..b00c631c4053 100644
--- a/include/sound/hdaudio.h
+++ b/include/sound/hdaudio.h
@@ -140,6 +140,11 @@ int snd_hdac_get_connections(struct hdac_device *codec, hda_nid_t nid,
 			     hda_nid_t *conn_list, int max_conns);
 int snd_hdac_get_sub_nodes(struct hdac_device *codec, hda_nid_t nid,
 			   hda_nid_t *start_id);
+unsigned int snd_hdac_stream_format_bits(snd_pcm_format_t format, snd_pcm_subformat_t subformat,
+					 unsigned int maxbits);
+unsigned int snd_hdac_stream_format(unsigned int channels, unsigned int bits, unsigned int rate);
+unsigned int snd_hdac_spdif_stream_format(unsigned int channels, unsigned int bits,
+					  unsigned int rate, unsigned short spdif_ctls);
 unsigned int snd_hdac_calc_stream_format(unsigned int rate,
 					 unsigned int channels,
 					 snd_pcm_format_t format,
diff --git a/include/sound/pcm_params.h b/include/sound/pcm_params.h
index ba184f49f7e1..fbf35df6e5cf 100644
--- a/include/sound/pcm_params.h
+++ b/include/sound/pcm_params.h
@@ -362,6 +362,8 @@ static inline int params_physical_width(const struct snd_pcm_hw_params *p)
 	return snd_pcm_format_physical_width(params_format(p));
 }
 
+int snd_pcm_hw_params_bits(const struct snd_pcm_hw_params *p);
+
 static inline void
 params_set_format(struct snd_pcm_hw_params *p, snd_pcm_format_t fmt)
 {
diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c
index a11cd7d6295f..41103e5c43ce 100644
--- a/sound/core/pcm_lib.c
+++ b/sound/core/pcm_lib.c
@@ -1706,6 +1706,40 @@ int snd_pcm_hw_param_last(struct snd_pcm_substream *pcm,
 }
 EXPORT_SYMBOL(snd_pcm_hw_param_last);
 
+/**
+ * snd_pcm_hw_params_bits - Get the number of bits per the sample.
+ * @p: hardware parameters
+ *
+ * Return: The number of bits per sample based on the format,
+ * subformat and msbits the specified hw params has.
+ */
+int snd_pcm_hw_params_bits(const struct snd_pcm_hw_params *p)
+{
+	snd_pcm_subformat_t subformat = params_subformat(p);
+	snd_pcm_format_t format = params_format(p);
+
+	switch (format) {
+	case SNDRV_PCM_FORMAT_S32_LE:
+	case SNDRV_PCM_FORMAT_U32_LE:
+	case SNDRV_PCM_FORMAT_S32_BE:
+	case SNDRV_PCM_FORMAT_U32_BE:
+		switch (subformat) {
+		case SNDRV_PCM_SUBFORMAT_MSBITS_20:
+			return 20;
+		case SNDRV_PCM_SUBFORMAT_MSBITS_24:
+			return 24;
+		case SNDRV_PCM_SUBFORMAT_MSBITS_MAX:
+		case SNDRV_PCM_SUBFORMAT_STD:
+		default:
+			break;
+		}
+		fallthrough;
+	default:
+		return snd_pcm_format_width(format);
+	}
+}
+EXPORT_SYMBOL(snd_pcm_hw_params_bits);
+
 static int snd_pcm_lib_ioctl_reset(struct snd_pcm_substream *substream,
 				   void *arg)
 {
diff --git a/sound/hda/hdac_device.c b/sound/hda/hdac_device.c
index cde4d5c33771..556bd24f4014 100644
--- a/sound/hda/hdac_device.c
+++ b/sound/hda/hdac_device.c
@@ -13,6 +13,7 @@
 #include <sound/hdaudio.h>
 #include <sound/hda_regmap.h>
 #include <sound/pcm.h>
+#include <sound/pcm_params.h>
 #include "local.h"
 
 static void setup_fg_nodes(struct hdac_device *codec);
@@ -725,6 +726,129 @@ static const struct hda_rate_tbl rate_bits[] = {
 	{ 0 } /* terminator */
 };
 
+static snd_pcm_format_t snd_hdac_format_normalize(snd_pcm_format_t format)
+{
+	switch (format) {
+	case SNDRV_PCM_FORMAT_S20_LE:
+	case SNDRV_PCM_FORMAT_S24_LE:
+		return SNDRV_PCM_FORMAT_S32_LE;
+
+	case SNDRV_PCM_FORMAT_U20_LE:
+	case SNDRV_PCM_FORMAT_U24_LE:
+		return SNDRV_PCM_FORMAT_U32_LE;
+
+	case SNDRV_PCM_FORMAT_S20_BE:
+	case SNDRV_PCM_FORMAT_S24_BE:
+		return SNDRV_PCM_FORMAT_S32_BE;
+
+	case SNDRV_PCM_FORMAT_U20_BE:
+	case SNDRV_PCM_FORMAT_U24_BE:
+		return SNDRV_PCM_FORMAT_U32_BE;
+
+	default:
+		return format;
+	}
+}
+
+/**
+ * snd_hdac_stream_format_bits - obtain bits per sample value.
+ * @format:	the PCM format.
+ * @subformat:	the PCM subformat.
+ * @maxbits:	the maximum bits per sample.
+ *
+ * Return: The number of bits per sample.
+ */
+unsigned int snd_hdac_stream_format_bits(snd_pcm_format_t format, snd_pcm_subformat_t subformat,
+					 unsigned int maxbits)
+{
+	struct snd_pcm_hw_params params;
+	unsigned int bits;
+
+	memset(&params, 0, sizeof(params));
+
+	params_set_format(&params, snd_hdac_format_normalize(format));
+	snd_mask_set(hw_param_mask(&params, SNDRV_PCM_HW_PARAM_SUBFORMAT),
+		     (__force unsigned int)subformat);
+
+	bits = snd_pcm_hw_params_bits(&params);
+	if (maxbits)
+		return min(bits, maxbits);
+	return bits;
+}
+EXPORT_SYMBOL_GPL(snd_hdac_stream_format_bits);
+
+/**
+ * snd_hdac_stream_format - convert format parameters to SDxFMT value.
+ * @channels:	the number of channels.
+ * @bits:	bits per sample.
+ * @rate:	the sample rate.
+ *
+ * Return: The format bitset or zero if invalid.
+ */
+unsigned int snd_hdac_stream_format(unsigned int channels, unsigned int bits, unsigned int rate)
+{
+	unsigned int val = 0;
+	int i;
+
+	for (i = 0; rate_bits[i].hz; i++) {
+		if (rate_bits[i].hz == rate) {
+			val = rate_bits[i].hda_fmt;
+			break;
+		}
+	}
+
+	if (!rate_bits[i].hz)
+		return 0;
+
+	if (channels == 0 || channels > 8)
+		return 0;
+	val |= channels - 1;
+
+	switch (bits) {
+	case 8:
+		val |= AC_FMT_BITS_8;
+		break;
+	case 16:
+		val |= AC_FMT_BITS_16;
+		break;
+	case 20:
+		val |= AC_FMT_BITS_20;
+		break;
+	case 24:
+		val |= AC_FMT_BITS_24;
+		break;
+	case 32:
+		val |= AC_FMT_BITS_32;
+		break;
+	default:
+		return 0;
+	}
+
+	return val;
+}
+EXPORT_SYMBOL_GPL(snd_hdac_stream_format);
+
+/**
+ * snd_hdac_spdif_stream_format - convert format parameters to SDxFMT value.
+ * @channels:	the number of channels.
+ * @bits:	bits per sample.
+ * @rate:	the sample rate.
+ * @spdif_ctls:	HD-audio SPDIF status bits (0 if irrelevant).
+ *
+ * Return: The format bitset or zero if invalid.
+ */
+unsigned int snd_hdac_spdif_stream_format(unsigned int channels, unsigned int bits,
+					  unsigned int rate, unsigned short spdif_ctls)
+{
+	unsigned int val = snd_hdac_stream_format(channels, bits, rate);
+
+	if (val && spdif_ctls & AC_DIG1_NONAUDIO)
+		val |= AC_FMT_TYPE_NON_PCM;
+
+	return val;
+}
+EXPORT_SYMBOL_GPL(snd_hdac_spdif_stream_format);
+
 /**
  * snd_hdac_calc_stream_format - calculate the format bitset
  * @rate: the sample rate
-- 
cgit v1.2.3


From dfd6ba6813dd0fdea54de58e7b80ca304ce3fca5 Mon Sep 17 00:00:00 2001
From: Cezary Rojewski <cezary.rojewski@intel.com>
Date: Fri, 17 Nov 2023 13:06:08 +0100
Subject: ALSA: hda: Drop snd_hdac_calc_stream_format()

There are no users of the function.

Acked-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Cezary Rojewski <cezary.rojewski@intel.com>
Acked-by: Jaroslav Kysela <perex@perex.cz>
Link: https://lore.kernel.org/r/20231117120610.1755254-15-cezary.rojewski@intel.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/hdaudio.h |  5 ----
 sound/hda/hdac_device.c | 61 -------------------------------------------------
 2 files changed, 66 deletions(-)

(limited to 'include')

diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h
index b00c631c4053..62a3cd154ff2 100644
--- a/include/sound/hdaudio.h
+++ b/include/sound/hdaudio.h
@@ -145,11 +145,6 @@ unsigned int snd_hdac_stream_format_bits(snd_pcm_format_t format, snd_pcm_subfor
 unsigned int snd_hdac_stream_format(unsigned int channels, unsigned int bits, unsigned int rate);
 unsigned int snd_hdac_spdif_stream_format(unsigned int channels, unsigned int bits,
 					  unsigned int rate, unsigned short spdif_ctls);
-unsigned int snd_hdac_calc_stream_format(unsigned int rate,
-					 unsigned int channels,
-					 snd_pcm_format_t format,
-					 unsigned int maxbps,
-					 unsigned short spdif_ctls);
 int snd_hdac_query_supported_pcm(struct hdac_device *codec, hda_nid_t nid,
 				 u32 *ratesp, u64 *formatsp, u32 *subformatsp,
 				 unsigned int *bpsp);
diff --git a/sound/hda/hdac_device.c b/sound/hda/hdac_device.c
index 556bd24f4014..7f7b67fe1b65 100644
--- a/sound/hda/hdac_device.c
+++ b/sound/hda/hdac_device.c
@@ -849,67 +849,6 @@ unsigned int snd_hdac_spdif_stream_format(unsigned int channels, unsigned int bi
 }
 EXPORT_SYMBOL_GPL(snd_hdac_spdif_stream_format);
 
-/**
- * snd_hdac_calc_stream_format - calculate the format bitset
- * @rate: the sample rate
- * @channels: the number of channels
- * @format: the PCM format (SNDRV_PCM_FORMAT_XXX)
- * @maxbps: the max. bps
- * @spdif_ctls: HD-audio SPDIF status bits (0 if irrelevant)
- *
- * Calculate the format bitset from the given rate, channels and th PCM format.
- *
- * Return zero if invalid.
- */
-unsigned int snd_hdac_calc_stream_format(unsigned int rate,
-					 unsigned int channels,
-					 snd_pcm_format_t format,
-					 unsigned int maxbps,
-					 unsigned short spdif_ctls)
-{
-	int i;
-	unsigned int val = 0;
-
-	for (i = 0; rate_bits[i].hz; i++)
-		if (rate_bits[i].hz == rate) {
-			val = rate_bits[i].hda_fmt;
-			break;
-		}
-	if (!rate_bits[i].hz)
-		return 0;
-
-	if (channels == 0 || channels > 8)
-		return 0;
-	val |= channels - 1;
-
-	switch (snd_pcm_format_width(format)) {
-	case 8:
-		val |= AC_FMT_BITS_8;
-		break;
-	case 16:
-		val |= AC_FMT_BITS_16;
-		break;
-	case 20:
-	case 24:
-	case 32:
-		if (maxbps >= 32 || format == SNDRV_PCM_FORMAT_FLOAT_LE)
-			val |= AC_FMT_BITS_32;
-		else if (maxbps >= 24)
-			val |= AC_FMT_BITS_24;
-		else
-			val |= AC_FMT_BITS_20;
-		break;
-	default:
-		return 0;
-	}
-
-	if (spdif_ctls & AC_DIG1_NONAUDIO)
-		val |= AC_FMT_TYPE_NON_PCM;
-
-	return val;
-}
-EXPORT_SYMBOL_GPL(snd_hdac_calc_stream_format);
-
 static unsigned int query_pcm_param(struct hdac_device *codec, hda_nid_t nid)
 {
 	unsigned int val = 0;
-- 
cgit v1.2.3


From 95ba893c9f4feb836ddce627efd0bb6af6667031 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Tue, 14 Nov 2023 13:37:09 +0100
Subject: dma-buf: fix check in dma_resv_add_fence
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It's valid to add the same fence multiple times to a dma-resv object and
we shouldn't need one extra slot for each.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Fixes: a3f7c10a269d5 ("dma-buf/dma-resv: check if the new fence is really later")
Cc: stable@vger.kernel.org # v5.19+
Link: https://patchwork.freedesktop.org/patch/msgid/20231115093035.1889-1-christian.koenig@amd.com
---
 drivers/dma-buf/dma-resv.c |  2 +-
 include/linux/dma-fence.h  | 15 +++++++++++++++
 2 files changed, 16 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c
index 38b4110378de..eb8b733065b2 100644
--- a/drivers/dma-buf/dma-resv.c
+++ b/drivers/dma-buf/dma-resv.c
@@ -301,7 +301,7 @@ void dma_resv_add_fence(struct dma_resv *obj, struct dma_fence *fence,
 
 		dma_resv_list_entry(fobj, i, obj, &old, &old_usage);
 		if ((old->context == fence->context && old_usage >= usage &&
-		     dma_fence_is_later(fence, old)) ||
+		     dma_fence_is_later_or_same(fence, old)) ||
 		    dma_fence_is_signaled(old)) {
 			dma_resv_list_set(fobj, i, fence, usage);
 			dma_fence_put(old);
diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h
index ebe78bd3d121..b3772edca2e6 100644
--- a/include/linux/dma-fence.h
+++ b/include/linux/dma-fence.h
@@ -498,6 +498,21 @@ static inline bool dma_fence_is_later(struct dma_fence *f1,
 	return __dma_fence_is_later(f1->seqno, f2->seqno, f1->ops);
 }
 
+/**
+ * dma_fence_is_later_or_same - return true if f1 is later or same as f2
+ * @f1: the first fence from the same context
+ * @f2: the second fence from the same context
+ *
+ * Returns true if f1 is chronologically later than f2 or the same fence. Both
+ * fences must be from the same context, since a seqno is not re-used across
+ * contexts.
+ */
+static inline bool dma_fence_is_later_or_same(struct dma_fence *f1,
+					      struct dma_fence *f2)
+{
+	return f1 == f2 || dma_fence_is_later(f1, f2);
+}
+
 /**
  * dma_fence_later - return the chronologically later fence
  * @f1:	the first fence from the same context
-- 
cgit v1.2.3


From 4e86f32a13af1970d21be94f659cae56bbe487ee Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Mon, 20 Nov 2023 14:05:08 +0300
Subject: uapi: propagate __struct_group() attributes to the container union

Recently the kernel test robot has reported an ARM-specific BUILD_BUG_ON()
in an old and unmaintained wil6210 wireless driver. The problem comes from
the structure packing rules of old ARM ABI ('-mabi=apcs-gnu'). For example,
the following structure is packed to 18 bytes instead of 16:

struct poorly_packed {
        unsigned int a;
        unsigned int b;
        unsigned short c;
        union {
                struct {
                        unsigned short d;
                        unsigned int e;
                } __attribute__((packed));
                struct {
                        unsigned short d;
                        unsigned int e;
                } __attribute__((packed)) inner;
        };
} __attribute__((packed));

To fit it into 16 bytes, it's required to add packed attribute to the
container union as well:

struct poorly_packed {
        unsigned int a;
        unsigned int b;
        unsigned short c;
        union {
                struct {
                        unsigned short d;
                        unsigned int e;
                } __attribute__((packed));
                struct {
                        unsigned short d;
                        unsigned int e;
                } __attribute__((packed)) inner;
        } __attribute__((packed));
} __attribute__((packed));

Thanks to Andrew Pinski of GCC team for sorting the things out at
https://gcc.gnu.org/pipermail/gcc/2023-November/242888.html.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202311150821.cI4yciFE-lkp@intel.com
Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Link: https://lore.kernel.org/r/20231120110607.98956-1-dmantipov@yandex.ru
Fixes: 50d7bd38c3aa ("stddef: Introduce struct_group() helper macro")
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 include/uapi/linux/stddef.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h
index 5c6c4269f7ef..2ec6f35cda32 100644
--- a/include/uapi/linux/stddef.h
+++ b/include/uapi/linux/stddef.h
@@ -27,7 +27,7 @@
 	union { \
 		struct { MEMBERS } ATTRS; \
 		struct TAG { MEMBERS } ATTRS NAME; \
-	}
+	} ATTRS
 
 #ifdef __cplusplus
 /* sizeof(struct{}) is 1 in C++, not 0, can't use C version of the macro. */
-- 
cgit v1.2.3


From 243ad8df7a1bd24c2e01bd99d9f0bb88844dae91 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Fri, 24 Nov 2023 12:27:52 +0000
Subject: net: phy: add possible interfaces

Add a possible_interfaces member to struct phy_device to indicate which
interfaces a clause 45 PHY may switch between depending on the media.
This must be populated by the PHY driver by the time the .config_init()
method completes according to the PHYs host-side configuration.

For example, the Marvell 88x3310 PHY can switch between 10GBASE-R,
5GBASE-R, 2500BASE-X, and SGMII on the host side depending on the media
side speed, so all these interface modes are set in the
possible_interfaces member.

This allows phylib users (such as phylink) to know in advance which
interface modes to expect, which allows them to appropriately restrict
the advertised link modes according to the capabilities of other parts
of the link.

Tested-by: Luo Jie <quic_luoj@quicinc.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/r/E1r6VHk-00DDLN-I7@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phy_device.c | 2 ++
 include/linux/phy.h          | 3 +++
 2 files changed, 5 insertions(+)

(limited to 'include')

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 478126f6b5bc..400fb09d9cd6 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1246,6 +1246,8 @@ int phy_init_hw(struct phy_device *phydev)
 	if (ret < 0)
 		return ret;
 
+	phy_interface_zero(phydev->possible_interfaces);
+
 	if (phydev->drv->config_init) {
 		ret = phydev->drv->config_init(phydev);
 		if (ret < 0)
diff --git a/include/linux/phy.h b/include/linux/phy.h
index e5f1f41e399c..6e7ebcc50b85 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -605,6 +605,8 @@ struct macsec_ops;
  * @irq_rerun: Flag indicating interrupts occurred while PHY was suspended,
  *             requiring a rerun of the interrupt handler after resume
  * @interface: enum phy_interface_t value
+ * @possible_interfaces: bitmap if interface modes that the attached PHY
+ *			 will switch between depending on media speed.
  * @skb: Netlink message for cable diagnostics
  * @nest: Netlink nest used for cable diagnostics
  * @ehdr: nNtlink header for cable diagnostics
@@ -674,6 +676,7 @@ struct phy_device {
 	u32 dev_flags;
 
 	phy_interface_t interface;
+	DECLARE_PHY_INTERFACE_MASK(possible_interfaces);
 
 	/*
 	 * forced speed & duplex (no autoneg)
-- 
cgit v1.2.3


From b9c02e1052650af56d4487efa5fade3fb70e3653 Mon Sep 17 00:00:00 2001
From: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Date: Mon, 6 Nov 2023 12:48:27 +0100
Subject: drm/gpuvm: Fix deprecated license identifier
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

"GPL-2.0-only" in the license header was incorrectly changed to the
now deprecated "GPL-2.0". Fix.

Cc: Maxime Ripard <mripard@kernel.org>
Cc: Danilo Krummrich <dakr@redhat.com>
Reported-by: David Edelsohn <dje.gcc@gmail.com>
Closes: https://lore.kernel.org/dri-devel/5lfrhdpkwhpgzipgngojs3tyqfqbesifzu5nf4l5q3nhfdhcf2@25nmiq7tfrew/T/#m5c356d68815711eea30dd94cc6f7ea8cd4344fe3
Fixes: f7749a549b4f ("drm/gpuvm: Dual-licence the drm_gpuvm code GPL-2.0 OR MIT")
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Acked-by: Maxime Ripard <mripard@kernel.org>
Acked-by: Danilo Krummrich <dakr@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231106114827.62492-1-thomas.hellstrom@linux.intel.com
---
 drivers/gpu/drm/drm_gpuvm.c | 2 +-
 include/drm/drm_gpuvm.h     | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_gpuvm.c b/drivers/gpu/drm/drm_gpuvm.c
index 08c088319652..b80d4e1cc9b7 100644
--- a/drivers/gpu/drm/drm_gpuvm.c
+++ b/drivers/gpu/drm/drm_gpuvm.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0 OR MIT
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
 /*
  * Copyright (c) 2022 Red Hat.
  *
diff --git a/include/drm/drm_gpuvm.h b/include/drm/drm_gpuvm.h
index bdfafc4a7705..c7a0594bdab1 100644
--- a/include/drm/drm_gpuvm.h
+++ b/include/drm/drm_gpuvm.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/* SPDX-License-Identifier: GPL-2.0-only OR MIT */
 
 #ifndef __DRM_GPUVM_H__
 #define __DRM_GPUVM_H__
-- 
cgit v1.2.3


From 073d3d2ca7d462afc8159ca0175675b9b7b4f162 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Fri, 27 Oct 2023 12:40:04 +0530
Subject: OPP: Level zero is valid

The level zero can be used by some OPPs to drop performance state vote
for the device. It is perfectly fine to allow the same.

_set_opp_level() considers it as an invalid value currently and returns
early.

In order to support this properly, initialize the level field with
U32_MAX, which denotes unused level field.

Reported-by: Stephan Gerhold <stephan.gerhold@kernkonzept.com>
Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Tested-by: Stephan Gerhold <stephan.gerhold@kernkonzept.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
---
 drivers/opp/core.c     | 24 ++++++++++++++++++++----
 drivers/opp/of.c       |  8 +++++++-
 include/linux/pm_opp.h |  5 ++++-
 3 files changed, 31 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index 84f345c69ea5..f2e2aa07b431 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -201,7 +201,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_freq_indexed);
  * @opp:	opp for which level value has to be returned for
  *
  * Return: level read from device tree corresponding to the opp, else
- * return 0.
+ * return U32_MAX.
  */
 unsigned int dev_pm_opp_get_level(struct dev_pm_opp *opp)
 {
@@ -221,7 +221,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_level);
  * @index:	index of the required opp
  *
  * Return: performance state read from device tree corresponding to the
- * required opp, else return 0.
+ * required opp, else return U32_MAX.
  */
 unsigned int dev_pm_opp_get_required_pstate(struct dev_pm_opp *opp,
 					    unsigned int index)
@@ -808,6 +808,14 @@ struct dev_pm_opp *dev_pm_opp_find_level_ceil(struct device *dev,
 	struct dev_pm_opp *opp;
 
 	opp = _find_key_ceil(dev, &temp, 0, true, _read_level, NULL);
+
+	/* False match */
+	if (temp == OPP_LEVEL_UNSET) {
+		dev_err(dev, "%s: OPP levels aren't available\n", __func__);
+		dev_pm_opp_put(opp);
+		return ERR_PTR(-ENODEV);
+	}
+
 	*level = temp;
 	return opp;
 }
@@ -1049,12 +1057,18 @@ static int _set_opp_bw(const struct opp_table *opp_table,
 static int _set_performance_state(struct device *dev, struct device *pd_dev,
 				  struct dev_pm_opp *opp, int i)
 {
-	unsigned int pstate = likely(opp) ? opp->required_opps[i]->level: 0;
+	unsigned int pstate = 0;
 	int ret;
 
 	if (!pd_dev)
 		return 0;
 
+	if (likely(opp)) {
+		pstate = opp->required_opps[i]->level;
+		if (pstate == OPP_LEVEL_UNSET)
+			return 0;
+	}
+
 	ret = dev_pm_domain_set_performance_state(pd_dev, pstate);
 	if (ret) {
 		dev_err(dev, "Failed to set performance state of %s: %d (%d)\n",
@@ -1135,7 +1149,7 @@ static int _set_opp_level(struct device *dev, struct opp_table *opp_table,
 	int ret = 0;
 
 	if (opp) {
-		if (!opp->level)
+		if (opp->level == OPP_LEVEL_UNSET)
 			return 0;
 
 		level = opp->level;
@@ -1867,6 +1881,8 @@ struct dev_pm_opp *_opp_allocate(struct opp_table *opp_table)
 
 	INIT_LIST_HEAD(&opp->node);
 
+	opp->level = OPP_LEVEL_UNSET;
+
 	return opp;
 }
 
diff --git a/drivers/opp/of.c b/drivers/opp/of.c
index 81fa27599d58..85fad7ca0007 100644
--- a/drivers/opp/of.c
+++ b/drivers/opp/of.c
@@ -1393,8 +1393,14 @@ int of_get_required_opp_performance_state(struct device_node *np, int index)
 
 	opp = _find_opp_of_np(opp_table, required_np);
 	if (opp) {
-		pstate = opp->level;
+		if (opp->level == OPP_LEVEL_UNSET) {
+			pr_err("%s: OPP levels aren't available for %pOF\n",
+			       __func__, np);
+		} else {
+			pstate = opp->level;
+		}
 		dev_pm_opp_put(opp);
+
 	}
 
 	dev_pm_opp_put_opp_table(opp_table);
diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h
index ccd97bcef269..af53101a1383 100644
--- a/include/linux/pm_opp.h
+++ b/include/linux/pm_opp.h
@@ -92,9 +92,12 @@ struct dev_pm_opp_config {
 	struct device ***virt_devs;
 };
 
+#define OPP_LEVEL_UNSET			U32_MAX
+
 /**
  * struct dev_pm_opp_data - The data to use to initialize an OPP.
- * @level: The performance level for the OPP.
+ * @level: The performance level for the OPP. Set level to OPP_LEVEL_UNSET if
+ * level field isn't used.
  * @freq: The clock rate in Hz for the OPP.
  * @u_volt: The voltage in uV for the OPP.
  */
-- 
cgit v1.2.3


From e37440e7e2c2760475d60c5556b59c8880a7fd63 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Fri, 27 Oct 2023 14:17:48 +0530
Subject: OPP: Call dev_pm_opp_set_opp() for required OPPs

Configuring the required OPP was never properly implemented, we just
took an exception for genpds and configured them directly, while leaving
out all other required OPP types.

Now that a standard call to dev_pm_opp_set_opp() takes care of
configuring the opp->level too, the special handling for genpds can be
avoided by simply calling dev_pm_opp_set_opp() for the required OPPs,
which shall eventually configure the corresponding level for genpds.

This also makes it possible for us to configure other type of required
OPPs (no concrete users yet though), via the same path. This is how
other frameworks take care of parent nodes, like clock, regulators, etc,
where we recursively call the same helper.

In order to call dev_pm_opp_set_opp() for the virtual genpd devices,
they must share the OPP table of the genpd. Call _add_opp_dev() for them
to get that done.

This commit also extends the struct dev_pm_opp_config to pass required
devices, for non-genpd cases, which can be used to call
dev_pm_opp_set_opp() for the non-genpd required devices.

Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Tested-by: Stephan Gerhold <stephan.gerhold@kernkonzept.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
---
 drivers/opp/core.c     | 168 ++++++++++++++++++++++++-------------------------
 drivers/opp/of.c       |  17 ++---
 drivers/opp/opp.h      |   8 +--
 include/linux/pm_opp.h |   7 ++-
 4 files changed, 100 insertions(+), 100 deletions(-)

(limited to 'include')

diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index aeb216f7e978..e08375ed50aa 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -1054,48 +1054,22 @@ static int _set_opp_bw(const struct opp_table *opp_table,
 	return 0;
 }
 
-static int _set_performance_state(struct device *dev, struct device *pd_dev,
-				  struct dev_pm_opp *opp, int i)
-{
-	unsigned int pstate = 0;
-	int ret;
-
-	if (!pd_dev)
-		return 0;
-
-	if (likely(opp)) {
-		pstate = opp->required_opps[i]->level;
-		if (pstate == OPP_LEVEL_UNSET)
-			return 0;
-	}
-
-	ret = dev_pm_domain_set_performance_state(pd_dev, pstate);
-	if (ret) {
-		dev_err(dev, "Failed to set performance state of %s: %d (%d)\n",
-			dev_name(pd_dev), pstate, ret);
-	}
-
-	return ret;
-}
-
-static int _opp_set_required_opps_generic(struct device *dev,
-	struct opp_table *opp_table, struct dev_pm_opp *opp, bool scaling_down)
-{
-	dev_err(dev, "setting required-opps isn't supported for non-genpd devices\n");
-	return -ENOENT;
-}
-
-static int _opp_set_required_opps_genpd(struct device *dev,
-	struct opp_table *opp_table, struct dev_pm_opp *opp, bool scaling_down)
+/* This is only called for PM domain for now */
+static int _set_required_opps(struct device *dev, struct opp_table *opp_table,
+			      struct dev_pm_opp *opp, bool up)
 {
-	struct device **genpd_virt_devs = opp_table->genpd_virt_devs;
+	struct device **devs = opp_table->required_devs;
 	int index, target, delta, ret;
 
-	if (!genpd_virt_devs)
+	if (!devs)
 		return 0;
 
+	/* required-opps not fully initialized yet */
+	if (lazy_linking_pending(opp_table))
+		return -EBUSY;
+
 	/* Scaling up? Set required OPPs in normal order, else reverse */
-	if (!scaling_down) {
+	if (up) {
 		index = 0;
 		target = opp_table->required_opp_count;
 		delta = 1;
@@ -1106,9 +1080,11 @@ static int _opp_set_required_opps_genpd(struct device *dev,
 	}
 
 	while (index != target) {
-		ret = _set_performance_state(dev, genpd_virt_devs[index], opp, index);
-		if (ret)
-			return ret;
+		if (devs[index]) {
+			ret = dev_pm_opp_set_opp(devs[index], opp->required_opps[index]);
+			if (ret)
+				return ret;
+		}
 
 		index += delta;
 	}
@@ -1116,34 +1092,6 @@ static int _opp_set_required_opps_genpd(struct device *dev,
 	return 0;
 }
 
-/* This is only called for PM domain for now */
-static int _set_required_opps(struct device *dev, struct opp_table *opp_table,
-			      struct dev_pm_opp *opp, bool up)
-{
-	/* required-opps not fully initialized yet */
-	if (lazy_linking_pending(opp_table))
-		return -EBUSY;
-
-	if (opp_table->set_required_opps)
-		return opp_table->set_required_opps(dev, opp_table, opp, up);
-
-	return 0;
-}
-
-/* Update set_required_opps handler */
-void _update_set_required_opps(struct opp_table *opp_table)
-{
-	/* Already set */
-	if (opp_table->set_required_opps)
-		return;
-
-	/* All required OPPs will belong to genpd or none */
-	if (opp_table->required_opp_tables[0]->is_genpd)
-		opp_table->set_required_opps = _opp_set_required_opps_genpd;
-	else
-		opp_table->set_required_opps = _opp_set_required_opps_generic;
-}
-
 static int _set_opp_level(struct device *dev, struct opp_table *opp_table,
 			  struct dev_pm_opp *opp)
 {
@@ -2406,19 +2354,13 @@ static void _opp_detach_genpd(struct opp_table *opp_table)
 {
 	int index;
 
-	if (!opp_table->genpd_virt_devs)
-		return;
-
 	for (index = 0; index < opp_table->required_opp_count; index++) {
-		if (!opp_table->genpd_virt_devs[index])
+		if (!opp_table->required_devs[index])
 			continue;
 
-		dev_pm_domain_detach(opp_table->genpd_virt_devs[index], false);
-		opp_table->genpd_virt_devs[index] = NULL;
+		dev_pm_domain_detach(opp_table->required_devs[index], false);
+		opp_table->required_devs[index] = NULL;
 	}
-
-	kfree(opp_table->genpd_virt_devs);
-	opp_table->genpd_virt_devs = NULL;
 }
 
 /*
@@ -2445,14 +2387,14 @@ static int _opp_attach_genpd(struct opp_table *opp_table, struct device *dev,
 	int index = 0, ret = -EINVAL;
 	const char * const *name = names;
 
-	if (opp_table->genpd_virt_devs)
-		return 0;
+	if (!opp_table->required_devs) {
+		dev_err(dev, "Required OPPs not available, can't attach genpd\n");
+		return -EINVAL;
+	}
 
-	opp_table->genpd_virt_devs = kcalloc(opp_table->required_opp_count,
-					     sizeof(*opp_table->genpd_virt_devs),
-					     GFP_KERNEL);
-	if (!opp_table->genpd_virt_devs)
-		return -ENOMEM;
+	/* Checking only the first one is enough ? */
+	if (opp_table->required_devs[0])
+		return 0;
 
 	while (*name) {
 		if (index >= opp_table->required_opp_count) {
@@ -2468,13 +2410,25 @@ static int _opp_attach_genpd(struct opp_table *opp_table, struct device *dev,
 			goto err;
 		}
 
-		opp_table->genpd_virt_devs[index] = virt_dev;
+		/*
+		 * Add the virtual genpd device as a user of the OPP table, so
+		 * we can call dev_pm_opp_set_opp() on it directly.
+		 *
+		 * This will be automatically removed when the OPP table is
+		 * removed, don't need to handle that here.
+		 */
+		if (!_add_opp_dev(virt_dev, opp_table->required_opp_tables[index])) {
+			ret = -ENOMEM;
+			goto err;
+		}
+
+		opp_table->required_devs[index] = virt_dev;
 		index++;
 		name++;
 	}
 
 	if (virt_devs)
-		*virt_devs = opp_table->genpd_virt_devs;
+		*virt_devs = opp_table->required_devs;
 
 	return 0;
 
@@ -2484,10 +2438,42 @@ err:
 
 }
 
+static int _opp_set_required_devs(struct opp_table *opp_table,
+				  struct device *dev,
+				  struct device **required_devs)
+{
+	int i;
+
+	if (!opp_table->required_devs) {
+		dev_err(dev, "Required OPPs not available, can't set required devs\n");
+		return -EINVAL;
+	}
+
+	/* Another device that shares the OPP table has set the required devs ? */
+	if (opp_table->required_devs[0])
+		return 0;
+
+	for (i = 0; i < opp_table->required_opp_count; i++)
+		opp_table->required_devs[i] = required_devs[i];
+
+	return 0;
+}
+
+static void _opp_put_required_devs(struct opp_table *opp_table)
+{
+	int i;
+
+	for (i = 0; i < opp_table->required_opp_count; i++)
+		opp_table->required_devs[i] = NULL;
+}
+
 static void _opp_clear_config(struct opp_config_data *data)
 {
-	if (data->flags & OPP_CONFIG_GENPD)
+	if (data->flags & OPP_CONFIG_REQUIRED_DEVS)
+		_opp_put_required_devs(data->opp_table);
+	else if (data->flags & OPP_CONFIG_GENPD)
 		_opp_detach_genpd(data->opp_table);
+
 	if (data->flags & OPP_CONFIG_REGULATOR)
 		_opp_put_regulators(data->opp_table);
 	if (data->flags & OPP_CONFIG_SUPPORTED_HW)
@@ -2601,12 +2587,22 @@ int dev_pm_opp_set_config(struct device *dev, struct dev_pm_opp_config *config)
 
 	/* Attach genpds */
 	if (config->genpd_names) {
+		if (config->required_devs)
+			goto err;
+
 		ret = _opp_attach_genpd(opp_table, dev, config->genpd_names,
 					config->virt_devs);
 		if (ret)
 			goto err;
 
 		data->flags |= OPP_CONFIG_GENPD;
+	} else if (config->required_devs) {
+		ret = _opp_set_required_devs(opp_table, dev,
+					     config->required_devs);
+		if (ret)
+			goto err;
+
+		data->flags |= OPP_CONFIG_REQUIRED_DEVS;
 	}
 
 	ret = xa_alloc(&opp_configs, &id, data, XA_LIMIT(1, INT_MAX),
diff --git a/drivers/opp/of.c b/drivers/opp/of.c
index 4cdeeab5ceee..5a7e294e56b7 100644
--- a/drivers/opp/of.c
+++ b/drivers/opp/of.c
@@ -165,7 +165,7 @@ static void _opp_table_alloc_required_tables(struct opp_table *opp_table,
 	struct opp_table **required_opp_tables;
 	struct device_node *required_np, *np;
 	bool lazy = false;
-	int count, i;
+	int count, i, size;
 
 	/* Traversing the first OPP node is all we need */
 	np = of_get_next_available_child(opp_np, NULL);
@@ -179,12 +179,13 @@ static void _opp_table_alloc_required_tables(struct opp_table *opp_table,
 	if (count <= 0)
 		goto put_np;
 
-	required_opp_tables = kcalloc(count, sizeof(*required_opp_tables),
-				      GFP_KERNEL);
+	size = sizeof(*required_opp_tables) + sizeof(*opp_table->required_devs);
+	required_opp_tables = kcalloc(count, size, GFP_KERNEL);
 	if (!required_opp_tables)
 		goto put_np;
 
 	opp_table->required_opp_tables = required_opp_tables;
+	opp_table->required_devs = (void *)(required_opp_tables + count);
 	opp_table->required_opp_count = count;
 
 	for (i = 0; i < count; i++) {
@@ -208,8 +209,6 @@ static void _opp_table_alloc_required_tables(struct opp_table *opp_table,
 		mutex_lock(&opp_table_lock);
 		list_add(&opp_table->lazy, &lazy_opp_tables);
 		mutex_unlock(&opp_table_lock);
-	} else {
-		_update_set_required_opps(opp_table);
 	}
 
 	goto put_np;
@@ -332,9 +331,14 @@ static int _link_required_opps(struct dev_pm_opp *opp, struct opp_table *opp_tab
 	 *
 	 * Just update the `level` with the right value, which
 	 * dev_pm_opp_set_opp() will take care of in the normal path itself.
+	 *
+	 * There is another case though, where a genpd's OPP table has
+	 * required-opps set to a parent genpd. The OPP core expects the user to
+	 * set the respective required `struct device` pointer via
+	 * dev_pm_opp_set_config().
 	 */
 	if (required_table->is_genpd && opp_table->required_opp_count == 1 &&
-	    !opp_table->genpd_virt_devs) {
+	    !opp_table->required_devs[0]) {
 		if (!WARN_ON(opp->level != OPP_LEVEL_UNSET))
 			opp->level = opp->required_opps[0]->level;
 	}
@@ -447,7 +451,6 @@ static void lazy_link_required_opp_table(struct opp_table *new_table)
 
 		/* All required opp-tables found, remove from lazy list */
 		if (!lazy) {
-			_update_set_required_opps(opp_table);
 			list_del_init(&opp_table->lazy);
 
 			list_for_each_entry(opp, &opp_table->opp_list, node)
diff --git a/drivers/opp/opp.h b/drivers/opp/opp.h
index 08366f90f16b..23dcb2fbf8c3 100644
--- a/drivers/opp/opp.h
+++ b/drivers/opp/opp.h
@@ -35,6 +35,7 @@ extern struct list_head opp_tables;
 #define OPP_CONFIG_PROP_NAME		BIT(3)
 #define OPP_CONFIG_SUPPORTED_HW		BIT(4)
 #define OPP_CONFIG_GENPD		BIT(5)
+#define OPP_CONFIG_REQUIRED_DEVS	BIT(6)
 
 /**
  * struct opp_config_data - data for set config operations
@@ -160,9 +161,9 @@ enum opp_table_access {
  * @rate_clk_single: Currently configured frequency for single clk.
  * @current_opp: Currently configured OPP for the table.
  * @suspend_opp: Pointer to OPP to be used during device suspend.
- * @genpd_virt_devs: List of virtual devices for multiple genpd support.
  * @required_opp_tables: List of device OPP tables that are required by OPPs in
  *		this table.
+ * @required_devs: List of devices for required OPP tables.
  * @required_opp_count: Number of required devices.
  * @supported_hw: Array of version number to support.
  * @supported_hw_count: Number of elements in supported_hw array.
@@ -180,7 +181,6 @@ enum opp_table_access {
  * @path_count: Number of interconnect paths
  * @enabled: Set to true if the device's resources are enabled/configured.
  * @is_genpd: Marks if the OPP table belongs to a genpd.
- * @set_required_opps: Helper responsible to set required OPPs.
  * @dentry:	debugfs dentry pointer of the real device directory (not links).
  * @dentry_name: Name of the real dentry.
  *
@@ -211,8 +211,8 @@ struct opp_table {
 	struct dev_pm_opp *current_opp;
 	struct dev_pm_opp *suspend_opp;
 
-	struct device **genpd_virt_devs;
 	struct opp_table **required_opp_tables;
+	struct device **required_devs;
 	unsigned int required_opp_count;
 
 	unsigned int *supported_hw;
@@ -229,8 +229,6 @@ struct opp_table {
 	unsigned int path_count;
 	bool enabled;
 	bool is_genpd;
-	int (*set_required_opps)(struct device *dev,
-		struct opp_table *opp_table, struct dev_pm_opp *opp, bool scaling_down);
 
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *dentry;
diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h
index af53101a1383..81dff7facdc9 100644
--- a/include/linux/pm_opp.h
+++ b/include/linux/pm_opp.h
@@ -74,8 +74,10 @@ typedef int (*config_clks_t)(struct device *dev, struct opp_table *opp_table,
  * @supported_hw_count: Number of elements in the array.
  * @regulator_names: Array of pointers to the names of the regulator, NULL terminated.
  * @genpd_names: Null terminated array of pointers containing names of genpd to
- *		 attach.
- * @virt_devs: Pointer to return the array of virtual devices.
+ *		attach. Mutually exclusive with required_devs.
+ * @virt_devs: Pointer to return the array of genpd virtual devices. Mutually
+ *		exclusive with required_devs.
+ * @required_devs: Required OPP devices. Mutually exclusive with genpd_names/virt_devs.
  *
  * This structure contains platform specific OPP configurations for the device.
  */
@@ -90,6 +92,7 @@ struct dev_pm_opp_config {
 	const char * const *regulator_names;
 	const char * const *genpd_names;
 	struct device ***virt_devs;
+	struct device **required_devs;
 };
 
 #define OPP_LEVEL_UNSET			U32_MAX
-- 
cgit v1.2.3


From 45b3fae4675dc1d4ee2d7aefa19d85ee4f891377 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Sat, 25 Nov 2023 15:33:58 -0600
Subject: neighbour: Fix __randomize_layout crash in struct neighbour

Previously, one-element and zero-length arrays were treated as true
flexible arrays, even though they are actually "fake" flex arrays.
The __randomize_layout would leave them untouched at the end of the
struct, similarly to proper C99 flex-array members.

However, this approach changed with commit 1ee60356c2dc ("gcc-plugins:
randstruct: Only warn about true flexible arrays"). Now, only C99
flexible-array members will remain untouched at the end of the struct,
while one-element and zero-length arrays will be subject to randomization.

Fix a `__randomize_layout` crash in `struct neighbour` by transforming
zero-length array `primary_key` into a proper C99 flexible-array member.

Fixes: 1ee60356c2dc ("gcc-plugins: randstruct: Only warn about true flexible arrays")
Closes: https://lore.kernel.org/linux-hardening/20231124102458.GB1503258@e124191.cambridge.arm.com/
Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Tested-by: Joey Gouly <joey.gouly@arm.com>
Link: https://lore.kernel.org/r/ZWJoRsJGnCPdJ3+2@work
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/neighbour.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 07022bb0d44d..0d28172193fa 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -162,7 +162,7 @@ struct neighbour {
 	struct rcu_head		rcu;
 	struct net_device	*dev;
 	netdevice_tracker	dev_tracker;
-	u8			primary_key[0];
+	u8			primary_key[];
 } __randomize_layout;
 
 struct neigh_ops {
-- 
cgit v1.2.3


From 3652117f854819a148ff0fbe4492587d3520b5e5 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Wed, 22 Nov 2023 13:48:23 +0100
Subject: eventfd: simplify eventfd_signal()

Ever since the eventfd type was introduced back in 2007 in commit
e1ad7468c77d ("signal/timer/event: eventfd core") the eventfd_signal()
function only ever passed 1 as a value for @n. There's no point in
keeping that additional argument.

Link: https://lore.kernel.org/r/20231122-vfs-eventfd-signal-v2-2-bd549b14ce0c@kernel.org
Acked-by: Xu Yilun <yilun.xu@intel.com>
Acked-by: Andrew Donnellan <ajd@linux.ibm.com> # ocxl
Acked-by: Eric Farman <farman@linux.ibm.com>  # s390
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 arch/x86/kvm/hyperv.c                     |  2 +-
 arch/x86/kvm/xen.c                        |  2 +-
 drivers/accel/habanalabs/common/device.c  |  2 +-
 drivers/fpga/dfl.c                        |  2 +-
 drivers/gpu/drm/drm_syncobj.c             |  6 +++---
 drivers/gpu/drm/i915/gvt/interrupt.c      |  2 +-
 drivers/infiniband/hw/mlx5/devx.c         |  2 +-
 drivers/misc/ocxl/file.c                  |  2 +-
 drivers/s390/cio/vfio_ccw_chp.c           |  2 +-
 drivers/s390/cio/vfio_ccw_drv.c           |  4 ++--
 drivers/s390/cio/vfio_ccw_ops.c           |  6 +++---
 drivers/s390/crypto/vfio_ap_ops.c         |  2 +-
 drivers/usb/gadget/function/f_fs.c        |  4 ++--
 drivers/vdpa/vdpa_user/vduse_dev.c        |  6 +++---
 drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c    |  2 +-
 drivers/vfio/pci/vfio_pci_core.c          |  6 +++---
 drivers/vfio/pci/vfio_pci_intrs.c         | 12 ++++++------
 drivers/vfio/platform/vfio_platform_irq.c |  4 ++--
 drivers/vhost/vdpa.c                      |  4 ++--
 drivers/vhost/vhost.c                     | 10 +++++-----
 drivers/vhost/vhost.h                     |  2 +-
 drivers/virt/acrn/ioeventfd.c             |  2 +-
 drivers/xen/privcmd.c                     |  2 +-
 fs/aio.c                                  |  2 +-
 fs/eventfd.c                              | 11 ++++-------
 include/linux/eventfd.h                   |  4 ++--
 mm/memcontrol.c                           | 10 +++++-----
 mm/vmpressure.c                           |  2 +-
 samples/vfio-mdev/mtty.c                  |  4 ++--
 virt/kvm/eventfd.c                        |  4 ++--
 30 files changed, 61 insertions(+), 64 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 238afd7335e4..4943f6b2bbee 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -2388,7 +2388,7 @@ static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *h
 	if (!eventfd)
 		return HV_STATUS_INVALID_PORT_ID;
 
-	eventfd_signal(eventfd, 1);
+	eventfd_signal(eventfd);
 	return HV_STATUS_SUCCESS;
 }
 
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index e53fad915a62..523bb6df5ac9 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -2088,7 +2088,7 @@ static bool kvm_xen_hcall_evtchn_send(struct kvm_vcpu *vcpu, u64 param, u64 *r)
 		if (ret < 0 && ret != -ENOTCONN)
 			return false;
 	} else {
-		eventfd_signal(evtchnfd->deliver.eventfd.ctx, 1);
+		eventfd_signal(evtchnfd->deliver.eventfd.ctx);
 	}
 
 	*r = 0;
diff --git a/drivers/accel/habanalabs/common/device.c b/drivers/accel/habanalabs/common/device.c
index 9711e8fc979d..3a89644f087c 100644
--- a/drivers/accel/habanalabs/common/device.c
+++ b/drivers/accel/habanalabs/common/device.c
@@ -2044,7 +2044,7 @@ static void hl_notifier_event_send(struct hl_notifier_event *notifier_event, u64
 	notifier_event->events_mask |= event_mask;
 
 	if (notifier_event->eventfd)
-		eventfd_signal(notifier_event->eventfd, 1);
+		eventfd_signal(notifier_event->eventfd);
 
 	mutex_unlock(&notifier_event->lock);
 }
diff --git a/drivers/fpga/dfl.c b/drivers/fpga/dfl.c
index dd7a783d53b5..e73f88050f08 100644
--- a/drivers/fpga/dfl.c
+++ b/drivers/fpga/dfl.c
@@ -1872,7 +1872,7 @@ static irqreturn_t dfl_irq_handler(int irq, void *arg)
 {
 	struct eventfd_ctx *trigger = arg;
 
-	eventfd_signal(trigger, 1);
+	eventfd_signal(trigger);
 	return IRQ_HANDLED;
 }
 
diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c
index 01da6789d044..b9cc62982196 100644
--- a/drivers/gpu/drm/drm_syncobj.c
+++ b/drivers/gpu/drm/drm_syncobj.c
@@ -1365,7 +1365,7 @@ static void syncobj_eventfd_entry_fence_func(struct dma_fence *fence,
 	struct syncobj_eventfd_entry *entry =
 		container_of(cb, struct syncobj_eventfd_entry, fence_cb);
 
-	eventfd_signal(entry->ev_fd_ctx, 1);
+	eventfd_signal(entry->ev_fd_ctx);
 	syncobj_eventfd_entry_free(entry);
 }
 
@@ -1388,13 +1388,13 @@ syncobj_eventfd_entry_func(struct drm_syncobj *syncobj,
 	entry->fence = fence;
 
 	if (entry->flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE) {
-		eventfd_signal(entry->ev_fd_ctx, 1);
+		eventfd_signal(entry->ev_fd_ctx);
 		syncobj_eventfd_entry_free(entry);
 	} else {
 		ret = dma_fence_add_callback(fence, &entry->fence_cb,
 					     syncobj_eventfd_entry_fence_func);
 		if (ret == -ENOENT) {
-			eventfd_signal(entry->ev_fd_ctx, 1);
+			eventfd_signal(entry->ev_fd_ctx);
 			syncobj_eventfd_entry_free(entry);
 		}
 	}
diff --git a/drivers/gpu/drm/i915/gvt/interrupt.c b/drivers/gpu/drm/i915/gvt/interrupt.c
index b32ba5f2b240..c8e7dfc9f791 100644
--- a/drivers/gpu/drm/i915/gvt/interrupt.c
+++ b/drivers/gpu/drm/i915/gvt/interrupt.c
@@ -453,7 +453,7 @@ static void inject_virtual_interrupt(struct intel_vgpu *vgpu)
 	if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
 		return;
 	if (vgpu->msi_trigger)
-		eventfd_signal(vgpu->msi_trigger, 1);
+		eventfd_signal(vgpu->msi_trigger);
 }
 
 static void propagate_event(struct intel_gvt_irq *irq,
diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c
index 8ba53edf2311..869369cb5b5f 100644
--- a/drivers/infiniband/hw/mlx5/devx.c
+++ b/drivers/infiniband/hw/mlx5/devx.c
@@ -2498,7 +2498,7 @@ static void dispatch_event_fd(struct list_head *fd_list,
 
 	list_for_each_entry_rcu(item, fd_list, xa_list) {
 		if (item->eventfd)
-			eventfd_signal(item->eventfd, 1);
+			eventfd_signal(item->eventfd);
 		else
 			deliver_event(item, data);
 	}
diff --git a/drivers/misc/ocxl/file.c b/drivers/misc/ocxl/file.c
index ac69b7f361f5..7eb74711ac96 100644
--- a/drivers/misc/ocxl/file.c
+++ b/drivers/misc/ocxl/file.c
@@ -184,7 +184,7 @@ static irqreturn_t irq_handler(void *private)
 {
 	struct eventfd_ctx *ev_ctx = private;
 
-	eventfd_signal(ev_ctx, 1);
+	eventfd_signal(ev_ctx);
 	return IRQ_HANDLED;
 }
 
diff --git a/drivers/s390/cio/vfio_ccw_chp.c b/drivers/s390/cio/vfio_ccw_chp.c
index d3f3a611f95b..38c176cf6295 100644
--- a/drivers/s390/cio/vfio_ccw_chp.c
+++ b/drivers/s390/cio/vfio_ccw_chp.c
@@ -115,7 +115,7 @@ static ssize_t vfio_ccw_crw_region_read(struct vfio_ccw_private *private,
 
 	/* Notify the guest if more CRWs are on our queue */
 	if (!list_empty(&private->crw) && private->crw_trigger)
-		eventfd_signal(private->crw_trigger, 1);
+		eventfd_signal(private->crw_trigger);
 
 	return ret;
 }
diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c
index 43601816ea4e..bfb35cfce1ef 100644
--- a/drivers/s390/cio/vfio_ccw_drv.c
+++ b/drivers/s390/cio/vfio_ccw_drv.c
@@ -112,7 +112,7 @@ void vfio_ccw_sch_io_todo(struct work_struct *work)
 		private->state = VFIO_CCW_STATE_IDLE;
 
 	if (private->io_trigger)
-		eventfd_signal(private->io_trigger, 1);
+		eventfd_signal(private->io_trigger);
 }
 
 void vfio_ccw_crw_todo(struct work_struct *work)
@@ -122,7 +122,7 @@ void vfio_ccw_crw_todo(struct work_struct *work)
 	private = container_of(work, struct vfio_ccw_private, crw_work);
 
 	if (!list_empty(&private->crw) && private->crw_trigger)
-		eventfd_signal(private->crw_trigger, 1);
+		eventfd_signal(private->crw_trigger);
 }
 
 /*
diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c
index cba4971618ff..ea532a8a4a0c 100644
--- a/drivers/s390/cio/vfio_ccw_ops.c
+++ b/drivers/s390/cio/vfio_ccw_ops.c
@@ -421,7 +421,7 @@ static int vfio_ccw_mdev_set_irqs(struct vfio_ccw_private *private,
 	case VFIO_IRQ_SET_DATA_NONE:
 	{
 		if (*ctx)
-			eventfd_signal(*ctx, 1);
+			eventfd_signal(*ctx);
 		return 0;
 	}
 	case VFIO_IRQ_SET_DATA_BOOL:
@@ -432,7 +432,7 @@ static int vfio_ccw_mdev_set_irqs(struct vfio_ccw_private *private,
 			return -EFAULT;
 
 		if (trigger && *ctx)
-			eventfd_signal(*ctx, 1);
+			eventfd_signal(*ctx);
 		return 0;
 	}
 	case VFIO_IRQ_SET_DATA_EVENTFD:
@@ -612,7 +612,7 @@ static void vfio_ccw_mdev_request(struct vfio_device *vdev, unsigned int count)
 					       "Relaying device request to user (#%u)\n",
 					       count);
 
-		eventfd_signal(private->req_trigger, 1);
+		eventfd_signal(private->req_trigger);
 	} else if (count == 0) {
 		dev_notice(dev,
 			   "No device request channel registered, blocked until released by user\n");
diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c
index 4db538a55192..542b5be73a6a 100644
--- a/drivers/s390/crypto/vfio_ap_ops.c
+++ b/drivers/s390/crypto/vfio_ap_ops.c
@@ -1794,7 +1794,7 @@ static void vfio_ap_mdev_request(struct vfio_device *vdev, unsigned int count)
 					       "Relaying device request to user (#%u)\n",
 					       count);
 
-		eventfd_signal(matrix_mdev->req_trigger, 1);
+		eventfd_signal(matrix_mdev->req_trigger);
 	} else if (count == 0) {
 		dev_notice(dev,
 			   "No device request registered, blocked until released by user\n");
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index efe3e3b85769..fdd0fc7b8f25 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -831,7 +831,7 @@ static void ffs_user_copy_worker(struct work_struct *work)
 	io_data->kiocb->ki_complete(io_data->kiocb, ret);
 
 	if (io_data->ffs->ffs_eventfd && !kiocb_has_eventfd)
-		eventfd_signal(io_data->ffs->ffs_eventfd, 1);
+		eventfd_signal(io_data->ffs->ffs_eventfd);
 
 	if (io_data->read)
 		kfree(io_data->to_free);
@@ -2738,7 +2738,7 @@ static void __ffs_event_add(struct ffs_data *ffs,
 	ffs->ev.types[ffs->ev.count++] = type;
 	wake_up_locked(&ffs->ev.waitq);
 	if (ffs->ffs_eventfd)
-		eventfd_signal(ffs->ffs_eventfd, 1);
+		eventfd_signal(ffs->ffs_eventfd);
 }
 
 static void ffs_event_add(struct ffs_data *ffs,
diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c
index 0ddd4b8abecb..6cb5ce4a8b9a 100644
--- a/drivers/vdpa/vdpa_user/vduse_dev.c
+++ b/drivers/vdpa/vdpa_user/vduse_dev.c
@@ -493,7 +493,7 @@ static void vduse_vq_kick(struct vduse_virtqueue *vq)
 		goto unlock;
 
 	if (vq->kickfd)
-		eventfd_signal(vq->kickfd, 1);
+		eventfd_signal(vq->kickfd);
 	else
 		vq->kicked = true;
 unlock:
@@ -911,7 +911,7 @@ static int vduse_kickfd_setup(struct vduse_dev *dev,
 		eventfd_ctx_put(vq->kickfd);
 	vq->kickfd = ctx;
 	if (vq->ready && vq->kicked && vq->kickfd) {
-		eventfd_signal(vq->kickfd, 1);
+		eventfd_signal(vq->kickfd);
 		vq->kicked = false;
 	}
 	spin_unlock(&vq->kick_lock);
@@ -960,7 +960,7 @@ static bool vduse_vq_signal_irqfd(struct vduse_virtqueue *vq)
 
 	spin_lock_irq(&vq->irq_lock);
 	if (vq->ready && vq->cb.trigger) {
-		eventfd_signal(vq->cb.trigger, 1);
+		eventfd_signal(vq->cb.trigger);
 		signal = true;
 	}
 	spin_unlock_irq(&vq->irq_lock);
diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c b/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c
index c51229fccbd6..d62fbfff20b8 100644
--- a/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c
+++ b/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c
@@ -54,7 +54,7 @@ static irqreturn_t vfio_fsl_mc_irq_handler(int irq_num, void *arg)
 {
 	struct vfio_fsl_mc_irq *mc_irq = (struct vfio_fsl_mc_irq *)arg;
 
-	eventfd_signal(mc_irq->trigger, 1);
+	eventfd_signal(mc_irq->trigger);
 	return IRQ_HANDLED;
 }
 
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 1929103ee59a..1cbc990d42e0 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -443,7 +443,7 @@ static int vfio_pci_core_runtime_resume(struct device *dev)
 	 */
 	down_write(&vdev->memory_lock);
 	if (vdev->pm_wake_eventfd_ctx) {
-		eventfd_signal(vdev->pm_wake_eventfd_ctx, 1);
+		eventfd_signal(vdev->pm_wake_eventfd_ctx);
 		__vfio_pci_runtime_pm_exit(vdev);
 	}
 	up_write(&vdev->memory_lock);
@@ -1883,7 +1883,7 @@ void vfio_pci_core_request(struct vfio_device *core_vdev, unsigned int count)
 			pci_notice_ratelimited(pdev,
 				"Relaying device request to user (#%u)\n",
 				count);
-		eventfd_signal(vdev->req_trigger, 1);
+		eventfd_signal(vdev->req_trigger);
 	} else if (count == 0) {
 		pci_warn(pdev,
 			"No device request channel registered, blocked until released by user\n");
@@ -2302,7 +2302,7 @@ pci_ers_result_t vfio_pci_core_aer_err_detected(struct pci_dev *pdev,
 	mutex_lock(&vdev->igate);
 
 	if (vdev->err_trigger)
-		eventfd_signal(vdev->err_trigger, 1);
+		eventfd_signal(vdev->err_trigger);
 
 	mutex_unlock(&vdev->igate);
 
diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c
index cbb4bcbfbf83..237beac83809 100644
--- a/drivers/vfio/pci/vfio_pci_intrs.c
+++ b/drivers/vfio/pci/vfio_pci_intrs.c
@@ -94,7 +94,7 @@ static void vfio_send_intx_eventfd(void *opaque, void *unused)
 		ctx = vfio_irq_ctx_get(vdev, 0);
 		if (WARN_ON_ONCE(!ctx))
 			return;
-		eventfd_signal(ctx->trigger, 1);
+		eventfd_signal(ctx->trigger);
 	}
 }
 
@@ -342,7 +342,7 @@ static irqreturn_t vfio_msihandler(int irq, void *arg)
 {
 	struct eventfd_ctx *trigger = arg;
 
-	eventfd_signal(trigger, 1);
+	eventfd_signal(trigger);
 	return IRQ_HANDLED;
 }
 
@@ -689,11 +689,11 @@ static int vfio_pci_set_msi_trigger(struct vfio_pci_core_device *vdev,
 		if (!ctx)
 			continue;
 		if (flags & VFIO_IRQ_SET_DATA_NONE) {
-			eventfd_signal(ctx->trigger, 1);
+			eventfd_signal(ctx->trigger);
 		} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
 			uint8_t *bools = data;
 			if (bools[i - start])
-				eventfd_signal(ctx->trigger, 1);
+				eventfd_signal(ctx->trigger);
 		}
 	}
 	return 0;
@@ -707,7 +707,7 @@ static int vfio_pci_set_ctx_trigger_single(struct eventfd_ctx **ctx,
 	if (flags & VFIO_IRQ_SET_DATA_NONE) {
 		if (*ctx) {
 			if (count) {
-				eventfd_signal(*ctx, 1);
+				eventfd_signal(*ctx);
 			} else {
 				eventfd_ctx_put(*ctx);
 				*ctx = NULL;
@@ -722,7 +722,7 @@ static int vfio_pci_set_ctx_trigger_single(struct eventfd_ctx **ctx,
 
 		trigger = *(uint8_t *)data;
 		if (trigger && *ctx)
-			eventfd_signal(*ctx, 1);
+			eventfd_signal(*ctx);
 
 		return 0;
 	} else if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
diff --git a/drivers/vfio/platform/vfio_platform_irq.c b/drivers/vfio/platform/vfio_platform_irq.c
index 665197caed89..61a1bfb68ac7 100644
--- a/drivers/vfio/platform/vfio_platform_irq.c
+++ b/drivers/vfio/platform/vfio_platform_irq.c
@@ -155,7 +155,7 @@ static irqreturn_t vfio_automasked_irq_handler(int irq, void *dev_id)
 	spin_unlock_irqrestore(&irq_ctx->lock, flags);
 
 	if (ret == IRQ_HANDLED)
-		eventfd_signal(irq_ctx->trigger, 1);
+		eventfd_signal(irq_ctx->trigger);
 
 	return ret;
 }
@@ -164,7 +164,7 @@ static irqreturn_t vfio_irq_handler(int irq, void *dev_id)
 {
 	struct vfio_platform_irq *irq_ctx = dev_id;
 
-	eventfd_signal(irq_ctx->trigger, 1);
+	eventfd_signal(irq_ctx->trigger);
 
 	return IRQ_HANDLED;
 }
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index 30df5c58db73..8d9f958946d6 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -178,7 +178,7 @@ static irqreturn_t vhost_vdpa_virtqueue_cb(void *private)
 	struct eventfd_ctx *call_ctx = vq->call_ctx.ctx;
 
 	if (call_ctx)
-		eventfd_signal(call_ctx, 1);
+		eventfd_signal(call_ctx);
 
 	return IRQ_HANDLED;
 }
@@ -189,7 +189,7 @@ static irqreturn_t vhost_vdpa_config_cb(void *private)
 	struct eventfd_ctx *config_ctx = v->config_ctx;
 
 	if (config_ctx)
-		eventfd_signal(config_ctx, 1);
+		eventfd_signal(config_ctx);
 
 	return IRQ_HANDLED;
 }
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index e0c181ad17e3..045f666b4f12 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -2248,7 +2248,7 @@ int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
 		len -= l;
 		if (!len) {
 			if (vq->log_ctx)
-				eventfd_signal(vq->log_ctx, 1);
+				eventfd_signal(vq->log_ctx);
 			return 0;
 		}
 	}
@@ -2271,7 +2271,7 @@ static int vhost_update_used_flags(struct vhost_virtqueue *vq)
 		log_used(vq, (used - (void __user *)vq->used),
 			 sizeof vq->used->flags);
 		if (vq->log_ctx)
-			eventfd_signal(vq->log_ctx, 1);
+			eventfd_signal(vq->log_ctx);
 	}
 	return 0;
 }
@@ -2289,7 +2289,7 @@ static int vhost_update_avail_event(struct vhost_virtqueue *vq)
 		log_used(vq, (used - (void __user *)vq->used),
 			 sizeof *vhost_avail_event(vq));
 		if (vq->log_ctx)
-			eventfd_signal(vq->log_ctx, 1);
+			eventfd_signal(vq->log_ctx);
 	}
 	return 0;
 }
@@ -2715,7 +2715,7 @@ int vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads,
 		log_used(vq, offsetof(struct vring_used, idx),
 			 sizeof vq->used->idx);
 		if (vq->log_ctx)
-			eventfd_signal(vq->log_ctx, 1);
+			eventfd_signal(vq->log_ctx);
 	}
 	return r;
 }
@@ -2763,7 +2763,7 @@ void vhost_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 {
 	/* Signal the Guest tell them we used something up. */
 	if (vq->call_ctx.ctx && vhost_notify(dev, vq))
-		eventfd_signal(vq->call_ctx.ctx, 1);
+		eventfd_signal(vq->call_ctx.ctx);
 }
 EXPORT_SYMBOL_GPL(vhost_signal);
 
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index f60d5f7bef94..9e942fcda5c3 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -249,7 +249,7 @@ void vhost_iotlb_map_free(struct vhost_iotlb *iotlb,
 #define vq_err(vq, fmt, ...) do {                                  \
 		pr_debug(pr_fmt(fmt), ##__VA_ARGS__);       \
 		if ((vq)->error_ctx)                               \
-				eventfd_signal((vq)->error_ctx, 1);\
+				eventfd_signal((vq)->error_ctx);\
 	} while (0)
 
 enum {
diff --git a/drivers/virt/acrn/ioeventfd.c b/drivers/virt/acrn/ioeventfd.c
index ac4037e9f947..4e845c6ca0b5 100644
--- a/drivers/virt/acrn/ioeventfd.c
+++ b/drivers/virt/acrn/ioeventfd.c
@@ -223,7 +223,7 @@ static int acrn_ioeventfd_handler(struct acrn_ioreq_client *client,
 	mutex_lock(&client->vm->ioeventfds_lock);
 	p = hsm_ioeventfd_match(client->vm, addr, val, size, req->type);
 	if (p)
-		eventfd_signal(p->eventfd, 1);
+		eventfd_signal(p->eventfd);
 	mutex_unlock(&client->vm->ioeventfds_lock);
 
 	return 0;
diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index 1ce7f3c7a950..7efc0c62e984 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -1147,7 +1147,7 @@ static irqreturn_t ioeventfd_interrupt(int irq, void *dev_id)
 		if (ioreq->addr == kioeventfd->addr + VIRTIO_MMIO_QUEUE_NOTIFY &&
 		    ioreq->size == kioeventfd->addr_len &&
 		    (ioreq->data & QUEUE_NOTIFY_VQ_MASK) == kioeventfd->vq) {
-			eventfd_signal(kioeventfd->eventfd, 1);
+			eventfd_signal(kioeventfd->eventfd);
 			state = STATE_IORESP_READY;
 			break;
 		}
diff --git a/fs/aio.c b/fs/aio.c
index d02842156b35..7c691cf84cc7 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1166,7 +1166,7 @@ static void aio_complete(struct aio_kiocb *iocb)
 	 * from IRQ context.
 	 */
 	if (iocb->ki_eventfd)
-		eventfd_signal(iocb->ki_eventfd, 1);
+		eventfd_signal(iocb->ki_eventfd);
 
 	/*
 	 * We have to order our ring_info tail store above and test
diff --git a/fs/eventfd.c b/fs/eventfd.c
index 33a918f9566c..d2f7d2d8a351 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -72,22 +72,19 @@ __u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, __poll_t mask)
 }
 
 /**
- * eventfd_signal - Adds @n to the eventfd counter.
+ * eventfd_signal - Increment the event counter
  * @ctx: [in] Pointer to the eventfd context.
- * @n: [in] Value of the counter to be added to the eventfd internal counter.
- *          The value cannot be negative.
  *
  * This function is supposed to be called by the kernel in paths that do not
  * allow sleeping. In this function we allow the counter to reach the ULLONG_MAX
  * value, and we signal this as overflow condition by returning a EPOLLERR
  * to poll(2).
  *
- * Returns the amount by which the counter was incremented.  This will be less
- * than @n if the counter has overflowed.
+ * Returns the amount by which the counter was incremented.
  */
-__u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n)
+__u64 eventfd_signal(struct eventfd_ctx *ctx)
 {
-	return eventfd_signal_mask(ctx, n, 0);
+	return eventfd_signal_mask(ctx, 1, 0);
 }
 EXPORT_SYMBOL_GPL(eventfd_signal);
 
diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h
index b9d83652c097..562089431551 100644
--- a/include/linux/eventfd.h
+++ b/include/linux/eventfd.h
@@ -35,7 +35,7 @@ void eventfd_ctx_put(struct eventfd_ctx *ctx);
 struct file *eventfd_fget(int fd);
 struct eventfd_ctx *eventfd_ctx_fdget(int fd);
 struct eventfd_ctx *eventfd_ctx_fileget(struct file *file);
-__u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n);
+__u64 eventfd_signal(struct eventfd_ctx *ctx);
 __u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, __poll_t mask);
 int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait,
 				  __u64 *cnt);
@@ -58,7 +58,7 @@ static inline struct eventfd_ctx *eventfd_ctx_fdget(int fd)
 	return ERR_PTR(-ENOSYS);
 }
 
-static inline int eventfd_signal(struct eventfd_ctx *ctx, __u64 n)
+static inline int eventfd_signal(struct eventfd_ctx *ctx)
 {
 	return -ENOSYS;
 }
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 774bd6e21e27..dfbb1d3b77b7 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4378,7 +4378,7 @@ static void __mem_cgroup_threshold(struct mem_cgroup *memcg, bool swap)
 	 * only one element of the array here.
 	 */
 	for (; i >= 0 && unlikely(t->entries[i].threshold > usage); i--)
-		eventfd_signal(t->entries[i].eventfd, 1);
+		eventfd_signal(t->entries[i].eventfd);
 
 	/* i = current_threshold + 1 */
 	i++;
@@ -4390,7 +4390,7 @@ static void __mem_cgroup_threshold(struct mem_cgroup *memcg, bool swap)
 	 * only one element of the array here.
 	 */
 	for (; i < t->size && unlikely(t->entries[i].threshold <= usage); i++)
-		eventfd_signal(t->entries[i].eventfd, 1);
+		eventfd_signal(t->entries[i].eventfd);
 
 	/* Update current_threshold */
 	t->current_threshold = i - 1;
@@ -4430,7 +4430,7 @@ static int mem_cgroup_oom_notify_cb(struct mem_cgroup *memcg)
 	spin_lock(&memcg_oom_lock);
 
 	list_for_each_entry(ev, &memcg->oom_notify, list)
-		eventfd_signal(ev->eventfd, 1);
+		eventfd_signal(ev->eventfd);
 
 	spin_unlock(&memcg_oom_lock);
 	return 0;
@@ -4649,7 +4649,7 @@ static int mem_cgroup_oom_register_event(struct mem_cgroup *memcg,
 
 	/* already in OOM ? */
 	if (memcg->under_oom)
-		eventfd_signal(eventfd, 1);
+		eventfd_signal(eventfd);
 	spin_unlock(&memcg_oom_lock);
 
 	return 0;
@@ -4941,7 +4941,7 @@ static void memcg_event_remove(struct work_struct *work)
 	event->unregister_event(memcg, event->eventfd);
 
 	/* Notify userspace the event is going away. */
-	eventfd_signal(event->eventfd, 1);
+	eventfd_signal(event->eventfd);
 
 	eventfd_ctx_put(event->eventfd);
 	kfree(event);
diff --git a/mm/vmpressure.c b/mm/vmpressure.c
index 22c6689d9302..bd5183dfd879 100644
--- a/mm/vmpressure.c
+++ b/mm/vmpressure.c
@@ -169,7 +169,7 @@ static bool vmpressure_event(struct vmpressure *vmpr,
 			continue;
 		if (level < ev->level)
 			continue;
-		eventfd_signal(ev->efd, 1);
+		eventfd_signal(ev->efd);
 		ret = true;
 	}
 	mutex_unlock(&vmpr->events_lock);
diff --git a/samples/vfio-mdev/mtty.c b/samples/vfio-mdev/mtty.c
index 69ba0281f9e0..2284b3751240 100644
--- a/samples/vfio-mdev/mtty.c
+++ b/samples/vfio-mdev/mtty.c
@@ -234,10 +234,10 @@ static void mtty_trigger_interrupt(struct mdev_state *mdev_state)
 
 	if (is_msi(mdev_state)) {
 		if (mdev_state->msi_evtfd)
-			eventfd_signal(mdev_state->msi_evtfd, 1);
+			eventfd_signal(mdev_state->msi_evtfd);
 	} else if (is_intx(mdev_state)) {
 		if (mdev_state->intx_evtfd && !mdev_state->intx_mask) {
-			eventfd_signal(mdev_state->intx_evtfd, 1);
+			eventfd_signal(mdev_state->intx_evtfd);
 			mdev_state->intx_mask = true;
 		}
 	}
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 89912a17f5d5..c0e230f4c3e9 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -61,7 +61,7 @@ static void irqfd_resampler_notify(struct kvm_kernel_irqfd_resampler *resampler)
 
 	list_for_each_entry_srcu(irqfd, &resampler->list, resampler_link,
 				 srcu_read_lock_held(&resampler->kvm->irq_srcu))
-		eventfd_signal(irqfd->resamplefd, 1);
+		eventfd_signal(irqfd->resamplefd);
 }
 
 /*
@@ -786,7 +786,7 @@ ioeventfd_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this, gpa_t addr,
 	if (!ioeventfd_in_range(p, addr, len, val))
 		return -EOPNOTSUPP;
 
-	eventfd_signal(p->eventfd, 1);
+	eventfd_signal(p->eventfd);
 	return 0;
 }
 
-- 
cgit v1.2.3


From 120ae58593630819209a011a3f9c89f73bcc9894 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Wed, 22 Nov 2023 13:48:24 +0100
Subject: eventfd: simplify eventfd_signal_mask()

The eventfd_signal_mask() helper was introduced for io_uring and similar
to eventfd_signal() it always passed 1 for @n. So don't bother with that
argument at all.

Link: https://lore.kernel.org/r/20231122-vfs-eventfd-signal-v2-3-bd549b14ce0c@kernel.org
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/eventfd.c            | 7 ++++---
 include/linux/eventfd.h | 5 ++---
 io_uring/io_uring.c     | 4 ++--
 3 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/fs/eventfd.c b/fs/eventfd.c
index d2f7d2d8a351..41109ba6bbe0 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -43,9 +43,10 @@ struct eventfd_ctx {
 	int id;
 };
 
-__u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, __poll_t mask)
+__u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __poll_t mask)
 {
 	unsigned long flags;
+	__u64 n = 1;
 
 	/*
 	 * Deadlock or stack overflow issues can happen if we recurse here
@@ -68,7 +69,7 @@ __u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, __poll_t mask)
 	current->in_eventfd = 0;
 	spin_unlock_irqrestore(&ctx->wqh.lock, flags);
 
-	return n;
+	return n == 1;
 }
 
 /**
@@ -84,7 +85,7 @@ __u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, __poll_t mask)
  */
 __u64 eventfd_signal(struct eventfd_ctx *ctx)
 {
-	return eventfd_signal_mask(ctx, 1, 0);
+	return eventfd_signal_mask(ctx, 0);
 }
 EXPORT_SYMBOL_GPL(eventfd_signal);
 
diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h
index 562089431551..971943ecb2a6 100644
--- a/include/linux/eventfd.h
+++ b/include/linux/eventfd.h
@@ -36,7 +36,7 @@ struct file *eventfd_fget(int fd);
 struct eventfd_ctx *eventfd_ctx_fdget(int fd);
 struct eventfd_ctx *eventfd_ctx_fileget(struct file *file);
 __u64 eventfd_signal(struct eventfd_ctx *ctx);
-__u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, __poll_t mask);
+__u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __poll_t mask);
 int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait,
 				  __u64 *cnt);
 void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt);
@@ -63,8 +63,7 @@ static inline int eventfd_signal(struct eventfd_ctx *ctx)
 	return -ENOSYS;
 }
 
-static inline int eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n,
-				      unsigned mask)
+static inline int eventfd_signal_mask(struct eventfd_ctx *ctx, __poll_t mask)
 {
 	return -ENOSYS;
 }
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index ed254076c723..70170a41eac4 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -558,7 +558,7 @@ static void io_eventfd_ops(struct rcu_head *rcu)
 	int ops = atomic_xchg(&ev_fd->ops, 0);
 
 	if (ops & BIT(IO_EVENTFD_OP_SIGNAL_BIT))
-		eventfd_signal_mask(ev_fd->cq_ev_fd, 1, EPOLL_URING_WAKE);
+		eventfd_signal_mask(ev_fd->cq_ev_fd, EPOLL_URING_WAKE);
 
 	/* IO_EVENTFD_OP_FREE_BIT may not be set here depending on callback
 	 * ordering in a race but if references are 0 we know we have to free
@@ -594,7 +594,7 @@ static void io_eventfd_signal(struct io_ring_ctx *ctx)
 		goto out;
 
 	if (likely(eventfd_signal_allowed())) {
-		eventfd_signal_mask(ev_fd->cq_ev_fd, 1, EPOLL_URING_WAKE);
+		eventfd_signal_mask(ev_fd->cq_ev_fd, EPOLL_URING_WAKE);
 	} else {
 		atomic_inc(&ev_fd->refs);
 		if (!atomic_fetch_or(BIT(IO_EVENTFD_OP_SIGNAL_BIT), &ev_fd->ops))
-- 
cgit v1.2.3


From b7638ad0c7802ea854599ce753d0e6d20690f7e2 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Wed, 22 Nov 2023 13:48:25 +0100
Subject: eventfd: make eventfd_signal{_mask}() void

No caller care about the return value.

Link: https://lore.kernel.org/r/20231122-vfs-eventfd-signal-v2-4-bd549b14ce0c@kernel.org
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/eventfd.c            | 40 +++++++++++++++-------------------------
 include/linux/eventfd.h | 16 +++++++---------
 2 files changed, 22 insertions(+), 34 deletions(-)

(limited to 'include')

diff --git a/fs/eventfd.c b/fs/eventfd.c
index 41109ba6bbe0..16bea05a7c78 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -43,10 +43,19 @@ struct eventfd_ctx {
 	int id;
 };
 
-__u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __poll_t mask)
+/**
+ * eventfd_signal_mask - Increment the event counter
+ * @ctx: [in] Pointer to the eventfd context.
+ * @mask: [in] poll mask
+ *
+ * This function is supposed to be called by the kernel in paths that do not
+ * allow sleeping. In this function we allow the counter to reach the ULLONG_MAX
+ * value, and we signal this as overflow condition by returning a EPOLLERR
+ * to poll(2).
+ */
+void eventfd_signal_mask(struct eventfd_ctx *ctx, __poll_t mask)
 {
 	unsigned long flags;
-	__u64 n = 1;
 
 	/*
 	 * Deadlock or stack overflow issues can happen if we recurse here
@@ -57,37 +66,18 @@ __u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __poll_t mask)
 	 * safe context.
 	 */
 	if (WARN_ON_ONCE(current->in_eventfd))
-		return 0;
+		return;
 
 	spin_lock_irqsave(&ctx->wqh.lock, flags);
 	current->in_eventfd = 1;
-	if (ULLONG_MAX - ctx->count < n)
-		n = ULLONG_MAX - ctx->count;
-	ctx->count += n;
+	if (ctx->count < ULLONG_MAX)
+		ctx->count++;
 	if (waitqueue_active(&ctx->wqh))
 		wake_up_locked_poll(&ctx->wqh, EPOLLIN | mask);
 	current->in_eventfd = 0;
 	spin_unlock_irqrestore(&ctx->wqh.lock, flags);
-
-	return n == 1;
-}
-
-/**
- * eventfd_signal - Increment the event counter
- * @ctx: [in] Pointer to the eventfd context.
- *
- * This function is supposed to be called by the kernel in paths that do not
- * allow sleeping. In this function we allow the counter to reach the ULLONG_MAX
- * value, and we signal this as overflow condition by returning a EPOLLERR
- * to poll(2).
- *
- * Returns the amount by which the counter was incremented.
- */
-__u64 eventfd_signal(struct eventfd_ctx *ctx)
-{
-	return eventfd_signal_mask(ctx, 0);
 }
-EXPORT_SYMBOL_GPL(eventfd_signal);
+EXPORT_SYMBOL_GPL(eventfd_signal_mask);
 
 static void eventfd_free_ctx(struct eventfd_ctx *ctx)
 {
diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h
index 971943ecb2a6..e32bee4345fb 100644
--- a/include/linux/eventfd.h
+++ b/include/linux/eventfd.h
@@ -35,8 +35,7 @@ void eventfd_ctx_put(struct eventfd_ctx *ctx);
 struct file *eventfd_fget(int fd);
 struct eventfd_ctx *eventfd_ctx_fdget(int fd);
 struct eventfd_ctx *eventfd_ctx_fileget(struct file *file);
-__u64 eventfd_signal(struct eventfd_ctx *ctx);
-__u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __poll_t mask);
+void eventfd_signal_mask(struct eventfd_ctx *ctx, __poll_t mask);
 int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait,
 				  __u64 *cnt);
 void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt);
@@ -58,14 +57,8 @@ static inline struct eventfd_ctx *eventfd_ctx_fdget(int fd)
 	return ERR_PTR(-ENOSYS);
 }
 
-static inline int eventfd_signal(struct eventfd_ctx *ctx)
+static inline void eventfd_signal_mask(struct eventfd_ctx *ctx, __poll_t mask)
 {
-	return -ENOSYS;
-}
-
-static inline int eventfd_signal_mask(struct eventfd_ctx *ctx, __poll_t mask)
-{
-	return -ENOSYS;
 }
 
 static inline void eventfd_ctx_put(struct eventfd_ctx *ctx)
@@ -91,5 +84,10 @@ static inline void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt)
 
 #endif
 
+static inline void eventfd_signal(struct eventfd_ctx *ctx)
+{
+	eventfd_signal_mask(ctx, 0);
+}
+
 #endif /* _LINUX_EVENTFD_H */
 
-- 
cgit v1.2.3


From e65a29f0235a438ece414d2d99bbf0d31aa97d04 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Wed, 22 Nov 2023 13:44:37 +0100
Subject: mnt_idmapping: remove check_fsmapping()

The helper is a bit pointless. Just open-code the check.

Link: https://lore.kernel.org/r/20231122-vfs-mnt_idmap-v1-1-dae4abdde5bd@kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/mnt_idmapping.c            | 17 ++---------------
 fs/namespace.c                |  2 +-
 include/linux/mnt_idmapping.h |  3 ---
 3 files changed, 3 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/fs/mnt_idmapping.c b/fs/mnt_idmapping.c
index 57d1dedf3f8f..2674942311c3 100644
--- a/fs/mnt_idmapping.c
+++ b/fs/mnt_idmapping.c
@@ -25,19 +25,6 @@ struct mnt_idmap nop_mnt_idmap = {
 };
 EXPORT_SYMBOL_GPL(nop_mnt_idmap);
 
-/**
- * check_fsmapping - check whether an mount idmapping is allowed
- * @idmap: idmap of the relevent mount
- * @sb:    super block of the filesystem
- *
- * Return: true if @idmap is allowed, false if not.
- */
-bool check_fsmapping(const struct mnt_idmap *idmap,
-		     const struct super_block *sb)
-{
-	return idmap->owner != sb->s_user_ns;
-}
-
 /**
  * initial_idmapping - check whether this is the initial mapping
  * @ns: idmapping to check
@@ -94,8 +81,8 @@ static inline bool no_idmapping(const struct user_namespace *mnt_userns,
  */
 
 vfsuid_t make_vfsuid(struct mnt_idmap *idmap,
-				   struct user_namespace *fs_userns,
-				   kuid_t kuid)
+		     struct user_namespace *fs_userns,
+		     kuid_t kuid)
 {
 	uid_t uid;
 	struct user_namespace *mnt_userns = idmap->owner;
diff --git a/fs/namespace.c b/fs/namespace.c
index b899cbbe24d9..78366f114515 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -4289,7 +4289,7 @@ static int can_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt)
 	 * Creating an idmapped mount with the filesystem wide idmapping
 	 * doesn't make sense so block that. We don't allow mushy semantics.
 	 */
-	if (!check_fsmapping(kattr->mnt_idmap, m->mnt_sb))
+	if (kattr->mnt_userns == m->mnt_sb->s_user_ns)
 		return -EINVAL;
 
 	/*
diff --git a/include/linux/mnt_idmapping.h b/include/linux/mnt_idmapping.h
index b8da2db4ecd2..cd4d5c8781f5 100644
--- a/include/linux/mnt_idmapping.h
+++ b/include/linux/mnt_idmapping.h
@@ -244,7 +244,4 @@ static inline kgid_t mapped_fsgid(struct mnt_idmap *idmap,
 	return from_vfsgid(idmap, fs_userns, VFSGIDT_INIT(current_fsgid()));
 }
 
-bool check_fsmapping(const struct mnt_idmap *idmap,
-		     const struct super_block *sb);
-
 #endif /* _LINUX_MNT_IDMAPPING_H */
-- 
cgit v1.2.3


From 783822e44594639848b78d4bb61dde26fba04e05 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Wed, 22 Nov 2023 13:44:39 +0100
Subject: mnt_idmapping: decouple from namespaces

There's no reason we need to couple mnt idmapping to namespaces in the
way we currently do. Copy the idmapping when an idmapped mount is
created and don't take any reference on the namespace at all.

We also can't easily refcount struct uid_gid_map because it needs to
stay the size of a cacheline otherwise we risk performance regressions
(Ignoring for a second that right now struct uid_gid_map isn't actually
 64 byte but 72 but that's a fix for another patch series.).

Link: https://lore.kernel.org/r/20231122-vfs-mnt_idmap-v1-3-dae4abdde5bd@kernel.org
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/mnt_idmapping.c      | 106 +++++++++++++++++++++++++++++++++++++++++-------
 include/linux/uidgid.h  |  13 ++++++
 kernel/user_namespace.c |   4 +-
 3 files changed, 106 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/fs/mnt_idmapping.c b/fs/mnt_idmapping.c
index 35d78cb3c38a..64c5205e2b5e 100644
--- a/fs/mnt_idmapping.c
+++ b/fs/mnt_idmapping.c
@@ -9,8 +9,16 @@
 
 #include "internal.h"
 
+/*
+ * Outside of this file vfs{g,u}id_t are always created from k{g,u}id_t,
+ * never from raw values. These are just internal helpers.
+ */
+#define VFSUIDT_INIT_RAW(val) (vfsuid_t){ val }
+#define VFSGIDT_INIT_RAW(val) (vfsgid_t){ val }
+
 struct mnt_idmap {
-	struct user_namespace *owner;
+	struct uid_gid_map uid_map;
+	struct uid_gid_map gid_map;
 	refcount_t count;
 };
 
@@ -20,7 +28,6 @@ struct mnt_idmap {
  * mapped to {g,u}id 1, [...], {g,u}id 1000 to {g,u}id 1000, [...].
  */
 struct mnt_idmap nop_mnt_idmap = {
-	.owner	= &init_user_ns,
 	.count	= REFCOUNT_INIT(1),
 };
 EXPORT_SYMBOL_GPL(nop_mnt_idmap);
@@ -65,7 +72,6 @@ vfsuid_t make_vfsuid(struct mnt_idmap *idmap,
 		     kuid_t kuid)
 {
 	uid_t uid;
-	struct user_namespace *mnt_userns = idmap->owner;
 
 	if (idmap == &nop_mnt_idmap)
 		return VFSUIDT_INIT(kuid);
@@ -75,7 +81,7 @@ vfsuid_t make_vfsuid(struct mnt_idmap *idmap,
 		uid = from_kuid(fs_userns, kuid);
 	if (uid == (uid_t)-1)
 		return INVALID_VFSUID;
-	return VFSUIDT_INIT(make_kuid(mnt_userns, uid));
+	return VFSUIDT_INIT_RAW(map_id_down(&idmap->uid_map, uid));
 }
 EXPORT_SYMBOL_GPL(make_vfsuid);
 
@@ -103,7 +109,6 @@ vfsgid_t make_vfsgid(struct mnt_idmap *idmap,
 		     struct user_namespace *fs_userns, kgid_t kgid)
 {
 	gid_t gid;
-	struct user_namespace *mnt_userns = idmap->owner;
 
 	if (idmap == &nop_mnt_idmap)
 		return VFSGIDT_INIT(kgid);
@@ -113,7 +118,7 @@ vfsgid_t make_vfsgid(struct mnt_idmap *idmap,
 		gid = from_kgid(fs_userns, kgid);
 	if (gid == (gid_t)-1)
 		return INVALID_VFSGID;
-	return VFSGIDT_INIT(make_kgid(mnt_userns, gid));
+	return VFSGIDT_INIT_RAW(map_id_down(&idmap->gid_map, gid));
 }
 EXPORT_SYMBOL_GPL(make_vfsgid);
 
@@ -132,11 +137,10 @@ kuid_t from_vfsuid(struct mnt_idmap *idmap,
 		   struct user_namespace *fs_userns, vfsuid_t vfsuid)
 {
 	uid_t uid;
-	struct user_namespace *mnt_userns = idmap->owner;
 
 	if (idmap == &nop_mnt_idmap)
 		return AS_KUIDT(vfsuid);
-	uid = from_kuid(mnt_userns, AS_KUIDT(vfsuid));
+	uid = map_id_up(&idmap->uid_map, __vfsuid_val(vfsuid));
 	if (uid == (uid_t)-1)
 		return INVALID_UID;
 	if (initial_idmapping(fs_userns))
@@ -160,11 +164,10 @@ kgid_t from_vfsgid(struct mnt_idmap *idmap,
 		   struct user_namespace *fs_userns, vfsgid_t vfsgid)
 {
 	gid_t gid;
-	struct user_namespace *mnt_userns = idmap->owner;
 
 	if (idmap == &nop_mnt_idmap)
 		return AS_KGIDT(vfsgid);
-	gid = from_kgid(mnt_userns, AS_KGIDT(vfsgid));
+	gid = map_id_up(&idmap->gid_map, __vfsgid_val(vfsgid));
 	if (gid == (gid_t)-1)
 		return INVALID_GID;
 	if (initial_idmapping(fs_userns))
@@ -195,16 +198,91 @@ int vfsgid_in_group_p(vfsgid_t vfsgid)
 #endif
 EXPORT_SYMBOL_GPL(vfsgid_in_group_p);
 
+static int copy_mnt_idmap(struct uid_gid_map *map_from,
+			  struct uid_gid_map *map_to)
+{
+	struct uid_gid_extent *forward, *reverse;
+	u32 nr_extents = READ_ONCE(map_from->nr_extents);
+	/* Pairs with smp_wmb() when writing the idmapping. */
+	smp_rmb();
+
+	/*
+	 * Don't blindly copy @map_to into @map_from if nr_extents is
+	 * smaller or equal to UID_GID_MAP_MAX_BASE_EXTENTS. Since we
+	 * read @nr_extents someone could have written an idmapping and
+	 * then we might end up with inconsistent data. So just don't do
+	 * anything at all.
+	 */
+	if (nr_extents == 0)
+		return 0;
+
+	/*
+	 * Here we know that nr_extents is greater than zero which means
+	 * a map has been written. Since idmappings can't be changed
+	 * once they have been written we know that we can safely copy
+	 * from @map_to into @map_from.
+	 */
+
+	if (nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) {
+		*map_to = *map_from;
+		return 0;
+	}
+
+	forward = kmemdup(map_from->forward,
+			  nr_extents * sizeof(struct uid_gid_extent),
+			  GFP_KERNEL_ACCOUNT);
+	if (!forward)
+		return -ENOMEM;
+
+	reverse = kmemdup(map_from->reverse,
+			  nr_extents * sizeof(struct uid_gid_extent),
+			  GFP_KERNEL_ACCOUNT);
+	if (!reverse) {
+		kfree(forward);
+		return -ENOMEM;
+	}
+
+	/*
+	 * The idmapping isn't exposed anywhere so we don't need to care
+	 * about ordering between extent pointers and @nr_extents
+	 * initialization.
+	 */
+	map_to->forward = forward;
+	map_to->reverse = reverse;
+	map_to->nr_extents = nr_extents;
+	return 0;
+}
+
+static void free_mnt_idmap(struct mnt_idmap *idmap)
+{
+	if (idmap->uid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) {
+		kfree(idmap->uid_map.forward);
+		kfree(idmap->uid_map.reverse);
+	}
+	if (idmap->gid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) {
+		kfree(idmap->gid_map.forward);
+		kfree(idmap->gid_map.reverse);
+	}
+	kfree(idmap);
+}
+
 struct mnt_idmap *alloc_mnt_idmap(struct user_namespace *mnt_userns)
 {
 	struct mnt_idmap *idmap;
+	int ret;
 
 	idmap = kzalloc(sizeof(struct mnt_idmap), GFP_KERNEL_ACCOUNT);
 	if (!idmap)
 		return ERR_PTR(-ENOMEM);
 
-	idmap->owner = get_user_ns(mnt_userns);
 	refcount_set(&idmap->count, 1);
+	ret = copy_mnt_idmap(&mnt_userns->uid_map, &idmap->uid_map);
+	if (!ret)
+		ret = copy_mnt_idmap(&mnt_userns->gid_map, &idmap->gid_map);
+	if (ret) {
+		free_mnt_idmap(idmap);
+		idmap = ERR_PTR(ret);
+	}
 	return idmap;
 }
 
@@ -234,9 +312,7 @@ EXPORT_SYMBOL_GPL(mnt_idmap_get);
  */
 void mnt_idmap_put(struct mnt_idmap *idmap)
 {
-	if (idmap != &nop_mnt_idmap && refcount_dec_and_test(&idmap->count)) {
-		put_user_ns(idmap->owner);
-		kfree(idmap);
-	}
+	if (idmap != &nop_mnt_idmap && refcount_dec_and_test(&idmap->count))
+		free_mnt_idmap(idmap);
 }
 EXPORT_SYMBOL_GPL(mnt_idmap_put);
diff --git a/include/linux/uidgid.h b/include/linux/uidgid.h
index b0542cd11aeb..415a7ca2b882 100644
--- a/include/linux/uidgid.h
+++ b/include/linux/uidgid.h
@@ -17,6 +17,7 @@
 
 struct user_namespace;
 extern struct user_namespace init_user_ns;
+struct uid_gid_map;
 
 typedef struct {
 	uid_t val;
@@ -138,6 +139,9 @@ static inline bool kgid_has_mapping(struct user_namespace *ns, kgid_t gid)
 	return from_kgid(ns, gid) != (gid_t) -1;
 }
 
+u32 map_id_down(struct uid_gid_map *map, u32 id);
+u32 map_id_up(struct uid_gid_map *map, u32 id);
+
 #else
 
 static inline kuid_t make_kuid(struct user_namespace *from, uid_t uid)
@@ -186,6 +190,15 @@ static inline bool kgid_has_mapping(struct user_namespace *ns, kgid_t gid)
 	return gid_valid(gid);
 }
 
+static inline u32 map_id_down(struct uid_gid_map *map, u32 id)
+{
+	return id;
+}
+
+static inline u32 map_id_up(struct uid_gid_map *map, u32 id)
+{
+	return id;
+}
 #endif /* CONFIG_USER_NS */
 
 #endif /* _LINUX_UIDGID_H */
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 625101249e4d..ce4d99df5f0e 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -332,7 +332,7 @@ static u32 map_id_range_down(struct uid_gid_map *map, u32 id, u32 count)
 	return id;
 }
 
-static u32 map_id_down(struct uid_gid_map *map, u32 id)
+u32 map_id_down(struct uid_gid_map *map, u32 id)
 {
 	return map_id_range_down(map, id, 1);
 }
@@ -375,7 +375,7 @@ map_id_up_max(unsigned extents, struct uid_gid_map *map, u32 id)
 		       sizeof(struct uid_gid_extent), cmp_map_id);
 }
 
-static u32 map_id_up(struct uid_gid_map *map, u32 id)
+u32 map_id_up(struct uid_gid_map *map, u32 id)
 {
 	struct uid_gid_extent *extent;
 	unsigned extents = map->nr_extents;
-- 
cgit v1.2.3


From e0894ff038d86f30614ec16ec26dacb88c8d2bd4 Mon Sep 17 00:00:00 2001
From: "Luke D. Jones" <luke@ljones.dev>
Date: Mon, 27 Nov 2023 12:05:21 +1300
Subject: platform/x86: asus-wmi: disable USB0 hub on ROG Ally before suspend
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

ASUS have worked around an issue in XInput where it doesn't support USB
selective suspend, which causes suspend issues in Windows. They worked
around this by adjusting the MCU firmware to disable the USB0 hub when
the screen is switched off during the Microsoft DSM suspend path in ACPI.

The issue we have with this however is one of timing - the call the tells
the MCU to this isn't able to complete before suspend is done so we call
this in a prepare() and add a small msleep() to ensure it is done. This
must be done before the screen is switched off to prevent a variety of
possible races.

Further to this the MCU powersave option must also be disabled as it can
cause a number of issues such as:
- unreliable resume connection of N-Key
- complete loss of N-Key if the power is plugged in while suspended
Disabling the powersave option prevents this.

Without this the MCU is unable to initialise itself correctly on resume.

Signed-off-by: "Luke D. Jones" <luke@ljones.dev>
Tested-by: Philip Mueller <philm@manjaro.org>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20231126230521.125708-2-luke@ljones.dev
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/asus-wmi.c            | 50 ++++++++++++++++++++++++++++++
 include/linux/platform_data/x86/asus-wmi.h |  3 ++
 2 files changed, 53 insertions(+)

(limited to 'include')

diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index ca668cf04020..9f7e23c5c6b4 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -16,6 +16,7 @@
 #include <linux/acpi.h>
 #include <linux/backlight.h>
 #include <linux/debugfs.h>
+#include <linux/delay.h>
 #include <linux/dmi.h>
 #include <linux/fb.h>
 #include <linux/hwmon.h>
@@ -132,6 +133,11 @@ module_param(fnlock_default, bool, 0444);
 #define ASUS_SCREENPAD_BRIGHT_MAX 255
 #define ASUS_SCREENPAD_BRIGHT_DEFAULT 60
 
+/* Controls the power state of the USB0 hub on ROG Ally which input is on */
+#define ASUS_USB0_PWR_EC0_CSEE "\\_SB.PCI0.SBRG.EC0.CSEE"
+/* 300ms so far seems to produce a reliable result on AC and battery */
+#define ASUS_USB0_PWR_EC0_CSEE_WAIT 300
+
 static const char * const ashs_ids[] = { "ATK4001", "ATK4002", NULL };
 
 static int throttle_thermal_policy_write(struct asus_wmi *);
@@ -300,6 +306,9 @@ struct asus_wmi {
 
 	bool fnlock_locked;
 
+	/* The ROG Ally device requires the MCU USB device be disconnected before suspend */
+	bool ally_mcu_usb_switch;
+
 	struct asus_wmi_debug debug;
 
 	struct asus_wmi_driver *driver;
@@ -4488,6 +4497,8 @@ static int asus_wmi_add(struct platform_device *pdev)
 	asus->nv_temp_tgt_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_NV_THERM_TARGET);
 	asus->panel_overdrive_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_PANEL_OD);
 	asus->mini_led_mode_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_MINI_LED_MODE);
+	asus->ally_mcu_usb_switch = acpi_has_method(NULL, ASUS_USB0_PWR_EC0_CSEE)
+						&& dmi_match(DMI_BOARD_NAME, "RC71L");
 
 	err = fan_boost_mode_check_present(asus);
 	if (err)
@@ -4662,6 +4673,43 @@ static int asus_hotk_resume(struct device *device)
 		asus_wmi_fnlock_update(asus);
 
 	asus_wmi_tablet_mode_get_state(asus);
+
+	return 0;
+}
+
+static int asus_hotk_resume_early(struct device *device)
+{
+	struct asus_wmi *asus = dev_get_drvdata(device);
+
+	if (asus->ally_mcu_usb_switch) {
+		if (ACPI_FAILURE(acpi_execute_simple_method(NULL, ASUS_USB0_PWR_EC0_CSEE, 0xB8)))
+			dev_err(device, "ROG Ally MCU failed to connect USB dev\n");
+		else
+			msleep(ASUS_USB0_PWR_EC0_CSEE_WAIT);
+	}
+	return 0;
+}
+
+static int asus_hotk_prepare(struct device *device)
+{
+	struct asus_wmi *asus = dev_get_drvdata(device);
+	int result, err;
+
+	if (asus->ally_mcu_usb_switch) {
+		/* When powersave is enabled it causes many issues with resume of USB hub */
+		result = asus_wmi_get_devstate_simple(asus, ASUS_WMI_DEVID_MCU_POWERSAVE);
+		if (result == 1) {
+			dev_warn(device, "MCU powersave enabled, disabling to prevent resume issues");
+			err = asus_wmi_set_devstate(ASUS_WMI_DEVID_MCU_POWERSAVE, 0, &result);
+			if (err || result != 1)
+				dev_err(device, "Failed to set MCU powersave mode: %d\n", err);
+		}
+		/* sleep required to ensure USB0 is disabled before sleep continues */
+		if (ACPI_FAILURE(acpi_execute_simple_method(NULL, ASUS_USB0_PWR_EC0_CSEE, 0xB7)))
+			dev_err(device, "ROG Ally MCU failed to disconnect USB dev\n");
+		else
+			msleep(ASUS_USB0_PWR_EC0_CSEE_WAIT);
+	}
 	return 0;
 }
 
@@ -4709,6 +4757,8 @@ static const struct dev_pm_ops asus_pm_ops = {
 	.thaw = asus_hotk_thaw,
 	.restore = asus_hotk_restore,
 	.resume = asus_hotk_resume,
+	.resume_early = asus_hotk_resume_early,
+	.prepare = asus_hotk_prepare,
 };
 
 /* Registration ***************************************************************/
diff --git a/include/linux/platform_data/x86/asus-wmi.h b/include/linux/platform_data/x86/asus-wmi.h
index 63e630276499..ab1c7deff118 100644
--- a/include/linux/platform_data/x86/asus-wmi.h
+++ b/include/linux/platform_data/x86/asus-wmi.h
@@ -114,6 +114,9 @@
 /* Charging mode - 1=Barrel, 2=USB */
 #define ASUS_WMI_DEVID_CHARGE_MODE	0x0012006C
 
+/* MCU powersave mode */
+#define ASUS_WMI_DEVID_MCU_POWERSAVE   0x001200E2
+
 /* epu is connected? 1 == true */
 #define ASUS_WMI_DEVID_EGPU_CONNECTED	0x00090018
 /* egpu on/off */
-- 
cgit v1.2.3


From f17c69649c698e4df3cfe0010b7bbf142dec3e40 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Sun, 26 Nov 2023 15:07:29 -0800
Subject: net: page_pool: id the page pools

To give ourselves the flexibility of creating netlink commands
and ability to refer to page pool instances in uAPIs create
IDs for page pools.

Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/page_pool/types.h |  4 ++++
 net/core/Makefile             |  2 +-
 net/core/page_pool.c          | 21 ++++++++++++++++-----
 net/core/page_pool_priv.h     |  9 +++++++++
 net/core/page_pool_user.c     | 36 ++++++++++++++++++++++++++++++++++++
 5 files changed, 66 insertions(+), 6 deletions(-)
 create mode 100644 net/core/page_pool_priv.h
 create mode 100644 net/core/page_pool_user.c

(limited to 'include')

diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index e1bb92c192de..c19f0df3bf0b 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -187,6 +187,10 @@ struct page_pool {
 
 	/* Slow/Control-path information follows */
 	struct page_pool_params_slow slow;
+	/* User-facing fields, protected by page_pools_lock */
+	struct {
+		u32 id;
+	} user;
 };
 
 struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp);
diff --git a/net/core/Makefile b/net/core/Makefile
index 0cb734cbc24b..821aec06abf1 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -18,7 +18,7 @@ obj-y		     += dev.o dev_addr_lists.o dst.o netevent.o \
 obj-$(CONFIG_NETDEV_ADDR_LIST_TEST) += dev_addr_lists_test.o
 
 obj-y += net-sysfs.o
-obj-$(CONFIG_PAGE_POOL) += page_pool.o
+obj-$(CONFIG_PAGE_POOL) += page_pool.o page_pool_user.o
 obj-$(CONFIG_PROC_FS) += net-procfs.o
 obj-$(CONFIG_NET_PKTGEN) += pktgen.o
 obj-$(CONFIG_NETPOLL) += netpoll.o
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 2e4575477e71..a8d96ea38d18 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -23,6 +23,8 @@
 
 #include <trace/events/page_pool.h>
 
+#include "page_pool_priv.h"
+
 #define DEFER_TIME (msecs_to_jiffies(1000))
 #define DEFER_WARN_INTERVAL (60 * HZ)
 
@@ -264,13 +266,21 @@ struct page_pool *page_pool_create(const struct page_pool_params *params)
 		return ERR_PTR(-ENOMEM);
 
 	err = page_pool_init(pool, params);
-	if (err < 0) {
-		pr_warn("%s() gave up with errno %d\n", __func__, err);
-		kfree(pool);
-		return ERR_PTR(err);
-	}
+	if (err < 0)
+		goto err_free;
+
+	err = page_pool_list(pool);
+	if (err)
+		goto err_uninit;
 
 	return pool;
+
+err_uninit:
+	page_pool_uninit(pool);
+err_free:
+	pr_warn("%s() gave up with errno %d\n", __func__, err);
+	kfree(pool);
+	return ERR_PTR(err);
 }
 EXPORT_SYMBOL(page_pool_create);
 
@@ -833,6 +843,7 @@ static void __page_pool_destroy(struct page_pool *pool)
 	if (pool->disconnect)
 		pool->disconnect(pool);
 
+	page_pool_unlist(pool);
 	page_pool_uninit(pool);
 	kfree(pool);
 }
diff --git a/net/core/page_pool_priv.h b/net/core/page_pool_priv.h
new file mode 100644
index 000000000000..c17ea092b4ab
--- /dev/null
+++ b/net/core/page_pool_priv.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __PAGE_POOL_PRIV_H
+#define __PAGE_POOL_PRIV_H
+
+int page_pool_list(struct page_pool *pool);
+void page_pool_unlist(struct page_pool *pool);
+
+#endif
diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c
new file mode 100644
index 000000000000..630d1eeecf2a
--- /dev/null
+++ b/net/core/page_pool_user.c
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/mutex.h>
+#include <linux/xarray.h>
+#include <net/page_pool/types.h>
+
+#include "page_pool_priv.h"
+
+static DEFINE_XARRAY_FLAGS(page_pools, XA_FLAGS_ALLOC1);
+static DEFINE_MUTEX(page_pools_lock);
+
+int page_pool_list(struct page_pool *pool)
+{
+	static u32 id_alloc_next;
+	int err;
+
+	mutex_lock(&page_pools_lock);
+	err = xa_alloc_cyclic(&page_pools, &pool->user.id, pool, xa_limit_32b,
+			      &id_alloc_next, GFP_KERNEL);
+	if (err < 0)
+		goto err_unlock;
+
+	mutex_unlock(&page_pools_lock);
+	return 0;
+
+err_unlock:
+	mutex_unlock(&page_pools_lock);
+	return err;
+}
+
+void page_pool_unlist(struct page_pool *pool)
+{
+	mutex_lock(&page_pools_lock);
+	xa_erase(&page_pools, pool->user.id);
+	mutex_unlock(&page_pools_lock);
+}
-- 
cgit v1.2.3


From 083772c9f972dcc248913b52a0dec1025baa1e16 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Sun, 26 Nov 2023 15:07:30 -0800
Subject: net: page_pool: record pools per netdev

Link the page pools with netdevs. This needs to be netns compatible
so we have two options. Either we record the pools per netns and
have to worry about moving them as the netdev gets moved.
Or we record them directly on the netdev so they move with the netdev
without any extra work.

Implement the latter option. Since pools may outlast netdev we need
a place to store orphans. In time honored tradition use loopback
for this purpose.

Reviewed-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/linux/list.h          | 20 +++++++++++
 include/linux/netdevice.h     |  4 +++
 include/linux/poison.h        |  2 ++
 include/net/page_pool/types.h |  4 +++
 net/core/page_pool_user.c     | 84 +++++++++++++++++++++++++++++++++++++++++++
 5 files changed, 114 insertions(+)

(limited to 'include')

diff --git a/include/linux/list.h b/include/linux/list.h
index 1837caedf723..059aa1fff41e 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -1119,6 +1119,26 @@ static inline void hlist_move_list(struct hlist_head *old,
 	old->first = NULL;
 }
 
+/**
+ * hlist_splice_init() - move all entries from one list to another
+ * @from: hlist_head from which entries will be moved
+ * @last: last entry on the @from list
+ * @to:   hlist_head to which entries will be moved
+ *
+ * @to can be empty, @from must contain at least @last.
+ */
+static inline void hlist_splice_init(struct hlist_head *from,
+				     struct hlist_node *last,
+				     struct hlist_head *to)
+{
+	if (to->first)
+		to->first->pprev = &last->next;
+	last->next = to->first;
+	to->first = from->first;
+	from->first->pprev = &to->first;
+	from->first = NULL;
+}
+
 #define hlist_entry(ptr, type, member) container_of(ptr,type,member)
 
 #define hlist_for_each(pos, head) \
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index e87caa81f70c..998c7aaa98b8 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2447,6 +2447,10 @@ struct net_device {
 #if IS_ENABLED(CONFIG_DPLL)
 	struct dpll_pin		*dpll_pin;
 #endif
+#if IS_ENABLED(CONFIG_PAGE_POOL)
+	/** @page_pools: page pools created for this netdevice */
+	struct hlist_head	page_pools;
+#endif
 };
 #define to_net_dev(d) container_of(d, struct net_device, dev)
 
diff --git a/include/linux/poison.h b/include/linux/poison.h
index 851a855d3868..27a7dad17eef 100644
--- a/include/linux/poison.h
+++ b/include/linux/poison.h
@@ -83,6 +83,8 @@
 
 /********** net/core/skbuff.c **********/
 #define SKB_LIST_POISON_NEXT	((void *)(0x800 + POISON_POINTER_DELTA))
+/********** net/ **********/
+#define NET_PTR_POISON		((void *)(0x801 + POISON_POINTER_DELTA))
 
 /********** kernel/bpf/ **********/
 #define BPF_PTR_POISON ((void *)(0xeB9FUL + POISON_POINTER_DELTA))
diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index c19f0df3bf0b..b258a571201e 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -5,6 +5,7 @@
 
 #include <linux/dma-direction.h>
 #include <linux/ptr_ring.h>
+#include <linux/types.h>
 
 #define PP_FLAG_DMA_MAP		BIT(0) /* Should page_pool do the DMA
 					* map/unmap
@@ -48,6 +49,7 @@ struct pp_alloc_cache {
  * @pool_size:	size of the ptr_ring
  * @nid:	NUMA node id to allocate from pages from
  * @dev:	device, for DMA pre-mapping purposes
+ * @netdev:	netdev this pool will serve (leave as NULL if none or multiple)
  * @napi:	NAPI which is the sole consumer of pages, otherwise NULL
  * @dma_dir:	DMA mapping direction
  * @max_len:	max DMA sync memory size for PP_FLAG_DMA_SYNC_DEV
@@ -66,6 +68,7 @@ struct page_pool_params {
 		unsigned int	offset;
 	);
 	struct_group_tagged(page_pool_params_slow, slow,
+		struct net_device *netdev;
 /* private: used by test code only */
 		void (*init_callback)(struct page *page, void *arg);
 		void *init_arg;
@@ -189,6 +192,7 @@ struct page_pool {
 	struct page_pool_params_slow slow;
 	/* User-facing fields, protected by page_pools_lock */
 	struct {
+		struct hlist_node list;
 		u32 id;
 	} user;
 };
diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c
index 630d1eeecf2a..e5c7f078fbd4 100644
--- a/net/core/page_pool_user.c
+++ b/net/core/page_pool_user.c
@@ -1,14 +1,31 @@
 // SPDX-License-Identifier: GPL-2.0
 
 #include <linux/mutex.h>
+#include <linux/netdevice.h>
 #include <linux/xarray.h>
+#include <net/net_debug.h>
 #include <net/page_pool/types.h>
 
 #include "page_pool_priv.h"
 
 static DEFINE_XARRAY_FLAGS(page_pools, XA_FLAGS_ALLOC1);
+/* Protects: page_pools, netdevice->page_pools, pool->slow.netdev, pool->user.
+ * Ordering: inside rtnl_lock
+ */
 static DEFINE_MUTEX(page_pools_lock);
 
+/* Page pools are only reachable from user space (via netlink) if they are
+ * linked to a netdev at creation time. Following page pool "visibility"
+ * states are possible:
+ *  - normal
+ *    - user.list: linked to real netdev, netdev: real netdev
+ *  - orphaned - real netdev has disappeared
+ *    - user.list: linked to lo, netdev: lo
+ *  - invisible - either (a) created without netdev linking, (b) unlisted due
+ *      to error, or (c) the entire namespace which owned this pool disappeared
+ *    - user.list: unhashed, netdev: unknown
+ */
+
 int page_pool_list(struct page_pool *pool)
 {
 	static u32 id_alloc_next;
@@ -20,6 +37,10 @@ int page_pool_list(struct page_pool *pool)
 	if (err < 0)
 		goto err_unlock;
 
+	if (pool->slow.netdev)
+		hlist_add_head(&pool->user.list,
+			       &pool->slow.netdev->page_pools);
+
 	mutex_unlock(&page_pools_lock);
 	return 0;
 
@@ -32,5 +53,68 @@ void page_pool_unlist(struct page_pool *pool)
 {
 	mutex_lock(&page_pools_lock);
 	xa_erase(&page_pools, pool->user.id);
+	hlist_del(&pool->user.list);
+	mutex_unlock(&page_pools_lock);
+}
+
+static void page_pool_unreg_netdev_wipe(struct net_device *netdev)
+{
+	struct page_pool *pool;
+	struct hlist_node *n;
+
+	mutex_lock(&page_pools_lock);
+	hlist_for_each_entry_safe(pool, n, &netdev->page_pools, user.list) {
+		hlist_del_init(&pool->user.list);
+		pool->slow.netdev = NET_PTR_POISON;
+	}
+	mutex_unlock(&page_pools_lock);
+}
+
+static void page_pool_unreg_netdev(struct net_device *netdev)
+{
+	struct page_pool *pool, *last;
+	struct net_device *lo;
+
+	lo = dev_net(netdev)->loopback_dev;
+
+	mutex_lock(&page_pools_lock);
+	last = NULL;
+	hlist_for_each_entry(pool, &netdev->page_pools, user.list) {
+		pool->slow.netdev = lo;
+		last = pool;
+	}
+	if (last)
+		hlist_splice_init(&netdev->page_pools, &last->user.list,
+				  &lo->page_pools);
 	mutex_unlock(&page_pools_lock);
 }
+
+static int
+page_pool_netdevice_event(struct notifier_block *nb,
+			  unsigned long event, void *ptr)
+{
+	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
+
+	if (event != NETDEV_UNREGISTER)
+		return NOTIFY_DONE;
+
+	if (hlist_empty(&netdev->page_pools))
+		return NOTIFY_OK;
+
+	if (netdev->ifindex != LOOPBACK_IFINDEX)
+		page_pool_unreg_netdev(netdev);
+	else
+		page_pool_unreg_netdev_wipe(netdev);
+	return NOTIFY_OK;
+}
+
+static struct notifier_block page_pool_netdevice_nb = {
+	.notifier_call = page_pool_netdevice_event,
+};
+
+static int __init page_pool_user_init(void)
+{
+	return register_netdevice_notifier(&page_pool_netdevice_nb);
+}
+
+subsys_initcall(page_pool_user_init);
-- 
cgit v1.2.3


From 02b3de80c5f879f92e5f4bb3f535d172e0fc0ea0 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Sun, 26 Nov 2023 15:07:31 -0800
Subject: net: page_pool: stash the NAPI ID for easier access

To avoid any issues with race conditions on accessing napi
and having to think about the lifetime of NAPI objects
in netlink GET - stash the napi_id to which page pool
was linked at creation time.

Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/page_pool/types.h | 1 +
 net/core/page_pool_user.c     | 4 +++-
 2 files changed, 4 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index b258a571201e..7e47d7bb2c1e 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -193,6 +193,7 @@ struct page_pool {
 	/* User-facing fields, protected by page_pools_lock */
 	struct {
 		struct hlist_node list;
+		u32 napi_id;
 		u32 id;
 	} user;
 };
diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c
index e5c7f078fbd4..2888aa8dd3e4 100644
--- a/net/core/page_pool_user.c
+++ b/net/core/page_pool_user.c
@@ -37,9 +37,11 @@ int page_pool_list(struct page_pool *pool)
 	if (err < 0)
 		goto err_unlock;
 
-	if (pool->slow.netdev)
+	if (pool->slow.netdev) {
 		hlist_add_head(&pool->user.list,
 			       &pool->slow.netdev->page_pools);
+		pool->user.napi_id = pool->p.napi ? pool->p.napi->napi_id : 0;
+	}
 
 	mutex_unlock(&page_pools_lock);
 	return 0;
-- 
cgit v1.2.3


From 950ab53b77ab829defeb22bc98d40a5e926ae018 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Sun, 26 Nov 2023 15:07:34 -0800
Subject: net: page_pool: implement GET in the netlink API

Expose the very basic page pool information via netlink.

Example using ynl-py for a system with 9 queues:

$ ./cli.py --no-schema --spec netlink/specs/netdev.yaml \
           --dump page-pool-get
[{'id': 19, 'ifindex': 2, 'napi-id': 147},
 {'id': 18, 'ifindex': 2, 'napi-id': 146},
 {'id': 17, 'ifindex': 2, 'napi-id': 145},
 {'id': 16, 'ifindex': 2, 'napi-id': 144},
 {'id': 15, 'ifindex': 2, 'napi-id': 143},
 {'id': 14, 'ifindex': 2, 'napi-id': 142},
 {'id': 13, 'ifindex': 2, 'napi-id': 141},
 {'id': 12, 'ifindex': 2, 'napi-id': 140},
 {'id': 11, 'ifindex': 2, 'napi-id': 139},
 {'id': 10, 'ifindex': 2, 'napi-id': 138}]

Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/uapi/linux/netdev.h |  10 ++++
 net/core/netdev-genl-gen.c  |  27 ++++++++++
 net/core/netdev-genl-gen.h  |   3 ++
 net/core/page_pool_user.c   | 127 ++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 167 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index 2943a151d4f1..176665bcf0da 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -64,11 +64,21 @@ enum {
 	NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1)
 };
 
+enum {
+	NETDEV_A_PAGE_POOL_ID = 1,
+	NETDEV_A_PAGE_POOL_IFINDEX,
+	NETDEV_A_PAGE_POOL_NAPI_ID,
+
+	__NETDEV_A_PAGE_POOL_MAX,
+	NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1)
+};
+
 enum {
 	NETDEV_CMD_DEV_GET = 1,
 	NETDEV_CMD_DEV_ADD_NTF,
 	NETDEV_CMD_DEV_DEL_NTF,
 	NETDEV_CMD_DEV_CHANGE_NTF,
+	NETDEV_CMD_PAGE_POOL_GET,
 
 	__NETDEV_CMD_MAX,
 	NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)
diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c
index ea9231378aa6..bfde13981c77 100644
--- a/net/core/netdev-genl-gen.c
+++ b/net/core/netdev-genl-gen.c
@@ -10,11 +10,24 @@
 
 #include <uapi/linux/netdev.h>
 
+/* Integer value ranges */
+static const struct netlink_range_validation netdev_a_page_pool_id_range = {
+	.min	= 1ULL,
+	.max	= 4294967295ULL,
+};
+
 /* NETDEV_CMD_DEV_GET - do */
 static const struct nla_policy netdev_dev_get_nl_policy[NETDEV_A_DEV_IFINDEX + 1] = {
 	[NETDEV_A_DEV_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1),
 };
 
+/* NETDEV_CMD_PAGE_POOL_GET - do */
+#ifdef CONFIG_PAGE_POOL
+static const struct nla_policy netdev_page_pool_get_nl_policy[NETDEV_A_PAGE_POOL_ID + 1] = {
+	[NETDEV_A_PAGE_POOL_ID] = NLA_POLICY_FULL_RANGE(NLA_UINT, &netdev_a_page_pool_id_range),
+};
+#endif /* CONFIG_PAGE_POOL */
+
 /* Ops table for netdev */
 static const struct genl_split_ops netdev_nl_ops[] = {
 	{
@@ -29,6 +42,20 @@ static const struct genl_split_ops netdev_nl_ops[] = {
 		.dumpit	= netdev_nl_dev_get_dumpit,
 		.flags	= GENL_CMD_CAP_DUMP,
 	},
+#ifdef CONFIG_PAGE_POOL
+	{
+		.cmd		= NETDEV_CMD_PAGE_POOL_GET,
+		.doit		= netdev_nl_page_pool_get_doit,
+		.policy		= netdev_page_pool_get_nl_policy,
+		.maxattr	= NETDEV_A_PAGE_POOL_ID,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd	= NETDEV_CMD_PAGE_POOL_GET,
+		.dumpit	= netdev_nl_page_pool_get_dumpit,
+		.flags	= GENL_CMD_CAP_DUMP,
+	},
+#endif /* CONFIG_PAGE_POOL */
 };
 
 static const struct genl_multicast_group netdev_nl_mcgrps[] = {
diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h
index 7b370c073e7d..a011d12abff4 100644
--- a/net/core/netdev-genl-gen.h
+++ b/net/core/netdev-genl-gen.h
@@ -13,6 +13,9 @@
 
 int netdev_nl_dev_get_doit(struct sk_buff *skb, struct genl_info *info);
 int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
+int netdev_nl_page_pool_get_doit(struct sk_buff *skb, struct genl_info *info);
+int netdev_nl_page_pool_get_dumpit(struct sk_buff *skb,
+				   struct netlink_callback *cb);
 
 enum {
 	NETDEV_NLGRP_MGMT,
diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c
index 2888aa8dd3e4..7eb37c31fce9 100644
--- a/net/core/page_pool_user.c
+++ b/net/core/page_pool_user.c
@@ -5,8 +5,10 @@
 #include <linux/xarray.h>
 #include <net/net_debug.h>
 #include <net/page_pool/types.h>
+#include <net/sock.h>
 
 #include "page_pool_priv.h"
+#include "netdev-genl-gen.h"
 
 static DEFINE_XARRAY_FLAGS(page_pools, XA_FLAGS_ALLOC1);
 /* Protects: page_pools, netdevice->page_pools, pool->slow.netdev, pool->user.
@@ -26,6 +28,131 @@ static DEFINE_MUTEX(page_pools_lock);
  *    - user.list: unhashed, netdev: unknown
  */
 
+typedef int (*pp_nl_fill_cb)(struct sk_buff *rsp, const struct page_pool *pool,
+			     const struct genl_info *info);
+
+static int
+netdev_nl_page_pool_get_do(struct genl_info *info, u32 id, pp_nl_fill_cb fill)
+{
+	struct page_pool *pool;
+	struct sk_buff *rsp;
+	int err;
+
+	mutex_lock(&page_pools_lock);
+	pool = xa_load(&page_pools, id);
+	if (!pool || hlist_unhashed(&pool->user.list) ||
+	    !net_eq(dev_net(pool->slow.netdev), genl_info_net(info))) {
+		err = -ENOENT;
+		goto err_unlock;
+	}
+
+	rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!rsp) {
+		err = -ENOMEM;
+		goto err_unlock;
+	}
+
+	err = fill(rsp, pool, info);
+	if (err)
+		goto err_free_msg;
+
+	mutex_unlock(&page_pools_lock);
+
+	return genlmsg_reply(rsp, info);
+
+err_free_msg:
+	nlmsg_free(rsp);
+err_unlock:
+	mutex_unlock(&page_pools_lock);
+	return err;
+}
+
+struct page_pool_dump_cb {
+	unsigned long ifindex;
+	u32 pp_id;
+};
+
+static int
+netdev_nl_page_pool_get_dump(struct sk_buff *skb, struct netlink_callback *cb,
+			     pp_nl_fill_cb fill)
+{
+	struct page_pool_dump_cb *state = (void *)cb->ctx;
+	const struct genl_info *info = genl_info_dump(cb);
+	struct net *net = sock_net(skb->sk);
+	struct net_device *netdev;
+	struct page_pool *pool;
+	int err = 0;
+
+	rtnl_lock();
+	mutex_lock(&page_pools_lock);
+	for_each_netdev_dump(net, netdev, state->ifindex) {
+		hlist_for_each_entry(pool, &netdev->page_pools, user.list) {
+			if (state->pp_id && state->pp_id < pool->user.id)
+				continue;
+
+			state->pp_id = pool->user.id;
+			err = fill(skb, pool, info);
+			if (err)
+				break;
+		}
+
+		state->pp_id = 0;
+	}
+	mutex_unlock(&page_pools_lock);
+	rtnl_unlock();
+
+	if (skb->len && err == -EMSGSIZE)
+		return skb->len;
+	return err;
+}
+
+static int
+page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool,
+		  const struct genl_info *info)
+{
+	void *hdr;
+
+	hdr = genlmsg_iput(rsp, info);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (nla_put_uint(rsp, NETDEV_A_PAGE_POOL_ID, pool->user.id))
+		goto err_cancel;
+
+	if (pool->slow.netdev->ifindex != LOOPBACK_IFINDEX &&
+	    nla_put_u32(rsp, NETDEV_A_PAGE_POOL_IFINDEX,
+			pool->slow.netdev->ifindex))
+		goto err_cancel;
+	if (pool->user.napi_id &&
+	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_NAPI_ID, pool->user.napi_id))
+		goto err_cancel;
+
+	genlmsg_end(rsp, hdr);
+
+	return 0;
+err_cancel:
+	genlmsg_cancel(rsp, hdr);
+	return -EMSGSIZE;
+}
+
+int netdev_nl_page_pool_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	u32 id;
+
+	if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_PAGE_POOL_ID))
+		return -EINVAL;
+
+	id = nla_get_uint(info->attrs[NETDEV_A_PAGE_POOL_ID]);
+
+	return netdev_nl_page_pool_get_do(info, id, page_pool_nl_fill);
+}
+
+int netdev_nl_page_pool_get_dumpit(struct sk_buff *skb,
+				   struct netlink_callback *cb)
+{
+	return netdev_nl_page_pool_get_dump(skb, cb, page_pool_nl_fill);
+}
+
 int page_pool_list(struct page_pool *pool)
 {
 	static u32 id_alloc_next;
-- 
cgit v1.2.3


From d2ef6aa077bdd0b3495dba5dcae6d3f19579b20b Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Sun, 26 Nov 2023 15:07:35 -0800
Subject: net: page_pool: add netlink notifications for state changes

Generate netlink notifications about page pool state changes.

Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 Documentation/netlink/specs/netdev.yaml | 20 ++++++++++++++++++
 include/uapi/linux/netdev.h             |  4 ++++
 net/core/netdev-genl-gen.c              |  1 +
 net/core/netdev-genl-gen.h              |  1 +
 net/core/page_pool_user.c               | 36 +++++++++++++++++++++++++++++++++
 5 files changed, 62 insertions(+)

(limited to 'include')

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index 84ca3c2ab872..82fbe81f7a49 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -166,8 +166,28 @@ operations:
       dump:
         reply: *pp-reply
       config-cond: page-pool
+    -
+      name: page-pool-add-ntf
+      doc: Notification about page pool appearing.
+      notify: page-pool-get
+      mcgrp: page-pool
+      config-cond: page-pool
+    -
+      name: page-pool-del-ntf
+      doc: Notification about page pool disappearing.
+      notify: page-pool-get
+      mcgrp: page-pool
+      config-cond: page-pool
+    -
+      name: page-pool-change-ntf
+      doc: Notification about page pool configuration being changed.
+      notify: page-pool-get
+      mcgrp: page-pool
+      config-cond: page-pool
 
 mcast-groups:
   list:
     -
       name: mgmt
+    -
+      name: page-pool
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index 176665bcf0da..beb158872226 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -79,11 +79,15 @@ enum {
 	NETDEV_CMD_DEV_DEL_NTF,
 	NETDEV_CMD_DEV_CHANGE_NTF,
 	NETDEV_CMD_PAGE_POOL_GET,
+	NETDEV_CMD_PAGE_POOL_ADD_NTF,
+	NETDEV_CMD_PAGE_POOL_DEL_NTF,
+	NETDEV_CMD_PAGE_POOL_CHANGE_NTF,
 
 	__NETDEV_CMD_MAX,
 	NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)
 };
 
 #define NETDEV_MCGRP_MGMT	"mgmt"
+#define NETDEV_MCGRP_PAGE_POOL	"page-pool"
 
 #endif /* _UAPI_LINUX_NETDEV_H */
diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c
index bfde13981c77..47fb5e1b6369 100644
--- a/net/core/netdev-genl-gen.c
+++ b/net/core/netdev-genl-gen.c
@@ -60,6 +60,7 @@ static const struct genl_split_ops netdev_nl_ops[] = {
 
 static const struct genl_multicast_group netdev_nl_mcgrps[] = {
 	[NETDEV_NLGRP_MGMT] = { "mgmt", },
+	[NETDEV_NLGRP_PAGE_POOL] = { "page-pool", },
 };
 
 struct genl_family netdev_nl_family __ro_after_init = {
diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h
index a011d12abff4..738097847100 100644
--- a/net/core/netdev-genl-gen.h
+++ b/net/core/netdev-genl-gen.h
@@ -19,6 +19,7 @@ int netdev_nl_page_pool_get_dumpit(struct sk_buff *skb,
 
 enum {
 	NETDEV_NLGRP_MGMT,
+	NETDEV_NLGRP_PAGE_POOL,
 };
 
 extern struct genl_family netdev_nl_family;
diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c
index 7eb37c31fce9..1577fef880c9 100644
--- a/net/core/page_pool_user.c
+++ b/net/core/page_pool_user.c
@@ -135,6 +135,37 @@ err_cancel:
 	return -EMSGSIZE;
 }
 
+static void netdev_nl_page_pool_event(const struct page_pool *pool, u32 cmd)
+{
+	struct genl_info info;
+	struct sk_buff *ntf;
+	struct net *net;
+
+	lockdep_assert_held(&page_pools_lock);
+
+	/* 'invisible' page pools don't matter */
+	if (hlist_unhashed(&pool->user.list))
+		return;
+	net = dev_net(pool->slow.netdev);
+
+	if (!genl_has_listeners(&netdev_nl_family, net, NETDEV_NLGRP_PAGE_POOL))
+		return;
+
+	genl_info_init_ntf(&info, &netdev_nl_family, cmd);
+
+	ntf = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!ntf)
+		return;
+
+	if (page_pool_nl_fill(ntf, pool, &info)) {
+		nlmsg_free(ntf);
+		return;
+	}
+
+	genlmsg_multicast_netns(&netdev_nl_family, net, ntf,
+				0, NETDEV_NLGRP_PAGE_POOL, GFP_KERNEL);
+}
+
 int netdev_nl_page_pool_get_doit(struct sk_buff *skb, struct genl_info *info)
 {
 	u32 id;
@@ -168,6 +199,8 @@ int page_pool_list(struct page_pool *pool)
 		hlist_add_head(&pool->user.list,
 			       &pool->slow.netdev->page_pools);
 		pool->user.napi_id = pool->p.napi ? pool->p.napi->napi_id : 0;
+
+		netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_ADD_NTF);
 	}
 
 	mutex_unlock(&page_pools_lock);
@@ -181,6 +214,7 @@ err_unlock:
 void page_pool_unlist(struct page_pool *pool)
 {
 	mutex_lock(&page_pools_lock);
+	netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_DEL_NTF);
 	xa_erase(&page_pools, pool->user.id);
 	hlist_del(&pool->user.list);
 	mutex_unlock(&page_pools_lock);
@@ -210,6 +244,8 @@ static void page_pool_unreg_netdev(struct net_device *netdev)
 	last = NULL;
 	hlist_for_each_entry(pool, &netdev->page_pools, user.list) {
 		pool->slow.netdev = lo;
+		netdev_nl_page_pool_event(pool,
+					  NETDEV_CMD_PAGE_POOL_CHANGE_NTF);
 		last = pool;
 	}
 	if (last)
-- 
cgit v1.2.3


From 7aee8429eedd0970d8add2fb5b856bfc5f5f1fc1 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Sun, 26 Nov 2023 15:07:36 -0800
Subject: net: page_pool: report amount of memory held by page pools

Advanced deployments need the ability to check memory use
of various system components. It makes it possible to make informed
decisions about memory allocation and to find regressions and leaks.

Report memory use of page pools. Report both number of references
and bytes held.

Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 Documentation/netlink/specs/netdev.yaml | 15 +++++++++++++++
 include/uapi/linux/netdev.h             |  2 ++
 net/core/page_pool.c                    | 13 +++++++++----
 net/core/page_pool_priv.h               |  2 ++
 net/core/page_pool_user.c               |  8 ++++++++
 5 files changed, 36 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index 82fbe81f7a49..b76623ff2932 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -114,6 +114,19 @@ attribute-sets:
         checks:
           min: 1
           max: u32-max
+      -
+        name: inflight
+        type: uint
+        doc: |
+          Number of outstanding references to this page pool (allocated
+          but yet to be freed pages). Allocated pages may be held in
+          socket receive queues, driver receive ring, page pool recycling
+          ring, the page pool cache, etc.
+      -
+        name: inflight-mem
+        type: uint
+        doc: |
+          Amount of memory held by inflight pages.
 
 operations:
   list:
@@ -163,6 +176,8 @@ operations:
             - id
             - ifindex
             - napi-id
+            - inflight
+            - inflight-mem
       dump:
         reply: *pp-reply
       config-cond: page-pool
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index beb158872226..26ae5bdd3187 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -68,6 +68,8 @@ enum {
 	NETDEV_A_PAGE_POOL_ID = 1,
 	NETDEV_A_PAGE_POOL_IFINDEX,
 	NETDEV_A_PAGE_POOL_NAPI_ID,
+	NETDEV_A_PAGE_POOL_INFLIGHT,
+	NETDEV_A_PAGE_POOL_INFLIGHT_MEM,
 
 	__NETDEV_A_PAGE_POOL_MAX,
 	NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1)
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index a8d96ea38d18..566390759294 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -529,7 +529,7 @@ EXPORT_SYMBOL(page_pool_alloc_pages);
  */
 #define _distance(a, b)	(s32)((a) - (b))
 
-static s32 page_pool_inflight(struct page_pool *pool)
+s32 page_pool_inflight(const struct page_pool *pool, bool strict)
 {
 	u32 release_cnt = atomic_read(&pool->pages_state_release_cnt);
 	u32 hold_cnt = READ_ONCE(pool->pages_state_hold_cnt);
@@ -537,8 +537,13 @@ static s32 page_pool_inflight(struct page_pool *pool)
 
 	inflight = _distance(hold_cnt, release_cnt);
 
-	trace_page_pool_release(pool, inflight, hold_cnt, release_cnt);
-	WARN(inflight < 0, "Negative(%d) inflight packet-pages", inflight);
+	if (strict) {
+		trace_page_pool_release(pool, inflight, hold_cnt, release_cnt);
+		WARN(inflight < 0, "Negative(%d) inflight packet-pages",
+		     inflight);
+	} else {
+		inflight = max(0, inflight);
+	}
 
 	return inflight;
 }
@@ -881,7 +886,7 @@ static int page_pool_release(struct page_pool *pool)
 	int inflight;
 
 	page_pool_scrub(pool);
-	inflight = page_pool_inflight(pool);
+	inflight = page_pool_inflight(pool, true);
 	if (!inflight)
 		__page_pool_destroy(pool);
 
diff --git a/net/core/page_pool_priv.h b/net/core/page_pool_priv.h
index c17ea092b4ab..72fb21ea1ddc 100644
--- a/net/core/page_pool_priv.h
+++ b/net/core/page_pool_priv.h
@@ -3,6 +3,8 @@
 #ifndef __PAGE_POOL_PRIV_H
 #define __PAGE_POOL_PRIV_H
 
+s32 page_pool_inflight(const struct page_pool *pool, bool strict);
+
 int page_pool_list(struct page_pool *pool);
 void page_pool_unlist(struct page_pool *pool);
 
diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c
index 1577fef880c9..2db71e718485 100644
--- a/net/core/page_pool_user.c
+++ b/net/core/page_pool_user.c
@@ -110,6 +110,7 @@ static int
 page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool,
 		  const struct genl_info *info)
 {
+	size_t inflight, refsz;
 	void *hdr;
 
 	hdr = genlmsg_iput(rsp, info);
@@ -127,6 +128,13 @@ page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool,
 	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_NAPI_ID, pool->user.napi_id))
 		goto err_cancel;
 
+	inflight = page_pool_inflight(pool, false);
+	refsz =	PAGE_SIZE << pool->p.order;
+	if (nla_put_uint(rsp, NETDEV_A_PAGE_POOL_INFLIGHT, inflight) ||
+	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_INFLIGHT_MEM,
+			 inflight * refsz))
+		goto err_cancel;
+
 	genlmsg_end(rsp, hdr);
 
 	return 0;
-- 
cgit v1.2.3


From 69cb4952b6f6a226c1c0a7ca400398aaa8f75cf2 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Sun, 26 Nov 2023 15:07:37 -0800
Subject: net: page_pool: report when page pool was destroyed

Report when page pool was destroyed. Together with the inflight
/ memory use reporting this can serve as a replacement for the
warning about leaked page pools we currently print to dmesg.

Example output for a fake leaked page pool using some hacks
in netdevsim (one "live" pool, and one "leaked" on the same dev):

$ ./cli.py --no-schema --spec netlink/specs/netdev.yaml \
           --dump page-pool-get
[{'id': 2, 'ifindex': 3},
 {'id': 1, 'ifindex': 3, 'destroyed': 133, 'inflight': 1}]

Tested-by: Dragos Tatulea <dtatulea@nvidia.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 Documentation/netlink/specs/netdev.yaml | 13 +++++++++++++
 include/net/page_pool/types.h           |  1 +
 include/uapi/linux/netdev.h             |  1 +
 net/core/page_pool.c                    |  1 +
 net/core/page_pool_priv.h               |  1 +
 net/core/page_pool_user.c               | 12 ++++++++++++
 6 files changed, 29 insertions(+)

(limited to 'include')

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index b76623ff2932..b5f715cf9e06 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -127,6 +127,18 @@ attribute-sets:
         type: uint
         doc: |
           Amount of memory held by inflight pages.
+      -
+        name: detach-time
+        type: uint
+        doc: |
+          Seconds in CLOCK_BOOTTIME of when Page Pool was detached by
+          the driver. Once detached Page Pool can no longer be used to
+          allocate memory.
+          Page Pools wait for all the memory allocated from them to be freed
+          before truly disappearing. "Detached" Page Pools cannot be
+          "re-attached", they are just waiting to disappear.
+          Attribute is absent if Page Pool has not been detached, and
+          can still be used to allocate new memory.
 
 operations:
   list:
@@ -178,6 +190,7 @@ operations:
             - napi-id
             - inflight
             - inflight-mem
+            - detach-time
       dump:
         reply: *pp-reply
       config-cond: page-pool
diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index 7e47d7bb2c1e..ac286ea8ce2d 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -193,6 +193,7 @@ struct page_pool {
 	/* User-facing fields, protected by page_pools_lock */
 	struct {
 		struct hlist_node list;
+		u64 detach_time;
 		u32 napi_id;
 		u32 id;
 	} user;
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index 26ae5bdd3187..756410274120 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -70,6 +70,7 @@ enum {
 	NETDEV_A_PAGE_POOL_NAPI_ID,
 	NETDEV_A_PAGE_POOL_INFLIGHT,
 	NETDEV_A_PAGE_POOL_INFLIGHT_MEM,
+	NETDEV_A_PAGE_POOL_DETACH_TIME,
 
 	__NETDEV_A_PAGE_POOL_MAX,
 	NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1)
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 566390759294..a821fb5fe054 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -953,6 +953,7 @@ void page_pool_destroy(struct page_pool *pool)
 	if (!page_pool_release(pool))
 		return;
 
+	page_pool_detached(pool);
 	pool->defer_start = jiffies;
 	pool->defer_warn  = jiffies + DEFER_WARN_INTERVAL;
 
diff --git a/net/core/page_pool_priv.h b/net/core/page_pool_priv.h
index 72fb21ea1ddc..90665d40f1eb 100644
--- a/net/core/page_pool_priv.h
+++ b/net/core/page_pool_priv.h
@@ -6,6 +6,7 @@
 s32 page_pool_inflight(const struct page_pool *pool, bool strict);
 
 int page_pool_list(struct page_pool *pool);
+void page_pool_detached(struct page_pool *pool);
 void page_pool_unlist(struct page_pool *pool);
 
 #endif
diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c
index 2db71e718485..bd5ca94f683f 100644
--- a/net/core/page_pool_user.c
+++ b/net/core/page_pool_user.c
@@ -134,6 +134,10 @@ page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool,
 	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_INFLIGHT_MEM,
 			 inflight * refsz))
 		goto err_cancel;
+	if (pool->user.detach_time &&
+	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_DETACH_TIME,
+			 pool->user.detach_time))
+		goto err_cancel;
 
 	genlmsg_end(rsp, hdr);
 
@@ -219,6 +223,14 @@ err_unlock:
 	return err;
 }
 
+void page_pool_detached(struct page_pool *pool)
+{
+	mutex_lock(&page_pools_lock);
+	pool->user.detach_time = ktime_get_boottime_seconds();
+	netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_CHANGE_NTF);
+	mutex_unlock(&page_pools_lock);
+}
+
 void page_pool_unlist(struct page_pool *pool)
 {
 	mutex_lock(&page_pools_lock);
-- 
cgit v1.2.3


From d49010adae737638447369a4eff8f1aab736b076 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Sun, 26 Nov 2023 15:07:38 -0800
Subject: net: page_pool: expose page pool stats via netlink

Dump the stats into netlink. More clever approaches
like dumping the stats per-CPU for each CPU individually
to see where the packets get consumed can be implemented
in the future.

A trimmed example from a real (but recently booted system):

$ ./cli.py --no-schema --spec netlink/specs/netdev.yaml \
           --dump page-pool-stats-get
[{'info': {'id': 19, 'ifindex': 2},
  'alloc-empty': 48,
  'alloc-fast': 3024,
  'alloc-refill': 0,
  'alloc-slow': 48,
  'alloc-slow-high-order': 0,
  'alloc-waive': 0,
  'recycle-cache-full': 0,
  'recycle-cached': 0,
  'recycle-released-refcnt': 0,
  'recycle-ring': 0,
  'recycle-ring-full': 0},
 {'info': {'id': 18, 'ifindex': 2},
  'alloc-empty': 66,
  'alloc-fast': 11811,
  'alloc-refill': 35,
  'alloc-slow': 66,
  'alloc-slow-high-order': 0,
  'alloc-waive': 0,
  'recycle-cache-full': 1145,
  'recycle-cached': 6541,
  'recycle-released-refcnt': 0,
  'recycle-ring': 1275,
  'recycle-ring-full': 0},
 {'info': {'id': 17, 'ifindex': 2},
  'alloc-empty': 73,
  'alloc-fast': 62099,
  'alloc-refill': 413,
...

Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 Documentation/netlink/specs/netdev.yaml |  78 ++++++++++++++++++++++++
 Documentation/networking/page_pool.rst  |  10 +++-
 include/net/page_pool/helpers.h         |   8 +--
 include/uapi/linux/netdev.h             |  19 ++++++
 net/core/netdev-genl-gen.c              |  32 ++++++++++
 net/core/netdev-genl-gen.h              |   7 +++
 net/core/page_pool.c                    |   2 +-
 net/core/page_pool_user.c               | 103 ++++++++++++++++++++++++++++++++
 8 files changed, 250 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index b5f715cf9e06..20f75b7d3240 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -139,6 +139,59 @@ attribute-sets:
           "re-attached", they are just waiting to disappear.
           Attribute is absent if Page Pool has not been detached, and
           can still be used to allocate new memory.
+  -
+    name: page-pool-info
+    subset-of: page-pool
+    attributes:
+      -
+        name: id
+      -
+        name: ifindex
+  -
+    name: page-pool-stats
+    doc: |
+      Page pool statistics, see docs for struct page_pool_stats
+      for information about individual statistics.
+    attributes:
+      -
+        name: info
+        doc: Page pool identifying information.
+        type: nest
+        nested-attributes: page-pool-info
+      -
+        name: alloc-fast
+        type: uint
+        value: 8 # reserve some attr ids in case we need more metadata later
+      -
+        name: alloc-slow
+        type: uint
+      -
+        name: alloc-slow-high-order
+        type: uint
+      -
+        name: alloc-empty
+        type: uint
+      -
+        name: alloc-refill
+        type: uint
+      -
+        name: alloc-waive
+        type: uint
+      -
+        name: recycle-cached
+        type: uint
+      -
+        name: recycle-cache-full
+        type: uint
+      -
+        name: recycle-ring
+        type: uint
+      -
+        name: recycle-ring-full
+        type: uint
+      -
+        name: recycle-released-refcnt
+        type: uint
 
 operations:
   list:
@@ -212,6 +265,31 @@ operations:
       notify: page-pool-get
       mcgrp: page-pool
       config-cond: page-pool
+    -
+      name: page-pool-stats-get
+      doc: Get page pool statistics.
+      attribute-set: page-pool-stats
+      do:
+        request:
+          attributes:
+            - info
+        reply: &pp-stats-reply
+          attributes:
+            - info
+            - alloc-fast
+            - alloc-slow
+            - alloc-slow-high-order
+            - alloc-empty
+            - alloc-refill
+            - alloc-waive
+            - recycle-cached
+            - recycle-cache-full
+            - recycle-ring
+            - recycle-ring-full
+            - recycle-released-refcnt
+      dump:
+        reply: *pp-stats-reply
+      config-cond: page-pool-stats
 
 mcast-groups:
   list:
diff --git a/Documentation/networking/page_pool.rst b/Documentation/networking/page_pool.rst
index 60993cb56b32..9d958128a57c 100644
--- a/Documentation/networking/page_pool.rst
+++ b/Documentation/networking/page_pool.rst
@@ -41,6 +41,11 @@ Architecture overview
                           |   Fast cache    |     |  ptr-ring cache  |
                           +-----------------+     +------------------+
 
+Monitoring
+==========
+Information about page pools on the system can be accessed via the netdev
+genetlink family (see Documentation/netlink/specs/netdev.yaml).
+
 API interface
 =============
 The number of pools created **must** match the number of hardware queues
@@ -107,8 +112,9 @@ page_pool_get_stats() and structures described below are available.
 It takes a  pointer to a ``struct page_pool`` and a pointer to a struct
 page_pool_stats allocated by the caller.
 
-The API will fill in the provided struct page_pool_stats with
-statistics about the page_pool.
+Older drivers expose page pool statistics via ethtool or debugfs.
+The same statistics are accessible via the netlink netdev family
+in a driver-independent fashion.
 
 .. kernel-doc:: include/net/page_pool/types.h
    :identifiers: struct page_pool_recycle_stats
diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h
index 4ebd544ae977..7dc65774cde5 100644
--- a/include/net/page_pool/helpers.h
+++ b/include/net/page_pool/helpers.h
@@ -55,16 +55,12 @@
 #include <net/page_pool/types.h>
 
 #ifdef CONFIG_PAGE_POOL_STATS
+/* Deprecated driver-facing API, use netlink instead */
 int page_pool_ethtool_stats_get_count(void);
 u8 *page_pool_ethtool_stats_get_strings(u8 *data);
 u64 *page_pool_ethtool_stats_get(u64 *data, void *stats);
 
-/*
- * Drivers that wish to harvest page pool stats and report them to users
- * (perhaps via ethtool, debugfs, or another mechanism) can allocate a
- * struct page_pool_stats call page_pool_get_stats to get stats for the specified pool.
- */
-bool page_pool_get_stats(struct page_pool *pool,
+bool page_pool_get_stats(const struct page_pool *pool,
 			 struct page_pool_stats *stats);
 #else
 static inline int page_pool_ethtool_stats_get_count(void)
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index 756410274120..2b37233e00c0 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -76,6 +76,24 @@ enum {
 	NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1)
 };
 
+enum {
+	NETDEV_A_PAGE_POOL_STATS_INFO = 1,
+	NETDEV_A_PAGE_POOL_STATS_ALLOC_FAST = 8,
+	NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW,
+	NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW_HIGH_ORDER,
+	NETDEV_A_PAGE_POOL_STATS_ALLOC_EMPTY,
+	NETDEV_A_PAGE_POOL_STATS_ALLOC_REFILL,
+	NETDEV_A_PAGE_POOL_STATS_ALLOC_WAIVE,
+	NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHED,
+	NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHE_FULL,
+	NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING,
+	NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING_FULL,
+	NETDEV_A_PAGE_POOL_STATS_RECYCLE_RELEASED_REFCNT,
+
+	__NETDEV_A_PAGE_POOL_STATS_MAX,
+	NETDEV_A_PAGE_POOL_STATS_MAX = (__NETDEV_A_PAGE_POOL_STATS_MAX - 1)
+};
+
 enum {
 	NETDEV_CMD_DEV_GET = 1,
 	NETDEV_CMD_DEV_ADD_NTF,
@@ -85,6 +103,7 @@ enum {
 	NETDEV_CMD_PAGE_POOL_ADD_NTF,
 	NETDEV_CMD_PAGE_POOL_DEL_NTF,
 	NETDEV_CMD_PAGE_POOL_CHANGE_NTF,
+	NETDEV_CMD_PAGE_POOL_STATS_GET,
 
 	__NETDEV_CMD_MAX,
 	NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)
diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c
index 47fb5e1b6369..dccd8c3a141e 100644
--- a/net/core/netdev-genl-gen.c
+++ b/net/core/netdev-genl-gen.c
@@ -16,6 +16,17 @@ static const struct netlink_range_validation netdev_a_page_pool_id_range = {
 	.max	= 4294967295ULL,
 };
 
+static const struct netlink_range_validation netdev_a_page_pool_ifindex_range = {
+	.min	= 1ULL,
+	.max	= 2147483647ULL,
+};
+
+/* Common nested types */
+const struct nla_policy netdev_page_pool_info_nl_policy[NETDEV_A_PAGE_POOL_IFINDEX + 1] = {
+	[NETDEV_A_PAGE_POOL_ID] = NLA_POLICY_FULL_RANGE(NLA_UINT, &netdev_a_page_pool_id_range),
+	[NETDEV_A_PAGE_POOL_IFINDEX] = NLA_POLICY_FULL_RANGE(NLA_U32, &netdev_a_page_pool_ifindex_range),
+};
+
 /* NETDEV_CMD_DEV_GET - do */
 static const struct nla_policy netdev_dev_get_nl_policy[NETDEV_A_DEV_IFINDEX + 1] = {
 	[NETDEV_A_DEV_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1),
@@ -28,6 +39,13 @@ static const struct nla_policy netdev_page_pool_get_nl_policy[NETDEV_A_PAGE_POOL
 };
 #endif /* CONFIG_PAGE_POOL */
 
+/* NETDEV_CMD_PAGE_POOL_STATS_GET - do */
+#ifdef CONFIG_PAGE_POOL_STATS
+static const struct nla_policy netdev_page_pool_stats_get_nl_policy[NETDEV_A_PAGE_POOL_STATS_INFO + 1] = {
+	[NETDEV_A_PAGE_POOL_STATS_INFO] = NLA_POLICY_NESTED(netdev_page_pool_info_nl_policy),
+};
+#endif /* CONFIG_PAGE_POOL_STATS */
+
 /* Ops table for netdev */
 static const struct genl_split_ops netdev_nl_ops[] = {
 	{
@@ -56,6 +74,20 @@ static const struct genl_split_ops netdev_nl_ops[] = {
 		.flags	= GENL_CMD_CAP_DUMP,
 	},
 #endif /* CONFIG_PAGE_POOL */
+#ifdef CONFIG_PAGE_POOL_STATS
+	{
+		.cmd		= NETDEV_CMD_PAGE_POOL_STATS_GET,
+		.doit		= netdev_nl_page_pool_stats_get_doit,
+		.policy		= netdev_page_pool_stats_get_nl_policy,
+		.maxattr	= NETDEV_A_PAGE_POOL_STATS_INFO,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd	= NETDEV_CMD_PAGE_POOL_STATS_GET,
+		.dumpit	= netdev_nl_page_pool_stats_get_dumpit,
+		.flags	= GENL_CMD_CAP_DUMP,
+	},
+#endif /* CONFIG_PAGE_POOL_STATS */
 };
 
 static const struct genl_multicast_group netdev_nl_mcgrps[] = {
diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h
index 738097847100..649e4b46eccf 100644
--- a/net/core/netdev-genl-gen.h
+++ b/net/core/netdev-genl-gen.h
@@ -11,11 +11,18 @@
 
 #include <uapi/linux/netdev.h>
 
+/* Common nested types */
+extern const struct nla_policy netdev_page_pool_info_nl_policy[NETDEV_A_PAGE_POOL_IFINDEX + 1];
+
 int netdev_nl_dev_get_doit(struct sk_buff *skb, struct genl_info *info);
 int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
 int netdev_nl_page_pool_get_doit(struct sk_buff *skb, struct genl_info *info);
 int netdev_nl_page_pool_get_dumpit(struct sk_buff *skb,
 				   struct netlink_callback *cb);
+int netdev_nl_page_pool_stats_get_doit(struct sk_buff *skb,
+				       struct genl_info *info);
+int netdev_nl_page_pool_stats_get_dumpit(struct sk_buff *skb,
+					 struct netlink_callback *cb);
 
 enum {
 	NETDEV_NLGRP_MGMT,
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index a821fb5fe054..3d0938a60646 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -71,7 +71,7 @@ static const char pp_stats[][ETH_GSTRING_LEN] = {
  * is passed to this API which is filled in. The caller can then report
  * those stats to the user (perhaps via ethtool, debugfs, etc.).
  */
-bool page_pool_get_stats(struct page_pool *pool,
+bool page_pool_get_stats(const struct page_pool *pool,
 			 struct page_pool_stats *stats)
 {
 	int cpu = 0;
diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c
index bd5ca94f683f..1426434a7e15 100644
--- a/net/core/page_pool_user.c
+++ b/net/core/page_pool_user.c
@@ -5,6 +5,7 @@
 #include <linux/xarray.h>
 #include <net/net_debug.h>
 #include <net/page_pool/types.h>
+#include <net/page_pool/helpers.h>
 #include <net/sock.h>
 
 #include "page_pool_priv.h"
@@ -106,6 +107,108 @@ netdev_nl_page_pool_get_dump(struct sk_buff *skb, struct netlink_callback *cb,
 	return err;
 }
 
+static int
+page_pool_nl_stats_fill(struct sk_buff *rsp, const struct page_pool *pool,
+			const struct genl_info *info)
+{
+#ifdef CONFIG_PAGE_POOL_STATS
+	struct page_pool_stats stats = {};
+	struct nlattr *nest;
+	void *hdr;
+
+	if (!page_pool_get_stats(pool, &stats))
+		return 0;
+
+	hdr = genlmsg_iput(rsp, info);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	nest = nla_nest_start(rsp, NETDEV_A_PAGE_POOL_STATS_INFO);
+
+	if (nla_put_uint(rsp, NETDEV_A_PAGE_POOL_ID, pool->user.id) ||
+	    (pool->slow.netdev->ifindex != LOOPBACK_IFINDEX &&
+	     nla_put_u32(rsp, NETDEV_A_PAGE_POOL_IFINDEX,
+			 pool->slow.netdev->ifindex)))
+		goto err_cancel_nest;
+
+	nla_nest_end(rsp, nest);
+
+	if (nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_FAST,
+			 stats.alloc_stats.fast) ||
+	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW,
+			 stats.alloc_stats.slow) ||
+	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW_HIGH_ORDER,
+			 stats.alloc_stats.slow_high_order) ||
+	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_EMPTY,
+			 stats.alloc_stats.empty) ||
+	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_REFILL,
+			 stats.alloc_stats.refill) ||
+	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_WAIVE,
+			 stats.alloc_stats.waive) ||
+	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHED,
+			 stats.recycle_stats.cached) ||
+	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHE_FULL,
+			 stats.recycle_stats.cache_full) ||
+	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING,
+			 stats.recycle_stats.ring) ||
+	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING_FULL,
+			 stats.recycle_stats.ring_full) ||
+	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_RELEASED_REFCNT,
+			 stats.recycle_stats.released_refcnt))
+		goto err_cancel_msg;
+
+	genlmsg_end(rsp, hdr);
+
+	return 0;
+err_cancel_nest:
+	nla_nest_cancel(rsp, nest);
+err_cancel_msg:
+	genlmsg_cancel(rsp, hdr);
+	return -EMSGSIZE;
+#else
+	GENL_SET_ERR_MSG(info, "kernel built without CONFIG_PAGE_POOL_STATS");
+	return -EOPNOTSUPP;
+#endif
+}
+
+int netdev_nl_page_pool_stats_get_doit(struct sk_buff *skb,
+				       struct genl_info *info)
+{
+	struct nlattr *tb[ARRAY_SIZE(netdev_page_pool_info_nl_policy)];
+	struct nlattr *nest;
+	int err;
+	u32 id;
+
+	if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_PAGE_POOL_STATS_INFO))
+		return -EINVAL;
+
+	nest = info->attrs[NETDEV_A_PAGE_POOL_STATS_INFO];
+	err = nla_parse_nested(tb, ARRAY_SIZE(tb) - 1, nest,
+			       netdev_page_pool_info_nl_policy,
+			       info->extack);
+	if (err)
+		return err;
+
+	if (NL_REQ_ATTR_CHECK(info->extack, nest, tb, NETDEV_A_PAGE_POOL_ID))
+		return -EINVAL;
+	if (tb[NETDEV_A_PAGE_POOL_IFINDEX]) {
+		NL_SET_ERR_MSG_ATTR(info->extack,
+				    tb[NETDEV_A_PAGE_POOL_IFINDEX],
+				    "selecting by ifindex not supported");
+		return -EINVAL;
+	}
+
+	id = nla_get_uint(tb[NETDEV_A_PAGE_POOL_ID]);
+
+	return netdev_nl_page_pool_get_do(info, id, page_pool_nl_stats_fill);
+}
+
+int netdev_nl_page_pool_stats_get_dumpit(struct sk_buff *skb,
+					 struct netlink_callback *cb)
+{
+	return netdev_nl_page_pool_get_dump(skb, cb, page_pool_nl_stats_fill);
+}
+
 static int
 page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool,
 		  const struct genl_info *info)
-- 
cgit v1.2.3


From c392cbecd8eca4c53f2bf508731257d9d0a21c2d Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Mon, 27 Nov 2023 16:47:04 -0700
Subject: io_uring/kbuf: defer release of mapped buffer rings

If a provided buffer ring is setup with IOU_PBUF_RING_MMAP, then the
kernel allocates the memory for it and the application is expected to
mmap(2) this memory. However, io_uring uses remap_pfn_range() for this
operation, so we cannot rely on normal munmap/release on freeing them
for us.

Stash an io_buf_free entry away for each of these, if any, and provide
a helper to free them post ->release().

Cc: stable@vger.kernel.org
Fixes: c56e022c0a27 ("io_uring: add support for user mapped provided buffer ring")
Reported-by: Jann Horn <jannh@google.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/io_uring_types.h |  3 +++
 io_uring/io_uring.c            |  2 ++
 io_uring/kbuf.c                | 44 +++++++++++++++++++++++++++++++++++++-----
 io_uring/kbuf.h                |  2 ++
 4 files changed, 46 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index d3009d56af0b..805bb635cdf5 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -340,6 +340,9 @@ struct io_ring_ctx {
 
 	struct list_head	io_buffers_cache;
 
+	/* deferred free list, protected by ->uring_lock */
+	struct hlist_head	io_buf_list;
+
 	/* Keep this last, we don't need it for the fast path */
 	struct wait_queue_head		poll_wq;
 	struct io_restriction		restrictions;
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index e40b11438210..3a216f0744dd 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -325,6 +325,7 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
 	INIT_LIST_HEAD(&ctx->sqd_list);
 	INIT_LIST_HEAD(&ctx->cq_overflow_list);
 	INIT_LIST_HEAD(&ctx->io_buffers_cache);
+	INIT_HLIST_HEAD(&ctx->io_buf_list);
 	io_alloc_cache_init(&ctx->rsrc_node_cache, IO_NODE_ALLOC_CACHE_MAX,
 			    sizeof(struct io_rsrc_node));
 	io_alloc_cache_init(&ctx->apoll_cache, IO_ALLOC_CACHE_MAX,
@@ -2950,6 +2951,7 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx)
 		ctx->mm_account = NULL;
 	}
 	io_rings_free(ctx);
+	io_kbuf_mmap_list_free(ctx);
 
 	percpu_ref_exit(&ctx->refs);
 	free_uid(ctx->user);
diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c
index a1e4239c7d75..85e680fc74ce 100644
--- a/io_uring/kbuf.c
+++ b/io_uring/kbuf.c
@@ -33,6 +33,11 @@ struct io_provide_buf {
 	__u16				bid;
 };
 
+struct io_buf_free {
+	struct hlist_node		list;
+	void				*mem;
+};
+
 static inline struct io_buffer_list *io_buffer_get_list(struct io_ring_ctx *ctx,
 							unsigned int bgid)
 {
@@ -223,7 +228,10 @@ static int __io_remove_buffers(struct io_ring_ctx *ctx,
 	if (bl->is_mapped) {
 		i = bl->buf_ring->tail - bl->head;
 		if (bl->is_mmap) {
-			folio_put(virt_to_folio(bl->buf_ring));
+			/*
+			 * io_kbuf_list_free() will free the page(s) at
+			 * ->release() time.
+			 */
 			bl->buf_ring = NULL;
 			bl->is_mmap = 0;
 		} else if (bl->buf_nr_pages) {
@@ -531,18 +539,28 @@ error_unpin:
 	return -EINVAL;
 }
 
-static int io_alloc_pbuf_ring(struct io_uring_buf_reg *reg,
+static int io_alloc_pbuf_ring(struct io_ring_ctx *ctx,
+			      struct io_uring_buf_reg *reg,
 			      struct io_buffer_list *bl)
 {
-	gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO | __GFP_NOWARN | __GFP_COMP;
+	struct io_buf_free *ibf;
 	size_t ring_size;
 	void *ptr;
 
 	ring_size = reg->ring_entries * sizeof(struct io_uring_buf_ring);
-	ptr = (void *) __get_free_pages(gfp, get_order(ring_size));
+	ptr = io_mem_alloc(ring_size);
 	if (!ptr)
 		return -ENOMEM;
 
+	/* Allocate and store deferred free entry */
+	ibf = kmalloc(sizeof(*ibf), GFP_KERNEL_ACCOUNT);
+	if (!ibf) {
+		io_mem_free(ptr);
+		return -ENOMEM;
+	}
+	ibf->mem = ptr;
+	hlist_add_head(&ibf->list, &ctx->io_buf_list);
+
 	bl->buf_ring = ptr;
 	bl->is_mapped = 1;
 	bl->is_mmap = 1;
@@ -599,7 +617,7 @@ int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg)
 	if (!(reg.flags & IOU_PBUF_RING_MMAP))
 		ret = io_pin_pbuf_ring(&reg, bl);
 	else
-		ret = io_alloc_pbuf_ring(&reg, bl);
+		ret = io_alloc_pbuf_ring(ctx, &reg, bl);
 
 	if (!ret) {
 		bl->nr_entries = reg.ring_entries;
@@ -649,3 +667,19 @@ void *io_pbuf_get_address(struct io_ring_ctx *ctx, unsigned long bgid)
 
 	return bl->buf_ring;
 }
+
+/*
+ * Called at or after ->release(), free the mmap'ed buffers that we used
+ * for memory mapped provided buffer rings.
+ */
+void io_kbuf_mmap_list_free(struct io_ring_ctx *ctx)
+{
+	struct io_buf_free *ibf;
+	struct hlist_node *tmp;
+
+	hlist_for_each_entry_safe(ibf, tmp, &ctx->io_buf_list, list) {
+		hlist_del(&ibf->list);
+		io_mem_free(ibf->mem);
+		kfree(ibf);
+	}
+}
diff --git a/io_uring/kbuf.h b/io_uring/kbuf.h
index f2d615236b2c..6c7646e6057c 100644
--- a/io_uring/kbuf.h
+++ b/io_uring/kbuf.h
@@ -51,6 +51,8 @@ int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags);
 int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg);
 int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg);
 
+void io_kbuf_mmap_list_free(struct io_ring_ctx *ctx);
+
 unsigned int __io_put_kbuf(struct io_kiocb *req, unsigned issue_flags);
 
 bool io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags);
-- 
cgit v1.2.3


From 9a5f580c1c71b6aedba696c4898a7a7184cef8ad Mon Sep 17 00:00:00 2001
From: Muralidhara M K <muralidhara.mk@amd.com>
Date: Thu, 2 Nov 2023 11:42:24 +0000
Subject: EDAC/mc: Add support for HBM3 memory type

AMD MI300A models use HBM3 (High Bandwidth Memory Gen 3) memory. HBM is
a high-speed computer memory interface for 3D-stacked synchronous
dynamic random-access memory (SDRAM).

Signed-off-by: Muralidhara M K <muralidhara.mk@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20231102114225.2006878-4-muralimk@amd.com
---
 drivers/edac/edac_mc.c | 1 +
 include/linux/edac.h   | 3 +++
 2 files changed, 4 insertions(+)

(limited to 'include')

diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index 6faeb2ab3960..d6eed727b0cd 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -166,6 +166,7 @@ const char * const edac_mem_types[] = {
 	[MEM_NVDIMM]	= "Non-volatile-RAM",
 	[MEM_WIO2]	= "Wide-IO-2",
 	[MEM_HBM2]	= "High-bandwidth-memory-Gen2",
+	[MEM_HBM3]	= "High-bandwidth-memory-Gen3",
 };
 EXPORT_SYMBOL_GPL(edac_mem_types);
 
diff --git a/include/linux/edac.h b/include/linux/edac.h
index fa4bda2a70f6..1174beb94ab6 100644
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -187,6 +187,7 @@ static inline char *mc_event_error_type(const unsigned int err_type)
  * @MEM_NVDIMM:		Non-volatile RAM
  * @MEM_WIO2:		Wide I/O 2.
  * @MEM_HBM2:		High bandwidth Memory Gen 2.
+ * @MEM_HBM3:		High bandwidth Memory Gen 3.
  */
 enum mem_type {
 	MEM_EMPTY = 0,
@@ -218,6 +219,7 @@ enum mem_type {
 	MEM_NVDIMM,
 	MEM_WIO2,
 	MEM_HBM2,
+	MEM_HBM3,
 };
 
 #define MEM_FLAG_EMPTY		BIT(MEM_EMPTY)
@@ -248,6 +250,7 @@ enum mem_type {
 #define MEM_FLAG_NVDIMM		BIT(MEM_NVDIMM)
 #define MEM_FLAG_WIO2		BIT(MEM_WIO2)
 #define MEM_FLAG_HBM2		BIT(MEM_HBM2)
+#define MEM_FLAG_HBM3		BIT(MEM_HBM3)
 
 /**
  * enum edac_type - Error Detection and Correction capabilities and mode
-- 
cgit v1.2.3


From 0c0ea61c9b3a9e4df9cf029971f973cb12ccfef9 Mon Sep 17 00:00:00 2001
From: Zelong Dong <zelong.dong@amlogic.com>
Date: Thu, 14 Sep 2023 14:40:16 +0800
Subject: dt-bindings: reset: Add compatible and DT bindings for Amlogic C3
 Reset Controller

Add new compatible and DT bindings for Amlogic C3 Reset Controller

Signed-off-by: Zelong Dong <zelong.dong@amlogic.com>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Dmitry Rokosov <ddrokosov@sberdevices.ru>
Reviewed-by: Rob Herring <robh@kernel.org>
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20230914064018.18790-2-zelong.dong@amlogic.com
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 .../bindings/reset/amlogic,meson-reset.yaml        |   1 +
 include/dt-bindings/reset/amlogic,c3-reset.h       | 119 +++++++++++++++++++++
 2 files changed, 120 insertions(+)
 create mode 100644 include/dt-bindings/reset/amlogic,c3-reset.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/reset/amlogic,meson-reset.yaml b/Documentation/devicetree/bindings/reset/amlogic,meson-reset.yaml
index d3fdee89d4f8..f0c6c0df0ce3 100644
--- a/Documentation/devicetree/bindings/reset/amlogic,meson-reset.yaml
+++ b/Documentation/devicetree/bindings/reset/amlogic,meson-reset.yaml
@@ -18,6 +18,7 @@ properties:
       - amlogic,meson-axg-reset # Reset Controller on AXG and compatible SoCs
       - amlogic,meson-a1-reset # Reset Controller on A1 and compatible SoCs
       - amlogic,meson-s4-reset # Reset Controller on S4 and compatible SoCs
+      - amlogic,c3-reset # Reset Controller on C3 and compatible SoCs
 
   reg:
     maxItems: 1
diff --git a/include/dt-bindings/reset/amlogic,c3-reset.h b/include/dt-bindings/reset/amlogic,c3-reset.h
new file mode 100644
index 000000000000..d9127863f603
--- /dev/null
+++ b/include/dt-bindings/reset/amlogic,c3-reset.h
@@ -0,0 +1,119 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR MIT) */
+/*
+ * Copyright (c) 2023 Amlogic, Inc. All rights reserved.
+ */
+
+#ifndef _DT_BINDINGS_AMLOGIC_C3_RESET_H
+#define _DT_BINDINGS_AMLOGIC_C3_RESET_H
+
+/* RESET0 */
+/*						0-3 */
+#define RESET_USBCTRL				4
+/*						5-7 */
+#define RESET_USBPHY20				8
+/*						9 */
+#define RESET_USB2DRD				10
+#define RESET_MIPI_DSI_HOST			11
+#define RESET_MIPI_DSI_PHY			12
+/*						13-20 */
+#define RESET_GE2D				21
+#define RESET_DWAP				22
+/*						23-31 */
+
+/* RESET1 */
+#define RESET_AUDIO				32
+/*						33-34 */
+#define RESET_DDRAPB				35
+#define RESET_DDR				36
+#define RESET_DOS_CAPB3				37
+#define RESET_DOS				38
+/*						39-46 */
+#define RESET_NNA				47
+#define RESET_ETHERNET				48
+#define RESET_ISP				49
+#define RESET_VC9000E_APB			50
+#define RESET_VC9000E_A				51
+/*						52 */
+#define RESET_VC9000E_CORE			53
+/*						54-63 */
+
+/* RESET2 */
+#define RESET_ABUS_ARB				64
+#define RESET_IRCTRL				65
+/*						66 */
+#define RESET_TEMP_PII				67
+/*						68-72 */
+#define RESET_SPICC_0				73
+#define RESET_SPICC_1				74
+#define RESET_RSA				75
+
+/*						76-79 */
+#define RESET_MSR_CLK				80
+#define RESET_SPIFC				81
+#define RESET_SAR_ADC				82
+/*						83-87 */
+#define RESET_ACODEC				88
+/*						89-90 */
+#define RESET_WATCHDOG				91
+/*						92-95 */
+
+/* RESET3 */
+#define RESET_ISP_NIC_GPV			96
+#define RESET_ISP_NIC_MAIN			97
+#define RESET_ISP_NIC_VCLK			98
+#define RESET_ISP_NIC_VOUT			99
+#define RESET_ISP_NIC_ALL			100
+#define RESET_VOUT				101
+#define RESET_VOUT_VENC				102
+/*						103 */
+#define RESET_CVE_NIC_GPV			104
+#define RESET_CVE_NIC_MAIN			105
+#define RESET_CVE_NIC_GE2D			106
+#define RESET_CVE_NIC_DW			106
+#define RESET_CVE_NIC_CVE			108
+#define RESET_CVE_NIC_ALL			109
+#define RESET_CVE				110
+/*						112-127 */
+
+/* RESET4 */
+#define RESET_RTC				128
+#define RESET_PWM_AB				129
+#define RESET_PWM_CD				130
+#define RESET_PWM_EF				131
+#define RESET_PWM_GH				132
+#define RESET_PWM_IJ				133
+#define RESET_PWM_KL				134
+#define RESET_PWM_MN				135
+/*						136-137 */
+#define RESET_UART_A				138
+#define RESET_UART_B				139
+#define RESET_UART_C				140
+#define RESET_UART_D				141
+#define RESET_UART_E				142
+#define RESET_UART_F				143
+#define RESET_I2C_S_A				144
+#define RESET_I2C_M_A				145
+#define RESET_I2C_M_B				146
+#define RESET_I2C_M_C				147
+#define RESET_I2C_M_D				148
+/*						149-151 */
+#define RESET_SD_EMMC_A				152
+#define RESET_SD_EMMC_B				153
+#define RESET_SD_EMMC_C				154
+
+/* RESET5 */
+/*						160-172 */
+#define RESET_BRG_NIC_NNA			173
+#define RESET_BRG_MUX_NIC_MAIN			174
+#define RESET_BRG_AO_NIC_ALL			175
+/*						176-183 */
+#define RESET_BRG_NIC_VAPB			184
+#define RESET_BRG_NIC_SDIO_B			185
+#define RESET_BRG_NIC_SDIO_A			186
+#define RESET_BRG_NIC_EMMC			187
+#define RESET_BRG_NIC_DSU			188
+#define RESET_BRG_NIC_SYSCLK			189
+#define RESET_BRG_NIC_MAIN			190
+#define RESET_BRG_NIC_ALL			191
+
+#endif
-- 
cgit v1.2.3


From 5f23ffdf17e805218e56a9796bdc67497ab11bac Mon Sep 17 00:00:00 2001
From: Chao Yu <chao@kernel.org>
Date: Tue, 28 Nov 2023 17:31:29 +0800
Subject: f2fs: introduce tracepoint for f2fs_rename()

This patch adds tracepoints for f2fs_rename().

Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/namei.c             | 16 +++++++----
 include/trace/events/f2fs.h | 69 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 80 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index a765db9e26c2..ede6afb81762 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -1315,21 +1315,27 @@ static int f2fs_rename2(struct mnt_idmap *idmap,
 	if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT))
 		return -EINVAL;
 
+	trace_f2fs_rename_start(old_dir, old_dentry, new_dir, new_dentry,
+								flags);
+
 	err = fscrypt_prepare_rename(old_dir, old_dentry, new_dir, new_dentry,
 				     flags);
 	if (err)
 		return err;
 
-	if (flags & RENAME_EXCHANGE) {
-		return f2fs_cross_rename(old_dir, old_dentry,
-					 new_dir, new_dentry);
-	}
+	if (flags & RENAME_EXCHANGE)
+		err = f2fs_cross_rename(old_dir, old_dentry,
+					new_dir, new_dentry);
+	else
 	/*
 	 * VFS has already handled the new dentry existence case,
 	 * here, we just deal with "RENAME_NOREPLACE" as regular rename.
 	 */
-	return f2fs_rename(idmap, old_dir, old_dentry,
+		err = f2fs_rename(idmap, old_dir, old_dentry,
 					new_dir, new_dentry, flags);
+
+	trace_f2fs_rename_end(old_dentry, new_dentry, flags, err);
+	return err;
 }
 
 static const char *f2fs_encrypted_get_link(struct dentry *dentry,
diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
index 793f82cc1515..36d9e29ca3c5 100644
--- a/include/trace/events/f2fs.h
+++ b/include/trace/events/f2fs.h
@@ -866,6 +866,75 @@ TRACE_EVENT(f2fs_lookup_end,
 		__entry->err)
 );
 
+TRACE_EVENT(f2fs_rename_start,
+
+	TP_PROTO(struct inode *old_dir, struct dentry *old_dentry,
+			struct inode *new_dir, struct dentry *new_dentry,
+			unsigned int flags),
+
+	TP_ARGS(old_dir, old_dentry, new_dir, new_dentry, flags),
+
+	TP_STRUCT__entry(
+		__field(dev_t,		dev)
+		__field(ino_t,		ino)
+		__string(old_name,	old_dentry->d_name.name)
+		__field(ino_t,		new_pino)
+		__string(new_name,	new_dentry->d_name.name)
+		__field(unsigned int,	flags)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= old_dir->i_sb->s_dev;
+		__entry->ino		= old_dir->i_ino;
+		__assign_str(old_name, old_dentry->d_name.name);
+		__entry->new_pino	= new_dir->i_ino;
+		__assign_str(new_name, new_dentry->d_name.name);
+		__entry->flags		= flags;
+	),
+
+	TP_printk("dev = (%d,%d), old_dir = %lu, old_name: %s, "
+		"new_dir = %lu, new_name: %s, flags = %u",
+		show_dev_ino(__entry),
+		__get_str(old_name),
+		__entry->new_pino,
+		__get_str(new_name),
+		__entry->flags)
+);
+
+TRACE_EVENT(f2fs_rename_end,
+
+	TP_PROTO(struct dentry *old_dentry, struct dentry *new_dentry,
+			unsigned int flags, int ret),
+
+	TP_ARGS(old_dentry, new_dentry, flags, ret),
+
+	TP_STRUCT__entry(
+		__field(dev_t,		dev)
+		__field(ino_t,		ino)
+		__string(old_name,	old_dentry->d_name.name)
+		__string(new_name,	new_dentry->d_name.name)
+		__field(unsigned int,	flags)
+		__field(int,		ret)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= old_dentry->d_sb->s_dev;
+		__entry->ino		= old_dentry->d_inode->i_ino;
+		__assign_str(old_name, old_dentry->d_name.name);
+		__assign_str(new_name, new_dentry->d_name.name);
+		__entry->flags		= flags;
+		__entry->ret		= ret;
+	),
+
+	TP_printk("dev = (%d,%d), ino = %lu, old_name: %s, "
+		"new_name: %s, flags = %u, ret = %d",
+		show_dev_ino(__entry),
+		__get_str(old_name),
+		__get_str(new_name),
+		__entry->flags,
+		__entry->ret)
+);
+
 TRACE_EVENT(f2fs_readdir,
 
 	TP_PROTO(struct inode *dir, loff_t start_pos, loff_t end_pos, int err),
-- 
cgit v1.2.3


From 8e9cf55ef89c775fdaaa7c6212dbb691420a4673 Mon Sep 17 00:00:00 2001
From: Chao Yu <chao@kernel.org>
Date: Tue, 28 Nov 2023 17:31:30 +0800
Subject: f2fs: show i_mode in trace_f2fs_new_inode()

This patch supports to show i_mode field in trace_f2fs_new_inode().

Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 include/trace/events/f2fs.h | 19 ++++++++++++++++++-
 1 file changed, 18 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
index 36d9e29ca3c5..479d26eae22f 100644
--- a/include/trace/events/f2fs.h
+++ b/include/trace/events/f2fs.h
@@ -161,6 +161,19 @@ TRACE_DEFINE_ENUM(EX_BLOCK_AGE);
 		{ EX_READ,	"Read" },				\
 		{ EX_BLOCK_AGE,	"Block Age" })
 
+#define show_inode_type(x) \
+	__print_symbolic(x, \
+		{ S_IFLNK,		"symbolic" }, \
+		{ S_IFREG,		"regular" }, \
+		{ S_IFDIR,		"directory" }, \
+		{ S_IFCHR,		"character" }, \
+		{ S_IFBLK,		"block" }, \
+		{ S_IFIFO,		"fifo" }, \
+		{ S_IFSOCK,		"sock" })
+
+#define S_ALL_PERM	(S_ISUID | S_ISGID | S_ISVTX |	\
+			S_IRWXU | S_IRWXG | S_IRWXO)
+
 struct f2fs_sb_info;
 struct f2fs_io_info;
 struct extent_info;
@@ -215,17 +228,21 @@ DECLARE_EVENT_CLASS(f2fs__inode_exit,
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
 		__field(ino_t,	ino)
+		__field(umode_t, mode)
 		__field(int,	ret)
 	),
 
 	TP_fast_assign(
 		__entry->dev	= inode->i_sb->s_dev;
 		__entry->ino	= inode->i_ino;
+		__entry->mode	= inode->i_mode;
 		__entry->ret	= ret;
 	),
 
-	TP_printk("dev = (%d,%d), ino = %lu, ret = %d",
+	TP_printk("dev = (%d,%d), ino = %lu, type: %s, mode = 0%o, ret = %d",
 		show_dev_ino(__entry),
+		show_inode_type(__entry->mode & S_IFMT),
+		__entry->mode & S_ALL_PERM,
 		__entry->ret)
 );
 
-- 
cgit v1.2.3


From b9873755a6c8ccfce79094c4dce9efa3ecb1a749 Mon Sep 17 00:00:00 2001
From: Alexander Graf <graf@amazon.com>
Date: Wed, 11 Oct 2023 21:35:22 +0000
Subject: misc: Add Nitro Secure Module driver

When running Linux inside a Nitro Enclave, the hypervisor provides a
special virtio device called "Nitro Security Module" (NSM). This device
has 3 main functions:

  1) Provide attestation reports
  2) Modify PCR state
  3) Provide entropy

This patch adds a driver for NSM that exposes a /dev/nsm device node which
user space can issue an ioctl on this device with raw NSM CBOR formatted
commands to request attestation documents, influence PCR states, read
entropy and enumerate status of the device. In addition, the driver
implements a hwrng backend.

Originally-by: Petre Eftime <petre.eftime@gmail.com>
Signed-off-by: Alexander Graf <graf@amazon.com>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20231011213522.51781-1-graf@amazon.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 MAINTAINERS              |   9 +
 drivers/misc/Kconfig     |  13 ++
 drivers/misc/Makefile    |   1 +
 drivers/misc/nsm.c       | 506 +++++++++++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/nsm.h |  31 +++
 5 files changed, 560 insertions(+)
 create mode 100644 drivers/misc/nsm.c
 create mode 100644 include/uapi/linux/nsm.h

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index 012df8ccf34e..b9bbbd82742a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15291,6 +15291,15 @@ F:	include/linux/nitro_enclaves.h
 F:	include/uapi/linux/nitro_enclaves.h
 F:	samples/nitro_enclaves/
 
+NITRO SECURE MODULE (NSM)
+M:	Alexander Graf <graf@amazon.com>
+L:	linux-kernel@vger.kernel.org
+L:	The AWS Nitro Enclaves Team <aws-nitro-enclaves-devel@amazon.com>
+S:	Supported
+W:	https://aws.amazon.com/ec2/nitro/nitro-enclaves/
+F:	drivers/misc/nsm.c
+F:	include/uapi/linux/nsm.h
+
 NOHZ, DYNTICKS SUPPORT
 M:	Frederic Weisbecker <frederic@kernel.org>
 M:	Thomas Gleixner <tglx@linutronix.de>
diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index f37c4b8380ae..8932b6cf9595 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -562,6 +562,19 @@ config TPS6594_PFSM
 	  This driver can also be built as a module.  If so, the module
 	  will be called tps6594-pfsm.
 
+config NSM
+	tristate "Nitro (Enclaves) Security Module support"
+	depends on VIRTIO
+	select HW_RANDOM
+	select CBOR
+	help
+	  This driver provides support for the Nitro Security Module
+	  in AWS EC2 Nitro based Enclaves. The driver exposes a /dev/nsm
+	  device user space can use to communicate with the hypervisor.
+
+	  To compile this driver as a module, choose M here.
+	  The module will be called nsm.
+
 source "drivers/misc/c2port/Kconfig"
 source "drivers/misc/eeprom/Kconfig"
 source "drivers/misc/cb710/Kconfig"
diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile
index f2a4d1ff65d4..ea6ea5bbbc9c 100644
--- a/drivers/misc/Makefile
+++ b/drivers/misc/Makefile
@@ -67,3 +67,4 @@ obj-$(CONFIG_TMR_MANAGER)      += xilinx_tmr_manager.o
 obj-$(CONFIG_TMR_INJECT)	+= xilinx_tmr_inject.o
 obj-$(CONFIG_TPS6594_ESM)	+= tps6594-esm.o
 obj-$(CONFIG_TPS6594_PFSM)	+= tps6594-pfsm.o
+obj-$(CONFIG_NSM)		+= nsm.o
diff --git a/drivers/misc/nsm.c b/drivers/misc/nsm.c
new file mode 100644
index 000000000000..0eaa3b4484bd
--- /dev/null
+++ b/drivers/misc/nsm.c
@@ -0,0 +1,506 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Amazon Nitro Secure Module driver.
+ *
+ * Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+ *
+ * The Nitro Secure Module implements commands via CBOR over virtio.
+ * This driver exposes a raw message ioctls on /dev/nsm that user
+ * space can use to issue these commands.
+ */
+
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/interrupt.h>
+#include <linux/hw_random.h>
+#include <linux/miscdevice.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/uaccess.h>
+#include <linux/uio.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_ids.h>
+#include <linux/virtio.h>
+#include <linux/wait.h>
+#include <uapi/linux/nsm.h>
+
+/* Timeout for NSM virtqueue respose in milliseconds. */
+#define NSM_DEFAULT_TIMEOUT_MSECS (120000) /* 2 minutes */
+
+/* Maximum length input data */
+struct nsm_data_req {
+	u32 len;
+	u8  data[NSM_REQUEST_MAX_SIZE];
+};
+
+/* Maximum length output data */
+struct nsm_data_resp {
+	u32 len;
+	u8  data[NSM_RESPONSE_MAX_SIZE];
+};
+
+/* Full NSM request/response message */
+struct nsm_msg {
+	struct nsm_data_req req;
+	struct nsm_data_resp resp;
+};
+
+struct nsm {
+	struct virtio_device *vdev;
+	struct virtqueue     *vq;
+	struct mutex          lock;
+	struct completion     cmd_done;
+	struct miscdevice     misc;
+	struct hwrng          hwrng;
+	struct work_struct    misc_init;
+	struct nsm_msg        msg;
+};
+
+/* NSM device ID */
+static const struct virtio_device_id id_table[] = {
+	{ VIRTIO_ID_NITRO_SEC_MOD, VIRTIO_DEV_ANY_ID },
+	{ 0 },
+};
+
+static struct nsm *file_to_nsm(struct file *file)
+{
+	return container_of(file->private_data, struct nsm, misc);
+}
+
+static struct nsm *hwrng_to_nsm(struct hwrng *rng)
+{
+	return container_of(rng, struct nsm, hwrng);
+}
+
+#define CBOR_TYPE_MASK  0xE0
+#define CBOR_TYPE_MAP 0xA0
+#define CBOR_TYPE_TEXT 0x60
+#define CBOR_TYPE_ARRAY 0x40
+#define CBOR_HEADER_SIZE_SHORT 1
+
+#define CBOR_SHORT_SIZE_MAX_VALUE 23
+#define CBOR_LONG_SIZE_U8  24
+#define CBOR_LONG_SIZE_U16 25
+#define CBOR_LONG_SIZE_U32 26
+#define CBOR_LONG_SIZE_U64 27
+
+static bool cbor_object_is_array(const u8 *cbor_object, size_t cbor_object_size)
+{
+	if (cbor_object_size == 0 || cbor_object == NULL)
+		return false;
+
+	return (cbor_object[0] & CBOR_TYPE_MASK) == CBOR_TYPE_ARRAY;
+}
+
+static int cbor_object_get_array(u8 *cbor_object, size_t cbor_object_size, u8 **cbor_array)
+{
+	u8 cbor_short_size;
+	void *array_len_p;
+	u64 array_len;
+	u64 array_offset;
+
+	if (!cbor_object_is_array(cbor_object, cbor_object_size))
+		return -EFAULT;
+
+	cbor_short_size = (cbor_object[0] & 0x1F);
+
+	/* Decoding byte array length */
+	array_offset = CBOR_HEADER_SIZE_SHORT;
+	if (cbor_short_size >= CBOR_LONG_SIZE_U8)
+		array_offset += BIT(cbor_short_size - CBOR_LONG_SIZE_U8);
+
+	if (cbor_object_size < array_offset)
+		return -EFAULT;
+
+	array_len_p = &cbor_object[1];
+
+	switch (cbor_short_size) {
+	case CBOR_SHORT_SIZE_MAX_VALUE: /* short encoding */
+		array_len = cbor_short_size;
+		break;
+	case CBOR_LONG_SIZE_U8:
+		array_len = *(u8 *)array_len_p;
+		break;
+	case CBOR_LONG_SIZE_U16:
+		array_len = be16_to_cpup((__be16 *)array_len_p);
+		break;
+	case CBOR_LONG_SIZE_U32:
+		array_len = be32_to_cpup((__be32 *)array_len_p);
+		break;
+	case CBOR_LONG_SIZE_U64:
+		array_len = be64_to_cpup((__be64 *)array_len_p);
+		break;
+	}
+
+	if (cbor_object_size < array_offset)
+		return -EFAULT;
+
+	if (cbor_object_size - array_offset < array_len)
+		return -EFAULT;
+
+	if (array_len > INT_MAX)
+		return -EFAULT;
+
+	*cbor_array = cbor_object + array_offset;
+	return array_len;
+}
+
+/* Copy the request of a raw message to kernel space */
+static int fill_req_raw(struct nsm *nsm, struct nsm_data_req *req,
+			struct nsm_raw *raw)
+{
+	/* Verify the user input size. */
+	if (raw->request.len > sizeof(req->data))
+		return -EMSGSIZE;
+
+	/* Copy the request payload */
+	if (copy_from_user(req->data, u64_to_user_ptr(raw->request.addr),
+			   raw->request.len))
+		return -EFAULT;
+
+	req->len = raw->request.len;
+
+	return 0;
+}
+
+/* Copy the response of a raw message back to user-space */
+static int parse_resp_raw(struct nsm *nsm, struct nsm_data_resp *resp,
+			  struct nsm_raw *raw)
+{
+	/* Truncate any message that does not fit. */
+	raw->response.len = min_t(u64, raw->response.len, resp->len);
+
+	/* Copy the response content to user space */
+	if (copy_to_user(u64_to_user_ptr(raw->response.addr),
+			 resp->data, raw->response.len))
+		return -EFAULT;
+
+	return 0;
+}
+
+/* Virtqueue interrupt handler */
+static void nsm_vq_callback(struct virtqueue *vq)
+{
+	struct nsm *nsm = vq->vdev->priv;
+
+	complete(&nsm->cmd_done);
+}
+
+/* Forward a message to the NSM device and wait for the response from it */
+static int nsm_sendrecv_msg_locked(struct nsm *nsm)
+{
+	struct device *dev = &nsm->vdev->dev;
+	struct scatterlist sg_in, sg_out;
+	struct nsm_msg *msg = &nsm->msg;
+	struct virtqueue *vq = nsm->vq;
+	unsigned int len;
+	void *queue_buf;
+	bool kicked;
+	int rc;
+
+	/* Initialize scatter-gather lists with request and response buffers. */
+	sg_init_one(&sg_out, msg->req.data, msg->req.len);
+	sg_init_one(&sg_in, msg->resp.data, sizeof(msg->resp.data));
+
+	init_completion(&nsm->cmd_done);
+	/* Add the request buffer (read by the device). */
+	rc = virtqueue_add_outbuf(vq, &sg_out, 1, msg->req.data, GFP_KERNEL);
+	if (rc)
+		return rc;
+
+	/* Add the response buffer (written by the device). */
+	rc = virtqueue_add_inbuf(vq, &sg_in, 1, msg->resp.data, GFP_KERNEL);
+	if (rc)
+		goto cleanup;
+
+	kicked = virtqueue_kick(vq);
+	if (!kicked) {
+		/* Cannot kick the virtqueue. */
+		rc = -EIO;
+		goto cleanup;
+	}
+
+	/* If the kick succeeded, wait for the device's response. */
+	if (!wait_for_completion_io_timeout(&nsm->cmd_done,
+		msecs_to_jiffies(NSM_DEFAULT_TIMEOUT_MSECS))) {
+		rc = -ETIMEDOUT;
+		goto cleanup;
+	}
+
+	queue_buf = virtqueue_get_buf(vq, &len);
+	if (!queue_buf || (queue_buf != msg->req.data)) {
+		dev_err(dev, "wrong request buffer.");
+		rc = -ENODATA;
+		goto cleanup;
+	}
+
+	queue_buf = virtqueue_get_buf(vq, &len);
+	if (!queue_buf || (queue_buf != msg->resp.data)) {
+		dev_err(dev, "wrong response buffer.");
+		rc = -ENODATA;
+		goto cleanup;
+	}
+
+	msg->resp.len = len;
+
+	rc = 0;
+
+cleanup:
+	if (rc) {
+		/* Clean the virtqueue. */
+		while (virtqueue_get_buf(vq, &len) != NULL)
+			;
+	}
+
+	return rc;
+}
+
+static int fill_req_get_random(struct nsm *nsm, struct nsm_data_req *req)
+{
+	/*
+	 * 69                          # text(9)
+	 *     47657452616E646F6D      # "GetRandom"
+	 */
+	const u8 request[] = { CBOR_TYPE_TEXT + strlen("GetRandom"),
+			       'G', 'e', 't', 'R', 'a', 'n', 'd', 'o', 'm' };
+
+	memcpy(req->data, request, sizeof(request));
+	req->len = sizeof(request);
+
+	return 0;
+}
+
+static int parse_resp_get_random(struct nsm *nsm, struct nsm_data_resp *resp,
+				 void *out, size_t max)
+{
+	/*
+	 * A1                          # map(1)
+	 *     69                      # text(9) - Name of field
+	 *         47657452616E646F6D  # "GetRandom"
+	 * A1                          # map(1) - The field itself
+	 *     66                      # text(6)
+	 *         72616E646F6D        # "random"
+	 *	# The rest of the response is random data
+	 */
+	const u8 response[] = { CBOR_TYPE_MAP + 1,
+				CBOR_TYPE_TEXT + strlen("GetRandom"),
+				'G', 'e', 't', 'R', 'a', 'n', 'd', 'o', 'm',
+				CBOR_TYPE_MAP + 1,
+				CBOR_TYPE_TEXT + strlen("random"),
+				'r', 'a', 'n', 'd', 'o', 'm' };
+	struct device *dev = &nsm->vdev->dev;
+	u8 *rand_data = NULL;
+	u8 *resp_ptr = resp->data;
+	u64 resp_len = resp->len;
+	int rc;
+
+	if ((resp->len < sizeof(response) + 1) ||
+	    (memcmp(resp_ptr, response, sizeof(response)) != 0)) {
+		dev_err(dev, "Invalid response for GetRandom");
+		return -EFAULT;
+	}
+
+	resp_ptr += sizeof(response);
+	resp_len -= sizeof(response);
+
+	rc = cbor_object_get_array(resp_ptr, resp_len, &rand_data);
+	if (rc < 0) {
+		dev_err(dev, "GetRandom: Invalid CBOR encoding\n");
+		return rc;
+	}
+
+	rc = min_t(size_t, rc, max);
+	memcpy(out, rand_data, rc);
+
+	return rc;
+}
+
+/*
+ * HwRNG implementation
+ */
+static int nsm_rng_read(struct hwrng *rng, void *data, size_t max, bool wait)
+{
+	struct nsm *nsm = hwrng_to_nsm(rng);
+	struct device *dev = &nsm->vdev->dev;
+	int rc = 0;
+
+	/* NSM always needs to wait for a response */
+	if (!wait)
+		return 0;
+
+	mutex_lock(&nsm->lock);
+
+	rc = fill_req_get_random(nsm, &nsm->msg.req);
+	if (rc != 0)
+		goto out;
+
+	rc = nsm_sendrecv_msg_locked(nsm);
+	if (rc != 0)
+		goto out;
+
+	rc = parse_resp_get_random(nsm, &nsm->msg.resp, data, max);
+	if (rc < 0)
+		goto out;
+
+	dev_dbg(dev, "RNG: returning rand bytes = %d", rc);
+out:
+	mutex_unlock(&nsm->lock);
+	return rc;
+}
+
+static long nsm_dev_ioctl(struct file *file, unsigned int cmd,
+	unsigned long arg)
+{
+	void __user *argp = u64_to_user_ptr((u64)arg);
+	struct nsm *nsm = file_to_nsm(file);
+	struct nsm_raw raw;
+	int r = 0;
+
+	if (cmd != NSM_IOCTL_RAW)
+		return -EINVAL;
+
+	if (_IOC_SIZE(cmd) != sizeof(raw))
+		return -EINVAL;
+
+	/* Copy user argument struct to kernel argument struct */
+	r = -EFAULT;
+	if (copy_from_user(&raw, argp, _IOC_SIZE(cmd)))
+		goto out;
+
+	mutex_lock(&nsm->lock);
+
+	/* Convert kernel argument struct to device request */
+	r = fill_req_raw(nsm, &nsm->msg.req, &raw);
+	if (r)
+		goto out;
+
+	/* Send message to NSM and read reply */
+	r = nsm_sendrecv_msg_locked(nsm);
+	if (r)
+		goto out;
+
+	/* Parse device response into kernel argument struct */
+	r = parse_resp_raw(nsm, &nsm->msg.resp, &raw);
+	if (r)
+		goto out;
+
+	/* Copy kernel argument struct back to user argument struct */
+	r = -EFAULT;
+	if (copy_to_user(argp, &raw, sizeof(raw)))
+		goto out;
+
+	r = 0;
+
+out:
+	mutex_unlock(&nsm->lock);
+	return r;
+}
+
+static int nsm_device_init_vq(struct virtio_device *vdev)
+{
+	struct virtqueue *vq = virtio_find_single_vq(vdev,
+		nsm_vq_callback, "nsm.vq.0");
+	struct nsm *nsm = vdev->priv;
+
+	if (IS_ERR(vq))
+		return PTR_ERR(vq);
+
+	nsm->vq = vq;
+
+	return 0;
+}
+
+static const struct file_operations nsm_dev_fops = {
+	.unlocked_ioctl = nsm_dev_ioctl,
+	.compat_ioctl = compat_ptr_ioctl,
+};
+
+/* Handler for probing the NSM device */
+static int nsm_device_probe(struct virtio_device *vdev)
+{
+	struct device *dev = &vdev->dev;
+	struct nsm *nsm;
+	int rc;
+
+	nsm = devm_kzalloc(&vdev->dev, sizeof(*nsm), GFP_KERNEL);
+	if (!nsm)
+		return -ENOMEM;
+
+	vdev->priv = nsm;
+	nsm->vdev = vdev;
+
+	rc = nsm_device_init_vq(vdev);
+	if (rc) {
+		dev_err(dev, "queue failed to initialize: %d.\n", rc);
+		goto err_init_vq;
+	}
+
+	mutex_init(&nsm->lock);
+
+	/* Register as hwrng provider */
+	nsm->hwrng = (struct hwrng) {
+		.read = nsm_rng_read,
+		.name = "nsm-hwrng",
+		.quality = 1000,
+	};
+
+	rc = hwrng_register(&nsm->hwrng);
+	if (rc) {
+		dev_err(dev, "RNG initialization error: %d.\n", rc);
+		goto err_hwrng;
+	}
+
+	/* Register /dev/nsm device node */
+	nsm->misc = (struct miscdevice) {
+		.minor	= MISC_DYNAMIC_MINOR,
+		.name	= "nsm",
+		.fops	= &nsm_dev_fops,
+		.mode	= 0666,
+	};
+
+	rc = misc_register(&nsm->misc);
+	if (rc) {
+		dev_err(dev, "misc device registration error: %d.\n", rc);
+		goto err_misc;
+	}
+
+	return 0;
+
+err_misc:
+	hwrng_unregister(&nsm->hwrng);
+err_hwrng:
+	vdev->config->del_vqs(vdev);
+err_init_vq:
+	return rc;
+}
+
+/* Handler for removing the NSM device */
+static void nsm_device_remove(struct virtio_device *vdev)
+{
+	struct nsm *nsm = vdev->priv;
+
+	hwrng_unregister(&nsm->hwrng);
+
+	vdev->config->del_vqs(vdev);
+	misc_deregister(&nsm->misc);
+}
+
+/* NSM device configuration structure */
+static struct virtio_driver virtio_nsm_driver = {
+	.feature_table             = 0,
+	.feature_table_size        = 0,
+	.feature_table_legacy      = 0,
+	.feature_table_size_legacy = 0,
+	.driver.name               = KBUILD_MODNAME,
+	.driver.owner              = THIS_MODULE,
+	.id_table                  = id_table,
+	.probe                     = nsm_device_probe,
+	.remove                    = nsm_device_remove,
+};
+
+module_virtio_driver(virtio_nsm_driver);
+MODULE_DEVICE_TABLE(virtio, id_table);
+MODULE_DESCRIPTION("Virtio NSM driver");
+MODULE_LICENSE("GPL");
diff --git a/include/uapi/linux/nsm.h b/include/uapi/linux/nsm.h
new file mode 100644
index 000000000000..e529f232f6c0
--- /dev/null
+++ b/include/uapi/linux/nsm.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+ */
+
+#ifndef __UAPI_LINUX_NSM_H
+#define __UAPI_LINUX_NSM_H
+
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+#define NSM_MAGIC		0x0A
+
+#define NSM_REQUEST_MAX_SIZE	0x1000
+#define NSM_RESPONSE_MAX_SIZE	0x3000
+
+struct nsm_iovec {
+	__u64 addr; /* Virtual address of target buffer */
+	__u64 len;  /* Length of target buffer */
+};
+
+/* Raw NSM message. Only available with CAP_SYS_ADMIN. */
+struct nsm_raw {
+	/* Request from user */
+	struct nsm_iovec request;
+	/* Response to user */
+	struct nsm_iovec response;
+};
+#define NSM_IOCTL_RAW		_IOWR(NSM_MAGIC, 0x0, struct nsm_raw)
+
+#endif /* __UAPI_LINUX_NSM_H */
-- 
cgit v1.2.3


From fad907cffd4bde7384812cf32fcf69becab805cc Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Tue, 28 Nov 2023 20:30:26 +0800
Subject: block: move .bd_inode into 1st cacheline of block_device

The .bd_inode field of block_device is used in IO fast path of
blkdev_write_iter() and blkdev_llseek(), so it is more efficient to keep
it into the 1st cacheline.

.bd_openers is only touched in open()/close(), and .bd_size_lock is only
for updating bdev capacity, which is in slow path too.

So swap .bd_inode layout with .bd_openers & .bd_size_lock to move
.bd_inode into the 1st cache line.

Cc: Yu Kuai <yukuai3@huawei.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20231128123027.971610-2-yukuai1@huaweicloud.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blk_types.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index d5c5e59ddbd2..f7d40692dd94 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -49,9 +49,10 @@ struct block_device {
 	bool			bd_write_holder;
 	bool			bd_has_submit_bio;
 	dev_t			bd_dev;
+	struct inode		*bd_inode;	/* will die */
+
 	atomic_t		bd_openers;
 	spinlock_t		bd_size_lock; /* for bd_inode->i_size updates */
-	struct inode *		bd_inode;	/* will die */
 	void *			bd_claiming;
 	void *			bd_holder;
 	const struct blk_holder_ops *bd_holder_ops;
-- 
cgit v1.2.3


From 67d995e069535c32829f5d368d919063492cec6e Mon Sep 17 00:00:00 2001
From: Yu Kuai <yukuai3@huawei.com>
Date: Tue, 28 Nov 2023 20:30:27 +0800
Subject: block: warn once for each partition in bio_check_ro()

Commit 1b0a151c10a6 ("blk-core: use pr_warn_ratelimited() in
bio_check_ro()") fix message storm by limit the rate, however, there
will still be lots of message in the long term. Fix it better by warn
once for each partition.

Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20231128123027.971610-3-yukuai1@huaweicloud.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c          | 14 +++++++++++---
 include/linux/blk_types.h |  1 +
 2 files changed, 12 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/block/blk-core.c b/block/blk-core.c
index fdf25b8d6e78..2eca76ccf4ee 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -501,9 +501,17 @@ static inline void bio_check_ro(struct bio *bio)
 	if (op_is_write(bio_op(bio)) && bdev_read_only(bio->bi_bdev)) {
 		if (op_is_flush(bio->bi_opf) && !bio_sectors(bio))
 			return;
-		pr_warn_ratelimited("Trying to write to read-only block-device %pg\n",
-				    bio->bi_bdev);
-		/* Older lvm-tools actually trigger this */
+
+		if (bio->bi_bdev->bd_ro_warned)
+			return;
+
+		bio->bi_bdev->bd_ro_warned = true;
+		/*
+		 * Use ioctl to set underlying disk of raid/dm to read-only
+		 * will trigger this.
+		 */
+		pr_warn("Trying to write to read-only block-device %pg\n",
+			bio->bi_bdev);
 	}
 }
 
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index f7d40692dd94..b29ebd53417d 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -70,6 +70,7 @@ struct block_device {
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 	bool			bd_make_it_fail;
 #endif
+	bool			bd_ro_warned;
 	/*
 	 * keep this out-of-line as it's both big and not needed in the fast
 	 * path
-- 
cgit v1.2.3


From a3db64c575ca201c9783f100c70b82d52bd78a93 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Mon, 27 Nov 2023 13:37:09 +0100
Subject: tty: make tty const in tty_get_baud_rate()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

After commit 87888fb9ac0c ("tty: Remove baudrate dead code & make
ktermios params const"), the 'tty' parameter is only read in
tty_get_baud_rate(). Therefore, we can make 'tty' accepted in the
function 'const' for clarity.

The "the terminal bit flags may be updated." part of the
tty_get_baud_rate()'s kernel-doc is dropped as it is no longer true.
Because of the same commit above. And it was misplaced anyway.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Cc: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://lore.kernel.org/r/20231127123713.14504-1-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/tty.h | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/tty.h b/include/linux/tty.h
index 7625fc98fef3..e96c85f4f91e 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -440,10 +440,9 @@ void tty_encode_baud_rate(struct tty_struct *tty, speed_t ibaud,
  *
  * Returns: the baud rate as an integer for this terminal
  *
- * Locking: The termios lock must be held by the caller and the terminal bit
- * flags may be updated.
+ * Locking: The termios lock must be held by the caller.
  */
-static inline speed_t tty_get_baud_rate(struct tty_struct *tty)
+static inline speed_t tty_get_baud_rate(const struct tty_struct *tty)
 {
 	return tty_termios_baud_rate(&tty->termios);
 }
-- 
cgit v1.2.3


From eec4954b81c3d9a38b99e78afb553c359db40093 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 28 Nov 2023 10:28:15 +0000
Subject: driver core: make device_is_dependent() static

The function device_is_dependent() is only called by the driver core
internally and should not, at this time, be called by anyone else
outside of it, so mark it as static so as not to give driver authors the
wrong idea.

Cc: Saravana Kannan <saravanak@google.com>
Acked-by: "Rafael J. Wysocki" <rafael@kernel.org>
Link: https://lore.kernel.org/r/2023112815-faculty-thud-add8@gregkh
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/core.c    | 2 +-
 include/linux/device.h | 1 -
 2 files changed, 1 insertion(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/base/core.c b/drivers/base/core.c
index 67ba592afc77..e57467194104 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -298,7 +298,7 @@ static inline bool device_link_flag_is_sync_state_only(u32 flags)
  * Check if @target depends on @dev or any device dependent on it (its child or
  * its consumer etc).  Return 1 if that is the case or 0 otherwise.
  */
-int device_is_dependent(struct device *dev, void *target)
+static int device_is_dependent(struct device *dev, void *target)
 {
 	struct device_link *link;
 	int ret;
diff --git a/include/linux/device.h b/include/linux/device.h
index d7a72a8749ea..4aa34c8d1361 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -1071,7 +1071,6 @@ int device_rename(struct device *dev, const char *new_name);
 int device_move(struct device *dev, struct device *new_parent,
 		enum dpm_order dpm_order);
 int device_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid);
-int device_is_dependent(struct device *dev, void *target);
 
 static inline bool device_supports_offline(struct device *dev)
 {
-- 
cgit v1.2.3


From e56fdbfb06e26a7066b070967badef4148528df2 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Sat, 25 Nov 2023 20:31:27 +0100
Subject: bpf: Add link_info support for uprobe multi link

Adding support to get uprobe_link details through bpf_link_info
interface.

Adding new struct uprobe_multi to struct bpf_link_info to carry
the uprobe_multi link details.

The uprobe_multi.count is passed from user space to denote size
of array fields (offsets/ref_ctr_offsets/cookies). The actual
array size is stored back to uprobe_multi.count (allowing user
to find out the actual array size) and array fields are populated
up to the user passed size.

All the non-array fields (path/count/flags/pid) are always set.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/bpf/20231125193130.834322-4-jolsa@kernel.org
---
 include/uapi/linux/bpf.h       | 10 ++++++
 kernel/trace/bpf_trace.c       | 72 ++++++++++++++++++++++++++++++++++++++++++
 tools/include/uapi/linux/bpf.h | 10 ++++++
 3 files changed, 92 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 7a5498242eaa..e88746ba7d21 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -6562,6 +6562,16 @@ struct bpf_link_info {
 			__u32 flags;
 			__u64 missed;
 		} kprobe_multi;
+		struct {
+			__aligned_u64 path;
+			__aligned_u64 offsets;
+			__aligned_u64 ref_ctr_offsets;
+			__aligned_u64 cookies;
+			__u32 path_size; /* in/out: real path size on success, including zero byte */
+			__u32 count; /* in/out: uprobe_multi offsets/ref_ctr_offsets/cookies count */
+			__u32 flags;
+			__u32 pid;
+		} uprobe_multi;
 		struct {
 			__u32 type; /* enum bpf_perf_event_type */
 			__u32 :32;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index ad0323f27288..c284a4ad0315 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -3042,6 +3042,7 @@ struct bpf_uprobe_multi_link {
 	struct path path;
 	struct bpf_link link;
 	u32 cnt;
+	u32 flags;
 	struct bpf_uprobe *uprobes;
 	struct task_struct *task;
 };
@@ -3083,9 +3084,79 @@ static void bpf_uprobe_multi_link_dealloc(struct bpf_link *link)
 	kfree(umulti_link);
 }
 
+static int bpf_uprobe_multi_link_fill_link_info(const struct bpf_link *link,
+						struct bpf_link_info *info)
+{
+	u64 __user *uref_ctr_offsets = u64_to_user_ptr(info->uprobe_multi.ref_ctr_offsets);
+	u64 __user *ucookies = u64_to_user_ptr(info->uprobe_multi.cookies);
+	u64 __user *uoffsets = u64_to_user_ptr(info->uprobe_multi.offsets);
+	u64 __user *upath = u64_to_user_ptr(info->uprobe_multi.path);
+	u32 upath_size = info->uprobe_multi.path_size;
+	struct bpf_uprobe_multi_link *umulti_link;
+	u32 ucount = info->uprobe_multi.count;
+	int err = 0, i;
+	long left;
+
+	if (!upath ^ !upath_size)
+		return -EINVAL;
+
+	if ((uoffsets || uref_ctr_offsets || ucookies) && !ucount)
+		return -EINVAL;
+
+	umulti_link = container_of(link, struct bpf_uprobe_multi_link, link);
+	info->uprobe_multi.count = umulti_link->cnt;
+	info->uprobe_multi.flags = umulti_link->flags;
+	info->uprobe_multi.pid = umulti_link->task ?
+				 task_pid_nr_ns(umulti_link->task, task_active_pid_ns(current)) : 0;
+
+	if (upath) {
+		char *p, *buf;
+
+		upath_size = min_t(u32, upath_size, PATH_MAX);
+
+		buf = kmalloc(upath_size, GFP_KERNEL);
+		if (!buf)
+			return -ENOMEM;
+		p = d_path(&umulti_link->path, buf, upath_size);
+		if (IS_ERR(p)) {
+			kfree(buf);
+			return PTR_ERR(p);
+		}
+		upath_size = buf + upath_size - p;
+		left = copy_to_user(upath, p, upath_size);
+		kfree(buf);
+		if (left)
+			return -EFAULT;
+		info->uprobe_multi.path_size = upath_size;
+	}
+
+	if (!uoffsets && !ucookies && !uref_ctr_offsets)
+		return 0;
+
+	if (ucount < umulti_link->cnt)
+		err = -ENOSPC;
+	else
+		ucount = umulti_link->cnt;
+
+	for (i = 0; i < ucount; i++) {
+		if (uoffsets &&
+		    put_user(umulti_link->uprobes[i].offset, uoffsets + i))
+			return -EFAULT;
+		if (uref_ctr_offsets &&
+		    put_user(umulti_link->uprobes[i].ref_ctr_offset, uref_ctr_offsets + i))
+			return -EFAULT;
+		if (ucookies &&
+		    put_user(umulti_link->uprobes[i].cookie, ucookies + i))
+			return -EFAULT;
+	}
+
+	return err;
+}
+
 static const struct bpf_link_ops bpf_uprobe_multi_link_lops = {
 	.release = bpf_uprobe_multi_link_release,
 	.dealloc = bpf_uprobe_multi_link_dealloc,
+	.fill_link_info = bpf_uprobe_multi_link_fill_link_info,
 };
 
 static int uprobe_prog_run(struct bpf_uprobe *uprobe,
@@ -3274,6 +3345,7 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 	link->uprobes = uprobes;
 	link->path = path;
 	link->task = task;
+	link->flags = flags;
 
 	bpf_link_init(&link->link, BPF_LINK_TYPE_UPROBE_MULTI,
 		      &bpf_uprobe_multi_link_lops, prog);
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 7a5498242eaa..e88746ba7d21 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -6562,6 +6562,16 @@ struct bpf_link_info {
 			__u32 flags;
 			__u64 missed;
 		} kprobe_multi;
+		struct {
+			__aligned_u64 path;
+			__aligned_u64 offsets;
+			__aligned_u64 ref_ctr_offsets;
+			__aligned_u64 cookies;
+			__u32 path_size; /* in/out: real path size on success, including zero byte */
+			__u32 count; /* in/out: uprobe_multi offsets/ref_ctr_offsets/cookies count */
+			__u32 flags;
+			__u32 pid;
+		} uprobe_multi;
 		struct {
 			__u32 type; /* enum bpf_perf_event_type */
 			__u32 :32;
-- 
cgit v1.2.3


From 1162d267eabd6392d0d07bc88b75056e88042fc0 Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Date: Wed, 29 Nov 2023 14:53:17 +0200
Subject: ASoC: SOF: Add placeholder for platform IPC type and path overrides

Add a struct sof_loadable_file_profile which can be filled by platforms
(sof-acpi-dev.c, sof-of-dev.c and sof-acpi-dev.c) to be able to use common,
generic code to handle path customization.

Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Link: https://lore.kernel.org/r/20231129125327.23708-4-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/sof.h | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

(limited to 'include')

diff --git a/include/sound/sof.h b/include/sound/sof.h
index 268d0ca0f69f..05213bb515a3 100644
--- a/include/sound/sof.h
+++ b/include/sound/sof.h
@@ -57,6 +57,18 @@ enum sof_ipc_type {
 	SOF_IPC_TYPE_COUNT
 };
 
+struct sof_loadable_file_profile {
+	enum sof_ipc_type ipc_type;
+
+	const char *fw_path;
+	const char *fw_path_postfix;
+	const char *fw_name;
+	const char *fw_lib_path;
+	const char *fw_lib_path_postfix;
+	const char *tplg_path;
+	const char *tplg_name;
+};
+
 /*
  * SOF Platform data.
  */
@@ -86,6 +98,9 @@ struct snd_sof_pdata {
 	/* descriptor */
 	const struct sof_dev_desc *desc;
 
+	/* platform's preferred IPC type and path overrides */
+	struct sof_loadable_file_profile ipc_file_profile_base;
+
 	/* firmware and topology filenames */
 	const char *fw_filename_prefix;
 	const char *fw_filename;
-- 
cgit v1.2.3


From 5431fdd2c181dd2eac218e45b44deb2925fa48f0 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Sun, 17 Sep 2023 13:24:21 +0200
Subject: ptrace: Convert ptrace_attach() to use lock guards

Created as testing for the conditional guard infrastructure.
Specifically this makes use of the following form:

  scoped_cond_guard (mutex_intr, return -ERESTARTNOINTR,
		     &task->signal->cred_guard_mutex) {
    ...
  }
  ...
  return 0;

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Link: https://lkml.kernel.org/r/20231102110706.568467727%40infradead.org
---
 include/linux/sched/task.h |   2 +
 include/linux/spinlock.h   |  26 +++++++++
 kernel/ptrace.c            | 128 +++++++++++++++++++++------------------------
 3 files changed, 89 insertions(+), 67 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index a23af225c898..4f3dca353556 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -226,4 +226,6 @@ static inline void task_unlock(struct task_struct *p)
 	spin_unlock(&p->alloc_lock);
 }
 
+DEFINE_GUARD(task_lock, struct task_struct *, task_lock(_T), task_unlock(_T))
+
 #endif /* _LINUX_SCHED_TASK_H */
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index ceb56b39c70f..90bc853cafb6 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -548,5 +548,31 @@ DEFINE_LOCK_GUARD_1(spinlock_irqsave, spinlock_t,
 DEFINE_LOCK_GUARD_1_COND(spinlock_irqsave, _try,
 			 spin_trylock_irqsave(_T->lock, _T->flags))
 
+DEFINE_LOCK_GUARD_1(read_lock, rwlock_t,
+		    read_lock(_T->lock),
+		    read_unlock(_T->lock))
+
+DEFINE_LOCK_GUARD_1(read_lock_irq, rwlock_t,
+		    read_lock_irq(_T->lock),
+		    read_unlock_irq(_T->lock))
+
+DEFINE_LOCK_GUARD_1(read_lock_irqsave, rwlock_t,
+		    read_lock_irqsave(_T->lock, _T->flags),
+		    read_unlock_irqrestore(_T->lock, _T->flags),
+		    unsigned long flags)
+
+DEFINE_LOCK_GUARD_1(write_lock, rwlock_t,
+		    write_lock(_T->lock),
+		    write_unlock(_T->lock))
+
+DEFINE_LOCK_GUARD_1(write_lock_irq, rwlock_t,
+		    write_lock_irq(_T->lock),
+		    write_unlock_irq(_T->lock))
+
+DEFINE_LOCK_GUARD_1(write_lock_irqsave, rwlock_t,
+		    write_lock_irqsave(_T->lock, _T->flags),
+		    write_unlock_irqrestore(_T->lock, _T->flags),
+		    unsigned long flags)
+
 #undef __LINUX_INSIDE_SPINLOCK_H
 #endif /* __LINUX_SPINLOCK_H */
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index d8b5e13a2229..5c579fb9a5e3 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -386,6 +386,34 @@ static int check_ptrace_options(unsigned long data)
 	return 0;
 }
 
+static inline void ptrace_set_stopped(struct task_struct *task)
+{
+	guard(spinlock)(&task->sighand->siglock);
+
+	/*
+	 * If the task is already STOPPED, set JOBCTL_TRAP_STOP and
+	 * TRAPPING, and kick it so that it transits to TRACED.  TRAPPING
+	 * will be cleared if the child completes the transition or any
+	 * event which clears the group stop states happens.  We'll wait
+	 * for the transition to complete before returning from this
+	 * function.
+	 *
+	 * This hides STOPPED -> RUNNING -> TRACED transition from the
+	 * attaching thread but a different thread in the same group can
+	 * still observe the transient RUNNING state.  IOW, if another
+	 * thread's WNOHANG wait(2) on the stopped tracee races against
+	 * ATTACH, the wait(2) may fail due to the transient RUNNING.
+	 *
+	 * The following task_is_stopped() test is safe as both transitions
+	 * in and out of STOPPED are protected by siglock.
+	 */
+	if (task_is_stopped(task) &&
+	    task_set_jobctl_pending(task, JOBCTL_TRAP_STOP | JOBCTL_TRAPPING)) {
+		task->jobctl &= ~JOBCTL_STOPPED;
+		signal_wake_up_state(task, __TASK_STOPPED);
+	}
+}
+
 static int ptrace_attach(struct task_struct *task, long request,
 			 unsigned long addr,
 			 unsigned long flags)
@@ -393,17 +421,17 @@ static int ptrace_attach(struct task_struct *task, long request,
 	bool seize = (request == PTRACE_SEIZE);
 	int retval;
 
-	retval = -EIO;
 	if (seize) {
 		if (addr != 0)
-			goto out;
+			return -EIO;
 		/*
 		 * This duplicates the check in check_ptrace_options() because
 		 * ptrace_attach() and ptrace_setoptions() have historically
 		 * used different error codes for unknown ptrace options.
 		 */
 		if (flags & ~(unsigned long)PTRACE_O_MASK)
-			goto out;
+			return -EIO;
+
 		retval = check_ptrace_options(flags);
 		if (retval)
 			return retval;
@@ -414,88 +442,54 @@ static int ptrace_attach(struct task_struct *task, long request,
 
 	audit_ptrace(task);
 
-	retval = -EPERM;
 	if (unlikely(task->flags & PF_KTHREAD))
-		goto out;
+		return -EPERM;
 	if (same_thread_group(task, current))
-		goto out;
+		return -EPERM;
 
 	/*
 	 * Protect exec's credential calculations against our interference;
 	 * SUID, SGID and LSM creds get determined differently
 	 * under ptrace.
 	 */
-	retval = -ERESTARTNOINTR;
-	if (mutex_lock_interruptible(&task->signal->cred_guard_mutex))
-		goto out;
+	scoped_cond_guard (mutex_intr, return -ERESTARTNOINTR,
+			   &task->signal->cred_guard_mutex) {
 
-	task_lock(task);
-	retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS);
-	task_unlock(task);
-	if (retval)
-		goto unlock_creds;
+		scoped_guard (task_lock, task) {
+			retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS);
+			if (retval)
+				return retval;
+		}
 
-	write_lock_irq(&tasklist_lock);
-	retval = -EPERM;
-	if (unlikely(task->exit_state))
-		goto unlock_tasklist;
-	if (task->ptrace)
-		goto unlock_tasklist;
+		scoped_guard (write_lock_irq, &tasklist_lock) {
+			if (unlikely(task->exit_state))
+				return -EPERM;
+			if (task->ptrace)
+				return -EPERM;
 
-	task->ptrace = flags;
+			task->ptrace = flags;
 
-	ptrace_link(task, current);
+			ptrace_link(task, current);
 
-	/* SEIZE doesn't trap tracee on attach */
-	if (!seize)
-		send_sig_info(SIGSTOP, SEND_SIG_PRIV, task);
+			/* SEIZE doesn't trap tracee on attach */
+			if (!seize)
+				send_sig_info(SIGSTOP, SEND_SIG_PRIV, task);
 
-	spin_lock(&task->sighand->siglock);
+			ptrace_set_stopped(task);
+		}
+	}
 
 	/*
-	 * If the task is already STOPPED, set JOBCTL_TRAP_STOP and
-	 * TRAPPING, and kick it so that it transits to TRACED.  TRAPPING
-	 * will be cleared if the child completes the transition or any
-	 * event which clears the group stop states happens.  We'll wait
-	 * for the transition to complete before returning from this
-	 * function.
-	 *
-	 * This hides STOPPED -> RUNNING -> TRACED transition from the
-	 * attaching thread but a different thread in the same group can
-	 * still observe the transient RUNNING state.  IOW, if another
-	 * thread's WNOHANG wait(2) on the stopped tracee races against
-	 * ATTACH, the wait(2) may fail due to the transient RUNNING.
-	 *
-	 * The following task_is_stopped() test is safe as both transitions
-	 * in and out of STOPPED are protected by siglock.
+	 * We do not bother to change retval or clear JOBCTL_TRAPPING
+	 * if wait_on_bit() was interrupted by SIGKILL. The tracer will
+	 * not return to user-mode, it will exit and clear this bit in
+	 * __ptrace_unlink() if it wasn't already cleared by the tracee;
+	 * and until then nobody can ptrace this task.
 	 */
-	if (task_is_stopped(task) &&
-	    task_set_jobctl_pending(task, JOBCTL_TRAP_STOP | JOBCTL_TRAPPING)) {
-		task->jobctl &= ~JOBCTL_STOPPED;
-		signal_wake_up_state(task, __TASK_STOPPED);
-	}
-
-	spin_unlock(&task->sighand->siglock);
-
-	retval = 0;
-unlock_tasklist:
-	write_unlock_irq(&tasklist_lock);
-unlock_creds:
-	mutex_unlock(&task->signal->cred_guard_mutex);
-out:
-	if (!retval) {
-		/*
-		 * We do not bother to change retval or clear JOBCTL_TRAPPING
-		 * if wait_on_bit() was interrupted by SIGKILL. The tracer will
-		 * not return to user-mode, it will exit and clear this bit in
-		 * __ptrace_unlink() if it wasn't already cleared by the tracee;
-		 * and until then nobody can ptrace this task.
-		 */
-		wait_on_bit(&task->jobctl, JOBCTL_TRAPPING_BIT, TASK_KILLABLE);
-		proc_ptrace_connector(task, PTRACE_ATTACH);
-	}
+	wait_on_bit(&task->jobctl, JOBCTL_TRAPPING_BIT, TASK_KILLABLE);
+	proc_ptrace_connector(task, PTRACE_ATTACH);
 
-	return retval;
+	return 0;
 }
 
 /**
-- 
cgit v1.2.3


From febab20caebac959fdc3d7520bc52de8b1184455 Mon Sep 17 00:00:00 2001
From: Wyes Karny <wyes.karny@amd.com>
Date: Fri, 17 Nov 2023 06:38:39 +0000
Subject: cpufreq/amd-pstate: Fix scaling_min_freq and scaling_max_freq update

When amd_pstate is running, writing to scaling_min_freq and
scaling_max_freq has no effect. These values are only passed to the
policy level, but not to the platform level. This means that the
platform does not know about the frequency limits set by the user.

To fix this, update the min_perf and max_perf values at the platform
level whenever the user changes the scaling_min_freq and scaling_max_freq
values.

Fixes: ffa5096a7c33 ("cpufreq: amd-pstate: implement Pstate EPP support for the AMD processors")
Acked-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Wyes Karny <wyes.karny@amd.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/amd-pstate.c | 60 ++++++++++++++++++++++++++++++++++----------
 include/linux/amd-pstate.h   |  4 +++
 2 files changed, 51 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 300f81d36291..3313d1d2c6dd 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -307,11 +307,11 @@ static int pstate_init_perf(struct amd_cpudata *cpudata)
 		highest_perf = AMD_CPPC_HIGHEST_PERF(cap1);
 
 	WRITE_ONCE(cpudata->highest_perf, highest_perf);
-
+	WRITE_ONCE(cpudata->max_limit_perf, highest_perf);
 	WRITE_ONCE(cpudata->nominal_perf, AMD_CPPC_NOMINAL_PERF(cap1));
 	WRITE_ONCE(cpudata->lowest_nonlinear_perf, AMD_CPPC_LOWNONLIN_PERF(cap1));
 	WRITE_ONCE(cpudata->lowest_perf, AMD_CPPC_LOWEST_PERF(cap1));
-
+	WRITE_ONCE(cpudata->min_limit_perf, AMD_CPPC_LOWEST_PERF(cap1));
 	return 0;
 }
 
@@ -329,11 +329,12 @@ static int cppc_init_perf(struct amd_cpudata *cpudata)
 		highest_perf = cppc_perf.highest_perf;
 
 	WRITE_ONCE(cpudata->highest_perf, highest_perf);
-
+	WRITE_ONCE(cpudata->max_limit_perf, highest_perf);
 	WRITE_ONCE(cpudata->nominal_perf, cppc_perf.nominal_perf);
 	WRITE_ONCE(cpudata->lowest_nonlinear_perf,
 		   cppc_perf.lowest_nonlinear_perf);
 	WRITE_ONCE(cpudata->lowest_perf, cppc_perf.lowest_perf);
+	WRITE_ONCE(cpudata->min_limit_perf, cppc_perf.lowest_perf);
 
 	if (cppc_state == AMD_PSTATE_ACTIVE)
 		return 0;
@@ -432,6 +433,10 @@ static void amd_pstate_update(struct amd_cpudata *cpudata, u32 min_perf,
 	u64 prev = READ_ONCE(cpudata->cppc_req_cached);
 	u64 value = prev;
 
+	min_perf = clamp_t(unsigned long, min_perf, cpudata->min_limit_perf,
+			cpudata->max_limit_perf);
+	max_perf = clamp_t(unsigned long, max_perf, cpudata->min_limit_perf,
+			cpudata->max_limit_perf);
 	des_perf = clamp_t(unsigned long, des_perf, min_perf, max_perf);
 
 	if ((cppc_state == AMD_PSTATE_GUIDED) && (gov_flags & CPUFREQ_GOV_DYNAMIC_SWITCHING)) {
@@ -470,6 +475,22 @@ static int amd_pstate_verify(struct cpufreq_policy_data *policy)
 	return 0;
 }
 
+static int amd_pstate_update_min_max_limit(struct cpufreq_policy *policy)
+{
+	u32 max_limit_perf, min_limit_perf;
+	struct amd_cpudata *cpudata = policy->driver_data;
+
+	max_limit_perf = div_u64(policy->max * cpudata->highest_perf, cpudata->max_freq);
+	min_limit_perf = div_u64(policy->min * cpudata->highest_perf, cpudata->max_freq);
+
+	WRITE_ONCE(cpudata->max_limit_perf, max_limit_perf);
+	WRITE_ONCE(cpudata->min_limit_perf, min_limit_perf);
+	WRITE_ONCE(cpudata->max_limit_freq, policy->max);
+	WRITE_ONCE(cpudata->min_limit_freq, policy->min);
+
+	return 0;
+}
+
 static int amd_pstate_update_freq(struct cpufreq_policy *policy,
 				  unsigned int target_freq, bool fast_switch)
 {
@@ -480,6 +501,9 @@ static int amd_pstate_update_freq(struct cpufreq_policy *policy,
 	if (!cpudata->max_freq)
 		return -ENODEV;
 
+	if (policy->min != cpudata->min_limit_freq || policy->max != cpudata->max_limit_freq)
+		amd_pstate_update_min_max_limit(policy);
+
 	cap_perf = READ_ONCE(cpudata->highest_perf);
 	min_perf = READ_ONCE(cpudata->lowest_perf);
 	max_perf = cap_perf;
@@ -534,6 +558,10 @@ static void amd_pstate_adjust_perf(unsigned int cpu,
 	struct amd_cpudata *cpudata = policy->driver_data;
 	unsigned int target_freq;
 
+	if (policy->min != cpudata->min_limit_freq || policy->max != cpudata->max_limit_freq)
+		amd_pstate_update_min_max_limit(policy);
+
+
 	cap_perf = READ_ONCE(cpudata->highest_perf);
 	lowest_nonlinear_perf = READ_ONCE(cpudata->lowest_nonlinear_perf);
 	max_freq = READ_ONCE(cpudata->max_freq);
@@ -747,6 +775,8 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy)
 	/* Initial processor data capability frequencies */
 	cpudata->max_freq = max_freq;
 	cpudata->min_freq = min_freq;
+	cpudata->max_limit_freq = max_freq;
+	cpudata->min_limit_freq = min_freq;
 	cpudata->nominal_freq = nominal_freq;
 	cpudata->lowest_nonlinear_freq = lowest_nonlinear_freq;
 
@@ -1185,16 +1215,25 @@ static int amd_pstate_epp_cpu_exit(struct cpufreq_policy *policy)
 	return 0;
 }
 
-static void amd_pstate_epp_init(unsigned int cpu)
+static void amd_pstate_epp_update_limit(struct cpufreq_policy *policy)
 {
-	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
 	struct amd_cpudata *cpudata = policy->driver_data;
-	u32 max_perf, min_perf;
+	u32 max_perf, min_perf, min_limit_perf, max_limit_perf;
 	u64 value;
 	s16 epp;
 
 	max_perf = READ_ONCE(cpudata->highest_perf);
 	min_perf = READ_ONCE(cpudata->lowest_perf);
+	max_limit_perf = div_u64(policy->max * cpudata->highest_perf, cpudata->max_freq);
+	min_limit_perf = div_u64(policy->min * cpudata->highest_perf, cpudata->max_freq);
+
+	max_perf = clamp_t(unsigned long, max_perf, cpudata->min_limit_perf,
+			cpudata->max_limit_perf);
+	min_perf = clamp_t(unsigned long, min_perf, cpudata->min_limit_perf,
+			cpudata->max_limit_perf);
+
+	WRITE_ONCE(cpudata->max_limit_perf, max_limit_perf);
+	WRITE_ONCE(cpudata->min_limit_perf, min_limit_perf);
 
 	value = READ_ONCE(cpudata->cppc_req_cached);
 
@@ -1212,9 +1251,6 @@ static void amd_pstate_epp_init(unsigned int cpu)
 	value &= ~AMD_CPPC_DES_PERF(~0L);
 	value |= AMD_CPPC_DES_PERF(0);
 
-	if (cpudata->epp_policy == cpudata->policy)
-		goto skip_epp;
-
 	cpudata->epp_policy = cpudata->policy;
 
 	/* Get BIOS pre-defined epp value */
@@ -1224,7 +1260,7 @@ static void amd_pstate_epp_init(unsigned int cpu)
 		 * This return value can only be negative for shared_memory
 		 * systems where EPP register read/write not supported.
 		 */
-		goto skip_epp;
+		return;
 	}
 
 	if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE)
@@ -1238,8 +1274,6 @@ static void amd_pstate_epp_init(unsigned int cpu)
 
 	WRITE_ONCE(cpudata->cppc_req_cached, value);
 	amd_pstate_set_epp(cpudata, epp);
-skip_epp:
-	cpufreq_cpu_put(policy);
 }
 
 static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy)
@@ -1254,7 +1288,7 @@ static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy)
 
 	cpudata->policy = policy->policy;
 
-	amd_pstate_epp_init(policy->cpu);
+	amd_pstate_epp_update_limit(policy);
 
 	return 0;
 }
diff --git a/include/linux/amd-pstate.h b/include/linux/amd-pstate.h
index 446394f84606..6ad02ad9c7b4 100644
--- a/include/linux/amd-pstate.h
+++ b/include/linux/amd-pstate.h
@@ -70,6 +70,10 @@ struct amd_cpudata {
 	u32	nominal_perf;
 	u32	lowest_nonlinear_perf;
 	u32	lowest_perf;
+	u32     min_limit_perf;
+	u32     max_limit_perf;
+	u32     min_limit_freq;
+	u32     max_limit_freq;
 
 	u32	max_freq;
 	u32	min_freq;
-- 
cgit v1.2.3


From 341ac980eab90ac1f6c22ee9f9da83ed9604d899 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Mon, 27 Nov 2023 11:03:07 -0800
Subject: xsk: Support tx_metadata_len

For zerocopy mode, tx_desc->addr can point to an arbitrary offset
and carry some TX metadata in the headroom. For copy mode, there
is no way currently to populate skb metadata.

Introduce new tx_metadata_len umem config option that indicates how many
bytes to treat as metadata. Metadata bytes come prior to tx_desc address
(same as in RX case).

The size of the metadata has mostly the same constraints as XDP:
- less than 256 bytes
- 8-byte aligned (compared to 4-byte alignment on xdp, due to 8-byte
  timestamp in the completion)
- non-zero

This data is not interpreted in any way right now.

Reviewed-by: Song Yoong Siang <yoong.siang.song@intel.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20231127190319.1190813-2-sdf@google.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/net/xdp_sock.h            |  1 +
 include/net/xsk_buff_pool.h       |  1 +
 include/uapi/linux/if_xdp.h       |  1 +
 net/xdp/xdp_umem.c                |  4 ++++
 net/xdp/xsk.c                     | 12 +++++++++++-
 net/xdp/xsk_buff_pool.c           |  1 +
 net/xdp/xsk_queue.h               | 17 ++++++++++-------
 tools/include/uapi/linux/if_xdp.h |  1 +
 8 files changed, 30 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index f83128007fb0..bcf765124f72 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -30,6 +30,7 @@ struct xdp_umem {
 	struct user_struct *user;
 	refcount_t users;
 	u8 flags;
+	u8 tx_metadata_len;
 	bool zc;
 	struct page **pgs;
 	int id;
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index b0bdff26fc88..1985ffaf9b0c 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -77,6 +77,7 @@ struct xsk_buff_pool {
 	u32 chunk_size;
 	u32 chunk_shift;
 	u32 frame_len;
+	u8 tx_metadata_len; /* inherited from umem */
 	u8 cached_need_wakeup;
 	bool uses_need_wakeup;
 	bool dma_need_sync;
diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h
index 8d48863472b9..2ecf79282c26 100644
--- a/include/uapi/linux/if_xdp.h
+++ b/include/uapi/linux/if_xdp.h
@@ -76,6 +76,7 @@ struct xdp_umem_reg {
 	__u32 chunk_size;
 	__u32 headroom;
 	__u32 flags;
+	__u32 tx_metadata_len;
 };
 
 struct xdp_statistics {
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index 06cead2b8e34..946a687fb8e8 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -199,6 +199,9 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 	if (headroom >= chunk_size - XDP_PACKET_HEADROOM)
 		return -EINVAL;
 
+	if (mr->tx_metadata_len >= 256 || mr->tx_metadata_len % 8)
+		return -EINVAL;
+
 	umem->size = size;
 	umem->headroom = headroom;
 	umem->chunk_size = chunk_size;
@@ -207,6 +210,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 	umem->pgs = NULL;
 	umem->user = NULL;
 	umem->flags = mr->flags;
+	umem->tx_metadata_len = mr->tx_metadata_len;
 
 	INIT_LIST_HEAD(&umem->xsk_dma_list);
 	refcount_set(&umem->users, 1);
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index ae9f8cb611f6..c904356e2800 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -1283,6 +1283,14 @@ struct xdp_umem_reg_v1 {
 	__u32 headroom;
 };
 
+struct xdp_umem_reg_v2 {
+	__u64 addr; /* Start of packet data area */
+	__u64 len; /* Length of packet data area */
+	__u32 chunk_size;
+	__u32 headroom;
+	__u32 flags;
+};
+
 static int xsk_setsockopt(struct socket *sock, int level, int optname,
 			  sockptr_t optval, unsigned int optlen)
 {
@@ -1326,8 +1334,10 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
 
 		if (optlen < sizeof(struct xdp_umem_reg_v1))
 			return -EINVAL;
-		else if (optlen < sizeof(mr))
+		else if (optlen < sizeof(struct xdp_umem_reg_v2))
 			mr_size = sizeof(struct xdp_umem_reg_v1);
+		else if (optlen < sizeof(mr))
+			mr_size = sizeof(struct xdp_umem_reg_v2);
 
 		if (copy_from_sockptr(&mr, optval, mr_size))
 			return -EFAULT;
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 49cb9f9a09be..386eddcdf837 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -85,6 +85,7 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
 		XDP_PACKET_HEADROOM;
 	pool->umem = umem;
 	pool->addrs = umem->addrs;
+	pool->tx_metadata_len = umem->tx_metadata_len;
 	INIT_LIST_HEAD(&pool->free_list);
 	INIT_LIST_HEAD(&pool->xskb_list);
 	INIT_LIST_HEAD(&pool->xsk_tx_list);
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index 13354a1e4280..c74a1372bcb9 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -143,15 +143,17 @@ static inline bool xp_unused_options_set(u32 options)
 static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool,
 					    struct xdp_desc *desc)
 {
-	u64 offset = desc->addr & (pool->chunk_size - 1);
+	u64 addr = desc->addr - pool->tx_metadata_len;
+	u64 len = desc->len + pool->tx_metadata_len;
+	u64 offset = addr & (pool->chunk_size - 1);
 
 	if (!desc->len)
 		return false;
 
-	if (offset + desc->len > pool->chunk_size)
+	if (offset + len > pool->chunk_size)
 		return false;
 
-	if (desc->addr >= pool->addrs_cnt)
+	if (addr >= pool->addrs_cnt)
 		return false;
 
 	if (xp_unused_options_set(desc->options))
@@ -162,16 +164,17 @@ static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool,
 static inline bool xp_unaligned_validate_desc(struct xsk_buff_pool *pool,
 					      struct xdp_desc *desc)
 {
-	u64 addr = xp_unaligned_add_offset_to_addr(desc->addr);
+	u64 addr = xp_unaligned_add_offset_to_addr(desc->addr) - pool->tx_metadata_len;
+	u64 len = desc->len + pool->tx_metadata_len;
 
 	if (!desc->len)
 		return false;
 
-	if (desc->len > pool->chunk_size)
+	if (len > pool->chunk_size)
 		return false;
 
-	if (addr >= pool->addrs_cnt || addr + desc->len > pool->addrs_cnt ||
-	    xp_desc_crosses_non_contig_pg(pool, addr, desc->len))
+	if (addr >= pool->addrs_cnt || addr + len > pool->addrs_cnt ||
+	    xp_desc_crosses_non_contig_pg(pool, addr, len))
 		return false;
 
 	if (xp_unused_options_set(desc->options))
diff --git a/tools/include/uapi/linux/if_xdp.h b/tools/include/uapi/linux/if_xdp.h
index 73a47da885dc..34411a2e5b6c 100644
--- a/tools/include/uapi/linux/if_xdp.h
+++ b/tools/include/uapi/linux/if_xdp.h
@@ -76,6 +76,7 @@ struct xdp_umem_reg {
 	__u32 chunk_size;
 	__u32 headroom;
 	__u32 flags;
+	__u32 tx_metadata_len;
 };
 
 struct xdp_statistics {
-- 
cgit v1.2.3


From 48eb03dd26304c24f03bdbb9382e89c8564e71df Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Mon, 27 Nov 2023 11:03:08 -0800
Subject: xsk: Add TX timestamp and TX checksum offload support

This change actually defines the (initial) metadata layout
that should be used by AF_XDP userspace (xsk_tx_metadata).
The first field is flags which requests appropriate offloads,
followed by the offload-specific fields. The supported per-device
offloads are exported via netlink (new xsk-flags).

The offloads themselves are still implemented in a bit of a
framework-y fashion that's left from my initial kfunc attempt.
I'm introducing new xsk_tx_metadata_ops which drivers are
supposed to implement. The drivers are also supposed
to call xsk_tx_metadata_request/xsk_tx_metadata_complete in
the right places. Since xsk_tx_metadata_{request,_complete}
are static inline, we don't incur any extra overhead doing
indirect calls.

The benefit of this scheme is as follows:
- keeps all metadata layout parsing away from driver code
- makes it easy to grep and see which drivers implement what
- don't need any extra flags to maintain to keep track of what
  offloads are implemented; if the callback is implemented - the offload
  is supported (used by netlink reporting code)

Two offloads are defined right now:
1. XDP_TXMD_FLAGS_CHECKSUM: skb-style csum_start+csum_offset
2. XDP_TXMD_FLAGS_TIMESTAMP: writes TX timestamp back into metadata
   area upon completion (tx_timestamp field)

XDP_TXMD_FLAGS_TIMESTAMP is also implemented for XDP_COPY mode: it writes
SW timestamp from the skb destructor (note I'm reusing hwtstamps to pass
metadata pointer).

The struct is forward-compatible and can be extended in the future
by appending more fields.

Reviewed-by: Song Yoong Siang <yoong.siang.song@intel.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20231127190319.1190813-3-sdf@google.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 Documentation/netlink/specs/netdev.yaml |  19 +++++-
 include/linux/netdevice.h               |   2 +
 include/linux/skbuff.h                  |  14 +++-
 include/net/xdp_sock.h                  | 110 ++++++++++++++++++++++++++++++++
 include/net/xdp_sock_drv.h              |  13 ++++
 include/net/xsk_buff_pool.h             |   6 ++
 include/uapi/linux/if_xdp.h             |  38 +++++++++++
 include/uapi/linux/netdev.h             |  16 +++++
 net/core/netdev-genl.c                  |  13 +++-
 net/xdp/xsk.c                           |  34 ++++++++++
 net/xdp/xsk_queue.h                     |   2 +-
 tools/include/uapi/linux/if_xdp.h       |  52 +++++++++++++--
 tools/include/uapi/linux/netdev.h       |  16 +++++
 tools/net/ynl/generated/netdev-user.c   |  19 ++++++
 tools/net/ynl/generated/netdev-user.h   |   3 +
 15 files changed, 348 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index 14511b13f305..00439bcbd2e3 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -45,7 +45,6 @@ definitions:
   -
     type: flags
     name: xdp-rx-metadata
-    render-max: true
     entries:
       -
         name: timestamp
@@ -55,6 +54,18 @@ definitions:
         name: hash
         doc:
           Device is capable of exposing receive packet hash via bpf_xdp_metadata_rx_hash().
+  -
+    type: flags
+    name: xsk-flags
+    entries:
+      -
+        name: tx-timestamp
+        doc:
+          HW timestamping egress packets is supported by the driver.
+      -
+        name: tx-checksum
+        doc:
+          L3 checksum HW offload is supported by the driver.
 
 attribute-sets:
   -
@@ -86,6 +97,11 @@ attribute-sets:
              See Documentation/networking/xdp-rx-metadata.rst for more details.
         type: u64
         enum: xdp-rx-metadata
+      -
+        name: xsk-features
+        doc: Bitmask of enabled AF_XDP features.
+        type: u64
+        enum: xsk-flags
 
 operations:
   list:
@@ -103,6 +119,7 @@ operations:
             - xdp-features
             - xdp-zc-max-segs
             - xdp-rx-metadata-features
+            - xsk-features
       dump:
         reply: *dev-all
     -
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index e87caa81f70c..08da8b28c816 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1865,6 +1865,7 @@ enum netdev_stat_type {
  *	@netdev_ops:	Includes several pointers to callbacks,
  *			if one wants to override the ndo_*() functions
  *	@xdp_metadata_ops:	Includes pointers to XDP metadata callbacks.
+ *	@xsk_tx_metadata_ops:	Includes pointers to AF_XDP TX metadata callbacks.
  *	@ethtool_ops:	Management operations
  *	@l3mdev_ops:	Layer 3 master device operations
  *	@ndisc_ops:	Includes callbacks for different IPv6 neighbour
@@ -2128,6 +2129,7 @@ struct net_device {
 	unsigned long long	priv_flags;
 	const struct net_device_ops *netdev_ops;
 	const struct xdp_metadata_ops *xdp_metadata_ops;
+	const struct xsk_tx_metadata_ops *xsk_tx_metadata_ops;
 	int			ifindex;
 	unsigned short		gflags;
 	unsigned short		hard_header_len;
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 27998f73183e..b370eb8d70f7 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -566,6 +566,15 @@ struct ubuf_info_msgzc {
 int mm_account_pinned_pages(struct mmpin *mmp, size_t size);
 void mm_unaccount_pinned_pages(struct mmpin *mmp);
 
+/* Preserve some data across TX submission and completion.
+ *
+ * Note, this state is stored in the driver. Extending the layout
+ * might need some special care.
+ */
+struct xsk_tx_metadata_compl {
+	__u64 *tx_timestamp;
+};
+
 /* This data is invariant across clones and lives at
  * the end of the header data, ie. at skb->end.
  */
@@ -578,7 +587,10 @@ struct skb_shared_info {
 	/* Warning: this field is not always filled in (UFO)! */
 	unsigned short	gso_segs;
 	struct sk_buff	*frag_list;
-	struct skb_shared_hwtstamps hwtstamps;
+	union {
+		struct skb_shared_hwtstamps hwtstamps;
+		struct xsk_tx_metadata_compl xsk_meta;
+	};
 	unsigned int	gso_type;
 	u32		tskey;
 
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index bcf765124f72..3cb4dc9bd70e 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -93,12 +93,105 @@ struct xdp_sock {
 	struct xsk_queue *cq_tmp; /* Only as tmp storage before bind */
 };
 
+/*
+ * AF_XDP TX metadata hooks for network devices.
+ * The following hooks can be defined; unless noted otherwise, they are
+ * optional and can be filled with a null pointer.
+ *
+ * void (*tmo_request_timestamp)(void *priv)
+ *     Called when AF_XDP frame requested egress timestamp.
+ *
+ * u64 (*tmo_fill_timestamp)(void *priv)
+ *     Called when AF_XDP frame, that had requested egress timestamp,
+ *     received a completion. The hook needs to return the actual HW timestamp.
+ *
+ * void (*tmo_request_checksum)(u16 csum_start, u16 csum_offset, void *priv)
+ *     Called when AF_XDP frame requested HW checksum offload. csum_start
+ *     indicates position where checksumming should start.
+ *     csum_offset indicates position where checksum should be stored.
+ *
+ */
+struct xsk_tx_metadata_ops {
+	void	(*tmo_request_timestamp)(void *priv);
+	u64	(*tmo_fill_timestamp)(void *priv);
+	void	(*tmo_request_checksum)(u16 csum_start, u16 csum_offset, void *priv);
+};
+
 #ifdef CONFIG_XDP_SOCKETS
 
 int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp);
 int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp);
 void __xsk_map_flush(void);
 
+/**
+ *  xsk_tx_metadata_to_compl - Save enough relevant metadata information
+ *  to perform tx completion in the future.
+ *  @meta: pointer to AF_XDP metadata area
+ *  @compl: pointer to output struct xsk_tx_metadata_to_compl
+ *
+ *  This function should be called by the networking device when
+ *  it prepares AF_XDP egress packet. The value of @compl should be stored
+ *  and passed to xsk_tx_metadata_complete upon TX completion.
+ */
+static inline void xsk_tx_metadata_to_compl(struct xsk_tx_metadata *meta,
+					    struct xsk_tx_metadata_compl *compl)
+{
+	if (!meta)
+		return;
+
+	if (meta->flags & XDP_TXMD_FLAGS_TIMESTAMP)
+		compl->tx_timestamp = &meta->completion.tx_timestamp;
+	else
+		compl->tx_timestamp = NULL;
+}
+
+/**
+ *  xsk_tx_metadata_request - Evaluate AF_XDP TX metadata at submission
+ *  and call appropriate xsk_tx_metadata_ops operation.
+ *  @meta: pointer to AF_XDP metadata area
+ *  @ops: pointer to struct xsk_tx_metadata_ops
+ *  @priv: pointer to driver-private aread
+ *
+ *  This function should be called by the networking device when
+ *  it prepares AF_XDP egress packet.
+ */
+static inline void xsk_tx_metadata_request(const struct xsk_tx_metadata *meta,
+					   const struct xsk_tx_metadata_ops *ops,
+					   void *priv)
+{
+	if (!meta)
+		return;
+
+	if (ops->tmo_request_timestamp)
+		if (meta->flags & XDP_TXMD_FLAGS_TIMESTAMP)
+			ops->tmo_request_timestamp(priv);
+
+	if (ops->tmo_request_checksum)
+		if (meta->flags & XDP_TXMD_FLAGS_CHECKSUM)
+			ops->tmo_request_checksum(meta->request.csum_start,
+						  meta->request.csum_offset, priv);
+}
+
+/**
+ *  xsk_tx_metadata_complete - Evaluate AF_XDP TX metadata at completion
+ *  and call appropriate xsk_tx_metadata_ops operation.
+ *  @compl: pointer to completion metadata produced from xsk_tx_metadata_to_compl
+ *  @ops: pointer to struct xsk_tx_metadata_ops
+ *  @priv: pointer to driver-private aread
+ *
+ *  This function should be called by the networking device upon
+ *  AF_XDP egress completion.
+ */
+static inline void xsk_tx_metadata_complete(struct xsk_tx_metadata_compl *compl,
+					    const struct xsk_tx_metadata_ops *ops,
+					    void *priv)
+{
+	if (!compl)
+		return;
+
+	*compl->tx_timestamp = ops->tmo_fill_timestamp(priv);
+}
+
 #else
 
 static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
@@ -115,6 +208,23 @@ static inline void __xsk_map_flush(void)
 {
 }
 
+static inline void xsk_tx_metadata_to_compl(struct xsk_tx_metadata *meta,
+					    struct xsk_tx_metadata_compl *compl)
+{
+}
+
+static inline void xsk_tx_metadata_request(struct xsk_tx_metadata *meta,
+					   const struct xsk_tx_metadata_ops *ops,
+					   void *priv)
+{
+}
+
+static inline void xsk_tx_metadata_complete(struct xsk_tx_metadata_compl *compl,
+					    const struct xsk_tx_metadata_ops *ops,
+					    void *priv)
+{
+}
+
 #endif /* CONFIG_XDP_SOCKETS */
 
 #if defined(CONFIG_XDP_SOCKETS) && defined(CONFIG_DEBUG_NET)
diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index 1f6fc8c7a84c..e2558ac3e195 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -165,6 +165,14 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
 	return xp_raw_get_data(pool, addr);
 }
 
+static inline struct xsk_tx_metadata *xsk_buff_get_metadata(struct xsk_buff_pool *pool, u64 addr)
+{
+	if (!pool->tx_metadata_len)
+		return NULL;
+
+	return xp_raw_get_data(pool, addr) - pool->tx_metadata_len;
+}
+
 static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool)
 {
 	struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
@@ -324,6 +332,11 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
 	return NULL;
 }
 
+static inline struct xsk_tx_metadata *xsk_buff_get_metadata(struct xsk_buff_pool *pool, u64 addr)
+{
+	return NULL;
+}
+
 static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool)
 {
 }
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index 1985ffaf9b0c..97f5cc10d79e 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -33,6 +33,7 @@ struct xdp_buff_xsk {
 };
 
 #define XSK_CHECK_PRIV_TYPE(t) BUILD_BUG_ON(sizeof(t) > offsetofend(struct xdp_buff_xsk, cb))
+#define XSK_TX_COMPL_FITS(t) BUILD_BUG_ON(sizeof(struct xsk_tx_metadata_compl) > sizeof(t))
 
 struct xsk_dma_map {
 	dma_addr_t *dma_pages;
@@ -234,4 +235,9 @@ static inline u64 xp_get_handle(struct xdp_buff_xsk *xskb)
 	return xskb->orig_addr + (offset << XSK_UNALIGNED_BUF_OFFSET_SHIFT);
 }
 
+static inline bool xp_tx_metadata_enabled(const struct xsk_buff_pool *pool)
+{
+	return pool->tx_metadata_len > 0;
+}
+
 #endif /* XSK_BUFF_POOL_H_ */
diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h
index 2ecf79282c26..95de66d5a26c 100644
--- a/include/uapi/linux/if_xdp.h
+++ b/include/uapi/linux/if_xdp.h
@@ -106,6 +106,41 @@ struct xdp_options {
 #define XSK_UNALIGNED_BUF_ADDR_MASK \
 	((1ULL << XSK_UNALIGNED_BUF_OFFSET_SHIFT) - 1)
 
+/* Request transmit timestamp. Upon completion, put it into tx_timestamp
+ * field of struct xsk_tx_metadata.
+ */
+#define XDP_TXMD_FLAGS_TIMESTAMP		(1 << 0)
+
+/* Request transmit checksum offload. Checksum start position and offset
+ * are communicated via csum_start and csum_offset fields of struct
+ * xsk_tx_metadata.
+ */
+#define XDP_TXMD_FLAGS_CHECKSUM			(1 << 1)
+
+/* AF_XDP offloads request. 'request' union member is consumed by the driver
+ * when the packet is being transmitted. 'completion' union member is
+ * filled by the driver when the transmit completion arrives.
+ */
+struct xsk_tx_metadata {
+	__u64 flags;
+
+	union {
+		struct {
+			/* XDP_TXMD_FLAGS_CHECKSUM */
+
+			/* Offset from desc->addr where checksumming should start. */
+			__u16 csum_start;
+			/* Offset from csum_start where checksum should be stored. */
+			__u16 csum_offset;
+		} request;
+
+		struct {
+			/* XDP_TXMD_FLAGS_TIMESTAMP */
+			__u64 tx_timestamp;
+		} completion;
+	};
+};
+
 /* Rx/Tx descriptor */
 struct xdp_desc {
 	__u64 addr;
@@ -122,4 +157,7 @@ struct xdp_desc {
  */
 #define XDP_PKT_CONTD (1 << 0)
 
+/* TX packet carries valid metadata. */
+#define XDP_TX_METADATA (1 << 1)
+
 #endif /* _LINUX_IF_XDP_H */
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index 2943a151d4f1..48d5477a668c 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -53,12 +53,28 @@ enum netdev_xdp_rx_metadata {
 	NETDEV_XDP_RX_METADATA_MASK = 3,
 };
 
+/**
+ * enum netdev_xsk_flags
+ * @NETDEV_XSK_FLAGS_TX_TIMESTAMP: HW timestamping egress packets is supported
+ *   by the driver.
+ * @NETDEV_XSK_FLAGS_TX_CHECKSUM: L3 checksum HW offload is supported by the
+ *   driver.
+ */
+enum netdev_xsk_flags {
+	NETDEV_XSK_FLAGS_TX_TIMESTAMP = 1,
+	NETDEV_XSK_FLAGS_TX_CHECKSUM = 2,
+
+	/* private: */
+	NETDEV_XSK_FLAGS_MASK = 3,
+};
+
 enum {
 	NETDEV_A_DEV_IFINDEX = 1,
 	NETDEV_A_DEV_PAD,
 	NETDEV_A_DEV_XDP_FEATURES,
 	NETDEV_A_DEV_XDP_ZC_MAX_SEGS,
 	NETDEV_A_DEV_XDP_RX_METADATA_FEATURES,
+	NETDEV_A_DEV_XSK_FEATURES,
 
 	__NETDEV_A_DEV_MAX,
 	NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1)
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index fe61f85bcf33..10f2124e9e23 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -6,6 +6,7 @@
 #include <net/net_namespace.h>
 #include <net/sock.h>
 #include <net/xdp.h>
+#include <net/xdp_sock.h>
 
 #include "netdev-genl-gen.h"
 
@@ -13,6 +14,7 @@ static int
 netdev_nl_dev_fill(struct net_device *netdev, struct sk_buff *rsp,
 		   const struct genl_info *info)
 {
+	u64 xsk_features = 0;
 	u64 xdp_rx_meta = 0;
 	void *hdr;
 
@@ -26,11 +28,20 @@ netdev_nl_dev_fill(struct net_device *netdev, struct sk_buff *rsp,
 XDP_METADATA_KFUNC_xxx
 #undef XDP_METADATA_KFUNC
 
+	if (netdev->xsk_tx_metadata_ops) {
+		if (netdev->xsk_tx_metadata_ops->tmo_fill_timestamp)
+			xsk_features |= NETDEV_XSK_FLAGS_TX_TIMESTAMP;
+		if (netdev->xsk_tx_metadata_ops->tmo_request_checksum)
+			xsk_features |= NETDEV_XSK_FLAGS_TX_CHECKSUM;
+	}
+
 	if (nla_put_u32(rsp, NETDEV_A_DEV_IFINDEX, netdev->ifindex) ||
 	    nla_put_u64_64bit(rsp, NETDEV_A_DEV_XDP_FEATURES,
 			      netdev->xdp_features, NETDEV_A_DEV_PAD) ||
 	    nla_put_u64_64bit(rsp, NETDEV_A_DEV_XDP_RX_METADATA_FEATURES,
-			      xdp_rx_meta, NETDEV_A_DEV_PAD)) {
+			      xdp_rx_meta, NETDEV_A_DEV_PAD) ||
+	    nla_put_u64_64bit(rsp, NETDEV_A_DEV_XSK_FEATURES,
+			      xsk_features, NETDEV_A_DEV_PAD)) {
 		genlmsg_cancel(rsp, hdr);
 		return -EINVAL;
 	}
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index c904356e2800..e83ade32f1fd 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -571,6 +571,13 @@ static u32 xsk_get_num_desc(struct sk_buff *skb)
 
 static void xsk_destruct_skb(struct sk_buff *skb)
 {
+	struct xsk_tx_metadata_compl *compl = &skb_shinfo(skb)->xsk_meta;
+
+	if (compl->tx_timestamp) {
+		/* sw completion timestamp, not a real one */
+		*compl->tx_timestamp = ktime_get_tai_fast_ns();
+	}
+
 	xsk_cq_submit_locked(xdp_sk(skb->sk), xsk_get_num_desc(skb));
 	sock_wfree(skb);
 }
@@ -655,8 +662,10 @@ static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs,
 static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 				     struct xdp_desc *desc)
 {
+	struct xsk_tx_metadata *meta = NULL;
 	struct net_device *dev = xs->dev;
 	struct sk_buff *skb = xs->skb;
+	bool first_frag = false;
 	int err;
 
 	if (dev->priv_flags & IFF_TX_SKB_NO_LINEAR) {
@@ -687,6 +696,8 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 				kfree_skb(skb);
 				goto free_err;
 			}
+
+			first_frag = true;
 		} else {
 			int nr_frags = skb_shinfo(skb)->nr_frags;
 			struct page *page;
@@ -709,12 +720,35 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 
 			skb_add_rx_frag(skb, nr_frags, page, 0, len, 0);
 		}
+
+		if (first_frag && desc->options & XDP_TX_METADATA) {
+			if (unlikely(xs->pool->tx_metadata_len == 0)) {
+				err = -EINVAL;
+				goto free_err;
+			}
+
+			meta = buffer - xs->pool->tx_metadata_len;
+
+			if (meta->flags & XDP_TXMD_FLAGS_CHECKSUM) {
+				if (unlikely(meta->request.csum_start +
+					     meta->request.csum_offset +
+					     sizeof(__sum16) > len)) {
+					err = -EINVAL;
+					goto free_err;
+				}
+
+				skb->csum_start = hr + meta->request.csum_start;
+				skb->csum_offset = meta->request.csum_offset;
+				skb->ip_summed = CHECKSUM_PARTIAL;
+			}
+		}
 	}
 
 	skb->dev = dev;
 	skb->priority = READ_ONCE(xs->sk.sk_priority);
 	skb->mark = READ_ONCE(xs->sk.sk_mark);
 	skb->destructor = xsk_destruct_skb;
+	xsk_tx_metadata_to_compl(meta, &skb_shinfo(skb)->xsk_meta);
 	xsk_set_destructor_arg(skb);
 
 	return skb;
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index c74a1372bcb9..6f2d1621c992 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -137,7 +137,7 @@ static inline bool xskq_cons_read_addr_unchecked(struct xsk_queue *q, u64 *addr)
 
 static inline bool xp_unused_options_set(u32 options)
 {
-	return options & ~XDP_PKT_CONTD;
+	return options & ~(XDP_PKT_CONTD | XDP_TX_METADATA);
 }
 
 static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool,
diff --git a/tools/include/uapi/linux/if_xdp.h b/tools/include/uapi/linux/if_xdp.h
index 34411a2e5b6c..d0882edc1642 100644
--- a/tools/include/uapi/linux/if_xdp.h
+++ b/tools/include/uapi/linux/if_xdp.h
@@ -26,11 +26,11 @@
  */
 #define XDP_USE_NEED_WAKEUP (1 << 3)
 /* By setting this option, userspace application indicates that it can
- * handle multiple descriptors per packet thus enabling xsk core to split
+ * handle multiple descriptors per packet thus enabling AF_XDP to split
  * multi-buffer XDP frames into multiple Rx descriptors. Without this set
- * such frames will be dropped by xsk.
+ * such frames will be dropped.
  */
-#define XDP_USE_SG     (1 << 4)
+#define XDP_USE_SG	(1 << 4)
 
 /* Flags for xsk_umem_config flags */
 #define XDP_UMEM_UNALIGNED_CHUNK_FLAG (1 << 0)
@@ -106,6 +106,41 @@ struct xdp_options {
 #define XSK_UNALIGNED_BUF_ADDR_MASK \
 	((1ULL << XSK_UNALIGNED_BUF_OFFSET_SHIFT) - 1)
 
+/* Request transmit timestamp. Upon completion, put it into tx_timestamp
+ * field of union xsk_tx_metadata.
+ */
+#define XDP_TXMD_FLAGS_TIMESTAMP		(1 << 0)
+
+/* Request transmit checksum offload. Checksum start position and offset
+ * are communicated via csum_start and csum_offset fields of union
+ * xsk_tx_metadata.
+ */
+#define XDP_TXMD_FLAGS_CHECKSUM			(1 << 1)
+
+/* AF_XDP offloads request. 'request' union member is consumed by the driver
+ * when the packet is being transmitted. 'completion' union member is
+ * filled by the driver when the transmit completion arrives.
+ */
+struct xsk_tx_metadata {
+	__u64 flags;
+
+	union {
+		struct {
+			/* XDP_TXMD_FLAGS_CHECKSUM */
+
+			/* Offset from desc->addr where checksumming should start. */
+			__u16 csum_start;
+			/* Offset from csum_start where checksum should be stored. */
+			__u16 csum_offset;
+		} request;
+
+		struct {
+			/* XDP_TXMD_FLAGS_TIMESTAMP */
+			__u64 tx_timestamp;
+		} completion;
+	};
+};
+
 /* Rx/Tx descriptor */
 struct xdp_desc {
 	__u64 addr;
@@ -113,9 +148,16 @@ struct xdp_desc {
 	__u32 options;
 };
 
-/* Flag indicating packet constitutes of multiple buffers*/
+/* UMEM descriptor is __u64 */
+
+/* Flag indicating that the packet continues with the buffer pointed out by the
+ * next frame in the ring. The end of the packet is signalled by setting this
+ * bit to zero. For single buffer packets, every descriptor has 'options' set
+ * to 0 and this maintains backward compatibility.
+ */
 #define XDP_PKT_CONTD (1 << 0)
 
-/* UMEM descriptor is __u64 */
+/* TX packet carries valid metadata. */
+#define XDP_TX_METADATA (1 << 1)
 
 #endif /* _LINUX_IF_XDP_H */
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index 2943a151d4f1..48d5477a668c 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -53,12 +53,28 @@ enum netdev_xdp_rx_metadata {
 	NETDEV_XDP_RX_METADATA_MASK = 3,
 };
 
+/**
+ * enum netdev_xsk_flags
+ * @NETDEV_XSK_FLAGS_TX_TIMESTAMP: HW timestamping egress packets is supported
+ *   by the driver.
+ * @NETDEV_XSK_FLAGS_TX_CHECKSUM: L3 checksum HW offload is supported by the
+ *   driver.
+ */
+enum netdev_xsk_flags {
+	NETDEV_XSK_FLAGS_TX_TIMESTAMP = 1,
+	NETDEV_XSK_FLAGS_TX_CHECKSUM = 2,
+
+	/* private: */
+	NETDEV_XSK_FLAGS_MASK = 3,
+};
+
 enum {
 	NETDEV_A_DEV_IFINDEX = 1,
 	NETDEV_A_DEV_PAD,
 	NETDEV_A_DEV_XDP_FEATURES,
 	NETDEV_A_DEV_XDP_ZC_MAX_SEGS,
 	NETDEV_A_DEV_XDP_RX_METADATA_FEATURES,
+	NETDEV_A_DEV_XSK_FEATURES,
 
 	__NETDEV_A_DEV_MAX,
 	NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1)
diff --git a/tools/net/ynl/generated/netdev-user.c b/tools/net/ynl/generated/netdev-user.c
index b5ffe8cd1144..6283d87dad37 100644
--- a/tools/net/ynl/generated/netdev-user.c
+++ b/tools/net/ynl/generated/netdev-user.c
@@ -58,6 +58,19 @@ const char *netdev_xdp_rx_metadata_str(enum netdev_xdp_rx_metadata value)
 	return netdev_xdp_rx_metadata_strmap[value];
 }
 
+static const char * const netdev_xsk_flags_strmap[] = {
+	[0] = "tx-timestamp",
+	[1] = "tx-checksum",
+};
+
+const char *netdev_xsk_flags_str(enum netdev_xsk_flags value)
+{
+	value = ffs(value) - 1;
+	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(netdev_xsk_flags_strmap))
+		return NULL;
+	return netdev_xsk_flags_strmap[value];
+}
+
 /* Policies */
 struct ynl_policy_attr netdev_dev_policy[NETDEV_A_DEV_MAX + 1] = {
 	[NETDEV_A_DEV_IFINDEX] = { .name = "ifindex", .type = YNL_PT_U32, },
@@ -65,6 +78,7 @@ struct ynl_policy_attr netdev_dev_policy[NETDEV_A_DEV_MAX + 1] = {
 	[NETDEV_A_DEV_XDP_FEATURES] = { .name = "xdp-features", .type = YNL_PT_U64, },
 	[NETDEV_A_DEV_XDP_ZC_MAX_SEGS] = { .name = "xdp-zc-max-segs", .type = YNL_PT_U32, },
 	[NETDEV_A_DEV_XDP_RX_METADATA_FEATURES] = { .name = "xdp-rx-metadata-features", .type = YNL_PT_U64, },
+	[NETDEV_A_DEV_XSK_FEATURES] = { .name = "xsk-features", .type = YNL_PT_U64, },
 };
 
 struct ynl_policy_nest netdev_dev_nest = {
@@ -116,6 +130,11 @@ int netdev_dev_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
 				return MNL_CB_ERROR;
 			dst->_present.xdp_rx_metadata_features = 1;
 			dst->xdp_rx_metadata_features = mnl_attr_get_u64(attr);
+		} else if (type == NETDEV_A_DEV_XSK_FEATURES) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.xsk_features = 1;
+			dst->xsk_features = mnl_attr_get_u64(attr);
 		}
 	}
 
diff --git a/tools/net/ynl/generated/netdev-user.h b/tools/net/ynl/generated/netdev-user.h
index 4fafac879df3..39af1908444b 100644
--- a/tools/net/ynl/generated/netdev-user.h
+++ b/tools/net/ynl/generated/netdev-user.h
@@ -19,6 +19,7 @@ extern const struct ynl_family ynl_netdev_family;
 const char *netdev_op_str(int op);
 const char *netdev_xdp_act_str(enum netdev_xdp_act value);
 const char *netdev_xdp_rx_metadata_str(enum netdev_xdp_rx_metadata value);
+const char *netdev_xsk_flags_str(enum netdev_xsk_flags value);
 
 /* Common nested types */
 /* ============== NETDEV_CMD_DEV_GET ============== */
@@ -50,12 +51,14 @@ struct netdev_dev_get_rsp {
 		__u32 xdp_features:1;
 		__u32 xdp_zc_max_segs:1;
 		__u32 xdp_rx_metadata_features:1;
+		__u32 xsk_features:1;
 	} _present;
 
 	__u32 ifindex;
 	__u64 xdp_features;
 	__u32 xdp_zc_max_segs;
 	__u64 xdp_rx_metadata_features;
+	__u64 xsk_features;
 };
 
 void netdev_dev_get_rsp_free(struct netdev_dev_get_rsp *rsp);
-- 
cgit v1.2.3


From ce59f9686e0eca19431571c7403394a6c36371e2 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Mon, 27 Nov 2023 11:03:13 -0800
Subject: xsk: Validate xsk_tx_metadata flags

Accept only the flags that the kernel knows about to make
sure we can extend this field in the future. Note that only
in XDP_COPY mode we propagate the error signal back to the user
(via sendmsg). For zerocopy mode we silently skip the metadata
for the descriptors that have wrong flags (since we process
the descriptors deep in the driver).

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/r/20231127190319.1190813-8-sdf@google.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/net/xdp_sock_drv.h | 23 ++++++++++++++++++++++-
 net/xdp/xsk.c              |  4 ++++
 2 files changed, 26 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index e2558ac3e195..81e02de3f453 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -165,12 +165,28 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
 	return xp_raw_get_data(pool, addr);
 }
 
+#define XDP_TXMD_FLAGS_VALID ( \
+		XDP_TXMD_FLAGS_TIMESTAMP | \
+		XDP_TXMD_FLAGS_CHECKSUM | \
+	0)
+
+static inline bool xsk_buff_valid_tx_metadata(struct xsk_tx_metadata *meta)
+{
+	return !(meta->flags & ~XDP_TXMD_FLAGS_VALID);
+}
+
 static inline struct xsk_tx_metadata *xsk_buff_get_metadata(struct xsk_buff_pool *pool, u64 addr)
 {
+	struct xsk_tx_metadata *meta;
+
 	if (!pool->tx_metadata_len)
 		return NULL;
 
-	return xp_raw_get_data(pool, addr) - pool->tx_metadata_len;
+	meta = xp_raw_get_data(pool, addr) - pool->tx_metadata_len;
+	if (unlikely(!xsk_buff_valid_tx_metadata(meta)))
+		return NULL; /* no way to signal the error to the user */
+
+	return meta;
 }
 
 static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool)
@@ -332,6 +348,11 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
 	return NULL;
 }
 
+static inline bool xsk_buff_valid_tx_metadata(struct xsk_tx_metadata *meta)
+{
+	return false;
+}
+
 static inline struct xsk_tx_metadata *xsk_buff_get_metadata(struct xsk_buff_pool *pool, u64 addr)
 {
 	return NULL;
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index e83ade32f1fd..d66ba9d6154f 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -728,6 +728,10 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 			}
 
 			meta = buffer - xs->pool->tx_metadata_len;
+			if (unlikely(!xsk_buff_valid_tx_metadata(meta))) {
+				err = -EINVAL;
+				goto free_err;
+			}
 
 			if (meta->flags & XDP_TXMD_FLAGS_CHECKSUM) {
 				if (unlikely(meta->request.csum_start +
-- 
cgit v1.2.3


From 11614723af26e7c32fcb704d8f30fdf60c1122dc Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Mon, 27 Nov 2023 11:03:14 -0800
Subject: xsk: Add option to calculate TX checksum in SW

For XDP_COPY mode, add a UMEM option XDP_UMEM_TX_SW_CSUM
to call skb_checksum_help in transmit path. Might be useful
to debugging issues with real hardware. I also use this mode
in the selftests.

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/r/20231127190319.1190813-9-sdf@google.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 Documentation/networking/xsk-tx-metadata.rst | 9 +++++++++
 include/net/xsk_buff_pool.h                  | 1 +
 include/uapi/linux/if_xdp.h                  | 8 +++++++-
 net/xdp/xdp_umem.c                           | 7 ++++++-
 net/xdp/xsk.c                                | 6 ++++++
 net/xdp/xsk_buff_pool.c                      | 1 +
 tools/include/uapi/linux/if_xdp.h            | 8 +++++++-
 7 files changed, 37 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/Documentation/networking/xsk-tx-metadata.rst b/Documentation/networking/xsk-tx-metadata.rst
index 4f376560b23f..97ecfa480d00 100644
--- a/Documentation/networking/xsk-tx-metadata.rst
+++ b/Documentation/networking/xsk-tx-metadata.rst
@@ -50,6 +50,15 @@ packet's ``struct xdp_desc`` descriptor should set ``XDP_TX_METADATA``
 bit in the ``options`` field. Also note that in a multi-buffer packet
 only the first chunk should carry the metadata.
 
+Software TX Checksum
+====================
+
+For development and testing purposes its possible to pass
+``XDP_UMEM_TX_SW_CSUM`` flag to ``XDP_UMEM_REG`` UMEM registration call.
+In this case, when running in ``XDK_COPY`` mode, the TX checksum
+is calculated on the CPU. Do not enable this option in production because
+it will negatively affect performance.
+
 Querying Device Capabilities
 ============================
 
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index 97f5cc10d79e..8d48d37ab7c0 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -83,6 +83,7 @@ struct xsk_buff_pool {
 	bool uses_need_wakeup;
 	bool dma_need_sync;
 	bool unaligned;
+	bool tx_sw_csum;
 	void *addrs;
 	/* Mutual exclusion of the completion ring in the SKB mode. Two cases to protect:
 	 * NAPI TX thread and sendmsg error paths in the SKB destructor callback and when
diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h
index 95de66d5a26c..d31698410410 100644
--- a/include/uapi/linux/if_xdp.h
+++ b/include/uapi/linux/if_xdp.h
@@ -33,7 +33,13 @@
 #define XDP_USE_SG	(1 << 4)
 
 /* Flags for xsk_umem_config flags */
-#define XDP_UMEM_UNALIGNED_CHUNK_FLAG (1 << 0)
+#define XDP_UMEM_UNALIGNED_CHUNK_FLAG	(1 << 0)
+
+/* Force checksum calculation in software. Can be used for testing or
+ * working around potential HW issues. This option causes performance
+ * degradation and only works in XDP_COPY mode.
+ */
+#define XDP_UMEM_TX_SW_CSUM		(1 << 1)
 
 struct sockaddr_xdp {
 	__u16 sxdp_family;
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index 946a687fb8e8..caa340134b0e 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -148,6 +148,11 @@ static int xdp_umem_account_pages(struct xdp_umem *umem)
 	return 0;
 }
 
+#define XDP_UMEM_FLAGS_VALID ( \
+		XDP_UMEM_UNALIGNED_CHUNK_FLAG | \
+		XDP_UMEM_TX_SW_CSUM | \
+	0)
+
 static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 {
 	bool unaligned_chunks = mr->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG;
@@ -167,7 +172,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 		return -EINVAL;
 	}
 
-	if (mr->flags & ~XDP_UMEM_UNALIGNED_CHUNK_FLAG)
+	if (mr->flags & ~XDP_UMEM_FLAGS_VALID)
 		return -EINVAL;
 
 	if (!unaligned_chunks && !is_power_of_2(chunk_size))
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index d66ba9d6154f..281d49b4fca4 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -744,6 +744,12 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 				skb->csum_start = hr + meta->request.csum_start;
 				skb->csum_offset = meta->request.csum_offset;
 				skb->ip_summed = CHECKSUM_PARTIAL;
+
+				if (unlikely(xs->pool->tx_sw_csum)) {
+					err = skb_checksum_help(skb);
+					if (err)
+						goto free_err;
+				}
 			}
 		}
 	}
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 386eddcdf837..4f6f538a5462 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -86,6 +86,7 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
 	pool->umem = umem;
 	pool->addrs = umem->addrs;
 	pool->tx_metadata_len = umem->tx_metadata_len;
+	pool->tx_sw_csum = umem->flags & XDP_UMEM_TX_SW_CSUM;
 	INIT_LIST_HEAD(&pool->free_list);
 	INIT_LIST_HEAD(&pool->xskb_list);
 	INIT_LIST_HEAD(&pool->xsk_tx_list);
diff --git a/tools/include/uapi/linux/if_xdp.h b/tools/include/uapi/linux/if_xdp.h
index d0882edc1642..638c606dfa74 100644
--- a/tools/include/uapi/linux/if_xdp.h
+++ b/tools/include/uapi/linux/if_xdp.h
@@ -33,7 +33,13 @@
 #define XDP_USE_SG	(1 << 4)
 
 /* Flags for xsk_umem_config flags */
-#define XDP_UMEM_UNALIGNED_CHUNK_FLAG (1 << 0)
+#define XDP_UMEM_UNALIGNED_CHUNK_FLAG	(1 << 0)
+
+/* Force checksum calculation in software. Can be used for testing or
+ * working around potential HW issues. This option causes performance
+ * degradation and only works in XDP_COPY mode.
+ */
+#define XDP_UMEM_TX_SW_CSUM		(1 << 1)
 
 struct sockaddr_xdp {
 	__u16 sxdp_family;
-- 
cgit v1.2.3


From 8866730aed5100f06d3d965c22f1c61f74942541 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Tue, 28 Nov 2023 17:25:56 -0800
Subject: bpf, sockmap: af_unix stream sockets need to hold ref for pair sock

AF_UNIX stream sockets are a paired socket. So sending on one of the pairs
will lookup the paired socket as part of the send operation. It is possible
however to put just one of the pairs in a BPF map. This currently increments
the refcnt on the sock in the sockmap to ensure it is not free'd by the
stack before sockmap cleans up its state and stops any skbs being sent/recv'd
to that socket.

But we missed a case. If the peer socket is closed it will be free'd by the
stack. However, the paired socket can still be referenced from BPF sockmap
side because we hold a reference there. Then if we are sending traffic through
BPF sockmap to that socket it will try to dereference the free'd pair in its
send logic creating a use after free. And following splat:

   [59.900375] BUG: KASAN: slab-use-after-free in sk_wake_async+0x31/0x1b0
   [59.901211] Read of size 8 at addr ffff88811acbf060 by task kworker/1:2/954
   [...]
   [59.905468] Call Trace:
   [59.905787]  <TASK>
   [59.906066]  dump_stack_lvl+0x130/0x1d0
   [59.908877]  print_report+0x16f/0x740
   [59.910629]  kasan_report+0x118/0x160
   [59.912576]  sk_wake_async+0x31/0x1b0
   [59.913554]  sock_def_readable+0x156/0x2a0
   [59.914060]  unix_stream_sendmsg+0x3f9/0x12a0
   [59.916398]  sock_sendmsg+0x20e/0x250
   [59.916854]  skb_send_sock+0x236/0xac0
   [59.920527]  sk_psock_backlog+0x287/0xaa0

To fix let BPF sockmap hold a refcnt on both the socket in the sockmap and its
paired socket. It wasn't obvious how to contain the fix to bpf_unix logic. The
primarily problem with keeping this logic in bpf_unix was: In the sock close()
we could handle the deref by having a close handler. But, when we are destroying
the psock through a map delete operation we wouldn't have gotten any signal
thorugh the proto struct other than it being replaced. If we do the deref from
the proto replace its too early because we need to deref the sk_pair after the
backlog worker has been stopped.

Given all this it seems best to just cache it at the end of the psock and eat 8B
for the af_unix and vsock users. Notice dgram sockets are OK because they handle
locking already.

Fixes: 94531cfcbe79 ("af_unix: Add unix_stream_proto for sockmap")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/bpf/20231129012557.95371-2-john.fastabend@gmail.com
---
 include/linux/skmsg.h | 1 +
 include/net/af_unix.h | 1 +
 net/core/skmsg.c      | 2 ++
 net/unix/af_unix.c    | 2 --
 net/unix/unix_bpf.c   | 5 +++++
 5 files changed, 9 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index c1637515a8a4..c953b8c0d2f4 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -106,6 +106,7 @@ struct sk_psock {
 	struct mutex			work_mutex;
 	struct sk_psock_work_state	work_state;
 	struct delayed_work		work;
+	struct sock			*sk_pair;
 	struct rcu_work			rwork;
 };
 
diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index 824c258143a3..49c4640027d8 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -75,6 +75,7 @@ struct unix_sock {
 };
 
 #define unix_sk(ptr) container_of_const(ptr, struct unix_sock, sk)
+#define unix_peer(sk) (unix_sk(sk)->peer)
 
 #define peer_wait peer_wq.wait
 
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 6c31eefbd777..93ecfceac1bc 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -826,6 +826,8 @@ static void sk_psock_destroy(struct work_struct *work)
 
 	if (psock->sk_redir)
 		sock_put(psock->sk_redir);
+	if (psock->sk_pair)
+		sock_put(psock->sk_pair);
 	sock_put(psock->sk);
 	kfree(psock);
 }
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index a357dc5f2404..ac1f2bc18fc9 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -213,8 +213,6 @@ static inline bool unix_secdata_eq(struct scm_cookie *scm, struct sk_buff *skb)
 }
 #endif /* CONFIG_SECURITY_NETWORK */
 
-#define unix_peer(sk) (unix_sk(sk)->peer)
-
 static inline int unix_our_peer(struct sock *sk, struct sock *osk)
 {
 	return unix_peer(osk) == sk;
diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c
index 2f9d8271c6ec..7ea7c3a0d0d0 100644
--- a/net/unix/unix_bpf.c
+++ b/net/unix/unix_bpf.c
@@ -159,12 +159,17 @@ int unix_dgram_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool re
 
 int unix_stream_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
 {
+	struct sock *sk_pair;
+
 	if (restore) {
 		sk->sk_write_space = psock->saved_write_space;
 		sock_replace_proto(sk, psock->sk_proto);
 		return 0;
 	}
 
+	sk_pair = unix_peer(sk);
+	sock_hold(sk_pair);
+	psock->sk_pair = sk_pair;
 	unix_stream_bpf_check_needs_rebuild(psock->sk_proto);
 	sock_replace_proto(sk, &unix_stream_bpf_prot);
 	return 0;
-- 
cgit v1.2.3


From 6ebf6f90ab4ac09a76172a6d387e8819d3259595 Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliang.tang@suse.com>
Date: Tue, 28 Nov 2023 15:18:45 -0800
Subject: mptcp: add mptcpi_subflows_total counter

If the initial subflow has been removed, we cannot know without checking
other counters, e.g. ss -ti <filter> | grep -c tcp-ulp-mptcp or
getsockopt(SOL_MPTCP, MPTCP_FULL_INFO, ...) (or others except MPTCP_INFO
of course) and then check mptcp_subflow_data->num_subflows to get the
total amount of subflows.

This patch adds a new counter mptcpi_subflows_total in mptcpi_flags to
store the total amount of subflows, including the initial one. A new
helper __mptcp_has_initial_subflow() is added to check whether the
initial subflow has been removed or not. With this helper, we can then
compute the total amount of subflows from mptcp_info by doing something
like:

    mptcpi_subflows_total = mptcpi_subflows +
            __mptcp_has_initial_subflow(msk).

Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/428
Reviewed-by: Matthieu Baerts <matttbe@kernel.org>
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
Signed-off-by: Mat Martineau <martineau@kernel.org>
Link: https://lore.kernel.org/r/20231128-send-net-next-2023107-v4-1-8d6b94150f6b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/uapi/linux/mptcp.h | 1 +
 net/mptcp/protocol.h       | 9 +++++++++
 net/mptcp/sockopt.c        | 2 ++
 3 files changed, 12 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h
index a6451561f3f8..74cfe496891e 100644
--- a/include/uapi/linux/mptcp.h
+++ b/include/uapi/linux/mptcp.h
@@ -57,6 +57,7 @@ struct mptcp_info {
 	__u64	mptcpi_bytes_sent;
 	__u64	mptcpi_bytes_received;
 	__u64	mptcpi_bytes_acked;
+	__u8	mptcpi_subflows_total;
 };
 
 /* MPTCP Reset reason codes, rfc8684 */
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index fe6f2d399ee8..458a2d7bb0dd 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -1072,6 +1072,15 @@ static inline void __mptcp_do_fallback(struct mptcp_sock *msk)
 	set_bit(MPTCP_FALLBACK_DONE, &msk->flags);
 }
 
+static inline bool __mptcp_has_initial_subflow(const struct mptcp_sock *msk)
+{
+	struct sock *ssk = READ_ONCE(msk->first);
+
+	return ssk && ((1 << inet_sk_state_load(ssk)) &
+		       (TCPF_ESTABLISHED | TCPF_SYN_SENT |
+			TCPF_SYN_RECV | TCPF_LISTEN));
+}
+
 static inline void mptcp_do_fallback(struct sock *ssk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index 353680733700..cabe856b2a45 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -938,6 +938,8 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info)
 	info->mptcpi_bytes_sent = msk->bytes_sent;
 	info->mptcpi_bytes_received = msk->bytes_received;
 	info->mptcpi_bytes_retrans = msk->bytes_retrans;
+	info->mptcpi_subflows_total = info->mptcpi_subflows +
+		__mptcp_has_initial_subflow(msk);
 	unlock_sock_fast(sk, slow);
 }
 EXPORT_SYMBOL_GPL(mptcp_diag_fill_info);
-- 
cgit v1.2.3


From f422544118cbdfc3bba7b7c5189e18147acb9047 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Tue, 28 Nov 2023 09:53:04 +0000
Subject: net: mana: Fix spelling mistake "enforecement" -> "enforcement"

There is a spelling mistake in struct field hc_tx_err_sqpdid_enforecement.
Fix it.

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Signed-off-by: Shradha Gupta <shradhagupta@linux.microsoft.com>
Link: https://lore.kernel.org/r/20231128095304.515492-1-colin.i.king@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/microsoft/mana/mana_en.c      | 2 +-
 drivers/net/ethernet/microsoft/mana/mana_ethtool.c | 4 ++--
 include/net/mana/mana.h                            | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 0eb8321d76c9..cb7b9d8ef618 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -2446,7 +2446,7 @@ void mana_query_gf_stats(struct mana_port_context *apc)
 	apc->eth_stats.hc_tx_err_eth_type_enforcement =
 					     resp.tx_err_ethtype_enforcement;
 	apc->eth_stats.hc_tx_err_sa_enforcement = resp.tx_err_SA_enforcement;
-	apc->eth_stats.hc_tx_err_sqpdid_enforecement =
+	apc->eth_stats.hc_tx_err_sqpdid_enforcement =
 					     resp.tx_err_SQPDID_enforcement;
 	apc->eth_stats.hc_tx_err_cqpdid_enforcement =
 					     resp.tx_err_CQPDID_enforcement;
diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
index 7077d647d99a..777e65b8223d 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
@@ -43,8 +43,8 @@ static const struct {
 	 offsetof(struct mana_ethtool_stats, hc_tx_err_eth_type_enforcement)},
 	{"hc_tx_err_sa_enforcement", offsetof(struct mana_ethtool_stats,
 					      hc_tx_err_sa_enforcement)},
-	{"hc_tx_err_sqpdid_enforecement",
-	 offsetof(struct mana_ethtool_stats, hc_tx_err_sqpdid_enforecement)},
+	{"hc_tx_err_sqpdid_enforcement",
+	 offsetof(struct mana_ethtool_stats, hc_tx_err_sqpdid_enforcement)},
 	{"hc_tx_err_cqpdid_enforcement",
 	 offsetof(struct mana_ethtool_stats, hc_tx_err_cqpdid_enforcement)},
 	{"hc_tx_err_mtu_violation", offsetof(struct mana_ethtool_stats,
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index 5567f5bc8eb6..76147feb0d10 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -368,7 +368,7 @@ struct mana_ethtool_stats {
 	u64 hc_tx_err_vlan_enforcement;
 	u64 hc_tx_err_eth_type_enforcement;
 	u64 hc_tx_err_sa_enforcement;
-	u64 hc_tx_err_sqpdid_enforecement;
+	u64 hc_tx_err_sqpdid_enforcement;
 	u64 hc_tx_err_cqpdid_enforcement;
 	u64 hc_tx_err_mtu_violation;
 	u64 hc_tx_err_inval_oob;
-- 
cgit v1.2.3


From 7577bc8249c3fc86096ef1b1c9a8f4b6232231e7 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Tue, 28 Nov 2023 18:29:20 -0800
Subject: tcp: Don't pass cookie to __cookie_v[46]_check().

tcp_hdr(skb) and SYN Cookie are passed to __cookie_v[46]_check(), but
none of the callers passes cookie other than ntohl(th->ack_seq) - 1.

Let's fetch it in __cookie_v[46]_check() instead of passing the cookie
over and over.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20231129022924.96156-5-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netfilter_ipv6.h   |  8 ++++----
 include/net/tcp.h                |  6 ++----
 net/core/filter.c                | 15 ++++-----------
 net/ipv4/syncookies.c            | 15 ++++++++-------
 net/ipv6/syncookies.c            | 15 ++++++++-------
 net/netfilter/nf_synproxy_core.c |  4 ++--
 6 files changed, 28 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h
index 7834c0be2831..61aa48f46dd7 100644
--- a/include/linux/netfilter_ipv6.h
+++ b/include/linux/netfilter_ipv6.h
@@ -51,7 +51,7 @@ struct nf_ipv6_ops {
 	u32 (*cookie_init_sequence)(const struct ipv6hdr *iph,
 				    const struct tcphdr *th, u16 *mssp);
 	int (*cookie_v6_check)(const struct ipv6hdr *iph,
-			       const struct tcphdr *th, __u32 cookie);
+			       const struct tcphdr *th);
 #endif
 	void (*route_input)(struct sk_buff *skb);
 	int (*fragment)(struct net *net, struct sock *sk, struct sk_buff *skb,
@@ -179,16 +179,16 @@ static inline u32 nf_ipv6_cookie_init_sequence(const struct ipv6hdr *iph,
 }
 
 static inline int nf_cookie_v6_check(const struct ipv6hdr *iph,
-				     const struct tcphdr *th, __u32 cookie)
+				     const struct tcphdr *th)
 {
 #if IS_ENABLED(CONFIG_SYN_COOKIES)
 #if IS_MODULE(CONFIG_IPV6)
 	const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops();
 
 	if (v6_ops)
-		return v6_ops->cookie_v6_check(iph, th, cookie);
+		return v6_ops->cookie_v6_check(iph, th);
 #elif IS_BUILTIN(CONFIG_IPV6)
-	return __cookie_v6_check(iph, th, cookie);
+	return __cookie_v6_check(iph, th);
 #endif
 #endif
 	return 0;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index d2f0736b76b8..2b2c79c7bbcd 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -491,8 +491,7 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb);
 struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb,
 				 struct request_sock *req,
 				 struct dst_entry *dst, u32 tsoff);
-int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th,
-		      u32 cookie);
+int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th);
 struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb);
 struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops,
 					    const struct tcp_request_sock_ops *af_ops,
@@ -586,8 +585,7 @@ bool cookie_ecn_ok(const struct tcp_options_received *opt,
 		   const struct net *net, const struct dst_entry *dst);
 
 /* From net/ipv6/syncookies.c */
-int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th,
-		      u32 cookie);
+int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th);
 struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb);
 
 u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph,
diff --git a/net/core/filter.c b/net/core/filter.c
index 7e4d7c3bcc84..0adaa4afa35f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -7238,7 +7238,6 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len
 	   struct tcphdr *, th, u32, th_len)
 {
 #ifdef CONFIG_SYN_COOKIES
-	u32 cookie;
 	int ret;
 
 	if (unlikely(!sk || th_len < sizeof(*th)))
@@ -7260,8 +7259,6 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len
 	if (tcp_synq_no_recent_overflow(sk))
 		return -ENOENT;
 
-	cookie = ntohl(th->ack_seq) - 1;
-
 	/* Both struct iphdr and struct ipv6hdr have the version field at the
 	 * same offset so we can cast to the shorter header (struct iphdr).
 	 */
@@ -7270,7 +7267,7 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len
 		if (sk->sk_family == AF_INET6 && ipv6_only_sock(sk))
 			return -EINVAL;
 
-		ret = __cookie_v4_check((struct iphdr *)iph, th, cookie);
+		ret = __cookie_v4_check((struct iphdr *)iph, th);
 		break;
 
 #if IS_BUILTIN(CONFIG_IPV6)
@@ -7281,7 +7278,7 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len
 		if (sk->sk_family != AF_INET6)
 			return -EINVAL;
 
-		ret = __cookie_v6_check((struct ipv6hdr *)iph, th, cookie);
+		ret = __cookie_v6_check((struct ipv6hdr *)iph, th);
 		break;
 #endif /* CONFIG_IPV6 */
 
@@ -7734,9 +7731,7 @@ static const struct bpf_func_proto bpf_tcp_raw_gen_syncookie_ipv6_proto = {
 BPF_CALL_2(bpf_tcp_raw_check_syncookie_ipv4, struct iphdr *, iph,
 	   struct tcphdr *, th)
 {
-	u32 cookie = ntohl(th->ack_seq) - 1;
-
-	if (__cookie_v4_check(iph, th, cookie) > 0)
+	if (__cookie_v4_check(iph, th) > 0)
 		return 0;
 
 	return -EACCES;
@@ -7757,9 +7752,7 @@ BPF_CALL_2(bpf_tcp_raw_check_syncookie_ipv6, struct ipv6hdr *, iph,
 	   struct tcphdr *, th)
 {
 #if IS_BUILTIN(CONFIG_IPV6)
-	u32 cookie = ntohl(th->ack_seq) - 1;
-
-	if (__cookie_v6_check(iph, th, cookie) > 0)
+	if (__cookie_v6_check(iph, th) > 0)
 		return 0;
 
 	return -EACCES;
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 8b7d7d7788af..c08428d63d11 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -189,12 +189,14 @@ __u32 cookie_v4_init_sequence(const struct sk_buff *skb, __u16 *mssp)
  * Check if a ack sequence number is a valid syncookie.
  * Return the decoded mss if it is, or 0 if not.
  */
-int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th,
-		      u32 cookie)
+int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th)
 {
+	__u32 cookie = ntohl(th->ack_seq) - 1;
 	__u32 seq = ntohl(th->seq) - 1;
-	__u32 mssind = check_tcp_syn_cookie(cookie, iph->saddr, iph->daddr,
-					    th->source, th->dest, seq);
+	__u32 mssind;
+
+	mssind = check_tcp_syn_cookie(cookie, iph->saddr, iph->daddr,
+				      th->source, th->dest, seq);
 
 	return mssind < ARRAY_SIZE(msstab) ? msstab[mssind] : 0;
 }
@@ -332,7 +334,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 {
 	struct ip_options *opt = &TCP_SKB_CB(skb)->header.h4.opt;
 	const struct tcphdr *th = tcp_hdr(skb);
-	__u32 cookie = ntohl(th->ack_seq) - 1;
 	struct tcp_options_received tcp_opt;
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_request_sock *ireq;
@@ -354,7 +355,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	if (tcp_synq_no_recent_overflow(sk))
 		goto out;
 
-	mss = __cookie_v4_check(ip_hdr(skb), th, cookie);
+	mss = __cookie_v4_check(ip_hdr(skb), th);
 	if (mss == 0) {
 		__NET_INC_STATS(net, LINUX_MIB_SYNCOOKIESFAILED);
 		goto out;
@@ -384,7 +385,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	ireq = inet_rsk(req);
 	treq = tcp_rsk(req);
 	treq->rcv_isn		= ntohl(th->seq) - 1;
-	treq->snt_isn		= cookie;
+	treq->snt_isn		= ntohl(th->ack_seq) - 1;
 	treq->ts_off		= 0;
 	treq->txhash		= net_tx_rndhash();
 	req->mss		= mss;
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 106376cbc9de..4cd26c481168 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -114,12 +114,14 @@ __u32 cookie_v6_init_sequence(const struct sk_buff *skb, __u16 *mssp)
 	return __cookie_v6_init_sequence(iph, th, mssp);
 }
 
-int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th,
-		      __u32 cookie)
+int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th)
 {
+	__u32 cookie = ntohl(th->ack_seq) - 1;
 	__u32 seq = ntohl(th->seq) - 1;
-	__u32 mssind = check_tcp_syn_cookie(cookie, &iph->saddr, &iph->daddr,
-					    th->source, th->dest, seq);
+	__u32 mssind;
+
+	mssind = check_tcp_syn_cookie(cookie, &iph->saddr, &iph->daddr,
+				      th->source, th->dest, seq);
 
 	return mssind < ARRAY_SIZE(msstab) ? msstab[mssind] : 0;
 }
@@ -128,7 +130,6 @@ EXPORT_SYMBOL_GPL(__cookie_v6_check);
 struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 {
 	const struct tcphdr *th = tcp_hdr(skb);
-	__u32 cookie = ntohl(th->ack_seq) - 1;
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct tcp_options_received tcp_opt;
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -150,7 +151,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	if (tcp_synq_no_recent_overflow(sk))
 		goto out;
 
-	mss = __cookie_v6_check(ipv6_hdr(skb), th, cookie);
+	mss = __cookie_v6_check(ipv6_hdr(skb), th);
 	if (mss == 0) {
 		__NET_INC_STATS(net, LINUX_MIB_SYNCOOKIESFAILED);
 		goto out;
@@ -213,7 +214,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	req->ts_recent		= tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0;
 	treq->snt_synack	= 0;
 	treq->rcv_isn = ntohl(th->seq) - 1;
-	treq->snt_isn = cookie;
+	treq->snt_isn = ntohl(th->ack_seq) - 1;
 	treq->ts_off = 0;
 	treq->txhash = net_tx_rndhash();
 
diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c
index 467671f2d42f..fbbc4fd37349 100644
--- a/net/netfilter/nf_synproxy_core.c
+++ b/net/netfilter/nf_synproxy_core.c
@@ -617,7 +617,7 @@ synproxy_recv_client_ack(struct net *net,
 	struct synproxy_net *snet = synproxy_pernet(net);
 	int mss;
 
-	mss = __cookie_v4_check(ip_hdr(skb), th, ntohl(th->ack_seq) - 1);
+	mss = __cookie_v4_check(ip_hdr(skb), th);
 	if (mss == 0) {
 		this_cpu_inc(snet->stats->cookie_invalid);
 		return false;
@@ -1034,7 +1034,7 @@ synproxy_recv_client_ack_ipv6(struct net *net,
 	struct synproxy_net *snet = synproxy_pernet(net);
 	int mss;
 
-	mss = nf_cookie_v6_check(ipv6_hdr(skb), th, ntohl(th->ack_seq) - 1);
+	mss = nf_cookie_v6_check(ipv6_hdr(skb), th);
 	if (mss == 0) {
 		this_cpu_inc(snet->stats->cookie_invalid);
 		return false;
-- 
cgit v1.2.3


From efce3d1fdff53ef45b11ff407f16bc2f6f292b93 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Tue, 28 Nov 2023 18:29:21 -0800
Subject: tcp: Don't initialise tp->tsoffset in tcp_get_cookie_sock().

When we create a full socket from SYN Cookie, we initialise
tcp_sk(sk)->tsoffset redundantly in tcp_get_cookie_sock() as
the field is inherited from tcp_rsk(req)->ts_off.

  cookie_v[46]_check
  |- treq->ts_off = 0
  `- tcp_get_cookie_sock
     |- tcp_v[46]_syn_recv_sock
     |  `- tcp_create_openreq_child
     |	   `- newtp->tsoffset = treq->ts_off
     `- tcp_sk(child)->tsoffset = tsoff

Let's initialise tcp_rsk(req)->ts_off with the correct offset
and remove the second initialisation of tcp_sk(sk)->tsoffset.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20231129022924.96156-6-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/tcp.h     | 2 +-
 net/ipv4/syncookies.c | 7 +++----
 net/ipv6/syncookies.c | 4 ++--
 3 files changed, 6 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 2b2c79c7bbcd..cc7143a781da 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -490,7 +490,7 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb);
 /* From syncookies.c */
 struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb,
 				 struct request_sock *req,
-				 struct dst_entry *dst, u32 tsoff);
+				 struct dst_entry *dst);
 int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th);
 struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb);
 struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops,
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index c08428d63d11..de051eb08db8 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -204,7 +204,7 @@ EXPORT_SYMBOL_GPL(__cookie_v4_check);
 
 struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb,
 				 struct request_sock *req,
-				 struct dst_entry *dst, u32 tsoff)
+				 struct dst_entry *dst)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct sock *child;
@@ -214,7 +214,6 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb,
 						 NULL, &own_req);
 	if (child) {
 		refcount_set(&req->rsk_refcnt, 1);
-		tcp_sk(child)->tsoffset = tsoff;
 		sock_rps_save_rxhash(child, skb);
 
 		if (rsk_drop_req(req)) {
@@ -386,7 +385,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	treq = tcp_rsk(req);
 	treq->rcv_isn		= ntohl(th->seq) - 1;
 	treq->snt_isn		= ntohl(th->ack_seq) - 1;
-	treq->ts_off		= 0;
+	treq->ts_off		= tsoff;
 	treq->txhash		= net_tx_rndhash();
 	req->mss		= mss;
 	ireq->ir_num		= ntohs(th->dest);
@@ -452,7 +451,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	ireq->rcv_wscale  = rcv_wscale;
 	ireq->ecn_ok = cookie_ecn_ok(&tcp_opt, net, &rt->dst);
 
-	ret = tcp_get_cookie_sock(sk, skb, req, &rt->dst, tsoff);
+	ret = tcp_get_cookie_sock(sk, skb, req, &rt->dst);
 	/* ip_queue_xmit() depends on our flow being setup
 	 * Normal sockets get it right from inet_csk_route_child_sock()
 	 */
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 4cd26c481168..18c2e3c1677b 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -215,7 +215,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	treq->snt_synack	= 0;
 	treq->rcv_isn = ntohl(th->seq) - 1;
 	treq->snt_isn = ntohl(th->ack_seq) - 1;
-	treq->ts_off = 0;
+	treq->ts_off = tsoff;
 	treq->txhash = net_tx_rndhash();
 
 	l3index = l3mdev_master_ifindex_by_index(net, ireq->ir_iif);
@@ -264,7 +264,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	ireq->rcv_wscale = rcv_wscale;
 	ireq->ecn_ok = cookie_ecn_ok(&tcp_opt, net, dst);
 
-	ret = tcp_get_cookie_sock(sk, skb, req, dst, tsoff);
+	ret = tcp_get_cookie_sock(sk, skb, req, dst);
 out:
 	return ret;
 out_free:
-- 
cgit v1.2.3


From 7b0f570f879adecf12329ecd60485e7e6b4783c1 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Tue, 28 Nov 2023 18:29:22 -0800
Subject: tcp: Move TCP-AO bits from cookie_v[46]_check() to
 tcp_ao_syncookie().

We initialise treq->af_specific in cookie_tcp_reqsk_alloc() so that
we can look up a key later in tcp_create_openreq_child().

Initially, that change was added for MD5 by commit ba5a4fdd63ae ("tcp:
make sure treq->af_specific is initialized"), but it has not been used
since commit d0f2b7a9ca0a ("tcp: Disable header prediction for MD5
flow.").

Now, treq->af_specific is used only by TCP-AO, so, we can move that
initialisation into tcp_ao_syncookie().

In addition to that, l3index in cookie_v[46]_check() is only used for
tcp_ao_syncookie(), so let's move it as well.

While at it, we move down tcp_ao_syncookie() in cookie_v4_check() so
that it will be called after security_inet_conn_request() to make
functions order consistent with cookie_v6_check().

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20231129022924.96156-7-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/tcp.h     |  1 -
 include/net/tcp_ao.h  |  6 ++----
 net/ipv4/syncookies.c | 16 ++++------------
 net/ipv4/tcp_ao.c     | 16 ++++++++++++++--
 net/ipv6/syncookies.c |  7 ++-----
 5 files changed, 22 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index cc7143a781da..d4d0e9763175 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -494,7 +494,6 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb,
 int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th);
 struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb);
 struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops,
-					    const struct tcp_request_sock_ops *af_ops,
 					    struct sock *sk, struct sk_buff *skb);
 #ifdef CONFIG_SYN_COOKIES
 
diff --git a/include/net/tcp_ao.h b/include/net/tcp_ao.h
index b56be10838f0..4d900ef8dfc3 100644
--- a/include/net/tcp_ao.h
+++ b/include/net/tcp_ao.h
@@ -265,8 +265,7 @@ void tcp_ao_established(struct sock *sk);
 void tcp_ao_finish_connect(struct sock *sk, struct sk_buff *skb);
 void tcp_ao_connect_init(struct sock *sk);
 void tcp_ao_syncookie(struct sock *sk, const struct sk_buff *skb,
-		      struct tcp_request_sock *treq,
-		      unsigned short int family, int l3index);
+		      struct request_sock *req, unsigned short int family);
 #else /* CONFIG_TCP_AO */
 
 static inline int tcp_ao_transmit_skb(struct sock *sk, struct sk_buff *skb,
@@ -277,8 +276,7 @@ static inline int tcp_ao_transmit_skb(struct sock *sk, struct sk_buff *skb,
 }
 
 static inline void tcp_ao_syncookie(struct sock *sk, const struct sk_buff *skb,
-				    struct tcp_request_sock *treq,
-				    unsigned short int family, int l3index)
+				    struct request_sock *req, unsigned short int family)
 {
 }
 
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index de051eb08db8..1e3783c97e28 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -286,9 +286,7 @@ bool cookie_ecn_ok(const struct tcp_options_received *tcp_opt,
 EXPORT_SYMBOL(cookie_ecn_ok);
 
 struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops,
-					    const struct tcp_request_sock_ops *af_ops,
-					    struct sock *sk,
-					    struct sk_buff *skb)
+					    struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_request_sock *treq;
 	struct request_sock *req;
@@ -303,9 +301,6 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops,
 
 	treq = tcp_rsk(req);
 
-	/* treq->af_specific might be used to perform TCP_MD5 lookup */
-	treq->af_specific = af_ops;
-
 	treq->syn_tos = TCP_SKB_CB(skb)->ip_dsfield;
 	treq->req_usec_ts = false;
 
@@ -345,7 +340,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	struct rtable *rt;
 	__u8 rcv_wscale;
 	u32 tsoff = 0;
-	int l3index;
 
 	if (!READ_ONCE(net->ipv4.sysctl_tcp_syncookies) ||
 	    !th->ack || th->rst)
@@ -376,8 +370,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	if (!cookie_timestamp_decode(net, &tcp_opt))
 		goto out;
 
-	req = cookie_tcp_reqsk_alloc(&tcp_request_sock_ops,
-				     &tcp_request_sock_ipv4_ops, sk, skb);
+	req = cookie_tcp_reqsk_alloc(&tcp_request_sock_ops, sk, skb);
 	if (!req)
 		goto out_drop;
 
@@ -406,9 +399,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 
 	ireq->ir_iif = inet_request_bound_dev_if(sk, skb);
 
-	l3index = l3mdev_master_ifindex_by_index(net, ireq->ir_iif);
-	tcp_ao_syncookie(sk, skb, treq, AF_INET, l3index);
-
 	/* We throwed the options of the initial SYN away, so we hope
 	 * the ACK carries the same options again (see RFC1122 4.2.3.8)
 	 */
@@ -417,6 +407,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	if (security_inet_conn_request(sk, skb, req))
 		goto out_free;
 
+	tcp_ao_syncookie(sk, skb, req, AF_INET);
+
 	req->num_retrans = 0;
 
 	/*
diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c
index 7696417d0640..c4cd1e09eb6b 100644
--- a/net/ipv4/tcp_ao.c
+++ b/net/ipv4/tcp_ao.c
@@ -844,18 +844,30 @@ static struct tcp_ao_key *tcp_ao_inbound_lookup(unsigned short int family,
 }
 
 void tcp_ao_syncookie(struct sock *sk, const struct sk_buff *skb,
-		      struct tcp_request_sock *treq,
-		      unsigned short int family, int l3index)
+		      struct request_sock *req, unsigned short int family)
 {
+	struct tcp_request_sock *treq = tcp_rsk(req);
 	const struct tcphdr *th = tcp_hdr(skb);
 	const struct tcp_ao_hdr *aoh;
 	struct tcp_ao_key *key;
+	int l3index;
+
+	/* treq->af_specific is used to perform TCP_AO lookup
+	 * in tcp_create_openreq_child().
+	 */
+#if IS_ENABLED(CONFIG_IPV6)
+	if (family == AF_INET6)
+		treq->af_specific = &tcp_request_sock_ipv6_ops;
+	else
+#endif
+		treq->af_specific = &tcp_request_sock_ipv4_ops;
 
 	treq->maclen = 0;
 
 	if (tcp_parse_auth_options(th, NULL, &aoh) || !aoh)
 		return;
 
+	l3index = l3mdev_master_ifindex_by_index(sock_net(sk), inet_rsk(req)->ir_iif);
 	key = tcp_ao_inbound_lookup(family, sk, skb, -1, aoh->keyid, l3index);
 	if (!key)
 		/* Key not found, continue without TCP-AO */
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 18c2e3c1677b..12b1809245f9 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -142,7 +142,6 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	int full_space, mss;
 	__u8 rcv_wscale;
 	u32 tsoff = 0;
-	int l3index;
 
 	if (!READ_ONCE(net->ipv4.sysctl_tcp_syncookies) ||
 	    !th->ack || th->rst)
@@ -173,8 +172,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	if (!cookie_timestamp_decode(net, &tcp_opt))
 		goto out;
 
-	req = cookie_tcp_reqsk_alloc(&tcp6_request_sock_ops,
-				     &tcp_request_sock_ipv6_ops, sk, skb);
+	req = cookie_tcp_reqsk_alloc(&tcp6_request_sock_ops, sk, skb);
 	if (!req)
 		goto out_drop;
 
@@ -218,8 +216,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	treq->ts_off = tsoff;
 	treq->txhash = net_tx_rndhash();
 
-	l3index = l3mdev_master_ifindex_by_index(net, ireq->ir_iif);
-	tcp_ao_syncookie(sk, skb, treq, AF_INET6, l3index);
+	tcp_ao_syncookie(sk, skb, req, AF_INET6);
 
 	if (IS_ENABLED(CONFIG_SMC))
 		ireq->smc_ok = 0;
-- 
cgit v1.2.3


From 8e7bab6b9652cd07a05ee0380b623c0e00e3eb00 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Tue, 28 Nov 2023 18:29:24 -0800
Subject: tcp: Factorise cookie-dependent fields initialisation in
 cookie_v[46]_check()

We will support arbitrary SYN Cookie with BPF, and then kfunc at
TC will preallocate reqsk and initialise some fields that should
not be overwritten later by cookie_v[46]_check().

To simplify the flow in cookie_v[46]_check(), we move such fields'
initialisation to cookie_tcp_reqsk_alloc() and factorise non-BPF
SYN Cookie handling into cookie_tcp_check(), where we validate the
cookie and allocate reqsk, as done by kfunc later.

Note that we set ireq->ecn_ok in two steps, the latter of which will
be shared by the BPF case.  As cookie_ecn_ok() is one-liner, now
it's inlined.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20231129022924.96156-9-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/tcp.h     |  13 +++++--
 net/ipv4/syncookies.c | 106 +++++++++++++++++++++++++++-----------------------
 net/ipv6/syncookies.c |  61 +++++++++++++++--------------
 3 files changed, 99 insertions(+), 81 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index d4d0e9763175..973555cb1d3f 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -494,7 +494,10 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb,
 int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th);
 struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb);
 struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops,
-					    struct sock *sk, struct sk_buff *skb);
+					    struct sock *sk, struct sk_buff *skb,
+					    struct tcp_options_received *tcp_opt,
+					    int mss, u32 tsoff);
+
 #ifdef CONFIG_SYN_COOKIES
 
 /* Syncookies use a monotonic timer which increments every 60 seconds.
@@ -580,8 +583,12 @@ __u32 cookie_v4_init_sequence(const struct sk_buff *skb, __u16 *mss);
 u64 cookie_init_timestamp(struct request_sock *req, u64 now);
 bool cookie_timestamp_decode(const struct net *net,
 			     struct tcp_options_received *opt);
-bool cookie_ecn_ok(const struct tcp_options_received *opt,
-		   const struct net *net, const struct dst_entry *dst);
+
+static inline bool cookie_ecn_ok(const struct net *net, const struct dst_entry *dst)
+{
+	return READ_ONCE(net->ipv4.sysctl_tcp_ecn) ||
+		dst_feature(dst, RTAX_FEATURE_ECN);
+}
 
 /* From net/ipv6/syncookies.c */
 int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th);
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index f4bcd4822fe0..61f1c96cfe63 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -270,21 +270,6 @@ bool cookie_timestamp_decode(const struct net *net,
 }
 EXPORT_SYMBOL(cookie_timestamp_decode);
 
-bool cookie_ecn_ok(const struct tcp_options_received *tcp_opt,
-		   const struct net *net, const struct dst_entry *dst)
-{
-	bool ecn_ok = tcp_opt->rcv_tsecr & TS_OPT_ECN;
-
-	if (!ecn_ok)
-		return false;
-
-	if (READ_ONCE(net->ipv4.sysctl_tcp_ecn))
-		return true;
-
-	return dst_feature(dst, RTAX_FEATURE_ECN);
-}
-EXPORT_SYMBOL(cookie_ecn_ok);
-
 static int cookie_tcp_reqsk_init(struct sock *sk, struct sk_buff *skb,
 				 struct request_sock *req)
 {
@@ -320,8 +305,12 @@ static int cookie_tcp_reqsk_init(struct sock *sk, struct sk_buff *skb,
 }
 
 struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops,
-					    struct sock *sk, struct sk_buff *skb)
+					    struct sock *sk, struct sk_buff *skb,
+					    struct tcp_options_received *tcp_opt,
+					    int mss, u32 tsoff)
 {
+	struct inet_request_sock *ireq;
+	struct tcp_request_sock *treq;
 	struct request_sock *req;
 
 	if (sk_is_mptcp(sk))
@@ -337,40 +326,36 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops,
 		return NULL;
 	}
 
+	ireq = inet_rsk(req);
+	treq = tcp_rsk(req);
+
+	req->mss = mss;
+	req->ts_recent = tcp_opt->saw_tstamp ? tcp_opt->rcv_tsval : 0;
+
+	ireq->snd_wscale = tcp_opt->snd_wscale;
+	ireq->tstamp_ok = tcp_opt->saw_tstamp;
+	ireq->sack_ok = tcp_opt->sack_ok;
+	ireq->wscale_ok = tcp_opt->wscale_ok;
+	ireq->ecn_ok = !!(tcp_opt->rcv_tsecr & TS_OPT_ECN);
+
+	treq->ts_off = tsoff;
+
 	return req;
 }
 EXPORT_SYMBOL_GPL(cookie_tcp_reqsk_alloc);
 
-/* On input, sk is a listener.
- * Output is listener if incoming packet would not create a child
- *           NULL if memory could not be allocated.
- */
-struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
+static struct request_sock *cookie_tcp_check(struct net *net, struct sock *sk,
+					     struct sk_buff *skb)
 {
-	struct ip_options *opt = &TCP_SKB_CB(skb)->header.h4.opt;
-	const struct tcphdr *th = tcp_hdr(skb);
 	struct tcp_options_received tcp_opt;
-	struct tcp_sock *tp = tcp_sk(sk);
-	struct inet_request_sock *ireq;
-	struct net *net = sock_net(sk);
-	struct tcp_request_sock *treq;
-	struct request_sock *req;
-	struct sock *ret = sk;
-	int full_space, mss;
-	struct flowi4 fl4;
-	struct rtable *rt;
-	__u8 rcv_wscale;
 	u32 tsoff = 0;
-
-	if (!READ_ONCE(net->ipv4.sysctl_tcp_syncookies) ||
-	    !th->ack || th->rst)
-		goto out;
+	int mss;
 
 	if (tcp_synq_no_recent_overflow(sk))
 		goto out;
 
-	mss = __cookie_v4_check(ip_hdr(skb), th);
-	if (mss == 0) {
+	mss = __cookie_v4_check(ip_hdr(skb), tcp_hdr(skb));
+	if (!mss) {
 		__NET_INC_STATS(net, LINUX_MIB_SYNCOOKIESFAILED);
 		goto out;
 	}
@@ -391,21 +376,44 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	if (!cookie_timestamp_decode(net, &tcp_opt))
 		goto out;
 
-	req = cookie_tcp_reqsk_alloc(&tcp_request_sock_ops, sk, skb);
+	return cookie_tcp_reqsk_alloc(&tcp_request_sock_ops, sk, skb,
+				      &tcp_opt, mss, tsoff);
+out:
+	return ERR_PTR(-EINVAL);
+}
+
+/* On input, sk is a listener.
+ * Output is listener if incoming packet would not create a child
+ *           NULL if memory could not be allocated.
+ */
+struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
+{
+	struct ip_options *opt = &TCP_SKB_CB(skb)->header.h4.opt;
+	const struct tcphdr *th = tcp_hdr(skb);
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct inet_request_sock *ireq;
+	struct net *net = sock_net(sk);
+	struct request_sock *req;
+	struct sock *ret = sk;
+	struct flowi4 fl4;
+	struct rtable *rt;
+	__u8 rcv_wscale;
+	int full_space;
+
+	if (!READ_ONCE(net->ipv4.sysctl_tcp_syncookies) ||
+	    !th->ack || th->rst)
+		goto out;
+
+	req = cookie_tcp_check(net, sk, skb);
+	if (IS_ERR(req))
+		goto out;
 	if (!req)
 		goto out_drop;
 
 	ireq = inet_rsk(req);
-	treq = tcp_rsk(req);
-	treq->ts_off		= tsoff;
-	req->mss		= mss;
+
 	sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr);
 	sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr);
-	ireq->snd_wscale	= tcp_opt.snd_wscale;
-	ireq->sack_ok		= tcp_opt.sack_ok;
-	ireq->wscale_ok		= tcp_opt.wscale_ok;
-	ireq->tstamp_ok		= tcp_opt.saw_tstamp;
-	req->ts_recent		= tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0;
 
 	/* We throwed the options of the initial SYN away, so we hope
 	 * the ACK carries the same options again (see RFC1122 4.2.3.8)
@@ -447,7 +455,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 				  dst_metric(&rt->dst, RTAX_INITRWND));
 
 	ireq->rcv_wscale  = rcv_wscale;
-	ireq->ecn_ok = cookie_ecn_ok(&tcp_opt, net, &rt->dst);
+	ireq->ecn_ok &= cookie_ecn_ok(net, &rt->dst);
 
 	ret = tcp_get_cookie_sock(sk, skb, req, &rt->dst);
 	/* ip_queue_xmit() depends on our flow being setup
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index e0a9220d1536..c8d2ca27220c 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -127,31 +127,18 @@ int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th)
 }
 EXPORT_SYMBOL_GPL(__cookie_v6_check);
 
-struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
+static struct request_sock *cookie_tcp_check(struct net *net, struct sock *sk,
+					     struct sk_buff *skb)
 {
-	const struct tcphdr *th = tcp_hdr(skb);
-	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct tcp_options_received tcp_opt;
-	struct tcp_sock *tp = tcp_sk(sk);
-	struct inet_request_sock *ireq;
-	struct net *net = sock_net(sk);
-	struct tcp_request_sock *treq;
-	struct request_sock *req;
-	struct dst_entry *dst;
-	struct sock *ret = sk;
-	int full_space, mss;
-	__u8 rcv_wscale;
 	u32 tsoff = 0;
-
-	if (!READ_ONCE(net->ipv4.sysctl_tcp_syncookies) ||
-	    !th->ack || th->rst)
-		goto out;
+	int mss;
 
 	if (tcp_synq_no_recent_overflow(sk))
 		goto out;
 
-	mss = __cookie_v6_check(ipv6_hdr(skb), th);
-	if (mss == 0) {
+	mss = __cookie_v6_check(ipv6_hdr(skb), tcp_hdr(skb));
+	if (!mss) {
 		__NET_INC_STATS(net, LINUX_MIB_SYNCOOKIESFAILED);
 		goto out;
 	}
@@ -172,14 +159,37 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	if (!cookie_timestamp_decode(net, &tcp_opt))
 		goto out;
 
-	req = cookie_tcp_reqsk_alloc(&tcp6_request_sock_ops, sk, skb);
+	return cookie_tcp_reqsk_alloc(&tcp6_request_sock_ops, sk, skb,
+				      &tcp_opt, mss, tsoff);
+out:
+	return ERR_PTR(-EINVAL);
+}
+
+struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
+{
+	const struct tcphdr *th = tcp_hdr(skb);
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct inet_request_sock *ireq;
+	struct net *net = sock_net(sk);
+	struct request_sock *req;
+	struct dst_entry *dst;
+	struct sock *ret = sk;
+	__u8 rcv_wscale;
+	int full_space;
+
+	if (!READ_ONCE(net->ipv4.sysctl_tcp_syncookies) ||
+	    !th->ack || th->rst)
+		goto out;
+
+	req = cookie_tcp_check(net, sk, skb);
+	if (IS_ERR(req))
+		goto out;
 	if (!req)
 		goto out_drop;
 
 	ireq = inet_rsk(req);
-	treq = tcp_rsk(req);
 
-	req->mss = mss;
 	ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
 	ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
 
@@ -198,13 +208,6 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	    ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
 		ireq->ir_iif = tcp_v6_iif(skb);
 
-	ireq->snd_wscale	= tcp_opt.snd_wscale;
-	ireq->sack_ok		= tcp_opt.sack_ok;
-	ireq->wscale_ok		= tcp_opt.wscale_ok;
-	ireq->tstamp_ok		= tcp_opt.saw_tstamp;
-	req->ts_recent		= tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0;
-	treq->ts_off = tsoff;
-
 	tcp_ao_syncookie(sk, skb, req, AF_INET6);
 
 	/*
@@ -245,7 +248,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 				  dst_metric(dst, RTAX_INITRWND));
 
 	ireq->rcv_wscale = rcv_wscale;
-	ireq->ecn_ok = cookie_ecn_ok(&tcp_opt, net, dst);
+	ireq->ecn_ok &= cookie_ecn_ok(net, dst);
 
 	ret = tcp_get_cookie_sock(sk, skb, req, dst);
 out:
-- 
cgit v1.2.3


From f32f977fa8ab1d2fde0cd7136e0d0393fce31d84 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Thu, 23 Nov 2023 17:17:41 +0100
Subject: dt-bindings: power: meson-g12a-power: document ISP power domain

Add MIPI ISP power domain ID to the G12A Power domains bindings header

Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Reviewed-by: Daniel Scally <dan.scally@ideasonboard.com>
Tested-by: Daniel Scally <dan.scally@ideasonboard.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20231123-topic-amlogic-upstream-isp-pmdomain-v2-1-61f2fcf709e5@linaro.org
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 include/dt-bindings/power/meson-g12a-power.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/dt-bindings/power/meson-g12a-power.h b/include/dt-bindings/power/meson-g12a-power.h
index 44ec0c50e340..01fd0ac4dd08 100644
--- a/include/dt-bindings/power/meson-g12a-power.h
+++ b/include/dt-bindings/power/meson-g12a-power.h
@@ -10,5 +10,6 @@
 #define PWRC_G12A_VPU_ID		0
 #define PWRC_G12A_ETH_ID		1
 #define PWRC_G12A_NNA_ID		2
+#define PWRC_G12A_ISP_ID		3
 
 #endif
-- 
cgit v1.2.3


From 39cefd85098d12439586824c39f8e1948fac186d Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 29 Nov 2023 17:31:55 +0100
Subject: spi: introduce SPI_TRANS_FAIL_IO for error reporting

The default message transfer implementation - spi_transfer_one_message -
invokes the specific device driver's transfer_one(), then waits for
completion. However, there is no mechanism for the device driver to
report failure in the middle of the transfer.

Introduce SPI_TRANS_FAIL_IO for drivers to report transfer failure.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/4b420dac528e60f122adde16851da88e4798c1ea.1701274975.git.namcao@linutronix.de
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi.c       |  3 +++
 include/linux/spi/spi.h | 12 ++++++++----
 2 files changed, 11 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 8ead7acb99f3..a4b8c07c5951 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -1361,6 +1361,9 @@ static int spi_transfer_wait(struct spi_controller *ctlr,
 				"SPI transfer timed out\n");
 			return -ETIMEDOUT;
 		}
+
+		if (xfer->error & SPI_TRANS_FAIL_IO)
+			return -EIO;
 	}
 
 	return 0;
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 255a0562aea5..aa25ae04c5c3 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -461,10 +461,13 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch
  *                  - return 1 if the transfer is still in progress. When
  *                    the driver is finished with this transfer it must
  *                    call spi_finalize_current_transfer() so the subsystem
- *                    can issue the next transfer. Note: transfer_one and
- *                    transfer_one_message are mutually exclusive; when both
- *                    are set, the generic subsystem does not call your
- *                    transfer_one callback.
+ *                    can issue the next transfer. If the transfer fails, the
+ *                    driver must set the flag SPI_TRANS_FAIL_IO to
+ *                    spi_transfer->error first, before calling
+ *                    spi_finalize_current_transfer().
+ *                    Note: transfer_one and transfer_one_message are mutually
+ *                    exclusive; when both are set, the generic subsystem does
+ *                    not call your transfer_one callback.
  * @handle_err: the subsystem calls the driver to handle an error that occurs
  *		in the generic implementation of transfer_one_message().
  * @mem_ops: optimized/dedicated operations for interactions with SPI memory.
@@ -1040,6 +1043,7 @@ struct spi_transfer {
 	unsigned	len;
 
 #define SPI_TRANS_FAIL_NO_START	BIT(0)
+#define SPI_TRANS_FAIL_IO	BIT(1)
 	u16		error;
 
 	dma_addr_t	tx_dma;
-- 
cgit v1.2.3


From cff49d58f57e5667c10a0db85d7461790bb85cf8 Mon Sep 17 00:00:00 2001
From: "Chia-Lin Kao (AceLan)" <acelan.kao@canonical.com>
Date: Wed, 29 Nov 2023 14:43:10 +0800
Subject: spi: Unify error codes by replacing -ENOTSUPP with -EOPNOTSUPP

This commit updates the SPI subsystem, particularly affecting "SPI MEM"
drivers and core parts, by replacing the -ENOTSUPP error code with
-EOPNOTSUPP.

The key motivations for this change are as follows:
1. The spi-nor driver currently uses EOPNOTSUPP, whereas calls to spi-mem
might return ENOTSUPP. This update aims to unify the error reporting
within the SPI subsystem for clarity and consistency.

2. The use of ENOTSUPP has been flagged by checkpatch as inappropriate,
mainly being reserved for NFS-related errors. To align with kernel coding
standards and recommendations, this change is being made.

3. By using EOPNOTSUPP, we provide more specific context to the error,
indicating that a particular operation is not supported. This helps
differentiate from the more generic ENOTSUPP error, allowing drivers to
better handle and respond to different error scenarios.

Risks and Considerations:
While this change is primarily intended as a code cleanup and error code
unification, there is a minor risk of breaking user-space applications
that rely on specific return codes for unsupported operations. However,
this risk is considered low, as such use-cases are unlikely to be common
or critical. Nevertheless, developers and users should be aware of this
change, especially if they have scripts or tools that specifically handle
SPI error codes.

This commit does not introduce any functional changes to the SPI subsystem
or the affected drivers.

Signed-off-by: "Chia-Lin Kao (AceLan)" <acelan.kao@canonical.com>
Acked-by: Tudor Ambarus <tudor.ambarus@linaro.org>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Miquel Raynal <miquel.raynal@bootlin.com>
Acked-by: Michael Walle <michael@walle.cc>
Link: https://lore.kernel.org/r/20231129064311.272422-1-acelan.kao@canonical.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/mtd/nand/spi/core.c | 2 +-
 drivers/mtd/spi-nor/core.c  | 2 +-
 drivers/spi/atmel-quadspi.c | 2 +-
 drivers/spi/spi-ath79.c     | 2 +-
 drivers/spi/spi-bcm-qspi.c  | 2 +-
 drivers/spi/spi-mem.c       | 6 +++---
 drivers/spi/spi-npcm-fiu.c  | 2 +-
 drivers/spi/spi-ti-qspi.c   | 4 ++--
 drivers/spi/spi-wpcm-fiu.c  | 2 +-
 include/linux/spi/spi-mem.h | 2 ++
 10 files changed, 14 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c
index 849ccfedbc72..e0b6715e5dfe 100644
--- a/drivers/mtd/nand/spi/core.c
+++ b/drivers/mtd/nand/spi/core.c
@@ -974,7 +974,7 @@ static int spinand_manufacturer_match(struct spinand_device *spinand,
 		spinand->manufacturer = manufacturer;
 		return 0;
 	}
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 
 static int spinand_id_detect(struct spinand_device *spinand)
diff --git a/drivers/mtd/spi-nor/core.c b/drivers/mtd/spi-nor/core.c
index 1c443fe568cf..87cb2047df80 100644
--- a/drivers/mtd/spi-nor/core.c
+++ b/drivers/mtd/spi-nor/core.c
@@ -3146,7 +3146,7 @@ int spi_nor_set_4byte_addr_mode(struct spi_nor *nor, bool enable)
 	int ret;
 
 	ret = params->set_4byte_addr_mode(nor, enable);
-	if (ret && ret != -ENOTSUPP)
+	if (ret && ret != -EOPNOTSUPP)
 		return ret;
 
 	if (enable) {
diff --git a/drivers/spi/atmel-quadspi.c b/drivers/spi/atmel-quadspi.c
index 3d1252566134..370c4d1572ed 100644
--- a/drivers/spi/atmel-quadspi.c
+++ b/drivers/spi/atmel-quadspi.c
@@ -272,7 +272,7 @@ static int atmel_qspi_find_mode(const struct spi_mem_op *op)
 		if (atmel_qspi_is_compatible(op, &atmel_qspi_modes[i]))
 			return i;
 
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 
 static bool atmel_qspi_supports_op(struct spi_mem *mem,
diff --git a/drivers/spi/spi-ath79.c b/drivers/spi/spi-ath79.c
index c9f1d1e1dcf7..b7ada981464a 100644
--- a/drivers/spi/spi-ath79.c
+++ b/drivers/spi/spi-ath79.c
@@ -146,7 +146,7 @@ static int ath79_exec_mem_op(struct spi_mem *mem,
 	/* Only use for fast-read op. */
 	if (op->cmd.opcode != 0x0b || op->data.dir != SPI_MEM_DATA_IN ||
 	    op->addr.nbytes != 3 || op->dummy.nbytes != 1)
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	/* disable GPIO mode */
 	ath79_spi_wr(sp, AR71XX_SPI_REG_FS, 0);
diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c
index ef08fcac2f6d..d96222e6d7d2 100644
--- a/drivers/spi/spi-bcm-qspi.c
+++ b/drivers/spi/spi-bcm-qspi.c
@@ -1199,7 +1199,7 @@ static int bcm_qspi_exec_mem_op(struct spi_mem *mem,
 
 	if (!op->data.nbytes || !op->addr.nbytes || op->addr.nbytes > 4 ||
 	    op->data.dir != SPI_MEM_DATA_IN)
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	buf = op->data.buf.in;
 	addr = op->addr.val;
diff --git a/drivers/spi/spi-mem.c b/drivers/spi/spi-mem.c
index edd7430d4c05..2dc8ceb85374 100644
--- a/drivers/spi/spi-mem.c
+++ b/drivers/spi/spi-mem.c
@@ -323,7 +323,7 @@ int spi_mem_exec_op(struct spi_mem *mem, const struct spi_mem_op *op)
 		return ret;
 
 	if (!spi_mem_internal_supports_op(mem, op))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	if (ctlr->mem_ops && ctlr->mem_ops->exec_op && !spi_get_csgpiod(mem->spi, 0)) {
 		ret = spi_mem_access_start(mem);
@@ -339,7 +339,7 @@ int spi_mem_exec_op(struct spi_mem *mem, const struct spi_mem_op *op)
 		 * read path) and expect the core to use the regular SPI
 		 * interface in other cases.
 		 */
-		if (!ret || ret != -ENOTSUPP)
+		if (!ret || ret != -ENOTSUPP || ret != -EOPNOTSUPP)
 			return ret;
 	}
 
@@ -559,7 +559,7 @@ spi_mem_dirmap_create(struct spi_mem *mem,
 	if (ret) {
 		desc->nodirmap = true;
 		if (!spi_mem_supports_op(desc->mem, &desc->info.op_tmpl))
-			ret = -ENOTSUPP;
+			ret = -EOPNOTSUPP;
 		else
 			ret = 0;
 	}
diff --git a/drivers/spi/spi-npcm-fiu.c b/drivers/spi/spi-npcm-fiu.c
index 03db9f016a11..f3bb8bbc192f 100644
--- a/drivers/spi/spi-npcm-fiu.c
+++ b/drivers/spi/spi-npcm-fiu.c
@@ -556,7 +556,7 @@ static int npcm_fiu_exec_op(struct spi_mem *mem, const struct spi_mem_op *op)
 		op->data.nbytes);
 
 	if (fiu->spix_mode || op->addr.nbytes > 4)
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	if (fiu->clkrate != chip->clkrate) {
 		ret = clk_set_rate(fiu->clk, chip->clkrate);
diff --git a/drivers/spi/spi-ti-qspi.c b/drivers/spi/spi-ti-qspi.c
index fdc092a05284..a6a89c59c418 100644
--- a/drivers/spi/spi-ti-qspi.c
+++ b/drivers/spi/spi-ti-qspi.c
@@ -613,12 +613,12 @@ static int ti_qspi_exec_mem_op(struct spi_mem *mem,
 	/* Only optimize read path. */
 	if (!op->data.nbytes || op->data.dir != SPI_MEM_DATA_IN ||
 	    !op->addr.nbytes || op->addr.nbytes > 4)
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	/* Address exceeds MMIO window size, fall back to regular mode. */
 	from = op->addr.val;
 	if (from + op->data.nbytes > qspi->mmap_size)
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	mutex_lock(&qspi->list_lock);
 
diff --git a/drivers/spi/spi-wpcm-fiu.c b/drivers/spi/spi-wpcm-fiu.c
index 852ffe013d32..d76f7b5a9b97 100644
--- a/drivers/spi/spi-wpcm-fiu.c
+++ b/drivers/spi/spi-wpcm-fiu.c
@@ -361,7 +361,7 @@ static int wpcm_fiu_exec_op(struct spi_mem *mem, const struct spi_mem_op *op)
 
 	wpcm_fiu_stall_host(fiu, false);
 
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 
 static int wpcm_fiu_adjust_op_size(struct spi_mem *mem, struct spi_mem_op *op)
diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h
index 6b0a7dc48a4b..f866d5c8ed32 100644
--- a/include/linux/spi/spi-mem.h
+++ b/include/linux/spi/spi-mem.h
@@ -233,6 +233,8 @@ static inline void *spi_mem_get_drvdata(struct spi_mem *mem)
  *		    limitations)
  * @supports_op: check if an operation is supported by the controller
  * @exec_op: execute a SPI memory operation
+ *           not all driver provides supports_op(), so it can return -EOPNOTSUPP
+ *           if the op is not supported by the driver/controller
  * @get_name: get a custom name for the SPI mem device from the controller.
  *	      This might be needed if the controller driver has been ported
  *	      to use the SPI mem layer and a custom name is used to keep
-- 
cgit v1.2.3


From 4ea95c04fa6b9043a1a301240996aeebe3cb28ec Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 29 Nov 2023 16:10:00 -0800
Subject: vfio: Drop vfio_file_iommu_group() stub to fudge around a KVM wart

Drop the vfio_file_iommu_group() stub and instead unconditionally declare
the function to fudge around a KVM wart where KVM tries to do symbol_get()
on vfio_file_iommu_group() (and other VFIO symbols) even if CONFIG_VFIO=n.

Ensuring the symbol is always declared fixes a PPC build error when
modules are also disabled, in which case symbol_get() simply points at the
address of the symbol (with some attributes shenanigans).  Because KVM
does symbol_get() instead of directly depending on VFIO, the lack of a
fully defined symbol is not problematic (ugly, but "fine").

   arch/powerpc/kvm/../../../virt/kvm/vfio.c:89:7:
   error: attribute declaration must precede definition [-Werror,-Wignored-attributes]
           fn = symbol_get(vfio_file_iommu_group);
                ^
   include/linux/module.h:805:60: note: expanded from macro 'symbol_get'
   #define symbol_get(x) ({ extern typeof(x) x __attribute__((weak,visibility("hidden"))); &(x); })
                                                              ^
   include/linux/vfio.h:294:35: note: previous definition is here
   static inline struct iommu_group *vfio_file_iommu_group(struct file *file)
                                     ^
   arch/powerpc/kvm/../../../virt/kvm/vfio.c:89:7:
   error: attribute declaration must precede definition [-Werror,-Wignored-attributes]
           fn = symbol_get(vfio_file_iommu_group);
                ^
   include/linux/module.h:805:65: note: expanded from macro 'symbol_get'
   #define symbol_get(x) ({ extern typeof(x) x __attribute__((weak,visibility("hidden"))); &(x); })
                                                                   ^
   include/linux/vfio.h:294:35: note: previous definition is here
   static inline struct iommu_group *vfio_file_iommu_group(struct file *file)
                                     ^
   2 errors generated.

Although KVM is firmly in the wrong (there is zero reason for KVM to build
virt/kvm/vfio.c when VFIO is disabled), fudge around the error in VFIO as
the stub is unnecessary and doesn't serve its intended purpose (KVM is the
only external user of vfio_file_iommu_group()), and there is an in-flight
series to clean up the entire KVM<->VFIO interaction, i.e. fixing this in
KVM would result in more churn in the long run, and the stub needs to go
away regardless.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202308251949.5IiaV0sz-lkp@intel.com
Closes: https://lore.kernel.org/oe-kbuild-all/202309030741.82aLACDG-lkp@intel.com
Closes: https://lore.kernel.org/oe-kbuild-all/202309110914.QLH0LU6L-lkp@intel.com
Link: https://lore.kernel.org/all/0-v1-08396538817d+13c5-vfio_kvm_kconfig_jgg@nvidia.com
Link: https://lore.kernel.org/all/20230916003118.2540661-1-seanjc@google.com
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Tested-by: Michael Ellerman <mpe@ellerman.id.au>
Fixes: c1cce6d079b8 ("vfio: Compile vfio_group infrastructure optionally")
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20231130001000.543240-1-seanjc@google.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 include/linux/vfio.h | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index 454e9295970c..a65b2513f8cd 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -289,16 +289,12 @@ void vfio_combine_iova_ranges(struct rb_root_cached *root, u32 cur_nodes,
 /*
  * External user API
  */
-#if IS_ENABLED(CONFIG_VFIO_GROUP)
 struct iommu_group *vfio_file_iommu_group(struct file *file);
+
+#if IS_ENABLED(CONFIG_VFIO_GROUP)
 bool vfio_file_is_group(struct file *file);
 bool vfio_file_has_dev(struct file *file, struct vfio_device *device);
 #else
-static inline struct iommu_group *vfio_file_iommu_group(struct file *file)
-{
-	return NULL;
-}
-
 static inline bool vfio_file_is_group(struct file *file)
 {
 	return false;
-- 
cgit v1.2.3


From 0514f63cfff38a0dcb7ba9c5f245827edc0c5107 Mon Sep 17 00:00:00 2001
From: Felix Kuehling <Felix.Kuehling@amd.com>
Date: Fri, 17 Nov 2023 16:44:17 -0500
Subject: Revert "drm/prime: Unexport helpers for fd/handle conversion"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This reverts commit 71a7974ac7019afeec105a54447ae1dc7216cbb3.

These helper functions are needed for KFD to export and import DMABufs
the right way without duplicating the tracking of DMABufs associated with
GEM objects while ensuring that move notifier callbacks are working as
intended.

CC: Christian König <christian.koenig@amd.com>
CC: Thomas Zimmermann <tzimmermann@suse.de>
Acked-by: Thomas Zimmermann <tzimmermann@suse.de>
Acked-by: Daniel Vetter <daniel@ffwll.ch>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/drm_prime.c | 33 ++++++++++++++++++---------------
 include/drm/drm_prime.h     |  7 +++++++
 2 files changed, 25 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index 63b709a67471..834a5e28abbe 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -278,7 +278,7 @@ void drm_gem_dmabuf_release(struct dma_buf *dma_buf)
 }
 EXPORT_SYMBOL(drm_gem_dmabuf_release);
 
-/*
+/**
  * drm_gem_prime_fd_to_handle - PRIME import function for GEM drivers
  * @dev: drm_device to import into
  * @file_priv: drm file-private structure
@@ -292,9 +292,9 @@ EXPORT_SYMBOL(drm_gem_dmabuf_release);
  *
  * Returns 0 on success or a negative error code on failure.
  */
-static int drm_gem_prime_fd_to_handle(struct drm_device *dev,
-				      struct drm_file *file_priv, int prime_fd,
-				      uint32_t *handle)
+int drm_gem_prime_fd_to_handle(struct drm_device *dev,
+			       struct drm_file *file_priv, int prime_fd,
+			       uint32_t *handle)
 {
 	struct dma_buf *dma_buf;
 	struct drm_gem_object *obj;
@@ -360,6 +360,7 @@ out_put:
 	dma_buf_put(dma_buf);
 	return ret;
 }
+EXPORT_SYMBOL(drm_gem_prime_fd_to_handle);
 
 int drm_prime_fd_to_handle_ioctl(struct drm_device *dev, void *data,
 				 struct drm_file *file_priv)
@@ -408,7 +409,7 @@ static struct dma_buf *export_and_register_object(struct drm_device *dev,
 	return dmabuf;
 }
 
-/*
+/**
  * drm_gem_prime_handle_to_fd - PRIME export function for GEM drivers
  * @dev: dev to export the buffer from
  * @file_priv: drm file-private structure
@@ -421,10 +422,10 @@ static struct dma_buf *export_and_register_object(struct drm_device *dev,
  * The actual exporting from GEM object to a dma-buf is done through the
  * &drm_gem_object_funcs.export callback.
  */
-static int drm_gem_prime_handle_to_fd(struct drm_device *dev,
-				      struct drm_file *file_priv, uint32_t handle,
-				      uint32_t flags,
-				      int *prime_fd)
+int drm_gem_prime_handle_to_fd(struct drm_device *dev,
+			       struct drm_file *file_priv, uint32_t handle,
+			       uint32_t flags,
+			       int *prime_fd)
 {
 	struct drm_gem_object *obj;
 	int ret = 0;
@@ -506,6 +507,7 @@ out_unlock:
 
 	return ret;
 }
+EXPORT_SYMBOL(drm_gem_prime_handle_to_fd);
 
 int drm_prime_handle_to_fd_ioctl(struct drm_device *dev, void *data,
 				 struct drm_file *file_priv)
@@ -864,9 +866,9 @@ EXPORT_SYMBOL(drm_prime_get_contiguous_size);
  * @obj: GEM object to export
  * @flags: flags like DRM_CLOEXEC and DRM_RDWR
  *
- * This is the implementation of the &drm_gem_object_funcs.export functions
- * for GEM drivers using the PRIME helpers. It is used as the default for
- * drivers that do not set their own.
+ * This is the implementation of the &drm_gem_object_funcs.export functions for GEM drivers
+ * using the PRIME helpers. It is used as the default in
+ * drm_gem_prime_handle_to_fd().
  */
 struct dma_buf *drm_gem_prime_export(struct drm_gem_object *obj,
 				     int flags)
@@ -962,9 +964,10 @@ EXPORT_SYMBOL(drm_gem_prime_import_dev);
  * @dev: drm_device to import into
  * @dma_buf: dma-buf object to import
  *
- * This is the implementation of the gem_prime_import functions for GEM
- * drivers using the PRIME helpers. It is the default for drivers that do
- * not set their own &drm_driver.gem_prime_import.
+ * This is the implementation of the gem_prime_import functions for GEM drivers
+ * using the PRIME helpers. Drivers can use this as their
+ * &drm_driver.gem_prime_import implementation. It is used as the default
+ * implementation in drm_gem_prime_fd_to_handle().
  *
  * Drivers must arrange to call drm_prime_gem_destroy() from their
  * &drm_gem_object_funcs.free hook when using this function.
diff --git a/include/drm/drm_prime.h b/include/drm/drm_prime.h
index a7abf9f3e697..2a1d01e5b56b 100644
--- a/include/drm/drm_prime.h
+++ b/include/drm/drm_prime.h
@@ -60,12 +60,19 @@ enum dma_data_direction;
 
 struct drm_device;
 struct drm_gem_object;
+struct drm_file;
 
 /* core prime functions */
 struct dma_buf *drm_gem_dmabuf_export(struct drm_device *dev,
 				      struct dma_buf_export_info *exp_info);
 void drm_gem_dmabuf_release(struct dma_buf *dma_buf);
 
+int drm_gem_prime_fd_to_handle(struct drm_device *dev,
+			       struct drm_file *file_priv, int prime_fd, uint32_t *handle);
+int drm_gem_prime_handle_to_fd(struct drm_device *dev,
+			       struct drm_file *file_priv, uint32_t handle, uint32_t flags,
+			       int *prime_fd);
+
 /* helper functions for exporting */
 int drm_gem_map_attach(struct dma_buf *dma_buf,
 		       struct dma_buf_attachment *attach);
-- 
cgit v1.2.3


From 3717194f249227a3dfd8433bd9374cc7e0cf823d Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Wed, 29 Nov 2023 13:06:15 +0200
Subject: Input: gpio-keys - add system suspend support for dedicated wakeirqs

Some SoCs have a separate dedicated wake-up interrupt controller that can
be used to wake up the system from deeper idle states. We already support
configuring a separate interrupt for a gpio-keys button to be used with a
gpio line. However, we are lacking support system suspend for cases where
a separate interrupt needs to be used in deeper sleep modes.

Because of it's nature, gpio-keys does not know about the runtime PM state
of the button gpios, and may have several gpio buttons configured for each
gpio-keys device instance. Implementing runtime PM support for gpio-keys
does not help, and we cannot use drivers/base/power/wakeirq.c support. We
need to implement custom wakeirq support for gpio-keys.

For handling a dedicated wakeirq for system suspend, we enable and disable
it with gpio_keys_enable_wakeup() and gpio_keys_disable_wakeup() that we
already use based on device_may_wakeup().

Some systems may have a dedicated wakeirq that can also be used as the
main interrupt, this is already working for gpio-keys. Let's add some
wakeirq related comments while at it as the usage with a gpio line and
separate interrupt line may not be obvious.

Tested-by: Dhruva Gole <d-gole@ti.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
Link: https://lore.kernel.org/r/20231129110618.27551-2-tony@atomide.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/gpio_keys.c | 69 +++++++++++++++++++++++++++++++++++---
 include/linux/gpio_keys.h          |  2 ++
 2 files changed, 67 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/input/keyboard/gpio_keys.c b/drivers/input/keyboard/gpio_keys.c
index 2e7c2c046e67..06c09b7addf8 100644
--- a/drivers/input/keyboard/gpio_keys.c
+++ b/drivers/input/keyboard/gpio_keys.c
@@ -45,7 +45,9 @@ struct gpio_button_data {
 	unsigned int software_debounce;	/* in msecs, for GPIO-driven buttons */
 
 	unsigned int irq;
+	unsigned int wakeirq;
 	unsigned int wakeup_trigger_type;
+
 	spinlock_t lock;
 	bool disabled;
 	bool key_pressed;
@@ -511,6 +513,7 @@ static int gpio_keys_setup_key(struct platform_device *pdev,
 	struct gpio_button_data *bdata = &ddata->data[idx];
 	irq_handler_t isr;
 	unsigned long irqflags;
+	const char *wakedesc;
 	int irq;
 	int error;
 
@@ -575,6 +578,14 @@ static int gpio_keys_setup_key(struct platform_device *pdev,
 					!gpiod_cansleep(bdata->gpiod);
 		}
 
+		/*
+		 * If an interrupt was specified, use it instead of the gpio
+		 * interrupt and use the gpio for reading the state. A separate
+		 * interrupt may be used as the main button interrupt for
+		 * runtime PM to detect events also in deeper idle states. If a
+		 * dedicated wakeirq is used for system suspend only, see below
+		 * for bdata->wakeirq setup.
+		 */
 		if (button->irq) {
 			bdata->irq = button->irq;
 		} else {
@@ -672,6 +683,36 @@ static int gpio_keys_setup_key(struct platform_device *pdev,
 		return error;
 	}
 
+	if (!button->wakeirq)
+		return 0;
+
+	/* Use :wakeup suffix like drivers/base/power/wakeirq.c does */
+	wakedesc = devm_kasprintf(dev, GFP_KERNEL, "%s:wakeup", desc);
+	if (!wakedesc)
+		return -ENOMEM;
+
+	bdata->wakeirq = button->wakeirq;
+	irqflags |= IRQF_NO_SUSPEND;
+
+	/*
+	 * Wakeirq shares the handler with the main interrupt, it's only
+	 * active during system suspend. See gpio_keys_button_enable_wakeup()
+	 * and gpio_keys_button_disable_wakeup().
+	 */
+	error = devm_request_any_context_irq(dev, bdata->wakeirq, isr,
+					     irqflags, wakedesc, bdata);
+	if (error < 0) {
+		dev_err(dev, "Unable to claim wakeirq %d; error %d\n",
+			bdata->irq, error);
+		return error;
+	}
+
+	/*
+	 * Disable wakeirq until suspend. IRQF_NO_AUTOEN won't work if
+	 * IRQF_SHARED was set based on !button->can_disable.
+	 */
+	disable_irq(bdata->wakeirq);
+
 	return 0;
 }
 
@@ -728,7 +769,7 @@ gpio_keys_get_devtree_pdata(struct device *dev)
 	struct gpio_keys_platform_data *pdata;
 	struct gpio_keys_button *button;
 	struct fwnode_handle *child;
-	int nbuttons;
+	int nbuttons, irq;
 
 	nbuttons = device_get_child_node_count(dev);
 	if (nbuttons == 0)
@@ -750,9 +791,19 @@ gpio_keys_get_devtree_pdata(struct device *dev)
 	device_property_read_string(dev, "label", &pdata->name);
 
 	device_for_each_child_node(dev, child) {
-		if (is_of_node(child))
-			button->irq =
-				irq_of_parse_and_map(to_of_node(child), 0);
+		if (is_of_node(child)) {
+			irq = of_irq_get_byname(to_of_node(child), "irq");
+			if (irq > 0)
+				button->irq = irq;
+
+			irq = of_irq_get_byname(to_of_node(child), "wakeup");
+			if (irq > 0)
+				button->wakeirq = irq;
+
+			if (!button->irq && !button->wakeirq)
+				button->irq =
+					irq_of_parse_and_map(to_of_node(child), 0);
+		}
 
 		if (fwnode_property_read_u32(child, "linux,code",
 					     &button->code)) {
@@ -921,6 +972,11 @@ gpio_keys_button_enable_wakeup(struct gpio_button_data *bdata)
 		}
 	}
 
+	if (bdata->wakeirq) {
+		enable_irq(bdata->wakeirq);
+		disable_irq(bdata->irq);
+	}
+
 	return 0;
 }
 
@@ -929,6 +985,11 @@ gpio_keys_button_disable_wakeup(struct gpio_button_data *bdata)
 {
 	int error;
 
+	if (bdata->wakeirq) {
+		enable_irq(bdata->irq);
+		disable_irq(bdata->wakeirq);
+	}
+
 	/*
 	 * The trigger type is always both edges for gpio-based keys and we do
 	 * not support changing wakeup trigger for interrupt-based keys.
diff --git a/include/linux/gpio_keys.h b/include/linux/gpio_keys.h
index 3f84aeb81e48..80fa930b04c6 100644
--- a/include/linux/gpio_keys.h
+++ b/include/linux/gpio_keys.h
@@ -21,6 +21,7 @@ struct device;
  *			disable button via sysfs
  * @value:		axis value for %EV_ABS
  * @irq:		Irq number in case of interrupt keys
+ * @wakeirq:		Optional dedicated wake-up interrupt
  */
 struct gpio_keys_button {
 	unsigned int code;
@@ -34,6 +35,7 @@ struct gpio_keys_button {
 	bool can_disable;
 	int value;
 	unsigned int irq;
+	unsigned int wakeirq;
 };
 
 /**
-- 
cgit v1.2.3


From da2e08d4630ab04ee5b61515fe423c582b5c3be2 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 3 Oct 2023 16:18:38 -0700
Subject: i40e: Annotate struct i40e_qvlist_info with __counted_by

Prepare for the coming implementation by GCC and Clang of the __counted_by
attribute. Flexible array members annotated with __counted_by can have
their accesses bounds-checked at run-time via CONFIG_UBSAN_BOUNDS (for
array indexing) and CONFIG_FORTIFY_SOURCE (for strcpy/memcpy-family
functions).

As found with Coccinelle[1], add __counted_by for struct i40e_qvlist_info.

Cc: Tony Nguyen <anthony.l.nguyen@intel.com>
Cc: Shiraz Saleem <shiraz.saleem@intel.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Jesse Brandeburg <jesse.brandeburg@intel.com>
Cc: Gurucharan G <gurucharanx.g@intel.com>
Cc: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Link: https://github.com/kees/kernel-tools/blob/trunk/coccinelle/examples/counted_by.cocci [1]
Reviewed-by: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Link: https://lore.kernel.org/r/20231003231838.work.510-kees@kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 include/linux/net/intel/i40e_client.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/net/intel/i40e_client.h b/include/linux/net/intel/i40e_client.h
index ed42bd5f639f..0aa4411528fc 100644
--- a/include/linux/net/intel/i40e_client.h
+++ b/include/linux/net/intel/i40e_client.h
@@ -45,7 +45,7 @@ struct i40e_qv_info {
 
 struct i40e_qvlist_info {
 	u32 num_vectors;
-	struct i40e_qv_info qv_info[];
+	struct i40e_qv_info qv_info[] __counted_by(num_vectors);
 };
 
 
-- 
cgit v1.2.3


From 6a3afb6ac6dfab158ebdd4b87941178f58c8939f Mon Sep 17 00:00:00 2001
From: Zhang Yi <yi.zhang@huawei.com>
Date: Wed, 29 Nov 2023 19:47:40 +0800
Subject: jbd2: increase the journal IO's priority

Current jbd2 only add REQ_SYNC for descriptor block, metadata log
buffer, commit buffer and superblock buffer, the submitted IO could be
throttled by writeback throttle in block layer, that could lead to
priority inversion in some cases. The log IO looks like a kind of high
priority metadata IO, so it should not be throttled by WBT like QOS
policies in block layer, let's add REQ_SYNC | REQ_IDLE to exempt from
writeback throttle, and also add REQ_META together indicates it's a
metadata IO.

Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20231129114740.2686201-2-yi.zhang@huaweicloud.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/jbd2/commit.c     |  9 +++++----
 fs/jbd2/journal.c    | 20 +++++++++++---------
 include/linux/jbd2.h |  3 +++
 3 files changed, 19 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 8d6f934c3d95..9bdb377a348f 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -119,7 +119,7 @@ static int journal_submit_commit_record(journal_t *journal,
 	struct commit_header *tmp;
 	struct buffer_head *bh;
 	struct timespec64 now;
-	blk_opf_t write_flags = REQ_OP_WRITE | REQ_SYNC;
+	blk_opf_t write_flags = REQ_OP_WRITE | JBD2_JOURNAL_REQ_FLAGS;
 
 	*cbh = NULL;
 
@@ -395,8 +395,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 		 */
 		jbd2_journal_update_sb_log_tail(journal,
 						journal->j_tail_sequence,
-						journal->j_tail,
-						REQ_SYNC);
+						journal->j_tail, 0);
 		mutex_unlock(&journal->j_checkpoint_mutex);
 	} else {
 		jbd2_debug(3, "superblock not updated\n");
@@ -715,6 +714,7 @@ start_journal_io:
 
 			for (i = 0; i < bufs; i++) {
 				struct buffer_head *bh = wbuf[i];
+
 				/*
 				 * Compute checksum.
 				 */
@@ -727,7 +727,8 @@ start_journal_io:
 				clear_buffer_dirty(bh);
 				set_buffer_uptodate(bh);
 				bh->b_end_io = journal_end_buffer_io_sync;
-				submit_bh(REQ_OP_WRITE | REQ_SYNC, bh);
+				submit_bh(REQ_OP_WRITE | JBD2_JOURNAL_REQ_FLAGS,
+					  bh);
 			}
 			cond_resched();
 
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 71b30f6a662d..206cb53ef2b0 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1100,8 +1100,7 @@ int __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block)
 	 * space and if we lose sb update during power failure we'd replay
 	 * old transaction with possibly newly overwritten data.
 	 */
-	ret = jbd2_journal_update_sb_log_tail(journal, tid, block,
-					      REQ_SYNC | REQ_FUA);
+	ret = jbd2_journal_update_sb_log_tail(journal, tid, block, REQ_FUA);
 	if (ret)
 		goto out;
 
@@ -1775,8 +1774,7 @@ static int journal_reset(journal_t *journal)
 		 */
 		jbd2_journal_update_sb_log_tail(journal,
 						journal->j_tail_sequence,
-						journal->j_tail,
-						REQ_SYNC | REQ_FUA);
+						journal->j_tail, REQ_FUA);
 		mutex_unlock(&journal->j_checkpoint_mutex);
 	}
 	return jbd2_journal_start_thread(journal);
@@ -1798,6 +1796,11 @@ static int jbd2_write_superblock(journal_t *journal, blk_opf_t write_flags)
 		return -EIO;
 	}
 
+	/*
+	 * Always set high priority flags to exempt from block layer's
+	 * QOS policies, e.g. writeback throttle.
+	 */
+	write_flags |= JBD2_JOURNAL_REQ_FLAGS;
 	if (!(journal->j_flags & JBD2_BARRIER))
 		write_flags &= ~(REQ_FUA | REQ_PREFLUSH);
 
@@ -2052,7 +2055,7 @@ void jbd2_journal_update_sb_errno(journal_t *journal)
 	jbd2_debug(1, "JBD2: updating superblock error (errno %d)\n", errcode);
 	sb->s_errno    = cpu_to_be32(errcode);
 
-	jbd2_write_superblock(journal, REQ_SYNC | REQ_FUA);
+	jbd2_write_superblock(journal, REQ_FUA);
 }
 EXPORT_SYMBOL(jbd2_journal_update_sb_errno);
 
@@ -2173,8 +2176,7 @@ int jbd2_journal_destroy(journal_t *journal)
 				++journal->j_transaction_sequence;
 			write_unlock(&journal->j_state_lock);
 
-			jbd2_mark_journal_empty(journal,
-					REQ_SYNC | REQ_PREFLUSH | REQ_FUA);
+			jbd2_mark_journal_empty(journal, REQ_PREFLUSH | REQ_FUA);
 			mutex_unlock(&journal->j_checkpoint_mutex);
 		} else
 			err = -EIO;
@@ -2475,7 +2477,7 @@ int jbd2_journal_flush(journal_t *journal, unsigned int flags)
 	 * the magic code for a fully-recovered superblock.  Any future
 	 * commits of data to the journal will restore the current
 	 * s_start value. */
-	jbd2_mark_journal_empty(journal, REQ_SYNC | REQ_FUA);
+	jbd2_mark_journal_empty(journal, REQ_FUA);
 
 	if (flags)
 		err = __jbd2_journal_erase(journal, flags);
@@ -2521,7 +2523,7 @@ int jbd2_journal_wipe(journal_t *journal, int write)
 	if (write) {
 		/* Lock to make assertions happy... */
 		mutex_lock_io(&journal->j_checkpoint_mutex);
-		jbd2_mark_journal_empty(journal, REQ_SYNC | REQ_FUA);
+		jbd2_mark_journal_empty(journal, REQ_FUA);
 		mutex_unlock(&journal->j_checkpoint_mutex);
 	}
 
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 6dcbb4eb80fb..beb30719ee16 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1374,6 +1374,9 @@ JBD2_FEATURE_INCOMPAT_FUNCS(csum2,		CSUM_V2)
 JBD2_FEATURE_INCOMPAT_FUNCS(csum3,		CSUM_V3)
 JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit,	FAST_COMMIT)
 
+/* Journal high priority write IO operation flags */
+#define JBD2_JOURNAL_REQ_FLAGS		(REQ_META | REQ_SYNC | REQ_IDLE)
+
 /*
  * Journal flag definitions
  */
-- 
cgit v1.2.3


From d839a656d0f3caca9f96e9bf912fd394ac6a11bc Mon Sep 17 00:00:00 2001
From: JP Kobryn <inwardvessel@gmail.com>
Date: Fri, 1 Dec 2023 14:53:55 +0900
Subject: kprobes: consistent rcu api usage for kretprobe holder

It seems that the pointer-to-kretprobe "rp" within the kretprobe_holder is
RCU-managed, based on the (non-rethook) implementation of get_kretprobe().
The thought behind this patch is to make use of the RCU API where possible
when accessing this pointer so that the needed barriers are always in place
and to self-document the code.

The __rcu annotation to "rp" allows for sparse RCU checking. Plain writes
done to the "rp" pointer are changed to make use of the RCU macro for
assignment. For the single read, the implementation of get_kretprobe()
is simplified by making use of an RCU macro which accomplishes the same,
but note that the log warning text will be more generic.

I did find that there is a difference in assembly generated between the
usage of the RCU macros vs without. For example, on arm64, when using
rcu_assign_pointer(), the corresponding store instruction is a
store-release (STLR) which has an implicit barrier. When normal assignment
is done, a regular store (STR) is found. In the macro case, this seems to
be a result of rcu_assign_pointer() using smp_store_release() when the
value to write is not NULL.

Link: https://lore.kernel.org/all/20231122132058.3359-1-inwardvessel@gmail.com/

Fixes: d741bf41d7c7 ("kprobes: Remove kretprobe hash")
Cc: stable@vger.kernel.org
Signed-off-by: JP Kobryn <inwardvessel@gmail.com>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
 include/linux/kprobes.h | 7 ++-----
 kernel/kprobes.c        | 4 ++--
 2 files changed, 4 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index ab1da3142b06..64672bace560 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -139,7 +139,7 @@ static inline bool kprobe_ftrace(struct kprobe *p)
  *
  */
 struct kretprobe_holder {
-	struct kretprobe	*rp;
+	struct kretprobe __rcu *rp;
 	struct objpool_head	pool;
 };
 
@@ -245,10 +245,7 @@ unsigned long kretprobe_trampoline_handler(struct pt_regs *regs,
 
 static nokprobe_inline struct kretprobe *get_kretprobe(struct kretprobe_instance *ri)
 {
-	RCU_LOCKDEP_WARN(!rcu_read_lock_any_held(),
-		"Kretprobe is accessed from instance under preemptive context");
-
-	return READ_ONCE(ri->rph->rp);
+	return rcu_dereference_check(ri->rph->rp, rcu_read_lock_any_held());
 }
 
 static nokprobe_inline unsigned long get_kretprobe_retaddr(struct kretprobe_instance *ri)
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 075a632e6c7c..d5a0ee40bf66 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2252,7 +2252,7 @@ int register_kretprobe(struct kretprobe *rp)
 		rp->rph = NULL;
 		return -ENOMEM;
 	}
-	rp->rph->rp = rp;
+	rcu_assign_pointer(rp->rph->rp, rp);
 	rp->nmissed = 0;
 	/* Establish function entry probe point */
 	ret = register_kprobe(&rp->kp);
@@ -2300,7 +2300,7 @@ void unregister_kretprobes(struct kretprobe **rps, int num)
 #ifdef CONFIG_KRETPROBE_ON_RETHOOK
 		rethook_free(rps[i]->rh);
 #else
-		rps[i]->rph->rp = NULL;
+		rcu_assign_pointer(rps[i]->rph->rp, NULL);
 #endif
 	}
 	mutex_unlock(&kprobe_mutex);
-- 
cgit v1.2.3


From a1461f1fd6cfdc4b8917c9d4a91e92605d1f28dc Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Fri, 1 Dec 2023 14:53:56 +0900
Subject: rethook: Use __rcu pointer for rethook::handler

Since the rethook::handler is an RCU-maganged pointer so that it will
notice readers the rethook is stopped (unregistered) or not, it should
be an __rcu pointer and use appropriate functions to be accessed. This
will use appropriate memory barrier when accessing it. OTOH,
rethook::data is never changed, so we don't need to check it in
get_kretprobe().

NOTE: To avoid sparse warning, rethook::handler is defined by a raw
function pointer type with __rcu instead of rethook_handler_t.

Link: https://lore.kernel.org/all/170126066201.398836.837498688669005979.stgit@devnote2/

Fixes: 54ecbe6f1ed5 ("rethook: Add a generic return hook")
Cc: stable@vger.kernel.org
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202311241808.rv9ceuAh-lkp@intel.com/
Tested-by: JP Kobryn <inwardvessel@gmail.com>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
 include/linux/kprobes.h |  6 ++----
 include/linux/rethook.h |  7 ++++++-
 kernel/trace/rethook.c  | 23 ++++++++++++++---------
 3 files changed, 22 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 64672bace560..0ff44d6633e3 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -197,10 +197,8 @@ extern int arch_trampoline_kprobe(struct kprobe *p);
 #ifdef CONFIG_KRETPROBE_ON_RETHOOK
 static nokprobe_inline struct kretprobe *get_kretprobe(struct kretprobe_instance *ri)
 {
-	RCU_LOCKDEP_WARN(!rcu_read_lock_any_held(),
-		"Kretprobe is accessed from instance under preemptive context");
-
-	return (struct kretprobe *)READ_ONCE(ri->node.rethook->data);
+	/* rethook::data is non-changed field, so that you can access it freely. */
+	return (struct kretprobe *)ri->node.rethook->data;
 }
 static nokprobe_inline unsigned long get_kretprobe_retaddr(struct kretprobe_instance *ri)
 {
diff --git a/include/linux/rethook.h b/include/linux/rethook.h
index ce69b2b7bc35..ba60962805f6 100644
--- a/include/linux/rethook.h
+++ b/include/linux/rethook.h
@@ -28,7 +28,12 @@ typedef void (*rethook_handler_t) (struct rethook_node *, void *, unsigned long,
  */
 struct rethook {
 	void			*data;
-	rethook_handler_t	handler;
+	/*
+	 * To avoid sparse warnings, this uses a raw function pointer with
+	 * __rcu, instead of rethook_handler_t. But this must be same as
+	 * rethook_handler_t.
+	 */
+	void (__rcu *handler) (struct rethook_node *, void *, unsigned long, struct pt_regs *);
 	struct objpool_head	pool;
 	struct rcu_head		rcu;
 };
diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c
index 6fd7d4ecbbc6..fa03094e9e69 100644
--- a/kernel/trace/rethook.c
+++ b/kernel/trace/rethook.c
@@ -48,7 +48,7 @@ static void rethook_free_rcu(struct rcu_head *head)
  */
 void rethook_stop(struct rethook *rh)
 {
-	WRITE_ONCE(rh->handler, NULL);
+	rcu_assign_pointer(rh->handler, NULL);
 }
 
 /**
@@ -63,7 +63,7 @@ void rethook_stop(struct rethook *rh)
  */
 void rethook_free(struct rethook *rh)
 {
-	WRITE_ONCE(rh->handler, NULL);
+	rethook_stop(rh);
 
 	call_rcu(&rh->rcu, rethook_free_rcu);
 }
@@ -82,6 +82,12 @@ static int rethook_fini_pool(struct objpool_head *head, void *context)
 	return 0;
 }
 
+static inline rethook_handler_t rethook_get_handler(struct rethook *rh)
+{
+	return (rethook_handler_t)rcu_dereference_check(rh->handler,
+							rcu_read_lock_any_held());
+}
+
 /**
  * rethook_alloc() - Allocate struct rethook.
  * @data: a data to pass the @handler when hooking the return.
@@ -107,7 +113,7 @@ struct rethook *rethook_alloc(void *data, rethook_handler_t handler,
 		return ERR_PTR(-ENOMEM);
 
 	rh->data = data;
-	rh->handler = handler;
+	rcu_assign_pointer(rh->handler, handler);
 
 	/* initialize the objpool for rethook nodes */
 	if (objpool_init(&rh->pool, num, size, GFP_KERNEL, rh,
@@ -135,9 +141,10 @@ static void free_rethook_node_rcu(struct rcu_head *head)
  */
 void rethook_recycle(struct rethook_node *node)
 {
-	lockdep_assert_preemption_disabled();
+	rethook_handler_t handler;
 
-	if (likely(READ_ONCE(node->rethook->handler)))
+	handler = rethook_get_handler(node->rethook);
+	if (likely(handler))
 		objpool_push(node, &node->rethook->pool);
 	else
 		call_rcu(&node->rcu, free_rethook_node_rcu);
@@ -153,9 +160,7 @@ NOKPROBE_SYMBOL(rethook_recycle);
  */
 struct rethook_node *rethook_try_get(struct rethook *rh)
 {
-	rethook_handler_t handler = READ_ONCE(rh->handler);
-
-	lockdep_assert_preemption_disabled();
+	rethook_handler_t handler = rethook_get_handler(rh);
 
 	/* Check whether @rh is going to be freed. */
 	if (unlikely(!handler))
@@ -300,7 +305,7 @@ unsigned long rethook_trampoline_handler(struct pt_regs *regs,
 		rhn = container_of(first, struct rethook_node, llist);
 		if (WARN_ON_ONCE(rhn->frame != frame))
 			break;
-		handler = READ_ONCE(rhn->rethook->handler);
+		handler = rethook_get_handler(rhn->rethook);
 		if (handler)
 			handler(rhn, rhn->rethook->data,
 				correct_ret_addr, regs);
-- 
cgit v1.2.3


From df16c1c51d8166958f533c0c886766f7ee9dd50f Mon Sep 17 00:00:00 2001
From: Andrew Halaney <ahalaney@redhat.com>
Date: Mon, 27 Nov 2023 15:41:10 -0600
Subject: net: phy: mdio_device: Reset device only when necessary

Currently the phy reset sequence is as shown below for a
devicetree described mdio phy on boot:

1. Assert the phy_device's reset as part of registering
2. Deassert the phy_device's reset as part of registering
3. Deassert the phy_device's reset as part of phy_probe
4. Deassert the phy_device's reset as part of phy_hw_init

The extra two deasserts include waiting the deassert delay afterwards,
which is adding unnecessary delay.

This applies to both possible types of resets (reset controller
reference and a reset gpio) that can be used.

Here's some snipped tracing output using the following command line
params "trace_event=gpio:* trace_options=stacktrace" illustrating
the reset handling and where its coming from:

    /* Assert */
       systemd-udevd-283     [002] .....     6.780434: gpio_value: 544 set 0
       systemd-udevd-283     [002] .....     6.783849: <stack trace>
     => gpiod_set_raw_value_commit
     => gpiod_set_value_nocheck
     => gpiod_set_value_cansleep
     => mdio_device_reset
     => mdiobus_register_device
     => phy_device_register
     => fwnode_mdiobus_phy_device_register
     => fwnode_mdiobus_register_phy
     => __of_mdiobus_register
     => stmmac_mdio_register
     => stmmac_dvr_probe
     => stmmac_pltfr_probe
     => devm_stmmac_pltfr_probe
     => qcom_ethqos_probe
     => platform_probe

    /* Deassert */
       systemd-udevd-283     [002] .....     6.802480: gpio_value: 544 set 1
       systemd-udevd-283     [002] .....     6.805886: <stack trace>
     => gpiod_set_raw_value_commit
     => gpiod_set_value_nocheck
     => gpiod_set_value_cansleep
     => mdio_device_reset
     => phy_device_register
     => fwnode_mdiobus_phy_device_register
     => fwnode_mdiobus_register_phy
     => __of_mdiobus_register
     => stmmac_mdio_register
     => stmmac_dvr_probe
     => stmmac_pltfr_probe
     => devm_stmmac_pltfr_probe
     => qcom_ethqos_probe
     => platform_probe

    /* Deassert */
       systemd-udevd-283     [002] .....     6.882601: gpio_value: 544 set 1
       systemd-udevd-283     [002] .....     6.886014: <stack trace>
     => gpiod_set_raw_value_commit
     => gpiod_set_value_nocheck
     => gpiod_set_value_cansleep
     => mdio_device_reset
     => phy_probe
     => really_probe
     => __driver_probe_device
     => driver_probe_device
     => __device_attach_driver
     => bus_for_each_drv
     => __device_attach
     => device_initial_probe
     => bus_probe_device
     => device_add
     => phy_device_register
     => fwnode_mdiobus_phy_device_register
     => fwnode_mdiobus_register_phy
     => __of_mdiobus_register
     => stmmac_mdio_register
     => stmmac_dvr_probe
     => stmmac_pltfr_probe
     => devm_stmmac_pltfr_probe
     => qcom_ethqos_probe
     => platform_probe

    /* Deassert */
      NetworkManager-477     [000] .....     7.023144: gpio_value: 544 set 1
      NetworkManager-477     [000] .....     7.026596: <stack trace>
     => gpiod_set_raw_value_commit
     => gpiod_set_value_nocheck
     => gpiod_set_value_cansleep
     => mdio_device_reset
     => phy_init_hw
     => phy_attach_direct
     => phylink_fwnode_phy_connect
     => __stmmac_open
     => stmmac_open

There's a lot of paths where the device is getting its reset
asserted and deasserted. Let's track the state and only actually
do the assert/deassert when it changes.

Reported-by: Sagar Cheluvegowda <quic_scheluve@quicinc.com>
Signed-off-by: Andrew Halaney <ahalaney@redhat.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/r/20231127-net-phy-reset-once-v2-1-448e8658779e@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/mdio_device.c | 6 ++++++
 drivers/net/phy/phy_device.c  | 1 +
 include/linux/mdio.h          | 1 +
 3 files changed, 8 insertions(+)

(limited to 'include')

diff --git a/drivers/net/phy/mdio_device.c b/drivers/net/phy/mdio_device.c
index 044828d081d2..73f6539b9e50 100644
--- a/drivers/net/phy/mdio_device.c
+++ b/drivers/net/phy/mdio_device.c
@@ -62,6 +62,7 @@ struct mdio_device *mdio_device_create(struct mii_bus *bus, int addr)
 	mdiodev->device_remove = mdio_device_remove;
 	mdiodev->bus = bus;
 	mdiodev->addr = addr;
+	mdiodev->reset_state = -1;
 
 	dev_set_name(&mdiodev->dev, PHY_ID_FMT, bus->id, addr);
 
@@ -122,6 +123,9 @@ void mdio_device_reset(struct mdio_device *mdiodev, int value)
 	if (!mdiodev->reset_gpio && !mdiodev->reset_ctrl)
 		return;
 
+	if (mdiodev->reset_state == value)
+		return;
+
 	if (mdiodev->reset_gpio)
 		gpiod_set_value_cansleep(mdiodev->reset_gpio, value);
 
@@ -135,6 +139,8 @@ void mdio_device_reset(struct mdio_device *mdiodev, int value)
 	d = value ? mdiodev->reset_assert_delay : mdiodev->reset_deassert_delay;
 	if (d)
 		fsleep(d);
+
+	mdiodev->reset_state = value;
 }
 EXPORT_SYMBOL(mdio_device_reset);
 
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 400fb09d9cd6..d8e9335d415c 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -654,6 +654,7 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id,
 	mdiodev->flags = MDIO_DEVICE_FLAG_PHY;
 	mdiodev->device_free = phy_mdio_device_free;
 	mdiodev->device_remove = phy_mdio_device_remove;
+	mdiodev->reset_state = -1;
 
 	dev->speed = SPEED_UNKNOWN;
 	dev->duplex = DUPLEX_UNKNOWN;
diff --git a/include/linux/mdio.h b/include/linux/mdio.h
index 007fd9c3e4b6..79ceee3c8673 100644
--- a/include/linux/mdio.h
+++ b/include/linux/mdio.h
@@ -38,6 +38,7 @@ struct mdio_device {
 	/* Bus address of the MDIO device (0-31) */
 	int addr;
 	int flags;
+	int reset_state;
 	struct gpio_desc *reset_gpio;
 	struct reset_control *reset_ctrl;
 	unsigned int reset_assert_delay;
-- 
cgit v1.2.3


From 7232522e6cafdf466ed7649c14546fd07ccc1978 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Thu, 30 Nov 2023 18:56:18 +0200
Subject: fanotify: store fsid in mark instead of in connector

Some filesystems like fuse and nfs have zero or non-unique fsid.
We would like to avoid reporting ambiguous fsid in events, so we need
to avoid marking objects with same fsid and different sb.

To make this easier to enforce, store the fsid in the marks of the group
instead of in the shared conenctor.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Message-Id: <20231130165619.3386452-2-amir73il@gmail.com>
---
 fs/notify/fanotify/fanotify.c      | 19 ++++----------
 fs/notify/fanotify/fanotify.h      | 10 ++++++++
 fs/notify/fanotify/fanotify_user.c | 18 ++++++++++---
 fs/notify/mark.c                   | 52 ++++++--------------------------------
 include/linux/fsnotify_backend.h   | 13 ++++------
 5 files changed, 42 insertions(+), 70 deletions(-)

(limited to 'include')

diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 9dac7f6e72d2..aff1ab3c32aa 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -838,9 +838,8 @@ out:
 }
 
 /*
- * Get cached fsid of the filesystem containing the object from any connector.
- * All connectors are supposed to have the same fsid, but we do not verify that
- * here.
+ * Get cached fsid of the filesystem containing the object from any mark.
+ * All marks are supposed to have the same fsid, but we do not verify that here.
  */
 static __kernel_fsid_t fanotify_get_fsid(struct fsnotify_iter_info *iter_info)
 {
@@ -849,17 +848,9 @@ static __kernel_fsid_t fanotify_get_fsid(struct fsnotify_iter_info *iter_info)
 	__kernel_fsid_t fsid = {};
 
 	fsnotify_foreach_iter_mark_type(iter_info, mark, type) {
-		struct fsnotify_mark_connector *conn;
-
-		conn = READ_ONCE(mark->connector);
-		/* Mark is just getting destroyed or created? */
-		if (!conn)
-			continue;
-		if (!(conn->flags & FSNOTIFY_CONN_FLAG_HAS_FSID))
+		if (!(mark->flags & FSNOTIFY_MARK_FLAG_HAS_FSID))
 			continue;
-		/* Pairs with smp_wmb() in fsnotify_add_mark_list() */
-		smp_rmb();
-		fsid = conn->fsid;
+		fsid = FANOTIFY_MARK(mark)->fsid;
 		if (WARN_ON_ONCE(!fsid.val[0] && !fsid.val[1]))
 			continue;
 		return fsid;
@@ -1068,7 +1059,7 @@ static void fanotify_freeing_mark(struct fsnotify_mark *mark,
 
 static void fanotify_free_mark(struct fsnotify_mark *fsn_mark)
 {
-	kmem_cache_free(fanotify_mark_cache, fsn_mark);
+	kmem_cache_free(fanotify_mark_cache, FANOTIFY_MARK(fsn_mark));
 }
 
 const struct fsnotify_ops fanotify_fsnotify_ops = {
diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h
index 6936671e148d..f3b9ef60f0c0 100644
--- a/fs/notify/fanotify/fanotify.h
+++ b/fs/notify/fanotify/fanotify.h
@@ -489,6 +489,16 @@ static inline unsigned int fanotify_event_hash_bucket(
 	return event->hash & FANOTIFY_HTABLE_MASK;
 }
 
+struct fanotify_mark {
+	struct fsnotify_mark fsn_mark;
+	__kernel_fsid_t fsid;
+};
+
+static inline struct fanotify_mark *FANOTIFY_MARK(struct fsnotify_mark *mark)
+{
+	return container_of(mark, struct fanotify_mark, fsn_mark);
+}
+
 static inline unsigned int fanotify_mark_user_flags(struct fsnotify_mark *mark)
 {
 	unsigned int mflags = 0;
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 4d765c72496f..e3d836d4d156 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -1199,6 +1199,7 @@ static struct fsnotify_mark *fanotify_add_new_mark(struct fsnotify_group *group,
 						   __kernel_fsid_t *fsid)
 {
 	struct ucounts *ucounts = group->fanotify_data.ucounts;
+	struct fanotify_mark *fan_mark;
 	struct fsnotify_mark *mark;
 	int ret;
 
@@ -1211,17 +1212,26 @@ static struct fsnotify_mark *fanotify_add_new_mark(struct fsnotify_group *group,
 	    !inc_ucount(ucounts->ns, ucounts->uid, UCOUNT_FANOTIFY_MARKS))
 		return ERR_PTR(-ENOSPC);
 
-	mark = kmem_cache_alloc(fanotify_mark_cache, GFP_KERNEL);
-	if (!mark) {
+	fan_mark = kmem_cache_alloc(fanotify_mark_cache, GFP_KERNEL);
+	if (!fan_mark) {
 		ret = -ENOMEM;
 		goto out_dec_ucounts;
 	}
 
+	mark = &fan_mark->fsn_mark;
 	fsnotify_init_mark(mark, group);
 	if (fan_flags & FAN_MARK_EVICTABLE)
 		mark->flags |= FSNOTIFY_MARK_FLAG_NO_IREF;
 
-	ret = fsnotify_add_mark_locked(mark, connp, obj_type, 0, fsid);
+	/* Cache fsid of filesystem containing the marked object */
+	if (fsid) {
+		fan_mark->fsid = *fsid;
+		mark->flags |= FSNOTIFY_MARK_FLAG_HAS_FSID;
+	} else {
+		fan_mark->fsid.val[0] = fan_mark->fsid.val[1] = 0;
+	}
+
+	ret = fsnotify_add_mark_locked(mark, connp, obj_type, 0);
 	if (ret) {
 		fsnotify_put_mark(mark);
 		goto out_dec_ucounts;
@@ -1935,7 +1945,7 @@ static int __init fanotify_user_setup(void)
 	BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 12);
 	BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 11);
 
-	fanotify_mark_cache = KMEM_CACHE(fsnotify_mark,
+	fanotify_mark_cache = KMEM_CACHE(fanotify_mark,
 					 SLAB_PANIC|SLAB_ACCOUNT);
 	fanotify_fid_event_cachep = KMEM_CACHE(fanotify_fid_event,
 					       SLAB_PANIC);
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index c74ef947447d..d6944ff86ffa 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -537,8 +537,7 @@ int fsnotify_compare_groups(struct fsnotify_group *a, struct fsnotify_group *b)
 }
 
 static int fsnotify_attach_connector_to_object(fsnotify_connp_t *connp,
-					       unsigned int obj_type,
-					       __kernel_fsid_t *fsid)
+					       unsigned int obj_type)
 {
 	struct fsnotify_mark_connector *conn;
 
@@ -550,14 +549,7 @@ static int fsnotify_attach_connector_to_object(fsnotify_connp_t *connp,
 	conn->flags = 0;
 	conn->type = obj_type;
 	conn->obj = connp;
-	/* Cache fsid of filesystem containing the object */
-	if (fsid) {
-		conn->fsid = *fsid;
-		conn->flags = FSNOTIFY_CONN_FLAG_HAS_FSID;
-	} else {
-		conn->fsid.val[0] = conn->fsid.val[1] = 0;
-		conn->flags = 0;
-	}
+	conn->flags = 0;
 	fsnotify_get_sb_connectors(conn);
 
 	/*
@@ -608,8 +600,7 @@ out:
  */
 static int fsnotify_add_mark_list(struct fsnotify_mark *mark,
 				  fsnotify_connp_t *connp,
-				  unsigned int obj_type,
-				  int add_flags, __kernel_fsid_t *fsid)
+				  unsigned int obj_type, int add_flags)
 {
 	struct fsnotify_mark *lmark, *last = NULL;
 	struct fsnotify_mark_connector *conn;
@@ -619,41 +610,15 @@ static int fsnotify_add_mark_list(struct fsnotify_mark *mark,
 	if (WARN_ON(!fsnotify_valid_obj_type(obj_type)))
 		return -EINVAL;
 
-	/* Backend is expected to check for zero fsid (e.g. tmpfs) */
-	if (fsid && WARN_ON_ONCE(!fsid->val[0] && !fsid->val[1]))
-		return -ENODEV;
-
 restart:
 	spin_lock(&mark->lock);
 	conn = fsnotify_grab_connector(connp);
 	if (!conn) {
 		spin_unlock(&mark->lock);
-		err = fsnotify_attach_connector_to_object(connp, obj_type,
-							  fsid);
+		err = fsnotify_attach_connector_to_object(connp, obj_type);
 		if (err)
 			return err;
 		goto restart;
-	} else if (fsid && !(conn->flags & FSNOTIFY_CONN_FLAG_HAS_FSID)) {
-		conn->fsid = *fsid;
-		/* Pairs with smp_rmb() in fanotify_get_fsid() */
-		smp_wmb();
-		conn->flags |= FSNOTIFY_CONN_FLAG_HAS_FSID;
-	} else if (fsid && (conn->flags & FSNOTIFY_CONN_FLAG_HAS_FSID) &&
-		   (fsid->val[0] != conn->fsid.val[0] ||
-		    fsid->val[1] != conn->fsid.val[1])) {
-		/*
-		 * Backend is expected to check for non uniform fsid
-		 * (e.g. btrfs), but maybe we missed something?
-		 * Only allow setting conn->fsid once to non zero fsid.
-		 * inotify and non-fid fanotify groups do not set nor test
-		 * conn->fsid.
-		 */
-		pr_warn_ratelimited("%s: fsid mismatch on object of type %u: "
-				    "%x.%x != %x.%x\n", __func__, conn->type,
-				    fsid->val[0], fsid->val[1],
-				    conn->fsid.val[0], conn->fsid.val[1]);
-		err = -EXDEV;
-		goto out_err;
 	}
 
 	/* is mark the first mark? */
@@ -703,7 +668,7 @@ out_err:
  */
 int fsnotify_add_mark_locked(struct fsnotify_mark *mark,
 			     fsnotify_connp_t *connp, unsigned int obj_type,
-			     int add_flags, __kernel_fsid_t *fsid)
+			     int add_flags)
 {
 	struct fsnotify_group *group = mark->group;
 	int ret = 0;
@@ -723,7 +688,7 @@ int fsnotify_add_mark_locked(struct fsnotify_mark *mark,
 	fsnotify_get_mark(mark); /* for g_list */
 	spin_unlock(&mark->lock);
 
-	ret = fsnotify_add_mark_list(mark, connp, obj_type, add_flags, fsid);
+	ret = fsnotify_add_mark_list(mark, connp, obj_type, add_flags);
 	if (ret)
 		goto err;
 
@@ -742,14 +707,13 @@ err:
 }
 
 int fsnotify_add_mark(struct fsnotify_mark *mark, fsnotify_connp_t *connp,
-		      unsigned int obj_type, int add_flags,
-		      __kernel_fsid_t *fsid)
+		      unsigned int obj_type, int add_flags)
 {
 	int ret;
 	struct fsnotify_group *group = mark->group;
 
 	fsnotify_group_lock(group);
-	ret = fsnotify_add_mark_locked(mark, connp, obj_type, add_flags, fsid);
+	ret = fsnotify_add_mark_locked(mark, connp, obj_type, add_flags);
 	fsnotify_group_unlock(group);
 	return ret;
 }
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index c0892d75ce33..a80b525ca653 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -472,10 +472,8 @@ typedef struct fsnotify_mark_connector __rcu *fsnotify_connp_t;
 struct fsnotify_mark_connector {
 	spinlock_t lock;
 	unsigned short type;	/* Type of object [lock] */
-#define FSNOTIFY_CONN_FLAG_HAS_FSID	0x01
 #define FSNOTIFY_CONN_FLAG_HAS_IREF	0x02
 	unsigned short flags;	/* flags [lock] */
-	__kernel_fsid_t fsid;	/* fsid of filesystem containing object */
 	union {
 		/* Object pointer [lock] */
 		fsnotify_connp_t *obj;
@@ -530,6 +528,7 @@ struct fsnotify_mark {
 #define FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY	0x0100
 #define FSNOTIFY_MARK_FLAG_NO_IREF		0x0200
 #define FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS	0x0400
+#define FSNOTIFY_MARK_FLAG_HAS_FSID		0x0800
 	unsigned int flags;		/* flags [mark->lock] */
 };
 
@@ -763,11 +762,10 @@ extern struct fsnotify_mark *fsnotify_find_mark(fsnotify_connp_t *connp,
 /* attach the mark to the object */
 extern int fsnotify_add_mark(struct fsnotify_mark *mark,
 			     fsnotify_connp_t *connp, unsigned int obj_type,
-			     int add_flags, __kernel_fsid_t *fsid);
+			     int add_flags);
 extern int fsnotify_add_mark_locked(struct fsnotify_mark *mark,
 				    fsnotify_connp_t *connp,
-				    unsigned int obj_type, int add_flags,
-				    __kernel_fsid_t *fsid);
+				    unsigned int obj_type, int add_flags);
 
 /* attach the mark to the inode */
 static inline int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
@@ -775,15 +773,14 @@ static inline int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
 					  int add_flags)
 {
 	return fsnotify_add_mark(mark, &inode->i_fsnotify_marks,
-				 FSNOTIFY_OBJ_TYPE_INODE, add_flags, NULL);
+				 FSNOTIFY_OBJ_TYPE_INODE, add_flags);
 }
 static inline int fsnotify_add_inode_mark_locked(struct fsnotify_mark *mark,
 						 struct inode *inode,
 						 int add_flags)
 {
 	return fsnotify_add_mark_locked(mark, &inode->i_fsnotify_marks,
-					FSNOTIFY_OBJ_TYPE_INODE, add_flags,
-					NULL);
+					FSNOTIFY_OBJ_TYPE_INODE, add_flags);
 }
 
 /* given a group and a mark, flag mark to be freed when all references are dropped */
-- 
cgit v1.2.3


From 30ad1938326bf9303ca38090339d948975a626f5 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Thu, 30 Nov 2023 18:56:19 +0200
Subject: fanotify: allow "weak" fsid when watching a single filesystem

So far, fanotify returns -ENODEV or -EXDEV when trying to set a mark
on a filesystem with a "weak" fsid, namely, zero fsid (e.g. fuse), or
non-uniform fsid (e.g. btrfs non-root subvol).

When group is watching inodes all from the same filesystem (or subvol),
allow adding inode marks with "weak" fsid, because there is no ambiguity
regarding which filesystem reports the event.

The first mark added to a group determines if this group is single or
multi filesystem, depending on the fsid at the path of the added mark.

If the first mark added has a "strong" fsid, marks with "weak" fsid
cannot be added and vice versa.

If the first mark added has a "weak" fsid, following marks must have
the same "weak" fsid and the same sb as the first mark.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Message-Id: <20231130165619.3386452-3-amir73il@gmail.com>
---
 fs/notify/fanotify/fanotify.c      |  15 +----
 fs/notify/fanotify/fanotify.h      |   6 ++
 fs/notify/fanotify/fanotify_user.c | 112 ++++++++++++++++++++++++++++++-------
 include/linux/fsnotify_backend.h   |   1 +
 4 files changed, 101 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index aff1ab3c32aa..1e4def21811e 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -29,12 +29,6 @@ static unsigned int fanotify_hash_path(const struct path *path)
 		hash_ptr(path->mnt, FANOTIFY_EVENT_HASH_BITS);
 }
 
-static inline bool fanotify_fsid_equal(__kernel_fsid_t *fsid1,
-				       __kernel_fsid_t *fsid2)
-{
-	return fsid1->val[0] == fsid2->val[0] && fsid1->val[1] == fsid2->val[1];
-}
-
 static unsigned int fanotify_hash_fsid(__kernel_fsid_t *fsid)
 {
 	return hash_32(fsid->val[0], FANOTIFY_EVENT_HASH_BITS) ^
@@ -851,7 +845,8 @@ static __kernel_fsid_t fanotify_get_fsid(struct fsnotify_iter_info *iter_info)
 		if (!(mark->flags & FSNOTIFY_MARK_FLAG_HAS_FSID))
 			continue;
 		fsid = FANOTIFY_MARK(mark)->fsid;
-		if (WARN_ON_ONCE(!fsid.val[0] && !fsid.val[1]))
+		if (!(mark->flags & FSNOTIFY_MARK_FLAG_WEAK_FSID) &&
+		    WARN_ON_ONCE(!fsid.val[0] && !fsid.val[1]))
 			continue;
 		return fsid;
 	}
@@ -933,12 +928,8 @@ static int fanotify_handle_event(struct fsnotify_group *group, u32 mask,
 			return 0;
 	}
 
-	if (FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS)) {
+	if (FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS))
 		fsid = fanotify_get_fsid(iter_info);
-		/* Racing with mark destruction or creation? */
-		if (!fsid.val[0] && !fsid.val[1])
-			return 0;
-	}
 
 	event = fanotify_alloc_event(group, mask, data, data_type, dir,
 				     file_name, &fsid, match_mask);
diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h
index f3b9ef60f0c0..e5ab33cae6a7 100644
--- a/fs/notify/fanotify/fanotify.h
+++ b/fs/notify/fanotify/fanotify.h
@@ -499,6 +499,12 @@ static inline struct fanotify_mark *FANOTIFY_MARK(struct fsnotify_mark *mark)
 	return container_of(mark, struct fanotify_mark, fsn_mark);
 }
 
+static inline bool fanotify_fsid_equal(__kernel_fsid_t *fsid1,
+				       __kernel_fsid_t *fsid2)
+{
+	return fsid1->val[0] == fsid2->val[0] && fsid1->val[1] == fsid2->val[1];
+}
+
 static inline unsigned int fanotify_mark_user_flags(struct fsnotify_mark *mark)
 {
 	unsigned int mflags = 0;
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index e3d836d4d156..f83e7cc5ccf2 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -23,7 +23,7 @@
 
 #include <asm/ioctls.h>
 
-#include "../../mount.h"
+#include "../fsnotify.h"
 #include "../fdinfo.h"
 #include "fanotify.h"
 
@@ -1192,11 +1192,68 @@ static bool fanotify_mark_add_to_mask(struct fsnotify_mark *fsn_mark,
 	return recalc;
 }
 
+struct fan_fsid {
+	struct super_block *sb;
+	__kernel_fsid_t id;
+	bool weak;
+};
+
+static int fanotify_set_mark_fsid(struct fsnotify_group *group,
+				  struct fsnotify_mark *mark,
+				  struct fan_fsid *fsid)
+{
+	struct fsnotify_mark_connector *conn;
+	struct fsnotify_mark *old;
+	struct super_block *old_sb = NULL;
+
+	FANOTIFY_MARK(mark)->fsid = fsid->id;
+	mark->flags |= FSNOTIFY_MARK_FLAG_HAS_FSID;
+	if (fsid->weak)
+		mark->flags |= FSNOTIFY_MARK_FLAG_WEAK_FSID;
+
+	/* First mark added will determine if group is single or multi fsid */
+	if (list_empty(&group->marks_list))
+		return 0;
+
+	/* Find sb of an existing mark */
+	list_for_each_entry(old, &group->marks_list, g_list) {
+		conn = READ_ONCE(old->connector);
+		if (!conn)
+			continue;
+		old_sb = fsnotify_connector_sb(conn);
+		if (old_sb)
+			break;
+	}
+
+	/* Only detached marks left? */
+	if (!old_sb)
+		return 0;
+
+	/* Do not allow mixing of marks with weak and strong fsid */
+	if ((mark->flags ^ old->flags) & FSNOTIFY_MARK_FLAG_WEAK_FSID)
+		return -EXDEV;
+
+	/* Allow mixing of marks with strong fsid from different fs */
+	if (!fsid->weak)
+		return 0;
+
+	/* Do not allow mixing marks with weak fsid from different fs */
+	if (old_sb != fsid->sb)
+		return -EXDEV;
+
+	/* Do not allow mixing marks from different btrfs sub-volumes */
+	if (!fanotify_fsid_equal(&FANOTIFY_MARK(old)->fsid,
+				 &FANOTIFY_MARK(mark)->fsid))
+		return -EXDEV;
+
+	return 0;
+}
+
 static struct fsnotify_mark *fanotify_add_new_mark(struct fsnotify_group *group,
 						   fsnotify_connp_t *connp,
 						   unsigned int obj_type,
 						   unsigned int fan_flags,
-						   __kernel_fsid_t *fsid)
+						   struct fan_fsid *fsid)
 {
 	struct ucounts *ucounts = group->fanotify_data.ucounts;
 	struct fanotify_mark *fan_mark;
@@ -1225,20 +1282,21 @@ static struct fsnotify_mark *fanotify_add_new_mark(struct fsnotify_group *group,
 
 	/* Cache fsid of filesystem containing the marked object */
 	if (fsid) {
-		fan_mark->fsid = *fsid;
-		mark->flags |= FSNOTIFY_MARK_FLAG_HAS_FSID;
+		ret = fanotify_set_mark_fsid(group, mark, fsid);
+		if (ret)
+			goto out_put_mark;
 	} else {
 		fan_mark->fsid.val[0] = fan_mark->fsid.val[1] = 0;
 	}
 
 	ret = fsnotify_add_mark_locked(mark, connp, obj_type, 0);
-	if (ret) {
-		fsnotify_put_mark(mark);
-		goto out_dec_ucounts;
-	}
+	if (ret)
+		goto out_put_mark;
 
 	return mark;
 
+out_put_mark:
+	fsnotify_put_mark(mark);
 out_dec_ucounts:
 	if (!FAN_GROUP_FLAG(group, FAN_UNLIMITED_MARKS))
 		dec_ucount(ucounts, UCOUNT_FANOTIFY_MARKS);
@@ -1289,7 +1347,7 @@ static int fanotify_may_update_existing_mark(struct fsnotify_mark *fsn_mark,
 static int fanotify_add_mark(struct fsnotify_group *group,
 			     fsnotify_connp_t *connp, unsigned int obj_type,
 			     __u32 mask, unsigned int fan_flags,
-			     __kernel_fsid_t *fsid)
+			     struct fan_fsid *fsid)
 {
 	struct fsnotify_mark *fsn_mark;
 	bool recalc;
@@ -1337,7 +1395,7 @@ out:
 
 static int fanotify_add_vfsmount_mark(struct fsnotify_group *group,
 				      struct vfsmount *mnt, __u32 mask,
-				      unsigned int flags, __kernel_fsid_t *fsid)
+				      unsigned int flags, struct fan_fsid *fsid)
 {
 	return fanotify_add_mark(group, &real_mount(mnt)->mnt_fsnotify_marks,
 				 FSNOTIFY_OBJ_TYPE_VFSMOUNT, mask, flags, fsid);
@@ -1345,7 +1403,7 @@ static int fanotify_add_vfsmount_mark(struct fsnotify_group *group,
 
 static int fanotify_add_sb_mark(struct fsnotify_group *group,
 				struct super_block *sb, __u32 mask,
-				unsigned int flags, __kernel_fsid_t *fsid)
+				unsigned int flags, struct fan_fsid *fsid)
 {
 	return fanotify_add_mark(group, &sb->s_fsnotify_marks,
 				 FSNOTIFY_OBJ_TYPE_SB, mask, flags, fsid);
@@ -1353,7 +1411,7 @@ static int fanotify_add_sb_mark(struct fsnotify_group *group,
 
 static int fanotify_add_inode_mark(struct fsnotify_group *group,
 				   struct inode *inode, __u32 mask,
-				   unsigned int flags, __kernel_fsid_t *fsid)
+				   unsigned int flags, struct fan_fsid *fsid)
 {
 	pr_debug("%s: group=%p inode=%p\n", __func__, group, inode);
 
@@ -1564,20 +1622,25 @@ out_destroy_group:
 	return fd;
 }
 
-static int fanotify_test_fsid(struct dentry *dentry, __kernel_fsid_t *fsid)
+static int fanotify_test_fsid(struct dentry *dentry, unsigned int flags,
+			      struct fan_fsid *fsid)
 {
+	unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS;
 	__kernel_fsid_t root_fsid;
 	int err;
 
 	/*
 	 * Make sure dentry is not of a filesystem with zero fsid (e.g. fuse).
 	 */
-	err = vfs_get_fsid(dentry, fsid);
+	err = vfs_get_fsid(dentry, &fsid->id);
 	if (err)
 		return err;
 
-	if (!fsid->val[0] && !fsid->val[1])
-		return -ENODEV;
+	fsid->sb = dentry->d_sb;
+	if (!fsid->id.val[0] && !fsid->id.val[1]) {
+		err = -ENODEV;
+		goto weak;
+	}
 
 	/*
 	 * Make sure dentry is not of a filesystem subvolume (e.g. btrfs)
@@ -1587,11 +1650,18 @@ static int fanotify_test_fsid(struct dentry *dentry, __kernel_fsid_t *fsid)
 	if (err)
 		return err;
 
-	if (root_fsid.val[0] != fsid->val[0] ||
-	    root_fsid.val[1] != fsid->val[1])
-		return -EXDEV;
+	if (!fanotify_fsid_equal(&root_fsid, &fsid->id)) {
+		err = -EXDEV;
+		goto weak;
+	}
 
+	fsid->weak = false;
 	return 0;
+
+weak:
+	/* Allow weak fsid when marking inodes */
+	fsid->weak = true;
+	return (mark_type == FAN_MARK_INODE) ? 0 : err;
 }
 
 /* Check if filesystem can encode a unique fid */
@@ -1675,7 +1745,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
 	struct fsnotify_group *group;
 	struct fd f;
 	struct path path;
-	__kernel_fsid_t __fsid, *fsid = NULL;
+	struct fan_fsid __fsid, *fsid = NULL;
 	u32 valid_mask = FANOTIFY_EVENTS | FANOTIFY_EVENT_FLAGS;
 	unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS;
 	unsigned int mark_cmd = flags & FANOTIFY_MARK_CMD_BITS;
@@ -1827,7 +1897,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
 	}
 
 	if (fid_mode) {
-		ret = fanotify_test_fsid(path.dentry, &__fsid);
+		ret = fanotify_test_fsid(path.dentry, flags, &__fsid);
 		if (ret)
 			goto path_put_and_out;
 
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index a80b525ca653..7f63be5ca0f1 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -529,6 +529,7 @@ struct fsnotify_mark {
 #define FSNOTIFY_MARK_FLAG_NO_IREF		0x0200
 #define FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS	0x0400
 #define FSNOTIFY_MARK_FLAG_HAS_FSID		0x0800
+#define FSNOTIFY_MARK_FLAG_WEAK_FSID		0x1000
 	unsigned int flags;		/* flags [mark->lock] */
 };
 
-- 
cgit v1.2.3


From c66272a4c9932d6c585eef99039747617d48d662 Mon Sep 17 00:00:00 2001
From: Weili Qian <qianweili@huawei.com>
Date: Sat, 25 Nov 2023 19:50:10 +0800
Subject: crypto: hisilicon/qm - simplify the status of qm

The 'QM_INIT' and 'QM_CLOSE' status of qm and 'QP_INIT'
and 'QP_CLOSE' status of queue are not actually used. Currently,
driver only needs to switch status when the device or queue
is enabled or stopped, Therefore, remove unneeded status to
simplify driver. In addition, rename'QM_START to'QM_WORK' for
ease to understand.

Signed-off-by: Weili Qian <qianweili@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 Documentation/ABI/testing/debugfs-hisi-hpre |   2 +-
 Documentation/ABI/testing/debugfs-hisi-sec  |   2 +-
 Documentation/ABI/testing/debugfs-hisi-zip  |   2 +-
 drivers/crypto/hisilicon/debugfs.c          |   4 +
 drivers/crypto/hisilicon/qm.c               | 130 ++++------------------------
 drivers/crypto/hisilicon/qm_common.h        |   4 -
 include/linux/hisi_acc_qm.h                 |   8 +-
 7 files changed, 25 insertions(+), 127 deletions(-)

(limited to 'include')

diff --git a/Documentation/ABI/testing/debugfs-hisi-hpre b/Documentation/ABI/testing/debugfs-hisi-hpre
index 82abf92df429..8e8de49c5cc6 100644
--- a/Documentation/ABI/testing/debugfs-hisi-hpre
+++ b/Documentation/ABI/testing/debugfs-hisi-hpre
@@ -101,7 +101,7 @@ What:		/sys/kernel/debug/hisi_hpre/<bdf>/qm/status
 Date:		Apr 2020
 Contact:	linux-crypto@vger.kernel.org
 Description:	Dump the status of the QM.
-		Four states: initiated, started, stopped and closed.
+		Two states: work, stop.
 		Available for both PF and VF, and take no other effect on HPRE.
 
 What:		/sys/kernel/debug/hisi_hpre/<bdf>/qm/diff_regs
diff --git a/Documentation/ABI/testing/debugfs-hisi-sec b/Documentation/ABI/testing/debugfs-hisi-sec
index 93c530d1bf0f..deeefe2c735e 100644
--- a/Documentation/ABI/testing/debugfs-hisi-sec
+++ b/Documentation/ABI/testing/debugfs-hisi-sec
@@ -81,7 +81,7 @@ What:		/sys/kernel/debug/hisi_sec2/<bdf>/qm/status
 Date:		Apr 2020
 Contact:	linux-crypto@vger.kernel.org
 Description:	Dump the status of the QM.
-		Four states: initiated, started, stopped and closed.
+		Two states: work, stop.
 		Available for both PF and VF, and take no other effect on SEC.
 
 What:		/sys/kernel/debug/hisi_sec2/<bdf>/qm/diff_regs
diff --git a/Documentation/ABI/testing/debugfs-hisi-zip b/Documentation/ABI/testing/debugfs-hisi-zip
index fd3f314cf8d1..593714afaed2 100644
--- a/Documentation/ABI/testing/debugfs-hisi-zip
+++ b/Documentation/ABI/testing/debugfs-hisi-zip
@@ -94,7 +94,7 @@ What:		/sys/kernel/debug/hisi_zip/<bdf>/qm/status
 Date:		Apr 2020
 Contact:	linux-crypto@vger.kernel.org
 Description:	Dump the status of the QM.
-		Four states: initiated, started, stopped and closed.
+		Two states: work, stop.
 		Available for both PF and VF, and take no other effect on ZIP.
 
 What:		/sys/kernel/debug/hisi_zip/<bdf>/qm/diff_regs
diff --git a/drivers/crypto/hisilicon/debugfs.c b/drivers/crypto/hisilicon/debugfs.c
index 415139b4abc1..80ed4b2d209c 100644
--- a/drivers/crypto/hisilicon/debugfs.c
+++ b/drivers/crypto/hisilicon/debugfs.c
@@ -31,6 +31,10 @@ static const char * const qm_debug_file_name[] = {
 	[CLEAR_ENABLE] = "clear_enable",
 };
 
+static const char * const qm_s[] = {
+	"work", "stop",
+};
+
 struct qm_dfx_item {
 	const char *name;
 	u32 offset;
diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c
index 4d91a249be74..7d22412774ba 100644
--- a/drivers/crypto/hisilicon/qm.c
+++ b/drivers/crypto/hisilicon/qm.c
@@ -402,10 +402,6 @@ static const char * const qm_fifo_overflow[] = {
 	"cq", "eq", "aeq",
 };
 
-static const char * const qp_s[] = {
-	"none", "init", "start", "stop", "close",
-};
-
 struct qm_typical_qos_table {
 	u32 start;
 	u32 end;
@@ -433,85 +429,6 @@ static struct qm_typical_qos_table shaper_cbs_s[] = {
 
 static void qm_irqs_unregister(struct hisi_qm *qm);
 
-static bool qm_avail_state(struct hisi_qm *qm, enum qm_state new)
-{
-	enum qm_state curr = atomic_read(&qm->status.flags);
-	bool avail = false;
-
-	switch (curr) {
-	case QM_INIT:
-		if (new == QM_START || new == QM_CLOSE)
-			avail = true;
-		break;
-	case QM_START:
-		if (new == QM_STOP)
-			avail = true;
-		break;
-	case QM_STOP:
-		if (new == QM_CLOSE || new == QM_START)
-			avail = true;
-		break;
-	default:
-		break;
-	}
-
-	dev_dbg(&qm->pdev->dev, "change qm state from %s to %s\n",
-		qm_s[curr], qm_s[new]);
-
-	if (!avail)
-		dev_warn(&qm->pdev->dev, "Can not change qm state from %s to %s\n",
-			 qm_s[curr], qm_s[new]);
-
-	return avail;
-}
-
-static bool qm_qp_avail_state(struct hisi_qm *qm, struct hisi_qp *qp,
-			      enum qp_state new)
-{
-	enum qm_state qm_curr = atomic_read(&qm->status.flags);
-	enum qp_state qp_curr = 0;
-	bool avail = false;
-
-	if (qp)
-		qp_curr = atomic_read(&qp->qp_status.flags);
-
-	switch (new) {
-	case QP_INIT:
-		if (qm_curr == QM_START || qm_curr == QM_INIT)
-			avail = true;
-		break;
-	case QP_START:
-		if ((qm_curr == QM_START && qp_curr == QP_INIT) ||
-		    (qm_curr == QM_START && qp_curr == QP_STOP))
-			avail = true;
-		break;
-	case QP_STOP:
-		if ((qm_curr == QM_START && qp_curr == QP_START) ||
-		    (qp_curr == QP_INIT))
-			avail = true;
-		break;
-	case QP_CLOSE:
-		if ((qm_curr == QM_START && qp_curr == QP_INIT) ||
-		    (qm_curr == QM_START && qp_curr == QP_STOP) ||
-		    (qm_curr == QM_STOP && qp_curr == QP_STOP)  ||
-		    (qm_curr == QM_STOP && qp_curr == QP_INIT))
-			avail = true;
-		break;
-	default:
-		break;
-	}
-
-	dev_dbg(&qm->pdev->dev, "change qp state from %s to %s in QM %s\n",
-		qp_s[qp_curr], qp_s[new], qm_s[qm_curr]);
-
-	if (!avail)
-		dev_warn(&qm->pdev->dev,
-			 "Can not change qp state from %s to %s in QM %s\n",
-			 qp_s[qp_curr], qp_s[new], qm_s[qm_curr]);
-
-	return avail;
-}
-
 static u32 qm_get_hw_error_status(struct hisi_qm *qm)
 {
 	return readl(qm->io_base + QM_ABNORMAL_INT_STATUS);
@@ -1853,8 +1770,10 @@ static struct hisi_qp *qm_create_qp_nolock(struct hisi_qm *qm, u8 alg_type)
 	struct hisi_qp *qp;
 	int qp_id;
 
-	if (!qm_qp_avail_state(qm, NULL, QP_INIT))
+	if (atomic_read(&qm->status.flags) == QM_STOP) {
+		dev_info_ratelimited(dev, "failed to create qp as qm is stop!\n");
 		return ERR_PTR(-EPERM);
+	}
 
 	if (qm->qp_in_used == qm->qp_num) {
 		dev_info_ratelimited(dev, "All %u queues of QM are busy!\n",
@@ -1881,7 +1800,6 @@ static struct hisi_qp *qm_create_qp_nolock(struct hisi_qm *qm, u8 alg_type)
 	qp->alg_type = alg_type;
 	qp->is_in_kernel = true;
 	qm->qp_in_used++;
-	atomic_set(&qp->qp_status.flags, QP_INIT);
 
 	return qp;
 }
@@ -1924,11 +1842,6 @@ static void hisi_qm_release_qp(struct hisi_qp *qp)
 
 	down_write(&qm->qps_lock);
 
-	if (!qm_qp_avail_state(qm, qp, QP_CLOSE)) {
-		up_write(&qm->qps_lock);
-		return;
-	}
-
 	qm->qp_in_used--;
 	idr_remove(&qm->qp_idr, qp->qp_id);
 
@@ -2008,8 +1921,10 @@ static int qm_start_qp_nolock(struct hisi_qp *qp, unsigned long arg)
 	u32 pasid = arg;
 	int ret;
 
-	if (!qm_qp_avail_state(qm, qp, QP_START))
+	if (atomic_read(&qm->status.flags) == QM_STOP) {
+		dev_info_ratelimited(dev, "failed to start qp as qm is stop!\n");
 		return -EPERM;
+	}
 
 	ret = qm_qp_ctx_cfg(qp, qp_id, pasid);
 	if (ret)
@@ -2131,21 +2046,17 @@ static int qm_stop_qp_nolock(struct hisi_qp *qp)
 	 * is_resetting flag should be set negative so that this qp will not
 	 * be restarted after reset.
 	 */
-	if (atomic_read(&qp->qp_status.flags) == QP_STOP) {
+	if (atomic_read(&qp->qp_status.flags) != QP_START) {
 		qp->is_resetting = false;
 		return 0;
 	}
 
-	if (!qm_qp_avail_state(qp->qm, qp, QP_STOP))
-		return -EPERM;
-
 	atomic_set(&qp->qp_status.flags, QP_STOP);
 
 	ret = qm_drain_qp(qp);
 	if (ret)
 		dev_err(dev, "Failed to drain out data for stopping!\n");
 
-
 	flush_workqueue(qp->qm->wq);
 	if (unlikely(qp->is_resetting && atomic_read(&qp->qp_status.used)))
 		qp_stop_fail_cb(qp);
@@ -2865,13 +2776,8 @@ void hisi_qm_uninit(struct hisi_qm *qm)
 {
 	qm_cmd_uninit(qm);
 	hisi_qm_unint_work(qm);
-	down_write(&qm->qps_lock);
-
-	if (!qm_avail_state(qm, QM_CLOSE)) {
-		up_write(&qm->qps_lock);
-		return;
-	}
 
+	down_write(&qm->qps_lock);
 	hisi_qm_memory_uninit(qm);
 	hisi_qm_set_state(qm, QM_NOT_READY);
 	up_write(&qm->qps_lock);
@@ -3045,11 +2951,6 @@ int hisi_qm_start(struct hisi_qm *qm)
 
 	down_write(&qm->qps_lock);
 
-	if (!qm_avail_state(qm, QM_START)) {
-		up_write(&qm->qps_lock);
-		return -EPERM;
-	}
-
 	dev_dbg(dev, "qm start with %u queue pairs\n", qm->qp_num);
 
 	if (!qm->qp_num) {
@@ -3059,10 +2960,12 @@ int hisi_qm_start(struct hisi_qm *qm)
 	}
 
 	ret = __hisi_qm_start(qm);
-	if (!ret)
-		atomic_set(&qm->status.flags, QM_START);
+	if (ret)
+		goto err_unlock;
 
+	atomic_set(&qm->status.flags, QM_WORK);
 	hisi_qm_set_state(qm, QM_READY);
+
 err_unlock:
 	up_write(&qm->qps_lock);
 	return ret;
@@ -3159,10 +3062,11 @@ int hisi_qm_stop(struct hisi_qm *qm, enum qm_stop_reason r)
 	down_write(&qm->qps_lock);
 
 	qm->status.stop_reason = r;
-	if (!qm_avail_state(qm, QM_STOP)) {
-		ret = -EPERM;
+	if (atomic_read(&qm->status.flags) == QM_STOP)
 		goto err_unlock;
-	}
+
+	/* Stop all the request sending at first. */
+	atomic_set(&qm->status.flags, QM_STOP);
 
 	if (qm->status.stop_reason == QM_SOFT_RESET ||
 	    qm->status.stop_reason == QM_DOWN) {
@@ -3186,7 +3090,6 @@ int hisi_qm_stop(struct hisi_qm *qm, enum qm_stop_reason r)
 	}
 
 	qm_clear_queues(qm);
-	atomic_set(&qm->status.flags, QM_STOP);
 
 err_unlock:
 	up_write(&qm->qps_lock);
@@ -5350,7 +5253,6 @@ int hisi_qm_init(struct hisi_qm *qm)
 		goto err_free_qm_memory;
 
 	qm_cmd_init(qm);
-	atomic_set(&qm->status.flags, QM_INIT);
 
 	return 0;
 
diff --git a/drivers/crypto/hisilicon/qm_common.h b/drivers/crypto/hisilicon/qm_common.h
index 7b0b15c83ec1..0760bf55f13e 100644
--- a/drivers/crypto/hisilicon/qm_common.h
+++ b/drivers/crypto/hisilicon/qm_common.h
@@ -72,10 +72,6 @@ struct qm_aeqc {
 	__le32 dw6;
 };
 
-static const char * const qm_s[] = {
-	"init", "start", "close", "stop",
-};
-
 int qm_set_and_get_xqc(struct hisi_qm *qm, u8 cmd, void *xqc, u32 qp_id, bool op);
 void hisi_qm_show_last_dfx_regs(struct hisi_qm *qm);
 void hisi_qm_set_algqos_init(struct hisi_qm *qm);
diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h
index ddc7ebb70523..e3c0a1297b2c 100644
--- a/include/linux/hisi_acc_qm.h
+++ b/include/linux/hisi_acc_qm.h
@@ -108,17 +108,13 @@ enum qm_stop_reason {
 };
 
 enum qm_state {
-	QM_INIT = 0,
-	QM_START,
-	QM_CLOSE,
+	QM_WORK = 0,
 	QM_STOP,
 };
 
 enum qp_state {
-	QP_INIT = 1,
-	QP_START,
+	QP_START = 1,
 	QP_STOP,
-	QP_CLOSE,
 };
 
 enum qm_hw_ver {
-- 
cgit v1.2.3


From 488e8f685207e0758398963d6834f81e5e61c162 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Thu, 30 Nov 2023 16:16:22 +0200
Subject: fs: fork splice_file_range() from do_splice_direct()

In preparation of calling do_splice_direct() without file_start_write()
held, create a new helper splice_file_range(), to be called from context
of ->copy_file_range() methods instead of do_splice_direct().

Currently, the only difference is that splice_file_range() does not take
flags argument and that it asserts that file_start_write() is held, but
we factor out a common helper do_splice_direct_actor() that will be used
later.

Use the new helper from __ceph_copy_file_range(), that was incorrectly
passing to do_splice_direct() the copy flags argument as splice flags.
The value of copy flags in ceph is always 0, so it is a smenatic bug fix.

Move the declaration of both helpers to linux/splice.h.

Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Link: https://lore.kernel.org/r/20231130141624.3338942-2-amir73il@gmail.com
Acked-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/ceph/file.c         |  9 ++++---
 fs/read_write.c        |  6 ++---
 fs/splice.c            | 71 ++++++++++++++++++++++++++++++++++++--------------
 include/linux/fs.h     |  2 --
 include/linux/splice.h | 13 +++++----
 5 files changed, 66 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 3b5aae29e944..f11de6e1f1c1 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -12,6 +12,7 @@
 #include <linux/falloc.h>
 #include <linux/iversion.h>
 #include <linux/ktime.h>
+#include <linux/splice.h>
 
 #include "super.h"
 #include "mds_client.h"
@@ -3010,8 +3011,8 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off,
 		 * {read,write}_iter, which will get caps again.
 		 */
 		put_rd_wr_caps(src_ci, src_got, dst_ci, dst_got);
-		ret = do_splice_direct(src_file, &src_off, dst_file,
-				       &dst_off, src_objlen, flags);
+		ret = splice_file_range(src_file, &src_off, dst_file, &dst_off,
+					src_objlen);
 		/* Abort on short copies or on error */
 		if (ret < (long)src_objlen) {
 			doutc(cl, "Failed partial copy (%zd)\n", ret);
@@ -3065,8 +3066,8 @@ out_caps:
 	 */
 	if (len && (len < src_ci->i_layout.object_size)) {
 		doutc(cl, "Final partial copy of %zu bytes\n", len);
-		bytes = do_splice_direct(src_file, &src_off, dst_file,
-					 &dst_off, len, flags);
+		bytes = splice_file_range(src_file, &src_off, dst_file,
+					  &dst_off, len);
 		if (bytes > 0)
 			ret += bytes;
 		else
diff --git a/fs/read_write.c b/fs/read_write.c
index f791555fa246..642c7ce1ced1 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1423,10 +1423,8 @@ ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in,
 				struct file *file_out, loff_t pos_out,
 				size_t len, unsigned int flags)
 {
-	lockdep_assert(file_write_started(file_out));
-
-	return do_splice_direct(file_in, &pos_in, file_out, &pos_out,
-				len > MAX_RW_COUNT ? MAX_RW_COUNT : len, 0);
+	return splice_file_range(file_in, &pos_in, file_out, &pos_out,
+				 min_t(size_t, len, MAX_RW_COUNT));
 }
 EXPORT_SYMBOL(generic_copy_file_range);
 
diff --git a/fs/splice.c b/fs/splice.c
index 3fce5f6072dd..9007b2c8baa8 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -1170,25 +1170,10 @@ static void direct_file_splice_eof(struct splice_desc *sd)
 		file->f_op->splice_eof(file);
 }
 
-/**
- * do_splice_direct - splices data directly between two files
- * @in:		file to splice from
- * @ppos:	input file offset
- * @out:	file to splice to
- * @opos:	output file offset
- * @len:	number of bytes to splice
- * @flags:	splice modifier flags
- *
- * Description:
- *    For use by do_sendfile(). splice can easily emulate sendfile, but
- *    doing it in the application would incur an extra system call
- *    (splice in + splice out, as compared to just sendfile()). So this helper
- *    can splice directly through a process-private pipe.
- *
- * Callers already called rw_verify_area() on the entire range.
- */
-long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
-		      loff_t *opos, size_t len, unsigned int flags)
+static long do_splice_direct_actor(struct file *in, loff_t *ppos,
+				   struct file *out, loff_t *opos,
+				   size_t len, unsigned int flags,
+				   splice_direct_actor *actor)
 {
 	struct splice_desc sd = {
 		.len		= len,
@@ -1207,14 +1192,60 @@ long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
 	if (unlikely(out->f_flags & O_APPEND))
 		return -EINVAL;
 
-	ret = splice_direct_to_actor(in, &sd, direct_splice_actor);
+	ret = splice_direct_to_actor(in, &sd, actor);
 	if (ret > 0)
 		*ppos = sd.pos;
 
 	return ret;
 }
+/**
+ * do_splice_direct - splices data directly between two files
+ * @in:		file to splice from
+ * @ppos:	input file offset
+ * @out:	file to splice to
+ * @opos:	output file offset
+ * @len:	number of bytes to splice
+ * @flags:	splice modifier flags
+ *
+ * Description:
+ *    For use by do_sendfile(). splice can easily emulate sendfile, but
+ *    doing it in the application would incur an extra system call
+ *    (splice in + splice out, as compared to just sendfile()). So this helper
+ *    can splice directly through a process-private pipe.
+ *
+ * Callers already called rw_verify_area() on the entire range.
+ */
+long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
+		      loff_t *opos, size_t len, unsigned int flags)
+{
+	return do_splice_direct_actor(in, ppos, out, opos, len, flags,
+				      direct_splice_actor);
+}
 EXPORT_SYMBOL(do_splice_direct);
 
+/**
+ * splice_file_range - splices data between two files for copy_file_range()
+ * @in:		file to splice from
+ * @ppos:	input file offset
+ * @out:	file to splice to
+ * @opos:	output file offset
+ * @len:	number of bytes to splice
+ *
+ * Description:
+ *    For use by generic_copy_file_range() and ->copy_file_range() methods.
+ *
+ * Callers already called rw_verify_area() on the entire range.
+ */
+long splice_file_range(struct file *in, loff_t *ppos, struct file *out,
+		       loff_t *opos, size_t len)
+{
+	lockdep_assert(file_write_started(out));
+
+	return do_splice_direct_actor(in, ppos, out, opos, len, 0,
+				      direct_splice_actor);
+}
+EXPORT_SYMBOL(splice_file_range);
+
 static int wait_for_space(struct pipe_inode_info *pipe, unsigned flags)
 {
 	for (;;) {
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ae0e2fb7bcea..04422a0eccdd 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3052,8 +3052,6 @@ ssize_t copy_splice_read(struct file *in, loff_t *ppos,
 			 size_t len, unsigned int flags);
 extern ssize_t iter_file_splice_write(struct pipe_inode_info *,
 		struct file *, loff_t *, size_t, unsigned int);
-extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
-		loff_t *opos, size_t len, unsigned int flags);
 
 
 extern void
diff --git a/include/linux/splice.h b/include/linux/splice.h
index 6c461573434d..49532d5dda52 100644
--- a/include/linux/splice.h
+++ b/include/linux/splice.h
@@ -80,11 +80,14 @@ extern ssize_t add_to_pipe(struct pipe_inode_info *,
 long vfs_splice_read(struct file *in, loff_t *ppos,
 		     struct pipe_inode_info *pipe, size_t len,
 		     unsigned int flags);
-extern ssize_t splice_direct_to_actor(struct file *, struct splice_desc *,
-				      splice_direct_actor *);
-extern long do_splice(struct file *in, loff_t *off_in,
-		      struct file *out, loff_t *off_out,
-		      size_t len, unsigned int flags);
+ssize_t splice_direct_to_actor(struct file *file, struct splice_desc *sd,
+			       splice_direct_actor *actor);
+long do_splice(struct file *in, loff_t *off_in, struct file *out,
+	       loff_t *off_out, size_t len, unsigned int flags);
+long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
+		      loff_t *opos, size_t len, unsigned int flags);
+long splice_file_range(struct file *in, loff_t *ppos, struct file *out,
+		       loff_t *opos, size_t len);
 
 extern long do_tee(struct file *in, struct file *out, size_t len,
 		   unsigned int flags);
-- 
cgit v1.2.3


From 42d1178d223ba9498c1ed40a5fc243a43d35ec97 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Fri, 1 Dec 2023 14:20:35 +0100
Subject: ASoC: cs4271: Convert to GPIO descriptors

This converts the Cirrus CS4271 ASoC codec driver to use
GPIO descriptors.

It turns out that there are two in-kernel users of the platform
data passing mechanism so these are switched over as well.

One locally defined GPIO "gpio_disabled" is declared in the
state struct but completely unused in the driver, so we delete
it.

Reviewed-by: Alexander Sverdlin <alexander.sverdlin@gmail.com>
Acked-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231201-descriptors-sound-cirrus-v2-6-ee9f9d4655eb@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 arch/arm/mach-ep93xx/edb93xx.c       | 32 +++++++++++++++++++++++++----
 arch/arm/mach-ep93xx/vision_ep9307.c | 12 ++++++++++-
 include/sound/cs4271.h               |  1 -
 sound/soc/codecs/cs4271.c            | 39 ++++++++++++------------------------
 4 files changed, 52 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-ep93xx/edb93xx.c b/arch/arm/mach-ep93xx/edb93xx.c
index 4b90899a66e9..dbdb822a0100 100644
--- a/arch/arm/mach-ep93xx/edb93xx.c
+++ b/arch/arm/mach-ep93xx/edb93xx.c
@@ -88,7 +88,7 @@ static void __init edb93xx_register_i2c(void)
  * EDB93xx SPI peripheral handling
  *************************************************************************/
 static struct cs4271_platform_data edb93xx_cs4271_data = {
-	.gpio_nreset	= -EINVAL,	/* filled in later */
+	/* Intentionally left blank */
 };
 
 static struct spi_board_info edb93xx_spi_board_info[] __initdata = {
@@ -114,14 +114,38 @@ static struct ep93xx_spi_info edb93xx_spi_info __initdata = {
 	/* Intentionally left blank */
 };
 
+static struct gpiod_lookup_table edb93xx_cs4272_edb9301_gpio_table = {
+	.dev_id = "spi0.0", /* CS0 on SPI0 */
+	.table = {
+		GPIO_LOOKUP("A", 1, "reset", GPIO_ACTIVE_LOW),
+		{ },
+	},
+};
+
+static struct gpiod_lookup_table edb93xx_cs4272_edb9302_gpio_table = {
+	.dev_id = "spi0.0", /* CS0 on SPI0 */
+	.table = {
+		GPIO_LOOKUP("H", 2, "reset", GPIO_ACTIVE_LOW),
+		{ },
+	},
+};
+
+static struct gpiod_lookup_table edb93xx_cs4272_edb9315_gpio_table = {
+	.dev_id = "spi0.0", /* CS0 on SPI0 */
+	.table = {
+		GPIO_LOOKUP("B", 6, "reset", GPIO_ACTIVE_LOW),
+		{ },
+	},
+};
+
 static void __init edb93xx_register_spi(void)
 {
 	if (machine_is_edb9301() || machine_is_edb9302())
-		edb93xx_cs4271_data.gpio_nreset = EP93XX_GPIO_LINE_EGPIO1;
+		gpiod_add_lookup_table(&edb93xx_cs4272_edb9301_gpio_table);
 	else if (machine_is_edb9302a() || machine_is_edb9307a())
-		edb93xx_cs4271_data.gpio_nreset = EP93XX_GPIO_LINE_H(2);
+		gpiod_add_lookup_table(&edb93xx_cs4272_edb9302_gpio_table);
 	else if (machine_is_edb9315a())
-		edb93xx_cs4271_data.gpio_nreset = EP93XX_GPIO_LINE_EGPIO14;
+		gpiod_add_lookup_table(&edb93xx_cs4272_edb9315_gpio_table);
 
 	gpiod_add_lookup_table(&edb93xx_spi_cs_gpio_table);
 	ep93xx_register_spi(&edb93xx_spi_info, edb93xx_spi_board_info,
diff --git a/arch/arm/mach-ep93xx/vision_ep9307.c b/arch/arm/mach-ep93xx/vision_ep9307.c
index 30d9cf3791eb..9471938df64c 100644
--- a/arch/arm/mach-ep93xx/vision_ep9307.c
+++ b/arch/arm/mach-ep93xx/vision_ep9307.c
@@ -164,7 +164,7 @@ static struct i2c_board_info vision_i2c_info[] __initdata = {
  * SPI CS4271 Audio Codec
  *************************************************************************/
 static struct cs4271_platform_data vision_cs4271_data = {
-	.gpio_nreset	= EP93XX_GPIO_LINE_H(2),
+	/* Intentionally left blank */
 };
 
 /*************************************************************************
@@ -241,6 +241,15 @@ static struct spi_board_info vision_spi_board_info[] __initdata = {
 	},
 };
 
+static struct gpiod_lookup_table vision_spi_cs4271_gpio_table = {
+	.dev_id = "spi0.0", /* cs4271 @ CS0 */
+	.table = {
+		/* RESET */
+		GPIO_LOOKUP_IDX("H", 2, NULL, 0, GPIO_ACTIVE_LOW),
+		{ },
+	},
+};
+
 static struct gpiod_lookup_table vision_spi_cs_gpio_table = {
 	.dev_id = "spi0",
 	.table = {
@@ -292,6 +301,7 @@ static void __init vision_init_machine(void)
 
 	ep93xx_register_i2c(vision_i2c_info,
 				ARRAY_SIZE(vision_i2c_info));
+	gpiod_add_lookup_table(&vision_spi_cs4271_gpio_table);
 	gpiod_add_lookup_table(&vision_spi_mmc_gpio_table);
 	gpiod_add_lookup_table(&vision_spi_cs_gpio_table);
 	ep93xx_register_spi(&vision_spi_master, vision_spi_board_info,
diff --git a/include/sound/cs4271.h b/include/sound/cs4271.h
index 6ff23ab48894..5a55d135bdea 100644
--- a/include/sound/cs4271.h
+++ b/include/sound/cs4271.h
@@ -9,7 +9,6 @@
 #define __CS4271_H
 
 struct cs4271_platform_data {
-	int gpio_nreset;	/* GPIO driving Reset pin, if any */
 	bool amutec_eq_bmutec;	/* flag to enable AMUTEC=BMUTEC */
 
 	/*
diff --git a/sound/soc/codecs/cs4271.c b/sound/soc/codecs/cs4271.c
index 9e6f8a048dd5..74a84832d958 100644
--- a/sound/soc/codecs/cs4271.c
+++ b/sound/soc/codecs/cs4271.c
@@ -13,9 +13,8 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/delay.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/of.h>
-#include <linux/of_gpio.h>
 #include <linux/regulator/consumer.h>
 #include <sound/pcm.h>
 #include <sound/soc.h>
@@ -160,9 +159,7 @@ struct cs4271_private {
 	/* Current sample rate for de-emphasis control */
 	int				rate;
 	/* GPIO driving Reset pin, if any */
-	int				gpio_nreset;
-	/* GPIO that disable serial bus, if any */
-	int				gpio_disable;
+	struct gpio_desc		*reset;
 	/* enable soft reset workaround */
 	bool				enable_soft_reset;
 	struct regulator_bulk_data      supplies[ARRAY_SIZE(supply_names)];
@@ -487,12 +484,10 @@ static int cs4271_reset(struct snd_soc_component *component)
 {
 	struct cs4271_private *cs4271 = snd_soc_component_get_drvdata(component);
 
-	if (gpio_is_valid(cs4271->gpio_nreset)) {
-		gpio_direction_output(cs4271->gpio_nreset, 0);
-		mdelay(1);
-		gpio_set_value(cs4271->gpio_nreset, 1);
-		mdelay(1);
-	}
+	gpiod_direction_output(cs4271->reset, 1);
+	mdelay(1);
+	gpiod_set_value(cs4271->reset, 0);
+	mdelay(1);
 
 	return 0;
 }
@@ -612,9 +607,8 @@ static void cs4271_component_remove(struct snd_soc_component *component)
 {
 	struct cs4271_private *cs4271 = snd_soc_component_get_drvdata(component);
 
-	if (gpio_is_valid(cs4271->gpio_nreset))
-		/* Set codec to the reset state */
-		gpio_set_value(cs4271->gpio_nreset, 0);
+	/* Set codec to the reset state */
+	gpiod_set_value(cs4271->reset, 1);
 
 	regcache_mark_dirty(cs4271->regmap);
 	regulator_bulk_disable(ARRAY_SIZE(cs4271->supplies), cs4271->supplies);
@@ -639,7 +633,6 @@ static const struct snd_soc_component_driver soc_component_dev_cs4271 = {
 static int cs4271_common_probe(struct device *dev,
 			       struct cs4271_private **c)
 {
-	struct cs4271_platform_data *cs4271plat = dev->platform_data;
 	struct cs4271_private *cs4271;
 	int i, ret;
 
@@ -647,17 +640,11 @@ static int cs4271_common_probe(struct device *dev,
 	if (!cs4271)
 		return -ENOMEM;
 
-	cs4271->gpio_nreset = of_get_named_gpio(dev->of_node, "reset-gpio", 0);
-
-	if (cs4271plat)
-		cs4271->gpio_nreset = cs4271plat->gpio_nreset;
-
-	if (gpio_is_valid(cs4271->gpio_nreset)) {
-		ret = devm_gpio_request(dev, cs4271->gpio_nreset,
-					"CS4271 Reset");
-		if (ret < 0)
-			return ret;
-	}
+	cs4271->reset = devm_gpiod_get_optional(dev, "reset", GPIOD_ASIS);
+	if (IS_ERR(cs4271->reset))
+		return dev_err_probe(dev, PTR_ERR(cs4271->reset),
+				     "error retrieveing RESET GPIO\n");
+	gpiod_set_consumer_name(cs4271->reset, "CS4271 Reset");
 
 	for (i = 0; i < ARRAY_SIZE(supply_names); i++)
 		cs4271->supplies[i].supply = supply_names[i];
-- 
cgit v1.2.3


From 77070eeb882124614a40616f01bfe60947be5778 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Thu, 30 Nov 2023 15:43:27 -0500
Subject: cgroup: Avoid false cacheline sharing of read mostly rstat_cpu

The rstat_cpu and also rstat_css_list of the cgroup structure are read
mostly variables. However, they may share the same cacheline as the
subsequent rstat_flush_next and *bstat variables which can be updated
frequently.  That will slow down the cgroup_rstat_cpu() call which is
called pretty frequently in the rstat code. Add a CACHELINE_PADDING()
line in between them to avoid false cacheline sharing.

A parallel kernel build on a 2-socket x86-64 server is used as the
benchmarking tool for measuring the lock hold time. Below were the lock
hold time frequency distribution before and after the patch:

      Run time        Before patch       After patch
      --------        ------------       -----------
       0-01 us         9,928,562          9,820,428
      01-05 us           110,151             50,935
      05-10 us               270                 93
      10-15 us               273                146
      15-20 us               135                 76
      20-25 us                 0                  2
      25-30 us                 1                  0

It can be seen that the patch further pushes the lock hold time towards
the lower end.

Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/cgroup-defs.h | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 37518436cfe7..5a97ea95b564 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -496,6 +496,13 @@ struct cgroup {
 	struct cgroup_rstat_cpu __percpu *rstat_cpu;
 	struct list_head rstat_css_list;
 
+	/*
+	 * Add padding to separate the read mostly rstat_cpu and
+	 * rstat_css_list into a different cacheline from the following
+	 * rstat_flush_next and *bstat fields which can have frequent updates.
+	 */
+	CACHELINE_PADDING(_pad_);
+
 	/*
 	 * A singly-linked list of cgroup structures to be rstat flushed.
 	 * This is a scratch field to be used exclusively by
-- 
cgit v1.2.3


From aabf7c37dfbce3e5fe24f0c86a34bc8f2f63cee8 Mon Sep 17 00:00:00 2001
From: Stephen Boyd <swboyd@chromium.org>
Date: Wed, 29 Nov 2023 13:44:04 -0800
Subject: lkdtm: Add kfence read after free crash type

Add the ability to allocate memory from kfence and trigger a read after
free on that memory to validate that kfence is working properly. This is
used by ChromeOS integration tests to validate that kfence errors can be
collected on user devices and parsed properly.

Cc: Alexander Potapenko <glider@google.com>
Acked-by: Marco Elver <elver@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: kasan-dev@googlegroups.com
Signed-off-by: Stephen Boyd <swboyd@chromium.org>
Link: https://lore.kernel.org/r/20231129214413.3156334-1-swboyd@chromium.org
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 drivers/misc/lkdtm/heap.c | 60 +++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/kfence.h    |  2 ++
 2 files changed, 62 insertions(+)

(limited to 'include')

diff --git a/drivers/misc/lkdtm/heap.c b/drivers/misc/lkdtm/heap.c
index 0ce4cbf6abda..4f467d3972a6 100644
--- a/drivers/misc/lkdtm/heap.c
+++ b/drivers/misc/lkdtm/heap.c
@@ -4,6 +4,7 @@
  * page allocation and slab allocations.
  */
 #include "lkdtm.h"
+#include <linux/kfence.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/sched.h>
@@ -132,6 +133,64 @@ static void lkdtm_READ_AFTER_FREE(void)
 	kfree(val);
 }
 
+static void lkdtm_KFENCE_READ_AFTER_FREE(void)
+{
+	int *base, val, saw;
+	unsigned long timeout, resched_after;
+	size_t len = 1024;
+	/*
+	 * The slub allocator will use the either the first word or
+	 * the middle of the allocation to store the free pointer,
+	 * depending on configurations. Store in the second word to
+	 * avoid running into the freelist.
+	 */
+	size_t offset = sizeof(*base);
+
+	/*
+	 * 100x the sample interval should be more than enough to ensure we get
+	 * a KFENCE allocation eventually.
+	 */
+	timeout = jiffies + msecs_to_jiffies(100 * kfence_sample_interval);
+	/*
+	 * Especially for non-preemption kernels, ensure the allocation-gate
+	 * timer can catch up: after @resched_after, every failed allocation
+	 * attempt yields, to ensure the allocation-gate timer is scheduled.
+	 */
+	resched_after = jiffies + msecs_to_jiffies(kfence_sample_interval);
+	do {
+		base = kmalloc(len, GFP_KERNEL);
+		if (!base) {
+			pr_err("FAIL: Unable to allocate kfence memory!\n");
+			return;
+		}
+
+		if (is_kfence_address(base)) {
+			val = 0x12345678;
+			base[offset] = val;
+			pr_info("Value in memory before free: %x\n", base[offset]);
+
+			kfree(base);
+
+			pr_info("Attempting bad read from freed memory\n");
+			saw = base[offset];
+			if (saw != val) {
+				/* Good! Poisoning happened, so declare a win. */
+				pr_info("Memory correctly poisoned (%x)\n", saw);
+			} else {
+				pr_err("FAIL: Memory was not poisoned!\n");
+				pr_expected_config_param(CONFIG_INIT_ON_FREE_DEFAULT_ON, "init_on_free");
+			}
+			return;
+		}
+
+		kfree(base);
+		if (time_after(jiffies, resched_after))
+			cond_resched();
+	} while (time_before(jiffies, timeout));
+
+	pr_err("FAIL: kfence memory never allocated!\n");
+}
+
 static void lkdtm_WRITE_BUDDY_AFTER_FREE(void)
 {
 	unsigned long p = __get_free_page(GFP_KERNEL);
@@ -327,6 +386,7 @@ static struct crashtype crashtypes[] = {
 	CRASHTYPE(VMALLOC_LINEAR_OVERFLOW),
 	CRASHTYPE(WRITE_AFTER_FREE),
 	CRASHTYPE(READ_AFTER_FREE),
+	CRASHTYPE(KFENCE_READ_AFTER_FREE),
 	CRASHTYPE(WRITE_BUDDY_AFTER_FREE),
 	CRASHTYPE(READ_BUDDY_AFTER_FREE),
 	CRASHTYPE(SLAB_INIT_ON_ALLOC),
diff --git a/include/linux/kfence.h b/include/linux/kfence.h
index 401af4757514..88100cc9caba 100644
--- a/include/linux/kfence.h
+++ b/include/linux/kfence.h
@@ -223,6 +223,8 @@ bool __kfence_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *sla
 
 #else /* CONFIG_KFENCE */
 
+#define kfence_sample_interval	(0)
+
 static inline bool is_kfence_address(const void *addr) { return false; }
 static inline void kfence_alloc_pool_and_metadata(void) { }
 static inline void kfence_init(void) { }
-- 
cgit v1.2.3


From 12cd3cd8c797e07afcc47bc4afa760e4ec75e9d7 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 20 Nov 2023 17:11:42 +0200
Subject: params: Introduce the param_unknown_fn type

Introduce a new type for the callback to parse an unknown argument.
This unifies function prototypes which takes that as a parameter.

Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231120151419.1661807-2-andriy.shevchenko@linux.intel.com
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 include/linux/moduleparam.h | 6 +++---
 kernel/params.c             | 8 ++------
 2 files changed, 5 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index 4fa9726bc328..bfb85fd13e1f 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -385,6 +385,8 @@ extern bool parameq(const char *name1, const char *name2);
  */
 extern bool parameqn(const char *name1, const char *name2, size_t n);
 
+typedef int (*parse_unknown_fn)(char *param, char *val, const char *doing, void *arg);
+
 /* Called on module insert or kernel boot */
 extern char *parse_args(const char *name,
 		      char *args,
@@ -392,9 +394,7 @@ extern char *parse_args(const char *name,
 		      unsigned num,
 		      s16 level_min,
 		      s16 level_max,
-		      void *arg,
-		      int (*unknown)(char *param, char *val,
-				     const char *doing, void *arg));
+		      void *arg, parse_unknown_fn unknown);
 
 /* Called by module remove. */
 #ifdef CONFIG_SYSFS
diff --git a/kernel/params.c b/kernel/params.c
index 2d4a0564697e..626fa8265932 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -120,9 +120,7 @@ static int parse_one(char *param,
 		     unsigned num_params,
 		     s16 min_level,
 		     s16 max_level,
-		     void *arg,
-		     int (*handle_unknown)(char *param, char *val,
-				     const char *doing, void *arg))
+		     void *arg, parse_unknown_fn handle_unknown)
 {
 	unsigned int i;
 	int err;
@@ -165,9 +163,7 @@ char *parse_args(const char *doing,
 		 unsigned num,
 		 s16 min_level,
 		 s16 max_level,
-		 void *arg,
-		 int (*unknown)(char *param, char *val,
-				const char *doing, void *arg))
+		 void *arg, parse_unknown_fn unknown)
 {
 	char *param, *val, *err = NULL;
 
-- 
cgit v1.2.3


From 492c5d455969fc2e829f26ed4c83487b068f0dd7 Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Thu, 30 Nov 2023 13:53:06 -0800
Subject: block: bio-integrity: directly map user buffers

Passthrough commands that utilize metadata currently need to bounce the
user space buffer through the kernel. Add support for mapping user space
directly so that we can avoid this costly overhead. This is similar to
how the normal bio data payload utilizes user addresses with
bio_map_user_iov().

If the user address can't directly be used for reason, like too many
segments or address unalignement, fallback to a copy of the user vec
while keeping the user address pinned for the IO duration so that it
can safely be copied on completion in any process context.

Signed-off-by: Keith Busch <kbusch@kernel.org>
Link: https://lore.kernel.org/r/20231130215309.2923568-2-kbusch@meta.com
[axboe: fold in fix from Kanchan Joshi]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bio-integrity.c | 218 +++++++++++++++++++++++++++++++++++++++++++++++++-
 include/linux/bio.h   |   9 +++
 2 files changed, 225 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index ec8ac8cf6e1b..feef615e2c9c 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -69,15 +69,15 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
 
 	memset(bip, 0, sizeof(*bip));
 
+	/* always report as many vecs as asked explicitly, not inline vecs */
+	bip->bip_max_vcnt = nr_vecs;
 	if (nr_vecs > inline_vecs) {
-		bip->bip_max_vcnt = nr_vecs;
 		bip->bip_vec = bvec_alloc(&bs->bvec_integrity_pool,
 					  &bip->bip_max_vcnt, gfp_mask);
 		if (!bip->bip_vec)
 			goto err;
 	} else {
 		bip->bip_vec = bip->bip_inline_vecs;
-		bip->bip_max_vcnt = inline_vecs;
 	}
 
 	bip->bip_bio = bio;
@@ -91,6 +91,47 @@ err:
 }
 EXPORT_SYMBOL(bio_integrity_alloc);
 
+static void bio_integrity_unpin_bvec(struct bio_vec *bv, int nr_vecs,
+				     bool dirty)
+{
+	int i;
+
+	for (i = 0; i < nr_vecs; i++) {
+		if (dirty && !PageCompound(bv[i].bv_page))
+			set_page_dirty_lock(bv[i].bv_page);
+		unpin_user_page(bv[i].bv_page);
+	}
+}
+
+static void bio_integrity_uncopy_user(struct bio_integrity_payload *bip)
+{
+	unsigned short nr_vecs = bip->bip_max_vcnt - 1;
+	struct bio_vec *copy = &bip->bip_vec[1];
+	size_t bytes = bip->bip_iter.bi_size;
+	struct iov_iter iter;
+	int ret;
+
+	iov_iter_bvec(&iter, ITER_DEST, copy, nr_vecs, bytes);
+	ret = copy_to_iter(bvec_virt(bip->bip_vec), bytes, &iter);
+	WARN_ON_ONCE(ret != bytes);
+
+	bio_integrity_unpin_bvec(copy, nr_vecs, true);
+}
+
+static void bio_integrity_unmap_user(struct bio_integrity_payload *bip)
+{
+	bool dirty = bio_data_dir(bip->bip_bio) == READ;
+
+	if (bip->bip_flags & BIP_COPY_USER) {
+		if (dirty)
+			bio_integrity_uncopy_user(bip);
+		kfree(bvec_virt(bip->bip_vec));
+		return;
+	}
+
+	bio_integrity_unpin_bvec(bip->bip_vec, bip->bip_max_vcnt, dirty);
+}
+
 /**
  * bio_integrity_free - Free bio integrity payload
  * @bio:	bio containing bip to be freed
@@ -105,6 +146,8 @@ void bio_integrity_free(struct bio *bio)
 
 	if (bip->bip_flags & BIP_BLOCK_INTEGRITY)
 		kfree(bvec_virt(bip->bip_vec));
+	else if (bip->bip_flags & BIP_INTEGRITY_USER)
+		bio_integrity_unmap_user(bip);
 
 	__bio_integrity_free(bs, bip);
 	bio->bi_integrity = NULL;
@@ -160,6 +203,177 @@ int bio_integrity_add_page(struct bio *bio, struct page *page,
 }
 EXPORT_SYMBOL(bio_integrity_add_page);
 
+static int bio_integrity_copy_user(struct bio *bio, struct bio_vec *bvec,
+				   int nr_vecs, unsigned int len,
+				   unsigned int direction, u32 seed)
+{
+	bool write = direction == ITER_SOURCE;
+	struct bio_integrity_payload *bip;
+	struct iov_iter iter;
+	void *buf;
+	int ret;
+
+	buf = kmalloc(len, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	if (write) {
+		iov_iter_bvec(&iter, direction, bvec, nr_vecs, len);
+		if (!copy_from_iter_full(buf, len, &iter)) {
+			ret = -EFAULT;
+			goto free_buf;
+		}
+
+		bip = bio_integrity_alloc(bio, GFP_KERNEL, 1);
+	} else {
+		memset(buf, 0, len);
+
+		/*
+		 * We need to preserve the original bvec and the number of vecs
+		 * in it for completion handling
+		 */
+		bip = bio_integrity_alloc(bio, GFP_KERNEL, nr_vecs + 1);
+	}
+
+	if (IS_ERR(bip)) {
+		ret = PTR_ERR(bip);
+		goto free_buf;
+	}
+
+	if (write)
+		bio_integrity_unpin_bvec(bvec, nr_vecs, false);
+	else
+		memcpy(&bip->bip_vec[1], bvec, nr_vecs * sizeof(*bvec));
+
+	ret = bio_integrity_add_page(bio, virt_to_page(buf), len,
+				     offset_in_page(buf));
+	if (ret != len) {
+		ret = -ENOMEM;
+		goto free_bip;
+	}
+
+	bip->bip_flags |= BIP_INTEGRITY_USER | BIP_COPY_USER;
+	bip->bip_iter.bi_sector = seed;
+	return 0;
+free_bip:
+	bio_integrity_free(bio);
+free_buf:
+	kfree(buf);
+	return ret;
+}
+
+static int bio_integrity_init_user(struct bio *bio, struct bio_vec *bvec,
+				   int nr_vecs, unsigned int len, u32 seed)
+{
+	struct bio_integrity_payload *bip;
+
+	bip = bio_integrity_alloc(bio, GFP_KERNEL, nr_vecs);
+	if (IS_ERR(bip))
+		return PTR_ERR(bip);
+
+	memcpy(bip->bip_vec, bvec, nr_vecs * sizeof(*bvec));
+	bip->bip_flags |= BIP_INTEGRITY_USER;
+	bip->bip_iter.bi_sector = seed;
+	bip->bip_iter.bi_size = len;
+	return 0;
+}
+
+static unsigned int bvec_from_pages(struct bio_vec *bvec, struct page **pages,
+				    int nr_vecs, ssize_t bytes, ssize_t offset)
+{
+	unsigned int nr_bvecs = 0;
+	int i, j;
+
+	for (i = 0; i < nr_vecs; i = j) {
+		size_t size = min_t(size_t, bytes, PAGE_SIZE - offset);
+		struct folio *folio = page_folio(pages[i]);
+
+		bytes -= size;
+		for (j = i + 1; j < nr_vecs; j++) {
+			size_t next = min_t(size_t, PAGE_SIZE, bytes);
+
+			if (page_folio(pages[j]) != folio ||
+			    pages[j] != pages[j - 1] + 1)
+				break;
+			unpin_user_page(pages[j]);
+			size += next;
+			bytes -= next;
+		}
+
+		bvec_set_page(&bvec[nr_bvecs], pages[i], size, offset);
+		offset = 0;
+		nr_bvecs++;
+	}
+
+	return nr_bvecs;
+}
+
+int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t bytes,
+			   u32 seed)
+{
+	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
+	unsigned int align = q->dma_pad_mask | queue_dma_alignment(q);
+	struct page *stack_pages[UIO_FASTIOV], **pages = stack_pages;
+	struct bio_vec stack_vec[UIO_FASTIOV], *bvec = stack_vec;
+	unsigned int direction, nr_bvecs;
+	struct iov_iter iter;
+	int ret, nr_vecs;
+	size_t offset;
+	bool copy;
+
+	if (bio_integrity(bio))
+		return -EINVAL;
+	if (bytes >> SECTOR_SHIFT > queue_max_hw_sectors(q))
+		return -E2BIG;
+
+	if (bio_data_dir(bio) == READ)
+		direction = ITER_DEST;
+	else
+		direction = ITER_SOURCE;
+
+	iov_iter_ubuf(&iter, direction, ubuf, bytes);
+	nr_vecs = iov_iter_npages(&iter, BIO_MAX_VECS + 1);
+	if (nr_vecs > BIO_MAX_VECS)
+		return -E2BIG;
+	if (nr_vecs > UIO_FASTIOV) {
+		bvec = kcalloc(sizeof(*bvec), nr_vecs, GFP_KERNEL);
+		if (!bvec)
+			return -ENOMEM;
+		pages = NULL;
+	}
+
+	copy = !iov_iter_is_aligned(&iter, align, align);
+	ret = iov_iter_extract_pages(&iter, &pages, bytes, nr_vecs, 0, &offset);
+	if (unlikely(ret < 0))
+		goto free_bvec;
+
+	nr_bvecs = bvec_from_pages(bvec, pages, nr_vecs, bytes, offset);
+	if (pages != stack_pages)
+		kvfree(pages);
+	if (nr_bvecs > queue_max_integrity_segments(q))
+		copy = true;
+
+	if (copy)
+		ret = bio_integrity_copy_user(bio, bvec, nr_bvecs, bytes,
+					      direction, seed);
+	else
+		ret = bio_integrity_init_user(bio, bvec, nr_bvecs, bytes, seed);
+	if (ret)
+		goto release_pages;
+	if (bvec != stack_vec)
+		kfree(bvec);
+
+	return 0;
+
+release_pages:
+	bio_integrity_unpin_bvec(bvec, nr_bvecs, false);
+free_bvec:
+	if (bvec != stack_vec)
+		kfree(bvec);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(bio_integrity_map_user);
+
 /**
  * bio_integrity_process - Process integrity metadata for a bio
  * @bio:	bio to generate/verify integrity metadata for
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 41d417ee1349..ec4db73e5f4e 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -324,6 +324,8 @@ enum bip_flags {
 	BIP_CTRL_NOCHECK	= 1 << 2, /* disable HBA integrity checking */
 	BIP_DISK_NOCHECK	= 1 << 3, /* disable disk integrity checking */
 	BIP_IP_CHECKSUM		= 1 << 4, /* IP checksum */
+	BIP_INTEGRITY_USER	= 1 << 5, /* Integrity payload is user address */
+	BIP_COPY_USER		= 1 << 6, /* Kernel bounce buffer in use */
 };
 
 /*
@@ -718,6 +720,7 @@ static inline bool bioset_initialized(struct bio_set *bs)
 	for_each_bio(_bio)						\
 		bip_for_each_vec(_bvl, _bio->bi_integrity, _iter)
 
+int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t len, u32 seed);
 extern struct bio_integrity_payload *bio_integrity_alloc(struct bio *, gfp_t, unsigned int);
 extern int bio_integrity_add_page(struct bio *, struct page *, unsigned int, unsigned int);
 extern bool bio_integrity_prep(struct bio *);
@@ -789,6 +792,12 @@ static inline int bio_integrity_add_page(struct bio *bio, struct page *page,
 	return 0;
 }
 
+static inline int bio_integrity_map_user(struct bio *bio, void __user *ubuf,
+					 ssize_t len, u32 seed)
+{
+	return -EINVAL;
+}
+
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
 /*
-- 
cgit v1.2.3


From e5da71f1e373f36c7506ffa9a60ef7ec6e84674d Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Thu, 30 Nov 2023 13:53:08 -0800
Subject: iouring: remove IORING_URING_CMD_POLLED

No more users of this flag.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Link: https://lore.kernel.org/r/20231130215309.2923568-4-kbusch@meta.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/io_uring.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index aefb73eeeebf..fe23bf88f86f 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -28,7 +28,6 @@ enum io_uring_cmd_flags {
 
 /* only top 8 bits of sqe->uring_cmd_flags for kernel internal use */
 #define IORING_URING_CMD_CANCELABLE	(1U << 30)
-#define IORING_URING_CMD_POLLED		(1U << 31)
 
 struct io_uring_cmd {
 	struct file	*file;
-- 
cgit v1.2.3


From 8fadb86d4ced8b8349a3b227d6d66736ff150819 Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Thu, 30 Nov 2023 13:53:09 -0800
Subject: io_uring: remove uring_cmd cookie

No more users of this field.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Link: https://lore.kernel.org/r/20231130215309.2923568-5-kbusch@meta.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/io_uring.h | 8 ++------
 io_uring/uring_cmd.c     | 1 -
 2 files changed, 2 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index fe23bf88f86f..9e6ce6d4ab51 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -32,12 +32,8 @@ enum io_uring_cmd_flags {
 struct io_uring_cmd {
 	struct file	*file;
 	const struct io_uring_sqe *sqe;
-	union {
-		/* callback to defer completions to task context */
-		void (*task_work_cb)(struct io_uring_cmd *cmd, unsigned);
-		/* used for polled completion */
-		void *cookie;
-	};
+	/* callback to defer completions to task context */
+	void (*task_work_cb)(struct io_uring_cmd *cmd, unsigned);
 	u32		cmd_op;
 	u32		flags;
 	u8		pdu[32]; /* available inline for free use */
diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c
index acbc2924ecd2..b39ec25c36bc 100644
--- a/io_uring/uring_cmd.c
+++ b/io_uring/uring_cmd.c
@@ -182,7 +182,6 @@ int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags)
 			return -EOPNOTSUPP;
 		issue_flags |= IO_URING_F_IOPOLL;
 		req->iopoll_completed = 0;
-		WRITE_ONCE(ioucmd->cookie, NULL);
 	}
 
 	ret = file->f_op->uring_cmd(ioucmd, issue_flags);
-- 
cgit v1.2.3


From 45b5623f2d721c25d1a2fdc8c4600fb4b7b61c75 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Sat, 2 Dec 2023 09:56:55 -0800
Subject: bpf: rearrange bpf_func_state fields to save a bit of memory

It's a trivial rearrangement saving 8 bytes. We have 4 bytes of padding
at the end which can be filled with another field without increasing
struct bpf_func_state.

copy_func_state() logic remains correct without any further changes.

BEFORE
======
struct bpf_func_state {
        struct bpf_reg_state       regs[11];             /*     0  1320 */
        /* --- cacheline 20 boundary (1280 bytes) was 40 bytes ago --- */
        int                        callsite;             /*  1320     4 */
        u32                        frameno;              /*  1324     4 */
        u32                        subprogno;            /*  1328     4 */
        u32                        async_entry_cnt;      /*  1332     4 */
        bool                       in_callback_fn;       /*  1336     1 */

        /* XXX 7 bytes hole, try to pack */

        /* --- cacheline 21 boundary (1344 bytes) --- */
        struct tnum                callback_ret_range;   /*  1344    16 */
        bool                       in_async_callback_fn; /*  1360     1 */
        bool                       in_exception_callback_fn; /*  1361     1 */

        /* XXX 2 bytes hole, try to pack */

        int                        acquired_refs;        /*  1364     4 */
        struct bpf_reference_state * refs;               /*  1368     8 */
        int                        allocated_stack;      /*  1376     4 */

        /* XXX 4 bytes hole, try to pack */

        struct bpf_stack_state *   stack;                /*  1384     8 */

        /* size: 1392, cachelines: 22, members: 13 */
        /* sum members: 1379, holes: 3, sum holes: 13 */
        /* last cacheline: 48 bytes */
};

AFTER
=====
struct bpf_func_state {
        struct bpf_reg_state       regs[11];             /*     0  1320 */
        /* --- cacheline 20 boundary (1280 bytes) was 40 bytes ago --- */
        int                        callsite;             /*  1320     4 */
        u32                        frameno;              /*  1324     4 */
        u32                        subprogno;            /*  1328     4 */
        u32                        async_entry_cnt;      /*  1332     4 */
        struct tnum                callback_ret_range;   /*  1336    16 */
        /* --- cacheline 21 boundary (1344 bytes) was 8 bytes ago --- */
        bool                       in_callback_fn;       /*  1352     1 */
        bool                       in_async_callback_fn; /*  1353     1 */
        bool                       in_exception_callback_fn; /*  1354     1 */

        /* XXX 1 byte hole, try to pack */

        int                        acquired_refs;        /*  1356     4 */
        struct bpf_reference_state * refs;               /*  1360     8 */
        struct bpf_stack_state *   stack;                /*  1368     8 */
        int                        allocated_stack;      /*  1376     4 */

        /* size: 1384, cachelines: 22, members: 13 */
        /* sum members: 1379, holes: 1, sum holes: 1 */
        /* padding: 4 */
        /* last cacheline: 40 bytes */
};

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20231202175705.885270-2-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf_verifier.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index d99a636d36a7..0c0e1bccad45 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -297,8 +297,8 @@ struct bpf_func_state {
 	 * void foo(void) { bpf_timer_set_callback(,foo); }
 	 */
 	u32 async_entry_cnt;
-	bool in_callback_fn;
 	struct tnum callback_ret_range;
+	bool in_callback_fn;
 	bool in_async_callback_fn;
 	bool in_exception_callback_fn;
 	/* For callback calling functions that limit number of possible
@@ -316,8 +316,8 @@ struct bpf_func_state {
 	/* The following fields should be last. See copy_func_state() */
 	int acquired_refs;
 	struct bpf_reference_state *refs;
-	int allocated_stack;
 	struct bpf_stack_state *stack;
+	int allocated_stack;
 };
 
 struct bpf_idx_pair {
-- 
cgit v1.2.3


From 8fa4ecd49b81ccd9d1d87f1c8b2260e218644878 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Sat, 2 Dec 2023 09:56:58 -0800
Subject: bpf: enforce exact retval range on subprog/callback exit

Instead of relying on potentially imprecise tnum representation of
expected return value range for callbacks and subprogs, validate that
smin/smax range satisfy exact expected range of return values.

E.g., if callback would need to return [0, 2] range, tnum can't
represent this precisely and instead will allow [0, 3] range. By
checking smin/smax range, we can make sure that subprog/callback indeed
returns only valid [0, 2] range.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Acked-by: Shung-Hsi Yu <shung-hsi.yu@suse.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20231202175705.885270-5-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf_verifier.h |  7 ++++++-
 kernel/bpf/verifier.c        | 33 ++++++++++++++++++++++-----------
 2 files changed, 28 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 0c0e1bccad45..3378cc753061 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -275,6 +275,11 @@ struct bpf_reference_state {
 	int callback_ref;
 };
 
+struct bpf_retval_range {
+	s32 minval;
+	s32 maxval;
+};
+
 /* state of the program:
  * type of all registers and stack info
  */
@@ -297,7 +302,7 @@ struct bpf_func_state {
 	 * void foo(void) { bpf_timer_set_callback(,foo); }
 	 */
 	u32 async_entry_cnt;
-	struct tnum callback_ret_range;
+	struct bpf_retval_range callback_ret_range;
 	bool in_callback_fn;
 	bool in_async_callback_fn;
 	bool in_exception_callback_fn;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 849fbf47b5f3..f3d9d7de68da 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2305,6 +2305,11 @@ static void init_reg_state(struct bpf_verifier_env *env,
 	regs[BPF_REG_FP].frameno = state->frameno;
 }
 
+static struct bpf_retval_range retval_range(s32 minval, s32 maxval)
+{
+	return (struct bpf_retval_range){ minval, maxval };
+}
+
 #define BPF_MAIN_FUNC (-1)
 static void init_func_state(struct bpf_verifier_env *env,
 			    struct bpf_func_state *state,
@@ -2313,7 +2318,7 @@ static void init_func_state(struct bpf_verifier_env *env,
 	state->callsite = callsite;
 	state->frameno = frameno;
 	state->subprogno = subprogno;
-	state->callback_ret_range = tnum_range(0, 0);
+	state->callback_ret_range = retval_range(0, 0);
 	init_reg_state(env, state);
 	mark_verifier_state_scratched(env);
 }
@@ -9396,7 +9401,7 @@ static int set_map_elem_callback_state(struct bpf_verifier_env *env,
 		return err;
 
 	callee->in_callback_fn = true;
-	callee->callback_ret_range = tnum_range(0, 1);
+	callee->callback_ret_range = retval_range(0, 1);
 	return 0;
 }
 
@@ -9418,7 +9423,7 @@ static int set_loop_callback_state(struct bpf_verifier_env *env,
 	__mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
 
 	callee->in_callback_fn = true;
-	callee->callback_ret_range = tnum_range(0, 1);
+	callee->callback_ret_range = retval_range(0, 1);
 	return 0;
 }
 
@@ -9448,7 +9453,7 @@ static int set_timer_callback_state(struct bpf_verifier_env *env,
 	__mark_reg_not_init(env, &callee->regs[BPF_REG_4]);
 	__mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
 	callee->in_async_callback_fn = true;
-	callee->callback_ret_range = tnum_range(0, 1);
+	callee->callback_ret_range = retval_range(0, 1);
 	return 0;
 }
 
@@ -9476,7 +9481,7 @@ static int set_find_vma_callback_state(struct bpf_verifier_env *env,
 	__mark_reg_not_init(env, &callee->regs[BPF_REG_4]);
 	__mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
 	callee->in_callback_fn = true;
-	callee->callback_ret_range = tnum_range(0, 1);
+	callee->callback_ret_range = retval_range(0, 1);
 	return 0;
 }
 
@@ -9499,7 +9504,7 @@ static int set_user_ringbuf_callback_state(struct bpf_verifier_env *env,
 	__mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
 
 	callee->in_callback_fn = true;
-	callee->callback_ret_range = tnum_range(0, 1);
+	callee->callback_ret_range = retval_range(0, 1);
 	return 0;
 }
 
@@ -9531,7 +9536,7 @@ static int set_rbtree_add_callback_state(struct bpf_verifier_env *env,
 	__mark_reg_not_init(env, &callee->regs[BPF_REG_4]);
 	__mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
 	callee->in_callback_fn = true;
-	callee->callback_ret_range = tnum_range(0, 1);
+	callee->callback_ret_range = retval_range(0, 1);
 	return 0;
 }
 
@@ -9560,6 +9565,11 @@ static bool in_rbtree_lock_required_cb(struct bpf_verifier_env *env)
 	return is_rbtree_lock_required_kfunc(kfunc_btf_id);
 }
 
+static bool retval_range_within(struct bpf_retval_range range, const struct bpf_reg_state *reg)
+{
+	return range.minval <= reg->smin_value && reg->smax_value <= range.maxval;
+}
+
 static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 {
 	struct bpf_verifier_state *state = env->cur_state, *prev_st;
@@ -9583,9 +9593,6 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 
 	caller = state->frame[state->curframe - 1];
 	if (callee->in_callback_fn) {
-		/* enforce R0 return value range [0, 1]. */
-		struct tnum range = callee->callback_ret_range;
-
 		if (r0->type != SCALAR_VALUE) {
 			verbose(env, "R0 not a scalar value\n");
 			return -EACCES;
@@ -9597,7 +9604,11 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 		if (err)
 			return err;
 
-		if (!tnum_in(range, r0->var_off)) {
+		/* enforce R0 return value range */
+		if (!retval_range_within(callee->callback_ret_range, r0)) {
+			struct tnum range = tnum_range(callee->callback_ret_range.minval,
+						       callee->callback_ret_range.maxval);
+
 			verbose_invalid_scalar(env, r0, &range, "callback return", "R0");
 			return -EINVAL;
 		}
-- 
cgit v1.2.3


From aeb9ce058d7c6193dc41e06b3a5b29d22c446b14 Mon Sep 17 00:00:00 2001
From: Coco Li <lixiaoyan@google.com>
Date: Wed, 29 Nov 2023 07:27:53 +0000
Subject: cache: enforce cache groups

Set up build time warnings to safeguard against future header changes of
organized structs.

Warning includes:

1) whether all variables are still in the same cache group
2) whether all the cache groups have the sum of the members size (in the
   maximum condition, including all members defined in configs)

The __cache_group* variables are ignored in kernel-doc check in the
various header files they appear in to enforce the cache groups.

Suggested-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Coco Li <lixiaoyan@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/cache.h | 25 +++++++++++++++++++++++++
 scripts/kernel-doc    |  5 +++++
 2 files changed, 30 insertions(+)

(limited to 'include')

diff --git a/include/linux/cache.h b/include/linux/cache.h
index 9900d20b76c2..0ecb17bb6883 100644
--- a/include/linux/cache.h
+++ b/include/linux/cache.h
@@ -85,6 +85,31 @@
 #define cache_line_size()	L1_CACHE_BYTES
 #endif
 
+#ifndef __cacheline_group_begin
+#define __cacheline_group_begin(GROUP) \
+	__u8 __cacheline_group_begin__##GROUP[0]
+#endif
+
+#ifndef __cacheline_group_end
+#define __cacheline_group_end(GROUP) \
+	__u8 __cacheline_group_end__##GROUP[0]
+#endif
+
+#ifndef CACHELINE_ASSERT_GROUP_MEMBER
+#define CACHELINE_ASSERT_GROUP_MEMBER(TYPE, GROUP, MEMBER) \
+	BUILD_BUG_ON(!(offsetof(TYPE, MEMBER) >= \
+		       offsetofend(TYPE, __cacheline_group_begin__##GROUP) && \
+		       offsetofend(TYPE, MEMBER) <= \
+		       offsetof(TYPE, __cacheline_group_end__##GROUP)))
+#endif
+
+#ifndef CACHELINE_ASSERT_GROUP_SIZE
+#define CACHELINE_ASSERT_GROUP_SIZE(TYPE, GROUP, SIZE) \
+	BUILD_BUG_ON(offsetof(TYPE, __cacheline_group_end__##GROUP) - \
+		     offsetofend(TYPE, __cacheline_group_begin__##GROUP) > \
+		     SIZE)
+#endif
+
 /*
  * Helper to add padding within a struct to ensure data fall into separate
  * cachelines.
diff --git a/scripts/kernel-doc b/scripts/kernel-doc
index 08a3e603db19..0a890fe4d22b 100755
--- a/scripts/kernel-doc
+++ b/scripts/kernel-doc
@@ -1592,6 +1592,11 @@ sub push_parameter($$$$$) {
 		$parameterdescs{$param} = "anonymous\n";
 		$anon_struct_union = 1;
 	}
+	elsif ($param =~ "__cacheline_group" )
+	# handle cache group enforcing variables: they do not need be described in header files
+	{
+		return; # ignore __cacheline_group_begin and __cacheline_group_end
+	}
 
 	# warn if parameter has no description
 	# (but ignore ones starting with # as these are not parameters
-- 
cgit v1.2.3


From 18fd64d2542292713b0322e6815be059bdee440c Mon Sep 17 00:00:00 2001
From: Coco Li <lixiaoyan@google.com>
Date: Wed, 29 Nov 2023 07:27:54 +0000
Subject: netns-ipv4: reorganize netns_ipv4 fast path variables

Reorganize fast path variables on tx-txrx-rx order.
Fastpath cacheline ends after sysctl_tcp_rmem.
There are only read-only variables here. (write is on the control path
and not considered in this case)

Below data generated with pahole on x86 architecture.
Fast path variables span cache lines before change: 4
Fast path variables span cache lines after change: 2

Suggested-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Wei Wang <weiwan@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Coco Li <lixiaoyan@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netns/ipv4.h | 47 ++++++++++++++++++++++++++++++++---------------
 net/core/net_namespace.c | 45 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 77 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 73f43f699199..ea882964c71e 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -42,6 +42,38 @@ struct inet_timewait_death_row {
 struct tcp_fastopen_context;
 
 struct netns_ipv4 {
+	/* Cacheline organization can be found documented in
+	 * Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst.
+	 * Please update the document when adding new fields.
+	 */
+
+	/* TX readonly hotpath cache lines */
+	__cacheline_group_begin(netns_ipv4_read_tx);
+	u8 sysctl_tcp_early_retrans;
+	u8 sysctl_tcp_tso_win_divisor;
+	u8 sysctl_tcp_tso_rtt_log;
+	u8 sysctl_tcp_autocorking;
+	int sysctl_tcp_min_snd_mss;
+	unsigned int sysctl_tcp_notsent_lowat;
+	int sysctl_tcp_limit_output_bytes;
+	int sysctl_tcp_min_rtt_wlen;
+	int sysctl_tcp_wmem[3];
+	u8 sysctl_ip_fwd_use_pmtu;
+	__cacheline_group_end(netns_ipv4_read_tx);
+
+	/* TXRX readonly hotpath cache lines */
+	__cacheline_group_begin(netns_ipv4_read_txrx);
+	u8 sysctl_tcp_moderate_rcvbuf;
+	__cacheline_group_end(netns_ipv4_read_txrx);
+
+	/* RX readonly hotpath cache line */
+	__cacheline_group_begin(netns_ipv4_read_rx);
+	u8 sysctl_ip_early_demux;
+	u8 sysctl_tcp_early_demux;
+	int sysctl_tcp_reordering;
+	int sysctl_tcp_rmem[3];
+	__cacheline_group_end(netns_ipv4_read_rx);
+
 	struct inet_timewait_death_row tcp_death_row;
 	struct udp_table *udp_table;
 
@@ -96,17 +128,14 @@ struct netns_ipv4 {
 
 	u8 sysctl_ip_default_ttl;
 	u8 sysctl_ip_no_pmtu_disc;
-	u8 sysctl_ip_fwd_use_pmtu;
 	u8 sysctl_ip_fwd_update_priority;
 	u8 sysctl_ip_nonlocal_bind;
 	u8 sysctl_ip_autobind_reuse;
 	/* Shall we try to damage output packets if routing dev changes? */
 	u8 sysctl_ip_dynaddr;
-	u8 sysctl_ip_early_demux;
 #ifdef CONFIG_NET_L3_MASTER_DEV
 	u8 sysctl_raw_l3mdev_accept;
 #endif
-	u8 sysctl_tcp_early_demux;
 	u8 sysctl_udp_early_demux;
 
 	u8 sysctl_nexthop_compat_mode;
@@ -119,7 +148,6 @@ struct netns_ipv4 {
 	u8 sysctl_tcp_mtu_probing;
 	int sysctl_tcp_mtu_probe_floor;
 	int sysctl_tcp_base_mss;
-	int sysctl_tcp_min_snd_mss;
 	int sysctl_tcp_probe_threshold;
 	u32 sysctl_tcp_probe_interval;
 
@@ -135,17 +163,14 @@ struct netns_ipv4 {
 	u8 sysctl_tcp_backlog_ack_defer;
 	u8 sysctl_tcp_pingpong_thresh;
 
-	int sysctl_tcp_reordering;
 	u8 sysctl_tcp_retries1;
 	u8 sysctl_tcp_retries2;
 	u8 sysctl_tcp_orphan_retries;
 	u8 sysctl_tcp_tw_reuse;
 	int sysctl_tcp_fin_timeout;
-	unsigned int sysctl_tcp_notsent_lowat;
 	u8 sysctl_tcp_sack;
 	u8 sysctl_tcp_window_scaling;
 	u8 sysctl_tcp_timestamps;
-	u8 sysctl_tcp_early_retrans;
 	u8 sysctl_tcp_recovery;
 	u8 sysctl_tcp_thin_linear_timeouts;
 	u8 sysctl_tcp_slow_start_after_idle;
@@ -161,21 +186,13 @@ struct netns_ipv4 {
 	u8 sysctl_tcp_frto;
 	u8 sysctl_tcp_nometrics_save;
 	u8 sysctl_tcp_no_ssthresh_metrics_save;
-	u8 sysctl_tcp_moderate_rcvbuf;
-	u8 sysctl_tcp_tso_win_divisor;
 	u8 sysctl_tcp_workaround_signed_windows;
-	int sysctl_tcp_limit_output_bytes;
 	int sysctl_tcp_challenge_ack_limit;
-	int sysctl_tcp_min_rtt_wlen;
 	u8 sysctl_tcp_min_tso_segs;
-	u8 sysctl_tcp_tso_rtt_log;
-	u8 sysctl_tcp_autocorking;
 	u8 sysctl_tcp_reflect_tos;
 	int sysctl_tcp_invalid_ratelimit;
 	int sysctl_tcp_pacing_ss_ratio;
 	int sysctl_tcp_pacing_ca_ratio;
-	int sysctl_tcp_wmem[3];
-	int sysctl_tcp_rmem[3];
 	unsigned int sysctl_tcp_child_ehash_entries;
 	unsigned long sysctl_tcp_comp_sack_delay_ns;
 	unsigned long sysctl_tcp_comp_sack_slack_ns;
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index f4183c4c1ec8..cb8bcbff9e83 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -1099,11 +1099,56 @@ out:
 	rtnl_set_sk_err(net, RTNLGRP_NSID, err);
 }
 
+#ifdef CONFIG_NET_NS
+static void __init netns_ipv4_struct_check(void)
+{
+	/* TX readonly hotpath cache lines */
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx,
+				      sysctl_tcp_early_retrans);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx,
+				      sysctl_tcp_tso_win_divisor);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx,
+				      sysctl_tcp_tso_rtt_log);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx,
+				      sysctl_tcp_autocorking);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx,
+				      sysctl_tcp_min_snd_mss);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx,
+				      sysctl_tcp_notsent_lowat);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx,
+				      sysctl_tcp_limit_output_bytes);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx,
+				      sysctl_tcp_min_rtt_wlen);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx,
+				      sysctl_tcp_wmem);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx,
+				      sysctl_ip_fwd_use_pmtu);
+	CACHELINE_ASSERT_GROUP_SIZE(struct netns_ipv4, netns_ipv4_read_tx, 33);
+
+	/* TXRX readonly hotpath cache lines */
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_txrx,
+				      sysctl_tcp_moderate_rcvbuf);
+	CACHELINE_ASSERT_GROUP_SIZE(struct netns_ipv4, netns_ipv4_read_txrx, 1);
+
+	/* RX readonly hotpath cache line */
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx,
+				      sysctl_ip_early_demux);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx,
+				      sysctl_tcp_early_demux);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx,
+				      sysctl_tcp_reordering);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx,
+				      sysctl_tcp_rmem);
+	CACHELINE_ASSERT_GROUP_SIZE(struct netns_ipv4, netns_ipv4_read_rx, 18);
+}
+#endif
+
 void __init net_ns_init(void)
 {
 	struct net_generic *ng;
 
 #ifdef CONFIG_NET_NS
+	netns_ipv4_struct_check();
 	net_cachep = kmem_cache_create("net_namespace", sizeof(struct net),
 					SMP_CACHE_BYTES,
 					SLAB_PANIC|SLAB_ACCOUNT, NULL);
-- 
cgit v1.2.3


From 18c74d56fe6070c7c38058d7b43ccf2102abebcd Mon Sep 17 00:00:00 2001
From: Luca Weiss <luca.weiss@fairphone.com>
Date: Fri, 13 Oct 2023 10:09:53 +0200
Subject: iio: adc: Add PM7325 PMIC7 ADC bindings

Add the defines for the ADC channels found on the PM7325. The list is
taken from downstream msm-5.4 and adjusted for mainline.

Signed-off-by: Luca Weiss <luca.weiss@fairphone.com>
Acked-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Link: https://lore.kernel.org/r/20231013-fp5-thermals-v1-1-f14df01922e6@fairphone.com
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 include/dt-bindings/iio/qcom,spmi-adc7-pm7325.h | 69 +++++++++++++++++++++++++
 1 file changed, 69 insertions(+)
 create mode 100644 include/dt-bindings/iio/qcom,spmi-adc7-pm7325.h

(limited to 'include')

diff --git a/include/dt-bindings/iio/qcom,spmi-adc7-pm7325.h b/include/dt-bindings/iio/qcom,spmi-adc7-pm7325.h
new file mode 100644
index 000000000000..96908014e09e
--- /dev/null
+++ b/include/dt-bindings/iio/qcom,spmi-adc7-pm7325.h
@@ -0,0 +1,69 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2020 The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _DT_BINDINGS_QCOM_SPMI_VADC_PM7325_H
+#define _DT_BINDINGS_QCOM_SPMI_VADC_PM7325_H
+
+#ifndef PM7325_SID
+#define PM7325_SID					1
+#endif
+
+#include <dt-bindings/iio/qcom,spmi-vadc.h>
+
+/* ADC channels for PM7325_ADC for PMIC7 */
+#define PM7325_ADC7_REF_GND			(PM7325_SID << 8 | ADC7_REF_GND)
+#define PM7325_ADC7_1P25VREF			(PM7325_SID << 8 | ADC7_1P25VREF)
+#define PM7325_ADC7_VREF_VADC			(PM7325_SID << 8 | ADC7_VREF_VADC)
+#define PM7325_ADC7_DIE_TEMP			(PM7325_SID << 8 | ADC7_DIE_TEMP)
+
+#define PM7325_ADC7_AMUX_THM1			(PM7325_SID << 8 | ADC7_AMUX_THM1)
+#define PM7325_ADC7_AMUX_THM2			(PM7325_SID << 8 | ADC7_AMUX_THM2)
+#define PM7325_ADC7_AMUX_THM3			(PM7325_SID << 8 | ADC7_AMUX_THM3)
+#define PM7325_ADC7_AMUX_THM4			(PM7325_SID << 8 | ADC7_AMUX_THM4)
+#define PM7325_ADC7_AMUX_THM5			(PM7325_SID << 8 | ADC7_AMUX_THM5)
+#define PM7325_ADC7_GPIO1			(PM7325_SID << 8 | ADC7_GPIO1)
+#define PM7325_ADC7_GPIO2			(PM7325_SID << 8 | ADC7_GPIO2)
+#define PM7325_ADC7_GPIO3			(PM7325_SID << 8 | ADC7_GPIO3)
+#define PM7325_ADC7_GPIO4			(PM7325_SID << 8 | ADC7_GPIO4)
+
+/* 30k pull-up1 */
+#define PM7325_ADC7_AMUX_THM1_30K_PU		(PM7325_SID << 8 | ADC7_AMUX_THM1_30K_PU)
+#define PM7325_ADC7_AMUX_THM2_30K_PU		(PM7325_SID << 8 | ADC7_AMUX_THM2_30K_PU)
+#define PM7325_ADC7_AMUX_THM3_30K_PU		(PM7325_SID << 8 | ADC7_AMUX_THM3_30K_PU)
+#define PM7325_ADC7_AMUX_THM4_30K_PU		(PM7325_SID << 8 | ADC7_AMUX_THM4_30K_PU)
+#define PM7325_ADC7_AMUX_THM5_30K_PU		(PM7325_SID << 8 | ADC7_AMUX_THM5_30K_PU)
+#define PM7325_ADC7_GPIO1_30K_PU		(PM7325_SID << 8 | ADC7_GPIO1_30K_PU)
+#define PM7325_ADC7_GPIO2_30K_PU		(PM7325_SID << 8 | ADC7_GPIO2_30K_PU)
+#define PM7325_ADC7_GPIO3_30K_PU		(PM7325_SID << 8 | ADC7_GPIO3_30K_PU)
+#define PM7325_ADC7_GPIO4_30K_PU		(PM7325_SID << 8 | ADC7_GPIO4_30K_PU)
+
+/* 100k pull-up2 */
+#define PM7325_ADC7_AMUX_THM1_100K_PU		(PM7325_SID << 8 | ADC7_AMUX_THM1_100K_PU)
+#define PM7325_ADC7_AMUX_THM2_100K_PU		(PM7325_SID << 8 | ADC7_AMUX_THM2_100K_PU)
+#define PM7325_ADC7_AMUX_THM3_100K_PU		(PM7325_SID << 8 | ADC7_AMUX_THM3_100K_PU)
+#define PM7325_ADC7_AMUX_THM4_100K_PU		(PM7325_SID << 8 | ADC7_AMUX_THM4_100K_PU)
+#define PM7325_ADC7_AMUX_THM5_100K_PU		(PM7325_SID << 8 | ADC7_AMUX_THM5_100K_PU)
+#define PM7325_ADC7_GPIO1_100K_PU		(PM7325_SID << 8 | ADC7_GPIO1_100K_PU)
+#define PM7325_ADC7_GPIO2_100K_PU		(PM7325_SID << 8 | ADC7_GPIO2_100K_PU)
+#define PM7325_ADC7_GPIO3_100K_PU		(PM7325_SID << 8 | ADC7_GPIO3_100K_PU)
+#define PM7325_ADC7_GPIO4_100K_PU		(PM7325_SID << 8 | ADC7_GPIO4_100K_PU)
+
+/* 400k pull-up3 */
+#define PM7325_ADC7_AMUX_THM1_400K_PU		(PM7325_SID << 8 | ADC7_AMUX_THM1_400K_PU)
+#define PM7325_ADC7_AMUX_THM2_400K_PU		(PM7325_SID << 8 | ADC7_AMUX_THM2_400K_PU)
+#define PM7325_ADC7_AMUX_THM3_400K_PU		(PM7325_SID << 8 | ADC7_AMUX_THM3_400K_PU)
+#define PM7325_ADC7_AMUX_THM4_400K_PU		(PM7325_SID << 8 | ADC7_AMUX_THM4_400K_PU)
+#define PM7325_ADC7_AMUX_THM5_400K_PU		(PM7325_SID << 8 | ADC7_AMUX_THM5_400K_PU)
+#define PM7325_ADC7_GPIO1_400K_PU		(PM7325_SID << 8 | ADC7_GPIO1_400K_PU)
+#define PM7325_ADC7_GPIO2_400K_PU		(PM7325_SID << 8 | ADC7_GPIO2_400K_PU)
+#define PM7325_ADC7_GPIO3_400K_PU		(PM7325_SID << 8 | ADC7_GPIO3_400K_PU)
+#define PM7325_ADC7_GPIO4_400K_PU		(PM7325_SID << 8 | ADC7_GPIO4_400K_PU)
+
+/* 1/3 Divider */
+#define PM7325_ADC7_GPIO4_DIV3			(PM7325_SID << 8 | ADC7_GPIO4_DIV3)
+
+#define PM7325_ADC7_VPH_PWR			(PM7325_SID << 8 | ADC7_VPH_PWR)
+
+#endif /* _DT_BINDINGS_QCOM_SPMI_VADC_PM7325_H */
-- 
cgit v1.2.3


From c55e0a55b165202f18cbc4a20650d2e1becd5507 Mon Sep 17 00:00:00 2001
From: Tyler Fanelli <tfanelli@redhat.com>
Date: Tue, 19 Sep 2023 22:40:00 -0400
Subject: fuse: Rename DIRECT_IO_RELAX to DIRECT_IO_ALLOW_MMAP

Although DIRECT_IO_RELAX's initial usage is to allow shared mmap, its
description indicates a purpose of reducing memory footprint. This
may imply that it could be further used to relax other DIRECT_IO
operations in the future.

Replace it with a flag DIRECT_IO_ALLOW_MMAP which does only one thing,
allow shared mmap of DIRECT_IO files while still bypassing the cache
on regular reads and writes.

[Miklos] Also Keep DIRECT_IO_RELAX definition for backward compatibility.

Signed-off-by: Tyler Fanelli <tfanelli@redhat.com>
Fixes: e78662e818f9 ("fuse: add a new fuse init flag to relax restrictions in no cache mode")
Cc: <stable@vger.kernel.org> # v6.6
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/file.c            |  6 +++---
 fs/fuse/fuse_i.h          |  4 ++--
 fs/fuse/inode.c           |  6 +++---
 include/uapi/linux/fuse.h | 10 ++++++----
 4 files changed, 14 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 1cdb6327511e..89e870d1a526 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1448,7 +1448,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
 	if (!ia)
 		return -ENOMEM;
 
-	if (fopen_direct_io && fc->direct_io_relax) {
+	if (fopen_direct_io && fc->direct_io_allow_mmap) {
 		res = filemap_write_and_wait_range(mapping, pos, pos + count - 1);
 		if (res) {
 			fuse_io_free(ia);
@@ -2466,9 +2466,9 @@ static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma)
 
 	if (ff->open_flags & FOPEN_DIRECT_IO) {
 		/* Can't provide the coherency needed for MAP_SHARED
-		 * if FUSE_DIRECT_IO_RELAX isn't set.
+		 * if FUSE_DIRECT_IO_ALLOW_MMAP isn't set.
 		 */
-		if ((vma->vm_flags & VM_MAYSHARE) && !fc->direct_io_relax)
+		if ((vma->vm_flags & VM_MAYSHARE) && !fc->direct_io_allow_mmap)
 			return -ENODEV;
 
 		invalidate_inode_pages2(file->f_mapping);
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 6e6e721f421b..69bcffaf4832 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -797,8 +797,8 @@ struct fuse_conn {
 	/* Is tmpfile not implemented by fs? */
 	unsigned int no_tmpfile:1;
 
-	/* relax restrictions in FOPEN_DIRECT_IO mode */
-	unsigned int direct_io_relax:1;
+	/* Relax restrictions to allow shared mmap in FOPEN_DIRECT_IO mode */
+	unsigned int direct_io_allow_mmap:1;
 
 	/* Is statx not implemented by fs? */
 	unsigned int no_statx:1;
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 74d4f09d5827..88090c6026a7 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -1230,8 +1230,8 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args,
 				fc->init_security = 1;
 			if (flags & FUSE_CREATE_SUPP_GROUP)
 				fc->create_supp_group = 1;
-			if (flags & FUSE_DIRECT_IO_RELAX)
-				fc->direct_io_relax = 1;
+			if (flags & FUSE_DIRECT_IO_ALLOW_MMAP)
+				fc->direct_io_allow_mmap = 1;
 		} else {
 			ra_pages = fc->max_read / PAGE_SIZE;
 			fc->no_lock = 1;
@@ -1278,7 +1278,7 @@ void fuse_send_init(struct fuse_mount *fm)
 		FUSE_NO_OPENDIR_SUPPORT | FUSE_EXPLICIT_INVAL_DATA |
 		FUSE_HANDLE_KILLPRIV_V2 | FUSE_SETXATTR_EXT | FUSE_INIT_EXT |
 		FUSE_SECURITY_CTX | FUSE_CREATE_SUPP_GROUP |
-		FUSE_HAS_EXPIRE_ONLY | FUSE_DIRECT_IO_RELAX;
+		FUSE_HAS_EXPIRE_ONLY | FUSE_DIRECT_IO_ALLOW_MMAP;
 #ifdef CONFIG_FUSE_DAX
 	if (fm->fc->dax)
 		flags |= FUSE_MAP_ALIGNMENT;
diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h
index db92a7202b34..e7418d15fe39 100644
--- a/include/uapi/linux/fuse.h
+++ b/include/uapi/linux/fuse.h
@@ -209,7 +209,7 @@
  *  - add FUSE_HAS_EXPIRE_ONLY
  *
  *  7.39
- *  - add FUSE_DIRECT_IO_RELAX
+ *  - add FUSE_DIRECT_IO_ALLOW_MMAP
  *  - add FUSE_STATX and related structures
  */
 
@@ -409,8 +409,7 @@ struct fuse_file_lock {
  * FUSE_CREATE_SUPP_GROUP: add supplementary group info to create, mkdir,
  *			symlink and mknod (single group that matches parent)
  * FUSE_HAS_EXPIRE_ONLY: kernel supports expiry-only entry invalidation
- * FUSE_DIRECT_IO_RELAX: relax restrictions in FOPEN_DIRECT_IO mode, for now
- *                       allow shared mmap
+ * FUSE_DIRECT_IO_ALLOW_MMAP: allow shared mmap in FOPEN_DIRECT_IO mode.
  */
 #define FUSE_ASYNC_READ		(1 << 0)
 #define FUSE_POSIX_LOCKS	(1 << 1)
@@ -449,7 +448,10 @@ struct fuse_file_lock {
 #define FUSE_HAS_INODE_DAX	(1ULL << 33)
 #define FUSE_CREATE_SUPP_GROUP	(1ULL << 34)
 #define FUSE_HAS_EXPIRE_ONLY	(1ULL << 35)
-#define FUSE_DIRECT_IO_RELAX	(1ULL << 36)
+#define FUSE_DIRECT_IO_ALLOW_MMAP (1ULL << 36)
+
+/* Obsolete alias for FUSE_DIRECT_IO_ALLOW_MMAP */
+#define FUSE_DIRECT_IO_RELAX	FUSE_DIRECT_IO_ALLOW_MMAP
 
 /**
  * CUSE INIT request/reply flags
-- 
cgit v1.2.3


From a9c8c738066b7ba9e208cfc3200a6f60593982b4 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Mon, 6 Nov 2023 09:31:41 +0200
Subject: device property: Add fwnode_name_eq()

Add fwnode_name_eq() to implement the functionality of of_node_name_eq()
on fwnode property API. The same convention of ending the comparison at
'@' (besides NUL) is applied on also both ACPI and swnode. The function
is intended for comparing unit address-less node names on DT and firmware
or swnodes compliant with DT bindings.

Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Tested-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Acked-by: Rafael J. Wysocki <rafael@kernel.org>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
---
 drivers/base/property.c  | 28 ++++++++++++++++++++++++++++
 include/linux/property.h |  1 +
 2 files changed, 29 insertions(+)

(limited to 'include')

diff --git a/drivers/base/property.c b/drivers/base/property.c
index 8c40abed7852..b79608ee0b46 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -594,6 +594,34 @@ const char *fwnode_get_name_prefix(const struct fwnode_handle *fwnode)
 	return fwnode_call_ptr_op(fwnode, get_name_prefix);
 }
 
+/**
+ * fwnode_name_eq - Return true if node name is equal
+ * @fwnode: The firmware node
+ * @name: The name to which to compare the node name
+ *
+ * Compare the name provided as an argument to the name of the node, stopping
+ * the comparison at either NUL or '@' character, whichever comes first. This
+ * function is generally used for comparing node names while ignoring the
+ * possible unit address of the node.
+ *
+ * Return: true if the node name matches with the name provided in the @name
+ * argument, false otherwise.
+ */
+bool fwnode_name_eq(const struct fwnode_handle *fwnode, const char *name)
+{
+	const char *node_name;
+	ptrdiff_t len;
+
+	node_name = fwnode_get_name(fwnode);
+	if (!node_name)
+		return false;
+
+	len = strchrnul(node_name, '@') - node_name;
+
+	return str_has_prefix(node_name, name) == len;
+}
+EXPORT_SYMBOL_GPL(fwnode_name_eq);
+
 /**
  * fwnode_get_parent - Return parent firwmare node
  * @fwnode: Firmware whose parent is retrieved
diff --git a/include/linux/property.h b/include/linux/property.h
index 9f2585d705a8..4ebbb169df20 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -109,6 +109,7 @@ struct fwnode_handle *fwnode_find_reference(const struct fwnode_handle *fwnode,
 
 const char *fwnode_get_name(const struct fwnode_handle *fwnode);
 const char *fwnode_get_name_prefix(const struct fwnode_handle *fwnode);
+bool fwnode_name_eq(const struct fwnode_handle *fwnode, const char *name);
 
 struct fwnode_handle *fwnode_get_parent(const struct fwnode_handle *fwnode);
 struct fwnode_handle *fwnode_get_next_parent(struct fwnode_handle *fwnode);
-- 
cgit v1.2.3


From 0d9e32a8075a6cccbab294f98ccf7d33821d9b1c Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Date: Fri, 24 Nov 2023 16:26:24 +0200
Subject: media: uapi: Add controls for the THP7312 ISP

The THP7312 is an external ISP from THine. As such, it implements a
large number of parameters to control all aspects of the image
processing. Many of those controls are already standard in V4L2, but
some are fairly device-specific.

Reserve a range of 32 controls for the device. The driver will implement
4 device-specific controls to start with, define and document them. 28
additional device-specific controls should be enough for future
development.

Co-developed-by: Paul Elder <paul.elder@ideasonboard.com>
Signed-off-by: Paul Elder <paul.elder@ideasonboard.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
---
 .../userspace-api/media/drivers/index.rst          |  1 +
 .../userspace-api/media/drivers/thp7312.rst        | 39 ++++++++++++++++++++++
 MAINTAINERS                                        |  2 ++
 include/uapi/linux/thp7312.h                       | 19 +++++++++++
 include/uapi/linux/v4l2-controls.h                 |  6 ++++
 5 files changed, 67 insertions(+)
 create mode 100644 Documentation/userspace-api/media/drivers/thp7312.rst
 create mode 100644 include/uapi/linux/thp7312.h

(limited to 'include')

diff --git a/Documentation/userspace-api/media/drivers/index.rst b/Documentation/userspace-api/media/drivers/index.rst
index 1726f8ec86fa..6b62c818899f 100644
--- a/Documentation/userspace-api/media/drivers/index.rst
+++ b/Documentation/userspace-api/media/drivers/index.rst
@@ -41,4 +41,5 @@ For more details see the file COPYING in the source distribution of Linux.
 	npcm-video
 	omap3isp-uapi
 	st-vgxy61
+	thp7312
 	uvcvideo
diff --git a/Documentation/userspace-api/media/drivers/thp7312.rst b/Documentation/userspace-api/media/drivers/thp7312.rst
new file mode 100644
index 000000000000..7c777e6fb7d2
--- /dev/null
+++ b/Documentation/userspace-api/media/drivers/thp7312.rst
@@ -0,0 +1,39 @@
+.. SPDX-License-Identifier: GPL-2.0-only
+
+THine THP7312 ISP driver
+========================
+
+The THP7312 driver implements the following driver-specific controls:
+
+``V4L2_CID_THP7312_LOW_LIGHT_COMPENSATION``
+    Enable/Disable auto-adjustment, based on lighting conditions, of the frame
+    rate when auto-exposure is enabled.
+
+``V4L2_CID_THP7312_AUTO_FOCUS_METHOD``
+    Set method of auto-focus. Only takes effect when auto-focus is enabled.
+
+    .. flat-table::
+        :header-rows:  0
+        :stub-columns: 0
+        :widths:       1 4
+
+        * - ``0``
+          - Contrast-based auto-focus
+        * - ``1``
+          - PDAF
+        * - ``2``
+          - Hybrid of contrast-based and PDAF
+
+    Supported values for the control depend on the camera sensor module
+    connected to the THP7312. If the module doesn't have a focus lens actuator,
+    this control will not be exposed by the THP7312 driver. If the module has a
+    controllable focus lens but the sensor doesn't support PDAF, only the
+    contrast-based auto-focus value will be valid. Otherwise all values for the
+    controls will be supported.
+
+``V4L2_CID_THP7312_NOISE_REDUCTION_AUTO``
+    Enable/Disable auto noise reduction.
+
+``V4L2_CID_THP7312_NOISE_REDUCTION_ABSOLUTE``
+    Set the noise reduction strength, where 0 is the weakest and 10 is the
+    strongest.
diff --git a/MAINTAINERS b/MAINTAINERS
index 6d20dc6f617c..c4468f6a4cb2 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -21670,6 +21670,8 @@ L:	linux-media@vger.kernel.org
 S:	Maintained
 T:	git git://linuxtv.org/media_tree.git
 F:	Documentation/devicetree/bindings/media/i2c/thine,thp7312.yaml
+F:	Documentation/userspace-api/media/drivers/thp7312.rst
+F:	include/uapi/linux/thp7312.h
 
 THUNDERBOLT DMA TRAFFIC TEST DRIVER
 M:	Isaac Hazan <isaac.hazan@intel.com>
diff --git a/include/uapi/linux/thp7312.h b/include/uapi/linux/thp7312.h
new file mode 100644
index 000000000000..2b629e05daf9
--- /dev/null
+++ b/include/uapi/linux/thp7312.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
+/*
+ * THine THP7312 user space header file.
+ *
+ * Copyright (C) 2021 THine Electronics, Inc.
+ * Copyright (C) 2023 Ideas on Board Oy
+ */
+
+#ifndef __UAPI_THP7312_H_
+#define __UAPI_THP7312_H_
+
+#include <linux/v4l2-controls.h>
+
+#define V4L2_CID_THP7312_LOW_LIGHT_COMPENSATION		(V4L2_CID_USER_THP7312_BASE + 0x01)
+#define V4L2_CID_THP7312_AUTO_FOCUS_METHOD		(V4L2_CID_USER_THP7312_BASE + 0x02)
+#define V4L2_CID_THP7312_NOISE_REDUCTION_AUTO		(V4L2_CID_USER_THP7312_BASE + 0x03)
+#define V4L2_CID_THP7312_NOISE_REDUCTION_ABSOLUTE	(V4L2_CID_USER_THP7312_BASE + 0x04)
+
+#endif /* __UAPI_THP7312_H_ */
diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h
index 68db66d4aae8..99c3f5e99da7 100644
--- a/include/uapi/linux/v4l2-controls.h
+++ b/include/uapi/linux/v4l2-controls.h
@@ -209,6 +209,12 @@ enum v4l2_colorfx {
  */
 #define V4L2_CID_USER_NPCM_BASE			(V4L2_CID_USER_BASE + 0x11b0)
 
+/*
+ * The base for THine THP7312 driver controls.
+ * We reserve 32 controls for this driver.
+ */
+#define V4L2_CID_USER_THP7312_BASE		(V4L2_CID_USER_BASE + 0x11c0)
+
 /* MPEG-class control IDs */
 /* The MPEG controls are applicable to all codec controls
  * and the 'MPEG' part of the define is historical */
-- 
cgit v1.2.3


From 5755be5f15d9e651ed433e5dbf7b7b968efb3064 Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Date: Mon, 27 Nov 2023 11:07:44 +0200
Subject: media: v4l2-subdev: Rename .init_cfg() operation to .init_state()

The subdev .init_cfg() operation is affected by two issues:

- It has long been extended to initialize a whole v4l2_subdev_state
  instead of just a v4l2_subdev_pad_config, but its name has stuck
  around.

- Despite operating on a whole subdev state and not being directly
  exposed to the subdev users (either in-kernel or through the userspace
  API), .init_cfg() is categorized as a subdev pad operation.

This participates in making the subdev API confusing for new developers.
Fix it by renaming the operation to .init_state(), and make it a subdev
internal operation.

Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Acked-by: Michael Riesch <michael.riesch@wolfvision.net> # for imx415
Acked-by: Shuah Khan <skhan@linuxfoundation.org> # for vimc
Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de>
Reviewed-by: Tomi Valkeinen <tomi.valkeinen@ideasonboard.com>
[Sakari Ailus: Resolved a conflict in Renesas vsp1 driver.]
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
---
 drivers/media/i2c/adv7180.c                        | 10 ++--
 drivers/media/i2c/ccs/ccs-core.c                   |  6 +--
 drivers/media/i2c/ds90ub913.c                      | 10 ++--
 drivers/media/i2c/ds90ub953.c                      | 10 ++--
 drivers/media/i2c/ds90ub960.c                      | 11 +++--
 drivers/media/i2c/gc2145.c                         | 10 ++--
 drivers/media/i2c/hi846.c                          | 10 ++--
 drivers/media/i2c/imx214.c                         | 12 +++--
 drivers/media/i2c/imx219.c                         |  9 ++--
 drivers/media/i2c/imx290.c                         | 10 ++--
 drivers/media/i2c/imx296.c                         | 10 ++--
 drivers/media/i2c/imx334.c                         | 12 +++--
 drivers/media/i2c/imx335.c                         | 12 +++--
 drivers/media/i2c/imx412.c                         | 12 +++--
 drivers/media/i2c/imx415.c                         | 10 ++--
 drivers/media/i2c/mt9m001.c                        | 10 ++--
 drivers/media/i2c/mt9m111.c                        | 10 ++--
 drivers/media/i2c/mt9m114.c                        | 16 ++++---
 drivers/media/i2c/mt9p031.c                        |  8 ++--
 drivers/media/i2c/mt9v111.c                        | 10 ++--
 drivers/media/i2c/ov01a10.c                        | 10 ++--
 drivers/media/i2c/ov02a10.c                        | 10 ++--
 drivers/media/i2c/ov2640.c                         | 10 ++--
 drivers/media/i2c/ov2680.c                         | 10 ++--
 drivers/media/i2c/ov2740.c                         | 10 ++--
 drivers/media/i2c/ov5640.c                         | 10 ++--
 drivers/media/i2c/ov5645.c                         | 12 +++--
 drivers/media/i2c/ov5670.c                         | 10 ++--
 drivers/media/i2c/ov7251.c                         | 12 +++--
 drivers/media/i2c/ov8858.c                         | 10 ++--
 drivers/media/i2c/ov9282.c                         | 12 +++--
 drivers/media/i2c/st-vgxy61.c                      | 10 ++--
 drivers/media/i2c/tc358746.c                       | 10 ++--
 drivers/media/i2c/tda1997x.c                       | 10 ++--
 drivers/media/i2c/thp7312.c                        | 10 ++--
 drivers/media/i2c/tvp5150.c                        |  6 +--
 drivers/media/pci/intel/ivsc/mei_csi.c             | 10 ++--
 drivers/media/platform/cadence/cdns-csi2rx.c       | 10 ++--
 .../media/platform/microchip/microchip-csi2dc.c    | 10 ++--
 .../platform/microchip/microchip-isc-scaler.c      | 10 ++--
 drivers/media/platform/nxp/imx-mipi-csis.c         | 10 ++--
 drivers/media/platform/nxp/imx7-media-csi.c        |  6 +--
 .../platform/nxp/imx8-isi/imx8-isi-crossbar.c      | 10 ++--
 .../media/platform/nxp/imx8-isi/imx8-isi-pipe.c    | 10 ++--
 drivers/media/platform/nxp/imx8mq-mipi-csi2.c      | 10 ++--
 .../media/platform/renesas/rzg2l-cru/rzg2l-csi2.c  | 10 ++--
 .../media/platform/renesas/rzg2l-cru/rzg2l-ip.c    | 10 ++--
 drivers/media/platform/renesas/vsp1/vsp1_brx.c     |  1 -
 drivers/media/platform/renesas/vsp1/vsp1_clu.c     |  1 -
 drivers/media/platform/renesas/vsp1/vsp1_entity.c  | 53 ++++++++++------------
 drivers/media/platform/renesas/vsp1/vsp1_entity.h  |  2 -
 drivers/media/platform/renesas/vsp1/vsp1_hsit.c    |  1 -
 drivers/media/platform/renesas/vsp1/vsp1_lif.c     |  1 -
 drivers/media/platform/renesas/vsp1/vsp1_lut.c     |  1 -
 drivers/media/platform/renesas/vsp1/vsp1_rwpf.c    |  1 -
 drivers/media/platform/renesas/vsp1/vsp1_sru.c     |  1 -
 drivers/media/platform/renesas/vsp1/vsp1_uds.c     |  1 -
 drivers/media/platform/renesas/vsp1/vsp1_uif.c     |  1 -
 .../media/platform/rockchip/rkisp1/rkisp1-csi.c    | 10 ++--
 .../media/platform/rockchip/rkisp1/rkisp1-isp.c    | 10 ++--
 .../platform/rockchip/rkisp1/rkisp1-resizer.c      | 10 ++--
 drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c |  1 +
 drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.h |  1 +
 .../media/platform/sunxi/sun4i-csi/sun4i_v4l2.c    |  9 ++--
 .../platform/sunxi/sun6i-csi/sun6i_csi_bridge.c    | 10 ++--
 .../sunxi/sun6i-mipi-csi2/sun6i_mipi_csi2.c        | 10 ++--
 .../sun8i-a83t-mipi-csi2/sun8i_a83t_mipi_csi2.c    | 10 ++--
 drivers/media/platform/ti/cal/cal-camerarx.c       | 10 ++--
 drivers/media/platform/video-mux.c                 | 10 ++--
 drivers/media/platform/xilinx/xilinx-csi2rxss.c    | 10 ++--
 drivers/media/test-drivers/vimc/vimc-debayer.c     | 11 +++--
 drivers/media/test-drivers/vimc/vimc-scaler.c      | 11 +++--
 drivers/media/test-drivers/vimc/vimc-sensor.c      | 11 +++--
 drivers/media/v4l2-core/v4l2-subdev.c              | 20 ++++----
 drivers/staging/media/imx/imx-ic-prp.c             |  2 +-
 drivers/staging/media/imx/imx-ic-prpencvf.c        |  2 +-
 drivers/staging/media/imx/imx-media-csi.c          |  2 +-
 drivers/staging/media/imx/imx-media-utils.c        |  8 ++--
 drivers/staging/media/imx/imx-media-vdic.c         |  2 +-
 drivers/staging/media/imx/imx-media.h              |  4 +-
 drivers/staging/media/imx/imx6-mipi-csi2.c         |  2 +-
 drivers/staging/media/starfive/camss/stf-isp.c     |  6 ++-
 .../staging/media/sunxi/sun6i-isp/sun6i_isp_proc.c | 10 ++--
 include/media/v4l2-subdev.h                        |  7 +--
 84 files changed, 481 insertions(+), 258 deletions(-)

(limited to 'include')

diff --git a/drivers/media/i2c/adv7180.c b/drivers/media/i2c/adv7180.c
index 444c322d756a..e10811cce801 100644
--- a/drivers/media/i2c/adv7180.c
+++ b/drivers/media/i2c/adv7180.c
@@ -813,8 +813,8 @@ static int adv7180_set_pad_format(struct v4l2_subdev *sd,
 	return ret;
 }
 
-static int adv7180_init_cfg(struct v4l2_subdev *sd,
-			    struct v4l2_subdev_state *sd_state)
+static int adv7180_init_state(struct v4l2_subdev *sd,
+			      struct v4l2_subdev_state *sd_state)
 {
 	struct v4l2_subdev_format fmt = {
 		.which = sd_state ? V4L2_SUBDEV_FORMAT_TRY
@@ -929,7 +929,6 @@ static const struct v4l2_subdev_core_ops adv7180_core_ops = {
 };
 
 static const struct v4l2_subdev_pad_ops adv7180_pad_ops = {
-	.init_cfg = adv7180_init_cfg,
 	.enum_mbus_code = adv7180_enum_mbus_code,
 	.set_fmt = adv7180_set_pad_format,
 	.get_fmt = adv7180_get_pad_format,
@@ -947,6 +946,10 @@ static const struct v4l2_subdev_ops adv7180_ops = {
 	.sensor = &adv7180_sensor_ops,
 };
 
+static const struct v4l2_subdev_internal_ops adv7180_internal_ops = {
+	.init_state = adv7180_init_state,
+};
+
 static irqreturn_t adv7180_irq(int irq, void *devid)
 {
 	struct adv7180_state *state = devid;
@@ -1458,6 +1461,7 @@ static int adv7180_probe(struct i2c_client *client)
 	state->input = 0;
 	sd = &state->sd;
 	v4l2_i2c_subdev_init(sd, client, &adv7180_ops);
+	sd->internal_ops = &adv7180_internal_ops;
 	sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE | V4L2_SUBDEV_FL_HAS_EVENTS;
 
 	ret = adv7180_init_controls(state);
diff --git a/drivers/media/i2c/ccs/ccs-core.c b/drivers/media/i2c/ccs/ccs-core.c
index fb713b03ad4a..92ef98a2b951 100644
--- a/drivers/media/i2c/ccs/ccs-core.c
+++ b/drivers/media/i2c/ccs/ccs-core.c
@@ -3006,8 +3006,8 @@ static int ccs_init_subdev(struct ccs_sensor *sensor,
 	return 0;
 }
 
-static int ccs_init_cfg(struct v4l2_subdev *sd,
-			struct v4l2_subdev_state *sd_state)
+static int ccs_init_state(struct v4l2_subdev *sd,
+			  struct v4l2_subdev_state *sd_state)
 {
 	struct ccs_subdev *ssd = to_ccs_subdev(sd);
 	struct ccs_sensor *sensor = ssd->sensor;
@@ -3055,7 +3055,6 @@ static const struct v4l2_subdev_video_ops ccs_video_ops = {
 };
 
 static const struct v4l2_subdev_pad_ops ccs_pad_ops = {
-	.init_cfg = ccs_init_cfg,
 	.enum_mbus_code = ccs_enum_mbus_code,
 	.get_fmt = ccs_get_format,
 	.set_fmt = ccs_set_format,
@@ -3079,6 +3078,7 @@ static const struct media_entity_operations ccs_entity_ops = {
 };
 
 static const struct v4l2_subdev_internal_ops ccs_internal_src_ops = {
+	.init_state = ccs_init_state,
 	.registered = ccs_registered,
 	.unregistered = ccs_unregistered,
 };
diff --git a/drivers/media/i2c/ds90ub913.c b/drivers/media/i2c/ds90ub913.c
index 8bb6be956780..ca9bb29dab89 100644
--- a/drivers/media/i2c/ds90ub913.c
+++ b/drivers/media/i2c/ds90ub913.c
@@ -443,8 +443,8 @@ static int ub913_set_fmt(struct v4l2_subdev *sd,
 	return 0;
 }
 
-static int ub913_init_cfg(struct v4l2_subdev *sd,
-			  struct v4l2_subdev_state *state)
+static int ub913_init_state(struct v4l2_subdev *sd,
+			    struct v4l2_subdev_state *state)
 {
 	struct v4l2_subdev_route routes[] = {
 		{
@@ -503,7 +503,6 @@ static const struct v4l2_subdev_pad_ops ub913_pad_ops = {
 	.get_frame_desc = ub913_get_frame_desc,
 	.get_fmt = v4l2_subdev_get_fmt,
 	.set_fmt = ub913_set_fmt,
-	.init_cfg = ub913_init_cfg,
 };
 
 static const struct v4l2_subdev_ops ub913_subdev_ops = {
@@ -511,6 +510,10 @@ static const struct v4l2_subdev_ops ub913_subdev_ops = {
 	.pad = &ub913_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops ub913_internal_ops = {
+	.init_state = ub913_init_state,
+};
+
 static const struct media_entity_operations ub913_entity_ops = {
 	.link_validate = v4l2_subdev_link_validate,
 };
@@ -744,6 +747,7 @@ static int ub913_subdev_init(struct ub913_data *priv)
 	int ret;
 
 	v4l2_i2c_subdev_init(&priv->sd, priv->client, &ub913_subdev_ops);
+	priv->sd.internal_ops = &ub913_internal_ops;
 	priv->sd.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE | V4L2_SUBDEV_FL_STREAMS;
 	priv->sd.entity.function = MEDIA_ENT_F_VID_IF_BRIDGE;
 	priv->sd.entity.ops = &ub913_entity_ops;
diff --git a/drivers/media/i2c/ds90ub953.c b/drivers/media/i2c/ds90ub953.c
index 4eb08e3a31c7..16f88db14981 100644
--- a/drivers/media/i2c/ds90ub953.c
+++ b/drivers/media/i2c/ds90ub953.c
@@ -575,8 +575,8 @@ static int ub953_set_fmt(struct v4l2_subdev *sd,
 	return 0;
 }
 
-static int ub953_init_cfg(struct v4l2_subdev *sd,
-			  struct v4l2_subdev_state *state)
+static int ub953_init_state(struct v4l2_subdev *sd,
+			    struct v4l2_subdev_state *state)
 {
 	struct v4l2_subdev_route routes[] = {
 		{
@@ -713,7 +713,6 @@ static const struct v4l2_subdev_pad_ops ub953_pad_ops = {
 	.get_frame_desc = ub953_get_frame_desc,
 	.get_fmt = v4l2_subdev_get_fmt,
 	.set_fmt = ub953_set_fmt,
-	.init_cfg = ub953_init_cfg,
 };
 
 static const struct v4l2_subdev_core_ops ub953_subdev_core_ops = {
@@ -727,6 +726,10 @@ static const struct v4l2_subdev_ops ub953_subdev_ops = {
 	.pad = &ub953_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops ub953_internal_ops = {
+	.init_state = ub953_init_state,
+};
+
 static const struct media_entity_operations ub953_entity_ops = {
 	.link_validate = v4l2_subdev_link_validate,
 };
@@ -1240,6 +1243,7 @@ static int ub953_subdev_init(struct ub953_data *priv)
 	int ret;
 
 	v4l2_i2c_subdev_init(&priv->sd, priv->client, &ub953_subdev_ops);
+	priv->sd.internal_ops = &ub953_internal_ops;
 
 	priv->sd.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE |
 			  V4L2_SUBDEV_FL_HAS_EVENTS | V4L2_SUBDEV_FL_STREAMS;
diff --git a/drivers/media/i2c/ds90ub960.c b/drivers/media/i2c/ds90ub960.c
index 1d1476098c92..ffe5f25f8647 100644
--- a/drivers/media/i2c/ds90ub960.c
+++ b/drivers/media/i2c/ds90ub960.c
@@ -2906,8 +2906,8 @@ static int ub960_set_fmt(struct v4l2_subdev *sd,
 	return 0;
 }
 
-static int ub960_init_cfg(struct v4l2_subdev *sd,
-			  struct v4l2_subdev_state *state)
+static int ub960_init_state(struct v4l2_subdev *sd,
+			    struct v4l2_subdev_state *state)
 {
 	struct ub960_data *priv = sd_to_ub960(sd);
 
@@ -2938,8 +2938,6 @@ static const struct v4l2_subdev_pad_ops ub960_pad_ops = {
 
 	.get_fmt = v4l2_subdev_get_fmt,
 	.set_fmt = ub960_set_fmt,
-
-	.init_cfg = ub960_init_cfg,
 };
 
 static int ub960_log_status(struct v4l2_subdev *sd)
@@ -3091,6 +3089,10 @@ static const struct v4l2_subdev_core_ops ub960_subdev_core_ops = {
 	.unsubscribe_event = v4l2_event_subdev_unsubscribe,
 };
 
+static const struct v4l2_subdev_internal_ops ub960_internal_ops = {
+	.init_state = ub960_init_state,
+};
+
 static const struct v4l2_subdev_ops ub960_subdev_ops = {
 	.core = &ub960_subdev_core_ops,
 	.pad = &ub960_pad_ops,
@@ -3650,6 +3652,7 @@ static int ub960_create_subdev(struct ub960_data *priv)
 	int ret;
 
 	v4l2_i2c_subdev_init(&priv->sd, priv->client, &ub960_subdev_ops);
+	priv->sd.internal_ops = &ub960_internal_ops;
 
 	v4l2_ctrl_handler_init(&priv->ctrl_handler, 1);
 	priv->sd.ctrl_handler = &priv->ctrl_handler;
diff --git a/drivers/media/i2c/gc2145.c b/drivers/media/i2c/gc2145.c
index 12d3780b5548..bef7b0e056a8 100644
--- a/drivers/media/i2c/gc2145.c
+++ b/drivers/media/i2c/gc2145.c
@@ -653,8 +653,8 @@ static void gc2145_update_pad_format(struct gc2145 *gc2145,
 	fmt->xfer_func = V4L2_XFER_FUNC_DEFAULT;
 }
 
-static int gc2145_init_cfg(struct v4l2_subdev *sd,
-			   struct v4l2_subdev_state *state)
+static int gc2145_init_state(struct v4l2_subdev *sd,
+			     struct v4l2_subdev_state *state)
 {
 	struct gc2145 *gc2145 = to_gc2145(sd);
 	struct v4l2_mbus_framefmt *format;
@@ -1079,7 +1079,6 @@ static const struct v4l2_subdev_video_ops gc2145_video_ops = {
 };
 
 static const struct v4l2_subdev_pad_ops gc2145_pad_ops = {
-	.init_cfg = gc2145_init_cfg,
 	.enum_mbus_code = gc2145_enum_mbus_code,
 	.get_fmt = v4l2_subdev_get_fmt,
 	.set_fmt = gc2145_set_pad_format,
@@ -1093,6 +1092,10 @@ static const struct v4l2_subdev_ops gc2145_subdev_ops = {
 	.pad = &gc2145_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops gc2145_subdev_internal_ops = {
+	.init_state = gc2145_init_state,
+};
+
 static int gc2145_set_ctrl_test_pattern(struct gc2145 *gc2145, int value)
 {
 	int ret = 0;
@@ -1286,6 +1289,7 @@ static int gc2145_probe(struct i2c_client *client)
 		return -ENOMEM;
 
 	v4l2_i2c_subdev_init(&gc2145->sd, client, &gc2145_subdev_ops);
+	gc2145->sd.internal_ops = &gc2145_subdev_internal_ops;
 
 	/* Check the hardware configuration in device tree */
 	if (gc2145_check_hwcfg(dev))
diff --git a/drivers/media/i2c/hi846.c b/drivers/media/i2c/hi846.c
index 0595080c2211..9c565ec033d4 100644
--- a/drivers/media/i2c/hi846.c
+++ b/drivers/media/i2c/hi846.c
@@ -1871,8 +1871,8 @@ static int hi846_get_selection(struct v4l2_subdev *sd,
 	}
 }
 
-static int hi846_init_cfg(struct v4l2_subdev *sd,
-			  struct v4l2_subdev_state *sd_state)
+static int hi846_init_state(struct v4l2_subdev *sd,
+			    struct v4l2_subdev_state *sd_state)
 {
 	struct hi846 *hi846 = to_hi846(sd);
 	struct v4l2_mbus_framefmt *mf;
@@ -1895,7 +1895,6 @@ static const struct v4l2_subdev_video_ops hi846_video_ops = {
 };
 
 static const struct v4l2_subdev_pad_ops hi846_pad_ops = {
-	.init_cfg = hi846_init_cfg,
 	.enum_frame_size = hi846_enum_frame_size,
 	.enum_mbus_code = hi846_enum_mbus_code,
 	.set_fmt = hi846_set_format,
@@ -1908,6 +1907,10 @@ static const struct v4l2_subdev_ops hi846_subdev_ops = {
 	.pad = &hi846_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops hi846_internal_ops = {
+	.init_state = hi846_init_state,
+};
+
 static const struct media_entity_operations hi846_subdev_entity_ops = {
 	.link_validate = v4l2_subdev_link_validate,
 };
@@ -2071,6 +2074,7 @@ static int hi846_probe(struct i2c_client *client)
 		return ret;
 
 	v4l2_i2c_subdev_init(&hi846->sd, client, &hi846_subdev_ops);
+	hi846->sd.internal_ops = &hi846_internal_ops;
 
 	mutex_init(&hi846->mutex);
 
diff --git a/drivers/media/i2c/imx214.c b/drivers/media/i2c/imx214.c
index 8bc7b114c57d..474c95572bf6 100644
--- a/drivers/media/i2c/imx214.c
+++ b/drivers/media/i2c/imx214.c
@@ -633,8 +633,8 @@ static int imx214_get_selection(struct v4l2_subdev *sd,
 	return 0;
 }
 
-static int imx214_entity_init_cfg(struct v4l2_subdev *subdev,
-				  struct v4l2_subdev_state *sd_state)
+static int imx214_entity_init_state(struct v4l2_subdev *subdev,
+				    struct v4l2_subdev_state *sd_state)
 {
 	struct v4l2_subdev_format fmt = { };
 
@@ -839,7 +839,6 @@ static const struct v4l2_subdev_pad_ops imx214_subdev_pad_ops = {
 	.get_fmt = imx214_get_format,
 	.set_fmt = imx214_set_format,
 	.get_selection = imx214_get_selection,
-	.init_cfg = imx214_entity_init_cfg,
 };
 
 static const struct v4l2_subdev_ops imx214_subdev_ops = {
@@ -848,6 +847,10 @@ static const struct v4l2_subdev_ops imx214_subdev_ops = {
 	.pad = &imx214_subdev_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops imx214_internal_ops = {
+	.init_state = imx214_entity_init_state,
+};
+
 static const struct regmap_config sensor_regmap_config = {
 	.reg_bits = 16,
 	.val_bits = 8,
@@ -957,6 +960,7 @@ static int imx214_probe(struct i2c_client *client)
 	}
 
 	v4l2_i2c_subdev_init(&imx214->sd, client, &imx214_subdev_ops);
+	imx214->sd.internal_ops = &imx214_internal_ops;
 
 	/*
 	 * Enable power initially, to avoid warnings
@@ -1021,7 +1025,7 @@ static int imx214_probe(struct i2c_client *client)
 		goto free_ctrl;
 	}
 
-	imx214_entity_init_cfg(&imx214->sd, NULL);
+	imx214_entity_init_state(&imx214->sd, NULL);
 
 	ret = v4l2_async_register_subdev_sensor(&imx214->sd);
 	if (ret < 0) {
diff --git a/drivers/media/i2c/imx219.c b/drivers/media/i2c/imx219.c
index 675795ac2e83..e17ef2e9d9d0 100644
--- a/drivers/media/i2c/imx219.c
+++ b/drivers/media/i2c/imx219.c
@@ -905,8 +905,8 @@ static int imx219_get_selection(struct v4l2_subdev *sd,
 	return -EINVAL;
 }
 
-static int imx219_init_cfg(struct v4l2_subdev *sd,
-			   struct v4l2_subdev_state *state)
+static int imx219_init_state(struct v4l2_subdev *sd,
+			     struct v4l2_subdev_state *state)
 {
 	struct v4l2_subdev_format fmt = {
 		.which = V4L2_SUBDEV_FORMAT_TRY,
@@ -933,7 +933,6 @@ static const struct v4l2_subdev_video_ops imx219_video_ops = {
 };
 
 static const struct v4l2_subdev_pad_ops imx219_pad_ops = {
-	.init_cfg = imx219_init_cfg,
 	.enum_mbus_code = imx219_enum_mbus_code,
 	.get_fmt = v4l2_subdev_get_fmt,
 	.set_fmt = imx219_set_pad_format,
@@ -947,6 +946,9 @@ static const struct v4l2_subdev_ops imx219_subdev_ops = {
 	.pad = &imx219_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops imx219_internal_ops = {
+	.init_state = imx219_init_state,
+};
 
 /* -----------------------------------------------------------------------------
  * Power management
@@ -1098,6 +1100,7 @@ static int imx219_probe(struct i2c_client *client)
 		return -ENOMEM;
 
 	v4l2_i2c_subdev_init(&imx219->sd, client, &imx219_subdev_ops);
+	imx219->sd.internal_ops = &imx219_internal_ops;
 
 	/* Check the hardware configuration in device tree */
 	if (imx219_check_hwcfg(dev, imx219))
diff --git a/drivers/media/i2c/imx290.c b/drivers/media/i2c/imx290.c
index aa8cfbcd40aa..52ba6188911b 100644
--- a/drivers/media/i2c/imx290.c
+++ b/drivers/media/i2c/imx290.c
@@ -1195,8 +1195,8 @@ static int imx290_get_selection(struct v4l2_subdev *sd,
 	}
 }
 
-static int imx290_entity_init_cfg(struct v4l2_subdev *subdev,
-				  struct v4l2_subdev_state *sd_state)
+static int imx290_entity_init_state(struct v4l2_subdev *subdev,
+				    struct v4l2_subdev_state *sd_state)
 {
 	struct v4l2_subdev_format fmt = {
 		.which = V4L2_SUBDEV_FORMAT_TRY,
@@ -1221,7 +1221,6 @@ static const struct v4l2_subdev_video_ops imx290_video_ops = {
 };
 
 static const struct v4l2_subdev_pad_ops imx290_pad_ops = {
-	.init_cfg = imx290_entity_init_cfg,
 	.enum_mbus_code = imx290_enum_mbus_code,
 	.enum_frame_size = imx290_enum_frame_size,
 	.get_fmt = v4l2_subdev_get_fmt,
@@ -1235,6 +1234,10 @@ static const struct v4l2_subdev_ops imx290_subdev_ops = {
 	.pad = &imx290_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops imx290_internal_ops = {
+	.init_state = imx290_entity_init_state,
+};
+
 static const struct media_entity_operations imx290_subdev_entity_ops = {
 	.link_validate = v4l2_subdev_link_validate,
 };
@@ -1248,6 +1251,7 @@ static int imx290_subdev_init(struct imx290 *imx290)
 	imx290->current_mode = &imx290_modes_ptr(imx290)[0];
 
 	v4l2_i2c_subdev_init(&imx290->sd, client, &imx290_subdev_ops);
+	imx290->sd.internal_ops = &imx290_internal_ops;
 	imx290->sd.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE |
 			    V4L2_SUBDEV_FL_HAS_EVENTS;
 	imx290->sd.dev = imx290->dev;
diff --git a/drivers/media/i2c/imx296.c b/drivers/media/i2c/imx296.c
index 8399cca496a7..83149fa729c4 100644
--- a/drivers/media/i2c/imx296.c
+++ b/drivers/media/i2c/imx296.c
@@ -798,8 +798,8 @@ static int imx296_set_selection(struct v4l2_subdev *sd,
 	return 0;
 }
 
-static int imx296_init_cfg(struct v4l2_subdev *sd,
-			   struct v4l2_subdev_state *state)
+static int imx296_init_state(struct v4l2_subdev *sd,
+			     struct v4l2_subdev_state *state)
 {
 	struct v4l2_subdev_selection sel = {
 		.target = V4L2_SEL_TGT_CROP,
@@ -830,7 +830,6 @@ static const struct v4l2_subdev_pad_ops imx296_subdev_pad_ops = {
 	.set_fmt = imx296_set_format,
 	.get_selection = imx296_get_selection,
 	.set_selection = imx296_set_selection,
-	.init_cfg = imx296_init_cfg,
 };
 
 static const struct v4l2_subdev_ops imx296_subdev_ops = {
@@ -838,12 +837,17 @@ static const struct v4l2_subdev_ops imx296_subdev_ops = {
 	.pad = &imx296_subdev_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops imx296_internal_ops = {
+	.init_state = imx296_init_state,
+};
+
 static int imx296_subdev_init(struct imx296 *sensor)
 {
 	struct i2c_client *client = to_i2c_client(sensor->dev);
 	int ret;
 
 	v4l2_i2c_subdev_init(&sensor->subdev, client, &imx296_subdev_ops);
+	sensor->subdev.internal_ops = &imx296_internal_ops;
 
 	ret = imx296_ctrls_init(sensor);
 	if (ret < 0)
diff --git a/drivers/media/i2c/imx334.c b/drivers/media/i2c/imx334.c
index 42cf71c1f6fd..6725b3e2a73e 100644
--- a/drivers/media/i2c/imx334.c
+++ b/drivers/media/i2c/imx334.c
@@ -935,14 +935,14 @@ static int imx334_set_pad_format(struct v4l2_subdev *sd,
 }
 
 /**
- * imx334_init_cfg() - Initialize sub-device state
+ * imx334_init_state() - Initialize sub-device state
  * @sd: pointer to imx334 V4L2 sub-device structure
  * @sd_state: V4L2 sub-device state
  *
  * Return: 0 if successful, error code otherwise.
  */
-static int imx334_init_cfg(struct v4l2_subdev *sd,
-			   struct v4l2_subdev_state *sd_state)
+static int imx334_init_state(struct v4l2_subdev *sd,
+			     struct v4l2_subdev_state *sd_state)
 {
 	struct imx334 *imx334 = to_imx334(sd);
 	struct v4l2_subdev_format fmt = { 0 };
@@ -1190,7 +1190,6 @@ static const struct v4l2_subdev_video_ops imx334_video_ops = {
 };
 
 static const struct v4l2_subdev_pad_ops imx334_pad_ops = {
-	.init_cfg = imx334_init_cfg,
 	.enum_mbus_code = imx334_enum_mbus_code,
 	.enum_frame_size = imx334_enum_frame_size,
 	.get_fmt = imx334_get_pad_format,
@@ -1202,6 +1201,10 @@ static const struct v4l2_subdev_ops imx334_subdev_ops = {
 	.pad = &imx334_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops imx334_internal_ops = {
+	.init_state = imx334_init_state,
+};
+
 /**
  * imx334_power_on() - Sensor power on sequence
  * @dev: pointer to i2c device
@@ -1359,6 +1362,7 @@ static int imx334_probe(struct i2c_client *client)
 
 	/* Initialize subdev */
 	v4l2_i2c_subdev_init(&imx334->sd, client, &imx334_subdev_ops);
+	imx334->sd.internal_ops = &imx334_internal_ops;
 
 	ret = imx334_parse_hw_config(imx334);
 	if (ret) {
diff --git a/drivers/media/i2c/imx335.c b/drivers/media/i2c/imx335.c
index 0432f059e913..205a150971b7 100644
--- a/drivers/media/i2c/imx335.c
+++ b/drivers/media/i2c/imx335.c
@@ -618,14 +618,14 @@ static int imx335_set_pad_format(struct v4l2_subdev *sd,
 }
 
 /**
- * imx335_init_cfg() - Initialize sub-device state
+ * imx335_init_state() - Initialize sub-device state
  * @sd: pointer to imx335 V4L2 sub-device structure
  * @sd_state: V4L2 sub-device configuration
  *
  * Return: 0 if successful, error code otherwise.
  */
-static int imx335_init_cfg(struct v4l2_subdev *sd,
-			   struct v4l2_subdev_state *sd_state)
+static int imx335_init_state(struct v4l2_subdev *sd,
+			     struct v4l2_subdev_state *sd_state)
 {
 	struct imx335 *imx335 = to_imx335(sd);
 	struct v4l2_subdev_format fmt = { 0 };
@@ -835,7 +835,6 @@ static const struct v4l2_subdev_video_ops imx335_video_ops = {
 };
 
 static const struct v4l2_subdev_pad_ops imx335_pad_ops = {
-	.init_cfg = imx335_init_cfg,
 	.enum_mbus_code = imx335_enum_mbus_code,
 	.enum_frame_size = imx335_enum_frame_size,
 	.get_fmt = imx335_get_pad_format,
@@ -847,6 +846,10 @@ static const struct v4l2_subdev_ops imx335_subdev_ops = {
 	.pad = &imx335_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops imx335_internal_ops = {
+	.init_state = imx335_init_state,
+};
+
 /**
  * imx335_power_on() - Sensor power on sequence
  * @dev: pointer to i2c device
@@ -999,6 +1002,7 @@ static int imx335_probe(struct i2c_client *client)
 
 	/* Initialize subdev */
 	v4l2_i2c_subdev_init(&imx335->sd, client, &imx335_subdev_ops);
+	imx335->sd.internal_ops = &imx335_internal_ops;
 
 	ret = imx335_parse_hw_config(imx335);
 	if (ret) {
diff --git a/drivers/media/i2c/imx412.c b/drivers/media/i2c/imx412.c
index 41d756a20f3c..0efce329525e 100644
--- a/drivers/media/i2c/imx412.c
+++ b/drivers/media/i2c/imx412.c
@@ -770,14 +770,14 @@ static int imx412_set_pad_format(struct v4l2_subdev *sd,
 }
 
 /**
- * imx412_init_cfg() - Initialize sub-device state
+ * imx412_init_state() - Initialize sub-device state
  * @sd: pointer to imx412 V4L2 sub-device structure
  * @sd_state: V4L2 sub-device configuration
  *
  * Return: 0 if successful, error code otherwise.
  */
-static int imx412_init_cfg(struct v4l2_subdev *sd,
-			   struct v4l2_subdev_state *sd_state)
+static int imx412_init_state(struct v4l2_subdev *sd,
+			     struct v4l2_subdev_state *sd_state)
 {
 	struct imx412 *imx412 = to_imx412(sd);
 	struct v4l2_subdev_format fmt = { 0 };
@@ -997,7 +997,6 @@ static const struct v4l2_subdev_video_ops imx412_video_ops = {
 };
 
 static const struct v4l2_subdev_pad_ops imx412_pad_ops = {
-	.init_cfg = imx412_init_cfg,
 	.enum_mbus_code = imx412_enum_mbus_code,
 	.enum_frame_size = imx412_enum_frame_size,
 	.get_fmt = imx412_get_pad_format,
@@ -1009,6 +1008,10 @@ static const struct v4l2_subdev_ops imx412_subdev_ops = {
 	.pad = &imx412_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops imx412_internal_ops = {
+	.init_state = imx412_init_state,
+};
+
 /**
  * imx412_power_on() - Sensor power on sequence
  * @dev: pointer to i2c device
@@ -1177,6 +1180,7 @@ static int imx412_probe(struct i2c_client *client)
 
 	/* Initialize subdev */
 	v4l2_i2c_subdev_init(&imx412->sd, client, &imx412_subdev_ops);
+	imx412->sd.internal_ops = &imx412_internal_ops;
 
 	ret = imx412_parse_hw_config(imx412);
 	if (ret) {
diff --git a/drivers/media/i2c/imx415.c b/drivers/media/i2c/imx415.c
index 6436a32c4025..1e5f20c3ed82 100644
--- a/drivers/media/i2c/imx415.c
+++ b/drivers/media/i2c/imx415.c
@@ -880,8 +880,8 @@ static int imx415_get_selection(struct v4l2_subdev *sd,
 	return -EINVAL;
 }
 
-static int imx415_init_cfg(struct v4l2_subdev *sd,
-			   struct v4l2_subdev_state *state)
+static int imx415_init_state(struct v4l2_subdev *sd,
+			     struct v4l2_subdev_state *state)
 {
 	struct v4l2_subdev_format format = {
 		.format = {
@@ -905,7 +905,6 @@ static const struct v4l2_subdev_pad_ops imx415_subdev_pad_ops = {
 	.get_fmt = v4l2_subdev_get_fmt,
 	.set_fmt = imx415_set_format,
 	.get_selection = imx415_get_selection,
-	.init_cfg = imx415_init_cfg,
 };
 
 static const struct v4l2_subdev_ops imx415_subdev_ops = {
@@ -913,12 +912,17 @@ static const struct v4l2_subdev_ops imx415_subdev_ops = {
 	.pad = &imx415_subdev_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops imx415_internal_ops = {
+	.init_state = imx415_init_state,
+};
+
 static int imx415_subdev_init(struct imx415 *sensor)
 {
 	struct i2c_client *client = to_i2c_client(sensor->dev);
 	int ret;
 
 	v4l2_i2c_subdev_init(&sensor->subdev, client, &imx415_subdev_ops);
+	sensor->subdev.internal_ops = &imx415_internal_ops;
 
 	ret = imx415_ctrls_init(sensor);
 	if (ret)
diff --git a/drivers/media/i2c/mt9m001.c b/drivers/media/i2c/mt9m001.c
index 4c897bb07fed..ad1a3ab77411 100644
--- a/drivers/media/i2c/mt9m001.c
+++ b/drivers/media/i2c/mt9m001.c
@@ -650,8 +650,8 @@ static const struct v4l2_subdev_core_ops mt9m001_subdev_core_ops = {
 #endif
 };
 
-static int mt9m001_init_cfg(struct v4l2_subdev *sd,
-			    struct v4l2_subdev_state *sd_state)
+static int mt9m001_init_state(struct v4l2_subdev *sd,
+			      struct v4l2_subdev_state *sd_state)
 {
 	struct i2c_client *client = v4l2_get_subdevdata(sd);
 	struct mt9m001 *mt9m001 = to_mt9m001(client);
@@ -708,7 +708,6 @@ static const struct v4l2_subdev_sensor_ops mt9m001_subdev_sensor_ops = {
 };
 
 static const struct v4l2_subdev_pad_ops mt9m001_subdev_pad_ops = {
-	.init_cfg	= mt9m001_init_cfg,
 	.enum_mbus_code = mt9m001_enum_mbus_code,
 	.get_selection	= mt9m001_get_selection,
 	.set_selection	= mt9m001_set_selection,
@@ -724,6 +723,10 @@ static const struct v4l2_subdev_ops mt9m001_subdev_ops = {
 	.pad	= &mt9m001_subdev_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops mt9m001_internal_ops = {
+	.init_state	= mt9m001_init_state,
+};
+
 static int mt9m001_probe(struct i2c_client *client)
 {
 	struct mt9m001 *mt9m001;
@@ -755,6 +758,7 @@ static int mt9m001_probe(struct i2c_client *client)
 		return PTR_ERR(mt9m001->reset_gpio);
 
 	v4l2_i2c_subdev_init(&mt9m001->subdev, client, &mt9m001_subdev_ops);
+	mt9m001->subdev.internal_ops = &mt9m001_internal_ops;
 	mt9m001->subdev.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE |
 				 V4L2_SUBDEV_FL_HAS_EVENTS;
 	v4l2_ctrl_handler_init(&mt9m001->hdl, 4);
diff --git a/drivers/media/i2c/mt9m111.c b/drivers/media/i2c/mt9m111.c
index 17ca92810b58..54a7a4c623ea 100644
--- a/drivers/media/i2c/mt9m111.c
+++ b/drivers/media/i2c/mt9m111.c
@@ -1111,8 +1111,8 @@ static int mt9m111_s_stream(struct v4l2_subdev *sd, int enable)
 	return 0;
 }
 
-static int mt9m111_init_cfg(struct v4l2_subdev *sd,
-			    struct v4l2_subdev_state *sd_state)
+static int mt9m111_init_state(struct v4l2_subdev *sd,
+			      struct v4l2_subdev_state *sd_state)
 {
 	struct v4l2_mbus_framefmt *format =
 		v4l2_subdev_state_get_format(sd_state, 0);
@@ -1156,7 +1156,6 @@ static const struct v4l2_subdev_video_ops mt9m111_subdev_video_ops = {
 };
 
 static const struct v4l2_subdev_pad_ops mt9m111_subdev_pad_ops = {
-	.init_cfg	= mt9m111_init_cfg,
 	.enum_mbus_code = mt9m111_enum_mbus_code,
 	.get_selection	= mt9m111_get_selection,
 	.set_selection	= mt9m111_set_selection,
@@ -1171,6 +1170,10 @@ static const struct v4l2_subdev_ops mt9m111_subdev_ops = {
 	.pad	= &mt9m111_subdev_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops mt9m111_internal_ops = {
+	.init_state	= mt9m111_init_state,
+};
+
 /*
  * Interface active, can use i2c. If it fails, it can indeed mean, that
  * this wasn't our capture interface, so, we wait for the right one
@@ -1275,6 +1278,7 @@ static int mt9m111_probe(struct i2c_client *client)
 	mt9m111->ctx = &context_b;
 
 	v4l2_i2c_subdev_init(&mt9m111->subdev, client, &mt9m111_subdev_ops);
+	mt9m111->subdev.internal_ops = &mt9m111_internal_ops;
 	mt9m111->subdev.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE |
 				 V4L2_SUBDEV_FL_HAS_EVENTS;
 
diff --git a/drivers/media/i2c/mt9m114.c b/drivers/media/i2c/mt9m114.c
index 23cf84f1a746..0a22f328981d 100644
--- a/drivers/media/i2c/mt9m114.c
+++ b/drivers/media/i2c/mt9m114.c
@@ -1152,8 +1152,8 @@ static inline struct mt9m114 *pa_to_mt9m114(struct v4l2_subdev *sd)
 	return container_of(sd, struct mt9m114, pa.sd);
 }
 
-static int mt9m114_pa_init_cfg(struct v4l2_subdev *sd,
-			       struct v4l2_subdev_state *state)
+static int mt9m114_pa_init_state(struct v4l2_subdev *sd,
+				 struct v4l2_subdev_state *state)
 {
 	struct v4l2_mbus_framefmt *format;
 	struct v4l2_rect *crop;
@@ -1304,7 +1304,6 @@ static int mt9m114_pa_set_selection(struct v4l2_subdev *sd,
 }
 
 static const struct v4l2_subdev_pad_ops mt9m114_pa_pad_ops = {
-	.init_cfg = mt9m114_pa_init_cfg,
 	.enum_mbus_code = mt9m114_pa_enum_mbus_code,
 	.enum_frame_size = mt9m114_pa_enum_framesizes,
 	.get_fmt = v4l2_subdev_get_fmt,
@@ -1317,6 +1316,10 @@ static const struct v4l2_subdev_ops mt9m114_pa_ops = {
 	.pad = &mt9m114_pa_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops mt9m114_pa_internal_ops = {
+	.init_state = mt9m114_pa_init_state,
+};
+
 static int mt9m114_pa_init(struct mt9m114 *sensor)
 {
 	struct v4l2_ctrl_handler *hdl = &sensor->pa.hdl;
@@ -1329,6 +1332,7 @@ static int mt9m114_pa_init(struct mt9m114 *sensor)
 
 	/* Initialize the subdev. */
 	v4l2_subdev_init(sd, &mt9m114_pa_ops);
+	sd->internal_ops = &mt9m114_pa_internal_ops;
 	v4l2_i2c_subdev_set_name(sd, sensor->client, NULL, " pixel array");
 
 	sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
@@ -1624,8 +1628,8 @@ static int mt9m114_ifp_s_frame_interval(struct v4l2_subdev *sd,
 	return ret;
 }
 
-static int mt9m114_ifp_init_cfg(struct v4l2_subdev *sd,
-				struct v4l2_subdev_state *state)
+static int mt9m114_ifp_init_state(struct v4l2_subdev *sd,
+				  struct v4l2_subdev_state *state)
 {
 	struct mt9m114 *sensor = ifp_to_mt9m114(sd);
 	struct v4l2_mbus_framefmt *format;
@@ -1968,7 +1972,6 @@ static const struct v4l2_subdev_video_ops mt9m114_ifp_video_ops = {
 };
 
 static const struct v4l2_subdev_pad_ops mt9m114_ifp_pad_ops = {
-	.init_cfg = mt9m114_ifp_init_cfg,
 	.enum_mbus_code = mt9m114_ifp_enum_mbus_code,
 	.enum_frame_size = mt9m114_ifp_enum_framesizes,
 	.enum_frame_interval = mt9m114_ifp_enum_frameintervals,
@@ -1984,6 +1987,7 @@ static const struct v4l2_subdev_ops mt9m114_ifp_ops = {
 };
 
 static const struct v4l2_subdev_internal_ops mt9m114_ifp_internal_ops = {
+	.init_state = mt9m114_ifp_init_state,
 	.registered = mt9m114_ifp_registered,
 	.unregistered = mt9m114_ifp_unregistered,
 };
diff --git a/drivers/media/i2c/mt9p031.c b/drivers/media/i2c/mt9p031.c
index 89bcd48748b9..596200d0248c 100644
--- a/drivers/media/i2c/mt9p031.c
+++ b/drivers/media/i2c/mt9p031.c
@@ -696,8 +696,8 @@ static int mt9p031_set_selection(struct v4l2_subdev *subdev,
 	return 0;
 }
 
-static int mt9p031_init_cfg(struct v4l2_subdev *subdev,
-			    struct v4l2_subdev_state *sd_state)
+static int mt9p031_init_state(struct v4l2_subdev *subdev,
+			      struct v4l2_subdev_state *sd_state)
 {
 	struct mt9p031 *mt9p031 = to_mt9p031(subdev);
 	struct v4l2_mbus_framefmt *format;
@@ -1041,7 +1041,6 @@ static const struct v4l2_subdev_video_ops mt9p031_subdev_video_ops = {
 };
 
 static const struct v4l2_subdev_pad_ops mt9p031_subdev_pad_ops = {
-	.init_cfg = mt9p031_init_cfg,
 	.enum_mbus_code = mt9p031_enum_mbus_code,
 	.enum_frame_size = mt9p031_enum_frame_size,
 	.get_fmt = mt9p031_get_format,
@@ -1057,6 +1056,7 @@ static const struct v4l2_subdev_ops mt9p031_subdev_ops = {
 };
 
 static const struct v4l2_subdev_internal_ops mt9p031_subdev_internal_ops = {
+	.init_state = mt9p031_init_state,
 	.registered = mt9p031_registered,
 	.open = mt9p031_open,
 	.close = mt9p031_close,
@@ -1189,7 +1189,7 @@ static int mt9p031_probe(struct i2c_client *client)
 
 	mt9p031->subdev.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
 
-	ret = mt9p031_init_cfg(&mt9p031->subdev, NULL);
+	ret = mt9p031_init_state(&mt9p031->subdev, NULL);
 	if (ret)
 		goto done;
 
diff --git a/drivers/media/i2c/mt9v111.c b/drivers/media/i2c/mt9v111.c
index 6752582cb2c7..b186e9160d94 100644
--- a/drivers/media/i2c/mt9v111.c
+++ b/drivers/media/i2c/mt9v111.c
@@ -948,8 +948,8 @@ done:
 	return 0;
 }
 
-static int mt9v111_init_cfg(struct v4l2_subdev *subdev,
-			    struct v4l2_subdev_state *sd_state)
+static int mt9v111_init_state(struct v4l2_subdev *subdev,
+			      struct v4l2_subdev_state *sd_state)
 {
 	*v4l2_subdev_state_get_format(sd_state, 0) = mt9v111_def_fmt;
 
@@ -967,7 +967,6 @@ static const struct v4l2_subdev_video_ops mt9v111_video_ops = {
 };
 
 static const struct v4l2_subdev_pad_ops mt9v111_pad_ops = {
-	.init_cfg		= mt9v111_init_cfg,
 	.enum_mbus_code		= mt9v111_enum_mbus_code,
 	.enum_frame_size	= mt9v111_enum_frame_size,
 	.enum_frame_interval	= mt9v111_enum_frame_interval,
@@ -981,6 +980,10 @@ static const struct v4l2_subdev_ops mt9v111_ops = {
 	.pad	= &mt9v111_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops mt9v111_internal_ops = {
+	.init_state		= mt9v111_init_state,
+};
+
 static const struct media_entity_operations mt9v111_subdev_entity_ops = {
 	.link_validate = v4l2_subdev_link_validate,
 };
@@ -1194,6 +1197,7 @@ static int mt9v111_probe(struct i2c_client *client)
 	mt9v111->pending	= true;
 
 	v4l2_i2c_subdev_init(&mt9v111->sd, client, &mt9v111_ops);
+	mt9v111->sd.internal_ops = &mt9v111_internal_ops;
 
 	mt9v111->sd.flags	|= V4L2_SUBDEV_FL_HAS_DEVNODE;
 	mt9v111->sd.entity.ops	= &mt9v111_subdev_entity_ops;
diff --git a/drivers/media/i2c/ov01a10.c b/drivers/media/i2c/ov01a10.c
index c72280bb1f5b..7cca9294ea31 100644
--- a/drivers/media/i2c/ov01a10.c
+++ b/drivers/media/i2c/ov01a10.c
@@ -729,8 +729,8 @@ static int ov01a10_set_format(struct v4l2_subdev *sd,
 	return 0;
 }
 
-static int ov01a10_init_cfg(struct v4l2_subdev *sd,
-			    struct v4l2_subdev_state *state)
+static int ov01a10_init_state(struct v4l2_subdev *sd,
+			      struct v4l2_subdev_state *state)
 {
 	struct v4l2_subdev_format fmt = {
 		.which = V4L2_SUBDEV_FORMAT_TRY,
@@ -813,7 +813,6 @@ static const struct v4l2_subdev_video_ops ov01a10_video_ops = {
 };
 
 static const struct v4l2_subdev_pad_ops ov01a10_pad_ops = {
-	.init_cfg = ov01a10_init_cfg,
 	.set_fmt = ov01a10_set_format,
 	.get_fmt = v4l2_subdev_get_fmt,
 	.get_selection = ov01a10_get_selection,
@@ -827,6 +826,10 @@ static const struct v4l2_subdev_ops ov01a10_subdev_ops = {
 	.pad = &ov01a10_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops ov01a10_internal_ops = {
+	.init_state = ov01a10_init_state,
+};
+
 static const struct media_entity_operations ov01a10_subdev_entity_ops = {
 	.link_validate = v4l2_subdev_link_validate,
 };
@@ -872,6 +875,7 @@ static int ov01a10_probe(struct i2c_client *client)
 		return -ENOMEM;
 
 	v4l2_i2c_subdev_init(&ov01a10->sd, client, &ov01a10_subdev_ops);
+	ov01a10->sd.internal_ops = &ov01a10_internal_ops;
 
 	ret = ov01a10_identify_module(ov01a10);
 	if (ret)
diff --git a/drivers/media/i2c/ov02a10.c b/drivers/media/i2c/ov02a10.c
index 8454cb39a47b..6c30e1a0d814 100644
--- a/drivers/media/i2c/ov02a10.c
+++ b/drivers/media/i2c/ov02a10.c
@@ -511,8 +511,8 @@ static int __ov02a10_stop_stream(struct ov02a10 *ov02a10)
 					 SC_CTRL_MODE_STANDBY);
 }
 
-static int ov02a10_entity_init_cfg(struct v4l2_subdev *sd,
-				   struct v4l2_subdev_state *sd_state)
+static int ov02a10_init_state(struct v4l2_subdev *sd,
+			      struct v4l2_subdev_state *sd_state)
 {
 	struct v4l2_subdev_format fmt = {
 		.which = V4L2_SUBDEV_FORMAT_TRY,
@@ -709,7 +709,6 @@ static const struct v4l2_subdev_video_ops ov02a10_video_ops = {
 };
 
 static const struct v4l2_subdev_pad_ops ov02a10_pad_ops = {
-	.init_cfg = ov02a10_entity_init_cfg,
 	.enum_mbus_code = ov02a10_enum_mbus_code,
 	.enum_frame_size = ov02a10_enum_frame_sizes,
 	.get_fmt = ov02a10_get_fmt,
@@ -721,6 +720,10 @@ static const struct v4l2_subdev_ops ov02a10_subdev_ops = {
 	.pad	= &ov02a10_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops ov02a10_internal_ops = {
+	.init_state = ov02a10_init_state,
+};
+
 static const struct media_entity_operations ov02a10_subdev_entity_ops = {
 	.link_validate = v4l2_subdev_link_validate,
 };
@@ -869,6 +872,7 @@ static int ov02a10_probe(struct i2c_client *client)
 				     "failed to check HW configuration\n");
 
 	v4l2_i2c_subdev_init(&ov02a10->subdev, client, &ov02a10_subdev_ops);
+	ov02a10->subdev.internal_ops = &ov02a10_internal_ops;
 
 	ov02a10->mipi_clock_voltage = OV02A10_MIPI_TX_SPEED_DEFAULT;
 	ov02a10->fmt.code = MEDIA_BUS_FMT_SBGGR10_1X10;
diff --git a/drivers/media/i2c/ov2640.c b/drivers/media/i2c/ov2640.c
index 28911d5169f7..67c4bd2916e8 100644
--- a/drivers/media/i2c/ov2640.c
+++ b/drivers/media/i2c/ov2640.c
@@ -996,8 +996,8 @@ out:
 	return ret;
 }
 
-static int ov2640_init_cfg(struct v4l2_subdev *sd,
-			   struct v4l2_subdev_state *sd_state)
+static int ov2640_init_state(struct v4l2_subdev *sd,
+			     struct v4l2_subdev_state *sd_state)
 {
 	struct v4l2_mbus_framefmt *try_fmt =
 		v4l2_subdev_state_get_format(sd_state, 0);
@@ -1125,7 +1125,6 @@ static const struct v4l2_subdev_core_ops ov2640_subdev_core_ops = {
 };
 
 static const struct v4l2_subdev_pad_ops ov2640_subdev_pad_ops = {
-	.init_cfg	= ov2640_init_cfg,
 	.enum_mbus_code = ov2640_enum_mbus_code,
 	.get_selection	= ov2640_get_selection,
 	.get_fmt	= ov2640_get_fmt,
@@ -1142,6 +1141,10 @@ static const struct v4l2_subdev_ops ov2640_subdev_ops = {
 	.video	= &ov2640_subdev_video_ops,
 };
 
+static const struct v4l2_subdev_internal_ops ov2640_internal_ops = {
+	.init_state	= ov2640_init_state,
+};
+
 static int ov2640_probe_dt(struct i2c_client *client,
 		struct ov2640_priv *priv)
 {
@@ -1211,6 +1214,7 @@ static int ov2640_probe(struct i2c_client *client)
 	priv->cfmt_code = MEDIA_BUS_FMT_UYVY8_2X8;
 
 	v4l2_i2c_subdev_init(&priv->subdev, client, &ov2640_subdev_ops);
+	priv->subdev.internal_ops = &ov2640_internal_ops;
 	priv->subdev.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE |
 			      V4L2_SUBDEV_FL_HAS_EVENTS;
 	mutex_init(&priv->lock);
diff --git a/drivers/media/i2c/ov2680.c b/drivers/media/i2c/ov2680.c
index 9b53ea9af45a..d34d1972dcd9 100644
--- a/drivers/media/i2c/ov2680.c
+++ b/drivers/media/i2c/ov2680.c
@@ -755,8 +755,8 @@ static int ov2680_set_selection(struct v4l2_subdev *sd,
 	return 0;
 }
 
-static int ov2680_init_cfg(struct v4l2_subdev *sd,
-			   struct v4l2_subdev_state *sd_state)
+static int ov2680_init_state(struct v4l2_subdev *sd,
+			     struct v4l2_subdev_state *sd_state)
 {
 	struct ov2680_dev *sensor = to_ov2680_dev(sd);
 
@@ -876,7 +876,6 @@ static const struct v4l2_subdev_video_ops ov2680_video_ops = {
 };
 
 static const struct v4l2_subdev_pad_ops ov2680_pad_ops = {
-	.init_cfg		= ov2680_init_cfg,
 	.enum_mbus_code		= ov2680_enum_mbus_code,
 	.enum_frame_size	= ov2680_enum_frame_size,
 	.enum_frame_interval	= ov2680_enum_frame_interval,
@@ -891,6 +890,10 @@ static const struct v4l2_subdev_ops ov2680_subdev_ops = {
 	.pad	= &ov2680_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops ov2680_internal_ops = {
+	.init_state		= ov2680_init_state,
+};
+
 static int ov2680_mode_init(struct ov2680_dev *sensor)
 {
 	/* set initial mode */
@@ -915,6 +918,7 @@ static int ov2680_v4l2_register(struct ov2680_dev *sensor)
 	int ret = 0;
 
 	v4l2_i2c_subdev_init(&sensor->sd, client, &ov2680_subdev_ops);
+	sensor->sd.internal_ops = &ov2680_internal_ops;
 
 	sensor->sd.flags = V4L2_SUBDEV_FL_HAS_DEVNODE;
 	sensor->pad.flags = MEDIA_PAD_FL_SOURCE;
diff --git a/drivers/media/i2c/ov2740.c b/drivers/media/i2c/ov2740.c
index 23cbd8b7846e..f0be51b343a7 100644
--- a/drivers/media/i2c/ov2740.c
+++ b/drivers/media/i2c/ov2740.c
@@ -879,8 +879,8 @@ static int ov2740_enum_frame_size(struct v4l2_subdev *sd,
 	return 0;
 }
 
-static int ov2740_init_cfg(struct v4l2_subdev *sd,
-			   struct v4l2_subdev_state *sd_state)
+static int ov2740_init_state(struct v4l2_subdev *sd,
+			     struct v4l2_subdev_state *sd_state)
 {
 	ov2740_update_pad_format(&supported_modes[0],
 				 v4l2_subdev_state_get_format(sd_state, 0));
@@ -897,7 +897,6 @@ static const struct v4l2_subdev_pad_ops ov2740_pad_ops = {
 	.set_fmt = ov2740_set_format,
 	.enum_mbus_code = ov2740_enum_mbus_code,
 	.enum_frame_size = ov2740_enum_frame_size,
-	.init_cfg = ov2740_init_cfg,
 };
 
 static const struct v4l2_subdev_ops ov2740_subdev_ops = {
@@ -905,6 +904,10 @@ static const struct v4l2_subdev_ops ov2740_subdev_ops = {
 	.pad = &ov2740_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops ov2740_internal_ops = {
+	.init_state = ov2740_init_state,
+};
+
 static const struct media_entity_operations ov2740_subdev_entity_ops = {
 	.link_validate = v4l2_subdev_link_validate,
 };
@@ -1074,6 +1077,7 @@ static int ov2740_probe(struct i2c_client *client)
 		return -ENOMEM;
 
 	v4l2_i2c_subdev_init(&ov2740->sd, client, &ov2740_subdev_ops);
+	ov2740->sd.internal_ops = &ov2740_internal_ops;
 	full_power = acpi_dev_state_d0(&client->dev);
 	if (full_power) {
 		ret = ov2740_identify_module(ov2740);
diff --git a/drivers/media/i2c/ov5640.c b/drivers/media/i2c/ov5640.c
index 3f79a3b77044..6fd98b8cb181 100644
--- a/drivers/media/i2c/ov5640.c
+++ b/drivers/media/i2c/ov5640.c
@@ -3744,8 +3744,8 @@ out:
 	return ret;
 }
 
-static int ov5640_init_cfg(struct v4l2_subdev *sd,
-			   struct v4l2_subdev_state *state)
+static int ov5640_init_state(struct v4l2_subdev *sd,
+			     struct v4l2_subdev_state *state)
 {
 	struct ov5640_dev *sensor = to_ov5640_dev(sd);
 	struct v4l2_mbus_framefmt *fmt =
@@ -3776,7 +3776,6 @@ static const struct v4l2_subdev_video_ops ov5640_video_ops = {
 };
 
 static const struct v4l2_subdev_pad_ops ov5640_pad_ops = {
-	.init_cfg = ov5640_init_cfg,
 	.enum_mbus_code = ov5640_enum_mbus_code,
 	.get_fmt = ov5640_get_fmt,
 	.set_fmt = ov5640_set_fmt,
@@ -3791,6 +3790,10 @@ static const struct v4l2_subdev_ops ov5640_subdev_ops = {
 	.pad = &ov5640_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops ov5640_internal_ops = {
+	.init_state = ov5640_init_state,
+};
+
 static int ov5640_get_regulators(struct ov5640_dev *sensor)
 {
 	int i;
@@ -3905,6 +3908,7 @@ static int ov5640_probe(struct i2c_client *client)
 		return PTR_ERR(sensor->reset_gpio);
 
 	v4l2_i2c_subdev_init(&sensor->sd, client, &ov5640_subdev_ops);
+	sensor->sd.internal_ops = &ov5640_internal_ops;
 
 	sensor->sd.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE |
 			    V4L2_SUBDEV_FL_HAS_EVENTS;
diff --git a/drivers/media/i2c/ov5645.c b/drivers/media/i2c/ov5645.c
index 695f4f673536..a26ac11c989d 100644
--- a/drivers/media/i2c/ov5645.c
+++ b/drivers/media/i2c/ov5645.c
@@ -934,8 +934,8 @@ static int ov5645_set_format(struct v4l2_subdev *sd,
 	return 0;
 }
 
-static int ov5645_entity_init_cfg(struct v4l2_subdev *subdev,
-				  struct v4l2_subdev_state *sd_state)
+static int ov5645_init_state(struct v4l2_subdev *subdev,
+			     struct v4l2_subdev_state *sd_state)
 {
 	struct v4l2_subdev_format fmt = { 0 };
 
@@ -1023,7 +1023,6 @@ static const struct v4l2_subdev_video_ops ov5645_video_ops = {
 };
 
 static const struct v4l2_subdev_pad_ops ov5645_subdev_pad_ops = {
-	.init_cfg = ov5645_entity_init_cfg,
 	.enum_mbus_code = ov5645_enum_mbus_code,
 	.enum_frame_size = ov5645_enum_frame_size,
 	.get_fmt = ov5645_get_format,
@@ -1036,6 +1035,10 @@ static const struct v4l2_subdev_ops ov5645_subdev_ops = {
 	.pad = &ov5645_subdev_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops ov5645_internal_ops = {
+	.init_state = ov5645_init_state,
+};
+
 static int ov5645_probe(struct i2c_client *client)
 {
 	struct device *dev = &client->dev;
@@ -1162,6 +1165,7 @@ static int ov5645_probe(struct i2c_client *client)
 	}
 
 	v4l2_i2c_subdev_init(&ov5645->sd, client, &ov5645_subdev_ops);
+	ov5645->sd.internal_ops = &ov5645_internal_ops;
 	ov5645->sd.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
 	ov5645->pad.flags = MEDIA_PAD_FL_SOURCE;
 	ov5645->sd.dev = &client->dev;
@@ -1220,7 +1224,7 @@ static int ov5645_probe(struct i2c_client *client)
 	pm_runtime_get_noresume(dev);
 	pm_runtime_enable(dev);
 
-	ov5645_entity_init_cfg(&ov5645->sd, NULL);
+	ov5645_init_state(&ov5645->sd, NULL);
 
 	ret = v4l2_async_register_subdev(&ov5645->sd);
 	if (ret < 0) {
diff --git a/drivers/media/i2c/ov5670.c b/drivers/media/i2c/ov5670.c
index 470d848f40d8..2aee85965cf7 100644
--- a/drivers/media/i2c/ov5670.c
+++ b/drivers/media/i2c/ov5670.c
@@ -2196,8 +2196,8 @@ error:
 	return ret;
 }
 
-static int ov5670_init_cfg(struct v4l2_subdev *sd,
-			   struct v4l2_subdev_state *state)
+static int ov5670_init_state(struct v4l2_subdev *sd,
+			     struct v4l2_subdev_state *state)
 {
 	struct v4l2_mbus_framefmt *fmt =
 				v4l2_subdev_state_get_format(state, 0);
@@ -2592,7 +2592,6 @@ static const struct v4l2_subdev_video_ops ov5670_video_ops = {
 };
 
 static const struct v4l2_subdev_pad_ops ov5670_pad_ops = {
-	.init_cfg = ov5670_init_cfg,
 	.enum_mbus_code = ov5670_enum_mbus_code,
 	.get_fmt = ov5670_get_pad_format,
 	.set_fmt = ov5670_set_pad_format,
@@ -2612,6 +2611,10 @@ static const struct v4l2_subdev_ops ov5670_subdev_ops = {
 	.sensor = &ov5670_sensor_ops,
 };
 
+static const struct v4l2_subdev_internal_ops ov5670_internal_ops = {
+	.init_state = ov5670_init_state,
+};
+
 static const struct media_entity_operations ov5670_subdev_entity_ops = {
 	.link_validate = v4l2_subdev_link_validate,
 };
@@ -2675,6 +2678,7 @@ static int ov5670_probe(struct i2c_client *client)
 
 	/* Initialize subdev */
 	v4l2_i2c_subdev_init(&ov5670->sd, client, &ov5670_subdev_ops);
+	ov5670->sd.internal_ops = &ov5670_internal_ops;
 
 	ret = ov5670_regulators_probe(ov5670);
 	if (ret)
diff --git a/drivers/media/i2c/ov7251.c b/drivers/media/i2c/ov7251.c
index 774f5dfb8186..897a0763df4a 100644
--- a/drivers/media/i2c/ov7251.c
+++ b/drivers/media/i2c/ov7251.c
@@ -1282,8 +1282,8 @@ exit:
 	return ret;
 }
 
-static int ov7251_entity_init_cfg(struct v4l2_subdev *subdev,
-				  struct v4l2_subdev_state *sd_state)
+static int ov7251_init_state(struct v4l2_subdev *subdev,
+			     struct v4l2_subdev_state *sd_state)
 {
 	struct v4l2_subdev_format fmt = {
 		.which = sd_state ? V4L2_SUBDEV_FORMAT_TRY
@@ -1441,7 +1441,6 @@ static const struct v4l2_subdev_video_ops ov7251_video_ops = {
 };
 
 static const struct v4l2_subdev_pad_ops ov7251_subdev_pad_ops = {
-	.init_cfg = ov7251_entity_init_cfg,
 	.enum_mbus_code = ov7251_enum_mbus_code,
 	.enum_frame_size = ov7251_enum_frame_size,
 	.enum_frame_interval = ov7251_enum_frame_ival,
@@ -1455,6 +1454,10 @@ static const struct v4l2_subdev_ops ov7251_subdev_ops = {
 	.pad = &ov7251_subdev_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops ov7251_internal_ops = {
+	.init_state = ov7251_init_state,
+};
+
 static int ov7251_check_hwcfg(struct ov7251 *ov7251)
 {
 	struct fwnode_handle *fwnode = dev_fwnode(ov7251->dev);
@@ -1693,6 +1696,7 @@ static int ov7251_probe(struct i2c_client *client)
 	}
 
 	v4l2_i2c_subdev_init(&ov7251->sd, client, &ov7251_subdev_ops);
+	ov7251->sd.internal_ops = &ov7251_internal_ops;
 	ov7251->sd.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
 	ov7251->pad.flags = MEDIA_PAD_FL_SOURCE;
 	ov7251->sd.dev = &client->dev;
@@ -1750,7 +1754,7 @@ static int ov7251_probe(struct i2c_client *client)
 		goto free_entity;
 	}
 
-	ov7251_entity_init_cfg(&ov7251->sd, NULL);
+	ov7251_init_state(&ov7251->sd, NULL);
 
 	return 0;
 
diff --git a/drivers/media/i2c/ov8858.c b/drivers/media/i2c/ov8858.c
index 0e3776136136..174c65f76886 100644
--- a/drivers/media/i2c/ov8858.c
+++ b/drivers/media/i2c/ov8858.c
@@ -1476,8 +1476,8 @@ static int ov8858_enum_mbus_code(struct v4l2_subdev *sd,
 	return 0;
 }
 
-static int ov8858_init_cfg(struct v4l2_subdev *sd,
-			   struct v4l2_subdev_state *sd_state)
+static int ov8858_init_state(struct v4l2_subdev *sd,
+			     struct v4l2_subdev_state *sd_state)
 {
 	const struct ov8858_mode *def_mode = &ov8858_modes[0];
 	struct v4l2_subdev_format fmt = {
@@ -1494,7 +1494,6 @@ static int ov8858_init_cfg(struct v4l2_subdev *sd,
 }
 
 static const struct v4l2_subdev_pad_ops ov8858_pad_ops = {
-	.init_cfg = ov8858_init_cfg,
 	.enum_mbus_code = ov8858_enum_mbus_code,
 	.enum_frame_size = ov8858_enum_frame_sizes,
 	.get_fmt = v4l2_subdev_get_fmt,
@@ -1512,6 +1511,10 @@ static const struct v4l2_subdev_ops ov8858_subdev_ops = {
 	.pad	= &ov8858_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops ov8858_internal_ops = {
+	.init_state = ov8858_init_state,
+};
+
 /* ----------------------------------------------------------------------------
  * Controls handling
  */
@@ -1899,6 +1902,7 @@ static int ov8858_probe(struct i2c_client *client)
 				     "Failed to get powerdown gpio\n");
 
 	v4l2_i2c_subdev_init(&ov8858->subdev, client, &ov8858_subdev_ops);
+	ov8858->subdev.internal_ops = &ov8858_internal_ops;
 
 	ret = ov8858_configure_regulators(ov8858);
 	if (ret)
diff --git a/drivers/media/i2c/ov9282.c b/drivers/media/i2c/ov9282.c
index 1707bc22ca91..251a4b534914 100644
--- a/drivers/media/i2c/ov9282.c
+++ b/drivers/media/i2c/ov9282.c
@@ -876,14 +876,14 @@ static int ov9282_set_pad_format(struct v4l2_subdev *sd,
 }
 
 /**
- * ov9282_init_cfg() - Initialize sub-device state
+ * ov9282_init_state() - Initialize sub-device state
  * @sd: pointer to ov9282 V4L2 sub-device structure
  * @sd_state: V4L2 sub-device configuration
  *
  * Return: 0 if successful, error code otherwise.
  */
-static int ov9282_init_cfg(struct v4l2_subdev *sd,
-			   struct v4l2_subdev_state *sd_state)
+static int ov9282_init_state(struct v4l2_subdev *sd,
+			     struct v4l2_subdev_state *sd_state)
 {
 	struct ov9282 *ov9282 = to_ov9282(sd);
 	struct v4l2_subdev_format fmt = { 0 };
@@ -1192,7 +1192,6 @@ static const struct v4l2_subdev_video_ops ov9282_video_ops = {
 };
 
 static const struct v4l2_subdev_pad_ops ov9282_pad_ops = {
-	.init_cfg = ov9282_init_cfg,
 	.enum_mbus_code = ov9282_enum_mbus_code,
 	.enum_frame_size = ov9282_enum_frame_size,
 	.get_fmt = ov9282_get_pad_format,
@@ -1206,6 +1205,10 @@ static const struct v4l2_subdev_ops ov9282_subdev_ops = {
 	.pad = &ov9282_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops ov9282_internal_ops = {
+	.init_state = ov9282_init_state,
+};
+
 /**
  * ov9282_power_on() - Sensor power on sequence
  * @dev: pointer to i2c device
@@ -1394,6 +1397,7 @@ static int ov9282_probe(struct i2c_client *client)
 
 	/* Initialize subdev */
 	v4l2_i2c_subdev_init(&ov9282->sd, client, &ov9282_subdev_ops);
+	ov9282->sd.internal_ops = &ov9282_internal_ops;
 	v4l2_i2c_subdev_set_name(&ov9282->sd, client,
 				 device_get_match_data(ov9282->dev), NULL);
 
diff --git a/drivers/media/i2c/st-vgxy61.c b/drivers/media/i2c/st-vgxy61.c
index 507cd9661e9d..98d8975dcd67 100644
--- a/drivers/media/i2c/st-vgxy61.c
+++ b/drivers/media/i2c/st-vgxy61.c
@@ -1322,8 +1322,8 @@ out:
 	return ret;
 }
 
-static int vgxy61_init_cfg(struct v4l2_subdev *sd,
-			   struct v4l2_subdev_state *sd_state)
+static int vgxy61_init_state(struct v4l2_subdev *sd,
+			     struct v4l2_subdev_state *sd_state)
 {
 	struct vgxy61_dev *sensor = to_vgxy61_dev(sd);
 	struct v4l2_subdev_format fmt = { 0 };
@@ -1469,7 +1469,6 @@ static const struct v4l2_subdev_video_ops vgxy61_video_ops = {
 };
 
 static const struct v4l2_subdev_pad_ops vgxy61_pad_ops = {
-	.init_cfg = vgxy61_init_cfg,
 	.enum_mbus_code = vgxy61_enum_mbus_code,
 	.get_fmt = vgxy61_get_fmt,
 	.set_fmt = vgxy61_set_fmt,
@@ -1482,6 +1481,10 @@ static const struct v4l2_subdev_ops vgxy61_subdev_ops = {
 	.pad = &vgxy61_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops vgxy61_internal_ops = {
+	.init_state = vgxy61_init_state,
+};
+
 static const struct media_entity_operations vgxy61_subdev_entity_ops = {
 	.link_validate = v4l2_subdev_link_validate,
 };
@@ -1842,6 +1845,7 @@ static int vgxy61_probe(struct i2c_client *client)
 		device_property_read_bool(dev, "st,strobe-gpios-polarity");
 
 	v4l2_i2c_subdev_init(&sensor->sd, client, &vgxy61_subdev_ops);
+	sensor->sd.internal_ops = &vgxy61_internal_ops;
 	sensor->sd.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
 	sensor->pad.flags = MEDIA_PAD_FL_SOURCE;
 	sensor->sd.entity.ops = &vgxy61_subdev_entity_ops;
diff --git a/drivers/media/i2c/tc358746.c b/drivers/media/i2c/tc358746.c
index 8be9c0f293e0..106de4271d2e 100644
--- a/drivers/media/i2c/tc358746.c
+++ b/drivers/media/i2c/tc358746.c
@@ -740,8 +740,8 @@ err_out:
 	return v4l2_subdev_call(src, video, s_stream, 0);
 }
 
-static int tc358746_init_cfg(struct v4l2_subdev *sd,
-			     struct v4l2_subdev_state *state)
+static int tc358746_init_state(struct v4l2_subdev *sd,
+			       struct v4l2_subdev_state *state)
 {
 	struct v4l2_mbus_framefmt *fmt;
 
@@ -1038,7 +1038,6 @@ static const struct v4l2_subdev_video_ops tc358746_video_ops = {
 };
 
 static const struct v4l2_subdev_pad_ops tc358746_pad_ops = {
-	.init_cfg = tc358746_init_cfg,
 	.enum_mbus_code = tc358746_enum_mbus_code,
 	.set_fmt = tc358746_set_fmt,
 	.get_fmt = v4l2_subdev_get_fmt,
@@ -1052,6 +1051,10 @@ static const struct v4l2_subdev_ops tc358746_ops = {
 	.pad = &tc358746_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops tc358746_internal_ops = {
+	.init_state = tc358746_init_state,
+};
+
 static const struct media_entity_operations tc358746_entity_ops = {
 	.get_fwnode_pad = v4l2_subdev_get_fwnode_pad_1_to_1,
 	.link_validate = v4l2_subdev_link_validate,
@@ -1282,6 +1285,7 @@ tc358746_init_subdev(struct tc358746 *tc358746, struct i2c_client *client)
 	int err;
 
 	v4l2_i2c_subdev_init(sd, client, &tc358746_ops);
+	sd->internal_ops = &tc358746_internal_ops;
 	sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
 	sd->entity.function = MEDIA_ENT_F_VID_IF_BRIDGE;
 	sd->entity.ops = &tc358746_entity_ops;
diff --git a/drivers/media/i2c/tda1997x.c b/drivers/media/i2c/tda1997x.c
index 63c12b77ff1e..1ea703a9909f 100644
--- a/drivers/media/i2c/tda1997x.c
+++ b/drivers/media/i2c/tda1997x.c
@@ -1734,8 +1734,8 @@ static const struct v4l2_subdev_video_ops tda1997x_video_ops = {
  * v4l2_subdev_pad_ops
  */
 
-static int tda1997x_init_cfg(struct v4l2_subdev *sd,
-			     struct v4l2_subdev_state *sd_state)
+static int tda1997x_init_state(struct v4l2_subdev *sd,
+			       struct v4l2_subdev_state *sd_state)
 {
 	struct tda1997x_state *state = to_state(sd);
 	struct v4l2_mbus_framefmt *mf;
@@ -1925,7 +1925,6 @@ static int tda1997x_enum_dv_timings(struct v4l2_subdev *sd,
 }
 
 static const struct v4l2_subdev_pad_ops tda1997x_pad_ops = {
-	.init_cfg = tda1997x_init_cfg,
 	.enum_mbus_code = tda1997x_enum_mbus_code,
 	.get_fmt = tda1997x_get_format,
 	.set_fmt = tda1997x_set_format,
@@ -2047,6 +2046,10 @@ static const struct v4l2_subdev_ops tda1997x_subdev_ops = {
 	.pad = &tda1997x_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops tda1997x_internal_ops = {
+	.init_state = tda1997x_init_state,
+};
+
 /* -----------------------------------------------------------------------------
  * v4l2_controls
  */
@@ -2588,6 +2591,7 @@ static int tda1997x_probe(struct i2c_client *client)
 	/* initialize subdev */
 	sd = &state->sd;
 	v4l2_i2c_subdev_init(sd, client, &tda1997x_subdev_ops);
+	sd->internal_ops = &tda1997x_internal_ops;
 	snprintf(sd->name, sizeof(sd->name), "%s %d-%04x",
 		 id->name, i2c_adapter_id(client->adapter),
 		 client->addr);
diff --git a/drivers/media/i2c/thp7312.c b/drivers/media/i2c/thp7312.c
index 9b387e568603..3d46e428e0ac 100644
--- a/drivers/media/i2c/thp7312.c
+++ b/drivers/media/i2c/thp7312.c
@@ -837,8 +837,8 @@ finish_unlock:
 	return ret;
 }
 
-static int thp7312_init_cfg(struct v4l2_subdev *sd,
-			    struct v4l2_subdev_state *sd_state)
+static int thp7312_init_state(struct v4l2_subdev *sd,
+			      struct v4l2_subdev_state *sd_state)
 {
 	const struct thp7312_mode_info *default_mode = &thp7312_mode_info_data[0];
 	struct v4l2_mbus_framefmt *fmt;
@@ -875,7 +875,6 @@ static const struct v4l2_subdev_video_ops thp7312_video_ops = {
 
 static const struct v4l2_subdev_pad_ops thp7312_pad_ops = {
 	.enum_mbus_code = thp7312_enum_mbus_code,
-	.init_cfg = thp7312_init_cfg,
 	.get_fmt = v4l2_subdev_get_fmt,
 	.set_fmt = thp7312_set_fmt,
 	.enum_frame_size = thp7312_enum_frame_size,
@@ -888,6 +887,10 @@ static const struct v4l2_subdev_ops thp7312_subdev_ops = {
 	.pad = &thp7312_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops thp7312_internal_ops = {
+	.init_state = thp7312_init_state,
+};
+
 /* -----------------------------------------------------------------------------
  * V4L2 Control Operations
  */
@@ -2106,6 +2109,7 @@ static int thp7312_probe(struct i2c_client *client)
 		return thp7312_register_flash_mode(thp7312);
 
 	v4l2_i2c_subdev_init(&thp7312->sd, client, &thp7312_subdev_ops);
+	thp7312->sd.internal_ops = &thp7312_internal_ops;
 	thp7312->sd.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE | V4L2_SUBDEV_FL_HAS_EVENTS;
 	thp7312->pad.flags = MEDIA_PAD_FL_SOURCE;
 	thp7312->sd.entity.function = MEDIA_ENT_F_CAM_SENSOR;
diff --git a/drivers/media/i2c/tvp5150.c b/drivers/media/i2c/tvp5150.c
index 76a92bfb6fde..9fc586cfdcd8 100644
--- a/drivers/media/i2c/tvp5150.c
+++ b/drivers/media/i2c/tvp5150.c
@@ -1209,8 +1209,8 @@ static int tvp5150_get_mbus_config(struct v4l2_subdev *sd,
 /****************************************************************************
 			V4L2 subdev pad ops
  ****************************************************************************/
-static int tvp5150_init_cfg(struct v4l2_subdev *sd,
-			    struct v4l2_subdev_state *sd_state)
+static int tvp5150_init_state(struct v4l2_subdev *sd,
+			      struct v4l2_subdev_state *sd_state)
 {
 	struct tvp5150 *decoder = to_tvp5150(sd);
 	v4l2_std_id std;
@@ -1722,7 +1722,6 @@ static const struct v4l2_subdev_vbi_ops tvp5150_vbi_ops = {
 };
 
 static const struct v4l2_subdev_pad_ops tvp5150_pad_ops = {
-	.init_cfg = tvp5150_init_cfg,
 	.enum_mbus_code = tvp5150_enum_mbus_code,
 	.enum_frame_size = tvp5150_enum_frame_size,
 	.set_fmt = tvp5150_fill_fmt,
@@ -1741,6 +1740,7 @@ static const struct v4l2_subdev_ops tvp5150_ops = {
 };
 
 static const struct v4l2_subdev_internal_ops tvp5150_internal_ops = {
+	.init_state = tvp5150_init_state,
 	.registered = tvp5150_registered,
 	.open = tvp5150_open,
 	.close = tvp5150_close,
diff --git a/drivers/media/pci/intel/ivsc/mei_csi.c b/drivers/media/pci/intel/ivsc/mei_csi.c
index 8bf90e2bd856..15b905f66ab7 100644
--- a/drivers/media/pci/intel/ivsc/mei_csi.c
+++ b/drivers/media/pci/intel/ivsc/mei_csi.c
@@ -346,8 +346,8 @@ mei_csi_get_pad_format(struct v4l2_subdev *sd,
 	}
 }
 
-static int mei_csi_init_cfg(struct v4l2_subdev *sd,
-			    struct v4l2_subdev_state *sd_state)
+static int mei_csi_init_state(struct v4l2_subdev *sd,
+			      struct v4l2_subdev_state *sd_state)
 {
 	struct v4l2_mbus_framefmt *mbusformat;
 	struct mei_csi *csi = sd_to_csi(sd);
@@ -554,7 +554,6 @@ static const struct v4l2_subdev_video_ops mei_csi_video_ops = {
 };
 
 static const struct v4l2_subdev_pad_ops mei_csi_pad_ops = {
-	.init_cfg = mei_csi_init_cfg,
 	.get_fmt = mei_csi_get_fmt,
 	.set_fmt = mei_csi_set_fmt,
 };
@@ -564,6 +563,10 @@ static const struct v4l2_subdev_ops mei_csi_subdev_ops = {
 	.pad = &mei_csi_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops mei_csi_internal_ops = {
+	.init_state = mei_csi_init_state,
+};
+
 static const struct media_entity_operations mei_csi_entity_ops = {
 	.link_validate = v4l2_subdev_link_validate,
 };
@@ -747,6 +750,7 @@ static int mei_csi_probe(struct mei_cl_device *cldev,
 
 	csi->subdev.dev = &cldev->dev;
 	v4l2_subdev_init(&csi->subdev, &mei_csi_subdev_ops);
+	csi->subdev.internal_ops = &mei_csi_internal_ops;
 	v4l2_set_subdevdata(&csi->subdev, csi);
 	csi->subdev.flags = V4L2_SUBDEV_FL_HAS_DEVNODE |
 			    V4L2_SUBDEV_FL_HAS_EVENTS;
diff --git a/drivers/media/platform/cadence/cdns-csi2rx.c b/drivers/media/platform/cadence/cdns-csi2rx.c
index 0171ea7b834d..fead5426830e 100644
--- a/drivers/media/platform/cadence/cdns-csi2rx.c
+++ b/drivers/media/platform/cadence/cdns-csi2rx.c
@@ -418,8 +418,8 @@ static int csi2rx_set_fmt(struct v4l2_subdev *subdev,
 	return 0;
 }
 
-static int csi2rx_init_cfg(struct v4l2_subdev *subdev,
-			   struct v4l2_subdev_state *state)
+static int csi2rx_init_state(struct v4l2_subdev *subdev,
+			     struct v4l2_subdev_state *state)
 {
 	struct v4l2_subdev_format format = {
 		.pad = CSI2RX_PAD_SINK,
@@ -441,7 +441,6 @@ static int csi2rx_init_cfg(struct v4l2_subdev *subdev,
 static const struct v4l2_subdev_pad_ops csi2rx_pad_ops = {
 	.get_fmt	= v4l2_subdev_get_fmt,
 	.set_fmt	= csi2rx_set_fmt,
-	.init_cfg	= csi2rx_init_cfg,
 };
 
 static const struct v4l2_subdev_video_ops csi2rx_video_ops = {
@@ -453,6 +452,10 @@ static const struct v4l2_subdev_ops csi2rx_subdev_ops = {
 	.pad		= &csi2rx_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops csi2rx_internal_ops = {
+	.init_state	= csi2rx_init_state,
+};
+
 static const struct media_entity_operations csi2rx_media_ops = {
 	.link_validate = v4l2_subdev_link_validate,
 };
@@ -663,6 +666,7 @@ static int csi2rx_probe(struct platform_device *pdev)
 	csi2rx->subdev.owner = THIS_MODULE;
 	csi2rx->subdev.dev = &pdev->dev;
 	v4l2_subdev_init(&csi2rx->subdev, &csi2rx_subdev_ops);
+	csi2rx->subdev.internal_ops = &csi2rx_internal_ops;
 	v4l2_set_subdevdata(&csi2rx->subdev, &pdev->dev);
 	snprintf(csi2rx->subdev.name, sizeof(csi2rx->subdev.name),
 		 "%s.%s", KBUILD_MODNAME, dev_name(&pdev->dev));
diff --git a/drivers/media/platform/microchip/microchip-csi2dc.c b/drivers/media/platform/microchip/microchip-csi2dc.c
index 87a2d092aad2..fee73260bb1e 100644
--- a/drivers/media/platform/microchip/microchip-csi2dc.c
+++ b/drivers/media/platform/microchip/microchip-csi2dc.c
@@ -435,8 +435,8 @@ static int csi2dc_s_stream(struct v4l2_subdev *csi2dc_sd, int enable)
 	return ret;
 }
 
-static int csi2dc_init_cfg(struct v4l2_subdev *csi2dc_sd,
-			   struct v4l2_subdev_state *sd_state)
+static int csi2dc_init_state(struct v4l2_subdev *csi2dc_sd,
+			     struct v4l2_subdev_state *sd_state)
 {
 	struct v4l2_mbus_framefmt *v4l2_try_fmt =
 		v4l2_subdev_state_get_format(sd_state, 0);
@@ -461,7 +461,6 @@ static const struct v4l2_subdev_pad_ops csi2dc_pad_ops = {
 	.enum_mbus_code = csi2dc_enum_mbus_code,
 	.set_fmt = csi2dc_set_fmt,
 	.get_fmt = csi2dc_get_fmt,
-	.init_cfg = csi2dc_init_cfg,
 };
 
 static const struct v4l2_subdev_video_ops csi2dc_video_ops = {
@@ -473,6 +472,10 @@ static const struct v4l2_subdev_ops csi2dc_subdev_ops = {
 	.video = &csi2dc_video_ops,
 };
 
+static const struct v4l2_subdev_internal_ops csi2dc_internal_ops = {
+	.init_state = csi2dc_init_state,
+};
+
 static int csi2dc_async_bound(struct v4l2_async_notifier *notifier,
 			      struct v4l2_subdev *subdev,
 			      struct v4l2_async_connection *asd)
@@ -677,6 +680,7 @@ static int csi2dc_probe(struct platform_device *pdev)
 	}
 
 	v4l2_subdev_init(&csi2dc->csi2dc_sd, &csi2dc_subdev_ops);
+	csi2dc->csi2dc_sd.internal_ops = &csi2dc_internal_ops;
 
 	csi2dc->csi2dc_sd.owner = THIS_MODULE;
 	csi2dc->csi2dc_sd.dev = dev;
diff --git a/drivers/media/platform/microchip/microchip-isc-scaler.c b/drivers/media/platform/microchip/microchip-isc-scaler.c
index 58dffbc9fbcb..e83463543e21 100644
--- a/drivers/media/platform/microchip/microchip-isc-scaler.c
+++ b/drivers/media/platform/microchip/microchip-isc-scaler.c
@@ -145,8 +145,8 @@ static int isc_scaler_g_sel(struct v4l2_subdev *sd,
 	return 0;
 }
 
-static int isc_scaler_init_cfg(struct v4l2_subdev *sd,
-			       struct v4l2_subdev_state *sd_state)
+static int isc_scaler_init_state(struct v4l2_subdev *sd,
+				 struct v4l2_subdev_state *sd_state)
 {
 	struct v4l2_mbus_framefmt *v4l2_try_fmt =
 		v4l2_subdev_state_get_format(sd_state, 0);
@@ -170,7 +170,6 @@ static const struct v4l2_subdev_pad_ops isc_scaler_pad_ops = {
 	.set_fmt = isc_scaler_set_fmt,
 	.get_fmt = isc_scaler_get_fmt,
 	.get_selection = isc_scaler_g_sel,
-	.init_cfg = isc_scaler_init_cfg,
 };
 
 static const struct media_entity_operations isc_scaler_entity_ops = {
@@ -181,11 +180,16 @@ static const struct v4l2_subdev_ops xisc_scaler_subdev_ops = {
 	.pad = &isc_scaler_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops isc_scaler_internal_ops = {
+	.init_state = isc_scaler_init_state,
+};
+
 int isc_scaler_init(struct isc_device *isc)
 {
 	int ret;
 
 	v4l2_subdev_init(&isc->scaler_sd, &xisc_scaler_subdev_ops);
+	isc->scaler_sd.internal_ops = &isc_scaler_internal_ops;
 
 	isc->scaler_sd.owner = THIS_MODULE;
 	isc->scaler_sd.dev = isc->dev;
diff --git a/drivers/media/platform/nxp/imx-mipi-csis.c b/drivers/media/platform/nxp/imx-mipi-csis.c
index a2c748217376..b12e2435ef60 100644
--- a/drivers/media/platform/nxp/imx-mipi-csis.c
+++ b/drivers/media/platform/nxp/imx-mipi-csis.c
@@ -1122,8 +1122,8 @@ static int mipi_csis_get_frame_desc(struct v4l2_subdev *sd, unsigned int pad,
 	return 0;
 }
 
-static int mipi_csis_init_cfg(struct v4l2_subdev *sd,
-			      struct v4l2_subdev_state *sd_state)
+static int mipi_csis_init_state(struct v4l2_subdev *sd,
+				struct v4l2_subdev_state *sd_state)
 {
 	struct v4l2_subdev_format fmt = {
 		.pad = CSIS_PAD_SINK,
@@ -1163,7 +1163,6 @@ static const struct v4l2_subdev_video_ops mipi_csis_video_ops = {
 };
 
 static const struct v4l2_subdev_pad_ops mipi_csis_pad_ops = {
-	.init_cfg		= mipi_csis_init_cfg,
 	.enum_mbus_code		= mipi_csis_enum_mbus_code,
 	.get_fmt		= v4l2_subdev_get_fmt,
 	.set_fmt		= mipi_csis_set_fmt,
@@ -1176,6 +1175,10 @@ static const struct v4l2_subdev_ops mipi_csis_subdev_ops = {
 	.pad	= &mipi_csis_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops mipi_csis_internal_ops = {
+	.init_state		= mipi_csis_init_state,
+};
+
 /* -----------------------------------------------------------------------------
  * Media entity operations
  */
@@ -1350,6 +1353,7 @@ static int mipi_csis_subdev_init(struct mipi_csis_device *csis)
 	int ret;
 
 	v4l2_subdev_init(sd, &mipi_csis_subdev_ops);
+	sd->internal_ops = &mipi_csis_internal_ops;
 	sd->owner = THIS_MODULE;
 	snprintf(sd->name, sizeof(sd->name), "csis-%s",
 		 dev_name(csis->dev));
diff --git a/drivers/media/platform/nxp/imx7-media-csi.c b/drivers/media/platform/nxp/imx7-media-csi.c
index 1d2464ca59b8..651151da3ab4 100644
--- a/drivers/media/platform/nxp/imx7-media-csi.c
+++ b/drivers/media/platform/nxp/imx7-media-csi.c
@@ -1729,8 +1729,8 @@ out_unlock:
 	return ret;
 }
 
-static int imx7_csi_init_cfg(struct v4l2_subdev *sd,
-			     struct v4l2_subdev_state *sd_state)
+static int imx7_csi_init_state(struct v4l2_subdev *sd,
+			       struct v4l2_subdev_state *sd_state)
 {
 	const struct imx7_csi_pixfmt *cc;
 	int i;
@@ -2006,7 +2006,6 @@ static const struct v4l2_subdev_video_ops imx7_csi_video_ops = {
 };
 
 static const struct v4l2_subdev_pad_ops imx7_csi_pad_ops = {
-	.init_cfg	= imx7_csi_init_cfg,
 	.enum_mbus_code	= imx7_csi_enum_mbus_code,
 	.get_fmt	= v4l2_subdev_get_fmt,
 	.set_fmt	= imx7_csi_set_fmt,
@@ -2019,6 +2018,7 @@ static const struct v4l2_subdev_ops imx7_csi_subdev_ops = {
 };
 
 static const struct v4l2_subdev_internal_ops imx7_csi_internal_ops = {
+	.init_state	= imx7_csi_init_state,
 	.registered	= imx7_csi_registered,
 	.unregistered	= imx7_csi_unregistered,
 };
diff --git a/drivers/media/platform/nxp/imx8-isi/imx8-isi-crossbar.c b/drivers/media/platform/nxp/imx8-isi/imx8-isi-crossbar.c
index 9401261eb239..575f17337388 100644
--- a/drivers/media/platform/nxp/imx8-isi/imx8-isi-crossbar.c
+++ b/drivers/media/platform/nxp/imx8-isi/imx8-isi-crossbar.c
@@ -176,8 +176,8 @@ mxc_isi_crossbar_xlate_streams(struct mxc_isi_crossbar *xbar,
 	return sd;
 }
 
-static int mxc_isi_crossbar_init_cfg(struct v4l2_subdev *sd,
-				     struct v4l2_subdev_state *state)
+static int mxc_isi_crossbar_init_state(struct v4l2_subdev *sd,
+				       struct v4l2_subdev_state *state)
 {
 	struct mxc_isi_crossbar *xbar = to_isi_crossbar(sd);
 	struct v4l2_subdev_krouting routing = { };
@@ -404,7 +404,6 @@ static int mxc_isi_crossbar_disable_streams(struct v4l2_subdev *sd,
 }
 
 static const struct v4l2_subdev_pad_ops mxc_isi_crossbar_subdev_pad_ops = {
-	.init_cfg = mxc_isi_crossbar_init_cfg,
 	.enum_mbus_code = mxc_isi_crossbar_enum_mbus_code,
 	.get_fmt = v4l2_subdev_get_fmt,
 	.set_fmt = mxc_isi_crossbar_set_fmt,
@@ -417,6 +416,10 @@ static const struct v4l2_subdev_ops mxc_isi_crossbar_subdev_ops = {
 	.pad = &mxc_isi_crossbar_subdev_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops mxc_isi_crossbar_internal_ops = {
+	.init_state = mxc_isi_crossbar_init_state,
+};
+
 static const struct media_entity_operations mxc_isi_cross_entity_ops = {
 	.get_fwnode_pad = v4l2_subdev_get_fwnode_pad_1_to_1,
 	.link_validate	= v4l2_subdev_link_validate,
@@ -438,6 +441,7 @@ int mxc_isi_crossbar_init(struct mxc_isi_dev *isi)
 	xbar->isi = isi;
 
 	v4l2_subdev_init(sd, &mxc_isi_crossbar_subdev_ops);
+	sd->internal_ops = &mxc_isi_crossbar_internal_ops;
 	sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE | V4L2_SUBDEV_FL_STREAMS;
 	strscpy(sd->name, "crossbar", sizeof(sd->name));
 	sd->dev = isi->dev;
diff --git a/drivers/media/platform/nxp/imx8-isi/imx8-isi-pipe.c b/drivers/media/platform/nxp/imx8-isi/imx8-isi-pipe.c
index 14c6da392803..d76eb58deb09 100644
--- a/drivers/media/platform/nxp/imx8-isi/imx8-isi-pipe.c
+++ b/drivers/media/platform/nxp/imx8-isi/imx8-isi-pipe.c
@@ -341,8 +341,8 @@ mxc_isi_pipe_get_pad_compose(struct mxc_isi_pipe *pipe,
 	return v4l2_subdev_state_get_compose(state, pad);
 }
 
-static int mxc_isi_pipe_init_cfg(struct v4l2_subdev *sd,
-				 struct v4l2_subdev_state *state)
+static int mxc_isi_pipe_init_state(struct v4l2_subdev *sd,
+				   struct v4l2_subdev_state *state)
 {
 	struct mxc_isi_pipe *pipe = to_isi_pipe(sd);
 	struct v4l2_mbus_framefmt *fmt_source;
@@ -682,7 +682,6 @@ static int mxc_isi_pipe_set_selection(struct v4l2_subdev *sd,
 }
 
 static const struct v4l2_subdev_pad_ops mxc_isi_pipe_subdev_pad_ops = {
-	.init_cfg = mxc_isi_pipe_init_cfg,
 	.enum_mbus_code = mxc_isi_pipe_enum_mbus_code,
 	.get_fmt = v4l2_subdev_get_fmt,
 	.set_fmt = mxc_isi_pipe_set_fmt,
@@ -694,6 +693,10 @@ static const struct v4l2_subdev_ops mxc_isi_pipe_subdev_ops = {
 	.pad = &mxc_isi_pipe_subdev_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops mxc_isi_pipe_internal_ops = {
+	.init_state = mxc_isi_pipe_init_state,
+};
+
 /* -----------------------------------------------------------------------------
  * IRQ handling
  */
@@ -767,6 +770,7 @@ int mxc_isi_pipe_init(struct mxc_isi_dev *isi, unsigned int id)
 
 	sd = &pipe->sd;
 	v4l2_subdev_init(sd, &mxc_isi_pipe_subdev_ops);
+	sd->internal_ops = &mxc_isi_pipe_internal_ops;
 	sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
 	snprintf(sd->name, sizeof(sd->name), "mxc_isi.%d", pipe->id);
 	sd->dev = isi->dev;
diff --git a/drivers/media/platform/nxp/imx8mq-mipi-csi2.c b/drivers/media/platform/nxp/imx8mq-mipi-csi2.c
index 02a4c546a90a..ba2e81f24965 100644
--- a/drivers/media/platform/nxp/imx8mq-mipi-csi2.c
+++ b/drivers/media/platform/nxp/imx8mq-mipi-csi2.c
@@ -437,8 +437,8 @@ unlock:
 	return ret;
 }
 
-static int imx8mq_mipi_csi_init_cfg(struct v4l2_subdev *sd,
-				    struct v4l2_subdev_state *sd_state)
+static int imx8mq_mipi_csi_init_state(struct v4l2_subdev *sd,
+				      struct v4l2_subdev_state *sd_state)
 {
 	struct v4l2_mbus_framefmt *fmt_sink;
 	struct v4l2_mbus_framefmt *fmt_source;
@@ -535,7 +535,6 @@ static const struct v4l2_subdev_video_ops imx8mq_mipi_csi_video_ops = {
 };
 
 static const struct v4l2_subdev_pad_ops imx8mq_mipi_csi_pad_ops = {
-	.init_cfg		= imx8mq_mipi_csi_init_cfg,
 	.enum_mbus_code		= imx8mq_mipi_csi_enum_mbus_code,
 	.get_fmt		= v4l2_subdev_get_fmt,
 	.set_fmt		= imx8mq_mipi_csi_set_fmt,
@@ -546,6 +545,10 @@ static const struct v4l2_subdev_ops imx8mq_mipi_csi_subdev_ops = {
 	.pad	= &imx8mq_mipi_csi_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops imx8mq_mipi_csi_internal_ops = {
+	.init_state		= imx8mq_mipi_csi_init_state,
+};
+
 /* -----------------------------------------------------------------------------
  * Media entity operations
  */
@@ -760,6 +763,7 @@ static int imx8mq_mipi_csi_subdev_init(struct csi_state *state)
 	int ret;
 
 	v4l2_subdev_init(sd, &imx8mq_mipi_csi_subdev_ops);
+	sd->internal_ops = &imx8mq_mipi_csi_internal_ops;
 	sd->owner = THIS_MODULE;
 	snprintf(sd->name, sizeof(sd->name), "%s %s",
 		 MIPI_CSI2_SUBDEV_NAME, dev_name(state->dev));
diff --git a/drivers/media/platform/renesas/rzg2l-cru/rzg2l-csi2.c b/drivers/media/platform/renesas/rzg2l-cru/rzg2l-csi2.c
index 04e61e783045..d20f4eff93a4 100644
--- a/drivers/media/platform/renesas/rzg2l-cru/rzg2l-csi2.c
+++ b/drivers/media/platform/renesas/rzg2l-cru/rzg2l-csi2.c
@@ -530,8 +530,8 @@ static int rzg2l_csi2_set_format(struct v4l2_subdev *sd,
 	return 0;
 }
 
-static int rzg2l_csi2_init_config(struct v4l2_subdev *sd,
-				  struct v4l2_subdev_state *sd_state)
+static int rzg2l_csi2_init_state(struct v4l2_subdev *sd,
+				 struct v4l2_subdev_state *sd_state)
 {
 	struct v4l2_subdev_format fmt = { .pad = RZG2L_CSI2_SINK, };
 
@@ -582,7 +582,6 @@ static const struct v4l2_subdev_video_ops rzg2l_csi2_video_ops = {
 
 static const struct v4l2_subdev_pad_ops rzg2l_csi2_pad_ops = {
 	.enum_mbus_code = rzg2l_csi2_enum_mbus_code,
-	.init_cfg = rzg2l_csi2_init_config,
 	.enum_frame_size = rzg2l_csi2_enum_frame_size,
 	.set_fmt = rzg2l_csi2_set_format,
 	.get_fmt = v4l2_subdev_get_fmt,
@@ -593,6 +592,10 @@ static const struct v4l2_subdev_ops rzg2l_csi2_subdev_ops = {
 	.pad	= &rzg2l_csi2_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops rzg2l_csi2_internal_ops = {
+	.init_state = rzg2l_csi2_init_state,
+};
+
 /* -----------------------------------------------------------------------------
  * Async handling and registration of subdevices and links.
  */
@@ -777,6 +780,7 @@ static int rzg2l_csi2_probe(struct platform_device *pdev)
 
 	csi2->subdev.dev = &pdev->dev;
 	v4l2_subdev_init(&csi2->subdev, &rzg2l_csi2_subdev_ops);
+	csi2->subdev.internal_ops = &rzg2l_csi2_internal_ops;
 	v4l2_set_subdevdata(&csi2->subdev, &pdev->dev);
 	snprintf(csi2->subdev.name, sizeof(csi2->subdev.name),
 		 "csi-%s", dev_name(&pdev->dev));
diff --git a/drivers/media/platform/renesas/rzg2l-cru/rzg2l-ip.c b/drivers/media/platform/renesas/rzg2l-cru/rzg2l-ip.c
index 17a59dfc8363..9f351a05893e 100644
--- a/drivers/media/platform/renesas/rzg2l-cru/rzg2l-ip.c
+++ b/drivers/media/platform/renesas/rzg2l-cru/rzg2l-ip.c
@@ -168,8 +168,8 @@ static int rzg2l_cru_ip_enum_frame_size(struct v4l2_subdev *sd,
 	return 0;
 }
 
-static int rzg2l_cru_ip_init_config(struct v4l2_subdev *sd,
-				    struct v4l2_subdev_state *sd_state)
+static int rzg2l_cru_ip_init_state(struct v4l2_subdev *sd,
+				   struct v4l2_subdev_state *sd_state)
 {
 	struct v4l2_subdev_format fmt = { .pad = RZG2L_CRU_IP_SINK, };
 
@@ -192,7 +192,6 @@ static const struct v4l2_subdev_video_ops rzg2l_cru_ip_video_ops = {
 static const struct v4l2_subdev_pad_ops rzg2l_cru_ip_pad_ops = {
 	.enum_mbus_code = rzg2l_cru_ip_enum_mbus_code,
 	.enum_frame_size = rzg2l_cru_ip_enum_frame_size,
-	.init_cfg = rzg2l_cru_ip_init_config,
 	.get_fmt = v4l2_subdev_get_fmt,
 	.set_fmt = rzg2l_cru_ip_set_format,
 };
@@ -202,6 +201,10 @@ static const struct v4l2_subdev_ops rzg2l_cru_ip_subdev_ops = {
 	.pad = &rzg2l_cru_ip_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops rzg2l_cru_ip_internal_ops = {
+	.init_state = rzg2l_cru_ip_init_state,
+};
+
 static const struct media_entity_operations rzg2l_cru_ip_entity_ops = {
 	.link_validate = v4l2_subdev_link_validate,
 };
@@ -213,6 +216,7 @@ int rzg2l_cru_ip_subdev_register(struct rzg2l_cru_dev *cru)
 
 	ip->subdev.dev = cru->dev;
 	v4l2_subdev_init(&ip->subdev, &rzg2l_cru_ip_subdev_ops);
+	ip->subdev.internal_ops = &rzg2l_cru_ip_internal_ops;
 	v4l2_set_subdevdata(&ip->subdev, cru);
 	snprintf(ip->subdev.name, sizeof(ip->subdev.name),
 		 "cru-ip-%s", dev_name(cru->dev));
diff --git a/drivers/media/platform/renesas/vsp1/vsp1_brx.c b/drivers/media/platform/renesas/vsp1/vsp1_brx.c
index 758525a03289..a8535c6e2c46 100644
--- a/drivers/media/platform/renesas/vsp1/vsp1_brx.c
+++ b/drivers/media/platform/renesas/vsp1/vsp1_brx.c
@@ -264,7 +264,6 @@ done:
 }
 
 static const struct v4l2_subdev_pad_ops brx_pad_ops = {
-	.init_cfg = vsp1_entity_init_cfg,
 	.enum_mbus_code = brx_enum_mbus_code,
 	.enum_frame_size = brx_enum_frame_size,
 	.get_fmt = vsp1_subdev_get_pad_format,
diff --git a/drivers/media/platform/renesas/vsp1/vsp1_clu.c b/drivers/media/platform/renesas/vsp1/vsp1_clu.c
index 50a5c0dc0e86..625776a9bda4 100644
--- a/drivers/media/platform/renesas/vsp1/vsp1_clu.c
+++ b/drivers/media/platform/renesas/vsp1/vsp1_clu.c
@@ -155,7 +155,6 @@ static int clu_set_format(struct v4l2_subdev *subdev,
  */
 
 static const struct v4l2_subdev_pad_ops clu_pad_ops = {
-	.init_cfg = vsp1_entity_init_cfg,
 	.enum_mbus_code = clu_enum_mbus_code,
 	.enum_frame_size = clu_enum_frame_size,
 	.get_fmt = vsp1_subdev_get_pad_format,
diff --git a/drivers/media/platform/renesas/vsp1/vsp1_entity.c b/drivers/media/platform/renesas/vsp1/vsp1_entity.c
index 0280b8ff7ba9..0a5a7f9cc870 100644
--- a/drivers/media/platform/renesas/vsp1/vsp1_entity.c
+++ b/drivers/media/platform/renesas/vsp1/vsp1_entity.c
@@ -170,33 +170,6 @@ vsp1_entity_get_pad_selection(struct vsp1_entity *entity,
 	}
 }
 
-/*
- * vsp1_entity_init_cfg - Initialize formats on all pads
- * @subdev: V4L2 subdevice
- * @sd_state: V4L2 subdev state
- *
- * Initialize all pad formats with default values in the given subdev state.
- * This function can be used as a handler for the subdev pad::init_cfg
- * operation.
- */
-int vsp1_entity_init_cfg(struct v4l2_subdev *subdev,
-			 struct v4l2_subdev_state *sd_state)
-{
-	unsigned int pad;
-
-	for (pad = 0; pad < subdev->entity.num_pads - 1; ++pad) {
-		struct v4l2_subdev_format format = {
-			.pad = pad,
-			.which = sd_state ? V4L2_SUBDEV_FORMAT_TRY
-			       : V4L2_SUBDEV_FORMAT_ACTIVE,
-		};
-
-		v4l2_subdev_call(subdev, pad, set_fmt, sd_state, &format);
-	}
-
-	return 0;
-}
-
 /*
  * vsp1_subdev_get_pad_format - Subdev pad get_fmt handler
  * @subdev: V4L2 subdevice
@@ -424,6 +397,29 @@ done:
 	return ret;
 }
 
+static int vsp1_entity_init_state(struct v4l2_subdev *subdev,
+				  struct v4l2_subdev_state *sd_state)
+{
+	unsigned int pad;
+
+	/* Initialize all pad formats with default values. */
+	for (pad = 0; pad < subdev->entity.num_pads - 1; ++pad) {
+		struct v4l2_subdev_format format = {
+			.pad = pad,
+			.which = sd_state ? V4L2_SUBDEV_FORMAT_TRY
+			       : V4L2_SUBDEV_FORMAT_ACTIVE,
+		};
+
+		v4l2_subdev_call(subdev, pad, set_fmt, sd_state, &format);
+	}
+
+	return 0;
+}
+
+static const struct v4l2_subdev_internal_ops vsp1_entity_internal_ops = {
+	.init_state = vsp1_entity_init_state,
+};
+
 /* -----------------------------------------------------------------------------
  * Media Operations
  */
@@ -658,6 +654,7 @@ int vsp1_entity_init(struct vsp1_device *vsp1, struct vsp1_entity *entity,
 	/* Initialize the V4L2 subdev. */
 	subdev = &entity->subdev;
 	v4l2_subdev_init(subdev, ops);
+	subdev->internal_ops = &vsp1_entity_internal_ops;
 
 	subdev->entity.function = function;
 	subdev->entity.ops = &vsp1->media_ops;
@@ -666,7 +663,7 @@ int vsp1_entity_init(struct vsp1_device *vsp1, struct vsp1_entity *entity,
 	snprintf(subdev->name, sizeof(subdev->name), "%s %s",
 		 dev_name(vsp1->dev), name);
 
-	vsp1_entity_init_cfg(subdev, NULL);
+	vsp1_entity_init_state(subdev, NULL);
 
 	/*
 	 * Allocate the subdev state to store formats and selection
diff --git a/drivers/media/platform/renesas/vsp1/vsp1_entity.h b/drivers/media/platform/renesas/vsp1/vsp1_entity.h
index 8c737cadee81..735f32dde4b5 100644
--- a/drivers/media/platform/renesas/vsp1/vsp1_entity.h
+++ b/drivers/media/platform/renesas/vsp1/vsp1_entity.h
@@ -146,8 +146,6 @@ struct v4l2_rect *
 vsp1_entity_get_pad_selection(struct vsp1_entity *entity,
 			      struct v4l2_subdev_state *sd_state,
 			      unsigned int pad, unsigned int target);
-int vsp1_entity_init_cfg(struct v4l2_subdev *subdev,
-			 struct v4l2_subdev_state *sd_state);
 
 void vsp1_entity_route_setup(struct vsp1_entity *entity,
 			     struct vsp1_pipeline *pipe,
diff --git a/drivers/media/platform/renesas/vsp1/vsp1_hsit.c b/drivers/media/platform/renesas/vsp1/vsp1_hsit.c
index 6342ac7bdf54..bc1299c29ac9 100644
--- a/drivers/media/platform/renesas/vsp1/vsp1_hsit.c
+++ b/drivers/media/platform/renesas/vsp1/vsp1_hsit.c
@@ -113,7 +113,6 @@ done:
 }
 
 static const struct v4l2_subdev_pad_ops hsit_pad_ops = {
-	.init_cfg = vsp1_entity_init_cfg,
 	.enum_mbus_code = hsit_enum_mbus_code,
 	.enum_frame_size = hsit_enum_frame_size,
 	.get_fmt = vsp1_subdev_get_pad_format,
diff --git a/drivers/media/platform/renesas/vsp1/vsp1_lif.c b/drivers/media/platform/renesas/vsp1/vsp1_lif.c
index 75c24df41a7a..b1d21a54837b 100644
--- a/drivers/media/platform/renesas/vsp1/vsp1_lif.c
+++ b/drivers/media/platform/renesas/vsp1/vsp1_lif.c
@@ -68,7 +68,6 @@ static int lif_set_format(struct v4l2_subdev *subdev,
 }
 
 static const struct v4l2_subdev_pad_ops lif_pad_ops = {
-	.init_cfg = vsp1_entity_init_cfg,
 	.enum_mbus_code = lif_enum_mbus_code,
 	.enum_frame_size = lif_enum_frame_size,
 	.get_fmt = vsp1_subdev_get_pad_format,
diff --git a/drivers/media/platform/renesas/vsp1/vsp1_lut.c b/drivers/media/platform/renesas/vsp1/vsp1_lut.c
index ac6802a325f5..451d24ab0b56 100644
--- a/drivers/media/platform/renesas/vsp1/vsp1_lut.c
+++ b/drivers/media/platform/renesas/vsp1/vsp1_lut.c
@@ -131,7 +131,6 @@ static int lut_set_format(struct v4l2_subdev *subdev,
  */
 
 static const struct v4l2_subdev_pad_ops lut_pad_ops = {
-	.init_cfg = vsp1_entity_init_cfg,
 	.enum_mbus_code = lut_enum_mbus_code,
 	.enum_frame_size = lut_enum_frame_size,
 	.get_fmt = vsp1_subdev_get_pad_format,
diff --git a/drivers/media/platform/renesas/vsp1/vsp1_rwpf.c b/drivers/media/platform/renesas/vsp1/vsp1_rwpf.c
index cb3ab351b7de..09fb6ffa14e2 100644
--- a/drivers/media/platform/renesas/vsp1/vsp1_rwpf.c
+++ b/drivers/media/platform/renesas/vsp1/vsp1_rwpf.c
@@ -240,7 +240,6 @@ done:
 }
 
 static const struct v4l2_subdev_pad_ops vsp1_rwpf_pad_ops = {
-	.init_cfg = vsp1_entity_init_cfg,
 	.enum_mbus_code = vsp1_rwpf_enum_mbus_code,
 	.enum_frame_size = vsp1_rwpf_enum_frame_size,
 	.get_fmt = vsp1_subdev_get_pad_format,
diff --git a/drivers/media/platform/renesas/vsp1/vsp1_sru.c b/drivers/media/platform/renesas/vsp1/vsp1_sru.c
index 2dd6f8575614..11e008aa9f20 100644
--- a/drivers/media/platform/renesas/vsp1/vsp1_sru.c
+++ b/drivers/media/platform/renesas/vsp1/vsp1_sru.c
@@ -252,7 +252,6 @@ done:
 }
 
 static const struct v4l2_subdev_pad_ops sru_pad_ops = {
-	.init_cfg = vsp1_entity_init_cfg,
 	.enum_mbus_code = sru_enum_mbus_code,
 	.enum_frame_size = sru_enum_frame_size,
 	.get_fmt = vsp1_subdev_get_pad_format,
diff --git a/drivers/media/platform/renesas/vsp1/vsp1_uds.c b/drivers/media/platform/renesas/vsp1/vsp1_uds.c
index 59ff4ae46cea..d89f1197b86c 100644
--- a/drivers/media/platform/renesas/vsp1/vsp1_uds.c
+++ b/drivers/media/platform/renesas/vsp1/vsp1_uds.c
@@ -239,7 +239,6 @@ done:
  */
 
 static const struct v4l2_subdev_pad_ops uds_pad_ops = {
-	.init_cfg = vsp1_entity_init_cfg,
 	.enum_mbus_code = uds_enum_mbus_code,
 	.enum_frame_size = uds_enum_frame_size,
 	.get_fmt = vsp1_subdev_get_pad_format,
diff --git a/drivers/media/platform/renesas/vsp1/vsp1_uif.c b/drivers/media/platform/renesas/vsp1/vsp1_uif.c
index d84d10f35090..f66936a28a2a 100644
--- a/drivers/media/platform/renesas/vsp1/vsp1_uif.c
+++ b/drivers/media/platform/renesas/vsp1/vsp1_uif.c
@@ -174,7 +174,6 @@ done:
  */
 
 static const struct v4l2_subdev_pad_ops uif_pad_ops = {
-	.init_cfg = vsp1_entity_init_cfg,
 	.enum_mbus_code = uif_enum_mbus_code,
 	.enum_frame_size = uif_enum_frame_size,
 	.get_fmt = vsp1_subdev_get_pad_format,
diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-csi.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-csi.c
index 47f4353a1784..e6642a2167ef 100644
--- a/drivers/media/platform/rockchip/rkisp1/rkisp1-csi.c
+++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-csi.c
@@ -270,8 +270,8 @@ static int rkisp1_csi_enum_mbus_code(struct v4l2_subdev *sd,
 	return -EINVAL;
 }
 
-static int rkisp1_csi_init_config(struct v4l2_subdev *sd,
-				  struct v4l2_subdev_state *sd_state)
+static int rkisp1_csi_init_state(struct v4l2_subdev *sd,
+				 struct v4l2_subdev_state *sd_state)
 {
 	struct v4l2_mbus_framefmt *sink_fmt, *src_fmt;
 
@@ -405,7 +405,6 @@ static const struct v4l2_subdev_video_ops rkisp1_csi_video_ops = {
 
 static const struct v4l2_subdev_pad_ops rkisp1_csi_pad_ops = {
 	.enum_mbus_code = rkisp1_csi_enum_mbus_code,
-	.init_cfg = rkisp1_csi_init_config,
 	.get_fmt = v4l2_subdev_get_fmt,
 	.set_fmt = rkisp1_csi_set_fmt,
 };
@@ -415,6 +414,10 @@ static const struct v4l2_subdev_ops rkisp1_csi_ops = {
 	.pad = &rkisp1_csi_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops rkisp1_csi_internal_ops = {
+	.init_state = rkisp1_csi_init_state,
+};
+
 int rkisp1_csi_register(struct rkisp1_device *rkisp1)
 {
 	struct rkisp1_csi *csi = &rkisp1->csi;
@@ -426,6 +429,7 @@ int rkisp1_csi_register(struct rkisp1_device *rkisp1)
 
 	sd = &csi->sd;
 	v4l2_subdev_init(sd, &rkisp1_csi_ops);
+	sd->internal_ops = &rkisp1_csi_internal_ops;
 	sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
 	sd->entity.ops = &rkisp1_csi_media_ops;
 	sd->entity.function = MEDIA_ENT_F_VID_IF_BRIDGE;
diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-isp.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-isp.c
index 96353648c032..ca6703bfd27b 100644
--- a/drivers/media/platform/rockchip/rkisp1/rkisp1-isp.c
+++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-isp.c
@@ -409,8 +409,8 @@ static int rkisp1_isp_enum_frame_size(struct v4l2_subdev *sd,
 	return 0;
 }
 
-static int rkisp1_isp_init_config(struct v4l2_subdev *sd,
-				  struct v4l2_subdev_state *sd_state)
+static int rkisp1_isp_init_state(struct v4l2_subdev *sd,
+				 struct v4l2_subdev_state *sd_state)
 {
 	struct v4l2_mbus_framefmt *sink_fmt, *src_fmt;
 	struct v4l2_rect *sink_crop, *src_crop;
@@ -769,7 +769,6 @@ static const struct v4l2_subdev_pad_ops rkisp1_isp_pad_ops = {
 	.enum_frame_size = rkisp1_isp_enum_frame_size,
 	.get_selection = rkisp1_isp_get_selection,
 	.set_selection = rkisp1_isp_set_selection,
-	.init_cfg = rkisp1_isp_init_config,
 	.get_fmt = v4l2_subdev_get_fmt,
 	.set_fmt = rkisp1_isp_set_fmt,
 	.link_validate = v4l2_subdev_link_validate_default,
@@ -880,6 +879,10 @@ static const struct v4l2_subdev_ops rkisp1_isp_ops = {
 	.pad = &rkisp1_isp_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops rkisp1_isp_internal_ops = {
+	.init_state = rkisp1_isp_init_state,
+};
+
 int rkisp1_isp_register(struct rkisp1_device *rkisp1)
 {
 	struct rkisp1_isp *isp = &rkisp1->isp;
@@ -890,6 +893,7 @@ int rkisp1_isp_register(struct rkisp1_device *rkisp1)
 	isp->rkisp1 = rkisp1;
 
 	v4l2_subdev_init(sd, &rkisp1_isp_ops);
+	sd->internal_ops = &rkisp1_isp_internal_ops;
 	sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE | V4L2_SUBDEV_FL_HAS_EVENTS;
 	sd->entity.ops = &rkisp1_isp_media_ops;
 	sd->entity.function = MEDIA_ENT_F_PROC_VIDEO_PIXEL_FORMATTER;
diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-resizer.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-resizer.c
index 9f94b9f60c35..f7af360dcb28 100644
--- a/drivers/media/platform/rockchip/rkisp1/rkisp1-resizer.c
+++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-resizer.c
@@ -366,8 +366,8 @@ static int rkisp1_rsz_enum_mbus_code(struct v4l2_subdev *sd,
 	return ret;
 }
 
-static int rkisp1_rsz_init_config(struct v4l2_subdev *sd,
-				  struct v4l2_subdev_state *sd_state)
+static int rkisp1_rsz_init_state(struct v4l2_subdev *sd,
+				 struct v4l2_subdev_state *sd_state)
 {
 	struct v4l2_mbus_framefmt *sink_fmt, *src_fmt;
 	struct v4l2_rect *sink_crop;
@@ -605,7 +605,6 @@ static const struct v4l2_subdev_pad_ops rkisp1_rsz_pad_ops = {
 	.enum_mbus_code = rkisp1_rsz_enum_mbus_code,
 	.get_selection = rkisp1_rsz_get_selection,
 	.set_selection = rkisp1_rsz_set_selection,
-	.init_cfg = rkisp1_rsz_init_config,
 	.get_fmt = v4l2_subdev_get_fmt,
 	.set_fmt = rkisp1_rsz_set_fmt,
 	.link_validate = v4l2_subdev_link_validate_default,
@@ -652,6 +651,10 @@ static const struct v4l2_subdev_ops rkisp1_rsz_ops = {
 	.pad = &rkisp1_rsz_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops rkisp1_rsz_internal_ops = {
+	.init_state = rkisp1_rsz_init_state,
+};
+
 static void rkisp1_rsz_unregister(struct rkisp1_resizer *rsz)
 {
 	if (!rsz->rkisp1)
@@ -681,6 +684,7 @@ static int rkisp1_rsz_register(struct rkisp1_resizer *rsz)
 	}
 
 	v4l2_subdev_init(sd, &rkisp1_rsz_ops);
+	sd->internal_ops = &rkisp1_rsz_internal_ops;
 	sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
 	sd->entity.ops = &rkisp1_rsz_media_ops;
 	sd->entity.function = MEDIA_ENT_F_PROC_VIDEO_SCALER;
diff --git a/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c b/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c
index ad13d447d483..097a3a08ef7d 100644
--- a/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c
+++ b/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c
@@ -211,6 +211,7 @@ static int sun4i_csi_probe(struct platform_device *pdev)
 
 	/* Initialize subdev */
 	v4l2_subdev_init(subdev, &sun4i_csi_subdev_ops);
+	subdev->internal_ops = &sun4i_csi_subdev_internal_ops;
 	subdev->flags = V4L2_SUBDEV_FL_HAS_DEVNODE | V4L2_SUBDEV_FL_HAS_EVENTS;
 	subdev->entity.function = MEDIA_ENT_F_VID_IF_BRIDGE;
 	subdev->owner = THIS_MODULE;
diff --git a/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.h b/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.h
index 8eeed87bfb13..4e0c2df45d4d 100644
--- a/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.h
+++ b/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.h
@@ -89,6 +89,7 @@ enum csi_subdev_pads {
 };
 
 extern const struct v4l2_subdev_ops sun4i_csi_subdev_ops;
+extern const struct v4l2_subdev_internal_ops sun4i_csi_subdev_internal_ops;
 
 struct sun4i_csi_format {
 	u32			mbus;
diff --git a/drivers/media/platform/sunxi/sun4i-csi/sun4i_v4l2.c b/drivers/media/platform/sunxi/sun4i-csi/sun4i_v4l2.c
index c37bb1d76ef6..744197b0fccb 100644
--- a/drivers/media/platform/sunxi/sun4i-csi/sun4i_v4l2.c
+++ b/drivers/media/platform/sunxi/sun4i-csi/sun4i_v4l2.c
@@ -266,8 +266,8 @@ static const struct v4l2_mbus_framefmt sun4i_csi_pad_fmt_default = {
 	.xfer_func = V4L2_XFER_FUNC_DEFAULT,
 };
 
-static int sun4i_csi_subdev_init_cfg(struct v4l2_subdev *subdev,
-				     struct v4l2_subdev_state *sd_state)
+static int sun4i_csi_subdev_init_state(struct v4l2_subdev *subdev,
+				       struct v4l2_subdev_state *sd_state)
 {
 	struct v4l2_mbus_framefmt *fmt;
 
@@ -334,7 +334,6 @@ sun4i_csi_subdev_enum_mbus_code(struct v4l2_subdev *subdev,
 
 static const struct v4l2_subdev_pad_ops sun4i_csi_subdev_pad_ops = {
 	.link_validate	= v4l2_subdev_link_validate_default,
-	.init_cfg	= sun4i_csi_subdev_init_cfg,
 	.get_fmt	= sun4i_csi_subdev_get_fmt,
 	.set_fmt	= sun4i_csi_subdev_set_fmt,
 	.enum_mbus_code	= sun4i_csi_subdev_enum_mbus_code,
@@ -344,6 +343,10 @@ const struct v4l2_subdev_ops sun4i_csi_subdev_ops = {
 	.pad = &sun4i_csi_subdev_pad_ops,
 };
 
+const struct v4l2_subdev_internal_ops sun4i_csi_subdev_internal_ops = {
+	.init_state	= sun4i_csi_subdev_init_state,
+};
+
 int sun4i_csi_v4l2_register(struct sun4i_csi *csi)
 {
 	struct video_device *vdev = &csi->vdev;
diff --git a/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi_bridge.c b/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi_bridge.c
index d57481feee05..d006d9dd0170 100644
--- a/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi_bridge.c
+++ b/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi_bridge.c
@@ -501,8 +501,8 @@ sun6i_csi_bridge_mbus_format_prepare(struct v4l2_mbus_framefmt *mbus_format)
 	mbus_format->xfer_func = V4L2_XFER_FUNC_DEFAULT;
 }
 
-static int sun6i_csi_bridge_init_cfg(struct v4l2_subdev *subdev,
-				     struct v4l2_subdev_state *state)
+static int sun6i_csi_bridge_init_state(struct v4l2_subdev *subdev,
+				       struct v4l2_subdev_state *state)
 {
 	struct sun6i_csi_device *csi_dev = v4l2_get_subdevdata(subdev);
 	unsigned int pad = SUN6I_CSI_BRIDGE_PAD_SINK;
@@ -581,7 +581,6 @@ static int sun6i_csi_bridge_set_fmt(struct v4l2_subdev *subdev,
 }
 
 static const struct v4l2_subdev_pad_ops sun6i_csi_bridge_pad_ops = {
-	.init_cfg	= sun6i_csi_bridge_init_cfg,
 	.enum_mbus_code	= sun6i_csi_bridge_enum_mbus_code,
 	.get_fmt	= sun6i_csi_bridge_get_fmt,
 	.set_fmt	= sun6i_csi_bridge_set_fmt,
@@ -592,6 +591,10 @@ static const struct v4l2_subdev_ops sun6i_csi_bridge_subdev_ops = {
 	.pad	= &sun6i_csi_bridge_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops sun6i_csi_bridge_internal_ops = {
+	.init_state	= sun6i_csi_bridge_init_state,
+};
+
 /* Media Entity */
 
 static const struct media_entity_operations sun6i_csi_bridge_entity_ops = {
@@ -782,6 +785,7 @@ int sun6i_csi_bridge_setup(struct sun6i_csi_device *csi_dev)
 	/* V4L2 Subdev */
 
 	v4l2_subdev_init(subdev, &sun6i_csi_bridge_subdev_ops);
+	subdev->internal_ops = &sun6i_csi_bridge_internal_ops;
 	strscpy(subdev->name, SUN6I_CSI_BRIDGE_NAME, sizeof(subdev->name));
 	subdev->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
 	subdev->owner = THIS_MODULE;
diff --git a/drivers/media/platform/sunxi/sun6i-mipi-csi2/sun6i_mipi_csi2.c b/drivers/media/platform/sunxi/sun6i-mipi-csi2/sun6i_mipi_csi2.c
index d2c9f5d20496..f9d4dc45b490 100644
--- a/drivers/media/platform/sunxi/sun6i-mipi-csi2/sun6i_mipi_csi2.c
+++ b/drivers/media/platform/sunxi/sun6i-mipi-csi2/sun6i_mipi_csi2.c
@@ -305,8 +305,8 @@ sun6i_mipi_csi2_mbus_format_prepare(struct v4l2_mbus_framefmt *mbus_format)
 	mbus_format->xfer_func = V4L2_XFER_FUNC_DEFAULT;
 }
 
-static int sun6i_mipi_csi2_init_cfg(struct v4l2_subdev *subdev,
-				    struct v4l2_subdev_state *state)
+static int sun6i_mipi_csi2_init_state(struct v4l2_subdev *subdev,
+				      struct v4l2_subdev_state *state)
 {
 	struct sun6i_mipi_csi2_device *csi2_dev = v4l2_get_subdevdata(subdev);
 	unsigned int pad = SUN6I_MIPI_CSI2_PAD_SINK;
@@ -385,7 +385,6 @@ static int sun6i_mipi_csi2_set_fmt(struct v4l2_subdev *subdev,
 }
 
 static const struct v4l2_subdev_pad_ops sun6i_mipi_csi2_pad_ops = {
-	.init_cfg	= sun6i_mipi_csi2_init_cfg,
 	.enum_mbus_code	= sun6i_mipi_csi2_enum_mbus_code,
 	.get_fmt	= sun6i_mipi_csi2_get_fmt,
 	.set_fmt	= sun6i_mipi_csi2_set_fmt,
@@ -396,6 +395,10 @@ static const struct v4l2_subdev_ops sun6i_mipi_csi2_subdev_ops = {
 	.pad	= &sun6i_mipi_csi2_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops sun6i_mipi_csi2_internal_ops = {
+	.init_state	= sun6i_mipi_csi2_init_state,
+};
+
 /* Media Entity */
 
 static const struct media_entity_operations sun6i_mipi_csi2_entity_ops = {
@@ -504,6 +507,7 @@ static int sun6i_mipi_csi2_bridge_setup(struct sun6i_mipi_csi2_device *csi2_dev)
 	/* V4L2 Subdev */
 
 	v4l2_subdev_init(subdev, &sun6i_mipi_csi2_subdev_ops);
+	subdev->internal_ops = &sun6i_mipi_csi2_internal_ops;
 	strscpy(subdev->name, SUN6I_MIPI_CSI2_NAME, sizeof(subdev->name));
 	subdev->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
 	subdev->owner = THIS_MODULE;
diff --git a/drivers/media/platform/sunxi/sun8i-a83t-mipi-csi2/sun8i_a83t_mipi_csi2.c b/drivers/media/platform/sunxi/sun8i-a83t-mipi-csi2/sun8i_a83t_mipi_csi2.c
index d6275954af98..4a5698eb12b7 100644
--- a/drivers/media/platform/sunxi/sun8i-a83t-mipi-csi2/sun8i_a83t_mipi_csi2.c
+++ b/drivers/media/platform/sunxi/sun8i-a83t-mipi-csi2/sun8i_a83t_mipi_csi2.c
@@ -338,8 +338,8 @@ sun8i_a83t_mipi_csi2_mbus_format_prepare(struct v4l2_mbus_framefmt *mbus_format)
 	mbus_format->xfer_func = V4L2_XFER_FUNC_DEFAULT;
 }
 
-static int sun8i_a83t_mipi_csi2_init_cfg(struct v4l2_subdev *subdev,
-					 struct v4l2_subdev_state *state)
+static int sun8i_a83t_mipi_csi2_init_state(struct v4l2_subdev *subdev,
+					   struct v4l2_subdev_state *state)
 {
 	struct sun8i_a83t_mipi_csi2_device *csi2_dev =
 		v4l2_get_subdevdata(subdev);
@@ -422,7 +422,6 @@ static int sun8i_a83t_mipi_csi2_set_fmt(struct v4l2_subdev *subdev,
 }
 
 static const struct v4l2_subdev_pad_ops sun8i_a83t_mipi_csi2_pad_ops = {
-	.init_cfg	= sun8i_a83t_mipi_csi2_init_cfg,
 	.enum_mbus_code	= sun8i_a83t_mipi_csi2_enum_mbus_code,
 	.get_fmt	= sun8i_a83t_mipi_csi2_get_fmt,
 	.set_fmt	= sun8i_a83t_mipi_csi2_set_fmt,
@@ -433,6 +432,10 @@ static const struct v4l2_subdev_ops sun8i_a83t_mipi_csi2_subdev_ops = {
 	.pad	= &sun8i_a83t_mipi_csi2_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops sun8i_a83t_mipi_csi2_internal_ops = {
+	.init_state	= sun8i_a83t_mipi_csi2_init_state,
+};
+
 /* Media Entity */
 
 static const struct media_entity_operations sun8i_a83t_mipi_csi2_entity_ops = {
@@ -542,6 +545,7 @@ sun8i_a83t_mipi_csi2_bridge_setup(struct sun8i_a83t_mipi_csi2_device *csi2_dev)
 	/* V4L2 Subdev */
 
 	v4l2_subdev_init(subdev, &sun8i_a83t_mipi_csi2_subdev_ops);
+	subdev->internal_ops = &sun8i_a83t_mipi_csi2_internal_ops;
 	strscpy(subdev->name, SUN8I_A83T_MIPI_CSI2_NAME, sizeof(subdev->name));
 	subdev->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
 	subdev->owner = THIS_MODULE;
diff --git a/drivers/media/platform/ti/cal/cal-camerarx.c b/drivers/media/platform/ti/cal/cal-camerarx.c
index 61433744c6c4..4afc2ad00330 100644
--- a/drivers/media/platform/ti/cal/cal-camerarx.c
+++ b/drivers/media/platform/ti/cal/cal-camerarx.c
@@ -721,8 +721,8 @@ static int cal_camerarx_sd_set_fmt(struct v4l2_subdev *sd,
 	return 0;
 }
 
-static int cal_camerarx_sd_init_cfg(struct v4l2_subdev *sd,
-				    struct v4l2_subdev_state *state)
+static int cal_camerarx_sd_init_state(struct v4l2_subdev *sd,
+				      struct v4l2_subdev_state *state)
 {
 	struct v4l2_subdev_format format = {
 		.which = state ? V4L2_SUBDEV_FORMAT_TRY
@@ -782,7 +782,6 @@ static const struct v4l2_subdev_video_ops cal_camerarx_video_ops = {
 };
 
 static const struct v4l2_subdev_pad_ops cal_camerarx_pad_ops = {
-	.init_cfg = cal_camerarx_sd_init_cfg,
 	.enum_mbus_code = cal_camerarx_sd_enum_mbus_code,
 	.enum_frame_size = cal_camerarx_sd_enum_frame_size,
 	.get_fmt = v4l2_subdev_get_fmt,
@@ -795,6 +794,10 @@ static const struct v4l2_subdev_ops cal_camerarx_subdev_ops = {
 	.pad = &cal_camerarx_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops cal_camerarx_internal_ops = {
+	.init_state = cal_camerarx_sd_init_state,
+};
+
 static struct media_entity_operations cal_camerarx_media_ops = {
 	.link_validate = v4l2_subdev_link_validate,
 };
@@ -846,6 +849,7 @@ struct cal_camerarx *cal_camerarx_create(struct cal_dev *cal,
 	/* Initialize the V4L2 subdev and media entity. */
 	sd = &phy->subdev;
 	v4l2_subdev_init(sd, &cal_camerarx_subdev_ops);
+	sd->internal_ops = &cal_camerarx_internal_ops;
 	sd->entity.function = MEDIA_ENT_F_VID_IF_BRIDGE;
 	sd->flags = V4L2_SUBDEV_FL_HAS_DEVNODE;
 	snprintf(sd->name, sizeof(sd->name), "CAMERARX%u", instance);
diff --git a/drivers/media/platform/video-mux.c b/drivers/media/platform/video-mux.c
index 06a28531ed02..31e9e92e723e 100644
--- a/drivers/media/platform/video-mux.c
+++ b/drivers/media/platform/video-mux.c
@@ -282,8 +282,8 @@ static int video_mux_set_format(struct v4l2_subdev *sd,
 	return 0;
 }
 
-static int video_mux_init_cfg(struct v4l2_subdev *sd,
-			      struct v4l2_subdev_state *sd_state)
+static int video_mux_init_state(struct v4l2_subdev *sd,
+				struct v4l2_subdev_state *sd_state)
 {
 	struct video_mux *vmux = v4l2_subdev_to_video_mux(sd);
 	struct v4l2_mbus_framefmt *mbusformat;
@@ -302,7 +302,6 @@ static int video_mux_init_cfg(struct v4l2_subdev *sd,
 }
 
 static const struct v4l2_subdev_pad_ops video_mux_pad_ops = {
-	.init_cfg = video_mux_init_cfg,
 	.get_fmt = v4l2_subdev_get_fmt,
 	.set_fmt = video_mux_set_format,
 };
@@ -312,6 +311,10 @@ static const struct v4l2_subdev_ops video_mux_subdev_ops = {
 	.video = &video_mux_subdev_video_ops,
 };
 
+static const struct v4l2_subdev_internal_ops video_mux_internal_ops = {
+	.init_state = video_mux_init_state,
+};
+
 static int video_mux_notify_bound(struct v4l2_async_notifier *notifier,
 				  struct v4l2_subdev *sd,
 				  struct v4l2_async_connection *asd)
@@ -400,6 +403,7 @@ static int video_mux_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, vmux);
 
 	v4l2_subdev_init(&vmux->subdev, &video_mux_subdev_ops);
+	vmux->subdev.internal_ops = &video_mux_internal_ops;
 	snprintf(vmux->subdev.name, sizeof(vmux->subdev.name), "%pOFn", np);
 	vmux->subdev.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
 	vmux->subdev.dev = dev;
diff --git a/drivers/media/platform/xilinx/xilinx-csi2rxss.c b/drivers/media/platform/xilinx/xilinx-csi2rxss.c
index bca8ec94ee35..f953d5474ae0 100644
--- a/drivers/media/platform/xilinx/xilinx-csi2rxss.c
+++ b/drivers/media/platform/xilinx/xilinx-csi2rxss.c
@@ -661,8 +661,8 @@ __xcsi2rxss_get_pad_format(struct xcsi2rxss_state *xcsi2rxss,
 	}
 }
 
-static int xcsi2rxss_init_cfg(struct v4l2_subdev *sd,
-			      struct v4l2_subdev_state *sd_state)
+static int xcsi2rxss_init_state(struct v4l2_subdev *sd,
+				struct v4l2_subdev_state *sd_state)
 {
 	struct xcsi2rxss_state *xcsi2rxss = to_xcsi2rxssstate(sd);
 	struct v4l2_mbus_framefmt *format;
@@ -780,7 +780,6 @@ static const struct v4l2_subdev_video_ops xcsi2rxss_video_ops = {
 };
 
 static const struct v4l2_subdev_pad_ops xcsi2rxss_pad_ops = {
-	.init_cfg = xcsi2rxss_init_cfg,
 	.get_fmt = xcsi2rxss_get_format,
 	.set_fmt = xcsi2rxss_set_format,
 	.enum_mbus_code = xcsi2rxss_enum_mbus_code,
@@ -793,6 +792,10 @@ static const struct v4l2_subdev_ops xcsi2rxss_ops = {
 	.pad = &xcsi2rxss_pad_ops
 };
 
+static const struct v4l2_subdev_internal_ops xcsi2rxss_internal_ops = {
+	.init_state = xcsi2rxss_init_state,
+};
+
 static int xcsi2rxss_parse_of(struct xcsi2rxss_state *xcsi2rxss)
 {
 	struct device *dev = xcsi2rxss->dev;
@@ -970,6 +973,7 @@ static int xcsi2rxss_probe(struct platform_device *pdev)
 	/* Initialize V4L2 subdevice and media entity */
 	subdev = &xcsi2rxss->subdev;
 	v4l2_subdev_init(subdev, &xcsi2rxss_ops);
+	subdev->internal_ops = &xcsi2rxss_internal_ops;
 	subdev->dev = dev;
 	strscpy(subdev->name, dev_name(dev), sizeof(subdev->name));
 	subdev->flags |= V4L2_SUBDEV_FL_HAS_EVENTS | V4L2_SUBDEV_FL_HAS_DEVNODE;
diff --git a/drivers/media/test-drivers/vimc/vimc-debayer.c b/drivers/media/test-drivers/vimc/vimc-debayer.c
index a2fb32c97c84..d72ed086e00b 100644
--- a/drivers/media/test-drivers/vimc/vimc-debayer.c
+++ b/drivers/media/test-drivers/vimc/vimc-debayer.c
@@ -150,8 +150,8 @@ static bool vimc_debayer_src_code_is_valid(u32 code)
 	return false;
 }
 
-static int vimc_debayer_init_cfg(struct v4l2_subdev *sd,
-				 struct v4l2_subdev_state *sd_state)
+static int vimc_debayer_init_state(struct v4l2_subdev *sd,
+				   struct v4l2_subdev_state *sd_state)
 {
 	struct vimc_debayer_device *vdebayer = v4l2_get_subdevdata(sd);
 	struct v4l2_mbus_framefmt *mf;
@@ -307,7 +307,6 @@ static int vimc_debayer_set_fmt(struct v4l2_subdev *sd,
 }
 
 static const struct v4l2_subdev_pad_ops vimc_debayer_pad_ops = {
-	.init_cfg		= vimc_debayer_init_cfg,
 	.enum_mbus_code		= vimc_debayer_enum_mbus_code,
 	.enum_frame_size	= vimc_debayer_enum_frame_size,
 	.get_fmt		= vimc_debayer_get_fmt,
@@ -395,6 +394,10 @@ static const struct v4l2_subdev_ops vimc_debayer_ops = {
 	.video = &vimc_debayer_video_ops,
 };
 
+static const struct v4l2_subdev_internal_ops vimc_debayer_internal_ops = {
+	.init_state = vimc_debayer_init_state,
+};
+
 static unsigned int vimc_debayer_get_val(const u8 *bytes,
 					 const unsigned int n_bytes)
 {
@@ -595,6 +598,8 @@ static struct vimc_ent_device *vimc_debayer_add(struct vimc_device *vimc,
 	if (ret)
 		goto err_free_hdl;
 
+	vdebayer->sd.internal_ops = &vimc_debayer_internal_ops;
+
 	vdebayer->ved.process_frame = vimc_debayer_process_frame;
 	vdebayer->ved.dev = vimc->mdev.dev;
 	vdebayer->mean_win_size = vimc_debayer_ctrl_mean_win_size.def;
diff --git a/drivers/media/test-drivers/vimc/vimc-scaler.c b/drivers/media/test-drivers/vimc/vimc-scaler.c
index f6592a789f1e..afe13d6af321 100644
--- a/drivers/media/test-drivers/vimc/vimc-scaler.c
+++ b/drivers/media/test-drivers/vimc/vimc-scaler.c
@@ -70,8 +70,8 @@ vimc_scaler_get_crop_bound_sink(const struct v4l2_mbus_framefmt *sink_fmt)
 	return r;
 }
 
-static int vimc_scaler_init_cfg(struct v4l2_subdev *sd,
-			     struct v4l2_subdev_state *sd_state)
+static int vimc_scaler_init_state(struct v4l2_subdev *sd,
+				  struct v4l2_subdev_state *sd_state)
 {
 	struct v4l2_mbus_framefmt *mf;
 	struct v4l2_rect *r;
@@ -292,7 +292,6 @@ static int vimc_scaler_set_selection(struct v4l2_subdev *sd,
 }
 
 static const struct v4l2_subdev_pad_ops vimc_scaler_pad_ops = {
-	.init_cfg		= vimc_scaler_init_cfg,
 	.enum_mbus_code		= vimc_scaler_enum_mbus_code,
 	.enum_frame_size	= vimc_scaler_enum_frame_size,
 	.get_fmt		= vimc_scaler_get_fmt,
@@ -347,6 +346,10 @@ static const struct v4l2_subdev_ops vimc_scaler_ops = {
 	.video = &vimc_scaler_video_ops,
 };
 
+static const struct v4l2_subdev_internal_ops vimc_scaler_internal_ops = {
+	.init_state = vimc_scaler_init_state,
+};
+
 static void vimc_scaler_fill_src_frame(const struct vimc_scaler_device *const vscaler,
 				    const u8 *const sink_frame)
 {
@@ -424,6 +427,8 @@ static struct vimc_ent_device *vimc_scaler_add(struct vimc_device *vimc,
 		return ERR_PTR(ret);
 	}
 
+	vscaler->sd.internal_ops = &vimc_scaler_internal_ops;
+
 	vscaler->ved.process_frame = vimc_scaler_process_frame;
 	vscaler->ved.dev = vimc->mdev.dev;
 
diff --git a/drivers/media/test-drivers/vimc/vimc-sensor.c b/drivers/media/test-drivers/vimc/vimc-sensor.c
index 676ab503f0ca..5e34b1aed95e 100644
--- a/drivers/media/test-drivers/vimc/vimc-sensor.c
+++ b/drivers/media/test-drivers/vimc/vimc-sensor.c
@@ -41,8 +41,8 @@ static const struct v4l2_mbus_framefmt fmt_default = {
 	.colorspace = V4L2_COLORSPACE_SRGB,
 };
 
-static int vimc_sensor_init_cfg(struct v4l2_subdev *sd,
-				struct v4l2_subdev_state *sd_state)
+static int vimc_sensor_init_state(struct v4l2_subdev *sd,
+				  struct v4l2_subdev_state *sd_state)
 {
 	unsigned int i;
 
@@ -183,7 +183,6 @@ static int vimc_sensor_set_fmt(struct v4l2_subdev *sd,
 }
 
 static const struct v4l2_subdev_pad_ops vimc_sensor_pad_ops = {
-	.init_cfg		= vimc_sensor_init_cfg,
 	.enum_mbus_code		= vimc_sensor_enum_mbus_code,
 	.enum_frame_size	= vimc_sensor_enum_frame_size,
 	.get_fmt		= vimc_sensor_get_fmt,
@@ -294,6 +293,10 @@ static const struct v4l2_subdev_ops vimc_sensor_ops = {
 	.video = &vimc_sensor_video_ops,
 };
 
+static const struct v4l2_subdev_internal_ops vimc_sensor_internal_ops = {
+	.init_state = vimc_sensor_init_state,
+};
+
 static int vimc_sensor_s_ctrl(struct v4l2_ctrl *ctrl)
 {
 	struct vimc_sensor_device *vsensor =
@@ -429,6 +432,8 @@ static struct vimc_ent_device *vimc_sensor_add(struct vimc_device *vimc,
 	if (ret)
 		goto err_free_tpg;
 
+	vsensor->sd.internal_ops = &vimc_sensor_internal_ops;
+
 	vsensor->ved.process_frame = vimc_sensor_process_frame;
 	vsensor->ved.dev = vimc->mdev.dev;
 
diff --git a/drivers/media/v4l2-core/v4l2-subdev.c b/drivers/media/v4l2-core/v4l2-subdev.c
index 985873b7981e..4fbefe4cd714 100644
--- a/drivers/media/v4l2-core/v4l2-subdev.c
+++ b/drivers/media/v4l2-core/v4l2-subdev.c
@@ -1460,16 +1460,18 @@ __v4l2_subdev_state_alloc(struct v4l2_subdev *sd, const char *lock_name,
 		}
 	}
 
-	/*
-	 * There can be no race at this point, but we lock the state anyway to
-	 * satisfy lockdep checks.
-	 */
-	v4l2_subdev_lock_state(state);
-	ret = v4l2_subdev_call(sd, pad, init_cfg, state);
-	v4l2_subdev_unlock_state(state);
+	if (sd->internal_ops && sd->internal_ops->init_state) {
+		/*
+		 * There can be no race at this point, but we lock the state
+		 * anyway to satisfy lockdep checks.
+		 */
+		v4l2_subdev_lock_state(state);
+		ret = sd->internal_ops->init_state(sd, state);
+		v4l2_subdev_unlock_state(state);
 
-	if (ret < 0 && ret != -ENOIOCTLCMD)
-		goto err;
+		if (ret)
+			goto err;
+	}
 
 	return state;
 
diff --git a/drivers/staging/media/imx/imx-ic-prp.c b/drivers/staging/media/imx/imx-ic-prp.c
index 61d69f19657e..8bd9be49cc08 100644
--- a/drivers/staging/media/imx/imx-ic-prp.c
+++ b/drivers/staging/media/imx/imx-ic-prp.c
@@ -448,7 +448,6 @@ static int prp_registered(struct v4l2_subdev *sd)
 }
 
 static const struct v4l2_subdev_pad_ops prp_pad_ops = {
-	.init_cfg = imx_media_init_cfg,
 	.enum_mbus_code = prp_enum_mbus_code,
 	.get_fmt = prp_get_fmt,
 	.set_fmt = prp_set_fmt,
@@ -472,6 +471,7 @@ static const struct v4l2_subdev_ops prp_subdev_ops = {
 };
 
 static const struct v4l2_subdev_internal_ops prp_internal_ops = {
+	.init_state = imx_media_init_state,
 	.registered = prp_registered,
 };
 
diff --git a/drivers/staging/media/imx/imx-ic-prpencvf.c b/drivers/staging/media/imx/imx-ic-prpencvf.c
index ec73c901079e..04878f07eeba 100644
--- a/drivers/staging/media/imx/imx-ic-prpencvf.c
+++ b/drivers/staging/media/imx/imx-ic-prpencvf.c
@@ -1296,7 +1296,6 @@ static void prp_unregistered(struct v4l2_subdev *sd)
 }
 
 static const struct v4l2_subdev_pad_ops prp_pad_ops = {
-	.init_cfg = imx_media_init_cfg,
 	.enum_mbus_code = prp_enum_mbus_code,
 	.enum_frame_size = prp_enum_frame_size,
 	.get_fmt = prp_get_fmt,
@@ -1320,6 +1319,7 @@ static const struct v4l2_subdev_ops prp_subdev_ops = {
 };
 
 static const struct v4l2_subdev_internal_ops prp_internal_ops = {
+	.init_state = imx_media_init_state,
 	.registered = prp_registered,
 	.unregistered = prp_unregistered,
 };
diff --git a/drivers/staging/media/imx/imx-media-csi.c b/drivers/staging/media/imx/imx-media-csi.c
index 33902f5daf80..2fc94011fe4d 100644
--- a/drivers/staging/media/imx/imx-media-csi.c
+++ b/drivers/staging/media/imx/imx-media-csi.c
@@ -1866,7 +1866,6 @@ static const struct v4l2_subdev_video_ops csi_video_ops = {
 };
 
 static const struct v4l2_subdev_pad_ops csi_pad_ops = {
-	.init_cfg = imx_media_init_cfg,
 	.enum_mbus_code = csi_enum_mbus_code,
 	.enum_frame_size = csi_enum_frame_size,
 	.enum_frame_interval = csi_enum_frame_interval,
@@ -1884,6 +1883,7 @@ static const struct v4l2_subdev_ops csi_subdev_ops = {
 };
 
 static const struct v4l2_subdev_internal_ops csi_internal_ops = {
+	.init_state = imx_media_init_state,
 	.registered = csi_registered,
 	.unregistered = csi_unregistered,
 };
diff --git a/drivers/staging/media/imx/imx-media-utils.c b/drivers/staging/media/imx/imx-media-utils.c
index ec4349ab48cd..1b5af8945e6b 100644
--- a/drivers/staging/media/imx/imx-media-utils.c
+++ b/drivers/staging/media/imx/imx-media-utils.c
@@ -426,10 +426,10 @@ EXPORT_SYMBOL_GPL(imx_media_init_mbus_fmt);
 
 /*
  * Initializes the TRY format to the ACTIVE format on all pads
- * of a subdev. Can be used as the .init_cfg pad operation.
+ * of a subdev. Can be used as the .init_state internal operation.
  */
-int imx_media_init_cfg(struct v4l2_subdev *sd,
-		       struct v4l2_subdev_state *sd_state)
+int imx_media_init_state(struct v4l2_subdev *sd,
+			 struct v4l2_subdev_state *sd_state)
 {
 	struct v4l2_mbus_framefmt *mf_try;
 	unsigned int pad;
@@ -451,7 +451,7 @@ int imx_media_init_cfg(struct v4l2_subdev *sd,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(imx_media_init_cfg);
+EXPORT_SYMBOL_GPL(imx_media_init_state);
 
 /*
  * Default the colorspace in tryfmt to SRGB if set to an unsupported
diff --git a/drivers/staging/media/imx/imx-media-vdic.c b/drivers/staging/media/imx/imx-media-vdic.c
index 792bca1d2d25..810b38ea3ab9 100644
--- a/drivers/staging/media/imx/imx-media-vdic.c
+++ b/drivers/staging/media/imx/imx-media-vdic.c
@@ -882,7 +882,6 @@ static void vdic_unregistered(struct v4l2_subdev *sd)
 }
 
 static const struct v4l2_subdev_pad_ops vdic_pad_ops = {
-	.init_cfg = imx_media_init_cfg,
 	.enum_mbus_code = vdic_enum_mbus_code,
 	.get_fmt = vdic_get_fmt,
 	.set_fmt = vdic_set_fmt,
@@ -906,6 +905,7 @@ static const struct v4l2_subdev_ops vdic_subdev_ops = {
 };
 
 static const struct v4l2_subdev_internal_ops vdic_internal_ops = {
+	.init_state = imx_media_init_state,
 	.registered = vdic_registered,
 	.unregistered = vdic_unregistered,
 };
diff --git a/drivers/staging/media/imx/imx-media.h b/drivers/staging/media/imx/imx-media.h
index 2640cd34dce2..f095d9134fee 100644
--- a/drivers/staging/media/imx/imx-media.h
+++ b/drivers/staging/media/imx/imx-media.h
@@ -192,8 +192,8 @@ static inline int imx_media_enum_ipu_formats(u32 *code, u32 index,
 int imx_media_init_mbus_fmt(struct v4l2_mbus_framefmt *mbus,
 			    u32 width, u32 height, u32 code, u32 field,
 			    const struct imx_media_pixfmt **cc);
-int imx_media_init_cfg(struct v4l2_subdev *sd,
-		       struct v4l2_subdev_state *sd_state);
+int imx_media_init_state(struct v4l2_subdev *sd,
+			 struct v4l2_subdev_state *sd_state);
 void imx_media_try_colorimetry(struct v4l2_mbus_framefmt *tryfmt,
 			       bool ic_route);
 int imx_media_mbus_fmt_to_pix_fmt(struct v4l2_pix_format *pix,
diff --git a/drivers/staging/media/imx/imx6-mipi-csi2.c b/drivers/staging/media/imx/imx6-mipi-csi2.c
index 6906220ee89e..0d8b42061623 100644
--- a/drivers/staging/media/imx/imx6-mipi-csi2.c
+++ b/drivers/staging/media/imx/imx6-mipi-csi2.c
@@ -619,7 +619,6 @@ static const struct v4l2_subdev_video_ops csi2_video_ops = {
 };
 
 static const struct v4l2_subdev_pad_ops csi2_pad_ops = {
-	.init_cfg = imx_media_init_cfg,
 	.get_fmt = csi2_get_fmt,
 	.set_fmt = csi2_set_fmt,
 };
@@ -631,6 +630,7 @@ static const struct v4l2_subdev_ops csi2_subdev_ops = {
 };
 
 static const struct v4l2_subdev_internal_ops csi2_internal_ops = {
+	.init_state = imx_media_init_state,
 	.registered = csi2_registered,
 };
 
diff --git a/drivers/staging/media/starfive/camss/stf-isp.c b/drivers/staging/media/starfive/camss/stf-isp.c
index 893dbd8cddc8..6bffffb2b20c 100644
--- a/drivers/staging/media/starfive/camss/stf-isp.c
+++ b/drivers/staging/media/starfive/camss/stf-isp.c
@@ -311,7 +311,6 @@ static const struct v4l2_subdev_video_ops isp_video_ops = {
 };
 
 static const struct v4l2_subdev_pad_ops isp_pad_ops = {
-	.init_cfg = isp_init_formats,
 	.enum_mbus_code = isp_enum_mbus_code,
 	.get_fmt = v4l2_subdev_get_fmt,
 	.set_fmt = isp_set_format,
@@ -324,6 +323,10 @@ static const struct v4l2_subdev_ops isp_v4l2_ops = {
 	.pad = &isp_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops isp_internal_ops = {
+	.init_state = isp_init_formats,
+};
+
 static const struct media_entity_operations isp_media_ops = {
 	.link_validate = v4l2_subdev_link_validate,
 };
@@ -335,6 +338,7 @@ int stf_isp_register(struct stf_isp_dev *isp_dev, struct v4l2_device *v4l2_dev)
 	int ret;
 
 	v4l2_subdev_init(sd, &isp_v4l2_ops);
+	sd->internal_ops = &isp_internal_ops;
 	sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
 	snprintf(sd->name, ARRAY_SIZE(sd->name), "stf_isp");
 	v4l2_set_subdevdata(sd, isp_dev);
diff --git a/drivers/staging/media/sunxi/sun6i-isp/sun6i_isp_proc.c b/drivers/staging/media/sunxi/sun6i-isp/sun6i_isp_proc.c
index b2ce0d4fae95..46a334b602f1 100644
--- a/drivers/staging/media/sunxi/sun6i-isp/sun6i_isp_proc.c
+++ b/drivers/staging/media/sunxi/sun6i-isp/sun6i_isp_proc.c
@@ -256,8 +256,8 @@ sun6i_isp_proc_mbus_format_prepare(struct v4l2_mbus_framefmt *mbus_format)
 	mbus_format->xfer_func = V4L2_XFER_FUNC_DEFAULT;
 }
 
-static int sun6i_isp_proc_init_cfg(struct v4l2_subdev *subdev,
-				   struct v4l2_subdev_state *state)
+static int sun6i_isp_proc_init_state(struct v4l2_subdev *subdev,
+				     struct v4l2_subdev_state *state)
 {
 	struct sun6i_isp_device *isp_dev = v4l2_get_subdevdata(subdev);
 	unsigned int pad = SUN6I_ISP_PROC_PAD_SINK_CSI;
@@ -336,7 +336,6 @@ static int sun6i_isp_proc_set_fmt(struct v4l2_subdev *subdev,
 }
 
 static const struct v4l2_subdev_pad_ops sun6i_isp_proc_pad_ops = {
-	.init_cfg	= sun6i_isp_proc_init_cfg,
 	.enum_mbus_code	= sun6i_isp_proc_enum_mbus_code,
 	.get_fmt	= sun6i_isp_proc_get_fmt,
 	.set_fmt	= sun6i_isp_proc_set_fmt,
@@ -347,6 +346,10 @@ static const struct v4l2_subdev_ops sun6i_isp_proc_subdev_ops = {
 	.pad	= &sun6i_isp_proc_pad_ops,
 };
 
+static const struct v4l2_subdev_internal_ops sun6i_isp_proc_internal_ops = {
+	.init_state = sun6i_isp_proc_init_state,
+};
+
 /* Media Entity */
 
 static const struct media_entity_operations sun6i_isp_proc_entity_ops = {
@@ -501,6 +504,7 @@ int sun6i_isp_proc_setup(struct sun6i_isp_device *isp_dev)
 	/* V4L2 Subdev */
 
 	v4l2_subdev_init(subdev, &sun6i_isp_proc_subdev_ops);
+	subdev->internal_ops = &sun6i_isp_proc_internal_ops;
 	strscpy(subdev->name, SUN6I_ISP_PROC_NAME, sizeof(subdev->name));
 	subdev->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
 	subdev->owner = THIS_MODULE;
diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h
index 2a438e516095..8b08f6640dee 100644
--- a/include/media/v4l2-subdev.h
+++ b/include/media/v4l2-subdev.h
@@ -771,7 +771,6 @@ struct v4l2_subdev_state {
 /**
  * struct v4l2_subdev_pad_ops - v4l2-subdev pad level operations
  *
- * @init_cfg: initialize the subdev state to default values
  * @enum_mbus_code: callback for VIDIOC_SUBDEV_ENUM_MBUS_CODE() ioctl handler
  *		    code.
  * @enum_frame_size: callback for VIDIOC_SUBDEV_ENUM_FRAME_SIZE() ioctl handler
@@ -836,8 +835,6 @@ struct v4l2_subdev_state {
  *	directly, use v4l2_subdev_disable_streams() instead.
  */
 struct v4l2_subdev_pad_ops {
-	int (*init_cfg)(struct v4l2_subdev *sd,
-			struct v4l2_subdev_state *state);
 	int (*enum_mbus_code)(struct v4l2_subdev *sd,
 			      struct v4l2_subdev_state *state,
 			      struct v4l2_subdev_mbus_code_enum *code);
@@ -914,6 +911,8 @@ struct v4l2_subdev_ops {
 /**
  * struct v4l2_subdev_internal_ops - V4L2 subdev internal ops
  *
+ * @init_state: initialize the subdev state to default values
+ *
  * @registered: called when this subdev is registered. When called the v4l2_dev
  *	field is set to the correct v4l2_device.
  *
@@ -939,6 +938,8 @@ struct v4l2_subdev_ops {
  *	these ops.
  */
 struct v4l2_subdev_internal_ops {
+	int (*init_state)(struct v4l2_subdev *sd,
+			  struct v4l2_subdev_state *state);
 	int (*registered)(struct v4l2_subdev *sd);
 	void (*unregistered)(struct v4l2_subdev *sd);
 	int (*open)(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh);
-- 
cgit v1.2.3


From eba5058633b4d11e2a4d65eae9f1fce0b96365d9 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Tue, 7 Nov 2023 10:45:30 +0200
Subject: media: v4l: cci: Include linux/bits.h

linux/bits.h is needed for GENMASK(). Include it.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
---
 include/media/v4l2-cci.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/media/v4l2-cci.h b/include/media/v4l2-cci.h
index 0f6803e4b17e..f2c2962e936b 100644
--- a/include/media/v4l2-cci.h
+++ b/include/media/v4l2-cci.h
@@ -7,6 +7,7 @@
 #ifndef _V4L2_CCI_H
 #define _V4L2_CCI_H
 
+#include <linux/bits.h>
 #include <linux/types.h>
 
 struct i2c_client;
-- 
cgit v1.2.3


From 94ed00981b5167e22f66fd5bfedcc7cc7fd72551 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Tue, 7 Nov 2023 11:31:13 +0200
Subject: media: v4l: cci: Add driver-private bit definitions

Provide a few bits for drivers to store private information on register
definitions.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
---
 include/media/v4l2-cci.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/media/v4l2-cci.h b/include/media/v4l2-cci.h
index f2c2962e936b..ee469f03e440 100644
--- a/include/media/v4l2-cci.h
+++ b/include/media/v4l2-cci.h
@@ -33,6 +33,11 @@ struct cci_reg_sequence {
 #define CCI_REG_ADDR_MASK		GENMASK(15, 0)
 #define CCI_REG_WIDTH_SHIFT		16
 #define CCI_REG_WIDTH_MASK		GENMASK(19, 16)
+/*
+ * Private CCI register flags, for the use of drivers.
+ */
+#define CCI_REG_PRIVATE_SHIFT		28U
+#define CCI_REG_PRIVATE_MASK		GENMASK(31U, CCI_REG_PRIVATE_SHIFT)
 
 #define CCI_REG8(x)			((1 << CCI_REG_WIDTH_SHIFT) | (x))
 #define CCI_REG16(x)			((2 << CCI_REG_WIDTH_SHIFT) | (x))
-- 
cgit v1.2.3


From cd93cc245dfe334c38da98c14b34f9597e1b4ea6 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Tue, 7 Nov 2023 17:42:40 +0200
Subject: media: v4l: cci: Add macros to obtain register width and address

Add CCI_REG_WIDTH() macro to obtain register width in bits and similarly,
CCI_REG_WIDTH_BYTES() to obtain it in bytes.

Also add CCI_REG_ADDR() macro to obtain the address of a register.

Use both macros in v4l2-cci.c, too.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
---
 drivers/media/v4l2-core/v4l2-cci.c | 8 ++++----
 include/media/v4l2-cci.h           | 5 +++++
 2 files changed, 9 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/media/v4l2-core/v4l2-cci.c b/drivers/media/v4l2-core/v4l2-cci.c
index bc2dbec019b0..3179160abde3 100644
--- a/drivers/media/v4l2-core/v4l2-cci.c
+++ b/drivers/media/v4l2-core/v4l2-cci.c
@@ -25,8 +25,8 @@ int cci_read(struct regmap *map, u32 reg, u64 *val, int *err)
 	if (err && *err)
 		return *err;
 
-	len = FIELD_GET(CCI_REG_WIDTH_MASK, reg);
-	reg = FIELD_GET(CCI_REG_ADDR_MASK, reg);
+	len = CCI_REG_WIDTH_BYTES(reg);
+	reg = CCI_REG_ADDR(reg);
 
 	ret = regmap_bulk_read(map, reg, buf, len);
 	if (ret) {
@@ -75,8 +75,8 @@ int cci_write(struct regmap *map, u32 reg, u64 val, int *err)
 	if (err && *err)
 		return *err;
 
-	len = FIELD_GET(CCI_REG_WIDTH_MASK, reg);
-	reg = FIELD_GET(CCI_REG_ADDR_MASK, reg);
+	len = CCI_REG_WIDTH_BYTES(reg);
+	reg = CCI_REG_ADDR(reg);
 
 	switch (len) {
 	case 1:
diff --git a/include/media/v4l2-cci.h b/include/media/v4l2-cci.h
index ee469f03e440..406772a4e32e 100644
--- a/include/media/v4l2-cci.h
+++ b/include/media/v4l2-cci.h
@@ -7,6 +7,7 @@
 #ifndef _V4L2_CCI_H
 #define _V4L2_CCI_H
 
+#include <linux/bitfield.h>
 #include <linux/bits.h>
 #include <linux/types.h>
 
@@ -39,6 +40,10 @@ struct cci_reg_sequence {
 #define CCI_REG_PRIVATE_SHIFT		28U
 #define CCI_REG_PRIVATE_MASK		GENMASK(31U, CCI_REG_PRIVATE_SHIFT)
 
+#define CCI_REG_WIDTH_BYTES(x)		FIELD_GET(CCI_REG_WIDTH_MASK, x)
+#define CCI_REG_WIDTH(x)		(CCI_REG_WIDTH_BYTES(x) << 3)
+#define CCI_REG_ADDR(x)			FIELD_GET(CCI_REG_ADDR_MASK, x)
+
 #define CCI_REG8(x)			((1 << CCI_REG_WIDTH_SHIFT) | (x))
 #define CCI_REG16(x)			((2 << CCI_REG_WIDTH_SHIFT) | (x))
 #define CCI_REG24(x)			((3 << CCI_REG_WIDTH_SHIFT) | (x))
-- 
cgit v1.2.3


From 2112f3a28e8d9d1e2faaa32d124b450bde055b72 Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Date: Mon, 23 Oct 2023 21:19:22 +0300
Subject: media: v4l2-subdev: Fix indentation in v4l2-subdev.h

Fix a simple indentation issue in the v4l2-subdev.h header.

Fixes: f57fa2959244 ("media: v4l2-subdev: Add new ioctl for client capabilities")
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
---
 include/uapi/linux/v4l2-subdev.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/v4l2-subdev.h b/include/uapi/linux/v4l2-subdev.h
index b383c2fe0cf3..f0fbb4a7c150 100644
--- a/include/uapi/linux/v4l2-subdev.h
+++ b/include/uapi/linux/v4l2-subdev.h
@@ -239,7 +239,7 @@ struct v4l2_subdev_routing {
  * set (which is the default), the 'stream' fields will be forced to 0 by the
  * kernel.
  */
- #define V4L2_SUBDEV_CLIENT_CAP_STREAMS		(1ULL << 0)
+#define V4L2_SUBDEV_CLIENT_CAP_STREAMS		(1ULL << 0)
 
 /**
  * struct v4l2_subdev_client_capability - Capabilities of the client accessing
-- 
cgit v1.2.3


From 578dc962ff2000ba4bf52d50717aea0819615634 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <bbrezillon@kernel.org>
Date: Fri, 24 Nov 2023 17:24:35 -0800
Subject: mtd: rawnand: Add destructive operation

Erase and program operations need the write protect (wp) pin to be
de-asserted to take effect. Add the concept of destructive
operation and pass the information to exec_op() so controllers know
when they should de-assert this pin without having to decode
the command opcode.

Signed-off-by: Boris Brezillon <bbrezillon@kernel.org>
Signed-off-by: David Regan <dregan@broadcom.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20231125012438.15191-1-dregan@broadcom.com
---
 drivers/mtd/nand/raw/nand_base.c |  6 ++++--
 include/linux/mtd/rawnand.h      | 11 +++++++++++
 2 files changed, 15 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 9e24bedffd89..7dd9be5d58c4 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -1493,7 +1493,8 @@ static int nand_exec_prog_page_op(struct nand_chip *chip, unsigned int page,
 			    NAND_COMMON_TIMING_NS(conf, tWB_max)),
 		NAND_OP_WAIT_RDY(NAND_COMMON_TIMING_MS(conf, tPROG_max), 0),
 	};
-	struct nand_operation op = NAND_OPERATION(chip->cur_cs, instrs);
+	struct nand_operation op = NAND_DESTRUCTIVE_OPERATION(chip->cur_cs,
+							      instrs);
 	int naddrs = nand_fill_column_cycles(chip, addrs, offset_in_page);
 
 	if (naddrs < 0)
@@ -1916,7 +1917,8 @@ int nand_erase_op(struct nand_chip *chip, unsigned int eraseblock)
 			NAND_OP_WAIT_RDY(NAND_COMMON_TIMING_MS(conf, tBERS_max),
 					 0),
 		};
-		struct nand_operation op = NAND_OPERATION(chip->cur_cs, instrs);
+		struct nand_operation op = NAND_DESTRUCTIVE_OPERATION(chip->cur_cs,
+								      instrs);
 
 		if (chip->options & NAND_ROW_ADDR_3)
 			instrs[1].ctx.addr.naddrs++;
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index c29ace15a053..bd02aba5e6e3 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -1003,6 +1003,8 @@ struct nand_op_parser {
 /**
  * struct nand_operation - NAND operation descriptor
  * @cs: the CS line to select for this NAND operation
+ * @deassert_wp: set to true when the operation requires the WP pin to be
+ *		 de-asserted (ERASE, PROG, ...)
  * @instrs: array of instructions to execute
  * @ninstrs: length of the @instrs array
  *
@@ -1010,6 +1012,7 @@ struct nand_op_parser {
  */
 struct nand_operation {
 	unsigned int cs;
+	bool deassert_wp;
 	const struct nand_op_instr *instrs;
 	unsigned int ninstrs;
 };
@@ -1021,6 +1024,14 @@ struct nand_operation {
 		.ninstrs = ARRAY_SIZE(_instrs),			\
 	}
 
+#define NAND_DESTRUCTIVE_OPERATION(_cs, _instrs)		\
+	{							\
+		.cs = _cs,					\
+		.deassert_wp = true,				\
+		.instrs = _instrs,				\
+		.ninstrs = ARRAY_SIZE(_instrs),			\
+	}
+
 int nand_op_parser_exec_op(struct nand_chip *chip,
 			   const struct nand_op_parser *parser,
 			   const struct nand_operation *op, bool check_only);
-- 
cgit v1.2.3


From 68cce21e3cc5fea8d955a62394454149270c98bc Mon Sep 17 00:00:00 2001
From: David Regan <dregan@broadcom.com>
Date: Fri, 24 Nov 2023 17:24:36 -0800
Subject: mtd: rawnand: NAND controller write protect

Allow NAND controller to be responsible for write protect pin
handling during fast path and exec_op destructive operation
when controller_wp flag is set.

Signed-off-by: David Regan <dregan@broadcom.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20231125012438.15191-2-dregan@broadcom.com
---
 drivers/mtd/nand/raw/nand_base.c | 4 ++++
 include/linux/mtd/rawnand.h      | 2 ++
 2 files changed, 6 insertions(+)

(limited to 'include')

diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 7dd9be5d58c4..0f342cd691a3 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -366,6 +366,10 @@ static int nand_check_wp(struct nand_chip *chip)
 	if (chip->options & NAND_BROKEN_XD)
 		return 0;
 
+	/* controller responsible for NAND write protect */
+	if (chip->controller->controller_wp)
+		return 0;
+
 	/* Check the WP bit */
 	ret = nand_status_op(chip, &status);
 	if (ret)
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index bd02aba5e6e3..a17f795070d8 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -1115,6 +1115,7 @@ struct nand_controller_ops {
  *			the bus without restarting an entire read operation nor
  *			changing the column.
  * @supported_op.cont_read: The controller supports sequential cache reads.
+ * @controller_wp:	the controller is in charge of handling the WP pin.
  */
 struct nand_controller {
 	struct mutex lock;
@@ -1123,6 +1124,7 @@ struct nand_controller {
 		unsigned int data_only_read: 1;
 		unsigned int cont_read: 1;
 	} supported_op;
+	bool controller_wp;
 };
 
 static inline void nand_controller_init(struct nand_controller *nfc)
-- 
cgit v1.2.3


From a87b8e3be926af0fc3b9b1af42b1127bd1ff077c Mon Sep 17 00:00:00 2001
From: Douglas Anderson <dianders@chromium.org>
Date: Fri, 1 Dec 2023 10:29:51 -0800
Subject: usb: core: Allow subclassed USB drivers to override
 usb_choose_configuration()

For some USB devices we might want to do something different for
usb_choose_configuration(). One example here is the r8152 driver where
we want to end up using the vendor driver with the preferred
interface.

The r8152 driver tried to make things work by implementing a USB
generic_subclass driver and then overriding the normal config
selection after it happened. This is less than ideal and also caused
breakage if someone deauthorized and re-authorized the USB device
because the USB core ended up going back to it's default logic for
choosing the best config. I made an attempt to fix this [1] but it was
a bit ugly.

Let's do this better and allow USB generic_subclass drivers to
override usb_choose_configuration().

[1] https://lore.kernel.org/r/20231130154337.1.Ie00e07f07f87149c9ce0b27ae4e26991d307e14b@changeid

Suggested-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Douglas Anderson <dianders@chromium.org>
Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
Link: https://lore.kernel.org/r/20231201102946.v2.2.Iade5fa31997f1a0ca3e1dec0591633b02471df12@changeid
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/generic.c | 7 +++++++
 include/linux/usb.h        | 6 ++++++
 2 files changed, 13 insertions(+)

(limited to 'include')

diff --git a/drivers/usb/core/generic.c b/drivers/usb/core/generic.c
index 740342a2812a..dcb897158228 100644
--- a/drivers/usb/core/generic.c
+++ b/drivers/usb/core/generic.c
@@ -59,10 +59,17 @@ int usb_choose_configuration(struct usb_device *udev)
 	int num_configs;
 	int insufficient_power = 0;
 	struct usb_host_config *c, *best;
+	struct usb_device_driver *udriver = to_usb_device_driver(udev->dev.driver);
 
 	if (usb_device_is_owned(udev))
 		return 0;
 
+	if (udriver->choose_configuration) {
+		i = udriver->choose_configuration(udev);
+		if (i >= 0)
+			return i;
+	}
+
 	best = NULL;
 	c = udev->config;
 	num_configs = udev->descriptor.bNumConfigurations;
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 8c61643acd49..618e5a0b1a22 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -1264,6 +1264,9 @@ struct usb_driver {
  *	module is being unloaded.
  * @suspend: Called when the device is going to be suspended by the system.
  * @resume: Called when the device is being resumed by the system.
+ * @choose_configuration: If non-NULL, called instead of the default
+ *	usb_choose_configuration(). If this returns an error then we'll go
+ *	on to call the normal usb_choose_configuration().
  * @dev_groups: Attributes attached to the device that will be created once it
  *	is bound to the driver.
  * @drvwrap: Driver-model core structure wrapper.
@@ -1287,6 +1290,9 @@ struct usb_device_driver {
 
 	int (*suspend) (struct usb_device *udev, pm_message_t message);
 	int (*resume) (struct usb_device *udev, pm_message_t message);
+
+	int (*choose_configuration) (struct usb_device *udev);
+
 	const struct attribute_group **dev_groups;
 	struct usbdrv_wrap drvwrap;
 	const struct usb_device_id *id_table;
-- 
cgit v1.2.3


From db9e54709895241dda23f9347f619afb15291353 Mon Sep 17 00:00:00 2001
From: RD Babiera <rdbabiera@google.com>
Date: Tue, 21 Nov 2023 20:38:47 +0000
Subject: usb: typec: tcpm: add tcpm_port_error_recovery symbol

Add tcpm_port_error_recovery symbol and corresponding event that runs in
tcpm_pd_event handler to set the port to the ERROR_RECOVERY state. tcpci
drivers can use the symbol to reset the port when tcpc faults affect port
functionality.

Signed-off-by: RD Babiera <rdbabiera@google.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20231121203845.170234-5-rdbabiera@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tcpm/tcpm.c | 14 ++++++++++++++
 include/linux/usb/tcpm.h      |  1 +
 2 files changed, 15 insertions(+)

(limited to 'include')

diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 50cbc52386b3..ff67553b6932 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -251,6 +251,7 @@ enum frs_typec_current {
 #define TCPM_FRS_EVENT		BIT(3)
 #define TCPM_SOURCING_VBUS	BIT(4)
 #define TCPM_PORT_CLEAN		BIT(5)
+#define TCPM_PORT_ERROR		BIT(6)
 
 #define LOG_BUFFER_ENTRIES	1024
 #define LOG_BUFFER_ENTRY_SIZE	128
@@ -5487,6 +5488,10 @@ static void tcpm_pd_event_handler(struct kthread_work *work)
 					tcpm_set_state(port, tcpm_default_state(port), 0);
 			}
 		}
+		if (events & TCPM_PORT_ERROR) {
+			tcpm_log(port, "port triggering error recovery");
+			tcpm_set_state(port, ERROR_RECOVERY, 0);
+		}
 
 		spin_lock(&port->pd_event_lock);
 	}
@@ -5554,6 +5559,15 @@ bool tcpm_port_is_toggling(struct tcpm_port *port)
 }
 EXPORT_SYMBOL_GPL(tcpm_port_is_toggling);
 
+void tcpm_port_error_recovery(struct tcpm_port *port)
+{
+	spin_lock(&port->pd_event_lock);
+	port->pd_events |= TCPM_PORT_ERROR;
+	spin_unlock(&port->pd_event_lock);
+	kthread_queue_work(port->wq, &port->event_work);
+}
+EXPORT_SYMBOL_GPL(tcpm_port_error_recovery);
+
 static void tcpm_enable_frs_work(struct kthread_work *work)
 {
 	struct tcpm_port *port = container_of(work, struct tcpm_port, enable_frs);
diff --git a/include/linux/usb/tcpm.h b/include/linux/usb/tcpm.h
index ab7ca872950b..65fac5e1f317 100644
--- a/include/linux/usb/tcpm.h
+++ b/include/linux/usb/tcpm.h
@@ -173,5 +173,6 @@ void tcpm_pd_hard_reset(struct tcpm_port *port);
 void tcpm_tcpc_reset(struct tcpm_port *port);
 void tcpm_port_clean(struct tcpm_port *port);
 bool tcpm_port_is_toggling(struct tcpm_port *port);
+void tcpm_port_error_recovery(struct tcpm_port *port);
 
 #endif /* __LINUX_USB_TCPM_H */
-- 
cgit v1.2.3


From 5e4c8814a431d21bfaf20b464134f40f2f81e152 Mon Sep 17 00:00:00 2001
From: RD Babiera <rdbabiera@google.com>
Date: Tue, 21 Nov 2023 20:38:48 +0000
Subject: usb: typec: tcpci: add vconn over current fault handling to
 maxim_core

Add TCPC_FAULT_STATUS_VCONN_OC constant and corresponding mask definition.
Maxim TCPC is capable of detecting VConn over current faults, so add
fault to alert mask. When a Vconn over current fault is triggered, put the
port in an error recovery state via tcpm_port_error_recovery.

Signed-off-by: RD Babiera <rdbabiera@google.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20231121203845.170234-6-rdbabiera@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tcpm/tcpci_maxim_core.c | 20 +++++++++++++++++++-
 include/linux/usb/tcpci.h                 |  5 ++++-
 2 files changed, 23 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/typec/tcpm/tcpci_maxim_core.c b/drivers/usb/typec/tcpm/tcpci_maxim_core.c
index 9454b12a073c..7fb966fd639b 100644
--- a/drivers/usb/typec/tcpm/tcpci_maxim_core.c
+++ b/drivers/usb/typec/tcpm/tcpci_maxim_core.c
@@ -92,11 +92,16 @@ static void max_tcpci_init_regs(struct max_tcpci_chip *chip)
 		return;
 	}
 
+	/* Vconn Over Current Protection */
+	ret = max_tcpci_write8(chip, TCPC_FAULT_STATUS_MASK, TCPC_FAULT_STATUS_MASK_VCONN_OC);
+	if (ret < 0)
+		return;
+
 	alert_mask = TCPC_ALERT_TX_SUCCESS | TCPC_ALERT_TX_DISCARDED | TCPC_ALERT_TX_FAILED |
 		TCPC_ALERT_RX_HARD_RST | TCPC_ALERT_RX_STATUS | TCPC_ALERT_CC_STATUS |
 		TCPC_ALERT_VBUS_DISCNCT | TCPC_ALERT_RX_BUF_OVF | TCPC_ALERT_POWER_STATUS |
 		/* Enable Extended alert for detecting Fast Role Swap Signal */
-		TCPC_ALERT_EXTND | TCPC_ALERT_EXTENDED_STATUS;
+		TCPC_ALERT_EXTND | TCPC_ALERT_EXTENDED_STATUS | TCPC_ALERT_FAULT;
 
 	ret = max_tcpci_write16(chip, TCPC_ALERT_MASK, alert_mask);
 	if (ret < 0) {
@@ -295,6 +300,19 @@ static irqreturn_t _max_tcpci_irq(struct max_tcpci_chip *chip, u16 status)
 		}
 	}
 
+	if (status & TCPC_ALERT_FAULT) {
+		ret = max_tcpci_read8(chip, TCPC_FAULT_STATUS, &reg_status);
+		if (ret < 0)
+			return ret;
+
+		ret = max_tcpci_write8(chip, TCPC_FAULT_STATUS, reg_status);
+		if (ret < 0)
+			return ret;
+
+		if (reg_status & TCPC_FAULT_STATUS_VCONN_OC)
+			tcpm_port_error_recovery(chip->port);
+	}
+
 	if (status & TCPC_ALERT_EXTND) {
 		ret = max_tcpci_read8(chip, TCPC_ALERT_EXTENDED, &reg_status);
 		if (ret < 0)
diff --git a/include/linux/usb/tcpci.h b/include/linux/usb/tcpci.h
index 83376473ac76..467e8045e9f8 100644
--- a/include/linux/usb/tcpci.h
+++ b/include/linux/usb/tcpci.h
@@ -36,7 +36,9 @@
 
 #define TCPC_ALERT_MASK			0x12
 #define TCPC_POWER_STATUS_MASK		0x14
-#define TCPC_FAULT_STATUS_MASK		0x15
+
+#define TCPC_FAULT_STATUS_MASK			0x15
+#define TCPC_FAULT_STATUS_MASK_VCONN_OC		BIT(1)
 
 #define TCPC_EXTENDED_STATUS_MASK		0x16
 #define TCPC_EXTENDED_STATUS_MASK_VSAFE0V	BIT(0)
@@ -104,6 +106,7 @@
 
 #define TCPC_FAULT_STATUS		0x1f
 #define TCPC_FAULT_STATUS_ALL_REG_RST_TO_DEFAULT BIT(7)
+#define TCPC_FAULT_STATUS_VCONN_OC	BIT(1)
 
 #define TCPC_ALERT_EXTENDED		0x21
 
-- 
cgit v1.2.3


From b89710bd215e650f0aaf8ffe7104413d46d44392 Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Date: Mon, 27 Nov 2023 18:34:28 +0100
Subject: iio: add modifiers for A and B ultraviolet light

Currently there are only two modifiers for ultraviolet light: a generic
one for any ultraviolet light (IIO_MOD_LIGHT_UV) and one for deep
ultraviolet (IIO_MOD_LIGHT_DUV), which is also referred as ultraviolet
C (UV-C) band and covers short-wave ultraviolet.

There are still no modifiers for the long-wave and medium-wave
ultraviolet bands. These two bands are the main components used to
obtain the UV index on the Earth's surface.

Add modifiers for the ultraviolet A (UV-A) and ultraviolet B (UV-B)
bands.

Signed-off-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20231110-veml6075-v3-1-6ee46775b422@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 Documentation/ABI/testing/sysfs-bus-iio | 7 +++++--
 drivers/iio/industrialio-core.c         | 2 ++
 include/uapi/linux/iio/types.h          | 2 ++
 tools/iio/iio_event_monitor.c           | 2 ++
 4 files changed, 11 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio
index 0eadc08c3a13..0d3ec5fc45f2 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio
+++ b/Documentation/ABI/testing/sysfs-bus-iio
@@ -1574,6 +1574,8 @@ What:		/sys/.../iio:deviceX/in_intensityY_raw
 What:		/sys/.../iio:deviceX/in_intensityY_ir_raw
 What:		/sys/.../iio:deviceX/in_intensityY_both_raw
 What:		/sys/.../iio:deviceX/in_intensityY_uv_raw
+What:		/sys/.../iio:deviceX/in_intensityY_uva_raw
+What:		/sys/.../iio:deviceX/in_intensityY_uvb_raw
 What:		/sys/.../iio:deviceX/in_intensityY_duv_raw
 KernelVersion:	3.4
 Contact:	linux-iio@vger.kernel.org
@@ -1582,8 +1584,9 @@ Description:
 		that measurements contain visible and infrared light
 		components or just infrared light, respectively. Modifier
 		uv indicates that measurements contain ultraviolet light
-		components. Modifier duv indicates that measurements
-		contain deep ultraviolet light components.
+		components. Modifiers uva, uvb and duv indicate that
+		measurements contain A, B or deep (C) ultraviolet light
+		components respectively.
 
 What:		/sys/.../iio:deviceX/in_uvindex_input
 KernelVersion:	4.6
diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index 34e1f8d0071c..f6a123d397db 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -117,6 +117,8 @@ static const char * const iio_modifier_names[] = {
 	[IIO_MOD_LIGHT_GREEN] = "green",
 	[IIO_MOD_LIGHT_BLUE] = "blue",
 	[IIO_MOD_LIGHT_UV] = "uv",
+	[IIO_MOD_LIGHT_UVA] = "uva",
+	[IIO_MOD_LIGHT_UVB] = "uvb",
 	[IIO_MOD_LIGHT_DUV] = "duv",
 	[IIO_MOD_QUATERNION] = "quaternion",
 	[IIO_MOD_TEMP_AMBIENT] = "ambient",
diff --git a/include/uapi/linux/iio/types.h b/include/uapi/linux/iio/types.h
index 9c2ffdcd6623..5060963707b1 100644
--- a/include/uapi/linux/iio/types.h
+++ b/include/uapi/linux/iio/types.h
@@ -91,6 +91,8 @@ enum iio_modifier {
 	IIO_MOD_CO2,
 	IIO_MOD_VOC,
 	IIO_MOD_LIGHT_UV,
+	IIO_MOD_LIGHT_UVA,
+	IIO_MOD_LIGHT_UVB,
 	IIO_MOD_LIGHT_DUV,
 	IIO_MOD_PM1,
 	IIO_MOD_PM2P5,
diff --git a/tools/iio/iio_event_monitor.c b/tools/iio/iio_event_monitor.c
index 2eaaa7123b04..8073c9e4fe46 100644
--- a/tools/iio/iio_event_monitor.c
+++ b/tools/iio/iio_event_monitor.c
@@ -105,6 +105,8 @@ static const char * const iio_modifier_names[] = {
 	[IIO_MOD_LIGHT_GREEN] = "green",
 	[IIO_MOD_LIGHT_BLUE] = "blue",
 	[IIO_MOD_LIGHT_UV] = "uv",
+	[IIO_MOD_LIGHT_UVA] = "uva",
+	[IIO_MOD_LIGHT_UVB] = "uvb",
 	[IIO_MOD_LIGHT_DUV] = "duv",
 	[IIO_MOD_QUATERNION] = "quaternion",
 	[IIO_MOD_TEMP_AMBIENT] = "ambient",
-- 
cgit v1.2.3


From 7cc4e6b0e4ddf610477fcec8e3d2a9caae7e8a6c Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 29 Nov 2023 18:06:46 +0200
Subject: pinctrl: Convert unsigned to unsigned int

Simple type conversion with no functional change implied.
While at it, adjust indentation where it makes sense.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20231129161459.1002323-24-andriy.shevchenko@linux.intel.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/core.c                  | 28 ++++++++++++-------------
 drivers/pinctrl/core.h                  | 14 ++++++-------
 drivers/pinctrl/devicetree.c            |  8 ++++----
 drivers/pinctrl/pinconf-generic.c       | 16 +++++++--------
 drivers/pinctrl/pinconf.c               | 14 ++++++-------
 drivers/pinctrl/pinconf.h               | 10 ++++-----
 drivers/pinctrl/pinctrl-utils.c         | 26 ++++++++++++------------
 drivers/pinctrl/pinctrl-utils.h         | 18 ++++++++---------
 drivers/pinctrl/pinmux.c                | 36 ++++++++++++++++-----------------
 drivers/pinctrl/pinmux.h                | 20 +++++++++---------
 include/linux/pinctrl/machine.h         |  6 +++---
 include/linux/pinctrl/pinconf-generic.h | 10 ++++-----
 include/linux/pinctrl/pinconf.h         | 16 +++++++--------
 include/linux/pinctrl/pinctrl.h         | 24 +++++++++++-----------
 include/linux/pinctrl/pinmux.h          | 22 ++++++++++----------
 15 files changed, 134 insertions(+), 134 deletions(-)

(limited to 'include')

diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c
index e55959e1af5a..6d1e44efb5f3 100644
--- a/drivers/pinctrl/core.c
+++ b/drivers/pinctrl/core.c
@@ -143,7 +143,7 @@ struct pinctrl_dev *get_pinctrl_dev_from_of_node(struct device_node *np)
  */
 int pin_get_from_name(struct pinctrl_dev *pctldev, const char *name)
 {
-	unsigned i, pin;
+	unsigned int i, pin;
 
 	/* The pin number can be retrived from the pin controller descriptor */
 	for (i = 0; i < pctldev->desc->npins; i++) {
@@ -164,7 +164,7 @@ int pin_get_from_name(struct pinctrl_dev *pctldev, const char *name)
  * @pctldev: the pin control device to lookup the pin on
  * @pin: pin number/id to look up
  */
-const char *pin_get_name(struct pinctrl_dev *pctldev, const unsigned pin)
+const char *pin_get_name(struct pinctrl_dev *pctldev, const unsigned int pin)
 {
 	const struct pin_desc *desc;
 
@@ -182,7 +182,7 @@ EXPORT_SYMBOL_GPL(pin_get_name);
 /* Deletes a range of pin descriptors */
 static void pinctrl_free_pindescs(struct pinctrl_dev *pctldev,
 				  const struct pinctrl_pin_desc *pins,
-				  unsigned num_pins)
+				  unsigned int num_pins)
 {
 	int i;
 
@@ -250,9 +250,9 @@ failed:
 
 static int pinctrl_register_pins(struct pinctrl_dev *pctldev,
 				 const struct pinctrl_pin_desc *pins,
-				 unsigned num_descs)
+				 unsigned int num_descs)
 {
-	unsigned i;
+	unsigned int i;
 	int ret = 0;
 
 	for (i = 0; i < num_descs; i++) {
@@ -426,7 +426,7 @@ EXPORT_SYMBOL_GPL(pinctrl_add_gpio_range);
 
 void pinctrl_add_gpio_ranges(struct pinctrl_dev *pctldev,
 			     struct pinctrl_gpio_range *ranges,
-			     unsigned nranges)
+			     unsigned int nranges)
 {
 	int i;
 
@@ -457,7 +457,7 @@ struct pinctrl_dev *pinctrl_find_and_add_gpio_range(const char *devname,
 EXPORT_SYMBOL_GPL(pinctrl_find_and_add_gpio_range);
 
 int pinctrl_get_group_pins(struct pinctrl_dev *pctldev, const char *pin_group,
-				const unsigned **pins, unsigned *num_pins)
+			   const unsigned int **pins, unsigned int *num_pins)
 {
 	const struct pinctrl_ops *pctlops = pctldev->desc->pctlops;
 	int gs;
@@ -732,8 +732,8 @@ int pinctrl_get_group_selector(struct pinctrl_dev *pctldev,
 			       const char *pin_group)
 {
 	const struct pinctrl_ops *pctlops = pctldev->desc->pctlops;
-	unsigned ngroups = pctlops->get_groups_count(pctldev);
-	unsigned group_selector = 0;
+	unsigned int ngroups = pctlops->get_groups_count(pctldev);
+	unsigned int group_selector = 0;
 
 	while (group_selector < ngroups) {
 		const char *gname = pctlops->get_group_name(pctldev,
@@ -1430,7 +1430,7 @@ EXPORT_SYMBOL_GPL(devm_pinctrl_put);
  * @num_maps: the number of maps in the mapping table
  */
 int pinctrl_register_mappings(const struct pinctrl_map *maps,
-			      unsigned num_maps)
+			      unsigned int num_maps)
 {
 	int i, ret;
 	struct pinctrl_maps *maps_node;
@@ -1645,7 +1645,7 @@ static int pinctrl_pins_show(struct seq_file *s, void *what)
 {
 	struct pinctrl_dev *pctldev = s->private;
 	const struct pinctrl_ops *ops = pctldev->desc->pctlops;
-	unsigned i, pin;
+	unsigned int i, pin;
 #ifdef CONFIG_GPIOLIB
 	struct gpio_device *gdev __free(gpio_device_put) = NULL;
 	struct pinctrl_gpio_range *range;
@@ -1709,7 +1709,7 @@ static int pinctrl_groups_show(struct seq_file *s, void *what)
 {
 	struct pinctrl_dev *pctldev = s->private;
 	const struct pinctrl_ops *ops = pctldev->desc->pctlops;
-	unsigned ngroups, selector = 0;
+	unsigned int ngroups, selector = 0;
 
 	mutex_lock(&pctldev->mutex);
 
@@ -1717,8 +1717,8 @@ static int pinctrl_groups_show(struct seq_file *s, void *what)
 
 	seq_puts(s, "registered pin groups:\n");
 	while (selector < ngroups) {
-		const unsigned *pins = NULL;
-		unsigned num_pins = 0;
+		const unsigned int *pins = NULL;
+		unsigned int num_pins = 0;
 		const char *gname = ops->get_group_name(pctldev, selector);
 		const char *pname;
 		int ret = 0;
diff --git a/drivers/pinctrl/core.h b/drivers/pinctrl/core.h
index 530370443c19..8b59dd72e4ff 100644
--- a/drivers/pinctrl/core.h
+++ b/drivers/pinctrl/core.h
@@ -111,8 +111,8 @@ struct pinctrl_state {
  * @func: the function selector to program
  */
 struct pinctrl_setting_mux {
-	unsigned group;
-	unsigned func;
+	unsigned int group;
+	unsigned int func;
 };
 
 /**
@@ -124,9 +124,9 @@ struct pinctrl_setting_mux {
  * @num_configs: the number of entries in array @configs
  */
 struct pinctrl_setting_configs {
-	unsigned group_or_pin;
+	unsigned int group_or_pin;
 	unsigned long *configs;
-	unsigned num_configs;
+	unsigned int num_configs;
 };
 
 /**
@@ -173,7 +173,7 @@ struct pin_desc {
 	void *drv_data;
 	/* These fields only added when supporting pinmux drivers */
 #ifdef CONFIG_PINMUX
-	unsigned mux_usecount;
+	unsigned int mux_usecount;
 	const char *mux_owner;
 	const struct pinctrl_setting_mux *mux_setting;
 	const char *gpio_owner;
@@ -189,7 +189,7 @@ struct pin_desc {
 struct pinctrl_maps {
 	struct list_head node;
 	const struct pinctrl_map *maps;
-	unsigned num_maps;
+	unsigned int num_maps;
 };
 
 #ifdef CONFIG_GENERIC_PINCTRL_GROUPS
@@ -232,7 +232,7 @@ int pinctrl_generic_remove_group(struct pinctrl_dev *pctldev,
 struct pinctrl_dev *get_pinctrl_dev_from_devname(const char *dev_name);
 struct pinctrl_dev *get_pinctrl_dev_from_of_node(struct device_node *np);
 int pin_get_from_name(struct pinctrl_dev *pctldev, const char *name);
-const char *pin_get_name(struct pinctrl_dev *pctldev, const unsigned pin);
+const char *pin_get_name(struct pinctrl_dev *pctldev, const unsigned int pin);
 int pinctrl_get_group_selector(struct pinctrl_dev *pctldev,
 			       const char *pin_group);
 
diff --git a/drivers/pinctrl/devicetree.c b/drivers/pinctrl/devicetree.c
index 6e0a40962f38..df1efc2e5202 100644
--- a/drivers/pinctrl/devicetree.c
+++ b/drivers/pinctrl/devicetree.c
@@ -24,11 +24,11 @@ struct pinctrl_dt_map {
 	struct list_head node;
 	struct pinctrl_dev *pctldev;
 	struct pinctrl_map *map;
-	unsigned num_maps;
+	unsigned int num_maps;
 };
 
 static void dt_free_map(struct pinctrl_dev *pctldev,
-		     struct pinctrl_map *map, unsigned num_maps)
+			struct pinctrl_map *map, unsigned int num_maps)
 {
 	int i;
 
@@ -64,7 +64,7 @@ void pinctrl_dt_free_maps(struct pinctrl *p)
 
 static int dt_remember_or_free_map(struct pinctrl *p, const char *statename,
 				   struct pinctrl_dev *pctldev,
-				   struct pinctrl_map *map, unsigned num_maps)
+				   struct pinctrl_map *map, unsigned int num_maps)
 {
 	int i;
 	struct pinctrl_dt_map *dt_map;
@@ -116,7 +116,7 @@ static int dt_to_map_one_config(struct pinctrl *p,
 	const struct pinctrl_ops *ops;
 	int ret;
 	struct pinctrl_map *map;
-	unsigned num_maps;
+	unsigned int num_maps;
 	bool allow_default = false;
 
 	/* Find the pin controller containing np_config */
diff --git a/drivers/pinctrl/pinconf-generic.c b/drivers/pinctrl/pinconf-generic.c
index 8313cb5f3b3c..cada5d18ffae 100644
--- a/drivers/pinctrl/pinconf-generic.c
+++ b/drivers/pinctrl/pinconf-generic.c
@@ -57,7 +57,7 @@ static const struct pin_config_item conf_items[] = {
 
 static void pinconf_generic_dump_one(struct pinctrl_dev *pctldev,
 				     struct seq_file *s, const char *gname,
-				     unsigned pin,
+				     unsigned int pin,
 				     const struct pin_config_item *items,
 				     int nitems, int *print_sep)
 {
@@ -110,7 +110,7 @@ static void pinconf_generic_dump_one(struct pinctrl_dev *pctldev,
  * to be specified the other can be NULL/0.
  */
 void pinconf_generic_dump_pins(struct pinctrl_dev *pctldev, struct seq_file *s,
-			       const char *gname, unsigned pin)
+			       const char *gname, unsigned int pin)
 {
 	const struct pinconf_ops *ops = pctldev->desc->confops;
 	int print_sep = 0;
@@ -295,15 +295,15 @@ EXPORT_SYMBOL_GPL(pinconf_generic_parse_dt_config);
 
 int pinconf_generic_dt_subnode_to_map(struct pinctrl_dev *pctldev,
 		struct device_node *np, struct pinctrl_map **map,
-		unsigned *reserved_maps, unsigned *num_maps,
+		unsigned int *reserved_maps, unsigned int *num_maps,
 		enum pinctrl_map_type type)
 {
 	int ret;
 	const char *function;
 	struct device *dev = pctldev->dev;
 	unsigned long *configs = NULL;
-	unsigned num_configs = 0;
-	unsigned reserve, strings_count;
+	unsigned int num_configs = 0;
+	unsigned int reserve, strings_count;
 	struct property *prop;
 	const char *group;
 	const char *subnode_target_type = "pins";
@@ -379,9 +379,9 @@ EXPORT_SYMBOL_GPL(pinconf_generic_dt_subnode_to_map);
 
 int pinconf_generic_dt_node_to_map(struct pinctrl_dev *pctldev,
 		struct device_node *np_config, struct pinctrl_map **map,
-		unsigned *num_maps, enum pinctrl_map_type type)
+		unsigned int *num_maps, enum pinctrl_map_type type)
 {
-	unsigned reserved_maps;
+	unsigned int reserved_maps;
 	struct device_node *np;
 	int ret;
 
@@ -412,7 +412,7 @@ EXPORT_SYMBOL_GPL(pinconf_generic_dt_node_to_map);
 
 void pinconf_generic_dt_free_map(struct pinctrl_dev *pctldev,
 				 struct pinctrl_map *map,
-				 unsigned num_maps)
+				 unsigned int num_maps)
 {
 	pinctrl_utils_free_map(pctldev, map, num_maps);
 }
diff --git a/drivers/pinctrl/pinconf.c b/drivers/pinctrl/pinconf.c
index 96d853a8f339..dca963633b5d 100644
--- a/drivers/pinctrl/pinconf.c
+++ b/drivers/pinctrl/pinconf.c
@@ -55,7 +55,7 @@ int pinconf_validate_map(const struct pinctrl_map *map, int i)
 	return 0;
 }
 
-int pin_config_get_for_pin(struct pinctrl_dev *pctldev, unsigned pin,
+int pin_config_get_for_pin(struct pinctrl_dev *pctldev, unsigned int pin,
 			   unsigned long *config)
 {
 	const struct pinconf_ops *ops = pctldev->desc->confops;
@@ -199,7 +199,7 @@ int pinconf_apply_setting(const struct pinctrl_setting *setting)
 	return 0;
 }
 
-int pinconf_set_config(struct pinctrl_dev *pctldev, unsigned pin,
+int pinconf_set_config(struct pinctrl_dev *pctldev, unsigned int pin,
 		       unsigned long *configs, size_t nconfigs)
 {
 	const struct pinconf_ops *ops;
@@ -214,7 +214,7 @@ int pinconf_set_config(struct pinctrl_dev *pctldev, unsigned pin,
 #ifdef CONFIG_DEBUG_FS
 
 static void pinconf_show_config(struct seq_file *s, struct pinctrl_dev *pctldev,
-		      unsigned long *configs, unsigned num_configs)
+				unsigned long *configs, unsigned int num_configs)
 {
 	const struct pinconf_ops *confops;
 	int i;
@@ -304,7 +304,7 @@ static void pinconf_dump_pin(struct pinctrl_dev *pctldev,
 static int pinconf_pins_show(struct seq_file *s, void *what)
 {
 	struct pinctrl_dev *pctldev = s->private;
-	unsigned i, pin;
+	unsigned int i, pin;
 
 	seq_puts(s, "Pin config settings per pin\n");
 	seq_puts(s, "Format: pin (name): configs\n");
@@ -333,7 +333,7 @@ static int pinconf_pins_show(struct seq_file *s, void *what)
 }
 
 static void pinconf_dump_group(struct pinctrl_dev *pctldev,
-			       struct seq_file *s, unsigned selector,
+			       struct seq_file *s, unsigned int selector,
 			       const char *gname)
 {
 	const struct pinconf_ops *ops = pctldev->desc->confops;
@@ -348,8 +348,8 @@ static int pinconf_groups_show(struct seq_file *s, void *what)
 {
 	struct pinctrl_dev *pctldev = s->private;
 	const struct pinctrl_ops *pctlops = pctldev->desc->pctlops;
-	unsigned ngroups = pctlops->get_groups_count(pctldev);
-	unsigned selector = 0;
+	unsigned int ngroups = pctlops->get_groups_count(pctldev);
+	unsigned int selector = 0;
 
 	seq_puts(s, "Pin config settings per pin group\n");
 	seq_puts(s, "Format: group (name): configs\n");
diff --git a/drivers/pinctrl/pinconf.h b/drivers/pinctrl/pinconf.h
index 694bfc9961fa..a14c950bc700 100644
--- a/drivers/pinctrl/pinconf.h
+++ b/drivers/pinctrl/pinconf.h
@@ -29,14 +29,14 @@ int pinconf_map_to_setting(const struct pinctrl_map *map,
 void pinconf_free_setting(const struct pinctrl_setting *setting);
 int pinconf_apply_setting(const struct pinctrl_setting *setting);
 
-int pinconf_set_config(struct pinctrl_dev *pctldev, unsigned pin,
+int pinconf_set_config(struct pinctrl_dev *pctldev, unsigned int pin,
 		       unsigned long *configs, size_t nconfigs);
 
 /*
  * You will only be interested in these if you're using PINCONF
  * so don't supply any stubs for these.
  */
-int pin_config_get_for_pin(struct pinctrl_dev *pctldev, unsigned pin,
+int pin_config_get_for_pin(struct pinctrl_dev *pctldev, unsigned int pin,
 			   unsigned long *config);
 int pin_config_group_get(const char *dev_name, const char *pin_group,
 			 unsigned long *config);
@@ -68,7 +68,7 @@ static inline int pinconf_apply_setting(const struct pinctrl_setting *setting)
 	return 0;
 }
 
-static inline int pinconf_set_config(struct pinctrl_dev *pctldev, unsigned pin,
+static inline int pinconf_set_config(struct pinctrl_dev *pctldev, unsigned int pin,
 				     unsigned long *configs, size_t nconfigs)
 {
 	return -ENOTSUPP;
@@ -112,7 +112,7 @@ static inline void pinconf_init_device_debugfs(struct dentry *devroot,
 
 void pinconf_generic_dump_pins(struct pinctrl_dev *pctldev,
 			       struct seq_file *s, const char *gname,
-			       unsigned pin);
+			       unsigned int pin);
 
 void pinconf_generic_dump_config(struct pinctrl_dev *pctldev,
 				 struct seq_file *s, unsigned long config);
@@ -120,7 +120,7 @@ void pinconf_generic_dump_config(struct pinctrl_dev *pctldev,
 
 static inline void pinconf_generic_dump_pins(struct pinctrl_dev *pctldev,
 					     struct seq_file *s,
-					     const char *gname, unsigned pin)
+					     const char *gname, unsigned int pin)
 {
 	return;
 }
diff --git a/drivers/pinctrl/pinctrl-utils.c b/drivers/pinctrl/pinctrl-utils.c
index 40862f7bd6ca..d81d7b46116c 100644
--- a/drivers/pinctrl/pinctrl-utils.c
+++ b/drivers/pinctrl/pinctrl-utils.c
@@ -18,11 +18,11 @@
 #include "pinctrl-utils.h"
 
 int pinctrl_utils_reserve_map(struct pinctrl_dev *pctldev,
-		struct pinctrl_map **map, unsigned *reserved_maps,
-		unsigned *num_maps, unsigned reserve)
+		struct pinctrl_map **map, unsigned int *reserved_maps,
+		unsigned int *num_maps, unsigned int reserve)
 {
-	unsigned old_num = *reserved_maps;
-	unsigned new_num = *num_maps + reserve;
+	unsigned int old_num = *reserved_maps;
+	unsigned int new_num = *num_maps + reserve;
 	struct pinctrl_map *new_map;
 
 	if (old_num >= new_num)
@@ -43,8 +43,8 @@ int pinctrl_utils_reserve_map(struct pinctrl_dev *pctldev,
 EXPORT_SYMBOL_GPL(pinctrl_utils_reserve_map);
 
 int pinctrl_utils_add_map_mux(struct pinctrl_dev *pctldev,
-		struct pinctrl_map **map, unsigned *reserved_maps,
-		unsigned *num_maps, const char *group,
+		struct pinctrl_map **map, unsigned int *reserved_maps,
+		unsigned int *num_maps, const char *group,
 		const char *function)
 {
 	if (WARN_ON(*num_maps == *reserved_maps))
@@ -60,9 +60,9 @@ int pinctrl_utils_add_map_mux(struct pinctrl_dev *pctldev,
 EXPORT_SYMBOL_GPL(pinctrl_utils_add_map_mux);
 
 int pinctrl_utils_add_map_configs(struct pinctrl_dev *pctldev,
-		struct pinctrl_map **map, unsigned *reserved_maps,
-		unsigned *num_maps, const char *group,
-		unsigned long *configs, unsigned num_configs,
+		struct pinctrl_map **map, unsigned int *reserved_maps,
+		unsigned int *num_maps, const char *group,
+		unsigned long *configs, unsigned int num_configs,
 		enum pinctrl_map_type type)
 {
 	unsigned long *dup_configs;
@@ -86,11 +86,11 @@ int pinctrl_utils_add_map_configs(struct pinctrl_dev *pctldev,
 EXPORT_SYMBOL_GPL(pinctrl_utils_add_map_configs);
 
 int pinctrl_utils_add_config(struct pinctrl_dev *pctldev,
-		unsigned long **configs, unsigned *num_configs,
+		unsigned long **configs, unsigned int *num_configs,
 		unsigned long config)
 {
-	unsigned old_num = *num_configs;
-	unsigned new_num = old_num + 1;
+	unsigned int old_num = *num_configs;
+	unsigned int new_num = old_num + 1;
 	unsigned long *new_configs;
 
 	new_configs = krealloc(*configs, sizeof(*new_configs) * new_num,
@@ -110,7 +110,7 @@ int pinctrl_utils_add_config(struct pinctrl_dev *pctldev,
 EXPORT_SYMBOL_GPL(pinctrl_utils_add_config);
 
 void pinctrl_utils_free_map(struct pinctrl_dev *pctldev,
-	      struct pinctrl_map *map, unsigned num_maps)
+	      struct pinctrl_map *map, unsigned int num_maps)
 {
 	int i;
 
diff --git a/drivers/pinctrl/pinctrl-utils.h b/drivers/pinctrl/pinctrl-utils.h
index 4108ee2dd6d0..203fba257d71 100644
--- a/drivers/pinctrl/pinctrl-utils.h
+++ b/drivers/pinctrl/pinctrl-utils.h
@@ -15,21 +15,21 @@ struct pinctrl_dev;
 struct pinctrl_map;
 
 int pinctrl_utils_reserve_map(struct pinctrl_dev *pctldev,
-		struct pinctrl_map **map, unsigned *reserved_maps,
-		unsigned *num_maps, unsigned reserve);
+		struct pinctrl_map **map, unsigned int *reserved_maps,
+		unsigned int *num_maps, unsigned int reserve);
 int pinctrl_utils_add_map_mux(struct pinctrl_dev *pctldev,
-		struct pinctrl_map **map, unsigned *reserved_maps,
-		unsigned *num_maps, const char *group,
+		struct pinctrl_map **map, unsigned int *reserved_maps,
+		unsigned int *num_maps, const char *group,
 		const char *function);
 int pinctrl_utils_add_map_configs(struct pinctrl_dev *pctldev,
-		struct pinctrl_map **map, unsigned *reserved_maps,
-		unsigned *num_maps, const char *group,
-		unsigned long *configs, unsigned num_configs,
+		struct pinctrl_map **map, unsigned int *reserved_maps,
+		unsigned int *num_maps, const char *group,
+		unsigned long *configs, unsigned int num_configs,
 		enum pinctrl_map_type type);
 int pinctrl_utils_add_config(struct pinctrl_dev *pctldev,
-		unsigned long **configs, unsigned *num_configs,
+		unsigned long **configs, unsigned int *num_configs,
 		unsigned long config);
 void pinctrl_utils_free_map(struct pinctrl_dev *pctldev,
-		struct pinctrl_map *map, unsigned num_maps);
+		struct pinctrl_map *map, unsigned int num_maps);
 
 #endif /* __PINCTRL_UTILS_H__ */
diff --git a/drivers/pinctrl/pinmux.c b/drivers/pinctrl/pinmux.c
index 23d2da0b99b9..abbb044d6ace 100644
--- a/drivers/pinctrl/pinmux.c
+++ b/drivers/pinctrl/pinmux.c
@@ -35,8 +35,8 @@
 int pinmux_check_ops(struct pinctrl_dev *pctldev)
 {
 	const struct pinmux_ops *ops = pctldev->desc->pmxops;
-	unsigned nfuncs;
-	unsigned selector = 0;
+	unsigned int nfuncs;
+	unsigned int selector = 0;
 
 	/* Check that we implement required operations */
 	if (!ops ||
@@ -84,7 +84,7 @@ int pinmux_validate_map(const struct pinctrl_map *map, int i)
  * Controllers not defined as strict will always return true,
  * menaning that the gpio can be used.
  */
-bool pinmux_can_be_used_for_gpio(struct pinctrl_dev *pctldev, unsigned pin)
+bool pinmux_can_be_used_for_gpio(struct pinctrl_dev *pctldev, unsigned int pin)
 {
 	struct pin_desc *desc = pin_desc_get(pctldev, pin);
 	const struct pinmux_ops *ops = pctldev->desc->pmxops;
@@ -262,7 +262,7 @@ static const char *pin_free(struct pinctrl_dev *pctldev, int pin,
  */
 int pinmux_request_gpio(struct pinctrl_dev *pctldev,
 			struct pinctrl_gpio_range *range,
-			unsigned pin, unsigned gpio)
+			unsigned int pin, unsigned int gpio)
 {
 	const char *owner;
 	int ret;
@@ -285,7 +285,7 @@ int pinmux_request_gpio(struct pinctrl_dev *pctldev,
  * @pin: the affected currently GPIO-muxed in pin
  * @range: applicable GPIO range
  */
-void pinmux_free_gpio(struct pinctrl_dev *pctldev, unsigned pin,
+void pinmux_free_gpio(struct pinctrl_dev *pctldev, unsigned int pin,
 		      struct pinctrl_gpio_range *range)
 {
 	const char *owner;
@@ -303,7 +303,7 @@ void pinmux_free_gpio(struct pinctrl_dev *pctldev, unsigned pin,
  */
 int pinmux_gpio_direction(struct pinctrl_dev *pctldev,
 			  struct pinctrl_gpio_range *range,
-			  unsigned pin, bool input)
+			  unsigned int pin, bool input)
 {
 	const struct pinmux_ops *ops;
 	int ret;
@@ -322,8 +322,8 @@ static int pinmux_func_name_to_selector(struct pinctrl_dev *pctldev,
 					const char *function)
 {
 	const struct pinmux_ops *ops = pctldev->desc->pmxops;
-	unsigned nfuncs = ops->get_functions_count(pctldev);
-	unsigned selector = 0;
+	unsigned int nfuncs = ops->get_functions_count(pctldev);
+	unsigned int selector = 0;
 
 	/* See if this pctldev has this function */
 	while (selector < nfuncs) {
@@ -344,7 +344,7 @@ int pinmux_map_to_setting(const struct pinctrl_map *map,
 	struct pinctrl_dev *pctldev = setting->pctldev;
 	const struct pinmux_ops *pmxops = pctldev->desc->pmxops;
 	char const * const *groups;
-	unsigned num_groups;
+	unsigned int num_groups;
 	int ret;
 	const char *group;
 
@@ -409,8 +409,8 @@ int pinmux_enable_setting(const struct pinctrl_setting *setting)
 	const struct pinctrl_ops *pctlops = pctldev->desc->pctlops;
 	const struct pinmux_ops *ops = pctldev->desc->pmxops;
 	int ret = 0;
-	const unsigned *pins = NULL;
-	unsigned num_pins = 0;
+	const unsigned int *pins = NULL;
+	unsigned int num_pins = 0;
 	int i;
 	struct pin_desc *desc;
 
@@ -489,8 +489,8 @@ void pinmux_disable_setting(const struct pinctrl_setting *setting)
 	struct pinctrl_dev *pctldev = setting->pctldev;
 	const struct pinctrl_ops *pctlops = pctldev->desc->pctlops;
 	int ret = 0;
-	const unsigned *pins = NULL;
-	unsigned num_pins = 0;
+	const unsigned int *pins = NULL;
+	unsigned int num_pins = 0;
 	int i;
 	struct pin_desc *desc;
 
@@ -541,8 +541,8 @@ static int pinmux_functions_show(struct seq_file *s, void *what)
 {
 	struct pinctrl_dev *pctldev = s->private;
 	const struct pinmux_ops *pmxops = pctldev->desc->pmxops;
-	unsigned nfuncs;
-	unsigned func_selector = 0;
+	unsigned int nfuncs;
+	unsigned int func_selector = 0;
 
 	if (!pmxops)
 		return 0;
@@ -553,7 +553,7 @@ static int pinmux_functions_show(struct seq_file *s, void *what)
 		const char *func = pmxops->get_function_name(pctldev,
 							  func_selector);
 		const char * const *groups;
-		unsigned num_groups;
+		unsigned int num_groups;
 		int ret;
 		int i;
 
@@ -584,7 +584,7 @@ static int pinmux_pins_show(struct seq_file *s, void *what)
 	struct pinctrl_dev *pctldev = s->private;
 	const struct pinctrl_ops *pctlops = pctldev->desc->pctlops;
 	const struct pinmux_ops *pmxops = pctldev->desc->pmxops;
-	unsigned i, pin;
+	unsigned int i, pin;
 
 	if (!pmxops)
 		return 0;
@@ -818,7 +818,7 @@ EXPORT_SYMBOL_GPL(pinmux_generic_get_function_name);
 int pinmux_generic_get_function_groups(struct pinctrl_dev *pctldev,
 				       unsigned int selector,
 				       const char * const **groups,
-				       unsigned * const num_groups)
+				       unsigned int * const num_groups)
 {
 	struct function_desc *function;
 
diff --git a/drivers/pinctrl/pinmux.h b/drivers/pinctrl/pinmux.h
index ea6f99c24aa5..7c8aa25ccc80 100644
--- a/drivers/pinctrl/pinmux.h
+++ b/drivers/pinctrl/pinmux.h
@@ -26,16 +26,16 @@ int pinmux_check_ops(struct pinctrl_dev *pctldev);
 
 int pinmux_validate_map(const struct pinctrl_map *map, int i);
 
-bool pinmux_can_be_used_for_gpio(struct pinctrl_dev *pctldev, unsigned pin);
+bool pinmux_can_be_used_for_gpio(struct pinctrl_dev *pctldev, unsigned int pin);
 
 int pinmux_request_gpio(struct pinctrl_dev *pctldev,
 			struct pinctrl_gpio_range *range,
-			unsigned pin, unsigned gpio);
-void pinmux_free_gpio(struct pinctrl_dev *pctldev, unsigned pin,
+			unsigned int pin, unsigned int gpio);
+void pinmux_free_gpio(struct pinctrl_dev *pctldev, unsigned int pin,
 		      struct pinctrl_gpio_range *range);
 int pinmux_gpio_direction(struct pinctrl_dev *pctldev,
 			  struct pinctrl_gpio_range *range,
-			  unsigned pin, bool input);
+			  unsigned int pin, bool input);
 
 int pinmux_map_to_setting(const struct pinctrl_map *map,
 			  struct pinctrl_setting *setting);
@@ -56,27 +56,27 @@ static inline int pinmux_validate_map(const struct pinctrl_map *map, int i)
 }
 
 static inline bool pinmux_can_be_used_for_gpio(struct pinctrl_dev *pctldev,
-					       unsigned pin)
+					       unsigned int pin)
 {
 	return true;
 }
 
 static inline int pinmux_request_gpio(struct pinctrl_dev *pctldev,
 			struct pinctrl_gpio_range *range,
-			unsigned pin, unsigned gpio)
+			unsigned int pin, unsigned int gpio)
 {
 	return 0;
 }
 
 static inline void pinmux_free_gpio(struct pinctrl_dev *pctldev,
-				    unsigned pin,
+				    unsigned int pin,
 				    struct pinctrl_gpio_range *range)
 {
 }
 
 static inline int pinmux_gpio_direction(struct pinctrl_dev *pctldev,
 					struct pinctrl_gpio_range *range,
-					unsigned pin, bool input)
+					unsigned int pin, bool input)
 {
 	return 0;
 }
@@ -154,7 +154,7 @@ pinmux_generic_get_function_name(struct pinctrl_dev *pctldev,
 int pinmux_generic_get_function_groups(struct pinctrl_dev *pctldev,
 				       unsigned int selector,
 				       const char * const **groups,
-				       unsigned * const num_groups);
+				       unsigned int * const num_groups);
 
 struct function_desc *pinmux_generic_get_function(struct pinctrl_dev *pctldev,
 						  unsigned int selector);
@@ -162,7 +162,7 @@ struct function_desc *pinmux_generic_get_function(struct pinctrl_dev *pctldev,
 int pinmux_generic_add_function(struct pinctrl_dev *pctldev,
 				const char *name,
 				const char * const *groups,
-				unsigned const num_groups,
+				unsigned int const num_groups,
 				void *data);
 
 int pinmux_generic_remove_function(struct pinctrl_dev *pctldev,
diff --git a/include/linux/pinctrl/machine.h b/include/linux/pinctrl/machine.h
index ee8803f6ad07..673e96df453b 100644
--- a/include/linux/pinctrl/machine.h
+++ b/include/linux/pinctrl/machine.h
@@ -47,7 +47,7 @@ struct pinctrl_map_mux {
 struct pinctrl_map_configs {
 	const char *group_or_pin;
 	unsigned long *configs;
-	unsigned num_configs;
+	unsigned int num_configs;
 };
 
 /**
@@ -154,13 +154,13 @@ struct pinctrl_map;
 #ifdef CONFIG_PINCTRL
 
 extern int pinctrl_register_mappings(const struct pinctrl_map *map,
-				     unsigned num_maps);
+				     unsigned int num_maps);
 extern void pinctrl_unregister_mappings(const struct pinctrl_map *map);
 extern void pinctrl_provide_dummies(void);
 #else
 
 static inline int pinctrl_register_mappings(const struct pinctrl_map *map,
-					    unsigned num_maps)
+					    unsigned int num_maps)
 {
 	return 0;
 }
diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h
index d74b7a4ea154..a65d3d078e58 100644
--- a/include/linux/pinctrl/pinconf-generic.h
+++ b/include/linux/pinctrl/pinconf-generic.h
@@ -193,17 +193,17 @@ struct pinconf_generic_params {
 
 int pinconf_generic_dt_subnode_to_map(struct pinctrl_dev *pctldev,
 		struct device_node *np, struct pinctrl_map **map,
-		unsigned *reserved_maps, unsigned *num_maps,
+		unsigned int *reserved_maps, unsigned int *num_maps,
 		enum pinctrl_map_type type);
 int pinconf_generic_dt_node_to_map(struct pinctrl_dev *pctldev,
 		struct device_node *np_config, struct pinctrl_map **map,
-		unsigned *num_maps, enum pinctrl_map_type type);
+		unsigned int *num_maps, enum pinctrl_map_type type);
 void pinconf_generic_dt_free_map(struct pinctrl_dev *pctldev,
-		struct pinctrl_map *map, unsigned num_maps);
+		struct pinctrl_map *map, unsigned int num_maps);
 
 static inline int pinconf_generic_dt_node_to_map_group(struct pinctrl_dev *pctldev,
 		struct device_node *np_config, struct pinctrl_map **map,
-		unsigned *num_maps)
+		unsigned int *num_maps)
 {
 	return pinconf_generic_dt_node_to_map(pctldev, np_config, map, num_maps,
 			PIN_MAP_TYPE_CONFIGS_GROUP);
@@ -211,7 +211,7 @@ static inline int pinconf_generic_dt_node_to_map_group(struct pinctrl_dev *pctld
 
 static inline int pinconf_generic_dt_node_to_map_pin(struct pinctrl_dev *pctldev,
 		struct device_node *np_config, struct pinctrl_map **map,
-		unsigned *num_maps)
+		unsigned int *num_maps)
 {
 	return pinconf_generic_dt_node_to_map(pctldev, np_config, map, num_maps,
 			PIN_MAP_TYPE_CONFIGS_PIN);
diff --git a/include/linux/pinctrl/pinconf.h b/include/linux/pinctrl/pinconf.h
index f8a8215e9021..770ec2221156 100644
--- a/include/linux/pinctrl/pinconf.h
+++ b/include/linux/pinctrl/pinconf.h
@@ -40,25 +40,25 @@ struct pinconf_ops {
 	bool is_generic;
 #endif
 	int (*pin_config_get) (struct pinctrl_dev *pctldev,
-			       unsigned pin,
+			       unsigned int pin,
 			       unsigned long *config);
 	int (*pin_config_set) (struct pinctrl_dev *pctldev,
-			       unsigned pin,
+			       unsigned int pin,
 			       unsigned long *configs,
-			       unsigned num_configs);
+			       unsigned int num_configs);
 	int (*pin_config_group_get) (struct pinctrl_dev *pctldev,
-				     unsigned selector,
+				     unsigned int selector,
 				     unsigned long *config);
 	int (*pin_config_group_set) (struct pinctrl_dev *pctldev,
-				     unsigned selector,
+				     unsigned int selector,
 				     unsigned long *configs,
-				     unsigned num_configs);
+				     unsigned int num_configs);
 	void (*pin_config_dbg_show) (struct pinctrl_dev *pctldev,
 				     struct seq_file *s,
-				     unsigned offset);
+				     unsigned int offset);
 	void (*pin_config_group_dbg_show) (struct pinctrl_dev *pctldev,
 					   struct seq_file *s,
-					   unsigned selector);
+					   unsigned int selector);
 	void (*pin_config_config_dbg_show) (struct pinctrl_dev *pctldev,
 					    struct seq_file *s,
 					    unsigned long config);
diff --git a/include/linux/pinctrl/pinctrl.h b/include/linux/pinctrl/pinctrl.h
index 4d252ea00ed1..9a8189ffd0f2 100644
--- a/include/linux/pinctrl/pinctrl.h
+++ b/include/linux/pinctrl/pinctrl.h
@@ -54,7 +54,7 @@ struct pingroup {
  * @drv_data: driver-defined per-pin data. pinctrl core does not touch this
  */
 struct pinctrl_pin_desc {
-	unsigned number;
+	unsigned int number;
 	const char *name;
 	void *drv_data;
 };
@@ -82,7 +82,7 @@ struct pinctrl_gpio_range {
 	unsigned int base;
 	unsigned int pin_base;
 	unsigned int npins;
-	unsigned const *pins;
+	unsigned int const *pins;
 	struct gpio_chip *gc;
 };
 
@@ -108,18 +108,18 @@ struct pinctrl_gpio_range {
 struct pinctrl_ops {
 	int (*get_groups_count) (struct pinctrl_dev *pctldev);
 	const char *(*get_group_name) (struct pinctrl_dev *pctldev,
-				       unsigned selector);
+				       unsigned int selector);
 	int (*get_group_pins) (struct pinctrl_dev *pctldev,
-			       unsigned selector,
-			       const unsigned **pins,
-			       unsigned *num_pins);
+			       unsigned int selector,
+			       const unsigned int **pins,
+			       unsigned int *num_pins);
 	void (*pin_dbg_show) (struct pinctrl_dev *pctldev, struct seq_file *s,
-			  unsigned offset);
+			      unsigned int offset);
 	int (*dt_node_to_map) (struct pinctrl_dev *pctldev,
 			       struct device_node *np_config,
-			       struct pinctrl_map **map, unsigned *num_maps);
+			       struct pinctrl_map **map, unsigned int *num_maps);
 	void (*dt_free_map) (struct pinctrl_dev *pctldev,
-			     struct pinctrl_map *map, unsigned num_maps);
+			     struct pinctrl_map *map, unsigned int num_maps);
 };
 
 /**
@@ -193,7 +193,7 @@ extern void pinctrl_add_gpio_range(struct pinctrl_dev *pctldev,
 				struct pinctrl_gpio_range *range);
 extern void pinctrl_add_gpio_ranges(struct pinctrl_dev *pctldev,
 				struct pinctrl_gpio_range *ranges,
-				unsigned nranges);
+				unsigned int nranges);
 extern void pinctrl_remove_gpio_range(struct pinctrl_dev *pctldev,
 				struct pinctrl_gpio_range *range);
 
@@ -203,8 +203,8 @@ extern struct pinctrl_gpio_range *
 pinctrl_find_gpio_range_from_pin(struct pinctrl_dev *pctldev,
 				 unsigned int pin);
 extern int pinctrl_get_group_pins(struct pinctrl_dev *pctldev,
-				const char *pin_group, const unsigned **pins,
-				unsigned *num_pins);
+				  const char *pin_group, const unsigned int **pins,
+				  unsigned int *num_pins);
 
 /**
  * struct pinfunction - Description about a function
diff --git a/include/linux/pinctrl/pinmux.h b/include/linux/pinctrl/pinmux.h
index a7e370965c53..d6f7b58d6ad0 100644
--- a/include/linux/pinctrl/pinmux.h
+++ b/include/linux/pinctrl/pinmux.h
@@ -57,26 +57,26 @@ struct pinctrl_gpio_range;
  *	the pin request.
  */
 struct pinmux_ops {
-	int (*request) (struct pinctrl_dev *pctldev, unsigned offset);
-	int (*free) (struct pinctrl_dev *pctldev, unsigned offset);
+	int (*request) (struct pinctrl_dev *pctldev, unsigned int offset);
+	int (*free) (struct pinctrl_dev *pctldev, unsigned int offset);
 	int (*get_functions_count) (struct pinctrl_dev *pctldev);
 	const char *(*get_function_name) (struct pinctrl_dev *pctldev,
-					  unsigned selector);
+					  unsigned int selector);
 	int (*get_function_groups) (struct pinctrl_dev *pctldev,
-				  unsigned selector,
-				  const char * const **groups,
-				  unsigned *num_groups);
-	int (*set_mux) (struct pinctrl_dev *pctldev, unsigned func_selector,
-			unsigned group_selector);
+				    unsigned int selector,
+				    const char * const **groups,
+				    unsigned int *num_groups);
+	int (*set_mux) (struct pinctrl_dev *pctldev, unsigned int func_selector,
+			unsigned int group_selector);
 	int (*gpio_request_enable) (struct pinctrl_dev *pctldev,
 				    struct pinctrl_gpio_range *range,
-				    unsigned offset);
+				    unsigned int offset);
 	void (*gpio_disable_free) (struct pinctrl_dev *pctldev,
 				   struct pinctrl_gpio_range *range,
-				   unsigned offset);
+				   unsigned int offset);
 	int (*gpio_set_direction) (struct pinctrl_dev *pctldev,
 				   struct pinctrl_gpio_range *range,
-				   unsigned offset,
+				   unsigned int offset,
 				   bool input);
 	bool strict;
 };
-- 
cgit v1.2.3


From 2202844e4468c7539dba0c0b06577c93735af952 Mon Sep 17 00:00:00 2001
From: Longfang Liu <liulongfang@huawei.com>
Date: Mon, 6 Nov 2023 15:22:23 +0800
Subject: vfio/migration: Add debugfs to live migration driver
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There are multiple devices, software and operational steps involved
in the process of live migration. An error occurred on any node may
cause the live migration operation to fail.
This complex process makes it very difficult to locate and analyze
the cause when the function fails.

In order to quickly locate the cause of the problem when the
live migration fails, I added a set of debugfs to the vfio
live migration driver.

    +-------------------------------------------+
    |                                           |
    |                                           |
    |                  QEMU                     |
    |                                           |
    |                                           |
    +---+----------------------------+----------+
        |      ^                     |      ^
        |      |                     |      |
        |      |                     |      |
        v      |                     v      |
     +---------+--+               +---------+--+
     |src vfio_dev|               |dst vfio_dev|
     +--+---------+               +--+---------+
        |      ^                     |      ^
        |      |                     |      |
        v      |                     |      |
   +-----------+----+           +-----------+----+
   |src dev debugfs |           |dst dev debugfs |
   +----------------+           +----------------+

The entire debugfs directory will be based on the definition of
the CONFIG_DEBUG_FS macro. If this macro is not enabled, the
interfaces in vfio.h will be empty definitions, and the creation
and initialization of the debugfs directory will not be executed.

   vfio
    |
    +---<dev_name1>
    |    +---migration
    |        +--state
    |
    +---<dev_name2>
         +---migration
             +--state

debugfs will create a public root directory "vfio" file.
then create a dev_name() file for each live migration device.
First, create a unified state acquisition file of "migration"
in this device directory.
Then, create a public live migration state lookup file "state".

Signed-off-by: Longfang Liu <liulongfang@huawei.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/r/20231106072225.28577-2-liulongfang@huawei.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/Kconfig      | 10 ++++++
 drivers/vfio/Makefile     |  1 +
 drivers/vfio/debugfs.c    | 92 +++++++++++++++++++++++++++++++++++++++++++++++
 drivers/vfio/vfio.h       | 14 ++++++++
 drivers/vfio/vfio_main.c  |  4 +++
 include/linux/vfio.h      |  7 ++++
 include/uapi/linux/vfio.h |  1 +
 7 files changed, 129 insertions(+)
 create mode 100644 drivers/vfio/debugfs.c

(limited to 'include')

diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig
index 6bda6dbb4878..ceae52fd7586 100644
--- a/drivers/vfio/Kconfig
+++ b/drivers/vfio/Kconfig
@@ -80,6 +80,16 @@ config VFIO_VIRQFD
 	select EVENTFD
 	default n
 
+config VFIO_DEBUGFS
+	bool "Export VFIO internals in DebugFS"
+	depends on DEBUG_FS
+	help
+	  Allows exposure of VFIO device internals. This option enables
+	  the use of debugfs by VFIO drivers as required. The device can
+	  cause the VFIO code create a top-level debug/vfio directory
+	  during initialization, and then populate a subdirectory with
+	  entries as required.
+
 source "drivers/vfio/pci/Kconfig"
 source "drivers/vfio/platform/Kconfig"
 source "drivers/vfio/mdev/Kconfig"
diff --git a/drivers/vfio/Makefile b/drivers/vfio/Makefile
index 68c05705200f..b2fc9fb499d8 100644
--- a/drivers/vfio/Makefile
+++ b/drivers/vfio/Makefile
@@ -7,6 +7,7 @@ vfio-$(CONFIG_VFIO_GROUP) += group.o
 vfio-$(CONFIG_IOMMUFD) += iommufd.o
 vfio-$(CONFIG_VFIO_CONTAINER) += container.o
 vfio-$(CONFIG_VFIO_VIRQFD) += virqfd.o
+vfio-$(CONFIG_VFIO_DEBUGFS) += debugfs.o
 
 obj-$(CONFIG_VFIO_IOMMU_TYPE1) += vfio_iommu_type1.o
 obj-$(CONFIG_VFIO_IOMMU_SPAPR_TCE) += vfio_iommu_spapr_tce.o
diff --git a/drivers/vfio/debugfs.c b/drivers/vfio/debugfs.c
new file mode 100644
index 000000000000..298bd866f157
--- /dev/null
+++ b/drivers/vfio/debugfs.c
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023, HiSilicon Ltd.
+ */
+
+#include <linux/device.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/vfio.h>
+#include "vfio.h"
+
+static struct dentry *vfio_debugfs_root;
+
+static int vfio_device_state_read(struct seq_file *seq, void *data)
+{
+	struct device *vf_dev = seq->private;
+	struct vfio_device *vdev = container_of(vf_dev,
+						struct vfio_device, device);
+	enum vfio_device_mig_state state;
+	int ret;
+
+	BUILD_BUG_ON(VFIO_DEVICE_STATE_NR !=
+		     VFIO_DEVICE_STATE_PRE_COPY_P2P + 1);
+
+	ret = vdev->mig_ops->migration_get_state(vdev, &state);
+	if (ret)
+		return -EINVAL;
+
+	switch (state) {
+	case VFIO_DEVICE_STATE_ERROR:
+		seq_puts(seq, "ERROR\n");
+		break;
+	case VFIO_DEVICE_STATE_STOP:
+		seq_puts(seq, "STOP\n");
+		break;
+	case VFIO_DEVICE_STATE_RUNNING:
+		seq_puts(seq, "RUNNING\n");
+		break;
+	case VFIO_DEVICE_STATE_STOP_COPY:
+		seq_puts(seq, "STOP_COPY\n");
+		break;
+	case VFIO_DEVICE_STATE_RESUMING:
+		seq_puts(seq, "RESUMING\n");
+		break;
+	case VFIO_DEVICE_STATE_RUNNING_P2P:
+		seq_puts(seq, "RUNNING_P2P\n");
+		break;
+	case VFIO_DEVICE_STATE_PRE_COPY:
+		seq_puts(seq, "PRE_COPY\n");
+		break;
+	case VFIO_DEVICE_STATE_PRE_COPY_P2P:
+		seq_puts(seq, "PRE_COPY_P2P\n");
+		break;
+	default:
+		seq_puts(seq, "Invalid\n");
+	}
+
+	return 0;
+}
+
+void vfio_device_debugfs_init(struct vfio_device *vdev)
+{
+	struct device *dev = &vdev->device;
+
+	vdev->debug_root = debugfs_create_dir(dev_name(vdev->dev),
+					      vfio_debugfs_root);
+
+	if (vdev->mig_ops) {
+		struct dentry *vfio_dev_migration = NULL;
+
+		vfio_dev_migration = debugfs_create_dir("migration",
+							vdev->debug_root);
+		debugfs_create_devm_seqfile(dev, "state", vfio_dev_migration,
+					    vfio_device_state_read);
+	}
+}
+
+void vfio_device_debugfs_exit(struct vfio_device *vdev)
+{
+	debugfs_remove_recursive(vdev->debug_root);
+}
+
+void vfio_debugfs_create_root(void)
+{
+	vfio_debugfs_root = debugfs_create_dir("vfio", NULL);
+}
+
+void vfio_debugfs_remove_root(void)
+{
+	debugfs_remove_recursive(vfio_debugfs_root);
+	vfio_debugfs_root = NULL;
+}
diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h
index 307e3f29b527..bde84ad344e5 100644
--- a/drivers/vfio/vfio.h
+++ b/drivers/vfio/vfio.h
@@ -448,4 +448,18 @@ static inline void vfio_device_put_kvm(struct vfio_device *device)
 }
 #endif
 
+#ifdef CONFIG_VFIO_DEBUGFS
+void vfio_debugfs_create_root(void);
+void vfio_debugfs_remove_root(void);
+
+void vfio_device_debugfs_init(struct vfio_device *vdev);
+void vfio_device_debugfs_exit(struct vfio_device *vdev);
+#else
+static inline void vfio_debugfs_create_root(void) { }
+static inline void vfio_debugfs_remove_root(void) { }
+
+static inline void vfio_device_debugfs_init(struct vfio_device *vdev) { }
+static inline void vfio_device_debugfs_exit(struct vfio_device *vdev) { }
+#endif /* CONFIG_VFIO_DEBUGFS */
+
 #endif
diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c
index 8d4995ada74a..1cc93aac99a2 100644
--- a/drivers/vfio/vfio_main.c
+++ b/drivers/vfio/vfio_main.c
@@ -311,6 +311,7 @@ static int __vfio_register_dev(struct vfio_device *device,
 	refcount_set(&device->refcount, 1);
 
 	vfio_device_group_register(device);
+	vfio_device_debugfs_init(device);
 
 	return 0;
 err_out:
@@ -378,6 +379,7 @@ void vfio_unregister_group_dev(struct vfio_device *device)
 		}
 	}
 
+	vfio_device_debugfs_exit(device);
 	/* Balances vfio_device_set_group in register path */
 	vfio_device_remove_group(device);
 }
@@ -1676,6 +1678,7 @@ static int __init vfio_init(void)
 	if (ret)
 		goto err_alloc_dev_chrdev;
 
+	vfio_debugfs_create_root();
 	pr_info(DRIVER_DESC " version: " DRIVER_VERSION "\n");
 	return 0;
 
@@ -1691,6 +1694,7 @@ err_virqfd:
 
 static void __exit vfio_cleanup(void)
 {
+	vfio_debugfs_remove_root();
 	ida_destroy(&vfio.device_ida);
 	vfio_cdev_cleanup();
 	class_destroy(vfio.device_class);
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index a65b2513f8cd..89b265bc6ec3 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -69,6 +69,13 @@ struct vfio_device {
 	u8 iommufd_attached:1;
 #endif
 	u8 cdev_opened:1;
+#ifdef CONFIG_DEBUG_FS
+	/*
+	 * debug_root is a static property of the vfio_device
+	 * which must be set prior to registering the vfio_device.
+	 */
+	struct dentry *debug_root;
+#endif
 };
 
 /**
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 7f5fb010226d..2b68e6cdf190 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -1219,6 +1219,7 @@ enum vfio_device_mig_state {
 	VFIO_DEVICE_STATE_RUNNING_P2P = 5,
 	VFIO_DEVICE_STATE_PRE_COPY = 6,
 	VFIO_DEVICE_STATE_PRE_COPY_P2P = 7,
+	VFIO_DEVICE_STATE_NR,
 };
 
 /**
-- 
cgit v1.2.3


From 6c4df324d78ceb6a3ebb0d42243d131a424c85c3 Mon Sep 17 00:00:00 2001
From: Baofeng Tian <baofeng.tian@intel.com>
Date: Mon, 4 Dec 2023 15:47:11 -0600
Subject: ASoC: SOF: align topology header file with sof topology header

Add missed definition and align variable names with sof topology
header file.

Signed-off-by: Baofeng Tian <baofeng.tian@intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Link: https://lore.kernel.org/r/20231204214713.208951-3-pierre-louis.bossart@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/sof/topology.h | 25 ++++++++++++++++---------
 1 file changed, 16 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/sound/sof/topology.h b/include/sound/sof/topology.h
index 906e2f327ad2..466ab8e73d98 100644
--- a/include/sound/sof/topology.h
+++ b/include/sound/sof/topology.h
@@ -39,6 +39,7 @@ enum sof_comp_type {
 	SOF_COMP_ASRC,		/**< Asynchronous sample rate converter */
 	SOF_COMP_DCBLOCK,
 	SOF_COMP_SMART_AMP,             /**< smart amplifier component */
+	SOF_COMP_MODULE_ADAPTER,		/**< module adapter */
 	/* keep FILEREAD/FILEWRITE as the last ones */
 	SOF_COMP_FILEREAD = 10000,	/**< host test based file IO */
 	SOF_COMP_FILEWRITE = 10001,	/**< host test based file IO */
@@ -68,14 +69,15 @@ struct sof_ipc_comp {
 /*
  * SOF memory capabilities, add new ones at the end
  */
-#define SOF_MEM_CAPS_RAM			(1 << 0)
-#define SOF_MEM_CAPS_ROM			(1 << 1)
-#define SOF_MEM_CAPS_EXT			(1 << 2) /**< external */
-#define SOF_MEM_CAPS_LP			(1 << 3) /**< low power */
-#define SOF_MEM_CAPS_HP			(1 << 4) /**< high performance */
-#define SOF_MEM_CAPS_DMA			(1 << 5) /**< DMA'able */
-#define SOF_MEM_CAPS_CACHE			(1 << 6) /**< cacheable */
-#define SOF_MEM_CAPS_EXEC			(1 << 7) /**< executable */
+#define SOF_MEM_CAPS_RAM		BIT(0)
+#define SOF_MEM_CAPS_ROM		BIT(1)
+#define SOF_MEM_CAPS_EXT		BIT(2) /**< external */
+#define SOF_MEM_CAPS_LP			BIT(3) /**< low power */
+#define SOF_MEM_CAPS_HP			BIT(4) /**< high performance */
+#define SOF_MEM_CAPS_DMA		BIT(5) /**< DMA'able */
+#define SOF_MEM_CAPS_CACHE		BIT(6) /**< cacheable */
+#define SOF_MEM_CAPS_EXEC		BIT(7) /**< executable */
+#define SOF_MEM_CAPS_L3			BIT(8) /**< L3 memory */
 
 /*
  * overrun will cause ring buffer overwrite, instead of XRUN.
@@ -87,6 +89,9 @@ struct sof_ipc_comp {
  */
 #define SOF_BUF_UNDERRUN_PERMITTED	BIT(1)
 
+/* the UUID size in bytes, shared between FW and host */
+#define SOF_UUID_SIZE	16
+
 /* create new component buffer - SOF_IPC_TPLG_BUFFER_NEW */
 struct sof_ipc_buffer {
 	struct sof_ipc_comp comp;
@@ -140,6 +145,8 @@ enum sof_volume_ramp {
 	SOF_VOLUME_LOG,
 	SOF_VOLUME_LINEAR_ZC,
 	SOF_VOLUME_LOG_ZC,
+	SOF_VOLUME_WINDOWS_FADE,
+	SOF_VOLUME_WINDOWS_NO_FADE,
 };
 
 /* generic volume component */
@@ -234,7 +241,7 @@ struct sof_ipc_comp_process {
 	/* reserved for future use */
 	uint32_t reserved[7];
 
-	uint8_t data[];
+	unsigned char data[];
 } __packed;
 
 /* frees components, buffers and pipelines
-- 
cgit v1.2.3


From 8ec56af3da4dad008ab10115eb4cec34836afc04 Mon Sep 17 00:00:00 2001
From: Baofeng Tian <baofeng.tian@intel.com>
Date: Mon, 4 Dec 2023 15:47:12 -0600
Subject: ASoC: SOF: add alignment for topology header file struct definition

sof header file requires these struct with 4 byte aligned, so
add same alignment in sof driver definition.

Signed-off-by: Baofeng Tian <baofeng.tian@intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Link: https://lore.kernel.org/r/20231204214713.208951-4-pierre-louis.bossart@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/sof/topology.h | 36 ++++++++++++++++++------------------
 1 file changed, 18 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/sound/sof/topology.h b/include/sound/sof/topology.h
index 466ab8e73d98..b3ca886fa28f 100644
--- a/include/sound/sof/topology.h
+++ b/include/sound/sof/topology.h
@@ -60,7 +60,7 @@ struct sof_ipc_comp {
 
 	/* extended data length, 0 if no extended data */
 	uint32_t ext_data_length;
-} __packed;
+} __packed __aligned(4);
 
 /*
  * Component Buffers
@@ -99,7 +99,7 @@ struct sof_ipc_buffer {
 	uint32_t caps;		/**< SOF_MEM_CAPS_ */
 	uint32_t flags;		/**< SOF_BUF_ flags defined above */
 	uint32_t reserved;	/**< reserved for future use */
-} __packed;
+} __packed __aligned(4);
 
 /* generic component config data - must always be after struct sof_ipc_comp */
 struct sof_ipc_comp_config {
@@ -112,7 +112,7 @@ struct sof_ipc_comp_config {
 
 	/* reserved for future use */
 	uint32_t reserved[2];
-} __packed;
+} __packed __aligned(4);
 
 /* generic host component */
 struct sof_ipc_comp_host {
@@ -121,7 +121,7 @@ struct sof_ipc_comp_host {
 	uint32_t direction;	/**< SOF_IPC_STREAM_ */
 	uint32_t no_irq;	/**< don't send periodic IRQ to host/DSP */
 	uint32_t dmac_config; /**< DMA engine specific */
-}  __packed;
+} __packed __aligned(4);
 
 /* generic DAI component */
 struct sof_ipc_comp_dai {
@@ -131,13 +131,13 @@ struct sof_ipc_comp_dai {
 	uint32_t dai_index;	/**< index of this type dai */
 	uint32_t type;		/**< DAI type - SOF_DAI_ */
 	uint32_t reserved;	/**< reserved */
-}  __packed;
+} __packed __aligned(4);
 
 /* generic mixer component */
 struct sof_ipc_comp_mixer {
 	struct sof_ipc_comp comp;
 	struct sof_ipc_comp_config config;
-}  __packed;
+} __packed __aligned(4);
 
 /* volume ramping types */
 enum sof_volume_ramp {
@@ -158,7 +158,7 @@ struct sof_ipc_comp_volume {
 	uint32_t max_value;
 	uint32_t ramp;		/**< SOF_VOLUME_ */
 	uint32_t initial_ramp;	/**< ramp space in ms */
-}  __packed;
+} __packed __aligned(4);
 
 /* generic SRC component */
 struct sof_ipc_comp_src {
@@ -168,7 +168,7 @@ struct sof_ipc_comp_src {
 	uint32_t source_rate;	/**< source rate or 0 for variable */
 	uint32_t sink_rate;	/**< sink rate or 0 for variable */
 	uint32_t rate_mask;	/**< SOF_RATE_ supported rates */
-} __packed;
+} __packed __aligned(4);
 
 /* generic ASRC component */
 struct sof_ipc_comp_asrc {
@@ -194,13 +194,13 @@ struct sof_ipc_comp_asrc {
 
 	/* reserved for future use */
 	uint32_t reserved[4];
-} __attribute__((packed));
+} __packed __aligned(4);
 
 /* generic MUX component */
 struct sof_ipc_comp_mux {
 	struct sof_ipc_comp comp;
 	struct sof_ipc_comp_config config;
-} __packed;
+} __packed __aligned(4);
 
 /* generic tone generator component */
 struct sof_ipc_comp_tone {
@@ -215,7 +215,7 @@ struct sof_ipc_comp_tone {
 	int32_t period;
 	int32_t repeats;
 	int32_t ramp_step;
-} __packed;
+} __packed __aligned(4);
 
 /** \brief Types of processing components */
 enum sof_ipc_process_type {
@@ -242,7 +242,7 @@ struct sof_ipc_comp_process {
 	uint32_t reserved[7];
 
 	unsigned char data[];
-} __packed;
+} __packed __aligned(4);
 
 /* frees components, buffers and pipelines
  * SOF_IPC_TPLG_COMP_FREE, SOF_IPC_TPLG_PIPE_FREE, SOF_IPC_TPLG_BUFFER_FREE
@@ -250,13 +250,13 @@ struct sof_ipc_comp_process {
 struct sof_ipc_free {
 	struct sof_ipc_cmd_hdr hdr;
 	uint32_t id;
-} __packed;
+} __packed __aligned(4);
 
 struct sof_ipc_comp_reply {
 	struct sof_ipc_reply rhdr;
 	uint32_t id;
 	uint32_t offset;
-} __packed;
+} __packed __aligned(4);
 
 /*
  * Pipeline
@@ -281,25 +281,25 @@ struct sof_ipc_pipe_new {
 	uint32_t frames_per_sched;/**< output frames of pipeline, 0 is variable */
 	uint32_t xrun_limit_usecs; /**< report xruns greater than limit */
 	uint32_t time_domain;	/**< scheduling time domain */
-}  __packed;
+} __packed __aligned(4);
 
 /* pipeline construction complete - SOF_IPC_TPLG_PIPE_COMPLETE */
 struct sof_ipc_pipe_ready {
 	struct sof_ipc_cmd_hdr hdr;
 	uint32_t comp_id;
-}  __packed;
+} __packed __aligned(4);
 
 struct sof_ipc_pipe_free {
 	struct sof_ipc_cmd_hdr hdr;
 	uint32_t comp_id;
-}  __packed;
+} __packed __aligned(4);
 
 /* connect two components in pipeline - SOF_IPC_TPLG_COMP_CONNECT */
 struct sof_ipc_pipe_comp_connect {
 	struct sof_ipc_cmd_hdr hdr;
 	uint32_t source_id;
 	uint32_t sink_id;
-}  __packed;
+} __packed __aligned(4);
 
 /* external events */
 enum sof_event_types {
-- 
cgit v1.2.3


From ebd12b2ca6145550a7e42cd2320870db02dd0f3c Mon Sep 17 00:00:00 2001
From: Curtis Malainey <cujomalainey@chromium.org>
Date: Mon, 4 Dec 2023 15:47:13 -0600
Subject: ASoC: SOF: Wire up buffer flags

Buffer flags have been in firmware for ages but were never fully
implemented in the topology/kernel system. This commit finishes off the
implementation.

Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Signed-off-by: Curtis Malainey <cujomalainey@chromium.org>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Link: https://lore.kernel.org/r/20231204214713.208951-5-pierre-louis.bossart@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/uapi/sound/sof/tokens.h | 1 +
 sound/soc/sof/ipc3-topology.c   | 2 ++
 2 files changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/uapi/sound/sof/tokens.h b/include/uapi/sound/sof/tokens.h
index 0fb39780f9bd..ee5708934614 100644
--- a/include/uapi/sound/sof/tokens.h
+++ b/include/uapi/sound/sof/tokens.h
@@ -35,6 +35,7 @@
 /* buffers */
 #define SOF_TKN_BUF_SIZE			100
 #define SOF_TKN_BUF_CAPS			101
+#define SOF_TKN_BUF_FLAGS			102
 
 /* DAI */
 /* Token retired with ABI 3.2, do not use for new capabilities
diff --git a/sound/soc/sof/ipc3-topology.c b/sound/soc/sof/ipc3-topology.c
index 7a4932c152a9..a8e0054cb8a6 100644
--- a/sound/soc/sof/ipc3-topology.c
+++ b/sound/soc/sof/ipc3-topology.c
@@ -72,6 +72,8 @@ static const struct sof_topology_token buffer_tokens[] = {
 		offsetof(struct sof_ipc_buffer, size)},
 	{SOF_TKN_BUF_CAPS, SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32,
 		offsetof(struct sof_ipc_buffer, caps)},
+	{SOF_TKN_BUF_FLAGS, SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32,
+		offsetof(struct sof_ipc_buffer, flags)},
 };
 
 /* DAI */
-- 
cgit v1.2.3


From 91051f003948432f83b5d2766eeb83b2b4993649 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Fri, 1 Dec 2023 15:49:52 +0100
Subject: tcp: Dump bound-only sockets in inet_diag.

Walk the hashinfo->bhash2 table so that inet_diag can dump TCP sockets
that are bound but haven't yet called connect() or listen().

The code is inspired by the ->lhash2 loop. However there's no manual
test of the source port, since this kind of filtering is already
handled by inet_diag_bc_sk(). Also, a maximum of 16 sockets are dumped
at a time, to avoid running with bh disabled for too long.

There's no TCP state for bound but otherwise inactive sockets. Such
sockets normally map to TCP_CLOSE. However, "ss -l", which is supposed
to only dump listening sockets, actually requests the kernel to dump
sockets in either the TCP_LISTEN or TCP_CLOSE states. To avoid dumping
bound-only sockets with "ss -l", we therefore need to define a new
pseudo-state (TCP_BOUND_INACTIVE) that user space will be able to set
explicitly.

With an IPv4, an IPv6 and an IPv6-only socket, bound respectively to
40000, 64000, 60000, an updated version of iproute2 could work as
follow:

  $ ss -t state bound-inactive
  Recv-Q   Send-Q     Local Address:Port       Peer Address:Port   Process
  0        0                0.0.0.0:40000           0.0.0.0:*
  0        0                   [::]:60000              [::]:*
  0        0                      *:64000                 *:*

Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/b3a84ae61e19c06806eea9c602b3b66e8f0cfc81.1701362867.git.gnault@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/tcp_states.h |  2 ++
 include/uapi/linux/bpf.h |  1 +
 net/ipv4/inet_diag.c     | 86 +++++++++++++++++++++++++++++++++++++++++++++++-
 net/ipv4/tcp.c           |  1 +
 4 files changed, 89 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/tcp_states.h b/include/net/tcp_states.h
index cc00118acca1..d60e8148ff4c 100644
--- a/include/net/tcp_states.h
+++ b/include/net/tcp_states.h
@@ -22,6 +22,7 @@ enum {
 	TCP_LISTEN,
 	TCP_CLOSING,	/* Now a valid state */
 	TCP_NEW_SYN_RECV,
+	TCP_BOUND_INACTIVE, /* Pseudo-state for inet_diag */
 
 	TCP_MAX_STATES	/* Leave at the end! */
 };
@@ -43,6 +44,7 @@ enum {
 	TCPF_LISTEN	 = (1 << TCP_LISTEN),
 	TCPF_CLOSING	 = (1 << TCP_CLOSING),
 	TCPF_NEW_SYN_RECV = (1 << TCP_NEW_SYN_RECV),
+	TCPF_BOUND_INACTIVE = (1 << TCP_BOUND_INACTIVE),
 };
 
 #endif	/* _LINUX_TCP_STATES_H */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index e88746ba7d21..b1e8c5bdfc82 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -6902,6 +6902,7 @@ enum {
 	BPF_TCP_LISTEN,
 	BPF_TCP_CLOSING,	/* Now a valid state */
 	BPF_TCP_NEW_SYN_RECV,
+	BPF_TCP_BOUND_INACTIVE,
 
 	BPF_TCP_MAX_STATES	/* Leave at the end! */
 };
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 7d0e7aaa71e0..46b13962ad02 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -1077,10 +1077,94 @@ skip_listen_ht:
 		s_i = num = s_num = 0;
 	}
 
+/* Process a maximum of SKARR_SZ sockets at a time when walking hash buckets
+ * with bh disabled.
+ */
+#define SKARR_SZ 16
+
+	/* Dump bound but inactive (not listening, connecting, etc.) sockets */
+	if (cb->args[0] == 1) {
+		if (!(idiag_states & TCPF_BOUND_INACTIVE))
+			goto skip_bind_ht;
+
+		for (i = s_i; i < hashinfo->bhash_size; i++) {
+			struct inet_bind_hashbucket *ibb;
+			struct inet_bind2_bucket *tb2;
+			struct sock *sk_arr[SKARR_SZ];
+			int num_arr[SKARR_SZ];
+			int idx, accum, res;
+
+resume_bind_walk:
+			num = 0;
+			accum = 0;
+			ibb = &hashinfo->bhash2[i];
+
+			spin_lock_bh(&ibb->lock);
+			inet_bind_bucket_for_each(tb2, &ibb->chain) {
+				if (!net_eq(ib2_net(tb2), net))
+					continue;
+
+				sk_for_each_bound_bhash2(sk, &tb2->owners) {
+					struct inet_sock *inet = inet_sk(sk);
+
+					if (num < s_num)
+						goto next_bind;
+
+					if (sk->sk_state != TCP_CLOSE ||
+					    !inet->inet_num)
+						goto next_bind;
+
+					if (r->sdiag_family != AF_UNSPEC &&
+					    r->sdiag_family != sk->sk_family)
+						goto next_bind;
+
+					if (!inet_diag_bc_sk(bc, sk))
+						goto next_bind;
+
+					sock_hold(sk);
+					num_arr[accum] = num;
+					sk_arr[accum] = sk;
+					if (++accum == SKARR_SZ)
+						goto pause_bind_walk;
+next_bind:
+					num++;
+				}
+			}
+pause_bind_walk:
+			spin_unlock_bh(&ibb->lock);
+
+			res = 0;
+			for (idx = 0; idx < accum; idx++) {
+				if (res >= 0) {
+					res = inet_sk_diag_fill(sk_arr[idx],
+								NULL, skb, cb,
+								r, NLM_F_MULTI,
+								net_admin);
+					if (res < 0)
+						num = num_arr[idx];
+				}
+				sock_put(sk_arr[idx]);
+			}
+			if (res < 0)
+				goto done;
+
+			cond_resched();
+
+			if (accum == SKARR_SZ) {
+				s_num = num + 1;
+				goto resume_bind_walk;
+			}
+
+			s_num = 0;
+		}
+skip_bind_ht:
+		cb->args[0] = 2;
+		s_i = num = s_num = 0;
+	}
+
 	if (!(idiag_states & ~TCPF_LISTEN))
 		goto out;
 
-#define SKARR_SZ 16
 	for (i = s_i; i <= hashinfo->ehash_mask; i++) {
 		struct inet_ehash_bucket *head = &hashinfo->ehash[i];
 		spinlock_t *lock = inet_ehash_lockp(hashinfo, i);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 53bcc17c91e4..a100df07d34a 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2605,6 +2605,7 @@ void tcp_set_state(struct sock *sk, int state)
 	BUILD_BUG_ON((int)BPF_TCP_LISTEN != (int)TCP_LISTEN);
 	BUILD_BUG_ON((int)BPF_TCP_CLOSING != (int)TCP_CLOSING);
 	BUILD_BUG_ON((int)BPF_TCP_NEW_SYN_RECV != (int)TCP_NEW_SYN_RECV);
+	BUILD_BUG_ON((int)BPF_TCP_BOUND_INACTIVE != (int)TCP_BOUND_INACTIVE);
 	BUILD_BUG_ON((int)BPF_TCP_MAX_STATES != (int)TCP_MAX_STATES);
 
 	/* bpf uapi header bpf.h defines an anonymous enum with values
-- 
cgit v1.2.3


From 4fbc3a52cd4d14de3793f4b2c721d7306ea84cf9 Mon Sep 17 00:00:00 2001
From: Mike Marciniszyn <mike.marciniszyn@intel.com>
Date: Wed, 29 Nov 2023 14:21:41 -0600
Subject: RDMA/core: Fix umem iterator when PAGE_SIZE is greater then HCA pgsz

64k pages introduce the situation in this diagram when the HCA 4k page
size is being used:

 +-------------------------------------------+ <--- 64k aligned VA
 |                                           |
 |              HCA 4k page                  |
 |                                           |
 +-------------------------------------------+
 |                   o                       |
 |                                           |
 |                   o                       |
 |                                           |
 |                   o                       |
 +-------------------------------------------+
 |                                           |
 |              HCA 4k page                  |
 |                                           |
 +-------------------------------------------+ <--- Live HCA page
 |OOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOO| <--- offset
 |                                           | <--- VA
 |                MR data                    |
 +-------------------------------------------+
 |                                           |
 |              HCA 4k page                  |
 |                                           |
 +-------------------------------------------+
 |                   o                       |
 |                                           |
 |                   o                       |
 |                                           |
 |                   o                       |
 +-------------------------------------------+
 |                                           |
 |              HCA 4k page                  |
 |                                           |
 +-------------------------------------------+

The VA addresses are coming from rdma-core in this diagram can be
arbitrary, but for 64k pages, the VA may be offset by some number of HCA
4k pages and followed by some number of HCA 4k pages.

The current iterator doesn't account for either the preceding 4k pages or
the following 4k pages.

Fix the issue by extending the ib_block_iter to contain the number of DMA
pages like comment [1] says and by using __sg_advance to start the
iterator at the first live HCA page.

The changes are contained in a parallel set of iterator start and next
functions that are umem aware and specific to umem since there is one user
of the rdma_for_each_block() without umem.

These two fixes prevents the extra pages before and after the user MR
data.

Fix the preceding pages by using the __sq_advance field to start at the
first 4k page containing MR data.

Fix the following pages by saving the number of pgsz blocks in the
iterator state and downcounting on each next.

This fix allows for the elimination of the small page crutch noted in the
Fixes.

Fixes: 10c75ccb54e4 ("RDMA/umem: Prevent small pages from being returned by ib_umem_find_best_pgsz()")
Link: https://lore.kernel.org/r/20231129202143.1434-2-shiraz.saleem@intel.com
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/core/umem.c | 6 ------
 include/rdma/ib_umem.h         | 9 ++++++++-
 include/rdma/ib_verbs.h        | 1 +
 3 files changed, 9 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index f9ab671c8eda..07c571c7b699 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -96,12 +96,6 @@ unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem,
 		return page_size;
 	}
 
-	/* rdma_for_each_block() has a bug if the page size is smaller than the
-	 * page size used to build the umem. For now prevent smaller page sizes
-	 * from being returned.
-	 */
-	pgsz_bitmap &= GENMASK(BITS_PER_LONG - 1, PAGE_SHIFT);
-
 	/* The best result is the smallest page size that results in the minimum
 	 * number of required pages. Compute the largest page size that could
 	 * work based on VA address bits that don't change.
diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h
index 95896472a82b..565a85044541 100644
--- a/include/rdma/ib_umem.h
+++ b/include/rdma/ib_umem.h
@@ -77,6 +77,13 @@ static inline void __rdma_umem_block_iter_start(struct ib_block_iter *biter,
 {
 	__rdma_block_iter_start(biter, umem->sgt_append.sgt.sgl,
 				umem->sgt_append.sgt.nents, pgsz);
+	biter->__sg_advance = ib_umem_offset(umem) & ~(pgsz - 1);
+	biter->__sg_numblocks = ib_umem_num_dma_blocks(umem, pgsz);
+}
+
+static inline bool __rdma_umem_block_iter_next(struct ib_block_iter *biter)
+{
+	return __rdma_block_iter_next(biter) && biter->__sg_numblocks--;
 }
 
 /**
@@ -92,7 +99,7 @@ static inline void __rdma_umem_block_iter_start(struct ib_block_iter *biter,
  */
 #define rdma_umem_for_each_dma_block(umem, biter, pgsz)                        \
 	for (__rdma_umem_block_iter_start(biter, umem, pgsz);                  \
-	     __rdma_block_iter_next(biter);)
+	     __rdma_umem_block_iter_next(biter);)
 
 #ifdef CONFIG_INFINIBAND_USER_MEM
 
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index fb1a2d6b1969..b7b6b58dd348 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2850,6 +2850,7 @@ struct ib_block_iter {
 	/* internal states */
 	struct scatterlist *__sg;	/* sg holding the current aligned block */
 	dma_addr_t __dma_addr;		/* unaligned DMA address of this block */
+	size_t __sg_numblocks;		/* ib_umem_num_dma_blocks() */
 	unsigned int __sg_nents;	/* number of SG entries */
 	unsigned int __sg_advance;	/* number of bytes to advance in sg in next step */
 	unsigned int __pg_bit;		/* alignment of current block */
-- 
cgit v1.2.3


From 20c20bd11a0702ce4dc9300c3da58acf551d9725 Mon Sep 17 00:00:00 2001
From: Hou Tao <houtao1@huawei.com>
Date: Mon, 4 Dec 2023 22:04:20 +0800
Subject: bpf: Add map and need_defer parameters to .map_fd_put_ptr()

map is the pointer of outer map, and need_defer needs some explanation.
need_defer tells the implementation to defer the reference release of
the passed element and ensure that the element is still alive before
the bpf program, which may manipulate it, exits.

The following three cases will invoke map_fd_put_ptr() and different
need_defer values will be passed to these callers:

1) release the reference of the old element in the map during map update
   or map deletion. The release must be deferred, otherwise the bpf
   program may incur use-after-free problem, so need_defer needs to be
   true.
2) release the reference of the to-be-added element in the error path of
   map update. The to-be-added element is not visible to any bpf
   program, so it is OK to pass false for need_defer parameter.
3) release the references of all elements in the map during map release.
   Any bpf program which has access to the map must have been exited and
   released, so need_defer=false will be OK.

These two parameters will be used by the following patches to fix the
potential use-after-free problem for map-in-map.

Signed-off-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/r/20231204140425.1480317-3-houtao@huaweicloud.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h     |  6 +++++-
 kernel/bpf/arraymap.c   | 12 +++++++-----
 kernel/bpf/hashtab.c    |  6 +++---
 kernel/bpf/map_in_map.c |  2 +-
 kernel/bpf/map_in_map.h |  2 +-
 5 files changed, 17 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index eb447b0a9423..d273348cfb2f 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -106,7 +106,11 @@ struct bpf_map_ops {
 	/* funcs called by prog_array and perf_event_array map */
 	void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file,
 				int fd);
-	void (*map_fd_put_ptr)(void *ptr);
+	/* If need_defer is true, the implementation should guarantee that
+	 * the to-be-put element is still alive before the bpf program, which
+	 * may manipulate it, exists.
+	 */
+	void (*map_fd_put_ptr)(struct bpf_map *map, void *ptr, bool need_defer);
 	int (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf);
 	u32 (*map_fd_sys_lookup_elem)(void *ptr);
 	void (*map_seq_show_elem)(struct bpf_map *map, void *key,
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 2058e89b5ddd..f9aed5909d6e 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -867,7 +867,7 @@ int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file,
 	}
 
 	if (old_ptr)
-		map->ops->map_fd_put_ptr(old_ptr);
+		map->ops->map_fd_put_ptr(map, old_ptr, true);
 	return 0;
 }
 
@@ -890,7 +890,7 @@ static long fd_array_map_delete_elem(struct bpf_map *map, void *key)
 	}
 
 	if (old_ptr) {
-		map->ops->map_fd_put_ptr(old_ptr);
+		map->ops->map_fd_put_ptr(map, old_ptr, true);
 		return 0;
 	} else {
 		return -ENOENT;
@@ -913,8 +913,9 @@ static void *prog_fd_array_get_ptr(struct bpf_map *map,
 	return prog;
 }
 
-static void prog_fd_array_put_ptr(void *ptr)
+static void prog_fd_array_put_ptr(struct bpf_map *map, void *ptr, bool need_defer)
 {
+	/* bpf_prog is freed after one RCU or tasks trace grace period */
 	bpf_prog_put(ptr);
 }
 
@@ -1239,8 +1240,9 @@ err_out:
 	return ee;
 }
 
-static void perf_event_fd_array_put_ptr(void *ptr)
+static void perf_event_fd_array_put_ptr(struct bpf_map *map, void *ptr, bool need_defer)
 {
+	/* bpf_perf_event is freed after one RCU grace period */
 	bpf_event_entry_free_rcu(ptr);
 }
 
@@ -1294,7 +1296,7 @@ static void *cgroup_fd_array_get_ptr(struct bpf_map *map,
 	return cgroup_get_from_fd(fd);
 }
 
-static void cgroup_fd_array_put_ptr(void *ptr)
+static void cgroup_fd_array_put_ptr(struct bpf_map *map, void *ptr, bool need_defer)
 {
 	/* cgroup_put free cgrp after a rcu grace period */
 	cgroup_put(ptr);
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index fd8d4b0addfc..5b9146fa825f 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -897,7 +897,7 @@ static void htab_put_fd_value(struct bpf_htab *htab, struct htab_elem *l)
 
 	if (map->ops->map_fd_put_ptr) {
 		ptr = fd_htab_map_get_ptr(map, l);
-		map->ops->map_fd_put_ptr(ptr);
+		map->ops->map_fd_put_ptr(map, ptr, true);
 	}
 }
 
@@ -2484,7 +2484,7 @@ static void fd_htab_map_free(struct bpf_map *map)
 		hlist_nulls_for_each_entry_safe(l, n, head, hash_node) {
 			void *ptr = fd_htab_map_get_ptr(map, l);
 
-			map->ops->map_fd_put_ptr(ptr);
+			map->ops->map_fd_put_ptr(map, ptr, false);
 		}
 	}
 
@@ -2525,7 +2525,7 @@ int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file,
 
 	ret = htab_map_update_elem(map, key, &ptr, map_flags);
 	if (ret)
-		map->ops->map_fd_put_ptr(ptr);
+		map->ops->map_fd_put_ptr(map, ptr, false);
 
 	return ret;
 }
diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c
index cd5eafaba97e..2dfeb5835e16 100644
--- a/kernel/bpf/map_in_map.c
+++ b/kernel/bpf/map_in_map.c
@@ -127,7 +127,7 @@ void *bpf_map_fd_get_ptr(struct bpf_map *map,
 	return inner_map;
 }
 
-void bpf_map_fd_put_ptr(void *ptr)
+void bpf_map_fd_put_ptr(struct bpf_map *map, void *ptr, bool need_defer)
 {
 	/* ptr->ops->map_free() has to go through one
 	 * rcu grace period by itself.
diff --git a/kernel/bpf/map_in_map.h b/kernel/bpf/map_in_map.h
index bcb7534afb3c..7d61602354de 100644
--- a/kernel/bpf/map_in_map.h
+++ b/kernel/bpf/map_in_map.h
@@ -13,7 +13,7 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd);
 void bpf_map_meta_free(struct bpf_map *map_meta);
 void *bpf_map_fd_get_ptr(struct bpf_map *map, struct file *map_file,
 			 int ufd);
-void bpf_map_fd_put_ptr(void *ptr);
+void bpf_map_fd_put_ptr(struct bpf_map *map, void *ptr, bool need_defer);
 u32 bpf_map_fd_sys_lookup_elem(void *ptr);
 
 #endif
-- 
cgit v1.2.3


From 876673364161da50eed6b472d746ef88242b2368 Mon Sep 17 00:00:00 2001
From: Hou Tao <houtao1@huawei.com>
Date: Mon, 4 Dec 2023 22:04:22 +0800
Subject: bpf: Defer the free of inner map when necessary

When updating or deleting an inner map in map array or map htab, the map
may still be accessed by non-sleepable program or sleepable program.
However bpf_map_fd_put_ptr() decreases the ref-counter of the inner map
directly through bpf_map_put(), if the ref-counter is the last one
(which is true for most cases), the inner map will be freed by
ops->map_free() in a kworker. But for now, most .map_free() callbacks
don't use synchronize_rcu() or its variants to wait for the elapse of a
RCU grace period, so after the invocation of ops->map_free completes,
the bpf program which is accessing the inner map may incur
use-after-free problem.

Fix the free of inner map by invoking bpf_map_free_deferred() after both
one RCU grace period and one tasks trace RCU grace period if the inner
map has been removed from the outer map before. The deferment is
accomplished by using call_rcu() or call_rcu_tasks_trace() when
releasing the last ref-counter of bpf map. The newly-added rcu_head
field in bpf_map shares the same storage space with work field to
reduce the size of bpf_map.

Fixes: bba1dc0b55ac ("bpf: Remove redundant synchronize_rcu.")
Fixes: 638e4b825d52 ("bpf: Allows per-cpu maps and map-in-map in sleepable programs")
Signed-off-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/r/20231204140425.1480317-5-houtao@huaweicloud.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h     |  7 ++++++-
 kernel/bpf/map_in_map.c | 11 ++++++++---
 kernel/bpf/syscall.c    | 32 +++++++++++++++++++++++++++-----
 3 files changed, 41 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index d273348cfb2f..de3bd03cbeea 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -276,7 +276,11 @@ struct bpf_map {
 	 */
 	atomic64_t refcnt ____cacheline_aligned;
 	atomic64_t usercnt;
-	struct work_struct work;
+	/* rcu is used before freeing and work is only used during freeing */
+	union {
+		struct work_struct work;
+		struct rcu_head rcu;
+	};
 	struct mutex freeze_mutex;
 	atomic64_t writecnt;
 	/* 'Ownership' of program-containing map is claimed by the first program
@@ -292,6 +296,7 @@ struct bpf_map {
 	} owner;
 	bool bypass_spec_v1;
 	bool frozen; /* write-once; write-protected by freeze_mutex */
+	bool free_after_mult_rcu_gp;
 	s64 __percpu *elem_count;
 };
 
diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c
index 2dfeb5835e16..3248ff5d8161 100644
--- a/kernel/bpf/map_in_map.c
+++ b/kernel/bpf/map_in_map.c
@@ -129,10 +129,15 @@ void *bpf_map_fd_get_ptr(struct bpf_map *map,
 
 void bpf_map_fd_put_ptr(struct bpf_map *map, void *ptr, bool need_defer)
 {
-	/* ptr->ops->map_free() has to go through one
-	 * rcu grace period by itself.
+	struct bpf_map *inner_map = ptr;
+
+	/* The inner map may still be used by both non-sleepable and sleepable
+	 * bpf program, so free it after one RCU grace period and one tasks
+	 * trace RCU grace period.
 	 */
-	bpf_map_put(ptr);
+	if (need_defer)
+		WRITE_ONCE(inner_map->free_after_mult_rcu_gp, true);
+	bpf_map_put(inner_map);
 }
 
 u32 bpf_map_fd_sys_lookup_elem(void *ptr)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 5e43ddd1b83f..dd515f6b9741 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -719,6 +719,28 @@ static void bpf_map_put_uref(struct bpf_map *map)
 	}
 }
 
+static void bpf_map_free_in_work(struct bpf_map *map)
+{
+	INIT_WORK(&map->work, bpf_map_free_deferred);
+	/* Avoid spawning kworkers, since they all might contend
+	 * for the same mutex like slab_mutex.
+	 */
+	queue_work(system_unbound_wq, &map->work);
+}
+
+static void bpf_map_free_rcu_gp(struct rcu_head *rcu)
+{
+	bpf_map_free_in_work(container_of(rcu, struct bpf_map, rcu));
+}
+
+static void bpf_map_free_mult_rcu_gp(struct rcu_head *rcu)
+{
+	if (rcu_trace_implies_rcu_gp())
+		bpf_map_free_rcu_gp(rcu);
+	else
+		call_rcu(rcu, bpf_map_free_rcu_gp);
+}
+
 /* decrement map refcnt and schedule it for freeing via workqueue
  * (underlying map implementation ops->map_free() might sleep)
  */
@@ -728,11 +750,11 @@ void bpf_map_put(struct bpf_map *map)
 		/* bpf_map_free_id() must be called first */
 		bpf_map_free_id(map);
 		btf_put(map->btf);
-		INIT_WORK(&map->work, bpf_map_free_deferred);
-		/* Avoid spawning kworkers, since they all might contend
-		 * for the same mutex like slab_mutex.
-		 */
-		queue_work(system_unbound_wq, &map->work);
+
+		if (READ_ONCE(map->free_after_mult_rcu_gp))
+			call_rcu_tasks_trace(&map->rcu, bpf_map_free_mult_rcu_gp);
+		else
+			bpf_map_free_in_work(map);
 	}
 }
 EXPORT_SYMBOL_GPL(bpf_map_put);
-- 
cgit v1.2.3


From af66bfd3c8538ed21cf72af18426fc4a408665cf Mon Sep 17 00:00:00 2001
From: Hou Tao <houtao1@huawei.com>
Date: Mon, 4 Dec 2023 22:04:23 +0800
Subject: bpf: Optimize the free of inner map

When removing the inner map from the outer map, the inner map will be
freed after one RCU grace period and one RCU tasks trace grace
period, so it is certain that the bpf program, which may access the
inner map, has exited before the inner map is freed.

However there is no need to wait for one RCU tasks trace grace period if
the outer map is only accessed by non-sleepable program. So adding
sleepable_refcnt in bpf_map and increasing sleepable_refcnt when adding
the outer map into env->used_maps for sleepable program. Although the
max number of bpf program is INT_MAX - 1, the number of bpf programs
which are being loaded may be greater than INT_MAX, so using atomic64_t
instead of atomic_t for sleepable_refcnt. When removing the inner map
from the outer map, using sleepable_refcnt to decide whether or not a
RCU tasks trace grace period is needed before freeing the inner map.

Signed-off-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/r/20231204140425.1480317-6-houtao@huaweicloud.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h     |  2 ++
 kernel/bpf/core.c       |  4 ++++
 kernel/bpf/map_in_map.c | 14 +++++++++-----
 kernel/bpf/syscall.c    |  8 ++++++++
 kernel/bpf/verifier.c   |  4 +++-
 5 files changed, 26 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index de3bd03cbeea..10e5e4d8a00f 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -297,6 +297,8 @@ struct bpf_map {
 	bool bypass_spec_v1;
 	bool frozen; /* write-once; write-protected by freeze_mutex */
 	bool free_after_mult_rcu_gp;
+	bool free_after_rcu_gp;
+	atomic64_t sleepable_refcnt;
 	s64 __percpu *elem_count;
 };
 
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index cd3afe57ece3..4b813da8d6c0 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2664,12 +2664,16 @@ void __bpf_free_used_maps(struct bpf_prog_aux *aux,
 			  struct bpf_map **used_maps, u32 len)
 {
 	struct bpf_map *map;
+	bool sleepable;
 	u32 i;
 
+	sleepable = aux->sleepable;
 	for (i = 0; i < len; i++) {
 		map = used_maps[i];
 		if (map->ops->map_poke_untrack)
 			map->ops->map_poke_untrack(map, aux);
+		if (sleepable)
+			atomic64_dec(&map->sleepable_refcnt);
 		bpf_map_put(map);
 	}
 }
diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c
index 3248ff5d8161..8ef269e66ba5 100644
--- a/kernel/bpf/map_in_map.c
+++ b/kernel/bpf/map_in_map.c
@@ -131,12 +131,16 @@ void bpf_map_fd_put_ptr(struct bpf_map *map, void *ptr, bool need_defer)
 {
 	struct bpf_map *inner_map = ptr;
 
-	/* The inner map may still be used by both non-sleepable and sleepable
-	 * bpf program, so free it after one RCU grace period and one tasks
-	 * trace RCU grace period.
+	/* Defer the freeing of inner map according to the sleepable attribute
+	 * of bpf program which owns the outer map, so unnecessary waiting for
+	 * RCU tasks trace grace period can be avoided.
 	 */
-	if (need_defer)
-		WRITE_ONCE(inner_map->free_after_mult_rcu_gp, true);
+	if (need_defer) {
+		if (atomic64_read(&map->sleepable_refcnt))
+			WRITE_ONCE(inner_map->free_after_mult_rcu_gp, true);
+		else
+			WRITE_ONCE(inner_map->free_after_rcu_gp, true);
+	}
 	bpf_map_put(inner_map);
 }
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index dd515f6b9741..ebaccf77d56e 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -751,8 +751,11 @@ void bpf_map_put(struct bpf_map *map)
 		bpf_map_free_id(map);
 		btf_put(map->btf);
 
+		WARN_ON_ONCE(atomic64_read(&map->sleepable_refcnt));
 		if (READ_ONCE(map->free_after_mult_rcu_gp))
 			call_rcu_tasks_trace(&map->rcu, bpf_map_free_mult_rcu_gp);
+		else if (READ_ONCE(map->free_after_rcu_gp))
+			call_rcu(&map->rcu, bpf_map_free_rcu_gp);
 		else
 			bpf_map_free_in_work(map);
 	}
@@ -5345,6 +5348,11 @@ static int bpf_prog_bind_map(union bpf_attr *attr)
 		goto out_unlock;
 	}
 
+	/* The bpf program will not access the bpf map, but for the sake of
+	 * simplicity, increase sleepable_refcnt for sleepable program as well.
+	 */
+	if (prog->aux->sleepable)
+		atomic64_inc(&map->sleepable_refcnt);
 	memcpy(used_maps_new, used_maps_old,
 	       sizeof(used_maps_old[0]) * prog->aux->used_map_cnt);
 	used_maps_new[prog->aux->used_map_cnt] = map;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index cdb4f5f0ba79..1ed39665f802 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -17889,10 +17889,12 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env)
 				return -E2BIG;
 			}
 
+			if (env->prog->aux->sleepable)
+				atomic64_inc(&map->sleepable_refcnt);
 			/* hold the map. If the program is rejected by verifier,
 			 * the map will be released by release_maps() or it
 			 * will be used by the valid program until it's unloaded
-			 * and all maps are released in free_used_maps()
+			 * and all maps are released in bpf_free_used_maps()
 			 */
 			bpf_map_inc(map);
 
-- 
cgit v1.2.3


From bc877956272f0521fef107838555817112a450dc Mon Sep 17 00:00:00 2001
From: Amritha Nambiar <amritha.nambiar@intel.com>
Date: Fri, 1 Dec 2023 15:28:29 -0800
Subject: netdev-genl: spec: Extend netdev netlink spec in YAML for queue

Add support in netlink spec(netdev.yaml) for queue information.
Add code generated from the spec.

Note: The "queue-type" attribute takes values 0 and 1 for rx
and tx queue type respectively.

Signed-off-by: Amritha Nambiar <amritha.nambiar@intel.com>
Reviewed-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
Link: https://lore.kernel.org/r/170147330963.5260.2576294626647300472.stgit@anambiarhost.jf.intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/netdev.yaml |  52 +++++++++++
 include/uapi/linux/netdev.h             |  16 ++++
 net/core/netdev-genl-gen.c              |  26 ++++++
 net/core/netdev-genl-gen.h              |   3 +
 net/core/netdev-genl.c                  |  10 +++
 tools/include/uapi/linux/netdev.h       |  16 ++++
 tools/net/ynl/generated/netdev-user.c   | 153 ++++++++++++++++++++++++++++++++
 tools/net/ynl/generated/netdev-user.h   |  99 +++++++++++++++++++++
 8 files changed, 375 insertions(+)

(limited to 'include')

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index eef6358ec587..719e6aafbfdb 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -66,6 +66,10 @@ definitions:
         name: tx-checksum
         doc:
           L3 checksum HW offload is supported by the driver.
+  -
+    name: queue-type
+    type: enum
+    entries: [ rx, tx ]
 
 attribute-sets:
   -
@@ -209,6 +213,31 @@ attribute-sets:
         name: recycle-released-refcnt
         type: uint
 
+  -
+    name: queue
+    attributes:
+      -
+        name: id
+        doc: Queue index; most queue types are indexed like a C array, with
+             indexes starting at 0 and ending at queue count - 1. Queue indexes
+             are scoped to an interface and queue type.
+        type: u32
+      -
+        name: ifindex
+        doc: ifindex of the netdevice to which the queue belongs.
+        type: u32
+        checks:
+          min: 1
+      -
+        name: type
+        doc: Queue type as rx, tx. Each queue type defines a separate ID space.
+        type: u32
+        enum: queue-type
+      -
+        name: napi-id
+        doc: ID of the NAPI instance which services this queue.
+        type: u32
+
 operations:
   list:
     -
@@ -307,6 +336,29 @@ operations:
       dump:
         reply: *pp-stats-reply
       config-cond: page-pool-stats
+    -
+      name: queue-get
+      doc: Get queue information from the kernel.
+           Only configured queues will be reported (as opposed to all available
+           hardware queues).
+      attribute-set: queue
+      do:
+        request:
+          attributes:
+            - ifindex
+            - type
+            - id
+        reply: &queue-get-op
+          attributes:
+            - id
+            - type
+            - napi-id
+            - ifindex
+      dump:
+        request:
+          attributes:
+            - ifindex
+        reply: *queue-get-op
 
 mcast-groups:
   list:
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index 6244c0164976..f857960a7f06 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -62,6 +62,11 @@ enum netdev_xsk_flags {
 	NETDEV_XSK_FLAGS_TX_CHECKSUM = 2,
 };
 
+enum netdev_queue_type {
+	NETDEV_QUEUE_TYPE_RX,
+	NETDEV_QUEUE_TYPE_TX,
+};
+
 enum {
 	NETDEV_A_DEV_IFINDEX = 1,
 	NETDEV_A_DEV_PAD,
@@ -104,6 +109,16 @@ enum {
 	NETDEV_A_PAGE_POOL_STATS_MAX = (__NETDEV_A_PAGE_POOL_STATS_MAX - 1)
 };
 
+enum {
+	NETDEV_A_QUEUE_ID = 1,
+	NETDEV_A_QUEUE_IFINDEX,
+	NETDEV_A_QUEUE_TYPE,
+	NETDEV_A_QUEUE_NAPI_ID,
+
+	__NETDEV_A_QUEUE_MAX,
+	NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1)
+};
+
 enum {
 	NETDEV_CMD_DEV_GET = 1,
 	NETDEV_CMD_DEV_ADD_NTF,
@@ -114,6 +129,7 @@ enum {
 	NETDEV_CMD_PAGE_POOL_DEL_NTF,
 	NETDEV_CMD_PAGE_POOL_CHANGE_NTF,
 	NETDEV_CMD_PAGE_POOL_STATS_GET,
+	NETDEV_CMD_QUEUE_GET,
 
 	__NETDEV_CMD_MAX,
 	NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)
diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c
index dccd8c3a141e..b1dcf88c82cf 100644
--- a/net/core/netdev-genl-gen.c
+++ b/net/core/netdev-genl-gen.c
@@ -46,6 +46,18 @@ static const struct nla_policy netdev_page_pool_stats_get_nl_policy[NETDEV_A_PAG
 };
 #endif /* CONFIG_PAGE_POOL_STATS */
 
+/* NETDEV_CMD_QUEUE_GET - do */
+static const struct nla_policy netdev_queue_get_do_nl_policy[NETDEV_A_QUEUE_TYPE + 1] = {
+	[NETDEV_A_QUEUE_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1),
+	[NETDEV_A_QUEUE_TYPE] = NLA_POLICY_MAX(NLA_U32, 1),
+	[NETDEV_A_QUEUE_ID] = { .type = NLA_U32, },
+};
+
+/* NETDEV_CMD_QUEUE_GET - dump */
+static const struct nla_policy netdev_queue_get_dump_nl_policy[NETDEV_A_QUEUE_IFINDEX + 1] = {
+	[NETDEV_A_QUEUE_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1),
+};
+
 /* Ops table for netdev */
 static const struct genl_split_ops netdev_nl_ops[] = {
 	{
@@ -88,6 +100,20 @@ static const struct genl_split_ops netdev_nl_ops[] = {
 		.flags	= GENL_CMD_CAP_DUMP,
 	},
 #endif /* CONFIG_PAGE_POOL_STATS */
+	{
+		.cmd		= NETDEV_CMD_QUEUE_GET,
+		.doit		= netdev_nl_queue_get_doit,
+		.policy		= netdev_queue_get_do_nl_policy,
+		.maxattr	= NETDEV_A_QUEUE_TYPE,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= NETDEV_CMD_QUEUE_GET,
+		.dumpit		= netdev_nl_queue_get_dumpit,
+		.policy		= netdev_queue_get_dump_nl_policy,
+		.maxattr	= NETDEV_A_QUEUE_IFINDEX,
+		.flags		= GENL_CMD_CAP_DUMP,
+	},
 };
 
 static const struct genl_multicast_group netdev_nl_mcgrps[] = {
diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h
index 649e4b46eccf..086623c1797a 100644
--- a/net/core/netdev-genl-gen.h
+++ b/net/core/netdev-genl-gen.h
@@ -23,6 +23,9 @@ int netdev_nl_page_pool_stats_get_doit(struct sk_buff *skb,
 				       struct genl_info *info);
 int netdev_nl_page_pool_stats_get_dumpit(struct sk_buff *skb,
 					 struct netlink_callback *cb);
+int netdev_nl_queue_get_doit(struct sk_buff *skb, struct genl_info *info);
+int netdev_nl_queue_get_dumpit(struct sk_buff *skb,
+			       struct netlink_callback *cb);
 
 enum {
 	NETDEV_NLGRP_MGMT,
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 10f2124e9e23..35e2d692f651 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -140,6 +140,16 @@ int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 	return skb->len;
 }
 
+int netdev_nl_queue_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	return -EOPNOTSUPP;
+}
+
+int netdev_nl_queue_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	return -EOPNOTSUPP;
+}
+
 static int netdev_genl_netdevice_event(struct notifier_block *nb,
 				       unsigned long event, void *ptr)
 {
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index 6244c0164976..f857960a7f06 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -62,6 +62,11 @@ enum netdev_xsk_flags {
 	NETDEV_XSK_FLAGS_TX_CHECKSUM = 2,
 };
 
+enum netdev_queue_type {
+	NETDEV_QUEUE_TYPE_RX,
+	NETDEV_QUEUE_TYPE_TX,
+};
+
 enum {
 	NETDEV_A_DEV_IFINDEX = 1,
 	NETDEV_A_DEV_PAD,
@@ -104,6 +109,16 @@ enum {
 	NETDEV_A_PAGE_POOL_STATS_MAX = (__NETDEV_A_PAGE_POOL_STATS_MAX - 1)
 };
 
+enum {
+	NETDEV_A_QUEUE_ID = 1,
+	NETDEV_A_QUEUE_IFINDEX,
+	NETDEV_A_QUEUE_TYPE,
+	NETDEV_A_QUEUE_NAPI_ID,
+
+	__NETDEV_A_QUEUE_MAX,
+	NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1)
+};
+
 enum {
 	NETDEV_CMD_DEV_GET = 1,
 	NETDEV_CMD_DEV_ADD_NTF,
@@ -114,6 +129,7 @@ enum {
 	NETDEV_CMD_PAGE_POOL_DEL_NTF,
 	NETDEV_CMD_PAGE_POOL_CHANGE_NTF,
 	NETDEV_CMD_PAGE_POOL_STATS_GET,
+	NETDEV_CMD_QUEUE_GET,
 
 	__NETDEV_CMD_MAX,
 	NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)
diff --git a/tools/net/ynl/generated/netdev-user.c b/tools/net/ynl/generated/netdev-user.c
index 3b9dee94d4ce..fbf7e24ade91 100644
--- a/tools/net/ynl/generated/netdev-user.c
+++ b/tools/net/ynl/generated/netdev-user.c
@@ -23,6 +23,7 @@ static const char * const netdev_op_strmap[] = {
 	[NETDEV_CMD_PAGE_POOL_DEL_NTF] = "page-pool-del-ntf",
 	[NETDEV_CMD_PAGE_POOL_CHANGE_NTF] = "page-pool-change-ntf",
 	[NETDEV_CMD_PAGE_POOL_STATS_GET] = "page-pool-stats-get",
+	[NETDEV_CMD_QUEUE_GET] = "queue-get",
 };
 
 const char *netdev_op_str(int op)
@@ -76,6 +77,18 @@ const char *netdev_xsk_flags_str(enum netdev_xsk_flags value)
 	return netdev_xsk_flags_strmap[value];
 }
 
+static const char * const netdev_queue_type_strmap[] = {
+	[0] = "rx",
+	[1] = "tx",
+};
+
+const char *netdev_queue_type_str(enum netdev_queue_type value)
+{
+	if (value < 0 || value >= (int)MNL_ARRAY_SIZE(netdev_queue_type_strmap))
+		return NULL;
+	return netdev_queue_type_strmap[value];
+}
+
 /* Policies */
 struct ynl_policy_attr netdev_page_pool_info_policy[NETDEV_A_PAGE_POOL_MAX + 1] = {
 	[NETDEV_A_PAGE_POOL_ID] = { .name = "id", .type = YNL_PT_UINT, },
@@ -135,6 +148,18 @@ struct ynl_policy_nest netdev_page_pool_stats_nest = {
 	.table = netdev_page_pool_stats_policy,
 };
 
+struct ynl_policy_attr netdev_queue_policy[NETDEV_A_QUEUE_MAX + 1] = {
+	[NETDEV_A_QUEUE_ID] = { .name = "id", .type = YNL_PT_U32, },
+	[NETDEV_A_QUEUE_IFINDEX] = { .name = "ifindex", .type = YNL_PT_U32, },
+	[NETDEV_A_QUEUE_TYPE] = { .name = "type", .type = YNL_PT_U32, },
+	[NETDEV_A_QUEUE_NAPI_ID] = { .name = "napi-id", .type = YNL_PT_U32, },
+};
+
+struct ynl_policy_nest netdev_queue_nest = {
+	.max_attr = NETDEV_A_QUEUE_MAX,
+	.table = netdev_queue_policy,
+};
+
 /* Common nested types */
 void netdev_page_pool_info_free(struct netdev_page_pool_info *obj)
 {
@@ -617,6 +642,134 @@ free_list:
 	return NULL;
 }
 
+/* ============== NETDEV_CMD_QUEUE_GET ============== */
+/* NETDEV_CMD_QUEUE_GET - do */
+void netdev_queue_get_req_free(struct netdev_queue_get_req *req)
+{
+	free(req);
+}
+
+void netdev_queue_get_rsp_free(struct netdev_queue_get_rsp *rsp)
+{
+	free(rsp);
+}
+
+int netdev_queue_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
+{
+	struct ynl_parse_arg *yarg = data;
+	struct netdev_queue_get_rsp *dst;
+	const struct nlattr *attr;
+
+	dst = yarg->data;
+
+	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == NETDEV_A_QUEUE_ID) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.id = 1;
+			dst->id = mnl_attr_get_u32(attr);
+		} else if (type == NETDEV_A_QUEUE_TYPE) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.type = 1;
+			dst->type = mnl_attr_get_u32(attr);
+		} else if (type == NETDEV_A_QUEUE_NAPI_ID) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.napi_id = 1;
+			dst->napi_id = mnl_attr_get_u32(attr);
+		} else if (type == NETDEV_A_QUEUE_IFINDEX) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.ifindex = 1;
+			dst->ifindex = mnl_attr_get_u32(attr);
+		}
+	}
+
+	return MNL_CB_OK;
+}
+
+struct netdev_queue_get_rsp *
+netdev_queue_get(struct ynl_sock *ys, struct netdev_queue_get_req *req)
+{
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
+	struct netdev_queue_get_rsp *rsp;
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, NETDEV_CMD_QUEUE_GET, 1);
+	ys->req_policy = &netdev_queue_nest;
+	yrs.yarg.rsp_policy = &netdev_queue_nest;
+
+	if (req->_present.ifindex)
+		mnl_attr_put_u32(nlh, NETDEV_A_QUEUE_IFINDEX, req->ifindex);
+	if (req->_present.type)
+		mnl_attr_put_u32(nlh, NETDEV_A_QUEUE_TYPE, req->type);
+	if (req->_present.id)
+		mnl_attr_put_u32(nlh, NETDEV_A_QUEUE_ID, req->id);
+
+	rsp = calloc(1, sizeof(*rsp));
+	yrs.yarg.data = rsp;
+	yrs.cb = netdev_queue_get_rsp_parse;
+	yrs.rsp_cmd = NETDEV_CMD_QUEUE_GET;
+
+	err = ynl_exec(ys, nlh, &yrs);
+	if (err < 0)
+		goto err_free;
+
+	return rsp;
+
+err_free:
+	netdev_queue_get_rsp_free(rsp);
+	return NULL;
+}
+
+/* NETDEV_CMD_QUEUE_GET - dump */
+void netdev_queue_get_list_free(struct netdev_queue_get_list *rsp)
+{
+	struct netdev_queue_get_list *next = rsp;
+
+	while ((void *)next != YNL_LIST_END) {
+		rsp = next;
+		next = rsp->next;
+
+		free(rsp);
+	}
+}
+
+struct netdev_queue_get_list *
+netdev_queue_get_dump(struct ynl_sock *ys,
+		      struct netdev_queue_get_req_dump *req)
+{
+	struct ynl_dump_state yds = {};
+	struct nlmsghdr *nlh;
+	int err;
+
+	yds.ys = ys;
+	yds.alloc_sz = sizeof(struct netdev_queue_get_list);
+	yds.cb = netdev_queue_get_rsp_parse;
+	yds.rsp_cmd = NETDEV_CMD_QUEUE_GET;
+	yds.rsp_policy = &netdev_queue_nest;
+
+	nlh = ynl_gemsg_start_dump(ys, ys->family_id, NETDEV_CMD_QUEUE_GET, 1);
+	ys->req_policy = &netdev_queue_nest;
+
+	if (req->_present.ifindex)
+		mnl_attr_put_u32(nlh, NETDEV_A_QUEUE_IFINDEX, req->ifindex);
+
+	err = ynl_exec_dump(ys, nlh, &yds);
+	if (err < 0)
+		goto free_list;
+
+	return yds.first;
+
+free_list:
+	netdev_queue_get_list_free(yds.first);
+	return NULL;
+}
+
 static const struct ynl_ntf_info netdev_ntf_info[] =  {
 	[NETDEV_CMD_DEV_ADD_NTF] =  {
 		.alloc_sz	= sizeof(struct netdev_dev_get_ntf),
diff --git a/tools/net/ynl/generated/netdev-user.h b/tools/net/ynl/generated/netdev-user.h
index cc3d80d1cf8c..d7daf6df3df0 100644
--- a/tools/net/ynl/generated/netdev-user.h
+++ b/tools/net/ynl/generated/netdev-user.h
@@ -20,6 +20,7 @@ const char *netdev_op_str(int op);
 const char *netdev_xdp_act_str(enum netdev_xdp_act value);
 const char *netdev_xdp_rx_metadata_str(enum netdev_xdp_rx_metadata value);
 const char *netdev_xsk_flags_str(enum netdev_xsk_flags value);
+const char *netdev_queue_type_str(enum netdev_queue_type value);
 
 /* Common nested types */
 struct netdev_page_pool_info {
@@ -261,4 +262,102 @@ netdev_page_pool_stats_get_list_free(struct netdev_page_pool_stats_get_list *rsp
 struct netdev_page_pool_stats_get_list *
 netdev_page_pool_stats_get_dump(struct ynl_sock *ys);
 
+/* ============== NETDEV_CMD_QUEUE_GET ============== */
+/* NETDEV_CMD_QUEUE_GET - do */
+struct netdev_queue_get_req {
+	struct {
+		__u32 ifindex:1;
+		__u32 type:1;
+		__u32 id:1;
+	} _present;
+
+	__u32 ifindex;
+	enum netdev_queue_type type;
+	__u32 id;
+};
+
+static inline struct netdev_queue_get_req *netdev_queue_get_req_alloc(void)
+{
+	return calloc(1, sizeof(struct netdev_queue_get_req));
+}
+void netdev_queue_get_req_free(struct netdev_queue_get_req *req);
+
+static inline void
+netdev_queue_get_req_set_ifindex(struct netdev_queue_get_req *req,
+				 __u32 ifindex)
+{
+	req->_present.ifindex = 1;
+	req->ifindex = ifindex;
+}
+static inline void
+netdev_queue_get_req_set_type(struct netdev_queue_get_req *req,
+			      enum netdev_queue_type type)
+{
+	req->_present.type = 1;
+	req->type = type;
+}
+static inline void
+netdev_queue_get_req_set_id(struct netdev_queue_get_req *req, __u32 id)
+{
+	req->_present.id = 1;
+	req->id = id;
+}
+
+struct netdev_queue_get_rsp {
+	struct {
+		__u32 id:1;
+		__u32 type:1;
+		__u32 napi_id:1;
+		__u32 ifindex:1;
+	} _present;
+
+	__u32 id;
+	enum netdev_queue_type type;
+	__u32 napi_id;
+	__u32 ifindex;
+};
+
+void netdev_queue_get_rsp_free(struct netdev_queue_get_rsp *rsp);
+
+/*
+ * Get queue information from the kernel. Only configured queues will be reported (as opposed to all available hardware queues).
+ */
+struct netdev_queue_get_rsp *
+netdev_queue_get(struct ynl_sock *ys, struct netdev_queue_get_req *req);
+
+/* NETDEV_CMD_QUEUE_GET - dump */
+struct netdev_queue_get_req_dump {
+	struct {
+		__u32 ifindex:1;
+	} _present;
+
+	__u32 ifindex;
+};
+
+static inline struct netdev_queue_get_req_dump *
+netdev_queue_get_req_dump_alloc(void)
+{
+	return calloc(1, sizeof(struct netdev_queue_get_req_dump));
+}
+void netdev_queue_get_req_dump_free(struct netdev_queue_get_req_dump *req);
+
+static inline void
+netdev_queue_get_req_dump_set_ifindex(struct netdev_queue_get_req_dump *req,
+				      __u32 ifindex)
+{
+	req->_present.ifindex = 1;
+	req->ifindex = ifindex;
+}
+
+struct netdev_queue_get_list {
+	struct netdev_queue_get_list *next;
+	struct netdev_queue_get_rsp obj __attribute__((aligned(8)));
+};
+
+void netdev_queue_get_list_free(struct netdev_queue_get_list *rsp);
+
+struct netdev_queue_get_list *
+netdev_queue_get_dump(struct ynl_sock *ys,
+		      struct netdev_queue_get_req_dump *req);
+
 #endif /* _LINUX_NETDEV_GEN_H */
-- 
cgit v1.2.3


From 2a502ff0c4e42a739b5aa550c901bf3852795532 Mon Sep 17 00:00:00 2001
From: Amritha Nambiar <amritha.nambiar@intel.com>
Date: Fri, 1 Dec 2023 15:28:34 -0800
Subject: net: Add queue and napi association

Add the napi pointer in netdev queue for tracking the napi
instance for each queue. This achieves the queue<->napi mapping.

Signed-off-by: Amritha Nambiar <amritha.nambiar@intel.com>
Reviewed-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
Link: https://lore.kernel.org/r/170147331483.5260.15723438819994285695.stgit@anambiarhost.jf.intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdevice.h     |  8 ++++++++
 include/net/netdev_rx_queue.h |  4 ++++
 net/core/dev.c                | 37 +++++++++++++++++++++++++++++++++++++
 3 files changed, 49 insertions(+)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index c2d74bc112dd..5ddff11cbe26 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -665,6 +665,10 @@ struct netdev_queue {
 #ifdef CONFIG_XDP_SOCKETS
 	struct xsk_buff_pool    *pool;
 #endif
+	/* NAPI instance for the queue
+	 * Readers and writers must hold RTNL
+	 */
+	struct napi_struct      *napi;
 /*
  * write-mostly part
  */
@@ -2657,6 +2661,10 @@ static inline void *netdev_priv(const struct net_device *dev)
  */
 #define SET_NETDEV_DEVTYPE(net, devtype)	((net)->dev.type = (devtype))
 
+void netif_queue_set_napi(struct net_device *dev, unsigned int queue_index,
+			  enum netdev_queue_type type,
+			  struct napi_struct *napi);
+
 /* Default NAPI poll() weight
  * Device drivers are strongly advised to not use bigger value
  */
diff --git a/include/net/netdev_rx_queue.h b/include/net/netdev_rx_queue.h
index cdcafb30d437..aa1716fb0e53 100644
--- a/include/net/netdev_rx_queue.h
+++ b/include/net/netdev_rx_queue.h
@@ -21,6 +21,10 @@ struct netdev_rx_queue {
 #ifdef CONFIG_XDP_SOCKETS
 	struct xsk_buff_pool            *pool;
 #endif
+	/* NAPI instance for the queue
+	 * Readers and writers must hold RTNL
+	 */
+	struct napi_struct		*napi;
 } ____cacheline_aligned_in_smp;
 
 /*
diff --git a/net/core/dev.c b/net/core/dev.c
index 3950ced396b5..0a2eecbeef38 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6400,6 +6400,43 @@ int dev_set_threaded(struct net_device *dev, bool threaded)
 }
 EXPORT_SYMBOL(dev_set_threaded);
 
+/**
+ * netif_queue_set_napi - Associate queue with the napi
+ * @dev: device to which NAPI and queue belong
+ * @queue_index: Index of queue
+ * @type: queue type as RX or TX
+ * @napi: NAPI context, pass NULL to clear previously set NAPI
+ *
+ * Set queue with its corresponding napi context. This should be done after
+ * registering the NAPI handler for the queue-vector and the queues have been
+ * mapped to the corresponding interrupt vector.
+ */
+void netif_queue_set_napi(struct net_device *dev, unsigned int queue_index,
+			  enum netdev_queue_type type, struct napi_struct *napi)
+{
+	struct netdev_rx_queue *rxq;
+	struct netdev_queue *txq;
+
+	if (WARN_ON_ONCE(napi && !napi->dev))
+		return;
+	if (dev->reg_state >= NETREG_REGISTERED)
+		ASSERT_RTNL();
+
+	switch (type) {
+	case NETDEV_QUEUE_TYPE_RX:
+		rxq = __netif_get_rx_queue(dev, queue_index);
+		rxq->napi = napi;
+		return;
+	case NETDEV_QUEUE_TYPE_TX:
+		txq = netdev_get_tx_queue(dev, queue_index);
+		txq->napi = napi;
+		return;
+	default:
+		return;
+	}
+}
+EXPORT_SYMBOL(netif_queue_set_napi);
+
 void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi,
 			   int (*poll)(struct napi_struct *, int), int weight)
 {
-- 
cgit v1.2.3


From ff9991499fb53575c45eb92cd064bcd7141bb572 Mon Sep 17 00:00:00 2001
From: Amritha Nambiar <amritha.nambiar@intel.com>
Date: Fri, 1 Dec 2023 15:28:51 -0800
Subject: netdev-genl: spec: Extend netdev netlink spec in YAML for NAPI

Add support in netlink spec(netdev.yaml) for napi related information.
Add code generated from the spec.

Signed-off-by: Amritha Nambiar <amritha.nambiar@intel.com>
Reviewed-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
Link: https://lore.kernel.org/r/170147333119.5260.7050639053080529108.stgit@anambiarhost.jf.intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/netdev.yaml |  30 ++++++++
 include/uapi/linux/netdev.h             |   9 +++
 net/core/netdev-genl-gen.c              |  24 +++++++
 net/core/netdev-genl-gen.h              |   2 +
 net/core/netdev-genl.c                  |  10 +++
 tools/include/uapi/linux/netdev.h       |   9 +++
 tools/net/ynl/generated/netdev-user.c   | 124 ++++++++++++++++++++++++++++++++
 tools/net/ynl/generated/netdev-user.h   |  75 +++++++++++++++++++
 8 files changed, 283 insertions(+)

(limited to 'include')

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index 719e6aafbfdb..76d6b2e15b67 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -213,6 +213,19 @@ attribute-sets:
         name: recycle-released-refcnt
         type: uint
 
+  -
+    name: napi
+    attributes:
+      -
+        name: ifindex
+        doc: ifindex of the netdevice to which NAPI instance belongs.
+        type: u32
+        checks:
+          min: 1
+      -
+        name: id
+        doc: ID of the NAPI instance.
+        type: u32
   -
     name: queue
     attributes:
@@ -359,6 +372,23 @@ operations:
           attributes:
             - ifindex
         reply: *queue-get-op
+    -
+      name: napi-get
+      doc: Get information about NAPI instances configured on the system.
+      attribute-set: napi
+      do:
+        request:
+          attributes:
+            - id
+        reply: &napi-get-op
+          attributes:
+            - id
+            - ifindex
+      dump:
+        request:
+          attributes:
+            - ifindex
+        reply: *napi-get-op
 
 mcast-groups:
   list:
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index f857960a7f06..e7bdbcb01f22 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -109,6 +109,14 @@ enum {
 	NETDEV_A_PAGE_POOL_STATS_MAX = (__NETDEV_A_PAGE_POOL_STATS_MAX - 1)
 };
 
+enum {
+	NETDEV_A_NAPI_IFINDEX = 1,
+	NETDEV_A_NAPI_ID,
+
+	__NETDEV_A_NAPI_MAX,
+	NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1)
+};
+
 enum {
 	NETDEV_A_QUEUE_ID = 1,
 	NETDEV_A_QUEUE_IFINDEX,
@@ -130,6 +138,7 @@ enum {
 	NETDEV_CMD_PAGE_POOL_CHANGE_NTF,
 	NETDEV_CMD_PAGE_POOL_STATS_GET,
 	NETDEV_CMD_QUEUE_GET,
+	NETDEV_CMD_NAPI_GET,
 
 	__NETDEV_CMD_MAX,
 	NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)
diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c
index b1dcf88c82cf..be7f2ebd61b2 100644
--- a/net/core/netdev-genl-gen.c
+++ b/net/core/netdev-genl-gen.c
@@ -58,6 +58,16 @@ static const struct nla_policy netdev_queue_get_dump_nl_policy[NETDEV_A_QUEUE_IF
 	[NETDEV_A_QUEUE_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1),
 };
 
+/* NETDEV_CMD_NAPI_GET - do */
+static const struct nla_policy netdev_napi_get_do_nl_policy[NETDEV_A_NAPI_ID + 1] = {
+	[NETDEV_A_NAPI_ID] = { .type = NLA_U32, },
+};
+
+/* NETDEV_CMD_NAPI_GET - dump */
+static const struct nla_policy netdev_napi_get_dump_nl_policy[NETDEV_A_NAPI_IFINDEX + 1] = {
+	[NETDEV_A_NAPI_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1),
+};
+
 /* Ops table for netdev */
 static const struct genl_split_ops netdev_nl_ops[] = {
 	{
@@ -114,6 +124,20 @@ static const struct genl_split_ops netdev_nl_ops[] = {
 		.maxattr	= NETDEV_A_QUEUE_IFINDEX,
 		.flags		= GENL_CMD_CAP_DUMP,
 	},
+	{
+		.cmd		= NETDEV_CMD_NAPI_GET,
+		.doit		= netdev_nl_napi_get_doit,
+		.policy		= netdev_napi_get_do_nl_policy,
+		.maxattr	= NETDEV_A_NAPI_ID,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= NETDEV_CMD_NAPI_GET,
+		.dumpit		= netdev_nl_napi_get_dumpit,
+		.policy		= netdev_napi_get_dump_nl_policy,
+		.maxattr	= NETDEV_A_NAPI_IFINDEX,
+		.flags		= GENL_CMD_CAP_DUMP,
+	},
 };
 
 static const struct genl_multicast_group netdev_nl_mcgrps[] = {
diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h
index 086623c1797a..a47f2bcbe4fa 100644
--- a/net/core/netdev-genl-gen.h
+++ b/net/core/netdev-genl-gen.h
@@ -26,6 +26,8 @@ int netdev_nl_page_pool_stats_get_dumpit(struct sk_buff *skb,
 int netdev_nl_queue_get_doit(struct sk_buff *skb, struct genl_info *info);
 int netdev_nl_queue_get_dumpit(struct sk_buff *skb,
 			       struct netlink_callback *cb);
+int netdev_nl_napi_get_doit(struct sk_buff *skb, struct genl_info *info);
+int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
 
 enum {
 	NETDEV_NLGRP_MGMT,
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 3bc1661e6ebf..4c8ea6a4f015 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -155,6 +155,16 @@ int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 	return skb->len;
 }
 
+int netdev_nl_napi_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	return -EOPNOTSUPP;
+}
+
+int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	return -EOPNOTSUPP;
+}
+
 static int
 netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev,
 			 u32 q_idx, u32 q_type, const struct genl_info *info)
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index f857960a7f06..e7bdbcb01f22 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -109,6 +109,14 @@ enum {
 	NETDEV_A_PAGE_POOL_STATS_MAX = (__NETDEV_A_PAGE_POOL_STATS_MAX - 1)
 };
 
+enum {
+	NETDEV_A_NAPI_IFINDEX = 1,
+	NETDEV_A_NAPI_ID,
+
+	__NETDEV_A_NAPI_MAX,
+	NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1)
+};
+
 enum {
 	NETDEV_A_QUEUE_ID = 1,
 	NETDEV_A_QUEUE_IFINDEX,
@@ -130,6 +138,7 @@ enum {
 	NETDEV_CMD_PAGE_POOL_CHANGE_NTF,
 	NETDEV_CMD_PAGE_POOL_STATS_GET,
 	NETDEV_CMD_QUEUE_GET,
+	NETDEV_CMD_NAPI_GET,
 
 	__NETDEV_CMD_MAX,
 	NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)
diff --git a/tools/net/ynl/generated/netdev-user.c b/tools/net/ynl/generated/netdev-user.c
index fbf7e24ade91..906b61554698 100644
--- a/tools/net/ynl/generated/netdev-user.c
+++ b/tools/net/ynl/generated/netdev-user.c
@@ -24,6 +24,7 @@ static const char * const netdev_op_strmap[] = {
 	[NETDEV_CMD_PAGE_POOL_CHANGE_NTF] = "page-pool-change-ntf",
 	[NETDEV_CMD_PAGE_POOL_STATS_GET] = "page-pool-stats-get",
 	[NETDEV_CMD_QUEUE_GET] = "queue-get",
+	[NETDEV_CMD_NAPI_GET] = "napi-get",
 };
 
 const char *netdev_op_str(int op)
@@ -160,6 +161,16 @@ struct ynl_policy_nest netdev_queue_nest = {
 	.table = netdev_queue_policy,
 };
 
+struct ynl_policy_attr netdev_napi_policy[NETDEV_A_NAPI_MAX + 1] = {
+	[NETDEV_A_NAPI_IFINDEX] = { .name = "ifindex", .type = YNL_PT_U32, },
+	[NETDEV_A_NAPI_ID] = { .name = "id", .type = YNL_PT_U32, },
+};
+
+struct ynl_policy_nest netdev_napi_nest = {
+	.max_attr = NETDEV_A_NAPI_MAX,
+	.table = netdev_napi_policy,
+};
+
 /* Common nested types */
 void netdev_page_pool_info_free(struct netdev_page_pool_info *obj)
 {
@@ -770,6 +781,119 @@ free_list:
 	return NULL;
 }
 
+/* ============== NETDEV_CMD_NAPI_GET ============== */
+/* NETDEV_CMD_NAPI_GET - do */
+void netdev_napi_get_req_free(struct netdev_napi_get_req *req)
+{
+	free(req);
+}
+
+void netdev_napi_get_rsp_free(struct netdev_napi_get_rsp *rsp)
+{
+	free(rsp);
+}
+
+int netdev_napi_get_rsp_parse(const struct nlmsghdr *nlh, void *data)
+{
+	struct ynl_parse_arg *yarg = data;
+	struct netdev_napi_get_rsp *dst;
+	const struct nlattr *attr;
+
+	dst = yarg->data;
+
+	mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
+		unsigned int type = mnl_attr_get_type(attr);
+
+		if (type == NETDEV_A_NAPI_ID) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.id = 1;
+			dst->id = mnl_attr_get_u32(attr);
+		} else if (type == NETDEV_A_NAPI_IFINDEX) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.ifindex = 1;
+			dst->ifindex = mnl_attr_get_u32(attr);
+		}
+	}
+
+	return MNL_CB_OK;
+}
+
+struct netdev_napi_get_rsp *
+netdev_napi_get(struct ynl_sock *ys, struct netdev_napi_get_req *req)
+{
+	struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };
+	struct netdev_napi_get_rsp *rsp;
+	struct nlmsghdr *nlh;
+	int err;
+
+	nlh = ynl_gemsg_start_req(ys, ys->family_id, NETDEV_CMD_NAPI_GET, 1);
+	ys->req_policy = &netdev_napi_nest;
+	yrs.yarg.rsp_policy = &netdev_napi_nest;
+
+	if (req->_present.id)
+		mnl_attr_put_u32(nlh, NETDEV_A_NAPI_ID, req->id);
+
+	rsp = calloc(1, sizeof(*rsp));
+	yrs.yarg.data = rsp;
+	yrs.cb = netdev_napi_get_rsp_parse;
+	yrs.rsp_cmd = NETDEV_CMD_NAPI_GET;
+
+	err = ynl_exec(ys, nlh, &yrs);
+	if (err < 0)
+		goto err_free;
+
+	return rsp;
+
+err_free:
+	netdev_napi_get_rsp_free(rsp);
+	return NULL;
+}
+
+/* NETDEV_CMD_NAPI_GET - dump */
+void netdev_napi_get_list_free(struct netdev_napi_get_list *rsp)
+{
+	struct netdev_napi_get_list *next = rsp;
+
+	while ((void *)next != YNL_LIST_END) {
+		rsp = next;
+		next = rsp->next;
+
+		free(rsp);
+	}
+}
+
+struct netdev_napi_get_list *
+netdev_napi_get_dump(struct ynl_sock *ys, struct netdev_napi_get_req_dump *req)
+{
+	struct ynl_dump_state yds = {};
+	struct nlmsghdr *nlh;
+	int err;
+
+	yds.ys = ys;
+	yds.alloc_sz = sizeof(struct netdev_napi_get_list);
+	yds.cb = netdev_napi_get_rsp_parse;
+	yds.rsp_cmd = NETDEV_CMD_NAPI_GET;
+	yds.rsp_policy = &netdev_napi_nest;
+
+	nlh = ynl_gemsg_start_dump(ys, ys->family_id, NETDEV_CMD_NAPI_GET, 1);
+	ys->req_policy = &netdev_napi_nest;
+
+	if (req->_present.ifindex)
+		mnl_attr_put_u32(nlh, NETDEV_A_NAPI_IFINDEX, req->ifindex);
+
+	err = ynl_exec_dump(ys, nlh, &yds);
+	if (err < 0)
+		goto free_list;
+
+	return yds.first;
+
+free_list:
+	netdev_napi_get_list_free(yds.first);
+	return NULL;
+}
+
 static const struct ynl_ntf_info netdev_ntf_info[] =  {
 	[NETDEV_CMD_DEV_ADD_NTF] =  {
 		.alloc_sz	= sizeof(struct netdev_dev_get_ntf),
diff --git a/tools/net/ynl/generated/netdev-user.h b/tools/net/ynl/generated/netdev-user.h
index d7daf6df3df0..481c9e45b689 100644
--- a/tools/net/ynl/generated/netdev-user.h
+++ b/tools/net/ynl/generated/netdev-user.h
@@ -360,4 +360,79 @@ struct netdev_queue_get_list *
 netdev_queue_get_dump(struct ynl_sock *ys,
 		      struct netdev_queue_get_req_dump *req);
 
+/* ============== NETDEV_CMD_NAPI_GET ============== */
+/* NETDEV_CMD_NAPI_GET - do */
+struct netdev_napi_get_req {
+	struct {
+		__u32 id:1;
+	} _present;
+
+	__u32 id;
+};
+
+static inline struct netdev_napi_get_req *netdev_napi_get_req_alloc(void)
+{
+	return calloc(1, sizeof(struct netdev_napi_get_req));
+}
+void netdev_napi_get_req_free(struct netdev_napi_get_req *req);
+
+static inline void
+netdev_napi_get_req_set_id(struct netdev_napi_get_req *req, __u32 id)
+{
+	req->_present.id = 1;
+	req->id = id;
+}
+
+struct netdev_napi_get_rsp {
+	struct {
+		__u32 id:1;
+		__u32 ifindex:1;
+	} _present;
+
+	__u32 id;
+	__u32 ifindex;
+};
+
+void netdev_napi_get_rsp_free(struct netdev_napi_get_rsp *rsp);
+
+/*
+ * Get information about NAPI instances configured on the system.
+ */
+struct netdev_napi_get_rsp *
+netdev_napi_get(struct ynl_sock *ys, struct netdev_napi_get_req *req);
+
+/* NETDEV_CMD_NAPI_GET - dump */
+struct netdev_napi_get_req_dump {
+	struct {
+		__u32 ifindex:1;
+	} _present;
+
+	__u32 ifindex;
+};
+
+static inline struct netdev_napi_get_req_dump *
+netdev_napi_get_req_dump_alloc(void)
+{
+	return calloc(1, sizeof(struct netdev_napi_get_req_dump));
+}
+void netdev_napi_get_req_dump_free(struct netdev_napi_get_req_dump *req);
+
+static inline void
+netdev_napi_get_req_dump_set_ifindex(struct netdev_napi_get_req_dump *req,
+				     __u32 ifindex)
+{
+	req->_present.ifindex = 1;
+	req->ifindex = ifindex;
+}
+
+struct netdev_napi_get_list {
+	struct netdev_napi_get_list *next;
+	struct netdev_napi_get_rsp obj __attribute__((aligned(8)));
+};
+
+void netdev_napi_get_list_free(struct netdev_napi_get_list *rsp);
+
+struct netdev_napi_get_list *
+netdev_napi_get_dump(struct ynl_sock *ys, struct netdev_napi_get_req_dump *req);
+
 #endif /* _LINUX_NETDEV_GEN_H */
-- 
cgit v1.2.3


From 5a5131d66fe02337de0b1b2e021b58f0f55c6df5 Mon Sep 17 00:00:00 2001
From: Amritha Nambiar <amritha.nambiar@intel.com>
Date: Fri, 1 Dec 2023 15:29:02 -0800
Subject: netdev-genl: spec: Add irq in netdev netlink YAML spec

Add support in netlink spec(netdev.yaml) for interrupt number
among the NAPI attributes. Add code generated from the spec.

Signed-off-by: Amritha Nambiar <amritha.nambiar@intel.com>
Reviewed-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
Link: https://lore.kernel.org/r/170147334210.5260.18178387869057516983.stgit@anambiarhost.jf.intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/netdev.yaml | 5 +++++
 include/uapi/linux/netdev.h             | 1 +
 tools/include/uapi/linux/netdev.h       | 1 +
 tools/net/ynl/generated/netdev-user.c   | 6 ++++++
 tools/net/ynl/generated/netdev-user.h   | 2 ++
 5 files changed, 15 insertions(+)

(limited to 'include')

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index 76d6b2e15b67..a3a1c6ad521b 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -226,6 +226,10 @@ attribute-sets:
         name: id
         doc: ID of the NAPI instance.
         type: u32
+      -
+        name: irq
+        doc: The associated interrupt vector number for the napi
+        type: u32
   -
     name: queue
     attributes:
@@ -384,6 +388,7 @@ operations:
           attributes:
             - id
             - ifindex
+            - irq
       dump:
         request:
           attributes:
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index e7bdbcb01f22..30fea409b71e 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -112,6 +112,7 @@ enum {
 enum {
 	NETDEV_A_NAPI_IFINDEX = 1,
 	NETDEV_A_NAPI_ID,
+	NETDEV_A_NAPI_IRQ,
 
 	__NETDEV_A_NAPI_MAX,
 	NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1)
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index e7bdbcb01f22..30fea409b71e 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -112,6 +112,7 @@ enum {
 enum {
 	NETDEV_A_NAPI_IFINDEX = 1,
 	NETDEV_A_NAPI_ID,
+	NETDEV_A_NAPI_IRQ,
 
 	__NETDEV_A_NAPI_MAX,
 	NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1)
diff --git a/tools/net/ynl/generated/netdev-user.c b/tools/net/ynl/generated/netdev-user.c
index 906b61554698..58e5196da4bd 100644
--- a/tools/net/ynl/generated/netdev-user.c
+++ b/tools/net/ynl/generated/netdev-user.c
@@ -164,6 +164,7 @@ struct ynl_policy_nest netdev_queue_nest = {
 struct ynl_policy_attr netdev_napi_policy[NETDEV_A_NAPI_MAX + 1] = {
 	[NETDEV_A_NAPI_IFINDEX] = { .name = "ifindex", .type = YNL_PT_U32, },
 	[NETDEV_A_NAPI_ID] = { .name = "id", .type = YNL_PT_U32, },
+	[NETDEV_A_NAPI_IRQ] = { .name = "irq", .type = YNL_PT_U32, },
 };
 
 struct ynl_policy_nest netdev_napi_nest = {
@@ -210,6 +211,11 @@ int netdev_page_pool_info_parse(struct ynl_parse_arg *yarg,
 				return MNL_CB_ERROR;
 			dst->_present.ifindex = 1;
 			dst->ifindex = mnl_attr_get_u32(attr);
+		} else if (type == NETDEV_A_NAPI_IRQ) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.irq = 1;
+			dst->irq = mnl_attr_get_u32(attr);
 		}
 	}
 
diff --git a/tools/net/ynl/generated/netdev-user.h b/tools/net/ynl/generated/netdev-user.h
index 481c9e45b689..0c3224017c12 100644
--- a/tools/net/ynl/generated/netdev-user.h
+++ b/tools/net/ynl/generated/netdev-user.h
@@ -387,10 +387,12 @@ struct netdev_napi_get_rsp {
 	struct {
 		__u32 id:1;
 		__u32 ifindex:1;
+		__u32 irq:1;
 	} _present;
 
 	__u32 id;
 	__u32 ifindex;
+	__u32 irq;
 };
 
 void netdev_napi_get_rsp_free(struct netdev_napi_get_rsp *rsp);
-- 
cgit v1.2.3


From 26793bfb5d6072326d1465343e7cbf6156abca4f Mon Sep 17 00:00:00 2001
From: Amritha Nambiar <amritha.nambiar@intel.com>
Date: Fri, 1 Dec 2023 15:29:07 -0800
Subject: net: Add NAPI IRQ support

Add support to associate the interrupt vector number for a
NAPI instance.

Signed-off-by: Amritha Nambiar <amritha.nambiar@intel.com>
Reviewed-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
Link: https://lore.kernel.org/r/170147334728.5260.13221803396905901904.stgit@anambiarhost.jf.intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_lib.c | 2 ++
 include/linux/netdevice.h                | 6 ++++++
 net/core/dev.c                           | 1 +
 net/core/netdev-genl.c                   | 4 ++++
 4 files changed, 13 insertions(+)

(limited to 'include')

diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 83f6977fad22..626577c7d5b2 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -2978,6 +2978,8 @@ void ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector, bool locked)
 		ice_queue_set_napi(q_vector->vsi->netdev, tx_ring->q_index,
 				   NETDEV_QUEUE_TYPE_TX, &q_vector->napi,
 				   locked);
+	/* Also set the interrupt number for the NAPI */
+	netif_napi_set_irq(&q_vector->napi, q_vector->irq.virq);
 }
 
 /**
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5ddff11cbe26..5551177e024e 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -382,6 +382,7 @@ struct napi_struct {
 	/* control-path-only fields follow */
 	struct list_head	dev_list;
 	struct hlist_node	napi_hash_node;
+	int			irq;
 };
 
 enum {
@@ -2665,6 +2666,11 @@ void netif_queue_set_napi(struct net_device *dev, unsigned int queue_index,
 			  enum netdev_queue_type type,
 			  struct napi_struct *napi);
 
+static inline void netif_napi_set_irq(struct napi_struct *napi, int irq)
+{
+	napi->irq = irq;
+}
+
 /* Default NAPI poll() weight
  * Device drivers are strongly advised to not use bigger value
  */
diff --git a/net/core/dev.c b/net/core/dev.c
index 13c9d1580e62..1d720fc59161 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6471,6 +6471,7 @@ void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi,
 	 */
 	if (dev->threaded && napi_kthread_create(napi))
 		dev->threaded = 0;
+	netif_napi_set_irq(napi, -1);
 }
 EXPORT_SYMBOL(netif_napi_add_weight);
 
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index d55c92f9f26c..9753c19e36de 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -180,7 +180,11 @@ netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi,
 	if (nla_put_u32(rsp, NETDEV_A_NAPI_IFINDEX, napi->dev->ifindex))
 		goto nla_put_failure;
 
+	if (napi->irq >= 0 && nla_put_u32(rsp, NETDEV_A_NAPI_IRQ, napi->irq))
+		goto nla_put_failure;
+
 	genlmsg_end(rsp, hdr);
+
 	return 0;
 
 nla_put_failure:
-- 
cgit v1.2.3


From 8481a249a0eaf0000dbb18f7689ccd50ea9835cd Mon Sep 17 00:00:00 2001
From: Amritha Nambiar <amritha.nambiar@intel.com>
Date: Fri, 1 Dec 2023 15:29:13 -0800
Subject: netdev-genl: spec: Add PID in netdev netlink YAML spec

Add support in netlink spec(netdev.yaml) for PID of the
NAPI thread. Add code generated from the spec.

Signed-off-by: Amritha Nambiar <amritha.nambiar@intel.com>
Reviewed-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
Link: https://lore.kernel.org/r/170147335301.5260.11872351477120434501.stgit@anambiarhost.jf.intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/netdev.yaml | 7 +++++++
 include/uapi/linux/netdev.h             | 1 +
 tools/include/uapi/linux/netdev.h       | 1 +
 tools/net/ynl/generated/netdev-user.c   | 6 ++++++
 tools/net/ynl/generated/netdev-user.h   | 2 ++
 5 files changed, 17 insertions(+)

(limited to 'include')

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index a3a1c6ad521b..f2c76d103bd8 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -230,6 +230,12 @@ attribute-sets:
         name: irq
         doc: The associated interrupt vector number for the napi
         type: u32
+      -
+        name: pid
+        doc: PID of the napi thread, if NAPI is configured to operate in
+             threaded mode. If NAPI is not in threaded mode (i.e. uses normal
+             softirq context), the attribute will be absent.
+        type: u32
   -
     name: queue
     attributes:
@@ -389,6 +395,7 @@ operations:
             - id
             - ifindex
             - irq
+            - pid
       dump:
         request:
           attributes:
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index 30fea409b71e..424c5e28f495 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -113,6 +113,7 @@ enum {
 	NETDEV_A_NAPI_IFINDEX = 1,
 	NETDEV_A_NAPI_ID,
 	NETDEV_A_NAPI_IRQ,
+	NETDEV_A_NAPI_PID,
 
 	__NETDEV_A_NAPI_MAX,
 	NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1)
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index 30fea409b71e..424c5e28f495 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -113,6 +113,7 @@ enum {
 	NETDEV_A_NAPI_IFINDEX = 1,
 	NETDEV_A_NAPI_ID,
 	NETDEV_A_NAPI_IRQ,
+	NETDEV_A_NAPI_PID,
 
 	__NETDEV_A_NAPI_MAX,
 	NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1)
diff --git a/tools/net/ynl/generated/netdev-user.c b/tools/net/ynl/generated/netdev-user.c
index 58e5196da4bd..ed8bcb855a1d 100644
--- a/tools/net/ynl/generated/netdev-user.c
+++ b/tools/net/ynl/generated/netdev-user.c
@@ -165,6 +165,7 @@ struct ynl_policy_attr netdev_napi_policy[NETDEV_A_NAPI_MAX + 1] = {
 	[NETDEV_A_NAPI_IFINDEX] = { .name = "ifindex", .type = YNL_PT_U32, },
 	[NETDEV_A_NAPI_ID] = { .name = "id", .type = YNL_PT_U32, },
 	[NETDEV_A_NAPI_IRQ] = { .name = "irq", .type = YNL_PT_U32, },
+	[NETDEV_A_NAPI_PID] = { .name = "pid", .type = YNL_PT_U32, },
 };
 
 struct ynl_policy_nest netdev_napi_nest = {
@@ -216,6 +217,11 @@ int netdev_page_pool_info_parse(struct ynl_parse_arg *yarg,
 				return MNL_CB_ERROR;
 			dst->_present.irq = 1;
 			dst->irq = mnl_attr_get_u32(attr);
+		} else if (type == NETDEV_A_NAPI_PID) {
+			if (ynl_attr_validate(yarg, attr))
+				return MNL_CB_ERROR;
+			dst->_present.pid = 1;
+			dst->pid = mnl_attr_get_u32(attr);
 		}
 	}
 
diff --git a/tools/net/ynl/generated/netdev-user.h b/tools/net/ynl/generated/netdev-user.h
index 0c3224017c12..3830cf2ab6b8 100644
--- a/tools/net/ynl/generated/netdev-user.h
+++ b/tools/net/ynl/generated/netdev-user.h
@@ -388,11 +388,13 @@ struct netdev_napi_get_rsp {
 		__u32 id:1;
 		__u32 ifindex:1;
 		__u32 irq:1;
+		__u32 pid:1;
 	} _present;
 
 	__u32 id;
 	__u32 ifindex;
 	__u32 irq;
+	__u32 pid;
 };
 
 void netdev_napi_get_rsp_free(struct netdev_napi_get_rsp *rsp);
-- 
cgit v1.2.3


From 37e4b8df27bc68340f3fc80dbb27e3549c7f881c Mon Sep 17 00:00:00 2001
From: Jianheng Zhang <Jianheng.Zhang@synopsys.com>
Date: Fri, 1 Dec 2023 03:22:03 +0000
Subject: net: stmmac: fix FPE events losing

The status bits of register MAC_FPE_CTRL_STS are clear on read. Using
32-bit read for MAC_FPE_CTRL_STS in dwmac5_fpe_configure() and
dwmac5_fpe_send_mpacket() clear the status bits. Then the stmmac interrupt
handler missing FPE event status and leads to FPE handshaking failure and
retries.
To avoid clear status bits of MAC_FPE_CTRL_STS in dwmac5_fpe_configure()
and dwmac5_fpe_send_mpacket(), add fpe_csr to stmmac_fpe_cfg structure to
cache the control bits of MAC_FPE_CTRL_STS and to avoid reading
MAC_FPE_CTRL_STS in those methods.

Fixes: 5a5586112b92 ("net: stmmac: support FPE link partner hand-shaking procedure")
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Jianheng Zhang <Jianheng.Zhang@synopsys.com>
Link: https://lore.kernel.org/r/CY5PR12MB637225A7CF529D5BE0FBE59CBF81A@CY5PR12MB6372.namprd12.prod.outlook.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac5.c       | 45 +++++++++-------------
 drivers/net/ethernet/stmicro/stmmac/dwmac5.h       |  4 +-
 .../net/ethernet/stmicro/stmmac/dwxgmac2_core.c    |  3 +-
 drivers/net/ethernet/stmicro/stmmac/hwif.h         |  4 +-
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c  |  8 +++-
 drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c    |  1 +
 include/linux/stmmac.h                             |  1 +
 7 files changed, 36 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
index e95d35f1e5a0..8fd167501fa0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
@@ -710,28 +710,22 @@ void dwmac5_est_irq_status(void __iomem *ioaddr, struct net_device *dev,
 	}
 }
 
-void dwmac5_fpe_configure(void __iomem *ioaddr, u32 num_txq, u32 num_rxq,
+void dwmac5_fpe_configure(void __iomem *ioaddr, struct stmmac_fpe_cfg *cfg,
+			  u32 num_txq, u32 num_rxq,
 			  bool enable)
 {
 	u32 value;
 
-	if (!enable) {
-		value = readl(ioaddr + MAC_FPE_CTRL_STS);
-
-		value &= ~EFPE;
-
-		writel(value, ioaddr + MAC_FPE_CTRL_STS);
-		return;
+	if (enable) {
+		cfg->fpe_csr = EFPE;
+		value = readl(ioaddr + GMAC_RXQ_CTRL1);
+		value &= ~GMAC_RXQCTRL_FPRQ;
+		value |= (num_rxq - 1) << GMAC_RXQCTRL_FPRQ_SHIFT;
+		writel(value, ioaddr + GMAC_RXQ_CTRL1);
+	} else {
+		cfg->fpe_csr = 0;
 	}
-
-	value = readl(ioaddr + GMAC_RXQ_CTRL1);
-	value &= ~GMAC_RXQCTRL_FPRQ;
-	value |= (num_rxq - 1) << GMAC_RXQCTRL_FPRQ_SHIFT;
-	writel(value, ioaddr + GMAC_RXQ_CTRL1);
-
-	value = readl(ioaddr + MAC_FPE_CTRL_STS);
-	value |= EFPE;
-	writel(value, ioaddr + MAC_FPE_CTRL_STS);
+	writel(cfg->fpe_csr, ioaddr + MAC_FPE_CTRL_STS);
 }
 
 int dwmac5_fpe_irq_status(void __iomem *ioaddr, struct net_device *dev)
@@ -741,6 +735,9 @@ int dwmac5_fpe_irq_status(void __iomem *ioaddr, struct net_device *dev)
 
 	status = FPE_EVENT_UNKNOWN;
 
+	/* Reads from the MAC_FPE_CTRL_STS register should only be performed
+	 * here, since the status flags of MAC_FPE_CTRL_STS are "clear on read"
+	 */
 	value = readl(ioaddr + MAC_FPE_CTRL_STS);
 
 	if (value & TRSP) {
@@ -766,19 +763,15 @@ int dwmac5_fpe_irq_status(void __iomem *ioaddr, struct net_device *dev)
 	return status;
 }
 
-void dwmac5_fpe_send_mpacket(void __iomem *ioaddr, enum stmmac_mpacket_type type)
+void dwmac5_fpe_send_mpacket(void __iomem *ioaddr, struct stmmac_fpe_cfg *cfg,
+			     enum stmmac_mpacket_type type)
 {
-	u32 value;
+	u32 value = cfg->fpe_csr;
 
-	value = readl(ioaddr + MAC_FPE_CTRL_STS);
-
-	if (type == MPACKET_VERIFY) {
-		value &= ~SRSP;
+	if (type == MPACKET_VERIFY)
 		value |= SVER;
-	} else {
-		value &= ~SVER;
+	else if (type == MPACKET_RESPONSE)
 		value |= SRSP;
-	}
 
 	writel(value, ioaddr + MAC_FPE_CTRL_STS);
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h
index 53c138d0ff48..34e620790eb3 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h
@@ -153,9 +153,11 @@ int dwmac5_est_configure(void __iomem *ioaddr, struct stmmac_est *cfg,
 			 unsigned int ptp_rate);
 void dwmac5_est_irq_status(void __iomem *ioaddr, struct net_device *dev,
 			   struct stmmac_extra_stats *x, u32 txqcnt);
-void dwmac5_fpe_configure(void __iomem *ioaddr, u32 num_txq, u32 num_rxq,
+void dwmac5_fpe_configure(void __iomem *ioaddr, struct stmmac_fpe_cfg *cfg,
+			  u32 num_txq, u32 num_rxq,
 			  bool enable);
 void dwmac5_fpe_send_mpacket(void __iomem *ioaddr,
+			     struct stmmac_fpe_cfg *cfg,
 			     enum stmmac_mpacket_type type);
 int dwmac5_fpe_irq_status(void __iomem *ioaddr, struct net_device *dev);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index 453e88b75be0..a74e71db79f9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -1484,7 +1484,8 @@ static int dwxgmac3_est_configure(void __iomem *ioaddr, struct stmmac_est *cfg,
 	return 0;
 }
 
-static void dwxgmac3_fpe_configure(void __iomem *ioaddr, u32 num_txq,
+static void dwxgmac3_fpe_configure(void __iomem *ioaddr, struct stmmac_fpe_cfg *cfg,
+				   u32 num_txq,
 				   u32 num_rxq, bool enable)
 {
 	u32 value;
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index b95d3e137813..68aa2d5ca6e5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -412,9 +412,11 @@ struct stmmac_ops {
 			     unsigned int ptp_rate);
 	void (*est_irq_status)(void __iomem *ioaddr, struct net_device *dev,
 			       struct stmmac_extra_stats *x, u32 txqcnt);
-	void (*fpe_configure)(void __iomem *ioaddr, u32 num_txq, u32 num_rxq,
+	void (*fpe_configure)(void __iomem *ioaddr, struct stmmac_fpe_cfg *cfg,
+			      u32 num_txq, u32 num_rxq,
 			      bool enable);
 	void (*fpe_send_mpacket)(void __iomem *ioaddr,
+				 struct stmmac_fpe_cfg *cfg,
 				 enum stmmac_mpacket_type type);
 	int (*fpe_irq_status)(void __iomem *ioaddr, struct net_device *dev);
 };
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 2afb2bd25977..37e64283f910 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -964,7 +964,8 @@ static void stmmac_fpe_link_state_handle(struct stmmac_priv *priv, bool is_up)
 	bool *hs_enable = &fpe_cfg->hs_enable;
 
 	if (is_up && *hs_enable) {
-		stmmac_fpe_send_mpacket(priv, priv->ioaddr, MPACKET_VERIFY);
+		stmmac_fpe_send_mpacket(priv, priv->ioaddr, fpe_cfg,
+					MPACKET_VERIFY);
 	} else {
 		*lo_state = FPE_STATE_OFF;
 		*lp_state = FPE_STATE_OFF;
@@ -5839,6 +5840,7 @@ static void stmmac_fpe_event_status(struct stmmac_priv *priv, int status)
 		/* If user has requested FPE enable, quickly response */
 		if (*hs_enable)
 			stmmac_fpe_send_mpacket(priv, priv->ioaddr,
+						fpe_cfg,
 						MPACKET_RESPONSE);
 	}
 
@@ -7263,6 +7265,7 @@ static void stmmac_fpe_lp_task(struct work_struct *work)
 		if (*lo_state == FPE_STATE_ENTERING_ON &&
 		    *lp_state == FPE_STATE_ENTERING_ON) {
 			stmmac_fpe_configure(priv, priv->ioaddr,
+					     fpe_cfg,
 					     priv->plat->tx_queues_to_use,
 					     priv->plat->rx_queues_to_use,
 					     *enable);
@@ -7281,6 +7284,7 @@ static void stmmac_fpe_lp_task(struct work_struct *work)
 			netdev_info(priv->dev, SEND_VERIFY_MPAKCET_FMT,
 				    *lo_state, *lp_state);
 			stmmac_fpe_send_mpacket(priv, priv->ioaddr,
+						fpe_cfg,
 						MPACKET_VERIFY);
 		}
 		/* Sleep then retry */
@@ -7295,6 +7299,7 @@ void stmmac_fpe_handshake(struct stmmac_priv *priv, bool enable)
 	if (priv->plat->fpe_cfg->hs_enable != enable) {
 		if (enable) {
 			stmmac_fpe_send_mpacket(priv, priv->ioaddr,
+						priv->plat->fpe_cfg,
 						MPACKET_VERIFY);
 		} else {
 			priv->plat->fpe_cfg->lo_fpe_state = FPE_STATE_OFF;
@@ -7755,6 +7760,7 @@ int stmmac_suspend(struct device *dev)
 	if (priv->dma_cap.fpesel) {
 		/* Disable FPE */
 		stmmac_fpe_configure(priv, priv->ioaddr,
+				     priv->plat->fpe_cfg,
 				     priv->plat->tx_queues_to_use,
 				     priv->plat->rx_queues_to_use, false);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
index ac41ef4cbd2f..6ad3e0a11936 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
@@ -1079,6 +1079,7 @@ disable:
 
 	priv->plat->fpe_cfg->enable = false;
 	stmmac_fpe_configure(priv, priv->ioaddr,
+			     priv->plat->fpe_cfg,
 			     priv->plat->tx_queues_to_use,
 			     priv->plat->rx_queues_to_use,
 			     false);
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index 0b4658a7eceb..dee5ad6e48c5 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -175,6 +175,7 @@ struct stmmac_fpe_cfg {
 	bool hs_enable;				/* FPE handshake enable */
 	enum stmmac_fpe_state lp_fpe_state;	/* Link Partner FPE state */
 	enum stmmac_fpe_state lo_fpe_state;	/* Local station FPE state */
+	u32 fpe_csr;				/* MAC_FPE_CTRL_STS reg cache */
 };
 
 struct stmmac_safety_feature_cfg {
-- 
cgit v1.2.3


From a5e400a985df8041ed4659ed1462aa9134318130 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Sun, 20 Aug 2023 20:58:56 +0300
Subject: net/mlx5e: Honor user choice of IPsec replay window size

Users can configure IPsec replay window size, but mlx5 driver didn't
honor their choice and set always 32bits. Fix assignment logic to
configure right size from the beginning.

Fixes: 7db21ef4566e ("net/mlx5e: Set IPsec replay sequence numbers")
Reviewed-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 .../ethernet/mellanox/mlx5/core/en_accel/ipsec.c    | 21 +++++++++++++++++++++
 .../mellanox/mlx5/core/en_accel/ipsec_offload.c     |  2 +-
 include/linux/mlx5/mlx5_ifc.h                       |  7 +++++++
 3 files changed, 29 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
index 655496598c68..4028932d93ce 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
@@ -335,6 +335,27 @@ void mlx5e_ipsec_build_accel_xfrm_attrs(struct mlx5e_ipsec_sa_entry *sa_entry,
 		attrs->replay_esn.esn = sa_entry->esn_state.esn;
 		attrs->replay_esn.esn_msb = sa_entry->esn_state.esn_msb;
 		attrs->replay_esn.overlap = sa_entry->esn_state.overlap;
+		switch (x->replay_esn->replay_window) {
+		case 32:
+			attrs->replay_esn.replay_window =
+				MLX5_IPSEC_ASO_REPLAY_WIN_32BIT;
+			break;
+		case 64:
+			attrs->replay_esn.replay_window =
+				MLX5_IPSEC_ASO_REPLAY_WIN_64BIT;
+			break;
+		case 128:
+			attrs->replay_esn.replay_window =
+				MLX5_IPSEC_ASO_REPLAY_WIN_128BIT;
+			break;
+		case 256:
+			attrs->replay_esn.replay_window =
+				MLX5_IPSEC_ASO_REPLAY_WIN_256BIT;
+			break;
+		default:
+			WARN_ON(true);
+			return;
+		}
 	}
 
 	attrs->dir = x->xso.dir;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
index a91f772dc981..4e018fba2d5f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
@@ -95,7 +95,7 @@ static void mlx5e_ipsec_packet_setup(void *obj, u32 pdn,
 
 		if (attrs->dir == XFRM_DEV_OFFLOAD_IN) {
 			MLX5_SET(ipsec_aso, aso_ctx, window_sz,
-				 attrs->replay_esn.replay_window / 64);
+				 attrs->replay_esn.replay_window);
 			MLX5_SET(ipsec_aso, aso_ctx, mode,
 				 MLX5_IPSEC_ASO_REPLAY_PROTECTION);
 		}
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 6f3631425f38..90ca63f4bf63 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -12001,6 +12001,13 @@ enum {
 	MLX5_IPSEC_ASO_INC_SN            = 0x2,
 };
 
+enum {
+	MLX5_IPSEC_ASO_REPLAY_WIN_32BIT  = 0x0,
+	MLX5_IPSEC_ASO_REPLAY_WIN_64BIT  = 0x1,
+	MLX5_IPSEC_ASO_REPLAY_WIN_128BIT = 0x2,
+	MLX5_IPSEC_ASO_REPLAY_WIN_256BIT = 0x3,
+};
+
 struct mlx5_ifc_ipsec_aso_bits {
 	u8         valid[0x1];
 	u8         reserved_at_201[0x1];
-- 
cgit v1.2.3


From c2bf84f1d1a1595dcc45fe867f0e02b331993fee Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Sun, 12 Nov 2023 13:50:00 +0200
Subject: net/mlx5e: Tidy up IPsec NAT-T SA discovery

IPsec NAT-T packets are UDP encapsulated packets over ESP normal ones.
In case they arrive to RX, the SPI and ESP are located in inner header,
while the check was performed on outer header instead.

That wrong check caused to the situation where received rekeying request
was missed and caused to rekey timeout, which "compensated" this failure
by completing rekeying.

Fixes: d65954934937 ("net/mlx5e: Support IPsec NAT-T functionality")
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 .../mellanox/mlx5/core/en_accel/ipsec_fs.c         | 22 ++++++++++++++++------
 include/linux/mlx5/mlx5_ifc.h                      |  2 +-
 2 files changed, 17 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index aeb399d8dae5..7a789061c998 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -1212,13 +1212,22 @@ static void setup_fte_esp(struct mlx5_flow_spec *spec)
 	MLX5_SET(fte_match_param, spec->match_value, outer_headers.ip_protocol, IPPROTO_ESP);
 }
 
-static void setup_fte_spi(struct mlx5_flow_spec *spec, u32 spi)
+static void setup_fte_spi(struct mlx5_flow_spec *spec, u32 spi, bool encap)
 {
 	/* SPI number */
 	spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS;
 
-	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters.outer_esp_spi);
-	MLX5_SET(fte_match_param, spec->match_value, misc_parameters.outer_esp_spi, spi);
+	if (encap) {
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+				 misc_parameters.inner_esp_spi);
+		MLX5_SET(fte_match_param, spec->match_value,
+			 misc_parameters.inner_esp_spi, spi);
+	} else {
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+				 misc_parameters.outer_esp_spi);
+		MLX5_SET(fte_match_param, spec->match_value,
+			 misc_parameters.outer_esp_spi, spi);
+	}
 }
 
 static void setup_fte_no_frags(struct mlx5_flow_spec *spec)
@@ -1596,8 +1605,9 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 	else
 		setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6);
 
-	setup_fte_spi(spec, attrs->spi);
-	setup_fte_esp(spec);
+	setup_fte_spi(spec, attrs->spi, attrs->encap);
+	if (!attrs->encap)
+		setup_fte_esp(spec);
 	setup_fte_no_frags(spec);
 	setup_fte_upper_proto_match(spec, &attrs->upspec);
 
@@ -1719,7 +1729,7 @@ static int tx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 
 	switch (attrs->type) {
 	case XFRM_DEV_OFFLOAD_CRYPTO:
-		setup_fte_spi(spec, attrs->spi);
+		setup_fte_spi(spec, attrs->spi, false);
 		setup_fte_esp(spec);
 		setup_fte_reg_a(spec);
 		break;
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 90ca63f4bf63..3f7b664d625b 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -621,7 +621,7 @@ struct mlx5_ifc_fte_match_set_misc_bits {
 
 	u8         reserved_at_140[0x8];
 	u8         bth_dst_qp[0x18];
-	u8	   reserved_at_160[0x20];
+	u8	   inner_esp_spi[0x20];
 	u8	   outer_esp_spi[0x20];
 	u8         reserved_at_1a0[0x60];
 };
-- 
cgit v1.2.3


From 8ebe06611666a399162de31cdd6f2f48ffa87748 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Fri, 1 Dec 2023 16:19:42 +0800
Subject: net: bridge: add document for IFLA_BR enum

Add document for IFLA_BR enum so we can use it in
Documentation/networking/bridge.rst.

Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/uapi/linux/if_link.h | 280 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 280 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 8181ef23a7a2..a5f873c85a72 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -461,6 +461,286 @@ enum in6_addr_gen_mode {
 
 /* Bridge section */
 
+/**
+ * DOC: Bridge enum definition
+ *
+ * Please *note* that the timer values in the following section are expected
+ * in clock_t format, which is seconds multiplied by USER_HZ (generally
+ * defined as 100).
+ *
+ * @IFLA_BR_FORWARD_DELAY
+ *   The bridge forwarding delay is the time spent in LISTENING state
+ *   (before moving to LEARNING) and in LEARNING state (before moving
+ *   to FORWARDING). Only relevant if STP is enabled.
+ *
+ *   The valid values are between (2 * USER_HZ) and (30 * USER_HZ).
+ *   The default value is (15 * USER_HZ).
+ *
+ * @IFLA_BR_HELLO_TIME
+ *   The time between hello packets sent by the bridge, when it is a root
+ *   bridge or a designated bridge. Only relevant if STP is enabled.
+ *
+ *   The valid values are between (1 * USER_HZ) and (10 * USER_HZ).
+ *   The default value is (2 * USER_HZ).
+ *
+ * @IFLA_BR_MAX_AGE
+ *   The hello packet timeout is the time until another bridge in the
+ *   spanning tree is assumed to be dead, after reception of its last hello
+ *   message. Only relevant if STP is enabled.
+ *
+ *   The valid values are between (6 * USER_HZ) and (40 * USER_HZ).
+ *   The default value is (20 * USER_HZ).
+ *
+ * @IFLA_BR_AGEING_TIME
+ *   Configure the bridge's FDB entries aging time. It is the time a MAC
+ *   address will be kept in the FDB after a packet has been received from
+ *   that address. After this time has passed, entries are cleaned up.
+ *   Allow values outside the 802.1 standard specification for special cases:
+ *
+ *     * 0 - entry never ages (all permanent)
+ *     * 1 - entry disappears (no persistence)
+ *
+ *   The default value is (300 * USER_HZ).
+ *
+ * @IFLA_BR_STP_STATE
+ *   Turn spanning tree protocol on (*IFLA_BR_STP_STATE* > 0) or off
+ *   (*IFLA_BR_STP_STATE* == 0) for this bridge.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_PRIORITY
+ *   Set this bridge's spanning tree priority, used during STP root bridge
+ *   election.
+ *
+ *   The valid values are between 0 and 65535.
+ *
+ * @IFLA_BR_VLAN_FILTERING
+ *   Turn VLAN filtering on (*IFLA_BR_VLAN_FILTERING* > 0) or off
+ *   (*IFLA_BR_VLAN_FILTERING* == 0). When disabled, the bridge will not
+ *   consider the VLAN tag when handling packets.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_VLAN_PROTOCOL
+ *   Set the protocol used for VLAN filtering.
+ *
+ *   The valid values are 0x8100(802.1Q) or 0x88A8(802.1AD). The default value
+ *   is 0x8100(802.1Q).
+ *
+ * @IFLA_BR_GROUP_FWD_MASK
+ *   The group forwarding mask. This is the bitmask that is applied to
+ *   decide whether to forward incoming frames destined to link-local
+ *   addresses (of the form 01:80:C2:00:00:0X).
+ *
+ *   The default value is 0, which means the bridge does not forward any
+ *   link-local frames coming on this port.
+ *
+ * @IFLA_BR_ROOT_ID
+ *   The bridge root id, read only.
+ *
+ * @IFLA_BR_BRIDGE_ID
+ *   The bridge id, read only.
+ *
+ * @IFLA_BR_ROOT_PORT
+ *   The bridge root port, read only.
+ *
+ * @IFLA_BR_ROOT_PATH_COST
+ *   The bridge root path cost, read only.
+ *
+ * @IFLA_BR_TOPOLOGY_CHANGE
+ *   The bridge topology change, read only.
+ *
+ * @IFLA_BR_TOPOLOGY_CHANGE_DETECTED
+ *   The bridge topology change detected, read only.
+ *
+ * @IFLA_BR_HELLO_TIMER
+ *   The bridge hello timer, read only.
+ *
+ * @IFLA_BR_TCN_TIMER
+ *   The bridge tcn timer, read only.
+ *
+ * @IFLA_BR_TOPOLOGY_CHANGE_TIMER
+ *   The bridge topology change timer, read only.
+ *
+ * @IFLA_BR_GC_TIMER
+ *   The bridge gc timer, read only.
+ *
+ * @IFLA_BR_GROUP_ADDR
+ *   Set the MAC address of the multicast group this bridge uses for STP.
+ *   The address must be a link-local address in standard Ethernet MAC address
+ *   format. It is an address of the form 01:80:C2:00:00:0X, with X in [0, 4..f].
+ *
+ *   The default value is 0.
+ *
+ * @IFLA_BR_FDB_FLUSH
+ *   Flush bridge's fdb dynamic entries.
+ *
+ * @IFLA_BR_MCAST_ROUTER
+ *   Set bridge's multicast router if IGMP snooping is enabled.
+ *   The valid values are:
+ *
+ *     * 0 - disabled.
+ *     * 1 - automatic (queried).
+ *     * 2 - permanently enabled.
+ *
+ *   The default value is 1.
+ *
+ * @IFLA_BR_MCAST_SNOOPING
+ *   Turn multicast snooping on (*IFLA_BR_MCAST_SNOOPING* > 0) or off
+ *   (*IFLA_BR_MCAST_SNOOPING* == 0).
+ *
+ *   The default value is 1.
+ *
+ * @IFLA_BR_MCAST_QUERY_USE_IFADDR
+ *   If enabled use the bridge's own IP address as source address for IGMP
+ *   queries (*IFLA_BR_MCAST_QUERY_USE_IFADDR* > 0) or the default of 0.0.0.0
+ *   (*IFLA_BR_MCAST_QUERY_USE_IFADDR* == 0).
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_MCAST_QUERIER
+ *   Enable (*IFLA_BR_MULTICAST_QUERIER* > 0) or disable
+ *   (*IFLA_BR_MULTICAST_QUERIER* == 0) IGMP querier, ie sending of multicast
+ *   queries by the bridge.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_MCAST_HASH_ELASTICITY
+ *   Set multicast database hash elasticity, It is the maximum chain length in
+ *   the multicast hash table. This attribute is *deprecated* and the value
+ *   is always 16.
+ *
+ * @IFLA_BR_MCAST_HASH_MAX
+ *   Set maximum size of the multicast hash table
+ *
+ *   The default value is 4096, the value must be a power of 2.
+ *
+ * @IFLA_BR_MCAST_LAST_MEMBER_CNT
+ *   The Last Member Query Count is the number of Group-Specific Queries
+ *   sent before the router assumes there are no local members. The Last
+ *   Member Query Count is also the number of Group-and-Source-Specific
+ *   Queries sent before the router assumes there are no listeners for a
+ *   particular source.
+ *
+ *   The default value is 2.
+ *
+ * @IFLA_BR_MCAST_STARTUP_QUERY_CNT
+ *   The Startup Query Count is the number of Queries sent out on startup,
+ *   separated by the Startup Query Interval.
+ *
+ *   The default value is 2.
+ *
+ * @IFLA_BR_MCAST_LAST_MEMBER_INTVL
+ *   The Last Member Query Interval is the Max Response Time inserted into
+ *   Group-Specific Queries sent in response to Leave Group messages, and
+ *   is also the amount of time between Group-Specific Query messages.
+ *
+ *   The default value is (1 * USER_HZ).
+ *
+ * @IFLA_BR_MCAST_MEMBERSHIP_INTVL
+ *   The interval after which the bridge will leave a group, if no membership
+ *   reports for this group are received.
+ *
+ *   The default value is (260 * USER_HZ).
+ *
+ * @IFLA_BR_MCAST_QUERIER_INTVL
+ *   The interval between queries sent by other routers. if no queries are
+ *   seen after this delay has passed, the bridge will start to send its own
+ *   queries (as if *IFLA_BR_MCAST_QUERIER_INTVL* was enabled).
+ *
+ *   The default value is (255 * USER_HZ).
+ *
+ * @IFLA_BR_MCAST_QUERY_INTVL
+ *   The Query Interval is the interval between General Queries sent by
+ *   the Querier.
+ *
+ *   The default value is (125 * USER_HZ). The minimum value is (1 * USER_HZ).
+ *
+ * @IFLA_BR_MCAST_QUERY_RESPONSE_INTVL
+ *   The Max Response Time used to calculate the Max Resp Code inserted
+ *   into the periodic General Queries.
+ *
+ *   The default value is (10 * USER_HZ).
+ *
+ * @IFLA_BR_MCAST_STARTUP_QUERY_INTVL
+ *   The interval between queries in the startup phase.
+ *
+ *   The default value is (125 * USER_HZ) / 4. The minimum value is (1 * USER_HZ).
+ *
+ * @IFLA_BR_NF_CALL_IPTABLES
+ *   Enable (*NF_CALL_IPTABLES* > 0) or disable (*NF_CALL_IPTABLES* == 0)
+ *   iptables hooks on the bridge.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_NF_CALL_IP6TABLES
+ *   Enable (*NF_CALL_IP6TABLES* > 0) or disable (*NF_CALL_IP6TABLES* == 0)
+ *   ip6tables hooks on the bridge.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_NF_CALL_ARPTABLES
+ *   Enable (*NF_CALL_ARPTABLES* > 0) or disable (*NF_CALL_ARPTABLES* == 0)
+ *   arptables hooks on the bridge.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_VLAN_DEFAULT_PVID
+ *   VLAN ID applied to untagged and priority-tagged incoming packets.
+ *
+ *   The default value is 1. Setting to the special value 0 makes all ports of
+ *   this bridge not have a PVID by default, which means that they will
+ *   not accept VLAN-untagged traffic.
+ *
+ * @IFLA_BR_PAD
+ *   Bridge attribute padding type for netlink message.
+ *
+ * @IFLA_BR_VLAN_STATS_ENABLED
+ *   Enable (*IFLA_BR_VLAN_STATS_ENABLED* == 1) or disable
+ *   (*IFLA_BR_VLAN_STATS_ENABLED* == 0) per-VLAN stats accounting.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_MCAST_STATS_ENABLED
+ *   Enable (*IFLA_BR_MCAST_STATS_ENABLED* > 0) or disable
+ *   (*IFLA_BR_MCAST_STATS_ENABLED* == 0) multicast (IGMP/MLD) stats
+ *   accounting.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_MCAST_IGMP_VERSION
+ *   Set the IGMP version.
+ *
+ *   The valid values are 2 and 3. The default value is 2.
+ *
+ * @IFLA_BR_MCAST_MLD_VERSION
+ *   Set the MLD version.
+ *
+ *   The valid values are 1 and 2. The default value is 1.
+ *
+ * @IFLA_BR_VLAN_STATS_PER_PORT
+ *   Enable (*IFLA_BR_VLAN_STATS_PER_PORT* == 1) or disable
+ *   (*IFLA_BR_VLAN_STATS_PER_PORT* == 0) per-VLAN per-port stats accounting.
+ *   Can be changed only when there are no port VLANs configured.
+ *
+ *   The default value is 0 (disabled).
+ *
+ * @IFLA_BR_MULTI_BOOLOPT
+ *   The multi_boolopt is used to control new boolean options to avoid adding
+ *   new netlink attributes. You can look at ``enum br_boolopt_id`` for those
+ *   options.
+ *
+ * @IFLA_BR_MCAST_QUERIER_STATE
+ *   Bridge mcast querier states, read only.
+ *
+ * @IFLA_BR_FDB_N_LEARNED
+ *   The number of dynamically learned FDB entries for the current bridge,
+ *   read only.
+ *
+ * @IFLA_BR_FDB_MAX_LEARNED
+ *   Set the number of max dynamically learned FDB entries for the current
+ *   bridge.
+ */
 enum {
 	IFLA_BR_UNSPEC,
 	IFLA_BR_FORWARD_DELAY,
-- 
cgit v1.2.3


From 8c4bafdb01cc7809903aced4981f563e3708ea37 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Fri, 1 Dec 2023 16:19:43 +0800
Subject: net: bridge: add document for IFLA_BRPORT enum

Add document for IFLA_BRPORT enum so we can use it in
Documentation/networking/bridge.rst.

Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/uapi/linux/if_link.h | 241 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 241 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index a5f873c85a72..ab9bcff96e4d 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -802,11 +802,252 @@ struct ifla_bridge_id {
 	__u8	addr[6]; /* ETH_ALEN */
 };
 
+/**
+ * DOC: Bridge mode enum definition
+ *
+ * @BRIDGE_MODE_HAIRPIN
+ *   Controls whether traffic may be sent back out of the port on which it
+ *   was received. This option is also called reflective relay mode, and is
+ *   used to support basic VEPA (Virtual Ethernet Port Aggregator)
+ *   capabilities. By default, this flag is turned off and the bridge will
+ *   not forward traffic back out of the receiving port.
+ */
 enum {
 	BRIDGE_MODE_UNSPEC,
 	BRIDGE_MODE_HAIRPIN,
 };
 
+/**
+ * DOC: Bridge port enum definition
+ *
+ * @IFLA_BRPORT_STATE
+ *   The operation state of the port. Here are the valid values.
+ *
+ *     * 0 - port is in STP *DISABLED* state. Make this port completely
+ *       inactive for STP. This is also called BPDU filter and could be used
+ *       to disable STP on an untrusted port, like a leaf virtual device.
+ *       The traffic forwarding is also stopped on this port.
+ *     * 1 - port is in STP *LISTENING* state. Only valid if STP is enabled
+ *       on the bridge. In this state the port listens for STP BPDUs and
+ *       drops all other traffic frames.
+ *     * 2 - port is in STP *LEARNING* state. Only valid if STP is enabled on
+ *       the bridge. In this state the port will accept traffic only for the
+ *       purpose of updating MAC address tables.
+ *     * 3 - port is in STP *FORWARDING* state. Port is fully active.
+ *     * 4 - port is in STP *BLOCKING* state. Only valid if STP is enabled on
+ *       the bridge. This state is used during the STP election process.
+ *       In this state, port will only process STP BPDUs.
+ *
+ * @IFLA_BRPORT_PRIORITY
+ *   The STP port priority. The valid values are between 0 and 255.
+ *
+ * @IFLA_BRPORT_COST
+ *   The STP path cost of the port. The valid values are between 1 and 65535.
+ *
+ * @IFLA_BRPORT_MODE
+ *   Set the bridge port mode. See *BRIDGE_MODE_HAIRPIN* for more details.
+ *
+ * @IFLA_BRPORT_GUARD
+ *   Controls whether STP BPDUs will be processed by the bridge port. By
+ *   default, the flag is turned off to allow BPDU processing. Turning this
+ *   flag on will disable the bridge port if a STP BPDU packet is received.
+ *
+ *   If the bridge has Spanning Tree enabled, hostile devices on the network
+ *   may send BPDU on a port and cause network failure. Setting *guard on*
+ *   will detect and stop this by disabling the port. The port will be
+ *   restarted if the link is brought down, or removed and reattached.
+ *
+ * @IFLA_BRPORT_PROTECT
+ *   Controls whether a given port is allowed to become a root port or not.
+ *   Only used when STP is enabled on the bridge. By default the flag is off.
+ *
+ *   This feature is also called root port guard. If BPDU is received from a
+ *   leaf (edge) port, it should not be elected as root port. This could
+ *   be used if using STP on a bridge and the downstream bridges are not fully
+ *   trusted; this prevents a hostile guest from rerouting traffic.
+ *
+ * @IFLA_BRPORT_FAST_LEAVE
+ *   This flag allows the bridge to immediately stop multicast traffic
+ *   forwarding on a port that receives an IGMP Leave message. It is only used
+ *   when IGMP snooping is enabled on the bridge. By default the flag is off.
+ *
+ * @IFLA_BRPORT_LEARNING
+ *   Controls whether a given port will learn *source* MAC addresses from
+ *   received traffic or not. Also controls whether dynamic FDB entries
+ *   (which can also be added by software) will be refreshed by incoming
+ *   traffic. By default this flag is on.
+ *
+ * @IFLA_BRPORT_UNICAST_FLOOD
+ *   Controls whether unicast traffic for which there is no FDB entry will
+ *   be flooded towards this port. By default this flag is on.
+ *
+ * @IFLA_BRPORT_PROXYARP
+ *   Enable proxy ARP on this port.
+ *
+ * @IFLA_BRPORT_LEARNING_SYNC
+ *   Controls whether a given port will sync MAC addresses learned on device
+ *   port to bridge FDB.
+ *
+ * @IFLA_BRPORT_PROXYARP_WIFI
+ *   Enable proxy ARP on this port which meets extended requirements by
+ *   IEEE 802.11 and Hotspot 2.0 specifications.
+ *
+ * @IFLA_BRPORT_ROOT_ID
+ *
+ * @IFLA_BRPORT_BRIDGE_ID
+ *
+ * @IFLA_BRPORT_DESIGNATED_PORT
+ *
+ * @IFLA_BRPORT_DESIGNATED_COST
+ *
+ * @IFLA_BRPORT_ID
+ *
+ * @IFLA_BRPORT_NO
+ *
+ * @IFLA_BRPORT_TOPOLOGY_CHANGE_ACK
+ *
+ * @IFLA_BRPORT_CONFIG_PENDING
+ *
+ * @IFLA_BRPORT_MESSAGE_AGE_TIMER
+ *
+ * @IFLA_BRPORT_FORWARD_DELAY_TIMER
+ *
+ * @IFLA_BRPORT_HOLD_TIMER
+ *
+ * @IFLA_BRPORT_FLUSH
+ *   Flush bridge ports' fdb dynamic entries.
+ *
+ * @IFLA_BRPORT_MULTICAST_ROUTER
+ *   Configure the port's multicast router presence. A port with
+ *   a multicast router will receive all multicast traffic.
+ *   The valid values are:
+ *
+ *     * 0 disable multicast routers on this port
+ *     * 1 let the system detect the presence of routers (default)
+ *     * 2 permanently enable multicast traffic forwarding on this port
+ *     * 3 enable multicast routers temporarily on this port, not depending
+ *         on incoming queries.
+ *
+ * @IFLA_BRPORT_PAD
+ *
+ * @IFLA_BRPORT_MCAST_FLOOD
+ *   Controls whether a given port will flood multicast traffic for which
+ *   there is no MDB entry. By default this flag is on.
+ *
+ * @IFLA_BRPORT_MCAST_TO_UCAST
+ *   Controls whether a given port will replicate packets using unicast
+ *   instead of multicast. By default this flag is off.
+ *
+ *   This is done by copying the packet per host and changing the multicast
+ *   destination MAC to a unicast one accordingly.
+ *
+ *   *mcast_to_unicast* works on top of the multicast snooping feature of the
+ *   bridge. Which means unicast copies are only delivered to hosts which
+ *   are interested in unicast and signaled this via IGMP/MLD reports previously.
+ *
+ *   This feature is intended for interface types which have a more reliable
+ *   and/or efficient way to deliver unicast packets than broadcast ones
+ *   (e.g. WiFi).
+ *
+ *   However, it should only be enabled on interfaces where no IGMPv2/MLDv1
+ *   report suppression takes place. IGMP/MLD report suppression issue is
+ *   usually overcome by the network daemon (supplicant) enabling AP isolation
+ *   and by that separating all STAs.
+ *
+ *   Delivery of STA-to-STA IP multicast is made possible again by enabling
+ *   and utilizing the bridge hairpin mode, which considers the incoming port
+ *   as a potential outgoing port, too (see *BRIDGE_MODE_HAIRPIN* option).
+ *   Hairpin mode is performed after multicast snooping, therefore leading
+ *   to only deliver reports to STAs running a multicast router.
+ *
+ * @IFLA_BRPORT_VLAN_TUNNEL
+ *   Controls whether vlan to tunnel mapping is enabled on the port.
+ *   By default this flag is off.
+ *
+ * @IFLA_BRPORT_BCAST_FLOOD
+ *   Controls flooding of broadcast traffic on the given port. By default
+ *   this flag is on.
+ *
+ * @IFLA_BRPORT_GROUP_FWD_MASK
+ *   Set the group forward mask. This is a bitmask that is applied to
+ *   decide whether to forward incoming frames destined to link-local
+ *   addresses. The addresses of the form are 01:80:C2:00:00:0X (defaults
+ *   to 0, which means the bridge does not forward any link-local frames
+ *   coming on this port).
+ *
+ * @IFLA_BRPORT_NEIGH_SUPPRESS
+ *   Controls whether neighbor discovery (arp and nd) proxy and suppression
+ *   is enabled on the port. By default this flag is off.
+ *
+ * @IFLA_BRPORT_ISOLATED
+ *   Controls whether a given port will be isolated, which means it will be
+ *   able to communicate with non-isolated ports only. By default this
+ *   flag is off.
+ *
+ * @IFLA_BRPORT_BACKUP_PORT
+ *   Set a backup port. If the port loses carrier all traffic will be
+ *   redirected to the configured backup port. Set the value to 0 to disable
+ *   it.
+ *
+ * @IFLA_BRPORT_MRP_RING_OPEN
+ *
+ * @IFLA_BRPORT_MRP_IN_OPEN
+ *
+ * @IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT
+ *   The number of per-port EHT hosts limit. The default value is 512.
+ *   Setting to 0 is not allowed.
+ *
+ * @IFLA_BRPORT_MCAST_EHT_HOSTS_CNT
+ *   The current number of tracked hosts, read only.
+ *
+ * @IFLA_BRPORT_LOCKED
+ *   Controls whether a port will be locked, meaning that hosts behind the
+ *   port will not be able to communicate through the port unless an FDB
+ *   entry with the unit's MAC address is in the FDB. The common use case is
+ *   that hosts are allowed access through authentication with the IEEE 802.1X
+ *   protocol or based on whitelists. By default this flag is off.
+ *
+ *   Please note that secure 802.1X deployments should always use the
+ *   *BR_BOOLOPT_NO_LL_LEARN* flag, to not permit the bridge to populate its
+ *   FDB based on link-local (EAPOL) traffic received on the port.
+ *
+ * @IFLA_BRPORT_MAB
+ *   Controls whether a port will use MAC Authentication Bypass (MAB), a
+ *   technique through which select MAC addresses may be allowed on a locked
+ *   port, without using 802.1X authentication. Packets with an unknown source
+ *   MAC address generates a "locked" FDB entry on the incoming bridge port.
+ *   The common use case is for user space to react to these bridge FDB
+ *   notifications and optionally replace the locked FDB entry with a normal
+ *   one, allowing traffic to pass for whitelisted MAC addresses.
+ *
+ *   Setting this flag also requires *IFLA_BRPORT_LOCKED* and
+ *   *IFLA_BRPORT_LEARNING*. *IFLA_BRPORT_LOCKED* ensures that unauthorized
+ *   data packets are dropped, and *IFLA_BRPORT_LEARNING* allows the dynamic
+ *   FDB entries installed by user space (as replacements for the locked FDB
+ *   entries) to be refreshed and/or aged out.
+ *
+ * @IFLA_BRPORT_MCAST_N_GROUPS
+ *
+ * @IFLA_BRPORT_MCAST_MAX_GROUPS
+ *   Sets the maximum number of MDB entries that can be registered for a
+ *   given port. Attempts to register more MDB entries at the port than this
+ *   limit allows will be rejected, whether they are done through netlink
+ *   (e.g. the bridge tool), or IGMP or MLD membership reports. Setting a
+ *   limit of 0 disables the limit. The default value is 0.
+ *
+ * @IFLA_BRPORT_NEIGH_VLAN_SUPPRESS
+ *   Controls whether neighbor discovery (arp and nd) proxy and suppression is
+ *   enabled for a given port. By default this flag is off.
+ *
+ *   Note that this option only takes effect when *IFLA_BRPORT_NEIGH_SUPPRESS*
+ *   is enabled for a given port.
+ *
+ * @IFLA_BRPORT_BACKUP_NHID
+ *   The FDB nexthop object ID to attach to packets being redirected to a
+ *   backup port that has VLAN tunnel mapping enabled (via the
+ *   *IFLA_BRPORT_VLAN_TUNNEL* option). Setting a value of 0 (default) has
+ *   the effect of not attaching any ID.
+ */
 enum {
 	IFLA_BRPORT_UNSPEC,
 	IFLA_BRPORT_STATE,	/* Spanning tree state     */
-- 
cgit v1.2.3


From 70da1d01edf6da3fde1df98b2125a77083a0fb82 Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Mon, 2 Oct 2023 16:36:55 +0200
Subject: cpu/hotplug: remove CPUHP_SLAB_PREPARE hooks

The CPUHP_SLAB_PREPARE hooks are only used by SLAB which is removed.
SLUB defines them as NULL, so we can remove those altogether.

Acked-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: David Rientjes <rientjes@google.com>
Tested-by: David Rientjes <rientjes@google.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
 include/linux/cpuhotplug.h | 1 -
 include/linux/slab.h       | 8 --------
 kernel/cpu.c               | 5 -----
 3 files changed, 14 deletions(-)

(limited to 'include')

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index d305db70674b..07cb8f7030b6 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -108,7 +108,6 @@ enum cpuhp_state {
 	CPUHP_X2APIC_PREPARE,
 	CPUHP_SMPCFD_PREPARE,
 	CPUHP_RELAY_PREPARE,
-	CPUHP_SLAB_PREPARE,
 	CPUHP_MD_RAID5_PREPARE,
 	CPUHP_RCUTREE_PREP,
 	CPUHP_CPUIDLE_COUPLED_PREPARE,
diff --git a/include/linux/slab.h b/include/linux/slab.h
index d6d6ffeeb9a2..34e43cddc520 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -788,12 +788,4 @@ size_t kmalloc_size_roundup(size_t size);
 
 void __init kmem_cache_init_late(void);
 
-#if defined(CONFIG_SMP) && defined(CONFIG_SLAB)
-int slab_prepare_cpu(unsigned int cpu);
-int slab_dead_cpu(unsigned int cpu);
-#else
-#define slab_prepare_cpu	NULL
-#define slab_dead_cpu		NULL
-#endif
-
 #endif	/* _LINUX_SLAB_H */
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 9e4c6780adde..530b026d95a1 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -2125,11 +2125,6 @@ static struct cpuhp_step cpuhp_hp_states[] = {
 		.startup.single		= relay_prepare_cpu,
 		.teardown.single	= NULL,
 	},
-	[CPUHP_SLAB_PREPARE] = {
-		.name			= "slab:prepare",
-		.startup.single		= slab_prepare_cpu,
-		.teardown.single	= slab_dead_cpu,
-	},
 	[CPUHP_RCUTREE_PREP] = {
 		.name			= "RCU/tree:prepare",
 		.startup.single		= rcutree_prepare_cpu,
-- 
cgit v1.2.3


From a9e0b9f27266d46ed6e73aac8d0844602cd0cb93 Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Mon, 2 Oct 2023 17:43:38 +0200
Subject: mm/slab: remove CONFIG_SLAB code from slab common code

In slab_common.c and slab.h headers, we can now remove all code behind
CONFIG_SLAB and CONFIG_DEBUG_SLAB ifdefs, and remove all CONFIG_SLUB
ifdefs.

Reviewed-by: Kees Cook <keescook@chromium.org>
Acked-by: David Rientjes <rientjes@google.com>
Tested-by: David Rientjes <rientjes@google.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
 include/linux/slab.h | 14 ++---------
 mm/slab.h            | 69 ++++------------------------------------------------
 mm/slab_common.c     | 22 ++---------------
 3 files changed, 9 insertions(+), 96 deletions(-)

(limited to 'include')

diff --git a/include/linux/slab.h b/include/linux/slab.h
index 34e43cddc520..b2015d0e01ad 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -24,7 +24,7 @@
 
 /*
  * Flags to pass to kmem_cache_create().
- * The ones marked DEBUG are only valid if CONFIG_DEBUG_SLAB is set.
+ * The ones marked DEBUG need CONFIG_SLUB_DEBUG enabled, otherwise are no-op
  */
 /* DEBUG: Perform (expensive) checks on alloc/free */
 #define SLAB_CONSISTENCY_CHECKS	((slab_flags_t __force)0x00000100U)
@@ -302,25 +302,15 @@ static inline unsigned int arch_slab_minalign(void)
  * Kmalloc array related definitions
  */
 
-#ifdef CONFIG_SLAB
 /*
- * SLAB and SLUB directly allocates requests fitting in to an order-1 page
+ * SLUB directly allocates requests fitting in to an order-1 page
  * (PAGE_SIZE*2).  Larger requests are passed to the page allocator.
  */
 #define KMALLOC_SHIFT_HIGH	(PAGE_SHIFT + 1)
 #define KMALLOC_SHIFT_MAX	(MAX_ORDER + PAGE_SHIFT)
 #ifndef KMALLOC_SHIFT_LOW
-#define KMALLOC_SHIFT_LOW	5
-#endif
-#endif
-
-#ifdef CONFIG_SLUB
-#define KMALLOC_SHIFT_HIGH	(PAGE_SHIFT + 1)
-#define KMALLOC_SHIFT_MAX	(MAX_ORDER + PAGE_SHIFT)
-#ifndef KMALLOC_SHIFT_LOW
 #define KMALLOC_SHIFT_LOW	3
 #endif
-#endif
 
 /* Maximum allocatable size */
 #define KMALLOC_MAX_SIZE	(1UL << KMALLOC_SHIFT_MAX)
diff --git a/mm/slab.h b/mm/slab.h
index 3d07fb428393..014c36ea51fa 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -42,21 +42,6 @@ typedef union {
 struct slab {
 	unsigned long __page_flags;
 
-#if defined(CONFIG_SLAB)
-
-	struct kmem_cache *slab_cache;
-	union {
-		struct {
-			struct list_head slab_list;
-			void *freelist;	/* array of free object indexes */
-			void *s_mem;	/* first object */
-		};
-		struct rcu_head rcu_head;
-	};
-	unsigned int active;
-
-#elif defined(CONFIG_SLUB)
-
 	struct kmem_cache *slab_cache;
 	union {
 		struct {
@@ -91,10 +76,6 @@ struct slab {
 	};
 	unsigned int __unused;
 
-#else
-#error "Unexpected slab allocator configured"
-#endif
-
 	atomic_t __page_refcount;
 #ifdef CONFIG_MEMCG
 	unsigned long memcg_data;
@@ -111,7 +92,7 @@ SLAB_MATCH(memcg_data, memcg_data);
 #endif
 #undef SLAB_MATCH
 static_assert(sizeof(struct slab) <= sizeof(struct page));
-#if defined(system_has_freelist_aba) && defined(CONFIG_SLUB)
+#if defined(system_has_freelist_aba)
 static_assert(IS_ALIGNED(offsetof(struct slab, freelist), sizeof(freelist_aba_t)));
 #endif
 
@@ -228,13 +209,7 @@ static inline size_t slab_size(const struct slab *slab)
 	return PAGE_SIZE << slab_order(slab);
 }
 
-#ifdef CONFIG_SLAB
-#include <linux/slab_def.h>
-#endif
-
-#ifdef CONFIG_SLUB
 #include <linux/slub_def.h>
-#endif
 
 #include <linux/memcontrol.h>
 #include <linux/fault-inject.h>
@@ -320,26 +295,16 @@ static inline bool is_kmalloc_cache(struct kmem_cache *s)
 			 SLAB_CACHE_DMA32 | SLAB_PANIC | \
 			 SLAB_TYPESAFE_BY_RCU | SLAB_DEBUG_OBJECTS )
 
-#if defined(CONFIG_DEBUG_SLAB)
-#define SLAB_DEBUG_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER)
-#elif defined(CONFIG_SLUB_DEBUG)
+#ifdef CONFIG_SLUB_DEBUG
 #define SLAB_DEBUG_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \
 			  SLAB_TRACE | SLAB_CONSISTENCY_CHECKS)
 #else
 #define SLAB_DEBUG_FLAGS (0)
 #endif
 
-#if defined(CONFIG_SLAB)
-#define SLAB_CACHE_FLAGS (SLAB_MEM_SPREAD | SLAB_NOLEAKTRACE | \
-			  SLAB_RECLAIM_ACCOUNT | SLAB_TEMPORARY | \
-			  SLAB_ACCOUNT | SLAB_NO_MERGE)
-#elif defined(CONFIG_SLUB)
 #define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE | SLAB_RECLAIM_ACCOUNT | \
 			  SLAB_TEMPORARY | SLAB_ACCOUNT | \
 			  SLAB_NO_USER_FLAGS | SLAB_KMALLOC | SLAB_NO_MERGE)
-#else
-#define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE)
-#endif
 
 /* Common flags available with current configuration */
 #define CACHE_CREATE_MASK (SLAB_CORE_FLAGS | SLAB_DEBUG_FLAGS | SLAB_CACHE_FLAGS)
@@ -672,18 +637,14 @@ size_t __ksize(const void *objp);
 
 static inline size_t slab_ksize(const struct kmem_cache *s)
 {
-#ifndef CONFIG_SLUB
-	return s->object_size;
-
-#else /* CONFIG_SLUB */
-# ifdef CONFIG_SLUB_DEBUG
+#ifdef CONFIG_SLUB_DEBUG
 	/*
 	 * Debugging requires use of the padding between object
 	 * and whatever may come after it.
 	 */
 	if (s->flags & (SLAB_RED_ZONE | SLAB_POISON))
 		return s->object_size;
-# endif
+#endif
 	if (s->flags & SLAB_KASAN)
 		return s->object_size;
 	/*
@@ -697,7 +658,6 @@ static inline size_t slab_ksize(const struct kmem_cache *s)
 	 * Else we can use all the padding etc for the allocation
 	 */
 	return s->size;
-#endif
 }
 
 static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s,
@@ -775,23 +735,6 @@ static inline void slab_post_alloc_hook(struct kmem_cache *s,
  * The slab lists for all objects.
  */
 struct kmem_cache_node {
-#ifdef CONFIG_SLAB
-	raw_spinlock_t list_lock;
-	struct list_head slabs_partial;	/* partial list first, better asm code */
-	struct list_head slabs_full;
-	struct list_head slabs_free;
-	unsigned long total_slabs;	/* length of all slab lists */
-	unsigned long free_slabs;	/* length of free slab list only */
-	unsigned long free_objects;
-	unsigned int free_limit;
-	unsigned int colour_next;	/* Per-node cache coloring */
-	struct array_cache *shared;	/* shared per node */
-	struct alien_cache **alien;	/* on other nodes */
-	unsigned long next_reap;	/* updated without locking */
-	int free_touched;		/* updated without locking */
-#endif
-
-#ifdef CONFIG_SLUB
 	spinlock_t list_lock;
 	unsigned long nr_partial;
 	struct list_head partial;
@@ -800,8 +743,6 @@ struct kmem_cache_node {
 	atomic_long_t total_objects;
 	struct list_head full;
 #endif
-#endif
-
 };
 
 static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
@@ -818,7 +759,7 @@ static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
 		 if ((__n = get_node(__s, __node)))
 
 
-#if defined(CONFIG_SLAB) || defined(CONFIG_SLUB_DEBUG)
+#ifdef CONFIG_SLUB_DEBUG
 void dump_unreclaimable_slab(void);
 #else
 static inline void dump_unreclaimable_slab(void)
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 8d431193c273..63b8411db7ce 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -71,10 +71,8 @@ static int __init setup_slab_merge(char *str)
 	return 1;
 }
 
-#ifdef CONFIG_SLUB
 __setup_param("slub_nomerge", slub_nomerge, setup_slab_nomerge, 0);
 __setup_param("slub_merge", slub_merge, setup_slab_merge, 0);
-#endif
 
 __setup("slab_nomerge", setup_slab_nomerge);
 __setup("slab_merge", setup_slab_merge);
@@ -197,10 +195,6 @@ struct kmem_cache *find_mergeable(unsigned int size, unsigned int align,
 		if (s->size - size >= sizeof(void *))
 			continue;
 
-		if (IS_ENABLED(CONFIG_SLAB) && align &&
-			(align > s->align || s->align % align))
-			continue;
-
 		return s;
 	}
 	return NULL;
@@ -1222,12 +1216,8 @@ void cache_random_seq_destroy(struct kmem_cache *cachep)
 }
 #endif /* CONFIG_SLAB_FREELIST_RANDOM */
 
-#if defined(CONFIG_SLAB) || defined(CONFIG_SLUB_DEBUG)
-#ifdef CONFIG_SLAB
-#define SLABINFO_RIGHTS (0600)
-#else
+#ifdef CONFIG_SLUB_DEBUG
 #define SLABINFO_RIGHTS (0400)
-#endif
 
 static void print_slabinfo_header(struct seq_file *m)
 {
@@ -1235,18 +1225,10 @@ static void print_slabinfo_header(struct seq_file *m)
 	 * Output format version, so at least we can change it
 	 * without _too_ many complaints.
 	 */
-#ifdef CONFIG_DEBUG_SLAB
-	seq_puts(m, "slabinfo - version: 2.1 (statistics)\n");
-#else
 	seq_puts(m, "slabinfo - version: 2.1\n");
-#endif
 	seq_puts(m, "# name            <active_objs> <num_objs> <objsize> <objperslab> <pagesperslab>");
 	seq_puts(m, " : tunables <limit> <batchcount> <sharedfactor>");
 	seq_puts(m, " : slabdata <active_slabs> <num_slabs> <sharedavail>");
-#ifdef CONFIG_DEBUG_SLAB
-	seq_puts(m, " : globalstat <listallocs> <maxobjs> <grown> <reaped> <error> <maxfreeable> <nodeallocs> <remotefrees> <alienoverflow>");
-	seq_puts(m, " : cpustat <allochit> <allocmiss> <freehit> <freemiss>");
-#endif
 	seq_putc(m, '\n');
 }
 
@@ -1370,7 +1352,7 @@ static int __init slab_proc_init(void)
 }
 module_init(slab_proc_init);
 
-#endif /* CONFIG_SLAB || CONFIG_SLUB_DEBUG */
+#endif /* CONFIG_SLUB_DEBUG */
 
 static __always_inline __realloc_size(2) void *
 __do_krealloc(const void *p, size_t new_size, gfp_t flags)
-- 
cgit v1.2.3


From 6ac805d13870925c787a28e3fe5cc73610cacd03 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Mon, 4 Dec 2023 10:47:49 -0700
Subject: iov_iter: remove unused 'iov' argument from import_single_range()

It is entirely unused, just get rid of it.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
Link: https://lore.kernel.org/r/20231204174827.1258875-2-axboe@kernel.dk
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 drivers/block/ublk_drv.c         | 6 ++----
 drivers/char/random.c            | 6 ++----
 fs/aio.c                         | 2 +-
 include/linux/uio.h              | 2 +-
 kernel/trace/trace_events_user.c | 3 +--
 lib/iov_iter.c                   | 2 +-
 net/ipv4/tcp.c                   | 6 ++----
 net/socket.c                     | 6 ++----
 security/keys/keyctl.c           | 3 +--
 9 files changed, 13 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 83600b45e12a..5656b0a1233d 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -893,11 +893,10 @@ static int ublk_map_io(const struct ublk_queue *ubq, const struct request *req,
 	 */
 	if (ublk_need_map_req(req)) {
 		struct iov_iter iter;
-		struct iovec iov;
 		const int dir = ITER_DEST;
 
 		import_single_range(dir, u64_to_user_ptr(io->addr), rq_bytes,
-				&iov, &iter);
+					&iter);
 
 		return ublk_copy_user_pages(req, 0, &iter, dir);
 	}
@@ -915,13 +914,12 @@ static int ublk_unmap_io(const struct ublk_queue *ubq,
 
 	if (ublk_need_unmap_req(req)) {
 		struct iov_iter iter;
-		struct iovec iov;
 		const int dir = ITER_SOURCE;
 
 		WARN_ON_ONCE(io->res > rq_bytes);
 
 		import_single_range(dir, u64_to_user_ptr(io->addr), io->res,
-				&iov, &iter);
+					&iter);
 		return ublk_copy_user_pages(req, 0, &iter, dir);
 	}
 	return rq_bytes;
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 4a9c79391dee..e79ae238b30d 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -1364,7 +1364,6 @@ static void __cold try_to_generate_entropy(void)
 SYSCALL_DEFINE3(getrandom, char __user *, ubuf, size_t, len, unsigned int, flags)
 {
 	struct iov_iter iter;
-	struct iovec iov;
 	int ret;
 
 	if (flags & ~(GRND_NONBLOCK | GRND_RANDOM | GRND_INSECURE))
@@ -1385,7 +1384,7 @@ SYSCALL_DEFINE3(getrandom, char __user *, ubuf, size_t, len, unsigned int, flags
 			return ret;
 	}
 
-	ret = import_single_range(ITER_DEST, ubuf, len, &iov, &iter);
+	ret = import_single_range(ITER_DEST, ubuf, len, &iter);
 	if (unlikely(ret))
 		return ret;
 	return get_random_bytes_user(&iter);
@@ -1491,7 +1490,6 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
 		return 0;
 	case RNDADDENTROPY: {
 		struct iov_iter iter;
-		struct iovec iov;
 		ssize_t ret;
 		int len;
 
@@ -1503,7 +1501,7 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
 			return -EINVAL;
 		if (get_user(len, p++))
 			return -EFAULT;
-		ret = import_single_range(ITER_SOURCE, p, len, &iov, &iter);
+		ret = import_single_range(ITER_SOURCE, p, len, &iter);
 		if (unlikely(ret))
 			return ret;
 		ret = write_pool_user(&iter);
diff --git a/fs/aio.c b/fs/aio.c
index f8589caef9c1..251eeaef7fbf 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1498,7 +1498,7 @@ static ssize_t aio_setup_rw(int rw, const struct iocb *iocb,
 	size_t len = iocb->aio_nbytes;
 
 	if (!vectored) {
-		ssize_t ret = import_single_range(rw, buf, len, *iovec, iter);
+		ssize_t ret = import_single_range(rw, buf, len, iter);
 		*iovec = NULL;
 		return ret;
 	}
diff --git a/include/linux/uio.h b/include/linux/uio.h
index b6214cbf2a43..bfafd3542fa7 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -348,7 +348,7 @@ ssize_t __import_iovec(int type, const struct iovec __user *uvec,
 		 unsigned nr_segs, unsigned fast_segs, struct iovec **iovp,
 		 struct iov_iter *i, bool compat);
 int import_single_range(int type, void __user *buf, size_t len,
-		 struct iovec *iov, struct iov_iter *i);
+		 struct iov_iter *i);
 int import_ubuf(int type, void __user *buf, size_t len, struct iov_iter *i);
 
 static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction,
diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c
index 9365ce407426..4efc75d90a0d 100644
--- a/kernel/trace/trace_events_user.c
+++ b/kernel/trace/trace_events_user.c
@@ -2177,14 +2177,13 @@ static int user_events_open(struct inode *node, struct file *file)
 static ssize_t user_events_write(struct file *file, const char __user *ubuf,
 				 size_t count, loff_t *ppos)
 {
-	struct iovec iov;
 	struct iov_iter i;
 
 	if (unlikely(*ppos != 0))
 		return -EFAULT;
 
 	if (unlikely(import_single_range(ITER_SOURCE, (char __user *)ubuf,
-					 count, &iov, &i)))
+					 count, &i)))
 		return -EFAULT;
 
 	return user_events_write_core(file, &i);
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index de7d11cf4c63..d60c73354e1f 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -1370,7 +1370,7 @@ ssize_t import_iovec(int type, const struct iovec __user *uvec,
 EXPORT_SYMBOL(import_iovec);
 
 int import_single_range(int rw, void __user *buf, size_t len,
-		 struct iovec *iov, struct iov_iter *i)
+			struct iov_iter *i)
 {
 	if (len > MAX_RW_COUNT)
 		len = MAX_RW_COUNT;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 53bcc17c91e4..57cf3adb191a 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1849,7 +1849,6 @@ static int receive_fallback_to_copy(struct sock *sk,
 {
 	unsigned long copy_address = (unsigned long)zc->copybuf_address;
 	struct msghdr msg = {};
-	struct iovec iov;
 	int err;
 
 	zc->length = 0;
@@ -1859,7 +1858,7 @@ static int receive_fallback_to_copy(struct sock *sk,
 		return -EINVAL;
 
 	err = import_single_range(ITER_DEST, (void __user *)copy_address,
-				  inq, &iov, &msg.msg_iter);
+				  inq, &msg.msg_iter);
 	if (err)
 		return err;
 
@@ -1886,14 +1885,13 @@ static int tcp_copy_straggler_data(struct tcp_zerocopy_receive *zc,
 {
 	unsigned long copy_address = (unsigned long)zc->copybuf_address;
 	struct msghdr msg = {};
-	struct iovec iov;
 	int err;
 
 	if (copy_address != zc->copybuf_address)
 		return -EINVAL;
 
 	err = import_single_range(ITER_DEST, (void __user *)copy_address,
-				  copylen, &iov, &msg.msg_iter);
+				  copylen, &msg.msg_iter);
 	if (err)
 		return err;
 	err = skb_copy_datagram_msg(skb, *offset, &msg, copylen);
diff --git a/net/socket.c b/net/socket.c
index 3379c64217a4..1f0d0e8d0a50 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2161,10 +2161,9 @@ int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags,
 	struct sockaddr_storage address;
 	int err;
 	struct msghdr msg;
-	struct iovec iov;
 	int fput_needed;
 
-	err = import_single_range(ITER_SOURCE, buff, len, &iov, &msg.msg_iter);
+	err = import_single_range(ITER_SOURCE, buff, len, &msg.msg_iter);
 	if (unlikely(err))
 		return err;
 	sock = sockfd_lookup_light(fd, &err, &fput_needed);
@@ -2226,11 +2225,10 @@ int __sys_recvfrom(int fd, void __user *ubuf, size_t size, unsigned int flags,
 		.msg_name = addr ? (struct sockaddr *)&address : NULL,
 	};
 	struct socket *sock;
-	struct iovec iov;
 	int err, err2;
 	int fput_needed;
 
-	err = import_single_range(ITER_DEST, ubuf, size, &iov, &msg.msg_iter);
+	err = import_single_range(ITER_DEST, ubuf, size, &msg.msg_iter);
 	if (unlikely(err))
 		return err;
 	sock = sockfd_lookup_light(fd, &err, &fput_needed);
diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c
index 19be69fa4d05..193df7ca3ca8 100644
--- a/security/keys/keyctl.c
+++ b/security/keys/keyctl.c
@@ -1252,12 +1252,11 @@ long keyctl_instantiate_key(key_serial_t id,
 			    key_serial_t ringid)
 {
 	if (_payload && plen) {
-		struct iovec iov;
 		struct iov_iter from;
 		int ret;
 
 		ret = import_single_range(ITER_SOURCE, (void __user *)_payload, plen,
-					  &iov, &from);
+					  &from);
 		if (unlikely(ret))
 			return ret;
 
-- 
cgit v1.2.3


From 9fd7874c0e5c89d7da0b4442271696ec0f8edcba Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Mon, 4 Dec 2023 10:47:50 -0700
Subject: iov_iter: replace import_single_range() with import_ubuf()

With the removal of the 'iov' argument to import_single_range(), the two
functions are now fully identical. Convert the import_single_range()
callers to import_ubuf(), and remove the former fully.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
Link: https://lore.kernel.org/r/20231204174827.1258875-3-axboe@kernel.dk
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 drivers/block/ublk_drv.c         |  7 ++-----
 drivers/char/random.c            |  4 ++--
 fs/aio.c                         |  2 +-
 include/linux/uio.h              |  2 --
 kernel/trace/trace_events_user.c |  3 +--
 lib/iov_iter.c                   | 13 -------------
 net/ipv4/tcp.c                   |  8 ++++----
 net/socket.c                     |  4 ++--
 security/keys/keyctl.c           |  4 ++--
 9 files changed, 14 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 5656b0a1233d..3eaf02ebeebe 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -895,9 +895,7 @@ static int ublk_map_io(const struct ublk_queue *ubq, const struct request *req,
 		struct iov_iter iter;
 		const int dir = ITER_DEST;
 
-		import_single_range(dir, u64_to_user_ptr(io->addr), rq_bytes,
-					&iter);
-
+		import_ubuf(dir, u64_to_user_ptr(io->addr), rq_bytes, &iter);
 		return ublk_copy_user_pages(req, 0, &iter, dir);
 	}
 	return rq_bytes;
@@ -918,8 +916,7 @@ static int ublk_unmap_io(const struct ublk_queue *ubq,
 
 		WARN_ON_ONCE(io->res > rq_bytes);
 
-		import_single_range(dir, u64_to_user_ptr(io->addr), io->res,
-					&iter);
+		import_ubuf(dir, u64_to_user_ptr(io->addr), io->res, &iter);
 		return ublk_copy_user_pages(req, 0, &iter, dir);
 	}
 	return rq_bytes;
diff --git a/drivers/char/random.c b/drivers/char/random.c
index e79ae238b30d..456be28ba67c 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -1384,7 +1384,7 @@ SYSCALL_DEFINE3(getrandom, char __user *, ubuf, size_t, len, unsigned int, flags
 			return ret;
 	}
 
-	ret = import_single_range(ITER_DEST, ubuf, len, &iter);
+	ret = import_ubuf(ITER_DEST, ubuf, len, &iter);
 	if (unlikely(ret))
 		return ret;
 	return get_random_bytes_user(&iter);
@@ -1501,7 +1501,7 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
 			return -EINVAL;
 		if (get_user(len, p++))
 			return -EFAULT;
-		ret = import_single_range(ITER_SOURCE, p, len, &iter);
+		ret = import_ubuf(ITER_SOURCE, p, len, &iter);
 		if (unlikely(ret))
 			return ret;
 		ret = write_pool_user(&iter);
diff --git a/fs/aio.c b/fs/aio.c
index 251eeaef7fbf..4ea639509d41 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1498,7 +1498,7 @@ static ssize_t aio_setup_rw(int rw, const struct iocb *iocb,
 	size_t len = iocb->aio_nbytes;
 
 	if (!vectored) {
-		ssize_t ret = import_single_range(rw, buf, len, iter);
+		ssize_t ret = import_ubuf(rw, buf, len, iter);
 		*iovec = NULL;
 		return ret;
 	}
diff --git a/include/linux/uio.h b/include/linux/uio.h
index bfafd3542fa7..bea9c89922d9 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -347,8 +347,6 @@ ssize_t import_iovec(int type, const struct iovec __user *uvec,
 ssize_t __import_iovec(int type, const struct iovec __user *uvec,
 		 unsigned nr_segs, unsigned fast_segs, struct iovec **iovp,
 		 struct iov_iter *i, bool compat);
-int import_single_range(int type, void __user *buf, size_t len,
-		 struct iov_iter *i);
 int import_ubuf(int type, void __user *buf, size_t len, struct iov_iter *i);
 
 static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction,
diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c
index 4efc75d90a0d..e76f5e1efdf2 100644
--- a/kernel/trace/trace_events_user.c
+++ b/kernel/trace/trace_events_user.c
@@ -2182,8 +2182,7 @@ static ssize_t user_events_write(struct file *file, const char __user *ubuf,
 	if (unlikely(*ppos != 0))
 		return -EFAULT;
 
-	if (unlikely(import_single_range(ITER_SOURCE, (char __user *)ubuf,
-					 count, &i)))
+	if (unlikely(import_ubuf(ITER_SOURCE, (char __user *)ubuf, count, &i)))
 		return -EFAULT;
 
 	return user_events_write_core(file, &i);
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index d60c73354e1f..009875bc95aa 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -1369,19 +1369,6 @@ ssize_t import_iovec(int type, const struct iovec __user *uvec,
 }
 EXPORT_SYMBOL(import_iovec);
 
-int import_single_range(int rw, void __user *buf, size_t len,
-			struct iov_iter *i)
-{
-	if (len > MAX_RW_COUNT)
-		len = MAX_RW_COUNT;
-	if (unlikely(!access_ok(buf, len)))
-		return -EFAULT;
-
-	iov_iter_ubuf(i, rw, buf, len);
-	return 0;
-}
-EXPORT_SYMBOL(import_single_range);
-
 int import_ubuf(int rw, void __user *buf, size_t len, struct iov_iter *i)
 {
 	if (len > MAX_RW_COUNT)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 57cf3adb191a..54d3c762d400 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1857,8 +1857,8 @@ static int receive_fallback_to_copy(struct sock *sk,
 	if (copy_address != zc->copybuf_address)
 		return -EINVAL;
 
-	err = import_single_range(ITER_DEST, (void __user *)copy_address,
-				  inq, &msg.msg_iter);
+	err = import_ubuf(ITER_DEST, (void __user *)copy_address, inq,
+			  &msg.msg_iter);
 	if (err)
 		return err;
 
@@ -1890,8 +1890,8 @@ static int tcp_copy_straggler_data(struct tcp_zerocopy_receive *zc,
 	if (copy_address != zc->copybuf_address)
 		return -EINVAL;
 
-	err = import_single_range(ITER_DEST, (void __user *)copy_address,
-				  copylen, &msg.msg_iter);
+	err = import_ubuf(ITER_DEST, (void __user *)copy_address, copylen,
+			  &msg.msg_iter);
 	if (err)
 		return err;
 	err = skb_copy_datagram_msg(skb, *offset, &msg, copylen);
diff --git a/net/socket.c b/net/socket.c
index 1f0d0e8d0a50..5d49ae0c1b79 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2163,7 +2163,7 @@ int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags,
 	struct msghdr msg;
 	int fput_needed;
 
-	err = import_single_range(ITER_SOURCE, buff, len, &msg.msg_iter);
+	err = import_ubuf(ITER_SOURCE, buff, len, &msg.msg_iter);
 	if (unlikely(err))
 		return err;
 	sock = sockfd_lookup_light(fd, &err, &fput_needed);
@@ -2228,7 +2228,7 @@ int __sys_recvfrom(int fd, void __user *ubuf, size_t size, unsigned int flags,
 	int err, err2;
 	int fput_needed;
 
-	err = import_single_range(ITER_DEST, ubuf, size, &msg.msg_iter);
+	err = import_ubuf(ITER_DEST, ubuf, size, &msg.msg_iter);
 	if (unlikely(err))
 		return err;
 	sock = sockfd_lookup_light(fd, &err, &fput_needed);
diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c
index 193df7ca3ca8..10ba439968f7 100644
--- a/security/keys/keyctl.c
+++ b/security/keys/keyctl.c
@@ -1255,8 +1255,8 @@ long keyctl_instantiate_key(key_serial_t id,
 		struct iov_iter from;
 		int ret;
 
-		ret = import_single_range(ITER_SOURCE, (void __user *)_payload, plen,
-					  &from);
+		ret = import_ubuf(ITER_SOURCE, (void __user *)_payload, plen,
+				  &from);
 		if (unlikely(ret))
 			return ret;
 
-- 
cgit v1.2.3


From a931c6816078af3e306e0f444f492396ce40de31 Mon Sep 17 00:00:00 2001
From: JP Kobryn <inwardvessel@gmail.com>
Date: Mon, 4 Dec 2023 12:23:20 -0800
Subject: 9p: prevent read overrun in protocol dump tracepoint

An out of bounds read can occur within the tracepoint 9p_protocol_dump. In
the fast assign, there is a memcpy that uses a constant size of 32 (macro
named P9_PROTO_DUMP_SZ). When the copy is invoked, the source buffer is not
guaranteed match this size.  It was found that in some cases the source
buffer size is less than 32, resulting in a read that overruns.

The size of the source buffer seems to be known at the time of the
tracepoint being invoked. The allocations happen within p9_fcall_init(),
where the capacity field is set to the allocated size of the payload
buffer. This patch tries to fix the overrun by changing the fixed array to
a dynamically sized array and using the minimum of the capacity value or
P9_PROTO_DUMP_SZ as its length. The trace log statement is adjusted to
account for this. Note that the trace log no longer splits the payload on
the first 16 bytes. The full payload is now logged to a single line.

To repro the orignal problem, operations to a plan 9 managed resource can
be used. The simplest approach might just be mounting a shared filesystem
(between host and guest vm) using the plan 9 protocol while the tracepoint
is enabled.

mount -t 9p -o trans=virtio <mount_tag> <mount_path>

The bpftrace program below can be used to show the out of bounds read.
Note that a recent version of bpftrace is needed for the raw tracepoint
support. The script was tested using v0.19.0.

/* from include/net/9p/9p.h */
struct p9_fcall {
    u32 size;
    u8 id;
    u16 tag;
    size_t offset;
    size_t capacity;
    struct kmem_cache *cache;
    u8 *sdata;
    bool zc;
};

tracepoint:9p:9p_protocol_dump
{
    /* out of bounds read can happen when this tracepoint is enabled */
}

rawtracepoint:9p_protocol_dump
{
    $pdu = (struct p9_fcall *)arg1;
    $dump_sz = (uint64)32;

    if ($dump_sz > $pdu->capacity) {
        printf("reading %zu bytes from src buffer of %zu bytes\n",
            $dump_sz, $pdu->capacity);
    }
}

Signed-off-by: JP Kobryn <inwardvessel@gmail.com>
Message-ID: <20231204202321.22730-1-inwardvessel@gmail.com>
Fixes: 60ece0833b6c ("net/9p: allocate appropriate reduced message buffers")
Cc: stable@vger.kernel.org
Reviewed-by: Christian Schoenebeck <linux_oss@crudebyte.com>
Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
---
 include/trace/events/9p.h | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/9p.h b/include/trace/events/9p.h
index 4dfa6d7f83ba..cd104a1343e2 100644
--- a/include/trace/events/9p.h
+++ b/include/trace/events/9p.h
@@ -178,18 +178,21 @@ TRACE_EVENT(9p_protocol_dump,
 		    __field(	void *,		clnt				)
 		    __field(	__u8,		type				)
 		    __field(	__u16,		tag				)
-		    __array(	unsigned char,	line,	P9_PROTO_DUMP_SZ	)
+		    __dynamic_array(unsigned char, line,
+				min_t(size_t, pdu->capacity, P9_PROTO_DUMP_SZ))
 		    ),
 
 	    TP_fast_assign(
 		    __entry->clnt   =  clnt;
 		    __entry->type   =  pdu->id;
 		    __entry->tag    =  pdu->tag;
-		    memcpy(__entry->line, pdu->sdata, P9_PROTO_DUMP_SZ);
+		    memcpy(__get_dynamic_array(line), pdu->sdata,
+				__get_dynamic_array_len(line));
 		    ),
-	    TP_printk("clnt %lu %s(tag = %d)\n%.3x: %16ph\n%.3x: %16ph\n",
+	    TP_printk("clnt %lu %s(tag = %d)\n%*ph\n",
 		      (unsigned long)__entry->clnt, show_9p_op(__entry->type),
-		      __entry->tag, 0, __entry->line, 16, __entry->line + 16)
+		      __entry->tag, __get_dynamic_array_len(line),
+		      __get_dynamic_array(line))
  );
 
 
-- 
cgit v1.2.3


From 118eb89b1e7f6807776c012cffc5c9b07fd26164 Mon Sep 17 00:00:00 2001
From: Anshuman Khandual <anshuman.khandual@arm.com>
Date: Wed, 15 Nov 2023 14:58:05 +0530
Subject: drivers: perf: arm_pmu: Drop 'pmu_lock' element from 'struct
 pmu_hw_events'

As 'pmu_lock' element is not being used in any ARM PMU implementation, just
drop this from 'struct pmu_hw_events'.

Cc: Will Deacon <will@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Link: https://lore.kernel.org/r/20231115092805.737822-3-anshuman.khandual@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/perf/arm_pmu.c       | 1 -
 include/linux/perf/arm_pmu.h | 6 ------
 2 files changed, 7 deletions(-)

(limited to 'include')

diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index d712a19e47ac..379479b50bdd 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -893,7 +893,6 @@ struct arm_pmu *armpmu_alloc(void)
 		struct pmu_hw_events *events;
 
 		events = per_cpu_ptr(pmu->hw_events, cpu);
-		raw_spin_lock_init(&events->pmu_lock);
 		events->percpu_pmu = pmu;
 	}
 
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index 143fbc10ecfe..e2503d48ddee 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -59,12 +59,6 @@ struct pmu_hw_events {
 	 */
 	DECLARE_BITMAP(used_mask, ARMPMU_MAX_HWEVENTS);
 
-	/*
-	 * Hardware lock to serialize accesses to PMU registers. Needed for the
-	 * read/modify/write sequences.
-	 */
-	raw_spinlock_t		pmu_lock;
-
 	/*
 	 * When using percpu IRQs, we need a percpu dev_id. Place it here as we
 	 * already have to allocate this struct per cpu.
-- 
cgit v1.2.3


From 75b5e0bf90bffaca4b1f19114065dc59f5cc161f Mon Sep 17 00:00:00 2001
From: Huang Shijie <shijie@os.amperecomputing.com>
Date: Fri, 24 Nov 2023 11:15:13 +0800
Subject: arm64: irq: set the correct node for VMAP stack

In current code, init_irq_stacks() will call cpu_to_node().
The cpu_to_node() depends on percpu "numa_node" which is initialized in:
     arch_call_rest_init() --> rest_init() -- kernel_init()
	--> kernel_init_freeable() --> smp_prepare_cpus()

But init_irq_stacks() is called in init_IRQ() which is before
arch_call_rest_init().

So in init_irq_stacks(), the cpu_to_node() does not work, it
always return 0. In NUMA, it makes the node 1 cpu accesses the IRQ stack which
is in the node 0.

This patch fixes it by:
  1.) export the early_cpu_to_node(), and use it in the init_irq_stacks().
  2.) change init_irq_stacks() to __init function.

Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Huang Shijie <shijie@os.amperecomputing.com>
Link: https://lore.kernel.org/r/20231124031513.81548-1-shijie@os.amperecomputing.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/irq.c    | 5 +++--
 drivers/base/arch_numa.c   | 2 +-
 include/asm-generic/numa.h | 2 ++
 3 files changed, 6 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index 6ad5c6ef5329..9f253d8efe90 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -22,6 +22,7 @@
 #include <linux/vmalloc.h>
 #include <asm/daifflags.h>
 #include <asm/exception.h>
+#include <asm/numa.h>
 #include <asm/softirq_stack.h>
 #include <asm/stacktrace.h>
 #include <asm/vmap_stack.h>
@@ -51,13 +52,13 @@ static void init_irq_scs(void)
 }
 
 #ifdef CONFIG_VMAP_STACK
-static void init_irq_stacks(void)
+static void __init init_irq_stacks(void)
 {
 	int cpu;
 	unsigned long *p;
 
 	for_each_possible_cpu(cpu) {
-		p = arch_alloc_vmap_stack(IRQ_STACK_SIZE, cpu_to_node(cpu));
+		p = arch_alloc_vmap_stack(IRQ_STACK_SIZE, early_cpu_to_node(cpu));
 		per_cpu(irq_stack_ptr, cpu) = p;
 	}
 }
diff --git a/drivers/base/arch_numa.c b/drivers/base/arch_numa.c
index eaa31e567d1e..5b59d133b6af 100644
--- a/drivers/base/arch_numa.c
+++ b/drivers/base/arch_numa.c
@@ -144,7 +144,7 @@ void __init early_map_cpu_to_node(unsigned int cpu, int nid)
 unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
 EXPORT_SYMBOL(__per_cpu_offset);
 
-static int __init early_cpu_to_node(int cpu)
+int __init early_cpu_to_node(int cpu)
 {
 	return cpu_to_node_map[cpu];
 }
diff --git a/include/asm-generic/numa.h b/include/asm-generic/numa.h
index 1a3ad6d29833..c32e0cf23c90 100644
--- a/include/asm-generic/numa.h
+++ b/include/asm-generic/numa.h
@@ -35,6 +35,7 @@ int __init numa_add_memblk(int nodeid, u64 start, u64 end);
 void __init numa_set_distance(int from, int to, int distance);
 void __init numa_free_distance(void);
 void __init early_map_cpu_to_node(unsigned int cpu, int nid);
+int __init early_cpu_to_node(int cpu);
 void numa_store_cpu_info(unsigned int cpu);
 void numa_add_cpu(unsigned int cpu);
 void numa_remove_cpu(unsigned int cpu);
@@ -46,6 +47,7 @@ static inline void numa_add_cpu(unsigned int cpu) { }
 static inline void numa_remove_cpu(unsigned int cpu) { }
 static inline void arch_numa_init(void) { }
 static inline void early_map_cpu_to_node(unsigned int cpu, int nid) { }
+static inline int early_cpu_to_node(int cpu) { return 0; }
 
 #endif	/* CONFIG_NUMA */
 
-- 
cgit v1.2.3


From 41f6f64e6999a837048b1bd13a2f8742964eca6b Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 5 Dec 2023 10:42:39 -0800
Subject: bpf: support non-r10 register spill/fill to/from stack in precision
 tracking

Use instruction (jump) history to record instructions that performed
register spill/fill to/from stack, regardless if this was done through
read-only r10 register, or any other register after copying r10 into it
*and* potentially adjusting offset.

To make this work reliably, we push extra per-instruction flags into
instruction history, encoding stack slot index (spi) and stack frame
number in extra 10 bit flags we take away from prev_idx in instruction
history. We don't touch idx field for maximum performance, as it's
checked most frequently during backtracking.

This change removes basically the last remaining practical limitation of
precision backtracking logic in BPF verifier. It fixes known
deficiencies, but also opens up new opportunities to reduce number of
verified states, explored in the subsequent patches.

There are only three differences in selftests' BPF object files
according to veristat, all in the positive direction (less states).

File                                    Program        Insns (A)  Insns (B)  Insns  (DIFF)  States (A)  States (B)  States (DIFF)
--------------------------------------  -------------  ---------  ---------  -------------  ----------  ----------  -------------
test_cls_redirect_dynptr.bpf.linked3.o  cls_redirect        2987       2864  -123 (-4.12%)         240         231    -9 (-3.75%)
xdp_synproxy_kern.bpf.linked3.o         syncookie_tc       82848      82661  -187 (-0.23%)        5107        5073   -34 (-0.67%)
xdp_synproxy_kern.bpf.linked3.o         syncookie_xdp      85116      84964  -152 (-0.18%)        5162        5130   -32 (-0.62%)

Note, I avoided renaming jmp_history to more generic insn_hist to
minimize number of lines changed and potential merge conflicts between
bpf and bpf-next trees.

Notice also cur_hist_entry pointer reset to NULL at the beginning of
instruction verification loop. This pointer avoids the problem of
relying on last jump history entry's insn_idx to determine whether we
already have entry for current instruction or not. It can happen that we
added jump history entry because current instruction is_jmp_point(), but
also we need to add instruction flags for stack access. In this case, we
don't want to entries, so we need to reuse last added entry, if it is
present.

Relying on insn_idx comparison has the same ambiguity problem as the one
that was fixed recently in [0], so we avoid that.

  [0] https://patchwork.kernel.org/project/netdevbpf/patch/20231110002638.4168352-3-andrii@kernel.org/

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Reported-by: Tao Lyu <tao.lyu@epfl.ch>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20231205184248.1502704-2-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf_verifier.h                       |  31 +++-
 kernel/bpf/verifier.c                              | 175 ++++++++++++---------
 .../bpf/progs/verifier_subprog_precision.c         |  23 ++-
 tools/testing/selftests/bpf/verifier/precise.c     |  38 +++--
 4 files changed, 169 insertions(+), 98 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 3378cc753061..bada59812e00 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -325,12 +325,34 @@ struct bpf_func_state {
 	int allocated_stack;
 };
 
-struct bpf_idx_pair {
-	u32 prev_idx;
+#define MAX_CALL_FRAMES 8
+
+/* instruction history flags, used in bpf_jmp_history_entry.flags field */
+enum {
+	/* instruction references stack slot through PTR_TO_STACK register;
+	 * we also store stack's frame number in lower 3 bits (MAX_CALL_FRAMES is 8)
+	 * and accessed stack slot's index in next 6 bits (MAX_BPF_STACK is 512,
+	 * 8 bytes per slot, so slot index (spi) is [0, 63])
+	 */
+	INSN_F_FRAMENO_MASK = 0x7, /* 3 bits */
+
+	INSN_F_SPI_MASK = 0x3f, /* 6 bits */
+	INSN_F_SPI_SHIFT = 3, /* shifted 3 bits to the left */
+
+	INSN_F_STACK_ACCESS = BIT(9), /* we need 10 bits total */
+};
+
+static_assert(INSN_F_FRAMENO_MASK + 1 >= MAX_CALL_FRAMES);
+static_assert(INSN_F_SPI_MASK + 1 >= MAX_BPF_STACK / 8);
+
+struct bpf_jmp_history_entry {
 	u32 idx;
+	/* insn idx can't be bigger than 1 million */
+	u32 prev_idx : 22;
+	/* special flags, e.g., whether insn is doing register stack spill/load */
+	u32 flags : 10;
 };
 
-#define MAX_CALL_FRAMES 8
 /* Maximum number of register states that can exist at once */
 #define BPF_ID_MAP_SIZE ((MAX_BPF_REG + MAX_BPF_STACK / BPF_REG_SIZE) * MAX_CALL_FRAMES)
 struct bpf_verifier_state {
@@ -413,7 +435,7 @@ struct bpf_verifier_state {
 	 * For most states jmp_history_cnt is [0-3].
 	 * For loops can go up to ~40.
 	 */
-	struct bpf_idx_pair *jmp_history;
+	struct bpf_jmp_history_entry *jmp_history;
 	u32 jmp_history_cnt;
 	u32 dfs_depth;
 	u32 callback_unroll_depth;
@@ -656,6 +678,7 @@ struct bpf_verifier_env {
 		int cur_stack;
 	} cfg;
 	struct backtrack_state bt;
+	struct bpf_jmp_history_entry *cur_hist_ent;
 	u32 pass_cnt; /* number of times do_check() was called */
 	u32 subprog_cnt;
 	/* number of instructions analyzed by the verifier */
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 1ed39665f802..9bc16dc66465 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1355,8 +1355,8 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state,
 	int i, err;
 
 	dst_state->jmp_history = copy_array(dst_state->jmp_history, src->jmp_history,
-					    src->jmp_history_cnt, sizeof(struct bpf_idx_pair),
-					    GFP_USER);
+					  src->jmp_history_cnt, sizeof(*dst_state->jmp_history),
+					  GFP_USER);
 	if (!dst_state->jmp_history)
 		return -ENOMEM;
 	dst_state->jmp_history_cnt = src->jmp_history_cnt;
@@ -3221,6 +3221,21 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno,
 	return __check_reg_arg(env, state->regs, regno, t);
 }
 
+static int insn_stack_access_flags(int frameno, int spi)
+{
+	return INSN_F_STACK_ACCESS | (spi << INSN_F_SPI_SHIFT) | frameno;
+}
+
+static int insn_stack_access_spi(int insn_flags)
+{
+	return (insn_flags >> INSN_F_SPI_SHIFT) & INSN_F_SPI_MASK;
+}
+
+static int insn_stack_access_frameno(int insn_flags)
+{
+	return insn_flags & INSN_F_FRAMENO_MASK;
+}
+
 static void mark_jmp_point(struct bpf_verifier_env *env, int idx)
 {
 	env->insn_aux_data[idx].jmp_point = true;
@@ -3232,28 +3247,51 @@ static bool is_jmp_point(struct bpf_verifier_env *env, int insn_idx)
 }
 
 /* for any branch, call, exit record the history of jmps in the given state */
-static int push_jmp_history(struct bpf_verifier_env *env,
-			    struct bpf_verifier_state *cur)
+static int push_jmp_history(struct bpf_verifier_env *env, struct bpf_verifier_state *cur,
+			    int insn_flags)
 {
 	u32 cnt = cur->jmp_history_cnt;
-	struct bpf_idx_pair *p;
+	struct bpf_jmp_history_entry *p;
 	size_t alloc_size;
 
-	if (!is_jmp_point(env, env->insn_idx))
+	/* combine instruction flags if we already recorded this instruction */
+	if (env->cur_hist_ent) {
+		/* atomic instructions push insn_flags twice, for READ and
+		 * WRITE sides, but they should agree on stack slot
+		 */
+		WARN_ONCE((env->cur_hist_ent->flags & insn_flags) &&
+			  (env->cur_hist_ent->flags & insn_flags) != insn_flags,
+			  "verifier insn history bug: insn_idx %d cur flags %x new flags %x\n",
+			  env->insn_idx, env->cur_hist_ent->flags, insn_flags);
+		env->cur_hist_ent->flags |= insn_flags;
 		return 0;
+	}
 
 	cnt++;
 	alloc_size = kmalloc_size_roundup(size_mul(cnt, sizeof(*p)));
 	p = krealloc(cur->jmp_history, alloc_size, GFP_USER);
 	if (!p)
 		return -ENOMEM;
-	p[cnt - 1].idx = env->insn_idx;
-	p[cnt - 1].prev_idx = env->prev_insn_idx;
 	cur->jmp_history = p;
+
+	p = &cur->jmp_history[cnt - 1];
+	p->idx = env->insn_idx;
+	p->prev_idx = env->prev_insn_idx;
+	p->flags = insn_flags;
 	cur->jmp_history_cnt = cnt;
+	env->cur_hist_ent = p;
+
 	return 0;
 }
 
+static struct bpf_jmp_history_entry *get_jmp_hist_entry(struct bpf_verifier_state *st,
+						        u32 hist_end, int insn_idx)
+{
+	if (hist_end > 0 && st->jmp_history[hist_end - 1].idx == insn_idx)
+		return &st->jmp_history[hist_end - 1];
+	return NULL;
+}
+
 /* Backtrack one insn at a time. If idx is not at the top of recorded
  * history then previous instruction came from straight line execution.
  * Return -ENOENT if we exhausted all instructions within given state.
@@ -3415,9 +3453,14 @@ static inline bool bt_is_reg_set(struct backtrack_state *bt, u32 reg)
 	return bt->reg_masks[bt->frame] & (1 << reg);
 }
 
+static inline bool bt_is_frame_slot_set(struct backtrack_state *bt, u32 frame, u32 slot)
+{
+	return bt->stack_masks[frame] & (1ull << slot);
+}
+
 static inline bool bt_is_slot_set(struct backtrack_state *bt, u32 slot)
 {
-	return bt->stack_masks[bt->frame] & (1ull << slot);
+	return bt_is_frame_slot_set(bt, bt->frame, slot);
 }
 
 /* format registers bitmask, e.g., "r0,r2,r4" for 0x15 mask */
@@ -3471,7 +3514,7 @@ static bool calls_callback(struct bpf_verifier_env *env, int insn_idx);
  *   - *was* processed previously during backtracking.
  */
 static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
-			  struct backtrack_state *bt)
+			  struct bpf_jmp_history_entry *hist, struct backtrack_state *bt)
 {
 	const struct bpf_insn_cbs cbs = {
 		.cb_call	= disasm_kfunc_name,
@@ -3484,7 +3527,7 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
 	u8 mode = BPF_MODE(insn->code);
 	u32 dreg = insn->dst_reg;
 	u32 sreg = insn->src_reg;
-	u32 spi, i;
+	u32 spi, i, fr;
 
 	if (insn->code == 0)
 		return 0;
@@ -3545,20 +3588,15 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
 		 * by 'precise' mark in corresponding register of this state.
 		 * No further tracking necessary.
 		 */
-		if (insn->src_reg != BPF_REG_FP)
+		if (!hist || !(hist->flags & INSN_F_STACK_ACCESS))
 			return 0;
-
 		/* dreg = *(u64 *)[fp - off] was a fill from the stack.
 		 * that [fp - off] slot contains scalar that needs to be
 		 * tracked with precision
 		 */
-		spi = (-insn->off - 1) / BPF_REG_SIZE;
-		if (spi >= 64) {
-			verbose(env, "BUG spi %d\n", spi);
-			WARN_ONCE(1, "verifier backtracking bug");
-			return -EFAULT;
-		}
-		bt_set_slot(bt, spi);
+		spi = insn_stack_access_spi(hist->flags);
+		fr = insn_stack_access_frameno(hist->flags);
+		bt_set_frame_slot(bt, fr, spi);
 	} else if (class == BPF_STX || class == BPF_ST) {
 		if (bt_is_reg_set(bt, dreg))
 			/* stx & st shouldn't be using _scalar_ dst_reg
@@ -3567,17 +3605,13 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
 			 */
 			return -ENOTSUPP;
 		/* scalars can only be spilled into stack */
-		if (insn->dst_reg != BPF_REG_FP)
+		if (!hist || !(hist->flags & INSN_F_STACK_ACCESS))
 			return 0;
-		spi = (-insn->off - 1) / BPF_REG_SIZE;
-		if (spi >= 64) {
-			verbose(env, "BUG spi %d\n", spi);
-			WARN_ONCE(1, "verifier backtracking bug");
-			return -EFAULT;
-		}
-		if (!bt_is_slot_set(bt, spi))
+		spi = insn_stack_access_spi(hist->flags);
+		fr = insn_stack_access_frameno(hist->flags);
+		if (!bt_is_frame_slot_set(bt, fr, spi))
 			return 0;
-		bt_clear_slot(bt, spi);
+		bt_clear_frame_slot(bt, fr, spi);
 		if (class == BPF_STX)
 			bt_set_reg(bt, sreg);
 	} else if (class == BPF_JMP || class == BPF_JMP32) {
@@ -3621,10 +3655,14 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
 					WARN_ONCE(1, "verifier backtracking bug");
 					return -EFAULT;
 				}
-				/* we don't track register spills perfectly,
-				 * so fallback to force-precise instead of failing */
-				if (bt_stack_mask(bt) != 0)
-					return -ENOTSUPP;
+				/* we are now tracking register spills correctly,
+				 * so any instance of leftover slots is a bug
+				 */
+				if (bt_stack_mask(bt) != 0) {
+					verbose(env, "BUG stack slots %llx\n", bt_stack_mask(bt));
+					WARN_ONCE(1, "verifier backtracking bug (subprog leftover stack slots)");
+					return -EFAULT;
+				}
 				/* propagate r1-r5 to the caller */
 				for (i = BPF_REG_1; i <= BPF_REG_5; i++) {
 					if (bt_is_reg_set(bt, i)) {
@@ -3649,8 +3687,11 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
 				WARN_ONCE(1, "verifier backtracking bug");
 				return -EFAULT;
 			}
-			if (bt_stack_mask(bt) != 0)
-				return -ENOTSUPP;
+			if (bt_stack_mask(bt) != 0) {
+				verbose(env, "BUG stack slots %llx\n", bt_stack_mask(bt));
+				WARN_ONCE(1, "verifier backtracking bug (callback leftover stack slots)");
+				return -EFAULT;
+			}
 			/* clear r1-r5 in callback subprog's mask */
 			for (i = BPF_REG_1; i <= BPF_REG_5; i++)
 				bt_clear_reg(bt, i);
@@ -4087,6 +4128,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
 	for (;;) {
 		DECLARE_BITMAP(mask, 64);
 		u32 history = st->jmp_history_cnt;
+		struct bpf_jmp_history_entry *hist;
 
 		if (env->log.level & BPF_LOG_LEVEL2) {
 			verbose(env, "mark_precise: frame%d: last_idx %d first_idx %d subseq_idx %d \n",
@@ -4150,7 +4192,8 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
 				err = 0;
 				skip_first = false;
 			} else {
-				err = backtrack_insn(env, i, subseq_idx, bt);
+				hist = get_jmp_hist_entry(st, history, i);
+				err = backtrack_insn(env, i, subseq_idx, hist, bt);
 			}
 			if (err == -ENOTSUPP) {
 				mark_all_scalars_precise(env, env->cur_state);
@@ -4203,22 +4246,10 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
 			bitmap_from_u64(mask, bt_frame_stack_mask(bt, fr));
 			for_each_set_bit(i, mask, 64) {
 				if (i >= func->allocated_stack / BPF_REG_SIZE) {
-					/* the sequence of instructions:
-					 * 2: (bf) r3 = r10
-					 * 3: (7b) *(u64 *)(r3 -8) = r0
-					 * 4: (79) r4 = *(u64 *)(r10 -8)
-					 * doesn't contain jmps. It's backtracked
-					 * as a single block.
-					 * During backtracking insn 3 is not recognized as
-					 * stack access, so at the end of backtracking
-					 * stack slot fp-8 is still marked in stack_mask.
-					 * However the parent state may not have accessed
-					 * fp-8 and it's "unallocated" stack space.
-					 * In such case fallback to conservative.
-					 */
-					mark_all_scalars_precise(env, env->cur_state);
-					bt_reset(bt);
-					return 0;
+					verbose(env, "BUG backtracking (stack slot %d, total slots %d)\n",
+						i, func->allocated_stack / BPF_REG_SIZE);
+					WARN_ONCE(1, "verifier backtracking bug (stack slot out of bounds)");
+					return -EFAULT;
 				}
 
 				if (!is_spilled_scalar_reg(&func->stack[i])) {
@@ -4391,7 +4422,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 	int i, slot = -off - 1, spi = slot / BPF_REG_SIZE, err;
 	struct bpf_insn *insn = &env->prog->insnsi[insn_idx];
 	struct bpf_reg_state *reg = NULL;
-	u32 dst_reg = insn->dst_reg;
+	int insn_flags = insn_stack_access_flags(state->frameno, spi);
 
 	err = grow_stack_state(state, round_up(slot + 1, BPF_REG_SIZE));
 	if (err)
@@ -4432,17 +4463,6 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 	mark_stack_slot_scratched(env, spi);
 	if (reg && !(off % BPF_REG_SIZE) && register_is_bounded(reg) &&
 	    !register_is_null(reg) && env->bpf_capable) {
-		if (dst_reg != BPF_REG_FP) {
-			/* The backtracking logic can only recognize explicit
-			 * stack slot address like [fp - 8]. Other spill of
-			 * scalar via different register has to be conservative.
-			 * Backtrack from here and mark all registers as precise
-			 * that contributed into 'reg' being a constant.
-			 */
-			err = mark_chain_precision(env, value_regno);
-			if (err)
-				return err;
-		}
 		save_register_state(state, spi, reg, size);
 		/* Break the relation on a narrowing spill. */
 		if (fls64(reg->umax_value) > BITS_PER_BYTE * size)
@@ -4454,6 +4474,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 		__mark_reg_known(&fake_reg, insn->imm);
 		fake_reg.type = SCALAR_VALUE;
 		save_register_state(state, spi, &fake_reg, size);
+		insn_flags = 0; /* not a register spill */
 	} else if (reg && is_spillable_regtype(reg->type)) {
 		/* register containing pointer is being spilled into stack */
 		if (size != BPF_REG_SIZE) {
@@ -4499,9 +4520,12 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 
 		/* Mark slots affected by this stack write. */
 		for (i = 0; i < size; i++)
-			state->stack[spi].slot_type[(slot - i) % BPF_REG_SIZE] =
-				type;
+			state->stack[spi].slot_type[(slot - i) % BPF_REG_SIZE] = type;
+		insn_flags = 0; /* not a register spill */
 	}
+
+	if (insn_flags)
+		return push_jmp_history(env, env->cur_state, insn_flags);
 	return 0;
 }
 
@@ -4694,6 +4718,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
 	int i, slot = -off - 1, spi = slot / BPF_REG_SIZE;
 	struct bpf_reg_state *reg;
 	u8 *stype, type;
+	int insn_flags = insn_stack_access_flags(reg_state->frameno, spi);
 
 	stype = reg_state->stack[spi].slot_type;
 	reg = &reg_state->stack[spi].spilled_ptr;
@@ -4739,12 +4764,10 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
 					return -EACCES;
 				}
 				mark_reg_unknown(env, state->regs, dst_regno);
+				insn_flags = 0; /* not restoring original register state */
 			}
 			state->regs[dst_regno].live |= REG_LIVE_WRITTEN;
-			return 0;
-		}
-
-		if (dst_regno >= 0) {
+		} else if (dst_regno >= 0) {
 			/* restore register state from stack */
 			copy_register_state(&state->regs[dst_regno], reg);
 			/* mark reg as written since spilled pointer state likely
@@ -4780,7 +4803,10 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
 		mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64);
 		if (dst_regno >= 0)
 			mark_reg_stack_read(env, reg_state, off, off + size, dst_regno);
+		insn_flags = 0; /* we are not restoring spilled register */
 	}
+	if (insn_flags)
+		return push_jmp_history(env, env->cur_state, insn_flags);
 	return 0;
 }
 
@@ -6940,7 +6966,6 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i
 			       BPF_SIZE(insn->code), BPF_WRITE, -1, true, false);
 	if (err)
 		return err;
-
 	return 0;
 }
 
@@ -16910,7 +16935,8 @@ hit:
 			 * the precision needs to be propagated back in
 			 * the current state.
 			 */
-			err = err ? : push_jmp_history(env, cur);
+			if (is_jmp_point(env, env->insn_idx))
+				err = err ? : push_jmp_history(env, cur, 0);
 			err = err ? : propagate_precision(env, &sl->state);
 			if (err)
 				return err;
@@ -17135,6 +17161,9 @@ static int do_check(struct bpf_verifier_env *env)
 		u8 class;
 		int err;
 
+		/* reset current history entry on each new instruction */
+		env->cur_hist_ent = NULL;
+
 		env->prev_insn_idx = prev_insn_idx;
 		if (env->insn_idx >= insn_cnt) {
 			verbose(env, "invalid insn idx %d insn_cnt %d\n",
@@ -17174,7 +17203,7 @@ static int do_check(struct bpf_verifier_env *env)
 		}
 
 		if (is_jmp_point(env, env->insn_idx)) {
-			err = push_jmp_history(env, state);
+			err = push_jmp_history(env, state, 0);
 			if (err)
 				return err;
 		}
diff --git a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c
index 0dfe3f8b69ac..eba98fab2f54 100644
--- a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c
+++ b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c
@@ -589,11 +589,24 @@ static __u64 subprog_spill_reg_precise(void)
 
 SEC("?raw_tp")
 __success __log_level(2)
-/* precision backtracking can't currently handle stack access not through r10,
- * so we won't be able to mark stack slot fp-8 as precise, and so will
- * fallback to forcing all as precise
- */
-__msg("mark_precise: frame0: falling back to forcing all scalars precise")
+__msg("10: (0f) r1 += r7")
+__msg("mark_precise: frame0: last_idx 10 first_idx 7 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r7 stack= before 9: (bf) r1 = r8")
+__msg("mark_precise: frame0: regs=r7 stack= before 8: (27) r7 *= 4")
+__msg("mark_precise: frame0: regs=r7 stack= before 7: (79) r7 = *(u64 *)(r10 -8)")
+__msg("mark_precise: frame0: parent state regs= stack=-8:  R0_w=2 R6_w=1 R8_rw=map_value(map=.data.vals,ks=4,vs=16) R10=fp0 fp-8_rw=P1")
+__msg("mark_precise: frame0: last_idx 18 first_idx 0 subseq_idx 7")
+__msg("mark_precise: frame0: regs= stack=-8 before 18: (95) exit")
+__msg("mark_precise: frame1: regs= stack= before 17: (0f) r0 += r2")
+__msg("mark_precise: frame1: regs= stack= before 16: (79) r2 = *(u64 *)(r1 +0)")
+__msg("mark_precise: frame1: regs= stack= before 15: (79) r0 = *(u64 *)(r10 -16)")
+__msg("mark_precise: frame1: regs= stack= before 14: (7b) *(u64 *)(r10 -16) = r2")
+__msg("mark_precise: frame1: regs= stack= before 13: (7b) *(u64 *)(r1 +0) = r2")
+__msg("mark_precise: frame1: regs=r2 stack= before 6: (85) call pc+6")
+__msg("mark_precise: frame0: regs=r2 stack= before 5: (bf) r2 = r6")
+__msg("mark_precise: frame0: regs=r6 stack= before 4: (07) r1 += -8")
+__msg("mark_precise: frame0: regs=r6 stack= before 3: (bf) r1 = r10")
+__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 1")
 __naked int subprog_spill_into_parent_stack_slot_precise(void)
 {
 	asm volatile (
diff --git a/tools/testing/selftests/bpf/verifier/precise.c b/tools/testing/selftests/bpf/verifier/precise.c
index 0d84dd1f38b6..8a2ff81d8350 100644
--- a/tools/testing/selftests/bpf/verifier/precise.c
+++ b/tools/testing/selftests/bpf/verifier/precise.c
@@ -140,10 +140,11 @@
 	.result = REJECT,
 },
 {
-	"precise: ST insn causing spi > allocated_stack",
+	"precise: ST zero to stack insn is supported",
 	.insns = {
 	BPF_MOV64_REG(BPF_REG_3, BPF_REG_10),
 	BPF_JMP_IMM(BPF_JNE, BPF_REG_3, 123, 0),
+	/* not a register spill, so we stop precision propagation for R4 here */
 	BPF_ST_MEM(BPF_DW, BPF_REG_3, -8, 0),
 	BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8),
 	BPF_MOV64_IMM(BPF_REG_0, -1),
@@ -157,11 +158,11 @@
 	mark_precise: frame0: last_idx 4 first_idx 2\
 	mark_precise: frame0: regs=r4 stack= before 4\
 	mark_precise: frame0: regs=r4 stack= before 3\
-	mark_precise: frame0: regs= stack=-8 before 2\
-	mark_precise: frame0: falling back to forcing all scalars precise\
-	force_precise: frame0: forcing r0 to be precise\
 	mark_precise: frame0: last_idx 5 first_idx 5\
-	mark_precise: frame0: parent state regs= stack=:",
+	mark_precise: frame0: parent state regs=r0 stack=:\
+	mark_precise: frame0: last_idx 4 first_idx 2\
+	mark_precise: frame0: regs=r0 stack= before 4\
+	5: R0=-1 R4=0",
 	.result = VERBOSE_ACCEPT,
 	.retval = -1,
 },
@@ -169,6 +170,8 @@
 	"precise: STX insn causing spi > allocated_stack",
 	.insns = {
 	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
+	/* make later reg spill more interesting by having somewhat known scalar */
+	BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0xff),
 	BPF_MOV64_REG(BPF_REG_3, BPF_REG_10),
 	BPF_JMP_IMM(BPF_JNE, BPF_REG_3, 123, 0),
 	BPF_STX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, -8),
@@ -179,18 +182,21 @@
 	},
 	.prog_type = BPF_PROG_TYPE_XDP,
 	.flags = BPF_F_TEST_STATE_FREQ,
-	.errstr = "mark_precise: frame0: last_idx 6 first_idx 6\
+	.errstr = "mark_precise: frame0: last_idx 7 first_idx 7\
 	mark_precise: frame0: parent state regs=r4 stack=:\
-	mark_precise: frame0: last_idx 5 first_idx 3\
-	mark_precise: frame0: regs=r4 stack= before 5\
-	mark_precise: frame0: regs=r4 stack= before 4\
-	mark_precise: frame0: regs= stack=-8 before 3\
-	mark_precise: frame0: falling back to forcing all scalars precise\
-	force_precise: frame0: forcing r0 to be precise\
-	force_precise: frame0: forcing r0 to be precise\
-	force_precise: frame0: forcing r0 to be precise\
-	force_precise: frame0: forcing r0 to be precise\
-	mark_precise: frame0: last_idx 6 first_idx 6\
+	mark_precise: frame0: last_idx 6 first_idx 4\
+	mark_precise: frame0: regs=r4 stack= before 6: (b7) r0 = -1\
+	mark_precise: frame0: regs=r4 stack= before 5: (79) r4 = *(u64 *)(r10 -8)\
+	mark_precise: frame0: regs= stack=-8 before 4: (7b) *(u64 *)(r3 -8) = r0\
+	mark_precise: frame0: parent state regs=r0 stack=:\
+	mark_precise: frame0: last_idx 3 first_idx 3\
+	mark_precise: frame0: regs=r0 stack= before 3: (55) if r3 != 0x7b goto pc+0\
+	mark_precise: frame0: regs=r0 stack= before 2: (bf) r3 = r10\
+	mark_precise: frame0: regs=r0 stack= before 1: (57) r0 &= 255\
+	mark_precise: frame0: parent state regs=r0 stack=:\
+	mark_precise: frame0: last_idx 0 first_idx 0\
+	mark_precise: frame0: regs=r0 stack= before 0: (85) call bpf_get_prandom_u32#7\
+	mark_precise: frame0: last_idx 7 first_idx 7\
 	mark_precise: frame0: parent state regs= stack=:",
 	.result = VERBOSE_ACCEPT,
 	.retval = -1,
-- 
cgit v1.2.3


From 9536af615dc9ded0357341e8bd0efc8b34b2b484 Mon Sep 17 00:00:00 2001
From: Chandrakanth patil <chandrakanth.patil@broadcom.com>
Date: Wed, 6 Dec 2023 00:46:29 +0530
Subject: scsi: mpi3mr: Support for preallocation of SGL BSG data buffers
 part-3

The driver acquires the required NVMe SGLs from the pre-allocated
pool.

Co-developed-by: Sathya Prakash <sathya.prakash@broadcom.com>
Signed-off-by: Sathya Prakash <sathya.prakash@broadcom.com>
Signed-off-by: Chandrakanth patil <chandrakanth.patil@broadcom.com>
Link: https://lore.kernel.org/r/20231205191630.12201-4-chandrakanth.patil@broadcom.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/mpi3mr/mpi3mr.h        |  10 +--
 drivers/scsi/mpi3mr/mpi3mr_app.c    | 124 +++++++++++++++++++++++++++++-------
 include/uapi/scsi/scsi_bsg_mpi3mr.h |   2 +
 3 files changed, 109 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/mpi3mr/mpi3mr.h b/drivers/scsi/mpi3mr/mpi3mr.h
index dfff3df3a666..795e86626101 100644
--- a/drivers/scsi/mpi3mr/mpi3mr.h
+++ b/drivers/scsi/mpi3mr/mpi3mr.h
@@ -218,14 +218,16 @@ extern atomic64_t event_counter;
  * @length: SGE length
  * @rsvd: Reserved
  * @rsvd1: Reserved
- * @sgl_type: sgl type
+ * @sub_type: sgl sub type
+ * @type: sgl type
  */
 struct mpi3mr_nvme_pt_sge {
-	u64 base_addr;
-	u32 length;
+	__le64 base_addr;
+	__le32 length;
 	u16 rsvd;
 	u8 rsvd1;
-	u8 sgl_type;
+	u8 sub_type:4;
+	u8 type:4;
 };
 
 /**
diff --git a/drivers/scsi/mpi3mr/mpi3mr_app.c b/drivers/scsi/mpi3mr/mpi3mr_app.c
index e8b0b121a6e3..4b93b7440da6 100644
--- a/drivers/scsi/mpi3mr/mpi3mr_app.c
+++ b/drivers/scsi/mpi3mr/mpi3mr_app.c
@@ -783,14 +783,20 @@ static int mpi3mr_build_nvme_sgl(struct mpi3mr_ioc *mrioc,
 	struct mpi3mr_buf_map *drv_bufs, u8 bufcnt)
 {
 	struct mpi3mr_nvme_pt_sge *nvme_sgl;
-	u64 sgl_ptr;
+	__le64 sgl_dma;
 	u8 count;
 	size_t length = 0;
+	u16 available_sges = 0, i;
+	u32 sge_element_size = sizeof(struct mpi3mr_nvme_pt_sge);
 	struct mpi3mr_buf_map *drv_buf_iter = drv_bufs;
 	u64 sgemod_mask = ((u64)((mrioc->facts.sge_mod_mask) <<
 			    mrioc->facts.sge_mod_shift) << 32);
 	u64 sgemod_val = ((u64)(mrioc->facts.sge_mod_value) <<
 			  mrioc->facts.sge_mod_shift) << 32;
+	u32 size;
+
+	nvme_sgl = (struct mpi3mr_nvme_pt_sge *)
+	    ((u8 *)(nvme_encap_request->command) + MPI3MR_NVME_CMD_SGL_OFFSET);
 
 	/*
 	 * Not all commands require a data transfer. If no data, just return
@@ -799,27 +805,59 @@ static int mpi3mr_build_nvme_sgl(struct mpi3mr_ioc *mrioc,
 	for (count = 0; count < bufcnt; count++, drv_buf_iter++) {
 		if (drv_buf_iter->data_dir == DMA_NONE)
 			continue;
-		sgl_ptr = (u64)drv_buf_iter->kern_buf_dma;
 		length = drv_buf_iter->kern_buf_len;
 		break;
 	}
-	if (!length)
+	if (!length || !drv_buf_iter->num_dma_desc)
 		return 0;
 
-	if (sgl_ptr & sgemod_mask) {
+	if (drv_buf_iter->num_dma_desc == 1) {
+		available_sges = 1;
+		goto build_sges;
+	}
+
+	sgl_dma = cpu_to_le64(mrioc->ioctl_chain_sge.dma_addr);
+	if (sgl_dma & sgemod_mask) {
 		dprint_bsg_err(mrioc,
-		    "%s: SGL address collides with SGE modifier\n",
+		    "%s: SGL chain address collides with SGE modifier\n",
 		    __func__);
 		return -1;
 	}
 
-	sgl_ptr &= ~sgemod_mask;
-	sgl_ptr |= sgemod_val;
-	nvme_sgl = (struct mpi3mr_nvme_pt_sge *)
-	    ((u8 *)(nvme_encap_request->command) + MPI3MR_NVME_CMD_SGL_OFFSET);
+	sgl_dma &= ~sgemod_mask;
+	sgl_dma |= sgemod_val;
+
+	memset(mrioc->ioctl_chain_sge.addr, 0, mrioc->ioctl_chain_sge.size);
+	available_sges = mrioc->ioctl_chain_sge.size / sge_element_size;
+	if (available_sges < drv_buf_iter->num_dma_desc)
+		return -1;
 	memset(nvme_sgl, 0, sizeof(struct mpi3mr_nvme_pt_sge));
-	nvme_sgl->base_addr = sgl_ptr;
-	nvme_sgl->length = length;
+	nvme_sgl->base_addr = sgl_dma;
+	size = drv_buf_iter->num_dma_desc * sizeof(struct mpi3mr_nvme_pt_sge);
+	nvme_sgl->length = cpu_to_le32(size);
+	nvme_sgl->type = MPI3MR_NVMESGL_LAST_SEGMENT;
+	nvme_sgl = (struct mpi3mr_nvme_pt_sge *)mrioc->ioctl_chain_sge.addr;
+
+build_sges:
+	for (i = 0; i < drv_buf_iter->num_dma_desc; i++) {
+		sgl_dma = cpu_to_le64(drv_buf_iter->dma_desc[i].dma_addr);
+		if (sgl_dma & sgemod_mask) {
+			dprint_bsg_err(mrioc,
+				       "%s: SGL address collides with SGE modifier\n",
+				       __func__);
+		return -1;
+		}
+
+		sgl_dma &= ~sgemod_mask;
+		sgl_dma |= sgemod_val;
+
+		nvme_sgl->base_addr = sgl_dma;
+		nvme_sgl->length = cpu_to_le32(drv_buf_iter->dma_desc[i].size);
+		nvme_sgl->type = MPI3MR_NVMESGL_DATA_SEGMENT;
+		nvme_sgl++;
+		available_sges--;
+	}
+
 	return 0;
 }
 
@@ -847,7 +885,7 @@ static int mpi3mr_build_nvme_prp(struct mpi3mr_ioc *mrioc,
 	dma_addr_t prp_entry_dma, prp_page_dma, dma_addr;
 	u32 offset, entry_len, dev_pgsz;
 	u32 page_mask_result, page_mask;
-	size_t length = 0;
+	size_t length = 0, desc_len;
 	u8 count;
 	struct mpi3mr_buf_map *drv_buf_iter = drv_bufs;
 	u64 sgemod_mask = ((u64)((mrioc->facts.sge_mod_mask) <<
@@ -856,6 +894,7 @@ static int mpi3mr_build_nvme_prp(struct mpi3mr_ioc *mrioc,
 			  mrioc->facts.sge_mod_shift) << 32;
 	u16 dev_handle = nvme_encap_request->dev_handle;
 	struct mpi3mr_tgt_dev *tgtdev;
+	u16 desc_count = 0;
 
 	tgtdev = mpi3mr_get_tgtdev_by_handle(mrioc, dev_handle);
 	if (!tgtdev) {
@@ -874,6 +913,21 @@ static int mpi3mr_build_nvme_prp(struct mpi3mr_ioc *mrioc,
 
 	dev_pgsz = 1 << (tgtdev->dev_spec.pcie_inf.pgsz);
 	mpi3mr_tgtdev_put(tgtdev);
+	page_mask = dev_pgsz - 1;
+
+	if (dev_pgsz > MPI3MR_IOCTL_SGE_SIZE) {
+		dprint_bsg_err(mrioc,
+			       "%s: NVMe device page size(%d) is greater than ioctl data sge size(%d) for handle 0x%04x\n",
+			       __func__, dev_pgsz,  MPI3MR_IOCTL_SGE_SIZE, dev_handle);
+		return -1;
+	}
+
+	if (MPI3MR_IOCTL_SGE_SIZE % dev_pgsz) {
+		dprint_bsg_err(mrioc,
+			       "%s: ioctl data sge size(%d) is not a multiple of NVMe device page size(%d) for handle 0x%04x\n",
+			       __func__, MPI3MR_IOCTL_SGE_SIZE, dev_pgsz, dev_handle);
+		return -1;
+	}
 
 	/*
 	 * Not all commands require a data transfer. If no data, just return
@@ -882,14 +936,26 @@ static int mpi3mr_build_nvme_prp(struct mpi3mr_ioc *mrioc,
 	for (count = 0; count < bufcnt; count++, drv_buf_iter++) {
 		if (drv_buf_iter->data_dir == DMA_NONE)
 			continue;
-		dma_addr = drv_buf_iter->kern_buf_dma;
 		length = drv_buf_iter->kern_buf_len;
 		break;
 	}
 
-	if (!length)
+	if (!length || !drv_buf_iter->num_dma_desc)
 		return 0;
 
+	for (count = 0; count < drv_buf_iter->num_dma_desc; count++) {
+		dma_addr = drv_buf_iter->dma_desc[count].dma_addr;
+		if (dma_addr & page_mask) {
+			dprint_bsg_err(mrioc,
+				       "%s:dma_addr 0x%llx is not aligned with page size 0x%x\n",
+				       __func__,  dma_addr, dev_pgsz);
+			return -1;
+		}
+	}
+
+	dma_addr = drv_buf_iter->dma_desc[0].dma_addr;
+	desc_len = drv_buf_iter->dma_desc[0].size;
+
 	mrioc->prp_sz = 0;
 	mrioc->prp_list_virt = dma_alloc_coherent(&mrioc->pdev->dev,
 	    dev_pgsz, &mrioc->prp_list_dma, GFP_KERNEL);
@@ -919,7 +985,6 @@ static int mpi3mr_build_nvme_prp(struct mpi3mr_ioc *mrioc,
 	 * Check if we are within 1 entry of a page boundary we don't
 	 * want our first entry to be a PRP List entry.
 	 */
-	page_mask = dev_pgsz - 1;
 	page_mask_result = (uintptr_t)((u8 *)prp_page + prp_size) & page_mask;
 	if (!page_mask_result) {
 		dprint_bsg_err(mrioc, "%s: PRP page is not page aligned\n",
@@ -1033,18 +1098,31 @@ static int mpi3mr_build_nvme_prp(struct mpi3mr_ioc *mrioc,
 			prp_entry_dma += prp_size;
 		}
 
-		/*
-		 * Bump the phys address of the command's data buffer by the
-		 * entry_len.
-		 */
-		dma_addr += entry_len;
-
 		/* decrement length accounting for last partial page. */
-		if (entry_len > length)
+		if (entry_len >= length) {
 			length = 0;
-		else
+		} else {
+			if (entry_len <= desc_len) {
+				dma_addr += entry_len;
+				desc_len -= entry_len;
+			}
+			if (!desc_len) {
+				if ((++desc_count) >=
+				   drv_buf_iter->num_dma_desc) {
+					dprint_bsg_err(mrioc,
+						       "%s: Invalid len %ld while building PRP\n",
+						       __func__, length);
+					goto err_out;
+				}
+				dma_addr =
+				    drv_buf_iter->dma_desc[desc_count].dma_addr;
+				desc_len =
+				    drv_buf_iter->dma_desc[desc_count].size;
+			}
 			length -= entry_len;
+		}
 	}
+
 	return 0;
 err_out:
 	if (mrioc->prp_list_virt) {
diff --git a/include/uapi/scsi/scsi_bsg_mpi3mr.h b/include/uapi/scsi/scsi_bsg_mpi3mr.h
index 907d345f04f9..c72ce387286a 100644
--- a/include/uapi/scsi/scsi_bsg_mpi3mr.h
+++ b/include/uapi/scsi/scsi_bsg_mpi3mr.h
@@ -491,6 +491,8 @@ struct mpi3_nvme_encapsulated_error_reply {
 #define MPI3MR_NVME_DATA_FORMAT_PRP	0
 #define MPI3MR_NVME_DATA_FORMAT_SGL1	1
 #define MPI3MR_NVME_DATA_FORMAT_SGL2	2
+#define MPI3MR_NVMESGL_DATA_SEGMENT	0x00
+#define MPI3MR_NVMESGL_LAST_SEGMENT	0x03
 
 /* MPI3: task management related definitions */
 struct mpi3_scsi_task_mgmt_request {
-- 
cgit v1.2.3


From 0949dd96dffec39683c6066cf8d0877cebc321ec Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Tue, 21 Nov 2023 13:44:25 +0000
Subject: drivers: base: Allow parts of GENERIC_CPU_DEVICES to be overridden

Architectures often have extra per-cpu work that needs doing
before a CPU is registered, often to determine if a CPU is
hotpluggable.

To allow the ACPI architectures to use GENERIC_CPU_DEVICES, move
the cpu_register() call into arch_register_cpu(), which is made __weak
so architectures with extra work can override it.
This aligns with the way x86, ia64 and loongarch register hotplug CPUs
when they become present.

Signed-off-by: James Morse <james.morse@arm.com>
Reviewed-by: Shaoqin Huang <shahuang@redhat.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Signed-off-by: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/E1r5R3B-00Csz6-Uh@rmk-PC.armlinux.org.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/cpu.c  | 14 ++++++++++----
 include/linux/cpu.h |  4 ++++
 2 files changed, 14 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 34b48f660b6b..579064fda97b 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -525,19 +525,25 @@ bool cpu_is_hotpluggable(unsigned int cpu)
 EXPORT_SYMBOL_GPL(cpu_is_hotpluggable);
 
 #ifdef CONFIG_GENERIC_CPU_DEVICES
-static DEFINE_PER_CPU(struct cpu, cpu_devices);
+DEFINE_PER_CPU(struct cpu, cpu_devices);
+
+int __weak arch_register_cpu(int cpu)
+{
+	return register_cpu(&per_cpu(cpu_devices, cpu), cpu);
+}
 #endif
 
 static void __init cpu_dev_register_generic(void)
 {
-#ifdef CONFIG_GENERIC_CPU_DEVICES
 	int i;
 
+	if (!IS_ENABLED(CONFIG_GENERIC_CPU_DEVICES))
+		return;
+
 	for_each_present_cpu(i) {
-		if (register_cpu(&per_cpu(cpu_devices, i), i))
+		if (arch_register_cpu(i))
 			panic("Failed to register CPU device");
 	}
-#endif
 }
 
 #ifdef CONFIG_GENERIC_CPU_VULNERABILITIES
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index fc8094419084..1e982d63eae8 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -88,6 +88,10 @@ extern ssize_t arch_cpu_probe(const char *, size_t);
 extern ssize_t arch_cpu_release(const char *, size_t);
 #endif
 
+#ifdef CONFIG_GENERIC_CPU_DEVICES
+DECLARE_PER_CPU(struct cpu, cpu_devices);
+#endif
+
 /*
  * These states are not related to the core CPU hotplug mechanism. They are
  * used by various (sub)architectures to track internal state
-- 
cgit v1.2.3


From bb5e44fb3be685ecb3feb120aca4269a92cc84cf Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Tue, 21 Nov 2023 13:44:36 +0000
Subject: drivers: base: add arch_cpu_is_hotpluggable()

The differences between architecture specific implementations of
arch_register_cpu() are down to whether the CPU is hotpluggable or not.
Rather than overriding the weak version of arch_register_cpu(), provide
a function that can be used to provide this detail instead.

Reviewed-by: Shaoqin Huang <shahuang@redhat.com>
Signed-off-by: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/E1r5R3M-00CszH-6r@rmk-PC.armlinux.org.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/cpu.c  | 11 ++++++++++-
 include/linux/cpu.h |  1 +
 2 files changed, 11 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 58bb86091b34..221ffbeb1c9b 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -527,9 +527,18 @@ EXPORT_SYMBOL_GPL(cpu_is_hotpluggable);
 #ifdef CONFIG_GENERIC_CPU_DEVICES
 DEFINE_PER_CPU(struct cpu, cpu_devices);
 
+bool __weak arch_cpu_is_hotpluggable(int cpu)
+{
+	return false;
+}
+
 int __weak arch_register_cpu(int cpu)
 {
-	return register_cpu(&per_cpu(cpu_devices, cpu), cpu);
+	struct cpu *c = &per_cpu(cpu_devices, cpu);
+
+	c->hotpluggable = arch_cpu_is_hotpluggable(cpu);
+
+	return register_cpu(c, cpu);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 1e982d63eae8..dcb89c987164 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -80,6 +80,7 @@ extern __printf(4, 5)
 struct device *cpu_device_create(struct device *parent, void *drvdata,
 				 const struct attribute_group **groups,
 				 const char *fmt, ...);
+extern bool arch_cpu_is_hotpluggable(int cpu);
 extern int arch_register_cpu(int cpu);
 extern void arch_unregister_cpu(int cpu);
 #ifdef CONFIG_HOTPLUG_CPU
-- 
cgit v1.2.3


From 58d3aade20cdddbac6c9707ac0f3f5f8c1278b74 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 4 Dec 2023 17:08:05 +0100
Subject: tcp: fix mid stream window clamp.

After the blamed commit below, if the user-space application performs
window clamping when tp->rcv_wnd is 0, the TCP socket will never be
able to announce a non 0 receive window, even after completely emptying
the receive buffer and re-setting the window clamp to higher values.

Refactor tcp_set_window_clamp() to address the issue: when the user
decreases the current clamp value, set rcv_ssthresh according to the
same logic used at buffer initialization, but ensuring reserved mem
provisioning.

To avoid code duplication factor-out the relevant bits from
tcp_adjust_rcv_ssthresh() in a new helper and reuse it in the above
scenario.

When increasing the clamp value, give the rcv_ssthresh a chance to grow
according to previously implemented heuristic.

Fixes: 3aa7857fe1d7 ("tcp: enable mid stream window clamp")
Reported-by: David Gibson <david@gibson.dropbear.id.au>
Reported-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/705dad54e6e6e9a010e571bf58e0b35a8ae70503.1701706073.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/tcp.h |  9 +++++++--
 net/ipv4/tcp.c    | 22 +++++++++++++++++++---
 2 files changed, 26 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index d2f0736b76b8..144ba48bb07b 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1514,17 +1514,22 @@ static inline int tcp_full_space(const struct sock *sk)
 	return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf));
 }
 
-static inline void tcp_adjust_rcv_ssthresh(struct sock *sk)
+static inline void __tcp_adjust_rcv_ssthresh(struct sock *sk, u32 new_ssthresh)
 {
 	int unused_mem = sk_unused_reserved_mem(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss);
+	tp->rcv_ssthresh = min(tp->rcv_ssthresh, new_ssthresh);
 	if (unused_mem)
 		tp->rcv_ssthresh = max_t(u32, tp->rcv_ssthresh,
 					 tcp_win_from_space(sk, unused_mem));
 }
 
+static inline void tcp_adjust_rcv_ssthresh(struct sock *sk)
+{
+	__tcp_adjust_rcv_ssthresh(sk, 4U * tcp_sk(sk)->advmss);
+}
+
 void tcp_cleanup_rbuf(struct sock *sk, int copied);
 void __tcp_cleanup_rbuf(struct sock *sk, int copied);
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 53bcc17c91e4..c9f078224569 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3368,9 +3368,25 @@ int tcp_set_window_clamp(struct sock *sk, int val)
 			return -EINVAL;
 		tp->window_clamp = 0;
 	} else {
-		tp->window_clamp = val < SOCK_MIN_RCVBUF / 2 ?
-			SOCK_MIN_RCVBUF / 2 : val;
-		tp->rcv_ssthresh = min(tp->rcv_wnd, tp->window_clamp);
+		u32 new_rcv_ssthresh, old_window_clamp = tp->window_clamp;
+		u32 new_window_clamp = val < SOCK_MIN_RCVBUF / 2 ?
+						SOCK_MIN_RCVBUF / 2 : val;
+
+		if (new_window_clamp == old_window_clamp)
+			return 0;
+
+		tp->window_clamp = new_window_clamp;
+		if (new_window_clamp < old_window_clamp) {
+			/* need to apply the reserved mem provisioning only
+			 * when shrinking the window clamp
+			 */
+			__tcp_adjust_rcv_ssthresh(sk, tp->window_clamp);
+
+		} else {
+			new_rcv_ssthresh = min(tp->rcv_wnd, tp->window_clamp);
+			tp->rcv_ssthresh = max(new_rcv_ssthresh,
+					       tp->rcv_ssthresh);
+		}
 	}
 	return 0;
 }
-- 
cgit v1.2.3


From 43a71cd66b9c0a4af3d15d8644359fde35bdbed0 Mon Sep 17 00:00:00 2001
From: Coco Li <lixiaoyan@google.com>
Date: Mon, 4 Dec 2023 20:12:30 +0000
Subject: net-device: reorganize net_device fast path variables

Reorganize fast path variables on tx-txrx-rx order
Fastpath variables end after npinfo.

Below data generated with pahole on x86 architecture.

Fast path variables span cache lines before change: 12
Fast path variables span cache lines after change: 4

Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Coco Li <lixiaoyan@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20231204201232.520025-2-lixiaoyan@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdevice.h | 117 +++++++++++++++++++++++++---------------------
 net/core/dev.c            |  56 ++++++++++++++++++++++
 2 files changed, 120 insertions(+), 53 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5551177e024e..cb96aad6a6ee 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2097,6 +2097,70 @@ enum netdev_stat_type {
  */
 
 struct net_device {
+	/* Cacheline organization can be found documented in
+	 * Documentation/networking/net_cachelines/net_device.rst.
+	 * Please update the document when adding new fields.
+	 */
+
+	/* TX read-mostly hotpath */
+	__cacheline_group_begin(net_device_read_tx);
+	unsigned long long	priv_flags;
+	const struct net_device_ops *netdev_ops;
+	const struct header_ops *header_ops;
+	struct netdev_queue	*_tx;
+	unsigned int		real_num_tx_queues;
+	unsigned int		gso_max_size;
+	unsigned int		gso_ipv4_max_size;
+	u16			gso_max_segs;
+	s16			num_tc;
+	/* Note : dev->mtu is often read without holding a lock.
+	 * Writers usually hold RTNL.
+	 * It is recommended to use READ_ONCE() to annotate the reads,
+	 * and to use WRITE_ONCE() to annotate the writes.
+	 */
+	unsigned int		mtu;
+	unsigned short		needed_headroom;
+	struct netdev_tc_txq	tc_to_txq[TC_MAX_QUEUE];
+#ifdef CONFIG_XPS
+	struct xps_dev_maps __rcu *xps_maps[XPS_MAPS_MAX];
+#endif
+#ifdef CONFIG_NETFILTER_EGRESS
+	struct nf_hook_entries __rcu *nf_hooks_egress;
+#endif
+#ifdef CONFIG_NET_XGRESS
+	struct bpf_mprog_entry __rcu *tcx_egress;
+#endif
+	__cacheline_group_end(net_device_read_tx);
+
+	/* TXRX read-mostly hotpath */
+	__cacheline_group_begin(net_device_read_txrx);
+	unsigned int		flags;
+	unsigned short		hard_header_len;
+	netdev_features_t	features;
+	struct inet6_dev __rcu	*ip6_ptr;
+	__cacheline_group_end(net_device_read_txrx);
+
+	/* RX read-mostly hotpath */
+	__cacheline_group_begin(net_device_read_rx);
+	struct list_head	ptype_specific;
+	int			ifindex;
+	unsigned int		real_num_rx_queues;
+	struct netdev_rx_queue	*_rx;
+	unsigned long		gro_flush_timeout;
+	int			napi_defer_hard_irqs;
+	unsigned int		gro_max_size;
+	unsigned int		gro_ipv4_max_size;
+	rx_handler_func_t __rcu	*rx_handler;
+	void __rcu		*rx_handler_data;
+	possible_net_t			nd_net;
+#ifdef CONFIG_NETPOLL
+	struct netpoll_info __rcu	*npinfo;
+#endif
+#ifdef CONFIG_NET_XGRESS
+	struct bpf_mprog_entry __rcu *tcx_ingress;
+#endif
+	__cacheline_group_end(net_device_read_rx);
+
 	char			name[IFNAMSIZ];
 	struct netdev_name_node	*name_node;
 	struct dev_ifalias	__rcu *ifalias;
@@ -2121,7 +2185,6 @@ struct net_device {
 	struct list_head	unreg_list;
 	struct list_head	close_list;
 	struct list_head	ptype_all;
-	struct list_head	ptype_specific;
 
 	struct {
 		struct list_head upper;
@@ -2129,26 +2192,13 @@ struct net_device {
 	} adj_list;
 
 	/* Read-mostly cache-line for fast-path access */
-	unsigned int		flags;
 	xdp_features_t		xdp_features;
-	unsigned long long	priv_flags;
-	const struct net_device_ops *netdev_ops;
 	const struct xdp_metadata_ops *xdp_metadata_ops;
 	const struct xsk_tx_metadata_ops *xsk_tx_metadata_ops;
-	int			ifindex;
 	unsigned short		gflags;
-	unsigned short		hard_header_len;
 
-	/* Note : dev->mtu is often read without holding a lock.
-	 * Writers usually hold RTNL.
-	 * It is recommended to use READ_ONCE() to annotate the reads,
-	 * and to use WRITE_ONCE() to annotate the writes.
-	 */
-	unsigned int		mtu;
-	unsigned short		needed_headroom;
 	unsigned short		needed_tailroom;
 
-	netdev_features_t	features;
 	netdev_features_t	hw_features;
 	netdev_features_t	wanted_features;
 	netdev_features_t	vlan_features;
@@ -2192,8 +2242,6 @@ struct net_device {
 	const struct tlsdev_ops *tlsdev_ops;
 #endif
 
-	const struct header_ops *header_ops;
-
 	unsigned char		operstate;
 	unsigned char		link_mode;
 
@@ -2234,9 +2282,7 @@ struct net_device {
 
 
 	/* Protocol-specific pointers */
-
 	struct in_device __rcu	*ip_ptr;
-	struct inet6_dev __rcu	*ip6_ptr;
 #if IS_ENABLED(CONFIG_VLAN_8021Q)
 	struct vlan_info __rcu	*vlan_info;
 #endif
@@ -2271,26 +2317,14 @@ struct net_device {
 	/* Interface address info used in eth_type_trans() */
 	const unsigned char	*dev_addr;
 
-	struct netdev_rx_queue	*_rx;
 	unsigned int		num_rx_queues;
-	unsigned int		real_num_rx_queues;
-
 	struct bpf_prog __rcu	*xdp_prog;
-	unsigned long		gro_flush_timeout;
-	int			napi_defer_hard_irqs;
 #define GRO_LEGACY_MAX_SIZE	65536u
 /* TCP minimal MSS is 8 (TCP_MIN_GSO_SIZE),
  * and shinfo->gso_segs is a 16bit field.
  */
 #define GRO_MAX_SIZE		(8 * 65535u)
-	unsigned int		gro_max_size;
-	unsigned int		gro_ipv4_max_size;
 	unsigned int		xdp_zc_max_segs;
-	rx_handler_func_t __rcu	*rx_handler;
-	void __rcu		*rx_handler_data;
-#ifdef CONFIG_NET_XGRESS
-	struct bpf_mprog_entry __rcu *tcx_ingress;
-#endif
 	struct netdev_queue __rcu *ingress_queue;
 #ifdef CONFIG_NETFILTER_INGRESS
 	struct nf_hook_entries __rcu *nf_hooks_ingress;
@@ -2305,25 +2339,13 @@ struct net_device {
 /*
  * Cache lines mostly used on transmit path
  */
-	struct netdev_queue	*_tx ____cacheline_aligned_in_smp;
 	unsigned int		num_tx_queues;
-	unsigned int		real_num_tx_queues;
 	struct Qdisc __rcu	*qdisc;
 	unsigned int		tx_queue_len;
 	spinlock_t		tx_global_lock;
 
 	struct xdp_dev_bulk_queue __percpu *xdp_bulkq;
 
-#ifdef CONFIG_XPS
-	struct xps_dev_maps __rcu *xps_maps[XPS_MAPS_MAX];
-#endif
-#ifdef CONFIG_NET_XGRESS
-	struct bpf_mprog_entry __rcu *tcx_egress;
-#endif
-#ifdef CONFIG_NETFILTER_EGRESS
-	struct nf_hook_entries __rcu *nf_hooks_egress;
-#endif
-
 #ifdef CONFIG_NET_SCHED
 	DECLARE_HASHTABLE	(qdisc_hash, 4);
 #endif
@@ -2362,12 +2384,6 @@ struct net_device {
 	bool needs_free_netdev;
 	void (*priv_destructor)(struct net_device *dev);
 
-#ifdef CONFIG_NETPOLL
-	struct netpoll_info __rcu	*npinfo;
-#endif
-
-	possible_net_t			nd_net;
-
 	/* mid-layer private */
 	void				*ml_priv;
 	enum netdev_ml_priv_type	ml_priv_type;
@@ -2402,20 +2418,15 @@ struct net_device {
  */
 #define GSO_MAX_SIZE		(8 * GSO_MAX_SEGS)
 
-	unsigned int		gso_max_size;
 #define TSO_LEGACY_MAX_SIZE	65536
 #define TSO_MAX_SIZE		UINT_MAX
 	unsigned int		tso_max_size;
-	u16			gso_max_segs;
 #define TSO_MAX_SEGS		U16_MAX
 	u16			tso_max_segs;
-	unsigned int		gso_ipv4_max_size;
 
 #ifdef CONFIG_DCB
 	const struct dcbnl_rtnl_ops *dcbnl_ops;
 #endif
-	s16			num_tc;
-	struct netdev_tc_txq	tc_to_txq[TC_MAX_QUEUE];
 	u8			prio_tc_map[TC_BITMASK + 1];
 
 #if IS_ENABLED(CONFIG_FCOE)
diff --git a/net/core/dev.c b/net/core/dev.c
index 1d720fc59161..c5679dfbaa70 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -11609,6 +11609,60 @@ static struct pernet_operations __net_initdata default_device_ops = {
 	.exit_batch = default_device_exit_batch,
 };
 
+static void __init net_dev_struct_check(void)
+{
+	/* TX read-mostly hotpath */
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, priv_flags);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, netdev_ops);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, header_ops);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, _tx);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, real_num_tx_queues);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_max_size);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_ipv4_max_size);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_max_segs);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, num_tc);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, mtu);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, needed_headroom);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, tc_to_txq);
+#ifdef CONFIG_XPS
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, xps_maps);
+#endif
+#ifdef CONFIG_NETFILTER_EGRESS
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, nf_hooks_egress);
+#endif
+#ifdef CONFIG_NET_XGRESS
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, tcx_egress);
+#endif
+	CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_tx, 152);
+
+	/* TXRX read-mostly hotpath */
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, flags);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, hard_header_len);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, features);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, ip6_ptr);
+	CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_txrx, 30);
+
+	/* RX read-mostly hotpath */
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, ptype_specific);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, ifindex);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, real_num_rx_queues);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, _rx);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, gro_flush_timeout);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, napi_defer_hard_irqs);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, gro_max_size);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, gro_ipv4_max_size);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, rx_handler);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, rx_handler_data);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, nd_net);
+#ifdef CONFIG_NETPOLL
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, npinfo);
+#endif
+#ifdef CONFIG_NET_XGRESS
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, tcx_ingress);
+#endif
+	CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_rx, 96);
+}
+
 /*
  *	Initialize the DEV module. At boot time this walks the device list and
  *	unhooks any devices that fail to initialise (normally hardware not
@@ -11626,6 +11680,8 @@ static int __init net_dev_init(void)
 
 	BUG_ON(!dev_boot_phase);
 
+	net_dev_struct_check();
+
 	if (dev_proc_init())
 		goto out;
 
-- 
cgit v1.2.3


From d5fed5addb2b6bc13035de4338b7ea2052a2e006 Mon Sep 17 00:00:00 2001
From: Coco Li <lixiaoyan@google.com>
Date: Mon, 4 Dec 2023 20:12:31 +0000
Subject: tcp: reorganize tcp_sock fast path variables

The variables are organized according in the following way:

- TX read-mostly hotpath cache lines
- TXRX read-mostly hotpath cache lines
- RX read-mostly hotpath cache lines
- TX read-write hotpath cache line
- TXRX read-write hotpath cache line
- RX read-write hotpath cache line

Fastpath cachelines end after rcvq_space.

Cache line boundaries are enforced only between read-mostly and
read-write. That is, if read-mostly tx cachelines bleed into
read-mostly txrx cachelines, we do not care. We care about the
boundaries between read and write cachelines because we want
to prevent false sharing.

Fast path variables span cache lines before change: 12
Fast path variables span cache lines after change: 8

Suggested-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Wei Wang <weiwan@google.com>
Signed-off-by: Coco Li <lixiaoyan@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20231204201232.520025-3-lixiaoyan@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/tcp.h | 248 ++++++++++++++++++++++++++++------------------------
 net/ipv4/tcp.c      |  93 ++++++++++++++++++++
 2 files changed, 227 insertions(+), 114 deletions(-)

(limited to 'include')

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 68f3d315d2e1..f55ec155f5b7 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -194,23 +194,121 @@ static inline bool tcp_rsk_used_ao(const struct request_sock *req)
 #define TCP_RMEM_TO_WIN_SCALE 8
 
 struct tcp_sock {
+	/* Cacheline organization can be found documented in
+	 * Documentation/networking/net_cachelines/tcp_sock.rst.
+	 * Please update the document when adding new fields.
+	 */
+
 	/* inet_connection_sock has to be the first member of tcp_sock */
 	struct inet_connection_sock	inet_conn;
-	u16	tcp_header_len;	/* Bytes of tcp header to send		*/
+
+	/* TX read-mostly hotpath cache lines */
+	__cacheline_group_begin(tcp_sock_read_tx);
+	/* timestamp of last sent data packet (for restart window) */
+	u32	max_window;	/* Maximal window ever seen from peer	*/
+	u32	rcv_ssthresh;	/* Current window clamp			*/
+	u32	reordering;	/* Packet reordering metric.		*/
+	u32	notsent_lowat;	/* TCP_NOTSENT_LOWAT */
 	u16	gso_segs;	/* Max number of segs per GSO packet	*/
+	/* from STCP, retrans queue hinting */
+	struct sk_buff *lost_skb_hint;
+	struct sk_buff *retransmit_skb_hint;
+	__cacheline_group_end(tcp_sock_read_tx);
+
+	/* TXRX read-mostly hotpath cache lines */
+	__cacheline_group_begin(tcp_sock_read_txrx);
+	u32	tsoffset;	/* timestamp offset */
+	u32	snd_wnd;	/* The window we expect to receive	*/
+	u32	mss_cache;	/* Cached effective mss, not including SACKS */
+	u32	snd_cwnd;	/* Sending congestion window		*/
+	u32	prr_out;	/* Total number of pkts sent during Recovery. */
+	u32	lost_out;	/* Lost packets			*/
+	u32	sacked_out;	/* SACK'd packets			*/
+	u16	tcp_header_len;	/* Bytes of tcp header to send		*/
+	u8	chrono_type : 2,	/* current chronograph type */
+		repair      : 1,
+		is_sack_reneg:1,    /* in recovery from loss with SACK reneg? */
+		is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */
+	__cacheline_group_end(tcp_sock_read_txrx);
+
+	/* RX read-mostly hotpath cache lines */
+	__cacheline_group_begin(tcp_sock_read_rx);
+	u32	copied_seq;	/* Head of yet unread data */
+	u32	rcv_tstamp;	/* timestamp of last received ACK (for keepalives) */
+	u32	snd_wl1;	/* Sequence for window update		*/
+	u32	tlp_high_seq;	/* snd_nxt at the time of TLP */
+	u32	rttvar_us;	/* smoothed mdev_max			*/
+	u32	retrans_out;	/* Retransmitted packets out		*/
+	u16	advmss;		/* Advertised MSS			*/
+	u16	urg_data;	/* Saved octet of OOB data and control flags */
+	u32	lost;		/* Total data packets lost incl. rexmits */
+	struct  minmax rtt_min;
+	/* OOO segments go in this rbtree. Socket lock must be held. */
+	struct rb_root	out_of_order_queue;
+	u32	snd_ssthresh;	/* Slow start size threshold		*/
+	__cacheline_group_end(tcp_sock_read_rx);
 
+	/* TX read-write hotpath cache lines */
+	__cacheline_group_begin(tcp_sock_write_tx) ____cacheline_aligned;
+	u32	segs_out;	/* RFC4898 tcpEStatsPerfSegsOut
+				 * The total number of segments sent.
+				 */
+	u32	data_segs_out;	/* RFC4898 tcpEStatsPerfDataSegsOut
+				 * total number of data segments sent.
+				 */
+	u64	bytes_sent;	/* RFC4898 tcpEStatsPerfHCDataOctetsOut
+				 * total number of data bytes sent.
+				 */
+	u32	snd_sml;	/* Last byte of the most recently transmitted small packet */
+	u32	chrono_start;	/* Start time in jiffies of a TCP chrono */
+	u32	chrono_stat[3];	/* Time in jiffies for chrono_stat stats */
+	u32	write_seq;	/* Tail(+1) of data held in tcp send buffer */
+	u32	pushed_seq;	/* Last pushed seq, required to talk to windows */
+	u32	lsndtime;
+	u32	mdev_us;	/* medium deviation			*/
+	u64	tcp_wstamp_ns;	/* departure time for next sent data packet */
+	u64	tcp_clock_cache; /* cache last tcp_clock_ns() (see tcp_mstamp_refresh()) */
+	u64	tcp_mstamp;	/* most recent packet received/sent */
+	u32	rtt_seq;	/* sequence number to update rttvar	*/
+	struct list_head tsorted_sent_queue; /* time-sorted sent but un-SACKed skbs */
+	struct sk_buff *highest_sack;   /* skb just after the highest
+					 * skb with SACKed bit set
+					 * (validity guaranteed only if
+					 * sacked_out > 0)
+					 */
+	u8	ecn_flags;	/* ECN status bits.			*/
+	__cacheline_group_end(tcp_sock_write_tx);
+
+	/* TXRX read-write hotpath cache lines */
+	__cacheline_group_begin(tcp_sock_write_txrx);
 /*
  *	Header prediction flags
  *	0x5?10 << 16 + snd_wnd in net byte order
  */
 	__be32	pred_flags;
-
+	u32	rcv_nxt;	/* What we want to receive next		*/
+	u32	snd_nxt;	/* Next sequence we send		*/
+	u32	snd_una;	/* First byte we want an ack for	*/
+	u32	window_clamp;	/* Maximal window to advertise		*/
+	u32	srtt_us;	/* smoothed round trip time << 3 in usecs */
+	u32	packets_out;	/* Packets which are "in flight"	*/
+	u32	snd_up;		/* Urgent pointer		*/
+	u32	delivered;	/* Total data packets delivered incl. rexmits */
+	u32	delivered_ce;	/* Like the above but only ECE marked packets */
+	u32	app_limited;	/* limited until "delivered" reaches this val */
+	u32	rcv_wnd;	/* Current receiver window		*/
 /*
- *	RFC793 variables by their proper names. This means you can
- *	read the code and the spec side by side (and laugh ...)
- *	See RFC793 and RFC1122. The RFC writes these in capitals.
+ *      Options received (usually on last packet, some only on SYN packets).
  */
-	u64	bytes_received;	/* RFC4898 tcpEStatsAppHCThruOctetsReceived
+	struct tcp_options_received rx_opt;
+	u8	nonagle     : 4,/* Disable Nagle algorithm?             */
+		rate_app_limited:1;  /* rate_{delivered,interval_us} limited? */
+	__cacheline_group_end(tcp_sock_write_txrx);
+
+	/* RX read-write hotpath cache lines */
+	__cacheline_group_begin(tcp_sock_write_rx);
+	u64	bytes_received;
+				/* RFC4898 tcpEStatsAppHCThruOctetsReceived
 				 * sum(delta(rcv_nxt)), or how many bytes
 				 * were acked.
 				 */
@@ -220,45 +318,44 @@ struct tcp_sock {
 	u32	data_segs_in;	/* RFC4898 tcpEStatsPerfDataSegsIn
 				 * total number of data segments in.
 				 */
- 	u32	rcv_nxt;	/* What we want to receive next 	*/
-	u32	copied_seq;	/* Head of yet unread data		*/
 	u32	rcv_wup;	/* rcv_nxt on last window update sent	*/
- 	u32	snd_nxt;	/* Next sequence we send		*/
-	u32	segs_out;	/* RFC4898 tcpEStatsPerfSegsOut
-				 * The total number of segments sent.
-				 */
-	u32	data_segs_out;	/* RFC4898 tcpEStatsPerfDataSegsOut
-				 * total number of data segments sent.
-				 */
-	u64	bytes_sent;	/* RFC4898 tcpEStatsPerfHCDataOctetsOut
-				 * total number of data bytes sent.
-				 */
+	u32	max_packets_out;  /* max packets_out in last window */
+	u32	cwnd_usage_seq;  /* right edge of cwnd usage tracking flight */
+	u32	rate_delivered;    /* saved rate sample: packets delivered */
+	u32	rate_interval_us;  /* saved rate sample: time elapsed */
+	u32	rcv_rtt_last_tsecr;
+	u64	first_tx_mstamp;  /* start of window send phase */
+	u64	delivered_mstamp; /* time we reached "delivered" */
 	u64	bytes_acked;	/* RFC4898 tcpEStatsAppHCThruOctetsAcked
 				 * sum(delta(snd_una)), or how many bytes
 				 * were acked.
 				 */
+	struct {
+		u32	rtt_us;
+		u32	seq;
+		u64	time;
+	} rcv_rtt_est;
+/* Receiver queue space */
+	struct {
+		u32	space;
+		u32	seq;
+		u64	time;
+	} rcvq_space;
+	__cacheline_group_end(tcp_sock_write_rx);
+	/* End of Hot Path */
+
+/*
+ *	RFC793 variables by their proper names. This means you can
+ *	read the code and the spec side by side (and laugh ...)
+ *	See RFC793 and RFC1122. The RFC writes these in capitals.
+ */
 	u32	dsack_dups;	/* RFC4898 tcpEStatsStackDSACKDups
 				 * total number of DSACK blocks received
 				 */
- 	u32	snd_una;	/* First byte we want an ack for	*/
- 	u32	snd_sml;	/* Last byte of the most recently transmitted small packet */
-	u32	rcv_tstamp;	/* timestamp of last received ACK (for keepalives) */
-	u32	lsndtime;	/* timestamp of last sent data packet (for restart window) */
 	u32	last_oow_ack_time;  /* timestamp of last out-of-window ACK */
 	u32	compressed_ack_rcv_nxt;
-
-	u32	tsoffset;	/* timestamp offset */
-
 	struct list_head tsq_node; /* anchor in tsq_tasklet.head list */
-	struct list_head tsorted_sent_queue; /* time-sorted sent but un-SACKed skbs */
-
-	u32	snd_wl1;	/* Sequence for window update		*/
-	u32	snd_wnd;	/* The window we expect to receive	*/
-	u32	max_window;	/* Maximal window ever seen from peer	*/
-	u32	mss_cache;	/* Cached effective mss, not including SACKS */
 
-	u32	window_clamp;	/* Maximal window to advertise		*/
-	u32	rcv_ssthresh;	/* Current window clamp			*/
 	u8	scaling_ratio;	/* see tcp_win_from_space() */
 	/* Information of the most recently (s)acked skb */
 	struct tcp_rack {
@@ -272,24 +369,16 @@ struct tcp_sock {
 		   dsack_seen:1, /* Whether DSACK seen after last adj */
 		   advanced:1;	 /* mstamp advanced since last lost marking */
 	} rack;
-	u16	advmss;		/* Advertised MSS			*/
 	u8	compressed_ack;
 	u8	dup_ack_counter:2,
 		tlp_retrans:1,	/* TLP is a retransmission */
 		tcp_usec_ts:1, /* TSval values in usec */
 		unused:4;
-	u32	chrono_start;	/* Start time in jiffies of a TCP chrono */
-	u32	chrono_stat[3];	/* Time in jiffies for chrono_stat stats */
-	u8	chrono_type:2,	/* current chronograph type */
-		rate_app_limited:1,  /* rate_{delivered,interval_us} limited? */
+	u8	thin_lto    : 1,/* Use linear timeouts for thin streams */
+		recvmsg_inq : 1,/* Indicate # of bytes in queue upon recvmsg */
 		fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */
 		fastopen_no_cookie:1, /* Allow send/recv SYN+data without a cookie */
-		is_sack_reneg:1,    /* in recovery from loss with SACK reneg? */
-		fastopen_client_fail:2; /* reason why fastopen failed */
-	u8	nonagle     : 4,/* Disable Nagle algorithm?             */
-		thin_lto    : 1,/* Use linear timeouts for thin streams */
-		recvmsg_inq : 1,/* Indicate # of bytes in queue upon recvmsg */
-		repair      : 1,
+		fastopen_client_fail:2, /* reason why fastopen failed */
 		frto        : 1;/* F-RTO (RFC5682) activated in CA_Loss */
 	u8	repair_queue;
 	u8	save_syn:2,	/* Save headers of SYN packet */
@@ -297,45 +386,19 @@ struct tcp_sock {
 		syn_fastopen:1,	/* SYN includes Fast Open option */
 		syn_fastopen_exp:1,/* SYN includes Fast Open exp. option */
 		syn_fastopen_ch:1, /* Active TFO re-enabling probe */
-		syn_data_acked:1,/* data in SYN is acked by SYN-ACK */
-		is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */
-	u32	tlp_high_seq;	/* snd_nxt at the time of TLP */
+		syn_data_acked:1;/* data in SYN is acked by SYN-ACK */
 
 	u32	tcp_tx_delay;	/* delay (in usec) added to TX packets */
-	u64	tcp_wstamp_ns;	/* departure time for next sent data packet */
-	u64	tcp_clock_cache; /* cache last tcp_clock_ns() (see tcp_mstamp_refresh()) */
 
 /* RTT measurement */
-	u64	tcp_mstamp;	/* most recent packet received/sent */
-	u32	srtt_us;	/* smoothed round trip time << 3 in usecs */
-	u32	mdev_us;	/* medium deviation			*/
 	u32	mdev_max_us;	/* maximal mdev for the last rtt period	*/
-	u32	rttvar_us;	/* smoothed mdev_max			*/
-	u32	rtt_seq;	/* sequence number to update rttvar	*/
-	struct  minmax rtt_min;
 
-	u32	packets_out;	/* Packets which are "in flight"	*/
-	u32	retrans_out;	/* Retransmitted packets out		*/
-	u32	max_packets_out;  /* max packets_out in last window */
-	u32	cwnd_usage_seq;  /* right edge of cwnd usage tracking flight */
-
-	u16	urg_data;	/* Saved octet of OOB data and control flags */
-	u8	ecn_flags;	/* ECN status bits.			*/
 	u8	keepalive_probes; /* num of allowed keep alive probes	*/
-	u32	reordering;	/* Packet reordering metric.		*/
 	u32	reord_seen;	/* number of data packet reordering events */
-	u32	snd_up;		/* Urgent pointer		*/
-
-/*
- *      Options received (usually on last packet, some only on SYN packets).
- */
-	struct tcp_options_received rx_opt;
 
 /*
  *	Slow start and congestion control (see also Nagle, and Karn & Partridge)
  */
- 	u32	snd_ssthresh;	/* Slow start size threshold		*/
- 	u32	snd_cwnd;	/* Sending congestion window		*/
 	u32	snd_cwnd_cnt;	/* Linear increase counter		*/
 	u32	snd_cwnd_clamp; /* Do not allow snd_cwnd to grow above this */
 	u32	snd_cwnd_used;
@@ -343,32 +406,10 @@ struct tcp_sock {
 	u32	prior_cwnd;	/* cwnd right before starting loss recovery */
 	u32	prr_delivered;	/* Number of newly delivered packets to
 				 * receiver in Recovery. */
-	u32	prr_out;	/* Total number of pkts sent during Recovery. */
-	u32	delivered;	/* Total data packets delivered incl. rexmits */
-	u32	delivered_ce;	/* Like the above but only ECE marked packets */
-	u32	lost;		/* Total data packets lost incl. rexmits */
-	u32	app_limited;	/* limited until "delivered" reaches this val */
-	u64	first_tx_mstamp;  /* start of window send phase */
-	u64	delivered_mstamp; /* time we reached "delivered" */
-	u32	rate_delivered;    /* saved rate sample: packets delivered */
-	u32	rate_interval_us;  /* saved rate sample: time elapsed */
-
- 	u32	rcv_wnd;	/* Current receiver window		*/
-	u32	write_seq;	/* Tail(+1) of data held in tcp send buffer */
-	u32	notsent_lowat;	/* TCP_NOTSENT_LOWAT */
-	u32	pushed_seq;	/* Last pushed seq, required to talk to windows */
-	u32	lost_out;	/* Lost packets			*/
-	u32	sacked_out;	/* SACK'd packets			*/
 
 	struct hrtimer	pacing_timer;
 	struct hrtimer	compressed_ack_timer;
 
-	/* from STCP, retrans queue hinting */
-	struct sk_buff* lost_skb_hint;
-	struct sk_buff *retransmit_skb_hint;
-
-	/* OOO segments go in this rbtree. Socket lock must be held. */
-	struct rb_root	out_of_order_queue;
 	struct sk_buff	*ooo_last_skb; /* cache rb_last(out_of_order_queue) */
 
 	/* SACKs data, these 2 need to be together (see tcp_options_write) */
@@ -377,12 +418,6 @@ struct tcp_sock {
 
 	struct tcp_sack_block recv_sack_cache[4];
 
-	struct sk_buff *highest_sack;   /* skb just after the highest
-					 * skb with SACKed bit set
-					 * (validity guaranteed only if
-					 * sacked_out > 0)
-					 */
-
 	int     lost_cnt_hint;
 
 	u32	prior_ssthresh; /* ssthresh saved at recovery start	*/
@@ -433,21 +468,6 @@ struct tcp_sock {
 
 	u32 rcv_ooopack; /* Received out-of-order packets, for tcpinfo */
 
-/* Receiver side RTT estimation */
-	u32 rcv_rtt_last_tsecr;
-	struct {
-		u32	rtt_us;
-		u32	seq;
-		u64	time;
-	} rcv_rtt_est;
-
-/* Receiver queue space */
-	struct {
-		u32	space;
-		u32	seq;
-		u64	time;
-	} rcvq_space;
-
 /* TCP-specific MTU probe information. */
 	struct {
 		u32		  probe_seq_start;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index a100df07d34a..70a1bafbefba 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -4564,6 +4564,97 @@ static void __init tcp_init_mem(void)
 	sysctl_tcp_mem[2] = sysctl_tcp_mem[0] * 2;	/* 9.37 % */
 }
 
+static void __init tcp_struct_check(void)
+{
+	/* TX read-mostly hotpath cache lines */
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, max_window);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, rcv_ssthresh);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, reordering);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, notsent_lowat);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, gso_segs);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, lost_skb_hint);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, retransmit_skb_hint);
+	CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_tx, 40);
+
+	/* TXRX read-mostly hotpath cache lines */
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, tsoffset);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, snd_wnd);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, mss_cache);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, snd_cwnd);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, prr_out);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, lost_out);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, sacked_out);
+	CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_txrx, 31);
+
+	/* RX read-mostly hotpath cache lines */
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, copied_seq);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, rcv_tstamp);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, snd_wl1);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, tlp_high_seq);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, rttvar_us);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, retrans_out);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, advmss);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, urg_data);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, lost);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, rtt_min);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, out_of_order_queue);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, snd_ssthresh);
+	CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_rx, 69);
+
+	/* TX read-write hotpath cache lines */
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, segs_out);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, data_segs_out);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, bytes_sent);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, snd_sml);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, chrono_start);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, chrono_stat);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, write_seq);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, pushed_seq);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, lsndtime);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, mdev_us);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tcp_wstamp_ns);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tcp_clock_cache);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tcp_mstamp);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, rtt_seq);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tsorted_sent_queue);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, highest_sack);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, ecn_flags);
+	CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_tx, 113);
+
+	/* TXRX read-write hotpath cache lines */
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, pred_flags);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rcv_nxt);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, snd_nxt);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, snd_una);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, window_clamp);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, srtt_us);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, packets_out);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, snd_up);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, delivered);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, delivered_ce);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, app_limited);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rcv_wnd);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rx_opt);
+	CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_txrx, 76);
+
+	/* RX read-write hotpath cache lines */
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, bytes_received);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, segs_in);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, data_segs_in);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcv_wup);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, max_packets_out);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, cwnd_usage_seq);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rate_delivered);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rate_interval_us);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcv_rtt_last_tsecr);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, first_tx_mstamp);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, delivered_mstamp);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, bytes_acked);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcv_rtt_est);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcvq_space);
+	CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_rx, 99);
+}
+
 void __init tcp_init(void)
 {
 	int max_rshare, max_wshare, cnt;
@@ -4574,6 +4665,8 @@ void __init tcp_init(void)
 	BUILD_BUG_ON(sizeof(struct tcp_skb_cb) >
 		     sizeof_field(struct sk_buff, cb));
 
+	tcp_struct_check();
+
 	percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL);
 
 	timer_setup(&tcp_orphan_timer, tcp_orphan_update, TIMER_DEFERRABLE);
-- 
cgit v1.2.3


From facd15dfd69122042502d99ab8c9f888b48ee994 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 4 Dec 2023 21:47:07 +0100
Subject: net: core: synchronize link-watch when carrier is queried

There are multiple ways to query for the carrier state: through
rtnetlink, sysfs, and (possibly) ethtool. Synchronize linkwatch
work before these operations so that we don't have a situation
where userspace queries the carrier state between the driver's
carrier off->on transition and linkwatch running and expects it
to work, when really (at least) TX cannot work until linkwatch
has run.

I previously posted a longer explanation of how this applies to
wireless [1] but with this wireless can simply query the state
before sending data, to ensure the kernel is ready for it.

[1] https://lore.kernel.org/all/346b21d87c69f817ea3c37caceb34f1f56255884.camel@sipsolutions.net/

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20231204214706.303c62768415.I1caedccae72ee5a45c9085c5eb49c145ce1c0dd5@changeid
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdevice.h | 9 +++++++++
 net/core/dev.c            | 2 +-
 net/core/dev.h            | 1 -
 net/core/link_watch.c     | 2 +-
 net/core/net-sysfs.c      | 8 +++++++-
 net/core/rtnetlink.c      | 8 ++++++++
 net/ethtool/ioctl.c       | 3 +++
 7 files changed, 29 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index cb96aad6a6ee..1b935ee341b4 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4229,6 +4229,15 @@ static inline void netdev_ref_replace(struct net_device *odev,
  */
 void linkwatch_fire_event(struct net_device *dev);
 
+/**
+ * linkwatch_sync_dev - sync linkwatch for the given device
+ * @dev: network device to sync linkwatch for
+ *
+ * Sync linkwatch for the given device, removing it from the
+ * pending work list (if queued).
+ */
+void linkwatch_sync_dev(struct net_device *dev);
+
 /**
  *	netif_carrier_ok - test if carrier present
  *	@dev: network device
diff --git a/net/core/dev.c b/net/core/dev.c
index c5679dfbaa70..0432b04cf9b0 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -10548,7 +10548,7 @@ void netdev_run_todo(void)
 		write_lock(&dev_base_lock);
 		dev->reg_state = NETREG_UNREGISTERED;
 		write_unlock(&dev_base_lock);
-		linkwatch_forget_dev(dev);
+		linkwatch_sync_dev(dev);
 	}
 
 	while (!list_empty(&list)) {
diff --git a/net/core/dev.h b/net/core/dev.h
index 7795b8ad841d..cf93e188785b 100644
--- a/net/core/dev.h
+++ b/net/core/dev.h
@@ -30,7 +30,6 @@ int __init dev_proc_init(void);
 #endif
 
 void linkwatch_init_dev(struct net_device *dev);
-void linkwatch_forget_dev(struct net_device *dev);
 void linkwatch_run_queue(void);
 
 void dev_addr_flush(struct net_device *dev);
diff --git a/net/core/link_watch.c b/net/core/link_watch.c
index c469d1c4db5d..a19f21403339 100644
--- a/net/core/link_watch.c
+++ b/net/core/link_watch.c
@@ -245,7 +245,7 @@ static void __linkwatch_run_queue(int urgent_only)
 	spin_unlock_irq(&lweventlist_lock);
 }
 
-void linkwatch_forget_dev(struct net_device *dev)
+void linkwatch_sync_dev(struct net_device *dev)
 {
 	unsigned long flags;
 	int clean = 0;
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index fccaa5bac0ed..d9b33e923b18 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -194,8 +194,14 @@ static ssize_t carrier_show(struct device *dev,
 {
 	struct net_device *netdev = to_net_dev(dev);
 
-	if (netif_running(netdev))
+	if (netif_running(netdev)) {
+		/* Synchronize carrier state with link watch,
+		 * see also rtnl_getlink().
+		 */
+		linkwatch_sync_dev(netdev);
+
 		return sysfs_emit(buf, fmt_dec, !!netif_carrier_ok(netdev));
+	}
 
 	return -EINVAL;
 }
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 592164c2a540..5e0ab4c08f72 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3853,6 +3853,14 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (nskb == NULL)
 		goto out;
 
+	/* Synchronize the carrier state so we don't report a state
+	 * that we're not actually going to honour immediately; if
+	 * the driver just did a carrier off->on transition, we can
+	 * only TX if link watch work has run, but without this we'd
+	 * already report carrier on, even if it doesn't work yet.
+	 */
+	linkwatch_sync_dev(dev);
+
 	err = rtnl_fill_ifinfo(nskb, dev, net,
 			       RTM_NEWLINK, NETLINK_CB(skb).portid,
 			       nlh->nlmsg_seq, 0, 0, ext_filter_mask,
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 0b0ce4f81c01..a977f8903467 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -58,6 +58,9 @@ static struct devlink *netdev_to_devlink_get(struct net_device *dev)
 
 u32 ethtool_op_get_link(struct net_device *dev)
 {
+	/* Synchronize carrier state with link watch, see also rtnl_getlink() */
+	linkwatch_sync_dev(dev);
+
 	return netif_carrier_ok(dev) ? 1 : 0;
 }
 EXPORT_SYMBOL(ethtool_op_get_link);
-- 
cgit v1.2.3


From 2f57dd94bdef083855366138646b26b05f410d99 Mon Sep 17 00:00:00 2001
From: Yan Zhai <yan@cloudflare.com>
Date: Mon, 4 Dec 2023 11:33:28 -0800
Subject: packet: add a generic drop reason for receive

Commit da37845fdce2 ("packet: uses kfree_skb() for errors.") switches
from consume_skb to kfree_skb to improve error handling. However, this
could bring a lot of noises when we monitor real packet drops in
kfree_skb[1], because in tpacket_rcv or packet_rcv only packet clones
can be freed, not actual packets.

Adding a generic drop reason to allow distinguish these "clone drops".

[1]: https://lore.kernel.org/netdev/CABWYdi00L+O30Q=Zah28QwZ_5RU-xcxLFUK2Zj08A8MrLk9jzg@mail.gmail.com/
Fixes: da37845fdce2 ("packet: uses kfree_skb() for errors.")
Suggested-by: Eric Dumazet <edumazet@google.com>
Suggested-by: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
Signed-off-by: Yan Zhai <yan@cloudflare.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/ZW4piNbx3IenYnuw@debian.debian
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/dropreason-core.h |  6 ++++++
 net/packet/af_packet.c        | 20 +++++++-------------
 2 files changed, 13 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/net/dropreason-core.h b/include/net/dropreason-core.h
index 3c70ad53a49c..278e4c7d465c 100644
--- a/include/net/dropreason-core.h
+++ b/include/net/dropreason-core.h
@@ -86,6 +86,7 @@
 	FN(IPV6_NDISC_NS_OTHERHOST)	\
 	FN(QUEUE_PURGE)			\
 	FN(TC_ERROR)			\
+	FN(PACKET_SOCK_ERROR)		\
 	FNe(MAX)
 
 /**
@@ -378,6 +379,11 @@ enum skb_drop_reason {
 	SKB_DROP_REASON_QUEUE_PURGE,
 	/** @SKB_DROP_REASON_TC_ERROR: generic internal tc error. */
 	SKB_DROP_REASON_TC_ERROR,
+	/**
+	 * @SKB_DROP_REASON_PACKET_SOCK_ERROR: generic packet socket errors
+	 * after its filter matches an incoming packet.
+	 */
+	SKB_DROP_REASON_PACKET_SOCK_ERROR,
 	/**
 	 * @SKB_DROP_REASON_MAX: the maximum of core drop reasons, which
 	 * shouldn't be used as a real 'reason' - only for tracing code gen
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index a84e00b5904b..f92edba4c40f 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2121,13 +2121,13 @@ static int packet_rcv_vnet(struct msghdr *msg, const struct sk_buff *skb,
 static int packet_rcv(struct sk_buff *skb, struct net_device *dev,
 		      struct packet_type *pt, struct net_device *orig_dev)
 {
+	enum skb_drop_reason drop_reason = SKB_CONSUMED;
 	struct sock *sk;
 	struct sockaddr_ll *sll;
 	struct packet_sock *po;
 	u8 *skb_head = skb->data;
 	int skb_len = skb->len;
 	unsigned int snaplen, res;
-	bool is_drop_n_account = false;
 
 	if (skb->pkt_type == PACKET_LOOPBACK)
 		goto drop;
@@ -2217,9 +2217,9 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev,
 	return 0;
 
 drop_n_acct:
-	is_drop_n_account = true;
 	atomic_inc(&po->tp_drops);
 	atomic_inc(&sk->sk_drops);
+	drop_reason = SKB_DROP_REASON_PACKET_SOCK_ERROR;
 
 drop_n_restore:
 	if (skb_head != skb->data && skb_shared(skb)) {
@@ -2227,16 +2227,14 @@ drop_n_restore:
 		skb->len = skb_len;
 	}
 drop:
-	if (!is_drop_n_account)
-		consume_skb(skb);
-	else
-		kfree_skb(skb);
+	kfree_skb_reason(skb, drop_reason);
 	return 0;
 }
 
 static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 		       struct packet_type *pt, struct net_device *orig_dev)
 {
+	enum skb_drop_reason drop_reason = SKB_CONSUMED;
 	struct sock *sk;
 	struct packet_sock *po;
 	struct sockaddr_ll *sll;
@@ -2250,7 +2248,6 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	struct sk_buff *copy_skb = NULL;
 	struct timespec64 ts;
 	__u32 ts_status;
-	bool is_drop_n_account = false;
 	unsigned int slot_id = 0;
 	int vnet_hdr_sz = 0;
 
@@ -2498,19 +2495,16 @@ drop_n_restore:
 		skb->len = skb_len;
 	}
 drop:
-	if (!is_drop_n_account)
-		consume_skb(skb);
-	else
-		kfree_skb(skb);
+	kfree_skb_reason(skb, drop_reason);
 	return 0;
 
 drop_n_account:
 	spin_unlock(&sk->sk_receive_queue.lock);
 	atomic_inc(&po->tp_drops);
-	is_drop_n_account = true;
+	drop_reason = SKB_DROP_REASON_PACKET_SOCK_ERROR;
 
 	sk->sk_data_ready(sk);
-	kfree_skb(copy_skb);
+	kfree_skb_reason(copy_skb, drop_reason);
 	goto drop_n_restore;
 }
 
-- 
cgit v1.2.3


From 7037d95a047cd89b1f680eed253c6ab586bef1ed Mon Sep 17 00:00:00 2001
From: Kelly Kane <kelly@hawknetworks.com>
Date: Sat, 2 Dec 2023 17:17:12 -0800
Subject: r8152: add vendor/device ID pair for ASUS USB-C2500

The ASUS USB-C2500 is an RTL8156 based 2.5G Ethernet controller.

Add the vendor and product ID values to the driver. This makes Ethernet
work with the adapter.

Signed-off-by: Kelly Kane <kelly@hawknetworks.com>
Link: https://lore.kernel.org/r/20231203011712.6314-1-kelly@hawknetworks.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/usb/r8152.c   | 1 +
 include/linux/usb/r8152.h | 1 +
 2 files changed, 2 insertions(+)

(limited to 'include')

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index fcdc9ba0f826..9bf2140fd0a1 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -10049,6 +10049,7 @@ static const struct usb_device_id rtl8152_table[] = {
 	{ USB_DEVICE(VENDOR_ID_NVIDIA,  0x09ff) },
 	{ USB_DEVICE(VENDOR_ID_TPLINK,  0x0601) },
 	{ USB_DEVICE(VENDOR_ID_DLINK,   0xb301) },
+	{ USB_DEVICE(VENDOR_ID_ASUS,    0x1976) },
 	{}
 };
 
diff --git a/include/linux/usb/r8152.h b/include/linux/usb/r8152.h
index 287e9d83fb8b..33a4c146dc19 100644
--- a/include/linux/usb/r8152.h
+++ b/include/linux/usb/r8152.h
@@ -30,6 +30,7 @@
 #define VENDOR_ID_NVIDIA		0x0955
 #define VENDOR_ID_TPLINK		0x2357
 #define VENDOR_ID_DLINK			0x2001
+#define VENDOR_ID_ASUS			0x0b05
 
 #if IS_REACHABLE(CONFIG_USB_RTL8152)
 extern u8 rtl8152_get_version(struct usb_interface *intf);
-- 
cgit v1.2.3


From e0f04e41e8eedd4e5a1275f2318df7e1841855f2 Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Mon, 4 Dec 2023 09:32:33 +0100
Subject: drm/atomic-helpers: Invoke end_fb_access while owning plane state

Invoke drm_plane_helper_funcs.end_fb_access before
drm_atomic_helper_commit_hw_done(). The latter function hands over
ownership of the plane state to the following commit, which might
free it. Releasing resources in end_fb_access then operates on undefined
state. This bug has been observed with non-blocking commits when they
are being queued up quickly.

Here is an example stack trace from the bug report. The plane state has
been free'd already, so the pages for drm_gem_fb_vunmap() are gone.

Unable to handle kernel paging request at virtual address 0000000100000049
[...]
 drm_gem_fb_vunmap+0x18/0x74
 drm_gem_end_shadow_fb_access+0x1c/0x2c
 drm_atomic_helper_cleanup_planes+0x58/0xd8
 drm_atomic_helper_commit_tail+0x90/0xa0
 commit_tail+0x15c/0x188
 commit_work+0x14/0x20

Fix this by running end_fb_access immediately after updating all planes
in drm_atomic_helper_commit_planes(). The existing clean-up helper
drm_atomic_helper_cleanup_planes() now only handles cleanup_fb.

For aborted commits, roll back from drm_atomic_helper_prepare_planes()
in the new helper drm_atomic_helper_unprepare_planes(). This case is
different from regular cleanup, as we have to release the new state;
regular cleanup releases the old state. The new helper also invokes
cleanup_fb for all planes.

The changes mostly involve DRM's atomic helpers. Only two drivers, i915
and nouveau, implement their own commit function. Update them to invoke
drm_atomic_helper_unprepare_planes(). Drivers with custom commit_tail
function do not require changes.

v4:
	* fix documentation (kernel test robot)
v3:
	* add drm_atomic_helper_unprepare_planes() for rolling back
	* use correct state for end_fb_access
v2:
	* fix test in drm_atomic_helper_cleanup_planes()

Reported-by: Alyssa Ross <hi@alyssa.is>
Closes: https://lore.kernel.org/dri-devel/87leazm0ya.fsf@alyssa.is/
Suggested-by: Daniel Vetter <daniel@ffwll.ch>
Fixes: 94d879eaf7fb ("drm/atomic-helper: Add {begin,end}_fb_access to plane helpers")
Tested-by: Alyssa Ross <hi@alyssa.is>
Reviewed-by: Alyssa Ross <hi@alyssa.is>
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Cc: <stable@vger.kernel.org> # v6.2+
Link: https://patchwork.freedesktop.org/patch/msgid/20231204083247.22006-1-tzimmermann@suse.de
---
 drivers/gpu/drm/drm_atomic_helper.c          | 78 ++++++++++++++++++----------
 drivers/gpu/drm/i915/display/intel_display.c |  2 +-
 drivers/gpu/drm/nouveau/dispnv50/disp.c      |  2 +-
 include/drm/drm_atomic_helper.h              |  2 +
 4 files changed, 56 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 2444fc33dd7c..68ffcc0b00dc 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -2012,7 +2012,7 @@ int drm_atomic_helper_commit(struct drm_device *dev,
 			return ret;
 
 		drm_atomic_helper_async_commit(dev, state);
-		drm_atomic_helper_cleanup_planes(dev, state);
+		drm_atomic_helper_unprepare_planes(dev, state);
 
 		return 0;
 	}
@@ -2072,7 +2072,7 @@ int drm_atomic_helper_commit(struct drm_device *dev,
 	return 0;
 
 err:
-	drm_atomic_helper_cleanup_planes(dev, state);
+	drm_atomic_helper_unprepare_planes(dev, state);
 	return ret;
 }
 EXPORT_SYMBOL(drm_atomic_helper_commit);
@@ -2650,6 +2650,39 @@ fail_prepare_fb:
 }
 EXPORT_SYMBOL(drm_atomic_helper_prepare_planes);
 
+/**
+ * drm_atomic_helper_unprepare_planes - release plane resources on aborts
+ * @dev: DRM device
+ * @state: atomic state object with old state structures
+ *
+ * This function cleans up plane state, specifically framebuffers, from the
+ * atomic state. It undoes the effects of drm_atomic_helper_prepare_planes()
+ * when aborting an atomic commit. For cleaning up after a successful commit
+ * use drm_atomic_helper_cleanup_planes().
+ */
+void drm_atomic_helper_unprepare_planes(struct drm_device *dev,
+					struct drm_atomic_state *state)
+{
+	struct drm_plane *plane;
+	struct drm_plane_state *new_plane_state;
+	int i;
+
+	for_each_new_plane_in_state(state, plane, new_plane_state, i) {
+		const struct drm_plane_helper_funcs *funcs = plane->helper_private;
+
+		if (funcs->end_fb_access)
+			funcs->end_fb_access(plane, new_plane_state);
+	}
+
+	for_each_new_plane_in_state(state, plane, new_plane_state, i) {
+		const struct drm_plane_helper_funcs *funcs = plane->helper_private;
+
+		if (funcs->cleanup_fb)
+			funcs->cleanup_fb(plane, new_plane_state);
+	}
+}
+EXPORT_SYMBOL(drm_atomic_helper_unprepare_planes);
+
 static bool plane_crtc_active(const struct drm_plane_state *state)
 {
 	return state->crtc && state->crtc->state->active;
@@ -2784,6 +2817,17 @@ void drm_atomic_helper_commit_planes(struct drm_device *dev,
 
 		funcs->atomic_flush(crtc, old_state);
 	}
+
+	/*
+	 * Signal end of framebuffer access here before hw_done. After hw_done,
+	 * a later commit might have already released the plane state.
+	 */
+	for_each_old_plane_in_state(old_state, plane, old_plane_state, i) {
+		const struct drm_plane_helper_funcs *funcs = plane->helper_private;
+
+		if (funcs->end_fb_access)
+			funcs->end_fb_access(plane, old_plane_state);
+	}
 }
 EXPORT_SYMBOL(drm_atomic_helper_commit_planes);
 
@@ -2911,40 +2955,22 @@ EXPORT_SYMBOL(drm_atomic_helper_disable_planes_on_crtc);
  * configuration. Hence the old configuration must be perserved in @old_state to
  * be able to call this function.
  *
- * This function must also be called on the new state when the atomic update
- * fails at any point after calling drm_atomic_helper_prepare_planes().
+ * This function may not be called on the new state when the atomic update
+ * fails at any point after calling drm_atomic_helper_prepare_planes(). Use
+ * drm_atomic_helper_unprepare_planes() in this case.
  */
 void drm_atomic_helper_cleanup_planes(struct drm_device *dev,
 				      struct drm_atomic_state *old_state)
 {
 	struct drm_plane *plane;
-	struct drm_plane_state *old_plane_state, *new_plane_state;
+	struct drm_plane_state *old_plane_state;
 	int i;
 
-	for_each_oldnew_plane_in_state(old_state, plane, old_plane_state, new_plane_state, i) {
+	for_each_old_plane_in_state(old_state, plane, old_plane_state, i) {
 		const struct drm_plane_helper_funcs *funcs = plane->helper_private;
 
-		if (funcs->end_fb_access)
-			funcs->end_fb_access(plane, new_plane_state);
-	}
-
-	for_each_oldnew_plane_in_state(old_state, plane, old_plane_state, new_plane_state, i) {
-		const struct drm_plane_helper_funcs *funcs;
-		struct drm_plane_state *plane_state;
-
-		/*
-		 * This might be called before swapping when commit is aborted,
-		 * in which case we have to cleanup the new state.
-		 */
-		if (old_plane_state == plane->state)
-			plane_state = new_plane_state;
-		else
-			plane_state = old_plane_state;
-
-		funcs = plane->helper_private;
-
 		if (funcs->cleanup_fb)
-			funcs->cleanup_fb(plane, plane_state);
+			funcs->cleanup_fb(plane, old_plane_state);
 	}
 }
 EXPORT_SYMBOL(drm_atomic_helper_cleanup_planes);
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 28d85e1e858e..02f873738905 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -7475,7 +7475,7 @@ int intel_atomic_commit(struct drm_device *dev, struct drm_atomic_state *_state,
 		for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i)
 			intel_color_cleanup_commit(new_crtc_state);
 
-		drm_atomic_helper_cleanup_planes(dev, &state->base);
+		drm_atomic_helper_unprepare_planes(dev, &state->base);
 		intel_runtime_pm_put(&dev_priv->runtime_pm, state->wakeref);
 		return ret;
 	}
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index 7840b6428afb..118807e38422 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -2474,7 +2474,7 @@ nv50_disp_atomic_commit(struct drm_device *dev,
 
 err_cleanup:
 	if (ret)
-		drm_atomic_helper_cleanup_planes(dev, state);
+		drm_atomic_helper_unprepare_planes(dev, state);
 done:
 	pm_runtime_put_autosuspend(dev->dev);
 	return ret;
diff --git a/include/drm/drm_atomic_helper.h b/include/drm/drm_atomic_helper.h
index 536a0b0091c3..006b5c977ad7 100644
--- a/include/drm/drm_atomic_helper.h
+++ b/include/drm/drm_atomic_helper.h
@@ -97,6 +97,8 @@ void drm_atomic_helper_commit_modeset_enables(struct drm_device *dev,
 
 int drm_atomic_helper_prepare_planes(struct drm_device *dev,
 				     struct drm_atomic_state *state);
+void drm_atomic_helper_unprepare_planes(struct drm_device *dev,
+					struct drm_atomic_state *state);
 
 #define DRM_PLANE_COMMIT_ACTIVE_ONLY			BIT(0)
 #define DRM_PLANE_COMMIT_NO_DISABLE_AFTER_MODESET	BIT(1)
-- 
cgit v1.2.3


From a3a44d2d3a5c5ff6e73c711db5b1911b5a676bb0 Mon Sep 17 00:00:00 2001
From: Even Xu <even.xu@intel.com>
Date: Tue, 5 Dec 2023 09:50:30 +0800
Subject: HID: Intel-ish-hid: Ishtp: Add helper functions for client connection

For every ishtp client driver during initialization state, the flow is:
1 - Allocate an ISHTP client instance
2 - Reserve a host id and link the client instance
3 - Search a firmware client using UUID and get related
    client information
4 - Bind firmware client id to the ISHTP client instance
5 - Set the state the ISHTP client instance to CONNECTING
6 - Send connect request to firmware
7 - Register event callback for messages from the firmware

During deinitizalization state, the flow is:
9 - Set the state the ISHTP client instance to ISHTP_CL_DISCONNECTING
10 - Issue disconnect request to firmware
11 - Unlike the client instance
12 - Flush message queue
13 - Free ISHTP client instance

Step 2-7 are identical to the steps of client driver initialization
and driver reset flow, but reallocation of the RX/TX ring buffers
can be avoided in reset flow.

Also for step 9-12, they are identical to the steps of client driver
failure handling after connect request, driver reset flow and
driver removing.

So, add two helper functions to simplify client driver code.
ishtp_cl_establish_connection()
ishtp_cl_destroy_connection()

No functional changes are expected.

Signed-off-by: Even Xu <even.xu@intel.com>
Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/intel-ish-hid/ishtp/client.c | 185 +++++++++++++++++++++++++++++--
 include/linux/intel-ish-client-if.h      |   3 +
 2 files changed, 177 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/hid/intel-ish-hid/ishtp/client.c b/drivers/hid/intel-ish-hid/ishtp/client.c
index 2d92fc129ce4..82c907f01bd3 100644
--- a/drivers/hid/intel-ish-hid/ishtp/client.c
+++ b/drivers/hid/intel-ish-hid/ishtp/client.c
@@ -339,16 +339,17 @@ static bool ishtp_cl_is_other_connecting(struct ishtp_cl *cl)
 }
 
 /**
- * ishtp_cl_connect() - Send connect request to firmware
+ * ishtp_cl_connect_to_fw() - Send connect request to firmware
  * @cl: client device instance
  *
- * Send a connect request for a client to firmware. If successful it will
- * RX and TX ring buffers
+ * Send a connect request to the firmware and wait for firmware response.
+ * If there is successful connection response from the firmware, change
+ * client state to ISHTP_CL_CONNECTED, and bind client to related
+ * firmware client_id.
  *
- * Return: 0 if successful connect response from the firmware and able
- * to bind and allocate ring buffers or error code on failure
+ * Return: 0 for success and error code on failure
  */
-int ishtp_cl_connect(struct ishtp_cl *cl)
+static int ishtp_cl_connect_to_fw(struct ishtp_cl *cl)
 {
 	struct ishtp_device *dev;
 	int rets;
@@ -358,8 +359,6 @@ int ishtp_cl_connect(struct ishtp_cl *cl)
 
 	dev = cl->dev;
 
-	dev->print_log(dev, "%s() current_state = %d\n", __func__, cl->state);
-
 	if (ishtp_cl_is_other_connecting(cl)) {
 		dev->print_log(dev, "%s() Busy\n", __func__);
 		return	-EBUSY;
@@ -405,6 +404,38 @@ int ishtp_cl_connect(struct ishtp_cl *cl)
 		return rets;
 	}
 
+	return rets;
+}
+
+/**
+ * ishtp_cl_connect() - Build connection with firmware
+ * @cl: client device instance
+ *
+ * Call ishtp_cl_connect_to_fw() to connect and bind to firmware. If successful,
+ * allocate RX and TX ring buffers, and start flow control with firmware to
+ * start communication.
+ *
+ * Return: 0 if there is successful connection to the firmware, allocate
+ * ring buffers.
+ */
+int ishtp_cl_connect(struct ishtp_cl *cl)
+{
+	struct ishtp_device *dev;
+	int rets;
+
+	if (!cl || !cl->dev)
+		return -ENODEV;
+
+	dev = cl->dev;
+
+	dev->print_log(dev, "%s() current_state = %d\n", __func__, cl->state);
+
+	rets = ishtp_cl_connect_to_fw(cl);
+	if (rets) {
+		dev->print_log(dev, "%s() Connect to fw failed\n", __func__);
+		return rets;
+	}
+
 	rets = ishtp_cl_alloc_rx_ring(cl);
 	if (rets) {
 		dev->print_log(dev, "%s() Alloc RX ring failed\n", __func__);
@@ -422,15 +453,147 @@ int ishtp_cl_connect(struct ishtp_cl *cl)
 		return rets;
 	}
 
-	/* Upon successful connection and allocation, emit flow-control */
+	/*
+	 * Upon successful connection and allocation, start flow-control.
+	 */
 	rets = ishtp_cl_read_start(cl);
 
-	dev->print_log(dev, "%s() successful\n", __func__);
-
 	return rets;
 }
 EXPORT_SYMBOL(ishtp_cl_connect);
 
+/**
+ * ishtp_cl_establish_connection() - Establish connection with the firmware
+ * @cl: client device instance
+ * @uuid: uuid of the client to search
+ * @tx_size: TX ring buffer size
+ * @rx_size: RX ring buffer size
+ * @reset: true if called for reset connection, otherwise for first connection
+ *
+ * This is a helper function for client driver to build connection with firmware.
+ * If it's first time connecting to the firmware, set reset to false, this
+ * function will link client to bus, find client id and send connect request to
+ * the firmware.
+ *
+ * If it's called for reset handler where client lost connection after
+ * firmware reset, set reset to true, this function will reinit client state and
+ * establish connection again. In this case, this function reuses current client
+ * structure and ring buffers to avoid allocation failure and memory fragments.
+ *
+ * Return: 0 for successful connection with the firmware,
+ * or error code on failure
+ */
+int ishtp_cl_establish_connection(struct ishtp_cl *cl, const guid_t *uuid,
+				  int tx_size, int rx_size, bool reset)
+{
+	struct ishtp_device *dev;
+	struct ishtp_fw_client *fw_client;
+	int rets;
+
+	if (!cl || !cl->dev)
+		return -ENODEV;
+
+	dev = cl->dev;
+
+	ishtp_set_connection_state(cl, ISHTP_CL_INITIALIZING);
+
+	/* reinit ishtp_cl structure if call for reset */
+	if (reset) {
+		cl->host_client_id = 0;
+		cl->fw_client_id = 0;
+		cl->ishtp_flow_ctrl_creds = 0;
+		cl->out_flow_ctrl_creds = 0;
+
+		cl->last_tx_path = CL_TX_PATH_IPC;
+		cl->last_dma_acked = 1;
+		cl->last_dma_addr = NULL;
+		cl->last_ipc_acked = 1;
+
+		cl->sending = 0;
+		cl->err_send_msg = 0;
+		cl->err_send_fc = 0;
+
+		cl->send_msg_cnt_ipc = 0;
+		cl->send_msg_cnt_dma = 0;
+		cl->recv_msg_cnt_ipc = 0;
+		cl->recv_msg_cnt_dma = 0;
+		cl->recv_msg_num_frags = 0;
+		cl->ishtp_flow_ctrl_cnt = 0;
+		cl->out_flow_ctrl_cnt = 0;
+	}
+
+	/* link to bus */
+	rets = ishtp_cl_link(cl);
+	if (rets) {
+		dev->print_log(dev, "%s() ishtp_cl_link failed\n", __func__);
+		return rets;
+	}
+
+	/* find firmware client */
+	fw_client = ishtp_fw_cl_get_client(dev, uuid);
+	if (!fw_client) {
+		dev->print_log(dev,
+			       "%s() ish client uuid not found\n", __func__);
+		return -ENOENT;
+	}
+
+	ishtp_set_tx_ring_size(cl, tx_size);
+	ishtp_set_rx_ring_size(cl, rx_size);
+
+	ishtp_cl_set_fw_client_id(cl, ishtp_get_fw_client_id(fw_client));
+
+	ishtp_set_connection_state(cl, ISHTP_CL_CONNECTING);
+
+	/*
+	 * For reset case, not allocate tx/rx ring buffer which are already
+	 * done in ishtp_cl_connect() during first connection.
+	 */
+	if (reset) {
+		rets = ishtp_cl_connect_to_fw(cl);
+		if (!rets)
+			rets = ishtp_cl_read_start(cl);
+		else
+			dev->print_log(dev,
+				"%s() connect to fw failed\n", __func__);
+	} else {
+		rets = ishtp_cl_connect(cl);
+	}
+
+	return rets;
+}
+EXPORT_SYMBOL(ishtp_cl_establish_connection);
+
+/**
+ * ishtp_cl_destroy_connection() - Disconnect with the firmware
+ * @cl: client device instance
+ * @reset: true if called for firmware reset, false for normal disconnection
+ *
+ * This is a helper function for client driver to disconnect with firmware,
+ * unlink to bus and flush message queue.
+ */
+void ishtp_cl_destroy_connection(struct ishtp_cl *cl, bool reset)
+{
+	if (!cl)
+		return;
+
+	if (reset) {
+		/*
+		 * For reset case, connection is already lost during fw reset.
+		 * Just set state to DISCONNECTED is enough.
+		 */
+		ishtp_set_connection_state(cl, ISHTP_CL_DISCONNECTED);
+	} else {
+		if (cl->state != ISHTP_CL_DISCONNECTED) {
+			ishtp_set_connection_state(cl, ISHTP_CL_DISCONNECTING);
+			ishtp_cl_disconnect(cl);
+		}
+	}
+
+	ishtp_cl_unlink(cl);
+	ishtp_cl_flush_queues(cl);
+}
+EXPORT_SYMBOL(ishtp_cl_destroy_connection);
+
 /**
  * ishtp_cl_read_start() - Prepare to read client message
  * @cl: client device instance
diff --git a/include/linux/intel-ish-client-if.h b/include/linux/intel-ish-client-if.h
index f45f13304add..771622650247 100644
--- a/include/linux/intel-ish-client-if.h
+++ b/include/linux/intel-ish-client-if.h
@@ -94,6 +94,9 @@ int ishtp_cl_link(struct ishtp_cl *cl);
 void ishtp_cl_unlink(struct ishtp_cl *cl);
 int ishtp_cl_disconnect(struct ishtp_cl *cl);
 int ishtp_cl_connect(struct ishtp_cl *cl);
+int ishtp_cl_establish_connection(struct ishtp_cl *cl, const guid_t *uuid,
+				  int tx_size, int rx_size, bool reset);
+void ishtp_cl_destroy_connection(struct ishtp_cl *cl, bool reset);
 int ishtp_cl_send(struct ishtp_cl *cl, uint8_t *buf, size_t length);
 int ishtp_cl_flush_queues(struct ishtp_cl *cl);
 int ishtp_cl_io_rb_recycle(struct ishtp_cl_rb *rb);
-- 
cgit v1.2.3


From 88f29324042752a28245ec0ab285d71c7f4d9c6a Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 30 Nov 2023 22:50:58 +0100
Subject: wifi: cfg80211: make RX assoc data const

This is just a collection of data and we only read it,
so make it const.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 2 +-
 net/wireless/mlme.c    | 2 +-
 net/wireless/nl80211.c | 2 +-
 net/wireless/nl80211.h | 2 +-
 net/wireless/trace.h   | 2 +-
 5 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index d36ad4cedf3b..d59669d86718 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -7312,7 +7312,7 @@ struct cfg80211_rx_assoc_resp_data {
  * This function may sleep. The caller must hold the corresponding wdev's mutex.
  */
 void cfg80211_rx_assoc_resp(struct net_device *dev,
-			    struct cfg80211_rx_assoc_resp_data *data);
+			    const struct cfg80211_rx_assoc_resp_data *data);
 
 /**
  * struct cfg80211_assoc_failure - association failure data
diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c
index bad9e4fd842f..f635a8b6ca2e 100644
--- a/net/wireless/mlme.c
+++ b/net/wireless/mlme.c
@@ -22,7 +22,7 @@
 
 
 void cfg80211_rx_assoc_resp(struct net_device *dev,
-			    struct cfg80211_rx_assoc_resp_data *data)
+			    const struct cfg80211_rx_assoc_resp_data *data)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct wiphy *wiphy = wdev->wiphy;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 46a79ed1c97c..403a4a38966a 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -17815,7 +17815,7 @@ void nl80211_send_rx_auth(struct cfg80211_registered_device *rdev,
 
 void nl80211_send_rx_assoc(struct cfg80211_registered_device *rdev,
 			   struct net_device *netdev,
-			   struct cfg80211_rx_assoc_resp_data *data)
+			   const struct cfg80211_rx_assoc_resp_data *data)
 {
 	struct nl80211_mlme_event event = {
 		.cmd = NL80211_CMD_ASSOCIATE,
diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h
index aad40240d9cb..6376f3a87f8a 100644
--- a/net/wireless/nl80211.h
+++ b/net/wireless/nl80211.h
@@ -60,7 +60,7 @@ void nl80211_send_rx_auth(struct cfg80211_registered_device *rdev,
 			  const u8 *buf, size_t len, gfp_t gfp);
 void nl80211_send_rx_assoc(struct cfg80211_registered_device *rdev,
 			   struct net_device *netdev,
-			   struct cfg80211_rx_assoc_resp_data *data);
+			   const struct cfg80211_rx_assoc_resp_data *data);
 void nl80211_send_deauth(struct cfg80211_registered_device *rdev,
 			 struct net_device *netdev,
 			 const u8 *buf, size_t len,
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index 30cd1bd58aac..4de710efa47e 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -2928,7 +2928,7 @@ DEFINE_EVENT(netdev_evt_only, cfg80211_send_rx_auth,
 
 TRACE_EVENT(cfg80211_send_rx_assoc,
 	TP_PROTO(struct net_device *netdev,
-		 struct cfg80211_rx_assoc_resp_data *data),
+		 const struct cfg80211_rx_assoc_resp_data *data),
 	TP_ARGS(netdev, data),
 	TP_STRUCT__entry(
 		NETDEV_ENTRY
-- 
cgit v1.2.3


From 16a1d968358aa9e897ce995fa45cb15d55a0e83d Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Mon, 2 Oct 2023 20:43:43 +0200
Subject: mm/slab: remove mm/slab.c and slab_def.h

Remove the SLAB implementation. Update CREDITS.
Also update and properly sort the SLOB entry there.

RIP SLAB allocator (1996 - 2024)

Reviewed-by: Kees Cook <keescook@chromium.org>
Acked-by: Christoph Lameter <cl@linux.com>
Acked-by: David Rientjes <rientjes@google.com>
Tested-by: David Rientjes <rientjes@google.com>
Acked-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
 CREDITS                  |   12 +-
 include/linux/slab_def.h |  124 --
 mm/slab.c                | 4005 ----------------------------------------------
 3 files changed, 8 insertions(+), 4133 deletions(-)
 delete mode 100644 include/linux/slab_def.h
 delete mode 100644 mm/slab.c

(limited to 'include')

diff --git a/CREDITS b/CREDITS
index f33a33fd2371..e9a094a93287 100644
--- a/CREDITS
+++ b/CREDITS
@@ -9,10 +9,6 @@
 			Linus
 ----------
 
-N: Matt Mackal
-E: mpm@selenic.com
-D: SLOB slab allocator
-
 N: Matti Aarnio
 E: mea@nic.funet.fi
 D: Alpha systems hacking, IPv6 and other network related stuff
@@ -1572,6 +1568,10 @@ S: Ampferstr. 50 / 4
 S: 6020 Innsbruck
 S: Austria
 
+N: Mark Hemment
+E: markhe@nextd.demon.co.uk
+D: SLAB allocator implementation
+
 N: Richard Henderson
 E: rth@twiddle.net
 E: rth@cygnus.com
@@ -2437,6 +2437,10 @@ D: work on suspend-to-ram/disk, killing duplicates from ioctl32,
 D: Altera SoCFPGA and Nokia N900 support.
 S: Czech Republic
 
+N: Olivia Mackall
+E: olivia@selenic.com
+D: SLOB slab allocator
+
 N: Paul Mackerras
 E: paulus@samba.org
 D: PPP driver
diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h
deleted file mode 100644
index a61e7d55d0d3..000000000000
--- a/include/linux/slab_def.h
+++ /dev/null
@@ -1,124 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_SLAB_DEF_H
-#define	_LINUX_SLAB_DEF_H
-
-#include <linux/kfence.h>
-#include <linux/reciprocal_div.h>
-
-/*
- * Definitions unique to the original Linux SLAB allocator.
- */
-
-struct kmem_cache {
-	struct array_cache __percpu *cpu_cache;
-
-/* 1) Cache tunables. Protected by slab_mutex */
-	unsigned int batchcount;
-	unsigned int limit;
-	unsigned int shared;
-
-	unsigned int size;
-	struct reciprocal_value reciprocal_buffer_size;
-/* 2) touched by every alloc & free from the backend */
-
-	slab_flags_t flags;		/* constant flags */
-	unsigned int num;		/* # of objs per slab */
-
-/* 3) cache_grow/shrink */
-	/* order of pgs per slab (2^n) */
-	unsigned int gfporder;
-
-	/* force GFP flags, e.g. GFP_DMA */
-	gfp_t allocflags;
-
-	size_t colour;			/* cache colouring range */
-	unsigned int colour_off;	/* colour offset */
-	unsigned int freelist_size;
-
-	/* constructor func */
-	void (*ctor)(void *obj);
-
-/* 4) cache creation/removal */
-	const char *name;
-	struct list_head list;
-	int refcount;
-	int object_size;
-	int align;
-
-/* 5) statistics */
-#ifdef CONFIG_DEBUG_SLAB
-	unsigned long num_active;
-	unsigned long num_allocations;
-	unsigned long high_mark;
-	unsigned long grown;
-	unsigned long reaped;
-	unsigned long errors;
-	unsigned long max_freeable;
-	unsigned long node_allocs;
-	unsigned long node_frees;
-	unsigned long node_overflow;
-	atomic_t allochit;
-	atomic_t allocmiss;
-	atomic_t freehit;
-	atomic_t freemiss;
-
-	/*
-	 * If debugging is enabled, then the allocator can add additional
-	 * fields and/or padding to every object. 'size' contains the total
-	 * object size including these internal fields, while 'obj_offset'
-	 * and 'object_size' contain the offset to the user object and its
-	 * size.
-	 */
-	int obj_offset;
-#endif /* CONFIG_DEBUG_SLAB */
-
-#ifdef CONFIG_KASAN_GENERIC
-	struct kasan_cache kasan_info;
-#endif
-
-#ifdef CONFIG_SLAB_FREELIST_RANDOM
-	unsigned int *random_seq;
-#endif
-
-#ifdef CONFIG_HARDENED_USERCOPY
-	unsigned int useroffset;	/* Usercopy region offset */
-	unsigned int usersize;		/* Usercopy region size */
-#endif
-
-	struct kmem_cache_node *node[MAX_NUMNODES];
-};
-
-static inline void *nearest_obj(struct kmem_cache *cache, const struct slab *slab,
-				void *x)
-{
-	void *object = x - (x - slab->s_mem) % cache->size;
-	void *last_object = slab->s_mem + (cache->num - 1) * cache->size;
-
-	if (unlikely(object > last_object))
-		return last_object;
-	else
-		return object;
-}
-
-/*
- * We want to avoid an expensive divide : (offset / cache->size)
- *   Using the fact that size is a constant for a particular cache,
- *   we can replace (offset / cache->size) by
- *   reciprocal_divide(offset, cache->reciprocal_buffer_size)
- */
-static inline unsigned int obj_to_index(const struct kmem_cache *cache,
-					const struct slab *slab, void *obj)
-{
-	u32 offset = (obj - slab->s_mem);
-	return reciprocal_divide(offset, cache->reciprocal_buffer_size);
-}
-
-static inline int objs_per_slab(const struct kmem_cache *cache,
-				     const struct slab *slab)
-{
-	if (is_kfence_address(slab_address(slab)))
-		return 1;
-	return cache->num;
-}
-
-#endif	/* _LINUX_SLAB_DEF_H */
diff --git a/mm/slab.c b/mm/slab.c
deleted file mode 100644
index 37efe3241f9c..000000000000
--- a/mm/slab.c
+++ /dev/null
@@ -1,4005 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * linux/mm/slab.c
- * Written by Mark Hemment, 1996/97.
- * (markhe@nextd.demon.co.uk)
- *
- * kmem_cache_destroy() + some cleanup - 1999 Andrea Arcangeli
- *
- * Major cleanup, different bufctl logic, per-cpu arrays
- *	(c) 2000 Manfred Spraul
- *
- * Cleanup, make the head arrays unconditional, preparation for NUMA
- * 	(c) 2002 Manfred Spraul
- *
- * An implementation of the Slab Allocator as described in outline in;
- *	UNIX Internals: The New Frontiers by Uresh Vahalia
- *	Pub: Prentice Hall	ISBN 0-13-101908-2
- * or with a little more detail in;
- *	The Slab Allocator: An Object-Caching Kernel Memory Allocator
- *	Jeff Bonwick (Sun Microsystems).
- *	Presented at: USENIX Summer 1994 Technical Conference
- *
- * The memory is organized in caches, one cache for each object type.
- * (e.g. inode_cache, dentry_cache, buffer_head, vm_area_struct)
- * Each cache consists out of many slabs (they are small (usually one
- * page long) and always contiguous), and each slab contains multiple
- * initialized objects.
- *
- * This means, that your constructor is used only for newly allocated
- * slabs and you must pass objects with the same initializations to
- * kmem_cache_free.
- *
- * Each cache can only support one memory type (GFP_DMA, GFP_HIGHMEM,
- * normal). If you need a special memory type, then must create a new
- * cache for that memory type.
- *
- * In order to reduce fragmentation, the slabs are sorted in 3 groups:
- *   full slabs with 0 free objects
- *   partial slabs
- *   empty slabs with no allocated objects
- *
- * If partial slabs exist, then new allocations come from these slabs,
- * otherwise from empty slabs or new slabs are allocated.
- *
- * kmem_cache_destroy() CAN CRASH if you try to allocate from the cache
- * during kmem_cache_destroy(). The caller must prevent concurrent allocs.
- *
- * Each cache has a short per-cpu head array, most allocs
- * and frees go into that array, and if that array overflows, then 1/2
- * of the entries in the array are given back into the global cache.
- * The head array is strictly LIFO and should improve the cache hit rates.
- * On SMP, it additionally reduces the spinlock operations.
- *
- * The c_cpuarray may not be read with enabled local interrupts -
- * it's changed with a smp_call_function().
- *
- * SMP synchronization:
- *  constructors and destructors are called without any locking.
- *  Several members in struct kmem_cache and struct slab never change, they
- *	are accessed without any locking.
- *  The per-cpu arrays are never accessed from the wrong cpu, no locking,
- *  	and local interrupts are disabled so slab code is preempt-safe.
- *  The non-constant members are protected with a per-cache irq spinlock.
- *
- * Many thanks to Mark Hemment, who wrote another per-cpu slab patch
- * in 2000 - many ideas in the current implementation are derived from
- * his patch.
- *
- * Further notes from the original documentation:
- *
- * 11 April '97.  Started multi-threading - markhe
- *	The global cache-chain is protected by the mutex 'slab_mutex'.
- *	The sem is only needed when accessing/extending the cache-chain, which
- *	can never happen inside an interrupt (kmem_cache_create(),
- *	kmem_cache_shrink() and kmem_cache_reap()).
- *
- *	At present, each engine can be growing a cache.  This should be blocked.
- *
- * 15 March 2005. NUMA slab allocator.
- *	Shai Fultheim <shai@scalex86.org>.
- *	Shobhit Dayal <shobhit@calsoftinc.com>
- *	Alok N Kataria <alokk@calsoftinc.com>
- *	Christoph Lameter <christoph@lameter.com>
- *
- *	Modified the slab allocator to be node aware on NUMA systems.
- *	Each node has its own list of partial, free and full slabs.
- *	All object allocations for a node occur from node specific slab lists.
- */
-
-#include	<linux/slab.h>
-#include	<linux/mm.h>
-#include	<linux/poison.h>
-#include	<linux/swap.h>
-#include	<linux/cache.h>
-#include	<linux/interrupt.h>
-#include	<linux/init.h>
-#include	<linux/compiler.h>
-#include	<linux/cpuset.h>
-#include	<linux/proc_fs.h>
-#include	<linux/seq_file.h>
-#include	<linux/notifier.h>
-#include	<linux/kallsyms.h>
-#include	<linux/kfence.h>
-#include	<linux/cpu.h>
-#include	<linux/sysctl.h>
-#include	<linux/module.h>
-#include	<linux/rcupdate.h>
-#include	<linux/string.h>
-#include	<linux/uaccess.h>
-#include	<linux/nodemask.h>
-#include	<linux/kmemleak.h>
-#include	<linux/mempolicy.h>
-#include	<linux/mutex.h>
-#include	<linux/fault-inject.h>
-#include	<linux/rtmutex.h>
-#include	<linux/reciprocal_div.h>
-#include	<linux/debugobjects.h>
-#include	<linux/memory.h>
-#include	<linux/prefetch.h>
-#include	<linux/sched/task_stack.h>
-
-#include	<net/sock.h>
-
-#include	<asm/cacheflush.h>
-#include	<asm/tlbflush.h>
-#include	<asm/page.h>
-
-#include <trace/events/kmem.h>
-
-#include	"internal.h"
-
-#include	"slab.h"
-
-/*
- * DEBUG	- 1 for kmem_cache_create() to honour; SLAB_RED_ZONE & SLAB_POISON.
- *		  0 for faster, smaller code (especially in the critical paths).
- *
- * STATS	- 1 to collect stats for /proc/slabinfo.
- *		  0 for faster, smaller code (especially in the critical paths).
- *
- * FORCED_DEBUG	- 1 enables SLAB_RED_ZONE and SLAB_POISON (if possible)
- */
-
-#ifdef CONFIG_DEBUG_SLAB
-#define	DEBUG		1
-#define	STATS		1
-#define	FORCED_DEBUG	1
-#else
-#define	DEBUG		0
-#define	STATS		0
-#define	FORCED_DEBUG	0
-#endif
-
-/* Shouldn't this be in a header file somewhere? */
-#define	BYTES_PER_WORD		sizeof(void *)
-#define	REDZONE_ALIGN		max(BYTES_PER_WORD, __alignof__(unsigned long long))
-
-#ifndef ARCH_KMALLOC_FLAGS
-#define ARCH_KMALLOC_FLAGS SLAB_HWCACHE_ALIGN
-#endif
-
-#define FREELIST_BYTE_INDEX (((PAGE_SIZE >> BITS_PER_BYTE) \
-				<= SLAB_OBJ_MIN_SIZE) ? 1 : 0)
-
-#if FREELIST_BYTE_INDEX
-typedef unsigned char freelist_idx_t;
-#else
-typedef unsigned short freelist_idx_t;
-#endif
-
-#define SLAB_OBJ_MAX_NUM ((1 << sizeof(freelist_idx_t) * BITS_PER_BYTE) - 1)
-
-/*
- * struct array_cache
- *
- * Purpose:
- * - LIFO ordering, to hand out cache-warm objects from _alloc
- * - reduce the number of linked list operations
- * - reduce spinlock operations
- *
- * The limit is stored in the per-cpu structure to reduce the data cache
- * footprint.
- *
- */
-struct array_cache {
-	unsigned int avail;
-	unsigned int limit;
-	unsigned int batchcount;
-	unsigned int touched;
-	void *entry[];	/*
-			 * Must have this definition in here for the proper
-			 * alignment of array_cache. Also simplifies accessing
-			 * the entries.
-			 */
-};
-
-struct alien_cache {
-	spinlock_t lock;
-	struct array_cache ac;
-};
-
-/*
- * Need this for bootstrapping a per node allocator.
- */
-#define NUM_INIT_LISTS (2 * MAX_NUMNODES)
-static struct kmem_cache_node __initdata init_kmem_cache_node[NUM_INIT_LISTS];
-#define	CACHE_CACHE 0
-#define	SIZE_NODE (MAX_NUMNODES)
-
-static int drain_freelist(struct kmem_cache *cache,
-			struct kmem_cache_node *n, int tofree);
-static void free_block(struct kmem_cache *cachep, void **objpp, int len,
-			int node, struct list_head *list);
-static void slabs_destroy(struct kmem_cache *cachep, struct list_head *list);
-static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp);
-static void cache_reap(struct work_struct *unused);
-
-static inline void fixup_objfreelist_debug(struct kmem_cache *cachep,
-						void **list);
-static inline void fixup_slab_list(struct kmem_cache *cachep,
-				struct kmem_cache_node *n, struct slab *slab,
-				void **list);
-
-#define INDEX_NODE kmalloc_index(sizeof(struct kmem_cache_node))
-
-static void kmem_cache_node_init(struct kmem_cache_node *parent)
-{
-	INIT_LIST_HEAD(&parent->slabs_full);
-	INIT_LIST_HEAD(&parent->slabs_partial);
-	INIT_LIST_HEAD(&parent->slabs_free);
-	parent->total_slabs = 0;
-	parent->free_slabs = 0;
-	parent->shared = NULL;
-	parent->alien = NULL;
-	parent->colour_next = 0;
-	raw_spin_lock_init(&parent->list_lock);
-	parent->free_objects = 0;
-	parent->free_touched = 0;
-}
-
-#define MAKE_LIST(cachep, listp, slab, nodeid)				\
-	do {								\
-		INIT_LIST_HEAD(listp);					\
-		list_splice(&get_node(cachep, nodeid)->slab, listp);	\
-	} while (0)
-
-#define	MAKE_ALL_LISTS(cachep, ptr, nodeid)				\
-	do {								\
-	MAKE_LIST((cachep), (&(ptr)->slabs_full), slabs_full, nodeid);	\
-	MAKE_LIST((cachep), (&(ptr)->slabs_partial), slabs_partial, nodeid); \
-	MAKE_LIST((cachep), (&(ptr)->slabs_free), slabs_free, nodeid);	\
-	} while (0)
-
-#define CFLGS_OBJFREELIST_SLAB	((slab_flags_t __force)0x40000000U)
-#define CFLGS_OFF_SLAB		((slab_flags_t __force)0x80000000U)
-#define	OBJFREELIST_SLAB(x)	((x)->flags & CFLGS_OBJFREELIST_SLAB)
-#define	OFF_SLAB(x)	((x)->flags & CFLGS_OFF_SLAB)
-
-#define BATCHREFILL_LIMIT	16
-/*
- * Optimization question: fewer reaps means less probability for unnecessary
- * cpucache drain/refill cycles.
- *
- * OTOH the cpuarrays can contain lots of objects,
- * which could lock up otherwise freeable slabs.
- */
-#define REAPTIMEOUT_AC		(2*HZ)
-#define REAPTIMEOUT_NODE	(4*HZ)
-
-#if STATS
-#define	STATS_INC_ACTIVE(x)	((x)->num_active++)
-#define	STATS_DEC_ACTIVE(x)	((x)->num_active--)
-#define	STATS_INC_ALLOCED(x)	((x)->num_allocations++)
-#define	STATS_INC_GROWN(x)	((x)->grown++)
-#define	STATS_ADD_REAPED(x, y)	((x)->reaped += (y))
-#define	STATS_SET_HIGH(x)						\
-	do {								\
-		if ((x)->num_active > (x)->high_mark)			\
-			(x)->high_mark = (x)->num_active;		\
-	} while (0)
-#define	STATS_INC_ERR(x)	((x)->errors++)
-#define	STATS_INC_NODEALLOCS(x)	((x)->node_allocs++)
-#define	STATS_INC_NODEFREES(x)	((x)->node_frees++)
-#define STATS_INC_ACOVERFLOW(x)   ((x)->node_overflow++)
-#define	STATS_SET_FREEABLE(x, i)					\
-	do {								\
-		if ((x)->max_freeable < i)				\
-			(x)->max_freeable = i;				\
-	} while (0)
-#define STATS_INC_ALLOCHIT(x)	atomic_inc(&(x)->allochit)
-#define STATS_INC_ALLOCMISS(x)	atomic_inc(&(x)->allocmiss)
-#define STATS_INC_FREEHIT(x)	atomic_inc(&(x)->freehit)
-#define STATS_INC_FREEMISS(x)	atomic_inc(&(x)->freemiss)
-#else
-#define	STATS_INC_ACTIVE(x)	do { } while (0)
-#define	STATS_DEC_ACTIVE(x)	do { } while (0)
-#define	STATS_INC_ALLOCED(x)	do { } while (0)
-#define	STATS_INC_GROWN(x)	do { } while (0)
-#define	STATS_ADD_REAPED(x, y)	do { (void)(y); } while (0)
-#define	STATS_SET_HIGH(x)	do { } while (0)
-#define	STATS_INC_ERR(x)	do { } while (0)
-#define	STATS_INC_NODEALLOCS(x)	do { } while (0)
-#define	STATS_INC_NODEFREES(x)	do { } while (0)
-#define STATS_INC_ACOVERFLOW(x)   do { } while (0)
-#define	STATS_SET_FREEABLE(x, i) do { } while (0)
-#define STATS_INC_ALLOCHIT(x)	do { } while (0)
-#define STATS_INC_ALLOCMISS(x)	do { } while (0)
-#define STATS_INC_FREEHIT(x)	do { } while (0)
-#define STATS_INC_FREEMISS(x)	do { } while (0)
-#endif
-
-#if DEBUG
-
-/*
- * memory layout of objects:
- * 0		: objp
- * 0 .. cachep->obj_offset - BYTES_PER_WORD - 1: padding. This ensures that
- * 		the end of an object is aligned with the end of the real
- * 		allocation. Catches writes behind the end of the allocation.
- * cachep->obj_offset - BYTES_PER_WORD .. cachep->obj_offset - 1:
- * 		redzone word.
- * cachep->obj_offset: The real object.
- * cachep->size - 2* BYTES_PER_WORD: redzone word [BYTES_PER_WORD long]
- * cachep->size - 1* BYTES_PER_WORD: last caller address
- *					[BYTES_PER_WORD long]
- */
-static int obj_offset(struct kmem_cache *cachep)
-{
-	return cachep->obj_offset;
-}
-
-static unsigned long long *dbg_redzone1(struct kmem_cache *cachep, void *objp)
-{
-	BUG_ON(!(cachep->flags & SLAB_RED_ZONE));
-	return (unsigned long long *) (objp + obj_offset(cachep) -
-				      sizeof(unsigned long long));
-}
-
-static unsigned long long *dbg_redzone2(struct kmem_cache *cachep, void *objp)
-{
-	BUG_ON(!(cachep->flags & SLAB_RED_ZONE));
-	if (cachep->flags & SLAB_STORE_USER)
-		return (unsigned long long *)(objp + cachep->size -
-					      sizeof(unsigned long long) -
-					      REDZONE_ALIGN);
-	return (unsigned long long *) (objp + cachep->size -
-				       sizeof(unsigned long long));
-}
-
-static void **dbg_userword(struct kmem_cache *cachep, void *objp)
-{
-	BUG_ON(!(cachep->flags & SLAB_STORE_USER));
-	return (void **)(objp + cachep->size - BYTES_PER_WORD);
-}
-
-#else
-
-#define obj_offset(x)			0
-#define dbg_redzone1(cachep, objp)	({BUG(); (unsigned long long *)NULL;})
-#define dbg_redzone2(cachep, objp)	({BUG(); (unsigned long long *)NULL;})
-#define dbg_userword(cachep, objp)	({BUG(); (void **)NULL;})
-
-#endif
-
-/*
- * Do not go above this order unless 0 objects fit into the slab or
- * overridden on the command line.
- */
-#define	SLAB_MAX_ORDER_HI	1
-#define	SLAB_MAX_ORDER_LO	0
-static int slab_max_order = SLAB_MAX_ORDER_LO;
-static bool slab_max_order_set __initdata;
-
-static inline void *index_to_obj(struct kmem_cache *cache,
-				 const struct slab *slab, unsigned int idx)
-{
-	return slab->s_mem + cache->size * idx;
-}
-
-#define BOOT_CPUCACHE_ENTRIES	1
-/* internal cache of cache description objs */
-static struct kmem_cache kmem_cache_boot = {
-	.batchcount = 1,
-	.limit = BOOT_CPUCACHE_ENTRIES,
-	.shared = 1,
-	.size = sizeof(struct kmem_cache),
-	.name = "kmem_cache",
-};
-
-static DEFINE_PER_CPU(struct delayed_work, slab_reap_work);
-
-static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep)
-{
-	return this_cpu_ptr(cachep->cpu_cache);
-}
-
-/*
- * Calculate the number of objects and left-over bytes for a given buffer size.
- */
-static unsigned int cache_estimate(unsigned long gfporder, size_t buffer_size,
-		slab_flags_t flags, size_t *left_over)
-{
-	unsigned int num;
-	size_t slab_size = PAGE_SIZE << gfporder;
-
-	/*
-	 * The slab management structure can be either off the slab or
-	 * on it. For the latter case, the memory allocated for a
-	 * slab is used for:
-	 *
-	 * - @buffer_size bytes for each object
-	 * - One freelist_idx_t for each object
-	 *
-	 * We don't need to consider alignment of freelist because
-	 * freelist will be at the end of slab page. The objects will be
-	 * at the correct alignment.
-	 *
-	 * If the slab management structure is off the slab, then the
-	 * alignment will already be calculated into the size. Because
-	 * the slabs are all pages aligned, the objects will be at the
-	 * correct alignment when allocated.
-	 */
-	if (flags & (CFLGS_OBJFREELIST_SLAB | CFLGS_OFF_SLAB)) {
-		num = slab_size / buffer_size;
-		*left_over = slab_size % buffer_size;
-	} else {
-		num = slab_size / (buffer_size + sizeof(freelist_idx_t));
-		*left_over = slab_size %
-			(buffer_size + sizeof(freelist_idx_t));
-	}
-
-	return num;
-}
-
-#if DEBUG
-#define slab_error(cachep, msg) __slab_error(__func__, cachep, msg)
-
-static void __slab_error(const char *function, struct kmem_cache *cachep,
-			char *msg)
-{
-	pr_err("slab error in %s(): cache `%s': %s\n",
-	       function, cachep->name, msg);
-	dump_stack();
-	add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
-}
-#endif
-
-/*
- * By default on NUMA we use alien caches to stage the freeing of
- * objects allocated from other nodes. This causes massive memory
- * inefficiencies when using fake NUMA setup to split memory into a
- * large number of small nodes, so it can be disabled on the command
- * line
-  */
-
-static int use_alien_caches __read_mostly = 1;
-static int __init noaliencache_setup(char *s)
-{
-	use_alien_caches = 0;
-	return 1;
-}
-__setup("noaliencache", noaliencache_setup);
-
-static int __init slab_max_order_setup(char *str)
-{
-	get_option(&str, &slab_max_order);
-	slab_max_order = slab_max_order < 0 ? 0 :
-				min(slab_max_order, MAX_ORDER);
-	slab_max_order_set = true;
-
-	return 1;
-}
-__setup("slab_max_order=", slab_max_order_setup);
-
-#ifdef CONFIG_NUMA
-/*
- * Special reaping functions for NUMA systems called from cache_reap().
- * These take care of doing round robin flushing of alien caches (containing
- * objects freed on different nodes from which they were allocated) and the
- * flushing of remote pcps by calling drain_node_pages.
- */
-static DEFINE_PER_CPU(unsigned long, slab_reap_node);
-
-static void init_reap_node(int cpu)
-{
-	per_cpu(slab_reap_node, cpu) = next_node_in(cpu_to_mem(cpu),
-						    node_online_map);
-}
-
-static void next_reap_node(void)
-{
-	int node = __this_cpu_read(slab_reap_node);
-
-	node = next_node_in(node, node_online_map);
-	__this_cpu_write(slab_reap_node, node);
-}
-
-#else
-#define init_reap_node(cpu) do { } while (0)
-#define next_reap_node(void) do { } while (0)
-#endif
-
-/*
- * Initiate the reap timer running on the target CPU.  We run at around 1 to 2Hz
- * via the workqueue/eventd.
- * Add the CPU number into the expiration time to minimize the possibility of
- * the CPUs getting into lockstep and contending for the global cache chain
- * lock.
- */
-static void start_cpu_timer(int cpu)
-{
-	struct delayed_work *reap_work = &per_cpu(slab_reap_work, cpu);
-
-	if (reap_work->work.func == NULL) {
-		init_reap_node(cpu);
-		INIT_DEFERRABLE_WORK(reap_work, cache_reap);
-		schedule_delayed_work_on(cpu, reap_work,
-					__round_jiffies_relative(HZ, cpu));
-	}
-}
-
-static void init_arraycache(struct array_cache *ac, int limit, int batch)
-{
-	if (ac) {
-		ac->avail = 0;
-		ac->limit = limit;
-		ac->batchcount = batch;
-		ac->touched = 0;
-	}
-}
-
-static struct array_cache *alloc_arraycache(int node, int entries,
-					    int batchcount, gfp_t gfp)
-{
-	size_t memsize = sizeof(void *) * entries + sizeof(struct array_cache);
-	struct array_cache *ac = NULL;
-
-	ac = kmalloc_node(memsize, gfp, node);
-	/*
-	 * The array_cache structures contain pointers to free object.
-	 * However, when such objects are allocated or transferred to another
-	 * cache the pointers are not cleared and they could be counted as
-	 * valid references during a kmemleak scan. Therefore, kmemleak must
-	 * not scan such objects.
-	 */
-	kmemleak_no_scan(ac);
-	init_arraycache(ac, entries, batchcount);
-	return ac;
-}
-
-static noinline void cache_free_pfmemalloc(struct kmem_cache *cachep,
-					struct slab *slab, void *objp)
-{
-	struct kmem_cache_node *n;
-	int slab_node;
-	LIST_HEAD(list);
-
-	slab_node = slab_nid(slab);
-	n = get_node(cachep, slab_node);
-
-	raw_spin_lock(&n->list_lock);
-	free_block(cachep, &objp, 1, slab_node, &list);
-	raw_spin_unlock(&n->list_lock);
-
-	slabs_destroy(cachep, &list);
-}
-
-/*
- * Transfer objects in one arraycache to another.
- * Locking must be handled by the caller.
- *
- * Return the number of entries transferred.
- */
-static int transfer_objects(struct array_cache *to,
-		struct array_cache *from, unsigned int max)
-{
-	/* Figure out how many entries to transfer */
-	int nr = min3(from->avail, max, to->limit - to->avail);
-
-	if (!nr)
-		return 0;
-
-	memcpy(to->entry + to->avail, from->entry + from->avail - nr,
-			sizeof(void *) *nr);
-
-	from->avail -= nr;
-	to->avail += nr;
-	return nr;
-}
-
-/* &alien->lock must be held by alien callers. */
-static __always_inline void __free_one(struct array_cache *ac, void *objp)
-{
-	/* Avoid trivial double-free. */
-	if (IS_ENABLED(CONFIG_SLAB_FREELIST_HARDENED) &&
-	    WARN_ON_ONCE(ac->avail > 0 && ac->entry[ac->avail - 1] == objp))
-		return;
-	ac->entry[ac->avail++] = objp;
-}
-
-#ifndef CONFIG_NUMA
-
-#define drain_alien_cache(cachep, alien) do { } while (0)
-#define reap_alien(cachep, n) do { } while (0)
-
-static inline struct alien_cache **alloc_alien_cache(int node,
-						int limit, gfp_t gfp)
-{
-	return NULL;
-}
-
-static inline void free_alien_cache(struct alien_cache **ac_ptr)
-{
-}
-
-static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
-{
-	return 0;
-}
-
-static inline gfp_t gfp_exact_node(gfp_t flags)
-{
-	return flags & ~__GFP_NOFAIL;
-}
-
-#else	/* CONFIG_NUMA */
-
-static struct alien_cache *__alloc_alien_cache(int node, int entries,
-						int batch, gfp_t gfp)
-{
-	size_t memsize = sizeof(void *) * entries + sizeof(struct alien_cache);
-	struct alien_cache *alc = NULL;
-
-	alc = kmalloc_node(memsize, gfp, node);
-	if (alc) {
-		kmemleak_no_scan(alc);
-		init_arraycache(&alc->ac, entries, batch);
-		spin_lock_init(&alc->lock);
-	}
-	return alc;
-}
-
-static struct alien_cache **alloc_alien_cache(int node, int limit, gfp_t gfp)
-{
-	struct alien_cache **alc_ptr;
-	int i;
-
-	if (limit > 1)
-		limit = 12;
-	alc_ptr = kcalloc_node(nr_node_ids, sizeof(void *), gfp, node);
-	if (!alc_ptr)
-		return NULL;
-
-	for_each_node(i) {
-		if (i == node || !node_online(i))
-			continue;
-		alc_ptr[i] = __alloc_alien_cache(node, limit, 0xbaadf00d, gfp);
-		if (!alc_ptr[i]) {
-			for (i--; i >= 0; i--)
-				kfree(alc_ptr[i]);
-			kfree(alc_ptr);
-			return NULL;
-		}
-	}
-	return alc_ptr;
-}
-
-static void free_alien_cache(struct alien_cache **alc_ptr)
-{
-	int i;
-
-	if (!alc_ptr)
-		return;
-	for_each_node(i)
-	    kfree(alc_ptr[i]);
-	kfree(alc_ptr);
-}
-
-static void __drain_alien_cache(struct kmem_cache *cachep,
-				struct array_cache *ac, int node,
-				struct list_head *list)
-{
-	struct kmem_cache_node *n = get_node(cachep, node);
-
-	if (ac->avail) {
-		raw_spin_lock(&n->list_lock);
-		/*
-		 * Stuff objects into the remote nodes shared array first.
-		 * That way we could avoid the overhead of putting the objects
-		 * into the free lists and getting them back later.
-		 */
-		if (n->shared)
-			transfer_objects(n->shared, ac, ac->limit);
-
-		free_block(cachep, ac->entry, ac->avail, node, list);
-		ac->avail = 0;
-		raw_spin_unlock(&n->list_lock);
-	}
-}
-
-/*
- * Called from cache_reap() to regularly drain alien caches round robin.
- */
-static void reap_alien(struct kmem_cache *cachep, struct kmem_cache_node *n)
-{
-	int node = __this_cpu_read(slab_reap_node);
-
-	if (n->alien) {
-		struct alien_cache *alc = n->alien[node];
-		struct array_cache *ac;
-
-		if (alc) {
-			ac = &alc->ac;
-			if (ac->avail && spin_trylock_irq(&alc->lock)) {
-				LIST_HEAD(list);
-
-				__drain_alien_cache(cachep, ac, node, &list);
-				spin_unlock_irq(&alc->lock);
-				slabs_destroy(cachep, &list);
-			}
-		}
-	}
-}
-
-static void drain_alien_cache(struct kmem_cache *cachep,
-				struct alien_cache **alien)
-{
-	int i = 0;
-	struct alien_cache *alc;
-	struct array_cache *ac;
-	unsigned long flags;
-
-	for_each_online_node(i) {
-		alc = alien[i];
-		if (alc) {
-			LIST_HEAD(list);
-
-			ac = &alc->ac;
-			spin_lock_irqsave(&alc->lock, flags);
-			__drain_alien_cache(cachep, ac, i, &list);
-			spin_unlock_irqrestore(&alc->lock, flags);
-			slabs_destroy(cachep, &list);
-		}
-	}
-}
-
-static int __cache_free_alien(struct kmem_cache *cachep, void *objp,
-				int node, int slab_node)
-{
-	struct kmem_cache_node *n;
-	struct alien_cache *alien = NULL;
-	struct array_cache *ac;
-	LIST_HEAD(list);
-
-	n = get_node(cachep, node);
-	STATS_INC_NODEFREES(cachep);
-	if (n->alien && n->alien[slab_node]) {
-		alien = n->alien[slab_node];
-		ac = &alien->ac;
-		spin_lock(&alien->lock);
-		if (unlikely(ac->avail == ac->limit)) {
-			STATS_INC_ACOVERFLOW(cachep);
-			__drain_alien_cache(cachep, ac, slab_node, &list);
-		}
-		__free_one(ac, objp);
-		spin_unlock(&alien->lock);
-		slabs_destroy(cachep, &list);
-	} else {
-		n = get_node(cachep, slab_node);
-		raw_spin_lock(&n->list_lock);
-		free_block(cachep, &objp, 1, slab_node, &list);
-		raw_spin_unlock(&n->list_lock);
-		slabs_destroy(cachep, &list);
-	}
-	return 1;
-}
-
-static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
-{
-	int slab_node = slab_nid(virt_to_slab(objp));
-	int node = numa_mem_id();
-	/*
-	 * Make sure we are not freeing an object from another node to the array
-	 * cache on this cpu.
-	 */
-	if (likely(node == slab_node))
-		return 0;
-
-	return __cache_free_alien(cachep, objp, node, slab_node);
-}
-
-/*
- * Construct gfp mask to allocate from a specific node but do not reclaim or
- * warn about failures.
- */
-static inline gfp_t gfp_exact_node(gfp_t flags)
-{
-	return (flags | __GFP_THISNODE | __GFP_NOWARN) & ~(__GFP_RECLAIM|__GFP_NOFAIL);
-}
-#endif
-
-static int init_cache_node(struct kmem_cache *cachep, int node, gfp_t gfp)
-{
-	struct kmem_cache_node *n;
-
-	/*
-	 * Set up the kmem_cache_node for cpu before we can
-	 * begin anything. Make sure some other cpu on this
-	 * node has not already allocated this
-	 */
-	n = get_node(cachep, node);
-	if (n) {
-		raw_spin_lock_irq(&n->list_lock);
-		n->free_limit = (1 + nr_cpus_node(node)) * cachep->batchcount +
-				cachep->num;
-		raw_spin_unlock_irq(&n->list_lock);
-
-		return 0;
-	}
-
-	n = kmalloc_node(sizeof(struct kmem_cache_node), gfp, node);
-	if (!n)
-		return -ENOMEM;
-
-	kmem_cache_node_init(n);
-	n->next_reap = jiffies + REAPTIMEOUT_NODE +
-		    ((unsigned long)cachep) % REAPTIMEOUT_NODE;
-
-	n->free_limit =
-		(1 + nr_cpus_node(node)) * cachep->batchcount + cachep->num;
-
-	/*
-	 * The kmem_cache_nodes don't come and go as CPUs
-	 * come and go.  slab_mutex provides sufficient
-	 * protection here.
-	 */
-	cachep->node[node] = n;
-
-	return 0;
-}
-
-#if defined(CONFIG_NUMA) || defined(CONFIG_SMP)
-/*
- * Allocates and initializes node for a node on each slab cache, used for
- * either memory or cpu hotplug.  If memory is being hot-added, the kmem_cache_node
- * will be allocated off-node since memory is not yet online for the new node.
- * When hotplugging memory or a cpu, existing nodes are not replaced if
- * already in use.
- *
- * Must hold slab_mutex.
- */
-static int init_cache_node_node(int node)
-{
-	int ret;
-	struct kmem_cache *cachep;
-
-	list_for_each_entry(cachep, &slab_caches, list) {
-		ret = init_cache_node(cachep, node, GFP_KERNEL);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-#endif
-
-static int setup_kmem_cache_node(struct kmem_cache *cachep,
-				int node, gfp_t gfp, bool force_change)
-{
-	int ret = -ENOMEM;
-	struct kmem_cache_node *n;
-	struct array_cache *old_shared = NULL;
-	struct array_cache *new_shared = NULL;
-	struct alien_cache **new_alien = NULL;
-	LIST_HEAD(list);
-
-	if (use_alien_caches) {
-		new_alien = alloc_alien_cache(node, cachep->limit, gfp);
-		if (!new_alien)
-			goto fail;
-	}
-
-	if (cachep->shared) {
-		new_shared = alloc_arraycache(node,
-			cachep->shared * cachep->batchcount, 0xbaadf00d, gfp);
-		if (!new_shared)
-			goto fail;
-	}
-
-	ret = init_cache_node(cachep, node, gfp);
-	if (ret)
-		goto fail;
-
-	n = get_node(cachep, node);
-	raw_spin_lock_irq(&n->list_lock);
-	if (n->shared && force_change) {
-		free_block(cachep, n->shared->entry,
-				n->shared->avail, node, &list);
-		n->shared->avail = 0;
-	}
-
-	if (!n->shared || force_change) {
-		old_shared = n->shared;
-		n->shared = new_shared;
-		new_shared = NULL;
-	}
-
-	if (!n->alien) {
-		n->alien = new_alien;
-		new_alien = NULL;
-	}
-
-	raw_spin_unlock_irq(&n->list_lock);
-	slabs_destroy(cachep, &list);
-
-	/*
-	 * To protect lockless access to n->shared during irq disabled context.
-	 * If n->shared isn't NULL in irq disabled context, accessing to it is
-	 * guaranteed to be valid until irq is re-enabled, because it will be
-	 * freed after synchronize_rcu().
-	 */
-	if (old_shared && force_change)
-		synchronize_rcu();
-
-fail:
-	kfree(old_shared);
-	kfree(new_shared);
-	free_alien_cache(new_alien);
-
-	return ret;
-}
-
-#ifdef CONFIG_SMP
-
-static void cpuup_canceled(long cpu)
-{
-	struct kmem_cache *cachep;
-	struct kmem_cache_node *n = NULL;
-	int node = cpu_to_mem(cpu);
-	const struct cpumask *mask = cpumask_of_node(node);
-
-	list_for_each_entry(cachep, &slab_caches, list) {
-		struct array_cache *nc;
-		struct array_cache *shared;
-		struct alien_cache **alien;
-		LIST_HEAD(list);
-
-		n = get_node(cachep, node);
-		if (!n)
-			continue;
-
-		raw_spin_lock_irq(&n->list_lock);
-
-		/* Free limit for this kmem_cache_node */
-		n->free_limit -= cachep->batchcount;
-
-		/* cpu is dead; no one can alloc from it. */
-		nc = per_cpu_ptr(cachep->cpu_cache, cpu);
-		free_block(cachep, nc->entry, nc->avail, node, &list);
-		nc->avail = 0;
-
-		if (!cpumask_empty(mask)) {
-			raw_spin_unlock_irq(&n->list_lock);
-			goto free_slab;
-		}
-
-		shared = n->shared;
-		if (shared) {
-			free_block(cachep, shared->entry,
-				   shared->avail, node, &list);
-			n->shared = NULL;
-		}
-
-		alien = n->alien;
-		n->alien = NULL;
-
-		raw_spin_unlock_irq(&n->list_lock);
-
-		kfree(shared);
-		if (alien) {
-			drain_alien_cache(cachep, alien);
-			free_alien_cache(alien);
-		}
-
-free_slab:
-		slabs_destroy(cachep, &list);
-	}
-	/*
-	 * In the previous loop, all the objects were freed to
-	 * the respective cache's slabs,  now we can go ahead and
-	 * shrink each nodelist to its limit.
-	 */
-	list_for_each_entry(cachep, &slab_caches, list) {
-		n = get_node(cachep, node);
-		if (!n)
-			continue;
-		drain_freelist(cachep, n, INT_MAX);
-	}
-}
-
-static int cpuup_prepare(long cpu)
-{
-	struct kmem_cache *cachep;
-	int node = cpu_to_mem(cpu);
-	int err;
-
-	/*
-	 * We need to do this right in the beginning since
-	 * alloc_arraycache's are going to use this list.
-	 * kmalloc_node allows us to add the slab to the right
-	 * kmem_cache_node and not this cpu's kmem_cache_node
-	 */
-	err = init_cache_node_node(node);
-	if (err < 0)
-		goto bad;
-
-	/*
-	 * Now we can go ahead with allocating the shared arrays and
-	 * array caches
-	 */
-	list_for_each_entry(cachep, &slab_caches, list) {
-		err = setup_kmem_cache_node(cachep, node, GFP_KERNEL, false);
-		if (err)
-			goto bad;
-	}
-
-	return 0;
-bad:
-	cpuup_canceled(cpu);
-	return -ENOMEM;
-}
-
-int slab_prepare_cpu(unsigned int cpu)
-{
-	int err;
-
-	mutex_lock(&slab_mutex);
-	err = cpuup_prepare(cpu);
-	mutex_unlock(&slab_mutex);
-	return err;
-}
-
-/*
- * This is called for a failed online attempt and for a successful
- * offline.
- *
- * Even if all the cpus of a node are down, we don't free the
- * kmem_cache_node of any cache. This is to avoid a race between cpu_down, and
- * a kmalloc allocation from another cpu for memory from the node of
- * the cpu going down.  The kmem_cache_node structure is usually allocated from
- * kmem_cache_create() and gets destroyed at kmem_cache_destroy().
- */
-int slab_dead_cpu(unsigned int cpu)
-{
-	mutex_lock(&slab_mutex);
-	cpuup_canceled(cpu);
-	mutex_unlock(&slab_mutex);
-	return 0;
-}
-#endif
-
-static int slab_online_cpu(unsigned int cpu)
-{
-	start_cpu_timer(cpu);
-	return 0;
-}
-
-static int slab_offline_cpu(unsigned int cpu)
-{
-	/*
-	 * Shutdown cache reaper. Note that the slab_mutex is held so
-	 * that if cache_reap() is invoked it cannot do anything
-	 * expensive but will only modify reap_work and reschedule the
-	 * timer.
-	 */
-	cancel_delayed_work_sync(&per_cpu(slab_reap_work, cpu));
-	/* Now the cache_reaper is guaranteed to be not running. */
-	per_cpu(slab_reap_work, cpu).work.func = NULL;
-	return 0;
-}
-
-#if defined(CONFIG_NUMA)
-/*
- * Drains freelist for a node on each slab cache, used for memory hot-remove.
- * Returns -EBUSY if all objects cannot be drained so that the node is not
- * removed.
- *
- * Must hold slab_mutex.
- */
-static int __meminit drain_cache_node_node(int node)
-{
-	struct kmem_cache *cachep;
-	int ret = 0;
-
-	list_for_each_entry(cachep, &slab_caches, list) {
-		struct kmem_cache_node *n;
-
-		n = get_node(cachep, node);
-		if (!n)
-			continue;
-
-		drain_freelist(cachep, n, INT_MAX);
-
-		if (!list_empty(&n->slabs_full) ||
-		    !list_empty(&n->slabs_partial)) {
-			ret = -EBUSY;
-			break;
-		}
-	}
-	return ret;
-}
-
-static int __meminit slab_memory_callback(struct notifier_block *self,
-					unsigned long action, void *arg)
-{
-	struct memory_notify *mnb = arg;
-	int ret = 0;
-	int nid;
-
-	nid = mnb->status_change_nid;
-	if (nid < 0)
-		goto out;
-
-	switch (action) {
-	case MEM_GOING_ONLINE:
-		mutex_lock(&slab_mutex);
-		ret = init_cache_node_node(nid);
-		mutex_unlock(&slab_mutex);
-		break;
-	case MEM_GOING_OFFLINE:
-		mutex_lock(&slab_mutex);
-		ret = drain_cache_node_node(nid);
-		mutex_unlock(&slab_mutex);
-		break;
-	case MEM_ONLINE:
-	case MEM_OFFLINE:
-	case MEM_CANCEL_ONLINE:
-	case MEM_CANCEL_OFFLINE:
-		break;
-	}
-out:
-	return notifier_from_errno(ret);
-}
-#endif /* CONFIG_NUMA */
-
-/*
- * swap the static kmem_cache_node with kmalloced memory
- */
-static void __init init_list(struct kmem_cache *cachep, struct kmem_cache_node *list,
-				int nodeid)
-{
-	struct kmem_cache_node *ptr;
-
-	ptr = kmalloc_node(sizeof(struct kmem_cache_node), GFP_NOWAIT, nodeid);
-	BUG_ON(!ptr);
-
-	memcpy(ptr, list, sizeof(struct kmem_cache_node));
-	/*
-	 * Do not assume that spinlocks can be initialized via memcpy:
-	 */
-	raw_spin_lock_init(&ptr->list_lock);
-
-	MAKE_ALL_LISTS(cachep, ptr, nodeid);
-	cachep->node[nodeid] = ptr;
-}
-
-/*
- * For setting up all the kmem_cache_node for cache whose buffer_size is same as
- * size of kmem_cache_node.
- */
-static void __init set_up_node(struct kmem_cache *cachep, int index)
-{
-	int node;
-
-	for_each_online_node(node) {
-		cachep->node[node] = &init_kmem_cache_node[index + node];
-		cachep->node[node]->next_reap = jiffies +
-		    REAPTIMEOUT_NODE +
-		    ((unsigned long)cachep) % REAPTIMEOUT_NODE;
-	}
-}
-
-/*
- * Initialisation.  Called after the page allocator have been initialised and
- * before smp_init().
- */
-void __init kmem_cache_init(void)
-{
-	int i;
-
-	kmem_cache = &kmem_cache_boot;
-
-	if (!IS_ENABLED(CONFIG_NUMA) || num_possible_nodes() == 1)
-		use_alien_caches = 0;
-
-	for (i = 0; i < NUM_INIT_LISTS; i++)
-		kmem_cache_node_init(&init_kmem_cache_node[i]);
-
-	/*
-	 * Fragmentation resistance on low memory - only use bigger
-	 * page orders on machines with more than 32MB of memory if
-	 * not overridden on the command line.
-	 */
-	if (!slab_max_order_set && totalram_pages() > (32 << 20) >> PAGE_SHIFT)
-		slab_max_order = SLAB_MAX_ORDER_HI;
-
-	/* Bootstrap is tricky, because several objects are allocated
-	 * from caches that do not exist yet:
-	 * 1) initialize the kmem_cache cache: it contains the struct
-	 *    kmem_cache structures of all caches, except kmem_cache itself:
-	 *    kmem_cache is statically allocated.
-	 *    Initially an __init data area is used for the head array and the
-	 *    kmem_cache_node structures, it's replaced with a kmalloc allocated
-	 *    array at the end of the bootstrap.
-	 * 2) Create the first kmalloc cache.
-	 *    The struct kmem_cache for the new cache is allocated normally.
-	 *    An __init data area is used for the head array.
-	 * 3) Create the remaining kmalloc caches, with minimally sized
-	 *    head arrays.
-	 * 4) Replace the __init data head arrays for kmem_cache and the first
-	 *    kmalloc cache with kmalloc allocated arrays.
-	 * 5) Replace the __init data for kmem_cache_node for kmem_cache and
-	 *    the other cache's with kmalloc allocated memory.
-	 * 6) Resize the head arrays of the kmalloc caches to their final sizes.
-	 */
-
-	/* 1) create the kmem_cache */
-
-	/*
-	 * struct kmem_cache size depends on nr_node_ids & nr_cpu_ids
-	 */
-	create_boot_cache(kmem_cache, "kmem_cache",
-		offsetof(struct kmem_cache, node) +
-				  nr_node_ids * sizeof(struct kmem_cache_node *),
-				  SLAB_HWCACHE_ALIGN, 0, 0);
-	list_add(&kmem_cache->list, &slab_caches);
-	slab_state = PARTIAL;
-
-	/*
-	 * Initialize the caches that provide memory for the  kmem_cache_node
-	 * structures first.  Without this, further allocations will bug.
-	 */
-	new_kmalloc_cache(INDEX_NODE, KMALLOC_NORMAL, ARCH_KMALLOC_FLAGS);
-	slab_state = PARTIAL_NODE;
-	setup_kmalloc_cache_index_table();
-
-	/* 5) Replace the bootstrap kmem_cache_node */
-	{
-		int nid;
-
-		for_each_online_node(nid) {
-			init_list(kmem_cache, &init_kmem_cache_node[CACHE_CACHE + nid], nid);
-
-			init_list(kmalloc_caches[KMALLOC_NORMAL][INDEX_NODE],
-					  &init_kmem_cache_node[SIZE_NODE + nid], nid);
-		}
-	}
-
-	create_kmalloc_caches(ARCH_KMALLOC_FLAGS);
-}
-
-void __init kmem_cache_init_late(void)
-{
-	struct kmem_cache *cachep;
-
-	/* 6) resize the head arrays to their final sizes */
-	mutex_lock(&slab_mutex);
-	list_for_each_entry(cachep, &slab_caches, list)
-		if (enable_cpucache(cachep, GFP_NOWAIT))
-			BUG();
-	mutex_unlock(&slab_mutex);
-
-	/* Done! */
-	slab_state = FULL;
-
-#ifdef CONFIG_NUMA
-	/*
-	 * Register a memory hotplug callback that initializes and frees
-	 * node.
-	 */
-	hotplug_memory_notifier(slab_memory_callback, SLAB_CALLBACK_PRI);
-#endif
-
-	/*
-	 * The reap timers are started later, with a module init call: That part
-	 * of the kernel is not yet operational.
-	 */
-}
-
-static int __init cpucache_init(void)
-{
-	int ret;
-
-	/*
-	 * Register the timers that return unneeded pages to the page allocator
-	 */
-	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "SLAB online",
-				slab_online_cpu, slab_offline_cpu);
-	WARN_ON(ret < 0);
-
-	return 0;
-}
-__initcall(cpucache_init);
-
-static noinline void
-slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid)
-{
-#if DEBUG
-	struct kmem_cache_node *n;
-	unsigned long flags;
-	int node;
-	static DEFINE_RATELIMIT_STATE(slab_oom_rs, DEFAULT_RATELIMIT_INTERVAL,
-				      DEFAULT_RATELIMIT_BURST);
-
-	if ((gfpflags & __GFP_NOWARN) || !__ratelimit(&slab_oom_rs))
-		return;
-
-	pr_warn("SLAB: Unable to allocate memory on node %d, gfp=%#x(%pGg)\n",
-		nodeid, gfpflags, &gfpflags);
-	pr_warn("  cache: %s, object size: %d, order: %d\n",
-		cachep->name, cachep->size, cachep->gfporder);
-
-	for_each_kmem_cache_node(cachep, node, n) {
-		unsigned long total_slabs, free_slabs, free_objs;
-
-		raw_spin_lock_irqsave(&n->list_lock, flags);
-		total_slabs = n->total_slabs;
-		free_slabs = n->free_slabs;
-		free_objs = n->free_objects;
-		raw_spin_unlock_irqrestore(&n->list_lock, flags);
-
-		pr_warn("  node %d: slabs: %ld/%ld, objs: %ld/%ld\n",
-			node, total_slabs - free_slabs, total_slabs,
-			(total_slabs * cachep->num) - free_objs,
-			total_slabs * cachep->num);
-	}
-#endif
-}
-
-/*
- * Interface to system's page allocator. No need to hold the
- * kmem_cache_node ->list_lock.
- *
- * If we requested dmaable memory, we will get it. Even if we
- * did not request dmaable memory, we might get it, but that
- * would be relatively rare and ignorable.
- */
-static struct slab *kmem_getpages(struct kmem_cache *cachep, gfp_t flags,
-								int nodeid)
-{
-	struct folio *folio;
-	struct slab *slab;
-
-	flags |= cachep->allocflags;
-
-	folio = (struct folio *) __alloc_pages_node(nodeid, flags, cachep->gfporder);
-	if (!folio) {
-		slab_out_of_memory(cachep, flags, nodeid);
-		return NULL;
-	}
-
-	slab = folio_slab(folio);
-
-	account_slab(slab, cachep->gfporder, cachep, flags);
-	__folio_set_slab(folio);
-	/* Make the flag visible before any changes to folio->mapping */
-	smp_wmb();
-	/* Record if ALLOC_NO_WATERMARKS was set when allocating the slab */
-	if (sk_memalloc_socks() && folio_is_pfmemalloc(folio))
-		slab_set_pfmemalloc(slab);
-
-	return slab;
-}
-
-/*
- * Interface to system's page release.
- */
-static void kmem_freepages(struct kmem_cache *cachep, struct slab *slab)
-{
-	int order = cachep->gfporder;
-	struct folio *folio = slab_folio(slab);
-
-	BUG_ON(!folio_test_slab(folio));
-	__slab_clear_pfmemalloc(slab);
-	page_mapcount_reset(&folio->page);
-	folio->mapping = NULL;
-	/* Make the mapping reset visible before clearing the flag */
-	smp_wmb();
-	__folio_clear_slab(folio);
-
-	mm_account_reclaimed_pages(1 << order);
-	unaccount_slab(slab, order, cachep);
-	__free_pages(&folio->page, order);
-}
-
-static void kmem_rcu_free(struct rcu_head *head)
-{
-	struct kmem_cache *cachep;
-	struct slab *slab;
-
-	slab = container_of(head, struct slab, rcu_head);
-	cachep = slab->slab_cache;
-
-	kmem_freepages(cachep, slab);
-}
-
-#if DEBUG
-static inline bool is_debug_pagealloc_cache(struct kmem_cache *cachep)
-{
-	return debug_pagealloc_enabled_static() && OFF_SLAB(cachep) &&
-			((cachep->size % PAGE_SIZE) == 0);
-}
-
-#ifdef CONFIG_DEBUG_PAGEALLOC
-static void slab_kernel_map(struct kmem_cache *cachep, void *objp, int map)
-{
-	if (!is_debug_pagealloc_cache(cachep))
-		return;
-
-	__kernel_map_pages(virt_to_page(objp), cachep->size / PAGE_SIZE, map);
-}
-
-#else
-static inline void slab_kernel_map(struct kmem_cache *cachep, void *objp,
-				int map) {}
-
-#endif
-
-static void poison_obj(struct kmem_cache *cachep, void *addr, unsigned char val)
-{
-	int size = cachep->object_size;
-	addr = &((char *)addr)[obj_offset(cachep)];
-
-	memset(addr, val, size);
-	*(unsigned char *)(addr + size - 1) = POISON_END;
-}
-
-static void dump_line(char *data, int offset, int limit)
-{
-	int i;
-	unsigned char error = 0;
-	int bad_count = 0;
-
-	pr_err("%03x: ", offset);
-	for (i = 0; i < limit; i++) {
-		if (data[offset + i] != POISON_FREE) {
-			error = data[offset + i];
-			bad_count++;
-		}
-	}
-	print_hex_dump(KERN_CONT, "", 0, 16, 1,
-			&data[offset], limit, 1);
-
-	if (bad_count == 1) {
-		error ^= POISON_FREE;
-		if (!(error & (error - 1))) {
-			pr_err("Single bit error detected. Probably bad RAM.\n");
-#ifdef CONFIG_X86
-			pr_err("Run memtest86+ or a similar memory test tool.\n");
-#else
-			pr_err("Run a memory test tool.\n");
-#endif
-		}
-	}
-}
-#endif
-
-#if DEBUG
-
-static void print_objinfo(struct kmem_cache *cachep, void *objp, int lines)
-{
-	int i, size;
-	char *realobj;
-
-	if (cachep->flags & SLAB_RED_ZONE) {
-		pr_err("Redzone: 0x%llx/0x%llx\n",
-		       *dbg_redzone1(cachep, objp),
-		       *dbg_redzone2(cachep, objp));
-	}
-
-	if (cachep->flags & SLAB_STORE_USER)
-		pr_err("Last user: (%pSR)\n", *dbg_userword(cachep, objp));
-	realobj = (char *)objp + obj_offset(cachep);
-	size = cachep->object_size;
-	for (i = 0; i < size && lines; i += 16, lines--) {
-		int limit;
-		limit = 16;
-		if (i + limit > size)
-			limit = size - i;
-		dump_line(realobj, i, limit);
-	}
-}
-
-static void check_poison_obj(struct kmem_cache *cachep, void *objp)
-{
-	char *realobj;
-	int size, i;
-	int lines = 0;
-
-	if (is_debug_pagealloc_cache(cachep))
-		return;
-
-	realobj = (char *)objp + obj_offset(cachep);
-	size = cachep->object_size;
-
-	for (i = 0; i < size; i++) {
-		char exp = POISON_FREE;
-		if (i == size - 1)
-			exp = POISON_END;
-		if (realobj[i] != exp) {
-			int limit;
-			/* Mismatch ! */
-			/* Print header */
-			if (lines == 0) {
-				pr_err("Slab corruption (%s): %s start=%px, len=%d\n",
-				       print_tainted(), cachep->name,
-				       realobj, size);
-				print_objinfo(cachep, objp, 0);
-			}
-			/* Hexdump the affected line */
-			i = (i / 16) * 16;
-			limit = 16;
-			if (i + limit > size)
-				limit = size - i;
-			dump_line(realobj, i, limit);
-			i += 16;
-			lines++;
-			/* Limit to 5 lines */
-			if (lines > 5)
-				break;
-		}
-	}
-	if (lines != 0) {
-		/* Print some data about the neighboring objects, if they
-		 * exist:
-		 */
-		struct slab *slab = virt_to_slab(objp);
-		unsigned int objnr;
-
-		objnr = obj_to_index(cachep, slab, objp);
-		if (objnr) {
-			objp = index_to_obj(cachep, slab, objnr - 1);
-			realobj = (char *)objp + obj_offset(cachep);
-			pr_err("Prev obj: start=%px, len=%d\n", realobj, size);
-			print_objinfo(cachep, objp, 2);
-		}
-		if (objnr + 1 < cachep->num) {
-			objp = index_to_obj(cachep, slab, objnr + 1);
-			realobj = (char *)objp + obj_offset(cachep);
-			pr_err("Next obj: start=%px, len=%d\n", realobj, size);
-			print_objinfo(cachep, objp, 2);
-		}
-	}
-}
-#endif
-
-#if DEBUG
-static void slab_destroy_debugcheck(struct kmem_cache *cachep,
-						struct slab *slab)
-{
-	int i;
-
-	if (OBJFREELIST_SLAB(cachep) && cachep->flags & SLAB_POISON) {
-		poison_obj(cachep, slab->freelist - obj_offset(cachep),
-			POISON_FREE);
-	}
-
-	for (i = 0; i < cachep->num; i++) {
-		void *objp = index_to_obj(cachep, slab, i);
-
-		if (cachep->flags & SLAB_POISON) {
-			check_poison_obj(cachep, objp);
-			slab_kernel_map(cachep, objp, 1);
-		}
-		if (cachep->flags & SLAB_RED_ZONE) {
-			if (*dbg_redzone1(cachep, objp) != RED_INACTIVE)
-				slab_error(cachep, "start of a freed object was overwritten");
-			if (*dbg_redzone2(cachep, objp) != RED_INACTIVE)
-				slab_error(cachep, "end of a freed object was overwritten");
-		}
-	}
-}
-#else
-static void slab_destroy_debugcheck(struct kmem_cache *cachep,
-						struct slab *slab)
-{
-}
-#endif
-
-/**
- * slab_destroy - destroy and release all objects in a slab
- * @cachep: cache pointer being destroyed
- * @slab: slab being destroyed
- *
- * Destroy all the objs in a slab, and release the mem back to the system.
- * Before calling the slab must have been unlinked from the cache. The
- * kmem_cache_node ->list_lock is not held/needed.
- */
-static void slab_destroy(struct kmem_cache *cachep, struct slab *slab)
-{
-	void *freelist;
-
-	freelist = slab->freelist;
-	slab_destroy_debugcheck(cachep, slab);
-	if (unlikely(cachep->flags & SLAB_TYPESAFE_BY_RCU))
-		call_rcu(&slab->rcu_head, kmem_rcu_free);
-	else
-		kmem_freepages(cachep, slab);
-
-	/*
-	 * From now on, we don't use freelist
-	 * although actual page can be freed in rcu context
-	 */
-	if (OFF_SLAB(cachep))
-		kfree(freelist);
-}
-
-/*
- * Update the size of the caches before calling slabs_destroy as it may
- * recursively call kfree.
- */
-static void slabs_destroy(struct kmem_cache *cachep, struct list_head *list)
-{
-	struct slab *slab, *n;
-
-	list_for_each_entry_safe(slab, n, list, slab_list) {
-		list_del(&slab->slab_list);
-		slab_destroy(cachep, slab);
-	}
-}
-
-/**
- * calculate_slab_order - calculate size (page order) of slabs
- * @cachep: pointer to the cache that is being created
- * @size: size of objects to be created in this cache.
- * @flags: slab allocation flags
- *
- * Also calculates the number of objects per slab.
- *
- * This could be made much more intelligent.  For now, try to avoid using
- * high order pages for slabs.  When the gfp() functions are more friendly
- * towards high-order requests, this should be changed.
- *
- * Return: number of left-over bytes in a slab
- */
-static size_t calculate_slab_order(struct kmem_cache *cachep,
-				size_t size, slab_flags_t flags)
-{
-	size_t left_over = 0;
-	int gfporder;
-
-	for (gfporder = 0; gfporder <= KMALLOC_MAX_ORDER; gfporder++) {
-		unsigned int num;
-		size_t remainder;
-
-		num = cache_estimate(gfporder, size, flags, &remainder);
-		if (!num)
-			continue;
-
-		/* Can't handle number of objects more than SLAB_OBJ_MAX_NUM */
-		if (num > SLAB_OBJ_MAX_NUM)
-			break;
-
-		if (flags & CFLGS_OFF_SLAB) {
-			struct kmem_cache *freelist_cache;
-			size_t freelist_size;
-			size_t freelist_cache_size;
-
-			freelist_size = num * sizeof(freelist_idx_t);
-			if (freelist_size > KMALLOC_MAX_CACHE_SIZE) {
-				freelist_cache_size = PAGE_SIZE << get_order(freelist_size);
-			} else {
-				freelist_cache = kmalloc_slab(freelist_size, 0u, _RET_IP_);
-				if (!freelist_cache)
-					continue;
-				freelist_cache_size = freelist_cache->size;
-
-				/*
-				 * Needed to avoid possible looping condition
-				 * in cache_grow_begin()
-				 */
-				if (OFF_SLAB(freelist_cache))
-					continue;
-			}
-
-			/* check if off slab has enough benefit */
-			if (freelist_cache_size > cachep->size / 2)
-				continue;
-		}
-
-		/* Found something acceptable - save it away */
-		cachep->num = num;
-		cachep->gfporder = gfporder;
-		left_over = remainder;
-
-		/*
-		 * A VFS-reclaimable slab tends to have most allocations
-		 * as GFP_NOFS and we really don't want to have to be allocating
-		 * higher-order pages when we are unable to shrink dcache.
-		 */
-		if (flags & SLAB_RECLAIM_ACCOUNT)
-			break;
-
-		/*
-		 * Large number of objects is good, but very large slabs are
-		 * currently bad for the gfp()s.
-		 */
-		if (gfporder >= slab_max_order)
-			break;
-
-		/*
-		 * Acceptable internal fragmentation?
-		 */
-		if (left_over * 8 <= (PAGE_SIZE << gfporder))
-			break;
-	}
-	return left_over;
-}
-
-static struct array_cache __percpu *alloc_kmem_cache_cpus(
-		struct kmem_cache *cachep, int entries, int batchcount)
-{
-	int cpu;
-	size_t size;
-	struct array_cache __percpu *cpu_cache;
-
-	size = sizeof(void *) * entries + sizeof(struct array_cache);
-	cpu_cache = __alloc_percpu(size, sizeof(void *));
-
-	if (!cpu_cache)
-		return NULL;
-
-	for_each_possible_cpu(cpu) {
-		init_arraycache(per_cpu_ptr(cpu_cache, cpu),
-				entries, batchcount);
-	}
-
-	return cpu_cache;
-}
-
-static int __ref setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp)
-{
-	if (slab_state >= FULL)
-		return enable_cpucache(cachep, gfp);
-
-	cachep->cpu_cache = alloc_kmem_cache_cpus(cachep, 1, 1);
-	if (!cachep->cpu_cache)
-		return 1;
-
-	if (slab_state == DOWN) {
-		/* Creation of first cache (kmem_cache). */
-		set_up_node(kmem_cache, CACHE_CACHE);
-	} else if (slab_state == PARTIAL) {
-		/* For kmem_cache_node */
-		set_up_node(cachep, SIZE_NODE);
-	} else {
-		int node;
-
-		for_each_online_node(node) {
-			cachep->node[node] = kmalloc_node(
-				sizeof(struct kmem_cache_node), gfp, node);
-			BUG_ON(!cachep->node[node]);
-			kmem_cache_node_init(cachep->node[node]);
-		}
-	}
-
-	cachep->node[numa_mem_id()]->next_reap =
-			jiffies + REAPTIMEOUT_NODE +
-			((unsigned long)cachep) % REAPTIMEOUT_NODE;
-
-	cpu_cache_get(cachep)->avail = 0;
-	cpu_cache_get(cachep)->limit = BOOT_CPUCACHE_ENTRIES;
-	cpu_cache_get(cachep)->batchcount = 1;
-	cpu_cache_get(cachep)->touched = 0;
-	cachep->batchcount = 1;
-	cachep->limit = BOOT_CPUCACHE_ENTRIES;
-	return 0;
-}
-
-slab_flags_t kmem_cache_flags(unsigned int object_size,
-	slab_flags_t flags, const char *name)
-{
-	return flags;
-}
-
-struct kmem_cache *
-__kmem_cache_alias(const char *name, unsigned int size, unsigned int align,
-		   slab_flags_t flags, void (*ctor)(void *))
-{
-	struct kmem_cache *cachep;
-
-	cachep = find_mergeable(size, align, flags, name, ctor);
-	if (cachep) {
-		cachep->refcount++;
-
-		/*
-		 * Adjust the object sizes so that we clear
-		 * the complete object on kzalloc.
-		 */
-		cachep->object_size = max_t(int, cachep->object_size, size);
-	}
-	return cachep;
-}
-
-static bool set_objfreelist_slab_cache(struct kmem_cache *cachep,
-			size_t size, slab_flags_t flags)
-{
-	size_t left;
-
-	cachep->num = 0;
-
-	/*
-	 * If slab auto-initialization on free is enabled, store the freelist
-	 * off-slab, so that its contents don't end up in one of the allocated
-	 * objects.
-	 */
-	if (unlikely(slab_want_init_on_free(cachep)))
-		return false;
-
-	if (cachep->ctor || flags & SLAB_TYPESAFE_BY_RCU)
-		return false;
-
-	left = calculate_slab_order(cachep, size,
-			flags | CFLGS_OBJFREELIST_SLAB);
-	if (!cachep->num)
-		return false;
-
-	if (cachep->num * sizeof(freelist_idx_t) > cachep->object_size)
-		return false;
-
-	cachep->colour = left / cachep->colour_off;
-
-	return true;
-}
-
-static bool set_off_slab_cache(struct kmem_cache *cachep,
-			size_t size, slab_flags_t flags)
-{
-	size_t left;
-
-	cachep->num = 0;
-
-	/*
-	 * Always use on-slab management when SLAB_NOLEAKTRACE
-	 * to avoid recursive calls into kmemleak.
-	 */
-	if (flags & SLAB_NOLEAKTRACE)
-		return false;
-
-	/*
-	 * Size is large, assume best to place the slab management obj
-	 * off-slab (should allow better packing of objs).
-	 */
-	left = calculate_slab_order(cachep, size, flags | CFLGS_OFF_SLAB);
-	if (!cachep->num)
-		return false;
-
-	/*
-	 * If the slab has been placed off-slab, and we have enough space then
-	 * move it on-slab. This is at the expense of any extra colouring.
-	 */
-	if (left >= cachep->num * sizeof(freelist_idx_t))
-		return false;
-
-	cachep->colour = left / cachep->colour_off;
-
-	return true;
-}
-
-static bool set_on_slab_cache(struct kmem_cache *cachep,
-			size_t size, slab_flags_t flags)
-{
-	size_t left;
-
-	cachep->num = 0;
-
-	left = calculate_slab_order(cachep, size, flags);
-	if (!cachep->num)
-		return false;
-
-	cachep->colour = left / cachep->colour_off;
-
-	return true;
-}
-
-/*
- * __kmem_cache_create - Create a cache.
- * @cachep: cache management descriptor
- * @flags: SLAB flags
- *
- * Returns zero on success, nonzero on failure.
- *
- * The flags are
- *
- * %SLAB_POISON - Poison the slab with a known test pattern (a5a5a5a5)
- * to catch references to uninitialised memory.
- *
- * %SLAB_RED_ZONE - Insert `Red' zones around the allocated memory to check
- * for buffer overruns.
- *
- * %SLAB_HWCACHE_ALIGN - Align the objects in this cache to a hardware
- * cacheline.  This can be beneficial if you're counting cycles as closely
- * as davem.
- */
-int __kmem_cache_create(struct kmem_cache *cachep, slab_flags_t flags)
-{
-	size_t ralign = BYTES_PER_WORD;
-	gfp_t gfp;
-	int err;
-	unsigned int size = cachep->size;
-
-#if DEBUG
-#if FORCED_DEBUG
-	/*
-	 * Enable redzoning and last user accounting, except for caches with
-	 * large objects, if the increased size would increase the object size
-	 * above the next power of two: caches with object sizes just above a
-	 * power of two have a significant amount of internal fragmentation.
-	 */
-	if (size < 4096 || fls(size - 1) == fls(size-1 + REDZONE_ALIGN +
-						2 * sizeof(unsigned long long)))
-		flags |= SLAB_RED_ZONE | SLAB_STORE_USER;
-	if (!(flags & SLAB_TYPESAFE_BY_RCU))
-		flags |= SLAB_POISON;
-#endif
-#endif
-
-	/*
-	 * Check that size is in terms of words.  This is needed to avoid
-	 * unaligned accesses for some archs when redzoning is used, and makes
-	 * sure any on-slab bufctl's are also correctly aligned.
-	 */
-	size = ALIGN(size, BYTES_PER_WORD);
-
-	if (flags & SLAB_RED_ZONE) {
-		ralign = REDZONE_ALIGN;
-		/* If redzoning, ensure that the second redzone is suitably
-		 * aligned, by adjusting the object size accordingly. */
-		size = ALIGN(size, REDZONE_ALIGN);
-	}
-
-	/* 3) caller mandated alignment */
-	if (ralign < cachep->align) {
-		ralign = cachep->align;
-	}
-	/* disable debug if necessary */
-	if (ralign > __alignof__(unsigned long long))
-		flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
-	/*
-	 * 4) Store it.
-	 */
-	cachep->align = ralign;
-	cachep->colour_off = cache_line_size();
-	/* Offset must be a multiple of the alignment. */
-	if (cachep->colour_off < cachep->align)
-		cachep->colour_off = cachep->align;
-
-	if (slab_is_available())
-		gfp = GFP_KERNEL;
-	else
-		gfp = GFP_NOWAIT;
-
-#if DEBUG
-
-	/*
-	 * Both debugging options require word-alignment which is calculated
-	 * into align above.
-	 */
-	if (flags & SLAB_RED_ZONE) {
-		/* add space for red zone words */
-		cachep->obj_offset += sizeof(unsigned long long);
-		size += 2 * sizeof(unsigned long long);
-	}
-	if (flags & SLAB_STORE_USER) {
-		/* user store requires one word storage behind the end of
-		 * the real object. But if the second red zone needs to be
-		 * aligned to 64 bits, we must allow that much space.
-		 */
-		if (flags & SLAB_RED_ZONE)
-			size += REDZONE_ALIGN;
-		else
-			size += BYTES_PER_WORD;
-	}
-#endif
-
-	kasan_cache_create(cachep, &size, &flags);
-
-	size = ALIGN(size, cachep->align);
-	/*
-	 * We should restrict the number of objects in a slab to implement
-	 * byte sized index. Refer comment on SLAB_OBJ_MIN_SIZE definition.
-	 */
-	if (FREELIST_BYTE_INDEX && size < SLAB_OBJ_MIN_SIZE)
-		size = ALIGN(SLAB_OBJ_MIN_SIZE, cachep->align);
-
-#if DEBUG
-	/*
-	 * To activate debug pagealloc, off-slab management is necessary
-	 * requirement. In early phase of initialization, small sized slab
-	 * doesn't get initialized so it would not be possible. So, we need
-	 * to check size >= 256. It guarantees that all necessary small
-	 * sized slab is initialized in current slab initialization sequence.
-	 */
-	if (debug_pagealloc_enabled_static() && (flags & SLAB_POISON) &&
-		size >= 256 && cachep->object_size > cache_line_size()) {
-		if (size < PAGE_SIZE || size % PAGE_SIZE == 0) {
-			size_t tmp_size = ALIGN(size, PAGE_SIZE);
-
-			if (set_off_slab_cache(cachep, tmp_size, flags)) {
-				flags |= CFLGS_OFF_SLAB;
-				cachep->obj_offset += tmp_size - size;
-				size = tmp_size;
-				goto done;
-			}
-		}
-	}
-#endif
-
-	if (set_objfreelist_slab_cache(cachep, size, flags)) {
-		flags |= CFLGS_OBJFREELIST_SLAB;
-		goto done;
-	}
-
-	if (set_off_slab_cache(cachep, size, flags)) {
-		flags |= CFLGS_OFF_SLAB;
-		goto done;
-	}
-
-	if (set_on_slab_cache(cachep, size, flags))
-		goto done;
-
-	return -E2BIG;
-
-done:
-	cachep->freelist_size = cachep->num * sizeof(freelist_idx_t);
-	cachep->flags = flags;
-	cachep->allocflags = __GFP_COMP;
-	if (flags & SLAB_CACHE_DMA)
-		cachep->allocflags |= GFP_DMA;
-	if (flags & SLAB_CACHE_DMA32)
-		cachep->allocflags |= GFP_DMA32;
-	if (flags & SLAB_RECLAIM_ACCOUNT)
-		cachep->allocflags |= __GFP_RECLAIMABLE;
-	cachep->size = size;
-	cachep->reciprocal_buffer_size = reciprocal_value(size);
-
-#if DEBUG
-	/*
-	 * If we're going to use the generic kernel_map_pages()
-	 * poisoning, then it's going to smash the contents of
-	 * the redzone and userword anyhow, so switch them off.
-	 */
-	if (IS_ENABLED(CONFIG_PAGE_POISONING) &&
-		(cachep->flags & SLAB_POISON) &&
-		is_debug_pagealloc_cache(cachep))
-		cachep->flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
-#endif
-
-	err = setup_cpu_cache(cachep, gfp);
-	if (err) {
-		__kmem_cache_release(cachep);
-		return err;
-	}
-
-	return 0;
-}
-
-#if DEBUG
-static void check_irq_off(void)
-{
-	BUG_ON(!irqs_disabled());
-}
-
-static void check_irq_on(void)
-{
-	BUG_ON(irqs_disabled());
-}
-
-static void check_mutex_acquired(void)
-{
-	BUG_ON(!mutex_is_locked(&slab_mutex));
-}
-
-static void check_spinlock_acquired(struct kmem_cache *cachep)
-{
-#ifdef CONFIG_SMP
-	check_irq_off();
-	assert_raw_spin_locked(&get_node(cachep, numa_mem_id())->list_lock);
-#endif
-}
-
-static void check_spinlock_acquired_node(struct kmem_cache *cachep, int node)
-{
-#ifdef CONFIG_SMP
-	check_irq_off();
-	assert_raw_spin_locked(&get_node(cachep, node)->list_lock);
-#endif
-}
-
-#else
-#define check_irq_off()	do { } while(0)
-#define check_irq_on()	do { } while(0)
-#define check_mutex_acquired()	do { } while(0)
-#define check_spinlock_acquired(x) do { } while(0)
-#define check_spinlock_acquired_node(x, y) do { } while(0)
-#endif
-
-static void drain_array_locked(struct kmem_cache *cachep, struct array_cache *ac,
-				int node, bool free_all, struct list_head *list)
-{
-	int tofree;
-
-	if (!ac || !ac->avail)
-		return;
-
-	tofree = free_all ? ac->avail : (ac->limit + 4) / 5;
-	if (tofree > ac->avail)
-		tofree = (ac->avail + 1) / 2;
-
-	free_block(cachep, ac->entry, tofree, node, list);
-	ac->avail -= tofree;
-	memmove(ac->entry, &(ac->entry[tofree]), sizeof(void *) * ac->avail);
-}
-
-static void do_drain(void *arg)
-{
-	struct kmem_cache *cachep = arg;
-	struct array_cache *ac;
-	int node = numa_mem_id();
-	struct kmem_cache_node *n;
-	LIST_HEAD(list);
-
-	check_irq_off();
-	ac = cpu_cache_get(cachep);
-	n = get_node(cachep, node);
-	raw_spin_lock(&n->list_lock);
-	free_block(cachep, ac->entry, ac->avail, node, &list);
-	raw_spin_unlock(&n->list_lock);
-	ac->avail = 0;
-	slabs_destroy(cachep, &list);
-}
-
-static void drain_cpu_caches(struct kmem_cache *cachep)
-{
-	struct kmem_cache_node *n;
-	int node;
-	LIST_HEAD(list);
-
-	on_each_cpu(do_drain, cachep, 1);
-	check_irq_on();
-	for_each_kmem_cache_node(cachep, node, n)
-		if (n->alien)
-			drain_alien_cache(cachep, n->alien);
-
-	for_each_kmem_cache_node(cachep, node, n) {
-		raw_spin_lock_irq(&n->list_lock);
-		drain_array_locked(cachep, n->shared, node, true, &list);
-		raw_spin_unlock_irq(&n->list_lock);
-
-		slabs_destroy(cachep, &list);
-	}
-}
-
-/*
- * Remove slabs from the list of free slabs.
- * Specify the number of slabs to drain in tofree.
- *
- * Returns the actual number of slabs released.
- */
-static int drain_freelist(struct kmem_cache *cache,
-			struct kmem_cache_node *n, int tofree)
-{
-	struct list_head *p;
-	int nr_freed;
-	struct slab *slab;
-
-	nr_freed = 0;
-	while (nr_freed < tofree && !list_empty(&n->slabs_free)) {
-
-		raw_spin_lock_irq(&n->list_lock);
-		p = n->slabs_free.prev;
-		if (p == &n->slabs_free) {
-			raw_spin_unlock_irq(&n->list_lock);
-			goto out;
-		}
-
-		slab = list_entry(p, struct slab, slab_list);
-		list_del(&slab->slab_list);
-		n->free_slabs--;
-		n->total_slabs--;
-		/*
-		 * Safe to drop the lock. The slab is no longer linked
-		 * to the cache.
-		 */
-		n->free_objects -= cache->num;
-		raw_spin_unlock_irq(&n->list_lock);
-		slab_destroy(cache, slab);
-		nr_freed++;
-
-		cond_resched();
-	}
-out:
-	return nr_freed;
-}
-
-bool __kmem_cache_empty(struct kmem_cache *s)
-{
-	int node;
-	struct kmem_cache_node *n;
-
-	for_each_kmem_cache_node(s, node, n)
-		if (!list_empty(&n->slabs_full) ||
-		    !list_empty(&n->slabs_partial))
-			return false;
-	return true;
-}
-
-int __kmem_cache_shrink(struct kmem_cache *cachep)
-{
-	int ret = 0;
-	int node;
-	struct kmem_cache_node *n;
-
-	drain_cpu_caches(cachep);
-
-	check_irq_on();
-	for_each_kmem_cache_node(cachep, node, n) {
-		drain_freelist(cachep, n, INT_MAX);
-
-		ret += !list_empty(&n->slabs_full) ||
-			!list_empty(&n->slabs_partial);
-	}
-	return (ret ? 1 : 0);
-}
-
-int __kmem_cache_shutdown(struct kmem_cache *cachep)
-{
-	return __kmem_cache_shrink(cachep);
-}
-
-void __kmem_cache_release(struct kmem_cache *cachep)
-{
-	int i;
-	struct kmem_cache_node *n;
-
-	cache_random_seq_destroy(cachep);
-
-	free_percpu(cachep->cpu_cache);
-
-	/* NUMA: free the node structures */
-	for_each_kmem_cache_node(cachep, i, n) {
-		kfree(n->shared);
-		free_alien_cache(n->alien);
-		kfree(n);
-		cachep->node[i] = NULL;
-	}
-}
-
-/*
- * Get the memory for a slab management obj.
- *
- * For a slab cache when the slab descriptor is off-slab, the
- * slab descriptor can't come from the same cache which is being created,
- * Because if it is the case, that means we defer the creation of
- * the kmalloc_{dma,}_cache of size sizeof(slab descriptor) to this point.
- * And we eventually call down to __kmem_cache_create(), which
- * in turn looks up in the kmalloc_{dma,}_caches for the desired-size one.
- * This is a "chicken-and-egg" problem.
- *
- * So the off-slab slab descriptor shall come from the kmalloc_{dma,}_caches,
- * which are all initialized during kmem_cache_init().
- */
-static void *alloc_slabmgmt(struct kmem_cache *cachep,
-				   struct slab *slab, int colour_off,
-				   gfp_t local_flags, int nodeid)
-{
-	void *freelist;
-	void *addr = slab_address(slab);
-
-	slab->s_mem = addr + colour_off;
-	slab->active = 0;
-
-	if (OBJFREELIST_SLAB(cachep))
-		freelist = NULL;
-	else if (OFF_SLAB(cachep)) {
-		/* Slab management obj is off-slab. */
-		freelist = kmalloc_node(cachep->freelist_size,
-					      local_flags, nodeid);
-	} else {
-		/* We will use last bytes at the slab for freelist */
-		freelist = addr + (PAGE_SIZE << cachep->gfporder) -
-				cachep->freelist_size;
-	}
-
-	return freelist;
-}
-
-static inline freelist_idx_t get_free_obj(struct slab *slab, unsigned int idx)
-{
-	return ((freelist_idx_t *) slab->freelist)[idx];
-}
-
-static inline void set_free_obj(struct slab *slab,
-					unsigned int idx, freelist_idx_t val)
-{
-	((freelist_idx_t *)(slab->freelist))[idx] = val;
-}
-
-static void cache_init_objs_debug(struct kmem_cache *cachep, struct slab *slab)
-{
-#if DEBUG
-	int i;
-
-	for (i = 0; i < cachep->num; i++) {
-		void *objp = index_to_obj(cachep, slab, i);
-
-		if (cachep->flags & SLAB_STORE_USER)
-			*dbg_userword(cachep, objp) = NULL;
-
-		if (cachep->flags & SLAB_RED_ZONE) {
-			*dbg_redzone1(cachep, objp) = RED_INACTIVE;
-			*dbg_redzone2(cachep, objp) = RED_INACTIVE;
-		}
-		/*
-		 * Constructors are not allowed to allocate memory from the same
-		 * cache which they are a constructor for.  Otherwise, deadlock.
-		 * They must also be threaded.
-		 */
-		if (cachep->ctor && !(cachep->flags & SLAB_POISON)) {
-			kasan_unpoison_object_data(cachep,
-						   objp + obj_offset(cachep));
-			cachep->ctor(objp + obj_offset(cachep));
-			kasan_poison_object_data(
-				cachep, objp + obj_offset(cachep));
-		}
-
-		if (cachep->flags & SLAB_RED_ZONE) {
-			if (*dbg_redzone2(cachep, objp) != RED_INACTIVE)
-				slab_error(cachep, "constructor overwrote the end of an object");
-			if (*dbg_redzone1(cachep, objp) != RED_INACTIVE)
-				slab_error(cachep, "constructor overwrote the start of an object");
-		}
-		/* need to poison the objs? */
-		if (cachep->flags & SLAB_POISON) {
-			poison_obj(cachep, objp, POISON_FREE);
-			slab_kernel_map(cachep, objp, 0);
-		}
-	}
-#endif
-}
-
-#ifdef CONFIG_SLAB_FREELIST_RANDOM
-/* Hold information during a freelist initialization */
-struct freelist_init_state {
-	unsigned int pos;
-	unsigned int *list;
-	unsigned int count;
-};
-
-/*
- * Initialize the state based on the randomization method available.
- * return true if the pre-computed list is available, false otherwise.
- */
-static bool freelist_state_initialize(struct freelist_init_state *state,
-				struct kmem_cache *cachep,
-				unsigned int count)
-{
-	bool ret;
-	if (!cachep->random_seq) {
-		ret = false;
-	} else {
-		state->list = cachep->random_seq;
-		state->count = count;
-		state->pos = get_random_u32_below(count);
-		ret = true;
-	}
-	return ret;
-}
-
-/* Get the next entry on the list and randomize it using a random shift */
-static freelist_idx_t next_random_slot(struct freelist_init_state *state)
-{
-	if (state->pos >= state->count)
-		state->pos = 0;
-	return state->list[state->pos++];
-}
-
-/* Swap two freelist entries */
-static void swap_free_obj(struct slab *slab, unsigned int a, unsigned int b)
-{
-	swap(((freelist_idx_t *) slab->freelist)[a],
-		((freelist_idx_t *) slab->freelist)[b]);
-}
-
-/*
- * Shuffle the freelist initialization state based on pre-computed lists.
- * return true if the list was successfully shuffled, false otherwise.
- */
-static bool shuffle_freelist(struct kmem_cache *cachep, struct slab *slab)
-{
-	unsigned int objfreelist = 0, i, rand, count = cachep->num;
-	struct freelist_init_state state;
-	bool precomputed;
-
-	if (count < 2)
-		return false;
-
-	precomputed = freelist_state_initialize(&state, cachep, count);
-
-	/* Take a random entry as the objfreelist */
-	if (OBJFREELIST_SLAB(cachep)) {
-		if (!precomputed)
-			objfreelist = count - 1;
-		else
-			objfreelist = next_random_slot(&state);
-		slab->freelist = index_to_obj(cachep, slab, objfreelist) +
-						obj_offset(cachep);
-		count--;
-	}
-
-	/*
-	 * On early boot, generate the list dynamically.
-	 * Later use a pre-computed list for speed.
-	 */
-	if (!precomputed) {
-		for (i = 0; i < count; i++)
-			set_free_obj(slab, i, i);
-
-		/* Fisher-Yates shuffle */
-		for (i = count - 1; i > 0; i--) {
-			rand = get_random_u32_below(i + 1);
-			swap_free_obj(slab, i, rand);
-		}
-	} else {
-		for (i = 0; i < count; i++)
-			set_free_obj(slab, i, next_random_slot(&state));
-	}
-
-	if (OBJFREELIST_SLAB(cachep))
-		set_free_obj(slab, cachep->num - 1, objfreelist);
-
-	return true;
-}
-#else
-static inline bool shuffle_freelist(struct kmem_cache *cachep,
-				struct slab *slab)
-{
-	return false;
-}
-#endif /* CONFIG_SLAB_FREELIST_RANDOM */
-
-static void cache_init_objs(struct kmem_cache *cachep,
-			    struct slab *slab)
-{
-	int i;
-	void *objp;
-	bool shuffled;
-
-	cache_init_objs_debug(cachep, slab);
-
-	/* Try to randomize the freelist if enabled */
-	shuffled = shuffle_freelist(cachep, slab);
-
-	if (!shuffled && OBJFREELIST_SLAB(cachep)) {
-		slab->freelist = index_to_obj(cachep, slab, cachep->num - 1) +
-						obj_offset(cachep);
-	}
-
-	for (i = 0; i < cachep->num; i++) {
-		objp = index_to_obj(cachep, slab, i);
-		objp = kasan_init_slab_obj(cachep, objp);
-
-		/* constructor could break poison info */
-		if (DEBUG == 0 && cachep->ctor) {
-			kasan_unpoison_object_data(cachep, objp);
-			cachep->ctor(objp);
-			kasan_poison_object_data(cachep, objp);
-		}
-
-		if (!shuffled)
-			set_free_obj(slab, i, i);
-	}
-}
-
-static void *slab_get_obj(struct kmem_cache *cachep, struct slab *slab)
-{
-	void *objp;
-
-	objp = index_to_obj(cachep, slab, get_free_obj(slab, slab->active));
-	slab->active++;
-
-	return objp;
-}
-
-static void slab_put_obj(struct kmem_cache *cachep,
-			struct slab *slab, void *objp)
-{
-	unsigned int objnr = obj_to_index(cachep, slab, objp);
-#if DEBUG
-	unsigned int i;
-
-	/* Verify double free bug */
-	for (i = slab->active; i < cachep->num; i++) {
-		if (get_free_obj(slab, i) == objnr) {
-			pr_err("slab: double free detected in cache '%s', objp %px\n",
-			       cachep->name, objp);
-			BUG();
-		}
-	}
-#endif
-	slab->active--;
-	if (!slab->freelist)
-		slab->freelist = objp + obj_offset(cachep);
-
-	set_free_obj(slab, slab->active, objnr);
-}
-
-/*
- * Grow (by 1) the number of slabs within a cache.  This is called by
- * kmem_cache_alloc() when there are no active objs left in a cache.
- */
-static struct slab *cache_grow_begin(struct kmem_cache *cachep,
-				gfp_t flags, int nodeid)
-{
-	void *freelist;
-	size_t offset;
-	gfp_t local_flags;
-	int slab_node;
-	struct kmem_cache_node *n;
-	struct slab *slab;
-
-	/*
-	 * Be lazy and only check for valid flags here,  keeping it out of the
-	 * critical path in kmem_cache_alloc().
-	 */
-	if (unlikely(flags & GFP_SLAB_BUG_MASK))
-		flags = kmalloc_fix_flags(flags);
-
-	WARN_ON_ONCE(cachep->ctor && (flags & __GFP_ZERO));
-	local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK);
-
-	check_irq_off();
-	if (gfpflags_allow_blocking(local_flags))
-		local_irq_enable();
-
-	/*
-	 * Get mem for the objs.  Attempt to allocate a physical page from
-	 * 'nodeid'.
-	 */
-	slab = kmem_getpages(cachep, local_flags, nodeid);
-	if (!slab)
-		goto failed;
-
-	slab_node = slab_nid(slab);
-	n = get_node(cachep, slab_node);
-
-	/* Get colour for the slab, and cal the next value. */
-	n->colour_next++;
-	if (n->colour_next >= cachep->colour)
-		n->colour_next = 0;
-
-	offset = n->colour_next;
-	if (offset >= cachep->colour)
-		offset = 0;
-
-	offset *= cachep->colour_off;
-
-	/*
-	 * Call kasan_poison_slab() before calling alloc_slabmgmt(), so
-	 * page_address() in the latter returns a non-tagged pointer,
-	 * as it should be for slab pages.
-	 */
-	kasan_poison_slab(slab);
-
-	/* Get slab management. */
-	freelist = alloc_slabmgmt(cachep, slab, offset,
-			local_flags & ~GFP_CONSTRAINT_MASK, slab_node);
-	if (OFF_SLAB(cachep) && !freelist)
-		goto opps1;
-
-	slab->slab_cache = cachep;
-	slab->freelist = freelist;
-
-	cache_init_objs(cachep, slab);
-
-	if (gfpflags_allow_blocking(local_flags))
-		local_irq_disable();
-
-	return slab;
-
-opps1:
-	kmem_freepages(cachep, slab);
-failed:
-	if (gfpflags_allow_blocking(local_flags))
-		local_irq_disable();
-	return NULL;
-}
-
-static void cache_grow_end(struct kmem_cache *cachep, struct slab *slab)
-{
-	struct kmem_cache_node *n;
-	void *list = NULL;
-
-	check_irq_off();
-
-	if (!slab)
-		return;
-
-	INIT_LIST_HEAD(&slab->slab_list);
-	n = get_node(cachep, slab_nid(slab));
-
-	raw_spin_lock(&n->list_lock);
-	n->total_slabs++;
-	if (!slab->active) {
-		list_add_tail(&slab->slab_list, &n->slabs_free);
-		n->free_slabs++;
-	} else
-		fixup_slab_list(cachep, n, slab, &list);
-
-	STATS_INC_GROWN(cachep);
-	n->free_objects += cachep->num - slab->active;
-	raw_spin_unlock(&n->list_lock);
-
-	fixup_objfreelist_debug(cachep, &list);
-}
-
-#if DEBUG
-
-/*
- * Perform extra freeing checks:
- * - detect bad pointers.
- * - POISON/RED_ZONE checking
- */
-static void kfree_debugcheck(const void *objp)
-{
-	if (!virt_addr_valid(objp)) {
-		pr_err("kfree_debugcheck: out of range ptr %lxh\n",
-		       (unsigned long)objp);
-		BUG();
-	}
-}
-
-static inline void verify_redzone_free(struct kmem_cache *cache, void *obj)
-{
-	unsigned long long redzone1, redzone2;
-
-	redzone1 = *dbg_redzone1(cache, obj);
-	redzone2 = *dbg_redzone2(cache, obj);
-
-	/*
-	 * Redzone is ok.
-	 */
-	if (redzone1 == RED_ACTIVE && redzone2 == RED_ACTIVE)
-		return;
-
-	if (redzone1 == RED_INACTIVE && redzone2 == RED_INACTIVE)
-		slab_error(cache, "double free detected");
-	else
-		slab_error(cache, "memory outside object was overwritten");
-
-	pr_err("%px: redzone 1:0x%llx, redzone 2:0x%llx\n",
-	       obj, redzone1, redzone2);
-}
-
-static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
-				   unsigned long caller)
-{
-	unsigned int objnr;
-	struct slab *slab;
-
-	BUG_ON(virt_to_cache(objp) != cachep);
-
-	objp -= obj_offset(cachep);
-	kfree_debugcheck(objp);
-	slab = virt_to_slab(objp);
-
-	if (cachep->flags & SLAB_RED_ZONE) {
-		verify_redzone_free(cachep, objp);
-		*dbg_redzone1(cachep, objp) = RED_INACTIVE;
-		*dbg_redzone2(cachep, objp) = RED_INACTIVE;
-	}
-	if (cachep->flags & SLAB_STORE_USER)
-		*dbg_userword(cachep, objp) = (void *)caller;
-
-	objnr = obj_to_index(cachep, slab, objp);
-
-	BUG_ON(objnr >= cachep->num);
-	BUG_ON(objp != index_to_obj(cachep, slab, objnr));
-
-	if (cachep->flags & SLAB_POISON) {
-		poison_obj(cachep, objp, POISON_FREE);
-		slab_kernel_map(cachep, objp, 0);
-	}
-	return objp;
-}
-
-#else
-#define kfree_debugcheck(x) do { } while(0)
-#define cache_free_debugcheck(x, objp, z) (objp)
-#endif
-
-static inline void fixup_objfreelist_debug(struct kmem_cache *cachep,
-						void **list)
-{
-#if DEBUG
-	void *next = *list;
-	void *objp;
-
-	while (next) {
-		objp = next - obj_offset(cachep);
-		next = *(void **)next;
-		poison_obj(cachep, objp, POISON_FREE);
-	}
-#endif
-}
-
-static inline void fixup_slab_list(struct kmem_cache *cachep,
-				struct kmem_cache_node *n, struct slab *slab,
-				void **list)
-{
-	/* move slabp to correct slabp list: */
-	list_del(&slab->slab_list);
-	if (slab->active == cachep->num) {
-		list_add(&slab->slab_list, &n->slabs_full);
-		if (OBJFREELIST_SLAB(cachep)) {
-#if DEBUG
-			/* Poisoning will be done without holding the lock */
-			if (cachep->flags & SLAB_POISON) {
-				void **objp = slab->freelist;
-
-				*objp = *list;
-				*list = objp;
-			}
-#endif
-			slab->freelist = NULL;
-		}
-	} else
-		list_add(&slab->slab_list, &n->slabs_partial);
-}
-
-/* Try to find non-pfmemalloc slab if needed */
-static noinline struct slab *get_valid_first_slab(struct kmem_cache_node *n,
-					struct slab *slab, bool pfmemalloc)
-{
-	if (!slab)
-		return NULL;
-
-	if (pfmemalloc)
-		return slab;
-
-	if (!slab_test_pfmemalloc(slab))
-		return slab;
-
-	/* No need to keep pfmemalloc slab if we have enough free objects */
-	if (n->free_objects > n->free_limit) {
-		slab_clear_pfmemalloc(slab);
-		return slab;
-	}
-
-	/* Move pfmemalloc slab to the end of list to speed up next search */
-	list_del(&slab->slab_list);
-	if (!slab->active) {
-		list_add_tail(&slab->slab_list, &n->slabs_free);
-		n->free_slabs++;
-	} else
-		list_add_tail(&slab->slab_list, &n->slabs_partial);
-
-	list_for_each_entry(slab, &n->slabs_partial, slab_list) {
-		if (!slab_test_pfmemalloc(slab))
-			return slab;
-	}
-
-	n->free_touched = 1;
-	list_for_each_entry(slab, &n->slabs_free, slab_list) {
-		if (!slab_test_pfmemalloc(slab)) {
-			n->free_slabs--;
-			return slab;
-		}
-	}
-
-	return NULL;
-}
-
-static struct slab *get_first_slab(struct kmem_cache_node *n, bool pfmemalloc)
-{
-	struct slab *slab;
-
-	assert_raw_spin_locked(&n->list_lock);
-	slab = list_first_entry_or_null(&n->slabs_partial, struct slab,
-					slab_list);
-	if (!slab) {
-		n->free_touched = 1;
-		slab = list_first_entry_or_null(&n->slabs_free, struct slab,
-						slab_list);
-		if (slab)
-			n->free_slabs--;
-	}
-
-	if (sk_memalloc_socks())
-		slab = get_valid_first_slab(n, slab, pfmemalloc);
-
-	return slab;
-}
-
-static noinline void *cache_alloc_pfmemalloc(struct kmem_cache *cachep,
-				struct kmem_cache_node *n, gfp_t flags)
-{
-	struct slab *slab;
-	void *obj;
-	void *list = NULL;
-
-	if (!gfp_pfmemalloc_allowed(flags))
-		return NULL;
-
-	raw_spin_lock(&n->list_lock);
-	slab = get_first_slab(n, true);
-	if (!slab) {
-		raw_spin_unlock(&n->list_lock);
-		return NULL;
-	}
-
-	obj = slab_get_obj(cachep, slab);
-	n->free_objects--;
-
-	fixup_slab_list(cachep, n, slab, &list);
-
-	raw_spin_unlock(&n->list_lock);
-	fixup_objfreelist_debug(cachep, &list);
-
-	return obj;
-}
-
-/*
- * Slab list should be fixed up by fixup_slab_list() for existing slab
- * or cache_grow_end() for new slab
- */
-static __always_inline int alloc_block(struct kmem_cache *cachep,
-		struct array_cache *ac, struct slab *slab, int batchcount)
-{
-	/*
-	 * There must be at least one object available for
-	 * allocation.
-	 */
-	BUG_ON(slab->active >= cachep->num);
-
-	while (slab->active < cachep->num && batchcount--) {
-		STATS_INC_ALLOCED(cachep);
-		STATS_INC_ACTIVE(cachep);
-		STATS_SET_HIGH(cachep);
-
-		ac->entry[ac->avail++] = slab_get_obj(cachep, slab);
-	}
-
-	return batchcount;
-}
-
-static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags)
-{
-	int batchcount;
-	struct kmem_cache_node *n;
-	struct array_cache *ac, *shared;
-	int node;
-	void *list = NULL;
-	struct slab *slab;
-
-	check_irq_off();
-	node = numa_mem_id();
-
-	ac = cpu_cache_get(cachep);
-	batchcount = ac->batchcount;
-	if (!ac->touched && batchcount > BATCHREFILL_LIMIT) {
-		/*
-		 * If there was little recent activity on this cache, then
-		 * perform only a partial refill.  Otherwise we could generate
-		 * refill bouncing.
-		 */
-		batchcount = BATCHREFILL_LIMIT;
-	}
-	n = get_node(cachep, node);
-
-	BUG_ON(ac->avail > 0 || !n);
-	shared = READ_ONCE(n->shared);
-	if (!n->free_objects && (!shared || !shared->avail))
-		goto direct_grow;
-
-	raw_spin_lock(&n->list_lock);
-	shared = READ_ONCE(n->shared);
-
-	/* See if we can refill from the shared array */
-	if (shared && transfer_objects(ac, shared, batchcount)) {
-		shared->touched = 1;
-		goto alloc_done;
-	}
-
-	while (batchcount > 0) {
-		/* Get slab alloc is to come from. */
-		slab = get_first_slab(n, false);
-		if (!slab)
-			goto must_grow;
-
-		check_spinlock_acquired(cachep);
-
-		batchcount = alloc_block(cachep, ac, slab, batchcount);
-		fixup_slab_list(cachep, n, slab, &list);
-	}
-
-must_grow:
-	n->free_objects -= ac->avail;
-alloc_done:
-	raw_spin_unlock(&n->list_lock);
-	fixup_objfreelist_debug(cachep, &list);
-
-direct_grow:
-	if (unlikely(!ac->avail)) {
-		/* Check if we can use obj in pfmemalloc slab */
-		if (sk_memalloc_socks()) {
-			void *obj = cache_alloc_pfmemalloc(cachep, n, flags);
-
-			if (obj)
-				return obj;
-		}
-
-		slab = cache_grow_begin(cachep, gfp_exact_node(flags), node);
-
-		/*
-		 * cache_grow_begin() can reenable interrupts,
-		 * then ac could change.
-		 */
-		ac = cpu_cache_get(cachep);
-		if (!ac->avail && slab)
-			alloc_block(cachep, ac, slab, batchcount);
-		cache_grow_end(cachep, slab);
-
-		if (!ac->avail)
-			return NULL;
-	}
-	ac->touched = 1;
-
-	return ac->entry[--ac->avail];
-}
-
-#if DEBUG
-static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
-				gfp_t flags, void *objp, unsigned long caller)
-{
-	WARN_ON_ONCE(cachep->ctor && (flags & __GFP_ZERO));
-	if (!objp || is_kfence_address(objp))
-		return objp;
-	if (cachep->flags & SLAB_POISON) {
-		check_poison_obj(cachep, objp);
-		slab_kernel_map(cachep, objp, 1);
-		poison_obj(cachep, objp, POISON_INUSE);
-	}
-	if (cachep->flags & SLAB_STORE_USER)
-		*dbg_userword(cachep, objp) = (void *)caller;
-
-	if (cachep->flags & SLAB_RED_ZONE) {
-		if (*dbg_redzone1(cachep, objp) != RED_INACTIVE ||
-				*dbg_redzone2(cachep, objp) != RED_INACTIVE) {
-			slab_error(cachep, "double free, or memory outside object was overwritten");
-			pr_err("%px: redzone 1:0x%llx, redzone 2:0x%llx\n",
-			       objp, *dbg_redzone1(cachep, objp),
-			       *dbg_redzone2(cachep, objp));
-		}
-		*dbg_redzone1(cachep, objp) = RED_ACTIVE;
-		*dbg_redzone2(cachep, objp) = RED_ACTIVE;
-	}
-
-	objp += obj_offset(cachep);
-	if (cachep->ctor && cachep->flags & SLAB_POISON)
-		cachep->ctor(objp);
-	if ((unsigned long)objp & (arch_slab_minalign() - 1)) {
-		pr_err("0x%px: not aligned to arch_slab_minalign()=%u\n", objp,
-		       arch_slab_minalign());
-	}
-	return objp;
-}
-#else
-#define cache_alloc_debugcheck_after(a, b, objp, d) (objp)
-#endif
-
-static inline void *____cache_alloc(struct kmem_cache *cachep, gfp_t flags)
-{
-	void *objp;
-	struct array_cache *ac;
-
-	check_irq_off();
-
-	ac = cpu_cache_get(cachep);
-	if (likely(ac->avail)) {
-		ac->touched = 1;
-		objp = ac->entry[--ac->avail];
-
-		STATS_INC_ALLOCHIT(cachep);
-		goto out;
-	}
-
-	STATS_INC_ALLOCMISS(cachep);
-	objp = cache_alloc_refill(cachep, flags);
-	/*
-	 * the 'ac' may be updated by cache_alloc_refill(),
-	 * and kmemleak_erase() requires its correct value.
-	 */
-	ac = cpu_cache_get(cachep);
-
-out:
-	/*
-	 * To avoid a false negative, if an object that is in one of the
-	 * per-CPU caches is leaked, we need to make sure kmemleak doesn't
-	 * treat the array pointers as a reference to the object.
-	 */
-	if (objp)
-		kmemleak_erase(&ac->entry[ac->avail]);
-	return objp;
-}
-
-#ifdef CONFIG_NUMA
-static void *____cache_alloc_node(struct kmem_cache *, gfp_t, int);
-
-/*
- * Try allocating on another node if PFA_SPREAD_SLAB is a mempolicy is set.
- *
- * If we are in_interrupt, then process context, including cpusets and
- * mempolicy, may not apply and should not be used for allocation policy.
- */
-static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags)
-{
-	int nid_alloc, nid_here;
-
-	if (in_interrupt() || (flags & __GFP_THISNODE))
-		return NULL;
-	nid_alloc = nid_here = numa_mem_id();
-	if (cpuset_do_slab_mem_spread() && (cachep->flags & SLAB_MEM_SPREAD))
-		nid_alloc = cpuset_slab_spread_node();
-	else if (current->mempolicy)
-		nid_alloc = mempolicy_slab_node();
-	if (nid_alloc != nid_here)
-		return ____cache_alloc_node(cachep, flags, nid_alloc);
-	return NULL;
-}
-
-/*
- * Fallback function if there was no memory available and no objects on a
- * certain node and fall back is permitted. First we scan all the
- * available node for available objects. If that fails then we
- * perform an allocation without specifying a node. This allows the page
- * allocator to do its reclaim / fallback magic. We then insert the
- * slab into the proper nodelist and then allocate from it.
- */
-static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags)
-{
-	struct zonelist *zonelist;
-	struct zoneref *z;
-	struct zone *zone;
-	enum zone_type highest_zoneidx = gfp_zone(flags);
-	void *obj = NULL;
-	struct slab *slab;
-	int nid;
-	unsigned int cpuset_mems_cookie;
-
-	if (flags & __GFP_THISNODE)
-		return NULL;
-
-retry_cpuset:
-	cpuset_mems_cookie = read_mems_allowed_begin();
-	zonelist = node_zonelist(mempolicy_slab_node(), flags);
-
-retry:
-	/*
-	 * Look through allowed nodes for objects available
-	 * from existing per node queues.
-	 */
-	for_each_zone_zonelist(zone, z, zonelist, highest_zoneidx) {
-		nid = zone_to_nid(zone);
-
-		if (cpuset_zone_allowed(zone, flags) &&
-			get_node(cache, nid) &&
-			get_node(cache, nid)->free_objects) {
-				obj = ____cache_alloc_node(cache,
-					gfp_exact_node(flags), nid);
-				if (obj)
-					break;
-		}
-	}
-
-	if (!obj) {
-		/*
-		 * This allocation will be performed within the constraints
-		 * of the current cpuset / memory policy requirements.
-		 * We may trigger various forms of reclaim on the allowed
-		 * set and go into memory reserves if necessary.
-		 */
-		slab = cache_grow_begin(cache, flags, numa_mem_id());
-		cache_grow_end(cache, slab);
-		if (slab) {
-			nid = slab_nid(slab);
-			obj = ____cache_alloc_node(cache,
-				gfp_exact_node(flags), nid);
-
-			/*
-			 * Another processor may allocate the objects in
-			 * the slab since we are not holding any locks.
-			 */
-			if (!obj)
-				goto retry;
-		}
-	}
-
-	if (unlikely(!obj && read_mems_allowed_retry(cpuset_mems_cookie)))
-		goto retry_cpuset;
-	return obj;
-}
-
-/*
- * An interface to enable slab creation on nodeid
- */
-static void *____cache_alloc_node(struct kmem_cache *cachep, gfp_t flags,
-				int nodeid)
-{
-	struct slab *slab;
-	struct kmem_cache_node *n;
-	void *obj = NULL;
-	void *list = NULL;
-
-	VM_BUG_ON(nodeid < 0 || nodeid >= MAX_NUMNODES);
-	n = get_node(cachep, nodeid);
-	BUG_ON(!n);
-
-	check_irq_off();
-	raw_spin_lock(&n->list_lock);
-	slab = get_first_slab(n, false);
-	if (!slab)
-		goto must_grow;
-
-	check_spinlock_acquired_node(cachep, nodeid);
-
-	STATS_INC_NODEALLOCS(cachep);
-	STATS_INC_ACTIVE(cachep);
-	STATS_SET_HIGH(cachep);
-
-	BUG_ON(slab->active == cachep->num);
-
-	obj = slab_get_obj(cachep, slab);
-	n->free_objects--;
-
-	fixup_slab_list(cachep, n, slab, &list);
-
-	raw_spin_unlock(&n->list_lock);
-	fixup_objfreelist_debug(cachep, &list);
-	return obj;
-
-must_grow:
-	raw_spin_unlock(&n->list_lock);
-	slab = cache_grow_begin(cachep, gfp_exact_node(flags), nodeid);
-	if (slab) {
-		/* This slab isn't counted yet so don't update free_objects */
-		obj = slab_get_obj(cachep, slab);
-	}
-	cache_grow_end(cachep, slab);
-
-	return obj ? obj : fallback_alloc(cachep, flags);
-}
-
-static __always_inline void *
-__do_cache_alloc(struct kmem_cache *cachep, gfp_t flags, int nodeid)
-{
-	void *objp = NULL;
-	int slab_node = numa_mem_id();
-
-	if (nodeid == NUMA_NO_NODE) {
-		if (current->mempolicy || cpuset_do_slab_mem_spread()) {
-			objp = alternate_node_alloc(cachep, flags);
-			if (objp)
-				goto out;
-		}
-		/*
-		 * Use the locally cached objects if possible.
-		 * However ____cache_alloc does not allow fallback
-		 * to other nodes. It may fail while we still have
-		 * objects on other nodes available.
-		 */
-		objp = ____cache_alloc(cachep, flags);
-		nodeid = slab_node;
-	} else if (nodeid == slab_node) {
-		objp = ____cache_alloc(cachep, flags);
-	} else if (!get_node(cachep, nodeid)) {
-		/* Node not bootstrapped yet */
-		objp = fallback_alloc(cachep, flags);
-		goto out;
-	}
-
-	/*
-	 * We may just have run out of memory on the local node.
-	 * ____cache_alloc_node() knows how to locate memory on other nodes
-	 */
-	if (!objp)
-		objp = ____cache_alloc_node(cachep, flags, nodeid);
-out:
-	return objp;
-}
-#else
-
-static __always_inline void *
-__do_cache_alloc(struct kmem_cache *cachep, gfp_t flags, int nodeid __maybe_unused)
-{
-	return ____cache_alloc(cachep, flags);
-}
-
-#endif /* CONFIG_NUMA */
-
-static __always_inline void *
-slab_alloc_node(struct kmem_cache *cachep, struct list_lru *lru, gfp_t flags,
-		int nodeid, size_t orig_size, unsigned long caller)
-{
-	unsigned long save_flags;
-	void *objp;
-	struct obj_cgroup *objcg = NULL;
-	bool init = false;
-
-	flags &= gfp_allowed_mask;
-	cachep = slab_pre_alloc_hook(cachep, lru, &objcg, 1, flags);
-	if (unlikely(!cachep))
-		return NULL;
-
-	objp = kfence_alloc(cachep, orig_size, flags);
-	if (unlikely(objp))
-		goto out;
-
-	local_irq_save(save_flags);
-	objp = __do_cache_alloc(cachep, flags, nodeid);
-	local_irq_restore(save_flags);
-	objp = cache_alloc_debugcheck_after(cachep, flags, objp, caller);
-	prefetchw(objp);
-	init = slab_want_init_on_alloc(flags, cachep);
-
-out:
-	slab_post_alloc_hook(cachep, objcg, flags, 1, &objp, init,
-				cachep->object_size);
-	return objp;
-}
-
-static __always_inline void *
-slab_alloc(struct kmem_cache *cachep, struct list_lru *lru, gfp_t flags,
-	   size_t orig_size, unsigned long caller)
-{
-	return slab_alloc_node(cachep, lru, flags, NUMA_NO_NODE, orig_size,
-			       caller);
-}
-
-/*
- * Caller needs to acquire correct kmem_cache_node's list_lock
- * @list: List of detached free slabs should be freed by caller
- */
-static void free_block(struct kmem_cache *cachep, void **objpp,
-			int nr_objects, int node, struct list_head *list)
-{
-	int i;
-	struct kmem_cache_node *n = get_node(cachep, node);
-	struct slab *slab;
-
-	n->free_objects += nr_objects;
-
-	for (i = 0; i < nr_objects; i++) {
-		void *objp;
-		struct slab *slab;
-
-		objp = objpp[i];
-
-		slab = virt_to_slab(objp);
-		list_del(&slab->slab_list);
-		check_spinlock_acquired_node(cachep, node);
-		slab_put_obj(cachep, slab, objp);
-		STATS_DEC_ACTIVE(cachep);
-
-		/* fixup slab chains */
-		if (slab->active == 0) {
-			list_add(&slab->slab_list, &n->slabs_free);
-			n->free_slabs++;
-		} else {
-			/* Unconditionally move a slab to the end of the
-			 * partial list on free - maximum time for the
-			 * other objects to be freed, too.
-			 */
-			list_add_tail(&slab->slab_list, &n->slabs_partial);
-		}
-	}
-
-	while (n->free_objects > n->free_limit && !list_empty(&n->slabs_free)) {
-		n->free_objects -= cachep->num;
-
-		slab = list_last_entry(&n->slabs_free, struct slab, slab_list);
-		list_move(&slab->slab_list, list);
-		n->free_slabs--;
-		n->total_slabs--;
-	}
-}
-
-static void cache_flusharray(struct kmem_cache *cachep, struct array_cache *ac)
-{
-	int batchcount;
-	struct kmem_cache_node *n;
-	int node = numa_mem_id();
-	LIST_HEAD(list);
-
-	batchcount = ac->batchcount;
-
-	check_irq_off();
-	n = get_node(cachep, node);
-	raw_spin_lock(&n->list_lock);
-	if (n->shared) {
-		struct array_cache *shared_array = n->shared;
-		int max = shared_array->limit - shared_array->avail;
-		if (max) {
-			if (batchcount > max)
-				batchcount = max;
-			memcpy(&(shared_array->entry[shared_array->avail]),
-			       ac->entry, sizeof(void *) * batchcount);
-			shared_array->avail += batchcount;
-			goto free_done;
-		}
-	}
-
-	free_block(cachep, ac->entry, batchcount, node, &list);
-free_done:
-#if STATS
-	{
-		int i = 0;
-		struct slab *slab;
-
-		list_for_each_entry(slab, &n->slabs_free, slab_list) {
-			BUG_ON(slab->active);
-
-			i++;
-		}
-		STATS_SET_FREEABLE(cachep, i);
-	}
-#endif
-	raw_spin_unlock(&n->list_lock);
-	ac->avail -= batchcount;
-	memmove(ac->entry, &(ac->entry[batchcount]), sizeof(void *)*ac->avail);
-	slabs_destroy(cachep, &list);
-}
-
-/*
- * Release an obj back to its cache. If the obj has a constructed state, it must
- * be in this state _before_ it is released.  Called with disabled ints.
- */
-static __always_inline void __cache_free(struct kmem_cache *cachep, void *objp,
-					 unsigned long caller)
-{
-	bool init;
-
-	memcg_slab_free_hook(cachep, virt_to_slab(objp), &objp, 1);
-
-	if (is_kfence_address(objp)) {
-		kmemleak_free_recursive(objp, cachep->flags);
-		__kfence_free(objp);
-		return;
-	}
-
-	/*
-	 * As memory initialization might be integrated into KASAN,
-	 * kasan_slab_free and initialization memset must be
-	 * kept together to avoid discrepancies in behavior.
-	 */
-	init = slab_want_init_on_free(cachep);
-	if (init && !kasan_has_integrated_init())
-		memset(objp, 0, cachep->object_size);
-	/* KASAN might put objp into memory quarantine, delaying its reuse. */
-	if (kasan_slab_free(cachep, objp, init))
-		return;
-
-	/* Use KCSAN to help debug racy use-after-free. */
-	if (!(cachep->flags & SLAB_TYPESAFE_BY_RCU))
-		__kcsan_check_access(objp, cachep->object_size,
-				     KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ASSERT);
-
-	___cache_free(cachep, objp, caller);
-}
-
-void ___cache_free(struct kmem_cache *cachep, void *objp,
-		unsigned long caller)
-{
-	struct array_cache *ac = cpu_cache_get(cachep);
-
-	check_irq_off();
-	kmemleak_free_recursive(objp, cachep->flags);
-	objp = cache_free_debugcheck(cachep, objp, caller);
-
-	/*
-	 * Skip calling cache_free_alien() when the platform is not numa.
-	 * This will avoid cache misses that happen while accessing slabp (which
-	 * is per page memory  reference) to get nodeid. Instead use a global
-	 * variable to skip the call, which is mostly likely to be present in
-	 * the cache.
-	 */
-	if (nr_online_nodes > 1 && cache_free_alien(cachep, objp))
-		return;
-
-	if (ac->avail < ac->limit) {
-		STATS_INC_FREEHIT(cachep);
-	} else {
-		STATS_INC_FREEMISS(cachep);
-		cache_flusharray(cachep, ac);
-	}
-
-	if (sk_memalloc_socks()) {
-		struct slab *slab = virt_to_slab(objp);
-
-		if (unlikely(slab_test_pfmemalloc(slab))) {
-			cache_free_pfmemalloc(cachep, slab, objp);
-			return;
-		}
-	}
-
-	__free_one(ac, objp);
-}
-
-static __always_inline
-void *__kmem_cache_alloc_lru(struct kmem_cache *cachep, struct list_lru *lru,
-			     gfp_t flags)
-{
-	void *ret = slab_alloc(cachep, lru, flags, cachep->object_size, _RET_IP_);
-
-	trace_kmem_cache_alloc(_RET_IP_, ret, cachep, flags, NUMA_NO_NODE);
-
-	return ret;
-}
-
-void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags)
-{
-	return __kmem_cache_alloc_lru(cachep, NULL, flags);
-}
-EXPORT_SYMBOL(kmem_cache_alloc);
-
-void *kmem_cache_alloc_lru(struct kmem_cache *cachep, struct list_lru *lru,
-			   gfp_t flags)
-{
-	return __kmem_cache_alloc_lru(cachep, lru, flags);
-}
-EXPORT_SYMBOL(kmem_cache_alloc_lru);
-
-static __always_inline void
-cache_alloc_debugcheck_after_bulk(struct kmem_cache *s, gfp_t flags,
-				  size_t size, void **p, unsigned long caller)
-{
-	size_t i;
-
-	for (i = 0; i < size; i++)
-		p[i] = cache_alloc_debugcheck_after(s, flags, p[i], caller);
-}
-
-int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
-			  void **p)
-{
-	struct obj_cgroup *objcg = NULL;
-	unsigned long irqflags;
-	size_t i;
-
-	s = slab_pre_alloc_hook(s, NULL, &objcg, size, flags);
-	if (!s)
-		return 0;
-
-	local_irq_save(irqflags);
-	for (i = 0; i < size; i++) {
-		void *objp = kfence_alloc(s, s->object_size, flags) ?:
-			     __do_cache_alloc(s, flags, NUMA_NO_NODE);
-
-		if (unlikely(!objp))
-			goto error;
-		p[i] = objp;
-	}
-	local_irq_restore(irqflags);
-
-	cache_alloc_debugcheck_after_bulk(s, flags, size, p, _RET_IP_);
-
-	/*
-	 * memcg and kmem_cache debug support and memory initialization.
-	 * Done outside of the IRQ disabled section.
-	 */
-	slab_post_alloc_hook(s, objcg, flags, size, p,
-			slab_want_init_on_alloc(flags, s), s->object_size);
-	/* FIXME: Trace call missing. Christoph would like a bulk variant */
-	return size;
-error:
-	local_irq_restore(irqflags);
-	cache_alloc_debugcheck_after_bulk(s, flags, i, p, _RET_IP_);
-	slab_post_alloc_hook(s, objcg, flags, i, p, false, s->object_size);
-	kmem_cache_free_bulk(s, i, p);
-	return 0;
-}
-EXPORT_SYMBOL(kmem_cache_alloc_bulk);
-
-void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid)
-{
-	void *ret = slab_alloc_node(cachep, NULL, flags, nodeid, cachep->object_size, _RET_IP_);
-
-	trace_kmem_cache_alloc(_RET_IP_, ret, cachep, flags, nodeid);
-
-	return ret;
-}
-EXPORT_SYMBOL(kmem_cache_alloc_node);
-
-void *__kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags,
-			     int nodeid, size_t orig_size,
-			     unsigned long caller)
-{
-	return slab_alloc_node(cachep, NULL, flags, nodeid,
-			       orig_size, caller);
-}
-
-#ifdef CONFIG_PRINTK
-void __kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab)
-{
-	struct kmem_cache *cachep;
-	unsigned int objnr;
-	void *objp;
-
-	kpp->kp_ptr = object;
-	kpp->kp_slab = slab;
-	cachep = slab->slab_cache;
-	kpp->kp_slab_cache = cachep;
-	objp = object - obj_offset(cachep);
-	kpp->kp_data_offset = obj_offset(cachep);
-	slab = virt_to_slab(objp);
-	objnr = obj_to_index(cachep, slab, objp);
-	objp = index_to_obj(cachep, slab, objnr);
-	kpp->kp_objp = objp;
-	if (DEBUG && cachep->flags & SLAB_STORE_USER)
-		kpp->kp_ret = *dbg_userword(cachep, objp);
-}
-#endif
-
-static __always_inline
-void __do_kmem_cache_free(struct kmem_cache *cachep, void *objp,
-			  unsigned long caller)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	debug_check_no_locks_freed(objp, cachep->object_size);
-	if (!(cachep->flags & SLAB_DEBUG_OBJECTS))
-		debug_check_no_obj_freed(objp, cachep->object_size);
-	__cache_free(cachep, objp, caller);
-	local_irq_restore(flags);
-}
-
-void __kmem_cache_free(struct kmem_cache *cachep, void *objp,
-		       unsigned long caller)
-{
-	__do_kmem_cache_free(cachep, objp, caller);
-}
-
-void kmem_cache_free(struct kmem_cache *cachep, void *objp)
-{
-	cachep = cache_from_obj(cachep, objp);
-	if (!cachep)
-		return;
-
-	trace_kmem_cache_free(_RET_IP_, objp, cachep);
-	__do_kmem_cache_free(cachep, objp, _RET_IP_);
-}
-EXPORT_SYMBOL(kmem_cache_free);
-
-void kmem_cache_free_bulk(struct kmem_cache *orig_s, size_t size, void **p)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	for (int i = 0; i < size; i++) {
-		void *objp = p[i];
-		struct kmem_cache *s;
-
-		if (!orig_s) {
-			struct folio *folio = virt_to_folio(objp);
-
-			/* called via kfree_bulk */
-			if (!folio_test_slab(folio)) {
-				local_irq_restore(flags);
-				free_large_kmalloc(folio, objp);
-				local_irq_save(flags);
-				continue;
-			}
-			s = folio_slab(folio)->slab_cache;
-		} else {
-			s = cache_from_obj(orig_s, objp);
-		}
-
-		if (!s)
-			continue;
-
-		debug_check_no_locks_freed(objp, s->object_size);
-		if (!(s->flags & SLAB_DEBUG_OBJECTS))
-			debug_check_no_obj_freed(objp, s->object_size);
-
-		__cache_free(s, objp, _RET_IP_);
-	}
-	local_irq_restore(flags);
-
-	/* FIXME: add tracing */
-}
-EXPORT_SYMBOL(kmem_cache_free_bulk);
-
-/*
- * This initializes kmem_cache_node or resizes various caches for all nodes.
- */
-static int setup_kmem_cache_nodes(struct kmem_cache *cachep, gfp_t gfp)
-{
-	int ret;
-	int node;
-	struct kmem_cache_node *n;
-
-	for_each_online_node(node) {
-		ret = setup_kmem_cache_node(cachep, node, gfp, true);
-		if (ret)
-			goto fail;
-
-	}
-
-	return 0;
-
-fail:
-	if (!cachep->list.next) {
-		/* Cache is not active yet. Roll back what we did */
-		node--;
-		while (node >= 0) {
-			n = get_node(cachep, node);
-			if (n) {
-				kfree(n->shared);
-				free_alien_cache(n->alien);
-				kfree(n);
-				cachep->node[node] = NULL;
-			}
-			node--;
-		}
-	}
-	return -ENOMEM;
-}
-
-/* Always called with the slab_mutex held */
-static int do_tune_cpucache(struct kmem_cache *cachep, int limit,
-			    int batchcount, int shared, gfp_t gfp)
-{
-	struct array_cache __percpu *cpu_cache, *prev;
-	int cpu;
-
-	cpu_cache = alloc_kmem_cache_cpus(cachep, limit, batchcount);
-	if (!cpu_cache)
-		return -ENOMEM;
-
-	prev = cachep->cpu_cache;
-	cachep->cpu_cache = cpu_cache;
-	/*
-	 * Without a previous cpu_cache there's no need to synchronize remote
-	 * cpus, so skip the IPIs.
-	 */
-	if (prev)
-		kick_all_cpus_sync();
-
-	check_irq_on();
-	cachep->batchcount = batchcount;
-	cachep->limit = limit;
-	cachep->shared = shared;
-
-	if (!prev)
-		goto setup_node;
-
-	for_each_online_cpu(cpu) {
-		LIST_HEAD(list);
-		int node;
-		struct kmem_cache_node *n;
-		struct array_cache *ac = per_cpu_ptr(prev, cpu);
-
-		node = cpu_to_mem(cpu);
-		n = get_node(cachep, node);
-		raw_spin_lock_irq(&n->list_lock);
-		free_block(cachep, ac->entry, ac->avail, node, &list);
-		raw_spin_unlock_irq(&n->list_lock);
-		slabs_destroy(cachep, &list);
-	}
-	free_percpu(prev);
-
-setup_node:
-	return setup_kmem_cache_nodes(cachep, gfp);
-}
-
-/* Called with slab_mutex held always */
-static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp)
-{
-	int err;
-	int limit = 0;
-	int shared = 0;
-	int batchcount = 0;
-
-	err = cache_random_seq_create(cachep, cachep->num, gfp);
-	if (err)
-		goto end;
-
-	/*
-	 * The head array serves three purposes:
-	 * - create a LIFO ordering, i.e. return objects that are cache-warm
-	 * - reduce the number of spinlock operations.
-	 * - reduce the number of linked list operations on the slab and
-	 *   bufctl chains: array operations are cheaper.
-	 * The numbers are guessed, we should auto-tune as described by
-	 * Bonwick.
-	 */
-	if (cachep->size > 131072)
-		limit = 1;
-	else if (cachep->size > PAGE_SIZE)
-		limit = 8;
-	else if (cachep->size > 1024)
-		limit = 24;
-	else if (cachep->size > 256)
-		limit = 54;
-	else
-		limit = 120;
-
-	/*
-	 * CPU bound tasks (e.g. network routing) can exhibit cpu bound
-	 * allocation behaviour: Most allocs on one cpu, most free operations
-	 * on another cpu. For these cases, an efficient object passing between
-	 * cpus is necessary. This is provided by a shared array. The array
-	 * replaces Bonwick's magazine layer.
-	 * On uniprocessor, it's functionally equivalent (but less efficient)
-	 * to a larger limit. Thus disabled by default.
-	 */
-	shared = 0;
-	if (cachep->size <= PAGE_SIZE && num_possible_cpus() > 1)
-		shared = 8;
-
-#if DEBUG
-	/*
-	 * With debugging enabled, large batchcount lead to excessively long
-	 * periods with disabled local interrupts. Limit the batchcount
-	 */
-	if (limit > 32)
-		limit = 32;
-#endif
-	batchcount = (limit + 1) / 2;
-	err = do_tune_cpucache(cachep, limit, batchcount, shared, gfp);
-end:
-	if (err)
-		pr_err("enable_cpucache failed for %s, error %d\n",
-		       cachep->name, -err);
-	return err;
-}
-
-/*
- * Drain an array if it contains any elements taking the node lock only if
- * necessary. Note that the node listlock also protects the array_cache
- * if drain_array() is used on the shared array.
- */
-static void drain_array(struct kmem_cache *cachep, struct kmem_cache_node *n,
-			 struct array_cache *ac, int node)
-{
-	LIST_HEAD(list);
-
-	/* ac from n->shared can be freed if we don't hold the slab_mutex. */
-	check_mutex_acquired();
-
-	if (!ac || !ac->avail)
-		return;
-
-	if (ac->touched) {
-		ac->touched = 0;
-		return;
-	}
-
-	raw_spin_lock_irq(&n->list_lock);
-	drain_array_locked(cachep, ac, node, false, &list);
-	raw_spin_unlock_irq(&n->list_lock);
-
-	slabs_destroy(cachep, &list);
-}
-
-/**
- * cache_reap - Reclaim memory from caches.
- * @w: work descriptor
- *
- * Called from workqueue/eventd every few seconds.
- * Purpose:
- * - clear the per-cpu caches for this CPU.
- * - return freeable pages to the main free memory pool.
- *
- * If we cannot acquire the cache chain mutex then just give up - we'll try
- * again on the next iteration.
- */
-static void cache_reap(struct work_struct *w)
-{
-	struct kmem_cache *searchp;
-	struct kmem_cache_node *n;
-	int node = numa_mem_id();
-	struct delayed_work *work = to_delayed_work(w);
-
-	if (!mutex_trylock(&slab_mutex))
-		/* Give up. Setup the next iteration. */
-		goto out;
-
-	list_for_each_entry(searchp, &slab_caches, list) {
-		check_irq_on();
-
-		/*
-		 * We only take the node lock if absolutely necessary and we
-		 * have established with reasonable certainty that
-		 * we can do some work if the lock was obtained.
-		 */
-		n = get_node(searchp, node);
-
-		reap_alien(searchp, n);
-
-		drain_array(searchp, n, cpu_cache_get(searchp), node);
-
-		/*
-		 * These are racy checks but it does not matter
-		 * if we skip one check or scan twice.
-		 */
-		if (time_after(n->next_reap, jiffies))
-			goto next;
-
-		n->next_reap = jiffies + REAPTIMEOUT_NODE;
-
-		drain_array(searchp, n, n->shared, node);
-
-		if (n->free_touched)
-			n->free_touched = 0;
-		else {
-			int freed;
-
-			freed = drain_freelist(searchp, n, (n->free_limit +
-				5 * searchp->num - 1) / (5 * searchp->num));
-			STATS_ADD_REAPED(searchp, freed);
-		}
-next:
-		cond_resched();
-	}
-	check_irq_on();
-	mutex_unlock(&slab_mutex);
-	next_reap_node();
-out:
-	/* Set up the next iteration */
-	schedule_delayed_work_on(smp_processor_id(), work,
-				round_jiffies_relative(REAPTIMEOUT_AC));
-}
-
-void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo)
-{
-	unsigned long active_objs, num_objs, active_slabs;
-	unsigned long total_slabs = 0, free_objs = 0, shared_avail = 0;
-	unsigned long free_slabs = 0;
-	int node;
-	struct kmem_cache_node *n;
-
-	for_each_kmem_cache_node(cachep, node, n) {
-		check_irq_on();
-		raw_spin_lock_irq(&n->list_lock);
-
-		total_slabs += n->total_slabs;
-		free_slabs += n->free_slabs;
-		free_objs += n->free_objects;
-
-		if (n->shared)
-			shared_avail += n->shared->avail;
-
-		raw_spin_unlock_irq(&n->list_lock);
-	}
-	num_objs = total_slabs * cachep->num;
-	active_slabs = total_slabs - free_slabs;
-	active_objs = num_objs - free_objs;
-
-	sinfo->active_objs = active_objs;
-	sinfo->num_objs = num_objs;
-	sinfo->active_slabs = active_slabs;
-	sinfo->num_slabs = total_slabs;
-	sinfo->shared_avail = shared_avail;
-	sinfo->limit = cachep->limit;
-	sinfo->batchcount = cachep->batchcount;
-	sinfo->shared = cachep->shared;
-	sinfo->objects_per_slab = cachep->num;
-	sinfo->cache_order = cachep->gfporder;
-}
-
-void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *cachep)
-{
-#if STATS
-	{			/* node stats */
-		unsigned long high = cachep->high_mark;
-		unsigned long allocs = cachep->num_allocations;
-		unsigned long grown = cachep->grown;
-		unsigned long reaped = cachep->reaped;
-		unsigned long errors = cachep->errors;
-		unsigned long max_freeable = cachep->max_freeable;
-		unsigned long node_allocs = cachep->node_allocs;
-		unsigned long node_frees = cachep->node_frees;
-		unsigned long overflows = cachep->node_overflow;
-
-		seq_printf(m, " : globalstat %7lu %6lu %5lu %4lu %4lu %4lu %4lu %4lu %4lu",
-			   allocs, high, grown,
-			   reaped, errors, max_freeable, node_allocs,
-			   node_frees, overflows);
-	}
-	/* cpu stats */
-	{
-		unsigned long allochit = atomic_read(&cachep->allochit);
-		unsigned long allocmiss = atomic_read(&cachep->allocmiss);
-		unsigned long freehit = atomic_read(&cachep->freehit);
-		unsigned long freemiss = atomic_read(&cachep->freemiss);
-
-		seq_printf(m, " : cpustat %6lu %6lu %6lu %6lu",
-			   allochit, allocmiss, freehit, freemiss);
-	}
-#endif
-}
-
-#define MAX_SLABINFO_WRITE 128
-/**
- * slabinfo_write - Tuning for the slab allocator
- * @file: unused
- * @buffer: user buffer
- * @count: data length
- * @ppos: unused
- *
- * Return: %0 on success, negative error code otherwise.
- */
-ssize_t slabinfo_write(struct file *file, const char __user *buffer,
-		       size_t count, loff_t *ppos)
-{
-	char kbuf[MAX_SLABINFO_WRITE + 1], *tmp;
-	int limit, batchcount, shared, res;
-	struct kmem_cache *cachep;
-
-	if (count > MAX_SLABINFO_WRITE)
-		return -EINVAL;
-	if (copy_from_user(&kbuf, buffer, count))
-		return -EFAULT;
-	kbuf[MAX_SLABINFO_WRITE] = '\0';
-
-	tmp = strchr(kbuf, ' ');
-	if (!tmp)
-		return -EINVAL;
-	*tmp = '\0';
-	tmp++;
-	if (sscanf(tmp, " %d %d %d", &limit, &batchcount, &shared) != 3)
-		return -EINVAL;
-
-	/* Find the cache in the chain of caches. */
-	mutex_lock(&slab_mutex);
-	res = -EINVAL;
-	list_for_each_entry(cachep, &slab_caches, list) {
-		if (!strcmp(cachep->name, kbuf)) {
-			if (limit < 1 || batchcount < 1 ||
-					batchcount > limit || shared < 0) {
-				res = 0;
-			} else {
-				res = do_tune_cpucache(cachep, limit,
-						       batchcount, shared,
-						       GFP_KERNEL);
-			}
-			break;
-		}
-	}
-	mutex_unlock(&slab_mutex);
-	if (res >= 0)
-		res = count;
-	return res;
-}
-
-#ifdef CONFIG_HARDENED_USERCOPY
-/*
- * Rejects incorrectly sized objects and objects that are to be copied
- * to/from userspace but do not fall entirely within the containing slab
- * cache's usercopy region.
- *
- * Returns NULL if check passes, otherwise const char * to name of cache
- * to indicate an error.
- */
-void __check_heap_object(const void *ptr, unsigned long n,
-			 const struct slab *slab, bool to_user)
-{
-	struct kmem_cache *cachep;
-	unsigned int objnr;
-	unsigned long offset;
-
-	ptr = kasan_reset_tag(ptr);
-
-	/* Find and validate object. */
-	cachep = slab->slab_cache;
-	objnr = obj_to_index(cachep, slab, (void *)ptr);
-	BUG_ON(objnr >= cachep->num);
-
-	/* Find offset within object. */
-	if (is_kfence_address(ptr))
-		offset = ptr - kfence_object_start(ptr);
-	else
-		offset = ptr - index_to_obj(cachep, slab, objnr) - obj_offset(cachep);
-
-	/* Allow address range falling entirely within usercopy region. */
-	if (offset >= cachep->useroffset &&
-	    offset - cachep->useroffset <= cachep->usersize &&
-	    n <= cachep->useroffset - offset + cachep->usersize)
-		return;
-
-	usercopy_abort("SLAB object", cachep->name, to_user, offset, n);
-}
-#endif /* CONFIG_HARDENED_USERCOPY */
-- 
cgit v1.2.3


From 7ef08ae8277c66657127844179912214c67fb4bc Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Tue, 3 Oct 2023 09:54:15 +0200
Subject: mm/slab: move struct kmem_cache_cpu declaration to slub.c

Nothing outside SLUB itself accesses the struct kmem_cache_cpu fields so
it does not need to be declared in slub_def.h. This allows also to move
enum stat_item.

Reviewed-by: Kees Cook <keescook@chromium.org>
Acked-by: David Rientjes <rientjes@google.com>
Tested-by: David Rientjes <rientjes@google.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
 include/linux/slub_def.h | 54 ------------------------------------------------
 mm/slub.c                | 54 ++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 54 insertions(+), 54 deletions(-)

(limited to 'include')

diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index deb90cf4bffb..a0229ea42977 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -12,60 +12,6 @@
 #include <linux/reciprocal_div.h>
 #include <linux/local_lock.h>
 
-enum stat_item {
-	ALLOC_FASTPATH,		/* Allocation from cpu slab */
-	ALLOC_SLOWPATH,		/* Allocation by getting a new cpu slab */
-	FREE_FASTPATH,		/* Free to cpu slab */
-	FREE_SLOWPATH,		/* Freeing not to cpu slab */
-	FREE_FROZEN,		/* Freeing to frozen slab */
-	FREE_ADD_PARTIAL,	/* Freeing moves slab to partial list */
-	FREE_REMOVE_PARTIAL,	/* Freeing removes last object */
-	ALLOC_FROM_PARTIAL,	/* Cpu slab acquired from node partial list */
-	ALLOC_SLAB,		/* Cpu slab acquired from page allocator */
-	ALLOC_REFILL,		/* Refill cpu slab from slab freelist */
-	ALLOC_NODE_MISMATCH,	/* Switching cpu slab */
-	FREE_SLAB,		/* Slab freed to the page allocator */
-	CPUSLAB_FLUSH,		/* Abandoning of the cpu slab */
-	DEACTIVATE_FULL,	/* Cpu slab was full when deactivated */
-	DEACTIVATE_EMPTY,	/* Cpu slab was empty when deactivated */
-	DEACTIVATE_TO_HEAD,	/* Cpu slab was moved to the head of partials */
-	DEACTIVATE_TO_TAIL,	/* Cpu slab was moved to the tail of partials */
-	DEACTIVATE_REMOTE_FREES,/* Slab contained remotely freed objects */
-	DEACTIVATE_BYPASS,	/* Implicit deactivation */
-	ORDER_FALLBACK,		/* Number of times fallback was necessary */
-	CMPXCHG_DOUBLE_CPU_FAIL,/* Failure of this_cpu_cmpxchg_double */
-	CMPXCHG_DOUBLE_FAIL,	/* Number of times that cmpxchg double did not match */
-	CPU_PARTIAL_ALLOC,	/* Used cpu partial on alloc */
-	CPU_PARTIAL_FREE,	/* Refill cpu partial on free */
-	CPU_PARTIAL_NODE,	/* Refill cpu partial from node partial */
-	CPU_PARTIAL_DRAIN,	/* Drain cpu partial to node partial */
-	NR_SLUB_STAT_ITEMS
-};
-
-#ifndef CONFIG_SLUB_TINY
-/*
- * When changing the layout, make sure freelist and tid are still compatible
- * with this_cpu_cmpxchg_double() alignment requirements.
- */
-struct kmem_cache_cpu {
-	union {
-		struct {
-			void **freelist;	/* Pointer to next available object */
-			unsigned long tid;	/* Globally unique transaction id */
-		};
-		freelist_aba_t freelist_tid;
-	};
-	struct slab *slab;	/* The slab from which we are allocating */
-#ifdef CONFIG_SLUB_CPU_PARTIAL
-	struct slab *partial;	/* Partially allocated frozen slabs */
-#endif
-	local_lock_t lock;	/* Protects the fields above */
-#ifdef CONFIG_SLUB_STATS
-	unsigned stat[NR_SLUB_STAT_ITEMS];
-#endif
-};
-#endif /* CONFIG_SLUB_TINY */
-
 #ifdef CONFIG_SLUB_CPU_PARTIAL
 #define slub_percpu_partial(c)		((c)->partial)
 
diff --git a/mm/slub.c b/mm/slub.c
index 3e01731783df..979932d046fd 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -330,6 +330,60 @@ static void debugfs_slab_add(struct kmem_cache *);
 static inline void debugfs_slab_add(struct kmem_cache *s) { }
 #endif
 
+enum stat_item {
+	ALLOC_FASTPATH,		/* Allocation from cpu slab */
+	ALLOC_SLOWPATH,		/* Allocation by getting a new cpu slab */
+	FREE_FASTPATH,		/* Free to cpu slab */
+	FREE_SLOWPATH,		/* Freeing not to cpu slab */
+	FREE_FROZEN,		/* Freeing to frozen slab */
+	FREE_ADD_PARTIAL,	/* Freeing moves slab to partial list */
+	FREE_REMOVE_PARTIAL,	/* Freeing removes last object */
+	ALLOC_FROM_PARTIAL,	/* Cpu slab acquired from node partial list */
+	ALLOC_SLAB,		/* Cpu slab acquired from page allocator */
+	ALLOC_REFILL,		/* Refill cpu slab from slab freelist */
+	ALLOC_NODE_MISMATCH,	/* Switching cpu slab */
+	FREE_SLAB,		/* Slab freed to the page allocator */
+	CPUSLAB_FLUSH,		/* Abandoning of the cpu slab */
+	DEACTIVATE_FULL,	/* Cpu slab was full when deactivated */
+	DEACTIVATE_EMPTY,	/* Cpu slab was empty when deactivated */
+	DEACTIVATE_TO_HEAD,	/* Cpu slab was moved to the head of partials */
+	DEACTIVATE_TO_TAIL,	/* Cpu slab was moved to the tail of partials */
+	DEACTIVATE_REMOTE_FREES,/* Slab contained remotely freed objects */
+	DEACTIVATE_BYPASS,	/* Implicit deactivation */
+	ORDER_FALLBACK,		/* Number of times fallback was necessary */
+	CMPXCHG_DOUBLE_CPU_FAIL,/* Failures of this_cpu_cmpxchg_double */
+	CMPXCHG_DOUBLE_FAIL,	/* Failures of slab freelist update */
+	CPU_PARTIAL_ALLOC,	/* Used cpu partial on alloc */
+	CPU_PARTIAL_FREE,	/* Refill cpu partial on free */
+	CPU_PARTIAL_NODE,	/* Refill cpu partial from node partial */
+	CPU_PARTIAL_DRAIN,	/* Drain cpu partial to node partial */
+	NR_SLUB_STAT_ITEMS
+};
+
+#ifndef CONFIG_SLUB_TINY
+/*
+ * When changing the layout, make sure freelist and tid are still compatible
+ * with this_cpu_cmpxchg_double() alignment requirements.
+ */
+struct kmem_cache_cpu {
+	union {
+		struct {
+			void **freelist;	/* Pointer to next available object */
+			unsigned long tid;	/* Globally unique transaction id */
+		};
+		freelist_aba_t freelist_tid;
+	};
+	struct slab *slab;	/* The slab from which we are allocating */
+#ifdef CONFIG_SLUB_CPU_PARTIAL
+	struct slab *partial;	/* Partially allocated frozen slabs */
+#endif
+	local_lock_t lock;	/* Protects the fields above */
+#ifdef CONFIG_SLUB_STATS
+	unsigned int stat[NR_SLUB_STAT_ITEMS];
+#endif
+};
+#endif /* CONFIG_SLUB_TINY */
+
 static inline void stat(const struct kmem_cache *s, enum stat_item si)
 {
 #ifdef CONFIG_SLUB_STATS
-- 
cgit v1.2.3


From 19975f83412fbb9b1458f3dfbf16ca043a57788a Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Tue, 3 Oct 2023 09:59:48 +0200
Subject: mm/slab: move the rest of slub_def.h to mm/slab.h

mm/slab.h is the only place to include include/linux/slub_def.h which
has allowed switching between SLAB and SLUB. Now we can simply move the
contents over and remove slub_def.h.

Use this opportunity to fix up some whitespace (alignment) issues.

Reviewed-by: Kees Cook <keescook@chromium.org>
Acked-by: David Rientjes <rientjes@google.com>
Tested-by: David Rientjes <rientjes@google.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
 include/linux/slub_def.h | 150 -----------------------------------------------
 mm/slab.h                | 138 ++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 137 insertions(+), 151 deletions(-)
 delete mode 100644 include/linux/slub_def.h

(limited to 'include')

diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
deleted file mode 100644
index a0229ea42977..000000000000
--- a/include/linux/slub_def.h
+++ /dev/null
@@ -1,150 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_SLUB_DEF_H
-#define _LINUX_SLUB_DEF_H
-
-/*
- * SLUB : A Slab allocator without object queues.
- *
- * (C) 2007 SGI, Christoph Lameter
- */
-#include <linux/kfence.h>
-#include <linux/kobject.h>
-#include <linux/reciprocal_div.h>
-#include <linux/local_lock.h>
-
-#ifdef CONFIG_SLUB_CPU_PARTIAL
-#define slub_percpu_partial(c)		((c)->partial)
-
-#define slub_set_percpu_partial(c, p)		\
-({						\
-	slub_percpu_partial(c) = (p)->next;	\
-})
-
-#define slub_percpu_partial_read_once(c)     READ_ONCE(slub_percpu_partial(c))
-#else
-#define slub_percpu_partial(c)			NULL
-
-#define slub_set_percpu_partial(c, p)
-
-#define slub_percpu_partial_read_once(c)	NULL
-#endif // CONFIG_SLUB_CPU_PARTIAL
-
-/*
- * Word size structure that can be atomically updated or read and that
- * contains both the order and the number of objects that a slab of the
- * given order would contain.
- */
-struct kmem_cache_order_objects {
-	unsigned int x;
-};
-
-/*
- * Slab cache management.
- */
-struct kmem_cache {
-#ifndef CONFIG_SLUB_TINY
-	struct kmem_cache_cpu __percpu *cpu_slab;
-#endif
-	/* Used for retrieving partial slabs, etc. */
-	slab_flags_t flags;
-	unsigned long min_partial;
-	unsigned int size;	/* The size of an object including metadata */
-	unsigned int object_size;/* The size of an object without metadata */
-	struct reciprocal_value reciprocal_size;
-	unsigned int offset;	/* Free pointer offset */
-#ifdef CONFIG_SLUB_CPU_PARTIAL
-	/* Number of per cpu partial objects to keep around */
-	unsigned int cpu_partial;
-	/* Number of per cpu partial slabs to keep around */
-	unsigned int cpu_partial_slabs;
-#endif
-	struct kmem_cache_order_objects oo;
-
-	/* Allocation and freeing of slabs */
-	struct kmem_cache_order_objects min;
-	gfp_t allocflags;	/* gfp flags to use on each alloc */
-	int refcount;		/* Refcount for slab cache destroy */
-	void (*ctor)(void *);
-	unsigned int inuse;		/* Offset to metadata */
-	unsigned int align;		/* Alignment */
-	unsigned int red_left_pad;	/* Left redzone padding size */
-	const char *name;	/* Name (only for display!) */
-	struct list_head list;	/* List of slab caches */
-#ifdef CONFIG_SYSFS
-	struct kobject kobj;	/* For sysfs */
-#endif
-#ifdef CONFIG_SLAB_FREELIST_HARDENED
-	unsigned long random;
-#endif
-
-#ifdef CONFIG_NUMA
-	/*
-	 * Defragmentation by allocating from a remote node.
-	 */
-	unsigned int remote_node_defrag_ratio;
-#endif
-
-#ifdef CONFIG_SLAB_FREELIST_RANDOM
-	unsigned int *random_seq;
-#endif
-
-#ifdef CONFIG_KASAN_GENERIC
-	struct kasan_cache kasan_info;
-#endif
-
-#ifdef CONFIG_HARDENED_USERCOPY
-	unsigned int useroffset;	/* Usercopy region offset */
-	unsigned int usersize;		/* Usercopy region size */
-#endif
-
-	struct kmem_cache_node *node[MAX_NUMNODES];
-};
-
-#if defined(CONFIG_SYSFS) && !defined(CONFIG_SLUB_TINY)
-#define SLAB_SUPPORTS_SYSFS
-void sysfs_slab_unlink(struct kmem_cache *);
-void sysfs_slab_release(struct kmem_cache *);
-#else
-static inline void sysfs_slab_unlink(struct kmem_cache *s)
-{
-}
-static inline void sysfs_slab_release(struct kmem_cache *s)
-{
-}
-#endif
-
-void *fixup_red_left(struct kmem_cache *s, void *p);
-
-static inline void *nearest_obj(struct kmem_cache *cache, const struct slab *slab,
-				void *x) {
-	void *object = x - (x - slab_address(slab)) % cache->size;
-	void *last_object = slab_address(slab) +
-		(slab->objects - 1) * cache->size;
-	void *result = (unlikely(object > last_object)) ? last_object : object;
-
-	result = fixup_red_left(cache, result);
-	return result;
-}
-
-/* Determine object index from a given position */
-static inline unsigned int __obj_to_index(const struct kmem_cache *cache,
-					  void *addr, void *obj)
-{
-	return reciprocal_divide(kasan_reset_tag(obj) - addr,
-				 cache->reciprocal_size);
-}
-
-static inline unsigned int obj_to_index(const struct kmem_cache *cache,
-					const struct slab *slab, void *obj)
-{
-	if (is_kfence_address(obj))
-		return 0;
-	return __obj_to_index(cache, slab_address(slab), obj);
-}
-
-static inline int objs_per_slab(const struct kmem_cache *cache,
-				     const struct slab *slab)
-{
-	return slab->objects;
-}
-#endif /* _LINUX_SLUB_DEF_H */
diff --git a/mm/slab.h b/mm/slab.h
index 014c36ea51fa..3a8d13c099fa 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -209,7 +209,143 @@ static inline size_t slab_size(const struct slab *slab)
 	return PAGE_SIZE << slab_order(slab);
 }
 
-#include <linux/slub_def.h>
+#include <linux/kfence.h>
+#include <linux/kobject.h>
+#include <linux/reciprocal_div.h>
+#include <linux/local_lock.h>
+
+#ifdef CONFIG_SLUB_CPU_PARTIAL
+#define slub_percpu_partial(c)			((c)->partial)
+
+#define slub_set_percpu_partial(c, p)		\
+({						\
+	slub_percpu_partial(c) = (p)->next;	\
+})
+
+#define slub_percpu_partial_read_once(c)	READ_ONCE(slub_percpu_partial(c))
+#else
+#define slub_percpu_partial(c)			NULL
+
+#define slub_set_percpu_partial(c, p)
+
+#define slub_percpu_partial_read_once(c)	NULL
+#endif // CONFIG_SLUB_CPU_PARTIAL
+
+/*
+ * Word size structure that can be atomically updated or read and that
+ * contains both the order and the number of objects that a slab of the
+ * given order would contain.
+ */
+struct kmem_cache_order_objects {
+	unsigned int x;
+};
+
+/*
+ * Slab cache management.
+ */
+struct kmem_cache {
+#ifndef CONFIG_SLUB_TINY
+	struct kmem_cache_cpu __percpu *cpu_slab;
+#endif
+	/* Used for retrieving partial slabs, etc. */
+	slab_flags_t flags;
+	unsigned long min_partial;
+	unsigned int size;		/* Object size including metadata */
+	unsigned int object_size;	/* Object size without metadata */
+	struct reciprocal_value reciprocal_size;
+	unsigned int offset;		/* Free pointer offset */
+#ifdef CONFIG_SLUB_CPU_PARTIAL
+	/* Number of per cpu partial objects to keep around */
+	unsigned int cpu_partial;
+	/* Number of per cpu partial slabs to keep around */
+	unsigned int cpu_partial_slabs;
+#endif
+	struct kmem_cache_order_objects oo;
+
+	/* Allocation and freeing of slabs */
+	struct kmem_cache_order_objects min;
+	gfp_t allocflags;		/* gfp flags to use on each alloc */
+	int refcount;			/* Refcount for slab cache destroy */
+	void (*ctor)(void *object);	/* Object constructor */
+	unsigned int inuse;		/* Offset to metadata */
+	unsigned int align;		/* Alignment */
+	unsigned int red_left_pad;	/* Left redzone padding size */
+	const char *name;		/* Name (only for display!) */
+	struct list_head list;		/* List of slab caches */
+#ifdef CONFIG_SYSFS
+	struct kobject kobj;		/* For sysfs */
+#endif
+#ifdef CONFIG_SLAB_FREELIST_HARDENED
+	unsigned long random;
+#endif
+
+#ifdef CONFIG_NUMA
+	/*
+	 * Defragmentation by allocating from a remote node.
+	 */
+	unsigned int remote_node_defrag_ratio;
+#endif
+
+#ifdef CONFIG_SLAB_FREELIST_RANDOM
+	unsigned int *random_seq;
+#endif
+
+#ifdef CONFIG_KASAN_GENERIC
+	struct kasan_cache kasan_info;
+#endif
+
+#ifdef CONFIG_HARDENED_USERCOPY
+	unsigned int useroffset;	/* Usercopy region offset */
+	unsigned int usersize;		/* Usercopy region size */
+#endif
+
+	struct kmem_cache_node *node[MAX_NUMNODES];
+};
+
+#if defined(CONFIG_SYSFS) && !defined(CONFIG_SLUB_TINY)
+#define SLAB_SUPPORTS_SYSFS
+void sysfs_slab_unlink(struct kmem_cache *s);
+void sysfs_slab_release(struct kmem_cache *s);
+#else
+static inline void sysfs_slab_unlink(struct kmem_cache *s) { }
+static inline void sysfs_slab_release(struct kmem_cache *s) { }
+#endif
+
+void *fixup_red_left(struct kmem_cache *s, void *p);
+
+static inline void *nearest_obj(struct kmem_cache *cache,
+				const struct slab *slab, void *x)
+{
+	void *object = x - (x - slab_address(slab)) % cache->size;
+	void *last_object = slab_address(slab) +
+		(slab->objects - 1) * cache->size;
+	void *result = (unlikely(object > last_object)) ? last_object : object;
+
+	result = fixup_red_left(cache, result);
+	return result;
+}
+
+/* Determine object index from a given position */
+static inline unsigned int __obj_to_index(const struct kmem_cache *cache,
+					  void *addr, void *obj)
+{
+	return reciprocal_divide(kasan_reset_tag(obj) - addr,
+				 cache->reciprocal_size);
+}
+
+static inline unsigned int obj_to_index(const struct kmem_cache *cache,
+					const struct slab *slab, void *obj)
+{
+	if (is_kfence_address(obj))
+		return 0;
+	return __obj_to_index(cache, slab_address(slab), obj);
+}
+
+static inline int objs_per_slab(const struct kmem_cache *cache,
+				const struct slab *slab)
+{
+	return slab->objects;
+}
 
 #include <linux/memcontrol.h>
 #include <linux/fault-inject.h>
-- 
cgit v1.2.3


From da7dfaa6d6f731c30eca6ffa808b83634d43e26f Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <dima@arista.com>
Date: Mon, 4 Dec 2023 19:00:41 +0000
Subject: net/tcp: Consistently align TCP-AO option in the header

Currently functions that pre-calculate TCP header options length use
unaligned TCP-AO header + MAC-length for skb reservation.
And the functions that actually write TCP-AO options into skb do align
the header. Nothing good can come out of this for ((maclen % 4) != 0).

Provide tcp_ao_len_aligned() helper and use it everywhere for TCP
header options space calculations.

Fixes: 1e03d32bea8e ("net/tcp: Add TCP-AO sign to outgoing packets")
Signed-off-by: Dmitry Safonov <dima@arista.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/tcp_ao.h     | 6 ++++++
 net/ipv4/tcp_ao.c        | 4 ++--
 net/ipv4/tcp_ipv4.c      | 4 ++--
 net/ipv4/tcp_minisocks.c | 2 +-
 net/ipv4/tcp_output.c    | 6 +++---
 net/ipv6/tcp_ipv6.c      | 2 +-
 6 files changed, 15 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp_ao.h b/include/net/tcp_ao.h
index b56be10838f0..647781080613 100644
--- a/include/net/tcp_ao.h
+++ b/include/net/tcp_ao.h
@@ -62,11 +62,17 @@ static inline int tcp_ao_maclen(const struct tcp_ao_key *key)
 	return key->maclen;
 }
 
+/* Use tcp_ao_len_aligned() for TCP header calculations */
 static inline int tcp_ao_len(const struct tcp_ao_key *key)
 {
 	return tcp_ao_maclen(key) + sizeof(struct tcp_ao_hdr);
 }
 
+static inline int tcp_ao_len_aligned(const struct tcp_ao_key *key)
+{
+	return round_up(tcp_ao_len(key), 4);
+}
+
 static inline unsigned int tcp_ao_digest_size(struct tcp_ao_key *key)
 {
 	return key->digest_size;
diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c
index 7696417d0640..c8be1d526eac 100644
--- a/net/ipv4/tcp_ao.c
+++ b/net/ipv4/tcp_ao.c
@@ -1100,7 +1100,7 @@ void tcp_ao_connect_init(struct sock *sk)
 			ao_info->current_key = key;
 		if (!ao_info->rnext_key)
 			ao_info->rnext_key = key;
-		tp->tcp_header_len += tcp_ao_len(key);
+		tp->tcp_header_len += tcp_ao_len_aligned(key);
 
 		ao_info->lisn = htonl(tp->write_seq);
 		ao_info->snd_sne = 0;
@@ -1346,7 +1346,7 @@ static int tcp_ao_parse_crypto(struct tcp_ao_add *cmd, struct tcp_ao_key *key)
 	syn_tcp_option_space -= TCPOLEN_MSS_ALIGNED;
 	syn_tcp_option_space -= TCPOLEN_TSTAMP_ALIGNED;
 	syn_tcp_option_space -= TCPOLEN_WSCALE_ALIGNED;
-	if (tcp_ao_len(key) > syn_tcp_option_space) {
+	if (tcp_ao_len_aligned(key) > syn_tcp_option_space) {
 		err = -EMSGSIZE;
 		goto err_kfree;
 	}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 5f693bbd578d..0c50c5a32b84 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -690,7 +690,7 @@ static bool tcp_v4_ao_sign_reset(const struct sock *sk, struct sk_buff *skb,
 
 	reply_options[0] = htonl((TCPOPT_AO << 24) | (tcp_ao_len(key) << 16) |
 				 (aoh->rnext_keyid << 8) | keyid);
-	arg->iov[0].iov_len += round_up(tcp_ao_len(key), 4);
+	arg->iov[0].iov_len += tcp_ao_len_aligned(key);
 	reply->doff = arg->iov[0].iov_len / 4;
 
 	if (tcp_ao_hash_hdr(AF_INET, (char *)&reply_options[1],
@@ -978,7 +978,7 @@ static void tcp_v4_send_ack(const struct sock *sk,
 					  (tcp_ao_len(key->ao_key) << 16) |
 					  (key->ao_key->sndid << 8) |
 					  key->rcv_next);
-		arg.iov[0].iov_len += round_up(tcp_ao_len(key->ao_key), 4);
+		arg.iov[0].iov_len += tcp_ao_len_aligned(key->ao_key);
 		rep.th.doff = arg.iov[0].iov_len / 4;
 
 		tcp_ao_hash_hdr(AF_INET, (char *)&rep.opt[offset],
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index a9807eeb311c..9e85f2a0bddd 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -615,7 +615,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 	ao_key = treq->af_specific->ao_lookup(sk, req,
 				tcp_rsk(req)->ao_keyid, -1);
 	if (ao_key)
-		newtp->tcp_header_len += tcp_ao_len(ao_key);
+		newtp->tcp_header_len += tcp_ao_len_aligned(ao_key);
  #endif
 	if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len)
 		newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index eb13a55d660c..93eef1dbbc55 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -825,7 +825,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 		timestamps = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps);
 		if (tcp_key_is_ao(key)) {
 			opts->options |= OPTION_AO;
-			remaining -= tcp_ao_len(key->ao_key);
+			remaining -= tcp_ao_len_aligned(key->ao_key);
 		}
 	}
 
@@ -915,7 +915,7 @@ static unsigned int tcp_synack_options(const struct sock *sk,
 			ireq->tstamp_ok &= !ireq->sack_ok;
 	} else if (tcp_key_is_ao(key)) {
 		opts->options |= OPTION_AO;
-		remaining -= tcp_ao_len(key->ao_key);
+		remaining -= tcp_ao_len_aligned(key->ao_key);
 		ireq->tstamp_ok &= !ireq->sack_ok;
 	}
 
@@ -982,7 +982,7 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
 		size += TCPOLEN_MD5SIG_ALIGNED;
 	} else if (tcp_key_is_ao(key)) {
 		opts->options |= OPTION_AO;
-		size += tcp_ao_len(key->ao_key);
+		size += tcp_ao_len_aligned(key->ao_key);
 	}
 
 	if (likely(tp->rx_opt.tstamp_ok)) {
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 937a02c2e534..8c6623496dd7 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -881,7 +881,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
 	if (tcp_key_is_md5(key))
 		tot_len += TCPOLEN_MD5SIG_ALIGNED;
 	if (tcp_key_is_ao(key))
-		tot_len += tcp_ao_len(key->ao_key);
+		tot_len += tcp_ao_len_aligned(key->ao_key);
 
 #ifdef CONFIG_MPTCP
 	if (rst && !tcp_key_is_md5(key)) {
-- 
cgit v1.2.3


From 9396c4ee93f9ac03cd0cea0bb345fbc657772943 Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <dima@arista.com>
Date: Mon, 4 Dec 2023 19:00:44 +0000
Subject: net/tcp: Don't store TCP-AO maclen on reqsk

This extra check doesn't work for a handshake when SYN segment has
(current_key.maclen != rnext_key.maclen). It could be amended to
preserve rnext_key.maclen instead of current_key.maclen, but that
requires a lookup on listen socket.

Originally, this extra maclen check was introduced just because it was
cheap. Drop it and convert tcp_request_sock::maclen into boolean
tcp_request_sock::used_tcp_ao.

Fixes: 06b22ef29591 ("net/tcp: Wire TCP-AO to request sockets")
Signed-off-by: Dmitry Safonov <dima@arista.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/linux/tcp.h   | 8 ++------
 net/ipv4/tcp_ao.c     | 4 ++--
 net/ipv4/tcp_input.c  | 5 +++--
 net/ipv4/tcp_output.c | 9 +++------
 4 files changed, 10 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 68f3d315d2e1..b646b574b060 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -169,7 +169,7 @@ struct tcp_request_sock {
 #ifdef CONFIG_TCP_AO
 	u8				ao_keyid;
 	u8				ao_rcv_next;
-	u8				maclen;
+	bool				used_tcp_ao;
 #endif
 };
 
@@ -180,14 +180,10 @@ static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req)
 
 static inline bool tcp_rsk_used_ao(const struct request_sock *req)
 {
-	/* The real length of MAC is saved in the request socket,
-	 * signing anything with zero-length makes no sense, so here is
-	 * a little hack..
-	 */
 #ifndef CONFIG_TCP_AO
 	return false;
 #else
-	return tcp_rsk(req)->maclen != 0;
+	return tcp_rsk(req)->used_tcp_ao;
 #endif
 }
 
diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c
index 18dacfef7a07..f8308d3f565e 100644
--- a/net/ipv4/tcp_ao.c
+++ b/net/ipv4/tcp_ao.c
@@ -851,7 +851,7 @@ void tcp_ao_syncookie(struct sock *sk, const struct sk_buff *skb,
 	const struct tcp_ao_hdr *aoh;
 	struct tcp_ao_key *key;
 
-	treq->maclen = 0;
+	treq->used_tcp_ao = false;
 
 	if (tcp_parse_auth_options(th, NULL, &aoh) || !aoh)
 		return;
@@ -863,7 +863,7 @@ void tcp_ao_syncookie(struct sock *sk, const struct sk_buff *skb,
 
 	treq->ao_rcv_next = aoh->keyid;
 	treq->ao_keyid = aoh->rnext_keyid;
-	treq->maclen = tcp_ao_maclen(key);
+	treq->used_tcp_ao = true;
 }
 
 static enum skb_drop_reason
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index bcb55d98004c..337c8bb07ccc 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -7182,11 +7182,12 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	if (tcp_parse_auth_options(tcp_hdr(skb), NULL, &aoh))
 		goto drop_and_release; /* Invalid TCP options */
 	if (aoh) {
-		tcp_rsk(req)->maclen = aoh->length - sizeof(struct tcp_ao_hdr);
+		tcp_rsk(req)->used_tcp_ao = true;
 		tcp_rsk(req)->ao_rcv_next = aoh->keyid;
 		tcp_rsk(req)->ao_keyid = aoh->rnext_keyid;
+
 	} else {
-		tcp_rsk(req)->maclen = 0;
+		tcp_rsk(req)->used_tcp_ao = false;
 	}
 #endif
 	tcp_rsk(req)->snt_isn = isn;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 93eef1dbbc55..f5ef15e1d9ac 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3720,7 +3720,6 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	if (tcp_rsk_used_ao(req)) {
 #ifdef CONFIG_TCP_AO
 		struct tcp_ao_key *ao_key = NULL;
-		u8 maclen = tcp_rsk(req)->maclen;
 		u8 keyid = tcp_rsk(req)->ao_keyid;
 
 		ao_key = tcp_sk(sk)->af_specific->ao_lookup(sk, req_to_sk(req),
@@ -3730,13 +3729,11 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 		 * for another peer-matching key, but the peer has requested
 		 * ao_keyid (RFC5925 RNextKeyID), so let's keep it simple here.
 		 */
-		if (unlikely(!ao_key || tcp_ao_maclen(ao_key) != maclen)) {
-			u8 key_maclen = ao_key ? tcp_ao_maclen(ao_key) : 0;
-
+		if (unlikely(!ao_key)) {
 			rcu_read_unlock();
 			kfree_skb(skb);
-			net_warn_ratelimited("TCP-AO: the keyid %u with maclen %u|%u from SYN packet is not present - not sending SYNACK\n",
-					     keyid, maclen, key_maclen);
+			net_warn_ratelimited("TCP-AO: the keyid %u from SYN packet is not present - not sending SYNACK\n",
+					     keyid);
 			return NULL;
 		}
 		key.ao_key = ao_key;
-- 
cgit v1.2.3


From 742aa6c563d29c367edbf0ef7236a7a853ed9be4 Mon Sep 17 00:00:00 2001
From: Conor Dooley <conor.dooley@microchip.com>
Date: Fri, 20 Oct 2023 14:18:40 +0100
Subject: soc: microchip: mpfs: enable access to the system controller's flash

The system controller has a flash that contains images used to reprogram
the FPGA using IAP (In-Application Programming).
Introduce a function that allows a driver with a reference to the system
controller to get one to a flash device attached to it.

Signed-off-by: Conor Dooley <conor.dooley@microchip.com>
---
 drivers/soc/microchip/Kconfig               |  1 +
 drivers/soc/microchip/mpfs-sys-controller.c | 20 ++++++++++++++++++++
 include/soc/microchip/mpfs.h                |  2 ++
 3 files changed, 23 insertions(+)

(limited to 'include')

diff --git a/drivers/soc/microchip/Kconfig b/drivers/soc/microchip/Kconfig
index eb656b33156b..9b0fdd95276e 100644
--- a/drivers/soc/microchip/Kconfig
+++ b/drivers/soc/microchip/Kconfig
@@ -1,6 +1,7 @@
 config POLARFIRE_SOC_SYS_CTRL
 	tristate "POLARFIRE_SOC_SYS_CTRL"
 	depends on POLARFIRE_SOC_MAILBOX
+	depends on MTD
 	help
 	  This driver adds support for the PolarFire SoC (MPFS) system controller.
 
diff --git a/drivers/soc/microchip/mpfs-sys-controller.c b/drivers/soc/microchip/mpfs-sys-controller.c
index 0935e9e94172..c7e063993d92 100644
--- a/drivers/soc/microchip/mpfs-sys-controller.c
+++ b/drivers/soc/microchip/mpfs-sys-controller.c
@@ -12,6 +12,8 @@
 #include <linux/kref.h>
 #include <linux/module.h>
 #include <linux/jiffies.h>
+#include <linux/mtd/mtd.h>
+#include <linux/spi/spi.h>
 #include <linux/interrupt.h>
 #include <linux/of.h>
 #include <linux/mailbox_client.h>
@@ -30,6 +32,7 @@ struct mpfs_sys_controller {
 	struct mbox_client client;
 	struct mbox_chan *chan;
 	struct completion c;
+	struct mtd_info *flash;
 	struct kref consumers;
 };
 
@@ -99,6 +102,12 @@ static void mpfs_sys_controller_put(void *data)
 	kref_put(&sys_controller->consumers, mpfs_sys_controller_delete);
 }
 
+struct mtd_info *mpfs_sys_controller_get_flash(struct mpfs_sys_controller *mpfs_client)
+{
+	return mpfs_client->flash;
+}
+EXPORT_SYMBOL(mpfs_sys_controller_get_flash);
+
 static struct platform_device subdevs[] = {
 	{
 		.name		= "mpfs-rng",
@@ -114,12 +123,23 @@ static int mpfs_sys_controller_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct mpfs_sys_controller *sys_controller;
+	struct device_node *np;
 	int i, ret;
 
 	sys_controller = kzalloc(sizeof(*sys_controller), GFP_KERNEL);
 	if (!sys_controller)
 		return -ENOMEM;
 
+	np = of_parse_phandle(dev->of_node, "microchip,bitstream-flash", 0);
+	if (!np)
+		goto no_flash;
+
+	sys_controller->flash = of_get_mtd_device_by_node(np);
+	of_node_put(np);
+	if (IS_ERR(sys_controller->flash))
+		return dev_err_probe(dev, PTR_ERR(sys_controller->flash), "Failed to get flash\n");
+
+no_flash:
 	sys_controller->client.dev = dev;
 	sys_controller->client.rx_callback = mpfs_sys_controller_rx_callback;
 	sys_controller->client.tx_block = 1U;
diff --git a/include/soc/microchip/mpfs.h b/include/soc/microchip/mpfs.h
index f916dcde457f..09722f83b0ca 100644
--- a/include/soc/microchip/mpfs.h
+++ b/include/soc/microchip/mpfs.h
@@ -38,6 +38,8 @@ int mpfs_blocking_transaction(struct mpfs_sys_controller *mpfs_client, struct mp
 
 struct mpfs_sys_controller *mpfs_sys_controller_get(struct device *dev);
 
+struct mtd_info *mpfs_sys_controller_get_flash(struct mpfs_sys_controller *mpfs_client);
+
 #endif /* if IS_ENABLED(CONFIG_POLARFIRE_SOC_SYS_CTRL) */
 
 #if IS_ENABLED(CONFIG_MCHP_CLK_MPFS)
-- 
cgit v1.2.3


From 16e5ac127d8d18adf85fe5ba847d77b58d1ed418 Mon Sep 17 00:00:00 2001
From: Naresh Solanki <naresh.solanki@9elements.com>
Date: Tue, 5 Dec 2023 16:22:04 +0530
Subject: regulator: event: Add regulator netlink event support

This commit introduces netlink event support to the regulator subsystem.

Changes:
- Introduce event.c and regnl.h for netlink event handling.
- Implement reg_generate_netlink_event to broadcast regulator events.
- Update Makefile to include the new event.c file.

Signed-off-by: Naresh Solanki <naresh.solanki@9elements.com>
Link: https://lore.kernel.org/r/20231205105207.1262928-1-naresh.solanki@9elements.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/Kconfig          | 10 +++++
 drivers/regulator/Makefile         |  1 +
 drivers/regulator/core.c           | 19 +++++++-
 drivers/regulator/event.c          | 91 ++++++++++++++++++++++++++++++++++++++
 drivers/regulator/regnl.h          | 13 ++++++
 include/linux/regulator/consumer.h | 47 +-------------------
 include/uapi/regulator/regulator.h | 90 +++++++++++++++++++++++++++++++++++++
 7 files changed, 224 insertions(+), 47 deletions(-)
 create mode 100644 drivers/regulator/event.c
 create mode 100644 drivers/regulator/regnl.h
 create mode 100644 include/uapi/regulator/regulator.h

(limited to 'include')

diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig
index f3ec24691378..550145f82726 100644
--- a/drivers/regulator/Kconfig
+++ b/drivers/regulator/Kconfig
@@ -56,6 +56,16 @@ config REGULATOR_USERSPACE_CONSUMER
 
 	  If unsure, say no.
 
+config REGULATOR_NETLINK_EVENTS
+	bool "Enable support for receiving regulator events via netlink"
+	depends on NET
+	help
+	  Enabling this option allows the kernel to broadcast regulator events using
+	  the netlink mechanism. User-space applications can subscribe to these events
+	  for real-time updates on various regulator events.
+
+	  If unsure, say no.
+
 config REGULATOR_88PG86X
 	tristate "Marvell 88PG86X voltage regulators"
 	depends on I2C
diff --git a/drivers/regulator/Makefile b/drivers/regulator/Makefile
index b2b059b5ee56..46fb569e6be8 100644
--- a/drivers/regulator/Makefile
+++ b/drivers/regulator/Makefile
@@ -5,6 +5,7 @@
 
 
 obj-$(CONFIG_REGULATOR) += core.o dummy.o fixed-helper.o helpers.o devres.o irq_helpers.o
+obj-$(CONFIG_REGULATOR_NETLINK_EVENTS) += event.o
 obj-$(CONFIG_OF) += of_regulator.o
 obj-$(CONFIG_REGULATOR_FIXED_VOLTAGE) += fixed.o
 obj-$(CONFIG_REGULATOR_VIRTUAL_CONSUMER) += virtual.o
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 4aa9ec8c22f3..a968dabb48f5 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -33,6 +33,7 @@
 
 #include "dummy.h"
 #include "internal.h"
+#include "regnl.h"
 
 static DEFINE_WW_CLASS(regulator_ww_class);
 static DEFINE_MUTEX(regulator_nesting_mutex);
@@ -4854,7 +4855,23 @@ static int _notifier_call_chain(struct regulator_dev *rdev,
 				  unsigned long event, void *data)
 {
 	/* call rdev chain first */
-	return blocking_notifier_call_chain(&rdev->notifier, event, data);
+	int ret =  blocking_notifier_call_chain(&rdev->notifier, event, data);
+
+	if (IS_REACHABLE(CONFIG_REGULATOR_NETLINK_EVENTS)) {
+		struct device *parent = rdev->dev.parent;
+		const char *rname = rdev_get_name(rdev);
+		char name[32];
+
+		/* Avoid duplicate debugfs directory names */
+		if (parent && rname == rdev->desc->name) {
+			snprintf(name, sizeof(name), "%s-%s", dev_name(parent),
+				 rname);
+			rname = name;
+		}
+		reg_generate_netlink_event(rname, event);
+	}
+
+	return ret;
 }
 
 int _regulator_bulk_get(struct device *dev, int num_consumers,
diff --git a/drivers/regulator/event.c b/drivers/regulator/event.c
new file mode 100644
index 000000000000..0ec58f306b38
--- /dev/null
+++ b/drivers/regulator/event.c
@@ -0,0 +1,91 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Regulator event over netlink
+ *
+ * Author: Naresh Solanki <Naresh.Solanki@9elements.com>
+ */
+
+#include <regulator/regulator.h>
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+#include "regnl.h"
+
+static unsigned int reg_event_seqnum;
+
+static const struct genl_multicast_group reg_event_mcgrps[] = {
+	{ .name = REG_GENL_MCAST_GROUP_NAME, },
+};
+
+static struct genl_family reg_event_genl_family __ro_after_init = {
+	.module = THIS_MODULE,
+	.name = REG_GENL_FAMILY_NAME,
+	.version = REG_GENL_VERSION,
+	.maxattr = REG_GENL_ATTR_MAX,
+	.mcgrps = reg_event_mcgrps,
+	.n_mcgrps = ARRAY_SIZE(reg_event_mcgrps),
+};
+
+int reg_generate_netlink_event(const char *reg_name, u64 event)
+{
+	struct sk_buff *skb;
+	struct nlattr *attr;
+	struct reg_genl_event *edata;
+	void *msg_header;
+	int size;
+
+	/* allocate memory */
+	size = nla_total_size(sizeof(struct reg_genl_event)) +
+	    nla_total_size(0);
+
+	skb = genlmsg_new(size, GFP_ATOMIC);
+	if (!skb)
+		return -ENOMEM;
+
+	/* add the genetlink message header */
+	msg_header = genlmsg_put(skb, 0, reg_event_seqnum++,
+				 &reg_event_genl_family, 0,
+				 REG_GENL_CMD_EVENT);
+	if (!msg_header) {
+		nlmsg_free(skb);
+		return -ENOMEM;
+	}
+
+	/* fill the data */
+	attr = nla_reserve(skb, REG_GENL_ATTR_EVENT, sizeof(struct reg_genl_event));
+	if (!attr) {
+		nlmsg_free(skb);
+		return -EINVAL;
+	}
+
+	edata = nla_data(attr);
+	memset(edata, 0, sizeof(struct reg_genl_event));
+
+	strscpy(edata->reg_name, reg_name, sizeof(edata->reg_name));
+	edata->event = event;
+
+	/* send multicast genetlink message */
+	genlmsg_end(skb, msg_header);
+	size = genlmsg_multicast(&reg_event_genl_family, skb, 0, 0, GFP_ATOMIC);
+
+	return size;
+}
+
+static int __init reg_event_genetlink_init(void)
+{
+	return genl_register_family(&reg_event_genl_family);
+}
+
+static int __init reg_event_init(void)
+{
+	int error;
+
+	/* create genetlink for acpi event */
+	error = reg_event_genetlink_init();
+	if (error)
+		pr_warn("Failed to create genetlink family for reg event\n");
+
+	return 0;
+}
+
+fs_initcall(reg_event_init);
diff --git a/drivers/regulator/regnl.h b/drivers/regulator/regnl.h
new file mode 100644
index 000000000000..bcba16cc05cc
--- /dev/null
+++ b/drivers/regulator/regnl.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Regulator event over netlink
+ *
+ * Author: Naresh Solanki <Naresh.Solanki@9elements.com>
+ */
+
+#ifndef __REGULATOR_EVENT_H
+#define __REGULATOR_EVENT_H
+
+int reg_generate_netlink_event(const char *reg_name, u64 event);
+
+#endif
diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h
index 39b666b40ea6..4660582a3302 100644
--- a/include/linux/regulator/consumer.h
+++ b/include/linux/regulator/consumer.h
@@ -33,6 +33,7 @@
 
 #include <linux/err.h>
 #include <linux/suspend.h>
+#include <regulator/regulator.h>
 
 struct device;
 struct notifier_block;
@@ -84,52 +85,6 @@ struct regulator_dev;
 #define REGULATOR_MODE_IDLE			0x4
 #define REGULATOR_MODE_STANDBY			0x8
 
-/*
- * Regulator notifier events.
- *
- * UNDER_VOLTAGE  Regulator output is under voltage.
- * OVER_CURRENT   Regulator output current is too high.
- * REGULATION_OUT Regulator output is out of regulation.
- * FAIL           Regulator output has failed.
- * OVER_TEMP      Regulator over temp.
- * FORCE_DISABLE  Regulator forcibly shut down by software.
- * VOLTAGE_CHANGE Regulator voltage changed.
- *                Data passed is old voltage cast to (void *).
- * DISABLE        Regulator was disabled.
- * PRE_VOLTAGE_CHANGE   Regulator is about to have voltage changed.
- *                      Data passed is "struct pre_voltage_change_data"
- * ABORT_VOLTAGE_CHANGE Regulator voltage change failed for some reason.
- *                      Data passed is old voltage cast to (void *).
- * PRE_DISABLE    Regulator is about to be disabled
- * ABORT_DISABLE  Regulator disable failed for some reason
- *
- * NOTE: These events can be OR'ed together when passed into handler.
- */
-
-#define REGULATOR_EVENT_UNDER_VOLTAGE		0x01
-#define REGULATOR_EVENT_OVER_CURRENT		0x02
-#define REGULATOR_EVENT_REGULATION_OUT		0x04
-#define REGULATOR_EVENT_FAIL			0x08
-#define REGULATOR_EVENT_OVER_TEMP		0x10
-#define REGULATOR_EVENT_FORCE_DISABLE		0x20
-#define REGULATOR_EVENT_VOLTAGE_CHANGE		0x40
-#define REGULATOR_EVENT_DISABLE			0x80
-#define REGULATOR_EVENT_PRE_VOLTAGE_CHANGE	0x100
-#define REGULATOR_EVENT_ABORT_VOLTAGE_CHANGE	0x200
-#define REGULATOR_EVENT_PRE_DISABLE		0x400
-#define REGULATOR_EVENT_ABORT_DISABLE		0x800
-#define REGULATOR_EVENT_ENABLE			0x1000
-/*
- * Following notifications should be emitted only if detected condition
- * is such that the HW is likely to still be working but consumers should
- * take a recovery action to prevent problems esacalating into errors.
- */
-#define REGULATOR_EVENT_UNDER_VOLTAGE_WARN	0x2000
-#define REGULATOR_EVENT_OVER_CURRENT_WARN	0x4000
-#define REGULATOR_EVENT_OVER_VOLTAGE_WARN	0x8000
-#define REGULATOR_EVENT_OVER_TEMP_WARN		0x10000
-#define REGULATOR_EVENT_WARN_MASK		0x1E000
-
 /*
  * Regulator errors that can be queried using regulator_get_error_flags
  *
diff --git a/include/uapi/regulator/regulator.h b/include/uapi/regulator/regulator.h
new file mode 100644
index 000000000000..d2b5612198b6
--- /dev/null
+++ b/include/uapi/regulator/regulator.h
@@ -0,0 +1,90 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Regulator uapi header
+ *
+ * Author: Naresh Solanki <Naresh.Solanki@9elements.com>
+ */
+
+#ifndef _UAPI_REGULATOR_H
+#define _UAPI_REGULATOR_H
+
+#ifdef __KERNEL__
+#include <linux/types.h>
+#else
+#include <stdint.h>
+#endif
+
+/*
+ * Regulator notifier events.
+ *
+ * UNDER_VOLTAGE  Regulator output is under voltage.
+ * OVER_CURRENT   Regulator output current is too high.
+ * REGULATION_OUT Regulator output is out of regulation.
+ * FAIL           Regulator output has failed.
+ * OVER_TEMP      Regulator over temp.
+ * FORCE_DISABLE  Regulator forcibly shut down by software.
+ * VOLTAGE_CHANGE Regulator voltage changed.
+ *                Data passed is old voltage cast to (void *).
+ * DISABLE        Regulator was disabled.
+ * PRE_VOLTAGE_CHANGE   Regulator is about to have voltage changed.
+ *                      Data passed is "struct pre_voltage_change_data"
+ * ABORT_VOLTAGE_CHANGE Regulator voltage change failed for some reason.
+ *                      Data passed is old voltage cast to (void *).
+ * PRE_DISABLE    Regulator is about to be disabled
+ * ABORT_DISABLE  Regulator disable failed for some reason
+ *
+ * NOTE: These events can be OR'ed together when passed into handler.
+ */
+
+#define REGULATOR_EVENT_UNDER_VOLTAGE		0x01
+#define REGULATOR_EVENT_OVER_CURRENT		0x02
+#define REGULATOR_EVENT_REGULATION_OUT		0x04
+#define REGULATOR_EVENT_FAIL			0x08
+#define REGULATOR_EVENT_OVER_TEMP		0x10
+#define REGULATOR_EVENT_FORCE_DISABLE		0x20
+#define REGULATOR_EVENT_VOLTAGE_CHANGE		0x40
+#define REGULATOR_EVENT_DISABLE			0x80
+#define REGULATOR_EVENT_PRE_VOLTAGE_CHANGE	0x100
+#define REGULATOR_EVENT_ABORT_VOLTAGE_CHANGE	0x200
+#define REGULATOR_EVENT_PRE_DISABLE		0x400
+#define REGULATOR_EVENT_ABORT_DISABLE		0x800
+#define REGULATOR_EVENT_ENABLE			0x1000
+/*
+ * Following notifications should be emitted only if detected condition
+ * is such that the HW is likely to still be working but consumers should
+ * take a recovery action to prevent problems esacalating into errors.
+ */
+#define REGULATOR_EVENT_UNDER_VOLTAGE_WARN	0x2000
+#define REGULATOR_EVENT_OVER_CURRENT_WARN	0x4000
+#define REGULATOR_EVENT_OVER_VOLTAGE_WARN	0x8000
+#define REGULATOR_EVENT_OVER_TEMP_WARN		0x10000
+#define REGULATOR_EVENT_WARN_MASK		0x1E000
+
+struct reg_genl_event {
+	char reg_name[32];
+	uint64_t event;
+};
+
+/* attributes of reg_genl_family */
+enum {
+	REG_GENL_ATTR_UNSPEC,
+	REG_GENL_ATTR_EVENT,	/* reg event info needed by user space */
+	__REG_GENL_ATTR_MAX,
+};
+
+#define REG_GENL_ATTR_MAX (__REG_GENL_ATTR_MAX - 1)
+
+/* commands supported by the reg_genl_family */
+enum {
+	REG_GENL_CMD_UNSPEC,
+	REG_GENL_CMD_EVENT,	/* kernel->user notifications for reg events */
+	__REG_GENL_CMD_MAX,
+};
+
+#define REG_GENL_CMD_MAX (__REG_GENL_CMD_MAX - 1)
+
+#define REG_GENL_FAMILY_NAME		"reg_event"
+#define REG_GENL_VERSION		0x01
+#define REG_GENL_MCAST_GROUP_NAME	"reg_mc_group"
+
+#endif /* _UAPI_REGULATOR_H */
-- 
cgit v1.2.3


From 658902913c7044ac5d56b14cea54e735a071fe41 Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@linaro.org>
Date: Wed, 29 Nov 2023 15:41:01 +0100
Subject: dt-bindings: interconnect: Add Qualcomm SM6115 NoC

Add bindings for Qualcomm SM6115 Network-On-Chip interconnect.

Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231125-topic-6115icc-v3-1-bd8907b8cfd7@linaro.org
Signed-off-by: Georgi Djakov <djakov@kernel.org>
---
 .../bindings/interconnect/qcom,sm6115.yaml         | 152 +++++++++++++++++++++
 include/dt-bindings/interconnect/qcom,sm6115.h     | 111 +++++++++++++++
 2 files changed, 263 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/interconnect/qcom,sm6115.yaml
 create mode 100644 include/dt-bindings/interconnect/qcom,sm6115.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/interconnect/qcom,sm6115.yaml b/Documentation/devicetree/bindings/interconnect/qcom,sm6115.yaml
new file mode 100644
index 000000000000..14b1a0b08e73
--- /dev/null
+++ b/Documentation/devicetree/bindings/interconnect/qcom,sm6115.yaml
@@ -0,0 +1,152 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/interconnect/qcom,sm6115.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm SM6115 Network-On-Chip interconnect
+
+maintainers:
+  - Konrad Dybcio <konradybcio@kernel.org>
+
+description:
+  The Qualcomm SM6115 interconnect providers support adjusting the
+  bandwidth requirements between the various NoC fabrics.
+
+properties:
+  compatible:
+    enum:
+      - qcom,sm6115-bimc
+      - qcom,sm6115-cnoc
+      - qcom,sm6115-snoc
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    minItems: 1
+    maxItems: 4
+
+  clock-names:
+    minItems: 1
+    maxItems: 4
+
+# Child node's properties
+patternProperties:
+  '^interconnect-[a-z0-9]+$':
+    type: object
+    description:
+      The interconnect providers do not have a separate QoS register space,
+      but share parent's space.
+
+    $ref: qcom,rpm-common.yaml#
+
+    properties:
+      compatible:
+        enum:
+          - qcom,sm6115-clk-virt
+          - qcom,sm6115-mmrt-virt
+          - qcom,sm6115-mmnrt-virt
+
+    required:
+      - compatible
+
+    unevaluatedProperties: false
+
+required:
+  - compatible
+  - reg
+
+allOf:
+  - $ref: qcom,rpm-common.yaml#
+  - if:
+      properties:
+        compatible:
+          const: qcom,sm6115-cnoc
+
+    then:
+      properties:
+        clocks:
+          items:
+            - description: USB-NoC AXI clock
+
+        clock-names:
+          items:
+            - const: usb_axi
+
+  - if:
+      properties:
+        compatible:
+          const: qcom,sm6115-snoc
+
+    then:
+      properties:
+        clocks:
+          items:
+            - description: CPU-NoC AXI clock.
+            - description: UFS-NoC AXI clock.
+            - description: USB-NoC AXI clock.
+            - description: IPA clock.
+
+        clock-names:
+          items:
+            - const: cpu_axi
+            - const: ufs_axi
+            - const: usb_axi
+            - const: ipa
+
+  - if:
+      properties:
+        compatible:
+          enum:
+            - qcom,sm6115-bimc
+            - qcom,sm6115-clk-virt
+            - qcom,sm6115-mmrt-virt
+            - qcom,sm6115-mmnrt-virt
+
+    then:
+      properties:
+        clocks: false
+        clock-names: false
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/qcom,gcc-sm6115.h>
+    #include <dt-bindings/clock/qcom,rpmcc.h>
+
+    snoc: interconnect@1880000 {
+        compatible = "qcom,sm6115-snoc";
+        reg = <0x01880000 0x60200>;
+        clocks = <&gcc GCC_SYS_NOC_CPUSS_AHB_CLK>,
+                 <&gcc GCC_SYS_NOC_UFS_PHY_AXI_CLK>,
+                 <&gcc GCC_SYS_NOC_USB3_PRIM_AXI_CLK>,
+                 <&rpmcc RPM_SMD_IPA_CLK>;
+        clock-names = "cpu_axi",
+                      "ufs_axi",
+                      "usb_axi",
+                      "ipa";
+        #interconnect-cells = <1>;
+
+        qup_virt: interconnect-clk {
+            compatible = "qcom,sm6115-clk-virt";
+            #interconnect-cells = <1>;
+        };
+
+        mmnrt_virt: interconnect-mmnrt {
+            compatible = "qcom,sm6115-mmnrt-virt";
+            #interconnect-cells = <1>;
+        };
+
+        mmrt_virt: interconnect-mmrt {
+            compatible = "qcom,sm6115-mmrt-virt";
+            #interconnect-cells = <1>;
+        };
+    };
+
+    cnoc: interconnect@1900000 {
+        compatible = "qcom,sm6115-cnoc";
+        reg = <0x01900000 0x8200>;
+        #interconnect-cells = <1>;
+    };
diff --git a/include/dt-bindings/interconnect/qcom,sm6115.h b/include/dt-bindings/interconnect/qcom,sm6115.h
new file mode 100644
index 000000000000..21090e585f05
--- /dev/null
+++ b/include/dt-bindings/interconnect/qcom,sm6115.h
@@ -0,0 +1,111 @@
+/* SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause */
+/*
+ * Copyright (c) 2020, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#ifndef __DT_BINDINGS_INTERCONNECT_QCOM_SM6115_H
+#define __DT_BINDINGS_INTERCONNECT_QCOM_SM6115_H
+
+/* BIMC */
+#define MASTER_AMPSS_M0				0
+#define MASTER_SNOC_BIMC_RT			1
+#define MASTER_SNOC_BIMC_NRT			2
+#define SNOC_BIMC_MAS				3
+#define MASTER_GRAPHICS_3D			4
+#define MASTER_TCU_0				5
+#define SLAVE_EBI_CH0				6
+#define BIMC_SNOC_SLV				7
+
+/* CNOC */
+#define SNOC_CNOC_MAS				0
+#define MASTER_QDSS_DAP				1
+#define SLAVE_AHB2PHY_USB			2
+#define SLAVE_APSS_THROTTLE_CFG			3
+#define SLAVE_BIMC_CFG				4
+#define SLAVE_BOOT_ROM				5
+#define SLAVE_CAMERA_NRT_THROTTLE_CFG		6
+#define SLAVE_CAMERA_RT_THROTTLE_CFG		7
+#define SLAVE_CAMERA_CFG			8
+#define SLAVE_CLK_CTL				9
+#define SLAVE_RBCPR_CX_CFG			10
+#define SLAVE_RBCPR_MX_CFG			11
+#define SLAVE_CRYPTO_0_CFG			12
+#define SLAVE_DCC_CFG				13
+#define SLAVE_DDR_PHY_CFG			14
+#define SLAVE_DDR_SS_CFG			15
+#define SLAVE_DISPLAY_CFG			16
+#define SLAVE_DISPLAY_THROTTLE_CFG		17
+#define SLAVE_GPU_CFG				18
+#define SLAVE_GPU_THROTTLE_CFG			19
+#define SLAVE_HWKM_CORE				20
+#define SLAVE_IMEM_CFG				21
+#define SLAVE_IPA_CFG				22
+#define SLAVE_LPASS				23
+#define SLAVE_MAPSS				24
+#define SLAVE_MDSP_MPU_CFG			25
+#define SLAVE_MESSAGE_RAM			26
+#define SLAVE_CNOC_MSS				27
+#define SLAVE_PDM				28
+#define SLAVE_PIMEM_CFG				29
+#define SLAVE_PKA_CORE				30
+#define SLAVE_PMIC_ARB				31
+#define SLAVE_QDSS_CFG				32
+#define SLAVE_QM_CFG				33
+#define SLAVE_QM_MPU_CFG			34
+#define SLAVE_QPIC				35
+#define SLAVE_QUP_0				36
+#define SLAVE_RPM				37
+#define SLAVE_SDCC_1				38
+#define SLAVE_SDCC_2				39
+#define SLAVE_SECURITY				40
+#define SLAVE_SNOC_CFG				41
+#define SLAVE_TCSR				42
+#define SLAVE_TLMM				43
+#define SLAVE_USB3				44
+#define SLAVE_VENUS_CFG				45
+#define SLAVE_VENUS_THROTTLE_CFG		46
+#define SLAVE_VSENSE_CTRL_CFG			47
+#define SLAVE_SERVICE_CNOC			48
+
+/* SNOC */
+#define MASTER_CRYPTO_CORE0			0
+#define MASTER_SNOC_CFG				1
+#define MASTER_TIC				2
+#define MASTER_ANOC_SNOC			3
+#define BIMC_SNOC_MAS				4
+#define MASTER_PIMEM				5
+#define MASTER_QDSS_BAM				6
+#define MASTER_QPIC				7
+#define MASTER_QUP_0				8
+#define MASTER_IPA				9
+#define MASTER_QDSS_ETR				10
+#define MASTER_SDCC_1				11
+#define MASTER_SDCC_2				12
+#define MASTER_USB3				13
+#define SLAVE_APPSS				14
+#define SNOC_CNOC_SLV				15
+#define SLAVE_OCIMEM				16
+#define SLAVE_PIMEM				17
+#define SNOC_BIMC_SLV				18
+#define SLAVE_SERVICE_SNOC			19
+#define SLAVE_QDSS_STM				20
+#define SLAVE_TCU				21
+#define SLAVE_ANOC_SNOC				22
+
+/* CLK Virtual */
+#define MASTER_QUP_CORE_0			0
+#define SLAVE_QUP_CORE_0			1
+
+/* MMRT Virtual */
+#define MASTER_CAMNOC_HF			0
+#define MASTER_MDP_PORT0			1
+#define SLAVE_SNOC_BIMC_RT			2
+
+/* MMNRT Virtual */
+#define MASTER_CAMNOC_SF			0
+#define MASTER_VIDEO_P0				1
+#define MASTER_VIDEO_PROC			2
+#define SLAVE_SNOC_BIMC_NRT			3
+
+#endif
-- 
cgit v1.2.3


From 15bece7bec0df91a8ed1c185483d67708425ca8e Mon Sep 17 00:00:00 2001
From: Zenghui Yu <yuzenghui@huawei.com>
Date: Fri, 24 Nov 2023 20:16:15 +0800
Subject: cpu/hotplug: Remove unused CPU hotplug states

There are unused hotplug states which either have never been used or the
removal of the usage did not remove the state constant.

Drop them to reduce the size of the cpuhp_hp_states array.

Signed-off-by: Zenghui Yu <yuzenghui@huawei.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20231124121615.1604-1-yuzenghui@huawei.com
---
 include/linux/cpuhotplug.h | 14 --------------
 1 file changed, 14 deletions(-)

(limited to 'include')

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index efc0c0b07efb..af6c21aab985 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -66,15 +66,12 @@ enum cpuhp_state {
 	CPUHP_PERF_POWER,
 	CPUHP_PERF_SUPERH,
 	CPUHP_X86_HPET_DEAD,
-	CPUHP_X86_APB_DEAD,
 	CPUHP_X86_MCE_DEAD,
 	CPUHP_VIRT_NET_DEAD,
 	CPUHP_IBMVNIC_DEAD,
 	CPUHP_SLUB_DEAD,
 	CPUHP_DEBUG_OBJ_DEAD,
 	CPUHP_MM_WRITEBACK_DEAD,
-	/* Must be after CPUHP_MM_VMSTAT_DEAD */
-	CPUHP_MM_DEMOTION_DEAD,
 	CPUHP_MM_VMSTAT_DEAD,
 	CPUHP_SOFTIRQ_DEAD,
 	CPUHP_NET_MVNETA_DEAD,
@@ -96,7 +93,6 @@ enum cpuhp_state {
 	CPUHP_NET_DEV_DEAD,
 	CPUHP_PCI_XGENE_DEAD,
 	CPUHP_IOMMU_IOVA_DEAD,
-	CPUHP_LUSTRE_CFS_DEAD,
 	CPUHP_AP_ARM_CACHE_B15_RAC_DEAD,
 	CPUHP_PADATA_DEAD,
 	CPUHP_AP_DTPM_CPU_DEAD,
@@ -118,7 +114,6 @@ enum cpuhp_state {
 	CPUHP_XEN_EVTCHN_PREPARE,
 	CPUHP_ARM_SHMOBILE_SCU_PREPARE,
 	CPUHP_SH_SH3X_PREPARE,
-	CPUHP_NET_FLOW_PREPARE,
 	CPUHP_TOPOLOGY_PREPARE,
 	CPUHP_NET_IUCV_PREPARE,
 	CPUHP_ARM_BL_PREPARE,
@@ -151,18 +146,14 @@ enum cpuhp_state {
 	CPUHP_AP_IRQ_ARMADA_XP_STARTING,
 	CPUHP_AP_IRQ_BCM2836_STARTING,
 	CPUHP_AP_IRQ_MIPS_GIC_STARTING,
-	CPUHP_AP_IRQ_RISCV_STARTING,
 	CPUHP_AP_IRQ_LOONGARCH_STARTING,
 	CPUHP_AP_IRQ_SIFIVE_PLIC_STARTING,
 	CPUHP_AP_ARM_MVEBU_COHERENCY,
-	CPUHP_AP_MICROCODE_LOADER,
 	CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING,
 	CPUHP_AP_PERF_X86_STARTING,
 	CPUHP_AP_PERF_X86_AMD_IBS_STARTING,
-	CPUHP_AP_PERF_X86_CQM_STARTING,
 	CPUHP_AP_PERF_X86_CSTATE_STARTING,
 	CPUHP_AP_PERF_XTENSA_STARTING,
-	CPUHP_AP_MIPS_OP_LOONGSON3_STARTING,
 	CPUHP_AP_ARM_VFP_STARTING,
 	CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING,
 	CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING,
@@ -179,7 +170,6 @@ enum cpuhp_state {
 	CPUHP_AP_QCOM_TIMER_STARTING,
 	CPUHP_AP_TEGRA_TIMER_STARTING,
 	CPUHP_AP_ARMADA_TIMER_STARTING,
-	CPUHP_AP_MARCO_TIMER_STARTING,
 	CPUHP_AP_MIPS_GIC_TIMER_STARTING,
 	CPUHP_AP_ARC_TIMER_STARTING,
 	CPUHP_AP_RISCV_TIMER_STARTING,
@@ -217,9 +207,7 @@ enum cpuhp_state {
 	CPUHP_AP_PERF_X86_AMD_UNCORE_ONLINE,
 	CPUHP_AP_PERF_X86_AMD_POWER_ONLINE,
 	CPUHP_AP_PERF_X86_RAPL_ONLINE,
-	CPUHP_AP_PERF_X86_CQM_ONLINE,
 	CPUHP_AP_PERF_X86_CSTATE_ONLINE,
-	CPUHP_AP_PERF_X86_IDXD_ONLINE,
 	CPUHP_AP_PERF_S390_CF_ONLINE,
 	CPUHP_AP_PERF_S390_SF_ONLINE,
 	CPUHP_AP_PERF_ARM_CCI_ONLINE,
@@ -252,8 +240,6 @@ enum cpuhp_state {
 	CPUHP_AP_BASE_CACHEINFO_ONLINE,
 	CPUHP_AP_ONLINE_DYN,
 	CPUHP_AP_ONLINE_DYN_END		= CPUHP_AP_ONLINE_DYN + 30,
-	/* Must be after CPUHP_AP_ONLINE_DYN for node_states[N_CPU] update */
-	CPUHP_AP_MM_DEMOTION_ONLINE,
 	CPUHP_AP_X86_HPET_ONLINE,
 	CPUHP_AP_X86_KVM_CLK_ONLINE,
 	CPUHP_AP_ACTIVE,
-- 
cgit v1.2.3


From 57b8543ceee82ea72be1745a6dc3a9111d55a151 Mon Sep 17 00:00:00 2001
From: Raag Jadav <raag.jadav@intel.com>
Date: Thu, 23 Nov 2023 15:36:13 +0530
Subject: ACPI: bus: update acpi_dev_uid_match() to support multiple types

According to the ACPI specification, a _UID object can evaluate to
either a numeric value or a string.

Update acpi_dev_uid_match() to support _UID matching for both integer
and string types.

Suggested-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Raag Jadav <raag.jadav@intel.com>
[ rjw: Rename auxiliary macros, relocate kerneldoc comment ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/utils.c    | 19 -------------------
 include/acpi/acpi_bus.h | 41 ++++++++++++++++++++++++++++++++++++++++-
 include/linux/acpi.h    |  8 +++-----
 3 files changed, 43 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c
index 28c75242fca9..fe7e850c6479 100644
--- a/drivers/acpi/utils.c
+++ b/drivers/acpi/utils.c
@@ -824,25 +824,6 @@ bool acpi_check_dsm(acpi_handle handle, const guid_t *guid, u64 rev, u64 funcs)
 }
 EXPORT_SYMBOL(acpi_check_dsm);
 
-/**
- * acpi_dev_uid_match - Match device by supplied UID
- * @adev: ACPI device to match.
- * @uid2: Unique ID of the device.
- *
- * Matches UID in @adev with given @uid2.
- *
- * Returns:
- *  - %true if matches.
- *  - %false otherwise.
- */
-bool acpi_dev_uid_match(struct acpi_device *adev, const char *uid2)
-{
-	const char *uid1 = acpi_device_uid(adev);
-
-	return uid1 && uid2 && !strcmp(uid1, uid2);
-}
-EXPORT_SYMBOL_GPL(acpi_dev_uid_match);
-
 /**
  * acpi_dev_hid_uid_match - Match device by supplied HID and UID
  * @adev: ACPI device to match.
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 1216d72c650f..4bde0b417476 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -764,10 +764,49 @@ static inline bool acpi_device_can_poweroff(struct acpi_device *adev)
 		adev->power.states[ACPI_STATE_D3_HOT].flags.explicit_set);
 }
 
-bool acpi_dev_uid_match(struct acpi_device *adev, const char *uid2);
 bool acpi_dev_hid_uid_match(struct acpi_device *adev, const char *hid2, const char *uid2);
 int acpi_dev_uid_to_integer(struct acpi_device *adev, u64 *integer);
 
+static inline bool acpi_str_uid_match(struct acpi_device *adev, const char *uid2)
+{
+	const char *uid1 = acpi_device_uid(adev);
+
+	return uid1 && uid2 && !strcmp(uid1, uid2);
+}
+
+static inline bool acpi_int_uid_match(struct acpi_device *adev, u64 uid2)
+{
+	u64 uid1;
+
+	return !acpi_dev_uid_to_integer(adev, &uid1) && uid1 == uid2;
+}
+
+#define TYPE_ENTRY(type, x)			\
+	const type: x,				\
+	type: x
+
+#define ACPI_STR_TYPES(match)			\
+	TYPE_ENTRY(unsigned char *, match),	\
+	TYPE_ENTRY(signed char *, match),		\
+	TYPE_ENTRY(char *, match),		\
+	TYPE_ENTRY(void *, match)
+
+/**
+ * acpi_dev_uid_match - Match device by supplied UID
+ * @adev: ACPI device to match.
+ * @uid2: Unique ID of the device.
+ *
+ * Matches UID in @adev with given @uid2.
+ *
+ * Returns: %true if matches, %false otherwise.
+ */
+#define acpi_dev_uid_match(adev, uid2)					\
+	_Generic(uid2,							\
+		 /* Treat @uid2 as a string for acpi string types */	\
+		 ACPI_STR_TYPES(acpi_str_uid_match),			\
+		 /* Treat as an integer otherwise */			\
+		 default: acpi_int_uid_match)(adev, uid2)
+
 void acpi_dev_clear_dependencies(struct acpi_device *supplier);
 bool acpi_dev_ready_for_enumeration(const struct acpi_device *device);
 struct acpi_device *acpi_dev_get_next_consumer_dev(struct acpi_device *supplier,
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 4db54e928b36..2abe81f074de 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -756,6 +756,9 @@ const char *acpi_get_subsystem_id(acpi_handle handle);
 #define ACPI_HANDLE(dev)		(NULL)
 #define ACPI_HANDLE_FWNODE(fwnode)	(NULL)
 
+/* Get rid of the -Wunused-variable for adev */
+#define acpi_dev_uid_match(adev, uid2)			(adev && false)
+
 #include <acpi/acpi_numa.h>
 
 struct fwnode_handle;
@@ -772,11 +775,6 @@ static inline bool acpi_dev_present(const char *hid, const char *uid, s64 hrv)
 
 struct acpi_device;
 
-static inline bool acpi_dev_uid_match(struct acpi_device *adev, const char *uid2)
-{
-	return false;
-}
-
 static inline bool
 acpi_dev_hid_uid_match(struct acpi_device *adev, const char *hid2, const char *uid2)
 {
-- 
cgit v1.2.3


From b2b32a1738815155d4a0039bb7a6092d40f23e81 Mon Sep 17 00:00:00 2001
From: Raag Jadav <raag.jadav@intel.com>
Date: Thu, 23 Nov 2023 15:36:14 +0530
Subject: ACPI: bus: update acpi_dev_hid_uid_match() to support multiple types

Now that we have _UID matching support for both integer and string types,
we can support them into acpi_dev_hid_uid_match() helper as well.

Signed-off-by: Raag Jadav <raag.jadav@intel.com>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/utils.c    | 29 -----------------------------
 include/acpi/acpi_bus.h | 24 +++++++++++++++++++++++-
 include/linux/acpi.h    |  7 +------
 3 files changed, 24 insertions(+), 36 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c
index fe7e850c6479..03f6de9a0807 100644
--- a/drivers/acpi/utils.c
+++ b/drivers/acpi/utils.c
@@ -824,35 +824,6 @@ bool acpi_check_dsm(acpi_handle handle, const guid_t *guid, u64 rev, u64 funcs)
 }
 EXPORT_SYMBOL(acpi_check_dsm);
 
-/**
- * acpi_dev_hid_uid_match - Match device by supplied HID and UID
- * @adev: ACPI device to match.
- * @hid2: Hardware ID of the device.
- * @uid2: Unique ID of the device, pass NULL to not check _UID.
- *
- * Matches HID and UID in @adev with given @hid2 and @uid2. Absence of @uid2
- * will be treated as a match. If user wants to validate @uid2, it should be
- * done before calling this function.
- *
- * Returns:
- *  - %true if matches or @uid2 is NULL.
- *  - %false otherwise.
- */
-bool acpi_dev_hid_uid_match(struct acpi_device *adev,
-			    const char *hid2, const char *uid2)
-{
-	const char *hid1 = acpi_device_hid(adev);
-
-	if (strcmp(hid1, hid2))
-		return false;
-
-	if (!uid2)
-		return true;
-
-	return acpi_dev_uid_match(adev, uid2);
-}
-EXPORT_SYMBOL(acpi_dev_hid_uid_match);
-
 /**
  * acpi_dev_uid_to_integer - treat ACPI device _UID as integer
  * @adev: ACPI device to get _UID from
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 4bde0b417476..aae31552c574 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -764,9 +764,15 @@ static inline bool acpi_device_can_poweroff(struct acpi_device *adev)
 		adev->power.states[ACPI_STATE_D3_HOT].flags.explicit_set);
 }
 
-bool acpi_dev_hid_uid_match(struct acpi_device *adev, const char *hid2, const char *uid2);
 int acpi_dev_uid_to_integer(struct acpi_device *adev, u64 *integer);
 
+static inline bool acpi_dev_hid_match(struct acpi_device *adev, const char *hid2)
+{
+	const char *hid1 = acpi_device_hid(adev);
+
+	return hid1 && hid2 && !strcmp(hid1, hid2);
+}
+
 static inline bool acpi_str_uid_match(struct acpi_device *adev, const char *uid2)
 {
 	const char *uid1 = acpi_device_uid(adev);
@@ -807,6 +813,22 @@ static inline bool acpi_int_uid_match(struct acpi_device *adev, u64 uid2)
 		 /* Treat as an integer otherwise */			\
 		 default: acpi_int_uid_match)(adev, uid2)
 
+/**
+ * acpi_dev_hid_uid_match - Match device by supplied HID and UID
+ * @adev: ACPI device to match.
+ * @hid2: Hardware ID of the device.
+ * @uid2: Unique ID of the device, pass 0 or NULL to not check _UID.
+ *
+ * Matches HID and UID in @adev with given @hid2 and @uid2. Absence of @uid2
+ * will be treated as a match. If user wants to validate @uid2, it should be
+ * done before calling this function.
+ *
+ * Returns: %true if matches or @uid2 is 0 or NULL, %false otherwise.
+ */
+#define acpi_dev_hid_uid_match(adev, hid2, uid2)			\
+	(acpi_dev_hid_match(adev, hid2) &&				\
+		(!(uid2) || acpi_dev_uid_match(adev, uid2)))
+
 void acpi_dev_clear_dependencies(struct acpi_device *supplier);
 bool acpi_dev_ready_for_enumeration(const struct acpi_device *device);
 struct acpi_device *acpi_dev_get_next_consumer_dev(struct acpi_device *supplier,
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 2abe81f074de..75274585656c 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -758,6 +758,7 @@ const char *acpi_get_subsystem_id(acpi_handle handle);
 
 /* Get rid of the -Wunused-variable for adev */
 #define acpi_dev_uid_match(adev, uid2)			(adev && false)
+#define acpi_dev_hid_uid_match(adev, hid2, uid2)	(adev && false)
 
 #include <acpi/acpi_numa.h>
 
@@ -775,12 +776,6 @@ static inline bool acpi_dev_present(const char *hid, const char *uid, s64 hrv)
 
 struct acpi_device;
 
-static inline bool
-acpi_dev_hid_uid_match(struct acpi_device *adev, const char *hid2, const char *uid2)
-{
-	return false;
-}
-
 static inline int acpi_dev_uid_to_integer(struct acpi_device *adev, u64 *integer)
 {
 	return -ENODEV;
-- 
cgit v1.2.3


From 40bba140c60fbb3ee8df6203c82fbd3de9f19d95 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Thu, 30 Nov 2023 10:52:14 -0800
Subject: bpf: add BPF token delegation mount options to BPF FS

Add few new mount options to BPF FS that allow to specify that a given
BPF FS instance allows creation of BPF token (added in the next patch),
and what sort of operations are allowed under BPF token. As such, we get
4 new mount options, each is a bit mask
  - `delegate_cmds` allow to specify which bpf() syscall commands are
    allowed with BPF token derived from this BPF FS instance;
  - if BPF_MAP_CREATE command is allowed, `delegate_maps` specifies
    a set of allowable BPF map types that could be created with BPF token;
  - if BPF_PROG_LOAD command is allowed, `delegate_progs` specifies
    a set of allowable BPF program types that could be loaded with BPF token;
  - if BPF_PROG_LOAD command is allowed, `delegate_attachs` specifies
    a set of allowable BPF program attach types that could be loaded with
    BPF token; delegate_progs and delegate_attachs are meant to be used
    together, as full BPF program type is, in general, determined
    through both program type and program attach type.

Currently, these mount options accept the following forms of values:
  - a special value "any", that enables all possible values of a given
  bit set;
  - numeric value (decimal or hexadecimal, determined by kernel
  automatically) that specifies a bit mask value directly;
  - all the values for a given mount option are combined, if specified
  multiple times. E.g., `mount -t bpf nodev /path/to/mount -o
  delegate_maps=0x1 -o delegate_maps=0x2` will result in a combined 0x3
  mask.

Ideally, more convenient (for humans) symbolic form derived from
corresponding UAPI enums would be accepted (e.g., `-o
delegate_progs=kprobe|tracepoint`) and I intend to implement this, but
it requires a bunch of UAPI header churn, so I postponed it until this
feature lands upstream or at least there is a definite consensus that
this feature is acceptable and is going to make it, just to minimize
amount of wasted effort and not increase amount of non-essential code to
be reviewed.

Attentive reader will notice that BPF FS is now marked as
FS_USERNS_MOUNT, which theoretically makes it mountable inside non-init
user namespace as long as the process has sufficient *namespaced*
capabilities within that user namespace. But in reality we still
restrict BPF FS to be mountable only by processes with CAP_SYS_ADMIN *in
init userns* (extra check in bpf_fill_super()). FS_USERNS_MOUNT is added
to allow creating BPF FS context object (i.e., fsopen("bpf")) from
inside unprivileged process inside non-init userns, to capture that
userns as the owning userns. It will still be required to pass this
context object back to privileged process to instantiate and mount it.

This manipulation is important, because capturing non-init userns as the
owning userns of BPF FS instance (super block) allows to use that userns
to constraint BPF token to that userns later on (see next patch). So
creating BPF FS with delegation inside unprivileged userns will restrict
derived BPF token objects to only "work" inside that intended userns,
making it scoped to a intended "container". Also, setting these
delegation options requires capable(CAP_SYS_ADMIN), so unprivileged
process cannot set this up without involvement of a privileged process.

There is a set of selftests at the end of the patch set that simulates
this sequence of steps and validates that everything works as intended.
But careful review is requested to make sure there are no missed gaps in
the implementation and testing.

This somewhat subtle set of aspects is the result of previous
discussions ([0]) about various user namespace implications and
interactions with BPF token functionality and is necessary to contain
BPF token inside intended user namespace.

  [0] https://lore.kernel.org/bpf/20230704-hochverdient-lehne-eeb9eeef785e@brauner/

Acked-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20231130185229.2688956-3-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h | 10 ++++++
 kernel/bpf/inode.c  | 88 +++++++++++++++++++++++++++++++++++++++++++++++------
 2 files changed, 88 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 10e5e4d8a00f..d3c9acc593ea 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1581,6 +1581,16 @@ struct bpf_link_primer {
 	u32 id;
 };
 
+struct bpf_mount_opts {
+	umode_t mode;
+
+	/* BPF token-related delegation options */
+	u64 delegate_cmds;
+	u64 delegate_maps;
+	u64 delegate_progs;
+	u64 delegate_attachs;
+};
+
 struct bpf_struct_ops_value;
 struct btf_member;
 
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 1aafb2ff2e95..220fe0f99095 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -20,6 +20,7 @@
 #include <linux/filter.h>
 #include <linux/bpf.h>
 #include <linux/bpf_trace.h>
+#include <linux/kstrtox.h>
 #include "preload/bpf_preload.h"
 
 enum bpf_type {
@@ -599,10 +600,31 @@ EXPORT_SYMBOL(bpf_prog_get_type_path);
  */
 static int bpf_show_options(struct seq_file *m, struct dentry *root)
 {
+	struct bpf_mount_opts *opts = root->d_sb->s_fs_info;
 	umode_t mode = d_inode(root)->i_mode & S_IALLUGO & ~S_ISVTX;
 
 	if (mode != S_IRWXUGO)
 		seq_printf(m, ",mode=%o", mode);
+
+	if (opts->delegate_cmds == ~0ULL)
+		seq_printf(m, ",delegate_cmds=any");
+	else if (opts->delegate_cmds)
+		seq_printf(m, ",delegate_cmds=0x%llx", opts->delegate_cmds);
+
+	if (opts->delegate_maps == ~0ULL)
+		seq_printf(m, ",delegate_maps=any");
+	else if (opts->delegate_maps)
+		seq_printf(m, ",delegate_maps=0x%llx", opts->delegate_maps);
+
+	if (opts->delegate_progs == ~0ULL)
+		seq_printf(m, ",delegate_progs=any");
+	else if (opts->delegate_progs)
+		seq_printf(m, ",delegate_progs=0x%llx", opts->delegate_progs);
+
+	if (opts->delegate_attachs == ~0ULL)
+		seq_printf(m, ",delegate_attachs=any");
+	else if (opts->delegate_attachs)
+		seq_printf(m, ",delegate_attachs=0x%llx", opts->delegate_attachs);
 	return 0;
 }
 
@@ -626,22 +648,27 @@ static const struct super_operations bpf_super_ops = {
 
 enum {
 	OPT_MODE,
+	OPT_DELEGATE_CMDS,
+	OPT_DELEGATE_MAPS,
+	OPT_DELEGATE_PROGS,
+	OPT_DELEGATE_ATTACHS,
 };
 
 static const struct fs_parameter_spec bpf_fs_parameters[] = {
 	fsparam_u32oct	("mode",			OPT_MODE),
+	fsparam_string	("delegate_cmds",		OPT_DELEGATE_CMDS),
+	fsparam_string	("delegate_maps",		OPT_DELEGATE_MAPS),
+	fsparam_string	("delegate_progs",		OPT_DELEGATE_PROGS),
+	fsparam_string	("delegate_attachs",		OPT_DELEGATE_ATTACHS),
 	{}
 };
 
-struct bpf_mount_opts {
-	umode_t mode;
-};
-
 static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param)
 {
-	struct bpf_mount_opts *opts = fc->fs_private;
+	struct bpf_mount_opts *opts = fc->s_fs_info;
 	struct fs_parse_result result;
-	int opt;
+	int opt, err;
+	u64 msk;
 
 	opt = fs_parse(fc, bpf_fs_parameters, param, &result);
 	if (opt < 0) {
@@ -665,6 +692,28 @@ static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param)
 	case OPT_MODE:
 		opts->mode = result.uint_32 & S_IALLUGO;
 		break;
+	case OPT_DELEGATE_CMDS:
+	case OPT_DELEGATE_MAPS:
+	case OPT_DELEGATE_PROGS:
+	case OPT_DELEGATE_ATTACHS:
+		if (strcmp(param->string, "any") == 0) {
+			msk = ~0ULL;
+		} else {
+			err = kstrtou64(param->string, 0, &msk);
+			if (err)
+				return err;
+		}
+		/* Setting delegation mount options requires privileges */
+		if (msk && !capable(CAP_SYS_ADMIN))
+			return -EPERM;
+		switch (opt) {
+		case OPT_DELEGATE_CMDS: opts->delegate_cmds |= msk; break;
+		case OPT_DELEGATE_MAPS: opts->delegate_maps |= msk; break;
+		case OPT_DELEGATE_PROGS: opts->delegate_progs |= msk; break;
+		case OPT_DELEGATE_ATTACHS: opts->delegate_attachs |= msk; break;
+		default: return -EINVAL;
+		}
+		break;
 	}
 
 	return 0;
@@ -739,10 +788,14 @@ out:
 static int bpf_fill_super(struct super_block *sb, struct fs_context *fc)
 {
 	static const struct tree_descr bpf_rfiles[] = { { "" } };
-	struct bpf_mount_opts *opts = fc->fs_private;
+	struct bpf_mount_opts *opts = sb->s_fs_info;
 	struct inode *inode;
 	int ret;
 
+	/* Mounting an instance of BPF FS requires privileges */
+	if (fc->user_ns != &init_user_ns && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	ret = simple_fill_super(sb, BPF_FS_MAGIC, bpf_rfiles);
 	if (ret)
 		return ret;
@@ -764,7 +817,7 @@ static int bpf_get_tree(struct fs_context *fc)
 
 static void bpf_free_fc(struct fs_context *fc)
 {
-	kfree(fc->fs_private);
+	kfree(fc->s_fs_info);
 }
 
 static const struct fs_context_operations bpf_context_ops = {
@@ -786,17 +839,32 @@ static int bpf_init_fs_context(struct fs_context *fc)
 
 	opts->mode = S_IRWXUGO;
 
-	fc->fs_private = opts;
+	/* start out with no BPF token delegation enabled */
+	opts->delegate_cmds = 0;
+	opts->delegate_maps = 0;
+	opts->delegate_progs = 0;
+	opts->delegate_attachs = 0;
+
+	fc->s_fs_info = opts;
 	fc->ops = &bpf_context_ops;
 	return 0;
 }
 
+static void bpf_kill_super(struct super_block *sb)
+{
+	struct bpf_mount_opts *opts = sb->s_fs_info;
+
+	kill_litter_super(sb);
+	kfree(opts);
+}
+
 static struct file_system_type bpf_fs_type = {
 	.owner		= THIS_MODULE,
 	.name		= "bpf",
 	.init_fs_context = bpf_init_fs_context,
 	.parameters	= bpf_fs_parameters,
-	.kill_sb	= kill_litter_super,
+	.kill_sb	= bpf_kill_super,
+	.fs_flags	= FS_USERNS_MOUNT,
 };
 
 static int __init bpf_init(void)
-- 
cgit v1.2.3


From 4527358b76861dfd64ee34aba45d81648fbc8a61 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Thu, 30 Nov 2023 10:52:15 -0800
Subject: bpf: introduce BPF token object

Add new kind of BPF kernel object, BPF token. BPF token is meant to
allow delegating privileged BPF functionality, like loading a BPF
program or creating a BPF map, from privileged process to a *trusted*
unprivileged process, all while having a good amount of control over which
privileged operations could be performed using provided BPF token.

This is achieved through mounting BPF FS instance with extra delegation
mount options, which determine what operations are delegatable, and also
constraining it to the owning user namespace (as mentioned in the
previous patch).

BPF token itself is just a derivative from BPF FS and can be created
through a new bpf() syscall command, BPF_TOKEN_CREATE, which accepts BPF
FS FD, which can be attained through open() API by opening BPF FS mount
point. Currently, BPF token "inherits" delegated command, map types,
prog type, and attach type bit sets from BPF FS as is. In the future,
having an BPF token as a separate object with its own FD, we can allow
to further restrict BPF token's allowable set of things either at the
creation time or after the fact, allowing the process to guard itself
further from unintentionally trying to load undesired kind of BPF
programs. But for now we keep things simple and just copy bit sets as is.

When BPF token is created from BPF FS mount, we take reference to the
BPF super block's owning user namespace, and then use that namespace for
checking all the {CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN, CAP_SYS_ADMIN}
capabilities that are normally only checked against init userns (using
capable()), but now we check them using ns_capable() instead (if BPF
token is provided). See bpf_token_capable() for details.

Such setup means that BPF token in itself is not sufficient to grant BPF
functionality. User namespaced process has to *also* have necessary
combination of capabilities inside that user namespace. So while
previously CAP_BPF was useless when granted within user namespace, now
it gains a meaning and allows container managers and sys admins to have
a flexible control over which processes can and need to use BPF
functionality within the user namespace (i.e., container in practice).
And BPF FS delegation mount options and derived BPF tokens serve as
a per-container "flag" to grant overall ability to use bpf() (plus further
restrict on which parts of bpf() syscalls are treated as namespaced).

Note also, BPF_TOKEN_CREATE command itself requires ns_capable(CAP_BPF)
within the BPF FS owning user namespace, rounding up the ns_capable()
story of BPF token.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20231130185229.2688956-4-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h            |  41 ++++++++
 include/uapi/linux/bpf.h       |  37 +++++++
 kernel/bpf/Makefile            |   2 +-
 kernel/bpf/inode.c             |  12 ++-
 kernel/bpf/syscall.c           |  17 ++++
 kernel/bpf/token.c             | 214 +++++++++++++++++++++++++++++++++++++++++
 tools/include/uapi/linux/bpf.h |  37 +++++++
 7 files changed, 354 insertions(+), 6 deletions(-)
 create mode 100644 kernel/bpf/token.c

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index d3c9acc593ea..aa9cf8e5fab1 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -51,6 +51,10 @@ struct module;
 struct bpf_func_state;
 struct ftrace_ops;
 struct cgroup;
+struct bpf_token;
+struct user_namespace;
+struct super_block;
+struct inode;
 
 extern struct idr btf_idr;
 extern spinlock_t btf_idr_lock;
@@ -1591,6 +1595,13 @@ struct bpf_mount_opts {
 	u64 delegate_attachs;
 };
 
+struct bpf_token {
+	struct work_struct work;
+	atomic64_t refcnt;
+	struct user_namespace *userns;
+	u64 allowed_cmds;
+};
+
 struct bpf_struct_ops_value;
 struct btf_member;
 
@@ -2048,6 +2059,7 @@ static inline void bpf_enable_instrumentation(void)
 	migrate_enable();
 }
 
+extern const struct super_operations bpf_super_ops;
 extern const struct file_operations bpf_map_fops;
 extern const struct file_operations bpf_prog_fops;
 extern const struct file_operations bpf_iter_fops;
@@ -2182,6 +2194,8 @@ static inline void bpf_map_dec_elem_count(struct bpf_map *map)
 
 extern int sysctl_unprivileged_bpf_disabled;
 
+bool bpf_token_capable(const struct bpf_token *token, int cap);
+
 static inline bool bpf_allow_ptr_leaks(void)
 {
 	return perfmon_capable();
@@ -2216,8 +2230,17 @@ int bpf_link_new_fd(struct bpf_link *link);
 struct bpf_link *bpf_link_get_from_fd(u32 ufd);
 struct bpf_link *bpf_link_get_curr_or_next(u32 *id);
 
+void bpf_token_inc(struct bpf_token *token);
+void bpf_token_put(struct bpf_token *token);
+int bpf_token_create(union bpf_attr *attr);
+struct bpf_token *bpf_token_get_from_fd(u32 ufd);
+
+bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd);
+
 int bpf_obj_pin_user(u32 ufd, int path_fd, const char __user *pathname);
 int bpf_obj_get_user(int path_fd, const char __user *pathname, int flags);
+struct inode *bpf_get_inode(struct super_block *sb, const struct inode *dir,
+			    umode_t mode);
 
 #define BPF_ITER_FUNC_PREFIX "bpf_iter_"
 #define DEFINE_BPF_ITER_FUNC(target, args...)			\
@@ -2580,6 +2603,24 @@ static inline int bpf_obj_get_user(const char __user *pathname, int flags)
 	return -EOPNOTSUPP;
 }
 
+static inline bool bpf_token_capable(const struct bpf_token *token, int cap)
+{
+	return capable(cap) || (cap != CAP_SYS_ADMIN && capable(CAP_SYS_ADMIN));
+}
+
+static inline void bpf_token_inc(struct bpf_token *token)
+{
+}
+
+static inline void bpf_token_put(struct bpf_token *token)
+{
+}
+
+static inline struct bpf_token *bpf_token_get_from_fd(u32 ufd)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
 static inline void __dev_flush(void)
 {
 }
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index e88746ba7d21..d4a567e5bc3c 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -847,6 +847,36 @@ union bpf_iter_link_info {
  *		Returns zero on success. On error, -1 is returned and *errno*
  *		is set appropriately.
  *
+ * BPF_TOKEN_CREATE
+ *	Description
+ *		Create BPF token with embedded information about what
+ *		BPF-related functionality it allows:
+ *		- a set of allowed bpf() syscall commands;
+ *		- a set of allowed BPF map types to be created with
+ *		BPF_MAP_CREATE command, if BPF_MAP_CREATE itself is allowed;
+ *		- a set of allowed BPF program types and BPF program attach
+ *		types to be loaded with BPF_PROG_LOAD command, if
+ *		BPF_PROG_LOAD itself is allowed.
+ *
+ *		BPF token is created (derived) from an instance of BPF FS,
+ *		assuming it has necessary delegation mount options specified.
+ *		This BPF token can be passed as an extra parameter to various
+ *		bpf() syscall commands to grant BPF subsystem functionality to
+ *		unprivileged processes.
+ *
+ *		When created, BPF token is "associated" with the owning
+ *		user namespace of BPF FS instance (super block) that it was
+ *		derived from, and subsequent BPF operations performed with
+ *		BPF token would be performing capabilities checks (i.e.,
+ *		CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN, CAP_SYS_ADMIN) within
+ *		that user namespace. Without BPF token, such capabilities
+ *		have to be granted in init user namespace, making bpf()
+ *		syscall incompatible with user namespace, for the most part.
+ *
+ *	Return
+ *		A new file descriptor (a nonnegative integer), or -1 if an
+ *		error occurred (in which case, *errno* is set appropriately).
+ *
  * NOTES
  *	eBPF objects (maps and programs) can be shared between processes.
  *
@@ -901,6 +931,8 @@ enum bpf_cmd {
 	BPF_ITER_CREATE,
 	BPF_LINK_DETACH,
 	BPF_PROG_BIND_MAP,
+	BPF_TOKEN_CREATE,
+	__MAX_BPF_CMD,
 };
 
 enum bpf_map_type {
@@ -1712,6 +1744,11 @@ union bpf_attr {
 		__u32		flags;		/* extra flags */
 	} prog_bind_map;
 
+	struct { /* struct used by BPF_TOKEN_CREATE command */
+		__u32		flags;
+		__u32		bpffs_fd;
+	} token_create;
+
 } __attribute__((aligned(8)));
 
 /* The description below is an attempt at providing documentation to eBPF
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index f526b7573e97..4ce95acfcaa7 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -6,7 +6,7 @@ cflags-nogcse-$(CONFIG_X86)$(CONFIG_CC_IS_GCC) := -fno-gcse
 endif
 CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy)
 
-obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o log.o
+obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o log.o token.o
 obj-$(CONFIG_BPF_SYSCALL) += bpf_iter.o map_iter.o task_iter.o prog_iter.o link_iter.o
 obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o bloom_filter.o
 obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 220fe0f99095..6ce3f9696e72 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -99,9 +99,9 @@ static const struct inode_operations bpf_prog_iops = { };
 static const struct inode_operations bpf_map_iops  = { };
 static const struct inode_operations bpf_link_iops  = { };
 
-static struct inode *bpf_get_inode(struct super_block *sb,
-				   const struct inode *dir,
-				   umode_t mode)
+struct inode *bpf_get_inode(struct super_block *sb,
+			    const struct inode *dir,
+			    umode_t mode)
 {
 	struct inode *inode;
 
@@ -602,11 +602,13 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root)
 {
 	struct bpf_mount_opts *opts = root->d_sb->s_fs_info;
 	umode_t mode = d_inode(root)->i_mode & S_IALLUGO & ~S_ISVTX;
+	u64 mask;
 
 	if (mode != S_IRWXUGO)
 		seq_printf(m, ",mode=%o", mode);
 
-	if (opts->delegate_cmds == ~0ULL)
+	mask = (1ULL << __MAX_BPF_CMD) - 1;
+	if ((opts->delegate_cmds & mask) == mask)
 		seq_printf(m, ",delegate_cmds=any");
 	else if (opts->delegate_cmds)
 		seq_printf(m, ",delegate_cmds=0x%llx", opts->delegate_cmds);
@@ -639,7 +641,7 @@ static void bpf_free_inode(struct inode *inode)
 	free_inode_nonrcu(inode);
 }
 
-static const struct super_operations bpf_super_ops = {
+const struct super_operations bpf_super_ops = {
 	.statfs		= simple_statfs,
 	.drop_inode	= generic_delete_inode,
 	.show_options	= bpf_show_options,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index ee33a52abf18..a156d549b356 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -5377,6 +5377,20 @@ out_prog_put:
 	return ret;
 }
 
+#define BPF_TOKEN_CREATE_LAST_FIELD token_create.bpffs_fd
+
+static int token_create(union bpf_attr *attr)
+{
+	if (CHECK_ATTR(BPF_TOKEN_CREATE))
+		return -EINVAL;
+
+	/* no flags are supported yet */
+	if (attr->token_create.flags)
+		return -EINVAL;
+
+	return bpf_token_create(attr);
+}
+
 static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size)
 {
 	union bpf_attr attr;
@@ -5510,6 +5524,9 @@ static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size)
 	case BPF_PROG_BIND_MAP:
 		err = bpf_prog_bind_map(&attr);
 		break;
+	case BPF_TOKEN_CREATE:
+		err = token_create(&attr);
+		break;
 	default:
 		err = -EINVAL;
 		break;
diff --git a/kernel/bpf/token.c b/kernel/bpf/token.c
new file mode 100644
index 000000000000..e18aaecc67e9
--- /dev/null
+++ b/kernel/bpf/token.c
@@ -0,0 +1,214 @@
+#include <linux/bpf.h>
+#include <linux/vmalloc.h>
+#include <linux/fdtable.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/kernel.h>
+#include <linux/idr.h>
+#include <linux/namei.h>
+#include <linux/user_namespace.h>
+
+bool bpf_token_capable(const struct bpf_token *token, int cap)
+{
+	/* BPF token allows ns_capable() level of capabilities, but only if
+	 * token's userns is *exactly* the same as current user's userns
+	 */
+	if (token && current_user_ns() == token->userns) {
+		if (ns_capable(token->userns, cap))
+			return true;
+		if (cap != CAP_SYS_ADMIN && ns_capable(token->userns, CAP_SYS_ADMIN))
+			return true;
+	}
+	/* otherwise fallback to capable() checks */
+	return capable(cap) || (cap != CAP_SYS_ADMIN && capable(CAP_SYS_ADMIN));
+}
+
+void bpf_token_inc(struct bpf_token *token)
+{
+	atomic64_inc(&token->refcnt);
+}
+
+static void bpf_token_free(struct bpf_token *token)
+{
+	put_user_ns(token->userns);
+	kvfree(token);
+}
+
+static void bpf_token_put_deferred(struct work_struct *work)
+{
+	struct bpf_token *token = container_of(work, struct bpf_token, work);
+
+	bpf_token_free(token);
+}
+
+void bpf_token_put(struct bpf_token *token)
+{
+	if (!token)
+		return;
+
+	if (!atomic64_dec_and_test(&token->refcnt))
+		return;
+
+	INIT_WORK(&token->work, bpf_token_put_deferred);
+	schedule_work(&token->work);
+}
+
+static int bpf_token_release(struct inode *inode, struct file *filp)
+{
+	struct bpf_token *token = filp->private_data;
+
+	bpf_token_put(token);
+	return 0;
+}
+
+static void bpf_token_show_fdinfo(struct seq_file *m, struct file *filp)
+{
+	struct bpf_token *token = filp->private_data;
+	u64 mask;
+
+	BUILD_BUG_ON(__MAX_BPF_CMD >= 64);
+	mask = (1ULL << __MAX_BPF_CMD) - 1;
+	if ((token->allowed_cmds & mask) == mask)
+		seq_printf(m, "allowed_cmds:\tany\n");
+	else
+		seq_printf(m, "allowed_cmds:\t0x%llx\n", token->allowed_cmds);
+}
+
+#define BPF_TOKEN_INODE_NAME "bpf-token"
+
+static const struct inode_operations bpf_token_iops = { };
+
+static const struct file_operations bpf_token_fops = {
+	.release	= bpf_token_release,
+	.show_fdinfo	= bpf_token_show_fdinfo,
+};
+
+int bpf_token_create(union bpf_attr *attr)
+{
+	struct bpf_mount_opts *mnt_opts;
+	struct bpf_token *token = NULL;
+	struct user_namespace *userns;
+	struct inode *inode;
+	struct file *file;
+	struct path path;
+	struct fd f;
+	umode_t mode;
+	int err, fd;
+
+	f = fdget(attr->token_create.bpffs_fd);
+	if (!f.file)
+		return -EBADF;
+
+	path = f.file->f_path;
+	path_get(&path);
+	fdput(f);
+
+	if (path.dentry != path.mnt->mnt_sb->s_root) {
+		err = -EINVAL;
+		goto out_path;
+	}
+	if (path.mnt->mnt_sb->s_op != &bpf_super_ops) {
+		err = -EINVAL;
+		goto out_path;
+	}
+	err = path_permission(&path, MAY_ACCESS);
+	if (err)
+		goto out_path;
+
+	userns = path.dentry->d_sb->s_user_ns;
+	/*
+	 * Enforce that creators of BPF tokens are in the same user
+	 * namespace as the BPF FS instance. This makes reasoning about
+	 * permissions a lot easier and we can always relax this later.
+	 */
+	if (current_user_ns() != userns) {
+		err = -EPERM;
+		goto out_path;
+	}
+	if (!ns_capable(userns, CAP_BPF)) {
+		err = -EPERM;
+		goto out_path;
+	}
+
+	mode = S_IFREG | ((S_IRUSR | S_IWUSR) & ~current_umask());
+	inode = bpf_get_inode(path.mnt->mnt_sb, NULL, mode);
+	if (IS_ERR(inode)) {
+		err = PTR_ERR(inode);
+		goto out_path;
+	}
+
+	inode->i_op = &bpf_token_iops;
+	inode->i_fop = &bpf_token_fops;
+	clear_nlink(inode); /* make sure it is unlinked */
+
+	file = alloc_file_pseudo(inode, path.mnt, BPF_TOKEN_INODE_NAME, O_RDWR, &bpf_token_fops);
+	if (IS_ERR(file)) {
+		iput(inode);
+		err = PTR_ERR(file);
+		goto out_path;
+	}
+
+	token = kvzalloc(sizeof(*token), GFP_USER);
+	if (!token) {
+		err = -ENOMEM;
+		goto out_file;
+	}
+
+	atomic64_set(&token->refcnt, 1);
+
+	/* remember bpffs owning userns for future ns_capable() checks */
+	token->userns = get_user_ns(userns);
+
+	mnt_opts = path.dentry->d_sb->s_fs_info;
+	token->allowed_cmds = mnt_opts->delegate_cmds;
+
+	fd = get_unused_fd_flags(O_CLOEXEC);
+	if (fd < 0) {
+		err = fd;
+		goto out_token;
+	}
+
+	file->private_data = token;
+	fd_install(fd, file);
+
+	path_put(&path);
+	return fd;
+
+out_token:
+	bpf_token_free(token);
+out_file:
+	fput(file);
+out_path:
+	path_put(&path);
+	return err;
+}
+
+struct bpf_token *bpf_token_get_from_fd(u32 ufd)
+{
+	struct fd f = fdget(ufd);
+	struct bpf_token *token;
+
+	if (!f.file)
+		return ERR_PTR(-EBADF);
+	if (f.file->f_op != &bpf_token_fops) {
+		fdput(f);
+		return ERR_PTR(-EINVAL);
+	}
+
+	token = f.file->private_data;
+	bpf_token_inc(token);
+	fdput(f);
+
+	return token;
+}
+
+bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd)
+{
+	/* BPF token can be used only within exactly the same userns in which
+	 * it was created
+	 */
+	if (!token || current_user_ns() != token->userns)
+		return false;
+
+	return token->allowed_cmds & (1ULL << cmd);
+}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index e88746ba7d21..d4a567e5bc3c 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -847,6 +847,36 @@ union bpf_iter_link_info {
  *		Returns zero on success. On error, -1 is returned and *errno*
  *		is set appropriately.
  *
+ * BPF_TOKEN_CREATE
+ *	Description
+ *		Create BPF token with embedded information about what
+ *		BPF-related functionality it allows:
+ *		- a set of allowed bpf() syscall commands;
+ *		- a set of allowed BPF map types to be created with
+ *		BPF_MAP_CREATE command, if BPF_MAP_CREATE itself is allowed;
+ *		- a set of allowed BPF program types and BPF program attach
+ *		types to be loaded with BPF_PROG_LOAD command, if
+ *		BPF_PROG_LOAD itself is allowed.
+ *
+ *		BPF token is created (derived) from an instance of BPF FS,
+ *		assuming it has necessary delegation mount options specified.
+ *		This BPF token can be passed as an extra parameter to various
+ *		bpf() syscall commands to grant BPF subsystem functionality to
+ *		unprivileged processes.
+ *
+ *		When created, BPF token is "associated" with the owning
+ *		user namespace of BPF FS instance (super block) that it was
+ *		derived from, and subsequent BPF operations performed with
+ *		BPF token would be performing capabilities checks (i.e.,
+ *		CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN, CAP_SYS_ADMIN) within
+ *		that user namespace. Without BPF token, such capabilities
+ *		have to be granted in init user namespace, making bpf()
+ *		syscall incompatible with user namespace, for the most part.
+ *
+ *	Return
+ *		A new file descriptor (a nonnegative integer), or -1 if an
+ *		error occurred (in which case, *errno* is set appropriately).
+ *
  * NOTES
  *	eBPF objects (maps and programs) can be shared between processes.
  *
@@ -901,6 +931,8 @@ enum bpf_cmd {
 	BPF_ITER_CREATE,
 	BPF_LINK_DETACH,
 	BPF_PROG_BIND_MAP,
+	BPF_TOKEN_CREATE,
+	__MAX_BPF_CMD,
 };
 
 enum bpf_map_type {
@@ -1712,6 +1744,11 @@ union bpf_attr {
 		__u32		flags;		/* extra flags */
 	} prog_bind_map;
 
+	struct { /* struct used by BPF_TOKEN_CREATE command */
+		__u32		flags;
+		__u32		bpffs_fd;
+	} token_create;
+
 } __attribute__((aligned(8)));
 
 /* The description below is an attempt at providing documentation to eBPF
-- 
cgit v1.2.3


From 688b7270b3cb75e8ac78123d719967db40336e5b Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Thu, 30 Nov 2023 10:52:16 -0800
Subject: bpf: add BPF token support to BPF_MAP_CREATE command

Allow providing token_fd for BPF_MAP_CREATE command to allow controlled
BPF map creation from unprivileged process through delegated BPF token.

Wire through a set of allowed BPF map types to BPF token, derived from
BPF FS at BPF token creation time. This, in combination with allowed_cmds
allows to create a narrowly-focused BPF token (controlled by privileged
agent) with a restrictive set of BPF maps that application can attempt
to create.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20231130185229.2688956-5-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h                                |  2 +
 include/uapi/linux/bpf.h                           |  2 +
 kernel/bpf/inode.c                                 |  3 +-
 kernel/bpf/syscall.c                               | 52 ++++++++++++++++------
 kernel/bpf/token.c                                 | 16 +++++++
 tools/include/uapi/linux/bpf.h                     |  2 +
 .../selftests/bpf/prog_tests/libbpf_probes.c       |  2 +
 .../testing/selftests/bpf/prog_tests/libbpf_str.c  |  3 ++
 8 files changed, 67 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index aa9cf8e5fab1..e08e8436df38 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1600,6 +1600,7 @@ struct bpf_token {
 	atomic64_t refcnt;
 	struct user_namespace *userns;
 	u64 allowed_cmds;
+	u64 allowed_maps;
 };
 
 struct bpf_struct_ops_value;
@@ -2236,6 +2237,7 @@ int bpf_token_create(union bpf_attr *attr);
 struct bpf_token *bpf_token_get_from_fd(u32 ufd);
 
 bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd);
+bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type);
 
 int bpf_obj_pin_user(u32 ufd, int path_fd, const char __user *pathname);
 int bpf_obj_get_user(int path_fd, const char __user *pathname, int flags);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index d4a567e5bc3c..0bba3392b17a 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -983,6 +983,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_BLOOM_FILTER,
 	BPF_MAP_TYPE_USER_RINGBUF,
 	BPF_MAP_TYPE_CGRP_STORAGE,
+	__MAX_BPF_MAP_TYPE
 };
 
 /* Note that tracing related programs such as
@@ -1433,6 +1434,7 @@ union bpf_attr {
 		 * to using 5 hash functions).
 		 */
 		__u64	map_extra;
+		__u32	map_token_fd;
 	};
 
 	struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 6ce3f9696e72..9c7865d1c53d 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -613,7 +613,8 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root)
 	else if (opts->delegate_cmds)
 		seq_printf(m, ",delegate_cmds=0x%llx", opts->delegate_cmds);
 
-	if (opts->delegate_maps == ~0ULL)
+	mask = (1ULL << __MAX_BPF_MAP_TYPE) - 1;
+	if ((opts->delegate_maps & mask) == mask)
 		seq_printf(m, ",delegate_maps=any");
 	else if (opts->delegate_maps)
 		seq_printf(m, ",delegate_maps=0x%llx", opts->delegate_maps);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index a156d549b356..22e14124cd61 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1009,8 +1009,8 @@ int map_check_no_btf(const struct bpf_map *map,
 	return -ENOTSUPP;
 }
 
-static int map_check_btf(struct bpf_map *map, const struct btf *btf,
-			 u32 btf_key_id, u32 btf_value_id)
+static int map_check_btf(struct bpf_map *map, struct bpf_token *token,
+			 const struct btf *btf, u32 btf_key_id, u32 btf_value_id)
 {
 	const struct btf_type *key_type, *value_type;
 	u32 key_size, value_size;
@@ -1038,7 +1038,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf,
 	if (!IS_ERR_OR_NULL(map->record)) {
 		int i;
 
-		if (!bpf_capable()) {
+		if (!bpf_token_capable(token, CAP_BPF)) {
 			ret = -EPERM;
 			goto free_map_tab;
 		}
@@ -1126,11 +1126,12 @@ static bool bpf_net_capable(void)
 	return capable(CAP_NET_ADMIN) || capable(CAP_SYS_ADMIN);
 }
 
-#define BPF_MAP_CREATE_LAST_FIELD map_extra
+#define BPF_MAP_CREATE_LAST_FIELD map_token_fd
 /* called via syscall */
 static int map_create(union bpf_attr *attr)
 {
 	const struct bpf_map_ops *ops;
+	struct bpf_token *token = NULL;
 	int numa_node = bpf_map_attr_numa_node(attr);
 	u32 map_type = attr->map_type;
 	struct bpf_map *map;
@@ -1181,14 +1182,32 @@ static int map_create(union bpf_attr *attr)
 	if (!ops->map_mem_usage)
 		return -EINVAL;
 
+	if (attr->map_token_fd) {
+		token = bpf_token_get_from_fd(attr->map_token_fd);
+		if (IS_ERR(token))
+			return PTR_ERR(token);
+
+		/* if current token doesn't grant map creation permissions,
+		 * then we can't use this token, so ignore it and rely on
+		 * system-wide capabilities checks
+		 */
+		if (!bpf_token_allow_cmd(token, BPF_MAP_CREATE) ||
+		    !bpf_token_allow_map_type(token, attr->map_type)) {
+			bpf_token_put(token);
+			token = NULL;
+		}
+	}
+
+	err = -EPERM;
+
 	/* Intent here is for unprivileged_bpf_disabled to block BPF map
 	 * creation for unprivileged users; other actions depend
 	 * on fd availability and access to bpffs, so are dependent on
 	 * object creation success. Even with unprivileged BPF disabled,
 	 * capability checks are still carried out.
 	 */
-	if (sysctl_unprivileged_bpf_disabled && !bpf_capable())
-		return -EPERM;
+	if (sysctl_unprivileged_bpf_disabled && !bpf_token_capable(token, CAP_BPF))
+		goto put_token;
 
 	/* check privileged map type permissions */
 	switch (map_type) {
@@ -1221,25 +1240,27 @@ static int map_create(union bpf_attr *attr)
 	case BPF_MAP_TYPE_LRU_PERCPU_HASH:
 	case BPF_MAP_TYPE_STRUCT_OPS:
 	case BPF_MAP_TYPE_CPUMAP:
-		if (!bpf_capable())
-			return -EPERM;
+		if (!bpf_token_capable(token, CAP_BPF))
+			goto put_token;
 		break;
 	case BPF_MAP_TYPE_SOCKMAP:
 	case BPF_MAP_TYPE_SOCKHASH:
 	case BPF_MAP_TYPE_DEVMAP:
 	case BPF_MAP_TYPE_DEVMAP_HASH:
 	case BPF_MAP_TYPE_XSKMAP:
-		if (!bpf_net_capable())
-			return -EPERM;
+		if (!bpf_token_capable(token, CAP_NET_ADMIN))
+			goto put_token;
 		break;
 	default:
 		WARN(1, "unsupported map type %d", map_type);
-		return -EPERM;
+		goto put_token;
 	}
 
 	map = ops->map_alloc(attr);
-	if (IS_ERR(map))
-		return PTR_ERR(map);
+	if (IS_ERR(map)) {
+		err = PTR_ERR(map);
+		goto put_token;
+	}
 	map->ops = ops;
 	map->map_type = map_type;
 
@@ -1276,7 +1297,7 @@ static int map_create(union bpf_attr *attr)
 		map->btf = btf;
 
 		if (attr->btf_value_type_id) {
-			err = map_check_btf(map, btf, attr->btf_key_type_id,
+			err = map_check_btf(map, token, btf, attr->btf_key_type_id,
 					    attr->btf_value_type_id);
 			if (err)
 				goto free_map;
@@ -1297,6 +1318,7 @@ static int map_create(union bpf_attr *attr)
 		goto free_map_sec;
 
 	bpf_map_save_memcg(map);
+	bpf_token_put(token);
 
 	err = bpf_map_new_fd(map, f_flags);
 	if (err < 0) {
@@ -1317,6 +1339,8 @@ free_map_sec:
 free_map:
 	btf_put(map->btf);
 	map->ops->map_free(map);
+put_token:
+	bpf_token_put(token);
 	return err;
 }
 
diff --git a/kernel/bpf/token.c b/kernel/bpf/token.c
index e18aaecc67e9..06c34dae658e 100644
--- a/kernel/bpf/token.c
+++ b/kernel/bpf/token.c
@@ -72,6 +72,13 @@ static void bpf_token_show_fdinfo(struct seq_file *m, struct file *filp)
 		seq_printf(m, "allowed_cmds:\tany\n");
 	else
 		seq_printf(m, "allowed_cmds:\t0x%llx\n", token->allowed_cmds);
+
+	BUILD_BUG_ON(__MAX_BPF_MAP_TYPE >= 64);
+	mask = (1ULL << __MAX_BPF_MAP_TYPE) - 1;
+	if ((token->allowed_maps & mask) == mask)
+		seq_printf(m, "allowed_maps:\tany\n");
+	else
+		seq_printf(m, "allowed_maps:\t0x%llx\n", token->allowed_maps);
 }
 
 #define BPF_TOKEN_INODE_NAME "bpf-token"
@@ -161,6 +168,7 @@ int bpf_token_create(union bpf_attr *attr)
 
 	mnt_opts = path.dentry->d_sb->s_fs_info;
 	token->allowed_cmds = mnt_opts->delegate_cmds;
+	token->allowed_maps = mnt_opts->delegate_maps;
 
 	fd = get_unused_fd_flags(O_CLOEXEC);
 	if (fd < 0) {
@@ -212,3 +220,11 @@ bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd)
 
 	return token->allowed_cmds & (1ULL << cmd);
 }
+
+bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type)
+{
+	if (!token || type >= __MAX_BPF_MAP_TYPE)
+		return false;
+
+	return token->allowed_maps & (1ULL << type);
+}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index d4a567e5bc3c..0bba3392b17a 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -983,6 +983,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_BLOOM_FILTER,
 	BPF_MAP_TYPE_USER_RINGBUF,
 	BPF_MAP_TYPE_CGRP_STORAGE,
+	__MAX_BPF_MAP_TYPE
 };
 
 /* Note that tracing related programs such as
@@ -1433,6 +1434,7 @@ union bpf_attr {
 		 * to using 5 hash functions).
 		 */
 		__u64	map_extra;
+		__u32	map_token_fd;
 	};
 
 	struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c
index 9f766ddd946a..573249a2814d 100644
--- a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c
+++ b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c
@@ -68,6 +68,8 @@ void test_libbpf_probe_map_types(void)
 
 		if (map_type == BPF_MAP_TYPE_UNSPEC)
 			continue;
+		if (strcmp(map_type_name, "__MAX_BPF_MAP_TYPE") == 0)
+			continue;
 
 		if (!test__start_subtest(map_type_name))
 			continue;
diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c
index c440ea3311ed..2a0633f43c73 100644
--- a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c
+++ b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c
@@ -132,6 +132,9 @@ static void test_libbpf_bpf_map_type_str(void)
 		const char *map_type_str;
 		char buf[256];
 
+		if (map_type == __MAX_BPF_MAP_TYPE)
+			continue;
+
 		map_type_name = btf__str_by_offset(btf, e->name_off);
 		map_type_str = libbpf_bpf_map_type_str(map_type);
 		ASSERT_OK_PTR(map_type_str, map_type_name);
-- 
cgit v1.2.3


From ee54b1a910e4d49c9a104f31ae3f5b979131adf8 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Thu, 30 Nov 2023 10:52:17 -0800
Subject: bpf: add BPF token support to BPF_BTF_LOAD command

Accept BPF token FD in BPF_BTF_LOAD command to allow BTF data loading
through delegated BPF token. BTF loading is a pretty straightforward
operation, so as long as BPF token is created with allow_cmds granting
BPF_BTF_LOAD command, kernel proceeds to parsing BTF data and creating
BTF object.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20231130185229.2688956-6-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h       |  1 +
 kernel/bpf/syscall.c           | 20 ++++++++++++++++++--
 tools/include/uapi/linux/bpf.h |  1 +
 3 files changed, 20 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 0bba3392b17a..9f9989e0d062 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1616,6 +1616,7 @@ union bpf_attr {
 		 * truncated), or smaller (if log buffer wasn't filled completely).
 		 */
 		__u32		btf_log_true_size;
+		__u32		btf_token_fd;
 	};
 
 	struct {
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 22e14124cd61..d87c5c27cde3 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -4777,15 +4777,31 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr,
 	return err;
 }
 
-#define BPF_BTF_LOAD_LAST_FIELD btf_log_true_size
+#define BPF_BTF_LOAD_LAST_FIELD btf_token_fd
 
 static int bpf_btf_load(const union bpf_attr *attr, bpfptr_t uattr, __u32 uattr_size)
 {
+	struct bpf_token *token = NULL;
+
 	if (CHECK_ATTR(BPF_BTF_LOAD))
 		return -EINVAL;
 
-	if (!bpf_capable())
+	if (attr->btf_token_fd) {
+		token = bpf_token_get_from_fd(attr->btf_token_fd);
+		if (IS_ERR(token))
+			return PTR_ERR(token);
+		if (!bpf_token_allow_cmd(token, BPF_BTF_LOAD)) {
+			bpf_token_put(token);
+			token = NULL;
+		}
+	}
+
+	if (!bpf_token_capable(token, CAP_BPF)) {
+		bpf_token_put(token);
 		return -EPERM;
+	}
+
+	bpf_token_put(token);
 
 	return btf_new_fd(attr, uattr, uattr_size);
 }
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 0bba3392b17a..9f9989e0d062 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1616,6 +1616,7 @@ union bpf_attr {
 		 * truncated), or smaller (if log buffer wasn't filled completely).
 		 */
 		__u32		btf_log_true_size;
+		__u32		btf_token_fd;
 	};
 
 	struct {
-- 
cgit v1.2.3


From e1cef620f598853a90f17701fcb1057a6768f7b8 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Thu, 30 Nov 2023 10:52:18 -0800
Subject: bpf: add BPF token support to BPF_PROG_LOAD command

Add basic support of BPF token to BPF_PROG_LOAD. Wire through a set of
allowed BPF program types and attach types, derived from BPF FS at BPF
token creation time. Then make sure we perform bpf_token_capable()
checks everywhere where it's relevant.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20231130185229.2688956-7-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h                                |  6 ++
 include/uapi/linux/bpf.h                           |  2 +
 kernel/bpf/core.c                                  |  1 +
 kernel/bpf/inode.c                                 |  6 +-
 kernel/bpf/syscall.c                               | 87 ++++++++++++++++------
 kernel/bpf/token.c                                 | 27 +++++++
 tools/include/uapi/linux/bpf.h                     |  2 +
 .../selftests/bpf/prog_tests/libbpf_probes.c       |  2 +
 .../testing/selftests/bpf/prog_tests/libbpf_str.c  |  3 +
 9 files changed, 110 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index e08e8436df38..20af87b59d70 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1461,6 +1461,7 @@ struct bpf_prog_aux {
 #ifdef CONFIG_SECURITY
 	void *security;
 #endif
+	struct bpf_token *token;
 	struct bpf_prog_offload *offload;
 	struct btf *btf;
 	struct bpf_func_info *func_info;
@@ -1601,6 +1602,8 @@ struct bpf_token {
 	struct user_namespace *userns;
 	u64 allowed_cmds;
 	u64 allowed_maps;
+	u64 allowed_progs;
+	u64 allowed_attachs;
 };
 
 struct bpf_struct_ops_value;
@@ -2238,6 +2241,9 @@ struct bpf_token *bpf_token_get_from_fd(u32 ufd);
 
 bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd);
 bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type);
+bool bpf_token_allow_prog_type(const struct bpf_token *token,
+			       enum bpf_prog_type prog_type,
+			       enum bpf_attach_type attach_type);
 
 int bpf_obj_pin_user(u32 ufd, int path_fd, const char __user *pathname);
 int bpf_obj_get_user(int path_fd, const char __user *pathname, int flags);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 9f9989e0d062..4df2d025c784 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1028,6 +1028,7 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_SK_LOOKUP,
 	BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */
 	BPF_PROG_TYPE_NETFILTER,
+	__MAX_BPF_PROG_TYPE
 };
 
 enum bpf_attach_type {
@@ -1504,6 +1505,7 @@ union bpf_attr {
 		 * truncated), or smaller (if log buffer wasn't filled completely).
 		 */
 		__u32		log_true_size;
+		__u32		prog_token_fd;
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 4b813da8d6c0..47085839af8d 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2751,6 +2751,7 @@ void bpf_prog_free(struct bpf_prog *fp)
 
 	if (aux->dst_prog)
 		bpf_prog_put(aux->dst_prog);
+	bpf_token_put(aux->token);
 	INIT_WORK(&aux->work, bpf_prog_free_deferred);
 	schedule_work(&aux->work);
 }
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 9c7865d1c53d..5359a0929c35 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -619,12 +619,14 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root)
 	else if (opts->delegate_maps)
 		seq_printf(m, ",delegate_maps=0x%llx", opts->delegate_maps);
 
-	if (opts->delegate_progs == ~0ULL)
+	mask = (1ULL << __MAX_BPF_PROG_TYPE) - 1;
+	if ((opts->delegate_progs & mask) == mask)
 		seq_printf(m, ",delegate_progs=any");
 	else if (opts->delegate_progs)
 		seq_printf(m, ",delegate_progs=0x%llx", opts->delegate_progs);
 
-	if (opts->delegate_attachs == ~0ULL)
+	mask = (1ULL << __MAX_BPF_ATTACH_TYPE) - 1;
+	if ((opts->delegate_attachs & mask) == mask)
 		seq_printf(m, ",delegate_attachs=any");
 	else if (opts->delegate_attachs)
 		seq_printf(m, ",delegate_attachs=0x%llx", opts->delegate_attachs);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index d87c5c27cde3..2c8393c21b8c 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2608,13 +2608,15 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type)
 }
 
 /* last field in 'union bpf_attr' used by this command */
-#define	BPF_PROG_LOAD_LAST_FIELD log_true_size
+#define BPF_PROG_LOAD_LAST_FIELD prog_token_fd
 
 static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
 {
 	enum bpf_prog_type type = attr->prog_type;
 	struct bpf_prog *prog, *dst_prog = NULL;
 	struct btf *attach_btf = NULL;
+	struct bpf_token *token = NULL;
+	bool bpf_cap;
 	int err;
 	char license[128];
 
@@ -2631,10 +2633,31 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
 				 BPF_F_TEST_REG_INVARIANTS))
 		return -EINVAL;
 
+	bpf_prog_load_fixup_attach_type(attr);
+
+	if (attr->prog_token_fd) {
+		token = bpf_token_get_from_fd(attr->prog_token_fd);
+		if (IS_ERR(token))
+			return PTR_ERR(token);
+		/* if current token doesn't grant prog loading permissions,
+		 * then we can't use this token, so ignore it and rely on
+		 * system-wide capabilities checks
+		 */
+		if (!bpf_token_allow_cmd(token, BPF_PROG_LOAD) ||
+		    !bpf_token_allow_prog_type(token, attr->prog_type,
+					       attr->expected_attach_type)) {
+			bpf_token_put(token);
+			token = NULL;
+		}
+	}
+
+	bpf_cap = bpf_token_capable(token, CAP_BPF);
+	err = -EPERM;
+
 	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) &&
 	    (attr->prog_flags & BPF_F_ANY_ALIGNMENT) &&
-	    !bpf_capable())
-		return -EPERM;
+	    !bpf_cap)
+		goto put_token;
 
 	/* Intent here is for unprivileged_bpf_disabled to block BPF program
 	 * creation for unprivileged users; other actions depend
@@ -2643,21 +2666,23 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
 	 * capability checks are still carried out for these
 	 * and other operations.
 	 */
-	if (sysctl_unprivileged_bpf_disabled && !bpf_capable())
-		return -EPERM;
+	if (sysctl_unprivileged_bpf_disabled && !bpf_cap)
+		goto put_token;
 
 	if (attr->insn_cnt == 0 ||
-	    attr->insn_cnt > (bpf_capable() ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS))
-		return -E2BIG;
+	    attr->insn_cnt > (bpf_cap ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS)) {
+		err = -E2BIG;
+		goto put_token;
+	}
 	if (type != BPF_PROG_TYPE_SOCKET_FILTER &&
 	    type != BPF_PROG_TYPE_CGROUP_SKB &&
-	    !bpf_capable())
-		return -EPERM;
+	    !bpf_cap)
+		goto put_token;
 
-	if (is_net_admin_prog_type(type) && !bpf_net_capable())
-		return -EPERM;
-	if (is_perfmon_prog_type(type) && !perfmon_capable())
-		return -EPERM;
+	if (is_net_admin_prog_type(type) && !bpf_token_capable(token, CAP_NET_ADMIN))
+		goto put_token;
+	if (is_perfmon_prog_type(type) && !bpf_token_capable(token, CAP_PERFMON))
+		goto put_token;
 
 	/* attach_prog_fd/attach_btf_obj_fd can specify fd of either bpf_prog
 	 * or btf, we need to check which one it is
@@ -2667,27 +2692,33 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
 		if (IS_ERR(dst_prog)) {
 			dst_prog = NULL;
 			attach_btf = btf_get_by_fd(attr->attach_btf_obj_fd);
-			if (IS_ERR(attach_btf))
-				return -EINVAL;
+			if (IS_ERR(attach_btf)) {
+				err = -EINVAL;
+				goto put_token;
+			}
 			if (!btf_is_kernel(attach_btf)) {
 				/* attaching through specifying bpf_prog's BTF
 				 * objects directly might be supported eventually
 				 */
 				btf_put(attach_btf);
-				return -ENOTSUPP;
+				err = -ENOTSUPP;
+				goto put_token;
 			}
 		}
 	} else if (attr->attach_btf_id) {
 		/* fall back to vmlinux BTF, if BTF type ID is specified */
 		attach_btf = bpf_get_btf_vmlinux();
-		if (IS_ERR(attach_btf))
-			return PTR_ERR(attach_btf);
-		if (!attach_btf)
-			return -EINVAL;
+		if (IS_ERR(attach_btf)) {
+			err = PTR_ERR(attach_btf);
+			goto put_token;
+		}
+		if (!attach_btf) {
+			err = -EINVAL;
+			goto put_token;
+		}
 		btf_get(attach_btf);
 	}
 
-	bpf_prog_load_fixup_attach_type(attr);
 	if (bpf_prog_load_check_attach(type, attr->expected_attach_type,
 				       attach_btf, attr->attach_btf_id,
 				       dst_prog)) {
@@ -2695,7 +2726,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
 			bpf_prog_put(dst_prog);
 		if (attach_btf)
 			btf_put(attach_btf);
-		return -EINVAL;
+		err = -EINVAL;
+		goto put_token;
 	}
 
 	/* plain bpf_prog allocation */
@@ -2705,7 +2737,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
 			bpf_prog_put(dst_prog);
 		if (attach_btf)
 			btf_put(attach_btf);
-		return -ENOMEM;
+		err = -EINVAL;
+		goto put_token;
 	}
 
 	prog->expected_attach_type = attr->expected_attach_type;
@@ -2716,6 +2749,10 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
 	prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE;
 	prog->aux->xdp_has_frags = attr->prog_flags & BPF_F_XDP_HAS_FRAGS;
 
+	/* move token into prog->aux, reuse taken refcnt */
+	prog->aux->token = token;
+	token = NULL;
+
 	err = security_bpf_prog_alloc(prog->aux);
 	if (err)
 		goto free_prog;
@@ -2817,6 +2854,8 @@ free_prog:
 	if (prog->aux->attach_btf)
 		btf_put(prog->aux->attach_btf);
 	bpf_prog_free(prog);
+put_token:
+	bpf_token_put(token);
 	return err;
 }
 
@@ -3806,7 +3845,7 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
 	case BPF_PROG_TYPE_SK_LOOKUP:
 		return attach_type == prog->expected_attach_type ? 0 : -EINVAL;
 	case BPF_PROG_TYPE_CGROUP_SKB:
-		if (!bpf_net_capable())
+		if (!bpf_token_capable(prog->aux->token, CAP_NET_ADMIN))
 			/* cg-skb progs can be loaded by unpriv user.
 			 * check permissions at attach time.
 			 */
diff --git a/kernel/bpf/token.c b/kernel/bpf/token.c
index 06c34dae658e..5a51e6b8f6bf 100644
--- a/kernel/bpf/token.c
+++ b/kernel/bpf/token.c
@@ -79,6 +79,20 @@ static void bpf_token_show_fdinfo(struct seq_file *m, struct file *filp)
 		seq_printf(m, "allowed_maps:\tany\n");
 	else
 		seq_printf(m, "allowed_maps:\t0x%llx\n", token->allowed_maps);
+
+	BUILD_BUG_ON(__MAX_BPF_PROG_TYPE >= 64);
+	mask = (1ULL << __MAX_BPF_PROG_TYPE) - 1;
+	if ((token->allowed_progs & mask) == mask)
+		seq_printf(m, "allowed_progs:\tany\n");
+	else
+		seq_printf(m, "allowed_progs:\t0x%llx\n", token->allowed_progs);
+
+	BUILD_BUG_ON(__MAX_BPF_ATTACH_TYPE >= 64);
+	mask = (1ULL << __MAX_BPF_ATTACH_TYPE) - 1;
+	if ((token->allowed_attachs & mask) == mask)
+		seq_printf(m, "allowed_attachs:\tany\n");
+	else
+		seq_printf(m, "allowed_attachs:\t0x%llx\n", token->allowed_attachs);
 }
 
 #define BPF_TOKEN_INODE_NAME "bpf-token"
@@ -169,6 +183,8 @@ int bpf_token_create(union bpf_attr *attr)
 	mnt_opts = path.dentry->d_sb->s_fs_info;
 	token->allowed_cmds = mnt_opts->delegate_cmds;
 	token->allowed_maps = mnt_opts->delegate_maps;
+	token->allowed_progs = mnt_opts->delegate_progs;
+	token->allowed_attachs = mnt_opts->delegate_attachs;
 
 	fd = get_unused_fd_flags(O_CLOEXEC);
 	if (fd < 0) {
@@ -228,3 +244,14 @@ bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type t
 
 	return token->allowed_maps & (1ULL << type);
 }
+
+bool bpf_token_allow_prog_type(const struct bpf_token *token,
+			       enum bpf_prog_type prog_type,
+			       enum bpf_attach_type attach_type)
+{
+	if (!token || prog_type >= __MAX_BPF_PROG_TYPE || attach_type >= __MAX_BPF_ATTACH_TYPE)
+		return false;
+
+	return (token->allowed_progs & (1ULL << prog_type)) &&
+	       (token->allowed_attachs & (1ULL << attach_type));
+}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 9f9989e0d062..4df2d025c784 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1028,6 +1028,7 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_SK_LOOKUP,
 	BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */
 	BPF_PROG_TYPE_NETFILTER,
+	__MAX_BPF_PROG_TYPE
 };
 
 enum bpf_attach_type {
@@ -1504,6 +1505,7 @@ union bpf_attr {
 		 * truncated), or smaller (if log buffer wasn't filled completely).
 		 */
 		__u32		log_true_size;
+		__u32		prog_token_fd;
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c
index 573249a2814d..4ed46ed58a7b 100644
--- a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c
+++ b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c
@@ -30,6 +30,8 @@ void test_libbpf_probe_prog_types(void)
 
 		if (prog_type == BPF_PROG_TYPE_UNSPEC)
 			continue;
+		if (strcmp(prog_type_name, "__MAX_BPF_PROG_TYPE") == 0)
+			continue;
 
 		if (!test__start_subtest(prog_type_name))
 			continue;
diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c
index 2a0633f43c73..384bc1f7a65e 100644
--- a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c
+++ b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c
@@ -189,6 +189,9 @@ static void test_libbpf_bpf_prog_type_str(void)
 		const char *prog_type_str;
 		char buf[256];
 
+		if (prog_type == __MAX_BPF_PROG_TYPE)
+			continue;
+
 		prog_type_name = btf__str_by_offset(btf, e->name_off);
 		prog_type_str = libbpf_bpf_prog_type_str(prog_type);
 		ASSERT_OK_PTR(prog_type_str, prog_type_name);
-- 
cgit v1.2.3


From 4cbb270e115bc197ff2046aeb54cc951666b16ec Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Thu, 30 Nov 2023 10:52:19 -0800
Subject: bpf: take into account BPF token when fetching helper protos

Instead of performing unconditional system-wide bpf_capable() and
perfmon_capable() calls inside bpf_base_func_proto() function (and other
similar ones) to determine eligibility of a given BPF helper for a given
program, use previously recorded BPF token during BPF_PROG_LOAD command
handling to inform the decision.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20231130185229.2688956-8-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 drivers/media/rc/bpf-lirc.c |  2 +-
 include/linux/bpf.h         |  5 +++--
 kernel/bpf/cgroup.c         |  6 +++---
 kernel/bpf/helpers.c        |  6 +++---
 kernel/bpf/syscall.c        |  5 +++--
 kernel/trace/bpf_trace.c    |  2 +-
 net/core/filter.c           | 32 ++++++++++++++++----------------
 net/ipv4/bpf_tcp_ca.c       |  2 +-
 net/netfilter/nf_bpf_link.c |  2 +-
 9 files changed, 32 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c
index fe17c7f98e81..6d07693c6b9f 100644
--- a/drivers/media/rc/bpf-lirc.c
+++ b/drivers/media/rc/bpf-lirc.c
@@ -110,7 +110,7 @@ lirc_mode2_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_get_prandom_u32:
 		return &bpf_get_prandom_u32_proto;
 	case BPF_FUNC_trace_printk:
-		if (perfmon_capable())
+		if (bpf_token_capable(prog->aux->token, CAP_PERFMON))
 			return bpf_get_trace_printk_proto();
 		fallthrough;
 	default:
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 20af87b59d70..2a3ab4f3dd8c 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2492,7 +2492,8 @@ const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type
 struct bpf_prog *bpf_prog_by_id(u32 id);
 struct bpf_link *bpf_link_by_id(u32 id);
 
-const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id);
+const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id,
+						 const struct bpf_prog *prog);
 void bpf_task_storage_free(struct task_struct *task);
 void bpf_cgrp_storage_free(struct cgroup *cgroup);
 bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog);
@@ -2752,7 +2753,7 @@ static inline int btf_struct_access(struct bpf_verifier_log *log,
 }
 
 static inline const struct bpf_func_proto *
-bpf_base_func_proto(enum bpf_func_id func_id)
+bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
 	return NULL;
 }
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 491d20038cbe..98e0e3835b28 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -1630,7 +1630,7 @@ cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_perf_event_output:
 		return &bpf_event_output_data_proto;
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_base_func_proto(func_id, prog);
 	}
 }
 
@@ -2191,7 +2191,7 @@ sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_perf_event_output:
 		return &bpf_event_output_data_proto;
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_base_func_proto(func_id, prog);
 	}
 }
 
@@ -2348,7 +2348,7 @@ cg_sockopt_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_perf_event_output:
 		return &bpf_event_output_data_proto;
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_base_func_proto(func_id, prog);
 	}
 }
 
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index ee9bdf29246a..b3be5742d6f1 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1679,7 +1679,7 @@ const struct bpf_func_proto bpf_probe_read_kernel_str_proto __weak;
 const struct bpf_func_proto bpf_task_pt_regs_proto __weak;
 
 const struct bpf_func_proto *
-bpf_base_func_proto(enum bpf_func_id func_id)
+bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
 	switch (func_id) {
 	case BPF_FUNC_map_lookup_elem:
@@ -1730,7 +1730,7 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		break;
 	}
 
-	if (!bpf_capable())
+	if (!bpf_token_capable(prog->aux->token, CAP_BPF))
 		return NULL;
 
 	switch (func_id) {
@@ -1788,7 +1788,7 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		break;
 	}
 
-	if (!perfmon_capable())
+	if (!bpf_token_capable(prog->aux->token, CAP_PERFMON))
 		return NULL;
 
 	switch (func_id) {
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 2c8393c21b8c..1cc03f08c9cd 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -5712,7 +5712,7 @@ static const struct bpf_func_proto bpf_sys_bpf_proto = {
 const struct bpf_func_proto * __weak
 tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
-	return bpf_base_func_proto(func_id);
+	return bpf_base_func_proto(func_id, prog);
 }
 
 BPF_CALL_1(bpf_sys_close, u32, fd)
@@ -5762,7 +5762,8 @@ syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
 	switch (func_id) {
 	case BPF_FUNC_sys_bpf:
-		return !perfmon_capable() ? NULL : &bpf_sys_bpf_proto;
+		return !bpf_token_capable(prog->aux->token, CAP_PERFMON)
+		       ? NULL : &bpf_sys_bpf_proto;
 	case BPF_FUNC_btf_find_by_name_kind:
 		return &bpf_btf_find_by_name_kind_proto;
 	case BPF_FUNC_sys_close:
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 1648bde28f01..774cf476a892 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1626,7 +1626,7 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_trace_vprintk:
 		return bpf_get_trace_vprintk_proto();
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_base_func_proto(func_id, prog);
 	}
 }
 
diff --git a/net/core/filter.c b/net/core/filter.c
index 0adaa4afa35f..0bf2a03d8203 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -87,7 +87,7 @@
 #include "dev.h"
 
 static const struct bpf_func_proto *
-bpf_sk_base_func_proto(enum bpf_func_id func_id);
+bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog);
 
 int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len)
 {
@@ -7841,7 +7841,7 @@ sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_ktime_get_coarse_ns:
 		return &bpf_ktime_get_coarse_ns_proto;
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_base_func_proto(func_id, prog);
 	}
 }
 
@@ -7934,7 +7934,7 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 			return NULL;
 		}
 	default:
-		return bpf_sk_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id, prog);
 	}
 }
 
@@ -7953,7 +7953,7 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_perf_event_output:
 		return &bpf_skb_event_output_proto;
 	default:
-		return bpf_sk_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id, prog);
 	}
 }
 
@@ -8140,7 +8140,7 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 #endif
 #endif
 	default:
-		return bpf_sk_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id, prog);
 	}
 }
 
@@ -8199,7 +8199,7 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 #endif
 #endif
 	default:
-		return bpf_sk_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id, prog);
 	}
 
 #if IS_MODULE(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)
@@ -8260,7 +8260,7 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_tcp_sock_proto;
 #endif /* CONFIG_INET */
 	default:
-		return bpf_sk_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id, prog);
 	}
 }
 
@@ -8302,7 +8302,7 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_cgroup_classid_curr_proto;
 #endif
 	default:
-		return bpf_sk_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id, prog);
 	}
 }
 
@@ -8346,7 +8346,7 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_skc_lookup_tcp_proto;
 #endif
 	default:
-		return bpf_sk_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id, prog);
 	}
 }
 
@@ -8357,7 +8357,7 @@ flow_dissector_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_skb_load_bytes:
 		return &bpf_flow_dissector_load_bytes_proto;
 	default:
-		return bpf_sk_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id, prog);
 	}
 }
 
@@ -8384,7 +8384,7 @@ lwt_out_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_skb_under_cgroup:
 		return &bpf_skb_under_cgroup_proto;
 	default:
-		return bpf_sk_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id, prog);
 	}
 }
 
@@ -11215,7 +11215,7 @@ sk_reuseport_func_proto(enum bpf_func_id func_id,
 	case BPF_FUNC_ktime_get_coarse_ns:
 		return &bpf_ktime_get_coarse_ns_proto;
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_base_func_proto(func_id, prog);
 	}
 }
 
@@ -11397,7 +11397,7 @@ sk_lookup_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_sk_release:
 		return &bpf_sk_release_proto;
 	default:
-		return bpf_sk_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id, prog);
 	}
 }
 
@@ -11731,7 +11731,7 @@ const struct bpf_func_proto bpf_sock_from_file_proto = {
 };
 
 static const struct bpf_func_proto *
-bpf_sk_base_func_proto(enum bpf_func_id func_id)
+bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
 	const struct bpf_func_proto *func;
 
@@ -11760,10 +11760,10 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id)
 	case BPF_FUNC_ktime_get_coarse_ns:
 		return &bpf_ktime_get_coarse_ns_proto;
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_base_func_proto(func_id, prog);
 	}
 
-	if (!perfmon_capable())
+	if (!bpf_token_capable(prog->aux->token, CAP_PERFMON))
 		return NULL;
 
 	return func;
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index 39dcccf0f174..c7bbd8f3c708 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -191,7 +191,7 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id,
 	case BPF_FUNC_ktime_get_coarse_ns:
 		return &bpf_ktime_get_coarse_ns_proto;
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_base_func_proto(func_id, prog);
 	}
 }
 
diff --git a/net/netfilter/nf_bpf_link.c b/net/netfilter/nf_bpf_link.c
index e502ec00b2fe..1969facac91c 100644
--- a/net/netfilter/nf_bpf_link.c
+++ b/net/netfilter/nf_bpf_link.c
@@ -314,7 +314,7 @@ static bool nf_is_valid_access(int off, int size, enum bpf_access_type type,
 static const struct bpf_func_proto *
 bpf_nf_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
-	return bpf_base_func_proto(func_id);
+	return bpf_base_func_proto(func_id, prog);
 }
 
 const struct bpf_verifier_ops netfilter_verifier_ops = {
-- 
cgit v1.2.3


From 8062fb12de99b2da33754c6a3be1bfc30d9a35f4 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Thu, 30 Nov 2023 10:52:20 -0800
Subject: bpf: consistently use BPF token throughout BPF verifier logic

Remove remaining direct queries to perfmon_capable() and bpf_capable()
in BPF verifier logic and instead use BPF token (if available) to make
decisions about privileges.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20231130185229.2688956-9-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h    | 16 ++++++++--------
 include/linux/filter.h |  2 +-
 kernel/bpf/arraymap.c  |  2 +-
 kernel/bpf/core.c      |  2 +-
 kernel/bpf/verifier.c  | 13 ++++++-------
 net/core/filter.c      |  4 ++--
 6 files changed, 19 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 2a3ab4f3dd8c..435abad3cc61 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2200,24 +2200,24 @@ extern int sysctl_unprivileged_bpf_disabled;
 
 bool bpf_token_capable(const struct bpf_token *token, int cap);
 
-static inline bool bpf_allow_ptr_leaks(void)
+static inline bool bpf_allow_ptr_leaks(const struct bpf_token *token)
 {
-	return perfmon_capable();
+	return bpf_token_capable(token, CAP_PERFMON);
 }
 
-static inline bool bpf_allow_uninit_stack(void)
+static inline bool bpf_allow_uninit_stack(const struct bpf_token *token)
 {
-	return perfmon_capable();
+	return bpf_token_capable(token, CAP_PERFMON);
 }
 
-static inline bool bpf_bypass_spec_v1(void)
+static inline bool bpf_bypass_spec_v1(const struct bpf_token *token)
 {
-	return cpu_mitigations_off() || perfmon_capable();
+	return cpu_mitigations_off() || bpf_token_capable(token, CAP_PERFMON);
 }
 
-static inline bool bpf_bypass_spec_v4(void)
+static inline bool bpf_bypass_spec_v4(const struct bpf_token *token)
 {
-	return cpu_mitigations_off() || perfmon_capable();
+	return cpu_mitigations_off() || bpf_token_capable(token, CAP_PERFMON);
 }
 
 int bpf_map_new_fd(struct bpf_map *map, int flags);
diff --git a/include/linux/filter.h b/include/linux/filter.h
index a4953fafc8cb..14354605ad26 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1139,7 +1139,7 @@ static inline bool bpf_jit_blinding_enabled(struct bpf_prog *prog)
 		return false;
 	if (!bpf_jit_harden)
 		return false;
-	if (bpf_jit_harden == 1 && bpf_capable())
+	if (bpf_jit_harden == 1 && bpf_token_capable(prog->aux->token, CAP_BPF))
 		return false;
 
 	return true;
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 4a4a67956e21..8d365bda9a8b 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -82,7 +82,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 	bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY;
 	int numa_node = bpf_map_attr_numa_node(attr);
 	u32 elem_size, index_mask, max_entries;
-	bool bypass_spec_v1 = bpf_bypass_spec_v1();
+	bool bypass_spec_v1 = bpf_bypass_spec_v1(NULL);
 	u64 array_size, mask64;
 	struct bpf_array *array;
 
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 47085839af8d..ced511f44174 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -675,7 +675,7 @@ static bool bpf_prog_kallsyms_candidate(const struct bpf_prog *fp)
 void bpf_prog_kallsyms_add(struct bpf_prog *fp)
 {
 	if (!bpf_prog_kallsyms_candidate(fp) ||
-	    !bpf_capable())
+	    !bpf_token_capable(fp->aux->token, CAP_BPF))
 		return;
 
 	bpf_prog_ksym_set_addr(fp);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index e5ce530641ba..45e85fb76d82 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -20597,7 +20597,12 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
 	env->prog = *prog;
 	env->ops = bpf_verifier_ops[env->prog->type];
 	env->fd_array = make_bpfptr(attr->fd_array, uattr.is_kernel);
-	is_priv = bpf_capable();
+
+	env->allow_ptr_leaks = bpf_allow_ptr_leaks(env->prog->aux->token);
+	env->allow_uninit_stack = bpf_allow_uninit_stack(env->prog->aux->token);
+	env->bypass_spec_v1 = bpf_bypass_spec_v1(env->prog->aux->token);
+	env->bypass_spec_v4 = bpf_bypass_spec_v4(env->prog->aux->token);
+	env->bpf_capable = is_priv = bpf_token_capable(env->prog->aux->token, CAP_BPF);
 
 	bpf_get_btf_vmlinux();
 
@@ -20629,12 +20634,6 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
 	if (attr->prog_flags & BPF_F_ANY_ALIGNMENT)
 		env->strict_alignment = false;
 
-	env->allow_ptr_leaks = bpf_allow_ptr_leaks();
-	env->allow_uninit_stack = bpf_allow_uninit_stack();
-	env->bypass_spec_v1 = bpf_bypass_spec_v1();
-	env->bypass_spec_v4 = bpf_bypass_spec_v4();
-	env->bpf_capable = bpf_capable();
-
 	if (is_priv)
 		env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ;
 	env->test_reg_invariants = attr->prog_flags & BPF_F_TEST_REG_INVARIANTS;
diff --git a/net/core/filter.c b/net/core/filter.c
index 0bf2a03d8203..adcfc2c25754 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -8559,7 +8559,7 @@ static bool cg_skb_is_valid_access(int off, int size,
 		return false;
 	case bpf_ctx_range(struct __sk_buff, data):
 	case bpf_ctx_range(struct __sk_buff, data_end):
-		if (!bpf_capable())
+		if (!bpf_token_capable(prog->aux->token, CAP_BPF))
 			return false;
 		break;
 	}
@@ -8571,7 +8571,7 @@ static bool cg_skb_is_valid_access(int off, int size,
 		case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]):
 			break;
 		case bpf_ctx_range(struct __sk_buff, tstamp):
-			if (!bpf_capable())
+			if (!bpf_token_capable(prog->aux->token, CAP_BPF))
 				return false;
 			break;
 		default:
-- 
cgit v1.2.3


From c3dd6e94df7193f33f45d33303f5e85afb2a72dc Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Thu, 30 Nov 2023 10:52:21 -0800
Subject: bpf,lsm: refactor bpf_prog_alloc/bpf_prog_free LSM hooks

Based on upstream discussion ([0]), rework existing
bpf_prog_alloc_security LSM hook. Rename it to bpf_prog_load and instead
of passing bpf_prog_aux, pass proper bpf_prog pointer for a full BPF
program struct. Also, we pass bpf_attr union with all the user-provided
arguments for BPF_PROG_LOAD command.  This will give LSMs as much
information as we can basically provide.

The hook is also BPF token-aware now, and optional bpf_token struct is
passed as a third argument. bpf_prog_load LSM hook is called after
a bunch of sanity checks were performed, bpf_prog and bpf_prog_aux were
allocated and filled out, but right before performing full-fledged BPF
verification step.

bpf_prog_free LSM hook is now accepting struct bpf_prog argument, for
consistency. SELinux code is adjusted to all new names, types, and
signatures.

Note, given that bpf_prog_load (previously bpf_prog_alloc) hook can be
used by some LSMs to allocate extra security blob, but also by other
LSMs to reject BPF program loading, we need to make sure that
bpf_prog_free LSM hook is called after bpf_prog_load/bpf_prog_alloc one
*even* if the hook itself returned error. If we don't do that, we run
the risk of leaking memory. This seems to be possible today when
combining SELinux and BPF LSM, as one example, depending on their
relative ordering.

Also, for BPF LSM setup, add bpf_prog_load and bpf_prog_free to
sleepable LSM hooks list, as they are both executed in sleepable
context. Also drop bpf_prog_load hook from untrusted, as there is no
issue with refcount or anything else anymore, that originally forced us
to add it to untrusted list in c0c852dd1876 ("bpf: Do not mark certain LSM
hook arguments as trusted"). We now trigger this hook much later and it
should not be an issue anymore.

  [0] https://lore.kernel.org/bpf/9fe88aef7deabbe87d3fc38c4aea3c69.paul@paul-moore.com/

Acked-by: Paul Moore <paul@paul-moore.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20231130185229.2688956-10-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/lsm_hook_defs.h |  5 +++--
 include/linux/security.h      | 12 +++++++-----
 kernel/bpf/bpf_lsm.c          |  5 +++--
 kernel/bpf/syscall.c          | 25 +++++++++++++------------
 security/security.c           | 25 +++++++++++++++----------
 security/selinux/hooks.c      | 15 ++++++++-------
 6 files changed, 49 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index ff217a5ce552..41ec4a7c070e 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -400,8 +400,9 @@ LSM_HOOK(int, 0, bpf_map, struct bpf_map *map, fmode_t fmode)
 LSM_HOOK(int, 0, bpf_prog, struct bpf_prog *prog)
 LSM_HOOK(int, 0, bpf_map_alloc_security, struct bpf_map *map)
 LSM_HOOK(void, LSM_RET_VOID, bpf_map_free_security, struct bpf_map *map)
-LSM_HOOK(int, 0, bpf_prog_alloc_security, struct bpf_prog_aux *aux)
-LSM_HOOK(void, LSM_RET_VOID, bpf_prog_free_security, struct bpf_prog_aux *aux)
+LSM_HOOK(int, 0, bpf_prog_load, struct bpf_prog *prog, union bpf_attr *attr,
+	 struct bpf_token *token)
+LSM_HOOK(void, LSM_RET_VOID, bpf_prog_free, struct bpf_prog *prog)
 #endif /* CONFIG_BPF_SYSCALL */
 
 LSM_HOOK(int, 0, locked_down, enum lockdown_reason what)
diff --git a/include/linux/security.h b/include/linux/security.h
index 1d1df326c881..65467eef6678 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -2020,15 +2020,16 @@ static inline void securityfs_remove(struct dentry *dentry)
 union bpf_attr;
 struct bpf_map;
 struct bpf_prog;
-struct bpf_prog_aux;
+struct bpf_token;
 #ifdef CONFIG_SECURITY
 extern int security_bpf(int cmd, union bpf_attr *attr, unsigned int size);
 extern int security_bpf_map(struct bpf_map *map, fmode_t fmode);
 extern int security_bpf_prog(struct bpf_prog *prog);
 extern int security_bpf_map_alloc(struct bpf_map *map);
 extern void security_bpf_map_free(struct bpf_map *map);
-extern int security_bpf_prog_alloc(struct bpf_prog_aux *aux);
-extern void security_bpf_prog_free(struct bpf_prog_aux *aux);
+extern int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr,
+				  struct bpf_token *token);
+extern void security_bpf_prog_free(struct bpf_prog *prog);
 #else
 static inline int security_bpf(int cmd, union bpf_attr *attr,
 					     unsigned int size)
@@ -2054,12 +2055,13 @@ static inline int security_bpf_map_alloc(struct bpf_map *map)
 static inline void security_bpf_map_free(struct bpf_map *map)
 { }
 
-static inline int security_bpf_prog_alloc(struct bpf_prog_aux *aux)
+static inline int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr,
+					 struct bpf_token *token)
 {
 	return 0;
 }
 
-static inline void security_bpf_prog_free(struct bpf_prog_aux *aux)
+static inline void security_bpf_prog_free(struct bpf_prog *prog)
 { }
 #endif /* CONFIG_SECURITY */
 #endif /* CONFIG_BPF_SYSCALL */
diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c
index e14c822f8911..3e956f6302f3 100644
--- a/kernel/bpf/bpf_lsm.c
+++ b/kernel/bpf/bpf_lsm.c
@@ -263,6 +263,8 @@ BTF_ID(func, bpf_lsm_bpf_map)
 BTF_ID(func, bpf_lsm_bpf_map_alloc_security)
 BTF_ID(func, bpf_lsm_bpf_map_free_security)
 BTF_ID(func, bpf_lsm_bpf_prog)
+BTF_ID(func, bpf_lsm_bpf_prog_load)
+BTF_ID(func, bpf_lsm_bpf_prog_free)
 BTF_ID(func, bpf_lsm_bprm_check_security)
 BTF_ID(func, bpf_lsm_bprm_committed_creds)
 BTF_ID(func, bpf_lsm_bprm_committing_creds)
@@ -346,8 +348,7 @@ BTF_SET_END(sleepable_lsm_hooks)
 
 BTF_SET_START(untrusted_lsm_hooks)
 BTF_ID(func, bpf_lsm_bpf_map_free_security)
-BTF_ID(func, bpf_lsm_bpf_prog_alloc_security)
-BTF_ID(func, bpf_lsm_bpf_prog_free_security)
+BTF_ID(func, bpf_lsm_bpf_prog_free)
 BTF_ID(func, bpf_lsm_file_alloc_security)
 BTF_ID(func, bpf_lsm_file_free_security)
 #ifdef CONFIG_SECURITY_NETWORK
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 1cc03f08c9cd..7717c7c7b95d 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2162,7 +2162,7 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu)
 	kvfree(aux->func_info);
 	kfree(aux->func_info_aux);
 	free_uid(aux->user);
-	security_bpf_prog_free(aux);
+	security_bpf_prog_free(aux->prog);
 	bpf_prog_free(aux->prog);
 }
 
@@ -2753,10 +2753,6 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
 	prog->aux->token = token;
 	token = NULL;
 
-	err = security_bpf_prog_alloc(prog->aux);
-	if (err)
-		goto free_prog;
-
 	prog->aux->user = get_current_user();
 	prog->len = attr->insn_cnt;
 
@@ -2764,12 +2760,12 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
 	if (copy_from_bpfptr(prog->insns,
 			     make_bpfptr(attr->insns, uattr.is_kernel),
 			     bpf_prog_insn_size(prog)) != 0)
-		goto free_prog_sec;
+		goto free_prog;
 	/* copy eBPF program license from user space */
 	if (strncpy_from_bpfptr(license,
 				make_bpfptr(attr->license, uattr.is_kernel),
 				sizeof(license) - 1) < 0)
-		goto free_prog_sec;
+		goto free_prog;
 	license[sizeof(license) - 1] = 0;
 
 	/* eBPF programs must be GPL compatible to use GPL-ed functions */
@@ -2783,25 +2779,29 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
 	if (bpf_prog_is_dev_bound(prog->aux)) {
 		err = bpf_prog_dev_bound_init(prog, attr);
 		if (err)
-			goto free_prog_sec;
+			goto free_prog;
 	}
 
 	if (type == BPF_PROG_TYPE_EXT && dst_prog &&
 	    bpf_prog_is_dev_bound(dst_prog->aux)) {
 		err = bpf_prog_dev_bound_inherit(prog, dst_prog);
 		if (err)
-			goto free_prog_sec;
+			goto free_prog;
 	}
 
 	/* find program type: socket_filter vs tracing_filter */
 	err = find_prog_type(type, prog);
 	if (err < 0)
-		goto free_prog_sec;
+		goto free_prog;
 
 	prog->aux->load_time = ktime_get_boottime_ns();
 	err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name,
 			       sizeof(attr->prog_name));
 	if (err < 0)
+		goto free_prog;
+
+	err = security_bpf_prog_load(prog, attr, token);
+	if (err)
 		goto free_prog_sec;
 
 	/* run eBPF verifier */
@@ -2847,10 +2847,11 @@ free_used_maps:
 	 */
 	__bpf_prog_put_noref(prog, prog->aux->real_func_cnt);
 	return err;
+
 free_prog_sec:
-	free_uid(prog->aux->user);
-	security_bpf_prog_free(prog->aux);
+	security_bpf_prog_free(prog);
 free_prog:
+	free_uid(prog->aux->user);
 	if (prog->aux->attach_btf)
 		btf_put(prog->aux->attach_btf);
 	bpf_prog_free(prog);
diff --git a/security/security.c b/security/security.c
index dcb3e7014f9b..c8a1c66cfaad 100644
--- a/security/security.c
+++ b/security/security.c
@@ -5180,16 +5180,21 @@ int security_bpf_map_alloc(struct bpf_map *map)
 }
 
 /**
- * security_bpf_prog_alloc() - Allocate a bpf program LSM blob
- * @aux: bpf program aux info struct
+ * security_bpf_prog_load() - Check if loading of BPF program is allowed
+ * @prog: BPF program object
+ * @attr: BPF syscall attributes used to create BPF program
+ * @token: BPF token used to grant user access to BPF subsystem
  *
- * Initialize the security field inside bpf program.
+ * Perform an access control check when the kernel loads a BPF program and
+ * allocates associated BPF program object. This hook is also responsible for
+ * allocating any required LSM state for the BPF program.
  *
  * Return: Returns 0 on success, error on failure.
  */
-int security_bpf_prog_alloc(struct bpf_prog_aux *aux)
+int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr,
+			   struct bpf_token *token)
 {
-	return call_int_hook(bpf_prog_alloc_security, 0, aux);
+	return call_int_hook(bpf_prog_load, 0, prog, attr, token);
 }
 
 /**
@@ -5204,14 +5209,14 @@ void security_bpf_map_free(struct bpf_map *map)
 }
 
 /**
- * security_bpf_prog_free() - Free a bpf program's LSM blob
- * @aux: bpf program aux info struct
+ * security_bpf_prog_free() - Free a BPF program's LSM blob
+ * @prog: BPF program struct
  *
- * Clean up the security information stored inside bpf prog.
+ * Clean up the security information stored inside BPF program.
  */
-void security_bpf_prog_free(struct bpf_prog_aux *aux)
+void security_bpf_prog_free(struct bpf_prog *prog)
 {
-	call_void_hook(bpf_prog_free_security, aux);
+	call_void_hook(bpf_prog_free, prog);
 }
 #endif /* CONFIG_BPF_SYSCALL */
 
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index feda711c6b7b..eabee39e983c 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -6805,7 +6805,8 @@ static void selinux_bpf_map_free(struct bpf_map *map)
 	kfree(bpfsec);
 }
 
-static int selinux_bpf_prog_alloc(struct bpf_prog_aux *aux)
+static int selinux_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr,
+				 struct bpf_token *token)
 {
 	struct bpf_security_struct *bpfsec;
 
@@ -6814,16 +6815,16 @@ static int selinux_bpf_prog_alloc(struct bpf_prog_aux *aux)
 		return -ENOMEM;
 
 	bpfsec->sid = current_sid();
-	aux->security = bpfsec;
+	prog->aux->security = bpfsec;
 
 	return 0;
 }
 
-static void selinux_bpf_prog_free(struct bpf_prog_aux *aux)
+static void selinux_bpf_prog_free(struct bpf_prog *prog)
 {
-	struct bpf_security_struct *bpfsec = aux->security;
+	struct bpf_security_struct *bpfsec = prog->aux->security;
 
-	aux->security = NULL;
+	prog->aux->security = NULL;
 	kfree(bpfsec);
 }
 #endif
@@ -7180,7 +7181,7 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = {
 	LSM_HOOK_INIT(bpf_map, selinux_bpf_map),
 	LSM_HOOK_INIT(bpf_prog, selinux_bpf_prog),
 	LSM_HOOK_INIT(bpf_map_free_security, selinux_bpf_map_free),
-	LSM_HOOK_INIT(bpf_prog_free_security, selinux_bpf_prog_free),
+	LSM_HOOK_INIT(bpf_prog_free, selinux_bpf_prog_free),
 #endif
 
 #ifdef CONFIG_PERF_EVENTS
@@ -7238,7 +7239,7 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = {
 #endif
 #ifdef CONFIG_BPF_SYSCALL
 	LSM_HOOK_INIT(bpf_map_alloc_security, selinux_bpf_map_alloc),
-	LSM_HOOK_INIT(bpf_prog_alloc_security, selinux_bpf_prog_alloc),
+	LSM_HOOK_INIT(bpf_prog_load, selinux_bpf_prog_load),
 #endif
 #ifdef CONFIG_PERF_EVENTS
 	LSM_HOOK_INIT(perf_event_alloc, selinux_perf_event_alloc),
-- 
cgit v1.2.3


From 66d636d70a79c1d37e3eea67ab50969e6aaef983 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Thu, 30 Nov 2023 10:52:22 -0800
Subject: bpf,lsm: refactor bpf_map_alloc/bpf_map_free LSM hooks

Similarly to bpf_prog_alloc LSM hook, rename and extend bpf_map_alloc
hook into bpf_map_create, taking not just struct bpf_map, but also
bpf_attr and bpf_token, to give a fuller context to LSMs.

Unlike bpf_prog_alloc, there is no need to move the hook around, as it
currently is firing right before allocating BPF map ID and FD, which
seems to be a sweet spot.

But like bpf_prog_alloc/bpf_prog_free combo, make sure that bpf_map_free
LSM hook is called even if bpf_map_create hook returned error, as if few
LSMs are combined together it could be that one LSM successfully
allocated security blob for its needs, while subsequent LSM rejected BPF
map creation. The former LSM would still need to free up LSM blob, so we
need to ensure security_bpf_map_free() is called regardless of the
outcome.

Acked-by: Paul Moore <paul@paul-moore.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20231130185229.2688956-11-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/lsm_hook_defs.h |  5 +++--
 include/linux/security.h      |  6 ++++--
 kernel/bpf/bpf_lsm.c          |  6 +++---
 kernel/bpf/syscall.c          |  4 ++--
 security/security.c           | 16 ++++++++++------
 security/selinux/hooks.c      |  7 ++++---
 6 files changed, 26 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index 41ec4a7c070e..adb25cc63ce3 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -398,8 +398,9 @@ LSM_HOOK(void, LSM_RET_VOID, audit_rule_free, void *lsmrule)
 LSM_HOOK(int, 0, bpf, int cmd, union bpf_attr *attr, unsigned int size)
 LSM_HOOK(int, 0, bpf_map, struct bpf_map *map, fmode_t fmode)
 LSM_HOOK(int, 0, bpf_prog, struct bpf_prog *prog)
-LSM_HOOK(int, 0, bpf_map_alloc_security, struct bpf_map *map)
-LSM_HOOK(void, LSM_RET_VOID, bpf_map_free_security, struct bpf_map *map)
+LSM_HOOK(int, 0, bpf_map_create, struct bpf_map *map, union bpf_attr *attr,
+	 struct bpf_token *token)
+LSM_HOOK(void, LSM_RET_VOID, bpf_map_free, struct bpf_map *map)
 LSM_HOOK(int, 0, bpf_prog_load, struct bpf_prog *prog, union bpf_attr *attr,
 	 struct bpf_token *token)
 LSM_HOOK(void, LSM_RET_VOID, bpf_prog_free, struct bpf_prog *prog)
diff --git a/include/linux/security.h b/include/linux/security.h
index 65467eef6678..08fd777cbe94 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -2025,7 +2025,8 @@ struct bpf_token;
 extern int security_bpf(int cmd, union bpf_attr *attr, unsigned int size);
 extern int security_bpf_map(struct bpf_map *map, fmode_t fmode);
 extern int security_bpf_prog(struct bpf_prog *prog);
-extern int security_bpf_map_alloc(struct bpf_map *map);
+extern int security_bpf_map_create(struct bpf_map *map, union bpf_attr *attr,
+				   struct bpf_token *token);
 extern void security_bpf_map_free(struct bpf_map *map);
 extern int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr,
 				  struct bpf_token *token);
@@ -2047,7 +2048,8 @@ static inline int security_bpf_prog(struct bpf_prog *prog)
 	return 0;
 }
 
-static inline int security_bpf_map_alloc(struct bpf_map *map)
+static inline int security_bpf_map_create(struct bpf_map *map, union bpf_attr *attr,
+					  struct bpf_token *token)
 {
 	return 0;
 }
diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c
index 3e956f6302f3..9e4e615f11eb 100644
--- a/kernel/bpf/bpf_lsm.c
+++ b/kernel/bpf/bpf_lsm.c
@@ -260,8 +260,8 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 BTF_SET_START(sleepable_lsm_hooks)
 BTF_ID(func, bpf_lsm_bpf)
 BTF_ID(func, bpf_lsm_bpf_map)
-BTF_ID(func, bpf_lsm_bpf_map_alloc_security)
-BTF_ID(func, bpf_lsm_bpf_map_free_security)
+BTF_ID(func, bpf_lsm_bpf_map_create)
+BTF_ID(func, bpf_lsm_bpf_map_free)
 BTF_ID(func, bpf_lsm_bpf_prog)
 BTF_ID(func, bpf_lsm_bpf_prog_load)
 BTF_ID(func, bpf_lsm_bpf_prog_free)
@@ -347,7 +347,7 @@ BTF_ID(func, bpf_lsm_userns_create)
 BTF_SET_END(sleepable_lsm_hooks)
 
 BTF_SET_START(untrusted_lsm_hooks)
-BTF_ID(func, bpf_lsm_bpf_map_free_security)
+BTF_ID(func, bpf_lsm_bpf_map_free)
 BTF_ID(func, bpf_lsm_bpf_prog_free)
 BTF_ID(func, bpf_lsm_file_alloc_security)
 BTF_ID(func, bpf_lsm_file_free_security)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 7717c7c7b95d..aff045eed375 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1309,9 +1309,9 @@ static int map_create(union bpf_attr *attr)
 			attr->btf_vmlinux_value_type_id;
 	}
 
-	err = security_bpf_map_alloc(map);
+	err = security_bpf_map_create(map, attr, token);
 	if (err)
-		goto free_map;
+		goto free_map_sec;
 
 	err = bpf_map_alloc_id(map);
 	if (err)
diff --git a/security/security.c b/security/security.c
index c8a1c66cfaad..ad24cf36da94 100644
--- a/security/security.c
+++ b/security/security.c
@@ -5167,16 +5167,20 @@ int security_bpf_prog(struct bpf_prog *prog)
 }
 
 /**
- * security_bpf_map_alloc() - Allocate a bpf map LSM blob
- * @map: bpf map
+ * security_bpf_map_create() - Check if BPF map creation is allowed
+ * @map: BPF map object
+ * @attr: BPF syscall attributes used to create BPF map
+ * @token: BPF token used to grant user access
  *
- * Initialize the security field inside bpf map.
+ * Do a check when the kernel creates a new BPF map. This is also the
+ * point where LSM blob is allocated for LSMs that need them.
  *
  * Return: Returns 0 on success, error on failure.
  */
-int security_bpf_map_alloc(struct bpf_map *map)
+int security_bpf_map_create(struct bpf_map *map, union bpf_attr *attr,
+			    struct bpf_token *token)
 {
-	return call_int_hook(bpf_map_alloc_security, 0, map);
+	return call_int_hook(bpf_map_create, 0, map, attr, token);
 }
 
 /**
@@ -5205,7 +5209,7 @@ int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr,
  */
 void security_bpf_map_free(struct bpf_map *map)
 {
-	call_void_hook(bpf_map_free_security, map);
+	call_void_hook(bpf_map_free, map);
 }
 
 /**
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index eabee39e983c..002351ab67b7 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -6783,7 +6783,8 @@ static int selinux_bpf_prog(struct bpf_prog *prog)
 			    BPF__PROG_RUN, NULL);
 }
 
-static int selinux_bpf_map_alloc(struct bpf_map *map)
+static int selinux_bpf_map_create(struct bpf_map *map, union bpf_attr *attr,
+				  struct bpf_token *token)
 {
 	struct bpf_security_struct *bpfsec;
 
@@ -7180,7 +7181,7 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = {
 	LSM_HOOK_INIT(bpf, selinux_bpf),
 	LSM_HOOK_INIT(bpf_map, selinux_bpf_map),
 	LSM_HOOK_INIT(bpf_prog, selinux_bpf_prog),
-	LSM_HOOK_INIT(bpf_map_free_security, selinux_bpf_map_free),
+	LSM_HOOK_INIT(bpf_map_free, selinux_bpf_map_free),
 	LSM_HOOK_INIT(bpf_prog_free, selinux_bpf_prog_free),
 #endif
 
@@ -7238,7 +7239,7 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = {
 	LSM_HOOK_INIT(audit_rule_init, selinux_audit_rule_init),
 #endif
 #ifdef CONFIG_BPF_SYSCALL
-	LSM_HOOK_INIT(bpf_map_alloc_security, selinux_bpf_map_alloc),
+	LSM_HOOK_INIT(bpf_map_create, selinux_bpf_map_create),
 	LSM_HOOK_INIT(bpf_prog_load, selinux_bpf_prog_load),
 #endif
 #ifdef CONFIG_PERF_EVENTS
-- 
cgit v1.2.3


From d734ca7b33dbf60eb15dcf7c44f3da7073356777 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Thu, 30 Nov 2023 10:52:23 -0800
Subject: bpf,lsm: add BPF token LSM hooks

Wire up bpf_token_create and bpf_token_free LSM hooks, which allow to
allocate LSM security blob (we add `void *security` field to struct
bpf_token for that), but also control who can instantiate BPF token.
This follows existing pattern for BPF map and BPF prog.

Also add security_bpf_token_allow_cmd() and security_bpf_token_capable()
LSM hooks that allow LSM implementation to control and negate (if
necessary) BPF token's delegation of a specific bpf_cmd and capability,
respectively.

Acked-by: Paul Moore <paul@paul-moore.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20231130185229.2688956-12-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h           |  3 +++
 include/linux/lsm_hook_defs.h |  5 ++++
 include/linux/security.h      | 25 ++++++++++++++++++
 kernel/bpf/bpf_lsm.c          |  4 +++
 kernel/bpf/token.c            | 18 ++++++++-----
 security/security.c           | 60 +++++++++++++++++++++++++++++++++++++++++++
 6 files changed, 109 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 435abad3cc61..7a483f6b6d5f 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1604,6 +1604,9 @@ struct bpf_token {
 	u64 allowed_maps;
 	u64 allowed_progs;
 	u64 allowed_attachs;
+#ifdef CONFIG_SECURITY
+	void *security;
+#endif
 };
 
 struct bpf_struct_ops_value;
diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index adb25cc63ce3..3fdd00b452ac 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -404,6 +404,11 @@ LSM_HOOK(void, LSM_RET_VOID, bpf_map_free, struct bpf_map *map)
 LSM_HOOK(int, 0, bpf_prog_load, struct bpf_prog *prog, union bpf_attr *attr,
 	 struct bpf_token *token)
 LSM_HOOK(void, LSM_RET_VOID, bpf_prog_free, struct bpf_prog *prog)
+LSM_HOOK(int, 0, bpf_token_create, struct bpf_token *token, union bpf_attr *attr,
+	 struct path *path)
+LSM_HOOK(void, LSM_RET_VOID, bpf_token_free, struct bpf_token *token)
+LSM_HOOK(int, 0, bpf_token_cmd, const struct bpf_token *token, enum bpf_cmd cmd)
+LSM_HOOK(int, 0, bpf_token_capable, const struct bpf_token *token, int cap)
 #endif /* CONFIG_BPF_SYSCALL */
 
 LSM_HOOK(int, 0, locked_down, enum lockdown_reason what)
diff --git a/include/linux/security.h b/include/linux/security.h
index 08fd777cbe94..00809d2d5c38 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -32,6 +32,7 @@
 #include <linux/string.h>
 #include <linux/mm.h>
 #include <linux/sockptr.h>
+#include <linux/bpf.h>
 
 struct linux_binprm;
 struct cred;
@@ -2031,6 +2032,11 @@ extern void security_bpf_map_free(struct bpf_map *map);
 extern int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr,
 				  struct bpf_token *token);
 extern void security_bpf_prog_free(struct bpf_prog *prog);
+extern int security_bpf_token_create(struct bpf_token *token, union bpf_attr *attr,
+				     struct path *path);
+extern void security_bpf_token_free(struct bpf_token *token);
+extern int security_bpf_token_cmd(const struct bpf_token *token, enum bpf_cmd cmd);
+extern int security_bpf_token_capable(const struct bpf_token *token, int cap);
 #else
 static inline int security_bpf(int cmd, union bpf_attr *attr,
 					     unsigned int size)
@@ -2065,6 +2071,25 @@ static inline int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *
 
 static inline void security_bpf_prog_free(struct bpf_prog *prog)
 { }
+
+static inline int security_bpf_token_create(struct bpf_token *token, union bpf_attr *attr,
+				     struct path *path)
+{
+	return 0;
+}
+
+static inline void security_bpf_token_free(struct bpf_token *token)
+{ }
+
+static inline int security_bpf_token_cmd(const struct bpf_token *token, enum bpf_cmd cmd)
+{
+	return 0;
+}
+
+static inline int security_bpf_token_capable(const struct bpf_token *token, int cap)
+{
+	return 0;
+}
 #endif /* CONFIG_SECURITY */
 #endif /* CONFIG_BPF_SYSCALL */
 
diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c
index 9e4e615f11eb..7d2f96413a57 100644
--- a/kernel/bpf/bpf_lsm.c
+++ b/kernel/bpf/bpf_lsm.c
@@ -265,6 +265,10 @@ BTF_ID(func, bpf_lsm_bpf_map_free)
 BTF_ID(func, bpf_lsm_bpf_prog)
 BTF_ID(func, bpf_lsm_bpf_prog_load)
 BTF_ID(func, bpf_lsm_bpf_prog_free)
+BTF_ID(func, bpf_lsm_bpf_token_create)
+BTF_ID(func, bpf_lsm_bpf_token_free)
+BTF_ID(func, bpf_lsm_bpf_token_cmd)
+BTF_ID(func, bpf_lsm_bpf_token_capable)
 BTF_ID(func, bpf_lsm_bprm_check_security)
 BTF_ID(func, bpf_lsm_bprm_committed_creds)
 BTF_ID(func, bpf_lsm_bprm_committing_creds)
diff --git a/kernel/bpf/token.c b/kernel/bpf/token.c
index 5a51e6b8f6bf..17212efcde60 100644
--- a/kernel/bpf/token.c
+++ b/kernel/bpf/token.c
@@ -7,6 +7,7 @@
 #include <linux/idr.h>
 #include <linux/namei.h>
 #include <linux/user_namespace.h>
+#include <linux/security.h>
 
 bool bpf_token_capable(const struct bpf_token *token, int cap)
 {
@@ -14,10 +15,9 @@ bool bpf_token_capable(const struct bpf_token *token, int cap)
 	 * token's userns is *exactly* the same as current user's userns
 	 */
 	if (token && current_user_ns() == token->userns) {
-		if (ns_capable(token->userns, cap))
-			return true;
-		if (cap != CAP_SYS_ADMIN && ns_capable(token->userns, CAP_SYS_ADMIN))
-			return true;
+		if (ns_capable(token->userns, cap) ||
+		    (cap != CAP_SYS_ADMIN && ns_capable(token->userns, CAP_SYS_ADMIN)))
+			return security_bpf_token_capable(token, cap) == 0;
 	}
 	/* otherwise fallback to capable() checks */
 	return capable(cap) || (cap != CAP_SYS_ADMIN && capable(CAP_SYS_ADMIN));
@@ -30,6 +30,7 @@ void bpf_token_inc(struct bpf_token *token)
 
 static void bpf_token_free(struct bpf_token *token)
 {
+	security_bpf_token_free(token);
 	put_user_ns(token->userns);
 	kvfree(token);
 }
@@ -186,6 +187,10 @@ int bpf_token_create(union bpf_attr *attr)
 	token->allowed_progs = mnt_opts->delegate_progs;
 	token->allowed_attachs = mnt_opts->delegate_attachs;
 
+	err = security_bpf_token_create(token, attr, &path);
+	if (err)
+		goto out_token;
+
 	fd = get_unused_fd_flags(O_CLOEXEC);
 	if (fd < 0) {
 		err = fd;
@@ -233,8 +238,9 @@ bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd)
 	 */
 	if (!token || current_user_ns() != token->userns)
 		return false;
-
-	return token->allowed_cmds & (1ULL << cmd);
+	if (!(token->allowed_cmds & (1ULL << cmd)))
+		return false;
+	return security_bpf_token_cmd(token, cmd) == 0;
 }
 
 bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type)
diff --git a/security/security.c b/security/security.c
index ad24cf36da94..088a79c35c26 100644
--- a/security/security.c
+++ b/security/security.c
@@ -5201,6 +5201,55 @@ int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr,
 	return call_int_hook(bpf_prog_load, 0, prog, attr, token);
 }
 
+/**
+ * security_bpf_token_create() - Check if creating of BPF token is allowed
+ * @token: BPF token object
+ * @attr: BPF syscall attributes used to create BPF token
+ * @path: path pointing to BPF FS mount point from which BPF token is created
+ *
+ * Do a check when the kernel instantiates a new BPF token object from BPF FS
+ * instance. This is also the point where LSM blob can be allocated for LSMs.
+ *
+ * Return: Returns 0 on success, error on failure.
+ */
+int security_bpf_token_create(struct bpf_token *token, union bpf_attr *attr,
+			      struct path *path)
+{
+	return call_int_hook(bpf_token_create, 0, token, attr, path);
+}
+
+/**
+ * security_bpf_token_cmd() - Check if BPF token is allowed to delegate
+ * requested BPF syscall command
+ * @token: BPF token object
+ * @cmd: BPF syscall command requested to be delegated by BPF token
+ *
+ * Do a check when the kernel decides whether provided BPF token should allow
+ * delegation of requested BPF syscall command.
+ *
+ * Return: Returns 0 on success, error on failure.
+ */
+int security_bpf_token_cmd(const struct bpf_token *token, enum bpf_cmd cmd)
+{
+	return call_int_hook(bpf_token_cmd, 0, token, cmd);
+}
+
+/**
+ * security_bpf_token_capable() - Check if BPF token is allowed to delegate
+ * requested BPF-related capability
+ * @token: BPF token object
+ * @cap: capabilities requested to be delegated by BPF token
+ *
+ * Do a check when the kernel decides whether provided BPF token should allow
+ * delegation of requested BPF-related capabilities.
+ *
+ * Return: Returns 0 on success, error on failure.
+ */
+int security_bpf_token_capable(const struct bpf_token *token, int cap)
+{
+	return call_int_hook(bpf_token_capable, 0, token, cap);
+}
+
 /**
  * security_bpf_map_free() - Free a bpf map's LSM blob
  * @map: bpf map
@@ -5222,6 +5271,17 @@ void security_bpf_prog_free(struct bpf_prog *prog)
 {
 	call_void_hook(bpf_prog_free, prog);
 }
+
+/**
+ * security_bpf_token_free() - Free a BPF token's LSM blob
+ * @token: BPF token struct
+ *
+ * Clean up the security information stored inside BPF token.
+ */
+void security_bpf_token_free(struct bpf_token *token)
+{
+	call_void_hook(bpf_token_free, token);
+}
 #endif /* CONFIG_BPF_SYSCALL */
 
 /**
-- 
cgit v1.2.3


From 3232e7aad11e541da86bbb1fa5ea5737b30bd006 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Tue, 5 Dec 2023 17:21:14 -0500
Subject: cgroup/cpuset: Include isolated cpuset CPUs in cpu_is_isolated()
 check

Currently, the cpu_is_isolated() function checks only the statically
isolated CPUs specified via the "isolcpus" and "nohz_full" kernel
command line options. This function is used by vmstat and memcg to
reduce interference with isolated CPUs by not doing stat flushing
or scheduling works on those CPUs.

Workloads running on isolated CPUs within isolated cpuset
partitions should receive the same treatment to reduce unnecessary
interference. This patch introduces a new cpuset_cpu_is_isolated()
function to be called by cpu_is_isolated() so that the set of dynamically
created cpuset isolated CPUs will be included in the check.

Assuming that testing a bit in a cpumask is atomic, no synchronization
primitive is currently used to synchronize access to the cpuset's
isolated_cpus mask.

Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/cpuset.h          |  6 ++++++
 include/linux/sched/isolation.h |  4 +++-
 kernel/cgroup/cpuset.c          | 11 +++++++++++
 3 files changed, 20 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index d629094fac6e..875d12598bd2 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -77,6 +77,7 @@ extern void cpuset_lock(void);
 extern void cpuset_unlock(void);
 extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask);
 extern bool cpuset_cpus_allowed_fallback(struct task_struct *p);
+extern bool cpuset_cpu_is_isolated(int cpu);
 extern nodemask_t cpuset_mems_allowed(struct task_struct *p);
 #define cpuset_current_mems_allowed (current->mems_allowed)
 void cpuset_init_current_mems_allowed(void);
@@ -207,6 +208,11 @@ static inline bool cpuset_cpus_allowed_fallback(struct task_struct *p)
 	return false;
 }
 
+static inline bool cpuset_cpu_is_isolated(int cpu)
+{
+	return false;
+}
+
 static inline nodemask_t cpuset_mems_allowed(struct task_struct *p)
 {
 	return node_possible_map;
diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h
index fe1a46f30d24..2b461129d1fa 100644
--- a/include/linux/sched/isolation.h
+++ b/include/linux/sched/isolation.h
@@ -2,6 +2,7 @@
 #define _LINUX_SCHED_ISOLATION_H
 
 #include <linux/cpumask.h>
+#include <linux/cpuset.h>
 #include <linux/init.h>
 #include <linux/tick.h>
 
@@ -67,7 +68,8 @@ static inline bool housekeeping_cpu(int cpu, enum hk_type type)
 static inline bool cpu_is_isolated(int cpu)
 {
 	return !housekeeping_test_cpu(cpu, HK_TYPE_DOMAIN) ||
-		 !housekeeping_test_cpu(cpu, HK_TYPE_TICK);
+	       !housekeeping_test_cpu(cpu, HK_TYPE_TICK) ||
+	       cpuset_cpu_is_isolated(cpu);
 }
 
 #endif /* _LINUX_SCHED_ISOLATION_H */
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 2a16df86c55c..dfbb16aca9f4 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1518,6 +1518,17 @@ static void update_unbound_workqueue_cpumask(bool isolcpus_updated)
 	WARN_ON_ONCE(ret < 0);
 }
 
+/**
+ * cpuset_cpu_is_isolated - Check if the given CPU is isolated
+ * @cpu: the CPU number to be checked
+ * Return: true if CPU is used in an isolated partition, false otherwise
+ */
+bool cpuset_cpu_is_isolated(int cpu)
+{
+	return cpumask_test_cpu(cpu, isolated_cpus);
+}
+EXPORT_SYMBOL_GPL(cpuset_cpu_is_isolated);
+
 /*
  * compute_effective_exclusive_cpumask - compute effective exclusive CPUs
  * @cs: cpuset
-- 
cgit v1.2.3


From be0a3600aa1ebe9d23243c91d41ab1a2d5091a9b Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Tue, 5 Dec 2023 13:24:08 +0100
Subject: thermal: sysfs: Rework the handling of trip point updates

Both trip_point_temp_store() and trip_point_hyst_store() use
thermal_zone_set_trip() to update a given trip point, but none of them
actually needs to change more than one field in struct thermal_trip
representing it.  However, each of them effectively calls
__thermal_zone_get_trip() twice in a row for the same trip index value,
once directly and once via thermal_zone_set_trip(), which is not
particularly efficient, and the way in which thermal_zone_set_trip()
carries out the update is not particularly straightforward.

Moreover, input processing need not be done under the thermal zone lock
in any of these functions.

Rework trip_point_temp_store() and trip_point_hyst_store() to address
the above, move the part of thermal_zone_set_trip() that is still
useful to a new function called thermal_zone_trip_updated() and drop
the rest of it.

While at it, make trip_point_hyst_store() reject negative hysteresis
values.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Daniel Lezcano <daniel.lezcano@linaro.org>
---
 drivers/thermal/thermal_core.h  |  2 ++
 drivers/thermal/thermal_sysfs.c | 52 ++++++++++++++++++++++++++++-------------
 drivers/thermal/thermal_trip.c  | 45 +++++++----------------------------
 include/linux/thermal.h         |  4 ----
 4 files changed, 47 insertions(+), 56 deletions(-)

(limited to 'include')

diff --git a/drivers/thermal/thermal_core.h b/drivers/thermal/thermal_core.h
index 0a3b3ec5120b..7dfe6c8deb8e 100644
--- a/drivers/thermal/thermal_core.h
+++ b/drivers/thermal/thermal_core.h
@@ -124,6 +124,8 @@ int __thermal_zone_get_trip(struct thermal_zone_device *tz, int trip_id,
 			    struct thermal_trip *trip);
 int thermal_zone_trip_id(struct thermal_zone_device *tz,
 			 const struct thermal_trip *trip);
+void thermal_zone_trip_updated(struct thermal_zone_device *tz,
+			       const struct thermal_trip *trip);
 int __thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp);
 
 /* sysfs I/F */
diff --git a/drivers/thermal/thermal_sysfs.c b/drivers/thermal/thermal_sysfs.c
index eef40d4f3063..06202aa50060 100644
--- a/drivers/thermal/thermal_sysfs.c
+++ b/drivers/thermal/thermal_sysfs.c
@@ -120,8 +120,13 @@ trip_point_temp_store(struct device *dev, struct device_attribute *attr,
 		      const char *buf, size_t count)
 {
 	struct thermal_zone_device *tz = to_thermal_zone(dev);
-	struct thermal_trip trip;
+	struct thermal_trip *trip;
 	int trip_id, ret;
+	int temp;
+
+	ret = kstrtoint(buf, 10, &temp);
+	if (ret)
+		return -EINVAL;
 
 	if (sscanf(attr->attr.name, "trip_point_%d_temp", &trip_id) != 1)
 		return -EINVAL;
@@ -133,15 +138,20 @@ trip_point_temp_store(struct device *dev, struct device_attribute *attr,
 		goto unlock;
 	}
 
-	ret = __thermal_zone_get_trip(tz, trip_id, &trip);
-	if (ret)
-		goto unlock;
+	trip = &tz->trips[trip_id];
 
-	ret = kstrtoint(buf, 10, &trip.temperature);
-	if (ret)
-		goto unlock;
+	if (temp != trip->temperature) {
+		if (tz->ops->set_trip_temp) {
+			ret = tz->ops->set_trip_temp(tz, trip_id, temp);
+			if (ret)
+				goto unlock;
+		}
+
+		trip->temperature = temp;
+
+		thermal_zone_trip_updated(tz, trip);
+	}
 
-	ret = thermal_zone_set_trip(tz, trip_id, &trip);
 unlock:
 	mutex_unlock(&tz->lock);
 	
@@ -179,8 +189,13 @@ trip_point_hyst_store(struct device *dev, struct device_attribute *attr,
 		      const char *buf, size_t count)
 {
 	struct thermal_zone_device *tz = to_thermal_zone(dev);
-	struct thermal_trip trip;
+	struct thermal_trip *trip;
 	int trip_id, ret;
+	int hyst;
+
+	ret = kstrtoint(buf, 10, &hyst);
+	if (ret || hyst < 0)
+		return -EINVAL;
 
 	if (sscanf(attr->attr.name, "trip_point_%d_hyst", &trip_id) != 1)
 		return -EINVAL;
@@ -192,15 +207,20 @@ trip_point_hyst_store(struct device *dev, struct device_attribute *attr,
 		goto unlock;
 	}
 
-	ret = __thermal_zone_get_trip(tz, trip_id, &trip);
-	if (ret)
-		goto unlock;
+	trip = &tz->trips[trip_id];
 
-	ret = kstrtoint(buf, 10, &trip.hysteresis);
-	if (ret)
-		goto unlock;
+	if (hyst != trip->hysteresis) {
+		if (tz->ops->set_trip_hyst) {
+			ret = tz->ops->set_trip_hyst(tz, trip_id, hyst);
+			if (ret)
+				goto unlock;
+		}
+
+		trip->hysteresis = hyst;
+
+		thermal_zone_trip_updated(tz, trip);
+	}
 
-	ret = thermal_zone_set_trip(tz, trip_id, &trip);
 unlock:
 	mutex_unlock(&tz->lock);
 
diff --git a/drivers/thermal/thermal_trip.c b/drivers/thermal/thermal_trip.c
index e3dd583234dd..90861dec7eb0 100644
--- a/drivers/thermal/thermal_trip.c
+++ b/drivers/thermal/thermal_trip.c
@@ -147,42 +147,6 @@ int thermal_zone_get_trip(struct thermal_zone_device *tz, int trip_id,
 }
 EXPORT_SYMBOL_GPL(thermal_zone_get_trip);
 
-int thermal_zone_set_trip(struct thermal_zone_device *tz, int trip_id,
-			  const struct thermal_trip *trip)
-{
-	struct thermal_trip t;
-	int ret;
-
-	ret = __thermal_zone_get_trip(tz, trip_id, &t);
-	if (ret)
-		return ret;
-
-	if (t.type != trip->type)
-		return -EINVAL;
-
-	if (t.temperature != trip->temperature && tz->ops->set_trip_temp) {
-		ret = tz->ops->set_trip_temp(tz, trip_id, trip->temperature);
-		if (ret)
-			return ret;
-	}
-
-	if (t.hysteresis != trip->hysteresis && tz->ops->set_trip_hyst) {
-		ret = tz->ops->set_trip_hyst(tz, trip_id, trip->hysteresis);
-		if (ret)
-			return ret;
-	}
-
-	if (tz->trips && (t.temperature != trip->temperature || t.hysteresis != trip->hysteresis))
-		tz->trips[trip_id] = *trip;
-
-	thermal_notify_tz_trip_change(tz->id, trip_id, trip->type,
-				      trip->temperature, trip->hysteresis);
-
-	__thermal_zone_device_update(tz, THERMAL_TRIP_CHANGED);
-
-	return 0;
-}
-
 int thermal_zone_trip_id(struct thermal_zone_device *tz,
 			 const struct thermal_trip *trip)
 {
@@ -192,3 +156,12 @@ int thermal_zone_trip_id(struct thermal_zone_device *tz,
 	 */
 	return trip - tz->trips;
 }
+
+void thermal_zone_trip_updated(struct thermal_zone_device *tz,
+			       const struct thermal_trip *trip)
+{
+	thermal_notify_tz_trip_change(tz->id, thermal_zone_trip_id(tz, trip),
+				      trip->type, trip->temperature,
+				      trip->hysteresis);
+	__thermal_zone_device_update(tz, THERMAL_TRIP_CHANGED);
+}
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 1f9ee869f9f9..0ea99f50d57c 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -282,10 +282,6 @@ int __thermal_zone_get_trip(struct thermal_zone_device *tz, int trip_id,
 			    struct thermal_trip *trip);
 int thermal_zone_get_trip(struct thermal_zone_device *tz, int trip_id,
 			  struct thermal_trip *trip);
-
-int thermal_zone_set_trip(struct thermal_zone_device *tz, int trip_id,
-			  const struct thermal_trip *trip);
-
 int for_each_thermal_trip(struct thermal_zone_device *tz,
 			  int (*cb)(struct thermal_trip *, void *),
 			  void *data);
-- 
cgit v1.2.3


From 4b7de801606e504e69689df71475d27e35336fb3 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Wed, 6 Dec 2023 09:30:40 +0100
Subject: bpf: Fix prog_array_map_poke_run map poke update

Lee pointed out issue found by syscaller [0] hitting BUG in prog array
map poke update in prog_array_map_poke_run function due to error value
returned from bpf_arch_text_poke function.

There's race window where bpf_arch_text_poke can fail due to missing
bpf program kallsym symbols, which is accounted for with check for
-EINVAL in that BUG_ON call.

The problem is that in such case we won't update the tail call jump
and cause imbalance for the next tail call update check which will
fail with -EBUSY in bpf_arch_text_poke.

I'm hitting following race during the program load:

  CPU 0                             CPU 1

  bpf_prog_load
    bpf_check
      do_misc_fixups
        prog_array_map_poke_track

                                    map_update_elem
                                      bpf_fd_array_map_update_elem
                                        prog_array_map_poke_run

                                          bpf_arch_text_poke returns -EINVAL

    bpf_prog_kallsyms_add

After bpf_arch_text_poke (CPU 1) fails to update the tail call jump, the next
poke update fails on expected jump instruction check in bpf_arch_text_poke
with -EBUSY and triggers the BUG_ON in prog_array_map_poke_run.

Similar race exists on the program unload.

Fixing this by moving the update to bpf_arch_poke_desc_update function which
makes sure we call __bpf_arch_text_poke that skips the bpf address check.

Each architecture has slightly different approach wrt looking up bpf address
in bpf_arch_text_poke, so instead of splitting the function or adding new
'checkip' argument in previous version, it seems best to move the whole
map_poke_run update as arch specific code.

  [0] https://syzkaller.appspot.com/bug?extid=97a4fe20470e9bc30810

Fixes: ebf7d1f508a7 ("bpf, x64: rework pro/epilogue and tailcall handling in JIT")
Reported-by: syzbot+97a4fe20470e9bc30810@syzkaller.appspotmail.com
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Cc: Lee Jones <lee@kernel.org>
Cc: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/bpf/20231206083041.1306660-2-jolsa@kernel.org
---
 arch/x86/net/bpf_jit_comp.c | 46 +++++++++++++++++++++++++++++++++++
 include/linux/bpf.h         |  3 +++
 kernel/bpf/arraymap.c       | 58 ++++++++-------------------------------------
 3 files changed, 59 insertions(+), 48 deletions(-)

(limited to 'include')

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 8c10d9abc239..e89e415aa743 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -3025,3 +3025,49 @@ void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp
 #endif
 	WARN(1, "verification of programs using bpf_throw should have failed\n");
 }
+
+void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke,
+			       struct bpf_prog *new, struct bpf_prog *old)
+{
+	u8 *old_addr, *new_addr, *old_bypass_addr;
+	int ret;
+
+	old_bypass_addr = old ? NULL : poke->bypass_addr;
+	old_addr = old ? (u8 *)old->bpf_func + poke->adj_off : NULL;
+	new_addr = new ? (u8 *)new->bpf_func + poke->adj_off : NULL;
+
+	/*
+	 * On program loading or teardown, the program's kallsym entry
+	 * might not be in place, so we use __bpf_arch_text_poke to skip
+	 * the kallsyms check.
+	 */
+	if (new) {
+		ret = __bpf_arch_text_poke(poke->tailcall_target,
+					   BPF_MOD_JUMP,
+					   old_addr, new_addr);
+		BUG_ON(ret < 0);
+		if (!old) {
+			ret = __bpf_arch_text_poke(poke->tailcall_bypass,
+						   BPF_MOD_JUMP,
+						   poke->bypass_addr,
+						   NULL);
+			BUG_ON(ret < 0);
+		}
+	} else {
+		ret = __bpf_arch_text_poke(poke->tailcall_bypass,
+					   BPF_MOD_JUMP,
+					   old_bypass_addr,
+					   poke->bypass_addr);
+		BUG_ON(ret < 0);
+		/* let other CPUs finish the execution of program
+		 * so that it will not possible to expose them
+		 * to invalid nop, stack unwind, nop state
+		 */
+		if (!ret)
+			synchronize_rcu();
+		ret = __bpf_arch_text_poke(poke->tailcall_target,
+					   BPF_MOD_JUMP,
+					   old_addr, NULL);
+		BUG_ON(ret < 0);
+	}
+}
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 6762dac3ef76..cff5bb08820e 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -3175,6 +3175,9 @@ enum bpf_text_poke_type {
 int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 		       void *addr1, void *addr2);
 
+void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke,
+			       struct bpf_prog *new, struct bpf_prog *old);
+
 void *bpf_arch_text_copy(void *dst, void *src, size_t len);
 int bpf_arch_text_invalidate(void *dst, size_t len);
 
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 2058e89b5ddd..c85ff9162a5c 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -1012,11 +1012,16 @@ static void prog_array_map_poke_untrack(struct bpf_map *map,
 	mutex_unlock(&aux->poke_mutex);
 }
 
+void __weak bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke,
+				      struct bpf_prog *new, struct bpf_prog *old)
+{
+	WARN_ON_ONCE(1);
+}
+
 static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
 				    struct bpf_prog *old,
 				    struct bpf_prog *new)
 {
-	u8 *old_addr, *new_addr, *old_bypass_addr;
 	struct prog_poke_elem *elem;
 	struct bpf_array_aux *aux;
 
@@ -1025,7 +1030,7 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
 
 	list_for_each_entry(elem, &aux->poke_progs, list) {
 		struct bpf_jit_poke_descriptor *poke;
-		int i, ret;
+		int i;
 
 		for (i = 0; i < elem->aux->size_poke_tab; i++) {
 			poke = &elem->aux->poke_tab[i];
@@ -1044,21 +1049,10 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
 			 *    activated, so tail call updates can arrive from here
 			 *    while JIT is still finishing its final fixup for
 			 *    non-activated poke entries.
-			 * 3) On program teardown, the program's kallsym entry gets
-			 *    removed out of RCU callback, but we can only untrack
-			 *    from sleepable context, therefore bpf_arch_text_poke()
-			 *    might not see that this is in BPF text section and
-			 *    bails out with -EINVAL. As these are unreachable since
-			 *    RCU grace period already passed, we simply skip them.
-			 * 4) Also programs reaching refcount of zero while patching
+			 * 3) Also programs reaching refcount of zero while patching
 			 *    is in progress is okay since we're protected under
 			 *    poke_mutex and untrack the programs before the JIT
-			 *    buffer is freed. When we're still in the middle of
-			 *    patching and suddenly kallsyms entry of the program
-			 *    gets evicted, we just skip the rest which is fine due
-			 *    to point 3).
-			 * 5) Any other error happening below from bpf_arch_text_poke()
-			 *    is a unexpected bug.
+			 *    buffer is freed.
 			 */
 			if (!READ_ONCE(poke->tailcall_target_stable))
 				continue;
@@ -1068,39 +1062,7 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
 			    poke->tail_call.key != key)
 				continue;
 
-			old_bypass_addr = old ? NULL : poke->bypass_addr;
-			old_addr = old ? (u8 *)old->bpf_func + poke->adj_off : NULL;
-			new_addr = new ? (u8 *)new->bpf_func + poke->adj_off : NULL;
-
-			if (new) {
-				ret = bpf_arch_text_poke(poke->tailcall_target,
-							 BPF_MOD_JUMP,
-							 old_addr, new_addr);
-				BUG_ON(ret < 0 && ret != -EINVAL);
-				if (!old) {
-					ret = bpf_arch_text_poke(poke->tailcall_bypass,
-								 BPF_MOD_JUMP,
-								 poke->bypass_addr,
-								 NULL);
-					BUG_ON(ret < 0 && ret != -EINVAL);
-				}
-			} else {
-				ret = bpf_arch_text_poke(poke->tailcall_bypass,
-							 BPF_MOD_JUMP,
-							 old_bypass_addr,
-							 poke->bypass_addr);
-				BUG_ON(ret < 0 && ret != -EINVAL);
-				/* let other CPUs finish the execution of program
-				 * so that it will not possible to expose them
-				 * to invalid nop, stack unwind, nop state
-				 */
-				if (!ret)
-					synchronize_rcu();
-				ret = bpf_arch_text_poke(poke->tailcall_target,
-							 BPF_MOD_JUMP,
-							 old_addr, NULL);
-				BUG_ON(ret < 0 && ret != -EINVAL);
-			}
+			bpf_arch_poke_desc_update(poke, new, old);
 		}
 	}
 }
-- 
cgit v1.2.3


From 7065eefb38f16c91e9ace36fb7c873e4c9857c27 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Wed, 6 Dec 2023 11:09:20 -0800
Subject: bpf: rename MAX_BPF_LINK_TYPE into __MAX_BPF_LINK_TYPE for
 consistency

To stay consistent with the naming pattern used for similar cases in BPF
UAPI (__MAX_BPF_ATTACH_TYPE, etc), rename MAX_BPF_LINK_TYPE into
__MAX_BPF_LINK_TYPE.

Also similar to MAX_BPF_ATTACH_TYPE and MAX_BPF_REG, add:

  #define MAX_BPF_LINK_TYPE __MAX_BPF_LINK_TYPE

Not all __MAX_xxx enums have such #define, so I'm not sure if we should
add it or not, but I figured I'll start with a completely backwards
compatible way, and we can drop that, if necessary.

Also adjust a selftest that used MAX_BPF_LINK_TYPE enum.

Suggested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20231206190920.1651226-1-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h                            | 4 +++-
 tools/include/uapi/linux/bpf.h                      | 4 +++-
 tools/testing/selftests/bpf/prog_tests/libbpf_str.c | 2 +-
 3 files changed, 7 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 4df2d025c784..e0545201b55f 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1108,9 +1108,11 @@ enum bpf_link_type {
 	BPF_LINK_TYPE_TCX = 11,
 	BPF_LINK_TYPE_UPROBE_MULTI = 12,
 	BPF_LINK_TYPE_NETKIT = 13,
-	MAX_BPF_LINK_TYPE,
+	__MAX_BPF_LINK_TYPE,
 };
 
+#define MAX_BPF_LINK_TYPE __MAX_BPF_LINK_TYPE
+
 enum bpf_perf_event_type {
 	BPF_PERF_EVENT_UNSPEC = 0,
 	BPF_PERF_EVENT_UPROBE = 1,
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 4df2d025c784..e0545201b55f 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1108,9 +1108,11 @@ enum bpf_link_type {
 	BPF_LINK_TYPE_TCX = 11,
 	BPF_LINK_TYPE_UPROBE_MULTI = 12,
 	BPF_LINK_TYPE_NETKIT = 13,
-	MAX_BPF_LINK_TYPE,
+	__MAX_BPF_LINK_TYPE,
 };
 
+#define MAX_BPF_LINK_TYPE __MAX_BPF_LINK_TYPE
+
 enum bpf_perf_event_type {
 	BPF_PERF_EVENT_UNSPEC = 0,
 	BPF_PERF_EVENT_UPROBE = 1,
diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c
index 384bc1f7a65e..62ea855ec4d0 100644
--- a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c
+++ b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c
@@ -87,7 +87,7 @@ static void test_libbpf_bpf_link_type_str(void)
 		const char *link_type_str;
 		char buf[256];
 
-		if (link_type == MAX_BPF_LINK_TYPE)
+		if (link_type == __MAX_BPF_LINK_TYPE)
 			continue;
 
 		link_type_name = btf__str_by_offset(btf, e->name_off);
-- 
cgit v1.2.3


From 187da0f8250aa94bd96266096aef6f694e0b4cd2 Mon Sep 17 00:00:00 2001
From: Mike Kravetz <mike.kravetz@oracle.com>
Date: Mon, 13 Nov 2023 17:20:33 -0800
Subject: hugetlb: fix null-ptr-deref in hugetlb_vma_lock_write

The routine __vma_private_lock tests for the existence of a reserve map
associated with a private hugetlb mapping.  A pointer to the reserve map
is in vma->vm_private_data.  __vma_private_lock was checking the pointer
for NULL.  However, it is possible that the low bits of the pointer could
be used as flags.  In such instances, vm_private_data is not NULL and not
a valid pointer.  This results in the null-ptr-deref reported by syzbot:

general protection fault, probably for non-canonical address 0xdffffc000000001d:
 0000 [#1] PREEMPT SMP KASAN
KASAN: null-ptr-deref in range [0x00000000000000e8-0x00000000000000ef]
CPU: 0 PID: 5048 Comm: syz-executor139 Not tainted 6.6.0-rc7-syzkaller-00142-g88
8cf78c29e2 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 1
0/09/2023
RIP: 0010:__lock_acquire+0x109/0x5de0 kernel/locking/lockdep.c:5004
...
Call Trace:
 <TASK>
 lock_acquire kernel/locking/lockdep.c:5753 [inline]
 lock_acquire+0x1ae/0x510 kernel/locking/lockdep.c:5718
 down_write+0x93/0x200 kernel/locking/rwsem.c:1573
 hugetlb_vma_lock_write mm/hugetlb.c:300 [inline]
 hugetlb_vma_lock_write+0xae/0x100 mm/hugetlb.c:291
 __hugetlb_zap_begin+0x1e9/0x2b0 mm/hugetlb.c:5447
 hugetlb_zap_begin include/linux/hugetlb.h:258 [inline]
 unmap_vmas+0x2f4/0x470 mm/memory.c:1733
 exit_mmap+0x1ad/0xa60 mm/mmap.c:3230
 __mmput+0x12a/0x4d0 kernel/fork.c:1349
 mmput+0x62/0x70 kernel/fork.c:1371
 exit_mm kernel/exit.c:567 [inline]
 do_exit+0x9ad/0x2a20 kernel/exit.c:861
 __do_sys_exit kernel/exit.c:991 [inline]
 __se_sys_exit kernel/exit.c:989 [inline]
 __x64_sys_exit+0x42/0x50 kernel/exit.c:989
 do_syscall_x64 arch/x86/entry/common.c:50 [inline]
 do_syscall_64+0x38/0xb0 arch/x86/entry/common.c:80
 entry_SYSCALL_64_after_hwframe+0x63/0xcd

Mask off low bit flags before checking for NULL pointer.  In addition, the
reserve map only 'belongs' to the OWNER (parent in parent/child
relationships) so also check for the OWNER flag.

Link: https://lkml.kernel.org/r/20231114012033.259600-1-mike.kravetz@oracle.com
Reported-by: syzbot+6ada951e7c0f7bc8a71e@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/linux-mm/00000000000078d1e00608d7878b@google.com/
Fixes: bf4916922c60 ("hugetlbfs: extend hugetlb_vma_lock to private VMAs")
Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: Rik van Riel <riel@surriel.com>
Cc: Edward Adam Davis <eadavis@qq.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Tom Rix <trix@redhat.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/hugetlb.h | 5 +----
 mm/hugetlb.c            | 7 +++++++
 2 files changed, 8 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index d3acecc5db4b..236ec7b63c54 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -1268,10 +1268,7 @@ static inline bool __vma_shareable_lock(struct vm_area_struct *vma)
 	return (vma->vm_flags & VM_MAYSHARE) && vma->vm_private_data;
 }
 
-static inline bool __vma_private_lock(struct vm_area_struct *vma)
-{
-	return (!(vma->vm_flags & VM_MAYSHARE)) && vma->vm_private_data;
-}
+bool __vma_private_lock(struct vm_area_struct *vma);
 
 /*
  * Safe version of huge_pte_offset() to check the locks.  See comments
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 1169ef2f2176..6feb3e0630d1 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1182,6 +1182,13 @@ static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag)
 	return (get_vma_private_data(vma) & flag) != 0;
 }
 
+bool __vma_private_lock(struct vm_area_struct *vma)
+{
+	return !(vma->vm_flags & VM_MAYSHARE) &&
+		get_vma_private_data(vma) & ~HPAGE_RESV_MASK &&
+		is_vma_resv_set(vma, HPAGE_RESV_OWNER);
+}
+
 void hugetlb_dup_vma_private(struct vm_area_struct *vma)
 {
 	VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma);
-- 
cgit v1.2.3


From 8e92157d7f6190c86bfd6144a409001469827100 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 28 Nov 2023 19:44:03 +0200
Subject: units: add missing header

BITS_PER_BYTE is defined in bits.h.

Link: https://lkml.kernel.org/r/20231128174404.393393-1-andriy.shevchenko@linux.intel.com
Fixes: e8eed5f7366f ("units: Add BYTES_PER_*BIT")
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Damian Muszynski <damian.muszynski@intel.com>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/units.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/units.h b/include/linux/units.h
index ff1bd6b5f5b3..45110daaf8d3 100644
--- a/include/linux/units.h
+++ b/include/linux/units.h
@@ -2,6 +2,7 @@
 #ifndef _LINUX_UNITS_H
 #define _LINUX_UNITS_H
 
+#include <linux/bits.h>
 #include <linux/math.h>
 
 /* Metric prefixes in accordance with Système international (d'unités) */
-- 
cgit v1.2.3


From 73424d00dc63ba681856e06cfb0a5abbdb62e2b5 Mon Sep 17 00:00:00 2001
From: Su Hui <suhui@nfschina.com>
Date: Thu, 30 Nov 2023 11:40:18 +0800
Subject: highmem: fix a memory copy problem in memcpy_from_folio

Clang static checker complains that value stored to 'from' is never read.
And memcpy_from_folio() only copy the last chunk memory from folio to
destination.  Use 'to += chunk' to replace 'from += chunk' to fix this
typo problem.

Link: https://lkml.kernel.org/r/20231130034017.1210429-1-suhui@nfschina.com
Fixes: b23d03ef7af5 ("highmem: add memcpy_to_folio() and memcpy_from_folio()")
Signed-off-by: Su Hui <suhui@nfschina.com>
Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Jiaqi Yan <jiaqiyan@google.com>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Peter Collingbourne <pcc@google.com>
Cc: Tom Rix <trix@redhat.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/highmem.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 4cacc0e43b51..be20cff4ba73 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -454,7 +454,7 @@ static inline void memcpy_from_folio(char *to, struct folio *folio,
 		memcpy(to, from, chunk);
 		kunmap_local(from);
 
-		from += chunk;
+		to += chunk;
 		offset += chunk;
 		len -= chunk;
 	} while (len > 0);
-- 
cgit v1.2.3


From f08a1c658257c73697a819c4ded3a84b6f0ead74 Mon Sep 17 00:00:00 2001
From: Song Liu <song@kernel.org>
Date: Wed, 6 Dec 2023 14:40:48 -0800
Subject: bpf: Let bpf_prog_pack_free handle any pointer
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently, bpf_prog_pack_free only can only free pointer to struct
bpf_binary_header, which is not flexible. Add a size argument to
bpf_prog_pack_free so that it can handle any pointer.

Signed-off-by: Song Liu <song@kernel.org>
Acked-by: Ilya Leoshkevich <iii@linux.ibm.com>
Tested-by: Ilya Leoshkevich <iii@linux.ibm.com>  # on s390x
Reviewed-by: Björn Töpel <bjorn@rivosinc.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20231206224054.492250-2-song@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/filter.h  |  2 +-
 kernel/bpf/core.c       | 21 ++++++++++-----------
 kernel/bpf/dispatcher.c |  5 +----
 3 files changed, 12 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 14354605ad26..12d907f17d36 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1067,7 +1067,7 @@ struct bpf_binary_header *
 bpf_jit_binary_pack_hdr(const struct bpf_prog *fp);
 
 void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns);
-void bpf_prog_pack_free(struct bpf_binary_header *hdr);
+void bpf_prog_pack_free(void *ptr, u32 size);
 
 static inline bool bpf_prog_kallsyms_verify_off(const struct bpf_prog *fp)
 {
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index ced511f44174..c34513d645c4 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -928,20 +928,20 @@ out:
 	return ptr;
 }
 
-void bpf_prog_pack_free(struct bpf_binary_header *hdr)
+void bpf_prog_pack_free(void *ptr, u32 size)
 {
 	struct bpf_prog_pack *pack = NULL, *tmp;
 	unsigned int nbits;
 	unsigned long pos;
 
 	mutex_lock(&pack_mutex);
-	if (hdr->size > BPF_PROG_PACK_SIZE) {
-		bpf_jit_free_exec(hdr);
+	if (size > BPF_PROG_PACK_SIZE) {
+		bpf_jit_free_exec(ptr);
 		goto out;
 	}
 
 	list_for_each_entry(tmp, &pack_list, list) {
-		if ((void *)hdr >= tmp->ptr && (tmp->ptr + BPF_PROG_PACK_SIZE) > (void *)hdr) {
+		if (ptr >= tmp->ptr && (tmp->ptr + BPF_PROG_PACK_SIZE) > ptr) {
 			pack = tmp;
 			break;
 		}
@@ -950,10 +950,10 @@ void bpf_prog_pack_free(struct bpf_binary_header *hdr)
 	if (WARN_ONCE(!pack, "bpf_prog_pack bug\n"))
 		goto out;
 
-	nbits = BPF_PROG_SIZE_TO_NBITS(hdr->size);
-	pos = ((unsigned long)hdr - (unsigned long)pack->ptr) >> BPF_PROG_CHUNK_SHIFT;
+	nbits = BPF_PROG_SIZE_TO_NBITS(size);
+	pos = ((unsigned long)ptr - (unsigned long)pack->ptr) >> BPF_PROG_CHUNK_SHIFT;
 
-	WARN_ONCE(bpf_arch_text_invalidate(hdr, hdr->size),
+	WARN_ONCE(bpf_arch_text_invalidate(ptr, size),
 		  "bpf_prog_pack bug: missing bpf_arch_text_invalidate?\n");
 
 	bitmap_clear(pack->bitmap, pos, nbits);
@@ -1100,8 +1100,7 @@ bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **image_ptr,
 
 	*rw_header = kvmalloc(size, GFP_KERNEL);
 	if (!*rw_header) {
-		bpf_arch_text_copy(&ro_header->size, &size, sizeof(size));
-		bpf_prog_pack_free(ro_header);
+		bpf_prog_pack_free(ro_header, size);
 		bpf_jit_uncharge_modmem(size);
 		return NULL;
 	}
@@ -1132,7 +1131,7 @@ int bpf_jit_binary_pack_finalize(struct bpf_prog *prog,
 	kvfree(rw_header);
 
 	if (IS_ERR(ptr)) {
-		bpf_prog_pack_free(ro_header);
+		bpf_prog_pack_free(ro_header, ro_header->size);
 		return PTR_ERR(ptr);
 	}
 	return 0;
@@ -1153,7 +1152,7 @@ void bpf_jit_binary_pack_free(struct bpf_binary_header *ro_header,
 {
 	u32 size = ro_header->size;
 
-	bpf_prog_pack_free(ro_header);
+	bpf_prog_pack_free(ro_header, size);
 	kvfree(rw_header);
 	bpf_jit_uncharge_modmem(size);
 }
diff --git a/kernel/bpf/dispatcher.c b/kernel/bpf/dispatcher.c
index fa3e9225aedc..56760fc10e78 100644
--- a/kernel/bpf/dispatcher.c
+++ b/kernel/bpf/dispatcher.c
@@ -150,10 +150,7 @@ void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from,
 			goto out;
 		d->rw_image = bpf_jit_alloc_exec(PAGE_SIZE);
 		if (!d->rw_image) {
-			u32 size = PAGE_SIZE;
-
-			bpf_arch_text_copy(d->image, &size, sizeof(size));
-			bpf_prog_pack_free((struct bpf_binary_header *)d->image);
+			bpf_prog_pack_free(d->image, PAGE_SIZE);
 			d->image = NULL;
 			goto out;
 		}
-- 
cgit v1.2.3


From 7a3d9a159b178e87306a6e989071ed9a114a1a31 Mon Sep 17 00:00:00 2001
From: Song Liu <song@kernel.org>
Date: Wed, 6 Dec 2023 14:40:49 -0800
Subject: bpf: Adjust argument names of arch_prepare_bpf_trampoline()

We are using "im" for "struct bpf_tramp_image" and "tr" for "struct
bpf_trampoline" in most of the code base. The only exception is the
prototype and fallback version of arch_prepare_bpf_trampoline(). Update
them to match the rest of the code base.

We mix "orig_call" and "func_addr" for the argument in different versions
of arch_prepare_bpf_trampoline(). s/orig_call/func_addr/g so they match.

Signed-off-by: Song Liu <song@kernel.org>
Acked-by: Ilya Leoshkevich <iii@linux.ibm.com>
Tested-by: Ilya Leoshkevich <iii@linux.ibm.com>  # on s390x
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20231206224054.492250-3-song@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/arm64/net/bpf_jit_comp.c | 10 +++++-----
 include/linux/bpf.h           |  4 ++--
 kernel/bpf/trampoline.c       |  4 ++--
 3 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 7d4af64e3982..d81b886ea4df 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -1828,7 +1828,7 @@ static void restore_args(struct jit_ctx *ctx, int args_off, int nregs)
  *
  */
 static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
-			      struct bpf_tramp_links *tlinks, void *orig_call,
+			      struct bpf_tramp_links *tlinks, void *func_addr,
 			      int nregs, u32 flags)
 {
 	int i;
@@ -1926,7 +1926,7 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
 
 	if (flags & BPF_TRAMP_F_IP_ARG) {
 		/* save ip address of the traced function */
-		emit_addr_mov_i64(A64_R(10), (const u64)orig_call, ctx);
+		emit_addr_mov_i64(A64_R(10), (const u64)func_addr, ctx);
 		emit(A64_STR64I(A64_R(10), A64_SP, ip_off), ctx);
 	}
 
@@ -2029,7 +2029,7 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
 int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image,
 				void *image_end, const struct btf_func_model *m,
 				u32 flags, struct bpf_tramp_links *tlinks,
-				void *orig_call)
+				void *func_addr)
 {
 	int i, ret;
 	int nregs = m->nr_args;
@@ -2050,7 +2050,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image,
 	if (nregs > 8)
 		return -ENOTSUPP;
 
-	ret = prepare_trampoline(&ctx, im, tlinks, orig_call, nregs, flags);
+	ret = prepare_trampoline(&ctx, im, tlinks, func_addr, nregs, flags);
 	if (ret < 0)
 		return ret;
 
@@ -2061,7 +2061,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image,
 	ctx.idx = 0;
 
 	jit_fill_hole(image, (unsigned int)(image_end - image));
-	ret = prepare_trampoline(&ctx, im, tlinks, orig_call, nregs, flags);
+	ret = prepare_trampoline(&ctx, im, tlinks, func_addr, nregs, flags);
 
 	if (ret > 0 && validate_code(&ctx) < 0)
 		ret = -EINVAL;
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 7a483f6b6d5f..17eb6d905204 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1098,10 +1098,10 @@ struct bpf_tramp_run_ctx;
  *      fexit = a set of program to run after original function
  */
 struct bpf_tramp_image;
-int arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end,
+int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end,
 				const struct btf_func_model *m, u32 flags,
 				struct bpf_tramp_links *tlinks,
-				void *orig_call);
+				void *func_addr);
 u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog,
 					     struct bpf_tramp_run_ctx *run_ctx);
 void notrace __bpf_prog_exit_sleepable_recur(struct bpf_prog *prog, u64 start,
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index e97aeda3a86b..e114a1c7961e 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -1032,10 +1032,10 @@ bpf_trampoline_exit_t bpf_trampoline_exit(const struct bpf_prog *prog)
 }
 
 int __weak
-arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end,
+arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end,
 			    const struct btf_func_model *m, u32 flags,
 			    struct bpf_tramp_links *tlinks,
-			    void *orig_call)
+			    void *func_addr)
 {
 	return -ENOTSUPP;
 }
-- 
cgit v1.2.3


From 82583daa2efc2e336962b231a46bad03a280b3e0 Mon Sep 17 00:00:00 2001
From: Song Liu <song@kernel.org>
Date: Wed, 6 Dec 2023 14:40:50 -0800
Subject: bpf: Add helpers for trampoline image management

As BPF trampoline of different archs moves from bpf_jit_[alloc|free]_exec()
to bpf_prog_pack_[alloc|free](), we need to use different _alloc, _free for
different archs during the transition. Add the following helpers for this
transition:

void *arch_alloc_bpf_trampoline(unsigned int size);
void arch_free_bpf_trampoline(void *image, unsigned int size);
void arch_protect_bpf_trampoline(void *image, unsigned int size);
void arch_unprotect_bpf_trampoline(void *image, unsigned int size);

The fallback version of these helpers require size <= PAGE_SIZE, but they
are only called with size == PAGE_SIZE. They will be called with size <
PAGE_SIZE when arch_bpf_trampoline_size() helper is introduced later.

Signed-off-by: Song Liu <song@kernel.org>
Acked-by: Ilya Leoshkevich <iii@linux.ibm.com>
Tested-by: Ilya Leoshkevich <iii@linux.ibm.com>  # on s390x
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20231206224054.492250-4-song@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h            |  5 +++++
 kernel/bpf/bpf_struct_ops.c    | 12 +++++------
 kernel/bpf/trampoline.c        | 46 +++++++++++++++++++++++++++++++++++-------
 net/bpf/bpf_dummy_struct_ops.c |  7 +++----
 4 files changed, 52 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 17eb6d905204..b7fca151cf1b 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1102,6 +1102,11 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 				const struct btf_func_model *m, u32 flags,
 				struct bpf_tramp_links *tlinks,
 				void *func_addr);
+void *arch_alloc_bpf_trampoline(unsigned int size);
+void arch_free_bpf_trampoline(void *image, unsigned int size);
+void arch_protect_bpf_trampoline(void *image, unsigned int size);
+void arch_unprotect_bpf_trampoline(void *image, unsigned int size);
+
 u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog,
 					     struct bpf_tramp_run_ctx *run_ctx);
 void notrace __bpf_prog_exit_sleepable_recur(struct bpf_prog *prog, u64 start,
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index db6176fb64dc..e9e95879bce2 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -515,7 +515,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 			if (err)
 				goto reset_unlock;
 		}
-		set_memory_rox((long)st_map->image, 1);
+		arch_protect_bpf_trampoline(st_map->image, PAGE_SIZE);
 		/* Let bpf_link handle registration & unregistration.
 		 *
 		 * Pair with smp_load_acquire() during lookup_elem().
@@ -524,7 +524,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 		goto unlock;
 	}
 
-	set_memory_rox((long)st_map->image, 1);
+	arch_protect_bpf_trampoline(st_map->image, PAGE_SIZE);
 	err = st_ops->reg(kdata);
 	if (likely(!err)) {
 		/* This refcnt increment on the map here after
@@ -547,8 +547,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 	 * there was a race in registering the struct_ops (under the same name) to
 	 * a sub-system through different struct_ops's maps.
 	 */
-	set_memory_nx((long)st_map->image, 1);
-	set_memory_rw((long)st_map->image, 1);
+	arch_unprotect_bpf_trampoline(st_map->image, PAGE_SIZE);
 
 reset_unlock:
 	bpf_struct_ops_map_put_progs(st_map);
@@ -616,7 +615,7 @@ static void __bpf_struct_ops_map_free(struct bpf_map *map)
 		bpf_struct_ops_map_put_progs(st_map);
 	bpf_map_area_free(st_map->links);
 	if (st_map->image) {
-		bpf_jit_free_exec(st_map->image);
+		arch_free_bpf_trampoline(st_map->image, PAGE_SIZE);
 		bpf_jit_uncharge_modmem(PAGE_SIZE);
 	}
 	bpf_map_area_free(st_map->uvalue);
@@ -691,7 +690,7 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
 		return ERR_PTR(ret);
 	}
 
-	st_map->image = bpf_jit_alloc_exec(PAGE_SIZE);
+	st_map->image = arch_alloc_bpf_trampoline(PAGE_SIZE);
 	if (!st_map->image) {
 		/* __bpf_struct_ops_map_free() uses st_map->image as flag
 		 * for "charged or not". In this case, we need to unchange
@@ -711,7 +710,6 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
 	}
 
 	mutex_init(&st_map->lock);
-	set_vm_flush_reset_perms(st_map->image);
 	bpf_map_init_from_attr(map, attr);
 
 	return map;
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index e114a1c7961e..affbcbf7e76e 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -254,7 +254,7 @@ bpf_trampoline_get_progs(const struct bpf_trampoline *tr, int *total, bool *ip_a
 static void bpf_tramp_image_free(struct bpf_tramp_image *im)
 {
 	bpf_image_ksym_del(&im->ksym);
-	bpf_jit_free_exec(im->image);
+	arch_free_bpf_trampoline(im->image, PAGE_SIZE);
 	bpf_jit_uncharge_modmem(PAGE_SIZE);
 	percpu_ref_exit(&im->pcref);
 	kfree_rcu(im, rcu);
@@ -365,10 +365,9 @@ static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key)
 		goto out_free_im;
 
 	err = -ENOMEM;
-	im->image = image = bpf_jit_alloc_exec(PAGE_SIZE);
+	im->image = image = arch_alloc_bpf_trampoline(PAGE_SIZE);
 	if (!image)
 		goto out_uncharge;
-	set_vm_flush_reset_perms(image);
 
 	err = percpu_ref_init(&im->pcref, __bpf_tramp_image_release, 0, GFP_KERNEL);
 	if (err)
@@ -381,7 +380,7 @@ static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key)
 	return im;
 
 out_free_image:
-	bpf_jit_free_exec(im->image);
+	arch_free_bpf_trampoline(im->image, PAGE_SIZE);
 out_uncharge:
 	bpf_jit_uncharge_modmem(PAGE_SIZE);
 out_free_im:
@@ -444,7 +443,7 @@ again:
 	if (err < 0)
 		goto out_free;
 
-	set_memory_rox((long)im->image, 1);
+	arch_protect_bpf_trampoline(im->image, PAGE_SIZE);
 
 	WARN_ON(tr->cur_image && total == 0);
 	if (tr->cur_image)
@@ -465,8 +464,7 @@ again:
 		tr->fops->trampoline = 0;
 
 		/* reset im->image memory attr for arch_prepare_bpf_trampoline */
-		set_memory_nx((long)im->image, 1);
-		set_memory_rw((long)im->image, 1);
+		arch_unprotect_bpf_trampoline(im->image, PAGE_SIZE);
 		goto again;
 	}
 #endif
@@ -1040,6 +1038,40 @@ arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image
 	return -ENOTSUPP;
 }
 
+void * __weak arch_alloc_bpf_trampoline(unsigned int size)
+{
+	void *image;
+
+	if (WARN_ON_ONCE(size > PAGE_SIZE))
+		return NULL;
+	image = bpf_jit_alloc_exec(PAGE_SIZE);
+	if (image)
+		set_vm_flush_reset_perms(image);
+	return image;
+}
+
+void __weak arch_free_bpf_trampoline(void *image, unsigned int size)
+{
+	WARN_ON_ONCE(size > PAGE_SIZE);
+	/* bpf_jit_free_exec doesn't need "size", but
+	 * bpf_prog_pack_free() needs it.
+	 */
+	bpf_jit_free_exec(image);
+}
+
+void __weak arch_protect_bpf_trampoline(void *image, unsigned int size)
+{
+	WARN_ON_ONCE(size > PAGE_SIZE);
+	set_memory_rox((long)image, 1);
+}
+
+void __weak arch_unprotect_bpf_trampoline(void *image, unsigned int size)
+{
+	WARN_ON_ONCE(size > PAGE_SIZE);
+	set_memory_nx((long)image, 1);
+	set_memory_rw((long)image, 1);
+}
+
 static int __init init_trampolines(void)
 {
 	int i;
diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c
index 5918d1b32e19..2748f9d77b18 100644
--- a/net/bpf/bpf_dummy_struct_ops.c
+++ b/net/bpf/bpf_dummy_struct_ops.c
@@ -101,12 +101,11 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr,
 		goto out;
 	}
 
-	image = bpf_jit_alloc_exec(PAGE_SIZE);
+	image = arch_alloc_bpf_trampoline(PAGE_SIZE);
 	if (!image) {
 		err = -ENOMEM;
 		goto out;
 	}
-	set_vm_flush_reset_perms(image);
 
 	link = kzalloc(sizeof(*link), GFP_USER);
 	if (!link) {
@@ -124,7 +123,7 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr,
 	if (err < 0)
 		goto out;
 
-	set_memory_rox((long)image, 1);
+	arch_protect_bpf_trampoline(image, PAGE_SIZE);
 	prog_ret = dummy_ops_call_op(image, args);
 
 	err = dummy_ops_copy_args(args);
@@ -134,7 +133,7 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr,
 		err = -EFAULT;
 out:
 	kfree(args);
-	bpf_jit_free_exec(image);
+	arch_free_bpf_trampoline(image, PAGE_SIZE);
 	if (link)
 		bpf_link_put(&link->link);
 	kfree(tlinks);
-- 
cgit v1.2.3


From 96d1b7c081c0c96cbe8901045f4ff15a2e9974a2 Mon Sep 17 00:00:00 2001
From: Song Liu <song@kernel.org>
Date: Wed, 6 Dec 2023 14:40:52 -0800
Subject: bpf: Add arch_bpf_trampoline_size()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This helper will be used to calculate the size of the trampoline before
allocating the memory.

arch_prepare_bpf_trampoline() for arm64 and riscv64 can use
arch_bpf_trampoline_size() to check the trampoline fits in the image.

OTOH, arch_prepare_bpf_trampoline() for s390 has to call the JIT process
twice, so it cannot use arch_bpf_trampoline_size().

Signed-off-by: Song Liu <song@kernel.org>
Acked-by: Ilya Leoshkevich <iii@linux.ibm.com>
Tested-by: Ilya Leoshkevich <iii@linux.ibm.com>  # on s390x
Acked-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Björn Töpel <bjorn@rivosinc.com>
Tested-by: Björn Töpel <bjorn@rivosinc.com> # on riscv
Link: https://lore.kernel.org/r/20231206224054.492250-6-song@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/arm64/net/bpf_jit_comp.c   | 56 ++++++++++++++++++++++++++++++-----------
 arch/riscv/net/bpf_jit_comp64.c | 22 ++++++++++++----
 arch/s390/net/bpf_jit_comp.c    | 56 +++++++++++++++++++++++++----------------
 arch/x86/net/bpf_jit_comp.c     | 40 ++++++++++++++++++++++++++---
 include/linux/bpf.h             |  2 ++
 kernel/bpf/trampoline.c         |  6 +++++
 6 files changed, 136 insertions(+), 46 deletions(-)

(limited to 'include')

diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index d81b886ea4df..a6671253b7ed 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -2026,18 +2026,10 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
 	return ctx->idx;
 }
 
-int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image,
-				void *image_end, const struct btf_func_model *m,
-				u32 flags, struct bpf_tramp_links *tlinks,
-				void *func_addr)
+static int btf_func_model_nregs(const struct btf_func_model *m)
 {
-	int i, ret;
 	int nregs = m->nr_args;
-	int max_insns = ((long)image_end - (long)image) / AARCH64_INSN_SIZE;
-	struct jit_ctx ctx = {
-		.image = NULL,
-		.idx = 0,
-	};
+	int i;
 
 	/* extra registers needed for struct argument */
 	for (i = 0; i < MAX_BPF_FUNC_ARGS; i++) {
@@ -2046,19 +2038,53 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image,
 			nregs += (m->arg_size[i] + 7) / 8 - 1;
 	}
 
+	return nregs;
+}
+
+int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
+			     struct bpf_tramp_links *tlinks, void *func_addr)
+{
+	struct jit_ctx ctx = {
+		.image = NULL,
+		.idx = 0,
+	};
+	struct bpf_tramp_image im;
+	int nregs, ret;
+
+	nregs = btf_func_model_nregs(m);
 	/* the first 8 registers are used for arguments */
 	if (nregs > 8)
 		return -ENOTSUPP;
 
-	ret = prepare_trampoline(&ctx, im, tlinks, func_addr, nregs, flags);
+	ret = prepare_trampoline(&ctx, &im, tlinks, func_addr, nregs, flags);
 	if (ret < 0)
 		return ret;
 
-	if (ret > max_insns)
-		return -EFBIG;
+	return ret < 0 ? ret : ret * AARCH64_INSN_SIZE;
+}
 
-	ctx.image = image;
-	ctx.idx = 0;
+int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image,
+				void *image_end, const struct btf_func_model *m,
+				u32 flags, struct bpf_tramp_links *tlinks,
+				void *func_addr)
+{
+	int ret, nregs;
+	struct jit_ctx ctx = {
+		.image = image,
+		.idx = 0,
+	};
+
+	nregs = btf_func_model_nregs(m);
+	/* the first 8 registers are used for arguments */
+	if (nregs > 8)
+		return -ENOTSUPP;
+
+	ret = arch_bpf_trampoline_size(m, flags, tlinks, func_addr);
+	if (ret < 0)
+		return ret;
+
+	if (ret > ((long)image_end - (long)image))
+		return -EFBIG;
 
 	jit_fill_hole(image, (unsigned int)(image_end - image));
 	ret = prepare_trampoline(&ctx, im, tlinks, func_addr, nregs, flags);
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 8581693e62d3..35747fafde57 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -1029,6 +1029,21 @@ out:
 	return ret;
 }
 
+int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
+			     struct bpf_tramp_links *tlinks, void *func_addr)
+{
+	struct bpf_tramp_image im;
+	struct rv_jit_context ctx;
+	int ret;
+
+	ctx.ninsns = 0;
+	ctx.insns = NULL;
+	ctx.ro_insns = NULL;
+	ret = __arch_prepare_bpf_trampoline(&im, m, tlinks, func_addr, flags, &ctx);
+
+	return ret < 0 ? ret : ninsns_rvoff(ctx.ninsns);
+}
+
 int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image,
 				void *image_end, const struct btf_func_model *m,
 				u32 flags, struct bpf_tramp_links *tlinks,
@@ -1037,14 +1052,11 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image,
 	int ret;
 	struct rv_jit_context ctx;
 
-	ctx.ninsns = 0;
-	ctx.insns = NULL;
-	ctx.ro_insns = NULL;
-	ret = __arch_prepare_bpf_trampoline(im, m, tlinks, func_addr, flags, &ctx);
+	ret = arch_bpf_trampoline_size(im, m, flags, tlinks, func_addr);
 	if (ret < 0)
 		return ret;
 
-	if (ninsns_rvoff(ret) > (long)image_end - (long)image)
+	if (ret > (long)image_end - (long)image)
 		return -EFBIG;
 
 	ctx.ninsns = 0;
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index bf06b7283f0c..cc129617480a 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -2637,6 +2637,21 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 	return 0;
 }
 
+int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
+			     struct bpf_tramp_links *tlinks, void *orig_call)
+{
+	struct bpf_tramp_image im;
+	struct bpf_tramp_jit tjit;
+	int ret;
+
+	memset(&tjit, 0, sizeof(tjit));
+
+	ret = __arch_prepare_bpf_trampoline(&im, &tjit, m, flags,
+					    tlinks, orig_call);
+
+	return ret < 0 ? ret : tjit.common.prg;
+}
+
 int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image,
 				void *image_end, const struct btf_func_model *m,
 				u32 flags, struct bpf_tramp_links *tlinks,
@@ -2644,30 +2659,27 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image,
 {
 	struct bpf_tramp_jit tjit;
 	int ret;
-	int i;
 
-	for (i = 0; i < 2; i++) {
-		if (i == 0) {
-			/* Compute offsets, check whether the code fits. */
-			memset(&tjit, 0, sizeof(tjit));
-		} else {
-			/* Generate the code. */
-			tjit.common.prg = 0;
-			tjit.common.prg_buf = image;
-		}
-		ret = __arch_prepare_bpf_trampoline(im, &tjit, m, flags,
-						    tlinks, func_addr);
-		if (ret < 0)
-			return ret;
-		if (tjit.common.prg > (char *)image_end - (char *)image)
-			/*
-			 * Use the same error code as for exceeding
-			 * BPF_MAX_TRAMP_LINKS.
-			 */
-			return -E2BIG;
-	}
+	/* Compute offsets, check whether the code fits. */
+	memset(&tjit, 0, sizeof(tjit));
+	ret = __arch_prepare_bpf_trampoline(im, &tjit, m, flags,
+					    tlinks, func_addr);
+
+	if (ret < 0)
+		return ret;
+	if (tjit.common.prg > (char *)image_end - (char *)image)
+		/*
+		 * Use the same error code as for exceeding
+		 * BPF_MAX_TRAMP_LINKS.
+		 */
+		return -E2BIG;
+
+	tjit.common.prg = 0;
+	tjit.common.prg_buf = image;
+	ret = __arch_prepare_bpf_trampoline(im, &tjit, m, flags,
+					    tlinks, func_addr);
 
-	return tjit.common.prg;
+	return ret < 0 ? ret : tjit.common.prg;
 }
 
 bool bpf_jit_supports_subprog_tailcalls(void)
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 5f7528cac344..5d75069fdcc2 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -2422,10 +2422,10 @@ static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog,
  * add rsp, 8                      // skip eth_type_trans's frame
  * ret                             // return to its caller
  */
-int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end,
-				const struct btf_func_model *m, u32 flags,
-				struct bpf_tramp_links *tlinks,
-				void *func_addr)
+static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end,
+					 const struct btf_func_model *m, u32 flags,
+					 struct bpf_tramp_links *tlinks,
+					 void *func_addr)
 {
 	int i, ret, nr_regs = m->nr_args, stack_size = 0;
 	int regs_off, nregs_off, ip_off, run_ctx_off, arg_stack_off, rbx_off;
@@ -2678,6 +2678,38 @@ cleanup:
 	return ret;
 }
 
+int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end,
+				const struct btf_func_model *m, u32 flags,
+				struct bpf_tramp_links *tlinks,
+				void *func_addr)
+{
+	return __arch_prepare_bpf_trampoline(im, image, image_end, m, flags, tlinks, func_addr);
+}
+
+int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
+			     struct bpf_tramp_links *tlinks, void *func_addr)
+{
+	struct bpf_tramp_image im;
+	void *image;
+	int ret;
+
+	/* Allocate a temporary buffer for __arch_prepare_bpf_trampoline().
+	 * This will NOT cause fragmentation in direct map, as we do not
+	 * call set_memory_*() on this buffer.
+	 *
+	 * We cannot use kvmalloc here, because we need image to be in
+	 * module memory range.
+	 */
+	image = bpf_jit_alloc_exec(PAGE_SIZE);
+	if (!image)
+		return -ENOMEM;
+
+	ret = __arch_prepare_bpf_trampoline(&im, image, image + PAGE_SIZE, m, flags,
+					    tlinks, func_addr);
+	bpf_jit_free_exec(image);
+	return ret;
+}
+
 static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs, u8 *image, u8 *buf)
 {
 	u8 *jg_reloc, *prog = *pprog;
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index b7fca151cf1b..2332ddeb396b 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1106,6 +1106,8 @@ void *arch_alloc_bpf_trampoline(unsigned int size);
 void arch_free_bpf_trampoline(void *image, unsigned int size);
 void arch_protect_bpf_trampoline(void *image, unsigned int size);
 void arch_unprotect_bpf_trampoline(void *image, unsigned int size);
+int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
+			     struct bpf_tramp_links *tlinks, void *func_addr);
 
 u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog,
 					     struct bpf_tramp_run_ctx *run_ctx);
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index affbcbf7e76e..b553cbd89e55 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -1072,6 +1072,12 @@ void __weak arch_unprotect_bpf_trampoline(void *image, unsigned int size)
 	set_memory_rw((long)image, 1);
 }
 
+int __weak arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
+				    struct bpf_tramp_links *tlinks, void *func_addr)
+{
+	return -ENOTSUPP;
+}
+
 static int __init init_trampolines(void)
 {
 	int i;
-- 
cgit v1.2.3


From 26ef208c209a0e6eed8942a5d191b39dccfa6e38 Mon Sep 17 00:00:00 2001
From: Song Liu <song@kernel.org>
Date: Wed, 6 Dec 2023 14:40:53 -0800
Subject: bpf: Use arch_bpf_trampoline_size
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Instead of blindly allocating PAGE_SIZE for each trampoline, check the size
of the trampoline with arch_bpf_trampoline_size(). This size is saved in
bpf_tramp_image->size, and used for modmem charge/uncharge. The fallback
arch_alloc_bpf_trampoline() still allocates a whole page because we need to
use set_memory_* to protect the memory.

struct_ops trampoline still uses a whole page for multiple trampolines.

With this size check at caller (regular trampoline and struct_ops
trampoline), remove arch_bpf_trampoline_size() from
arch_prepare_bpf_trampoline() in archs.

Also, update bpf_image_ksym_add() to handle symbol of different sizes.

Signed-off-by: Song Liu <song@kernel.org>
Acked-by: Ilya Leoshkevich <iii@linux.ibm.com>
Tested-by: Ilya Leoshkevich <iii@linux.ibm.com>  # on s390x
Acked-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Björn Töpel <bjorn@rivosinc.com>
Tested-by: Björn Töpel <bjorn@rivosinc.com> # on riscv
Link: https://lore.kernel.org/r/20231206224054.492250-7-song@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/arm64/net/bpf_jit_comp.c   |  7 ------
 arch/riscv/net/bpf_jit_comp64.c |  7 ------
 include/linux/bpf.h             |  3 ++-
 kernel/bpf/bpf_struct_ops.c     |  7 ++++++
 kernel/bpf/dispatcher.c         |  2 +-
 kernel/bpf/trampoline.c         | 55 +++++++++++++++++++++++++----------------
 6 files changed, 44 insertions(+), 37 deletions(-)

(limited to 'include')

diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index a6671253b7ed..8955da5c47cf 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -2079,13 +2079,6 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image,
 	if (nregs > 8)
 		return -ENOTSUPP;
 
-	ret = arch_bpf_trampoline_size(m, flags, tlinks, func_addr);
-	if (ret < 0)
-		return ret;
-
-	if (ret > ((long)image_end - (long)image))
-		return -EFBIG;
-
 	jit_fill_hole(image, (unsigned int)(image_end - image));
 	ret = prepare_trampoline(&ctx, im, tlinks, func_addr, nregs, flags);
 
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 35747fafde57..58dc64dd94a8 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -1052,13 +1052,6 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image,
 	int ret;
 	struct rv_jit_context ctx;
 
-	ret = arch_bpf_trampoline_size(im, m, flags, tlinks, func_addr);
-	if (ret < 0)
-		return ret;
-
-	if (ret > (long)image_end - (long)image)
-		return -EFBIG;
-
 	ctx.ninsns = 0;
 	/*
 	 * The bpf_int_jit_compile() uses a RW buffer (ctx.insns) to write the
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 2332ddeb396b..c1a06263a4f3 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1141,6 +1141,7 @@ enum bpf_tramp_prog_type {
 
 struct bpf_tramp_image {
 	void *image;
+	int size;
 	struct bpf_ksym ksym;
 	struct percpu_ref pcref;
 	void *ip_after_call;
@@ -1325,7 +1326,7 @@ int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_func
 void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from,
 				struct bpf_prog *to);
 /* Called only from JIT-enabled code, so there's no need for stubs. */
-void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym);
+void bpf_image_ksym_add(void *data, unsigned int size, struct bpf_ksym *ksym);
 void bpf_image_ksym_del(struct bpf_ksym *ksym);
 void bpf_ksym_add(struct bpf_ksym *ksym);
 void bpf_ksym_del(struct bpf_ksym *ksym);
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index e9e95879bce2..4d53c53fc5aa 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -355,6 +355,7 @@ int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks,
 				      void *image, void *image_end)
 {
 	u32 flags;
+	int size;
 
 	tlinks[BPF_TRAMP_FENTRY].links[0] = link;
 	tlinks[BPF_TRAMP_FENTRY].nr_links = 1;
@@ -362,6 +363,12 @@ int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks,
 	 * and it must be used alone.
 	 */
 	flags = model->ret_size > 0 ? BPF_TRAMP_F_RET_FENTRY_RET : 0;
+
+	size = arch_bpf_trampoline_size(model, flags, tlinks, NULL);
+	if (size < 0)
+		return size;
+	if (size > (unsigned long)image_end - (unsigned long)image)
+		return -E2BIG;
 	return arch_prepare_bpf_trampoline(NULL, image, image_end,
 					   model, flags, tlinks, NULL);
 }
diff --git a/kernel/bpf/dispatcher.c b/kernel/bpf/dispatcher.c
index 56760fc10e78..70fb82bf1637 100644
--- a/kernel/bpf/dispatcher.c
+++ b/kernel/bpf/dispatcher.c
@@ -154,7 +154,7 @@ void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from,
 			d->image = NULL;
 			goto out;
 		}
-		bpf_image_ksym_add(d->image, &d->ksym);
+		bpf_image_ksym_add(d->image, PAGE_SIZE, &d->ksym);
 	}
 
 	prev_num_progs = d->num_progs;
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index b553cbd89e55..d382f5ebe06c 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -115,10 +115,10 @@ bool bpf_prog_has_trampoline(const struct bpf_prog *prog)
 		(ptype == BPF_PROG_TYPE_LSM && eatype == BPF_LSM_MAC);
 }
 
-void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym)
+void bpf_image_ksym_add(void *data, unsigned int size, struct bpf_ksym *ksym)
 {
 	ksym->start = (unsigned long) data;
-	ksym->end = ksym->start + PAGE_SIZE;
+	ksym->end = ksym->start + size;
 	bpf_ksym_add(ksym);
 	perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF, ksym->start,
 			   PAGE_SIZE, false, ksym->name);
@@ -254,8 +254,8 @@ bpf_trampoline_get_progs(const struct bpf_trampoline *tr, int *total, bool *ip_a
 static void bpf_tramp_image_free(struct bpf_tramp_image *im)
 {
 	bpf_image_ksym_del(&im->ksym);
-	arch_free_bpf_trampoline(im->image, PAGE_SIZE);
-	bpf_jit_uncharge_modmem(PAGE_SIZE);
+	arch_free_bpf_trampoline(im->image, im->size);
+	bpf_jit_uncharge_modmem(im->size);
 	percpu_ref_exit(&im->pcref);
 	kfree_rcu(im, rcu);
 }
@@ -349,7 +349,7 @@ static void bpf_tramp_image_put(struct bpf_tramp_image *im)
 	call_rcu_tasks_trace(&im->rcu, __bpf_tramp_image_put_rcu_tasks);
 }
 
-static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key)
+static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key, int size)
 {
 	struct bpf_tramp_image *im;
 	struct bpf_ksym *ksym;
@@ -360,12 +360,13 @@ static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key)
 	if (!im)
 		goto out;
 
-	err = bpf_jit_charge_modmem(PAGE_SIZE);
+	err = bpf_jit_charge_modmem(size);
 	if (err)
 		goto out_free_im;
+	im->size = size;
 
 	err = -ENOMEM;
-	im->image = image = arch_alloc_bpf_trampoline(PAGE_SIZE);
+	im->image = image = arch_alloc_bpf_trampoline(size);
 	if (!image)
 		goto out_uncharge;
 
@@ -376,13 +377,13 @@ static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key)
 	ksym = &im->ksym;
 	INIT_LIST_HEAD_RCU(&ksym->lnode);
 	snprintf(ksym->name, KSYM_NAME_LEN, "bpf_trampoline_%llu", key);
-	bpf_image_ksym_add(image, ksym);
+	bpf_image_ksym_add(image, size, ksym);
 	return im;
 
 out_free_image:
-	arch_free_bpf_trampoline(im->image, PAGE_SIZE);
+	arch_free_bpf_trampoline(im->image, im->size);
 out_uncharge:
-	bpf_jit_uncharge_modmem(PAGE_SIZE);
+	bpf_jit_uncharge_modmem(size);
 out_free_im:
 	kfree(im);
 out:
@@ -395,7 +396,7 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut
 	struct bpf_tramp_links *tlinks;
 	u32 orig_flags = tr->flags;
 	bool ip_arg = false;
-	int err, total;
+	int err, total, size;
 
 	tlinks = bpf_trampoline_get_progs(tr, &total, &ip_arg);
 	if (IS_ERR(tlinks))
@@ -408,12 +409,6 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut
 		goto out;
 	}
 
-	im = bpf_tramp_image_alloc(tr->key);
-	if (IS_ERR(im)) {
-		err = PTR_ERR(im);
-		goto out;
-	}
-
 	/* clear all bits except SHARE_IPMODIFY and TAIL_CALL_CTX */
 	tr->flags &= (BPF_TRAMP_F_SHARE_IPMODIFY | BPF_TRAMP_F_TAIL_CALL_CTX);
 
@@ -437,13 +432,31 @@ again:
 		tr->flags |= BPF_TRAMP_F_ORIG_STACK;
 #endif
 
-	err = arch_prepare_bpf_trampoline(im, im->image, im->image + PAGE_SIZE,
+	size = arch_bpf_trampoline_size(&tr->func.model, tr->flags,
+					tlinks, tr->func.addr);
+	if (size < 0) {
+		err = size;
+		goto out;
+	}
+
+	if (size > PAGE_SIZE) {
+		err = -E2BIG;
+		goto out;
+	}
+
+	im = bpf_tramp_image_alloc(tr->key, size);
+	if (IS_ERR(im)) {
+		err = PTR_ERR(im);
+		goto out;
+	}
+
+	err = arch_prepare_bpf_trampoline(im, im->image, im->image + size,
 					  &tr->func.model, tr->flags, tlinks,
 					  tr->func.addr);
 	if (err < 0)
 		goto out_free;
 
-	arch_protect_bpf_trampoline(im->image, PAGE_SIZE);
+	arch_protect_bpf_trampoline(im->image, im->size);
 
 	WARN_ON(tr->cur_image && total == 0);
 	if (tr->cur_image)
@@ -463,8 +476,8 @@ again:
 		tr->fops->func = NULL;
 		tr->fops->trampoline = 0;
 
-		/* reset im->image memory attr for arch_prepare_bpf_trampoline */
-		arch_unprotect_bpf_trampoline(im->image, PAGE_SIZE);
+		/* free im memory and reallocate later */
+		bpf_tramp_image_free(im);
 		goto again;
 	}
 #endif
-- 
cgit v1.2.3


From f922b16aa5fad7284e2b7fd7c22bab13c0e418b6 Mon Sep 17 00:00:00 2001
From: Jay Buddhabhatti <jay.buddhabhatti@amd.com>
Date: Wed, 29 Nov 2023 03:27:09 -0800
Subject: firmware: xilinx: Update firmware call interface to support
 additional args

System-level platform management layer (do_fw_call()) has support for
maximum of 5 arguments as of now (1 EEMI API ID + 4 command arguments).
In order to support new EEMI PM_IOCTL IDs (Secure Read/Write), this
support must be extended to support one additional argument, which
results in a configuration of - 1 EEMI API ID + 5 command arguments.

Update zynqmp_pm_invoke_fn() and do_fw_call() with this new definition
containing variable arguments. As a result, update all the references
to pm invoke function with the updated definition.

Co-developed-by: Izhar Ameer Shaikh <izhar.ameer.shaikh@amd.com>
Signed-off-by: Izhar Ameer Shaikh <izhar.ameer.shaikh@amd.com>
Signed-off-by: Jay Buddhabhatti <jay.buddhabhatti@amd.com>
Link: https://lore.kernel.org/r/20231129112713.22718-2-jay.buddhabhatti@amd.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/xilinx/zynqmp.c        | 278 +++++++++++++++-----------------
 drivers/soc/xilinx/xlnx_event_manager.c |   2 +-
 drivers/soc/xilinx/zynqmp_power.c       |   2 +-
 include/linux/firmware/xlnx-zynqmp.h    |   3 +-
 4 files changed, 132 insertions(+), 153 deletions(-)

(limited to 'include')

diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c
index 7156b4884b41..2a7fd3fbac8c 100644
--- a/drivers/firmware/xilinx/zynqmp.c
+++ b/drivers/firmware/xilinx/zynqmp.c
@@ -106,8 +106,7 @@ static int zynqmp_pm_ret_code(u32 ret_status)
 	}
 }
 
-static noinline int do_fw_call_fail(u64 arg0, u64 arg1, u64 arg2,
-				    u32 *ret_payload)
+static noinline int do_fw_call_fail(u32 *ret_payload, u32 num_args, ...)
 {
 	return -ENODEV;
 }
@@ -116,25 +115,35 @@ static noinline int do_fw_call_fail(u64 arg0, u64 arg1, u64 arg2,
  * PM function call wrapper
  * Invoke do_fw_call_smc or do_fw_call_hvc, depending on the configuration
  */
-static int (*do_fw_call)(u64, u64, u64, u32 *ret_payload) = do_fw_call_fail;
+static int (*do_fw_call)(u32 *ret_payload, u32, ...) = do_fw_call_fail;
 
 /**
  * do_fw_call_smc() - Call system-level platform management layer (SMC)
- * @arg0:		Argument 0 to SMC call
- * @arg1:		Argument 1 to SMC call
- * @arg2:		Argument 2 to SMC call
+ * @num_args:		Number of variable arguments should be <= 8
  * @ret_payload:	Returned value array
  *
  * Invoke platform management function via SMC call (no hypervisor present).
  *
  * Return: Returns status, either success or error+reason
  */
-static noinline int do_fw_call_smc(u64 arg0, u64 arg1, u64 arg2,
-				   u32 *ret_payload)
+static noinline int do_fw_call_smc(u32 *ret_payload, u32 num_args, ...)
 {
 	struct arm_smccc_res res;
+	u64 args[8] = {0};
+	va_list arg_list;
+	u8 i;
 
-	arm_smccc_smc(arg0, arg1, arg2, 0, 0, 0, 0, 0, &res);
+	if (num_args > 8)
+		return -EINVAL;
+
+	va_start(arg_list, num_args);
+
+	for (i = 0; i < num_args; i++)
+		args[i] = va_arg(arg_list, u64);
+
+	va_end(arg_list);
+
+	arm_smccc_smc(args[0], args[1], args[2], args[3], args[4], args[5], args[6], args[7], &res);
 
 	if (ret_payload) {
 		ret_payload[0] = lower_32_bits(res.a0);
@@ -148,9 +157,7 @@ static noinline int do_fw_call_smc(u64 arg0, u64 arg1, u64 arg2,
 
 /**
  * do_fw_call_hvc() - Call system-level platform management layer (HVC)
- * @arg0:		Argument 0 to HVC call
- * @arg1:		Argument 1 to HVC call
- * @arg2:		Argument 2 to HVC call
+ * @num_args:		Number of variable arguments should be <= 8
  * @ret_payload:	Returned value array
  *
  * Invoke platform management function via HVC
@@ -159,12 +166,24 @@ static noinline int do_fw_call_smc(u64 arg0, u64 arg1, u64 arg2,
  *
  * Return: Returns status, either success or error+reason
  */
-static noinline int do_fw_call_hvc(u64 arg0, u64 arg1, u64 arg2,
-				   u32 *ret_payload)
+static noinline int do_fw_call_hvc(u32 *ret_payload, u32 num_args, ...)
 {
 	struct arm_smccc_res res;
+	u64 args[8] = {0};
+	va_list arg_list;
+	u8 i;
+
+	if (num_args > 8)
+		return -EINVAL;
+
+	va_start(arg_list, num_args);
+
+	for (i = 0; i < num_args; i++)
+		args[i] = va_arg(arg_list, u64);
 
-	arm_smccc_hvc(arg0, arg1, arg2, 0, 0, 0, 0, 0, &res);
+	va_end(arg_list);
+
+	arm_smccc_hvc(args[0], args[1], args[2], args[3], args[4], args[5], args[6], args[7], &res);
 
 	if (ret_payload) {
 		ret_payload[0] = lower_32_bits(res.a0);
@@ -184,7 +203,7 @@ static int __do_feature_check_call(const u32 api_id, u32 *ret_payload)
 	smc_arg[0] = PM_SIP_SVC | PM_FEATURE_CHECK;
 	smc_arg[1] = api_id;
 
-	ret = do_fw_call(smc_arg[0], smc_arg[1], 0, ret_payload);
+	ret = do_fw_call(ret_payload, 2, smc_arg[0], smc_arg[1]);
 	if (ret)
 		ret = -EOPNOTSUPP;
 	else
@@ -295,11 +314,8 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_is_function_supported);
  * zynqmp_pm_invoke_fn() - Invoke the system-level platform management layer
  *			   caller function depending on the configuration
  * @pm_api_id:		Requested PM-API call
- * @arg0:		Argument 0 to requested PM-API call
- * @arg1:		Argument 1 to requested PM-API call
- * @arg2:		Argument 2 to requested PM-API call
- * @arg3:		Argument 3 to requested PM-API call
  * @ret_payload:	Returned value array
+ * @num_args:		Number of arguments to requested PM-API call
  *
  * Invoke platform management function for SMC or HVC call, depending on
  * configuration.
@@ -316,26 +332,38 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_is_function_supported);
  *
  * Return: Returns status, either success or error+reason
  */
-int zynqmp_pm_invoke_fn(u32 pm_api_id, u32 arg0, u32 arg1,
-			u32 arg2, u32 arg3, u32 *ret_payload)
+int zynqmp_pm_invoke_fn(u32 pm_api_id, u32 *ret_payload, u32 num_args, ...)
 {
 	/*
 	 * Added SIP service call Function Identifier
 	 * Make sure to stay in x0 register
 	 */
-	u64 smc_arg[4];
-	int ret;
+	u64 smc_arg[8];
+	int ret, i;
+	va_list arg_list;
+	u32 args[14] = {0};
+
+	if (num_args > 14)
+		return -EINVAL;
+
+	va_start(arg_list, num_args);
 
 	/* Check if feature is supported or not */
 	ret = zynqmp_pm_feature(pm_api_id);
 	if (ret < 0)
 		return ret;
 
+	for (i = 0; i < num_args; i++)
+		args[i] = va_arg(arg_list, u32);
+
+	va_end(arg_list);
+
 	smc_arg[0] = PM_SIP_SVC | pm_api_id;
-	smc_arg[1] = ((u64)arg1 << 32) | arg0;
-	smc_arg[2] = ((u64)arg3 << 32) | arg2;
+	for (i = 0; i < 7; i++)
+		smc_arg[i + 1] = ((u64)args[(i * 2) + 1] << 32) | args[i * 2];
 
-	return do_fw_call(smc_arg[0], smc_arg[1], smc_arg[2], ret_payload);
+	return do_fw_call(ret_payload, 8, smc_arg[0], smc_arg[1], smc_arg[2], smc_arg[3],
+			  smc_arg[4], smc_arg[5], smc_arg[6], smc_arg[7]);
 }
 
 static u32 pm_api_version;
@@ -347,14 +375,12 @@ int zynqmp_pm_register_sgi(u32 sgi_num, u32 reset)
 {
 	int ret;
 
-	ret = zynqmp_pm_invoke_fn(TF_A_PM_REGISTER_SGI, sgi_num, reset, 0, 0,
-				  NULL);
+	ret = zynqmp_pm_invoke_fn(TF_A_PM_REGISTER_SGI, NULL, 2, sgi_num, reset);
 	if (!ret)
 		return ret;
 
 	/* try old implementation as fallback strategy if above fails */
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_REGISTER_SGI, sgi_num,
-				   reset, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 3, IOCTL_REGISTER_SGI, sgi_num, reset);
 }
 
 /**
@@ -376,7 +402,7 @@ int zynqmp_pm_get_api_version(u32 *version)
 		*version = pm_api_version;
 		return 0;
 	}
-	ret = zynqmp_pm_invoke_fn(PM_GET_API_VERSION, 0, 0, 0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_GET_API_VERSION, ret_payload, 0);
 	*version = ret_payload[1];
 
 	return ret;
@@ -399,7 +425,7 @@ int zynqmp_pm_get_chipid(u32 *idcode, u32 *version)
 	if (!idcode || !version)
 		return -EINVAL;
 
-	ret = zynqmp_pm_invoke_fn(PM_GET_CHIPID, 0, 0, 0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_GET_CHIPID, ret_payload, 0);
 	*idcode = ret_payload[1];
 	*version = ret_payload[2];
 
@@ -427,7 +453,7 @@ static int zynqmp_pm_get_family_info(u32 *family, u32 *subfamily)
 		return 0;
 	}
 
-	ret = zynqmp_pm_invoke_fn(PM_GET_CHIPID, 0, 0, 0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_GET_CHIPID, ret_payload, 0);
 	if (ret < 0)
 		return ret;
 
@@ -459,8 +485,7 @@ static int zynqmp_pm_get_trustzone_version(u32 *version)
 		*version = pm_tz_version;
 		return 0;
 	}
-	ret = zynqmp_pm_invoke_fn(PM_GET_TRUSTZONE_VERSION, 0, 0,
-				  0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_GET_TRUSTZONE_VERSION, ret_payload, 0);
 	*version = ret_payload[1];
 
 	return ret;
@@ -507,8 +532,8 @@ int zynqmp_pm_query_data(struct zynqmp_pm_query_data qdata, u32 *out)
 {
 	int ret;
 
-	ret = zynqmp_pm_invoke_fn(PM_QUERY_DATA, qdata.qid, qdata.arg1,
-				  qdata.arg2, qdata.arg3, out);
+	ret = zynqmp_pm_invoke_fn(PM_QUERY_DATA, out, 4, qdata.qid, qdata.arg1, qdata.arg2,
+				  qdata.arg3);
 
 	/*
 	 * For clock name query, all bytes in SMC response are clock name
@@ -530,7 +555,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_query_data);
  */
 int zynqmp_pm_clock_enable(u32 clock_id)
 {
-	return zynqmp_pm_invoke_fn(PM_CLOCK_ENABLE, clock_id, 0, 0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_CLOCK_ENABLE, NULL, 1, clock_id);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_clock_enable);
 
@@ -545,7 +570,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_clock_enable);
  */
 int zynqmp_pm_clock_disable(u32 clock_id)
 {
-	return zynqmp_pm_invoke_fn(PM_CLOCK_DISABLE, clock_id, 0, 0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_CLOCK_DISABLE, NULL, 1, clock_id);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_clock_disable);
 
@@ -564,8 +589,7 @@ int zynqmp_pm_clock_getstate(u32 clock_id, u32 *state)
 	u32 ret_payload[PAYLOAD_ARG_CNT];
 	int ret;
 
-	ret = zynqmp_pm_invoke_fn(PM_CLOCK_GETSTATE, clock_id, 0,
-				  0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_CLOCK_GETSTATE, ret_payload, 1, clock_id);
 	*state = ret_payload[1];
 
 	return ret;
@@ -584,8 +608,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_clock_getstate);
  */
 int zynqmp_pm_clock_setdivider(u32 clock_id, u32 divider)
 {
-	return zynqmp_pm_invoke_fn(PM_CLOCK_SETDIVIDER, clock_id, divider,
-				   0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_CLOCK_SETDIVIDER, NULL, 2, clock_id, divider);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_clock_setdivider);
 
@@ -604,8 +627,7 @@ int zynqmp_pm_clock_getdivider(u32 clock_id, u32 *divider)
 	u32 ret_payload[PAYLOAD_ARG_CNT];
 	int ret;
 
-	ret = zynqmp_pm_invoke_fn(PM_CLOCK_GETDIVIDER, clock_id, 0,
-				  0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_CLOCK_GETDIVIDER, ret_payload, 1, clock_id);
 	*divider = ret_payload[1];
 
 	return ret;
@@ -623,10 +645,8 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_clock_getdivider);
  */
 int zynqmp_pm_clock_setrate(u32 clock_id, u64 rate)
 {
-	return zynqmp_pm_invoke_fn(PM_CLOCK_SETRATE, clock_id,
-				   lower_32_bits(rate),
-				   upper_32_bits(rate),
-				   0, NULL);
+	return zynqmp_pm_invoke_fn(PM_CLOCK_SETRATE, NULL, 3, clock_id, lower_32_bits(rate),
+				   upper_32_bits(rate));
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_clock_setrate);
 
@@ -645,8 +665,7 @@ int zynqmp_pm_clock_getrate(u32 clock_id, u64 *rate)
 	u32 ret_payload[PAYLOAD_ARG_CNT];
 	int ret;
 
-	ret = zynqmp_pm_invoke_fn(PM_CLOCK_GETRATE, clock_id, 0,
-				  0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_CLOCK_GETRATE, ret_payload, 1, clock_id);
 	*rate = ((u64)ret_payload[2] << 32) | ret_payload[1];
 
 	return ret;
@@ -664,8 +683,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_clock_getrate);
  */
 int zynqmp_pm_clock_setparent(u32 clock_id, u32 parent_id)
 {
-	return zynqmp_pm_invoke_fn(PM_CLOCK_SETPARENT, clock_id,
-				   parent_id, 0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_CLOCK_SETPARENT, NULL, 2, clock_id, parent_id);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_clock_setparent);
 
@@ -684,8 +702,7 @@ int zynqmp_pm_clock_getparent(u32 clock_id, u32 *parent_id)
 	u32 ret_payload[PAYLOAD_ARG_CNT];
 	int ret;
 
-	ret = zynqmp_pm_invoke_fn(PM_CLOCK_GETPARENT, clock_id, 0,
-				  0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_CLOCK_GETPARENT, ret_payload, 1, clock_id);
 	*parent_id = ret_payload[1];
 
 	return ret;
@@ -704,8 +721,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_clock_getparent);
  */
 int zynqmp_pm_set_pll_frac_mode(u32 clk_id, u32 mode)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_SET_PLL_FRAC_MODE,
-				   clk_id, mode, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 4, 0, IOCTL_SET_PLL_FRAC_MODE, clk_id, mode);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_set_pll_frac_mode);
 
@@ -721,8 +737,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_set_pll_frac_mode);
  */
 int zynqmp_pm_get_pll_frac_mode(u32 clk_id, u32 *mode)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_GET_PLL_FRAC_MODE,
-				   clk_id, 0, mode);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, mode, 3, 0, IOCTL_GET_PLL_FRAC_MODE, clk_id);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_get_pll_frac_mode);
 
@@ -739,8 +754,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_get_pll_frac_mode);
  */
 int zynqmp_pm_set_pll_frac_data(u32 clk_id, u32 data)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_SET_PLL_FRAC_DATA,
-				   clk_id, data, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 4, 0, IOCTL_SET_PLL_FRAC_DATA, clk_id, data);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_set_pll_frac_data);
 
@@ -756,8 +770,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_set_pll_frac_data);
  */
 int zynqmp_pm_get_pll_frac_data(u32 clk_id, u32 *data)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_GET_PLL_FRAC_DATA,
-				   clk_id, 0, data);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, data, 3, 0, IOCTL_GET_PLL_FRAC_DATA, clk_id);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_get_pll_frac_data);
 
@@ -778,9 +791,8 @@ int zynqmp_pm_set_sd_tapdelay(u32 node_id, u32 type, u32 value)
 	u32 mask = (node_id == NODE_SD_0) ? GENMASK(15, 0) : GENMASK(31, 16);
 
 	if (value) {
-		return zynqmp_pm_invoke_fn(PM_IOCTL, node_id,
-					   IOCTL_SET_SD_TAPDELAY,
-					   type, value, NULL);
+		return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 4, node_id, IOCTL_SET_SD_TAPDELAY, type,
+					   value);
 	}
 
 	/*
@@ -798,7 +810,7 @@ int zynqmp_pm_set_sd_tapdelay(u32 node_id, u32 type, u32 value)
 	 * Use PM_MMIO_READ/PM_MMIO_WRITE to re-implement the missing counter
 	 * part of IOCTL_SET_SD_TAPDELAY which clears SDx_ITAPDLYENA bits.
 	 */
-	return zynqmp_pm_invoke_fn(PM_MMIO_WRITE, reg, mask, 0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_MMIO_WRITE, NULL, 2, reg, mask);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_set_sd_tapdelay);
 
@@ -814,8 +826,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_set_sd_tapdelay);
  */
 int zynqmp_pm_sd_dll_reset(u32 node_id, u32 type)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, node_id, IOCTL_SD_DLL_RESET,
-				   type, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 3, node_id, IOCTL_SD_DLL_RESET, type);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_sd_dll_reset);
 
@@ -831,8 +842,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_sd_dll_reset);
  */
 int zynqmp_pm_ospi_mux_select(u32 dev_id, u32 select)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, dev_id, IOCTL_OSPI_MUX_SELECT,
-				   select, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 3, dev_id, IOCTL_OSPI_MUX_SELECT, select);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_ospi_mux_select);
 
@@ -847,8 +857,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_ospi_mux_select);
  */
 int zynqmp_pm_write_ggs(u32 index, u32 value)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_WRITE_GGS,
-				   index, value, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 4, 0, IOCTL_WRITE_GGS, index, value);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_write_ggs);
 
@@ -863,8 +872,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_write_ggs);
  */
 int zynqmp_pm_read_ggs(u32 index, u32 *value)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_READ_GGS,
-				   index, 0, value);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, value, 3, 0, IOCTL_READ_GGS, index);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_read_ggs);
 
@@ -880,8 +888,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_read_ggs);
  */
 int zynqmp_pm_write_pggs(u32 index, u32 value)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_WRITE_PGGS, index, value,
-				   NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 4, 0, IOCTL_WRITE_PGGS, index, value);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_write_pggs);
 
@@ -897,15 +904,13 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_write_pggs);
  */
 int zynqmp_pm_read_pggs(u32 index, u32 *value)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_READ_PGGS, index, 0,
-				   value);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, value, 3, 0, IOCTL_READ_PGGS, index);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_read_pggs);
 
 int zynqmp_pm_set_tapdelay_bypass(u32 index, u32 value)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_SET_TAPDELAY_BYPASS,
-				   index, value, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 4, 0, IOCTL_SET_TAPDELAY_BYPASS, index, value);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_set_tapdelay_bypass);
 
@@ -920,8 +925,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_set_tapdelay_bypass);
  */
 int zynqmp_pm_set_boot_health_status(u32 value)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_SET_BOOT_HEALTH_STATUS,
-				   value, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 3, 0, IOCTL_SET_BOOT_HEALTH_STATUS, value);
 }
 
 /**
@@ -935,8 +939,7 @@ int zynqmp_pm_set_boot_health_status(u32 value)
 int zynqmp_pm_reset_assert(const enum zynqmp_pm_reset reset,
 			   const enum zynqmp_pm_reset_action assert_flag)
 {
-	return zynqmp_pm_invoke_fn(PM_RESET_ASSERT, reset, assert_flag,
-				   0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_RESET_ASSERT, NULL, 2, reset, assert_flag);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_reset_assert);
 
@@ -955,8 +958,7 @@ int zynqmp_pm_reset_get_status(const enum zynqmp_pm_reset reset, u32 *status)
 	if (!status)
 		return -EINVAL;
 
-	ret = zynqmp_pm_invoke_fn(PM_RESET_GET_STATUS, reset, 0,
-				  0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_RESET_GET_STATUS, ret_payload, 1, reset);
 	*status = ret_payload[1];
 
 	return ret;
@@ -981,9 +983,8 @@ int zynqmp_pm_fpga_load(const u64 address, const u32 size, const u32 flags)
 	u32 ret_payload[PAYLOAD_ARG_CNT];
 	int ret;
 
-	ret = zynqmp_pm_invoke_fn(PM_FPGA_LOAD, lower_32_bits(address),
-				  upper_32_bits(address), size, flags,
-				  ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_FPGA_LOAD, ret_payload, 4, lower_32_bits(address),
+				  upper_32_bits(address), size, flags);
 	if (ret_payload[0])
 		return -ret_payload[0];
 
@@ -1008,7 +1009,7 @@ int zynqmp_pm_fpga_get_status(u32 *value)
 	if (!value)
 		return -EINVAL;
 
-	ret = zynqmp_pm_invoke_fn(PM_FPGA_GET_STATUS, 0, 0, 0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_FPGA_GET_STATUS, ret_payload, 0);
 	*value = ret_payload[1];
 
 	return ret;
@@ -1036,11 +1037,9 @@ int zynqmp_pm_fpga_get_config_status(u32 *value)
 	lower_addr = lower_32_bits((u64)&buf);
 	upper_addr = upper_32_bits((u64)&buf);
 
-	ret = zynqmp_pm_invoke_fn(PM_FPGA_READ,
-				  XILINX_ZYNQMP_PM_FPGA_CONFIG_STAT_OFFSET,
-				  lower_addr, upper_addr,
-				  XILINX_ZYNQMP_PM_FPGA_READ_CONFIG_REG,
-				  ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_FPGA_READ, ret_payload, 4,
+				  XILINX_ZYNQMP_PM_FPGA_CONFIG_STAT_OFFSET, lower_addr, upper_addr,
+				  XILINX_ZYNQMP_PM_FPGA_READ_CONFIG_REG);
 
 	*value = ret_payload[1];
 
@@ -1058,7 +1057,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_fpga_get_config_status);
  */
 int zynqmp_pm_pinctrl_request(const u32 pin)
 {
-	return zynqmp_pm_invoke_fn(PM_PINCTRL_REQUEST, pin, 0, 0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_PINCTRL_REQUEST, NULL, 1, pin);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_pinctrl_request);
 
@@ -1072,7 +1071,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_pinctrl_request);
  */
 int zynqmp_pm_pinctrl_release(const u32 pin)
 {
-	return zynqmp_pm_invoke_fn(PM_PINCTRL_RELEASE, pin, 0, 0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_PINCTRL_RELEASE, NULL, 1, pin);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_pinctrl_release);
 
@@ -1093,8 +1092,7 @@ int zynqmp_pm_pinctrl_get_function(const u32 pin, u32 *id)
 	if (!id)
 		return -EINVAL;
 
-	ret = zynqmp_pm_invoke_fn(PM_PINCTRL_GET_FUNCTION, pin, 0,
-				  0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_PINCTRL_GET_FUNCTION, ret_payload, 1, pin);
 	*id = ret_payload[1];
 
 	return ret;
@@ -1112,8 +1110,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_pinctrl_get_function);
  */
 int zynqmp_pm_pinctrl_set_function(const u32 pin, const u32 id)
 {
-	return zynqmp_pm_invoke_fn(PM_PINCTRL_SET_FUNCTION, pin, id,
-				   0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_PINCTRL_SET_FUNCTION, NULL, 2, pin, id);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_pinctrl_set_function);
 
@@ -1136,8 +1133,7 @@ int zynqmp_pm_pinctrl_get_config(const u32 pin, const u32 param,
 	if (!value)
 		return -EINVAL;
 
-	ret = zynqmp_pm_invoke_fn(PM_PINCTRL_CONFIG_PARAM_GET, pin, param,
-				  0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_PINCTRL_CONFIG_PARAM_GET, ret_payload, 2, pin, param);
 	*value = ret_payload[1];
 
 	return ret;
@@ -1166,8 +1162,7 @@ int zynqmp_pm_pinctrl_set_config(const u32 pin, const u32 param,
 			return -EOPNOTSUPP;
 	}
 
-	return zynqmp_pm_invoke_fn(PM_PINCTRL_CONFIG_PARAM_SET, pin,
-				   param, value, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_PINCTRL_CONFIG_PARAM_SET, NULL, 3, pin, param, value);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_pinctrl_set_config);
 
@@ -1185,8 +1180,7 @@ unsigned int zynqmp_pm_bootmode_read(u32 *ps_mode)
 	unsigned int ret;
 	u32 ret_payload[PAYLOAD_ARG_CNT];
 
-	ret = zynqmp_pm_invoke_fn(PM_MMIO_READ, CRL_APB_BOOT_PIN_CTRL, 0,
-				  0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_MMIO_READ, ret_payload, 1, CRL_APB_BOOT_PIN_CTRL);
 
 	*ps_mode = ret_payload[1];
 
@@ -1205,8 +1199,8 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_bootmode_read);
  */
 int zynqmp_pm_bootmode_write(u32 ps_mode)
 {
-	return zynqmp_pm_invoke_fn(PM_MMIO_WRITE, CRL_APB_BOOT_PIN_CTRL,
-				   CRL_APB_BOOTPIN_CTRL_MASK, ps_mode, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_MMIO_WRITE, NULL, 3, CRL_APB_BOOT_PIN_CTRL,
+				   CRL_APB_BOOTPIN_CTRL_MASK, ps_mode);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_bootmode_write);
 
@@ -1221,7 +1215,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_bootmode_write);
  */
 int zynqmp_pm_init_finalize(void)
 {
-	return zynqmp_pm_invoke_fn(PM_PM_INIT_FINALIZE, 0, 0, 0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_PM_INIT_FINALIZE, NULL, 0);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_init_finalize);
 
@@ -1235,7 +1229,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_init_finalize);
  */
 int zynqmp_pm_set_suspend_mode(u32 mode)
 {
-	return zynqmp_pm_invoke_fn(PM_SET_SUSPEND_MODE, mode, 0, 0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_SET_SUSPEND_MODE, NULL, 1, mode);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_set_suspend_mode);
 
@@ -1254,8 +1248,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_set_suspend_mode);
 int zynqmp_pm_request_node(const u32 node, const u32 capabilities,
 			   const u32 qos, const enum zynqmp_pm_request_ack ack)
 {
-	return zynqmp_pm_invoke_fn(PM_REQUEST_NODE, node, capabilities,
-				   qos, ack, NULL);
+	return zynqmp_pm_invoke_fn(PM_REQUEST_NODE, NULL, 4, node, capabilities, qos, ack);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_request_node);
 
@@ -1271,7 +1264,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_request_node);
  */
 int zynqmp_pm_release_node(const u32 node)
 {
-	return zynqmp_pm_invoke_fn(PM_RELEASE_NODE, node, 0, 0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_RELEASE_NODE, NULL, 1, node);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_release_node);
 
@@ -1290,8 +1283,7 @@ int zynqmp_pm_get_rpu_mode(u32 node_id, enum rpu_oper_mode *rpu_mode)
 	u32 ret_payload[PAYLOAD_ARG_CNT];
 	int ret;
 
-	ret = zynqmp_pm_invoke_fn(PM_IOCTL, node_id,
-				  IOCTL_GET_RPU_OPER_MODE, 0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_IOCTL, ret_payload, 2, node_id, IOCTL_GET_RPU_OPER_MODE);
 
 	/* only set rpu_mode if no error */
 	if (ret == XST_PM_SUCCESS)
@@ -1313,9 +1305,8 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_get_rpu_mode);
  */
 int zynqmp_pm_set_rpu_mode(u32 node_id, enum rpu_oper_mode rpu_mode)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, node_id,
-				   IOCTL_SET_RPU_OPER_MODE, (u32)rpu_mode,
-				   0, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 3, node_id, IOCTL_SET_RPU_OPER_MODE,
+				   (u32)rpu_mode);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_set_rpu_mode);
 
@@ -1331,9 +1322,8 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_set_rpu_mode);
  */
 int zynqmp_pm_set_tcm_config(u32 node_id, enum rpu_tcm_comb tcm_mode)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, node_id,
-				   IOCTL_TCM_COMB_CONFIG, (u32)tcm_mode, 0,
-				   NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 3, node_id, IOCTL_TCM_COMB_CONFIG,
+				   (u32)tcm_mode);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_set_tcm_config);
 
@@ -1348,7 +1338,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_set_tcm_config);
 int zynqmp_pm_force_pwrdwn(const u32 node,
 			   const enum zynqmp_pm_request_ack ack)
 {
-	return zynqmp_pm_invoke_fn(PM_FORCE_POWERDOWN, node, ack, 0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_FORCE_POWERDOWN, NULL, 2, node, ack);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_force_pwrdwn);
 
@@ -1367,8 +1357,8 @@ int zynqmp_pm_request_wake(const u32 node,
 			   const enum zynqmp_pm_request_ack ack)
 {
 	/* set_addr flag is encoded into 1st bit of address */
-	return zynqmp_pm_invoke_fn(PM_REQUEST_WAKEUP, node, address | set_addr,
-				   address >> 32, ack, NULL);
+	return zynqmp_pm_invoke_fn(PM_REQUEST_WAKEUP, NULL, 4, node, address | set_addr,
+				   address >> 32, ack);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_request_wake);
 
@@ -1388,8 +1378,7 @@ int zynqmp_pm_set_requirement(const u32 node, const u32 capabilities,
 			      const u32 qos,
 			      const enum zynqmp_pm_request_ack ack)
 {
-	return zynqmp_pm_invoke_fn(PM_SET_REQUIREMENT, node, capabilities,
-				   qos, ack, NULL);
+	return zynqmp_pm_invoke_fn(PM_SET_REQUIREMENT, NULL, 4, node, capabilities, qos, ack);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_set_requirement);
 
@@ -1404,9 +1393,8 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_set_requirement);
  */
 int zynqmp_pm_load_pdi(const u32 src, const u64 address)
 {
-	return zynqmp_pm_invoke_fn(PM_LOAD_PDI, src,
-				   lower_32_bits(address),
-				   upper_32_bits(address), 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_LOAD_PDI, NULL, 3, src, lower_32_bits(address),
+				   upper_32_bits(address));
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_load_pdi);
 
@@ -1426,9 +1414,8 @@ int zynqmp_pm_aes_engine(const u64 address, u32 *out)
 	if (!out)
 		return -EINVAL;
 
-	ret = zynqmp_pm_invoke_fn(PM_SECURE_AES, upper_32_bits(address),
-				  lower_32_bits(address),
-				  0, 0, ret_payload);
+	ret = zynqmp_pm_invoke_fn(PM_SECURE_AES, ret_payload, 2, upper_32_bits(address),
+				  lower_32_bits(address));
 	*out = ret_payload[1];
 
 	return ret;
@@ -1456,8 +1443,7 @@ int zynqmp_pm_sha_hash(const u64 address, const u32 size, const u32 flags)
 	u32 lower_addr = lower_32_bits(address);
 	u32 upper_addr = upper_32_bits(address);
 
-	return zynqmp_pm_invoke_fn(PM_SECURE_SHA, upper_addr, lower_addr,
-				   size, flags, NULL);
+	return zynqmp_pm_invoke_fn(PM_SECURE_SHA, NULL, 4, upper_addr, lower_addr, size, flags);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_sha_hash);
 
@@ -1479,8 +1465,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_sha_hash);
 int zynqmp_pm_register_notifier(const u32 node, const u32 event,
 				const u32 wake, const u32 enable)
 {
-	return zynqmp_pm_invoke_fn(PM_REGISTER_NOTIFIER, node, event,
-				   wake, enable, NULL);
+	return zynqmp_pm_invoke_fn(PM_REGISTER_NOTIFIER, NULL, 4, node, event, wake, enable);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_register_notifier);
 
@@ -1493,8 +1478,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_register_notifier);
  */
 int zynqmp_pm_system_shutdown(const u32 type, const u32 subtype)
 {
-	return zynqmp_pm_invoke_fn(PM_SYSTEM_SHUTDOWN, type, subtype,
-				   0, 0, NULL);
+	return zynqmp_pm_invoke_fn(PM_SYSTEM_SHUTDOWN, NULL, 2, type, subtype);
 }
 
 /**
@@ -1506,8 +1490,7 @@ int zynqmp_pm_system_shutdown(const u32 type, const u32 subtype)
  */
 int zynqmp_pm_set_feature_config(enum pm_feature_config_id id, u32 value)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_SET_FEATURE_CONFIG,
-				   id, value, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 4, 0, IOCTL_SET_FEATURE_CONFIG, id, value);
 }
 
 /**
@@ -1520,8 +1503,7 @@ int zynqmp_pm_set_feature_config(enum pm_feature_config_id id, u32 value)
 int zynqmp_pm_get_feature_config(enum pm_feature_config_id id,
 				 u32 *payload)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_GET_FEATURE_CONFIG,
-				   id, 0, payload);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, payload, 3, 0, IOCTL_GET_FEATURE_CONFIG, id);
 }
 
 /**
@@ -1534,8 +1516,7 @@ int zynqmp_pm_get_feature_config(enum pm_feature_config_id id,
  */
 int zynqmp_pm_set_sd_config(u32 node, enum pm_sd_config_type config, u32 value)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, node, IOCTL_SET_SD_CONFIG,
-				   config, value, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 4, node, IOCTL_SET_SD_CONFIG, config, value);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_set_sd_config);
 
@@ -1550,8 +1531,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_set_sd_config);
 int zynqmp_pm_set_gem_config(u32 node, enum pm_gem_config_type config,
 			     u32 value)
 {
-	return zynqmp_pm_invoke_fn(PM_IOCTL, node, IOCTL_SET_GEM_CONFIG,
-				   config, value, NULL);
+	return zynqmp_pm_invoke_fn(PM_IOCTL, NULL, 4, node, IOCTL_SET_GEM_CONFIG, config, value);
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_set_gem_config);
 
diff --git a/drivers/soc/xilinx/xlnx_event_manager.c b/drivers/soc/xilinx/xlnx_event_manager.c
index 86a048a10a13..adb875f89829 100644
--- a/drivers/soc/xilinx/xlnx_event_manager.c
+++ b/drivers/soc/xilinx/xlnx_event_manager.c
@@ -483,7 +483,7 @@ static void xlnx_call_notify_cb_handler(const u32 *payload)
 
 static void xlnx_get_event_callback_data(u32 *buf)
 {
-	zynqmp_pm_invoke_fn(GET_CALLBACK_DATA, 0, 0, 0, 0, buf);
+	zynqmp_pm_invoke_fn(GET_CALLBACK_DATA, buf, 0);
 }
 
 static irqreturn_t xlnx_event_handler(int irq, void *dev_id)
diff --git a/drivers/soc/xilinx/zynqmp_power.c b/drivers/soc/xilinx/zynqmp_power.c
index c2c819701eec..0de0acf80ef8 100644
--- a/drivers/soc/xilinx/zynqmp_power.c
+++ b/drivers/soc/xilinx/zynqmp_power.c
@@ -51,7 +51,7 @@ static enum pm_suspend_mode suspend_mode = PM_SUSPEND_MODE_STD;
 
 static void zynqmp_pm_get_callback_data(u32 *buf)
 {
-	zynqmp_pm_invoke_fn(GET_CALLBACK_DATA, 0, 0, 0, 0, buf);
+	zynqmp_pm_invoke_fn(GET_CALLBACK_DATA, buf, 0);
 }
 
 static void suspend_event_callback(const u32 *payload, void *data)
diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h
index d1ea3898564c..41190bbed8ed 100644
--- a/include/linux/firmware/xlnx-zynqmp.h
+++ b/include/linux/firmware/xlnx-zynqmp.h
@@ -509,8 +509,7 @@ struct zynqmp_pm_query_data {
 	u32 arg3;
 };
 
-int zynqmp_pm_invoke_fn(u32 pm_api_id, u32 arg0, u32 arg1,
-			u32 arg2, u32 arg3, u32 *ret_payload);
+int zynqmp_pm_invoke_fn(u32 pm_api_id, u32 *ret_payload, u32 num_args, ...);
 
 #if IS_REACHABLE(CONFIG_ZYNQMP_FIRMWARE)
 int zynqmp_pm_get_api_version(u32 *version);
-- 
cgit v1.2.3


From f689a0ca45fcdf4139727a3a02a49efbb1902306 Mon Sep 17 00:00:00 2001
From: Jay Buddhabhatti <jay.buddhabhatti@amd.com>
Date: Wed, 29 Nov 2023 03:27:10 -0800
Subject: firmware: xilinx: Expand feature check to support all PLM modules

To support feature check for all modules, append the module id of the API
that is being checked to the feature check API so it could be routed to
the target module for processing.

There is no need to check compatible string because the board information
is taken via firmware interface.

Co-developed-by: Saeed Nowshadi <saeed.nowshadi@amd.com>
Signed-off-by: Saeed Nowshadi <saeed.nowshadi@amd.com>
Signed-off-by: Jay Buddhabhatti <jay.buddhabhatti@amd.com>
Link: https://lore.kernel.org/r/20231129112713.22718-3-jay.buddhabhatti@amd.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/xilinx/zynqmp.c     | 41 +++++++++++++++++++++---------------
 include/linux/firmware/xlnx-zynqmp.h | 11 ++++++++++
 2 files changed, 35 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c
index 2a7fd3fbac8c..ec77aefee17e 100644
--- a/drivers/firmware/xilinx/zynqmp.c
+++ b/drivers/firmware/xilinx/zynqmp.c
@@ -199,9 +199,29 @@ static int __do_feature_check_call(const u32 api_id, u32 *ret_payload)
 {
 	int ret;
 	u64 smc_arg[2];
+	u32 module_id;
+	u32 feature_check_api_id;
 
-	smc_arg[0] = PM_SIP_SVC | PM_FEATURE_CHECK;
-	smc_arg[1] = api_id;
+	module_id = FIELD_GET(MODULE_ID_MASK, api_id);
+
+	/*
+	 * Feature check of APIs belonging to PM, XSEM, and TF-A are handled by calling
+	 * PM_FEATURE_CHECK API. For other modules, call PM_API_FEATURES API.
+	 */
+	if (module_id == PM_MODULE_ID || module_id == XSEM_MODULE_ID || module_id == TF_A_MODULE_ID)
+		feature_check_api_id = PM_FEATURE_CHECK;
+	else
+		feature_check_api_id = PM_API_FEATURES;
+
+	/*
+	 * Feature check of TF-A APIs is done in the TF-A layer and it expects for
+	 * MODULE_ID_MASK bits of SMC's arg[0] to be the same as PM_MODULE_ID.
+	 */
+	if (module_id == TF_A_MODULE_ID)
+		module_id = PM_MODULE_ID;
+
+	smc_arg[0] = PM_SIP_SVC | FIELD_PREP(MODULE_ID_MASK, module_id) | feature_check_api_id;
+	smc_arg[1] = (api_id & API_ID_MASK);
 
 	ret = do_fw_call(ret_payload, 2, smc_arg[0], smc_arg[1]);
 	if (ret)
@@ -1904,22 +1924,9 @@ static int zynqmp_firmware_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	np = of_find_compatible_node(NULL, NULL, "xlnx,zynqmp");
-	if (!np) {
-		np = of_find_compatible_node(NULL, NULL, "xlnx,versal");
-		if (!np)
-			return 0;
-
+	ret = do_feature_check_call(PM_FEATURE_CHECK);
+	if (ret >= 0 && ((ret & FIRMWARE_VERSION_MASK) >= PM_API_VERSION_1))
 		feature_check_enabled = true;
-	}
-
-	if (!feature_check_enabled) {
-		ret = do_feature_check_call(PM_FEATURE_CHECK);
-		if (ret >= 0)
-			feature_check_enabled = true;
-	}
-
-	of_node_put(np);
 
 	devinfo = devm_kzalloc(dev, sizeof(*devinfo), GFP_KERNEL);
 	if (!devinfo)
diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h
index 41190bbed8ed..e9a7fece5efe 100644
--- a/include/linux/firmware/xlnx-zynqmp.h
+++ b/include/linux/firmware/xlnx-zynqmp.h
@@ -32,6 +32,7 @@
 #define PM_SIP_SVC			0xC2000000
 
 /* PM API versions */
+#define PM_API_VERSION_1	1
 #define PM_API_VERSION_2	2
 
 #define PM_PINCTRL_PARAM_SET_VERSION	2
@@ -47,6 +48,9 @@
 #define FAMILY_CODE_MASK	GENMASK(27, 21)
 #define SUB_FAMILY_CODE_MASK	GENMASK(20, 19)
 
+#define API_ID_MASK		GENMASK(7, 0)
+#define MODULE_ID_MASK		GENMASK(11, 8)
+
 /* ATF only commands */
 #define TF_A_PM_REGISTER_SGI		0xa04
 #define PM_GET_TRUSTZONE_VERSION	0xa03
@@ -112,6 +116,12 @@
 #define XPM_EVENT_ERROR_MASK_NOC_NCR		BIT(13)
 #define XPM_EVENT_ERROR_MASK_NOC_CR		BIT(12)
 
+enum pm_module_id {
+	PM_MODULE_ID = 0x0,
+	XSEM_MODULE_ID = 0x3,
+	TF_A_MODULE_ID = 0xa,
+};
+
 enum pm_api_cb_id {
 	PM_INIT_SUSPEND_CB = 30,
 	PM_ACKNOWLEDGE_CB = 31,
@@ -119,6 +129,7 @@ enum pm_api_cb_id {
 };
 
 enum pm_api_id {
+	PM_API_FEATURES = 0,
 	PM_GET_API_VERSION = 1,
 	PM_REGISTER_NOTIFIER = 5,
 	PM_FORCE_POWERDOWN = 8,
-- 
cgit v1.2.3


From 8c016c807a90535432543204dbbb032e4a709009 Mon Sep 17 00:00:00 2001
From: Jay Buddhabhatti <jay.buddhabhatti@amd.com>
Date: Wed, 29 Nov 2023 03:27:12 -0800
Subject: drivers: soc: xilinx: Fix error message on SGI registration failure

Failure to register SGI for firmware event notification is non-fatal error
when feature is not supported by other modules such as Xen and TF-A. Add
_info level log message for such special case.

Also add XST_PM_INVALID_VERSION error code and map it to -EOPNOSUPP Linux
kernel error code. If feature is not supported or EEMI API version is
mismatch, firmware can return XST_PM_INVALID_VERSION = 4 or
XST_PM_NO_FEATURE = 19 error code.

Co-developed-by: Tanmay Shah <tanmay.shah@amd.com>
Signed-off-by: Tanmay Shah <tanmay.shah@amd.com>
Signed-off-by: Jay Buddhabhatti <jay.buddhabhatti@amd.com>
Link: https://lore.kernel.org/r/20231129112713.22718-5-jay.buddhabhatti@amd.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/xilinx/zynqmp.c        | 4 +++-
 drivers/soc/xilinx/xlnx_event_manager.c | 6 +++++-
 include/linux/firmware/xlnx-zynqmp.h    | 1 +
 3 files changed, 9 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c
index 533679a07b57..077b49e440b5 100644
--- a/drivers/firmware/xilinx/zynqmp.c
+++ b/drivers/firmware/xilinx/zynqmp.c
@@ -92,6 +92,8 @@ static int zynqmp_pm_ret_code(u32 ret_status)
 		return 0;
 	case XST_PM_NO_FEATURE:
 		return -ENOTSUPP;
+	case XST_PM_INVALID_VERSION:
+		return -EOPNOTSUPP;
 	case XST_PM_NO_ACCESS:
 		return -EACCES;
 	case XST_PM_ABORT_SUSPEND:
@@ -396,7 +398,7 @@ int zynqmp_pm_register_sgi(u32 sgi_num, u32 reset)
 	int ret;
 
 	ret = zynqmp_pm_invoke_fn(TF_A_PM_REGISTER_SGI, NULL, 2, sgi_num, reset);
-	if (!ret)
+	if (ret != -EOPNOTSUPP && !ret)
 		return ret;
 
 	/* try old implementation as fallback strategy if above fails */
diff --git a/drivers/soc/xilinx/xlnx_event_manager.c b/drivers/soc/xilinx/xlnx_event_manager.c
index adb875f89829..27a8d89a0a09 100644
--- a/drivers/soc/xilinx/xlnx_event_manager.c
+++ b/drivers/soc/xilinx/xlnx_event_manager.c
@@ -653,7 +653,11 @@ static int xlnx_event_manager_probe(struct platform_device *pdev)
 
 	ret = zynqmp_pm_register_sgi(sgi_num, 0);
 	if (ret) {
-		dev_err(&pdev->dev, "SGI %d Registration over TF-A failed with %d\n", sgi_num, ret);
+		if (ret == -EOPNOTSUPP)
+			dev_err(&pdev->dev, "SGI registration not supported by TF-A or Xen\n");
+		else
+			dev_err(&pdev->dev, "SGI %d registration failed, err %d\n", sgi_num, ret);
+
 		xlnx_event_cleanup_sgi(pdev);
 		return ret;
 	}
diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h
index e9a7fece5efe..ec1800c86006 100644
--- a/include/linux/firmware/xlnx-zynqmp.h
+++ b/include/linux/firmware/xlnx-zynqmp.h
@@ -172,6 +172,7 @@ enum pm_api_id {
 /* PMU-FW return status codes */
 enum pm_ret_status {
 	XST_PM_SUCCESS = 0,
+	XST_PM_INVALID_VERSION = 4,
 	XST_PM_NO_FEATURE = 19,
 	XST_PM_INTERNAL = 2000,
 	XST_PM_CONFLICT = 2001,
-- 
cgit v1.2.3


From 5dac2a98f6542ae1ce78b702374ea4be3f5ee07d Mon Sep 17 00:00:00 2001
From: Jay Buddhabhatti <jay.buddhabhatti@amd.com>
Date: Wed, 29 Nov 2023 03:27:13 -0800
Subject: firmware: zynqmp: Add support to handle IPI CRC failure

Added new PM error code XST_PM_INVALID_CRC to handle CRC validation failure
during IPI communication.

Co-developed-by: Naman Trivedi Manojbhai <naman.trivedimanojbhai@amd.com>
Signed-off-by: Naman Trivedi Manojbhai <naman.trivedimanojbhai@amd.com>
Signed-off-by: Jay Buddhabhatti <jay.buddhabhatti@amd.com>
Link: https://lore.kernel.org/r/20231129112713.22718-6-jay.buddhabhatti@amd.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/xilinx/zynqmp.c     | 1 +
 include/linux/firmware/xlnx-zynqmp.h | 1 +
 2 files changed, 2 insertions(+)

(limited to 'include')

diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c
index 077b49e440b5..caa0952bfc42 100644
--- a/drivers/firmware/xilinx/zynqmp.c
+++ b/drivers/firmware/xilinx/zynqmp.c
@@ -103,6 +103,7 @@ static int zynqmp_pm_ret_code(u32 ret_status)
 	case XST_PM_INTERNAL:
 	case XST_PM_CONFLICT:
 	case XST_PM_INVALID_NODE:
+	case XST_PM_INVALID_CRC:
 	default:
 		return -EINVAL;
 	}
diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h
index ec1800c86006..6b48294f3c92 100644
--- a/include/linux/firmware/xlnx-zynqmp.h
+++ b/include/linux/firmware/xlnx-zynqmp.h
@@ -174,6 +174,7 @@ enum pm_ret_status {
 	XST_PM_SUCCESS = 0,
 	XST_PM_INVALID_VERSION = 4,
 	XST_PM_NO_FEATURE = 19,
+	XST_PM_INVALID_CRC = 301,
 	XST_PM_INTERNAL = 2000,
 	XST_PM_CONFLICT = 2001,
 	XST_PM_NO_ACCESS = 2002,
-- 
cgit v1.2.3


From 5a08d0065a915ccf325563d7ca57fa8b4897881c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 5 Dec 2023 17:32:50 +0000
Subject: ipv6: add debug checks in fib6_info_release()

Some elusive syzbot reports are hinting to fib6_info_release(),
with a potential dangling f6i->gc_link anchor.

Add debug checks so that syzbot can catch the issue earlier eventually.

BUG: KASAN: slab-use-after-free in __hlist_del include/linux/list.h:990 [inline]
BUG: KASAN: slab-use-after-free in hlist_del_init include/linux/list.h:1016 [inline]
BUG: KASAN: slab-use-after-free in fib6_clean_expires_locked include/net/ip6_fib.h:533 [inline]
BUG: KASAN: slab-use-after-free in fib6_purge_rt+0x986/0x9c0 net/ipv6/ip6_fib.c:1064
Write of size 8 at addr ffff88802805a840 by task syz-executor.1/10057

CPU: 1 PID: 10057 Comm: syz-executor.1 Not tainted 6.7.0-rc2-syzkaller-00029-g9b6de136b5f0 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 11/10/2023
Call Trace:
<TASK>
__dump_stack lib/dump_stack.c:88 [inline]
dump_stack_lvl+0xd9/0x1b0 lib/dump_stack.c:106
print_address_description mm/kasan/report.c:364 [inline]
print_report+0xc4/0x620 mm/kasan/report.c:475
kasan_report+0xda/0x110 mm/kasan/report.c:588
__hlist_del include/linux/list.h:990 [inline]
hlist_del_init include/linux/list.h:1016 [inline]
fib6_clean_expires_locked include/net/ip6_fib.h:533 [inline]
fib6_purge_rt+0x986/0x9c0 net/ipv6/ip6_fib.c:1064
fib6_del_route net/ipv6/ip6_fib.c:1993 [inline]
fib6_del+0xa7a/0x1750 net/ipv6/ip6_fib.c:2038
__ip6_del_rt net/ipv6/route.c:3866 [inline]
ip6_del_rt+0xf7/0x200 net/ipv6/route.c:3881
ndisc_router_discovery+0x295b/0x3560 net/ipv6/ndisc.c:1372
ndisc_rcv+0x3de/0x5f0 net/ipv6/ndisc.c:1856
icmpv6_rcv+0x1470/0x19c0 net/ipv6/icmp.c:979
ip6_protocol_deliver_rcu+0x170/0x13e0 net/ipv6/ip6_input.c:438
ip6_input_finish+0x14f/0x2f0 net/ipv6/ip6_input.c:483
NF_HOOK include/linux/netfilter.h:314 [inline]
NF_HOOK include/linux/netfilter.h:308 [inline]
ip6_input+0xa1/0xc0 net/ipv6/ip6_input.c:492
ip6_mc_input+0x48b/0xf40 net/ipv6/ip6_input.c:586
dst_input include/net/dst.h:461 [inline]
ip6_rcv_finish net/ipv6/ip6_input.c:79 [inline]
NF_HOOK include/linux/netfilter.h:314 [inline]
NF_HOOK include/linux/netfilter.h:308 [inline]
ipv6_rcv+0x24e/0x380 net/ipv6/ip6_input.c:310
__netif_receive_skb_one_core+0x115/0x180 net/core/dev.c:5529
__netif_receive_skb+0x1f/0x1b0 net/core/dev.c:5643
netif_receive_skb_internal net/core/dev.c:5729 [inline]
netif_receive_skb+0x133/0x700 net/core/dev.c:5788
tun_rx_batched+0x429/0x780 drivers/net/tun.c:1579
tun_get_user+0x29e3/0x3bc0 drivers/net/tun.c:2002
tun_chr_write_iter+0xe8/0x210 drivers/net/tun.c:2048
call_write_iter include/linux/fs.h:2020 [inline]
new_sync_write fs/read_write.c:491 [inline]
vfs_write+0x64f/0xdf0 fs/read_write.c:584
ksys_write+0x12f/0x250 fs/read_write.c:637
do_syscall_x64 arch/x86/entry/common.c:51 [inline]
do_syscall_64+0x40/0x110 arch/x86/entry/common.c:82
entry_SYSCALL_64_after_hwframe+0x63/0x6b
RIP: 0033:0x7f38e387b82f
Code: 89 54 24 18 48 89 74 24 10 89 7c 24 08 e8 b9 80 02 00 48 8b 54 24 18 48 8b 74 24 10 41 89 c0 8b 7c 24 08 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 31 44 89 c7 48 89 44 24 08 e8 0c 81 02 00 48
RSP: 002b:00007f38e45c9090 EFLAGS: 00000293 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 00007f38e399bf80 RCX: 00007f38e387b82f
RDX: 00000000000003b6 RSI: 0000000020000680 RDI: 00000000000000c8
RBP: 00007f38e38c847a R08: 0000000000000000 R09: 0000000000000000
R10: 00000000000003b6 R11: 0000000000000293 R12: 0000000000000000
R13: 000000000000000b R14: 00007f38e399bf80 R15: 00007f38e3abfa48
</TASK>

Allocated by task 10044:
kasan_save_stack+0x33/0x50 mm/kasan/common.c:45
kasan_set_track+0x25/0x30 mm/kasan/common.c:52
____kasan_kmalloc mm/kasan/common.c:374 [inline]
__kasan_kmalloc+0xa2/0xb0 mm/kasan/common.c:383
kasan_kmalloc include/linux/kasan.h:198 [inline]
__do_kmalloc_node mm/slab_common.c:1007 [inline]
__kmalloc+0x59/0x90 mm/slab_common.c:1020
kmalloc include/linux/slab.h:604 [inline]
kzalloc include/linux/slab.h:721 [inline]
fib6_info_alloc+0x40/0x160 net/ipv6/ip6_fib.c:155
ip6_route_info_create+0x337/0x1e70 net/ipv6/route.c:3749
ip6_route_add+0x26/0x150 net/ipv6/route.c:3843
rt6_add_route_info+0x2e7/0x4b0 net/ipv6/route.c:4316
rt6_route_rcv+0x76c/0xbf0 net/ipv6/route.c:985
ndisc_router_discovery+0x138b/0x3560 net/ipv6/ndisc.c:1529
ndisc_rcv+0x3de/0x5f0 net/ipv6/ndisc.c:1856
icmpv6_rcv+0x1470/0x19c0 net/ipv6/icmp.c:979
ip6_protocol_deliver_rcu+0x170/0x13e0 net/ipv6/ip6_input.c:438
ip6_input_finish+0x14f/0x2f0 net/ipv6/ip6_input.c:483
NF_HOOK include/linux/netfilter.h:314 [inline]
NF_HOOK include/linux/netfilter.h:308 [inline]
ip6_input+0xa1/0xc0 net/ipv6/ip6_input.c:492
ip6_mc_input+0x48b/0xf40 net/ipv6/ip6_input.c:586
dst_input include/net/dst.h:461 [inline]
ip6_rcv_finish net/ipv6/ip6_input.c:79 [inline]
NF_HOOK include/linux/netfilter.h:314 [inline]
NF_HOOK include/linux/netfilter.h:308 [inline]
ipv6_rcv+0x24e/0x380 net/ipv6/ip6_input.c:310
__netif_receive_skb_one_core+0x115/0x180 net/core/dev.c:5529
__netif_receive_skb+0x1f/0x1b0 net/core/dev.c:5643
netif_receive_skb_internal net/core/dev.c:5729 [inline]
netif_receive_skb+0x133/0x700 net/core/dev.c:5788
tun_rx_batched+0x429/0x780 drivers/net/tun.c:1579
tun_get_user+0x29e3/0x3bc0 drivers/net/tun.c:2002
tun_chr_write_iter+0xe8/0x210 drivers/net/tun.c:2048
call_write_iter include/linux/fs.h:2020 [inline]
new_sync_write fs/read_write.c:491 [inline]
vfs_write+0x64f/0xdf0 fs/read_write.c:584
ksys_write+0x12f/0x250 fs/read_write.c:637
do_syscall_x64 arch/x86/entry/common.c:51 [inline]
do_syscall_64+0x40/0x110 arch/x86/entry/common.c:82
entry_SYSCALL_64_after_hwframe+0x63/0x6b

Freed by task 5123:
kasan_save_stack+0x33/0x50 mm/kasan/common.c:45
kasan_set_track+0x25/0x30 mm/kasan/common.c:52
kasan_save_free_info+0x2b/0x40 mm/kasan/generic.c:522
____kasan_slab_free mm/kasan/common.c:236 [inline]
____kasan_slab_free+0x15b/0x1b0 mm/kasan/common.c:200
kasan_slab_free include/linux/kasan.h:164 [inline]
slab_free_hook mm/slub.c:1800 [inline]
slab_free_freelist_hook+0x114/0x1e0 mm/slub.c:1826
slab_free mm/slub.c:3809 [inline]
__kmem_cache_free+0xc0/0x180 mm/slub.c:3822
rcu_do_batch kernel/rcu/tree.c:2158 [inline]
rcu_core+0x819/0x1680 kernel/rcu/tree.c:2431
__do_softirq+0x21a/0x8de kernel/softirq.c:553

Last potentially related work creation:
kasan_save_stack+0x33/0x50 mm/kasan/common.c:45
__kasan_record_aux_stack+0xbc/0xd0 mm/kasan/generic.c:492
__call_rcu_common.constprop.0+0x9a/0x7a0 kernel/rcu/tree.c:2681
fib6_info_release include/net/ip6_fib.h:332 [inline]
fib6_info_release include/net/ip6_fib.h:329 [inline]
rt6_route_rcv+0xa4e/0xbf0 net/ipv6/route.c:997
ndisc_router_discovery+0x138b/0x3560 net/ipv6/ndisc.c:1529
ndisc_rcv+0x3de/0x5f0 net/ipv6/ndisc.c:1856
icmpv6_rcv+0x1470/0x19c0 net/ipv6/icmp.c:979
ip6_protocol_deliver_rcu+0x170/0x13e0 net/ipv6/ip6_input.c:438
ip6_input_finish+0x14f/0x2f0 net/ipv6/ip6_input.c:483
NF_HOOK include/linux/netfilter.h:314 [inline]
NF_HOOK include/linux/netfilter.h:308 [inline]
ip6_input+0xa1/0xc0 net/ipv6/ip6_input.c:492
ip6_mc_input+0x48b/0xf40 net/ipv6/ip6_input.c:586
dst_input include/net/dst.h:461 [inline]
ip6_rcv_finish net/ipv6/ip6_input.c:79 [inline]
NF_HOOK include/linux/netfilter.h:314 [inline]
NF_HOOK include/linux/netfilter.h:308 [inline]
ipv6_rcv+0x24e/0x380 net/ipv6/ip6_input.c:310
__netif_receive_skb_one_core+0x115/0x180 net/core/dev.c:5529
__netif_receive_skb+0x1f/0x1b0 net/core/dev.c:5643
netif_receive_skb_internal net/core/dev.c:5729 [inline]
netif_receive_skb+0x133/0x700 net/core/dev.c:5788
tun_rx_batched+0x429/0x780 drivers/net/tun.c:1579
tun_get_user+0x29e3/0x3bc0 drivers/net/tun.c:2002
tun_chr_write_iter+0xe8/0x210 drivers/net/tun.c:2048
call_write_iter include/linux/fs.h:2020 [inline]
new_sync_write fs/read_write.c:491 [inline]
vfs_write+0x64f/0xdf0 fs/read_write.c:584
ksys_write+0x12f/0x250 fs/read_write.c:637
do_syscall_x64 arch/x86/entry/common.c:51 [inline]
do_syscall_64+0x40/0x110 arch/x86/entry/common.c:82
entry_SYSCALL_64_after_hwframe+0x63/0x6b

Second to last potentially related work creation:
kasan_save_stack+0x33/0x50 mm/kasan/common.c:45
__kasan_record_aux_stack+0xbc/0xd0 mm/kasan/generic.c:492
insert_work+0x38/0x230 kernel/workqueue.c:1647
__queue_work+0xcdc/0x11f0 kernel/workqueue.c:1803
call_timer_fn+0x193/0x590 kernel/time/timer.c:1700
expire_timers kernel/time/timer.c:1746 [inline]
__run_timers+0x585/0xb20 kernel/time/timer.c:2022
run_timer_softirq+0x58/0xd0 kernel/time/timer.c:2035
__do_softirq+0x21a/0x8de kernel/softirq.c:553

The buggy address belongs to the object at ffff88802805a800
which belongs to the cache kmalloc-512 of size 512
The buggy address is located 64 bytes inside of
freed 512-byte region [ffff88802805a800, ffff88802805aa00)

The buggy address belongs to the physical page:
page:ffffea0000a01600 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x28058
head:ffffea0000a01600 order:2 entire_mapcount:0 nr_pages_mapped:0 pincount:0
flags: 0xfff00000000840(slab|head|node=0|zone=1|lastcpupid=0x7ff)
page_type: 0xffffffff()
raw: 00fff00000000840 ffff888013041c80 ffffea0001e02600 dead000000000002
raw: 0000000000000000 0000000000100010 00000001ffffffff 0000000000000000
page dumped because: kasan: bad access detected
page_owner tracks the page as allocated
page last allocated via order 2, migratetype Unmovable, gfp_mask 0x1d20c0(__GFP_IO|__GFP_FS|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP|__GFP_NOMEMALLOC|__GFP_HARDWALL), pid 18706, tgid 18699 (syz-executor.2), ts 999991973280, free_ts 996884464281
set_page_owner include/linux/page_owner.h:31 [inline]
post_alloc_hook+0x2d0/0x350 mm/page_alloc.c:1537
prep_new_page mm/page_alloc.c:1544 [inline]
get_page_from_freelist+0xa25/0x36d0 mm/page_alloc.c:3312
__alloc_pages+0x22e/0x2420 mm/page_alloc.c:4568
alloc_pages_mpol+0x258/0x5f0 mm/mempolicy.c:2133
alloc_slab_page mm/slub.c:1870 [inline]
allocate_slab mm/slub.c:2017 [inline]
new_slab+0x283/0x3c0 mm/slub.c:2070
___slab_alloc+0x979/0x1500 mm/slub.c:3223
__slab_alloc.constprop.0+0x56/0xa0 mm/slub.c:3322
__slab_alloc_node mm/slub.c:3375 [inline]
slab_alloc_node mm/slub.c:3468 [inline]
__kmem_cache_alloc_node+0x131/0x310 mm/slub.c:3517
__do_kmalloc_node mm/slab_common.c:1006 [inline]
__kmalloc+0x49/0x90 mm/slab_common.c:1020
kmalloc include/linux/slab.h:604 [inline]
kzalloc include/linux/slab.h:721 [inline]
copy_splice_read+0x1ac/0x8f0 fs/splice.c:338
vfs_splice_read fs/splice.c:992 [inline]
vfs_splice_read+0x2ea/0x3b0 fs/splice.c:962
splice_direct_to_actor+0x2a5/0xa30 fs/splice.c:1069
do_splice_direct+0x1af/0x280 fs/splice.c:1194
do_sendfile+0xb3e/0x1310 fs/read_write.c:1254
__do_sys_sendfile64 fs/read_write.c:1322 [inline]
__se_sys_sendfile64 fs/read_write.c:1308 [inline]
__x64_sys_sendfile64+0x1d6/0x220 fs/read_write.c:1308
do_syscall_x64 arch/x86/entry/common.c:51 [inline]
do_syscall_64+0x40/0x110 arch/x86/entry/common.c:82
page last free stack trace:
reset_page_owner include/linux/page_owner.h:24 [inline]
free_pages_prepare mm/page_alloc.c:1137 [inline]
free_unref_page_prepare+0x4fa/0xaa0 mm/page_alloc.c:2347
free_unref_page_list+0xe6/0xb40 mm/page_alloc.c:2533
release_pages+0x32a/0x14f0 mm/swap.c:1042
tlb_batch_pages_flush+0x9a/0x190 mm/mmu_gather.c:98
tlb_flush_mmu_free mm/mmu_gather.c:293 [inline]
tlb_flush_mmu mm/mmu_gather.c:300 [inline]
tlb_finish_mmu+0x14b/0x6f0 mm/mmu_gather.c:392
exit_mmap+0x38b/0xa70 mm/mmap.c:3321
__mmput+0x12a/0x4d0 kernel/fork.c:1349
mmput+0x62/0x70 kernel/fork.c:1371
exit_mm kernel/exit.c:567 [inline]
do_exit+0x9ad/0x2ae0 kernel/exit.c:858
do_group_exit+0xd4/0x2a0 kernel/exit.c:1021
get_signal+0x23be/0x2790 kernel/signal.c:2904
arch_do_signal_or_restart+0x90/0x7f0 arch/x86/kernel/signal.c:309
exit_to_user_mode_loop kernel/entry/common.c:168 [inline]
exit_to_user_mode_prepare+0x121/0x240 kernel/entry/common.c:204
irqentry_exit_to_user_mode+0xa/0x40 kernel/entry/common.c:309
asm_sysvec_apic_timer_interrupt+0x1a/0x20 arch/x86/include/asm/idtentry.h:645

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20231205173250.2982846-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/ip6_fib.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 1ba9f4ddf2f6..e1e7a894863a 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -328,8 +328,11 @@ static inline bool fib6_info_hold_safe(struct fib6_info *f6i)
 
 static inline void fib6_info_release(struct fib6_info *f6i)
 {
-	if (f6i && refcount_dec_and_test(&f6i->fib6_ref))
+	if (f6i && refcount_dec_and_test(&f6i->fib6_ref)) {
+		DEBUG_NET_WARN_ON_ONCE(fib6_has_expires(f6i));
+		DEBUG_NET_WARN_ON_ONCE(!hlist_unhashed(&f6i->gc_link));
 		call_rcu(&f6i->rcu, fib6_info_destroy_rcu);
+	}
 }
 
 enum fib6_walk_state {
-- 
cgit v1.2.3


From 5ec42bf04d72fd6d0a6855810cc779e0ee31dfd7 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Mon, 4 Dec 2023 15:27:06 -0600
Subject: PCI: add INTEL_HDA_ARL to pci_ids.h
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The PCI ID insertion follows the increasing order in the table, but
this hardware follows MTL (MeteorLake).

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Péter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Acked-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20231204212710.185976-2-pierre-louis.bossart@linux.intel.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/linux/pci_ids.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 275799b5f535..97cc0baad0f4 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -3065,6 +3065,7 @@
 #define PCI_DEVICE_ID_INTEL_82443GX_0	0x71a0
 #define PCI_DEVICE_ID_INTEL_82443GX_2	0x71a2
 #define PCI_DEVICE_ID_INTEL_82372FB_1	0x7601
+#define PCI_DEVICE_ID_INTEL_HDA_ARL	0x7728
 #define PCI_DEVICE_ID_INTEL_HDA_RPL_S	0x7a50
 #define PCI_DEVICE_ID_INTEL_HDA_ADL_S	0x7ad0
 #define PCI_DEVICE_ID_INTEL_HDA_MTL	0x7e28
-- 
cgit v1.2.3


From fa422b353d212373fb2b2857a5ea5a6fa4876f9c Mon Sep 17 00:00:00 2001
From: Shiyang Ruan <ruansy.fnst@fujitsu.com>
Date: Mon, 23 Oct 2023 15:20:46 +0800
Subject: mm, pmem, xfs: Introduce MF_MEM_PRE_REMOVE for unbind

Now, if we suddenly remove a PMEM device(by calling unbind) which
contains FSDAX while programs are still accessing data in this device,
e.g.:
```
 $FSSTRESS_PROG -d $SCRATCH_MNT -n 99999 -p 4 &
 # $FSX_PROG -N 1000000 -o 8192 -l 500000 $SCRATCH_MNT/t001 &
 echo "pfn1.1" > /sys/bus/nd/drivers/nd_pmem/unbind
```
it could come into an unacceptable state:
  1. device has gone but mount point still exists, and umount will fail
       with "target is busy"
  2. programs will hang and cannot be killed
  3. may crash with NULL pointer dereference

To fix this, we introduce a MF_MEM_PRE_REMOVE flag to let it know that we
are going to remove the whole device, and make sure all related processes
could be notified so that they could end up gracefully.

This patch is inspired by Dan's "mm, dax, pmem: Introduce
dev_pagemap_failure()"[1].  With the help of dax_holder and
->notify_failure() mechanism, the pmem driver is able to ask filesystem
on it to unmap all files in use, and notify processes who are using
those files.

Call trace:
trigger unbind
 -> unbind_store()
  -> ... (skip)
   -> devres_release_all()
    -> kill_dax()
     -> dax_holder_notify_failure(dax_dev, 0, U64_MAX, MF_MEM_PRE_REMOVE)
      -> xfs_dax_notify_failure()
      `-> freeze_super()             // freeze (kernel call)
      `-> do xfs rmap
      ` -> mf_dax_kill_procs()
      `  -> collect_procs_fsdax()    // all associated processes
      `  -> unmap_and_kill()
      ` -> invalidate_inode_pages2_range() // drop file's cache
      `-> thaw_super()               // thaw (both kernel & user call)

Introduce MF_MEM_PRE_REMOVE to let filesystem know this is a remove
event.  Use the exclusive freeze/thaw[2] to lock the filesystem to prevent
new dax mapping from being created.  Do not shutdown filesystem directly
if configuration is not supported, or if failure range includes metadata
area.  Make sure all files and processes(not only the current progress)
are handled correctly.  Also drop the cache of associated files before
pmem is removed.

[1]: https://lore.kernel.org/linux-mm/161604050314.1463742.14151665140035795571.stgit@dwillia2-desk3.amr.corp.intel.com/
[2]: https://lore.kernel.org/linux-xfs/169116275623.3187159.16862410128731457358.stg-ugh@frogsfrogsfrogs/

Signed-off-by: Shiyang Ruan <ruansy.fnst@fujitsu.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
---
 drivers/dax/super.c         |   3 +-
 fs/xfs/xfs_notify_failure.c | 108 +++++++++++++++++++++++++++++++++++++++++---
 include/linux/mm.h          |   1 +
 mm/memory-failure.c         |  21 +++++++--
 4 files changed, 122 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 0da9232ea175..f4b635526345 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -326,7 +326,8 @@ void kill_dax(struct dax_device *dax_dev)
 		return;
 
 	if (dax_dev->holder_data != NULL)
-		dax_holder_notify_failure(dax_dev, 0, U64_MAX, 0);
+		dax_holder_notify_failure(dax_dev, 0, U64_MAX,
+				MF_MEM_PRE_REMOVE);
 
 	clear_bit(DAXDEV_ALIVE, &dax_dev->flags);
 	synchronize_srcu(&dax_srcu);
diff --git a/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c
index a7daa522e00f..fa50e5308292 100644
--- a/fs/xfs/xfs_notify_failure.c
+++ b/fs/xfs/xfs_notify_failure.c
@@ -22,6 +22,7 @@
 
 #include <linux/mm.h>
 #include <linux/dax.h>
+#include <linux/fs.h>
 
 struct xfs_failure_info {
 	xfs_agblock_t		startblock;
@@ -73,10 +74,16 @@ xfs_dax_failure_fn(
 	struct xfs_mount		*mp = cur->bc_mp;
 	struct xfs_inode		*ip;
 	struct xfs_failure_info		*notify = data;
+	struct address_space		*mapping;
+	pgoff_t				pgoff;
+	unsigned long			pgcnt;
 	int				error = 0;
 
 	if (XFS_RMAP_NON_INODE_OWNER(rec->rm_owner) ||
 	    (rec->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK))) {
+		/* Continue the query because this isn't a failure. */
+		if (notify->mf_flags & MF_MEM_PRE_REMOVE)
+			return 0;
 		notify->want_shutdown = true;
 		return 0;
 	}
@@ -92,14 +99,60 @@ xfs_dax_failure_fn(
 		return 0;
 	}
 
-	error = mf_dax_kill_procs(VFS_I(ip)->i_mapping,
-				  xfs_failure_pgoff(mp, rec, notify),
-				  xfs_failure_pgcnt(mp, rec, notify),
-				  notify->mf_flags);
+	mapping = VFS_I(ip)->i_mapping;
+	pgoff = xfs_failure_pgoff(mp, rec, notify);
+	pgcnt = xfs_failure_pgcnt(mp, rec, notify);
+
+	/* Continue the rmap query if the inode isn't a dax file. */
+	if (dax_mapping(mapping))
+		error = mf_dax_kill_procs(mapping, pgoff, pgcnt,
+					  notify->mf_flags);
+
+	/* Invalidate the cache in dax pages. */
+	if (notify->mf_flags & MF_MEM_PRE_REMOVE)
+		invalidate_inode_pages2_range(mapping, pgoff,
+					      pgoff + pgcnt - 1);
+
 	xfs_irele(ip);
 	return error;
 }
 
+static int
+xfs_dax_notify_failure_freeze(
+	struct xfs_mount	*mp)
+{
+	struct super_block	*sb = mp->m_super;
+	int			error;
+
+	error = freeze_super(sb, FREEZE_HOLDER_KERNEL);
+	if (error)
+		xfs_emerg(mp, "already frozen by kernel, err=%d", error);
+
+	return error;
+}
+
+static void
+xfs_dax_notify_failure_thaw(
+	struct xfs_mount	*mp,
+	bool			kernel_frozen)
+{
+	struct super_block	*sb = mp->m_super;
+	int			error;
+
+	if (kernel_frozen) {
+		error = thaw_super(sb, FREEZE_HOLDER_KERNEL);
+		if (error)
+			xfs_emerg(mp, "still frozen after notify failure, err=%d",
+				error);
+	}
+
+	/*
+	 * Also thaw userspace call anyway because the device is about to be
+	 * removed immediately.
+	 */
+	thaw_super(sb, FREEZE_HOLDER_USERSPACE);
+}
+
 static int
 xfs_dax_notify_ddev_failure(
 	struct xfs_mount	*mp,
@@ -112,15 +165,29 @@ xfs_dax_notify_ddev_failure(
 	struct xfs_btree_cur	*cur = NULL;
 	struct xfs_buf		*agf_bp = NULL;
 	int			error = 0;
+	bool			kernel_frozen = false;
 	xfs_fsblock_t		fsbno = XFS_DADDR_TO_FSB(mp, daddr);
 	xfs_agnumber_t		agno = XFS_FSB_TO_AGNO(mp, fsbno);
 	xfs_fsblock_t		end_fsbno = XFS_DADDR_TO_FSB(mp,
 							     daddr + bblen - 1);
 	xfs_agnumber_t		end_agno = XFS_FSB_TO_AGNO(mp, end_fsbno);
 
+	if (mf_flags & MF_MEM_PRE_REMOVE) {
+		xfs_info(mp, "Device is about to be removed!");
+		/*
+		 * Freeze fs to prevent new mappings from being created.
+		 * - Keep going on if others already hold the kernel forzen.
+		 * - Keep going on if other errors too because this device is
+		 *   starting to fail.
+		 * - If kernel frozen state is hold successfully here, thaw it
+		 *   here as well at the end.
+		 */
+		kernel_frozen = xfs_dax_notify_failure_freeze(mp) == 0;
+	}
+
 	error = xfs_trans_alloc_empty(mp, &tp);
 	if (error)
-		return error;
+		goto out;
 
 	for (; agno <= end_agno; agno++) {
 		struct xfs_rmap_irec	ri_low = { };
@@ -165,11 +232,26 @@ xfs_dax_notify_ddev_failure(
 	}
 
 	xfs_trans_cancel(tp);
-	if (error || notify.want_shutdown) {
+
+	/*
+	 * Shutdown fs from a force umount in pre-remove case which won't fail,
+	 * so errors can be ignored.  Otherwise, shutdown the filesystem with
+	 * CORRUPT flag if error occured or notify.want_shutdown was set during
+	 * RMAP querying.
+	 */
+	if (mf_flags & MF_MEM_PRE_REMOVE)
+		xfs_force_shutdown(mp, SHUTDOWN_FORCE_UMOUNT);
+	else if (error || notify.want_shutdown) {
 		xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_ONDISK);
 		if (!error)
 			error = -EFSCORRUPTED;
 	}
+
+out:
+	/* Thaw the fs if it has been frozen before. */
+	if (mf_flags & MF_MEM_PRE_REMOVE)
+		xfs_dax_notify_failure_thaw(mp, kernel_frozen);
+
 	return error;
 }
 
@@ -197,6 +279,14 @@ xfs_dax_notify_failure(
 
 	if (mp->m_logdev_targp && mp->m_logdev_targp->bt_daxdev == dax_dev &&
 	    mp->m_logdev_targp != mp->m_ddev_targp) {
+		/*
+		 * In the pre-remove case the failure notification is attempting
+		 * to trigger a force unmount.  The expectation is that the
+		 * device is still present, but its removal is in progress and
+		 * can not be cancelled, proceed with accessing the log device.
+		 */
+		if (mf_flags & MF_MEM_PRE_REMOVE)
+			return 0;
 		xfs_err(mp, "ondisk log corrupt, shutting down fs!");
 		xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_ONDISK);
 		return -EFSCORRUPTED;
@@ -210,6 +300,12 @@ xfs_dax_notify_failure(
 	ddev_start = mp->m_ddev_targp->bt_dax_part_off;
 	ddev_end = ddev_start + bdev_nr_bytes(mp->m_ddev_targp->bt_bdev) - 1;
 
+	/* Notify failure on the whole device. */
+	if (offset == 0 && len == U64_MAX) {
+		offset = ddev_start;
+		len = bdev_nr_bytes(mp->m_ddev_targp->bt_bdev);
+	}
+
 	/* Ignore the range out of filesystem area */
 	if (offset + len - 1 < ddev_start)
 		return -ENXIO;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 418d26608ece..caf13e94260e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3904,6 +3904,7 @@ enum mf_flags {
 	MF_UNPOISON = 1 << 4,
 	MF_SW_SIMULATED = 1 << 5,
 	MF_NO_RETRY = 1 << 6,
+	MF_MEM_PRE_REMOVE = 1 << 7,
 };
 int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index,
 		      unsigned long count, int mf_flags);
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 660c21859118..cff3bda60691 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -679,7 +679,7 @@ static void add_to_kill_fsdax(struct task_struct *tsk, struct page *p,
  */
 static void collect_procs_fsdax(struct page *page,
 		struct address_space *mapping, pgoff_t pgoff,
-		struct list_head *to_kill)
+		struct list_head *to_kill, bool pre_remove)
 {
 	struct vm_area_struct *vma;
 	struct task_struct *tsk;
@@ -687,8 +687,15 @@ static void collect_procs_fsdax(struct page *page,
 	i_mmap_lock_read(mapping);
 	rcu_read_lock();
 	for_each_process(tsk) {
-		struct task_struct *t = task_early_kill(tsk, true);
+		struct task_struct *t = tsk;
 
+		/*
+		 * Search for all tasks while MF_MEM_PRE_REMOVE is set, because
+		 * the current may not be the one accessing the fsdax page.
+		 * Otherwise, search for the current task.
+		 */
+		if (!pre_remove)
+			t = task_early_kill(tsk, true);
 		if (!t)
 			continue;
 		vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) {
@@ -1795,6 +1802,7 @@ int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index,
 	dax_entry_t cookie;
 	struct page *page;
 	size_t end = index + count;
+	bool pre_remove = mf_flags & MF_MEM_PRE_REMOVE;
 
 	mf_flags |= MF_ACTION_REQUIRED | MF_MUST_KILL;
 
@@ -1806,9 +1814,14 @@ int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index,
 		if (!page)
 			goto unlock;
 
-		SetPageHWPoison(page);
+		if (!pre_remove)
+			SetPageHWPoison(page);
 
-		collect_procs_fsdax(page, mapping, index, &to_kill);
+		/*
+		 * The pre_remove case is revoking access, the memory is still
+		 * good and could theoretically be put back into service.
+		 */
+		collect_procs_fsdax(page, mapping, index, &to_kill, pre_remove);
 		unmap_and_kill(&to_kill, page_to_pfn(page), mapping,
 				index, mf_flags);
 unlock:
-- 
cgit v1.2.3


From 812cc1da7ffd9e178ef66b8a22113be10fba466c Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Tue, 5 Dec 2023 13:13:36 -0700
Subject: drm/bridge: Return NULL instead of plain 0 in
 drm_dp_hpd_bridge_register() stub

sparse complains:

  drivers/usb/typec/tcpm/qcom/qcom_pmic_typec.c: note: in included file:
  include/drm/bridge/aux-bridge.h:29:16: sparse: sparse: Using plain integer as NULL pointer

Return NULL to clear up the warning.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202312060025.BdeqZrWx-lkp@intel.com/
Fixes: e560518a6c2e ("drm/bridge: implement generic DP HPD bridge")
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20231205-drm_aux_bridge-fixes-v1-3-d242a0ae9df4@kernel.org
---
 include/drm/bridge/aux-bridge.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/drm/bridge/aux-bridge.h b/include/drm/bridge/aux-bridge.h
index 66249ff0858e..c4c423e97f06 100644
--- a/include/drm/bridge/aux-bridge.h
+++ b/include/drm/bridge/aux-bridge.h
@@ -26,7 +26,7 @@ void drm_aux_hpd_bridge_notify(struct device *dev, enum drm_connector_status sta
 static inline struct device *drm_dp_hpd_bridge_register(struct device *parent,
 							struct device_node *np)
 {
-	return 0;
+	return NULL;
 }
 
 static inline void drm_aux_hpd_bridge_notify(struct device *dev, enum drm_connector_status status)
-- 
cgit v1.2.3


From 3bc05faf37876f99e2a7baffa9c66fdcfb11d1f7 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Tue, 5 Dec 2023 17:42:30 +0100
Subject: net: dsa: microchip: properly support platform_data probing

The ksz driver has bits and pieces of platform_data probing support, but
it doesn't work.

The conventional thing to do is to have an encapsulating structure for
struct dsa_chip_data that gets put into dev->platform_data. This driver
expects a struct ksz_platform_data, but that doesn't contain a struct
dsa_chip_data as first element, which will obviously not work with
dsa_switch_probe() -> dsa_switch_parse().

Pointing dev->platform_data to a struct dsa_chip_data directly is in
principle possible, but that doesn't work either. The driver has
ksz_switch_detect() to read the device ID from hardware, followed by
ksz_check_device_id() to compare it against a predetermined expected
value. This protects against early errors in the SPI/I2C communication.
With platform_data, the mechanism in ksz_check_device_id() doesn't work
and even leads to NULL pointer dereferences, since of_device_get_match_data()
doesn't work in that probe path.

So obviously, the platform_data support is actually missing, and the
existing handling of struct ksz_platform_data is bogus. Complete the
support by adding a struct dsa_chip_data as first element, and fixing up
ksz_check_device_id() to pick up the platform_data instead of the
unavailable of_device_get_match_data().

The early dev->chip_id assignment from ksz_switch_register() is also
bogus, because ksz_switch_detect() sets it to an initial value. So
remove it.

Also, ksz_platform_data :: enabled_ports isn't used anywhere, delete it.

Link: https://lore.kernel.org/netdev/20231204154315.3906267-1-dd@embedd.com/
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: Daniel Danzberger <dd@embedd.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/microchip/ksz_common.c      | 21 +++++++++++++--------
 include/linux/platform_data/microchip-ksz.h |  4 +++-
 2 files changed, 16 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index 9545aed905f5..db1bbcf3a5f2 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -1673,15 +1673,23 @@ static const struct ksz_chip_data *ksz_lookup_info(unsigned int prod_num)
 
 static int ksz_check_device_id(struct ksz_device *dev)
 {
-	const struct ksz_chip_data *dt_chip_data;
+	const struct ksz_chip_data *expected_chip_data;
+	u32 expected_chip_id;
 
-	dt_chip_data = of_device_get_match_data(dev->dev);
+	if (dev->pdata) {
+		expected_chip_id = dev->pdata->chip_id;
+		expected_chip_data = ksz_lookup_info(expected_chip_id);
+		if (WARN_ON(!expected_chip_data))
+			return -ENODEV;
+	} else {
+		expected_chip_data = of_device_get_match_data(dev->dev);
+		expected_chip_id = expected_chip_data->chip_id;
+	}
 
-	/* Check for Device Tree and Chip ID */
-	if (dt_chip_data->chip_id != dev->chip_id) {
+	if (expected_chip_id != dev->chip_id) {
 		dev_err(dev->dev,
 			"Device tree specifies chip %s but found %s, please fix it!\n",
-			dt_chip_data->dev_name, dev->info->dev_name);
+			expected_chip_data->dev_name, dev->info->dev_name);
 		return -ENODEV;
 	}
 
@@ -4156,9 +4164,6 @@ int ksz_switch_register(struct ksz_device *dev)
 	int ret;
 	int i;
 
-	if (dev->pdata)
-		dev->chip_id = dev->pdata->chip_id;
-
 	dev->reset_gpio = devm_gpiod_get_optional(dev->dev, "reset",
 						  GPIOD_OUT_LOW);
 	if (IS_ERR(dev->reset_gpio))
diff --git a/include/linux/platform_data/microchip-ksz.h b/include/linux/platform_data/microchip-ksz.h
index ea1cc6d829e9..6480bf4af0fb 100644
--- a/include/linux/platform_data/microchip-ksz.h
+++ b/include/linux/platform_data/microchip-ksz.h
@@ -20,10 +20,12 @@
 #define __MICROCHIP_KSZ_H
 
 #include <linux/types.h>
+#include <linux/platform_data/dsa.h>
 
 struct ksz_platform_data {
+	/* Must be first such that dsa_register_switch() can access it */
+	struct dsa_chip_data cd;
 	u32 chip_id;
-	u16 enabled_ports;
 };
 
 #endif
-- 
cgit v1.2.3


From d16f1096b320d42e41ad9dee4d4098afd140d3e1 Mon Sep 17 00:00:00 2001
From: Daniel Danzberger <dd@embedd.com>
Date: Tue, 5 Dec 2023 17:42:31 +0100
Subject: net: dsa: microchip: move ksz_chip_id enum to platform include

With the ksz_chip_id enums moved to the platform include file for ksz
switches, platform code that instantiates a device can now use these to
set ksz_platform_data::chip_id.

Signed-off-by: Daniel Danzberger <dd@embedd.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/microchip/ksz_common.h      | 20 +-------------------
 include/linux/platform_data/microchip-ksz.h | 19 +++++++++++++++++++
 2 files changed, 20 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h
index d1a1c876ba0d..15612101a155 100644
--- a/drivers/net/dsa/microchip/ksz_common.h
+++ b/drivers/net/dsa/microchip/ksz_common.h
@@ -14,6 +14,7 @@
 #include <linux/regmap.h>
 #include <net/dsa.h>
 #include <linux/irq.h>
+#include <linux/platform_data/microchip-ksz.h>
 
 #include "ksz_ptp.h"
 
@@ -203,25 +204,6 @@ enum ksz_model {
 	LAN9374,
 };
 
-enum ksz_chip_id {
-	KSZ8563_CHIP_ID = 0x8563,
-	KSZ8795_CHIP_ID = 0x8795,
-	KSZ8794_CHIP_ID = 0x8794,
-	KSZ8765_CHIP_ID = 0x8765,
-	KSZ8830_CHIP_ID = 0x8830,
-	KSZ9477_CHIP_ID = 0x00947700,
-	KSZ9896_CHIP_ID = 0x00989600,
-	KSZ9897_CHIP_ID = 0x00989700,
-	KSZ9893_CHIP_ID = 0x00989300,
-	KSZ9563_CHIP_ID = 0x00956300,
-	KSZ9567_CHIP_ID = 0x00956700,
-	LAN9370_CHIP_ID = 0x00937000,
-	LAN9371_CHIP_ID = 0x00937100,
-	LAN9372_CHIP_ID = 0x00937200,
-	LAN9373_CHIP_ID = 0x00937300,
-	LAN9374_CHIP_ID = 0x00937400,
-};
-
 enum ksz_regs {
 	REG_SW_MAC_ADDR,
 	REG_IND_CTRL_0,
diff --git a/include/linux/platform_data/microchip-ksz.h b/include/linux/platform_data/microchip-ksz.h
index 6480bf4af0fb..f177416635a2 100644
--- a/include/linux/platform_data/microchip-ksz.h
+++ b/include/linux/platform_data/microchip-ksz.h
@@ -22,6 +22,25 @@
 #include <linux/types.h>
 #include <linux/platform_data/dsa.h>
 
+enum ksz_chip_id {
+	KSZ8563_CHIP_ID = 0x8563,
+	KSZ8795_CHIP_ID = 0x8795,
+	KSZ8794_CHIP_ID = 0x8794,
+	KSZ8765_CHIP_ID = 0x8765,
+	KSZ8830_CHIP_ID = 0x8830,
+	KSZ9477_CHIP_ID = 0x00947700,
+	KSZ9896_CHIP_ID = 0x00989600,
+	KSZ9897_CHIP_ID = 0x00989700,
+	KSZ9893_CHIP_ID = 0x00989300,
+	KSZ9563_CHIP_ID = 0x00956300,
+	KSZ9567_CHIP_ID = 0x00956700,
+	LAN9370_CHIP_ID = 0x00937000,
+	LAN9371_CHIP_ID = 0x00937100,
+	LAN9372_CHIP_ID = 0x00937200,
+	LAN9373_CHIP_ID = 0x00937300,
+	LAN9374_CHIP_ID = 0x00937400,
+};
+
 struct ksz_platform_data {
 	/* Must be first such that dsa_register_switch() can access it */
 	struct dsa_chip_data cd;
-- 
cgit v1.2.3


From 37c8ceb6d92c955f5dd8223c3f6c90b277322210 Mon Sep 17 00:00:00 2001
From: Avri Altman <avri.altman@wdc.com>
Date: Mon, 30 Oct 2023 08:22:26 +0200
Subject: mmc: core: Remove packed command leftovers

Packed commands support was removed long time ago, but some bits got
left behind. Remove them.

Signed-off-by: Avri Altman <avri.altman@wdc.com>
Link: https://lore.kernel.org/r/20231030062226.1895692-1-avri.altman@wdc.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/core/mmc.c   |  5 -----
 include/linux/mmc/card.h |  3 ---
 include/linux/mmc/core.h |  1 -
 include/linux/mmc/mmc.h  | 10 ----------
 4 files changed, 19 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 705942edacc6..7b996db570c9 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -613,11 +613,6 @@ static int mmc_decode_ext_csd(struct mmc_card *card, u8 *ext_csd)
 		} else {
 			card->ext_csd.data_tag_unit_size = 0;
 		}
-
-		card->ext_csd.max_packed_writes =
-			ext_csd[EXT_CSD_MAX_PACKED_WRITES];
-		card->ext_csd.max_packed_reads =
-			ext_csd[EXT_CSD_MAX_PACKED_READS];
 	} else {
 		card->ext_csd.data_sector_size = 512;
 	}
diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h
index 7b12eebc5586..47eeb122524c 100644
--- a/include/linux/mmc/card.h
+++ b/include/linux/mmc/card.h
@@ -52,9 +52,6 @@ struct mmc_ext_csd {
 	u8			part_config;
 	u8			cache_ctrl;
 	u8			rst_n_function;
-	u8			max_packed_writes;
-	u8			max_packed_reads;
-	u8			packed_event_en;
 	unsigned int		part_time;		/* Units: ms */
 	unsigned int		sa_timeout;		/* Units: 100ns */
 	unsigned int		generic_cmd6_time;	/* Units: 10ms */
diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h
index 6efec0b9820c..2c7928a50907 100644
--- a/include/linux/mmc/core.h
+++ b/include/linux/mmc/core.h
@@ -27,7 +27,6 @@ struct mmc_command {
 	u32			opcode;
 	u32			arg;
 #define MMC_CMD23_ARG_REL_WR	(1 << 31)
-#define MMC_CMD23_ARG_PACKED	((0 << 31) | (1 << 30))
 #define MMC_CMD23_ARG_TAG_REQ	(1 << 29)
 	u32			resp[4];
 	unsigned int		flags;		/* expected response type */
diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h
index 6f7993803ee7..cf2bcb5da30d 100644
--- a/include/linux/mmc/mmc.h
+++ b/include/linux/mmc/mmc.h
@@ -257,8 +257,6 @@ static inline bool mmc_ready_for_data(u32 status)
 #define EXT_CSD_FLUSH_CACHE		32      /* W */
 #define EXT_CSD_CACHE_CTRL		33      /* R/W */
 #define EXT_CSD_POWER_OFF_NOTIFICATION	34	/* R/W */
-#define EXT_CSD_PACKED_FAILURE_INDEX	35	/* RO */
-#define EXT_CSD_PACKED_CMD_STATUS	36	/* RO */
 #define EXT_CSD_EXP_EVENTS_STATUS	54	/* RO, 2 bytes */
 #define EXT_CSD_EXP_EVENTS_CTRL		56	/* R/W, 2 bytes */
 #define EXT_CSD_DATA_SECTOR_SIZE	61	/* R */
@@ -321,8 +319,6 @@ static inline bool mmc_ready_for_data(u32 status)
 #define EXT_CSD_SUPPORTED_MODE		493	/* RO */
 #define EXT_CSD_TAG_UNIT_SIZE		498	/* RO */
 #define EXT_CSD_DATA_TAG_SUPPORT	499	/* RO */
-#define EXT_CSD_MAX_PACKED_WRITES	500	/* RO */
-#define EXT_CSD_MAX_PACKED_READS	501	/* RO */
 #define EXT_CSD_BKOPS_SUPPORT		502	/* RO */
 #define EXT_CSD_HPI_FEATURES		503	/* RO */
 
@@ -402,18 +398,12 @@ static inline bool mmc_ready_for_data(u32 status)
 #define EXT_CSD_PWR_CL_8BIT_SHIFT	4
 #define EXT_CSD_PWR_CL_4BIT_SHIFT	0
 
-#define EXT_CSD_PACKED_EVENT_EN	BIT(3)
-
 /*
  * EXCEPTION_EVENT_STATUS field
  */
 #define EXT_CSD_URGENT_BKOPS		BIT(0)
 #define EXT_CSD_DYNCAP_NEEDED		BIT(1)
 #define EXT_CSD_SYSPOOL_EXHAUSTED	BIT(2)
-#define EXT_CSD_PACKED_FAILURE		BIT(3)
-
-#define EXT_CSD_PACKED_GENERIC_ERROR	BIT(0)
-#define EXT_CSD_PACKED_INDEXED_ERROR	BIT(1)
 
 /*
  * BKOPS status level
-- 
cgit v1.2.3


From d3f4020a213e1cb125eed2363fca372a23f7de7a Mon Sep 17 00:00:00 2001
From: Junxian Huang <huangjunxian6@hisilicon.com>
Date: Thu, 7 Dec 2023 19:42:28 +0800
Subject: RDMA/hns: Response dmac to userspace

While creating AH, dmac is already resolved in kernel. Response dmac
to userspace so that userspace doesn't need to resolve dmac repeatedly.

Signed-off-by: Junxian Huang <huangjunxian6@hisilicon.com>
Link: https://lore.kernel.org/r/20231207114231.2872104-3-huangjunxian6@hisilicon.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/hns/hns_roce_ah.c | 7 +++++++
 include/uapi/rdma/hns-abi.h             | 5 +++++
 2 files changed, 12 insertions(+)

(limited to 'include')

diff --git a/drivers/infiniband/hw/hns/hns_roce_ah.c b/drivers/infiniband/hw/hns/hns_roce_ah.c
index fbf046982374..b4209b6aed8d 100644
--- a/drivers/infiniband/hw/hns/hns_roce_ah.c
+++ b/drivers/infiniband/hw/hns/hns_roce_ah.c
@@ -57,6 +57,7 @@ int hns_roce_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr,
 	struct rdma_ah_attr *ah_attr = init_attr->ah_attr;
 	const struct ib_global_route *grh = rdma_ah_read_grh(ah_attr);
 	struct hns_roce_dev *hr_dev = to_hr_dev(ibah->device);
+	struct hns_roce_ib_create_ah_resp resp = {};
 	struct hns_roce_ah *ah = to_hr_ah(ibah);
 	int ret = 0;
 	u32 max_sl;
@@ -97,6 +98,12 @@ int hns_roce_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr,
 		ah->av.vlan_en = ah->av.vlan_id < VLAN_N_VID;
 	}
 
+	if (udata) {
+		memcpy(resp.dmac, ah_attr->roce.dmac, ETH_ALEN);
+		ret = ib_copy_to_udata(udata, &resp,
+				       min(udata->outlen, sizeof(resp)));
+	}
+
 err_out:
 	if (ret)
 		atomic64_inc(&hr_dev->dfx_cnt[HNS_ROCE_DFX_AH_CREATE_ERR_CNT]);
diff --git a/include/uapi/rdma/hns-abi.h b/include/uapi/rdma/hns-abi.h
index ce0f37f83416..c996e151081e 100644
--- a/include/uapi/rdma/hns-abi.h
+++ b/include/uapi/rdma/hns-abi.h
@@ -125,4 +125,9 @@ struct hns_roce_ib_alloc_pd_resp {
 	__u32 pdn;
 };
 
+struct hns_roce_ib_create_ah_resp {
+	__u8 dmac[6];
+	__u8 reserved[2];
+};
+
 #endif /* HNS_ABI_USER_H */
-- 
cgit v1.2.3


From 9c0a5b3f9e55cf9a3dc85843666cae28adfdf7e3 Mon Sep 17 00:00:00 2001
From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Date: Mon, 4 Dec 2023 23:05:21 +0100
Subject: w1: gpio: Don't use platform data for driver data
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

struct device's .platform_data isn't for drivers to write to. For
driver-specific data there is .driver_data instead.

As there is no in-tree platform that provides w1_gpio_platform_data,
drop the include file and replace it by a local struct w1_gpio_ddata.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/8f7ebe03ddaa5a5c6e2b36fecdf59da7fc373527.1701727212.git.u.kleine-koenig@pengutronix.de
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 drivers/w1/masters/w1-gpio.c | 56 +++++++++++++++++++++-----------------------
 include/linux/w1-gpio.h      | 22 -----------------
 2 files changed, 27 insertions(+), 51 deletions(-)
 delete mode 100644 include/linux/w1-gpio.h

(limited to 'include')

diff --git a/drivers/w1/masters/w1-gpio.c b/drivers/w1/masters/w1-gpio.c
index e45acb6d916e..8d65db65178c 100644
--- a/drivers/w1/masters/w1-gpio.c
+++ b/drivers/w1/masters/w1-gpio.c
@@ -9,7 +9,6 @@
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
-#include <linux/w1-gpio.h>
 #include <linux/gpio/consumer.h>
 #include <linux/of_platform.h>
 #include <linux/err.h>
@@ -18,9 +17,16 @@
 
 #include <linux/w1.h>
 
+struct w1_gpio_ddata {
+	struct gpio_desc *gpiod;
+	struct gpio_desc *pullup_gpiod;
+	void (*enable_external_pullup)(int enable);
+	unsigned int pullup_duration;
+};
+
 static u8 w1_gpio_set_pullup(void *data, int delay)
 {
-	struct w1_gpio_platform_data *pdata = data;
+	struct w1_gpio_ddata *pdata = data;
 
 	if (delay) {
 		pdata->pullup_duration = delay;
@@ -46,14 +52,14 @@ static u8 w1_gpio_set_pullup(void *data, int delay)
 
 static void w1_gpio_write_bit(void *data, u8 bit)
 {
-	struct w1_gpio_platform_data *pdata = data;
+	struct w1_gpio_ddata *pdata = data;
 
 	gpiod_set_value(pdata->gpiod, bit);
 }
 
 static u8 w1_gpio_read_bit(void *data)
 {
-	struct w1_gpio_platform_data *pdata = data;
+	struct w1_gpio_ddata *pdata = data;
 
 	return gpiod_get_value(pdata->gpiod) ? 1 : 0;
 }
@@ -69,35 +75,25 @@ MODULE_DEVICE_TABLE(of, w1_gpio_dt_ids);
 static int w1_gpio_probe(struct platform_device *pdev)
 {
 	struct w1_bus_master *master;
-	struct w1_gpio_platform_data *pdata;
+	struct w1_gpio_ddata *pdata;
 	struct device *dev = &pdev->dev;
 	struct device_node *np = dev->of_node;
 	/* Enforce open drain mode by default */
 	enum gpiod_flags gflags = GPIOD_OUT_LOW_OPEN_DRAIN;
 	int err;
 
-	if (of_have_populated_dt()) {
-		pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
-		if (!pdata)
-			return -ENOMEM;
-
-		/*
-		 * This parameter means that something else than the gpiolib has
-		 * already set the line into open drain mode, so we should just
-		 * driver it high/low like we are in full control of the line and
-		 * open drain will happen transparently.
-		 */
-		if (of_property_present(np, "linux,open-drain"))
-			gflags = GPIOD_OUT_LOW;
-
-		pdev->dev.platform_data = pdata;
-	}
-	pdata = dev_get_platdata(dev);
+	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
+	if (!pdata)
+		return -ENOMEM;
 
-	if (!pdata) {
-		dev_err(dev, "No configuration data\n");
-		return -ENXIO;
-	}
+	/*
+	 * This parameter means that something else than the gpiolib has
+	 * already set the line into open drain mode, so we should just
+	 * driver it high/low like we are in full control of the line and
+	 * open drain will happen transparently.
+	 */
+	if (of_property_present(np, "linux,open-drain"))
+		gflags = GPIOD_OUT_LOW;
 
 	master = devm_kzalloc(dev, sizeof(struct w1_bus_master),
 			GFP_KERNEL);
@@ -152,7 +148,7 @@ static int w1_gpio_probe(struct platform_device *pdev)
 static int w1_gpio_remove(struct platform_device *pdev)
 {
 	struct w1_bus_master *master = platform_get_drvdata(pdev);
-	struct w1_gpio_platform_data *pdata = dev_get_platdata(&pdev->dev);
+	struct w1_gpio_ddata *pdata = master->data;
 
 	if (pdata->enable_external_pullup)
 		pdata->enable_external_pullup(0);
@@ -167,7 +163,8 @@ static int w1_gpio_remove(struct platform_device *pdev)
 
 static int __maybe_unused w1_gpio_suspend(struct device *dev)
 {
-	struct w1_gpio_platform_data *pdata = dev_get_platdata(dev);
+	struct w1_bus_master *master = dev_get_drvdata(dev);
+	struct w1_gpio_ddata *pdata = master->data;
 
 	if (pdata->enable_external_pullup)
 		pdata->enable_external_pullup(0);
@@ -177,7 +174,8 @@ static int __maybe_unused w1_gpio_suspend(struct device *dev)
 
 static int __maybe_unused w1_gpio_resume(struct device *dev)
 {
-	struct w1_gpio_platform_data *pdata = dev_get_platdata(dev);
+	struct w1_bus_master *master = dev_get_drvdata(dev);
+	struct w1_gpio_ddata *pdata = master->data;
 
 	if (pdata->enable_external_pullup)
 		pdata->enable_external_pullup(1);
diff --git a/include/linux/w1-gpio.h b/include/linux/w1-gpio.h
deleted file mode 100644
index 3495fd0dc790..000000000000
--- a/include/linux/w1-gpio.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * w1-gpio interface to platform code
- *
- * Copyright (C) 2007 Ville Syrjala <syrjala@sci.fi>
- */
-#ifndef _LINUX_W1_GPIO_H
-#define _LINUX_W1_GPIO_H
-
-struct gpio_desc;
-
-/**
- * struct w1_gpio_platform_data - Platform-dependent data for w1-gpio
- */
-struct w1_gpio_platform_data {
-	struct gpio_desc *gpiod;
-	struct gpio_desc *pullup_gpiod;
-	void (*enable_external_pullup)(int enable);
-	unsigned int pullup_duration;
-};
-
-#endif /* _LINUX_W1_GPIO_H */
-- 
cgit v1.2.3


From 4773d2f1a5c73c590c0c83bf42b156532bc69cb2 Mon Sep 17 00:00:00 2001
From: Dang Huynh <danct12@riseup.net>
Date: Tue, 21 Nov 2023 12:34:59 +0700
Subject: mfd: qcom-spmi-pmic: Add support for PM8937

Add the subtype and compatible strings for PM8937.

The PM8937 is found in various SoCs, including MSM8917, MSM8937,
MSM8940 and APQ variants.

Reviewed-by: Caleb Connolly <caleb.connolly@linaro.org>
Signed-off-by: Dang Huynh <danct12@riseup.net>
Link: https://lore.kernel.org/r/20231121-pm8937-v2-1-b0171ab62075@riseup.net
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/qcom-spmi-pmic.c      | 1 +
 include/soc/qcom/qcom-spmi-pmic.h | 1 +
 2 files changed, 2 insertions(+)

(limited to 'include')

diff --git a/drivers/mfd/qcom-spmi-pmic.c b/drivers/mfd/qcom-spmi-pmic.c
index 4549fa9f7d4b..eab5bf6cff10 100644
--- a/drivers/mfd/qcom-spmi-pmic.c
+++ b/drivers/mfd/qcom-spmi-pmic.c
@@ -53,6 +53,7 @@ static const struct of_device_id pmic_spmi_id_table[] = {
 	{ .compatible = "qcom,pm8901", .data = N_USIDS(2) },
 	{ .compatible = "qcom,pm8909", .data = N_USIDS(2) },
 	{ .compatible = "qcom,pm8916", .data = N_USIDS(2) },
+	{ .compatible = "qcom,pm8937", .data = N_USIDS(2) },
 	{ .compatible = "qcom,pm8941", .data = N_USIDS(2) },
 	{ .compatible = "qcom,pm8950", .data = N_USIDS(2) },
 	{ .compatible = "qcom,pm8994", .data = N_USIDS(2) },
diff --git a/include/soc/qcom/qcom-spmi-pmic.h b/include/soc/qcom/qcom-spmi-pmic.h
index c47cc71a999e..17a0a8c3d656 100644
--- a/include/soc/qcom/qcom-spmi-pmic.h
+++ b/include/soc/qcom/qcom-spmi-pmic.h
@@ -31,6 +31,7 @@
 #define PM8998_SUBTYPE		0x14
 #define PMI8998_SUBTYPE		0x15
 #define PM8005_SUBTYPE		0x18
+#define PM8937_SUBTYPE		0x19
 #define PM660L_SUBTYPE		0x1a
 #define PM660_SUBTYPE		0x1b
 #define PM8150_SUBTYPE		0x1e
-- 
cgit v1.2.3


From 1fe13d83e2873b0aedeb5b9a299ca763bd37d75f Mon Sep 17 00:00:00 2001
From: Kaihua Zhong <zhongkaihua@kylinos.cn>
Date: Wed, 29 Nov 2023 09:55:26 +0800
Subject: mfd: Fix a few spelling mistakes in PMIC header file comments

Fix four comment typos in MFD PMIC header files.

Reported-by: k2ci <kernel-bot@kylinos.cn>
Signed-off-by: Kaihua Zhong <zhongkaihua@kylinos.cn>
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Link: https://lore.kernel.org/r/20231129015526.3302865-1-zhongkaihua@kylinos.cn
Signed-off-by: Lee Jones <lee@kernel.org>
---
 include/linux/mfd/max77693-private.h | 2 +-
 include/linux/mfd/max77843-private.h | 2 +-
 include/linux/mfd/si476x-platform.h  | 2 +-
 include/linux/mfd/tps65910.h         | 2 +-
 4 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/mfd/max77693-private.h b/include/linux/mfd/max77693-private.h
index 311f7d3d2323..54444ff2a5de 100644
--- a/include/linux/mfd/max77693-private.h
+++ b/include/linux/mfd/max77693-private.h
@@ -405,7 +405,7 @@ enum max77693_haptic_reg {
 	MAX77693_HAPTIC_REG_END,
 };
 
-/* max77693-pmic LSCNFG configuraton register */
+/* max77693-pmic LSCNFG configuration register */
 #define MAX77693_PMIC_LOW_SYS_MASK      0x80
 #define MAX77693_PMIC_LOW_SYS_SHIFT     7
 
diff --git a/include/linux/mfd/max77843-private.h b/include/linux/mfd/max77843-private.h
index 0bc7454c4dbe..2fb4db67f110 100644
--- a/include/linux/mfd/max77843-private.h
+++ b/include/linux/mfd/max77843-private.h
@@ -198,7 +198,7 @@ enum max77843_irq_muic {
 #define MAX77843_MCONFIG_MEN_MASK		BIT(MCONFIG_MEN_SHIFT)
 #define MAX77843_MCONFIG_PDIV_MASK		(0x3 << MCONFIG_PDIV_SHIFT)
 
-/* Max77843 charger insterrupts */
+/* Max77843 charger interrupts */
 #define MAX77843_CHG_BYP_I			BIT(0)
 #define MAX77843_CHG_BATP_I			BIT(2)
 #define MAX77843_CHG_BAT_I			BIT(3)
diff --git a/include/linux/mfd/si476x-platform.h b/include/linux/mfd/si476x-platform.h
index 18363b773d07..cb99e16ca947 100644
--- a/include/linux/mfd/si476x-platform.h
+++ b/include/linux/mfd/si476x-platform.h
@@ -10,7 +10,7 @@
 #ifndef __SI476X_PLATFORM_H__
 #define __SI476X_PLATFORM_H__
 
-/* It is possible to select one of the four adresses using pins A0
+/* It is possible to select one of the four addresses using pins A0
  * and A1 on SI476x */
 #define SI476X_I2C_ADDR_1	0x60
 #define SI476X_I2C_ADDR_2	0x61
diff --git a/include/linux/mfd/tps65910.h b/include/linux/mfd/tps65910.h
index 701925db75b3..f67ef0a4e041 100644
--- a/include/linux/mfd/tps65910.h
+++ b/include/linux/mfd/tps65910.h
@@ -749,7 +749,7 @@
 #define VDDCTRL_ST_SHIFT                                 0
 
 
-/*Register VDDCTRL_OP  (0x28) bit definitios */
+/*Register VDDCTRL_OP  (0x28) bit definitions */
 #define VDDCTRL_OP_CMD_MASK                              0x80
 #define VDDCTRL_OP_CMD_SHIFT                             7
 #define VDDCTRL_OP_SEL_MASK                              0x7F
-- 
cgit v1.2.3


From 216382b1555de2fe11684ffd99d598ac77a92ed8 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Mon, 30 Oct 2023 10:55:19 +0100
Subject: dt-bindings: arm: qcom,ids: Add SoC ID for SM8650

Add the ID for the Qualcomm SM8650 SoC.

Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Mukesh Ojha <quic_mojha@quicinc.com>
Link: https://lore.kernel.org/r/20231030-topic-sm8650-upstream-socinfo-v2-1-4751e7391dc9@linaro.org
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 include/dt-bindings/arm/qcom,ids.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/dt-bindings/arm/qcom,ids.h b/include/dt-bindings/arm/qcom,ids.h
index f7248348a459..51e0f6059410 100644
--- a/include/dt-bindings/arm/qcom,ids.h
+++ b/include/dt-bindings/arm/qcom,ids.h
@@ -255,6 +255,7 @@
 #define QCOM_ID_SA8775P			534
 #define QCOM_ID_QRU1000			539
 #define QCOM_ID_QDU1000			545
+#define QCOM_ID_SM8650			557
 #define QCOM_ID_SM4450			568
 #define QCOM_ID_QDU1010			587
 #define QCOM_ID_QRU1032			588
-- 
cgit v1.2.3


From 206cd759fbd2fce07cadb6c73a302ecfc95ebdff Mon Sep 17 00:00:00 2001
From: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
Date: Thu, 26 Oct 2023 11:53:43 +0100
Subject: dt-bindings: clock: Add SC8280XP CAMCC

Add device tree bindings for the camera clock controller on
Qualcomm SC8280XP platform.

Signed-off-by: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231026105345.3376-3-bryan.odonoghue@linaro.org
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 .../bindings/clock/qcom,sm8450-camcc.yaml          |   2 +
 include/dt-bindings/clock/qcom,sc8280xp-camcc.h    | 179 +++++++++++++++++++++
 2 files changed, 181 insertions(+)
 create mode 100644 include/dt-bindings/clock/qcom,sc8280xp-camcc.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/clock/qcom,sm8450-camcc.yaml b/Documentation/devicetree/bindings/clock/qcom,sm8450-camcc.yaml
index 6915498deacf..48986460f994 100644
--- a/Documentation/devicetree/bindings/clock/qcom,sm8450-camcc.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,sm8450-camcc.yaml
@@ -16,6 +16,7 @@ description: |
   See also::
     include/dt-bindings/clock/qcom,sm8450-camcc.h
     include/dt-bindings/clock/qcom,sm8550-camcc.h
+    include/dt-bindings/clock/qcom,sc8280xp-camcc.h
 
 allOf:
   - $ref: qcom,gcc.yaml#
@@ -23,6 +24,7 @@ allOf:
 properties:
   compatible:
     enum:
+      - qcom,sc8280xp-camcc
       - qcom,sm8450-camcc
       - qcom,sm8550-camcc
 
diff --git a/include/dt-bindings/clock/qcom,sc8280xp-camcc.h b/include/dt-bindings/clock/qcom,sc8280xp-camcc.h
new file mode 100644
index 000000000000..ea5ec73c8c6a
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,sc8280xp-camcc.h
@@ -0,0 +1,179 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/*
+ * Copyright (c) 2021, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2023, Linaro Ltd.
+ */
+
+#ifndef __DT_BINDINGS_CLK_QCOM_CAMCC_SC8280XP_H__
+#define __DT_BINDINGS_CLK_QCOM_CAMCC_SC8280XP_H__
+
+/* CAMCC clocks */
+#define CAMCC_PLL0					0
+#define CAMCC_PLL0_OUT_EVEN				1
+#define CAMCC_PLL0_OUT_ODD				2
+#define CAMCC_PLL1					3
+#define CAMCC_PLL1_OUT_EVEN				4
+#define CAMCC_PLL2					5
+#define CAMCC_PLL3					6
+#define CAMCC_PLL3_OUT_EVEN				7
+#define CAMCC_PLL4					8
+#define CAMCC_PLL4_OUT_EVEN				9
+#define CAMCC_PLL5					10
+#define CAMCC_PLL5_OUT_EVEN				11
+#define CAMCC_PLL6					12
+#define CAMCC_PLL6_OUT_EVEN				13
+#define CAMCC_PLL7					14
+#define CAMCC_PLL7_OUT_EVEN				15
+#define CAMCC_PLL7_OUT_ODD				16
+#define CAMCC_BPS_AHB_CLK				17
+#define CAMCC_BPS_AREG_CLK				18
+#define CAMCC_BPS_AXI_CLK				19
+#define CAMCC_BPS_CLK					20
+#define CAMCC_BPS_CLK_SRC				21
+#define CAMCC_CAMNOC_AXI_CLK				22
+#define CAMCC_CAMNOC_AXI_CLK_SRC			23
+#define CAMCC_CAMNOC_DCD_XO_CLK				24
+#define CAMCC_CCI_0_CLK					25
+#define CAMCC_CCI_0_CLK_SRC				26
+#define CAMCC_CCI_1_CLK					27
+#define CAMCC_CCI_1_CLK_SRC				28
+#define CAMCC_CCI_2_CLK					29
+#define CAMCC_CCI_2_CLK_SRC				30
+#define CAMCC_CCI_3_CLK					31
+#define CAMCC_CCI_3_CLK_SRC				32
+#define CAMCC_CORE_AHB_CLK				33
+#define CAMCC_CPAS_AHB_CLK				34
+#define CAMCC_CPHY_RX_CLK_SRC				35
+#define CAMCC_CSI0PHYTIMER_CLK				36
+#define CAMCC_CSI0PHYTIMER_CLK_SRC			37
+#define CAMCC_CSI1PHYTIMER_CLK				38
+#define CAMCC_CSI1PHYTIMER_CLK_SRC			39
+#define CAMCC_CSI2PHYTIMER_CLK				40
+#define CAMCC_CSI2PHYTIMER_CLK_SRC			41
+#define CAMCC_CSI3PHYTIMER_CLK				42
+#define CAMCC_CSI3PHYTIMER_CLK_SRC			43
+#define CAMCC_CSIPHY0_CLK				44
+#define CAMCC_CSIPHY1_CLK				45
+#define CAMCC_CSIPHY2_CLK				46
+#define CAMCC_CSIPHY3_CLK				47
+#define CAMCC_FAST_AHB_CLK_SRC				48
+#define CAMCC_GDSC_CLK					49
+#define CAMCC_ICP_AHB_CLK				50
+#define CAMCC_ICP_CLK					51
+#define CAMCC_ICP_CLK_SRC				52
+#define CAMCC_IFE_0_AXI_CLK				53
+#define CAMCC_IFE_0_CLK					54
+#define CAMCC_IFE_0_CLK_SRC				55
+#define CAMCC_IFE_0_CPHY_RX_CLK				56
+#define CAMCC_IFE_0_CSID_CLK				57
+#define CAMCC_IFE_0_CSID_CLK_SRC			58
+#define CAMCC_IFE_0_DSP_CLK				59
+#define CAMCC_IFE_1_AXI_CLK				60
+#define CAMCC_IFE_1_CLK					61
+#define CAMCC_IFE_1_CLK_SRC				62
+#define CAMCC_IFE_1_CPHY_RX_CLK				63
+#define CAMCC_IFE_1_CSID_CLK				64
+#define CAMCC_IFE_1_CSID_CLK_SRC			65
+#define CAMCC_IFE_1_DSP_CLK				66
+#define CAMCC_IFE_2_AXI_CLK				67
+#define CAMCC_IFE_2_CLK					68
+#define CAMCC_IFE_2_CLK_SRC				69
+#define CAMCC_IFE_2_CPHY_RX_CLK				70
+#define CAMCC_IFE_2_CSID_CLK				71
+#define CAMCC_IFE_2_CSID_CLK_SRC			72
+#define CAMCC_IFE_2_DSP_CLK				73
+#define CAMCC_IFE_3_AXI_CLK				74
+#define CAMCC_IFE_3_CLK					75
+#define CAMCC_IFE_3_CLK_SRC				76
+#define CAMCC_IFE_3_CPHY_RX_CLK				77
+#define CAMCC_IFE_3_CSID_CLK				78
+#define CAMCC_IFE_3_CSID_CLK_SRC			79
+#define CAMCC_IFE_3_DSP_CLK				80
+#define CAMCC_IFE_LITE_0_CLK				81
+#define CAMCC_IFE_LITE_0_CLK_SRC			82
+#define CAMCC_IFE_LITE_0_CPHY_RX_CLK			83
+#define CAMCC_IFE_LITE_0_CSID_CLK			84
+#define CAMCC_IFE_LITE_0_CSID_CLK_SRC			85
+#define CAMCC_IFE_LITE_1_CLK				86
+#define CAMCC_IFE_LITE_1_CLK_SRC			87
+#define CAMCC_IFE_LITE_1_CPHY_RX_CLK			88
+#define CAMCC_IFE_LITE_1_CSID_CLK			89
+#define CAMCC_IFE_LITE_1_CSID_CLK_SRC			90
+#define CAMCC_IFE_LITE_2_CLK				91
+#define CAMCC_IFE_LITE_2_CLK_SRC			92
+#define CAMCC_IFE_LITE_2_CPHY_RX_CLK			93
+#define CAMCC_IFE_LITE_2_CSID_CLK			94
+#define CAMCC_IFE_LITE_2_CSID_CLK_SRC			95
+#define CAMCC_IFE_LITE_3_CLK				96
+#define CAMCC_IFE_LITE_3_CLK_SRC			97
+#define CAMCC_IFE_LITE_3_CPHY_RX_CLK			98
+#define CAMCC_IFE_LITE_3_CSID_CLK			99
+#define CAMCC_IFE_LITE_3_CSID_CLK_SRC			100
+#define CAMCC_IPE_0_AHB_CLK				101
+#define CAMCC_IPE_0_AREG_CLK				102
+#define CAMCC_IPE_0_AXI_CLK				103
+#define CAMCC_IPE_0_CLK					104
+#define CAMCC_IPE_0_CLK_SRC				105
+#define CAMCC_IPE_1_AHB_CLK				106
+#define CAMCC_IPE_1_AREG_CLK				107
+#define CAMCC_IPE_1_AXI_CLK				108
+#define CAMCC_IPE_1_CLK					109
+#define CAMCC_JPEG_CLK					110
+#define CAMCC_JPEG_CLK_SRC				111
+#define CAMCC_LRME_CLK					112
+#define CAMCC_LRME_CLK_SRC				113
+#define CAMCC_MCLK0_CLK					114
+#define CAMCC_MCLK0_CLK_SRC				115
+#define CAMCC_MCLK1_CLK					116
+#define CAMCC_MCLK1_CLK_SRC				117
+#define CAMCC_MCLK2_CLK					118
+#define CAMCC_MCLK2_CLK_SRC				119
+#define CAMCC_MCLK3_CLK					120
+#define CAMCC_MCLK3_CLK_SRC				121
+#define CAMCC_MCLK4_CLK					122
+#define CAMCC_MCLK4_CLK_SRC				123
+#define CAMCC_MCLK5_CLK					124
+#define CAMCC_MCLK5_CLK_SRC				125
+#define CAMCC_MCLK6_CLK					126
+#define CAMCC_MCLK6_CLK_SRC				127
+#define CAMCC_MCLK7_CLK					128
+#define CAMCC_MCLK7_CLK_SRC				129
+#define CAMCC_SLEEP_CLK					130
+#define CAMCC_SLEEP_CLK_SRC				131
+#define CAMCC_SLOW_AHB_CLK_SRC				132
+#define CAMCC_XO_CLK_SRC				133
+
+/* CAMCC resets */
+#define CAMCC_BPS_BCR					0
+#define CAMCC_CAMNOC_BCR				1
+#define CAMCC_CCI_BCR					2
+#define CAMCC_CPAS_BCR					3
+#define CAMCC_CSI0PHY_BCR				4
+#define CAMCC_CSI1PHY_BCR				5
+#define CAMCC_CSI2PHY_BCR				6
+#define CAMCC_CSI3PHY_BCR				7
+#define CAMCC_ICP_BCR					8
+#define CAMCC_IFE_0_BCR					9
+#define CAMCC_IFE_1_BCR					10
+#define CAMCC_IFE_2_BCR					11
+#define CAMCC_IFE_3_BCR					12
+#define CAMCC_IFE_LITE_0_BCR				13
+#define CAMCC_IFE_LITE_1_BCR				14
+#define CAMCC_IFE_LITE_2_BCR				15
+#define CAMCC_IFE_LITE_3_BCR				16
+#define CAMCC_IPE_0_BCR					17
+#define CAMCC_IPE_1_BCR					18
+#define CAMCC_JPEG_BCR					19
+#define CAMCC_LRME_BCR					20
+
+/* CAMCC GDSCRs */
+#define BPS_GDSC					0
+#define IFE_0_GDSC					1
+#define IFE_1_GDSC					2
+#define IFE_2_GDSC					3
+#define IFE_3_GDSC					4
+#define IPE_0_GDSC					5
+#define IPE_1_GDSC					6
+#define TITAN_TOP_GDSC					7
+
+#endif /* __DT_BINDINGS_CLK_QCOM_CAMCC_SC8280XP_H__ */
-- 
cgit v1.2.3


From 3f373de6da2c960f0630a63890dded7d53358e2a Mon Sep 17 00:00:00 2001
From: Vincent Knecht <vincent.knecht@mailoo.org>
Date: Sun, 29 Oct 2023 07:19:47 +0100
Subject: dt-bindings: clock: qcom,gcc-msm8939: Add CSI2 related clocks

When adding in the indexes for this clock-controller we missed
GCC_CAMSS_CSI2_AHB_CLK, GCC_CAMSS_CSI2_CLK, GCC_CAMSS_CSI2PHY_CLK,
GCC_CAMSS_CSI2PIX_CLK and GCC_CAMSS_CSI2RDI_CLK.

Add them in now.

Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Reviewed-by: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
Signed-off-by: Vincent Knecht <vincent.knecht@mailoo.org>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231029061948.505883-1-vincent.knecht@mailoo.org
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 include/dt-bindings/clock/qcom,gcc-msm8939.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'include')

diff --git a/include/dt-bindings/clock/qcom,gcc-msm8939.h b/include/dt-bindings/clock/qcom,gcc-msm8939.h
index 2d545ed0d35a..9a9bc55b49af 100644
--- a/include/dt-bindings/clock/qcom,gcc-msm8939.h
+++ b/include/dt-bindings/clock/qcom,gcc-msm8939.h
@@ -193,6 +193,12 @@
 #define GCC_VENUS0_CORE1_VCODEC0_CLK		184
 #define GCC_OXILI_TIMER_CLK			185
 #define SYSTEM_MM_NOC_BFDCD_CLK_SRC		186
+#define CSI2_CLK_SRC				187
+#define GCC_CAMSS_CSI2_AHB_CLK			188
+#define GCC_CAMSS_CSI2_CLK			189
+#define GCC_CAMSS_CSI2PHY_CLK			190
+#define GCC_CAMSS_CSI2PIX_CLK			191
+#define GCC_CAMSS_CSI2RDI_CLK			192
 
 /* Indexes for GDSCs */
 #define BIMC_GDSC				0
-- 
cgit v1.2.3


From 1a3b3bd142ffea56cdfd458246b2e4da6df19da6 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Mon, 6 Nov 2023 09:25:54 +0100
Subject: dt-bindings: clock: qcom: document the SM8650 TCSR Clock Controller

Add bindings documentation for the SM8650 TCSR Clock Controller.

Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231106-topic-sm8650-upstream-clocks-v3-1-761a6fadb4c0@linaro.org
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 .../devicetree/bindings/clock/qcom,sm8550-tcsr.yaml    |  8 ++++++--
 include/dt-bindings/clock/qcom,sm8650-tcsr.h           | 18 ++++++++++++++++++
 2 files changed, 24 insertions(+), 2 deletions(-)
 create mode 100644 include/dt-bindings/clock/qcom,sm8650-tcsr.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/clock/qcom,sm8550-tcsr.yaml b/Documentation/devicetree/bindings/clock/qcom,sm8550-tcsr.yaml
index 1bf1a41fd89c..af16b05eac96 100644
--- a/Documentation/devicetree/bindings/clock/qcom,sm8550-tcsr.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,sm8550-tcsr.yaml
@@ -13,12 +13,16 @@ description: |
   Qualcomm TCSR clock control module provides the clocks, resets and
   power domains on SM8550
 
-  See also:: include/dt-bindings/clock/qcom,sm8550-tcsr.h
+  See also:
+  - include/dt-bindings/clock/qcom,sm8550-tcsr.h
+  - include/dt-bindings/clock/qcom,sm8650-tcsr.h
 
 properties:
   compatible:
     items:
-      - const: qcom,sm8550-tcsr
+      - enum:
+          - qcom,sm8550-tcsr
+          - qcom,sm8650-tcsr
       - const: syscon
 
   clocks:
diff --git a/include/dt-bindings/clock/qcom,sm8650-tcsr.h b/include/dt-bindings/clock/qcom,sm8650-tcsr.h
new file mode 100644
index 000000000000..b2c72d492f1f
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,sm8650-tcsr.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/*
+ * Copyright (c) 2022, Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#ifndef _DT_BINDINGS_CLK_QCOM_TCSR_CC_SM8650_H
+#define _DT_BINDINGS_CLK_QCOM_TCSR_CC_SM8650_H
+
+/* TCSR CC clocks */
+#define TCSR_PCIE_0_CLKREF_EN					0
+#define TCSR_PCIE_1_CLKREF_EN					1
+#define TCSR_UFS_CLKREF_EN					2
+#define TCSR_UFS_PAD_CLKREF_EN					3
+#define TCSR_USB2_CLKREF_EN					4
+#define TCSR_USB3_CLKREF_EN					5
+
+#endif
-- 
cgit v1.2.3


From b69d932154dcfa84540aea55dd51a74fbc88d370 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Mon, 6 Nov 2023 09:25:55 +0100
Subject: dt-bindings: clock: qcom: document the SM8650 General Clock
 Controller

Add bindings documentation for the SM8650 General Clock Controller.

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20231106-topic-sm8650-upstream-clocks-v3-2-761a6fadb4c0@linaro.org
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 .../devicetree/bindings/clock/qcom,sm8650-gcc.yaml |  65 ++++++
 include/dt-bindings/clock/qcom,sm8650-gcc.h        | 254 +++++++++++++++++++++
 2 files changed, 319 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/clock/qcom,sm8650-gcc.yaml
 create mode 100644 include/dt-bindings/clock/qcom,sm8650-gcc.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/clock/qcom,sm8650-gcc.yaml b/Documentation/devicetree/bindings/clock/qcom,sm8650-gcc.yaml
new file mode 100644
index 000000000000..b54761cc8674
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/qcom,sm8650-gcc.yaml
@@ -0,0 +1,65 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/qcom,sm8650-gcc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm Global Clock & Reset Controller on SM8650
+
+maintainers:
+  - Bjorn Andersson <andersson@kernel.org>
+
+description: |
+  Qualcomm global clock control module provides the clocks, resets and power
+  domains on SM8650
+
+  See also:: include/dt-bindings/clock/qcom,sm8650-gcc.h
+
+properties:
+  compatible:
+    const: qcom,sm8650-gcc
+
+  clocks:
+    items:
+      - description: Board XO source
+      - description: Board Always On XO source
+      - description: Sleep clock source
+      - description: PCIE 0 Pipe clock source
+      - description: PCIE 1 Pipe clock source
+      - description: PCIE 1 Phy Auxiliary clock source
+      - description: UFS Phy Rx symbol 0 clock source
+      - description: UFS Phy Rx symbol 1 clock source
+      - description: UFS Phy Tx symbol 0 clock source
+      - description: USB3 Phy wrapper pipe clock source
+
+required:
+  - compatible
+  - clocks
+
+allOf:
+  - $ref: qcom,gcc.yaml#
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/qcom,rpmh.h>
+    clock-controller@100000 {
+      compatible = "qcom,sm8650-gcc";
+      reg = <0x00100000 0x001f4200>;
+      clocks = <&rpmhcc RPMH_CXO_CLK>,
+               <&rpmhcc RPMH_CXO_CLK_A>,
+               <&sleep_clk>,
+               <&pcie0_phy>,
+               <&pcie1_phy>,
+               <&pcie_1_phy_aux_clk>,
+               <&ufs_mem_phy 0>,
+               <&ufs_mem_phy 1>,
+               <&ufs_mem_phy 2>,
+               <&usb_1_qmpphy>;
+      #clock-cells = <1>;
+      #reset-cells = <1>;
+      #power-domain-cells = <1>;
+    };
+
+...
diff --git a/include/dt-bindings/clock/qcom,sm8650-gcc.h b/include/dt-bindings/clock/qcom,sm8650-gcc.h
new file mode 100644
index 000000000000..0c543ba46079
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,sm8650-gcc.h
@@ -0,0 +1,254 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/*
+ * Copyright (c) 2022, Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#ifndef _DT_BINDINGS_CLK_QCOM_GCC_SM8650_H
+#define _DT_BINDINGS_CLK_QCOM_GCC_SM8650_H
+
+/* GCC clocks */
+#define GCC_AGGRE_NOC_PCIE_AXI_CLK				0
+#define GCC_AGGRE_UFS_PHY_AXI_CLK				1
+#define GCC_AGGRE_UFS_PHY_AXI_HW_CTL_CLK			2
+#define GCC_AGGRE_USB3_PRIM_AXI_CLK				3
+#define GCC_BOOT_ROM_AHB_CLK					4
+#define GCC_CAMERA_AHB_CLK					5
+#define GCC_CAMERA_HF_AXI_CLK					6
+#define GCC_CAMERA_SF_AXI_CLK					7
+#define GCC_CAMERA_XO_CLK					8
+#define GCC_CFG_NOC_PCIE_ANOC_AHB_CLK				9
+#define GCC_CFG_NOC_USB3_PRIM_AXI_CLK				10
+#define GCC_CNOC_PCIE_SF_AXI_CLK				11
+#define GCC_DDRSS_GPU_AXI_CLK					12
+#define GCC_DDRSS_PCIE_SF_QTB_CLK				13
+#define GCC_DISP_AHB_CLK					14
+#define GCC_DISP_HF_AXI_CLK					15
+#define GCC_DISP_XO_CLK						16
+#define GCC_GP1_CLK						17
+#define GCC_GP1_CLK_SRC						18
+#define GCC_GP2_CLK						19
+#define GCC_GP2_CLK_SRC						20
+#define GCC_GP3_CLK						21
+#define GCC_GP3_CLK_SRC						22
+#define GCC_GPLL0						23
+#define GCC_GPLL0_OUT_EVEN					24
+#define GCC_GPLL1						25
+#define GCC_GPLL3						26
+#define GCC_GPLL4						27
+#define GCC_GPLL6						28
+#define GCC_GPLL7						29
+#define GCC_GPLL9						30
+#define GCC_GPU_CFG_AHB_CLK					31
+#define GCC_GPU_GPLL0_CLK_SRC					32
+#define GCC_GPU_GPLL0_DIV_CLK_SRC				33
+#define GCC_GPU_MEMNOC_GFX_CLK					34
+#define GCC_GPU_SNOC_DVM_GFX_CLK				35
+#define GCC_PCIE_0_AUX_CLK					36
+#define GCC_PCIE_0_AUX_CLK_SRC					37
+#define GCC_PCIE_0_CFG_AHB_CLK					38
+#define GCC_PCIE_0_MSTR_AXI_CLK					39
+#define GCC_PCIE_0_PHY_RCHNG_CLK				40
+#define GCC_PCIE_0_PHY_RCHNG_CLK_SRC				41
+#define GCC_PCIE_0_PIPE_CLK					42
+#define GCC_PCIE_0_PIPE_CLK_SRC					43
+#define GCC_PCIE_0_SLV_AXI_CLK					44
+#define GCC_PCIE_0_SLV_Q2A_AXI_CLK				45
+#define GCC_PCIE_1_AUX_CLK					46
+#define GCC_PCIE_1_AUX_CLK_SRC					47
+#define GCC_PCIE_1_CFG_AHB_CLK					48
+#define GCC_PCIE_1_MSTR_AXI_CLK					49
+#define GCC_PCIE_1_PHY_AUX_CLK					50
+#define GCC_PCIE_1_PHY_AUX_CLK_SRC				51
+#define GCC_PCIE_1_PHY_RCHNG_CLK				52
+#define GCC_PCIE_1_PHY_RCHNG_CLK_SRC				53
+#define GCC_PCIE_1_PIPE_CLK					54
+#define GCC_PCIE_1_PIPE_CLK_SRC					55
+#define GCC_PCIE_1_SLV_AXI_CLK					56
+#define GCC_PCIE_1_SLV_Q2A_AXI_CLK				57
+#define GCC_PDM2_CLK						58
+#define GCC_PDM2_CLK_SRC					59
+#define GCC_PDM_AHB_CLK						60
+#define GCC_PDM_XO4_CLK						61
+#define GCC_QMIP_CAMERA_NRT_AHB_CLK				62
+#define GCC_QMIP_CAMERA_RT_AHB_CLK				63
+#define GCC_QMIP_DISP_AHB_CLK					64
+#define GCC_QMIP_GPU_AHB_CLK					65
+#define GCC_QMIP_PCIE_AHB_CLK					66
+#define GCC_QMIP_VIDEO_CV_CPU_AHB_CLK				67
+#define GCC_QMIP_VIDEO_CVP_AHB_CLK				68
+#define GCC_QMIP_VIDEO_V_CPU_AHB_CLK				69
+#define GCC_QMIP_VIDEO_VCODEC_AHB_CLK				70
+#define GCC_QUPV3_I2C_CORE_CLK					71
+#define GCC_QUPV3_I2C_S0_CLK					72
+#define GCC_QUPV3_I2C_S0_CLK_SRC				73
+#define GCC_QUPV3_I2C_S1_CLK					74
+#define GCC_QUPV3_I2C_S1_CLK_SRC				75
+#define GCC_QUPV3_I2C_S2_CLK					76
+#define GCC_QUPV3_I2C_S2_CLK_SRC				77
+#define GCC_QUPV3_I2C_S3_CLK					78
+#define GCC_QUPV3_I2C_S3_CLK_SRC				79
+#define GCC_QUPV3_I2C_S4_CLK					80
+#define GCC_QUPV3_I2C_S4_CLK_SRC				81
+#define GCC_QUPV3_I2C_S5_CLK					82
+#define GCC_QUPV3_I2C_S5_CLK_SRC				83
+#define GCC_QUPV3_I2C_S6_CLK					84
+#define GCC_QUPV3_I2C_S6_CLK_SRC				85
+#define GCC_QUPV3_I2C_S7_CLK					86
+#define GCC_QUPV3_I2C_S7_CLK_SRC				87
+#define GCC_QUPV3_I2C_S8_CLK					88
+#define GCC_QUPV3_I2C_S8_CLK_SRC				89
+#define GCC_QUPV3_I2C_S9_CLK					90
+#define GCC_QUPV3_I2C_S9_CLK_SRC				91
+#define GCC_QUPV3_I2C_S_AHB_CLK					92
+#define GCC_QUPV3_WRAP1_CORE_2X_CLK				93
+#define GCC_QUPV3_WRAP1_CORE_CLK				94
+#define GCC_QUPV3_WRAP1_QSPI_REF_CLK				95
+#define GCC_QUPV3_WRAP1_QSPI_REF_CLK_SRC			96
+#define GCC_QUPV3_WRAP1_S0_CLK					97
+#define GCC_QUPV3_WRAP1_S0_CLK_SRC				98
+#define GCC_QUPV3_WRAP1_S1_CLK					99
+#define GCC_QUPV3_WRAP1_S1_CLK_SRC				100
+#define GCC_QUPV3_WRAP1_S2_CLK					101
+#define GCC_QUPV3_WRAP1_S2_CLK_SRC				102
+#define GCC_QUPV3_WRAP1_S3_CLK					103
+#define GCC_QUPV3_WRAP1_S3_CLK_SRC				104
+#define GCC_QUPV3_WRAP1_S4_CLK					105
+#define GCC_QUPV3_WRAP1_S4_CLK_SRC				106
+#define GCC_QUPV3_WRAP1_S5_CLK					107
+#define GCC_QUPV3_WRAP1_S5_CLK_SRC				108
+#define GCC_QUPV3_WRAP1_S6_CLK					109
+#define GCC_QUPV3_WRAP1_S6_CLK_SRC				110
+#define GCC_QUPV3_WRAP1_S7_CLK					111
+#define GCC_QUPV3_WRAP1_S7_CLK_SRC				112
+#define GCC_QUPV3_WRAP2_CORE_2X_CLK				113
+#define GCC_QUPV3_WRAP2_CORE_CLK				114
+#define GCC_QUPV3_WRAP2_IBI_CTRL_0_CLK_SRC			115
+#define GCC_QUPV3_WRAP2_IBI_CTRL_2_CLK				116
+#define GCC_QUPV3_WRAP2_IBI_CTRL_3_CLK				117
+#define GCC_QUPV3_WRAP2_S0_CLK					118
+#define GCC_QUPV3_WRAP2_S0_CLK_SRC				119
+#define GCC_QUPV3_WRAP2_S1_CLK					120
+#define GCC_QUPV3_WRAP2_S1_CLK_SRC				121
+#define GCC_QUPV3_WRAP2_S2_CLK					122
+#define GCC_QUPV3_WRAP2_S2_CLK_SRC				123
+#define GCC_QUPV3_WRAP2_S3_CLK					124
+#define GCC_QUPV3_WRAP2_S3_CLK_SRC				125
+#define GCC_QUPV3_WRAP2_S4_CLK					126
+#define GCC_QUPV3_WRAP2_S4_CLK_SRC				127
+#define GCC_QUPV3_WRAP2_S5_CLK					128
+#define GCC_QUPV3_WRAP2_S5_CLK_SRC				129
+#define GCC_QUPV3_WRAP2_S6_CLK					130
+#define GCC_QUPV3_WRAP2_S6_CLK_SRC				131
+#define GCC_QUPV3_WRAP2_S7_CLK					132
+#define GCC_QUPV3_WRAP2_S7_CLK_SRC				133
+#define GCC_QUPV3_WRAP3_CORE_2X_CLK				134
+#define GCC_QUPV3_WRAP3_CORE_CLK				135
+#define GCC_QUPV3_WRAP3_QSPI_REF_CLK				136
+#define GCC_QUPV3_WRAP3_QSPI_REF_CLK_SRC			137
+#define GCC_QUPV3_WRAP3_S0_CLK					138
+#define GCC_QUPV3_WRAP3_S0_CLK_SRC				139
+#define GCC_QUPV3_WRAP_1_M_AHB_CLK				140
+#define GCC_QUPV3_WRAP_1_S_AHB_CLK				141
+#define GCC_QUPV3_WRAP_2_IBI_2_AHB_CLK				142
+#define GCC_QUPV3_WRAP_2_IBI_3_AHB_CLK				143
+#define GCC_QUPV3_WRAP_2_M_AHB_CLK				144
+#define GCC_QUPV3_WRAP_2_S_AHB_CLK				145
+#define GCC_QUPV3_WRAP_3_M_AHB_CLK				146
+#define GCC_QUPV3_WRAP_3_S_AHB_CLK				147
+#define GCC_SDCC2_AHB_CLK					148
+#define GCC_SDCC2_APPS_CLK					149
+#define GCC_SDCC2_APPS_CLK_SRC					150
+#define GCC_SDCC4_AHB_CLK					151
+#define GCC_SDCC4_APPS_CLK					152
+#define GCC_SDCC4_APPS_CLK_SRC					153
+#define GCC_UFS_PHY_AHB_CLK					154
+#define GCC_UFS_PHY_AXI_CLK					155
+#define GCC_UFS_PHY_AXI_CLK_SRC					156
+#define GCC_UFS_PHY_AXI_HW_CTL_CLK				157
+#define GCC_UFS_PHY_ICE_CORE_CLK				158
+#define GCC_UFS_PHY_ICE_CORE_CLK_SRC				159
+#define GCC_UFS_PHY_ICE_CORE_HW_CTL_CLK				160
+#define GCC_UFS_PHY_PHY_AUX_CLK					161
+#define GCC_UFS_PHY_PHY_AUX_CLK_SRC				162
+#define GCC_UFS_PHY_PHY_AUX_HW_CTL_CLK				163
+#define GCC_UFS_PHY_RX_SYMBOL_0_CLK				164
+#define GCC_UFS_PHY_RX_SYMBOL_0_CLK_SRC				165
+#define GCC_UFS_PHY_RX_SYMBOL_1_CLK				166
+#define GCC_UFS_PHY_RX_SYMBOL_1_CLK_SRC				167
+#define GCC_UFS_PHY_TX_SYMBOL_0_CLK				168
+#define GCC_UFS_PHY_TX_SYMBOL_0_CLK_SRC				169
+#define GCC_UFS_PHY_UNIPRO_CORE_CLK				170
+#define GCC_UFS_PHY_UNIPRO_CORE_CLK_SRC				171
+#define GCC_UFS_PHY_UNIPRO_CORE_HW_CTL_CLK			172
+#define GCC_USB30_PRIM_MASTER_CLK				173
+#define GCC_USB30_PRIM_MASTER_CLK_SRC				174
+#define GCC_USB30_PRIM_MOCK_UTMI_CLK				175
+#define GCC_USB30_PRIM_MOCK_UTMI_CLK_SRC			176
+#define GCC_USB30_PRIM_MOCK_UTMI_POSTDIV_CLK_SRC		177
+#define GCC_USB30_PRIM_SLEEP_CLK				178
+#define GCC_USB3_PRIM_PHY_AUX_CLK				179
+#define GCC_USB3_PRIM_PHY_AUX_CLK_SRC				180
+#define GCC_USB3_PRIM_PHY_COM_AUX_CLK				181
+#define GCC_USB3_PRIM_PHY_PIPE_CLK				182
+#define GCC_USB3_PRIM_PHY_PIPE_CLK_SRC				183
+#define GCC_VIDEO_AHB_CLK					184
+#define GCC_VIDEO_AXI0_CLK					185
+#define GCC_VIDEO_AXI1_CLK					186
+#define GCC_VIDEO_XO_CLK					187
+#define GCC_GPLL0_AO						188
+#define GCC_GPLL0_OUT_EVEN_AO					189
+#define GCC_GPLL1_AO						190
+#define GCC_GPLL3_AO						191
+#define GCC_GPLL4_AO						192
+#define GCC_GPLL6_AO						193
+
+/* GCC resets */
+#define GCC_CAMERA_BCR						0
+#define GCC_DISPLAY_BCR						1
+#define GCC_GPU_BCR						2
+#define GCC_PCIE_0_BCR						3
+#define GCC_PCIE_0_LINK_DOWN_BCR				4
+#define GCC_PCIE_0_NOCSR_COM_PHY_BCR				5
+#define GCC_PCIE_0_PHY_BCR					6
+#define GCC_PCIE_0_PHY_NOCSR_COM_PHY_BCR			7
+#define GCC_PCIE_1_BCR						8
+#define GCC_PCIE_1_LINK_DOWN_BCR				9
+#define GCC_PCIE_1_NOCSR_COM_PHY_BCR				10
+#define GCC_PCIE_1_PHY_BCR					11
+#define GCC_PCIE_1_PHY_NOCSR_COM_PHY_BCR			12
+#define GCC_PCIE_PHY_BCR					13
+#define GCC_PCIE_PHY_CFG_AHB_BCR				14
+#define GCC_PCIE_PHY_COM_BCR					15
+#define GCC_PDM_BCR						16
+#define GCC_QUPV3_WRAPPER_1_BCR					17
+#define GCC_QUPV3_WRAPPER_2_BCR					18
+#define GCC_QUPV3_WRAPPER_3_BCR					19
+#define GCC_QUPV3_WRAPPER_I2C_BCR				20
+#define GCC_QUSB2PHY_PRIM_BCR					21
+#define GCC_QUSB2PHY_SEC_BCR					22
+#define GCC_SDCC2_BCR						23
+#define GCC_SDCC4_BCR						24
+#define GCC_UFS_PHY_BCR						25
+#define GCC_USB30_PRIM_BCR					26
+#define GCC_USB3_DP_PHY_PRIM_BCR				27
+#define GCC_USB3_DP_PHY_SEC_BCR					28
+#define GCC_USB3_PHY_PRIM_BCR					29
+#define GCC_USB3_PHY_SEC_BCR					30
+#define GCC_USB3PHY_PHY_PRIM_BCR				31
+#define GCC_USB3PHY_PHY_SEC_BCR					32
+#define GCC_VIDEO_AXI0_CLK_ARES					33
+#define GCC_VIDEO_AXI1_CLK_ARES					34
+#define GCC_VIDEO_BCR						35
+
+/* GCC power domains */
+#define PCIE_0_GDSC						0
+#define PCIE_0_PHY_GDSC						1
+#define PCIE_1_GDSC						2
+#define PCIE_1_PHY_GDSC						3
+#define UFS_PHY_GDSC						4
+#define UFS_MEM_PHY_GDSC					5
+#define USB30_PRIM_GDSC						6
+#define USB3_PHY_GDSC						7
+
+#endif
-- 
cgit v1.2.3


From c1120359d4c2a1050e6a5bddd47ee1887bb0c713 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Mon, 6 Nov 2023 09:25:56 +0100
Subject: dt-bindings: clock: qcom: document the SM8650 Display Clock
 Controller

Add bindings documentation for the SM8650 Display Clock Controller.

Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20231106-topic-sm8650-upstream-clocks-v3-3-761a6fadb4c0@linaro.org
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 .../bindings/clock/qcom,sm8650-dispcc.yaml         | 106 +++++++++++++++++++++
 include/dt-bindings/clock/qcom,sm8650-dispcc.h     | 102 ++++++++++++++++++++
 2 files changed, 208 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/clock/qcom,sm8650-dispcc.yaml
 create mode 100644 include/dt-bindings/clock/qcom,sm8650-dispcc.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/clock/qcom,sm8650-dispcc.yaml b/Documentation/devicetree/bindings/clock/qcom,sm8650-dispcc.yaml
new file mode 100644
index 000000000000..5e0c45c380f5
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/qcom,sm8650-dispcc.yaml
@@ -0,0 +1,106 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/qcom,sm8650-dispcc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm Display Clock & Reset Controller for SM8650
+
+maintainers:
+  - Bjorn Andersson <andersson@kernel.org>
+  - Neil Armstrong <neil.armstrong@linaro.org>
+
+description: |
+  Qualcomm display clock control module provides the clocks, resets and power
+  domains on SM8650.
+
+  See also:: include/dt-bindings/clock/qcom,sm8650-dispcc.h
+
+properties:
+  compatible:
+    enum:
+      - qcom,sm8650-dispcc
+
+  clocks:
+    items:
+      - description: Board XO source
+      - description: Board Always On XO source
+      - description: Display's AHB clock
+      - description: sleep clock
+      - description: Byte clock from DSI PHY0
+      - description: Pixel clock from DSI PHY0
+      - description: Byte clock from DSI PHY1
+      - description: Pixel clock from DSI PHY1
+      - description: Link clock from DP PHY0
+      - description: VCO DIV clock from DP PHY0
+      - description: Link clock from DP PHY1
+      - description: VCO DIV clock from DP PHY1
+      - description: Link clock from DP PHY2
+      - description: VCO DIV clock from DP PHY2
+      - description: Link clock from DP PHY3
+      - description: VCO DIV clock from DP PHY3
+
+  '#clock-cells':
+    const: 1
+
+  '#reset-cells':
+    const: 1
+
+  '#power-domain-cells':
+    const: 1
+
+  reg:
+    maxItems: 1
+
+  power-domains:
+    description:
+      A phandle and PM domain specifier for the MMCX power domain.
+    maxItems: 1
+
+  required-opps:
+    description:
+      A phandle to an OPP node describing required MMCX performance point.
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - '#clock-cells'
+  - '#reset-cells'
+  - '#power-domain-cells'
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/qcom,sm8650-gcc.h>
+    #include <dt-bindings/clock/qcom,rpmh.h>
+    #include <dt-bindings/power/qcom-rpmpd.h>
+    #include <dt-bindings/power/qcom,rpmhpd.h>
+    clock-controller@af00000 {
+      compatible = "qcom,sm8650-dispcc";
+      reg = <0x0af00000 0x10000>;
+      clocks = <&rpmhcc RPMH_CXO_CLK>,
+               <&rpmhcc RPMH_CXO_CLK_A>,
+               <&gcc GCC_DISP_AHB_CLK>,
+               <&sleep_clk>,
+               <&dsi0_phy 0>,
+               <&dsi0_phy 1>,
+               <&dsi1_phy 0>,
+               <&dsi1_phy 1>,
+               <&dp0_phy 0>,
+               <&dp0_phy 1>,
+               <&dp1_phy 0>,
+               <&dp1_phy 1>,
+               <&dp2_phy 0>,
+               <&dp2_phy 1>,
+               <&dp3_phy 0>,
+               <&dp3_phy 1>;
+      #clock-cells = <1>;
+      #reset-cells = <1>;
+      #power-domain-cells = <1>;
+      power-domains = <&rpmhpd RPMHPD_MMCX>;
+      required-opps = <&rpmhpd_opp_low_svs>;
+    };
+...
diff --git a/include/dt-bindings/clock/qcom,sm8650-dispcc.h b/include/dt-bindings/clock/qcom,sm8650-dispcc.h
new file mode 100644
index 000000000000..b0a668b395a5
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,sm8650-dispcc.h
@@ -0,0 +1,102 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/*
+ * Copyright (c) 2022, Qualcomm Innovation Center, Inc. All rights reserved
+ * Copyright (c) 2023, Linaro Ltd.
+ */
+
+#ifndef _DT_BINDINGS_CLK_QCOM_SM8650_DISP_CC_H
+#define _DT_BINDINGS_CLK_QCOM_SM8650_DISP_CC_H
+
+/* DISP_CC clocks */
+#define DISP_CC_MDSS_ACCU_CLK					0
+#define DISP_CC_MDSS_AHB1_CLK					1
+#define DISP_CC_MDSS_AHB_CLK					2
+#define DISP_CC_MDSS_AHB_CLK_SRC				3
+#define DISP_CC_MDSS_BYTE0_CLK					4
+#define DISP_CC_MDSS_BYTE0_CLK_SRC				5
+#define DISP_CC_MDSS_BYTE0_DIV_CLK_SRC				6
+#define DISP_CC_MDSS_BYTE0_INTF_CLK				7
+#define DISP_CC_MDSS_BYTE1_CLK					8
+#define DISP_CC_MDSS_BYTE1_CLK_SRC				9
+#define DISP_CC_MDSS_BYTE1_DIV_CLK_SRC				10
+#define DISP_CC_MDSS_BYTE1_INTF_CLK				11
+#define DISP_CC_MDSS_DPTX0_AUX_CLK				12
+#define DISP_CC_MDSS_DPTX0_AUX_CLK_SRC				13
+#define DISP_CC_MDSS_DPTX0_CRYPTO_CLK				14
+#define DISP_CC_MDSS_DPTX0_LINK_CLK				15
+#define DISP_CC_MDSS_DPTX0_LINK_CLK_SRC				16
+#define DISP_CC_MDSS_DPTX0_LINK_DIV_CLK_SRC			17
+#define DISP_CC_MDSS_DPTX0_LINK_INTF_CLK			18
+#define DISP_CC_MDSS_DPTX0_PIXEL0_CLK				19
+#define DISP_CC_MDSS_DPTX0_PIXEL0_CLK_SRC			20
+#define DISP_CC_MDSS_DPTX0_PIXEL1_CLK				21
+#define DISP_CC_MDSS_DPTX0_PIXEL1_CLK_SRC			22
+#define DISP_CC_MDSS_DPTX0_USB_ROUTER_LINK_INTF_CLK		23
+#define DISP_CC_MDSS_DPTX1_AUX_CLK				24
+#define DISP_CC_MDSS_DPTX1_AUX_CLK_SRC				25
+#define DISP_CC_MDSS_DPTX1_CRYPTO_CLK				26
+#define DISP_CC_MDSS_DPTX1_LINK_CLK				27
+#define DISP_CC_MDSS_DPTX1_LINK_CLK_SRC				28
+#define DISP_CC_MDSS_DPTX1_LINK_DIV_CLK_SRC			29
+#define DISP_CC_MDSS_DPTX1_LINK_INTF_CLK			30
+#define DISP_CC_MDSS_DPTX1_PIXEL0_CLK				31
+#define DISP_CC_MDSS_DPTX1_PIXEL0_CLK_SRC			32
+#define DISP_CC_MDSS_DPTX1_PIXEL1_CLK				33
+#define DISP_CC_MDSS_DPTX1_PIXEL1_CLK_SRC			34
+#define DISP_CC_MDSS_DPTX1_USB_ROUTER_LINK_INTF_CLK		35
+#define DISP_CC_MDSS_DPTX2_AUX_CLK				36
+#define DISP_CC_MDSS_DPTX2_AUX_CLK_SRC				37
+#define DISP_CC_MDSS_DPTX2_CRYPTO_CLK				38
+#define DISP_CC_MDSS_DPTX2_LINK_CLK				39
+#define DISP_CC_MDSS_DPTX2_LINK_CLK_SRC				40
+#define DISP_CC_MDSS_DPTX2_LINK_DIV_CLK_SRC			41
+#define DISP_CC_MDSS_DPTX2_LINK_INTF_CLK			42
+#define DISP_CC_MDSS_DPTX2_PIXEL0_CLK				43
+#define DISP_CC_MDSS_DPTX2_PIXEL0_CLK_SRC			44
+#define DISP_CC_MDSS_DPTX2_PIXEL1_CLK				45
+#define DISP_CC_MDSS_DPTX2_PIXEL1_CLK_SRC			46
+#define DISP_CC_MDSS_DPTX3_AUX_CLK				47
+#define DISP_CC_MDSS_DPTX3_AUX_CLK_SRC				48
+#define DISP_CC_MDSS_DPTX3_CRYPTO_CLK				49
+#define DISP_CC_MDSS_DPTX3_LINK_CLK				50
+#define DISP_CC_MDSS_DPTX3_LINK_CLK_SRC				51
+#define DISP_CC_MDSS_DPTX3_LINK_DIV_CLK_SRC			52
+#define DISP_CC_MDSS_DPTX3_LINK_INTF_CLK			53
+#define DISP_CC_MDSS_DPTX3_PIXEL0_CLK				54
+#define DISP_CC_MDSS_DPTX3_PIXEL0_CLK_SRC			55
+#define DISP_CC_MDSS_ESC0_CLK					56
+#define DISP_CC_MDSS_ESC0_CLK_SRC				57
+#define DISP_CC_MDSS_ESC1_CLK					58
+#define DISP_CC_MDSS_ESC1_CLK_SRC				59
+#define DISP_CC_MDSS_MDP1_CLK					60
+#define DISP_CC_MDSS_MDP_CLK					61
+#define DISP_CC_MDSS_MDP_CLK_SRC				62
+#define DISP_CC_MDSS_MDP_LUT1_CLK				63
+#define DISP_CC_MDSS_MDP_LUT_CLK				64
+#define DISP_CC_MDSS_NON_GDSC_AHB_CLK				65
+#define DISP_CC_MDSS_PCLK0_CLK					66
+#define DISP_CC_MDSS_PCLK0_CLK_SRC				67
+#define DISP_CC_MDSS_PCLK1_CLK					68
+#define DISP_CC_MDSS_PCLK1_CLK_SRC				69
+#define DISP_CC_MDSS_RSCC_AHB_CLK				70
+#define DISP_CC_MDSS_RSCC_VSYNC_CLK				71
+#define DISP_CC_MDSS_VSYNC1_CLK					72
+#define DISP_CC_MDSS_VSYNC_CLK					73
+#define DISP_CC_MDSS_VSYNC_CLK_SRC				74
+#define DISP_CC_PLL0						75
+#define DISP_CC_PLL1						76
+#define DISP_CC_SLEEP_CLK					77
+#define DISP_CC_SLEEP_CLK_SRC					78
+#define DISP_CC_XO_CLK						79
+#define DISP_CC_XO_CLK_SRC					80
+
+/* DISP_CC resets */
+#define DISP_CC_MDSS_CORE_BCR					0
+#define DISP_CC_MDSS_CORE_INT2_BCR				1
+#define DISP_CC_MDSS_RSCC_BCR					2
+
+/* DISP_CC GDSCR */
+#define MDSS_GDSC						0
+#define MDSS_INT2_GDSC						1
+
+#endif
-- 
cgit v1.2.3


From a0aa7fa5c3f0e74e684c667e26824fe1e28f5c27 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Mon, 6 Nov 2023 09:25:57 +0100
Subject: dt-bindings: clock: qcom: document the SM8650 GPU Clock Controller

Add bindings documentation for the SM8650 Graphics Clock Controller.

Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20231106-topic-sm8650-upstream-clocks-v3-4-761a6fadb4c0@linaro.org
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 .../bindings/clock/qcom,sm8450-gpucc.yaml          |  2 +
 include/dt-bindings/clock/qcom,sm8650-gpucc.h      | 43 ++++++++++++++++++++++
 include/dt-bindings/reset/qcom,sm8650-gpucc.h      | 20 ++++++++++
 3 files changed, 65 insertions(+)
 create mode 100644 include/dt-bindings/clock/qcom,sm8650-gpucc.h
 create mode 100644 include/dt-bindings/reset/qcom,sm8650-gpucc.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/clock/qcom,sm8450-gpucc.yaml b/Documentation/devicetree/bindings/clock/qcom,sm8450-gpucc.yaml
index 2320be920a5f..1a384e8532a5 100644
--- a/Documentation/devicetree/bindings/clock/qcom,sm8450-gpucc.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,sm8450-gpucc.yaml
@@ -17,12 +17,14 @@ description: |
     include/dt-bindings/clock/qcom,sm8450-gpucc.h
     include/dt-bindings/clock/qcom,sm8550-gpucc.h
     include/dt-bindings/reset/qcom,sm8450-gpucc.h
+    include/dt-bindings/reset/qcom,sm8650-gpucc.h
 
 properties:
   compatible:
     enum:
       - qcom,sm8450-gpucc
       - qcom,sm8550-gpucc
+      - qcom,sm8650-gpucc
 
   clocks:
     items:
diff --git a/include/dt-bindings/clock/qcom,sm8650-gpucc.h b/include/dt-bindings/clock/qcom,sm8650-gpucc.h
new file mode 100644
index 000000000000..d0dc457cfe75
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,sm8650-gpucc.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/*
+ * Copyright (c) 2022, Qualcomm Innovation Center, Inc. All rights reserved
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#ifndef _DT_BINDINGS_CLK_QCOM_GPU_CC_SM8650_H
+#define _DT_BINDINGS_CLK_QCOM_GPU_CC_SM8650_H
+
+/* GPU_CC clocks */
+#define GPU_CC_AHB_CLK				0
+#define GPU_CC_CRC_AHB_CLK			1
+#define GPU_CC_CX_ACCU_SHIFT_CLK		2
+#define GPU_CC_CX_FF_CLK			3
+#define GPU_CC_CX_GMU_CLK			4
+#define GPU_CC_CXO_AON_CLK			5
+#define GPU_CC_CXO_CLK				6
+#define GPU_CC_DEMET_CLK			7
+#define GPU_CC_DPM_CLK				8
+#define GPU_CC_FF_CLK_SRC			9
+#define GPU_CC_FREQ_MEASURE_CLK			10
+#define GPU_CC_GMU_CLK_SRC			11
+#define GPU_CC_GX_ACCU_SHIFT_CLK		12
+#define GPU_CC_GX_FF_CLK			13
+#define GPU_CC_GX_GFX3D_CLK			14
+#define GPU_CC_GX_GFX3D_RDVM_CLK		15
+#define GPU_CC_GX_GMU_CLK			16
+#define GPU_CC_GX_VSENSE_CLK			17
+#define GPU_CC_HLOS1_VOTE_GPU_SMMU_CLK		18
+#define GPU_CC_HUB_AON_CLK			19
+#define GPU_CC_HUB_CLK_SRC			20
+#define GPU_CC_HUB_CX_INT_CLK			21
+#define GPU_CC_HUB_DIV_CLK_SRC			22
+#define GPU_CC_MEMNOC_GFX_CLK			23
+#define GPU_CC_PLL0				24
+#define GPU_CC_PLL1				25
+#define GPU_CC_SLEEP_CLK			26
+
+/* GDSCs */
+#define GPU_GX_GDSC				0
+#define GPU_CX_GDSC				1
+
+#endif
diff --git a/include/dt-bindings/reset/qcom,sm8650-gpucc.h b/include/dt-bindings/reset/qcom,sm8650-gpucc.h
new file mode 100644
index 000000000000..f021a6cccc66
--- /dev/null
+++ b/include/dt-bindings/reset/qcom,sm8650-gpucc.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/*
+ * Copyright (c) 2019, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+#ifndef _DT_BINDINGS_RESET_QCOM_GPU_CC_SM8650_H
+#define _DT_BINDINGS_RESET_QCOM_GPU_CC_SM8650_H
+
+#define GPUCC_GPU_CC_ACD_BCR			0
+#define GPUCC_GPU_CC_CX_BCR			1
+#define GPUCC_GPU_CC_FAST_HUB_BCR		2
+#define GPUCC_GPU_CC_FF_BCR			3
+#define GPUCC_GPU_CC_GFX3D_AON_BCR		4
+#define GPUCC_GPU_CC_GMU_BCR			5
+#define GPUCC_GPU_CC_GX_BCR			6
+#define GPUCC_GPU_CC_XO_BCR			7
+#define GPUCC_GPU_CC_GX_ACD_IROOT_BCR		8
+
+#endif
-- 
cgit v1.2.3


From 4d8ff6b0991d5e86b17b235fc46ec62e9195cb9b Mon Sep 17 00:00:00 2001
From: Amit Kumar Mahapatra <amit.kumar-mahapatra@amd.com>
Date: Sat, 25 Nov 2023 14:51:30 +0530
Subject: spi: Add multi-cs memories support in SPI core

AMD-Xilinx GQSPI controller has two advanced mode that allows the
controller to consider two flashes as one single device.

One of these two mode is the parallel mode in which each byte of data is
stored in both devices, the even bits in the lower flash & the odd bits in
the upper flash. The byte split is automatically handled by the QSPI
controller.

The other mode is the stacked mode in which both the flashes share the
same SPI bus but each of the device contain half of the data. In this mode,
the controller does not follow CS requests but instead internally wires the
two CS levels with the value of the most significant address bit.

For supporting both these modes SPI core need to be updated for providing
multiple CS for a single SPI device.

For adding multi CS support the SPI device need to be aware of all the CS
values. So, the "chip_select" member in the spi_device structure is now an
array that holds all the CS values.

spi_device structure now has a "cs_index_mask" member. This acts as an
index to the chip_select array. If nth bit of spi->cs_index_mask is set
then the driver would assert spi->chip_select[n].

In parallel mode all the chip selects are asserted/de-asserted
simultaneously and each byte of data is stored in both devices, the even
bits in one, the odd bits in the other. The split is automatically handled
by the GQSPI controller. The GQSPI controller supports a maximum of two
flashes connected in parallel mode. A SPI_CONTROLLER_MULTI_CS flag bit is
added in the spi controller flags, through ctlr->flags the spi core
will make sure that the controller is capable of handling multiple chip
selects at once.

For supporting multiple CS via GPIO the cs_gpiod member of the spi_device
structure is now an array that holds the gpio descriptor for each
chipselect.

CS GPIO is not tested on our hardware, but it has been tested by @Stefan
https://lore.kernel.org/all/005001da1efc$619ad5a0$24d080e0$@opensource.cirrus.com/

Signed-off-by: Amit Kumar Mahapatra <amit.kumar-mahapatra@amd.com>
Tested-by: Stefan Binding <sbinding@opensource.cirrus.com>
Link: https://lore.kernel.org/r/20231125092137.2948-4-amit.kumar-mahapatra@amd.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi.c       | 259 ++++++++++++++++++++++++++++++++++++++++--------
 include/linux/spi/spi.h |  51 ++++++++--
 2 files changed, 258 insertions(+), 52 deletions(-)

(limited to 'include')

diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 8ead7acb99f3..45b6898cf0ee 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -612,10 +612,21 @@ static int spi_dev_check(struct device *dev, void *data)
 {
 	struct spi_device *spi = to_spi_device(dev);
 	struct spi_device *new_spi = data;
-
-	if (spi->controller == new_spi->controller &&
-	    spi_get_chipselect(spi, 0) == spi_get_chipselect(new_spi, 0))
-		return -EBUSY;
+	int idx, nw_idx;
+	u8 cs, cs_nw;
+
+	if (spi->controller == new_spi->controller) {
+		for (idx = 0; idx < SPI_CS_CNT_MAX; idx++) {
+			cs = spi_get_chipselect(spi, idx);
+			for (nw_idx = 0; nw_idx < SPI_CS_CNT_MAX; nw_idx++) {
+				cs_nw = spi_get_chipselect(new_spi, nw_idx);
+				if (cs != 0xFF && cs_nw != 0xFF && cs == cs_nw) {
+					dev_err(dev, "chipselect %d already in use\n", cs_nw);
+					return -EBUSY;
+				}
+			}
+		}
+	}
 	return 0;
 }
 
@@ -629,13 +640,32 @@ static int __spi_add_device(struct spi_device *spi)
 {
 	struct spi_controller *ctlr = spi->controller;
 	struct device *dev = ctlr->dev.parent;
-	int status;
+	int status, idx, nw_idx;
+	u8 cs, nw_cs;
+
+	for (idx = 0; idx < SPI_CS_CNT_MAX; idx++) {
+		/* Chipselects are numbered 0..max; validate. */
+		cs = spi_get_chipselect(spi, idx);
+		if (cs != 0xFF && cs >= ctlr->num_chipselect) {
+			dev_err(dev, "cs%d >= max %d\n", spi_get_chipselect(spi, idx),
+				ctlr->num_chipselect);
+			return -EINVAL;
+		}
+	}
 
-	/* Chipselects are numbered 0..max; validate. */
-	if (spi_get_chipselect(spi, 0) >= ctlr->num_chipselect) {
-		dev_err(dev, "cs%d >= max %d\n", spi_get_chipselect(spi, 0),
-			ctlr->num_chipselect);
-		return -EINVAL;
+	/*
+	 * Make sure that multiple logical CS doesn't map to the same physical CS.
+	 * For example, spi->chip_select[0] != spi->chip_select[1] and so on.
+	 */
+	for (idx = 0; idx < SPI_CS_CNT_MAX; idx++) {
+		cs = spi_get_chipselect(spi, idx);
+		for (nw_idx = idx + 1; nw_idx < SPI_CS_CNT_MAX; nw_idx++) {
+			nw_cs = spi_get_chipselect(spi, nw_idx);
+			if (cs != 0xFF && nw_cs != 0xFF && cs == nw_cs) {
+				dev_err(dev, "chipselect %d already in use\n", nw_cs);
+				return -EBUSY;
+			}
+		}
 	}
 
 	/* Set the bus ID string */
@@ -647,11 +677,8 @@ static int __spi_add_device(struct spi_device *spi)
 	 * its configuration.
 	 */
 	status = bus_for_each_dev(&spi_bus_type, NULL, spi, spi_dev_check);
-	if (status) {
-		dev_err(dev, "chipselect %d already in use\n",
-				spi_get_chipselect(spi, 0));
+	if (status)
 		return status;
-	}
 
 	/* Controller may unregister concurrently */
 	if (IS_ENABLED(CONFIG_SPI_DYNAMIC) &&
@@ -659,8 +686,15 @@ static int __spi_add_device(struct spi_device *spi)
 		return -ENODEV;
 	}
 
-	if (ctlr->cs_gpiods)
-		spi_set_csgpiod(spi, 0, ctlr->cs_gpiods[spi_get_chipselect(spi, 0)]);
+	if (ctlr->cs_gpiods) {
+		u8 cs;
+
+		for (idx = 0; idx < SPI_CS_CNT_MAX; idx++) {
+			cs = spi_get_chipselect(spi, idx);
+			if (cs != 0xFF)
+				spi_set_csgpiod(spi, idx, ctlr->cs_gpiods[cs]);
+		}
+	}
 
 	/*
 	 * Drivers may modify this initial i/o setup, but will
@@ -701,6 +735,9 @@ int spi_add_device(struct spi_device *spi)
 	struct spi_controller *ctlr = spi->controller;
 	int status;
 
+	/* Set the bus ID string */
+	spi_dev_set_name(spi);
+
 	mutex_lock(&ctlr->add_lock);
 	status = __spi_add_device(spi);
 	mutex_unlock(&ctlr->add_lock);
@@ -727,6 +764,7 @@ struct spi_device *spi_new_device(struct spi_controller *ctlr,
 {
 	struct spi_device	*proxy;
 	int			status;
+	u8                      idx;
 
 	/*
 	 * NOTE:  caller did any chip->bus_num checks necessary.
@@ -742,6 +780,18 @@ struct spi_device *spi_new_device(struct spi_controller *ctlr,
 
 	WARN_ON(strlen(chip->modalias) >= sizeof(proxy->modalias));
 
+	/*
+	 * Zero(0) is a valid physical CS value and can be located at any
+	 * logical CS in the spi->chip_select[]. If all the physical CS
+	 * are initialized to 0 then It would be difficult to differentiate
+	 * between a valid physical CS 0 & an unused logical CS whose physical
+	 * CS can be 0. As a solution to this issue initialize all the CS to 0xFF.
+	 * Now all the unused logical CS will have 0xFF physical CS value & can be
+	 * ignore while performing physical CS validity checks.
+	 */
+	for (idx = 0; idx < SPI_CS_CNT_MAX; idx++)
+		spi_set_chipselect(proxy, idx, 0xFF);
+
 	spi_set_chipselect(proxy, 0, chip->chip_select);
 	proxy->max_speed_hz = chip->max_speed_hz;
 	proxy->mode = chip->mode;
@@ -750,6 +800,15 @@ struct spi_device *spi_new_device(struct spi_controller *ctlr,
 	proxy->dev.platform_data = (void *) chip->platform_data;
 	proxy->controller_data = chip->controller_data;
 	proxy->controller_state = NULL;
+	/*
+	 * spi->chip_select[i] gives the corresponding physical CS for logical CS i
+	 * logical CS number is represented by setting the ith bit in spi->cs_index_mask
+	 * So, for example, if spi->cs_index_mask = 0x01 then logical CS number is 0 and
+	 * spi->chip_select[0] will give the physical CS.
+	 * By default spi->chip_select[0] will hold the physical CS number so, set
+	 * spi->cs_index_mask as 0x01.
+	 */
+	proxy->cs_index_mask = 0x01;
 
 	if (chip->swnode) {
 		status = device_add_software_node(&proxy->dev, chip->swnode);
@@ -942,32 +1001,51 @@ static void spi_res_release(struct spi_controller *ctlr, struct spi_message *mes
 }
 
 /*-------------------------------------------------------------------------*/
+static inline bool spi_is_last_cs(struct spi_device *spi)
+{
+	u8 idx;
+	bool last = false;
+
+	for (idx = 0; idx < SPI_CS_CNT_MAX; idx++) {
+		if ((spi->cs_index_mask >> idx) & 0x01) {
+			if (spi->controller->last_cs[idx] == spi_get_chipselect(spi, idx))
+				last = true;
+		}
+	}
+	return last;
+}
+
 
 static void spi_set_cs(struct spi_device *spi, bool enable, bool force)
 {
 	bool activate = enable;
+	u8 idx;
 
 	/*
 	 * Avoid calling into the driver (or doing delays) if the chip select
 	 * isn't actually changing from the last time this was called.
 	 */
-	if (!force && ((enable && spi->controller->last_cs == spi_get_chipselect(spi, 0)) ||
-		       (!enable && spi->controller->last_cs != spi_get_chipselect(spi, 0))) &&
+	if (!force && ((enable && spi->controller->last_cs_index_mask == spi->cs_index_mask &&
+			spi_is_last_cs(spi)) ||
+		       (!enable && spi->controller->last_cs_index_mask == spi->cs_index_mask &&
+			!spi_is_last_cs(spi))) &&
 	    (spi->controller->last_cs_mode_high == (spi->mode & SPI_CS_HIGH)))
 		return;
 
 	trace_spi_set_cs(spi, activate);
 
-	spi->controller->last_cs = enable ? spi_get_chipselect(spi, 0) : -1;
+	spi->controller->last_cs_index_mask = spi->cs_index_mask;
+	for (idx = 0; idx < SPI_CS_CNT_MAX; idx++)
+		spi->controller->last_cs[idx] = enable ? spi_get_chipselect(spi, 0) : -1;
 	spi->controller->last_cs_mode_high = spi->mode & SPI_CS_HIGH;
 
-	if ((spi_get_csgpiod(spi, 0) || !spi->controller->set_cs_timing) && !activate)
-		spi_delay_exec(&spi->cs_hold, NULL);
-
 	if (spi->mode & SPI_CS_HIGH)
 		enable = !enable;
 
-	if (spi_get_csgpiod(spi, 0)) {
+	if (spi_is_csgpiod(spi)) {
+		if (!spi->controller->set_cs_timing && !activate)
+			spi_delay_exec(&spi->cs_hold, NULL);
+
 		if (!(spi->mode & SPI_NO_CS)) {
 			/*
 			 * Historically ACPI has no means of the GPIO polarity and
@@ -979,26 +1057,38 @@ static void spi_set_cs(struct spi_device *spi, bool enable, bool force)
 			 * ambiguity. That's why we use enable, that takes SPI_CS_HIGH
 			 * into account.
 			 */
-			if (has_acpi_companion(&spi->dev))
-				gpiod_set_value_cansleep(spi_get_csgpiod(spi, 0), !enable);
-			else
-				/* Polarity handled by GPIO library */
-				gpiod_set_value_cansleep(spi_get_csgpiod(spi, 0), activate);
+			for (idx = 0; idx < SPI_CS_CNT_MAX; idx++) {
+				if (((spi->cs_index_mask >> idx) & 0x01) &&
+				    spi_get_csgpiod(spi, idx)) {
+					if (has_acpi_companion(&spi->dev))
+						gpiod_set_value_cansleep(spi_get_csgpiod(spi, idx),
+									 !enable);
+					else
+						/* Polarity handled by GPIO library */
+						gpiod_set_value_cansleep(spi_get_csgpiod(spi, idx),
+									 activate);
+
+					if (activate)
+						spi_delay_exec(&spi->cs_setup, NULL);
+					else
+						spi_delay_exec(&spi->cs_inactive, NULL);
+				}
+			}
 		}
 		/* Some SPI masters need both GPIO CS & slave_select */
 		if ((spi->controller->flags & SPI_CONTROLLER_GPIO_SS) &&
 		    spi->controller->set_cs)
 			spi->controller->set_cs(spi, !enable);
+
+		if (!spi->controller->set_cs_timing) {
+			if (activate)
+				spi_delay_exec(&spi->cs_setup, NULL);
+			else
+				spi_delay_exec(&spi->cs_inactive, NULL);
+		}
 	} else if (spi->controller->set_cs) {
 		spi->controller->set_cs(spi, !enable);
 	}
-
-	if (spi_get_csgpiod(spi, 0) || !spi->controller->set_cs_timing) {
-		if (activate)
-			spi_delay_exec(&spi->cs_setup, NULL);
-		else
-			spi_delay_exec(&spi->cs_inactive, NULL);
-	}
 }
 
 #ifdef CONFIG_HAS_DMA
@@ -2222,8 +2312,8 @@ static void of_spi_parse_dt_cs_delay(struct device_node *nc,
 static int of_spi_parse_dt(struct spi_controller *ctlr, struct spi_device *spi,
 			   struct device_node *nc)
 {
-	u32 value;
-	int rc;
+	u32 value, cs[SPI_CS_CNT_MAX];
+	int rc, idx;
 
 	/* Mode (clock phase/polarity/etc.) */
 	if (of_property_read_bool(nc, "spi-cpha"))
@@ -2295,14 +2385,53 @@ static int of_spi_parse_dt(struct spi_controller *ctlr, struct spi_device *spi,
 		return 0;
 	}
 
+	if (ctlr->num_chipselect > SPI_CS_CNT_MAX) {
+		dev_err(&ctlr->dev, "No. of CS is more than max. no. of supported CS\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * Zero(0) is a valid physical CS value and can be located at any
+	 * logical CS in the spi->chip_select[]. If all the physical CS
+	 * are initialized to 0 then It would be difficult to differentiate
+	 * between a valid physical CS 0 & an unused logical CS whose physical
+	 * CS can be 0. As a solution to this issue initialize all the CS to 0xFF.
+	 * Now all the unused logical CS will have 0xFF physical CS value & can be
+	 * ignore while performing physical CS validity checks.
+	 */
+	for (idx = 0; idx < SPI_CS_CNT_MAX; idx++)
+		spi_set_chipselect(spi, idx, 0xFF);
+
 	/* Device address */
-	rc = of_property_read_u32(nc, "reg", &value);
-	if (rc) {
+	rc = of_property_read_variable_u32_array(nc, "reg", &cs[0], 1,
+						 SPI_CS_CNT_MAX);
+	if (rc < 0) {
 		dev_err(&ctlr->dev, "%pOF has no valid 'reg' property (%d)\n",
 			nc, rc);
 		return rc;
 	}
-	spi_set_chipselect(spi, 0, value);
+	if (rc > ctlr->num_chipselect) {
+		dev_err(&ctlr->dev, "%pOF has number of CS > ctlr->num_chipselect (%d)\n",
+			nc, rc);
+		return rc;
+	}
+	if ((of_property_read_bool(nc, "parallel-memories")) &&
+	    (!(ctlr->flags & SPI_CONTROLLER_MULTI_CS))) {
+		dev_err(&ctlr->dev, "SPI controller doesn't support multi CS\n");
+		return -EINVAL;
+	}
+	for (idx = 0; idx < rc; idx++)
+		spi_set_chipselect(spi, idx, cs[idx]);
+
+	/*
+	 * spi->chip_select[i] gives the corresponding physical CS for logical CS i
+	 * logical CS number is represented by setting the ith bit in spi->cs_index_mask
+	 * So, for example, if spi->cs_index_mask = 0x01 then logical CS number is 0 and
+	 * spi->chip_select[0] will give the physical CS.
+	 * By default spi->chip_select[0] will hold the physical CS number so, set
+	 * spi->cs_index_mask as 0x01.
+	 */
+	spi->cs_index_mask = 0x01;
 
 	/* Device speed */
 	if (!of_property_read_u32(nc, "spi-max-frequency", &value))
@@ -2408,6 +2537,7 @@ struct spi_device *spi_new_ancillary_device(struct spi_device *spi,
 	struct spi_controller *ctlr = spi->controller;
 	struct spi_device *ancillary;
 	int rc = 0;
+	u8 idx;
 
 	/* Alloc an spi_device */
 	ancillary = spi_alloc_device(ctlr);
@@ -2418,12 +2548,33 @@ struct spi_device *spi_new_ancillary_device(struct spi_device *spi,
 
 	strscpy(ancillary->modalias, "dummy", sizeof(ancillary->modalias));
 
+	/*
+	 * Zero(0) is a valid physical CS value and can be located at any
+	 * logical CS in the spi->chip_select[]. If all the physical CS
+	 * are initialized to 0 then It would be difficult to differentiate
+	 * between a valid physical CS 0 & an unused logical CS whose physical
+	 * CS can be 0. As a solution to this issue initialize all the CS to 0xFF.
+	 * Now all the unused logical CS will have 0xFF physical CS value & can be
+	 * ignore while performing physical CS validity checks.
+	 */
+	for (idx = 0; idx < SPI_CS_CNT_MAX; idx++)
+		spi_set_chipselect(ancillary, idx, 0xFF);
+
 	/* Use provided chip-select for ancillary device */
 	spi_set_chipselect(ancillary, 0, chip_select);
 
 	/* Take over SPI mode/speed from SPI main device */
 	ancillary->max_speed_hz = spi->max_speed_hz;
 	ancillary->mode = spi->mode;
+	/*
+	 * spi->chip_select[i] gives the corresponding physical CS for logical CS i
+	 * logical CS number is represented by setting the ith bit in spi->cs_index_mask
+	 * So, for example, if spi->cs_index_mask = 0x01 then logical CS number is 0 and
+	 * spi->chip_select[0] will give the physical CS.
+	 * By default spi->chip_select[0] will hold the physical CS number so, set
+	 * spi->cs_index_mask as 0x01.
+	 */
+	ancillary->cs_index_mask = 0x01;
 
 	WARN_ON(!mutex_is_locked(&ctlr->add_lock));
 
@@ -2626,6 +2777,7 @@ struct spi_device *acpi_spi_device_alloc(struct spi_controller *ctlr,
 	struct acpi_spi_lookup lookup = {};
 	struct spi_device *spi;
 	int ret;
+	u8 idx;
 
 	if (!ctlr && index == -1)
 		return ERR_PTR(-EINVAL);
@@ -2661,12 +2813,33 @@ struct spi_device *acpi_spi_device_alloc(struct spi_controller *ctlr,
 		return ERR_PTR(-ENOMEM);
 	}
 
+	/*
+	 * Zero(0) is a valid physical CS value and can be located at any
+	 * logical CS in the spi->chip_select[]. If all the physical CS
+	 * are initialized to 0 then It would be difficult to differentiate
+	 * between a valid physical CS 0 & an unused logical CS whose physical
+	 * CS can be 0. As a solution to this issue initialize all the CS to 0xFF.
+	 * Now all the unused logical CS will have 0xFF physical CS value & can be
+	 * ignore while performing physical CS validity checks.
+	 */
+	for (idx = 0; idx < SPI_CS_CNT_MAX; idx++)
+		spi_set_chipselect(spi, idx, 0xFF);
+
 	ACPI_COMPANION_SET(&spi->dev, adev);
 	spi->max_speed_hz	= lookup.max_speed_hz;
 	spi->mode		|= lookup.mode;
 	spi->irq		= lookup.irq;
 	spi->bits_per_word	= lookup.bits_per_word;
 	spi_set_chipselect(spi, 0, lookup.chip_select);
+	/*
+	 * spi->chip_select[i] gives the corresponding physical CS for logical CS i
+	 * logical CS number is represented by setting the ith bit in spi->cs_index_mask
+	 * So, for example, if spi->cs_index_mask = 0x01 then logical CS number is 0 and
+	 * spi->chip_select[0] will give the physical CS.
+	 * By default spi->chip_select[0] will hold the physical CS number so, set
+	 * spi->cs_index_mask as 0x01.
+	 */
+	spi->cs_index_mask	= 0x01;
 
 	return spi;
 }
@@ -3100,6 +3273,7 @@ int spi_register_controller(struct spi_controller *ctlr)
 	struct boardinfo	*bi;
 	int			first_dynamic;
 	int			status;
+	int			idx;
 
 	if (!dev)
 		return -ENODEV;
@@ -3164,7 +3338,8 @@ int spi_register_controller(struct spi_controller *ctlr)
 	}
 
 	/* Setting last_cs to -1 means no chip selected */
-	ctlr->last_cs = -1;
+	for (idx = 0; idx < SPI_CS_CNT_MAX; idx++)
+		ctlr->last_cs[idx] = -1;
 
 	status = device_add(&ctlr->dev);
 	if (status < 0)
@@ -3889,7 +4064,7 @@ static int __spi_validate(struct spi_device *spi, struct spi_message *message)
 	 * cs_change is set for each transfer.
 	 */
 	if ((spi->mode & SPI_CS_WORD) && (!(ctlr->mode_bits & SPI_CS_WORD) ||
-					  spi_get_csgpiod(spi, 0))) {
+					  spi_is_csgpiod(spi))) {
 		size_t maxsize = BITS_TO_BYTES(spi->bits_per_word);
 		int ret;
 
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 255a0562aea5..50622054b6af 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -20,6 +20,9 @@
 
 #include <uapi/linux/spi/spi.h>
 
+/* Max no. of CS supported per spi device */
+#define SPI_CS_CNT_MAX 4
+
 struct dma_chan;
 struct software_node;
 struct ptp_system_timestamp;
@@ -132,7 +135,8 @@ extern void spi_transfer_cs_change_delay_exec(struct spi_message *msg,
  * @max_speed_hz: Maximum clock rate to be used with this chip
  *	(on this board); may be changed by the device's driver.
  *	The spi_transfer.speed_hz can override this for each transfer.
- * @chip_select: Chipselect, distinguishing chips handled by @controller.
+ * @chip_select: Array of physical chipselect, spi->chipselect[i] gives
+ *	the corresponding physical CS for logical CS i.
  * @mode: The spi mode defines how data is clocked out and in.
  *	This may be changed by the device's driver.
  *	The "active low" default for chipselect mode can be overridden
@@ -157,8 +161,8 @@ extern void spi_transfer_cs_change_delay_exec(struct spi_message *msg,
  *	the device will bind to the named driver and only the named driver.
  *	Do not set directly, because core frees it; use driver_set_override() to
  *	set or clear it.
- * @cs_gpiod: GPIO descriptor of the chipselect line (optional, NULL when
- *	not using a GPIO line)
+ * @cs_gpiod: Array of GPIO descriptors of the corresponding chipselect lines
+ *	(optional, NULL when not using a GPIO line)
  * @word_delay: delay to be inserted between consecutive
  *	words of a transfer
  * @cs_setup: delay to be introduced by the controller after CS is asserted
@@ -167,6 +171,7 @@ extern void spi_transfer_cs_change_delay_exec(struct spi_message *msg,
  *	deasserted. If @cs_change_delay is used from @spi_transfer, then the
  *	two delays will be added up.
  * @pcpu_statistics: statistics for the spi_device
+ * @cs_index_mask: Bit mask of the active chipselect(s) in the chipselect array
  *
  * A @spi_device is used to interchange data between an SPI slave
  * (usually a discrete chip) and CPU memory.
@@ -182,7 +187,7 @@ struct spi_device {
 	struct spi_controller	*controller;
 	struct spi_controller	*master;	/* Compatibility layer */
 	u32			max_speed_hz;
-	u8			chip_select;
+	u8			chip_select[SPI_CS_CNT_MAX];
 	u8			bits_per_word;
 	bool			rt;
 #define SPI_NO_TX		BIT(31)		/* No transmit wire */
@@ -213,7 +218,7 @@ struct spi_device {
 	void			*controller_data;
 	char			modalias[SPI_NAME_SIZE];
 	const char		*driver_override;
-	struct gpio_desc	*cs_gpiod;	/* Chip select GPIO descriptor */
+	struct gpio_desc	*cs_gpiod[SPI_CS_CNT_MAX];	/* Chip select gpio desc */
 	struct spi_delay	word_delay; /* Inter-word delay */
 	/* CS delays */
 	struct spi_delay	cs_setup;
@@ -223,6 +228,13 @@ struct spi_device {
 	/* The statistics */
 	struct spi_statistics __percpu	*pcpu_statistics;
 
+	/* Bit mask of the chipselect(s) that the driver need to use from
+	 * the chipselect array.When the controller is capable to handle
+	 * multiple chip selects & memories are connected in parallel
+	 * then more than one bit need to be set in cs_index_mask.
+	 */
+	u32			cs_index_mask : SPI_CS_CNT_MAX;
+
 	/*
 	 * Likely need more hooks for more protocol options affecting how
 	 * the controller talks to each chip, like:
@@ -279,22 +291,33 @@ static inline void *spi_get_drvdata(const struct spi_device *spi)
 
 static inline u8 spi_get_chipselect(const struct spi_device *spi, u8 idx)
 {
-	return spi->chip_select;
+	return spi->chip_select[idx];
 }
 
 static inline void spi_set_chipselect(struct spi_device *spi, u8 idx, u8 chipselect)
 {
-	spi->chip_select = chipselect;
+	spi->chip_select[idx] = chipselect;
 }
 
 static inline struct gpio_desc *spi_get_csgpiod(const struct spi_device *spi, u8 idx)
 {
-	return spi->cs_gpiod;
+	return spi->cs_gpiod[idx];
 }
 
 static inline void spi_set_csgpiod(struct spi_device *spi, u8 idx, struct gpio_desc *csgpiod)
 {
-	spi->cs_gpiod = csgpiod;
+	spi->cs_gpiod[idx] = csgpiod;
+}
+
+static inline bool spi_is_csgpiod(struct spi_device *spi)
+{
+	u8 idx;
+
+	for (idx = 0; idx < SPI_CS_CNT_MAX; idx++) {
+		if (spi_get_csgpiod(spi, idx))
+			return true;
+	}
+	return false;
 }
 
 /**
@@ -399,6 +422,8 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch
  * @bus_lock_spinlock: spinlock for SPI bus locking
  * @bus_lock_mutex: mutex for exclusion of multiple callers
  * @bus_lock_flag: indicates that the SPI bus is locked for exclusive use
+ * @multi_cs_cap: indicates that the SPI Controller can assert/de-assert
+ *	more than one chip select at once.
  * @setup: updates the device mode and clocking records used by a
  *	device's SPI controller; protocol code may call this.  This
  *	must fail if an unrecognized or unsupported mode is requested.
@@ -567,6 +592,11 @@ struct spi_controller {
 #define SPI_CONTROLLER_MUST_TX		BIT(4)	/* Requires tx */
 #define SPI_CONTROLLER_GPIO_SS		BIT(5)	/* GPIO CS must select slave */
 #define SPI_CONTROLLER_SUSPENDED	BIT(6)	/* Currently suspended */
+	/*
+	 * The spi-controller has multi chip select capability and can
+	 * assert/de-assert more than one chip select at once.
+	 */
+#define SPI_CONTROLLER_MULTI_CS		BIT(7)
 
 	/* Flag indicating if the allocation of this struct is devres-managed */
 	bool			devm_allocated;
@@ -677,7 +707,8 @@ struct spi_controller {
 	bool				rt;
 	bool				auto_runtime_pm;
 	bool				cur_msg_mapped;
-	char				last_cs;
+	char				last_cs[SPI_CS_CNT_MAX];
+	char				last_cs_index_mask;
 	bool				last_cs_mode_high;
 	bool                            fallback;
 	struct completion               xfer_completion;
-- 
cgit v1.2.3


From 7bf421f44549cd0bca32bd0b4cf6e4cfe5b4f865 Mon Sep 17 00:00:00 2001
From: Nia Espera <nespera@igalia.com>
Date: Sat, 11 Nov 2023 23:07:39 +0100
Subject: dt-bindings: iio: adc: qcom: Add Qualcomm smb139x

Bindings for a charger controller chip found on sm8350

Signed-off-by: Nia Espera <nespera@igalia.com>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Acked-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Link: https://lore.kernel.org/r/20231111-nia-sm8350-for-upstream-v4-1-3a638b02eea5@igalia.com
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 include/dt-bindings/iio/qcom,spmi-adc7-smb139x.h | 19 +++++++++++++++++++
 include/dt-bindings/iio/qcom,spmi-vadc.h         |  3 +++
 2 files changed, 22 insertions(+)
 create mode 100644 include/dt-bindings/iio/qcom,spmi-adc7-smb139x.h

(limited to 'include')

diff --git a/include/dt-bindings/iio/qcom,spmi-adc7-smb139x.h b/include/dt-bindings/iio/qcom,spmi-adc7-smb139x.h
new file mode 100644
index 000000000000..c0680d1285cf
--- /dev/null
+++ b/include/dt-bindings/iio/qcom,spmi-adc7-smb139x.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0-only OR BSD-3-Clause */
+/*
+ * Copyright (c) 2020 The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _DT_BINDINGS_QCOM_SPMI_VADC_SMB139X_H
+#define _DT_BINDINGS_QCOM_SPMI_VADC_SMB139X_H
+
+#include <dt-bindings/iio/qcom,spmi-vadc.h>
+
+#define SMB139x_1_ADC7_SMB_TEMP			(SMB139x_1_SID << 8 | ADC7_SMB_TEMP)
+#define SMB139x_1_ADC7_ICHG_SMB			(SMB139x_1_SID << 8 | ADC7_ICHG_SMB)
+#define SMB139x_1_ADC7_IIN_SMB			(SMB139x_1_SID << 8 | ADC7_IIN_SMB)
+
+#define SMB139x_2_ADC7_SMB_TEMP			(SMB139x_2_SID << 8 | ADC7_SMB_TEMP)
+#define SMB139x_2_ADC7_ICHG_SMB			(SMB139x_2_SID << 8 | ADC7_ICHG_SMB)
+#define SMB139x_2_ADC7_IIN_SMB			(SMB139x_2_SID << 8 | ADC7_IIN_SMB)
+
+#endif
diff --git a/include/dt-bindings/iio/qcom,spmi-vadc.h b/include/dt-bindings/iio/qcom,spmi-vadc.h
index 08adfe25964c..ef07ecd4d585 100644
--- a/include/dt-bindings/iio/qcom,spmi-vadc.h
+++ b/include/dt-bindings/iio/qcom,spmi-vadc.h
@@ -239,12 +239,15 @@
 #define ADC7_GPIO3				0x0c
 #define ADC7_GPIO4				0x0d
 
+#define ADC7_SMB_TEMP				0x06
 #define ADC7_CHG_TEMP				0x10
 #define ADC7_USB_IN_V_16			0x11
 #define ADC7_VDC_16				0x12
 #define ADC7_CC1_ID				0x13
 #define ADC7_VREF_BAT_THERM			0x15
 #define ADC7_IIN_FB				0x17
+#define ADC7_ICHG_SMB				0x18
+#define ADC7_IIN_SMB				0x19
 
 /* 30k pull-up1 */
 #define ADC7_AMUX_THM1_30K_PU			0x24
-- 
cgit v1.2.3


From d4a599c59d2cc6f1e8a7c3debc85d7186a0caadb Mon Sep 17 00:00:00 2001
From: Imran Shaik <quic_imrashai@quicinc.com>
Date: Thu, 23 Nov 2023 12:17:32 +0530
Subject: dt-bindings: clock: qcom: Add ECPRICC clocks for QDU1000 and QRU1000

Add device tree bindings for qcom ecpri clock controller on QDU1000 and
QRU1000 SoCs.

Signed-off-by: Imran Shaik <quic_imrashai@quicinc.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231123064735.2979802-2-quic_imrashai@quicinc.com
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 .../bindings/clock/qcom,qdu1000-ecpricc.yaml       |  68 ++++++++++
 include/dt-bindings/clock/qcom,qdu1000-ecpricc.h   | 147 +++++++++++++++++++++
 2 files changed, 215 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/clock/qcom,qdu1000-ecpricc.yaml
 create mode 100644 include/dt-bindings/clock/qcom,qdu1000-ecpricc.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/clock/qcom,qdu1000-ecpricc.yaml b/Documentation/devicetree/bindings/clock/qcom,qdu1000-ecpricc.yaml
new file mode 100644
index 000000000000..fd21df0e7697
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/qcom,qdu1000-ecpricc.yaml
@@ -0,0 +1,68 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/qcom,qdu1000-ecpricc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm ECPRI Clock & Reset Controller for QDU1000 and QRU1000
+
+maintainers:
+  - Taniya Das <quic_tdas@quicinc.com>
+  - Imran Shaik <quic_imrashai@quicinc.com>
+
+description: |
+  Qualcomm ECPRI Specification V2.0 Common Public Radio Interface clock control
+  module which supports the clocks, resets on QDU1000 and QRU1000
+
+  See also:: include/dt-bindings/clock/qcom,qdu1000-ecpricc.h
+
+properties:
+  compatible:
+    enum:
+      - qcom,qdu1000-ecpricc
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: Board XO source
+      - description: GPLL0 source from GCC
+      - description: GPLL1 source from GCC
+      - description: GPLL2 source from GCC
+      - description: GPLL3 source from GCC
+      - description: GPLL4 source from GCC
+      - description: GPLL5 source from GCC
+
+  '#clock-cells':
+    const: 1
+
+  '#reset-cells':
+    const: 1
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - '#clock-cells'
+  - '#reset-cells'
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/qcom,qdu1000-gcc.h>
+    #include <dt-bindings/clock/qcom,rpmh.h>
+    clock-controller@280000 {
+      compatible = "qcom,qdu1000-ecpricc";
+      reg = <0x00280000 0x31c00>;
+      clocks = <&rpmhcc RPMH_CXO_CLK>,
+               <&gcc GCC_ECPRI_CC_GPLL0_CLK_SRC>,
+               <&gcc GCC_ECPRI_CC_GPLL1_EVEN_CLK_SRC>,
+               <&gcc GCC_ECPRI_CC_GPLL2_EVEN_CLK_SRC>,
+               <&gcc GCC_ECPRI_CC_GPLL3_CLK_SRC>,
+               <&gcc GCC_ECPRI_CC_GPLL4_CLK_SRC>,
+               <&gcc GCC_ECPRI_CC_GPLL5_EVEN_CLK_SRC>;
+      #clock-cells = <1>;
+      #reset-cells = <1>;
+    };
diff --git a/include/dt-bindings/clock/qcom,qdu1000-ecpricc.h b/include/dt-bindings/clock/qcom,qdu1000-ecpricc.h
new file mode 100644
index 000000000000..731e404a2ce6
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,qdu1000-ecpricc.h
@@ -0,0 +1,147 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/*
+ * Copyright (c) 2022-2023, Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#ifndef _DT_BINDINGS_CLK_QCOM_ECPRI_CC_QDU1000_H
+#define _DT_BINDINGS_CLK_QCOM_ECPRI_CC_QDU1000_H
+
+/* ECPRI_CC clocks */
+#define ECPRI_CC_PLL0						0
+#define ECPRI_CC_PLL1						1
+#define ECPRI_CC_ECPRI_CG_CLK					2
+#define ECPRI_CC_ECPRI_CLK_SRC					3
+#define ECPRI_CC_ECPRI_DMA_CLK					4
+#define ECPRI_CC_ECPRI_DMA_CLK_SRC				5
+#define ECPRI_CC_ECPRI_DMA_NOC_CLK				6
+#define ECPRI_CC_ECPRI_FAST_CLK					7
+#define ECPRI_CC_ECPRI_FAST_CLK_SRC				8
+#define ECPRI_CC_ECPRI_FAST_DIV2_CLK				9
+#define ECPRI_CC_ECPRI_FAST_DIV2_CLK_SRC			10
+#define ECPRI_CC_ECPRI_FAST_DIV2_NOC_CLK			11
+#define ECPRI_CC_ECPRI_FR_CLK					12
+#define ECPRI_CC_ECPRI_ORAN_CLK_SRC				13
+#define ECPRI_CC_ECPRI_ORAN_DIV2_CLK				14
+#define ECPRI_CC_ETH_100G_C2C0_HM_FF_CLK_SRC			15
+#define ECPRI_CC_ETH_100G_C2C0_UDP_FIFO_CLK			16
+#define ECPRI_CC_ETH_100G_C2C1_UDP_FIFO_CLK			17
+#define ECPRI_CC_ETH_100G_C2C_0_HM_FF_0_CLK			18
+#define ECPRI_CC_ETH_100G_C2C_0_HM_FF_1_CLK			19
+#define ECPRI_CC_ETH_100G_C2C_HM_FF_0_DIV_CLK_SRC		20
+#define ECPRI_CC_ETH_100G_C2C_HM_FF_1_DIV_CLK_SRC		21
+#define ECPRI_CC_ETH_100G_C2C_HM_MACSEC_CLK			22
+#define ECPRI_CC_ETH_100G_C2C_HM_MACSEC_CLK_SRC			23
+#define ECPRI_CC_ETH_100G_DBG_C2C_HM_FF_0_CLK			24
+#define ECPRI_CC_ETH_100G_DBG_C2C_HM_FF_0_DIV_CLK_SRC		25
+#define ECPRI_CC_ETH_100G_DBG_C2C_HM_FF_1_CLK			26
+#define ECPRI_CC_ETH_100G_DBG_C2C_HM_FF_1_DIV_CLK_SRC		27
+#define ECPRI_CC_ETH_100G_DBG_C2C_HM_FF_CLK_SRC			28
+#define ECPRI_CC_ETH_100G_DBG_C2C_UDP_FIFO_CLK			29
+#define ECPRI_CC_ETH_100G_FH0_HM_FF_CLK_SRC			30
+#define ECPRI_CC_ETH_100G_FH0_MACSEC_CLK_SRC			31
+#define ECPRI_CC_ETH_100G_FH1_HM_FF_CLK_SRC			32
+#define ECPRI_CC_ETH_100G_FH1_MACSEC_CLK_SRC			33
+#define ECPRI_CC_ETH_100G_FH2_HM_FF_CLK_SRC			34
+#define ECPRI_CC_ETH_100G_FH2_MACSEC_CLK_SRC			35
+#define ECPRI_CC_ETH_100G_FH_0_HM_FF_0_CLK			36
+#define ECPRI_CC_ETH_100G_FH_0_HM_FF_0_DIV_CLK_SRC		37
+#define ECPRI_CC_ETH_100G_FH_0_HM_FF_1_CLK			38
+#define ECPRI_CC_ETH_100G_FH_0_HM_FF_1_DIV_CLK_SRC		39
+#define ECPRI_CC_ETH_100G_FH_0_HM_FF_2_CLK			40
+#define ECPRI_CC_ETH_100G_FH_0_HM_FF_2_DIV_CLK_SRC		41
+#define ECPRI_CC_ETH_100G_FH_0_HM_FF_3_CLK			42
+#define ECPRI_CC_ETH_100G_FH_0_HM_FF_3_DIV_CLK_SRC		43
+#define ECPRI_CC_ETH_100G_FH_0_UDP_FIFO_CLK			44
+#define ECPRI_CC_ETH_100G_FH_1_HM_FF_0_CLK			45
+#define ECPRI_CC_ETH_100G_FH_1_HM_FF_0_DIV_CLK_SRC		46
+#define ECPRI_CC_ETH_100G_FH_1_HM_FF_1_CLK			47
+#define ECPRI_CC_ETH_100G_FH_1_HM_FF_1_DIV_CLK_SRC		48
+#define ECPRI_CC_ETH_100G_FH_1_HM_FF_2_CLK			49
+#define ECPRI_CC_ETH_100G_FH_1_HM_FF_2_DIV_CLK_SRC		50
+#define ECPRI_CC_ETH_100G_FH_1_HM_FF_3_CLK			51
+#define ECPRI_CC_ETH_100G_FH_1_HM_FF_3_DIV_CLK_SRC		52
+#define ECPRI_CC_ETH_100G_FH_1_UDP_FIFO_CLK			53
+#define ECPRI_CC_ETH_100G_FH_2_HM_FF_0_CLK			54
+#define ECPRI_CC_ETH_100G_FH_2_HM_FF_0_DIV_CLK_SRC		55
+#define ECPRI_CC_ETH_100G_FH_2_HM_FF_1_CLK			56
+#define ECPRI_CC_ETH_100G_FH_2_HM_FF_1_DIV_CLK_SRC		57
+#define ECPRI_CC_ETH_100G_FH_2_HM_FF_2_CLK			58
+#define ECPRI_CC_ETH_100G_FH_2_HM_FF_2_DIV_CLK_SRC		59
+#define ECPRI_CC_ETH_100G_FH_2_HM_FF_3_CLK			60
+#define ECPRI_CC_ETH_100G_FH_2_HM_FF_3_DIV_CLK_SRC		61
+#define ECPRI_CC_ETH_100G_FH_2_UDP_FIFO_CLK			62
+#define ECPRI_CC_ETH_100G_FH_MACSEC_0_CLK			63
+#define ECPRI_CC_ETH_100G_FH_MACSEC_1_CLK			64
+#define ECPRI_CC_ETH_100G_FH_MACSEC_2_CLK			65
+#define ECPRI_CC_ETH_100G_MAC_C2C_HM_REF_CLK			66
+#define ECPRI_CC_ETH_100G_MAC_C2C_HM_REF_CLK_SRC		67
+#define ECPRI_CC_ETH_100G_MAC_DBG_C2C_HM_REF_CLK		68
+#define ECPRI_CC_ETH_100G_MAC_DBG_C2C_HM_REF_CLK_SRC		69
+#define ECPRI_CC_ETH_100G_MAC_FH0_HM_REF_CLK			70
+#define ECPRI_CC_ETH_100G_MAC_FH0_HM_REF_CLK_SRC		71
+#define ECPRI_CC_ETH_100G_MAC_FH1_HM_REF_CLK			72
+#define ECPRI_CC_ETH_100G_MAC_FH1_HM_REF_CLK_SRC		73
+#define ECPRI_CC_ETH_100G_MAC_FH2_HM_REF_CLK			74
+#define ECPRI_CC_ETH_100G_MAC_FH2_HM_REF_CLK_SRC		75
+#define ECPRI_CC_ETH_DBG_NFAPI_AXI_CLK				76
+#define ECPRI_CC_ETH_DBG_NOC_AXI_CLK				77
+#define ECPRI_CC_ETH_PHY_0_OCK_SRAM_CLK				78
+#define ECPRI_CC_ETH_PHY_1_OCK_SRAM_CLK				79
+#define ECPRI_CC_ETH_PHY_2_OCK_SRAM_CLK				80
+#define ECPRI_CC_ETH_PHY_3_OCK_SRAM_CLK				81
+#define ECPRI_CC_ETH_PHY_4_OCK_SRAM_CLK				82
+#define ECPRI_CC_MSS_EMAC_CLK					83
+#define ECPRI_CC_MSS_EMAC_CLK_SRC				84
+#define ECPRI_CC_MSS_ORAN_CLK					85
+#define ECPRI_CC_PHY0_LANE0_RX_CLK				86
+#define ECPRI_CC_PHY0_LANE0_TX_CLK				87
+#define ECPRI_CC_PHY0_LANE1_RX_CLK				88
+#define ECPRI_CC_PHY0_LANE1_TX_CLK				89
+#define ECPRI_CC_PHY0_LANE2_RX_CLK				90
+#define ECPRI_CC_PHY0_LANE2_TX_CLK				91
+#define ECPRI_CC_PHY0_LANE3_RX_CLK				92
+#define ECPRI_CC_PHY0_LANE3_TX_CLK				93
+#define ECPRI_CC_PHY1_LANE0_RX_CLK				94
+#define ECPRI_CC_PHY1_LANE0_TX_CLK				95
+#define ECPRI_CC_PHY1_LANE1_RX_CLK				96
+#define ECPRI_CC_PHY1_LANE1_TX_CLK				97
+#define ECPRI_CC_PHY1_LANE2_RX_CLK				98
+#define ECPRI_CC_PHY1_LANE2_TX_CLK				99
+#define ECPRI_CC_PHY1_LANE3_RX_CLK				100
+#define ECPRI_CC_PHY1_LANE3_TX_CLK				101
+#define ECPRI_CC_PHY2_LANE0_RX_CLK				102
+#define ECPRI_CC_PHY2_LANE0_TX_CLK				103
+#define ECPRI_CC_PHY2_LANE1_RX_CLK				104
+#define ECPRI_CC_PHY2_LANE1_TX_CLK				105
+#define ECPRI_CC_PHY2_LANE2_RX_CLK				106
+#define ECPRI_CC_PHY2_LANE2_TX_CLK				107
+#define ECPRI_CC_PHY2_LANE3_RX_CLK				108
+#define ECPRI_CC_PHY2_LANE3_TX_CLK				109
+#define ECPRI_CC_PHY3_LANE0_RX_CLK				110
+#define ECPRI_CC_PHY3_LANE0_TX_CLK				111
+#define ECPRI_CC_PHY3_LANE1_RX_CLK				112
+#define ECPRI_CC_PHY3_LANE1_TX_CLK				113
+#define ECPRI_CC_PHY3_LANE2_RX_CLK				114
+#define ECPRI_CC_PHY3_LANE2_TX_CLK				115
+#define ECPRI_CC_PHY3_LANE3_RX_CLK				116
+#define ECPRI_CC_PHY3_LANE3_TX_CLK				117
+#define ECPRI_CC_PHY4_LANE0_RX_CLK				118
+#define ECPRI_CC_PHY4_LANE0_TX_CLK				119
+#define ECPRI_CC_PHY4_LANE1_RX_CLK				120
+#define ECPRI_CC_PHY4_LANE1_TX_CLK				121
+#define ECPRI_CC_PHY4_LANE2_RX_CLK				122
+#define ECPRI_CC_PHY4_LANE2_TX_CLK				123
+#define ECPRI_CC_PHY4_LANE3_RX_CLK				124
+#define ECPRI_CC_PHY4_LANE3_TX_CLK				125
+
+/* ECPRI_CC resets */
+#define ECPRI_CC_CLK_CTL_TOP_ECPRI_CC_ECPRI_SS_BCR		0
+#define ECPRI_CC_CLK_CTL_TOP_ECPRI_CC_ETH_C2C_BCR		1
+#define ECPRI_CC_CLK_CTL_TOP_ECPRI_CC_ETH_FH0_BCR		2
+#define ECPRI_CC_CLK_CTL_TOP_ECPRI_CC_ETH_FH1_BCR		3
+#define ECPRI_CC_CLK_CTL_TOP_ECPRI_CC_ETH_FH2_BCR		4
+#define ECPRI_CC_CLK_CTL_TOP_ECPRI_CC_ETH_WRAPPER_TOP_BCR	5
+#define ECPRI_CC_CLK_CTL_TOP_ECPRI_CC_MODEM_BCR			6
+#define ECPRI_CC_CLK_CTL_TOP_ECPRI_CC_NOC_BCR			7
+
+#endif
-- 
cgit v1.2.3


From e03781879a0d524ce3126678d50a80484a513c4b Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 6 Dec 2023 23:31:02 +0200
Subject: drop_monitor: Require 'CAP_SYS_ADMIN' when joining "events" group

The "NET_DM" generic netlink family notifies drop locations over the
"events" multicast group. This is problematic since by default generic
netlink allows non-root users to listen to these notifications.

Fix by adding a new field to the generic netlink multicast group
structure that when set prevents non-root users or root without the
'CAP_SYS_ADMIN' capability (in the user namespace owning the network
namespace) from joining the group. Set this field for the "events"
group. Use 'CAP_SYS_ADMIN' rather than 'CAP_NET_ADMIN' because of the
nature of the information that is shared over this group.

Note that the capability check in this case will always be performed
against the initial user namespace since the family is not netns aware
and only operates in the initial network namespace.

A new field is added to the structure rather than using the "flags"
field because the existing field uses uAPI flags and it is inappropriate
to add a new uAPI flag for an internal kernel check. In net-next we can
rework the "flags" field to use internal flags and fold the new field
into it. But for now, in order to reduce the amount of changes, add a
new field.

Since the information can only be consumed by root, mark the control
plane operations that start and stop the tracing as root-only using the
'GENL_ADMIN_PERM' flag.

Tested using [1].

Before:

 # capsh -- -c ./dm_repo
 # capsh --drop=cap_sys_admin -- -c ./dm_repo

After:

 # capsh -- -c ./dm_repo
 # capsh --drop=cap_sys_admin -- -c ./dm_repo
 Failed to join "events" multicast group

[1]
 $ cat dm.c
 #include <stdio.h>
 #include <netlink/genl/ctrl.h>
 #include <netlink/genl/genl.h>
 #include <netlink/socket.h>

 int main(int argc, char **argv)
 {
 	struct nl_sock *sk;
 	int grp, err;

 	sk = nl_socket_alloc();
 	if (!sk) {
 		fprintf(stderr, "Failed to allocate socket\n");
 		return -1;
 	}

 	err = genl_connect(sk);
 	if (err) {
 		fprintf(stderr, "Failed to connect socket\n");
 		return err;
 	}

 	grp = genl_ctrl_resolve_grp(sk, "NET_DM", "events");
 	if (grp < 0) {
 		fprintf(stderr,
 			"Failed to resolve \"events\" multicast group\n");
 		return grp;
 	}

 	err = nl_socket_add_memberships(sk, grp, NFNLGRP_NONE);
 	if (err) {
 		fprintf(stderr, "Failed to join \"events\" multicast group\n");
 		return err;
 	}

 	return 0;
 }
 $ gcc -I/usr/include/libnl3 -lnl-3 -lnl-genl-3 -o dm_repo dm.c

Fixes: 9a8afc8d3962 ("Network Drop Monitor: Adding drop monitor implementation & Netlink protocol")
Reported-by: "The UK's National Cyber Security Centre (NCSC)" <security@ncsc.gov.uk>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20231206213102.1824398-3-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/genetlink.h | 2 ++
 net/core/drop_monitor.c | 4 +++-
 net/netlink/genetlink.c | 3 +++
 3 files changed, 8 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index e18a4c0d69ee..c53244f20437 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -12,10 +12,12 @@
  * struct genl_multicast_group - generic netlink multicast group
  * @name: name of the multicast group, names are per-family
  * @flags: GENL_* flags (%GENL_ADMIN_PERM or %GENL_UNS_ADMIN_PERM)
+ * @cap_sys_admin: whether %CAP_SYS_ADMIN is required for binding
  */
 struct genl_multicast_group {
 	char			name[GENL_NAMSIZ];
 	u8			flags;
+	u8			cap_sys_admin:1;
 };
 
 struct genl_split_ops;
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index aff31cd944c2..b240d9aae4a6 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -183,7 +183,7 @@ out:
 }
 
 static const struct genl_multicast_group dropmon_mcgrps[] = {
-	{ .name = "events", },
+	{ .name = "events", .cap_sys_admin = 1 },
 };
 
 static void send_dm_alert(struct work_struct *work)
@@ -1619,11 +1619,13 @@ static const struct genl_small_ops dropmon_ops[] = {
 		.cmd = NET_DM_CMD_START,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = net_dm_cmd_trace,
+		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = NET_DM_CMD_STOP,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = net_dm_cmd_trace,
+		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = NET_DM_CMD_CONFIG_GET,
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 92ef5ed2e7b0..9c7ffd10df2a 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -1691,6 +1691,9 @@ static int genl_bind(struct net *net, int group)
 		if ((grp->flags & GENL_UNS_ADMIN_PERM) &&
 		    !ns_capable(net->user_ns, CAP_NET_ADMIN))
 			ret = -EPERM;
+		if (grp->cap_sys_admin &&
+		    !ns_capable(net->user_ns, CAP_SYS_ADMIN))
+			ret = -EPERM;
 
 		break;
 	}
-- 
cgit v1.2.3


From cb46fca88d14939da2785567253d0a297f31be27 Mon Sep 17 00:00:00 2001
From: Davidlohr Bueso <dave@stgolabs.net>
Date: Tue, 29 Aug 2023 08:20:14 -0700
Subject: cxl: Add Support for Get Timestamp

Add the call to the UAPI such that userspace may corelate the
timestamps from the device log with system wall time, if, for
example there's any sort of inaccuracy or skew in the device.

Signed-off-by: Davidlohr Bueso <dave@stgolabs.net>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Link: https://lore.kernel.org/r/20230829152014.15452-1-dave@stgolabs.net
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/core/mbox.c      | 1 +
 drivers/cxl/cxlmem.h         | 1 +
 include/uapi/linux/cxl_mem.h | 1 +
 3 files changed, 3 insertions(+)

(limited to 'include')

diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
index 36270dcfb42e..b86dbd25740c 100644
--- a/drivers/cxl/core/mbox.c
+++ b/drivers/cxl/core/mbox.c
@@ -63,6 +63,7 @@ static struct cxl_mem_command cxl_mem_commands[CXL_MEM_COMMAND_ID_MAX] = {
 	CXL_CMD(GET_SHUTDOWN_STATE, 0, 0x1, 0),
 	CXL_CMD(SET_SHUTDOWN_STATE, 0x1, 0, 0),
 	CXL_CMD(GET_SCAN_MEDIA_CAPS, 0x10, 0x4, 0),
+	CXL_CMD(GET_TIMESTAMP, 0, 0x8, 0),
 };
 
 /*
diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h
index a2fcbca253f3..6a6becee402b 100644
--- a/drivers/cxl/cxlmem.h
+++ b/drivers/cxl/cxlmem.h
@@ -503,6 +503,7 @@ enum cxl_opcode {
 	CXL_MBOX_OP_GET_FW_INFO		= 0x0200,
 	CXL_MBOX_OP_TRANSFER_FW		= 0x0201,
 	CXL_MBOX_OP_ACTIVATE_FW		= 0x0202,
+	CXL_MBOX_OP_GET_TIMESTAMP	= 0x0300,
 	CXL_MBOX_OP_SET_TIMESTAMP	= 0x0301,
 	CXL_MBOX_OP_GET_SUPPORTED_LOGS	= 0x0400,
 	CXL_MBOX_OP_GET_LOG		= 0x0401,
diff --git a/include/uapi/linux/cxl_mem.h b/include/uapi/linux/cxl_mem.h
index 14bc6e742148..42066f4eb890 100644
--- a/include/uapi/linux/cxl_mem.h
+++ b/include/uapi/linux/cxl_mem.h
@@ -46,6 +46,7 @@
 	___C(GET_SCAN_MEDIA_CAPS, "Get Scan Media Capabilities"),         \
 	___DEPRECATED(SCAN_MEDIA, "Scan Media"),                          \
 	___DEPRECATED(GET_SCAN_MEDIA, "Get Scan Media Results"),          \
+	___C(GET_TIMESTAMP, "Get Timestamp"),                             \
 	___C(MAX, "invalid / last command")
 
 #define ___C(a, b) CXL_MEM_COMMAND_ID_##a
-- 
cgit v1.2.3


From a7fb0423c201ba12815877a0b5a68a6a1710b23a Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Thu, 7 Dec 2023 08:46:14 -0500
Subject: cgroup: Move rcu_head up near the top of cgroup_root
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit d23b5c577715 ("cgroup: Make operations on the cgroup root_list RCU
safe") adds a new rcu_head to the cgroup_root structure and kvfree_rcu()
for freeing the cgroup_root.

The current implementation of kvfree_rcu(), however, has the limitation
that the offset of the rcu_head structure within the larger data
structure must be less than 4096 or the compilation will fail. See the
macro definition of __is_kvfree_rcu_offset() in include/linux/rcupdate.h
for more information.

By putting rcu_head below the large cgroup structure, any change to the
cgroup structure that makes it larger run the risk of causing build
failure under certain configurations. Commit 77070eeb8821 ("cgroup:
Avoid false cacheline sharing of read mostly rstat_cpu") happens to be
the last straw that breaks it. Fix this problem by moving the rcu_head
structure up before the cgroup structure.

Fixes: d23b5c577715 ("cgroup: Make operations on the cgroup root_list RCU safe")
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Closes: https://lore.kernel.org/lkml/20231207143806.114e0a74@canb.auug.org.au/
Signed-off-by: Waiman Long <longman@redhat.com>
Acked-by: Yafang Shao <laoar.shao@gmail.com>
Reviewed-by: Yosry Ahmed <yosryahmed@google.com>
Reviewed-by: Michal Koutný <mkoutny@suse.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/cgroup-defs.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 5a97ea95b564..ea48c861cd36 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -562,6 +562,10 @@ struct cgroup_root {
 	/* Unique id for this hierarchy. */
 	int hierarchy_id;
 
+	/* A list running through the active hierarchies */
+	struct list_head root_list;
+	struct rcu_head rcu;	/* Must be near the top */
+
 	/*
 	 * The root cgroup. The containing cgroup_root will be destroyed on its
 	 * release. cgrp->ancestors[0] will be used overflowing into the
@@ -575,10 +579,6 @@ struct cgroup_root {
 	/* Number of cgroups in the hierarchy, used only for /proc/cgroups */
 	atomic_t nr_cgrps;
 
-	/* A list running through the active hierarchies */
-	struct list_head root_list;
-	struct rcu_head rcu;
-
 	/* Hierarchy-specific flags */
 	unsigned int flags;
 
-- 
cgit v1.2.3


From 6d72283526090850274d065cd5d60af732cc5fc8 Mon Sep 17 00:00:00 2001
From: Paul Durrant <pdurrant@amazon.com>
Date: Thu, 2 Nov 2023 16:21:28 +0000
Subject: KVM x86/xen: add an override for PVCLOCK_TSC_STABLE_BIT

Unless explicitly told to do so (by passing 'clocksource=tsc' and
'tsc=stable:socket', and then jumping through some hoops concerning
potential CPU hotplug) Xen will never use TSC as its clocksource.
Hence, by default, a Xen guest will not see PVCLOCK_TSC_STABLE_BIT set
in either the primary or secondary pvclock memory areas. This has
led to bugs in some guest kernels which only become evident if
PVCLOCK_TSC_STABLE_BIT *is* set in the pvclocks. Hence, to support
such guests, give the VMM a new Xen HVM config flag to tell KVM to
forcibly clear the bit in the Xen pvclocks.

Signed-off-by: Paul Durrant <pdurrant@amazon.com>
Reviewed-by: David Woodhouse <dwmw@amazon.co.uk>
Link: https://lore.kernel.org/r/20231102162128.2353459-1-paul@xen.org
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 Documentation/virt/kvm/api.rst |  6 ++++++
 arch/x86/kvm/x86.c             | 28 +++++++++++++++++++++++-----
 arch/x86/kvm/xen.c             |  9 ++++++++-
 include/uapi/linux/kvm.h       |  1 +
 4 files changed, 38 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 926241e23aeb..dca83c65d97f 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -8562,6 +8562,7 @@ PVHVM guests. Valid flags are::
   #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL		(1 << 4)
   #define KVM_XEN_HVM_CONFIG_EVTCHN_SEND		(1 << 5)
   #define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG	(1 << 6)
+  #define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE	(1 << 7)
 
 The KVM_XEN_HVM_CONFIG_HYPERCALL_MSR flag indicates that the KVM_XEN_HVM_CONFIG
 ioctl is available, for the guest to set its hypercall page.
@@ -8605,6 +8606,11 @@ behave more correctly, not using the XEN_RUNSTATE_UPDATE flag until/unless
 specifically enabled (by the guest making the hypercall, causing the VMM
 to enable the KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG attribute).
 
+The KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE flag indicates that KVM supports
+clearing the PVCLOCK_TSC_STABLE_BIT flag in Xen pvclock sources. This will be
+done when the KVM_CAP_XEN_HVM ioctl sets the
+KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE flag.
+
 8.31 KVM_CAP_PPC_MULTITCE
 -------------------------
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6d0772b47041..aa7cea9600b0 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3104,7 +3104,8 @@ u64 get_kvmclock_ns(struct kvm *kvm)
 
 static void kvm_setup_guest_pvclock(struct kvm_vcpu *v,
 				    struct gfn_to_pfn_cache *gpc,
-				    unsigned int offset)
+				    unsigned int offset,
+				    bool force_tsc_unstable)
 {
 	struct kvm_vcpu_arch *vcpu = &v->arch;
 	struct pvclock_vcpu_time_info *guest_hv_clock;
@@ -3141,6 +3142,10 @@ static void kvm_setup_guest_pvclock(struct kvm_vcpu *v,
 	}
 
 	memcpy(guest_hv_clock, &vcpu->hv_clock, sizeof(*guest_hv_clock));
+
+	if (force_tsc_unstable)
+		guest_hv_clock->flags &= ~PVCLOCK_TSC_STABLE_BIT;
+
 	smp_wmb();
 
 	guest_hv_clock->version = ++vcpu->hv_clock.version;
@@ -3161,6 +3166,16 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	u64 tsc_timestamp, host_tsc;
 	u8 pvclock_flags;
 	bool use_master_clock;
+#ifdef CONFIG_KVM_XEN
+	/*
+	 * For Xen guests we may need to override PVCLOCK_TSC_STABLE_BIT as unless
+	 * explicitly told to use TSC as its clocksource Xen will not set this bit.
+	 * This default behaviour led to bugs in some guest kernels which cause
+	 * problems if they observe PVCLOCK_TSC_STABLE_BIT in the pvclock flags.
+	 */
+	bool xen_pvclock_tsc_unstable =
+		ka->xen_hvm_config.flags & KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE;
+#endif
 
 	kernel_ns = 0;
 	host_tsc = 0;
@@ -3239,13 +3254,15 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	vcpu->hv_clock.flags = pvclock_flags;
 
 	if (vcpu->pv_time.active)
-		kvm_setup_guest_pvclock(v, &vcpu->pv_time, 0);
+		kvm_setup_guest_pvclock(v, &vcpu->pv_time, 0, false);
 #ifdef CONFIG_KVM_XEN
 	if (vcpu->xen.vcpu_info_cache.active)
 		kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_info_cache,
-					offsetof(struct compat_vcpu_info, time));
+					offsetof(struct compat_vcpu_info, time),
+					xen_pvclock_tsc_unstable);
 	if (vcpu->xen.vcpu_time_info_cache.active)
-		kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_time_info_cache, 0);
+		kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_time_info_cache, 0,
+					xen_pvclock_tsc_unstable);
 #endif
 	kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock);
 	return 0;
@@ -4646,7 +4663,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		    KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL |
 		    KVM_XEN_HVM_CONFIG_SHARED_INFO |
 		    KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL |
-		    KVM_XEN_HVM_CONFIG_EVTCHN_SEND;
+		    KVM_XEN_HVM_CONFIG_EVTCHN_SEND |
+		    KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE;
 		if (sched_info_on())
 			r |= KVM_XEN_HVM_CONFIG_RUNSTATE |
 			     KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG;
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index e53fad915a62..e43948b87f94 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -1162,7 +1162,9 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc)
 {
 	/* Only some feature flags need to be *enabled* by userspace */
 	u32 permitted_flags = KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL |
-		KVM_XEN_HVM_CONFIG_EVTCHN_SEND;
+		KVM_XEN_HVM_CONFIG_EVTCHN_SEND |
+		KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE;
+	u32 old_flags;
 
 	if (xhc->flags & ~permitted_flags)
 		return -EINVAL;
@@ -1183,9 +1185,14 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc)
 	else if (!xhc->msr && kvm->arch.xen_hvm_config.msr)
 		static_branch_slow_dec_deferred(&kvm_xen_enabled);
 
+	old_flags = kvm->arch.xen_hvm_config.flags;
 	memcpy(&kvm->arch.xen_hvm_config, xhc, sizeof(*xhc));
 
 	mutex_unlock(&kvm->arch.xen.xen_lock);
+
+	if ((old_flags ^ xhc->flags) & KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE)
+		kvm_make_all_cpus_request(kvm, KVM_REQ_CLOCK_UPDATE);
+
 	return 0;
 }
 
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index e9cb2df67a1d..175420b26e36 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1318,6 +1318,7 @@ struct kvm_x86_mce {
 #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL	(1 << 4)
 #define KVM_XEN_HVM_CONFIG_EVTCHN_SEND		(1 << 5)
 #define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG	(1 << 6)
+#define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE	(1 << 7)
 
 struct kvm_xen_hvm_config {
 	__u32 flags;
-- 
cgit v1.2.3


From 67b164a871af1d736f131fd6fe78a610909f06f3 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Tue, 28 Nov 2023 16:25:49 +0800
Subject: crypto: af_alg - Disallow multiple in-flight AIO requests

Having multiple in-flight AIO requests results in unpredictable
output because they all share the same IV.  Fix this by only allowing
one request at a time.

Fixes: 83094e5e9e49 ("crypto: af_alg - add async support to algif_aead")
Fixes: a596999b7ddf ("crypto: algif - change algif_skcipher to be asynchronous")
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/af_alg.c         | 14 +++++++++++++-
 include/crypto/if_alg.h |  3 +++
 2 files changed, 16 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index ea6fb8e89d06..68cc9290cabe 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -1116,9 +1116,13 @@ EXPORT_SYMBOL_GPL(af_alg_sendmsg);
 void af_alg_free_resources(struct af_alg_async_req *areq)
 {
 	struct sock *sk = areq->sk;
+	struct af_alg_ctx *ctx;
 
 	af_alg_free_areq_sgls(areq);
 	sock_kfree_s(sk, areq, areq->areqlen);
+
+	ctx = alg_sk(sk)->private;
+	ctx->inflight = false;
 }
 EXPORT_SYMBOL_GPL(af_alg_free_resources);
 
@@ -1188,11 +1192,19 @@ EXPORT_SYMBOL_GPL(af_alg_poll);
 struct af_alg_async_req *af_alg_alloc_areq(struct sock *sk,
 					   unsigned int areqlen)
 {
-	struct af_alg_async_req *areq = sock_kmalloc(sk, areqlen, GFP_KERNEL);
+	struct af_alg_ctx *ctx = alg_sk(sk)->private;
+	struct af_alg_async_req *areq;
+
+	/* Only one AIO request can be in flight. */
+	if (ctx->inflight)
+		return ERR_PTR(-EBUSY);
 
+	areq = sock_kmalloc(sk, areqlen, GFP_KERNEL);
 	if (unlikely(!areq))
 		return ERR_PTR(-ENOMEM);
 
+	ctx->inflight = true;
+
 	areq->areqlen = areqlen;
 	areq->sk = sk;
 	areq->first_rsgl.sgl.sgt.sgl = areq->first_rsgl.sgl.sgl;
diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h
index ef8ce86b1f78..08b803a4fcde 100644
--- a/include/crypto/if_alg.h
+++ b/include/crypto/if_alg.h
@@ -136,6 +136,7 @@ struct af_alg_async_req {
  *			recvmsg is invoked.
  * @init:		True if metadata has been sent.
  * @len:		Length of memory allocated for this data structure.
+ * @inflight:		Non-zero when AIO requests are in flight.
  */
 struct af_alg_ctx {
 	struct list_head tsgl_list;
@@ -154,6 +155,8 @@ struct af_alg_ctx {
 	bool init;
 
 	unsigned int len;
+
+	unsigned int inflight;
 };
 
 int af_alg_register_type(const struct af_alg_type *type);
-- 
cgit v1.2.3


From f76f0d7f20672611974d3cc705996751fc403734 Mon Sep 17 00:00:00 2001
From: Wenkai Lin <linwenkai6@hisilicon.com>
Date: Sat, 2 Dec 2023 17:17:18 +0800
Subject: crypto: hisilicon/qm - add a function to set qm algs

Extract a public function to set qm algs and remove
the similar code for setting qm algs in each module.

Signed-off-by: Wenkai Lin <linwenkai6@hisilicon.com>
Signed-off-by: Hao Fang <fanghao11@huawei.com>
Signed-off-by: Zhiqi Song <songzhiqi1@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/hisilicon/hpre/hpre_main.c | 42 +++-----------------------
 drivers/crypto/hisilicon/qm.c             | 36 +++++++++++++++++++++++
 drivers/crypto/hisilicon/sec2/sec_main.c  | 47 +++++------------------------
 drivers/crypto/hisilicon/zip/zip_main.c   | 49 +++++--------------------------
 include/linux/hisi_acc_qm.h               |  8 ++++-
 5 files changed, 62 insertions(+), 120 deletions(-)

(limited to 'include')

diff --git a/drivers/crypto/hisilicon/hpre/hpre_main.c b/drivers/crypto/hisilicon/hpre/hpre_main.c
index 56777099ef69..84c92d85d23d 100644
--- a/drivers/crypto/hisilicon/hpre/hpre_main.c
+++ b/drivers/crypto/hisilicon/hpre/hpre_main.c
@@ -118,8 +118,6 @@
 #define HPRE_DFX_COMMON2_LEN		0xE
 #define HPRE_DFX_CORE_LEN		0x43
 
-#define HPRE_DEV_ALG_MAX_LEN	256
-
 static const char hpre_name[] = "hisi_hpre";
 static struct dentry *hpre_debugfs_root;
 static const struct pci_device_id hpre_dev_ids[] = {
@@ -135,12 +133,7 @@ struct hpre_hw_error {
 	const char *msg;
 };
 
-struct hpre_dev_alg {
-	u32 alg_msk;
-	const char *alg;
-};
-
-static const struct hpre_dev_alg hpre_dev_algs[] = {
+static const struct qm_dev_alg hpre_dev_algs[] = {
 	{
 		.alg_msk = BIT(0),
 		.alg = "rsa\n"
@@ -362,35 +355,6 @@ bool hpre_check_alg_support(struct hisi_qm *qm, u32 alg)
 	return false;
 }
 
-static int hpre_set_qm_algs(struct hisi_qm *qm)
-{
-	struct device *dev = &qm->pdev->dev;
-	char *algs, *ptr;
-	u32 alg_msk;
-	int i;
-
-	if (!qm->use_sva)
-		return 0;
-
-	algs = devm_kzalloc(dev, HPRE_DEV_ALG_MAX_LEN * sizeof(char), GFP_KERNEL);
-	if (!algs)
-		return -ENOMEM;
-
-	alg_msk = hisi_qm_get_hw_info(qm, hpre_basic_info, HPRE_DEV_ALG_BITMAP_CAP, qm->cap_ver);
-
-	for (i = 0; i < ARRAY_SIZE(hpre_dev_algs); i++)
-		if (alg_msk & hpre_dev_algs[i].alg_msk)
-			strcat(algs, hpre_dev_algs[i].alg);
-
-	ptr = strrchr(algs, '\n');
-	if (ptr)
-		*ptr = '\0';
-
-	qm->uacce->algs = algs;
-
-	return 0;
-}
-
 static int hpre_diff_regs_show(struct seq_file *s, void *unused)
 {
 	struct hisi_qm *qm = s->private;
@@ -1141,6 +1105,7 @@ static void hpre_debugfs_exit(struct hisi_qm *qm)
 
 static int hpre_qm_init(struct hisi_qm *qm, struct pci_dev *pdev)
 {
+	u64 alg_msk;
 	int ret;
 
 	if (pdev->revision == QM_HW_V1) {
@@ -1171,7 +1136,8 @@ static int hpre_qm_init(struct hisi_qm *qm, struct pci_dev *pdev)
 		return ret;
 	}
 
-	ret = hpre_set_qm_algs(qm);
+	alg_msk = hisi_qm_get_hw_info(qm, hpre_basic_info, HPRE_DEV_ALG_BITMAP_CAP, qm->cap_ver);
+	ret = hisi_qm_set_algs(qm, alg_msk, hpre_dev_algs, ARRAY_SIZE(hpre_dev_algs));
 	if (ret) {
 		pci_err(pdev, "Failed to set hpre algs!\n");
 		hisi_qm_uninit(qm);
diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c
index 7ed079a9c929..4170c24c2ed1 100644
--- a/drivers/crypto/hisilicon/qm.c
+++ b/drivers/crypto/hisilicon/qm.c
@@ -234,6 +234,8 @@
 #define QM_QOS_MAX_CIR_U		6
 #define QM_AUTOSUSPEND_DELAY		3000
 
+#define QM_DEV_ALG_MAX_LEN		256
+
 #define QM_MK_CQC_DW3_V1(hop_num, pg_sz, buf_sz, cqe_sz) \
 	(((hop_num) << QM_CQ_HOP_NUM_SHIFT) | \
 	((pg_sz) << QM_CQ_PAGE_SIZE_SHIFT) | \
@@ -749,6 +751,40 @@ static void qm_get_xqc_depth(struct hisi_qm *qm, u16 *low_bits,
 	*high_bits = (depth >> QM_XQ_DEPTH_SHIFT) & QM_XQ_DEPTH_MASK;
 }
 
+int hisi_qm_set_algs(struct hisi_qm *qm, u64 alg_msk, const struct qm_dev_alg *dev_algs,
+		     u32 dev_algs_size)
+{
+	struct device *dev = &qm->pdev->dev;
+	char *algs, *ptr;
+	int i;
+
+	if (!qm->uacce)
+		return 0;
+
+	if (dev_algs_size >= QM_DEV_ALG_MAX_LEN) {
+		dev_err(dev, "algs size %u is equal or larger than %d.\n",
+			dev_algs_size, QM_DEV_ALG_MAX_LEN);
+		return -EINVAL;
+	}
+
+	algs = devm_kzalloc(dev, QM_DEV_ALG_MAX_LEN * sizeof(char), GFP_KERNEL);
+	if (!algs)
+		return -ENOMEM;
+
+	for (i = 0; i < dev_algs_size; i++)
+		if (alg_msk & dev_algs[i].alg_msk)
+			strcat(algs, dev_algs[i].alg);
+
+	ptr = strrchr(algs, '\n');
+	if (ptr) {
+		*ptr = '\0';
+		qm->uacce->algs = algs;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(hisi_qm_set_algs);
+
 static u32 qm_get_irq_num(struct hisi_qm *qm)
 {
 	if (qm->fun_type == QM_HW_PF)
diff --git a/drivers/crypto/hisilicon/sec2/sec_main.c b/drivers/crypto/hisilicon/sec2/sec_main.c
index 0e56a47eb862..2eceab7600ca 100644
--- a/drivers/crypto/hisilicon/sec2/sec_main.c
+++ b/drivers/crypto/hisilicon/sec2/sec_main.c
@@ -120,7 +120,6 @@
 					GENMASK_ULL(42, 25))
 #define SEC_AEAD_BITMAP			(GENMASK_ULL(7, 6) | GENMASK_ULL(18, 17) | \
 					GENMASK_ULL(45, 43))
-#define SEC_DEV_ALG_MAX_LEN		256
 
 struct sec_hw_error {
 	u32 int_msk;
@@ -132,11 +131,6 @@ struct sec_dfx_item {
 	u32 offset;
 };
 
-struct sec_dev_alg {
-	u64 alg_msk;
-	const char *algs;
-};
-
 static const char sec_name[] = "hisi_sec2";
 static struct dentry *sec_debugfs_root;
 
@@ -173,15 +167,15 @@ static const struct hisi_qm_cap_info sec_basic_info[] = {
 	{SEC_CORE4_ALG_BITMAP_HIGH, 0x3170, 0, GENMASK(31, 0), 0x3FFF, 0x3FFF, 0x3FFF},
 };
 
-static const struct sec_dev_alg sec_dev_algs[] = { {
+static const struct qm_dev_alg sec_dev_algs[] = { {
 		.alg_msk = SEC_CIPHER_BITMAP,
-		.algs = "cipher\n",
+		.alg = "cipher\n",
 	}, {
 		.alg_msk = SEC_DIGEST_BITMAP,
-		.algs = "digest\n",
+		.alg = "digest\n",
 	}, {
 		.alg_msk = SEC_AEAD_BITMAP,
-		.algs = "aead\n",
+		.alg = "aead\n",
 	},
 };
 
@@ -1077,37 +1071,9 @@ static int sec_pf_probe_init(struct sec_dev *sec)
 	return ret;
 }
 
-static int sec_set_qm_algs(struct hisi_qm *qm)
-{
-	struct device *dev = &qm->pdev->dev;
-	char *algs, *ptr;
-	u64 alg_mask;
-	int i;
-
-	if (!qm->use_sva)
-		return 0;
-
-	algs = devm_kzalloc(dev, SEC_DEV_ALG_MAX_LEN * sizeof(char), GFP_KERNEL);
-	if (!algs)
-		return -ENOMEM;
-
-	alg_mask = sec_get_alg_bitmap(qm, SEC_DEV_ALG_BITMAP_HIGH, SEC_DEV_ALG_BITMAP_LOW);
-
-	for (i = 0; i < ARRAY_SIZE(sec_dev_algs); i++)
-		if (alg_mask & sec_dev_algs[i].alg_msk)
-			strcat(algs, sec_dev_algs[i].algs);
-
-	ptr = strrchr(algs, '\n');
-	if (ptr)
-		*ptr = '\0';
-
-	qm->uacce->algs = algs;
-
-	return 0;
-}
-
 static int sec_qm_init(struct hisi_qm *qm, struct pci_dev *pdev)
 {
+	u64 alg_msk;
 	int ret;
 
 	qm->pdev = pdev;
@@ -1142,7 +1108,8 @@ static int sec_qm_init(struct hisi_qm *qm, struct pci_dev *pdev)
 		return ret;
 	}
 
-	ret = sec_set_qm_algs(qm);
+	alg_msk = sec_get_alg_bitmap(qm, SEC_DEV_ALG_BITMAP_HIGH, SEC_DEV_ALG_BITMAP_LOW);
+	ret = hisi_qm_set_algs(qm, alg_msk, sec_dev_algs, ARRAY_SIZE(sec_dev_algs));
 	if (ret) {
 		pci_err(qm->pdev, "Failed to set sec algs!\n");
 		hisi_qm_uninit(qm);
diff --git a/drivers/crypto/hisilicon/zip/zip_main.c b/drivers/crypto/hisilicon/zip/zip_main.c
index 07ab61c113ab..2934de25efa4 100644
--- a/drivers/crypto/hisilicon/zip/zip_main.c
+++ b/drivers/crypto/hisilicon/zip/zip_main.c
@@ -74,7 +74,6 @@
 #define HZIP_AXI_SHUTDOWN_ENABLE	BIT(14)
 #define HZIP_WR_PORT			BIT(11)
 
-#define HZIP_DEV_ALG_MAX_LEN		256
 #define HZIP_ALG_ZLIB_BIT		GENMASK(1, 0)
 #define HZIP_ALG_GZIP_BIT		GENMASK(3, 2)
 #define HZIP_ALG_DEFLATE_BIT		GENMASK(5, 4)
@@ -128,23 +127,18 @@ struct zip_dfx_item {
 	u32 offset;
 };
 
-struct zip_dev_alg {
-	u32 alg_msk;
-	const char *algs;
-};
-
-static const struct zip_dev_alg zip_dev_algs[] = { {
+static const struct qm_dev_alg zip_dev_algs[] = { {
 		.alg_msk = HZIP_ALG_ZLIB_BIT,
-		.algs = "zlib\n",
+		.alg = "zlib\n",
 	}, {
 		.alg_msk = HZIP_ALG_GZIP_BIT,
-		.algs = "gzip\n",
+		.alg = "gzip\n",
 	}, {
 		.alg_msk = HZIP_ALG_DEFLATE_BIT,
-		.algs = "deflate\n",
+		.alg = "deflate\n",
 	}, {
 		.alg_msk = HZIP_ALG_LZ77_BIT,
-		.algs = "lz77_zstd\n",
+		.alg = "lz77_zstd\n",
 	},
 };
 
@@ -478,35 +472,6 @@ static int hisi_zip_set_high_perf(struct hisi_qm *qm)
 	return ret;
 }
 
-static int hisi_zip_set_qm_algs(struct hisi_qm *qm)
-{
-	struct device *dev = &qm->pdev->dev;
-	char *algs, *ptr;
-	u32 alg_mask;
-	int i;
-
-	if (!qm->use_sva)
-		return 0;
-
-	algs = devm_kzalloc(dev, HZIP_DEV_ALG_MAX_LEN * sizeof(char), GFP_KERNEL);
-	if (!algs)
-		return -ENOMEM;
-
-	alg_mask = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_DEV_ALG_BITMAP, qm->cap_ver);
-
-	for (i = 0; i < ARRAY_SIZE(zip_dev_algs); i++)
-		if (alg_mask & zip_dev_algs[i].alg_msk)
-			strcat(algs, zip_dev_algs[i].algs);
-
-	ptr = strrchr(algs, '\n');
-	if (ptr)
-		*ptr = '\0';
-
-	qm->uacce->algs = algs;
-
-	return 0;
-}
-
 static void hisi_zip_open_sva_prefetch(struct hisi_qm *qm)
 {
 	u32 val;
@@ -1193,6 +1158,7 @@ static int hisi_zip_pf_probe_init(struct hisi_zip *hisi_zip)
 
 static int hisi_zip_qm_init(struct hisi_qm *qm, struct pci_dev *pdev)
 {
+	u64 alg_msk;
 	int ret;
 
 	qm->pdev = pdev;
@@ -1228,7 +1194,8 @@ static int hisi_zip_qm_init(struct hisi_qm *qm, struct pci_dev *pdev)
 		return ret;
 	}
 
-	ret = hisi_zip_set_qm_algs(qm);
+	alg_msk = hisi_qm_get_hw_info(qm, zip_basic_cap_info, ZIP_DEV_ALG_BITMAP, qm->cap_ver);
+	ret = hisi_qm_set_algs(qm, alg_msk, zip_dev_algs, ARRAY_SIZE(zip_dev_algs));
 	if (ret) {
 		pci_err(qm->pdev, "Failed to set zip algs!\n");
 		hisi_qm_uninit(qm);
diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h
index e3c0a1297b2c..cdc979f66dba 100644
--- a/include/linux/hisi_acc_qm.h
+++ b/include/linux/hisi_acc_qm.h
@@ -156,6 +156,11 @@ enum qm_cap_bits {
 	QM_SUPPORT_RPM,
 };
 
+struct qm_dev_alg {
+	u64 alg_msk;
+	const char *alg;
+};
+
 struct dfx_diff_registers {
 	u32 *regs;
 	u32 reg_offset;
@@ -361,7 +366,6 @@ struct hisi_qm {
 	struct work_struct rst_work;
 	struct work_struct cmd_process;
 
-	const char *algs;
 	bool use_sva;
 
 	resource_size_t phys_base;
@@ -559,6 +563,8 @@ void hisi_qm_regs_dump(struct seq_file *s, struct debugfs_regset32 *regset);
 u32 hisi_qm_get_hw_info(struct hisi_qm *qm,
 			const struct hisi_qm_cap_info *info_table,
 			u32 index, bool is_read);
+int hisi_qm_set_algs(struct hisi_qm *qm, u64 alg_msk, const struct qm_dev_alg *dev_algs,
+		     u32 dev_algs_size);
 
 /* Used by VFIO ACC live migration driver */
 struct pci_driver *hisi_sec_get_pf_driver(void);
-- 
cgit v1.2.3


From cabe13d0bd2efb8dd50ed2310f57b33e1a69a0d4 Mon Sep 17 00:00:00 2001
From: Zhiqi Song <songzhiqi1@huawei.com>
Date: Sat, 2 Dec 2023 17:17:19 +0800
Subject: crypto: hisilicon/qm - save capability registers in qm init process

In previous capability register implementation, qm irq related values
were read from capability registers dynamically when needed. But in
abnormal scenario, e.g. the core is timeout and the device needs to
soft reset and reset failed after disabling the MSE, the device can
not be removed normally, causing the following call trace:

	| Call trace:
        |  pci_irq_vector+0xfc/0x140
        |  hisi_qm_uninit+0x278/0x3b0 [hisi_qm]
        |  hpre_remove+0x16c/0x1c0 [hisi_hpre]
        |  pci_device_remove+0x6c/0x264
        |  device_release_driver_internal+0x1ec/0x3e0
        |  device_release_driver+0x3c/0x60
        |  pci_stop_bus_device+0xfc/0x22c
        |  pci_stop_and_remove_bus_device+0x38/0x70
        |  pci_iov_remove_virtfn+0x108/0x1c0
        |  sriov_disable+0x7c/0x1e4
        |  pci_disable_sriov+0x4c/0x6c
        |  hisi_qm_sriov_disable+0x90/0x160 [hisi_qm]
        |  hpre_remove+0x1a8/0x1c0 [hisi_hpre]
        |  pci_device_remove+0x6c/0x264
        |  device_release_driver_internal+0x1ec/0x3e0
        |  driver_detach+0x168/0x2d0
        |  bus_remove_driver+0xc0/0x230
        |  driver_unregister+0x58/0xdc
        |  pci_unregister_driver+0x40/0x220
        |  hpre_exit+0x34/0x64 [hisi_hpre]
        |  __arm64_sys_delete_module+0x374/0x620
        [...]

        | Call trace:
        |  free_msi_irqs+0x25c/0x300
        |  pci_disable_msi+0x19c/0x264
        |  pci_free_irq_vectors+0x4c/0x70
        |  hisi_qm_pci_uninit+0x44/0x90 [hisi_qm]
        |  hisi_qm_uninit+0x28c/0x3b0 [hisi_qm]
        |  hpre_remove+0x16c/0x1c0 [hisi_hpre]
        |  pci_device_remove+0x6c/0x264
        [...]

The reason for this call trace is that when the MSE is disabled, the value
of capability registers in the BAR space become invalid. This will make the
subsequent unregister process get the wrong irq vector through capability
registers and get the wrong irq number by pci_irq_vector().

So add a capability table structure to pre-store the valid value of the irq
information capability register in qm init process, avoid obtaining invalid
capability register value after the MSE is disabled.

Fixes: 3536cc55cada ("crypto: hisilicon/qm - support get device irq information from hardware registers")
Signed-off-by: Zhiqi Song <songzhiqi1@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/hisilicon/qm.c | 62 ++++++++++++++++++++++++++++++++++++-------
 include/linux/hisi_acc_qm.h   | 12 +++++++++
 2 files changed, 64 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c
index 4170c24c2ed1..d05ad2b16d0a 100644
--- a/drivers/crypto/hisilicon/qm.c
+++ b/drivers/crypto/hisilicon/qm.c
@@ -301,6 +301,13 @@ enum qm_basic_type {
 	QM_VF_IRQ_NUM_CAP,
 };
 
+enum qm_pre_store_cap_idx {
+	QM_EQ_IRQ_TYPE_CAP_IDX = 0x0,
+	QM_AEQ_IRQ_TYPE_CAP_IDX,
+	QM_ABN_IRQ_TYPE_CAP_IDX,
+	QM_PF2VF_IRQ_TYPE_CAP_IDX,
+};
+
 static const struct hisi_qm_cap_info qm_cap_info_comm[] = {
 	{QM_SUPPORT_DB_ISOLATION, 0x30,   0, BIT(0),  0x0, 0x0, 0x0},
 	{QM_SUPPORT_FUNC_QOS,     0x3100, 0, BIT(8),  0x0, 0x0, 0x1},
@@ -330,6 +337,13 @@ static const struct hisi_qm_cap_info qm_basic_info[] = {
 	{QM_VF_IRQ_NUM_CAP,     0x311c,   0,  GENMASK(15, 0), 0x1,       0x2,       0x3},
 };
 
+static const u32 qm_pre_store_caps[] = {
+	QM_EQ_IRQ_TYPE_CAP,
+	QM_AEQ_IRQ_TYPE_CAP,
+	QM_ABN_IRQ_TYPE_CAP,
+	QM_PF2VF_IRQ_TYPE_CAP,
+};
+
 struct qm_mailbox {
 	__le16 w0;
 	__le16 queue_num;
@@ -4774,7 +4788,7 @@ static void qm_unregister_abnormal_irq(struct hisi_qm *qm)
 	if (qm->fun_type == QM_HW_VF)
 		return;
 
-	val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_ABN_IRQ_TYPE_CAP, qm->cap_ver);
+	val = qm->cap_tables.qm_cap_table[QM_ABN_IRQ_TYPE_CAP_IDX].cap_val;
 	if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_ABN_IRQ_TYPE_MASK))
 		return;
 
@@ -4791,7 +4805,7 @@ static int qm_register_abnormal_irq(struct hisi_qm *qm)
 	if (qm->fun_type == QM_HW_VF)
 		return 0;
 
-	val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_ABN_IRQ_TYPE_CAP, qm->cap_ver);
+	val = qm->cap_tables.qm_cap_table[QM_ABN_IRQ_TYPE_CAP_IDX].cap_val;
 	if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_ABN_IRQ_TYPE_MASK))
 		return 0;
 
@@ -4808,7 +4822,7 @@ static void qm_unregister_mb_cmd_irq(struct hisi_qm *qm)
 	struct pci_dev *pdev = qm->pdev;
 	u32 irq_vector, val;
 
-	val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_PF2VF_IRQ_TYPE_CAP, qm->cap_ver);
+	val = qm->cap_tables.qm_cap_table[QM_PF2VF_IRQ_TYPE_CAP_IDX].cap_val;
 	if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_IRQ_TYPE_MASK))
 		return;
 
@@ -4822,7 +4836,7 @@ static int qm_register_mb_cmd_irq(struct hisi_qm *qm)
 	u32 irq_vector, val;
 	int ret;
 
-	val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_PF2VF_IRQ_TYPE_CAP, qm->cap_ver);
+	val = qm->cap_tables.qm_cap_table[QM_PF2VF_IRQ_TYPE_CAP_IDX].cap_val;
 	if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_IRQ_TYPE_MASK))
 		return 0;
 
@@ -4839,7 +4853,7 @@ static void qm_unregister_aeq_irq(struct hisi_qm *qm)
 	struct pci_dev *pdev = qm->pdev;
 	u32 irq_vector, val;
 
-	val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_AEQ_IRQ_TYPE_CAP, qm->cap_ver);
+	val = qm->cap_tables.qm_cap_table[QM_AEQ_IRQ_TYPE_CAP_IDX].cap_val;
 	if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_IRQ_TYPE_MASK))
 		return;
 
@@ -4853,7 +4867,7 @@ static int qm_register_aeq_irq(struct hisi_qm *qm)
 	u32 irq_vector, val;
 	int ret;
 
-	val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_AEQ_IRQ_TYPE_CAP, qm->cap_ver);
+	val = qm->cap_tables.qm_cap_table[QM_AEQ_IRQ_TYPE_CAP_IDX].cap_val;
 	if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_IRQ_TYPE_MASK))
 		return 0;
 
@@ -4871,7 +4885,7 @@ static void qm_unregister_eq_irq(struct hisi_qm *qm)
 	struct pci_dev *pdev = qm->pdev;
 	u32 irq_vector, val;
 
-	val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_EQ_IRQ_TYPE_CAP, qm->cap_ver);
+	val = qm->cap_tables.qm_cap_table[QM_EQ_IRQ_TYPE_CAP_IDX].cap_val;
 	if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_IRQ_TYPE_MASK))
 		return;
 
@@ -4885,7 +4899,7 @@ static int qm_register_eq_irq(struct hisi_qm *qm)
 	u32 irq_vector, val;
 	int ret;
 
-	val = hisi_qm_get_hw_info(qm, qm_basic_info, QM_EQ_IRQ_TYPE_CAP, qm->cap_ver);
+	val = qm->cap_tables.qm_cap_table[QM_EQ_IRQ_TYPE_CAP_IDX].cap_val;
 	if (!((val >> QM_IRQ_TYPE_SHIFT) & QM_IRQ_TYPE_MASK))
 		return 0;
 
@@ -4973,7 +4987,29 @@ static int qm_get_qp_num(struct hisi_qm *qm)
 	return 0;
 }
 
-static void qm_get_hw_caps(struct hisi_qm *qm)
+static int qm_pre_store_irq_type_caps(struct hisi_qm *qm)
+{
+	struct hisi_qm_cap_record *qm_cap;
+	struct pci_dev *pdev = qm->pdev;
+	size_t i, size;
+
+	size = ARRAY_SIZE(qm_pre_store_caps);
+	qm_cap = devm_kzalloc(&pdev->dev, sizeof(*qm_cap) * size, GFP_KERNEL);
+	if (!qm_cap)
+		return -ENOMEM;
+
+	for (i = 0; i < size; i++) {
+		qm_cap[i].type = qm_pre_store_caps[i];
+		qm_cap[i].cap_val = hisi_qm_get_hw_info(qm, qm_basic_info,
+							qm_pre_store_caps[i], qm->cap_ver);
+	}
+
+	qm->cap_tables.qm_cap_table = qm_cap;
+
+	return 0;
+}
+
+static int qm_get_hw_caps(struct hisi_qm *qm)
 {
 	const struct hisi_qm_cap_info *cap_info = qm->fun_type == QM_HW_PF ?
 						  qm_cap_info_pf : qm_cap_info_vf;
@@ -5004,6 +5040,9 @@ static void qm_get_hw_caps(struct hisi_qm *qm)
 		if (val)
 			set_bit(cap_info[i].type, &qm->caps);
 	}
+
+	/* Fetch and save the value of irq type related capability registers */
+	return qm_pre_store_irq_type_caps(qm);
 }
 
 static int qm_get_pci_res(struct hisi_qm *qm)
@@ -5025,7 +5064,10 @@ static int qm_get_pci_res(struct hisi_qm *qm)
 		goto err_request_mem_regions;
 	}
 
-	qm_get_hw_caps(qm);
+	ret = qm_get_hw_caps(qm);
+	if (ret)
+		goto err_ioremap;
+
 	if (test_bit(QM_SUPPORT_DB_ISOLATION, &qm->caps)) {
 		qm->db_interval = QM_QP_DB_INTERVAL;
 		qm->db_phys_base = pci_resource_start(pdev, PCI_BAR_4);
diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h
index cdc979f66dba..5f4c74facf6a 100644
--- a/include/linux/hisi_acc_qm.h
+++ b/include/linux/hisi_acc_qm.h
@@ -266,6 +266,16 @@ struct hisi_qm_cap_info {
 	u32 v3_val;
 };
 
+struct hisi_qm_cap_record {
+	u32 type;
+	u32 cap_val;
+};
+
+struct hisi_qm_cap_tables {
+	struct hisi_qm_cap_record *qm_cap_table;
+	struct hisi_qm_cap_record *dev_cap_table;
+};
+
 struct hisi_qm_list {
 	struct mutex lock;
 	struct list_head list;
@@ -376,6 +386,8 @@ struct hisi_qm {
 	u32 mb_qos;
 	u32 type_rate;
 	struct qm_err_isolate isolate_data;
+
+	struct hisi_qm_cap_tables cap_tables;
 };
 
 struct hisi_qp_status {
-- 
cgit v1.2.3


From 0ae4dcc1ebf63118364d540b84c70352e8b2b2a4 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Mon, 27 Nov 2023 18:14:08 +0800
Subject: crypto: skcipher - Add internal state support

Unlike chaining modes such as CBC, stream ciphers other than CTR
usually hold an internal state that must be preserved if the
operation is to be done piecemeal.  This has not been represented
in the API, resulting in the inability to split up stream cipher
operations.

This patch adds the basic representation of an internal state to
skcipher and lskcipher.  In the interest of backwards compatibility,
the default has been set such that existing users are assumed to
be operating in one go as opposed to piecemeal.

With the new API, each lskcipher/skcipher algorithm has a new
attribute called statesize.  For skcipher, this is the size of
the buffer that can be exported or imported similar to ahash.
For lskcipher, instead of providing a buffer of ivsize, the user
now has to provide a buffer of ivsize + statesize.

Each skcipher operation is assumed to be final as they are now,
but this may be overridden with a request flag.  When the override
occurs, the user may then export the partial state and reimport
it later.

For lskcipher operations this is reversed.  All operations are
not final and the state will be exported unless the FINAL bit is
set.  However, the CONT bit still has to be set for the state
to be used.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/arc4.c             |  2 +-
 crypto/cbc.c              |  6 ++--
 crypto/ecb.c              | 10 +++---
 crypto/lskcipher.c        | 14 ++++----
 include/crypto/skcipher.h | 84 ++++++++++++++++++++++++++++++++++++++++++-----
 5 files changed, 94 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/crypto/arc4.c b/crypto/arc4.c
index eb3590dc9282..2150f94e7d03 100644
--- a/crypto/arc4.c
+++ b/crypto/arc4.c
@@ -23,7 +23,7 @@ static int crypto_arc4_setkey(struct crypto_lskcipher *tfm, const u8 *in_key,
 }
 
 static int crypto_arc4_crypt(struct crypto_lskcipher *tfm, const u8 *src,
-			     u8 *dst, unsigned nbytes, u8 *iv, bool final)
+			     u8 *dst, unsigned nbytes, u8 *iv, u32 flags)
 {
 	struct arc4_ctx *ctx = crypto_lskcipher_ctx(tfm);
 
diff --git a/crypto/cbc.c b/crypto/cbc.c
index 28345b8d921c..eedddef9ce40 100644
--- a/crypto/cbc.c
+++ b/crypto/cbc.c
@@ -51,9 +51,10 @@ out:
 }
 
 static int crypto_cbc_encrypt(struct crypto_lskcipher *tfm, const u8 *src,
-			      u8 *dst, unsigned len, u8 *iv, bool final)
+			      u8 *dst, unsigned len, u8 *iv, u32 flags)
 {
 	struct crypto_lskcipher **ctx = crypto_lskcipher_ctx(tfm);
+	bool final = flags & CRYPTO_LSKCIPHER_FLAG_FINAL;
 	struct crypto_lskcipher *cipher = *ctx;
 	int rem;
 
@@ -119,9 +120,10 @@ out:
 }
 
 static int crypto_cbc_decrypt(struct crypto_lskcipher *tfm, const u8 *src,
-			      u8 *dst, unsigned len, u8 *iv, bool final)
+			      u8 *dst, unsigned len, u8 *iv, u32 flags)
 {
 	struct crypto_lskcipher **ctx = crypto_lskcipher_ctx(tfm);
+	bool final = flags & CRYPTO_LSKCIPHER_FLAG_FINAL;
 	struct crypto_lskcipher *cipher = *ctx;
 	int rem;
 
diff --git a/crypto/ecb.c b/crypto/ecb.c
index cc7625d1a475..e3a67789050e 100644
--- a/crypto/ecb.c
+++ b/crypto/ecb.c
@@ -32,22 +32,24 @@ static int crypto_ecb_crypt(struct crypto_cipher *cipher, const u8 *src,
 }
 
 static int crypto_ecb_encrypt2(struct crypto_lskcipher *tfm, const u8 *src,
-			       u8 *dst, unsigned len, u8 *iv, bool final)
+			       u8 *dst, unsigned len, u8 *iv, u32 flags)
 {
 	struct crypto_cipher **ctx = crypto_lskcipher_ctx(tfm);
 	struct crypto_cipher *cipher = *ctx;
 
-	return crypto_ecb_crypt(cipher, src, dst, len, final,
+	return crypto_ecb_crypt(cipher, src, dst, len,
+				flags & CRYPTO_LSKCIPHER_FLAG_FINAL,
 				crypto_cipher_alg(cipher)->cia_encrypt);
 }
 
 static int crypto_ecb_decrypt2(struct crypto_lskcipher *tfm, const u8 *src,
-			       u8 *dst, unsigned len, u8 *iv, bool final)
+			       u8 *dst, unsigned len, u8 *iv, u32 flags)
 {
 	struct crypto_cipher **ctx = crypto_lskcipher_ctx(tfm);
 	struct crypto_cipher *cipher = *ctx;
 
-	return crypto_ecb_crypt(cipher, src, dst, len, final,
+	return crypto_ecb_crypt(cipher, src, dst, len,
+				flags & CRYPTO_LSKCIPHER_FLAG_FINAL,
 				crypto_cipher_alg(cipher)->cia_decrypt);
 }
 
diff --git a/crypto/lskcipher.c b/crypto/lskcipher.c
index 9edc89730951..51bcf85070c7 100644
--- a/crypto/lskcipher.c
+++ b/crypto/lskcipher.c
@@ -88,7 +88,7 @@ EXPORT_SYMBOL_GPL(crypto_lskcipher_setkey);
 static int crypto_lskcipher_crypt_unaligned(
 	struct crypto_lskcipher *tfm, const u8 *src, u8 *dst, unsigned len,
 	u8 *iv, int (*crypt)(struct crypto_lskcipher *tfm, const u8 *src,
-			     u8 *dst, unsigned len, u8 *iv, bool final))
+			     u8 *dst, unsigned len, u8 *iv, u32 flags))
 {
 	unsigned ivsize = crypto_lskcipher_ivsize(tfm);
 	unsigned bs = crypto_lskcipher_blocksize(tfm);
@@ -119,7 +119,7 @@ static int crypto_lskcipher_crypt_unaligned(
 			chunk &= ~(cs - 1);
 
 		memcpy(p, src, chunk);
-		err = crypt(tfm, p, p, chunk, tiv, true);
+		err = crypt(tfm, p, p, chunk, tiv, CRYPTO_LSKCIPHER_FLAG_FINAL);
 		if (err)
 			goto out;
 
@@ -143,7 +143,7 @@ static int crypto_lskcipher_crypt(struct crypto_lskcipher *tfm, const u8 *src,
 				  int (*crypt)(struct crypto_lskcipher *tfm,
 					       const u8 *src, u8 *dst,
 					       unsigned len, u8 *iv,
-					       bool final))
+					       u32 flags))
 {
 	unsigned long alignmask = crypto_lskcipher_alignmask(tfm);
 	struct lskcipher_alg *alg = crypto_lskcipher_alg(tfm);
@@ -156,7 +156,7 @@ static int crypto_lskcipher_crypt(struct crypto_lskcipher *tfm, const u8 *src,
 		goto out;
 	}
 
-	ret = crypt(tfm, src, dst, len, iv, true);
+	ret = crypt(tfm, src, dst, len, iv, CRYPTO_LSKCIPHER_FLAG_FINAL);
 
 out:
 	return crypto_lskcipher_errstat(alg, ret);
@@ -198,7 +198,7 @@ static int crypto_lskcipher_crypt_sg(struct skcipher_request *req,
 				     int (*crypt)(struct crypto_lskcipher *tfm,
 						  const u8 *src, u8 *dst,
 						  unsigned len, u8 *iv,
-						  bool final))
+						  u32 flags))
 {
 	struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req);
 	struct crypto_lskcipher **ctx = crypto_skcipher_ctx(skcipher);
@@ -210,7 +210,9 @@ static int crypto_lskcipher_crypt_sg(struct skcipher_request *req,
 
 	while (walk.nbytes) {
 		err = crypt(tfm, walk.src.virt.addr, walk.dst.virt.addr,
-			    walk.nbytes, walk.iv, walk.nbytes == walk.total);
+			    walk.nbytes, walk.iv,
+			    walk.nbytes == walk.total ?
+			    CRYPTO_LSKCIPHER_FLAG_FINAL : 0);
 		err = skcipher_walk_done(&walk, err);
 	}
 
diff --git a/include/crypto/skcipher.h b/include/crypto/skcipher.h
index ea18af48346b..5302f8f33afc 100644
--- a/include/crypto/skcipher.h
+++ b/include/crypto/skcipher.h
@@ -15,6 +15,17 @@
 #include <linux/string.h>
 #include <linux/types.h>
 
+/* Set this bit if the lskcipher operation is a continuation. */
+#define CRYPTO_LSKCIPHER_FLAG_CONT	0x00000001
+/* Set this bit if the lskcipher operation is final. */
+#define CRYPTO_LSKCIPHER_FLAG_FINAL	0x00000002
+/* The bit CRYPTO_TFM_REQ_MAY_SLEEP can also be set if needed. */
+
+/* Set this bit if the skcipher operation is a continuation. */
+#define CRYPTO_SKCIPHER_REQ_CONT	0x00000001
+/* Set this bit if the skcipher operation is not final. */
+#define CRYPTO_SKCIPHER_REQ_NOTFINAL	0x00000002
+
 struct scatterlist;
 
 /**
@@ -91,6 +102,7 @@ struct crypto_istat_cipher {
  *	    IV of exactly that size to perform the encrypt or decrypt operation.
  * @chunksize: Equal to the block size except for stream ciphers such as
  *	       CTR where it is set to the underlying block size.
+ * @statesize: Size of the internal state for the algorithm.
  * @stat: Statistics for cipher algorithm
  * @base: Definition of a generic crypto algorithm.
  */
@@ -99,6 +111,7 @@ struct crypto_istat_cipher {
 	unsigned int max_keysize;	\
 	unsigned int ivsize;		\
 	unsigned int chunksize;		\
+	unsigned int statesize;		\
 					\
 	SKCIPHER_ALG_COMMON_STAT	\
 					\
@@ -141,6 +154,17 @@ struct skcipher_alg_common SKCIPHER_ALG_COMMON;
  *	     be called in parallel with the same transformation object.
  * @decrypt: Decrypt a single block. This is a reverse counterpart to @encrypt
  *	     and the conditions are exactly the same.
+ * @export: Export partial state of the transformation. This function dumps the
+ *	    entire state of the ongoing transformation into a provided block of
+ *	    data so it can be @import 'ed back later on. This is useful in case
+ *	    you want to save partial result of the transformation after
+ *	    processing certain amount of data and reload this partial result
+ *	    multiple times later on for multiple re-use. No data processing
+ *	    happens at this point.
+ * @import: Import partial state of the transformation. This function loads the
+ *	    entire state of the ongoing transformation from a provided block of
+ *	    data so the transformation can continue from this point onward. No
+ *	    data processing happens at this point.
  * @init: Initialize the cryptographic transformation object. This function
  *	  is used to initialize the cryptographic transformation object.
  *	  This function is called only once at the instantiation time, right
@@ -170,6 +194,8 @@ struct skcipher_alg {
 	              unsigned int keylen);
 	int (*encrypt)(struct skcipher_request *req);
 	int (*decrypt)(struct skcipher_request *req);
+	int (*export)(struct skcipher_request *req, void *out);
+	int (*import)(struct skcipher_request *req, const void *in);
 	int (*init)(struct crypto_skcipher *tfm);
 	void (*exit)(struct crypto_skcipher *tfm);
 
@@ -200,6 +226,9 @@ struct skcipher_alg {
  *	     may be left over if length is not a multiple of blocks
  *	     and there is more to come (final == false).  The number of
  *	     left-over bytes should be returned in case of success.
+ *	     The siv field shall be as long as ivsize + statesize with
+ *	     the IV placed at the front.  The state will be used by the
+ *	     algorithm internally.
  * @decrypt: Decrypt a number of bytes. This is a reverse counterpart to
  *	     @encrypt and the conditions are exactly the same.
  * @init: Initialize the cryptographic transformation object. This function
@@ -215,9 +244,9 @@ struct lskcipher_alg {
 	int (*setkey)(struct crypto_lskcipher *tfm, const u8 *key,
 	              unsigned int keylen);
 	int (*encrypt)(struct crypto_lskcipher *tfm, const u8 *src,
-		       u8 *dst, unsigned len, u8 *iv, bool final);
+		       u8 *dst, unsigned len, u8 *siv, u32 flags);
 	int (*decrypt)(struct crypto_lskcipher *tfm, const u8 *src,
-		       u8 *dst, unsigned len, u8 *iv, bool final);
+		       u8 *dst, unsigned len, u8 *siv, u32 flags);
 	int (*init)(struct crypto_lskcipher *tfm);
 	void (*exit)(struct crypto_lskcipher *tfm);
 
@@ -496,6 +525,40 @@ static inline unsigned int crypto_lskcipher_chunksize(
 	return crypto_lskcipher_alg(tfm)->co.chunksize;
 }
 
+/**
+ * crypto_skcipher_statesize() - obtain state size
+ * @tfm: cipher handle
+ *
+ * Some algorithms cannot be chained with the IV alone.  They carry
+ * internal state which must be replicated if data is to be processed
+ * incrementally.  The size of that state can be obtained with this
+ * function.
+ *
+ * Return: state size in bytes
+ */
+static inline unsigned int crypto_skcipher_statesize(
+	struct crypto_skcipher *tfm)
+{
+	return crypto_skcipher_alg_common(tfm)->statesize;
+}
+
+/**
+ * crypto_lskcipher_statesize() - obtain state size
+ * @tfm: cipher handle
+ *
+ * Some algorithms cannot be chained with the IV alone.  They carry
+ * internal state which must be replicated if data is to be processed
+ * incrementally.  The size of that state can be obtained with this
+ * function.
+ *
+ * Return: state size in bytes
+ */
+static inline unsigned int crypto_lskcipher_statesize(
+	struct crypto_lskcipher *tfm)
+{
+	return crypto_lskcipher_alg(tfm)->co.statesize;
+}
+
 static inline unsigned int crypto_sync_skcipher_blocksize(
 	struct crypto_sync_skcipher *tfm)
 {
@@ -689,9 +752,10 @@ int crypto_skcipher_decrypt(struct skcipher_request *req);
  * @src: source buffer
  * @dst: destination buffer
  * @len: number of bytes to process
- * @iv: IV for the cipher operation which must comply with the IV size defined
- *      by crypto_lskcipher_ivsize
- *
+ * @siv: IV + state for the cipher operation.  The length of the IV must
+ *	 comply with the IV size defined by crypto_lskcipher_ivsize.  The
+ *	 IV is then followed with a buffer with the length as specified by
+ *	 crypto_lskcipher_statesize.
  * Encrypt plaintext data using the lskcipher handle.
  *
  * Return: >=0 if the cipher operation was successful, if positive
@@ -699,7 +763,7 @@ int crypto_skcipher_decrypt(struct skcipher_request *req);
  *	   < 0 if an error occurred
  */
 int crypto_lskcipher_encrypt(struct crypto_lskcipher *tfm, const u8 *src,
-			     u8 *dst, unsigned len, u8 *iv);
+			     u8 *dst, unsigned len, u8 *siv);
 
 /**
  * crypto_lskcipher_decrypt() - decrypt ciphertext
@@ -707,8 +771,10 @@ int crypto_lskcipher_encrypt(struct crypto_lskcipher *tfm, const u8 *src,
  * @src: source buffer
  * @dst: destination buffer
  * @len: number of bytes to process
- * @iv: IV for the cipher operation which must comply with the IV size defined
- *      by crypto_lskcipher_ivsize
+ * @siv: IV + state for the cipher operation.  The length of the IV must
+ *	 comply with the IV size defined by crypto_lskcipher_ivsize.  The
+ *	 IV is then followed with a buffer with the length as specified by
+ *	 crypto_lskcipher_statesize.
  *
  * Decrypt ciphertext data using the lskcipher handle.
  *
@@ -717,7 +783,7 @@ int crypto_lskcipher_encrypt(struct crypto_lskcipher *tfm, const u8 *src,
  *	   < 0 if an error occurred
  */
 int crypto_lskcipher_decrypt(struct crypto_lskcipher *tfm, const u8 *src,
-			     u8 *dst, unsigned len, u8 *iv);
+			     u8 *dst, unsigned len, u8 *siv);
 
 /**
  * DOC: Symmetric Key Cipher Request Handle
-- 
cgit v1.2.3


From 662ea18d089ba6fa02859fbd64f2aa78d88c6648 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Tue, 28 Nov 2023 14:33:19 +0800
Subject: crypto: skcipher - Make use of internal state

This patch adds code to the skcipher/lskcipher API to make use
of the internal state if present.  In particular, the skcipher
lskcipher wrapper will allocate a buffer for the IV/state and
feed that to the underlying lskcipher algorithm.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/lskcipher.c        | 34 ++++++++++++++++----
 crypto/skcipher.c         | 80 +++++++++++++++++++++++++++++++++++++++++++++--
 include/crypto/skcipher.h | 33 +++++++++++++++++++
 3 files changed, 139 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/crypto/lskcipher.c b/crypto/lskcipher.c
index 51bcf85070c7..a06008e112f3 100644
--- a/crypto/lskcipher.c
+++ b/crypto/lskcipher.c
@@ -90,6 +90,7 @@ static int crypto_lskcipher_crypt_unaligned(
 	u8 *iv, int (*crypt)(struct crypto_lskcipher *tfm, const u8 *src,
 			     u8 *dst, unsigned len, u8 *iv, u32 flags))
 {
+	unsigned statesize = crypto_lskcipher_statesize(tfm);
 	unsigned ivsize = crypto_lskcipher_ivsize(tfm);
 	unsigned bs = crypto_lskcipher_blocksize(tfm);
 	unsigned cs = crypto_lskcipher_chunksize(tfm);
@@ -104,7 +105,7 @@ static int crypto_lskcipher_crypt_unaligned(
 	if (!tiv)
 		return -ENOMEM;
 
-	memcpy(tiv, iv, ivsize);
+	memcpy(tiv, iv, ivsize + statesize);
 
 	p = kmalloc(PAGE_SIZE, GFP_ATOMIC);
 	err = -ENOMEM;
@@ -132,7 +133,7 @@ static int crypto_lskcipher_crypt_unaligned(
 	err = len ? -EINVAL : 0;
 
 out:
-	memcpy(iv, tiv, ivsize);
+	memcpy(iv, tiv, ivsize + statesize);
 	kfree_sensitive(p);
 	kfree_sensitive(tiv);
 	return err;
@@ -197,25 +198,45 @@ EXPORT_SYMBOL_GPL(crypto_lskcipher_decrypt);
 static int crypto_lskcipher_crypt_sg(struct skcipher_request *req,
 				     int (*crypt)(struct crypto_lskcipher *tfm,
 						  const u8 *src, u8 *dst,
-						  unsigned len, u8 *iv,
+						  unsigned len, u8 *ivs,
 						  u32 flags))
 {
 	struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req);
 	struct crypto_lskcipher **ctx = crypto_skcipher_ctx(skcipher);
+	u8 *ivs = skcipher_request_ctx(req);
 	struct crypto_lskcipher *tfm = *ctx;
 	struct skcipher_walk walk;
+	unsigned ivsize;
+	u32 flags;
 	int err;
 
+	ivsize = crypto_lskcipher_ivsize(tfm);
+	ivs = PTR_ALIGN(ivs, crypto_skcipher_alignmask(skcipher) + 1);
+
+	flags = req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP;
+
+	if (req->base.flags & CRYPTO_SKCIPHER_REQ_CONT)
+		flags |= CRYPTO_LSKCIPHER_FLAG_CONT;
+	else
+		memcpy(ivs, req->iv, ivsize);
+
+	if (!(req->base.flags & CRYPTO_SKCIPHER_REQ_NOTFINAL))
+		flags |= CRYPTO_LSKCIPHER_FLAG_FINAL;
+
 	err = skcipher_walk_virt(&walk, req, false);
 
 	while (walk.nbytes) {
 		err = crypt(tfm, walk.src.virt.addr, walk.dst.virt.addr,
-			    walk.nbytes, walk.iv,
-			    walk.nbytes == walk.total ?
-			    CRYPTO_LSKCIPHER_FLAG_FINAL : 0);
+			    walk.nbytes, ivs,
+			    flags & ~(walk.nbytes == walk.total ?
+			    0 : CRYPTO_LSKCIPHER_FLAG_FINAL));
 		err = skcipher_walk_done(&walk, err);
+		flags |= CRYPTO_LSKCIPHER_FLAG_CONT;
 	}
 
+	if (flags & CRYPTO_LSKCIPHER_FLAG_FINAL)
+		memcpy(req->iv, ivs, ivsize);
+
 	return err;
 }
 
@@ -278,6 +299,7 @@ static void __maybe_unused crypto_lskcipher_show(
 	seq_printf(m, "max keysize  : %u\n", skcipher->co.max_keysize);
 	seq_printf(m, "ivsize       : %u\n", skcipher->co.ivsize);
 	seq_printf(m, "chunksize    : %u\n", skcipher->co.chunksize);
+	seq_printf(m, "statesize    : %u\n", skcipher->co.statesize);
 }
 
 static int __maybe_unused crypto_lskcipher_report(
diff --git a/crypto/skcipher.c b/crypto/skcipher.c
index ac8b8c042654..bc70e159d27d 100644
--- a/crypto/skcipher.c
+++ b/crypto/skcipher.c
@@ -698,6 +698,64 @@ int crypto_skcipher_decrypt(struct skcipher_request *req)
 }
 EXPORT_SYMBOL_GPL(crypto_skcipher_decrypt);
 
+static int crypto_lskcipher_export(struct skcipher_request *req, void *out)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	u8 *ivs = skcipher_request_ctx(req);
+
+	ivs = PTR_ALIGN(ivs, crypto_skcipher_alignmask(tfm) + 1);
+
+	memcpy(out, ivs + crypto_skcipher_ivsize(tfm),
+	       crypto_skcipher_statesize(tfm));
+
+	return 0;
+}
+
+static int crypto_lskcipher_import(struct skcipher_request *req, const void *in)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	u8 *ivs = skcipher_request_ctx(req);
+
+	ivs = PTR_ALIGN(ivs, crypto_skcipher_alignmask(tfm) + 1);
+
+	memcpy(ivs + crypto_skcipher_ivsize(tfm), in,
+	       crypto_skcipher_statesize(tfm));
+
+	return 0;
+}
+
+static int skcipher_noexport(struct skcipher_request *req, void *out)
+{
+	return 0;
+}
+
+static int skcipher_noimport(struct skcipher_request *req, const void *in)
+{
+	return 0;
+}
+
+int crypto_skcipher_export(struct skcipher_request *req, void *out)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct skcipher_alg *alg = crypto_skcipher_alg(tfm);
+
+	if (alg->co.base.cra_type != &crypto_skcipher_type)
+		return crypto_lskcipher_export(req, out);
+	return alg->export(req, out);
+}
+EXPORT_SYMBOL_GPL(crypto_skcipher_export);
+
+int crypto_skcipher_import(struct skcipher_request *req, const void *in)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct skcipher_alg *alg = crypto_skcipher_alg(tfm);
+
+	if (alg->co.base.cra_type != &crypto_skcipher_type)
+		return crypto_lskcipher_import(req, in);
+	return alg->import(req, in);
+}
+EXPORT_SYMBOL_GPL(crypto_skcipher_import);
+
 static void crypto_skcipher_exit_tfm(struct crypto_tfm *tfm)
 {
 	struct crypto_skcipher *skcipher = __crypto_skcipher_cast(tfm);
@@ -713,8 +771,17 @@ static int crypto_skcipher_init_tfm(struct crypto_tfm *tfm)
 
 	skcipher_set_needkey(skcipher);
 
-	if (tfm->__crt_alg->cra_type != &crypto_skcipher_type)
+	if (tfm->__crt_alg->cra_type != &crypto_skcipher_type) {
+		unsigned am = crypto_skcipher_alignmask(skcipher);
+		unsigned reqsize;
+
+		reqsize = am & ~(crypto_tfm_ctx_alignment() - 1);
+		reqsize += crypto_skcipher_ivsize(skcipher);
+		reqsize += crypto_skcipher_statesize(skcipher);
+		crypto_skcipher_set_reqsize(skcipher, reqsize);
+
 		return crypto_init_lskcipher_ops_sg(tfm);
+	}
 
 	if (alg->exit)
 		skcipher->base.exit = crypto_skcipher_exit_tfm;
@@ -756,6 +823,7 @@ static void crypto_skcipher_show(struct seq_file *m, struct crypto_alg *alg)
 	seq_printf(m, "ivsize       : %u\n", skcipher->ivsize);
 	seq_printf(m, "chunksize    : %u\n", skcipher->chunksize);
 	seq_printf(m, "walksize     : %u\n", skcipher->walksize);
+	seq_printf(m, "statesize    : %u\n", skcipher->statesize);
 }
 
 static int __maybe_unused crypto_skcipher_report(
@@ -870,7 +938,9 @@ int skcipher_prepare_alg_common(struct skcipher_alg_common *alg)
 	struct crypto_istat_cipher *istat = skcipher_get_stat_common(alg);
 	struct crypto_alg *base = &alg->base;
 
-	if (alg->ivsize > PAGE_SIZE / 8 || alg->chunksize > PAGE_SIZE / 8)
+	if (alg->ivsize > PAGE_SIZE / 8 || alg->chunksize > PAGE_SIZE / 8 ||
+	    alg->statesize > PAGE_SIZE / 2 ||
+	    (alg->ivsize + alg->statesize) > PAGE_SIZE / 2)
 		return -EINVAL;
 
 	if (!alg->chunksize)
@@ -899,6 +969,12 @@ static int skcipher_prepare_alg(struct skcipher_alg *alg)
 	if (!alg->walksize)
 		alg->walksize = alg->chunksize;
 
+	if (!alg->statesize) {
+		alg->import = skcipher_noimport;
+		alg->export = skcipher_noexport;
+	} else if (!(alg->import && alg->export))
+		return -EINVAL;
+
 	base->cra_type = &crypto_skcipher_type;
 	base->cra_flags |= CRYPTO_ALG_TYPE_SKCIPHER;
 
diff --git a/include/crypto/skcipher.h b/include/crypto/skcipher.h
index 5302f8f33afc..f881740df194 100644
--- a/include/crypto/skcipher.h
+++ b/include/crypto/skcipher.h
@@ -746,6 +746,39 @@ int crypto_skcipher_encrypt(struct skcipher_request *req);
  */
 int crypto_skcipher_decrypt(struct skcipher_request *req);
 
+/**
+ * crypto_skcipher_export() - export partial state
+ * @req: reference to the skcipher_request handle that holds all information
+ *	 needed to perform the operation
+ * @out: output buffer of sufficient size that can hold the state
+ *
+ * Export partial state of the transformation. This function dumps the
+ * entire state of the ongoing transformation into a provided block of
+ * data so it can be @import 'ed back later on. This is useful in case
+ * you want to save partial result of the transformation after
+ * processing certain amount of data and reload this partial result
+ * multiple times later on for multiple re-use. No data processing
+ * happens at this point.
+ *
+ * Return: 0 if the cipher operation was successful; < 0 if an error occurred
+ */
+int crypto_skcipher_export(struct skcipher_request *req, void *out);
+
+/**
+ * crypto_skcipher_import() - import partial state
+ * @req: reference to the skcipher_request handle that holds all information
+ *	 needed to perform the operation
+ * @in: buffer holding the state
+ *
+ * Import partial state of the transformation. This function loads the
+ * entire state of the ongoing transformation from a provided block of
+ * data so the transformation can continue from this point onward. No
+ * data processing happens at this point.
+ *
+ * Return: 0 if the cipher operation was successful; < 0 if an error occurred
+ */
+int crypto_skcipher_import(struct skcipher_request *req, const void *in);
+
 /**
  * crypto_lskcipher_encrypt() - encrypt plaintext
  * @tfm: lskcipher handle
-- 
cgit v1.2.3


From 99bd99d3e3a7f73c1c01ef510d48730b3bdd2c4a Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Wed, 29 Nov 2023 12:27:04 +0800
Subject: crypto: algif_skcipher - Fix stream cipher chaining

Unlike algif_aead which is always issued in one go (thus limiting
the maximum size of the request), algif_skcipher has always allowed
unlimited input data by cutting them up as necessary and feeding
the fragments to the underlying algorithm one at a time.

However, because of deficiencies in the API, this has been broken
for most stream ciphers such as arc4 or chacha.  This is because
they have an internal state in addition to the IV that must be
preserved in order to continue processing.

Fix this by using the new skcipher state API.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/algif_skcipher.c | 72 ++++++++++++++++++++++++++++++++++++++++++++++---
 include/crypto/if_alg.h |  2 ++
 2 files changed, 71 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index 9ada9b741af8..02cea2149504 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -47,6 +47,52 @@ static int skcipher_sendmsg(struct socket *sock, struct msghdr *msg,
 	return af_alg_sendmsg(sock, msg, size, ivsize);
 }
 
+static int algif_skcipher_export(struct sock *sk, struct skcipher_request *req)
+{
+	struct alg_sock *ask = alg_sk(sk);
+	struct crypto_skcipher *tfm;
+	struct af_alg_ctx *ctx;
+	struct alg_sock *pask;
+	unsigned statesize;
+	struct sock *psk;
+	int err;
+
+	if (!(req->base.flags & CRYPTO_SKCIPHER_REQ_NOTFINAL))
+		return 0;
+
+	ctx = ask->private;
+	psk = ask->parent;
+	pask = alg_sk(psk);
+	tfm = pask->private;
+
+	statesize = crypto_skcipher_statesize(tfm);
+	ctx->state = sock_kmalloc(sk, statesize, GFP_ATOMIC);
+	if (!ctx->state)
+		return -ENOMEM;
+
+	err = crypto_skcipher_export(req, ctx->state);
+	if (err) {
+		sock_kzfree_s(sk, ctx->state, statesize);
+		ctx->state = NULL;
+	}
+
+	return err;
+}
+
+static void algif_skcipher_done(void *data, int err)
+{
+	struct af_alg_async_req *areq = data;
+	struct sock *sk = areq->sk;
+
+	if (err)
+		goto out;
+
+	err = algif_skcipher_export(sk, &areq->cra_u.skcipher_req);
+
+out:
+	af_alg_async_cb(data, err);
+}
+
 static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg,
 			     size_t ignored, int flags)
 {
@@ -58,6 +104,7 @@ static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg,
 	struct crypto_skcipher *tfm = pask->private;
 	unsigned int bs = crypto_skcipher_chunksize(tfm);
 	struct af_alg_async_req *areq;
+	unsigned cflags = 0;
 	int err = 0;
 	size_t len = 0;
 
@@ -82,8 +129,10 @@ static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg,
 	 * If more buffers are to be expected to be processed, process only
 	 * full block size buffers.
 	 */
-	if (ctx->more || len < ctx->used)
+	if (ctx->more || len < ctx->used) {
 		len -= len % bs;
+		cflags |= CRYPTO_SKCIPHER_REQ_NOTFINAL;
+	}
 
 	/*
 	 * Create a per request TX SGL for this request which tracks the
@@ -107,6 +156,16 @@ static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg,
 	skcipher_request_set_crypt(&areq->cra_u.skcipher_req, areq->tsgl,
 				   areq->first_rsgl.sgl.sgt.sgl, len, ctx->iv);
 
+	if (ctx->state) {
+		err = crypto_skcipher_import(&areq->cra_u.skcipher_req,
+					     ctx->state);
+		sock_kzfree_s(sk, ctx->state, crypto_skcipher_statesize(tfm));
+		ctx->state = NULL;
+		if (err)
+			goto free;
+		cflags |= CRYPTO_SKCIPHER_REQ_CONT;
+	}
+
 	if (msg->msg_iocb && !is_sync_kiocb(msg->msg_iocb)) {
 		/* AIO operation */
 		sock_hold(sk);
@@ -116,8 +175,9 @@ static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg,
 		areq->outlen = len;
 
 		skcipher_request_set_callback(&areq->cra_u.skcipher_req,
+					      cflags |
 					      CRYPTO_TFM_REQ_MAY_SLEEP,
-					      af_alg_async_cb, areq);
+					      algif_skcipher_done, areq);
 		err = ctx->enc ?
 			crypto_skcipher_encrypt(&areq->cra_u.skcipher_req) :
 			crypto_skcipher_decrypt(&areq->cra_u.skcipher_req);
@@ -130,6 +190,7 @@ static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg,
 	} else {
 		/* Synchronous operation */
 		skcipher_request_set_callback(&areq->cra_u.skcipher_req,
+					      cflags |
 					      CRYPTO_TFM_REQ_MAY_SLEEP |
 					      CRYPTO_TFM_REQ_MAY_BACKLOG,
 					      crypto_req_done, &ctx->wait);
@@ -137,8 +198,11 @@ static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg,
 			crypto_skcipher_encrypt(&areq->cra_u.skcipher_req) :
 			crypto_skcipher_decrypt(&areq->cra_u.skcipher_req),
 						 &ctx->wait);
-	}
 
+		if (!err)
+			err = algif_skcipher_export(
+				sk, &areq->cra_u.skcipher_req);
+	}
 
 free:
 	af_alg_free_resources(areq);
@@ -301,6 +365,8 @@ static void skcipher_sock_destruct(struct sock *sk)
 
 	af_alg_pull_tsgl(sk, ctx->used, NULL, 0);
 	sock_kzfree_s(sk, ctx->iv, crypto_skcipher_ivsize(tfm));
+	if (ctx->state)
+		sock_kzfree_s(sk, ctx->state, crypto_skcipher_statesize(tfm));
 	sock_kfree_s(sk, ctx, ctx->len);
 	af_alg_release_parent(sk);
 }
diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h
index 08b803a4fcde..78ecaf5db04c 100644
--- a/include/crypto/if_alg.h
+++ b/include/crypto/if_alg.h
@@ -121,6 +121,7 @@ struct af_alg_async_req {
  *
  * @tsgl_list:		Link to TX SGL
  * @iv:			IV for cipher operation
+ * @state:		Existing state for continuing operation
  * @aead_assoclen:	Length of AAD for AEAD cipher operations
  * @completion:		Work queue for synchronous operation
  * @used:		TX bytes sent to kernel. This variable is used to
@@ -142,6 +143,7 @@ struct af_alg_ctx {
 	struct list_head tsgl_list;
 
 	void *iv;
+	void *state;
 	size_t aead_assoclen;
 
 	struct crypto_wait wait;
-- 
cgit v1.2.3


From 4dc7e7d2eead9abc10e2327d40ff6ca0d24cd83a Mon Sep 17 00:00:00 2001
From: Rajendra Nayak <quic_rjendra@quicinc.com>
Date: Tue, 5 Dec 2023 11:39:59 +0530
Subject: dt-bindings: clock: qcom: Add X1E80100 GCC clocks

Add device tree bindings for global clock controller on X1E80100 SoCs.

Signed-off-by: Rajendra Nayak <quic_rjendra@quicinc.com>
Co-developed-by: Sibi Sankar <quic_sibis@quicinc.com>
Signed-off-by: Sibi Sankar <quic_sibis@quicinc.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231205061002.30759-2-quic_sibis@quicinc.com
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 .../bindings/clock/qcom,x1e80100-gcc.yaml          |  72 +++
 include/dt-bindings/clock/qcom,x1e80100-gcc.h      | 485 +++++++++++++++++++++
 2 files changed, 557 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/clock/qcom,x1e80100-gcc.yaml
 create mode 100644 include/dt-bindings/clock/qcom,x1e80100-gcc.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/clock/qcom,x1e80100-gcc.yaml b/Documentation/devicetree/bindings/clock/qcom,x1e80100-gcc.yaml
new file mode 100644
index 000000000000..14a796dbf8bc
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/qcom,x1e80100-gcc.yaml
@@ -0,0 +1,72 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/qcom,x1e80100-gcc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm Global Clock & Reset Controller on X1E80100
+
+maintainers:
+  - Rajendra Nayak <quic_rjendra@quicinc.com>
+
+description: |
+  Qualcomm global clock control module provides the clocks, resets and power
+  domains on X1E80100
+
+  See also:: include/dt-bindings/clock/qcom,x1e80100-gcc.h
+
+properties:
+  compatible:
+    const: qcom,x1e80100-gcc
+
+  clocks:
+    items:
+      - description: Board XO source
+      - description: Sleep clock source
+      - description: PCIe 3 pipe clock
+      - description: PCIe 4 pipe clock
+      - description: PCIe 5 pipe clock
+      - description: PCIe 6a pipe clock
+      - description: PCIe 6b pipe clock
+      - description: USB QMP Phy 0 clock source
+      - description: USB QMP Phy 1 clock source
+      - description: USB QMP Phy 2 clock source
+
+  power-domains:
+    description:
+      A phandle and PM domain specifier for the CX power domain.
+    maxItems: 1
+
+required:
+  - compatible
+  - clocks
+  - power-domains
+
+allOf:
+  - $ref: qcom,gcc.yaml#
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/power/qcom,rpmhpd.h>
+    clock-controller@100000 {
+      compatible = "qcom,x1e80100-gcc";
+      reg = <0x00100000 0x200000>;
+      clocks = <&bi_tcxo_div2>,
+               <&sleep_clk>,
+               <&pcie3_phy>,
+               <&pcie4_phy>,
+               <&pcie5_phy>,
+               <&pcie6a_phy>,
+               <&pcie6b_phy>,
+               <&usb_1_ss0_qmpphy 0>,
+               <&usb_1_ss1_qmpphy 1>,
+               <&usb_1_ss2_qmpphy 2>;
+      power-domains = <&rpmhpd RPMHPD_CX>;
+      #clock-cells = <1>;
+      #reset-cells = <1>;
+      #power-domain-cells = <1>;
+    };
+
+...
diff --git a/include/dt-bindings/clock/qcom,x1e80100-gcc.h b/include/dt-bindings/clock/qcom,x1e80100-gcc.h
new file mode 100644
index 000000000000..24ba9e2a5cf6
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,x1e80100-gcc.h
@@ -0,0 +1,485 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/*
+ * Copyright (c) 2023, Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#ifndef _DT_BINDINGS_CLK_QCOM_GCC_X1E80100_H
+#define _DT_BINDINGS_CLK_QCOM_GCC_X1E80100_H
+
+/* GCC clocks */
+#define GCC_AGGRE_NOC_USB_NORTH_AXI_CLK				0
+#define GCC_AGGRE_NOC_USB_SOUTH_AXI_CLK				1
+#define GCC_AGGRE_UFS_PHY_AXI_CLK				2
+#define GCC_AGGRE_USB2_PRIM_AXI_CLK				3
+#define GCC_AGGRE_USB3_MP_AXI_CLK				4
+#define GCC_AGGRE_USB3_PRIM_AXI_CLK				5
+#define GCC_AGGRE_USB3_SEC_AXI_CLK				6
+#define GCC_AGGRE_USB3_TERT_AXI_CLK				7
+#define GCC_AGGRE_USB4_0_AXI_CLK				8
+#define GCC_AGGRE_USB4_1_AXI_CLK				9
+#define GCC_AGGRE_USB4_2_AXI_CLK				10
+#define GCC_AGGRE_USB_NOC_AXI_CLK				11
+#define GCC_AV1E_AHB_CLK					12
+#define GCC_AV1E_AXI_CLK					13
+#define GCC_AV1E_XO_CLK						14
+#define GCC_BOOT_ROM_AHB_CLK					15
+#define GCC_CAMERA_AHB_CLK					16
+#define GCC_CAMERA_HF_AXI_CLK					17
+#define GCC_CAMERA_SF_AXI_CLK					18
+#define GCC_CAMERA_XO_CLK					19
+#define GCC_CFG_NOC_PCIE_ANOC_AHB_CLK				20
+#define GCC_CFG_NOC_PCIE_ANOC_NORTH_AHB_CLK			21
+#define GCC_CFG_NOC_PCIE_ANOC_SOUTH_AHB_CLK			22
+#define GCC_CFG_NOC_USB2_PRIM_AXI_CLK				23
+#define GCC_CFG_NOC_USB3_MP_AXI_CLK				24
+#define GCC_CFG_NOC_USB3_PRIM_AXI_CLK				25
+#define GCC_CFG_NOC_USB3_SEC_AXI_CLK				26
+#define GCC_CFG_NOC_USB3_TERT_AXI_CLK				27
+#define GCC_CFG_NOC_USB_ANOC_AHB_CLK				28
+#define GCC_CFG_NOC_USB_ANOC_NORTH_AHB_CLK			29
+#define GCC_CFG_NOC_USB_ANOC_SOUTH_AHB_CLK			30
+#define GCC_CNOC_PCIE1_TUNNEL_CLK				31
+#define GCC_CNOC_PCIE2_TUNNEL_CLK				32
+#define GCC_CNOC_PCIE_NORTH_SF_AXI_CLK				33
+#define GCC_CNOC_PCIE_SOUTH_SF_AXI_CLK				34
+#define GCC_CNOC_PCIE_TUNNEL_CLK				35
+#define GCC_DDRSS_GPU_AXI_CLK					36
+#define GCC_DISP_AHB_CLK					37
+#define GCC_DISP_HF_AXI_CLK					38
+#define GCC_DISP_XO_CLK						39
+#define GCC_GP1_CLK						40
+#define GCC_GP1_CLK_SRC						41
+#define GCC_GP2_CLK						42
+#define GCC_GP2_CLK_SRC						43
+#define GCC_GP3_CLK						44
+#define GCC_GP3_CLK_SRC						45
+#define GCC_GPLL0						46
+#define GCC_GPLL0_OUT_EVEN					47
+#define GCC_GPLL4						48
+#define GCC_GPLL7						49
+#define GCC_GPLL8						50
+#define GCC_GPLL9						51
+#define GCC_GPU_CFG_AHB_CLK					52
+#define GCC_GPU_GPLL0_CPH_CLK_SRC				53
+#define GCC_GPU_GPLL0_DIV_CPH_CLK_SRC				54
+#define GCC_GPU_MEMNOC_GFX_CLK					55
+#define GCC_GPU_SNOC_DVM_GFX_CLK				56
+#define GCC_PCIE0_PHY_RCHNG_CLK					57
+#define GCC_PCIE1_PHY_RCHNG_CLK					58
+#define GCC_PCIE2_PHY_RCHNG_CLK					59
+#define GCC_PCIE_0_AUX_CLK					60
+#define GCC_PCIE_0_AUX_CLK_SRC					61
+#define GCC_PCIE_0_CFG_AHB_CLK					62
+#define GCC_PCIE_0_MSTR_AXI_CLK					63
+#define GCC_PCIE_0_PHY_RCHNG_CLK_SRC				64
+#define GCC_PCIE_0_PIPE_CLK					65
+#define GCC_PCIE_0_SLV_AXI_CLK					66
+#define GCC_PCIE_0_SLV_Q2A_AXI_CLK				67
+#define GCC_PCIE_1_AUX_CLK					68
+#define GCC_PCIE_1_AUX_CLK_SRC					69
+#define GCC_PCIE_1_CFG_AHB_CLK					70
+#define GCC_PCIE_1_MSTR_AXI_CLK					71
+#define GCC_PCIE_1_PHY_RCHNG_CLK_SRC				72
+#define GCC_PCIE_1_PIPE_CLK					73
+#define GCC_PCIE_1_SLV_AXI_CLK					74
+#define GCC_PCIE_1_SLV_Q2A_AXI_CLK				75
+#define GCC_PCIE_2_AUX_CLK					76
+#define GCC_PCIE_2_AUX_CLK_SRC					77
+#define GCC_PCIE_2_CFG_AHB_CLK					78
+#define GCC_PCIE_2_MSTR_AXI_CLK					79
+#define GCC_PCIE_2_PHY_RCHNG_CLK_SRC				80
+#define GCC_PCIE_2_PIPE_CLK					81
+#define GCC_PCIE_2_SLV_AXI_CLK					82
+#define GCC_PCIE_2_SLV_Q2A_AXI_CLK				83
+#define GCC_PCIE_3_AUX_CLK					84
+#define GCC_PCIE_3_AUX_CLK_SRC					85
+#define GCC_PCIE_3_CFG_AHB_CLK					86
+#define GCC_PCIE_3_MSTR_AXI_CLK					87
+#define GCC_PCIE_3_PHY_AUX_CLK					88
+#define GCC_PCIE_3_PHY_RCHNG_CLK				89
+#define GCC_PCIE_3_PHY_RCHNG_CLK_SRC				90
+#define GCC_PCIE_3_PIPE_CLK					91
+#define GCC_PCIE_3_PIPE_DIV_CLK_SRC				92
+#define GCC_PCIE_3_PIPEDIV2_CLK					93
+#define GCC_PCIE_3_SLV_AXI_CLK					94
+#define GCC_PCIE_3_SLV_Q2A_AXI_CLK				95
+#define GCC_PCIE_4_AUX_CLK					96
+#define GCC_PCIE_4_AUX_CLK_SRC					97
+#define GCC_PCIE_4_CFG_AHB_CLK					98
+#define GCC_PCIE_4_MSTR_AXI_CLK					99
+#define GCC_PCIE_4_PHY_RCHNG_CLK				100
+#define GCC_PCIE_4_PHY_RCHNG_CLK_SRC				101
+#define GCC_PCIE_4_PIPE_CLK					102
+#define GCC_PCIE_4_PIPE_DIV_CLK_SRC				103
+#define GCC_PCIE_4_PIPEDIV2_CLK					104
+#define GCC_PCIE_4_SLV_AXI_CLK					105
+#define GCC_PCIE_4_SLV_Q2A_AXI_CLK				106
+#define GCC_PCIE_5_AUX_CLK					107
+#define GCC_PCIE_5_AUX_CLK_SRC					108
+#define GCC_PCIE_5_CFG_AHB_CLK					109
+#define GCC_PCIE_5_MSTR_AXI_CLK					110
+#define GCC_PCIE_5_PHY_RCHNG_CLK				111
+#define GCC_PCIE_5_PHY_RCHNG_CLK_SRC				112
+#define GCC_PCIE_5_PIPE_CLK					113
+#define GCC_PCIE_5_PIPE_DIV_CLK_SRC				114
+#define GCC_PCIE_5_PIPEDIV2_CLK					115
+#define GCC_PCIE_5_SLV_AXI_CLK					116
+#define GCC_PCIE_5_SLV_Q2A_AXI_CLK				117
+#define GCC_PCIE_6A_AUX_CLK					118
+#define GCC_PCIE_6A_AUX_CLK_SRC					119
+#define GCC_PCIE_6A_CFG_AHB_CLK					120
+#define GCC_PCIE_6A_MSTR_AXI_CLK				121
+#define GCC_PCIE_6A_PHY_AUX_CLK					122
+#define GCC_PCIE_6A_PHY_RCHNG_CLK				123
+#define GCC_PCIE_6A_PHY_RCHNG_CLK_SRC				124
+#define GCC_PCIE_6A_PIPE_CLK					125
+#define GCC_PCIE_6A_PIPE_DIV_CLK_SRC				126
+#define GCC_PCIE_6A_PIPEDIV2_CLK				127
+#define GCC_PCIE_6A_SLV_AXI_CLK					128
+#define GCC_PCIE_6A_SLV_Q2A_AXI_CLK				129
+#define GCC_PCIE_6B_AUX_CLK					130
+#define GCC_PCIE_6B_AUX_CLK_SRC					131
+#define GCC_PCIE_6B_CFG_AHB_CLK					132
+#define GCC_PCIE_6B_MSTR_AXI_CLK				133
+#define GCC_PCIE_6B_PHY_AUX_CLK					134
+#define GCC_PCIE_6B_PHY_RCHNG_CLK				135
+#define GCC_PCIE_6B_PHY_RCHNG_CLK_SRC				136
+#define GCC_PCIE_6B_PIPE_CLK					137
+#define GCC_PCIE_6B_PIPE_DIV_CLK_SRC				138
+#define GCC_PCIE_6B_PIPEDIV2_CLK				139
+#define GCC_PCIE_6B_SLV_AXI_CLK					140
+#define GCC_PCIE_6B_SLV_Q2A_AXI_CLK				141
+#define GCC_PCIE_RSCC_AHB_CLK					142
+#define GCC_PCIE_RSCC_XO_CLK					143
+#define GCC_PCIE_RSCC_XO_CLK_SRC				144
+#define GCC_PDM2_CLK						145
+#define GCC_PDM2_CLK_SRC					146
+#define GCC_PDM_AHB_CLK						147
+#define GCC_PDM_XO4_CLK						148
+#define GCC_QMIP_AV1E_AHB_CLK					149
+#define GCC_QMIP_CAMERA_NRT_AHB_CLK				150
+#define GCC_QMIP_CAMERA_RT_AHB_CLK				151
+#define GCC_QMIP_DISP_AHB_CLK					152
+#define GCC_QMIP_GPU_AHB_CLK					153
+#define GCC_QMIP_VIDEO_CV_CPU_AHB_CLK				154
+#define GCC_QMIP_VIDEO_CVP_AHB_CLK				155
+#define GCC_QMIP_VIDEO_V_CPU_AHB_CLK				156
+#define GCC_QMIP_VIDEO_VCODEC_AHB_CLK				157
+#define GCC_QUPV3_WRAP0_CORE_2X_CLK				158
+#define GCC_QUPV3_WRAP0_CORE_CLK				159
+#define GCC_QUPV3_WRAP0_QSPI_S2_CLK				160
+#define GCC_QUPV3_WRAP0_QSPI_S3_CLK				161
+#define GCC_QUPV3_WRAP0_S0_CLK					162
+#define GCC_QUPV3_WRAP0_S0_CLK_SRC				163
+#define GCC_QUPV3_WRAP0_S1_CLK					164
+#define GCC_QUPV3_WRAP0_S1_CLK_SRC				165
+#define GCC_QUPV3_WRAP0_S2_CLK					166
+#define GCC_QUPV3_WRAP0_S2_CLK_SRC				167
+#define GCC_QUPV3_WRAP0_S2_DIV_CLK_SRC				168
+#define GCC_QUPV3_WRAP0_S3_CLK					169
+#define GCC_QUPV3_WRAP0_S3_CLK_SRC				170
+#define GCC_QUPV3_WRAP0_S3_DIV_CLK_SRC				171
+#define GCC_QUPV3_WRAP0_S4_CLK					172
+#define GCC_QUPV3_WRAP0_S4_CLK_SRC				173
+#define GCC_QUPV3_WRAP0_S5_CLK					174
+#define GCC_QUPV3_WRAP0_S5_CLK_SRC				175
+#define GCC_QUPV3_WRAP0_S6_CLK					176
+#define GCC_QUPV3_WRAP0_S6_CLK_SRC				177
+#define GCC_QUPV3_WRAP0_S7_CLK					178
+#define GCC_QUPV3_WRAP0_S7_CLK_SRC				179
+#define GCC_QUPV3_WRAP1_CORE_2X_CLK				180
+#define GCC_QUPV3_WRAP1_CORE_CLK				181
+#define GCC_QUPV3_WRAP1_QSPI_S2_CLK				182
+#define GCC_QUPV3_WRAP1_QSPI_S3_CLK				183
+#define GCC_QUPV3_WRAP1_S0_CLK					184
+#define GCC_QUPV3_WRAP1_S0_CLK_SRC				185
+#define GCC_QUPV3_WRAP1_S1_CLK					186
+#define GCC_QUPV3_WRAP1_S1_CLK_SRC				187
+#define GCC_QUPV3_WRAP1_S2_CLK					188
+#define GCC_QUPV3_WRAP1_S2_CLK_SRC				189
+#define GCC_QUPV3_WRAP1_S2_DIV_CLK_SRC				190
+#define GCC_QUPV3_WRAP1_S3_CLK					191
+#define GCC_QUPV3_WRAP1_S3_CLK_SRC				192
+#define GCC_QUPV3_WRAP1_S3_DIV_CLK_SRC				193
+#define GCC_QUPV3_WRAP1_S4_CLK					194
+#define GCC_QUPV3_WRAP1_S4_CLK_SRC				195
+#define GCC_QUPV3_WRAP1_S5_CLK					196
+#define GCC_QUPV3_WRAP1_S5_CLK_SRC				197
+#define GCC_QUPV3_WRAP1_S6_CLK					198
+#define GCC_QUPV3_WRAP1_S6_CLK_SRC				199
+#define GCC_QUPV3_WRAP1_S7_CLK					200
+#define GCC_QUPV3_WRAP1_S7_CLK_SRC				201
+#define GCC_QUPV3_WRAP2_CORE_2X_CLK				202
+#define GCC_QUPV3_WRAP2_CORE_CLK				203
+#define GCC_QUPV3_WRAP2_QSPI_S2_CLK				204
+#define GCC_QUPV3_WRAP2_QSPI_S3_CLK				205
+#define GCC_QUPV3_WRAP2_S0_CLK					206
+#define GCC_QUPV3_WRAP2_S0_CLK_SRC				207
+#define GCC_QUPV3_WRAP2_S1_CLK					208
+#define GCC_QUPV3_WRAP2_S1_CLK_SRC				209
+#define GCC_QUPV3_WRAP2_S2_CLK					210
+#define GCC_QUPV3_WRAP2_S2_CLK_SRC				211
+#define GCC_QUPV3_WRAP2_S2_DIV_CLK_SRC				212
+#define GCC_QUPV3_WRAP2_S3_CLK					213
+#define GCC_QUPV3_WRAP2_S3_CLK_SRC				214
+#define GCC_QUPV3_WRAP2_S3_DIV_CLK_SRC				215
+#define GCC_QUPV3_WRAP2_S4_CLK					216
+#define GCC_QUPV3_WRAP2_S4_CLK_SRC				217
+#define GCC_QUPV3_WRAP2_S5_CLK					218
+#define GCC_QUPV3_WRAP2_S5_CLK_SRC				219
+#define GCC_QUPV3_WRAP2_S6_CLK					220
+#define GCC_QUPV3_WRAP2_S6_CLK_SRC				221
+#define GCC_QUPV3_WRAP2_S7_CLK					222
+#define GCC_QUPV3_WRAP2_S7_CLK_SRC				223
+#define GCC_QUPV3_WRAP_0_M_AHB_CLK				224
+#define GCC_QUPV3_WRAP_0_S_AHB_CLK				225
+#define GCC_QUPV3_WRAP_1_M_AHB_CLK				226
+#define GCC_QUPV3_WRAP_1_S_AHB_CLK				227
+#define GCC_QUPV3_WRAP_2_M_AHB_CLK				228
+#define GCC_QUPV3_WRAP_2_S_AHB_CLK				229
+#define GCC_SDCC2_AHB_CLK					230
+#define GCC_SDCC2_APPS_CLK					231
+#define GCC_SDCC2_APPS_CLK_SRC					232
+#define GCC_SDCC4_AHB_CLK					233
+#define GCC_SDCC4_APPS_CLK					234
+#define GCC_SDCC4_APPS_CLK_SRC					235
+#define GCC_SYS_NOC_USB_AXI_CLK					236
+#define GCC_UFS_PHY_AHB_CLK					237
+#define GCC_UFS_PHY_AXI_CLK					238
+#define GCC_UFS_PHY_AXI_CLK_SRC					239
+#define GCC_UFS_PHY_ICE_CORE_CLK				240
+#define GCC_UFS_PHY_ICE_CORE_CLK_SRC				241
+#define GCC_UFS_PHY_PHY_AUX_CLK					242
+#define GCC_UFS_PHY_PHY_AUX_CLK_SRC				243
+#define GCC_UFS_PHY_RX_SYMBOL_0_CLK				244
+#define GCC_UFS_PHY_RX_SYMBOL_1_CLK				245
+#define GCC_UFS_PHY_TX_SYMBOL_0_CLK				246
+#define GCC_UFS_PHY_UNIPRO_CORE_CLK				247
+#define GCC_UFS_PHY_UNIPRO_CORE_CLK_SRC				248
+#define GCC_USB20_MASTER_CLK					249
+#define GCC_USB20_MASTER_CLK_SRC				250
+#define GCC_USB20_MOCK_UTMI_CLK					251
+#define GCC_USB20_MOCK_UTMI_CLK_SRC				252
+#define GCC_USB20_MOCK_UTMI_POSTDIV_CLK_SRC			253
+#define GCC_USB20_SLEEP_CLK					254
+#define GCC_USB30_MP_MASTER_CLK					255
+#define GCC_USB30_MP_MASTER_CLK_SRC				256
+#define GCC_USB30_MP_MOCK_UTMI_CLK				257
+#define GCC_USB30_MP_MOCK_UTMI_CLK_SRC				258
+#define GCC_USB30_MP_MOCK_UTMI_POSTDIV_CLK_SRC			259
+#define GCC_USB30_MP_SLEEP_CLK					260
+#define GCC_USB30_PRIM_MASTER_CLK				261
+#define GCC_USB30_PRIM_MASTER_CLK_SRC				262
+#define GCC_USB30_PRIM_MOCK_UTMI_CLK				263
+#define GCC_USB30_PRIM_MOCK_UTMI_CLK_SRC			264
+#define GCC_USB30_PRIM_MOCK_UTMI_POSTDIV_CLK_SRC		265
+#define GCC_USB30_PRIM_SLEEP_CLK				266
+#define GCC_USB30_SEC_MASTER_CLK				267
+#define GCC_USB30_SEC_MASTER_CLK_SRC				268
+#define GCC_USB30_SEC_MOCK_UTMI_CLK				269
+#define GCC_USB30_SEC_MOCK_UTMI_CLK_SRC				270
+#define GCC_USB30_SEC_MOCK_UTMI_POSTDIV_CLK_SRC			271
+#define GCC_USB30_SEC_SLEEP_CLK					272
+#define GCC_USB30_TERT_MASTER_CLK				273
+#define GCC_USB30_TERT_MASTER_CLK_SRC				274
+#define GCC_USB30_TERT_MOCK_UTMI_CLK				275
+#define GCC_USB30_TERT_MOCK_UTMI_CLK_SRC			276
+#define GCC_USB30_TERT_MOCK_UTMI_POSTDIV_CLK_SRC		277
+#define GCC_USB30_TERT_SLEEP_CLK				278
+#define GCC_USB3_MP_PHY_AUX_CLK					279
+#define GCC_USB3_MP_PHY_AUX_CLK_SRC				280
+#define GCC_USB3_MP_PHY_COM_AUX_CLK				281
+#define GCC_USB3_MP_PHY_PIPE_0_CLK				282
+#define GCC_USB3_MP_PHY_PIPE_1_CLK				283
+#define GCC_USB3_PRIM_PHY_AUX_CLK				284
+#define GCC_USB3_PRIM_PHY_AUX_CLK_SRC				285
+#define GCC_USB3_PRIM_PHY_COM_AUX_CLK				286
+#define GCC_USB3_PRIM_PHY_PIPE_CLK				287
+#define GCC_USB3_SEC_PHY_AUX_CLK				288
+#define GCC_USB3_SEC_PHY_AUX_CLK_SRC				289
+#define GCC_USB3_SEC_PHY_COM_AUX_CLK				290
+#define GCC_USB3_SEC_PHY_PIPE_CLK				291
+#define GCC_USB3_TERT_PHY_AUX_CLK				292
+#define GCC_USB3_TERT_PHY_AUX_CLK_SRC				293
+#define GCC_USB3_TERT_PHY_COM_AUX_CLK				294
+#define GCC_USB3_TERT_PHY_PIPE_CLK				295
+#define GCC_USB4_0_CFG_AHB_CLK					296
+#define GCC_USB4_0_DP0_CLK					297
+#define GCC_USB4_0_DP1_CLK					298
+#define GCC_USB4_0_MASTER_CLK					299
+#define GCC_USB4_0_MASTER_CLK_SRC				300
+#define GCC_USB4_0_PHY_P2RR2P_PIPE_CLK				301
+#define GCC_USB4_0_PHY_PCIE_PIPE_CLK				302
+#define GCC_USB4_0_PHY_PCIE_PIPE_CLK_SRC			303
+#define GCC_USB4_0_PHY_RX0_CLK					304
+#define GCC_USB4_0_PHY_RX1_CLK					305
+#define GCC_USB4_0_PHY_USB_PIPE_CLK				306
+#define GCC_USB4_0_SB_IF_CLK					307
+#define GCC_USB4_0_SB_IF_CLK_SRC				308
+#define GCC_USB4_0_SYS_CLK					309
+#define GCC_USB4_0_TMU_CLK					310
+#define GCC_USB4_0_TMU_CLK_SRC					311
+#define GCC_USB4_1_CFG_AHB_CLK					312
+#define GCC_USB4_1_DP0_CLK					313
+#define GCC_USB4_1_DP1_CLK					314
+#define GCC_USB4_1_MASTER_CLK					315
+#define GCC_USB4_1_MASTER_CLK_SRC				316
+#define GCC_USB4_1_PHY_P2RR2P_PIPE_CLK				317
+#define GCC_USB4_1_PHY_PCIE_PIPE_CLK				318
+#define GCC_USB4_1_PHY_PCIE_PIPE_CLK_SRC			319
+#define GCC_USB4_1_PHY_RX0_CLK					320
+#define GCC_USB4_1_PHY_RX1_CLK					321
+#define GCC_USB4_1_PHY_USB_PIPE_CLK				322
+#define GCC_USB4_1_SB_IF_CLK					323
+#define GCC_USB4_1_SB_IF_CLK_SRC				324
+#define GCC_USB4_1_SYS_CLK					325
+#define GCC_USB4_1_TMU_CLK					326
+#define GCC_USB4_1_TMU_CLK_SRC					327
+#define GCC_USB4_2_CFG_AHB_CLK					328
+#define GCC_USB4_2_DP0_CLK					329
+#define GCC_USB4_2_DP1_CLK					330
+#define GCC_USB4_2_MASTER_CLK					331
+#define GCC_USB4_2_MASTER_CLK_SRC				332
+#define GCC_USB4_2_PHY_P2RR2P_PIPE_CLK				333
+#define GCC_USB4_2_PHY_PCIE_PIPE_CLK				334
+#define GCC_USB4_2_PHY_PCIE_PIPE_CLK_SRC			335
+#define GCC_USB4_2_PHY_RX0_CLK					336
+#define GCC_USB4_2_PHY_RX1_CLK					337
+#define GCC_USB4_2_PHY_USB_PIPE_CLK				338
+#define GCC_USB4_2_SB_IF_CLK					339
+#define GCC_USB4_2_SB_IF_CLK_SRC				340
+#define GCC_USB4_2_SYS_CLK					341
+#define GCC_USB4_2_TMU_CLK					342
+#define GCC_USB4_2_TMU_CLK_SRC					343
+#define GCC_VIDEO_AHB_CLK					344
+#define GCC_VIDEO_AXI0_CLK					345
+#define GCC_VIDEO_AXI1_CLK					346
+#define GCC_VIDEO_XO_CLK					347
+#define GCC_PCIE_3_PIPE_CLK_SRC					348
+#define GCC_PCIE_4_PIPE_CLK_SRC					349
+#define GCC_PCIE_5_PIPE_CLK_SRC					350
+#define GCC_PCIE_6A_PIPE_CLK_SRC				351
+#define GCC_PCIE_6B_PIPE_CLK_SRC				352
+#define GCC_USB3_PRIM_PHY_PIPE_CLK_SRC				353
+#define GCC_USB3_SEC_PHY_PIPE_CLK_SRC				354
+#define GCC_USB3_TERT_PHY_PIPE_CLK_SRC				355
+
+/* GCC power domains */
+#define GCC_PCIE_0_TUNNEL_GDSC					0
+#define GCC_PCIE_1_TUNNEL_GDSC					1
+#define GCC_PCIE_2_TUNNEL_GDSC					2
+#define GCC_PCIE_3_GDSC						3
+#define GCC_PCIE_3_PHY_GDSC					4
+#define GCC_PCIE_4_GDSC						5
+#define GCC_PCIE_4_PHY_GDSC					6
+#define GCC_PCIE_5_GDSC						7
+#define GCC_PCIE_5_PHY_GDSC					8
+#define GCC_PCIE_6_PHY_GDSC					9
+#define GCC_PCIE_6A_GDSC					10
+#define GCC_PCIE_6B_GDSC					11
+#define GCC_UFS_MEM_PHY_GDSC					12
+#define GCC_UFS_PHY_GDSC					13
+#define GCC_USB20_PRIM_GDSC					14
+#define GCC_USB30_MP_GDSC					15
+#define GCC_USB30_PRIM_GDSC					16
+#define GCC_USB30_SEC_GDSC					17
+#define GCC_USB30_TERT_GDSC					18
+#define GCC_USB3_MP_SS0_PHY_GDSC				19
+#define GCC_USB3_MP_SS1_PHY_GDSC				20
+#define GCC_USB4_0_GDSC						21
+#define GCC_USB4_1_GDSC						22
+#define GCC_USB4_2_GDSC						23
+#define GCC_USB_0_PHY_GDSC					24
+#define GCC_USB_1_PHY_GDSC					25
+#define GCC_USB_2_PHY_GDSC					26
+
+/* GCC resets */
+#define GCC_AV1E_BCR						0
+#define GCC_CAMERA_BCR						1
+#define GCC_DISPLAY_BCR						2
+#define GCC_GPU_BCR						3
+#define GCC_PCIE_0_LINK_DOWN_BCR				4
+#define GCC_PCIE_0_NOCSR_COM_PHY_BCR				5
+#define GCC_PCIE_0_PHY_BCR					6
+#define GCC_PCIE_0_PHY_NOCSR_COM_PHY_BCR			7
+#define GCC_PCIE_0_TUNNEL_BCR					8
+#define GCC_PCIE_1_LINK_DOWN_BCR				9
+#define GCC_PCIE_1_NOCSR_COM_PHY_BCR				10
+#define GCC_PCIE_1_PHY_BCR					11
+#define GCC_PCIE_1_PHY_NOCSR_COM_PHY_BCR			12
+#define GCC_PCIE_1_TUNNEL_BCR					13
+#define GCC_PCIE_2_LINK_DOWN_BCR				14
+#define GCC_PCIE_2_NOCSR_COM_PHY_BCR				15
+#define GCC_PCIE_2_PHY_BCR					16
+#define GCC_PCIE_2_PHY_NOCSR_COM_PHY_BCR			17
+#define GCC_PCIE_2_TUNNEL_BCR					18
+#define GCC_PCIE_3_BCR						19
+#define GCC_PCIE_3_LINK_DOWN_BCR				20
+#define GCC_PCIE_3_NOCSR_COM_PHY_BCR				21
+#define GCC_PCIE_3_PHY_BCR					22
+#define GCC_PCIE_3_PHY_NOCSR_COM_PHY_BCR			23
+#define GCC_PCIE_4_BCR						24
+#define GCC_PCIE_4_LINK_DOWN_BCR				25
+#define GCC_PCIE_4_NOCSR_COM_PHY_BCR				26
+#define GCC_PCIE_4_PHY_BCR					27
+#define GCC_PCIE_4_PHY_NOCSR_COM_PHY_BCR			28
+#define GCC_PCIE_5_BCR						29
+#define GCC_PCIE_5_LINK_DOWN_BCR				30
+#define GCC_PCIE_5_NOCSR_COM_PHY_BCR				31
+#define GCC_PCIE_5_PHY_BCR					32
+#define GCC_PCIE_5_PHY_NOCSR_COM_PHY_BCR			33
+#define GCC_PCIE_6A_BCR						34
+#define GCC_PCIE_6A_LINK_DOWN_BCR				35
+#define GCC_PCIE_6A_NOCSR_COM_PHY_BCR				36
+#define GCC_PCIE_6A_PHY_BCR					37
+#define GCC_PCIE_6A_PHY_NOCSR_COM_PHY_BCR			38
+#define GCC_PCIE_6B_BCR						39
+#define GCC_PCIE_6B_LINK_DOWN_BCR				40
+#define GCC_PCIE_6B_NOCSR_COM_PHY_BCR				41
+#define GCC_PCIE_6B_PHY_BCR					42
+#define GCC_PCIE_6B_PHY_NOCSR_COM_PHY_BCR			43
+#define GCC_PCIE_PHY_BCR					44
+#define GCC_PCIE_PHY_CFG_AHB_BCR				45
+#define GCC_PCIE_PHY_COM_BCR					46
+#define GCC_PCIE_RSCC_BCR					47
+#define GCC_PDM_BCR						48
+#define GCC_QUPV3_WRAPPER_0_BCR					49
+#define GCC_QUPV3_WRAPPER_1_BCR					50
+#define GCC_QUPV3_WRAPPER_2_BCR					51
+#define GCC_QUSB2PHY_HS0_MP_BCR					52
+#define GCC_QUSB2PHY_HS1_MP_BCR					53
+#define GCC_QUSB2PHY_PRIM_BCR					54
+#define GCC_QUSB2PHY_SEC_BCR					55
+#define GCC_QUSB2PHY_TERT_BCR					56
+#define GCC_QUSB2PHY_USB20_HS_BCR				57
+#define GCC_SDCC2_BCR						58
+#define GCC_SDCC4_BCR						59
+#define GCC_UFS_PHY_BCR						60
+#define GCC_USB20_PRIM_BCR					61
+#define GCC_USB30_MP_BCR					62
+#define GCC_USB30_PRIM_BCR					63
+#define GCC_USB30_SEC_BCR					64
+#define GCC_USB30_TERT_BCR					65
+#define GCC_USB3_MP_SS0_PHY_BCR					66
+#define GCC_USB3_MP_SS1_PHY_BCR					67
+#define GCC_USB3_PHY_PRIM_BCR					68
+#define GCC_USB3_PHY_SEC_BCR					69
+#define GCC_USB3_PHY_TERT_BCR					70
+#define GCC_USB3_UNIPHY_MP0_BCR					71
+#define GCC_USB3_UNIPHY_MP1_BCR					72
+#define GCC_USB3PHY_PHY_PRIM_BCR				73
+#define GCC_USB3PHY_PHY_SEC_BCR					74
+#define GCC_USB3PHY_PHY_TERT_BCR				75
+#define GCC_USB3UNIPHY_PHY_MP0_BCR				76
+#define GCC_USB3UNIPHY_PHY_MP1_BCR				77
+#define GCC_USB4_0_BCR						78
+#define GCC_USB4_0_DP0_PHY_PRIM_BCR				79
+#define GCC_USB4_1_DP0_PHY_SEC_BCR				80
+#define GCC_USB4_2_DP0_PHY_TERT_BCR				81
+#define GCC_USB4_1_BCR						82
+#define GCC_USB4_2_BCR						83
+#define GCC_USB_0_PHY_BCR					84
+#define GCC_USB_1_PHY_BCR					85
+#define GCC_USB_2_PHY_BCR					86
+#define GCC_VIDEO_BCR						87
+#endif
-- 
cgit v1.2.3


From ee25fba76acd8324f9de6628872c8c612a684209 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Mon, 4 Dec 2023 10:35:00 +0100
Subject: gpiolib: provide gpiochip_dup_line_label()

gpiochip_is_requested() not only has a misleading name but it returns
a pointer to a string that is freed when the descriptor is released.

Provide a new helper meant to replace it, which returns a copy of the
label string instead.

Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpiolib.c      | 29 +++++++++++++++++++++++++++++
 include/linux/gpio/driver.h |  1 +
 2 files changed, 30 insertions(+)

(limited to 'include')

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 95d2a7b2ea3e..0147c900afea 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -2386,6 +2386,35 @@ const char *gpiochip_is_requested(struct gpio_chip *gc, unsigned int offset)
 }
 EXPORT_SYMBOL_GPL(gpiochip_is_requested);
 
+/**
+ * gpiochip_dup_line_label - Get a copy of the consumer label.
+ * @gc: GPIO chip controlling this line.
+ * @offset: Hardware offset of the line.
+ *
+ * Returns:
+ * Pointer to a copy of the consumer label if the line is requested or NULL
+ * if it's not. If a valid pointer was returned, it must be freed using
+ * kfree(). In case of a memory allocation error, the function returns %ENOMEM.
+ *
+ * Must not be called from atomic context.
+ */
+char *gpiochip_dup_line_label(struct gpio_chip *gc, unsigned int offset)
+{
+	const char *label;
+	char *copy;
+
+	label = gpiochip_is_requested(gc, offset);
+	if (!label)
+		return NULL;
+
+	copy = kstrdup(label, GFP_KERNEL);
+	if (!copy)
+		return ERR_PTR(-ENOMEM);
+
+	return copy;
+}
+EXPORT_SYMBOL_GPL(gpiochip_dup_line_label);
+
 /**
  * gpiochip_request_own_desc - Allow GPIO chip to request its own descriptor
  * @gc: GPIO chip
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index 0aed62f0c633..5ac6dc30c547 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -532,6 +532,7 @@ struct gpio_chip {
 };
 
 const char *gpiochip_is_requested(struct gpio_chip *gc, unsigned int offset);
+char *gpiochip_dup_line_label(struct gpio_chip *gc, unsigned int offset);
 
 /**
  * for_each_requested_gpio_in_range - iterates over requested GPIOs in a given range
-- 
cgit v1.2.3


From 6fd9c9933475a3efd7eed2f80c7778908a560a1f Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Mon, 4 Dec 2023 10:35:08 +0100
Subject: gpiolib: use gpiochip_dup_line_label() in for_each helpers

Rework for_each_requested_gpio_in_range() to use the new helper to
retrieve a dynamically allocated copy of the descriptor label and free
it at the end of each iteration. We need to leverage the CLASS()'
destructor to make sure that the label is freed even when breaking out
of the loop.

Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
---
 include/linux/gpio/driver.h | 37 +++++++++++++++++++++++++++++--------
 1 file changed, 29 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index 5ac6dc30c547..cae4cdaa87db 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -534,17 +534,38 @@ struct gpio_chip {
 const char *gpiochip_is_requested(struct gpio_chip *gc, unsigned int offset);
 char *gpiochip_dup_line_label(struct gpio_chip *gc, unsigned int offset);
 
+
+struct _gpiochip_for_each_data {
+	const char **label;
+	unsigned int *i;
+};
+
+DEFINE_CLASS(_gpiochip_for_each_data,
+	     struct _gpiochip_for_each_data,
+	     if (*_T.label) kfree(*_T.label),
+	     ({
+		struct _gpiochip_for_each_data _data = { label, i };
+		*_data.i = 0;
+		_data;
+	     }),
+	     const char **label, int *i)
+
 /**
  * for_each_requested_gpio_in_range - iterates over requested GPIOs in a given range
- * @chip:	the chip to query
- * @i:		loop variable
- * @base:	first GPIO in the range
- * @size:	amount of GPIOs to check starting from @base
- * @label:	label of current GPIO
+ * @_chip:	the chip to query
+ * @_i:		loop variable
+ * @_base:	first GPIO in the range
+ * @_size:	amount of GPIOs to check starting from @base
+ * @_label:	label of current GPIO
  */
-#define for_each_requested_gpio_in_range(chip, i, base, size, label)			\
-	for (i = 0; i < size; i++)							\
-		if ((label = gpiochip_is_requested(chip, base + i)) == NULL) {} else
+#define for_each_requested_gpio_in_range(_chip, _i, _base, _size, _label)		\
+	for (CLASS(_gpiochip_for_each_data, _data)(&_label, &_i);			\
+	     *_data.i < _size;								\
+	     (*_data.i)++, kfree(*(_data.label)), *_data.label = NULL)			\
+		if ((*_data.label =							\
+			gpiochip_dup_line_label(_chip, _base + *_data.i)) == NULL) {}	\
+		else if (IS_ERR(*_data.label)) {}					\
+		else
 
 /* Iterates over all requested GPIO of the given @chip */
 #define for_each_requested_gpio(chip, i, label)						\
-- 
cgit v1.2.3


From f8d05e276b45e3097dfddd628fa991ce69c05c99 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Mon, 4 Dec 2023 10:35:09 +0100
Subject: gpiolib: remove gpiochip_is_requested()

We have no external users of gpiochip_is_requested(). Let's remove it
and replace its internal calls with direct testing of the REQUESTED flag.

Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpiolib.c      | 48 ++++++++++++---------------------------------
 include/linux/gpio/driver.h |  1 -
 2 files changed, 13 insertions(+), 36 deletions(-)

(limited to 'include')

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 0147c900afea..0ca33397812c 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1071,7 +1071,7 @@ void gpiochip_remove(struct gpio_chip *gc)
 
 	spin_lock_irqsave(&gpio_lock, flags);
 	for (i = 0; i < gdev->ngpio; i++) {
-		if (gpiochip_is_requested(gc, i))
+		if (test_bit(FLAG_REQUESTED, &gdev->descs[i].flags))
 			break;
 	}
 	spin_unlock_irqrestore(&gpio_lock, flags);
@@ -2359,33 +2359,6 @@ void gpiod_free(struct gpio_desc *desc)
 	gpio_device_put(desc->gdev);
 }
 
-/**
- * gpiochip_is_requested - return string iff signal was requested
- * @gc: controller managing the signal
- * @offset: of signal within controller's 0..(ngpio - 1) range
- *
- * Returns NULL if the GPIO is not currently requested, else a string.
- * The string returned is the label passed to gpio_request(); if none has been
- * passed it is a meaningless, non-NULL constant.
- *
- * This function is for use by GPIO controller drivers.  The label can
- * help with diagnostics, and knowing that the signal is used as a GPIO
- * can help avoid accidentally multiplexing it to another controller.
- */
-const char *gpiochip_is_requested(struct gpio_chip *gc, unsigned int offset)
-{
-	struct gpio_desc *desc;
-
-	desc = gpiochip_get_desc(gc, offset);
-	if (IS_ERR(desc))
-		return NULL;
-
-	if (test_bit(FLAG_REQUESTED, &desc->flags) == 0)
-		return NULL;
-	return desc->label;
-}
-EXPORT_SYMBOL_GPL(gpiochip_is_requested);
-
 /**
  * gpiochip_dup_line_label - Get a copy of the consumer label.
  * @gc: GPIO chip controlling this line.
@@ -2400,18 +2373,23 @@ EXPORT_SYMBOL_GPL(gpiochip_is_requested);
  */
 char *gpiochip_dup_line_label(struct gpio_chip *gc, unsigned int offset)
 {
-	const char *label;
-	char *copy;
+	struct gpio_desc *desc;
+	char *label;
 
-	label = gpiochip_is_requested(gc, offset);
-	if (!label)
+	desc = gpiochip_get_desc(gc, offset);
+	if (IS_ERR(desc))
 		return NULL;
 
-	copy = kstrdup(label, GFP_KERNEL);
-	if (!copy)
+	guard(spinlock_irqsave)(&gpio_lock);
+
+	if (!test_bit(FLAG_REQUESTED, &desc->flags))
+		return NULL;
+
+	label = kstrdup(desc->label, GFP_KERNEL);
+	if (!label)
 		return ERR_PTR(-ENOMEM);
 
-	return copy;
+	return label;
 }
 EXPORT_SYMBOL_GPL(gpiochip_dup_line_label);
 
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index cae4cdaa87db..d1a3cb061927 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -531,7 +531,6 @@ struct gpio_chip {
 #endif /* CONFIG_OF_GPIO */
 };
 
-const char *gpiochip_is_requested(struct gpio_chip *gc, unsigned int offset);
 char *gpiochip_dup_line_label(struct gpio_chip *gc, unsigned int offset);
 
 
-- 
cgit v1.2.3


From 66f011145b835f9a68af9d7156c8d84a6f29c331 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Fri, 8 Dec 2023 04:03:13 +0300
Subject: drm/atomic-helper: rename drm_atomic_helper_check_wb_encoder_state

The drm_atomic_helper_check_wb_encoder_state() function doesn't use
encoder for anything other than getting the drm_device instance. The
function's description talks about checking the writeback connector
state, not the encoder state. Moreover, there is no such thing as an
encoder state, encoders generally do not have a state on their own.

Rename the function to drm_atomic_helper_check_wb_connector_state()
and change arguments to drm_writeback_connector and drm_atomic_state.

Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Maxime Ripard <mripard@kernel.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20231208010314.3395904-2-dmitry.baryshkov@linaro.org
---
 drivers/gpu/drm/drm_atomic_helper.c   | 16 +++++++++-------
 drivers/gpu/drm/vkms/vkms_writeback.c |  3 ++-
 include/drm/drm_atomic_helper.h       |  5 ++---
 3 files changed, 13 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index c3f677130def..c98a766ca3bd 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -795,9 +795,9 @@ drm_atomic_helper_check_modeset(struct drm_device *dev,
 EXPORT_SYMBOL(drm_atomic_helper_check_modeset);
 
 /**
- * drm_atomic_helper_check_wb_encoder_state() - Check writeback encoder state
- * @encoder: encoder state to check
- * @conn_state: connector state to check
+ * drm_atomic_helper_check_wb_connector_state() - Check writeback connector state
+ * @connector: corresponding connector
+ * @state: the driver state object
  *
  * Checks if the writeback connector state is valid, and returns an error if it
  * isn't.
@@ -806,9 +806,11 @@ EXPORT_SYMBOL(drm_atomic_helper_check_modeset);
  * Zero for success or -errno
  */
 int
-drm_atomic_helper_check_wb_encoder_state(struct drm_encoder *encoder,
-					 struct drm_connector_state *conn_state)
+drm_atomic_helper_check_wb_connector_state(struct drm_connector *connector,
+					   struct drm_atomic_state *state)
 {
+	struct drm_connector_state *conn_state =
+		drm_atomic_get_new_connector_state(state, connector);
 	struct drm_writeback_job *wb_job = conn_state->writeback_job;
 	struct drm_property_blob *pixel_format_blob;
 	struct drm_framebuffer *fb;
@@ -827,11 +829,11 @@ drm_atomic_helper_check_wb_encoder_state(struct drm_encoder *encoder,
 		if (fb->format->format == formats[i])
 			return 0;
 
-	drm_dbg_kms(encoder->dev, "Invalid pixel format %p4cc\n", &fb->format->format);
+	drm_dbg_kms(connector->dev, "Invalid pixel format %p4cc\n", &fb->format->format);
 
 	return -EINVAL;
 }
-EXPORT_SYMBOL(drm_atomic_helper_check_wb_encoder_state);
+EXPORT_SYMBOL(drm_atomic_helper_check_wb_connector_state);
 
 /**
  * drm_atomic_helper_check_plane_state() - Check plane state for validity
diff --git a/drivers/gpu/drm/vkms/vkms_writeback.c b/drivers/gpu/drm/vkms/vkms_writeback.c
index d7e63aa14663..fef7f3daf2c9 100644
--- a/drivers/gpu/drm/vkms/vkms_writeback.c
+++ b/drivers/gpu/drm/vkms/vkms_writeback.c
@@ -34,6 +34,7 @@ static int vkms_wb_encoder_atomic_check(struct drm_encoder *encoder,
 					struct drm_crtc_state *crtc_state,
 					struct drm_connector_state *conn_state)
 {
+	struct drm_connector *connector = conn_state->connector;
 	struct drm_framebuffer *fb;
 	const struct drm_display_mode *mode = &crtc_state->mode;
 	int ret;
@@ -48,7 +49,7 @@ static int vkms_wb_encoder_atomic_check(struct drm_encoder *encoder,
 		return -EINVAL;
 	}
 
-	ret = drm_atomic_helper_check_wb_encoder_state(encoder, conn_state);
+	ret = drm_atomic_helper_check_wb_connector_state(connector, conn_state->state);
 	if (ret < 0)
 		return ret;
 
diff --git a/include/drm/drm_atomic_helper.h b/include/drm/drm_atomic_helper.h
index 536a0b0091c3..fea528aacfe2 100644
--- a/include/drm/drm_atomic_helper.h
+++ b/include/drm/drm_atomic_helper.h
@@ -49,9 +49,8 @@ struct drm_private_state;
 
 int drm_atomic_helper_check_modeset(struct drm_device *dev,
 				struct drm_atomic_state *state);
-int
-drm_atomic_helper_check_wb_encoder_state(struct drm_encoder *encoder,
-					 struct drm_connector_state *conn_state);
+int drm_atomic_helper_check_wb_connector_state(struct drm_connector *connector,
+					       struct drm_atomic_state *state);
 int drm_atomic_helper_check_plane_state(struct drm_plane_state *plane_state,
 					const struct drm_crtc_state *crtc_state,
 					int min_scale,
-- 
cgit v1.2.3


From bd4a816752bab609dd6d65ae021387beb9e2ddbd Mon Sep 17 00:00:00 2001
From: Maciej Żenczykowski <maze@google.com>
Date: Wed, 6 Dec 2023 09:36:12 -0800
Subject: net: ipv6: support reporting otherwise unknown prefix flags in
 RTM_NEWPREFIX
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Lorenzo points out that we effectively clear all unknown
flags from PIO when copying them to userspace in the netlink
RTM_NEWPREFIX notification.

We could fix this one at a time as new flags are defined,
or in one fell swoop - I choose the latter.

We could either define 6 new reserved flags (reserved1..6) and handle
them individually (and rename them as new flags are defined), or we
could simply copy the entire unmodified byte over - I choose the latter.

This unfortunately requires some anonymous union/struct magic,
so we add a static assert on the struct size for a little extra safety.

Cc: David Ahern <dsahern@kernel.org>
Cc: Lorenzo Colitti <lorenzo@google.com>
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Maciej Żenczykowski <maze@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/addrconf.h | 12 ++++++++++--
 include/net/if_inet6.h |  4 ----
 net/ipv6/addrconf.c    |  6 +-----
 3 files changed, 11 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 82da55101b5a..61ebe723ee4d 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -31,17 +31,22 @@ struct prefix_info {
 	__u8			length;
 	__u8			prefix_len;
 
+	union __packed {
+		__u8		flags;
+		struct __packed {
 #if defined(__BIG_ENDIAN_BITFIELD)
-	__u8			onlink : 1,
+			__u8	onlink : 1,
 			 	autoconf : 1,
 				reserved : 6;
 #elif defined(__LITTLE_ENDIAN_BITFIELD)
-	__u8			reserved : 6,
+			__u8	reserved : 6,
 				autoconf : 1,
 				onlink : 1;
 #else
 #error "Please fix <asm/byteorder.h>"
 #endif
+		};
+	};
 	__be32			valid;
 	__be32			prefered;
 	__be32			reserved2;
@@ -49,6 +54,9 @@ struct prefix_info {
 	struct in6_addr		prefix;
 };
 
+/* rfc4861 4.6.2: IPv6 PIO is 32 bytes in size */
+static_assert(sizeof(struct prefix_info) == 32);
+
 #include <linux/ipv6.h>
 #include <linux/netdevice.h>
 #include <net/if_inet6.h>
diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h
index 3e454c4d7ba6..f07642264c1e 100644
--- a/include/net/if_inet6.h
+++ b/include/net/if_inet6.h
@@ -22,10 +22,6 @@
 #define IF_RS_SENT	0x10
 #define IF_READY	0x80000000
 
-/* prefix flags */
-#define IF_PREFIX_ONLINK	0x01
-#define IF_PREFIX_AUTOCONF	0x02
-
 enum {
 	INET6_IFADDR_STATE_PREDAD,
 	INET6_IFADDR_STATE_DAD,
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 3aaea56b5166..2692a7b24c40 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -6149,11 +6149,7 @@ static int inet6_fill_prefix(struct sk_buff *skb, struct inet6_dev *idev,
 	pmsg->prefix_len = pinfo->prefix_len;
 	pmsg->prefix_type = pinfo->type;
 	pmsg->prefix_pad3 = 0;
-	pmsg->prefix_flags = 0;
-	if (pinfo->onlink)
-		pmsg->prefix_flags |= IF_PREFIX_ONLINK;
-	if (pinfo->autoconf)
-		pmsg->prefix_flags |= IF_PREFIX_AUTOCONF;
+	pmsg->prefix_flags = pinfo->flags;
 
 	if (nla_put(skb, PREFIX_ADDRESS, sizeof(pinfo->prefix), &pinfo->prefix))
 		goto nla_put_failure;
-- 
cgit v1.2.3


From 2a48c635fd9a48699805bbfeee1e4b94b8fe819d Mon Sep 17 00:00:00 2001
From: "justinstitt@google.com" <justinstitt@google.com>
Date: Wed, 6 Dec 2023 23:16:10 +0000
Subject: ethtool: Implement ethtool_puts()

Use strscpy() to implement ethtool_puts().

Functionally the same as ethtool_sprintf() when it's used with two
arguments or with just "%s" format specifier.

Signed-off-by: Justin Stitt <justinstitt@google.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Madhuri Sripada <madhuri.sripada@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ethtool.h | 13 +++++++++++++
 net/ethtool/ioctl.c     |  7 +++++++
 2 files changed, 20 insertions(+)

(limited to 'include')

diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index c2bb74143eda..deb683d3360f 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -1061,6 +1061,19 @@ int ethtool_get_ts_info_by_layer(struct net_device *dev, struct ethtool_ts_info
  */
 extern __printf(2, 3) void ethtool_sprintf(u8 **data, const char *fmt, ...);
 
+/**
+ * ethtool_puts - Write string to ethtool string data
+ * @data: Pointer to a pointer to the start of string to update
+ * @str: String to write
+ *
+ * Write string to *data without a trailing newline. Update *data
+ * to point at start of next string.
+ *
+ * Prefer this function to ethtool_sprintf() when given only
+ * two arguments or if @fmt is just "%s".
+ */
+extern void ethtool_puts(u8 **data, const char *str);
+
 /* Link mode to forced speed capabilities maps */
 struct ethtool_forced_speed_map {
 	u32		speed;
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index a977f8903467..755a4be01bef 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -1994,6 +1994,13 @@ __printf(2, 3) void ethtool_sprintf(u8 **data, const char *fmt, ...)
 }
 EXPORT_SYMBOL(ethtool_sprintf);
 
+void ethtool_puts(u8 **data, const char *str)
+{
+	strscpy(*data, str, ETH_GSTRING_LEN);
+	*data += ETH_GSTRING_LEN;
+}
+EXPORT_SYMBOL(ethtool_puts);
+
 static int ethtool_phys_id(struct net_device *dev, void __user *useraddr)
 {
 	struct ethtool_value id;
-- 
cgit v1.2.3


From 675bf8ef209cc8da28ffefd7d8a93c53735cc84a Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Thu, 30 Nov 2023 12:30:01 +0100
Subject: tty: virtio: drop virtio_cons_early_init()

The last user of virtio_cons_early_init() was dropped in commit
7fb2b2d51244 ("s390/virtio: remove the old KVM virtio transport").

So now, drop virtio_cons_early_init() and the logic and headers behind
too.

Signed-off-by: Jiri Slaby (SUSE) <jirislaby@kernel.org>
Acked-by: Jason Wang <jasowang@redhat.com>
Cc: Richard Henderson <richard.henderson@linaro.org>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Amit Shah <amit@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Cc: linux-alpha@vger.kernel.org
Cc: virtualization@lists.linux.dev
Link: https://lore.kernel.org/r/20231130113001.29154-1-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 MAINTAINERS                    |  1 -
 drivers/char/virtio_console.c  | 48 ------------------------------------------
 include/linux/virtio_console.h | 38 ---------------------------------
 3 files changed, 87 deletions(-)
 delete mode 100644 include/linux/virtio_console.h

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index ea790149af79..d60009f3ef9c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -23018,7 +23018,6 @@ M:	Amit Shah <amit@kernel.org>
 L:	virtualization@lists.linux.dev
 S:	Maintained
 F:	drivers/char/virtio_console.c
-F:	include/linux/virtio_console.h
 F:	include/uapi/linux/virtio_console.h
 
 VIRTIO CORE AND NET DRIVERS
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 431e9e5bf9c1..8abe599c1c07 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -230,9 +230,6 @@ struct port {
 	bool guest_connected;
 };
 
-/* This is the very early arch-specified put chars function. */
-static int (*early_put_chars)(u32, const char *, int);
-
 static struct port *find_port_by_vtermno(u32 vtermno)
 {
 	struct port *port;
@@ -1114,9 +1111,6 @@ static int put_chars(u32 vtermno, const char *buf, int count)
 	void *data;
 	int ret;
 
-	if (unlikely(early_put_chars))
-		return early_put_chars(vtermno, buf, count);
-
 	port = find_port_by_vtermno(vtermno);
 	if (!port)
 		return -EPIPE;
@@ -1142,10 +1136,6 @@ static int get_chars(u32 vtermno, char *buf, int count)
 {
 	struct port *port;
 
-	/* If we've not set up the port yet, we have no input to give. */
-	if (unlikely(early_put_chars))
-		return 0;
-
 	port = find_port_by_vtermno(vtermno);
 	if (!port)
 		return -EPIPE;
@@ -1201,21 +1191,6 @@ static const struct hv_ops hv_ops = {
 	.notifier_hangup = notifier_del_vio,
 };
 
-/*
- * Console drivers are initialized very early so boot messages can go
- * out, so we do things slightly differently from the generic virtio
- * initialization of the net and block drivers.
- *
- * At this stage, the console is output-only.  It's too early to set
- * up a virtqueue, so we let the drivers do some boutique early-output
- * thing.
- */
-int __init virtio_cons_early_init(int (*put_chars)(u32, const char *, int))
-{
-	early_put_chars = put_chars;
-	return hvc_instantiate(0, 0, &hv_ops);
-}
-
 static int init_port_console(struct port *port)
 {
 	int ret;
@@ -1256,13 +1231,6 @@ static int init_port_console(struct port *port)
 	spin_unlock_irq(&pdrvdata_lock);
 	port->guest_connected = true;
 
-	/*
-	 * Start using the new console output if this is the first
-	 * console to come up.
-	 */
-	if (early_put_chars)
-		early_put_chars = NULL;
-
 	/* Notify host of port being opened */
 	send_control_msg(port, VIRTIO_CONSOLE_PORT_OPEN, 1);
 
@@ -1999,7 +1967,6 @@ static int virtcons_probe(struct virtio_device *vdev)
 	struct ports_device *portdev;
 	int err;
 	bool multiport;
-	bool early = early_put_chars != NULL;
 
 	/* We only need a config space if features are offered */
 	if (!vdev->config->get &&
@@ -2010,9 +1977,6 @@ static int virtcons_probe(struct virtio_device *vdev)
 		return -EINVAL;
 	}
 
-	/* Ensure to read early_put_chars now */
-	barrier();
-
 	portdev = kmalloc(sizeof(*portdev), GFP_KERNEL);
 	if (!portdev) {
 		err = -ENOMEM;
@@ -2100,18 +2064,6 @@ static int virtcons_probe(struct virtio_device *vdev)
 	__send_control_msg(portdev, VIRTIO_CONSOLE_BAD_ID,
 			   VIRTIO_CONSOLE_DEVICE_READY, 1);
 
-	/*
-	 * If there was an early virtio console, assume that there are no
-	 * other consoles. We need to wait until the hvc_alloc matches the
-	 * hvc_instantiate, otherwise tty_open will complain, resulting in
-	 * a "Warning: unable to open an initial console" boot failure.
-	 * Without multiport this is done in add_port above. With multiport
-	 * this might take some host<->guest communication - thus we have to
-	 * wait.
-	 */
-	if (multiport && early)
-		wait_for_completion(&early_console_added);
-
 	return 0;
 
 free_chrdev:
diff --git a/include/linux/virtio_console.h b/include/linux/virtio_console.h
deleted file mode 100644
index d2e2785af602..000000000000
--- a/include/linux/virtio_console.h
+++ /dev/null
@@ -1,38 +0,0 @@
-/*
- * This header, excluding the #ifdef __KERNEL__ part, is BSD licensed so
- * anyone can use the definitions to implement compatible drivers/servers:
- *
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the name of IBM nor the names of its contributors
- *    may be used to endorse or promote products derived from this software
- *    without specific prior written permission.
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
- * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
- * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
- * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
- * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
- * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
- * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
- * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
- * SUCH DAMAGE.
- *
- * Copyright (C) Red Hat, Inc., 2009, 2010, 2011
- * Copyright (C) Amit Shah <amit.shah@redhat.com>, 2009, 2010, 2011
- */
-#ifndef _LINUX_VIRTIO_CONSOLE_H
-#define _LINUX_VIRTIO_CONSOLE_H
-
-#include <uapi/linux/virtio_console.h>
-
-int __init virtio_cons_early_init(int (*put_chars)(u32, const char *, int));
-#endif /* _LINUX_VIRTIO_CONSOLE_H */
-- 
cgit v1.2.3


From 093258a9963bfac043244995bff87dc2c931b9b5 Mon Sep 17 00:00:00 2001
From: Théo Lebrun <theo.lebrun@bootlin.com>
Date: Thu, 30 Nov 2023 15:07:13 +0100
Subject: tty: serial: amba: cleanup whitespace
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix whitespace in include/linux/amba/serial.h to match current kernel
coding standards. Fixes about:

 - CHECK: spaces preferred around that '|' (ctx:VxV)
 - ERROR: code indent should use tabs where possible
 - WARNING: Unnecessary space before function pointer arguments
 - WARNING: please, no spaces at the start of a line

Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Théo Lebrun <theo.lebrun@bootlin.com>
Link: https://lore.kernel.org/r/20231130-mbly-uart-v5-1-6566703a04b5@bootlin.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/amba/serial.h | 28 ++++++++++++++--------------
 1 file changed, 14 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/linux/amba/serial.h b/include/linux/amba/serial.h
index a1307b58cc2c..27003ec52114 100644
--- a/include/linux/amba/serial.h
+++ b/include/linux/amba/serial.h
@@ -75,10 +75,10 @@
 #define UART011_DR_PE		(1 << 9)
 #define UART011_DR_FE		(1 << 8)
 
-#define UART01x_RSR_OE 		0x08
-#define UART01x_RSR_BE 		0x04
-#define UART01x_RSR_PE 		0x02
-#define UART01x_RSR_FE 		0x01
+#define UART01x_RSR_OE		0x08
+#define UART01x_RSR_BE		0x04
+#define UART01x_RSR_PE		0x02
+#define UART01x_RSR_FE		0x01
 
 #define UART011_FR_RI		0x100
 #define UART011_FR_TXFE		0x080
@@ -86,9 +86,9 @@
 #define UART01x_FR_TXFF		0x020
 #define UART01x_FR_RXFE		0x010
 #define UART01x_FR_BUSY		0x008
-#define UART01x_FR_DCD 		0x004
-#define UART01x_FR_DSR 		0x002
-#define UART01x_FR_CTS 		0x001
+#define UART01x_FR_DCD		0x004
+#define UART01x_FR_DSR		0x002
+#define UART01x_FR_CTS		0x001
 #define UART01x_FR_TMSK		(UART01x_FR_TXFF + UART01x_FR_BUSY)
 
 /*
@@ -110,14 +110,14 @@
 #define UART011_CR_TXE		0x0100	/* transmit enable */
 #define UART011_CR_LBE		0x0080	/* loopback enable */
 #define UART010_CR_RTIE		0x0040
-#define UART010_CR_TIE 		0x0020
-#define UART010_CR_RIE 		0x0010
+#define UART010_CR_TIE		0x0020
+#define UART010_CR_RIE		0x0010
 #define UART010_CR_MSIE		0x0008
 #define ST_UART011_CR_OVSFACT	0x0008	/* Oversampling factor */
 #define UART01x_CR_IIRLP	0x0004	/* SIR low power mode */
 #define UART01x_CR_SIREN	0x0002	/* SIR enable */
 #define UART01x_CR_UARTEN	0x0001	/* UART enable */
- 
+
 #define UART011_LCRH_SPS	0x80
 #define UART01x_LCRH_WLEN_8	0x60
 #define UART01x_LCRH_WLEN_7	0x40
@@ -203,8 +203,8 @@
 #define UART011_TXDMAE		(1 << 1)	/* enable transmit dma */
 #define UART011_RXDMAE		(1 << 0)	/* enable receive dma */
 
-#define UART01x_RSR_ANY		(UART01x_RSR_OE|UART01x_RSR_BE|UART01x_RSR_PE|UART01x_RSR_FE)
-#define UART01x_FR_MODEM_ANY	(UART01x_FR_DCD|UART01x_FR_DSR|UART01x_FR_CTS)
+#define UART01x_RSR_ANY		(UART01x_RSR_OE | UART01x_RSR_BE | UART01x_RSR_PE | UART01x_RSR_FE)
+#define UART01x_FR_MODEM_ANY	(UART01x_FR_DCD | UART01x_FR_DSR | UART01x_FR_CTS)
 
 #ifndef __ASSEMBLY__
 struct amba_device; /* in uncompress this is included but amba/bus.h is not */
@@ -220,8 +220,8 @@ struct amba_pl011_data {
 	bool dma_rx_poll_enable;
 	unsigned int dma_rx_poll_rate;
 	unsigned int dma_rx_poll_timeout;
-        void (*init) (void);
-	void (*exit) (void);
+	void (*init)(void);
+	void (*exit)(void);
 };
 #endif
 
-- 
cgit v1.2.3


From 49943393c9f0be61fd494a884851aa117cd72382 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 6 Dec 2023 08:36:48 +0100
Subject: tty: switch tty_port::xmit_* to u8

Both xmit_buf and xmit_fifo of struct tty_port should be u8. To conform
to characters in the rest of the tty layer.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Link: https://lore.kernel.org/r/20231206073712.17776-4-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/tty_port.c   | 2 +-
 include/linux/tty_port.h | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/tty_port.c b/drivers/tty/tty_port.c
index ef72d2e4b928..14cca33d2269 100644
--- a/drivers/tty/tty_port.c
+++ b/drivers/tty/tty_port.c
@@ -247,7 +247,7 @@ int tty_port_alloc_xmit_buf(struct tty_port *port)
 	/* We may sleep in get_zeroed_page() */
 	mutex_lock(&port->buf_mutex);
 	if (port->xmit_buf == NULL) {
-		port->xmit_buf = (unsigned char *)get_zeroed_page(GFP_KERNEL);
+		port->xmit_buf = (u8 *)get_zeroed_page(GFP_KERNEL);
 		if (port->xmit_buf)
 			kfifo_init(&port->xmit_fifo, port->xmit_buf, PAGE_SIZE);
 	}
diff --git a/include/linux/tty_port.h b/include/linux/tty_port.h
index 3276311a7f38..1b861f2100b6 100644
--- a/include/linux/tty_port.h
+++ b/include/linux/tty_port.h
@@ -114,8 +114,8 @@ struct tty_port {
 	unsigned char		console:1;
 	struct mutex		mutex;
 	struct mutex		buf_mutex;
-	unsigned char		*xmit_buf;
-	DECLARE_KFIFO_PTR(xmit_fifo, unsigned char);
+	u8			*xmit_buf;
+	DECLARE_KFIFO_PTR(xmit_fifo, u8);
 	unsigned int		close_delay;
 	unsigned int		closing_wait;
 	int			drain_delay;
-- 
cgit v1.2.3


From 3a00da027946cd08db1c1be2de4620950bbdf074 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 6 Dec 2023 08:36:49 +0100
Subject: tty: make tty_operations::send_xchar accept u8 char

tty_operations::send_xchar is one of the last users of 'char' type for
characters in the tty layer. Convert it to u8 now.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Cc: Karsten Keil <isdn@linux-pingi.de>
Cc: Ulf Hansson <ulf.hansson@linaro.org>
Cc: Marcel Holtmann <marcel@holtmann.org>
Cc: Johan Hedberg <johan.hedberg@gmail.com>
Cc: Luiz Augusto von Dentz <luiz.dentz@gmail.com>
Cc: netdev@vger.kernel.org
Cc: linux-mmc@vger.kernel.org
Cc: linux-bluetooth@vger.kernel.org
Reviewed-by: Geert Uytterhoeven <geert@linux-m68k.org>
Link: https://lore.kernel.org/r/20231206073712.17776-5-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/isdn/capi/capi.c         | 4 ++--
 drivers/mmc/core/sdio_uart.c     | 2 +-
 drivers/tty/amiserial.c          | 2 +-
 drivers/tty/serial/serial_core.c | 2 +-
 drivers/tty/tty_io.c             | 2 +-
 include/linux/tty.h              | 2 +-
 include/linux/tty_driver.h       | 4 ++--
 net/bluetooth/rfcomm/tty.c       | 2 +-
 8 files changed, 10 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/isdn/capi/capi.c b/drivers/isdn/capi/capi.c
index 2f3789515445..6e80d7bd3c4d 100644
--- a/drivers/isdn/capi/capi.c
+++ b/drivers/isdn/capi/capi.c
@@ -1231,9 +1231,9 @@ static void capinc_tty_hangup(struct tty_struct *tty)
 	tty_port_hangup(&mp->port);
 }
 
-static void capinc_tty_send_xchar(struct tty_struct *tty, char ch)
+static void capinc_tty_send_xchar(struct tty_struct *tty, u8 ch)
 {
-	pr_debug("capinc_tty_send_xchar(%d)\n", ch);
+	pr_debug("capinc_tty_send_xchar(%u)\n", ch);
 }
 
 static const struct tty_operations capinc_ops = {
diff --git a/drivers/mmc/core/sdio_uart.c b/drivers/mmc/core/sdio_uart.c
index a05322f15771..370fadf1d6d1 100644
--- a/drivers/mmc/core/sdio_uart.c
+++ b/drivers/mmc/core/sdio_uart.c
@@ -792,7 +792,7 @@ static unsigned int sdio_uart_chars_in_buffer(struct tty_struct *tty)
 	return kfifo_len(&port->xmit_fifo);
 }
 
-static void sdio_uart_send_xchar(struct tty_struct *tty, char ch)
+static void sdio_uart_send_xchar(struct tty_struct *tty, u8 ch)
 {
 	struct sdio_uart_port *port = tty->driver_data;
 
diff --git a/drivers/tty/amiserial.c b/drivers/tty/amiserial.c
index a80f059f77bf..a30dc054ffbf 100644
--- a/drivers/tty/amiserial.c
+++ b/drivers/tty/amiserial.c
@@ -811,7 +811,7 @@ static void rs_flush_buffer(struct tty_struct *tty)
  * This function is used to send a high-priority XON/XOFF character to
  * the device
  */
-static void rs_send_xchar(struct tty_struct *tty, char ch)
+static void rs_send_xchar(struct tty_struct *tty, u8 ch)
 {
 	struct serial_state *info = tty->driver_data;
         unsigned long flags;
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 0393853b9947..80085b151b34 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -687,7 +687,7 @@ EXPORT_SYMBOL_GPL(uart_xchar_out);
  * This function is used to send a high-priority XON/XOFF character to
  * the device
  */
-static void uart_send_xchar(struct tty_struct *tty, char ch)
+static void uart_send_xchar(struct tty_struct *tty, u8 ch)
 {
 	struct uart_state *state = tty->driver_data;
 	struct uart_port *port;
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 005d91c63707..6a502110da61 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -1149,7 +1149,7 @@ ssize_t redirected_tty_write(struct kiocb *iocb, struct iov_iter *iter)
  *
  * Locking: none for xchar method, write ordering for write method.
  */
-int tty_send_xchar(struct tty_struct *tty, char ch)
+int tty_send_xchar(struct tty_struct *tty, u8 ch)
 {
 	bool was_stopped = tty->flow.stopped;
 
diff --git a/include/linux/tty.h b/include/linux/tty.h
index e96c85f4f91e..d3bedcc08738 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -410,7 +410,7 @@ void tty_wait_until_sent(struct tty_struct *tty, long timeout);
 void stop_tty(struct tty_struct *tty);
 void start_tty(struct tty_struct *tty);
 void tty_write_message(struct tty_struct *tty, char *msg);
-int tty_send_xchar(struct tty_struct *tty, char ch);
+int tty_send_xchar(struct tty_struct *tty, u8 ch);
 int tty_put_char(struct tty_struct *tty, unsigned char c);
 unsigned int tty_chars_in_buffer(struct tty_struct *tty);
 unsigned int tty_write_room(struct tty_struct *tty);
diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h
index f428c1b784a2..7372124fbf90 100644
--- a/include/linux/tty_driver.h
+++ b/include/linux/tty_driver.h
@@ -242,7 +242,7 @@ struct serial_struct;
  *	Optional: If not provided, the device is assumed to have no FIFO.
  *	Usually correct to invoke via tty_wait_until_sent(). May sleep.
  *
- * @send_xchar: ``void ()(struct tty_struct *tty, char ch)``
+ * @send_xchar: ``void ()(struct tty_struct *tty, u8 ch)``
  *
  *	This routine is used to send a high-priority XON/XOFF character (@ch)
  *	to the @tty device.
@@ -374,7 +374,7 @@ struct tty_operations {
 	void (*flush_buffer)(struct tty_struct *tty);
 	void (*set_ldisc)(struct tty_struct *tty);
 	void (*wait_until_sent)(struct tty_struct *tty, int timeout);
-	void (*send_xchar)(struct tty_struct *tty, char ch);
+	void (*send_xchar)(struct tty_struct *tty, u8 ch);
 	int (*tiocmget)(struct tty_struct *tty);
 	int (*tiocmset)(struct tty_struct *tty,
 			unsigned int set, unsigned int clear);
diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c
index 94ec913dfb76..69c75c041fe1 100644
--- a/net/bluetooth/rfcomm/tty.c
+++ b/net/bluetooth/rfcomm/tty.c
@@ -1041,7 +1041,7 @@ static void rfcomm_tty_flush_buffer(struct tty_struct *tty)
 	tty_wakeup(tty);
 }
 
-static void rfcomm_tty_send_xchar(struct tty_struct *tty, char ch)
+static void rfcomm_tty_send_xchar(struct tty_struct *tty, u8 ch)
 {
 	BT_DBG("tty %p ch %c", tty, ch);
 }
-- 
cgit v1.2.3


From 4e8d8878145f1478886e1630c44113ad2c2eb99d Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 6 Dec 2023 08:36:50 +0100
Subject: tty: core: the rest to u8

There are still last minor users in the tty core that still reference
characters by the 'char' type. Switch them to u8.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Link: https://lore.kernel.org/r/20231206073712.17776-6-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/tty_io.c | 10 +++++-----
 include/linux/tty.h  |  4 ++--
 2 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 6a502110da61..f3ca2105b66d 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -852,9 +852,9 @@ static ssize_t iterate_tty_read(struct tty_ldisc *ld, struct tty_struct *tty,
 {
 	void *cookie = NULL;
 	unsigned long offset = 0;
-	char kernel_buf[64];
 	ssize_t retval = 0;
 	size_t copied, count = iov_iter_count(to);
+	u8 kernel_buf[64];
 
 	do {
 		ssize_t size = min(count, sizeof(kernel_buf));
@@ -995,7 +995,7 @@ static ssize_t iterate_tty_write(struct tty_ldisc *ld, struct tty_struct *tty,
 
 	/* write_buf/write_cnt is protected by the atomic_write_lock mutex */
 	if (tty->write_cnt < chunk) {
-		unsigned char *buf_chunk;
+		u8 *buf_chunk;
 
 		if (chunk < 1024)
 			chunk = 1024;
@@ -2278,10 +2278,10 @@ static bool tty_legacy_tiocsti __read_mostly = IS_ENABLED(CONFIG_LEGACY_TIOCSTI)
  *  * Called functions take tty_ldiscs_lock
  *  * current->signal->tty check is safe without locks
  */
-static int tiocsti(struct tty_struct *tty, char __user *p)
+static int tiocsti(struct tty_struct *tty, u8 __user *p)
 {
-	char ch;
 	struct tty_ldisc *ld;
+	u8 ch;
 
 	if (!tty_legacy_tiocsti && !capable(CAP_SYS_ADMIN))
 		return -EIO;
@@ -3142,7 +3142,7 @@ struct tty_struct *alloc_tty_struct(struct tty_driver *driver, int idx)
  *
  * Return: the number of characters successfully output.
  */
-int tty_put_char(struct tty_struct *tty, unsigned char ch)
+int tty_put_char(struct tty_struct *tty, u8 ch)
 {
 	if (tty->ops->put_char)
 		return tty->ops->put_char(tty, ch);
diff --git a/include/linux/tty.h b/include/linux/tty.h
index d3bedcc08738..cc08f7e1c122 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -242,7 +242,7 @@ struct tty_struct {
 	void *driver_data;
 	spinlock_t files_lock;
 	int write_cnt;
-	unsigned char *write_buf;
+	u8 *write_buf;
 
 	struct list_head tty_files;
 
@@ -411,7 +411,7 @@ void stop_tty(struct tty_struct *tty);
 void start_tty(struct tty_struct *tty);
 void tty_write_message(struct tty_struct *tty, char *msg);
 int tty_send_xchar(struct tty_struct *tty, u8 ch);
-int tty_put_char(struct tty_struct *tty, unsigned char c);
+int tty_put_char(struct tty_struct *tty, u8 c);
 unsigned int tty_chars_in_buffer(struct tty_struct *tty);
 unsigned int tty_write_room(struct tty_struct *tty);
 void tty_driver_flush_buffer(struct tty_struct *tty);
-- 
cgit v1.2.3


From f2470d2bc4327c2c1a604c6e247442dbb14c90c5 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 6 Dec 2023 08:37:07 +0100
Subject: tty: serdev: convert to u8 and size_t in serdev_controller_ops

Switch character types to u8 and sizes to size_t. To conform to
characters/sizes in the rest of the tty layer.

In this patch, only struct serdev_controller_ops hooks. The rest will
follow.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Cc: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20231206073712.17776-23-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serdev/serdev-ttyport.c | 2 +-
 include/linux/serdev.h              | 8 ++++----
 2 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/serdev/serdev-ttyport.c b/drivers/tty/serdev/serdev-ttyport.c
index c5381fe15e1c..e94e090cf0a1 100644
--- a/drivers/tty/serdev/serdev-ttyport.c
+++ b/drivers/tty/serdev/serdev-ttyport.c
@@ -74,7 +74,7 @@ static const struct tty_port_client_operations client_ops = {
  * Callback functions from the serdev core.
  */
 
-static int ttyport_write_buf(struct serdev_controller *ctrl, const unsigned char *data, size_t len)
+static ssize_t ttyport_write_buf(struct serdev_controller *ctrl, const u8 *data, size_t len)
 {
 	struct serport *serport = serdev_controller_get_drvdata(ctrl);
 	struct tty_struct *tty = serport->tty;
diff --git a/include/linux/serdev.h b/include/linux/serdev.h
index 0ebf53bb254f..8cdab2c3b6d5 100644
--- a/include/linux/serdev.h
+++ b/include/linux/serdev.h
@@ -82,7 +82,7 @@ enum serdev_parity {
  * serdev controller structures
  */
 struct serdev_controller_ops {
-	int (*write_buf)(struct serdev_controller *, const unsigned char *, size_t);
+	ssize_t (*write_buf)(struct serdev_controller *, const u8 *, size_t);
 	void (*write_flush)(struct serdev_controller *);
 	int (*write_room)(struct serdev_controller *);
 	int (*open)(struct serdev_controller *);
@@ -185,9 +185,9 @@ static inline void serdev_controller_write_wakeup(struct serdev_controller *ctrl
 	serdev->ops->write_wakeup(serdev);
 }
 
-static inline int serdev_controller_receive_buf(struct serdev_controller *ctrl,
-					      const unsigned char *data,
-					      size_t count)
+static inline ssize_t serdev_controller_receive_buf(struct serdev_controller *ctrl,
+						    const u8 *data,
+						    size_t count)
 {
 	struct serdev_device *serdev = ctrl->serdev;
 
-- 
cgit v1.2.3


From 475fc6e2de6fec0ff3c9a74ddcfd2b52c90adc0d Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 6 Dec 2023 08:37:08 +0100
Subject: tty: serdev: convert to u8 and size_t

Switch character types to u8 and sizes to size_t. To conform to
characters/sizes in the rest of the tty layer.

This patch converts struct serdev_device_ops hooks and its
instantiations.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Cc: Rob Herring <robh@kernel.org>
Acked-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20231206073712.17776-24-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bluetooth/btmtkuart.c                          |  4 ++--
 drivers/bluetooth/btnxpuart.c                          |  4 ++--
 drivers/bluetooth/hci_serdev.c                         |  4 ++--
 drivers/gnss/serial.c                                  |  4 ++--
 drivers/gnss/sirf.c                                    |  4 ++--
 drivers/greybus/gb-beagleplay.c                        |  5 +++--
 drivers/iio/chemical/pms7003.c                         |  6 +++---
 drivers/iio/chemical/scd30_serial.c                    |  6 +++---
 drivers/iio/chemical/sps30_serial.c                    | 18 +++++++++---------
 drivers/iio/imu/bno055/bno055_ser_core.c               |  6 +++---
 drivers/mfd/rave-sp.c                                  | 10 +++++-----
 drivers/net/ethernet/qualcomm/qca_uart.c               |  5 ++---
 drivers/nfc/pn533/uart.c                               |  4 ++--
 drivers/nfc/s3fwrn5/uart.c                             |  5 ++---
 drivers/platform/chrome/cros_ec_uart.c                 |  5 ++---
 drivers/platform/surface/aggregator/controller.h       |  4 ++--
 drivers/platform/surface/aggregator/core.c             |  4 ++--
 drivers/platform/surface/aggregator/ssh_packet_layer.c |  4 ++--
 drivers/platform/surface/aggregator/ssh_packet_layer.h |  2 +-
 drivers/tty/serdev/core.c                              | 12 +++++-------
 include/linux/serdev.h                                 | 13 +++++++------
 sound/drivers/serial-generic.c                         |  4 ++--
 22 files changed, 65 insertions(+), 68 deletions(-)

(limited to 'include')

diff --git a/drivers/bluetooth/btmtkuart.c b/drivers/bluetooth/btmtkuart.c
index 935feab815d9..d4f4e40ac5d2 100644
--- a/drivers/bluetooth/btmtkuart.c
+++ b/drivers/bluetooth/btmtkuart.c
@@ -385,8 +385,8 @@ static int btmtkuart_recv(struct hci_dev *hdev, const u8 *data, size_t count)
 	return 0;
 }
 
-static int btmtkuart_receive_buf(struct serdev_device *serdev, const u8 *data,
-				 size_t count)
+static ssize_t btmtkuart_receive_buf(struct serdev_device *serdev,
+				     const u8 *data, size_t count)
 {
 	struct btmtkuart_dev *bdev = serdev_device_get_drvdata(serdev);
 	int err;
diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c
index b7e66b7ac570..d75487a90bba 100644
--- a/drivers/bluetooth/btnxpuart.c
+++ b/drivers/bluetooth/btnxpuart.c
@@ -1264,8 +1264,8 @@ static const struct h4_recv_pkt nxp_recv_pkts[] = {
 	{ NXP_RECV_FW_REQ_V3,   .recv = nxp_recv_fw_req_v3 },
 };
 
-static int btnxpuart_receive_buf(struct serdev_device *serdev, const u8 *data,
-				 size_t count)
+static ssize_t btnxpuart_receive_buf(struct serdev_device *serdev,
+				     const u8 *data, size_t count)
 {
 	struct btnxpuart_dev *nxpdev = serdev_device_get_drvdata(serdev);
 
diff --git a/drivers/bluetooth/hci_serdev.c b/drivers/bluetooth/hci_serdev.c
index f16fd79bc02b..39c8b567da3c 100644
--- a/drivers/bluetooth/hci_serdev.c
+++ b/drivers/bluetooth/hci_serdev.c
@@ -271,8 +271,8 @@ static void hci_uart_write_wakeup(struct serdev_device *serdev)
  *
  * Return: number of processed bytes
  */
-static int hci_uart_receive_buf(struct serdev_device *serdev, const u8 *data,
-				   size_t count)
+static ssize_t hci_uart_receive_buf(struct serdev_device *serdev,
+				    const u8 *data, size_t count)
 {
 	struct hci_uart *hu = serdev_device_get_drvdata(serdev);
 
diff --git a/drivers/gnss/serial.c b/drivers/gnss/serial.c
index 5d8e9bfb24d0..baa956494e79 100644
--- a/drivers/gnss/serial.c
+++ b/drivers/gnss/serial.c
@@ -80,8 +80,8 @@ static const struct gnss_operations gnss_serial_gnss_ops = {
 	.write_raw	= gnss_serial_write_raw,
 };
 
-static int gnss_serial_receive_buf(struct serdev_device *serdev,
-					const unsigned char *buf, size_t count)
+static ssize_t gnss_serial_receive_buf(struct serdev_device *serdev,
+				       const u8 *buf, size_t count)
 {
 	struct gnss_serial *gserial = serdev_device_get_drvdata(serdev);
 	struct gnss_device *gdev = gserial->gdev;
diff --git a/drivers/gnss/sirf.c b/drivers/gnss/sirf.c
index bcb53ccfee4d..6801a8fb2040 100644
--- a/drivers/gnss/sirf.c
+++ b/drivers/gnss/sirf.c
@@ -160,8 +160,8 @@ static const struct gnss_operations sirf_gnss_ops = {
 	.write_raw	= sirf_write_raw,
 };
 
-static int sirf_receive_buf(struct serdev_device *serdev,
-				const unsigned char *buf, size_t count)
+static ssize_t sirf_receive_buf(struct serdev_device *serdev,
+				const u8 *buf, size_t count)
 {
 	struct sirf_data *data = serdev_device_get_drvdata(serdev);
 	struct gnss_device *gdev = data->gdev;
diff --git a/drivers/greybus/gb-beagleplay.c b/drivers/greybus/gb-beagleplay.c
index 43318c1993ba..2da37ff92cf1 100644
--- a/drivers/greybus/gb-beagleplay.c
+++ b/drivers/greybus/gb-beagleplay.c
@@ -257,7 +257,7 @@ static void hdlc_rx_frame(struct gb_beagleplay *bg)
 	}
 }
 
-static int hdlc_rx(struct gb_beagleplay *bg, const u8 *data, size_t count)
+static ssize_t hdlc_rx(struct gb_beagleplay *bg, const u8 *data, size_t count)
 {
 	size_t i;
 	u8 c;
@@ -317,7 +317,8 @@ static void hdlc_deinit(struct gb_beagleplay *bg)
 	flush_work(&bg->tx_work);
 }
 
-static int gb_tty_receive(struct serdev_device *sd, const unsigned char *data, size_t count)
+static ssize_t gb_tty_receive(struct serdev_device *sd, const u8 *data,
+			      size_t count)
 {
 	struct gb_beagleplay *bg = serdev_device_get_drvdata(sd);
 
diff --git a/drivers/iio/chemical/pms7003.c b/drivers/iio/chemical/pms7003.c
index e9857d93b307..b5cf15a515d2 100644
--- a/drivers/iio/chemical/pms7003.c
+++ b/drivers/iio/chemical/pms7003.c
@@ -211,13 +211,13 @@ static bool pms7003_frame_is_okay(struct pms7003_frame *frame)
 	return checksum == pms7003_calc_checksum(frame);
 }
 
-static int pms7003_receive_buf(struct serdev_device *serdev,
-			       const unsigned char *buf, size_t size)
+static ssize_t pms7003_receive_buf(struct serdev_device *serdev, const u8 *buf,
+				   size_t size)
 {
 	struct iio_dev *indio_dev = serdev_device_get_drvdata(serdev);
 	struct pms7003_state *state = iio_priv(indio_dev);
 	struct pms7003_frame *frame = &state->frame;
-	int num;
+	size_t num;
 
 	if (!frame->expected_length) {
 		u16 magic;
diff --git a/drivers/iio/chemical/scd30_serial.c b/drivers/iio/chemical/scd30_serial.c
index 3c519103d30b..a47654591e55 100644
--- a/drivers/iio/chemical/scd30_serial.c
+++ b/drivers/iio/chemical/scd30_serial.c
@@ -174,13 +174,13 @@ static int scd30_serdev_command(struct scd30_state *state, enum scd30_cmd cmd, u
 	return 0;
 }
 
-static int scd30_serdev_receive_buf(struct serdev_device *serdev,
-				    const unsigned char *buf, size_t size)
+static ssize_t scd30_serdev_receive_buf(struct serdev_device *serdev,
+					const u8 *buf, size_t size)
 {
 	struct iio_dev *indio_dev = serdev_device_get_drvdata(serdev);
 	struct scd30_serdev_priv *priv;
 	struct scd30_state *state;
-	int num;
+	size_t num;
 
 	if (!indio_dev)
 		return 0;
diff --git a/drivers/iio/chemical/sps30_serial.c b/drivers/iio/chemical/sps30_serial.c
index 164f4b3e025c..3afa89f8acc3 100644
--- a/drivers/iio/chemical/sps30_serial.c
+++ b/drivers/iio/chemical/sps30_serial.c
@@ -74,8 +74,8 @@ static int sps30_serial_xfer(struct sps30_state *state, const unsigned char *buf
 }
 
 static const struct {
-	unsigned char byte;
-	unsigned char byte2;
+	u8 byte;
+	u8 byte2;
 } sps30_serial_bytes[] = {
 	{ 0x11, 0x31 },
 	{ 0x13, 0x33 },
@@ -83,7 +83,7 @@ static const struct {
 	{ 0x7d, 0x5d },
 };
 
-static int sps30_serial_put_byte(unsigned char *buf, unsigned char byte)
+static int sps30_serial_put_byte(u8 *buf, u8 byte)
 {
 	int i;
 
@@ -102,7 +102,7 @@ static int sps30_serial_put_byte(unsigned char *buf, unsigned char byte)
 	return 1;
 }
 
-static char sps30_serial_get_byte(bool escaped, unsigned char byte2)
+static u8 sps30_serial_get_byte(bool escaped, u8 byte2)
 {
 	int i;
 
@@ -130,8 +130,8 @@ static unsigned char sps30_serial_calc_chksum(const unsigned char *buf, size_t n
 	return ~chksum;
 }
 
-static int sps30_serial_prep_frame(unsigned char *buf, unsigned char cmd,
-				   const unsigned char *arg, size_t arg_size)
+static int sps30_serial_prep_frame(u8 *buf, u8 cmd, const u8 *arg,
+				   size_t arg_size)
 {
 	unsigned char chksum;
 	int num = 0;
@@ -210,14 +210,14 @@ static int sps30_serial_command(struct sps30_state *state, unsigned char cmd,
 	return rsp_size;
 }
 
-static int sps30_serial_receive_buf(struct serdev_device *serdev,
-				    const unsigned char *buf, size_t size)
+static ssize_t sps30_serial_receive_buf(struct serdev_device *serdev,
+					const u8 *buf, size_t size)
 {
 	struct iio_dev *indio_dev = dev_get_drvdata(&serdev->dev);
 	struct sps30_serial_priv *priv;
 	struct sps30_state *state;
-	unsigned char byte;
 	size_t i;
+	u8 byte;
 
 	if (!indio_dev)
 		return 0;
diff --git a/drivers/iio/imu/bno055/bno055_ser_core.c b/drivers/iio/imu/bno055/bno055_ser_core.c
index 57728a568471..5677bdf4f846 100644
--- a/drivers/iio/imu/bno055/bno055_ser_core.c
+++ b/drivers/iio/imu/bno055/bno055_ser_core.c
@@ -378,12 +378,12 @@ static void bno055_ser_handle_rx(struct bno055_ser_priv *priv, int status)
  * Also, we assume to RX one pkt per time (i.e. the HW doesn't send anything
  * unless we require to AND we don't queue more than one request per time).
  */
-static int bno055_ser_receive_buf(struct serdev_device *serdev,
-				  const unsigned char *buf, size_t size)
+static ssize_t bno055_ser_receive_buf(struct serdev_device *serdev,
+				      const u8 *buf, size_t size)
 {
 	int status;
 	struct bno055_ser_priv *priv = serdev_device_get_drvdata(serdev);
-	int remaining = size;
+	size_t remaining = size;
 
 	if (size == 0)
 		return 0;
diff --git a/drivers/mfd/rave-sp.c b/drivers/mfd/rave-sp.c
index da50eba10014..b1229bb143ee 100644
--- a/drivers/mfd/rave-sp.c
+++ b/drivers/mfd/rave-sp.c
@@ -471,17 +471,17 @@ static void rave_sp_receive_frame(struct rave_sp *sp,
 		rave_sp_receive_reply(sp, data, length);
 }
 
-static int rave_sp_receive_buf(struct serdev_device *serdev,
-			       const unsigned char *buf, size_t size)
+static ssize_t rave_sp_receive_buf(struct serdev_device *serdev,
+				   const u8 *buf, size_t size)
 {
 	struct device *dev = &serdev->dev;
 	struct rave_sp *sp = dev_get_drvdata(dev);
 	struct rave_sp_deframer *deframer = &sp->deframer;
-	const unsigned char *src = buf;
-	const unsigned char *end = buf + size;
+	const u8 *src = buf;
+	const u8 *end = buf + size;
 
 	while (src < end) {
-		const unsigned char byte = *src++;
+		const u8 byte = *src++;
 
 		switch (deframer->state) {
 		case RAVE_SP_EXPECT_SOF:
diff --git a/drivers/net/ethernet/qualcomm/qca_uart.c b/drivers/net/ethernet/qualcomm/qca_uart.c
index 9adec91f35e9..223321897b96 100644
--- a/drivers/net/ethernet/qualcomm/qca_uart.c
+++ b/drivers/net/ethernet/qualcomm/qca_uart.c
@@ -58,9 +58,8 @@ struct qcauart {
 	unsigned char *tx_buffer;
 };
 
-static int
-qca_tty_receive(struct serdev_device *serdev, const unsigned char *data,
-		size_t count)
+static ssize_t
+qca_tty_receive(struct serdev_device *serdev, const u8 *data, size_t count)
 {
 	struct qcauart *qca = serdev_device_get_drvdata(serdev);
 	struct net_device *netdev = qca->net_dev;
diff --git a/drivers/nfc/pn533/uart.c b/drivers/nfc/pn533/uart.c
index a556acdb947b..2eb5978bd79e 100644
--- a/drivers/nfc/pn533/uart.c
+++ b/drivers/nfc/pn533/uart.c
@@ -203,8 +203,8 @@ static int pn532_uart_rx_is_frame(struct sk_buff *skb)
 	return 0;
 }
 
-static int pn532_receive_buf(struct serdev_device *serdev,
-		const unsigned char *data, size_t count)
+static ssize_t pn532_receive_buf(struct serdev_device *serdev,
+				 const u8 *data, size_t count)
 {
 	struct pn532_uart_phy *dev = serdev_device_get_drvdata(serdev);
 	size_t i;
diff --git a/drivers/nfc/s3fwrn5/uart.c b/drivers/nfc/s3fwrn5/uart.c
index 82ea35d748a5..456d3947116c 100644
--- a/drivers/nfc/s3fwrn5/uart.c
+++ b/drivers/nfc/s3fwrn5/uart.c
@@ -51,9 +51,8 @@ static const struct s3fwrn5_phy_ops uart_phy_ops = {
 	.write = s3fwrn82_uart_write,
 };
 
-static int s3fwrn82_uart_read(struct serdev_device *serdev,
-			      const unsigned char *data,
-			      size_t count)
+static ssize_t s3fwrn82_uart_read(struct serdev_device *serdev,
+				  const u8 *data, size_t count)
 {
 	struct s3fwrn82_uart_phy *phy = serdev_device_get_drvdata(serdev);
 	size_t i;
diff --git a/drivers/platform/chrome/cros_ec_uart.c b/drivers/platform/chrome/cros_ec_uart.c
index 788246559bbb..68d80559fddc 100644
--- a/drivers/platform/chrome/cros_ec_uart.c
+++ b/drivers/platform/chrome/cros_ec_uart.c
@@ -81,9 +81,8 @@ struct cros_ec_uart {
 	struct response_info response;
 };
 
-static int cros_ec_uart_rx_bytes(struct serdev_device *serdev,
-				 const u8 *data,
-				 size_t count)
+static ssize_t cros_ec_uart_rx_bytes(struct serdev_device *serdev,
+				     const u8 *data, size_t count)
 {
 	struct ec_host_response *host_response;
 	struct cros_ec_device *ec_dev = serdev_device_get_drvdata(serdev);
diff --git a/drivers/platform/surface/aggregator/controller.h b/drivers/platform/surface/aggregator/controller.h
index f0d987abc51e..f1638c2081e8 100644
--- a/drivers/platform/surface/aggregator/controller.h
+++ b/drivers/platform/surface/aggregator/controller.h
@@ -238,8 +238,8 @@ struct ssam_controller {
  * layer of the controller has been shut down, %-ESHUTDOWN.
  */
 static inline
-int ssam_controller_receive_buf(struct ssam_controller *ctrl,
-				const unsigned char *buf, size_t n)
+ssize_t ssam_controller_receive_buf(struct ssam_controller *ctrl, const u8 *buf,
+				    size_t n)
 {
 	return ssh_ptl_rx_rcvbuf(&ctrl->rtl.ptl, buf, n);
 }
diff --git a/drivers/platform/surface/aggregator/core.c b/drivers/platform/surface/aggregator/core.c
index 1a6373dea109..72d7314a4efd 100644
--- a/drivers/platform/surface/aggregator/core.c
+++ b/drivers/platform/surface/aggregator/core.c
@@ -227,8 +227,8 @@ EXPORT_SYMBOL_GPL(ssam_client_bind);
 
 /* -- Glue layer (serdev_device -> ssam_controller). ------------------------ */
 
-static int ssam_receive_buf(struct serdev_device *dev, const unsigned char *buf,
-			    size_t n)
+static ssize_t ssam_receive_buf(struct serdev_device *dev, const u8 *buf,
+				size_t n)
 {
 	struct ssam_controller *ctrl;
 
diff --git a/drivers/platform/surface/aggregator/ssh_packet_layer.c b/drivers/platform/surface/aggregator/ssh_packet_layer.c
index def8d7ac541f..d726b1a86319 100644
--- a/drivers/platform/surface/aggregator/ssh_packet_layer.c
+++ b/drivers/platform/surface/aggregator/ssh_packet_layer.c
@@ -1887,9 +1887,9 @@ int ssh_ptl_rx_stop(struct ssh_ptl *ptl)
  * Return: Returns the number of bytes transferred (positive or zero) on
  * success. Returns %-ESHUTDOWN if the packet layer has been shut down.
  */
-int ssh_ptl_rx_rcvbuf(struct ssh_ptl *ptl, const u8 *buf, size_t n)
+ssize_t ssh_ptl_rx_rcvbuf(struct ssh_ptl *ptl, const u8 *buf, size_t n)
 {
-	int used;
+	size_t used;
 
 	if (test_bit(SSH_PTL_SF_SHUTDOWN_BIT, &ptl->state))
 		return -ESHUTDOWN;
diff --git a/drivers/platform/surface/aggregator/ssh_packet_layer.h b/drivers/platform/surface/aggregator/ssh_packet_layer.h
index 64633522f971..c80e822070df 100644
--- a/drivers/platform/surface/aggregator/ssh_packet_layer.h
+++ b/drivers/platform/surface/aggregator/ssh_packet_layer.h
@@ -162,7 +162,7 @@ void ssh_ptl_shutdown(struct ssh_ptl *ptl);
 int ssh_ptl_submit(struct ssh_ptl *ptl, struct ssh_packet *p);
 void ssh_ptl_cancel(struct ssh_packet *p);
 
-int ssh_ptl_rx_rcvbuf(struct ssh_ptl *ptl, const u8 *buf, size_t n);
+ssize_t ssh_ptl_rx_rcvbuf(struct ssh_ptl *ptl, const u8 *buf, size_t n);
 
 /**
  * ssh_ptl_tx_wakeup_transfer() - Wake up packet transmitter thread for
diff --git a/drivers/tty/serdev/core.c b/drivers/tty/serdev/core.c
index 3090e3454c44..de8d87d4858d 100644
--- a/drivers/tty/serdev/core.c
+++ b/drivers/tty/serdev/core.c
@@ -225,8 +225,7 @@ EXPORT_SYMBOL_GPL(serdev_device_write_wakeup);
  * Return: The number of bytes written (less than count if not enough room in
  * the write buffer), or a negative errno on errors.
  */
-int serdev_device_write_buf(struct serdev_device *serdev,
-			    const unsigned char *buf, size_t count)
+int serdev_device_write_buf(struct serdev_device *serdev, const u8 *buf, size_t count)
 {
 	struct serdev_controller *ctrl = serdev->ctrl;
 
@@ -259,13 +258,12 @@ EXPORT_SYMBOL_GPL(serdev_device_write_buf);
  * -ETIMEDOUT or -ERESTARTSYS if interrupted before any bytes were written, or
  * a negative errno on errors.
  */
-int serdev_device_write(struct serdev_device *serdev,
-			const unsigned char *buf, size_t count,
-			long timeout)
+ssize_t serdev_device_write(struct serdev_device *serdev, const u8 *buf,
+			    size_t count, long timeout)
 {
 	struct serdev_controller *ctrl = serdev->ctrl;
-	int written = 0;
-	int ret;
+	size_t written = 0;
+	ssize_t ret;
 
 	if (!ctrl || !ctrl->ops->write_buf || !serdev->ops->write_wakeup)
 		return -EINVAL;
diff --git a/include/linux/serdev.h b/include/linux/serdev.h
index 8cdab2c3b6d5..3fab88ba265e 100644
--- a/include/linux/serdev.h
+++ b/include/linux/serdev.h
@@ -27,7 +27,7 @@ struct serdev_device;
  *			not sleep.
  */
 struct serdev_device_ops {
-	int (*receive_buf)(struct serdev_device *, const unsigned char *, size_t);
+	ssize_t (*receive_buf)(struct serdev_device *, const u8 *, size_t);
 	void (*write_wakeup)(struct serdev_device *);
 };
 
@@ -204,13 +204,13 @@ void serdev_device_close(struct serdev_device *);
 int devm_serdev_device_open(struct device *, struct serdev_device *);
 unsigned int serdev_device_set_baudrate(struct serdev_device *, unsigned int);
 void serdev_device_set_flow_control(struct serdev_device *, bool);
-int serdev_device_write_buf(struct serdev_device *, const unsigned char *, size_t);
+int serdev_device_write_buf(struct serdev_device *, const u8 *, size_t);
 void serdev_device_wait_until_sent(struct serdev_device *, long);
 int serdev_device_get_tiocm(struct serdev_device *);
 int serdev_device_set_tiocm(struct serdev_device *, int, int);
 int serdev_device_break_ctl(struct serdev_device *serdev, int break_state);
 void serdev_device_write_wakeup(struct serdev_device *);
-int serdev_device_write(struct serdev_device *, const unsigned char *, size_t, long);
+ssize_t serdev_device_write(struct serdev_device *, const u8 *, size_t, long);
 void serdev_device_write_flush(struct serdev_device *);
 int serdev_device_write_room(struct serdev_device *);
 
@@ -248,7 +248,7 @@ static inline unsigned int serdev_device_set_baudrate(struct serdev_device *sdev
 }
 static inline void serdev_device_set_flow_control(struct serdev_device *sdev, bool enable) {}
 static inline int serdev_device_write_buf(struct serdev_device *serdev,
-					  const unsigned char *buf,
+					  const u8 *buf,
 					  size_t count)
 {
 	return -ENODEV;
@@ -266,8 +266,9 @@ static inline int serdev_device_break_ctl(struct serdev_device *serdev, int brea
 {
 	return -EOPNOTSUPP;
 }
-static inline int serdev_device_write(struct serdev_device *sdev, const unsigned char *buf,
-				      size_t count, unsigned long timeout)
+static inline ssize_t serdev_device_write(struct serdev_device *sdev,
+					  const u8 *buf, size_t count,
+					  unsigned long timeout)
 {
 	return -ENODEV;
 }
diff --git a/sound/drivers/serial-generic.c b/sound/drivers/serial-generic.c
index c8db6c75d133..d6e5aafd697c 100644
--- a/sound/drivers/serial-generic.c
+++ b/sound/drivers/serial-generic.c
@@ -100,8 +100,8 @@ static void snd_serial_generic_write_wakeup(struct serdev_device *serdev)
 	snd_serial_generic_tx_wakeup(drvdata);
 }
 
-static int snd_serial_generic_receive_buf(struct serdev_device *serdev,
-				const unsigned char *buf, size_t count)
+static ssize_t snd_serial_generic_receive_buf(struct serdev_device *serdev,
+					      const u8 *buf, size_t count)
 {
 	int ret;
 	struct snd_serial_generic *drvdata = serdev_device_get_drvdata(serdev);
-- 
cgit v1.2.3


From b53d47775651aa51bb98cdeb968dedb45699d9a1 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Fri, 8 Dec 2023 11:09:25 +0100
Subject: ASoC: wm0010: Convert to GPIO descriptors

This converts the WM0010 codec to use GPIO descriptors.
It's a pretty straight-forward conversion also switching over
the single in-tree user in the S3C Cragganmore module
for S3C 6410.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://lore.kernel.org/r/20231208-descriptors-sound-wlf-v1-1-c4dab6f521ec@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 arch/arm/mach-s3c/mach-crag6410-module.c | 16 +++++++++---
 include/sound/wm0010.h                   |  6 -----
 sound/soc/codecs/wm0010.c                | 44 ++++++++------------------------
 3 files changed, 23 insertions(+), 43 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-s3c/mach-crag6410-module.c b/arch/arm/mach-s3c/mach-crag6410-module.c
index 8fce1e815ee8..a9a713641047 100644
--- a/arch/arm/mach-s3c/mach-crag6410-module.c
+++ b/arch/arm/mach-s3c/mach-crag6410-module.c
@@ -32,9 +32,18 @@
 
 #include "crag6410.h"
 
+static struct gpiod_lookup_table wm0010_gpiod_table = {
+	.dev_id = "spi0.0", /* SPI device name */
+	.table = {
+		/* Active high for Glenfarclas Rev 2 */
+		GPIO_LOOKUP("GPION", 6,
+			    "reset", GPIO_ACTIVE_HIGH),
+		{ },
+	},
+};
+
 static struct wm0010_pdata wm0010_pdata = {
-	.gpio_reset = S3C64XX_GPN(6),
-	.reset_active_high = 1, /* Active high for Glenfarclas Rev 2 */
+	/* Intentionally left blank */
 };
 
 static struct spi_board_info wm1253_devs[] = {
@@ -337,7 +346,8 @@ static const struct {
 	{ .id = 0x21, .rev = 0xff, .name = "1275-EV1 Mortlach" },
 	{ .id = 0x25, .rev = 0xff, .name = "1274-EV1 Glencadam" },
 	{ .id = 0x31, .rev = 0xff, .name = "1253-EV1 Tomatin",
-	  .spi_devs = wm1253_devs, .num_spi_devs = ARRAY_SIZE(wm1253_devs) },
+	  .spi_devs = wm1253_devs, .num_spi_devs = ARRAY_SIZE(wm1253_devs),
+	  .gpiod_table = &wm0010_gpiod_table },
 	{ .id = 0x32, .rev = 0xff, .name = "XXXX-EV1 Caol Illa" },
 	{ .id = 0x33, .rev = 0xff, .name = "XXXX-EV1 Oban" },
 	{ .id = 0x34, .rev = 0xff, .name = "WM0010-6320-CS42 Balblair",
diff --git a/include/sound/wm0010.h b/include/sound/wm0010.h
index 13b473935ca1..14ff9056c5d0 100644
--- a/include/sound/wm0010.h
+++ b/include/sound/wm0010.h
@@ -11,12 +11,6 @@
 #define WM0010_PDATA_H
 
 struct wm0010_pdata {
-	int gpio_reset;
-
-	/* Set if there is an inverter between the GPIO controlling
-	 * the reset signal and the device.
-	 */
-	int reset_active_high;
 	int irq_flags;
 };
 
diff --git a/sound/soc/codecs/wm0010.c b/sound/soc/codecs/wm0010.c
index 1d4259433f47..8f862729a2ca 100644
--- a/sound/soc/codecs/wm0010.c
+++ b/sound/soc/codecs/wm0010.c
@@ -18,7 +18,7 @@
 #include <linux/firmware.h>
 #include <linux/delay.h>
 #include <linux/fs.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/regulator/consumer.h>
 #include <linux/mutex.h>
 #include <linux/workqueue.h>
@@ -94,8 +94,7 @@ struct wm0010_priv {
 
 	struct wm0010_pdata pdata;
 
-	int gpio_reset;
-	int gpio_reset_value;
+	struct gpio_desc *reset;
 
 	struct regulator_bulk_data core_supplies[2];
 	struct regulator *dbvdd;
@@ -174,8 +173,7 @@ static void wm0010_halt(struct snd_soc_component *component)
 	case WM0010_STAGE2:
 	case WM0010_FIRMWARE:
 		/* Remember to put chip back into reset */
-		gpio_set_value_cansleep(wm0010->gpio_reset,
-					wm0010->gpio_reset_value);
+		gpiod_set_value_cansleep(wm0010->reset, 1);
 		/* Disable the regulators */
 		regulator_disable(wm0010->dbvdd);
 		regulator_bulk_disable(ARRAY_SIZE(wm0010->core_supplies),
@@ -610,7 +608,7 @@ static int wm0010_boot(struct snd_soc_component *component)
 	}
 
 	/* Release reset */
-	gpio_set_value_cansleep(wm0010->gpio_reset, !wm0010->gpio_reset_value);
+	gpiod_set_value_cansleep(wm0010->reset, 0);
 	spin_lock_irqsave(&wm0010->irq_lock, flags);
 	wm0010->state = WM0010_OUT_OF_RESET;
 	spin_unlock_irqrestore(&wm0010->irq_lock, flags);
@@ -863,7 +861,6 @@ static int wm0010_probe(struct snd_soc_component *component)
 
 static int wm0010_spi_probe(struct spi_device *spi)
 {
-	unsigned long gpio_flags;
 	int ret;
 	int trigger;
 	int irq;
@@ -903,31 +900,11 @@ static int wm0010_spi_probe(struct spi_device *spi)
 		return ret;
 	}
 
-	if (wm0010->pdata.gpio_reset) {
-		wm0010->gpio_reset = wm0010->pdata.gpio_reset;
-
-		if (wm0010->pdata.reset_active_high)
-			wm0010->gpio_reset_value = 1;
-		else
-			wm0010->gpio_reset_value = 0;
-
-		if (wm0010->gpio_reset_value)
-			gpio_flags = GPIOF_OUT_INIT_HIGH;
-		else
-			gpio_flags = GPIOF_OUT_INIT_LOW;
-
-		ret = devm_gpio_request_one(wm0010->dev, wm0010->gpio_reset,
-					    gpio_flags, "wm0010 reset");
-		if (ret < 0) {
-			dev_err(wm0010->dev,
-				"Failed to request GPIO for DSP reset: %d\n",
-				ret);
-			return ret;
-		}
-	} else {
-		dev_err(wm0010->dev, "No reset GPIO configured\n");
-		return -EINVAL;
-	}
+	wm0010->reset = devm_gpiod_get(wm0010->dev, "reset", GPIOD_OUT_HIGH);
+	if (IS_ERR(wm0010->reset))
+		return dev_err_probe(wm0010->dev, PTR_ERR(wm0010->reset),
+				     "could not get RESET GPIO\n");
+	gpiod_set_consumer_name(wm0010->reset, "wm0010 reset");
 
 	wm0010->state = WM0010_POWER_OFF;
 
@@ -972,8 +949,7 @@ static void wm0010_spi_remove(struct spi_device *spi)
 {
 	struct wm0010_priv *wm0010 = spi_get_drvdata(spi);
 
-	gpio_set_value_cansleep(wm0010->gpio_reset,
-				wm0010->gpio_reset_value);
+	gpiod_set_value_cansleep(wm0010->reset, 1);
 
 	irq_set_irq_wake(wm0010->irq, 0);
 
-- 
cgit v1.2.3


From 10a366f36e2a2e240d9db6da90e501fa16655282 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Fri, 8 Dec 2023 11:09:26 +0100
Subject: ASoC: wm1250-ev1: Convert to GPIO descriptors

This converts the WM1250-EV1 codec to use GPIO descriptors.
It turns out that the platform data was only used to pass some
global GPIO numbers from a board file, so we get rid of this
and also switch over the single in-tree user in the S3C
Cragganmore module for S3C 6410.

The driver obtains two GPIO lines named OSR and master and just
pull them low, we leave this behaviour as it was.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://lore.kernel.org/r/20231208-descriptors-sound-wlf-v1-2-c4dab6f521ec@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 arch/arm/mach-s3c/mach-crag6410.c |  24 ++++----
 include/sound/wm1250-ev1.h        |  24 --------
 sound/soc/codecs/wm1250-ev1.c     | 118 ++++++++++++++------------------------
 3 files changed, 56 insertions(+), 110 deletions(-)
 delete mode 100644 include/sound/wm1250-ev1.h

(limited to 'include')

diff --git a/arch/arm/mach-s3c/mach-crag6410.c b/arch/arm/mach-s3c/mach-crag6410.c
index 7c4bed4370a1..e5df2cb51ab2 100644
--- a/arch/arm/mach-s3c/mach-crag6410.c
+++ b/arch/arm/mach-s3c/mach-crag6410.c
@@ -39,8 +39,6 @@
 #include <linux/mfd/wm831x/irq.h>
 #include <linux/mfd/wm831x/gpio.h>
 
-#include <sound/wm1250-ev1.h>
-
 #include <asm/mach/arch.h>
 #include <asm/mach-types.h>
 
@@ -713,13 +711,16 @@ static struct wm831x_pdata glenfarclas_pmic_pdata = {
 	.disable_touch = true,
 };
 
-static struct wm1250_ev1_pdata wm1250_ev1_pdata = {
-	.gpios = {
-		[WM1250_EV1_GPIO_CLK_ENA] = S3C64XX_GPN(12),
-		[WM1250_EV1_GPIO_CLK_SEL0] = S3C64XX_GPL(12),
-		[WM1250_EV1_GPIO_CLK_SEL1] = S3C64XX_GPL(13),
-		[WM1250_EV1_GPIO_OSR] = S3C64XX_GPL(14),
-		[WM1250_EV1_GPIO_MASTER] = S3C64XX_GPL(8),
+static struct gpiod_lookup_table crag_wm1250_ev1_gpiod_table = {
+	/* The WM1250-EV1 is device 0027 on I2C bus 1 */
+	.dev_id = "1-0027",
+	.table = {
+		GPIO_LOOKUP("GPION", 12, "clk-ena", GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP("GPIOL", 12, "clk-sel0", GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP("GPIOL", 13, "clk-sel1", GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP("GPIOL", 14, "osr", GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP("GPIOL", 8, "master", GPIO_ACTIVE_HIGH),
+		{ },
 	},
 };
 
@@ -733,9 +734,7 @@ static struct i2c_board_info i2c_devs1[] = {
 	{ I2C_BOARD_INFO("wlf-gf-module", 0x24) },
 	{ I2C_BOARD_INFO("wlf-gf-module", 0x25) },
 	{ I2C_BOARD_INFO("wlf-gf-module", 0x26) },
-
-	{ I2C_BOARD_INFO("wm1250-ev1", 0x27),
-	  .platform_data = &wm1250_ev1_pdata },
+	{ I2C_BOARD_INFO("wm1250-ev1", 0x27), },
 };
 
 static struct s3c2410_platform_i2c i2c1_pdata = {
@@ -862,6 +861,7 @@ static void __init crag6410_machine_init(void)
 
 	gpiod_add_lookup_table(&crag_pmic_gpiod_table);
 	i2c_register_board_info(0, i2c_devs0, ARRAY_SIZE(i2c_devs0));
+	gpiod_add_lookup_table(&crag_wm1250_ev1_gpiod_table);
 	i2c_register_board_info(1, i2c_devs1, ARRAY_SIZE(i2c_devs1));
 
 	samsung_keypad_set_platdata(&crag6410_keypad_data);
diff --git a/include/sound/wm1250-ev1.h b/include/sound/wm1250-ev1.h
deleted file mode 100644
index d16614ebecb4..000000000000
--- a/include/sound/wm1250-ev1.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/sound/wm1250-ev1.h - Platform data for WM1250-EV1
- *
- * Copyright 2011 Wolfson Microelectronics. PLC.
- */
-
-#ifndef __LINUX_SND_WM1250_EV1_H
-#define __LINUX_SND_WM1250_EV1_H
-
-#define WM1250_EV1_NUM_GPIOS 5
-
-#define WM1250_EV1_GPIO_CLK_ENA  0
-#define WM1250_EV1_GPIO_CLK_SEL0 1
-#define WM1250_EV1_GPIO_CLK_SEL1 2
-#define WM1250_EV1_GPIO_OSR      3
-#define WM1250_EV1_GPIO_MASTER   4
-
-
-struct wm1250_ev1_pdata {
-	int gpios[WM1250_EV1_NUM_GPIOS];
-};
-
-#endif
diff --git a/sound/soc/codecs/wm1250-ev1.c b/sound/soc/codecs/wm1250-ev1.c
index d7eeb41ba60f..a2a8b2a4b19b 100644
--- a/sound/soc/codecs/wm1250-ev1.c
+++ b/sound/soc/codecs/wm1250-ev1.c
@@ -9,34 +9,23 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/i2c.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 
 #include <sound/soc.h>
 #include <sound/soc-dapm.h>
-#include <sound/wm1250-ev1.h>
-
-static const char *wm1250_gpio_names[WM1250_EV1_NUM_GPIOS] = {
-	"WM1250 CLK_ENA",
-	"WM1250 CLK_SEL0",
-	"WM1250 CLK_SEL1",
-	"WM1250 OSR",
-	"WM1250 MASTER",
-};
 
 struct wm1250_priv {
-	struct gpio gpios[WM1250_EV1_NUM_GPIOS];
+	struct gpio_desc *clk_ena;
+	struct gpio_desc *clk_sel0;
+	struct gpio_desc *clk_sel1;
+	struct gpio_desc *osr;
+	struct gpio_desc *master;
 };
 
 static int wm1250_ev1_set_bias_level(struct snd_soc_component *component,
 				     enum snd_soc_bias_level level)
 {
 	struct wm1250_priv *wm1250 = dev_get_drvdata(component->dev);
-	int ena;
-
-	if (wm1250)
-		ena = wm1250->gpios[WM1250_EV1_GPIO_CLK_ENA].gpio;
-	else
-		ena = -1;
 
 	switch (level) {
 	case SND_SOC_BIAS_ON:
@@ -46,13 +35,11 @@ static int wm1250_ev1_set_bias_level(struct snd_soc_component *component,
 		break;
 
 	case SND_SOC_BIAS_STANDBY:
-		if (ena >= 0)
-			gpio_set_value_cansleep(ena, 1);
+		gpiod_set_value_cansleep(wm1250->clk_ena, 1);
 		break;
 
 	case SND_SOC_BIAS_OFF:
-		if (ena >= 0)
-			gpio_set_value_cansleep(ena, 0);
+		gpiod_set_value_cansleep(wm1250->clk_ena, 0);
 		break;
 	}
 
@@ -80,28 +67,20 @@ static int wm1250_ev1_hw_params(struct snd_pcm_substream *substream,
 
 	switch (params_rate(params)) {
 	case 8000:
-		gpio_set_value(wm1250->gpios[WM1250_EV1_GPIO_CLK_SEL0].gpio,
-			       1);
-		gpio_set_value(wm1250->gpios[WM1250_EV1_GPIO_CLK_SEL1].gpio,
-			       1);
+		gpiod_set_value(wm1250->clk_sel0, 1);
+		gpiod_set_value(wm1250->clk_sel1, 1);
 		break;
 	case 16000:
-		gpio_set_value(wm1250->gpios[WM1250_EV1_GPIO_CLK_SEL0].gpio,
-			       0);
-		gpio_set_value(wm1250->gpios[WM1250_EV1_GPIO_CLK_SEL1].gpio,
-			       1);
+		gpiod_set_value(wm1250->clk_sel0, 0);
+		gpiod_set_value(wm1250->clk_sel1, 1);
 		break;
 	case 32000:
-		gpio_set_value(wm1250->gpios[WM1250_EV1_GPIO_CLK_SEL0].gpio,
-			       1);
-		gpio_set_value(wm1250->gpios[WM1250_EV1_GPIO_CLK_SEL1].gpio,
-			       0);
+		gpiod_set_value(wm1250->clk_sel0, 1);
+		gpiod_set_value(wm1250->clk_sel1, 0);
 		break;
 	case 64000:
-		gpio_set_value(wm1250->gpios[WM1250_EV1_GPIO_CLK_SEL0].gpio,
-			       0);
-		gpio_set_value(wm1250->gpios[WM1250_EV1_GPIO_CLK_SEL1].gpio,
-			       0);
+		gpiod_set_value(wm1250->clk_sel0, 0);
+		gpiod_set_value(wm1250->clk_sel1, 0);
 		break;
 	default:
 		return -EINVAL;
@@ -150,45 +129,43 @@ static int wm1250_ev1_pdata(struct i2c_client *i2c)
 {
 	struct wm1250_ev1_pdata *pdata = dev_get_platdata(&i2c->dev);
 	struct wm1250_priv *wm1250;
-	int i, ret;
+	int ret;
 
 	if (!pdata)
 		return 0;
 
 	wm1250 = devm_kzalloc(&i2c->dev, sizeof(*wm1250), GFP_KERNEL);
-	if (!wm1250) {
-		ret = -ENOMEM;
-		goto err;
-	}
-
-	for (i = 0; i < ARRAY_SIZE(wm1250->gpios); i++) {
-		wm1250->gpios[i].gpio = pdata->gpios[i];
-		wm1250->gpios[i].label = wm1250_gpio_names[i];
-		wm1250->gpios[i].flags = GPIOF_OUT_INIT_LOW;
-	}
-	wm1250->gpios[WM1250_EV1_GPIO_CLK_SEL0].flags = GPIOF_OUT_INIT_HIGH;
-	wm1250->gpios[WM1250_EV1_GPIO_CLK_SEL1].flags = GPIOF_OUT_INIT_HIGH;
-
-	ret = gpio_request_array(wm1250->gpios, ARRAY_SIZE(wm1250->gpios));
-	if (ret != 0) {
-		dev_err(&i2c->dev, "Failed to get GPIOs: %d\n", ret);
-		goto err;
-	}
+	if (!wm1250)
+		return -ENOMEM;
+
+	wm1250->clk_ena = devm_gpiod_get(&i2c->dev, "clk-ena", GPIOD_OUT_LOW);
+	if (IS_ERR(wm1250->clk_ena))
+		return dev_err_probe(&i2c->dev, PTR_ERR(wm1250->clk_ena),
+				     "failed to get clock enable GPIO\n");
+
+	wm1250->clk_sel0 = devm_gpiod_get(&i2c->dev, "clk-sel0", GPIOD_OUT_HIGH);
+	if (IS_ERR(wm1250->clk_sel0))
+		return dev_err_probe(&i2c->dev, PTR_ERR(wm1250->clk_sel0),
+				     "failed to get clock sel0 GPIO\n");
+
+	wm1250->clk_sel1 = devm_gpiod_get(&i2c->dev, "clk-sel1", GPIOD_OUT_HIGH);
+	if (IS_ERR(wm1250->clk_sel1))
+		return dev_err_probe(&i2c->dev, PTR_ERR(wm1250->clk_sel1),
+				     "failed to get clock sel1 GPIO\n");
+
+	wm1250->osr = devm_gpiod_get(&i2c->dev, "osr", GPIOD_OUT_LOW);
+	if (IS_ERR(wm1250->osr))
+		return dev_err_probe(&i2c->dev, PTR_ERR(wm1250->osr),
+				     "failed to get OSR GPIO\n");
+
+	wm1250->master = devm_gpiod_get(&i2c->dev, "master", GPIOD_OUT_LOW);
+	if (IS_ERR(wm1250->master))
+		return dev_err_probe(&i2c->dev, PTR_ERR(wm1250->master),
+				     "failed to get MASTER GPIO\n");
 
 	dev_set_drvdata(&i2c->dev, wm1250);
 
 	return ret;
-
-err:
-	return ret;
-}
-
-static void wm1250_ev1_free(struct i2c_client *i2c)
-{
-	struct wm1250_priv *wm1250 = dev_get_drvdata(&i2c->dev);
-
-	if (wm1250)
-		gpio_free_array(wm1250->gpios, ARRAY_SIZE(wm1250->gpios));
 }
 
 static int wm1250_ev1_probe(struct i2c_client *i2c)
@@ -221,18 +198,12 @@ static int wm1250_ev1_probe(struct i2c_client *i2c)
 				     &wm1250_ev1_dai, 1);
 	if (ret != 0) {
 		dev_err(&i2c->dev, "Failed to register CODEC: %d\n", ret);
-		wm1250_ev1_free(i2c);
 		return ret;
 	}
 
 	return 0;
 }
 
-static void wm1250_ev1_remove(struct i2c_client *i2c)
-{
-	wm1250_ev1_free(i2c);
-}
-
 static const struct i2c_device_id wm1250_ev1_i2c_id[] = {
 	{ "wm1250-ev1", 0 },
 	{ }
@@ -244,7 +215,6 @@ static struct i2c_driver wm1250_ev1_i2c_driver = {
 		.name = "wm1250-ev1",
 	},
 	.probe =    wm1250_ev1_probe,
-	.remove =   wm1250_ev1_remove,
 	.id_table = wm1250_ev1_i2c_id,
 };
 
-- 
cgit v1.2.3


From 0119b2a24eb592f967a2849b772887c96617ad80 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Fri, 8 Dec 2023 11:09:27 +0100
Subject: ASoC: wm2200: Convert to GPIO descriptors

This converts the WM2200 codec to use GPIO descriptors.
This is a pretty straight-forward conversion, and it also
switches over the single in-tree user in the S3C
Cragganmore module for S3C 6410.

This coded does not seem to get selected or be selectable
through Kconfig, I had to hack another soundcard Kconfig
entry to select it for compile tests.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://lore.kernel.org/r/20231208-descriptors-sound-wlf-v1-3-c4dab6f521ec@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 arch/arm/mach-s3c/mach-crag6410-module.c | 13 ++++++-
 include/sound/wm2200.h                   |  2 -
 sound/soc/codecs/wm2200.c                | 67 ++++++++++++++++----------------
 3 files changed, 44 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-s3c/mach-crag6410-module.c b/arch/arm/mach-s3c/mach-crag6410-module.c
index a9a713641047..1df6b7e52c9d 100644
--- a/arch/arm/mach-s3c/mach-crag6410-module.c
+++ b/arch/arm/mach-s3c/mach-crag6410-module.c
@@ -305,12 +305,20 @@ static const struct i2c_board_info wm6230_i2c_devs[] = {
 };
 
 static struct wm2200_pdata wm2200_pdata = {
-	.ldo_ena = S3C64XX_GPN(7),
 	.gpio_defaults = {
 		[2] = 0x0005,  /* GPIO3 24.576MHz output clock */
 	},
 };
 
+static struct gpiod_lookup_table wm2200_gpiod_table = {
+	.dev_id = "1-003a", /* Device 003a on I2C bus 1 */
+	.table = {
+		GPIO_LOOKUP("GPION", 7,
+			    "wlf,ldo1ena", GPIO_ACTIVE_HIGH),
+		{ },
+	},
+};
+
 static const struct i2c_board_info wm2200_i2c[] = {
 	{ I2C_BOARD_INFO("wm2200", 0x3a),
 	  .platform_data = &wm2200_pdata, },
@@ -372,7 +380,8 @@ static const struct {
 	  .num_spi_devs = ARRAY_SIZE(wm5102_spi_devs),
 	  .gpiod_table = &wm5102_gpiod_table },
 	{ .id = 0x3f, .rev = -1, .name = "WM2200-6271-CS90-M-REV1",
-	  .i2c_devs = wm2200_i2c, .num_i2c_devs = ARRAY_SIZE(wm2200_i2c) },
+	  .i2c_devs = wm2200_i2c, .num_i2c_devs = ARRAY_SIZE(wm2200_i2c),
+	  .gpiod_table = &wm2200_gpiod_table },
 };
 
 static int wlf_gf_module_probe(struct i2c_client *i2c)
diff --git a/include/sound/wm2200.h b/include/sound/wm2200.h
index 9987e6c09bdc..2e4913ee2505 100644
--- a/include/sound/wm2200.h
+++ b/include/sound/wm2200.h
@@ -42,8 +42,6 @@ struct wm2200_micbias {
 };
 
 struct wm2200_pdata {
-	int reset;      /** GPIO controlling /RESET, if any */
-	int ldo_ena;    /** GPIO controlling LODENA, if any */
 	int irq_flags;
 
 	int gpio_defaults[4];
diff --git a/sound/soc/codecs/wm2200.c b/sound/soc/codecs/wm2200.c
index 9679906c6bd5..69c9c2bd7e7b 100644
--- a/sound/soc/codecs/wm2200.c
+++ b/sound/soc/codecs/wm2200.c
@@ -14,7 +14,7 @@
 #include <linux/pm.h>
 #include <linux/firmware.h>
 #include <linux/gcd.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/i2c.h>
 #include <linux/pm_runtime.h>
 #include <linux/regulator/consumer.h>
@@ -79,6 +79,8 @@ struct wm2200_priv {
 	struct snd_soc_component *component;
 	struct wm2200_pdata pdata;
 	struct regulator_bulk_data core_supplies[WM2200_NUM_CORE_SUPPLIES];
+	struct gpio_desc *ldo_ena;
+	struct gpio_desc *reset;
 
 	struct completion fll_lock;
 	int fll_fout;
@@ -975,9 +977,10 @@ static const struct reg_sequence wm2200_reva_patch[] = {
 
 static int wm2200_reset(struct wm2200_priv *wm2200)
 {
-	if (wm2200->pdata.reset) {
-		gpio_set_value_cansleep(wm2200->pdata.reset, 0);
-		gpio_set_value_cansleep(wm2200->pdata.reset, 1);
+	if (wm2200->reset) {
+		/* Descriptor flagged active low, so this will be inverted */
+		gpiod_set_value_cansleep(wm2200->reset, 1);
+		gpiod_set_value_cansleep(wm2200->reset, 0);
 
 		return 0;
 	} else {
@@ -2246,28 +2249,28 @@ static int wm2200_i2c_probe(struct i2c_client *i2c)
 		return ret;
 	}
 
-	if (wm2200->pdata.ldo_ena) {
-		ret = devm_gpio_request_one(&i2c->dev, wm2200->pdata.ldo_ena,
-					    GPIOF_OUT_INIT_HIGH,
-					    "WM2200 LDOENA");
-		if (ret < 0) {
-			dev_err(&i2c->dev, "Failed to request LDOENA %d: %d\n",
-				wm2200->pdata.ldo_ena, ret);
-			goto err_enable;
-		}
+	wm2200->ldo_ena = devm_gpiod_get_optional(&i2c->dev, "wlf,ldo1ena",
+						  GPIOD_OUT_HIGH);
+	if (IS_ERR(wm2200->ldo_ena)) {
+		ret = PTR_ERR(wm2200->ldo_ena);
+		dev_err(&i2c->dev, "Failed to request LDOENA GPIO %d\n",
+			ret);
+		goto err_enable;
+	}
+	if (wm2200->ldo_ena) {
+		gpiod_set_consumer_name(wm2200->ldo_ena, "WM2200 LDOENA");
 		msleep(2);
 	}
 
-	if (wm2200->pdata.reset) {
-		ret = devm_gpio_request_one(&i2c->dev, wm2200->pdata.reset,
-					    GPIOF_OUT_INIT_HIGH,
-					    "WM2200 /RESET");
-		if (ret < 0) {
-			dev_err(&i2c->dev, "Failed to request /RESET %d: %d\n",
-				wm2200->pdata.reset, ret);
-			goto err_ldo;
-		}
+	wm2200->reset = devm_gpiod_get_optional(&i2c->dev, "reset",
+						GPIOD_OUT_LOW);
+	if (IS_ERR(wm2200->reset)) {
+		ret = PTR_ERR(wm2200->reset);
+		dev_err(&i2c->dev, "Failed to request RESET GPIO %d\n",
+			ret);
+		goto err_ldo;
 	}
+	gpiod_set_consumer_name(wm2200->reset, "WM2200 /RESET");
 
 	ret = regmap_read(wm2200->regmap, WM2200_SOFTWARE_RESET, &reg);
 	if (ret < 0) {
@@ -2403,11 +2406,9 @@ err_pm_runtime:
 	if (i2c->irq)
 		free_irq(i2c->irq, wm2200);
 err_reset:
-	if (wm2200->pdata.reset)
-		gpio_set_value_cansleep(wm2200->pdata.reset, 0);
+	gpiod_set_value_cansleep(wm2200->reset, 1);
 err_ldo:
-	if (wm2200->pdata.ldo_ena)
-		gpio_set_value_cansleep(wm2200->pdata.ldo_ena, 0);
+	gpiod_set_value_cansleep(wm2200->ldo_ena, 0);
 err_enable:
 	regulator_bulk_disable(ARRAY_SIZE(wm2200->core_supplies),
 			       wm2200->core_supplies);
@@ -2421,10 +2422,9 @@ static void wm2200_i2c_remove(struct i2c_client *i2c)
 	pm_runtime_disable(&i2c->dev);
 	if (i2c->irq)
 		free_irq(i2c->irq, wm2200);
-	if (wm2200->pdata.reset)
-		gpio_set_value_cansleep(wm2200->pdata.reset, 0);
-	if (wm2200->pdata.ldo_ena)
-		gpio_set_value_cansleep(wm2200->pdata.ldo_ena, 0);
+	/* Assert RESET, disable LDO */
+	gpiod_set_value_cansleep(wm2200->reset, 1);
+	gpiod_set_value_cansleep(wm2200->ldo_ena, 0);
 	regulator_bulk_disable(ARRAY_SIZE(wm2200->core_supplies),
 			       wm2200->core_supplies);
 }
@@ -2436,8 +2436,7 @@ static int wm2200_runtime_suspend(struct device *dev)
 
 	regcache_cache_only(wm2200->regmap, true);
 	regcache_mark_dirty(wm2200->regmap);
-	if (wm2200->pdata.ldo_ena)
-		gpio_set_value_cansleep(wm2200->pdata.ldo_ena, 0);
+	gpiod_set_value_cansleep(wm2200->ldo_ena, 0);
 	regulator_bulk_disable(ARRAY_SIZE(wm2200->core_supplies),
 			       wm2200->core_supplies);
 
@@ -2457,8 +2456,8 @@ static int wm2200_runtime_resume(struct device *dev)
 		return ret;
 	}
 
-	if (wm2200->pdata.ldo_ena) {
-		gpio_set_value_cansleep(wm2200->pdata.ldo_ena, 1);
+	if (wm2200->ldo_ena) {
+		gpiod_set_value_cansleep(wm2200->ldo_ena, 1);
 		msleep(2);
 	}
 
-- 
cgit v1.2.3


From 8563cfe39ba5d00d974df25e310fb61b5b3687e1 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Fri, 8 Dec 2023 11:09:28 +0100
Subject: ASoC: wm5100: Convert to GPIO descriptors

This converts the WM5100 codec to use GPIO descriptors, a pretty
straight-forward conversion with the following peculiarities:

- The driver is instantiating a GPIO chip named wm5100, and the
  headphone polarity detection GPIO is lifted from there. We add
  this to the GPIO descriptor table as well, and we can then get
  rid of also the base address for the GPIO chip from the
  platform data and just use dynamic numbering.

- Fix up the only in-tree user which is the Cragganmore 6410
  module.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://lore.kernel.org/r/20231208-descriptors-sound-wlf-v1-4-c4dab6f521ec@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 arch/arm/mach-s3c/mach-crag6410-module.c |  17 +++--
 include/sound/wm5100.h                   |   4 --
 sound/soc/codecs/wm5100.c                | 107 +++++++++++--------------------
 3 files changed, 52 insertions(+), 76 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-s3c/mach-crag6410-module.c b/arch/arm/mach-s3c/mach-crag6410-module.c
index 1df6b7e52c9d..59456fbebf1b 100644
--- a/arch/arm/mach-s3c/mach-crag6410-module.c
+++ b/arch/arm/mach-s3c/mach-crag6410-module.c
@@ -70,10 +70,19 @@ static struct spi_board_info balblair_devs[] = {
 	},
 };
 
+static struct gpiod_lookup_table wm5100_gpiod_table = {
+	.dev_id = "1-001a", /* Device 001a on I2C bus 1 */
+	.table = {
+		GPIO_LOOKUP("GPION", 7,
+			    "wlf,ldo1ena", GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP("wm5100", 3,
+			    "hp-pol", GPIO_ACTIVE_HIGH),
+		{ },
+	},
+};
+
 static struct wm5100_pdata wm5100_pdata = {
-	.ldo_ena = S3C64XX_GPN(7),
 	.irq_flags = IRQF_TRIGGER_HIGH,
-	.gpio_base = CODEC_GPIO_BASE,
 
 	.in_mode = {
 		WM5100_IN_DIFF,
@@ -82,7 +91,6 @@ static struct wm5100_pdata wm5100_pdata = {
 		WM5100_IN_SE,
 	},
 
-	.hp_pol = CODEC_GPIO_BASE + 3,
 	.jack_modes = {
 		{ WM5100_MICDET_MICBIAS3, 0, 0 },
 		{ WM5100_MICDET_MICBIAS2, 1, 1 },
@@ -366,7 +374,8 @@ static const struct {
 	{ .id = 0x3a, .rev = 0xff, .name = "1259-EV1 Tobermory",
 	  .i2c_devs = wm1259_devs, .num_i2c_devs = ARRAY_SIZE(wm1259_devs) },
 	{ .id = 0x3b, .rev = 0xff, .name = "1255-EV1 Kilchoman",
-	  .i2c_devs = wm1255_devs, .num_i2c_devs = ARRAY_SIZE(wm1255_devs) },
+	  .i2c_devs = wm1255_devs, .num_i2c_devs = ARRAY_SIZE(wm1255_devs),
+	  .gpiod_table = &wm5100_gpiod_table },
 	{ .id = 0x3c, .rev = 0xff, .name = "1273-EV1 Longmorn" },
 	{ .id = 0x3d, .rev = 0xff, .name = "1277-EV1 Littlemill",
 	  .i2c_devs = wm1277_devs, .num_i2c_devs = ARRAY_SIZE(wm1277_devs),
diff --git a/include/sound/wm5100.h b/include/sound/wm5100.h
index b94badf72947..1c48090fdb2c 100644
--- a/include/sound/wm5100.h
+++ b/include/sound/wm5100.h
@@ -36,11 +36,7 @@ struct wm5100_jack_mode {
 #define WM5100_GPIO_SET 0x10000
 
 struct wm5100_pdata {
-	int reset;      /** GPIO controlling /RESET, if any */
-	int ldo_ena;    /** GPIO controlling LODENA, if any */
-	int hp_pol;     /** GPIO controlling headset polarity, if any */
 	int irq_flags;
-	int gpio_base;
 
 	struct wm5100_jack_mode jack_modes[2];
 
diff --git a/sound/soc/codecs/wm5100.c b/sound/soc/codecs/wm5100.c
index ff63723928a1..7ee4b45c0834 100644
--- a/sound/soc/codecs/wm5100.c
+++ b/sound/soc/codecs/wm5100.c
@@ -15,7 +15,7 @@
 #include <linux/pm.h>
 #include <linux/gcd.h>
 #include <linux/gpio/driver.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/i2c.h>
 #include <linux/pm_runtime.h>
 #include <linux/regulator/consumer.h>
@@ -55,6 +55,9 @@ struct wm5100_priv {
 	struct snd_soc_component *component;
 
 	struct regulator_bulk_data core_supplies[WM5100_NUM_CORE_SUPPLIES];
+	struct gpio_desc *reset;
+	struct gpio_desc *ldo_ena;
+	struct gpio_desc *hp_pol;
 
 	int rev;
 
@@ -205,9 +208,9 @@ static void wm5100_free_sr(struct snd_soc_component *component, int rate)
 
 static int wm5100_reset(struct wm5100_priv *wm5100)
 {
-	if (wm5100->pdata.reset) {
-		gpio_set_value_cansleep(wm5100->pdata.reset, 0);
-		gpio_set_value_cansleep(wm5100->pdata.reset, 1);
+	if (wm5100->reset) {
+		gpiod_set_value_cansleep(wm5100->reset, 1);
+		gpiod_set_value_cansleep(wm5100->reset, 0);
 
 		return 0;
 	} else {
@@ -1974,7 +1977,7 @@ static void wm5100_set_detect_mode(struct wm5100_priv *wm5100, int the_mode)
 	if (WARN_ON(the_mode >= ARRAY_SIZE(wm5100->pdata.jack_modes)))
 		return;
 
-	gpio_set_value_cansleep(wm5100->pdata.hp_pol, mode->hp_pol);
+	gpiod_set_value_cansleep(wm5100->hp_pol, mode->hp_pol);
 	regmap_update_bits(wm5100->regmap, WM5100_ACCESSORY_DETECT_MODE_1,
 			   WM5100_ACCDET_BIAS_SRC_MASK |
 			   WM5100_ACCDET_SRC,
@@ -2299,11 +2302,7 @@ static void wm5100_init_gpio(struct i2c_client *i2c)
 	wm5100->gpio_chip = wm5100_template_chip;
 	wm5100->gpio_chip.ngpio = 6;
 	wm5100->gpio_chip.parent = &i2c->dev;
-
-	if (wm5100->pdata.gpio_base)
-		wm5100->gpio_chip.base = wm5100->pdata.gpio_base;
-	else
-		wm5100->gpio_chip.base = -1;
+	wm5100->gpio_chip.base = -1;
 
 	ret = gpiochip_add_data(&wm5100->gpio_chip, wm5100);
 	if (ret != 0)
@@ -2349,35 +2348,20 @@ static int wm5100_probe(struct snd_soc_component *component)
 		snd_soc_dapm_new_controls(dapm, wm5100_dapm_widgets_noirq,
 					  ARRAY_SIZE(wm5100_dapm_widgets_noirq));
 
-	if (wm5100->pdata.hp_pol) {
-		ret = gpio_request_one(wm5100->pdata.hp_pol,
-				       GPIOF_OUT_INIT_HIGH, "WM5100 HP_POL");
-		if (ret < 0) {
-			dev_err(&i2c->dev, "Failed to request HP_POL %d: %d\n",
-				wm5100->pdata.hp_pol, ret);
-			goto err_gpio;
-		}
+	wm5100->hp_pol = devm_gpiod_get_optional(&i2c->dev, "hp-pol",
+						 GPIOD_OUT_HIGH);
+	if (IS_ERR(wm5100->hp_pol)) {
+		ret = PTR_ERR(wm5100->hp_pol);
+		dev_err(&i2c->dev, "Failed to request HP_POL GPIO: %d\n",
+			ret);
+		return ret;
 	}
 
 	return 0;
-
-err_gpio:
-
-	return ret;
-}
-
-static void wm5100_remove(struct snd_soc_component *component)
-{
-	struct wm5100_priv *wm5100 = snd_soc_component_get_drvdata(component);
-
-	if (wm5100->pdata.hp_pol) {
-		gpio_free(wm5100->pdata.hp_pol);
-	}
 }
 
 static const struct snd_soc_component_driver soc_component_dev_wm5100 = {
 	.probe			= wm5100_probe,
-	.remove			= wm5100_remove,
 	.set_sysclk		= wm5100_set_sysclk,
 	.set_pll		= wm5100_set_fll,
 	.seq_notifier		= wm5100_seq_notifier,
@@ -2460,26 +2444,26 @@ static int wm5100_i2c_probe(struct i2c_client *i2c)
 		goto err;
 	}
 
-	if (wm5100->pdata.ldo_ena) {
-		ret = gpio_request_one(wm5100->pdata.ldo_ena,
-				       GPIOF_OUT_INIT_HIGH, "WM5100 LDOENA");
-		if (ret < 0) {
-			dev_err(&i2c->dev, "Failed to request LDOENA %d: %d\n",
-				wm5100->pdata.ldo_ena, ret);
-			goto err_enable;
-		}
+	wm5100->ldo_ena = devm_gpiod_get_optional(&i2c->dev, "wlf,ldo1ena",
+						  GPIOD_OUT_HIGH);
+	if (IS_ERR(wm5100->ldo_ena)) {
+		ret = PTR_ERR(wm5100->ldo_ena);
+		dev_err(&i2c->dev, "Failed to request LDOENA GPIO: %d\n", ret);
+		goto err_enable;
+	}
+	if (wm5100->ldo_ena) {
+		gpiod_set_consumer_name(wm5100->ldo_ena, "WM5100 LDOENA");
 		msleep(2);
 	}
 
-	if (wm5100->pdata.reset) {
-		ret = gpio_request_one(wm5100->pdata.reset,
-				       GPIOF_OUT_INIT_HIGH, "WM5100 /RESET");
-		if (ret < 0) {
-			dev_err(&i2c->dev, "Failed to request /RESET %d: %d\n",
-				wm5100->pdata.reset, ret);
-			goto err_ldo;
-		}
+	wm5100->reset = devm_gpiod_get_optional(&i2c->dev, "reset",
+						GPIOD_OUT_LOW);
+	if (IS_ERR(wm5100->reset)) {
+		ret = PTR_ERR(wm5100->reset);
+		dev_err(&i2c->dev, "Failed to request /RESET GPIO: %d\n", ret);
+		goto err_ldo;
 	}
+	gpiod_set_consumer_name(wm5100->reset, "WM5100 /RESET");
 
 	ret = regmap_read(wm5100->regmap, WM5100_SOFTWARE_RESET, &reg);
 	if (ret < 0) {
@@ -2619,15 +2603,9 @@ err_reset:
 	if (i2c->irq)
 		free_irq(i2c->irq, wm5100);
 	wm5100_free_gpio(i2c);
-	if (wm5100->pdata.reset) {
-		gpio_set_value_cansleep(wm5100->pdata.reset, 0);
-		gpio_free(wm5100->pdata.reset);
-	}
+	gpiod_set_value_cansleep(wm5100->reset, 1);
 err_ldo:
-	if (wm5100->pdata.ldo_ena) {
-		gpio_set_value_cansleep(wm5100->pdata.ldo_ena, 0);
-		gpio_free(wm5100->pdata.ldo_ena);
-	}
+	gpiod_set_value_cansleep(wm5100->ldo_ena, 0);
 err_enable:
 	regulator_bulk_disable(ARRAY_SIZE(wm5100->core_supplies),
 			       wm5100->core_supplies);
@@ -2643,14 +2621,8 @@ static void wm5100_i2c_remove(struct i2c_client *i2c)
 	if (i2c->irq)
 		free_irq(i2c->irq, wm5100);
 	wm5100_free_gpio(i2c);
-	if (wm5100->pdata.reset) {
-		gpio_set_value_cansleep(wm5100->pdata.reset, 0);
-		gpio_free(wm5100->pdata.reset);
-	}
-	if (wm5100->pdata.ldo_ena) {
-		gpio_set_value_cansleep(wm5100->pdata.ldo_ena, 0);
-		gpio_free(wm5100->pdata.ldo_ena);
-	}
+	gpiod_set_value_cansleep(wm5100->reset, 1);
+	gpiod_set_value_cansleep(wm5100->ldo_ena, 0);
 }
 
 #ifdef CONFIG_PM
@@ -2660,8 +2632,7 @@ static int wm5100_runtime_suspend(struct device *dev)
 
 	regcache_cache_only(wm5100->regmap, true);
 	regcache_mark_dirty(wm5100->regmap);
-	if (wm5100->pdata.ldo_ena)
-		gpio_set_value_cansleep(wm5100->pdata.ldo_ena, 0);
+	gpiod_set_value_cansleep(wm5100->ldo_ena, 0);
 	regulator_bulk_disable(ARRAY_SIZE(wm5100->core_supplies),
 			       wm5100->core_supplies);
 
@@ -2681,8 +2652,8 @@ static int wm5100_runtime_resume(struct device *dev)
 		return ret;
 	}
 
-	if (wm5100->pdata.ldo_ena) {
-		gpio_set_value_cansleep(wm5100->pdata.ldo_ena, 1);
+	if (wm5100->ldo_ena) {
+		gpiod_set_value_cansleep(wm5100->ldo_ena, 1);
 		msleep(2);
 	}
 
-- 
cgit v1.2.3


From 729f02ec02ae12e5d8a53171bd37e9de56f33677 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Fri, 8 Dec 2023 11:09:29 +0100
Subject: ASoC: wm8996: Convert to GPIO descriptors

This converts the WM8996 codec to use GPIO descriptors, an a similar
way to WM5100.

The driver is instantiating a GPIO chip named wm8996, and we get
rid of the base address for the GPIO chip from the platform data and
just use dynamic numbering. Move base and ngpio into the static
gpio_chip template.

Fix up the only in-tree user which is the Cragganmore 6410 module.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://lore.kernel.org/r/20231208-descriptors-sound-wlf-v1-5-c4dab6f521ec@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 arch/arm/mach-s3c/mach-crag6410-module.c | 14 ++++++--
 include/sound/wm8996.h                   |  3 --
 sound/soc/codecs/wm8996.c                | 58 ++++++++++++++------------------
 3 files changed, 36 insertions(+), 39 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-s3c/mach-crag6410-module.c b/arch/arm/mach-s3c/mach-crag6410-module.c
index 59456fbebf1b..2de1a89f6e99 100644
--- a/arch/arm/mach-s3c/mach-crag6410-module.c
+++ b/arch/arm/mach-s3c/mach-crag6410-module.c
@@ -127,9 +127,16 @@ static struct wm8996_retune_mobile_config wm8996_retune[] = {
 	},
 };
 
+static struct gpiod_lookup_table wm8996_gpiod_table = {
+	.dev_id = "1-001a", /* Device 001a on I2C bus 1 */
+	.table = {
+		GPIO_LOOKUP("GPION", 7,
+			    "wlf,ldo1ena", GPIO_ACTIVE_HIGH),
+		{ },
+	},
+};
+
 static struct wm8996_pdata wm8996_pdata __initdata = {
-	.ldo_ena = S3C64XX_GPN(7),
-	.gpio_base = CODEC_GPIO_BASE,
 	.micdet_def = 1,
 	.inl_mode = WM8996_DIFFERRENTIAL_1,
 	.inr_mode = WM8996_DIFFERRENTIAL_1,
@@ -370,7 +377,8 @@ static const struct {
 	  .spi_devs = balblair_devs,
 	  .num_spi_devs = ARRAY_SIZE(balblair_devs) },
 	{ .id = 0x39, .rev = 0xff, .name = "1254-EV1 Dallas Dhu",
-	  .i2c_devs = wm1254_devs, .num_i2c_devs = ARRAY_SIZE(wm1254_devs) },
+	  .i2c_devs = wm1254_devs, .num_i2c_devs = ARRAY_SIZE(wm1254_devs),
+	  .gpiod_table = &wm8996_gpiod_table },
 	{ .id = 0x3a, .rev = 0xff, .name = "1259-EV1 Tobermory",
 	  .i2c_devs = wm1259_devs, .num_i2c_devs = ARRAY_SIZE(wm1259_devs) },
 	{ .id = 0x3b, .rev = 0xff, .name = "1255-EV1 Kilchoman",
diff --git a/include/sound/wm8996.h b/include/sound/wm8996.h
index 247f9917e33d..342abeef288f 100644
--- a/include/sound/wm8996.h
+++ b/include/sound/wm8996.h
@@ -33,8 +33,6 @@ struct wm8996_retune_mobile_config {
 struct wm8996_pdata {
 	int irq_flags;  /** Set IRQ trigger flags; default active low */
 
-	int ldo_ena;  /** GPIO for LDO1; -1 for none */
-
 	int micdet_def;  /** Default MICDET_SRC/HP1FB_SRC/MICD_BIAS */
 
 	enum wm8996_inmode inl_mode;
@@ -42,7 +40,6 @@ struct wm8996_pdata {
 
 	u32 spkmute_seq;  /** Value for register 0x802 */
 
-	int gpio_base;
 	u32 gpio_default[5];
 
 	int num_retune_mobile_cfgs;
diff --git a/sound/soc/codecs/wm8996.c b/sound/soc/codecs/wm8996.c
index df6195778c57..e738326e33ed 100644
--- a/sound/soc/codecs/wm8996.c
+++ b/sound/soc/codecs/wm8996.c
@@ -14,7 +14,7 @@
 #include <linux/pm.h>
 #include <linux/gcd.h>
 #include <linux/gpio/driver.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/i2c.h>
 #include <linux/regmap.h>
 #include <linux/regulator/consumer.h>
@@ -51,7 +51,7 @@ struct wm8996_priv {
 	struct regmap *regmap;
 	struct snd_soc_component *component;
 
-	int ldo1ena;
+	struct gpio_desc *ldo_ena;
 
 	int sysclk;
 	int sysclk_src;
@@ -1596,9 +1596,9 @@ static int wm8996_set_bias_level(struct snd_soc_component *component,
 				return ret;
 			}
 
-			if (wm8996->pdata.ldo_ena >= 0) {
-				gpio_set_value_cansleep(wm8996->pdata.ldo_ena,
-							1);
+			if (wm8996->ldo_ena) {
+				gpiod_set_value_cansleep(wm8996->ldo_ena,
+							 1);
 				msleep(5);
 			}
 
@@ -1615,8 +1615,8 @@ static int wm8996_set_bias_level(struct snd_soc_component *component,
 
 	case SND_SOC_BIAS_OFF:
 		regcache_cache_only(wm8996->regmap, true);
-		if (wm8996->pdata.ldo_ena >= 0) {
-			gpio_set_value_cansleep(wm8996->pdata.ldo_ena, 0);
+		if (wm8996->ldo_ena) {
+			gpiod_set_value_cansleep(wm8996->ldo_ena, 0);
 			regcache_cache_only(wm8996->regmap, true);
 		}
 		regulator_bulk_disable(ARRAY_SIZE(wm8996->supplies),
@@ -2188,6 +2188,8 @@ static const struct gpio_chip wm8996_template_chip = {
 	.direction_input	= wm8996_gpio_direction_in,
 	.get			= wm8996_gpio_get,
 	.can_sleep		= 1,
+	.ngpio			= 5,
+	.base			= -1,
 };
 
 static void wm8996_init_gpio(struct wm8996_priv *wm8996)
@@ -2195,14 +2197,8 @@ static void wm8996_init_gpio(struct wm8996_priv *wm8996)
 	int ret;
 
 	wm8996->gpio_chip = wm8996_template_chip;
-	wm8996->gpio_chip.ngpio = 5;
 	wm8996->gpio_chip.parent = wm8996->dev;
 
-	if (wm8996->pdata.gpio_base)
-		wm8996->gpio_chip.base = wm8996->pdata.gpio_base;
-	else
-		wm8996->gpio_chip.base = -1;
-
 	ret = gpiochip_add_data(&wm8996->gpio_chip, wm8996);
 	if (ret != 0)
 		dev_err(wm8996->dev, "Failed to add GPIOs: %d\n", ret);
@@ -2771,15 +2767,15 @@ static int wm8996_i2c_probe(struct i2c_client *i2c)
 		memcpy(&wm8996->pdata, dev_get_platdata(&i2c->dev),
 		       sizeof(wm8996->pdata));
 
-	if (wm8996->pdata.ldo_ena > 0) {
-		ret = gpio_request_one(wm8996->pdata.ldo_ena,
-				       GPIOF_OUT_INIT_LOW, "WM8996 ENA");
-		if (ret < 0) {
-			dev_err(&i2c->dev, "Failed to request GPIO %d: %d\n",
-				wm8996->pdata.ldo_ena, ret);
-			goto err;
-		}
+	wm8996->ldo_ena = devm_gpiod_get_optional(&i2c->dev, "wlf,ldo1ena",
+						  GPIOD_OUT_LOW);
+	if (IS_ERR(wm8996->ldo_ena)) {
+		ret = PTR_ERR(wm8996->ldo_ena);
+		dev_err(&i2c->dev, "Failed to request LDO ENA GPIO: %d\n",
+			ret);
+		goto err;
 	}
+	gpiod_set_consumer_name(wm8996->ldo_ena, "WM8996 ENA");
 
 	for (i = 0; i < ARRAY_SIZE(wm8996->supplies); i++)
 		wm8996->supplies[i].supply = wm8996_supply_names[i];
@@ -2814,8 +2810,8 @@ static int wm8996_i2c_probe(struct i2c_client *i2c)
 		goto err_gpio;
 	}
 
-	if (wm8996->pdata.ldo_ena > 0) {
-		gpio_set_value_cansleep(wm8996->pdata.ldo_ena, 1);
+	if (wm8996->ldo_ena) {
+		gpiod_set_value_cansleep(wm8996->ldo_ena, 1);
 		msleep(5);
 	}
 
@@ -2847,8 +2843,8 @@ static int wm8996_i2c_probe(struct i2c_client *i2c)
 	dev_info(&i2c->dev, "revision %c\n",
 		 (reg & WM8996_CHIP_REV_MASK) + 'A');
 
-	if (wm8996->pdata.ldo_ena > 0) {
-		gpio_set_value_cansleep(wm8996->pdata.ldo_ena, 0);
+	if (wm8996->ldo_ena) {
+		gpiod_set_value_cansleep(wm8996->ldo_ena, 0);
 		regcache_cache_only(wm8996->regmap, true);
 	} else {
 		ret = regmap_write(wm8996->regmap, WM8996_SOFTWARE_RESET,
@@ -3054,12 +3050,10 @@ err_gpiolib:
 	wm8996_free_gpio(wm8996);
 err_regmap:
 err_enable:
-	if (wm8996->pdata.ldo_ena > 0)
-		gpio_set_value_cansleep(wm8996->pdata.ldo_ena, 0);
+	if (wm8996->ldo_ena)
+		gpiod_set_value_cansleep(wm8996->ldo_ena, 0);
 	regulator_bulk_disable(ARRAY_SIZE(wm8996->supplies), wm8996->supplies);
 err_gpio:
-	if (wm8996->pdata.ldo_ena > 0)
-		gpio_free(wm8996->pdata.ldo_ena);
 err:
 
 	return ret;
@@ -3070,10 +3064,8 @@ static void wm8996_i2c_remove(struct i2c_client *client)
 	struct wm8996_priv *wm8996 = i2c_get_clientdata(client);
 
 	wm8996_free_gpio(wm8996);
-	if (wm8996->pdata.ldo_ena > 0) {
-		gpio_set_value_cansleep(wm8996->pdata.ldo_ena, 0);
-		gpio_free(wm8996->pdata.ldo_ena);
-	}
+	if (wm8996->ldo_ena)
+		gpiod_set_value_cansleep(wm8996->ldo_ena, 0);
 }
 
 static const struct i2c_device_id wm8996_i2c_id[] = {
-- 
cgit v1.2.3


From d9f28735af8781d9c8c6c406c2a102090644133d Mon Sep 17 00:00:00 2001
From: David Laight <David.Laight@ACULAB.COM>
Date: Wed, 6 Dec 2023 13:44:20 +0000
Subject: Use READ/WRITE_ONCE() for IP local_port_range.

Commit 227b60f5102cd added a seqlock to ensure that the low and high
port numbers were always updated together.
This is overkill because the two 16bit port numbers can be held in
a u32 and read/written in a single instruction.

More recently 91d0b78c5177f added support for finer per-socket limits.
The user-supplied value is 'high << 16 | low' but they are held
separately and the socket options protected by the socket lock.

Use a u32 containing 'high << 16 | low' for both the 'net' and 'sk'
fields and use READ_ONCE()/WRITE_ONCE() to ensure both values are
always updated together.

Change (the now trival) inet_get_local_port_range() to a static inline
to optimise the calling code.
(In particular avoiding returning integers by reference.)

Signed-off-by: David Laight <david.laight@aculab.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Acked-by: Mat Martineau <martineau@kernel.org>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/4e505d4198e946a8be03fb1b4c3072b0@AcuMS.aculab.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/inet_sock.h         |  5 +----
 include/net/ip.h                |  8 +++++++-
 include/net/netns/ipv4.h        |  3 +--
 net/ipv4/af_inet.c              |  4 +---
 net/ipv4/inet_connection_sock.c | 29 ++++++++++-------------------
 net/ipv4/ip_sockglue.c          | 33 ++++++++++++++++-----------------
 net/ipv4/sysctl_net_ipv4.c      | 18 +++++++-----------
 7 files changed, 43 insertions(+), 57 deletions(-)

(limited to 'include')

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 74db6d97cae1..aa86453f6b9b 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -234,10 +234,7 @@ struct inet_sock {
 	int			uc_index;
 	int			mc_index;
 	__be32			mc_addr;
-	struct {
-		__u16 lo;
-		__u16 hi;
-	}			local_port_range;
+	u32			local_port_range;	/* high << 16 | low */
 
 	struct ip_mc_socklist __rcu	*mc_list;
 	struct inet_cork_full	cork;
diff --git a/include/net/ip.h b/include/net/ip.h
index 1fc4c8d69e33..b31be912489a 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -349,7 +349,13 @@ static inline u64 snmp_fold_field64(void __percpu *mib, int offt, size_t syncp_o
 	} \
 }
 
-void inet_get_local_port_range(const struct net *net, int *low, int *high);
+static inline void inet_get_local_port_range(const struct net *net, int *low, int *high)
+{
+	u32 range = READ_ONCE(net->ipv4.ip_local_ports.range);
+
+	*low = range & 0xffff;
+	*high = range >> 16;
+}
 void inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high);
 
 #ifdef CONFIG_SYSCTL
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index ea882964c71e..c356c458b340 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -19,8 +19,7 @@ struct hlist_head;
 struct fib_table;
 struct sock;
 struct local_ports {
-	seqlock_t	lock;
-	int		range[2];
+	u32		range;	/* high << 16 | low */
 	bool		warned;
 };
 
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index fb81de10d332..fbeacf04dbf3 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1847,9 +1847,7 @@ static __net_init int inet_init_net(struct net *net)
 	/*
 	 * Set defaults for local port range
 	 */
-	seqlock_init(&net->ipv4.ip_local_ports.lock);
-	net->ipv4.ip_local_ports.range[0] =  32768;
-	net->ipv4.ip_local_ports.range[1] =  60999;
+	net->ipv4.ip_local_ports.range = 60999u << 16 | 32768u;
 
 	seqlock_init(&net->ipv4.ping_group_range.lock);
 	/*
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 394a498c2823..70be0f6fe879 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -117,34 +117,25 @@ bool inet_rcv_saddr_any(const struct sock *sk)
 	return !sk->sk_rcv_saddr;
 }
 
-void inet_get_local_port_range(const struct net *net, int *low, int *high)
-{
-	unsigned int seq;
-
-	do {
-		seq = read_seqbegin(&net->ipv4.ip_local_ports.lock);
-
-		*low = net->ipv4.ip_local_ports.range[0];
-		*high = net->ipv4.ip_local_ports.range[1];
-	} while (read_seqretry(&net->ipv4.ip_local_ports.lock, seq));
-}
-EXPORT_SYMBOL(inet_get_local_port_range);
-
 void inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high)
 {
 	const struct inet_sock *inet = inet_sk(sk);
 	const struct net *net = sock_net(sk);
 	int lo, hi, sk_lo, sk_hi;
+	u32 sk_range;
 
 	inet_get_local_port_range(net, &lo, &hi);
 
-	sk_lo = inet->local_port_range.lo;
-	sk_hi = inet->local_port_range.hi;
+	sk_range = READ_ONCE(inet->local_port_range);
+	if (unlikely(sk_range)) {
+		sk_lo = sk_range & 0xffff;
+		sk_hi = sk_range >> 16;
 
-	if (unlikely(lo <= sk_lo && sk_lo <= hi))
-		lo = sk_lo;
-	if (unlikely(lo <= sk_hi && sk_hi <= hi))
-		hi = sk_hi;
+		if (lo <= sk_lo && sk_lo <= hi)
+			lo = sk_lo;
+		if (lo <= sk_hi && sk_hi <= hi)
+			hi = sk_hi;
+	}
 
 	*low = lo;
 	*high = hi;
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 2efc53526a38..d7d13940774e 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1055,6 +1055,19 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 	case IP_TOS:	/* This sets both TOS and Precedence */
 		ip_sock_set_tos(sk, val);
 		return 0;
+	case IP_LOCAL_PORT_RANGE:
+	{
+		u16 lo = val;
+		u16 hi = val >> 16;
+
+		if (optlen != sizeof(u32))
+			return -EINVAL;
+		if (lo != 0 && hi != 0 && lo > hi)
+			return -EINVAL;
+
+		WRITE_ONCE(inet->local_port_range, val);
+		return 0;
+	}
 	}
 
 	err = 0;
@@ -1332,20 +1345,6 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 		err = xfrm_user_policy(sk, optname, optval, optlen);
 		break;
 
-	case IP_LOCAL_PORT_RANGE:
-	{
-		const __u16 lo = val;
-		const __u16 hi = val >> 16;
-
-		if (optlen != sizeof(__u32))
-			goto e_inval;
-		if (lo != 0 && hi != 0 && lo > hi)
-			goto e_inval;
-
-		inet->local_port_range.lo = lo;
-		inet->local_port_range.hi = hi;
-		break;
-	}
 	default:
 		err = -ENOPROTOOPT;
 		break;
@@ -1692,6 +1691,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 			return -EFAULT;
 		return 0;
 	}
+	case IP_LOCAL_PORT_RANGE:
+		val = READ_ONCE(inet->local_port_range);
+		goto copyval;
 	}
 
 	if (needs_rtnl)
@@ -1721,9 +1723,6 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname,
 		else
 			err = ip_get_mcast_msfilter(sk, optval, optlen, len);
 		goto out;
-	case IP_LOCAL_PORT_RANGE:
-		val = inet->local_port_range.hi << 16 | inet->local_port_range.lo;
-		break;
 	case IP_PROTOCOL:
 		val = inet_sk(sk)->inet_num;
 		break;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index f63a545a7374..7e4f16a7dcc1 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -50,26 +50,22 @@ static int tcp_plb_max_cong_thresh = 256;
 static int sysctl_tcp_low_latency __read_mostly;
 
 /* Update system visible IP port range */
-static void set_local_port_range(struct net *net, int range[2])
+static void set_local_port_range(struct net *net, unsigned int low, unsigned int high)
 {
-	bool same_parity = !((range[0] ^ range[1]) & 1);
+	bool same_parity = !((low ^ high) & 1);
 
-	write_seqlock_bh(&net->ipv4.ip_local_ports.lock);
 	if (same_parity && !net->ipv4.ip_local_ports.warned) {
 		net->ipv4.ip_local_ports.warned = true;
 		pr_err_ratelimited("ip_local_port_range: prefer different parity for start/end values.\n");
 	}
-	net->ipv4.ip_local_ports.range[0] = range[0];
-	net->ipv4.ip_local_ports.range[1] = range[1];
-	write_sequnlock_bh(&net->ipv4.ip_local_ports.lock);
+	WRITE_ONCE(net->ipv4.ip_local_ports.range, high << 16 | low);
 }
 
 /* Validate changes from /proc interface. */
 static int ipv4_local_port_range(struct ctl_table *table, int write,
 				 void *buffer, size_t *lenp, loff_t *ppos)
 {
-	struct net *net =
-		container_of(table->data, struct net, ipv4.ip_local_ports.range);
+	struct net *net = table->data;
 	int ret;
 	int range[2];
 	struct ctl_table tmp = {
@@ -93,7 +89,7 @@ static int ipv4_local_port_range(struct ctl_table *table, int write,
 		    (range[0] < READ_ONCE(net->ipv4.sysctl_ip_prot_sock)))
 			ret = -EINVAL;
 		else
-			set_local_port_range(net, range);
+			set_local_port_range(net, range[0], range[1]);
 	}
 
 	return ret;
@@ -733,8 +729,8 @@ static struct ctl_table ipv4_net_table[] = {
 	},
 	{
 		.procname	= "ip_local_port_range",
-		.maxlen		= sizeof(init_net.ipv4.ip_local_ports.range),
-		.data		= &init_net.ipv4.ip_local_ports.range,
+		.maxlen		= 0,
+		.data		= &init_net,
 		.mode		= 0644,
 		.proc_handler	= ipv4_local_port_range,
 	},
-- 
cgit v1.2.3


From 172db56d90d29e47e7d0d64885d5dbd92c87ec42 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Wed, 6 Dec 2023 12:59:07 -0800
Subject: netlink: Return unsigned value for nla_len()

The return value from nla_len() is never expected to be negative, and can
never be more than struct nlattr::nla_len (a u16). Adjust the prototype
on the function. This will let GCC's value range optimization passes
know that the return can never be negative, and can never be larger than
u16. As recently discussed[1], this silences the following warning in
GCC 12+:

net/wireless/nl80211.c: In function 'nl80211_set_cqm_rssi.isra':
net/wireless/nl80211.c:12892:17: warning: 'memcpy' specified bound 18446744073709551615 exceeds maximum object size 9223372036854775807 [-Wstringop-overflow=]
12892 |                 memcpy(cqm_config->rssi_thresholds, thresholds,
      |                 ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
12893 |                        flex_array_size(cqm_config, rssi_thresholds,
      |                        ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
12894 |                                        n_thresholds));
      |                                        ~~~~~~~~~~~~~~

A future change would be to clamp the subtraction to make sure it never
wraps around if nla_len is somehow less than NLA_HDRLEN, which would
have the additional benefit of being defensive in the face of nlattr
corruption or logic errors.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202311090752.hWcJWAHL-lkp@intel.com/ [1]
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: Jeff Johnson <quic_jjohnson@quicinc.com>
Cc: Michael Walle <mwalle@kernel.org>
Cc: Max Schulze <max.schulze@online.de>
Link: https://lore.kernel.org/r/20231202202539.it.704-kees@kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20231206205904.make.018-kees@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/netlink.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/netlink.h b/include/net/netlink.h
index 167b91348e57..28039e57070a 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -1214,7 +1214,7 @@ static inline void *nla_data(const struct nlattr *nla)
  * nla_len - length of payload
  * @nla: netlink attribute
  */
-static inline int nla_len(const struct nlattr *nla)
+static inline u16 nla_len(const struct nlattr *nla)
 {
 	return nla->nla_len - NLA_HDRLEN;
 }
-- 
cgit v1.2.3


From 8132d887a7023b212f242a51ae89281c69fde996 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Wed, 18 Oct 2023 12:11:56 -0400
Subject: KVM: remove CONFIG_HAVE_KVM_EVENTFD

virt/kvm/eventfd.c is compiled unconditionally, meaning that the ioeventfds
member of struct kvm is accessed unconditionally.  CONFIG_HAVE_KVM_EVENTFD
therefore must be defined for KVM common code to compile successfully,
remove it.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/arm64/kvm/Kconfig     |  1 -
 arch/loongarch/kvm/Kconfig |  1 -
 arch/mips/kvm/Kconfig      |  1 -
 arch/powerpc/kvm/Kconfig   |  1 -
 arch/riscv/kvm/Kconfig     |  1 -
 arch/s390/kvm/Kconfig      |  1 -
 arch/x86/kvm/Kconfig       |  1 -
 include/linux/kvm_host.h   | 30 +-----------------------------
 virt/kvm/Kconfig           |  5 +----
 9 files changed, 2 insertions(+), 40 deletions(-)

(limited to 'include')

diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 1a777715199f..87bd96c1254f 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -29,7 +29,6 @@ menuconfig KVM
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select KVM_XFER_TO_GUEST_WORK
 	select KVM_VFIO
-	select HAVE_KVM_EVENTFD
 	select HAVE_KVM_IRQFD
 	select HAVE_KVM_DIRTY_RING_ACQ_REL
 	select NEED_KVM_DIRTY_RING_WITH_BITMAP
diff --git a/arch/loongarch/kvm/Kconfig b/arch/loongarch/kvm/Kconfig
index f22bae89b07d..daba4cd5e87d 100644
--- a/arch/loongarch/kvm/Kconfig
+++ b/arch/loongarch/kvm/Kconfig
@@ -22,7 +22,6 @@ config KVM
 	depends on AS_HAS_LVZ_EXTENSION
 	depends on HAVE_KVM
 	select HAVE_KVM_DIRTY_RING_ACQ_REL
-	select HAVE_KVM_EVENTFD
 	select HAVE_KVM_VCPU_ASYNC_IOCTL
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select KVM_GENERIC_HARDWARE_ENABLING
diff --git a/arch/mips/kvm/Kconfig b/arch/mips/kvm/Kconfig
index c04987d2ed2e..428141b0b48f 100644
--- a/arch/mips/kvm/Kconfig
+++ b/arch/mips/kvm/Kconfig
@@ -22,7 +22,6 @@ config KVM
 	select EXPORT_UASM
 	select PREEMPT_NOTIFIERS
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
-	select HAVE_KVM_EVENTFD
 	select HAVE_KVM_VCPU_ASYNC_IOCTL
 	select KVM_MMIO
 	select KVM_GENERIC_MMU_NOTIFIER
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index b33358ee6424..0f4e6e7ba35d 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -20,7 +20,6 @@ if VIRTUALIZATION
 config KVM
 	bool
 	select PREEMPT_NOTIFIERS
-	select HAVE_KVM_EVENTFD
 	select HAVE_KVM_VCPU_ASYNC_IOCTL
 	select KVM_VFIO
 	select IRQ_BYPASS_MANAGER
diff --git a/arch/riscv/kvm/Kconfig b/arch/riscv/kvm/Kconfig
index ae2e05f050ec..be264b78487d 100644
--- a/arch/riscv/kvm/Kconfig
+++ b/arch/riscv/kvm/Kconfig
@@ -20,7 +20,6 @@ if VIRTUALIZATION
 config KVM
 	tristate "Kernel-based Virtual Machine (KVM) support (EXPERIMENTAL)"
 	depends on RISCV_SBI && MMU
-	select HAVE_KVM_EVENTFD
 	select HAVE_KVM_IRQCHIP
 	select HAVE_KVM_IRQFD
 	select HAVE_KVM_IRQ_ROUTING
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
index 45fdf2a9b2e3..ed567b858535 100644
--- a/arch/s390/kvm/Kconfig
+++ b/arch/s390/kvm/Kconfig
@@ -23,7 +23,6 @@ config KVM
 	select PREEMPT_NOTIFIERS
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
 	select HAVE_KVM_VCPU_ASYNC_IOCTL
-	select HAVE_KVM_EVENTFD
 	select KVM_ASYNC_PF
 	select KVM_ASYNC_PF_SYNC
 	select HAVE_KVM_IRQCHIP
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index c1716e83d176..088c66bee98f 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -33,7 +33,6 @@ config KVM
 	select IRQ_BYPASS_MANAGER
 	select HAVE_KVM_IRQ_BYPASS
 	select HAVE_KVM_IRQ_ROUTING
-	select HAVE_KVM_EVENTFD
 	select KVM_ASYNC_PF
 	select USER_RETURN_NOTIFIER
 	select KVM_MMIO
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index ea1523a7b83a..3fe5a6be7768 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -782,7 +782,6 @@ struct kvm {
 	struct list_head vm_list;
 	struct mutex lock;
 	struct kvm_io_bus __rcu *buses[KVM_NR_BUSES];
-#ifdef CONFIG_HAVE_KVM_EVENTFD
 	struct {
 		spinlock_t        lock;
 		struct list_head  items;
@@ -791,7 +790,6 @@ struct kvm {
 		struct mutex      resampler_lock;
 	} irqfds;
 	struct list_head ioeventfds;
-#endif
 	struct kvm_vm_stat stat;
 	struct kvm_arch arch;
 	refcount_t users_count;
@@ -2056,8 +2054,6 @@ static inline void kvm_free_irq_routing(struct kvm *kvm) {}
 
 int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi);
 
-#ifdef CONFIG_HAVE_KVM_EVENTFD
-
 void kvm_eventfd_init(struct kvm *kvm);
 int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args);
 
@@ -2082,31 +2078,7 @@ static inline bool kvm_notify_irqfd_resampler(struct kvm *kvm,
 {
 	return false;
 }
-#endif
-
-#else
-
-static inline void kvm_eventfd_init(struct kvm *kvm) {}
-
-static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args)
-{
-	return -EINVAL;
-}
-
-static inline void kvm_irqfd_release(struct kvm *kvm) {}
-
-#ifdef CONFIG_HAVE_KVM_IRQCHIP
-static inline void kvm_irq_routing_update(struct kvm *kvm)
-{
-}
-#endif
-
-static inline int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
-{
-	return -ENOSYS;
-}
-
-#endif /* CONFIG_HAVE_KVM_EVENTFD */
+#endif /* CONFIG_HAVE_KVM_IRQFD */
 
 void kvm_arch_irq_routing_update(struct kvm *kvm);
 
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 2c964586aa14..72e0cac864f9 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -3,6 +3,7 @@
 
 config HAVE_KVM
        bool
+       select EVENTFD
 
 config HAVE_KVM_PFNCACHE
        bool
@@ -39,10 +40,6 @@ config NEED_KVM_DIRTY_RING_WITH_BITMAP
 	bool
 	depends on HAVE_KVM_DIRTY_RING
 
-config HAVE_KVM_EVENTFD
-       bool
-       select EVENTFD
-
 config KVM_MMIO
        bool
 
-- 
cgit v1.2.3


From c5b31cc2371728ddefe9baf1d036aeb630a25d96 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Wed, 18 Oct 2023 12:07:32 -0400
Subject: KVM: remove CONFIG_HAVE_KVM_IRQFD

All platforms with a kernel irqchip have support for irqfd.  Unify the
two configuration items so that userspace can expect to use irqfd to
inject interrupts into the irqchip.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/arm64/kvm/Kconfig     | 1 -
 arch/powerpc/kvm/Kconfig   | 2 --
 arch/powerpc/kvm/powerpc.c | 2 +-
 arch/riscv/kvm/Kconfig     | 1 -
 arch/s390/kvm/Kconfig      | 1 -
 arch/x86/kvm/Kconfig       | 1 -
 include/linux/kvm_host.h   | 9 ++++-----
 include/trace/events/kvm.h | 8 ++++----
 virt/kvm/Kconfig           | 3 ---
 virt/kvm/eventfd.c         | 6 +++---
 virt/kvm/kvm_main.c        | 4 ++--
 11 files changed, 14 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 87bd96c1254f..b07c60c9737d 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -29,7 +29,6 @@ menuconfig KVM
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select KVM_XFER_TO_GUEST_WORK
 	select KVM_VFIO
-	select HAVE_KVM_IRQFD
 	select HAVE_KVM_DIRTY_RING_ACQ_REL
 	select NEED_KVM_DIRTY_RING_WITH_BITMAP
 	select HAVE_KVM_MSI
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 0f4e6e7ba35d..b47196085a42 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -224,7 +224,6 @@ config KVM_MPIC
 	bool "KVM in-kernel MPIC emulation"
 	depends on KVM && PPC_E500
 	select HAVE_KVM_IRQCHIP
-	select HAVE_KVM_IRQFD
 	select HAVE_KVM_IRQ_ROUTING
 	select HAVE_KVM_MSI
 	help
@@ -237,7 +236,6 @@ config KVM_XICS
 	bool "KVM in-kernel XICS emulation"
 	depends on KVM_BOOK3S_64 && !KVM_MPIC
 	select HAVE_KVM_IRQCHIP
-	select HAVE_KVM_IRQFD
 	default y
 	help
 	  Include support for the XICS (eXternal Interrupt Controller
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index c39945a7fce3..c3f82e238b70 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -578,7 +578,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		break;
 #endif
 
-#ifdef CONFIG_HAVE_KVM_IRQFD
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 	case KVM_CAP_IRQFD_RESAMPLE:
 		r = !xive_enabled();
 		break;
diff --git a/arch/riscv/kvm/Kconfig b/arch/riscv/kvm/Kconfig
index be264b78487d..2b0b51035302 100644
--- a/arch/riscv/kvm/Kconfig
+++ b/arch/riscv/kvm/Kconfig
@@ -21,7 +21,6 @@ config KVM
 	tristate "Kernel-based Virtual Machine (KVM) support (EXPERIMENTAL)"
 	depends on RISCV_SBI && MMU
 	select HAVE_KVM_IRQCHIP
-	select HAVE_KVM_IRQFD
 	select HAVE_KVM_IRQ_ROUTING
 	select HAVE_KVM_MSI
 	select HAVE_KVM_VCPU_ASYNC_IOCTL
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
index ed567b858535..bb6d90351119 100644
--- a/arch/s390/kvm/Kconfig
+++ b/arch/s390/kvm/Kconfig
@@ -26,7 +26,6 @@ config KVM
 	select KVM_ASYNC_PF
 	select KVM_ASYNC_PF_SYNC
 	select HAVE_KVM_IRQCHIP
-	select HAVE_KVM_IRQFD
 	select HAVE_KVM_IRQ_ROUTING
 	select HAVE_KVM_INVALID_WAKEUPS
 	select HAVE_KVM_NO_POLL
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 088c66bee98f..b07247b0b958 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -27,7 +27,6 @@ config KVM
 	select KVM_GENERIC_MMU_NOTIFIER
 	select HAVE_KVM_IRQCHIP
 	select HAVE_KVM_PFNCACHE
-	select HAVE_KVM_IRQFD
 	select HAVE_KVM_DIRTY_RING_TSO
 	select HAVE_KVM_DIRTY_RING_ACQ_REL
 	select IRQ_BYPASS_MANAGER
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 3fe5a6be7768..1bba24a13ec9 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -805,8 +805,7 @@ struct kvm {
 	 * Update side is protected by irq_lock.
 	 */
 	struct kvm_irq_routing_table __rcu *irq_routing;
-#endif
-#ifdef CONFIG_HAVE_KVM_IRQFD
+
 	struct hlist_head irq_ack_notifier_list;
 #endif
 
@@ -996,7 +995,7 @@ static inline void kvm_arch_post_irq_routing_update(struct kvm *kvm)
 }
 #endif
 
-#ifdef CONFIG_HAVE_KVM_IRQFD
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 int kvm_irqfd_init(void);
 void kvm_irqfd_exit(void);
 #else
@@ -2057,7 +2056,7 @@ int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi);
 void kvm_eventfd_init(struct kvm *kvm);
 int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args);
 
-#ifdef CONFIG_HAVE_KVM_IRQFD
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args);
 void kvm_irqfd_release(struct kvm *kvm);
 bool kvm_notify_irqfd_resampler(struct kvm *kvm,
@@ -2078,7 +2077,7 @@ static inline bool kvm_notify_irqfd_resampler(struct kvm *kvm,
 {
 	return false;
 }
-#endif /* CONFIG_HAVE_KVM_IRQFD */
+#endif /* CONFIG_HAVE_KVM_IRQCHIP */
 
 void kvm_arch_irq_routing_update(struct kvm *kvm);
 
diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index 3bd31ea23fee..011fba6b5552 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -62,7 +62,7 @@ TRACE_EVENT(kvm_vcpu_wakeup,
 		  __entry->valid ? "valid" : "invalid")
 );
 
-#if defined(CONFIG_HAVE_KVM_IRQFD)
+#if defined(CONFIG_HAVE_KVM_IRQCHIP)
 TRACE_EVENT(kvm_set_irq,
 	TP_PROTO(unsigned int gsi, int level, int irq_source_id),
 	TP_ARGS(gsi, level, irq_source_id),
@@ -82,7 +82,7 @@ TRACE_EVENT(kvm_set_irq,
 	TP_printk("gsi %u level %d source %d",
 		  __entry->gsi, __entry->level, __entry->irq_source_id)
 );
-#endif /* defined(CONFIG_HAVE_KVM_IRQFD) */
+#endif /* defined(CONFIG_HAVE_KVM_IRQCHIP) */
 
 #if defined(__KVM_HAVE_IOAPIC)
 #define kvm_deliver_mode		\
@@ -170,7 +170,7 @@ TRACE_EVENT(kvm_msi_set_irq,
 
 #endif /* defined(__KVM_HAVE_IOAPIC) */
 
-#if defined(CONFIG_HAVE_KVM_IRQFD)
+#if defined(CONFIG_HAVE_KVM_IRQCHIP)
 
 #ifdef kvm_irqchips
 #define kvm_ack_irq_string "irqchip %s pin %u"
@@ -197,7 +197,7 @@ TRACE_EVENT(kvm_ack_irq,
 	TP_printk(kvm_ack_irq_string, kvm_ack_irq_parm)
 );
 
-#endif /* defined(CONFIG_HAVE_KVM_IRQFD) */
+#endif /* defined(CONFIG_HAVE_KVM_IRQCHIP) */
 
 
 
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 72e0cac864f9..6793211a0b64 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -11,9 +11,6 @@ config HAVE_KVM_PFNCACHE
 config HAVE_KVM_IRQCHIP
        bool
 
-config HAVE_KVM_IRQFD
-       bool
-
 config HAVE_KVM_IRQ_ROUTING
        bool
 
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 89912a17f5d5..19534156d48c 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -28,7 +28,7 @@
 
 #include <kvm/iodev.h>
 
-#ifdef CONFIG_HAVE_KVM_IRQFD
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 
 static struct workqueue_struct *irqfd_cleanup_wq;
 
@@ -531,7 +531,7 @@ void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
 void
 kvm_eventfd_init(struct kvm *kvm)
 {
-#ifdef CONFIG_HAVE_KVM_IRQFD
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 	spin_lock_init(&kvm->irqfds.lock);
 	INIT_LIST_HEAD(&kvm->irqfds.items);
 	INIT_LIST_HEAD(&kvm->irqfds.resampler_list);
@@ -540,7 +540,7 @@ kvm_eventfd_init(struct kvm *kvm)
 	INIT_LIST_HEAD(&kvm->ioeventfds);
 }
 
-#ifdef CONFIG_HAVE_KVM_IRQFD
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 /*
  * shutdown any irqfd's that match fd+gsi
  */
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 8758cb799e18..a20cf1f9ad29 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1273,7 +1273,7 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 	if (r)
 		goto out_err_no_disable;
 
-#ifdef CONFIG_HAVE_KVM_IRQFD
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 	INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list);
 #endif
 
@@ -4826,7 +4826,7 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 #ifdef CONFIG_HAVE_KVM_MSI
 	case KVM_CAP_SIGNAL_MSI:
 #endif
-#ifdef CONFIG_HAVE_KVM_IRQFD
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 	case KVM_CAP_IRQFD:
 #endif
 	case KVM_CAP_IOEVENTFD_ANY_LENGTH:
-- 
cgit v1.2.3


From a5d3df8ae13fada772fbce952e9ee7b3433dba16 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Wed, 8 Nov 2023 10:34:03 +0100
Subject: KVM: remove deprecated UAPIs

The deprecated interfaces were removed 15 years ago.  KVM's
device assignment was deprecated in 4.2 and removed 6.5 years
ago; the only interest might be in compiling ancient versions
of QEMU, but QEMU has been using its own imported copy of the
kernel headers since June 2011.  So again we go into archaeology
territory; just remove the cruft.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virt/kvm/api.rst | 12 ------
 include/uapi/linux/kvm.h       | 90 ------------------------------------------
 virt/kvm/kvm_main.c            |  5 ---
 3 files changed, 107 deletions(-)

(limited to 'include')

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 926241e23aeb..9326af2a4869 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -627,18 +627,6 @@ interrupt number dequeues the interrupt.
 This is an asynchronous vcpu ioctl and can be invoked from any thread.
 
 
-4.17 KVM_DEBUG_GUEST
---------------------
-
-:Capability: basic
-:Architectures: none
-:Type: vcpu ioctl
-:Parameters: none)
-:Returns: -1 on error
-
-Support for this has been removed.  Use KVM_SET_GUEST_DEBUG instead.
-
-
 4.18 KVM_GET_MSRS
 -----------------
 
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index e9cb2df67a1d..b1f92a0edc35 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -16,76 +16,6 @@
 
 #define KVM_API_VERSION 12
 
-/* *** Deprecated interfaces *** */
-
-#define KVM_TRC_SHIFT           16
-
-#define KVM_TRC_ENTRYEXIT       (1 << KVM_TRC_SHIFT)
-#define KVM_TRC_HANDLER         (1 << (KVM_TRC_SHIFT + 1))
-
-#define KVM_TRC_VMENTRY         (KVM_TRC_ENTRYEXIT + 0x01)
-#define KVM_TRC_VMEXIT          (KVM_TRC_ENTRYEXIT + 0x02)
-#define KVM_TRC_PAGE_FAULT      (KVM_TRC_HANDLER + 0x01)
-
-#define KVM_TRC_HEAD_SIZE       12
-#define KVM_TRC_CYCLE_SIZE      8
-#define KVM_TRC_EXTRA_MAX       7
-
-#define KVM_TRC_INJ_VIRQ         (KVM_TRC_HANDLER + 0x02)
-#define KVM_TRC_REDELIVER_EVT    (KVM_TRC_HANDLER + 0x03)
-#define KVM_TRC_PEND_INTR        (KVM_TRC_HANDLER + 0x04)
-#define KVM_TRC_IO_READ          (KVM_TRC_HANDLER + 0x05)
-#define KVM_TRC_IO_WRITE         (KVM_TRC_HANDLER + 0x06)
-#define KVM_TRC_CR_READ          (KVM_TRC_HANDLER + 0x07)
-#define KVM_TRC_CR_WRITE         (KVM_TRC_HANDLER + 0x08)
-#define KVM_TRC_DR_READ          (KVM_TRC_HANDLER + 0x09)
-#define KVM_TRC_DR_WRITE         (KVM_TRC_HANDLER + 0x0A)
-#define KVM_TRC_MSR_READ         (KVM_TRC_HANDLER + 0x0B)
-#define KVM_TRC_MSR_WRITE        (KVM_TRC_HANDLER + 0x0C)
-#define KVM_TRC_CPUID            (KVM_TRC_HANDLER + 0x0D)
-#define KVM_TRC_INTR             (KVM_TRC_HANDLER + 0x0E)
-#define KVM_TRC_NMI              (KVM_TRC_HANDLER + 0x0F)
-#define KVM_TRC_VMMCALL          (KVM_TRC_HANDLER + 0x10)
-#define KVM_TRC_HLT              (KVM_TRC_HANDLER + 0x11)
-#define KVM_TRC_CLTS             (KVM_TRC_HANDLER + 0x12)
-#define KVM_TRC_LMSW             (KVM_TRC_HANDLER + 0x13)
-#define KVM_TRC_APIC_ACCESS      (KVM_TRC_HANDLER + 0x14)
-#define KVM_TRC_TDP_FAULT        (KVM_TRC_HANDLER + 0x15)
-#define KVM_TRC_GTLB_WRITE       (KVM_TRC_HANDLER + 0x16)
-#define KVM_TRC_STLB_WRITE       (KVM_TRC_HANDLER + 0x17)
-#define KVM_TRC_STLB_INVAL       (KVM_TRC_HANDLER + 0x18)
-#define KVM_TRC_PPC_INSTR        (KVM_TRC_HANDLER + 0x19)
-
-struct kvm_user_trace_setup {
-	__u32 buf_size;
-	__u32 buf_nr;
-};
-
-#define __KVM_DEPRECATED_MAIN_W_0x06 \
-	_IOW(KVMIO, 0x06, struct kvm_user_trace_setup)
-#define __KVM_DEPRECATED_MAIN_0x07 _IO(KVMIO, 0x07)
-#define __KVM_DEPRECATED_MAIN_0x08 _IO(KVMIO, 0x08)
-
-#define __KVM_DEPRECATED_VM_R_0x70 _IOR(KVMIO, 0x70, struct kvm_assigned_irq)
-
-struct kvm_breakpoint {
-	__u32 enabled;
-	__u32 padding;
-	__u64 address;
-};
-
-struct kvm_debug_guest {
-	__u32 enabled;
-	__u32 pad;
-	struct kvm_breakpoint breakpoints[4];
-	__u32 singlestep;
-};
-
-#define __KVM_DEPRECATED_VCPU_W_0x87 _IOW(KVMIO, 0x87, struct kvm_debug_guest)
-
-/* *** End of deprecated interfaces *** */
-
-
 /* for KVM_SET_USER_MEMORY_REGION */
 struct kvm_userspace_memory_region {
 	__u32 slot;
@@ -967,9 +897,6 @@ struct kvm_ppc_resize_hpt {
  */
 #define KVM_GET_VCPU_MMAP_SIZE    _IO(KVMIO,   0x04) /* in bytes */
 #define KVM_GET_SUPPORTED_CPUID   _IOWR(KVMIO, 0x05, struct kvm_cpuid2)
-#define KVM_TRACE_ENABLE          __KVM_DEPRECATED_MAIN_W_0x06
-#define KVM_TRACE_PAUSE           __KVM_DEPRECATED_MAIN_0x07
-#define KVM_TRACE_DISABLE         __KVM_DEPRECATED_MAIN_0x08
 #define KVM_GET_EMULATED_CPUID	  _IOWR(KVMIO, 0x09, struct kvm_cpuid2)
 #define KVM_GET_MSR_FEATURE_INDEX_LIST    _IOWR(KVMIO, 0x0a, struct kvm_msr_list)
 
@@ -1536,20 +1463,8 @@ struct kvm_s390_ucas_mapping {
 			_IOW(KVMIO,  0x67, struct kvm_coalesced_mmio_zone)
 #define KVM_UNREGISTER_COALESCED_MMIO \
 			_IOW(KVMIO,  0x68, struct kvm_coalesced_mmio_zone)
-#define KVM_ASSIGN_PCI_DEVICE     _IOR(KVMIO,  0x69, \
-				       struct kvm_assigned_pci_dev)
 #define KVM_SET_GSI_ROUTING       _IOW(KVMIO,  0x6a, struct kvm_irq_routing)
-/* deprecated, replaced by KVM_ASSIGN_DEV_IRQ */
-#define KVM_ASSIGN_IRQ            __KVM_DEPRECATED_VM_R_0x70
-#define KVM_ASSIGN_DEV_IRQ        _IOW(KVMIO,  0x70, struct kvm_assigned_irq)
 #define KVM_REINJECT_CONTROL      _IO(KVMIO,   0x71)
-#define KVM_DEASSIGN_PCI_DEVICE   _IOW(KVMIO,  0x72, \
-				       struct kvm_assigned_pci_dev)
-#define KVM_ASSIGN_SET_MSIX_NR    _IOW(KVMIO,  0x73, \
-				       struct kvm_assigned_msix_nr)
-#define KVM_ASSIGN_SET_MSIX_ENTRY _IOW(KVMIO,  0x74, \
-				       struct kvm_assigned_msix_entry)
-#define KVM_DEASSIGN_DEV_IRQ      _IOW(KVMIO,  0x75, struct kvm_assigned_irq)
 #define KVM_IRQFD                 _IOW(KVMIO,  0x76, struct kvm_irqfd)
 #define KVM_CREATE_PIT2		  _IOW(KVMIO,  0x77, struct kvm_pit_config)
 #define KVM_SET_BOOT_CPU_ID       _IO(KVMIO,   0x78)
@@ -1566,9 +1481,6 @@ struct kvm_s390_ucas_mapping {
 *  KVM_CAP_VM_TSC_CONTROL to set defaults for a VM */
 #define KVM_SET_TSC_KHZ           _IO(KVMIO,  0xa2)
 #define KVM_GET_TSC_KHZ           _IO(KVMIO,  0xa3)
-/* Available with KVM_CAP_PCI_2_3 */
-#define KVM_ASSIGN_SET_INTX_MASK  _IOW(KVMIO,  0xa4, \
-				       struct kvm_assigned_pci_dev)
 /* Available with KVM_CAP_SIGNAL_MSI */
 #define KVM_SIGNAL_MSI            _IOW(KVMIO,  0xa5, struct kvm_msi)
 /* Available with KVM_CAP_PPC_GET_SMMU_INFO */
@@ -1621,8 +1533,6 @@ struct kvm_s390_ucas_mapping {
 #define KVM_SET_SREGS             _IOW(KVMIO,  0x84, struct kvm_sregs)
 #define KVM_TRANSLATE             _IOWR(KVMIO, 0x85, struct kvm_translation)
 #define KVM_INTERRUPT             _IOW(KVMIO,  0x86, struct kvm_interrupt)
-/* KVM_DEBUG_GUEST is no longer supported, use KVM_SET_GUEST_DEBUG instead */
-#define KVM_DEBUG_GUEST           __KVM_DEPRECATED_VCPU_W_0x87
 #define KVM_GET_MSRS              _IOWR(KVMIO, 0x88, struct kvm_msrs)
 #define KVM_SET_MSRS              _IOW(KVMIO,  0x89, struct kvm_msrs)
 #define KVM_SET_CPUID             _IOW(KVMIO,  0x8a, struct kvm_cpuid)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index a20cf1f9ad29..acd67fb40183 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -5497,11 +5497,6 @@ static long kvm_dev_ioctl(struct file *filp,
 		r += PAGE_SIZE;    /* coalesced mmio ring page */
 #endif
 		break;
-	case KVM_TRACE_ENABLE:
-	case KVM_TRACE_PAUSE:
-	case KVM_TRACE_DISABLE:
-		r = -EOPNOTSUPP;
-		break;
 	default:
 		return kvm_arch_dev_ioctl(filp, ioctl, arg);
 	}
-- 
cgit v1.2.3


From 8ed26ab8d59111c2f7b86d200d1eb97d2a458fd1 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Wed, 18 Oct 2023 12:18:00 -0400
Subject: KVM: clean up directives to compile out irqfds

Keep all #ifdef CONFIG_HAVE_KVM_IRQCHIP parts of eventfd.c together, and
compile out the irqfds field of struct kvm if the symbol is not defined.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/kvm_host.h |  2 ++
 virt/kvm/eventfd.c       | 26 ++++++++++++--------------
 2 files changed, 14 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 1bba24a13ec9..7e7fd25b09b3 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -782,6 +782,7 @@ struct kvm {
 	struct list_head vm_list;
 	struct mutex lock;
 	struct kvm_io_bus __rcu *buses[KVM_NR_BUSES];
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 	struct {
 		spinlock_t        lock;
 		struct list_head  items;
@@ -789,6 +790,7 @@ struct kvm {
 		struct list_head  resampler_list;
 		struct mutex      resampler_lock;
 	} irqfds;
+#endif
 	struct list_head ioeventfds;
 	struct kvm_vm_stat stat;
 	struct kvm_arch arch;
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 19534156d48c..d516e6d33f56 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -526,21 +526,7 @@ void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
 	synchronize_srcu(&kvm->irq_srcu);
 	kvm_arch_post_irq_ack_notifier_list_update(kvm);
 }
-#endif
-
-void
-kvm_eventfd_init(struct kvm *kvm)
-{
-#ifdef CONFIG_HAVE_KVM_IRQCHIP
-	spin_lock_init(&kvm->irqfds.lock);
-	INIT_LIST_HEAD(&kvm->irqfds.items);
-	INIT_LIST_HEAD(&kvm->irqfds.resampler_list);
-	mutex_init(&kvm->irqfds.resampler_lock);
-#endif
-	INIT_LIST_HEAD(&kvm->ioeventfds);
-}
 
-#ifdef CONFIG_HAVE_KVM_IRQCHIP
 /*
  * shutdown any irqfd's that match fd+gsi
  */
@@ -1012,3 +998,15 @@ kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 
 	return kvm_assign_ioeventfd(kvm, args);
 }
+
+void
+kvm_eventfd_init(struct kvm *kvm)
+{
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
+	spin_lock_init(&kvm->irqfds.lock);
+	INIT_LIST_HEAD(&kvm->irqfds.items);
+	INIT_LIST_HEAD(&kvm->irqfds.resampler_list);
+	mutex_init(&kvm->irqfds.resampler_lock);
+#endif
+	INIT_LIST_HEAD(&kvm->ioeventfds);
+}
-- 
cgit v1.2.3


From 92e1567ee3e3f6f160e320890ac77eec50bf8e7d Mon Sep 17 00:00:00 2001
From: Andrei Matei <andreimatei1@gmail.com>
Date: Thu, 7 Dec 2023 22:25:17 -0500
Subject: bpf: Add some comments to stack representation

Add comments to the datastructure tracking the stack state, as the
mapping between each stack slot and where its state is stored is not
entirely obvious.

Signed-off-by: Andrei Matei <andreimatei1@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/bpf/20231208032519.260451-2-andreimatei1@gmail.com
---
 include/linux/bpf_verifier.h | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

(limited to 'include')

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index bada59812e00..314b679fb494 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -321,7 +321,17 @@ struct bpf_func_state {
 	/* The following fields should be last. See copy_func_state() */
 	int acquired_refs;
 	struct bpf_reference_state *refs;
+	/* The state of the stack. Each element of the array describes BPF_REG_SIZE
+	 * (i.e. 8) bytes worth of stack memory.
+	 * stack[0] represents bytes [*(r10-8)..*(r10-1)]
+	 * stack[1] represents bytes [*(r10-16)..*(r10-9)]
+	 * ...
+	 * stack[allocated_stack/8 - 1] represents [*(r10-allocated_stack)..*(r10-allocated_stack+7)]
+	 */
 	struct bpf_stack_state *stack;
+	/* Size of the current stack, in bytes. The stack state is tracked below, in
+	 * `stack`. allocated_stack is always a multiple of BPF_REG_SIZE.
+	 */
 	int allocated_stack;
 };
 
@@ -658,6 +668,10 @@ struct bpf_verifier_env {
 	int exception_callback_subprog;
 	bool explore_alu_limits;
 	bool allow_ptr_leaks;
+	/* Allow access to uninitialized stack memory. Writes with fixed offset are
+	 * always allowed, so this refers to reads (with fixed or variable offset),
+	 * to writes with variable offset and to indirect (helper) accesses.
+	 */
 	bool allow_uninit_stack;
 	bool bpf_capable;
 	bool bypass_spec_v1;
-- 
cgit v1.2.3


From a3c205d0560f63ff02516b6d9fc3348dc34251c8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 7 Dec 2023 20:13:22 +0000
Subject: ipv6: do not check fib6_has_expires() in fib6_info_release()

My prior patch went a bit too far, because apparently fib6_has_expires()
could be true while f6i->gc_link is not hashed yet.

fib6_set_expires_locked() can indeed set RTF_EXPIRES
while f6i->fib6_table is NULL.

Original syzbot reports were about corruptions caused
by dangling f6i->gc_link.

Fixes: 5a08d0065a91 ("ipv6: add debug checks in fib6_info_release()")
Reported-by: syzbot+c15aa445274af8674f41@syzkaller.appspotmail.com
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Kui-Feng Lee <thinker.li@gmail.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20231207201322.549000-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/ip6_fib.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index e1e7a894863a..95ed495c3a40 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -329,7 +329,6 @@ static inline bool fib6_info_hold_safe(struct fib6_info *f6i)
 static inline void fib6_info_release(struct fib6_info *f6i)
 {
 	if (f6i && refcount_dec_and_test(&f6i->fib6_ref)) {
-		DEBUG_NET_WARN_ON_ONCE(fib6_has_expires(f6i));
 		DEBUG_NET_WARN_ON_ONCE(!hlist_unhashed(&f6i->gc_link));
 		call_rcu(&f6i->rcu, fib6_info_destroy_rcu);
 	}
-- 
cgit v1.2.3


From 5b20755b7780464fea3e54af0af744258dcc2841 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sun, 26 Nov 2023 16:19:14 +0900
Subject: init: move THIS_MODULE from <linux/export.h> to <linux/init.h>

Commit f50169324df4 ("module.h: split out the EXPORT_SYMBOL into
export.h") appropriately separated EXPORT_SYMBOL into <linux/export.h>
because modules and EXPORT_SYMBOL are orthogonal; modules are symbol
consumers, while EXPORT_SYMBOL are used by symbol providers, which
may not be necessarily a module.

However, that commit also relocated THIS_MODULE. As explained in the
commit description, the intention was to define THIS_MODULE in a
lightweight header, but I do not believe <linux/export.h> was the
best location because EXPORT_SYMBOL and THIS_MODULE are unrelated.

Move it to another lightweight header, <linux/init.h>. The reason for
choosing <linux/init.h> is to make <linux/moduleparam.h> self-contained
without relying on <linux/linkage.h> incorrectly including
<linux/export.h>.

With this adjustment, the role of <linux/export.h> becomes clearer as
it only defines EXPORT_SYMBOL.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
---
 include/linux/export.h | 18 ------------------
 include/linux/init.h   |  7 +++++++
 2 files changed, 7 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/linux/export.h b/include/linux/export.h
index 9911508a9604..0bbd02fd351d 100644
--- a/include/linux/export.h
+++ b/include/linux/export.h
@@ -6,15 +6,6 @@
 #include <linux/linkage.h>
 #include <linux/stringify.h>
 
-/*
- * Export symbols from the kernel to modules.  Forked from module.h
- * to reduce the amount of pointless cruft we feed to gcc when only
- * exporting a simple symbol or two.
- *
- * Try not to add #includes here.  It slows compilation and makes kernel
- * hackers place grumpy comments in header files.
- */
-
 /*
  * This comment block is used by fixdep. Please do not remove.
  *
@@ -23,15 +14,6 @@
  * side effect of the *.o build rule.
  */
 
-#ifndef __ASSEMBLY__
-#ifdef MODULE
-extern struct module __this_module;
-#define THIS_MODULE (&__this_module)
-#else
-#define THIS_MODULE ((struct module *)0)
-#endif
-#endif /* __ASSEMBLY__ */
-
 #ifdef CONFIG_64BIT
 #define __EXPORT_SYMBOL_REF(sym)			\
 	.balign 8				ASM_NL	\
diff --git a/include/linux/init.h b/include/linux/init.h
index 01b52c9c7526..3fa3f6241350 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -179,6 +179,13 @@ extern void (*late_time_init)(void);
 
 extern bool initcall_debug;
 
+#ifdef MODULE
+extern struct module __this_module;
+#define THIS_MODULE (&__this_module)
+#else
+#define THIS_MODULE ((struct module *)0)
+#endif
+
 #endif
   
 #ifndef MODULE
-- 
cgit v1.2.3


From b73f08bb7fe5a0901646ca5ceaa1e7a2d5ee6293 Mon Sep 17 00:00:00 2001
From: Nuno Sa <nuno.sa@analog.com>
Date: Thu, 7 Dec 2023 13:39:27 +0100
Subject: iio: adc: ad9467: fix scale setting

When reading in_voltage_scale we can get something like:

root@analog:/sys/bus/iio/devices/iio:device2# cat in_voltage_scale
0.038146

However, when reading the available options:

root@analog:/sys/bus/iio/devices/iio:device2# cat
in_voltage_scale_available
2000.000000 2100.000006 2200.000007 2300.000008 2400.000009 2500.000010

which does not make sense. Moreover, when trying to set a new scale we
get an error because there's no call to __ad9467_get_scale() to give us
values as given when reading in_voltage_scale. Fix it by computing the
available scales during probe and properly pass the list when
.read_available() is called.

While at it, change to use .read_available() from iio_info. Also note
that to properly fix this, adi-axi-adc.c has to be changed accordingly.

Fixes: ad6797120238 ("iio: adc: ad9467: add support AD9467 ADC")
Signed-off-by: Nuno Sa <nuno.sa@analog.com>
Reviewed-by: David Lechner <dlechner@baylibre.com>
Link: https://lore.kernel.org/r/20231207-iio-backend-prep-v2-4-a4a33bc4d70e@analog.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad9467.c            | 47 +++++++++++++++++++++++
 drivers/iio/adc/adi-axi-adc.c       | 74 ++++++++-----------------------------
 include/linux/iio/adc/adi-axi-adc.h |  4 ++
 3 files changed, 66 insertions(+), 59 deletions(-)

(limited to 'include')

diff --git a/drivers/iio/adc/ad9467.c b/drivers/iio/adc/ad9467.c
index 104c6d394a3e..f668313730cb 100644
--- a/drivers/iio/adc/ad9467.c
+++ b/drivers/iio/adc/ad9467.c
@@ -120,6 +120,7 @@ struct ad9467_state {
 	struct spi_device		*spi;
 	struct clk			*clk;
 	unsigned int			output_mode;
+	unsigned int                    (*scales)[2];
 
 	struct gpio_desc		*pwrdown_gpio;
 	/* ensure consistent state obtained on multiple related accesses */
@@ -216,6 +217,7 @@ static void __ad9467_get_scale(struct adi_axi_adc_conv *conv, int index,
 	.channel = _chan,						\
 	.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE) |		\
 		BIT(IIO_CHAN_INFO_SAMP_FREQ),				\
+	.info_mask_shared_by_type_available = BIT(IIO_CHAN_INFO_SCALE), \
 	.scan_index = _si,						\
 	.scan_type = {							\
 		.sign = _sign,						\
@@ -370,6 +372,26 @@ static int ad9467_write_raw(struct adi_axi_adc_conv *conv,
 	}
 }
 
+static int ad9467_read_avail(struct adi_axi_adc_conv *conv,
+			     struct iio_chan_spec const *chan,
+			     const int **vals, int *type, int *length,
+			     long mask)
+{
+	const struct adi_axi_adc_chip_info *info = conv->chip_info;
+	struct ad9467_state *st = adi_axi_adc_conv_priv(conv);
+
+	switch (mask) {
+	case IIO_CHAN_INFO_SCALE:
+		*vals = (const int *)st->scales;
+		*type = IIO_VAL_INT_PLUS_MICRO;
+		/* Values are stored in a 2D matrix */
+		*length = info->num_scales * 2;
+		return IIO_AVAIL_LIST;
+	default:
+		return -EINVAL;
+	}
+}
+
 static int ad9467_outputmode_set(struct spi_device *spi, unsigned int mode)
 {
 	int ret;
@@ -382,6 +404,26 @@ static int ad9467_outputmode_set(struct spi_device *spi, unsigned int mode)
 				AN877_ADC_TRANSFER_SYNC);
 }
 
+static int ad9467_scale_fill(struct adi_axi_adc_conv *conv)
+{
+	const struct adi_axi_adc_chip_info *info = conv->chip_info;
+	struct ad9467_state *st = adi_axi_adc_conv_priv(conv);
+	unsigned int i, val1, val2;
+
+	st->scales = devm_kmalloc_array(&st->spi->dev, info->num_scales,
+					sizeof(*st->scales), GFP_KERNEL);
+	if (!st->scales)
+		return -ENOMEM;
+
+	for (i = 0; i < info->num_scales; i++) {
+		__ad9467_get_scale(conv, i, &val1, &val2);
+		st->scales[i][0] = val1;
+		st->scales[i][1] = val2;
+	}
+
+	return 0;
+}
+
 static int ad9467_preenable_setup(struct adi_axi_adc_conv *conv)
 {
 	struct ad9467_state *st = adi_axi_adc_conv_priv(conv);
@@ -440,6 +482,10 @@ static int ad9467_probe(struct spi_device *spi)
 
 	conv->chip_info = &info->axi_adc_info;
 
+	ret = ad9467_scale_fill(conv);
+	if (ret)
+		return ret;
+
 	id = ad9467_spi_read(spi, AN877_ADC_REG_CHIP_ID);
 	if (id != conv->chip_info->id) {
 		dev_err(&spi->dev, "Mismatch CHIP_ID, got 0x%X, expected 0x%X\n",
@@ -450,6 +496,7 @@ static int ad9467_probe(struct spi_device *spi)
 	conv->reg_access = ad9467_reg_access;
 	conv->write_raw = ad9467_write_raw;
 	conv->read_raw = ad9467_read_raw;
+	conv->read_avail = ad9467_read_avail;
 	conv->preenable_setup = ad9467_preenable_setup;
 
 	st->output_mode = info->default_output_mode |
diff --git a/drivers/iio/adc/adi-axi-adc.c b/drivers/iio/adc/adi-axi-adc.c
index aff0532a974a..ae83ada7f9f2 100644
--- a/drivers/iio/adc/adi-axi-adc.c
+++ b/drivers/iio/adc/adi-axi-adc.c
@@ -144,6 +144,20 @@ static int adi_axi_adc_write_raw(struct iio_dev *indio_dev,
 	return conv->write_raw(conv, chan, val, val2, mask);
 }
 
+static int adi_axi_adc_read_avail(struct iio_dev *indio_dev,
+				  struct iio_chan_spec const *chan,
+				  const int **vals, int *type, int *length,
+				  long mask)
+{
+	struct adi_axi_adc_state *st = iio_priv(indio_dev);
+	struct adi_axi_adc_conv *conv = &st->client->conv;
+
+	if (!conv->read_avail)
+		return -EOPNOTSUPP;
+
+	return conv->read_avail(conv, chan, vals, type, length, mask);
+}
+
 static int adi_axi_adc_update_scan_mode(struct iio_dev *indio_dev,
 					const unsigned long *scan_mask)
 {
@@ -228,69 +242,11 @@ struct adi_axi_adc_conv *devm_adi_axi_adc_conv_register(struct device *dev,
 }
 EXPORT_SYMBOL_NS_GPL(devm_adi_axi_adc_conv_register, IIO_ADI_AXI);
 
-static ssize_t in_voltage_scale_available_show(struct device *dev,
-					       struct device_attribute *attr,
-					       char *buf)
-{
-	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
-	struct adi_axi_adc_state *st = iio_priv(indio_dev);
-	struct adi_axi_adc_conv *conv = &st->client->conv;
-	size_t len = 0;
-	int i;
-
-	for (i = 0; i < conv->chip_info->num_scales; i++) {
-		const unsigned int *s = conv->chip_info->scale_table[i];
-
-		len += scnprintf(buf + len, PAGE_SIZE - len,
-				 "%u.%06u ", s[0], s[1]);
-	}
-	buf[len - 1] = '\n';
-
-	return len;
-}
-
-static IIO_DEVICE_ATTR_RO(in_voltage_scale_available, 0);
-
-enum {
-	ADI_AXI_ATTR_SCALE_AVAIL,
-};
-
-#define ADI_AXI_ATTR(_en_, _file_)			\
-	[ADI_AXI_ATTR_##_en_] = &iio_dev_attr_##_file_.dev_attr.attr
-
-static struct attribute *adi_axi_adc_attributes[] = {
-	ADI_AXI_ATTR(SCALE_AVAIL, in_voltage_scale_available),
-	NULL
-};
-
-static umode_t axi_adc_attr_is_visible(struct kobject *kobj,
-				       struct attribute *attr, int n)
-{
-	struct device *dev = kobj_to_dev(kobj);
-	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
-	struct adi_axi_adc_state *st = iio_priv(indio_dev);
-	struct adi_axi_adc_conv *conv = &st->client->conv;
-
-	switch (n) {
-	case ADI_AXI_ATTR_SCALE_AVAIL:
-		if (!conv->chip_info->num_scales)
-			return 0;
-		return attr->mode;
-	default:
-		return attr->mode;
-	}
-}
-
-static const struct attribute_group adi_axi_adc_attribute_group = {
-	.attrs = adi_axi_adc_attributes,
-	.is_visible = axi_adc_attr_is_visible,
-};
-
 static const struct iio_info adi_axi_adc_info = {
 	.read_raw = &adi_axi_adc_read_raw,
 	.write_raw = &adi_axi_adc_write_raw,
-	.attrs = &adi_axi_adc_attribute_group,
 	.update_scan_mode = &adi_axi_adc_update_scan_mode,
+	.read_avail = &adi_axi_adc_read_avail,
 };
 
 static const struct adi_axi_adc_core_info adi_axi_adc_10_0_a_info = {
diff --git a/include/linux/iio/adc/adi-axi-adc.h b/include/linux/iio/adc/adi-axi-adc.h
index 52620e5b8052..b7904992d561 100644
--- a/include/linux/iio/adc/adi-axi-adc.h
+++ b/include/linux/iio/adc/adi-axi-adc.h
@@ -41,6 +41,7 @@ struct adi_axi_adc_chip_info {
  * @reg_access		IIO debugfs_reg_access hook for the client ADC
  * @read_raw		IIO read_raw hook for the client ADC
  * @write_raw		IIO write_raw hook for the client ADC
+ * @read_avail		IIO read_avail hook for the client ADC
  */
 struct adi_axi_adc_conv {
 	const struct adi_axi_adc_chip_info		*chip_info;
@@ -54,6 +55,9 @@ struct adi_axi_adc_conv {
 	int (*write_raw)(struct adi_axi_adc_conv *conv,
 			 struct iio_chan_spec const *chan,
 			 int val, int val2, long mask);
+	int (*read_avail)(struct adi_axi_adc_conv *conv,
+			  struct iio_chan_spec const *chan,
+			  const int **val, int *type, int *length, long mask);
 };
 
 struct adi_axi_adc_conv *devm_adi_axi_adc_conv_register(struct device *dev,
-- 
cgit v1.2.3


From 0a910f1606384a5886a045e36b1fc80a7fa6706b Mon Sep 17 00:00:00 2001
From: Peter Griffin <peter.griffin@linaro.org>
Date: Sat, 9 Dec 2023 23:30:48 +0000
Subject: dt-bindings: clock: Add Google gs101 clock management unit bindings

Provide dt-schema documentation for Google gs101 SoC clock controller.
Currently this adds support for cmu_top, cmu_misc and cmu_apm.

Reviewed-by: Sam Protsenko <semen.protsenko@linaro.org>
Signed-off-by: Peter Griffin <peter.griffin@linaro.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231209233106.147416-3-peter.griffin@linaro.org
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 .../bindings/clock/google,gs101-clock.yaml         | 106 ++++++
 include/dt-bindings/clock/google,gs101.h           | 392 +++++++++++++++++++++
 2 files changed, 498 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/clock/google,gs101-clock.yaml
 create mode 100644 include/dt-bindings/clock/google,gs101.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/clock/google,gs101-clock.yaml b/Documentation/devicetree/bindings/clock/google,gs101-clock.yaml
new file mode 100644
index 000000000000..3eebc03a309b
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/google,gs101-clock.yaml
@@ -0,0 +1,106 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/google,gs101-clock.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Google GS101 SoC clock controller
+
+maintainers:
+  - Peter Griffin <peter.griffin@linaro.org>
+
+description: |
+  Google GS101 clock controller is comprised of several CMU units, generating
+  clocks for different domains. Those CMU units are modeled as separate device
+  tree nodes, and might depend on each other. The root clock in that clock tree
+  is OSCCLK (24.576 MHz). That external clock must be defined as a fixed-rate
+  clock in dts.
+
+  CMU_TOP is a top-level CMU, where all base clocks are prepared using PLLs and
+  dividers; all other leaf clocks (other CMUs) are usually derived from CMU_TOP.
+
+  Each clock is assigned an identifier and client nodes can use this identifier
+  to specify the clock which they consume. All clocks available for usage
+  in clock consumer nodes are defined as preprocessor macros in
+  'dt-bindings/clock/gs101.h' header.
+
+properties:
+  compatible:
+    enum:
+      - google,gs101-cmu-top
+      - google,gs101-cmu-apm
+      - google,gs101-cmu-misc
+
+  clocks:
+    minItems: 1
+    maxItems: 2
+
+  clock-names:
+    minItems: 1
+    maxItems: 2
+
+  "#clock-cells":
+    const: 1
+
+  reg:
+    maxItems: 1
+
+required:
+  - compatible
+  - "#clock-cells"
+  - clocks
+  - clock-names
+  - reg
+
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - google,gs101-cmu-top
+              - google,gs101-cmu-apm
+    then:
+      properties:
+        clocks:
+          items:
+            - description: External reference clock (24.576 MHz)
+
+        clock-names:
+          items:
+            - const: oscclk
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: google,gs101-cmu-misc
+
+    then:
+      properties:
+        clocks:
+          items:
+            - description: Misc bus clock (from CMU_TOP)
+            - description: Misc sss clock (from CMU_TOP)
+
+        clock-names:
+          items:
+            - const: dout_cmu_misc_bus
+            - const: dout_cmu_misc_sss
+
+additionalProperties: false
+
+examples:
+  # Clock controller node for CMU_TOP
+  - |
+    #include <dt-bindings/clock/google,gs101.h>
+
+    cmu_top: clock-controller@1e080000 {
+        compatible = "google,gs101-cmu-top";
+        reg = <0x1e080000 0x8000>;
+        #clock-cells = <1>;
+        clocks = <&ext_24_5m>;
+        clock-names = "oscclk";
+    };
+
+...
diff --git a/include/dt-bindings/clock/google,gs101.h b/include/dt-bindings/clock/google,gs101.h
new file mode 100644
index 000000000000..5d2c2d907a7b
--- /dev/null
+++ b/include/dt-bindings/clock/google,gs101.h
@@ -0,0 +1,392 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/*
+ * Copyright (C) 2023 Linaro Ltd.
+ * Author: Peter Griffin <peter.griffin@linaro.org>
+ *
+ * Device Tree binding constants for Google gs101 clock controller.
+ */
+
+#ifndef _DT_BINDINGS_CLOCK_GOOGLE_GS101_H
+#define _DT_BINDINGS_CLOCK_GOOGLE_GS101_H
+
+/* CMU_TOP PLL */
+#define CLK_FOUT_SHARED0_PLL		1
+#define CLK_FOUT_SHARED1_PLL		2
+#define CLK_FOUT_SHARED2_PLL		3
+#define CLK_FOUT_SHARED3_PLL		4
+#define CLK_FOUT_SPARE_PLL		5
+
+/* CMU_TOP MUX */
+#define CLK_MOUT_PLL_SHARED0		6
+#define CLK_MOUT_PLL_SHARED1		7
+#define CLK_MOUT_PLL_SHARED2		8
+#define CLK_MOUT_PLL_SHARED3		9
+#define CLK_MOUT_PLL_SPARE		10
+#define CLK_MOUT_CMU_BO_BUS		11
+#define CLK_MOUT_CMU_BUS0_BUS		12
+#define CLK_MOUT_CMU_BUS1_BUS		13
+#define CLK_MOUT_CMU_BUS2_BUS		14
+#define CLK_MOUT_CMU_CIS_CLK0		15
+#define CLK_MOUT_CMU_CIS_CLK1		16
+#define CLK_MOUT_CMU_CIS_CLK2		17
+#define CLK_MOUT_CMU_CIS_CLK3		18
+#define CLK_MOUT_CMU_CIS_CLK4		19
+#define CLK_MOUT_CMU_CIS_CLK5		20
+#define CLK_MOUT_CMU_CIS_CLK6		21
+#define CLK_MOUT_CMU_CIS_CLK7		22
+#define CLK_MOUT_CMU_CMU_BOOST		23
+#define CLK_MOUT_CMU_BOOST_OPTION1	24
+#define CLK_MOUT_CMU_CORE_BUS		25
+#define CLK_MOUT_CMU_CPUCL0_DBG		26
+#define CLK_MOUT_CMU_CPUCL0_SWITCH	27
+#define CLK_MOUT_CMU_CPUCL1_SWITCH	28
+#define CLK_MOUT_CMU_CPUCL2_SWITCH	29
+#define CLK_MOUT_CMU_CSIS_BUS		30
+#define CLK_MOUT_CMU_DISP_BUS		31
+#define CLK_MOUT_CMU_DNS_BUS		32
+#define CLK_MOUT_CMU_DPU_BUS		33
+#define CLK_MOUT_CMU_EH_BUS		34
+#define CLK_MOUT_CMU_G2D_G2D		35
+#define CLK_MOUT_CMU_G2D_MSCL		36
+#define CLK_MOUT_CMU_G3AA_G3AA		37
+#define CLK_MOUT_CMU_G3D_BUSD		38
+#define CLK_MOUT_CMU_G3D_GLB		39
+#define CLK_MOUT_CMU_G3D_SWITCH		40
+#define CLK_MOUT_CMU_GDC_GDC0		41
+#define CLK_MOUT_CMU_GDC_GDC1		42
+#define CLK_MOUT_CMU_GDC_SCSC		43
+#define CLK_MOUT_CMU_HPM		44
+#define CLK_MOUT_CMU_HSI0_BUS		45
+#define CLK_MOUT_CMU_HSI0_DPGTC		46
+#define CLK_MOUT_CMU_HSI0_USB31DRD	47
+#define CLK_MOUT_CMU_HSI0_USBDPDGB	48
+#define CLK_MOUT_CMU_HSI1_BUS		49
+#define CLK_MOUT_CMU_HSI1_PCIE		50
+#define CLK_MOUT_CMU_HSI2_BUS		51
+#define CLK_MOUT_CMU_HSI2_MMC_CARD	52
+#define CLK_MOUT_CMU_HSI2_PCIE		53
+#define CLK_MOUT_CMU_HSI2_UFS_EMBD	54
+#define CLK_MOUT_CMU_IPP_BUS		55
+#define CLK_MOUT_CMU_ITP_BUS		56
+#define CLK_MOUT_CMU_MCSC_ITSC		57
+#define CLK_MOUT_CMU_MCSC_MCSC		58
+#define CLK_MOUT_CMU_MFC_MFC		59
+#define CLK_MOUT_CMU_MIF_BUSP		60
+#define CLK_MOUT_CMU_MIF_SWITCH		61
+#define CLK_MOUT_CMU_MISC_BUS		62
+#define CLK_MOUT_CMU_MISC_SSS		63
+#define CLK_MOUT_CMU_PDP_BUS		64
+#define CLK_MOUT_CMU_PDP_VRA		65
+#define CLK_MOUT_CMU_PERIC0_BUS		66
+#define CLK_MOUT_CMU_PERIC0_IP		67
+#define CLK_MOUT_CMU_PERIC1_BUS		68
+#define CLK_MOUT_CMU_PERIC1_IP		69
+#define CLK_MOUT_CMU_TNR_BUS		70
+#define CLK_MOUT_CMU_TOP_BOOST_OPTION1	71
+#define CLK_MOUT_CMU_TOP_CMUREF		72
+#define CLK_MOUT_CMU_TPU_BUS		73
+#define CLK_MOUT_CMU_TPU_TPU		74
+#define CLK_MOUT_CMU_TPU_TPUCTL		75
+#define CLK_MOUT_CMU_TPU_UART		76
+#define CLK_MOUT_CMU_CMUREF		77
+
+/* CMU_TOP Dividers */
+#define CLK_DOUT_CMU_BO_BUS		78
+#define CLK_DOUT_CMU_BUS0_BUS		79
+#define CLK_DOUT_CMU_BUS1_BUS		80
+#define CLK_DOUT_CMU_BUS2_BUS		81
+#define CLK_DOUT_CMU_CIS_CLK0		82
+#define CLK_DOUT_CMU_CIS_CLK1		83
+#define CLK_DOUT_CMU_CIS_CLK2		84
+#define CLK_DOUT_CMU_CIS_CLK3		85
+#define CLK_DOUT_CMU_CIS_CLK4		86
+#define CLK_DOUT_CMU_CIS_CLK5		87
+#define CLK_DOUT_CMU_CIS_CLK6		88
+#define CLK_DOUT_CMU_CIS_CLK7		89
+#define CLK_DOUT_CMU_CORE_BUS		90
+#define CLK_DOUT_CMU_CPUCL0_DBG		91
+#define CLK_DOUT_CMU_CPUCL0_SWITCH	92
+#define CLK_DOUT_CMU_CPUCL1_SWITCH	93
+#define CLK_DOUT_CMU_CPUCL2_SWITCH	94
+#define CLK_DOUT_CMU_CSIS_BUS		95
+#define CLK_DOUT_CMU_DISP_BUS		96
+#define CLK_DOUT_CMU_DNS_BUS		97
+#define CLK_DOUT_CMU_DPU_BUS		98
+#define CLK_DOUT_CMU_EH_BUS		99
+#define CLK_DOUT_CMU_G2D_G2D		100
+#define CLK_DOUT_CMU_G2D_MSCL		101
+#define CLK_DOUT_CMU_G3AA_G3AA		102
+#define CLK_DOUT_CMU_G3D_BUSD		103
+#define CLK_DOUT_CMU_G3D_GLB		104
+#define CLK_DOUT_CMU_G3D_SWITCH		105
+#define CLK_DOUT_CMU_GDC_GDC0		106
+#define CLK_DOUT_CMU_GDC_GDC1		107
+#define CLK_DOUT_CMU_GDC_SCSC		108
+#define CLK_DOUT_CMU_CMU_HPM		109
+#define CLK_DOUT_CMU_HSI0_BUS		110
+#define CLK_DOUT_CMU_HSI0_DPGTC		111
+#define CLK_DOUT_CMU_HSI0_USB31DRD	112
+#define CLK_DOUT_CMU_HSI0_USBDPDBG	113
+#define CLK_DOUT_CMU_HSI1_BUS		114
+#define CLK_DOUT_CMU_HSI1_PCIE		115
+#define CLK_DOUT_CMU_HSI2_BUS		116
+#define CLK_DOUT_CMU_HSI2_MMC_CARD	117
+#define CLK_DOUT_CMU_HSI2_PCIE		118
+#define CLK_DOUT_CMU_HSI2_UFS_EMBD	119
+#define CLK_DOUT_CMU_IPP_BUS		120
+#define CLK_DOUT_CMU_ITP_BUS		121
+#define CLK_DOUT_CMU_MCSC_ITSC		122
+#define CLK_DOUT_CMU_MCSC_MCSC		123
+#define CLK_DOUT_CMU_MFC_MFC		124
+#define CLK_DOUT_CMU_MIF_BUSP		125
+#define CLK_DOUT_CMU_MISC_BUS		126
+#define CLK_DOUT_CMU_MISC_SSS		127
+#define CLK_DOUT_CMU_OTP		128
+#define CLK_DOUT_CMU_PDP_BUS		129
+#define CLK_DOUT_CMU_PDP_VRA		130
+#define CLK_DOUT_CMU_PERIC0_BUS		131
+#define CLK_DOUT_CMU_PERIC0_IP		132
+#define CLK_DOUT_CMU_PERIC1_BUS		133
+#define CLK_DOUT_CMU_PERIC1_IP		134
+#define CLK_DOUT_CMU_TNR_BUS		135
+#define CLK_DOUT_CMU_TPU_BUS		136
+#define CLK_DOUT_CMU_TPU_TPU		137
+#define CLK_DOUT_CMU_TPU_TPUCTL		138
+#define CLK_DOUT_CMU_TPU_UART		139
+#define CLK_DOUT_CMU_CMU_BOOST		140
+#define CLK_DOUT_CMU_CMU_CMUREF		141
+#define CLK_DOUT_CMU_SHARED0_DIV2	142
+#define CLK_DOUT_CMU_SHARED0_DIV3	143
+#define CLK_DOUT_CMU_SHARED0_DIV4	144
+#define CLK_DOUT_CMU_SHARED0_DIV5	145
+#define CLK_DOUT_CMU_SHARED1_DIV2	146
+#define CLK_DOUT_CMU_SHARED1_DIV3	147
+#define CLK_DOUT_CMU_SHARED1_DIV4	148
+#define CLK_DOUT_CMU_SHARED2_DIV2	149
+#define CLK_DOUT_CMU_SHARED3_DIV2	150
+
+/* CMU_TOP Gates */
+#define CLK_GOUT_BUS0_BOOST		151
+#define CLK_GOUT_BUS1_BOOST		152
+#define CLK_GOUT_BUS2_BOOST		153
+#define CLK_GOUT_CORE_BOOST		154
+#define CLK_GOUT_CPUCL0_BOOST		155
+#define CLK_GOUT_CPUCL1_BOOST		156
+#define CLK_GOUT_CPUCL2_BOOST		157
+#define CLK_GOUT_MIF_BOOST		158
+#define CLK_GOUT_MIF_SWITCH		159
+#define CLK_GOUT_BO_BUS			160
+#define CLK_GOUT_BUS0_BUS		161
+#define CLK_GOUT_BUS1_BUS		162
+#define CLK_GOUT_BUS2_BUS		163
+#define CLK_GOUT_CIS_CLK0		164
+#define CLK_GOUT_CIS_CLK1		165
+#define CLK_GOUT_CIS_CLK2		167
+#define CLK_GOUT_CIS_CLK3		168
+#define CLK_GOUT_CIS_CLK4		169
+#define CLK_GOUT_CIS_CLK5		170
+#define CLK_GOUT_CIS_CLK6		171
+#define CLK_GOUT_CIS_CLK7		172
+#define CLK_GOUT_CMU_BOOST		173
+#define CLK_GOUT_CORE_BUS		174
+#define CLK_GOUT_CPUCL0_DBG		175
+#define CLK_GOUT_CPUCL0_SWITCH		176
+#define CLK_GOUT_CPUCL1_SWITCH		177
+#define CLK_GOUT_CPUCL2_SWITCH		178
+#define CLK_GOUT_CSIS_BUS		179
+#define CLK_GOUT_DISP_BUS		180
+#define CLK_GOUT_DNS_BUS		181
+#define CLK_GOUT_DPU_BUS		182
+#define CLK_GOUT_EH_BUS			183
+#define CLK_GOUT_G2D_G2D		184
+#define CLK_GOUT_G2D_MSCL		185
+#define CLK_GOUT_G3AA_G3AA		186
+#define CLK_GOUT_G3D_BUSD		187
+#define CLK_GOUT_G3D_GLB		188
+#define CLK_GOUT_G3D_SWITCH		189
+#define CLK_GOUT_GDC_GDC0		190
+#define CLK_GOUT_GDC_GDC1		191
+#define CLK_GOUT_GDC_SCSC		192
+#define CLK_GOUT_CMU_HPM		193
+#define CLK_GOUT_HSI0_BUS		194
+#define CLK_GOUT_HSI0_DPGTC		195
+#define CLK_GOUT_HSI0_USB31DRD		196
+#define CLK_GOUT_HSI0_USBDPDGB		197
+#define CLK_GOUT_HSI1_BUS		198
+#define CLK_GOUT_HSI1_PCIE		199
+#define CLK_GOUT_HSI2_BUS		200
+#define CLK_GOUT_HSI2_MMC_CARD		201
+#define CLK_GOUT_HSI2_PCIE		202
+#define CLK_GOUT_HSI2_UFS_EMBD		203
+#define CLK_GOUT_IPP_BUS		204
+#define CLK_GOUT_ITP_BUS		205
+#define CLK_GOUT_MCSC_ITSC		206
+#define CLK_GOUT_MCSC_MCSC		207
+#define CLK_GOUT_MFC_MFC		208
+#define CLK_GOUT_MIF_BUSP		209
+#define CLK_GOUT_MISC_BUS		210
+#define CLK_GOUT_MISC_SSS		211
+#define CLK_GOUT_PDP_BUS		212
+#define CLK_GOUT_PDP_VRA		213
+#define CLK_GOUT_G3AA			214
+#define CLK_GOUT_PERIC0_BUS		215
+#define CLK_GOUT_PERIC0_IP		216
+#define CLK_GOUT_PERIC1_BUS		217
+#define CLK_GOUT_PERIC1_IP		218
+#define CLK_GOUT_TNR_BUS		219
+#define CLK_GOUT_TOP_CMUREF		220
+#define CLK_GOUT_TPU_BUS		221
+#define CLK_GOUT_TPU_TPU		222
+#define CLK_GOUT_TPU_TPUCTL		223
+#define CLK_GOUT_TPU_UART		224
+
+/* CMU_APM */
+#define CLK_MOUT_APM_FUNC				1
+#define CLK_MOUT_APM_FUNCSRC				2
+#define CLK_DOUT_APM_BOOST				3
+#define CLK_DOUT_APM_USI0_UART				4
+#define CLK_DOUT_APM_USI0_USI				5
+#define CLK_DOUT_APM_USI1_UART				6
+#define CLK_GOUT_APM_APM_CMU_APM_PCLK			7
+#define CLK_GOUT_BUS0_BOOST_OPTION1			8
+#define CLK_GOUT_CMU_BOOST_OPTION1			9
+#define CLK_GOUT_CORE_BOOST_OPTION1			10
+#define CLK_GOUT_APM_FUNC				11
+#define CLK_GOUT_APM_APBIF_GPIO_ALIVE_PCLK		12
+#define CLK_GOUT_APM_APBIF_GPIO_FAR_ALIVE_PCLK		13
+#define CLK_GOUT_APM_APBIF_PMU_ALIVE_PCLK		14
+#define CLK_GOUT_APM_APBIF_RTC_PCLK			15
+#define CLK_GOUT_APM_APBIF_TRTC_PCLK			16
+#define CLK_GOUT_APM_APM_USI0_UART_IPCLK		17
+#define CLK_GOUT_APM_APM_USI0_UART_PCLK			18
+#define CLK_GOUT_APM_APM_USI0_USI_IPCLK			19
+#define CLK_GOUT_APM_APM_USI0_USI_PCLK			20
+#define CLK_GOUT_APM_APM_USI1_UART_IPCLK		21
+#define CLK_GOUT_APM_APM_USI1_UART_PCLK			22
+#define CLK_GOUT_APM_D_TZPC_APM_PCLK			23
+#define CLK_GOUT_APM_GPC_APM_PCLK			24
+#define CLK_GOUT_APM_GREBEINTEGRATION_HCLK		25
+#define CLK_GOUT_APM_INTMEM_ACLK			26
+#define CLK_GOUT_APM_INTMEM_PCLK			27
+#define CLK_GOUT_APM_LHM_AXI_G_SWD_I_CLK		28
+#define CLK_GOUT_APM_LHM_AXI_P_AOCAPM_I_CLK		29
+#define CLK_GOUT_APM_LHM_AXI_P_APM_I_CLK		30
+#define CLK_GOUT_APM_LHS_AXI_D_APM_I_CLK		31
+#define CLK_GOUT_APM_LHS_AXI_G_DBGCORE_I_CLK		32
+#define CLK_GOUT_APM_LHS_AXI_G_SCAN2DRAM_I_CLK		33
+#define CLK_GOUT_APM_MAILBOX_APM_AOC_PCLK		34
+#define CLK_GOUT_APM_MAILBOX_APM_AP_PCLK		35
+#define CLK_GOUT_APM_MAILBOX_APM_GSA_PCLK		36
+#define CLK_GOUT_APM_MAILBOX_APM_SWD_PCLK		37
+#define CLK_GOUT_APM_MAILBOX_APM_TPU_PCLK		38
+#define CLK_GOUT_APM_MAILBOX_AP_AOC_PCLK		39
+#define CLK_GOUT_APM_MAILBOX_AP_DBGCORE_PCLK		40
+#define CLK_GOUT_APM_PMU_INTR_GEN_PCLK			41
+#define CLK_GOUT_APM_ROM_CRC32_HOST_ACLK		42
+#define CLK_GOUT_APM_ROM_CRC32_HOST_PCLK		43
+#define CLK_GOUT_APM_CLK_APM_BUS_CLK			44
+#define CLK_GOUT_APM_CLK_APM_USI0_UART_CLK		45
+#define CLK_GOUT_APM_CLK_APM_USI0_USI_CLK		46
+#define CLK_GOUT_APM_CLK_APM_USI1_UART_CLK		47
+#define CLK_GOUT_APM_SPEEDY_APM_PCLK			48
+#define CLK_GOUT_APM_SPEEDY_SUB_APM_PCLK		49
+#define CLK_GOUT_APM_SSMT_D_APM_ACLK			50
+#define CLK_GOUT_APM_SSMT_D_APM_PCLK			51
+#define CLK_GOUT_APM_SSMT_G_DBGCORE_ACLK		52
+#define CLK_GOUT_APM_SSMT_G_DBGCORE_PCLK		53
+#define CLK_GOUT_APM_SS_DBGCORE_SS_DBGCORE_HCLK		54
+#define CLK_GOUT_APM_SYSMMU_D_APM_CLK_S2		55
+#define CLK_GOUT_APM_SYSREG_APM_PCLK			56
+#define CLK_GOUT_APM_UASC_APM_ACLK			57
+#define CLK_GOUT_APM_UASC_APM_PCLK			58
+#define CLK_GOUT_APM_UASC_DBGCORE_ACLK			59
+#define CLK_GOUT_APM_UASC_DBGCORE_PCLK			60
+#define CLK_GOUT_APM_UASC_G_SWD_ACLK			61
+#define CLK_GOUT_APM_UASC_G_SWD_PCLK			62
+#define CLK_GOUT_APM_UASC_P_AOCAPM_ACLK			63
+#define CLK_GOUT_APM_UASC_P_AOCAPM_PCLK			64
+#define CLK_GOUT_APM_UASC_P_APM_ACLK			65
+#define CLK_GOUT_APM_UASC_P_APM_PCLK			66
+#define CLK_GOUT_APM_WDT_APM_PCLK			67
+#define CLK_GOUT_APM_XIU_DP_APM_ACLK			68
+#define CLK_APM_PLL_DIV2_APM				69
+#define CLK_APM_PLL_DIV4_APM				70
+#define CLK_APM_PLL_DIV16_APM				71
+
+/* CMU_MISC */
+#define CLK_MOUT_MISC_BUS_USER				1
+#define CLK_MOUT_MISC_SSS_USER				2
+#define CLK_MOUT_MISC_GIC				3
+#define CLK_DOUT_MISC_BUSP				4
+#define CLK_DOUT_MISC_GIC				5
+#define CLK_GOUT_MISC_MISC_CMU_MISC_PCLK		6
+#define CLK_GOUT_MISC_OTP_CON_BIRA_I_OSCCLK		7
+#define CLK_GOUT_MISC_OTP_CON_BISR_I_OSCCLK		8
+#define CLK_GOUT_MISC_OTP_CON_TOP_I_OSCCLK		9
+#define CLK_GOUT_MISC_CLK_MISC_OSCCLK_CLK		10
+#define CLK_GOUT_MISC_ADM_AHB_SSS_HCLKM			11
+#define CLK_GOUT_MISC_AD_APB_DIT_PCLKM			12
+#define CLK_GOUT_MISC_AD_APB_PUF_PCLKM			13
+#define CLK_GOUT_MISC_DIT_ICLKL2A			14
+#define CLK_GOUT_MISC_D_TZPC_MISC_PCLK			15
+#define CLK_GOUT_MISC_GIC_GICCLK			16
+#define CLK_GOUT_MISC_GPC_MISC_PCLK			17
+#define CLK_GOUT_MISC_LHM_AST_ICC_CPUGIC_I_CLK		18
+#define CLK_GOUT_MISC_LHM_AXI_D_SSS_I_CLK		19
+#define CLK_GOUT_MISC_LHM_AXI_P_GIC_I_CLK		20
+#define CLK_GOUT_MISC_LHM_AXI_P_MISC_I_CLK		21
+#define CLK_GOUT_MISC_LHS_ACEL_D_MISC_I_CLK		22
+#define CLK_GOUT_MISC_LHS_AST_IRI_GICCPU_I_CLK		23
+#define CLK_GOUT_MISC_LHS_AXI_D_SSS_I_CLK		24
+#define CLK_GOUT_MISC_MCT_PCLK				25
+#define CLK_GOUT_MISC_OTP_CON_BIRA_PCLK			26
+#define CLK_GOUT_MISC_OTP_CON_BISR_PCLK			27
+#define CLK_GOUT_MISC_OTP_CON_TOP_PCLK			28
+#define CLK_GOUT_MISC_PDMA_ACLK				29
+#define CLK_GOUT_MISC_PPMU_DMA_ACLK			30
+#define CLK_GOUT_MISC_PPMU_MISC_ACLK			31
+#define CLK_GOUT_MISC_PPMU_MISC_PCLK			32
+#define CLK_GOUT_MISC_PUF_I_CLK				33
+#define CLK_GOUT_MISC_QE_DIT_ACLK			34
+#define CLK_GOUT_MISC_QE_DIT_PCLK			35
+#define CLK_GOUT_MISC_QE_PDMA_ACLK			36
+#define CLK_GOUT_MISC_QE_PDMA_PCLK			37
+#define CLK_GOUT_MISC_QE_PPMU_DMA_ACLK			38
+#define CLK_GOUT_MISC_QE_PPMU_DMA_PCLK			39
+#define CLK_GOUT_MISC_QE_RTIC_ACLK			40
+#define CLK_GOUT_MISC_QE_RTIC_PCLK			41
+#define CLK_GOUT_MISC_QE_SPDMA_ACLK			42
+#define CLK_GOUT_MISC_QE_SPDMA_PCLK			43
+#define CLK_GOUT_MISC_QE_SSS_ACLK			44
+#define CLK_GOUT_MISC_QE_SSS_PCLK			45
+#define CLK_GOUT_MISC_CLK_MISC_BUSD_CLK			46
+#define CLK_GOUT_MISC_CLK_MISC_BUSP_CLK			47
+#define CLK_GOUT_MISC_CLK_MISC_GIC_CLK			48
+#define CLK_GOUT_MISC_CLK_MISC_SSS_CLK			49
+#define CLK_GOUT_MISC_RTIC_I_ACLK			50
+#define CLK_GOUT_MISC_RTIC_I_PCLK			51
+#define CLK_GOUT_MISC_SPDMA_ACLK			52
+#define CLK_GOUT_MISC_SSMT_DIT_ACLK			53
+#define CLK_GOUT_MISC_SSMT_DIT_PCLK			54
+#define CLK_GOUT_MISC_SSMT_PDMA_ACLK			55
+#define CLK_GOUT_MISC_SSMT_PDMA_PCLK			56
+#define CLK_GOUT_MISC_SSMT_PPMU_DMA_ACLK		57
+#define CLK_GOUT_MISC_SSMT_PPMU_DMA_PCLK		58
+#define CLK_GOUT_MISC_SSMT_RTIC_ACLK			59
+#define CLK_GOUT_MISC_SSMT_RTIC_PCLK			60
+#define CLK_GOUT_MISC_SSMT_SPDMA_ACLK			61
+#define CLK_GOUT_MISC_SSMT_SPDMA_PCLK			62
+#define CLK_GOUT_MISC_SSMT_SSS_ACLK			63
+#define CLK_GOUT_MISC_SSMT_SSS_PCLK			64
+#define CLK_GOUT_MISC_SSS_I_ACLK			65
+#define CLK_GOUT_MISC_SSS_I_PCLK			66
+#define CLK_GOUT_MISC_SYSMMU_MISC_CLK_S2		67
+#define CLK_GOUT_MISC_SYSMMU_SSS_CLK_S1			68
+#define CLK_GOUT_MISC_SYSREG_MISC_PCLK			69
+#define CLK_GOUT_MISC_TMU_SUB_PCLK			70
+#define CLK_GOUT_MISC_TMU_TOP_PCLK			71
+#define CLK_GOUT_MISC_WDT_CLUSTER0_PCLK			72
+#define CLK_GOUT_MISC_WDT_CLUSTER1_PCLK			73
+#define CLK_GOUT_MISC_XIU_D_MISC_ACLK			74
+
+#endif /* _DT_BINDINGS_CLOCK_GOOGLE_GS101_H */
-- 
cgit v1.2.3


From 44a88fa45665318473bfdbb832eba1da2d0a3740 Mon Sep 17 00:00:00 2001
From: Connor Abbott <cwabbott0@gmail.com>
Date: Thu, 7 Dec 2023 21:30:48 +0000
Subject: drm/msm: Add param for the highest bank bit

This parameter is programmed by the kernel and influences the tiling
layout of images. Exposing it to userspace will allow it to tile/untile
images correctly without guessing what value the kernel programmed, and
allow us to change it in the future without breaking userspace.

Signed-off-by: Connor Abbott <cwabbott0@gmail.com>
Patchwork: https://patchwork.freedesktop.org/patch/571181/
Signed-off-by: Rob Clark <robdclark@chromium.org>
---
 drivers/gpu/drm/msm/adreno/adreno_gpu.c | 3 +++
 include/uapi/drm/msm_drm.h              | 1 +
 2 files changed, 4 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 3fe9fd240cc7..074fb498706f 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -373,6 +373,9 @@ int adreno_get_param(struct msm_gpu *gpu, struct msm_file_private *ctx,
 			return -EINVAL;
 		*value = ctx->aspace->va_size;
 		return 0;
+	case MSM_PARAM_HIGHEST_BANK_BIT:
+		*value = adreno_gpu->ubwc_config.highest_bank_bit;
+		return 0;
 	default:
 		DBG("%s: invalid param: %u", gpu->name, param);
 		return -EINVAL;
diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h
index 6f2a7ad04aa4..d8a6b3472760 100644
--- a/include/uapi/drm/msm_drm.h
+++ b/include/uapi/drm/msm_drm.h
@@ -86,6 +86,7 @@ struct drm_msm_timespec {
 #define MSM_PARAM_CMDLINE    0x0d  /* WO: override for task cmdline */
 #define MSM_PARAM_VA_START   0x0e  /* RO: start of valid GPU iova range */
 #define MSM_PARAM_VA_SIZE    0x0f  /* RO: size of valid GPU iova range (bytes) */
+#define MSM_PARAM_HIGHEST_BANK_BIT 0x10 /* RO */
 
 /* For backwards compat.  The original support for preemption was based on
  * a single ring per priority level so # of priority levels equals the #
-- 
cgit v1.2.3


From 05d249352f1ae909230c230767ca8f4e9fdf8e7b Mon Sep 17 00:00:00 2001
From: Rob Clark <robdclark@chromium.org>
Date: Mon, 20 Nov 2023 16:38:50 -0800
Subject: drm/exec: Pass in initial # of objects
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In cases where the # is known ahead of time, it is silly to do the table
resize dance.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Christian König <christian.koenig@amd.com>
Patchwork: https://patchwork.freedesktop.org/patch/568338/
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c |  8 ++++----
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c           |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c          |  4 ++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c          |  4 ++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c          |  4 ++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c     |  4 ++--
 drivers/gpu/drm/amd/amdkfd/kfd_svm.c             |  2 +-
 drivers/gpu/drm/drm_exec.c                       | 13 ++++++++++---
 drivers/gpu/drm/drm_gpuvm.c                      |  4 ++--
 drivers/gpu/drm/imagination/pvr_job.c            |  2 +-
 drivers/gpu/drm/nouveau/nouveau_uvmm.c           |  2 +-
 drivers/gpu/drm/tests/drm_exec_test.c            | 16 ++++++++--------
 include/drm/drm_exec.h                           |  2 +-
 13 files changed, 37 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 41fbc4fd0fac..0bd3c4a6267a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1137,7 +1137,7 @@ static int reserve_bo_and_vm(struct kgd_mem *mem,
 
 	ctx->n_vms = 1;
 	ctx->sync = &mem->sync;
-	drm_exec_init(&ctx->exec, DRM_EXEC_INTERRUPTIBLE_WAIT);
+	drm_exec_init(&ctx->exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0);
 	drm_exec_until_all_locked(&ctx->exec) {
 		ret = amdgpu_vm_lock_pd(vm, &ctx->exec, 2);
 		drm_exec_retry_on_contention(&ctx->exec);
@@ -1176,7 +1176,7 @@ static int reserve_bo_and_cond_vms(struct kgd_mem *mem,
 	int ret;
 
 	ctx->sync = &mem->sync;
-	drm_exec_init(&ctx->exec, DRM_EXEC_INTERRUPTIBLE_WAIT);
+	drm_exec_init(&ctx->exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0);
 	drm_exec_until_all_locked(&ctx->exec) {
 		ctx->n_vms = 0;
 		list_for_each_entry(entry, &mem->attachments, list) {
@@ -2552,7 +2552,7 @@ static int validate_invalid_user_pages(struct amdkfd_process_info *process_info)
 
 	amdgpu_sync_create(&sync);
 
-	drm_exec_init(&exec, 0);
+	drm_exec_init(&exec, 0, 0);
 	/* Reserve all BOs and page tables for validation */
 	drm_exec_until_all_locked(&exec) {
 		/* Reserve all the page directories */
@@ -2793,7 +2793,7 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef)
 
 	mutex_lock(&process_info->lock);
 
-	drm_exec_init(&exec, 0);
+	drm_exec_init(&exec, 0, 0);
 	drm_exec_until_all_locked(&exec) {
 		list_for_each_entry(peer_vm, &process_info->vm_list_head,
 				    vm_list_node) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index e50be6500030..440e9a6786fc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -66,7 +66,7 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p,
 
 	amdgpu_sync_create(&p->sync);
 	drm_exec_init(&p->exec, DRM_EXEC_INTERRUPTIBLE_WAIT |
-		      DRM_EXEC_IGNORE_DUPLICATES);
+		      DRM_EXEC_IGNORE_DUPLICATES, 0);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c
index 720011019741..796fa6f1420b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c
@@ -70,7 +70,7 @@ int amdgpu_map_static_csa(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	struct drm_exec exec;
 	int r;
 
-	drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT);
+	drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0);
 	drm_exec_until_all_locked(&exec) {
 		r = amdgpu_vm_lock_pd(vm, &exec, 0);
 		if (likely(!r))
@@ -110,7 +110,7 @@ int amdgpu_unmap_static_csa(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	struct drm_exec exec;
 	int r;
 
-	drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT);
+	drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0);
 	drm_exec_until_all_locked(&exec) {
 		r = amdgpu_vm_lock_pd(vm, &exec, 0);
 		if (likely(!r))
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 84beeaa4d21c..49a5f1c73b3e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -203,7 +203,7 @@ static void amdgpu_gem_object_close(struct drm_gem_object *obj,
 	struct drm_exec exec;
 	long r;
 
-	drm_exec_init(&exec, DRM_EXEC_IGNORE_DUPLICATES);
+	drm_exec_init(&exec, DRM_EXEC_IGNORE_DUPLICATES, 0);
 	drm_exec_until_all_locked(&exec) {
 		r = drm_exec_prepare_obj(&exec, &bo->tbo.base, 1);
 		drm_exec_retry_on_contention(&exec);
@@ -739,7 +739,7 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
 	}
 
 	drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT |
-		      DRM_EXEC_IGNORE_DUPLICATES);
+		      DRM_EXEC_IGNORE_DUPLICATES, 0);
 	drm_exec_until_all_locked(&exec) {
 		if (gobj) {
 			r = drm_exec_lock_obj(&exec, gobj);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
index 9ddbf1494326..abd0b9763904 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
@@ -1122,7 +1122,7 @@ int amdgpu_mes_ctx_map_meta_data(struct amdgpu_device *adev,
 
 	amdgpu_sync_create(&sync);
 
-	drm_exec_init(&exec, 0);
+	drm_exec_init(&exec, 0, 0);
 	drm_exec_until_all_locked(&exec) {
 		r = drm_exec_lock_obj(&exec,
 				      &ctx_data->meta_data_obj->tbo.base);
@@ -1193,7 +1193,7 @@ int amdgpu_mes_ctx_unmap_meta_data(struct amdgpu_device *adev,
 	struct drm_exec exec;
 	long r;
 
-	drm_exec_init(&exec, 0);
+	drm_exec_init(&exec, 0, 0);
 	drm_exec_until_all_locked(&exec) {
 		r = drm_exec_lock_obj(&exec,
 				      &ctx_data->meta_data_obj->tbo.base);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c
index ca45ba8ac171..bfbf59326ee1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c
@@ -86,7 +86,7 @@ static int map_ring_data(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 
 	amdgpu_sync_create(&sync);
 
-	drm_exec_init(&exec, 0);
+	drm_exec_init(&exec, 0, 0);
 	drm_exec_until_all_locked(&exec) {
 		r = drm_exec_lock_obj(&exec, &bo->tbo.base);
 		drm_exec_retry_on_contention(&exec);
@@ -149,7 +149,7 @@ static int unmap_ring_data(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	struct drm_exec exec;
 	long r;
 
-	drm_exec_init(&exec, 0);
+	drm_exec_init(&exec, 0, 0);
 	drm_exec_until_all_locked(&exec) {
 		r = drm_exec_lock_obj(&exec, &bo->tbo.base);
 		drm_exec_retry_on_contention(&exec);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index f2f3c338fd94..76d9f14ccc7c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -1529,7 +1529,7 @@ static int svm_range_reserve_bos(struct svm_validate_context *ctx, bool intr)
 	uint32_t gpuidx;
 	int r;
 
-	drm_exec_init(&ctx->exec, intr ? DRM_EXEC_INTERRUPTIBLE_WAIT: 0);
+	drm_exec_init(&ctx->exec, intr ? DRM_EXEC_INTERRUPTIBLE_WAIT: 0, 0);
 	drm_exec_until_all_locked(&ctx->exec) {
 		for_each_set_bit(gpuidx, ctx->bitmap, MAX_GPU_INSTANCE) {
 			pdd = kfd_process_device_from_gpuidx(ctx->process, gpuidx);
diff --git a/drivers/gpu/drm/drm_exec.c b/drivers/gpu/drm/drm_exec.c
index 5d2809de4517..48ee851b61d9 100644
--- a/drivers/gpu/drm/drm_exec.c
+++ b/drivers/gpu/drm/drm_exec.c
@@ -69,16 +69,23 @@ static void drm_exec_unlock_all(struct drm_exec *exec)
  * drm_exec_init - initialize a drm_exec object
  * @exec: the drm_exec object to initialize
  * @flags: controls locking behavior, see DRM_EXEC_* defines
+ * @nr: the initial # of objects
  *
  * Initialize the object and make sure that we can track locked objects.
+ *
+ * If nr is non-zero then it is used as the initial objects table size.
+ * In either case, the table will grow (be re-allocated) on demand.
  */
-void drm_exec_init(struct drm_exec *exec, uint32_t flags)
+void drm_exec_init(struct drm_exec *exec, uint32_t flags, unsigned nr)
 {
+	if (!nr)
+		nr = PAGE_SIZE / sizeof(void *);
+
 	exec->flags = flags;
-	exec->objects = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	exec->objects = kvmalloc_array(nr, sizeof(void *), GFP_KERNEL);
 
 	/* If allocation here fails, just delay that till the first use */
-	exec->max_objects = exec->objects ? PAGE_SIZE / sizeof(void *) : 0;
+	exec->max_objects = exec->objects ? nr : 0;
 	exec->num_objects = 0;
 	exec->contended = DRM_EXEC_DUMMY;
 	exec->prelocked = NULL;
diff --git a/drivers/gpu/drm/drm_gpuvm.c b/drivers/gpu/drm/drm_gpuvm.c
index 9c0922c1a5a2..dc8edca61764 100644
--- a/drivers/gpu/drm/drm_gpuvm.c
+++ b/drivers/gpu/drm/drm_gpuvm.c
@@ -1250,7 +1250,7 @@ drm_gpuvm_exec_lock(struct drm_gpuvm_exec *vm_exec)
 	unsigned int num_fences = vm_exec->num_fences;
 	int ret;
 
-	drm_exec_init(exec, vm_exec->flags);
+	drm_exec_init(exec, vm_exec->flags, 0);
 
 	drm_exec_until_all_locked(exec) {
 		ret = drm_gpuvm_prepare_vm(gpuvm, exec, num_fences);
@@ -1341,7 +1341,7 @@ drm_gpuvm_exec_lock_range(struct drm_gpuvm_exec *vm_exec,
 	struct drm_exec *exec = &vm_exec->exec;
 	int ret;
 
-	drm_exec_init(exec, vm_exec->flags);
+	drm_exec_init(exec, vm_exec->flags, 0);
 
 	drm_exec_until_all_locked(exec) {
 		ret = drm_gpuvm_prepare_range(gpuvm, exec, addr, range,
diff --git a/drivers/gpu/drm/imagination/pvr_job.c b/drivers/gpu/drm/imagination/pvr_job.c
index 04139da6c04d..78c2f3c6dce0 100644
--- a/drivers/gpu/drm/imagination/pvr_job.c
+++ b/drivers/gpu/drm/imagination/pvr_job.c
@@ -746,7 +746,7 @@ pvr_submit_jobs(struct pvr_device *pvr_dev, struct pvr_file *pvr_file,
 	if (err)
 		goto out_job_data_cleanup;
 
-	drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT | DRM_EXEC_IGNORE_DUPLICATES);
+	drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT | DRM_EXEC_IGNORE_DUPLICATES, 0);
 
 	xa_init_flags(&signal_array, XA_FLAGS_ALLOC);
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.c b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
index dae3baf707a0..4f223c972c6a 100644
--- a/drivers/gpu/drm/nouveau/nouveau_uvmm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
@@ -1347,7 +1347,7 @@ nouveau_uvmm_bind_job_submit(struct nouveau_job *job,
 		}
 	}
 
-	drm_exec_init(exec, vme->flags);
+	drm_exec_init(exec, vme->flags, 0);
 	drm_exec_until_all_locked(exec) {
 		ret = bind_lock_validate(job, exec, vme->num_fences);
 		drm_exec_retry_on_contention(exec);
diff --git a/drivers/gpu/drm/tests/drm_exec_test.c b/drivers/gpu/drm/tests/drm_exec_test.c
index 563949d777dd..81f928a429ba 100644
--- a/drivers/gpu/drm/tests/drm_exec_test.c
+++ b/drivers/gpu/drm/tests/drm_exec_test.c
@@ -46,7 +46,7 @@ static void sanitycheck(struct kunit *test)
 {
 	struct drm_exec exec;
 
-	drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT);
+	drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0);
 	drm_exec_fini(&exec);
 	KUNIT_SUCCEED(test);
 }
@@ -60,7 +60,7 @@ static void test_lock(struct kunit *test)
 
 	drm_gem_private_object_init(priv->drm, &gobj, PAGE_SIZE);
 
-	drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT);
+	drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0);
 	drm_exec_until_all_locked(&exec) {
 		ret = drm_exec_lock_obj(&exec, &gobj);
 		drm_exec_retry_on_contention(&exec);
@@ -80,7 +80,7 @@ static void test_lock_unlock(struct kunit *test)
 
 	drm_gem_private_object_init(priv->drm, &gobj, PAGE_SIZE);
 
-	drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT);
+	drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0);
 	drm_exec_until_all_locked(&exec) {
 		ret = drm_exec_lock_obj(&exec, &gobj);
 		drm_exec_retry_on_contention(&exec);
@@ -107,7 +107,7 @@ static void test_duplicates(struct kunit *test)
 
 	drm_gem_private_object_init(priv->drm, &gobj, PAGE_SIZE);
 
-	drm_exec_init(&exec, DRM_EXEC_IGNORE_DUPLICATES);
+	drm_exec_init(&exec, DRM_EXEC_IGNORE_DUPLICATES, 0);
 	drm_exec_until_all_locked(&exec) {
 		ret = drm_exec_lock_obj(&exec, &gobj);
 		drm_exec_retry_on_contention(&exec);
@@ -134,7 +134,7 @@ static void test_prepare(struct kunit *test)
 
 	drm_gem_private_object_init(priv->drm, &gobj, PAGE_SIZE);
 
-	drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT);
+	drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0);
 	drm_exec_until_all_locked(&exec) {
 		ret = drm_exec_prepare_obj(&exec, &gobj, 1);
 		drm_exec_retry_on_contention(&exec);
@@ -159,7 +159,7 @@ static void test_prepare_array(struct kunit *test)
 	drm_gem_private_object_init(priv->drm, &gobj1, PAGE_SIZE);
 	drm_gem_private_object_init(priv->drm, &gobj2, PAGE_SIZE);
 
-	drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT);
+	drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0);
 	drm_exec_until_all_locked(&exec)
 		ret = drm_exec_prepare_array(&exec, array, ARRAY_SIZE(array),
 					     1);
@@ -174,14 +174,14 @@ static void test_multiple_loops(struct kunit *test)
 {
 	struct drm_exec exec;
 
-	drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT);
+	drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0);
 	drm_exec_until_all_locked(&exec)
 	{
 		break;
 	}
 	drm_exec_fini(&exec);
 
-	drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT);
+	drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0);
 	drm_exec_until_all_locked(&exec)
 	{
 		break;
diff --git a/include/drm/drm_exec.h b/include/drm/drm_exec.h
index b5bf0b6da791..f1a66c048721 100644
--- a/include/drm/drm_exec.h
+++ b/include/drm/drm_exec.h
@@ -135,7 +135,7 @@ static inline bool drm_exec_is_contended(struct drm_exec *exec)
 	return !!exec->contended;
 }
 
-void drm_exec_init(struct drm_exec *exec, uint32_t flags);
+void drm_exec_init(struct drm_exec *exec, uint32_t flags, unsigned nr);
 void drm_exec_fini(struct drm_exec *exec);
 bool drm_exec_cleanup(struct drm_exec *exec);
 int drm_exec_lock_obj(struct drm_exec *exec, struct drm_gem_object *obj);
-- 
cgit v1.2.3


From 23e9f0138963ceef2a252d887534923a0502b2da Mon Sep 17 00:00:00 2001
From: Li Zhijian <lizhijian@fujitsu.com>
Date: Fri, 3 Nov 2023 11:14:50 +0800
Subject: mm/vmstat: move pgdemote_* to per-node stats

Demotion will migrate pages across nodes.  Previously, only the global
demotion statistics were accounted for.  Changed them to per-node
statistics, making it easier to observe where demotion occurs on each
node.

This will help to identify which nodes are under pressure.

This patch also make pgdemote_* behind CONFIG_NUMA_BALANCING, since
demotion is not available for !CONFIG_NUMA_BALANCING

With this patch, here is a sample where node0 node1 are DRAM,
node3 is PMEM:
Global stats:
$ grep demote /proc/vmstat
pgdemote_kswapd 254288
pgdemote_direct 113497
pgdemote_khugepaged 0

Per-node stats:
$ grep demote /sys/devices/system/node/node0/vmstat # demotion source
pgdemote_kswapd 68454
pgdemote_direct 83431
pgdemote_khugepaged 0
$ grep demote /sys/devices/system/node/node1/vmstat # demotion source
pgdemote_kswapd 185834
pgdemote_direct 30066
pgdemote_khugepaged 0
$ grep demote /sys/devices/system/node/node3/vmstat # demotion target
pgdemote_kswapd 0
pgdemote_direct 0
pgdemote_khugepaged 0

Link: https://lkml.kernel.org/r/20231103031450.1456523-1-lizhijian@fujitsu.com
Signed-off-by: Li Zhijian <lizhijian@fujitsu.com>
Acked-by: "Huang, Ying" <ying.huang@intel.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "Rafael J. Wysocki" <rafael@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mmzone.h        |  4 ++++
 include/linux/vm_event_item.h |  3 ---
 mm/vmscan.c                   | 12 ++++++++----
 mm/vmstat.c                   |  6 +++---
 4 files changed, 15 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 3c25226beeed..14faffa4354f 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -206,6 +206,10 @@ enum node_stat_item {
 #ifdef CONFIG_NUMA_BALANCING
 	PGPROMOTE_SUCCESS,	/* promote successfully */
 	PGPROMOTE_CANDIDATE,	/* candidate pages to promote */
+	/* PGDEMOTE_*: pages demoted */
+	PGDEMOTE_KSWAPD,
+	PGDEMOTE_DIRECT,
+	PGDEMOTE_KHUGEPAGED,
 #endif
 	NR_VM_NODE_STAT_ITEMS
 };
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 8abfa1240040..d1b847502f09 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -41,9 +41,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		PGSTEAL_KSWAPD,
 		PGSTEAL_DIRECT,
 		PGSTEAL_KHUGEPAGED,
-		PGDEMOTE_KSWAPD,
-		PGDEMOTE_DIRECT,
-		PGDEMOTE_KHUGEPAGED,
 		PGSCAN_KSWAPD,
 		PGSCAN_DIRECT,
 		PGSCAN_KHUGEPAGED,
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 506f8220c5fe..5dc581cac225 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -409,12 +409,14 @@ void drop_slab(void)
 
 static int reclaimer_offset(void)
 {
+#ifdef CONFIG_NUMA_BALANCING
 	BUILD_BUG_ON(PGSTEAL_DIRECT - PGSTEAL_KSWAPD !=
 			PGDEMOTE_DIRECT - PGDEMOTE_KSWAPD);
-	BUILD_BUG_ON(PGSTEAL_DIRECT - PGSTEAL_KSWAPD !=
-			PGSCAN_DIRECT - PGSCAN_KSWAPD);
 	BUILD_BUG_ON(PGSTEAL_KHUGEPAGED - PGSTEAL_KSWAPD !=
 			PGDEMOTE_KHUGEPAGED - PGDEMOTE_KSWAPD);
+#endif
+	BUILD_BUG_ON(PGSTEAL_DIRECT - PGSTEAL_KSWAPD !=
+			PGSCAN_DIRECT - PGSCAN_KSWAPD);
 	BUILD_BUG_ON(PGSTEAL_KHUGEPAGED - PGSTEAL_KSWAPD !=
 			PGSCAN_KHUGEPAGED - PGSCAN_KSWAPD);
 
@@ -976,8 +978,10 @@ static unsigned int demote_folio_list(struct list_head *demote_folios,
 	migrate_pages(demote_folios, alloc_demote_folio, NULL,
 		      (unsigned long)&mtc, MIGRATE_ASYNC, MR_DEMOTION,
 		      &nr_succeeded);
-
-	__count_vm_events(PGDEMOTE_KSWAPD + reclaimer_offset(), nr_succeeded);
+#ifdef CONFIG_NUMA_BALANCING
+	mod_node_page_state(pgdat, PGDEMOTE_KSWAPD + reclaimer_offset(),
+			    nr_succeeded);
+#endif
 
 	return nr_succeeded;
 }
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 359460deb377..afa5a38fcc9c 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1248,6 +1248,9 @@ const char * const vmstat_text[] = {
 #ifdef CONFIG_NUMA_BALANCING
 	"pgpromote_success",
 	"pgpromote_candidate",
+	"pgdemote_kswapd",
+	"pgdemote_direct",
+	"pgdemote_khugepaged",
 #endif
 
 	/* enum writeback_stat_item counters */
@@ -1279,9 +1282,6 @@ const char * const vmstat_text[] = {
 	"pgsteal_kswapd",
 	"pgsteal_direct",
 	"pgsteal_khugepaged",
-	"pgdemote_kswapd",
-	"pgdemote_direct",
-	"pgdemote_khugepaged",
 	"pgscan_kswapd",
 	"pgscan_direct",
 	"pgscan_khugepaged",
-- 
cgit v1.2.3


From b2472efe4316b2687c153919c1513a098bd82c17 Mon Sep 17 00:00:00 2001
From: Peng Zhang <zhangpeng.00@bytedance.com>
Date: Fri, 27 Oct 2023 11:38:37 +0800
Subject: maple_tree: introduce {mtree,mas}_lock_nested()

In some cases, nested locks may be needed, so {mtree,mas}_lock_nested is
introduced.  For example, when duplicating maple tree, we need to hold the
locks of two trees, in which case nested locks are needed.

At the same time, add the definition of spin_lock_nested() in tools for
testing.

Link: https://lkml.kernel.org/r/20231027033845.90608-3-zhangpeng.00@bytedance.com
Signed-off-by: Peng Zhang <zhangpeng.00@bytedance.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Mateusz Guzik <mjguzik@gmail.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Mike Christie <michael.christie@oracle.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/maple_tree.h     | 4 ++++
 tools/include/linux/spinlock.h | 1 +
 2 files changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h
index d01e850b570f..f91dbc7fe091 100644
--- a/include/linux/maple_tree.h
+++ b/include/linux/maple_tree.h
@@ -256,6 +256,8 @@ struct maple_tree {
 	struct maple_tree name = MTREE_INIT(name, 0)
 
 #define mtree_lock(mt)		spin_lock((&(mt)->ma_lock))
+#define mtree_lock_nested(mas, subclass) \
+		spin_lock_nested((&(mt)->ma_lock), subclass)
 #define mtree_unlock(mt)	spin_unlock((&(mt)->ma_lock))
 
 /*
@@ -406,6 +408,8 @@ struct ma_wr_state {
 };
 
 #define mas_lock(mas)           spin_lock(&((mas)->tree->ma_lock))
+#define mas_lock_nested(mas, subclass) \
+		spin_lock_nested(&((mas)->tree->ma_lock), subclass)
 #define mas_unlock(mas)         spin_unlock(&((mas)->tree->ma_lock))
 
 
diff --git a/tools/include/linux/spinlock.h b/tools/include/linux/spinlock.h
index 622266b197d0..a6cdf25b6b9d 100644
--- a/tools/include/linux/spinlock.h
+++ b/tools/include/linux/spinlock.h
@@ -11,6 +11,7 @@
 #define spin_lock_init(x)	pthread_mutex_init(x, NULL)
 
 #define spin_lock(x)			pthread_mutex_lock(x)
+#define spin_lock_nested(x, subclass)	pthread_mutex_lock(x)
 #define spin_unlock(x)			pthread_mutex_unlock(x)
 #define spin_lock_bh(x)			pthread_mutex_lock(x)
 #define spin_unlock_bh(x)		pthread_mutex_unlock(x)
-- 
cgit v1.2.3


From fd32e4e9b7646510ee9010e0d5f8b8857d48a6f7 Mon Sep 17 00:00:00 2001
From: Peng Zhang <zhangpeng.00@bytedance.com>
Date: Fri, 27 Oct 2023 11:38:38 +0800
Subject: maple_tree: introduce interfaces __mt_dup() and mtree_dup()

Introduce interfaces __mt_dup() and mtree_dup(), which are used to
duplicate a maple tree.  They duplicate a maple tree in Depth-First Search
(DFS) pre-order traversal.  It uses memcopy() to copy nodes in the source
tree and allocate new child nodes in non-leaf nodes.  The new node is
exactly the same as the source node except for all the addresses stored in
it.  It will be faster than traversing all elements in the source tree and
inserting them one by one into the new tree.  The time complexity of these
two functions is O(n).

The difference between __mt_dup() and mtree_dup() is that mtree_dup()
handles locks internally.

Analysis of the average time complexity of this algorithm:

For simplicity, let's assume that the maximum branching factor of all
non-leaf nodes is 16 (in allocation mode, it is 10), and the tree is a
full tree.

Under the given conditions, if there is a maple tree with n elements, the
number of its leaves is n/16.  From bottom to top, the number of nodes in
each level is 1/16 of the number of nodes in the level below.  So the
total number of nodes in the entire tree is given by the sum of n/16 +
n/16^2 + n/16^3 + ...  + 1.  This is a geometric series, and it has log(n)
terms with base 16.  According to the formula for the sum of a geometric
series, the sum of this series can be calculated as (n-1)/15.  Each node
has only one parent node pointer, which can be considered as an edge.  In
total, there are (n-1)/15-1 edges.

This algorithm consists of two operations:

1. Traversing all nodes in DFS order.
2. For each node, making a copy and performing necessary modifications
   to create a new node.

For the first part, DFS traversal will visit each edge twice.  Let
T(ascend) represent the cost of taking one step downwards, and T(descend)
represent the cost of taking one step upwards.  And both of them are
constants (although mas_ascend() may not be, as it contains a loop, but
here we ignore it and treat it as a constant).  So the time spent on the
first part can be represented as ((n-1)/15-1) * (T(ascend) + T(descend)).

For the second part, each node will be copied, and the cost of copying a
node is denoted as T(copy_node).  For each non-leaf node, it is necessary
to reallocate all child nodes, and the cost of this operation is denoted
as T(dup_alloc).  The behavior behind memory allocation is complex and not
specific to the maple tree operation.  Here, we assume that the time
required for a single allocation is constant.  Since the size of a node is
fixed, both of these symbols are also constants.  We can calculate that
the time spent on the second part is ((n-1)/15) * T(copy_node) + ((n-1)/15
- n/16) * T(dup_alloc).

Adding both parts together, the total time spent by the algorithm can be
represented as:

((n-1)/15) * (T(ascend) + T(descend) + T(copy_node) + T(dup_alloc)) -
n/16 * T(dup_alloc) - (T(ascend) + T(descend))

Let C1 = T(ascend) + T(descend) + T(copy_node) + T(dup_alloc)
Let C2 = T(dup_alloc)
Let C3 = T(ascend) + T(descend)

Finally, the expression can be simplified as:
((16 * C1 - 15 * C2) / (15 * 16)) * n - (C1 / 15 + C3).

This is a linear function, so the average time complexity is O(n).

Link: https://lkml.kernel.org/r/20231027033845.90608-4-zhangpeng.00@bytedance.com
Signed-off-by: Peng Zhang <zhangpeng.00@bytedance.com>
Suggested-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Mateusz Guzik <mjguzik@gmail.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Mike Christie <michael.christie@oracle.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/maple_tree.h |   3 +
 lib/maple_tree.c           | 274 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 277 insertions(+)

(limited to 'include')

diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h
index f91dbc7fe091..a452dd8a1e5c 100644
--- a/include/linux/maple_tree.h
+++ b/include/linux/maple_tree.h
@@ -329,6 +329,9 @@ int mtree_store(struct maple_tree *mt, unsigned long index,
 		void *entry, gfp_t gfp);
 void *mtree_erase(struct maple_tree *mt, unsigned long index);
 
+int mtree_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp);
+int __mt_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp);
+
 void mtree_destroy(struct maple_tree *mt);
 void __mt_destroy(struct maple_tree *mt);
 
diff --git a/lib/maple_tree.c b/lib/maple_tree.c
index ca7039633844..718a222cc090 100644
--- a/lib/maple_tree.c
+++ b/lib/maple_tree.c
@@ -4,6 +4,8 @@
  * Copyright (c) 2018-2022 Oracle Corporation
  * Authors: Liam R. Howlett <Liam.Howlett@oracle.com>
  *	    Matthew Wilcox <willy@infradead.org>
+ * Copyright (c) 2023 ByteDance
+ * Author: Peng Zhang <zhangpeng.00@bytedance.com>
  */
 
 /*
@@ -6475,6 +6477,278 @@ void *mtree_erase(struct maple_tree *mt, unsigned long index)
 }
 EXPORT_SYMBOL(mtree_erase);
 
+/*
+ * mas_dup_free() - Free an incomplete duplication of a tree.
+ * @mas: The maple state of a incomplete tree.
+ *
+ * The parameter @mas->node passed in indicates that the allocation failed on
+ * this node. This function frees all nodes starting from @mas->node in the
+ * reverse order of mas_dup_build(). There is no need to hold the source tree
+ * lock at this time.
+ */
+static void mas_dup_free(struct ma_state *mas)
+{
+	struct maple_node *node;
+	enum maple_type type;
+	void __rcu **slots;
+	unsigned char count, i;
+
+	/* Maybe the first node allocation failed. */
+	if (mas_is_none(mas))
+		return;
+
+	while (!mte_is_root(mas->node)) {
+		mas_ascend(mas);
+		if (mas->offset) {
+			mas->offset--;
+			do {
+				mas_descend(mas);
+				mas->offset = mas_data_end(mas);
+			} while (!mte_is_leaf(mas->node));
+
+			mas_ascend(mas);
+		}
+
+		node = mte_to_node(mas->node);
+		type = mte_node_type(mas->node);
+		slots = ma_slots(node, type);
+		count = mas_data_end(mas) + 1;
+		for (i = 0; i < count; i++)
+			((unsigned long *)slots)[i] &= ~MAPLE_NODE_MASK;
+		mt_free_bulk(count, slots);
+	}
+
+	node = mte_to_node(mas->node);
+	mt_free_one(node);
+}
+
+/*
+ * mas_copy_node() - Copy a maple node and replace the parent.
+ * @mas: The maple state of source tree.
+ * @new_mas: The maple state of new tree.
+ * @parent: The parent of the new node.
+ *
+ * Copy @mas->node to @new_mas->node, set @parent to be the parent of
+ * @new_mas->node. If memory allocation fails, @mas is set to -ENOMEM.
+ */
+static inline void mas_copy_node(struct ma_state *mas, struct ma_state *new_mas,
+		struct maple_pnode *parent)
+{
+	struct maple_node *node = mte_to_node(mas->node);
+	struct maple_node *new_node = mte_to_node(new_mas->node);
+	unsigned long val;
+
+	/* Copy the node completely. */
+	memcpy(new_node, node, sizeof(struct maple_node));
+	/* Update the parent node pointer. */
+	val = (unsigned long)node->parent & MAPLE_NODE_MASK;
+	new_node->parent = ma_parent_ptr(val | (unsigned long)parent);
+}
+
+/*
+ * mas_dup_alloc() - Allocate child nodes for a maple node.
+ * @mas: The maple state of source tree.
+ * @new_mas: The maple state of new tree.
+ * @gfp: The GFP_FLAGS to use for allocations.
+ *
+ * This function allocates child nodes for @new_mas->node during the duplication
+ * process. If memory allocation fails, @mas is set to -ENOMEM.
+ */
+static inline void mas_dup_alloc(struct ma_state *mas, struct ma_state *new_mas,
+		gfp_t gfp)
+{
+	struct maple_node *node = mte_to_node(mas->node);
+	struct maple_node *new_node = mte_to_node(new_mas->node);
+	enum maple_type type;
+	unsigned char request, count, i;
+	void __rcu **slots;
+	void __rcu **new_slots;
+	unsigned long val;
+
+	/* Allocate memory for child nodes. */
+	type = mte_node_type(mas->node);
+	new_slots = ma_slots(new_node, type);
+	request = mas_data_end(mas) + 1;
+	count = mt_alloc_bulk(gfp, request, (void **)new_slots);
+	if (unlikely(count < request)) {
+		memset(new_slots, 0, request * sizeof(void *));
+		mas_set_err(mas, -ENOMEM);
+		return;
+	}
+
+	/* Restore node type information in slots. */
+	slots = ma_slots(node, type);
+	for (i = 0; i < count; i++) {
+		val = (unsigned long)mt_slot_locked(mas->tree, slots, i);
+		val &= MAPLE_NODE_MASK;
+		((unsigned long *)new_slots)[i] |= val;
+	}
+}
+
+/*
+ * mas_dup_build() - Build a new maple tree from a source tree
+ * @mas: The maple state of source tree, need to be in MAS_START state.
+ * @new_mas: The maple state of new tree, need to be in MAS_START state.
+ * @gfp: The GFP_FLAGS to use for allocations.
+ *
+ * This function builds a new tree in DFS preorder. If the memory allocation
+ * fails, the error code -ENOMEM will be set in @mas, and @new_mas points to the
+ * last node. mas_dup_free() will free the incomplete duplication of a tree.
+ *
+ * Note that the attributes of the two trees need to be exactly the same, and the
+ * new tree needs to be empty, otherwise -EINVAL will be set in @mas.
+ */
+static inline void mas_dup_build(struct ma_state *mas, struct ma_state *new_mas,
+		gfp_t gfp)
+{
+	struct maple_node *node;
+	struct maple_pnode *parent = NULL;
+	struct maple_enode *root;
+	enum maple_type type;
+
+	if (unlikely(mt_attr(mas->tree) != mt_attr(new_mas->tree)) ||
+	    unlikely(!mtree_empty(new_mas->tree))) {
+		mas_set_err(mas, -EINVAL);
+		return;
+	}
+
+	root = mas_start(mas);
+	if (mas_is_ptr(mas) || mas_is_none(mas))
+		goto set_new_tree;
+
+	node = mt_alloc_one(gfp);
+	if (!node) {
+		new_mas->node = MAS_NONE;
+		mas_set_err(mas, -ENOMEM);
+		return;
+	}
+
+	type = mte_node_type(mas->node);
+	root = mt_mk_node(node, type);
+	new_mas->node = root;
+	new_mas->min = 0;
+	new_mas->max = ULONG_MAX;
+	root = mte_mk_root(root);
+	while (1) {
+		mas_copy_node(mas, new_mas, parent);
+		if (!mte_is_leaf(mas->node)) {
+			/* Only allocate child nodes for non-leaf nodes. */
+			mas_dup_alloc(mas, new_mas, gfp);
+			if (unlikely(mas_is_err(mas)))
+				return;
+		} else {
+			/*
+			 * This is the last leaf node and duplication is
+			 * completed.
+			 */
+			if (mas->max == ULONG_MAX)
+				goto done;
+
+			/* This is not the last leaf node and needs to go up. */
+			do {
+				mas_ascend(mas);
+				mas_ascend(new_mas);
+			} while (mas->offset == mas_data_end(mas));
+
+			/* Move to the next subtree. */
+			mas->offset++;
+			new_mas->offset++;
+		}
+
+		mas_descend(mas);
+		parent = ma_parent_ptr(mte_to_node(new_mas->node));
+		mas_descend(new_mas);
+		mas->offset = 0;
+		new_mas->offset = 0;
+	}
+done:
+	/* Specially handle the parent of the root node. */
+	mte_to_node(root)->parent = ma_parent_ptr(mas_tree_parent(new_mas));
+set_new_tree:
+	/* Make them the same height */
+	new_mas->tree->ma_flags = mas->tree->ma_flags;
+	rcu_assign_pointer(new_mas->tree->ma_root, root);
+}
+
+/**
+ * __mt_dup(): Duplicate an entire maple tree
+ * @mt: The source maple tree
+ * @new: The new maple tree
+ * @gfp: The GFP_FLAGS to use for allocations
+ *
+ * This function duplicates a maple tree in Depth-First Search (DFS) pre-order
+ * traversal. It uses memcpy() to copy nodes in the source tree and allocate
+ * new child nodes in non-leaf nodes. The new node is exactly the same as the
+ * source node except for all the addresses stored in it. It will be faster than
+ * traversing all elements in the source tree and inserting them one by one into
+ * the new tree.
+ * The user needs to ensure that the attributes of the source tree and the new
+ * tree are the same, and the new tree needs to be an empty tree, otherwise
+ * -EINVAL will be returned.
+ * Note that the user needs to manually lock the source tree and the new tree.
+ *
+ * Return: 0 on success, -ENOMEM if memory could not be allocated, -EINVAL If
+ * the attributes of the two trees are different or the new tree is not an empty
+ * tree.
+ */
+int __mt_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp)
+{
+	int ret = 0;
+	MA_STATE(mas, mt, 0, 0);
+	MA_STATE(new_mas, new, 0, 0);
+
+	mas_dup_build(&mas, &new_mas, gfp);
+	if (unlikely(mas_is_err(&mas))) {
+		ret = xa_err(mas.node);
+		if (ret == -ENOMEM)
+			mas_dup_free(&new_mas);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL(__mt_dup);
+
+/**
+ * mtree_dup(): Duplicate an entire maple tree
+ * @mt: The source maple tree
+ * @new: The new maple tree
+ * @gfp: The GFP_FLAGS to use for allocations
+ *
+ * This function duplicates a maple tree in Depth-First Search (DFS) pre-order
+ * traversal. It uses memcpy() to copy nodes in the source tree and allocate
+ * new child nodes in non-leaf nodes. The new node is exactly the same as the
+ * source node except for all the addresses stored in it. It will be faster than
+ * traversing all elements in the source tree and inserting them one by one into
+ * the new tree.
+ * The user needs to ensure that the attributes of the source tree and the new
+ * tree are the same, and the new tree needs to be an empty tree, otherwise
+ * -EINVAL will be returned.
+ *
+ * Return: 0 on success, -ENOMEM if memory could not be allocated, -EINVAL If
+ * the attributes of the two trees are different or the new tree is not an empty
+ * tree.
+ */
+int mtree_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp)
+{
+	int ret = 0;
+	MA_STATE(mas, mt, 0, 0);
+	MA_STATE(new_mas, new, 0, 0);
+
+	mas_lock(&new_mas);
+	mas_lock_nested(&mas, SINGLE_DEPTH_NESTING);
+	mas_dup_build(&mas, &new_mas, gfp);
+	mas_unlock(&mas);
+	if (unlikely(mas_is_err(&mas))) {
+		ret = xa_err(mas.node);
+		if (ret == -ENOMEM)
+			mas_dup_free(&new_mas);
+	}
+
+	mas_unlock(&new_mas);
+	return ret;
+}
+EXPORT_SYMBOL(mtree_dup);
+
 /**
  * __mt_destroy() - Walk and free all nodes of a locked maple tree.
  * @mt: The maple tree
-- 
cgit v1.2.3


From d2406291483775ecddaee929231a39c70c08fda2 Mon Sep 17 00:00:00 2001
From: Peng Zhang <zhangpeng.00@bytedance.com>
Date: Fri, 27 Oct 2023 11:38:45 +0800
Subject: fork: use __mt_dup() to duplicate maple tree in dup_mmap()

In dup_mmap(), using __mt_dup() to duplicate the old maple tree and then
directly replacing the entries of VMAs in the new maple tree can result in
better performance.  __mt_dup() uses DFS pre-order to duplicate the maple
tree, so it is efficient.

The average time complexity of __mt_dup() is O(n), where n is the number
of VMAs.  The proof of the time complexity is provided in the commit log
that introduces __mt_dup().  After duplicating the maple tree, each
element is traversed and replaced (ignoring the cases of deletion, which
are rare).  Since it is only a replacement operation for each element,
this process is also O(n).

Analyzing the exact time complexity of the previous algorithm is
challenging because each insertion can involve appending to a node,
pushing data to adjacent nodes, or even splitting nodes.  The frequency of
each action is difficult to calculate.  The worst-case scenario for a
single insertion is when the tree undergoes splitting at every level.  If
we consider each insertion as the worst-case scenario, we can determine
that the upper bound of the time complexity is O(n*log(n)), although this
is a loose upper bound.  However, based on the test data, it appears that
the actual time complexity is likely to be O(n).

As the entire maple tree is duplicated using __mt_dup(), if dup_mmap()
fails, there will be a portion of VMAs that have not been duplicated in
the maple tree.  To handle this, we mark the failure point with
XA_ZERO_ENTRY.  In exit_mmap(), if this marker is encountered, stop
releasing VMAs that have not been duplicated after this point.

There is a "spawn" in byte-unixbench[1], which can be used to test the
performance of fork().  I modified it slightly to make it work with
different number of VMAs.

Below are the test results.  The first row shows the number of VMAs.  The
second and third rows show the number of fork() calls per ten seconds,
corresponding to next-20231006 and the this patchset, respectively.  The
test results were obtained with CPU binding to avoid scheduler load
balancing that could cause unstable results.  There are still some
fluctuations in the test results, but at least they are better than the
original performance.

21     121   221    421    821    1621   3221   6421   12821  25621  51221
112100 76261 54227  34035  20195  11112  6017   3161   1606   802    393
114558 83067 65008  45824  28751  16072  8922   4747   2436   1233   599
2.19%  8.92% 19.88% 34.64% 42.37% 44.64% 48.28% 50.17% 51.68% 53.74% 52.42%

[1] https://github.com/kdlucas/byte-unixbench/tree/master

Link: https://lkml.kernel.org/r/20231027033845.90608-11-zhangpeng.00@bytedance.com
Signed-off-by: Peng Zhang <zhangpeng.00@bytedance.com>
Suggested-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Mateusz Guzik <mjguzik@gmail.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Mike Christie <michael.christie@oracle.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mm.h | 11 +++++++++++
 kernel/fork.c      | 40 +++++++++++++++++++++++++++++-----------
 mm/internal.h      | 11 -----------
 mm/memory.c        |  7 ++++++-
 mm/mmap.c          |  9 ++++++---
 5 files changed, 52 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 418d26608ece..64cd1ee4aacc 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -994,6 +994,17 @@ static inline int vma_iter_bulk_alloc(struct vma_iterator *vmi,
 	return mas_expected_entries(&vmi->mas, count);
 }
 
+static inline int vma_iter_clear_gfp(struct vma_iterator *vmi,
+			unsigned long start, unsigned long end, gfp_t gfp)
+{
+	__mas_set_range(&vmi->mas, start, end - 1);
+	mas_store_gfp(&vmi->mas, NULL, gfp);
+	if (unlikely(mas_is_err(&vmi->mas)))
+		return -ENOMEM;
+
+	return 0;
+}
+
 /* Free any unused preallocations */
 static inline void vma_iter_free(struct vma_iterator *vmi)
 {
diff --git a/kernel/fork.c b/kernel/fork.c
index 10917c3e1f03..93924392a5c3 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -650,7 +650,6 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 	int retval;
 	unsigned long charge = 0;
 	LIST_HEAD(uf);
-	VMA_ITERATOR(old_vmi, oldmm, 0);
 	VMA_ITERATOR(vmi, mm, 0);
 
 	uprobe_start_dup_mmap();
@@ -678,16 +677,22 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 		goto out;
 	khugepaged_fork(mm, oldmm);
 
-	retval = vma_iter_bulk_alloc(&vmi, oldmm->map_count);
-	if (retval)
+	/* Use __mt_dup() to efficiently build an identical maple tree. */
+	retval = __mt_dup(&oldmm->mm_mt, &mm->mm_mt, GFP_KERNEL);
+	if (unlikely(retval))
 		goto out;
 
 	mt_clear_in_rcu(vmi.mas.tree);
-	for_each_vma(old_vmi, mpnt) {
+	for_each_vma(vmi, mpnt) {
 		struct file *file;
 
 		vma_start_write(mpnt);
 		if (mpnt->vm_flags & VM_DONTCOPY) {
+			retval = vma_iter_clear_gfp(&vmi, mpnt->vm_start,
+						    mpnt->vm_end, GFP_KERNEL);
+			if (retval)
+				goto loop_out;
+
 			vm_stat_account(mm, mpnt->vm_flags, -vma_pages(mpnt));
 			continue;
 		}
@@ -749,9 +754,11 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 		if (is_vm_hugetlb_page(tmp))
 			hugetlb_dup_vma_private(tmp);
 
-		/* Link the vma into the MT */
-		if (vma_iter_bulk_store(&vmi, tmp))
-			goto fail_nomem_vmi_store;
+		/*
+		 * Link the vma into the MT. After using __mt_dup(), memory
+		 * allocation is not necessary here, so it cannot fail.
+		 */
+		vma_iter_bulk_store(&vmi, tmp);
 
 		mm->map_count++;
 		if (!(tmp->vm_flags & VM_WIPEONFORK))
@@ -760,15 +767,28 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 		if (tmp->vm_ops && tmp->vm_ops->open)
 			tmp->vm_ops->open(tmp);
 
-		if (retval)
+		if (retval) {
+			mpnt = vma_next(&vmi);
 			goto loop_out;
+		}
 	}
 	/* a new mm has just been created */
 	retval = arch_dup_mmap(oldmm, mm);
 loop_out:
 	vma_iter_free(&vmi);
-	if (!retval)
+	if (!retval) {
 		mt_set_in_rcu(vmi.mas.tree);
+	} else if (mpnt) {
+		/*
+		 * The entire maple tree has already been duplicated. If the
+		 * mmap duplication fails, mark the failure point with
+		 * XA_ZERO_ENTRY. In exit_mmap(), if this marker is encountered,
+		 * stop releasing VMAs that have not been duplicated after this
+		 * point.
+		 */
+		mas_set_range(&vmi.mas, mpnt->vm_start, mpnt->vm_end - 1);
+		mas_store(&vmi.mas, XA_ZERO_ENTRY);
+	}
 out:
 	mmap_write_unlock(mm);
 	flush_tlb_mm(oldmm);
@@ -778,8 +798,6 @@ fail_uprobe_end:
 	uprobe_end_dup_mmap();
 	return retval;
 
-fail_nomem_vmi_store:
-	unlink_anon_vmas(tmp);
 fail_nomem_anon_vma_fork:
 	mpol_put(vma_policy(tmp));
 fail_nomem_policy:
diff --git a/mm/internal.h b/mm/internal.h
index b61034bd50f5..89a5a794d68f 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1154,17 +1154,6 @@ static inline void vma_iter_clear(struct vma_iterator *vmi)
 	mas_store_prealloc(&vmi->mas, NULL);
 }
 
-static inline int vma_iter_clear_gfp(struct vma_iterator *vmi,
-			unsigned long start, unsigned long end, gfp_t gfp)
-{
-	__mas_set_range(&vmi->mas, start, end - 1);
-	mas_store_gfp(&vmi->mas, NULL, gfp);
-	if (unlikely(mas_is_err(&vmi->mas)))
-		return -ENOMEM;
-
-	return 0;
-}
-
 static inline struct vm_area_struct *vma_iter_load(struct vma_iterator *vmi)
 {
 	return mas_walk(&vmi->mas);
diff --git a/mm/memory.c b/mm/memory.c
index 5c757fba8858..a7025ed5c65b 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -374,6 +374,8 @@ void free_pgtables(struct mmu_gather *tlb, struct ma_state *mas,
 		 * be 0.  This will underflow and is okay.
 		 */
 		next = mas_find(mas, ceiling - 1);
+		if (unlikely(xa_is_zero(next)))
+			next = NULL;
 
 		/*
 		 * Hide vma from rmap and truncate_pagecache before freeing
@@ -395,6 +397,8 @@ void free_pgtables(struct mmu_gather *tlb, struct ma_state *mas,
 			       && !is_vm_hugetlb_page(next)) {
 				vma = next;
 				next = mas_find(mas, ceiling - 1);
+				if (unlikely(xa_is_zero(next)))
+					next = NULL;
 				if (mm_wr_locked)
 					vma_start_write(vma);
 				unlink_anon_vmas(vma);
@@ -1744,7 +1748,8 @@ void unmap_vmas(struct mmu_gather *tlb, struct ma_state *mas,
 		unmap_single_vma(tlb, vma, start, end, &details,
 				 mm_wr_locked);
 		hugetlb_zap_end(vma, &details);
-	} while ((vma = mas_find(mas, tree_end - 1)) != NULL);
+		vma = mas_find(mas, tree_end - 1);
+	} while (vma && likely(!xa_is_zero(vma)));
 	mmu_notifier_invalidate_range_end(&range);
 }
 
diff --git a/mm/mmap.c b/mm/mmap.c
index 1971bfffcc03..4f1cb814586d 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -3294,10 +3294,11 @@ void exit_mmap(struct mm_struct *mm)
 	arch_exit_mmap(mm);
 
 	vma = mas_find(&mas, ULONG_MAX);
-	if (!vma) {
+	if (!vma || unlikely(xa_is_zero(vma))) {
 		/* Can happen if dup_mmap() received an OOM */
 		mmap_read_unlock(mm);
-		return;
+		mmap_write_lock(mm);
+		goto destroy;
 	}
 
 	lru_add_drain();
@@ -3332,11 +3333,13 @@ void exit_mmap(struct mm_struct *mm)
 		remove_vma(vma, true);
 		count++;
 		cond_resched();
-	} while ((vma = mas_find(&mas, ULONG_MAX)) != NULL);
+		vma = mas_find(&mas, ULONG_MAX);
+	} while (vma && likely(!xa_is_zero(vma)));
 
 	BUG_ON(count != mm->map_count);
 
 	trace_exit_mmap(mm);
+destroy:
 	__mt_destroy(&mm->mm_mt);
 	mmap_write_unlock(mm);
 	vm_unacct_memory(nr_accounted);
-- 
cgit v1.2.3


From ff6c3d81f2e86b63a3a530683f89ef393882782a Mon Sep 17 00:00:00 2001
From: Liam Ni <zhiguangni01@gmail.com>
Date: Thu, 26 Oct 2023 10:03:29 +0800
Subject: NUMA: optimize detection of memory with no node id assigned by
 firmware

Sanity check that makes sure the nodes cover all memory loops over
numa_meminfo to count the pages that have node id assigned by the
firmware, then loops again over memblock.memory to find the total amount
of memory and in the end checks that the difference between the total
memory and memory that covered by nodes is less than some threshold.
Worse, the loop over numa_meminfo calls __absent_pages_in_range() that
also partially traverses memblock.memory.

It's much simpler and more efficient to have a single traversal of
memblock.memory that verifies that amount of memory not covered by nodes
is less than a threshold.

Introduce memblock_validate_numa_coverage() that does exactly that and use
it instead of numa_meminfo_cover_memory().

Link: https://lkml.kernel.org/r/20231026020329.327329-1-zhiguangni01@gmail.com
Signed-off-by: Liam Ni <zhiguangni01@gmail.com>
Reviewed-by: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Bibo Mao <maobibo@loongson.cn>
Cc: Binbin Zhou <zhoubinbin@loongson.cn>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Feiyang Chen <chenfeiyang@loongson.cn>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: WANG Xuerui <kernel@xen0n.name>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/loongarch/kernel/numa.c | 28 +---------------------------
 arch/x86/mm/numa.c           | 34 ++--------------------------------
 include/linux/memblock.h     |  1 +
 mm/memblock.c                | 34 ++++++++++++++++++++++++++++++++++
 4 files changed, 38 insertions(+), 59 deletions(-)

(limited to 'include')

diff --git a/arch/loongarch/kernel/numa.c b/arch/loongarch/kernel/numa.c
index 6e65ff12d5c7..8fe21f868f72 100644
--- a/arch/loongarch/kernel/numa.c
+++ b/arch/loongarch/kernel/numa.c
@@ -226,32 +226,6 @@ static void __init node_mem_init(unsigned int node)
 
 #ifdef CONFIG_ACPI_NUMA
 
-/*
- * Sanity check to catch more bad NUMA configurations (they are amazingly
- * common).  Make sure the nodes cover all memory.
- */
-static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi)
-{
-	int i;
-	u64 numaram, biosram;
-
-	numaram = 0;
-	for (i = 0; i < mi->nr_blks; i++) {
-		u64 s = mi->blk[i].start >> PAGE_SHIFT;
-		u64 e = mi->blk[i].end >> PAGE_SHIFT;
-
-		numaram += e - s;
-		numaram -= __absent_pages_in_range(mi->blk[i].nid, s, e);
-		if ((s64)numaram < 0)
-			numaram = 0;
-	}
-	max_pfn = max_low_pfn;
-	biosram = max_pfn - absent_pages_in_range(0, max_pfn);
-
-	BUG_ON((s64)(biosram - numaram) >= (1 << (20 - PAGE_SHIFT)));
-	return true;
-}
-
 static void __init add_node_intersection(u32 node, u64 start, u64 size, u32 type)
 {
 	static unsigned long num_physpages;
@@ -396,7 +370,7 @@ int __init init_numa_memory(void)
 		return -EINVAL;
 
 	init_node_memblock();
-	if (numa_meminfo_cover_memory(&numa_meminfo) == false)
+	if (!memblock_validate_numa_coverage(SZ_1M))
 		return -EINVAL;
 
 	for_each_node_mask(node, node_possible_map) {
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index b29ceb19e46e..adc497b93f03 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -449,37 +449,6 @@ int __node_distance(int from, int to)
 }
 EXPORT_SYMBOL(__node_distance);
 
-/*
- * Sanity check to catch more bad NUMA configurations (they are amazingly
- * common).  Make sure the nodes cover all memory.
- */
-static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi)
-{
-	u64 numaram, e820ram;
-	int i;
-
-	numaram = 0;
-	for (i = 0; i < mi->nr_blks; i++) {
-		u64 s = mi->blk[i].start >> PAGE_SHIFT;
-		u64 e = mi->blk[i].end >> PAGE_SHIFT;
-		numaram += e - s;
-		numaram -= __absent_pages_in_range(mi->blk[i].nid, s, e);
-		if ((s64)numaram < 0)
-			numaram = 0;
-	}
-
-	e820ram = max_pfn - absent_pages_in_range(0, max_pfn);
-
-	/* We seem to lose 3 pages somewhere. Allow 1M of slack. */
-	if ((s64)(e820ram - numaram) >= (1 << (20 - PAGE_SHIFT))) {
-		printk(KERN_ERR "NUMA: nodes only cover %LuMB of your %LuMB e820 RAM. Not used.\n",
-		       (numaram << PAGE_SHIFT) >> 20,
-		       (e820ram << PAGE_SHIFT) >> 20);
-		return false;
-	}
-	return true;
-}
-
 /*
  * Mark all currently memblock-reserved physical memory (which covers the
  * kernel's own memory ranges) as hot-unswappable.
@@ -585,7 +554,8 @@ static int __init numa_register_memblks(struct numa_meminfo *mi)
 			return -EINVAL;
 		}
 	}
-	if (!numa_meminfo_cover_memory(mi))
+
+	if (!memblock_validate_numa_coverage(SZ_1M))
 		return -EINVAL;
 
 	/* Finally register nodes. */
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index ae3bde302f70..b695f9e946da 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -123,6 +123,7 @@ int memblock_physmem_add(phys_addr_t base, phys_addr_t size);
 void memblock_trim_memory(phys_addr_t align);
 bool memblock_overlaps_region(struct memblock_type *type,
 			      phys_addr_t base, phys_addr_t size);
+bool memblock_validate_numa_coverage(unsigned long threshold_bytes);
 int memblock_mark_hotplug(phys_addr_t base, phys_addr_t size);
 int memblock_clear_hotplug(phys_addr_t base, phys_addr_t size);
 int memblock_mark_mirror(phys_addr_t base, phys_addr_t size);
diff --git a/mm/memblock.c b/mm/memblock.c
index 5a88d6d24d79..4a62f7774b65 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -734,6 +734,40 @@ int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size)
 	return memblock_add_range(&memblock.memory, base, size, MAX_NUMNODES, 0);
 }
 
+/**
+ * memblock_validate_numa_coverage - check if amount of memory with
+ * no node ID assigned is less than a threshold
+ * @threshold_bytes: maximal number of pages that can have unassigned node
+ * ID (in bytes).
+ *
+ * A buggy firmware may report memory that does not belong to any node.
+ * Check if amount of such memory is below @threshold_bytes.
+ *
+ * Return: true on success, false on failure.
+ */
+bool __init_memblock memblock_validate_numa_coverage(unsigned long threshold_bytes)
+{
+	unsigned long nr_pages = 0;
+	unsigned long start_pfn, end_pfn, mem_size_mb;
+	int nid, i;
+
+	/* calculate lose page */
+	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) {
+		if (nid == NUMA_NO_NODE)
+			nr_pages += end_pfn - start_pfn;
+	}
+
+	if ((nr_pages << PAGE_SHIFT) >= threshold_bytes) {
+		mem_size_mb = memblock_phys_mem_size() >> 20;
+		pr_err("NUMA: no nodes coverage for %luMB of %luMB RAM\n",
+		       (nr_pages << PAGE_SHIFT) >> 20, mem_size_mb);
+		return false;
+	}
+
+	return true;
+}
+
+
 /**
  * memblock_isolate_range - isolate given range into disjoint memblocks
  * @type: memblock type to isolate range for
-- 
cgit v1.2.3


From e6a9a2cbc13bf43e4c03f57666e93d511249d5d7 Mon Sep 17 00:00:00 2001
From: Andrei Vagin <avagin@google.com>
Date: Mon, 6 Nov 2023 14:09:58 -0800
Subject: fs/proc/task_mmu: report SOFT_DIRTY bits through the PAGEMAP_SCAN
 ioctl
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The PAGEMAP_SCAN ioctl returns information regarding page table entries.
It is more efficient compared to reading pagemap files.  CRIU can start to
utilize this ioctl, but it needs info about soft-dirty bits to track
memory changes.

We are aware of a new method for tracking memory changes implemented in
the PAGEMAP_SCAN ioctl.  For CRIU, the primary advantage of this method is
its usability by unprivileged users.  However, it is not feasible to
transparently replace the soft-dirty tracker with the new one.  The main
problem here is userfault descriptors that have to be preserved between
pre-dump iterations.  It means criu continues supporting the soft-dirty
method to avoid breakage for current users.  The new method will be
implemented as a separate feature.

[avagin@google.com: update tools/include/uapi/linux/fs.h]
  Link: https://lkml.kernel.org/r/20231107164139.576046-1-avagin@google.com
Link: https://lkml.kernel.org/r/20231106220959.296568-1-avagin@google.com
Signed-off-by: Andrei Vagin <avagin@google.com>
Reviewed-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Cc: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 Documentation/admin-guide/mm/pagemap.rst |  1 +
 fs/proc/task_mmu.c                       | 17 ++++++++++++++++-
 include/uapi/linux/fs.h                  |  1 +
 tools/include/uapi/linux/fs.h            |  1 +
 4 files changed, 19 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/Documentation/admin-guide/mm/pagemap.rst b/Documentation/admin-guide/mm/pagemap.rst
index fe17cf210426..f5f065c67615 100644
--- a/Documentation/admin-guide/mm/pagemap.rst
+++ b/Documentation/admin-guide/mm/pagemap.rst
@@ -253,6 +253,7 @@ Following flags about pages are currently supported:
 - ``PAGE_IS_SWAPPED`` - Page is in swapped
 - ``PAGE_IS_PFNZERO`` - Page has zero PFN
 - ``PAGE_IS_HUGE`` - Page is THP or Hugetlb backed
+- ``PAGE_IS_SOFT_DIRTY`` - Page is soft-dirty
 
 The ``struct pm_scan_arg`` is used as the argument of the IOCTL.
 
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 435b61054b5b..d19924bf0a39 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1761,7 +1761,7 @@ static int pagemap_release(struct inode *inode, struct file *file)
 #define PM_SCAN_CATEGORIES	(PAGE_IS_WPALLOWED | PAGE_IS_WRITTEN |	\
 				 PAGE_IS_FILE |	PAGE_IS_PRESENT |	\
 				 PAGE_IS_SWAPPED | PAGE_IS_PFNZERO |	\
-				 PAGE_IS_HUGE)
+				 PAGE_IS_HUGE | PAGE_IS_SOFT_DIRTY)
 #define PM_SCAN_FLAGS		(PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC)
 
 struct pagemap_scan_private {
@@ -1793,6 +1793,8 @@ static unsigned long pagemap_page_category(struct pagemap_scan_private *p,
 
 		if (is_zero_pfn(pte_pfn(pte)))
 			categories |= PAGE_IS_PFNZERO;
+		if (pte_soft_dirty(pte))
+			categories |= PAGE_IS_SOFT_DIRTY;
 	} else if (is_swap_pte(pte)) {
 		swp_entry_t swp;
 
@@ -1806,6 +1808,8 @@ static unsigned long pagemap_page_category(struct pagemap_scan_private *p,
 			    !PageAnon(pfn_swap_entry_to_page(swp)))
 				categories |= PAGE_IS_FILE;
 		}
+		if (pte_swp_soft_dirty(pte))
+			categories |= PAGE_IS_SOFT_DIRTY;
 	}
 
 	return categories;
@@ -1853,12 +1857,16 @@ static unsigned long pagemap_thp_category(struct pagemap_scan_private *p,
 
 		if (is_zero_pfn(pmd_pfn(pmd)))
 			categories |= PAGE_IS_PFNZERO;
+		if (pmd_soft_dirty(pmd))
+			categories |= PAGE_IS_SOFT_DIRTY;
 	} else if (is_swap_pmd(pmd)) {
 		swp_entry_t swp;
 
 		categories |= PAGE_IS_SWAPPED;
 		if (!pmd_swp_uffd_wp(pmd))
 			categories |= PAGE_IS_WRITTEN;
+		if (pmd_swp_soft_dirty(pmd))
+			categories |= PAGE_IS_SOFT_DIRTY;
 
 		if (p->masks_of_interest & PAGE_IS_FILE) {
 			swp = pmd_to_swp_entry(pmd);
@@ -1905,10 +1913,14 @@ static unsigned long pagemap_hugetlb_category(pte_t pte)
 			categories |= PAGE_IS_FILE;
 		if (is_zero_pfn(pte_pfn(pte)))
 			categories |= PAGE_IS_PFNZERO;
+		if (pte_soft_dirty(pte))
+			categories |= PAGE_IS_SOFT_DIRTY;
 	} else if (is_swap_pte(pte)) {
 		categories |= PAGE_IS_SWAPPED;
 		if (!pte_swp_uffd_wp_any(pte))
 			categories |= PAGE_IS_WRITTEN;
+		if (pte_swp_soft_dirty(pte))
+			categories |= PAGE_IS_SOFT_DIRTY;
 	}
 
 	return categories;
@@ -2007,6 +2019,9 @@ static int pagemap_scan_test_walk(unsigned long start, unsigned long end,
 	if (wp_allowed)
 		vma_category |= PAGE_IS_WPALLOWED;
 
+	if (vma->vm_flags & VM_SOFTDIRTY)
+		vma_category |= PAGE_IS_SOFT_DIRTY;
+
 	if (!pagemap_scan_is_interesting_vma(vma_category, p))
 		return 1;
 
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index da43810b7485..48ad69f7722e 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -316,6 +316,7 @@ typedef int __bitwise __kernel_rwf_t;
 #define PAGE_IS_SWAPPED		(1 << 4)
 #define PAGE_IS_PFNZERO		(1 << 5)
 #define PAGE_IS_HUGE		(1 << 6)
+#define PAGE_IS_SOFT_DIRTY	(1 << 7)
 
 /*
  * struct page_region - Page region with flags
diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h
index da43810b7485..48ad69f7722e 100644
--- a/tools/include/uapi/linux/fs.h
+++ b/tools/include/uapi/linux/fs.h
@@ -316,6 +316,7 @@ typedef int __bitwise __kernel_rwf_t;
 #define PAGE_IS_SWAPPED		(1 << 4)
 #define PAGE_IS_PFNZERO		(1 << 5)
 #define PAGE_IS_HUGE		(1 << 6)
+#define PAGE_IS_SOFT_DIRTY	(1 << 7)
 
 /*
  * struct page_region - Page region with flags
-- 
cgit v1.2.3


From a4fc4a0c45f2617c3aa8b693739de264e0c09909 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Tue, 7 Nov 2023 21:26:40 +0000
Subject: mm: add folio_zero_tail() and use it in ext4

Patch series "Add folio_zero_tail() and folio_fill_tail()".

I'm trying to make it easier for filesystems with tailpacking / stuffing /
inline data to use folios.  The primary function here is
folio_fill_tail().  You give it a pointer to memory where the data
currently is, and it takes care of copying it into the folio at that
offset.  That works for gfs2 & iomap.  Then There's Ext4.  Rather than gin
up some kind of specialist "Here's a two pointers to two blocks of memory"
routine, just let it do its current thing, and let it call
folio_zero_tail(), which is also called by folio_fill_tail().

Other filesystems can be converted later; these ones seemed like good
examples as they're already partly or completely converted to folios.


This patch (of 3):

Instead of unmapping the folio after copying the data to it, then mapping
it again to zero the tail, provide folio_zero_tail() to zero the tail of
an already-mapped folio.

[akpm@linux-foundation.org: fix kerneldoc argument ordering]
Link: https://lkml.kernel.org/r/20231107212643.3490372-1-willy@infradead.org
Link: https://lkml.kernel.org/r/20231107212643.3490372-2-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Andreas Gruenbacher <agruenba@redhat.com>
Cc: Darrick J. Wong <djwong@kernel.org>
Cc: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/ext4/inline.c        |  3 +--
 include/linux/highmem.h | 38 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 39 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 9a84a5f9fef4..d5bd1e3a5d36 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -502,9 +502,8 @@ static int ext4_read_inline_folio(struct inode *inode, struct folio *folio)
 	BUG_ON(len > PAGE_SIZE);
 	kaddr = kmap_local_folio(folio, 0);
 	ret = ext4_read_inline_data(inode, kaddr, len, &iloc);
-	flush_dcache_folio(folio);
+	kaddr = folio_zero_tail(folio, len, kaddr + len);
 	kunmap_local(kaddr);
-	folio_zero_segment(folio, len, folio_size(folio));
 	folio_mark_uptodate(folio);
 	brelse(iloc.bh);
 
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index be20cff4ba73..5ebd5e4dfbf8 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -483,6 +483,44 @@ static inline void memcpy_to_folio(struct folio *folio, size_t offset,
 	flush_dcache_folio(folio);
 }
 
+/**
+ * folio_zero_tail - Zero the tail of a folio.
+ * @folio: The folio to zero.
+ * @offset: The byte offset in the folio to start zeroing at.
+ * @kaddr: The address the folio is currently mapped to.
+ *
+ * If you have already used kmap_local_folio() to map a folio, written
+ * some data to it and now need to zero the end of the folio (and flush
+ * the dcache), you can use this function.  If you do not have the
+ * folio kmapped (eg the folio has been partially populated by DMA),
+ * use folio_zero_range() or folio_zero_segment() instead.
+ *
+ * Return: An address which can be passed to kunmap_local().
+ */
+static inline __must_check void *folio_zero_tail(struct folio *folio,
+		size_t offset, void *kaddr)
+{
+	size_t len = folio_size(folio) - offset;
+
+	if (folio_test_highmem(folio)) {
+		size_t max = PAGE_SIZE - offset_in_page(offset);
+
+		while (len > max) {
+			memset(kaddr, 0, max);
+			kunmap_local(kaddr);
+			len -= max;
+			offset += max;
+			max = PAGE_SIZE;
+			kaddr = kmap_local_folio(folio, offset);
+		}
+	}
+
+	memset(kaddr, 0, len);
+	flush_dcache_folio(folio);
+
+	return kaddr;
+}
+
 /**
  * memcpy_from_file_folio - Copy some bytes from a file folio.
  * @to: The destination buffer.
-- 
cgit v1.2.3


From 6eaa266b54660f6b3654ad8902b4f7027054f55a Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Tue, 7 Nov 2023 21:26:41 +0000
Subject: mm: add folio_fill_tail() and use it in iomap

The iomap code was limited to PAGE_SIZE bytes; generalise it to cover
an arbitrary-sized folio, and move it to be a common helper.

[akpm@linux-foundation.org: fix folio_fill_tail(), per Andreas Gruenbacher]
Link: https://lkml.kernel.org/r/20231107212643.3490372-3-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Andreas Gruenbacher <agruenba@redhat.com>
Cc: Andreas Dilger <adilger.kernel@dilger.ca>
Cc: Darrick J. Wong <djwong@kernel.org>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: Andreas Gruenbacher <agruenba@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/iomap/buffered-io.c  | 14 ++------------
 include/linux/highmem.h | 38 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 40 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index f72df2babe56..093c4515b22a 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -305,28 +305,18 @@ static int iomap_read_inline_data(const struct iomap_iter *iter,
 {
 	const struct iomap *iomap = iomap_iter_srcmap(iter);
 	size_t size = i_size_read(iter->inode) - iomap->offset;
-	size_t poff = offset_in_page(iomap->offset);
 	size_t offset = offset_in_folio(folio, iomap->offset);
-	void *addr;
 
 	if (folio_test_uptodate(folio))
 		return 0;
 
-	if (WARN_ON_ONCE(size > PAGE_SIZE - poff))
-		return -EIO;
-	if (WARN_ON_ONCE(size > PAGE_SIZE -
-			 offset_in_page(iomap->inline_data)))
-		return -EIO;
 	if (WARN_ON_ONCE(size > iomap->length))
 		return -EIO;
 	if (offset > 0)
 		ifs_alloc(iter->inode, folio, iter->flags);
 
-	addr = kmap_local_folio(folio, offset);
-	memcpy(addr, iomap->inline_data, size);
-	memset(addr + size, 0, PAGE_SIZE - poff - size);
-	kunmap_local(addr);
-	iomap_set_range_uptodate(folio, offset, PAGE_SIZE - poff);
+	folio_fill_tail(folio, offset, iomap->inline_data, size);
+	iomap_set_range_uptodate(folio, offset, folio_size(folio) - offset);
 	return 0;
 }
 
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 5ebd5e4dfbf8..451c1dff0e87 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -521,6 +521,44 @@ static inline __must_check void *folio_zero_tail(struct folio *folio,
 	return kaddr;
 }
 
+/**
+ * folio_fill_tail - Copy some data to a folio and pad with zeroes.
+ * @folio: The destination folio.
+ * @offset: The offset into @folio at which to start copying.
+ * @from: The data to copy.
+ * @len: How many bytes of data to copy.
+ *
+ * This function is most useful for filesystems which support inline data.
+ * When they want to copy data from the inode into the page cache, this
+ * function does everything for them.  It supports large folios even on
+ * HIGHMEM configurations.
+ */
+static inline void folio_fill_tail(struct folio *folio, size_t offset,
+		const char *from, size_t len)
+{
+	char *to = kmap_local_folio(folio, offset);
+
+	VM_BUG_ON(offset + len > folio_size(folio));
+
+	if (folio_test_highmem(folio)) {
+		size_t max = PAGE_SIZE - offset_in_page(offset);
+
+		while (len > max) {
+			memcpy(to, from, max);
+			kunmap_local(to);
+			len -= max;
+			from += max;
+			offset += max;
+			max = PAGE_SIZE;
+			to = kmap_local_folio(folio, offset);
+		}
+	}
+
+	memcpy(to, from, len);
+	to = folio_zero_tail(folio, offset + len, to + len);
+	kunmap_local(to);
+}
+
 /**
  * memcpy_from_file_folio - Copy some bytes from a file folio.
  * @to: The destination buffer.
-- 
cgit v1.2.3


From c36f9d3d2c3e17f9eef1d2f47a63c91d51d55e87 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Wed, 8 Nov 2023 20:46:02 +0000
Subject: mm: remove test_set_page_writeback()

Patch series "Make folio_start_writeback return void".

Most of the folio flag-setting functions return void.
folio_start_writeback is gratuitously different; the only two filesystems
that do anything with the return value emit debug messages if it's already
set, and we can (and should) do that internally without bothering the
filesystem to do it.


This patch (of 4):

There are no more callers of this wrapper.

Link: https://lkml.kernel.org/r/20231108204605.745109-1-willy@infradead.org
Link: https://lkml.kernel.org/r/20231108204605.745109-2-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Steve French <sfrench@samba.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/page-flags.h | 5 -----
 1 file changed, 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index a88e64acebfe..a440062e9386 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -780,11 +780,6 @@ bool set_page_writeback(struct page *page);
 #define folio_start_writeback_keepwrite(folio)	\
 	__folio_start_writeback(folio, true)
 
-static inline bool test_set_page_writeback(struct page *page)
-{
-	return set_page_writeback(page);
-}
-
 static __always_inline bool folio_test_head(struct folio *folio)
 {
 	return test_bit(PG_head, folio_flags(folio, FOLIO_PF_ANY));
-- 
cgit v1.2.3


From b5612c368648a7be52411b288d09593e5945d1aa Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Wed, 8 Nov 2023 20:46:05 +0000
Subject: mm: return void from folio_start_writeback() and related functions

Nobody now checks the return value from any of these functions, so
add an assertion at the beginning of the function and return void.

Link: https://lkml.kernel.org/r/20231108204605.745109-5-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Steve French <sfrench@samba.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/page-flags.h |  4 ++--
 mm/folio-compat.c          |  4 ++--
 mm/page-writeback.c        | 54 +++++++++++++++++++++-------------------------
 3 files changed, 29 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index a440062e9386..735cddc13d20 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -772,8 +772,8 @@ static __always_inline void SetPageUptodate(struct page *page)
 
 CLEARPAGEFLAG(Uptodate, uptodate, PF_NO_TAIL)
 
-bool __folio_start_writeback(struct folio *folio, bool keep_write);
-bool set_page_writeback(struct page *page);
+void __folio_start_writeback(struct folio *folio, bool keep_write);
+void set_page_writeback(struct page *page);
 
 #define folio_start_writeback(folio)			\
 	__folio_start_writeback(folio, false)
diff --git a/mm/folio-compat.c b/mm/folio-compat.c
index 10c3247542cb..aee3b9a16828 100644
--- a/mm/folio-compat.c
+++ b/mm/folio-compat.c
@@ -46,9 +46,9 @@ void mark_page_accessed(struct page *page)
 }
 EXPORT_SYMBOL(mark_page_accessed);
 
-bool set_page_writeback(struct page *page)
+void set_page_writeback(struct page *page)
 {
-	return folio_start_writeback(page_folio(page));
+	folio_start_writeback(page_folio(page));
 }
 EXPORT_SYMBOL(set_page_writeback);
 
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index ee2fd6a6af40..ca64bd513fa2 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2982,67 +2982,63 @@ bool __folio_end_writeback(struct folio *folio)
 	return ret;
 }
 
-bool __folio_start_writeback(struct folio *folio, bool keep_write)
+void __folio_start_writeback(struct folio *folio, bool keep_write)
 {
 	long nr = folio_nr_pages(folio);
 	struct address_space *mapping = folio_mapping(folio);
-	bool ret;
 	int access_ret;
 
+	VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio);
+
 	folio_memcg_lock(folio);
 	if (mapping && mapping_use_writeback_tags(mapping)) {
 		XA_STATE(xas, &mapping->i_pages, folio_index(folio));
 		struct inode *inode = mapping->host;
 		struct backing_dev_info *bdi = inode_to_bdi(inode);
 		unsigned long flags;
+		bool on_wblist;
 
 		xas_lock_irqsave(&xas, flags);
 		xas_load(&xas);
-		ret = folio_test_set_writeback(folio);
-		if (!ret) {
-			bool on_wblist;
+		folio_test_set_writeback(folio);
 
-			on_wblist = mapping_tagged(mapping,
-						   PAGECACHE_TAG_WRITEBACK);
+		on_wblist = mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK);
 
-			xas_set_mark(&xas, PAGECACHE_TAG_WRITEBACK);
-			if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) {
-				struct bdi_writeback *wb = inode_to_wb(inode);
-
-				wb_stat_mod(wb, WB_WRITEBACK, nr);
-				if (!on_wblist)
-					wb_inode_writeback_start(wb);
-			}
+		xas_set_mark(&xas, PAGECACHE_TAG_WRITEBACK);
+		if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) {
+			struct bdi_writeback *wb = inode_to_wb(inode);
 
-			/*
-			 * We can come through here when swapping
-			 * anonymous folios, so we don't necessarily
-			 * have an inode to track for sync.
-			 */
-			if (mapping->host && !on_wblist)
-				sb_mark_inode_writeback(mapping->host);
+			wb_stat_mod(wb, WB_WRITEBACK, nr);
+			if (!on_wblist)
+				wb_inode_writeback_start(wb);
 		}
+
+		/*
+		 * We can come through here when swapping anonymous
+		 * folios, so we don't necessarily have an inode to
+		 * track for sync.
+		 */
+		if (mapping->host && !on_wblist)
+			sb_mark_inode_writeback(mapping->host);
 		if (!folio_test_dirty(folio))
 			xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY);
 		if (!keep_write)
 			xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE);
 		xas_unlock_irqrestore(&xas, flags);
 	} else {
-		ret = folio_test_set_writeback(folio);
-	}
-	if (!ret) {
-		lruvec_stat_mod_folio(folio, NR_WRITEBACK, nr);
-		zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, nr);
+		folio_test_set_writeback(folio);
 	}
+
+	lruvec_stat_mod_folio(folio, NR_WRITEBACK, nr);
+	zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, nr);
 	folio_memcg_unlock(folio);
+
 	access_ret = arch_make_folio_accessible(folio);
 	/*
 	 * If writeback has been triggered on a page that cannot be made
 	 * accessible, it is too late to recover here.
 	 */
 	VM_BUG_ON_FOLIO(access_ret != 0, folio);
-
-	return ret;
 }
 EXPORT_SYMBOL(__folio_start_writeback);
 
-- 
cgit v1.2.3


From 16f5dfbc851b55b87101a20e181d4a14be3007d6 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 9 Nov 2023 21:15:07 +0000
Subject: gfp: include __GFP_NOWARN in GFP_NOWAIT

GFP_NOWAIT callers are always prepared for their allocations to fail
because they fail so frequently.  Forcing the callers to remember to add
__GFP_NOWARN is just annoying and leads to an endless stream of patches
for the places where we forgot to add it.

We can now remove __GFP_NOWARN from all the callers which specify
GFP_NOWAIT, but I'd rather wait a cycle and send patches to each
maintainer instead of creating a big pile of merge conflicts.

Link: https://lkml.kernel.org/r/20231109211507.2262419-1-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/gfp_types.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h
index 6583a58670c5..ae994534a12a 100644
--- a/include/linux/gfp_types.h
+++ b/include/linux/gfp_types.h
@@ -274,7 +274,8 @@ typedef unsigned int __bitwise gfp_t;
  * accounted to kmemcg.
  *
  * %GFP_NOWAIT is for kernel allocations that should not stall for direct
- * reclaim, start physical IO or use any filesystem callback.
+ * reclaim, start physical IO or use any filesystem callback.  It is very
+ * likely to fail to allocate memory, even for very small allocations.
  *
  * %GFP_NOIO will use direct reclaim to discard clean pages or slab pages
  * that do not require the starting of any physical IO.
@@ -325,7 +326,7 @@ typedef unsigned int __bitwise gfp_t;
 #define GFP_ATOMIC	(__GFP_HIGH|__GFP_KSWAPD_RECLAIM)
 #define GFP_KERNEL	(__GFP_RECLAIM | __GFP_IO | __GFP_FS)
 #define GFP_KERNEL_ACCOUNT (GFP_KERNEL | __GFP_ACCOUNT)
-#define GFP_NOWAIT	(__GFP_KSWAPD_RECLAIM)
+#define GFP_NOWAIT	(__GFP_KSWAPD_RECLAIM | __GFP_NOWARN)
 #define GFP_NOIO	(__GFP_RECLAIM)
 #define GFP_NOFS	(__GFP_RECLAIM | __GFP_IO)
 #define GFP_USER	(__GFP_RECLAIM | __GFP_IO | __GFP_FS | __GFP_HARDWALL)
-- 
cgit v1.2.3


From af7628d6ec196999175ecb3fdb38336489b0f88a Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Fri, 17 Nov 2023 16:14:47 +0000
Subject: fs: convert error_remove_page to error_remove_folio

There were already assertions that we were not passing a tail page to
error_remove_page(), so make the compiler enforce that by converting
everything to pass and use a folio.

Link: https://lkml.kernel.org/r/20231117161447.2461643-7-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 Documentation/filesystems/locking.rst |  4 ++--
 Documentation/filesystems/vfs.rst     |  6 +++---
 block/fops.c                          |  2 +-
 fs/afs/write.c                        |  2 +-
 fs/bcachefs/fs.c                      |  2 +-
 fs/btrfs/inode.c                      |  2 +-
 fs/ceph/addr.c                        |  4 ++--
 fs/ext2/inode.c                       |  2 +-
 fs/ext4/inode.c                       |  6 +++---
 fs/f2fs/compress.c                    |  2 +-
 fs/f2fs/inode.c                       |  2 +-
 fs/gfs2/aops.c                        |  4 ++--
 fs/hugetlbfs/inode.c                  |  6 +++---
 fs/nfs/file.c                         |  2 +-
 fs/ntfs/aops.c                        |  6 +++---
 fs/ocfs2/aops.c                       |  2 +-
 fs/xfs/xfs_aops.c                     |  2 +-
 fs/zonefs/file.c                      |  2 +-
 include/linux/fs.h                    |  2 +-
 include/linux/mm.h                    |  3 ++-
 mm/memory-failure.c                   | 10 +++++-----
 mm/shmem.c                            |  6 +++---
 mm/truncate.c                         |  9 ++++-----
 23 files changed, 44 insertions(+), 44 deletions(-)

(limited to 'include')

diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst
index 7be2900806c8..421daf837940 100644
--- a/Documentation/filesystems/locking.rst
+++ b/Documentation/filesystems/locking.rst
@@ -261,7 +261,7 @@ prototypes::
 			struct folio *src, enum migrate_mode);
 	int (*launder_folio)(struct folio *);
 	bool (*is_partially_uptodate)(struct folio *, size_t from, size_t count);
-	int (*error_remove_page)(struct address_space *, struct page *);
+	int (*error_remove_folio)(struct address_space *, struct folio *);
 	int (*swap_activate)(struct swap_info_struct *sis, struct file *f, sector_t *span)
 	int (*swap_deactivate)(struct file *);
 	int (*swap_rw)(struct kiocb *iocb, struct iov_iter *iter);
@@ -287,7 +287,7 @@ direct_IO:
 migrate_folio:		yes (both)
 launder_folio:		yes
 is_partially_uptodate:	yes
-error_remove_page:	yes
+error_remove_folio:	yes
 swap_activate:		no
 swap_deactivate:	no
 swap_rw:		yes, unlocks
diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst
index 99acc2e98673..dd99ce5912d8 100644
--- a/Documentation/filesystems/vfs.rst
+++ b/Documentation/filesystems/vfs.rst
@@ -823,7 +823,7 @@ cache in your filesystem.  The following members are defined:
 		bool (*is_partially_uptodate) (struct folio *, size_t from,
 					       size_t count);
 		void (*is_dirty_writeback)(struct folio *, bool *, bool *);
-		int (*error_remove_page) (struct mapping *mapping, struct page *page);
+		int (*error_remove_folio)(struct mapping *mapping, struct folio *);
 		int (*swap_activate)(struct swap_info_struct *sis, struct file *f, sector_t *span)
 		int (*swap_deactivate)(struct file *);
 		int (*swap_rw)(struct kiocb *iocb, struct iov_iter *iter);
@@ -1034,8 +1034,8 @@ cache in your filesystem.  The following members are defined:
 	VM if a folio should be treated as dirty or writeback for the
 	purposes of stalling.
 
-``error_remove_page``
-	normally set to generic_error_remove_page if truncation is ok
+``error_remove_folio``
+	normally set to generic_error_remove_folio if truncation is ok
 	for this address space.  Used for memory failure handling.
 	Setting this implies you deal with pages going away under you,
 	unless you have them locked or reference counts increased.
diff --git a/block/fops.c b/block/fops.c
index 0abaac705daf..0bdad1e8d514 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -500,7 +500,7 @@ const struct address_space_operations def_blk_aops = {
 	.readahead		= blkdev_readahead,
 	.writepages		= blkdev_writepages,
 	.is_partially_uptodate  = iomap_is_partially_uptodate,
-	.error_remove_page	= generic_error_remove_page,
+	.error_remove_folio	= generic_error_remove_folio,
 	.migrate_folio		= filemap_migrate_folio,
 };
 #endif /* CONFIG_BUFFER_HEAD */
diff --git a/fs/afs/write.c b/fs/afs/write.c
index 57d05d67f0c2..e87b52b1f34c 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -242,7 +242,7 @@ static void afs_kill_pages(struct address_space *mapping,
 		folio_clear_uptodate(folio);
 		folio_end_writeback(folio);
 		folio_lock(folio);
-		generic_error_remove_page(mapping, &folio->page);
+		generic_error_remove_folio(mapping, folio);
 		folio_unlock(folio);
 		folio_put(folio);
 
diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c
index 4d51be813509..df4a97b6637b 100644
--- a/fs/bcachefs/fs.c
+++ b/fs/bcachefs/fs.c
@@ -1103,7 +1103,7 @@ static const struct address_space_operations bch_address_space_operations = {
 #ifdef CONFIG_MIGRATION
 	.migrate_folio	= filemap_migrate_folio,
 #endif
-	.error_remove_page = generic_error_remove_page,
+	.error_remove_folio = generic_error_remove_folio,
 };
 
 struct bcachefs_fid {
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 9f5a9894f88f..ff7b4efca24f 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -10930,7 +10930,7 @@ static const struct address_space_operations btrfs_aops = {
 	.release_folio	= btrfs_release_folio,
 	.migrate_folio	= btrfs_migrate_folio,
 	.dirty_folio	= filemap_dirty_folio,
-	.error_remove_page = generic_error_remove_page,
+	.error_remove_folio = generic_error_remove_folio,
 	.swap_activate	= btrfs_swap_activate,
 	.swap_deactivate = btrfs_swap_deactivate,
 };
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 85be3bf18cdf..13af429ab030 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -907,8 +907,8 @@ static void writepages_finish(struct ceph_osd_request *req)
 			doutc(cl, "unlocking %p\n", page);
 
 			if (remove_page)
-				generic_error_remove_page(inode->i_mapping,
-							  page);
+				generic_error_remove_folio(inode->i_mapping,
+							  page_folio(page));
 
 			unlock_page(page);
 		}
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 464faf6c217e..5a4272b2c6b0 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -969,7 +969,7 @@ const struct address_space_operations ext2_aops = {
 	.writepages		= ext2_writepages,
 	.migrate_folio		= buffer_migrate_folio,
 	.is_partially_uptodate	= block_is_partially_uptodate,
-	.error_remove_page	= generic_error_remove_page,
+	.error_remove_folio	= generic_error_remove_folio,
 };
 
 static const struct address_space_operations ext2_dax_aops = {
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 61277f7f8722..d7729b17a66b 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3564,7 +3564,7 @@ static const struct address_space_operations ext4_aops = {
 	.direct_IO		= noop_direct_IO,
 	.migrate_folio		= buffer_migrate_folio,
 	.is_partially_uptodate  = block_is_partially_uptodate,
-	.error_remove_page	= generic_error_remove_page,
+	.error_remove_folio	= generic_error_remove_folio,
 	.swap_activate		= ext4_iomap_swap_activate,
 };
 
@@ -3581,7 +3581,7 @@ static const struct address_space_operations ext4_journalled_aops = {
 	.direct_IO		= noop_direct_IO,
 	.migrate_folio		= buffer_migrate_folio_norefs,
 	.is_partially_uptodate  = block_is_partially_uptodate,
-	.error_remove_page	= generic_error_remove_page,
+	.error_remove_folio	= generic_error_remove_folio,
 	.swap_activate		= ext4_iomap_swap_activate,
 };
 
@@ -3598,7 +3598,7 @@ static const struct address_space_operations ext4_da_aops = {
 	.direct_IO		= noop_direct_IO,
 	.migrate_folio		= buffer_migrate_folio,
 	.is_partially_uptodate  = block_is_partially_uptodate,
-	.error_remove_page	= generic_error_remove_page,
+	.error_remove_folio	= generic_error_remove_folio,
 	.swap_activate		= ext4_iomap_swap_activate,
 };
 
diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c
index 36e5dab6baae..6b2af514660d 100644
--- a/fs/f2fs/compress.c
+++ b/fs/f2fs/compress.c
@@ -1944,7 +1944,7 @@ void f2fs_invalidate_compress_pages(struct f2fs_sb_info *sbi, nid_t ino)
 				continue;
 			}
 
-			generic_error_remove_page(mapping, &folio->page);
+			generic_error_remove_folio(mapping, folio);
 			folio_unlock(folio);
 		}
 		folio_batch_release(&fbatch);
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 560bfcad1af2..a9eb3891f417 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -600,7 +600,7 @@ make_now:
 #ifdef CONFIG_F2FS_FS_COMPRESSION
 		inode->i_mapping->a_ops = &f2fs_compress_aops;
 		/*
-		 * generic_error_remove_page only truncates pages of regular
+		 * generic_error_remove_folio only truncates pages of regular
 		 * inode
 		 */
 		inode->i_mode |= S_IFREG;
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index ba8742dc91f8..5cffb079b87c 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -745,7 +745,7 @@ static const struct address_space_operations gfs2_aops = {
 	.bmap = gfs2_bmap,
 	.migrate_folio = filemap_migrate_folio,
 	.is_partially_uptodate = iomap_is_partially_uptodate,
-	.error_remove_page = generic_error_remove_page,
+	.error_remove_folio = generic_error_remove_folio,
 };
 
 static const struct address_space_operations gfs2_jdata_aops = {
@@ -758,7 +758,7 @@ static const struct address_space_operations gfs2_jdata_aops = {
 	.invalidate_folio = gfs2_invalidate_folio,
 	.release_folio = gfs2_release_folio,
 	.is_partially_uptodate = block_is_partially_uptodate,
-	.error_remove_page = generic_error_remove_page,
+	.error_remove_folio = generic_error_remove_folio,
 };
 
 void gfs2_set_aops(struct inode *inode)
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index f757d4f7ad98..36132c9125f9 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -1129,8 +1129,8 @@ static int hugetlbfs_migrate_folio(struct address_space *mapping,
 #define hugetlbfs_migrate_folio NULL
 #endif
 
-static int hugetlbfs_error_remove_page(struct address_space *mapping,
-				struct page *page)
+static int hugetlbfs_error_remove_folio(struct address_space *mapping,
+				struct folio *folio)
 {
 	return 0;
 }
@@ -1277,7 +1277,7 @@ static const struct address_space_operations hugetlbfs_aops = {
 	.write_end	= hugetlbfs_write_end,
 	.dirty_folio	= noop_dirty_folio,
 	.migrate_folio  = hugetlbfs_migrate_folio,
-	.error_remove_page	= hugetlbfs_error_remove_page,
+	.error_remove_folio	= hugetlbfs_error_remove_folio,
 };
 
 
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 3f9768810427..e8cccb94b927 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -567,7 +567,7 @@ const struct address_space_operations nfs_file_aops = {
 	.migrate_folio = nfs_migrate_folio,
 	.launder_folio = nfs_launder_folio,
 	.is_dirty_writeback = nfs_check_dirty_writeback,
-	.error_remove_page = generic_error_remove_page,
+	.error_remove_folio = generic_error_remove_folio,
 	.swap_activate = nfs_swap_activate,
 	.swap_deactivate = nfs_swap_deactivate,
 	.swap_rw = nfs_swap_rw,
diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c
index 71e31e789b29..70479ce915e8 100644
--- a/fs/ntfs/aops.c
+++ b/fs/ntfs/aops.c
@@ -1644,7 +1644,7 @@ const struct address_space_operations ntfs_normal_aops = {
 	.bmap		= ntfs_bmap,
 	.migrate_folio	= buffer_migrate_folio,
 	.is_partially_uptodate = block_is_partially_uptodate,
-	.error_remove_page = generic_error_remove_page,
+	.error_remove_folio = generic_error_remove_folio,
 };
 
 /*
@@ -1658,7 +1658,7 @@ const struct address_space_operations ntfs_compressed_aops = {
 #endif /* NTFS_RW */
 	.migrate_folio	= buffer_migrate_folio,
 	.is_partially_uptodate = block_is_partially_uptodate,
-	.error_remove_page = generic_error_remove_page,
+	.error_remove_folio = generic_error_remove_folio,
 };
 
 /*
@@ -1673,7 +1673,7 @@ const struct address_space_operations ntfs_mst_aops = {
 #endif /* NTFS_RW */
 	.migrate_folio	= buffer_migrate_folio,
 	.is_partially_uptodate	= block_is_partially_uptodate,
-	.error_remove_page = generic_error_remove_page,
+	.error_remove_folio = generic_error_remove_folio,
 };
 
 #ifdef NTFS_RW
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index ba790219d528..795997806326 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -2480,5 +2480,5 @@ const struct address_space_operations ocfs2_aops = {
 	.release_folio		= ocfs2_release_folio,
 	.migrate_folio		= buffer_migrate_folio,
 	.is_partially_uptodate	= block_is_partially_uptodate,
-	.error_remove_page	= generic_error_remove_page,
+	.error_remove_folio	= generic_error_remove_folio,
 };
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 465d7630bb21..813f85156b0c 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -584,7 +584,7 @@ const struct address_space_operations xfs_address_space_operations = {
 	.bmap			= xfs_vm_bmap,
 	.migrate_folio		= filemap_migrate_folio,
 	.is_partially_uptodate  = iomap_is_partially_uptodate,
-	.error_remove_page	= generic_error_remove_page,
+	.error_remove_folio	= generic_error_remove_folio,
 	.swap_activate		= xfs_iomap_swapfile_activate,
 };
 
diff --git a/fs/zonefs/file.c b/fs/zonefs/file.c
index b2c9b35df8f7..6ab2318a9c8e 100644
--- a/fs/zonefs/file.c
+++ b/fs/zonefs/file.c
@@ -180,7 +180,7 @@ const struct address_space_operations zonefs_file_aops = {
 	.invalidate_folio	= iomap_invalidate_folio,
 	.migrate_folio		= filemap_migrate_folio,
 	.is_partially_uptodate	= iomap_is_partially_uptodate,
-	.error_remove_page	= generic_error_remove_page,
+	.error_remove_folio	= generic_error_remove_folio,
 	.swap_activate		= zonefs_swap_activate,
 };
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 98b7a7a8c42e..31b2cf963db9 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -434,7 +434,7 @@ struct address_space_operations {
 	bool (*is_partially_uptodate) (struct folio *, size_t from,
 			size_t count);
 	void (*is_dirty_writeback) (struct folio *, bool *dirty, bool *wb);
-	int (*error_remove_page)(struct address_space *, struct page *);
+	int (*error_remove_folio)(struct address_space *, struct folio *);
 
 	/* swapfile support */
 	int (*swap_activate)(struct swap_info_struct *sis, struct file *file,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 64cd1ee4aacc..13a090271716 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2384,7 +2384,8 @@ extern void truncate_pagecache(struct inode *inode, loff_t new);
 extern void truncate_setsize(struct inode *inode, loff_t newsize);
 void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to);
 void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end);
-int generic_error_remove_page(struct address_space *mapping, struct page *page);
+int generic_error_remove_folio(struct address_space *mapping,
+		struct folio *folio);
 
 struct vm_area_struct *lock_mm_and_find_vma(struct mm_struct *mm,
 		unsigned long address, struct pt_regs *regs);
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 6aec94821fda..d8c853b35dbb 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -927,13 +927,13 @@ static int delete_from_lru_cache(struct folio *folio)
 	return -EIO;
 }
 
-static int truncate_error_page(struct folio *folio, unsigned long pfn,
+static int truncate_error_folio(struct folio *folio, unsigned long pfn,
 				struct address_space *mapping)
 {
 	int ret = MF_FAILED;
 
-	if (mapping->a_ops->error_remove_page) {
-		int err = mapping->a_ops->error_remove_page(mapping, &folio->page);
+	if (mapping->a_ops->error_remove_folio) {
+		int err = mapping->a_ops->error_remove_folio(mapping, folio);
 
 		if (err != 0)
 			pr_info("%#lx: Failed to punch page: %d\n", pfn, err);
@@ -1054,7 +1054,7 @@ static int me_pagecache_clean(struct page_state *ps, struct page *p)
 	 *
 	 * Open: to take i_rwsem or not for this? Right now we don't.
 	 */
-	ret = truncate_error_page(folio, page_to_pfn(p), mapping);
+	ret = truncate_error_folio(folio, page_to_pfn(p), mapping);
 	if (has_extra_refcount(ps, p, extra_pins))
 		ret = MF_FAILED;
 
@@ -1188,7 +1188,7 @@ static int me_huge_page(struct page_state *ps, struct page *p)
 
 	mapping = folio_mapping(folio);
 	if (mapping) {
-		res = truncate_error_page(folio, page_to_pfn(p), mapping);
+		res = truncate_error_folio(folio, page_to_pfn(p), mapping);
 		/* The page is kept in page cache. */
 		extra_pins = true;
 		folio_unlock(folio);
diff --git a/mm/shmem.c b/mm/shmem.c
index 91e2620148b2..97bc622da774 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -4445,8 +4445,8 @@ static void __init shmem_destroy_inodecache(void)
 }
 
 /* Keep the page in page cache instead of truncating it */
-static int shmem_error_remove_page(struct address_space *mapping,
-				   struct page *page)
+static int shmem_error_remove_folio(struct address_space *mapping,
+				   struct folio *folio)
 {
 	return 0;
 }
@@ -4461,7 +4461,7 @@ const struct address_space_operations shmem_aops = {
 #ifdef CONFIG_MIGRATION
 	.migrate_folio	= migrate_folio,
 #endif
-	.error_remove_page = shmem_error_remove_page,
+	.error_remove_folio = shmem_error_remove_folio,
 };
 EXPORT_SYMBOL(shmem_aops);
 
diff --git a/mm/truncate.c b/mm/truncate.c
index 52e3a703e7b2..725b150e47ac 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -250,10 +250,9 @@ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end)
 /*
  * Used to get rid of pages on hardware memory corruption.
  */
-int generic_error_remove_page(struct address_space *mapping, struct page *page)
+int generic_error_remove_folio(struct address_space *mapping,
+		struct folio *folio)
 {
-	VM_BUG_ON_PAGE(PageTail(page), page);
-
 	if (!mapping)
 		return -EINVAL;
 	/*
@@ -262,9 +261,9 @@ int generic_error_remove_page(struct address_space *mapping, struct page *page)
 	 */
 	if (!S_ISREG(mapping->host->i_mode))
 		return -EIO;
-	return truncate_inode_folio(mapping, page_folio(page));
+	return truncate_inode_folio(mapping, folio);
 }
-EXPORT_SYMBOL(generic_error_remove_page);
+EXPORT_SYMBOL(generic_error_remove_folio);
 
 /**
  * mapping_evict_folio() - Remove an unused folio from the page-cache.
-- 
cgit v1.2.3


From 022012dcf44209074af97b6ae531a10c08736b31 Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Mon, 20 Nov 2023 18:47:13 +0100
Subject: lib/stackdepot, kasan: add flags to __stack_depot_save and rename

Change the bool can_alloc argument of __stack_depot_save to a u32
  argument that accepts a set of flags.

The following patch will add another flag to stack_depot_save_flags
  besides the existing STACK_DEPOT_FLAG_CAN_ALLOC.

Also rename the function to stack_depot_save_flags, as
  __stack_depot_save is a cryptic name,

Link: https://lkml.kernel.org/r/645fa15239621eebbd3a10331e5864b718839512.1700502145.git.andreyknvl@google.com
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Reviewed-by: Alexander Potapenko <glider@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Marco Elver <elver@google.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/stackdepot.h | 36 +++++++++++++++++++++++++-----------
 lib/stackdepot.c           | 16 +++++++++++-----
 mm/kasan/common.c          |  7 ++++---
 mm/kasan/generic.c         |  9 +++++----
 mm/kasan/kasan.h           |  2 +-
 mm/kasan/tags.c            |  3 ++-
 6 files changed, 48 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h
index e58306783d8e..0b262e14144e 100644
--- a/include/linux/stackdepot.h
+++ b/include/linux/stackdepot.h
@@ -32,6 +32,17 @@ typedef u32 depot_stack_handle_t;
  */
 #define STACK_DEPOT_EXTRA_BITS 5
 
+typedef u32 depot_flags_t;
+
+/*
+ * Flags that can be passed to stack_depot_save_flags(); see the comment next
+ * to its declaration for more details.
+ */
+#define STACK_DEPOT_FLAG_CAN_ALLOC	((depot_flags_t)0x0001)
+
+#define STACK_DEPOT_FLAGS_NUM	1
+#define STACK_DEPOT_FLAGS_MASK	((depot_flags_t)((1 << STACK_DEPOT_FLAGS_NUM) - 1))
+
 /*
  * Using stack depot requires its initialization, which can be done in 3 ways:
  *
@@ -69,31 +80,34 @@ static inline int stack_depot_early_init(void)	{ return 0; }
 #endif
 
 /**
- * __stack_depot_save - Save a stack trace to stack depot
+ * stack_depot_save_flags - Save a stack trace to stack depot
  *
  * @entries:		Pointer to the stack trace
  * @nr_entries:		Number of frames in the stack
  * @alloc_flags:	Allocation GFP flags
- * @can_alloc:		Allocate stack pools (increased chance of failure if false)
+ * @depot_flags:	Stack depot flags
+ *
+ * Saves a stack trace from @entries array of size @nr_entries.
  *
- * Saves a stack trace from @entries array of size @nr_entries. If @can_alloc is
- * %true, stack depot can replenish the stack pools in case no space is left
- * (allocates using GFP flags of @alloc_flags). If @can_alloc is %false, avoids
- * any allocations and fails if no space is left to store the stack trace.
+ * If STACK_DEPOT_FLAG_CAN_ALLOC is set in @depot_flags, stack depot can
+ * replenish the stack pools in case no space is left (allocates using GFP
+ * flags of @alloc_flags). Otherwise, stack depot avoids any allocations and
+ * fails if no space is left to store the stack trace.
  *
  * If the provided stack trace comes from the interrupt context, only the part
  * up to the interrupt entry is saved.
  *
- * Context: Any context, but setting @can_alloc to %false is required if
+ * Context: Any context, but setting STACK_DEPOT_FLAG_CAN_ALLOC is required if
  *          alloc_pages() cannot be used from the current context. Currently
  *          this is the case for contexts where neither %GFP_ATOMIC nor
  *          %GFP_NOWAIT can be used (NMI, raw_spin_lock).
  *
  * Return: Handle of the stack struct stored in depot, 0 on failure
  */
-depot_stack_handle_t __stack_depot_save(unsigned long *entries,
-					unsigned int nr_entries,
-					gfp_t gfp_flags, bool can_alloc);
+depot_stack_handle_t stack_depot_save_flags(unsigned long *entries,
+					    unsigned int nr_entries,
+					    gfp_t gfp_flags,
+					    depot_flags_t depot_flags);
 
 /**
  * stack_depot_save - Save a stack trace to stack depot
@@ -103,7 +117,7 @@ depot_stack_handle_t __stack_depot_save(unsigned long *entries,
  * @alloc_flags:	Allocation GFP flags
  *
  * Context: Contexts where allocations via alloc_pages() are allowed.
- *          See __stack_depot_save() for more details.
+ *          See stack_depot_save_flags() for more details.
  *
  * Return: Handle of the stack trace stored in depot, 0 on failure
  */
diff --git a/lib/stackdepot.c b/lib/stackdepot.c
index 4bb0af423f82..59d61d5c09a7 100644
--- a/lib/stackdepot.c
+++ b/lib/stackdepot.c
@@ -450,19 +450,24 @@ static inline struct stack_record *find_stack(struct list_head *bucket,
 	return NULL;
 }
 
-depot_stack_handle_t __stack_depot_save(unsigned long *entries,
-					unsigned int nr_entries,
-					gfp_t alloc_flags, bool can_alloc)
+depot_stack_handle_t stack_depot_save_flags(unsigned long *entries,
+					    unsigned int nr_entries,
+					    gfp_t alloc_flags,
+					    depot_flags_t depot_flags)
 {
 	struct list_head *bucket;
 	struct stack_record *found = NULL;
 	depot_stack_handle_t handle = 0;
 	struct page *page = NULL;
 	void *prealloc = NULL;
+	bool can_alloc = depot_flags & STACK_DEPOT_FLAG_CAN_ALLOC;
 	bool need_alloc = false;
 	unsigned long flags;
 	u32 hash;
 
+	if (WARN_ON(depot_flags & ~STACK_DEPOT_FLAGS_MASK))
+		return 0;
+
 	/*
 	 * If this stack trace is from an interrupt, including anything before
 	 * interrupt entry usually leads to unbounded stack depot growth.
@@ -541,13 +546,14 @@ exit:
 		handle = found->handle.handle;
 	return handle;
 }
-EXPORT_SYMBOL_GPL(__stack_depot_save);
+EXPORT_SYMBOL_GPL(stack_depot_save_flags);
 
 depot_stack_handle_t stack_depot_save(unsigned long *entries,
 				      unsigned int nr_entries,
 				      gfp_t alloc_flags)
 {
-	return __stack_depot_save(entries, nr_entries, alloc_flags, true);
+	return stack_depot_save_flags(entries, nr_entries, alloc_flags,
+				      STACK_DEPOT_FLAG_CAN_ALLOC);
 }
 EXPORT_SYMBOL_GPL(stack_depot_save);
 
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index 256930da578a..825a0240ec02 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -22,6 +22,7 @@
 #include <linux/sched.h>
 #include <linux/sched/task_stack.h>
 #include <linux/slab.h>
+#include <linux/stackdepot.h>
 #include <linux/stacktrace.h>
 #include <linux/string.h>
 #include <linux/types.h>
@@ -37,19 +38,19 @@ struct slab *kasan_addr_to_slab(const void *addr)
 	return NULL;
 }
 
-depot_stack_handle_t kasan_save_stack(gfp_t flags, bool can_alloc)
+depot_stack_handle_t kasan_save_stack(gfp_t flags, depot_flags_t depot_flags)
 {
 	unsigned long entries[KASAN_STACK_DEPTH];
 	unsigned int nr_entries;
 
 	nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 0);
-	return __stack_depot_save(entries, nr_entries, flags, can_alloc);
+	return stack_depot_save_flags(entries, nr_entries, flags, depot_flags);
 }
 
 void kasan_set_track(struct kasan_track *track, gfp_t flags)
 {
 	track->pid = current->pid;
-	track->stack = kasan_save_stack(flags, true);
+	track->stack = kasan_save_stack(flags, STACK_DEPOT_FLAG_CAN_ALLOC);
 }
 
 #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
diff --git a/mm/kasan/generic.c b/mm/kasan/generic.c
index 4d837ab83f08..5d168c9afb32 100644
--- a/mm/kasan/generic.c
+++ b/mm/kasan/generic.c
@@ -25,6 +25,7 @@
 #include <linux/sched.h>
 #include <linux/sched/task_stack.h>
 #include <linux/slab.h>
+#include <linux/stackdepot.h>
 #include <linux/stacktrace.h>
 #include <linux/string.h>
 #include <linux/types.h>
@@ -472,7 +473,7 @@ size_t kasan_metadata_size(struct kmem_cache *cache, bool in_object)
 			sizeof(struct kasan_free_meta) : 0);
 }
 
-static void __kasan_record_aux_stack(void *addr, bool can_alloc)
+static void __kasan_record_aux_stack(void *addr, depot_flags_t depot_flags)
 {
 	struct slab *slab = kasan_addr_to_slab(addr);
 	struct kmem_cache *cache;
@@ -489,17 +490,17 @@ static void __kasan_record_aux_stack(void *addr, bool can_alloc)
 		return;
 
 	alloc_meta->aux_stack[1] = alloc_meta->aux_stack[0];
-	alloc_meta->aux_stack[0] = kasan_save_stack(0, can_alloc);
+	alloc_meta->aux_stack[0] = kasan_save_stack(0, depot_flags);
 }
 
 void kasan_record_aux_stack(void *addr)
 {
-	return __kasan_record_aux_stack(addr, true);
+	return __kasan_record_aux_stack(addr, STACK_DEPOT_FLAG_CAN_ALLOC);
 }
 
 void kasan_record_aux_stack_noalloc(void *addr)
 {
-	return __kasan_record_aux_stack(addr, false);
+	return __kasan_record_aux_stack(addr, 0);
 }
 
 void kasan_save_alloc_info(struct kmem_cache *cache, void *object, gfp_t flags)
diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
index 8b06bab5c406..b29d46b83d1f 100644
--- a/mm/kasan/kasan.h
+++ b/mm/kasan/kasan.h
@@ -368,7 +368,7 @@ static inline void kasan_init_cache_meta(struct kmem_cache *cache, unsigned int
 static inline void kasan_init_object_meta(struct kmem_cache *cache, const void *object) { }
 #endif
 
-depot_stack_handle_t kasan_save_stack(gfp_t flags, bool can_alloc);
+depot_stack_handle_t kasan_save_stack(gfp_t flags, depot_flags_t depot_flags);
 void kasan_set_track(struct kasan_track *track, gfp_t flags);
 void kasan_save_alloc_info(struct kmem_cache *cache, void *object, gfp_t flags);
 void kasan_save_free_info(struct kmem_cache *cache, void *object);
diff --git a/mm/kasan/tags.c b/mm/kasan/tags.c
index 7dcfe341d48e..4fd32121b0fd 100644
--- a/mm/kasan/tags.c
+++ b/mm/kasan/tags.c
@@ -13,6 +13,7 @@
 #include <linux/memblock.h>
 #include <linux/memory.h>
 #include <linux/mm.h>
+#include <linux/stackdepot.h>
 #include <linux/static_key.h>
 #include <linux/string.h>
 #include <linux/types.h>
@@ -101,7 +102,7 @@ static void save_stack_info(struct kmem_cache *cache, void *object,
 	struct kasan_stack_ring_entry *entry;
 	void *old_ptr;
 
-	stack = kasan_save_stack(gfp_flags, true);
+	stack = kasan_save_stack(gfp_flags, STACK_DEPOT_FLAG_CAN_ALLOC);
 
 	/*
 	 * Prevent save_stack_info() from modifying stack ring
-- 
cgit v1.2.3


From 410b764f89f59cce858d94fc781b68c1f27a0ca9 Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Mon, 20 Nov 2023 18:47:14 +0100
Subject: lib/stackdepot: add refcount for records

Add a reference counter for how many times a stack records has been
  added to stack depot.

Add a new STACK_DEPOT_FLAG_GET flag to stack_depot_save_flags that
  instructs the stack depot to increment the refcount.

Do not yet decrement the refcount; this is implemented in one of the
  following patches.

Do not yet enable any users to use the flag to avoid overflowing the
  refcount.

This is preparatory patch for implementing the eviction of stack records
  from the stack depot.

Link: https://lkml.kernel.org/r/a3fc14a2359d019d2a008d4ff8b46a665371ffee.1700502145.git.andreyknvl@google.com
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Reviewed-by: Alexander Potapenko <glider@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Marco Elver <elver@google.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/stackdepot.h | 13 ++++++++++---
 lib/stackdepot.c           | 12 ++++++++++--
 2 files changed, 20 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h
index 0b262e14144e..611716702d73 100644
--- a/include/linux/stackdepot.h
+++ b/include/linux/stackdepot.h
@@ -39,8 +39,9 @@ typedef u32 depot_flags_t;
  * to its declaration for more details.
  */
 #define STACK_DEPOT_FLAG_CAN_ALLOC	((depot_flags_t)0x0001)
+#define STACK_DEPOT_FLAG_GET		((depot_flags_t)0x0002)
 
-#define STACK_DEPOT_FLAGS_NUM	1
+#define STACK_DEPOT_FLAGS_NUM	2
 #define STACK_DEPOT_FLAGS_MASK	((depot_flags_t)((1 << STACK_DEPOT_FLAGS_NUM) - 1))
 
 /*
@@ -94,6 +95,9 @@ static inline int stack_depot_early_init(void)	{ return 0; }
  * flags of @alloc_flags). Otherwise, stack depot avoids any allocations and
  * fails if no space is left to store the stack trace.
  *
+ * If STACK_DEPOT_FLAG_GET is set in @depot_flags, stack depot will increment
+ * the refcount on the saved stack trace if it already exists in stack depot.
+ *
  * If the provided stack trace comes from the interrupt context, only the part
  * up to the interrupt entry is saved.
  *
@@ -116,8 +120,11 @@ depot_stack_handle_t stack_depot_save_flags(unsigned long *entries,
  * @nr_entries:		Number of frames in the stack
  * @alloc_flags:	Allocation GFP flags
  *
- * Context: Contexts where allocations via alloc_pages() are allowed.
- *          See stack_depot_save_flags() for more details.
+ * Does not increment the refcount on the saved stack trace; see
+ * stack_depot_save_flags() for more details.
+ *
+ * Context: Contexts where allocations via alloc_pages() are allowed;
+ *          see stack_depot_save_flags() for more details.
  *
  * Return: Handle of the stack trace stored in depot, 0 on failure
  */
diff --git a/lib/stackdepot.c b/lib/stackdepot.c
index 59d61d5c09a7..911dee11bf39 100644
--- a/lib/stackdepot.c
+++ b/lib/stackdepot.c
@@ -23,6 +23,7 @@
 #include <linux/mutex.h>
 #include <linux/percpu.h>
 #include <linux/printk.h>
+#include <linux/refcount.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/stacktrace.h>
@@ -60,6 +61,7 @@ struct stack_record {
 	u32 hash;			/* Hash in hash table */
 	u32 size;			/* Number of stored frames */
 	union handle_parts handle;
+	refcount_t count;
 	unsigned long entries[CONFIG_STACKDEPOT_MAX_FRAMES];	/* Frames */
 };
 
@@ -373,6 +375,7 @@ depot_alloc_stack(unsigned long *entries, int size, u32 hash, void **prealloc)
 	stack->hash = hash;
 	stack->size = size;
 	/* stack->handle is already filled in by depot_init_pool(). */
+	refcount_set(&stack->count, 1);
 	memcpy(stack->entries, entries, flex_array_size(stack, entries, size));
 
 	/*
@@ -489,6 +492,8 @@ depot_stack_handle_t stack_depot_save_flags(unsigned long *entries,
 	/* Fast path: look the stack trace up without full locking. */
 	found = find_stack(bucket, entries, nr_entries, hash);
 	if (found) {
+		if (depot_flags & STACK_DEPOT_FLAG_GET)
+			refcount_inc(&found->count);
 		read_unlock_irqrestore(&pool_rwlock, flags);
 		goto exit;
 	}
@@ -528,12 +533,15 @@ depot_stack_handle_t stack_depot_save_flags(unsigned long *entries,
 			list_add(&new->list, bucket);
 			found = new;
 		}
-	} else if (prealloc) {
+	} else {
+		if (depot_flags & STACK_DEPOT_FLAG_GET)
+			refcount_inc(&found->count);
 		/*
 		 * Stack depot already contains this stack trace, but let's
 		 * keep the preallocated memory for future.
 		 */
-		depot_keep_new_pool(&prealloc);
+		if (prealloc)
+			depot_keep_new_pool(&prealloc);
 	}
 
 	write_unlock_irqrestore(&pool_rwlock, flags);
-- 
cgit v1.2.3


From 108be8def46e9422f5a5abc96b0ab8fb6b3fb344 Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Mon, 20 Nov 2023 18:47:15 +0100
Subject: lib/stackdepot: allow users to evict stack traces

Add stack_depot_put, a function that decrements the reference counter on a
stack record and removes it from the stack depot once the counter reaches
0.

Internally, when removing a stack record, the function unlinks it from the
hash table bucket and returns to the freelist.

With this change, the users of stack depot can call stack_depot_put when
keeping a stack trace in the stack depot is not needed anymore.  This
allows avoiding polluting the stack depot with irrelevant stack traces and
thus have more space to store the relevant ones before the stack depot
reaches its capacity.

Link: https://lkml.kernel.org/r/1d1ad5692ee43d4fc2b3fd9d221331d30b36123f.1700502145.git.andreyknvl@google.com
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Marco Elver <elver@google.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/stackdepot.h | 14 ++++++++++++++
 lib/stackdepot.c           | 37 ++++++++++++++++++++++++++++++++++++-
 2 files changed, 50 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h
index 611716702d73..a6796f178913 100644
--- a/include/linux/stackdepot.h
+++ b/include/linux/stackdepot.h
@@ -97,6 +97,8 @@ static inline int stack_depot_early_init(void)	{ return 0; }
  *
  * If STACK_DEPOT_FLAG_GET is set in @depot_flags, stack depot will increment
  * the refcount on the saved stack trace if it already exists in stack depot.
+ * Users of this flag must also call stack_depot_put() when keeping the stack
+ * trace is no longer required to avoid overflowing the refcount.
  *
  * If the provided stack trace comes from the interrupt context, only the part
  * up to the interrupt entry is saved.
@@ -162,6 +164,18 @@ void stack_depot_print(depot_stack_handle_t stack);
 int stack_depot_snprint(depot_stack_handle_t handle, char *buf, size_t size,
 		       int spaces);
 
+/**
+ * stack_depot_put - Drop a reference to a stack trace from stack depot
+ *
+ * @handle:	Stack depot handle returned from stack_depot_save()
+ *
+ * The stack trace is evicted from stack depot once all references to it have
+ * been dropped (once the number of stack_depot_evict() calls matches the
+ * number of stack_depot_save_flags() calls with STACK_DEPOT_FLAG_GET set for
+ * this stack trace).
+ */
+void stack_depot_put(depot_stack_handle_t handle);
+
 /**
  * stack_depot_set_extra_bits - Set extra bits in a stack depot handle
  *
diff --git a/lib/stackdepot.c b/lib/stackdepot.c
index 911dee11bf39..c1b31160f4b4 100644
--- a/lib/stackdepot.c
+++ b/lib/stackdepot.c
@@ -394,7 +394,7 @@ static struct stack_record *depot_fetch_stack(depot_stack_handle_t handle)
 	size_t offset = parts.offset << DEPOT_STACK_ALIGN;
 	struct stack_record *stack;
 
-	lockdep_assert_held_read(&pool_rwlock);
+	lockdep_assert_held(&pool_rwlock);
 
 	if (parts.pool_index > pools_num) {
 		WARN(1, "pool index %d out of bounds (%d) for stack id %08x\n",
@@ -410,6 +410,14 @@ static struct stack_record *depot_fetch_stack(depot_stack_handle_t handle)
 	return stack;
 }
 
+/* Links stack into the freelist. */
+static void depot_free_stack(struct stack_record *stack)
+{
+	lockdep_assert_held_write(&pool_rwlock);
+
+	list_add(&stack->list, &free_stacks);
+}
+
 /* Calculates the hash for a stack. */
 static inline u32 hash_stack(unsigned long *entries, unsigned int size)
 {
@@ -592,6 +600,33 @@ unsigned int stack_depot_fetch(depot_stack_handle_t handle,
 }
 EXPORT_SYMBOL_GPL(stack_depot_fetch);
 
+void stack_depot_put(depot_stack_handle_t handle)
+{
+	struct stack_record *stack;
+	unsigned long flags;
+
+	if (!handle || stack_depot_disabled)
+		return;
+
+	write_lock_irqsave(&pool_rwlock, flags);
+
+	stack = depot_fetch_stack(handle);
+	if (WARN_ON(!stack))
+		goto out;
+
+	if (refcount_dec_and_test(&stack->count)) {
+		/* Unlink stack from the hash table. */
+		list_del(&stack->list);
+
+		/* Free stack. */
+		depot_free_stack(stack);
+	}
+
+out:
+	write_unlock_irqrestore(&pool_rwlock, flags);
+}
+EXPORT_SYMBOL_GPL(stack_depot_put);
+
 void stack_depot_print(depot_stack_handle_t stack)
 {
 	unsigned long *entries;
-- 
cgit v1.2.3


From 95a2ac937013cc3aaaea02abcdd167b96874548d Mon Sep 17 00:00:00 2001
From: Sumanth Korikkar <sumanthk@linux.ibm.com>
Date: Mon, 20 Nov 2023 15:53:54 +0100
Subject: mm: use vmem_altmap code without CONFIG_ZONE_DEVICE

vmem_altmap_free() and vmem_altmap_offset() could be utlized without
CONFIG_ZONE_DEVICE enabled.  For example,
mm/memory_hotplug.c:__add_pages() relies on that.  The altmap is no longer
restricted to ZONE_DEVICE handling, but instead depends on
CONFIG_SPARSEMEM_VMEMMAP.

When CONFIG_SPARSEMEM_VMEMMAP is disabled, these functions are defined as
inline stubs, ensuring compatibility with configurations that do not use
sparsemem vmemmap.  Without it, lkp reported the following:

ld: arch/x86/mm/init_64.o: in function `remove_pagetable':
init_64.c:(.meminit.text+0xfc7): undefined reference to
`vmem_altmap_free'

Link: https://lkml.kernel.org/r/20231120145354.308999-4-sumanthk@linux.ibm.com
Signed-off-by: Sumanth Korikkar <sumanthk@linux.ibm.com>
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202311180545.VeyRXEDq-lkp@intel.com/
Reviewed-by: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/memremap.h | 12 ------------
 include/linux/mm.h       | 26 ++++++++++++++++++++++++++
 mm/memremap.c            | 14 +-------------
 3 files changed, 27 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index 1314d9c5f05b..744c830f4b13 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -196,8 +196,6 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
 		struct dev_pagemap *pgmap);
 bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn);
 
-unsigned long vmem_altmap_offset(struct vmem_altmap *altmap);
-void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns);
 unsigned long memremap_compat_align(void);
 #else
 static inline void *devm_memremap_pages(struct device *dev,
@@ -228,16 +226,6 @@ static inline bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn)
 	return false;
 }
 
-static inline unsigned long vmem_altmap_offset(struct vmem_altmap *altmap)
-{
-	return 0;
-}
-
-static inline void vmem_altmap_free(struct vmem_altmap *altmap,
-		unsigned long nr_pfns)
-{
-}
-
 /* when memremap_pages() is disabled all archs can remap a single page */
 static inline unsigned long memremap_compat_align(void)
 {
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 13a090271716..a422cc123a2d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3871,6 +3871,32 @@ void vmemmap_free(unsigned long start, unsigned long end,
 		struct vmem_altmap *altmap);
 #endif
 
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+static inline unsigned long vmem_altmap_offset(struct vmem_altmap *altmap)
+{
+	/* number of pfns from base where pfn_to_page() is valid */
+	if (altmap)
+		return altmap->reserve + altmap->free;
+	return 0;
+}
+
+static inline void vmem_altmap_free(struct vmem_altmap *altmap,
+				    unsigned long nr_pfns)
+{
+	altmap->alloc -= nr_pfns;
+}
+#else
+static inline unsigned long vmem_altmap_offset(struct vmem_altmap *altmap)
+{
+	return 0;
+}
+
+static inline void vmem_altmap_free(struct vmem_altmap *altmap,
+				    unsigned long nr_pfns)
+{
+}
+#endif
+
 #define VMEMMAP_RESERVE_NR	2
 #ifdef CONFIG_ARCH_WANT_OPTIMIZE_DAX_VMEMMAP
 static inline bool __vmemmap_can_optimize(struct vmem_altmap *altmap,
diff --git a/mm/memremap.c b/mm/memremap.c
index bee85560a243..9531faa92a7c 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -7,6 +7,7 @@
 #include <linux/memremap.h>
 #include <linux/pfn_t.h>
 #include <linux/swap.h>
+#include <linux/mm.h>
 #include <linux/mmzone.h>
 #include <linux/swapops.h>
 #include <linux/types.h>
@@ -422,19 +423,6 @@ void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap)
 }
 EXPORT_SYMBOL_GPL(devm_memunmap_pages);
 
-unsigned long vmem_altmap_offset(struct vmem_altmap *altmap)
-{
-	/* number of pfns from base where pfn_to_page() is valid */
-	if (altmap)
-		return altmap->reserve + altmap->free;
-	return 0;
-}
-
-void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns)
-{
-	altmap->alloc -= nr_pfns;
-}
-
 /**
  * get_dev_pagemap() - take a new live reference on the dev_pagemap for @pfn
  * @pfn: page frame number to lookup page_map
-- 
cgit v1.2.3


From 38ca8a185389716e9f7566bce4bb0085f71da61d Mon Sep 17 00:00:00 2001
From: Alexander Gordeev <agordeev@linux.ibm.com>
Date: Tue, 21 Nov 2023 20:43:49 +0100
Subject: pgtable: fix s390 ptdesc field comments

Patch series "minor ptdesc updates", v3.


This patch (of 2):

Since commit d08d4e7cd6bf ("s390/mm: use full 4KB page for 2KB PTE") there
is no fragmented page tracking on s390.  Fix the corresponding comments.

Link: https://lkml.kernel.org/r/cover.1700594815.git.agordeev@linux.ibm.com
Link: https://lkml.kernel.org/r/2eead241f3a45bed26c7911cf66bded1e35670b8.1700594815.git.agordeev@linux.ibm.com
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
Suggested-by: Heiko Carstens <hca@linux.ibm.com>
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Cc: Vishal Moola (Oracle) <vishal.moola@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mm_types.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 957ce38768b2..fbec64036baa 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -401,11 +401,11 @@ FOLIO_MATCH(compound_head, _head_2a);
  * @pmd_huge_pte:     Protected by ptdesc->ptl, used for THPs.
  * @__page_mapping:   Aliases with page->mapping. Unused for page tables.
  * @pt_mm:            Used for x86 pgds.
- * @pt_frag_refcount: For fragmented page table tracking. Powerpc and s390 only.
+ * @pt_frag_refcount: For fragmented page table tracking. Powerpc only.
  * @_pt_pad_2:        Padding to ensure proper alignment.
  * @ptl:              Lock for the page table.
  * @__page_type:      Same as page->page_type. Unused for page tables.
- * @_refcount:        Same as page refcount. Used for s390 page tables.
+ * @_refcount:        Same as page refcount.
  * @pt_memcg_data:    Memcg data. Tracked for page tables here.
  *
  * This struct overlays struct page for now. Do not modify without a good
-- 
cgit v1.2.3


From f7dd74ac239aad5ef7575ea03c45fd7956e00285 Mon Sep 17 00:00:00 2001
From: Alexander Gordeev <agordeev@linux.ibm.com>
Date: Tue, 21 Nov 2023 20:43:50 +0100
Subject: pgtable: rename ptdesc _refcount field to __page_refcount

Rename ptdesc _refcount field to __page_refcount similar to the other
unused page fields.

Link: https://lkml.kernel.org/r/982bdc652ba79a606c3d01c905766e7e076b3315.1700594815.git.agordeev@linux.ibm.com
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
Suggested-by: Vishal Moola <vishal.moola@gmail.com>
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mm_types.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index fbec64036baa..ef18d2b25378 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -405,7 +405,7 @@ FOLIO_MATCH(compound_head, _head_2a);
  * @_pt_pad_2:        Padding to ensure proper alignment.
  * @ptl:              Lock for the page table.
  * @__page_type:      Same as page->page_type. Unused for page tables.
- * @_refcount:        Same as page refcount.
+ * @__page_refcount:  Same as page refcount.
  * @pt_memcg_data:    Memcg data. Tracked for page tables here.
  *
  * This struct overlays struct page for now. Do not modify without a good
@@ -438,7 +438,7 @@ struct ptdesc {
 #endif
 	};
 	unsigned int __page_type;
-	atomic_t _refcount;
+	atomic_t __page_refcount;
 #ifdef CONFIG_MEMCG
 	unsigned long pt_memcg_data;
 #endif
@@ -452,7 +452,7 @@ TABLE_MATCH(compound_head, _pt_pad_1);
 TABLE_MATCH(mapping, __page_mapping);
 TABLE_MATCH(rcu_head, pt_rcu_head);
 TABLE_MATCH(page_type, __page_type);
-TABLE_MATCH(_refcount, _refcount);
+TABLE_MATCH(_refcount, __page_refcount);
 #ifdef CONFIG_MEMCG
 TABLE_MATCH(memcg_data, pt_memcg_data);
 #endif
-- 
cgit v1.2.3


From 7679e14098c9c3c8118a7130d6e1e9cfe2565c04 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 23 Nov 2023 19:23:17 +0200
Subject: mm: list_lru: Update kernel documentation to follow the requirements

kernel-doc is not happy about documentation in list_lru.h:

list_lru.h:90: warning: Function parameter or member 'lru' not described in 'list_lru_add'
list_lru.h:90: warning: Excess function parameter 'list_lru' description in 'list_lru_add'
list_lru.h:90: warning: No description found for return value of 'list_lru_add'
list_lru.h:103: warning: Function parameter or member 'lru' not described in 'list_lru_del'
list_lru.h:103: warning: Excess function parameter 'list_lru' description in 'list_lru_del'
list_lru.h:103: warning: No description found for return value of 'list_lru_del'
list_lru.h:116: warning: No description found for return value of 'list_lru_count_one'
list_lru.h:168: warning: No description found for return value of 'list_lru_walk_one'
list_lru.h:185: warning: No description found for return value of 'list_lru_walk_one_irq'

Fix the documentation accordingly.

While at it, fix the references to the parameters in functions
inside the long descriptions, on which the above script is not
complaining (yet?).

Link: https://lkml.kernel.org/r/20231123172320.2434780-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/list_lru.h | 36 +++++++++++++++++++-----------------
 1 file changed, 19 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index b35968ee9fb5..db86ad78d428 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -73,7 +73,7 @@ void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *paren
 
 /**
  * list_lru_add: add an element to the lru list's tail
- * @list_lru: the lru pointer
+ * @lru: the lru pointer
  * @item: the item to be added.
  *
  * If the element is already part of a list, this function returns doing
@@ -83,22 +83,22 @@ void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *paren
  * the caller organize itself in a way that elements can be in more than
  * one type of list, it is up to the caller to fully remove the item from
  * the previous list (with list_lru_del() for instance) before moving it
- * to @list_lru
+ * to @lru.
  *
- * Return value: true if the list was updated, false otherwise
+ * Return: true if the list was updated, false otherwise
  */
 bool list_lru_add(struct list_lru *lru, struct list_head *item);
 
 /**
  * list_lru_del: delete an element to the lru list
- * @list_lru: the lru pointer
+ * @lru: the lru pointer
  * @item: the item to be deleted.
  *
- * This function works analogously as list_lru_add in terms of list
+ * This function works analogously as list_lru_add() in terms of list
  * manipulation. The comments about an element already pertaining to
- * a list are also valid for list_lru_del.
+ * a list are also valid for list_lru_del().
  *
- * Return value: true if the list was updated, false otherwise
+ * Return: true if the list was updated, false otherwise
  */
 bool list_lru_del(struct list_lru *lru, struct list_head *item);
 
@@ -108,9 +108,11 @@ bool list_lru_del(struct list_lru *lru, struct list_head *item);
  * @nid: the node id to count from.
  * @memcg: the cgroup to count from.
  *
- * Always return a non-negative number, 0 for empty lists. There is no
- * guarantee that the list is not updated while the count is being computed.
- * Callers that want such a guarantee need to provide an outer lock.
+ * There is no guarantee that the list is not updated while the count is being
+ * computed. Callers that want such a guarantee need to provide an outer lock.
+ *
+ * Return: 0 for empty lists, otherwise the number of objects
+ * currently held by @lru.
  */
 unsigned long list_lru_count_one(struct list_lru *lru,
 				 int nid, struct mem_cgroup *memcg);
@@ -141,7 +143,7 @@ typedef enum lru_status (*list_lru_walk_cb)(struct list_head *item,
 		struct list_lru_one *list, spinlock_t *lock, void *cb_arg);
 
 /**
- * list_lru_walk_one: walk a list_lru, isolating and disposing freeable items.
+ * list_lru_walk_one: walk a @lru, isolating and disposing freeable items.
  * @lru: the lru pointer.
  * @nid: the node id to scan from.
  * @memcg: the cgroup to scan from.
@@ -150,24 +152,24 @@ typedef enum lru_status (*list_lru_walk_cb)(struct list_head *item,
  * @cb_arg: opaque type that will be passed to @isolate
  * @nr_to_walk: how many items to scan.
  *
- * This function will scan all elements in a particular list_lru, calling the
+ * This function will scan all elements in a particular @lru, calling the
  * @isolate callback for each of those items, along with the current list
  * spinlock and a caller-provided opaque. The @isolate callback can choose to
  * drop the lock internally, but *must* return with the lock held. The callback
- * will return an enum lru_status telling the list_lru infrastructure what to
+ * will return an enum lru_status telling the @lru infrastructure what to
  * do with the object being scanned.
  *
- * Please note that nr_to_walk does not mean how many objects will be freed,
+ * Please note that @nr_to_walk does not mean how many objects will be freed,
  * just how many objects will be scanned.
  *
- * Return value: the number of objects effectively removed from the LRU.
+ * Return: the number of objects effectively removed from the LRU.
  */
 unsigned long list_lru_walk_one(struct list_lru *lru,
 				int nid, struct mem_cgroup *memcg,
 				list_lru_walk_cb isolate, void *cb_arg,
 				unsigned long *nr_to_walk);
 /**
- * list_lru_walk_one_irq: walk a list_lru, isolating and disposing freeable items.
+ * list_lru_walk_one_irq: walk a @lru, isolating and disposing freeable items.
  * @lru: the lru pointer.
  * @nid: the node id to scan from.
  * @memcg: the cgroup to scan from.
@@ -176,7 +178,7 @@ unsigned long list_lru_walk_one(struct list_lru *lru,
  * @cb_arg: opaque type that will be passed to @isolate
  * @nr_to_walk: how many items to scan.
  *
- * Same as @list_lru_walk_one except that the spinlock is acquired with
+ * Same as list_lru_walk_one() except that the spinlock is acquired with
  * spin_lock_irq().
  */
 unsigned long list_lru_walk_one_irq(struct list_lru *lru,
-- 
cgit v1.2.3


From 61a7a5e25fe79b6c43f1c49705a0294be113c4a5 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Mon, 30 Oct 2023 16:57:10 +0100
Subject: introduce for_other_threads(p, t)

Cosmetic, but imho it makes the usage look more clear and simple, the new
helper doesn't require to initialize "t".

After this change while_each_thread() has only 3 users, and it is only
used in the do/while loops.

Link: https://lkml.kernel.org/r/20231030155710.GA9095@redhat.com
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Christian Brauner <brauner@kernel.org>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/exec.c                    |  3 +--
 include/linux/sched/signal.h |  3 +++
 kernel/signal.c              | 11 ++++-------
 3 files changed, 8 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/fs/exec.c b/fs/exec.c
index 4aa19b24f281..ee43597cb453 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1578,11 +1578,10 @@ static void check_unsafe_exec(struct linux_binprm *bprm)
 	 * will be able to manipulate the current directory, etc.
 	 * It would be nice to force an unshare instead...
 	 */
-	t = p;
 	n_fs = 1;
 	spin_lock(&p->fs->lock);
 	rcu_read_lock();
-	while_each_thread(p, t) {
+	for_other_threads(p, t) {
 		if (t->fs == p->fs)
 			n_fs++;
 	}
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 3499c1a8b929..41d6759d6a4a 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -646,6 +646,9 @@ extern bool current_is_single_threaded(void);
 #define while_each_thread(g, t) \
 	while ((t = next_thread(t)) != g)
 
+#define for_other_threads(p, t)	\
+	for (t = p; (t = next_thread(t)) != p; )
+
 #define __for_each_thread(signal, t)	\
 	list_for_each_entry_rcu(t, &(signal)->thread_head, thread_node, \
 		lockdep_is_held(&tasklist_lock))
diff --git a/kernel/signal.c b/kernel/signal.c
index 47a7602dfe8d..5aa216e841a2 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1376,12 +1376,12 @@ int force_sig_info(struct kernel_siginfo *info)
  */
 int zap_other_threads(struct task_struct *p)
 {
-	struct task_struct *t = p;
+	struct task_struct *t;
 	int count = 0;
 
 	p->signal->group_stop_count = 0;
 
-	while_each_thread(p, t) {
+	for_other_threads(p, t) {
 		task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK);
 		/* Don't require de_thread to wait for the vhost_worker */
 		if ((t->flags & (PF_IO_WORKER | PF_USER_WORKER)) != PF_USER_WORKER)
@@ -2465,12 +2465,10 @@ static bool do_signal_stop(int signr)
 			sig->group_exit_code = signr;
 
 		sig->group_stop_count = 0;
-
 		if (task_set_jobctl_pending(current, signr | gstop))
 			sig->group_stop_count++;
 
-		t = current;
-		while_each_thread(current, t) {
+		for_other_threads(current, t) {
 			/*
 			 * Setting state to TASK_STOPPED for a group
 			 * stop is always done with the siglock held,
@@ -2966,8 +2964,7 @@ static void retarget_shared_pending(struct task_struct *tsk, sigset_t *which)
 	if (sigisemptyset(&retarget))
 		return;
 
-	t = tsk;
-	while_each_thread(tsk, t) {
+	for_other_threads(tsk, t) {
 		if (t->flags & PF_EXITING)
 			continue;
 
-- 
cgit v1.2.3


From 0eb5085c38749f2a91e5bd8cbebb1ebf3398343c Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Thu, 16 Nov 2023 14:36:38 +0100
Subject: arch: remove ARCH_TASK_STRUCT_ON_STACK

IA-64 was the only architecture which selected ARCH_TASK_STRUCT_ON_STACK.
IA-64 was removed with commit cf8e8658100d ("arch: Remove Itanium (IA-64)
architecture"). Therefore remove support for ARCH_TASK_STRUCT_ON_STACK
as well.

Note: this also reveals a potential bug in powerpc code, which makes use of
__init_task_data without selecting ARCH_TASK_STRUCT_ON_STACK which makes
__init_task_data a no-op. This is broken since commit d11ed3ab3166 ("Expand
INIT_TASK() in init/init_task.c and remove") from 2018 and needs to be
addressed separately.

Link: https://lkml.kernel.org/r/20231116133638.1636277-4-hca@linux.ibm.com
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/Kconfig                 |  4 ----
 arch/powerpc/kexec/core_64.c |  3 +--
 include/linux/init_task.h    |  7 -------
 include/linux/sched.h        |  2 --
 init/init_task.c             | 10 ++--------
 5 files changed, 3 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/arch/Kconfig b/arch/Kconfig
index c2f87ef9f0ae..bfcc7c2dc039 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -301,10 +301,6 @@ config ARCH_HAS_DMA_CLEAR_UNCACHED
 config ARCH_HAS_CPU_FINALIZE_INIT
 	bool
 
-# Select if arch init_task must go in the __init_task_data section
-config ARCH_TASK_STRUCT_ON_STACK
-	bool
-
 config HAVE_ARCH_THREAD_STRUCT_WHITELIST
 	bool
 	help
diff --git a/arch/powerpc/kexec/core_64.c b/arch/powerpc/kexec/core_64.c
index 0bee7ca9a77c..762e4d09aacf 100644
--- a/arch/powerpc/kexec/core_64.c
+++ b/arch/powerpc/kexec/core_64.c
@@ -283,8 +283,7 @@ static void kexec_prepare_cpus(void)
  * We could use a smaller stack if we don't care about anything using
  * current, but that audit has not been performed.
  */
-static union thread_union kexec_stack __init_task_data =
-	{ };
+static union thread_union kexec_stack = { };
 
 /*
  * For similar reasons to the stack above, the kexecing CPU needs to be on a
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 40fc5813cf93..bccb3f1f6262 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -37,13 +37,6 @@ extern struct cred init_cred;
 
 #define INIT_TASK_COMM "swapper"
 
-/* Attach to the init_task data structure for proper alignment */
-#ifdef CONFIG_ARCH_TASK_STRUCT_ON_STACK
-#define __init_task_data __section(".data..init_task")
-#else
-#define __init_task_data /**/
-#endif
-
 /* Attach to the thread_info data structure for proper alignment */
 #define __init_thread_info __section(".data..init_thread_info")
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 292c31697248..c2ecb2e06046 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1955,9 +1955,7 @@ extern void ia64_set_curr_task(int cpu, struct task_struct *p);
 void yield(void);
 
 union thread_union {
-#ifndef CONFIG_ARCH_TASK_STRUCT_ON_STACK
 	struct task_struct task;
-#endif
 #ifndef CONFIG_THREAD_INFO_IN_TASK
 	struct thread_info thread_info;
 #endif
diff --git a/init/init_task.c b/init/init_task.c
index 5727d42149c3..6f6485d554df 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -51,8 +51,7 @@ static struct sighand_struct init_sighand = {
 };
 
 #ifdef CONFIG_SHADOW_CALL_STACK
-unsigned long init_shadow_call_stack[SCS_SIZE / sizeof(long)]
-		__init_task_data = {
+unsigned long init_shadow_call_stack[SCS_SIZE / sizeof(long)] = {
 	[(SCS_SIZE / sizeof(long)) - 1] = SCS_END_MAGIC
 };
 #endif
@@ -61,12 +60,7 @@ unsigned long init_shadow_call_stack[SCS_SIZE / sizeof(long)]
  * Set up the first task table, touch at your own risk!. Base=0,
  * limit=0x1fffff (=2MB)
  */
-struct task_struct init_task
-#ifdef CONFIG_ARCH_TASK_STRUCT_ON_STACK
-	__init_task_data
-#endif
-	__aligned(L1_CACHE_BYTES)
-= {
+struct task_struct init_task __aligned(L1_CACHE_BYTES) = {
 #ifdef CONFIG_THREAD_INFO_IN_TASK
 	.thread_info	= INIT_THREAD_INFO(init_task),
 	.stack_refcount	= REFCOUNT_INIT(1),
-- 
cgit v1.2.3


From b454ec29225cda9ae85ed0a154f4228f1922c872 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Mon, 20 Nov 2023 16:16:49 +0100
Subject: kernel/signal.c: simplify force_sig_info_to_task(), kill
 recalc_sigpending_and_wake()

The purpose of recalc_sigpending_and_wake() is not clear, it looks
"obviously unneeded" because we are going to send the signal which can't
be blocked or ignored.

Add the comment to explain why we can't rely on send_signal_locked() and
make this logic more simple/explicit.  recalc_sigpending_and_wake() has no
other users, it can die.

In fact I think we don't even need signal_wake_up(), the target task must
be either current or a TASK_TRACED child, otherwise the usage of siglock
is not safe.  But this needs another change.

Link: https://lkml.kernel.org/r/20231120151649.GA15995@redhat.com
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/sched/signal.h |  1 -
 kernel/signal.c              | 17 ++++-------------
 2 files changed, 4 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 41d6759d6a4a..015c0e3a3e1d 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -432,7 +432,6 @@ static inline bool fault_signal_pending(vm_fault_t fault_flags,
  * This is required every time the blocked sigset_t changes.
  * callers must hold sighand->siglock.
  */
-extern void recalc_sigpending_and_wake(struct task_struct *t);
 extern void recalc_sigpending(void);
 extern void calculate_sigpending(void);
 
diff --git a/kernel/signal.c b/kernel/signal.c
index 5aa216e841a2..c9c57d053ce4 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -171,16 +171,6 @@ static bool recalc_sigpending_tsk(struct task_struct *t)
 	return false;
 }
 
-/*
- * After recalculating TIF_SIGPENDING, we need to make sure the task wakes up.
- * This is superfluous when called on current, the wakeup is a harmless no-op.
- */
-void recalc_sigpending_and_wake(struct task_struct *t)
-{
-	if (recalc_sigpending_tsk(t))
-		signal_wake_up(t, 0);
-}
-
 void recalc_sigpending(void)
 {
 	if (!recalc_sigpending_tsk(current) && !freezing(current))
@@ -1348,10 +1338,8 @@ force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t,
 		action->sa.sa_handler = SIG_DFL;
 		if (handler == HANDLER_EXIT)
 			action->sa.sa_flags |= SA_IMMUTABLE;
-		if (blocked) {
+		if (blocked)
 			sigdelset(&t->blocked, sig);
-			recalc_sigpending_and_wake(t);
-		}
 	}
 	/*
 	 * Don't clear SIGNAL_UNKILLABLE for traced tasks, users won't expect
@@ -1361,6 +1349,9 @@ force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t,
 	    (!t->ptrace || (handler == HANDLER_EXIT)))
 		t->signal->flags &= ~SIGNAL_UNKILLABLE;
 	ret = send_signal_locked(sig, info, t, PIDTYPE_PID);
+	/* This can happen if the signal was already pending and blocked */
+	if (!task_sigpending(t))
+		signal_wake_up(t, 0);
 	spin_unlock_irqrestore(&t->sighand->siglock, flags);
 
 	return ret;
-- 
cgit v1.2.3


From 7acf164b259d9007264d9d8501da1023f140a3b4 Mon Sep 17 00:00:00 2001
From: Baoquan He <bhe@redhat.com>
Date: Wed, 15 Nov 2023 21:00:27 +0800
Subject: resource: add walk_system_ram_res_rev()

This function, being a variant of walk_system_ram_res() introduced in
commit 8c86e70acead ("resource: provide new functions to walk through
resources"), walks through a list of all the resources of System RAM in
reversed order, i.e., from higher to lower.

It will be used in kexec_file code to load kernel, initrd etc when
preparing kexec reboot.

Link: https://lkml.kernel.org/r/ZVTA6z/06cLnWKUz@MiWiFi-R3L-srv
Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org>
Signed-off-by: Baoquan He <bhe@redhat.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/ioport.h |  3 +++
 kernel/resource.c      | 57 ++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 60 insertions(+)

(limited to 'include')

diff --git a/include/linux/ioport.h b/include/linux/ioport.h
index 14f5cfabbbc8..db7fe25f3370 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -331,6 +331,9 @@ extern int
 walk_system_ram_res(u64 start, u64 end, void *arg,
 		    int (*func)(struct resource *, void *));
 extern int
+walk_system_ram_res_rev(u64 start, u64 end, void *arg,
+			int (*func)(struct resource *, void *));
+extern int
 walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start, u64 end,
 		    void *arg, int (*func)(struct resource *, void *));
 
diff --git a/kernel/resource.c b/kernel/resource.c
index 866ef3663a0b..e8a244300e5b 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -27,6 +27,8 @@
 #include <linux/mount.h>
 #include <linux/resource_ext.h>
 #include <uapi/linux/magic.h>
+#include <linux/string.h>
+#include <linux/vmalloc.h>
 #include <asm/io.h>
 
 
@@ -429,6 +431,61 @@ int walk_system_ram_res(u64 start, u64 end, void *arg,
 				     func);
 }
 
+/*
+ * This function, being a variant of walk_system_ram_res(), calls the @func
+ * callback against all memory ranges of type System RAM which are marked as
+ * IORESOURCE_SYSTEM_RAM and IORESOUCE_BUSY in reversed order, i.e., from
+ * higher to lower.
+ */
+int walk_system_ram_res_rev(u64 start, u64 end, void *arg,
+				int (*func)(struct resource *, void *))
+{
+	struct resource res, *rams;
+	int rams_size = 16, i;
+	unsigned long flags;
+	int ret = -1;
+
+	/* create a list */
+	rams = kvcalloc(rams_size, sizeof(struct resource), GFP_KERNEL);
+	if (!rams)
+		return ret;
+
+	flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+	i = 0;
+	while ((start < end) &&
+		(!find_next_iomem_res(start, end, flags, IORES_DESC_NONE, &res))) {
+		if (i >= rams_size) {
+			/* re-alloc */
+			struct resource *rams_new;
+
+			rams_new = kvrealloc(rams, rams_size * sizeof(struct resource),
+					     (rams_size + 16) * sizeof(struct resource),
+					     GFP_KERNEL);
+			if (!rams_new)
+				goto out;
+
+			rams = rams_new;
+			rams_size += 16;
+		}
+
+		rams[i].start = res.start;
+		rams[i++].end = res.end;
+
+		start = res.end + 1;
+	}
+
+	/* go reverse */
+	for (i--; i >= 0; i--) {
+		ret = (*func)(&rams[i], arg);
+		if (ret)
+			break;
+	}
+
+out:
+	kvfree(rams);
+	return ret;
+}
+
 /*
  * This function calls the @func callback against all memory ranges, which
  * are ranges marked as IORESOURCE_MEM and IORESOUCE_BUSY.
-- 
cgit v1.2.3


From 07f830ae4913d0b986c8c0ff88a7d597948b9bd8 Mon Sep 17 00:00:00 2001
From: Selvin Xavier <selvin.xavier@broadcom.com>
Date: Thu, 7 Dec 2023 02:47:40 -0800
Subject: RDMA/bnxt_re: Adds MSN table capability for Gen P7 adapters

GenP7 HW expects an MSN table instead of PSN table. Check
for the HW retransmission capability and populate the MSN
table if HW retansmission is supported.

Signed-off-by: Damodharam Ammepalli <damodharam.ammepalli@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://lore.kernel.org/r/1701946060-13931-7-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/bnxt_re/qplib_fp.c   | 67 +++++++++++++++++++++++++++---
 drivers/infiniband/hw/bnxt_re/qplib_fp.h   | 14 +++++++
 drivers/infiniband/hw/bnxt_re/qplib_rcfw.c |  2 +
 drivers/infiniband/hw/bnxt_re/qplib_res.h  |  9 ++++
 include/uapi/rdma/bnxt_re-abi.h            |  1 +
 5 files changed, 87 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
index 177c6c185f0c..c98e04fe2ddd 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
@@ -982,6 +982,9 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
 	u32 tbl_indx;
 	u16 nsge;
 
+	if (res->dattr)
+		qp->dev_cap_flags = res->dattr->dev_cap_flags;
+
 	sq->dbinfo.flags = 0;
 	bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req,
 				 CMDQ_BASE_OPCODE_CREATE_QP,
@@ -997,6 +1000,11 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
 		psn_sz = bnxt_qplib_is_chip_gen_p5_p7(res->cctx) ?
 			 sizeof(struct sq_psn_search_ext) :
 			 sizeof(struct sq_psn_search);
+
+		if (BNXT_RE_HW_RETX(qp->dev_cap_flags)) {
+			psn_sz = sizeof(struct sq_msn_search);
+			qp->msn = 0;
+		}
 	}
 
 	hwq_attr.res = res;
@@ -1005,6 +1013,13 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp)
 	hwq_attr.depth = bnxt_qplib_get_depth(sq);
 	hwq_attr.aux_stride = psn_sz;
 	hwq_attr.aux_depth = bnxt_qplib_set_sq_size(sq, qp->wqe_mode);
+	/* Update msn tbl size */
+	if (BNXT_RE_HW_RETX(qp->dev_cap_flags) && psn_sz) {
+		hwq_attr.aux_depth = roundup_pow_of_two(bnxt_qplib_set_sq_size(sq, qp->wqe_mode));
+		qp->msn_tbl_sz = hwq_attr.aux_depth;
+		qp->msn = 0;
+	}
+
 	hwq_attr.type = HWQ_TYPE_QUEUE;
 	rc = bnxt_qplib_alloc_init_hwq(&sq->hwq, &hwq_attr);
 	if (rc)
@@ -1587,6 +1602,27 @@ void *bnxt_qplib_get_qp1_rq_buf(struct bnxt_qplib_qp *qp,
 	return NULL;
 }
 
+/* Fil the MSN table into the next psn row */
+static void bnxt_qplib_fill_msn_search(struct bnxt_qplib_qp *qp,
+				       struct bnxt_qplib_swqe *wqe,
+				       struct bnxt_qplib_swq *swq)
+{
+	struct sq_msn_search *msns;
+	u32 start_psn, next_psn;
+	u16 start_idx;
+
+	msns = (struct sq_msn_search *)swq->psn_search;
+	msns->start_idx_next_psn_start_psn = 0;
+
+	start_psn = swq->start_psn;
+	next_psn = swq->next_psn;
+	start_idx = swq->slot_idx;
+	msns->start_idx_next_psn_start_psn |=
+		bnxt_re_update_msn_tbl(start_idx, next_psn, start_psn);
+	qp->msn++;
+	qp->msn %= qp->msn_tbl_sz;
+}
+
 static void bnxt_qplib_fill_psn_search(struct bnxt_qplib_qp *qp,
 				       struct bnxt_qplib_swqe *wqe,
 				       struct bnxt_qplib_swq *swq)
@@ -1598,6 +1634,12 @@ static void bnxt_qplib_fill_psn_search(struct bnxt_qplib_qp *qp,
 
 	if (!swq->psn_search)
 		return;
+	/* Handle MSN differently on cap flags  */
+	if (BNXT_RE_HW_RETX(qp->dev_cap_flags)) {
+		bnxt_qplib_fill_msn_search(qp, wqe, swq);
+		return;
+	}
+	psns = (struct sq_psn_search *)swq->psn_search;
 	psns = swq->psn_search;
 	psns_ext = swq->psn_ext;
 
@@ -1706,8 +1748,8 @@ static u16 bnxt_qplib_required_slots(struct bnxt_qplib_qp *qp,
 	return slot;
 }
 
-static void bnxt_qplib_pull_psn_buff(struct bnxt_qplib_q *sq,
-				     struct bnxt_qplib_swq *swq)
+static void bnxt_qplib_pull_psn_buff(struct bnxt_qplib_qp *qp, struct bnxt_qplib_q *sq,
+				     struct bnxt_qplib_swq *swq, bool hw_retx)
 {
 	struct bnxt_qplib_hwq *hwq;
 	u32 pg_num, pg_indx;
@@ -1718,6 +1760,11 @@ static void bnxt_qplib_pull_psn_buff(struct bnxt_qplib_q *sq,
 	if (!hwq->pad_pg)
 		return;
 	tail = swq->slot_idx / sq->dbinfo.max_slot;
+	if (hw_retx) {
+		/* For HW retx use qp msn index */
+		tail = qp->msn;
+		tail %= qp->msn_tbl_sz;
+	}
 	pg_num = (tail + hwq->pad_pgofft) / (PAGE_SIZE / hwq->pad_stride);
 	pg_indx = (tail + hwq->pad_pgofft) % (PAGE_SIZE / hwq->pad_stride);
 	buff = (void *)(hwq->pad_pg[pg_num] + pg_indx * hwq->pad_stride);
@@ -1742,6 +1789,7 @@ int bnxt_qplib_post_send(struct bnxt_qplib_qp *qp,
 	struct bnxt_qplib_swq *swq;
 	bool sch_handler = false;
 	u16 wqe_sz, qdf = 0;
+	bool msn_update;
 	void *base_hdr;
 	void *ext_hdr;
 	__le32 temp32;
@@ -1769,7 +1817,7 @@ int bnxt_qplib_post_send(struct bnxt_qplib_qp *qp,
 	}
 
 	swq = bnxt_qplib_get_swqe(sq, &wqe_idx);
-	bnxt_qplib_pull_psn_buff(sq, swq);
+	bnxt_qplib_pull_psn_buff(qp, sq, swq, BNXT_RE_HW_RETX(qp->dev_cap_flags));
 
 	idx = 0;
 	swq->slot_idx = hwq->prod;
@@ -1801,6 +1849,8 @@ int bnxt_qplib_post_send(struct bnxt_qplib_qp *qp,
 					       &idx);
 	if (data_len < 0)
 		goto queue_err;
+	/* Make sure we update MSN table only for wired wqes */
+	msn_update = true;
 	/* Specifics */
 	switch (wqe->type) {
 	case BNXT_QPLIB_SWQE_TYPE_SEND:
@@ -1841,6 +1891,7 @@ int bnxt_qplib_post_send(struct bnxt_qplib_qp *qp,
 						      SQ_SEND_DST_QP_MASK);
 			ext_sqe->avid = cpu_to_le32(wqe->send.avid &
 						    SQ_SEND_AVID_MASK);
+			msn_update = false;
 		} else {
 			sqe->length = cpu_to_le32(data_len);
 			if (qp->mtu)
@@ -1898,7 +1949,7 @@ int bnxt_qplib_post_send(struct bnxt_qplib_qp *qp,
 		sqe->wqe_type = wqe->type;
 		sqe->flags = wqe->flags;
 		sqe->inv_l_key = cpu_to_le32(wqe->local_inv.inv_l_key);
-
+		msn_update = false;
 		break;
 	}
 	case BNXT_QPLIB_SWQE_TYPE_FAST_REG_MR:
@@ -1930,6 +1981,7 @@ int bnxt_qplib_post_send(struct bnxt_qplib_qp *qp,
 						PTU_PTE_VALID);
 		ext_sqe->pblptr = cpu_to_le64(wqe->frmr.pbl_dma_ptr);
 		ext_sqe->va = cpu_to_le64(wqe->frmr.va);
+		msn_update = false;
 
 		break;
 	}
@@ -1947,6 +1999,7 @@ int bnxt_qplib_post_send(struct bnxt_qplib_qp *qp,
 		sqe->l_key = cpu_to_le32(wqe->bind.r_key);
 		ext_sqe->va = cpu_to_le64(wqe->bind.va);
 		ext_sqe->length_lo = cpu_to_le32(wqe->bind.length);
+		msn_update = false;
 		break;
 	}
 	default:
@@ -1954,8 +2007,10 @@ int bnxt_qplib_post_send(struct bnxt_qplib_qp *qp,
 		rc = -EINVAL;
 		goto done;
 	}
-	swq->next_psn = sq->psn & BTH_PSN_MASK;
-	bnxt_qplib_fill_psn_search(qp, wqe, swq);
+	if (!BNXT_RE_HW_RETX(qp->dev_cap_flags) || msn_update) {
+		swq->next_psn = sq->psn & BTH_PSN_MASK;
+		bnxt_qplib_fill_psn_search(qp, wqe, swq);
+	}
 queue_err:
 	bnxt_qplib_swq_mod_start(sq, wqe_idx);
 	bnxt_qplib_hwq_incr_prod(&sq->dbinfo, hwq, swq->slots);
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.h b/drivers/infiniband/hw/bnxt_re/qplib_fp.h
index 8a6bea201b29..967c6691e413 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.h
@@ -338,6 +338,9 @@ struct bnxt_qplib_qp {
 	dma_addr_t			rq_hdr_buf_map;
 	struct list_head		sq_flush;
 	struct list_head		rq_flush;
+	u32				msn;
+	u32				msn_tbl_sz;
+	u16				dev_cap_flags;
 };
 
 #define BNXT_QPLIB_MAX_CQE_ENTRY_SIZE	sizeof(struct cq_base)
@@ -627,4 +630,15 @@ static inline u16 bnxt_qplib_calc_ilsize(struct bnxt_qplib_swqe *wqe, u16 max)
 
 	return size;
 }
+
+/* MSN table update inlin */
+static inline uint64_t bnxt_re_update_msn_tbl(u32 st_idx, u32 npsn, u32 start_psn)
+{
+	return cpu_to_le64((((u64)(st_idx) << SQ_MSN_SEARCH_START_IDX_SFT) &
+		SQ_MSN_SEARCH_START_IDX_MASK) |
+		(((u64)(npsn) << SQ_MSN_SEARCH_NEXT_PSN_SFT) &
+		SQ_MSN_SEARCH_NEXT_PSN_MASK) |
+		(((start_psn) << SQ_MSN_SEARCH_START_PSN_SFT) &
+		SQ_MSN_SEARCH_START_PSN_MASK));
+}
 #endif /* __BNXT_QPLIB_FP_H__ */
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
index 403b6797d9c2..0ea7ccc70679 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
@@ -905,6 +905,8 @@ config_vf_res:
 	req.max_gid_per_vf = cpu_to_le32(ctx->vf_res.max_gid_per_vf);
 
 skip_ctx_setup:
+	if (BNXT_RE_HW_RETX(rcfw->res->dattr->dev_cap_flags))
+		req.flags |= CMDQ_INITIALIZE_FW_FLAGS_HW_REQUESTER_RETX_SUPPORTED;
 	req.stat_ctx_id = cpu_to_le32(ctx->stats.fw_id);
 	bnxt_qplib_fill_cmdqmsg(&msg, &req, &resp, NULL, sizeof(req), sizeof(resp), 0);
 	rc = bnxt_qplib_rcfw_send_message(rcfw, &msg);
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.h b/drivers/infiniband/hw/bnxt_re/qplib_res.h
index c228870eed29..382d89fa7d16 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_res.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_res.h
@@ -539,6 +539,15 @@ static inline bool _is_ext_stats_supported(u16 dev_cap_flags)
 		CREQ_QUERY_FUNC_RESP_SB_EXT_STATS;
 }
 
+static inline bool _is_hw_retx_supported(u16 dev_cap_flags)
+{
+	return dev_cap_flags &
+		(CREQ_QUERY_FUNC_RESP_SB_HW_REQUESTER_RETX_ENABLED |
+		 CREQ_QUERY_FUNC_RESP_SB_HW_RESPONDER_RETX_ENABLED);
+}
+
+#define BNXT_RE_HW_RETX(a) _is_hw_retx_supported((a))
+
 static inline u8 bnxt_qplib_dbr_pacing_en(struct bnxt_qplib_chip_ctx *cctx)
 {
 	return cctx->modes.dbr_pacing;
diff --git a/include/uapi/rdma/bnxt_re-abi.h b/include/uapi/rdma/bnxt_re-abi.h
index a1b896d6d940..3342276aeac1 100644
--- a/include/uapi/rdma/bnxt_re-abi.h
+++ b/include/uapi/rdma/bnxt_re-abi.h
@@ -55,6 +55,7 @@ enum {
 	BNXT_RE_UCNTX_CMASK_WC_DPI_ENABLED = 0x04ULL,
 	BNXT_RE_UCNTX_CMASK_DBR_PACING_ENABLED = 0x08ULL,
 	BNXT_RE_UCNTX_CMASK_POW2_DISABLED = 0x10ULL,
+	BNXT_RE_COMP_MASK_UCNTX_HW_RETX_ENABLED = 0x40,
 };
 
 enum bnxt_re_wqe_mode {
-- 
cgit v1.2.3


From 125f1c7f26ffcdbf96177abe75b70c1a6ceb17bc Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@nvidia.com>
Date: Tue, 5 Dec 2023 18:25:54 +0100
Subject: net/sched: act_ct: Take per-cb reference to tcf_ct_flow_table

The referenced change added custom cleanup code to act_ct to delete any
callbacks registered on the parent block when deleting the
tcf_ct_flow_table instance. However, the underlying issue is that the
drivers don't obtain the reference to the tcf_ct_flow_table instance when
registering callbacks which means that not only driver callbacks may still
be on the table when deleting it but also that the driver can still have
pointers to its internal nf_flowtable and can use it concurrently which
results either warning in netfilter[0] or use-after-free.

Fix the issue by taking a reference to the underlying struct
tcf_ct_flow_table instance when registering the callback and release the
reference when unregistering. Expose new API required for such reference
counting by adding two new callbacks to nf_flowtable_type and implementing
them for act_ct flowtable_ct type. This fixes the issue by extending the
lifetime of nf_flowtable until all users have unregistered.

[0]:
[106170.938634] ------------[ cut here ]------------
[106170.939111] WARNING: CPU: 21 PID: 3688 at include/net/netfilter/nf_flow_table.h:262 mlx5_tc_ct_del_ft_cb+0x267/0x2b0 [mlx5_core]
[106170.940108] Modules linked in: act_ct nf_flow_table act_mirred act_skbedit act_tunnel_key vxlan cls_matchall nfnetlink_cttimeout act_gact cls_flower sch_ingress mlx5_vdpa vringh vhost_iotlb vdpa bonding openvswitch nsh rpcrdma rdma_ucm
ib_iser libiscsi scsi_transport_iscsi ib_umad rdma_cm ib_ipoib iw_cm ib_cm mlx5_ib ib_uverbs ib_core xt_MASQUERADE nf_conntrack_netlink nfnetlink iptable_nat xt_addrtype xt_conntrack nf_nat br_netfilter rpcsec_gss_krb5 auth_rpcgss oid_regis
try overlay mlx5_core
[106170.943496] CPU: 21 PID: 3688 Comm: kworker/u48:0 Not tainted 6.6.0-rc7_for_upstream_min_debug_2023_11_01_13_02 #1
[106170.944361] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
[106170.945292] Workqueue: mlx5e mlx5e_rep_neigh_update [mlx5_core]
[106170.945846] RIP: 0010:mlx5_tc_ct_del_ft_cb+0x267/0x2b0 [mlx5_core]
[106170.946413] Code: 89 ef 48 83 05 71 a4 14 00 01 e8 f4 06 04 e1 48 83 05 6c a4 14 00 01 48 83 c4 28 5b 5d 41 5c 41 5d c3 48 83 05 d1 8b 14 00 01 <0f> 0b 48 83 05 d7 8b 14 00 01 e9 96 fe ff ff 48 83 05 a2 90 14 00
[106170.947924] RSP: 0018:ffff88813ff0fcb8 EFLAGS: 00010202
[106170.948397] RAX: 0000000000000000 RBX: ffff88811eabac40 RCX: ffff88811eabad48
[106170.949040] RDX: ffff88811eab8000 RSI: ffffffffa02cd560 RDI: 0000000000000000
[106170.949679] RBP: ffff88811eab8000 R08: 0000000000000001 R09: ffffffffa0229700
[106170.950317] R10: ffff888103538fc0 R11: 0000000000000001 R12: ffff88811eabad58
[106170.950969] R13: ffff888110c01c00 R14: ffff888106b40000 R15: 0000000000000000
[106170.951616] FS:  0000000000000000(0000) GS:ffff88885fd40000(0000) knlGS:0000000000000000
[106170.952329] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[106170.952834] CR2: 00007f1cefd28cb0 CR3: 000000012181b006 CR4: 0000000000370ea0
[106170.953482] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[106170.954121] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[106170.954766] Call Trace:
[106170.955057]  <TASK>
[106170.955315]  ? __warn+0x79/0x120
[106170.955648]  ? mlx5_tc_ct_del_ft_cb+0x267/0x2b0 [mlx5_core]
[106170.956172]  ? report_bug+0x17c/0x190
[106170.956537]  ? handle_bug+0x3c/0x60
[106170.956891]  ? exc_invalid_op+0x14/0x70
[106170.957264]  ? asm_exc_invalid_op+0x16/0x20
[106170.957666]  ? mlx5_del_flow_rules+0x10/0x310 [mlx5_core]
[106170.958172]  ? mlx5_tc_ct_block_flow_offload_add+0x1240/0x1240 [mlx5_core]
[106170.958788]  ? mlx5_tc_ct_del_ft_cb+0x267/0x2b0 [mlx5_core]
[106170.959339]  ? mlx5_tc_ct_del_ft_cb+0xc6/0x2b0 [mlx5_core]
[106170.959854]  ? mapping_remove+0x154/0x1d0 [mlx5_core]
[106170.960342]  ? mlx5e_tc_action_miss_mapping_put+0x4f/0x80 [mlx5_core]
[106170.960927]  mlx5_tc_ct_delete_flow+0x76/0xc0 [mlx5_core]
[106170.961441]  mlx5_free_flow_attr_actions+0x13b/0x220 [mlx5_core]
[106170.962001]  mlx5e_tc_del_fdb_flow+0x22c/0x3b0 [mlx5_core]
[106170.962524]  mlx5e_tc_del_flow+0x95/0x3c0 [mlx5_core]
[106170.963034]  mlx5e_flow_put+0x73/0xe0 [mlx5_core]
[106170.963506]  mlx5e_put_flow_list+0x38/0x70 [mlx5_core]
[106170.964002]  mlx5e_rep_update_flows+0xec/0x290 [mlx5_core]
[106170.964525]  mlx5e_rep_neigh_update+0x1da/0x310 [mlx5_core]
[106170.965056]  process_one_work+0x13a/0x2c0
[106170.965443]  worker_thread+0x2e5/0x3f0
[106170.965808]  ? rescuer_thread+0x410/0x410
[106170.966192]  kthread+0xc6/0xf0
[106170.966515]  ? kthread_complete_and_exit+0x20/0x20
[106170.966970]  ret_from_fork+0x2d/0x50
[106170.967332]  ? kthread_complete_and_exit+0x20/0x20
[106170.967774]  ret_from_fork_asm+0x11/0x20
[106170.970466]  </TASK>
[106170.970726] ---[ end trace 0000000000000000 ]---

Fixes: 77ac5e40c44e ("net/sched: act_ct: remove and free nf_table callbacks")
Signed-off-by: Vlad Buslov <vladbu@nvidia.com>
Reviewed-by: Paul Blakey <paulb@nvidia.com>
Acked-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netfilter/nf_flow_table.h | 10 ++++++++++
 net/sched/act_ct.c                    | 34 ++++++++++++++++++++++++++++------
 2 files changed, 38 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index fe1507c1db82..692d5955911c 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -62,6 +62,8 @@ struct nf_flowtable_type {
 						  enum flow_offload_tuple_dir dir,
 						  struct nf_flow_rule *flow_rule);
 	void				(*free)(struct nf_flowtable *ft);
+	void				(*get)(struct nf_flowtable *ft);
+	void				(*put)(struct nf_flowtable *ft);
 	nf_hookfn			*hook;
 	struct module			*owner;
 };
@@ -240,6 +242,11 @@ nf_flow_table_offload_add_cb(struct nf_flowtable *flow_table,
 	}
 
 	list_add_tail(&block_cb->list, &block->cb_list);
+	up_write(&flow_table->flow_block_lock);
+
+	if (flow_table->type->get)
+		flow_table->type->get(flow_table);
+	return 0;
 
 unlock:
 	up_write(&flow_table->flow_block_lock);
@@ -262,6 +269,9 @@ nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table,
 		WARN_ON(true);
 	}
 	up_write(&flow_table->flow_block_lock);
+
+	if (flow_table->type->put)
+		flow_table->type->put(flow_table);
 }
 
 void flow_offload_route_init(struct flow_offload *flow,
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index b3f4a503ee2b..f69c47945175 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -286,9 +286,31 @@ static bool tcf_ct_flow_is_outdated(const struct flow_offload *flow)
 	       !test_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags);
 }
 
+static void tcf_ct_flow_table_get_ref(struct tcf_ct_flow_table *ct_ft);
+
+static void tcf_ct_nf_get(struct nf_flowtable *ft)
+{
+	struct tcf_ct_flow_table *ct_ft =
+		container_of(ft, struct tcf_ct_flow_table, nf_ft);
+
+	tcf_ct_flow_table_get_ref(ct_ft);
+}
+
+static void tcf_ct_flow_table_put(struct tcf_ct_flow_table *ct_ft);
+
+static void tcf_ct_nf_put(struct nf_flowtable *ft)
+{
+	struct tcf_ct_flow_table *ct_ft =
+		container_of(ft, struct tcf_ct_flow_table, nf_ft);
+
+	tcf_ct_flow_table_put(ct_ft);
+}
+
 static struct nf_flowtable_type flowtable_ct = {
 	.gc		= tcf_ct_flow_is_outdated,
 	.action		= tcf_ct_flow_table_fill_actions,
+	.get		= tcf_ct_nf_get,
+	.put		= tcf_ct_nf_put,
 	.owner		= THIS_MODULE,
 };
 
@@ -337,9 +359,13 @@ err_alloc:
 	return err;
 }
 
+static void tcf_ct_flow_table_get_ref(struct tcf_ct_flow_table *ct_ft)
+{
+	refcount_inc(&ct_ft->ref);
+}
+
 static void tcf_ct_flow_table_cleanup_work(struct work_struct *work)
 {
-	struct flow_block_cb *block_cb, *tmp_cb;
 	struct tcf_ct_flow_table *ct_ft;
 	struct flow_block *block;
 
@@ -347,13 +373,9 @@ static void tcf_ct_flow_table_cleanup_work(struct work_struct *work)
 			     rwork);
 	nf_flow_table_free(&ct_ft->nf_ft);
 
-	/* Remove any remaining callbacks before cleanup */
 	block = &ct_ft->nf_ft.flow_block;
 	down_write(&ct_ft->nf_ft.flow_block_lock);
-	list_for_each_entry_safe(block_cb, tmp_cb, &block->cb_list, list) {
-		list_del(&block_cb->list);
-		flow_block_cb_free(block_cb);
-	}
+	WARN_ON(!list_empty(&block->cb_list));
 	up_write(&ct_ft->nf_ft.flow_block_lock);
 	kfree(ct_ft);
 
-- 
cgit v1.2.3


From 7973be94724464222ae0b1860a25be04ab7b0132 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 8 Dec 2023 18:52:38 +0200
Subject: clk: x86: lpss-atom: Drop unneeded 'extern' in the header
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

'extern' for the functions is not needed, drop it.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://lore.kernel.org/r/20231208165238.3309058-1-andriy.shevchenko@linux.intel.com
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 include/linux/platform_data/x86/clk-lpss.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/platform_data/x86/clk-lpss.h b/include/linux/platform_data/x86/clk-lpss.h
index 41df326583f9..7f132029316a 100644
--- a/include/linux/platform_data/x86/clk-lpss.h
+++ b/include/linux/platform_data/x86/clk-lpss.h
@@ -15,6 +15,6 @@ struct lpss_clk_data {
 	struct clk *clk;
 };
 
-extern int lpss_atom_clk_init(void);
+int lpss_atom_clk_init(void);
 
 #endif /* __CLK_LPSS_H */
-- 
cgit v1.2.3


From 72dd14d241e1c6e241fc5b265746c59f306c6aa3 Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Mon, 4 Dec 2023 14:17:37 -0800
Subject: platform/x86/intel/tpmi: Modify external interface to get read/write
 state
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Modify the external interface tpmi_get_feature_status() to get read
and write blocked instead of locked and disabled. Since auxiliary device
is not created when disabled, no use of returning disabled state. Also
locked state is not useful as feature driver can't use locked state
in a meaningful way.

Using read and write state, feature driver can decide which operations
to restrict for that feature.

Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://lore.kernel.org/r/20231204221740.3645130-3-srinivas.pandruvada@linux.intel.com
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 drivers/platform/x86/intel/tpmi.c | 8 ++++----
 include/linux/intel_tpmi.h        | 5 ++---
 2 files changed, 6 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/platform/x86/intel/tpmi.c b/drivers/platform/x86/intel/tpmi.c
index 09972e2b8a06..92c5c3a90d53 100644
--- a/drivers/platform/x86/intel/tpmi.c
+++ b/drivers/platform/x86/intel/tpmi.c
@@ -345,8 +345,8 @@ err_unlock:
 	return ret;
 }
 
-int tpmi_get_feature_status(struct auxiliary_device *auxdev, int feature_id,
-			    int *locked, int *disabled)
+int tpmi_get_feature_status(struct auxiliary_device *auxdev,
+			    int feature_id, bool *read_blocked, bool *write_blocked)
 {
 	struct intel_vsec_device *intel_vsec_dev = dev_to_ivdev(auxdev->dev.parent);
 	struct intel_tpmi_info *tpmi_info = auxiliary_get_drvdata(&intel_vsec_dev->auxdev);
@@ -357,8 +357,8 @@ int tpmi_get_feature_status(struct auxiliary_device *auxdev, int feature_id,
 	if (ret)
 		return ret;
 
-	*locked = feature_state.locked;
-	*disabled = !feature_state.enabled;
+	*read_blocked = feature_state.read_blocked;
+	*write_blocked = feature_state.write_blocked;
 
 	return 0;
 }
diff --git a/include/linux/intel_tpmi.h b/include/linux/intel_tpmi.h
index ee07393445f9..4f89c5bd8663 100644
--- a/include/linux/intel_tpmi.h
+++ b/include/linux/intel_tpmi.h
@@ -32,7 +32,6 @@ struct intel_tpmi_plat_info {
 struct intel_tpmi_plat_info *tpmi_get_platform_data(struct auxiliary_device *auxdev);
 struct resource *tpmi_get_resource_at_index(struct auxiliary_device *auxdev, int index);
 int tpmi_get_resource_count(struct auxiliary_device *auxdev);
-
-int tpmi_get_feature_status(struct auxiliary_device *auxdev, int feature_id, int *locked,
-			    int *disabled);
+int tpmi_get_feature_status(struct auxiliary_device *auxdev, int feature_id, bool *read_blocked,
+			    bool *write_blocked);
 #endif
-- 
cgit v1.2.3


From 046d7be6210e7f870e53eb38fd410237e9d1d88f Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Mon, 4 Dec 2023 14:17:38 -0800
Subject: platform/x86/intel/tpmi: Move TPMI ID definition
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Move TPMI ID definitions to common include file. In this way other
feature drivers don't have to redefine.

Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://lore.kernel.org/r/20231204221740.3645130-4-srinivas.pandruvada@linux.intel.com
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 drivers/platform/x86/intel/tpmi.c | 13 -------------
 include/linux/intel_tpmi.h        | 13 +++++++++++++
 2 files changed, 13 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/platform/x86/intel/tpmi.c b/drivers/platform/x86/intel/tpmi.c
index 92c5c3a90d53..e73cdea67fff 100644
--- a/drivers/platform/x86/intel/tpmi.c
+++ b/drivers/platform/x86/intel/tpmi.c
@@ -170,19 +170,6 @@ struct tpmi_feature_state {
 	u32 locked:1;
 } __packed;
 
-/*
- * List of supported TMPI IDs.
- * Some TMPI IDs are not used by Linux, so the numbers are not consecutive.
- */
-enum intel_tpmi_id {
-	TPMI_ID_RAPL = 0, /* Running Average Power Limit */
-	TPMI_ID_PEM = 1, /* Power and Perf excursion Monitor */
-	TPMI_ID_UNCORE = 2, /* Uncore Frequency Scaling */
-	TPMI_ID_SST = 5, /* Speed Select Technology */
-	TPMI_CONTROL_ID = 0x80, /* Special ID for getting feature status */
-	TPMI_INFO_ID = 0x81, /* Special ID for PCI BDF and Package ID information */
-};
-
 /*
  * The size from hardware is in u32 units. This size is from a trusted hardware,
  * but better to verify for pre silicon platforms. Set size to 0, when invalid.
diff --git a/include/linux/intel_tpmi.h b/include/linux/intel_tpmi.h
index 4f89c5bd8663..a3529b962be6 100644
--- a/include/linux/intel_tpmi.h
+++ b/include/linux/intel_tpmi.h
@@ -12,6 +12,19 @@
 #define TPMI_MINOR_VERSION(val)	FIELD_GET(GENMASK(4, 0), val)
 #define TPMI_MAJOR_VERSION(val)	FIELD_GET(GENMASK(7, 5), val)
 
+/*
+ * List of supported TMPI IDs.
+ * Some TMPI IDs are not used by Linux, so the numbers are not consecutive.
+ */
+enum intel_tpmi_id {
+	TPMI_ID_RAPL = 0,	/* Running Average Power Limit */
+	TPMI_ID_PEM = 1,	/* Power and Perf excursion Monitor */
+	TPMI_ID_UNCORE = 2,	/* Uncore Frequency Scaling */
+	TPMI_ID_SST = 5,	/* Speed Select Technology */
+	TPMI_CONTROL_ID = 0x80,	/* Special ID for getting feature status */
+	TPMI_INFO_ID = 0x81,	/* Special ID for PCI BDF and Package ID information */
+};
+
 /**
  * struct intel_tpmi_plat_info - Platform information for a TPMI device instance
  * @package_id:	CPU Package id
-- 
cgit v1.2.3


From 3526cfaed24269918135d09626afc5a155e4811a Mon Sep 17 00:00:00 2001
From: Hsiao Chien Sung <shawn.sung@mediatek.com>
Date: Tue, 24 Oct 2023 21:00:31 +0800
Subject: dt-bindings: reset: mt8188: Add VDOSYS reset control bits

Add MT8188 VDOSYS0 and VDOSYS1 reset control bits.

Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Hsiao Chien Sung <shawn.sung@mediatek.com>
Signed-off-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
---
 include/dt-bindings/reset/mt8188-resets.h | 75 +++++++++++++++++++++++++++++++
 1 file changed, 75 insertions(+)

(limited to 'include')

diff --git a/include/dt-bindings/reset/mt8188-resets.h b/include/dt-bindings/reset/mt8188-resets.h
index ba9a5e9b8899..5a58c54e7d20 100644
--- a/include/dt-bindings/reset/mt8188-resets.h
+++ b/include/dt-bindings/reset/mt8188-resets.h
@@ -38,4 +38,79 @@
 #define MT8188_INFRA_RST1_THERMAL_CTRL_RST         1
 #define MT8188_INFRA_RST3_PTP_CTRL_RST             2
 
+#define MT8188_VDO0_RST_DISP_OVL0		0
+#define MT8188_VDO0_RST_FAKE_ENG0		1
+#define MT8188_VDO0_RST_DISP_CCORR0		2
+#define MT8188_VDO0_RST_DISP_MUTEX0		3
+#define MT8188_VDO0_RST_DISP_GAMMA0		4
+#define MT8188_VDO0_RST_DISP_DITHER0		5
+#define MT8188_VDO0_RST_DISP_WDMA0		6
+#define MT8188_VDO0_RST_DISP_RDMA0		7
+#define MT8188_VDO0_RST_DSI0			8
+#define MT8188_VDO0_RST_DSI1			9
+#define MT8188_VDO0_RST_DSC_WRAP0		10
+#define MT8188_VDO0_RST_VPP_MERGE0		11
+#define MT8188_VDO0_RST_DP_INTF0		12
+#define MT8188_VDO0_RST_DISP_AAL0		13
+#define MT8188_VDO0_RST_INLINEROT0		14
+#define MT8188_VDO0_RST_APB_BUS			15
+#define MT8188_VDO0_RST_DISP_COLOR0		16
+#define MT8188_VDO0_RST_MDP_WROT0		17
+#define MT8188_VDO0_RST_DISP_RSZ0		18
+
+#define MT8188_VDO1_RST_SMI_LARB2		0
+#define MT8188_VDO1_RST_SMI_LARB3		1
+#define MT8188_VDO1_RST_GALS			2
+#define MT8188_VDO1_RST_FAKE_ENG0		3
+#define MT8188_VDO1_RST_FAKE_ENG1		4
+#define MT8188_VDO1_RST_MDP_RDMA0		5
+#define MT8188_VDO1_RST_MDP_RDMA1		6
+#define MT8188_VDO1_RST_MDP_RDMA2		7
+#define MT8188_VDO1_RST_MDP_RDMA3		8
+#define MT8188_VDO1_RST_VPP_MERGE0		9
+#define MT8188_VDO1_RST_VPP_MERGE1		10
+#define MT8188_VDO1_RST_VPP_MERGE2		11
+#define MT8188_VDO1_RST_VPP_MERGE3		12
+#define MT8188_VDO1_RST_VPP_MERGE4		13
+#define MT8188_VDO1_RST_VPP2_TO_VDO1_DL_ASYNC	14
+#define MT8188_VDO1_RST_VPP3_TO_VDO1_DL_ASYNC	15
+#define MT8188_VDO1_RST_DISP_MUTEX		16
+#define MT8188_VDO1_RST_MDP_RDMA4		17
+#define MT8188_VDO1_RST_MDP_RDMA5		18
+#define MT8188_VDO1_RST_MDP_RDMA6		19
+#define MT8188_VDO1_RST_MDP_RDMA7		20
+#define MT8188_VDO1_RST_DP_INTF1_MMCK		21
+#define MT8188_VDO1_RST_DPI0_MM_CK		22
+#define MT8188_VDO1_RST_DPI1_MM_CK		23
+#define MT8188_VDO1_RST_MERGE0_DL_ASYNC		24
+#define MT8188_VDO1_RST_MERGE1_DL_ASYNC		25
+#define MT8188_VDO1_RST_MERGE2_DL_ASYNC		26
+#define MT8188_VDO1_RST_MERGE3_DL_ASYNC		27
+#define MT8188_VDO1_RST_MERGE4_DL_ASYNC		28
+#define MT8188_VDO1_RST_VDO0_DSC_TO_VDO1_DL_ASYNC	29
+#define MT8188_VDO1_RST_VDO0_MERGE_TO_VDO1_DL_ASYNC	30
+#define MT8188_VDO1_RST_PADDING0		31
+#define MT8188_VDO1_RST_PADDING1		32
+#define MT8188_VDO1_RST_PADDING2		33
+#define MT8188_VDO1_RST_PADDING3		34
+#define MT8188_VDO1_RST_PADDING4		35
+#define MT8188_VDO1_RST_PADDING5		36
+#define MT8188_VDO1_RST_PADDING6		37
+#define MT8188_VDO1_RST_PADDING7		38
+#define MT8188_VDO1_RST_DISP_RSZ0		39
+#define MT8188_VDO1_RST_DISP_RSZ1		40
+#define MT8188_VDO1_RST_DISP_RSZ2		41
+#define MT8188_VDO1_RST_DISP_RSZ3		42
+#define MT8188_VDO1_RST_HDR_VDO_FE0		43
+#define MT8188_VDO1_RST_HDR_GFX_FE0		44
+#define MT8188_VDO1_RST_HDR_VDO_BE		45
+#define MT8188_VDO1_RST_HDR_VDO_FE1		46
+#define MT8188_VDO1_RST_HDR_GFX_FE1		47
+#define MT8188_VDO1_RST_DISP_MIXER		48
+#define MT8188_VDO1_RST_HDR_VDO_FE0_DL_ASYNC	49
+#define MT8188_VDO1_RST_HDR_VDO_FE1_DL_ASYNC	50
+#define MT8188_VDO1_RST_HDR_GFX_FE0_DL_ASYNC	51
+#define MT8188_VDO1_RST_HDR_GFX_FE1_DL_ASYNC	52
+#define MT8188_VDO1_RST_HDR_VDO_BE_DL_ASYNC	53
+
 #endif  /* _DT_BINDINGS_RESET_CONTROLLER_MT8188 */
-- 
cgit v1.2.3


From 6bb3703aa52c9b5bb9716cbeae7350247b675209 Mon Sep 17 00:00:00 2001
From: Masahisa Kojima <masahisa.kojima@linaro.org>
Date: Tue, 7 Nov 2023 14:40:52 +0900
Subject: efi: expose efivar generic ops register function

This is a preparation for supporting efivar operations provided by other
than efi subsystem.  Both register and unregister functions are exposed
so that non-efi subsystem can revert the efi generic operation.

Acked-by: Sumit Garg <sumit.garg@linaro.org>
Co-developed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: Masahisa Kojima <masahisa.kojima@linaro.org>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/efi.c | 12 ++++++++++++
 include/linux/efi.h        |  3 +++
 2 files changed, 15 insertions(+)

(limited to 'include')

diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 9d3910d1abe1..32a67c61c3b8 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -231,6 +231,18 @@ static void generic_ops_unregister(void)
 	efivars_unregister(&generic_efivars);
 }
 
+void efivars_generic_ops_register(void)
+{
+	generic_ops_register();
+}
+EXPORT_SYMBOL_GPL(efivars_generic_ops_register);
+
+void efivars_generic_ops_unregister(void)
+{
+	generic_ops_unregister();
+}
+EXPORT_SYMBOL_GPL(efivars_generic_ops_unregister);
+
 #ifdef CONFIG_EFI_CUSTOM_SSDT_OVERLAYS
 #define EFIVAR_SSDT_NAME_MAX	16UL
 static char efivar_ssdt[EFIVAR_SSDT_NAME_MAX] __initdata;
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 9cc5bf32f6f2..1b2f50efb98c 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -1348,4 +1348,7 @@ bool efi_config_table_is_usable(const efi_guid_t *guid, unsigned long table)
 
 umode_t efi_attr_is_visible(struct kobject *kobj, struct attribute *attr, int n);
 
+void efivars_generic_ops_register(void);
+void efivars_generic_ops_unregister(void);
+
 #endif /* _LINUX_EFI_H */
-- 
cgit v1.2.3


From 1f71f37fbbd065b3326d9b7d8bb5ae688cd653d0 Mon Sep 17 00:00:00 2001
From: Masahisa Kojima <masahisa.kojima@linaro.org>
Date: Tue, 7 Nov 2023 14:40:53 +0900
Subject: efi: Add EFI_ACCESS_DENIED status code

This commit adds the EFI_ACCESS_DENIED status code.

Acked-by: Sumit Garg <sumit.garg@linaro.org>
Co-developed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: Masahisa Kojima <masahisa.kojima@linaro.org>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 include/linux/efi.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/efi.h b/include/linux/efi.h
index 1b2f50efb98c..3668aa204c47 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -40,6 +40,7 @@ struct screen_info;
 #define EFI_WRITE_PROTECTED	( 8 | (1UL << (BITS_PER_LONG-1)))
 #define EFI_OUT_OF_RESOURCES	( 9 | (1UL << (BITS_PER_LONG-1)))
 #define EFI_NOT_FOUND		(14 | (1UL << (BITS_PER_LONG-1)))
+#define EFI_ACCESS_DENIED	(15 | (1UL << (BITS_PER_LONG-1)))
 #define EFI_TIMEOUT		(18 | (1UL << (BITS_PER_LONG-1)))
 #define EFI_ABORTED		(21 | (1UL << (BITS_PER_LONG-1)))
 #define EFI_SECURITY_VIOLATION	(26 | (1UL << (BITS_PER_LONG-1)))
-- 
cgit v1.2.3


From 94f7f6182c72ba642c1f20111681f9cc8621c95f Mon Sep 17 00:00:00 2001
From: Masahisa Kojima <masahisa.kojima@linaro.org>
Date: Tue, 7 Nov 2023 14:40:55 +0900
Subject: efivarfs: automatically update super block flag

efivar operation is updated when the tee_stmm_efi module is probed.
tee_stmm_efi module supports SetVariable runtime service, but user needs
to manually remount the efivarfs as RW to enable the write access if the
previous efivar operation does not support SetVariable and efivarfs is
mounted as read-only.

This commit notifies the update of efivar operation to efivarfs
subsystem, then drops SB_RDONLY flag if the efivar operation supports
SetVariable.

Signed-off-by: Masahisa Kojima <masahisa.kojima@linaro.org>
[ardb: use per-superblock instance of the notifier block]
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/efi.c  |  6 ++++++
 drivers/firmware/efi/vars.c |  8 ++++++++
 fs/efivarfs/internal.h      |  2 ++
 fs/efivarfs/super.c         | 27 +++++++++++++++++++++++++++
 include/linux/efi.h         |  8 ++++++++
 5 files changed, 51 insertions(+)

(limited to 'include')

diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 32a67c61c3b8..4fcda50acfa4 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -32,6 +32,7 @@
 #include <linux/ucs2_string.h>
 #include <linux/memblock.h>
 #include <linux/security.h>
+#include <linux/notifier.h>
 
 #include <asm/early_ioremap.h>
 
@@ -187,6 +188,9 @@ static const struct attribute_group efi_subsys_attr_group = {
 	.is_visible = efi_attr_is_visible,
 };
 
+struct blocking_notifier_head efivar_ops_nh;
+EXPORT_SYMBOL_GPL(efivar_ops_nh);
+
 static struct efivars generic_efivars;
 static struct efivar_operations generic_ops;
 
@@ -431,6 +435,8 @@ static int __init efisubsys_init(void)
 		platform_device_register_simple("efivars", 0, NULL, 0);
 	}
 
+	BLOCKING_INIT_NOTIFIER_HEAD(&efivar_ops_nh);
+
 	error = sysfs_create_group(efi_kobj, &efi_subsys_attr_group);
 	if (error) {
 		pr_err("efi: Sysfs attribute export failed with error %d.\n",
diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c
index e9dc7116daf1..f654e6f6af87 100644
--- a/drivers/firmware/efi/vars.c
+++ b/drivers/firmware/efi/vars.c
@@ -63,6 +63,7 @@ int efivars_register(struct efivars *efivars,
 		     const struct efivar_operations *ops)
 {
 	int rv;
+	int event;
 
 	if (down_interruptible(&efivars_lock))
 		return -EINTR;
@@ -77,6 +78,13 @@ int efivars_register(struct efivars *efivars,
 
 	__efivars = efivars;
 
+	if (efivar_supports_writes())
+		event = EFIVAR_OPS_RDWR;
+	else
+		event = EFIVAR_OPS_RDONLY;
+
+	blocking_notifier_call_chain(&efivar_ops_nh, event, NULL);
+
 	pr_info("Registered efivars operations\n");
 	rv = 0;
 out:
diff --git a/fs/efivarfs/internal.h b/fs/efivarfs/internal.h
index 1dc0ccce3cc3..169252e6dc46 100644
--- a/fs/efivarfs/internal.h
+++ b/fs/efivarfs/internal.h
@@ -17,6 +17,8 @@ struct efivarfs_mount_opts {
 struct efivarfs_fs_info {
 	struct efivarfs_mount_opts mount_opts;
 	struct list_head efivarfs_list;
+	struct super_block *sb;
+	struct notifier_block nb;
 };
 
 struct efi_variable {
diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index cee325b5bbdd..6038dd39367a 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -15,10 +15,30 @@
 #include <linux/slab.h>
 #include <linux/magic.h>
 #include <linux/statfs.h>
+#include <linux/notifier.h>
 #include <linux/printk.h>
 
 #include "internal.h"
 
+static int efivarfs_ops_notifier(struct notifier_block *nb, unsigned long event,
+				 void *data)
+{
+	struct efivarfs_fs_info *sfi = container_of(nb, struct efivarfs_fs_info, nb);
+
+	switch (event) {
+	case EFIVAR_OPS_RDONLY:
+		sfi->sb->s_flags |= SB_RDONLY;
+		break;
+	case EFIVAR_OPS_RDWR:
+		sfi->sb->s_flags &= ~SB_RDONLY;
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+
+	return NOTIFY_OK;
+}
+
 static void efivarfs_evict_inode(struct inode *inode)
 {
 	clear_inode(inode);
@@ -317,6 +337,12 @@ static int efivarfs_fill_super(struct super_block *sb, struct fs_context *fc)
 	if (!root)
 		return -ENOMEM;
 
+	sfi->sb = sb;
+	sfi->nb.notifier_call = efivarfs_ops_notifier;
+	err = blocking_notifier_chain_register(&efivar_ops_nh, &sfi->nb);
+	if (err)
+		return err;
+
 	err = efivar_init(efivarfs_callback, (void *)sb, true,
 			  &sfi->efivarfs_list);
 	if (err)
@@ -371,6 +397,7 @@ static void efivarfs_kill_sb(struct super_block *sb)
 {
 	struct efivarfs_fs_info *sfi = sb->s_fs_info;
 
+	blocking_notifier_chain_unregister(&efivar_ops_nh, &sfi->nb);
 	kill_litter_super(sb);
 
 	/* Remove all entries and destroy */
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 3668aa204c47..c74f47711f0b 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -1349,6 +1349,14 @@ bool efi_config_table_is_usable(const efi_guid_t *guid, unsigned long table)
 
 umode_t efi_attr_is_visible(struct kobject *kobj, struct attribute *attr, int n);
 
+/*
+ * efivar ops event type
+ */
+#define EFIVAR_OPS_RDONLY 0
+#define EFIVAR_OPS_RDWR 1
+
+extern struct blocking_notifier_head efivar_ops_nh;
+
 void efivars_generic_ops_register(void);
 void efivars_generic_ops_unregister(void);
 
-- 
cgit v1.2.3


From 704af3a40747e395b67892127943e6ffd5e2b642 Mon Sep 17 00:00:00 2001
From: Armin Wolf <W_Armin@gmx.de>
Date: Sun, 10 Dec 2023 21:24:43 +0100
Subject: platform/x86: wmi: Remove chardev interface
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The design of the WMI chardev interface is broken:
- it assumes that WMI drivers are not instantiated twice
- it offers next to no abstractions, the WMI driver gets
a raw byte buffer
- it is only used by a single driver, something which is
unlikely to change

Since the only user (dell-smbios-wmi) has been migrated
to his own ioctl interface, remove it.

Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Armin Wolf <W_Armin@gmx.de>
Link: https://lore.kernel.org/r/20231210202443.646427-6-W_Armin@gmx.de
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 drivers/platform/x86/wmi.c | 180 ++-------------------------------------------
 include/linux/wmi.h        |   8 --
 2 files changed, 5 insertions(+), 183 deletions(-)

(limited to 'include')

diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c
index 7df5b5ee7983..7303702290e5 100644
--- a/drivers/platform/x86/wmi.c
+++ b/drivers/platform/x86/wmi.c
@@ -23,17 +23,14 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/list.h>
-#include <linux/miscdevice.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/sysfs.h>
 #include <linux/types.h>
-#include <linux/uaccess.h>
 #include <linux/uuid.h>
 #include <linux/wmi.h>
 #include <linux/fs.h>
-#include <uapi/linux/wmi.h>
 
 MODULE_AUTHOR("Carlos Corbacho");
 MODULE_DESCRIPTION("ACPI-WMI Mapping Driver");
@@ -66,12 +63,9 @@ struct wmi_block {
 	struct wmi_device dev;
 	struct list_head list;
 	struct guid_block gblock;
-	struct miscdevice char_dev;
-	struct mutex char_mutex;
 	struct acpi_device *acpi_device;
 	wmi_notify_handler handler;
 	void *handler_data;
-	u64 req_buf_size;
 	unsigned long flags;
 };
 
@@ -256,26 +250,6 @@ static void wmi_device_put(struct wmi_device *wdev)
  * Exported WMI functions
  */
 
-/**
- * set_required_buffer_size - Sets the buffer size needed for performing IOCTL
- * @wdev: A wmi bus device from a driver
- * @length: Required buffer size
- *
- * Allocates memory needed for buffer, stores the buffer size in that memory.
- *
- * Return: 0 on success or a negative error code for failure.
- */
-int set_required_buffer_size(struct wmi_device *wdev, u64 length)
-{
-	struct wmi_block *wblock;
-
-	wblock = container_of(wdev, struct wmi_block, dev);
-	wblock->req_buf_size = length;
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(set_required_buffer_size);
-
 /**
  * wmi_instance_count - Get number of WMI object instances
  * @guid_string: 36 char string of the form fa50ff2b-f2e8-45de-83fa-65417f2f49ba
@@ -884,111 +858,12 @@ static int wmi_dev_match(struct device *dev, struct device_driver *driver)
 
 	return 0;
 }
-static int wmi_char_open(struct inode *inode, struct file *filp)
-{
-	/*
-	 * The miscdevice already stores a pointer to itself
-	 * inside filp->private_data
-	 */
-	struct wmi_block *wblock = container_of(filp->private_data, struct wmi_block, char_dev);
-
-	filp->private_data = wblock;
-
-	return nonseekable_open(inode, filp);
-}
-
-static ssize_t wmi_char_read(struct file *filp, char __user *buffer,
-			     size_t length, loff_t *offset)
-{
-	struct wmi_block *wblock = filp->private_data;
-
-	return simple_read_from_buffer(buffer, length, offset,
-				       &wblock->req_buf_size,
-				       sizeof(wblock->req_buf_size));
-}
-
-static long wmi_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
-{
-	struct wmi_ioctl_buffer __user *input =
-		(struct wmi_ioctl_buffer __user *) arg;
-	struct wmi_block *wblock = filp->private_data;
-	struct wmi_ioctl_buffer *buf;
-	struct wmi_driver *wdriver;
-	int ret;
-
-	if (_IOC_TYPE(cmd) != WMI_IOC)
-		return -ENOTTY;
-
-	/* make sure we're not calling a higher instance than exists*/
-	if (_IOC_NR(cmd) >= wblock->gblock.instance_count)
-		return -EINVAL;
-
-	mutex_lock(&wblock->char_mutex);
-	buf = wblock->handler_data;
-	if (get_user(buf->length, &input->length)) {
-		dev_dbg(&wblock->dev.dev, "Read length from user failed\n");
-		ret = -EFAULT;
-		goto out_ioctl;
-	}
-	/* if it's too small, abort */
-	if (buf->length < wblock->req_buf_size) {
-		dev_err(&wblock->dev.dev,
-			"Buffer %lld too small, need at least %lld\n",
-			buf->length, wblock->req_buf_size);
-		ret = -EINVAL;
-		goto out_ioctl;
-	}
-	/* if it's too big, warn, driver will only use what is needed */
-	if (buf->length > wblock->req_buf_size)
-		dev_warn(&wblock->dev.dev,
-			"Buffer %lld is bigger than required %lld\n",
-			buf->length, wblock->req_buf_size);
-
-	/* copy the structure from userspace */
-	if (copy_from_user(buf, input, wblock->req_buf_size)) {
-		dev_dbg(&wblock->dev.dev, "Copy %llu from user failed\n",
-			wblock->req_buf_size);
-		ret = -EFAULT;
-		goto out_ioctl;
-	}
-
-	/* let the driver do any filtering and do the call */
-	wdriver = drv_to_wdrv(wblock->dev.dev.driver);
-	if (!try_module_get(wdriver->driver.owner)) {
-		ret = -EBUSY;
-		goto out_ioctl;
-	}
-	ret = wdriver->filter_callback(&wblock->dev, cmd, buf);
-	module_put(wdriver->driver.owner);
-	if (ret)
-		goto out_ioctl;
-
-	/* return the result (only up to our internal buffer size) */
-	if (copy_to_user(input, buf, wblock->req_buf_size)) {
-		dev_dbg(&wblock->dev.dev, "Copy %llu to user failed\n",
-			wblock->req_buf_size);
-		ret = -EFAULT;
-	}
-
-out_ioctl:
-	mutex_unlock(&wblock->char_mutex);
-	return ret;
-}
-
-static const struct file_operations wmi_fops = {
-	.owner		= THIS_MODULE,
-	.read		= wmi_char_read,
-	.open		= wmi_char_open,
-	.unlocked_ioctl	= wmi_ioctl,
-	.compat_ioctl	= compat_ptr_ioctl,
-};
 
 static int wmi_dev_probe(struct device *dev)
 {
 	struct wmi_block *wblock = dev_to_wblock(dev);
 	struct wmi_driver *wdriver = drv_to_wdrv(dev->driver);
 	int ret = 0;
-	char *buf;
 
 	if (ACPI_FAILURE(wmi_method_enable(wblock, true)))
 		dev_warn(dev, "failed to enable device -- probing anyway\n");
@@ -996,55 +871,17 @@ static int wmi_dev_probe(struct device *dev)
 	if (wdriver->probe) {
 		ret = wdriver->probe(dev_to_wdev(dev),
 				find_guid_context(wblock, wdriver));
-		if (ret != 0)
-			goto probe_failure;
-	}
-
-	/* driver wants a character device made */
-	if (wdriver->filter_callback) {
-		/* check that required buffer size declared by driver or MOF */
-		if (!wblock->req_buf_size) {
-			dev_err(&wblock->dev.dev,
-				"Required buffer size not set\n");
-			ret = -EINVAL;
-			goto probe_failure;
-		}
+		if (!ret) {
+			if (ACPI_FAILURE(wmi_method_enable(wblock, false)))
+				dev_warn(dev, "Failed to disable device\n");
 
-		wblock->handler_data = kmalloc(wblock->req_buf_size,
-					       GFP_KERNEL);
-		if (!wblock->handler_data) {
-			ret = -ENOMEM;
-			goto probe_failure;
-		}
-
-		buf = kasprintf(GFP_KERNEL, "wmi/%s", wdriver->driver.name);
-		if (!buf) {
-			ret = -ENOMEM;
-			goto probe_string_failure;
-		}
-		wblock->char_dev.minor = MISC_DYNAMIC_MINOR;
-		wblock->char_dev.name = buf;
-		wblock->char_dev.fops = &wmi_fops;
-		wblock->char_dev.mode = 0444;
-		ret = misc_register(&wblock->char_dev);
-		if (ret) {
-			dev_warn(dev, "failed to register char dev: %d\n", ret);
-			ret = -ENOMEM;
-			goto probe_misc_failure;
+			return ret;
 		}
 	}
 
 	set_bit(WMI_PROBED, &wblock->flags);
-	return 0;
 
-probe_misc_failure:
-	kfree(buf);
-probe_string_failure:
-	kfree(wblock->handler_data);
-probe_failure:
-	if (ACPI_FAILURE(wmi_method_enable(wblock, false)))
-		dev_warn(dev, "failed to disable device\n");
-	return ret;
+	return 0;
 }
 
 static void wmi_dev_remove(struct device *dev)
@@ -1054,12 +891,6 @@ static void wmi_dev_remove(struct device *dev)
 
 	clear_bit(WMI_PROBED, &wblock->flags);
 
-	if (wdriver->filter_callback) {
-		misc_deregister(&wblock->char_dev);
-		kfree(wblock->char_dev.name);
-		kfree(wblock->handler_data);
-	}
-
 	if (wdriver->remove)
 		wdriver->remove(dev_to_wdev(dev));
 
@@ -1131,7 +962,6 @@ static int wmi_create_device(struct device *wmi_bus_dev,
 
 	if (wblock->gblock.flags & ACPI_WMI_METHOD) {
 		wblock->dev.dev.type = &wmi_type_method;
-		mutex_init(&wblock->char_mutex);
 		goto out_init;
 	}
 
diff --git a/include/linux/wmi.h b/include/linux/wmi.h
index 8a643c39fcce..50f7f1e4fd4f 100644
--- a/include/linux/wmi.h
+++ b/include/linux/wmi.h
@@ -11,7 +11,6 @@
 #include <linux/device.h>
 #include <linux/acpi.h>
 #include <linux/mod_devicetable.h>
-#include <uapi/linux/wmi.h>
 
 /**
  * struct wmi_device - WMI device structure
@@ -47,8 +46,6 @@ acpi_status wmidev_block_set(struct wmi_device *wdev, u8 instance, const struct
 
 u8 wmidev_instance_count(struct wmi_device *wdev);
 
-extern int set_required_buffer_size(struct wmi_device *wdev, u64 length);
-
 /**
  * struct wmi_driver - WMI driver structure
  * @driver: Driver model structure
@@ -57,11 +54,8 @@ extern int set_required_buffer_size(struct wmi_device *wdev, u64 length);
  * @probe: Callback for device binding
  * @remove: Callback for device unbinding
  * @notify: Callback for receiving WMI events
- * @filter_callback: Callback for filtering device IOCTLs
  *
  * This represents WMI drivers which handle WMI devices.
- * @filter_callback is only necessary for drivers which
- * want to set up a WMI IOCTL interface.
  */
 struct wmi_driver {
 	struct device_driver driver;
@@ -71,8 +65,6 @@ struct wmi_driver {
 	int (*probe)(struct wmi_device *wdev, const void *context);
 	void (*remove)(struct wmi_device *wdev);
 	void (*notify)(struct wmi_device *device, union acpi_object *data);
-	long (*filter_callback)(struct wmi_device *wdev, unsigned int cmd,
-				struct wmi_ioctl_buffer *arg);
 };
 
 extern int __must_check __wmi_driver_register(struct wmi_driver *driver,
-- 
cgit v1.2.3


From 58e82a62669da52e688f4a8b89922c1839bf1001 Mon Sep 17 00:00:00 2001
From: Ma Jun <Jun.Ma2@amd.com>
Date: Mon, 11 Dec 2023 18:06:23 +0800
Subject: platform/x86/amd: Add support for AMD ACPI based Wifi band RFI
 mitigation feature

Due to electrical and mechanical constraints in certain platform designs
there may be likely interference of relatively high-powered harmonics of
the (G-)DDR memory clocks with local radio module frequency bands used
by Wifi 6/6e/7.

To mitigate this, AMD has introduced a mechanism that devices can use to
notify active use of particular frequencies so that other devices can make
relative internal adjustments as necessary to avoid this resonance.

Co-developed-by: Evan Quan <quanliangl@hotmail.com>
Signed-off-by: Evan Quan <quanliangl@hotmail.com>
Signed-off-by: Ma Jun <Jun.Ma2@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 drivers/platform/x86/amd/Kconfig  |  14 ++
 drivers/platform/x86/amd/Makefile |   1 +
 drivers/platform/x86/amd/wbrf.c   | 317 ++++++++++++++++++++++++++++++++++++++
 include/linux/acpi_amd_wbrf.h     |  91 +++++++++++
 4 files changed, 423 insertions(+)
 create mode 100644 drivers/platform/x86/amd/wbrf.c
 create mode 100644 include/linux/acpi_amd_wbrf.h

(limited to 'include')

diff --git a/drivers/platform/x86/amd/Kconfig b/drivers/platform/x86/amd/Kconfig
index 55f3a2fc6aec..54753213cc61 100644
--- a/drivers/platform/x86/amd/Kconfig
+++ b/drivers/platform/x86/amd/Kconfig
@@ -18,3 +18,17 @@ config AMD_HSMP
 
 	  If you choose to compile this driver as a module the module will be
 	  called amd_hsmp.
+
+config AMD_WBRF
+	bool "AMD Wifi RF Band mitigations (WBRF)"
+	depends on ACPI
+	help
+	  WBRF(Wifi Band RFI mitigation) mechanism allows Wifi drivers
+	  to notify the frequencies they are using so that other hardware
+	  can be reconfigured to avoid harmonic conflicts.
+
+	  AMD provides an ACPI based mechanism to support WBRF on platform with
+	  appropriate underlying support.
+
+	  This mechanism will only be activated on platforms that advertise a
+	  need for it.
diff --git a/drivers/platform/x86/amd/Makefile b/drivers/platform/x86/amd/Makefile
index f04932b7a7d1..dcec0a46f8af 100644
--- a/drivers/platform/x86/amd/Makefile
+++ b/drivers/platform/x86/amd/Makefile
@@ -8,3 +8,4 @@ obj-$(CONFIG_AMD_PMC)		+= pmc/
 amd_hsmp-y			:= hsmp.o
 obj-$(CONFIG_AMD_HSMP)		+= amd_hsmp.o
 obj-$(CONFIG_AMD_PMF)		+= pmf/
+obj-$(CONFIG_AMD_WBRF)		+= wbrf.o
diff --git a/drivers/platform/x86/amd/wbrf.c b/drivers/platform/x86/amd/wbrf.c
new file mode 100644
index 000000000000..dd197b3aebe0
--- /dev/null
+++ b/drivers/platform/x86/amd/wbrf.c
@@ -0,0 +1,317 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Wifi Frequency Band Manage Interface
+ * Copyright (C) 2023 Advanced Micro Devices
+ */
+
+#include <linux/acpi.h>
+#include <linux/acpi_amd_wbrf.h>
+
+/*
+ * Functions bit vector for WBRF method
+ *
+ * Bit 0: WBRF supported.
+ * Bit 1: Function 1 (Add / Remove frequency) is supported.
+ * Bit 2: Function 2 (Get frequency list) is supported.
+ */
+#define WBRF_ENABLED		0x0
+#define WBRF_RECORD			0x1
+#define WBRF_RETRIEVE		0x2
+
+#define WBRF_REVISION		0x1
+
+/*
+ * The data structure used for WBRF_RETRIEVE is not naturally aligned.
+ * And unfortunately the design has been settled down.
+ */
+struct amd_wbrf_ranges_out {
+	u32			num_of_ranges;
+	struct freq_band_range	band_list[MAX_NUM_OF_WBRF_RANGES];
+} __packed;
+
+static const guid_t wifi_acpi_dsm_guid =
+	GUID_INIT(0x7b7656cf, 0xdc3d, 0x4c1c,
+		  0x83, 0xe9, 0x66, 0xe7, 0x21, 0xde, 0x30, 0x70);
+
+/*
+ * Used to notify consumer (amdgpu driver currently) about
+ * the wifi frequency is change.
+ */
+static BLOCKING_NOTIFIER_HEAD(wbrf_chain_head);
+
+static int wbrf_record(struct acpi_device *adev, uint8_t action, struct wbrf_ranges_in_out *in)
+{
+	union acpi_object argv4;
+	union acpi_object *tmp;
+	union acpi_object *obj;
+	u32 num_of_ranges = 0;
+	u32 num_of_elements;
+	u32 arg_idx = 0;
+	int ret;
+	u32 i;
+
+	if (!in)
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(in->band_list); i++) {
+		if (in->band_list[i].start && in->band_list[i].end)
+			num_of_ranges++;
+	}
+
+	/*
+	 * The num_of_ranges value in the "in" object supplied by
+	 * the caller is required to be equal to the number of
+	 * entries in the band_list array in there.
+	 */
+	if (num_of_ranges != in->num_of_ranges)
+		return -EINVAL;
+
+	/*
+	 * Every input frequency band comes with two end points(start/end)
+	 * and each is accounted as an element. Meanwhile the range count
+	 * and action type are accounted as an element each.
+	 * So, the total element count = 2 * num_of_ranges + 1 + 1.
+	 */
+	num_of_elements = 2 * num_of_ranges + 2;
+
+	tmp = kcalloc(num_of_elements, sizeof(*tmp), GFP_KERNEL);
+	if (!tmp)
+		return -ENOMEM;
+
+	argv4.package.type = ACPI_TYPE_PACKAGE;
+	argv4.package.count = num_of_elements;
+	argv4.package.elements = tmp;
+
+	/* save the number of ranges*/
+	tmp[0].integer.type = ACPI_TYPE_INTEGER;
+	tmp[0].integer.value = num_of_ranges;
+
+	/* save the action(WBRF_RECORD_ADD/REMOVE/RETRIEVE) */
+	tmp[1].integer.type = ACPI_TYPE_INTEGER;
+	tmp[1].integer.value = action;
+
+	arg_idx = 2;
+	for (i = 0; i < ARRAY_SIZE(in->band_list); i++) {
+		if (!in->band_list[i].start || !in->band_list[i].end)
+			continue;
+
+		tmp[arg_idx].integer.type = ACPI_TYPE_INTEGER;
+		tmp[arg_idx++].integer.value = in->band_list[i].start;
+		tmp[arg_idx].integer.type = ACPI_TYPE_INTEGER;
+		tmp[arg_idx++].integer.value = in->band_list[i].end;
+	}
+
+	obj = acpi_evaluate_dsm(adev->handle, &wifi_acpi_dsm_guid,
+				WBRF_REVISION, WBRF_RECORD, &argv4);
+
+	if (!obj)
+		return -EINVAL;
+
+	if (obj->type != ACPI_TYPE_INTEGER) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ret = obj->integer.value;
+	if (ret)
+		ret = -EINVAL;
+
+out:
+	ACPI_FREE(obj);
+	kfree(tmp);
+
+	return ret;
+}
+
+/**
+ * acpi_amd_wbrf_add_remove - add or remove the frequency band the device is using
+ *
+ * @dev: device pointer
+ * @action: remove or add the frequency band into bios
+ * @in: input structure containing the frequency band the device is using
+ *
+ * Broadcast to other consumers the frequency band the device starts
+ * to use. Underneath the surface the information is cached into an
+ * internal buffer first. Then a notification is sent to all those
+ * registered consumers. So then they can retrieve that buffer to
+ * know the latest active frequency bands. Consumers that haven't
+ * yet been registered can retrieve the information from the cache
+ * when they register.
+ *
+ * Return:
+ * 0 for success add/remove wifi frequency band.
+ * Returns a negative error code for failure.
+ */
+int acpi_amd_wbrf_add_remove(struct device *dev, uint8_t action, struct wbrf_ranges_in_out *in)
+{
+	struct acpi_device *adev;
+	int ret;
+
+	adev = ACPI_COMPANION(dev);
+	if (!adev)
+		return -ENODEV;
+
+	ret = wbrf_record(adev, action, in);
+	if (ret)
+		return ret;
+
+	blocking_notifier_call_chain(&wbrf_chain_head, WBRF_CHANGED, NULL);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(acpi_amd_wbrf_add_remove);
+
+/**
+ * acpi_amd_wbrf_supported_producer - determine if the WBRF can be enabled
+ *                                    for the device as a producer
+ *
+ * @dev: device pointer
+ *
+ * Check if the platform equipped with necessary implementations to
+ * support WBRF for the device as a producer.
+ *
+ * Return:
+ * true if WBRF is supported, otherwise returns false
+ */
+bool acpi_amd_wbrf_supported_producer(struct device *dev)
+{
+	struct acpi_device *adev;
+
+	adev = ACPI_COMPANION(dev);
+	if (!adev)
+		return false;
+
+	return acpi_check_dsm(adev->handle, &wifi_acpi_dsm_guid,
+			      WBRF_REVISION, BIT(WBRF_RECORD));
+}
+EXPORT_SYMBOL_GPL(acpi_amd_wbrf_supported_producer);
+
+/**
+ * acpi_amd_wbrf_supported_consumer - determine if the WBRF can be enabled
+ *                                    for the device as a consumer
+ *
+ * @dev: device pointer
+ *
+ * Determine if the platform equipped with necessary implementations to
+ * support WBRF for the device as a consumer.
+ *
+ * Return:
+ * true if WBRF is supported, otherwise returns false.
+ */
+bool acpi_amd_wbrf_supported_consumer(struct device *dev)
+{
+	struct acpi_device *adev;
+
+	adev = ACPI_COMPANION(dev);
+	if (!adev)
+		return false;
+
+	return acpi_check_dsm(adev->handle, &wifi_acpi_dsm_guid,
+			      WBRF_REVISION, BIT(WBRF_RETRIEVE));
+}
+EXPORT_SYMBOL_GPL(acpi_amd_wbrf_supported_consumer);
+
+/**
+ * amd_wbrf_retrieve_freq_band - retrieve current active frequency bands
+ *
+ * @dev: device pointer
+ * @out: output structure containing all the active frequency bands
+ *
+ * Retrieve the current active frequency bands which were broadcasted
+ * by other producers. The consumer who calls this API should take
+ * proper actions if any of the frequency band may cause RFI with its
+ * own frequency band used.
+ *
+ * Return:
+ * 0 for getting wifi freq band successfully.
+ * Returns a negative error code for failure.
+ */
+int amd_wbrf_retrieve_freq_band(struct device *dev, struct wbrf_ranges_in_out *out)
+{
+	struct amd_wbrf_ranges_out acpi_out = {0};
+	struct acpi_device *adev;
+	union acpi_object *obj;
+	union acpi_object param;
+	int ret = 0;
+
+	adev = ACPI_COMPANION(dev);
+	if (!adev)
+		return -ENODEV;
+
+	param.type = ACPI_TYPE_STRING;
+	param.string.length = 0;
+	param.string.pointer = NULL;
+
+	obj = acpi_evaluate_dsm(adev->handle, &wifi_acpi_dsm_guid,
+							WBRF_REVISION, WBRF_RETRIEVE, &param);
+	if (!obj)
+		return -EINVAL;
+
+	/*
+	 * The return buffer is with variable length and the format below:
+	 * number_of_entries(1 DWORD):       Number of entries
+	 * start_freq of 1st entry(1 QWORD): Start frequency of the 1st entry
+	 * end_freq of 1st entry(1 QWORD):   End frequency of the 1st entry
+	 * ...
+	 * ...
+	 * start_freq of the last entry(1 QWORD)
+	 * end_freq of the last entry(1 QWORD)
+	 *
+	 * Thus the buffer length is determined by the number of entries.
+	 * - For zero entry scenario, the buffer length will be 4 bytes.
+	 * - For one entry scenario, the buffer length will be 20 bytes.
+	 */
+	if (obj->buffer.length > sizeof(acpi_out) || obj->buffer.length < 4) {
+		dev_err(dev, "Wrong sized WBRT information");
+		ret = -EINVAL;
+		goto out;
+	}
+	memcpy(&acpi_out, obj->buffer.pointer, obj->buffer.length);
+
+	out->num_of_ranges = acpi_out.num_of_ranges;
+	memcpy(out->band_list, acpi_out.band_list, sizeof(acpi_out.band_list));
+
+out:
+	ACPI_FREE(obj);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(amd_wbrf_retrieve_freq_band);
+
+/**
+ * amd_wbrf_register_notifier - register for notifications of frequency
+ *                                   band update
+ *
+ * @nb: driver notifier block
+ *
+ * The consumer should register itself via this API so that it can get
+ * notified on the frequency band updates from other producers.
+ *
+ * Return:
+ * 0 for registering a consumer driver successfully.
+ * Returns a negative error code for failure.
+ */
+int amd_wbrf_register_notifier(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_register(&wbrf_chain_head, nb);
+}
+EXPORT_SYMBOL_GPL(amd_wbrf_register_notifier);
+
+/**
+ * amd_wbrf_unregister_notifier - unregister for notifications of
+ *                                     frequency band update
+ *
+ * @nb: driver notifier block
+ *
+ * The consumer should call this API when it is longer interested with
+ * the frequency band updates from other producers. Usually, this should
+ * be performed during driver cleanup.
+ *
+ * Return:
+ * 0 for unregistering a consumer driver.
+ * Returns a negative error code for failure.
+ */
+int amd_wbrf_unregister_notifier(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_unregister(&wbrf_chain_head, nb);
+}
+EXPORT_SYMBOL_GPL(amd_wbrf_unregister_notifier);
diff --git a/include/linux/acpi_amd_wbrf.h b/include/linux/acpi_amd_wbrf.h
new file mode 100644
index 000000000000..898f31d536d4
--- /dev/null
+++ b/include/linux/acpi_amd_wbrf.h
@@ -0,0 +1,91 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Wifi Band Exclusion Interface (AMD ACPI Implementation)
+ * Copyright (C) 2023 Advanced Micro Devices
+ */
+
+#ifndef _ACPI_AMD_WBRF_H
+#define _ACPI_AMD_WBRF_H
+
+#include <linux/device.h>
+#include <linux/notifier.h>
+
+/* The maximum number of frequency band ranges */
+#define MAX_NUM_OF_WBRF_RANGES		11
+
+/* Record actions */
+#define WBRF_RECORD_ADD		0x0
+#define WBRF_RECORD_REMOVE	0x1
+
+/**
+ * struct freq_band_range - Wifi frequency band range definition
+ * @start: start frequency point (in Hz)
+ * @end: end frequency point (in Hz)
+ */
+struct freq_band_range {
+	u64		start;
+	u64		end;
+};
+
+/**
+ * struct wbrf_ranges_in_out - wbrf ranges info
+ * @num_of_ranges: total number of band ranges in this struct
+ * @band_list: array of Wifi band ranges
+ */
+struct wbrf_ranges_in_out {
+	u64			num_of_ranges;
+	struct freq_band_range	band_list[MAX_NUM_OF_WBRF_RANGES];
+};
+
+/**
+ * enum wbrf_notifier_actions - wbrf notifier actions index
+ * @WBRF_CHANGED: there was some frequency band updates. The consumers
+ *               should retrieve the latest active frequency bands.
+ */
+enum wbrf_notifier_actions {
+	WBRF_CHANGED,
+};
+
+#if IS_ENABLED(CONFIG_AMD_WBRF)
+bool acpi_amd_wbrf_supported_producer(struct device *dev);
+int acpi_amd_wbrf_add_remove(struct device *dev, uint8_t action, struct wbrf_ranges_in_out *in);
+bool acpi_amd_wbrf_supported_consumer(struct device *dev);
+int amd_wbrf_retrieve_freq_band(struct device *dev, struct wbrf_ranges_in_out *out);
+int amd_wbrf_register_notifier(struct notifier_block *nb);
+int amd_wbrf_unregister_notifier(struct notifier_block *nb);
+#else
+static inline
+bool acpi_amd_wbrf_supported_consumer(struct device *dev)
+{
+	return false;
+}
+
+static inline
+int acpi_amd_wbrf_add_remove(struct device *dev, uint8_t action, struct wbrf_ranges_in_out *in)
+{
+	return -ENODEV;
+}
+
+static inline
+bool acpi_amd_wbrf_supported_producer(struct device *dev)
+{
+	return false;
+}
+static inline
+int amd_wbrf_retrieve_freq_band(struct device *dev, struct wbrf_ranges_in_out *out)
+{
+	return -ENODEV;
+}
+static inline
+int amd_wbrf_register_notifier(struct notifier_block *nb)
+{
+	return -ENODEV;
+}
+static inline
+int amd_wbrf_unregister_notifier(struct notifier_block *nb)
+{
+	return -ENODEV;
+}
+#endif /* CONFIG_AMD_WBRF */
+
+#endif /* _ACPI_AMD_WBRF_H */
-- 
cgit v1.2.3


From 2ffdd4773d98b1f7488f8e37bd881bbecec24d85 Mon Sep 17 00:00:00 2001
From: Hsiao Chien Sung <shawn.sung@mediatek.com>
Date: Tue, 24 Oct 2023 21:00:33 +0800
Subject: soc: mediatek: Support MT8188 VDOSYS1 Padding in mtk-mmsys

- Add Padding components
- Add Mutex module definitions for Padding

Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Signed-off-by: Hsiao Chien Sung <shawn.sung@mediatek.com>
Signed-off-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
---
 drivers/soc/mediatek/mtk-mutex.c       | 16 ++++++++++++++++
 include/linux/soc/mediatek/mtk-mmsys.h |  8 ++++++++
 2 files changed, 24 insertions(+)

(limited to 'include')

diff --git a/drivers/soc/mediatek/mtk-mutex.c b/drivers/soc/mediatek/mtk-mutex.c
index e76722289175..73c256d3950b 100644
--- a/drivers/soc/mediatek/mtk-mutex.c
+++ b/drivers/soc/mediatek/mtk-mutex.c
@@ -141,6 +141,14 @@
 #define MT8188_MUTEX_MOD_DISP1_MDP_RDMA5	5
 #define MT8188_MUTEX_MOD_DISP1_MDP_RDMA6	6
 #define MT8188_MUTEX_MOD_DISP1_MDP_RDMA7	7
+#define MT8188_MUTEX_MOD_DISP1_PADDING0		8
+#define MT8188_MUTEX_MOD_DISP1_PADDING1		9
+#define MT8188_MUTEX_MOD_DISP1_PADDING2		10
+#define MT8188_MUTEX_MOD_DISP1_PADDING3		11
+#define MT8188_MUTEX_MOD_DISP1_PADDING4		12
+#define MT8188_MUTEX_MOD_DISP1_PADDING5		13
+#define MT8188_MUTEX_MOD_DISP1_PADDING6		14
+#define MT8188_MUTEX_MOD_DISP1_PADDING7		15
 #define MT8188_MUTEX_MOD_DISP1_VPP_MERGE0	20
 #define MT8188_MUTEX_MOD_DISP1_VPP_MERGE1	21
 #define MT8188_MUTEX_MOD_DISP1_VPP_MERGE2	22
@@ -473,6 +481,14 @@ static const unsigned int mt8188_mutex_mod[DDP_COMPONENT_ID_MAX] = {
 	[DDP_COMPONENT_MDP_RDMA5] = MT8188_MUTEX_MOD_DISP1_MDP_RDMA5,
 	[DDP_COMPONENT_MDP_RDMA6] = MT8188_MUTEX_MOD_DISP1_MDP_RDMA6,
 	[DDP_COMPONENT_MDP_RDMA7] = MT8188_MUTEX_MOD_DISP1_MDP_RDMA7,
+	[DDP_COMPONENT_PADDING0] = MT8188_MUTEX_MOD_DISP1_PADDING0,
+	[DDP_COMPONENT_PADDING1] = MT8188_MUTEX_MOD_DISP1_PADDING1,
+	[DDP_COMPONENT_PADDING2] = MT8188_MUTEX_MOD_DISP1_PADDING2,
+	[DDP_COMPONENT_PADDING3] = MT8188_MUTEX_MOD_DISP1_PADDING3,
+	[DDP_COMPONENT_PADDING4] = MT8188_MUTEX_MOD_DISP1_PADDING4,
+	[DDP_COMPONENT_PADDING5] = MT8188_MUTEX_MOD_DISP1_PADDING5,
+	[DDP_COMPONENT_PADDING6] = MT8188_MUTEX_MOD_DISP1_PADDING6,
+	[DDP_COMPONENT_PADDING7] = MT8188_MUTEX_MOD_DISP1_PADDING7,
 	[DDP_COMPONENT_MERGE1] = MT8188_MUTEX_MOD_DISP1_VPP_MERGE0,
 	[DDP_COMPONENT_MERGE2] = MT8188_MUTEX_MOD_DISP1_VPP_MERGE1,
 	[DDP_COMPONENT_MERGE3] = MT8188_MUTEX_MOD_DISP1_VPP_MERGE2,
diff --git a/include/linux/soc/mediatek/mtk-mmsys.h b/include/linux/soc/mediatek/mtk-mmsys.h
index 2475ef914746..4885b065b849 100644
--- a/include/linux/soc/mediatek/mtk-mmsys.h
+++ b/include/linux/soc/mediatek/mtk-mmsys.h
@@ -62,6 +62,14 @@ enum mtk_ddp_comp_id {
 	DDP_COMPONENT_OVL_2L1,
 	DDP_COMPONENT_OVL_2L2,
 	DDP_COMPONENT_OVL1,
+	DDP_COMPONENT_PADDING0,
+	DDP_COMPONENT_PADDING1,
+	DDP_COMPONENT_PADDING2,
+	DDP_COMPONENT_PADDING3,
+	DDP_COMPONENT_PADDING4,
+	DDP_COMPONENT_PADDING5,
+	DDP_COMPONENT_PADDING6,
+	DDP_COMPONENT_PADDING7,
 	DDP_COMPONENT_POSTMASK0,
 	DDP_COMPONENT_PWM0,
 	DDP_COMPONENT_PWM1,
-- 
cgit v1.2.3


From d1c371035c8204112d84266e6bde7537f25448f7 Mon Sep 17 00:00:00 2001
From: Chao Yu <chao@kernel.org>
Date: Sun, 10 Dec 2023 10:50:28 +0800
Subject: quota: convert dquot_claim_space_nodirty() to return void

dquot_claim_space_nodirty() always return zero, let's convert it
to return void, then, its caller can get rid of handling failure
case.

Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jan Kara <jack@suse.cz>
Message-Id: <20231210025028.3262900-1-chao@kernel.org>
---
 fs/quota/dquot.c         |  6 +++---
 include/linux/quotaops.h | 15 +++++----------
 2 files changed, 8 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 58b5de081b57..44ff2813ae51 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -1787,7 +1787,7 @@ EXPORT_SYMBOL(dquot_alloc_inode);
 /*
  * Convert in-memory reserved quotas to real consumed quotas
  */
-int dquot_claim_space_nodirty(struct inode *inode, qsize_t number)
+void dquot_claim_space_nodirty(struct inode *inode, qsize_t number)
 {
 	struct dquot **dquots;
 	int cnt, index;
@@ -1797,7 +1797,7 @@ int dquot_claim_space_nodirty(struct inode *inode, qsize_t number)
 		*inode_reserved_space(inode) -= number;
 		__inode_add_bytes(inode, number);
 		spin_unlock(&inode->i_lock);
-		return 0;
+		return;
 	}
 
 	dquots = i_dquot(inode);
@@ -1822,7 +1822,7 @@ int dquot_claim_space_nodirty(struct inode *inode, qsize_t number)
 	spin_unlock(&inode->i_lock);
 	mark_all_dquot_dirty(dquots);
 	srcu_read_unlock(&dquot_srcu, index);
-	return 0;
+	return;
 }
 EXPORT_SYMBOL(dquot_claim_space_nodirty);
 
diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h
index 4fa4ef0a173a..06cc8888199e 100644
--- a/include/linux/quotaops.h
+++ b/include/linux/quotaops.h
@@ -74,7 +74,7 @@ void __dquot_free_space(struct inode *inode, qsize_t number, int flags);
 
 int dquot_alloc_inode(struct inode *inode);
 
-int dquot_claim_space_nodirty(struct inode *inode, qsize_t number);
+void dquot_claim_space_nodirty(struct inode *inode, qsize_t number);
 void dquot_free_inode(struct inode *inode);
 void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number);
 
@@ -257,10 +257,9 @@ static inline void __dquot_free_space(struct inode *inode, qsize_t number,
 		inode_sub_bytes(inode, number);
 }
 
-static inline int dquot_claim_space_nodirty(struct inode *inode, qsize_t number)
+static inline void dquot_claim_space_nodirty(struct inode *inode, qsize_t number)
 {
 	inode_add_bytes(inode, number);
-	return 0;
 }
 
 static inline int dquot_reclaim_space_nodirty(struct inode *inode,
@@ -358,14 +357,10 @@ static inline int dquot_reserve_block(struct inode *inode, qsize_t nr)
 				DQUOT_SPACE_WARN|DQUOT_SPACE_RESERVE);
 }
 
-static inline int dquot_claim_block(struct inode *inode, qsize_t nr)
+static inline void dquot_claim_block(struct inode *inode, qsize_t nr)
 {
-	int ret;
-
-	ret = dquot_claim_space_nodirty(inode, nr << inode->i_blkbits);
-	if (!ret)
-		mark_inode_dirty_sync(inode);
-	return ret;
+	dquot_claim_space_nodirty(inode, nr << inode->i_blkbits);
+	mark_inode_dirty_sync(inode);
 }
 
 static inline void dquot_reclaim_block(struct inode *inode, qsize_t nr)
-- 
cgit v1.2.3


From 2ebe81c814355d000fe49d9c4213983844dcb32b Mon Sep 17 00:00:00 2001
From: Aleksander Lobakin <aleksander.lobakin@intel.com>
Date: Wed, 6 Dec 2023 21:59:19 +0100
Subject: net, xdp: Allow metadata > 32

32 bytes may be not enough for some custom metadata. Relax the restriction,
allow metadata larger than 32 bytes and make __skb_metadata_differs() work
with bigger lengths.

Now size of metadata is only limited by the fact it is stored as u8 in
skb_shared_info, so maximum possible value is 255. Size still has to be
aligned to 4, so the actual upper limit becomes 252. Most driver
implementations will offer less, none can offer more.

Other important conditions, such as having enough space for xdp_frame
building, are already checked in bpf_xdp_adjust_meta().

Signed-off-by: Aleksander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/eb87653c-8ff8-447d-a7a1-25961f60518a@kernel.org
Link: https://lore.kernel.org/bpf/20231206205919.404415-3-larysa.zaremba@intel.com
---
 include/linux/skbuff.h | 13 ++++++++-----
 include/net/xdp.h      |  7 ++++++-
 2 files changed, 14 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index b370eb8d70f7..df6ef42639d8 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -4247,10 +4247,13 @@ static inline bool __skb_metadata_differs(const struct sk_buff *skb_a,
 {
 	const void *a = skb_metadata_end(skb_a);
 	const void *b = skb_metadata_end(skb_b);
-	/* Using more efficient varaiant than plain call to memcmp(). */
-#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
 	u64 diffs = 0;
 
+	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ||
+	    BITS_PER_LONG != 64)
+		goto slow;
+
+	/* Using more efficient variant than plain call to memcmp(). */
 	switch (meta_len) {
 #define __it(x, op) (x -= sizeof(u##op))
 #define __it_diff(a, b, op) (*(u##op *)__it(a, op)) ^ (*(u##op *)__it(b, op))
@@ -4270,11 +4273,11 @@ static inline bool __skb_metadata_differs(const struct sk_buff *skb_a,
 		fallthrough;
 	case  4: diffs |= __it_diff(a, b, 32);
 		break;
+	default:
+slow:
+		return memcmp(a - meta_len, b - meta_len, meta_len);
 	}
 	return diffs;
-#else
-	return memcmp(a - meta_len, b - meta_len, meta_len);
-#endif
 }
 
 static inline bool skb_metadata_differs(const struct sk_buff *skb_a,
diff --git a/include/net/xdp.h b/include/net/xdp.h
index 349c36fb5fd8..5d3673afc037 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -369,7 +369,12 @@ xdp_data_meta_unsupported(const struct xdp_buff *xdp)
 
 static inline bool xdp_metalen_invalid(unsigned long metalen)
 {
-	return (metalen & (sizeof(__u32) - 1)) || (metalen > 32);
+	unsigned long meta_max;
+
+	meta_max = type_max(typeof_member(struct skb_shared_info, meta_len));
+	BUILD_BUG_ON(!__builtin_constant_p(meta_max));
+
+	return !IS_ALIGNED(metalen, sizeof(u32)) || metalen > meta_max;
 }
 
 struct xdp_attachment_info {
-- 
cgit v1.2.3


From 718ab8226636a1a3a7d281f5d6a7ad7c925efe5a Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan+linaro@kernel.org>
Date: Tue, 28 Nov 2023 09:15:07 +0100
Subject: PCI/ASPM: Add pci_enable_link_state_locked()

Add pci_enable_link_state_locked() for enabling link states that can be
used in contexts where a pci_bus_sem read lock is already held (e.g. from
pci_walk_bus()).

This helper will be used to fix a couple of potential deadlocks where
the current helper is called with the lock already held, hence the CC
stable tag.

Fixes: f492edb40b54 ("PCI: vmd: Add quirk to configure PCIe ASPM and LTR")
Link: https://lore.kernel.org/r/20231128081512.19387-2-johan+linaro@kernel.org
Signed-off-by: Johan Hovold <johan+linaro@kernel.org>
[bhelgaas: include helper name in subject, commit log]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Cc: <stable@vger.kernel.org>	# 6.3
Cc: Michael Bottini <michael.a.bottini@linux.intel.com>
Cc: David E. Box <david.e.box@linux.intel.com>
---
 drivers/pci/pcie/aspm.c | 53 +++++++++++++++++++++++++++++++++++++------------
 include/linux/pci.h     |  3 +++
 2 files changed, 43 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index 50b04ae5c394..5eb462772354 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -1109,17 +1109,7 @@ int pci_disable_link_state(struct pci_dev *pdev, int state)
 }
 EXPORT_SYMBOL(pci_disable_link_state);
 
-/**
- * pci_enable_link_state - Clear and set the default device link state so that
- * the link may be allowed to enter the specified states. Note that if the
- * BIOS didn't grant ASPM control to the OS, this does nothing because we can't
- * touch the LNKCTL register. Also note that this does not enable states
- * disabled by pci_disable_link_state(). Return 0 or a negative errno.
- *
- * @pdev: PCI device
- * @state: Mask of ASPM link states to enable
- */
-int pci_enable_link_state(struct pci_dev *pdev, int state)
+static int __pci_enable_link_state(struct pci_dev *pdev, int state, bool locked)
 {
 	struct pcie_link_state *link = pcie_aspm_get_link(pdev);
 
@@ -1136,7 +1126,8 @@ int pci_enable_link_state(struct pci_dev *pdev, int state)
 		return -EPERM;
 	}
 
-	down_read(&pci_bus_sem);
+	if (!locked)
+		down_read(&pci_bus_sem);
 	mutex_lock(&aspm_lock);
 	link->aspm_default = 0;
 	if (state & PCIE_LINK_STATE_L0S)
@@ -1157,12 +1148,48 @@ int pci_enable_link_state(struct pci_dev *pdev, int state)
 	link->clkpm_default = (state & PCIE_LINK_STATE_CLKPM) ? 1 : 0;
 	pcie_set_clkpm(link, policy_to_clkpm_state(link));
 	mutex_unlock(&aspm_lock);
-	up_read(&pci_bus_sem);
+	if (!locked)
+		up_read(&pci_bus_sem);
 
 	return 0;
 }
+
+/**
+ * pci_enable_link_state - Clear and set the default device link state so that
+ * the link may be allowed to enter the specified states. Note that if the
+ * BIOS didn't grant ASPM control to the OS, this does nothing because we can't
+ * touch the LNKCTL register. Also note that this does not enable states
+ * disabled by pci_disable_link_state(). Return 0 or a negative errno.
+ *
+ * @pdev: PCI device
+ * @state: Mask of ASPM link states to enable
+ */
+int pci_enable_link_state(struct pci_dev *pdev, int state)
+{
+	return __pci_enable_link_state(pdev, state, false);
+}
 EXPORT_SYMBOL(pci_enable_link_state);
 
+/**
+ * pci_enable_link_state_locked - Clear and set the default device link state
+ * so that the link may be allowed to enter the specified states. Note that if
+ * the BIOS didn't grant ASPM control to the OS, this does nothing because we
+ * can't touch the LNKCTL register. Also note that this does not enable states
+ * disabled by pci_disable_link_state(). Return 0 or a negative errno.
+ *
+ * @pdev: PCI device
+ * @state: Mask of ASPM link states to enable
+ *
+ * Context: Caller holds pci_bus_sem read lock.
+ */
+int pci_enable_link_state_locked(struct pci_dev *pdev, int state)
+{
+	lockdep_assert_held_read(&pci_bus_sem);
+
+	return __pci_enable_link_state(pdev, state, true);
+}
+EXPORT_SYMBOL(pci_enable_link_state_locked);
+
 static int pcie_aspm_set_policy(const char *val,
 				const struct kernel_param *kp)
 {
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 60ca768bc867..dea043bc1e38 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1829,6 +1829,7 @@ extern bool pcie_ports_native;
 int pci_disable_link_state(struct pci_dev *pdev, int state);
 int pci_disable_link_state_locked(struct pci_dev *pdev, int state);
 int pci_enable_link_state(struct pci_dev *pdev, int state);
+int pci_enable_link_state_locked(struct pci_dev *pdev, int state);
 void pcie_no_aspm(void);
 bool pcie_aspm_support_enabled(void);
 bool pcie_aspm_enabled(struct pci_dev *pdev);
@@ -1839,6 +1840,8 @@ static inline int pci_disable_link_state_locked(struct pci_dev *pdev, int state)
 { return 0; }
 static inline int pci_enable_link_state(struct pci_dev *pdev, int state)
 { return 0; }
+static inline int pci_enable_link_state_locked(struct pci_dev *pdev, int state)
+{ return 0; }
 static inline void pcie_no_aspm(void) { }
 static inline bool pcie_aspm_support_enabled(void) { return false; }
 static inline bool pcie_aspm_enabled(struct pci_dev *pdev) { return false; }
-- 
cgit v1.2.3


From 46eae99ef73302f9fb3dddcd67c374b3dffe8fd6 Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@redhat.com>
Date: Wed, 25 Oct 2023 16:02:02 +0200
Subject: add statmount(2) syscall

Add a way to query attributes of a single mount instead of having to parse
the complete /proc/$PID/mountinfo, which might be huge.

Lookup the mount the new 64bit mount ID.  If a mount needs to be queried
based on path, then statx(2) can be used to first query the mount ID
belonging to the path.

Design is based on a suggestion by Linus:

  "So I'd suggest something that is very much like "statfsat()", which gets
   a buffer and a length, and returns an extended "struct statfs" *AND*
   just a string description at the end."

The interface closely mimics that of statx.

Handle ASCII attributes by appending after the end of the structure (as per
above suggestion).  Pointers to strings are stored in u64 members to make
the structure the same regardless of pointer size.  Strings are nul
terminated.

Link: https://lore.kernel.org/all/CAHk-=wh5YifP7hzKSbwJj94+DZ2czjrZsczy6GBimiogZws=rg@mail.gmail.com/
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Link: https://lore.kernel.org/r/20231025140205.3586473-5-mszeredi@redhat.com
Reviewed-by: Ian Kent <raven@themaw.net>
[Christian Brauner <brauner@kernel.org>: various minor changes]
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/namespace.c             | 281 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/syscalls.h   |   5 +
 include/uapi/linux/mount.h |  53 +++++++++
 3 files changed, 339 insertions(+)

(limited to 'include')

diff --git a/fs/namespace.c b/fs/namespace.c
index d3665d025acb..ae35d8b6aca8 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -4683,6 +4683,287 @@ int show_path(struct seq_file *m, struct dentry *root)
 	return 0;
 }
 
+static struct vfsmount *lookup_mnt_in_ns(u64 id, struct mnt_namespace *ns)
+{
+	struct mount *mnt = mnt_find_id_at(ns, id);
+
+	if (!mnt || mnt->mnt_id_unique != id)
+		return NULL;
+
+	return &mnt->mnt;
+}
+
+struct kstatmount {
+	struct statmount __user *const buf;
+	size_t const bufsize;
+	struct vfsmount *const mnt;
+	u64 const mask;
+	struct seq_file seq;
+	struct path root;
+	struct statmount sm;
+	size_t pos;
+	int err;
+};
+
+typedef int (*statmount_func_t)(struct kstatmount *);
+
+static int statmount_string_seq(struct kstatmount *s, statmount_func_t func)
+{
+	size_t rem = s->bufsize - s->pos - sizeof(s->sm);
+	struct seq_file *seq = &s->seq;
+	int ret;
+
+	seq->count = 0;
+	seq->size = min(seq->size, rem);
+	seq->buf = kvmalloc(seq->size, GFP_KERNEL_ACCOUNT);
+	if (!seq->buf)
+		return -ENOMEM;
+
+	ret = func(s);
+	if (ret)
+		return ret;
+
+	if (seq_has_overflowed(seq)) {
+		if (seq->size == rem)
+			return -EOVERFLOW;
+		seq->size *= 2;
+		if (seq->size > MAX_RW_COUNT)
+			return -ENOMEM;
+		kvfree(seq->buf);
+		return 0;
+	}
+
+	/* Done */
+	return 1;
+}
+
+static void statmount_string(struct kstatmount *s, u64 mask, statmount_func_t func,
+		       u32 *str)
+{
+	int ret = s->pos + sizeof(s->sm) >= s->bufsize ? -EOVERFLOW : 0;
+	struct statmount *sm = &s->sm;
+	struct seq_file *seq = &s->seq;
+
+	if (s->err || !(s->mask & mask))
+		return;
+
+	seq->size = PAGE_SIZE;
+	while (!ret)
+		ret = statmount_string_seq(s, func);
+
+	if (ret < 0) {
+		s->err = ret;
+	} else {
+		seq->buf[seq->count++] = '\0';
+		if (copy_to_user(s->buf->str + s->pos, seq->buf, seq->count)) {
+			s->err = -EFAULT;
+		} else {
+			*str = s->pos;
+			s->pos += seq->count;
+		}
+	}
+	kvfree(seq->buf);
+	sm->mask |= mask;
+}
+
+static void statmount_numeric(struct kstatmount *s, u64 mask, statmount_func_t func)
+{
+	if (s->err || !(s->mask & mask))
+		return;
+
+	s->err = func(s);
+	s->sm.mask |= mask;
+}
+
+static u64 mnt_to_attr_flags(struct vfsmount *mnt)
+{
+	unsigned int mnt_flags = READ_ONCE(mnt->mnt_flags);
+	u64 attr_flags = 0;
+
+	if (mnt_flags & MNT_READONLY)
+		attr_flags |= MOUNT_ATTR_RDONLY;
+	if (mnt_flags & MNT_NOSUID)
+		attr_flags |= MOUNT_ATTR_NOSUID;
+	if (mnt_flags & MNT_NODEV)
+		attr_flags |= MOUNT_ATTR_NODEV;
+	if (mnt_flags & MNT_NOEXEC)
+		attr_flags |= MOUNT_ATTR_NOEXEC;
+	if (mnt_flags & MNT_NODIRATIME)
+		attr_flags |= MOUNT_ATTR_NODIRATIME;
+	if (mnt_flags & MNT_NOSYMFOLLOW)
+		attr_flags |= MOUNT_ATTR_NOSYMFOLLOW;
+
+	if (mnt_flags & MNT_NOATIME)
+		attr_flags |= MOUNT_ATTR_NOATIME;
+	else if (mnt_flags & MNT_RELATIME)
+		attr_flags |= MOUNT_ATTR_RELATIME;
+	else
+		attr_flags |= MOUNT_ATTR_STRICTATIME;
+
+	if (is_idmapped_mnt(mnt))
+		attr_flags |= MOUNT_ATTR_IDMAP;
+
+	return attr_flags;
+}
+
+static u64 mnt_to_propagation_flags(struct mount *m)
+{
+	u64 propagation = 0;
+
+	if (IS_MNT_SHARED(m))
+		propagation |= MS_SHARED;
+	if (IS_MNT_SLAVE(m))
+		propagation |= MS_SLAVE;
+	if (IS_MNT_UNBINDABLE(m))
+		propagation |= MS_UNBINDABLE;
+	if (!propagation)
+		propagation |= MS_PRIVATE;
+
+	return propagation;
+}
+
+static int statmount_sb_basic(struct kstatmount *s)
+{
+	struct super_block *sb = s->mnt->mnt_sb;
+
+	s->sm.sb_dev_major = MAJOR(sb->s_dev);
+	s->sm.sb_dev_minor = MINOR(sb->s_dev);
+	s->sm.sb_magic = sb->s_magic;
+	s->sm.sb_flags = sb->s_flags & (SB_RDONLY|SB_SYNCHRONOUS|SB_DIRSYNC|SB_LAZYTIME);
+
+	return 0;
+}
+
+static int statmount_mnt_basic(struct kstatmount *s)
+{
+	struct mount *m = real_mount(s->mnt);
+
+	s->sm.mnt_id = m->mnt_id_unique;
+	s->sm.mnt_parent_id = m->mnt_parent->mnt_id_unique;
+	s->sm.mnt_id_old = m->mnt_id;
+	s->sm.mnt_parent_id_old = m->mnt_parent->mnt_id;
+	s->sm.mnt_attr = mnt_to_attr_flags(&m->mnt);
+	s->sm.mnt_propagation = mnt_to_propagation_flags(m);
+	s->sm.mnt_peer_group = IS_MNT_SHARED(m) ? m->mnt_group_id : 0;
+	s->sm.mnt_master = IS_MNT_SLAVE(m) ? m->mnt_master->mnt_group_id : 0;
+
+	return 0;
+}
+
+static int statmount_propagate_from(struct kstatmount *s)
+{
+	struct mount *m = real_mount(s->mnt);
+
+	if (!IS_MNT_SLAVE(m))
+		return 0;
+
+	s->sm.propagate_from = get_dominating_id(m, &current->fs->root);
+
+	return 0;
+}
+
+static int statmount_mnt_root(struct kstatmount *s)
+{
+	struct seq_file *seq = &s->seq;
+	int err = show_path(seq, s->mnt->mnt_root);
+
+	if (!err && !seq_has_overflowed(seq)) {
+		seq->buf[seq->count] = '\0';
+		seq->count = string_unescape_inplace(seq->buf, UNESCAPE_OCTAL);
+	}
+	return err;
+}
+
+static int statmount_mnt_point(struct kstatmount *s)
+{
+	struct vfsmount *mnt = s->mnt;
+	struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
+	int err = seq_path_root(&s->seq, &mnt_path, &s->root, "");
+
+	return err == SEQ_SKIP ? 0 : err;
+}
+
+static int statmount_fs_type(struct kstatmount *s)
+{
+	struct seq_file *seq = &s->seq;
+	struct super_block *sb = s->mnt->mnt_sb;
+
+	seq_puts(seq, sb->s_type->name);
+	return 0;
+}
+
+static int do_statmount(struct kstatmount *s)
+{
+	struct statmount *sm = &s->sm;
+	struct mount *m = real_mount(s->mnt);
+	size_t copysize = min_t(size_t, s->bufsize, sizeof(*sm));
+	int err;
+
+	/*
+	 * Don't trigger audit denials. We just want to determine what
+	 * mounts to show users.
+	 */
+	if (!is_path_reachable(m, m->mnt.mnt_root, &s->root) &&
+	    !ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN))
+		return -EPERM;
+
+	err = security_sb_statfs(s->mnt->mnt_root);
+	if (err)
+		return err;
+
+	statmount_numeric(s, STATMOUNT_SB_BASIC, statmount_sb_basic);
+	statmount_numeric(s, STATMOUNT_MNT_BASIC, statmount_mnt_basic);
+	statmount_numeric(s, STATMOUNT_PROPAGATE_FROM, statmount_propagate_from);
+	statmount_string(s, STATMOUNT_FS_TYPE, statmount_fs_type, &sm->fs_type);
+	statmount_string(s, STATMOUNT_MNT_ROOT, statmount_mnt_root, &sm->mnt_root);
+	statmount_string(s, STATMOUNT_MNT_POINT, statmount_mnt_point, &sm->mnt_point);
+
+	if (s->err)
+		return s->err;
+
+	/* Return the number of bytes copied to the buffer */
+	sm->size = copysize + s->pos;
+
+	if (copy_to_user(s->buf, sm, copysize))
+		return -EFAULT;
+
+	return 0;
+}
+
+SYSCALL_DEFINE4(statmount, const struct mnt_id_req __user *, req,
+		struct statmount __user *, buf, size_t, bufsize,
+		unsigned int, flags)
+{
+	struct vfsmount *mnt;
+	struct mnt_id_req kreq;
+	int ret;
+
+	if (flags)
+		return -EINVAL;
+
+	if (copy_from_user(&kreq, req, sizeof(kreq)))
+		return -EFAULT;
+
+	down_read(&namespace_sem);
+	mnt = lookup_mnt_in_ns(kreq.mnt_id, current->nsproxy->mnt_ns);
+	ret = -ENOENT;
+	if (mnt) {
+		struct kstatmount s = {
+			.mask = kreq.request_mask,
+			.buf = buf,
+			.bufsize = bufsize,
+			.mnt = mnt,
+		};
+
+		get_fs_root(current->fs, &s.root);
+		ret = do_statmount(&s);
+		path_put(&s.root);
+	}
+	up_read(&namespace_sem);
+
+	return ret;
+}
+
 static void __init init_mount_tree(void)
 {
 	struct vfsmount *mnt;
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index fd9d12de7e92..530ca9adf5f1 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -74,6 +74,8 @@ struct landlock_ruleset_attr;
 enum landlock_rule_type;
 struct cachestat_range;
 struct cachestat;
+struct statmount;
+struct mnt_id_req;
 
 #include <linux/types.h>
 #include <linux/aio_abi.h>
@@ -407,6 +409,9 @@ asmlinkage long sys_statfs64(const char __user *path, size_t sz,
 asmlinkage long sys_fstatfs(unsigned int fd, struct statfs __user *buf);
 asmlinkage long sys_fstatfs64(unsigned int fd, size_t sz,
 				struct statfs64 __user *buf);
+asmlinkage long sys_statmount(const struct mnt_id_req __user *req,
+			      struct statmount __user *buf, size_t bufsize,
+			      unsigned int flags);
 asmlinkage long sys_truncate(const char __user *path, long length);
 asmlinkage long sys_ftruncate(unsigned int fd, unsigned long length);
 #if BITS_PER_LONG == 32
diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h
index bb242fdcfe6b..afdf4f2f6672 100644
--- a/include/uapi/linux/mount.h
+++ b/include/uapi/linux/mount.h
@@ -138,4 +138,57 @@ struct mount_attr {
 /* List of all mount_attr versions. */
 #define MOUNT_ATTR_SIZE_VER0	32 /* sizeof first published struct */
 
+
+/*
+ * Structure for getting mount/superblock/filesystem info with statmount(2).
+ *
+ * The interface is similar to statx(2): individual fields or groups can be
+ * selected with the @mask argument of statmount().  Kernel will set the @mask
+ * field according to the supported fields.
+ *
+ * If string fields are selected, then the caller needs to pass a buffer that
+ * has space after the fixed part of the structure.  Nul terminated strings are
+ * copied there and offsets relative to @str are stored in the relevant fields.
+ * If the buffer is too small, then EOVERFLOW is returned.  The actually used
+ * size is returned in @size.
+ */
+struct statmount {
+	__u32 size;		/* Total size, including strings */
+	__u32 __spare1;
+	__u64 mask;		/* What results were written */
+	__u32 sb_dev_major;	/* Device ID */
+	__u32 sb_dev_minor;
+	__u64 sb_magic;		/* ..._SUPER_MAGIC */
+	__u32 sb_flags;		/* SB_{RDONLY,SYNCHRONOUS,DIRSYNC,LAZYTIME} */
+	__u32 fs_type;		/* [str] Filesystem type */
+	__u64 mnt_id;		/* Unique ID of mount */
+	__u64 mnt_parent_id;	/* Unique ID of parent (for root == mnt_id) */
+	__u32 mnt_id_old;	/* Reused IDs used in proc/.../mountinfo */
+	__u32 mnt_parent_id_old;
+	__u64 mnt_attr;		/* MOUNT_ATTR_... */
+	__u64 mnt_propagation;	/* MS_{SHARED,SLAVE,PRIVATE,UNBINDABLE} */
+	__u64 mnt_peer_group;	/* ID of shared peer group */
+	__u64 mnt_master;	/* Mount receives propagation from this ID */
+	__u64 propagate_from;	/* Propagation from in current namespace */
+	__u32 mnt_root;		/* [str] Root of mount relative to root of fs */
+	__u32 mnt_point;	/* [str] Mountpoint relative to current root */
+	__u64 __spare2[50];
+	char str[];		/* Variable size part containing strings */
+};
+
+struct mnt_id_req {
+	__u64 mnt_id;
+	__u64 request_mask;
+};
+
+/*
+ * @mask bits for statmount(2)
+ */
+#define STATMOUNT_SB_BASIC		0x00000001U     /* Want/got sb_... */
+#define STATMOUNT_MNT_BASIC		0x00000002U	/* Want/got mnt_... */
+#define STATMOUNT_PROPAGATE_FROM	0x00000004U	/* Want/got propagate_from */
+#define STATMOUNT_MNT_ROOT		0x00000008U	/* Want/got mnt_root  */
+#define STATMOUNT_MNT_POINT		0x00000010U	/* Want/got mnt_point */
+#define STATMOUNT_FS_TYPE		0x00000020U	/* Want/got fs_type */
+
 #endif /* _UAPI_LINUX_MOUNT_H */
-- 
cgit v1.2.3


From 5bc2ea60897e0f899fb93930dd867dae7c8eb11f Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Date: Mon, 11 Dec 2023 20:27:47 +0800
Subject: iio: core: introduce trough info element for minimum values

The IIO_CHAN_INFO_PEAK info element is used for maximum values and
currently there is no equivalent for minimum values. Instead of
overloading the existing peak info element, a new info element can
be added.

In principle there is no need to add a _TROUGH_SCALE element as the
scale will be the same as the one required for INFO_PEAK, which in
turn is sometimes omitted if a single scale for peaks and raw values
is required.

Add an IIO_CHAN_INFO_TROUGH info element for minimum values.

Signed-off-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Link: https://lore.kernel.org/r/20231211122747.9723-1-579lpy@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/industrialio-core.c | 1 +
 include/linux/iio/types.h       | 1 +
 2 files changed, 2 insertions(+)

(limited to 'include')

diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index f6a123d397db..9a85752124dd 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -184,6 +184,7 @@ static const char * const iio_chan_info_postfix[] = {
 	[IIO_CHAN_INFO_THERMOCOUPLE_TYPE] = "thermocouple_type",
 	[IIO_CHAN_INFO_CALIBAMBIENT] = "calibambient",
 	[IIO_CHAN_INFO_ZEROPOINT] = "zeropoint",
+	[IIO_CHAN_INFO_TROUGH] = "trough_raw",
 };
 /**
  * iio_device_id() - query the unique ID for the device
diff --git a/include/linux/iio/types.h b/include/linux/iio/types.h
index 117bde7d6ad7..d89982c98368 100644
--- a/include/linux/iio/types.h
+++ b/include/linux/iio/types.h
@@ -68,6 +68,7 @@ enum iio_chan_info_enum {
 	IIO_CHAN_INFO_THERMOCOUPLE_TYPE,
 	IIO_CHAN_INFO_CALIBAMBIENT,
 	IIO_CHAN_INFO_ZEROPOINT,
+	IIO_CHAN_INFO_TROUGH,
 };
 
 #endif /* _IIO_TYPES_H_ */
-- 
cgit v1.2.3


From 4649620d9404d3aceb25891c24bab77143e3f21c Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Fri, 8 Dec 2023 20:13:44 +0100
Subject: thermal: core: Make thermal_zone_device_unregister() return after
 freeing the zone

Make thermal_zone_device_unregister() wait until all of the references
to the given thermal zone object have been dropped and free it before
returning.

This guarantees that when thermal_zone_device_unregister() returns,
there is no leftover activity regarding the thermal zone in question
which is required by some of its callers (for instance, modular driver
code that wants to know when it is safe to let the module go away).

Subsequently, this will allow some confusing device_is_registered()
checks to be dropped from the thermal sysfs and core code.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-and-tested-by: Lukasz Luba <lukasz.luba@arm.com>
Acked-by: Daniel Lezcano <daniel.lezcano@linaro.org>
---
 drivers/thermal/thermal_core.c | 6 +++++-
 include/linux/thermal.h        | 2 ++
 2 files changed, 7 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 625ba07cbe2f..70a294d12187 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -822,7 +822,7 @@ static void thermal_release(struct device *dev)
 		tz = to_thermal_zone(dev);
 		thermal_zone_destroy_device_groups(tz);
 		mutex_destroy(&tz->lock);
-		kfree(tz);
+		complete(&tz->removal);
 	} else if (!strncmp(dev_name(dev), "cooling_device",
 			    sizeof("cooling_device") - 1)) {
 		cdev = to_cooling_device(dev);
@@ -1315,6 +1315,7 @@ thermal_zone_device_register_with_trips(const char *type, struct thermal_trip *t
 	INIT_LIST_HEAD(&tz->thermal_instances);
 	ida_init(&tz->ida);
 	mutex_init(&tz->lock);
+	init_completion(&tz->removal);
 	id = ida_alloc(&thermal_tz_ida, GFP_KERNEL);
 	if (id < 0) {
 		result = id;
@@ -1494,6 +1495,9 @@ void thermal_zone_device_unregister(struct thermal_zone_device *tz)
 	put_device(&tz->device);
 
 	thermal_notify_tz_delete(tz_id);
+
+	wait_for_completion(&tz->removal);
+	kfree(tz);
 }
 EXPORT_SYMBOL_GPL(thermal_zone_device_unregister);
 
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 0ea99f50d57c..bedbaec9a42e 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -117,6 +117,7 @@ struct thermal_cooling_device {
  * @id:		unique id number for each thermal zone
  * @type:	the thermal zone device type
  * @device:	&struct device for this thermal zone
+ * @removal:	removal completion
  * @trip_temp_attrs:	attributes for trip points for sysfs: trip temperature
  * @trip_type_attrs:	attributes for trip points for sysfs: trip type
  * @trip_hyst_attrs:	attributes for trip points for sysfs: trip hysteresis
@@ -156,6 +157,7 @@ struct thermal_zone_device {
 	int id;
 	char type[THERMAL_NAME_LENGTH];
 	struct device device;
+	struct completion removal;
 	struct attribute_group trips_attribute_group;
 	struct thermal_attr *trip_temp_attrs;
 	struct thermal_attr *trip_type_attrs;
-- 
cgit v1.2.3


From 4e58aaeebb3c27993c734c99eae6881b196b1ddb Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Wed, 1 Nov 2023 18:28:38 -0700
Subject: rcu: Restrict access to RCU CPU stall notifiers

Although the RCU CPU stall notifiers can be useful for dumping state when
tracking down delicate forward-progress bugs where NUMA effects cause
cache lines to be delivered to a given CPU regularly, but always in a
state that prevents that CPU from making forward progress.  These bugs can
be detected by the RCU CPU stall-warning mechanism, but in some cases,
the stall-warnings printk()s disrupt the forward-progress bug before
any useful state can be obtained.

Unfortunately, the notifier mechanism added by commit 5b404fdabacf ("rcu:
Add RCU CPU stall notifier") can make matters worse if used at all
carelessly. For example, if the stall warning was caused by a lock not
being released, then any attempt to acquire that lock in the notifier
will hang. This will prevent not only the notifier from producing any
useful output, but it will also prevent the stall-warning message from
ever appearing.

This commit therefore hides this new RCU CPU stall notifier
mechanism under a new RCU_CPU_STALL_NOTIFIER Kconfig option that
depends on both DEBUG_KERNEL and RCU_EXPERT.  In addition, the
rcupdate.rcu_cpu_stall_notifiers=1 kernel boot parameter must also
be specified.  The RCU_CPU_STALL_NOTIFIER Kconfig option's help text
contains a warning and explains the dangers of careless use, recommending
lockless notifier code.  In addition, a WARN() is triggered each time
that an attempt is made to register a stall-warning notifier in kernels
built with CONFIG_RCU_CPU_STALL_NOTIFIER=y.

This combination of measures will keep use of this mechanism confined to
debug kernels and away from routine deployments.

[ paulmck: Apply Dan Carpenter feedback. ]

Fixes: 5b404fdabacf ("rcu: Add RCU CPU stall notifier")
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Neeraj Upadhyay (AMD) <neeraj.iitr10@gmail.com>
---
 Documentation/admin-guide/kernel-parameters.txt |  6 ++++++
 include/linux/rcu_notifier.h                    |  6 +++---
 kernel/rcu/Kconfig.debug                        | 25 +++++++++++++++++++++++++
 kernel/rcu/rcu.h                                |  8 +++++---
 kernel/rcu/rcutorture.c                         | 12 +++++++-----
 kernel/rcu/tree_stall.h                         | 11 ++++++++++-
 kernel/rcu/update.c                             |  6 ++++++
 7 files changed, 62 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 65731b060e3f..b72e2049c487 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -5302,6 +5302,12 @@
 			Dump ftrace buffer after reporting RCU CPU
 			stall warning.
 
+	rcupdate.rcu_cpu_stall_notifiers= [KNL]
+			Provide RCU CPU stall notifiers, but see the
+			warnings in the RCU_CPU_STALL_NOTIFIER Kconfig
+			option's help text.  TL;DR:  You almost certainly
+			do not want rcupdate.rcu_cpu_stall_notifiers.
+
 	rcupdate.rcu_cpu_stall_suppress= [KNL]
 			Suppress RCU CPU stall warning messages.
 
diff --git a/include/linux/rcu_notifier.h b/include/linux/rcu_notifier.h
index ebf371364581..5640f024773b 100644
--- a/include/linux/rcu_notifier.h
+++ b/include/linux/rcu_notifier.h
@@ -13,7 +13,7 @@
 #define RCU_STALL_NOTIFY_NORM	1
 #define RCU_STALL_NOTIFY_EXP	2
 
-#ifdef CONFIG_RCU_STALL_COMMON
+#if defined(CONFIG_RCU_STALL_COMMON) && defined(CONFIG_RCU_CPU_STALL_NOTIFIER)
 
 #include <linux/notifier.h>
 #include <linux/types.h>
@@ -21,12 +21,12 @@
 int rcu_stall_chain_notifier_register(struct notifier_block *n);
 int rcu_stall_chain_notifier_unregister(struct notifier_block *n);
 
-#else // #ifdef CONFIG_RCU_STALL_COMMON
+#else // #if defined(CONFIG_RCU_STALL_COMMON) && defined(CONFIG_RCU_CPU_STALL_NOTIFIER)
 
 // No RCU CPU stall warnings in Tiny RCU.
 static inline int rcu_stall_chain_notifier_register(struct notifier_block *n) { return -EEXIST; }
 static inline int rcu_stall_chain_notifier_unregister(struct notifier_block *n) { return -ENOENT; }
 
-#endif // #else // #ifdef CONFIG_RCU_STALL_COMMON
+#endif // #else // #if defined(CONFIG_RCU_STALL_COMMON) && defined(CONFIG_RCU_CPU_STALL_NOTIFIER)
 
 #endif /* __LINUX_RCU_NOTIFIER_H */
diff --git a/kernel/rcu/Kconfig.debug b/kernel/rcu/Kconfig.debug
index 2984de629f74..9b0b52e1836f 100644
--- a/kernel/rcu/Kconfig.debug
+++ b/kernel/rcu/Kconfig.debug
@@ -105,6 +105,31 @@ config RCU_CPU_STALL_CPUTIME
 	  The boot option rcupdate.rcu_cpu_stall_cputime has the same function
 	  as this one, but will override this if it exists.
 
+config RCU_CPU_STALL_NOTIFIER
+	bool "Provide RCU CPU-stall notifiers"
+	depends on RCU_STALL_COMMON
+	depends on DEBUG_KERNEL
+	depends on RCU_EXPERT
+	default n
+	help
+	  WARNING:  You almost certainly do not want this!!!
+
+	  Enable RCU CPU-stall notifiers, which are invoked just before
+	  printing the RCU CPU stall warning.  As such, bugs in notifier
+	  callbacks can prevent stall warnings from being printed.
+	  And the whole reason that a stall warning is being printed is
+	  that something is hung up somewhere.	Therefore, the notifier
+	  callbacks must be written extremely carefully, preferably
+	  containing only lockless code.  After all, it is quite possible
+	  that the whole reason that the RCU CPU stall is happening in
+	  the first place is that someone forgot to release whatever lock
+	  that you are thinking of acquiring.  In which case, having your
+	  notifier callback acquire that lock will hang, preventing the
+	  RCU CPU stall warning from appearing.
+
+	  Say Y here if you want RCU CPU stall notifiers (you don't want them)
+	  Say N if you are unsure.
+
 config RCU_TRACE
 	bool "Enable tracing for RCU"
 	depends on DEBUG_KERNEL
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index b531c33e9545..f94f65877f2b 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -262,6 +262,8 @@ static inline bool rcu_stall_is_suppressed_at_boot(void)
 	return rcu_cpu_stall_suppress_at_boot && !rcu_inkernel_boot_has_ended();
 }
 
+extern int rcu_cpu_stall_notifiers;
+
 #ifdef CONFIG_RCU_STALL_COMMON
 
 extern int rcu_cpu_stall_ftrace_dump;
@@ -659,10 +661,10 @@ static inline bool rcu_cpu_beenfullyonline(int cpu) { return true; }
 bool rcu_cpu_beenfullyonline(int cpu);
 #endif
 
-#ifdef CONFIG_RCU_STALL_COMMON
+#if defined(CONFIG_RCU_STALL_COMMON) && defined(CONFIG_RCU_CPU_STALL_NOTIFIER)
 int rcu_stall_notifier_call_chain(unsigned long val, void *v);
-#else // #ifdef CONFIG_RCU_STALL_COMMON
+#else // #if defined(CONFIG_RCU_STALL_COMMON) && defined(CONFIG_RCU_CPU_STALL_NOTIFIER)
 static inline int rcu_stall_notifier_call_chain(unsigned long val, void *v) { return NOTIFY_DONE; }
-#endif // #else // #ifdef CONFIG_RCU_STALL_COMMON
+#endif // #else // #if defined(CONFIG_RCU_STALL_COMMON) && defined(CONFIG_RCU_CPU_STALL_NOTIFIER)
 
 #endif /* __LINUX_RCU_H */
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 30fc9d34e329..07a6a183c555 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -2450,10 +2450,12 @@ static int rcu_torture_stall(void *args)
 	unsigned long stop_at;
 
 	VERBOSE_TOROUT_STRING("rcu_torture_stall task started");
-	ret = rcu_stall_chain_notifier_register(&rcu_torture_stall_block);
-	if (ret)
-		pr_info("%s: rcu_stall_chain_notifier_register() returned %d, %sexpected.\n",
-			__func__, ret, !IS_ENABLED(CONFIG_RCU_STALL_COMMON) ? "un" : "");
+	if (rcu_cpu_stall_notifiers) {
+		ret = rcu_stall_chain_notifier_register(&rcu_torture_stall_block);
+		if (ret)
+			pr_info("%s: rcu_stall_chain_notifier_register() returned %d, %sexpected.\n",
+				__func__, ret, !IS_ENABLED(CONFIG_RCU_STALL_COMMON) ? "un" : "");
+	}
 	if (stall_cpu_holdoff > 0) {
 		VERBOSE_TOROUT_STRING("rcu_torture_stall begin holdoff");
 		schedule_timeout_interruptible(stall_cpu_holdoff * HZ);
@@ -2497,7 +2499,7 @@ static int rcu_torture_stall(void *args)
 		cur_ops->readunlock(idx);
 	}
 	pr_alert("%s end.\n", __func__);
-	if (!ret) {
+	if (rcu_cpu_stall_notifiers && !ret) {
 		ret = rcu_stall_chain_notifier_unregister(&rcu_torture_stall_block);
 		if (ret)
 			pr_info("%s: rcu_stall_chain_notifier_unregister() returned %d.\n", __func__, ret);
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index ac8e86babe44..5d666428546b 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -1061,6 +1061,7 @@ static int __init rcu_sysrq_init(void)
 }
 early_initcall(rcu_sysrq_init);
 
+#ifdef CONFIG_RCU_CPU_STALL_NOTIFIER
 
 //////////////////////////////////////////////////////////////////////////////
 //
@@ -1081,7 +1082,13 @@ static ATOMIC_NOTIFIER_HEAD(rcu_cpu_stall_notifier_list);
  */
 int rcu_stall_chain_notifier_register(struct notifier_block *n)
 {
-	return atomic_notifier_chain_register(&rcu_cpu_stall_notifier_list, n);
+	int rcsn = rcu_cpu_stall_notifiers;
+
+	WARN(1, "Adding %pS() to RCU stall notifier list (%s).\n", n->notifier_call,
+	     rcsn ? "possibly suppressing RCU CPU stall warnings" : "failed, so all is well");
+	if (rcsn)
+		return atomic_notifier_chain_register(&rcu_cpu_stall_notifier_list, n);
+	return -EEXIST;
 }
 EXPORT_SYMBOL_GPL(rcu_stall_chain_notifier_register);
 
@@ -1115,3 +1122,5 @@ int rcu_stall_notifier_call_chain(unsigned long val, void *v)
 {
 	return atomic_notifier_call_chain(&rcu_cpu_stall_notifier_list, val, v);
 }
+
+#endif // #ifdef CONFIG_RCU_CPU_STALL_NOTIFIER
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index c534d6806d3d..46aaaa9fe339 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -538,9 +538,15 @@ long torture_sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 EXPORT_SYMBOL_GPL(torture_sched_setaffinity);
 #endif
 
+int rcu_cpu_stall_notifiers __read_mostly; // !0 = provide stall notifiers (rarely useful)
+EXPORT_SYMBOL_GPL(rcu_cpu_stall_notifiers);
+
 #ifdef CONFIG_RCU_STALL_COMMON
 int rcu_cpu_stall_ftrace_dump __read_mostly;
 module_param(rcu_cpu_stall_ftrace_dump, int, 0644);
+#ifdef CONFIG_RCU_CPU_STALL_NOTIFIER
+module_param(rcu_cpu_stall_notifiers, int, 0444);
+#endif // #ifdef CONFIG_RCU_CPU_STALL_NOTIFIER
 int rcu_cpu_stall_suppress __read_mostly; // !0 = suppress stall warnings.
 EXPORT_SYMBOL_GPL(rcu_cpu_stall_suppress);
 module_param(rcu_cpu_stall_suppress, int, 0644);
-- 
cgit v1.2.3


From 23d90b2404050c00c15058710d56bb46e1c5ab36 Mon Sep 17 00:00:00 2001
From: Pedro Falcato <pedro.falcato@gmail.com>
Date: Fri, 20 Oct 2023 18:30:15 +0100
Subject: rcu: Remove unused macros from rcupdate.h

ulong2long, USHORT_CMP_GE and USHORT_CMP_LT are redundant and have been
unused for quite a few releases.

Signed-off-by: Pedro Falcato <pedro.falcato@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Neeraj Upadhyay (AMD) <neeraj.iitr10@gmail.com>
---
 include/linux/rcupdate.h | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index f7206b2623c9..aa87c82236dd 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -34,9 +34,6 @@
 
 #define ULONG_CMP_GE(a, b)	(ULONG_MAX / 2 >= (a) - (b))
 #define ULONG_CMP_LT(a, b)	(ULONG_MAX / 2 < (a) - (b))
-#define ulong2long(a)		(*(long *)(&(a)))
-#define USHORT_CMP_GE(a, b)	(USHRT_MAX / 2 >= (unsigned short)((a) - (b)))
-#define USHORT_CMP_LT(a, b)	(USHRT_MAX / 2 < (unsigned short)((a) - (b)))
 
 /* Exported common interfaces */
 void call_rcu(struct rcu_head *head, rcu_callback_t func);
-- 
cgit v1.2.3


From 87f3afd366f7c668be0269efda8a89741a3ea6b3 Mon Sep 17 00:00:00 2001
From: Chao Yu <chao@kernel.org>
Date: Sun, 10 Dec 2023 17:20:40 +0800
Subject: f2fs: add tracepoint for f2fs_vm_page_mkwrite()

This patch adds to support tracepoint for f2fs_vm_page_mkwrite(),
meanwhile it prints more details for trace_f2fs_filemap_fault().

Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/file.c              | 25 +++++++++++++++----------
 include/trace/events/f2fs.h | 39 ++++++++++++++++++++++++++-------------
 2 files changed, 41 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 3c7e6bfc1265..60290940018d 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -46,7 +46,7 @@ static vm_fault_t f2fs_filemap_fault(struct vm_fault *vmf)
 		f2fs_update_iostat(F2FS_I_SB(inode), inode,
 					APP_MAPPED_READ_IO, F2FS_BLKSIZE);
 
-	trace_f2fs_filemap_fault(inode, vmf->pgoff, (unsigned long)ret);
+	trace_f2fs_filemap_fault(inode, vmf->pgoff, vmf->vma->vm_flags, ret);
 
 	return ret;
 }
@@ -59,26 +59,29 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 	struct dnode_of_data dn;
 	bool need_alloc = true;
 	int err = 0;
+	vm_fault_t ret;
 
 	if (unlikely(IS_IMMUTABLE(inode)))
 		return VM_FAULT_SIGBUS;
 
-	if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED))
-		return VM_FAULT_SIGBUS;
+	if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) {
+		err = -EIO;
+		goto out;
+	}
 
 	if (unlikely(f2fs_cp_error(sbi))) {
 		err = -EIO;
-		goto err;
+		goto out;
 	}
 
 	if (!f2fs_is_checkpoint_ready(sbi)) {
 		err = -ENOSPC;
-		goto err;
+		goto out;
 	}
 
 	err = f2fs_convert_inline_inode(inode);
 	if (err)
-		goto err;
+		goto out;
 
 #ifdef CONFIG_F2FS_FS_COMPRESSION
 	if (f2fs_compressed_file(inode)) {
@@ -86,7 +89,7 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 
 		if (ret < 0) {
 			err = ret;
-			goto err;
+			goto out;
 		} else if (ret) {
 			need_alloc = false;
 		}
@@ -153,13 +156,15 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 	f2fs_update_iostat(sbi, inode, APP_MAPPED_IO, F2FS_BLKSIZE);
 	f2fs_update_time(sbi, REQ_TIME);
 
-	trace_f2fs_vm_page_mkwrite(page, DATA);
 out_sem:
 	filemap_invalidate_unlock_shared(inode->i_mapping);
 
 	sb_end_pagefault(inode->i_sb);
-err:
-	return vmf_fs_error(err);
+out:
+	ret = vmf_fs_error(err);
+
+	trace_f2fs_vm_page_mkwrite(inode, page->index, vmf->vma->vm_flags, ret);
+	return ret;
 }
 
 static const struct vm_operations_struct f2fs_file_vm_ops = {
diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
index 479d26eae22f..7ed0fc430dc6 100644
--- a/include/trace/events/f2fs.h
+++ b/include/trace/events/f2fs.h
@@ -1369,13 +1369,6 @@ DEFINE_EVENT(f2fs__page, f2fs_set_page_dirty,
 	TP_ARGS(page, type)
 );
 
-DEFINE_EVENT(f2fs__page, f2fs_vm_page_mkwrite,
-
-	TP_PROTO(struct page *page, int type),
-
-	TP_ARGS(page, type)
-);
-
 TRACE_EVENT(f2fs_replace_atomic_write_block,
 
 	TP_PROTO(struct inode *inode, struct inode *cow_inode, pgoff_t index,
@@ -1413,30 +1406,50 @@ TRACE_EVENT(f2fs_replace_atomic_write_block,
 		__entry->recovery)
 );
 
-TRACE_EVENT(f2fs_filemap_fault,
+DECLARE_EVENT_CLASS(f2fs_mmap,
 
-	TP_PROTO(struct inode *inode, pgoff_t index, unsigned long ret),
+	TP_PROTO(struct inode *inode, pgoff_t index,
+			vm_flags_t flags, vm_fault_t ret),
 
-	TP_ARGS(inode, index, ret),
+	TP_ARGS(inode, index, flags, ret),
 
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
 		__field(ino_t,	ino)
 		__field(pgoff_t, index)
-		__field(unsigned long, ret)
+		__field(vm_flags_t, flags)
+		__field(vm_fault_t, ret)
 	),
 
 	TP_fast_assign(
 		__entry->dev	= inode->i_sb->s_dev;
 		__entry->ino	= inode->i_ino;
 		__entry->index	= index;
+		__entry->flags	= flags;
 		__entry->ret	= ret;
 	),
 
-	TP_printk("dev = (%d,%d), ino = %lu, index = %lu, ret = %lx",
+	TP_printk("dev = (%d,%d), ino = %lu, index = %lu, flags: %s, ret: %s",
 		show_dev_ino(__entry),
 		(unsigned long)__entry->index,
-		__entry->ret)
+		__print_flags(__entry->flags, "|", FAULT_FLAG_TRACE),
+		__print_flags(__entry->ret, "|", VM_FAULT_RESULT_TRACE))
+);
+
+DEFINE_EVENT(f2fs_mmap, f2fs_filemap_fault,
+
+	TP_PROTO(struct inode *inode, pgoff_t index,
+			vm_flags_t flags, vm_fault_t ret),
+
+	TP_ARGS(inode, index, flags, ret)
+);
+
+DEFINE_EVENT(f2fs_mmap, f2fs_vm_page_mkwrite,
+
+	TP_PROTO(struct inode *inode, pgoff_t index,
+			vm_flags_t flags, vm_fault_t ret),
+
+	TP_ARGS(inode, index, flags, ret)
 );
 
 TRACE_EVENT(f2fs_writepages,
-- 
cgit v1.2.3


From c5e2a973448d958feb7881e4d875eac59fdeff3d Mon Sep 17 00:00:00 2001
From: Jamal Hadi Salim <jhs@mojatatu.com>
Date: Fri, 8 Dec 2023 16:28:41 -0300
Subject: rtnl: add helper to check if rtnl group has listeners

As of today, rtnl code creates a new skb and unconditionally fills and
broadcasts it to the relevant group. For most operations this is okay
and doesn't waste resources in general.

When operations are done without the rtnl_lock, as in tc-flower, such
skb allocation, message fill and no-op broadcasting can happen in all
cores of the system, which contributes to system pressure and wastes
precious cpu cycles when no one will receive the built message.

Introduce this helper so rtnetlink operations can simply check if someone
is listening and then proceed if necessary.

Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Victor Nogueira <victor@mojatatu.com>
Signed-off-by: Pedro Tammela <pctammela@mojatatu.com>
Link: https://lore.kernel.org/r/20231208192847.714940-2-pctammela@mojatatu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/rtnetlink.h | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index 3d6cf306cd55..a7d757e96c55 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -130,4 +130,11 @@ extern int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 
 extern void rtnl_offload_xstats_notify(struct net_device *dev);
 
+static inline int rtnl_has_listeners(const struct net *net, u32 group)
+{
+	struct sock *rtnl = net->rtnl;
+
+	return netlink_has_listeners(rtnl, group);
+}
+
 #endif	/* __LINUX_RTNETLINK_H */
-- 
cgit v1.2.3


From 8439109b76a3c405808383bf9dd532fc4b9c2dbd Mon Sep 17 00:00:00 2001
From: Victor Nogueira <victor@mojatatu.com>
Date: Fri, 8 Dec 2023 16:28:42 -0300
Subject: rtnl: add helper to check if a notification is needed

Building on the rtnl_has_listeners helper, add the rtnl_notify_needed
helper to check if we can bail out early in the notification routines.

Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Victor Nogueira <victor@mojatatu.com>
Signed-off-by: Pedro Tammela <pctammela@mojatatu.com>
Link: https://lore.kernel.org/r/20231208192847.714940-3-pctammela@mojatatu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/rtnetlink.h | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

(limited to 'include')

diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index a7d757e96c55..0cbbbded0331 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -137,4 +137,19 @@ static inline int rtnl_has_listeners(const struct net *net, u32 group)
 	return netlink_has_listeners(rtnl, group);
 }
 
+/**
+ * rtnl_notify_needed - check if notification is needed
+ * @net: Pointer to the net namespace
+ * @nlflags: netlink ingress message flags
+ * @group: rtnl group
+ *
+ * Based on the ingress message flags and rtnl group, returns true
+ * if a notification is needed, false otherwise.
+ */
+static inline bool
+rtnl_notify_needed(const struct net *net, u16 nlflags, u32 group)
+{
+	return (nlflags & NLM_F_ECHO) || rtnl_has_listeners(net, group);
+}
+
 #endif	/* __LINUX_RTNETLINK_H */
-- 
cgit v1.2.3


From ddb6b284bdc32b6e218b3d90b5a745ea26620812 Mon Sep 17 00:00:00 2001
From: Pedro Tammela <pctammela@mojatatu.com>
Date: Fri, 8 Dec 2023 16:28:43 -0300
Subject: rtnl: add helper to send if skb is not null

This is a convenience helper for routines handling conditional rtnl
events, that is code that might send a notification depending on
rtnl_has_listeners/rtnl_notify_needed.

Instead of:
   if (skb)
      rtnetlink_send(...)

Use:
      rtnetlink_maybe_send(...)

Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Pedro Tammela <pctammela@mojatatu.com>
Link: https://lore.kernel.org/r/20231208192847.714940-4-pctammela@mojatatu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/rtnetlink.h | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index 0cbbbded0331..6a8543b34e2c 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -10,6 +10,13 @@
 #include <uapi/linux/rtnetlink.h>
 
 extern int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, u32 group, int echo);
+
+static inline int rtnetlink_maybe_send(struct sk_buff *skb, struct net *net,
+				       u32 pid, u32 group, int echo)
+{
+	return !skb ? 0 : rtnetlink_send(skb, net, pid, group, echo);
+}
+
 extern int rtnl_unicast(struct sk_buff *skb, struct net *net, u32 pid);
 extern void rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid,
 			u32 group, const struct nlmsghdr *nlh, gfp_t flags);
-- 
cgit v1.2.3


From 1a1ad782dcbbacd9e8d4e2e7ff1bf14d1db80727 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Mon, 4 Dec 2023 15:39:21 -0800
Subject: bpf: tidy up exception callback management a bit

Use the fact that we are passing subprog index around and have
a corresponding struct bpf_subprog_info in bpf_verifier_env for each
subprogram. We don't need to separately pass around a flag whether
subprog is exception callback or not, each relevant verifier function
can determine this using provided subprog index if we maintain
bpf_subprog_info properly.

Also move out exception callback-specific logic from
btf_prepare_func_args(), keeping it generic. We can enforce all these
restriction right before exception callback verification pass. We add
out parameter, arg_cnt, for now, but this will be unnecessary with
subsequent refactoring and will be removed.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20231204233931.49758-4-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h   |  2 +-
 kernel/bpf/btf.c      | 11 ++---------
 kernel/bpf/verifier.c | 52 ++++++++++++++++++++++++++++++++++++++-------------
 3 files changed, 42 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index c1a06263a4f3..0bd4889e917a 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2494,7 +2494,7 @@ int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog,
 int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog,
 			   struct bpf_reg_state *regs);
 int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
-			  struct bpf_reg_state *reg, bool is_ex_cb);
+			  struct bpf_reg_state *reg, u32 *nargs);
 int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog,
 			 struct btf *btf, const struct btf_type *t);
 const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type *pt,
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 63cf4128fc05..d56433bf8aba 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -6956,7 +6956,7 @@ int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog,
  * (either PTR_TO_CTX or SCALAR_VALUE).
  */
 int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
-			  struct bpf_reg_state *regs, bool is_ex_cb)
+			  struct bpf_reg_state *regs, u32 *arg_cnt)
 {
 	struct bpf_verifier_log *log = &env->log;
 	struct bpf_prog *prog = env->prog;
@@ -7013,6 +7013,7 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
 			tname, nargs, MAX_BPF_FUNC_REG_ARGS);
 		return -EINVAL;
 	}
+	*arg_cnt = nargs;
 	/* check that function returns int, exception cb also requires this */
 	t = btf_type_by_id(btf, t->type);
 	while (btf_type_is_modifier(t))
@@ -7062,14 +7063,6 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
 			i, btf_type_str(t), tname);
 		return -EINVAL;
 	}
-	/* We have already ensured that the callback returns an integer, just
-	 * like all global subprogs. We need to determine it only has a single
-	 * scalar argument.
-	 */
-	if (is_ex_cb && (nargs != 1 || regs[BPF_REG_1].type != SCALAR_VALUE)) {
-		bpf_log(log, "exception cb only supports single integer argument\n");
-		return -EINVAL;
-	}
 	return 0;
 }
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 727a59e4a647..d1755db1b503 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -442,6 +442,25 @@ static struct bpf_func_info_aux *subprog_aux(const struct bpf_verifier_env *env,
 	return &env->prog->aux->func_info_aux[subprog];
 }
 
+static struct bpf_subprog_info *subprog_info(struct bpf_verifier_env *env, int subprog)
+{
+	return &env->subprog_info[subprog];
+}
+
+static void mark_subprog_exc_cb(struct bpf_verifier_env *env, int subprog)
+{
+	struct bpf_subprog_info *info = subprog_info(env, subprog);
+
+	info->is_cb = true;
+	info->is_async_cb = true;
+	info->is_exception_cb = true;
+}
+
+static bool subprog_is_exc_cb(struct bpf_verifier_env *env, int subprog)
+{
+	return subprog_info(env, subprog)->is_exception_cb;
+}
+
 static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg)
 {
 	return btf_record_has_field(reg_btf_record(reg), BPF_SPIN_LOCK);
@@ -2892,6 +2911,7 @@ static int add_subprog_and_kfunc(struct bpf_verifier_env *env)
 			if (env->subprog_info[i].start != ex_cb_insn)
 				continue;
 			env->exception_callback_subprog = i;
+			mark_subprog_exc_cb(env, i);
 			break;
 		}
 	}
@@ -19166,9 +19186,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
 
 		env->exception_callback_subprog = env->subprog_cnt - 1;
 		/* Don't update insn_cnt, as add_hidden_subprog always appends insns */
-		env->subprog_info[env->exception_callback_subprog].is_cb = true;
-		env->subprog_info[env->exception_callback_subprog].is_async_cb = true;
-		env->subprog_info[env->exception_callback_subprog].is_exception_cb = true;
+		mark_subprog_exc_cb(env, env->exception_callback_subprog);
 	}
 
 	for (i = 0; i < insn_cnt; i++, insn++) {
@@ -19868,7 +19886,7 @@ static void free_states(struct bpf_verifier_env *env)
 	}
 }
 
-static int do_check_common(struct bpf_verifier_env *env, int subprog, bool is_ex_cb)
+static int do_check_common(struct bpf_verifier_env *env, int subprog)
 {
 	bool pop_log = !(env->log.level & BPF_LOG_LEVEL2);
 	struct bpf_verifier_state *state;
@@ -19899,9 +19917,23 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog, bool is_ex
 
 	regs = state->frame[state->curframe]->regs;
 	if (subprog || env->prog->type == BPF_PROG_TYPE_EXT) {
-		ret = btf_prepare_func_args(env, subprog, regs, is_ex_cb);
+		u32 nargs;
+
+		ret = btf_prepare_func_args(env, subprog, regs, &nargs);
 		if (ret)
 			goto out;
+		if (subprog_is_exc_cb(env, subprog)) {
+			state->frame[0]->in_exception_callback_fn = true;
+			/* We have already ensured that the callback returns an integer, just
+			 * like all global subprogs. We need to determine it only has a single
+			 * scalar argument.
+			 */
+			if (nargs != 1 || regs[BPF_REG_1].type != SCALAR_VALUE) {
+				verbose(env, "exception cb only supports single integer argument\n");
+				ret = -EINVAL;
+				goto out;
+			}
+		}
 		for (i = BPF_REG_1; i <= BPF_REG_5; i++) {
 			if (regs[i].type == PTR_TO_CTX)
 				mark_reg_known_zero(env, regs, i);
@@ -19915,12 +19947,6 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog, bool is_ex
 				regs[i].id = ++env->id_gen;
 			}
 		}
-		if (is_ex_cb) {
-			state->frame[0]->in_exception_callback_fn = true;
-			env->subprog_info[subprog].is_cb = true;
-			env->subprog_info[subprog].is_async_cb = true;
-			env->subprog_info[subprog].is_exception_cb = true;
-		}
 	} else {
 		/* 1st arg to a function */
 		regs[BPF_REG_1].type = PTR_TO_CTX;
@@ -20000,7 +20026,7 @@ again:
 
 		env->insn_idx = env->subprog_info[i].start;
 		WARN_ON_ONCE(env->insn_idx == 0);
-		ret = do_check_common(env, i, env->exception_callback_subprog == i);
+		ret = do_check_common(env, i);
 		if (ret) {
 			return ret;
 		} else if (env->log.level & BPF_LOG_LEVEL) {
@@ -20030,7 +20056,7 @@ static int do_check_main(struct bpf_verifier_env *env)
 	int ret;
 
 	env->insn_idx = 0;
-	ret = do_check_common(env, 0, false);
+	ret = do_check_common(env, 0);
 	if (!ret)
 		env->prog->aux->stack_depth = env->subprog_info[0].stack_depth;
 	return ret;
-- 
cgit v1.2.3


From 406a6fa44bfbc8563f0612b08d43df2fa65e8bc5 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Mon, 4 Dec 2023 15:39:22 -0800
Subject: bpf: use bitfields for simple per-subprog bool flags

We have a bunch of bool flags for each subprog. Instead of wasting bytes
for them, use bitfields instead.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20231204233931.49758-5-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf_verifier.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 314b679fb494..c2819a6579a5 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -611,12 +611,12 @@ struct bpf_subprog_info {
 	u32 start; /* insn idx of function entry point */
 	u32 linfo_idx; /* The idx to the main_prog->aux->linfo */
 	u16 stack_depth; /* max. stack depth used by this function */
-	bool has_tail_call;
-	bool tail_call_reachable;
-	bool has_ld_abs;
-	bool is_cb;
-	bool is_async_cb;
-	bool is_exception_cb;
+	bool has_tail_call: 1;
+	bool tail_call_reachable: 1;
+	bool has_ld_abs: 1;
+	bool is_cb: 1;
+	bool is_async_cb: 1;
+	bool is_exception_cb: 1;
 };
 
 struct bpf_verifier_env;
-- 
cgit v1.2.3


From 1ca51628e7303718fdabe29c7d36f582500d5cf2 Mon Sep 17 00:00:00 2001
From: Shun Hao <shunh@nvidia.com>
Date: Wed, 6 Dec 2023 16:01:34 +0200
Subject: net/mlx5: Introduce indirect-sw-encap ICM properties

Add new fields for device memory capabilities, in order to support
creation of new ICM memory type of SW encap.

Signed-off-by: Shun Hao <shunh@nvidia.com>
Link: https://lore.kernel.org/r/107cca7dd6a932a1704abf6ebd1b801105546a8e.1701871118.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 include/linux/mlx5/mlx5_ifc.h | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 6f3631425f38..02b25dc36143 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1193,7 +1193,8 @@ struct mlx5_ifc_device_mem_cap_bits {
 	u8         log_sw_icm_alloc_granularity[0x6];
 	u8         log_steering_sw_icm_size[0x8];
 
-	u8         reserved_at_120[0x18];
+	u8         log_indirect_encap_sw_icm_size[0x8];
+	u8         reserved_at_128[0x10];
 	u8         log_header_modify_pattern_sw_icm_size[0x8];
 
 	u8         header_modify_sw_icm_start_address[0x40];
@@ -1204,7 +1205,11 @@ struct mlx5_ifc_device_mem_cap_bits {
 
 	u8         memic_operations[0x20];
 
-	u8         reserved_at_220[0x5e0];
+	u8         reserved_at_220[0x20];
+
+	u8         indirect_encap_sw_icm_start_address[0x40];
+
+	u8         reserved_at_280[0x580];
 };
 
 struct mlx5_ifc_device_event_cap_bits {
-- 
cgit v1.2.3


From a429ec96c07f3020af12029acefc46f42ff5c91c Mon Sep 17 00:00:00 2001
From: Shun Hao <shunh@nvidia.com>
Date: Wed, 6 Dec 2023 16:01:35 +0200
Subject: RDMA/mlx5: Support handling of SW encap ICM area

New type for this ICM area, now the user can allocate/deallocate
the new type of SW encap ICM memory, to store the encap header data
which are managed by SW.

Signed-off-by: Shun Hao <shunh@nvidia.com>
Link: https://lore.kernel.org/r/546fe43fc700240709e30acf7713ec6834d652bd.1701871118.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/mlx5/dm.c           | 5 +++++
 drivers/infiniband/hw/mlx5/mr.c           | 1 +
 include/linux/mlx5/driver.h               | 1 +
 include/uapi/rdma/mlx5_user_ioctl_verbs.h | 1 +
 4 files changed, 8 insertions(+)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx5/dm.c b/drivers/infiniband/hw/mlx5/dm.c
index 3669c90b2dad..b4c97fb62abf 100644
--- a/drivers/infiniband/hw/mlx5/dm.c
+++ b/drivers/infiniband/hw/mlx5/dm.c
@@ -341,6 +341,8 @@ static enum mlx5_sw_icm_type get_icm_type(int uapi_type)
 		return MLX5_SW_ICM_TYPE_HEADER_MODIFY;
 	case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_PATTERN_SW_ICM:
 		return MLX5_SW_ICM_TYPE_HEADER_MODIFY_PATTERN;
+	case MLX5_IB_UAPI_DM_TYPE_ENCAP_SW_ICM:
+		return MLX5_SW_ICM_TYPE_SW_ENCAP;
 	case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM:
 	default:
 		return MLX5_SW_ICM_TYPE_STEERING;
@@ -364,6 +366,7 @@ static struct ib_dm *handle_alloc_dm_sw_icm(struct ib_ucontext *ctx,
 	switch (type) {
 	case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM:
 	case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM:
+	case MLX5_IB_UAPI_DM_TYPE_ENCAP_SW_ICM:
 		if (!(MLX5_CAP_FLOWTABLE_NIC_RX(dev, sw_owner) ||
 		      MLX5_CAP_FLOWTABLE_NIC_TX(dev, sw_owner) ||
 		      MLX5_CAP_FLOWTABLE_NIC_RX(dev, sw_owner_v2) ||
@@ -438,6 +441,7 @@ struct ib_dm *mlx5_ib_alloc_dm(struct ib_device *ibdev,
 	case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM:
 	case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM:
 	case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_PATTERN_SW_ICM:
+	case MLX5_IB_UAPI_DM_TYPE_ENCAP_SW_ICM:
 		return handle_alloc_dm_sw_icm(context, attr, attrs, type);
 	default:
 		return ERR_PTR(-EOPNOTSUPP);
@@ -491,6 +495,7 @@ static int mlx5_ib_dealloc_dm(struct ib_dm *ibdm,
 	case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM:
 	case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM:
 	case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_PATTERN_SW_ICM:
+	case MLX5_IB_UAPI_DM_TYPE_ENCAP_SW_ICM:
 		return mlx5_dm_icm_dealloc(ctx, to_icm(ibdm));
 	default:
 		return -EOPNOTSUPP;
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 18e459b55746..a8ee2ca1f4a1 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -1347,6 +1347,7 @@ struct ib_mr *mlx5_ib_reg_dm_mr(struct ib_pd *pd, struct ib_dm *dm,
 	case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM:
 	case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM:
 	case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_PATTERN_SW_ICM:
+	case MLX5_IB_UAPI_DM_TYPE_ENCAP_SW_ICM:
 		if (attr->access_flags & ~MLX5_IB_DM_SW_ICM_ALLOWED_ACCESS)
 			return ERR_PTR(-EINVAL);
 
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index d2b8d4a74a30..96cb8845682d 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -688,6 +688,7 @@ enum mlx5_sw_icm_type {
 	MLX5_SW_ICM_TYPE_STEERING,
 	MLX5_SW_ICM_TYPE_HEADER_MODIFY,
 	MLX5_SW_ICM_TYPE_HEADER_MODIFY_PATTERN,
+	MLX5_SW_ICM_TYPE_SW_ENCAP,
 };
 
 #define MLX5_MAX_RESERVED_GIDS 8
diff --git a/include/uapi/rdma/mlx5_user_ioctl_verbs.h b/include/uapi/rdma/mlx5_user_ioctl_verbs.h
index 7af9e09ea556..3189c7f08d17 100644
--- a/include/uapi/rdma/mlx5_user_ioctl_verbs.h
+++ b/include/uapi/rdma/mlx5_user_ioctl_verbs.h
@@ -64,6 +64,7 @@ enum mlx5_ib_uapi_dm_type {
 	MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM,
 	MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM,
 	MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_PATTERN_SW_ICM,
+	MLX5_IB_UAPI_DM_TYPE_ENCAP_SW_ICM,
 };
 
 enum mlx5_ib_uapi_devx_create_event_channel_flags {
-- 
cgit v1.2.3


From eb524d0fd46249b0b9e5d52372dc65d8b32430c3 Mon Sep 17 00:00:00 2001
From: Mark Bloch <mbloch@nvidia.com>
Date: Wed, 6 Dec 2023 16:01:37 +0200
Subject: net/mlx5: E-Switch, expose eswitch manager vport

Expose the ability the query the eswitch manager vport number.
Next patch will utilize this capability to reveal the correct
register C0 value to the users.

Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://lore.kernel.org/r/614fb0e216250e2ce3340471ec141b83ec45c7f4.1701871118.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 7 -------
 include/linux/mlx5/eswitch.h                      | 8 ++++++++
 2 files changed, 8 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 37ab66e7b403..60a9a6cba0b1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -616,13 +616,6 @@ static inline bool mlx5_esw_allowed(const struct mlx5_eswitch *esw)
 	return esw && MLX5_ESWITCH_MANAGER(esw->dev);
 }
 
-/* The returned number is valid only when the dev is eswitch manager. */
-static inline u16 mlx5_eswitch_manager_vport(struct mlx5_core_dev *dev)
-{
-	return mlx5_core_is_ecpf_esw_manager(dev) ?
-		MLX5_VPORT_ECPF : MLX5_VPORT_PF;
-}
-
 static inline bool
 mlx5_esw_is_manager_vport(const struct mlx5_eswitch *esw, u16 vport_num)
 {
diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h
index 950d2431a53c..df73a2ccc9af 100644
--- a/include/linux/mlx5/eswitch.h
+++ b/include/linux/mlx5/eswitch.h
@@ -7,6 +7,7 @@
 #define _MLX5_ESWITCH_
 
 #include <linux/mlx5/driver.h>
+#include <linux/mlx5/vport.h>
 #include <net/devlink.h>
 
 #define MLX5_ESWITCH_MANAGER(mdev) MLX5_CAP_GEN(mdev, eswitch_manager)
@@ -210,4 +211,11 @@ static inline bool is_mdev_switchdev_mode(struct mlx5_core_dev *dev)
 	return mlx5_eswitch_mode(dev) == MLX5_ESWITCH_OFFLOADS;
 }
 
+/* The returned number is valid only when the dev is eswitch manager. */
+static inline u16 mlx5_eswitch_manager_vport(struct mlx5_core_dev *dev)
+{
+	return mlx5_core_is_ecpf_esw_manager(dev) ?
+		MLX5_VPORT_ECPF : MLX5_VPORT_PF;
+}
+
 #endif
-- 
cgit v1.2.3


From d727d27db536faea7178290c677cc0567f647231 Mon Sep 17 00:00:00 2001
From: Mark Bloch <mbloch@nvidia.com>
Date: Wed, 6 Dec 2023 16:01:38 +0200
Subject: RDMA/mlx5: Expose register c0 for RDMA device

This patch introduces improvements for matching egress traffic sent by the
local device. When applicable, all egress traffic from the local vport is
now tagged with the provided value. This enhancement is particularly useful
for FDB steering purposes.

The primary focus of this update is facilitating the transmission of
traffic from the hypervisor to a VF. To achieve this, one must initiate an
SQ on the hypervisor and subsequently create a rule in the FDB that matches
on the eswitch manager vport and the SQN of the aforementioned SQ.

Obtaining the SQN can be had from SQ opened, and the eswitch manager vport
match can be substituted with the register c0 value exposed by this patch.

Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Reviewed-by: Michael Guralnik <michaelgur@nvidia.com>
Link: https://lore.kernel.org/r/aa4120a91c98ff1c44f1213388c744d4cb0324d6.1701871118.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/mlx5/main.c | 24 ++++++++++++++++++++++++
 include/uapi/rdma/mlx5-abi.h      |  2 ++
 2 files changed, 26 insertions(+)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 650a15b6cfbc..c2b557e64290 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -818,6 +818,17 @@ static int mlx5_query_node_desc(struct mlx5_ib_dev *dev, char *node_desc)
 				    MLX5_REG_NODE_DESC, 0, 0);
 }
 
+static void fill_esw_mgr_reg_c0(struct mlx5_core_dev *mdev,
+				struct mlx5_ib_query_device_resp *resp)
+{
+	struct mlx5_eswitch *esw = mdev->priv.eswitch;
+	u16 vport = mlx5_eswitch_manager_vport(mdev);
+
+	resp->reg_c0.value = mlx5_eswitch_get_vport_metadata_for_match(esw,
+								      vport);
+	resp->reg_c0.mask = mlx5_eswitch_get_vport_metadata_mask();
+}
+
 static int mlx5_ib_query_device(struct ib_device *ibdev,
 				struct ib_device_attr *props,
 				struct ib_udata *uhw)
@@ -1209,6 +1220,19 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 			MLX5_CAP_GEN(mdev, log_max_dci_errored_streams);
 	}
 
+	if (offsetofend(typeof(resp), reserved) <= uhw_outlen)
+		resp.response_length += sizeof(resp.reserved);
+
+	if (offsetofend(typeof(resp), reg_c0) <= uhw_outlen) {
+		struct mlx5_eswitch *esw = mdev->priv.eswitch;
+
+		resp.response_length += sizeof(resp.reg_c0);
+
+		if (mlx5_eswitch_mode(mdev) == MLX5_ESWITCH_OFFLOADS &&
+		    mlx5_eswitch_vport_match_metadata_enabled(esw))
+			fill_esw_mgr_reg_c0(mdev, &resp);
+	}
+
 	if (uhw_outlen) {
 		err = ib_copy_to_udata(uhw, &resp, resp.response_length);
 
diff --git a/include/uapi/rdma/mlx5-abi.h b/include/uapi/rdma/mlx5-abi.h
index a96b7d2770e1..d4f6a36dffb0 100644
--- a/include/uapi/rdma/mlx5-abi.h
+++ b/include/uapi/rdma/mlx5-abi.h
@@ -37,6 +37,7 @@
 #include <linux/types.h>
 #include <linux/if_ether.h>	/* For ETH_ALEN. */
 #include <rdma/ib_user_ioctl_verbs.h>
+#include <rdma/mlx5_user_ioctl_verbs.h>
 
 enum {
 	MLX5_QP_FLAG_SIGNATURE		= 1 << 0,
@@ -275,6 +276,7 @@ struct mlx5_ib_query_device_resp {
 	__u32	tunnel_offloads_caps; /* enum mlx5_ib_tunnel_offloads */
 	struct  mlx5_ib_dci_streams_caps dci_streams_caps;
 	__u16 reserved;
+	struct mlx5_ib_uapi_reg reg_c0;
 };
 
 enum mlx5_ib_create_cq_flags {
-- 
cgit v1.2.3


From 98fb9b9680c9f3895ced02d6a73e27f5d7b5892b Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 6 Dec 2023 22:37:57 +0100
Subject: wifi: ieee80211: don't require protected vendor action frames

For vendor action frames, whether a protected one should be
used or not is clearly up to the individual vendor and frame,
so even though a protected dual is defined, it may not get
used. Thus, don't require protection for vendor action frames
when they're used in a connection.

Since we obviously don't process frames unknown to the kernel
in the kernel, it may makes sense to invert this list to have
all the ones the kernel processes and knows to be requiring
protection, but that'd be a different change.

Fixes: 91535613b609 ("wifi: mac80211: don't drop all unprotected public action frames")
Reported-by: Jouni Malinen <j@w1.fi>
Link: https://msgid.link/20231206223801.f6a2cf4e67ec.Ifa6acc774bd67801d3dafb405278f297683187aa@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index c2ac9e9e7ee9..2b5e500bf093 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -4447,7 +4447,8 @@ ieee80211_is_protected_dual_of_public_action(struct sk_buff *skb)
 		action != WLAN_PUB_ACTION_LOC_TRACK_NOTI &&
 		action != WLAN_PUB_ACTION_FTM_REQUEST &&
 		action != WLAN_PUB_ACTION_FTM_RESPONSE &&
-		action != WLAN_PUB_ACTION_FILS_DISCOVERY;
+		action != WLAN_PUB_ACTION_FILS_DISCOVERY &&
+		action != WLAN_PUB_ACTION_VENDOR_SPECIFIC;
 }
 
 /**
-- 
cgit v1.2.3


From 8f23f5dba6b4693448144bde4dd6f537543442c2 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Fri, 27 Oct 2023 08:05:20 +0800
Subject: iommu: Change kconfig around IOMMU_SVA

Linus suggested that the kconfig here is confusing:

https://lore.kernel.org/all/CAHk-=wgUiAtiszwseM1p2fCJ+sC4XWQ+YN4TanFhUgvUqjr9Xw@mail.gmail.com/

Let's break it into three kconfigs controlling distinct things:

 - CONFIG_IOMMU_MM_DATA controls if the mm_struct has the additional
   fields for the IOMMU. Currently only PASID, but later patches store
   a struct iommu_mm_data *

 - CONFIG_ARCH_HAS_CPU_PASID controls if the arch needs the scheduling bit
   for keeping track of the ENQCMD instruction. x86 will select this if
   IOMMU_SVA is enabled

 - IOMMU_SVA controls if the IOMMU core compiles in the SVA support code
   for iommu driver use and the IOMMU exported API

This way ARM will not enable CONFIG_ARCH_HAS_CPU_PASID

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20231027000525.1278806-2-tina.zhang@intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 arch/Kconfig             | 5 +++++
 arch/x86/Kconfig         | 1 +
 arch/x86/kernel/traps.c  | 2 +-
 drivers/iommu/Kconfig    | 1 +
 include/linux/iommu.h    | 2 +-
 include/linux/mm_types.h | 2 +-
 include/linux/sched.h    | 2 +-
 kernel/fork.c            | 2 +-
 mm/Kconfig               | 3 +++
 mm/init-mm.c             | 2 +-
 10 files changed, 16 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/arch/Kconfig b/arch/Kconfig
index f4b210ab0612..3e49f862670e 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -301,6 +301,11 @@ config ARCH_HAS_DMA_CLEAR_UNCACHED
 config ARCH_HAS_CPU_FINALIZE_INIT
 	bool
 
+# The architecture has a per-task state that includes the mm's PASID
+config ARCH_HAS_CPU_PASID
+	bool
+	select IOMMU_MM_DATA
+
 # Select if arch init_task must go in the __init_task_data section
 config ARCH_TASK_STRUCT_ON_STACK
 	bool
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 3762f41bb092..68a2ec36a46e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -71,6 +71,7 @@ config X86
 	select ARCH_HAS_CACHE_LINE_SIZE
 	select ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION
 	select ARCH_HAS_CPU_FINALIZE_INIT
+	select ARCH_HAS_CPU_PASID		if IOMMU_SVA
 	select ARCH_HAS_CURRENT_STACK_POINTER
 	select ARCH_HAS_DEBUG_VIRTUAL
 	select ARCH_HAS_DEBUG_VM_PGTABLE	if !X86_PAE
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index c876f1d36a81..2b62dbb3396a 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -565,7 +565,7 @@ static bool fixup_iopl_exception(struct pt_regs *regs)
  */
 static bool try_fixup_enqcmd_gp(void)
 {
-#ifdef CONFIG_IOMMU_SVA
+#ifdef CONFIG_ARCH_HAS_CPU_PASID
 	u32 pasid;
 
 	/*
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index 7673bb82945b..9a29d742617e 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -160,6 +160,7 @@ config IOMMU_DMA
 
 # Shared Virtual Addressing
 config IOMMU_SVA
+	select IOMMU_MM_DATA
 	bool
 
 config FSL_PAMU
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index c7394b39599c..cd3f398095bf 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -1337,7 +1337,7 @@ static inline bool tegra_dev_iommu_get_stream_id(struct device *dev, u32 *stream
 	return false;
 }
 
-#ifdef CONFIG_IOMMU_SVA
+#ifdef CONFIG_IOMMU_MM_DATA
 static inline void mm_pasid_init(struct mm_struct *mm)
 {
 	mm->pasid = IOMMU_PASID_INVALID;
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 957ce38768b2..41f248608dd9 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -938,7 +938,7 @@ struct mm_struct {
 #endif
 		struct work_struct async_put_work;
 
-#ifdef CONFIG_IOMMU_SVA
+#ifdef CONFIG_IOMMU_MM_DATA
 		u32 pasid;
 #endif
 #ifdef CONFIG_KSM
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 292c31697248..70888a36677b 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -954,7 +954,7 @@ struct task_struct {
 	/* Recursion prevention for eventfd_signal() */
 	unsigned			in_eventfd:1;
 #endif
-#ifdef CONFIG_IOMMU_SVA
+#ifdef CONFIG_ARCH_HAS_CPU_PASID
 	unsigned			pasid_activated:1;
 #endif
 #ifdef	CONFIG_CPU_SUP_INTEL
diff --git a/kernel/fork.c b/kernel/fork.c
index 10917c3e1f03..43fd9bc1a522 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1179,7 +1179,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 	tsk->use_memdelay = 0;
 #endif
 
-#ifdef CONFIG_IOMMU_SVA
+#ifdef CONFIG_ARCH_HAS_CPU_PASID
 	tsk->pasid_activated = 0;
 #endif
 
diff --git a/mm/Kconfig b/mm/Kconfig
index 89971a894b60..0143f4d905c9 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -1270,6 +1270,9 @@ config LOCK_MM_AND_FIND_VMA
 	bool
 	depends on !STACK_GROWSUP
 
+config IOMMU_MM_DATA
+	bool
+
 source "mm/damon/Kconfig"
 
 endmenu
diff --git a/mm/init-mm.c b/mm/init-mm.c
index cfd367822cdd..c52dc2740a3d 100644
--- a/mm/init-mm.c
+++ b/mm/init-mm.c
@@ -44,7 +44,7 @@ struct mm_struct init_mm = {
 #endif
 	.user_ns	= &init_user_ns,
 	.cpu_bitmap	= CPU_BITS_NONE,
-#ifdef CONFIG_IOMMU_SVA
+#ifdef CONFIG_IOMMU_MM_DATA
 	.pasid		= IOMMU_PASID_INVALID,
 #endif
 	INIT_MM_CONTEXT(init_mm)
-- 
cgit v1.2.3


From 2396046d75d3c0b2cfead852a77efd023f8539dc Mon Sep 17 00:00:00 2001
From: Tina Zhang <tina.zhang@intel.com>
Date: Fri, 27 Oct 2023 08:05:22 +0800
Subject: iommu: Add mm_get_enqcmd_pasid() helper function

mm_get_enqcmd_pasid() should be used by architecture code and closely
related to learn the PASID value that the x86 ENQCMD operation should
use for the mm.

For the moment SMMUv3 uses this without any connection to ENQCMD, it
will be cleaned up similar to how the prior patch made VT-d use the
PASID argument of set_dev_pasid().

The motivation is to replace mm->pasid with an iommu private data
structure that is introduced in a later patch.

Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Tina Zhang <tina.zhang@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20231027000525.1278806-4-tina.zhang@intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 arch/x86/kernel/traps.c                         |  2 +-
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c | 23 +++++++++++++++--------
 drivers/iommu/iommu-sva.c                       |  2 +-
 include/linux/iommu.h                           | 12 ++++++++++++
 4 files changed, 29 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 2b62dbb3396a..5944d759afe7 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -591,7 +591,7 @@ static bool try_fixup_enqcmd_gp(void)
 	if (!mm_valid_pasid(current->mm))
 		return false;
 
-	pasid = current->mm->pasid;
+	pasid = mm_get_enqcmd_pasid(current->mm);
 
 	/*
 	 * Did this thread already have its PASID activated?
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
index 353248ab18e7..05722121f00e 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
@@ -246,7 +246,8 @@ static void arm_smmu_mm_arch_invalidate_secondary_tlbs(struct mmu_notifier *mn,
 						    smmu_domain);
 	}
 
-	arm_smmu_atc_inv_domain(smmu_domain, mm->pasid, start, size);
+	arm_smmu_atc_inv_domain(smmu_domain, mm_get_enqcmd_pasid(mm), start,
+				size);
 }
 
 static void arm_smmu_mm_release(struct mmu_notifier *mn, struct mm_struct *mm)
@@ -264,10 +265,11 @@ static void arm_smmu_mm_release(struct mmu_notifier *mn, struct mm_struct *mm)
 	 * DMA may still be running. Keep the cd valid to avoid C_BAD_CD events,
 	 * but disable translation.
 	 */
-	arm_smmu_update_ctx_desc_devices(smmu_domain, mm->pasid, &quiet_cd);
+	arm_smmu_update_ctx_desc_devices(smmu_domain, mm_get_enqcmd_pasid(mm),
+					 &quiet_cd);
 
 	arm_smmu_tlb_inv_asid(smmu_domain->smmu, smmu_mn->cd->asid);
-	arm_smmu_atc_inv_domain(smmu_domain, mm->pasid, 0, 0);
+	arm_smmu_atc_inv_domain(smmu_domain, mm_get_enqcmd_pasid(mm), 0, 0);
 
 	smmu_mn->cleared = true;
 	mutex_unlock(&sva_lock);
@@ -325,10 +327,13 @@ arm_smmu_mmu_notifier_get(struct arm_smmu_domain *smmu_domain,
 
 	spin_lock_irqsave(&smmu_domain->devices_lock, flags);
 	list_for_each_entry(master, &smmu_domain->devices, domain_head) {
-		ret = arm_smmu_write_ctx_desc(master, mm->pasid, cd);
+		ret = arm_smmu_write_ctx_desc(master, mm_get_enqcmd_pasid(mm),
+					      cd);
 		if (ret) {
-			list_for_each_entry_from_reverse(master, &smmu_domain->devices, domain_head)
-				arm_smmu_write_ctx_desc(master, mm->pasid, NULL);
+			list_for_each_entry_from_reverse(
+				master, &smmu_domain->devices, domain_head)
+				arm_smmu_write_ctx_desc(
+					master, mm_get_enqcmd_pasid(mm), NULL);
 			break;
 		}
 	}
@@ -358,7 +363,8 @@ static void arm_smmu_mmu_notifier_put(struct arm_smmu_mmu_notifier *smmu_mn)
 
 	list_del(&smmu_mn->list);
 
-	arm_smmu_update_ctx_desc_devices(smmu_domain, mm->pasid, NULL);
+	arm_smmu_update_ctx_desc_devices(smmu_domain, mm_get_enqcmd_pasid(mm),
+					 NULL);
 
 	/*
 	 * If we went through clear(), we've already invalidated, and no
@@ -366,7 +372,8 @@ static void arm_smmu_mmu_notifier_put(struct arm_smmu_mmu_notifier *smmu_mn)
 	 */
 	if (!smmu_mn->cleared) {
 		arm_smmu_tlb_inv_asid(smmu_domain->smmu, cd->asid);
-		arm_smmu_atc_inv_domain(smmu_domain, mm->pasid, 0, 0);
+		arm_smmu_atc_inv_domain(smmu_domain, mm_get_enqcmd_pasid(mm), 0,
+					0);
 	}
 
 	/* Frees smmu_mn */
diff --git a/drivers/iommu/iommu-sva.c b/drivers/iommu/iommu-sva.c
index b78671a8a914..4a2f5699747f 100644
--- a/drivers/iommu/iommu-sva.c
+++ b/drivers/iommu/iommu-sva.c
@@ -141,7 +141,7 @@ u32 iommu_sva_get_pasid(struct iommu_sva *handle)
 {
 	struct iommu_domain *domain = handle->domain;
 
-	return domain->mm->pasid;
+	return mm_get_enqcmd_pasid(domain->mm);
 }
 EXPORT_SYMBOL_GPL(iommu_sva_get_pasid);
 
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index cd3f398095bf..4fb239c6ca8d 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -1346,6 +1346,12 @@ static inline bool mm_valid_pasid(struct mm_struct *mm)
 {
 	return mm->pasid != IOMMU_PASID_INVALID;
 }
+
+static inline u32 mm_get_enqcmd_pasid(struct mm_struct *mm)
+{
+	return mm->pasid;
+}
+
 void mm_pasid_drop(struct mm_struct *mm);
 struct iommu_sva *iommu_sva_bind_device(struct device *dev,
 					struct mm_struct *mm);
@@ -1368,6 +1374,12 @@ static inline u32 iommu_sva_get_pasid(struct iommu_sva *handle)
 }
 static inline void mm_pasid_init(struct mm_struct *mm) {}
 static inline bool mm_valid_pasid(struct mm_struct *mm) { return false; }
+
+static inline u32 mm_get_enqcmd_pasid(struct mm_struct *mm)
+{
+	return IOMMU_PASID_INVALID;
+}
+
 static inline void mm_pasid_drop(struct mm_struct *mm) {}
 #endif /* CONFIG_IOMMU_SVA */
 
-- 
cgit v1.2.3


From 541a3e257d48c16b77d19f39ed939ef5832046df Mon Sep 17 00:00:00 2001
From: Tina Zhang <tina.zhang@intel.com>
Date: Fri, 27 Oct 2023 08:05:23 +0800
Subject: mm: Add structure to keep sva information

Introduce iommu_mm_data structure to keep sva information (pasid and the
related sva domains). Add iommu_mm pointer, pointing to an instance of
iommu_mm_data structure, to mm.

Reviewed-by: Vasant Hegde <vasant.hegde@amd.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Tina Zhang <tina.zhang@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20231027000525.1278806-5-tina.zhang@intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 include/linux/iommu.h    | 5 +++++
 include/linux/mm_types.h | 2 ++
 2 files changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 4fb239c6ca8d..f7b1b469e98d 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -812,6 +812,11 @@ struct iommu_sva {
 	struct iommu_domain		*domain;
 };
 
+struct iommu_mm_data {
+	u32			pasid;
+	struct list_head	sva_domains;
+};
+
 int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode,
 		      const struct iommu_ops *ops);
 void iommu_fwspec_free(struct device *dev);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 41f248608dd9..0b4314fab478 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -727,6 +727,7 @@ struct mm_cid {
 #endif
 
 struct kioctx_table;
+struct iommu_mm_data;
 struct mm_struct {
 	struct {
 		/*
@@ -940,6 +941,7 @@ struct mm_struct {
 
 #ifdef CONFIG_IOMMU_MM_DATA
 		u32 pasid;
+		struct iommu_mm_data *iommu_mm;
 #endif
 #ifdef CONFIG_KSM
 		/*
-- 
cgit v1.2.3


From 092edaddb660376648acb97678570ed5d8299768 Mon Sep 17 00:00:00 2001
From: Tina Zhang <tina.zhang@intel.com>
Date: Fri, 27 Oct 2023 08:05:24 +0800
Subject: iommu: Support mm PASID 1:n with sva domains

Each mm bound to devices gets a PASID and corresponding sva domains
allocated in iommu_sva_bind_device(), which are referenced by iommu_mm
field of the mm. The PASID is released in __mmdrop(), while a sva domain
is released when no one is using it (the reference count is decremented
in iommu_sva_unbind_device()). However, although sva domains and their
PASID are separate objects such that their own life cycles could be
handled independently, an enqcmd use case may require releasing the
PASID in releasing the mm (i.e., once a PASID is allocated for a mm, it
will be permanently used by the mm and won't be released until the end
of mm) and only allows to drop the PASID after the sva domains are
released. To this end, mmgrab() is called in iommu_sva_domain_alloc() to
increment the mm reference count and mmdrop() is invoked in
iommu_domain_free() to decrement the mm reference count.

Since the required info of PASID and sva domains is kept in struct
iommu_mm_data of a mm, use mm->iommu_mm field instead of the old pasid
field in mm struct. The sva domain list is protected by iommu_sva_lock.

Besides, this patch removes mm_pasid_init(), as with the introduced
iommu_mm structure, initializing mm pasid in mm_init() is unnecessary.

Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Vasant Hegde <vasant.hegde@amd.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Tina Zhang <tina.zhang@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20231027000525.1278806-6-tina.zhang@intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/iommu-sva.c | 92 +++++++++++++++++++++++++++--------------------
 include/linux/iommu.h     | 23 ++++++++++--
 2 files changed, 74 insertions(+), 41 deletions(-)

(limited to 'include')

diff --git a/drivers/iommu/iommu-sva.c b/drivers/iommu/iommu-sva.c
index 4a2f5699747f..5175e8d85247 100644
--- a/drivers/iommu/iommu-sva.c
+++ b/drivers/iommu/iommu-sva.c
@@ -12,32 +12,42 @@
 static DEFINE_MUTEX(iommu_sva_lock);
 
 /* Allocate a PASID for the mm within range (inclusive) */
-static int iommu_sva_alloc_pasid(struct mm_struct *mm, struct device *dev)
+static struct iommu_mm_data *iommu_alloc_mm_data(struct mm_struct *mm, struct device *dev)
 {
+	struct iommu_mm_data *iommu_mm;
 	ioasid_t pasid;
-	int ret = 0;
+
+	lockdep_assert_held(&iommu_sva_lock);
 
 	if (!arch_pgtable_dma_compat(mm))
-		return -EBUSY;
+		return ERR_PTR(-EBUSY);
 
-	mutex_lock(&iommu_sva_lock);
+	iommu_mm = mm->iommu_mm;
 	/* Is a PASID already associated with this mm? */
-	if (mm_valid_pasid(mm)) {
-		if (mm->pasid >= dev->iommu->max_pasids)
-			ret = -EOVERFLOW;
-		goto out;
+	if (iommu_mm) {
+		if (iommu_mm->pasid >= dev->iommu->max_pasids)
+			return ERR_PTR(-EOVERFLOW);
+		return iommu_mm;
 	}
 
+	iommu_mm = kzalloc(sizeof(struct iommu_mm_data), GFP_KERNEL);
+	if (!iommu_mm)
+		return ERR_PTR(-ENOMEM);
+
 	pasid = iommu_alloc_global_pasid(dev);
 	if (pasid == IOMMU_PASID_INVALID) {
-		ret = -ENOSPC;
-		goto out;
+		kfree(iommu_mm);
+		return ERR_PTR(-ENOSPC);
 	}
-	mm->pasid = pasid;
-	ret = 0;
-out:
-	mutex_unlock(&iommu_sva_lock);
-	return ret;
+	iommu_mm->pasid = pasid;
+	INIT_LIST_HEAD(&iommu_mm->sva_domains);
+	/*
+	 * Make sure the write to mm->iommu_mm is not reordered in front of
+	 * initialization to iommu_mm fields. If it does, readers may see a
+	 * valid iommu_mm with uninitialized values.
+	 */
+	smp_store_release(&mm->iommu_mm, iommu_mm);
+	return iommu_mm;
 }
 
 /**
@@ -58,31 +68,33 @@ out:
  */
 struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm)
 {
+	struct iommu_mm_data *iommu_mm;
 	struct iommu_domain *domain;
 	struct iommu_sva *handle;
 	int ret;
 
+	mutex_lock(&iommu_sva_lock);
+
 	/* Allocate mm->pasid if necessary. */
-	ret = iommu_sva_alloc_pasid(mm, dev);
-	if (ret)
-		return ERR_PTR(ret);
+	iommu_mm = iommu_alloc_mm_data(mm, dev);
+	if (IS_ERR(iommu_mm)) {
+		ret = PTR_ERR(iommu_mm);
+		goto out_unlock;
+	}
 
 	handle = kzalloc(sizeof(*handle), GFP_KERNEL);
-	if (!handle)
-		return ERR_PTR(-ENOMEM);
-
-	mutex_lock(&iommu_sva_lock);
-	/* Search for an existing domain. */
-	domain = iommu_get_domain_for_dev_pasid(dev, mm->pasid,
-						IOMMU_DOMAIN_SVA);
-	if (IS_ERR(domain)) {
-		ret = PTR_ERR(domain);
+	if (!handle) {
+		ret = -ENOMEM;
 		goto out_unlock;
 	}
 
-	if (domain) {
-		domain->users++;
-		goto out;
+	/* Search for an existing domain. */
+	list_for_each_entry(domain, &mm->iommu_mm->sva_domains, next) {
+		ret = iommu_attach_device_pasid(domain, dev, iommu_mm->pasid);
+		if (!ret) {
+			domain->users++;
+			goto out;
+		}
 	}
 
 	/* Allocate a new domain and set it on device pasid. */
@@ -92,23 +104,23 @@ struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm
 		goto out_unlock;
 	}
 
-	ret = iommu_attach_device_pasid(domain, dev, mm->pasid);
+	ret = iommu_attach_device_pasid(domain, dev, iommu_mm->pasid);
 	if (ret)
 		goto out_free_domain;
 	domain->users = 1;
+	list_add(&domain->next, &mm->iommu_mm->sva_domains);
+
 out:
 	mutex_unlock(&iommu_sva_lock);
 	handle->dev = dev;
 	handle->domain = domain;
-
 	return handle;
 
 out_free_domain:
 	iommu_domain_free(domain);
+	kfree(handle);
 out_unlock:
 	mutex_unlock(&iommu_sva_lock);
-	kfree(handle);
-
 	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(iommu_sva_bind_device);
@@ -124,12 +136,13 @@ EXPORT_SYMBOL_GPL(iommu_sva_bind_device);
 void iommu_sva_unbind_device(struct iommu_sva *handle)
 {
 	struct iommu_domain *domain = handle->domain;
-	ioasid_t pasid = domain->mm->pasid;
+	struct iommu_mm_data *iommu_mm = domain->mm->iommu_mm;
 	struct device *dev = handle->dev;
 
 	mutex_lock(&iommu_sva_lock);
+	iommu_detach_device_pasid(domain, dev, iommu_mm->pasid);
 	if (--domain->users == 0) {
-		iommu_detach_device_pasid(domain, dev, pasid);
+		list_del(&domain->next);
 		iommu_domain_free(domain);
 	}
 	mutex_unlock(&iommu_sva_lock);
@@ -205,8 +218,11 @@ out_put_mm:
 
 void mm_pasid_drop(struct mm_struct *mm)
 {
-	if (likely(!mm_valid_pasid(mm)))
+	struct iommu_mm_data *iommu_mm = mm->iommu_mm;
+
+	if (!iommu_mm)
 		return;
 
-	iommu_free_global_pasid(mm->pasid);
+	iommu_free_global_pasid(iommu_mm->pasid);
+	kfree(iommu_mm);
 }
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index f7b1b469e98d..c6bbbe0901d0 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -121,6 +121,11 @@ struct iommu_domain {
 		struct {	/* IOMMU_DOMAIN_SVA */
 			struct mm_struct *mm;
 			int users;
+			/*
+			 * Next iommu_domain in mm->iommu_mm->sva-domains list
+			 * protected by iommu_sva_lock.
+			 */
+			struct list_head next;
 		};
 	};
 };
@@ -1345,16 +1350,28 @@ static inline bool tegra_dev_iommu_get_stream_id(struct device *dev, u32 *stream
 #ifdef CONFIG_IOMMU_MM_DATA
 static inline void mm_pasid_init(struct mm_struct *mm)
 {
-	mm->pasid = IOMMU_PASID_INVALID;
+	/*
+	 * During dup_mm(), a new mm will be memcpy'd from an old one and that makes
+	 * the new mm and the old one point to a same iommu_mm instance. When either
+	 * one of the two mms gets released, the iommu_mm instance is freed, leaving
+	 * the other mm running into a use-after-free/double-free problem. To avoid
+	 * the problem, zeroing the iommu_mm pointer of a new mm is needed here.
+	 */
+	mm->iommu_mm = NULL;
 }
+
 static inline bool mm_valid_pasid(struct mm_struct *mm)
 {
-	return mm->pasid != IOMMU_PASID_INVALID;
+	return READ_ONCE(mm->iommu_mm);
 }
 
 static inline u32 mm_get_enqcmd_pasid(struct mm_struct *mm)
 {
-	return mm->pasid;
+	struct iommu_mm_data *iommu_mm = READ_ONCE(mm->iommu_mm);
+
+	if (!iommu_mm)
+		return IOMMU_PASID_INVALID;
+	return iommu_mm->pasid;
 }
 
 void mm_pasid_drop(struct mm_struct *mm);
-- 
cgit v1.2.3


From 1fa05c932dc71c474da38e4fd0456131128f8486 Mon Sep 17 00:00:00 2001
From: Tina Zhang <tina.zhang@intel.com>
Date: Fri, 27 Oct 2023 08:05:25 +0800
Subject: mm: Deprecate pasid field

Drop the pasid field, as all the information needed for sva domain
management has been moved to the newly added iommu_mm field.

Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Vasant Hegde <vasant.hegde@amd.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Tina Zhang <tina.zhang@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20231027000525.1278806-7-tina.zhang@intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 include/linux/mm_types.h | 1 -
 mm/init-mm.c             | 3 ---
 2 files changed, 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 0b4314fab478..ec71c91e210b 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -940,7 +940,6 @@ struct mm_struct {
 		struct work_struct async_put_work;
 
 #ifdef CONFIG_IOMMU_MM_DATA
-		u32 pasid;
 		struct iommu_mm_data *iommu_mm;
 #endif
 #ifdef CONFIG_KSM
diff --git a/mm/init-mm.c b/mm/init-mm.c
index c52dc2740a3d..24c809379274 100644
--- a/mm/init-mm.c
+++ b/mm/init-mm.c
@@ -44,9 +44,6 @@ struct mm_struct init_mm = {
 #endif
 	.user_ns	= &init_user_ns,
 	.cpu_bitmap	= CPU_BITS_NONE,
-#ifdef CONFIG_IOMMU_MM_DATA
-	.pasid		= IOMMU_PASID_INVALID,
-#endif
 	INIT_MM_CONTEXT(init_mm)
 };
 
-- 
cgit v1.2.3


From 4720287c7bf76e59d19d4dfbdc3f54eeea6fd46b Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Thu, 7 Dec 2023 14:03:08 -0400
Subject: iommu: Remove struct iommu_ops *iommu from arch_setup_dma_ops()

This is not being used to pass ops, it is just a way to tell if an
iommu driver was probed. These days this can be detected directly via
device_iommu_mapped(). Call device_iommu_mapped() in the two places that
need to check it and remove the iommu parameter everywhere.

Reviewed-by: Jerry Snitselaar <jsnitsel@redhat.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Moritz Fischer <mdf@kernel.org>
Acked-by: Christoph Hellwig <hch@lst.de>
Acked-by: Rob Herring <robh@kernel.org>
Tested-by: Hector Martin <marcan@marcan.st>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/1-v2-16e4def25ebb+820-iommu_fwspec_p1_jgg@nvidia.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 arch/arc/mm/dma.c               |  2 +-
 arch/arm/mm/dma-mapping-nommu.c |  2 +-
 arch/arm/mm/dma-mapping.c       | 10 +++++-----
 arch/arm64/mm/dma-mapping.c     |  4 ++--
 arch/mips/mm/dma-noncoherent.c  |  2 +-
 arch/riscv/mm/dma-noncoherent.c |  2 +-
 drivers/acpi/scan.c             |  3 +--
 drivers/hv/hv_common.c          |  2 +-
 drivers/of/device.c             |  2 +-
 include/linux/dma-map-ops.h     |  4 ++--
 10 files changed, 16 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index 2a7fbbb83b70..197707bc7658 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -91,7 +91,7 @@ void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
  * Plug in direct dma map ops.
  */
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-			const struct iommu_ops *iommu, bool coherent)
+			bool coherent)
 {
 	/*
 	 * IOC hardware snoops all DMA traffic keeping the caches consistent
diff --git a/arch/arm/mm/dma-mapping-nommu.c b/arch/arm/mm/dma-mapping-nommu.c
index cfd9c933d2f0..b94850b57995 100644
--- a/arch/arm/mm/dma-mapping-nommu.c
+++ b/arch/arm/mm/dma-mapping-nommu.c
@@ -34,7 +34,7 @@ void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
 }
 
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-			const struct iommu_ops *iommu, bool coherent)
+			bool coherent)
 {
 	if (IS_ENABLED(CONFIG_CPU_V7M)) {
 		/*
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 5409225b4abc..6c359a3af8d9 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -1713,7 +1713,7 @@ void arm_iommu_detach_device(struct device *dev)
 EXPORT_SYMBOL_GPL(arm_iommu_detach_device);
 
 static void arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size,
-				    const struct iommu_ops *iommu, bool coherent)
+				    bool coherent)
 {
 	struct dma_iommu_mapping *mapping;
 
@@ -1748,7 +1748,7 @@ static void arm_teardown_iommu_dma_ops(struct device *dev)
 #else
 
 static void arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size,
-				    const struct iommu_ops *iommu, bool coherent)
+				    bool coherent)
 {
 }
 
@@ -1757,7 +1757,7 @@ static void arm_teardown_iommu_dma_ops(struct device *dev) { }
 #endif	/* CONFIG_ARM_DMA_USE_IOMMU */
 
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-			const struct iommu_ops *iommu, bool coherent)
+			bool coherent)
 {
 	/*
 	 * Due to legacy code that sets the ->dma_coherent flag from a bus
@@ -1776,8 +1776,8 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 	if (dev->dma_ops)
 		return;
 
-	if (iommu)
-		arm_setup_iommu_dma_ops(dev, dma_base, size, iommu, coherent);
+	if (device_iommu_mapped(dev))
+		arm_setup_iommu_dma_ops(dev, dma_base, size, coherent);
 
 	xen_setup_dma_ops(dev);
 	dev->archdata.dma_ops_setup = true;
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 3cb101e8cb29..61886e43e3a1 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -47,7 +47,7 @@ void arch_teardown_dma_ops(struct device *dev)
 #endif
 
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-			const struct iommu_ops *iommu, bool coherent)
+			bool coherent)
 {
 	int cls = cache_line_size_of_cpu();
 
@@ -58,7 +58,7 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 		   ARCH_DMA_MINALIGN, cls);
 
 	dev->dma_coherent = coherent;
-	if (iommu)
+	if (device_iommu_mapped(dev))
 		iommu_setup_dma_ops(dev, dma_base, dma_base + size - 1);
 
 	xen_setup_dma_ops(dev);
diff --git a/arch/mips/mm/dma-noncoherent.c b/arch/mips/mm/dma-noncoherent.c
index 3c4fc97b9f39..0f3cec663a12 100644
--- a/arch/mips/mm/dma-noncoherent.c
+++ b/arch/mips/mm/dma-noncoherent.c
@@ -138,7 +138,7 @@ void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
 
 #ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-		const struct iommu_ops *iommu, bool coherent)
+		bool coherent)
 {
 	dev->dma_coherent = coherent;
 }
diff --git a/arch/riscv/mm/dma-noncoherent.c b/arch/riscv/mm/dma-noncoherent.c
index 4e4e469b8dd6..843107f834b2 100644
--- a/arch/riscv/mm/dma-noncoherent.c
+++ b/arch/riscv/mm/dma-noncoherent.c
@@ -129,7 +129,7 @@ void arch_dma_prep_coherent(struct page *page, size_t size)
 }
 
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-		const struct iommu_ops *iommu, bool coherent)
+			bool coherent)
 {
 	WARN_TAINT(!coherent && riscv_cbom_block_size > ARCH_DMA_MINALIGN,
 		   TAINT_CPU_OUT_OF_SPEC,
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 02bb2cce423f..444a0b3c72f2 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1641,8 +1641,7 @@ int acpi_dma_configure_id(struct device *dev, enum dev_dma_attr attr,
 	if (PTR_ERR(iommu) == -EPROBE_DEFER)
 		return -EPROBE_DEFER;
 
-	arch_setup_dma_ops(dev, 0, U64_MAX,
-				iommu, attr == DEV_DMA_COHERENT);
+	arch_setup_dma_ops(dev, 0, U64_MAX, attr == DEV_DMA_COHERENT);
 
 	return 0;
 }
diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c
index 4372f5d146ab..0285a74363b3 100644
--- a/drivers/hv/hv_common.c
+++ b/drivers/hv/hv_common.c
@@ -488,7 +488,7 @@ void hv_setup_dma_ops(struct device *dev, bool coherent)
 	 * Hyper-V does not offer a vIOMMU in the guest
 	 * VM, so pass 0/NULL for the IOMMU settings
 	 */
-	arch_setup_dma_ops(dev, 0, 0, NULL, coherent);
+	arch_setup_dma_ops(dev, 0, 0, coherent);
 }
 EXPORT_SYMBOL_GPL(hv_setup_dma_ops);
 
diff --git a/drivers/of/device.c b/drivers/of/device.c
index 1ca42ad9dd15..65c71be71a8d 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -193,7 +193,7 @@ int of_dma_configure_id(struct device *dev, struct device_node *np,
 	dev_dbg(dev, "device is%sbehind an iommu\n",
 		iommu ? " " : " not ");
 
-	arch_setup_dma_ops(dev, dma_start, size, iommu, coherent);
+	arch_setup_dma_ops(dev, dma_start, size, coherent);
 
 	if (!iommu)
 		of_dma_set_restricted_buffer(dev, np);
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index a52e508d1869..e9cc317e9d7d 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -427,10 +427,10 @@ bool arch_dma_unmap_sg_direct(struct device *dev, struct scatterlist *sg,
 
 #ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-		const struct iommu_ops *iommu, bool coherent);
+		bool coherent);
 #else
 static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base,
-		u64 size, const struct iommu_ops *iommu, bool coherent)
+		u64 size, bool coherent)
 {
 }
 #endif /* CONFIG_ARCH_HAS_SETUP_DMA_OPS */
-- 
cgit v1.2.3


From 6ff6e184f1f4d4993d45ca3f934c8288890965fe Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Thu, 7 Dec 2023 14:03:09 -0400
Subject: iommmu/of: Do not return struct iommu_ops from of_iommu_configure()

Nothing needs this pointer. Return a normal error code with the usual
IOMMU semantic that ENODEV means 'there is no IOMMU driver'.

Reviewed-by: Jerry Snitselaar <jsnitsel@redhat.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Acked-by: Rob Herring <robh@kernel.org>
Tested-by: Hector Martin <marcan@marcan.st>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/2-v2-16e4def25ebb+820-iommu_fwspec_p1_jgg@nvidia.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/of_iommu.c | 31 +++++++++++++++++++------------
 drivers/of/device.c      | 22 +++++++++++++++-------
 include/linux/of_iommu.h | 13 ++++++-------
 3 files changed, 40 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c
index 5ecca53847d3..c6510d7e7b24 100644
--- a/drivers/iommu/of_iommu.c
+++ b/drivers/iommu/of_iommu.c
@@ -107,16 +107,22 @@ static int of_iommu_configure_device(struct device_node *master_np,
 		      of_iommu_configure_dev(master_np, dev);
 }
 
-const struct iommu_ops *of_iommu_configure(struct device *dev,
-					   struct device_node *master_np,
-					   const u32 *id)
+/*
+ * Returns:
+ *  0 on success, an iommu was configured
+ *  -ENODEV if the device does not have any IOMMU
+ *  -EPROBEDEFER if probing should be tried again
+ *  -errno fatal errors
+ */
+int of_iommu_configure(struct device *dev, struct device_node *master_np,
+		       const u32 *id)
 {
 	const struct iommu_ops *ops = NULL;
 	struct iommu_fwspec *fwspec;
 	int err = NO_IOMMU;
 
 	if (!master_np)
-		return NULL;
+		return -ENODEV;
 
 	/* Serialise to make dev->iommu stable under our potential fwspec */
 	mutex_lock(&iommu_probe_device_lock);
@@ -124,7 +130,7 @@ const struct iommu_ops *of_iommu_configure(struct device *dev,
 	if (fwspec) {
 		if (fwspec->ops) {
 			mutex_unlock(&iommu_probe_device_lock);
-			return fwspec->ops;
+			return 0;
 		}
 		/* In the deferred case, start again from scratch */
 		iommu_fwspec_free(dev);
@@ -169,14 +175,15 @@ const struct iommu_ops *of_iommu_configure(struct device *dev,
 		err = iommu_probe_device(dev);
 
 	/* Ignore all other errors apart from EPROBE_DEFER */
-	if (err == -EPROBE_DEFER) {
-		ops = ERR_PTR(err);
-	} else if (err < 0) {
-		dev_dbg(dev, "Adding to IOMMU failed: %d\n", err);
-		ops = NULL;
+	if (err < 0) {
+		if (err == -EPROBE_DEFER)
+			return err;
+		dev_dbg(dev, "Adding to IOMMU failed: %pe\n", ERR_PTR(err));
+		return err;
 	}
-
-	return ops;
+	if (!ops)
+		return -ENODEV;
+	return 0;
 }
 
 static enum iommu_resv_type __maybe_unused
diff --git a/drivers/of/device.c b/drivers/of/device.c
index 65c71be71a8d..873d933e8e6d 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -93,12 +93,12 @@ of_dma_set_restricted_buffer(struct device *dev, struct device_node *np)
 int of_dma_configure_id(struct device *dev, struct device_node *np,
 			bool force_dma, const u32 *id)
 {
-	const struct iommu_ops *iommu;
 	const struct bus_dma_region *map = NULL;
 	struct device_node *bus_np;
 	u64 dma_start = 0;
 	u64 mask, end, size = 0;
 	bool coherent;
+	int iommu_ret;
 	int ret;
 
 	if (np == dev->of_node)
@@ -181,21 +181,29 @@ int of_dma_configure_id(struct device *dev, struct device_node *np,
 	dev_dbg(dev, "device is%sdma coherent\n",
 		coherent ? " " : " not ");
 
-	iommu = of_iommu_configure(dev, np, id);
-	if (PTR_ERR(iommu) == -EPROBE_DEFER) {
+	iommu_ret = of_iommu_configure(dev, np, id);
+	if (iommu_ret == -EPROBE_DEFER) {
 		/* Don't touch range map if it wasn't set from a valid dma-ranges */
 		if (!ret)
 			dev->dma_range_map = NULL;
 		kfree(map);
 		return -EPROBE_DEFER;
-	}
+	} else if (iommu_ret == -ENODEV) {
+		dev_dbg(dev, "device is not behind an iommu\n");
+	} else if (iommu_ret) {
+		dev_err(dev, "iommu configuration for device failed with %pe\n",
+			ERR_PTR(iommu_ret));
 
-	dev_dbg(dev, "device is%sbehind an iommu\n",
-		iommu ? " " : " not ");
+		/*
+		 * Historically this routine doesn't fail driver probing
+		 * due to errors in of_iommu_configure()
+		 */
+	} else
+		dev_dbg(dev, "device is behind an iommu\n");
 
 	arch_setup_dma_ops(dev, dma_start, size, coherent);
 
-	if (!iommu)
+	if (iommu_ret)
 		of_dma_set_restricted_buffer(dev, np);
 
 	return 0;
diff --git a/include/linux/of_iommu.h b/include/linux/of_iommu.h
index 9a5e6b410dd2..e61cbbe12dac 100644
--- a/include/linux/of_iommu.h
+++ b/include/linux/of_iommu.h
@@ -8,20 +8,19 @@ struct iommu_ops;
 
 #ifdef CONFIG_OF_IOMMU
 
-extern const struct iommu_ops *of_iommu_configure(struct device *dev,
-					struct device_node *master_np,
-					const u32 *id);
+extern int of_iommu_configure(struct device *dev, struct device_node *master_np,
+			      const u32 *id);
 
 extern void of_iommu_get_resv_regions(struct device *dev,
 				      struct list_head *list);
 
 #else
 
-static inline const struct iommu_ops *of_iommu_configure(struct device *dev,
-					 struct device_node *master_np,
-					 const u32 *id)
+static inline int of_iommu_configure(struct device *dev,
+				     struct device_node *master_np,
+				     const u32 *id)
 {
-	return NULL;
+	return -ENODEV;
 }
 
 static inline void of_iommu_get_resv_regions(struct device *dev,
-- 
cgit v1.2.3


From eda1a94caf6b05482bbf57dc244e7a31a9dba77c Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Thu, 7 Dec 2023 14:03:12 -0400
Subject: iommu: Mark dev_iommu_priv_set() with a lockdep

A perfect driver would only call dev_iommu_priv_set() from its probe
callback. We've made it functionally correct to call it from the of_xlate
by adding a lock around that call.

lockdep assert that iommu_probe_device_lock is held to discourage misuse.

Exclude PPC kernels with CONFIG_FSL_PAMU turned on because FSL_PAMU uses a
global static for its priv and abuses priv for its domain.

Remove the pointless stores of NULL, all these are on paths where the core
code will free dev->iommu after the op returns.

Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jerry Snitselaar <jsnitsel@redhat.com>
Tested-by: Hector Martin <marcan@marcan.st>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/5-v2-16e4def25ebb+820-iommu_fwspec_p1_jgg@nvidia.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/amd/iommu.c                   | 2 --
 drivers/iommu/apple-dart.c                  | 1 -
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 1 -
 drivers/iommu/arm/arm-smmu/arm-smmu.c       | 1 -
 drivers/iommu/intel/iommu.c                 | 2 --
 drivers/iommu/iommu.c                       | 9 +++++++++
 drivers/iommu/omap-iommu.c                  | 1 -
 include/linux/iommu.h                       | 5 +----
 8 files changed, 10 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index fcc987f5d4ed..8199c678c2dc 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -551,8 +551,6 @@ static void amd_iommu_uninit_device(struct device *dev)
 	if (dev_data->domain)
 		detach_device(dev);
 
-	dev_iommu_priv_set(dev, NULL);
-
 	/*
 	 * We keep dev_data around for unplugged devices and reuse it when the
 	 * device is re-plugged - not doing so would introduce a ton of races.
diff --git a/drivers/iommu/apple-dart.c b/drivers/iommu/apple-dart.c
index ee05f4824bfa..56cfc33042e0 100644
--- a/drivers/iommu/apple-dart.c
+++ b/drivers/iommu/apple-dart.c
@@ -740,7 +740,6 @@ static void apple_dart_release_device(struct device *dev)
 {
 	struct apple_dart_master_cfg *cfg = dev_iommu_priv_get(dev);
 
-	dev_iommu_priv_set(dev, NULL);
 	kfree(cfg);
 }
 
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index fc4317c25b6d..1855d3892b15 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -2695,7 +2695,6 @@ static struct iommu_device *arm_smmu_probe_device(struct device *dev)
 
 err_free_master:
 	kfree(master);
-	dev_iommu_priv_set(dev, NULL);
 	return ERR_PTR(ret);
 }
 
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c
index 4d09c0047892..adc7937fd8a3 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c
@@ -1420,7 +1420,6 @@ static void arm_smmu_release_device(struct device *dev)
 
 	arm_smmu_rpm_put(cfg->smmu);
 
-	dev_iommu_priv_set(dev, NULL);
 	kfree(cfg);
 }
 
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 897159dba47d..511589341074 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -4461,7 +4461,6 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev)
 		ret = intel_pasid_alloc_table(dev);
 		if (ret) {
 			dev_err(dev, "PASID table allocation failed\n");
-			dev_iommu_priv_set(dev, NULL);
 			kfree(info);
 			return ERR_PTR(ret);
 		}
@@ -4479,7 +4478,6 @@ static void intel_iommu_release_device(struct device *dev)
 	dmar_remove_one_dev_info(dev);
 	intel_pasid_free_table(dev);
 	intel_iommu_debugfs_remove_dev(info);
-	dev_iommu_priv_set(dev, NULL);
 	kfree(info);
 	set_dma_ops(dev, NULL);
 }
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index df58025c001b..68e648b55767 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -387,6 +387,15 @@ static u32 dev_iommu_get_max_pasids(struct device *dev)
 	return min_t(u32, max_pasids, dev->iommu->iommu_dev->max_pasids);
 }
 
+void dev_iommu_priv_set(struct device *dev, void *priv)
+{
+	/* FSL_PAMU does something weird */
+	if (!IS_ENABLED(CONFIG_FSL_PAMU))
+		lockdep_assert_held(&iommu_probe_device_lock);
+	dev->iommu->priv = priv;
+}
+EXPORT_SYMBOL_GPL(dev_iommu_priv_set);
+
 /*
  * Init the dev->iommu and dev->iommu_group in the struct device and get the
  * driver probed
diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c
index c66b070841dd..c9528065a59a 100644
--- a/drivers/iommu/omap-iommu.c
+++ b/drivers/iommu/omap-iommu.c
@@ -1719,7 +1719,6 @@ static void omap_iommu_release_device(struct device *dev)
 	if (!dev->of_node || !arch_data)
 		return;
 
-	dev_iommu_priv_set(dev, NULL);
 	kfree(arch_data);
 
 }
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index c6bbbe0901d0..3a556996fea7 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -850,10 +850,7 @@ static inline void *dev_iommu_priv_get(struct device *dev)
 		return NULL;
 }
 
-static inline void dev_iommu_priv_set(struct device *dev, void *priv)
-{
-	dev->iommu->priv = priv;
-}
+void dev_iommu_priv_set(struct device *dev, void *priv);
 
 extern struct mutex iommu_probe_device_lock;
 int iommu_probe_device(struct device *dev);
-- 
cgit v1.2.3


From 0e034aec5be2e8b1199b87b04d32e4a8b805a9db Mon Sep 17 00:00:00 2001
From: Herve Codina <herve.codina@bootlin.com>
Date: Tue, 5 Dec 2023 16:21:01 +0100
Subject: soc: fsl: cpm1: qmc: Extend the API to provide Rx status

In HDLC mode, some status flags related to the data read transfer can be
set by the hardware and need to be known by a QMC consumer for further
analysis.

Extend the API in order to provide these transfer status flags at the
read complete() call.

In TRANSPARENT mode, these flags have no meaning. Keep only one read
complete() API and update the consumers working in transparent mode.
In this case, the newly introduced flags parameter is simply unused.

Signed-off-by: Herve Codina <herve.codina@bootlin.com>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Link: https://lore.kernel.org/r/20231205152116.122512-5-herve.codina@bootlin.com
---
 drivers/soc/fsl/qe/qmc.c      | 29 +++++++++++++++++++++++++----
 include/soc/fsl/qe/qmc.h      | 15 ++++++++++++++-
 sound/soc/fsl/fsl_qmc_audio.c |  2 +-
 3 files changed, 40 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/soc/fsl/qe/qmc.c b/drivers/soc/fsl/qe/qmc.c
index 2312152a44b3..4b4832d93c9b 100644
--- a/drivers/soc/fsl/qe/qmc.c
+++ b/drivers/soc/fsl/qe/qmc.c
@@ -166,7 +166,7 @@
 struct qmc_xfer_desc {
 	union {
 		void (*tx_complete)(void *context);
-		void (*rx_complete)(void *context, size_t length);
+		void (*rx_complete)(void *context, size_t length, unsigned int flags);
 	};
 	void *context;
 };
@@ -421,7 +421,8 @@ end:
 }
 
 int qmc_chan_read_submit(struct qmc_chan *chan, dma_addr_t addr, size_t length,
-			 void (*complete)(void *context, size_t length), void *context)
+			 void (*complete)(void *context, size_t length, unsigned int flags),
+			 void *context)
 {
 	struct qmc_xfer_desc *xfer_desc;
 	unsigned long flags;
@@ -454,6 +455,10 @@ int qmc_chan_read_submit(struct qmc_chan *chan, dma_addr_t addr, size_t length,
 	xfer_desc->rx_complete = complete;
 	xfer_desc->context = context;
 
+	/* Clear previous status flags */
+	ctrl &= ~(QMC_BD_RX_L | QMC_BD_RX_F | QMC_BD_RX_LG | QMC_BD_RX_NO |
+		  QMC_BD_RX_AB | QMC_BD_RX_CR);
+
 	/* Activate the descriptor */
 	ctrl |= (QMC_BD_RX_E | QMC_BD_RX_UB);
 	wmb(); /* Be sure to flush data before descriptor activation */
@@ -485,7 +490,7 @@ EXPORT_SYMBOL(qmc_chan_read_submit);
 
 static void qmc_chan_read_done(struct qmc_chan *chan)
 {
-	void (*complete)(void *context, size_t size);
+	void (*complete)(void *context, size_t size, unsigned int flags);
 	struct qmc_xfer_desc *xfer_desc;
 	unsigned long flags;
 	cbd_t __iomem *bd;
@@ -527,7 +532,23 @@ static void qmc_chan_read_done(struct qmc_chan *chan)
 
 		if (complete) {
 			spin_unlock_irqrestore(&chan->rx_lock, flags);
-			complete(context, datalen);
+
+			/*
+			 * Avoid conversion between internal hardware flags and
+			 * the software API flags.
+			 * -> Be sure that the software API flags are consistent
+			 *    with the hardware flags
+			 */
+			BUILD_BUG_ON(QMC_RX_FLAG_HDLC_LAST  != QMC_BD_RX_L);
+			BUILD_BUG_ON(QMC_RX_FLAG_HDLC_FIRST != QMC_BD_RX_F);
+			BUILD_BUG_ON(QMC_RX_FLAG_HDLC_OVF   != QMC_BD_RX_LG);
+			BUILD_BUG_ON(QMC_RX_FLAG_HDLC_UNA   != QMC_BD_RX_NO);
+			BUILD_BUG_ON(QMC_RX_FLAG_HDLC_ABORT != QMC_BD_RX_AB);
+			BUILD_BUG_ON(QMC_RX_FLAG_HDLC_CRC   != QMC_BD_RX_CR);
+
+			complete(context, datalen,
+				 ctrl & (QMC_BD_RX_L | QMC_BD_RX_F | QMC_BD_RX_LG |
+					 QMC_BD_RX_NO | QMC_BD_RX_AB | QMC_BD_RX_CR));
 			spin_lock_irqsave(&chan->rx_lock, flags);
 		}
 
diff --git a/include/soc/fsl/qe/qmc.h b/include/soc/fsl/qe/qmc.h
index 3c61a50d2ae2..6f1d6cebc9fe 100644
--- a/include/soc/fsl/qe/qmc.h
+++ b/include/soc/fsl/qe/qmc.h
@@ -9,6 +9,7 @@
 #ifndef __SOC_FSL_QMC_H__
 #define __SOC_FSL_QMC_H__
 
+#include <linux/bits.h>
 #include <linux/types.h>
 
 struct device_node;
@@ -56,8 +57,20 @@ int qmc_chan_set_param(struct qmc_chan *chan, const struct qmc_chan_param *param
 int qmc_chan_write_submit(struct qmc_chan *chan, dma_addr_t addr, size_t length,
 			  void (*complete)(void *context), void *context);
 
+/* Flags available (ORed) for read complete() flags parameter in HDLC mode.
+ * No flags are available in transparent mode and the read complete() flags
+ * parameter has no meaning in transparent mode.
+ */
+#define QMC_RX_FLAG_HDLC_LAST	BIT(11) /* Last in frame */
+#define QMC_RX_FLAG_HDLC_FIRST	BIT(10) /* First in frame */
+#define QMC_RX_FLAG_HDLC_OVF	BIT(5)  /* Data overflow */
+#define QMC_RX_FLAG_HDLC_UNA	BIT(4)  /* Unaligned (ie. bits received not multiple of 8) */
+#define QMC_RX_FLAG_HDLC_ABORT	BIT(3)  /* Received an abort sequence (seven consecutive ones) */
+#define QMC_RX_FLAG_HDLC_CRC	BIT(2)  /* CRC error */
+
 int qmc_chan_read_submit(struct qmc_chan *chan, dma_addr_t addr, size_t length,
-			 void (*complete)(void *context, size_t length),
+			 void (*complete)(void *context, size_t length,
+					  unsigned int flags),
 			 void *context);
 
 #define QMC_CHAN_READ  (1<<0)
diff --git a/sound/soc/fsl/fsl_qmc_audio.c b/sound/soc/fsl/fsl_qmc_audio.c
index 56d6b0b039a2..bfaaa451735b 100644
--- a/sound/soc/fsl/fsl_qmc_audio.c
+++ b/sound/soc/fsl/fsl_qmc_audio.c
@@ -99,7 +99,7 @@ static void qmc_audio_pcm_write_complete(void *context)
 	snd_pcm_period_elapsed(prtd->substream);
 }
 
-static void qmc_audio_pcm_read_complete(void *context, size_t length)
+static void qmc_audio_pcm_read_complete(void *context, size_t length, unsigned int flags)
 {
 	struct qmc_dai_prtd *prtd = context;
 	int ret;
-- 
cgit v1.2.3


From ba3b7e4753c5ad80b3670277a2104aeb421e0d7d Mon Sep 17 00:00:00 2001
From: Herve Codina <herve.codina@bootlin.com>
Date: Tue, 5 Dec 2023 16:21:03 +0100
Subject: soc: fsl: cpm1: qmc: Add support for child devices

QMC child devices support is needed to avoid orphan DT nodes that use a
simple DT phandle to reference a QMC channel.

Allow to instantiate child devices and also extend the API to get the
qmc_chan using a child device.

Signed-off-by: Herve Codina <herve.codina@bootlin.com>
Link: https://lore.kernel.org/r/20231205152116.122512-7-herve.codina@bootlin.com
---
 drivers/soc/fsl/qe/qmc.c | 91 +++++++++++++++++++++++++++++++++++++-----------
 include/soc/fsl/qe/qmc.h |  2 ++
 2 files changed, 73 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/drivers/soc/fsl/qe/qmc.c b/drivers/soc/fsl/qe/qmc.c
index 27f2f16deac9..e716f13669a0 100644
--- a/drivers/soc/fsl/qe/qmc.c
+++ b/drivers/soc/fsl/qe/qmc.c
@@ -1425,8 +1425,16 @@ static int qmc_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, qmc);
 
+	/* Populate channel related devices */
+	ret = devm_of_platform_populate(qmc->dev);
+	if (ret)
+		goto err_disable_txrx;
+
 	return 0;
 
+err_disable_txrx:
+	qmc_setbits32(qmc->scc_regs + SCC_GSMRL, 0);
+
 err_disable_intr:
 	qmc_write16(qmc->scc_regs + SCC_SCCM, 0);
 
@@ -1465,26 +1473,16 @@ static struct platform_driver qmc_driver = {
 };
 module_platform_driver(qmc_driver);
 
-struct qmc_chan *qmc_chan_get_byphandle(struct device_node *np, const char *phandle_name)
+static struct qmc_chan *qmc_chan_get_from_qmc(struct device_node *qmc_np, unsigned int chan_index)
 {
-	struct of_phandle_args out_args;
 	struct platform_device *pdev;
 	struct qmc_chan *qmc_chan;
 	struct qmc *qmc;
-	int ret;
 
-	ret = of_parse_phandle_with_fixed_args(np, phandle_name, 1, 0,
-					       &out_args);
-	if (ret < 0)
-		return ERR_PTR(ret);
-
-	if (!of_match_node(qmc_driver.driver.of_match_table, out_args.np)) {
-		of_node_put(out_args.np);
+	if (!of_match_node(qmc_driver.driver.of_match_table, qmc_np))
 		return ERR_PTR(-EINVAL);
-	}
 
-	pdev = of_find_device_by_node(out_args.np);
-	of_node_put(out_args.np);
+	pdev = of_find_device_by_node(qmc_np);
 	if (!pdev)
 		return ERR_PTR(-ENODEV);
 
@@ -1494,17 +1492,12 @@ struct qmc_chan *qmc_chan_get_byphandle(struct device_node *np, const char *phan
 		return ERR_PTR(-EPROBE_DEFER);
 	}
 
-	if (out_args.args_count != 1) {
+	if (chan_index >= ARRAY_SIZE(qmc->chans)) {
 		platform_device_put(pdev);
 		return ERR_PTR(-EINVAL);
 	}
 
-	if (out_args.args[0] >= ARRAY_SIZE(qmc->chans)) {
-		platform_device_put(pdev);
-		return ERR_PTR(-EINVAL);
-	}
-
-	qmc_chan = qmc->chans[out_args.args[0]];
+	qmc_chan = qmc->chans[chan_index];
 	if (!qmc_chan) {
 		platform_device_put(pdev);
 		return ERR_PTR(-ENOENT);
@@ -1512,8 +1505,44 @@ struct qmc_chan *qmc_chan_get_byphandle(struct device_node *np, const char *phan
 
 	return qmc_chan;
 }
+
+struct qmc_chan *qmc_chan_get_byphandle(struct device_node *np, const char *phandle_name)
+{
+	struct of_phandle_args out_args;
+	struct qmc_chan *qmc_chan;
+	int ret;
+
+	ret = of_parse_phandle_with_fixed_args(np, phandle_name, 1, 0,
+					       &out_args);
+	if (ret < 0)
+		return ERR_PTR(ret);
+
+	if (out_args.args_count != 1) {
+		of_node_put(out_args.np);
+		return ERR_PTR(-EINVAL);
+	}
+
+	qmc_chan = qmc_chan_get_from_qmc(out_args.np, out_args.args[0]);
+	of_node_put(out_args.np);
+	return qmc_chan;
+}
 EXPORT_SYMBOL(qmc_chan_get_byphandle);
 
+struct qmc_chan *qmc_chan_get_bychild(struct device_node *np)
+{
+	struct device_node *qmc_np;
+	u32 chan_index;
+	int ret;
+
+	qmc_np = np->parent;
+	ret = of_property_read_u32(np, "reg", &chan_index);
+	if (ret)
+		return ERR_PTR(-EINVAL);
+
+	return qmc_chan_get_from_qmc(qmc_np, chan_index);
+}
+EXPORT_SYMBOL(qmc_chan_get_bychild);
+
 void qmc_chan_put(struct qmc_chan *chan)
 {
 	put_device(chan->qmc->dev);
@@ -1550,6 +1579,28 @@ struct qmc_chan *devm_qmc_chan_get_byphandle(struct device *dev,
 }
 EXPORT_SYMBOL(devm_qmc_chan_get_byphandle);
 
+struct qmc_chan *devm_qmc_chan_get_bychild(struct device *dev,
+					   struct device_node *np)
+{
+	struct qmc_chan *qmc_chan;
+	struct qmc_chan **dr;
+
+	dr = devres_alloc(devm_qmc_chan_release, sizeof(*dr), GFP_KERNEL);
+	if (!dr)
+		return ERR_PTR(-ENOMEM);
+
+	qmc_chan = qmc_chan_get_bychild(np);
+	if (!IS_ERR(qmc_chan)) {
+		*dr = qmc_chan;
+		devres_add(dev, dr);
+	} else {
+		devres_free(dr);
+	}
+
+	return qmc_chan;
+}
+EXPORT_SYMBOL(devm_qmc_chan_get_bychild);
+
 MODULE_AUTHOR("Herve Codina <herve.codina@bootlin.com>");
 MODULE_DESCRIPTION("CPM QMC driver");
 MODULE_LICENSE("GPL");
diff --git a/include/soc/fsl/qe/qmc.h b/include/soc/fsl/qe/qmc.h
index 6f1d6cebc9fe..166484bb4294 100644
--- a/include/soc/fsl/qe/qmc.h
+++ b/include/soc/fsl/qe/qmc.h
@@ -17,9 +17,11 @@ struct device;
 struct qmc_chan;
 
 struct qmc_chan *qmc_chan_get_byphandle(struct device_node *np, const char *phandle_name);
+struct qmc_chan *qmc_chan_get_bychild(struct device_node *np);
 void qmc_chan_put(struct qmc_chan *chan);
 struct qmc_chan *devm_qmc_chan_get_byphandle(struct device *dev, struct device_node *np,
 					     const char *phandle_name);
+struct qmc_chan *devm_qmc_chan_get_bychild(struct device *dev, struct device_node *np);
 
 enum qmc_mode {
 	QMC_TRANSPARENT,
-- 
cgit v1.2.3


From 7a2ee1576dcc6bbe017a8283fba237b05b13fd15 Mon Sep 17 00:00:00 2001
From: Herve Codina <herve.codina@bootlin.com>
Date: Tue, 5 Dec 2023 16:21:14 +0100
Subject: soc: fsl: cpm1: qmc: Introduce functions to change timeslots at
 runtime

Introduce qmc_chan_{get,set}_ts_info() function to allow timeslots
modification at runtime.

The modification is provided using qmc_chan_set_ts_info() and will be
applied on next qmc_chan_start().
qmc_chan_set_ts_info() must be called with the channel rx and/or tx
stopped.

Signed-off-by: Herve Codina <herve.codina@bootlin.com>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Link: https://lore.kernel.org/r/20231205152116.122512-18-herve.codina@bootlin.com
---
 drivers/soc/fsl/qe/qmc.c | 51 ++++++++++++++++++++++++++++++++++++++++++++++++
 include/soc/fsl/qe/qmc.h | 10 ++++++++++
 2 files changed, 61 insertions(+)

(limited to 'include')

diff --git a/drivers/soc/fsl/qe/qmc.c b/drivers/soc/fsl/qe/qmc.c
index 45d9cb40a118..f498db9abe35 100644
--- a/drivers/soc/fsl/qe/qmc.c
+++ b/drivers/soc/fsl/qe/qmc.c
@@ -290,6 +290,57 @@ int qmc_chan_get_info(struct qmc_chan *chan, struct qmc_chan_info *info)
 }
 EXPORT_SYMBOL(qmc_chan_get_info);
 
+int qmc_chan_get_ts_info(struct qmc_chan *chan, struct qmc_chan_ts_info *ts_info)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&chan->ts_lock, flags);
+
+	ts_info->rx_ts_mask_avail = chan->rx_ts_mask_avail;
+	ts_info->tx_ts_mask_avail = chan->tx_ts_mask_avail;
+	ts_info->rx_ts_mask = chan->rx_ts_mask;
+	ts_info->tx_ts_mask = chan->tx_ts_mask;
+
+	spin_unlock_irqrestore(&chan->ts_lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL(qmc_chan_get_ts_info);
+
+int qmc_chan_set_ts_info(struct qmc_chan *chan, const struct qmc_chan_ts_info *ts_info)
+{
+	unsigned long flags;
+	int ret;
+
+	/* Only a subset of available timeslots is allowed */
+	if ((ts_info->rx_ts_mask & chan->rx_ts_mask_avail) != ts_info->rx_ts_mask)
+		return -EINVAL;
+	if ((ts_info->tx_ts_mask & chan->tx_ts_mask_avail) != ts_info->tx_ts_mask)
+		return -EINVAL;
+
+	/* In case of common rx/tx table, rx/tx masks must be identical */
+	if (chan->qmc->is_tsa_64rxtx) {
+		if (ts_info->rx_ts_mask != ts_info->tx_ts_mask)
+			return -EINVAL;
+	}
+
+	spin_lock_irqsave(&chan->ts_lock, flags);
+
+	if ((chan->tx_ts_mask != ts_info->tx_ts_mask && !chan->is_tx_stopped) ||
+	    (chan->rx_ts_mask != ts_info->rx_ts_mask && !chan->is_rx_stopped)) {
+		dev_err(chan->qmc->dev, "Channel rx and/or tx not stopped\n");
+		ret = -EBUSY;
+	} else {
+		chan->tx_ts_mask = ts_info->tx_ts_mask;
+		chan->rx_ts_mask = ts_info->rx_ts_mask;
+		ret = 0;
+	}
+	spin_unlock_irqrestore(&chan->ts_lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL(qmc_chan_set_ts_info);
+
 int qmc_chan_set_param(struct qmc_chan *chan, const struct qmc_chan_param *param)
 {
 	if (param->mode != chan->mode)
diff --git a/include/soc/fsl/qe/qmc.h b/include/soc/fsl/qe/qmc.h
index 166484bb4294..2a333fc1ea81 100644
--- a/include/soc/fsl/qe/qmc.h
+++ b/include/soc/fsl/qe/qmc.h
@@ -40,6 +40,16 @@ struct qmc_chan_info {
 
 int qmc_chan_get_info(struct qmc_chan *chan, struct qmc_chan_info *info);
 
+struct qmc_chan_ts_info {
+	u64 rx_ts_mask_avail;
+	u64 tx_ts_mask_avail;
+	u64 rx_ts_mask;
+	u64 tx_ts_mask;
+};
+
+int qmc_chan_get_ts_info(struct qmc_chan *chan, struct qmc_chan_ts_info *ts_info);
+int qmc_chan_set_ts_info(struct qmc_chan *chan, const struct qmc_chan_ts_info *ts_info);
+
 struct qmc_chan_param {
 	enum qmc_mode mode;
 	union {
-- 
cgit v1.2.3


From 10fa22b6fb68198ab6bf2ab468a11c54f083761d Mon Sep 17 00:00:00 2001
From: Evan Quan <quanliangl@hotmail.com>
Date: Mon, 11 Dec 2023 18:06:24 +0800
Subject: wifi: cfg80211: expose nl80211_chan_width_to_mhz for wide sharing

The newly added WBRF feature needs this interface for channel
width calculation.

Signed-off-by: Evan Quan <quanliangl@hotmail.com>
Signed-off-by: Ma Jun <Jun.Ma2@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://msgid.link/20231211100630.2170152-4-Jun.Ma2@amd.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 9 +++++++++
 net/wireless/chan.c    | 3 ++-
 2 files changed, 11 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index d59669d86718..324a5f710ad3 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -976,6 +976,15 @@ const struct cfg80211_chan_def *
 cfg80211_chandef_compatible(const struct cfg80211_chan_def *chandef1,
 			    const struct cfg80211_chan_def *chandef2);
 
+/**
+ * nl80211_chan_width_to_mhz - get the channel width in MHz
+ * @chan_width: the channel width from &enum nl80211_chan_width
+ *
+ * Return: channel width in MHz if the chan_width from &enum nl80211_chan_width
+ * is valid. -1 otherwise.
+ */
+int nl80211_chan_width_to_mhz(enum nl80211_chan_width chan_width);
+
 /**
  * cfg80211_chandef_valid - check if a channel definition is valid
  * @chandef: the channel definition to check
diff --git a/net/wireless/chan.c b/net/wireless/chan.c
index 2d21e423abdb..dfb4893421d7 100644
--- a/net/wireless/chan.c
+++ b/net/wireless/chan.c
@@ -141,7 +141,7 @@ static bool cfg80211_edmg_chandef_valid(const struct cfg80211_chan_def *chandef)
 	return true;
 }
 
-static int nl80211_chan_width_to_mhz(enum nl80211_chan_width chan_width)
+int nl80211_chan_width_to_mhz(enum nl80211_chan_width chan_width)
 {
 	int mhz;
 
@@ -190,6 +190,7 @@ static int nl80211_chan_width_to_mhz(enum nl80211_chan_width chan_width)
 	}
 	return mhz;
 }
+EXPORT_SYMBOL(nl80211_chan_width_to_mhz);
 
 static int cfg80211_chandef_get_width(const struct cfg80211_chan_def *c)
 {
-- 
cgit v1.2.3


From aa0887c4f18e280f8c2aa6964af602bd16c37f54 Mon Sep 17 00:00:00 2001
From: Vinayak Yadawad <vinayak.yadawad@broadcom.com>
Date: Wed, 29 Nov 2023 18:20:43 +0530
Subject: wifi: nl80211: Extend del pmksa support for SAE and OWE security

Current handling of del pmksa with SSID is limited to FILS
security. In the current change the del pmksa support is extended
to SAE/OWE security offloads as well. For OWE/SAE offloads, the
PMK is generated and cached at driver/FW, so user app needs the
capability to request cache deletion based on SSID for drivers
supporting SAE/OWE offload.

Signed-off-by: Vinayak Yadawad <vinayak.yadawad@broadcom.com>
Link: https://msgid.link/ecdae726459e0944c377a6a6f6cb2c34d2e057d0.1701262123.git.vinayak.yadawad@broadcom.com
[drop whitespace-damaged rdev_ops pointer completely, enabling tracing]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/uapi/linux/nl80211.h |  3 +-
 net/wireless/nl80211.c       | 94 +++++++++++++++++++++++++++++++-------------
 2 files changed, 69 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 0cd1da2c2902..8f42d598e285 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -568,7 +568,8 @@
  * @NL80211_CMD_DEL_PMKSA: Delete a PMKSA cache entry, using %NL80211_ATTR_MAC
  *	(for the BSSID) and %NL80211_ATTR_PMKID or using %NL80211_ATTR_SSID,
  *	%NL80211_ATTR_FILS_CACHE_ID, and %NL80211_ATTR_PMKID in case of FILS
- *	authentication.
+ *	authentication. Additionally in case of SAE offload and OWE offloads
+ *	PMKSA entry can be deleted using %NL80211_ATTR_SSID.
  * @NL80211_CMD_FLUSH_PMKSA: Flush all PMKSA cache entries.
  *
  * @NL80211_CMD_REG_CHANGE: indicates to userspace the regulatory domain
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 403a4a38966a..d6a20c21f094 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -12174,16 +12174,18 @@ static int nl80211_wiphy_netns(struct sk_buff *skb, struct genl_info *info)
 	return err;
 }
 
-static int nl80211_setdel_pmksa(struct sk_buff *skb, struct genl_info *info)
+static int nl80211_set_pmksa(struct sk_buff *skb, struct genl_info *info)
 {
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
-	int (*rdev_ops)(struct wiphy *wiphy, struct net_device *dev,
-			struct cfg80211_pmksa *pmksa) = NULL;
 	struct net_device *dev = info->user_ptr[1];
 	struct cfg80211_pmksa pmksa;
+	bool ap_pmksa_caching_support = false;
 
 	memset(&pmksa, 0, sizeof(struct cfg80211_pmksa));
 
+	ap_pmksa_caching_support = wiphy_ext_feature_isset(&rdev->wiphy,
+		NL80211_EXT_FEATURE_AP_PMKSA_CACHING);
+
 	if (!info->attrs[NL80211_ATTR_PMKID])
 		return -EINVAL;
 
@@ -12192,16 +12194,15 @@ static int nl80211_setdel_pmksa(struct sk_buff *skb, struct genl_info *info)
 	if (info->attrs[NL80211_ATTR_MAC]) {
 		pmksa.bssid = nla_data(info->attrs[NL80211_ATTR_MAC]);
 	} else if (info->attrs[NL80211_ATTR_SSID] &&
-		   info->attrs[NL80211_ATTR_FILS_CACHE_ID] &&
-		   (info->genlhdr->cmd == NL80211_CMD_DEL_PMKSA ||
-		    info->attrs[NL80211_ATTR_PMK])) {
+	           info->attrs[NL80211_ATTR_FILS_CACHE_ID] &&
+	           info->attrs[NL80211_ATTR_PMK]) {
 		pmksa.ssid = nla_data(info->attrs[NL80211_ATTR_SSID]);
 		pmksa.ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]);
-		pmksa.cache_id =
-			nla_data(info->attrs[NL80211_ATTR_FILS_CACHE_ID]);
+		pmksa.cache_id = nla_data(info->attrs[NL80211_ATTR_FILS_CACHE_ID]);
 	} else {
 		return -EINVAL;
 	}
+
 	if (info->attrs[NL80211_ATTR_PMK]) {
 		pmksa.pmk = nla_data(info->attrs[NL80211_ATTR_PMK]);
 		pmksa.pmk_len = nla_len(info->attrs[NL80211_ATTR_PMK]);
@@ -12213,32 +12214,71 @@ static int nl80211_setdel_pmksa(struct sk_buff *skb, struct genl_info *info)
 
 	if (info->attrs[NL80211_ATTR_PMK_REAUTH_THRESHOLD])
 		pmksa.pmk_reauth_threshold =
-			nla_get_u8(
-				info->attrs[NL80211_ATTR_PMK_REAUTH_THRESHOLD]);
+			nla_get_u8(info->attrs[NL80211_ATTR_PMK_REAUTH_THRESHOLD]);
 
 	if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION &&
 	    dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_CLIENT &&
-	    !(dev->ieee80211_ptr->iftype == NL80211_IFTYPE_AP &&
-	      wiphy_ext_feature_isset(&rdev->wiphy,
-				      NL80211_EXT_FEATURE_AP_PMKSA_CACHING)))
+	    !((dev->ieee80211_ptr->iftype == NL80211_IFTYPE_AP ||
+	       dev->ieee80211_ptr->iftype == NL80211_IFTYPE_P2P_GO) &&
+	       ap_pmksa_caching_support))
 		return -EOPNOTSUPP;
 
-	switch (info->genlhdr->cmd) {
-	case NL80211_CMD_SET_PMKSA:
-		rdev_ops = rdev->ops->set_pmksa;
-		break;
-	case NL80211_CMD_DEL_PMKSA:
-		rdev_ops = rdev->ops->del_pmksa;
-		break;
-	default:
-		WARN_ON(1);
-		break;
+	if (!rdev->ops->set_pmksa)
+		return -EOPNOTSUPP;
+
+	return rdev_set_pmksa(rdev, dev, &pmksa);
+}
+
+static int nl80211_del_pmksa(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg80211_registered_device *rdev = info->user_ptr[0];
+	struct net_device *dev = info->user_ptr[1];
+	struct cfg80211_pmksa pmksa;
+	bool sae_offload_support = false;
+	bool owe_offload_support = false;
+	bool ap_pmksa_caching_support = false;
+
+	memset(&pmksa, 0, sizeof(struct cfg80211_pmksa));
+
+	sae_offload_support = wiphy_ext_feature_isset(&rdev->wiphy,
+		NL80211_EXT_FEATURE_SAE_OFFLOAD);
+	owe_offload_support = wiphy_ext_feature_isset(&rdev->wiphy,
+		NL80211_EXT_FEATURE_OWE_OFFLOAD);
+	ap_pmksa_caching_support = wiphy_ext_feature_isset(&rdev->wiphy,
+		NL80211_EXT_FEATURE_AP_PMKSA_CACHING);
+
+	if (info->attrs[NL80211_ATTR_PMKID])
+		pmksa.pmkid = nla_data(info->attrs[NL80211_ATTR_PMKID]);
+
+	if (info->attrs[NL80211_ATTR_MAC]) {
+		pmksa.bssid = nla_data(info->attrs[NL80211_ATTR_MAC]);
+	} else if (info->attrs[NL80211_ATTR_SSID]) {
+		/* SSID based pmksa flush suppported only for FILS,
+		 * OWE/SAE OFFLOAD cases
+		 */
+		if (info->attrs[NL80211_ATTR_FILS_CACHE_ID] &&
+		    info->attrs[NL80211_ATTR_PMK]) {
+			pmksa.cache_id = nla_data(info->attrs[NL80211_ATTR_FILS_CACHE_ID]);
+		} else if (!sae_offload_support && !owe_offload_support) {
+			return -EINVAL;
+		}
+		pmksa.ssid = nla_data(info->attrs[NL80211_ATTR_SSID]);
+		pmksa.ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]);
+	} else {
+		return -EINVAL;
 	}
 
-	if (!rdev_ops)
+	if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION &&
+	    dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_CLIENT &&
+	    !((dev->ieee80211_ptr->iftype == NL80211_IFTYPE_AP ||
+	       dev->ieee80211_ptr->iftype == NL80211_IFTYPE_P2P_GO) &&
+	       ap_pmksa_caching_support))
+		return -EOPNOTSUPP;
+
+	if (!rdev->ops->del_pmksa)
 		return -EOPNOTSUPP;
 
-	return rdev_ops(&rdev->wiphy, dev, &pmksa);
+	return rdev_del_pmksa(rdev, dev, &pmksa);
 }
 
 static int nl80211_flush_pmksa(struct sk_buff *skb, struct genl_info *info)
@@ -16912,7 +16952,7 @@ static const struct genl_small_ops nl80211_small_ops[] = {
 	{
 		.cmd = NL80211_CMD_SET_PMKSA,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = nl80211_setdel_pmksa,
+		.doit = nl80211_set_pmksa,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP |
 					 NL80211_FLAG_CLEAR_SKB),
@@ -16920,7 +16960,7 @@ static const struct genl_small_ops nl80211_small_ops[] = {
 	{
 		.cmd = NL80211_CMD_DEL_PMKSA,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = nl80211_setdel_pmksa,
+		.doit = nl80211_del_pmksa,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP),
 	},
-- 
cgit v1.2.3


From d02a12b8e4bbd188f38321849791af02d494c7fd Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 11 Dec 2023 09:05:20 +0200
Subject: wifi: cfg80211: add BSS usage reporting

Sometimes there may be reasons for which a BSS that's
actually found in scan cannot be used to connect to,
for example a nonprimary link of an NSTR mobile AP MLD
cannot be used for normal direct connections to it.

Not indicating these to userspace as we do now of course
avoids being able to connect to them, but it's better if
they're shown to userspace and it can make an appropriate
decision, without e.g. doing an additional ML probe.

Thus add an indication of what a BSS can be used for,
currently "normal" and "MLD link", including a reason
bitmap for it being not usable.

The latter can be extended later for certain BSSes if there
are other reasons they cannot be used.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Ilan Peer <ilan.peer@intel.com>
Reviewed-by: Gregory Greenman <gregory.greenman@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20231211085121.0464f25e0b1d.I9f70ca9f1440565ad9a5207d0f4d00a20cca67e7@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       | 60 +++++++++++++++++++++++++++++++-----
 include/uapi/linux/nl80211.h | 40 ++++++++++++++++++++++++
 net/wireless/core.h          |  3 ++
 net/wireless/nl80211.c       | 54 ++++++++++++++++++++++++++------
 net/wireless/scan.c          | 73 +++++++++++++++++++++++++++++++++-----------
 5 files changed, 195 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 324a5f710ad3..cabe57a00eaf 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -2828,6 +2828,13 @@ enum cfg80211_signal_type {
  *	the BSS that requested the scan in which the beacon/probe was received.
  * @chains: bitmask for filled values in @chain_signal.
  * @chain_signal: per-chain signal strength of last received BSS in dBm.
+ * @restrict_use: restrict usage, if not set, assume @use_for is
+ *	%NL80211_BSS_USE_FOR_NORMAL.
+ * @use_for: bitmap of possible usage for this BSS, see
+ *	&enum nl80211_bss_use_for
+ * @cannot_use_reasons: the reasons (bitmap) for not being able to connect,
+ *	if @restrict_use is set and @use_for is zero (empty); may be 0 for
+ *	unspecified reasons; see &enum nl80211_bss_cannot_use_reasons
  * @drv_data: Data to be passed through to @inform_bss
  */
 struct cfg80211_inform_bss {
@@ -2839,6 +2846,9 @@ struct cfg80211_inform_bss {
 	u8 chains;
 	s8 chain_signal[IEEE80211_MAX_CHAINS];
 
+	u8 restrict_use:1, use_for:7;
+	u8 cannot_use_reasons;
+
 	void *drv_data;
 };
 
@@ -2890,6 +2900,11 @@ struct cfg80211_bss_ies {
  * @chain_signal: per-chain signal strength of last received BSS in dBm.
  * @bssid_index: index in the multiple BSS set
  * @max_bssid_indicator: max number of members in the BSS set
+ * @use_for: bitmap of possible usage for this BSS, see
+ *	&enum nl80211_bss_use_for
+ * @cannot_use_reasons: the reasons (bitmap) for not being able to connect,
+ *	if @restrict_use is set and @use_for is zero (empty); may be 0 for
+ *	unspecified reasons; see &enum nl80211_bss_cannot_use_reasons
  * @priv: private area for driver use, has at least wiphy->bss_priv_size bytes
  */
 struct cfg80211_bss {
@@ -2915,6 +2930,9 @@ struct cfg80211_bss {
 	u8 bssid_index;
 	u8 max_bssid_indicator;
 
+	u8 use_for;
+	u8 cannot_use_reasons;
+
 	u8 priv[] __aligned(sizeof(void *));
 };
 
@@ -4922,6 +4940,8 @@ struct cfg80211_ops {
  *	NL80211_REGDOM_SET_BY_DRIVER.
  * @WIPHY_FLAG_CHANNEL_CHANGE_ON_BEACON: reg_call_notifier() is called if driver
  *	set this flag to update channels on beacon hints.
+ * @WIPHY_FLAG_SUPPORTS_NSTR_NONPRIMARY: support connection to non-primary link
+ *	of an NSTR mobile AP MLD.
  */
 enum wiphy_flags {
 	WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK		= BIT(0),
@@ -4935,7 +4955,7 @@ enum wiphy_flags {
 	WIPHY_FLAG_IBSS_RSN			= BIT(8),
 	WIPHY_FLAG_MESH_AUTH			= BIT(10),
 	WIPHY_FLAG_SUPPORTS_EXT_KCK_32          = BIT(11),
-	/* use hole at 12 */
+	WIPHY_FLAG_SUPPORTS_NSTR_NONPRIMARY	= BIT(12),
 	WIPHY_FLAG_SUPPORTS_FW_ROAM		= BIT(13),
 	WIPHY_FLAG_AP_UAPSD			= BIT(14),
 	WIPHY_FLAG_SUPPORTS_TDLS		= BIT(15),
@@ -7173,6 +7193,25 @@ cfg80211_inform_bss(struct wiphy *wiphy,
 					gfp);
 }
 
+/**
+ * __cfg80211_get_bss - get a BSS reference
+ * @wiphy: the wiphy this BSS struct belongs to
+ * @channel: the channel to search on (or %NULL)
+ * @bssid: the desired BSSID (or %NULL)
+ * @ssid: the desired SSID (or %NULL)
+ * @ssid_len: length of the SSID (or 0)
+ * @bss_type: type of BSS, see &enum ieee80211_bss_type
+ * @privacy: privacy filter, see &enum ieee80211_privacy
+ * @use_for: indicates which use is intended
+ */
+struct cfg80211_bss *__cfg80211_get_bss(struct wiphy *wiphy,
+					struct ieee80211_channel *channel,
+					const u8 *bssid,
+					const u8 *ssid, size_t ssid_len,
+					enum ieee80211_bss_type bss_type,
+					enum ieee80211_privacy privacy,
+					u32 use_for);
+
 /**
  * cfg80211_get_bss - get a BSS reference
  * @wiphy: the wiphy this BSS struct belongs to
@@ -7182,13 +7221,20 @@ cfg80211_inform_bss(struct wiphy *wiphy,
  * @ssid_len: length of the SSID (or 0)
  * @bss_type: type of BSS, see &enum ieee80211_bss_type
  * @privacy: privacy filter, see &enum ieee80211_privacy
+ *
+ * This version implies regular usage, %NL80211_BSS_USE_FOR_NORMAL.
  */
-struct cfg80211_bss *cfg80211_get_bss(struct wiphy *wiphy,
-				      struct ieee80211_channel *channel,
-				      const u8 *bssid,
-				      const u8 *ssid, size_t ssid_len,
-				      enum ieee80211_bss_type bss_type,
-				      enum ieee80211_privacy privacy);
+static inline struct cfg80211_bss *
+cfg80211_get_bss(struct wiphy *wiphy, struct ieee80211_channel *channel,
+		 const u8 *bssid, const u8 *ssid, size_t ssid_len,
+		 enum ieee80211_bss_type bss_type,
+		 enum ieee80211_privacy privacy)
+{
+	return __cfg80211_get_bss(wiphy, channel, bssid, ssid, ssid_len,
+				  bss_type, privacy,
+				  NL80211_BSS_USE_FOR_NORMAL);
+}
+
 static inline struct cfg80211_bss *
 cfg80211_get_ibss(struct wiphy *wiphy,
 		  struct ieee80211_channel *channel,
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 8f42d598e285..07fc1fec4b12 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -2831,6 +2831,10 @@ enum nl80211_commands {
  * @NL80211_ATTR_MLO_LINK_DISABLED: Flag attribute indicating that the link is
  *	disabled.
  *
+ * @NL80211_ATTR_BSS_DUMP_INCLUDE_USE_DATA: Include BSS usage data, i.e.
+ *	include BSSes that can only be used in restricted scenarios and/or
+ *	cannot be used at all.
+ *
  * @NUM_NL80211_ATTR: total number of nl80211_attrs available
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
@@ -3369,6 +3373,8 @@ enum nl80211_attrs {
 
 	NL80211_ATTR_MLO_LINK_DISABLED,
 
+	NL80211_ATTR_BSS_DUMP_INCLUDE_USE_DATA,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
@@ -5032,6 +5038,30 @@ enum nl80211_bss_scan_width {
 	NL80211_BSS_CHAN_WIDTH_2,
 };
 
+/**
+ * enum nl80211_bss_use_for - bitmap indicating possible BSS use
+ * @NL80211_BSS_USE_FOR_NORMAL: Use this BSS for normal "connection",
+ *	including IBSS/MBSS depending on the type.
+ * @NL80211_BSS_USE_FOR_MLD_LINK: This BSS can be used as a link in an
+ *	MLO connection. Note that for an MLO connection, all links including
+ *	the assoc link must have this flag set, and the assoc link must
+ *	additionally have %NL80211_BSS_USE_FOR_NORMAL set.
+ */
+enum nl80211_bss_use_for {
+	NL80211_BSS_USE_FOR_NORMAL = 1 << 0,
+	NL80211_BSS_USE_FOR_MLD_LINK = 1 << 1,
+};
+
+/**
+ * enum nl80211_bss_cannot_use_reasons - reason(s) connection to a
+ *	BSS isn't possible
+ * @NL80211_BSS_CANNOT_USE_NSTR_NONPRIMARY: NSTR nonprimary links aren't
+ *	supported by the device, and this BSS entry represents one.
+ */
+enum nl80211_bss_cannot_use_reasons {
+	NL80211_BSS_CANNOT_USE_NSTR_NONPRIMARY	= 1 << 0,
+};
+
 /**
  * enum nl80211_bss - netlink attributes for a BSS
  *
@@ -5084,6 +5114,14 @@ enum nl80211_bss_scan_width {
  * @NL80211_BSS_FREQUENCY_OFFSET: frequency offset in KHz
  * @NL80211_BSS_MLO_LINK_ID: MLO link ID of the BSS (u8).
  * @NL80211_BSS_MLD_ADDR: MLD address of this BSS if connected to it.
+ * @NL80211_BSS_USE_FOR: u32 bitmap attribute indicating what the BSS can be
+ *	used for, see &enum nl80211_bss_use_for.
+ * @NL80211_BSS_CANNOT_USE_REASONS: Indicates the reason that this BSS cannot
+ *	be used for all or some of the possible uses by the device reporting it,
+ *	even though its presence was detected.
+ *	This is a u64 attribute containing a bitmap of values from
+ *	&enum nl80211_cannot_use_reasons, note that the attribute may be missing
+ *	if no reasons are specified.
  * @__NL80211_BSS_AFTER_LAST: internal
  * @NL80211_BSS_MAX: highest BSS attribute
  */
@@ -5111,6 +5149,8 @@ enum nl80211_bss {
 	NL80211_BSS_FREQUENCY_OFFSET,
 	NL80211_BSS_MLO_LINK_ID,
 	NL80211_BSS_MLD_ADDR,
+	NL80211_BSS_USE_FOR,
+	NL80211_BSS_CANNOT_USE_REASONS,
 
 	/* keep last */
 	__NL80211_BSS_AFTER_LAST,
diff --git a/net/wireless/core.h b/net/wireless/core.h
index 4c692c7faf30..87c5889b15e3 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -457,6 +457,9 @@ int cfg80211_scan(struct cfg80211_registered_device *rdev);
 
 extern struct work_struct cfg80211_disconnect_work;
 
+#define NL80211_BSS_USE_FOR_ALL	(NL80211_BSS_USE_FOR_NORMAL | \
+				 NL80211_BSS_USE_FOR_MLD_LINK)
+
 void cfg80211_set_dfs_state(struct wiphy *wiphy,
 			    const struct cfg80211_chan_def *chandef,
 			    enum nl80211_dfs_state dfs_state);
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index d6a20c21f094..2820336511a2 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -818,6 +818,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 	[NL80211_ATTR_HW_TIMESTAMP_ENABLED] = { .type = NLA_FLAG },
 	[NL80211_ATTR_EMA_RNR_ELEMS] = { .type = NLA_NESTED },
 	[NL80211_ATTR_MLO_LINK_DISABLED] = { .type = NLA_FLAG },
+	[NL80211_ATTR_BSS_DUMP_INCLUDE_USE_DATA] = { .type = NLA_FLAG },
 };
 
 /* policy for the key attributes */
@@ -10405,6 +10406,15 @@ static int nl80211_send_bss(struct sk_buff *msg, struct netlink_callback *cb,
 		break;
 	}
 
+	if (nla_put_u32(msg, NL80211_BSS_USE_FOR, res->use_for))
+		goto nla_put_failure;
+
+	if (res->cannot_use_reasons &&
+	    nla_put_u64_64bit(msg, NL80211_BSS_CANNOT_USE_REASONS,
+			      res->cannot_use_reasons,
+			      NL80211_BSS_PAD))
+		goto nla_put_failure;
+
 	nla_nest_end(msg, bss);
 
 	genlmsg_end(msg, hdr);
@@ -10422,15 +10432,27 @@ static int nl80211_dump_scan(struct sk_buff *skb, struct netlink_callback *cb)
 	struct cfg80211_registered_device *rdev;
 	struct cfg80211_internal_bss *scan;
 	struct wireless_dev *wdev;
+	struct nlattr **attrbuf;
 	int start = cb->args[2], idx = 0;
+	bool dump_include_use_data;
 	int err;
 
-	err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev, NULL);
-	if (err)
+	attrbuf = kcalloc(NUM_NL80211_ATTR, sizeof(*attrbuf), GFP_KERNEL);
+	if (!attrbuf)
+		return -ENOMEM;
+
+	err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev, attrbuf);
+	if (err) {
+		kfree(attrbuf);
 		return err;
+	}
 	/* nl80211_prepare_wdev_dump acquired it in the successful case */
 	__acquire(&rdev->wiphy.mtx);
 
+	dump_include_use_data =
+		attrbuf[NL80211_ATTR_BSS_DUMP_INCLUDE_USE_DATA];
+	kfree(attrbuf);
+
 	spin_lock_bh(&rdev->bss_lock);
 
 	/*
@@ -10447,6 +10469,9 @@ static int nl80211_dump_scan(struct sk_buff *skb, struct netlink_callback *cb)
 	list_for_each_entry(scan, &rdev->bss_list, list) {
 		if (++idx <= start)
 			continue;
+		if (!dump_include_use_data &&
+		    !(scan->pub.use_for & NL80211_BSS_USE_FOR_NORMAL))
+			continue;
 		if (nl80211_send_bss(skb, cb,
 				cb->nlh->nlmsg_seq, NLM_F_MULTI,
 				rdev, wdev, scan) < 0) {
@@ -10898,12 +10923,13 @@ static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev,
 
 static struct cfg80211_bss *nl80211_assoc_bss(struct cfg80211_registered_device *rdev,
 					      const u8 *ssid, int ssid_len,
-					      struct nlattr **attrs)
+					      struct nlattr **attrs,
+					      int assoc_link_id, int link_id)
 {
 	struct ieee80211_channel *chan;
 	struct cfg80211_bss *bss;
 	const u8 *bssid;
-	u32 freq;
+	u32 freq, use_for = 0;
 
 	if (!attrs[NL80211_ATTR_MAC] || !attrs[NL80211_ATTR_WIPHY_FREQ])
 		return ERR_PTR(-EINVAL);
@@ -10918,10 +10944,16 @@ static struct cfg80211_bss *nl80211_assoc_bss(struct cfg80211_registered_device
 	if (!chan)
 		return ERR_PTR(-EINVAL);
 
-	bss = cfg80211_get_bss(&rdev->wiphy, chan, bssid,
-			       ssid, ssid_len,
-			       IEEE80211_BSS_TYPE_ESS,
-			       IEEE80211_PRIVACY_ANY);
+	if (assoc_link_id >= 0)
+		use_for = NL80211_BSS_USE_FOR_MLD_LINK;
+	if (assoc_link_id == link_id)
+		use_for |= NL80211_BSS_USE_FOR_NORMAL;
+
+	bss = __cfg80211_get_bss(&rdev->wiphy, chan, bssid,
+				 ssid, ssid_len,
+				 IEEE80211_BSS_TYPE_ESS,
+				 IEEE80211_PRIVACY_ANY,
+				 use_for);
 	if (!bss)
 		return ERR_PTR(-ENOENT);
 
@@ -11100,7 +11132,8 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info)
 				goto free;
 			}
 			req.links[link_id].bss =
-				nl80211_assoc_bss(rdev, ssid, ssid_len, attrs);
+				nl80211_assoc_bss(rdev, ssid, ssid_len, attrs,
+						  req.link_id, link_id);
 			if (IS_ERR(req.links[link_id].bss)) {
 				err = PTR_ERR(req.links[link_id].bss);
 				req.links[link_id].bss = NULL;
@@ -11165,7 +11198,8 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info)
 		if (req.link_id >= 0)
 			return -EINVAL;
 
-		req.bss = nl80211_assoc_bss(rdev, ssid, ssid_len, info->attrs);
+		req.bss = nl80211_assoc_bss(rdev, ssid, ssid_len, info->attrs,
+					    -1, -1);
 		if (IS_ERR(req.bss))
 			return PTR_ERR(req.bss);
 		ap_addr = req.bss->bssid;
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 9e5ccffd6868..2f8c9b6f7ebc 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -1535,12 +1535,13 @@ static bool cfg80211_bss_type_match(u16 capability,
 }
 
 /* Returned bss is reference counted and must be cleaned up appropriately. */
-struct cfg80211_bss *cfg80211_get_bss(struct wiphy *wiphy,
-				      struct ieee80211_channel *channel,
-				      const u8 *bssid,
-				      const u8 *ssid, size_t ssid_len,
-				      enum ieee80211_bss_type bss_type,
-				      enum ieee80211_privacy privacy)
+struct cfg80211_bss *__cfg80211_get_bss(struct wiphy *wiphy,
+					struct ieee80211_channel *channel,
+					const u8 *bssid,
+					const u8 *ssid, size_t ssid_len,
+					enum ieee80211_bss_type bss_type,
+					enum ieee80211_privacy privacy,
+					u32 use_for)
 {
 	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct cfg80211_internal_bss *bss, *res = NULL;
@@ -1565,6 +1566,8 @@ struct cfg80211_bss *cfg80211_get_bss(struct wiphy *wiphy,
 			continue;
 		if (!is_valid_ether_addr(bss->pub.bssid))
 			continue;
+		if ((bss->pub.use_for & use_for) != use_for)
+			continue;
 		/* Don't get expired BSS structs */
 		if (time_after(now, bss->ts + IEEE80211_SCAN_RESULT_EXPIRE) &&
 		    !atomic_read(&bss->hold))
@@ -1582,7 +1585,7 @@ struct cfg80211_bss *cfg80211_get_bss(struct wiphy *wiphy,
 	trace_cfg80211_return_bss(&res->pub);
 	return &res->pub;
 }
-EXPORT_SYMBOL(cfg80211_get_bss);
+EXPORT_SYMBOL(__cfg80211_get_bss);
 
 static void rb_insert_bss(struct cfg80211_registered_device *rdev,
 			  struct cfg80211_internal_bss *bss)
@@ -1800,6 +1803,8 @@ cfg80211_update_known_bss(struct cfg80211_registered_device *rdev,
 	ether_addr_copy(known->parent_bssid, new->parent_bssid);
 	known->pub.max_bssid_indicator = new->pub.max_bssid_indicator;
 	known->pub.bssid_index = new->pub.bssid_index;
+	known->pub.use_for &= new->pub.use_for;
+	known->pub.cannot_use_reasons = new->pub.cannot_use_reasons;
 
 	return true;
 }
@@ -2044,6 +2049,9 @@ struct cfg80211_inform_single_bss_data {
 	struct cfg80211_bss *source_bss;
 	u8 max_bssid_indicator;
 	u8 bssid_index;
+
+	u8 use_for;
+	u64 cannot_use_reasons;
 };
 
 /* Returned bss is reference counted and must be cleaned up appropriately. */
@@ -2089,6 +2097,8 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy,
 	tmp.ts_boottime = drv_data->boottime_ns;
 	tmp.parent_tsf = drv_data->parent_tsf;
 	ether_addr_copy(tmp.parent_bssid, drv_data->parent_bssid);
+	tmp.pub.use_for = data->use_for;
+	tmp.pub.cannot_use_reasons = data->cannot_use_reasons;
 
 	if (data->bss_source != BSS_SOURCE_DIRECT) {
 		tmp.pub.transmitted_bss = data->source_bss;
@@ -2259,6 +2269,8 @@ cfg80211_parse_mbssid_data(struct wiphy *wiphy,
 		.beacon_interval = tx_data->beacon_interval,
 		.source_bss = source_bss,
 		.bss_source = BSS_SOURCE_MBSSID,
+		.use_for = tx_data->use_for,
+		.cannot_use_reasons = tx_data->cannot_use_reasons,
 	};
 	const u8 *mbssid_index_ie;
 	const struct element *elem, *sub;
@@ -2521,7 +2533,7 @@ error:
 	return NULL;
 }
 
-static bool
+static u8
 cfg80211_tbtt_info_for_mld_ap(const u8 *ie, size_t ielen, u8 mld_id, u8 link_id,
 			      const struct ieee80211_neighbor_ap_info **ap_info,
 			      const u8 **tbtt_info)
@@ -2540,6 +2552,7 @@ cfg80211_tbtt_info_for_mld_ap(const u8 *ie, size_t ielen, u8 mld_id, u8 link_id,
 			u16 params;
 			u8 length, i, count, mld_params_offset;
 			u8 type, lid;
+			u32 use_for;
 
 			info = (void *)pos;
 			count = u8_get_bits(info->tbtt_info_hdr,
@@ -2549,20 +2562,22 @@ cfg80211_tbtt_info_for_mld_ap(const u8 *ie, size_t ielen, u8 mld_id, u8 link_id,
 			pos += sizeof(*info);
 
 			if (count * length > end - pos)
-				return false;
+				return 0;
 
 			type = u8_get_bits(info->tbtt_info_hdr,
 					   IEEE80211_AP_INFO_TBTT_HDR_TYPE);
 
-			/* Only accept full TBTT information. NSTR mobile APs
-			 * use the shortened version, but we ignore them here.
-			 */
 			if (type == IEEE80211_TBTT_INFO_TYPE_TBTT &&
 			    length >=
 			    offsetofend(struct ieee80211_tbtt_info_ge_11,
 					mld_params)) {
 				mld_params_offset =
 					offsetof(struct ieee80211_tbtt_info_ge_11, mld_params);
+				use_for = NL80211_BSS_USE_FOR_ALL;
+			} else if (type == IEEE80211_TBTT_INFO_TYPE_MLD &&
+				   length >= sizeof(struct ieee80211_rnr_mld_params)) {
+				mld_params_offset = 0;
+				use_for = NL80211_BSS_USE_FOR_MLD_LINK;
 			} else {
 				pos += count * length;
 				continue;
@@ -2580,7 +2595,7 @@ cfg80211_tbtt_info_for_mld_ap(const u8 *ie, size_t ielen, u8 mld_id, u8 link_id,
 					*ap_info = info;
 					*tbtt_info = pos;
 
-					return true;
+					return use_for;
 				}
 
 				pos += length;
@@ -2588,7 +2603,7 @@ cfg80211_tbtt_info_for_mld_ap(const u8 *ie, size_t ielen, u8 mld_id, u8 link_id,
 		}
 	}
 
-	return false;
+	return 0;
 }
 
 static void cfg80211_parse_ml_sta_data(struct wiphy *wiphy,
@@ -2676,7 +2691,7 @@ static void cfg80211_parse_ml_sta_data(struct wiphy *wiphy,
 		const u8 *profile;
 		const u8 *tbtt_info;
 		ssize_t profile_len;
-		u8 link_id;
+		u8 link_id, use_for;
 
 		if (!ieee80211_mle_basic_sta_prof_size_ok((u8 *)mle->sta_prof[i],
 							  mle->sta_prof_len[i]))
@@ -2718,9 +2733,11 @@ static void cfg80211_parse_ml_sta_data(struct wiphy *wiphy,
 		profile_len -= 2;
 
 		/* Find in RNR to look up channel information */
-		if (!cfg80211_tbtt_info_for_mld_ap(tx_data->ie, tx_data->ielen,
-						   mld_id, link_id,
-						   &ap_info, &tbtt_info))
+		use_for = cfg80211_tbtt_info_for_mld_ap(tx_data->ie,
+							tx_data->ielen,
+							mld_id, link_id,
+							&ap_info, &tbtt_info);
+		if (!use_for)
 			continue;
 
 		/* We could sanity check the BSSID is included */
@@ -2732,6 +2749,14 @@ static void cfg80211_parse_ml_sta_data(struct wiphy *wiphy,
 		freq = ieee80211_channel_to_freq_khz(ap_info->channel, band);
 		data.channel = ieee80211_get_channel_khz(wiphy, freq);
 
+		if (use_for == NL80211_BSS_USE_FOR_MLD_LINK &&
+		    !(wiphy->flags & WIPHY_FLAG_SUPPORTS_NSTR_NONPRIMARY)) {
+			use_for = 0;
+			data.cannot_use_reasons =
+				NL80211_BSS_CANNOT_USE_NSTR_NONPRIMARY;
+		}
+		data.use_for = use_for;
+
 		/* Generate new elements */
 		memset(new_ie, 0, IEEE80211_MAX_DATA_LEN);
 		data.ie = new_ie;
@@ -2769,6 +2794,10 @@ cfg80211_inform_bss_data(struct wiphy *wiphy,
 		.beacon_interval = beacon_interval,
 		.ie = ie,
 		.ielen = ielen,
+		.use_for = data->restrict_use ?
+				data->use_for :
+				NL80211_BSS_USE_FOR_ALL,
+		.cannot_use_reasons = data->cannot_use_reasons,
 	};
 	struct cfg80211_bss *res;
 
@@ -2899,6 +2928,10 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy,
 	tmp.pub.chains = data->chains;
 	memcpy(tmp.pub.chain_signal, data->chain_signal, IEEE80211_MAX_CHAINS);
 	ether_addr_copy(tmp.parent_bssid, data->parent_bssid);
+	tmp.pub.use_for = data->restrict_use ?
+				data->use_for :
+				NL80211_BSS_USE_FOR_ALL;
+	tmp.pub.cannot_use_reasons = data->cannot_use_reasons;
 
 	signal_valid = data->chan == channel;
 	spin_lock_bh(&rdev->bss_lock);
@@ -2930,6 +2963,10 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy,
 		.ie = mgmt->u.probe_resp.variable,
 		.ielen = len - offsetof(struct ieee80211_mgmt,
 					u.probe_resp.variable),
+		.use_for = data->restrict_use ?
+				data->use_for :
+				NL80211_BSS_USE_FOR_ALL,
+		.cannot_use_reasons = data->cannot_use_reasons,
 	};
 	struct cfg80211_bss *res;
 
-- 
cgit v1.2.3


From 9adc8b65218f70cbf50151fc6c2c40949e29eb4f Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 11 Dec 2023 09:05:21 +0200
Subject: wifi: mac80211: update some locking documentation

With the locking rework, more functions need to be called
with the wiphy mutex held. Document that, and for that use
the "Context" description that shows up more nicely in the
generated documentation.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Gregory Greenman <gregory.greenman@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20231211085121.24fa44c7eeb4.I8c9e030ddd78e07c99dd21fe1d5156555390f92e@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h | 19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 580781ff9dcf..aa8e1055fc3a 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -5809,12 +5809,11 @@ void ieee80211_set_key_rx_seq(struct ieee80211_key_conf *keyconf,
  * ieee80211_remove_key - remove the given key
  * @keyconf: the parameter passed with the set key
  *
+ * Context: Must be called with the wiphy mutex held.
+ *
  * Remove the given key. If the key was uploaded to the hardware at the
  * time this function is called, it is not deleted in the hardware but
  * instead assumed to have been removed already.
- *
- * Note that due to locking considerations this function can (currently)
- * only be called during key iteration (ieee80211_iter_keys().)
  */
 void ieee80211_remove_key(struct ieee80211_key_conf *keyconf);
 
@@ -6368,12 +6367,12 @@ ieee80211_txq_airtime_check(struct ieee80211_hw *hw, struct ieee80211_txq *txq);
  * @iter: iterator function that will be called for each key
  * @iter_data: custom data to pass to the iterator function
  *
+ * Context: Must be called with wiphy mutex held; can sleep.
+ *
  * This function can be used to iterate all the keys known to
  * mac80211, even those that weren't previously programmed into
  * the device. This is intended for use in WoWLAN if the device
- * needs reprogramming of the keys during suspend. Note that due
- * to locking reasons, it is also only safe to call this at few
- * spots since it must hold the RTNL and be able to sleep.
+ * needs reprogramming of the keys during suspend.
  *
  * The order in which the keys are iterated matches the order
  * in which they were originally installed and handed to the
@@ -7435,6 +7434,9 @@ static inline bool ieee80211_is_tx_data(struct sk_buff *skb)
  * @vif: interface to set active links on
  * @active_links: the new active links bitmap
  *
+ * Context: Must be called with wiphy mutex held; may sleep; calls
+ *	back into the driver.
+ *
  * This changes the active links on an interface. The interface
  * must be in client mode (in AP mode, all links are always active),
  * and @active_links must be a subset of the vif's valid_links.
@@ -7442,6 +7444,7 @@ static inline bool ieee80211_is_tx_data(struct sk_buff *skb)
  * If a link is switched off and another is switched on at the same
  * time (e.g. active_links going from 0x1 to 0x10) then you will get
  * a sequence of calls like
+ *
  *  - change_vif_links(0x11)
  *  - unassign_vif_chanctx(link_id=0)
  *  - change_sta_links(0x11) for each affected STA (the AP)
@@ -7451,10 +7454,6 @@ static inline bool ieee80211_is_tx_data(struct sk_buff *skb)
  *  - change_sta_links(0x10) for each affected STA (the AP)
  *  - assign_vif_chanctx(link_id=4)
  *  - change_vif_links(0x10)
- *
- * Note: This function acquires some mac80211 locks and must not
- *	 be called with any driver locks held that could cause a
- *	 lock dependency inversion. Best call it without locks.
  */
 int ieee80211_set_active_links(struct ieee80211_vif *vif, u16 active_links);
 
-- 
cgit v1.2.3


From b61e6b41a2f6818ee7b8f92f670a8a6ebcd25a71 Mon Sep 17 00:00:00 2001
From: Ilan Peer <ilan.peer@intel.com>
Date: Mon, 11 Dec 2023 09:05:22 +0200
Subject: wifi: cfg80211: Add support for setting TID to link mapping

Add support for setting the TID to link mapping for a non-AP MLD
station.

This is useful in cases user space needs to restrict the possible
set of active links, e.g., since it got a BSS Transition Management
request forcing to use only a subset of the valid links etc.

Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Reviewed-by: Gregory Greenman <gregory.greenman@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20231211085121.da4d56a5f3ff.Iacf88e943326bf9c169c49b728c4a3445fdedc97@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       | 18 ++++++++++++++++++
 include/uapi/linux/nl80211.h | 19 +++++++++++++++++++
 net/wireless/nl80211.c       | 37 +++++++++++++++++++++++++++++++++++++
 net/wireless/rdev-ops.h      | 18 ++++++++++++++++++
 net/wireless/trace.h         | 20 ++++++++++++++++++++
 5 files changed, 112 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index cabe57a00eaf..4d6b9d801c2f 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1673,6 +1673,21 @@ struct link_station_del_parameters {
 	u32 link_id;
 };
 
+/**
+ * struct cfg80211_ttlm_params: TID to link mapping parameters
+ *
+ * Used for setting a TID to link mapping.
+ *
+ * @dlink: Downlink TID to link mapping, as defined in section 9.4.2.314
+ *     (TID-To-Link Mapping element) in Draft P802.11be_D4.0.
+ * @ulink: Uplink TID to link mapping, as defined in section 9.4.2.314
+ *     (TID-To-Link Mapping element) in Draft P802.11be_D4.0.
+ */
+struct cfg80211_ttlm_params {
+	u16 dlink[8];
+	u16 ulink[8];
+};
+
 /**
  * struct station_parameters - station parameters
  *
@@ -4523,6 +4538,7 @@ struct mgmt_frame_regs {
  * @del_link_station: Remove a link of a station.
  *
  * @set_hw_timestamp: Enable/disable HW timestamping of TM/FTM frames.
+ * @set_ttlm: set the TID to link mapping.
  */
 struct cfg80211_ops {
 	int	(*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow);
@@ -4882,6 +4898,8 @@ struct cfg80211_ops {
 				    struct link_station_del_parameters *params);
 	int	(*set_hw_timestamp)(struct wiphy *wiphy, struct net_device *dev,
 				    struct cfg80211_set_hw_timestamp *hwts);
+	int	(*set_ttlm)(struct wiphy *wiphy, struct net_device *dev,
+			    struct cfg80211_ttlm_params *params);
 };
 
 /*
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 07fc1fec4b12..2d8468cbc457 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -1328,6 +1328,11 @@
  *	Multi-Link reconfiguration. %NL80211_ATTR_MLO_LINKS is used to provide
  *	information about the removed STA MLD setup links.
  *
+ * @NL80211_CMD_SET_TID_TO_LINK_MAPPING: Set the TID to Link Mapping for a
+ *      non-AP MLD station. The %NL80211_ATTR_MLO_TTLM_DLINK and
+ *      %NL80211_ATTR_MLO_TTLM_ULINK attributes are used to specify the
+ *      TID to Link mapping for downlink/uplink traffic.
+ *
  * @NL80211_CMD_MAX: highest used command number
  * @__NL80211_CMD_AFTER_LAST: internal use
  */
@@ -1583,6 +1588,8 @@ enum nl80211_commands {
 
 	NL80211_CMD_LINKS_REMOVED,
 
+	NL80211_CMD_SET_TID_TO_LINK_MAPPING,
+
 	/* add new commands above here */
 
 	/* used to define NL80211_CMD_MAX below */
@@ -2835,6 +2842,15 @@ enum nl80211_commands {
  *	include BSSes that can only be used in restricted scenarios and/or
  *	cannot be used at all.
  *
+ * @NL80211_ATTR_MLO_TTLM_DLINK: Binary attribute specifying the downlink TID to
+ *      link mapping. The length is 8 * sizeof(u16). For each TID the link
+ *      mapping is as defined in section 9.4.2.314 (TID-To-Link Mapping element)
+ *      in Draft P802.11be_D4.0.
+ * @NL80211_ATTR_MLO_TTLM_ULINK: Binary attribute specifying the uplink TID to
+ *      link mapping. The length is 8 * sizeof(u16). For each TID the link
+ *      mapping is as defined in section 9.4.2.314 (TID-To-Link Mapping element)
+ *      in Draft P802.11be_D4.0.
+ *
  * @NUM_NL80211_ATTR: total number of nl80211_attrs available
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
@@ -3375,6 +3391,9 @@ enum nl80211_attrs {
 
 	NL80211_ATTR_BSS_DUMP_INCLUDE_USE_DATA,
 
+	NL80211_ATTR_MLO_TTLM_DLINK,
+	NL80211_ATTR_MLO_TTLM_ULINK,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 2820336511a2..0dec06cdf253 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -819,6 +819,8 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 	[NL80211_ATTR_EMA_RNR_ELEMS] = { .type = NLA_NESTED },
 	[NL80211_ATTR_MLO_LINK_DISABLED] = { .type = NLA_FLAG },
 	[NL80211_ATTR_BSS_DUMP_INCLUDE_USE_DATA] = { .type = NLA_FLAG },
+	[NL80211_ATTR_MLO_TTLM_DLINK] = NLA_POLICY_EXACT_LEN(sizeof(u16) * 8),
+	[NL80211_ATTR_MLO_TTLM_ULINK] = NLA_POLICY_EXACT_LEN(sizeof(u16) * 8),
 };
 
 /* policy for the key attributes */
@@ -16298,6 +16300,35 @@ static int nl80211_set_hw_timestamp(struct sk_buff *skb,
 	return rdev_set_hw_timestamp(rdev, dev, &hwts);
 }
 
+static int
+nl80211_set_ttlm(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg80211_ttlm_params params = {};
+	struct cfg80211_registered_device *rdev = info->user_ptr[0];
+	struct net_device *dev = info->user_ptr[1];
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
+
+	if (wdev->iftype != NL80211_IFTYPE_STATION &&
+	    wdev->iftype != NL80211_IFTYPE_P2P_CLIENT)
+		return -EOPNOTSUPP;
+
+	if (!wdev->connected)
+		return -ENOLINK;
+
+	if (!info->attrs[NL80211_ATTR_MLO_TTLM_DLINK] ||
+	    !info->attrs[NL80211_ATTR_MLO_TTLM_ULINK])
+		return -EINVAL;
+
+	nla_memcpy(params.dlink,
+		   info->attrs[NL80211_ATTR_MLO_TTLM_DLINK],
+		   sizeof(params.dlink));
+	nla_memcpy(params.ulink,
+		   info->attrs[NL80211_ATTR_MLO_TTLM_ULINK],
+		   sizeof(params.ulink));
+
+	return rdev_set_ttlm(rdev, dev, &params);
+}
+
 #define NL80211_FLAG_NEED_WIPHY		0x01
 #define NL80211_FLAG_NEED_NETDEV	0x02
 #define NL80211_FLAG_NEED_RTNL		0x04
@@ -17479,6 +17510,12 @@ static const struct genl_small_ops nl80211_small_ops[] = {
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP),
 	},
+	{
+		.cmd = NL80211_CMD_SET_TID_TO_LINK_MAPPING,
+		.doit = nl80211_set_ttlm,
+		.flags = GENL_UNS_ADMIN_PERM,
+		.internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP),
+	},
 };
 
 static struct genl_family nl80211_fam __ro_after_init = {
diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h
index 2214a90cf101..2a27a3448759 100644
--- a/net/wireless/rdev-ops.h
+++ b/net/wireless/rdev-ops.h
@@ -1524,4 +1524,22 @@ rdev_set_hw_timestamp(struct cfg80211_registered_device *rdev,
 
 	return ret;
 }
+
+static inline int
+rdev_set_ttlm(struct cfg80211_registered_device *rdev,
+	      struct net_device *dev,
+	      struct cfg80211_ttlm_params *params)
+{
+	struct wiphy *wiphy = &rdev->wiphy;
+	int ret;
+
+	if (!rdev->ops->set_ttlm)
+		return -EOPNOTSUPP;
+
+	trace_rdev_set_ttlm(wiphy, dev, params);
+	ret = rdev->ops->set_ttlm(wiphy, dev, params);
+	trace_rdev_return_int(wiphy, ret);
+
+	return ret;
+}
 #endif /* __CFG80211_RDEV_OPS */
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index 4de710efa47e..1f374c8a17a5 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -3979,6 +3979,26 @@ TRACE_EVENT(cfg80211_links_removed,
 		  __entry->link_mask)
 );
 
+TRACE_EVENT(rdev_set_ttlm,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
+		 struct cfg80211_ttlm_params *params),
+	TP_ARGS(wiphy, netdev, params),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		NETDEV_ENTRY
+		__array(u8, dlink, sizeof(u16) * 8)
+		__array(u8, ulink, sizeof(u16) * 8)
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		NETDEV_ASSIGN;
+		memcpy(__entry->dlink, params->dlink, sizeof(params->dlink));
+		memcpy(__entry->ulink, params->ulink, sizeof(params->ulink));
+	),
+	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT,
+		  WIPHY_PR_ARG, NETDEV_PR_ARG)
+);
+
 #endif /* !__RDEV_OPS_TRACE || TRACE_HEADER_MULTI_READ */
 
 #undef TRACE_INCLUDE_PATH
-- 
cgit v1.2.3


From 42b941cd6738d26abdae2f3fee520b79ea77e2fe Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 11 Dec 2023 09:05:23 +0200
Subject: wifi: mac80211: add a flag to disallow puncturing

There may be cases where puncturing isn't possible, and
a connection needs to be downgraded. Add a hardware flag
to support this.

This is likely temporary: it seems we will need to move
puncturing to the chandef/channel context.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Gregory Greenman <gregory.greenman@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20231211085121.c1e89ea55e93.I37b8ca0ee64d5d7699e351785a9010afc106da3c@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h |  4 ++++
 net/mac80211/debugfs.c |  1 +
 net/mac80211/mlme.c    | 12 ++++++++++--
 3 files changed, 15 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index aa8e1055fc3a..77a71b1396b1 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -2686,6 +2686,9 @@ struct ieee80211_txq {
  * @IEEE80211_HW_MLO_MCAST_MULTI_LINK_TX: Hardware/driver handles transmitting
  *	multicast frames on all links, mac80211 should not do that.
  *
+ * @IEEE80211_HW_DISALLOW_PUNCTURING: HW requires disabling puncturing in EHT
+ *	and connecting with a lower bandwidth instead
+ *
  * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays
  */
 enum ieee80211_hw_flags {
@@ -2743,6 +2746,7 @@ enum ieee80211_hw_flags {
 	IEEE80211_HW_SUPPORTS_CONC_MON_RX_DECAP,
 	IEEE80211_HW_DETECTS_COLOR_COLLISION,
 	IEEE80211_HW_MLO_MCAST_MULTI_LINK_TX,
+	IEEE80211_HW_DISALLOW_PUNCTURING,
 
 	/* keep last, obviously */
 	NUM_IEEE80211_HW_FLAGS
diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c
index b575ae90e57f..74be49191e70 100644
--- a/net/mac80211/debugfs.c
+++ b/net/mac80211/debugfs.c
@@ -497,6 +497,7 @@ static const char *hw_flag_names[] = {
 	FLAG(SUPPORTS_CONC_MON_RX_DECAP),
 	FLAG(DETECTS_COLOR_COLLISION),
 	FLAG(MLO_MCAST_MULTI_LINK_TX),
+	FLAG(DISALLOW_PUNCTURING),
 #undef FLAG
 };
 
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 887b496f2b81..2b1b64eb82f7 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -135,6 +135,7 @@ ieee80211_handle_puncturing_bitmap(struct ieee80211_link_data *link,
 				   u16 bitmap, u64 *changed)
 {
 	struct cfg80211_chan_def *chandef = &link->conf->chandef;
+	struct ieee80211_local *local = link->sdata->local;
 	u16 extracted;
 	u64 _changed = 0;
 
@@ -147,7 +148,9 @@ ieee80211_handle_puncturing_bitmap(struct ieee80211_link_data *link,
 							 bitmap);
 
 		if (cfg80211_valid_disable_subchannel_bitmap(&bitmap,
-							     chandef))
+							     chandef) &&
+		    !(bitmap && ieee80211_hw_check(&local->hw,
+						   DISALLOW_PUNCTURING)))
 			break;
 		link->u.mgd.conn_flags |=
 			ieee80211_chandef_downgrade(chandef);
@@ -5682,6 +5685,7 @@ static bool ieee80211_config_puncturing(struct ieee80211_link_data *link,
 					const struct ieee80211_eht_operation *eht_oper,
 					u64 *changed)
 {
+	struct ieee80211_local *local = link->sdata->local;
 	u16 bitmap = 0, extracted;
 
 	if ((eht_oper->params & IEEE80211_EHT_OPER_INFO_PRESENT) &&
@@ -5713,6 +5717,9 @@ static bool ieee80211_config_puncturing(struct ieee80211_link_data *link,
 		return false;
 	}
 
+	if (bitmap && ieee80211_hw_check(&local->hw, DISALLOW_PUNCTURING))
+		return false;
+
 	ieee80211_handle_puncturing_bitmap(link, eht_oper, bitmap, changed);
 	return true;
 }
@@ -7584,7 +7591,8 @@ ieee80211_setup_assoc_link(struct ieee80211_sub_if_data *sdata,
 
 			bitmap = get_unaligned_le16(disable_subchannel_bitmap);
 			if (cfg80211_valid_disable_subchannel_bitmap(&bitmap,
-								     &link->conf->chandef))
+								     &link->conf->chandef) &&
+			    !(bitmap && ieee80211_hw_check(&local->hw, DISALLOW_PUNCTURING)))
 				ieee80211_handle_puncturing_bitmap(link,
 								   eht_oper,
 								   bitmap,
-- 
cgit v1.2.3


From 62e1f212e5fe7624249212813ee96202e0c31430 Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@arm.com>
Date: Mon, 11 Dec 2023 16:13:14 +0000
Subject: arm: perf/kvm: Use GENMASK for ARMV8_PMU_PMCR_N

This is so that FIELD_GET and FIELD_PREP can be used and that the fields
are in a consistent format to arm64/tools/sysreg

Signed-off-by: James Clark <james.clark@arm.com>
Link: https://lore.kernel.org/r/20231211161331.1277825-3-james.clark@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kvm/pmu-emul.c      | 8 +++-----
 arch/arm64/kvm/sys_regs.c      | 4 ++--
 drivers/perf/arm_pmuv3.c       | 4 ++--
 include/linux/perf/arm_pmuv3.h | 3 +--
 4 files changed, 8 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index fe99b3dab6ce..3d9467ff73bc 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -267,9 +267,8 @@ void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu)
 
 u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu)
 {
-	u64 val = kvm_vcpu_read_pmcr(vcpu) >> ARMV8_PMU_PMCR_N_SHIFT;
+	u64 val = FIELD_GET(ARMV8_PMU_PMCR_N, kvm_vcpu_read_pmcr(vcpu));
 
-	val &= ARMV8_PMU_PMCR_N_MASK;
 	if (val == 0)
 		return BIT(ARMV8_PMU_CYCLE_IDX);
 	else
@@ -1136,8 +1135,7 @@ u8 kvm_arm_pmu_get_pmuver_limit(void)
  */
 u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu)
 {
-	u64 pmcr = __vcpu_sys_reg(vcpu, PMCR_EL0) &
-			~(ARMV8_PMU_PMCR_N_MASK << ARMV8_PMU_PMCR_N_SHIFT);
+	u64 pmcr = __vcpu_sys_reg(vcpu, PMCR_EL0);
 
-	return pmcr | ((u64)vcpu->kvm->arch.pmcr_n << ARMV8_PMU_PMCR_N_SHIFT);
+	return u64_replace_bits(pmcr, vcpu->kvm->arch.pmcr_n, ARMV8_PMU_PMCR_N);
 }
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 4735e1b37fb3..ff45d688bd7d 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -877,7 +877,7 @@ static bool pmu_counter_idx_valid(struct kvm_vcpu *vcpu, u64 idx)
 	u64 pmcr, val;
 
 	pmcr = kvm_vcpu_read_pmcr(vcpu);
-	val = (pmcr >> ARMV8_PMU_PMCR_N_SHIFT) & ARMV8_PMU_PMCR_N_MASK;
+	val = FIELD_GET(ARMV8_PMU_PMCR_N, pmcr);
 	if (idx >= val && idx != ARMV8_PMU_CYCLE_IDX) {
 		kvm_inject_undefined(vcpu);
 		return false;
@@ -1143,7 +1143,7 @@ static int get_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
 static int set_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
 		    u64 val)
 {
-	u8 new_n = (val >> ARMV8_PMU_PMCR_N_SHIFT) & ARMV8_PMU_PMCR_N_MASK;
+	u8 new_n = FIELD_GET(ARMV8_PMU_PMCR_N, val);
 	struct kvm *kvm = vcpu->kvm;
 
 	mutex_lock(&kvm->arch.config_lock);
diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c
index 09478e2b825e..374e973a4e42 100644
--- a/drivers/perf/arm_pmuv3.c
+++ b/drivers/perf/arm_pmuv3.c
@@ -15,6 +15,7 @@
 #include <clocksource/arm_arch_timer.h>
 
 #include <linux/acpi.h>
+#include <linux/bitfield.h>
 #include <linux/clocksource.h>
 #include <linux/of.h>
 #include <linux/perf/arm_pmu.h>
@@ -1111,8 +1112,7 @@ static void __armv8pmu_probe_pmu(void *info)
 	probe->present = true;
 
 	/* Read the nb of CNTx counters supported from PMNC */
-	cpu_pmu->num_events = (armv8pmu_pmcr_read() >> ARMV8_PMU_PMCR_N_SHIFT)
-		& ARMV8_PMU_PMCR_N_MASK;
+	cpu_pmu->num_events = FIELD_GET(ARMV8_PMU_PMCR_N, armv8pmu_pmcr_read());
 
 	/* Add the CPU cycles counter */
 	cpu_pmu->num_events += 1;
diff --git a/include/linux/perf/arm_pmuv3.h b/include/linux/perf/arm_pmuv3.h
index 9c226adf938a..ed62bd75cec7 100644
--- a/include/linux/perf/arm_pmuv3.h
+++ b/include/linux/perf/arm_pmuv3.h
@@ -215,8 +215,7 @@
 #define ARMV8_PMU_PMCR_DP	(1 << 5) /* Disable CCNT if non-invasive debug*/
 #define ARMV8_PMU_PMCR_LC	(1 << 6) /* Overflow on 64 bit cycle counter */
 #define ARMV8_PMU_PMCR_LP	(1 << 7) /* Long event counter enable */
-#define ARMV8_PMU_PMCR_N_SHIFT	11  /* Number of counters supported */
-#define ARMV8_PMU_PMCR_N_MASK	0x1f
+#define ARMV8_PMU_PMCR_N	GENMASK(15, 11) /* Number of counters supported */
 #define ARMV8_PMU_PMCR_MASK	0xff    /* Mask for writable bits */
 
 /*
-- 
cgit v1.2.3


From 2f6a00f30600417ee2737f2b1229c75663f1e3c9 Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@arm.com>
Date: Mon, 11 Dec 2023 16:13:15 +0000
Subject: arm: perf: Use GENMASK for PMMIR fields

This is so that FIELD_GET and FIELD_PREP can be used and that the fields
are in a consistent format to arm64/tools/sysreg

Signed-off-by: James Clark <james.clark@arm.com>
Link: https://lore.kernel.org/r/20231211161331.1277825-4-james.clark@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/perf/arm_pmuv3.c       | 8 +++-----
 include/linux/perf/arm_pmuv3.h | 9 +++------
 2 files changed, 6 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c
index 374e973a4e42..36bc00494f56 100644
--- a/drivers/perf/arm_pmuv3.c
+++ b/drivers/perf/arm_pmuv3.c
@@ -332,7 +332,7 @@ static ssize_t slots_show(struct device *dev, struct device_attribute *attr,
 {
 	struct pmu *pmu = dev_get_drvdata(dev);
 	struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu);
-	u32 slots = cpu_pmu->reg_pmmir & ARMV8_PMU_SLOTS_MASK;
+	u32 slots = FIELD_GET(ARMV8_PMU_SLOTS, cpu_pmu->reg_pmmir);
 
 	return sysfs_emit(page, "0x%08x\n", slots);
 }
@@ -344,8 +344,7 @@ static ssize_t bus_slots_show(struct device *dev, struct device_attribute *attr,
 {
 	struct pmu *pmu = dev_get_drvdata(dev);
 	struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu);
-	u32 bus_slots = (cpu_pmu->reg_pmmir >> ARMV8_PMU_BUS_SLOTS_SHIFT)
-			& ARMV8_PMU_BUS_SLOTS_MASK;
+	u32 bus_slots = FIELD_GET(ARMV8_PMU_BUS_SLOTS, cpu_pmu->reg_pmmir);
 
 	return sysfs_emit(page, "0x%08x\n", bus_slots);
 }
@@ -357,8 +356,7 @@ static ssize_t bus_width_show(struct device *dev, struct device_attribute *attr,
 {
 	struct pmu *pmu = dev_get_drvdata(dev);
 	struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu);
-	u32 bus_width = (cpu_pmu->reg_pmmir >> ARMV8_PMU_BUS_WIDTH_SHIFT)
-			& ARMV8_PMU_BUS_WIDTH_MASK;
+	u32 bus_width = FIELD_GET(ARMV8_PMU_BUS_WIDTH, cpu_pmu->reg_pmmir);
 	u32 val = 0;
 
 	/* Encoded as Log2(number of bytes), plus one */
diff --git a/include/linux/perf/arm_pmuv3.h b/include/linux/perf/arm_pmuv3.h
index ed62bd75cec7..1bc7678c10d4 100644
--- a/include/linux/perf/arm_pmuv3.h
+++ b/include/linux/perf/arm_pmuv3.h
@@ -250,12 +250,9 @@
 #define ARMV8_PMU_USERENR_ER	(1 << 3) /* Event counter can be read at EL0 */
 
 /* PMMIR_EL1.SLOTS mask */
-#define ARMV8_PMU_SLOTS_MASK	0xff
-
-#define ARMV8_PMU_BUS_SLOTS_SHIFT 8
-#define ARMV8_PMU_BUS_SLOTS_MASK 0xff
-#define ARMV8_PMU_BUS_WIDTH_SHIFT 16
-#define ARMV8_PMU_BUS_WIDTH_MASK 0xf
+#define ARMV8_PMU_SLOTS		GENMASK(7, 0)
+#define ARMV8_PMU_BUS_SLOTS	GENMASK(15, 8)
+#define ARMV8_PMU_BUS_WIDTH	GENMASK(19, 16)
 
 /*
  * This code is really good
-- 
cgit v1.2.3


From d30f09b6d7de5d159dbb537f9d67dceb67409420 Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@arm.com>
Date: Mon, 11 Dec 2023 16:13:16 +0000
Subject: arm: perf: Convert remaining fields to use GENMASK

Convert the remaining fields to use either GENMASK or be built from
other fields. These all already started at bit 0 so don't need a code
change for the lack of _SHIFT.

Signed-off-by: James Clark <james.clark@arm.com>
Link: https://lore.kernel.org/r/20231211161331.1277825-5-james.clark@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/perf/arm_pmuv3.c       |  2 +-
 include/linux/perf/arm_pmuv3.h | 18 +++++++++++++-----
 2 files changed, 14 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c
index 36bc00494f56..a93b4cf88562 100644
--- a/drivers/perf/arm_pmuv3.c
+++ b/drivers/perf/arm_pmuv3.c
@@ -675,7 +675,7 @@ static u32 armv8pmu_getreset_flags(void)
 	value = read_pmovsclr();
 
 	/* Write to clear flags */
-	value &= ARMV8_PMU_OVSR_MASK;
+	value &= ARMV8_PMU_OVERFLOWED_MASK;
 	write_pmovsclr(value);
 
 	return value;
diff --git a/include/linux/perf/arm_pmuv3.h b/include/linux/perf/arm_pmuv3.h
index 1bc7678c10d4..daa63542242d 100644
--- a/include/linux/perf/arm_pmuv3.h
+++ b/include/linux/perf/arm_pmuv3.h
@@ -216,19 +216,25 @@
 #define ARMV8_PMU_PMCR_LC	(1 << 6) /* Overflow on 64 bit cycle counter */
 #define ARMV8_PMU_PMCR_LP	(1 << 7) /* Long event counter enable */
 #define ARMV8_PMU_PMCR_N	GENMASK(15, 11) /* Number of counters supported */
-#define ARMV8_PMU_PMCR_MASK	0xff    /* Mask for writable bits */
+/* Mask for writable bits */
+#define ARMV8_PMU_PMCR_MASK	(ARMV8_PMU_PMCR_E | ARMV8_PMU_PMCR_P | \
+				 ARMV8_PMU_PMCR_C | ARMV8_PMU_PMCR_D | \
+				 ARMV8_PMU_PMCR_X | ARMV8_PMU_PMCR_DP | \
+				 ARMV8_PMU_PMCR_LC | ARMV8_PMU_PMCR_LP)
 
 /*
  * PMOVSR: counters overflow flag status reg
  */
-#define ARMV8_PMU_OVSR_MASK		0xffffffff	/* Mask for writable bits */
-#define ARMV8_PMU_OVERFLOWED_MASK	ARMV8_PMU_OVSR_MASK
+#define ARMV8_PMU_OVSR_P		GENMASK(30, 0)
+#define ARMV8_PMU_OVSR_C		BIT(31)
+/* Mask for writable bits is both P and C fields */
+#define ARMV8_PMU_OVERFLOWED_MASK	(ARMV8_PMU_OVSR_P | ARMV8_PMU_OVSR_C)
 
 /*
  * PMXEVTYPER: Event selection reg
  */
 #define ARMV8_PMU_EVTYPE_MASK	0xc800ffff	/* Mask for writable bits */
-#define ARMV8_PMU_EVTYPE_EVENT	0xffff		/* Mask for EVENT bits */
+#define ARMV8_PMU_EVTYPE_EVENT	GENMASK(15, 0)	/* Mask for EVENT bits */
 
 /*
  * Event filters for PMUv3
@@ -243,11 +249,13 @@
 /*
  * PMUSERENR: user enable reg
  */
-#define ARMV8_PMU_USERENR_MASK	0xf		/* Mask for writable bits */
 #define ARMV8_PMU_USERENR_EN	(1 << 0) /* PMU regs can be accessed at EL0 */
 #define ARMV8_PMU_USERENR_SW	(1 << 1) /* PMSWINC can be written at EL0 */
 #define ARMV8_PMU_USERENR_CR	(1 << 2) /* Cycle counter can be read at EL0 */
 #define ARMV8_PMU_USERENR_ER	(1 << 3) /* Event counter can be read at EL0 */
+/* Mask for writable bits */
+#define ARMV8_PMU_USERENR_MASK	(ARMV8_PMU_USERENR_EN | ARMV8_PMU_USERENR_SW | \
+				 ARMV8_PMU_USERENR_CR | ARMV8_PMU_USERENR_ER)
 
 /* PMMIR_EL1.SLOTS mask */
 #define ARMV8_PMU_SLOTS		GENMASK(7, 0)
-- 
cgit v1.2.3


From 3115ee021bfb04efde2e96507bfcc1330261a6a1 Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@arm.com>
Date: Mon, 11 Dec 2023 16:13:17 +0000
Subject: arm64: perf: Include threshold control fields in PMEVTYPER mask

FEAT_PMUv3_TH (Armv8.8) adds two new fields to PMEVTYPER, so include
them in the mask. These aren't writable on 32 bit kernels as they are in
the high part of the register, so only include them for arm64.

It would be difficult to do this statically in the asm header files for
each platform without resulting in circular includes or #ifdefs inline
in the code. For that reason the ARMV8_PMU_EVTYPE_MASK definition has
been removed and the mask is constructed programmatically.

Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Signed-off-by: James Clark <james.clark@arm.com>
Link: https://lore.kernel.org/r/20231211161331.1277825-6-james.clark@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/perf/arm_pmuv3.c       | 9 ++++++++-
 include/linux/perf/arm_pmuv3.h | 3 ++-
 2 files changed, 10 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c
index a93b4cf88562..441bf73ee3d5 100644
--- a/drivers/perf/arm_pmuv3.c
+++ b/drivers/perf/arm_pmuv3.c
@@ -558,8 +558,15 @@ static void armv8pmu_write_counter(struct perf_event *event, u64 value)
 static void armv8pmu_write_evtype(int idx, u32 val)
 {
 	u32 counter = ARMV8_IDX_TO_COUNTER(idx);
+	unsigned long mask = ARMV8_PMU_EVTYPE_EVENT |
+			     ARMV8_PMU_INCLUDE_EL2 |
+			     ARMV8_PMU_EXCLUDE_EL0 |
+			     ARMV8_PMU_EXCLUDE_EL1;
 
-	val &= ARMV8_PMU_EVTYPE_MASK;
+	if (IS_ENABLED(CONFIG_ARM64))
+		mask |= ARMV8_PMU_EVTYPE_TC | ARMV8_PMU_EVTYPE_TH;
+
+	val &= mask;
 	write_pmevtypern(counter, val);
 }
 
diff --git a/include/linux/perf/arm_pmuv3.h b/include/linux/perf/arm_pmuv3.h
index daa63542242d..91957b3468e9 100644
--- a/include/linux/perf/arm_pmuv3.h
+++ b/include/linux/perf/arm_pmuv3.h
@@ -233,8 +233,9 @@
 /*
  * PMXEVTYPER: Event selection reg
  */
-#define ARMV8_PMU_EVTYPE_MASK	0xc800ffff	/* Mask for writable bits */
 #define ARMV8_PMU_EVTYPE_EVENT	GENMASK(15, 0)	/* Mask for EVENT bits */
+#define ARMV8_PMU_EVTYPE_TH	GENMASK(43, 32)
+#define ARMV8_PMU_EVTYPE_TC	GENMASK(63, 61)
 
 /*
  * Event filters for PMUv3
-- 
cgit v1.2.3


From f6da86969a3c284466ab6080764b2ed91689f262 Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@arm.com>
Date: Mon, 11 Dec 2023 16:13:18 +0000
Subject: arm: pmu: Share user ABI format mechanism with SPE

This mechanism makes it much easier to define and read new attributes
so move it to the arm_pmu.h header so that it can be shared. At the same
time update the existing format attributes to use it.

GENMASK has to be changed to GENMASK_ULL because the config fields are
64 bits even on arm32 where this will also be used now.

Signed-off-by: James Clark <james.clark@arm.com>
Link: https://lore.kernel.org/r/20231211161331.1277825-7-james.clark@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/perf/arm_pmuv3.c     | 21 ++++++++++++++++-----
 drivers/perf/arm_spe_pmu.c   | 22 ----------------------
 include/linux/perf/arm_pmu.h | 22 ++++++++++++++++++++++
 3 files changed, 38 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c
index 441bf73ee3d5..8a573db81da1 100644
--- a/drivers/perf/arm_pmuv3.c
+++ b/drivers/perf/arm_pmuv3.c
@@ -299,20 +299,31 @@ static const struct attribute_group armv8_pmuv3_events_attr_group = {
 	.is_visible = armv8pmu_event_attr_is_visible,
 };
 
-PMU_FORMAT_ATTR(event, "config:0-15");
-PMU_FORMAT_ATTR(long, "config1:0");
-PMU_FORMAT_ATTR(rdpmc, "config1:1");
+/* User ABI */
+#define ATTR_CFG_FLD_event_CFG		config
+#define ATTR_CFG_FLD_event_LO		0
+#define ATTR_CFG_FLD_event_HI		15
+#define ATTR_CFG_FLD_long_CFG		config1
+#define ATTR_CFG_FLD_long_LO		0
+#define ATTR_CFG_FLD_long_HI		0
+#define ATTR_CFG_FLD_rdpmc_CFG		config1
+#define ATTR_CFG_FLD_rdpmc_LO		1
+#define ATTR_CFG_FLD_rdpmc_HI		1
+
+GEN_PMU_FORMAT_ATTR(event);
+GEN_PMU_FORMAT_ATTR(long);
+GEN_PMU_FORMAT_ATTR(rdpmc);
 
 static int sysctl_perf_user_access __read_mostly;
 
 static bool armv8pmu_event_is_64bit(struct perf_event *event)
 {
-	return event->attr.config1 & 0x1;
+	return ATTR_CFG_GET_FLD(&event->attr, long);
 }
 
 static bool armv8pmu_event_want_user_access(struct perf_event *event)
 {
-	return event->attr.config1 & 0x2;
+	return ATTR_CFG_GET_FLD(&event->attr, rdpmc);
 }
 
 static struct attribute *armv8_pmuv3_format_attrs[] = {
diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c
index d2b0cbf0e0c4..b622d75d8c9e 100644
--- a/drivers/perf/arm_spe_pmu.c
+++ b/drivers/perf/arm_spe_pmu.c
@@ -206,28 +206,6 @@ static const struct attribute_group arm_spe_pmu_cap_group = {
 #define ATTR_CFG_FLD_inv_event_filter_LO	0
 #define ATTR_CFG_FLD_inv_event_filter_HI	63
 
-/* Why does everything I do descend into this? */
-#define __GEN_PMU_FORMAT_ATTR(cfg, lo, hi)				\
-	(lo) == (hi) ? #cfg ":" #lo "\n" : #cfg ":" #lo "-" #hi
-
-#define _GEN_PMU_FORMAT_ATTR(cfg, lo, hi)				\
-	__GEN_PMU_FORMAT_ATTR(cfg, lo, hi)
-
-#define GEN_PMU_FORMAT_ATTR(name)					\
-	PMU_FORMAT_ATTR(name,						\
-	_GEN_PMU_FORMAT_ATTR(ATTR_CFG_FLD_##name##_CFG,			\
-			     ATTR_CFG_FLD_##name##_LO,			\
-			     ATTR_CFG_FLD_##name##_HI))
-
-#define _ATTR_CFG_GET_FLD(attr, cfg, lo, hi)				\
-	((((attr)->cfg) >> lo) & GENMASK(hi - lo, 0))
-
-#define ATTR_CFG_GET_FLD(attr, name)					\
-	_ATTR_CFG_GET_FLD(attr,						\
-			  ATTR_CFG_FLD_##name##_CFG,			\
-			  ATTR_CFG_FLD_##name##_LO,			\
-			  ATTR_CFG_FLD_##name##_HI)
-
 GEN_PMU_FORMAT_ATTR(ts_enable);
 GEN_PMU_FORMAT_ATTR(pa_enable);
 GEN_PMU_FORMAT_ATTR(pct_enable);
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index e2503d48ddee..b3b34f6670cf 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -183,4 +183,26 @@ void armpmu_free_irq(int irq, int cpu);
 #define ARMV8_SPE_PDEV_NAME "arm,spe-v1"
 #define ARMV8_TRBE_PDEV_NAME "arm,trbe"
 
+/* Why does everything I do descend into this? */
+#define __GEN_PMU_FORMAT_ATTR(cfg, lo, hi)				\
+	(lo) == (hi) ? #cfg ":" #lo "\n" : #cfg ":" #lo "-" #hi
+
+#define _GEN_PMU_FORMAT_ATTR(cfg, lo, hi)				\
+	__GEN_PMU_FORMAT_ATTR(cfg, lo, hi)
+
+#define GEN_PMU_FORMAT_ATTR(name)					\
+	PMU_FORMAT_ATTR(name,						\
+	_GEN_PMU_FORMAT_ATTR(ATTR_CFG_FLD_##name##_CFG,			\
+			     ATTR_CFG_FLD_##name##_LO,			\
+			     ATTR_CFG_FLD_##name##_HI))
+
+#define _ATTR_CFG_GET_FLD(attr, cfg, lo, hi)				\
+	((((attr)->cfg) >> lo) & GENMASK_ULL(hi - lo, 0))
+
+#define ATTR_CFG_GET_FLD(attr, name)					\
+	_ATTR_CFG_GET_FLD(attr,						\
+			  ATTR_CFG_FLD_##name##_CFG,			\
+			  ATTR_CFG_FLD_##name##_LO,			\
+			  ATTR_CFG_FLD_##name##_HI)
+
 #endif /* __ARM_PMU_H__ */
-- 
cgit v1.2.3


From 816c26754447e8b28d6c604e1f5b1d205b2586ee Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@arm.com>
Date: Mon, 11 Dec 2023 16:13:22 +0000
Subject: arm64: perf: Add support for event counting threshold

FEAT_PMUv3_TH (Armv8.8) permits a PMU counter to increment only on
events whose count meets a specified threshold condition. For example if
PMEVTYPERn.TC (Threshold Control) is set to 0b101 (Greater than or
equal, count), and the threshold is set to 2, then the PMU counter will
now only increment by 1 when an event would have previously incremented
the PMU counter by 2 or more on a single processor cycle.

Three new Perf event config fields, 'threshold', 'threshold_compare' and
'threshold_count' have been added to control the feature.
threshold_compare maps to the upper two bits of PMEVTYPERn.TC and
threshold_count maps to the first bit of TC. These separate attributes
have been picked rather than enumerating all the possible combinations
of the TC field as in the Arm ARM. The attributes would be used on a
Perf command line like this:

  $ perf stat -e stall_slot/threshold=2,threshold_compare=2/

A new capability for reading out the maximum supported threshold value
has also been added:

  $ cat /sys/bus/event_source/devices/armv8_pmuv3/caps/threshold_max

  0x000000ff

If a threshold higher than threshold_max is provided, then an error is
generated. If FEAT_PMUv3_TH isn't implemented or a 32 bit kernel is
running, then threshold_max reads zero, and attempting to set a
threshold value will also result in an error.

The threshold is per PMU counter, and there are potentially different
threshold_max values per PMU type on heterogeneous systems.

Bits higher than 32 now need to be written into PMEVTYPER, so
armv8pmu_write_evtype() has to be updated to take an unsigned long value
rather than u32 which gives the correct behavior on both aarch32 and 64.

Signed-off-by: James Clark <james.clark@arm.com>
Link: https://lore.kernel.org/r/20231211161331.1277825-11-james.clark@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/perf/arm_pmuv3.c       | 79 +++++++++++++++++++++++++++++++++++++++++-
 include/linux/perf/arm_pmuv3.h |  1 +
 2 files changed, 79 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c
index 2ba215f74d92..23fa6c5da82c 100644
--- a/drivers/perf/arm_pmuv3.c
+++ b/drivers/perf/arm_pmuv3.c
@@ -309,10 +309,22 @@ static const struct attribute_group armv8_pmuv3_events_attr_group = {
 #define ATTR_CFG_FLD_rdpmc_CFG		config1
 #define ATTR_CFG_FLD_rdpmc_LO		1
 #define ATTR_CFG_FLD_rdpmc_HI		1
+#define ATTR_CFG_FLD_threshold_count_CFG	config1 /* PMEVTYPER.TC[0] */
+#define ATTR_CFG_FLD_threshold_count_LO		2
+#define ATTR_CFG_FLD_threshold_count_HI		2
+#define ATTR_CFG_FLD_threshold_compare_CFG	config1 /* PMEVTYPER.TC[2:1] */
+#define ATTR_CFG_FLD_threshold_compare_LO	3
+#define ATTR_CFG_FLD_threshold_compare_HI	4
+#define ATTR_CFG_FLD_threshold_CFG		config1 /* PMEVTYPER.TH */
+#define ATTR_CFG_FLD_threshold_LO		5
+#define ATTR_CFG_FLD_threshold_HI		16
 
 GEN_PMU_FORMAT_ATTR(event);
 GEN_PMU_FORMAT_ATTR(long);
 GEN_PMU_FORMAT_ATTR(rdpmc);
+GEN_PMU_FORMAT_ATTR(threshold_count);
+GEN_PMU_FORMAT_ATTR(threshold_compare);
+GEN_PMU_FORMAT_ATTR(threshold);
 
 static int sysctl_perf_user_access __read_mostly;
 
@@ -326,10 +338,27 @@ static bool armv8pmu_event_want_user_access(struct perf_event *event)
 	return ATTR_CFG_GET_FLD(&event->attr, rdpmc);
 }
 
+static u8 armv8pmu_event_threshold_control(struct perf_event_attr *attr)
+{
+	u8 th_compare = ATTR_CFG_GET_FLD(attr, threshold_compare);
+	u8 th_count = ATTR_CFG_GET_FLD(attr, threshold_count);
+
+	/*
+	 * The count bit is always the bottom bit of the full control field, and
+	 * the comparison is the upper two bits, but it's not explicitly
+	 * labelled in the Arm ARM. For the Perf interface we split it into two
+	 * fields, so reconstruct it here.
+	 */
+	return (th_compare << 1) | th_count;
+}
+
 static struct attribute *armv8_pmuv3_format_attrs[] = {
 	&format_attr_event.attr,
 	&format_attr_long.attr,
 	&format_attr_rdpmc.attr,
+	&format_attr_threshold.attr,
+	&format_attr_threshold_compare.attr,
+	&format_attr_threshold_count.attr,
 	NULL,
 };
 
@@ -379,10 +408,38 @@ static ssize_t bus_width_show(struct device *dev, struct device_attribute *attr,
 
 static DEVICE_ATTR_RO(bus_width);
 
+static u32 threshold_max(struct arm_pmu *cpu_pmu)
+{
+	/*
+	 * PMMIR.THWIDTH is readable and non-zero on aarch32, but it would be
+	 * impossible to write the threshold in the upper 32 bits of PMEVTYPER.
+	 */
+	if (IS_ENABLED(CONFIG_ARM))
+		return 0;
+
+	/*
+	 * The largest value that can be written to PMEVTYPER<n>_EL0.TH is
+	 * (2 ^ PMMIR.THWIDTH) - 1.
+	 */
+	return (1 << FIELD_GET(ARMV8_PMU_THWIDTH, cpu_pmu->reg_pmmir)) - 1;
+}
+
+static ssize_t threshold_max_show(struct device *dev,
+				  struct device_attribute *attr, char *page)
+{
+	struct pmu *pmu = dev_get_drvdata(dev);
+	struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu);
+
+	return sysfs_emit(page, "0x%08x\n", threshold_max(cpu_pmu));
+}
+
+static DEVICE_ATTR_RO(threshold_max);
+
 static struct attribute *armv8_pmuv3_caps_attrs[] = {
 	&dev_attr_slots.attr,
 	&dev_attr_bus_slots.attr,
 	&dev_attr_bus_width.attr,
+	&dev_attr_threshold_max.attr,
 	NULL,
 };
 
@@ -566,7 +623,7 @@ static void armv8pmu_write_counter(struct perf_event *event, u64 value)
 		armv8pmu_write_hw_counter(event, value);
 }
 
-static void armv8pmu_write_evtype(int idx, u32 val)
+static void armv8pmu_write_evtype(int idx, unsigned long val)
 {
 	u32 counter = ARMV8_IDX_TO_COUNTER(idx);
 	unsigned long mask = ARMV8_PMU_EVTYPE_EVENT |
@@ -935,6 +992,10 @@ static int armv8pmu_set_event_filter(struct hw_perf_event *event,
 				     struct perf_event_attr *attr)
 {
 	unsigned long config_base = 0;
+	struct perf_event *perf_event = container_of(attr, struct perf_event,
+						     attr);
+	struct arm_pmu *cpu_pmu = to_arm_pmu(perf_event->pmu);
+	u32 th;
 
 	if (attr->exclude_idle) {
 		pr_debug("ARM performance counters do not support mode exclusion\n");
@@ -968,6 +1029,22 @@ static int armv8pmu_set_event_filter(struct hw_perf_event *event,
 	if (attr->exclude_user)
 		config_base |= ARMV8_PMU_EXCLUDE_EL0;
 
+	/*
+	 * If FEAT_PMUv3_TH isn't implemented, then THWIDTH (threshold_max) will
+	 * be 0 and will also trigger this check, preventing it from being used.
+	 */
+	th = ATTR_CFG_GET_FLD(attr, threshold);
+	if (th > threshold_max(cpu_pmu)) {
+		pr_debug("PMU event threshold exceeds max value\n");
+		return -EINVAL;
+	}
+
+	if (IS_ENABLED(CONFIG_ARM64) && th) {
+		config_base |= FIELD_PREP(ARMV8_PMU_EVTYPE_TH, th);
+		config_base |= FIELD_PREP(ARMV8_PMU_EVTYPE_TC,
+					  armv8pmu_event_threshold_control(attr));
+	}
+
 	/*
 	 * Install the filter into config_base as this is used to
 	 * construct the event type.
diff --git a/include/linux/perf/arm_pmuv3.h b/include/linux/perf/arm_pmuv3.h
index 91957b3468e9..0f4d62ef3a9a 100644
--- a/include/linux/perf/arm_pmuv3.h
+++ b/include/linux/perf/arm_pmuv3.h
@@ -262,6 +262,7 @@
 #define ARMV8_PMU_SLOTS		GENMASK(7, 0)
 #define ARMV8_PMU_BUS_SLOTS	GENMASK(15, 8)
 #define ARMV8_PMU_BUS_WIDTH	GENMASK(19, 16)
+#define ARMV8_PMU_THWIDTH	GENMASK(23, 20)
 
 /*
  * This code is really good
-- 
cgit v1.2.3


From 253ca8678d30bcf94410b54476fc1e0f1627a137 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 26 Nov 2023 12:24:38 -0800
Subject: Improve __fget_files_rcu() code generation (and thus __fget_light())

Commit 0ede61d8589c ("file: convert to SLAB_TYPESAFE_BY_RCU") caused a
performance regression as reported by the kernel test robot.

The __fget_light() function is one of those critical ones for some
loads, and the code generation was unnecessarily impacted.  Let's just
write that function to better.

Reported-by: kernel test robot <oliver.sang@intel.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jann Horn <jannh@google.com>
Cc: Mateusz Guzik <mjguzik@gmail.com>
Closes: https://lore.kernel.org/oe-lkp/202311201406.2022ca3f-oliver.sang@intel.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/CAHk-=wiCJtLbFWNURB34b9a_R_unaH3CiMRXfkR0-iihB_z68A@mail.gmail.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/file.c               | 51 ++++++++++++++++++++++++++++++++-----------------
 include/linux/fdtable.h | 17 +++++++++++------
 2 files changed, 44 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/fs/file.c b/fs/file.c
index 5fb0b146e79e..50df31e104a5 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -959,31 +959,45 @@ static inline struct file *__fget_files_rcu(struct files_struct *files,
 		struct file *file;
 		struct fdtable *fdt = rcu_dereference_raw(files->fdt);
 		struct file __rcu **fdentry;
+		unsigned long nospec_mask;
 
-		if (unlikely(fd >= fdt->max_fds))
-			return NULL;
-
-		fdentry = fdt->fd + array_index_nospec(fd, fdt->max_fds);
+		/* Mask is a 0 for invalid fd's, ~0 for valid ones */
+		nospec_mask = array_index_mask_nospec(fd, fdt->max_fds);
 
 		/*
-		 * Ok, we have a file pointer. However, because we do
-		 * this all locklessly under RCU, we may be racing with
-		 * that file being closed.
-		 *
-		 * Such a race can take two forms:
-		 *
-		 *  (a) the file ref already went down to zero and the
-		 *      file hasn't been reused yet or the file count
-		 *      isn't zero but the file has already been reused.
+		 * fdentry points to the 'fd' offset, or fdt->fd[0].
+		 * Loading from fdt->fd[0] is always safe, because the
+		 * array always exists.
 		 */
-		file = __get_file_rcu(fdentry);
+		fdentry = fdt->fd + (fd & nospec_mask);
+
+		/* Do the load, then mask any invalid result */
+		file = rcu_dereference_raw(*fdentry);
+		file = (void *)(nospec_mask & (unsigned long)file);
 		if (unlikely(!file))
 			return NULL;
 
-		if (unlikely(IS_ERR(file)))
+		/*
+		 * Ok, we have a file pointer that was valid at
+		 * some point, but it might have become stale since.
+		 *
+		 * We need to confirm it by incrementing the refcount
+		 * and then check the lookup again.
+		 *
+		 * atomic_long_inc_not_zero() gives us a full memory
+		 * barrier. We only really need an 'acquire' one to
+		 * protect the loads below, but we don't have that.
+		 */
+		if (unlikely(!atomic_long_inc_not_zero(&file->f_count)))
 			continue;
 
 		/*
+		 * Such a race can take two forms:
+		 *
+		 *  (a) the file ref already went down to zero and the
+		 *      file hasn't been reused yet or the file count
+		 *      isn't zero but the file has already been reused.
+		 *
 		 *  (b) the file table entry has changed under us.
 		 *       Note that we don't need to re-check the 'fdt->fd'
 		 *       pointer having changed, because it always goes
@@ -991,7 +1005,8 @@ static inline struct file *__fget_files_rcu(struct files_struct *files,
 		 *
 		 * If so, we need to put our ref and try again.
 		 */
-		if (unlikely(rcu_dereference_raw(files->fdt) != fdt)) {
+		if (unlikely(file != rcu_dereference_raw(*fdentry)) ||
+		    unlikely(rcu_dereference_raw(files->fdt) != fdt)) {
 			fput(file);
 			continue;
 		}
@@ -1128,13 +1143,13 @@ static unsigned long __fget_light(unsigned int fd, fmode_t mask)
 	 * atomic_read_acquire() pairs with atomic_dec_and_test() in
 	 * put_files_struct().
 	 */
-	if (atomic_read_acquire(&files->count) == 1) {
+	if (likely(atomic_read_acquire(&files->count) == 1)) {
 		file = files_lookup_fd_raw(files, fd);
 		if (!file || unlikely(file->f_mode & mask))
 			return 0;
 		return (unsigned long)file;
 	} else {
-		file = __fget(fd, mask);
+		file = __fget_files(files, fd, mask);
 		if (!file)
 			return 0;
 		return FDPUT_FPUT | (unsigned long)file;
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index bc4c3287a65e..80bd7789bab1 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -83,12 +83,17 @@ struct dentry;
 static inline struct file *files_lookup_fd_raw(struct files_struct *files, unsigned int fd)
 {
 	struct fdtable *fdt = rcu_dereference_raw(files->fdt);
-
-	if (fd < fdt->max_fds) {
-		fd = array_index_nospec(fd, fdt->max_fds);
-		return rcu_dereference_raw(fdt->fd[fd]);
-	}
-	return NULL;
+	unsigned long mask = array_index_mask_nospec(fd, fdt->max_fds);
+	struct file *needs_masking;
+
+	/*
+	 * 'mask' is zero for an out-of-bounds fd, all ones for ok.
+	 * 'fd&mask' is 'fd' for ok, or 0 for out of bounds.
+	 *
+	 * Accessing fdt->fd[0] is ok, but needs masking of the result.
+	 */
+	needs_masking = rcu_dereference_raw(fdt->fd[fd&mask]);
+	return (struct file *)(mask & (unsigned long)needs_masking);
 }
 
 static inline struct file *files_lookup_fd_locked(struct files_struct *files, unsigned int fd)
-- 
cgit v1.2.3


From a88c955fcfb49727d0ed86b47410f6555a8e69e4 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Thu, 30 Nov 2023 13:49:07 +0100
Subject: file: s/close_fd_get_file()/file_close_fd()/g

That really shouldn't have "get" in there as that implies we're bumping
the reference count which we don't do at all. We used to but not anmore.
Now we're just closing the fd and pick that file from the fdtable
without bumping the reference count. Update the wrong documentation
while at it.

Link: https://lore.kernel.org/r/20231130-vfs-files-fixes-v1-1-e73ca6f4ea83@kernel.org
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 drivers/android/binder.c |  2 +-
 fs/file.c                | 14 +++++++++-----
 fs/open.c                |  2 +-
 include/linux/fdtable.h  |  2 +-
 4 files changed, 12 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 92128aae2d06..7658103ba760 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -1921,7 +1921,7 @@ static void binder_deferred_fd_close(int fd)
 	if (!twcb)
 		return;
 	init_task_work(&twcb->twork, binder_do_fd_close);
-	twcb->file = close_fd_get_file(fd);
+	twcb->file = file_close_fd(fd);
 	if (twcb->file) {
 		// pin it until binder_do_fd_close(); see comments there
 		get_file(twcb->file);
diff --git a/fs/file.c b/fs/file.c
index 50df31e104a5..66f04442a384 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -796,7 +796,7 @@ int __close_range(unsigned fd, unsigned max_fd, unsigned int flags)
 }
 
 /*
- * See close_fd_get_file() below, this variant assumes current->files->file_lock
+ * See file_close_fd() below, this variant assumes current->files->file_lock
  * is held.
  */
 struct file *__close_fd_get_file(unsigned int fd)
@@ -804,11 +804,15 @@ struct file *__close_fd_get_file(unsigned int fd)
 	return pick_file(current->files, fd);
 }
 
-/*
- * variant of close_fd that gets a ref on the file for later fput.
- * The caller must ensure that filp_close() called on the file.
+/**
+ * file_close_fd - return file associated with fd
+ * @fd: file descriptor to retrieve file for
+ *
+ * Doesn't take a separate reference count.
+ *
+ * Returns: The file associated with @fd (NULL if @fd is not open)
  */
-struct file *close_fd_get_file(unsigned int fd)
+struct file *file_close_fd(unsigned int fd)
 {
 	struct files_struct *files = current->files;
 	struct file *file;
diff --git a/fs/open.c b/fs/open.c
index 02dc608d40d8..48775329f3f1 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -1577,7 +1577,7 @@ SYSCALL_DEFINE1(close, unsigned int, fd)
 	int retval;
 	struct file *file;
 
-	file = close_fd_get_file(fd);
+	file = file_close_fd(fd);
 	if (!file)
 		return -EBADF;
 
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index 80bd7789bab1..78c8326d74ae 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -119,7 +119,7 @@ int iterate_fd(struct files_struct *, unsigned,
 
 extern int close_fd(unsigned int fd);
 extern int __close_range(unsigned int fd, unsigned int max_fd, unsigned int flags);
-extern struct file *close_fd_get_file(unsigned int fd);
+extern struct file *file_close_fd(unsigned int fd);
 extern int unshare_fd(unsigned long unshare_flags, unsigned int max_fds,
 		      struct files_struct **new_fdp);
 
-- 
cgit v1.2.3


From 372a34e66fb7f95124fadae9c600b231c35696a7 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Thu, 30 Nov 2023 13:49:09 +0100
Subject: fs: replace f_rcuhead with f_task_work

The naming is actively misleading since we switched to
SLAB_TYPESAFE_BY_RCU. rcu_head is #define callback_head. Use
callback_head directly and rename f_rcuhead to f_task_work.

Add comments in there to explain what it's used for.

Link: https://lore.kernel.org/r/20231130-vfs-files-fixes-v1-3-e73ca6f4ea83@kernel.org
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/file_table.c    | 6 +++---
 include/linux/fs.h | 4 +++-
 2 files changed, 6 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/fs/file_table.c b/fs/file_table.c
index 6deac386486d..3ba764d73fc9 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -407,7 +407,7 @@ static void delayed_fput(struct work_struct *unused)
 
 static void ____fput(struct callback_head *work)
 {
-	__fput(container_of(work, struct file, f_rcuhead));
+	__fput(container_of(work, struct file, f_task_work));
 }
 
 /*
@@ -438,8 +438,8 @@ void fput(struct file *file)
 			return;
 		}
 		if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) {
-			init_task_work(&file->f_rcuhead, ____fput);
-			if (!task_work_add(task, &file->f_rcuhead, TWA_RESUME))
+			init_task_work(&file->f_task_work, ____fput);
+			if (!task_work_add(task, &file->f_task_work, TWA_RESUME))
 				return;
 			/*
 			 * After this task has run exit_task_work(),
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 98b7a7a8c42e..354fd02e0e11 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -991,8 +991,10 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
  */
 struct file {
 	union {
+		/* fput() uses task work when closing and freeing file (default). */
+		struct callback_head 	f_task_work;
+		/* fput() must use workqueue (most kernel threads). */
 		struct llist_node	f_llist;
-		struct rcu_head 	f_rcuhead;
 		unsigned int 		f_iocb_flags;
 	};
 
-- 
cgit v1.2.3


From eac9189c96196574a83a553ca5a7543dd9f5fe3e Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Thu, 30 Nov 2023 13:49:10 +0100
Subject: file: stop exposing receive_fd_user()

Not every subsystem needs to have their own specialized helper.
Just us the __receive_fd() helper.

Link: https://lore.kernel.org/r/20231130-vfs-files-fixes-v1-4-e73ca6f4ea83@kernel.org
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/file.h | 7 -------
 include/net/scm.h    | 9 +++++++++
 net/compat.c         | 2 +-
 net/core/scm.c       | 2 +-
 4 files changed, 11 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/file.h b/include/linux/file.h
index 6e9099d29343..c0d5219c2852 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -101,13 +101,6 @@ extern int __receive_fd(struct file *file, int __user *ufd,
 
 extern int receive_fd(struct file *file, unsigned int o_flags);
 
-static inline int receive_fd_user(struct file *file, int __user *ufd,
-				  unsigned int o_flags)
-{
-	if (ufd == NULL)
-		return -EFAULT;
-	return __receive_fd(file, ufd, o_flags);
-}
 int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags);
 
 extern void flush_delayed_fput(void);
diff --git a/include/net/scm.h b/include/net/scm.h
index e8c76b4be2fe..8aae2468bae0 100644
--- a/include/net/scm.h
+++ b/include/net/scm.h
@@ -5,6 +5,7 @@
 #include <linux/limits.h>
 #include <linux/net.h>
 #include <linux/cred.h>
+#include <linux/file.h>
 #include <linux/security.h>
 #include <linux/pid.h>
 #include <linux/nsproxy.h>
@@ -208,5 +209,13 @@ static inline void scm_recv_unix(struct socket *sock, struct msghdr *msg,
 	scm_destroy_cred(scm);
 }
 
+static inline int scm_recv_one_fd(struct file *f, int __user *ufd,
+				  unsigned int flags)
+{
+	if (!ufd)
+		return -EFAULT;
+	return __receive_fd(f, ufd, flags);
+}
+
 #endif /* __LINUX_NET_SCM_H */
 
diff --git a/net/compat.c b/net/compat.c
index 6564720f32b7..485db8ee9b28 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -297,7 +297,7 @@ void scm_detach_fds_compat(struct msghdr *msg, struct scm_cookie *scm)
 	int err = 0, i;
 
 	for (i = 0; i < fdmax; i++) {
-		err = receive_fd_user(scm->fp->fp[i], cmsg_data + i, o_flags);
+		err = scm_recv_one_fd(scm->fp->fp[i], cmsg_data + i, o_flags);
 		if (err < 0)
 			break;
 	}
diff --git a/net/core/scm.c b/net/core/scm.c
index 880027ecf516..eec78e312550 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -319,7 +319,7 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm)
 	}
 
 	for (i = 0; i < fdmax; i++) {
-		err = receive_fd_user(scm->fp->fp[i], cmsg_data + i, o_flags);
+		err = scm_recv_one_fd(scm->fp->fp[i], cmsg_data + i, o_flags);
 		if (err < 0)
 			break;
 	}
-- 
cgit v1.2.3


From 4e94ddfe2aab72139acb8d5372fac9e6c3f3e383 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Thu, 30 Nov 2023 13:49:11 +0100
Subject: file: remove __receive_fd()

Honestly, there's little value in having a helper with and without that
int __user *ufd argument. It's just messy and doesn't really give us
anything. Just expose receive_fd() with that argument and get rid of
that helper.

Link: https://lore.kernel.org/r/20231130-vfs-files-fixes-v1-5-e73ca6f4ea83@kernel.org
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 drivers/vdpa/vdpa_user/vduse_dev.c |  2 +-
 fs/file.c                          | 11 +++--------
 include/linux/file.h               |  5 +----
 include/net/scm.h                  |  2 +-
 kernel/pid.c                       |  2 +-
 kernel/seccomp.c                   |  2 +-
 6 files changed, 8 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c
index 0ddd4b8abecb..fafd4610b185 100644
--- a/drivers/vdpa/vdpa_user/vduse_dev.c
+++ b/drivers/vdpa/vdpa_user/vduse_dev.c
@@ -1157,7 +1157,7 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd,
 			fput(f);
 			break;
 		}
-		ret = receive_fd(f, perm_to_file_flags(entry.perm));
+		ret = receive_fd(f, NULL, perm_to_file_flags(entry.perm));
 		fput(f);
 		break;
 	}
diff --git a/fs/file.c b/fs/file.c
index c8eaa0b29a08..3b683b9101d8 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -1296,7 +1296,7 @@ out_unlock:
 }
 
 /**
- * __receive_fd() - Install received file into file descriptor table
+ * receive_fd() - Install received file into file descriptor table
  * @file: struct file that was received from another process
  * @ufd: __user pointer to write new fd number to
  * @o_flags: the O_* flags to apply to the new fd entry
@@ -1310,7 +1310,7 @@ out_unlock:
  *
  * Returns newly install fd or -ve on error.
  */
-int __receive_fd(struct file *file, int __user *ufd, unsigned int o_flags)
+int receive_fd(struct file *file, int __user *ufd, unsigned int o_flags)
 {
 	int new_fd;
 	int error;
@@ -1335,6 +1335,7 @@ int __receive_fd(struct file *file, int __user *ufd, unsigned int o_flags)
 	__receive_sock(file);
 	return new_fd;
 }
+EXPORT_SYMBOL_GPL(receive_fd);
 
 int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags)
 {
@@ -1350,12 +1351,6 @@ int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags)
 	return new_fd;
 }
 
-int receive_fd(struct file *file, unsigned int o_flags)
-{
-	return __receive_fd(file, NULL, o_flags);
-}
-EXPORT_SYMBOL_GPL(receive_fd);
-
 static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags)
 {
 	int err = -EBADF;
diff --git a/include/linux/file.h b/include/linux/file.h
index c0d5219c2852..6834a29338c4 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -96,10 +96,7 @@ DEFINE_CLASS(get_unused_fd, int, if (_T >= 0) put_unused_fd(_T),
 
 extern void fd_install(unsigned int fd, struct file *file);
 
-extern int __receive_fd(struct file *file, int __user *ufd,
-			unsigned int o_flags);
-
-extern int receive_fd(struct file *file, unsigned int o_flags);
+int receive_fd(struct file *file, int __user *ufd, unsigned int o_flags);
 
 int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags);
 
diff --git a/include/net/scm.h b/include/net/scm.h
index 8aae2468bae0..cf68acec4d70 100644
--- a/include/net/scm.h
+++ b/include/net/scm.h
@@ -214,7 +214,7 @@ static inline int scm_recv_one_fd(struct file *f, int __user *ufd,
 {
 	if (!ufd)
 		return -EFAULT;
-	return __receive_fd(f, ufd, flags);
+	return receive_fd(f, ufd, flags);
 }
 
 #endif /* __LINUX_NET_SCM_H */
diff --git a/kernel/pid.c b/kernel/pid.c
index 6500ef956f2f..b52b10865454 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -700,7 +700,7 @@ static int pidfd_getfd(struct pid *pid, int fd)
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	ret = receive_fd(file, O_CLOEXEC);
+	ret = receive_fd(file, NULL, O_CLOEXEC);
 	fput(file);
 
 	return ret;
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 255999ba9190..aca7b437882e 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -1072,7 +1072,7 @@ static void seccomp_handle_addfd(struct seccomp_kaddfd *addfd, struct seccomp_kn
 	 */
 	list_del_init(&addfd->list);
 	if (!addfd->setfd)
-		fd = receive_fd(addfd->file, addfd->flags);
+		fd = receive_fd(addfd->file, NULL, addfd->flags);
 	else
 		fd = receive_fd_replace(addfd->fd, addfd->file, addfd->flags);
 	addfd->ret = fd;
-- 
cgit v1.2.3


From b66509b8497f2b002a2654e386a440f1274ddcc7 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Fri, 1 Dec 2023 00:57:35 +0000
Subject: io_uring: split out cmd api into a separate header

linux/io_uring.h is slowly becoming a rubbish bin where we put
anything exposed to other subsystems. For instance, the task exit
hooks and io_uring cmd infra are completely orthogonal and don't need
each other's definitions. Start cleaning it up by splitting out all
command bits into a new header file.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/7ec50bae6e21f371d3850796e716917fc141225a.1701391955.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 MAINTAINERS                    |  1 +
 drivers/block/ublk_drv.c       |  2 +-
 drivers/nvme/host/ioctl.c      |  2 +-
 include/linux/io_uring.h       | 89 +-----------------------------------------
 include/linux/io_uring/cmd.h   | 81 ++++++++++++++++++++++++++++++++++++++
 include/linux/io_uring_types.h | 20 ++++++++++
 io_uring/io_uring.c            |  1 +
 io_uring/rw.c                  |  2 +-
 io_uring/uring_cmd.c           |  2 +-
 security/selinux/hooks.c       |  2 +-
 security/smack/smack_lsm.c     |  2 +-
 11 files changed, 110 insertions(+), 94 deletions(-)
 create mode 100644 include/linux/io_uring/cmd.h

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index e2c6187a3ac8..eb404a6b4a11 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -11102,6 +11102,7 @@ L:	io-uring@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.dk/linux-block
 T:	git git://git.kernel.dk/liburing
+F:	include/linux/io_uring/
 F:	include/linux/io_uring.h
 F:	include/linux/io_uring_types.h
 F:	include/trace/events/io_uring.h
diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 83600b45e12a..909377068a87 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -36,7 +36,7 @@
 #include <linux/sched/mm.h>
 #include <linux/uaccess.h>
 #include <linux/cdev.h>
-#include <linux/io_uring.h>
+#include <linux/io_uring/cmd.h>
 #include <linux/blk-mq.h>
 #include <linux/delay.h>
 #include <linux/mm.h>
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index 4939ed35638f..276788bbb96d 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -5,7 +5,7 @@
  */
 #include <linux/ptrace.h>	/* for force_successful_syscall_return */
 #include <linux/nvme_ioctl.h>
-#include <linux/io_uring.h>
+#include <linux/io_uring/cmd.h>
 #include "nvme.h"
 
 enum {
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index aefb73eeeebf..d8fc93492dc5 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -6,71 +6,13 @@
 #include <linux/xarray.h>
 #include <uapi/linux/io_uring.h>
 
-enum io_uring_cmd_flags {
-	IO_URING_F_COMPLETE_DEFER	= 1,
-	IO_URING_F_UNLOCKED		= 2,
-	/* the request is executed from poll, it should not be freed */
-	IO_URING_F_MULTISHOT		= 4,
-	/* executed by io-wq */
-	IO_URING_F_IOWQ			= 8,
-	/* int's last bit, sign checks are usually faster than a bit test */
-	IO_URING_F_NONBLOCK		= INT_MIN,
-
-	/* ctx state flags, for URING_CMD */
-	IO_URING_F_SQE128		= (1 << 8),
-	IO_URING_F_CQE32		= (1 << 9),
-	IO_URING_F_IOPOLL		= (1 << 10),
-
-	/* set when uring wants to cancel a previously issued command */
-	IO_URING_F_CANCEL		= (1 << 11),
-	IO_URING_F_COMPAT		= (1 << 12),
-};
-
-/* only top 8 bits of sqe->uring_cmd_flags for kernel internal use */
-#define IORING_URING_CMD_CANCELABLE	(1U << 30)
-#define IORING_URING_CMD_POLLED		(1U << 31)
-
-struct io_uring_cmd {
-	struct file	*file;
-	const struct io_uring_sqe *sqe;
-	union {
-		/* callback to defer completions to task context */
-		void (*task_work_cb)(struct io_uring_cmd *cmd, unsigned);
-		/* used for polled completion */
-		void *cookie;
-	};
-	u32		cmd_op;
-	u32		flags;
-	u8		pdu[32]; /* available inline for free use */
-};
-
-static inline const void *io_uring_sqe_cmd(const struct io_uring_sqe *sqe)
-{
-	return sqe->cmd;
-}
-
 #if defined(CONFIG_IO_URING)
-int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
-			      struct iov_iter *iter, void *ioucmd);
-void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2,
-			unsigned issue_flags);
 struct sock *io_uring_get_socket(struct file *file);
 void __io_uring_cancel(bool cancel_all);
 void __io_uring_free(struct task_struct *tsk);
 void io_uring_unreg_ringfd(void);
 const char *io_uring_get_opcode(u8 opcode);
-void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd,
-			    void (*task_work_cb)(struct io_uring_cmd *, unsigned),
-			    unsigned flags);
-/* users should follow semantics of IOU_F_TWQ_LAZY_WAKE */
-void io_uring_cmd_do_in_task_lazy(struct io_uring_cmd *ioucmd,
-			void (*task_work_cb)(struct io_uring_cmd *, unsigned));
-
-static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd,
-			void (*task_work_cb)(struct io_uring_cmd *, unsigned))
-{
-	__io_uring_cmd_do_in_task(ioucmd, task_work_cb, 0);
-}
+int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags);
 
 static inline void io_uring_files_cancel(void)
 {
@@ -89,28 +31,7 @@ static inline void io_uring_free(struct task_struct *tsk)
 	if (tsk->io_uring)
 		__io_uring_free(tsk);
 }
-int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags);
-void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd,
-		unsigned int issue_flags);
-struct task_struct *io_uring_cmd_get_task(struct io_uring_cmd *cmd);
 #else
-static inline int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
-			      struct iov_iter *iter, void *ioucmd)
-{
-	return -EOPNOTSUPP;
-}
-static inline void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret,
-		ssize_t ret2, unsigned issue_flags)
-{
-}
-static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd,
-			void (*task_work_cb)(struct io_uring_cmd *, unsigned))
-{
-}
-static inline void io_uring_cmd_do_in_task_lazy(struct io_uring_cmd *ioucmd,
-			void (*task_work_cb)(struct io_uring_cmd *, unsigned))
-{
-}
 static inline struct sock *io_uring_get_socket(struct file *file)
 {
 	return NULL;
@@ -133,14 +54,6 @@ static inline int io_uring_cmd_sock(struct io_uring_cmd *cmd,
 {
 	return -EOPNOTSUPP;
 }
-static inline void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd,
-		unsigned int issue_flags)
-{
-}
-static inline struct task_struct *io_uring_cmd_get_task(struct io_uring_cmd *cmd)
-{
-	return NULL;
-}
 #endif
 
 #endif
diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h
new file mode 100644
index 000000000000..62fcfaf6fcc9
--- /dev/null
+++ b/include/linux/io_uring/cmd.h
@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _LINUX_IO_URING_CMD_H
+#define _LINUX_IO_URING_CMD_H
+
+#include <uapi/linux/io_uring.h>
+#include <linux/io_uring_types.h>
+
+/* only top 8 bits of sqe->uring_cmd_flags for kernel internal use */
+#define IORING_URING_CMD_CANCELABLE	(1U << 30)
+#define IORING_URING_CMD_POLLED		(1U << 31)
+
+struct io_uring_cmd {
+	struct file	*file;
+	const struct io_uring_sqe *sqe;
+	union {
+		/* callback to defer completions to task context */
+		void (*task_work_cb)(struct io_uring_cmd *cmd, unsigned);
+		/* used for polled completion */
+		void *cookie;
+	};
+	u32		cmd_op;
+	u32		flags;
+	u8		pdu[32]; /* available inline for free use */
+};
+
+static inline const void *io_uring_sqe_cmd(const struct io_uring_sqe *sqe)
+{
+	return sqe->cmd;
+}
+
+#if defined(CONFIG_IO_URING)
+int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
+			      struct iov_iter *iter, void *ioucmd);
+void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2,
+			unsigned issue_flags);
+void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd,
+			    void (*task_work_cb)(struct io_uring_cmd *, unsigned),
+			    unsigned flags);
+/* users should follow semantics of IOU_F_TWQ_LAZY_WAKE */
+void io_uring_cmd_do_in_task_lazy(struct io_uring_cmd *ioucmd,
+			void (*task_work_cb)(struct io_uring_cmd *, unsigned));
+
+static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd,
+			void (*task_work_cb)(struct io_uring_cmd *, unsigned))
+{
+	__io_uring_cmd_do_in_task(ioucmd, task_work_cb, 0);
+}
+
+void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd,
+		unsigned int issue_flags);
+struct task_struct *io_uring_cmd_get_task(struct io_uring_cmd *cmd);
+
+#else
+static inline int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
+			      struct iov_iter *iter, void *ioucmd)
+{
+	return -EOPNOTSUPP;
+}
+static inline void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret,
+		ssize_t ret2, unsigned issue_flags)
+{
+}
+static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd,
+			void (*task_work_cb)(struct io_uring_cmd *, unsigned))
+{
+}
+static inline void io_uring_cmd_do_in_task_lazy(struct io_uring_cmd *ioucmd,
+			void (*task_work_cb)(struct io_uring_cmd *, unsigned))
+{
+}
+static inline void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd,
+		unsigned int issue_flags)
+{
+}
+static inline struct task_struct *io_uring_cmd_get_task(struct io_uring_cmd *cmd)
+{
+	return NULL;
+}
+#endif
+
+#endif /* _LINUX_IO_URING_CMD_H */
diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 805bb635cdf5..8c807bcc8b2b 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -7,6 +7,26 @@
 #include <linux/llist.h>
 #include <uapi/linux/io_uring.h>
 
+enum io_uring_cmd_flags {
+	IO_URING_F_COMPLETE_DEFER	= 1,
+	IO_URING_F_UNLOCKED		= 2,
+	/* the request is executed from poll, it should not be freed */
+	IO_URING_F_MULTISHOT		= 4,
+	/* executed by io-wq */
+	IO_URING_F_IOWQ			= 8,
+	/* int's last bit, sign checks are usually faster than a bit test */
+	IO_URING_F_NONBLOCK		= INT_MIN,
+
+	/* ctx state flags, for URING_CMD */
+	IO_URING_F_SQE128		= (1 << 8),
+	IO_URING_F_CQE32		= (1 << 9),
+	IO_URING_F_IOPOLL		= (1 << 10),
+
+	/* set when uring wants to cancel a previously issued command */
+	IO_URING_F_CANCEL		= (1 << 11),
+	IO_URING_F_COMPAT		= (1 << 12),
+};
+
 struct io_wq_work_node {
 	struct io_wq_work_node *next;
 };
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 0c269652ad26..5c946f3ed91c 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -70,6 +70,7 @@
 #include <linux/fadvise.h>
 #include <linux/task_work.h>
 #include <linux/io_uring.h>
+#include <linux/io_uring/cmd.h>
 #include <linux/audit.h>
 #include <linux/security.h>
 #include <asm/shmparam.h>
diff --git a/io_uring/rw.c b/io_uring/rw.c
index 64390d4e20c1..4943d683508b 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -10,7 +10,7 @@
 #include <linux/poll.h>
 #include <linux/nospec.h>
 #include <linux/compat.h>
-#include <linux/io_uring.h>
+#include <linux/io_uring/cmd.h>
 
 #include <uapi/linux/io_uring.h>
 
diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c
index acbc2924ecd2..4ed0c66e3aae 100644
--- a/io_uring/uring_cmd.c
+++ b/io_uring/uring_cmd.c
@@ -2,7 +2,7 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/file.h>
-#include <linux/io_uring.h>
+#include <linux/io_uring/cmd.h>
 #include <linux/security.h>
 #include <linux/nospec.h>
 
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index feda711c6b7b..17ec5e109aec 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -91,7 +91,7 @@
 #include <uapi/linux/mount.h>
 #include <linux/fsnotify.h>
 #include <linux/fanotify.h>
-#include <linux/io_uring.h>
+#include <linux/io_uring/cmd.h>
 
 #include "avc.h"
 #include "objsec.h"
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index 65130a791f57..2cdaa46088a0 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -42,7 +42,7 @@
 #include <linux/fs_context.h>
 #include <linux/fs_parser.h>
 #include <linux/watch_queue.h>
-#include <linux/io_uring.h>
+#include <linux/io_uring/cmd.h>
 #include "smack.h"
 
 #define TRANS_TRUE	"TRUE"
-- 
cgit v1.2.3


From 6b04a3737057ddfed396c954f9e4be4fe6d53c62 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Fri, 1 Dec 2023 00:57:36 +0000
Subject: io_uring/cmd: inline io_uring_cmd_do_in_task_lazy

Now as we can easily include io_uring_types.h, move IOU_F_TWQ_LAZY_WAKE
and inline io_uring_cmd_do_in_task_lazy().

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/2ec9fb31dd192d1c5cf26d0a2dec5657d88a8e48.1701391955.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/io_uring/cmd.h   | 31 ++++++++++++++++---------------
 include/linux/io_uring_types.h | 11 +++++++++++
 io_uring/io_uring.h            | 10 ----------
 io_uring/uring_cmd.c           |  7 -------
 4 files changed, 27 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h
index 62fcfaf6fcc9..ee9b3bc3a4af 100644
--- a/include/linux/io_uring/cmd.h
+++ b/include/linux/io_uring/cmd.h
@@ -36,15 +36,6 @@ void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2,
 void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd,
 			    void (*task_work_cb)(struct io_uring_cmd *, unsigned),
 			    unsigned flags);
-/* users should follow semantics of IOU_F_TWQ_LAZY_WAKE */
-void io_uring_cmd_do_in_task_lazy(struct io_uring_cmd *ioucmd,
-			void (*task_work_cb)(struct io_uring_cmd *, unsigned));
-
-static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd,
-			void (*task_work_cb)(struct io_uring_cmd *, unsigned))
-{
-	__io_uring_cmd_do_in_task(ioucmd, task_work_cb, 0);
-}
 
 void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd,
 		unsigned int issue_flags);
@@ -60,12 +51,9 @@ static inline void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret,
 		ssize_t ret2, unsigned issue_flags)
 {
 }
-static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd,
-			void (*task_work_cb)(struct io_uring_cmd *, unsigned))
-{
-}
-static inline void io_uring_cmd_do_in_task_lazy(struct io_uring_cmd *ioucmd,
-			void (*task_work_cb)(struct io_uring_cmd *, unsigned))
+static inline void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd,
+			    void (*task_work_cb)(struct io_uring_cmd *, unsigned),
+			    unsigned flags)
 {
 }
 static inline void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd,
@@ -78,4 +66,17 @@ static inline struct task_struct *io_uring_cmd_get_task(struct io_uring_cmd *cmd
 }
 #endif
 
+/* users must follow the IOU_F_TWQ_LAZY_WAKE semantics */
+static inline void io_uring_cmd_do_in_task_lazy(struct io_uring_cmd *ioucmd,
+			void (*task_work_cb)(struct io_uring_cmd *, unsigned))
+{
+	__io_uring_cmd_do_in_task(ioucmd, task_work_cb, IOU_F_TWQ_LAZY_WAKE);
+}
+
+static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd,
+			void (*task_work_cb)(struct io_uring_cmd *, unsigned))
+{
+	__io_uring_cmd_do_in_task(ioucmd, task_work_cb, 0);
+}
+
 #endif /* _LINUX_IO_URING_CMD_H */
diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 8c807bcc8b2b..bebab36abce8 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -7,6 +7,17 @@
 #include <linux/llist.h>
 #include <uapi/linux/io_uring.h>
 
+enum {
+	/*
+	 * A hint to not wake right away but delay until there are enough of
+	 * tw's queued to match the number of CQEs the task is waiting for.
+	 *
+	 * Must not be used wirh requests generating more than one CQE.
+	 * It's also ignored unless IORING_SETUP_DEFER_TASKRUN is set.
+	 */
+	IOU_F_TWQ_LAZY_WAKE			= 1,
+};
+
 enum io_uring_cmd_flags {
 	IO_URING_F_COMPLETE_DEFER	= 1,
 	IO_URING_F_UNLOCKED		= 2,
diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index ed84f2737b3a..ef783a2444ac 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -15,16 +15,6 @@
 #include <trace/events/io_uring.h>
 #endif
 
-enum {
-	/*
-	 * A hint to not wake right away but delay until there are enough of
-	 * tw's queued to match the number of CQEs the task is waiting for.
-	 *
-	 * Must not be used wirh requests generating more than one CQE.
-	 * It's also ignored unless IORING_SETUP_DEFER_TASKRUN is set.
-	 */
-	IOU_F_TWQ_LAZY_WAKE			= 1,
-};
 
 enum {
 	IOU_OK			= 0,
diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c
index 4ed0c66e3aae..94e9de1c24aa 100644
--- a/io_uring/uring_cmd.c
+++ b/io_uring/uring_cmd.c
@@ -78,13 +78,6 @@ void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd,
 }
 EXPORT_SYMBOL_GPL(__io_uring_cmd_do_in_task);
 
-void io_uring_cmd_do_in_task_lazy(struct io_uring_cmd *ioucmd,
-			void (*task_work_cb)(struct io_uring_cmd *, unsigned))
-{
-	__io_uring_cmd_do_in_task(ioucmd, task_work_cb, IOU_F_TWQ_LAZY_WAKE);
-}
-EXPORT_SYMBOL_GPL(io_uring_cmd_do_in_task_lazy);
-
 static inline void io_req_set_cqe32_extra(struct io_kiocb *req,
 					  u64 extra1, u64 extra2)
 {
-- 
cgit v1.2.3


From 055c15626a45b1ebc9f2f34981e705e1af171236 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Fri, 1 Dec 2023 00:57:37 +0000
Subject: io_uring/cmd: inline io_uring_cmd_get_task

With io_uring_types.h we see all required definitions to inline
io_uring_cmd_get_task().

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/aa8e317f09e651a5f3e72f8c0ad3902084c1f930.1701391955.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/io_uring/cmd.h | 10 +++++-----
 io_uring/uring_cmd.c         |  6 ------
 2 files changed, 5 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h
index ee9b3bc3a4af..d69b4038aa3e 100644
--- a/include/linux/io_uring/cmd.h
+++ b/include/linux/io_uring/cmd.h
@@ -39,7 +39,6 @@ void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd,
 
 void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd,
 		unsigned int issue_flags);
-struct task_struct *io_uring_cmd_get_task(struct io_uring_cmd *cmd);
 
 #else
 static inline int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
@@ -60,10 +59,6 @@ static inline void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd,
 		unsigned int issue_flags)
 {
 }
-static inline struct task_struct *io_uring_cmd_get_task(struct io_uring_cmd *cmd)
-{
-	return NULL;
-}
 #endif
 
 /* users must follow the IOU_F_TWQ_LAZY_WAKE semantics */
@@ -79,4 +74,9 @@ static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd,
 	__io_uring_cmd_do_in_task(ioucmd, task_work_cb, 0);
 }
 
+static inline struct task_struct *io_uring_cmd_get_task(struct io_uring_cmd *cmd)
+{
+	return cmd_to_io_kiocb(cmd)->task;
+}
+
 #endif /* _LINUX_IO_URING_CMD_H */
diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c
index 94e9de1c24aa..34030583b9b2 100644
--- a/io_uring/uring_cmd.c
+++ b/io_uring/uring_cmd.c
@@ -52,12 +52,6 @@ void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd,
 }
 EXPORT_SYMBOL_GPL(io_uring_cmd_mark_cancelable);
 
-struct task_struct *io_uring_cmd_get_task(struct io_uring_cmd *cmd)
-{
-	return cmd_to_io_kiocb(cmd)->task;
-}
-EXPORT_SYMBOL_GPL(io_uring_cmd_get_task);
-
 static void io_uring_cmd_work(struct io_kiocb *req, struct io_tw_state *ts)
 {
 	struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd);
-- 
cgit v1.2.3


From dc18b89ab113e9c6c7a529316ddf7029fb55132d Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 7 Dec 2023 20:06:02 -0700
Subject: io_uring/openclose: add support for IORING_OP_FIXED_FD_INSTALL

io_uring can currently open/close regular files or fixed/direct
descriptors. Or you can instantiate a fixed descriptor from a regular
one, and then close the regular descriptor. But you currently can't turn
a purely fixed/direct descriptor into a regular file descriptor.

IORING_OP_FIXED_FD_INSTALL adds support for installing a direct
descriptor into the normal file table, just like receiving a file
descriptor or opening a new file would do. This is all nicely abstracted
into receive_fd(), and hence adding support for this is truly trivial.

Since direct descriptors are only usable within io_uring itself, it can
be useful to turn them into real file descriptors if they ever need to
be accessed via normal syscalls. This can either be a transitory thing,
or just a permanent transition for a given direct descriptor.

By default, new fds are installed with O_CLOEXEC set. The application
can disable O_CLOEXEC by setting IORING_FIXED_FD_NO_CLOEXEC in the
sqe->install_fd_flags member.

Suggested-by: Christian Brauner <brauner@kernel.org>
Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/uapi/linux/io_uring.h |  9 +++++++++
 io_uring/opdef.c              |  9 +++++++++
 io_uring/openclose.c          | 44 +++++++++++++++++++++++++++++++++++++++++++
 io_uring/openclose.h          |  3 +++
 4 files changed, 65 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index f1c16f817742..db4b913e6b39 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -71,6 +71,7 @@ struct io_uring_sqe {
 		__u32		uring_cmd_flags;
 		__u32		waitid_flags;
 		__u32		futex_flags;
+		__u32		install_fd_flags;
 	};
 	__u64	user_data;	/* data to be passed back at completion time */
 	/* pack this to avoid bogus arm OABI complaints */
@@ -253,6 +254,7 @@ enum io_uring_op {
 	IORING_OP_FUTEX_WAIT,
 	IORING_OP_FUTEX_WAKE,
 	IORING_OP_FUTEX_WAITV,
+	IORING_OP_FIXED_FD_INSTALL,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,
@@ -386,6 +388,13 @@ enum {
 /* Pass through the flags from sqe->file_index to cqe->flags */
 #define IORING_MSG_RING_FLAGS_PASS	(1U << 1)
 
+/*
+ * IORING_OP_FIXED_FD_INSTALL flags (sqe->install_fd_flags)
+ *
+ * IORING_FIXED_FD_NO_CLOEXEC	Don't mark the fd as O_CLOEXEC
+ */
+#define IORING_FIXED_FD_NO_CLOEXEC	(1U << 0)
+
 /*
  * IO completion data structure (Completion Queue Entry)
  */
diff --git a/io_uring/opdef.c b/io_uring/opdef.c
index 799db44283c7..6705634e5f52 100644
--- a/io_uring/opdef.c
+++ b/io_uring/opdef.c
@@ -469,6 +469,12 @@ const struct io_issue_def io_issue_defs[] = {
 		.prep			= io_eopnotsupp_prep,
 #endif
 	},
+	[IORING_OP_FIXED_FD_INSTALL] = {
+		.needs_file		= 1,
+		.audit_skip		= 1,
+		.prep			= io_install_fixed_fd_prep,
+		.issue			= io_install_fixed_fd,
+	},
 };
 
 const struct io_cold_def io_cold_defs[] = {
@@ -704,6 +710,9 @@ const struct io_cold_def io_cold_defs[] = {
 	[IORING_OP_FUTEX_WAITV] = {
 		.name			= "FUTEX_WAITV",
 	},
+	[IORING_OP_FIXED_FD_INSTALL] = {
+		.name			= "FIXED_FD_INSTALL",
+	},
 };
 
 const char *io_uring_get_opcode(u8 opcode)
diff --git a/io_uring/openclose.c b/io_uring/openclose.c
index 74fc22461f48..0fe0dd305546 100644
--- a/io_uring/openclose.c
+++ b/io_uring/openclose.c
@@ -31,6 +31,11 @@ struct io_close {
 	u32				file_slot;
 };
 
+struct io_fixed_install {
+	struct file			*file;
+	unsigned int			o_flags;
+};
+
 static bool io_openat_force_async(struct io_open *open)
 {
 	/*
@@ -254,3 +259,42 @@ err:
 	io_req_set_res(req, ret, 0);
 	return IOU_OK;
 }
+
+int io_install_fixed_fd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_fixed_install *ifi;
+	unsigned int flags;
+
+	if (sqe->off || sqe->addr || sqe->len || sqe->buf_index ||
+	    sqe->splice_fd_in || sqe->addr3)
+		return -EINVAL;
+
+	/* must be a fixed file */
+	if (!(req->flags & REQ_F_FIXED_FILE))
+		return -EBADF;
+
+	flags = READ_ONCE(sqe->install_fd_flags);
+	if (flags & ~IORING_FIXED_FD_NO_CLOEXEC)
+		return -EINVAL;
+
+	/* default to O_CLOEXEC, disable if IORING_FIXED_FD_NO_CLOEXEC is set */
+	ifi = io_kiocb_to_cmd(req, struct io_fixed_install);
+	ifi->o_flags = O_CLOEXEC;
+	if (flags & IORING_FIXED_FD_NO_CLOEXEC)
+		ifi->o_flags = 0;
+
+	return 0;
+}
+
+int io_install_fixed_fd(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_fixed_install *ifi;
+	int ret;
+
+	ifi = io_kiocb_to_cmd(req, struct io_fixed_install);
+	ret = receive_fd(req->file, NULL, ifi->o_flags);
+	if (ret < 0)
+		req_set_fail(req);
+	io_req_set_res(req, ret, 0);
+	return IOU_OK;
+}
diff --git a/io_uring/openclose.h b/io_uring/openclose.h
index 4b1c28d3a66c..8a93c98ad0ad 100644
--- a/io_uring/openclose.h
+++ b/io_uring/openclose.h
@@ -12,3 +12,6 @@ int io_openat2(struct io_kiocb *req, unsigned int issue_flags);
 
 int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
 int io_close(struct io_kiocb *req, unsigned int issue_flags);
+
+int io_install_fixed_fd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_install_fixed_fd(struct io_kiocb *req, unsigned int issue_flags);
-- 
cgit v1.2.3


From 0f292086c22b43202daffc14b585d3b54b9a1206 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Tue, 12 Dec 2023 11:44:36 +0200
Subject: splice: return type ssize_t from all helpers

Not sure why some splice helpers return long, maybe historic reasons.
Change them all to return ssize_t to conform to the splice methods and
to the rest of the helpers.

Suggested-by: Christian Brauner <brauner@kernel.org>
Link: https://lore.kernel.org/r/20231208-horchen-helium-d3ec1535ede5@brauner/
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Link: https://lore.kernel.org/r/20231212094440.250945-2-amir73il@gmail.com
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/internal.h          |   8 ++--
 fs/overlayfs/copy_up.c |   2 +-
 fs/read_write.c        |   2 +-
 fs/splice.c            | 104 +++++++++++++++++++++++++------------------------
 include/linux/splice.h |  43 ++++++++++----------
 io_uring/splice.c      |   4 +-
 6 files changed, 82 insertions(+), 81 deletions(-)

(limited to 'include')

diff --git a/fs/internal.h b/fs/internal.h
index 58e43341aebf..4eaa758e3bfd 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -243,10 +243,10 @@ int do_statx(int dfd, struct filename *filename, unsigned int flags,
 /*
  * fs/splice.c:
  */
-long splice_file_to_pipe(struct file *in,
-			 struct pipe_inode_info *opipe,
-			 loff_t *offset,
-			 size_t len, unsigned int flags);
+ssize_t splice_file_to_pipe(struct file *in,
+			    struct pipe_inode_info *opipe,
+			    loff_t *offset,
+			    size_t len, unsigned int flags);
 
 /*
  * fs/xattr.c:
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index 2f587ee0b334..070d36ba0f09 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -285,7 +285,7 @@ static int ovl_copy_up_file(struct ovl_fs *ofs, struct dentry *dentry,
 
 	while (len) {
 		size_t this_len = OVL_COPY_UP_CHUNK_SIZE;
-		long bytes;
+		ssize_t bytes;
 
 		if (len < this_len)
 			this_len = len;
diff --git a/fs/read_write.c b/fs/read_write.c
index 01a14570015b..7783b8522693 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1214,7 +1214,7 @@ COMPAT_SYSCALL_DEFINE6(pwritev2, compat_ulong_t, fd,
 #endif /* CONFIG_COMPAT */
 
 static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
-		  	   size_t count, loff_t max)
+			   size_t count, loff_t max)
 {
 	struct fd in, out;
 	struct inode *in_inode, *out_inode;
diff --git a/fs/splice.c b/fs/splice.c
index 7cda013e5a1e..c39d1abf23c8 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -201,7 +201,8 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe,
 	unsigned int tail = pipe->tail;
 	unsigned int head = pipe->head;
 	unsigned int mask = pipe->ring_size - 1;
-	int ret = 0, page_nr = 0;
+	ssize_t ret = 0;
+	int page_nr = 0;
 
 	if (!spd_pages)
 		return 0;
@@ -932,8 +933,8 @@ static int warn_unsupported(struct file *file, const char *op)
 /*
  * Attempt to initiate a splice from pipe to file.
  */
-static long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
-			   loff_t *ppos, size_t len, unsigned int flags)
+static ssize_t do_splice_from(struct pipe_inode_info *pipe, struct file *out,
+			      loff_t *ppos, size_t len, unsigned int flags)
 {
 	if (unlikely(!out->f_op->splice_write))
 		return warn_unsupported(out, "write");
@@ -955,9 +956,9 @@ static void do_splice_eof(struct splice_desc *sd)
  * Callers already called rw_verify_area() on the entire range.
  * No need to call it for sub ranges.
  */
-static long do_splice_read(struct file *in, loff_t *ppos,
-			   struct pipe_inode_info *pipe, size_t len,
-			   unsigned int flags)
+static ssize_t do_splice_read(struct file *in, loff_t *ppos,
+			      struct pipe_inode_info *pipe, size_t len,
+			      unsigned int flags)
 {
 	unsigned int p_space;
 
@@ -999,11 +1000,11 @@ static long do_splice_read(struct file *in, loff_t *ppos,
  * If successful, it returns the amount of data spliced, 0 if it hit the EOF or
  * a hole and a negative error code otherwise.
  */
-long vfs_splice_read(struct file *in, loff_t *ppos,
-		     struct pipe_inode_info *pipe, size_t len,
-		     unsigned int flags)
+ssize_t vfs_splice_read(struct file *in, loff_t *ppos,
+			struct pipe_inode_info *pipe, size_t len,
+			unsigned int flags)
 {
-	int ret;
+	ssize_t ret;
 
 	ret = rw_verify_area(READ, in, ppos, len);
 	if (unlikely(ret < 0))
@@ -1030,7 +1031,7 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd,
 			       splice_direct_actor *actor)
 {
 	struct pipe_inode_info *pipe;
-	long ret, bytes;
+	ssize_t ret, bytes;
 	size_t len;
 	int i, flags, more;
 
@@ -1181,10 +1182,10 @@ static void direct_file_splice_eof(struct splice_desc *sd)
 		file->f_op->splice_eof(file);
 }
 
-static long do_splice_direct_actor(struct file *in, loff_t *ppos,
-				   struct file *out, loff_t *opos,
-				   size_t len, unsigned int flags,
-				   splice_direct_actor *actor)
+static ssize_t do_splice_direct_actor(struct file *in, loff_t *ppos,
+				      struct file *out, loff_t *opos,
+				      size_t len, unsigned int flags,
+				      splice_direct_actor *actor)
 {
 	struct splice_desc sd = {
 		.len		= len,
@@ -1195,7 +1196,7 @@ static long do_splice_direct_actor(struct file *in, loff_t *ppos,
 		.splice_eof	= direct_file_splice_eof,
 		.opos		= opos,
 	};
-	long ret;
+	ssize_t ret;
 
 	if (unlikely(!(out->f_mode & FMODE_WRITE)))
 		return -EBADF;
@@ -1226,8 +1227,8 @@ static long do_splice_direct_actor(struct file *in, loff_t *ppos,
  *
  * Callers already called rw_verify_area() on the entire range.
  */
-long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
-		      loff_t *opos, size_t len, unsigned int flags)
+ssize_t do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
+			 loff_t *opos, size_t len, unsigned int flags)
 {
 	return do_splice_direct_actor(in, ppos, out, opos, len, flags,
 				      direct_splice_actor);
@@ -1249,8 +1250,8 @@ EXPORT_SYMBOL(do_splice_direct);
  *
  * Callers already called rw_verify_area() on the entire range.
  */
-long splice_file_range(struct file *in, loff_t *ppos, struct file *out,
-		       loff_t *opos, size_t len)
+ssize_t splice_file_range(struct file *in, loff_t *ppos, struct file *out,
+			  loff_t *opos, size_t len)
 {
 	lockdep_assert(file_write_started(out));
 
@@ -1280,12 +1281,12 @@ static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe,
 			       struct pipe_inode_info *opipe,
 			       size_t len, unsigned int flags);
 
-long splice_file_to_pipe(struct file *in,
-			 struct pipe_inode_info *opipe,
-			 loff_t *offset,
-			 size_t len, unsigned int flags)
+ssize_t splice_file_to_pipe(struct file *in,
+			    struct pipe_inode_info *opipe,
+			    loff_t *offset,
+			    size_t len, unsigned int flags)
 {
-	long ret;
+	ssize_t ret;
 
 	pipe_lock(opipe);
 	ret = wait_for_space(opipe, flags);
@@ -1300,13 +1301,13 @@ long splice_file_to_pipe(struct file *in,
 /*
  * Determine where to splice to/from.
  */
-long do_splice(struct file *in, loff_t *off_in, struct file *out,
-	       loff_t *off_out, size_t len, unsigned int flags)
+ssize_t do_splice(struct file *in, loff_t *off_in, struct file *out,
+		  loff_t *off_out, size_t len, unsigned int flags)
 {
 	struct pipe_inode_info *ipipe;
 	struct pipe_inode_info *opipe;
 	loff_t offset;
-	long ret;
+	ssize_t ret;
 
 	if (unlikely(!(in->f_mode & FMODE_READ) ||
 		     !(out->f_mode & FMODE_WRITE)))
@@ -1397,14 +1398,14 @@ long do_splice(struct file *in, loff_t *off_in, struct file *out,
 	return ret;
 }
 
-static long __do_splice(struct file *in, loff_t __user *off_in,
-			struct file *out, loff_t __user *off_out,
-			size_t len, unsigned int flags)
+static ssize_t __do_splice(struct file *in, loff_t __user *off_in,
+			   struct file *out, loff_t __user *off_out,
+			   size_t len, unsigned int flags)
 {
 	struct pipe_inode_info *ipipe;
 	struct pipe_inode_info *opipe;
 	loff_t offset, *__off_in = NULL, *__off_out = NULL;
-	long ret;
+	ssize_t ret;
 
 	ipipe = get_pipe_info(in, true);
 	opipe = get_pipe_info(out, true);
@@ -1443,16 +1444,16 @@ static long __do_splice(struct file *in, loff_t __user *off_in,
 	return ret;
 }
 
-static int iter_to_pipe(struct iov_iter *from,
-			struct pipe_inode_info *pipe,
-			unsigned flags)
+static ssize_t iter_to_pipe(struct iov_iter *from,
+			    struct pipe_inode_info *pipe,
+			    unsigned int flags)
 {
 	struct pipe_buffer buf = {
 		.ops = &user_page_pipe_buf_ops,
 		.flags = flags
 	};
 	size_t total = 0;
-	int ret = 0;
+	ssize_t ret = 0;
 
 	while (iov_iter_count(from)) {
 		struct page *pages[16];
@@ -1501,8 +1502,8 @@ static int pipe_to_user(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
  * For lack of a better implementation, implement vmsplice() to userspace
  * as a simple copy of the pipes pages to the user iov.
  */
-static long vmsplice_to_user(struct file *file, struct iov_iter *iter,
-			     unsigned int flags)
+static ssize_t vmsplice_to_user(struct file *file, struct iov_iter *iter,
+				unsigned int flags)
 {
 	struct pipe_inode_info *pipe = get_pipe_info(file, true);
 	struct splice_desc sd = {
@@ -1510,7 +1511,7 @@ static long vmsplice_to_user(struct file *file, struct iov_iter *iter,
 		.flags = flags,
 		.u.data = iter
 	};
-	long ret = 0;
+	ssize_t ret = 0;
 
 	if (!pipe)
 		return -EBADF;
@@ -1534,11 +1535,11 @@ static long vmsplice_to_user(struct file *file, struct iov_iter *iter,
  * as splice-from-memory, where the regular splice is splice-from-file (or
  * to file). In both cases the output is a pipe, naturally.
  */
-static long vmsplice_to_pipe(struct file *file, struct iov_iter *iter,
-			     unsigned int flags)
+static ssize_t vmsplice_to_pipe(struct file *file, struct iov_iter *iter,
+				unsigned int flags)
 {
 	struct pipe_inode_info *pipe;
-	long ret = 0;
+	ssize_t ret = 0;
 	unsigned buf_flag = 0;
 
 	if (flags & SPLICE_F_GIFT)
@@ -1634,7 +1635,7 @@ SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in,
 		size_t, len, unsigned int, flags)
 {
 	struct fd in, out;
-	long error;
+	ssize_t error;
 
 	if (unlikely(!len))
 		return 0;
@@ -1648,7 +1649,7 @@ SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in,
 		out = fdget(fd_out);
 		if (out.file) {
 			error = __do_splice(in.file, off_in, out.file, off_out,
-						len, flags);
+					    len, flags);
 			fdput(out);
 		}
 		fdput(in);
@@ -1871,15 +1872,15 @@ retry:
 /*
  * Link contents of ipipe to opipe.
  */
-static int link_pipe(struct pipe_inode_info *ipipe,
-		     struct pipe_inode_info *opipe,
-		     size_t len, unsigned int flags)
+static ssize_t link_pipe(struct pipe_inode_info *ipipe,
+			 struct pipe_inode_info *opipe,
+			 size_t len, unsigned int flags)
 {
 	struct pipe_buffer *ibuf, *obuf;
 	unsigned int i_head, o_head;
 	unsigned int i_tail, o_tail;
 	unsigned int i_mask, o_mask;
-	int ret = 0;
+	ssize_t ret = 0;
 
 	/*
 	 * Potential ABBA deadlock, work around it by ordering lock
@@ -1962,11 +1963,12 @@ static int link_pipe(struct pipe_inode_info *ipipe,
  * The 'flags' used are the SPLICE_F_* variants, currently the only
  * applicable one is SPLICE_F_NONBLOCK.
  */
-long do_tee(struct file *in, struct file *out, size_t len, unsigned int flags)
+ssize_t do_tee(struct file *in, struct file *out, size_t len,
+	       unsigned int flags)
 {
 	struct pipe_inode_info *ipipe = get_pipe_info(in, true);
 	struct pipe_inode_info *opipe = get_pipe_info(out, true);
-	int ret = -EINVAL;
+	ssize_t ret = -EINVAL;
 
 	if (unlikely(!(in->f_mode & FMODE_READ) ||
 		     !(out->f_mode & FMODE_WRITE)))
@@ -2003,7 +2005,7 @@ long do_tee(struct file *in, struct file *out, size_t len, unsigned int flags)
 SYSCALL_DEFINE4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags)
 {
 	struct fd in, out;
-	int error;
+	ssize_t error;
 
 	if (unlikely(flags & ~SPLICE_F_ALL))
 		return -EINVAL;
diff --git a/include/linux/splice.h b/include/linux/splice.h
index 49532d5dda52..068a8e8ffd73 100644
--- a/include/linux/splice.h
+++ b/include/linux/splice.h
@@ -68,31 +68,30 @@ typedef int (splice_actor)(struct pipe_inode_info *, struct pipe_buffer *,
 typedef int (splice_direct_actor)(struct pipe_inode_info *,
 				  struct splice_desc *);
 
-extern ssize_t splice_from_pipe(struct pipe_inode_info *, struct file *,
-				loff_t *, size_t, unsigned int,
-				splice_actor *);
-extern ssize_t __splice_from_pipe(struct pipe_inode_info *,
-				  struct splice_desc *, splice_actor *);
-extern ssize_t splice_to_pipe(struct pipe_inode_info *,
-			      struct splice_pipe_desc *);
-extern ssize_t add_to_pipe(struct pipe_inode_info *,
-			      struct pipe_buffer *);
-long vfs_splice_read(struct file *in, loff_t *ppos,
-		     struct pipe_inode_info *pipe, size_t len,
-		     unsigned int flags);
+ssize_t splice_from_pipe(struct pipe_inode_info *pipe, struct file *out,
+			 loff_t *ppos, size_t len, unsigned int flags,
+			 splice_actor *actor);
+ssize_t __splice_from_pipe(struct pipe_inode_info *pipe,
+			   struct splice_desc *sd, splice_actor *actor);
+ssize_t splice_to_pipe(struct pipe_inode_info *pipe,
+			      struct splice_pipe_desc *spd);
+ssize_t add_to_pipe(struct pipe_inode_info *pipe, struct pipe_buffer *buf);
+ssize_t vfs_splice_read(struct file *in, loff_t *ppos,
+			struct pipe_inode_info *pipe, size_t len,
+			unsigned int flags);
 ssize_t splice_direct_to_actor(struct file *file, struct splice_desc *sd,
 			       splice_direct_actor *actor);
-long do_splice(struct file *in, loff_t *off_in, struct file *out,
-	       loff_t *off_out, size_t len, unsigned int flags);
-long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
-		      loff_t *opos, size_t len, unsigned int flags);
-long splice_file_range(struct file *in, loff_t *ppos, struct file *out,
-		       loff_t *opos, size_t len);
+ssize_t do_splice(struct file *in, loff_t *off_in, struct file *out,
+		  loff_t *off_out, size_t len, unsigned int flags);
+ssize_t do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
+			 loff_t *opos, size_t len, unsigned int flags);
+ssize_t splice_file_range(struct file *in, loff_t *ppos, struct file *out,
+			  loff_t *opos, size_t len);
 
-extern long do_tee(struct file *in, struct file *out, size_t len,
-		   unsigned int flags);
-extern ssize_t splice_to_socket(struct pipe_inode_info *pipe, struct file *out,
-				loff_t *ppos, size_t len, unsigned int flags);
+ssize_t do_tee(struct file *in, struct file *out, size_t len,
+	       unsigned int flags);
+ssize_t splice_to_socket(struct pipe_inode_info *pipe, struct file *out,
+			 loff_t *ppos, size_t len, unsigned int flags);
 
 /*
  * for dynamic pipe sizing
diff --git a/io_uring/splice.c b/io_uring/splice.c
index 7c4469e9540e..3b659cd23e9d 100644
--- a/io_uring/splice.c
+++ b/io_uring/splice.c
@@ -51,7 +51,7 @@ int io_tee(struct io_kiocb *req, unsigned int issue_flags)
 	struct file *out = sp->file_out;
 	unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED;
 	struct file *in;
-	long ret = 0;
+	ssize_t ret = 0;
 
 	WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK);
 
@@ -92,7 +92,7 @@ int io_splice(struct io_kiocb *req, unsigned int issue_flags)
 	unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED;
 	loff_t *poff_in, *poff_out;
 	struct file *in;
-	long ret = 0;
+	ssize_t ret = 0;
 
 	WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK);
 
-- 
cgit v1.2.3


From 705bcfcbde38b9dd4db00cd3deb0b98bddb0dd4a Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Tue, 12 Dec 2023 11:44:37 +0200
Subject: fs: use splice_copy_file_range() inline helper

generic_copy_file_range() is just a wrapper around splice_file_range(),
which caps the maximum copy length.

The only caller of splice_file_range(), namely __ceph_copy_file_range()
is already ready to cope with short copy.

Move the length capping into splice_file_range() and replace the exported
symbol generic_copy_file_range() with a simple inline helper.

Suggested-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/linux-fsdevel/20231204083849.GC32438@lst.de/
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Link: https://lore.kernel.org/r/20231212094440.250945-3-amir73il@gmail.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/ceph/file.c         |  4 ++--
 fs/fuse/file.c         |  5 +++--
 fs/nfs/nfs4file.c      |  5 +++--
 fs/read_write.c        | 34 ----------------------------------
 fs/smb/client/cifsfs.c |  5 +++--
 fs/splice.c            |  7 ++++---
 include/linux/fs.h     |  3 ---
 include/linux/splice.h |  7 +++++++
 8 files changed, 22 insertions(+), 48 deletions(-)

(limited to 'include')

diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index f11de6e1f1c1..d380d9dad0e0 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -3090,8 +3090,8 @@ static ssize_t ceph_copy_file_range(struct file *src_file, loff_t src_off,
 				     len, flags);
 
 	if (ret == -EOPNOTSUPP || ret == -EXDEV)
-		ret = generic_copy_file_range(src_file, src_off, dst_file,
-					      dst_off, len, flags);
+		ret = splice_copy_file_range(src_file, src_off, dst_file,
+					     dst_off, len);
 	return ret;
 }
 
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 1cdb6327511e..7d0860ef63d0 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -19,6 +19,7 @@
 #include <linux/uio.h>
 #include <linux/fs.h>
 #include <linux/filelock.h>
+#include <linux/splice.h>
 
 static int fuse_send_open(struct fuse_mount *fm, u64 nodeid,
 			  unsigned int open_flags, int opcode,
@@ -3193,8 +3194,8 @@ static ssize_t fuse_copy_file_range(struct file *src_file, loff_t src_off,
 				     len, flags);
 
 	if (ret == -EOPNOTSUPP || ret == -EXDEV)
-		ret = generic_copy_file_range(src_file, src_off, dst_file,
-					      dst_off, len, flags);
+		ret = splice_copy_file_range(src_file, src_off, dst_file,
+					     dst_off, len);
 	return ret;
 }
 
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 02788c3c85e5..e238abc78a13 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -10,6 +10,7 @@
 #include <linux/mount.h>
 #include <linux/nfs_fs.h>
 #include <linux/nfs_ssc.h>
+#include <linux/splice.h>
 #include "delegation.h"
 #include "internal.h"
 #include "iostat.h"
@@ -195,8 +196,8 @@ static ssize_t nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
 	ret = __nfs4_copy_file_range(file_in, pos_in, file_out, pos_out, count,
 				     flags);
 	if (ret == -EOPNOTSUPP || ret == -EXDEV)
-		ret = generic_copy_file_range(file_in, pos_in, file_out,
-					      pos_out, count, flags);
+		ret = splice_copy_file_range(file_in, pos_in, file_out,
+					     pos_out, count);
 	return ret;
 }
 
diff --git a/fs/read_write.c b/fs/read_write.c
index 7783b8522693..e3abf603eaaf 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1396,40 +1396,6 @@ COMPAT_SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd,
 }
 #endif
 
-/**
- * generic_copy_file_range - copy data between two files
- * @file_in:	file structure to read from
- * @pos_in:	file offset to read from
- * @file_out:	file structure to write data to
- * @pos_out:	file offset to write data to
- * @len:	amount of data to copy
- * @flags:	copy flags
- *
- * This is a generic filesystem helper to copy data from one file to another.
- * It has no constraints on the source or destination file owners - the files
- * can belong to different superblocks and different filesystem types. Short
- * copies are allowed.
- *
- * This should be called from the @file_out filesystem, as per the
- * ->copy_file_range() method.
- *
- * Returns the number of bytes copied or a negative error indicating the
- * failure.
- */
-
-ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in,
-				struct file *file_out, loff_t pos_out,
-				size_t len, unsigned int flags)
-{
-	/* May only be called from within ->copy_file_range() methods */
-	if (WARN_ON_ONCE(flags))
-		return -EINVAL;
-
-	return splice_file_range(file_in, &pos_in, file_out, &pos_out,
-				 min_t(size_t, len, MAX_RW_COUNT));
-}
-EXPORT_SYMBOL(generic_copy_file_range);
-
 /*
  * Performs necessary checks before doing a file copy
  *
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index ea3a7a668b45..ee461bf0ef63 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -25,6 +25,7 @@
 #include <linux/freezer.h>
 #include <linux/namei.h>
 #include <linux/random.h>
+#include <linux/splice.h>
 #include <linux/uuid.h>
 #include <linux/xattr.h>
 #include <uapi/linux/magic.h>
@@ -1362,8 +1363,8 @@ static ssize_t cifs_copy_file_range(struct file *src_file, loff_t off,
 	free_xid(xid);
 
 	if (rc == -EOPNOTSUPP || rc == -EXDEV)
-		rc = generic_copy_file_range(src_file, off, dst_file,
-					     destoff, len, flags);
+		rc = splice_copy_file_range(src_file, off, dst_file,
+					    destoff, len);
 	return rc;
 }
 
diff --git a/fs/splice.c b/fs/splice.c
index c39d1abf23c8..218e24b1ac40 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -1244,7 +1244,7 @@ EXPORT_SYMBOL(do_splice_direct);
  * @len:	number of bytes to splice
  *
  * Description:
- *    For use by generic_copy_file_range() and ->copy_file_range() methods.
+ *    For use by ->copy_file_range() methods.
  *    Like do_splice_direct(), but vfs_copy_file_range() already holds
  *    start_file_write() on @out file.
  *
@@ -1255,8 +1255,9 @@ ssize_t splice_file_range(struct file *in, loff_t *ppos, struct file *out,
 {
 	lockdep_assert(file_write_started(out));
 
-	return do_splice_direct_actor(in, ppos, out, opos, len, 0,
-				      splice_file_range_actor);
+	return do_splice_direct_actor(in, ppos, out, opos,
+				      min_t(size_t, len, MAX_RW_COUNT),
+				      0, splice_file_range_actor);
 }
 EXPORT_SYMBOL(splice_file_range);
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 04422a0eccdd..900d0cd55b50 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2090,9 +2090,6 @@ extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *);
 extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *);
 extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *,
 				   loff_t, size_t, unsigned int);
-extern ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in,
-				       struct file *file_out, loff_t pos_out,
-				       size_t len, unsigned int flags);
 int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 				    struct file *file_out, loff_t pos_out,
 				    loff_t *len, unsigned int remap_flags,
diff --git a/include/linux/splice.h b/include/linux/splice.h
index 068a8e8ffd73..9dec4861d09f 100644
--- a/include/linux/splice.h
+++ b/include/linux/splice.h
@@ -88,6 +88,13 @@ ssize_t do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
 ssize_t splice_file_range(struct file *in, loff_t *ppos, struct file *out,
 			  loff_t *opos, size_t len);
 
+static inline long splice_copy_file_range(struct file *in, loff_t pos_in,
+					  struct file *out, loff_t pos_out,
+					  size_t len)
+{
+	return splice_file_range(in, &pos_in, out, &pos_out, len);
+}
+
 ssize_t do_tee(struct file *in, struct file *out, size_t len,
 	       unsigned int flags);
 ssize_t splice_to_socket(struct pipe_inode_info *pipe, struct file *out,
-- 
cgit v1.2.3


From 36e28c42187c95eb148873ffb059bfdcb8cdb75b Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Tue, 12 Dec 2023 11:44:38 +0200
Subject: fsnotify: split fsnotify_perm() into two hooks

We would like to make changes to the fsnotify access permission hook -
add file range arguments and add the pre modify event.

In preparation for these changes, split the fsnotify_perm() hook into
fsnotify_open_perm() and fsnotify_file_perm().

This is needed for fanotify "pre content" events.

Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Link: https://lore.kernel.org/r/20231212094440.250945-4-amir73il@gmail.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/fsnotify.h | 34 +++++++++++++++++++---------------
 security/security.c      |  4 ++--
 2 files changed, 21 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index bcb6609b54b3..926bb4461b9e 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -100,29 +100,33 @@ static inline int fsnotify_file(struct file *file, __u32 mask)
 	return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH);
 }
 
-/* Simple call site for access decisions */
-static inline int fsnotify_perm(struct file *file, int mask)
+/*
+ * fsnotify_file_perm - permission hook before file access
+ */
+static inline int fsnotify_file_perm(struct file *file, int perm_mask)
 {
-	int ret;
-	__u32 fsnotify_mask = 0;
+	__u32 fsnotify_mask = FS_ACCESS_PERM;
 
-	if (!(mask & (MAY_READ | MAY_OPEN)))
+	if (!(perm_mask & MAY_READ))
 		return 0;
 
-	if (mask & MAY_OPEN) {
-		fsnotify_mask = FS_OPEN_PERM;
+	return fsnotify_file(file, fsnotify_mask);
+}
 
-		if (file->f_flags & __FMODE_EXEC) {
-			ret = fsnotify_file(file, FS_OPEN_EXEC_PERM);
+/*
+ * fsnotify_open_perm - permission hook before file open
+ */
+static inline int fsnotify_open_perm(struct file *file)
+{
+	int ret;
 
-			if (ret)
-				return ret;
-		}
-	} else if (mask & MAY_READ) {
-		fsnotify_mask = FS_ACCESS_PERM;
+	if (file->f_flags & __FMODE_EXEC) {
+		ret = fsnotify_file(file, FS_OPEN_EXEC_PERM);
+		if (ret)
+			return ret;
 	}
 
-	return fsnotify_file(file, fsnotify_mask);
+	return fsnotify_file(file, FS_OPEN_PERM);
 }
 
 /*
diff --git a/security/security.c b/security/security.c
index dcb3e7014f9b..d7f3703c5905 100644
--- a/security/security.c
+++ b/security/security.c
@@ -2586,7 +2586,7 @@ int security_file_permission(struct file *file, int mask)
 	if (ret)
 		return ret;
 
-	return fsnotify_perm(file, mask);
+	return fsnotify_file_perm(file, mask);
 }
 
 /**
@@ -2837,7 +2837,7 @@ int security_file_open(struct file *file)
 	if (ret)
 		return ret;
 
-	return fsnotify_perm(file, MAY_OPEN);
+	return fsnotify_open_perm(file);
 }
 
 /**
-- 
cgit v1.2.3


From cb383f06686734ef04daf63a4369566800717b7b Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Tue, 12 Dec 2023 11:44:39 +0200
Subject: fsnotify: assert that file_start_write() is not held in permission
 hooks

filesystem may be modified in the context of fanotify permission events
(e.g. by HSM service), so assert that sb freeze protection is not held.

If the assertion fails, then the following deadlock would be possible:

CPU0				CPU1			CPU2
-------------------------------------------------------------------------
file_start_write()#0
...
  fsnotify_perm()
    fanotify_get_response() =>	(read event and fill file)
				...
				...			freeze_super()
				...			  sb_wait_write()
				...
				vfs_write()
				  file_start_write()#1

This example demonstrates a use case of an hierarchical storage management
(HSM) service that uses fanotify permission events to fill the content of
a file before access, while a 3rd process starts fsfreeze.

This creates a circular dependeny:
  file_start_write()#0 => fanotify_get_response =>
    file_start_write()#1 =>
      sb_wait_write() =>
        file_end_write()#0

Where file_end_write()#0 can never be called and none of the threads can
make progress.

The assertion is checked for both MAY_READ and MAY_WRITE permission
hooks in preparation for a pre-modify permission event.

The assertion is not checked for an open permission event, because
do_open() takes mnt_want_write() in O_TRUNC case, meaning that it is not
safe to write to filesystem in the content of an open permission event.

Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Link: https://lore.kernel.org/r/20231212094440.250945-5-amir73il@gmail.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/fsnotify.h | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index 926bb4461b9e..0a9d6a8a747a 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -107,6 +107,13 @@ static inline int fsnotify_file_perm(struct file *file, int perm_mask)
 {
 	__u32 fsnotify_mask = FS_ACCESS_PERM;
 
+	/*
+	 * filesystem may be modified in the context of permission events
+	 * (e.g. by HSM filling a file on access), so sb freeze protection
+	 * must not be held.
+	 */
+	lockdep_assert_once(file_write_not_started(file));
+
 	if (!(perm_mask & MAY_READ))
 		return 0;
 
-- 
cgit v1.2.3


From d9e5d31084b024734e64307521414ef0ae1d5333 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Tue, 12 Dec 2023 11:44:40 +0200
Subject: fsnotify: optionally pass access range in file permission hooks

In preparation for pre-content permission events with file access range,
move fsnotify_file_perm() hook out of security_file_permission() and into
the callers.

Callers that have the access range information call the new hook
fsnotify_file_area_perm() with the access range.

Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Link: https://lore.kernel.org/r/20231212094440.250945-6-amir73il@gmail.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/open.c                |  4 ++++
 fs/read_write.c          | 10 ++++++++--
 fs/readdir.c             |  4 ++++
 fs/remap_range.c         |  8 +++++++-
 include/linux/fsnotify.h | 13 +++++++++++--
 security/security.c      |  8 +-------
 6 files changed, 35 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/fs/open.c b/fs/open.c
index 02dc608d40d8..d877228d5939 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -304,6 +304,10 @@ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 	if (ret)
 		return ret;
 
+	ret = fsnotify_file_area_perm(file, MAY_WRITE, &offset, len);
+	if (ret)
+		return ret;
+
 	if (S_ISFIFO(inode->i_mode))
 		return -ESPIPE;
 
diff --git a/fs/read_write.c b/fs/read_write.c
index e3abf603eaaf..d4c036e82b6c 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -354,6 +354,9 @@ out_putf:
 
 int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t count)
 {
+	int mask = read_write == READ ? MAY_READ : MAY_WRITE;
+	int ret;
+
 	if (unlikely((ssize_t) count < 0))
 		return -EINVAL;
 
@@ -371,8 +374,11 @@ int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t
 		}
 	}
 
-	return security_file_permission(file,
-				read_write == READ ? MAY_READ : MAY_WRITE);
+	ret = security_file_permission(file, mask);
+	if (ret)
+		return ret;
+
+	return fsnotify_file_area_perm(file, mask, ppos, count);
 }
 EXPORT_SYMBOL(rw_verify_area);
 
diff --git a/fs/readdir.c b/fs/readdir.c
index c8c46e294431..278bc0254732 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -96,6 +96,10 @@ int iterate_dir(struct file *file, struct dir_context *ctx)
 	if (res)
 		goto out;
 
+	res = fsnotify_file_perm(file, MAY_READ);
+	if (res)
+		goto out;
+
 	res = down_read_killable(&inode->i_rwsem);
 	if (res)
 		goto out;
diff --git a/fs/remap_range.c b/fs/remap_range.c
index 12131f2a6c9e..f8c1120b8311 100644
--- a/fs/remap_range.c
+++ b/fs/remap_range.c
@@ -102,7 +102,9 @@ static int generic_remap_checks(struct file *file_in, loff_t pos_in,
 static int remap_verify_area(struct file *file, loff_t pos, loff_t len,
 			     bool write)
 {
+	int mask = write ? MAY_WRITE : MAY_READ;
 	loff_t tmp;
+	int ret;
 
 	if (unlikely(pos < 0 || len < 0))
 		return -EINVAL;
@@ -110,7 +112,11 @@ static int remap_verify_area(struct file *file, loff_t pos, loff_t len,
 	if (unlikely(check_add_overflow(pos, len, &tmp)))
 		return -EINVAL;
 
-	return security_file_permission(file, write ? MAY_WRITE : MAY_READ);
+	ret = security_file_permission(file, mask);
+	if (ret)
+		return ret;
+
+	return fsnotify_file_area_perm(file, mask, &pos, len);
 }
 
 /*
diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index 0a9d6a8a747a..11e6434b8e71 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -101,9 +101,10 @@ static inline int fsnotify_file(struct file *file, __u32 mask)
 }
 
 /*
- * fsnotify_file_perm - permission hook before file access
+ * fsnotify_file_area_perm - permission hook before access to file range
  */
-static inline int fsnotify_file_perm(struct file *file, int perm_mask)
+static inline int fsnotify_file_area_perm(struct file *file, int perm_mask,
+					  const loff_t *ppos, size_t count)
 {
 	__u32 fsnotify_mask = FS_ACCESS_PERM;
 
@@ -120,6 +121,14 @@ static inline int fsnotify_file_perm(struct file *file, int perm_mask)
 	return fsnotify_file(file, fsnotify_mask);
 }
 
+/*
+ * fsnotify_file_perm - permission hook before file access
+ */
+static inline int fsnotify_file_perm(struct file *file, int perm_mask)
+{
+	return fsnotify_file_area_perm(file, perm_mask, NULL, 0);
+}
+
 /*
  * fsnotify_open_perm - permission hook before file open
  */
diff --git a/security/security.c b/security/security.c
index d7f3703c5905..2a7fc7881cbc 100644
--- a/security/security.c
+++ b/security/security.c
@@ -2580,13 +2580,7 @@ int security_kernfs_init_security(struct kernfs_node *kn_dir,
  */
 int security_file_permission(struct file *file, int mask)
 {
-	int ret;
-
-	ret = call_int_hook(file_permission, 0, file, mask);
-	if (ret)
-		return ret;
-
-	return fsnotify_file_perm(file, mask);
+	return call_int_hook(file_permission, 0, file, mask);
 }
 
 /**
-- 
cgit v1.2.3


From bf857ddd21d0bffc1edafc317e8e2ce0d6d5950c Mon Sep 17 00:00:00 2001
From: "Liam R. Howlett" <Liam.Howlett@oracle.com>
Date: Wed, 1 Nov 2023 13:16:20 -0400
Subject: maple_tree: move debug check to __mas_set_range()

__mas_set_range() was created to shortcut resetting the maple state and a
debug check was added to the caller (the vma iterator) to ensure the
internal maple state remains safe to use.  Move the debug check from the
vma iterator into the maple tree itself so other users do not incorrectly
use the advanced maple state modification.

Fallout from this change include a large amount of debug setup needed to
be moved to earlier in the header, and the maple_tree.h radix-tree test
code needed to move the inclusion of the header to after the atomic
define.  None of those changes have functional changes.

Link: https://lkml.kernel.org/r/20231101171629.3612299-4-Liam.Howlett@oracle.com
Signed-off-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Peng Zhang <zhangpeng.00@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/maple_tree.h                  | 255 ++++++++++++++--------------
 mm/internal.h                               |   2 -
 tools/testing/radix-tree/linux/maple_tree.h |   2 +-
 3 files changed, 130 insertions(+), 129 deletions(-)

(limited to 'include')

diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h
index a452dd8a1e5c..b5d5992578c9 100644
--- a/include/linux/maple_tree.h
+++ b/include/linux/maple_tree.h
@@ -557,6 +557,131 @@ static inline void mas_reset(struct ma_state *mas)
  */
 #define mas_for_each(__mas, __entry, __max) \
 	while (((__entry) = mas_find((__mas), (__max))) != NULL)
+
+#ifdef CONFIG_DEBUG_MAPLE_TREE
+enum mt_dump_format {
+	mt_dump_dec,
+	mt_dump_hex,
+};
+
+extern atomic_t maple_tree_tests_run;
+extern atomic_t maple_tree_tests_passed;
+
+void mt_dump(const struct maple_tree *mt, enum mt_dump_format format);
+void mas_dump(const struct ma_state *mas);
+void mas_wr_dump(const struct ma_wr_state *wr_mas);
+void mt_validate(struct maple_tree *mt);
+void mt_cache_shrink(void);
+#define MT_BUG_ON(__tree, __x) do {					\
+	atomic_inc(&maple_tree_tests_run);				\
+	if (__x) {							\
+		pr_info("BUG at %s:%d (%u)\n",				\
+		__func__, __LINE__, __x);				\
+		mt_dump(__tree, mt_dump_hex);				\
+		pr_info("Pass: %u Run:%u\n",				\
+			atomic_read(&maple_tree_tests_passed),		\
+			atomic_read(&maple_tree_tests_run));		\
+		dump_stack();						\
+	} else {							\
+		atomic_inc(&maple_tree_tests_passed);			\
+	}								\
+} while (0)
+
+#define MAS_BUG_ON(__mas, __x) do {					\
+	atomic_inc(&maple_tree_tests_run);				\
+	if (__x) {							\
+		pr_info("BUG at %s:%d (%u)\n",				\
+		__func__, __LINE__, __x);				\
+		mas_dump(__mas);					\
+		mt_dump((__mas)->tree, mt_dump_hex);			\
+		pr_info("Pass: %u Run:%u\n",				\
+			atomic_read(&maple_tree_tests_passed),		\
+			atomic_read(&maple_tree_tests_run));		\
+		dump_stack();						\
+	} else {							\
+		atomic_inc(&maple_tree_tests_passed);			\
+	}								\
+} while (0)
+
+#define MAS_WR_BUG_ON(__wrmas, __x) do {				\
+	atomic_inc(&maple_tree_tests_run);				\
+	if (__x) {							\
+		pr_info("BUG at %s:%d (%u)\n",				\
+		__func__, __LINE__, __x);				\
+		mas_wr_dump(__wrmas);					\
+		mas_dump((__wrmas)->mas);				\
+		mt_dump((__wrmas)->mas->tree, mt_dump_hex);		\
+		pr_info("Pass: %u Run:%u\n",				\
+			atomic_read(&maple_tree_tests_passed),		\
+			atomic_read(&maple_tree_tests_run));		\
+		dump_stack();						\
+	} else {							\
+		atomic_inc(&maple_tree_tests_passed);			\
+	}								\
+} while (0)
+
+#define MT_WARN_ON(__tree, __x)  ({					\
+	int ret = !!(__x);						\
+	atomic_inc(&maple_tree_tests_run);				\
+	if (ret) {							\
+		pr_info("WARN at %s:%d (%u)\n",				\
+		__func__, __LINE__, __x);				\
+		mt_dump(__tree, mt_dump_hex);				\
+		pr_info("Pass: %u Run:%u\n",				\
+			atomic_read(&maple_tree_tests_passed),		\
+			atomic_read(&maple_tree_tests_run));		\
+		dump_stack();						\
+	} else {							\
+		atomic_inc(&maple_tree_tests_passed);			\
+	}								\
+	unlikely(ret);							\
+})
+
+#define MAS_WARN_ON(__mas, __x) ({					\
+	int ret = !!(__x);						\
+	atomic_inc(&maple_tree_tests_run);				\
+	if (ret) {							\
+		pr_info("WARN at %s:%d (%u)\n",				\
+		__func__, __LINE__, __x);				\
+		mas_dump(__mas);					\
+		mt_dump((__mas)->tree, mt_dump_hex);			\
+		pr_info("Pass: %u Run:%u\n",				\
+			atomic_read(&maple_tree_tests_passed),		\
+			atomic_read(&maple_tree_tests_run));		\
+		dump_stack();						\
+	} else {							\
+		atomic_inc(&maple_tree_tests_passed);			\
+	}								\
+	unlikely(ret);							\
+})
+
+#define MAS_WR_WARN_ON(__wrmas, __x) ({					\
+	int ret = !!(__x);						\
+	atomic_inc(&maple_tree_tests_run);				\
+	if (ret) {							\
+		pr_info("WARN at %s:%d (%u)\n",				\
+		__func__, __LINE__, __x);				\
+		mas_wr_dump(__wrmas);					\
+		mas_dump((__wrmas)->mas);				\
+		mt_dump((__wrmas)->mas->tree, mt_dump_hex);		\
+		pr_info("Pass: %u Run:%u\n",				\
+			atomic_read(&maple_tree_tests_passed),		\
+			atomic_read(&maple_tree_tests_run));		\
+		dump_stack();						\
+	} else {							\
+		atomic_inc(&maple_tree_tests_passed);			\
+	}								\
+	unlikely(ret);							\
+})
+#else
+#define MT_BUG_ON(__tree, __x)		BUG_ON(__x)
+#define MAS_BUG_ON(__mas, __x)		BUG_ON(__x)
+#define MAS_WR_BUG_ON(__mas, __x)	BUG_ON(__x)
+#define MT_WARN_ON(__tree, __x)		WARN_ON(__x)
+#define MAS_WARN_ON(__mas, __x)		WARN_ON(__x)
+#define MAS_WR_WARN_ON(__mas, __x)	WARN_ON(__x)
+#endif /* CONFIG_DEBUG_MAPLE_TREE */
+
 /**
  * __mas_set_range() - Set up Maple Tree operation state to a sub-range of the
  * current location.
@@ -570,6 +695,9 @@ static inline void mas_reset(struct ma_state *mas)
 static inline void __mas_set_range(struct ma_state *mas, unsigned long start,
 		unsigned long last)
 {
+	/* Ensure the range starts within the current slot */
+	MAS_WARN_ON(mas, mas_is_active(mas) &&
+		   (mas->index > start || mas->last < start));
 	mas->index = start;
 	mas->last = last;
 }
@@ -587,8 +715,8 @@ static inline void __mas_set_range(struct ma_state *mas, unsigned long start,
 static inline
 void mas_set_range(struct ma_state *mas, unsigned long start, unsigned long last)
 {
-	__mas_set_range(mas, start, last);
 	mas->node = MAS_START;
+	__mas_set_range(mas, start, last);
 }
 
 /**
@@ -713,129 +841,4 @@ void *mt_next(struct maple_tree *mt, unsigned long index, unsigned long max);
 	for (__entry = mt_find(__tree, &(__index), __max); \
 		__entry; __entry = mt_find_after(__tree, &(__index), __max))
 
-
-#ifdef CONFIG_DEBUG_MAPLE_TREE
-enum mt_dump_format {
-	mt_dump_dec,
-	mt_dump_hex,
-};
-
-extern atomic_t maple_tree_tests_run;
-extern atomic_t maple_tree_tests_passed;
-
-void mt_dump(const struct maple_tree *mt, enum mt_dump_format format);
-void mas_dump(const struct ma_state *mas);
-void mas_wr_dump(const struct ma_wr_state *wr_mas);
-void mt_validate(struct maple_tree *mt);
-void mt_cache_shrink(void);
-#define MT_BUG_ON(__tree, __x) do {					\
-	atomic_inc(&maple_tree_tests_run);				\
-	if (__x) {							\
-		pr_info("BUG at %s:%d (%u)\n",				\
-		__func__, __LINE__, __x);				\
-		mt_dump(__tree, mt_dump_hex);				\
-		pr_info("Pass: %u Run:%u\n",				\
-			atomic_read(&maple_tree_tests_passed),		\
-			atomic_read(&maple_tree_tests_run));		\
-		dump_stack();						\
-	} else {							\
-		atomic_inc(&maple_tree_tests_passed);			\
-	}								\
-} while (0)
-
-#define MAS_BUG_ON(__mas, __x) do {					\
-	atomic_inc(&maple_tree_tests_run);				\
-	if (__x) {							\
-		pr_info("BUG at %s:%d (%u)\n",				\
-		__func__, __LINE__, __x);				\
-		mas_dump(__mas);					\
-		mt_dump((__mas)->tree, mt_dump_hex);			\
-		pr_info("Pass: %u Run:%u\n",				\
-			atomic_read(&maple_tree_tests_passed),		\
-			atomic_read(&maple_tree_tests_run));		\
-		dump_stack();						\
-	} else {							\
-		atomic_inc(&maple_tree_tests_passed);			\
-	}								\
-} while (0)
-
-#define MAS_WR_BUG_ON(__wrmas, __x) do {				\
-	atomic_inc(&maple_tree_tests_run);				\
-	if (__x) {							\
-		pr_info("BUG at %s:%d (%u)\n",				\
-		__func__, __LINE__, __x);				\
-		mas_wr_dump(__wrmas);					\
-		mas_dump((__wrmas)->mas);				\
-		mt_dump((__wrmas)->mas->tree, mt_dump_hex);		\
-		pr_info("Pass: %u Run:%u\n",				\
-			atomic_read(&maple_tree_tests_passed),		\
-			atomic_read(&maple_tree_tests_run));		\
-		dump_stack();						\
-	} else {							\
-		atomic_inc(&maple_tree_tests_passed);			\
-	}								\
-} while (0)
-
-#define MT_WARN_ON(__tree, __x)  ({					\
-	int ret = !!(__x);						\
-	atomic_inc(&maple_tree_tests_run);				\
-	if (ret) {							\
-		pr_info("WARN at %s:%d (%u)\n",				\
-		__func__, __LINE__, __x);				\
-		mt_dump(__tree, mt_dump_hex);				\
-		pr_info("Pass: %u Run:%u\n",				\
-			atomic_read(&maple_tree_tests_passed),		\
-			atomic_read(&maple_tree_tests_run));		\
-		dump_stack();						\
-	} else {							\
-		atomic_inc(&maple_tree_tests_passed);			\
-	}								\
-	unlikely(ret);							\
-})
-
-#define MAS_WARN_ON(__mas, __x) ({					\
-	int ret = !!(__x);						\
-	atomic_inc(&maple_tree_tests_run);				\
-	if (ret) {							\
-		pr_info("WARN at %s:%d (%u)\n",				\
-		__func__, __LINE__, __x);				\
-		mas_dump(__mas);					\
-		mt_dump((__mas)->tree, mt_dump_hex);			\
-		pr_info("Pass: %u Run:%u\n",				\
-			atomic_read(&maple_tree_tests_passed),		\
-			atomic_read(&maple_tree_tests_run));		\
-		dump_stack();						\
-	} else {							\
-		atomic_inc(&maple_tree_tests_passed);			\
-	}								\
-	unlikely(ret);							\
-})
-
-#define MAS_WR_WARN_ON(__wrmas, __x) ({					\
-	int ret = !!(__x);						\
-	atomic_inc(&maple_tree_tests_run);				\
-	if (ret) {							\
-		pr_info("WARN at %s:%d (%u)\n",				\
-		__func__, __LINE__, __x);				\
-		mas_wr_dump(__wrmas);					\
-		mas_dump((__wrmas)->mas);				\
-		mt_dump((__wrmas)->mas->tree, mt_dump_hex);		\
-		pr_info("Pass: %u Run:%u\n",				\
-			atomic_read(&maple_tree_tests_passed),		\
-			atomic_read(&maple_tree_tests_run));		\
-		dump_stack();						\
-	} else {							\
-		atomic_inc(&maple_tree_tests_passed);			\
-	}								\
-	unlikely(ret);							\
-})
-#else
-#define MT_BUG_ON(__tree, __x)		BUG_ON(__x)
-#define MAS_BUG_ON(__mas, __x)		BUG_ON(__x)
-#define MAS_WR_BUG_ON(__mas, __x)	BUG_ON(__x)
-#define MT_WARN_ON(__tree, __x)		WARN_ON(__x)
-#define MAS_WARN_ON(__mas, __x)		WARN_ON(__x)
-#define MAS_WR_WARN_ON(__mas, __x)	WARN_ON(__x)
-#endif /* CONFIG_DEBUG_MAPLE_TREE */
-
 #endif /*_LINUX_MAPLE_TREE_H */
diff --git a/mm/internal.h b/mm/internal.h
index 2bc9ff8db393..0005b8adbd5c 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1135,8 +1135,6 @@ static inline bool vma_soft_dirty_enabled(struct vm_area_struct *vma)
 static inline void vma_iter_config(struct vma_iterator *vmi,
 		unsigned long index, unsigned long last)
 {
-	MAS_BUG_ON(&vmi->mas, vmi->mas.node != MAS_START &&
-		   (vmi->mas.index > index || vmi->mas.last < index));
 	__mas_set_range(&vmi->mas, index, last - 1);
 }
 
diff --git a/tools/testing/radix-tree/linux/maple_tree.h b/tools/testing/radix-tree/linux/maple_tree.h
index 7d8d1f445b89..06c89bdcc515 100644
--- a/tools/testing/radix-tree/linux/maple_tree.h
+++ b/tools/testing/radix-tree/linux/maple_tree.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0+ */
 #define atomic_t int32_t
-#include "../../../../include/linux/maple_tree.h"
 #define atomic_inc(x) uatomic_inc(x)
 #define atomic_read(x) uatomic_read(x)
 #define atomic_set(x, y) do {} while (0)
 #define U8_MAX UCHAR_MAX
+#include "../../../../include/linux/maple_tree.h"
-- 
cgit v1.2.3


From 31c532a8af57513228c2b12d281104198ff412b8 Mon Sep 17 00:00:00 2001
From: "Liam R. Howlett" <Liam.Howlett@oracle.com>
Date: Wed, 1 Nov 2023 13:16:21 -0400
Subject: maple_tree: add end of node tracking to the maple state

Analysis of the mas_for_each() iteration showed that there is a
significant time spent finding the end of a node.  This time can be
greatly reduced if the end of the node is cached in the maple state.  Care
must be taken to update & invalidate as necessary.

Link: https://lkml.kernel.org/r/20231101171629.3612299-5-Liam.Howlett@oracle.com
Signed-off-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Peng Zhang <zhangpeng.00@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/maple_tree.h       | 1 +
 lib/maple_tree.c                 | 7 +++++++
 tools/testing/radix-tree/maple.c | 1 +
 3 files changed, 9 insertions(+)

(limited to 'include')

diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h
index b5d5992578c9..0b82efe0cf1e 100644
--- a/include/linux/maple_tree.h
+++ b/include/linux/maple_tree.h
@@ -393,6 +393,7 @@ struct ma_state {
 	unsigned char depth;		/* depth of tree descent during write */
 	unsigned char offset;
 	unsigned char mas_flags;
+	unsigned char end;		/* The end of the node */
 };
 
 struct ma_wr_state {
diff --git a/lib/maple_tree.c b/lib/maple_tree.c
index 8d379d34ea0a..ea0a36341fed 100644
--- a/lib/maple_tree.c
+++ b/lib/maple_tree.c
@@ -2841,6 +2841,7 @@ next:
 			goto dead_node;
 	} while (!ma_is_leaf(type));
 
+	mas->end = end;
 	mas->offset = offset;
 	mas->index = min;
 	mas->last = max;
@@ -3507,6 +3508,7 @@ static noinline_for_kasan int mas_commit_b_node(struct ma_wr_state *wr_mas,
 	mas_replace_node(wr_mas->mas, old_enode);
 reuse_node:
 	mas_update_gap(wr_mas->mas);
+	wr_mas->mas->end = b_end;
 	return 1;
 }
 
@@ -4010,6 +4012,7 @@ done:
 	}
 	trace_ma_write(__func__, mas, 0, wr_mas->entry);
 	mas_update_gap(mas);
+	mas->end = new_end;
 	return true;
 }
 
@@ -4190,6 +4193,7 @@ static inline bool mas_wr_append(struct ma_wr_state *wr_mas,
 	if (!wr_mas->content || !wr_mas->entry)
 		mas_update_gap(mas);
 
+	mas->end = new_end;
 	trace_ma_write(__func__, mas, new_end, wr_mas->entry);
 	return  true;
 }
@@ -4428,6 +4432,7 @@ static inline int mas_prev_node(struct ma_state *mas, unsigned long min)
 	if (unlikely(mte_dead_node(mas->node)))
 		return 1;
 
+	mas->end = mas->offset;
 	return 0;
 
 no_entry:
@@ -5074,6 +5079,7 @@ int mas_empty_area(struct ma_state *mas, unsigned long min,
 	if (mas->index < min)
 		mas->index = min;
 	mas->last = mas->index + size - 1;
+	mas->end = mas_data_end(mas);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(mas_empty_area);
@@ -5134,6 +5140,7 @@ int mas_empty_area_rev(struct ma_state *mas, unsigned long min,
 		mas->last = max;
 
 	mas->index = mas->last - size + 1;
+	mas->end = mas_data_end(mas);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(mas_empty_area_rev);
diff --git a/tools/testing/radix-tree/maple.c b/tools/testing/radix-tree/maple.c
index cb5358674521..7095fb0ec026 100644
--- a/tools/testing/radix-tree/maple.c
+++ b/tools/testing/radix-tree/maple.c
@@ -945,6 +945,7 @@ retry:
 		goto retry;
 	}
 
+	mas->end = mas_data_end(mas);
 	return ret;
 
 not_found:
-- 
cgit v1.2.3


From 067311d33e650adfe7ae23765959ddcc1ba18510 Mon Sep 17 00:00:00 2001
From: "Liam R. Howlett" <Liam.Howlett@oracle.com>
Date: Wed, 1 Nov 2023 13:16:25 -0400
Subject: maple_tree: separate ma_state node from status

The maple tree node is overloaded to keep status as well as the active
node.  This, unfortunately, results in a re-walk on underflow or overflow.
Since the maple state has room, the status can be placed in its own enum
in the structure.  Once an underflow/overflow is detected, certain modes
can restore the status to active and others may need to re-walk just that
one node to see the entry.

The status being an enum has the benefit of detecting unhandled status in
switch statements.

[Liam.Howlett@oracle.com: fix comments about MAS_*]
  Link: https://lkml.kernel.org/r/20231106154124.614247-1-Liam.Howlett@oracle.com
[Liam.Howlett@oracle.com: update forking to separate maple state and node]
  Link: https://lkml.kernel.org/r/20231106154551.615042-1-Liam.Howlett@oracle.com
[Liam.Howlett@oracle.com: fix mas_prev() state separation code]
  Link: https://lkml.kernel.org/r/20231207193319.4025462-1-Liam.Howlett@oracle.com
Link: https://lkml.kernel.org/r/20231101171629.3612299-9-Liam.Howlett@oracle.com
Signed-off-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Peng Zhang <zhangpeng.00@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/maple_tree.h       |  87 ++++----
 include/linux/mm_types.h         |   3 +-
 lib/maple_tree.c                 | 459 +++++++++++++++++++++++----------------
 lib/test_maple_tree.c            | 189 ++++++++--------
 mm/internal.h                    |   8 +-
 tools/testing/radix-tree/maple.c |  26 ++-
 6 files changed, 445 insertions(+), 327 deletions(-)

(limited to 'include')

diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h
index 0b82efe0cf1e..4dd668f7b111 100644
--- a/include/linux/maple_tree.h
+++ b/include/linux/maple_tree.h
@@ -349,6 +349,36 @@ static inline bool mtree_empty(const struct maple_tree *mt)
 
 /* Advanced API */
 
+/*
+ * Maple State Status
+ * ma_active means the maple state is pointing to a node and offset and can
+ * continue operating on the tree.
+ * ma_start means we have not searched the tree.
+ * ma_root means we have searched the tree and the entry we found lives in
+ * the root of the tree (ie it has index 0, length 1 and is the only entry in
+ * the tree).
+ * ma_none means we have searched the tree and there is no node in the
+ * tree for this entry.  For example, we searched for index 1 in an empty
+ * tree.  Or we have a tree which points to a full leaf node and we
+ * searched for an entry which is larger than can be contained in that
+ * leaf node.
+ * ma_pause means the data within the maple state may be stale, restart the
+ * operation
+ * ma_overflow means the search has reached the upper limit of the search
+ * ma_underflow means the search has reached the lower limit of the search
+ * ma_error means there was an error, check the node for the error number.
+ */
+enum maple_status {
+	ma_active,
+	ma_start,
+	ma_root,
+	ma_none,
+	ma_pause,
+	ma_overflow,
+	ma_underflow,
+	ma_error,
+};
+
 /*
  * The maple state is defined in the struct ma_state and is used to keep track
  * of information during operations, and even between operations when using the
@@ -381,6 +411,13 @@ static inline bool mtree_empty(const struct maple_tree *mt)
  * When returning a value the maple state index and last respectively contain
  * the start and end of the range for the entry.  Ranges are inclusive in the
  * Maple Tree.
+ *
+ * The status of the state is used to determine how the next action should treat
+ * the state.  For instance, if the status is ma_start then the next action
+ * should start at the root of the tree and walk down.  If the status is
+ * ma_pause then the node may be stale data and should be discarded.  If the
+ * status is ma_overflow, then the last action hit the upper limit.
+ *
  */
 struct ma_state {
 	struct maple_tree *tree;	/* The tree we're operating in */
@@ -390,6 +427,7 @@ struct ma_state {
 	unsigned long min;		/* The minimum index of this node - implied pivot min */
 	unsigned long max;		/* The maximum index of this node - implied pivot max */
 	struct maple_alloc *alloc;	/* Allocated nodes for this operation */
+	enum maple_status status;	/* The status of the state (active, start, none, etc) */
 	unsigned char depth;		/* depth of tree descent during write */
 	unsigned char offset;
 	unsigned char mas_flags;
@@ -416,28 +454,12 @@ struct ma_wr_state {
 		spin_lock_nested(&((mas)->tree->ma_lock), subclass)
 #define mas_unlock(mas)         spin_unlock(&((mas)->tree->ma_lock))
 
-
 /*
  * Special values for ma_state.node.
- * MAS_START means we have not searched the tree.
- * MAS_ROOT means we have searched the tree and the entry we found lives in
- * the root of the tree (ie it has index 0, length 1 and is the only entry in
- * the tree).
- * MAS_NONE means we have searched the tree and there is no node in the
- * tree for this entry.  For example, we searched for index 1 in an empty
- * tree.  Or we have a tree which points to a full leaf node and we
- * searched for an entry which is larger than can be contained in that
- * leaf node.
  * MA_ERROR represents an errno.  After dropping the lock and attempting
  * to resolve the error, the walk would have to be restarted from the
  * top of the tree as the tree may have been modified.
  */
-#define MAS_START	((struct maple_enode *)1UL)
-#define MAS_ROOT	((struct maple_enode *)5UL)
-#define MAS_NONE	((struct maple_enode *)9UL)
-#define MAS_PAUSE	((struct maple_enode *)17UL)
-#define MAS_OVERFLOW	((struct maple_enode *)33UL)
-#define MAS_UNDERFLOW	((struct maple_enode *)65UL)
 #define MA_ERROR(err) \
 		((struct maple_enode *)(((unsigned long)err << 2) | 2UL))
 
@@ -446,7 +468,8 @@ struct ma_wr_state {
 		.tree = mt,						\
 		.index = first,						\
 		.last = end,						\
-		.node = MAS_START,					\
+		.node = NULL,						\
+		.status = ma_start,					\
 		.min = 0,						\
 		.max = ULONG_MAX,					\
 		.alloc = NULL,						\
@@ -477,7 +500,6 @@ void *mas_find_range(struct ma_state *mas, unsigned long max);
 void *mas_find_rev(struct ma_state *mas, unsigned long min);
 void *mas_find_range_rev(struct ma_state *mas, unsigned long max);
 int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp);
-bool mas_is_err(struct ma_state *mas);
 
 bool mas_nomem(struct ma_state *mas, gfp_t gfp);
 void mas_pause(struct ma_state *mas);
@@ -506,28 +528,18 @@ static inline void mas_init(struct ma_state *mas, struct maple_tree *tree,
 	mas->tree = tree;
 	mas->index = mas->last = addr;
 	mas->max = ULONG_MAX;
-	mas->node = MAS_START;
+	mas->status = ma_start;
+	mas->node = NULL;
 }
 
-/* Checks if a mas has not found anything */
-static inline bool mas_is_none(const struct ma_state *mas)
-{
-	return mas->node == MAS_NONE;
-}
-
-/* Checks if a mas has been paused */
-static inline bool mas_is_paused(const struct ma_state *mas)
+static inline bool mas_is_active(struct ma_state *mas)
 {
-	return mas->node == MAS_PAUSE;
+	return mas->status == ma_active;
 }
 
-/* Check if the mas is pointing to a node or not */
-static inline bool mas_is_active(struct ma_state *mas)
+static inline bool mas_is_err(struct ma_state *mas)
 {
-	if ((unsigned long)mas->node >= MAPLE_RESERVED_RANGE)
-		return true;
-
-	return false;
+	return mas->status == ma_error;
 }
 
 /**
@@ -540,9 +552,10 @@ static inline bool mas_is_active(struct ma_state *mas)
  *
  * Context: Any context.
  */
-static inline void mas_reset(struct ma_state *mas)
+static __always_inline void mas_reset(struct ma_state *mas)
 {
-	mas->node = MAS_START;
+	mas->status = ma_start;
+	mas->node = NULL;
 }
 
 /**
@@ -716,7 +729,7 @@ static inline void __mas_set_range(struct ma_state *mas, unsigned long start,
 static inline
 void mas_set_range(struct ma_state *mas, unsigned long start, unsigned long last)
 {
-	mas->node = MAS_START;
+	mas_reset(mas);
 	__mas_set_range(mas, start, last);
 }
 
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index ef18d2b25378..a66534c78c4d 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -1071,7 +1071,8 @@ struct vma_iterator {
 		.mas = {						\
 			.tree = &(__mm)->mm_mt,				\
 			.index = __addr,				\
-			.node = MAS_START,				\
+			.node = NULL,					\
+			.status = ma_start,				\
 		},							\
 	}
 
diff --git a/lib/maple_tree.c b/lib/maple_tree.c
index f0d2aea91351..187a9796188e 100644
--- a/lib/maple_tree.c
+++ b/lib/maple_tree.c
@@ -249,40 +249,40 @@ static __always_inline bool mt_is_reserved(const void *entry)
 		xa_is_internal(entry);
 }
 
-static inline void mas_set_err(struct ma_state *mas, long err)
+static __always_inline void mas_set_err(struct ma_state *mas, long err)
 {
 	mas->node = MA_ERROR(err);
+	mas->status = ma_error;
 }
 
-static inline bool mas_is_ptr(const struct ma_state *mas)
+static __always_inline bool mas_is_ptr(const struct ma_state *mas)
 {
-	return mas->node == MAS_ROOT;
+	return mas->status == ma_root;
 }
 
-static inline bool mas_is_start(const struct ma_state *mas)
+static __always_inline bool mas_is_start(const struct ma_state *mas)
 {
-	return mas->node == MAS_START;
+	return mas->status == ma_start;
 }
 
-bool mas_is_err(struct ma_state *mas)
+static __always_inline bool mas_is_none(const struct ma_state *mas)
 {
-	return xa_is_err(mas->node);
+	return mas->status == ma_none;
 }
 
-static __always_inline bool mas_is_overflow(struct ma_state *mas)
+static __always_inline bool mas_is_paused(const struct ma_state *mas)
 {
-	if (unlikely(mas->node == MAS_OVERFLOW))
-		return true;
-
-	return false;
+	return mas->status == ma_pause;
 }
 
-static __always_inline bool mas_is_underflow(struct ma_state *mas)
+static __always_inline bool mas_is_overflow(struct ma_state *mas)
 {
-	if (unlikely(mas->node == MAS_UNDERFLOW))
-		return true;
+	return mas->status == ma_overflow;
+}
 
-	return false;
+static inline bool mas_is_underflow(struct ma_state *mas)
+{
+	return mas->status == ma_underflow;
 }
 
 static inline bool mas_searchable(struct ma_state *mas)
@@ -1274,6 +1274,7 @@ static inline void mas_alloc_nodes(struct ma_state *mas, gfp_t gfp)
 	if (mas->mas_flags & MA_STATE_PREALLOC) {
 		if (allocated)
 			return;
+		BUG_ON(!allocated);
 		WARN_ON(!allocated);
 	}
 
@@ -1379,14 +1380,14 @@ static void mas_node_count(struct ma_state *mas, int count)
  * mas_start() - Sets up maple state for operations.
  * @mas: The maple state.
  *
- * If mas->node == MAS_START, then set the min, max and depth to
+ * If mas->status == mas_start, then set the min, max and depth to
  * defaults.
  *
  * Return:
- * - If mas->node is an error or not MAS_START, return NULL.
- * - If it's an empty tree:     NULL & mas->node == MAS_NONE
- * - If it's a single entry:    The entry & mas->node == MAS_ROOT
- * - If it's a tree:            NULL & mas->node == safe root node.
+ * - If mas->node is an error or not mas_start, return NULL.
+ * - If it's an empty tree:     NULL & mas->status == ma_none
+ * - If it's a single entry:    The entry & mas->status == mas_root
+ * - If it's a tree:            NULL & mas->status == safe root node.
  */
 static inline struct maple_enode *mas_start(struct ma_state *mas)
 {
@@ -1402,6 +1403,7 @@ retry:
 		/* Tree with nodes */
 		if (likely(xa_is_node(root))) {
 			mas->depth = 1;
+			mas->status = ma_active;
 			mas->node = mte_safe_root(root);
 			mas->offset = 0;
 			if (mte_dead_node(mas->node))
@@ -1412,13 +1414,14 @@ retry:
 
 		/* empty tree */
 		if (unlikely(!root)) {
-			mas->node = MAS_NONE;
+			mas->node = NULL;
+			mas->status = ma_none;
 			mas->offset = MAPLE_NODE_SLOTS;
 			return NULL;
 		}
 
 		/* Single entry tree */
-		mas->node = MAS_ROOT;
+		mas->status = ma_root;
 		mas->offset = MAPLE_NODE_SLOTS;
 
 		/* Single entry tree. */
@@ -2225,19 +2228,21 @@ static inline bool mas_next_sibling(struct ma_state *mas)
 }
 
 /*
- * mte_node_or_node() - Return the encoded node or MAS_NONE.
+ * mte_node_or_none() - Set the enode and state.
  * @enode: The encoded maple node.
  *
- * Shorthand to avoid setting %NULLs in the tree or maple_subtree_state.
- *
- * Return: @enode or MAS_NONE
+ * Set the node to the enode and the status.
  */
-static inline struct maple_enode *mte_node_or_none(struct maple_enode *enode)
+static inline void mas_node_or_none(struct ma_state *mas,
+		struct maple_enode *enode)
 {
-	if (enode)
-		return enode;
-
-	return ma_enode_ptr(MAS_NONE);
+	if (enode) {
+		mas->node = enode;
+		mas->status = ma_active;
+	} else {
+		mas->node = NULL;
+		mas->status = ma_none;
+	}
 }
 
 /*
@@ -2557,13 +2562,15 @@ static inline void mast_set_split_parents(struct maple_subtree_state *mast,
  * The node will either be RCU freed or pushed back on the maple state.
  */
 static inline void mas_topiary_node(struct ma_state *mas,
-		struct maple_enode *enode, bool in_rcu)
+		struct ma_state *tmp_mas, bool in_rcu)
 {
 	struct maple_node *tmp;
+	struct maple_enode *enode;
 
-	if (enode == MAS_NONE)
+	if (mas_is_none(tmp_mas))
 		return;
 
+	enode = tmp_mas->node;
 	tmp = mte_to_node(enode);
 	mte_set_node_dead(enode);
 	if (in_rcu)
@@ -2603,8 +2610,8 @@ static inline void mas_topiary_replace(struct ma_state *mas,
 	/* Update the parent pointers in the tree */
 	tmp[0] = *mas;
 	tmp[0].offset = 0;
-	tmp[1].node = MAS_NONE;
-	tmp[2].node = MAS_NONE;
+	tmp[1].status = ma_none;
+	tmp[2].status = ma_none;
 	while (!mte_is_leaf(tmp[0].node)) {
 		n = 0;
 		for (i = 0; i < 3; i++) {
@@ -2624,7 +2631,7 @@ static inline void mas_topiary_replace(struct ma_state *mas,
 			break;
 
 		while (n < 3)
-			tmp_next[n++].node = MAS_NONE;
+			tmp_next[n++].status = ma_none;
 
 		for (i = 0; i < 3; i++)
 			tmp[i] = tmp_next[i];
@@ -2637,8 +2644,8 @@ static inline void mas_topiary_replace(struct ma_state *mas,
 	tmp[0] = *mas;
 	tmp[0].offset = 0;
 	tmp[0].node = old_enode;
-	tmp[1].node = MAS_NONE;
-	tmp[2].node = MAS_NONE;
+	tmp[1].status = ma_none;
+	tmp[2].status = ma_none;
 	in_rcu = mt_in_rcu(mas->tree);
 	do {
 		n = 0;
@@ -2653,7 +2660,7 @@ static inline void mas_topiary_replace(struct ma_state *mas,
 				if ((tmp_next[n].min >= tmp_next->index) &&
 				    (tmp_next[n].max <= tmp_next->last)) {
 					mat_add(&subtrees, tmp_next[n].node);
-					tmp_next[n].node = MAS_NONE;
+					tmp_next[n].status = ma_none;
 				} else {
 					n++;
 				}
@@ -2664,16 +2671,16 @@ static inline void mas_topiary_replace(struct ma_state *mas,
 			break;
 
 		while (n < 3)
-			tmp_next[n++].node = MAS_NONE;
+			tmp_next[n++].status = ma_none;
 
 		for (i = 0; i < 3; i++) {
-			mas_topiary_node(mas, tmp[i].node, in_rcu);
+			mas_topiary_node(mas, &tmp[i], in_rcu);
 			tmp[i] = tmp_next[i];
 		}
 	} while (!mte_is_leaf(tmp[0].node));
 
 	for (i = 0; i < 3; i++)
-		mas_topiary_node(mas, tmp[i].node, in_rcu);
+		mas_topiary_node(mas, &tmp[i], in_rcu);
 
 	mas_mat_destroy(mas, &subtrees);
 }
@@ -2712,9 +2719,9 @@ static inline void mast_cp_to_nodes(struct maple_subtree_state *mast,
 {
 	bool new_lmax = true;
 
-	mast->l->node = mte_node_or_none(left);
-	mast->m->node = mte_node_or_none(middle);
-	mast->r->node = mte_node_or_none(right);
+	mas_node_or_none(mast->l, left);
+	mas_node_or_none(mast->m, middle);
+	mas_node_or_none(mast->r, right);
 
 	mast->l->min = mast->orig_l->min;
 	if (split == mast->bn->b_end) {
@@ -2894,7 +2901,7 @@ static int mas_spanning_rebalance(struct ma_state *mas,
 	mast->l = &l_mas;
 	mast->m = &m_mas;
 	mast->r = &r_mas;
-	l_mas.node = r_mas.node = m_mas.node = MAS_NONE;
+	l_mas.status = r_mas.status = m_mas.status = ma_none;
 
 	/* Check if this is not root and has sufficient data.  */
 	if (((mast->orig_l->min != 0) || (mast->orig_r->max != ULONG_MAX)) &&
@@ -3421,7 +3428,6 @@ static int mas_split(struct ma_state *mas, struct maple_big_node *b_node)
 		/* Try to push left. */
 		if (mas_push_data(mas, height, &mast, true))
 			break;
-
 		/* Try to push right. */
 		if (mas_push_data(mas, height, &mast, false))
 			break;
@@ -3537,6 +3543,7 @@ static inline int mas_root_expand(struct ma_state *mas, void *entry)
 	slots = ma_slots(node, type);
 	node->parent = ma_parent_ptr(mas_tree_parent(mas));
 	mas->node = mt_mk_node(node, type);
+	mas->status = ma_active;
 
 	if (mas->index) {
 		if (contents) {
@@ -3569,7 +3576,7 @@ static inline void mas_store_root(struct ma_state *mas, void *entry)
 		mas_root_expand(mas, entry);
 	else {
 		rcu_assign_pointer(mas->tree->ma_root, entry);
-		mas->node = MAS_START;
+		mas->status = ma_start;
 	}
 }
 
@@ -3801,7 +3808,7 @@ static inline int mas_new_root(struct ma_state *mas, void *entry)
 		mas->depth = 0;
 		mas_set_height(mas);
 		rcu_assign_pointer(mas->tree->ma_root, entry);
-		mas->node = MAS_START;
+		mas->status = ma_start;
 		goto done;
 	}
 
@@ -3814,6 +3821,7 @@ static inline int mas_new_root(struct ma_state *mas, void *entry)
 	slots = ma_slots(node, type);
 	node->parent = ma_parent_ptr(mas_tree_parent(mas));
 	mas->node = mt_mk_node(node, type);
+	mas->status = ma_active;
 	rcu_assign_pointer(slots[0], entry);
 	pivots[0] = mas->last;
 	mas->depth = 1;
@@ -4367,11 +4375,13 @@ static __always_inline bool mas_rewalk_if_dead(struct ma_state *mas,
 
 /*
  * mas_prev_node() - Find the prev non-null entry at the same level in the
- * tree.  The prev value will be mas->node[mas->offset] or MAS_NONE.
+ * tree.  The prev value will be mas->node[mas->offset] or the status will be
+ * ma_none.
  * @mas: The maple state
  * @min: The lower limit to search
  *
- * The prev node value will be mas->node[mas->offset] or MAS_NONE.
+ * The prev node value will be mas->node[mas->offset] or the status will be
+ * ma_none.
  * Return: 1 if the node is dead, 0 otherwise.
  */
 static int mas_prev_node(struct ma_state *mas, unsigned long min)
@@ -4441,7 +4451,7 @@ no_entry:
 	if (unlikely(ma_dead_node(node)))
 		return 1;
 
-	mas->node = MAS_NONE;
+	mas->status = ma_underflow;
 	return 0;
 }
 
@@ -4455,8 +4465,7 @@ no_entry:
  *
  * Return: The entry in the previous slot which is possibly NULL
  */
-static void *mas_prev_slot(struct ma_state *mas, unsigned long min, bool empty,
-			   bool set_underflow)
+static void *mas_prev_slot(struct ma_state *mas, unsigned long min, bool empty)
 {
 	void *entry;
 	void __rcu **slots;
@@ -4489,13 +4498,16 @@ again:
 		mas->last = mas->index - 1;
 		mas->index = mas_safe_min(mas, pivots, mas->offset);
 	} else  {
+		if (mas->index <= min)
+			goto underflow;
+
 		if (mas_prev_node(mas, min)) {
 			mas_rewalk(mas, save_point);
 			goto retry;
 		}
 
-		if (mas_is_none(mas))
-			goto underflow;
+		if (WARN_ON_ONCE(mas_is_underflow(mas)))
+			return NULL;
 
 		mas->last = mas->max;
 		node = mas_mn(mas);
@@ -4509,12 +4521,15 @@ again:
 	if (unlikely(mas_rewalk_if_dead(mas, node, save_point)))
 		goto retry;
 
+
 	if (likely(entry))
 		return entry;
 
 	if (!empty) {
-		if (mas->index <= min)
-			goto underflow;
+		if (mas->index <= min) {
+			mas->status = ma_underflow;
+			return NULL;
+		}
 
 		goto again;
 	}
@@ -4522,8 +4537,7 @@ again:
 	return entry;
 
 underflow:
-	if (set_underflow)
-		mas->node = MAS_UNDERFLOW;
+	mas->status = ma_underflow;
 	return NULL;
 }
 
@@ -4532,7 +4546,8 @@ underflow:
  * @mas: The maple state
  * @max: The maximum pivot value to check.
  *
- * The next value will be mas->node[mas->offset] or MAS_NONE.
+ * The next value will be mas->node[mas->offset] or the status will have
+ * overflowed.
  * Return: 1 on dead node, 0 otherwise.
  */
 static int mas_next_node(struct ma_state *mas, struct maple_node *node,
@@ -4548,13 +4563,13 @@ static int mas_next_node(struct ma_state *mas, struct maple_node *node,
 	void __rcu **slots;
 
 	if (mas->max >= max)
-		goto no_entry;
+		goto overflow;
 
 	min = mas->max + 1;
 	level = 0;
 	do {
 		if (ma_is_root(node))
-			goto no_entry;
+			goto overflow;
 
 		/* Walk up. */
 		if (unlikely(mas_ascend(mas)))
@@ -4605,11 +4620,11 @@ static int mas_next_node(struct ma_state *mas, struct maple_node *node,
 	mas->min = min;
 	return 0;
 
-no_entry:
+overflow:
 	if (unlikely(ma_dead_node(node)))
 		return 1;
 
-	mas->node = MAS_NONE;
+	mas->status = ma_overflow;
 	return 0;
 }
 
@@ -4624,8 +4639,7 @@ no_entry:
  *
  * Return: The entry in the next slot which is possibly NULL
  */
-static void *mas_next_slot(struct ma_state *mas, unsigned long max, bool empty,
-			   bool set_overflow)
+static void *mas_next_slot(struct ma_state *mas, unsigned long max, bool empty)
 {
 	void __rcu **slots;
 	unsigned long *pivots;
@@ -4646,13 +4660,15 @@ retry:
 		if (likely(mas->offset < mas->end))
 			pivot = pivots[mas->offset];
 		else
-			goto overflow;
+			pivot = mas->max;
 
 		if (unlikely(mas_rewalk_if_dead(mas, node, save_point)))
 			goto retry;
 
-		if (pivot >= max)
-			goto overflow;
+		if (pivot >= max) { /* Was at the limit, next will extend beyond */
+			mas->status = ma_overflow;
+			return NULL;
+		}
 	}
 
 	if (likely(mas->offset < mas->end)) {
@@ -4664,16 +4680,18 @@ again:
 		else
 			mas->last = mas->max;
 	} else  {
+		if (mas->last >= max) {
+			mas->status = ma_overflow;
+			return NULL;
+		}
+
 		if (mas_next_node(mas, node, max)) {
 			mas_rewalk(mas, save_point);
 			goto retry;
 		}
 
-		if (WARN_ON_ONCE(mas_is_none(mas))) {
-			mas->node = MAS_OVERFLOW;
+		if (WARN_ON_ONCE(mas_is_overflow(mas)))
 			return NULL;
-			goto overflow;
-		}
 
 		mas->offset = 0;
 		mas->index = mas->min;
@@ -4691,20 +4709,18 @@ again:
 	if (entry)
 		return entry;
 
+
 	if (!empty) {
-		if (mas->last >= max)
-			goto overflow;
+		if (mas->last >= max) {
+			mas->status = ma_overflow;
+			return NULL;
+		}
 
 		mas->index = mas->last + 1;
 		goto again;
 	}
 
 	return entry;
-
-overflow:
-	if (set_overflow)
-		mas->node = MAS_OVERFLOW;
-	return NULL;
 }
 
 /*
@@ -4723,11 +4739,11 @@ overflow:
 static inline void *mas_next_entry(struct ma_state *mas, unsigned long limit)
 {
 	if (mas->last >= limit) {
-		mas->node = MAS_OVERFLOW;
+		mas->status = ma_overflow;
 		return NULL;
 	}
 
-	return mas_next_slot(mas, limit, false, true);
+	return mas_next_slot(mas, limit, false);
 }
 
 /*
@@ -4895,7 +4911,7 @@ done:
  * @mas: The maple state.
  *
  * mas->index and mas->last will be set to the range if there is a value.  If
- * mas->node is MAS_NONE, reset to MAS_START.
+ * mas->status is ma_none, reset to ma_start
  *
  * Return: the entry at the location or %NULL.
  */
@@ -4904,7 +4920,7 @@ void *mas_walk(struct ma_state *mas)
 	void *entry;
 
 	if (!mas_is_active(mas) || !mas_is_start(mas))
-		mas->node = MAS_START;
+		mas->status = ma_start;
 retry:
 	entry = mas_state_walk(mas);
 	if (mas_is_start(mas)) {
@@ -4920,7 +4936,7 @@ retry:
 
 		mas->index = 1;
 		mas->last = ULONG_MAX;
-		mas->node = MAS_NONE;
+		mas->status = ma_none;
 		return NULL;
 	}
 
@@ -5672,27 +5688,40 @@ static bool mas_next_setup(struct ma_state *mas, unsigned long max,
 	bool was_none = mas_is_none(mas);
 
 	if (unlikely(mas->last >= max)) {
-		mas->node = MAS_OVERFLOW;
+		mas->status = ma_overflow;
 		return true;
 	}
 
-	if (mas_is_active(mas))
+	switch (mas->status) {
+	case ma_active:
 		return false;
-
-	if (mas_is_none(mas) || mas_is_paused(mas)) {
-		mas->node = MAS_START;
-	} else if (mas_is_overflow(mas)) {
+	case ma_none:
+		fallthrough;
+	case ma_pause:
+		mas->status = ma_start;
+		fallthrough;
+	case ma_start:
+		mas_walk(mas); /* Retries on dead nodes handled by mas_walk */
+		break;
+	case ma_overflow:
 		/* Overflowed before, but the max changed */
-		mas->node = MAS_START;
-	} else if (mas_is_underflow(mas)) {
-		mas->node = MAS_START;
+		mas->status = ma_active;
+		break;
+	case ma_underflow:
+		/* The user expects the mas to be one before where it is */
+		mas->status = ma_active;
 		*entry = mas_walk(mas);
 		if (*entry)
 			return true;
+		break;
+	case ma_root:
+		break;
+	case ma_error:
+		return true;
 	}
 
-	if (mas_is_start(mas))
-		*entry = mas_walk(mas); /* Retries on dead nodes handled by mas_walk */
+	if (likely(mas_is_active(mas))) /* Fast path */
+		return false;
 
 	if (mas_is_ptr(mas)) {
 		*entry = NULL;
@@ -5702,7 +5731,7 @@ static bool mas_next_setup(struct ma_state *mas, unsigned long max,
 		}
 		mas->index = 1;
 		mas->last = ULONG_MAX;
-		mas->node = MAS_NONE;
+		mas->status = ma_none;
 		return true;
 	}
 
@@ -5731,7 +5760,7 @@ void *mas_next(struct ma_state *mas, unsigned long max)
 		return entry;
 
 	/* Retries on dead nodes handled by mas_next_slot */
-	return mas_next_slot(mas, max, false, true);
+	return mas_next_slot(mas, max, false);
 }
 EXPORT_SYMBOL_GPL(mas_next);
 
@@ -5754,7 +5783,7 @@ void *mas_next_range(struct ma_state *mas, unsigned long max)
 		return entry;
 
 	/* Retries on dead nodes handled by mas_next_slot */
-	return mas_next_slot(mas, max, true, true);
+	return mas_next_slot(mas, max, true);
 }
 EXPORT_SYMBOL_GPL(mas_next_range);
 
@@ -5785,33 +5814,45 @@ EXPORT_SYMBOL_GPL(mt_next);
 static bool mas_prev_setup(struct ma_state *mas, unsigned long min, void **entry)
 {
 	if (unlikely(mas->index <= min)) {
-		mas->node = MAS_UNDERFLOW;
+		mas->status = ma_underflow;
 		return true;
 	}
 
-	if (mas_is_active(mas))
+	switch (mas->status) {
+	case ma_active:
 		return false;
-
-	if (mas_is_overflow(mas)) {
-		mas->node = MAS_START;
+	case ma_start:
+		break;
+	case ma_none:
+		fallthrough;
+	case ma_pause:
+		mas->status = ma_start;
+		break;
+	case ma_underflow:
+		/* underflowed before but the min changed */
+		mas->status = ma_active;
+		break;
+	case ma_overflow:
+		/* User expects mas to be one after where it is */
+		mas->status = ma_active;
 		*entry = mas_walk(mas);
 		if (*entry)
 			return true;
-	}
-
-	if (mas_is_none(mas) || mas_is_paused(mas)) {
-		mas->node = MAS_START;
-	} else if (mas_is_underflow(mas)) {
-		/* underflowed before but the min changed */
-		mas->node = MAS_START;
+		break;
+	case ma_root:
+		break;
+	case ma_error:
+		return true;
 	}
 
 	if (mas_is_start(mas))
 		mas_walk(mas);
 
 	if (unlikely(mas_is_ptr(mas))) {
-		if (!mas->index)
-			goto none;
+		if (!mas->index) {
+			mas->status = ma_none;
+			return true;
+		}
 		mas->index = mas->last = 0;
 		*entry = mas_root(mas);
 		return true;
@@ -5821,7 +5862,7 @@ static bool mas_prev_setup(struct ma_state *mas, unsigned long min, void **entry
 		if (mas->index) {
 			/* Walked to out-of-range pointer? */
 			mas->index = mas->last = 0;
-			mas->node = MAS_ROOT;
+			mas->status = ma_root;
 			*entry = mas_root(mas);
 			return true;
 		}
@@ -5829,10 +5870,6 @@ static bool mas_prev_setup(struct ma_state *mas, unsigned long min, void **entry
 	}
 
 	return false;
-
-none:
-	mas->node = MAS_NONE;
-	return true;
 }
 
 /**
@@ -5841,7 +5878,7 @@ none:
  * @min: The minimum value to check.
  *
  * Must hold rcu_read_lock or the write lock.
- * Will reset mas to MAS_START if the node is MAS_NONE.  Will stop on not
+ * Will reset mas to ma_start if the status is ma_none.  Will stop on not
  * searchable nodes.
  *
  * Return: the previous value or %NULL.
@@ -5853,7 +5890,7 @@ void *mas_prev(struct ma_state *mas, unsigned long min)
 	if (mas_prev_setup(mas, min, &entry))
 		return entry;
 
-	return mas_prev_slot(mas, min, false, true);
+	return mas_prev_slot(mas, min, false);
 }
 EXPORT_SYMBOL_GPL(mas_prev);
 
@@ -5864,7 +5901,7 @@ EXPORT_SYMBOL_GPL(mas_prev);
  *
  * Sets @mas->index and @mas->last to the range.
  * Must hold rcu_read_lock or the write lock.
- * Will reset mas to MAS_START if the node is MAS_NONE.  Will stop on not
+ * Will reset mas to ma_start if the node is ma_none.  Will stop on not
  * searchable nodes.
  *
  * Return: the previous value or %NULL.
@@ -5876,7 +5913,7 @@ void *mas_prev_range(struct ma_state *mas, unsigned long min)
 	if (mas_prev_setup(mas, min, &entry))
 		return entry;
 
-	return mas_prev_slot(mas, min, true, true);
+	return mas_prev_slot(mas, min, true);
 }
 EXPORT_SYMBOL_GPL(mas_prev_range);
 
@@ -5919,7 +5956,8 @@ EXPORT_SYMBOL_GPL(mt_prev);
  */
 void mas_pause(struct ma_state *mas)
 {
-	mas->node = MAS_PAUSE;
+	mas->status = ma_pause;
+	mas->node = NULL;
 }
 EXPORT_SYMBOL_GPL(mas_pause);
 
@@ -5933,32 +5971,52 @@ EXPORT_SYMBOL_GPL(mas_pause);
  */
 static __always_inline bool mas_find_setup(struct ma_state *mas, unsigned long max, void **entry)
 {
-	if (mas_is_active(mas)) {
+	switch (mas->status) {
+	case ma_active:
 		if (mas->last < max)
 			return false;
-
 		return true;
-	}
-
-	if (mas_is_paused(mas)) {
+	case ma_start:
+		break;
+	case ma_pause:
 		if (unlikely(mas->last >= max))
 			return true;
 
 		mas->index = ++mas->last;
-		mas->node = MAS_START;
-	} else if (mas_is_none(mas)) {
+		mas->status = ma_start;
+		break;
+	case ma_none:
 		if (unlikely(mas->last >= max))
 			return true;
 
 		mas->index = mas->last;
-		mas->node = MAS_START;
-	} else if (mas_is_overflow(mas) || mas_is_underflow(mas)) {
-		if (mas->index > max) {
-			mas->node = MAS_OVERFLOW;
+		mas->status = ma_start;
+		break;
+	case ma_underflow:
+		/* mas is pointing at entry before unable to go lower */
+		if (unlikely(mas->index >= max)) {
+			mas->status = ma_overflow;
 			return true;
 		}
 
-		mas->node = MAS_START;
+		mas->status = ma_active;
+		*entry = mas_walk(mas);
+		if (*entry)
+			return true;
+		break;
+	case ma_overflow:
+		if (unlikely(mas->last >= max))
+			return true;
+
+		mas->status = ma_active;
+		*entry = mas_walk(mas);
+		if (*entry)
+			return true;
+		break;
+	case ma_root:
+		break;
+	case ma_error:
+		return true;
 	}
 
 	if (mas_is_start(mas)) {
@@ -5985,7 +6043,7 @@ static __always_inline bool mas_find_setup(struct ma_state *mas, unsigned long m
 	return false;
 
 ptr_out_of_range:
-	mas->node = MAS_NONE;
+	mas->status = ma_none;
 	mas->index = 1;
 	mas->last = ULONG_MAX;
 	return true;
@@ -5999,7 +6057,7 @@ ptr_out_of_range:
  *
  * Must hold rcu_read_lock or the write lock.
  * If an entry exists, last and index are updated accordingly.
- * May set @mas->node to MAS_NONE.
+ * May set @mas->status to ma_overflow.
  *
  * Return: The entry or %NULL.
  */
@@ -6011,7 +6069,10 @@ void *mas_find(struct ma_state *mas, unsigned long max)
 		return entry;
 
 	/* Retries on dead nodes handled by mas_next_slot */
-	return mas_next_slot(mas, max, false, false);
+	entry = mas_next_slot(mas, max, false);
+	/* Ignore overflow */
+	mas->status = ma_active;
+	return entry;
 }
 EXPORT_SYMBOL_GPL(mas_find);
 
@@ -6023,7 +6084,7 @@ EXPORT_SYMBOL_GPL(mas_find);
  *
  * Must hold rcu_read_lock or the write lock.
  * If an entry exists, last and index are updated accordingly.
- * May set @mas->node to MAS_NONE.
+ * May set @mas->status to ma_overflow.
  *
  * Return: The entry or %NULL.
  */
@@ -6035,7 +6096,7 @@ void *mas_find_range(struct ma_state *mas, unsigned long max)
 		return entry;
 
 	/* Retries on dead nodes handled by mas_next_slot */
-	return mas_next_slot(mas, max, true, false);
+	return mas_next_slot(mas, max, true);
 }
 EXPORT_SYMBOL_GPL(mas_find_range);
 
@@ -6050,33 +6111,45 @@ EXPORT_SYMBOL_GPL(mas_find_range);
 static bool mas_find_rev_setup(struct ma_state *mas, unsigned long min,
 		void **entry)
 {
-	if (mas_is_active(mas)) {
-		if (mas->index > min)
-			return false;
-
-		return true;
-	}
 
-	if (mas_is_paused(mas)) {
+	switch (mas->status) {
+	case ma_active:
+		goto active;
+	case ma_start:
+		break;
+	case ma_pause:
 		if (unlikely(mas->index <= min)) {
-			mas->node = MAS_NONE;
+			mas->status = ma_underflow;
 			return true;
 		}
-		mas->node = MAS_START;
 		mas->last = --mas->index;
-	} else if (mas_is_none(mas)) {
+		mas->status = ma_start;
+		break;
+	case ma_none:
 		if (mas->index <= min)
 			goto none;
 
 		mas->last = mas->index;
-		mas->node = MAS_START;
-	} else if (mas_is_underflow(mas) || mas_is_overflow(mas)) {
-		if (mas->last <= min) {
-			mas->node = MAS_UNDERFLOW;
+		mas->status = ma_start;
+		break;
+	case ma_overflow: /* user expects the mas to be one after where it is */
+		if (unlikely(mas->index <= min)) {
+			mas->status = ma_underflow;
 			return true;
 		}
 
-		mas->node = MAS_START;
+		mas->status = ma_active;
+		break;
+	case ma_underflow: /* user expects the mas to be one before where it is */
+		if (unlikely(mas->index <= min))
+			return true;
+
+		mas->status = ma_active;
+		break;
+	case ma_root:
+		break;
+	case ma_error:
+		return true;
 	}
 
 	if (mas_is_start(mas)) {
@@ -6099,19 +6172,20 @@ static bool mas_find_rev_setup(struct ma_state *mas, unsigned long min,
 			 * previous location is 0.
 			 */
 			mas->last = mas->index = 0;
-			mas->node = MAS_ROOT;
+			mas->status = ma_root;
 			*entry = mas_root(mas);
 			return true;
 		}
 	}
 
+active:
 	if (mas->index < min)
 		return true;
 
 	return false;
 
 none:
-	mas->node = MAS_NONE;
+	mas->status = ma_none;
 	return true;
 }
 
@@ -6124,7 +6198,7 @@ none:
  *
  * Must hold rcu_read_lock or the write lock.
  * If an entry exists, last and index are updated accordingly.
- * May set @mas->node to MAS_NONE.
+ * May set @mas->status to ma_underflow.
  *
  * Return: The entry or %NULL.
  */
@@ -6136,7 +6210,7 @@ void *mas_find_rev(struct ma_state *mas, unsigned long min)
 		return entry;
 
 	/* Retries on dead nodes handled by mas_prev_slot */
-	return mas_prev_slot(mas, min, false, false);
+	return mas_prev_slot(mas, min, false);
 
 }
 EXPORT_SYMBOL_GPL(mas_find_rev);
@@ -6150,7 +6224,7 @@ EXPORT_SYMBOL_GPL(mas_find_rev);
  *
  * Must hold rcu_read_lock or the write lock.
  * If an entry exists, last and index are updated accordingly.
- * May set @mas->node to MAS_NONE.
+ * May set @mas->status to ma_underflow.
  *
  * Return: The entry or %NULL.
  */
@@ -6162,7 +6236,7 @@ void *mas_find_range_rev(struct ma_state *mas, unsigned long min)
 		return entry;
 
 	/* Retries on dead nodes handled by mas_prev_slot */
-	return mas_prev_slot(mas, min, true, false);
+	return mas_prev_slot(mas, min, true);
 }
 EXPORT_SYMBOL_GPL(mas_find_range_rev);
 
@@ -6183,7 +6257,7 @@ void *mas_erase(struct ma_state *mas)
 	MA_WR_STATE(wr_mas, mas, NULL);
 
 	if (!mas_is_active(mas) || !mas_is_start(mas))
-		mas->node = MAS_START;
+		mas->status = ma_start;
 
 	/* Retry unnecessary when holding the write lock. */
 	entry = mas_state_walk(mas);
@@ -6228,7 +6302,7 @@ bool mas_nomem(struct ma_state *mas, gfp_t gfp)
 	if (!mas_allocated(mas))
 		return false;
 
-	mas->node = MAS_START;
+	mas->status = ma_start;
 	return true;
 }
 
@@ -6627,7 +6701,7 @@ static inline void mas_dup_build(struct ma_state *mas, struct ma_state *new_mas,
 
 	node = mt_alloc_one(gfp);
 	if (!node) {
-		new_mas->node = MAS_NONE;
+		new_mas->status = ma_none;
 		mas_set_err(mas, -ENOMEM);
 		return;
 	}
@@ -6971,11 +7045,11 @@ static inline struct maple_enode *mas_get_slot(struct ma_state *mas,
 static void mas_dfs_postorder(struct ma_state *mas, unsigned long max)
 {
 
-	struct maple_enode *p = MAS_NONE, *mn = mas->node;
+	struct maple_enode *p, *mn = mas->node;
 	unsigned long p_min, p_max;
 
 	mas_next_node(mas, mas_mn(mas), max);
-	if (!mas_is_none(mas))
+	if (!mas_is_overflow(mas))
 		return;
 
 	if (mte_is_root(mn))
@@ -6988,7 +7062,7 @@ static void mas_dfs_postorder(struct ma_state *mas, unsigned long max)
 		p_min = mas->min;
 		p_max = mas->max;
 		mas_prev_node(mas, 0);
-	} while (!mas_is_none(mas));
+	} while (!mas_is_underflow(mas));
 
 	mas->node = p;
 	mas->max = p_max;
@@ -7443,7 +7517,7 @@ static void mt_validate_nulls(struct maple_tree *mt)
 	MA_STATE(mas, mt, 0, 0);
 
 	mas_start(&mas);
-	if (mas_is_none(&mas) || (mas.node == MAS_ROOT))
+	if (mas_is_none(&mas) || (mas_is_ptr(&mas)))
 		return;
 
 	while (!mte_is_leaf(mas.node))
@@ -7460,7 +7534,7 @@ static void mt_validate_nulls(struct maple_tree *mt)
 		last = entry;
 		if (offset == mas_data_end(&mas)) {
 			mas_next_node(&mas, mas_mn(&mas), ULONG_MAX);
-			if (mas_is_none(&mas))
+			if (mas_is_overflow(&mas))
 				return;
 			offset = 0;
 			slots = ma_slots(mte_to_node(mas.node),
@@ -7469,7 +7543,7 @@ static void mt_validate_nulls(struct maple_tree *mt)
 			offset++;
 		}
 
-	} while (!mas_is_none(&mas));
+	} while (!mas_is_overflow(&mas));
 }
 
 /*
@@ -7490,7 +7564,7 @@ void mt_validate(struct maple_tree *mt)
 	while (!mte_is_leaf(mas.node))
 		mas_descend(&mas);
 
-	while (!mas_is_none(&mas)) {
+	while (!mas_is_overflow(&mas)) {
 		MAS_WARN_ON(&mas, mte_dead_node(mas.node));
 		end = mas_data_end(&mas);
 		if (MAS_WARN_ON(&mas, (end < mt_min_slot_count(mas.node)) &&
@@ -7515,16 +7589,35 @@ EXPORT_SYMBOL_GPL(mt_validate);
 void mas_dump(const struct ma_state *mas)
 {
 	pr_err("MAS: tree=%p enode=%p ", mas->tree, mas->node);
-	if (mas_is_none(mas))
-		pr_err("(MAS_NONE) ");
-	else if (mas_is_ptr(mas))
-		pr_err("(MAS_ROOT) ");
-	else if (mas_is_start(mas))
-		 pr_err("(MAS_START) ");
-	else if (mas_is_paused(mas))
-		pr_err("(MAS_PAUSED) ");
-
-	pr_err("[%u] index=%lx last=%lx\n", mas->offset, mas->index, mas->last);
+	switch (mas->status) {
+	case ma_active:
+		pr_err("(ma_active)");
+		break;
+	case ma_none:
+		pr_err("(ma_none)");
+		break;
+	case ma_root:
+		pr_err("(ma_root)");
+		break;
+	case ma_start:
+		pr_err("(ma_start) ");
+		break;
+	case ma_pause:
+		pr_err("(ma_pause) ");
+		break;
+	case ma_overflow:
+		pr_err("(ma_overflow) ");
+		break;
+	case ma_underflow:
+		pr_err("(ma_underflow) ");
+		break;
+	case ma_error:
+		pr_err("(ma_error) ");
+		break;
+	}
+
+	pr_err("[%u/%u] index=%lx last=%lx\n", mas->offset, mas->end,
+	       mas->index, mas->last);
 	pr_err("     min=%lx max=%lx alloc=%p, depth=%u, flags=%x\n",
 	       mas->min, mas->max, mas->alloc, mas->depth, mas->mas_flags);
 	if (mas->index > mas->last)
diff --git a/lib/test_maple_tree.c b/lib/test_maple_tree.c
index 3e4597fb49d3..e7a5d688c9e0 100644
--- a/lib/test_maple_tree.c
+++ b/lib/test_maple_tree.c
@@ -54,6 +54,11 @@ atomic_t maple_tree_tests_passed;
 #else
 #define cond_resched()			do {} while (0)
 #endif
+
+#define mas_is_none(x)		((x)->status == ma_none)
+#define mas_is_overflow(x)	((x)->status == ma_overflow)
+#define mas_is_underflow(x)	((x)->status == ma_underflow)
+
 static int __init mtree_insert_index(struct maple_tree *mt,
 				     unsigned long index, gfp_t gfp)
 {
@@ -582,7 +587,7 @@ static noinline void __init check_find(struct maple_tree *mt)
 	MT_BUG_ON(mt, last != mas.last);
 
 
-	mas.node = MAS_NONE;
+	mas.status = ma_none;
 	mas.index = ULONG_MAX;
 	mas.last = ULONG_MAX;
 	entry2 = mas_prev(&mas, 0);
@@ -2178,7 +2183,7 @@ static noinline void __init next_prev_test(struct maple_tree *mt)
 	MT_BUG_ON(mt, val != NULL);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 5);
-	MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW);
+	MT_BUG_ON(mt, !mas_is_underflow(&mas));
 
 	mas.index = 0;
 	mas.last = 5;
@@ -3042,10 +3047,6 @@ static noinline void __init check_empty_area_fill(struct maple_tree *mt)
  *		DNE	active		active		range of NULL
  */
 
-#define mas_active(x)		(((x).node != MAS_ROOT) && \
-				 ((x).node != MAS_START) && \
-				 ((x).node != MAS_PAUSE) && \
-				 ((x).node != MAS_NONE))
 static noinline void __init check_state_handling(struct maple_tree *mt)
 {
 	MA_STATE(mas, mt, 0, 0);
@@ -3060,7 +3061,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	/* prev: Start -> underflow*/
 	entry = mas_prev(&mas, 0);
 	MT_BUG_ON(mt, entry != NULL);
-	MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW);
+	MT_BUG_ON(mt, mas.status != ma_underflow);
 
 	/* prev: Start -> root */
 	mas_set(&mas, 10);
@@ -3068,7 +3069,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 0);
-	MT_BUG_ON(mt, mas.node != MAS_ROOT);
+	MT_BUG_ON(mt, mas.status != ma_root);
 
 	/* prev: pause -> root */
 	mas_set(&mas, 10);
@@ -3077,7 +3078,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 0);
-	MT_BUG_ON(mt, mas.node != MAS_ROOT);
+	MT_BUG_ON(mt, mas.status != ma_root);
 
 	/* next: start -> none */
 	mas_set(&mas, 0);
@@ -3085,7 +3086,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, mas.index != 1);
 	MT_BUG_ON(mt, mas.last != ULONG_MAX);
 	MT_BUG_ON(mt, entry != NULL);
-	MT_BUG_ON(mt, mas.node != MAS_NONE);
+	MT_BUG_ON(mt, mas.status != ma_none);
 
 	/* next: start -> none*/
 	mas_set(&mas, 10);
@@ -3093,7 +3094,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, mas.index != 1);
 	MT_BUG_ON(mt, mas.last != ULONG_MAX);
 	MT_BUG_ON(mt, entry != NULL);
-	MT_BUG_ON(mt, mas.node != MAS_NONE);
+	MT_BUG_ON(mt, mas.status != ma_none);
 
 	/* find: start -> root */
 	mas_set(&mas, 0);
@@ -3101,21 +3102,21 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 0);
-	MT_BUG_ON(mt, mas.node != MAS_ROOT);
+	MT_BUG_ON(mt, mas.status != ma_root);
 
 	/* find: root -> none */
 	entry = mas_find(&mas, ULONG_MAX);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 1);
 	MT_BUG_ON(mt, mas.last != ULONG_MAX);
-	MT_BUG_ON(mt, mas.node != MAS_NONE);
+	MT_BUG_ON(mt, mas.status != ma_none);
 
 	/* find: none -> none */
 	entry = mas_find(&mas, ULONG_MAX);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 1);
 	MT_BUG_ON(mt, mas.last != ULONG_MAX);
-	MT_BUG_ON(mt, mas.node != MAS_NONE);
+	MT_BUG_ON(mt, mas.status != ma_none);
 
 	/* find: start -> none */
 	mas_set(&mas, 10);
@@ -3123,14 +3124,14 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 1);
 	MT_BUG_ON(mt, mas.last != ULONG_MAX);
-	MT_BUG_ON(mt, mas.node != MAS_NONE);
+	MT_BUG_ON(mt, mas.status != ma_none);
 
 	/* find_rev: none -> root */
 	entry = mas_find_rev(&mas, 0);
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 0);
-	MT_BUG_ON(mt, mas.node != MAS_ROOT);
+	MT_BUG_ON(mt, mas.status != ma_root);
 
 	/* find_rev: start -> root */
 	mas_set(&mas, 0);
@@ -3138,21 +3139,21 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 0);
-	MT_BUG_ON(mt, mas.node != MAS_ROOT);
+	MT_BUG_ON(mt, mas.status != ma_root);
 
 	/* find_rev: root -> none */
 	entry = mas_find_rev(&mas, 0);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 0);
-	MT_BUG_ON(mt, mas.node != MAS_NONE);
+	MT_BUG_ON(mt, mas.status != ma_none);
 
 	/* find_rev: none -> none */
 	entry = mas_find_rev(&mas, 0);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 0);
-	MT_BUG_ON(mt, mas.node != MAS_NONE);
+	MT_BUG_ON(mt, mas.status != ma_none);
 
 	/* find_rev: start -> root */
 	mas_set(&mas, 10);
@@ -3160,7 +3161,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 0);
-	MT_BUG_ON(mt, mas.node != MAS_ROOT);
+	MT_BUG_ON(mt, mas.status != ma_root);
 
 	/* walk: start -> none */
 	mas_set(&mas, 10);
@@ -3168,7 +3169,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 1);
 	MT_BUG_ON(mt, mas.last != ULONG_MAX);
-	MT_BUG_ON(mt, mas.node != MAS_NONE);
+	MT_BUG_ON(mt, mas.status != ma_none);
 
 	/* walk: pause -> none*/
 	mas_set(&mas, 10);
@@ -3177,7 +3178,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 1);
 	MT_BUG_ON(mt, mas.last != ULONG_MAX);
-	MT_BUG_ON(mt, mas.node != MAS_NONE);
+	MT_BUG_ON(mt, mas.status != ma_none);
 
 	/* walk: none -> none */
 	mas.index = mas.last = 10;
@@ -3185,14 +3186,14 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 1);
 	MT_BUG_ON(mt, mas.last != ULONG_MAX);
-	MT_BUG_ON(mt, mas.node != MAS_NONE);
+	MT_BUG_ON(mt, mas.status != ma_none);
 
 	/* walk: none -> none */
 	entry = mas_walk(&mas);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 1);
 	MT_BUG_ON(mt, mas.last != ULONG_MAX);
-	MT_BUG_ON(mt, mas.node != MAS_NONE);
+	MT_BUG_ON(mt, mas.status != ma_none);
 
 	/* walk: start -> root */
 	mas_set(&mas, 0);
@@ -3200,7 +3201,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 0);
-	MT_BUG_ON(mt, mas.node != MAS_ROOT);
+	MT_BUG_ON(mt, mas.status != ma_root);
 
 	/* walk: pause -> root */
 	mas_set(&mas, 0);
@@ -3209,22 +3210,22 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 0);
-	MT_BUG_ON(mt, mas.node != MAS_ROOT);
+	MT_BUG_ON(mt, mas.status != ma_root);
 
 	/* walk: none -> root */
-	mas.node = MAS_NONE;
+	mas.status = ma_none;
 	entry = mas_walk(&mas);
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 0);
-	MT_BUG_ON(mt, mas.node != MAS_ROOT);
+	MT_BUG_ON(mt, mas.status != ma_root);
 
 	/* walk: root -> root */
 	entry = mas_walk(&mas);
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 0);
-	MT_BUG_ON(mt, mas.node != MAS_ROOT);
+	MT_BUG_ON(mt, mas.status != ma_root);
 
 	/* walk: root -> none */
 	mas_set(&mas, 10);
@@ -3232,7 +3233,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 1);
 	MT_BUG_ON(mt, mas.last != ULONG_MAX);
-	MT_BUG_ON(mt, mas.node != MAS_NONE);
+	MT_BUG_ON(mt, mas.status != ma_none);
 
 	/* walk: none -> root */
 	mas.index = mas.last = 0;
@@ -3240,7 +3241,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 0);
-	MT_BUG_ON(mt, mas.node != MAS_ROOT);
+	MT_BUG_ON(mt, mas.status != ma_root);
 
 	mas_unlock(&mas);
 
@@ -3258,7 +3259,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0x1000);
 	MT_BUG_ON(mt, mas.last != 0x1500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* next: pause ->active */
 	mas_set(&mas, 0);
@@ -3267,126 +3268,132 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0x1000);
 	MT_BUG_ON(mt, mas.last != 0x1500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* next: none ->active */
 	mas.index = mas.last = 0;
 	mas.offset = 0;
-	mas.node = MAS_NONE;
+	mas.status = ma_none;
 	entry = mas_next(&mas, ULONG_MAX);
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0x1000);
 	MT_BUG_ON(mt, mas.last != 0x1500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
-	/* next:active ->active */
-	entry = mas_next(&mas, ULONG_MAX);
+	/* next:active ->active (spanning limit) */
+	entry = mas_next(&mas, 0x2100);
 	MT_BUG_ON(mt, entry != ptr2);
 	MT_BUG_ON(mt, mas.index != 0x2000);
 	MT_BUG_ON(mt, mas.last != 0x2500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
-	/* next:active -> active beyond data */
+	/* next:active -> overflow (limit reached) beyond data */
 	entry = mas_next(&mas, 0x2999);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0x2501);
 	MT_BUG_ON(mt, mas.last != 0x2fff);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_overflow(&mas));
 
-	/* Continue after last range ends after max */
+	/* next:overflow -> active (limit changed) */
 	entry = mas_next(&mas, ULONG_MAX);
 	MT_BUG_ON(mt, entry != ptr3);
 	MT_BUG_ON(mt, mas.index != 0x3000);
 	MT_BUG_ON(mt, mas.last != 0x3500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
-	/* next:active -> active continued */
+	/* next:active ->  overflow (limit reached) */
 	entry = mas_next(&mas, ULONG_MAX);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0x3501);
 	MT_BUG_ON(mt, mas.last != ULONG_MAX);
-	MT_BUG_ON(mt, !mas_active(mas));
-
-	/* next:active -> overflow  */
-	entry = mas_next(&mas, ULONG_MAX);
-	MT_BUG_ON(mt, entry != NULL);
-	MT_BUG_ON(mt, mas.index != 0x3501);
-	MT_BUG_ON(mt, mas.last != ULONG_MAX);
-	MT_BUG_ON(mt, mas.node != MAS_OVERFLOW);
+	MT_BUG_ON(mt, !mas_is_overflow(&mas));
 
 	/* next:overflow -> overflow  */
 	entry = mas_next(&mas, ULONG_MAX);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0x3501);
 	MT_BUG_ON(mt, mas.last != ULONG_MAX);
-	MT_BUG_ON(mt, mas.node != MAS_OVERFLOW);
+	MT_BUG_ON(mt, !mas_is_overflow(&mas));
 
 	/* prev:overflow -> active  */
 	entry = mas_prev(&mas, 0);
 	MT_BUG_ON(mt, entry != ptr3);
 	MT_BUG_ON(mt, mas.index != 0x3000);
 	MT_BUG_ON(mt, mas.last != 0x3500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* next: none -> active, skip value at location */
 	mas_set(&mas, 0);
 	entry = mas_next(&mas, ULONG_MAX);
-	mas.node = MAS_NONE;
+	mas.status = ma_none;
 	mas.offset = 0;
 	entry = mas_next(&mas, ULONG_MAX);
 	MT_BUG_ON(mt, entry != ptr2);
 	MT_BUG_ON(mt, mas.index != 0x2000);
 	MT_BUG_ON(mt, mas.last != 0x2500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* prev:active ->active */
 	entry = mas_prev(&mas, 0);
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0x1000);
 	MT_BUG_ON(mt, mas.last != 0x1500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
-	/* prev:active -> active spanning end range */
+	/* prev:active -> underflow (span limit) */
+	mas_next(&mas, ULONG_MAX);
+	entry = mas_prev(&mas, 0x1200);
+	MT_BUG_ON(mt, entry != ptr);
+	MT_BUG_ON(mt, mas.index != 0x1000);
+	MT_BUG_ON(mt, mas.last != 0x1500);
+	MT_BUG_ON(mt, !mas_is_active(&mas)); /* spanning limit */
+	entry = mas_prev(&mas, 0x1200); /* underflow */
+	MT_BUG_ON(mt, entry != NULL);
+	MT_BUG_ON(mt, mas.index != 0x1000);
+	MT_BUG_ON(mt, mas.last != 0x1500);
+	MT_BUG_ON(mt, !mas_is_underflow(&mas));
+
+	/* prev:underflow -> underflow (lower limit) spanning end range */
 	entry = mas_prev(&mas, 0x0100);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 0x0FFF);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_underflow(&mas));
 
-	/* prev:active -> underflow */
+	/* prev:underflow -> underflow */
 	entry = mas_prev(&mas, 0);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 0x0FFF);
-	MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW);
+	MT_BUG_ON(mt, !mas_is_underflow(&mas));
 
 	/* prev:underflow -> underflow */
 	entry = mas_prev(&mas, 0);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 0x0FFF);
-	MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW);
+	MT_BUG_ON(mt, !mas_is_underflow(&mas));
 
 	/* next:underflow -> active */
 	entry = mas_next(&mas, ULONG_MAX);
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0x1000);
 	MT_BUG_ON(mt, mas.last != 0x1500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* prev:first value -> underflow */
 	entry = mas_prev(&mas, 0x1000);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0x1000);
 	MT_BUG_ON(mt, mas.last != 0x1500);
-	MT_BUG_ON(mt, mas.node != MAS_UNDERFLOW);
+	MT_BUG_ON(mt, !mas_is_underflow(&mas));
 
 	/* find:underflow -> first value */
 	entry = mas_find(&mas, ULONG_MAX);
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0x1000);
 	MT_BUG_ON(mt, mas.last != 0x1500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* prev: pause ->active */
 	mas_set(&mas, 0x3600);
@@ -3397,21 +3404,21 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr2);
 	MT_BUG_ON(mt, mas.index != 0x2000);
 	MT_BUG_ON(mt, mas.last != 0x2500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
-	/* prev:active -> active spanning min */
+	/* prev:active -> underflow spanning min */
 	entry = mas_prev(&mas, 0x1600);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0x1501);
 	MT_BUG_ON(mt, mas.last != 0x1FFF);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_underflow(&mas));
 
 	/* prev: active ->active, continue */
 	entry = mas_prev(&mas, 0);
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0x1000);
 	MT_BUG_ON(mt, mas.last != 0x1500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* find: start ->active */
 	mas_set(&mas, 0);
@@ -3419,7 +3426,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0x1000);
 	MT_BUG_ON(mt, mas.last != 0x1500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* find: pause ->active */
 	mas_set(&mas, 0);
@@ -3428,7 +3435,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0x1000);
 	MT_BUG_ON(mt, mas.last != 0x1500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* find: start ->active on value */;
 	mas_set(&mas, 1200);
@@ -3436,14 +3443,14 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0x1000);
 	MT_BUG_ON(mt, mas.last != 0x1500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* find:active ->active */
 	entry = mas_find(&mas, ULONG_MAX);
 	MT_BUG_ON(mt, entry != ptr2);
 	MT_BUG_ON(mt, mas.index != 0x2000);
 	MT_BUG_ON(mt, mas.last != 0x2500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 
 	/* find:active -> active (NULL)*/
@@ -3451,35 +3458,35 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0x2501);
 	MT_BUG_ON(mt, mas.last != 0x2FFF);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MAS_BUG_ON(&mas, !mas_is_active(&mas));
 
 	/* find: overflow ->active */
 	entry = mas_find(&mas, 0x5000);
 	MT_BUG_ON(mt, entry != ptr3);
 	MT_BUG_ON(mt, mas.index != 0x3000);
 	MT_BUG_ON(mt, mas.last != 0x3500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* find:active -> active (NULL) end*/
 	entry = mas_find(&mas, ULONG_MAX);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0x3501);
 	MT_BUG_ON(mt, mas.last != ULONG_MAX);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MAS_BUG_ON(&mas, !mas_is_active(&mas));
 
 	/* find_rev: active (END) ->active */
 	entry = mas_find_rev(&mas, 0);
 	MT_BUG_ON(mt, entry != ptr3);
 	MT_BUG_ON(mt, mas.index != 0x3000);
 	MT_BUG_ON(mt, mas.last != 0x3500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* find_rev:active ->active */
 	entry = mas_find_rev(&mas, 0);
 	MT_BUG_ON(mt, entry != ptr2);
 	MT_BUG_ON(mt, mas.index != 0x2000);
 	MT_BUG_ON(mt, mas.last != 0x2500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* find_rev: pause ->active */
 	mas_pause(&mas);
@@ -3487,14 +3494,14 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0x1000);
 	MT_BUG_ON(mt, mas.last != 0x1500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
-	/* find_rev:active -> active */
+	/* find_rev:active -> underflow */
 	entry = mas_find_rev(&mas, 0);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0);
 	MT_BUG_ON(mt, mas.last != 0x0FFF);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_underflow(&mas));
 
 	/* find_rev: start ->active */
 	mas_set(&mas, 0x1200);
@@ -3502,7 +3509,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0x1000);
 	MT_BUG_ON(mt, mas.last != 0x1500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* mas_walk start ->active */
 	mas_set(&mas, 0x1200);
@@ -3510,7 +3517,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0x1000);
 	MT_BUG_ON(mt, mas.last != 0x1500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* mas_walk start ->active */
 	mas_set(&mas, 0x1600);
@@ -3518,7 +3525,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0x1501);
 	MT_BUG_ON(mt, mas.last != 0x1fff);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* mas_walk pause ->active */
 	mas_set(&mas, 0x1200);
@@ -3527,7 +3534,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0x1000);
 	MT_BUG_ON(mt, mas.last != 0x1500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* mas_walk pause -> active */
 	mas_set(&mas, 0x1600);
@@ -3536,25 +3543,25 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0x1501);
 	MT_BUG_ON(mt, mas.last != 0x1fff);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* mas_walk none -> active */
 	mas_set(&mas, 0x1200);
-	mas.node = MAS_NONE;
+	mas.status = ma_none;
 	entry = mas_walk(&mas);
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0x1000);
 	MT_BUG_ON(mt, mas.last != 0x1500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* mas_walk none -> active */
 	mas_set(&mas, 0x1600);
-	mas.node = MAS_NONE;
+	mas.status = ma_none;
 	entry = mas_walk(&mas);
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0x1501);
 	MT_BUG_ON(mt, mas.last != 0x1fff);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* mas_walk active -> active */
 	mas.index = 0x1200;
@@ -3564,7 +3571,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != ptr);
 	MT_BUG_ON(mt, mas.index != 0x1000);
 	MT_BUG_ON(mt, mas.last != 0x1500);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	/* mas_walk active -> active */
 	mas.index = 0x1600;
@@ -3573,7 +3580,7 @@ static noinline void __init check_state_handling(struct maple_tree *mt)
 	MT_BUG_ON(mt, entry != NULL);
 	MT_BUG_ON(mt, mas.index != 0x1501);
 	MT_BUG_ON(mt, mas.last != 0x1fff);
-	MT_BUG_ON(mt, !mas_active(mas));
+	MT_BUG_ON(mt, !mas_is_active(&mas));
 
 	mas_unlock(&mas);
 }
diff --git a/mm/internal.h b/mm/internal.h
index 0005b8adbd5c..8450562744cf 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1163,13 +1163,13 @@ static inline void vma_iter_store(struct vma_iterator *vmi,
 {
 
 #if defined(CONFIG_DEBUG_VM_MAPLE_TREE)
-	if (MAS_WARN_ON(&vmi->mas, vmi->mas.node != MAS_START &&
+	if (MAS_WARN_ON(&vmi->mas, vmi->mas.status != ma_start &&
 			vmi->mas.index > vma->vm_start)) {
 		pr_warn("%lx > %lx\n store vma %lx-%lx\n into slot %lx-%lx\n",
 			vmi->mas.index, vma->vm_start, vma->vm_start,
 			vma->vm_end, vmi->mas.index, vmi->mas.last);
 	}
-	if (MAS_WARN_ON(&vmi->mas, vmi->mas.node != MAS_START &&
+	if (MAS_WARN_ON(&vmi->mas, vmi->mas.status != ma_start &&
 			vmi->mas.last <  vma->vm_start)) {
 		pr_warn("%lx < %lx\nstore vma %lx-%lx\ninto slot %lx-%lx\n",
 		       vmi->mas.last, vma->vm_start, vma->vm_start, vma->vm_end,
@@ -1177,7 +1177,7 @@ static inline void vma_iter_store(struct vma_iterator *vmi,
 	}
 #endif
 
-	if (vmi->mas.node != MAS_START &&
+	if (vmi->mas.status != ma_start &&
 	    ((vmi->mas.index > vma->vm_start) || (vmi->mas.last < vma->vm_start)))
 		vma_iter_invalidate(vmi);
 
@@ -1188,7 +1188,7 @@ static inline void vma_iter_store(struct vma_iterator *vmi,
 static inline int vma_iter_store_gfp(struct vma_iterator *vmi,
 			struct vm_area_struct *vma, gfp_t gfp)
 {
-	if (vmi->mas.node != MAS_START &&
+	if (vmi->mas.status != ma_start &&
 	    ((vmi->mas.index > vma->vm_start) || (vmi->mas.last < vma->vm_start)))
 		vma_iter_invalidate(vmi);
 
diff --git a/tools/testing/radix-tree/maple.c b/tools/testing/radix-tree/maple.c
index 7095fb0ec026..857c439e6bbc 100644
--- a/tools/testing/radix-tree/maple.c
+++ b/tools/testing/radix-tree/maple.c
@@ -118,6 +118,7 @@ static noinline void __init check_new_node(struct maple_tree *mt)
 	MT_BUG_ON(mt, mas.alloc == NULL);
 	MT_BUG_ON(mt, mas.alloc->slot[0] == NULL);
 	mas_push_node(&mas, mn);
+	mas_reset(&mas);
 	mas_nomem(&mas, GFP_KERNEL); /* free */
 	mtree_unlock(mt);
 
@@ -141,7 +142,7 @@ static noinline void __init check_new_node(struct maple_tree *mt)
 
 	mn->parent = ma_parent_ptr(mn);
 	ma_free_rcu(mn);
-	mas.node = MAS_START;
+	mas.status = ma_start;
 	mas_nomem(&mas, GFP_KERNEL);
 	/* Allocate 3 nodes, will fail. */
 	mas_node_count(&mas, 3);
@@ -158,6 +159,7 @@ static noinline void __init check_new_node(struct maple_tree *mt)
 	/* Ensure we counted 3. */
 	MT_BUG_ON(mt, mas_allocated(&mas) != 3);
 	/* Free. */
+	mas_reset(&mas);
 	mas_nomem(&mas, GFP_KERNEL);
 
 	/* Set allocation request to 1. */
@@ -272,6 +274,7 @@ static noinline void __init check_new_node(struct maple_tree *mt)
 			ma_free_rcu(mn);
 			MT_BUG_ON(mt, mas_allocated(&mas) != i - j - 1);
 		}
+		mas_reset(&mas);
 		MT_BUG_ON(mt, mas_nomem(&mas, GFP_KERNEL));
 
 	}
@@ -294,6 +297,7 @@ static noinline void __init check_new_node(struct maple_tree *mt)
 		smn = smn->slot[0]; /* next. */
 	}
 	MT_BUG_ON(mt, mas_allocated(&mas) != total);
+	mas_reset(&mas);
 	mas_nomem(&mas, GFP_KERNEL); /* Free. */
 
 	MT_BUG_ON(mt, mas_allocated(&mas) != 0);
@@ -441,7 +445,7 @@ static noinline void __init check_new_node(struct maple_tree *mt)
 	mas.node = MA_ERROR(-ENOMEM);
 	mas_node_count(&mas, 10); /* Request */
 	mas_nomem(&mas, GFP_KERNEL); /* Fill request */
-	mas.node = MAS_START;
+	mas.status = ma_start;
 	MT_BUG_ON(mt, mas_allocated(&mas) != 10);
 	mas_destroy(&mas);
 
@@ -452,7 +456,7 @@ static noinline void __init check_new_node(struct maple_tree *mt)
 	mas.node = MA_ERROR(-ENOMEM);
 	mas_node_count(&mas, 10 + MAPLE_ALLOC_SLOTS - 1); /* Request */
 	mas_nomem(&mas, GFP_KERNEL); /* Fill request */
-	mas.node = MAS_START;
+	mas.status = ma_start;
 	MT_BUG_ON(mt, mas_allocated(&mas) != 10 + MAPLE_ALLOC_SLOTS - 1);
 	mas_destroy(&mas);
 
@@ -941,7 +945,7 @@ retry:
 
 	ret = mas_descend_walk(mas, range_min, range_max);
 	if (unlikely(mte_dead_node(mas->node))) {
-		mas->node = MAS_START;
+		mas->status = ma_start;
 		goto retry;
 	}
 
@@ -961,10 +965,10 @@ static inline void *mas_range_load(struct ma_state *mas,
 	unsigned long index = mas->index;
 
 	if (mas_is_none(mas) || mas_is_paused(mas))
-		mas->node = MAS_START;
+		mas->status = ma_start;
 retry:
 	if (mas_tree_walk(mas, range_min, range_max))
-		if (unlikely(mas->node == MAS_ROOT))
+		if (unlikely(mas->status == ma_root))
 			return mas_root(mas);
 
 	if (likely(mas->offset != MAPLE_NODE_SLOTS))
@@ -35337,7 +35341,7 @@ static void mas_dfs_preorder(struct ma_state *mas)
 	unsigned char end, slot = 0;
 	unsigned long *pivots;
 
-	if (mas->node == MAS_START) {
+	if (mas->status == ma_start) {
 		mas_start(mas);
 		return;
 	}
@@ -35374,7 +35378,7 @@ walk_up:
 
 	return;
 done:
-	mas->node = MAS_NONE;
+	mas->status = ma_none;
 }
 
 
@@ -35833,7 +35837,7 @@ static noinline void __init check_nomem(struct maple_tree *mt)
 	mas_store(&ms, &ms); /* insert 1 -> &ms, fails. */
 	MT_BUG_ON(mt, ms.node != MA_ERROR(-ENOMEM));
 	mas_nomem(&ms, GFP_KERNEL); /* Node allocated in here. */
-	MT_BUG_ON(mt, ms.node != MAS_START);
+	MT_BUG_ON(mt, ms.status != ma_start);
 	mtree_unlock(mt);
 	MT_BUG_ON(mt, mtree_insert(mt, 2, mt, GFP_KERNEL) != 0);
 	mtree_lock(mt);
@@ -35952,7 +35956,7 @@ static int __init compare_tree(struct maple_tree *mt_a, struct maple_tree *mt_b)
 
 	if (mas_is_ptr(&mas_a) || mas_is_ptr(&mas_b)) {
 		if (!(mas_is_ptr(&mas_a) && mas_is_ptr(&mas_b))) {
-			pr_err("One is MAS_ROOT and the other is not.\n");
+			pr_err("One is ma_root and the other is not.\n");
 			return -1;
 		}
 		return 0;
@@ -35961,7 +35965,7 @@ static int __init compare_tree(struct maple_tree *mt_a, struct maple_tree *mt_b)
 	while (!mas_is_none(&mas_a) || !mas_is_none(&mas_b)) {
 
 		if (mas_is_none(&mas_a) || mas_is_none(&mas_b)) {
-			pr_err("One is MAS_NONE and the other is not.\n");
+			pr_err("One is ma_none and the other is not.\n");
 			return -1;
 		}
 
-- 
cgit v1.2.3


From 0de56e38b307b0cb2ac825e8e7cb371a28daf844 Mon Sep 17 00:00:00 2001
From: "Liam R. Howlett" <Liam.Howlett@oracle.com>
Date: Wed, 1 Nov 2023 13:16:27 -0400
Subject: maple_tree: use maple state end for write operations

ma_wr_state was previously tracking the end of the node for writing.
Since the implementation of the ma_state end tracking, this is duplicated
work.  This patch removes the maple write state tracking of the end of the
node and uses the maple state end instead.

Link: https://lkml.kernel.org/r/20231101171629.3612299-11-Liam.Howlett@oracle.com
Signed-off-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Peng Zhang <zhangpeng.00@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/maple_tree.h |  1 -
 lib/maple_tree.c           | 46 ++++++++++++++++++++++++----------------------
 2 files changed, 24 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h
index 4dd668f7b111..b3d63123b945 100644
--- a/include/linux/maple_tree.h
+++ b/include/linux/maple_tree.h
@@ -441,7 +441,6 @@ struct ma_wr_state {
 	unsigned long r_max;		/* range max */
 	enum maple_type type;		/* mas->node type */
 	unsigned char offset_end;	/* The offset where the write ends */
-	unsigned char node_end;		/* mas->node end */
 	unsigned long *pivots;		/* mas->node->pivots pointer */
 	unsigned long end_piv;		/* The pivot at the offset end */
 	void __rcu **slots;		/* mas->node->slots pointer */
diff --git a/lib/maple_tree.c b/lib/maple_tree.c
index c7016066f12b..59500fe6988b 100644
--- a/lib/maple_tree.c
+++ b/lib/maple_tree.c
@@ -2158,11 +2158,11 @@ static noinline_for_kasan void mas_store_b_node(struct ma_wr_state *wr_mas,
 	}
 
 	slot = offset_end + 1;
-	if (slot > wr_mas->node_end)
+	if (slot > mas->end)
 		goto b_end;
 
 	/* Copy end data to the end of the node. */
-	mas_mab_cp(mas, slot, wr_mas->node_end + 1, b_node, ++b_end);
+	mas_mab_cp(mas, slot, mas->end + 1, b_node, ++b_end);
 	b_node->b_end--;
 	return;
 
@@ -2253,8 +2253,8 @@ static inline void mas_wr_node_walk(struct ma_wr_state *wr_mas)
 
 	wr_mas->node = mas_mn(wr_mas->mas);
 	wr_mas->pivots = ma_pivots(wr_mas->node, wr_mas->type);
-	count = wr_mas->node_end = ma_data_end(wr_mas->node, wr_mas->type,
-					       wr_mas->pivots, mas->max);
+	count = mas->end = ma_data_end(wr_mas->node, wr_mas->type,
+				       wr_mas->pivots, mas->max);
 	offset = mas->offset;
 
 	while (offset < count && mas->index > wr_mas->pivots[offset])
@@ -3904,10 +3904,10 @@ static inline int mas_wr_spanning_store(struct ma_wr_state *wr_mas)
 
 	memset(&b_node, 0, sizeof(struct maple_big_node));
 	/* Copy l_mas and store the value in b_node. */
-	mas_store_b_node(&l_wr_mas, &b_node, l_wr_mas.node_end);
+	mas_store_b_node(&l_wr_mas, &b_node, l_mas.end);
 	/* Copy r_mas into b_node. */
-	if (r_mas.offset <= r_wr_mas.node_end)
-		mas_mab_cp(&r_mas, r_mas.offset, r_wr_mas.node_end,
+	if (r_mas.offset <= r_mas.end)
+		mas_mab_cp(&r_mas, r_mas.offset, r_mas.end,
 			   &b_node, b_node.b_end + 1);
 	else
 		b_node.b_end++;
@@ -3949,7 +3949,7 @@ static inline bool mas_wr_node_store(struct ma_wr_state *wr_mas,
 	if (mas->last == wr_mas->end_piv)
 		offset_end++; /* don't copy this offset */
 	else if (unlikely(wr_mas->r_max == ULONG_MAX))
-		mas_bulk_rebalance(mas, wr_mas->node_end, wr_mas->type);
+		mas_bulk_rebalance(mas, mas->end, wr_mas->type);
 
 	/* set up node. */
 	if (in_rcu) {
@@ -3985,12 +3985,12 @@ static inline bool mas_wr_node_store(struct ma_wr_state *wr_mas,
 	 * this range wrote to the end of the node or it overwrote the rest of
 	 * the data
 	 */
-	if (offset_end > wr_mas->node_end)
+	if (offset_end > mas->end)
 		goto done;
 
 	dst_offset = mas->offset + 1;
 	/* Copy to the end of node if necessary. */
-	copy_size = wr_mas->node_end - offset_end + 1;
+	copy_size = mas->end - offset_end + 1;
 	memcpy(dst_slots + dst_offset, wr_mas->slots + offset_end,
 	       sizeof(void *) * copy_size);
 	memcpy(dst_pivots + dst_offset, wr_mas->pivots + offset_end,
@@ -4077,10 +4077,10 @@ static inline void mas_wr_extend_null(struct ma_wr_state *wr_mas)
 	} else {
 		/* Check next slot(s) if we are overwriting the end */
 		if ((mas->last == wr_mas->end_piv) &&
-		    (wr_mas->node_end != wr_mas->offset_end) &&
+		    (mas->end != wr_mas->offset_end) &&
 		    !wr_mas->slots[wr_mas->offset_end + 1]) {
 			wr_mas->offset_end++;
-			if (wr_mas->offset_end == wr_mas->node_end)
+			if (wr_mas->offset_end == mas->end)
 				mas->last = mas->max;
 			else
 				mas->last = wr_mas->pivots[wr_mas->offset_end];
@@ -4105,11 +4105,11 @@ static inline void mas_wr_extend_null(struct ma_wr_state *wr_mas)
 
 static inline void mas_wr_end_piv(struct ma_wr_state *wr_mas)
 {
-	while ((wr_mas->offset_end < wr_mas->node_end) &&
+	while ((wr_mas->offset_end < wr_mas->mas->end) &&
 	       (wr_mas->mas->last > wr_mas->pivots[wr_mas->offset_end]))
 		wr_mas->offset_end++;
 
-	if (wr_mas->offset_end < wr_mas->node_end)
+	if (wr_mas->offset_end < wr_mas->mas->end)
 		wr_mas->end_piv = wr_mas->pivots[wr_mas->offset_end];
 	else
 		wr_mas->end_piv = wr_mas->mas->max;
@@ -4121,7 +4121,7 @@ static inline void mas_wr_end_piv(struct ma_wr_state *wr_mas)
 static inline unsigned char mas_wr_new_end(struct ma_wr_state *wr_mas)
 {
 	struct ma_state *mas = wr_mas->mas;
-	unsigned char new_end = wr_mas->node_end + 2;
+	unsigned char new_end = mas->end + 2;
 
 	new_end -= wr_mas->offset_end - mas->offset;
 	if (wr_mas->r_min == mas->index)
@@ -4155,10 +4155,10 @@ static inline bool mas_wr_append(struct ma_wr_state *wr_mas,
 	if (mt_in_rcu(mas->tree))
 		return false;
 
-	if (mas->offset != wr_mas->node_end)
+	if (mas->offset != mas->end)
 		return false;
 
-	end = wr_mas->node_end;
+	end = mas->end;
 	if (mas->offset != end)
 		return false;
 
@@ -4210,7 +4210,7 @@ static void mas_wr_bnode(struct ma_wr_state *wr_mas)
 	trace_ma_write(__func__, wr_mas->mas, 0, wr_mas->entry);
 	memset(&b_node, 0, sizeof(struct maple_big_node));
 	mas_store_b_node(wr_mas, &b_node, wr_mas->offset_end);
-	mas_commit_b_node(wr_mas, &b_node, wr_mas->node_end);
+	mas_commit_b_node(wr_mas, &b_node, wr_mas->mas->end);
 }
 
 static inline void mas_wr_modify(struct ma_wr_state *wr_mas)
@@ -4238,7 +4238,7 @@ static inline void mas_wr_modify(struct ma_wr_state *wr_mas)
 	if (mas_wr_append(wr_mas, new_end))
 		return;
 
-	if (new_end == wr_mas->node_end && mas_wr_slot_store(wr_mas))
+	if (new_end == mas->end && mas_wr_slot_store(wr_mas))
 		return;
 
 	if (mas_wr_node_store(wr_mas, new_end))
@@ -5052,6 +5052,7 @@ int mas_empty_area(struct ma_state *mas, unsigned long min,
 	unsigned char offset;
 	unsigned long *pivots;
 	enum maple_type mt;
+	struct maple_node *node;
 
 	if (min > max)
 		return -EINVAL;
@@ -5082,13 +5083,14 @@ int mas_empty_area(struct ma_state *mas, unsigned long min,
 	if (unlikely(offset == MAPLE_NODE_SLOTS))
 		return -EBUSY;
 
+	node = mas_mn(mas);
 	mt = mte_node_type(mas->node);
-	pivots = ma_pivots(mas_mn(mas), mt);
+	pivots = ma_pivots(node, mt);
 	min = mas_safe_min(mas, pivots, offset);
 	if (mas->index < min)
 		mas->index = min;
 	mas->last = mas->index + size - 1;
-	mas->end = mas_data_end(mas);
+	mas->end = ma_data_end(node, mt, pivots, mas->max);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(mas_empty_area);
@@ -7596,7 +7598,7 @@ void mas_wr_dump(const struct ma_wr_state *wr_mas)
 	pr_err("WR_MAS: node=%p r_min=%lx r_max=%lx\n",
 	       wr_mas->node, wr_mas->r_min, wr_mas->r_max);
 	pr_err("        type=%u off_end=%u, node_end=%u, end_piv=%lx\n",
-	       wr_mas->type, wr_mas->offset_end, wr_mas->node_end,
+	       wr_mas->type, wr_mas->offset_end, wr_mas->mas->end,
 	       wr_mas->end_piv);
 }
 EXPORT_SYMBOL_GPL(mas_wr_dump);
-- 
cgit v1.2.3


From 0a97c01cd20bb96359d8c9dedad92a061ed34e0b Mon Sep 17 00:00:00 2001
From: Nhat Pham <nphamcs@gmail.com>
Date: Thu, 30 Nov 2023 11:40:18 -0800
Subject: list_lru: allow explicit memcg and NUMA node selection

Patch series "workload-specific and memory pressure-driven zswap
writeback", v8.

There are currently several issues with zswap writeback:

1. There is only a single global LRU for zswap, making it impossible to
   perform worload-specific shrinking - an memcg under memory pressure
   cannot determine which pages in the pool it owns, and often ends up
   writing pages from other memcgs. This issue has been previously
   observed in practice and mitigated by simply disabling
   memcg-initiated shrinking:

   https://lore.kernel.org/all/20230530232435.3097106-1-nphamcs@gmail.com/T/#u

   But this solution leaves a lot to be desired, as we still do not
   have an avenue for an memcg to free up its own memory locked up in
   the zswap pool.

2. We only shrink the zswap pool when the user-defined limit is hit.
   This means that if we set the limit too high, cold data that are
   unlikely to be used again will reside in the pool, wasting precious
   memory. It is hard to predict how much zswap space will be needed
   ahead of time, as this depends on the workload (specifically, on
   factors such as memory access patterns and compressibility of the
   memory pages).

This patch series solves these issues by separating the global zswap LRU
into per-memcg and per-NUMA LRUs, and performs workload-specific (i.e
memcg- and NUMA-aware) zswap writeback under memory pressure.  The new
shrinker does not have any parameter that must be tuned by the user, and
can be opted in or out on a per-memcg basis.

As a proof of concept, we ran the following synthetic benchmark: build the
linux kernel in a memory-limited cgroup, and allocate some cold data in
tmpfs to see if the shrinker could write them out and improved the overall
performance.  Depending on the amount of cold data generated, we observe
from 14% to 35% reduction in kernel CPU time used in the kernel builds.


This patch (of 6):

The interface of list_lru is based on the assumption that the list node
and the data it represents belong to the same allocated on the correct
node/memcg.  While this assumption is valid for existing slab objects LRU
such as dentries and inodes, it is undocumented, and rather inflexible for
certain potential list_lru users (such as the upcoming zswap shrinker and
the THP shrinker).  It has caused us a lot of issues during our
development.

This patch changes list_lru interface so that the caller must explicitly
specify numa node and memcg when adding and removing objects.  The old
list_lru_add() and list_lru_del() are renamed to list_lru_add_obj() and
list_lru_del_obj(), respectively.

It also extends the list_lru API with a new function, list_lru_putback,
which undoes a previous list_lru_isolate call.  Unlike list_lru_add, it
does not increment the LRU node count (as list_lru_isolate does not
decrement the node count).  list_lru_putback also allows for explicit
memcg and NUMA node selection.

Link: https://lkml.kernel.org/r/20231130194023.4102148-1-nphamcs@gmail.com
Link: https://lkml.kernel.org/r/20231130194023.4102148-2-nphamcs@gmail.com
Signed-off-by: Nhat Pham <nphamcs@gmail.com>
Suggested-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Tested-by: Bagas Sanjaya <bagasdotme@gmail.com>
Cc: Chris Li <chrisl@kernel.org>
Cc: Dan Streetman <ddstreet@ieee.org>
Cc: Domenico Cerasuolo <cerasuolodomenico@gmail.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Seth Jennings <sjenning@redhat.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Vitaly Wool <vitaly.wool@konsulko.com>
Cc: Yosry Ahmed <yosryahmed@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 drivers/android/binder_alloc.c |  7 +++---
 fs/dcache.c                    |  8 ++++---
 fs/gfs2/quota.c                |  6 ++---
 fs/inode.c                     |  4 ++--
 fs/nfs/nfs42xattr.c            |  8 +++----
 fs/nfsd/filecache.c            |  4 ++--
 fs/xfs/xfs_buf.c               |  6 ++---
 fs/xfs/xfs_dquot.c             |  2 +-
 fs/xfs/xfs_qm.c                |  2 +-
 include/linux/list_lru.h       | 54 +++++++++++++++++++++++++++++++++++++++---
 mm/list_lru.c                  | 48 ++++++++++++++++++++++++++++++-------
 mm/workingset.c                |  4 ++--
 12 files changed, 117 insertions(+), 36 deletions(-)

(limited to 'include')

diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 138f6d43d13b..f69d30c9f50f 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -234,7 +234,7 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate,
 		if (page->page_ptr) {
 			trace_binder_alloc_lru_start(alloc, index);
 
-			on_lru = list_lru_del(&binder_alloc_lru, &page->lru);
+			on_lru = list_lru_del_obj(&binder_alloc_lru, &page->lru);
 			WARN_ON(!on_lru);
 
 			trace_binder_alloc_lru_end(alloc, index);
@@ -285,7 +285,7 @@ free_range:
 
 		trace_binder_free_lru_start(alloc, index);
 
-		ret = list_lru_add(&binder_alloc_lru, &page->lru);
+		ret = list_lru_add_obj(&binder_alloc_lru, &page->lru);
 		WARN_ON(!ret);
 
 		trace_binder_free_lru_end(alloc, index);
@@ -848,7 +848,7 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc)
 			if (!alloc->pages[i].page_ptr)
 				continue;
 
-			on_lru = list_lru_del(&binder_alloc_lru,
+			on_lru = list_lru_del_obj(&binder_alloc_lru,
 					      &alloc->pages[i].lru);
 			page_addr = alloc->buffer + i * PAGE_SIZE;
 			binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
@@ -1287,4 +1287,3 @@ int binder_alloc_copy_from_buffer(struct binder_alloc *alloc,
 	return binder_alloc_do_buffer_copy(alloc, false, buffer, buffer_offset,
 					   dest, bytes);
 }
-
diff --git a/fs/dcache.c b/fs/dcache.c
index c82ae731df9a..2ba37643b9c5 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -428,7 +428,8 @@ static void d_lru_add(struct dentry *dentry)
 	this_cpu_inc(nr_dentry_unused);
 	if (d_is_negative(dentry))
 		this_cpu_inc(nr_dentry_negative);
-	WARN_ON_ONCE(!list_lru_add(&dentry->d_sb->s_dentry_lru, &dentry->d_lru));
+	WARN_ON_ONCE(!list_lru_add_obj(
+			&dentry->d_sb->s_dentry_lru, &dentry->d_lru));
 }
 
 static void d_lru_del(struct dentry *dentry)
@@ -438,7 +439,8 @@ static void d_lru_del(struct dentry *dentry)
 	this_cpu_dec(nr_dentry_unused);
 	if (d_is_negative(dentry))
 		this_cpu_dec(nr_dentry_negative);
-	WARN_ON_ONCE(!list_lru_del(&dentry->d_sb->s_dentry_lru, &dentry->d_lru));
+	WARN_ON_ONCE(!list_lru_del_obj(
+			&dentry->d_sb->s_dentry_lru, &dentry->d_lru));
 }
 
 static void d_shrink_del(struct dentry *dentry)
@@ -1240,7 +1242,7 @@ static enum lru_status dentry_lru_isolate(struct list_head *item,
 		 *
 		 * This is guaranteed by the fact that all LRU management
 		 * functions are intermediated by the LRU API calls like
-		 * list_lru_add and list_lru_del. List movement in this file
+		 * list_lru_add_obj and list_lru_del_obj. List movement in this file
 		 * only ever occur through this functions or through callbacks
 		 * like this one, that are called from the LRU API.
 		 *
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 95dae7838b4e..b57f8c7b35be 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -271,7 +271,7 @@ static struct gfs2_quota_data *gfs2_qd_search_bucket(unsigned int hash,
 		if (qd->qd_sbd != sdp)
 			continue;
 		if (lockref_get_not_dead(&qd->qd_lockref)) {
-			list_lru_del(&gfs2_qd_lru, &qd->qd_lru);
+			list_lru_del_obj(&gfs2_qd_lru, &qd->qd_lru);
 			return qd;
 		}
 	}
@@ -344,7 +344,7 @@ static void qd_put(struct gfs2_quota_data *qd)
 	}
 
 	qd->qd_lockref.count = 0;
-	list_lru_add(&gfs2_qd_lru, &qd->qd_lru);
+	list_lru_add_obj(&gfs2_qd_lru, &qd->qd_lru);
 	spin_unlock(&qd->qd_lockref.lock);
 }
 
@@ -1517,7 +1517,7 @@ void gfs2_quota_cleanup(struct gfs2_sbd *sdp)
 		lockref_mark_dead(&qd->qd_lockref);
 		spin_unlock(&qd->qd_lockref.lock);
 
-		list_lru_del(&gfs2_qd_lru, &qd->qd_lru);
+		list_lru_del_obj(&gfs2_qd_lru, &qd->qd_lru);
 		list_add(&qd->qd_lru, &dispose);
 	}
 	spin_unlock(&qd_lock);
diff --git a/fs/inode.c b/fs/inode.c
index f238d987dec9..ef2034a985e0 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -464,7 +464,7 @@ static void __inode_add_lru(struct inode *inode, bool rotate)
 	if (!mapping_shrinkable(&inode->i_data))
 		return;
 
-	if (list_lru_add(&inode->i_sb->s_inode_lru, &inode->i_lru))
+	if (list_lru_add_obj(&inode->i_sb->s_inode_lru, &inode->i_lru))
 		this_cpu_inc(nr_unused);
 	else if (rotate)
 		inode->i_state |= I_REFERENCED;
@@ -482,7 +482,7 @@ void inode_add_lru(struct inode *inode)
 
 static void inode_lru_list_del(struct inode *inode)
 {
-	if (list_lru_del(&inode->i_sb->s_inode_lru, &inode->i_lru))
+	if (list_lru_del_obj(&inode->i_sb->s_inode_lru, &inode->i_lru))
 		this_cpu_dec(nr_unused);
 }
 
diff --git a/fs/nfs/nfs42xattr.c b/fs/nfs/nfs42xattr.c
index 2ad66a8922f4..49aaf28a6950 100644
--- a/fs/nfs/nfs42xattr.c
+++ b/fs/nfs/nfs42xattr.c
@@ -132,7 +132,7 @@ nfs4_xattr_entry_lru_add(struct nfs4_xattr_entry *entry)
 	lru = (entry->flags & NFS4_XATTR_ENTRY_EXTVAL) ?
 	    &nfs4_xattr_large_entry_lru : &nfs4_xattr_entry_lru;
 
-	return list_lru_add(lru, &entry->lru);
+	return list_lru_add_obj(lru, &entry->lru);
 }
 
 static bool
@@ -143,7 +143,7 @@ nfs4_xattr_entry_lru_del(struct nfs4_xattr_entry *entry)
 	lru = (entry->flags & NFS4_XATTR_ENTRY_EXTVAL) ?
 	    &nfs4_xattr_large_entry_lru : &nfs4_xattr_entry_lru;
 
-	return list_lru_del(lru, &entry->lru);
+	return list_lru_del_obj(lru, &entry->lru);
 }
 
 /*
@@ -349,7 +349,7 @@ nfs4_xattr_cache_unlink(struct inode *inode)
 
 	oldcache = nfsi->xattr_cache;
 	if (oldcache != NULL) {
-		list_lru_del(&nfs4_xattr_cache_lru, &oldcache->lru);
+		list_lru_del_obj(&nfs4_xattr_cache_lru, &oldcache->lru);
 		oldcache->inode = NULL;
 	}
 	nfsi->xattr_cache = NULL;
@@ -474,7 +474,7 @@ nfs4_xattr_get_cache(struct inode *inode, int add)
 			kref_get(&cache->ref);
 			nfsi->xattr_cache = cache;
 			cache->inode = inode;
-			list_lru_add(&nfs4_xattr_cache_lru, &cache->lru);
+			list_lru_add_obj(&nfs4_xattr_cache_lru, &cache->lru);
 		}
 
 		spin_unlock(&inode->i_lock);
diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index ef063f93fde9..6c2decfdeb4b 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -322,7 +322,7 @@ nfsd_file_check_writeback(struct nfsd_file *nf)
 static bool nfsd_file_lru_add(struct nfsd_file *nf)
 {
 	set_bit(NFSD_FILE_REFERENCED, &nf->nf_flags);
-	if (list_lru_add(&nfsd_file_lru, &nf->nf_lru)) {
+	if (list_lru_add_obj(&nfsd_file_lru, &nf->nf_lru)) {
 		trace_nfsd_file_lru_add(nf);
 		return true;
 	}
@@ -331,7 +331,7 @@ static bool nfsd_file_lru_add(struct nfsd_file *nf)
 
 static bool nfsd_file_lru_remove(struct nfsd_file *nf)
 {
-	if (list_lru_del(&nfsd_file_lru, &nf->nf_lru)) {
+	if (list_lru_del_obj(&nfsd_file_lru, &nf->nf_lru)) {
 		trace_nfsd_file_lru_del(nf);
 		return true;
 	}
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 545c7991b9b5..669332849680 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -169,7 +169,7 @@ xfs_buf_stale(
 
 	atomic_set(&bp->b_lru_ref, 0);
 	if (!(bp->b_state & XFS_BSTATE_DISPOSE) &&
-	    (list_lru_del(&bp->b_target->bt_lru, &bp->b_lru)))
+	    (list_lru_del_obj(&bp->b_target->bt_lru, &bp->b_lru)))
 		atomic_dec(&bp->b_hold);
 
 	ASSERT(atomic_read(&bp->b_hold) >= 1);
@@ -1047,7 +1047,7 @@ xfs_buf_rele(
 		 * buffer for the LRU and clear the (now stale) dispose list
 		 * state flag
 		 */
-		if (list_lru_add(&bp->b_target->bt_lru, &bp->b_lru)) {
+		if (list_lru_add_obj(&bp->b_target->bt_lru, &bp->b_lru)) {
 			bp->b_state &= ~XFS_BSTATE_DISPOSE;
 			atomic_inc(&bp->b_hold);
 		}
@@ -1060,7 +1060,7 @@ xfs_buf_rele(
 		 * was on was the disposal list
 		 */
 		if (!(bp->b_state & XFS_BSTATE_DISPOSE)) {
-			list_lru_del(&bp->b_target->bt_lru, &bp->b_lru);
+			list_lru_del_obj(&bp->b_target->bt_lru, &bp->b_lru);
 		} else {
 			ASSERT(list_empty(&bp->b_lru));
 		}
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index a013b87ab8d5..61a45a86ffe8 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -1065,7 +1065,7 @@ xfs_qm_dqput(
 		struct xfs_quotainfo	*qi = dqp->q_mount->m_quotainfo;
 		trace_xfs_dqput_free(dqp);
 
-		if (list_lru_add(&qi->qi_lru, &dqp->q_lru))
+		if (list_lru_add_obj(&qi->qi_lru, &dqp->q_lru))
 			XFS_STATS_INC(dqp->q_mount, xs_qm_dquot_unused);
 	}
 	xfs_dqunlock(dqp);
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 94a7932ac570..67d0a8564ff3 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -171,7 +171,7 @@ xfs_qm_dqpurge(
 	 * hits zero, so it really should be on the freelist here.
 	 */
 	ASSERT(!list_empty(&dqp->q_lru));
-	list_lru_del(&qi->qi_lru, &dqp->q_lru);
+	list_lru_del_obj(&qi->qi_lru, &dqp->q_lru);
 	XFS_STATS_DEC(dqp->q_mount, xs_qm_dquot_unused);
 
 	xfs_qm_dqdestroy(dqp);
diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index db86ad78d428..7675a48a0701 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -75,6 +75,8 @@ void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *paren
  * list_lru_add: add an element to the lru list's tail
  * @lru: the lru pointer
  * @item: the item to be added.
+ * @nid: the node id of the sublist to add the item to.
+ * @memcg: the cgroup of the sublist to add the item to.
  *
  * If the element is already part of a list, this function returns doing
  * nothing. Therefore the caller does not need to keep state about whether or
@@ -87,12 +89,28 @@ void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *paren
  *
  * Return: true if the list was updated, false otherwise
  */
-bool list_lru_add(struct list_lru *lru, struct list_head *item);
+bool list_lru_add(struct list_lru *lru, struct list_head *item, int nid,
+		    struct mem_cgroup *memcg);
 
 /**
- * list_lru_del: delete an element to the lru list
+ * list_lru_add_obj: add an element to the lru list's tail
+ * @lru: the lru pointer
+ * @item: the item to be added.
+ *
+ * This function is similar to list_lru_add(), but the NUMA node and the
+ * memcg of the sublist is determined by @item list_head. This assumption is
+ * valid for slab objects LRU such as dentries, inodes, etc.
+ *
+ * Return value: true if the list was updated, false otherwise
+ */
+bool list_lru_add_obj(struct list_lru *lru, struct list_head *item);
+
+/**
+ * list_lru_del: delete an element from the lru list
  * @lru: the lru pointer
  * @item: the item to be deleted.
+ * @nid: the node id of the sublist to delete the item from.
+ * @memcg: the cgroup of the sublist to delete the item from.
  *
  * This function works analogously as list_lru_add() in terms of list
  * manipulation. The comments about an element already pertaining to
@@ -100,7 +118,21 @@ bool list_lru_add(struct list_lru *lru, struct list_head *item);
  *
  * Return: true if the list was updated, false otherwise
  */
-bool list_lru_del(struct list_lru *lru, struct list_head *item);
+bool list_lru_del(struct list_lru *lru, struct list_head *item, int nid,
+		    struct mem_cgroup *memcg);
+
+/**
+ * list_lru_del_obj: delete an element from the lru list
+ * @lru: the lru pointer
+ * @item: the item to be deleted.
+ *
+ * This function is similar to list_lru_del(), but the NUMA node and the
+ * memcg of the sublist is determined by @item list_head. This assumption is
+ * valid for slab objects LRU such as dentries, inodes, etc.
+ *
+ * Return value: true if the list was updated, false otherwise.
+ */
+bool list_lru_del_obj(struct list_lru *lru, struct list_head *item);
 
 /**
  * list_lru_count_one: return the number of objects currently held by @lru
@@ -138,6 +170,22 @@ static inline unsigned long list_lru_count(struct list_lru *lru)
 void list_lru_isolate(struct list_lru_one *list, struct list_head *item);
 void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item,
 			   struct list_head *head);
+/**
+ * list_lru_putback: undo list_lru_isolate
+ * @lru: the lru pointer.
+ * @item: the item to put back.
+ * @nid: the node id of the sublist to put the item back to.
+ * @memcg: the cgroup of the sublist to put the item back to.
+ *
+ * Put back an isolated item into its original LRU. Note that unlike
+ * list_lru_add, this does not increment the node LRU count (as
+ * list_lru_isolate does not originally decrement this count).
+ *
+ * Since we might have dropped the LRU lock in between, recompute list_lru_one
+ * from the node's id and memcg.
+ */
+void list_lru_putback(struct list_lru *lru, struct list_head *item, int nid,
+		      struct mem_cgroup *memcg);
 
 typedef enum lru_status (*list_lru_walk_cb)(struct list_head *item,
 		struct list_lru_one *list, spinlock_t *lock, void *cb_arg);
diff --git a/mm/list_lru.c b/mm/list_lru.c
index a05e5bef3b40..fcca67ac26ec 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -116,21 +116,19 @@ list_lru_from_kmem(struct list_lru *lru, int nid, void *ptr,
 }
 #endif /* CONFIG_MEMCG_KMEM */
 
-bool list_lru_add(struct list_lru *lru, struct list_head *item)
+bool list_lru_add(struct list_lru *lru, struct list_head *item, int nid,
+		    struct mem_cgroup *memcg)
 {
-	int nid = page_to_nid(virt_to_page(item));
 	struct list_lru_node *nlru = &lru->node[nid];
-	struct mem_cgroup *memcg;
 	struct list_lru_one *l;
 
 	spin_lock(&nlru->lock);
 	if (list_empty(item)) {
-		l = list_lru_from_kmem(lru, nid, item, &memcg);
+		l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg));
 		list_add_tail(item, &l->list);
 		/* Set shrinker bit if the first element was added */
 		if (!l->nr_items++)
-			set_shrinker_bit(memcg, nid,
-					 lru_shrinker_id(lru));
+			set_shrinker_bit(memcg, nid, lru_shrinker_id(lru));
 		nlru->nr_items++;
 		spin_unlock(&nlru->lock);
 		return true;
@@ -140,15 +138,25 @@ bool list_lru_add(struct list_lru *lru, struct list_head *item)
 }
 EXPORT_SYMBOL_GPL(list_lru_add);
 
-bool list_lru_del(struct list_lru *lru, struct list_head *item)
+bool list_lru_add_obj(struct list_lru *lru, struct list_head *item)
 {
 	int nid = page_to_nid(virt_to_page(item));
+	struct mem_cgroup *memcg = list_lru_memcg_aware(lru) ?
+		mem_cgroup_from_slab_obj(item) : NULL;
+
+	return list_lru_add(lru, item, nid, memcg);
+}
+EXPORT_SYMBOL_GPL(list_lru_add_obj);
+
+bool list_lru_del(struct list_lru *lru, struct list_head *item, int nid,
+		    struct mem_cgroup *memcg)
+{
 	struct list_lru_node *nlru = &lru->node[nid];
 	struct list_lru_one *l;
 
 	spin_lock(&nlru->lock);
 	if (!list_empty(item)) {
-		l = list_lru_from_kmem(lru, nid, item, NULL);
+		l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg));
 		list_del_init(item);
 		l->nr_items--;
 		nlru->nr_items--;
@@ -160,6 +168,16 @@ bool list_lru_del(struct list_lru *lru, struct list_head *item)
 }
 EXPORT_SYMBOL_GPL(list_lru_del);
 
+bool list_lru_del_obj(struct list_lru *lru, struct list_head *item)
+{
+	int nid = page_to_nid(virt_to_page(item));
+	struct mem_cgroup *memcg = list_lru_memcg_aware(lru) ?
+		mem_cgroup_from_slab_obj(item) : NULL;
+
+	return list_lru_del(lru, item, nid, memcg);
+}
+EXPORT_SYMBOL_GPL(list_lru_del_obj);
+
 void list_lru_isolate(struct list_lru_one *list, struct list_head *item)
 {
 	list_del_init(item);
@@ -175,6 +193,20 @@ void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item,
 }
 EXPORT_SYMBOL_GPL(list_lru_isolate_move);
 
+void list_lru_putback(struct list_lru *lru, struct list_head *item, int nid,
+		      struct mem_cgroup *memcg)
+{
+	struct list_lru_one *list =
+		list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg));
+
+	if (list_empty(item)) {
+		list_add_tail(item, &list->list);
+		if (!list->nr_items++)
+			set_shrinker_bit(memcg, nid, lru_shrinker_id(lru));
+	}
+}
+EXPORT_SYMBOL_GPL(list_lru_putback);
+
 unsigned long list_lru_count_one(struct list_lru *lru,
 				 int nid, struct mem_cgroup *memcg)
 {
diff --git a/mm/workingset.c b/mm/workingset.c
index b192e44a0e7c..c17d45c6f29b 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -615,12 +615,12 @@ void workingset_update_node(struct xa_node *node)
 
 	if (node->count && node->count == node->nr_values) {
 		if (list_empty(&node->private_list)) {
-			list_lru_add(&shadow_nodes, &node->private_list);
+			list_lru_add_obj(&shadow_nodes, &node->private_list);
 			__inc_lruvec_kmem_state(node, WORKINGSET_NODES);
 		}
 	} else {
 		if (!list_empty(&node->private_list)) {
-			list_lru_del(&shadow_nodes, &node->private_list);
+			list_lru_del_obj(&shadow_nodes, &node->private_list);
 			__dec_lruvec_kmem_state(node, WORKINGSET_NODES);
 		}
 	}
-- 
cgit v1.2.3


From fdc4161ff6a5e96222e159c1f1b28d31a985130d Mon Sep 17 00:00:00 2001
From: Nhat Pham <nphamcs@gmail.com>
Date: Thu, 30 Nov 2023 11:40:19 -0800
Subject: memcontrol: implement mem_cgroup_tryget_online()

This patch implements a helper function that try to get a reference to an
memcg's css, as well as checking if it is online.  This new function is
almost exactly the same as the existing mem_cgroup_tryget(), except for
the onlineness check.  In the !CONFIG_MEMCG case, it always returns true,
analogous to mem_cgroup_tryget().  This is useful for e.g to the new zswap
writeback scheme, where we need to select the next online memcg as a
candidate for the global limit reclaim.

Link: https://lkml.kernel.org/r/20231130194023.4102148-3-nphamcs@gmail.com
Signed-off-by: Nhat Pham <nphamcs@gmail.com>
Tested-by: Bagas Sanjaya <bagasdotme@gmail.com>
Reviewed-by: Yosry Ahmed <yosryahmed@google.com>
Cc: Chris Li <chrisl@kernel.org>
Cc: Dan Streetman <ddstreet@ieee.org>
Cc: Domenico Cerasuolo <cerasuolodomenico@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Seth Jennings <sjenning@redhat.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Vitaly Wool <vitaly.wool@konsulko.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/memcontrol.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'include')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 7bdcf3020d7a..2bd7d14ace78 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -821,6 +821,11 @@ static inline bool mem_cgroup_tryget(struct mem_cgroup *memcg)
 	return !memcg || css_tryget(&memcg->css);
 }
 
+static inline bool mem_cgroup_tryget_online(struct mem_cgroup *memcg)
+{
+	return !memcg || css_tryget_online(&memcg->css);
+}
+
 static inline void mem_cgroup_put(struct mem_cgroup *memcg)
 {
 	if (memcg)
@@ -1349,6 +1354,11 @@ static inline bool mem_cgroup_tryget(struct mem_cgroup *memcg)
 	return true;
 }
 
+static inline bool mem_cgroup_tryget_online(struct mem_cgroup *memcg)
+{
+	return true;
+}
+
 static inline void mem_cgroup_put(struct mem_cgroup *memcg)
 {
 }
-- 
cgit v1.2.3


From a65b0e7607ccb5e5184591f73e48512f25c76061 Mon Sep 17 00:00:00 2001
From: Domenico Cerasuolo <cerasuolodomenico@gmail.com>
Date: Thu, 30 Nov 2023 11:40:20 -0800
Subject: zswap: make shrinking memcg-aware

Currently, we only have a single global LRU for zswap.  This makes it
impossible to perform worload-specific shrinking - an memcg cannot
determine which pages in the pool it owns, and often ends up writing pages
from other memcgs.  This issue has been previously observed in practice
and mitigated by simply disabling memcg-initiated shrinking:

https://lore.kernel.org/all/20230530232435.3097106-1-nphamcs@gmail.com/T/#u

This patch fully resolves the issue by replacing the global zswap LRU
with memcg- and NUMA-specific LRUs, and modify the reclaim logic:

a) When a store attempt hits an memcg limit, it now triggers a
   synchronous reclaim attempt that, if successful, allows the new
   hotter page to be accepted by zswap.
b) If the store attempt instead hits the global zswap limit, it will
   trigger an asynchronous reclaim attempt, in which an memcg is
   selected for reclaim in a round-robin-like fashion.

[nphamcs@gmail.com: use correct function for the onlineness check, use mem_cgroup_iter_break()]
  Link: https://lkml.kernel.org/r/20231205195419.2563217-1-nphamcs@gmail.com
[nphamcs@gmail.com: drop the pool's reference at the end of the writeback step]
  Link: https://lkml.kernel.org/r/20231206030627.4155634-1-nphamcs@gmail.com
Link: https://lkml.kernel.org/r/20231130194023.4102148-4-nphamcs@gmail.com
Signed-off-by: Domenico Cerasuolo <cerasuolodomenico@gmail.com>
Co-developed-by: Nhat Pham <nphamcs@gmail.com>
Signed-off-by: Nhat Pham <nphamcs@gmail.com>
Tested-by: Bagas Sanjaya <bagasdotme@gmail.com>
Cc: Chris Li <chrisl@kernel.org>
Cc: Dan Streetman <ddstreet@ieee.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Seth Jennings <sjenning@redhat.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Vitaly Wool <vitaly.wool@konsulko.com>
Cc: Yosry Ahmed <yosryahmed@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/memcontrol.h |   5 +
 include/linux/zswap.h      |   2 +
 mm/memcontrol.c            |   2 +
 mm/swap.h                  |   3 +-
 mm/swap_state.c            |  24 +++-
 mm/zswap.c                 | 268 ++++++++++++++++++++++++++++++++++++---------
 6 files changed, 245 insertions(+), 59 deletions(-)

(limited to 'include')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 2bd7d14ace78..a308c8eacf20 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -1192,6 +1192,11 @@ static inline struct mem_cgroup *page_memcg_check(struct page *page)
 	return NULL;
 }
 
+static inline struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg)
+{
+	return NULL;
+}
+
 static inline bool folio_memcg_kmem(struct folio *folio)
 {
 	return false;
diff --git a/include/linux/zswap.h b/include/linux/zswap.h
index 2a60ce39cfde..e571e393669b 100644
--- a/include/linux/zswap.h
+++ b/include/linux/zswap.h
@@ -15,6 +15,7 @@ bool zswap_load(struct folio *folio);
 void zswap_invalidate(int type, pgoff_t offset);
 void zswap_swapon(int type);
 void zswap_swapoff(int type);
+void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg);
 
 #else
 
@@ -31,6 +32,7 @@ static inline bool zswap_load(struct folio *folio)
 static inline void zswap_invalidate(int type, pgoff_t offset) {}
 static inline void zswap_swapon(int type) {}
 static inline void zswap_swapoff(int type) {}
+static inline void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg) {}
 
 #endif
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 592572d4842e..ce75e504fe8b 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5614,6 +5614,8 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
 	page_counter_set_min(&memcg->memory, 0);
 	page_counter_set_low(&memcg->memory, 0);
 
+	zswap_memcg_offline_cleanup(memcg);
+
 	memcg_offline_kmem(memcg);
 	reparent_shrinker_deferred(memcg);
 	wb_memcg_offline(memcg);
diff --git a/mm/swap.h b/mm/swap.h
index 73c332ee4d91..c0dc73e10e91 100644
--- a/mm/swap.h
+++ b/mm/swap.h
@@ -51,7 +51,8 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 				   struct swap_iocb **plug);
 struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 				     struct mempolicy *mpol, pgoff_t ilx,
-				     bool *new_page_allocated);
+				     bool *new_page_allocated,
+				     bool skip_if_exists);
 struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t flag,
 				    struct mempolicy *mpol, pgoff_t ilx);
 struct page *swapin_readahead(swp_entry_t entry, gfp_t flag,
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 85d9e5806a6a..6c84236382f3 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -412,7 +412,8 @@ struct folio *filemap_get_incore_folio(struct address_space *mapping,
 
 struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 				     struct mempolicy *mpol, pgoff_t ilx,
-				     bool *new_page_allocated)
+				     bool *new_page_allocated,
+				     bool skip_if_exists)
 {
 	struct swap_info_struct *si;
 	struct folio *folio;
@@ -470,6 +471,17 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		if (err != -EEXIST)
 			goto fail_put_swap;
 
+		/*
+		 * Protect against a recursive call to __read_swap_cache_async()
+		 * on the same entry waiting forever here because SWAP_HAS_CACHE
+		 * is set but the folio is not the swap cache yet. This can
+		 * happen today if mem_cgroup_swapin_charge_folio() below
+		 * triggers reclaim through zswap, which may call
+		 * __read_swap_cache_async() in the writeback path.
+		 */
+		if (skip_if_exists)
+			goto fail_put_swap;
+
 		/*
 		 * We might race against __delete_from_swap_cache(), and
 		 * stumble across a swap_map entry whose SWAP_HAS_CACHE
@@ -537,7 +549,7 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 
 	mpol = get_vma_policy(vma, addr, 0, &ilx);
 	page = __read_swap_cache_async(entry, gfp_mask, mpol, ilx,
-					&page_allocated);
+					&page_allocated, false);
 	mpol_cond_put(mpol);
 
 	if (page_allocated)
@@ -654,7 +666,7 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
 		/* Ok, do the async read-ahead now */
 		page = __read_swap_cache_async(
 				swp_entry(swp_type(entry), offset),
-				gfp_mask, mpol, ilx, &page_allocated);
+				gfp_mask, mpol, ilx, &page_allocated, false);
 		if (!page)
 			continue;
 		if (page_allocated) {
@@ -672,7 +684,7 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
 skip:
 	/* The page was likely read above, so no need for plugging here */
 	page = __read_swap_cache_async(entry, gfp_mask, mpol, ilx,
-					&page_allocated);
+					&page_allocated, false);
 	if (unlikely(page_allocated))
 		swap_readpage(page, false, NULL);
 	return page;
@@ -827,7 +839,7 @@ static struct page *swap_vma_readahead(swp_entry_t targ_entry, gfp_t gfp_mask,
 		pte_unmap(pte);
 		pte = NULL;
 		page = __read_swap_cache_async(entry, gfp_mask, mpol, ilx,
-						&page_allocated);
+						&page_allocated, false);
 		if (!page)
 			continue;
 		if (page_allocated) {
@@ -847,7 +859,7 @@ static struct page *swap_vma_readahead(swp_entry_t targ_entry, gfp_t gfp_mask,
 skip:
 	/* The page was likely read above, so no need for plugging here */
 	page = __read_swap_cache_async(targ_entry, gfp_mask, mpol, targ_ilx,
-					&page_allocated);
+					&page_allocated, false);
 	if (unlikely(page_allocated))
 		swap_readpage(page, false, NULL);
 	return page;
diff --git a/mm/zswap.c b/mm/zswap.c
index 699c6ee11222..213626e0f659 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -35,6 +35,7 @@
 #include <linux/writeback.h>
 #include <linux/pagemap.h>
 #include <linux/workqueue.h>
+#include <linux/list_lru.h>
 
 #include "swap.h"
 #include "internal.h"
@@ -174,8 +175,8 @@ struct zswap_pool {
 	struct work_struct shrink_work;
 	struct hlist_node node;
 	char tfm_name[CRYPTO_MAX_ALG_NAME];
-	struct list_head lru;
-	spinlock_t lru_lock;
+	struct list_lru list_lru;
+	struct mem_cgroup *next_shrink;
 };
 
 /*
@@ -291,15 +292,46 @@ static void zswap_update_total_size(void)
 	zswap_pool_total_size = total;
 }
 
+/* should be called under RCU */
+#ifdef CONFIG_MEMCG
+static inline struct mem_cgroup *mem_cgroup_from_entry(struct zswap_entry *entry)
+{
+	return entry->objcg ? obj_cgroup_memcg(entry->objcg) : NULL;
+}
+#else
+static inline struct mem_cgroup *mem_cgroup_from_entry(struct zswap_entry *entry)
+{
+	return NULL;
+}
+#endif
+
+static inline int entry_to_nid(struct zswap_entry *entry)
+{
+	return page_to_nid(virt_to_page(entry));
+}
+
+void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg)
+{
+	struct zswap_pool *pool;
+
+	/* lock out zswap pools list modification */
+	spin_lock(&zswap_pools_lock);
+	list_for_each_entry(pool, &zswap_pools, list) {
+		if (pool->next_shrink == memcg)
+			pool->next_shrink = mem_cgroup_iter(NULL, pool->next_shrink, NULL);
+	}
+	spin_unlock(&zswap_pools_lock);
+}
+
 /*********************************
 * zswap entry functions
 **********************************/
 static struct kmem_cache *zswap_entry_cache;
 
-static struct zswap_entry *zswap_entry_cache_alloc(gfp_t gfp)
+static struct zswap_entry *zswap_entry_cache_alloc(gfp_t gfp, int nid)
 {
 	struct zswap_entry *entry;
-	entry = kmem_cache_alloc(zswap_entry_cache, gfp);
+	entry = kmem_cache_alloc_node(zswap_entry_cache, gfp, nid);
 	if (!entry)
 		return NULL;
 	entry->refcount = 1;
@@ -312,6 +344,61 @@ static void zswap_entry_cache_free(struct zswap_entry *entry)
 	kmem_cache_free(zswap_entry_cache, entry);
 }
 
+/*********************************
+* lru functions
+**********************************/
+static void zswap_lru_add(struct list_lru *list_lru, struct zswap_entry *entry)
+{
+	int nid = entry_to_nid(entry);
+	struct mem_cgroup *memcg;
+
+	/*
+	 * Note that it is safe to use rcu_read_lock() here, even in the face of
+	 * concurrent memcg offlining. Thanks to the memcg->kmemcg_id indirection
+	 * used in list_lru lookup, only two scenarios are possible:
+	 *
+	 * 1. list_lru_add() is called before memcg->kmemcg_id is updated. The
+	 *    new entry will be reparented to memcg's parent's list_lru.
+	 * 2. list_lru_add() is called after memcg->kmemcg_id is updated. The
+	 *    new entry will be added directly to memcg's parent's list_lru.
+	 *
+	 * Similar reasoning holds for list_lru_del() and list_lru_putback().
+	 */
+	rcu_read_lock();
+	memcg = mem_cgroup_from_entry(entry);
+	/* will always succeed */
+	list_lru_add(list_lru, &entry->lru, nid, memcg);
+	rcu_read_unlock();
+}
+
+static void zswap_lru_del(struct list_lru *list_lru, struct zswap_entry *entry)
+{
+	int nid = entry_to_nid(entry);
+	struct mem_cgroup *memcg;
+
+	rcu_read_lock();
+	memcg = mem_cgroup_from_entry(entry);
+	/* will always succeed */
+	list_lru_del(list_lru, &entry->lru, nid, memcg);
+	rcu_read_unlock();
+}
+
+static void zswap_lru_putback(struct list_lru *list_lru,
+		struct zswap_entry *entry)
+{
+	int nid = entry_to_nid(entry);
+	spinlock_t *lock = &list_lru->node[nid].lock;
+	struct mem_cgroup *memcg;
+
+	rcu_read_lock();
+	memcg = mem_cgroup_from_entry(entry);
+	spin_lock(lock);
+	/* we cannot use list_lru_add here, because it increments node's lru count */
+	list_lru_putback(list_lru, &entry->lru, nid, memcg);
+	spin_unlock(lock);
+	rcu_read_unlock();
+}
+
 /*********************************
 * rbtree functions
 **********************************/
@@ -396,9 +483,7 @@ static void zswap_free_entry(struct zswap_entry *entry)
 	if (!entry->length)
 		atomic_dec(&zswap_same_filled_pages);
 	else {
-		spin_lock(&entry->pool->lru_lock);
-		list_del(&entry->lru);
-		spin_unlock(&entry->pool->lru_lock);
+		zswap_lru_del(&entry->pool->list_lru, entry);
 		zpool_free(zswap_find_zpool(entry), entry->handle);
 		zswap_pool_put(entry->pool);
 	}
@@ -632,21 +717,15 @@ static void zswap_invalidate_entry(struct zswap_tree *tree,
 		zswap_entry_put(tree, entry);
 }
 
-static int zswap_reclaim_entry(struct zswap_pool *pool)
+static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_one *l,
+				       spinlock_t *lock, void *arg)
 {
-	struct zswap_entry *entry;
+	struct zswap_entry *entry = container_of(item, struct zswap_entry, lru);
 	struct zswap_tree *tree;
 	pgoff_t swpoffset;
-	int ret;
+	enum lru_status ret = LRU_REMOVED_RETRY;
+	int writeback_result;
 
-	/* Get an entry off the LRU */
-	spin_lock(&pool->lru_lock);
-	if (list_empty(&pool->lru)) {
-		spin_unlock(&pool->lru_lock);
-		return -EINVAL;
-	}
-	entry = list_last_entry(&pool->lru, struct zswap_entry, lru);
-	list_del_init(&entry->lru);
 	/*
 	 * Once the lru lock is dropped, the entry might get freed. The
 	 * swpoffset is copied to the stack, and entry isn't deref'd again
@@ -654,28 +733,32 @@ static int zswap_reclaim_entry(struct zswap_pool *pool)
 	 */
 	swpoffset = swp_offset(entry->swpentry);
 	tree = zswap_trees[swp_type(entry->swpentry)];
-	spin_unlock(&pool->lru_lock);
+	list_lru_isolate(l, item);
+	/*
+	 * It's safe to drop the lock here because we return either
+	 * LRU_REMOVED_RETRY or LRU_RETRY.
+	 */
+	spin_unlock(lock);
 
 	/* Check for invalidate() race */
 	spin_lock(&tree->lock);
-	if (entry != zswap_rb_search(&tree->rbroot, swpoffset)) {
-		ret = -EAGAIN;
+	if (entry != zswap_rb_search(&tree->rbroot, swpoffset))
 		goto unlock;
-	}
+
 	/* Hold a reference to prevent a free during writeback */
 	zswap_entry_get(entry);
 	spin_unlock(&tree->lock);
 
-	ret = zswap_writeback_entry(entry, tree);
+	writeback_result = zswap_writeback_entry(entry, tree);
 
 	spin_lock(&tree->lock);
-	if (ret) {
-		/* Writeback failed, put entry back on LRU */
-		spin_lock(&pool->lru_lock);
-		list_move(&entry->lru, &pool->lru);
-		spin_unlock(&pool->lru_lock);
+	if (writeback_result) {
+		zswap_reject_reclaim_fail++;
+		zswap_lru_putback(&entry->pool->list_lru, entry);
+		ret = LRU_RETRY;
 		goto put_unlock;
 	}
+	zswap_written_back_pages++;
 
 	/*
 	 * Writeback started successfully, the page now belongs to the
@@ -689,24 +772,91 @@ put_unlock:
 	zswap_entry_put(tree, entry);
 unlock:
 	spin_unlock(&tree->lock);
-	return ret ? -EAGAIN : 0;
+	spin_lock(lock);
+	return ret;
+}
+
+static int shrink_memcg(struct mem_cgroup *memcg)
+{
+	struct zswap_pool *pool;
+	int nid, shrunk = 0;
+
+	/*
+	 * Skip zombies because their LRUs are reparented and we would be
+	 * reclaiming from the parent instead of the dead memcg.
+	 */
+	if (memcg && !mem_cgroup_online(memcg))
+		return -ENOENT;
+
+	pool = zswap_pool_current_get();
+	if (!pool)
+		return -EINVAL;
+
+	for_each_node_state(nid, N_NORMAL_MEMORY) {
+		unsigned long nr_to_walk = 1;
+
+		shrunk += list_lru_walk_one(&pool->list_lru, nid, memcg,
+					    &shrink_memcg_cb, NULL, &nr_to_walk);
+	}
+	zswap_pool_put(pool);
+	return shrunk ? 0 : -EAGAIN;
 }
 
 static void shrink_worker(struct work_struct *w)
 {
 	struct zswap_pool *pool = container_of(w, typeof(*pool),
 						shrink_work);
+	struct mem_cgroup *memcg;
 	int ret, failures = 0;
 
+	/* global reclaim will select cgroup in a round-robin fashion. */
 	do {
-		ret = zswap_reclaim_entry(pool);
-		if (ret) {
-			zswap_reject_reclaim_fail++;
-			if (ret != -EAGAIN)
+		spin_lock(&zswap_pools_lock);
+		pool->next_shrink = mem_cgroup_iter(NULL, pool->next_shrink, NULL);
+		memcg = pool->next_shrink;
+
+		/*
+		 * We need to retry if we have gone through a full round trip, or if we
+		 * got an offline memcg (or else we risk undoing the effect of the
+		 * zswap memcg offlining cleanup callback). This is not catastrophic
+		 * per se, but it will keep the now offlined memcg hostage for a while.
+		 *
+		 * Note that if we got an online memcg, we will keep the extra
+		 * reference in case the original reference obtained by mem_cgroup_iter
+		 * is dropped by the zswap memcg offlining callback, ensuring that the
+		 * memcg is not killed when we are reclaiming.
+		 */
+		if (!memcg) {
+			spin_unlock(&zswap_pools_lock);
+			if (++failures == MAX_RECLAIM_RETRIES)
 				break;
+
+			goto resched;
+		}
+
+		if (!mem_cgroup_tryget_online(memcg)) {
+			/* drop the reference from mem_cgroup_iter() */
+			mem_cgroup_iter_break(NULL, memcg);
+			pool->next_shrink = NULL;
+			spin_unlock(&zswap_pools_lock);
+
 			if (++failures == MAX_RECLAIM_RETRIES)
 				break;
+
+			goto resched;
 		}
+		spin_unlock(&zswap_pools_lock);
+
+		ret = shrink_memcg(memcg);
+		/* drop the extra reference */
+		mem_cgroup_put(memcg);
+
+		if (ret == -EINVAL)
+			break;
+		if (ret && ++failures == MAX_RECLAIM_RETRIES)
+			break;
+
+resched:
 		cond_resched();
 	} while (!zswap_can_accept());
 	zswap_pool_put(pool);
@@ -767,8 +917,7 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
 	 */
 	kref_init(&pool->kref);
 	INIT_LIST_HEAD(&pool->list);
-	INIT_LIST_HEAD(&pool->lru);
-	spin_lock_init(&pool->lru_lock);
+	list_lru_init_memcg(&pool->list_lru, NULL);
 	INIT_WORK(&pool->shrink_work, shrink_worker);
 
 	zswap_pool_debug("created", pool);
@@ -834,6 +983,13 @@ static void zswap_pool_destroy(struct zswap_pool *pool)
 
 	cpuhp_state_remove_instance(CPUHP_MM_ZSWP_POOL_PREPARE, &pool->node);
 	free_percpu(pool->acomp_ctx);
+	list_lru_destroy(&pool->list_lru);
+
+	spin_lock(&zswap_pools_lock);
+	mem_cgroup_iter_break(NULL, pool->next_shrink);
+	pool->next_shrink = NULL;
+	spin_unlock(&zswap_pools_lock);
+
 	for (i = 0; i < ZSWAP_NR_ZPOOLS; i++)
 		zpool_destroy_pool(pool->zpools[i]);
 	kfree(pool);
@@ -1081,7 +1237,7 @@ static int zswap_writeback_entry(struct zswap_entry *entry,
 	/* try to allocate swap cache page */
 	mpol = get_task_policy(current);
 	page = __read_swap_cache_async(swpentry, GFP_KERNEL, mpol,
-				NO_INTERLEAVE_INDEX, &page_was_allocated);
+				NO_INTERLEAVE_INDEX, &page_was_allocated, true);
 	if (!page) {
 		ret = -ENOMEM;
 		goto fail;
@@ -1147,7 +1303,6 @@ static int zswap_writeback_entry(struct zswap_entry *entry,
 	/* start writeback */
 	__swap_writepage(page, &wbc);
 	put_page(page);
-	zswap_written_back_pages++;
 
 	return ret;
 
@@ -1204,6 +1359,7 @@ bool zswap_store(struct folio *folio)
 	struct scatterlist input, output;
 	struct crypto_acomp_ctx *acomp_ctx;
 	struct obj_cgroup *objcg = NULL;
+	struct mem_cgroup *memcg = NULL;
 	struct zswap_pool *pool;
 	struct zpool *zpool;
 	unsigned int dlen = PAGE_SIZE;
@@ -1235,15 +1391,15 @@ bool zswap_store(struct folio *folio)
 		zswap_invalidate_entry(tree, dupentry);
 	}
 	spin_unlock(&tree->lock);
-
-	/*
-	 * XXX: zswap reclaim does not work with cgroups yet. Without a
-	 * cgroup-aware entry LRU, we will push out entries system-wide based on
-	 * local cgroup limits.
-	 */
 	objcg = get_obj_cgroup_from_folio(folio);
-	if (objcg && !obj_cgroup_may_zswap(objcg))
-		goto reject;
+	if (objcg && !obj_cgroup_may_zswap(objcg)) {
+		memcg = get_mem_cgroup_from_objcg(objcg);
+		if (shrink_memcg(memcg)) {
+			mem_cgroup_put(memcg);
+			goto reject;
+		}
+		mem_cgroup_put(memcg);
+	}
 
 	/* reclaim space if needed */
 	if (zswap_is_full()) {
@@ -1260,7 +1416,7 @@ bool zswap_store(struct folio *folio)
 	}
 
 	/* allocate entry */
-	entry = zswap_entry_cache_alloc(GFP_KERNEL);
+	entry = zswap_entry_cache_alloc(GFP_KERNEL, page_to_nid(page));
 	if (!entry) {
 		zswap_reject_kmemcache_fail++;
 		goto reject;
@@ -1287,6 +1443,15 @@ bool zswap_store(struct folio *folio)
 	if (!entry->pool)
 		goto freepage;
 
+	if (objcg) {
+		memcg = get_mem_cgroup_from_objcg(objcg);
+		if (memcg_list_lru_alloc(memcg, &entry->pool->list_lru, GFP_KERNEL)) {
+			mem_cgroup_put(memcg);
+			goto put_pool;
+		}
+		mem_cgroup_put(memcg);
+	}
+
 	/* compress */
 	acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
 
@@ -1365,9 +1530,8 @@ insert_entry:
 		zswap_invalidate_entry(tree, dupentry);
 	}
 	if (entry->length) {
-		spin_lock(&entry->pool->lru_lock);
-		list_add(&entry->lru, &entry->pool->lru);
-		spin_unlock(&entry->pool->lru_lock);
+		INIT_LIST_HEAD(&entry->lru);
+		zswap_lru_add(&entry->pool->list_lru, entry);
 	}
 	spin_unlock(&tree->lock);
 
@@ -1380,6 +1544,7 @@ insert_entry:
 
 put_dstmem:
 	mutex_unlock(acomp_ctx->mutex);
+put_pool:
 	zswap_pool_put(entry->pool);
 freepage:
 	zswap_entry_cache_free(entry);
@@ -1474,9 +1639,8 @@ freeentry:
 		zswap_invalidate_entry(tree, entry);
 		folio_mark_dirty(folio);
 	} else if (entry->length) {
-		spin_lock(&entry->pool->lru_lock);
-		list_move(&entry->lru, &entry->pool->lru);
-		spin_unlock(&entry->pool->lru_lock);
+		zswap_lru_del(&entry->pool->list_lru, entry);
+		zswap_lru_add(&entry->pool->list_lru, entry);
 	}
 	zswap_entry_put(tree, entry);
 	spin_unlock(&tree->lock);
-- 
cgit v1.2.3


From 7108cc3f765cafd48a6a35f8add140beaecfa75b Mon Sep 17 00:00:00 2001
From: Domenico Cerasuolo <cerasuolodomenico@gmail.com>
Date: Thu, 30 Nov 2023 11:40:21 -0800
Subject: mm: memcg: add per-memcg zswap writeback stat

Since zswap now writes back pages from memcg-specific LRUs, we now need a
new stat to show writebacks count for each memcg.

[nphamcs@gmail.com: rename ZSWP_WB to ZSWPWB]
  Link: https://lkml.kernel.org/r/20231205193307.2432803-1-nphamcs@gmail.com
Link: https://lkml.kernel.org/r/20231130194023.4102148-5-nphamcs@gmail.com
Suggested-by: Nhat Pham <nphamcs@gmail.com>
Signed-off-by: Domenico Cerasuolo <cerasuolodomenico@gmail.com>
Signed-off-by: Nhat Pham <nphamcs@gmail.com>
Tested-by: Bagas Sanjaya <bagasdotme@gmail.com>
Reviewed-by: Yosry Ahmed <yosryahmed@google.com>
Cc: Chris Li <chrisl@kernel.org>
Cc: Dan Streetman <ddstreet@ieee.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Seth Jennings <sjenning@redhat.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Vitaly Wool <vitaly.wool@konsulko.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/vm_event_item.h | 1 +
 mm/memcontrol.c               | 1 +
 mm/vmstat.c                   | 1 +
 mm/zswap.c                    | 4 ++++
 4 files changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index d1b847502f09..747943bc8cc2 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -142,6 +142,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 #ifdef CONFIG_ZSWAP
 		ZSWPIN,
 		ZSWPOUT,
+		ZSWPWB,
 #endif
 #ifdef CONFIG_X86
 		DIRECT_MAP_LEVEL2_SPLIT,
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ce75e504fe8b..69b0ad455242 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -703,6 +703,7 @@ static const unsigned int memcg_vm_event_stat[] = {
 #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
 	ZSWPIN,
 	ZSWPOUT,
+	ZSWPWB,
 #endif
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	THP_FAULT_ALLOC,
diff --git a/mm/vmstat.c b/mm/vmstat.c
index afa5a38fcc9c..cfd8d8256f8e 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1401,6 +1401,7 @@ const char * const vmstat_text[] = {
 #ifdef CONFIG_ZSWAP
 	"zswpin",
 	"zswpout",
+	"zswpwb",
 #endif
 #ifdef CONFIG_X86
 	"direct_map_level2_splits",
diff --git a/mm/zswap.c b/mm/zswap.c
index 213626e0f659..c329fca810c8 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -760,6 +760,10 @@ static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_o
 	}
 	zswap_written_back_pages++;
 
+	if (entry->objcg)
+		count_objcg_event(entry->objcg, ZSWPWB);
+
+	count_vm_event(ZSWPWB);
 	/*
 	 * Writeback started successfully, the page now belongs to the
 	 * swapcache. Drop the entry from zswap - unless invalidate already
-- 
cgit v1.2.3


From b5ba474f3f518701249598b35c581b92a3c95b48 Mon Sep 17 00:00:00 2001
From: Nhat Pham <nphamcs@gmail.com>
Date: Thu, 30 Nov 2023 11:40:23 -0800
Subject: zswap: shrink zswap pool based on memory pressure

Currently, we only shrink the zswap pool when the user-defined limit is
hit.  This means that if we set the limit too high, cold data that are
unlikely to be used again will reside in the pool, wasting precious
memory.  It is hard to predict how much zswap space will be needed ahead
of time, as this depends on the workload (specifically, on factors such as
memory access patterns and compressibility of the memory pages).

This patch implements a memcg- and NUMA-aware shrinker for zswap, that is
initiated when there is memory pressure.  The shrinker does not have any
parameter that must be tuned by the user, and can be opted in or out on a
per-memcg basis.

Furthermore, to make it more robust for many workloads and prevent
overshrinking (i.e evicting warm pages that might be refaulted into
memory), we build in the following heuristics:

* Estimate the number of warm pages residing in zswap, and attempt to
  protect this region of the zswap LRU.
* Scale the number of freeable objects by an estimate of the memory
  saving factor. The better zswap compresses the data, the fewer pages
  we will evict to swap (as we will otherwise incur IO for relatively
  small memory saving).
* During reclaim, if the shrinker encounters a page that is also being
  brought into memory, the shrinker will cautiously terminate its
  shrinking action, as this is a sign that it is touching the warmer
  region of the zswap LRU.

As a proof of concept, we ran the following synthetic benchmark: build the
linux kernel in a memory-limited cgroup, and allocate some cold data in
tmpfs to see if the shrinker could write them out and improved the overall
performance.  Depending on the amount of cold data generated, we observe
from 14% to 35% reduction in kernel CPU time used in the kernel builds.

[nphamcs@gmail.com: check shrinker enablement early, use less costly stat flushing]
  Link: https://lkml.kernel.org/r/20231206194456.3234203-1-nphamcs@gmail.com
Link: https://lkml.kernel.org/r/20231130194023.4102148-7-nphamcs@gmail.com
Signed-off-by: Nhat Pham <nphamcs@gmail.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Tested-by: Bagas Sanjaya <bagasdotme@gmail.com>
Cc: Chris Li <chrisl@kernel.org>
Cc: Dan Streetman <ddstreet@ieee.org>
Cc: Domenico Cerasuolo <cerasuolodomenico@gmail.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Seth Jennings <sjenning@redhat.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Vitaly Wool <vitaly.wool@konsulko.com>
Cc: Yosry Ahmed <yosryahmed@google.com>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 Documentation/admin-guide/mm/zswap.rst |  10 ++
 include/linux/mmzone.h                 |   2 +
 include/linux/zswap.h                  |  25 ++++-
 mm/Kconfig                             |  14 +++
 mm/mmzone.c                            |   1 +
 mm/swap_state.c                        |   2 +
 mm/zswap.c                             | 192 ++++++++++++++++++++++++++++++++-
 7 files changed, 240 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/Documentation/admin-guide/mm/zswap.rst b/Documentation/admin-guide/mm/zswap.rst
index 45b98390e938..62fc244ec702 100644
--- a/Documentation/admin-guide/mm/zswap.rst
+++ b/Documentation/admin-guide/mm/zswap.rst
@@ -153,6 +153,16 @@ attribute, e. g.::
 
 Setting this parameter to 100 will disable the hysteresis.
 
+When there is a sizable amount of cold memory residing in the zswap pool, it
+can be advantageous to proactively write these cold pages to swap and reclaim
+the memory for other use cases. By default, the zswap shrinker is disabled.
+User can enable it as follows:
+
+  echo Y > /sys/module/zswap/parameters/shrinker_enabled
+
+This can be enabled at the boot time if ``CONFIG_ZSWAP_SHRINKER_DEFAULT_ON`` is
+selected.
+
 A debugfs interface is provided for various statistic about pool size, number
 of pages stored, same-value filled pages and various counters for the reasons
 pages are rejected.
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 14faffa4354f..9ef9d010bff0 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -22,6 +22,7 @@
 #include <linux/mm_types.h>
 #include <linux/page-flags.h>
 #include <linux/local_lock.h>
+#include <linux/zswap.h>
 #include <asm/page.h>
 
 /* Free memory management - zoned buddy allocator.  */
@@ -641,6 +642,7 @@ struct lruvec {
 #ifdef CONFIG_MEMCG
 	struct pglist_data *pgdat;
 #endif
+	struct zswap_lruvec_state zswap_lruvec_state;
 };
 
 /* Isolate for asynchronous migration */
diff --git a/include/linux/zswap.h b/include/linux/zswap.h
index e571e393669b..08c240e16a01 100644
--- a/include/linux/zswap.h
+++ b/include/linux/zswap.h
@@ -5,20 +5,40 @@
 #include <linux/types.h>
 #include <linux/mm_types.h>
 
+struct lruvec;
+
 extern u64 zswap_pool_total_size;
 extern atomic_t zswap_stored_pages;
 
 #ifdef CONFIG_ZSWAP
 
+struct zswap_lruvec_state {
+	/*
+	 * Number of pages in zswap that should be protected from the shrinker.
+	 * This number is an estimate of the following counts:
+	 *
+	 * a) Recent page faults.
+	 * b) Recent insertion to the zswap LRU. This includes new zswap stores,
+	 *    as well as recent zswap LRU rotations.
+	 *
+	 * These pages are likely to be warm, and might incur IO if the are written
+	 * to swap.
+	 */
+	atomic_long_t nr_zswap_protected;
+};
+
 bool zswap_store(struct folio *folio);
 bool zswap_load(struct folio *folio);
 void zswap_invalidate(int type, pgoff_t offset);
 void zswap_swapon(int type);
 void zswap_swapoff(int type);
 void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg);
-
+void zswap_lruvec_state_init(struct lruvec *lruvec);
+void zswap_page_swapin(struct page *page);
 #else
 
+struct zswap_lruvec_state {};
+
 static inline bool zswap_store(struct folio *folio)
 {
 	return false;
@@ -33,7 +53,8 @@ static inline void zswap_invalidate(int type, pgoff_t offset) {}
 static inline void zswap_swapon(int type) {}
 static inline void zswap_swapoff(int type) {}
 static inline void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg) {}
-
+static inline void zswap_lruvec_state_init(struct lruvec *lruvec) {}
+static inline void zswap_page_swapin(struct page *page) {}
 #endif
 
 #endif /* _LINUX_ZSWAP_H */
diff --git a/mm/Kconfig b/mm/Kconfig
index 57cd378c73d6..ca87cdb72f11 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -61,6 +61,20 @@ config ZSWAP_EXCLUSIVE_LOADS_DEFAULT_ON
 	  The cost is that if the page was never dirtied and needs to be
 	  swapped out again, it will be re-compressed.
 
+config ZSWAP_SHRINKER_DEFAULT_ON
+	bool "Shrink the zswap pool on memory pressure"
+	depends on ZSWAP
+	default n
+	help
+	  If selected, the zswap shrinker will be enabled, and the pages
+	  stored in the zswap pool will become available for reclaim (i.e
+	  written back to the backing swap device) on memory pressure.
+
+	  This means that zswap writeback could happen even if the pool is
+	  not yet full, or the cgroup zswap limit has not been reached,
+	  reducing the chance that cold pages will reside in the zswap pool
+	  and consume memory indefinitely.
+
 choice
 	prompt "Default compressor"
 	depends on ZSWAP
diff --git a/mm/mmzone.c b/mm/mmzone.c
index b594d3f268fe..c01896eca736 100644
--- a/mm/mmzone.c
+++ b/mm/mmzone.c
@@ -78,6 +78,7 @@ void lruvec_init(struct lruvec *lruvec)
 
 	memset(lruvec, 0, sizeof(struct lruvec));
 	spin_lock_init(&lruvec->lru_lock);
+	zswap_lruvec_state_init(lruvec);
 
 	for_each_lru(lru)
 		INIT_LIST_HEAD(&lruvec->lists[lru]);
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 6c84236382f3..c597cec606e4 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -687,6 +687,7 @@ skip:
 					&page_allocated, false);
 	if (unlikely(page_allocated))
 		swap_readpage(page, false, NULL);
+	zswap_page_swapin(page);
 	return page;
 }
 
@@ -862,6 +863,7 @@ skip:
 					&page_allocated, false);
 	if (unlikely(page_allocated))
 		swap_readpage(page, false, NULL);
+	zswap_page_swapin(page);
 	return page;
 }
 
diff --git a/mm/zswap.c b/mm/zswap.c
index c329fca810c8..015425ed9003 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -148,6 +148,11 @@ module_param_named(exclusive_loads, zswap_exclusive_loads_enabled, bool, 0644);
 /* Number of zpools in zswap_pool (empirically determined for scalability) */
 #define ZSWAP_NR_ZPOOLS 32
 
+/* Enable/disable memory pressure-based shrinker. */
+static bool zswap_shrinker_enabled = IS_ENABLED(
+		CONFIG_ZSWAP_SHRINKER_DEFAULT_ON);
+module_param_named(shrinker_enabled, zswap_shrinker_enabled, bool, 0644);
+
 /*********************************
 * data structures
 **********************************/
@@ -177,6 +182,8 @@ struct zswap_pool {
 	char tfm_name[CRYPTO_MAX_ALG_NAME];
 	struct list_lru list_lru;
 	struct mem_cgroup *next_shrink;
+	struct shrinker *shrinker;
+	atomic_t nr_stored;
 };
 
 /*
@@ -275,17 +282,26 @@ static bool zswap_can_accept(void)
 			DIV_ROUND_UP(zswap_pool_total_size, PAGE_SIZE);
 }
 
+static u64 get_zswap_pool_size(struct zswap_pool *pool)
+{
+	u64 pool_size = 0;
+	int i;
+
+	for (i = 0; i < ZSWAP_NR_ZPOOLS; i++)
+		pool_size += zpool_get_total_size(pool->zpools[i]);
+
+	return pool_size;
+}
+
 static void zswap_update_total_size(void)
 {
 	struct zswap_pool *pool;
 	u64 total = 0;
-	int i;
 
 	rcu_read_lock();
 
 	list_for_each_entry_rcu(pool, &zswap_pools, list)
-		for (i = 0; i < ZSWAP_NR_ZPOOLS; i++)
-			total += zpool_get_total_size(pool->zpools[i]);
+		total += get_zswap_pool_size(pool);
 
 	rcu_read_unlock();
 
@@ -344,13 +360,34 @@ static void zswap_entry_cache_free(struct zswap_entry *entry)
 	kmem_cache_free(zswap_entry_cache, entry);
 }
 
+/*********************************
+* zswap lruvec functions
+**********************************/
+void zswap_lruvec_state_init(struct lruvec *lruvec)
+{
+	atomic_long_set(&lruvec->zswap_lruvec_state.nr_zswap_protected, 0);
+}
+
+void zswap_page_swapin(struct page *page)
+{
+	struct lruvec *lruvec;
+
+	if (page) {
+		lruvec = folio_lruvec(page_folio(page));
+		atomic_long_inc(&lruvec->zswap_lruvec_state.nr_zswap_protected);
+	}
+}
+
 /*********************************
 * lru functions
 **********************************/
 static void zswap_lru_add(struct list_lru *list_lru, struct zswap_entry *entry)
 {
+	atomic_long_t *nr_zswap_protected;
+	unsigned long lru_size, old, new;
 	int nid = entry_to_nid(entry);
 	struct mem_cgroup *memcg;
+	struct lruvec *lruvec;
 
 	/*
 	 * Note that it is safe to use rcu_read_lock() here, even in the face of
@@ -368,6 +405,19 @@ static void zswap_lru_add(struct list_lru *list_lru, struct zswap_entry *entry)
 	memcg = mem_cgroup_from_entry(entry);
 	/* will always succeed */
 	list_lru_add(list_lru, &entry->lru, nid, memcg);
+
+	/* Update the protection area */
+	lru_size = list_lru_count_one(list_lru, nid, memcg);
+	lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(nid));
+	nr_zswap_protected = &lruvec->zswap_lruvec_state.nr_zswap_protected;
+	old = atomic_long_inc_return(nr_zswap_protected);
+	/*
+	 * Decay to avoid overflow and adapt to changing workloads.
+	 * This is based on LRU reclaim cost decaying heuristics.
+	 */
+	do {
+		new = old > lru_size / 4 ? old / 2 : old;
+	} while (!atomic_long_try_cmpxchg(nr_zswap_protected, &old, new));
 	rcu_read_unlock();
 }
 
@@ -389,6 +439,7 @@ static void zswap_lru_putback(struct list_lru *list_lru,
 	int nid = entry_to_nid(entry);
 	spinlock_t *lock = &list_lru->node[nid].lock;
 	struct mem_cgroup *memcg;
+	struct lruvec *lruvec;
 
 	rcu_read_lock();
 	memcg = mem_cgroup_from_entry(entry);
@@ -396,6 +447,10 @@ static void zswap_lru_putback(struct list_lru *list_lru,
 	/* we cannot use list_lru_add here, because it increments node's lru count */
 	list_lru_putback(list_lru, &entry->lru, nid, memcg);
 	spin_unlock(lock);
+
+	lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(entry_to_nid(entry)));
+	/* increment the protection area to account for the LRU rotation. */
+	atomic_long_inc(&lruvec->zswap_lruvec_state.nr_zswap_protected);
 	rcu_read_unlock();
 }
 
@@ -485,6 +540,7 @@ static void zswap_free_entry(struct zswap_entry *entry)
 	else {
 		zswap_lru_del(&entry->pool->list_lru, entry);
 		zpool_free(zswap_find_zpool(entry), entry->handle);
+		atomic_dec(&entry->pool->nr_stored);
 		zswap_pool_put(entry->pool);
 	}
 	zswap_entry_cache_free(entry);
@@ -526,6 +582,109 @@ static struct zswap_entry *zswap_entry_find_get(struct rb_root *root,
 	return entry;
 }
 
+/*********************************
+* shrinker functions
+**********************************/
+static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_one *l,
+				       spinlock_t *lock, void *arg);
+
+static unsigned long zswap_shrinker_scan(struct shrinker *shrinker,
+		struct shrink_control *sc)
+{
+	struct lruvec *lruvec = mem_cgroup_lruvec(sc->memcg, NODE_DATA(sc->nid));
+	unsigned long shrink_ret, nr_protected, lru_size;
+	struct zswap_pool *pool = shrinker->private_data;
+	bool encountered_page_in_swapcache = false;
+
+	if (!zswap_shrinker_enabled) {
+		sc->nr_scanned = 0;
+		return SHRINK_STOP;
+	}
+
+	nr_protected =
+		atomic_long_read(&lruvec->zswap_lruvec_state.nr_zswap_protected);
+	lru_size = list_lru_shrink_count(&pool->list_lru, sc);
+
+	/*
+	 * Abort if we are shrinking into the protected region.
+	 *
+	 * This short-circuiting is necessary because if we have too many multiple
+	 * concurrent reclaimers getting the freeable zswap object counts at the
+	 * same time (before any of them made reasonable progress), the total
+	 * number of reclaimed objects might be more than the number of unprotected
+	 * objects (i.e the reclaimers will reclaim into the protected area of the
+	 * zswap LRU).
+	 */
+	if (nr_protected >= lru_size - sc->nr_to_scan) {
+		sc->nr_scanned = 0;
+		return SHRINK_STOP;
+	}
+
+	shrink_ret = list_lru_shrink_walk(&pool->list_lru, sc, &shrink_memcg_cb,
+		&encountered_page_in_swapcache);
+
+	if (encountered_page_in_swapcache)
+		return SHRINK_STOP;
+
+	return shrink_ret ? shrink_ret : SHRINK_STOP;
+}
+
+static unsigned long zswap_shrinker_count(struct shrinker *shrinker,
+		struct shrink_control *sc)
+{
+	struct zswap_pool *pool = shrinker->private_data;
+	struct mem_cgroup *memcg = sc->memcg;
+	struct lruvec *lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(sc->nid));
+	unsigned long nr_backing, nr_stored, nr_freeable, nr_protected;
+
+	if (!zswap_shrinker_enabled)
+		return 0;
+
+#ifdef CONFIG_MEMCG_KMEM
+	mem_cgroup_flush_stats();
+	nr_backing = memcg_page_state(memcg, MEMCG_ZSWAP_B) >> PAGE_SHIFT;
+	nr_stored = memcg_page_state(memcg, MEMCG_ZSWAPPED);
+#else
+	/* use pool stats instead of memcg stats */
+	nr_backing = get_zswap_pool_size(pool) >> PAGE_SHIFT;
+	nr_stored = atomic_read(&pool->nr_stored);
+#endif
+
+	if (!nr_stored)
+		return 0;
+
+	nr_protected =
+		atomic_long_read(&lruvec->zswap_lruvec_state.nr_zswap_protected);
+	nr_freeable = list_lru_shrink_count(&pool->list_lru, sc);
+	/*
+	 * Subtract the lru size by an estimate of the number of pages
+	 * that should be protected.
+	 */
+	nr_freeable = nr_freeable > nr_protected ? nr_freeable - nr_protected : 0;
+
+	/*
+	 * Scale the number of freeable pages by the memory saving factor.
+	 * This ensures that the better zswap compresses memory, the fewer
+	 * pages we will evict to swap (as it will otherwise incur IO for
+	 * relatively small memory saving).
+	 */
+	return mult_frac(nr_freeable, nr_backing, nr_stored);
+}
+
+static void zswap_alloc_shrinker(struct zswap_pool *pool)
+{
+	pool->shrinker =
+		shrinker_alloc(SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE, "mm-zswap");
+	if (!pool->shrinker)
+		return;
+
+	pool->shrinker->private_data = pool;
+	pool->shrinker->scan_objects = zswap_shrinker_scan;
+	pool->shrinker->count_objects = zswap_shrinker_count;
+	pool->shrinker->batch = 0;
+	pool->shrinker->seeks = DEFAULT_SEEKS;
+}
+
 /*********************************
 * per-cpu code
 **********************************/
@@ -721,6 +880,7 @@ static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_o
 				       spinlock_t *lock, void *arg)
 {
 	struct zswap_entry *entry = container_of(item, struct zswap_entry, lru);
+	bool *encountered_page_in_swapcache = (bool *)arg;
 	struct zswap_tree *tree;
 	pgoff_t swpoffset;
 	enum lru_status ret = LRU_REMOVED_RETRY;
@@ -756,6 +916,17 @@ static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_o
 		zswap_reject_reclaim_fail++;
 		zswap_lru_putback(&entry->pool->list_lru, entry);
 		ret = LRU_RETRY;
+
+		/*
+		 * Encountering a page already in swap cache is a sign that we are shrinking
+		 * into the warmer region. We should terminate shrinking (if we're in the dynamic
+		 * shrinker context).
+		 */
+		if (writeback_result == -EEXIST && encountered_page_in_swapcache) {
+			ret = LRU_SKIP;
+			*encountered_page_in_swapcache = true;
+		}
+
 		goto put_unlock;
 	}
 	zswap_written_back_pages++;
@@ -914,6 +1085,11 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
 				       &pool->node);
 	if (ret)
 		goto error;
+
+	zswap_alloc_shrinker(pool);
+	if (!pool->shrinker)
+		goto error;
+
 	pr_debug("using %s compressor\n", pool->tfm_name);
 
 	/* being the current pool takes 1 ref; this func expects the
@@ -921,13 +1097,19 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
 	 */
 	kref_init(&pool->kref);
 	INIT_LIST_HEAD(&pool->list);
-	list_lru_init_memcg(&pool->list_lru, NULL);
+	if (list_lru_init_memcg(&pool->list_lru, pool->shrinker))
+		goto lru_fail;
+	shrinker_register(pool->shrinker);
 	INIT_WORK(&pool->shrink_work, shrink_worker);
+	atomic_set(&pool->nr_stored, 0);
 
 	zswap_pool_debug("created", pool);
 
 	return pool;
 
+lru_fail:
+	list_lru_destroy(&pool->list_lru);
+	shrinker_free(pool->shrinker);
 error:
 	if (pool->acomp_ctx)
 		free_percpu(pool->acomp_ctx);
@@ -985,6 +1167,7 @@ static void zswap_pool_destroy(struct zswap_pool *pool)
 
 	zswap_pool_debug("destroying", pool);
 
+	shrinker_free(pool->shrinker);
 	cpuhp_state_remove_instance(CPUHP_MM_ZSWP_POOL_PREPARE, &pool->node);
 	free_percpu(pool->acomp_ctx);
 	list_lru_destroy(&pool->list_lru);
@@ -1536,6 +1719,7 @@ insert_entry:
 	if (entry->length) {
 		INIT_LIST_HEAD(&entry->lru);
 		zswap_lru_add(&entry->pool->list_lru, entry);
+		atomic_inc(&entry->pool->nr_stored);
 	}
 	spin_unlock(&tree->lock);
 
-- 
cgit v1.2.3


From 9294a037c01564786abb15436529fae3863268a2 Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Thu, 30 Nov 2023 02:36:44 +0000
Subject: mm/damon/core: implement goal-oriented feedback-driven quota
 auto-tuning

Patch series "mm/damon: let users feed and tame/auto-tune DAMOS".

Introduce Aim-oriented Feedback-driven DAMOS Aggressiveness Auto-tuning.
It makes DAMOS self-tuned with periodic simple user feedback.

Background: DAMOS Control Difficulty
====================================

DAMOS helps users easily implement access pattern aware system operations.
However, controlling DAMOS in the wild is not that easy.

The basic way for DAMOS control is specifying the target access pattern.
In this approach, the user is assumed to well understand the access
pattern and the characteristics of the system and the workloads.  Though
there are useful tools for that, it takes time and effort depending on the
complexity and the dynamicity of the system and the workloads.  After all,
the access pattern consists of three ranges, namely the size, the access
rate, and the age of the regions.  It means users need to tune six
parameters, which is anyway not a simple task.

One of the worst cases would be DAMOS being too aggressive like a
berserker, and therefore consuming too much system resource and making
unwanted radical system operations.  To let users avoid such cases, DAMOS
allows users to set the upper-limit of the schemes' aggressiveness, namely
DAMOS quota.  DAMOS further provides its best-effort under the limit by
prioritizing regions based on the access pattern of the regions.  For
example, users can ask DAMOS to page out up to 100 MiB of memory regions
per second.  Then DAMOS pages out regions that are not accessed for a
longer time (colder) first under the limit.  This allows users to set the
target access pattern a bit naive with wider ranges, and focus on tuning
only one parameter, the quota.  In other words, the number of parameters
to tune can be reduced from six to one.

Still, however, the optimum value for the quota depends on the system and
the workloads' characteristics, so not that simple.  The number of
parameters to tune can also increase again if the user needs to run
multiple schemes.

Aim-oriented Feedback-driven DAMOS Aggressiveness Auto Tuning
=============================================================

Users would use DAMOS since they want to achieve something with it.  They
will likely have measurable metrics representing the achievement and the
target number of the metric like SLO, and continuously measure that
anyway.  While the additional cost of getting the information is nearly
zero, it could be useful for DAMOS to understand how appropriate its
current aggressiveness is set, and adjust it on its own to make the metric
value more close to the target.

Based on this idea, we introduce a new way of tuning DAMOS with nearly
zero additional effort, namely Aim-oriented Feedback-driven DAMOS
Aggressiveness Auto Tuning.  It asks users to provide feedback
representing how well DAMOS is doing relative to the users' aim.  Then
DAMOS adjusts its aggressiveness, specifically the quota that provides
the best effort result under the limit, based on the current level of
the aggressiveness and the users' feedback.

Implementation
==============

The implementation asks users to represent the feedback with score
numbers.  The scores could be anything including user-space specific
metrics including latency and throughput of special user-space workloads,
and system metrics including free memory ratio, memory pressure stall time
(PSI), and active to inactive LRU lists size ratio.  The feedback scores
and the aggressiveness of the given DAMOS scheme are assumed to be
positively proportional, though.  Selecting metrics of the assumption is
the users' responsibility.

The core logic uses the below simple feedback loop algorithm to calculate
the next aggressiveness level of the scheme from the current
aggressiveness level and the current feedback (target_score and
current_score).  It calculates the compensation for next aggressiveness as
a proportion of current aggressiveness and distance to the target score.
As a result, it arrives at the near-goal state in a short time using big
steps when it's far from the goal, but avoids making unnecessarily radical
changes that could turn out to be a bad decision using small steps when
its near to the goal.

    f(n) = max(1, f(n - 1) * ((target_score - current_score) / target_score + 1))

Note that the compensation value becomes negative when it's over
achieving the goal.  That's why the feedback metric and the
aggressiveness of the scheme should be positively proportional.  The
distance-adaptive speed manipulation is simply applied.

Example Use Cases
=================

If users want to reduce the memory footprint of the system as much as
possible as long as the time spent for handling the resulting memory
pressure is within a threshold, they could use DAMOS scheme that reclaims
cold memory regions aiming for a little level of memory pressure stall
time.

If users want the active/inactive LRU lists well balanced to reduce the
performance impact due to possible future memory pressure, they could use
two schemes.  The first one would be set to locate hot pages in the active
LRU list, aiming for a specific active-to-inactive LRU list size ratio,
say, 70%.  The second one would be to locate cold pages in the inactive
LRU list, aiming for a specific inactive-to-active LRU list size ratio,
say, 30%.  Then, DAMOS will balance the two schemes based on the goal and
feedback.

This aim-oriented auto tuning could also be useful for general
balancing-required access aware system operations such as system memory
auto scaling[3] and tiered memory management[4].  These two example usages
are not what current DAMOS implementation is already supporting, but
require additional DAMOS action developments, though.

Evaluation: subtle memory pressure aiming proactive reclamation
===============================================================

To show if the implementation works as expected, we prepare four different
system configurations on AWS i3.metal instances.  The first setup
(original) runs the workload without any DAMOS scheme.  The second setup
(not-tuned) runs the workload with a virtual address space-based proactive
reclamation scheme that pages out memory regions that are not accessed for
five seconds or more.  The third setup (offline-tuned) runs the same
proactive reclamation DAMOS scheme, but after making it tuned for each
workload offline, using our previous user-space driven automatic tuning
approach, namely DAMOOS[1].  The fourth and final setup (AFDAA) runs the
scheme that is the same as that of 'not-tuned' setup, but aims to keep
0.5% of 'some' memory pressure stall time (PSI) for the last 10 seconds
using the aiming-oriented auto tuning.

For each setup, we run realistic workloads from PARSEC3 and SPLASH-2X
benchmark suites.  For each run, we measure RSS and runtime of the
workload, and 'some' memory pressure stall time (PSI) of the system.  We
repeat the runs five times and use averaged measurements.

For simple comparison of the results, we normalize the measurements to
those of 'original'.  In the case of the PSI, though, the measurement for
'original' was zero, so we normalize the value to that of 'not-tuned'
scheme's result.  The normalized results are shown below.

            Not-tuned         Offline-tuned     AFDAA
    RSS     0.622688178226118 0.787950678944904 0.740093483278979
    runtime 1.11767826657912  1.0564674983585   1.0910833880499
    PSI     1                 0.727521443794069 0.308498846350299

The 'not-tuned' scheme achieves about 38.7% memory saving but incur about
11.7% runtime slowdown.  The 'offline-tuned' scheme achieves about 22.2%
memory saving with about 5.5% runtime slowdown.  It also achieves about
28.2% memory pressure stall time saving.  AFDAA achieves about 26% memory
saving with about 9.1% runtime slowdown.  It also achieves about 69.1%
memory pressure stall time saving.  We repeat this test multiple times,
and get consistent results.  AFDAA is now integrated in our daily DAMON
performance test setup.

Apparently the aggressiveness of 'AFDAA' setup is somewhere between those
of 'not-tuned' and 'offline-tuned' setup, since its memory saving and
runtime overhead are between those of the other two setups.  Actually we
set the memory pressure stall time goal aiming for this middle
aggressiveness.  The difference in the two metrics are not significant,
though.  However, it shows significant saving of the memory pressure stall
time, which was the goal of the auto-tuning, over the two variants.
Hence, we conclude the automatic tuning is working as expected.

Please note that the AFDAA setup is only for the evaluation, and
therefore intentionally set a bit aggressive.  It might not be
appropriate for production environments.

The test code is also available[2], so you could reproduce it on your
system and workloads.

Patches Sequence
================

The first four patches implement the core logic and user interfaces for
the auto tuning.  The first patch implements the core logic for the auto
tuning, and the API for DAMOS users in the kernel space.  The second
patch implements basic file operations of DAMON sysfs directories and
files that will be used for setting the goals and providing the
feedback.  The third patch connects the quota goals files inputs to the
DAMOS core logic.  Finally the fourth patch implements a dedicated DAMOS
sysfs command for efficiently committing the quota goals feedback.

Two patches for simple tests of the logic and interfaces follow.  The
fifth patch implements the core logic unit test.  The sixth patch
implements a selftest for the DAMON Sysfs interface for the goals.

Finally, three patches for documentation follows.  The seventh patch
documents the design of the feature.  The eighth patch updates the API
doc for the new sysfs files.  The final eighth patch updates the usage
document for the features.

References
==========

[1] DAOS paper:
    https://www.amazon.science/publications/daos-data-access-aware-operating-system
[2] Evaluation code:
    https://github.com/damonitor/damon-tests/commit/3f884e61193f0166b8724554b6d06b0c449a712d
[3] Memory auto scaling RFC idea:
    https://lore.kernel.org/damon/20231112195114.61474-1-sj@kernel.org/
[4] DAMON-based tiered memory management RFC idea:
    https://lore.kernel.org/damon/20231112195602.61525-1-sj@kernel.org/


This patch (of 9)

Users can effectively control the upper-limit aggressiveness of DAMOS
schemes using the quota feature.  The quota provides best result under the
limit by prioritizing regions based on the access pattern.  That said,
finding the best value, which could depend on dynamic characteristics of
the system and the workloads, is still challenging.

Implement a simple feedback-driven tuning mechanism and use it for
automatic tuning of DAMOS quota.  The implementation allows users to
provide the feedback by setting a feedback score returning callback
function.  Then DAMOS periodically calls the function back and adjusts the
quota based on the return value of the callback and current quota value.

Note that the absolute-value based time/size quotas still work as the
maximum hard limits of the scheme's aggressiveness.  The feedback-driven
auto-tuned quota is applied only if it is not exceeding the manually set
maximum limits.  Same for the scheme-target access pattern and filters
like other features.

[sj@kernel.org: document get_score_arg field of struct damos_quota]
  Link: https://lkml.kernel.org/r/20231204170106.60992-1-sj@kernel.org
Link: https://lkml.kernel.org/r/20231130023652.50284-1-sj@kernel.org
Link: https://lkml.kernel.org/r/20231130023652.50284-2-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: Brendan Higgins <brendanhiggins@google.com>
Cc: David Gow <davidgow@google.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/damon.h | 20 +++++++++++++++
 mm/damon/core.c       | 68 ++++++++++++++++++++++++++++++++++++++++++++-------
 2 files changed, 79 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/damon.h b/include/linux/damon.h
index ab2f17d9926b..aa34ab433bc5 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -136,6 +136,9 @@ enum damos_action {
  * @weight_nr_accesses:	Weight of the region's nr_accesses for prioritization.
  * @weight_age:		Weight of the region's age for prioritization.
  *
+ * @get_score:		Feedback function for self-tuning quota.
+ * @get_score_arg:	Parameter for @get_score
+ *
  * To avoid consuming too much CPU time or IO resources for applying the
  * &struct damos->action to large memory, DAMON allows users to set time and/or
  * size quotas.  The quotas can be set by writing non-zero values to &ms and
@@ -153,6 +156,17 @@ enum damos_action {
  * You could customize the prioritization logic by setting &weight_sz,
  * &weight_nr_accesses, and &weight_age, because monitoring operations are
  * encouraged to respect those.
+ *
+ * If @get_score function pointer is set, DAMON calls it back with
+ * @get_score_arg and get the return value of it for every @reset_interval.
+ * Then, DAMON adjusts the effective quota using the return value as a feedback
+ * score to the current quota, using its internal feedback loop algorithm.
+ *
+ * The feedback loop algorithem assumes the quota input and the feedback score
+ * output are in a positive proportional relationship, and the goal of the
+ * tuning is getting the feedback screo value of 10,000.  If @ms and/or @sz are
+ * set together, those work as a hard limit quota.  If neither @ms nor @sz are
+ * set, the mechanism starts from the quota of one byte.
  */
 struct damos_quota {
 	unsigned long ms;
@@ -163,6 +177,9 @@ struct damos_quota {
 	unsigned int weight_nr_accesses;
 	unsigned int weight_age;
 
+	unsigned long (*get_score)(void *arg);
+	void *get_score_arg;
+
 /* private: */
 	/* For throughput estimation */
 	unsigned long total_charged_sz;
@@ -179,6 +196,9 @@ struct damos_quota {
 	/* For prioritization */
 	unsigned long histogram[DAMOS_MAX_SCORE + 1];
 	unsigned int min_score;
+
+	/* For feedback loop */
+	unsigned long esz_bp;
 };
 
 /**
diff --git a/mm/damon/core.c b/mm/damon/core.c
index ce1562783e7e..f91715a58dc7 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -1038,26 +1038,76 @@ static void damon_do_apply_schemes(struct damon_ctx *c,
 	}
 }
 
-/* Shouldn't be called if quota->ms and quota->sz are zero */
+/*
+ * damon_feed_loop_next_input() - get next input to achieve a target score.
+ * @last_input	The last input.
+ * @score	Current score that made with @last_input.
+ *
+ * Calculate next input to achieve the target score, based on the last input
+ * and current score.  Assuming the input and the score are positively
+ * proportional, calculate how much compensation should be added to or
+ * subtracted from the last input as a proportion of the last input.  Avoid
+ * next input always being zero by setting it non-zero always.  In short form
+ * (assuming support of float and signed calculations), the algorithm is as
+ * below.
+ *
+ * next_input = max(last_input * ((goal - current) / goal + 1), 1)
+ *
+ * For simple implementation, we assume the target score is always 10,000.  The
+ * caller should adjust @score for this.
+ *
+ * Returns next input that assumed to achieve the target score.
+ */
+static unsigned long damon_feed_loop_next_input(unsigned long last_input,
+		unsigned long score)
+{
+	const unsigned long goal = 10000;
+	unsigned long score_goal_diff = max(goal, score) - min(goal, score);
+	unsigned long score_goal_diff_bp = score_goal_diff * 10000 / goal;
+	unsigned long compensation = last_input * score_goal_diff_bp / 10000;
+	/* Set minimum input as 10000 to avoid compensation be zero */
+	const unsigned long min_input = 10000;
+
+	if (goal > score)
+		return last_input + compensation;
+	if (last_input > compensation + min_input)
+		return last_input - compensation;
+	return min_input;
+}
+
+/* Shouldn't be called if quota->ms, quota->sz, and quota->get_score unset */
 static void damos_set_effective_quota(struct damos_quota *quota)
 {
 	unsigned long throughput;
 	unsigned long esz;
 
-	if (!quota->ms) {
+	if (!quota->ms && !quota->get_score) {
 		quota->esz = quota->sz;
 		return;
 	}
 
-	if (quota->total_charged_ns)
-		throughput = quota->total_charged_sz * 1000000 /
-			quota->total_charged_ns;
-	else
-		throughput = PAGE_SIZE * 1024;
-	esz = throughput * quota->ms;
+	if (quota->get_score) {
+		quota->esz_bp = damon_feed_loop_next_input(
+				max(quota->esz_bp, 10000UL),
+				quota->get_score(quota->get_score_arg));
+		esz = quota->esz_bp / 10000;
+	}
+
+	if (quota->ms) {
+		if (quota->total_charged_ns)
+			throughput = quota->total_charged_sz * 1000000 /
+				quota->total_charged_ns;
+		else
+			throughput = PAGE_SIZE * 1024;
+		if (quota->get_score)
+			esz = min(throughput * quota->ms, esz);
+		else
+			esz = throughput * quota->ms;
+	}
 
 	if (quota->sz && quota->sz < esz)
 		esz = quota->sz;
+
 	quota->esz = esz;
 }
 
@@ -1069,7 +1119,7 @@ static void damos_adjust_quota(struct damon_ctx *c, struct damos *s)
 	unsigned long cumulated_sz;
 	unsigned int score, max_score = 0;
 
-	if (!quota->ms && !quota->sz)
+	if (!quota->ms && !quota->sz && !quota->get_score)
 		return;
 
 	/* New charge window starts */
-- 
cgit v1.2.3


From 1486fb50136f4799946f5ecfe050094574647153 Mon Sep 17 00:00:00 2001
From: Kefeng Wang <wangkefeng.wang@huawei.com>
Date: Sat, 18 Nov 2023 10:32:28 +0800
Subject: mm: ksm: use more folio api in ksm_might_need_to_copy()

Patch series "mm: cleanup and use more folio in page fault", v3.

Rename page_copy_prealloc() to folio_prealloc(), which is used by more
functions, also do more folio conversion in page fault.


This patch (of 5):

Since ksm only support normal page, no swapout/in for ksm large folio too,
add large folio check in ksm_might_need_to_copy(), also convert
page->index to folio->index as page->index is going away.

Then convert ksm_might_need_to_copy() to use more folio api to save nine
compound_head() calls, short 'address' to reduce max-line-length.

Link: https://lkml.kernel.org/r/20231118023232.1409103-1-wangkefeng.wang@huawei.com
Link: https://lkml.kernel.org/r/20231118023232.1409103-2-wangkefeng.wang@huawei.com
Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Sidhartha Kumar <sidhartha.kumar@oracle.com>
Cc: Vishal Moola (Oracle) <vishal.moola@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/ksm.h |  4 ++--
 mm/ksm.c            | 39 +++++++++++++++++++++------------------
 2 files changed, 23 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/linux/ksm.h b/include/linux/ksm.h
index c2dd786a30e1..4643d5244e77 100644
--- a/include/linux/ksm.h
+++ b/include/linux/ksm.h
@@ -77,7 +77,7 @@ static inline void ksm_exit(struct mm_struct *mm)
  * but what if the vma was unmerged while the page was swapped out?
  */
 struct page *ksm_might_need_to_copy(struct page *page,
-			struct vm_area_struct *vma, unsigned long address);
+			struct vm_area_struct *vma, unsigned long addr);
 
 void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc);
 void folio_migrate_ksm(struct folio *newfolio, struct folio *folio);
@@ -130,7 +130,7 @@ static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
 }
 
 static inline struct page *ksm_might_need_to_copy(struct page *page,
-			struct vm_area_struct *vma, unsigned long address)
+			struct vm_area_struct *vma, unsigned long addr)
 {
 	return page;
 }
diff --git a/mm/ksm.c b/mm/ksm.c
index 5d60d5385de6..b93389a3780e 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -2876,48 +2876,51 @@ void __ksm_exit(struct mm_struct *mm)
 }
 
 struct page *ksm_might_need_to_copy(struct page *page,
-			struct vm_area_struct *vma, unsigned long address)
+			struct vm_area_struct *vma, unsigned long addr)
 {
 	struct folio *folio = page_folio(page);
 	struct anon_vma *anon_vma = folio_anon_vma(folio);
-	struct page *new_page;
+	struct folio *new_folio;
 
-	if (PageKsm(page)) {
-		if (page_stable_node(page) &&
+	if (folio_test_large(folio))
+		return page;
+
+	if (folio_test_ksm(folio)) {
+		if (folio_stable_node(folio) &&
 		    !(ksm_run & KSM_RUN_UNMERGE))
 			return page;	/* no need to copy it */
 	} else if (!anon_vma) {
 		return page;		/* no need to copy it */
-	} else if (page->index == linear_page_index(vma, address) &&
+	} else if (folio->index == linear_page_index(vma, addr) &&
 			anon_vma->root == vma->anon_vma->root) {
 		return page;		/* still no need to copy it */
 	}
 	if (PageHWPoison(page))
 		return ERR_PTR(-EHWPOISON);
-	if (!PageUptodate(page))
+	if (!folio_test_uptodate(folio))
 		return page;		/* let do_swap_page report the error */
 
-	new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
-	if (new_page &&
-	    mem_cgroup_charge(page_folio(new_page), vma->vm_mm, GFP_KERNEL)) {
-		put_page(new_page);
-		new_page = NULL;
+	new_folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, addr, false);
+	if (new_folio &&
+	    mem_cgroup_charge(new_folio, vma->vm_mm, GFP_KERNEL)) {
+		folio_put(new_folio);
+		new_folio = NULL;
 	}
-	if (new_page) {
-		if (copy_mc_user_highpage(new_page, page, address, vma)) {
-			put_page(new_page);
+	if (new_folio) {
+		if (copy_mc_user_highpage(&new_folio->page, page, addr, vma)) {
+			folio_put(new_folio);
 			memory_failure_queue(page_to_pfn(page), 0);
 			return ERR_PTR(-EHWPOISON);
 		}
-		SetPageDirty(new_page);
-		__SetPageUptodate(new_page);
-		__SetPageLocked(new_page);
+		folio_set_dirty(new_folio);
+		__folio_mark_uptodate(new_folio);
+		__folio_set_locked(new_folio);
 #ifdef CONFIG_SWAP
 		count_vm_event(KSM_SWPIN_COPY);
 #endif
 	}
 
-	return new_page;
+	return new_folio ? &new_folio->page : NULL;
 }
 
 void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc)
-- 
cgit v1.2.3


From f67f8d4a8c1e1ebc85a6cbdb9a7266f14863461c Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Fri, 1 Dec 2023 14:59:36 -0500
Subject: mm/rmap: fix misplaced parenthesis of a likely()

Running my yearly branch profiler to see where likely/unlikely annotation
may be added or removed, I discovered this:

correct incorrect  %        Function                  File              Line
 ------- ---------  -        --------                  ----              ----
       0   457918 100 page_try_dup_anon_rmap         rmap.h               264
[..]
  458021        0   0 page_try_dup_anon_rmap         rmap.h               265

I thought it was interesting that line 264 of rmap.h had a 100% incorrect
annotation, but the line directly below it was 100% correct. Looking at the
code:

	if (likely(!is_device_private_page(page) &&
	    unlikely(page_needs_cow_for_dma(vma, page))))

It didn't make sense. The "likely()" was around the entire if statement
(not just the "!is_device_private_page(page)"), which also included the
"unlikely()" portion of that if condition.

If the unlikely portion is unlikely to be true, that would make the entire
if condition unlikely to be true, so it made no sense at all to say the
entire if condition is true.

What is more likely to be likely is just the first part of the if statement
before the && operation. It's likely to be a misplaced parenthesis. And
after making the if condition broken into a likely() && unlikely(), both
now appear to be correct!

Link: https://lkml.kernel.org/r/20231201145936.5ddfdb50@gandalf.local.home
Fixes:fb3d824d1a46c ("mm/rmap: split page_dup_rmap() into page_dup_file_rmap() and page_try_dup_anon_rmap()")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: David Hildenbrand <david@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/rmap.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index b26fe858fd44..3c2fc291b071 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -261,8 +261,8 @@ static inline int page_try_dup_anon_rmap(struct page *page, bool compound,
 	 * guarantee the pinned page won't be randomly replaced in the
 	 * future on write faults.
 	 */
-	if (likely(!is_device_private_page(page) &&
-	    unlikely(page_needs_cow_for_dma(vma, page))))
+	if (likely(!is_device_private_page(page)) &&
+	    unlikely(page_needs_cow_for_dma(vma, page)))
 		return -EBUSY;
 
 	ClearPageAnonExclusive(page);
-- 
cgit v1.2.3


From 5b02a863ba502482f25ae3a1bfa259838793785b Mon Sep 17 00:00:00 2001
From: Peter Griffin <peter.griffin@linaro.org>
Date: Mon, 11 Dec 2023 16:23:21 +0000
Subject: dt-bindings: clock: google,gs101: fix incorrect numbering and DGB
 suffix
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

166 was skipped by mistake and two clocks:
* CLK_MOUT_CMU_HSI0_USBDPDGB
* CLK_GOUT_HSI0_USBDPDGB

Have an incorrect DGB ending instead of DBG.

This is an ABI break, but as the patch was only applied yesterday this
header has never been in an actual release so it seems better to fix
this early than ignore it.

Fixes: 0a910f160638 ("dt-bindings: clock: Add Google gs101 clock management unit bindings")
Signed-off-by: Peter Griffin <peter.griffin@linaro.org>
Reviewed-by: Chanwoo Choi <cw00.choi@samsung.com>
Reviewed-by: Sam Protsenko <semen.protsenko@linaro.org>
Reviewed-by: André Draszik <andre.draszik@linaro.org>
Link: https://lore.kernel.org/r/20231211162331.435900-7-peter.griffin@linaro.org
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 include/dt-bindings/clock/google,gs101.h | 118 +++++++++++++++----------------
 1 file changed, 59 insertions(+), 59 deletions(-)

(limited to 'include')

diff --git a/include/dt-bindings/clock/google,gs101.h b/include/dt-bindings/clock/google,gs101.h
index 5d2c2d907a7b..9761c0b24e66 100644
--- a/include/dt-bindings/clock/google,gs101.h
+++ b/include/dt-bindings/clock/google,gs101.h
@@ -59,7 +59,7 @@
 #define CLK_MOUT_CMU_HSI0_BUS		45
 #define CLK_MOUT_CMU_HSI0_DPGTC		46
 #define CLK_MOUT_CMU_HSI0_USB31DRD	47
-#define CLK_MOUT_CMU_HSI0_USBDPDGB	48
+#define CLK_MOUT_CMU_HSI0_USBDPDBG	48
 #define CLK_MOUT_CMU_HSI1_BUS		49
 #define CLK_MOUT_CMU_HSI1_PCIE		50
 #define CLK_MOUT_CMU_HSI2_BUS		51
@@ -181,64 +181,64 @@
 #define CLK_GOUT_BUS2_BUS		163
 #define CLK_GOUT_CIS_CLK0		164
 #define CLK_GOUT_CIS_CLK1		165
-#define CLK_GOUT_CIS_CLK2		167
-#define CLK_GOUT_CIS_CLK3		168
-#define CLK_GOUT_CIS_CLK4		169
-#define CLK_GOUT_CIS_CLK5		170
-#define CLK_GOUT_CIS_CLK6		171
-#define CLK_GOUT_CIS_CLK7		172
-#define CLK_GOUT_CMU_BOOST		173
-#define CLK_GOUT_CORE_BUS		174
-#define CLK_GOUT_CPUCL0_DBG		175
-#define CLK_GOUT_CPUCL0_SWITCH		176
-#define CLK_GOUT_CPUCL1_SWITCH		177
-#define CLK_GOUT_CPUCL2_SWITCH		178
-#define CLK_GOUT_CSIS_BUS		179
-#define CLK_GOUT_DISP_BUS		180
-#define CLK_GOUT_DNS_BUS		181
-#define CLK_GOUT_DPU_BUS		182
-#define CLK_GOUT_EH_BUS			183
-#define CLK_GOUT_G2D_G2D		184
-#define CLK_GOUT_G2D_MSCL		185
-#define CLK_GOUT_G3AA_G3AA		186
-#define CLK_GOUT_G3D_BUSD		187
-#define CLK_GOUT_G3D_GLB		188
-#define CLK_GOUT_G3D_SWITCH		189
-#define CLK_GOUT_GDC_GDC0		190
-#define CLK_GOUT_GDC_GDC1		191
-#define CLK_GOUT_GDC_SCSC		192
-#define CLK_GOUT_CMU_HPM		193
-#define CLK_GOUT_HSI0_BUS		194
-#define CLK_GOUT_HSI0_DPGTC		195
-#define CLK_GOUT_HSI0_USB31DRD		196
-#define CLK_GOUT_HSI0_USBDPDGB		197
-#define CLK_GOUT_HSI1_BUS		198
-#define CLK_GOUT_HSI1_PCIE		199
-#define CLK_GOUT_HSI2_BUS		200
-#define CLK_GOUT_HSI2_MMC_CARD		201
-#define CLK_GOUT_HSI2_PCIE		202
-#define CLK_GOUT_HSI2_UFS_EMBD		203
-#define CLK_GOUT_IPP_BUS		204
-#define CLK_GOUT_ITP_BUS		205
-#define CLK_GOUT_MCSC_ITSC		206
-#define CLK_GOUT_MCSC_MCSC		207
-#define CLK_GOUT_MFC_MFC		208
-#define CLK_GOUT_MIF_BUSP		209
-#define CLK_GOUT_MISC_BUS		210
-#define CLK_GOUT_MISC_SSS		211
-#define CLK_GOUT_PDP_BUS		212
-#define CLK_GOUT_PDP_VRA		213
-#define CLK_GOUT_G3AA			214
-#define CLK_GOUT_PERIC0_BUS		215
-#define CLK_GOUT_PERIC0_IP		216
-#define CLK_GOUT_PERIC1_BUS		217
-#define CLK_GOUT_PERIC1_IP		218
-#define CLK_GOUT_TNR_BUS		219
-#define CLK_GOUT_TOP_CMUREF		220
-#define CLK_GOUT_TPU_BUS		221
-#define CLK_GOUT_TPU_TPU		222
-#define CLK_GOUT_TPU_TPUCTL		223
-#define CLK_GOUT_TPU_UART		224
+#define CLK_GOUT_CIS_CLK2		166
+#define CLK_GOUT_CIS_CLK3		167
+#define CLK_GOUT_CIS_CLK4		168
+#define CLK_GOUT_CIS_CLK5		169
+#define CLK_GOUT_CIS_CLK6		170
+#define CLK_GOUT_CIS_CLK7		171
+#define CLK_GOUT_CMU_BOOST		172
+#define CLK_GOUT_CORE_BUS		173
+#define CLK_GOUT_CPUCL0_DBG		174
+#define CLK_GOUT_CPUCL0_SWITCH		175
+#define CLK_GOUT_CPUCL1_SWITCH		176
+#define CLK_GOUT_CPUCL2_SWITCH		177
+#define CLK_GOUT_CSIS_BUS		178
+#define CLK_GOUT_DISP_BUS		179
+#define CLK_GOUT_DNS_BUS		180
+#define CLK_GOUT_DPU_BUS		181
+#define CLK_GOUT_EH_BUS			182
+#define CLK_GOUT_G2D_G2D		183
+#define CLK_GOUT_G2D_MSCL		184
+#define CLK_GOUT_G3AA_G3AA		185
+#define CLK_GOUT_G3D_BUSD		186
+#define CLK_GOUT_G3D_GLB		187
+#define CLK_GOUT_G3D_SWITCH		188
+#define CLK_GOUT_GDC_GDC0		189
+#define CLK_GOUT_GDC_GDC1		190
+#define CLK_GOUT_GDC_SCSC		191
+#define CLK_GOUT_CMU_HPM		192
+#define CLK_GOUT_HSI0_BUS		193
+#define CLK_GOUT_HSI0_DPGTC		194
+#define CLK_GOUT_HSI0_USB31DRD		195
+#define CLK_GOUT_HSI0_USBDPDBG		196
+#define CLK_GOUT_HSI1_BUS		197
+#define CLK_GOUT_HSI1_PCIE		198
+#define CLK_GOUT_HSI2_BUS		199
+#define CLK_GOUT_HSI2_MMC_CARD		200
+#define CLK_GOUT_HSI2_PCIE		201
+#define CLK_GOUT_HSI2_UFS_EMBD		202
+#define CLK_GOUT_IPP_BUS		203
+#define CLK_GOUT_ITP_BUS		204
+#define CLK_GOUT_MCSC_ITSC		205
+#define CLK_GOUT_MCSC_MCSC		206
+#define CLK_GOUT_MFC_MFC		207
+#define CLK_GOUT_MIF_BUSP		208
+#define CLK_GOUT_MISC_BUS		209
+#define CLK_GOUT_MISC_SSS		210
+#define CLK_GOUT_PDP_BUS		211
+#define CLK_GOUT_PDP_VRA		212
+#define CLK_GOUT_G3AA			213
+#define CLK_GOUT_PERIC0_BUS		214
+#define CLK_GOUT_PERIC0_IP		215
+#define CLK_GOUT_PERIC1_BUS		216
+#define CLK_GOUT_PERIC1_IP		217
+#define CLK_GOUT_TNR_BUS		218
+#define CLK_GOUT_TOP_CMUREF		219
+#define CLK_GOUT_TPU_BUS		220
+#define CLK_GOUT_TPU_TPU		221
+#define CLK_GOUT_TPU_TPUCTL		222
+#define CLK_GOUT_TPU_UART		223
 
 /* CMU_APM */
 #define CLK_MOUT_APM_FUNC				1
-- 
cgit v1.2.3


From 82c944d05b1a24c76948ee9d6bb1d7de1ebb8b3a Mon Sep 17 00:00:00 2001
From: Herve Codina <herve.codina@bootlin.com>
Date: Tue, 28 Nov 2023 14:25:30 +0100
Subject: net: wan: Add framer framework support

A framer is a component in charge of an E1/T1 line interface.
Connected usually to a TDM bus, it converts TDM frames to/from E1/T1
frames. It also provides information related to the E1/T1 line.

The framer framework provides a set of APIs for the framer drivers
(framer provider) to create/destroy a framer and APIs for the framer
users (framer consumer) to obtain a reference to the framer, and
use the framer.

This basic implementation provides a framer abstraction for:
 - power on/off the framer
 - get the framer status (line state)
 - be notified on framer status changes
 - get/set the framer configuration

Signed-off-by: Herve Codina <herve.codina@bootlin.com>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20231128132534.258459-2-herve.codina@bootlin.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/net/wan/Kconfig                |   2 +
 drivers/net/wan/Makefile               |   2 +
 drivers/net/wan/framer/Kconfig         |  25 +
 drivers/net/wan/framer/Makefile        |   6 +
 drivers/net/wan/framer/framer-core.c   | 882 +++++++++++++++++++++++++++++++++
 include/linux/framer/framer-provider.h | 194 ++++++++
 include/linux/framer/framer.h          | 205 ++++++++
 7 files changed, 1316 insertions(+)
 create mode 100644 drivers/net/wan/framer/Kconfig
 create mode 100644 drivers/net/wan/framer/Makefile
 create mode 100644 drivers/net/wan/framer/framer-core.c
 create mode 100644 include/linux/framer/framer-provider.h
 create mode 100644 include/linux/framer/framer.h

(limited to 'include')

diff --git a/drivers/net/wan/Kconfig b/drivers/net/wan/Kconfig
index dcb069dde66b..7dda87756d3f 100644
--- a/drivers/net/wan/Kconfig
+++ b/drivers/net/wan/Kconfig
@@ -95,6 +95,8 @@ config HDLC_X25
 comment "X.25/LAPB support is disabled"
 	depends on HDLC && (LAPB!=m || HDLC!=m) && LAPB!=y
 
+source "drivers/net/wan/framer/Kconfig"
+
 config PCI200SYN
 	tristate "Goramo PCI200SYN support"
 	depends on HDLC && PCI
diff --git a/drivers/net/wan/Makefile b/drivers/net/wan/Makefile
index 5bec8fae47f8..8119b49d1da9 100644
--- a/drivers/net/wan/Makefile
+++ b/drivers/net/wan/Makefile
@@ -14,6 +14,8 @@ obj-$(CONFIG_HDLC_FR)		+= hdlc_fr.o
 obj-$(CONFIG_HDLC_PPP)		+= hdlc_ppp.o
 obj-$(CONFIG_HDLC_X25)		+= hdlc_x25.o
 
+obj-y				+= framer/
+
 obj-$(CONFIG_FARSYNC)		+= farsync.o
 
 obj-$(CONFIG_LAPBETHER)		+= lapbether.o
diff --git a/drivers/net/wan/framer/Kconfig b/drivers/net/wan/framer/Kconfig
new file mode 100644
index 000000000000..57fe7ba6aa37
--- /dev/null
+++ b/drivers/net/wan/framer/Kconfig
@@ -0,0 +1,25 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# FRAMER
+#
+
+menuconfig FRAMER
+	tristate "Framer Subsystem"
+	help
+	  A framer is a component in charge of an E1/T1 line interface.
+	  Connected usually to a TDM bus, it converts TDM frames to/from E1/T1
+	  frames. It also provides information related to the E1/T1 line.
+	  Used with HDLC, the network can be reached through the E1/T1 line.
+
+	  This framework is designed to provide a generic interface for framer
+	  devices present in the kernel. This layer will have the generic
+	  API by which framer drivers can create framer using the framer
+	  framework and framer users can obtain reference to the framer.
+	  All the users of this framework should select this config.
+
+if FRAMER
+
+config GENERIC_FRAMER
+	bool
+
+endif # FRAMER
diff --git a/drivers/net/wan/framer/Makefile b/drivers/net/wan/framer/Makefile
new file mode 100644
index 000000000000..78dbd8e563d0
--- /dev/null
+++ b/drivers/net/wan/framer/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for the framer drivers.
+#
+
+obj-$(CONFIG_GENERIC_FRAMER)			+= framer-core.o
diff --git a/drivers/net/wan/framer/framer-core.c b/drivers/net/wan/framer/framer-core.c
new file mode 100644
index 000000000000..c04dc88bda6c
--- /dev/null
+++ b/drivers/net/wan/framer/framer-core.c
@@ -0,0 +1,882 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Generic Framer framework.
+ *
+ * Copyright 2023 CS GROUP France
+ *
+ * Author: Herve Codina <herve.codina@bootlin.com>
+ */
+
+#include <linux/device.h>
+#include <linux/framer/framer.h>
+#include <linux/framer/framer-provider.h>
+#include <linux/idr.h>
+#include <linux/module.h>
+#include <linux/notifier.h>
+#include <linux/of.h>
+#include <linux/pm_runtime.h>
+#include <linux/regulator/consumer.h>
+#include <linux/slab.h>
+
+static struct class *framer_class;
+static DEFINE_MUTEX(framer_provider_mutex);
+static LIST_HEAD(framer_provider_list);
+static DEFINE_IDA(framer_ida);
+
+#define dev_to_framer(a)	(container_of((a), struct framer, dev))
+
+int framer_pm_runtime_get(struct framer *framer)
+{
+	int ret;
+
+	if (!pm_runtime_enabled(&framer->dev))
+		return -EOPNOTSUPP;
+
+	ret = pm_runtime_get(&framer->dev);
+	if (ret < 0 && ret != -EINPROGRESS)
+		pm_runtime_put_noidle(&framer->dev);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(framer_pm_runtime_get);
+
+int framer_pm_runtime_get_sync(struct framer *framer)
+{
+	int ret;
+
+	if (!pm_runtime_enabled(&framer->dev))
+		return -EOPNOTSUPP;
+
+	ret = pm_runtime_get_sync(&framer->dev);
+	if (ret < 0)
+		pm_runtime_put_sync(&framer->dev);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(framer_pm_runtime_get_sync);
+
+int framer_pm_runtime_put(struct framer *framer)
+{
+	if (!pm_runtime_enabled(&framer->dev))
+		return -EOPNOTSUPP;
+
+	return pm_runtime_put(&framer->dev);
+}
+EXPORT_SYMBOL_GPL(framer_pm_runtime_put);
+
+int framer_pm_runtime_put_sync(struct framer *framer)
+{
+	if (!pm_runtime_enabled(&framer->dev))
+		return -EOPNOTSUPP;
+
+	return pm_runtime_put_sync(&framer->dev);
+}
+EXPORT_SYMBOL_GPL(framer_pm_runtime_put_sync);
+
+/**
+ * framer_init - framer internal initialization before framer operation
+ * @framer: the framer returned by framer_get()
+ *
+ * Used to allow framer's driver to perform framer internal initialization,
+ * such as PLL block powering, clock initialization or anything that's
+ * is required by the framer to perform the start of operation.
+ * Must be called before framer_power_on().
+ *
+ * Return: %0 if successful, a negative error code otherwise
+ */
+int framer_init(struct framer *framer)
+{
+	bool start_polling = false;
+	int ret;
+
+	ret = framer_pm_runtime_get_sync(framer);
+	if (ret < 0 && ret != -EOPNOTSUPP)
+		return ret;
+	ret = 0; /* Override possible ret == -EOPNOTSUPP */
+
+	mutex_lock(&framer->mutex);
+	if (framer->power_count > framer->init_count)
+		dev_warn(&framer->dev, "framer_power_on was called before framer init\n");
+
+	if (framer->init_count == 0) {
+		if (framer->ops->init) {
+			ret = framer->ops->init(framer);
+			if (ret < 0) {
+				dev_err(&framer->dev, "framer init failed --> %d\n", ret);
+				goto out;
+			}
+		}
+		if (framer->ops->flags & FRAMER_FLAG_POLL_STATUS)
+			start_polling = true;
+	}
+	++framer->init_count;
+
+out:
+	mutex_unlock(&framer->mutex);
+
+	if (!ret && start_polling) {
+		ret = framer_get_status(framer, &framer->prev_status);
+		if (ret < 0) {
+			dev_warn(&framer->dev, "framer get status failed --> %d\n", ret);
+			/* Will be retried on polling_work */
+			ret = 0;
+		}
+		queue_delayed_work(system_power_efficient_wq, &framer->polling_work, 1 * HZ);
+	}
+
+	framer_pm_runtime_put(framer);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(framer_init);
+
+/**
+ * framer_exit - Framer internal un-initialization
+ * @framer: the framer returned by framer_get()
+ *
+ * Must be called after framer_power_off().
+ */
+int framer_exit(struct framer *framer)
+{
+	int ret;
+
+	ret = framer_pm_runtime_get_sync(framer);
+	if (ret < 0 && ret != -EOPNOTSUPP)
+		return ret;
+	ret = 0; /* Override possible ret == -EOPNOTSUPP */
+
+	mutex_lock(&framer->mutex);
+	--framer->init_count;
+	if (framer->init_count == 0) {
+		if (framer->ops->flags & FRAMER_FLAG_POLL_STATUS) {
+			mutex_unlock(&framer->mutex);
+			cancel_delayed_work_sync(&framer->polling_work);
+			mutex_lock(&framer->mutex);
+		}
+
+		if (framer->ops->exit)
+			framer->ops->exit(framer);
+	}
+
+	mutex_unlock(&framer->mutex);
+	framer_pm_runtime_put(framer);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(framer_exit);
+
+/**
+ * framer_power_on - Enable the framer and enter proper operation
+ * @framer: the framer returned by framer_get()
+ *
+ * Must be called after framer_init().
+ *
+ * Return: %0 if successful, a negative error code otherwise
+ */
+int framer_power_on(struct framer *framer)
+{
+	int ret;
+
+	if (framer->pwr) {
+		ret = regulator_enable(framer->pwr);
+		if (ret)
+			return ret;
+	}
+
+	ret = framer_pm_runtime_get_sync(framer);
+	if (ret < 0 && ret != -EOPNOTSUPP)
+		goto err_pm_sync;
+
+	mutex_lock(&framer->mutex);
+	if (framer->power_count == 0 && framer->ops->power_on) {
+		ret = framer->ops->power_on(framer);
+		if (ret < 0) {
+			dev_err(&framer->dev, "framer poweron failed --> %d\n", ret);
+			goto err_pwr_on;
+		}
+	}
+	++framer->power_count;
+	mutex_unlock(&framer->mutex);
+	return 0;
+
+err_pwr_on:
+	mutex_unlock(&framer->mutex);
+	framer_pm_runtime_put_sync(framer);
+err_pm_sync:
+	if (framer->pwr)
+		regulator_disable(framer->pwr);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(framer_power_on);
+
+/**
+ * framer_power_off - Disable the framer.
+ * @framer: the framer returned by framer_get()
+ *
+ * Must be called before framer_exit().
+ *
+ * Return: %0 if successful, a negative error code otherwise
+ */
+int framer_power_off(struct framer *framer)
+{
+	int ret;
+
+	mutex_lock(&framer->mutex);
+	if (framer->power_count == 1 && framer->ops->power_off) {
+		ret = framer->ops->power_off(framer);
+		if (ret < 0) {
+			dev_err(&framer->dev, "framer poweroff failed --> %d\n", ret);
+			mutex_unlock(&framer->mutex);
+			return ret;
+		}
+	}
+	--framer->power_count;
+	mutex_unlock(&framer->mutex);
+	framer_pm_runtime_put(framer);
+
+	if (framer->pwr)
+		regulator_disable(framer->pwr);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(framer_power_off);
+
+/**
+ * framer_get_status() - Gets the framer status
+ * @framer: the framer returned by framer_get()
+ * @status: the status to retrieve
+ *
+ * Used to get the framer status. framer_init() must have been called
+ * on the framer.
+ *
+ * Return: %0 if successful, a negative error code otherwise
+ */
+int framer_get_status(struct framer *framer, struct framer_status *status)
+{
+	int ret;
+
+	if (!framer->ops->get_status)
+		return -EOPNOTSUPP;
+
+	/* Be sure to have known values (struct padding and future extensions) */
+	memset(status, 0, sizeof(*status));
+
+	mutex_lock(&framer->mutex);
+	ret = framer->ops->get_status(framer, status);
+	mutex_unlock(&framer->mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(framer_get_status);
+
+/**
+ * framer_set_config() - Sets the framer configuration
+ * @framer: the framer returned by framer_get()
+ * @config: the configuration to set
+ *
+ * Used to set the framer configuration. framer_init() must have been called
+ * on the framer.
+ *
+ * Return: %0 if successful, a negative error code otherwise
+ */
+int framer_set_config(struct framer *framer, const struct framer_config *config)
+{
+	int ret;
+
+	if (!framer->ops->set_config)
+		return -EOPNOTSUPP;
+
+	mutex_lock(&framer->mutex);
+	ret = framer->ops->set_config(framer, config);
+	mutex_unlock(&framer->mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(framer_set_config);
+
+/**
+ * framer_get_config() - Gets the framer configuration
+ * @framer: the framer returned by framer_get()
+ * @config: the configuration to retrieve
+ *
+ * Used to get the framer configuration. framer_init() must have been called
+ * on the framer.
+ *
+ * Return: %0 if successful, a negative error code otherwise
+ */
+int framer_get_config(struct framer *framer, struct framer_config *config)
+{
+	int ret;
+
+	if (!framer->ops->get_config)
+		return -EOPNOTSUPP;
+
+	mutex_lock(&framer->mutex);
+	ret = framer->ops->get_config(framer, config);
+	mutex_unlock(&framer->mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(framer_get_config);
+
+static void framer_polling_work(struct work_struct *work)
+{
+	struct framer *framer = container_of(work, struct framer, polling_work.work);
+	struct framer_status status;
+	int ret;
+
+	ret = framer_get_status(framer, &status);
+	if (ret) {
+		dev_err(&framer->dev, "polling, get status failed (%d)\n", ret);
+		goto end;
+	}
+	if (memcmp(&framer->prev_status, &status, sizeof(status))) {
+		blocking_notifier_call_chain(&framer->notifier_list,
+					     FRAMER_EVENT_STATUS, NULL);
+		memcpy(&framer->prev_status, &status, sizeof(status));
+	}
+
+end:
+	/* Re-schedule task in 1 sec */
+	queue_delayed_work(system_power_efficient_wq, &framer->polling_work, 1 * HZ);
+}
+
+/**
+ * framer_notifier_register() - Registers a notifier
+ * @framer: the framer returned by framer_get()
+ * @nb: the notifier block to register
+ *
+ * Used to register a notifier block on framer events. framer_init() must have
+ * been called on the framer.
+ * The available framer events are present in enum framer_events.
+ *
+ * Return: %0 if successful, a negative error code otherwise
+ */
+int framer_notifier_register(struct framer *framer, struct notifier_block *nb)
+{
+	return blocking_notifier_chain_register(&framer->notifier_list, nb);
+}
+EXPORT_SYMBOL_GPL(framer_notifier_register);
+
+/**
+ * framer_notifier_unregister() - Unregisters a notifier
+ * @framer: the framer returned by framer_get()
+ * @nb: the notifier block to unregister
+ *
+ * Used to unregister a notifier block. framer_init() must have
+ * been called on the framer.
+ *
+ * Return: %0 if successful, a negative error code otherwise
+ */
+int framer_notifier_unregister(struct framer *framer, struct notifier_block *nb)
+{
+	return blocking_notifier_chain_unregister(&framer->notifier_list, nb);
+}
+EXPORT_SYMBOL_GPL(framer_notifier_unregister);
+
+static struct framer_provider *framer_provider_of_lookup(const struct device_node *node)
+{
+	struct framer_provider *framer_provider;
+
+	list_for_each_entry(framer_provider, &framer_provider_list, list) {
+		if (device_match_of_node(framer_provider->dev, node))
+			return framer_provider;
+	}
+
+	return ERR_PTR(-EPROBE_DEFER);
+}
+
+static struct framer *framer_of_get_from_provider(struct of_phandle_args *args)
+{
+	struct framer_provider *framer_provider;
+	struct framer *framer;
+
+	mutex_lock(&framer_provider_mutex);
+	framer_provider = framer_provider_of_lookup(args->np);
+	if (IS_ERR(framer_provider) || !try_module_get(framer_provider->owner)) {
+		framer = ERR_PTR(-EPROBE_DEFER);
+		goto end;
+	}
+
+	framer = framer_provider->of_xlate(framer_provider->dev, args);
+
+	module_put(framer_provider->owner);
+
+end:
+	mutex_unlock(&framer_provider_mutex);
+
+	return framer;
+}
+
+static struct framer *framer_of_get_byphandle(struct device_node *np, const char *propname,
+					      int index)
+{
+	struct of_phandle_args args;
+	struct framer *framer;
+	int ret;
+
+	ret = of_parse_phandle_with_optional_args(np, propname, "#framer-cells", index, &args);
+	if (ret)
+		return ERR_PTR(-ENODEV);
+
+	if (!of_device_is_available(args.np)) {
+		framer = ERR_PTR(-ENODEV);
+		goto out_node_put;
+	}
+
+	framer = framer_of_get_from_provider(&args);
+
+out_node_put:
+	of_node_put(args.np);
+
+	return framer;
+}
+
+static struct framer *framer_of_get_byparent(struct device_node *np, int index)
+{
+	struct of_phandle_args args;
+	struct framer *framer;
+
+	args.np = of_get_parent(np);
+	args.args_count = 1;
+	args.args[0] = index;
+
+	while (args.np) {
+		framer = framer_of_get_from_provider(&args);
+		if (IS_ERR(framer) && PTR_ERR(framer) != -EPROBE_DEFER) {
+			args.np = of_get_next_parent(args.np);
+			continue;
+		}
+		of_node_put(args.np);
+		return framer;
+	}
+
+	return ERR_PTR(-ENODEV);
+}
+
+/**
+ * framer_get() - lookup and obtain a reference to a framer.
+ * @dev: device that requests the framer
+ * @con_id: name of the framer from device's point of view
+ *
+ * Returns the framer driver, after getting a refcount to it; or
+ * -ENODEV if there is no such framer. The caller is responsible for
+ * calling framer_put() to release that count.
+ */
+struct framer *framer_get(struct device *dev, const char *con_id)
+{
+	struct framer *framer = ERR_PTR(-ENODEV);
+	struct device_link *link;
+	int ret;
+
+	if (dev->of_node) {
+		if (con_id)
+			framer = framer_of_get_byphandle(dev->of_node, con_id, 0);
+		else
+			framer = framer_of_get_byparent(dev->of_node, 0);
+	}
+
+	if (IS_ERR(framer))
+		return framer;
+
+	get_device(&framer->dev);
+
+	if (!try_module_get(framer->ops->owner)) {
+		ret = -EPROBE_DEFER;
+		goto err_put_device;
+	}
+
+	link = device_link_add(dev, &framer->dev, DL_FLAG_STATELESS);
+	if (!link) {
+		dev_err(dev, "failed to create device_link to %s\n", dev_name(&framer->dev));
+		ret = -EPROBE_DEFER;
+		goto err_module_put;
+	}
+
+	return framer;
+
+err_module_put:
+	module_put(framer->ops->owner);
+err_put_device:
+	put_device(&framer->dev);
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(framer_get);
+
+/**
+ * framer_put() - release the framer
+ * @dev: device that wants to release this framer
+ * @framer: the framer returned by framer_get()
+ *
+ * Releases a refcount the caller received from framer_get().
+ */
+void framer_put(struct device *dev, struct framer *framer)
+{
+	device_link_remove(dev, &framer->dev);
+
+	module_put(framer->ops->owner);
+	put_device(&framer->dev);
+}
+EXPORT_SYMBOL_GPL(framer_put);
+
+static void devm_framer_put(struct device *dev, void *res)
+{
+	struct framer *framer = *(struct framer **)res;
+
+	framer_put(dev, framer);
+}
+
+/**
+ * devm_framer_get() - lookup and obtain a reference to a framer.
+ * @dev: device that requests this framer
+ * @con_id: name of the framer from device's point of view
+ *
+ * Gets the framer using framer_get(), and associates a device with it using
+ * devres. On driver detach, framer_put() function is invoked on the devres
+ * data, then, devres data is freed.
+ */
+struct framer *devm_framer_get(struct device *dev, const char *con_id)
+{
+	struct framer **ptr, *framer;
+
+	ptr = devres_alloc(devm_framer_put, sizeof(*ptr), GFP_KERNEL);
+	if (!ptr)
+		return ERR_PTR(-ENOMEM);
+
+	framer = framer_get(dev, con_id);
+	if (!IS_ERR(framer)) {
+		*ptr = framer;
+		devres_add(dev, ptr);
+	} else {
+		devres_free(ptr);
+		return framer;
+	}
+
+	return framer;
+}
+EXPORT_SYMBOL_GPL(devm_framer_get);
+
+/**
+ * devm_framer_optional_get() - lookup and obtain a reference to an optional
+ * framer.
+ * @dev: device that requests this framer
+ * @con_id: name of the framer from device's point of view
+ *
+ * Same as devm_framer_get() except that if the framer does not exist, it is not
+ * considered an error and -ENODEV will not be returned. Instead the NULL framer
+ * is returned.
+ */
+struct framer *devm_framer_optional_get(struct device *dev, const char *con_id)
+{
+	struct framer *framer = devm_framer_get(dev, con_id);
+
+	if (PTR_ERR(framer) == -ENODEV)
+		framer = NULL;
+
+	return framer;
+}
+EXPORT_SYMBOL_GPL(devm_framer_optional_get);
+
+static void framer_notify_status_work(struct work_struct *work)
+{
+	struct framer *framer = container_of(work, struct framer, notify_status_work);
+
+	blocking_notifier_call_chain(&framer->notifier_list, FRAMER_EVENT_STATUS, NULL);
+}
+
+void framer_notify_status_change(struct framer *framer)
+{
+	/* Can be called from atomic context -> just schedule a task to call
+	 * blocking notifiers
+	 */
+	queue_work(system_power_efficient_wq, &framer->notify_status_work);
+}
+EXPORT_SYMBOL_GPL(framer_notify_status_change);
+
+/**
+ * framer_create() - create a new framer
+ * @dev: device that is creating the new framer
+ * @node: device node of the framer. default to dev->of_node.
+ * @ops: function pointers for performing framer operations
+ *
+ * Called to create a framer using framer framework.
+ */
+struct framer *framer_create(struct device *dev, struct device_node *node,
+			     const struct framer_ops *ops)
+{
+	struct framer *framer;
+	int ret;
+	int id;
+
+	/* get_status() is mandatory if the provider ask for polling status */
+	if (WARN_ON((ops->flags & FRAMER_FLAG_POLL_STATUS) && !ops->get_status))
+		return ERR_PTR(-EINVAL);
+
+	framer = kzalloc(sizeof(*framer), GFP_KERNEL);
+	if (!framer)
+		return ERR_PTR(-ENOMEM);
+
+	id = ida_alloc(&framer_ida, GFP_KERNEL);
+	if (id < 0) {
+		dev_err(dev, "unable to get id\n");
+		ret = id;
+		goto free_framer;
+	}
+
+	device_initialize(&framer->dev);
+	mutex_init(&framer->mutex);
+	INIT_WORK(&framer->notify_status_work, framer_notify_status_work);
+	INIT_DELAYED_WORK(&framer->polling_work, framer_polling_work);
+	BLOCKING_INIT_NOTIFIER_HEAD(&framer->notifier_list);
+
+	framer->dev.class = framer_class;
+	framer->dev.parent = dev;
+	framer->dev.of_node = node ? node : dev->of_node;
+	framer->id = id;
+	framer->ops = ops;
+
+	ret = dev_set_name(&framer->dev, "framer-%s.%d", dev_name(dev), id);
+	if (ret)
+		goto put_dev;
+
+	/* framer-supply */
+	framer->pwr = regulator_get_optional(&framer->dev, "framer");
+	if (IS_ERR(framer->pwr)) {
+		ret = PTR_ERR(framer->pwr);
+		if (ret == -EPROBE_DEFER)
+			goto put_dev;
+
+		framer->pwr = NULL;
+	}
+
+	ret = device_add(&framer->dev);
+	if (ret)
+		goto put_dev;
+
+	if (pm_runtime_enabled(dev)) {
+		pm_runtime_enable(&framer->dev);
+		pm_runtime_no_callbacks(&framer->dev);
+	}
+
+	return framer;
+
+put_dev:
+	put_device(&framer->dev);  /* calls framer_release() which frees resources */
+	return ERR_PTR(ret);
+
+free_framer:
+	kfree(framer);
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(framer_create);
+
+/**
+ * framer_destroy() - destroy the framer
+ * @framer: the framer to be destroyed
+ *
+ * Called to destroy the framer.
+ */
+void framer_destroy(struct framer *framer)
+{
+	/* polling_work should already be stopped but if framer_exit() was not
+	 * called (bug), here it's the last time to do that ...
+	 */
+	cancel_delayed_work_sync(&framer->polling_work);
+	cancel_work_sync(&framer->notify_status_work);
+	pm_runtime_disable(&framer->dev);
+	device_unregister(&framer->dev); /* calls framer_release() which frees resources */
+}
+EXPORT_SYMBOL_GPL(framer_destroy);
+
+static void devm_framer_destroy(struct device *dev, void *res)
+{
+	struct framer *framer = *(struct framer **)res;
+
+	framer_destroy(framer);
+}
+
+/**
+ * devm_framer_create() - create a new framer
+ * @dev: device that is creating the new framer
+ * @node: device node of the framer
+ * @ops: function pointers for performing framer operations
+ *
+ * Creates a new framer device adding it to the framer class.
+ * While at that, it also associates the device with the framer using devres.
+ * On driver detach, release function is invoked on the devres data,
+ * then, devres data is freed.
+ */
+struct framer *devm_framer_create(struct device *dev, struct device_node *node,
+				  const struct framer_ops *ops)
+{
+	struct framer **ptr, *framer;
+
+	ptr = devres_alloc(devm_framer_destroy, sizeof(*ptr), GFP_KERNEL);
+	if (!ptr)
+		return ERR_PTR(-ENOMEM);
+
+	framer = framer_create(dev, node, ops);
+	if (!IS_ERR(framer)) {
+		*ptr = framer;
+		devres_add(dev, ptr);
+	} else {
+		devres_free(ptr);
+	}
+
+	return framer;
+}
+EXPORT_SYMBOL_GPL(devm_framer_create);
+
+/**
+ * framer_provider_simple_of_xlate() - returns the framer instance from framer provider
+ * @dev: the framer provider device
+ * @args: of_phandle_args (not used here)
+ *
+ * Intended to be used by framer provider for the common case where #framer-cells is
+ * 0. For other cases where #framer-cells is greater than '0', the framer provider
+ * should provide a custom of_xlate function that reads the *args* and returns
+ * the appropriate framer.
+ */
+struct framer *framer_provider_simple_of_xlate(struct device *dev, struct of_phandle_args *args)
+{
+	struct class_dev_iter iter;
+	struct framer *framer;
+
+	class_dev_iter_init(&iter, framer_class, NULL, NULL);
+	while ((dev = class_dev_iter_next(&iter))) {
+		framer = dev_to_framer(dev);
+		if (args->np != framer->dev.of_node)
+			continue;
+
+		class_dev_iter_exit(&iter);
+		return framer;
+	}
+
+	class_dev_iter_exit(&iter);
+	return ERR_PTR(-ENODEV);
+}
+EXPORT_SYMBOL_GPL(framer_provider_simple_of_xlate);
+
+/**
+ * __framer_provider_of_register() - create/register framer provider with the framework
+ * @dev: struct device of the framer provider
+ * @owner: the module owner containing of_xlate
+ * @of_xlate: function pointer to obtain framer instance from framer provider
+ *
+ * Creates struct framer_provider from dev and of_xlate function pointer.
+ * This is used in the case of dt boot for finding the framer instance from
+ * framer provider.
+ */
+struct framer_provider *
+__framer_provider_of_register(struct device *dev, struct module *owner,
+			      struct framer *(*of_xlate)(struct device *dev,
+							 struct of_phandle_args *args))
+{
+	struct framer_provider *framer_provider;
+
+	framer_provider = kzalloc(sizeof(*framer_provider), GFP_KERNEL);
+	if (!framer_provider)
+		return ERR_PTR(-ENOMEM);
+
+	framer_provider->dev = dev;
+	framer_provider->owner = owner;
+	framer_provider->of_xlate = of_xlate;
+
+	of_node_get(framer_provider->dev->of_node);
+
+	mutex_lock(&framer_provider_mutex);
+	list_add_tail(&framer_provider->list, &framer_provider_list);
+	mutex_unlock(&framer_provider_mutex);
+
+	return framer_provider;
+}
+EXPORT_SYMBOL_GPL(__framer_provider_of_register);
+
+/**
+ * framer_provider_of_unregister() - unregister framer provider from the framework
+ * @framer_provider: framer provider returned by framer_provider_of_register()
+ *
+ * Removes the framer_provider created using framer_provider_of_register().
+ */
+void framer_provider_of_unregister(struct framer_provider *framer_provider)
+{
+	mutex_lock(&framer_provider_mutex);
+	list_del(&framer_provider->list);
+	mutex_unlock(&framer_provider_mutex);
+
+	of_node_put(framer_provider->dev->of_node);
+	kfree(framer_provider);
+}
+EXPORT_SYMBOL_GPL(framer_provider_of_unregister);
+
+static void devm_framer_provider_of_unregister(struct device *dev, void *res)
+{
+	struct framer_provider *framer_provider = *(struct framer_provider **)res;
+
+	framer_provider_of_unregister(framer_provider);
+}
+
+/**
+ * __devm_framer_provider_of_register() - create/register framer provider with
+ * the framework
+ * @dev: struct device of the framer provider
+ * @owner: the module owner containing of_xlate
+ * @of_xlate: function pointer to obtain framer instance from framer provider
+ *
+ * Creates struct framer_provider from dev and of_xlate function pointer.
+ * This is used in the case of dt boot for finding the framer instance from
+ * framer provider. While at that, it also associates the device with the
+ * framer provider using devres. On driver detach, release function is invoked
+ * on the devres data, then, devres data is freed.
+ */
+struct framer_provider *
+__devm_framer_provider_of_register(struct device *dev, struct module *owner,
+				   struct framer *(*of_xlate)(struct device *dev,
+							      struct of_phandle_args *args))
+{
+	struct framer_provider **ptr, *framer_provider;
+
+	ptr = devres_alloc(devm_framer_provider_of_unregister, sizeof(*ptr), GFP_KERNEL);
+	if (!ptr)
+		return ERR_PTR(-ENOMEM);
+
+	framer_provider = __framer_provider_of_register(dev, owner, of_xlate);
+	if (!IS_ERR(framer_provider)) {
+		*ptr = framer_provider;
+		devres_add(dev, ptr);
+	} else {
+		devres_free(ptr);
+	}
+
+	return framer_provider;
+}
+EXPORT_SYMBOL_GPL(__devm_framer_provider_of_register);
+
+/**
+ * framer_release() - release the framer
+ * @dev: the dev member within framer
+ *
+ * When the last reference to the device is removed, it is called
+ * from the embedded kobject as release method.
+ */
+static void framer_release(struct device *dev)
+{
+	struct framer *framer;
+
+	framer = dev_to_framer(dev);
+	regulator_put(framer->pwr);
+	ida_free(&framer_ida, framer->id);
+	kfree(framer);
+}
+
+static int __init framer_core_init(void)
+{
+	framer_class = class_create("framer");
+	if (IS_ERR(framer_class)) {
+		pr_err("failed to create framer class (%pe)\n", framer_class);
+		return PTR_ERR(framer_class);
+	}
+
+	framer_class->dev_release = framer_release;
+
+	return 0;
+}
+device_initcall(framer_core_init);
diff --git a/include/linux/framer/framer-provider.h b/include/linux/framer/framer-provider.h
new file mode 100644
index 000000000000..782cd5fc83d5
--- /dev/null
+++ b/include/linux/framer/framer-provider.h
@@ -0,0 +1,194 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Generic framer profider header file
+ *
+ * Copyright 2023 CS GROUP France
+ *
+ * Author: Herve Codina <herve.codina@bootlin.com>
+ */
+
+#ifndef __DRIVERS_PROVIDER_FRAMER_H
+#define __DRIVERS_PROVIDER_FRAMER_H
+
+#include <linux/export.h>
+#include <linux/framer/framer.h>
+#include <linux/types.h>
+
+#define FRAMER_FLAG_POLL_STATUS  BIT(0)
+
+/**
+ * struct framer_ops - set of function pointers for performing framer operations
+ * @init: operation to be performed for initializing the framer
+ * @exit: operation to be performed while exiting
+ * @power_on: powering on the framer
+ * @power_off: powering off the framer
+ * @flags: OR-ed flags (FRAMER_FLAG_*) to ask for core functionality
+ *          - @FRAMER_FLAG_POLL_STATUS:
+ *            Ask the core to perform a polling to get the framer status and
+ *            notify consumers on change.
+ *            The framer should call @framer_notify_status_change() when it
+ *            detects a status change. This is usually done using interrupts.
+ *            If the framer cannot detect this change, it can ask the core for
+ *            a status polling. The core will call @get_status() periodically
+ *            and, on change detected, it will notify the consumer.
+ *            the @get_status()
+ * @owner: the module owner containing the ops
+ */
+struct framer_ops {
+	int	(*init)(struct framer *framer);
+	void	(*exit)(struct framer *framer);
+	int	(*power_on)(struct framer *framer);
+	int	(*power_off)(struct framer *framer);
+
+	/**
+	 * @get_status:
+	 *
+	 * Optional.
+	 *
+	 * Used to get the framer status. framer_init() must have
+	 * been called on the framer.
+	 *
+	 * Returns: 0 if successful, an negative error code otherwise
+	 */
+	int	(*get_status)(struct framer *framer, struct framer_status *status);
+
+	/**
+	 * @set_config:
+	 *
+	 * Optional.
+	 *
+	 * Used to set the framer configuration. framer_init() must have
+	 * been called on the framer.
+	 *
+	 * Returns: 0 if successful, an negative error code otherwise
+	 */
+	int	(*set_config)(struct framer *framer, const struct framer_config *config);
+
+	/**
+	 * @get_config:
+	 *
+	 * Optional.
+	 *
+	 * Used to get the framer configuration. framer_init() must have
+	 * been called on the framer.
+	 *
+	 * Returns: 0 if successful, an negative error code otherwise
+	 */
+	int	(*get_config)(struct framer *framer, struct framer_config *config);
+
+	u32 flags;
+	struct module *owner;
+};
+
+/**
+ * struct framer_provider - represents the framer provider
+ * @dev: framer provider device
+ * @children: can be used to override the default (dev->of_node) child node
+ * @owner: the module owner having of_xlate
+ * @list: to maintain a linked list of framer providers
+ * @of_xlate: function pointer to obtain framer instance from framer pointer
+ */
+struct framer_provider {
+	struct device		*dev;
+	struct module		*owner;
+	struct list_head	list;
+	struct framer * (*of_xlate)(struct device *dev,
+				    struct of_phandle_args *args);
+};
+
+static inline void framer_set_drvdata(struct framer *framer, void *data)
+{
+	dev_set_drvdata(&framer->dev, data);
+}
+
+static inline void *framer_get_drvdata(struct framer *framer)
+{
+	return dev_get_drvdata(&framer->dev);
+}
+
+#if IS_ENABLED(CONFIG_GENERIC_FRAMER)
+
+/* Create and destroy a framer */
+struct framer *framer_create(struct device *dev, struct device_node *node,
+			     const struct framer_ops *ops);
+void framer_destroy(struct framer *framer);
+
+/* devm version */
+struct framer *devm_framer_create(struct device *dev, struct device_node *node,
+				  const struct framer_ops *ops);
+
+struct framer *framer_provider_simple_of_xlate(struct device *dev,
+					       struct of_phandle_args *args);
+
+struct framer_provider *
+__framer_provider_of_register(struct device *dev, struct module *owner,
+			      struct framer *(*of_xlate)(struct device *dev,
+							 struct of_phandle_args *args));
+
+void framer_provider_of_unregister(struct framer_provider *framer_provider);
+
+struct framer_provider *
+__devm_framer_provider_of_register(struct device *dev, struct module *owner,
+				   struct framer *(*of_xlate)(struct device *dev,
+							      struct of_phandle_args *args));
+
+void framer_notify_status_change(struct framer *framer);
+
+#else /* IS_ENABLED(CONFIG_GENERIC_FRAMER) */
+
+static inline struct framer *framer_create(struct device *dev, struct device_node *node,
+					   const struct framer_ops *ops)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+static inline void framer_destroy(struct framer *framer)
+{
+}
+
+/* devm version */
+static inline struct framer *devm_framer_create(struct device *dev, struct device_node *node,
+						const struct framer_ops *ops)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+static inline struct framer *framer_provider_simple_of_xlate(struct device *dev,
+							     struct of_phandle_args *args)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+static inline struct framer_provider *
+__framer_provider_of_register(struct device *dev, struct module *owner,
+			      struct framer *(*of_xlate)(struct device *dev,
+							 struct of_phandle_args *args))
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+void framer_provider_of_unregister(struct framer_provider *framer_provider)
+{
+}
+
+static inline struct framer_provider *
+__devm_framer_provider_of_register(struct device *dev, struct module *owner,
+				   struct framer *(*of_xlate)(struct device *dev,
+							      struct of_phandle_args *args))
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+void framer_notify_status_change(struct framer *framer)
+{
+}
+
+#endif /* IS_ENABLED(CONFIG_GENERIC_FRAMER) */
+
+#define framer_provider_of_register(dev, xlate)		\
+	__framer_provider_of_register((dev), THIS_MODULE, (xlate))
+
+#define devm_framer_provider_of_register(dev, xlate)	\
+	__devm_framer_provider_of_register((dev), THIS_MODULE, (xlate))
+
+#endif /* __DRIVERS_PROVIDER_FRAMER_H */
diff --git a/include/linux/framer/framer.h b/include/linux/framer/framer.h
new file mode 100644
index 000000000000..9a9b88962c29
--- /dev/null
+++ b/include/linux/framer/framer.h
@@ -0,0 +1,205 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Generic framer header file
+ *
+ * Copyright 2023 CS GROUP France
+ *
+ * Author: Herve Codina <herve.codina@bootlin.com>
+ */
+
+#ifndef __DRIVERS_FRAMER_H
+#define __DRIVERS_FRAMER_H
+
+#include <linux/err.h>
+#include <linux/mutex.h>
+#include <linux/notifier.h>
+#include <linux/of.h>
+#include <linux/device.h>
+#include <linux/workqueue.h>
+
+/**
+ * enum framer_iface - Framer interface
+ * @FRAMER_IFACE_E1: E1 interface
+ * @FRAMER_IFACE_T1: T1 interface
+ */
+enum framer_iface {
+	FRAMER_IFACE_E1,
+	FRAMER_IFACE_T1,
+};
+
+/**
+ * enum framer_clock_type - Framer clock type
+ * @FRAMER_CLOCK_EXT: External clock
+ * @FRAMER_CLOCK_INT: Internal clock
+ */
+enum framer_clock_type {
+	FRAMER_CLOCK_EXT,
+	FRAMER_CLOCK_INT,
+};
+
+/**
+ * struct framer_config - Framer configuration
+ * @iface: Framer line interface
+ * @clock_type: Framer clock type
+ * @line_clock_rate: Framer line clock rate
+ */
+struct framer_config {
+	enum framer_iface iface;
+	enum framer_clock_type clock_type;
+	unsigned long line_clock_rate;
+};
+
+/**
+ * struct framer_status - Framer status
+ * @link_is_on: Framer link state. true, the link is on, false, the link is off.
+ */
+struct framer_status {
+	bool link_is_on;
+};
+
+/**
+ * enum framer_event - Event available for notification
+ * @FRAMER_EVENT_STATUS: Event notified on framer_status changes
+ */
+enum framer_event {
+	FRAMER_EVENT_STATUS,
+};
+
+/**
+ * struct framer - represents the framer device
+ * @dev: framer device
+ * @id: id of the framer device
+ * @ops: function pointers for performing framer operations
+ * @mutex: mutex to protect framer_ops
+ * @init_count: used to protect when the framer is used by multiple consumers
+ * @power_count: used to protect when the framer is used by multiple consumers
+ * @pwr: power regulator associated with the framer
+ * @notify_status_work: work structure used for status notifications
+ * @notifier_list: notifier list used for notifications
+ * @polling_work: delayed work structure used for the polling task
+ * @prev_status: previous read status used by the polling task to detect changes
+ */
+struct framer {
+	struct device			dev;
+	int				id;
+	const struct framer_ops		*ops;
+	struct mutex			mutex;	/* Protect framer */
+	int				init_count;
+	int				power_count;
+	struct regulator		*pwr;
+	struct work_struct		notify_status_work;
+	struct blocking_notifier_head	notifier_list;
+	struct delayed_work		polling_work;
+	struct framer_status		prev_status;
+};
+
+#if IS_ENABLED(CONFIG_GENERIC_FRAMER)
+int framer_pm_runtime_get(struct framer *framer);
+int framer_pm_runtime_get_sync(struct framer *framer);
+int framer_pm_runtime_put(struct framer *framer);
+int framer_pm_runtime_put_sync(struct framer *framer);
+int framer_init(struct framer *framer);
+int framer_exit(struct framer *framer);
+int framer_power_on(struct framer *framer);
+int framer_power_off(struct framer *framer);
+int framer_get_status(struct framer *framer, struct framer_status *status);
+int framer_get_config(struct framer *framer, struct framer_config *config);
+int framer_set_config(struct framer *framer, const struct framer_config *config);
+int framer_notifier_register(struct framer *framer, struct notifier_block *nb);
+int framer_notifier_unregister(struct framer *framer, struct notifier_block *nb);
+
+struct framer *framer_get(struct device *dev, const char *con_id);
+void framer_put(struct device *dev, struct framer *framer);
+
+struct framer *devm_framer_get(struct device *dev, const char *con_id);
+struct framer *devm_framer_optional_get(struct device *dev, const char *con_id);
+#else
+static inline int framer_pm_runtime_get(struct framer *framer)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_pm_runtime_get_sync(struct framer *framer)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_pm_runtime_put(struct framer *framer)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_pm_runtime_put_sync(struct framer *framer)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_init(struct framer *framer)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_exit(struct framer *framer)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_power_on(struct framer *framer)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_power_off(struct framer *framer)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_get_status(struct framer *framer, struct framer_status *status)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_get_config(struct framer *framer, struct framer_config *config)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_set_config(struct framer *framer, const struct framer_config *config)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_notifier_register(struct framer *framer,
+					   struct notifier_block *nb)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_notifier_unregister(struct framer *framer,
+					     struct notifier_block *nb)
+{
+	return -ENOSYS;
+}
+
+struct framer *framer_get(struct device *dev, const char *con_id)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+void framer_put(struct device *dev, struct framer *framer)
+{
+}
+
+static inline struct framer *devm_framer_get(struct device *dev, const char *con_id)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+static inline struct framer *devm_framer_optional_get(struct device *dev, const char *con_id)
+{
+	return NULL;
+}
+
+#endif
+
+#endif /* __DRIVERS_FRAMER_H */
-- 
cgit v1.2.3


From c96e976d9a05d559f4ac4f617ea0f798c75a1799 Mon Sep 17 00:00:00 2001
From: Herve Codina <herve.codina@bootlin.com>
Date: Tue, 28 Nov 2023 14:25:32 +0100
Subject: net: wan: framer: Add support for the Lantiq PEF2256 framer

The Lantiq PEF2256 is a framer and line interface component designed to
fulfill all required interfacing between an analog E1/T1/J1 line and the
digital PCM system highway/H.100 bus.

Signed-off-by: Herve Codina <herve.codina@bootlin.com>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20231128132534.258459-4-herve.codina@bootlin.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/net/wan/framer/Kconfig                |  17 +
 drivers/net/wan/framer/Makefile               |   1 +
 drivers/net/wan/framer/pef2256/Makefile       |   8 +
 drivers/net/wan/framer/pef2256/pef2256-regs.h | 250 ++++++++
 drivers/net/wan/framer/pef2256/pef2256.c      | 880 ++++++++++++++++++++++++++
 include/linux/framer/pef2256.h                |  31 +
 6 files changed, 1187 insertions(+)
 create mode 100644 drivers/net/wan/framer/pef2256/Makefile
 create mode 100644 drivers/net/wan/framer/pef2256/pef2256-regs.h
 create mode 100644 drivers/net/wan/framer/pef2256/pef2256.c
 create mode 100644 include/linux/framer/pef2256.h

(limited to 'include')

diff --git a/drivers/net/wan/framer/Kconfig b/drivers/net/wan/framer/Kconfig
index 57fe7ba6aa37..dc83caef9485 100644
--- a/drivers/net/wan/framer/Kconfig
+++ b/drivers/net/wan/framer/Kconfig
@@ -22,4 +22,21 @@ if FRAMER
 config GENERIC_FRAMER
 	bool
 
+config FRAMER_PEF2256
+	tristate "Lantiq PEF2256"
+	depends on OF
+	depends on HAS_IOMEM
+	select GENERIC_FRAMER
+	select MFD_CORE
+	select REGMAP_MMIO
+	help
+	  Enable support for the Lantiq PEF2256 (FALC56) framer.
+	  The PEF2256 is a framer and line interface between analog E1/T1/J1
+	  line and a digital PCM bus.
+
+	  If unsure, say N.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called framer-pef2256.
+
 endif # FRAMER
diff --git a/drivers/net/wan/framer/Makefile b/drivers/net/wan/framer/Makefile
index 78dbd8e563d0..3403f2b14534 100644
--- a/drivers/net/wan/framer/Makefile
+++ b/drivers/net/wan/framer/Makefile
@@ -4,3 +4,4 @@
 #
 
 obj-$(CONFIG_GENERIC_FRAMER)			+= framer-core.o
+obj-$(CONFIG_FRAMER_PEF2256)			+= pef2256/
diff --git a/drivers/net/wan/framer/pef2256/Makefile b/drivers/net/wan/framer/pef2256/Makefile
new file mode 100644
index 000000000000..f4d1208dd8a4
--- /dev/null
+++ b/drivers/net/wan/framer/pef2256/Makefile
@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for the pef2256 driver.
+#
+
+obj-$(CONFIG_FRAMER_PEF2256)		+= framer-pef2256.o
+
+framer-pef2256-objs	:= pef2256.o
diff --git a/drivers/net/wan/framer/pef2256/pef2256-regs.h b/drivers/net/wan/framer/pef2256/pef2256-regs.h
new file mode 100644
index 000000000000..5d3183c91714
--- /dev/null
+++ b/drivers/net/wan/framer/pef2256/pef2256-regs.h
@@ -0,0 +1,250 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * PEF2256 registers definition
+ *
+ * Copyright 2023 CS GROUP France
+ *
+ * Author: Herve Codina <herve.codina@bootlin.com>
+ */
+#ifndef __PEF2256_REGS_H__
+#define __PEF2256_REGS_H__
+
+#include "linux/bitfield.h"
+
+/* Command Register */
+#define PEF2256_CMDR		0x02
+#define PEF2256_CMDR_RRES	BIT(6)
+#define PEF2256_CMDR_XRES	BIT(4)
+#define PEF2256_CMDR_SRES	BIT(0)
+
+/* Interrupt Mask Register 0..5 */
+#define PEF2256_IMR0	        0x14
+#define PEF2256_IMR1	        0x15
+#define PEF2256_IMR2	        0x16
+#define PEF2256_IMR3	        0x17
+#define PEF2256_IMR4	        0x18
+#define PEF2256_IMR5	        0x19
+
+/* Framer Mode Register 0 */
+#define PEF2256_FMR0		0x1C
+#define PEF2256_FMR0_XC_MASK	GENMASK(7, 6)
+#define PEF2256_FMR0_XC_NRZ	FIELD_PREP_CONST(PEF2256_FMR0_XC_MASK, 0x0)
+#define PEF2256_FMR0_XC_CMI	FIELD_PREP_CONST(PEF2256_FMR0_XC_MASK, 0x1)
+#define PEF2256_FMR0_XC_AMI	FIELD_PREP_CONST(PEF2256_FMR0_XC_MASK, 0x2)
+#define PEF2256_FMR0_XC_HDB3	FIELD_PREP_CONST(PEF2256_FMR0_XC_MASK, 0x3)
+#define PEF2256_FMR0_RC_MASK	GENMASK(5, 4)
+#define PEF2256_FMR0_RC_NRZ	FIELD_PREP_CONST(PEF2256_FMR0_RC_MASK, 0x0)
+#define PEF2256_FMR0_RC_CMI	FIELD_PREP_CONST(PEF2256_FMR0_RC_MASK, 0x1)
+#define PEF2256_FMR0_RC_AMI	FIELD_PREP_CONST(PEF2256_FMR0_RC_MASK, 0x2)
+#define PEF2256_FMR0_RC_HDB3	FIELD_PREP_CONST(PEF2256_FMR0_RC_MASK, 0x3)
+
+/* Framer Mode Register 1 */
+#define PEF2256_FMR1		0x1D
+#define PEF2256_FMR1_XFS	BIT(3)
+#define PEF2256_FMR1_ECM	BIT(2)
+/* SSD is defined on 2 bits. The other bit is on SIC1 register */
+#define PEF2256_FMR1_SSD_MASK	GENMASK(1, 1)
+#define PEF2256_FMR1_SSD_2048	FIELD_PREP_CONST(PEF2256_FMR1_SSD_MASK, 0x0)
+#define PEF2256_FMR1_SSD_4096	FIELD_PREP_CONST(PEF2256_FMR1_SSD_MASK, 0x1)
+#define PEF2256_FMR1_SSD_8192	FIELD_PREP_CONST(PEF2256_FMR1_SSD_MASK, 0x0)
+#define PEF2256_FMR1_SSD_16384	FIELD_PREP_CONST(PEF2256_FMR1_SSD_MASK, 0x1)
+
+/* Framer Mode Register 2 */
+#define PEF2256_FMR2			  0x1E
+#define PEF2256_FMR2_RFS_MASK		  GENMASK(7, 6)
+#define PEF2256_FMR2_RFS_DOUBLEFRAME	  FIELD_PREP_CONST(PEF2256_FMR2_RFS_MASK, 0x0)
+#define PEF2256_FMR2_RFS_CRC4_MULTIFRAME  FIELD_PREP_CONST(PEF2256_FMR2_RFS_MASK, 0x2)
+#define PEF2256_FMR2_RFS_AUTO_MULTIFRAME  FIELD_PREP_CONST(PEF2256_FMR2_RFS_MASK, 0x3)
+#define PEF2256_FMR2_AXRA		  BIT(1)
+
+/* Transmit Service Word */
+#define PEF2256_XSW		0x20
+#define PEF2256_XSW_XSIS	BIT(7)
+#define PEF2256_XSW_XTM		BIT(6)
+#define PEF2256_XSW_XY_MASK	GENMASK(5, 0)
+#define PEF2256_XSW_XY(_v)	FIELD_PREP(PEF2256_XSW_XY_MASK, _v)
+
+/* Transmit Spare Bits */
+#define PEF2256_XSP	        0x21
+#define PEF2256_XSP_XSIF	BIT(2)
+
+/* Transmit Control 0..1 */
+#define PEF2256_XC0		0x22
+#define PEF2256_XC1		0x23
+
+/* Receive Control 0 */
+#define PEF2256_RC0		0x24
+#define PEF2256_RC0_SWD		BIT(7)
+#define PEF2256_RC0_ASY4	BIT(6)
+
+/* Receive Control 1 */
+#define PEF2256_RC1		0x25
+
+/* Transmit Pulse Mask 0..1 */
+#define PEF2256_XPM0		0x26
+#define PEF2256_XPM1		0x27
+
+/* Transmit Pulse Mask 2 */
+#define PEF2256_XPM2		0x28
+#define PEF2256_XPM2_XLT	BIT(6)
+
+/* Transparent Service Word Mask */
+#define PEF2256_TSWM		0x29
+
+/* Line Interface Mode 0 */
+#define PEF2256_LIM0		0x36
+#define PEF2256_2X_LIM0_BIT3	BIT(3) /* v2.x, described as a forced '1' bit */
+#define PEF2256_LIM0_MAS	BIT(0)
+
+/* Line Interface Mode 1 */
+#define PEF2256_LIM1		  0x37
+#define PEF2256_12_LIM1_RIL_MASK  GENMASK(6, 4)
+#define PEF2256_12_LIM1_RIL_910	  FIELD_PREP_CONST(PEF2256_12_LIM1_RIL_MASK, 0x0)
+#define PEF2256_12_LIM1_RIL_740	  FIELD_PREP_CONST(PEF2256_12_LIM1_RIL_MASK, 0x1)
+#define PEF2256_12_LIM1_RIL_590	  FIELD_PREP_CONST(PEF2256_12_LIM1_RIL_MASK, 0x2)
+#define PEF2256_12_LIM1_RIL_420	  FIELD_PREP_CONST(PEF2256_12_LIM1_RIL_MASK, 0x3)
+#define PEF2256_12_LIM1_RIL_320	  FIELD_PREP_CONST(PEF2256_12_LIM1_RIL_MASK, 0x4)
+#define PEF2256_12_LIM1_RIL_210	  FIELD_PREP_CONST(PEF2256_12_LIM1_RIL_MASK, 0x5)
+#define PEF2256_12_LIM1_RIL_160	  FIELD_PREP_CONST(PEF2256_12_LIM1_RIL_MASK, 0x6)
+#define PEF2256_12_LIM1_RIL_100	  FIELD_PREP_CONST(PEF2256_12_LIM1_RIL_MASK, 0x7)
+#define PEF2256_2X_LIM1_RIL_MASK  GENMASK(6, 4)
+#define PEF2256_2X_LIM1_RIL_2250  FIELD_PREP_CONST(PEF2256_2X_LIM1_RIL_MASK, 0x0)
+#define PEF2256_2X_LIM1_RIL_1100  FIELD_PREP_CONST(PEF2256_2X_LIM1_RIL_MASK, 0x1)
+#define PEF2256_2X_LIM1_RIL_600	  FIELD_PREP_CONST(PEF2256_2X_LIM1_RIL_MASK, 0x2)
+#define PEF2256_2X_LIM1_RIL_350	  FIELD_PREP_CONST(PEF2256_2X_LIM1_RIL_MASK, 0x3)
+#define PEF2256_2X_LIM1_RIL_210	  FIELD_PREP_CONST(PEF2256_2X_LIM1_RIL_MASK, 0x4)
+#define PEF2256_2X_LIM1_RIL_140	  FIELD_PREP_CONST(PEF2256_2X_LIM1_RIL_MASK, 0x5)
+#define PEF2256_2X_LIM1_RIL_100	  FIELD_PREP_CONST(PEF2256_2X_LIM1_RIL_MASK, 0x6)
+#define PEF2256_2X_LIM1_RIL_50	  FIELD_PREP_CONST(PEF2256_2X_LIM1_RIL_MASK, 0x7)
+
+/* Pulse Count Detection */
+#define PEF2256_PCD		0x38
+
+ /* Pulse Count Recovery */
+#define PEF2256_PCR		0x39
+
+ /* Line Interface Mode 2 */
+#define PEF2256_LIM2		0x3A
+#define PEF2256_LIM2_SLT_MASK	GENMASK(5, 4)
+#define PEF2256_LIM2_SLT_THR55	FIELD_PREP_CONST(PEF2256_LIM2_SLT_MASK, 0x0)
+#define PEF2256_LIM2_SLT_THR67	FIELD_PREP_CONST(PEF2256_LIM2_SLT_MASK, 0x1)
+#define PEF2256_LIM2_SLT_THR50	FIELD_PREP_CONST(PEF2256_LIM2_SLT_MASK, 0x2)
+#define PEF2256_LIM2_SLT_THR45	FIELD_PREP_CONST(PEF2256_LIM2_SLT_MASK, 0x3)
+#define PEF2256_LIM2_ELT	BIT(2)
+
+/* System Interface Control 1 */
+#define PEF2256_SIC1	          0x3E
+#define PEF2256_SIC1_SSC_MASK	  (BIT(7) |  BIT(3))
+#define PEF2256_SIC1_SSC_2048	  (0)
+#define PEF2256_SIC1_SSC_4096	  BIT(3)
+#define PEF2256_SIC1_SSC_8192	  BIT(7)
+#define PEF2256_SIC1_SSC_16384	  (BIT(7) |  BIT(3))
+/* SSD is defined on 2 bits. The other bit is on FMR1 register */
+#define PEF2256_SIC1_SSD_MASK	  GENMASK(6, 6)
+#define PEF2256_SIC1_SSD_2048	  FIELD_PREP_CONST(PEF2256_SIC1_SSD_MASK, 0x0)
+#define PEF2256_SIC1_SSD_4096	  FIELD_PREP_CONST(PEF2256_SIC1_SSD_MASK, 0x0)
+#define PEF2256_SIC1_SSD_8192	  FIELD_PREP_CONST(PEF2256_SIC1_SSD_MASK, 0x1)
+#define PEF2256_SIC1_SSD_16384	  FIELD_PREP_CONST(PEF2256_SIC1_SSD_MASK, 0x1)
+#define PEF2256_SIC1_RBS_MASK	  GENMASK(5, 4)
+#define PEF2256_SIC1_RBS_2FRAMES  FIELD_PREP_CONST(PEF2256_SIC1_RBS_MASK, 0x0)
+#define PEF2256_SIC1_RBS_1FRAME	  FIELD_PREP_CONST(PEF2256_SIC1_RBS_MASK, 0x1)
+#define PEF2256_SIC1_RBS_96BITS	  FIELD_PREP_CONST(PEF2256_SIC1_RBS_MASK, 0x2)
+#define PEF2256_SIC1_RBS_BYPASS	  FIELD_PREP_CONST(PEF2256_SIC1_RBS_MASK, 0x3)
+#define PEF2256_SIC1_XBS_MASK	  GENMASK(1, 0)
+#define PEF2256_SIC1_XBS_BYPASS	  FIELD_PREP_CONST(PEF2256_SIC1_XBS_MASK, 0x0)
+#define PEF2256_SIC1_XBS_1FRAME	  FIELD_PREP_CONST(PEF2256_SIC1_XBS_MASK, 0x1)
+#define PEF2256_SIC1_XBS_2FRAMES  FIELD_PREP_CONST(PEF2256_SIC1_XBS_MASK, 0x2)
+#define PEF2256_SIC1_XBS_96BITS	  FIELD_PREP_CONST(PEF2256_SIC1_XBS_MASK, 0x3)
+
+/* System Interface Control 2 */
+#define PEF2256_SIC2		0x3F
+#define PEF2256_SIC2_SICS_MASK	GENMASK(3, 1)
+#define PEF2256_SIC2_SICS(_v)	FIELD_PREP(PEF2256_SIC2_SICS_MASK, _v)
+
+/* System Interface Control 3 */
+#define PEF2256_SIC3		0x40
+#define PEF2256_SIC3_RTRI	BIT(5)
+#define PEF2256_SIC3_RESX	BIT(3)
+#define PEF2256_SIC3_RESR	BIT(2)
+
+/* Clock Mode Register 1 */
+#define PEF2256_CMR1			0x44
+#define PEF2256_CMR1_RS_MASK		GENMASK(5, 4)
+#define PEF2256_CMR1_RS_DPLL		FIELD_PREP_CONST(PEF2256_CMR1_RS_MASK, 0x0)
+#define PEF2256_CMR1_RS_DPLL_LOS_HIGH	FIELD_PREP_CONST(PEF2256_CMR1_RS_MASK, 0x1)
+#define PEF2256_CMR1_RS_DCOR_2048	FIELD_PREP_CONST(PEF2256_CMR1_RS_MASK, 0x2)
+#define PEF2256_CMR1_RS_DCOR_8192	FIELD_PREP_CONST(PEF2256_CMR1_RS_MASK, 0x3)
+#define PEF2256_CMR1_DCS		BIT(3)
+
+/* Clock Mode Register 2 */
+#define PEF2256_CMR2		0x45
+#define PEF2256_CMR2_DCOXC	BIT(5)
+
+/* Global Configuration Register */
+#define PEF2256_GCR		0x46
+#define PEF2256_GCR_SCI		BIT(6)
+#define PEF2256_GCR_ECMC	BIT(4)
+
+/* Port Configuration 5 */
+#define PEF2256_PC5		0x84
+#define PEF2256_PC5_CRP         BIT(0)
+
+/* Global Port Configuration 1 */
+#define PEF2256_GPC1			0x85
+#define PEF2256_GPC1_CSFP_MASK		GENMASK(7, 5)
+#define PEF2256_GPC1_CSFP_SEC_IN_HIGH	FIELD_PREP_CONST(PEF2256_GPC1_CSFP_MASK, 0x0)
+#define PEF2256_GPC1_CSFP_SEC_OUT_HIGH	FIELD_PREP_CONST(PEF2256_GPC1_CSFP_MASK, 0x1)
+#define PEF2256_GPC1_CSFP_FSC_OUT_HIGH	FIELD_PREP_CONST(PEF2256_GPC1_CSFP_MASK, 0x2)
+#define PEF2256_GPC1_CSFP_FSC_OUT_LOW	FIELD_PREP_CONST(PEF2256_GPC1_CSFP_MASK, 0x3)
+
+/* Port Configuration 6 */
+#define PEF2256_PC6		0x86
+
+/* Global Counter Mode n=1..8 */
+#define PEF2256_GCM(_n)         (0x92 + (_n) - 1)
+#define PEF2256_GCM1	        0x92
+#define PEF2256_GCM2	        0x93
+#define PEF2256_GCM3	        0x94
+#define PEF2256_GCM4	        0x95
+#define PEF2256_GCM5	        0x96
+#define PEF2256_GCM6	        0x97
+#define PEF2256_GCM7	        0x98
+#define PEF2256_GCM8	        0x99
+
+/* Version Status Register */
+#define PEF2256_VSTR		 0x4A
+#define PEF2256_VSTR_VERSION_12	 0x00
+#define PEF2256_VSTR_VERSION_21	 0x10
+#define PEF2256_VSTR_VERSION_2x	 0x05
+
+/* Framer Receive Status 0 */
+#define PEF2256_FRS0		0x4C
+#define PEF2256_FRS0_LOS	BIT(7)
+#define PEF2256_FRS0_AIS	BIT(6)
+
+/* Interrupt Status Register 0..5 */
+#define PEF2256_ISR(_n)		(0x68 + (_n))
+#define PEF2256_ISR0		0x68
+#define PEF2256_ISR1		0x69
+#define PEF2256_ISR2		0x6A
+#define PEF2256_ISR3		0x6B
+#define PEF2256_ISR4		0x6C
+#define PEF2256_ISR5		0x6D
+
+/* Global Interrupt Status */
+#define PEF2256_GIS		0x6E
+#define PEF2256_GIS_ISR(_n)	BIT(_n)
+
+/* Wafer Identification Register */
+#define PEF2256_WID		   0xEC
+#define PEF2256_12_WID_MASK	   GENMASK(1, 0)
+#define PEF2256_12_WID_VERSION_12  FIELD_PREP_CONST(PEF2256_12_WID_MASK, 0x3)
+#define PEF2256_2X_WID_MASK	   GENMASK(7, 6)
+#define PEF2256_2X_WID_VERSION_21  FIELD_PREP_CONST(PEF2256_2X_WID_MASK, 0x0)
+#define PEF2256_2X_WID_VERSION_22  FIELD_PREP_CONST(PEF2256_2X_WID_MASK, 0x1)
+
+/* IMR2/ISR2 Interrupts common bits */
+#define PEF2256_INT2_AIS	BIT(3)
+#define PEF2256_INT2_LOS	BIT(2)
+
+#endif /* __PEF2256_REGS_H__ */
diff --git a/drivers/net/wan/framer/pef2256/pef2256.c b/drivers/net/wan/framer/pef2256/pef2256.c
new file mode 100644
index 000000000000..4f81053ee4f0
--- /dev/null
+++ b/drivers/net/wan/framer/pef2256/pef2256.c
@@ -0,0 +1,880 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * PEF2256 also known as FALC56 driver
+ *
+ * Copyright 2023 CS GROUP France
+ *
+ * Author: Herve Codina <herve.codina@bootlin.com>
+ */
+
+#include <linux/framer/pef2256.h>
+#include <linux/clk.h>
+#include <linux/framer/framer-provider.h>
+#include <linux/gpio/consumer.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/mfd/core.h>
+#include <linux/module.h>
+#include <linux/notifier.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+#include "pef2256-regs.h"
+
+enum pef2256_frame_type {
+	PEF2256_FRAME_E1_DOUBLEFRAME,
+	PEF2256_FRAME_E1_CRC4_MULTIFRAME,
+	PEF2256_FRAME_E1_AUTO_MULTIFRAME,
+	PEF2256_FRAME_T1J1_4FRAME,
+	PEF2256_FRAME_T1J1_12FRAME,
+	PEF2256_FRAME_T1J1_24FRAME,
+	PEF2256_FRAME_T1J1_72FRAME,
+};
+
+struct pef2256 {
+	struct device *dev;
+	struct regmap *regmap;
+	enum pef2256_version version;
+	struct clk *mclk;
+	struct clk *sclkr;
+	struct clk *sclkx;
+	struct gpio_desc *reset_gpio;
+	unsigned long sysclk_rate;
+	u32 data_rate;
+	bool is_tx_falling_edge;
+	bool is_subordinate;
+	enum pef2256_frame_type frame_type;
+	u8 channel_phase;
+	atomic_t carrier;
+	struct framer *framer;
+};
+
+static u8 pef2256_read8(struct pef2256 *pef2256, int offset)
+{
+	int val;
+
+	regmap_read(pef2256->regmap, offset, &val);
+	return val;
+}
+
+static void pef2256_write8(struct pef2256 *pef2256, int offset, u8 val)
+{
+	regmap_write(pef2256->regmap, offset, val);
+}
+
+static void pef2256_clrbits8(struct pef2256 *pef2256, int offset, u8 clr)
+{
+	regmap_clear_bits(pef2256->regmap, offset, clr);
+}
+
+static void pef2256_setbits8(struct pef2256 *pef2256, int offset, u8 set)
+{
+	regmap_set_bits(pef2256->regmap, offset, set);
+}
+
+static void pef2256_clrsetbits8(struct pef2256 *pef2256, int offset, u8 clr, u8 set)
+{
+	regmap_update_bits(pef2256->regmap, offset, clr | set, set);
+}
+
+enum pef2256_version pef2256_get_version(struct pef2256 *pef2256)
+{
+	enum pef2256_version version = PEF2256_VERSION_UNKNOWN;
+	u8 vstr, wid;
+
+	vstr = pef2256_read8(pef2256, PEF2256_VSTR);
+	wid = pef2256_read8(pef2256, PEF2256_WID);
+
+	switch (vstr) {
+	case PEF2256_VSTR_VERSION_12:
+		if ((wid & PEF2256_12_WID_MASK) == PEF2256_12_WID_VERSION_12)
+			version = PEF2256_VERSION_1_2;
+		break;
+	case PEF2256_VSTR_VERSION_2x:
+		switch (wid & PEF2256_2X_WID_MASK) {
+		case PEF2256_2X_WID_VERSION_21:
+			version = PEF2256_VERSION_2_1;
+			break;
+		case PEF2256_2X_WID_VERSION_22:
+			version = PEF2256_VERSION_2_2;
+			break;
+		}
+		break;
+	case PEF2256_VSTR_VERSION_21:
+		version = PEF2256_VERSION_2_1;
+		break;
+	}
+
+	if (version == PEF2256_VERSION_UNKNOWN)
+		dev_err(pef2256->dev, "Unknown version (0x%02x, 0x%02x)\n", vstr, wid);
+
+	return version;
+}
+EXPORT_SYMBOL_GPL(pef2256_get_version);
+
+enum pef2256_gcm_config_item {
+	PEF2256_GCM_CONFIG_1544000 = 0,
+	PEF2256_GCM_CONFIG_2048000,
+	PEF2256_GCM_CONFIG_8192000,
+	PEF2256_GCM_CONFIG_10000000,
+	PEF2256_GCM_CONFIG_12352000,
+	PEF2256_GCM_CONFIG_16384000,
+};
+
+struct pef2256_gcm_config {
+	u8 gcm_12[6];
+	u8 gcm_2x[8];
+};
+
+static const struct pef2256_gcm_config pef2256_gcm_configs[] = {
+	[PEF2256_GCM_CONFIG_1544000] = {
+		.gcm_12 = {0xF0, 0x51, 0x00, 0x80, 0x00, 0x15},
+		.gcm_2x = {0x00, 0x15, 0x00, 0x08, 0x00, 0x3F, 0x9C, 0xDF},
+	},
+	[PEF2256_GCM_CONFIG_2048000] = {
+		.gcm_12 = {0x00, 0x58, 0xD2, 0xC2, 0x00, 0x10},
+		.gcm_2x = {0x00, 0x18, 0xFB, 0x0B, 0x00, 0x2F, 0xDB, 0xDF},
+	},
+	[PEF2256_GCM_CONFIG_8192000] = {
+		.gcm_12 = {0x00, 0x58, 0xD2, 0xC2, 0x03, 0x10},
+		.gcm_2x = {0x00, 0x18, 0xFB, 0x0B, 0x00, 0x0B, 0xDB, 0xDF},
+	},
+	[PEF2256_GCM_CONFIG_10000000] = {
+		.gcm_12 = {0x90, 0x51, 0x81, 0x8F, 0x04, 0x10},
+		.gcm_2x = {0x40, 0x1B, 0x3D, 0x0A, 0x00, 0x07, 0xC9, 0xDC},
+	},
+	[PEF2256_GCM_CONFIG_12352000] = {
+		.gcm_12 = {0xF0, 0x51, 0x00, 0x80, 0x07, 0x15},
+		.gcm_2x = {0x00, 0x19, 0x00, 0x08, 0x01, 0x0A, 0x98, 0xDA},
+	},
+	[PEF2256_GCM_CONFIG_16384000] = {
+		.gcm_12 = {0x00, 0x58, 0xD2, 0xC2, 0x07, 0x10},
+		.gcm_2x = {0x00, 0x18, 0xFB, 0x0B, 0x01, 0x0B, 0xDB, 0xDF},
+	},
+};
+
+static int pef2256_setup_gcm(struct pef2256 *pef2256)
+{
+	enum pef2256_gcm_config_item item;
+	unsigned long mclk_rate;
+	const u8 *gcm;
+	int i, count;
+
+	mclk_rate = clk_get_rate(pef2256->mclk);
+	switch (mclk_rate) {
+	case 1544000:
+		item = PEF2256_GCM_CONFIG_1544000;
+		break;
+	case 2048000:
+		item = PEF2256_GCM_CONFIG_2048000;
+		break;
+	case 8192000:
+		item = PEF2256_GCM_CONFIG_8192000;
+		break;
+	case 10000000:
+		item = PEF2256_GCM_CONFIG_10000000;
+		break;
+	case 12352000:
+		item = PEF2256_GCM_CONFIG_12352000;
+		break;
+	case 16384000:
+		item = PEF2256_GCM_CONFIG_16384000;
+		break;
+	default:
+		dev_err(pef2256->dev, "Unsupported v2.x MCLK rate %lu\n", mclk_rate);
+		return -EINVAL;
+	}
+
+	BUILD_BUG_ON(item >= ARRAY_SIZE(pef2256_gcm_configs));
+
+	if (pef2256->version == PEF2256_VERSION_1_2) {
+		gcm = pef2256_gcm_configs[item].gcm_12;
+		count = ARRAY_SIZE(pef2256_gcm_configs[item].gcm_12);
+	} else {
+		gcm = pef2256_gcm_configs[item].gcm_2x;
+		count = ARRAY_SIZE(pef2256_gcm_configs[item].gcm_2x);
+	}
+
+	for (i = 0; i < count; i++)
+		pef2256_write8(pef2256, PEF2256_GCM(i + 1), *(gcm + i));
+
+	return 0;
+}
+
+static int pef2256_setup_e1_line(struct pef2256 *pef2256)
+{
+	u8 fmr1, fmr2;
+
+	/* RCLK output : DPLL clock, DCO-X enabled, DCO-X internal ref clock */
+	pef2256_write8(pef2256, PEF2256_CMR1, 0x00);
+
+	/* SCLKR selected, SCLKX selected,
+	 * receive synchro pulse sourced by SYPR,
+	 * transmit synchro pulse sourced by SYPX,
+	 * DCO-X center frequency enabled
+	 */
+	pef2256_write8(pef2256, PEF2256_CMR2, PEF2256_CMR2_DCOXC);
+
+	if (pef2256->is_subordinate) {
+		/* select RCLK source = 2M,  disable switching from RCLK to SYNC */
+		pef2256_clrsetbits8(pef2256, PEF2256_CMR1, PEF2256_CMR1_RS_MASK,
+				    PEF2256_CMR1_RS_DCOR_2048 | PEF2256_CMR1_DCS);
+	}
+
+	/* slave mode, local loop off, mode short-haul
+	 * In v2.x, bit3 is a forced 1 bit in the datasheet -> Need to be set.
+	 */
+	if (pef2256->version == PEF2256_VERSION_1_2)
+		pef2256_write8(pef2256, PEF2256_LIM0, 0x00);
+	else
+		pef2256_write8(pef2256, PEF2256_LIM0, PEF2256_2X_LIM0_BIT3);
+
+	/* "master" mode */
+	if (!pef2256->is_subordinate)
+		pef2256_setbits8(pef2256, PEF2256_LIM0, PEF2256_LIM0_MAS);
+
+	/* analog interface selected, remote loop off */
+	pef2256_write8(pef2256, PEF2256_LIM1, 0x00);
+
+	/* receive input threshold = 0,21V */
+	if (pef2256->version == PEF2256_VERSION_1_2)
+		pef2256_clrsetbits8(pef2256, PEF2256_LIM1, PEF2256_12_LIM1_RIL_MASK,
+				    PEF2256_12_LIM1_RIL_210);
+	else
+		pef2256_clrsetbits8(pef2256, PEF2256_LIM1, PEF2256_2X_LIM1_RIL_MASK,
+				    PEF2256_2X_LIM1_RIL_210);
+
+	/* transmit pulse mask, default value from datasheet
+	 * transmit line in normal operation
+	 */
+	if (pef2256->version == PEF2256_VERSION_1_2)
+		pef2256_write8(pef2256, PEF2256_XPM0, 0x7B);
+	else
+		pef2256_write8(pef2256, PEF2256_XPM0, 0x9C);
+	pef2256_write8(pef2256, PEF2256_XPM1, 0x03);
+	pef2256_write8(pef2256, PEF2256_XPM2, 0x00);
+
+	/* HDB3 coding, no alarm simulation */
+	pef2256_write8(pef2256, PEF2256_FMR0, PEF2256_FMR0_XC_HDB3 | PEF2256_FMR0_RC_HDB3);
+
+	/* E1, frame format, 2 Mbit/s system data rate, no AIS
+	 * transmission to remote end or system interface, payload loop
+	 * off, transmit remote alarm on
+	 */
+	fmr1 = 0x00;
+	fmr2 = PEF2256_FMR2_AXRA;
+	switch (pef2256->frame_type) {
+	case PEF2256_FRAME_E1_DOUBLEFRAME:
+		fmr2 |= PEF2256_FMR2_RFS_DOUBLEFRAME;
+		break;
+	case PEF2256_FRAME_E1_CRC4_MULTIFRAME:
+		fmr1 |= PEF2256_FMR1_XFS;
+		fmr2 |= PEF2256_FMR2_RFS_CRC4_MULTIFRAME;
+		break;
+	case PEF2256_FRAME_E1_AUTO_MULTIFRAME:
+		fmr1 |= PEF2256_FMR1_XFS;
+		fmr2 |= PEF2256_FMR2_RFS_AUTO_MULTIFRAME;
+		break;
+	default:
+		dev_err(pef2256->dev, "Unsupported frame type %d\n", pef2256->frame_type);
+		return -EINVAL;
+	}
+	pef2256_clrsetbits8(pef2256, PEF2256_FMR1, PEF2256_FMR1_XFS, fmr1);
+	pef2256_write8(pef2256, PEF2256_FMR2, fmr2);
+
+	if (!pef2256->is_subordinate) {
+		/* SEC input, active high */
+		pef2256_write8(pef2256, PEF2256_GPC1, PEF2256_GPC1_CSFP_SEC_IN_HIGH);
+	} else {
+		/* FSC output, active high */
+		pef2256_write8(pef2256, PEF2256_GPC1, PEF2256_GPC1_CSFP_FSC_OUT_HIGH);
+	}
+
+	/* SCLKR, SCLKX, RCLK configured to inputs,
+	 * XFMS active low, CLK1 and CLK2 pin configuration
+	 */
+	pef2256_write8(pef2256, PEF2256_PC5, 0x00);
+	pef2256_write8(pef2256, PEF2256_PC6, 0x00);
+
+	/* port RCLK is output */
+	pef2256_setbits8(pef2256, PEF2256_PC5, PEF2256_PC5_CRP);
+
+	return 0;
+}
+
+static void pef2256_setup_e1_los(struct pef2256 *pef2256)
+{
+	/* detection of LOS alarm = 176 pulses (ie (10 + 1) * 16) */
+	pef2256_write8(pef2256, PEF2256_PCD, 10);
+	/* recovery of LOS alarm = 22 pulses (ie 21 + 1) */
+	pef2256_write8(pef2256, PEF2256_PCR, 21);
+	/* E1 default for the receive slicer threshold */
+	pef2256_write8(pef2256, PEF2256_LIM2, PEF2256_LIM2_SLT_THR50);
+	if (pef2256->is_subordinate) {
+		/* Loop-timed */
+		pef2256_setbits8(pef2256, PEF2256_LIM2, PEF2256_LIM2_ELT);
+	}
+}
+
+static int pef2256_setup_e1_system(struct pef2256 *pef2256)
+{
+	u8 sic1, fmr1;
+
+	/* 2.048 MHz system clocking rate, receive buffer 2 frames, transmit
+	 * buffer bypass, data sampled and transmitted on the falling edge of
+	 * SCLKR/X, automatic freeze signaling, data is active in the first
+	 * channel phase
+	 */
+	pef2256_write8(pef2256, PEF2256_SIC1, 0x00);
+	pef2256_write8(pef2256, PEF2256_SIC2, 0x00);
+	pef2256_write8(pef2256, PEF2256_SIC3, 0x00);
+
+	if (pef2256->is_subordinate) {
+		/* transmit buffer size = 2 frames, transparent mode */
+		pef2256_clrsetbits8(pef2256, PEF2256_SIC1, PEF2256_SIC1_XBS_MASK,
+				    PEF2256_SIC1_XBS_2FRAMES);
+	}
+
+	if (pef2256->version != PEF2256_VERSION_1_2) {
+		/* during inactive channel phase switch RDO/RSIG into tri-state */
+		pef2256_setbits8(pef2256, PEF2256_SIC3, PEF2256_SIC3_RTRI);
+	}
+
+	if (pef2256->is_tx_falling_edge) {
+		/* falling edge sync pulse transmit, rising edge sync pulse receive */
+		pef2256_clrsetbits8(pef2256, PEF2256_SIC3, PEF2256_SIC3_RESX, PEF2256_SIC3_RESR);
+	} else {
+		/* rising edge sync pulse transmit, falling edge sync pulse receive */
+		pef2256_clrsetbits8(pef2256, PEF2256_SIC3, PEF2256_SIC3_RESR, PEF2256_SIC3_RESX);
+	}
+
+	/* transmit offset counter (XCO10..0) = 4 */
+	pef2256_write8(pef2256, PEF2256_XC0, 0);
+	pef2256_write8(pef2256, PEF2256_XC1, 4);
+	/* receive offset counter (RCO10..0) = 4 */
+	pef2256_write8(pef2256, PEF2256_RC0, 0);
+	pef2256_write8(pef2256, PEF2256_RC1, 4);
+
+	/* system clock rate */
+	switch (pef2256->sysclk_rate) {
+	case 2048000:
+		sic1 = PEF2256_SIC1_SSC_2048;
+		break;
+	case 4096000:
+		sic1 = PEF2256_SIC1_SSC_4096;
+		break;
+	case 8192000:
+		sic1 = PEF2256_SIC1_SSC_8192;
+		break;
+	case 16384000:
+		sic1 = PEF2256_SIC1_SSC_16384;
+		break;
+	default:
+		dev_err(pef2256->dev, "Unsupported sysclk rate %lu\n", pef2256->sysclk_rate);
+		return -EINVAL;
+	}
+	pef2256_clrsetbits8(pef2256, PEF2256_SIC1, PEF2256_SIC1_SSC_MASK, sic1);
+
+	/* data clock rate */
+	switch (pef2256->data_rate) {
+	case 2048000:
+		fmr1 = PEF2256_FMR1_SSD_2048;
+		sic1 = PEF2256_SIC1_SSD_2048;
+		break;
+	case 4096000:
+		fmr1 = PEF2256_FMR1_SSD_4096;
+		sic1 = PEF2256_SIC1_SSD_4096;
+		break;
+	case 8192000:
+		fmr1 = PEF2256_FMR1_SSD_8192;
+		sic1 = PEF2256_SIC1_SSD_8192;
+		break;
+	case 16384000:
+		fmr1 = PEF2256_FMR1_SSD_16384;
+		sic1 = PEF2256_SIC1_SSD_16384;
+		break;
+	default:
+		dev_err(pef2256->dev, "Unsupported data rate %u\n", pef2256->data_rate);
+		return -EINVAL;
+	}
+	pef2256_clrsetbits8(pef2256, PEF2256_FMR1, PEF2256_FMR1_SSD_MASK, fmr1);
+	pef2256_clrsetbits8(pef2256, PEF2256_SIC1, PEF2256_SIC1_SSD_MASK, sic1);
+
+	/* channel phase */
+	pef2256_clrsetbits8(pef2256, PEF2256_SIC2, PEF2256_SIC2_SICS_MASK,
+			    PEF2256_SIC2_SICS(pef2256->channel_phase));
+
+	return 0;
+}
+
+static void pef2256_setup_e1_signaling(struct pef2256 *pef2256)
+{
+	/* All bits of the transmitted service word are cleared */
+	pef2256_write8(pef2256, PEF2256_XSW, PEF2256_XSW_XY(0x1F));
+
+	/* CAS disabled and clear spare bit values */
+	pef2256_write8(pef2256, PEF2256_XSP, 0x00);
+
+	if (pef2256->is_subordinate) {
+		/* transparent mode */
+		pef2256_setbits8(pef2256, PEF2256_XSW, PEF2256_XSW_XTM);
+	}
+
+	/* Si-Bit, Spare bit For International, FAS word */
+	pef2256_setbits8(pef2256, PEF2256_XSW, PEF2256_XSW_XSIS);
+	pef2256_setbits8(pef2256, PEF2256_XSP, PEF2256_XSP_XSIF);
+
+	/* no transparent mode active */
+	pef2256_write8(pef2256, PEF2256_TSWM, 0x00);
+}
+
+static void pef2256_setup_e1_errors(struct pef2256 *pef2256)
+{
+	/* error counter latched every 1s */
+	pef2256_setbits8(pef2256, PEF2256_FMR1, PEF2256_FMR1_ECM);
+
+	/* error counter mode COFA */
+	pef2256_setbits8(pef2256, PEF2256_GCR, PEF2256_GCR_ECMC);
+
+	/* errors in service words have no influence */
+	pef2256_setbits8(pef2256, PEF2256_RC0, PEF2256_RC0_SWD);
+
+	/* 4 consecutive incorrect FAS causes loss of sync */
+	pef2256_setbits8(pef2256, PEF2256_RC0, PEF2256_RC0_ASY4);
+}
+
+static int pef2256_setup_e1(struct pef2256 *pef2256)
+{
+	int ret;
+
+	/* Setup, Master clocking mode (GCM8..1) */
+	ret = pef2256_setup_gcm(pef2256);
+	if (ret)
+		return ret;
+
+	/* Select E1 mode */
+	pef2256_write8(pef2256, PEF2256_FMR1, 0x00);
+
+	/* internal second timer, power on */
+	pef2256_write8(pef2256, PEF2256_GCR, 0x00);
+
+	/* Setup line interface */
+	ret = pef2256_setup_e1_line(pef2256);
+	if (ret)
+		return ret;
+
+	/* Setup Loss-of-signal detection and recovery */
+	pef2256_setup_e1_los(pef2256);
+
+	/* Setup system interface */
+	ret = pef2256_setup_e1_system(pef2256);
+	if (ret)
+		return ret;
+
+	/* Setup signaling */
+	pef2256_setup_e1_signaling(pef2256);
+
+	/* Setup errors counters and condition */
+	pef2256_setup_e1_errors(pef2256);
+
+	/* status changed interrupt at both up and down */
+	pef2256_setbits8(pef2256, PEF2256_GCR, PEF2256_GCR_SCI);
+
+	/* Clear any ISR2 pending interrupts and unmask needed interrupts */
+	pef2256_read8(pef2256, PEF2256_ISR2);
+	pef2256_clrbits8(pef2256, PEF2256_IMR2, PEF2256_INT2_LOS | PEF2256_INT2_AIS);
+
+	/* reset lines */
+	pef2256_write8(pef2256, PEF2256_CMDR, PEF2256_CMDR_RRES | PEF2256_CMDR_XRES);
+	return 0;
+}
+
+static void pef2256_isr_default_handler(struct pef2256 *pef2256, u8 nbr, u8 isr)
+{
+	dev_warn_ratelimited(pef2256->dev, "ISR%u: 0x%02x not handled\n", nbr, isr);
+}
+
+static bool pef2256_is_carrier_on(struct pef2256 *pef2256)
+{
+	u8 frs0;
+
+	frs0 = pef2256_read8(pef2256, PEF2256_FRS0);
+	return !(frs0 & (PEF2256_FRS0_LOS | PEF2256_FRS0_AIS));
+}
+
+static void pef2256_isr2_handler(struct pef2256 *pef2256, u8 nbr, u8 isr)
+{
+	bool carrier;
+
+	if (isr & (PEF2256_INT2_LOS | PEF2256_INT2_AIS)) {
+		carrier = pef2256_is_carrier_on(pef2256);
+		if (atomic_xchg(&pef2256->carrier, carrier) != carrier)
+			framer_notify_status_change(pef2256->framer);
+	}
+}
+
+static irqreturn_t pef2256_irq_handler(int irq, void *priv)
+{
+	static void (*pef2256_isr_handler[])(struct pef2256 *, u8, u8) = {
+		[0] = pef2256_isr_default_handler,
+		[1] = pef2256_isr_default_handler,
+		[2] = pef2256_isr2_handler,
+		[3] = pef2256_isr_default_handler,
+		[4] = pef2256_isr_default_handler,
+		[5] = pef2256_isr_default_handler
+	};
+	struct pef2256 *pef2256 = (struct pef2256 *)priv;
+	u8 gis;
+	u8 isr;
+	u8 n;
+
+	gis = pef2256_read8(pef2256, PEF2256_GIS);
+
+	for (n = 0; n < ARRAY_SIZE(pef2256_isr_handler); n++) {
+		if (gis & PEF2256_GIS_ISR(n)) {
+			isr = pef2256_read8(pef2256, PEF2256_ISR(n));
+			pef2256_isr_handler[n](pef2256, n, isr);
+		}
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int pef2256_check_rates(struct pef2256 *pef2256, unsigned long sysclk_rate,
+			       unsigned long data_rate)
+{
+	unsigned long rate;
+
+	switch (sysclk_rate) {
+	case 2048000:
+	case 4096000:
+	case 8192000:
+	case 16384000:
+		break;
+	default:
+		dev_err(pef2256->dev, "Unsupported system clock rate %lu\n", sysclk_rate);
+		return -EINVAL;
+	}
+
+	for (rate = data_rate; rate <= data_rate * 4; rate *= 2) {
+		if (rate == sysclk_rate)
+			return 0;
+	}
+	dev_err(pef2256->dev, "Unsupported data rate %lu with system clock rate %lu\n",
+		data_rate, sysclk_rate);
+	return -EINVAL;
+}
+
+static int pef2556_of_parse(struct pef2256 *pef2256, struct device_node *np)
+{
+	int ret;
+
+	pef2256->data_rate = 2048000;
+	ret = of_property_read_u32(np, "lantiq,data-rate-bps", &pef2256->data_rate);
+	if (ret && ret != -EINVAL) {
+		dev_err(pef2256->dev, "%pOF: failed to read lantiq,data-rate-bps\n", np);
+		return ret;
+	}
+
+	ret =  pef2256_check_rates(pef2256, pef2256->sysclk_rate, pef2256->data_rate);
+	if (ret)
+		return ret;
+
+	pef2256->is_tx_falling_edge = of_property_read_bool(np, "lantiq,clock-falling-edge");
+
+	pef2256->channel_phase = 0;
+	ret = of_property_read_u8(np, "lantiq,channel-phase", &pef2256->channel_phase);
+	if (ret && ret != -EINVAL) {
+		dev_err(pef2256->dev, "%pOF: failed to read lantiq,channel-phase\n",
+			np);
+		return ret;
+	}
+	if (pef2256->channel_phase >= pef2256->sysclk_rate / pef2256->data_rate) {
+		dev_err(pef2256->dev, "%pOF: Invalid lantiq,channel-phase %u\n",
+			np, pef2256->channel_phase);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static const struct regmap_config pef2256_regmap_config = {
+	.reg_bits = 32,
+	.val_bits = 8,
+	.max_register = 0xff,
+};
+
+static const struct mfd_cell pef2256_devs[] = {
+	{ .name = "lantiq-pef2256-pinctrl", },
+};
+
+static int pef2256_add_audio_devices(struct pef2256 *pef2256)
+{
+	const char *compatible = "lantiq,pef2256-codec";
+	struct mfd_cell *audio_devs;
+	struct device_node *np;
+	unsigned int count = 0;
+	unsigned int i;
+	int ret;
+
+	for_each_available_child_of_node(pef2256->dev->of_node, np) {
+		if (of_device_is_compatible(np, compatible))
+			count++;
+	}
+
+	if (!count)
+		return 0;
+
+	audio_devs = kcalloc(count, sizeof(*audio_devs), GFP_KERNEL);
+	if (!audio_devs)
+		return -ENOMEM;
+
+	for (i = 0; i < count; i++) {
+		audio_devs[i].name = "framer-codec";
+		audio_devs[i].of_compatible = compatible;
+		audio_devs[i].id = i;
+	}
+
+	ret = mfd_add_devices(pef2256->dev, 0, audio_devs, count, NULL, 0, NULL);
+	kfree(audio_devs);
+	return ret;
+}
+
+static int pef2256_framer_get_status(struct framer *framer, struct framer_status *status)
+{
+	struct pef2256 *pef2256 = framer_get_drvdata(framer);
+
+	status->link_is_on = !!atomic_read(&pef2256->carrier);
+	return 0;
+}
+
+static int pef2256_framer_set_config(struct framer *framer, const struct framer_config *config)
+{
+	struct pef2256 *pef2256 = framer_get_drvdata(framer);
+
+	if (config->iface != FRAMER_IFACE_E1) {
+		dev_err(pef2256->dev, "Only E1 line is currently supported\n");
+		return -EOPNOTSUPP;
+	}
+
+	switch (config->clock_type) {
+	case FRAMER_CLOCK_EXT:
+		pef2256->is_subordinate = true;
+		break;
+	case FRAMER_CLOCK_INT:
+		pef2256->is_subordinate = false;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Apply the new settings */
+	return pef2256_setup_e1(pef2256);
+}
+
+static int pef2256_framer_get_config(struct framer *framer, struct framer_config *config)
+{
+	struct pef2256 *pef2256 = framer_get_drvdata(framer);
+
+	config->iface = FRAMER_IFACE_E1;
+	config->clock_type = pef2256->is_subordinate ? FRAMER_CLOCK_EXT : FRAMER_CLOCK_INT;
+	config->line_clock_rate = 2048000;
+	return 0;
+}
+
+static const struct framer_ops pef2256_framer_ops = {
+	.owner = THIS_MODULE,
+	.get_status = pef2256_framer_get_status,
+	.get_config = pef2256_framer_get_config,
+	.set_config = pef2256_framer_set_config,
+};
+
+static int pef2256_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	unsigned long sclkr_rate, sclkx_rate;
+	struct framer_provider *framer_provider;
+	struct pef2256 *pef2256;
+	const char *version_txt;
+	void __iomem *iomem;
+	int ret;
+	int irq;
+
+	pef2256 = devm_kzalloc(&pdev->dev, sizeof(*pef2256), GFP_KERNEL);
+	if (!pef2256)
+		return -ENOMEM;
+
+	pef2256->dev = &pdev->dev;
+	atomic_set(&pef2256->carrier, 0);
+
+	pef2256->is_subordinate = true;
+	pef2256->frame_type = PEF2256_FRAME_E1_DOUBLEFRAME;
+
+	iomem = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(iomem))
+		return PTR_ERR(iomem);
+
+	pef2256->regmap = devm_regmap_init_mmio(&pdev->dev, iomem,
+						&pef2256_regmap_config);
+	if (IS_ERR(pef2256->regmap)) {
+		dev_err(&pdev->dev, "Failed to initialise Regmap (%ld)\n",
+			PTR_ERR(pef2256->regmap));
+		return PTR_ERR(pef2256->regmap);
+	}
+
+	pef2256->mclk = devm_clk_get_enabled(&pdev->dev, "mclk");
+	if (IS_ERR(pef2256->mclk))
+		return PTR_ERR(pef2256->mclk);
+
+	pef2256->sclkr = devm_clk_get_enabled(&pdev->dev, "sclkr");
+	if (IS_ERR(pef2256->sclkr))
+		return PTR_ERR(pef2256->sclkr);
+
+	pef2256->sclkx = devm_clk_get_enabled(&pdev->dev, "sclkx");
+	if (IS_ERR(pef2256->sclkx))
+		return PTR_ERR(pef2256->sclkx);
+
+	/* Both SCLKR (receive) and SCLKX (transmit) must have the same rate,
+	 * stored as sysclk_rate.
+	 * The exact value will be checked at pef2256_check_rates()
+	 */
+	sclkr_rate = clk_get_rate(pef2256->sclkr);
+	sclkx_rate = clk_get_rate(pef2256->sclkx);
+	if (sclkr_rate != sclkx_rate) {
+		dev_err(pef2256->dev, "clk rate mismatch. sclkr %lu Hz, sclkx %lu Hz\n",
+			sclkr_rate, sclkx_rate);
+		return -EINVAL;
+	}
+	pef2256->sysclk_rate = sclkr_rate;
+
+	/* Reset the component. The MCLK clock must be active during reset */
+	pef2256->reset_gpio = devm_gpiod_get_optional(&pdev->dev, "reset", GPIOD_OUT_LOW);
+	if (IS_ERR(pef2256->reset_gpio))
+		return PTR_ERR(pef2256->reset_gpio);
+	if (pef2256->reset_gpio) {
+		gpiod_set_value_cansleep(pef2256->reset_gpio, 1);
+		usleep_range(10, 20);
+		gpiod_set_value_cansleep(pef2256->reset_gpio, 0);
+		usleep_range(10, 20);
+	}
+
+	pef2256->version = pef2256_get_version(pef2256);
+	switch (pef2256->version) {
+	case PEF2256_VERSION_1_2:
+		version_txt = "1.2";
+		break;
+	case PEF2256_VERSION_2_1:
+		version_txt = "2.1";
+		break;
+	case PEF2256_VERSION_2_2:
+		version_txt = "2.2";
+		break;
+	default:
+		return -ENODEV;
+	}
+	dev_info(pef2256->dev, "Version %s detected\n", version_txt);
+
+	ret = pef2556_of_parse(pef2256, np);
+	if (ret)
+		return ret;
+
+	/* Create the framer. It can be used on interrupts */
+	pef2256->framer = devm_framer_create(pef2256->dev, NULL, &pef2256_framer_ops);
+	if (IS_ERR(pef2256->framer))
+		return PTR_ERR(pef2256->framer);
+
+	framer_set_drvdata(pef2256->framer, pef2256);
+
+	/* Disable interrupts */
+	pef2256_write8(pef2256, PEF2256_IMR0, 0xff);
+	pef2256_write8(pef2256, PEF2256_IMR1, 0xff);
+	pef2256_write8(pef2256, PEF2256_IMR2, 0xff);
+	pef2256_write8(pef2256, PEF2256_IMR3, 0xff);
+	pef2256_write8(pef2256, PEF2256_IMR4, 0xff);
+	pef2256_write8(pef2256, PEF2256_IMR5, 0xff);
+
+	/* Clear any pending interrupts */
+	pef2256_read8(pef2256, PEF2256_ISR0);
+	pef2256_read8(pef2256, PEF2256_ISR1);
+	pef2256_read8(pef2256, PEF2256_ISR2);
+	pef2256_read8(pef2256, PEF2256_ISR3);
+	pef2256_read8(pef2256, PEF2256_ISR4);
+	pef2256_read8(pef2256, PEF2256_ISR5);
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+	ret = devm_request_irq(pef2256->dev, irq, pef2256_irq_handler, 0, "pef2256", pef2256);
+	if (ret < 0)
+		return ret;
+
+	platform_set_drvdata(pdev, pef2256);
+
+	ret = mfd_add_devices(pef2256->dev, 0, pef2256_devs,
+			      ARRAY_SIZE(pef2256_devs), NULL, 0, NULL);
+	if (ret) {
+		dev_err(pef2256->dev, "add devices failed (%d)\n", ret);
+		return ret;
+	}
+
+	ret = pef2256_setup_e1(pef2256);
+	if (ret)
+		return ret;
+
+	framer_provider = devm_framer_provider_of_register(pef2256->dev,
+							   framer_provider_simple_of_xlate);
+	if (IS_ERR(framer_provider))
+		return PTR_ERR(framer_provider);
+
+	/* Add audio devices */
+	ret = pef2256_add_audio_devices(pef2256);
+	if (ret < 0) {
+		dev_err(pef2256->dev, "add audio devices failed (%d)\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int pef2256_remove(struct platform_device *pdev)
+{
+	struct pef2256 *pef2256 = platform_get_drvdata(pdev);
+
+	/* Disable interrupts */
+	pef2256_write8(pef2256, PEF2256_IMR0, 0xff);
+	pef2256_write8(pef2256, PEF2256_IMR1, 0xff);
+	pef2256_write8(pef2256, PEF2256_IMR2, 0xff);
+	pef2256_write8(pef2256, PEF2256_IMR3, 0xff);
+	pef2256_write8(pef2256, PEF2256_IMR4, 0xff);
+	pef2256_write8(pef2256, PEF2256_IMR5, 0xff);
+
+	return 0;
+}
+
+static const struct of_device_id pef2256_id_table[] = {
+	{ .compatible = "lantiq,pef2256" },
+	{} /* sentinel */
+};
+MODULE_DEVICE_TABLE(of, pef2256_id_table);
+
+static struct platform_driver pef2256_driver = {
+	.driver = {
+		.name = "lantiq-pef2256",
+		.of_match_table = pef2256_id_table,
+	},
+	.probe = pef2256_probe,
+	.remove = pef2256_remove,
+};
+module_platform_driver(pef2256_driver);
+
+struct regmap *pef2256_get_regmap(struct pef2256 *pef2256)
+{
+	return pef2256->regmap;
+}
+EXPORT_SYMBOL_GPL(pef2256_get_regmap);
+
+MODULE_AUTHOR("Herve Codina <herve.codina@bootlin.com>");
+MODULE_DESCRIPTION("PEF2256 driver");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/framer/pef2256.h b/include/linux/framer/pef2256.h
new file mode 100644
index 000000000000..71d80af58c40
--- /dev/null
+++ b/include/linux/framer/pef2256.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * PEF2256 consumer API
+ *
+ * Copyright 2023 CS GROUP France
+ *
+ * Author: Herve Codina <herve.codina@bootlin.com>
+ */
+#ifndef __PEF2256_H__
+#define __PEF2256_H__
+
+#include <linux/types.h>
+
+struct pef2256;
+struct regmap;
+
+/* Retrieve the PEF2256 regmap */
+struct regmap *pef2256_get_regmap(struct pef2256 *pef2256);
+
+/* PEF2256 hardware versions */
+enum pef2256_version {
+	PEF2256_VERSION_UNKNOWN,
+	PEF2256_VERSION_1_2,
+	PEF2256_VERSION_2_1,
+	PEF2256_VERSION_2_2,
+};
+
+/* Get the PEF2256 hardware version */
+enum pef2256_version pef2256_get_version(struct pef2256 *pef2256);
+
+#endif /* __PEF2256_H__ */
-- 
cgit v1.2.3


From d3bb89ea9c13e5a98d2b7a0ba8e50a77893132cb Mon Sep 17 00:00:00 2001
From: Kefeng Wang <wangkefeng.wang@huawei.com>
Date: Thu, 7 Dec 2023 23:25:25 +0800
Subject: mm: fix VMA heap bounds checking

After converting selinux to VMA heap check helper, the gcl triggers an
execheap SELinux denial, which is caused by a changed logic check.

Previously selinux only checked that the VMA range was within the VMA heap
range, and the implementation checks the intersection between the two
ranges, but the corner case (vm_end=start_brk, brk=vm_start) isn't handled
correctly.

Since commit 11250fd12eb8 ("mm: factor out VMA stack and heap checks") was
only a function extraction, it seems that the issue was introduced by
commit 0db0c01b53a1 ("procfs: fix /proc/<pid>/maps heap check").  Let's
fix above corner cases, meanwhile, correct the wrong indentation of the
stack and heap check helpers.

Fixes: 11250fd12eb8 ("mm: factor out VMA stack and heap checks")
Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Reported-by: Ondrej Mosnacek <omosnace@redhat.com>
Closes: https://lore.kernel.org/selinux/CAFqZXNv0SVT0fkOK6neP9AXbj3nxJ61JAY4+zJzvxqJaeuhbFw@mail.gmail.com/
Tested-by: Ondrej Mosnacek <omosnace@redhat.com>
Link: https://lkml.kernel.org/r/20231207152525.2607420-1-wangkefeng.wang@huawei.com
Cc: David Hildenbrand <david@redhat.com>
Cc: Paul Moore <paul@paul-moore.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephen Smalley <stephen.smalley.work@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mm.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 418d26608ece..da5219b48d52 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -886,8 +886,8 @@ static inline bool vma_is_anonymous(struct vm_area_struct *vma)
  */
 static inline bool vma_is_initial_heap(const struct vm_area_struct *vma)
 {
-       return vma->vm_start <= vma->vm_mm->brk &&
-		vma->vm_end >= vma->vm_mm->start_brk;
+	return vma->vm_start < vma->vm_mm->brk &&
+		vma->vm_end > vma->vm_mm->start_brk;
 }
 
 /*
@@ -901,8 +901,8 @@ static inline bool vma_is_initial_stack(const struct vm_area_struct *vma)
 	 * its "stack".  It's not even well-defined for programs written
 	 * languages like Go.
 	 */
-       return vma->vm_start <= vma->vm_mm->start_stack &&
-	       vma->vm_end >= vma->vm_mm->start_stack;
+	return vma->vm_start <= vma->vm_mm->start_stack &&
+		vma->vm_end >= vma->vm_mm->start_stack;
 }
 
 static inline bool vma_is_temporary_stack(struct vm_area_struct *vma)
-- 
cgit v1.2.3


From 6376a824595607e99d032a39ba3394988b4fce96 Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Fri, 8 Dec 2023 17:50:18 +0000
Subject: mm/damon/core: make damon_start() waits until kdamond_fn() starts

The cleanup tasks of kdamond threads including reset of corresponding
DAMON context's ->kdamond field and decrease of global nr_running_ctxs
counter is supposed to be executed by kdamond_fn().  However, commit
0f91d13366a4 ("mm/damon: simplify stop mechanism") made neither
damon_start() nor damon_stop() ensure the corresponding kdamond has
started the execution of kdamond_fn().

As a result, the cleanup can be skipped if damon_stop() is called fast
enough after the previous damon_start().  Especially the skipped reset
of ->kdamond could cause a use-after-free.

Fix it by waiting for start of kdamond_fn() execution from
damon_start().

Link: https://lkml.kernel.org/r/20231208175018.63880-1-sj@kernel.org
Fixes: 0f91d13366a4 ("mm/damon: simplify stop mechanism")
Signed-off-by: SeongJae Park <sj@kernel.org>
Reported-by: Jakub Acs <acsjakub@amazon.de>
Cc: Changbin Du <changbin.du@intel.com>
Cc: Jakub Acs <acsjakub@amazon.de>
Cc: <stable@vger.kernel.org> # 5.15.x
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/damon.h | 2 ++
 mm/damon/core.c       | 6 ++++++
 2 files changed, 8 insertions(+)

(limited to 'include')

diff --git a/include/linux/damon.h b/include/linux/damon.h
index ab2f17d9926b..e00ddf1ed39c 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -559,6 +559,8 @@ struct damon_ctx {
 	 * update
 	 */
 	unsigned long next_ops_update_sis;
+	/* for waiting until the execution of the kdamond_fn is started */
+	struct completion kdamond_started;
 
 /* public: */
 	struct task_struct *kdamond;
diff --git a/mm/damon/core.c b/mm/damon/core.c
index ce1562783e7e..3a05e71509b9 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -445,6 +445,8 @@ struct damon_ctx *damon_new_ctx(void)
 	if (!ctx)
 		return NULL;
 
+	init_completion(&ctx->kdamond_started);
+
 	ctx->attrs.sample_interval = 5 * 1000;
 	ctx->attrs.aggr_interval = 100 * 1000;
 	ctx->attrs.ops_update_interval = 60 * 1000 * 1000;
@@ -668,11 +670,14 @@ static int __damon_start(struct damon_ctx *ctx)
 	mutex_lock(&ctx->kdamond_lock);
 	if (!ctx->kdamond) {
 		err = 0;
+		reinit_completion(&ctx->kdamond_started);
 		ctx->kdamond = kthread_run(kdamond_fn, ctx, "kdamond.%d",
 				nr_running_ctxs);
 		if (IS_ERR(ctx->kdamond)) {
 			err = PTR_ERR(ctx->kdamond);
 			ctx->kdamond = NULL;
+		} else {
+			wait_for_completion(&ctx->kdamond_started);
 		}
 	}
 	mutex_unlock(&ctx->kdamond_lock);
@@ -1433,6 +1438,7 @@ static int kdamond_fn(void *data)
 
 	pr_debug("kdamond (%d) starts\n", current->pid);
 
+	complete(&ctx->kdamond_started);
 	kdamond_init_intervals_sis(ctx);
 
 	if (ctx->ops.init)
-- 
cgit v1.2.3


From 081488051d28d32569ebb7c7a23572778b2e7d57 Mon Sep 17 00:00:00 2001
From: Yu Zhao <yuzhao@google.com>
Date: Thu, 7 Dec 2023 23:14:04 -0700
Subject: mm/mglru: fix underprotected page cache

Unmapped folios accessed through file descriptors can be underprotected.
Those folios are added to the oldest generation based on:

1. The fact that they are less costly to reclaim (no need to walk the
   rmap and flush the TLB) and have less impact on performance (don't
   cause major PFs and can be non-blocking if needed again).
2. The observation that they are likely to be single-use. E.g., for
   client use cases like Android, its apps parse configuration files
   and store the data in heap (anon); for server use cases like MySQL,
   it reads from InnoDB files and holds the cached data for tables in
   buffer pools (anon).

However, the oldest generation can be very short lived, and if so, it
doesn't provide the PID controller with enough time to respond to a surge
of refaults.  (Note that the PID controller uses weighted refaults and
those from evicted generations only take a half of the whole weight.) In
other words, for a short lived generation, the moving average smooths out
the spike quickly.

To fix the problem:
1. For folios that are already on LRU, if they can be beyond the
   tracking range of tiers, i.e., five accesses through file
   descriptors, move them to the second oldest generation to give them
   more time to age. (Note that tiers are used by the PID controller
   to statistically determine whether folios accessed multiple times
   through file descriptors are worth protecting.)
2. When adding unmapped folios to LRU, adjust the placement of them so
   that they are not too close to the tail. The effect of this is
   similar to the above.

On Android, launching 55 apps sequentially:
                           Before     After      Change
  workingset_refault_anon  25641024   25598972   0%
  workingset_refault_file  115016834  106178438  -8%

Link: https://lkml.kernel.org/r/20231208061407.2125867-1-yuzhao@google.com
Fixes: ac35a4902374 ("mm: multi-gen LRU: minimal implementation")
Signed-off-by: Yu Zhao <yuzhao@google.com>
Reported-by: Charan Teja Kalla <quic_charante@quicinc.com>
Tested-by: Kalesh Singh <kaleshsingh@google.com>
Cc: T.J. Mercier <tjmercier@google.com>
Cc: Kairui Song <ryncsn@gmail.com>
Cc: Hillf Danton <hdanton@sina.com>
Cc: Jaroslav Pulchart <jaroslav.pulchart@gooddata.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mm_inline.h | 23 ++++++++++++++---------
 mm/vmscan.c               |  2 +-
 mm/workingset.c           |  6 +++---
 3 files changed, 18 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index 9ae7def16cb2..f4fe593c1400 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -232,22 +232,27 @@ static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio,
 	if (folio_test_unevictable(folio) || !lrugen->enabled)
 		return false;
 	/*
-	 * There are three common cases for this page:
-	 * 1. If it's hot, e.g., freshly faulted in or previously hot and
-	 *    migrated, add it to the youngest generation.
-	 * 2. If it's cold but can't be evicted immediately, i.e., an anon page
-	 *    not in swapcache or a dirty page pending writeback, add it to the
-	 *    second oldest generation.
-	 * 3. Everything else (clean, cold) is added to the oldest generation.
+	 * There are four common cases for this page:
+	 * 1. If it's hot, i.e., freshly faulted in, add it to the youngest
+	 *    generation, and it's protected over the rest below.
+	 * 2. If it can't be evicted immediately, i.e., a dirty page pending
+	 *    writeback, add it to the second youngest generation.
+	 * 3. If it should be evicted first, e.g., cold and clean from
+	 *    folio_rotate_reclaimable(), add it to the oldest generation.
+	 * 4. Everything else falls between 2 & 3 above and is added to the
+	 *    second oldest generation if it's considered inactive, or the
+	 *    oldest generation otherwise. See lru_gen_is_active().
 	 */
 	if (folio_test_active(folio))
 		seq = lrugen->max_seq;
 	else if ((type == LRU_GEN_ANON && !folio_test_swapcache(folio)) ||
 		 (folio_test_reclaim(folio) &&
 		  (folio_test_dirty(folio) || folio_test_writeback(folio))))
-		seq = lrugen->min_seq[type] + 1;
-	else
+		seq = lrugen->max_seq - 1;
+	else if (reclaiming || lrugen->min_seq[type] + MIN_NR_GENS >= lrugen->max_seq)
 		seq = lrugen->min_seq[type];
+	else
+		seq = lrugen->min_seq[type] + 1;
 
 	gen = lru_gen_from_seq(seq);
 	flags = (gen + 1UL) << LRU_GEN_PGOFF;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 506f8220c5fe..540333f5415c 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4232,7 +4232,7 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c
 	}
 
 	/* protected */
-	if (tier > tier_idx) {
+	if (tier > tier_idx || refs == BIT(LRU_REFS_WIDTH)) {
 		int hist = lru_hist_from_seq(lrugen->min_seq[type]);
 
 		gen = folio_inc_gen(lruvec, folio, false);
diff --git a/mm/workingset.c b/mm/workingset.c
index b192e44a0e7c..33baad203277 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -313,10 +313,10 @@ static void lru_gen_refault(struct folio *folio, void *shadow)
 	 * 1. For pages accessed through page tables, hotter pages pushed out
 	 *    hot pages which refaulted immediately.
 	 * 2. For pages accessed multiple times through file descriptors,
-	 *    numbers of accesses might have been out of the range.
+	 *    they would have been protected by sort_folio().
 	 */
-	if (lru_gen_in_fault() || refs == BIT(LRU_REFS_WIDTH)) {
-		folio_set_workingset(folio);
+	if (lru_gen_in_fault() || refs >= BIT(LRU_REFS_WIDTH) - 1) {
+		set_mask_bits(&folio->flags, 0, LRU_REFS_MASK | BIT(PG_workingset));
 		mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + type, delta);
 	}
 unlock:
-- 
cgit v1.2.3


From 8aa420617918d12d1f5d55030a503c9418e73c2c Mon Sep 17 00:00:00 2001
From: Yu Zhao <yuzhao@google.com>
Date: Thu, 7 Dec 2023 23:14:06 -0700
Subject: mm/mglru: respect min_ttl_ms with memcgs

While investigating kswapd "consuming 100% CPU" [1] (also see "mm/mglru:
try to stop at high watermarks"), it was discovered that the memcg LRU can
breach the thrashing protection imposed by min_ttl_ms.

Before the memcg LRU:
  kswapd()
    shrink_node_memcgs()
      mem_cgroup_iter()
        inc_max_seq()  // always hit a different memcg
    lru_gen_age_node()
      mem_cgroup_iter()
        check the timestamp of the oldest generation

After the memcg LRU:
  kswapd()
    shrink_many()
      restart:
        iterate the memcg LRU:
          inc_max_seq()  // occasionally hit the same memcg
          if raced with lru_gen_rotate_memcg():
            goto restart
    lru_gen_age_node()
      mem_cgroup_iter()
        check the timestamp of the oldest generation

Specifically, when the restart happens in shrink_many(), it needs to stick
with the (memcg LRU) generation it began with.  In other words, it should
neither re-read memcg_lru->seq nor age an lruvec of a different
generation.  Otherwise it can hit the same memcg multiple times without
giving lru_gen_age_node() a chance to check the timestamp of that memcg's
oldest generation (against min_ttl_ms).

[1] https://lore.kernel.org/CAK8fFZ4DY+GtBA40Pm7Nn5xCHy+51w3sfxPqkqpqakSXYyX+Wg@mail.gmail.com/

Link: https://lkml.kernel.org/r/20231208061407.2125867-3-yuzhao@google.com
Fixes: e4dde56cd208 ("mm: multi-gen LRU: per-node lru_gen_folio lists")
Signed-off-by: Yu Zhao <yuzhao@google.com>
Tested-by: T.J. Mercier <tjmercier@google.com>
Cc: Charan Teja Kalla <quic_charante@quicinc.com>
Cc: Hillf Danton <hdanton@sina.com>
Cc: Jaroslav Pulchart <jaroslav.pulchart@gooddata.com>
Cc: Kairui Song <ryncsn@gmail.com>
Cc: Kalesh Singh <kaleshsingh@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mmzone.h | 30 +++++++++++++++++-------------
 mm/vmscan.c            | 30 ++++++++++++++++--------------
 2 files changed, 33 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 3c25226beeed..23533b12bee2 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -505,33 +505,37 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw);
  * the old generation, is incremented when all its bins become empty.
  *
  * There are four operations:
- * 1. MEMCG_LRU_HEAD, which moves an memcg to the head of a random bin in its
+ * 1. MEMCG_LRU_HEAD, which moves a memcg to the head of a random bin in its
  *    current generation (old or young) and updates its "seg" to "head";
- * 2. MEMCG_LRU_TAIL, which moves an memcg to the tail of a random bin in its
+ * 2. MEMCG_LRU_TAIL, which moves a memcg to the tail of a random bin in its
  *    current generation (old or young) and updates its "seg" to "tail";
- * 3. MEMCG_LRU_OLD, which moves an memcg to the head of a random bin in the old
+ * 3. MEMCG_LRU_OLD, which moves a memcg to the head of a random bin in the old
  *    generation, updates its "gen" to "old" and resets its "seg" to "default";
- * 4. MEMCG_LRU_YOUNG, which moves an memcg to the tail of a random bin in the
+ * 4. MEMCG_LRU_YOUNG, which moves a memcg to the tail of a random bin in the
  *    young generation, updates its "gen" to "young" and resets its "seg" to
  *    "default".
  *
  * The events that trigger the above operations are:
  * 1. Exceeding the soft limit, which triggers MEMCG_LRU_HEAD;
- * 2. The first attempt to reclaim an memcg below low, which triggers
+ * 2. The first attempt to reclaim a memcg below low, which triggers
  *    MEMCG_LRU_TAIL;
- * 3. The first attempt to reclaim an memcg below reclaimable size threshold,
+ * 3. The first attempt to reclaim a memcg below reclaimable size threshold,
  *    which triggers MEMCG_LRU_TAIL;
- * 4. The second attempt to reclaim an memcg below reclaimable size threshold,
+ * 4. The second attempt to reclaim a memcg below reclaimable size threshold,
  *    which triggers MEMCG_LRU_YOUNG;
- * 5. Attempting to reclaim an memcg below min, which triggers MEMCG_LRU_YOUNG;
+ * 5. Attempting to reclaim a memcg below min, which triggers MEMCG_LRU_YOUNG;
  * 6. Finishing the aging on the eviction path, which triggers MEMCG_LRU_YOUNG;
- * 7. Offlining an memcg, which triggers MEMCG_LRU_OLD.
+ * 7. Offlining a memcg, which triggers MEMCG_LRU_OLD.
  *
- * Note that memcg LRU only applies to global reclaim, and the round-robin
- * incrementing of their max_seq counters ensures the eventual fairness to all
- * eligible memcgs. For memcg reclaim, it still relies on mem_cgroup_iter().
+ * Notes:
+ * 1. Memcg LRU only applies to global reclaim, and the round-robin incrementing
+ *    of their max_seq counters ensures the eventual fairness to all eligible
+ *    memcgs. For memcg reclaim, it still relies on mem_cgroup_iter().
+ * 2. There are only two valid generations: old (seq) and young (seq+1).
+ *    MEMCG_NR_GENS is set to three so that when reading the generation counter
+ *    locklessly, a stale value (seq-1) does not wraparound to young.
  */
-#define MEMCG_NR_GENS	2
+#define MEMCG_NR_GENS	3
 #define MEMCG_NR_BINS	8
 
 struct lru_gen_memcg {
diff --git a/mm/vmscan.c b/mm/vmscan.c
index bb7dacd8f753..e5fe4a94345f 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4089,6 +4089,9 @@ static void lru_gen_rotate_memcg(struct lruvec *lruvec, int op)
 	else
 		VM_WARN_ON_ONCE(true);
 
+	WRITE_ONCE(lruvec->lrugen.seg, seg);
+	WRITE_ONCE(lruvec->lrugen.gen, new);
+
 	hlist_nulls_del_rcu(&lruvec->lrugen.list);
 
 	if (op == MEMCG_LRU_HEAD || op == MEMCG_LRU_OLD)
@@ -4099,9 +4102,6 @@ static void lru_gen_rotate_memcg(struct lruvec *lruvec, int op)
 	pgdat->memcg_lru.nr_memcgs[old]--;
 	pgdat->memcg_lru.nr_memcgs[new]++;
 
-	lruvec->lrugen.gen = new;
-	WRITE_ONCE(lruvec->lrugen.seg, seg);
-
 	if (!pgdat->memcg_lru.nr_memcgs[old] && old == get_memcg_gen(pgdat->memcg_lru.seq))
 		WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1);
 
@@ -4124,11 +4124,11 @@ void lru_gen_online_memcg(struct mem_cgroup *memcg)
 
 		gen = get_memcg_gen(pgdat->memcg_lru.seq);
 
+		lruvec->lrugen.gen = gen;
+
 		hlist_nulls_add_tail_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[gen][bin]);
 		pgdat->memcg_lru.nr_memcgs[gen]++;
 
-		lruvec->lrugen.gen = gen;
-
 		spin_unlock_irq(&pgdat->memcg_lru.lock);
 	}
 }
@@ -4635,7 +4635,7 @@ static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, bool
 	DEFINE_MAX_SEQ(lruvec);
 
 	if (mem_cgroup_below_min(sc->target_mem_cgroup, memcg))
-		return 0;
+		return -1;
 
 	if (!should_run_aging(lruvec, max_seq, sc, can_swap, &nr_to_scan))
 		return nr_to_scan;
@@ -4710,7 +4710,7 @@ static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 		cond_resched();
 	}
 
-	/* whether try_to_inc_max_seq() was successful */
+	/* whether this lruvec should be rotated */
 	return nr_to_scan < 0;
 }
 
@@ -4764,13 +4764,13 @@ static void shrink_many(struct pglist_data *pgdat, struct scan_control *sc)
 	struct lruvec *lruvec;
 	struct lru_gen_folio *lrugen;
 	struct mem_cgroup *memcg;
-	const struct hlist_nulls_node *pos;
+	struct hlist_nulls_node *pos;
 
+	gen = get_memcg_gen(READ_ONCE(pgdat->memcg_lru.seq));
 	bin = first_bin = get_random_u32_below(MEMCG_NR_BINS);
 restart:
 	op = 0;
 	memcg = NULL;
-	gen = get_memcg_gen(READ_ONCE(pgdat->memcg_lru.seq));
 
 	rcu_read_lock();
 
@@ -4781,6 +4781,10 @@ restart:
 		}
 
 		mem_cgroup_put(memcg);
+		memcg = NULL;
+
+		if (gen != READ_ONCE(lrugen->gen))
+			continue;
 
 		lruvec = container_of(lrugen, struct lruvec, lrugen);
 		memcg = lruvec_memcg(lruvec);
@@ -4865,16 +4869,14 @@ static void set_initial_priority(struct pglist_data *pgdat, struct scan_control
 	if (sc->priority != DEF_PRIORITY || sc->nr_to_reclaim < MIN_LRU_BATCH)
 		return;
 	/*
-	 * Determine the initial priority based on ((total / MEMCG_NR_GENS) >>
-	 * priority) * reclaimed_to_scanned_ratio = nr_to_reclaim, where the
-	 * estimated reclaimed_to_scanned_ratio = inactive / total.
+	 * Determine the initial priority based on
+	 * (total >> priority) * reclaimed_to_scanned_ratio = nr_to_reclaim,
+	 * where reclaimed_to_scanned_ratio = inactive / total.
 	 */
 	reclaimable = node_page_state(pgdat, NR_INACTIVE_FILE);
 	if (get_swappiness(lruvec, sc))
 		reclaimable += node_page_state(pgdat, NR_INACTIVE_ANON);
 
-	reclaimable /= MEMCG_NR_GENS;
-
 	/* round down reclaimable and round up sc->nr_to_reclaim */
 	priority = fls_long(reclaimable) - 1 - fls_long(sc->nr_to_reclaim - 1);
 
-- 
cgit v1.2.3


From 4376807bf2d5371c3e00080c972be568c3f8a7d1 Mon Sep 17 00:00:00 2001
From: Yu Zhao <yuzhao@google.com>
Date: Thu, 7 Dec 2023 23:14:07 -0700
Subject: mm/mglru: reclaim offlined memcgs harder

In the effort to reduce zombie memcgs [1], it was discovered that the
memcg LRU doesn't apply enough pressure on offlined memcgs.  Specifically,
instead of rotating them to the tail of the current generation
(MEMCG_LRU_TAIL) for a second attempt, it moves them to the next
generation (MEMCG_LRU_YOUNG) after the first attempt.

Not applying enough pressure on offlined memcgs can cause them to build
up, and this can be particularly harmful to memory-constrained systems.

On Pixel 8 Pro, launching apps for 50 cycles:
                 Before  After  Change
  Zombie memcgs  45      35     -22%

[1] https://lore.kernel.org/CABdmKX2M6koq4Q0Cmp_-=wbP0Qa190HdEGGaHfxNS05gAkUtPA@mail.gmail.com/

Link: https://lkml.kernel.org/r/20231208061407.2125867-4-yuzhao@google.com
Fixes: e4dde56cd208 ("mm: multi-gen LRU: per-node lru_gen_folio lists")
Signed-off-by: Yu Zhao <yuzhao@google.com>
Reported-by: T.J. Mercier <tjmercier@google.com>
Tested-by: T.J. Mercier <tjmercier@google.com>
Cc: Charan Teja Kalla <quic_charante@quicinc.com>
Cc: Hillf Danton <hdanton@sina.com>
Cc: Jaroslav Pulchart <jaroslav.pulchart@gooddata.com>
Cc: Kairui Song <ryncsn@gmail.com>
Cc: Kalesh Singh <kaleshsingh@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mmzone.h |  8 ++++----
 mm/vmscan.c            | 24 ++++++++++++++++--------
 2 files changed, 20 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 23533b12bee2..9db36e197712 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -519,10 +519,10 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw);
  * 1. Exceeding the soft limit, which triggers MEMCG_LRU_HEAD;
  * 2. The first attempt to reclaim a memcg below low, which triggers
  *    MEMCG_LRU_TAIL;
- * 3. The first attempt to reclaim a memcg below reclaimable size threshold,
- *    which triggers MEMCG_LRU_TAIL;
- * 4. The second attempt to reclaim a memcg below reclaimable size threshold,
- *    which triggers MEMCG_LRU_YOUNG;
+ * 3. The first attempt to reclaim a memcg offlined or below reclaimable size
+ *    threshold, which triggers MEMCG_LRU_TAIL;
+ * 4. The second attempt to reclaim a memcg offlined or below reclaimable size
+ *    threshold, which triggers MEMCG_LRU_YOUNG;
  * 5. Attempting to reclaim a memcg below min, which triggers MEMCG_LRU_YOUNG;
  * 6. Finishing the aging on the eviction path, which triggers MEMCG_LRU_YOUNG;
  * 7. Offlining a memcg, which triggers MEMCG_LRU_OLD.
diff --git a/mm/vmscan.c b/mm/vmscan.c
index e5fe4a94345f..9dd8977de5a2 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4598,7 +4598,12 @@ static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq,
 	}
 
 	/* try to scrape all its memory if this memcg was deleted */
-	*nr_to_scan = mem_cgroup_online(memcg) ? (total >> sc->priority) : total;
+	if (!mem_cgroup_online(memcg)) {
+		*nr_to_scan = total;
+		return false;
+	}
+
+	*nr_to_scan = total >> sc->priority;
 
 	/*
 	 * The aging tries to be lazy to reduce the overhead, while the eviction
@@ -4719,14 +4724,9 @@ static int shrink_one(struct lruvec *lruvec, struct scan_control *sc)
 	bool success;
 	unsigned long scanned = sc->nr_scanned;
 	unsigned long reclaimed = sc->nr_reclaimed;
-	int seg = lru_gen_memcg_seg(lruvec);
 	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
 	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
 
-	/* see the comment on MEMCG_NR_GENS */
-	if (!lruvec_is_sizable(lruvec, sc))
-		return seg != MEMCG_LRU_TAIL ? MEMCG_LRU_TAIL : MEMCG_LRU_YOUNG;
-
 	mem_cgroup_calculate_protection(NULL, memcg);
 
 	if (mem_cgroup_below_min(NULL, memcg))
@@ -4734,7 +4734,7 @@ static int shrink_one(struct lruvec *lruvec, struct scan_control *sc)
 
 	if (mem_cgroup_below_low(NULL, memcg)) {
 		/* see the comment on MEMCG_NR_GENS */
-		if (seg != MEMCG_LRU_TAIL)
+		if (lru_gen_memcg_seg(lruvec) != MEMCG_LRU_TAIL)
 			return MEMCG_LRU_TAIL;
 
 		memcg_memory_event(memcg, MEMCG_LOW);
@@ -4750,7 +4750,15 @@ static int shrink_one(struct lruvec *lruvec, struct scan_control *sc)
 
 	flush_reclaim_state(sc);
 
-	return success ? MEMCG_LRU_YOUNG : 0;
+	if (success && mem_cgroup_online(memcg))
+		return MEMCG_LRU_YOUNG;
+
+	if (!success && lruvec_is_sizable(lruvec, sc))
+		return 0;
+
+	/* one retry if offlined or too small */
+	return lru_gen_memcg_seg(lruvec) != MEMCG_LRU_TAIL ?
+	       MEMCG_LRU_TAIL : MEMCG_LRU_YOUNG;
 }
 
 #ifdef CONFIG_MEMCG
-- 
cgit v1.2.3


From 05ce71929efc79f5978589e0456a54eb0fe6485e Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Mon, 27 Nov 2023 16:19:31 +0100
Subject: PM: domains: Drop the unused pm_genpd_opp_to_performance_state()

Since commit 7c41cdcd3bbe ("OPP: Simplify the over-designed pstate <->
level dance"), there is no longer any users of the
pm_genpd_opp_to_performance_state() API. Let's therefore drop it and its
corresponding ->opp_to_performance_state() callback, which also no longer
has any users.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Acked-by: Rafael J. Wysocki <rafael@kernel.org>
Link: https://lore.kernel.org/r/20231127151931.47055-1-ulf.hansson@linaro.org
---
 drivers/base/power/domain.c | 32 --------------------------------
 include/linux/pm_domain.h   | 12 ------------
 2 files changed, 44 deletions(-)

(limited to 'include')

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index da1777e39eaa..cf65b5a9783c 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -3042,38 +3042,6 @@ int of_genpd_parse_idle_states(struct device_node *dn,
 }
 EXPORT_SYMBOL_GPL(of_genpd_parse_idle_states);
 
-/**
- * pm_genpd_opp_to_performance_state - Gets performance state of the genpd from its OPP node.
- *
- * @genpd_dev: Genpd's device for which the performance-state needs to be found.
- * @opp: struct dev_pm_opp of the OPP for which we need to find performance
- *	state.
- *
- * Returns performance state encoded in the OPP of the genpd. This calls
- * platform specific genpd->opp_to_performance_state() callback to translate
- * power domain OPP to performance state.
- *
- * Returns performance state on success and 0 on failure.
- */
-unsigned int pm_genpd_opp_to_performance_state(struct device *genpd_dev,
-					       struct dev_pm_opp *opp)
-{
-	struct generic_pm_domain *genpd = NULL;
-	int state;
-
-	genpd = container_of(genpd_dev, struct generic_pm_domain, dev);
-
-	if (unlikely(!genpd->opp_to_performance_state))
-		return 0;
-
-	genpd_lock(genpd);
-	state = genpd->opp_to_performance_state(genpd, opp);
-	genpd_unlock(genpd);
-
-	return state;
-}
-EXPORT_SYMBOL_GPL(pm_genpd_opp_to_performance_state);
-
 static int __init genpd_bus_init(void)
 {
 	return bus_register(&genpd_bus_type);
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 34663d0d5c55..b97c5e9820f9 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -118,7 +118,6 @@ struct genpd_power_state {
 };
 
 struct genpd_lock_ops;
-struct dev_pm_opp;
 struct opp_table;
 
 struct generic_pm_domain {
@@ -146,8 +145,6 @@ struct generic_pm_domain {
 	int (*power_on)(struct generic_pm_domain *domain);
 	struct raw_notifier_head power_notifiers; /* Power on/off notifiers */
 	struct opp_table *opp_table;	/* OPP table of the genpd */
-	unsigned int (*opp_to_performance_state)(struct generic_pm_domain *genpd,
-						 struct dev_pm_opp *opp);
 	int (*set_performance_state)(struct generic_pm_domain *genpd,
 				     unsigned int state);
 	struct gpd_dev_ops dev_ops;
@@ -348,8 +345,6 @@ int of_genpd_remove_subdomain(struct of_phandle_args *parent_spec,
 struct generic_pm_domain *of_genpd_remove_last(struct device_node *np);
 int of_genpd_parse_idle_states(struct device_node *dn,
 			       struct genpd_power_state **states, int *n);
-unsigned int pm_genpd_opp_to_performance_state(struct device *genpd_dev,
-					       struct dev_pm_opp *opp);
 
 int genpd_dev_pm_attach(struct device *dev);
 struct device *genpd_dev_pm_attach_by_id(struct device *dev,
@@ -395,13 +390,6 @@ static inline int of_genpd_parse_idle_states(struct device_node *dn,
 	return -ENODEV;
 }
 
-static inline unsigned int
-pm_genpd_opp_to_performance_state(struct device *genpd_dev,
-				  struct dev_pm_opp *opp)
-{
-	return 0;
-}
-
 static inline int genpd_dev_pm_attach(struct device *dev)
 {
 	return 0;
-- 
cgit v1.2.3


From 4f7aa122bc9219baca0bfface5917062d6c45ee8 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Thu, 7 Dec 2023 16:12:04 +0100
Subject: dpll: remove leftover mode_supported() op and use mode_get() instead

Mode supported is currently reported to the user exactly the same, as
the current mode. That's because mode changing is not implemented.
Remove the leftover mode_supported() op and use mode_get() to fill up
the supported mode exposed to user.

One, if even, mode changing is going to be introduced, this could be
very easily taken back. In the meantime, prevent drivers form
implementing this in wrong way (as for example recent netdevsim
implementation attempt intended to do).

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/dpll/dpll_netlink.c                    | 16 ++++++++++------
 drivers/net/ethernet/intel/ice/ice_dpll.c      | 26 --------------------------
 drivers/net/ethernet/mellanox/mlx5/core/dpll.c |  9 ---------
 drivers/ptp/ptp_ocp.c                          |  8 --------
 include/linux/dpll.h                           |  3 ---
 5 files changed, 10 insertions(+), 52 deletions(-)

(limited to 'include')

diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c
index 442a0ebeb953..e1a4737500f5 100644
--- a/drivers/dpll/dpll_netlink.c
+++ b/drivers/dpll/dpll_netlink.c
@@ -101,13 +101,17 @@ dpll_msg_add_mode_supported(struct sk_buff *msg, struct dpll_device *dpll,
 {
 	const struct dpll_device_ops *ops = dpll_device_ops(dpll);
 	enum dpll_mode mode;
+	int ret;
 
-	if (!ops->mode_supported)
-		return 0;
-	for (mode = DPLL_MODE_MANUAL; mode <= DPLL_MODE_MAX; mode++)
-		if (ops->mode_supported(dpll, dpll_priv(dpll), mode, extack))
-			if (nla_put_u32(msg, DPLL_A_MODE_SUPPORTED, mode))
-				return -EMSGSIZE;
+	/* No mode change is supported now, so the only supported mode is the
+	 * one obtained by mode_get().
+	 */
+
+	ret = ops->mode_get(dpll, dpll_priv(dpll), &mode, extack);
+	if (ret)
+		return ret;
+	if (nla_put_u32(msg, DPLL_A_MODE_SUPPORTED, mode))
+		return -EMSGSIZE;
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c
index 86b180cb32a0..b9c5eced6326 100644
--- a/drivers/net/ethernet/intel/ice/ice_dpll.c
+++ b/drivers/net/ethernet/intel/ice/ice_dpll.c
@@ -512,31 +512,6 @@ ice_dpll_lock_status_get(const struct dpll_device *dpll, void *dpll_priv,
 	return 0;
 }
 
-/**
- * ice_dpll_mode_supported - check if dpll's working mode is supported
- * @dpll: registered dpll pointer
- * @dpll_priv: private data pointer passed on dpll registration
- * @mode: mode to be checked for support
- * @extack: error reporting
- *
- * Dpll subsystem callback. Provides information if working mode is supported
- * by dpll.
- *
- * Return:
- * * true - mode is supported
- * * false - mode is not supported
- */
-static bool ice_dpll_mode_supported(const struct dpll_device *dpll,
-				    void *dpll_priv,
-				    enum dpll_mode mode,
-				    struct netlink_ext_ack *extack)
-{
-	if (mode == DPLL_MODE_AUTOMATIC)
-		return true;
-
-	return false;
-}
-
 /**
  * ice_dpll_mode_get - get dpll's working mode
  * @dpll: registered dpll pointer
@@ -1197,7 +1172,6 @@ static const struct dpll_pin_ops ice_dpll_output_ops = {
 
 static const struct dpll_device_ops ice_dpll_ops = {
 	.lock_status_get = ice_dpll_lock_status_get,
-	.mode_supported = ice_dpll_mode_supported,
 	.mode_get = ice_dpll_mode_get,
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dpll.c b/drivers/net/ethernet/mellanox/mlx5/core/dpll.c
index 2cd81bb32c66..a7ffd61fe248 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dpll.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dpll.c
@@ -128,18 +128,9 @@ static int mlx5_dpll_device_mode_get(const struct dpll_device *dpll,
 	return 0;
 }
 
-static bool mlx5_dpll_device_mode_supported(const struct dpll_device *dpll,
-					    void *priv,
-					    enum dpll_mode mode,
-					    struct netlink_ext_ack *extack)
-{
-	return mode == DPLL_MODE_MANUAL;
-}
-
 static const struct dpll_device_ops mlx5_dpll_device_ops = {
 	.lock_status_get = mlx5_dpll_device_lock_status_get,
 	.mode_get = mlx5_dpll_device_mode_get,
-	.mode_supported = mlx5_dpll_device_mode_supported,
 };
 
 static int mlx5_dpll_pin_direction_get(const struct dpll_pin *pin,
diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c
index 4021d3d325f9..b022af3d20fe 100644
--- a/drivers/ptp/ptp_ocp.c
+++ b/drivers/ptp/ptp_ocp.c
@@ -4260,13 +4260,6 @@ static int ptp_ocp_dpll_mode_get(const struct dpll_device *dpll, void *priv,
 	return 0;
 }
 
-static bool ptp_ocp_dpll_mode_supported(const struct dpll_device *dpll,
-					void *priv, const enum dpll_mode mode,
-					struct netlink_ext_ack *extack)
-{
-	return mode == DPLL_MODE_AUTOMATIC;
-}
-
 static int ptp_ocp_dpll_direction_get(const struct dpll_pin *pin,
 				      void *pin_priv,
 				      const struct dpll_device *dpll,
@@ -4350,7 +4343,6 @@ static int ptp_ocp_dpll_frequency_get(const struct dpll_pin *pin,
 static const struct dpll_device_ops dpll_ops = {
 	.lock_status_get = ptp_ocp_dpll_lock_status_get,
 	.mode_get = ptp_ocp_dpll_mode_get,
-	.mode_supported = ptp_ocp_dpll_mode_supported,
 };
 
 static const struct dpll_pin_ops dpll_pins_ops = {
diff --git a/include/linux/dpll.h b/include/linux/dpll.h
index 578fc5fa3750..b1a5f9ca8ee5 100644
--- a/include/linux/dpll.h
+++ b/include/linux/dpll.h
@@ -17,9 +17,6 @@ struct dpll_pin;
 struct dpll_device_ops {
 	int (*mode_get)(const struct dpll_device *dpll, void *dpll_priv,
 			enum dpll_mode *mode, struct netlink_ext_ack *extack);
-	bool (*mode_supported)(const struct dpll_device *dpll, void *dpll_priv,
-			       const enum dpll_mode mode,
-			       struct netlink_ext_ack *extack);
 	int (*lock_status_get)(const struct dpll_device *dpll, void *dpll_priv,
 			       enum dpll_lock_status *status,
 			       struct netlink_ext_ack *extack);
-- 
cgit v1.2.3


From 59b3e31e73322ec195e45e0a1da712c752ee1b0c Mon Sep 17 00:00:00 2001
From: Daniel Golle <daniel@makrotopia.org>
Date: Tue, 28 Nov 2023 04:00:10 +0000
Subject: leds: trigger: netdev: Extend speeds up to 10G

Add 2.5G, 5G and 10G as available speeds to the netdev LED trigger.

Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/r/99e7d3304c6bba7f4863a4a80764a869855f2085.1701143925.git.daniel@makrotopia.org
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/trigger/ledtrig-netdev.c | 32 +++++++++++++++++++++++++++++++-
 include/linux/leds.h                  |  3 +++
 2 files changed, 34 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/leds/trigger/ledtrig-netdev.c b/drivers/leds/trigger/ledtrig-netdev.c
index e358e77e4b38..bd68da15c723 100644
--- a/drivers/leds/trigger/ledtrig-netdev.c
+++ b/drivers/leds/trigger/ledtrig-netdev.c
@@ -99,6 +99,18 @@ static void set_baseline_state(struct led_netdev_data *trigger_data)
 		    trigger_data->link_speed == SPEED_1000)
 			blink_on = true;
 
+		if (test_bit(TRIGGER_NETDEV_LINK_2500, &trigger_data->mode) &&
+		    trigger_data->link_speed == SPEED_2500)
+			blink_on = true;
+
+		if (test_bit(TRIGGER_NETDEV_LINK_5000, &trigger_data->mode) &&
+		    trigger_data->link_speed == SPEED_5000)
+			blink_on = true;
+
+		if (test_bit(TRIGGER_NETDEV_LINK_10000, &trigger_data->mode) &&
+		    trigger_data->link_speed == SPEED_10000)
+			blink_on = true;
+
 		if (test_bit(TRIGGER_NETDEV_HALF_DUPLEX, &trigger_data->mode) &&
 		    trigger_data->duplex == DUPLEX_HALF)
 			blink_on = true;
@@ -286,6 +298,9 @@ static ssize_t netdev_led_attr_show(struct device *dev, char *buf,
 	case TRIGGER_NETDEV_LINK_10:
 	case TRIGGER_NETDEV_LINK_100:
 	case TRIGGER_NETDEV_LINK_1000:
+	case TRIGGER_NETDEV_LINK_2500:
+	case TRIGGER_NETDEV_LINK_5000:
+	case TRIGGER_NETDEV_LINK_10000:
 	case TRIGGER_NETDEV_HALF_DUPLEX:
 	case TRIGGER_NETDEV_FULL_DUPLEX:
 	case TRIGGER_NETDEV_TX:
@@ -316,6 +331,9 @@ static ssize_t netdev_led_attr_store(struct device *dev, const char *buf,
 	case TRIGGER_NETDEV_LINK_10:
 	case TRIGGER_NETDEV_LINK_100:
 	case TRIGGER_NETDEV_LINK_1000:
+	case TRIGGER_NETDEV_LINK_2500:
+	case TRIGGER_NETDEV_LINK_5000:
+	case TRIGGER_NETDEV_LINK_10000:
 	case TRIGGER_NETDEV_HALF_DUPLEX:
 	case TRIGGER_NETDEV_FULL_DUPLEX:
 	case TRIGGER_NETDEV_TX:
@@ -334,7 +352,10 @@ static ssize_t netdev_led_attr_store(struct device *dev, const char *buf,
 	if (test_bit(TRIGGER_NETDEV_LINK, &mode) &&
 	    (test_bit(TRIGGER_NETDEV_LINK_10, &mode) ||
 	     test_bit(TRIGGER_NETDEV_LINK_100, &mode) ||
-	     test_bit(TRIGGER_NETDEV_LINK_1000, &mode)))
+	     test_bit(TRIGGER_NETDEV_LINK_1000, &mode) ||
+	     test_bit(TRIGGER_NETDEV_LINK_2500, &mode) ||
+	     test_bit(TRIGGER_NETDEV_LINK_5000, &mode) ||
+	     test_bit(TRIGGER_NETDEV_LINK_10000, &mode)))
 		return -EINVAL;
 
 	cancel_delayed_work_sync(&trigger_data->work);
@@ -364,6 +385,9 @@ DEFINE_NETDEV_TRIGGER(link, TRIGGER_NETDEV_LINK);
 DEFINE_NETDEV_TRIGGER(link_10, TRIGGER_NETDEV_LINK_10);
 DEFINE_NETDEV_TRIGGER(link_100, TRIGGER_NETDEV_LINK_100);
 DEFINE_NETDEV_TRIGGER(link_1000, TRIGGER_NETDEV_LINK_1000);
+DEFINE_NETDEV_TRIGGER(link_2500, TRIGGER_NETDEV_LINK_2500);
+DEFINE_NETDEV_TRIGGER(link_5000, TRIGGER_NETDEV_LINK_5000);
+DEFINE_NETDEV_TRIGGER(link_10000, TRIGGER_NETDEV_LINK_10000);
 DEFINE_NETDEV_TRIGGER(half_duplex, TRIGGER_NETDEV_HALF_DUPLEX);
 DEFINE_NETDEV_TRIGGER(full_duplex, TRIGGER_NETDEV_FULL_DUPLEX);
 DEFINE_NETDEV_TRIGGER(tx, TRIGGER_NETDEV_TX);
@@ -422,6 +446,9 @@ static struct attribute *netdev_trig_attrs[] = {
 	&dev_attr_link_10.attr,
 	&dev_attr_link_100.attr,
 	&dev_attr_link_1000.attr,
+	&dev_attr_link_2500.attr,
+	&dev_attr_link_5000.attr,
+	&dev_attr_link_10000.attr,
 	&dev_attr_full_duplex.attr,
 	&dev_attr_half_duplex.attr,
 	&dev_attr_rx.attr,
@@ -519,6 +546,9 @@ static void netdev_trig_work(struct work_struct *work)
 			 test_bit(TRIGGER_NETDEV_LINK_10, &trigger_data->mode) ||
 			 test_bit(TRIGGER_NETDEV_LINK_100, &trigger_data->mode) ||
 			 test_bit(TRIGGER_NETDEV_LINK_1000, &trigger_data->mode) ||
+			 test_bit(TRIGGER_NETDEV_LINK_2500, &trigger_data->mode) ||
+			 test_bit(TRIGGER_NETDEV_LINK_5000, &trigger_data->mode) ||
+			 test_bit(TRIGGER_NETDEV_LINK_10000, &trigger_data->mode) ||
 			 test_bit(TRIGGER_NETDEV_HALF_DUPLEX, &trigger_data->mode) ||
 			 test_bit(TRIGGER_NETDEV_FULL_DUPLEX, &trigger_data->mode);
 		interval = jiffies_to_msecs(
diff --git a/include/linux/leds.h b/include/linux/leds.h
index aa16dc2a8230..1bdf7f5a0d7c 100644
--- a/include/linux/leds.h
+++ b/include/linux/leds.h
@@ -588,6 +588,9 @@ enum led_trigger_netdev_modes {
 	TRIGGER_NETDEV_LINK_10,
 	TRIGGER_NETDEV_LINK_100,
 	TRIGGER_NETDEV_LINK_1000,
+	TRIGGER_NETDEV_LINK_2500,
+	TRIGGER_NETDEV_LINK_5000,
+	TRIGGER_NETDEV_LINK_10000,
 	TRIGGER_NETDEV_HALF_DUPLEX,
 	TRIGGER_NETDEV_FULL_DUPLEX,
 	TRIGGER_NETDEV_TX,
-- 
cgit v1.2.3


From 4ff4379ce6eefe81695bcc2e021ce1dac3d707d2 Mon Sep 17 00:00:00 2001
From: Florian Eckert <fe@dev.tdt.de>
Date: Mon, 27 Nov 2023 12:03:08 +0100
Subject: tty: add new helper function tty_get_tiocm

There is no in-kernel function to get the status register of a tty device
like the TIOCMGET ioctl returns to userspace. Create a new function,
tty_get_tiocm(), to obtain the status register that other portions of the
kernel can call if they need this information, and move the existing
internal tty_tiocmget() function to use this interface.

Signed-off-by: Florian Eckert <fe@dev.tdt.de>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/20231127110311.3583957-2-fe@dev.tdt.de
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/tty/tty_io.c | 28 ++++++++++++++++++++++------
 include/linux/tty.h  |  1 +
 2 files changed, 23 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 06414e43e0b5..e2e93404133e 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -2498,6 +2498,24 @@ static int send_break(struct tty_struct *tty, unsigned int duration)
 	return retval;
 }
 
+/**
+ * tty_get_tiocm - get tiocm status register
+ * @tty: tty device
+ *
+ * Obtain the modem status bits from the tty driver if the feature
+ * is supported.
+ */
+int tty_get_tiocm(struct tty_struct *tty)
+{
+	int retval = -ENOTTY;
+
+	if (tty->ops->tiocmget)
+		retval = tty->ops->tiocmget(tty);
+
+	return retval;
+}
+EXPORT_SYMBOL_GPL(tty_get_tiocm);
+
 /**
  * tty_tiocmget - get modem status
  * @tty: tty device
@@ -2510,14 +2528,12 @@ static int send_break(struct tty_struct *tty, unsigned int duration)
  */
 static int tty_tiocmget(struct tty_struct *tty, int __user *p)
 {
-	int retval = -ENOTTY;
+	int retval;
 
-	if (tty->ops->tiocmget) {
-		retval = tty->ops->tiocmget(tty);
+	retval = tty_get_tiocm(tty);
+	if (retval >= 0)
+		retval = put_user(retval, p);
 
-		if (retval >= 0)
-			retval = put_user(retval, p);
-	}
 	return retval;
 }
 
diff --git a/include/linux/tty.h b/include/linux/tty.h
index 4b6340ac2af2..d219a11e3fe0 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -419,6 +419,7 @@ bool tty_unthrottle_safe(struct tty_struct *tty);
 int tty_do_resize(struct tty_struct *tty, struct winsize *ws);
 int tty_get_icount(struct tty_struct *tty,
 		struct serial_icounter_struct *icount);
+int tty_get_tiocm(struct tty_struct *tty);
 int is_current_pgrp_orphaned(void);
 void tty_hangup(struct tty_struct *tty);
 void tty_vhangup(struct tty_struct *tty);
-- 
cgit v1.2.3


From bdc22c8d52d70fc5655ab4dbf72fa79b034bb7b5 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Tue, 5 Dec 2023 20:18:39 +0100
Subject: thermal: trip: Send trip change notifications on all trip updates

The _store callbacks of the trip point temperature and hysteresis sysfs
attributes invoke thermal_notify_tz_trip_change() to send a notification
regarding the trip point change, but when trip points are updated by the
platform firmware, trip point change notifications are not sent.

To make the behavior after a trip point change more consistent,
modify all of the 3 places where trip point temperature is updated
to use a new function called thermal_zone_set_trip_temp() for this
purpose and make that function call thermal_notify_tz_trip_change().

Note that trip point hysteresis can only be updated via sysfs and
trip_point_hyst_store() calls thermal_notify_tz_trip_change() already,
so this code path need not be changed.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Daniel Lezcano <daniel.lezcano@linaro.org>
---
 drivers/acpi/thermal.c                                     |  7 +++++--
 .../thermal/intel/int340x_thermal/int340x_thermal_zone.c   |  8 +++++---
 drivers/thermal/thermal_sysfs.c                            |  4 ++--
 drivers/thermal/thermal_trip.c                             | 14 +++++++++++++-
 include/linux/thermal.h                                    |  2 ++
 5 files changed, 27 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c
index f74d81abdbfc..3e679e9feec5 100644
--- a/drivers/acpi/thermal.c
+++ b/drivers/acpi/thermal.c
@@ -297,6 +297,7 @@ static int acpi_thermal_adjust_trip(struct thermal_trip *trip, void *data)
 	struct acpi_thermal_trip *acpi_trip = trip->priv;
 	struct adjust_trip_data *atd = data;
 	struct acpi_thermal *tz = atd->tz;
+	int temp;
 
 	if (!acpi_trip || !acpi_thermal_trip_valid(acpi_trip))
 		return 0;
@@ -307,9 +308,11 @@ static int acpi_thermal_adjust_trip(struct thermal_trip *trip, void *data)
 		acpi_thermal_update_trip_devices(tz, trip);
 
 	if (acpi_thermal_trip_valid(acpi_trip))
-		trip->temperature = acpi_thermal_temp(tz, acpi_trip->temp_dk);
+		temp = acpi_thermal_temp(tz, acpi_trip->temp_dk);
 	else
-		trip->temperature = THERMAL_TEMP_INVALID;
+		temp = THERMAL_TEMP_INVALID;
+
+	thermal_zone_set_trip_temp(tz->thermal_zone, trip, temp);
 
 	return 0;
 }
diff --git a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
index a03b67579dd9..3e4bfe817fac 100644
--- a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
+++ b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
@@ -225,7 +225,8 @@ EXPORT_SYMBOL_GPL(int340x_thermal_zone_remove);
 
 static int int340x_update_one_trip(struct thermal_trip *trip, void *arg)
 {
-	struct acpi_device *zone_adev = arg;
+	struct int34x_thermal_zone *int34x_zone = arg;
+	struct acpi_device *zone_adev = int34x_zone->adev;
 	int temp, err;
 
 	switch (trip->type) {
@@ -249,14 +250,15 @@ static int int340x_update_one_trip(struct thermal_trip *trip, void *arg)
 	if (err)
 		temp = THERMAL_TEMP_INVALID;
 
-	trip->temperature = temp;
+	thermal_zone_set_trip_temp(int34x_zone->zone, trip, temp);
+
 	return 0;
 }
 
 void int340x_thermal_update_trips(struct int34x_thermal_zone *int34x_zone)
 {
 	thermal_zone_for_each_trip(int34x_zone->zone, int340x_update_one_trip,
-				   int34x_zone->adev);
+				   int34x_zone);
 }
 EXPORT_SYMBOL_GPL(int340x_thermal_update_trips);
 
diff --git a/drivers/thermal/thermal_sysfs.c b/drivers/thermal/thermal_sysfs.c
index f52af8a3b4b5..d8ff74a4338a 100644
--- a/drivers/thermal/thermal_sysfs.c
+++ b/drivers/thermal/thermal_sysfs.c
@@ -129,9 +129,9 @@ trip_point_temp_store(struct device *dev, struct device_attribute *attr,
 				goto unlock;
 		}
 
-		trip->temperature = temp;
+		thermal_zone_set_trip_temp(tz, trip, temp);
 
-		thermal_zone_trip_updated(tz, trip);
+		__thermal_zone_device_update(tz, THERMAL_TRIP_CHANGED);
 	}
 
 unlock:
diff --git a/drivers/thermal/thermal_trip.c b/drivers/thermal/thermal_trip.c
index 581f1cd883e5..a1ad345c0741 100644
--- a/drivers/thermal/thermal_trip.c
+++ b/drivers/thermal/thermal_trip.c
@@ -152,7 +152,6 @@ int thermal_zone_trip_id(struct thermal_zone_device *tz,
 	 */
 	return trip - tz->trips;
 }
-
 void thermal_zone_trip_updated(struct thermal_zone_device *tz,
 			       const struct thermal_trip *trip)
 {
@@ -161,3 +160,16 @@ void thermal_zone_trip_updated(struct thermal_zone_device *tz,
 				      trip->hysteresis);
 	__thermal_zone_device_update(tz, THERMAL_TRIP_CHANGED);
 }
+
+void thermal_zone_set_trip_temp(struct thermal_zone_device *tz,
+				struct thermal_trip *trip, int temp)
+{
+	if (trip->temperature == temp)
+		return;
+
+	trip->temperature = temp;
+	thermal_notify_tz_trip_change(tz->id, thermal_zone_trip_id(tz, trip),
+				      trip->type, trip->temperature,
+				      trip->hysteresis);
+}
+EXPORT_SYMBOL_GPL(thermal_zone_set_trip_temp);
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index bedbaec9a42e..09f6eb82c191 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -291,6 +291,8 @@ int thermal_zone_for_each_trip(struct thermal_zone_device *tz,
 			       int (*cb)(struct thermal_trip *, void *),
 			       void *data);
 int thermal_zone_get_num_trips(struct thermal_zone_device *tz);
+void thermal_zone_set_trip_temp(struct thermal_zone_device *tz,
+				struct thermal_trip *trip, int temp);
 
 int thermal_zone_get_crit_temp(struct thermal_zone_device *tz, int *temp);
 
-- 
cgit v1.2.3


From d92e7a013ff33f4e0b31bbf768d0c85a8acefebf Mon Sep 17 00:00:00 2001
From: Alexander Stein <alexander.stein@ew.tq-group.com>
Date: Thu, 2 Nov 2023 10:50:47 +0100
Subject: media: v4l2-cci: Add support for little-endian encoded registers

Some sensors, e.g. Sony IMX290, are using little-endian registers. Add
support for those by encoding the endianness into Bit 20 of the register
address.

Fixes: af73323b9770 ("media: imx290: Convert to new CCI register access helpers")
Cc: stable@vger.kernel.org
Signed-off-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
[Sakari Ailus: Fixed commit message.]
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
---
 drivers/media/v4l2-core/v4l2-cci.c | 44 +++++++++++++++++++++++++++++++-------
 include/media/v4l2-cci.h           |  5 +++++
 2 files changed, 41 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/media/v4l2-core/v4l2-cci.c b/drivers/media/v4l2-core/v4l2-cci.c
index 3179160abde3..10005c80f43b 100644
--- a/drivers/media/v4l2-core/v4l2-cci.c
+++ b/drivers/media/v4l2-core/v4l2-cci.c
@@ -18,6 +18,7 @@
 
 int cci_read(struct regmap *map, u32 reg, u64 *val, int *err)
 {
+	bool little_endian;
 	unsigned int len;
 	u8 buf[8];
 	int ret;
@@ -25,6 +26,7 @@ int cci_read(struct regmap *map, u32 reg, u64 *val, int *err)
 	if (err && *err)
 		return *err;
 
+	little_endian = reg & CCI_REG_LE;
 	len = CCI_REG_WIDTH_BYTES(reg);
 	reg = CCI_REG_ADDR(reg);
 
@@ -40,16 +42,28 @@ int cci_read(struct regmap *map, u32 reg, u64 *val, int *err)
 		*val = buf[0];
 		break;
 	case 2:
-		*val = get_unaligned_be16(buf);
+		if (little_endian)
+			*val = get_unaligned_le16(buf);
+		else
+			*val = get_unaligned_be16(buf);
 		break;
 	case 3:
-		*val = get_unaligned_be24(buf);
+		if (little_endian)
+			*val = get_unaligned_le24(buf);
+		else
+			*val = get_unaligned_be24(buf);
 		break;
 	case 4:
-		*val = get_unaligned_be32(buf);
+		if (little_endian)
+			*val = get_unaligned_le32(buf);
+		else
+			*val = get_unaligned_be32(buf);
 		break;
 	case 8:
-		*val = get_unaligned_be64(buf);
+		if (little_endian)
+			*val = get_unaligned_le64(buf);
+		else
+			*val = get_unaligned_be64(buf);
 		break;
 	default:
 		dev_err(regmap_get_device(map), "Error invalid reg-width %u for reg 0x%04x\n",
@@ -68,6 +82,7 @@ EXPORT_SYMBOL_GPL(cci_read);
 
 int cci_write(struct regmap *map, u32 reg, u64 val, int *err)
 {
+	bool little_endian;
 	unsigned int len;
 	u8 buf[8];
 	int ret;
@@ -75,6 +90,7 @@ int cci_write(struct regmap *map, u32 reg, u64 val, int *err)
 	if (err && *err)
 		return *err;
 
+	little_endian = reg & CCI_REG_LE;
 	len = CCI_REG_WIDTH_BYTES(reg);
 	reg = CCI_REG_ADDR(reg);
 
@@ -83,16 +99,28 @@ int cci_write(struct regmap *map, u32 reg, u64 val, int *err)
 		buf[0] = val;
 		break;
 	case 2:
-		put_unaligned_be16(val, buf);
+		if (little_endian)
+			put_unaligned_le16(val, buf);
+		else
+			put_unaligned_be16(val, buf);
 		break;
 	case 3:
-		put_unaligned_be24(val, buf);
+		if (little_endian)
+			put_unaligned_le24(val, buf);
+		else
+			put_unaligned_be24(val, buf);
 		break;
 	case 4:
-		put_unaligned_be32(val, buf);
+		if (little_endian)
+			put_unaligned_le32(val, buf);
+		else
+			put_unaligned_be32(val, buf);
 		break;
 	case 8:
-		put_unaligned_be64(val, buf);
+		if (little_endian)
+			put_unaligned_le64(val, buf);
+		else
+			put_unaligned_be64(val, buf);
 		break;
 	default:
 		dev_err(regmap_get_device(map), "Error invalid reg-width %u for reg 0x%04x\n",
diff --git a/include/media/v4l2-cci.h b/include/media/v4l2-cci.h
index 406772a4e32e..4e96e90ee636 100644
--- a/include/media/v4l2-cci.h
+++ b/include/media/v4l2-cci.h
@@ -43,12 +43,17 @@ struct cci_reg_sequence {
 #define CCI_REG_WIDTH_BYTES(x)		FIELD_GET(CCI_REG_WIDTH_MASK, x)
 #define CCI_REG_WIDTH(x)		(CCI_REG_WIDTH_BYTES(x) << 3)
 #define CCI_REG_ADDR(x)			FIELD_GET(CCI_REG_ADDR_MASK, x)
+#define CCI_REG_LE			BIT(20)
 
 #define CCI_REG8(x)			((1 << CCI_REG_WIDTH_SHIFT) | (x))
 #define CCI_REG16(x)			((2 << CCI_REG_WIDTH_SHIFT) | (x))
 #define CCI_REG24(x)			((3 << CCI_REG_WIDTH_SHIFT) | (x))
 #define CCI_REG32(x)			((4 << CCI_REG_WIDTH_SHIFT) | (x))
 #define CCI_REG64(x)			((8 << CCI_REG_WIDTH_SHIFT) | (x))
+#define CCI_REG16_LE(x)			(CCI_REG_LE | (2U << CCI_REG_WIDTH_SHIFT) | (x))
+#define CCI_REG24_LE(x)			(CCI_REG_LE | (3U << CCI_REG_WIDTH_SHIFT) | (x))
+#define CCI_REG32_LE(x)			(CCI_REG_LE | (4U << CCI_REG_WIDTH_SHIFT) | (x))
+#define CCI_REG64_LE(x)			(CCI_REG_LE | (8U << CCI_REG_WIDTH_SHIFT) | (x))
 
 /**
  * cci_read() - Read a value from a single CCI register
-- 
cgit v1.2.3


From ad6534c626fedd818718d76c36d69c7d8e7b61cc Mon Sep 17 00:00:00 2001
From: Shuai Xue <xueshuai@linux.alibaba.com>
Date: Fri, 8 Dec 2023 10:56:49 +0800
Subject: PCI: Add Alibaba Vendor ID to linux/pci_ids.h

The Alibaba Vendor ID (0x1ded) is now used by Alibaba elasticRDMA ("erdma")
and will be shared with the upcoming PCIe PMU ("dwc_pcie_pmu"). Move the
Vendor ID to linux/pci_ids.h so that it can shared by several drivers
later.

Signed-off-by: Shuai Xue <xueshuai@linux.alibaba.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>	# pci_ids.h
Tested-by: Ilkka Koskinen <ilkka@os.amperecomputing.com>
Link: https://lore.kernel.org/r/20231208025652.87192-3-xueshuai@linux.alibaba.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/infiniband/hw/erdma/erdma_hw.h | 2 --
 include/linux/pci_ids.h                | 2 ++
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/erdma/erdma_hw.h b/drivers/infiniband/hw/erdma/erdma_hw.h
index 9d316fdc6f9a..a155519a862f 100644
--- a/drivers/infiniband/hw/erdma/erdma_hw.h
+++ b/drivers/infiniband/hw/erdma/erdma_hw.h
@@ -11,8 +11,6 @@
 #include <linux/types.h>
 
 /* PCIe device related definition. */
-#define PCI_VENDOR_ID_ALIBABA 0x1ded
-
 #define ERDMA_PCI_WIDTH 64
 #define ERDMA_FUNC_BAR 0
 #define ERDMA_MISX_BAR 2
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 275799b5f535..844ffdac8d7d 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2605,6 +2605,8 @@
 #define PCI_VENDOR_ID_TEKRAM		0x1de1
 #define PCI_DEVICE_ID_TEKRAM_DC290	0xdc29
 
+#define PCI_VENDOR_ID_ALIBABA		0x1ded
+
 #define PCI_VENDOR_ID_TEHUTI		0x1fc9
 #define PCI_DEVICE_ID_TEHUTI_3009	0x3009
 #define PCI_DEVICE_ID_TEHUTI_3010	0x3010
-- 
cgit v1.2.3


From ac16087134b837d42b75bb1c741070b6c142f258 Mon Sep 17 00:00:00 2001
From: Shuai Xue <xueshuai@linux.alibaba.com>
Date: Fri, 8 Dec 2023 10:56:50 +0800
Subject: PCI: Move pci_clear_and_set_dword() helper to PCI header

The clear and set pattern is commonly used for accessing PCI config,
move the helper pci_clear_and_set_dword() from aspm.c into PCI header.
In addition, rename to pci_clear_and_set_config_dword() to retain the
"config" information and match the other accessors.

No functional change intended.

Signed-off-by: Shuai Xue <xueshuai@linux.alibaba.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Tested-by: Ilkka Koskinen <ilkka@os.amperecomputing.com>
Link: https://lore.kernel.org/r/20231208025652.87192-4-xueshuai@linux.alibaba.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/pci/access.c    | 12 +++++++++
 drivers/pci/pcie/aspm.c | 65 +++++++++++++++++++++++--------------------------
 include/linux/pci.h     |  2 ++
 3 files changed, 44 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/access.c b/drivers/pci/access.c
index 6554a2e89d36..6449056b57dd 100644
--- a/drivers/pci/access.c
+++ b/drivers/pci/access.c
@@ -598,3 +598,15 @@ int pci_write_config_dword(const struct pci_dev *dev, int where,
 	return pci_bus_write_config_dword(dev->bus, dev->devfn, where, val);
 }
 EXPORT_SYMBOL(pci_write_config_dword);
+
+void pci_clear_and_set_config_dword(const struct pci_dev *dev, int pos,
+				    u32 clear, u32 set)
+{
+	u32 val;
+
+	pci_read_config_dword(dev, pos, &val);
+	val &= ~clear;
+	val |= set;
+	pci_write_config_dword(dev, pos, val);
+}
+EXPORT_SYMBOL(pci_clear_and_set_config_dword);
diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index 50b04ae5c394..a720a8e3ced2 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -426,17 +426,6 @@ static void pcie_aspm_check_latency(struct pci_dev *endpoint)
 	}
 }
 
-static void pci_clear_and_set_dword(struct pci_dev *pdev, int pos,
-				    u32 clear, u32 set)
-{
-	u32 val;
-
-	pci_read_config_dword(pdev, pos, &val);
-	val &= ~clear;
-	val |= set;
-	pci_write_config_dword(pdev, pos, val);
-}
-
 /* Calculate L1.2 PM substate timing parameters */
 static void aspm_calc_l12_info(struct pcie_link_state *link,
 				u32 parent_l1ss_cap, u32 child_l1ss_cap)
@@ -501,10 +490,12 @@ static void aspm_calc_l12_info(struct pcie_link_state *link,
 	cl1_2_enables = cctl1 & PCI_L1SS_CTL1_L1_2_MASK;
 
 	if (pl1_2_enables || cl1_2_enables) {
-		pci_clear_and_set_dword(child, child->l1ss + PCI_L1SS_CTL1,
-					PCI_L1SS_CTL1_L1_2_MASK, 0);
-		pci_clear_and_set_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
-					PCI_L1SS_CTL1_L1_2_MASK, 0);
+		pci_clear_and_set_config_dword(child,
+					       child->l1ss + PCI_L1SS_CTL1,
+					       PCI_L1SS_CTL1_L1_2_MASK, 0);
+		pci_clear_and_set_config_dword(parent,
+					       parent->l1ss + PCI_L1SS_CTL1,
+					       PCI_L1SS_CTL1_L1_2_MASK, 0);
 	}
 
 	/* Program T_POWER_ON times in both ports */
@@ -512,22 +503,26 @@ static void aspm_calc_l12_info(struct pcie_link_state *link,
 	pci_write_config_dword(child, child->l1ss + PCI_L1SS_CTL2, ctl2);
 
 	/* Program Common_Mode_Restore_Time in upstream device */
-	pci_clear_and_set_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
-				PCI_L1SS_CTL1_CM_RESTORE_TIME, ctl1);
+	pci_clear_and_set_config_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
+				       PCI_L1SS_CTL1_CM_RESTORE_TIME, ctl1);
 
 	/* Program LTR_L1.2_THRESHOLD time in both ports */
-	pci_clear_and_set_dword(parent,	parent->l1ss + PCI_L1SS_CTL1,
-				PCI_L1SS_CTL1_LTR_L12_TH_VALUE |
-				PCI_L1SS_CTL1_LTR_L12_TH_SCALE, ctl1);
-	pci_clear_and_set_dword(child, child->l1ss + PCI_L1SS_CTL1,
-				PCI_L1SS_CTL1_LTR_L12_TH_VALUE |
-				PCI_L1SS_CTL1_LTR_L12_TH_SCALE, ctl1);
+	pci_clear_and_set_config_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
+				       PCI_L1SS_CTL1_LTR_L12_TH_VALUE |
+				       PCI_L1SS_CTL1_LTR_L12_TH_SCALE,
+				       ctl1);
+	pci_clear_and_set_config_dword(child, child->l1ss + PCI_L1SS_CTL1,
+				       PCI_L1SS_CTL1_LTR_L12_TH_VALUE |
+				       PCI_L1SS_CTL1_LTR_L12_TH_SCALE,
+				       ctl1);
 
 	if (pl1_2_enables || cl1_2_enables) {
-		pci_clear_and_set_dword(parent, parent->l1ss + PCI_L1SS_CTL1, 0,
-					pl1_2_enables);
-		pci_clear_and_set_dword(child, child->l1ss + PCI_L1SS_CTL1, 0,
-					cl1_2_enables);
+		pci_clear_and_set_config_dword(parent,
+					       parent->l1ss + PCI_L1SS_CTL1, 0,
+					       pl1_2_enables);
+		pci_clear_and_set_config_dword(child,
+					       child->l1ss + PCI_L1SS_CTL1, 0,
+					       cl1_2_enables);
 	}
 }
 
@@ -687,10 +682,10 @@ static void pcie_config_aspm_l1ss(struct pcie_link_state *link, u32 state)
 	 */
 
 	/* Disable all L1 substates */
-	pci_clear_and_set_dword(child, child->l1ss + PCI_L1SS_CTL1,
-				PCI_L1SS_CTL1_L1SS_MASK, 0);
-	pci_clear_and_set_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
-				PCI_L1SS_CTL1_L1SS_MASK, 0);
+	pci_clear_and_set_config_dword(child, child->l1ss + PCI_L1SS_CTL1,
+				       PCI_L1SS_CTL1_L1SS_MASK, 0);
+	pci_clear_and_set_config_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
+				       PCI_L1SS_CTL1_L1SS_MASK, 0);
 	/*
 	 * If needed, disable L1, and it gets enabled later
 	 * in pcie_config_aspm_link().
@@ -713,10 +708,10 @@ static void pcie_config_aspm_l1ss(struct pcie_link_state *link, u32 state)
 		val |= PCI_L1SS_CTL1_PCIPM_L1_2;
 
 	/* Enable what we need to enable */
-	pci_clear_and_set_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
-				PCI_L1SS_CTL1_L1SS_MASK, val);
-	pci_clear_and_set_dword(child, child->l1ss + PCI_L1SS_CTL1,
-				PCI_L1SS_CTL1_L1SS_MASK, val);
+	pci_clear_and_set_config_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
+				       PCI_L1SS_CTL1_L1SS_MASK, val);
+	pci_clear_and_set_config_dword(child, child->l1ss + PCI_L1SS_CTL1,
+				       PCI_L1SS_CTL1_L1SS_MASK, val);
 }
 
 static void pcie_config_aspm_dev(struct pci_dev *pdev, u32 val)
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 60ca768bc867..268c4bd98ef3 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1239,6 +1239,8 @@ int pci_read_config_dword(const struct pci_dev *dev, int where, u32 *val);
 int pci_write_config_byte(const struct pci_dev *dev, int where, u8 val);
 int pci_write_config_word(const struct pci_dev *dev, int where, u16 val);
 int pci_write_config_dword(const struct pci_dev *dev, int where, u32 val);
+void pci_clear_and_set_config_dword(const struct pci_dev *dev, int pos,
+				    u32 clear, u32 set);
 
 int pcie_capability_read_word(struct pci_dev *dev, int pos, u16 *val);
 int pcie_capability_read_dword(struct pci_dev *dev, int pos, u32 *val);
-- 
cgit v1.2.3


From dc7226acacc6502291446f9e33cf96246ec49a30 Mon Sep 17 00:00:00 2001
From: Andy Yan <andy.yan@rock-chips.com>
Date: Mon, 11 Dec 2023 19:59:07 +0800
Subject: dt-bindings: rockchip,vop2: Add more endpoint definition

There are 2 HDMI, 2 DP, 2 eDP on rk3588, so add
corresponding endpoint definition for it.

Signed-off-by: Andy Yan <andy.yan@rock-chips.com>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Link: https://patchwork.freedesktop.org/patch/msgid/20231211115907.1785377-1-andyshrk@163.com
---
 include/dt-bindings/soc/rockchip,vop2.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/dt-bindings/soc/rockchip,vop2.h b/include/dt-bindings/soc/rockchip,vop2.h
index 6e66a802b96a..668f199df9f0 100644
--- a/include/dt-bindings/soc/rockchip,vop2.h
+++ b/include/dt-bindings/soc/rockchip,vop2.h
@@ -10,5 +10,9 @@
 #define ROCKCHIP_VOP2_EP_LVDS0	5
 #define ROCKCHIP_VOP2_EP_MIPI1	6
 #define ROCKCHIP_VOP2_EP_LVDS1	7
+#define ROCKCHIP_VOP2_EP_HDMI1	8
+#define ROCKCHIP_VOP2_EP_EDP1	9
+#define ROCKCHIP_VOP2_EP_DP0	10
+#define ROCKCHIP_VOP2_EP_DP1	11
 
 #endif /* __DT_BINDINGS_ROCKCHIP_VOP2_H */
-- 
cgit v1.2.3


From c4c5391adae2c5a328232bb4fecd9510310b2fdf Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 12 Dec 2023 20:39:25 -0800
Subject: drm/fourcc: fix spelling/typos

Correct spelling mistakes that were identified by codespell.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: David Airlie <airlied@gmail.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Maxime Ripard <mripard@kernel.org>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Maxime Ripard <mripard@kernel.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20231213043925.13852-1-rdunlap@infradead.org
---
 include/uapi/drm/drm_fourcc.h | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h
index 3151f1fc7ebb..84d502e42961 100644
--- a/include/uapi/drm/drm_fourcc.h
+++ b/include/uapi/drm/drm_fourcc.h
@@ -54,7 +54,7 @@ extern "C" {
  * Format modifiers may change any property of the buffer, including the number
  * of planes and/or the required allocation size. Format modifiers are
  * vendor-namespaced, and as such the relationship between a fourcc code and a
- * modifier is specific to the modifer being used. For example, some modifiers
+ * modifier is specific to the modifier being used. For example, some modifiers
  * may preserve meaning - such as number of planes - from the fourcc code,
  * whereas others may not.
  *
@@ -79,7 +79,7 @@ extern "C" {
  *   format.
  * - Higher-level programs interfacing with KMS/GBM/EGL/Vulkan/etc: these users
  *   see modifiers as opaque tokens they can check for equality and intersect.
- *   These users musn't need to know to reason about the modifier value
+ *   These users mustn't need to know to reason about the modifier value
  *   (i.e. they are not expected to extract information out of the modifier).
  *
  * Vendors should document their modifier usage in as much detail as
@@ -540,7 +540,7 @@ extern "C" {
  * This is a tiled layout using 4Kb tiles in row-major layout.
  * Within the tile pixels are laid out in 16 256 byte units / sub-tiles which
  * are arranged in four groups (two wide, two high) with column-major layout.
- * Each group therefore consits out of four 256 byte units, which are also laid
+ * Each group therefore consists out of four 256 byte units, which are also laid
  * out as 2x2 column-major.
  * 256 byte units are made out of four 64 byte blocks of pixels, producing
  * either a square block or a 2:1 unit.
@@ -1103,7 +1103,7 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier)
  */
 
 /*
- * The top 4 bits (out of the 56 bits alloted for specifying vendor specific
+ * The top 4 bits (out of the 56 bits allotted for specifying vendor specific
  * modifiers) denote the category for modifiers. Currently we have three
  * categories of modifiers ie AFBC, MISC and AFRC. We can have a maximum of
  * sixteen different categories.
@@ -1419,7 +1419,7 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier)
  * Amlogic FBC Memory Saving mode
  *
  * Indicates the storage is packed when pixel size is multiple of word
- * boudaries, i.e. 8bit should be stored in this mode to save allocation
+ * boundaries, i.e. 8bit should be stored in this mode to save allocation
  * memory.
  *
  * This mode reduces body layout to 3072 bytes per 64x32 superblock with
-- 
cgit v1.2.3


From 37c476d68d29051f333944bd784d1054b495c5a8 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 12 Dec 2023 20:32:26 -0800
Subject: drm/drm_modeset_helper_vtables.h: fix typos/spellos

Fix spelling problems as identified by codespell.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: David Airlie <airlied@gmail.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Maxime Ripard <mripard@kernel.org>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Maxime Ripard <mripard@kernel.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20231213043226.10046-1-rdunlap@infradead.org
---
 include/drm/drm_modeset_helper_vtables.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/drm/drm_modeset_helper_vtables.h b/include/drm/drm_modeset_helper_vtables.h
index a33cf7488737..881b03e4dc28 100644
--- a/include/drm/drm_modeset_helper_vtables.h
+++ b/include/drm/drm_modeset_helper_vtables.h
@@ -134,7 +134,7 @@ struct drm_crtc_helper_funcs {
 	 * Since this function is both called from the check phase of an atomic
 	 * commit, and the mode validation in the probe paths it is not allowed
 	 * to look at anything else but the passed-in mode, and validate it
-	 * against configuration-invariant hardward constraints. Any further
+	 * against configuration-invariant hardware constraints. Any further
 	 * limits which depend upon the configuration can only be checked in
 	 * @mode_fixup or @atomic_check.
 	 *
@@ -550,7 +550,7 @@ struct drm_encoder_helper_funcs {
 	 * Since this function is both called from the check phase of an atomic
 	 * commit, and the mode validation in the probe paths it is not allowed
 	 * to look at anything else but the passed-in mode, and validate it
-	 * against configuration-invariant hardward constraints. Any further
+	 * against configuration-invariant hardware constraints. Any further
 	 * limits which depend upon the configuration can only be checked in
 	 * @mode_fixup or @atomic_check.
 	 *
@@ -1474,7 +1474,7 @@ struct drm_mode_config_helper_funcs {
 	 * swapped into the various state pointers. The passed in state
 	 * therefore contains copies of the old/previous state. This hook should
 	 * commit the new state into hardware. Note that the helpers have
-	 * already waited for preceeding atomic commits and fences, but drivers
+	 * already waited for preceding atomic commits and fences, but drivers
 	 * can add more waiting calls at the start of their implementation, e.g.
 	 * to wait for driver-internal request for implicit syncing, before
 	 * starting to commit the update to the hardware.
-- 
cgit v1.2.3


From 9567dab3a8cb4dfc4b0382c2678ad01bff13a3bf Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 12 Dec 2023 20:41:07 -0800
Subject: drm/uapi: drm_mode.h: fix spellos and grammar

Correct spellos reported by codespell.
Fix some grammar (as 's' to a few words).

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: David Airlie <airlied@gmail.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Maxime Ripard <mripard@kernel.org>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Maxime Ripard <mripard@kernel.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20231213044107.29214-1-rdunlap@infradead.org
---
 include/uapi/drm/drm_mode.h | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h
index 95630f170110..aee3d40c96f0 100644
--- a/include/uapi/drm/drm_mode.h
+++ b/include/uapi/drm/drm_mode.h
@@ -36,10 +36,10 @@ extern "C" {
 /**
  * DOC: overview
  *
- * DRM exposes many UAPI and structure definition to have a consistent
- * and standardized interface with user.
+ * DRM exposes many UAPI and structure definitions to have a consistent
+ * and standardized interface with users.
  * Userspace can refer to these structure definitions and UAPI formats
- * to communicate to driver
+ * to communicate to drivers.
  */
 
 #define DRM_CONNECTOR_NAME_LEN	32
@@ -540,7 +540,7 @@ struct drm_mode_get_connector {
 /* the PROP_ATOMIC flag is used to hide properties from userspace that
  * is not aware of atomic properties.  This is mostly to work around
  * older userspace (DDX drivers) that read/write each prop they find,
- * witout being aware that this could be triggering a lengthy modeset.
+ * without being aware that this could be triggering a lengthy modeset.
  */
 #define DRM_MODE_PROP_ATOMIC        0x80000000
 
@@ -664,7 +664,7 @@ struct drm_mode_fb_cmd {
 };
 
 #define DRM_MODE_FB_INTERLACED	(1<<0) /* for interlaced framebuffers */
-#define DRM_MODE_FB_MODIFIERS	(1<<1) /* enables ->modifer[] */
+#define DRM_MODE_FB_MODIFIERS	(1<<1) /* enables ->modifier[] */
 
 /**
  * struct drm_mode_fb_cmd2 - Frame-buffer metadata.
@@ -881,8 +881,8 @@ struct hdr_metadata_infoframe {
 	 * These are coded as unsigned 16-bit values in units of
 	 * 0.00002, where 0x0000 represents zero and 0xC350
 	 * represents 1.0000.
-	 * @display_primaries.x: X cordinate of color primary.
-	 * @display_primaries.y: Y cordinate of color primary.
+	 * @display_primaries.x: X coordinate of color primary.
+	 * @display_primaries.y: Y coordinate of color primary.
 	 */
 	struct {
 		__u16 x, y;
@@ -892,8 +892,8 @@ struct hdr_metadata_infoframe {
 	 * These are coded as unsigned 16-bit values in units of
 	 * 0.00002, where 0x0000 represents zero and 0xC350
 	 * represents 1.0000.
-	 * @white_point.x: X cordinate of whitepoint of color primary.
-	 * @white_point.y: Y cordinate of whitepoint of color primary.
+	 * @white_point.x: X coordinate of whitepoint of color primary.
+	 * @white_point.y: Y coordinate of whitepoint of color primary.
 	 */
 	struct {
 		__u16 x, y;
-- 
cgit v1.2.3


From 08e5c36410ca5cb14237e47e6dfe3fde02e0f275 Mon Sep 17 00:00:00 2001
From: Tomi Valkeinen <tomi.valkeinen@ideasonboard.com>
Date: Wed, 13 Dec 2023 17:00:03 +0200
Subject: media: v4l: subdev: Move out subdev state lock macros outside
 CONFIG_MEDIA_CONTROLLER

The subdev state locking macros and macros to get the active state are
currently behind CONFIG_MEDIA_CONTROLLER. This makes sense, as there can
be no subdev state without MC.

However, we have code paths common to MC and non-MC cases which call
subdev operations that have subdev state as a parameter. In the non-MC
case the state parameter would always be NULL.

Thus it makes sense to allow, e.g.:

v4l2_subdev_call_state_active(sd, pad, get_fmt, fmt)

which for non-MC case would call the subdev passing NULL as the state.

This currently fails:
https://lore.kernel.org/oe-kbuild-all/202312061101.PLrz5NnJ-lkp@intel.com/

Fix the issue by moving the related macros to be outside
CONFIG_MEDIA_CONTROLLER. The v4l2_subdev_lock_state() and
v4l2_subdev_unlock_state() macros will crash if given NULL as the state,
but the other macros behave correctly even when there's no active state,
and they will only call the lock/unlock macros if there is a state.

An alternative fix would be to make another version of
v4l2_subdev_call_state_try() with ifdefs, which would not use any state
macros and would always pass NULL as the state. But having two version
of a macro/function is always more confusing than having just one, so I
went this way.

So, this fixes the v4l2_subdev_call_state_active() macro. But we also
have v4l2_subdev_call_state_try(). It would be possible to fix that
macro by additionally creating "no-op" variants of the state alloc and
free functions. However, v4l2_subdev_call_state_try() is only used by a
single driver (stm32-dcmi), which selects MC, and the macro is supposed
to be removed as soon as the users have been converted away from the
macro. Thus I have not touched the state alloc/free functions, and I
think it makes sense to keep alloc/free functions available only if
there's actually something that can be allocated or freed.

Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ideasonboard.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Reviewed-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Link: https://lore.kernel.org/r/20231208-v4l2-state-mc-fix-v1-1-a0c8162557c6@ideasonboard.com
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
---
 include/media/v4l2-subdev.h | 166 ++++++++++++++++++++++----------------------
 1 file changed, 83 insertions(+), 83 deletions(-)

(limited to 'include')

diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h
index 8b08f6640dee..61024a74ce38 100644
--- a/include/media/v4l2-subdev.h
+++ b/include/media/v4l2-subdev.h
@@ -1311,89 +1311,6 @@ int __v4l2_subdev_init_finalize(struct v4l2_subdev *sd, const char *name,
  */
 void v4l2_subdev_cleanup(struct v4l2_subdev *sd);
 
-/**
- * v4l2_subdev_lock_state() - Locks the subdev state
- * @state: The subdevice state
- *
- * Locks the given subdev state.
- *
- * The state must be unlocked with v4l2_subdev_unlock_state() after use.
- */
-static inline void v4l2_subdev_lock_state(struct v4l2_subdev_state *state)
-{
-	mutex_lock(state->lock);
-}
-
-/**
- * v4l2_subdev_unlock_state() - Unlocks the subdev state
- * @state: The subdevice state
- *
- * Unlocks the given subdev state.
- */
-static inline void v4l2_subdev_unlock_state(struct v4l2_subdev_state *state)
-{
-	mutex_unlock(state->lock);
-}
-
-/**
- * v4l2_subdev_get_unlocked_active_state() - Checks that the active subdev state
- *					     is unlocked and returns it
- * @sd: The subdevice
- *
- * Returns the active state for the subdevice, or NULL if the subdev does not
- * support active state. If the state is not NULL, calls
- * lockdep_assert_not_held() to issue a warning if the state is locked.
- *
- * This function is to be used e.g. when getting the active state for the sole
- * purpose of passing it forward, without accessing the state fields.
- */
-static inline struct v4l2_subdev_state *
-v4l2_subdev_get_unlocked_active_state(struct v4l2_subdev *sd)
-{
-	if (sd->active_state)
-		lockdep_assert_not_held(sd->active_state->lock);
-	return sd->active_state;
-}
-
-/**
- * v4l2_subdev_get_locked_active_state() - Checks that the active subdev state
- *					   is locked and returns it
- *
- * @sd: The subdevice
- *
- * Returns the active state for the subdevice, or NULL if the subdev does not
- * support active state. If the state is not NULL, calls lockdep_assert_held()
- * to issue a warning if the state is not locked.
- *
- * This function is to be used when the caller knows that the active state is
- * already locked.
- */
-static inline struct v4l2_subdev_state *
-v4l2_subdev_get_locked_active_state(struct v4l2_subdev *sd)
-{
-	if (sd->active_state)
-		lockdep_assert_held(sd->active_state->lock);
-	return sd->active_state;
-}
-
-/**
- * v4l2_subdev_lock_and_get_active_state() - Locks and returns the active subdev
- *					     state for the subdevice
- * @sd: The subdevice
- *
- * Returns the locked active state for the subdevice, or NULL if the subdev
- * does not support active state.
- *
- * The state must be unlocked with v4l2_subdev_unlock_state() after use.
- */
-static inline struct v4l2_subdev_state *
-v4l2_subdev_lock_and_get_active_state(struct v4l2_subdev *sd)
-{
-	if (sd->active_state)
-		v4l2_subdev_lock_state(sd->active_state);
-	return sd->active_state;
-}
-
 /*
  * A macro to generate the macro or function name for sub-devices state access
  * wrapper macros below.
@@ -1738,6 +1655,89 @@ int v4l2_subdev_s_stream_helper(struct v4l2_subdev *sd, int enable);
 
 #endif /* CONFIG_MEDIA_CONTROLLER */
 
+/**
+ * v4l2_subdev_lock_state() - Locks the subdev state
+ * @state: The subdevice state
+ *
+ * Locks the given subdev state.
+ *
+ * The state must be unlocked with v4l2_subdev_unlock_state() after use.
+ */
+static inline void v4l2_subdev_lock_state(struct v4l2_subdev_state *state)
+{
+	mutex_lock(state->lock);
+}
+
+/**
+ * v4l2_subdev_unlock_state() - Unlocks the subdev state
+ * @state: The subdevice state
+ *
+ * Unlocks the given subdev state.
+ */
+static inline void v4l2_subdev_unlock_state(struct v4l2_subdev_state *state)
+{
+	mutex_unlock(state->lock);
+}
+
+/**
+ * v4l2_subdev_get_unlocked_active_state() - Checks that the active subdev state
+ *					     is unlocked and returns it
+ * @sd: The subdevice
+ *
+ * Returns the active state for the subdevice, or NULL if the subdev does not
+ * support active state. If the state is not NULL, calls
+ * lockdep_assert_not_held() to issue a warning if the state is locked.
+ *
+ * This function is to be used e.g. when getting the active state for the sole
+ * purpose of passing it forward, without accessing the state fields.
+ */
+static inline struct v4l2_subdev_state *
+v4l2_subdev_get_unlocked_active_state(struct v4l2_subdev *sd)
+{
+	if (sd->active_state)
+		lockdep_assert_not_held(sd->active_state->lock);
+	return sd->active_state;
+}
+
+/**
+ * v4l2_subdev_get_locked_active_state() - Checks that the active subdev state
+ *					   is locked and returns it
+ *
+ * @sd: The subdevice
+ *
+ * Returns the active state for the subdevice, or NULL if the subdev does not
+ * support active state. If the state is not NULL, calls lockdep_assert_held()
+ * to issue a warning if the state is not locked.
+ *
+ * This function is to be used when the caller knows that the active state is
+ * already locked.
+ */
+static inline struct v4l2_subdev_state *
+v4l2_subdev_get_locked_active_state(struct v4l2_subdev *sd)
+{
+	if (sd->active_state)
+		lockdep_assert_held(sd->active_state->lock);
+	return sd->active_state;
+}
+
+/**
+ * v4l2_subdev_lock_and_get_active_state() - Locks and returns the active subdev
+ *					     state for the subdevice
+ * @sd: The subdevice
+ *
+ * Returns the locked active state for the subdevice, or NULL if the subdev
+ * does not support active state.
+ *
+ * The state must be unlocked with v4l2_subdev_unlock_state() after use.
+ */
+static inline struct v4l2_subdev_state *
+v4l2_subdev_lock_and_get_active_state(struct v4l2_subdev *sd)
+{
+	if (sd->active_state)
+		v4l2_subdev_lock_state(sd->active_state);
+	return sd->active_state;
+}
+
 /**
  * v4l2_subdev_init - initializes the sub-device struct
  *
-- 
cgit v1.2.3


From 287fe160834acdf9c44e5b73676180c6dbdedf76 Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Date: Wed, 13 Dec 2023 17:00:04 +0200
Subject: media: v4l2-subdev: Turn .[gs]_frame_interval into pad operations

The subdev .[gs]_frame_interval are video operations, but they operate
on pads (and even on streams). Not only is this confusing, it causes
practical issues for drivers as the operations don't receive a subdev
state pointer, requiring manual state handling.

To improve the situation, turn the operations into pad operations, and
extend them to receive a state pointer like other pad operations.

While at it, rename the operations to .[gs]et_frame_interval at the same
time to match the naming scheme of other pad operations. This isn't
strictly necessary, but given that all drivers using those operations
need to be modified, handling the rename separately would generate more
churn for very little gain (if at all).

Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Reviewed-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de> # for imx-media
Reviewed-by: Luca Ceresoli <luca.ceresoli@bootlin.com> # for tegra-video
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
---
 drivers/media/i2c/adv7180.c                        |  7 +--
 drivers/media/i2c/alvium-csi2.c                    | 11 ++--
 drivers/media/i2c/et8ek8/et8ek8_driver.c           |  6 ++-
 drivers/media/i2c/imx214.c                         |  9 ++--
 drivers/media/i2c/imx274.c                         | 48 ++++++-----------
 drivers/media/i2c/max9286.c                        | 14 ++---
 drivers/media/i2c/mt9m111.c                        | 14 ++---
 drivers/media/i2c/mt9m114.c                        | 14 ++---
 drivers/media/i2c/mt9v011.c                        | 18 +++----
 drivers/media/i2c/mt9v111.c                        | 16 +++---
 drivers/media/i2c/ov2680.c                         |  7 +--
 drivers/media/i2c/ov5640.c                         | 16 +++---
 drivers/media/i2c/ov5648.c                         | 59 ++++++++++----------
 drivers/media/i2c/ov5693.c                         |  7 +--
 drivers/media/i2c/ov6650.c                         | 16 +++---
 drivers/media/i2c/ov7251.c                         |  6 ++-
 drivers/media/i2c/ov7670.c                         | 18 +++----
 drivers/media/i2c/ov772x.c                         | 14 ++---
 drivers/media/i2c/ov7740.c                         | 40 +++++---------
 drivers/media/i2c/ov8865.c                         | 51 +++++++++---------
 drivers/media/i2c/ov9650.c                         | 14 ++---
 drivers/media/i2c/s5c73m3/s5c73m3-core.c           | 14 ++---
 drivers/media/i2c/s5k5baf.c                        | 20 +++----
 drivers/media/i2c/thp7312.c                        | 22 +++-----
 drivers/media/i2c/tvp514x.c                        | 29 +++-------
 drivers/media/usb/em28xx/em28xx-video.c            |  6 ++-
 drivers/media/v4l2-core/v4l2-common.c              |  8 +--
 drivers/media/v4l2-core/v4l2-subdev.c              | 63 ++++++++++++----------
 drivers/staging/media/atomisp/i2c/atomisp-gc0310.c |  7 +--
 drivers/staging/media/atomisp/i2c/atomisp-gc2235.c |  7 +--
 .../staging/media/atomisp/i2c/atomisp-mt9m114.c    |  7 +--
 drivers/staging/media/atomisp/i2c/atomisp-ov2722.c |  7 +--
 drivers/staging/media/atomisp/pci/atomisp_cmd.c    |  4 +-
 drivers/staging/media/atomisp/pci/atomisp_ioctl.c  |  4 +-
 drivers/staging/media/imx/imx-ic-prp.c             | 14 ++---
 drivers/staging/media/imx/imx-ic-prpencvf.c        | 14 ++---
 drivers/staging/media/imx/imx-media-capture.c      |  6 ++-
 drivers/staging/media/imx/imx-media-csi.c          | 14 ++---
 drivers/staging/media/imx/imx-media-vdic.c         | 14 ++---
 drivers/staging/media/tegra-video/csi.c            |  9 ++--
 include/media/v4l2-common.h                        |  4 +-
 include/media/v4l2-subdev.h                        | 22 ++++----
 42 files changed, 352 insertions(+), 348 deletions(-)

(limited to 'include')

diff --git a/drivers/media/i2c/adv7180.c b/drivers/media/i2c/adv7180.c
index e10811cce801..7ed86030fb5c 100644
--- a/drivers/media/i2c/adv7180.c
+++ b/drivers/media/i2c/adv7180.c
@@ -463,8 +463,9 @@ static int adv7180_g_std(struct v4l2_subdev *sd, v4l2_std_id *norm)
 	return 0;
 }
 
-static int adv7180_g_frame_interval(struct v4l2_subdev *sd,
-				    struct v4l2_subdev_frame_interval *fi)
+static int adv7180_get_frame_interval(struct v4l2_subdev *sd,
+				      struct v4l2_subdev_state *sd_state,
+				      struct v4l2_subdev_frame_interval *fi)
 {
 	struct adv7180_state *state = to_state(sd);
 
@@ -913,7 +914,6 @@ static int adv7180_subscribe_event(struct v4l2_subdev *sd,
 static const struct v4l2_subdev_video_ops adv7180_video_ops = {
 	.s_std = adv7180_s_std,
 	.g_std = adv7180_g_std,
-	.g_frame_interval = adv7180_g_frame_interval,
 	.querystd = adv7180_querystd,
 	.g_input_status = adv7180_g_input_status,
 	.s_routing = adv7180_s_routing,
@@ -932,6 +932,7 @@ static const struct v4l2_subdev_pad_ops adv7180_pad_ops = {
 	.enum_mbus_code = adv7180_enum_mbus_code,
 	.set_fmt = adv7180_set_pad_format,
 	.get_fmt = adv7180_get_pad_format,
+	.get_frame_interval = adv7180_get_frame_interval,
 	.get_mbus_config = adv7180_get_mbus_config,
 };
 
diff --git a/drivers/media/i2c/alvium-csi2.c b/drivers/media/i2c/alvium-csi2.c
index c8827603eb23..a173abb0509f 100644
--- a/drivers/media/i2c/alvium-csi2.c
+++ b/drivers/media/i2c/alvium-csi2.c
@@ -1649,6 +1649,7 @@ static int alvium_hw_init(struct alvium_dev *alvium)
 /* --------------- Subdev Operations --------------- */
 
 static int alvium_g_frame_interval(struct v4l2_subdev *sd,
+				   struct v4l2_subdev_state *sd_state,
 				   struct v4l2_subdev_frame_interval *fi)
 {
 	struct alvium_dev *alvium = sd_to_alvium(sd);
@@ -1696,23 +1697,19 @@ static int alvium_set_frame_interval(struct alvium_dev *alvium,
 }
 
 static int alvium_s_frame_interval(struct v4l2_subdev *sd,
+				   struct v4l2_subdev_state *sd_state,
 				   struct v4l2_subdev_frame_interval *fi)
 {
 	struct alvium_dev *alvium = sd_to_alvium(sd);
-	struct v4l2_subdev_state *state;
 	int ret;
 
 	if (alvium->streaming)
 		return -EBUSY;
 
-	state = v4l2_subdev_lock_and_get_active_state(sd);
-
 	ret = alvium_set_frame_interval(alvium, fi);
 	if (!ret)
 		ret = alvium_set_frame_rate(alvium);
 
-	v4l2_subdev_unlock_state(state);
-
 	return ret;
 }
 
@@ -2238,8 +2235,6 @@ static const struct v4l2_subdev_core_ops alvium_core_ops = {
 };
 
 static const struct v4l2_subdev_video_ops alvium_video_ops = {
-	.g_frame_interval	= alvium_g_frame_interval,
-	.s_frame_interval	= alvium_s_frame_interval,
 	.s_stream		= alvium_s_stream,
 };
 
@@ -2249,6 +2244,8 @@ static const struct v4l2_subdev_pad_ops alvium_pad_ops = {
 	.set_fmt = alvium_set_fmt,
 	.get_selection = alvium_get_selection,
 	.set_selection = alvium_set_selection,
+	.get_frame_interval = alvium_g_frame_interval,
+	.set_frame_interval = alvium_s_frame_interval,
 };
 
 static const struct v4l2_subdev_internal_ops alvium_internal_ops = {
diff --git a/drivers/media/i2c/et8ek8/et8ek8_driver.c b/drivers/media/i2c/et8ek8/et8ek8_driver.c
index 63616dc5a02f..71fb5aebd3df 100644
--- a/drivers/media/i2c/et8ek8/et8ek8_driver.c
+++ b/drivers/media/i2c/et8ek8/et8ek8_driver.c
@@ -1046,6 +1046,7 @@ static int et8ek8_set_pad_format(struct v4l2_subdev *subdev,
 }
 
 static int et8ek8_get_frame_interval(struct v4l2_subdev *subdev,
+				     struct v4l2_subdev_state *sd_state,
 				     struct v4l2_subdev_frame_interval *fi)
 {
 	struct et8ek8_sensor *sensor = to_et8ek8_sensor(subdev);
@@ -1057,6 +1058,7 @@ static int et8ek8_get_frame_interval(struct v4l2_subdev *subdev,
 }
 
 static int et8ek8_set_frame_interval(struct v4l2_subdev *subdev,
+				     struct v4l2_subdev_state *sd_state,
 				     struct v4l2_subdev_frame_interval *fi)
 {
 	struct et8ek8_sensor *sensor = to_et8ek8_sensor(subdev);
@@ -1342,8 +1344,6 @@ static int et8ek8_close(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh)
 
 static const struct v4l2_subdev_video_ops et8ek8_video_ops = {
 	.s_stream = et8ek8_s_stream,
-	.g_frame_interval = et8ek8_get_frame_interval,
-	.s_frame_interval = et8ek8_set_frame_interval,
 };
 
 static const struct v4l2_subdev_core_ops et8ek8_core_ops = {
@@ -1356,6 +1356,8 @@ static const struct v4l2_subdev_pad_ops et8ek8_pad_ops = {
 	.enum_frame_interval = et8ek8_enum_frame_ival,
 	.get_fmt = et8ek8_get_pad_format,
 	.set_fmt = et8ek8_set_pad_format,
+	.get_frame_interval = et8ek8_get_frame_interval,
+	.set_frame_interval = et8ek8_set_frame_interval,
 };
 
 static const struct v4l2_subdev_ops et8ek8_ops = {
diff --git a/drivers/media/i2c/imx214.c b/drivers/media/i2c/imx214.c
index 00595a09e723..8e832a4e3544 100644
--- a/drivers/media/i2c/imx214.c
+++ b/drivers/media/i2c/imx214.c
@@ -901,8 +901,9 @@ err_rpm_put:
 	return ret;
 }
 
-static int imx214_g_frame_interval(struct v4l2_subdev *subdev,
-				   struct v4l2_subdev_frame_interval *fival)
+static int imx214_get_frame_interval(struct v4l2_subdev *subdev,
+				     struct v4l2_subdev_state *sd_state,
+				     struct v4l2_subdev_frame_interval *fival)
 {
 	fival->interval.numerator = 1;
 	fival->interval.denominator = IMX214_FPS;
@@ -934,8 +935,6 @@ static int imx214_enum_frame_interval(struct v4l2_subdev *subdev,
 
 static const struct v4l2_subdev_video_ops imx214_video_ops = {
 	.s_stream = imx214_s_stream,
-	.g_frame_interval = imx214_g_frame_interval,
-	.s_frame_interval = imx214_g_frame_interval,
 };
 
 static const struct v4l2_subdev_pad_ops imx214_subdev_pad_ops = {
@@ -945,6 +944,8 @@ static const struct v4l2_subdev_pad_ops imx214_subdev_pad_ops = {
 	.get_fmt = imx214_get_format,
 	.set_fmt = imx214_set_format,
 	.get_selection = imx214_get_selection,
+	.get_frame_interval = imx214_get_frame_interval,
+	.set_frame_interval = imx214_get_frame_interval,
 };
 
 static const struct v4l2_subdev_ops imx214_subdev_ops = {
diff --git a/drivers/media/i2c/imx274.c b/drivers/media/i2c/imx274.c
index 8dc11c9ec1ee..4040c642a36f 100644
--- a/drivers/media/i2c/imx274.c
+++ b/drivers/media/i2c/imx274.c
@@ -594,8 +594,8 @@ static int imx274_set_gain(struct stimx274 *priv, struct v4l2_ctrl *ctrl);
 static int imx274_set_exposure(struct stimx274 *priv, int val);
 static int imx274_set_vflip(struct stimx274 *priv, int val);
 static int imx274_set_test_pattern(struct stimx274 *priv, int val);
-static int imx274_set_frame_interval(struct stimx274 *priv,
-				     struct v4l2_fract frame_interval);
+static int __imx274_set_frame_interval(struct stimx274 *priv,
+				       struct v4l2_fract frame_interval);
 
 static inline void msleep_range(unsigned int delay_base)
 {
@@ -1327,17 +1327,9 @@ static int imx274_apply_trimming(struct stimx274 *imx274)
 	return err;
 }
 
-/**
- * imx274_g_frame_interval - Get the frame interval
- * @sd: Pointer to V4L2 Sub device structure
- * @fi: Pointer to V4l2 Sub device frame interval structure
- *
- * This function is used to get the frame interval.
- *
- * Return: 0 on success
- */
-static int imx274_g_frame_interval(struct v4l2_subdev *sd,
-				   struct v4l2_subdev_frame_interval *fi)
+static int imx274_get_frame_interval(struct v4l2_subdev *sd,
+				     struct v4l2_subdev_state *sd_state,
+				     struct v4l2_subdev_frame_interval *fi)
 {
 	struct stimx274 *imx274 = to_imx274(sd);
 
@@ -1349,17 +1341,9 @@ static int imx274_g_frame_interval(struct v4l2_subdev *sd,
 	return 0;
 }
 
-/**
- * imx274_s_frame_interval - Set the frame interval
- * @sd: Pointer to V4L2 Sub device structure
- * @fi: Pointer to V4l2 Sub device frame interval structure
- *
- * This function is used to set the frame intervavl.
- *
- * Return: 0 on success
- */
-static int imx274_s_frame_interval(struct v4l2_subdev *sd,
-				   struct v4l2_subdev_frame_interval *fi)
+static int imx274_set_frame_interval(struct v4l2_subdev *sd,
+				     struct v4l2_subdev_state *sd_state,
+				     struct v4l2_subdev_frame_interval *fi)
 {
 	struct stimx274 *imx274 = to_imx274(sd);
 	struct v4l2_ctrl *ctrl = imx274->ctrls.exposure;
@@ -1371,7 +1355,7 @@ static int imx274_s_frame_interval(struct v4l2_subdev *sd,
 		return ret;
 
 	mutex_lock(&imx274->lock);
-	ret = imx274_set_frame_interval(imx274, fi->interval);
+	ret = __imx274_set_frame_interval(imx274, fi->interval);
 
 	if (!ret) {
 		fi->interval = imx274->frame_interval;
@@ -1466,8 +1450,8 @@ static int imx274_s_stream(struct v4l2_subdev *sd, int on)
 		 * are changed.
 		 * gain is not affected.
 		 */
-		ret = imx274_set_frame_interval(imx274,
-						imx274->frame_interval);
+		ret = __imx274_set_frame_interval(imx274,
+						  imx274->frame_interval);
 		if (ret)
 			goto fail;
 
@@ -1830,7 +1814,7 @@ fail:
 }
 
 /*
- * imx274_set_frame_interval - Function called when setting frame interval
+ * __imx274_set_frame_interval - Function called when setting frame interval
  * @priv: Pointer to device structure
  * @frame_interval: Variable for frame interval
  *
@@ -1839,8 +1823,8 @@ fail:
  *
  * Return: 0 on success
  */
-static int imx274_set_frame_interval(struct stimx274 *priv,
-				     struct v4l2_fract frame_interval)
+static int __imx274_set_frame_interval(struct stimx274 *priv,
+				       struct v4l2_fract frame_interval)
 {
 	int err;
 	u32 frame_length, req_frame_rate;
@@ -1927,11 +1911,11 @@ static const struct v4l2_subdev_pad_ops imx274_pad_ops = {
 	.set_fmt = imx274_set_fmt,
 	.get_selection = imx274_get_selection,
 	.set_selection = imx274_set_selection,
+	.get_frame_interval = imx274_get_frame_interval,
+	.set_frame_interval = imx274_set_frame_interval,
 };
 
 static const struct v4l2_subdev_video_ops imx274_video_ops = {
-	.g_frame_interval = imx274_g_frame_interval,
-	.s_frame_interval = imx274_s_frame_interval,
 	.s_stream = imx274_s_stream,
 };
 
diff --git a/drivers/media/i2c/max9286.c b/drivers/media/i2c/max9286.c
index ee11ae682d8d..7e8cb53d31c3 100644
--- a/drivers/media/i2c/max9286.c
+++ b/drivers/media/i2c/max9286.c
@@ -868,8 +868,9 @@ static int max9286_s_stream(struct v4l2_subdev *sd, int enable)
 	return 0;
 }
 
-static int max9286_g_frame_interval(struct v4l2_subdev *sd,
-				    struct v4l2_subdev_frame_interval *interval)
+static int max9286_get_frame_interval(struct v4l2_subdev *sd,
+				      struct v4l2_subdev_state *sd_state,
+				      struct v4l2_subdev_frame_interval *interval)
 {
 	struct max9286_priv *priv = sd_to_max9286(sd);
 
@@ -881,8 +882,9 @@ static int max9286_g_frame_interval(struct v4l2_subdev *sd,
 	return 0;
 }
 
-static int max9286_s_frame_interval(struct v4l2_subdev *sd,
-				    struct v4l2_subdev_frame_interval *interval)
+static int max9286_set_frame_interval(struct v4l2_subdev *sd,
+				      struct v4l2_subdev_state *sd_state,
+				      struct v4l2_subdev_frame_interval *interval)
 {
 	struct max9286_priv *priv = sd_to_max9286(sd);
 
@@ -983,14 +985,14 @@ static int max9286_get_fmt(struct v4l2_subdev *sd,
 
 static const struct v4l2_subdev_video_ops max9286_video_ops = {
 	.s_stream	= max9286_s_stream,
-	.g_frame_interval = max9286_g_frame_interval,
-	.s_frame_interval = max9286_s_frame_interval,
 };
 
 static const struct v4l2_subdev_pad_ops max9286_pad_ops = {
 	.enum_mbus_code = max9286_enum_mbus_code,
 	.get_fmt	= max9286_get_fmt,
 	.set_fmt	= max9286_set_fmt,
+	.get_frame_interval = max9286_get_frame_interval,
+	.set_frame_interval = max9286_set_frame_interval,
 };
 
 static const struct v4l2_subdev_ops max9286_subdev_ops = {
diff --git a/drivers/media/i2c/mt9m111.c b/drivers/media/i2c/mt9m111.c
index 54a7a4c623ea..602954650f2e 100644
--- a/drivers/media/i2c/mt9m111.c
+++ b/drivers/media/i2c/mt9m111.c
@@ -1045,8 +1045,9 @@ static const struct v4l2_subdev_core_ops mt9m111_subdev_core_ops = {
 #endif
 };
 
-static int mt9m111_g_frame_interval(struct v4l2_subdev *sd,
-				   struct v4l2_subdev_frame_interval *fi)
+static int mt9m111_get_frame_interval(struct v4l2_subdev *sd,
+				      struct v4l2_subdev_state *sd_state,
+				      struct v4l2_subdev_frame_interval *fi)
 {
 	struct mt9m111 *mt9m111 = container_of(sd, struct mt9m111, subdev);
 
@@ -1055,8 +1056,9 @@ static int mt9m111_g_frame_interval(struct v4l2_subdev *sd,
 	return 0;
 }
 
-static int mt9m111_s_frame_interval(struct v4l2_subdev *sd,
-				   struct v4l2_subdev_frame_interval *fi)
+static int mt9m111_set_frame_interval(struct v4l2_subdev *sd,
+				      struct v4l2_subdev_state *sd_state,
+				      struct v4l2_subdev_frame_interval *fi)
 {
 	struct mt9m111 *mt9m111 = container_of(sd, struct mt9m111, subdev);
 	const struct mt9m111_mode_info *mode;
@@ -1151,8 +1153,6 @@ static int mt9m111_get_mbus_config(struct v4l2_subdev *sd,
 
 static const struct v4l2_subdev_video_ops mt9m111_subdev_video_ops = {
 	.s_stream	= mt9m111_s_stream,
-	.g_frame_interval = mt9m111_g_frame_interval,
-	.s_frame_interval = mt9m111_s_frame_interval,
 };
 
 static const struct v4l2_subdev_pad_ops mt9m111_subdev_pad_ops = {
@@ -1161,6 +1161,8 @@ static const struct v4l2_subdev_pad_ops mt9m111_subdev_pad_ops = {
 	.set_selection	= mt9m111_set_selection,
 	.get_fmt	= mt9m111_get_fmt,
 	.set_fmt	= mt9m111_set_fmt,
+	.get_frame_interval = mt9m111_get_frame_interval,
+	.set_frame_interval = mt9m111_set_frame_interval,
 	.get_mbus_config = mt9m111_get_mbus_config,
 };
 
diff --git a/drivers/media/i2c/mt9m114.c b/drivers/media/i2c/mt9m114.c
index 0a22f328981d..dcd94299787c 100644
--- a/drivers/media/i2c/mt9m114.c
+++ b/drivers/media/i2c/mt9m114.c
@@ -1585,8 +1585,9 @@ static int mt9m114_ifp_s_stream(struct v4l2_subdev *sd, int enable)
 	return ret;
 }
 
-static int mt9m114_ifp_g_frame_interval(struct v4l2_subdev *sd,
-					struct v4l2_subdev_frame_interval *interval)
+static int mt9m114_ifp_get_frame_interval(struct v4l2_subdev *sd,
+					  struct v4l2_subdev_state *sd_state,
+					  struct v4l2_subdev_frame_interval *interval)
 {
 	struct v4l2_fract *ival = &interval->interval;
 	struct mt9m114 *sensor = ifp_to_mt9m114(sd);
@@ -1601,8 +1602,9 @@ static int mt9m114_ifp_g_frame_interval(struct v4l2_subdev *sd,
 	return 0;
 }
 
-static int mt9m114_ifp_s_frame_interval(struct v4l2_subdev *sd,
-					struct v4l2_subdev_frame_interval *interval)
+static int mt9m114_ifp_set_frame_interval(struct v4l2_subdev *sd,
+					  struct v4l2_subdev_state *sd_state,
+					  struct v4l2_subdev_frame_interval *interval)
 {
 	struct v4l2_fract *ival = &interval->interval;
 	struct mt9m114 *sensor = ifp_to_mt9m114(sd);
@@ -1967,8 +1969,6 @@ static int mt9m114_ifp_registered(struct v4l2_subdev *sd)
 
 static const struct v4l2_subdev_video_ops mt9m114_ifp_video_ops = {
 	.s_stream = mt9m114_ifp_s_stream,
-	.g_frame_interval = mt9m114_ifp_g_frame_interval,
-	.s_frame_interval = mt9m114_ifp_s_frame_interval,
 };
 
 static const struct v4l2_subdev_pad_ops mt9m114_ifp_pad_ops = {
@@ -1979,6 +1979,8 @@ static const struct v4l2_subdev_pad_ops mt9m114_ifp_pad_ops = {
 	.set_fmt = mt9m114_ifp_set_fmt,
 	.get_selection = mt9m114_ifp_get_selection,
 	.set_selection = mt9m114_ifp_set_selection,
+	.get_frame_interval = mt9m114_ifp_get_frame_interval,
+	.set_frame_interval = mt9m114_ifp_set_frame_interval,
 };
 
 static const struct v4l2_subdev_ops mt9m114_ifp_ops = {
diff --git a/drivers/media/i2c/mt9v011.c b/drivers/media/i2c/mt9v011.c
index d0924b4ac6fb..3485761428ba 100644
--- a/drivers/media/i2c/mt9v011.c
+++ b/drivers/media/i2c/mt9v011.c
@@ -362,8 +362,9 @@ static int mt9v011_set_fmt(struct v4l2_subdev *sd,
 	return 0;
 }
 
-static int mt9v011_g_frame_interval(struct v4l2_subdev *sd,
-				    struct v4l2_subdev_frame_interval *ival)
+static int mt9v011_get_frame_interval(struct v4l2_subdev *sd,
+				      struct v4l2_subdev_state *sd_state,
+				      struct v4l2_subdev_frame_interval *ival)
 {
 	calc_fps(sd,
 		 &ival->interval.numerator,
@@ -372,8 +373,9 @@ static int mt9v011_g_frame_interval(struct v4l2_subdev *sd,
 	return 0;
 }
 
-static int mt9v011_s_frame_interval(struct v4l2_subdev *sd,
-				    struct v4l2_subdev_frame_interval *ival)
+static int mt9v011_set_frame_interval(struct v4l2_subdev *sd,
+				      struct v4l2_subdev_state *sd_state,
+				      struct v4l2_subdev_frame_interval *ival)
 {
 	struct v4l2_fract *tpf = &ival->interval;
 	u16 speed;
@@ -455,19 +457,15 @@ static const struct v4l2_subdev_core_ops mt9v011_core_ops = {
 #endif
 };
 
-static const struct v4l2_subdev_video_ops mt9v011_video_ops = {
-	.g_frame_interval = mt9v011_g_frame_interval,
-	.s_frame_interval = mt9v011_s_frame_interval,
-};
-
 static const struct v4l2_subdev_pad_ops mt9v011_pad_ops = {
 	.enum_mbus_code = mt9v011_enum_mbus_code,
 	.set_fmt = mt9v011_set_fmt,
+	.get_frame_interval = mt9v011_get_frame_interval,
+	.set_frame_interval = mt9v011_set_frame_interval,
 };
 
 static const struct v4l2_subdev_ops mt9v011_ops = {
 	.core  = &mt9v011_core_ops,
-	.video = &mt9v011_video_ops,
 	.pad   = &mt9v011_pad_ops,
 };
 
diff --git a/drivers/media/i2c/mt9v111.c b/drivers/media/i2c/mt9v111.c
index b186e9160d94..496be67c971b 100644
--- a/drivers/media/i2c/mt9v111.c
+++ b/drivers/media/i2c/mt9v111.c
@@ -35,7 +35,7 @@
  * The IFP can produce several output image formats from the sensor core
  * output. This driver currently supports only YUYV format permutations.
  *
- * The driver allows manual frame rate control through s_frame_interval subdev
+ * The driver allows manual frame rate control through set_frame_interval subdev
  * operation or V4L2_CID_V/HBLANK controls, but it is known that the
  * auto-exposure algorithm might modify the programmed frame rate. While the
  * driver initially programs the sensor with auto-exposure and
@@ -719,8 +719,9 @@ error_unlock:
 	return ret;
 }
 
-static int mt9v111_s_frame_interval(struct v4l2_subdev *sd,
-				    struct v4l2_subdev_frame_interval *ival)
+static int mt9v111_set_frame_interval(struct v4l2_subdev *sd,
+				      struct v4l2_subdev_state *sd_state,
+				      struct v4l2_subdev_frame_interval *ival)
 {
 	struct mt9v111_dev *mt9v111 = sd_to_mt9v111(sd);
 	struct v4l2_fract *tpf = &ival->interval;
@@ -771,8 +772,9 @@ static int mt9v111_s_frame_interval(struct v4l2_subdev *sd,
 	return 0;
 }
 
-static int mt9v111_g_frame_interval(struct v4l2_subdev *sd,
-				    struct v4l2_subdev_frame_interval *ival)
+static int mt9v111_get_frame_interval(struct v4l2_subdev *sd,
+				      struct v4l2_subdev_state *sd_state,
+				      struct v4l2_subdev_frame_interval *ival)
 {
 	struct mt9v111_dev *mt9v111 = sd_to_mt9v111(sd);
 	struct v4l2_fract *tpf = &ival->interval;
@@ -962,8 +964,6 @@ static const struct v4l2_subdev_core_ops mt9v111_core_ops = {
 
 static const struct v4l2_subdev_video_ops mt9v111_video_ops = {
 	.s_stream		= mt9v111_s_stream,
-	.s_frame_interval	= mt9v111_s_frame_interval,
-	.g_frame_interval	= mt9v111_g_frame_interval,
 };
 
 static const struct v4l2_subdev_pad_ops mt9v111_pad_ops = {
@@ -972,6 +972,8 @@ static const struct v4l2_subdev_pad_ops mt9v111_pad_ops = {
 	.enum_frame_interval	= mt9v111_enum_frame_interval,
 	.get_fmt		= mt9v111_get_format,
 	.set_fmt		= mt9v111_set_format,
+	.get_frame_interval	= mt9v111_get_frame_interval,
+	.set_frame_interval	= mt9v111_set_frame_interval,
 };
 
 static const struct v4l2_subdev_ops mt9v111_ops = {
diff --git a/drivers/media/i2c/ov2680.c b/drivers/media/i2c/ov2680.c
index d34d1972dcd9..e3ff64a9e6ca 100644
--- a/drivers/media/i2c/ov2680.c
+++ b/drivers/media/i2c/ov2680.c
@@ -552,7 +552,8 @@ err_disable_regulators:
 	return ret;
 }
 
-static int ov2680_s_g_frame_interval(struct v4l2_subdev *sd,
+static int ov2680_get_frame_interval(struct v4l2_subdev *sd,
+				     struct v4l2_subdev_state *sd_state,
 				     struct v4l2_subdev_frame_interval *fi)
 {
 	struct ov2680_dev *sensor = to_ov2680_dev(sd);
@@ -870,8 +871,6 @@ static const struct v4l2_ctrl_ops ov2680_ctrl_ops = {
 };
 
 static const struct v4l2_subdev_video_ops ov2680_video_ops = {
-	.g_frame_interval	= ov2680_s_g_frame_interval,
-	.s_frame_interval	= ov2680_s_g_frame_interval,
 	.s_stream		= ov2680_s_stream,
 };
 
@@ -883,6 +882,8 @@ static const struct v4l2_subdev_pad_ops ov2680_pad_ops = {
 	.set_fmt		= ov2680_set_fmt,
 	.get_selection		= ov2680_get_selection,
 	.set_selection		= ov2680_set_selection,
+	.get_frame_interval	= ov2680_get_frame_interval,
+	.set_frame_interval	= ov2680_get_frame_interval,
 };
 
 static const struct v4l2_subdev_ops ov2680_subdev_ops = {
diff --git a/drivers/media/i2c/ov5640.c b/drivers/media/i2c/ov5640.c
index 6fd98b8cb181..336bfd1ffd32 100644
--- a/drivers/media/i2c/ov5640.c
+++ b/drivers/media/i2c/ov5640.c
@@ -399,7 +399,7 @@ struct ov5640_mode_info {
 	const struct reg_value *reg_data;
 	u32 reg_data_size;
 
-	/* Used by s_frame_interval only. */
+	/* Used by set_frame_interval only. */
 	u32 max_fps;
 	u32 def_fps;
 };
@@ -3604,8 +3604,9 @@ static int ov5640_enum_frame_interval(
 	return 0;
 }
 
-static int ov5640_g_frame_interval(struct v4l2_subdev *sd,
-				   struct v4l2_subdev_frame_interval *fi)
+static int ov5640_get_frame_interval(struct v4l2_subdev *sd,
+				     struct v4l2_subdev_state *sd_state,
+				     struct v4l2_subdev_frame_interval *fi)
 {
 	struct ov5640_dev *sensor = to_ov5640_dev(sd);
 
@@ -3616,8 +3617,9 @@ static int ov5640_g_frame_interval(struct v4l2_subdev *sd,
 	return 0;
 }
 
-static int ov5640_s_frame_interval(struct v4l2_subdev *sd,
-				   struct v4l2_subdev_frame_interval *fi)
+static int ov5640_set_frame_interval(struct v4l2_subdev *sd,
+				     struct v4l2_subdev_state *sd_state,
+				     struct v4l2_subdev_frame_interval *fi)
 {
 	struct ov5640_dev *sensor = to_ov5640_dev(sd);
 	const struct ov5640_mode_info *mode;
@@ -3770,8 +3772,6 @@ static const struct v4l2_subdev_core_ops ov5640_core_ops = {
 };
 
 static const struct v4l2_subdev_video_ops ov5640_video_ops = {
-	.g_frame_interval = ov5640_g_frame_interval,
-	.s_frame_interval = ov5640_s_frame_interval,
 	.s_stream = ov5640_s_stream,
 };
 
@@ -3780,6 +3780,8 @@ static const struct v4l2_subdev_pad_ops ov5640_pad_ops = {
 	.get_fmt = ov5640_get_fmt,
 	.set_fmt = ov5640_set_fmt,
 	.get_selection = ov5640_get_selection,
+	.get_frame_interval = ov5640_get_frame_interval,
+	.set_frame_interval = ov5640_set_frame_interval,
 	.enum_frame_size = ov5640_enum_frame_size,
 	.enum_frame_interval = ov5640_enum_frame_interval,
 };
diff --git a/drivers/media/i2c/ov5648.c b/drivers/media/i2c/ov5648.c
index 13e6060d15d4..d0d7e9968f48 100644
--- a/drivers/media/i2c/ov5648.c
+++ b/drivers/media/i2c/ov5648.c
@@ -2158,37 +2158,8 @@ static int ov5648_s_stream(struct v4l2_subdev *subdev, int enable)
 	return 0;
 }
 
-static int ov5648_g_frame_interval(struct v4l2_subdev *subdev,
-				   struct v4l2_subdev_frame_interval *interval)
-{
-	struct ov5648_sensor *sensor = ov5648_subdev_sensor(subdev);
-	const struct ov5648_mode *mode;
-	int ret = 0;
-
-	mutex_lock(&sensor->mutex);
-
-	mode = sensor->state.mode;
-
-	switch (sensor->state.mbus_code) {
-	case MEDIA_BUS_FMT_SBGGR8_1X8:
-		interval->interval = mode->frame_interval[0];
-		break;
-	case MEDIA_BUS_FMT_SBGGR10_1X10:
-		interval->interval = mode->frame_interval[1];
-		break;
-	default:
-		ret = -EINVAL;
-	}
-
-	mutex_unlock(&sensor->mutex);
-
-	return ret;
-}
-
 static const struct v4l2_subdev_video_ops ov5648_subdev_video_ops = {
 	.s_stream		= ov5648_s_stream,
-	.g_frame_interval	= ov5648_g_frame_interval,
-	.s_frame_interval	= ov5648_g_frame_interval,
 };
 
 /* Subdev Pad Operations */
@@ -2297,6 +2268,34 @@ complete:
 	return ret;
 }
 
+static int ov5648_get_frame_interval(struct v4l2_subdev *subdev,
+				     struct v4l2_subdev_state *sd_state,
+				     struct v4l2_subdev_frame_interval *interval)
+{
+	struct ov5648_sensor *sensor = ov5648_subdev_sensor(subdev);
+	const struct ov5648_mode *mode;
+	int ret = 0;
+
+	mutex_lock(&sensor->mutex);
+
+	mode = sensor->state.mode;
+
+	switch (sensor->state.mbus_code) {
+	case MEDIA_BUS_FMT_SBGGR8_1X8:
+		interval->interval = mode->frame_interval[0];
+		break;
+	case MEDIA_BUS_FMT_SBGGR10_1X10:
+		interval->interval = mode->frame_interval[1];
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	mutex_unlock(&sensor->mutex);
+
+	return ret;
+}
+
 static int ov5648_enum_frame_size(struct v4l2_subdev *subdev,
 				  struct v4l2_subdev_state *sd_state,
 				  struct v4l2_subdev_frame_size_enum *size_enum)
@@ -2363,6 +2362,8 @@ static const struct v4l2_subdev_pad_ops ov5648_subdev_pad_ops = {
 	.enum_mbus_code		= ov5648_enum_mbus_code,
 	.get_fmt		= ov5648_get_fmt,
 	.set_fmt		= ov5648_set_fmt,
+	.get_frame_interval	= ov5648_get_frame_interval,
+	.set_frame_interval	= ov5648_get_frame_interval,
 	.enum_frame_size	= ov5648_enum_frame_size,
 	.enum_frame_interval	= ov5648_enum_frame_interval,
 };
diff --git a/drivers/media/i2c/ov5693.c b/drivers/media/i2c/ov5693.c
index 205193baa06e..a65645811fbc 100644
--- a/drivers/media/i2c/ov5693.c
+++ b/drivers/media/i2c/ov5693.c
@@ -1004,8 +1004,9 @@ err_power_down:
 	return ret;
 }
 
-static int ov5693_g_frame_interval(struct v4l2_subdev *sd,
-				   struct v4l2_subdev_frame_interval *interval)
+static int ov5693_get_frame_interval(struct v4l2_subdev *sd,
+				     struct v4l2_subdev_state *sd_state,
+				     struct v4l2_subdev_frame_interval *interval)
 {
 	struct ov5693_device *ov5693 = to_ov5693_sensor(sd);
 	unsigned int framesize = OV5693_FIXED_PPL * (ov5693->mode.format.height +
@@ -1054,7 +1055,6 @@ static int ov5693_enum_frame_size(struct v4l2_subdev *sd,
 
 static const struct v4l2_subdev_video_ops ov5693_video_ops = {
 	.s_stream = ov5693_s_stream,
-	.g_frame_interval = ov5693_g_frame_interval,
 };
 
 static const struct v4l2_subdev_pad_ops ov5693_pad_ops = {
@@ -1064,6 +1064,7 @@ static const struct v4l2_subdev_pad_ops ov5693_pad_ops = {
 	.set_fmt = ov5693_set_fmt,
 	.get_selection = ov5693_get_selection,
 	.set_selection = ov5693_set_selection,
+	.get_frame_interval = ov5693_get_frame_interval,
 };
 
 static const struct v4l2_subdev_ops ov5693_ops = {
diff --git a/drivers/media/i2c/ov6650.c b/drivers/media/i2c/ov6650.c
index bf1e7617ee08..a4dc45bdf3d7 100644
--- a/drivers/media/i2c/ov6650.c
+++ b/drivers/media/i2c/ov6650.c
@@ -197,7 +197,7 @@ struct ov6650 {
 	struct clk		*clk;
 	bool			half_scale;	/* scale down output by 2 */
 	struct v4l2_rect	rect;		/* sensor cropping window */
-	struct v4l2_fract	tpf;		/* as requested with s_frame_interval */
+	struct v4l2_fract	tpf;		/* as requested with set_frame_interval */
 	u32 code;
 };
 
@@ -799,8 +799,9 @@ static int ov6650_enum_frame_interval(struct v4l2_subdev *sd,
 	return 0;
 }
 
-static int ov6650_g_frame_interval(struct v4l2_subdev *sd,
-				   struct v4l2_subdev_frame_interval *ival)
+static int ov6650_get_frame_interval(struct v4l2_subdev *sd,
+				     struct v4l2_subdev_state *sd_state,
+				     struct v4l2_subdev_frame_interval *ival)
 {
 	struct i2c_client *client = v4l2_get_subdevdata(sd);
 	struct ov6650 *priv = to_ov6650(client);
@@ -813,8 +814,9 @@ static int ov6650_g_frame_interval(struct v4l2_subdev *sd,
 	return 0;
 }
 
-static int ov6650_s_frame_interval(struct v4l2_subdev *sd,
-				   struct v4l2_subdev_frame_interval *ival)
+static int ov6650_set_frame_interval(struct v4l2_subdev *sd,
+				     struct v4l2_subdev_state *sd_state,
+				     struct v4l2_subdev_frame_interval *ival)
 {
 	struct i2c_client *client = v4l2_get_subdevdata(sd);
 	struct ov6650 *priv = to_ov6650(client);
@@ -1006,8 +1008,6 @@ static int ov6650_get_mbus_config(struct v4l2_subdev *sd,
 
 static const struct v4l2_subdev_video_ops ov6650_video_ops = {
 	.s_stream	= ov6650_s_stream,
-	.g_frame_interval = ov6650_g_frame_interval,
-	.s_frame_interval = ov6650_s_frame_interval,
 };
 
 static const struct v4l2_subdev_pad_ops ov6650_pad_ops = {
@@ -1017,6 +1017,8 @@ static const struct v4l2_subdev_pad_ops ov6650_pad_ops = {
 	.set_selection		= ov6650_set_selection,
 	.get_fmt		= ov6650_get_fmt,
 	.set_fmt		= ov6650_set_fmt,
+	.get_frame_interval	= ov6650_get_frame_interval,
+	.set_frame_interval	= ov6650_set_frame_interval,
 	.get_mbus_config	= ov6650_get_mbus_config,
 };
 
diff --git a/drivers/media/i2c/ov7251.c b/drivers/media/i2c/ov7251.c
index 897a0763df4a..10d6b5deed83 100644
--- a/drivers/media/i2c/ov7251.c
+++ b/drivers/media/i2c/ov7251.c
@@ -1386,6 +1386,7 @@ err_power_down:
 }
 
 static int ov7251_get_frame_interval(struct v4l2_subdev *subdev,
+				     struct v4l2_subdev_state *sd_state,
 				     struct v4l2_subdev_frame_interval *fi)
 {
 	struct ov7251 *ov7251 = to_ov7251(subdev);
@@ -1398,6 +1399,7 @@ static int ov7251_get_frame_interval(struct v4l2_subdev *subdev,
 }
 
 static int ov7251_set_frame_interval(struct v4l2_subdev *subdev,
+				     struct v4l2_subdev_state *sd_state,
 				     struct v4l2_subdev_frame_interval *fi)
 {
 	struct ov7251 *ov7251 = to_ov7251(subdev);
@@ -1436,8 +1438,6 @@ exit:
 
 static const struct v4l2_subdev_video_ops ov7251_video_ops = {
 	.s_stream = ov7251_s_stream,
-	.g_frame_interval = ov7251_get_frame_interval,
-	.s_frame_interval = ov7251_set_frame_interval,
 };
 
 static const struct v4l2_subdev_pad_ops ov7251_subdev_pad_ops = {
@@ -1447,6 +1447,8 @@ static const struct v4l2_subdev_pad_ops ov7251_subdev_pad_ops = {
 	.get_fmt = ov7251_get_format,
 	.set_fmt = ov7251_set_format,
 	.get_selection = ov7251_get_selection,
+	.get_frame_interval = ov7251_get_frame_interval,
+	.set_frame_interval = ov7251_set_frame_interval,
 };
 
 static const struct v4l2_subdev_ops ov7251_subdev_ops = {
diff --git a/drivers/media/i2c/ov7670.c b/drivers/media/i2c/ov7670.c
index 8164c0c433c5..463f20ece36e 100644
--- a/drivers/media/i2c/ov7670.c
+++ b/drivers/media/i2c/ov7670.c
@@ -1154,8 +1154,9 @@ static int ov7670_get_fmt(struct v4l2_subdev *sd,
  * Implement G/S_PARM.  There is a "high quality" mode we could try
  * to do someday; for now, we just do the frame rate tweak.
  */
-static int ov7670_g_frame_interval(struct v4l2_subdev *sd,
-				   struct v4l2_subdev_frame_interval *ival)
+static int ov7670_get_frame_interval(struct v4l2_subdev *sd,
+				     struct v4l2_subdev_state *sd_state,
+				     struct v4l2_subdev_frame_interval *ival)
 {
 	struct ov7670_info *info = to_state(sd);
 
@@ -1165,8 +1166,9 @@ static int ov7670_g_frame_interval(struct v4l2_subdev *sd,
 	return 0;
 }
 
-static int ov7670_s_frame_interval(struct v4l2_subdev *sd,
-				   struct v4l2_subdev_frame_interval *ival)
+static int ov7670_set_frame_interval(struct v4l2_subdev *sd,
+				     struct v4l2_subdev_state *sd_state,
+				     struct v4l2_subdev_frame_interval *ival)
 {
 	struct v4l2_fract *tpf = &ival->interval;
 	struct ov7670_info *info = to_state(sd);
@@ -1728,22 +1730,18 @@ static const struct v4l2_subdev_core_ops ov7670_core_ops = {
 #endif
 };
 
-static const struct v4l2_subdev_video_ops ov7670_video_ops = {
-	.s_frame_interval = ov7670_s_frame_interval,
-	.g_frame_interval = ov7670_g_frame_interval,
-};
-
 static const struct v4l2_subdev_pad_ops ov7670_pad_ops = {
 	.enum_frame_interval = ov7670_enum_frame_interval,
 	.enum_frame_size = ov7670_enum_frame_size,
 	.enum_mbus_code = ov7670_enum_mbus_code,
 	.get_fmt = ov7670_get_fmt,
 	.set_fmt = ov7670_set_fmt,
+	.get_frame_interval = ov7670_get_frame_interval,
+	.set_frame_interval = ov7670_set_frame_interval,
 };
 
 static const struct v4l2_subdev_ops ov7670_ops = {
 	.core = &ov7670_core_ops,
-	.video = &ov7670_video_ops,
 	.pad = &ov7670_pad_ops,
 };
 
diff --git a/drivers/media/i2c/ov772x.c b/drivers/media/i2c/ov772x.c
index e397f7531e1d..a14a25946c5b 100644
--- a/drivers/media/i2c/ov772x.c
+++ b/drivers/media/i2c/ov772x.c
@@ -717,8 +717,9 @@ static int ov772x_set_frame_rate(struct ov772x_priv *priv,
 	return 0;
 }
 
-static int ov772x_g_frame_interval(struct v4l2_subdev *sd,
-				   struct v4l2_subdev_frame_interval *ival)
+static int ov772x_get_frame_interval(struct v4l2_subdev *sd,
+				     struct v4l2_subdev_state *sd_state,
+				     struct v4l2_subdev_frame_interval *ival)
 {
 	struct ov772x_priv *priv = to_ov772x(sd);
 	struct v4l2_fract *tpf = &ival->interval;
@@ -729,8 +730,9 @@ static int ov772x_g_frame_interval(struct v4l2_subdev *sd,
 	return 0;
 }
 
-static int ov772x_s_frame_interval(struct v4l2_subdev *sd,
-				   struct v4l2_subdev_frame_interval *ival)
+static int ov772x_set_frame_interval(struct v4l2_subdev *sd,
+				     struct v4l2_subdev_state *sd_state,
+				     struct v4l2_subdev_frame_interval *ival)
 {
 	struct ov772x_priv *priv = to_ov772x(sd);
 	struct v4l2_fract *tpf = &ival->interval;
@@ -1349,8 +1351,6 @@ static int ov772x_enum_mbus_code(struct v4l2_subdev *sd,
 
 static const struct v4l2_subdev_video_ops ov772x_subdev_video_ops = {
 	.s_stream		= ov772x_s_stream,
-	.s_frame_interval	= ov772x_s_frame_interval,
-	.g_frame_interval	= ov772x_g_frame_interval,
 };
 
 static const struct v4l2_subdev_pad_ops ov772x_subdev_pad_ops = {
@@ -1359,6 +1359,8 @@ static const struct v4l2_subdev_pad_ops ov772x_subdev_pad_ops = {
 	.get_selection		= ov772x_get_selection,
 	.get_fmt		= ov772x_get_fmt,
 	.set_fmt		= ov772x_set_fmt,
+	.get_frame_interval	= ov772x_get_frame_interval,
+	.set_frame_interval	= ov772x_set_frame_interval,
 };
 
 static const struct v4l2_subdev_ops ov772x_subdev_ops = {
diff --git a/drivers/media/i2c/ov7740.c b/drivers/media/i2c/ov7740.c
index 9c13ff5fe9fa..47b1b14d8796 100644
--- a/drivers/media/i2c/ov7740.c
+++ b/drivers/media/i2c/ov7740.c
@@ -638,34 +638,8 @@ err_unlock:
 	return ret;
 }
 
-static int ov7740_g_frame_interval(struct v4l2_subdev *sd,
-				   struct v4l2_subdev_frame_interval *ival)
-{
-	struct v4l2_fract *tpf = &ival->interval;
-
-
-	tpf->numerator = 1;
-	tpf->denominator = 60;
-
-	return 0;
-}
-
-static int ov7740_s_frame_interval(struct v4l2_subdev *sd,
-				   struct v4l2_subdev_frame_interval *ival)
-{
-	struct v4l2_fract *tpf = &ival->interval;
-
-
-	tpf->numerator = 1;
-	tpf->denominator = 60;
-
-	return 0;
-}
-
 static const struct v4l2_subdev_video_ops ov7740_subdev_video_ops = {
 	.s_stream = ov7740_set_stream,
-	.s_frame_interval = ov7740_s_frame_interval,
-	.g_frame_interval = ov7740_g_frame_interval,
 };
 
 static const struct reg_sequence ov7740_format_yuyv[] = {
@@ -852,12 +826,26 @@ static int ov7740_get_fmt(struct v4l2_subdev *sd,
 	return 0;
 }
 
+static int ov7740_get_frame_interval(struct v4l2_subdev *sd,
+				     struct v4l2_subdev_state *sd_state,
+				     struct v4l2_subdev_frame_interval *ival)
+{
+	struct v4l2_fract *tpf = &ival->interval;
+
+	tpf->numerator = 1;
+	tpf->denominator = 60;
+
+	return 0;
+}
+
 static const struct v4l2_subdev_pad_ops ov7740_subdev_pad_ops = {
 	.enum_frame_interval = ov7740_enum_frame_interval,
 	.enum_frame_size = ov7740_enum_frame_size,
 	.enum_mbus_code = ov7740_enum_mbus_code,
 	.get_fmt = ov7740_get_fmt,
 	.set_fmt = ov7740_set_fmt,
+	.get_frame_interval = ov7740_get_frame_interval,
+	.set_frame_interval = ov7740_get_frame_interval,
 };
 
 static const struct v4l2_subdev_ops ov7740_subdev_ops = {
diff --git a/drivers/media/i2c/ov8865.c b/drivers/media/i2c/ov8865.c
index fb19ab0c2a9d..02a595281c49 100644
--- a/drivers/media/i2c/ov8865.c
+++ b/drivers/media/i2c/ov8865.c
@@ -2640,33 +2640,8 @@ static int ov8865_s_stream(struct v4l2_subdev *subdev, int enable)
 	return 0;
 }
 
-static int ov8865_g_frame_interval(struct v4l2_subdev *subdev,
-				   struct v4l2_subdev_frame_interval *interval)
-{
-	struct ov8865_sensor *sensor = ov8865_subdev_sensor(subdev);
-	const struct ov8865_mode *mode;
-	unsigned int framesize;
-	unsigned int fps;
-
-	mutex_lock(&sensor->mutex);
-
-	mode = sensor->state.mode;
-	framesize = mode->hts * (mode->output_size_y +
-				 sensor->ctrls.vblank->val);
-	fps = DIV_ROUND_CLOSEST(sensor->ctrls.pixel_rate->val, framesize);
-
-	interval->interval.numerator = 1;
-	interval->interval.denominator = fps;
-
-	mutex_unlock(&sensor->mutex);
-
-	return 0;
-}
-
 static const struct v4l2_subdev_video_ops ov8865_subdev_video_ops = {
 	.s_stream		= ov8865_s_stream,
-	.g_frame_interval	= ov8865_g_frame_interval,
-	.s_frame_interval	= ov8865_g_frame_interval,
 };
 
 /* Subdev Pad Operations */
@@ -2862,6 +2837,30 @@ static int ov8865_get_selection(struct v4l2_subdev *subdev,
 	return 0;
 }
 
+static int ov8865_get_frame_interval(struct v4l2_subdev *subdev,
+				     struct v4l2_subdev_state *sd_state,
+				     struct v4l2_subdev_frame_interval *interval)
+{
+	struct ov8865_sensor *sensor = ov8865_subdev_sensor(subdev);
+	const struct ov8865_mode *mode;
+	unsigned int framesize;
+	unsigned int fps;
+
+	mutex_lock(&sensor->mutex);
+
+	mode = sensor->state.mode;
+	framesize = mode->hts * (mode->output_size_y +
+				 sensor->ctrls.vblank->val);
+	fps = DIV_ROUND_CLOSEST(sensor->ctrls.pixel_rate->val, framesize);
+
+	interval->interval.numerator = 1;
+	interval->interval.denominator = fps;
+
+	mutex_unlock(&sensor->mutex);
+
+	return 0;
+}
+
 static const struct v4l2_subdev_pad_ops ov8865_subdev_pad_ops = {
 	.enum_mbus_code		= ov8865_enum_mbus_code,
 	.get_fmt		= ov8865_get_fmt,
@@ -2869,6 +2868,8 @@ static const struct v4l2_subdev_pad_ops ov8865_subdev_pad_ops = {
 	.enum_frame_size	= ov8865_enum_frame_size,
 	.get_selection		= ov8865_get_selection,
 	.set_selection		= ov8865_get_selection,
+	.get_frame_interval	= ov8865_get_frame_interval,
+	.set_frame_interval	= ov8865_get_frame_interval,
 };
 
 static const struct v4l2_subdev_ops ov8865_subdev_ops = {
diff --git a/drivers/media/i2c/ov9650.c b/drivers/media/i2c/ov9650.c
index 753f6222102a..f528892c893f 100644
--- a/drivers/media/i2c/ov9650.c
+++ b/drivers/media/i2c/ov9650.c
@@ -1101,8 +1101,9 @@ static int ov965x_enum_frame_sizes(struct v4l2_subdev *sd,
 	return 0;
 }
 
-static int ov965x_g_frame_interval(struct v4l2_subdev *sd,
-				   struct v4l2_subdev_frame_interval *fi)
+static int ov965x_get_frame_interval(struct v4l2_subdev *sd,
+				     struct v4l2_subdev_state *sd_state,
+				     struct v4l2_subdev_frame_interval *fi)
 {
 	struct ov965x *ov965x = to_ov965x(sd);
 
@@ -1148,8 +1149,9 @@ static int __ov965x_set_frame_interval(struct ov965x *ov965x,
 	return 0;
 }
 
-static int ov965x_s_frame_interval(struct v4l2_subdev *sd,
-				   struct v4l2_subdev_frame_interval *fi)
+static int ov965x_set_frame_interval(struct v4l2_subdev *sd,
+				     struct v4l2_subdev_state *sd_state,
+				     struct v4l2_subdev_frame_interval *fi)
 {
 	struct ov965x *ov965x = to_ov965x(sd);
 	int ret;
@@ -1373,12 +1375,12 @@ static const struct v4l2_subdev_pad_ops ov965x_pad_ops = {
 	.enum_frame_size = ov965x_enum_frame_sizes,
 	.get_fmt = ov965x_get_fmt,
 	.set_fmt = ov965x_set_fmt,
+	.get_frame_interval = ov965x_get_frame_interval,
+	.set_frame_interval = ov965x_set_frame_interval,
 };
 
 static const struct v4l2_subdev_video_ops ov965x_video_ops = {
 	.s_stream = ov965x_s_stream,
-	.g_frame_interval = ov965x_g_frame_interval,
-	.s_frame_interval = ov965x_s_frame_interval,
 
 };
 
diff --git a/drivers/media/i2c/s5c73m3/s5c73m3-core.c b/drivers/media/i2c/s5c73m3/s5c73m3-core.c
index 8f9b5713daf7..73ca50f49812 100644
--- a/drivers/media/i2c/s5c73m3/s5c73m3-core.c
+++ b/drivers/media/i2c/s5c73m3/s5c73m3-core.c
@@ -866,8 +866,9 @@ static void s5c73m3_try_format(struct s5c73m3 *state,
 	s5c73m3_fill_mbus_fmt(&fmt->format, *fs, code);
 }
 
-static int s5c73m3_oif_g_frame_interval(struct v4l2_subdev *sd,
-				   struct v4l2_subdev_frame_interval *fi)
+static int s5c73m3_oif_get_frame_interval(struct v4l2_subdev *sd,
+					  struct v4l2_subdev_state *sd_state,
+					  struct v4l2_subdev_frame_interval *fi)
 {
 	struct s5c73m3 *state = oif_sd_to_s5c73m3(sd);
 
@@ -915,8 +916,9 @@ static int __s5c73m3_set_frame_interval(struct s5c73m3 *state,
 	return 0;
 }
 
-static int s5c73m3_oif_s_frame_interval(struct v4l2_subdev *sd,
-				   struct v4l2_subdev_frame_interval *fi)
+static int s5c73m3_oif_set_frame_interval(struct v4l2_subdev *sd,
+					  struct v4l2_subdev_state *sd_state,
+					  struct v4l2_subdev_frame_interval *fi)
 {
 	struct s5c73m3 *state = oif_sd_to_s5c73m3(sd);
 	int ret;
@@ -1497,6 +1499,8 @@ static const struct v4l2_subdev_pad_ops s5c73m3_oif_pad_ops = {
 	.enum_frame_interval	= s5c73m3_oif_enum_frame_interval,
 	.get_fmt		= s5c73m3_oif_get_fmt,
 	.set_fmt		= s5c73m3_oif_set_fmt,
+	.get_frame_interval	= s5c73m3_oif_get_frame_interval,
+	.set_frame_interval	= s5c73m3_oif_set_frame_interval,
 	.get_frame_desc		= s5c73m3_oif_get_frame_desc,
 	.set_frame_desc		= s5c73m3_oif_set_frame_desc,
 };
@@ -1508,8 +1512,6 @@ static const struct v4l2_subdev_core_ops s5c73m3_oif_core_ops = {
 
 static const struct v4l2_subdev_video_ops s5c73m3_oif_video_ops = {
 	.s_stream		= s5c73m3_oif_s_stream,
-	.g_frame_interval	= s5c73m3_oif_g_frame_interval,
-	.s_frame_interval	= s5c73m3_oif_s_frame_interval,
 };
 
 static const struct v4l2_subdev_ops oif_subdev_ops = {
diff --git a/drivers/media/i2c/s5k5baf.c b/drivers/media/i2c/s5k5baf.c
index 03ccfb0e1e11..2fd1ecfeb086 100644
--- a/drivers/media/i2c/s5k5baf.c
+++ b/drivers/media/i2c/s5k5baf.c
@@ -1118,8 +1118,9 @@ out:
 	return ret;
 }
 
-static int s5k5baf_g_frame_interval(struct v4l2_subdev *sd,
-				   struct v4l2_subdev_frame_interval *fi)
+static int s5k5baf_get_frame_interval(struct v4l2_subdev *sd,
+				      struct v4l2_subdev_state *sd_state,
+				      struct v4l2_subdev_frame_interval *fi)
 {
 	struct s5k5baf *state = to_s5k5baf(sd);
 
@@ -1131,8 +1132,8 @@ static int s5k5baf_g_frame_interval(struct v4l2_subdev *sd,
 	return 0;
 }
 
-static void s5k5baf_set_frame_interval(struct s5k5baf *state,
-				       struct v4l2_subdev_frame_interval *fi)
+static void __s5k5baf_set_frame_interval(struct s5k5baf *state,
+					 struct v4l2_subdev_frame_interval *fi)
 {
 	struct v4l2_fract *i = &fi->interval;
 
@@ -1155,13 +1156,14 @@ static void s5k5baf_set_frame_interval(struct s5k5baf *state,
 			  state->fiv);
 }
 
-static int s5k5baf_s_frame_interval(struct v4l2_subdev *sd,
-				   struct v4l2_subdev_frame_interval *fi)
+static int s5k5baf_set_frame_interval(struct v4l2_subdev *sd,
+				      struct v4l2_subdev_state *sd_state,
+				      struct v4l2_subdev_frame_interval *fi)
 {
 	struct s5k5baf *state = to_s5k5baf(sd);
 
 	mutex_lock(&state->lock);
-	s5k5baf_set_frame_interval(state, fi);
+	__s5k5baf_set_frame_interval(state, fi);
 	mutex_unlock(&state->lock);
 	return 0;
 }
@@ -1526,11 +1528,11 @@ static const struct v4l2_subdev_pad_ops s5k5baf_pad_ops = {
 	.set_fmt		= s5k5baf_set_fmt,
 	.get_selection		= s5k5baf_get_selection,
 	.set_selection		= s5k5baf_set_selection,
+	.get_frame_interval	= s5k5baf_get_frame_interval,
+	.set_frame_interval	= s5k5baf_set_frame_interval,
 };
 
 static const struct v4l2_subdev_video_ops s5k5baf_video_ops = {
-	.g_frame_interval	= s5k5baf_g_frame_interval,
-	.s_frame_interval	= s5k5baf_s_frame_interval,
 	.s_stream		= s5k5baf_s_stream,
 };
 
diff --git a/drivers/media/i2c/thp7312.c b/drivers/media/i2c/thp7312.c
index 3d46e428e0ac..d4975b180704 100644
--- a/drivers/media/i2c/thp7312.c
+++ b/drivers/media/i2c/thp7312.c
@@ -734,28 +734,26 @@ static int thp7312_set_fmt(struct v4l2_subdev *sd,
 	return 0;
 }
 
-static int thp7312_g_frame_interval(struct v4l2_subdev *sd,
-				    struct v4l2_subdev_frame_interval *fi)
+static int thp7312_get_frame_interval(struct v4l2_subdev *sd,
+				      struct v4l2_subdev_state *sd_state,
+				      struct v4l2_subdev_frame_interval *fi)
 {
 	struct thp7312_device *thp7312 = to_thp7312_dev(sd);
-	struct v4l2_subdev_state *sd_state;
 
-	sd_state = v4l2_subdev_lock_and_get_active_state(sd);
 	fi->interval.numerator = 1;
 	fi->interval.denominator = thp7312->current_rate->fps;
-	v4l2_subdev_unlock_state(sd_state);
 
 	return 0;
 }
 
-static int thp7312_s_frame_interval(struct v4l2_subdev *sd,
-				    struct v4l2_subdev_frame_interval *fi)
+static int thp7312_set_frame_interval(struct v4l2_subdev *sd,
+				      struct v4l2_subdev_state *sd_state,
+				      struct v4l2_subdev_frame_interval *fi)
 {
 	struct thp7312_device *thp7312 = to_thp7312_dev(sd);
 	const struct thp7312_mode_info *mode;
 	const struct thp7312_frame_rate *best_rate = NULL;
 	const struct thp7312_frame_rate *rate;
-	struct v4l2_subdev_state *sd_state;
 	unsigned int best_delta = UINT_MAX;
 	unsigned int fps;
 
@@ -764,8 +762,6 @@ static int thp7312_s_frame_interval(struct v4l2_subdev *sd,
 	    ? DIV_ROUND_CLOSEST(fi->interval.denominator, fi->interval.numerator)
 	    : UINT_MAX;
 
-	sd_state = v4l2_subdev_lock_and_get_active_state(sd);
-
 	mode = thp7312->current_mode;
 
 	for (rate = mode->rates; rate->fps && best_delta; ++rate) {
@@ -779,8 +775,6 @@ static int thp7312_s_frame_interval(struct v4l2_subdev *sd,
 
 	thp7312_set_frame_rate(thp7312, best_rate);
 
-	v4l2_subdev_unlock_state(sd_state);
-
 	fi->interval.numerator = 1;
 	fi->interval.denominator = best_rate->fps;
 
@@ -868,8 +862,6 @@ static const struct v4l2_subdev_core_ops thp7312_core_ops = {
 };
 
 static const struct v4l2_subdev_video_ops thp7312_video_ops = {
-	.g_frame_interval = thp7312_g_frame_interval,
-	.s_frame_interval = thp7312_s_frame_interval,
 	.s_stream = thp7312_s_stream,
 };
 
@@ -877,6 +869,8 @@ static const struct v4l2_subdev_pad_ops thp7312_pad_ops = {
 	.enum_mbus_code = thp7312_enum_mbus_code,
 	.get_fmt = v4l2_subdev_get_fmt,
 	.set_fmt = thp7312_set_fmt,
+	.get_frame_interval = thp7312_get_frame_interval,
+	.set_frame_interval = thp7312_set_frame_interval,
 	.enum_frame_size = thp7312_enum_frame_size,
 	.enum_frame_interval = thp7312_enum_frame_interval,
 };
diff --git a/drivers/media/i2c/tvp514x.c b/drivers/media/i2c/tvp514x.c
index c37f605cb75f..dee0cf992379 100644
--- a/drivers/media/i2c/tvp514x.c
+++ b/drivers/media/i2c/tvp514x.c
@@ -738,16 +738,10 @@ static int tvp514x_s_ctrl(struct v4l2_ctrl *ctrl)
 	return err;
 }
 
-/**
- * tvp514x_g_frame_interval() - V4L2 decoder interface handler
- * @sd: pointer to standard V4L2 sub-device structure
- * @ival: pointer to a v4l2_subdev_frame_interval structure
- *
- * Returns the decoder's video CAPTURE parameters.
- */
 static int
-tvp514x_g_frame_interval(struct v4l2_subdev *sd,
-			 struct v4l2_subdev_frame_interval *ival)
+tvp514x_get_frame_interval(struct v4l2_subdev *sd,
+			   struct v4l2_subdev_state *sd_state,
+			   struct v4l2_subdev_frame_interval *ival)
 {
 	struct tvp514x_decoder *decoder = to_decoder(sd);
 	enum tvp514x_std current_std;
@@ -762,17 +756,10 @@ tvp514x_g_frame_interval(struct v4l2_subdev *sd,
 	return 0;
 }
 
-/**
- * tvp514x_s_frame_interval() - V4L2 decoder interface handler
- * @sd: pointer to standard V4L2 sub-device structure
- * @ival: pointer to a v4l2_subdev_frame_interval structure
- *
- * Configures the decoder to use the input parameters, if possible. If
- * not possible, returns the appropriate error code.
- */
 static int
-tvp514x_s_frame_interval(struct v4l2_subdev *sd,
-			 struct v4l2_subdev_frame_interval *ival)
+tvp514x_set_frame_interval(struct v4l2_subdev *sd,
+			   struct v4l2_subdev_state *sd_state,
+			   struct v4l2_subdev_frame_interval *ival)
 {
 	struct tvp514x_decoder *decoder = to_decoder(sd);
 	struct v4l2_fract *timeperframe;
@@ -940,8 +927,6 @@ static const struct v4l2_subdev_video_ops tvp514x_video_ops = {
 	.s_std = tvp514x_s_std,
 	.s_routing = tvp514x_s_routing,
 	.querystd = tvp514x_querystd,
-	.g_frame_interval = tvp514x_g_frame_interval,
-	.s_frame_interval = tvp514x_s_frame_interval,
 	.s_stream = tvp514x_s_stream,
 };
 
@@ -949,6 +934,8 @@ static const struct v4l2_subdev_pad_ops tvp514x_pad_ops = {
 	.enum_mbus_code = tvp514x_enum_mbus_code,
 	.get_fmt = tvp514x_get_pad_format,
 	.set_fmt = tvp514x_set_pad_format,
+	.get_frame_interval = tvp514x_get_frame_interval,
+	.set_frame_interval = tvp514x_set_frame_interval,
 };
 
 static const struct v4l2_subdev_ops tvp514x_ops = {
diff --git a/drivers/media/usb/em28xx/em28xx-video.c b/drivers/media/usb/em28xx/em28xx-video.c
index 25e0620deff1..4aef584e21da 100644
--- a/drivers/media/usb/em28xx/em28xx-video.c
+++ b/drivers/media/usb/em28xx/em28xx-video.c
@@ -1607,7 +1607,8 @@ static int vidioc_g_parm(struct file *file, void *priv,
 	p->parm.capture.capability = V4L2_CAP_TIMEPERFRAME;
 	if (dev->is_webcam) {
 		rc = v4l2_device_call_until_err(&v4l2->v4l2_dev, 0,
-						video, g_frame_interval, &ival);
+						pad, get_frame_interval, NULL,
+						&ival);
 		if (!rc)
 			p->parm.capture.timeperframe = ival.interval;
 	} else {
@@ -1639,7 +1640,8 @@ static int vidioc_s_parm(struct file *file, void *priv,
 	p->parm.capture.readbuffers = EM28XX_MIN_BUF;
 	p->parm.capture.capability = V4L2_CAP_TIMEPERFRAME;
 	rc = v4l2_device_call_until_err(&dev->v4l2->v4l2_dev, 0,
-					video, s_frame_interval, &ival);
+					pad, set_frame_interval, NULL,
+					&ival);
 	if (!rc)
 		p->parm.capture.timeperframe = ival.interval;
 	return rc;
diff --git a/drivers/media/v4l2-core/v4l2-common.c b/drivers/media/v4l2-core/v4l2-common.c
index e9e7e70fa24e..273d83de2a87 100644
--- a/drivers/media/v4l2-core/v4l2-common.c
+++ b/drivers/media/v4l2-core/v4l2-common.c
@@ -195,9 +195,9 @@ int v4l2_g_parm_cap(struct video_device *vdev,
 
 	if (vdev->device_caps & V4L2_CAP_READWRITE)
 		a->parm.capture.readbuffers = 2;
-	if (v4l2_subdev_has_op(sd, video, g_frame_interval))
+	if (v4l2_subdev_has_op(sd, pad, get_frame_interval))
 		a->parm.capture.capability = V4L2_CAP_TIMEPERFRAME;
-	ret = v4l2_subdev_call(sd, video, g_frame_interval, &ival);
+	ret = v4l2_subdev_call_state_active(sd, pad, get_frame_interval, &ival);
 	if (!ret)
 		a->parm.capture.timeperframe = ival.interval;
 	return ret;
@@ -222,9 +222,9 @@ int v4l2_s_parm_cap(struct video_device *vdev,
 	else
 		a->parm.capture.readbuffers = 0;
 
-	if (v4l2_subdev_has_op(sd, video, g_frame_interval))
+	if (v4l2_subdev_has_op(sd, pad, get_frame_interval))
 		a->parm.capture.capability = V4L2_CAP_TIMEPERFRAME;
-	ret = v4l2_subdev_call(sd, video, s_frame_interval, &ival);
+	ret = v4l2_subdev_call_state_active(sd, pad, set_frame_interval, &ival);
 	if (!ret)
 		a->parm.capture.timeperframe = ival.interval;
 	return ret;
diff --git a/drivers/media/v4l2-core/v4l2-subdev.c b/drivers/media/v4l2-core/v4l2-subdev.c
index 1fa1acfa5b7b..405a4a2fa565 100644
--- a/drivers/media/v4l2-core/v4l2-subdev.c
+++ b/drivers/media/v4l2-core/v4l2-subdev.c
@@ -245,29 +245,6 @@ static int call_enum_frame_size(struct v4l2_subdev *sd,
 	       sd->ops->pad->enum_frame_size(sd, state, fse);
 }
 
-static inline int check_frame_interval(struct v4l2_subdev *sd,
-				       struct v4l2_subdev_frame_interval *fi)
-{
-	if (!fi)
-		return -EINVAL;
-
-	return check_pad(sd, fi->pad);
-}
-
-static int call_g_frame_interval(struct v4l2_subdev *sd,
-				 struct v4l2_subdev_frame_interval *fi)
-{
-	return check_frame_interval(sd, fi) ? :
-	       sd->ops->video->g_frame_interval(sd, fi);
-}
-
-static int call_s_frame_interval(struct v4l2_subdev *sd,
-				 struct v4l2_subdev_frame_interval *fi)
-{
-	return check_frame_interval(sd, fi) ? :
-	       sd->ops->video->s_frame_interval(sd, fi);
-}
-
 static int call_enum_frame_interval(struct v4l2_subdev *sd,
 				    struct v4l2_subdev_state *state,
 				    struct v4l2_subdev_frame_interval_enum *fie)
@@ -307,6 +284,34 @@ static int call_set_selection(struct v4l2_subdev *sd,
 	       sd->ops->pad->set_selection(sd, state, sel);
 }
 
+static inline int check_frame_interval(struct v4l2_subdev *sd,
+				       struct v4l2_subdev_state *state,
+				       struct v4l2_subdev_frame_interval *fi)
+{
+	if (!fi)
+		return -EINVAL;
+
+	return check_pad(sd, fi->pad) ? :
+	       check_state(sd, state, V4L2_SUBDEV_FORMAT_ACTIVE, fi->pad,
+			   fi->stream);
+}
+
+static int call_get_frame_interval(struct v4l2_subdev *sd,
+				   struct v4l2_subdev_state *state,
+				   struct v4l2_subdev_frame_interval *fi)
+{
+	return check_frame_interval(sd, state, fi) ? :
+	       sd->ops->pad->get_frame_interval(sd, state, fi);
+}
+
+static int call_set_frame_interval(struct v4l2_subdev *sd,
+				   struct v4l2_subdev_state *state,
+				   struct v4l2_subdev_frame_interval *fi)
+{
+	return check_frame_interval(sd, state, fi) ? :
+	       sd->ops->pad->set_frame_interval(sd, state, fi);
+}
+
 static int call_get_frame_desc(struct v4l2_subdev *sd, unsigned int pad,
 			       struct v4l2_mbus_frame_desc *fd)
 {
@@ -479,6 +484,8 @@ static const struct v4l2_subdev_pad_ops v4l2_subdev_call_pad_wrappers = {
 	.enum_frame_interval	= call_enum_frame_interval_state,
 	.get_selection		= call_get_selection_state,
 	.set_selection		= call_set_selection_state,
+	.get_frame_interval	= call_get_frame_interval,
+	.set_frame_interval	= call_set_frame_interval,
 	.get_edid		= call_get_edid,
 	.set_edid		= call_set_edid,
 	.dv_timings_cap		= call_dv_timings_cap,
@@ -488,8 +495,6 @@ static const struct v4l2_subdev_pad_ops v4l2_subdev_call_pad_wrappers = {
 };
 
 static const struct v4l2_subdev_video_ops v4l2_subdev_call_video_wrappers = {
-	.g_frame_interval	= call_g_frame_interval,
-	.s_frame_interval	= call_s_frame_interval,
 	.s_stream		= call_s_stream,
 };
 
@@ -531,6 +536,10 @@ subdev_ioctl_get_state(struct v4l2_subdev *sd, struct v4l2_subdev_fh *subdev_fh,
 	case VIDIOC_SUBDEV_S_SELECTION:
 		which = ((struct v4l2_subdev_selection *)arg)->which;
 		break;
+	case VIDIOC_SUBDEV_G_FRAME_INTERVAL:
+	case VIDIOC_SUBDEV_S_FRAME_INTERVAL:
+		which = V4L2_SUBDEV_FORMAT_ACTIVE;
+		break;
 	case VIDIOC_SUBDEV_G_ROUTING:
 	case VIDIOC_SUBDEV_S_ROUTING:
 		which = ((struct v4l2_subdev_routing *)arg)->which;
@@ -781,7 +790,7 @@ static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg,
 			fi->stream = 0;
 
 		memset(fi->reserved, 0, sizeof(fi->reserved));
-		return v4l2_subdev_call(sd, video, g_frame_interval, arg);
+		return v4l2_subdev_call(sd, pad, get_frame_interval, state, fi);
 	}
 
 	case VIDIOC_SUBDEV_S_FRAME_INTERVAL: {
@@ -794,7 +803,7 @@ static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg,
 			fi->stream = 0;
 
 		memset(fi->reserved, 0, sizeof(fi->reserved));
-		return v4l2_subdev_call(sd, video, s_frame_interval, arg);
+		return v4l2_subdev_call(sd, pad, set_frame_interval, state, fi);
 	}
 
 	case VIDIOC_SUBDEV_ENUM_FRAME_INTERVAL: {
diff --git a/drivers/staging/media/atomisp/i2c/atomisp-gc0310.c b/drivers/staging/media/atomisp/i2c/atomisp-gc0310.c
index 5d89e4c1b0c2..006e8adac47b 100644
--- a/drivers/staging/media/atomisp/i2c/atomisp-gc0310.c
+++ b/drivers/staging/media/atomisp/i2c/atomisp-gc0310.c
@@ -496,8 +496,9 @@ error_power_down:
 	return ret;
 }
 
-static int gc0310_g_frame_interval(struct v4l2_subdev *sd,
-				   struct v4l2_subdev_frame_interval *interval)
+static int gc0310_get_frame_interval(struct v4l2_subdev *sd,
+				     struct v4l2_subdev_state *sd_state,
+				     struct v4l2_subdev_frame_interval *interval)
 {
 	interval->interval.numerator = 1;
 	interval->interval.denominator = GC0310_FPS;
@@ -545,7 +546,6 @@ static const struct v4l2_subdev_sensor_ops gc0310_sensor_ops = {
 
 static const struct v4l2_subdev_video_ops gc0310_video_ops = {
 	.s_stream = gc0310_s_stream,
-	.g_frame_interval = gc0310_g_frame_interval,
 };
 
 static const struct v4l2_subdev_pad_ops gc0310_pad_ops = {
@@ -553,6 +553,7 @@ static const struct v4l2_subdev_pad_ops gc0310_pad_ops = {
 	.enum_frame_size = gc0310_enum_frame_size,
 	.get_fmt = gc0310_get_fmt,
 	.set_fmt = gc0310_set_fmt,
+	.get_frame_interval = gc0310_get_frame_interval,
 };
 
 static const struct v4l2_subdev_ops gc0310_ops = {
diff --git a/drivers/staging/media/atomisp/i2c/atomisp-gc2235.c b/drivers/staging/media/atomisp/i2c/atomisp-gc2235.c
index 9c20fe915238..aa257322a700 100644
--- a/drivers/staging/media/atomisp/i2c/atomisp-gc2235.c
+++ b/drivers/staging/media/atomisp/i2c/atomisp-gc2235.c
@@ -698,8 +698,9 @@ fail_power_off:
 	return ret;
 }
 
-static int gc2235_g_frame_interval(struct v4l2_subdev *sd,
-				   struct v4l2_subdev_frame_interval *interval)
+static int gc2235_get_frame_interval(struct v4l2_subdev *sd,
+				     struct v4l2_subdev_state *sd_state,
+				     struct v4l2_subdev_frame_interval *interval)
 {
 	struct gc2235_device *dev = to_gc2235_sensor(sd);
 
@@ -754,7 +755,6 @@ static const struct v4l2_subdev_sensor_ops gc2235_sensor_ops = {
 
 static const struct v4l2_subdev_video_ops gc2235_video_ops = {
 	.s_stream = gc2235_s_stream,
-	.g_frame_interval = gc2235_g_frame_interval,
 };
 
 static const struct v4l2_subdev_core_ops gc2235_core_ops = {
@@ -767,6 +767,7 @@ static const struct v4l2_subdev_pad_ops gc2235_pad_ops = {
 	.enum_frame_size = gc2235_enum_frame_size,
 	.get_fmt = gc2235_get_fmt,
 	.set_fmt = gc2235_set_fmt,
+	.get_frame_interval = gc2235_get_frame_interval,
 };
 
 static const struct v4l2_subdev_ops gc2235_ops = {
diff --git a/drivers/staging/media/atomisp/i2c/atomisp-mt9m114.c b/drivers/staging/media/atomisp/i2c/atomisp-mt9m114.c
index 8105365fbb2a..459c5b8233ce 100644
--- a/drivers/staging/media/atomisp/i2c/atomisp-mt9m114.c
+++ b/drivers/staging/media/atomisp/i2c/atomisp-mt9m114.c
@@ -1388,8 +1388,9 @@ static int mt9m114_t_vflip(struct v4l2_subdev *sd, int value)
 	return !!err;
 }
 
-static int mt9m114_g_frame_interval(struct v4l2_subdev *sd,
-				    struct v4l2_subdev_frame_interval *interval)
+static int mt9m114_get_frame_interval(struct v4l2_subdev *sd,
+				      struct v4l2_subdev_state *sd_state,
+				      struct v4l2_subdev_frame_interval *interval)
 {
 	struct mt9m114_device *dev = to_mt9m114_sensor(sd);
 
@@ -1479,7 +1480,6 @@ static int mt9m114_g_skip_frames(struct v4l2_subdev *sd, u32 *frames)
 
 static const struct v4l2_subdev_video_ops mt9m114_video_ops = {
 	.s_stream = mt9m114_s_stream,
-	.g_frame_interval = mt9m114_g_frame_interval,
 };
 
 static const struct v4l2_subdev_sensor_ops mt9m114_sensor_ops = {
@@ -1498,6 +1498,7 @@ static const struct v4l2_subdev_pad_ops mt9m114_pad_ops = {
 	.get_fmt = mt9m114_get_fmt,
 	.set_fmt = mt9m114_set_fmt,
 	.set_selection = mt9m114_s_exposure_selection,
+	.get_frame_interval = mt9m114_get_frame_interval,
 };
 
 static const struct v4l2_subdev_ops mt9m114_ops = {
diff --git a/drivers/staging/media/atomisp/i2c/atomisp-ov2722.c b/drivers/staging/media/atomisp/i2c/atomisp-ov2722.c
index 1de63c82cce1..b3ef04d7ccca 100644
--- a/drivers/staging/media/atomisp/i2c/atomisp-ov2722.c
+++ b/drivers/staging/media/atomisp/i2c/atomisp-ov2722.c
@@ -845,8 +845,9 @@ fail_power_off:
 	return ret;
 }
 
-static int ov2722_g_frame_interval(struct v4l2_subdev *sd,
-				   struct v4l2_subdev_frame_interval *interval)
+static int ov2722_get_frame_interval(struct v4l2_subdev *sd,
+				     struct v4l2_subdev_state *sd_state,
+				     struct v4l2_subdev_frame_interval *interval)
 {
 	struct ov2722_device *dev = to_ov2722_sensor(sd);
 
@@ -901,7 +902,6 @@ static const struct v4l2_subdev_sensor_ops ov2722_sensor_ops = {
 
 static const struct v4l2_subdev_video_ops ov2722_video_ops = {
 	.s_stream = ov2722_s_stream,
-	.g_frame_interval = ov2722_g_frame_interval,
 };
 
 static const struct v4l2_subdev_core_ops ov2722_core_ops = {
@@ -914,6 +914,7 @@ static const struct v4l2_subdev_pad_ops ov2722_pad_ops = {
 	.enum_frame_size = ov2722_enum_frame_size,
 	.get_fmt = ov2722_get_fmt,
 	.set_fmt = ov2722_set_fmt,
+	.get_frame_interval = ov2722_get_frame_interval,
 };
 
 static const struct v4l2_subdev_ops ov2722_ops = {
diff --git a/drivers/staging/media/atomisp/pci/atomisp_cmd.c b/drivers/staging/media/atomisp/pci/atomisp_cmd.c
index 759233a7ba50..f44e6412f4e3 100644
--- a/drivers/staging/media/atomisp/pci/atomisp_cmd.c
+++ b/drivers/staging/media/atomisp/pci/atomisp_cmd.c
@@ -105,8 +105,8 @@ static unsigned short atomisp_get_sensor_fps(struct atomisp_sub_device *asd)
 	unsigned short fps = 0;
 	int ret;
 
-	ret = v4l2_subdev_call(isp->inputs[asd->input_curr].camera,
-			       video, g_frame_interval, &fi);
+	ret = v4l2_subdev_call_state_active(isp->inputs[asd->input_curr].camera,
+					    pad, get_frame_interval, &fi);
 
 	if (!ret && fi.interval.numerator)
 		fps = fi.interval.denominator / fi.interval.numerator;
diff --git a/drivers/staging/media/atomisp/pci/atomisp_ioctl.c b/drivers/staging/media/atomisp/pci/atomisp_ioctl.c
index 09c0091b920f..01b7fa9b56a2 100644
--- a/drivers/staging/media/atomisp/pci/atomisp_ioctl.c
+++ b/drivers/staging/media/atomisp/pci/atomisp_ioctl.c
@@ -1739,8 +1739,8 @@ static int atomisp_s_parm(struct file *file, void *fh,
 
 		fi.interval = parm->parm.capture.timeperframe;
 
-		rval = v4l2_subdev_call(isp->inputs[asd->input_curr].camera,
-					video, s_frame_interval, &fi);
+		rval = v4l2_subdev_call_state_active(isp->inputs[asd->input_curr].camera,
+						     pad, set_frame_interval, &fi);
 		if (!rval)
 			parm->parm.capture.timeperframe = fi.interval;
 
diff --git a/drivers/staging/media/imx/imx-ic-prp.c b/drivers/staging/media/imx/imx-ic-prp.c
index 8bd9be49cc08..fb96f87e664e 100644
--- a/drivers/staging/media/imx/imx-ic-prp.c
+++ b/drivers/staging/media/imx/imx-ic-prp.c
@@ -393,8 +393,9 @@ out:
 	return ret;
 }
 
-static int prp_g_frame_interval(struct v4l2_subdev *sd,
-				struct v4l2_subdev_frame_interval *fi)
+static int prp_get_frame_interval(struct v4l2_subdev *sd,
+				  struct v4l2_subdev_state *sd_state,
+				  struct v4l2_subdev_frame_interval *fi)
 {
 	struct prp_priv *priv = sd_to_priv(sd);
 
@@ -408,8 +409,9 @@ static int prp_g_frame_interval(struct v4l2_subdev *sd,
 	return 0;
 }
 
-static int prp_s_frame_interval(struct v4l2_subdev *sd,
-				struct v4l2_subdev_frame_interval *fi)
+static int prp_set_frame_interval(struct v4l2_subdev *sd,
+				  struct v4l2_subdev_state *sd_state,
+				  struct v4l2_subdev_frame_interval *fi)
 {
 	struct prp_priv *priv = sd_to_priv(sd);
 
@@ -451,12 +453,12 @@ static const struct v4l2_subdev_pad_ops prp_pad_ops = {
 	.enum_mbus_code = prp_enum_mbus_code,
 	.get_fmt = prp_get_fmt,
 	.set_fmt = prp_set_fmt,
+	.get_frame_interval = prp_get_frame_interval,
+	.set_frame_interval = prp_set_frame_interval,
 	.link_validate = prp_link_validate,
 };
 
 static const struct v4l2_subdev_video_ops prp_video_ops = {
-	.g_frame_interval = prp_g_frame_interval,
-	.s_frame_interval = prp_s_frame_interval,
 	.s_stream = prp_s_stream,
 };
 
diff --git a/drivers/staging/media/imx/imx-ic-prpencvf.c b/drivers/staging/media/imx/imx-ic-prpencvf.c
index 04878f07eeba..7bfe433cd322 100644
--- a/drivers/staging/media/imx/imx-ic-prpencvf.c
+++ b/drivers/staging/media/imx/imx-ic-prpencvf.c
@@ -1203,8 +1203,9 @@ out:
 	return ret;
 }
 
-static int prp_g_frame_interval(struct v4l2_subdev *sd,
-				struct v4l2_subdev_frame_interval *fi)
+static int prp_get_frame_interval(struct v4l2_subdev *sd,
+				  struct v4l2_subdev_state *sd_state,
+				  struct v4l2_subdev_frame_interval *fi)
 {
 	struct prp_priv *priv = sd_to_priv(sd);
 
@@ -1218,8 +1219,9 @@ static int prp_g_frame_interval(struct v4l2_subdev *sd,
 	return 0;
 }
 
-static int prp_s_frame_interval(struct v4l2_subdev *sd,
-				struct v4l2_subdev_frame_interval *fi)
+static int prp_set_frame_interval(struct v4l2_subdev *sd,
+				  struct v4l2_subdev_state *sd_state,
+				  struct v4l2_subdev_frame_interval *fi)
 {
 	struct prp_priv *priv = sd_to_priv(sd);
 
@@ -1300,11 +1302,11 @@ static const struct v4l2_subdev_pad_ops prp_pad_ops = {
 	.enum_frame_size = prp_enum_frame_size,
 	.get_fmt = prp_get_fmt,
 	.set_fmt = prp_set_fmt,
+	.get_frame_interval = prp_get_frame_interval,
+	.set_frame_interval = prp_set_frame_interval,
 };
 
 static const struct v4l2_subdev_video_ops prp_video_ops = {
-	.g_frame_interval = prp_g_frame_interval,
-	.s_frame_interval = prp_s_frame_interval,
 	.s_stream = prp_s_stream,
 };
 
diff --git a/drivers/staging/media/imx/imx-media-capture.c b/drivers/staging/media/imx/imx-media-capture.c
index ce02199e7b1b..c944fb131b0a 100644
--- a/drivers/staging/media/imx/imx-media-capture.c
+++ b/drivers/staging/media/imx/imx-media-capture.c
@@ -511,7 +511,8 @@ static int capture_legacy_g_parm(struct file *file, void *fh,
 	if (a->type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
 		return -EINVAL;
 
-	ret = v4l2_subdev_call(priv->src_sd, video, g_frame_interval, &fi);
+	ret = v4l2_subdev_call_state_active(priv->src_sd, pad,
+					    get_frame_interval, &fi);
 	if (ret < 0)
 		return ret;
 
@@ -534,7 +535,8 @@ static int capture_legacy_s_parm(struct file *file, void *fh,
 		return -EINVAL;
 
 	fi.interval = a->parm.capture.timeperframe;
-	ret = v4l2_subdev_call(priv->src_sd, video, s_frame_interval, &fi);
+	ret = v4l2_subdev_call_state_active(priv->src_sd, pad,
+					    set_frame_interval, &fi);
 	if (ret < 0)
 		return ret;
 
diff --git a/drivers/staging/media/imx/imx-media-csi.c b/drivers/staging/media/imx/imx-media-csi.c
index 2fc94011fe4d..4308fdc9b58e 100644
--- a/drivers/staging/media/imx/imx-media-csi.c
+++ b/drivers/staging/media/imx/imx-media-csi.c
@@ -902,8 +902,9 @@ static const struct csi_skip_desc *csi_find_best_skip(struct v4l2_fract *in,
  * V4L2 subdev operations.
  */
 
-static int csi_g_frame_interval(struct v4l2_subdev *sd,
-				struct v4l2_subdev_frame_interval *fi)
+static int csi_get_frame_interval(struct v4l2_subdev *sd,
+				  struct v4l2_subdev_state *sd_state,
+				  struct v4l2_subdev_frame_interval *fi)
 {
 	struct csi_priv *priv = v4l2_get_subdevdata(sd);
 
@@ -919,8 +920,9 @@ static int csi_g_frame_interval(struct v4l2_subdev *sd,
 	return 0;
 }
 
-static int csi_s_frame_interval(struct v4l2_subdev *sd,
-				struct v4l2_subdev_frame_interval *fi)
+static int csi_set_frame_interval(struct v4l2_subdev *sd,
+				  struct v4l2_subdev_state *sd_state,
+				  struct v4l2_subdev_frame_interval *fi)
 {
 	struct csi_priv *priv = v4l2_get_subdevdata(sd);
 	struct v4l2_fract *input_fi;
@@ -1860,8 +1862,6 @@ static const struct v4l2_subdev_core_ops csi_core_ops = {
 };
 
 static const struct v4l2_subdev_video_ops csi_video_ops = {
-	.g_frame_interval = csi_g_frame_interval,
-	.s_frame_interval = csi_s_frame_interval,
 	.s_stream = csi_s_stream,
 };
 
@@ -1873,6 +1873,8 @@ static const struct v4l2_subdev_pad_ops csi_pad_ops = {
 	.set_fmt = csi_set_fmt,
 	.get_selection = csi_get_selection,
 	.set_selection = csi_set_selection,
+	.get_frame_interval = csi_get_frame_interval,
+	.set_frame_interval = csi_set_frame_interval,
 	.link_validate = csi_link_validate,
 };
 
diff --git a/drivers/staging/media/imx/imx-media-vdic.c b/drivers/staging/media/imx/imx-media-vdic.c
index 810b38ea3ab9..a51b37679239 100644
--- a/drivers/staging/media/imx/imx-media-vdic.c
+++ b/drivers/staging/media/imx/imx-media-vdic.c
@@ -780,8 +780,9 @@ static int vdic_link_validate(struct v4l2_subdev *sd,
 	return ret;
 }
 
-static int vdic_g_frame_interval(struct v4l2_subdev *sd,
-				struct v4l2_subdev_frame_interval *fi)
+static int vdic_get_frame_interval(struct v4l2_subdev *sd,
+				   struct v4l2_subdev_state *sd_state,
+				   struct v4l2_subdev_frame_interval *fi)
 {
 	struct vdic_priv *priv = v4l2_get_subdevdata(sd);
 
@@ -797,8 +798,9 @@ static int vdic_g_frame_interval(struct v4l2_subdev *sd,
 	return 0;
 }
 
-static int vdic_s_frame_interval(struct v4l2_subdev *sd,
-				struct v4l2_subdev_frame_interval *fi)
+static int vdic_set_frame_interval(struct v4l2_subdev *sd,
+				   struct v4l2_subdev_state *sd_state,
+				   struct v4l2_subdev_frame_interval *fi)
 {
 	struct vdic_priv *priv = v4l2_get_subdevdata(sd);
 	struct v4l2_fract *input_fi, *output_fi;
@@ -885,12 +887,12 @@ static const struct v4l2_subdev_pad_ops vdic_pad_ops = {
 	.enum_mbus_code = vdic_enum_mbus_code,
 	.get_fmt = vdic_get_fmt,
 	.set_fmt = vdic_set_fmt,
+	.get_frame_interval = vdic_get_frame_interval,
+	.set_frame_interval = vdic_set_frame_interval,
 	.link_validate = vdic_link_validate,
 };
 
 static const struct v4l2_subdev_video_ops vdic_video_ops = {
-	.g_frame_interval = vdic_g_frame_interval,
-	.s_frame_interval = vdic_s_frame_interval,
 	.s_stream = vdic_s_stream,
 };
 
diff --git a/drivers/staging/media/tegra-video/csi.c b/drivers/staging/media/tegra-video/csi.c
index 0d94115b9bbb..b1b666179be5 100644
--- a/drivers/staging/media/tegra-video/csi.c
+++ b/drivers/staging/media/tegra-video/csi.c
@@ -222,8 +222,9 @@ static int csi_set_format(struct v4l2_subdev *subdev,
 /*
  * V4L2 Subdevice Video Operations
  */
-static int tegra_csi_g_frame_interval(struct v4l2_subdev *subdev,
-				      struct v4l2_subdev_frame_interval *vfi)
+static int tegra_csi_get_frame_interval(struct v4l2_subdev *subdev,
+					struct v4l2_subdev_state *sd_state,
+					struct v4l2_subdev_frame_interval *vfi)
 {
 	struct tegra_csi_channel *csi_chan = to_csi_chan(subdev);
 
@@ -430,8 +431,6 @@ static int tegra_csi_s_stream(struct v4l2_subdev *subdev, int enable)
  */
 static const struct v4l2_subdev_video_ops tegra_csi_video_ops = {
 	.s_stream = tegra_csi_s_stream,
-	.g_frame_interval = tegra_csi_g_frame_interval,
-	.s_frame_interval = tegra_csi_g_frame_interval,
 };
 
 static const struct v4l2_subdev_pad_ops tegra_csi_pad_ops = {
@@ -440,6 +439,8 @@ static const struct v4l2_subdev_pad_ops tegra_csi_pad_ops = {
 	.enum_frame_interval	= csi_enum_frameintervals,
 	.get_fmt		= csi_get_format,
 	.set_fmt		= csi_set_format,
+	.get_frame_interval	= tegra_csi_get_frame_interval,
+	.set_frame_interval	= tegra_csi_get_frame_interval,
 };
 
 static const struct v4l2_subdev_ops tegra_csi_ops = {
diff --git a/include/media/v4l2-common.h b/include/media/v4l2-common.h
index d278836fd9cb..acf5be24a5ca 100644
--- a/include/media/v4l2-common.h
+++ b/include/media/v4l2-common.h
@@ -425,7 +425,7 @@ __v4l2_find_nearest_size(const void *array, size_t array_size,
 
 /**
  * v4l2_g_parm_cap - helper routine for vidioc_g_parm to fill this in by
- *      calling the g_frame_interval op of the given subdev. It only works
+ *      calling the get_frame_interval op of the given subdev. It only works
  *      for V4L2_BUF_TYPE_VIDEO_CAPTURE(_MPLANE), hence the _cap in the
  *      function name.
  *
@@ -438,7 +438,7 @@ int v4l2_g_parm_cap(struct video_device *vdev,
 
 /**
  * v4l2_s_parm_cap - helper routine for vidioc_s_parm to fill this in by
- *      calling the s_frame_interval op of the given subdev. It only works
+ *      calling the set_frame_interval op of the given subdev. It only works
  *      for V4L2_BUF_TYPE_VIDEO_CAPTURE(_MPLANE), hence the _cap in the
  *      function name.
  *
diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h
index 61024a74ce38..0ab7dce098e6 100644
--- a/include/media/v4l2-subdev.h
+++ b/include/media/v4l2-subdev.h
@@ -452,12 +452,6 @@ enum v4l2_subdev_pre_streamon_flags {
  *
  * @g_pixelaspect: callback to return the pixelaspect ratio.
  *
- * @g_frame_interval: callback for VIDIOC_SUBDEV_G_FRAME_INTERVAL()
- *		      ioctl handler code.
- *
- * @s_frame_interval: callback for VIDIOC_SUBDEV_S_FRAME_INTERVAL()
- *		      ioctl handler code.
- *
  * @s_dv_timings: Set custom dv timings in the sub device. This is used
  *	when sub device is capable of setting detailed timing information
  *	in the hardware to generate/detect the video signal.
@@ -496,10 +490,6 @@ struct v4l2_subdev_video_ops {
 	int (*g_input_status)(struct v4l2_subdev *sd, u32 *status);
 	int (*s_stream)(struct v4l2_subdev *sd, int enable);
 	int (*g_pixelaspect)(struct v4l2_subdev *sd, struct v4l2_fract *aspect);
-	int (*g_frame_interval)(struct v4l2_subdev *sd,
-				struct v4l2_subdev_frame_interval *interval);
-	int (*s_frame_interval)(struct v4l2_subdev *sd,
-				struct v4l2_subdev_frame_interval *interval);
 	int (*s_dv_timings)(struct v4l2_subdev *sd,
 			struct v4l2_dv_timings *timings);
 	int (*g_dv_timings)(struct v4l2_subdev *sd,
@@ -787,6 +777,12 @@ struct v4l2_subdev_state {
  *
  * @set_selection: callback for VIDIOC_SUBDEV_S_SELECTION() ioctl handler code.
  *
+ * @get_frame_interval: callback for VIDIOC_SUBDEV_G_FRAME_INTERVAL()
+ *			ioctl handler code.
+ *
+ * @set_frame_interval: callback for VIDIOC_SUBDEV_S_FRAME_INTERVAL()
+ *			ioctl handler code.
+ *
  * @get_edid: callback for VIDIOC_SUBDEV_G_EDID() ioctl handler code.
  *
  * @set_edid: callback for VIDIOC_SUBDEV_S_EDID() ioctl handler code.
@@ -856,6 +852,12 @@ struct v4l2_subdev_pad_ops {
 	int (*set_selection)(struct v4l2_subdev *sd,
 			     struct v4l2_subdev_state *state,
 			     struct v4l2_subdev_selection *sel);
+	int (*get_frame_interval)(struct v4l2_subdev *sd,
+				  struct v4l2_subdev_state *state,
+				  struct v4l2_subdev_frame_interval *interval);
+	int (*set_frame_interval)(struct v4l2_subdev *sd,
+				  struct v4l2_subdev_state *state,
+				  struct v4l2_subdev_frame_interval *interval);
 	int (*get_edid)(struct v4l2_subdev *sd, struct v4l2_edid *edid);
 	int (*set_edid)(struct v4l2_subdev *sd, struct v4l2_edid *edid);
 	int (*dv_timings_cap)(struct v4l2_subdev *sd,
-- 
cgit v1.2.3


From 805d4311a54a25d7347684fdf778c6239b190864 Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Date: Wed, 13 Dec 2023 17:00:05 +0200
Subject: media: v4l2-subdev: Add which field to struct
 v4l2_subdev_frame_interval

Due to a historical mishap, the v4l2_subdev_frame_interval structure
is the only part of the V4L2 subdev userspace API that doesn't contain a
'which' field. This prevents trying frame intervals using the subdev
'TRY' state mechanism.

Adding a 'which' field is simple as the structure has 8 reserved fields.
This would however break userspace as the field is currently set to 0,
corresponding to V4L2_SUBDEV_FORMAT_TRY, while the corresponding ioctls
currently operate on the 'ACTIVE' state. We thus need to add a new
subdev client cap, V4L2_SUBDEV_CLIENT_CAP_INTERVAL_USES_WHICH, to
indicate that userspace is aware of this new field.

All drivers that implement the subdev .get_frame_interval() and
.set_frame_interval() operations are updated to return -EINVAL when
operating on the TRY state, preserving the current behaviour.

While at it, fix a bad copy&paste in the documentation of the struct
v4l2_subdev_frame_interval_enum 'which' field.

Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de> # for imx-media
Reviewed-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Reviewed-by: Luca Ceresoli <luca.ceresoli@bootlin.com> # for tegra-video
Reviewed-by: Mauro Carvalho Chehab <mchehab@kernel.org>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
---
 .../media/v4l/vidioc-subdev-g-client-cap.rst       |  5 +++++
 .../media/v4l/vidioc-subdev-g-frame-interval.rst   | 17 +++++++++------
 drivers/media/i2c/adv7180.c                        |  7 ++++++
 drivers/media/i2c/alvium-csi2.c                    | 14 ++++++++++++
 drivers/media/i2c/et8ek8/et8ek8_driver.c           | 14 ++++++++++++
 drivers/media/i2c/imx214.c                         |  7 ++++++
 drivers/media/i2c/imx274.c                         | 14 ++++++++++++
 drivers/media/i2c/max9286.c                        | 14 ++++++++++++
 drivers/media/i2c/mt9m111.c                        | 14 ++++++++++++
 drivers/media/i2c/mt9m114.c                        | 14 ++++++++++++
 drivers/media/i2c/mt9v011.c                        | 14 ++++++++++++
 drivers/media/i2c/mt9v111.c                        | 14 ++++++++++++
 drivers/media/i2c/ov2680.c                         |  7 ++++++
 drivers/media/i2c/ov5640.c                         | 14 ++++++++++++
 drivers/media/i2c/ov5648.c                         |  7 ++++++
 drivers/media/i2c/ov5693.c                         |  7 ++++++
 drivers/media/i2c/ov6650.c                         | 14 ++++++++++++
 drivers/media/i2c/ov7251.c                         | 14 ++++++++++++
 drivers/media/i2c/ov7670.c                         | 12 +++++++++++
 drivers/media/i2c/ov772x.c                         | 14 ++++++++++++
 drivers/media/i2c/ov8865.c                         |  7 ++++++
 drivers/media/i2c/ov9650.c                         | 14 ++++++++++++
 drivers/media/i2c/s5c73m3/s5c73m3-core.c           | 14 ++++++++++++
 drivers/media/i2c/s5k5baf.c                        | 14 ++++++++++++
 drivers/media/i2c/thp7312.c                        | 14 ++++++++++++
 drivers/media/i2c/tvp514x.c                        | 12 +++++++++++
 drivers/media/v4l2-core/v4l2-subdev.c              | 25 ++++++++++++++--------
 drivers/staging/media/atomisp/i2c/atomisp-gc0310.c |  7 ++++++
 drivers/staging/media/atomisp/i2c/atomisp-gc2235.c |  7 ++++++
 .../staging/media/atomisp/i2c/atomisp-mt9m114.c    |  7 ++++++
 drivers/staging/media/atomisp/i2c/atomisp-ov2722.c |  7 ++++++
 drivers/staging/media/imx/imx-ic-prp.c             | 14 ++++++++++++
 drivers/staging/media/imx/imx-ic-prpencvf.c        | 14 ++++++++++++
 drivers/staging/media/imx/imx-media-csi.c          | 14 ++++++++++++
 drivers/staging/media/imx/imx-media-vdic.c         | 14 ++++++++++++
 drivers/staging/media/tegra-video/csi.c            |  7 ++++++
 include/uapi/linux/v4l2-subdev.h                   | 15 ++++++++++---
 37 files changed, 425 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/Documentation/userspace-api/media/v4l/vidioc-subdev-g-client-cap.rst b/Documentation/userspace-api/media/v4l/vidioc-subdev-g-client-cap.rst
index 20f12a1cc0f7..810b6a859dc8 100644
--- a/Documentation/userspace-api/media/v4l/vidioc-subdev-g-client-cap.rst
+++ b/Documentation/userspace-api/media/v4l/vidioc-subdev-g-client-cap.rst
@@ -71,6 +71,11 @@ is unknown to the kernel.
         of 'stream' fields (referring to the stream number) with various
         ioctls. If this is not set (which is the default), the 'stream' fields
         will be forced to 0 by the kernel.
+    * - ``V4L2_SUBDEV_CLIENT_CAP_INTERVAL_USES_WHICH``
+      - The client is aware of the :c:type:`v4l2_subdev_frame_interval`
+        ``which`` field. If this is not set (which is the default), the
+        ``which`` field is forced to ``V4L2_SUBDEV_FORMAT_ACTIVE`` by the
+        kernel.
 
 Return Value
 ============
diff --git a/Documentation/userspace-api/media/v4l/vidioc-subdev-g-frame-interval.rst b/Documentation/userspace-api/media/v4l/vidioc-subdev-g-frame-interval.rst
index 842f962d2aea..41e0e2c8ecc3 100644
--- a/Documentation/userspace-api/media/v4l/vidioc-subdev-g-frame-interval.rst
+++ b/Documentation/userspace-api/media/v4l/vidioc-subdev-g-frame-interval.rst
@@ -58,8 +58,9 @@ struct
 contains the current frame interval as would be returned by a
 ``VIDIOC_SUBDEV_G_FRAME_INTERVAL`` call.
 
-Calling ``VIDIOC_SUBDEV_S_FRAME_INTERVAL`` on a subdev device node that has been
-registered in read-only mode is not allowed. An error is returned and the errno
+If the subdev device node has been registered in read-only mode, calls to
+``VIDIOC_SUBDEV_S_FRAME_INTERVAL`` are only valid if the ``which`` field is set
+to ``V4L2_SUBDEV_FORMAT_TRY``, otherwise an error is returned and the errno
 variable is set to ``-EPERM``.
 
 Drivers must not return an error solely because the requested interval
@@ -93,7 +94,11 @@ the same sub-device is not defined.
       - ``stream``
       - Stream identifier.
     * - __u32
-      - ``reserved``\ [8]
+      - ``which``
+      - Active or try frame interval, from enum
+	:ref:`v4l2_subdev_format_whence <v4l2-subdev-format-whence>`.
+    * - __u32
+      - ``reserved``\ [7]
       - Reserved for future extensions. Applications and drivers must set
 	the array to zero.
 
@@ -114,9 +119,9 @@ EBUSY
 EINVAL
     The struct
     :c:type:`v4l2_subdev_frame_interval`
-    ``pad`` references a non-existing pad, or the pad doesn't support
-    frame intervals.
+    ``pad`` references a non-existing pad, the ``which`` field references a
+    non-existing frame interval, or the pad doesn't support frame intervals.
 
 EPERM
     The ``VIDIOC_SUBDEV_S_FRAME_INTERVAL`` ioctl has been called on a read-only
-    subdevice.
+    subdevice and the ``which`` field is set to ``V4L2_SUBDEV_FORMAT_ACTIVE``.
diff --git a/drivers/media/i2c/adv7180.c b/drivers/media/i2c/adv7180.c
index 7ed86030fb5c..409b9a37f018 100644
--- a/drivers/media/i2c/adv7180.c
+++ b/drivers/media/i2c/adv7180.c
@@ -469,6 +469,13 @@ static int adv7180_get_frame_interval(struct v4l2_subdev *sd,
 {
 	struct adv7180_state *state = to_state(sd);
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	if (state->curr_norm & V4L2_STD_525_60) {
 		fi->interval.numerator = 1001;
 		fi->interval.denominator = 30000;
diff --git a/drivers/media/i2c/alvium-csi2.c b/drivers/media/i2c/alvium-csi2.c
index a173abb0509f..34ff7fad3877 100644
--- a/drivers/media/i2c/alvium-csi2.c
+++ b/drivers/media/i2c/alvium-csi2.c
@@ -1654,6 +1654,13 @@ static int alvium_g_frame_interval(struct v4l2_subdev *sd,
 {
 	struct alvium_dev *alvium = sd_to_alvium(sd);
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	fi->interval = alvium->frame_interval;
 
 	return 0;
@@ -1703,6 +1710,13 @@ static int alvium_s_frame_interval(struct v4l2_subdev *sd,
 	struct alvium_dev *alvium = sd_to_alvium(sd);
 	int ret;
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	if (alvium->streaming)
 		return -EBUSY;
 
diff --git a/drivers/media/i2c/et8ek8/et8ek8_driver.c b/drivers/media/i2c/et8ek8/et8ek8_driver.c
index 71fb5aebd3df..f548b1bb75fb 100644
--- a/drivers/media/i2c/et8ek8/et8ek8_driver.c
+++ b/drivers/media/i2c/et8ek8/et8ek8_driver.c
@@ -1051,6 +1051,13 @@ static int et8ek8_get_frame_interval(struct v4l2_subdev *subdev,
 {
 	struct et8ek8_sensor *sensor = to_et8ek8_sensor(subdev);
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	memset(fi, 0, sizeof(*fi));
 	fi->interval = sensor->current_reglist->mode.timeperframe;
 
@@ -1064,6 +1071,13 @@ static int et8ek8_set_frame_interval(struct v4l2_subdev *subdev,
 	struct et8ek8_sensor *sensor = to_et8ek8_sensor(subdev);
 	struct et8ek8_reglist *reglist;
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	reglist = et8ek8_reglist_find_mode_ival(&meta_reglist,
 						sensor->current_reglist,
 						&fi->interval);
diff --git a/drivers/media/i2c/imx214.c b/drivers/media/i2c/imx214.c
index 8e832a4e3544..b148b1bd2bc3 100644
--- a/drivers/media/i2c/imx214.c
+++ b/drivers/media/i2c/imx214.c
@@ -905,6 +905,13 @@ static int imx214_get_frame_interval(struct v4l2_subdev *subdev,
 				     struct v4l2_subdev_state *sd_state,
 				     struct v4l2_subdev_frame_interval *fival)
 {
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (fival->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	fival->interval.numerator = 1;
 	fival->interval.denominator = IMX214_FPS;
 
diff --git a/drivers/media/i2c/imx274.c b/drivers/media/i2c/imx274.c
index 4040c642a36f..352da68b8b41 100644
--- a/drivers/media/i2c/imx274.c
+++ b/drivers/media/i2c/imx274.c
@@ -1333,6 +1333,13 @@ static int imx274_get_frame_interval(struct v4l2_subdev *sd,
 {
 	struct stimx274 *imx274 = to_imx274(sd);
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	fi->interval = imx274->frame_interval;
 	dev_dbg(&imx274->client->dev, "%s frame rate = %d / %d\n",
 		__func__, imx274->frame_interval.numerator,
@@ -1350,6 +1357,13 @@ static int imx274_set_frame_interval(struct v4l2_subdev *sd,
 	int min, max, def;
 	int ret;
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	ret = pm_runtime_resume_and_get(&imx274->client->dev);
 	if (ret < 0)
 		return ret;
diff --git a/drivers/media/i2c/max9286.c b/drivers/media/i2c/max9286.c
index 7e8cb53d31c3..d685d445cf23 100644
--- a/drivers/media/i2c/max9286.c
+++ b/drivers/media/i2c/max9286.c
@@ -874,6 +874,13 @@ static int max9286_get_frame_interval(struct v4l2_subdev *sd,
 {
 	struct max9286_priv *priv = sd_to_max9286(sd);
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (interval->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	if (interval->pad != MAX9286_SRC_PAD)
 		return -EINVAL;
 
@@ -888,6 +895,13 @@ static int max9286_set_frame_interval(struct v4l2_subdev *sd,
 {
 	struct max9286_priv *priv = sd_to_max9286(sd);
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (interval->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	if (interval->pad != MAX9286_SRC_PAD)
 		return -EINVAL;
 
diff --git a/drivers/media/i2c/mt9m111.c b/drivers/media/i2c/mt9m111.c
index 602954650f2e..ceeeb94c38d5 100644
--- a/drivers/media/i2c/mt9m111.c
+++ b/drivers/media/i2c/mt9m111.c
@@ -1051,6 +1051,13 @@ static int mt9m111_get_frame_interval(struct v4l2_subdev *sd,
 {
 	struct mt9m111 *mt9m111 = container_of(sd, struct mt9m111, subdev);
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	fi->interval = mt9m111->frame_interval;
 
 	return 0;
@@ -1068,6 +1075,13 @@ static int mt9m111_set_frame_interval(struct v4l2_subdev *sd,
 	if (mt9m111->is_streaming)
 		return -EBUSY;
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	if (fi->pad != 0)
 		return -EINVAL;
 
diff --git a/drivers/media/i2c/mt9m114.c b/drivers/media/i2c/mt9m114.c
index dcd94299787c..427eae13ce26 100644
--- a/drivers/media/i2c/mt9m114.c
+++ b/drivers/media/i2c/mt9m114.c
@@ -1592,6 +1592,13 @@ static int mt9m114_ifp_get_frame_interval(struct v4l2_subdev *sd,
 	struct v4l2_fract *ival = &interval->interval;
 	struct mt9m114 *sensor = ifp_to_mt9m114(sd);
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (interval->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	mutex_lock(sensor->ifp.hdl.lock);
 
 	ival->numerator = 1;
@@ -1610,6 +1617,13 @@ static int mt9m114_ifp_set_frame_interval(struct v4l2_subdev *sd,
 	struct mt9m114 *sensor = ifp_to_mt9m114(sd);
 	int ret = 0;
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (interval->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	mutex_lock(sensor->ifp.hdl.lock);
 
 	if (ival->numerator != 0 && ival->denominator != 0)
diff --git a/drivers/media/i2c/mt9v011.c b/drivers/media/i2c/mt9v011.c
index 3485761428ba..8834ff8786e5 100644
--- a/drivers/media/i2c/mt9v011.c
+++ b/drivers/media/i2c/mt9v011.c
@@ -366,6 +366,13 @@ static int mt9v011_get_frame_interval(struct v4l2_subdev *sd,
 				      struct v4l2_subdev_state *sd_state,
 				      struct v4l2_subdev_frame_interval *ival)
 {
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (ival->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	calc_fps(sd,
 		 &ival->interval.numerator,
 		 &ival->interval.denominator);
@@ -380,6 +387,13 @@ static int mt9v011_set_frame_interval(struct v4l2_subdev *sd,
 	struct v4l2_fract *tpf = &ival->interval;
 	u16 speed;
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (ival->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	speed = calc_speed(sd, tpf->numerator, tpf->denominator);
 
 	mt9v011_write(sd, R0A_MT9V011_CLK_SPEED, speed);
diff --git a/drivers/media/i2c/mt9v111.c b/drivers/media/i2c/mt9v111.c
index 496be67c971b..b0b98ed3c150 100644
--- a/drivers/media/i2c/mt9v111.c
+++ b/drivers/media/i2c/mt9v111.c
@@ -730,6 +730,13 @@ static int mt9v111_set_frame_interval(struct v4l2_subdev *sd,
 			   tpf->denominator;
 	unsigned int max_fps;
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (ival->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	if (!tpf->numerator)
 		tpf->numerator = 1;
 
@@ -779,6 +786,13 @@ static int mt9v111_get_frame_interval(struct v4l2_subdev *sd,
 	struct mt9v111_dev *mt9v111 = sd_to_mt9v111(sd);
 	struct v4l2_fract *tpf = &ival->interval;
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (ival->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	mutex_lock(&mt9v111->stream_mutex);
 
 	tpf->numerator = 1;
diff --git a/drivers/media/i2c/ov2680.c b/drivers/media/i2c/ov2680.c
index e3ff64a9e6ca..39d321e2b7f9 100644
--- a/drivers/media/i2c/ov2680.c
+++ b/drivers/media/i2c/ov2680.c
@@ -558,6 +558,13 @@ static int ov2680_get_frame_interval(struct v4l2_subdev *sd,
 {
 	struct ov2680_dev *sensor = to_ov2680_dev(sd);
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	mutex_lock(&sensor->lock);
 	fi->interval = sensor->mode.frame_interval;
 	mutex_unlock(&sensor->lock);
diff --git a/drivers/media/i2c/ov5640.c b/drivers/media/i2c/ov5640.c
index 336bfd1ffd32..5162d45fe73b 100644
--- a/drivers/media/i2c/ov5640.c
+++ b/drivers/media/i2c/ov5640.c
@@ -3610,6 +3610,13 @@ static int ov5640_get_frame_interval(struct v4l2_subdev *sd,
 {
 	struct ov5640_dev *sensor = to_ov5640_dev(sd);
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	mutex_lock(&sensor->lock);
 	fi->interval = sensor->frame_interval;
 	mutex_unlock(&sensor->lock);
@@ -3625,6 +3632,13 @@ static int ov5640_set_frame_interval(struct v4l2_subdev *sd,
 	const struct ov5640_mode_info *mode;
 	int frame_rate, ret = 0;
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	if (fi->pad != 0)
 		return -EINVAL;
 
diff --git a/drivers/media/i2c/ov5648.c b/drivers/media/i2c/ov5648.c
index d0d7e9968f48..4b86d2631bd1 100644
--- a/drivers/media/i2c/ov5648.c
+++ b/drivers/media/i2c/ov5648.c
@@ -2276,6 +2276,13 @@ static int ov5648_get_frame_interval(struct v4l2_subdev *subdev,
 	const struct ov5648_mode *mode;
 	int ret = 0;
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (interval->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	mutex_lock(&sensor->mutex);
 
 	mode = sensor->state.mode;
diff --git a/drivers/media/i2c/ov5693.c b/drivers/media/i2c/ov5693.c
index a65645811fbc..8deb28b55983 100644
--- a/drivers/media/i2c/ov5693.c
+++ b/drivers/media/i2c/ov5693.c
@@ -1013,6 +1013,13 @@ static int ov5693_get_frame_interval(struct v4l2_subdev *sd,
 				 ov5693->ctrls.vblank->val);
 	unsigned int fps = DIV_ROUND_CLOSEST(OV5693_PIXEL_RATE, framesize);
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (interval->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	interval->interval.numerator = 1;
 	interval->interval.denominator = fps;
 
diff --git a/drivers/media/i2c/ov6650.c b/drivers/media/i2c/ov6650.c
index a4dc45bdf3d7..b65befb22a79 100644
--- a/drivers/media/i2c/ov6650.c
+++ b/drivers/media/i2c/ov6650.c
@@ -806,6 +806,13 @@ static int ov6650_get_frame_interval(struct v4l2_subdev *sd,
 	struct i2c_client *client = v4l2_get_subdevdata(sd);
 	struct ov6650 *priv = to_ov6650(client);
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (ival->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	ival->interval = priv->tpf;
 
 	dev_dbg(&client->dev, "Frame interval: %u/%u s\n",
@@ -823,6 +830,13 @@ static int ov6650_set_frame_interval(struct v4l2_subdev *sd,
 	struct v4l2_fract *tpf = &ival->interval;
 	int div, ret;
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (ival->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	if (tpf->numerator == 0 || tpf->denominator == 0)
 		div = 1;  /* Reset to full rate */
 	else
diff --git a/drivers/media/i2c/ov7251.c b/drivers/media/i2c/ov7251.c
index 10d6b5deed83..30f61e04ecaf 100644
--- a/drivers/media/i2c/ov7251.c
+++ b/drivers/media/i2c/ov7251.c
@@ -1391,6 +1391,13 @@ static int ov7251_get_frame_interval(struct v4l2_subdev *subdev,
 {
 	struct ov7251 *ov7251 = to_ov7251(subdev);
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	mutex_lock(&ov7251->lock);
 	fi->interval = ov7251->current_mode->timeperframe;
 	mutex_unlock(&ov7251->lock);
@@ -1406,6 +1413,13 @@ static int ov7251_set_frame_interval(struct v4l2_subdev *subdev,
 	const struct ov7251_mode_info *new_mode;
 	int ret = 0;
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	mutex_lock(&ov7251->lock);
 	new_mode = ov7251_find_mode_by_ival(ov7251, &fi->interval);
 
diff --git a/drivers/media/i2c/ov7670.c b/drivers/media/i2c/ov7670.c
index 463f20ece36e..0cb96b6c9990 100644
--- a/drivers/media/i2c/ov7670.c
+++ b/drivers/media/i2c/ov7670.c
@@ -1160,6 +1160,12 @@ static int ov7670_get_frame_interval(struct v4l2_subdev *sd,
 {
 	struct ov7670_info *info = to_state(sd);
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (ival->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
 
 	info->devtype->get_framerate(sd, &ival->interval);
 
@@ -1173,6 +1179,12 @@ static int ov7670_set_frame_interval(struct v4l2_subdev *sd,
 	struct v4l2_fract *tpf = &ival->interval;
 	struct ov7670_info *info = to_state(sd);
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (ival->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
 
 	return info->devtype->set_framerate(sd, tpf);
 }
diff --git a/drivers/media/i2c/ov772x.c b/drivers/media/i2c/ov772x.c
index a14a25946c5b..3e36a55274ef 100644
--- a/drivers/media/i2c/ov772x.c
+++ b/drivers/media/i2c/ov772x.c
@@ -724,6 +724,13 @@ static int ov772x_get_frame_interval(struct v4l2_subdev *sd,
 	struct ov772x_priv *priv = to_ov772x(sd);
 	struct v4l2_fract *tpf = &ival->interval;
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (ival->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	tpf->numerator = 1;
 	tpf->denominator = priv->fps;
 
@@ -739,6 +746,13 @@ static int ov772x_set_frame_interval(struct v4l2_subdev *sd,
 	unsigned int fps;
 	int ret = 0;
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (ival->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	mutex_lock(&priv->lock);
 
 	if (priv->streaming) {
diff --git a/drivers/media/i2c/ov8865.c b/drivers/media/i2c/ov8865.c
index 02a595281c49..95ffe7536aa6 100644
--- a/drivers/media/i2c/ov8865.c
+++ b/drivers/media/i2c/ov8865.c
@@ -2846,6 +2846,13 @@ static int ov8865_get_frame_interval(struct v4l2_subdev *subdev,
 	unsigned int framesize;
 	unsigned int fps;
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (interval->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	mutex_lock(&sensor->mutex);
 
 	mode = sensor->state.mode;
diff --git a/drivers/media/i2c/ov9650.c b/drivers/media/i2c/ov9650.c
index f528892c893f..66cd0e9ddc9a 100644
--- a/drivers/media/i2c/ov9650.c
+++ b/drivers/media/i2c/ov9650.c
@@ -1107,6 +1107,13 @@ static int ov965x_get_frame_interval(struct v4l2_subdev *sd,
 {
 	struct ov965x *ov965x = to_ov965x(sd);
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	mutex_lock(&ov965x->lock);
 	fi->interval = ov965x->fiv->interval;
 	mutex_unlock(&ov965x->lock);
@@ -1156,6 +1163,13 @@ static int ov965x_set_frame_interval(struct v4l2_subdev *sd,
 	struct ov965x *ov965x = to_ov965x(sd);
 	int ret;
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	v4l2_dbg(1, debug, sd, "Setting %d/%d frame interval\n",
 		 fi->interval.numerator, fi->interval.denominator);
 
diff --git a/drivers/media/i2c/s5c73m3/s5c73m3-core.c b/drivers/media/i2c/s5c73m3/s5c73m3-core.c
index 73ca50f49812..af8d01f78c32 100644
--- a/drivers/media/i2c/s5c73m3/s5c73m3-core.c
+++ b/drivers/media/i2c/s5c73m3/s5c73m3-core.c
@@ -872,6 +872,13 @@ static int s5c73m3_oif_get_frame_interval(struct v4l2_subdev *sd,
 {
 	struct s5c73m3 *state = oif_sd_to_s5c73m3(sd);
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	if (fi->pad != OIF_SOURCE_PAD)
 		return -EINVAL;
 
@@ -923,6 +930,13 @@ static int s5c73m3_oif_set_frame_interval(struct v4l2_subdev *sd,
 	struct s5c73m3 *state = oif_sd_to_s5c73m3(sd);
 	int ret;
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	if (fi->pad != OIF_SOURCE_PAD)
 		return -EINVAL;
 
diff --git a/drivers/media/i2c/s5k5baf.c b/drivers/media/i2c/s5k5baf.c
index 2fd1ecfeb086..de079d2c9282 100644
--- a/drivers/media/i2c/s5k5baf.c
+++ b/drivers/media/i2c/s5k5baf.c
@@ -1124,6 +1124,13 @@ static int s5k5baf_get_frame_interval(struct v4l2_subdev *sd,
 {
 	struct s5k5baf *state = to_s5k5baf(sd);
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	mutex_lock(&state->lock);
 	fi->interval.numerator = state->fiv;
 	fi->interval.denominator = 10000;
@@ -1162,6 +1169,13 @@ static int s5k5baf_set_frame_interval(struct v4l2_subdev *sd,
 {
 	struct s5k5baf *state = to_s5k5baf(sd);
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	mutex_lock(&state->lock);
 	__s5k5baf_set_frame_interval(state, fi);
 	mutex_unlock(&state->lock);
diff --git a/drivers/media/i2c/thp7312.c b/drivers/media/i2c/thp7312.c
index d4975b180704..ad4f2b794e1a 100644
--- a/drivers/media/i2c/thp7312.c
+++ b/drivers/media/i2c/thp7312.c
@@ -740,6 +740,13 @@ static int thp7312_get_frame_interval(struct v4l2_subdev *sd,
 {
 	struct thp7312_device *thp7312 = to_thp7312_dev(sd);
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	fi->interval.numerator = 1;
 	fi->interval.denominator = thp7312->current_rate->fps;
 
@@ -757,6 +764,13 @@ static int thp7312_set_frame_interval(struct v4l2_subdev *sd,
 	unsigned int best_delta = UINT_MAX;
 	unsigned int fps;
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	/* Avoid divisions by 0, pick the highest frame if the interval is 0. */
 	fps = fi->interval.numerator
 	    ? DIV_ROUND_CLOSEST(fi->interval.denominator, fi->interval.numerator)
diff --git a/drivers/media/i2c/tvp514x.c b/drivers/media/i2c/tvp514x.c
index dee0cf992379..5a561e5bf659 100644
--- a/drivers/media/i2c/tvp514x.c
+++ b/drivers/media/i2c/tvp514x.c
@@ -746,6 +746,12 @@ tvp514x_get_frame_interval(struct v4l2_subdev *sd,
 	struct tvp514x_decoder *decoder = to_decoder(sd);
 	enum tvp514x_std current_std;
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (ival->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
 
 	/* get the current standard */
 	current_std = decoder->current_std;
@@ -765,6 +771,12 @@ tvp514x_set_frame_interval(struct v4l2_subdev *sd,
 	struct v4l2_fract *timeperframe;
 	enum tvp514x_std current_std;
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (ival->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
 
 	timeperframe = &ival->interval;
 
diff --git a/drivers/media/v4l2-core/v4l2-subdev.c b/drivers/media/v4l2-core/v4l2-subdev.c
index 405a4a2fa565..30131a37f2d5 100644
--- a/drivers/media/v4l2-core/v4l2-subdev.c
+++ b/drivers/media/v4l2-core/v4l2-subdev.c
@@ -291,9 +291,8 @@ static inline int check_frame_interval(struct v4l2_subdev *sd,
 	if (!fi)
 		return -EINVAL;
 
-	return check_pad(sd, fi->pad) ? :
-	       check_state(sd, state, V4L2_SUBDEV_FORMAT_ACTIVE, fi->pad,
-			   fi->stream);
+	return check_which(fi->which) ? : check_pad(sd, fi->pad) ? :
+	       check_state(sd, state, fi->which, fi->pad, fi->stream);
 }
 
 static int call_get_frame_interval(struct v4l2_subdev *sd,
@@ -537,9 +536,16 @@ subdev_ioctl_get_state(struct v4l2_subdev *sd, struct v4l2_subdev_fh *subdev_fh,
 		which = ((struct v4l2_subdev_selection *)arg)->which;
 		break;
 	case VIDIOC_SUBDEV_G_FRAME_INTERVAL:
-	case VIDIOC_SUBDEV_S_FRAME_INTERVAL:
-		which = V4L2_SUBDEV_FORMAT_ACTIVE;
+	case VIDIOC_SUBDEV_S_FRAME_INTERVAL: {
+		struct v4l2_subdev_frame_interval *fi = arg;
+
+		if (!(subdev_fh->client_caps &
+		      V4L2_SUBDEV_CLIENT_CAP_INTERVAL_USES_WHICH))
+			fi->which = V4L2_SUBDEV_FORMAT_ACTIVE;
+
+		which = fi->which;
 		break;
+	}
 	case VIDIOC_SUBDEV_G_ROUTING:
 	case VIDIOC_SUBDEV_S_ROUTING:
 		which = ((struct v4l2_subdev_routing *)arg)->which;
@@ -796,12 +802,12 @@ static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg,
 	case VIDIOC_SUBDEV_S_FRAME_INTERVAL: {
 		struct v4l2_subdev_frame_interval *fi = arg;
 
-		if (ro_subdev)
-			return -EPERM;
-
 		if (!client_supports_streams)
 			fi->stream = 0;
 
+		if (fi->which != V4L2_SUBDEV_FORMAT_TRY && ro_subdev)
+			return -EPERM;
+
 		memset(fi->reserved, 0, sizeof(fi->reserved));
 		return v4l2_subdev_call(sd, pad, set_frame_interval, state, fi);
 	}
@@ -998,7 +1004,8 @@ static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg,
 			client_cap->capabilities &= ~V4L2_SUBDEV_CLIENT_CAP_STREAMS;
 
 		/* Filter out unsupported capabilities */
-		client_cap->capabilities &= V4L2_SUBDEV_CLIENT_CAP_STREAMS;
+		client_cap->capabilities &= (V4L2_SUBDEV_CLIENT_CAP_STREAMS |
+					     V4L2_SUBDEV_CLIENT_CAP_INTERVAL_USES_WHICH);
 
 		subdev_fh->client_caps = client_cap->capabilities;
 
diff --git a/drivers/staging/media/atomisp/i2c/atomisp-gc0310.c b/drivers/staging/media/atomisp/i2c/atomisp-gc0310.c
index 006e8adac47b..5bcd634a2a44 100644
--- a/drivers/staging/media/atomisp/i2c/atomisp-gc0310.c
+++ b/drivers/staging/media/atomisp/i2c/atomisp-gc0310.c
@@ -500,6 +500,13 @@ static int gc0310_get_frame_interval(struct v4l2_subdev *sd,
 				     struct v4l2_subdev_state *sd_state,
 				     struct v4l2_subdev_frame_interval *interval)
 {
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (interval->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	interval->interval.numerator = 1;
 	interval->interval.denominator = GC0310_FPS;
 
diff --git a/drivers/staging/media/atomisp/i2c/atomisp-gc2235.c b/drivers/staging/media/atomisp/i2c/atomisp-gc2235.c
index aa257322a700..bec4c5615864 100644
--- a/drivers/staging/media/atomisp/i2c/atomisp-gc2235.c
+++ b/drivers/staging/media/atomisp/i2c/atomisp-gc2235.c
@@ -704,6 +704,13 @@ static int gc2235_get_frame_interval(struct v4l2_subdev *sd,
 {
 	struct gc2235_device *dev = to_gc2235_sensor(sd);
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (interval->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	interval->interval.numerator = 1;
 	interval->interval.denominator = dev->res->fps;
 
diff --git a/drivers/staging/media/atomisp/i2c/atomisp-mt9m114.c b/drivers/staging/media/atomisp/i2c/atomisp-mt9m114.c
index 459c5b8233ce..20f02d18a8de 100644
--- a/drivers/staging/media/atomisp/i2c/atomisp-mt9m114.c
+++ b/drivers/staging/media/atomisp/i2c/atomisp-mt9m114.c
@@ -1394,6 +1394,13 @@ static int mt9m114_get_frame_interval(struct v4l2_subdev *sd,
 {
 	struct mt9m114_device *dev = to_mt9m114_sensor(sd);
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (interval->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	interval->interval.numerator = 1;
 	interval->interval.denominator = mt9m114_res[dev->res].fps;
 
diff --git a/drivers/staging/media/atomisp/i2c/atomisp-ov2722.c b/drivers/staging/media/atomisp/i2c/atomisp-ov2722.c
index b3ef04d7ccca..133e346ae51b 100644
--- a/drivers/staging/media/atomisp/i2c/atomisp-ov2722.c
+++ b/drivers/staging/media/atomisp/i2c/atomisp-ov2722.c
@@ -851,6 +851,13 @@ static int ov2722_get_frame_interval(struct v4l2_subdev *sd,
 {
 	struct ov2722_device *dev = to_ov2722_sensor(sd);
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (interval->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	interval->interval.numerator = 1;
 	interval->interval.denominator = dev->res->fps;
 
diff --git a/drivers/staging/media/imx/imx-ic-prp.c b/drivers/staging/media/imx/imx-ic-prp.c
index fb96f87e664e..2b80d54006b3 100644
--- a/drivers/staging/media/imx/imx-ic-prp.c
+++ b/drivers/staging/media/imx/imx-ic-prp.c
@@ -399,6 +399,13 @@ static int prp_get_frame_interval(struct v4l2_subdev *sd,
 {
 	struct prp_priv *priv = sd_to_priv(sd);
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	if (fi->pad >= PRP_NUM_PADS)
 		return -EINVAL;
 
@@ -415,6 +422,13 @@ static int prp_set_frame_interval(struct v4l2_subdev *sd,
 {
 	struct prp_priv *priv = sd_to_priv(sd);
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	if (fi->pad >= PRP_NUM_PADS)
 		return -EINVAL;
 
diff --git a/drivers/staging/media/imx/imx-ic-prpencvf.c b/drivers/staging/media/imx/imx-ic-prpencvf.c
index 7bfe433cd322..17fd980c9d3c 100644
--- a/drivers/staging/media/imx/imx-ic-prpencvf.c
+++ b/drivers/staging/media/imx/imx-ic-prpencvf.c
@@ -1209,6 +1209,13 @@ static int prp_get_frame_interval(struct v4l2_subdev *sd,
 {
 	struct prp_priv *priv = sd_to_priv(sd);
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	if (fi->pad >= PRPENCVF_NUM_PADS)
 		return -EINVAL;
 
@@ -1225,6 +1232,13 @@ static int prp_set_frame_interval(struct v4l2_subdev *sd,
 {
 	struct prp_priv *priv = sd_to_priv(sd);
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	if (fi->pad >= PRPENCVF_NUM_PADS)
 		return -EINVAL;
 
diff --git a/drivers/staging/media/imx/imx-media-csi.c b/drivers/staging/media/imx/imx-media-csi.c
index 4308fdc9b58e..785aac881922 100644
--- a/drivers/staging/media/imx/imx-media-csi.c
+++ b/drivers/staging/media/imx/imx-media-csi.c
@@ -908,6 +908,13 @@ static int csi_get_frame_interval(struct v4l2_subdev *sd,
 {
 	struct csi_priv *priv = v4l2_get_subdevdata(sd);
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	if (fi->pad >= CSI_NUM_PADS)
 		return -EINVAL;
 
@@ -928,6 +935,13 @@ static int csi_set_frame_interval(struct v4l2_subdev *sd,
 	struct v4l2_fract *input_fi;
 	int ret = 0;
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	mutex_lock(&priv->lock);
 
 	input_fi = &priv->frame_interval[CSI_SINK_PAD];
diff --git a/drivers/staging/media/imx/imx-media-vdic.c b/drivers/staging/media/imx/imx-media-vdic.c
index a51b37679239..09da4103a8db 100644
--- a/drivers/staging/media/imx/imx-media-vdic.c
+++ b/drivers/staging/media/imx/imx-media-vdic.c
@@ -786,6 +786,13 @@ static int vdic_get_frame_interval(struct v4l2_subdev *sd,
 {
 	struct vdic_priv *priv = v4l2_get_subdevdata(sd);
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	if (fi->pad >= VDIC_NUM_PADS)
 		return -EINVAL;
 
@@ -806,6 +813,13 @@ static int vdic_set_frame_interval(struct v4l2_subdev *sd,
 	struct v4l2_fract *input_fi, *output_fi;
 	int ret = 0;
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (fi->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	mutex_lock(&priv->lock);
 
 	input_fi = &priv->frame_interval[priv->active_input_pad];
diff --git a/drivers/staging/media/tegra-video/csi.c b/drivers/staging/media/tegra-video/csi.c
index b1b666179be5..255cccd0c5fd 100644
--- a/drivers/staging/media/tegra-video/csi.c
+++ b/drivers/staging/media/tegra-video/csi.c
@@ -231,6 +231,13 @@ static int tegra_csi_get_frame_interval(struct v4l2_subdev *subdev,
 	if (!IS_ENABLED(CONFIG_VIDEO_TEGRA_TPG))
 		return -ENOIOCTLCMD;
 
+	/*
+	 * FIXME: Implement support for V4L2_SUBDEV_FORMAT_TRY, using the V4L2
+	 * subdev active state API.
+	 */
+	if (vfi->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
 	vfi->interval.numerator = 1;
 	vfi->interval.denominator = csi_chan->framerate;
 
diff --git a/include/uapi/linux/v4l2-subdev.h b/include/uapi/linux/v4l2-subdev.h
index f0fbb4a7c150..7048c51581c6 100644
--- a/include/uapi/linux/v4l2-subdev.h
+++ b/include/uapi/linux/v4l2-subdev.h
@@ -116,13 +116,15 @@ struct v4l2_subdev_frame_size_enum {
  * @pad: pad number, as reported by the media API
  * @interval: frame interval in seconds
  * @stream: stream number, defined in subdev routing
+ * @which: interval type (from enum v4l2_subdev_format_whence)
  * @reserved: drivers and applications must zero this array
  */
 struct v4l2_subdev_frame_interval {
 	__u32 pad;
 	struct v4l2_fract interval;
 	__u32 stream;
-	__u32 reserved[8];
+	__u32 which;
+	__u32 reserved[7];
 };
 
 /**
@@ -133,7 +135,7 @@ struct v4l2_subdev_frame_interval {
  * @width: frame width in pixels
  * @height: frame height in pixels
  * @interval: frame interval in seconds
- * @which: format type (from enum v4l2_subdev_format_whence)
+ * @which: interval type (from enum v4l2_subdev_format_whence)
  * @stream: stream number, defined in subdev routing
  * @reserved: drivers and applications must zero this array
  */
@@ -239,7 +241,14 @@ struct v4l2_subdev_routing {
  * set (which is the default), the 'stream' fields will be forced to 0 by the
  * kernel.
  */
-#define V4L2_SUBDEV_CLIENT_CAP_STREAMS		(1ULL << 0)
+#define V4L2_SUBDEV_CLIENT_CAP_STREAMS			(1ULL << 0)
+
+/*
+ * The client is aware of the struct v4l2_subdev_frame_interval which field. If
+ * this is not set (which is the default), the which field is forced to
+ * V4L2_SUBDEV_FORMAT_ACTIVE by the kernel.
+ */
+#define V4L2_SUBDEV_CLIENT_CAP_INTERVAL_USES_WHICH	(1ULL << 1)
 
 /**
  * struct v4l2_subdev_client_capability - Capabilities of the client accessing
-- 
cgit v1.2.3


From 6b456240b301956227d8a9b86e13e7d0d4f9429e Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Date: Wed, 13 Dec 2023 17:00:06 +0200
Subject: media: v4l2-subdev: Store frame interval in subdev state

Subdev states store all standard pad configuration data, except for
frame intervals. Fix it by adding interval fields in the
v4l2_subdev_pad_config and v4l2_subdev_stream_config structures, with
corresponding accessor functions and a helper function to implement the
.get_frame_interval() operation.

Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
---
 drivers/media/v4l2-core/v4l2-subdev.c | 52 +++++++++++++++++++++++++++++++++++
 include/media/v4l2-subdev.h           | 43 +++++++++++++++++++++++++++++
 2 files changed, 95 insertions(+)

(limited to 'include')

diff --git a/drivers/media/v4l2-core/v4l2-subdev.c b/drivers/media/v4l2-core/v4l2-subdev.c
index 30131a37f2d5..4c6198c48dd6 100644
--- a/drivers/media/v4l2-core/v4l2-subdev.c
+++ b/drivers/media/v4l2-core/v4l2-subdev.c
@@ -1652,6 +1652,42 @@ __v4l2_subdev_state_get_compose(struct v4l2_subdev_state *state,
 }
 EXPORT_SYMBOL_GPL(__v4l2_subdev_state_get_compose);
 
+struct v4l2_fract *
+__v4l2_subdev_state_get_interval(struct v4l2_subdev_state *state,
+				 unsigned int pad, u32 stream)
+{
+	struct v4l2_subdev_stream_configs *stream_configs;
+	unsigned int i;
+
+	if (WARN_ON(!state))
+		return NULL;
+
+	lockdep_assert_held(state->lock);
+
+	if (state->pads) {
+		if (stream)
+			return NULL;
+
+		if (pad >= state->sd->entity.num_pads)
+			return NULL;
+
+		return &state->pads[pad].interval;
+	}
+
+	lockdep_assert_held(state->lock);
+
+	stream_configs = &state->stream_configs;
+
+	for (i = 0; i < stream_configs->num_configs; ++i) {
+		if (stream_configs->configs[i].pad == pad &&
+		    stream_configs->configs[i].stream == stream)
+			return &stream_configs->configs[i].interval;
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(__v4l2_subdev_state_get_interval);
+
 #if defined(CONFIG_VIDEO_V4L2_SUBDEV_API)
 
 static int
@@ -1718,6 +1754,22 @@ int v4l2_subdev_get_fmt(struct v4l2_subdev *sd, struct v4l2_subdev_state *state,
 }
 EXPORT_SYMBOL_GPL(v4l2_subdev_get_fmt);
 
+int v4l2_subdev_get_frame_interval(struct v4l2_subdev *sd,
+				   struct v4l2_subdev_state *state,
+				   struct v4l2_subdev_frame_interval *fi)
+{
+	struct v4l2_fract *interval;
+
+	interval = v4l2_subdev_state_get_interval(state, fi->pad, fi->stream);
+	if (!interval)
+		return -EINVAL;
+
+	fi->interval = *interval;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(v4l2_subdev_get_frame_interval);
+
 int v4l2_subdev_set_routing(struct v4l2_subdev *sd,
 			    struct v4l2_subdev_state *state,
 			    const struct v4l2_subdev_krouting *routing)
diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h
index 0ab7dce098e6..a9e6b8146279 100644
--- a/include/media/v4l2-subdev.h
+++ b/include/media/v4l2-subdev.h
@@ -681,11 +681,13 @@ struct v4l2_subdev_ir_ops {
  * @format: &struct v4l2_mbus_framefmt
  * @crop: &struct v4l2_rect to be used for crop
  * @compose: &struct v4l2_rect to be used for compose
+ * @interval: frame interval
  */
 struct v4l2_subdev_pad_config {
 	struct v4l2_mbus_framefmt format;
 	struct v4l2_rect crop;
 	struct v4l2_rect compose;
+	struct v4l2_fract interval;
 };
 
 /**
@@ -697,6 +699,7 @@ struct v4l2_subdev_pad_config {
  * @fmt: &struct v4l2_mbus_framefmt
  * @crop: &struct v4l2_rect to be used for crop
  * @compose: &struct v4l2_rect to be used for compose
+ * @interval: frame interval
  *
  * This structure stores configuration for a stream.
  */
@@ -708,6 +711,7 @@ struct v4l2_subdev_stream_config {
 	struct v4l2_mbus_framefmt fmt;
 	struct v4l2_rect crop;
 	struct v4l2_rect compose;
+	struct v4l2_fract interval;
 };
 
 /**
@@ -1392,6 +1396,27 @@ struct v4l2_rect *
 __v4l2_subdev_state_get_compose(struct v4l2_subdev_state *state,
 				unsigned int pad, u32 stream);
 
+/**
+ * v4l2_subdev_state_get_interval() - Get pointer to a stream frame interval
+ * @state: subdevice state
+ * @pad: pad id
+ * @...: stream id (optional argument)
+ *
+ * This returns a pointer to the frame interval for the given pad + stream in
+ * the subdev state.
+ *
+ * For stream-unaware drivers the frame interval for the corresponding pad is
+ * returned. If the pad does not exist, NULL is returned.
+ */
+#define v4l2_subdev_state_get_interval(state, pad, ...)			\
+	__v4l2_subdev_state_gen_call(interval, ##__VA_ARGS__, , _pad)	\
+		(state, pad, ##__VA_ARGS__)
+#define __v4l2_subdev_state_get_interval_pad(state, pad)	\
+	__v4l2_subdev_state_get_interval(state, pad, 0)
+struct v4l2_fract *
+__v4l2_subdev_state_get_interval(struct v4l2_subdev_state *state,
+				 unsigned int pad, u32 stream);
+
 #if defined(CONFIG_VIDEO_V4L2_SUBDEV_API)
 
 /**
@@ -1411,6 +1436,24 @@ __v4l2_subdev_state_get_compose(struct v4l2_subdev_state *state,
 int v4l2_subdev_get_fmt(struct v4l2_subdev *sd, struct v4l2_subdev_state *state,
 			struct v4l2_subdev_format *format);
 
+/**
+ * v4l2_subdev_get_frame_interval() - Fill frame interval based on state
+ * @sd: subdevice
+ * @state: subdevice state
+ * @fi: pointer to &struct v4l2_subdev_frame_interval
+ *
+ * Fill @fi->interval field based on the information in the @fi struct.
+ *
+ * This function can be used by the subdev drivers which support active state to
+ * implement v4l2_subdev_pad_ops.get_frame_interval if the subdev driver does
+ * not need to do anything special in their get_frame_interval op.
+ *
+ * Returns 0 on success, error value otherwise.
+ */
+int v4l2_subdev_get_frame_interval(struct v4l2_subdev *sd,
+				   struct v4l2_subdev_state *state,
+				   struct v4l2_subdev_frame_interval *fi);
+
 /**
  * v4l2_subdev_set_routing() - Set given routing to subdev state
  * @sd: The subdevice
-- 
cgit v1.2.3


From c82a1662d4548c454de5343b88f69b9fc82266b3 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 8 Dec 2023 23:56:41 +0100
Subject: leds: trigger: Remove unused function led_trigger_rename_static()

This function was added with a8df7b1ab70b ("leds: add led_trigger_rename
function") 11 yrs ago, but it has no users. So remove it.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://lore.kernel.org/r/d90f30be-f661-4db7-b0b5-d09d07a78a68@gmail.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/led-triggers.c | 13 -------------
 include/linux/leds.h        | 17 -----------------
 2 files changed, 30 deletions(-)

(limited to 'include')

diff --git a/drivers/leds/led-triggers.c b/drivers/leds/led-triggers.c
index 6a5e1f41f9a4..bd59a14a4a90 100644
--- a/drivers/leds/led-triggers.c
+++ b/drivers/leds/led-triggers.c
@@ -269,19 +269,6 @@ void led_trigger_set_default(struct led_classdev *led_cdev)
 }
 EXPORT_SYMBOL_GPL(led_trigger_set_default);
 
-void led_trigger_rename_static(const char *name, struct led_trigger *trig)
-{
-	/* new name must be on a temporary string to prevent races */
-	BUG_ON(name == trig->name);
-
-	down_write(&triggers_list_lock);
-	/* this assumes that trig->name was originaly allocated to
-	 * non constant storage */
-	strcpy((char *)trig->name, name);
-	up_write(&triggers_list_lock);
-}
-EXPORT_SYMBOL_GPL(led_trigger_rename_static);
-
 /* LED Trigger Interface */
 
 int led_trigger_register(struct led_trigger *trig)
diff --git a/include/linux/leds.h b/include/linux/leds.h
index 1bdf7f5a0d7c..4754b02d3a2c 100644
--- a/include/linux/leds.h
+++ b/include/linux/leds.h
@@ -527,23 +527,6 @@ static inline void *led_get_trigger_data(struct led_classdev *led_cdev)
 	return led_cdev->trigger_data;
 }
 
-/**
- * led_trigger_rename_static - rename a trigger
- * @name: the new trigger name
- * @trig: the LED trigger to rename
- *
- * Change a LED trigger name by copying the string passed in
- * name into current trigger name, which MUST be large
- * enough for the new string.
- *
- * Note that name must NOT point to the same string used
- * during LED registration, as that could lead to races.
- *
- * This is meant to be used on triggers with statically
- * allocated name.
- */
-void led_trigger_rename_static(const char *name, struct led_trigger *trig);
-
 #define module_led_trigger(__led_trigger) \
 	module_driver(__led_trigger, led_trigger_register, \
 		      led_trigger_unregister)
-- 
cgit v1.2.3


From 595e52284d24adc376890d3fc93bdca4707d9aca Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Wed, 13 Dec 2023 08:58:15 -0700
Subject: io_uring/poll: don't enable lazy wake for POLLEXCLUSIVE

There are a few quirks around using lazy wake for poll unconditionally,
and one of them is related the EPOLLEXCLUSIVE. Those may trigger
exclusive wakeups, which wake a limited number of entries in the wait
queue. If that wake number is less than the number of entries someone is
waiting for (and that someone is also using DEFER_TASKRUN), then we can
get stuck waiting for more entries while we should be processing the ones
we already got.

If we're doing exclusive poll waits, flag the request as not being
compatible with lazy wakeups.

Reported-by: Pavel Begunkov <asml.silence@gmail.com>
Fixes: 6ce4a93dbb5b ("io_uring/poll: use IOU_F_TWQ_LAZY_WAKE for wakeups")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/io_uring_types.h |  3 +++
 io_uring/poll.c                | 20 +++++++++++++++++---
 2 files changed, 20 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 805bb635cdf5..239a4f68801b 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -434,6 +434,7 @@ enum {
 	/* keep async read/write and isreg together and in order */
 	REQ_F_SUPPORT_NOWAIT_BIT,
 	REQ_F_ISREG_BIT,
+	REQ_F_POLL_NO_LAZY_BIT,
 
 	/* not a real bit, just to check we're not overflowing the space */
 	__REQ_F_LAST_BIT,
@@ -501,6 +502,8 @@ enum {
 	REQ_F_CLEAR_POLLIN	= BIT(REQ_F_CLEAR_POLLIN_BIT),
 	/* hashed into ->cancel_hash_locked, protected by ->uring_lock */
 	REQ_F_HASH_LOCKED	= BIT(REQ_F_HASH_LOCKED_BIT),
+	/* don't use lazy poll wake for this request */
+	REQ_F_POLL_NO_LAZY	= BIT(REQ_F_POLL_NO_LAZY_BIT),
 };
 
 typedef void (*io_req_tw_func_t)(struct io_kiocb *req, struct io_tw_state *ts);
diff --git a/io_uring/poll.c b/io_uring/poll.c
index d38d05edb4fa..d59b74a99d4e 100644
--- a/io_uring/poll.c
+++ b/io_uring/poll.c
@@ -366,11 +366,16 @@ void io_poll_task_func(struct io_kiocb *req, struct io_tw_state *ts)
 
 static void __io_poll_execute(struct io_kiocb *req, int mask)
 {
+	unsigned flags = 0;
+
 	io_req_set_res(req, mask, 0);
 	req->io_task_work.func = io_poll_task_func;
 
 	trace_io_uring_task_add(req, mask);
-	__io_req_task_work_add(req, IOU_F_TWQ_LAZY_WAKE);
+
+	if (!(req->flags & REQ_F_POLL_NO_LAZY))
+		flags = IOU_F_TWQ_LAZY_WAKE;
+	__io_req_task_work_add(req, flags);
 }
 
 static inline void io_poll_execute(struct io_kiocb *req, int res)
@@ -526,10 +531,19 @@ static void __io_queue_proc(struct io_poll *poll, struct io_poll_table *pt,
 	poll->head = head;
 	poll->wait.private = (void *) wqe_private;
 
-	if (poll->events & EPOLLEXCLUSIVE)
+	if (poll->events & EPOLLEXCLUSIVE) {
+		/*
+		 * Exclusive waits may only wake a limited amount of entries
+		 * rather than all of them, this may interfere with lazy
+		 * wake if someone does wait(events > 1). Ensure we don't do
+		 * lazy wake for those, as we need to process each one as they
+		 * come in.
+		 */
+		req->flags |= REQ_F_POLL_NO_LAZY;
 		add_wait_queue_exclusive(head, &poll->wait);
-	else
+	} else {
 		add_wait_queue(head, &poll->wait);
+	}
 }
 
 static void io_poll_queue_proc(struct file *file, struct wait_queue_head *head,
-- 
cgit v1.2.3


From 80c2b40a51393add616a1fd186a1cc10bd676a3f Mon Sep 17 00:00:00 2001
From: Benjamin Gaignard <benjamin.gaignard@collabora.com>
Date: Mon, 11 Dec 2023 14:32:49 +0100
Subject: media: videobuf2: core: Rename min_buffers_needed field in vb2_queue

Rename min_buffers_needed into min_queued_buffers and update
the documentation about it.

Signed-off-by: Benjamin Gaignard <benjamin.gaignard@collabora.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
[hverkuil: Drop the change where min_queued_buffers + 1 buffers would be]
[hverkuil: allocated. Now this patch only renames this field instead of making]
[hverkuil: a functional change as well.]
[hverkuil: Renamed 3 remaining min_buffers_needed occurrences.]
---
 drivers/input/touchscreen/atmel_mxt_ts.c           |  2 +-
 drivers/input/touchscreen/sur40.c                  |  2 +-
 drivers/media/common/saa7146/saa7146_fops.c        |  2 +-
 drivers/media/common/videobuf2/videobuf2-core.c    | 28 +++++++++++-----------
 drivers/media/dvb-core/dvb_vb2.c                   |  2 +-
 drivers/media/i2c/video-i2c.c                      |  2 +-
 drivers/media/pci/bt8xx/bttv-driver.c              |  2 +-
 drivers/media/pci/cobalt/cobalt-v4l2.c             |  2 +-
 drivers/media/pci/cx18/cx18-streams.c              |  2 +-
 drivers/media/pci/cx23885/cx23885-417.c            |  2 +-
 drivers/media/pci/cx23885/cx23885-dvb.c            |  2 +-
 drivers/media/pci/cx23885/cx23885-video.c          |  4 ++--
 drivers/media/pci/cx25821/cx25821-video.c          |  2 +-
 drivers/media/pci/cx88/cx88-blackbird.c            |  2 +-
 drivers/media/pci/cx88/cx88-dvb.c                  |  2 +-
 drivers/media/pci/cx88/cx88-video.c                |  4 ++--
 drivers/media/pci/dt3155/dt3155.c                  |  2 +-
 drivers/media/pci/intel/ipu3/ipu3-cio2.c           |  2 +-
 drivers/media/pci/mgb4/mgb4_vin.c                  |  2 +-
 drivers/media/pci/mgb4/mgb4_vout.c                 |  2 +-
 drivers/media/pci/tw5864/tw5864-video.c            |  2 +-
 drivers/media/pci/tw68/tw68-video.c                |  2 +-
 drivers/media/pci/tw686x/tw686x-video.c            |  2 +-
 drivers/media/pci/zoran/zoran_driver.c             |  6 ++---
 drivers/media/platform/amphion/vpu_v4l2.c          |  4 ++--
 drivers/media/platform/aspeed/aspeed-video.c       |  2 +-
 drivers/media/platform/atmel/atmel-isi.c           |  2 +-
 .../media/platform/chips-media/coda/coda-common.c  |  2 +-
 .../media/platform/microchip/microchip-isc-base.c  |  2 +-
 drivers/media/platform/nuvoton/npcm-video.c        |  2 +-
 drivers/media/platform/nxp/imx7-media-csi.c        |  2 +-
 .../media/platform/nxp/imx8-isi/imx8-isi-video.c   |  2 +-
 drivers/media/platform/qcom/venus/vdec.c           |  4 ++--
 drivers/media/platform/qcom/venus/venc.c           |  4 ++--
 drivers/media/platform/renesas/rcar-vin/rcar-dma.c |  2 +-
 drivers/media/platform/renesas/renesas-ceu.c       |  2 +-
 .../media/platform/renesas/rzg2l-cru/rzg2l-video.c |  2 +-
 drivers/media/platform/renesas/sh_vou.c            |  2 +-
 .../platform/rockchip/rkisp1/rkisp1-capture.c      |  2 +-
 drivers/media/platform/st/sti/hva/hva-v4l2.c       |  4 ++--
 drivers/media/platform/st/stm32/stm32-dcmi.c       |  2 +-
 .../st/stm32/stm32-dcmipp/dcmipp-bytecap.c         |  4 ++--
 drivers/media/platform/sunxi/sun4i-csi/sun4i_dma.c |  2 +-
 .../platform/sunxi/sun6i-csi/sun6i_csi_capture.c   |  2 +-
 drivers/media/platform/sunxi/sun8i-di/sun8i-di.c   |  4 ++--
 .../platform/sunxi/sun8i-rotate/sun8i_rotate.c     |  4 ++--
 drivers/media/platform/ti/am437x/am437x-vpfe.c     |  2 +-
 drivers/media/platform/ti/cal/cal-video.c          |  2 +-
 drivers/media/platform/ti/davinci/vpif_capture.c   |  2 +-
 drivers/media/platform/ti/davinci/vpif_display.c   |  2 +-
 .../media/platform/ti/j721e-csi2rx/j721e-csi2rx.c  |  2 +-
 drivers/media/platform/ti/omap/omap_vout.c         |  2 +-
 drivers/media/test-drivers/vimc/vimc-capture.c     |  2 +-
 drivers/media/test-drivers/vivid/vivid-core.c      |  4 ++--
 drivers/media/usb/cx231xx/cx231xx-417.c            |  2 +-
 drivers/media/usb/cx231xx/cx231xx-video.c          |  4 ++--
 drivers/media/usb/dvb-usb/cxusb-analog.c           |  2 +-
 drivers/media/usb/gspca/gspca.c                    |  6 ++---
 .../media/deprecated/atmel/atmel-isc-base.c        |  2 +-
 drivers/staging/media/imx/imx-media-capture.c      |  2 +-
 drivers/staging/media/ipu3/ipu3-v4l2.c             |  2 +-
 drivers/staging/media/meson/vdec/vdec.c            |  6 ++---
 drivers/staging/media/starfive/camss/stf-video.c   |  2 +-
 .../media/sunxi/sun6i-isp/sun6i_isp_capture.c      |  2 +-
 .../media/sunxi/sun6i-isp/sun6i_isp_params.c       |  2 +-
 drivers/staging/media/tegra-video/vi.c             |  2 +-
 include/media/videobuf2-core.h                     |  9 ++++---
 samples/v4l/v4l2-pci-skeleton.c                    |  2 +-
 68 files changed, 103 insertions(+), 100 deletions(-)

(limited to 'include')

diff --git a/drivers/input/touchscreen/atmel_mxt_ts.c b/drivers/input/touchscreen/atmel_mxt_ts.c
index 20094b9899f0..a2c4b3b87f93 100644
--- a/drivers/input/touchscreen/atmel_mxt_ts.c
+++ b/drivers/input/touchscreen/atmel_mxt_ts.c
@@ -2546,7 +2546,7 @@ static const struct vb2_queue mxt_queue = {
 	.ops = &mxt_queue_ops,
 	.mem_ops = &vb2_vmalloc_memops,
 	.timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC,
-	.min_buffers_needed = 1,
+	.min_queued_buffers = 1,
 };
 
 static int mxt_vidioc_querycap(struct file *file, void *priv,
diff --git a/drivers/input/touchscreen/sur40.c b/drivers/input/touchscreen/sur40.c
index e7d2a52169a0..ae3aab428337 100644
--- a/drivers/input/touchscreen/sur40.c
+++ b/drivers/input/touchscreen/sur40.c
@@ -1124,7 +1124,7 @@ static const struct vb2_queue sur40_queue = {
 	.ops = &sur40_queue_ops,
 	.mem_ops = &vb2_dma_sg_memops,
 	.timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC,
-	.min_buffers_needed = 3,
+	.min_queued_buffers = 3,
 };
 
 static const struct v4l2_file_operations sur40_video_fops = {
diff --git a/drivers/media/common/saa7146/saa7146_fops.c b/drivers/media/common/saa7146/saa7146_fops.c
index 79214459387a..a7047e548245 100644
--- a/drivers/media/common/saa7146/saa7146_fops.c
+++ b/drivers/media/common/saa7146/saa7146_fops.c
@@ -387,7 +387,7 @@ int saa7146_register_device(struct video_device *vfd, struct saa7146_dev *dev,
 	q->gfp_flags = __GFP_DMA32;
 	q->buf_struct_size = sizeof(struct saa7146_buf);
 	q->lock = &dev->v4l2_lock;
-	q->min_buffers_needed = 2;
+	q->min_queued_buffers = 2;
 	q->dev = &dev->pci->dev;
 	err = vb2_queue_init(q);
 	if (err)
diff --git a/drivers/media/common/videobuf2/videobuf2-core.c b/drivers/media/common/videobuf2/videobuf2-core.c
index 40d89f29fa33..41a832dd1426 100644
--- a/drivers/media/common/videobuf2/videobuf2-core.c
+++ b/drivers/media/common/videobuf2/videobuf2-core.c
@@ -865,7 +865,7 @@ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory,
 	/*
 	 * Make sure the requested values and current defaults are sane.
 	 */
-	num_buffers = max_t(unsigned int, *count, q->min_buffers_needed);
+	num_buffers = max_t(unsigned int, *count, q->min_queued_buffers);
 	num_buffers = min_t(unsigned int, num_buffers, q->max_num_buffers);
 	memset(q->alloc_devs, 0, sizeof(q->alloc_devs));
 	/*
@@ -917,7 +917,7 @@ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory,
 	 * There is no point in continuing if we can't allocate the minimum
 	 * number of buffers needed by this vb2_queue.
 	 */
-	if (allocated_buffers < q->min_buffers_needed)
+	if (allocated_buffers < q->min_queued_buffers)
 		ret = -ENOMEM;
 
 	/*
@@ -1653,7 +1653,7 @@ EXPORT_SYMBOL_GPL(vb2_core_prepare_buf);
  * @q:		videobuf2 queue
  *
  * Attempt to start streaming. When this function is called there must be
- * at least q->min_buffers_needed buffers queued up (i.e. the minimum
+ * at least q->min_queued_buffers queued up (i.e. the minimum
  * number of buffers required for the DMA engine to function). If the
  * @start_streaming op fails it is supposed to return all the driver-owned
  * buffers back to vb2 in state QUEUED. Check if that happened and if
@@ -1846,7 +1846,7 @@ int vb2_core_qbuf(struct vb2_queue *q, struct vb2_buffer *vb, void *pb,
 	 * then we can finally call start_streaming().
 	 */
 	if (q->streaming && !q->start_streaming_called &&
-	    q->queued_count >= q->min_buffers_needed) {
+	    q->queued_count >= q->min_queued_buffers) {
 		ret = vb2_start_streaming(q);
 		if (ret) {
 			/*
@@ -2210,9 +2210,9 @@ int vb2_core_streamon(struct vb2_queue *q, unsigned int type)
 		return -EINVAL;
 	}
 
-	if (q_num_bufs < q->min_buffers_needed) {
-		dprintk(q, 1, "need at least %u allocated buffers\n",
-				q->min_buffers_needed);
+	if (q_num_bufs < q->min_queued_buffers) {
+		dprintk(q, 1, "need at least %u queued buffers\n",
+			q->min_queued_buffers);
 		return -EINVAL;
 	}
 
@@ -2224,7 +2224,7 @@ int vb2_core_streamon(struct vb2_queue *q, unsigned int type)
 	 * Tell driver to start streaming provided sufficient buffers
 	 * are available.
 	 */
-	if (q->queued_count >= q->min_buffers_needed) {
+	if (q->queued_count >= q->min_queued_buffers) {
 		ret = vb2_start_streaming(q);
 		if (ret)
 			goto unprepare;
@@ -2504,7 +2504,7 @@ int vb2_core_queue_init(struct vb2_queue *q)
 		return -EINVAL;
 
 	if (WARN_ON(q->max_num_buffers > MAX_BUFFER_INDEX) ||
-	    WARN_ON(q->min_buffers_needed > q->max_num_buffers))
+	    WARN_ON(q->min_queued_buffers > q->max_num_buffers))
 		return -EINVAL;
 
 	if (WARN_ON(q->requires_requests && !q->supports_requests))
@@ -2512,13 +2512,13 @@ int vb2_core_queue_init(struct vb2_queue *q)
 
 	/*
 	 * This combination is not allowed since a non-zero value of
-	 * q->min_buffers_needed can cause vb2_core_qbuf() to fail if
+	 * q->min_queued_buffers can cause vb2_core_qbuf() to fail if
 	 * it has to call start_streaming(), and the Request API expects
 	 * that queueing a request (and thus queueing a buffer contained
 	 * in that request) will always succeed. There is no method of
 	 * propagating an error back to userspace.
 	 */
-	if (WARN_ON(q->supports_requests && q->min_buffers_needed))
+	if (WARN_ON(q->supports_requests && q->min_queued_buffers))
 		return -EINVAL;
 
 	INIT_LIST_HEAD(&q->queued_list);
@@ -2735,14 +2735,14 @@ static int __vb2_init_fileio(struct vb2_queue *q, int read)
 		return -EBUSY;
 
 	/*
-	 * Start with q->min_buffers_needed + 1, driver can increase it in
+	 * Start with q->min_queued_buffers + 1, driver can increase it in
 	 * queue_setup()
 	 *
-	 * 'min_buffers_needed' buffers need to be queued up before you
+	 * 'min_queued_buffers' buffers need to be queued up before you
 	 * can start streaming, plus 1 for userspace (or in this case,
 	 * kernelspace) processing.
 	 */
-	count = max(2, q->min_buffers_needed + 1);
+	count = max(2, q->min_queued_buffers + 1);
 
 	dprintk(q, 3, "setting up file io: mode %s, count %d, read_once %d, write_immediately %d\n",
 		(read) ? "read" : "write", count, q->fileio_read_once,
diff --git a/drivers/media/dvb-core/dvb_vb2.c b/drivers/media/dvb-core/dvb_vb2.c
index 167ff82a6fed..192a8230c4aa 100644
--- a/drivers/media/dvb-core/dvb_vb2.c
+++ b/drivers/media/dvb-core/dvb_vb2.c
@@ -171,7 +171,7 @@ int dvb_vb2_init(struct dvb_vb2_ctx *ctx, const char *name, int nonblocking)
 	q->io_modes = VB2_MMAP;
 	q->drv_priv = ctx;
 	q->buf_struct_size = sizeof(struct dvb_buffer);
-	q->min_buffers_needed = 1;
+	q->min_queued_buffers = 1;
 	q->ops = &dvb_vb2_qops;
 	q->mem_ops = &vb2_vmalloc_memops;
 	q->buf_ops = &dvb_vb2_buf_ops;
diff --git a/drivers/media/i2c/video-i2c.c b/drivers/media/i2c/video-i2c.c
index ebf2ac98a068..56dbe07a1c99 100644
--- a/drivers/media/i2c/video-i2c.c
+++ b/drivers/media/i2c/video-i2c.c
@@ -795,7 +795,7 @@ static int video_i2c_probe(struct i2c_client *client)
 	queue->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	queue->drv_priv = data;
 	queue->buf_struct_size = sizeof(struct video_i2c_buffer);
-	queue->min_buffers_needed = 1;
+	queue->min_queued_buffers = 1;
 	queue->ops = &video_i2c_video_qops;
 	queue->mem_ops = &vb2_vmalloc_memops;
 
diff --git a/drivers/media/pci/bt8xx/bttv-driver.c b/drivers/media/pci/bt8xx/bttv-driver.c
index 49a3dd70ec0f..511f013cc338 100644
--- a/drivers/media/pci/bt8xx/bttv-driver.c
+++ b/drivers/media/pci/bt8xx/bttv-driver.c
@@ -3113,7 +3113,7 @@ static int vdev_init(struct bttv *btv, struct video_device *vfd,
 	q->gfp_flags = __GFP_DMA32;
 	q->buf_struct_size = sizeof(struct bttv_buffer);
 	q->lock = &btv->lock;
-	q->min_buffers_needed = 2;
+	q->min_queued_buffers = 2;
 	q->dev = &btv->c.pci->dev;
 	err = vb2_queue_init(q);
 	if (err)
diff --git a/drivers/media/pci/cobalt/cobalt-v4l2.c b/drivers/media/pci/cobalt/cobalt-v4l2.c
index 26bf58d17a3d..77ba08ace29f 100644
--- a/drivers/media/pci/cobalt/cobalt-v4l2.c
+++ b/drivers/media/pci/cobalt/cobalt-v4l2.c
@@ -1260,7 +1260,7 @@ static int cobalt_node_register(struct cobalt *cobalt, int node)
 	q->ops = &cobalt_qops;
 	q->mem_ops = &vb2_dma_sg_memops;
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-	q->min_buffers_needed = 2;
+	q->min_queued_buffers = 2;
 	q->lock = &s->lock;
 	q->dev = &cobalt->pci_dev->dev;
 	vdev->queue = q;
diff --git a/drivers/media/pci/cx18/cx18-streams.c b/drivers/media/pci/cx18/cx18-streams.c
index cfbc4a907802..acc6418db425 100644
--- a/drivers/media/pci/cx18/cx18-streams.c
+++ b/drivers/media/pci/cx18/cx18-streams.c
@@ -287,7 +287,7 @@ static int cx18_stream_init(struct cx18 *cx, int type)
 		s->vidq.ops = &cx18_vb2_qops;
 		s->vidq.mem_ops = &vb2_vmalloc_memops;
 		s->vidq.timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-		s->vidq.min_buffers_needed = 2;
+		s->vidq.min_queued_buffers = 2;
 		s->vidq.gfp_flags = GFP_DMA32;
 		s->vidq.dev = &cx->pci_dev->dev;
 		s->vidq.lock = &cx->serialize_lock;
diff --git a/drivers/media/pci/cx23885/cx23885-417.c b/drivers/media/pci/cx23885/cx23885-417.c
index 434677bd4ad1..fdb96f80c036 100644
--- a/drivers/media/pci/cx23885/cx23885-417.c
+++ b/drivers/media/pci/cx23885/cx23885-417.c
@@ -1525,7 +1525,7 @@ int cx23885_417_register(struct cx23885_dev *dev)
 	q->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
 	q->io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF | VB2_READ;
 	q->gfp_flags = GFP_DMA32;
-	q->min_buffers_needed = 2;
+	q->min_queued_buffers = 2;
 	q->drv_priv = dev;
 	q->buf_struct_size = sizeof(struct cx23885_buffer);
 	q->ops = &cx23885_qops;
diff --git a/drivers/media/pci/cx23885/cx23885-dvb.c b/drivers/media/pci/cx23885/cx23885-dvb.c
index 7551ca4a322a..3d01cdc4c7f3 100644
--- a/drivers/media/pci/cx23885/cx23885-dvb.c
+++ b/drivers/media/pci/cx23885/cx23885-dvb.c
@@ -2667,7 +2667,7 @@ int cx23885_dvb_register(struct cx23885_tsport *port)
 		q->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
 		q->io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF | VB2_READ;
 		q->gfp_flags = GFP_DMA32;
-		q->min_buffers_needed = 2;
+		q->min_queued_buffers = 2;
 		q->drv_priv = port;
 		q->buf_struct_size = sizeof(struct cx23885_buffer);
 		q->ops = &dvb_qops;
diff --git a/drivers/media/pci/cx23885/cx23885-video.c b/drivers/media/pci/cx23885/cx23885-video.c
index 9af2c5596121..42fdcf992e48 100644
--- a/drivers/media/pci/cx23885/cx23885-video.c
+++ b/drivers/media/pci/cx23885/cx23885-video.c
@@ -1321,7 +1321,7 @@ int cx23885_video_register(struct cx23885_dev *dev)
 	q->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
 	q->io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF | VB2_READ;
 	q->gfp_flags = GFP_DMA32;
-	q->min_buffers_needed = 2;
+	q->min_queued_buffers = 2;
 	q->drv_priv = dev;
 	q->buf_struct_size = sizeof(struct cx23885_buffer);
 	q->ops = &cx23885_video_qops;
@@ -1338,7 +1338,7 @@ int cx23885_video_register(struct cx23885_dev *dev)
 	q->type = V4L2_BUF_TYPE_VBI_CAPTURE;
 	q->io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF | VB2_READ;
 	q->gfp_flags = GFP_DMA32;
-	q->min_buffers_needed = 2;
+	q->min_queued_buffers = 2;
 	q->drv_priv = dev;
 	q->buf_struct_size = sizeof(struct cx23885_buffer);
 	q->ops = &cx23885_vbi_qops;
diff --git a/drivers/media/pci/cx25821/cx25821-video.c b/drivers/media/pci/cx25821/cx25821-video.c
index 1b80c990cb94..0bee4b728a60 100644
--- a/drivers/media/pci/cx25821/cx25821-video.c
+++ b/drivers/media/pci/cx25821/cx25821-video.c
@@ -730,7 +730,7 @@ int cx25821_video_register(struct cx25821_dev *dev)
 		q->io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF;
 		q->io_modes |= is_output ? VB2_WRITE : VB2_READ;
 		q->gfp_flags = GFP_DMA32;
-		q->min_buffers_needed = 2;
+		q->min_queued_buffers = 2;
 		q->drv_priv = chan;
 		q->buf_struct_size = sizeof(struct cx25821_buffer);
 		q->ops = &cx25821_video_qops;
diff --git a/drivers/media/pci/cx88/cx88-blackbird.c b/drivers/media/pci/cx88/cx88-blackbird.c
index c1b41a9283c1..d55df8fdb3b6 100644
--- a/drivers/media/pci/cx88/cx88-blackbird.c
+++ b/drivers/media/pci/cx88/cx88-blackbird.c
@@ -1195,7 +1195,7 @@ static int cx8802_blackbird_probe(struct cx8802_driver *drv)
 	q->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
 	q->io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF | VB2_READ;
 	q->gfp_flags = GFP_DMA32;
-	q->min_buffers_needed = 2;
+	q->min_queued_buffers = 2;
 	q->drv_priv = dev;
 	q->buf_struct_size = sizeof(struct cx88_buffer);
 	q->ops = &blackbird_qops;
diff --git a/drivers/media/pci/cx88/cx88-dvb.c b/drivers/media/pci/cx88/cx88-dvb.c
index 2087f2491c42..b33b3a5e32ec 100644
--- a/drivers/media/pci/cx88/cx88-dvb.c
+++ b/drivers/media/pci/cx88/cx88-dvb.c
@@ -1776,7 +1776,7 @@ static int cx8802_dvb_probe(struct cx8802_driver *drv)
 		q->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
 		q->io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF | VB2_READ;
 		q->gfp_flags = GFP_DMA32;
-		q->min_buffers_needed = 2;
+		q->min_queued_buffers = 2;
 		q->drv_priv = dev;
 		q->buf_struct_size = sizeof(struct cx88_buffer);
 		q->ops = &dvb_qops;
diff --git a/drivers/media/pci/cx88/cx88-video.c b/drivers/media/pci/cx88/cx88-video.c
index c0ef03ed74f9..cefb6b25e921 100644
--- a/drivers/media/pci/cx88/cx88-video.c
+++ b/drivers/media/pci/cx88/cx88-video.c
@@ -1411,7 +1411,7 @@ static int cx8800_initdev(struct pci_dev *pci_dev,
 	q->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
 	q->io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF | VB2_READ;
 	q->gfp_flags = GFP_DMA32;
-	q->min_buffers_needed = 2;
+	q->min_queued_buffers = 2;
 	q->drv_priv = dev;
 	q->buf_struct_size = sizeof(struct cx88_buffer);
 	q->ops = &cx8800_video_qops;
@@ -1428,7 +1428,7 @@ static int cx8800_initdev(struct pci_dev *pci_dev,
 	q->type = V4L2_BUF_TYPE_VBI_CAPTURE;
 	q->io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF | VB2_READ;
 	q->gfp_flags = GFP_DMA32;
-	q->min_buffers_needed = 2;
+	q->min_queued_buffers = 2;
 	q->drv_priv = dev;
 	q->buf_struct_size = sizeof(struct cx88_buffer);
 	q->ops = &cx8800_vbi_qops;
diff --git a/drivers/media/pci/dt3155/dt3155.c b/drivers/media/pci/dt3155/dt3155.c
index d09cde2f6ee4..dff853e73fdc 100644
--- a/drivers/media/pci/dt3155/dt3155.c
+++ b/drivers/media/pci/dt3155/dt3155.c
@@ -517,7 +517,7 @@ static int dt3155_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	pd->vidq.ops = &q_ops;
 	pd->vidq.mem_ops = &vb2_dma_contig_memops;
 	pd->vidq.drv_priv = pd;
-	pd->vidq.min_buffers_needed = 2;
+	pd->vidq.min_queued_buffers = 2;
 	pd->vidq.gfp_flags = GFP_DMA32;
 	pd->vidq.lock = &pd->mux; /* for locking v4l2_file_operations */
 	pd->vidq.dev = &pdev->dev;
diff --git a/drivers/media/pci/intel/ipu3/ipu3-cio2.c b/drivers/media/pci/intel/ipu3/ipu3-cio2.c
index 5d3b0ffd3d08..ed08bf4178f0 100644
--- a/drivers/media/pci/intel/ipu3/ipu3-cio2.c
+++ b/drivers/media/pci/intel/ipu3/ipu3-cio2.c
@@ -1589,7 +1589,7 @@ static int cio2_queue_init(struct cio2_device *cio2, struct cio2_queue *q)
 	vbq->mem_ops = &vb2_dma_sg_memops;
 	vbq->buf_struct_size = sizeof(struct cio2_buffer);
 	vbq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-	vbq->min_buffers_needed = 1;
+	vbq->min_queued_buffers = 1;
 	vbq->drv_priv = cio2;
 	vbq->lock = &q->lock;
 	r = vb2_queue_init(vbq);
diff --git a/drivers/media/pci/mgb4/mgb4_vin.c b/drivers/media/pci/mgb4/mgb4_vin.c
index d72b07b87cd1..2cd78c539889 100644
--- a/drivers/media/pci/mgb4/mgb4_vin.c
+++ b/drivers/media/pci/mgb4/mgb4_vin.c
@@ -849,7 +849,7 @@ struct mgb4_vin_dev *mgb4_vin_create(struct mgb4_dev *mgbdev, int id)
 	vindev->queue.mem_ops = &vb2_dma_sg_memops;
 	vindev->queue.gfp_flags = GFP_DMA32;
 	vindev->queue.timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-	vindev->queue.min_buffers_needed = 2;
+	vindev->queue.min_queued_buffers = 2;
 	vindev->queue.drv_priv = vindev;
 	vindev->queue.lock = &vindev->lock;
 	vindev->queue.dev = dev;
diff --git a/drivers/media/pci/mgb4/mgb4_vout.c b/drivers/media/pci/mgb4/mgb4_vout.c
index 857fc7bbd21a..241353ee77a5 100644
--- a/drivers/media/pci/mgb4/mgb4_vout.c
+++ b/drivers/media/pci/mgb4/mgb4_vout.c
@@ -523,7 +523,7 @@ struct mgb4_vout_dev *mgb4_vout_create(struct mgb4_dev *mgbdev, int id)
 	voutdev->queue.mem_ops = &vb2_dma_sg_memops;
 	voutdev->queue.gfp_flags = GFP_DMA32;
 	voutdev->queue.timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-	voutdev->queue.min_buffers_needed = 2;
+	voutdev->queue.min_queued_buffers = 2;
 	voutdev->queue.drv_priv = voutdev;
 	voutdev->queue.lock = &voutdev->lock;
 	voutdev->queue.dev = dev;
diff --git a/drivers/media/pci/tw5864/tw5864-video.c b/drivers/media/pci/tw5864/tw5864-video.c
index 197ed8978102..8b1aae4b6319 100644
--- a/drivers/media/pci/tw5864/tw5864-video.c
+++ b/drivers/media/pci/tw5864/tw5864-video.c
@@ -1114,7 +1114,7 @@ static int tw5864_video_input_init(struct tw5864_input *input, int video_nr)
 	input->vidq.gfp_flags = 0;
 	input->vidq.buf_struct_size = sizeof(struct tw5864_buf);
 	input->vidq.lock = &input->lock;
-	input->vidq.min_buffers_needed = 2;
+	input->vidq.min_queued_buffers = 2;
 	input->vidq.dev = &input->root->pci->dev;
 	ret = vb2_queue_init(&input->vidq);
 	if (ret)
diff --git a/drivers/media/pci/tw68/tw68-video.c b/drivers/media/pci/tw68/tw68-video.c
index 79b627ebc92a..cdf5d733b863 100644
--- a/drivers/media/pci/tw68/tw68-video.c
+++ b/drivers/media/pci/tw68/tw68-video.c
@@ -952,7 +952,7 @@ int tw68_video_init2(struct tw68_dev *dev, int video_nr)
 	dev->vidq.gfp_flags = __GFP_DMA32 | __GFP_KSWAPD_RECLAIM;
 	dev->vidq.buf_struct_size = sizeof(struct tw68_buf);
 	dev->vidq.lock = &dev->lock;
-	dev->vidq.min_buffers_needed = 2;
+	dev->vidq.min_queued_buffers = 2;
 	dev->vidq.dev = &dev->pci->dev;
 	ret = vb2_queue_init(&dev->vidq);
 	if (ret)
diff --git a/drivers/media/pci/tw686x/tw686x-video.c b/drivers/media/pci/tw686x/tw686x-video.c
index 6bc6d143d18c..63be95fce83d 100644
--- a/drivers/media/pci/tw686x/tw686x-video.c
+++ b/drivers/media/pci/tw686x/tw686x-video.c
@@ -1222,7 +1222,7 @@ int tw686x_video_init(struct tw686x_dev *dev)
 		vc->vidq.ops = &tw686x_video_qops;
 		vc->vidq.mem_ops = dev->dma_ops->mem_ops;
 		vc->vidq.timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-		vc->vidq.min_buffers_needed = 2;
+		vc->vidq.min_queued_buffers = 2;
 		vc->vidq.lock = &vc->vb_mutex;
 		vc->vidq.gfp_flags = dev->dma_mode != TW686X_DMA_MODE_MEMCPY ?
 				     GFP_DMA32 : 0;
diff --git a/drivers/media/pci/zoran/zoran_driver.c b/drivers/media/pci/zoran/zoran_driver.c
index fa672cc8bc67..5c05e64c71a9 100644
--- a/drivers/media/pci/zoran/zoran_driver.c
+++ b/drivers/media/pci/zoran/zoran_driver.c
@@ -749,8 +749,8 @@ static int zr_vb2_queue_setup(struct vb2_queue *vq, unsigned int *nbuffers, unsi
 
 	zr->buf_in_reserve = 0;
 
-	if (*nbuffers < vq->min_buffers_needed)
-		*nbuffers = vq->min_buffers_needed;
+	if (*nbuffers < vq->min_queued_buffers)
+		*nbuffers = vq->min_queued_buffers;
 
 	if (*nplanes) {
 		if (sizes[0] < size)
@@ -971,7 +971,7 @@ int zoran_queue_init(struct zoran *zr, struct vb2_queue *vq, int dir)
 	vq->mem_ops = &vb2_dma_contig_memops;
 	vq->gfp_flags = GFP_DMA32;
 	vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-	vq->min_buffers_needed = 9;
+	vq->min_queued_buffers = 9;
 	vq->lock = &zr->lock;
 	err = vb2_queue_init(vq);
 	if (err)
diff --git a/drivers/media/platform/amphion/vpu_v4l2.c b/drivers/media/platform/amphion/vpu_v4l2.c
index b7b5bc98cb2a..c88738e8fff7 100644
--- a/drivers/media/platform/amphion/vpu_v4l2.c
+++ b/drivers/media/platform/amphion/vpu_v4l2.c
@@ -649,7 +649,7 @@ static int vpu_m2m_queue_init(void *priv, struct vb2_queue *src_vq, struct vb2_q
 		src_vq->mem_ops = &vb2_vmalloc_memops;
 	src_vq->drv_priv = inst;
 	src_vq->buf_struct_size = sizeof(struct vpu_vb2_buffer);
-	src_vq->min_buffers_needed = 1;
+	src_vq->min_queued_buffers = 1;
 	src_vq->dev = inst->vpu->dev;
 	src_vq->lock = &inst->lock;
 	ret = vb2_queue_init(src_vq);
@@ -666,7 +666,7 @@ static int vpu_m2m_queue_init(void *priv, struct vb2_queue *src_vq, struct vb2_q
 		dst_vq->mem_ops = &vb2_vmalloc_memops;
 	dst_vq->drv_priv = inst;
 	dst_vq->buf_struct_size = sizeof(struct vpu_vb2_buffer);
-	dst_vq->min_buffers_needed = 1;
+	dst_vq->min_queued_buffers = 1;
 	dst_vq->dev = inst->vpu->dev;
 	dst_vq->lock = &inst->lock;
 	ret = vb2_queue_init(dst_vq);
diff --git a/drivers/media/platform/aspeed/aspeed-video.c b/drivers/media/platform/aspeed/aspeed-video.c
index d08aa7f73d4f..fc6050e3be0d 100644
--- a/drivers/media/platform/aspeed/aspeed-video.c
+++ b/drivers/media/platform/aspeed/aspeed-video.c
@@ -2034,7 +2034,7 @@ static int aspeed_video_setup_video(struct aspeed_video *video)
 	vbq->drv_priv = video;
 	vbq->buf_struct_size = sizeof(struct aspeed_video_buffer);
 	vbq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-	vbq->min_buffers_needed = ASPEED_VIDEO_V4L2_MIN_BUF_REQ;
+	vbq->min_queued_buffers = ASPEED_VIDEO_V4L2_MIN_BUF_REQ;
 
 	rc = vb2_queue_init(vbq);
 	if (rc) {
diff --git a/drivers/media/platform/atmel/atmel-isi.c b/drivers/media/platform/atmel/atmel-isi.c
index ed70c030858d..f8450a8ccda6 100644
--- a/drivers/media/platform/atmel/atmel-isi.c
+++ b/drivers/media/platform/atmel/atmel-isi.c
@@ -1245,7 +1245,7 @@ static int atmel_isi_probe(struct platform_device *pdev)
 	q->ops = &isi_video_qops;
 	q->mem_ops = &vb2_dma_contig_memops;
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-	q->min_buffers_needed = 2;
+	q->min_queued_buffers = 2;
 	q->dev = &pdev->dev;
 
 	ret = vb2_queue_init(q);
diff --git a/drivers/media/platform/chips-media/coda/coda-common.c b/drivers/media/platform/chips-media/coda/coda-common.c
index f1d85758f6dd..7da0194ec850 100644
--- a/drivers/media/platform/chips-media/coda/coda-common.c
+++ b/drivers/media/platform/chips-media/coda/coda-common.c
@@ -2546,7 +2546,7 @@ static int coda_queue_init(struct coda_ctx *ctx, struct vb2_queue *vq)
 	 * would need to be reflected in job_ready(). Currently we expect all
 	 * queues to have at least one buffer queued.
 	 */
-	vq->min_buffers_needed = 1;
+	vq->min_queued_buffers = 1;
 	vq->dev = ctx->dev->dev;
 
 	return vb2_queue_init(vq);
diff --git a/drivers/media/platform/microchip/microchip-isc-base.c b/drivers/media/platform/microchip/microchip-isc-base.c
index 540cb1378289..f3a5cbacadbe 100644
--- a/drivers/media/platform/microchip/microchip-isc-base.c
+++ b/drivers/media/platform/microchip/microchip-isc-base.c
@@ -1780,7 +1780,7 @@ static int isc_async_complete(struct v4l2_async_notifier *notifier)
 	q->mem_ops		= &vb2_dma_contig_memops;
 	q->timestamp_flags	= V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	q->lock			= &isc->lock;
-	q->min_buffers_needed	= 1;
+	q->min_queued_buffers	= 1;
 	q->dev			= isc->dev;
 
 	ret = vb2_queue_init(q);
diff --git a/drivers/media/platform/nuvoton/npcm-video.c b/drivers/media/platform/nuvoton/npcm-video.c
index 267e301f2b26..a1fcb616b256 100644
--- a/drivers/media/platform/nuvoton/npcm-video.c
+++ b/drivers/media/platform/nuvoton/npcm-video.c
@@ -1612,7 +1612,7 @@ static int npcm_video_setup_video(struct npcm_video *video)
 	vbq->drv_priv = video;
 	vbq->buf_struct_size = sizeof(struct npcm_video_buffer);
 	vbq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-	vbq->min_buffers_needed = 3;
+	vbq->min_queued_buffers = 3;
 
 	rc = vb2_queue_init(vbq);
 	if (rc) {
diff --git a/drivers/media/platform/nxp/imx7-media-csi.c b/drivers/media/platform/nxp/imx7-media-csi.c
index f992ae671065..9566ff738818 100644
--- a/drivers/media/platform/nxp/imx7-media-csi.c
+++ b/drivers/media/platform/nxp/imx7-media-csi.c
@@ -1691,7 +1691,7 @@ static int imx7_csi_video_init(struct imx7_csi *csi)
 	vq->mem_ops = &vb2_dma_contig_memops;
 	vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	vq->lock = &csi->vdev_mutex;
-	vq->min_buffers_needed = 2;
+	vq->min_queued_buffers = 2;
 	vq->dev = csi->dev;
 
 	ret = vb2_queue_init(vq);
diff --git a/drivers/media/platform/nxp/imx8-isi/imx8-isi-video.c b/drivers/media/platform/nxp/imx8-isi/imx8-isi-video.c
index 49bca2b01cc6..4091f1c0e78b 100644
--- a/drivers/media/platform/nxp/imx8-isi/imx8-isi-video.c
+++ b/drivers/media/platform/nxp/imx8-isi/imx8-isi-video.c
@@ -1453,7 +1453,7 @@ int mxc_isi_video_register(struct mxc_isi_pipe *pipe,
 	q->mem_ops = &vb2_dma_contig_memops;
 	q->buf_struct_size = sizeof(struct mxc_isi_buffer);
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-	q->min_buffers_needed = 2;
+	q->min_queued_buffers = 2;
 	q->lock = &video->lock;
 	q->dev = pipe->isi->dev;
 
diff --git a/drivers/media/platform/qcom/venus/vdec.c b/drivers/media/platform/qcom/venus/vdec.c
index dbf305cec120..29130a9441e7 100644
--- a/drivers/media/platform/qcom/venus/vdec.c
+++ b/drivers/media/platform/qcom/venus/vdec.c
@@ -1641,7 +1641,7 @@ static int m2m_queue_init(void *priv, struct vb2_queue *src_vq,
 	src_vq->drv_priv = inst;
 	src_vq->buf_struct_size = sizeof(struct venus_buffer);
 	src_vq->allow_zero_bytesused = 1;
-	src_vq->min_buffers_needed = 0;
+	src_vq->min_queued_buffers = 0;
 	src_vq->dev = inst->core->dev;
 	src_vq->lock = &inst->ctx_q_lock;
 	ret = vb2_queue_init(src_vq);
@@ -1656,7 +1656,7 @@ static int m2m_queue_init(void *priv, struct vb2_queue *src_vq,
 	dst_vq->drv_priv = inst;
 	dst_vq->buf_struct_size = sizeof(struct venus_buffer);
 	dst_vq->allow_zero_bytesused = 1;
-	dst_vq->min_buffers_needed = 0;
+	dst_vq->min_queued_buffers = 0;
 	dst_vq->dev = inst->core->dev;
 	dst_vq->lock = &inst->ctx_q_lock;
 	return vb2_queue_init(dst_vq);
diff --git a/drivers/media/platform/qcom/venus/venc.c b/drivers/media/platform/qcom/venus/venc.c
index 44b13696cf82..3ec2fb8d9fab 100644
--- a/drivers/media/platform/qcom/venus/venc.c
+++ b/drivers/media/platform/qcom/venus/venc.c
@@ -1398,7 +1398,7 @@ static int m2m_queue_init(void *priv, struct vb2_queue *src_vq,
 	src_vq->drv_priv = inst;
 	src_vq->buf_struct_size = sizeof(struct venus_buffer);
 	src_vq->allow_zero_bytesused = 1;
-	src_vq->min_buffers_needed = 1;
+	src_vq->min_queued_buffers = 1;
 	src_vq->dev = inst->core->dev;
 	src_vq->lock = &inst->ctx_q_lock;
 	if (inst->core->res->hfi_version == HFI_VERSION_1XX)
@@ -1415,7 +1415,7 @@ static int m2m_queue_init(void *priv, struct vb2_queue *src_vq,
 	dst_vq->drv_priv = inst;
 	dst_vq->buf_struct_size = sizeof(struct venus_buffer);
 	dst_vq->allow_zero_bytesused = 1;
-	dst_vq->min_buffers_needed = 1;
+	dst_vq->min_queued_buffers = 1;
 	dst_vq->dev = inst->core->dev;
 	dst_vq->lock = &inst->ctx_q_lock;
 	return vb2_queue_init(dst_vq);
diff --git a/drivers/media/platform/renesas/rcar-vin/rcar-dma.c b/drivers/media/platform/renesas/rcar-vin/rcar-dma.c
index 2a77353f10b5..e2c40abc6d3d 100644
--- a/drivers/media/platform/renesas/rcar-vin/rcar-dma.c
+++ b/drivers/media/platform/renesas/rcar-vin/rcar-dma.c
@@ -1559,7 +1559,7 @@ int rvin_dma_register(struct rvin_dev *vin, int irq)
 	q->ops = &rvin_qops;
 	q->mem_ops = &vb2_dma_contig_memops;
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-	q->min_buffers_needed = 4;
+	q->min_queued_buffers = 4;
 	q->dev = vin->dev;
 
 	ret = vb2_queue_init(q);
diff --git a/drivers/media/platform/renesas/renesas-ceu.c b/drivers/media/platform/renesas/renesas-ceu.c
index 2562b30acfb9..167760276796 100644
--- a/drivers/media/platform/renesas/renesas-ceu.c
+++ b/drivers/media/platform/renesas/renesas-ceu.c
@@ -1399,7 +1399,7 @@ static int ceu_notify_complete(struct v4l2_async_notifier *notifier)
 	q->mem_ops		= &vb2_dma_contig_memops;
 	q->buf_struct_size	= sizeof(struct ceu_buffer);
 	q->timestamp_flags	= V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-	q->min_buffers_needed	= 2;
+	q->min_queued_buffers	= 2;
 	q->lock			= &ceudev->mlock;
 	q->dev			= ceudev->v4l2_dev.dev;
 
diff --git a/drivers/media/platform/renesas/rzg2l-cru/rzg2l-video.c b/drivers/media/platform/renesas/rzg2l-cru/rzg2l-video.c
index e6eedd65b71d..d0ffa90bc656 100644
--- a/drivers/media/platform/renesas/rzg2l-cru/rzg2l-video.c
+++ b/drivers/media/platform/renesas/rzg2l-cru/rzg2l-video.c
@@ -767,7 +767,7 @@ int rzg2l_cru_dma_register(struct rzg2l_cru_dev *cru)
 	q->ops = &rzg2l_cru_qops;
 	q->mem_ops = &vb2_dma_contig_memops;
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-	q->min_buffers_needed = 4;
+	q->min_queued_buffers = 4;
 	q->dev = cru->dev;
 
 	ret = vb2_queue_init(q);
diff --git a/drivers/media/platform/renesas/sh_vou.c b/drivers/media/platform/renesas/sh_vou.c
index f792aedc9d82..1e74dd601c2b 100644
--- a/drivers/media/platform/renesas/sh_vou.c
+++ b/drivers/media/platform/renesas/sh_vou.c
@@ -1297,7 +1297,7 @@ static int sh_vou_probe(struct platform_device *pdev)
 	q->ops = &sh_vou_qops;
 	q->mem_ops = &vb2_dma_contig_memops;
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-	q->min_buffers_needed = 2;
+	q->min_queued_buffers = 2;
 	q->lock = &vou_dev->fop_lock;
 	q->dev = &pdev->dev;
 	ret = vb2_queue_init(q);
diff --git a/drivers/media/platform/rockchip/rkisp1/rkisp1-capture.c b/drivers/media/platform/rockchip/rkisp1/rkisp1-capture.c
index c6d7e01c8949..aebd3c12020b 100644
--- a/drivers/media/platform/rockchip/rkisp1/rkisp1-capture.c
+++ b/drivers/media/platform/rockchip/rkisp1/rkisp1-capture.c
@@ -1431,7 +1431,7 @@ static int rkisp1_register_capture(struct rkisp1_capture *cap)
 	q->ops = &rkisp1_vb2_ops;
 	q->mem_ops = &vb2_dma_contig_memops;
 	q->buf_struct_size = sizeof(struct rkisp1_buffer);
-	q->min_buffers_needed = RKISP1_MIN_BUFFERS_NEEDED;
+	q->min_queued_buffers = RKISP1_MIN_BUFFERS_NEEDED;
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	q->lock = &node->vlock;
 	q->dev = cap->rkisp1->dev;
diff --git a/drivers/media/platform/st/sti/hva/hva-v4l2.c b/drivers/media/platform/st/sti/hva/hva-v4l2.c
index cfe83e9dc01b..161a5c0fbc4e 100644
--- a/drivers/media/platform/st/sti/hva/hva-v4l2.c
+++ b/drivers/media/platform/st/sti/hva/hva-v4l2.c
@@ -1142,7 +1142,7 @@ static int hva_queue_init(void *priv, struct vb2_queue *src_vq,
 
 	src_vq->type = V4L2_BUF_TYPE_VIDEO_OUTPUT;
 	src_vq->buf_struct_size = sizeof(struct hva_frame);
-	src_vq->min_buffers_needed = MIN_FRAMES;
+	src_vq->min_queued_buffers = MIN_FRAMES;
 	src_vq->dev = ctx->hva_dev->dev;
 
 	ret = queue_init(ctx, src_vq);
@@ -1151,7 +1151,7 @@ static int hva_queue_init(void *priv, struct vb2_queue *src_vq,
 
 	dst_vq->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
 	dst_vq->buf_struct_size = sizeof(struct hva_stream);
-	dst_vq->min_buffers_needed = MIN_STREAMS;
+	dst_vq->min_queued_buffers = MIN_STREAMS;
 	dst_vq->dev = ctx->hva_dev->dev;
 
 	return queue_init(ctx, dst_vq);
diff --git a/drivers/media/platform/st/stm32/stm32-dcmi.c b/drivers/media/platform/st/stm32/stm32-dcmi.c
index 48140fdf40bb..c4610e305546 100644
--- a/drivers/media/platform/st/stm32/stm32-dcmi.c
+++ b/drivers/media/platform/st/stm32/stm32-dcmi.c
@@ -2031,7 +2031,7 @@ static int dcmi_probe(struct platform_device *pdev)
 	q->ops = &dcmi_video_qops;
 	q->mem_ops = &vb2_dma_contig_memops;
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-	q->min_buffers_needed = 2;
+	q->min_queued_buffers = 2;
 	q->allow_cache_hints = 1;
 	q->dev = &pdev->dev;
 
diff --git a/drivers/media/platform/st/stm32/stm32-dcmipp/dcmipp-bytecap.c b/drivers/media/platform/st/stm32/stm32-dcmipp/dcmipp-bytecap.c
index 0cd9b088bd97..9f768f011fa2 100644
--- a/drivers/media/platform/st/stm32/stm32-dcmipp/dcmipp-bytecap.c
+++ b/drivers/media/platform/st/stm32/stm32-dcmipp/dcmipp-bytecap.c
@@ -424,7 +424,7 @@ static int dcmipp_bytecap_start_streaming(struct vb2_queue *vq,
 	reg_set(vcap, DCMIPP_P0FSCR, DCMIPP_P0FSCR_PIPEN);
 
 	/*
-	 * vb2 framework guarantee that we have at least 'min_buffers_needed'
+	 * vb2 framework guarantee that we have at least 'min_queued_buffers'
 	 * buffers in the list at this moment
 	 */
 	vcap->next = list_first_entry(&vcap->buffers, typeof(*buf), list);
@@ -889,7 +889,7 @@ struct dcmipp_ent_device *dcmipp_bytecap_ent_init(struct device *dev,
 	q->ops = &dcmipp_bytecap_qops;
 	q->mem_ops = &vb2_dma_contig_memops;
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-	q->min_buffers_needed = 1;
+	q->min_queued_buffers = 1;
 	q->dev = dev;
 
 	/* DCMIPP requires 16 bytes aligned buffers */
diff --git a/drivers/media/platform/sunxi/sun4i-csi/sun4i_dma.c b/drivers/media/platform/sunxi/sun4i-csi/sun4i_dma.c
index 95b5633b7914..d1371e130113 100644
--- a/drivers/media/platform/sunxi/sun4i-csi/sun4i_dma.c
+++ b/drivers/media/platform/sunxi/sun4i-csi/sun4i_dma.c
@@ -411,7 +411,7 @@ int sun4i_csi_dma_register(struct sun4i_csi *csi, int irq)
 	for (i = 0; i < CSI_MAX_BUFFER; i++)
 		csi->current_buf[i] = NULL;
 
-	q->min_buffers_needed = 3;
+	q->min_queued_buffers = 3;
 	q->type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
 	q->io_modes = VB2_MMAP | VB2_DMABUF;
 	q->lock = &csi->lock;
diff --git a/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi_capture.c b/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi_capture.c
index cf6aadbc130b..14c0dc827c52 100644
--- a/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi_capture.c
+++ b/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi_capture.c
@@ -1010,7 +1010,7 @@ int sun6i_csi_capture_setup(struct sun6i_csi_device *csi_dev)
 	queue->buf_struct_size = sizeof(struct sun6i_csi_buffer);
 	queue->ops = &sun6i_csi_capture_queue_ops;
 	queue->mem_ops = &vb2_dma_contig_memops;
-	queue->min_buffers_needed = 2;
+	queue->min_queued_buffers = 2;
 	queue->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	queue->lock = &capture->lock;
 	queue->dev = csi_dev->dev;
diff --git a/drivers/media/platform/sunxi/sun8i-di/sun8i-di.c b/drivers/media/platform/sunxi/sun8i-di/sun8i-di.c
index 90ab1d77b6a5..954fabec27f6 100644
--- a/drivers/media/platform/sunxi/sun8i-di/sun8i-di.c
+++ b/drivers/media/platform/sunxi/sun8i-di/sun8i-di.c
@@ -673,7 +673,7 @@ static int deinterlace_queue_init(void *priv, struct vb2_queue *src_vq,
 	src_vq->io_modes = VB2_MMAP | VB2_DMABUF;
 	src_vq->drv_priv = ctx;
 	src_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer);
-	src_vq->min_buffers_needed = 1;
+	src_vq->min_queued_buffers = 1;
 	src_vq->ops = &deinterlace_qops;
 	src_vq->mem_ops = &vb2_dma_contig_memops;
 	src_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
@@ -688,7 +688,7 @@ static int deinterlace_queue_init(void *priv, struct vb2_queue *src_vq,
 	dst_vq->io_modes = VB2_MMAP | VB2_DMABUF;
 	dst_vq->drv_priv = ctx;
 	dst_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer);
-	dst_vq->min_buffers_needed = 2;
+	dst_vq->min_queued_buffers = 2;
 	dst_vq->ops = &deinterlace_qops;
 	dst_vq->mem_ops = &vb2_dma_contig_memops;
 	dst_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
diff --git a/drivers/media/platform/sunxi/sun8i-rotate/sun8i_rotate.c b/drivers/media/platform/sunxi/sun8i-rotate/sun8i_rotate.c
index 0b025ec91826..a12323ca89fa 100644
--- a/drivers/media/platform/sunxi/sun8i-rotate/sun8i_rotate.c
+++ b/drivers/media/platform/sunxi/sun8i-rotate/sun8i_rotate.c
@@ -536,7 +536,7 @@ static int rotate_queue_init(void *priv, struct vb2_queue *src_vq,
 	src_vq->io_modes = VB2_MMAP | VB2_DMABUF;
 	src_vq->drv_priv = ctx;
 	src_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer);
-	src_vq->min_buffers_needed = 1;
+	src_vq->min_queued_buffers = 1;
 	src_vq->ops = &rotate_qops;
 	src_vq->mem_ops = &vb2_dma_contig_memops;
 	src_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
@@ -551,7 +551,7 @@ static int rotate_queue_init(void *priv, struct vb2_queue *src_vq,
 	dst_vq->io_modes = VB2_MMAP | VB2_DMABUF;
 	dst_vq->drv_priv = ctx;
 	dst_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer);
-	dst_vq->min_buffers_needed = 2;
+	dst_vq->min_queued_buffers = 2;
 	dst_vq->ops = &rotate_qops;
 	dst_vq->mem_ops = &vb2_dma_contig_memops;
 	dst_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
diff --git a/drivers/media/platform/ti/am437x/am437x-vpfe.c b/drivers/media/platform/ti/am437x/am437x-vpfe.c
index f18acf9286a2..77e12457d149 100644
--- a/drivers/media/platform/ti/am437x/am437x-vpfe.c
+++ b/drivers/media/platform/ti/am437x/am437x-vpfe.c
@@ -2234,7 +2234,7 @@ static int vpfe_probe_complete(struct vpfe_device *vpfe)
 	q->buf_struct_size = sizeof(struct vpfe_cap_buffer);
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	q->lock = &vpfe->lock;
-	q->min_buffers_needed = 1;
+	q->min_queued_buffers = 1;
 	q->dev = vpfe->pdev;
 
 	err = vb2_queue_init(q);
diff --git a/drivers/media/platform/ti/cal/cal-video.c b/drivers/media/platform/ti/cal/cal-video.c
index e1c5e68e945b..e1ba5dfc217e 100644
--- a/drivers/media/platform/ti/cal/cal-video.c
+++ b/drivers/media/platform/ti/cal/cal-video.c
@@ -1010,7 +1010,7 @@ int cal_ctx_v4l2_init(struct cal_ctx *ctx)
 	q->mem_ops = &vb2_dma_contig_memops;
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	q->lock = &ctx->mutex;
-	q->min_buffers_needed = 3;
+	q->min_queued_buffers = 3;
 	q->dev = ctx->cal->dev;
 
 	ret = vb2_queue_init(q);
diff --git a/drivers/media/platform/ti/davinci/vpif_capture.c b/drivers/media/platform/ti/davinci/vpif_capture.c
index fc42b4bc37e6..c31a5566fc5a 100644
--- a/drivers/media/platform/ti/davinci/vpif_capture.c
+++ b/drivers/media/platform/ti/davinci/vpif_capture.c
@@ -1429,7 +1429,7 @@ static int vpif_probe_complete(void)
 		q->mem_ops = &vb2_dma_contig_memops;
 		q->buf_struct_size = sizeof(struct vpif_cap_buffer);
 		q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-		q->min_buffers_needed = 1;
+		q->min_queued_buffers = 1;
 		q->lock = &common->lock;
 		q->dev = vpif_dev;
 
diff --git a/drivers/media/platform/ti/davinci/vpif_display.c b/drivers/media/platform/ti/davinci/vpif_display.c
index 9dbab1003c1d..02ede1fe12cb 100644
--- a/drivers/media/platform/ti/davinci/vpif_display.c
+++ b/drivers/media/platform/ti/davinci/vpif_display.c
@@ -1169,7 +1169,7 @@ static int vpif_probe_complete(void)
 		q->mem_ops = &vb2_dma_contig_memops;
 		q->buf_struct_size = sizeof(struct vpif_disp_buffer);
 		q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-		q->min_buffers_needed = 1;
+		q->min_queued_buffers = 1;
 		q->lock = &common->lock;
 		q->dev = vpif_dev;
 		err = vb2_queue_init(q);
diff --git a/drivers/media/platform/ti/j721e-csi2rx/j721e-csi2rx.c b/drivers/media/platform/ti/j721e-csi2rx/j721e-csi2rx.c
index ada61391c8d2..59b30fc43144 100644
--- a/drivers/media/platform/ti/j721e-csi2rx/j721e-csi2rx.c
+++ b/drivers/media/platform/ti/j721e-csi2rx/j721e-csi2rx.c
@@ -873,7 +873,7 @@ static int ti_csi2rx_init_vb2q(struct ti_csi2rx_dev *csi)
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	q->dev = dmaengine_get_dma_device(csi->dma.chan);
 	q->lock = &csi->mutex;
-	q->min_buffers_needed = 1;
+	q->min_queued_buffers = 1;
 
 	ret = vb2_queue_init(q);
 	if (ret)
diff --git a/drivers/media/platform/ti/omap/omap_vout.c b/drivers/media/platform/ti/omap/omap_vout.c
index 72ce903717d3..1c56b6a87ced 100644
--- a/drivers/media/platform/ti/omap/omap_vout.c
+++ b/drivers/media/platform/ti/omap/omap_vout.c
@@ -1404,7 +1404,7 @@ static int __init omap_vout_setup_video_data(struct omap_vout_device *vout)
 	vq->ops = &omap_vout_vb2_ops;
 	vq->mem_ops = &vb2_dma_contig_memops;
 	vq->lock = &vout->lock;
-	vq->min_buffers_needed = 1;
+	vq->min_queued_buffers = 1;
 	vfd->queue = vq;
 
 	ret = vb2_queue_init(vq);
diff --git a/drivers/media/test-drivers/vimc/vimc-capture.c b/drivers/media/test-drivers/vimc/vimc-capture.c
index aa944270e716..2a2d19d23bab 100644
--- a/drivers/media/test-drivers/vimc/vimc-capture.c
+++ b/drivers/media/test-drivers/vimc/vimc-capture.c
@@ -432,7 +432,7 @@ static struct vimc_ent_device *vimc_capture_add(struct vimc_device *vimc,
 	q->mem_ops = vimc_allocator == VIMC_ALLOCATOR_DMA_CONTIG
 		   ? &vb2_dma_contig_memops : &vb2_vmalloc_memops;
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-	q->min_buffers_needed = 2;
+	q->min_queued_buffers = 2;
 	q->lock = &vcapture->lock;
 	q->dev = v4l2_dev->dev;
 
diff --git a/drivers/media/test-drivers/vivid/vivid-core.c b/drivers/media/test-drivers/vivid/vivid-core.c
index 353f035fcd19..159c72cbb5bf 100644
--- a/drivers/media/test-drivers/vivid/vivid-core.c
+++ b/drivers/media/test-drivers/vivid/vivid-core.c
@@ -861,7 +861,7 @@ static const struct media_device_ops vivid_media_ops = {
 static int vivid_create_queue(struct vivid_dev *dev,
 			      struct vb2_queue *q,
 			      u32 buf_type,
-			      unsigned int min_buffers_needed,
+			      unsigned int min_queued_buffers,
 			      const struct vb2_ops *ops)
 {
 	if (buf_type == V4L2_BUF_TYPE_VIDEO_CAPTURE && dev->multiplanar)
@@ -898,7 +898,7 @@ static int vivid_create_queue(struct vivid_dev *dev,
 	q->mem_ops = allocators[dev->inst] == 1 ? &vb2_dma_contig_memops :
 						  &vb2_vmalloc_memops;
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-	q->min_buffers_needed = supports_requests[dev->inst] ? 0 : min_buffers_needed;
+	q->min_queued_buffers = supports_requests[dev->inst] ? 0 : min_queued_buffers;
 	q->lock = &dev->mutex;
 	q->dev = dev->v4l2_dev.dev;
 	q->supports_requests = supports_requests[dev->inst];
diff --git a/drivers/media/usb/cx231xx/cx231xx-417.c b/drivers/media/usb/cx231xx/cx231xx-417.c
index 45973fe690b2..3b75d062e602 100644
--- a/drivers/media/usb/cx231xx/cx231xx-417.c
+++ b/drivers/media/usb/cx231xx/cx231xx-417.c
@@ -1782,7 +1782,7 @@ int cx231xx_417_register(struct cx231xx *dev)
 	q->ops = &cx231xx_video_qops;
 	q->mem_ops = &vb2_vmalloc_memops;
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-	q->min_buffers_needed = 1;
+	q->min_queued_buffers = 1;
 	q->lock = &dev->lock;
 	err = vb2_queue_init(q);
 	if (err)
diff --git a/drivers/media/usb/cx231xx/cx231xx-video.c b/drivers/media/usb/cx231xx/cx231xx-video.c
index c8eb4222319d..8f347bbeeb32 100644
--- a/drivers/media/usb/cx231xx/cx231xx-video.c
+++ b/drivers/media/usb/cx231xx/cx231xx-video.c
@@ -1811,7 +1811,7 @@ int cx231xx_register_analog_devices(struct cx231xx *dev)
 	q->ops = &cx231xx_video_qops;
 	q->mem_ops = &vb2_vmalloc_memops;
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-	q->min_buffers_needed = 1;
+	q->min_queued_buffers = 1;
 	q->lock = &dev->lock;
 	ret = vb2_queue_init(q);
 	if (ret)
@@ -1871,7 +1871,7 @@ int cx231xx_register_analog_devices(struct cx231xx *dev)
 	q->ops = &cx231xx_vbi_qops;
 	q->mem_ops = &vb2_vmalloc_memops;
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-	q->min_buffers_needed = 1;
+	q->min_queued_buffers = 1;
 	q->lock = &dev->lock;
 	ret = vb2_queue_init(q);
 	if (ret)
diff --git a/drivers/media/usb/dvb-usb/cxusb-analog.c b/drivers/media/usb/dvb-usb/cxusb-analog.c
index deba5224cb8d..b5d8c6b75ae1 100644
--- a/drivers/media/usb/dvb-usb/cxusb-analog.c
+++ b/drivers/media/usb/dvb-usb/cxusb-analog.c
@@ -1632,7 +1632,7 @@ static int cxusb_medion_register_analog_video(struct dvb_usb_device *dvbdev)
 	cxdev->videoqueue.buf_struct_size =
 		sizeof(struct cxusb_medion_vbuffer);
 	cxdev->videoqueue.timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-	cxdev->videoqueue.min_buffers_needed = 6;
+	cxdev->videoqueue.min_queued_buffers = 6;
 	cxdev->videoqueue.lock = &cxdev->dev_lock;
 
 	ret = vb2_queue_init(&cxdev->videoqueue);
diff --git a/drivers/media/usb/gspca/gspca.c b/drivers/media/usb/gspca/gspca.c
index 770714c34295..e8c8bdb9c40b 100644
--- a/drivers/media/usb/gspca/gspca.c
+++ b/drivers/media/usb/gspca/gspca.c
@@ -1257,7 +1257,7 @@ static int vidioc_g_parm(struct file *filp, void *priv,
 {
 	struct gspca_dev *gspca_dev = video_drvdata(filp);
 
-	parm->parm.capture.readbuffers = gspca_dev->queue.min_buffers_needed;
+	parm->parm.capture.readbuffers = gspca_dev->queue.min_queued_buffers;
 
 	if (!gspca_dev->sd_desc->get_streamparm)
 		return 0;
@@ -1273,7 +1273,7 @@ static int vidioc_s_parm(struct file *filp, void *priv,
 {
 	struct gspca_dev *gspca_dev = video_drvdata(filp);
 
-	parm->parm.capture.readbuffers = gspca_dev->queue.min_buffers_needed;
+	parm->parm.capture.readbuffers = gspca_dev->queue.min_queued_buffers;
 
 	if (!gspca_dev->sd_desc->set_streamparm) {
 		parm->parm.capture.capability = 0;
@@ -1517,7 +1517,7 @@ int gspca_dev_probe2(struct usb_interface *intf,
 	q->ops = &gspca_qops;
 	q->mem_ops = &vb2_vmalloc_memops;
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-	q->min_buffers_needed = 2;
+	q->min_queued_buffers = 2;
 	q->lock = &gspca_dev->usb_lock;
 	ret = vb2_queue_init(q);
 	if (ret)
diff --git a/drivers/staging/media/deprecated/atmel/atmel-isc-base.c b/drivers/staging/media/deprecated/atmel/atmel-isc-base.c
index 468568b5bb7a..305b103153d7 100644
--- a/drivers/staging/media/deprecated/atmel/atmel-isc-base.c
+++ b/drivers/staging/media/deprecated/atmel/atmel-isc-base.c
@@ -1871,7 +1871,7 @@ static int isc_async_complete(struct v4l2_async_notifier *notifier)
 	q->mem_ops		= &vb2_dma_contig_memops;
 	q->timestamp_flags	= V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	q->lock			= &isc->lock;
-	q->min_buffers_needed	= 1;
+	q->min_queued_buffers	= 1;
 	q->dev			= isc->dev;
 
 	ret = vb2_queue_init(q);
diff --git a/drivers/staging/media/imx/imx-media-capture.c b/drivers/staging/media/imx/imx-media-capture.c
index c944fb131b0a..efa7623b5cee 100644
--- a/drivers/staging/media/imx/imx-media-capture.c
+++ b/drivers/staging/media/imx/imx-media-capture.c
@@ -1024,7 +1024,7 @@ imx_media_capture_device_init(struct device *dev, struct v4l2_subdev *src_sd,
 	vq->mem_ops = &vb2_dma_contig_memops;
 	vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	vq->lock = &priv->mutex;
-	vq->min_buffers_needed = 2;
+	vq->min_queued_buffers = 2;
 	vq->dev = priv->dev;
 
 	ret = vb2_queue_init(vq);
diff --git a/drivers/staging/media/ipu3/ipu3-v4l2.c b/drivers/staging/media/ipu3/ipu3-v4l2.c
index 0fe2b858da83..a66f034380c0 100644
--- a/drivers/staging/media/ipu3/ipu3-v4l2.c
+++ b/drivers/staging/media/ipu3/ipu3-v4l2.c
@@ -1198,7 +1198,7 @@ static int imgu_v4l2_node_setup(struct imgu_device *imgu, unsigned int pipe,
 	vbq->buf_struct_size = imgu->buf_struct_size;
 	vbq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	/* can streamon w/o buffers */
-	vbq->min_buffers_needed = 0;
+	vbq->min_queued_buffers = 0;
 	vbq->drv_priv = imgu;
 	vbq->lock = &node->lock;
 	r = vb2_queue_init(vbq);
diff --git a/drivers/staging/media/meson/vdec/vdec.c b/drivers/staging/media/meson/vdec/vdec.c
index 1e2369f104c8..de3e0345ab7c 100644
--- a/drivers/staging/media/meson/vdec/vdec.c
+++ b/drivers/staging/media/meson/vdec/vdec.c
@@ -184,7 +184,7 @@ static void process_num_buffers(struct vb2_queue *q,
 	 * we need all of them to be queued into the driver
 	 */
 	sess->num_dst_bufs = q_num_bufs + *num_buffers;
-	q->min_buffers_needed = max(fmt_out->min_buffers, sess->num_dst_bufs);
+	q->min_queued_buffers = max(fmt_out->min_buffers, sess->num_dst_bufs);
 }
 
 static int vdec_queue_setup(struct vb2_queue *q, unsigned int *num_buffers,
@@ -825,7 +825,7 @@ static int m2m_queue_init(void *priv, struct vb2_queue *src_vq,
 	src_vq->mem_ops = &vb2_dma_contig_memops;
 	src_vq->drv_priv = sess;
 	src_vq->buf_struct_size = sizeof(struct dummy_buf);
-	src_vq->min_buffers_needed = 1;
+	src_vq->min_queued_buffers = 1;
 	src_vq->dev = sess->core->dev;
 	src_vq->lock = &sess->lock;
 	ret = vb2_queue_init(src_vq);
@@ -839,7 +839,7 @@ static int m2m_queue_init(void *priv, struct vb2_queue *src_vq,
 	dst_vq->mem_ops = &vb2_dma_contig_memops;
 	dst_vq->drv_priv = sess;
 	dst_vq->buf_struct_size = sizeof(struct dummy_buf);
-	dst_vq->min_buffers_needed = 1;
+	dst_vq->min_queued_buffers = 1;
 	dst_vq->dev = sess->core->dev;
 	dst_vq->lock = &sess->lock;
 	return vb2_queue_init(dst_vq);
diff --git a/drivers/staging/media/starfive/camss/stf-video.c b/drivers/staging/media/starfive/camss/stf-video.c
index 0b305f21eb53..989b5e82bae9 100644
--- a/drivers/staging/media/starfive/camss/stf-video.c
+++ b/drivers/staging/media/starfive/camss/stf-video.c
@@ -513,7 +513,7 @@ int stf_video_register(struct stfcamss_video *video,
 	q->buf_struct_size = sizeof(struct stfcamss_buffer);
 	q->dev = video->stfcamss->dev;
 	q->lock = &video->q_lock;
-	q->min_buffers_needed = STFCAMSS_MIN_BUFFERS;
+	q->min_queued_buffers = STFCAMSS_MIN_BUFFERS;
 	ret = vb2_queue_init(q);
 	if (ret < 0) {
 		dev_err(video->stfcamss->dev,
diff --git a/drivers/staging/media/sunxi/sun6i-isp/sun6i_isp_capture.c b/drivers/staging/media/sunxi/sun6i-isp/sun6i_isp_capture.c
index 1595a9607775..0eea4c2c3627 100644
--- a/drivers/staging/media/sunxi/sun6i-isp/sun6i_isp_capture.c
+++ b/drivers/staging/media/sunxi/sun6i-isp/sun6i_isp_capture.c
@@ -660,7 +660,7 @@ int sun6i_isp_capture_setup(struct sun6i_isp_device *isp_dev)
 	queue->buf_struct_size = sizeof(struct sun6i_isp_buffer);
 	queue->ops = &sun6i_isp_capture_queue_ops;
 	queue->mem_ops = &vb2_dma_contig_memops;
-	queue->min_buffers_needed = 2;
+	queue->min_queued_buffers = 2;
 	queue->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	queue->lock = &capture->lock;
 	queue->dev = isp_dev->dev;
diff --git a/drivers/staging/media/sunxi/sun6i-isp/sun6i_isp_params.c b/drivers/staging/media/sunxi/sun6i-isp/sun6i_isp_params.c
index e28be895b486..53d05e8a364b 100644
--- a/drivers/staging/media/sunxi/sun6i-isp/sun6i_isp_params.c
+++ b/drivers/staging/media/sunxi/sun6i-isp/sun6i_isp_params.c
@@ -489,7 +489,7 @@ int sun6i_isp_params_setup(struct sun6i_isp_device *isp_dev)
 	queue->buf_struct_size = sizeof(struct sun6i_isp_buffer);
 	queue->ops = &sun6i_isp_params_queue_ops;
 	queue->mem_ops = &vb2_vmalloc_memops;
-	queue->min_buffers_needed = 1;
+	queue->min_queued_buffers = 1;
 	queue->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	queue->lock = &params->lock;
 	queue->dev = isp_dev->dev;
diff --git a/drivers/staging/media/tegra-video/vi.c b/drivers/staging/media/tegra-video/vi.c
index e0bb59ee3c09..af6e3a0d8df4 100644
--- a/drivers/staging/media/tegra-video/vi.c
+++ b/drivers/staging/media/tegra-video/vi.c
@@ -1174,7 +1174,7 @@ static int tegra_channel_init(struct tegra_vi_channel *chan)
 	chan->queue.ops = &tegra_channel_queue_qops;
 	chan->queue.mem_ops = &vb2_dma_contig_memops;
 	chan->queue.timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-	chan->queue.min_buffers_needed = 2;
+	chan->queue.min_queued_buffers = 2;
 	chan->queue.dev = vi->dev;
 	ret = vb2_queue_init(&chan->queue);
 	if (ret < 0) {
diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h
index 5557d78b6f20..56719a26a46c 100644
--- a/include/media/videobuf2-core.h
+++ b/include/media/videobuf2-core.h
@@ -402,7 +402,7 @@ struct vb2_buffer {
  *			by calling vb2_buffer_done() with %VB2_BUF_STATE_QUEUED.
  *			If you need a minimum number of buffers before you can
  *			start streaming, then set
- *			&vb2_queue->min_buffers_needed. If that is non-zero
+ *			&vb2_queue->min_queued_buffers. If that is non-zero
  *			then @start_streaming won't be called until at least
  *			that many buffers have been queued up by userspace.
  * @stop_streaming:	called when 'streaming' state must be disabled; driver
@@ -546,10 +546,13 @@ struct vb2_buf_ops {
  * @gfp_flags:	additional gfp flags used when allocating the buffers.
  *		Typically this is 0, but it may be e.g. %GFP_DMA or %__GFP_DMA32
  *		to force the buffer allocation to a specific memory zone.
- * @min_buffers_needed: the minimum number of buffers needed before
+ * @min_queued_buffers: the minimum number of queued buffers needed before
  *		@start_streaming can be called. Used when a DMA engine
  *		cannot be started unless at least this number of buffers
  *		have been queued into the driver.
+ *		VIDIOC_REQBUFS will ensure at least @min_queued_buffers
+ *		buffers will be allocated. Note that VIDIOC_CREATE_BUFS will not
+ *		modify the requested buffer count.
  */
 /*
  * Private elements (won't appear at the uAPI book):
@@ -614,7 +617,7 @@ struct vb2_queue {
 	unsigned int			buf_struct_size;
 	u32				timestamp_flags;
 	gfp_t				gfp_flags;
-	u32				min_buffers_needed;
+	u32				min_queued_buffers;
 
 	struct device			*alloc_devs[VB2_MAX_PLANES];
 
diff --git a/samples/v4l/v4l2-pci-skeleton.c b/samples/v4l/v4l2-pci-skeleton.c
index a65aa9d1e9da..4fe8f58b270f 100644
--- a/samples/v4l/v4l2-pci-skeleton.c
+++ b/samples/v4l/v4l2-pci-skeleton.c
@@ -821,7 +821,7 @@ static int skeleton_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	 * available before it can be started. The start_streaming() op
 	 * won't be called until at least this many buffers are queued up.
 	 */
-	q->min_buffers_needed = 2;
+	q->min_queued_buffers = 2;
 	/*
 	 * The serialization lock for the streaming ioctls. This is the same
 	 * as the main serialization lock, but if some of the non-streaming
-- 
cgit v1.2.3


From 3c6b0c1c28184038d90dffe8eb542bedcb8ccf98 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 30 Nov 2023 14:27:29 +0100
Subject: srcu: Use try-lock lockdep annotation for NMI-safe access.

It is claimed that srcu_read_lock_nmisafe() NMI-safe. However it
triggers a lockdep if used from NMI because lockdep expects a deadlock
since nothing disables NMIs while the lock is acquired.

This is because commit f0f44752f5f61 ("rcu: Annotate SRCU's update-side
lockdep dependencies") annotates synchronize_srcu() as a write lock
usage. This helps to detect a deadlocks such as
	srcu_read_lock();
	synchronize_srcu();
	srcu_read_unlock();

The side effect is that the lock srcu_struct now has a USED usage in normal
contexts, so it conflicts with a USED_READ usage in NMI. But this shouldn't
cause a real deadlock because the write lock usage from synchronize_srcu()
is a fake one and only used for read/write deadlock detection.

Use a try-lock annotation for srcu_read_lock_nmisafe() to avoid lockdep
complains if used from NMI.

Fixes: f0f44752f5f6 ("rcu: Annotate SRCU's update-side lockdep dependencies")
Link: https://lore.kernel.org/r/20230927160231.XRCDDSK4@linutronix.de
Reviewed-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Neeraj Upadhyay (AMD) <neeraj.iitr10@gmail.com>
---
 include/linux/rcupdate.h | 6 ++++++
 include/linux/srcu.h     | 2 +-
 2 files changed, 7 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index f7206b2623c9..31d523c4e089 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -301,6 +301,11 @@ static inline void rcu_lock_acquire(struct lockdep_map *map)
 	lock_acquire(map, 0, 0, 2, 0, NULL, _THIS_IP_);
 }
 
+static inline void rcu_try_lock_acquire(struct lockdep_map *map)
+{
+	lock_acquire(map, 0, 1, 2, 0, NULL, _THIS_IP_);
+}
+
 static inline void rcu_lock_release(struct lockdep_map *map)
 {
 	lock_release(map, _THIS_IP_);
@@ -315,6 +320,7 @@ int rcu_read_lock_any_held(void);
 #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
 # define rcu_lock_acquire(a)		do { } while (0)
+# define rcu_try_lock_acquire(a)	do { } while (0)
 # define rcu_lock_release(a)		do { } while (0)
 
 static inline int rcu_read_lock_held(void)
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index 127ef3b2e607..236610e4a8fa 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -229,7 +229,7 @@ static inline int srcu_read_lock_nmisafe(struct srcu_struct *ssp) __acquires(ssp
 
 	srcu_check_nmi_safety(ssp, true);
 	retval = __srcu_read_lock_nmisafe(ssp);
-	rcu_lock_acquire(&ssp->dep_map);
+	rcu_try_lock_acquire(&ssp->dep_map);
 	return retval;
 }
 
-- 
cgit v1.2.3


From 493dffa3ab07b5d2c0b7bd5de5bff6e85f01f52a Mon Sep 17 00:00:00 2001
From: Philipp Stanner <pstanner@redhat.com>
Date: Wed, 20 Sep 2023 11:22:12 +0200
Subject: rculist.h: docs: Fix wrong function summary

The brief summary in the docstring for function list_next_or_null_rcu()
states that the function is supposed to provide the "first" member of a
list, whereas in truth it returns the next member.

Change the docstring so it describes what the function actually does.

Signed-off-by: Philipp Stanner <pstanner@redhat.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Neeraj Upadhyay (AMD) <neeraj.iitr10@gmail.com>
---
 include/linux/rculist.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index d29740be4833..3dc1e58865f7 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -355,7 +355,7 @@ static inline void list_splice_tail_init_rcu(struct list_head *list,
 })
 
 /**
- * list_next_or_null_rcu - get the first element from a list
+ * list_next_or_null_rcu - get the next element from a list
  * @head:	the head for the list.
  * @ptr:        the list head to take the next element from.
  * @type:       the type of the struct this is embedded in.
-- 
cgit v1.2.3


From 1e13c5644c443dee727ac1330bc118c909a1cf07 Mon Sep 17 00:00:00 2001
From: Melissa Wen <mwen@igalia.com>
Date: Thu, 16 Nov 2023 18:57:41 -0100
Subject: drm/drm_mode_object: increase max objects to accommodate new color
 props

DRM_OBJECT_MAX_PROPERTY limits the number of properties to be attached
and we are increasing that value all time we add a new property (generic
or driver-specific).

In this series, we are adding 13 new KMS driver-specific properties for
AMD color manage:
- CRTC Gamma enumerated Transfer Function
- Plane: Degamma LUT+size+TF, HDR multiplier, shaper LUT+size+TF, 3D
  LUT+size, blend LUT+size+TF (12)

Therefore, just increase DRM_OBJECT_MAX_PROPERTY to a number (64) that
accomodates these new properties and gives some room for others,
avoiding change this number everytime we add a new KMS property.

Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Reviewed-by: Simon Ser <contact@emersion.fr>
Signed-off-by: Melissa Wen <mwen@igalia.com>
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Acked-by: Maxime Ripard <mripard@kernel.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 include/drm/drm_mode_object.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/drm/drm_mode_object.h b/include/drm/drm_mode_object.h
index 912f1e415685..08d7a7f0188f 100644
--- a/include/drm/drm_mode_object.h
+++ b/include/drm/drm_mode_object.h
@@ -60,7 +60,7 @@ struct drm_mode_object {
 	void (*free_cb)(struct kref *kref);
 };
 
-#define DRM_OBJECT_MAX_PROPERTY 24
+#define DRM_OBJECT_MAX_PROPERTY 64
 /**
  * struct drm_object_properties - property tracking for &drm_mode_object
  */
-- 
cgit v1.2.3


From 601603105325ad4ec62db95c9bc428202ece2c8f Mon Sep 17 00:00:00 2001
From: Melissa Wen <mwen@igalia.com>
Date: Thu, 16 Nov 2023 18:57:42 -0100
Subject: drm/drm_property: make replace_property_blob_from_id a DRM helper

Place it in drm_property where drm_property_replace_blob and
drm_property_lookup_blob live. Then we can use the DRM helper for
driver-specific KMS properties too.

Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Reviewed-by: Liviu Dudau <liviu.dudau@arm.com>
Signed-off-by: Melissa Wen <mwen@igalia.com>
Acked-by: Maxime Ripard <mripard@kernel.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/arm/malidp_crtc.c |  2 +-
 drivers/gpu/drm/drm_atomic_uapi.c | 52 ++++------------------------------
 drivers/gpu/drm/drm_property.c    | 59 +++++++++++++++++++++++++++++++++++++++
 include/drm/drm_property.h        |  6 ++++
 4 files changed, 71 insertions(+), 48 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/arm/malidp_crtc.c b/drivers/gpu/drm/arm/malidp_crtc.c
index dc01c43f6193..d72c22dcf685 100644
--- a/drivers/gpu/drm/arm/malidp_crtc.c
+++ b/drivers/gpu/drm/arm/malidp_crtc.c
@@ -221,7 +221,7 @@ static int malidp_crtc_atomic_check_ctm(struct drm_crtc *crtc,
 
 	/*
 	 * The size of the ctm is checked in
-	 * drm_atomic_replace_property_blob_from_id.
+	 * drm_property_replace_blob_from_id.
 	 */
 	ctm = (struct drm_color_ctm *)state->ctm->data;
 	for (i = 0; i < ARRAY_SIZE(ctm->matrix); ++i) {
diff --git a/drivers/gpu/drm/drm_atomic_uapi.c b/drivers/gpu/drm/drm_atomic_uapi.c
index aee4a65d4959..29d4940188d4 100644
--- a/drivers/gpu/drm/drm_atomic_uapi.c
+++ b/drivers/gpu/drm/drm_atomic_uapi.c
@@ -362,48 +362,6 @@ static s32 __user *get_out_fence_for_connector(struct drm_atomic_state *state,
 	return fence_ptr;
 }
 
-static int
-drm_atomic_replace_property_blob_from_id(struct drm_device *dev,
-					 struct drm_property_blob **blob,
-					 uint64_t blob_id,
-					 ssize_t expected_size,
-					 ssize_t expected_elem_size,
-					 bool *replaced)
-{
-	struct drm_property_blob *new_blob = NULL;
-
-	if (blob_id != 0) {
-		new_blob = drm_property_lookup_blob(dev, blob_id);
-		if (new_blob == NULL) {
-			drm_dbg_atomic(dev,
-				       "cannot find blob ID %llu\n", blob_id);
-			return -EINVAL;
-		}
-
-		if (expected_size > 0 &&
-		    new_blob->length != expected_size) {
-			drm_dbg_atomic(dev,
-				       "[BLOB:%d] length %zu different from expected %zu\n",
-				       new_blob->base.id, new_blob->length, expected_size);
-			drm_property_blob_put(new_blob);
-			return -EINVAL;
-		}
-		if (expected_elem_size > 0 &&
-		    new_blob->length % expected_elem_size != 0) {
-			drm_dbg_atomic(dev,
-				       "[BLOB:%d] length %zu not divisible by element size %zu\n",
-				       new_blob->base.id, new_blob->length, expected_elem_size);
-			drm_property_blob_put(new_blob);
-			return -EINVAL;
-		}
-	}
-
-	*replaced |= drm_property_replace_blob(blob, new_blob);
-	drm_property_blob_put(new_blob);
-
-	return 0;
-}
-
 static int drm_atomic_crtc_set_property(struct drm_crtc *crtc,
 		struct drm_crtc_state *state, struct drm_property *property,
 		uint64_t val)
@@ -424,7 +382,7 @@ static int drm_atomic_crtc_set_property(struct drm_crtc *crtc,
 	} else if (property == config->prop_vrr_enabled) {
 		state->vrr_enabled = val;
 	} else if (property == config->degamma_lut_property) {
-		ret = drm_atomic_replace_property_blob_from_id(dev,
+		ret = drm_property_replace_blob_from_id(dev,
 					&state->degamma_lut,
 					val,
 					-1, sizeof(struct drm_color_lut),
@@ -432,7 +390,7 @@ static int drm_atomic_crtc_set_property(struct drm_crtc *crtc,
 		state->color_mgmt_changed |= replaced;
 		return ret;
 	} else if (property == config->ctm_property) {
-		ret = drm_atomic_replace_property_blob_from_id(dev,
+		ret = drm_property_replace_blob_from_id(dev,
 					&state->ctm,
 					val,
 					sizeof(struct drm_color_ctm), -1,
@@ -440,7 +398,7 @@ static int drm_atomic_crtc_set_property(struct drm_crtc *crtc,
 		state->color_mgmt_changed |= replaced;
 		return ret;
 	} else if (property == config->gamma_lut_property) {
-		ret = drm_atomic_replace_property_blob_from_id(dev,
+		ret = drm_property_replace_blob_from_id(dev,
 					&state->gamma_lut,
 					val,
 					-1, sizeof(struct drm_color_lut),
@@ -581,7 +539,7 @@ static int drm_atomic_plane_set_property(struct drm_plane *plane,
 	} else if (property == plane->color_range_property) {
 		state->color_range = val;
 	} else if (property == config->prop_fb_damage_clips) {
-		ret = drm_atomic_replace_property_blob_from_id(dev,
+		ret = drm_property_replace_blob_from_id(dev,
 					&state->fb_damage_clips,
 					val,
 					-1,
@@ -778,7 +736,7 @@ static int drm_atomic_connector_set_property(struct drm_connector *connector,
 		if (state->link_status != DRM_LINK_STATUS_GOOD)
 			state->link_status = val;
 	} else if (property == config->hdr_output_metadata_property) {
-		ret = drm_atomic_replace_property_blob_from_id(dev,
+		ret = drm_property_replace_blob_from_id(dev,
 				&state->hdr_output_metadata,
 				val,
 				sizeof(struct hdr_output_metadata), -1,
diff --git a/drivers/gpu/drm/drm_property.c b/drivers/gpu/drm/drm_property.c
index dfec479830e4..596272149a35 100644
--- a/drivers/gpu/drm/drm_property.c
+++ b/drivers/gpu/drm/drm_property.c
@@ -27,6 +27,7 @@
 #include <drm/drm_drv.h>
 #include <drm/drm_file.h>
 #include <drm/drm_framebuffer.h>
+#include <drm/drm_print.h>
 #include <drm/drm_property.h>
 
 #include "drm_crtc_internal.h"
@@ -751,6 +752,64 @@ bool drm_property_replace_blob(struct drm_property_blob **blob,
 }
 EXPORT_SYMBOL(drm_property_replace_blob);
 
+/**
+ * drm_property_replace_blob_from_id - replace a blob property taking a reference
+ * @dev: DRM device
+ * @blob: a pointer to the member blob to be replaced
+ * @blob_id: the id of the new blob to replace with
+ * @expected_size: expected size of the blob property
+ * @expected_elem_size: expected size of an element in the blob property
+ * @replaced: if the blob was in fact replaced
+ *
+ * Look up the new blob from id, take its reference, check expected sizes of
+ * the blob and its element and replace the old blob by the new one. Advertise
+ * if the replacement operation was successful.
+ *
+ * Return: true if the blob was in fact replaced. -EINVAL if the new blob was
+ * not found or sizes don't match.
+ */
+int drm_property_replace_blob_from_id(struct drm_device *dev,
+					 struct drm_property_blob **blob,
+					 uint64_t blob_id,
+					 ssize_t expected_size,
+					 ssize_t expected_elem_size,
+					 bool *replaced)
+{
+	struct drm_property_blob *new_blob = NULL;
+
+	if (blob_id != 0) {
+		new_blob = drm_property_lookup_blob(dev, blob_id);
+		if (new_blob == NULL) {
+			drm_dbg_atomic(dev,
+				       "cannot find blob ID %llu\n", blob_id);
+			return -EINVAL;
+		}
+
+		if (expected_size > 0 &&
+		    new_blob->length != expected_size) {
+			drm_dbg_atomic(dev,
+				       "[BLOB:%d] length %zu different from expected %zu\n",
+				       new_blob->base.id, new_blob->length, expected_size);
+			drm_property_blob_put(new_blob);
+			return -EINVAL;
+		}
+		if (expected_elem_size > 0 &&
+		    new_blob->length % expected_elem_size != 0) {
+			drm_dbg_atomic(dev,
+				       "[BLOB:%d] length %zu not divisible by element size %zu\n",
+				       new_blob->base.id, new_blob->length, expected_elem_size);
+			drm_property_blob_put(new_blob);
+			return -EINVAL;
+		}
+	}
+
+	*replaced |= drm_property_replace_blob(blob, new_blob);
+	drm_property_blob_put(new_blob);
+
+	return 0;
+}
+EXPORT_SYMBOL(drm_property_replace_blob_from_id);
+
 int drm_mode_getblob_ioctl(struct drm_device *dev,
 			   void *data, struct drm_file *file_priv)
 {
diff --git a/include/drm/drm_property.h b/include/drm/drm_property.h
index 65bc9710a470..082f29156b3e 100644
--- a/include/drm/drm_property.h
+++ b/include/drm/drm_property.h
@@ -279,6 +279,12 @@ struct drm_property_blob *drm_property_create_blob(struct drm_device *dev,
 						   const void *data);
 struct drm_property_blob *drm_property_lookup_blob(struct drm_device *dev,
 						   uint32_t id);
+int drm_property_replace_blob_from_id(struct drm_device *dev,
+				      struct drm_property_blob **blob,
+				      uint64_t blob_id,
+				      ssize_t expected_size,
+				      ssize_t expected_elem_size,
+				      bool *replaced);
 int drm_property_replace_global_blob(struct drm_device *dev,
 				     struct drm_property_blob **replace,
 				     size_t length,
-- 
cgit v1.2.3


From 24013b9301349881c9fcd27e7edacc672e0bf6d3 Mon Sep 17 00:00:00 2001
From: Melissa Wen <mwen@igalia.com>
Date: Thu, 16 Nov 2023 18:57:43 -0100
Subject: drm/drm_plane: track color mgmt changes per plane

We will add color mgmt properties to DRM planes in the next patches and
we want to track when one of this properties change to define atomic
commit behaviors. Using a similar approach from CRTC color props, we set
a color_mgmt_changed boolean whenever a plane color prop changes.

Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Melissa Wen <mwen@igalia.com>
Acked-by: Maxime Ripard <mripard@kernel.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/drm_atomic.c              | 1 +
 drivers/gpu/drm/drm_atomic_state_helper.c | 1 +
 include/drm/drm_plane.h                   | 7 +++++++
 3 files changed, 9 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index c31fc0b48c31..a91737adf8e7 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -733,6 +733,7 @@ static void drm_atomic_plane_print_state(struct drm_printer *p,
 		   drm_get_color_encoding_name(state->color_encoding));
 	drm_printf(p, "\tcolor-range=%s\n",
 		   drm_get_color_range_name(state->color_range));
+	drm_printf(p, "\tcolor_mgmt_changed=%d\n", state->color_mgmt_changed);
 
 	if (plane->funcs->atomic_print_state)
 		plane->funcs->atomic_print_state(p, state);
diff --git a/drivers/gpu/drm/drm_atomic_state_helper.c b/drivers/gpu/drm/drm_atomic_state_helper.c
index 54975de44a0e..519228eb1095 100644
--- a/drivers/gpu/drm/drm_atomic_state_helper.c
+++ b/drivers/gpu/drm/drm_atomic_state_helper.c
@@ -352,6 +352,7 @@ void __drm_atomic_helper_plane_duplicate_state(struct drm_plane *plane,
 	state->fence = NULL;
 	state->commit = NULL;
 	state->fb_damage_clips = NULL;
+	state->color_mgmt_changed = false;
 }
 EXPORT_SYMBOL(__drm_atomic_helper_plane_duplicate_state);
 
diff --git a/include/drm/drm_plane.h b/include/drm/drm_plane.h
index c6565a6f9324..641fe298052d 100644
--- a/include/drm/drm_plane.h
+++ b/include/drm/drm_plane.h
@@ -251,6 +251,13 @@ struct drm_plane_state {
 
 	/** @state: backpointer to global drm_atomic_state */
 	struct drm_atomic_state *state;
+
+	/**
+	 * @color_mgmt_changed: Color management properties have changed. Used
+	 * by the atomic helpers and drivers to steer the atomic commit control
+	 * flow.
+	 */
+	bool color_mgmt_changed : 1;
 };
 
 static inline struct drm_rect
-- 
cgit v1.2.3


From 750e785796bb72423b97cac21ecd0fa3b3b65610 Mon Sep 17 00:00:00 2001
From: Jie Jiang <jiejiang@chromium.org>
Date: Tue, 12 Dec 2023 09:39:23 +0000
Subject: bpf: Support uid and gid when mounting bpffs

Parse uid and gid in bpf_parse_param() so that they can be passed in as
the `data` parameter when mount() bpffs. This will be useful when we
want to control which user/group has the control to the mounted bpffs,
otherwise a separate chown() call will be needed.

Signed-off-by: Jie Jiang <jiejiang@chromium.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Mike Frysinger <vapier@chromium.org>
Acked-by: Christian Brauner <brauner@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20231212093923.497838-1-jiejiang@chromium.org
---
 include/linux/bpf.h |  2 ++
 kernel/bpf/inode.c  | 50 +++++++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 51 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 0bd4889e917a..c87c608a3689 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1595,6 +1595,8 @@ struct bpf_link_primer {
 };
 
 struct bpf_mount_opts {
+	kuid_t uid;
+	kgid_t gid;
 	umode_t mode;
 
 	/* BPF token-related delegation options */
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 5359a0929c35..0a8e1188ea46 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -601,9 +601,16 @@ EXPORT_SYMBOL(bpf_prog_get_type_path);
 static int bpf_show_options(struct seq_file *m, struct dentry *root)
 {
 	struct bpf_mount_opts *opts = root->d_sb->s_fs_info;
-	umode_t mode = d_inode(root)->i_mode & S_IALLUGO & ~S_ISVTX;
+	struct inode *inode = d_inode(root);
+	umode_t mode = inode->i_mode & S_IALLUGO & ~S_ISVTX;
 	u64 mask;
 
+	if (!uid_eq(inode->i_uid, GLOBAL_ROOT_UID))
+		seq_printf(m, ",uid=%u",
+			   from_kuid_munged(&init_user_ns, inode->i_uid));
+	if (!gid_eq(inode->i_gid, GLOBAL_ROOT_GID))
+		seq_printf(m, ",gid=%u",
+			   from_kgid_munged(&init_user_ns, inode->i_gid));
 	if (mode != S_IRWXUGO)
 		seq_printf(m, ",mode=%o", mode);
 
@@ -652,6 +659,8 @@ const struct super_operations bpf_super_ops = {
 };
 
 enum {
+	OPT_UID,
+	OPT_GID,
 	OPT_MODE,
 	OPT_DELEGATE_CMDS,
 	OPT_DELEGATE_MAPS,
@@ -660,6 +669,8 @@ enum {
 };
 
 static const struct fs_parameter_spec bpf_fs_parameters[] = {
+	fsparam_u32	("uid",				OPT_UID),
+	fsparam_u32	("gid",				OPT_GID),
 	fsparam_u32oct	("mode",			OPT_MODE),
 	fsparam_string	("delegate_cmds",		OPT_DELEGATE_CMDS),
 	fsparam_string	("delegate_maps",		OPT_DELEGATE_MAPS),
@@ -672,6 +683,8 @@ static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param)
 {
 	struct bpf_mount_opts *opts = fc->s_fs_info;
 	struct fs_parse_result result;
+	kuid_t uid;
+	kgid_t gid;
 	int opt, err;
 	u64 msk;
 
@@ -694,6 +707,34 @@ static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param)
 	}
 
 	switch (opt) {
+	case OPT_UID:
+		uid = make_kuid(current_user_ns(), result.uint_32);
+		if (!uid_valid(uid))
+			goto bad_value;
+
+		/*
+		 * The requested uid must be representable in the
+		 * filesystem's idmapping.
+		 */
+		if (!kuid_has_mapping(fc->user_ns, uid))
+			goto bad_value;
+
+		opts->uid = uid;
+		break;
+	case OPT_GID:
+		gid = make_kgid(current_user_ns(), result.uint_32);
+		if (!gid_valid(gid))
+			goto bad_value;
+
+		/*
+		 * The requested gid must be representable in the
+		 * filesystem's idmapping.
+		 */
+		if (!kgid_has_mapping(fc->user_ns, gid))
+			goto bad_value;
+
+		opts->gid = gid;
+		break;
 	case OPT_MODE:
 		opts->mode = result.uint_32 & S_IALLUGO;
 		break;
@@ -722,6 +763,9 @@ static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param)
 	}
 
 	return 0;
+
+bad_value:
+	return invalfc(fc, "Bad value for '%s'", param->key);
 }
 
 struct bpf_preload_ops *bpf_preload_ops;
@@ -808,6 +852,8 @@ static int bpf_fill_super(struct super_block *sb, struct fs_context *fc)
 	sb->s_op = &bpf_super_ops;
 
 	inode = sb->s_root->d_inode;
+	inode->i_uid = opts->uid;
+	inode->i_gid = opts->gid;
 	inode->i_op = &bpf_dir_iops;
 	inode->i_mode &= ~S_IALLUGO;
 	populate_bpffs(sb->s_root);
@@ -843,6 +889,8 @@ static int bpf_init_fs_context(struct fs_context *fc)
 		return -ENOMEM;
 
 	opts->mode = S_IRWXUGO;
+	opts->uid = current_fsuid();
+	opts->gid = current_fsgid();
 
 	/* start out with no BPF token delegation enabled */
 	opts->delegate_cmds = 0;
-- 
cgit v1.2.3


From 0e6a7b09597011985d7aad3b747c43e9b2a43555 Mon Sep 17 00:00:00 2001
From: Larysa Zaremba <larysa.zaremba@intel.com>
Date: Tue, 5 Dec 2023 22:08:35 +0100
Subject: ice: Support RX hash XDP hint

RX hash XDP hint requests both hash value and type.
Type is XDP-specific, so we need a separate way to map
these values to the hardware ptypes, so create a lookup table.

Instead of creating a new long list, reuse contents
of ice_decode_rx_desc_ptype[] through preprocessor.

Current hash type enum does not contain ICMP packet type,
but ice devices support it, so also add a new type into core code.

Then use previously refactored code and create a function
that allows XDP code to read RX hash.

Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Link: https://lore.kernel.org/r/20231205210847.28460-7-larysa.zaremba@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h | 412 +++++++++++++------------
 drivers/net/ethernet/intel/ice/ice_txrx_lib.c  |  73 +++++
 include/net/xdp.h                              |   3 +
 3 files changed, 284 insertions(+), 204 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
index 89f986a75cc8..d384ddfcb83e 100644
--- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
+++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
@@ -673,6 +673,212 @@ struct ice_tlan_ctx {
  *      Use the enum ice_rx_l2_ptype to decode the packet type
  * ENDIF
  */
+#define ICE_PTYPES								\
+	/* L2 Packet types */							\
+	ICE_PTT_UNUSED_ENTRY(0),						\
+	ICE_PTT(1, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),			\
+	ICE_PTT_UNUSED_ENTRY(2),						\
+	ICE_PTT_UNUSED_ENTRY(3),						\
+	ICE_PTT_UNUSED_ENTRY(4),						\
+	ICE_PTT_UNUSED_ENTRY(5),						\
+	ICE_PTT(6, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),			\
+	ICE_PTT(7, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),			\
+	ICE_PTT_UNUSED_ENTRY(8),						\
+	ICE_PTT_UNUSED_ENTRY(9),						\
+	ICE_PTT(10, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),		\
+	ICE_PTT(11, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),		\
+	ICE_PTT_UNUSED_ENTRY(12),						\
+	ICE_PTT_UNUSED_ENTRY(13),						\
+	ICE_PTT_UNUSED_ENTRY(14),						\
+	ICE_PTT_UNUSED_ENTRY(15),						\
+	ICE_PTT_UNUSED_ENTRY(16),						\
+	ICE_PTT_UNUSED_ENTRY(17),						\
+	ICE_PTT_UNUSED_ENTRY(18),						\
+	ICE_PTT_UNUSED_ENTRY(19),						\
+	ICE_PTT_UNUSED_ENTRY(20),						\
+	ICE_PTT_UNUSED_ENTRY(21),						\
+										\
+	/* Non Tunneled IPv4 */							\
+	ICE_PTT(22, IP, IPV4, FRG, NONE, NONE, NOF, NONE, PAY3),		\
+	ICE_PTT(23, IP, IPV4, NOF, NONE, NONE, NOF, NONE, PAY3),		\
+	ICE_PTT(24, IP, IPV4, NOF, NONE, NONE, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(25),						\
+	ICE_PTT(26, IP, IPV4, NOF, NONE, NONE, NOF, TCP,  PAY4),		\
+	ICE_PTT(27, IP, IPV4, NOF, NONE, NONE, NOF, SCTP, PAY4),		\
+	ICE_PTT(28, IP, IPV4, NOF, NONE, NONE, NOF, ICMP, PAY4),		\
+										\
+	/* IPv4 --> IPv4 */							\
+	ICE_PTT(29, IP, IPV4, NOF, IP_IP, IPV4, FRG, NONE, PAY3),		\
+	ICE_PTT(30, IP, IPV4, NOF, IP_IP, IPV4, NOF, NONE, PAY3),		\
+	ICE_PTT(31, IP, IPV4, NOF, IP_IP, IPV4, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(32),						\
+	ICE_PTT(33, IP, IPV4, NOF, IP_IP, IPV4, NOF, TCP,  PAY4),		\
+	ICE_PTT(34, IP, IPV4, NOF, IP_IP, IPV4, NOF, SCTP, PAY4),		\
+	ICE_PTT(35, IP, IPV4, NOF, IP_IP, IPV4, NOF, ICMP, PAY4),		\
+										\
+	/* IPv4 --> IPv6 */							\
+	ICE_PTT(36, IP, IPV4, NOF, IP_IP, IPV6, FRG, NONE, PAY3),		\
+	ICE_PTT(37, IP, IPV4, NOF, IP_IP, IPV6, NOF, NONE, PAY3),		\
+	ICE_PTT(38, IP, IPV4, NOF, IP_IP, IPV6, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(39),						\
+	ICE_PTT(40, IP, IPV4, NOF, IP_IP, IPV6, NOF, TCP,  PAY4),		\
+	ICE_PTT(41, IP, IPV4, NOF, IP_IP, IPV6, NOF, SCTP, PAY4),		\
+	ICE_PTT(42, IP, IPV4, NOF, IP_IP, IPV6, NOF, ICMP, PAY4),		\
+										\
+	/* IPv4 --> GRE/NAT */							\
+	ICE_PTT(43, IP, IPV4, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3),		\
+										\
+	/* IPv4 --> GRE/NAT --> IPv4 */						\
+	ICE_PTT(44, IP, IPV4, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3),		\
+	ICE_PTT(45, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3),		\
+	ICE_PTT(46, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(47),						\
+	ICE_PTT(48, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, TCP,  PAY4),		\
+	ICE_PTT(49, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4),		\
+	ICE_PTT(50, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4),		\
+										\
+	/* IPv4 --> GRE/NAT --> IPv6 */						\
+	ICE_PTT(51, IP, IPV4, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3),		\
+	ICE_PTT(52, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3),		\
+	ICE_PTT(53, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(54),						\
+	ICE_PTT(55, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, TCP,  PAY4),		\
+	ICE_PTT(56, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4),		\
+	ICE_PTT(57, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4),		\
+										\
+	/* IPv4 --> GRE/NAT --> MAC */						\
+	ICE_PTT(58, IP, IPV4, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3),	\
+										\
+	/* IPv4 --> GRE/NAT --> MAC --> IPv4 */					\
+	ICE_PTT(59, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3),	\
+	ICE_PTT(60, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3),	\
+	ICE_PTT(61, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP,  PAY4),	\
+	ICE_PTT_UNUSED_ENTRY(62),						\
+	ICE_PTT(63, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP,  PAY4),	\
+	ICE_PTT(64, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4),	\
+	ICE_PTT(65, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4),	\
+										\
+	/* IPv4 --> GRE/NAT -> MAC --> IPv6 */					\
+	ICE_PTT(66, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3),	\
+	ICE_PTT(67, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3),	\
+	ICE_PTT(68, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP,  PAY4),	\
+	ICE_PTT_UNUSED_ENTRY(69),						\
+	ICE_PTT(70, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP,  PAY4),	\
+	ICE_PTT(71, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4),	\
+	ICE_PTT(72, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4),	\
+										\
+	/* IPv4 --> GRE/NAT --> MAC/VLAN */					\
+	ICE_PTT(73, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3),	\
+										\
+	/* IPv4 ---> GRE/NAT -> MAC/VLAN --> IPv4 */				\
+	ICE_PTT(74, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3),	\
+	ICE_PTT(75, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3),	\
+	ICE_PTT(76, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP,  PAY4),	\
+	ICE_PTT_UNUSED_ENTRY(77),						\
+	ICE_PTT(78, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP,  PAY4),	\
+	ICE_PTT(79, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4),	\
+	ICE_PTT(80, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4),	\
+										\
+	/* IPv4 -> GRE/NAT -> MAC/VLAN --> IPv6 */				\
+	ICE_PTT(81, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3),	\
+	ICE_PTT(82, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3),	\
+	ICE_PTT(83, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP,  PAY4),	\
+	ICE_PTT_UNUSED_ENTRY(84),						\
+	ICE_PTT(85, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP,  PAY4),	\
+	ICE_PTT(86, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4),	\
+	ICE_PTT(87, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4),	\
+										\
+	/* Non Tunneled IPv6 */							\
+	ICE_PTT(88, IP, IPV6, FRG, NONE, NONE, NOF, NONE, PAY3),		\
+	ICE_PTT(89, IP, IPV6, NOF, NONE, NONE, NOF, NONE, PAY3),		\
+	ICE_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(91),						\
+	ICE_PTT(92, IP, IPV6, NOF, NONE, NONE, NOF, TCP,  PAY4),		\
+	ICE_PTT(93, IP, IPV6, NOF, NONE, NONE, NOF, SCTP, PAY4),		\
+	ICE_PTT(94, IP, IPV6, NOF, NONE, NONE, NOF, ICMP, PAY4),		\
+										\
+	/* IPv6 --> IPv4 */							\
+	ICE_PTT(95, IP, IPV6, NOF, IP_IP, IPV4, FRG, NONE, PAY3),		\
+	ICE_PTT(96, IP, IPV6, NOF, IP_IP, IPV4, NOF, NONE, PAY3),		\
+	ICE_PTT(97, IP, IPV6, NOF, IP_IP, IPV4, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(98),						\
+	ICE_PTT(99, IP, IPV6, NOF, IP_IP, IPV4, NOF, TCP,  PAY4),		\
+	ICE_PTT(100, IP, IPV6, NOF, IP_IP, IPV4, NOF, SCTP, PAY4),		\
+	ICE_PTT(101, IP, IPV6, NOF, IP_IP, IPV4, NOF, ICMP, PAY4),		\
+										\
+	/* IPv6 --> IPv6 */							\
+	ICE_PTT(102, IP, IPV6, NOF, IP_IP, IPV6, FRG, NONE, PAY3),		\
+	ICE_PTT(103, IP, IPV6, NOF, IP_IP, IPV6, NOF, NONE, PAY3),		\
+	ICE_PTT(104, IP, IPV6, NOF, IP_IP, IPV6, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(105),						\
+	ICE_PTT(106, IP, IPV6, NOF, IP_IP, IPV6, NOF, TCP,  PAY4),		\
+	ICE_PTT(107, IP, IPV6, NOF, IP_IP, IPV6, NOF, SCTP, PAY4),		\
+	ICE_PTT(108, IP, IPV6, NOF, IP_IP, IPV6, NOF, ICMP, PAY4),		\
+										\
+	/* IPv6 --> GRE/NAT */							\
+	ICE_PTT(109, IP, IPV6, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3),		\
+										\
+	/* IPv6 --> GRE/NAT -> IPv4 */						\
+	ICE_PTT(110, IP, IPV6, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3),		\
+	ICE_PTT(111, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3),		\
+	ICE_PTT(112, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(113),						\
+	ICE_PTT(114, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, TCP,  PAY4),		\
+	ICE_PTT(115, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4),		\
+	ICE_PTT(116, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4),		\
+										\
+	/* IPv6 --> GRE/NAT -> IPv6 */						\
+	ICE_PTT(117, IP, IPV6, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3),		\
+	ICE_PTT(118, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3),		\
+	ICE_PTT(119, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(120),						\
+	ICE_PTT(121, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, TCP,  PAY4),		\
+	ICE_PTT(122, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4),		\
+	ICE_PTT(123, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4),		\
+										\
+	/* IPv6 --> GRE/NAT -> MAC */						\
+	ICE_PTT(124, IP, IPV6, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3),	\
+										\
+	/* IPv6 --> GRE/NAT -> MAC -> IPv4 */					\
+	ICE_PTT(125, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3),	\
+	ICE_PTT(126, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3),	\
+	ICE_PTT(127, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP,  PAY4),	\
+	ICE_PTT_UNUSED_ENTRY(128),						\
+	ICE_PTT(129, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP,  PAY4),	\
+	ICE_PTT(130, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4),	\
+	ICE_PTT(131, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4),	\
+										\
+	/* IPv6 --> GRE/NAT -> MAC -> IPv6 */					\
+	ICE_PTT(132, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3),	\
+	ICE_PTT(133, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3),	\
+	ICE_PTT(134, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP,  PAY4),	\
+	ICE_PTT_UNUSED_ENTRY(135),						\
+	ICE_PTT(136, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP,  PAY4),	\
+	ICE_PTT(137, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4),	\
+	ICE_PTT(138, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4),	\
+										\
+	/* IPv6 --> GRE/NAT -> MAC/VLAN */					\
+	ICE_PTT(139, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3),	\
+										\
+	/* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv4 */				\
+	ICE_PTT(140, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3),	\
+	ICE_PTT(141, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3),	\
+	ICE_PTT(142, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP,  PAY4),	\
+	ICE_PTT_UNUSED_ENTRY(143),						\
+	ICE_PTT(144, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP,  PAY4),	\
+	ICE_PTT(145, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4),	\
+	ICE_PTT(146, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4),	\
+										\
+	/* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv6 */				\
+	ICE_PTT(147, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3),	\
+	ICE_PTT(148, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3),	\
+	ICE_PTT(149, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP,  PAY4),	\
+	ICE_PTT_UNUSED_ENTRY(150),						\
+	ICE_PTT(151, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP,  PAY4),	\
+	ICE_PTT(152, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4),	\
+	ICE_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4),
+
+#define ICE_NUM_DEFINED_PTYPES	154
 
 /* macro to make the table lines short, use explicit indexing with [PTYPE] */
 #define ICE_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\
@@ -695,212 +901,10 @@ struct ice_tlan_ctx {
 
 /* Lookup table mapping in the 10-bit HW PTYPE to the bit field for decoding */
 static const struct ice_rx_ptype_decoded ice_ptype_lkup[BIT(10)] = {
-	/* L2 Packet types */
-	ICE_PTT_UNUSED_ENTRY(0),
-	ICE_PTT(1, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
-	ICE_PTT_UNUSED_ENTRY(2),
-	ICE_PTT_UNUSED_ENTRY(3),
-	ICE_PTT_UNUSED_ENTRY(4),
-	ICE_PTT_UNUSED_ENTRY(5),
-	ICE_PTT(6, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),
-	ICE_PTT(7, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),
-	ICE_PTT_UNUSED_ENTRY(8),
-	ICE_PTT_UNUSED_ENTRY(9),
-	ICE_PTT(10, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),
-	ICE_PTT(11, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),
-	ICE_PTT_UNUSED_ENTRY(12),
-	ICE_PTT_UNUSED_ENTRY(13),
-	ICE_PTT_UNUSED_ENTRY(14),
-	ICE_PTT_UNUSED_ENTRY(15),
-	ICE_PTT_UNUSED_ENTRY(16),
-	ICE_PTT_UNUSED_ENTRY(17),
-	ICE_PTT_UNUSED_ENTRY(18),
-	ICE_PTT_UNUSED_ENTRY(19),
-	ICE_PTT_UNUSED_ENTRY(20),
-	ICE_PTT_UNUSED_ENTRY(21),
-
-	/* Non Tunneled IPv4 */
-	ICE_PTT(22, IP, IPV4, FRG, NONE, NONE, NOF, NONE, PAY3),
-	ICE_PTT(23, IP, IPV4, NOF, NONE, NONE, NOF, NONE, PAY3),
-	ICE_PTT(24, IP, IPV4, NOF, NONE, NONE, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(25),
-	ICE_PTT(26, IP, IPV4, NOF, NONE, NONE, NOF, TCP,  PAY4),
-	ICE_PTT(27, IP, IPV4, NOF, NONE, NONE, NOF, SCTP, PAY4),
-	ICE_PTT(28, IP, IPV4, NOF, NONE, NONE, NOF, ICMP, PAY4),
-
-	/* IPv4 --> IPv4 */
-	ICE_PTT(29, IP, IPV4, NOF, IP_IP, IPV4, FRG, NONE, PAY3),
-	ICE_PTT(30, IP, IPV4, NOF, IP_IP, IPV4, NOF, NONE, PAY3),
-	ICE_PTT(31, IP, IPV4, NOF, IP_IP, IPV4, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(32),
-	ICE_PTT(33, IP, IPV4, NOF, IP_IP, IPV4, NOF, TCP,  PAY4),
-	ICE_PTT(34, IP, IPV4, NOF, IP_IP, IPV4, NOF, SCTP, PAY4),
-	ICE_PTT(35, IP, IPV4, NOF, IP_IP, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv4 --> IPv6 */
-	ICE_PTT(36, IP, IPV4, NOF, IP_IP, IPV6, FRG, NONE, PAY3),
-	ICE_PTT(37, IP, IPV4, NOF, IP_IP, IPV6, NOF, NONE, PAY3),
-	ICE_PTT(38, IP, IPV4, NOF, IP_IP, IPV6, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(39),
-	ICE_PTT(40, IP, IPV4, NOF, IP_IP, IPV6, NOF, TCP,  PAY4),
-	ICE_PTT(41, IP, IPV4, NOF, IP_IP, IPV6, NOF, SCTP, PAY4),
-	ICE_PTT(42, IP, IPV4, NOF, IP_IP, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv4 --> GRE/NAT */
-	ICE_PTT(43, IP, IPV4, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3),
-
-	/* IPv4 --> GRE/NAT --> IPv4 */
-	ICE_PTT(44, IP, IPV4, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3),
-	ICE_PTT(45, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3),
-	ICE_PTT(46, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(47),
-	ICE_PTT(48, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, TCP,  PAY4),
-	ICE_PTT(49, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4),
-	ICE_PTT(50, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv4 --> GRE/NAT --> IPv6 */
-	ICE_PTT(51, IP, IPV4, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3),
-	ICE_PTT(52, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3),
-	ICE_PTT(53, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(54),
-	ICE_PTT(55, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, TCP,  PAY4),
-	ICE_PTT(56, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4),
-	ICE_PTT(57, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv4 --> GRE/NAT --> MAC */
-	ICE_PTT(58, IP, IPV4, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3),
-
-	/* IPv4 --> GRE/NAT --> MAC --> IPv4 */
-	ICE_PTT(59, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3),
-	ICE_PTT(60, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3),
-	ICE_PTT(61, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(62),
-	ICE_PTT(63, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP,  PAY4),
-	ICE_PTT(64, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4),
-	ICE_PTT(65, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv4 --> GRE/NAT -> MAC --> IPv6 */
-	ICE_PTT(66, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3),
-	ICE_PTT(67, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3),
-	ICE_PTT(68, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(69),
-	ICE_PTT(70, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP,  PAY4),
-	ICE_PTT(71, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4),
-	ICE_PTT(72, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv4 --> GRE/NAT --> MAC/VLAN */
-	ICE_PTT(73, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3),
-
-	/* IPv4 ---> GRE/NAT -> MAC/VLAN --> IPv4 */
-	ICE_PTT(74, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3),
-	ICE_PTT(75, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3),
-	ICE_PTT(76, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(77),
-	ICE_PTT(78, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP,  PAY4),
-	ICE_PTT(79, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4),
-	ICE_PTT(80, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv4 -> GRE/NAT -> MAC/VLAN --> IPv6 */
-	ICE_PTT(81, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3),
-	ICE_PTT(82, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3),
-	ICE_PTT(83, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(84),
-	ICE_PTT(85, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP,  PAY4),
-	ICE_PTT(86, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4),
-	ICE_PTT(87, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4),
-
-	/* Non Tunneled IPv6 */
-	ICE_PTT(88, IP, IPV6, FRG, NONE, NONE, NOF, NONE, PAY3),
-	ICE_PTT(89, IP, IPV6, NOF, NONE, NONE, NOF, NONE, PAY3),
-	ICE_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(91),
-	ICE_PTT(92, IP, IPV6, NOF, NONE, NONE, NOF, TCP,  PAY4),
-	ICE_PTT(93, IP, IPV6, NOF, NONE, NONE, NOF, SCTP, PAY4),
-	ICE_PTT(94, IP, IPV6, NOF, NONE, NONE, NOF, ICMP, PAY4),
-
-	/* IPv6 --> IPv4 */
-	ICE_PTT(95, IP, IPV6, NOF, IP_IP, IPV4, FRG, NONE, PAY3),
-	ICE_PTT(96, IP, IPV6, NOF, IP_IP, IPV4, NOF, NONE, PAY3),
-	ICE_PTT(97, IP, IPV6, NOF, IP_IP, IPV4, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(98),
-	ICE_PTT(99, IP, IPV6, NOF, IP_IP, IPV4, NOF, TCP,  PAY4),
-	ICE_PTT(100, IP, IPV6, NOF, IP_IP, IPV4, NOF, SCTP, PAY4),
-	ICE_PTT(101, IP, IPV6, NOF, IP_IP, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv6 --> IPv6 */
-	ICE_PTT(102, IP, IPV6, NOF, IP_IP, IPV6, FRG, NONE, PAY3),
-	ICE_PTT(103, IP, IPV6, NOF, IP_IP, IPV6, NOF, NONE, PAY3),
-	ICE_PTT(104, IP, IPV6, NOF, IP_IP, IPV6, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(105),
-	ICE_PTT(106, IP, IPV6, NOF, IP_IP, IPV6, NOF, TCP,  PAY4),
-	ICE_PTT(107, IP, IPV6, NOF, IP_IP, IPV6, NOF, SCTP, PAY4),
-	ICE_PTT(108, IP, IPV6, NOF, IP_IP, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT */
-	ICE_PTT(109, IP, IPV6, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3),
-
-	/* IPv6 --> GRE/NAT -> IPv4 */
-	ICE_PTT(110, IP, IPV6, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3),
-	ICE_PTT(111, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3),
-	ICE_PTT(112, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(113),
-	ICE_PTT(114, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, TCP,  PAY4),
-	ICE_PTT(115, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4),
-	ICE_PTT(116, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT -> IPv6 */
-	ICE_PTT(117, IP, IPV6, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3),
-	ICE_PTT(118, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3),
-	ICE_PTT(119, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(120),
-	ICE_PTT(121, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, TCP,  PAY4),
-	ICE_PTT(122, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4),
-	ICE_PTT(123, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT -> MAC */
-	ICE_PTT(124, IP, IPV6, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3),
-
-	/* IPv6 --> GRE/NAT -> MAC -> IPv4 */
-	ICE_PTT(125, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3),
-	ICE_PTT(126, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3),
-	ICE_PTT(127, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(128),
-	ICE_PTT(129, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP,  PAY4),
-	ICE_PTT(130, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4),
-	ICE_PTT(131, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT -> MAC -> IPv6 */
-	ICE_PTT(132, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3),
-	ICE_PTT(133, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3),
-	ICE_PTT(134, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(135),
-	ICE_PTT(136, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP,  PAY4),
-	ICE_PTT(137, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4),
-	ICE_PTT(138, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT -> MAC/VLAN */
-	ICE_PTT(139, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3),
-
-	/* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv4 */
-	ICE_PTT(140, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3),
-	ICE_PTT(141, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3),
-	ICE_PTT(142, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(143),
-	ICE_PTT(144, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP,  PAY4),
-	ICE_PTT(145, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4),
-	ICE_PTT(146, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv6 */
-	ICE_PTT(147, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3),
-	ICE_PTT(148, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3),
-	ICE_PTT(149, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(150),
-	ICE_PTT(151, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP,  PAY4),
-	ICE_PTT(152, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4),
-	ICE_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4),
+	ICE_PTYPES
 
 	/* unused entries */
-	[154 ... 1023] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 }
+	[ICE_NUM_DEFINED_PTYPES ... 1023] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 }
 };
 
 static inline struct ice_rx_ptype_decoded ice_decode_rx_desc_ptype(u16 ptype)
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
index 13b8a9addfac..09610c5615a8 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
@@ -527,6 +527,79 @@ static int ice_xdp_rx_hw_ts(const struct xdp_md *ctx, u64 *ts_ns)
 	return 0;
 }
 
+/* Define a ptype index -> XDP hash type lookup table.
+ * It uses the same ptype definitions as ice_decode_rx_desc_ptype[],
+ * avoiding possible copy-paste errors.
+ */
+#undef ICE_PTT
+#undef ICE_PTT_UNUSED_ENTRY
+
+#define ICE_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\
+	[PTYPE] = XDP_RSS_L3_##OUTER_IP_VER | XDP_RSS_L4_##I | XDP_RSS_TYPE_##PL
+
+#define ICE_PTT_UNUSED_ENTRY(PTYPE) [PTYPE] = 0
+
+/* A few supplementary definitions for when XDP hash types do not coincide
+ * with what can be generated from ptype definitions
+ * by means of preprocessor concatenation.
+ */
+#define XDP_RSS_L3_NONE		XDP_RSS_TYPE_NONE
+#define XDP_RSS_L4_NONE		XDP_RSS_TYPE_NONE
+#define XDP_RSS_TYPE_PAY2	XDP_RSS_TYPE_L2
+#define XDP_RSS_TYPE_PAY3	XDP_RSS_TYPE_NONE
+#define XDP_RSS_TYPE_PAY4	XDP_RSS_L4
+
+static const enum xdp_rss_hash_type
+ice_ptype_to_xdp_hash[ICE_NUM_DEFINED_PTYPES] = {
+	ICE_PTYPES
+};
+
+#undef XDP_RSS_L3_NONE
+#undef XDP_RSS_L4_NONE
+#undef XDP_RSS_TYPE_PAY2
+#undef XDP_RSS_TYPE_PAY3
+#undef XDP_RSS_TYPE_PAY4
+
+#undef ICE_PTT
+#undef ICE_PTT_UNUSED_ENTRY
+
+/**
+ * ice_xdp_rx_hash_type - Get XDP-specific hash type from the RX descriptor
+ * @eop_desc: End of Packet descriptor
+ */
+static enum xdp_rss_hash_type
+ice_xdp_rx_hash_type(const union ice_32b_rx_flex_desc *eop_desc)
+{
+	u16 ptype = ice_get_ptype(eop_desc);
+
+	if (unlikely(ptype >= ICE_NUM_DEFINED_PTYPES))
+		return 0;
+
+	return ice_ptype_to_xdp_hash[ptype];
+}
+
+/**
+ * ice_xdp_rx_hash - RX hash XDP hint handler
+ * @ctx: XDP buff pointer
+ * @hash: hash destination address
+ * @rss_type: XDP hash type destination address
+ *
+ * Copy RX hash (if available) and its type to the destination address.
+ */
+static int ice_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash,
+			   enum xdp_rss_hash_type *rss_type)
+{
+	const struct ice_xdp_buff *xdp_ext = (void *)ctx;
+
+	*hash = ice_get_rx_hash(xdp_ext->eop_desc);
+	*rss_type = ice_xdp_rx_hash_type(xdp_ext->eop_desc);
+	if (!likely(*hash))
+		return -ENODATA;
+
+	return 0;
+}
+
 const struct xdp_metadata_ops ice_xdp_md_ops = {
 	.xmo_rx_timestamp		= ice_xdp_rx_hw_ts,
+	.xmo_rx_hash			= ice_xdp_rx_hash,
 };
diff --git a/include/net/xdp.h b/include/net/xdp.h
index 5d3673afc037..b7d6fe61381f 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -432,6 +432,7 @@ enum xdp_rss_hash_type {
 	XDP_RSS_L4_UDP		= BIT(5),
 	XDP_RSS_L4_SCTP		= BIT(6),
 	XDP_RSS_L4_IPSEC	= BIT(7), /* L4 based hash include IPSEC SPI */
+	XDP_RSS_L4_ICMP		= BIT(8),
 
 	/* Second part: RSS hash type combinations used for driver HW mapping */
 	XDP_RSS_TYPE_NONE            = 0,
@@ -447,11 +448,13 @@ enum xdp_rss_hash_type {
 	XDP_RSS_TYPE_L4_IPV4_UDP     = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_UDP,
 	XDP_RSS_TYPE_L4_IPV4_SCTP    = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_SCTP,
 	XDP_RSS_TYPE_L4_IPV4_IPSEC   = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_IPSEC,
+	XDP_RSS_TYPE_L4_IPV4_ICMP    = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_ICMP,
 
 	XDP_RSS_TYPE_L4_IPV6_TCP     = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_TCP,
 	XDP_RSS_TYPE_L4_IPV6_UDP     = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_UDP,
 	XDP_RSS_TYPE_L4_IPV6_SCTP    = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_SCTP,
 	XDP_RSS_TYPE_L4_IPV6_IPSEC   = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_IPSEC,
+	XDP_RSS_TYPE_L4_IPV6_ICMP    = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_ICMP,
 
 	XDP_RSS_TYPE_L4_IPV6_TCP_EX  = XDP_RSS_TYPE_L4_IPV6_TCP  | XDP_RSS_L3_DYNHDR,
 	XDP_RSS_TYPE_L4_IPV6_UDP_EX  = XDP_RSS_TYPE_L4_IPV6_UDP  | XDP_RSS_L3_DYNHDR,
-- 
cgit v1.2.3


From b4e352ff1169ebce930c734630f9587b1677d163 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Tue, 5 Dec 2023 22:08:36 +0100
Subject: xsk: add functions to fill control buffer

Commit 94ecc5ca4dbf ("xsk: Add cb area to struct xdp_buff_xsk") has added
a buffer for custom data to xdp_buff_xsk. Particularly, this memory is used
for data, consumed by XDP hints kfuncs. It does not always change on
a per-packet basis and some parts can be set for example, at the same time
as RX queue info.

Add functions to fill all cbs in xsk_buff_pool with the same metadata.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/r/20231205210847.28460-8-larysa.zaremba@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/net/xdp_sock_drv.h  | 17 +++++++++++++++++
 include/net/xsk_buff_pool.h |  2 ++
 net/xdp/xsk_buff_pool.c     | 12 ++++++++++++
 3 files changed, 31 insertions(+)

(limited to 'include')

diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index 81e02de3f453..b62bb8525a5f 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -14,6 +14,12 @@
 
 #ifdef CONFIG_XDP_SOCKETS
 
+struct xsk_cb_desc {
+	void *src;
+	u8 off;
+	u8 bytes;
+};
+
 void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries);
 bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc);
 u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 max);
@@ -47,6 +53,12 @@ static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool,
 	xp_set_rxq_info(pool, rxq);
 }
 
+static inline void xsk_pool_fill_cb(struct xsk_buff_pool *pool,
+				    struct xsk_cb_desc *desc)
+{
+	xp_fill_cb(pool, desc);
+}
+
 static inline unsigned int xsk_pool_get_napi_id(struct xsk_buff_pool *pool)
 {
 #ifdef CONFIG_NET_RX_BUSY_POLL
@@ -274,6 +286,11 @@ static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool,
 {
 }
 
+static inline void xsk_pool_fill_cb(struct xsk_buff_pool *pool,
+				    struct xsk_cb_desc *desc)
+{
+}
+
 static inline unsigned int xsk_pool_get_napi_id(struct xsk_buff_pool *pool)
 {
 	return 0;
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index 8d48d37ab7c0..99dd7376df6a 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -12,6 +12,7 @@
 
 struct xsk_buff_pool;
 struct xdp_rxq_info;
+struct xsk_cb_desc;
 struct xsk_queue;
 struct xdp_desc;
 struct xdp_umem;
@@ -135,6 +136,7 @@ static inline void xp_init_xskb_dma(struct xdp_buff_xsk *xskb, struct xsk_buff_p
 
 /* AF_XDP ZC drivers, via xdp_sock_buff.h */
 void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq);
+void xp_fill_cb(struct xsk_buff_pool *pool, struct xsk_cb_desc *desc);
 int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev,
 	       unsigned long attrs, struct page **pages, u32 nr_pages);
 void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs);
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 4f6f538a5462..28711cc44ced 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -125,6 +125,18 @@ void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq)
 }
 EXPORT_SYMBOL(xp_set_rxq_info);
 
+void xp_fill_cb(struct xsk_buff_pool *pool, struct xsk_cb_desc *desc)
+{
+	u32 i;
+
+	for (i = 0; i < pool->heads_cnt; i++) {
+		struct xdp_buff_xsk *xskb = &pool->heads[i];
+
+		memcpy(xskb->cb + desc->off, desc->src, desc->bytes);
+	}
+}
+EXPORT_SYMBOL(xp_fill_cb);
+
 static void xp_disable_drv_zc(struct xsk_buff_pool *pool)
 {
 	struct netdev_bpf bpf;
-- 
cgit v1.2.3


From e6795330f88b4f643c649a02662d47b779340535 Mon Sep 17 00:00:00 2001
From: Larysa Zaremba <larysa.zaremba@intel.com>
Date: Tue, 5 Dec 2023 22:08:38 +0100
Subject: xdp: Add VLAN tag hint

Implement functionality that enables drivers to expose VLAN tag
to XDP code.

VLAN tag is represented by 2 variables:
- protocol ID, which is passed to bpf code in BE
- VLAN TCI, in host byte order

Acked-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Link: https://lore.kernel.org/r/20231205210847.28460-10-larysa.zaremba@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 Documentation/netlink/specs/netdev.yaml      |  4 ++++
 Documentation/networking/xdp-rx-metadata.rst |  8 ++++++-
 include/net/xdp.h                            |  6 +++++
 include/uapi/linux/netdev.h                  |  3 +++
 net/core/xdp.c                               | 33 ++++++++++++++++++++++++++++
 tools/include/uapi/linux/netdev.h            |  3 +++
 tools/net/ynl/generated/netdev-user.c        |  1 +
 7 files changed, 57 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index eef6358ec587..aeec090e1387 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -54,6 +54,10 @@ definitions:
         name: hash
         doc:
           Device is capable of exposing receive packet hash via bpf_xdp_metadata_rx_hash().
+      -
+        name: vlan-tag
+        doc:
+          Device is capable of exposing receive packet VLAN tag via bpf_xdp_metadata_rx_vlan_tag().
   -
     type: flags
     name: xsk-flags
diff --git a/Documentation/networking/xdp-rx-metadata.rst b/Documentation/networking/xdp-rx-metadata.rst
index e3e9420fd817..a6e0ece18be5 100644
--- a/Documentation/networking/xdp-rx-metadata.rst
+++ b/Documentation/networking/xdp-rx-metadata.rst
@@ -20,7 +20,13 @@ Currently, the following kfuncs are supported. In the future, as more
 metadata is supported, this set will grow:
 
 .. kernel-doc:: net/core/xdp.c
-   :identifiers: bpf_xdp_metadata_rx_timestamp bpf_xdp_metadata_rx_hash
+   :identifiers: bpf_xdp_metadata_rx_timestamp
+
+.. kernel-doc:: net/core/xdp.c
+   :identifiers: bpf_xdp_metadata_rx_hash
+
+.. kernel-doc:: net/core/xdp.c
+   :identifiers: bpf_xdp_metadata_rx_vlan_tag
 
 An XDP program can use these kfuncs to read the metadata into stack
 variables for its own consumption. Or, to pass the metadata on to other
diff --git a/include/net/xdp.h b/include/net/xdp.h
index b7d6fe61381f..8cd04a74dba5 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -404,6 +404,10 @@ void xdp_attachment_setup(struct xdp_attachment_info *info,
 			   NETDEV_XDP_RX_METADATA_HASH, \
 			   bpf_xdp_metadata_rx_hash, \
 			   xmo_rx_hash) \
+	XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_VLAN_TAG, \
+			   NETDEV_XDP_RX_METADATA_VLAN_TAG, \
+			   bpf_xdp_metadata_rx_vlan_tag, \
+			   xmo_rx_vlan_tag) \
 
 enum xdp_rx_metadata {
 #define XDP_METADATA_KFUNC(name, _, __, ___) name,
@@ -465,6 +469,8 @@ struct xdp_metadata_ops {
 	int	(*xmo_rx_timestamp)(const struct xdp_md *ctx, u64 *timestamp);
 	int	(*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash,
 			       enum xdp_rss_hash_type *rss_type);
+	int	(*xmo_rx_vlan_tag)(const struct xdp_md *ctx, __be16 *vlan_proto,
+				   u16 *vlan_tci);
 };
 
 #ifdef CONFIG_NET
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index 6244c0164976..966638b08ccf 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -44,10 +44,13 @@ enum netdev_xdp_act {
  *   timestamp via bpf_xdp_metadata_rx_timestamp().
  * @NETDEV_XDP_RX_METADATA_HASH: Device is capable of exposing receive packet
  *   hash via bpf_xdp_metadata_rx_hash().
+ * @NETDEV_XDP_RX_METADATA_VLAN_TAG: Device is capable of exposing receive
+ *   packet VLAN tag via bpf_xdp_metadata_rx_vlan_tag().
  */
 enum netdev_xdp_rx_metadata {
 	NETDEV_XDP_RX_METADATA_TIMESTAMP = 1,
 	NETDEV_XDP_RX_METADATA_HASH = 2,
+	NETDEV_XDP_RX_METADATA_VLAN_TAG = 4,
 };
 
 /**
diff --git a/net/core/xdp.c b/net/core/xdp.c
index b6f1d6dab3f2..4869c1c2d8f3 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -736,6 +736,39 @@ __bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash,
 	return -EOPNOTSUPP;
 }
 
+/**
+ * bpf_xdp_metadata_rx_vlan_tag - Get XDP packet outermost VLAN tag
+ * @ctx: XDP context pointer.
+ * @vlan_proto: Destination pointer for VLAN Tag protocol identifier (TPID).
+ * @vlan_tci: Destination pointer for VLAN TCI (VID + DEI + PCP)
+ *
+ * In case of success, ``vlan_proto`` contains *Tag protocol identifier (TPID)*,
+ * usually ``ETH_P_8021Q`` or ``ETH_P_8021AD``, but some networks can use
+ * custom TPIDs. ``vlan_proto`` is stored in **network byte order (BE)**
+ * and should be used as follows:
+ * ``if (vlan_proto == bpf_htons(ETH_P_8021Q)) do_something();``
+ *
+ * ``vlan_tci`` contains the remaining 16 bits of a VLAN tag.
+ * Driver is expected to provide those in **host byte order (usually LE)**,
+ * so the bpf program should not perform byte conversion.
+ * According to 802.1Q standard, *VLAN TCI (Tag control information)*
+ * is a bit field that contains:
+ * *VLAN identifier (VID)* that can be read with ``vlan_tci & 0xfff``,
+ * *Drop eligible indicator (DEI)* - 1 bit,
+ * *Priority code point (PCP)* - 3 bits.
+ * For detailed meaning of DEI and PCP, please refer to other sources.
+ *
+ * Return:
+ * * Returns 0 on success or ``-errno`` on error.
+ * * ``-EOPNOTSUPP`` : device driver doesn't implement kfunc
+ * * ``-ENODATA``    : VLAN tag was not stripped or is not available
+ */
+__bpf_kfunc int bpf_xdp_metadata_rx_vlan_tag(const struct xdp_md *ctx,
+					     __be16 *vlan_proto, u16 *vlan_tci)
+{
+	return -EOPNOTSUPP;
+}
+
 __bpf_kfunc_end_defs();
 
 BTF_SET8_START(xdp_metadata_kfunc_ids)
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index 6244c0164976..966638b08ccf 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -44,10 +44,13 @@ enum netdev_xdp_act {
  *   timestamp via bpf_xdp_metadata_rx_timestamp().
  * @NETDEV_XDP_RX_METADATA_HASH: Device is capable of exposing receive packet
  *   hash via bpf_xdp_metadata_rx_hash().
+ * @NETDEV_XDP_RX_METADATA_VLAN_TAG: Device is capable of exposing receive
+ *   packet VLAN tag via bpf_xdp_metadata_rx_vlan_tag().
  */
 enum netdev_xdp_rx_metadata {
 	NETDEV_XDP_RX_METADATA_TIMESTAMP = 1,
 	NETDEV_XDP_RX_METADATA_HASH = 2,
+	NETDEV_XDP_RX_METADATA_VLAN_TAG = 4,
 };
 
 /**
diff --git a/tools/net/ynl/generated/netdev-user.c b/tools/net/ynl/generated/netdev-user.c
index 3b9dee94d4ce..e3fe748086bd 100644
--- a/tools/net/ynl/generated/netdev-user.c
+++ b/tools/net/ynl/generated/netdev-user.c
@@ -53,6 +53,7 @@ const char *netdev_xdp_act_str(enum netdev_xdp_act value)
 static const char * const netdev_xdp_rx_metadata_strmap[] = {
 	[0] = "timestamp",
 	[1] = "hash",
+	[2] = "vlan-tag",
 };
 
 const char *netdev_xdp_rx_metadata_str(enum netdev_xdp_rx_metadata value)
-- 
cgit v1.2.3


From 537fec0733c4a72e2a2b69fee365459c5b75d92e Mon Sep 17 00:00:00 2001
From: Larysa Zaremba <larysa.zaremba@intel.com>
Date: Tue, 5 Dec 2023 22:08:42 +0100
Subject: net: make vlan_get_tag() return -ENODATA instead of -EINVAL

__vlan_hwaccel_get_tag() is used in veth XDP hints implementation,
its return value (-EINVAL if skb is not VLAN tagged) is passed to bpf code,
but XDP hints specification requires drivers to return -ENODATA, if a hint
cannot be provided for a particular packet.

Solve this inconsistency by changing error return value of
__vlan_hwaccel_get_tag() from -EINVAL to -ENODATA, do the same thing to
__vlan_get_tag(), because this function is supposed to follow the same
convention. This, in turn, makes -ENODATA the only non-zero value
vlan_get_tag() can return. We can do this with no side effects, because
none of the users of the 3 above-mentioned functions rely on the exact
value.

Suggested-by: Jesper Dangaard Brouer <jbrouer@redhat.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Link: https://lore.kernel.org/r/20231205210847.28460-14-larysa.zaremba@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/if_vlan.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 3028af87716e..c1645c86eed9 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -540,7 +540,7 @@ static inline int __vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci)
 	struct vlan_ethhdr *veth = skb_vlan_eth_hdr(skb);
 
 	if (!eth_type_vlan(veth->h_vlan_proto))
-		return -EINVAL;
+		return -ENODATA;
 
 	*vlan_tci = ntohs(veth->h_vlan_TCI);
 	return 0;
@@ -561,7 +561,7 @@ static inline int __vlan_hwaccel_get_tag(const struct sk_buff *skb,
 		return 0;
 	} else {
 		*vlan_tci = 0;
-		return -EINVAL;
+		return -ENODATA;
 	}
 }
 
-- 
cgit v1.2.3


From 7978bad4b6b9265a1e808a5f679ee428d1dd6523 Mon Sep 17 00:00:00 2001
From: Larysa Zaremba <larysa.zaremba@intel.com>
Date: Tue, 5 Dec 2023 22:08:43 +0100
Subject: mlx5: implement VLAN tag XDP hint

Implement the newly added .xmo_rx_vlan_tag() hint function.

Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Link: https://lore.kernel.org/r/20231205210847.28460-15-larysa.zaremba@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c | 15 +++++++++++++++
 include/linux/mlx5/device.h                      |  2 +-
 2 files changed, 16 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index e2e7d82cfca4..9e695ed122ee 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -256,9 +256,24 @@ static int mlx5e_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash,
 	return 0;
 }
 
+static int mlx5e_xdp_rx_vlan_tag(const struct xdp_md *ctx, __be16 *vlan_proto,
+				 u16 *vlan_tci)
+{
+	const struct mlx5e_xdp_buff *_ctx = (void *)ctx;
+	const struct mlx5_cqe64 *cqe = _ctx->cqe;
+
+	if (!cqe_has_vlan(cqe))
+		return -ENODATA;
+
+	*vlan_proto = htons(ETH_P_8021Q);
+	*vlan_tci = be16_to_cpu(cqe->vlan_info);
+	return 0;
+}
+
 const struct xdp_metadata_ops mlx5e_xdp_metadata_ops = {
 	.xmo_rx_timestamp		= mlx5e_xdp_rx_timestamp,
 	.xmo_rx_hash			= mlx5e_xdp_rx_hash,
+	.xmo_rx_vlan_tag		= mlx5e_xdp_rx_vlan_tag,
 };
 
 struct mlx5e_xsk_tx_complete {
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 820bca965fb6..01275c6e8468 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -918,7 +918,7 @@ static inline u8 get_cqe_tls_offload(struct mlx5_cqe64 *cqe)
 	return (cqe->tls_outer_l3_tunneled >> 3) & 0x3;
 }
 
-static inline bool cqe_has_vlan(struct mlx5_cqe64 *cqe)
+static inline bool cqe_has_vlan(const struct mlx5_cqe64 *cqe)
 {
 	return cqe->l4_l3_hdr_type & 0x1;
 }
-- 
cgit v1.2.3


From 8d6650646ce49e9a5b8c5c23eb94f74b1749f70f Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Fri, 1 Dec 2023 10:01:38 -0800
Subject: bpf: syzkaller found null ptr deref in unix_bpf proto add

I added logic to track the sock pair for stream_unix sockets so that we
ensure lifetime of the sock matches the time a sockmap could reference
the sock (see fixes tag). I forgot though that we allow af_unix unconnected
sockets into a sock{map|hash} map.

This is problematic because previous fixed expected sk_pair() to exist
and did not NULL check it. Because unconnected sockets have a NULL
sk_pair this resulted in the NULL ptr dereference found by syzkaller.

BUG: KASAN: null-ptr-deref in unix_stream_bpf_update_proto+0x72/0x430 net/unix/unix_bpf.c:171
Write of size 4 at addr 0000000000000080 by task syz-executor360/5073
Call Trace:
 <TASK>
 ...
 sock_hold include/net/sock.h:777 [inline]
 unix_stream_bpf_update_proto+0x72/0x430 net/unix/unix_bpf.c:171
 sock_map_init_proto net/core/sock_map.c:190 [inline]
 sock_map_link+0xb87/0x1100 net/core/sock_map.c:294
 sock_map_update_common+0xf6/0x870 net/core/sock_map.c:483
 sock_map_update_elem_sys+0x5b6/0x640 net/core/sock_map.c:577
 bpf_map_update_value+0x3af/0x820 kernel/bpf/syscall.c:167

We considered just checking for the null ptr and skipping taking a ref
on the NULL peer sock. But, if the socket is then connected() after
being added to the sockmap we can cause the original issue again. So
instead this patch blocks adding af_unix sockets that are not in the
ESTABLISHED state.

Reported-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot+e8030702aefd3444fb9e@syzkaller.appspotmail.com
Fixes: 8866730aed51 ("bpf, sockmap: af_unix stream sockets need to hold ref for pair sock")
Acked-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/r/20231201180139.328529-2-john.fastabend@gmail.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 include/net/sock.h  | 5 +++++
 net/core/sock_map.c | 2 ++
 2 files changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/net/sock.h b/include/net/sock.h
index 1d6931caf0c3..0201136b0b9c 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2799,6 +2799,11 @@ static inline bool sk_is_tcp(const struct sock *sk)
 	return sk->sk_type == SOCK_STREAM && sk->sk_protocol == IPPROTO_TCP;
 }
 
+static inline bool sk_is_stream_unix(const struct sock *sk)
+{
+	return sk->sk_family == AF_UNIX && sk->sk_type == SOCK_STREAM;
+}
+
 /**
  * sk_eat_skb - Release a skb if it is no longer needed
  * @sk: socket to eat this skb from
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 4292c2ed1828..27d733c0f65e 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -536,6 +536,8 @@ static bool sock_map_sk_state_allowed(const struct sock *sk)
 {
 	if (sk_is_tcp(sk))
 		return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_LISTEN);
+	if (sk_is_stream_unix(sk))
+		return (1 << sk->sk_state) & TCPF_ESTABLISHED;
 	return true;
 }
 
-- 
cgit v1.2.3


From 1dd7f18fc0ed75dad4d5f2ecc84f69c6b62b6a81 Mon Sep 17 00:00:00 2001
From: Pedro Tammela <pctammela@mojatatu.com>
Date: Mon, 11 Dec 2023 15:18:07 -0300
Subject: net/sched: act_api: skip idr replace on bound actions

tcf_idr_insert_many will replace the allocated -EBUSY pointer in
tcf_idr_check_alloc with the real action pointer, exposing it
to all operations. This operation is only needed when the action pointer
is created (ACT_P_CREATED). For actions which are bound to (returned 0),
the pointer already resides in the idr making such operation a nop.

Even though it's a nop, it's still not a cheap operation as internally
the idr code walks the idr and then does a replace on the appropriate slot.
So if the action was bound, better skip the idr replace entirely.

Signed-off-by: Pedro Tammela <pctammela@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Reviewed-by: Vlad Buslov <vladbu@nvidia.com>
Link: https://lore.kernel.org/r/20231211181807.96028-3-pctammela@mojatatu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/act_api.h |  2 +-
 net/sched/act_api.c   | 11 ++++++-----
 net/sched/cls_api.c   |  2 +-
 3 files changed, 8 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/act_api.h b/include/net/act_api.h
index 4ae0580b63ca..ea13e1e4a7c2 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -191,7 +191,7 @@ int tcf_idr_create_from_flags(struct tc_action_net *tn, u32 index,
 			      struct nlattr *est, struct tc_action **a,
 			      const struct tc_action_ops *ops, int bind,
 			      u32 flags);
-void tcf_idr_insert_many(struct tc_action *actions[]);
+void tcf_idr_insert_many(struct tc_action *actions[], int init_res[]);
 void tcf_idr_cleanup(struct tc_action_net *tn, u32 index);
 int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index,
 			struct tc_action **a, int bind);
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 076d5cdde656..3a7770eff52d 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -1304,7 +1304,7 @@ static const struct nla_policy tcf_action_policy[TCA_ACT_MAX + 1] = {
 	[TCA_ACT_HW_STATS]	= NLA_POLICY_BITFIELD32(TCA_ACT_HW_STATS_ANY),
 };
 
-void tcf_idr_insert_many(struct tc_action *actions[])
+void tcf_idr_insert_many(struct tc_action *actions[], int init_res[])
 {
 	struct tc_action *a;
 	int i;
@@ -1312,11 +1312,12 @@ void tcf_idr_insert_many(struct tc_action *actions[])
 	tcf_act_for_each_action(i, a, actions) {
 		struct tcf_idrinfo *idrinfo;
 
+		if (init_res[i] == 0) /* Bound */
+			continue;
+
 		idrinfo = a->idrinfo;
 		mutex_lock(&idrinfo->lock);
-		/* Replace ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc if
-		 * it is just created, otherwise this is just a nop.
-		 */
+		/* Replace ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc */
 		idr_replace(&idrinfo->action_idr, a, a->tcfa_index);
 		mutex_unlock(&idrinfo->lock);
 	}
@@ -1516,7 +1517,7 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
 	/* We have to commit them all together, because if any error happened in
 	 * between, we could not handle the failure gracefully.
 	 */
-	tcf_idr_insert_many(actions);
+	tcf_idr_insert_many(actions, init_res);
 
 	*attr_size = tcf_action_full_attrs_size(sz);
 	err = i - 1;
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 437daebc1fc4..dc1c19a25882 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -3313,7 +3313,7 @@ int tcf_exts_validate_ex(struct net *net, struct tcf_proto *tp, struct nlattr **
 			act->type = exts->type = TCA_OLD_COMPAT;
 			exts->actions[0] = act;
 			exts->nr_actions = 1;
-			tcf_idr_insert_many(exts->actions);
+			tcf_idr_insert_many(exts->actions, init_res);
 		} else if (exts->action && tb[exts->action]) {
 			int err;
 
-- 
cgit v1.2.3


From 0c476157085fe2ad13b9bec70ea672e86647fa1a Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Tue, 12 Dec 2023 06:41:43 +0100
Subject: net: phy: c45: add genphy_c45_pma_read_ext_abilities() function

Move part of the genphy_c45_pma_read_abilities() code to a separate
function.

Some PHYs do not implement PMA/PMD status 2 register (Register 1.8) but
do implement PMA/PMD extended ability register (Register 1.11). To make
use of it, we need to be able to access this part of code separately.

Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://lore.kernel.org/r/20231212054144.87527-2-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phy-c45.c | 129 ++++++++++++++++++++++++++--------------------
 include/linux/phy.h       |   1 +
 2 files changed, 75 insertions(+), 55 deletions(-)

(limited to 'include')

diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c
index 8e6fd4962c48..747d14bf152c 100644
--- a/drivers/net/phy/phy-c45.c
+++ b/drivers/net/phy/phy-c45.c
@@ -919,6 +919,79 @@ int genphy_c45_pma_baset1_read_abilities(struct phy_device *phydev)
 }
 EXPORT_SYMBOL_GPL(genphy_c45_pma_baset1_read_abilities);
 
+/**
+ * genphy_c45_pma_read_ext_abilities - read supported link modes from PMA
+ * @phydev: target phy_device struct
+ *
+ * Read the supported link modes from the PMA/PMD extended ability register
+ * (Register 1.11).
+ */
+int genphy_c45_pma_read_ext_abilities(struct phy_device *phydev)
+{
+	int val;
+
+	val = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_EXTABLE);
+	if (val < 0)
+		return val;
+
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseLRM_Full_BIT,
+			 phydev->supported,
+			 val & MDIO_PMA_EXTABLE_10GBLRM);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT,
+			 phydev->supported,
+			 val & MDIO_PMA_EXTABLE_10GBT);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT,
+			 phydev->supported,
+			 val & MDIO_PMA_EXTABLE_10GBKX4);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseKR_Full_BIT,
+			 phydev->supported,
+			 val & MDIO_PMA_EXTABLE_10GBKR);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+			 phydev->supported,
+			 val & MDIO_PMA_EXTABLE_1000BT);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseKX_Full_BIT,
+			 phydev->supported,
+			 val & MDIO_PMA_EXTABLE_1000BKX);
+
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT,
+			 phydev->supported,
+			 val & MDIO_PMA_EXTABLE_100BTX);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT,
+			 phydev->supported,
+			 val & MDIO_PMA_EXTABLE_100BTX);
+
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT,
+			 phydev->supported,
+			 val & MDIO_PMA_EXTABLE_10BT);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT,
+			 phydev->supported,
+			 val & MDIO_PMA_EXTABLE_10BT);
+
+	if (val & MDIO_PMA_EXTABLE_NBT) {
+		val = phy_read_mmd(phydev, MDIO_MMD_PMAPMD,
+				   MDIO_PMA_NG_EXTABLE);
+		if (val < 0)
+			return val;
+
+		linkmode_mod_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT,
+				 phydev->supported,
+				 val & MDIO_PMA_NG_EXTABLE_2_5GBT);
+
+		linkmode_mod_bit(ETHTOOL_LINK_MODE_5000baseT_Full_BIT,
+				 phydev->supported,
+				 val & MDIO_PMA_NG_EXTABLE_5GBT);
+	}
+
+	if (val & MDIO_PMA_EXTABLE_BT1) {
+		val = genphy_c45_pma_baset1_read_abilities(phydev);
+		if (val < 0)
+			return val;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(genphy_c45_pma_read_ext_abilities);
+
 /**
  * genphy_c45_pma_read_abilities - read supported link modes from PMA
  * @phydev: target phy_device struct
@@ -962,63 +1035,9 @@ int genphy_c45_pma_read_abilities(struct phy_device *phydev)
 			 val & MDIO_PMA_STAT2_10GBER);
 
 	if (val & MDIO_PMA_STAT2_EXTABLE) {
-		val = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_EXTABLE);
+		val = genphy_c45_pma_read_ext_abilities(phydev);
 		if (val < 0)
 			return val;
-
-		linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseLRM_Full_BIT,
-				 phydev->supported,
-				 val & MDIO_PMA_EXTABLE_10GBLRM);
-		linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT,
-				 phydev->supported,
-				 val & MDIO_PMA_EXTABLE_10GBT);
-		linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT,
-				 phydev->supported,
-				 val & MDIO_PMA_EXTABLE_10GBKX4);
-		linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseKR_Full_BIT,
-				 phydev->supported,
-				 val & MDIO_PMA_EXTABLE_10GBKR);
-		linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
-				 phydev->supported,
-				 val & MDIO_PMA_EXTABLE_1000BT);
-		linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseKX_Full_BIT,
-				 phydev->supported,
-				 val & MDIO_PMA_EXTABLE_1000BKX);
-
-		linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT,
-				 phydev->supported,
-				 val & MDIO_PMA_EXTABLE_100BTX);
-		linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT,
-				 phydev->supported,
-				 val & MDIO_PMA_EXTABLE_100BTX);
-
-		linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT,
-				 phydev->supported,
-				 val & MDIO_PMA_EXTABLE_10BT);
-		linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT,
-				 phydev->supported,
-				 val & MDIO_PMA_EXTABLE_10BT);
-
-		if (val & MDIO_PMA_EXTABLE_NBT) {
-			val = phy_read_mmd(phydev, MDIO_MMD_PMAPMD,
-					   MDIO_PMA_NG_EXTABLE);
-			if (val < 0)
-				return val;
-
-			linkmode_mod_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT,
-					 phydev->supported,
-					 val & MDIO_PMA_NG_EXTABLE_2_5GBT);
-
-			linkmode_mod_bit(ETHTOOL_LINK_MODE_5000baseT_Full_BIT,
-					 phydev->supported,
-					 val & MDIO_PMA_NG_EXTABLE_5GBT);
-		}
-
-		if (val & MDIO_PMA_EXTABLE_BT1) {
-			val = genphy_c45_pma_baset1_read_abilities(phydev);
-			if (val < 0)
-				return val;
-		}
 	}
 
 	/* This is optional functionality. If not supported, we may get an error
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 6e7ebcc50b85..dbb5e13e3e1b 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1866,6 +1866,7 @@ int genphy_c45_an_config_aneg(struct phy_device *phydev);
 int genphy_c45_an_disable_aneg(struct phy_device *phydev);
 int genphy_c45_read_mdix(struct phy_device *phydev);
 int genphy_c45_pma_read_abilities(struct phy_device *phydev);
+int genphy_c45_pma_read_ext_abilities(struct phy_device *phydev);
 int genphy_c45_pma_baset1_read_abilities(struct phy_device *phydev);
 int genphy_c45_read_eee_abilities(struct phy_device *phydev);
 int genphy_c45_pma_baset1_read_master_slave(struct phy_device *phydev);
-- 
cgit v1.2.3


From 13049408a4bd29c92227ca2d6befab80dbb96663 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@nvidia.com>
Date: Sun, 7 May 2023 16:47:42 +0300
Subject: net/mlx5: Add mlx5_ifc bits used for supporting single netdev
 Socket-Direct

Multiple device caps and features are required to support
single netdev Socket-Direct.
Add them here in preparation for the feature implementation.

Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Gal Pressman <gal@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 include/linux/mlx5/mlx5_ifc.h | 31 +++++++++++++++++++++++++------
 1 file changed, 25 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index ce2e71cd6d2a..405d141b4a08 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -435,7 +435,7 @@ struct mlx5_ifc_flow_table_prop_layout_bits {
 	u8         flow_table_modify[0x1];
 	u8         reformat[0x1];
 	u8         decap[0x1];
-	u8         reserved_at_9[0x1];
+	u8         reset_root_to_default[0x1];
 	u8         pop_vlan[0x1];
 	u8         push_vlan[0x1];
 	u8         reserved_at_c[0x1];
@@ -1801,7 +1801,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         disable_local_lb_uc[0x1];
 	u8         disable_local_lb_mc[0x1];
 	u8         log_min_hairpin_wq_data_sz[0x5];
-	u8         reserved_at_3e8[0x2];
+	u8         reserved_at_3e8[0x1];
+	u8         silent_mode[0x1];
 	u8         vhca_state[0x1];
 	u8         log_max_vlan_list[0x5];
 	u8         reserved_at_3f0[0x3];
@@ -1818,7 +1819,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 
 	u8         reserved_at_460[0x1];
 	u8         ats[0x1];
-	u8         reserved_at_462[0x1];
+	u8         cross_vhca_rqt[0x1];
 	u8         log_max_uctx[0x5];
 	u8         reserved_at_468[0x1];
 	u8         crypto[0x1];
@@ -1943,6 +1944,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 
 enum {
 	MLX5_CROSS_VHCA_OBJ_TO_OBJ_SUPPORTED_LOCAL_FLOW_TABLE_TO_REMOTE_FLOW_TABLE_MISS  = 0x80000,
+	MLX5_CROSS_VHCA_OBJ_TO_OBJ_SUPPORTED_LOCAL_FLOW_TABLE_ROOT_TO_REMOTE_FLOW_TABLE  = (1ULL << 20),
 };
 
 enum {
@@ -1992,7 +1994,11 @@ struct mlx5_ifc_cmd_hca_cap_2_bits {
 	u8	   reserved_at_260[0x120];
 	u8	   reserved_at_380[0x10];
 	u8	   ec_vf_vport_base[0x10];
-	u8	   reserved_at_3a0[0x460];
+
+	u8	   reserved_at_3a0[0x10];
+	u8	   max_rqt_vhca_id[0x10];
+
+	u8	   reserved_at_3c0[0x440];
 };
 
 enum mlx5_ifc_flow_destination_type {
@@ -2151,6 +2157,13 @@ struct mlx5_ifc_rq_num_bits {
 	u8         rq_num[0x18];
 };
 
+struct mlx5_ifc_rq_vhca_bits {
+	u8         reserved_at_0[0x8];
+	u8         rq_num[0x18];
+	u8         reserved_at_20[0x10];
+	u8         rq_vhca_id[0x10];
+};
+
 struct mlx5_ifc_mac_address_layout_bits {
 	u8         reserved_at_0[0x10];
 	u8         mac_addr_47_32[0x10];
@@ -3901,7 +3914,10 @@ struct mlx5_ifc_rqtc_bits {
 
 	u8    reserved_at_e0[0x6a0];
 
-	struct mlx5_ifc_rq_num_bits rq_num[];
+	union {
+		DECLARE_FLEX_ARRAY(struct mlx5_ifc_rq_num_bits, rq_num);
+		DECLARE_FLEX_ARRAY(struct mlx5_ifc_rq_vhca_bits, rq_vhca);
+	};
 };
 
 enum {
@@ -4744,7 +4760,10 @@ struct mlx5_ifc_set_l2_table_entry_in_bits {
 
 	u8         reserved_at_c0[0x20];
 
-	u8         reserved_at_e0[0x13];
+	u8         reserved_at_e0[0x10];
+	u8         silent_mode_valid[0x1];
+	u8         silent_mode[0x1];
+	u8         reserved_at_f2[0x1];
 	u8         vlan_valid[0x1];
 	u8         vlan[0xc];
 
-- 
cgit v1.2.3


From f5e956329960903d908668d7a20bbc08e0a8b92b Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@nvidia.com>
Date: Mon, 7 Aug 2023 09:05:34 +0300
Subject: net/mlx5: Expose Management PCIe Index Register (MPIR)

MPIR register allows to query the PCIe indexes
and Socket-Direct related parameters.

Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Gal Pressman <gal@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h |  1 +
 drivers/net/ethernet/mellanox/mlx5/core/port.c      | 10 ++++++++++
 include/linux/mlx5/driver.h                         |  1 +
 include/linux/mlx5/mlx5_ifc.h                       | 14 ++++++++++++++
 4 files changed, 26 insertions(+)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 6b14e347d914..a79b7959361b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -243,6 +243,7 @@ int mlx5_query_mcam_reg(struct mlx5_core_dev *dev, u32 *mcap, u8 feature_group,
 			u8 access_reg_group);
 int mlx5_query_qcam_reg(struct mlx5_core_dev *mdev, u32 *qcam,
 			u8 feature_group, u8 access_reg_group);
+int mlx5_query_mpir_reg(struct mlx5_core_dev *dev, u32 *mpir);
 
 void mlx5_lag_add_netdev(struct mlx5_core_dev *dev, struct net_device *netdev);
 void mlx5_lag_remove_netdev(struct mlx5_core_dev *dev, struct net_device *netdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index 7d8c732818f2..7fba1c46e2ac 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -1206,3 +1206,13 @@ int mlx5_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
 	*speed = max_speed;
 	return 0;
 }
+
+int mlx5_query_mpir_reg(struct mlx5_core_dev *dev, u32 *mpir)
+{
+	u32 in[MLX5_ST_SZ_DW(mpir_reg)] = {};
+	int sz = MLX5_ST_SZ_BYTES(mpir_reg);
+
+	MLX5_SET(mpir_reg, in, local_port, 1);
+
+	return mlx5_core_access_reg(dev, in, sz, mpir, sz, MLX5_REG_MPIR, 0, 0);
+}
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index d2b8d4a74a30..2f67cec1a898 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -150,6 +150,7 @@ enum {
 	MLX5_REG_MTPPSE		 = 0x9054,
 	MLX5_REG_MTUTC		 = 0x9055,
 	MLX5_REG_MPEGC		 = 0x9056,
+	MLX5_REG_MPIR		 = 0x9059,
 	MLX5_REG_MCQS		 = 0x9060,
 	MLX5_REG_MCQI		 = 0x9061,
 	MLX5_REG_MCC		 = 0x9062,
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 405d141b4a08..828938368fb7 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -10108,6 +10108,20 @@ struct mlx5_ifc_mpegc_reg_bits {
 	u8         reserved_at_60[0x100];
 };
 
+struct mlx5_ifc_mpir_reg_bits {
+	u8         sdm[0x1];
+	u8         reserved_at_1[0x1b];
+	u8         host_buses[0x4];
+
+	u8         reserved_at_20[0x20];
+
+	u8         local_port[0x8];
+	u8         reserved_at_28[0x15];
+	u8         sd_group[0x3];
+
+	u8         reserved_at_60[0x20];
+};
+
 enum {
 	MLX5_MTUTC_FREQ_ADJ_UNITS_PPB          = 0x0,
 	MLX5_MTUTC_FREQ_ADJ_UNITS_SCALED_PPM   = 0x1,
-- 
cgit v1.2.3


From b25bd37c859f32e50a436ab9d2078b76e433008e Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@nvidia.com>
Date: Sun, 6 Aug 2023 14:01:10 +0300
Subject: net/mlx5: Move TISes from priv to mdev HW resources

The transport interface send (TIS) object is responsible for performing
all transport related operations of the transmit side. Messages from
Send Queues get segmented and transmitted by the TIS including all
transport required implications, e.g. in the case of large send offload,
the TIS is responsible for the segmentation.

These are stateless objects and can be used by multiple netdevs (e.g.
representors) who share the same core device.

Providing the TISes as a service from the core layer to the netdev layer
reduces the number of replecated TIS objects (in case of multiple
netdevs), and will ease the transition to netdev with multiple mdevs.

Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Gal Pressman <gal@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |  19 ++--
 drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c   |   6 +-
 drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h   |   2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en/qos.c   |   7 +-
 .../net/ethernet/mellanox/mlx5/core/en_common.c    |  74 +++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  | 102 ++++-----------------
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c   |  10 +-
 .../net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c  |  19 +++-
 .../net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h  |   2 +
 .../ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c |   7 +-
 include/linux/mlx5/driver.h                        |   2 +
 11 files changed, 140 insertions(+), 110 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 43f027bf2da3..6808e0d82944 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -72,7 +72,6 @@ struct page_pool;
 #define MLX5E_HW2SW_MTU(params, hwmtu) ((hwmtu) - ((params)->hard_mtu))
 #define MLX5E_SW2HW_MTU(params, swmtu) ((swmtu) + ((params)->hard_mtu))
 
-#define MLX5E_MAX_NUM_TC	8
 #define MLX5E_MAX_NUM_MQPRIO_CH_TC TC_QOPT_MAX_QUEUE
 
 #define MLX5_RX_HEADROOM NET_SKB_PAD
@@ -758,7 +757,7 @@ struct mlx5e_channel {
 	/* data path */
 	struct mlx5e_rq            rq;
 	struct mlx5e_xdpsq         rq_xdpsq;
-	struct mlx5e_txqsq         sq[MLX5E_MAX_NUM_TC];
+	struct mlx5e_txqsq         sq[MLX5_MAX_NUM_TC];
 	struct mlx5e_icosq         icosq;   /* internal control operations */
 	struct mlx5e_txqsq __rcu * __rcu *qos_sqs;
 	bool                       xdp;
@@ -808,7 +807,7 @@ struct mlx5e_channels {
 
 struct mlx5e_channel_stats {
 	struct mlx5e_ch_stats ch;
-	struct mlx5e_sq_stats sq[MLX5E_MAX_NUM_TC];
+	struct mlx5e_sq_stats sq[MLX5_MAX_NUM_TC];
 	struct mlx5e_rq_stats rq;
 	struct mlx5e_rq_stats xskrq;
 	struct mlx5e_xdpsq_stats rq_xdpsq;
@@ -818,8 +817,8 @@ struct mlx5e_channel_stats {
 
 struct mlx5e_ptp_stats {
 	struct mlx5e_ch_stats ch;
-	struct mlx5e_sq_stats sq[MLX5E_MAX_NUM_TC];
-	struct mlx5e_ptp_cq_stats cq[MLX5E_MAX_NUM_TC];
+	struct mlx5e_sq_stats sq[MLX5_MAX_NUM_TC];
+	struct mlx5e_ptp_cq_stats cq[MLX5_MAX_NUM_TC];
 	struct mlx5e_rq_stats rq;
 } ____cacheline_aligned_in_smp;
 
@@ -886,7 +885,6 @@ struct mlx5e_priv {
 	struct mlx5e_rq            drop_rq;
 
 	struct mlx5e_channels      channels;
-	u32                        tisn[MLX5_MAX_PORTS][MLX5E_MAX_NUM_TC];
 	struct mlx5e_rx_res       *rx_res;
 	u32                       *tx_rates;
 
@@ -984,6 +982,8 @@ struct mlx5e_profile {
 	void	(*update_stats)(struct mlx5e_priv *priv);
 	void	(*update_carrier)(struct mlx5e_priv *priv);
 	int	(*max_nch_limit)(struct mlx5_core_dev *mdev);
+	u32	(*get_tisn)(struct mlx5_core_dev *mdev, struct mlx5e_priv *priv,
+			    u8 lag_port, u8 tc);
 	unsigned int (*stats_grps_num)(struct mlx5e_priv *priv);
 	mlx5e_stats_grp_t *stats_grps;
 	const struct mlx5e_rx_handlers *rx_handlers;
@@ -991,6 +991,11 @@ struct mlx5e_profile {
 	u32     features;
 };
 
+u32 mlx5e_profile_get_tisn(struct mlx5_core_dev *mdev,
+			   struct mlx5e_priv *priv,
+			   const struct mlx5e_profile *profile,
+			   u8 lag_port, u8 tc);
+
 #define mlx5e_profile_feature_cap(profile, feature)	\
 	((profile)->features & BIT(MLX5E_PROFILE_FEATURE_##feature))
 
@@ -1132,8 +1137,6 @@ void mlx5e_close_drop_rq(struct mlx5e_rq *drop_rq);
 int mlx5e_create_tis(struct mlx5_core_dev *mdev, void *in, u32 *tisn);
 void mlx5e_destroy_tis(struct mlx5_core_dev *mdev, u32 tisn);
 
-int mlx5e_create_tises(struct mlx5e_priv *priv);
-void mlx5e_destroy_tises(struct mlx5e_priv *priv);
 int mlx5e_update_nic_rx(struct mlx5e_priv *priv);
 void mlx5e_update_carrier(struct mlx5e_priv *priv);
 int mlx5e_close(struct net_device *netdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
index af3928eddafd..04cec76c1ac4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
@@ -518,9 +518,11 @@ static int mlx5e_ptp_open_txqsqs(struct mlx5e_ptp *c,
 
 	for (tc = 0; tc < num_tc; tc++) {
 		int txq_ix = ix_base + tc;
+		u32 tisn;
 
-		err = mlx5e_ptp_open_txqsq(c, c->priv->tisn[c->lag_port][tc], txq_ix,
-					   cparams, tc, &c->ptpsq[tc]);
+		tisn = mlx5e_profile_get_tisn(c->mdev, c->priv, c->priv->profile,
+					      c->lag_port, tc);
+		err = mlx5e_ptp_open_txqsq(c, tisn, txq_ix, cparams, tc, &c->ptpsq[tc]);
 		if (err)
 			goto close_txqsq;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
index 7b700d0f956a..86f1854698b4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
@@ -49,7 +49,7 @@ enum {
 
 struct mlx5e_ptp {
 	/* data path */
-	struct mlx5e_ptpsq         ptpsq[MLX5E_MAX_NUM_TC];
+	struct mlx5e_ptpsq         ptpsq[MLX5_MAX_NUM_TC];
 	struct mlx5e_rq            rq;
 	struct napi_struct         napi;
 	struct device             *pdev;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c
index 244bc15a42ab..9e2211f0c3a4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c
@@ -77,6 +77,7 @@ int mlx5e_open_qos_sq(struct mlx5e_priv *priv, struct mlx5e_channels *chs,
 	struct mlx5e_params *params;
 	struct mlx5e_channel *c;
 	struct mlx5e_txqsq *sq;
+	u32 tisn;
 
 	params = &chs->params;
 
@@ -126,8 +127,10 @@ int mlx5e_open_qos_sq(struct mlx5e_priv *priv, struct mlx5e_channels *chs,
 	err = mlx5e_open_cq(priv, params->tx_cq_moderation, &param_cq, &ccp, &sq->cq);
 	if (err)
 		goto err_free_sq;
-	err = mlx5e_open_txqsq(c, priv->tisn[c->lag_port][0], txq_ix, params,
-			       &param_sq, sq, 0, hw_id,
+
+	tisn = mlx5e_profile_get_tisn(c->mdev, c->priv, c->priv->profile,
+				      c->lag_port, 0);
+	err = mlx5e_open_txqsq(c, tisn, txq_ix, params, &param_sq, sq, 0, hw_id,
 			       priv->htb_qos_sq_stats[node_qid]);
 	if (err)
 		goto err_close_cq;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
index 41c396e76457..67f546683e85 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
@@ -74,6 +74,72 @@ int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, u32 *mkey)
 	return err;
 }
 
+int mlx5e_create_tis(struct mlx5_core_dev *mdev, void *in, u32 *tisn)
+{
+	void *tisc = MLX5_ADDR_OF(create_tis_in, in, ctx);
+
+	MLX5_SET(tisc, tisc, transport_domain, mdev->mlx5e_res.hw_objs.td.tdn);
+
+	if (mlx5_lag_is_lacp_owner(mdev))
+		MLX5_SET(tisc, tisc, strict_lag_tx_port_affinity, 1);
+
+	return mlx5_core_create_tis(mdev, in, tisn);
+}
+
+void mlx5e_destroy_tis(struct mlx5_core_dev *mdev, u32 tisn)
+{
+	mlx5_core_destroy_tis(mdev, tisn);
+}
+
+static void mlx5e_destroy_tises(struct mlx5_core_dev *mdev, u32 tisn[MLX5_MAX_PORTS][MLX5_MAX_NUM_TC])
+{
+	int tc, i;
+
+	for (i = 0; i < MLX5_MAX_PORTS; i++)
+		for (tc = 0; tc < MLX5_MAX_NUM_TC; tc++)
+			mlx5e_destroy_tis(mdev, tisn[i][tc]);
+}
+
+static bool mlx5_lag_should_assign_affinity(struct mlx5_core_dev *mdev)
+{
+	return MLX5_CAP_GEN(mdev, lag_tx_port_affinity) && mlx5e_get_num_lag_ports(mdev) > 1;
+}
+
+static int mlx5e_create_tises(struct mlx5_core_dev *mdev, u32 tisn[MLX5_MAX_PORTS][MLX5_MAX_NUM_TC])
+{
+	int tc, i;
+	int err;
+
+	for (i = 0; i < MLX5_MAX_PORTS; i++) {
+		for (tc = 0; tc < MLX5_MAX_NUM_TC; tc++) {
+			u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {};
+			void *tisc;
+
+			tisc = MLX5_ADDR_OF(create_tis_in, in, ctx);
+
+			MLX5_SET(tisc, tisc, prio, tc << 1);
+
+			if (mlx5_lag_should_assign_affinity(mdev))
+				MLX5_SET(tisc, tisc, lag_tx_port_affinity, i + 1);
+
+			err = mlx5e_create_tis(mdev, in, &tisn[i][tc]);
+			if (err)
+				goto err_close_tises;
+		}
+	}
+
+	return 0;
+
+err_close_tises:
+	for (; i >= 0; i--) {
+		for (tc--; tc >= 0; tc--)
+			mlx5e_destroy_tis(mdev, tisn[i][tc]);
+		tc = MLX5_MAX_NUM_TC;
+	}
+
+	return err;
+}
+
 int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev)
 {
 	struct mlx5e_hw_objs *res = &mdev->mlx5e_res.hw_objs;
@@ -103,6 +169,11 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev)
 		goto err_destroy_mkey;
 	}
 
+	err = mlx5e_create_tises(mdev, res->tisn);
+	if (err) {
+		mlx5_core_err(mdev, "alloc tises failed, %d\n", err);
+		goto err_destroy_bfreg;
+	}
 	INIT_LIST_HEAD(&res->td.tirs_list);
 	mutex_init(&res->td.list_lock);
 
@@ -115,6 +186,8 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev)
 
 	return 0;
 
+err_destroy_bfreg:
+	mlx5_free_bfreg(mdev, &res->bfreg);
 err_destroy_mkey:
 	mlx5_core_destroy_mkey(mdev, res->mkey);
 err_dealloc_transport_domain:
@@ -130,6 +203,7 @@ void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev)
 
 	mlx5_crypto_dek_cleanup(mdev->mlx5e_res.dek_priv);
 	mdev->mlx5e_res.dek_priv = NULL;
+	mlx5e_destroy_tises(mdev, res->tisn);
 	mlx5_free_bfreg(mdev, &res->bfreg);
 	mlx5_core_destroy_mkey(mdev, res->mkey);
 	mlx5_core_dealloc_transport_domain(mdev, res->td.tdn);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index b49b7c28863c..ecb40950ec8d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1352,6 +1352,17 @@ void mlx5e_close_rq(struct mlx5e_rq *rq)
 	mlx5e_free_rq(rq);
 }
 
+u32 mlx5e_profile_get_tisn(struct mlx5_core_dev *mdev,
+			   struct mlx5e_priv *priv,
+			   const struct mlx5e_profile *profile,
+			   u8 lag_port, u8 tc)
+{
+	if (profile->get_tisn)
+		return profile->get_tisn(mdev, priv, lag_port, tc);
+
+	return mdev->mlx5e_res.hw_objs.tisn[lag_port][tc];
+}
+
 static void mlx5e_free_xdpsq_db(struct mlx5e_xdpsq *sq)
 {
 	kvfree(sq->db.xdpi_fifo.xi);
@@ -1920,7 +1931,8 @@ int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params,
 		return err;
 
 	csp.tis_lst_sz      = 1;
-	csp.tisn            = c->priv->tisn[c->lag_port][0]; /* tc = 0 */
+	csp.tisn            = mlx5e_profile_get_tisn(c->mdev, c->priv, c->priv->profile,
+						     c->lag_port, 0); /* tc = 0 */
 	csp.cqn             = sq->cq.mcq.cqn;
 	csp.wq_ctrl         = &sq->wq_ctrl;
 	csp.min_inline_mode = sq->min_inline_mode;
@@ -2204,12 +2216,15 @@ static int mlx5e_open_sqs(struct mlx5e_channel *c,
 	for (tc = 0; tc < mlx5e_get_dcb_num_tc(params); tc++) {
 		int txq_ix = c->ix + tc * params->num_channels;
 		u32 qos_queue_group_id;
+		u32 tisn;
 
+		tisn = mlx5e_profile_get_tisn(c->mdev, c->priv, c->priv->profile,
+					      c->lag_port, tc);
 		err = mlx5e_txq_get_qos_node_hw_id(params, txq_ix, &qos_queue_group_id);
 		if (err)
 			goto err_close_sqs;
 
-		err = mlx5e_open_txqsq(c, c->priv->tisn[c->lag_port][tc], txq_ix,
+		err = mlx5e_open_txqsq(c, tisn, txq_ix,
 				       params, &cparam->txq_sq, &c->sq[tc], tc,
 				       qos_queue_group_id,
 				       &c->priv->channel_stats[c->ix]->sq[tc]);
@@ -3351,72 +3366,6 @@ void mlx5e_close_drop_rq(struct mlx5e_rq *drop_rq)
 	mlx5e_free_cq(&drop_rq->cq);
 }
 
-int mlx5e_create_tis(struct mlx5_core_dev *mdev, void *in, u32 *tisn)
-{
-	void *tisc = MLX5_ADDR_OF(create_tis_in, in, ctx);
-
-	MLX5_SET(tisc, tisc, transport_domain, mdev->mlx5e_res.hw_objs.td.tdn);
-
-	if (mlx5_lag_is_lacp_owner(mdev))
-		MLX5_SET(tisc, tisc, strict_lag_tx_port_affinity, 1);
-
-	return mlx5_core_create_tis(mdev, in, tisn);
-}
-
-void mlx5e_destroy_tis(struct mlx5_core_dev *mdev, u32 tisn)
-{
-	mlx5_core_destroy_tis(mdev, tisn);
-}
-
-void mlx5e_destroy_tises(struct mlx5e_priv *priv)
-{
-	int tc, i;
-
-	for (i = 0; i < mlx5e_get_num_lag_ports(priv->mdev); i++)
-		for (tc = 0; tc < priv->profile->max_tc; tc++)
-			mlx5e_destroy_tis(priv->mdev, priv->tisn[i][tc]);
-}
-
-static bool mlx5e_lag_should_assign_affinity(struct mlx5_core_dev *mdev)
-{
-	return MLX5_CAP_GEN(mdev, lag_tx_port_affinity) && mlx5e_get_num_lag_ports(mdev) > 1;
-}
-
-int mlx5e_create_tises(struct mlx5e_priv *priv)
-{
-	int tc, i;
-	int err;
-
-	for (i = 0; i < mlx5e_get_num_lag_ports(priv->mdev); i++) {
-		for (tc = 0; tc < priv->profile->max_tc; tc++) {
-			u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {};
-			void *tisc;
-
-			tisc = MLX5_ADDR_OF(create_tis_in, in, ctx);
-
-			MLX5_SET(tisc, tisc, prio, tc << 1);
-
-			if (mlx5e_lag_should_assign_affinity(priv->mdev))
-				MLX5_SET(tisc, tisc, lag_tx_port_affinity, i + 1);
-
-			err = mlx5e_create_tis(priv->mdev, in, &priv->tisn[i][tc]);
-			if (err)
-				goto err_close_tises;
-		}
-	}
-
-	return 0;
-
-err_close_tises:
-	for (; i >= 0; i--) {
-		for (tc--; tc >= 0; tc--)
-			mlx5e_destroy_tis(priv->mdev, priv->tisn[i][tc]);
-		tc = priv->profile->max_tc;
-	}
-
-	return err;
-}
-
 static void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv)
 {
 	if (priv->mqprio_rl) {
@@ -3425,7 +3374,6 @@ static void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv)
 		priv->mqprio_rl = NULL;
 	}
 	mlx5e_accel_cleanup_tx(priv);
-	mlx5e_destroy_tises(priv);
 }
 
 static int mlx5e_modify_channels_vsd(struct mlx5e_channels *chs, bool vsd)
@@ -3527,7 +3475,7 @@ static int mlx5e_setup_tc_mqprio_dcb(struct mlx5e_priv *priv,
 
 	mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
 
-	if (tc && tc != MLX5E_MAX_NUM_TC)
+	if (tc && tc != MLX5_MAX_NUM_TC)
 		return -EINVAL;
 
 	new_params = priv->channels.params;
@@ -5482,23 +5430,13 @@ static int mlx5e_init_nic_tx(struct mlx5e_priv *priv)
 {
 	int err;
 
-	err = mlx5e_create_tises(priv);
-	if (err) {
-		mlx5_core_warn(priv->mdev, "create tises failed, %d\n", err);
-		return err;
-	}
-
 	err = mlx5e_accel_init_tx(priv);
 	if (err)
-		goto err_destroy_tises;
+		return err;
 
 	mlx5e_set_mqprio_rl(priv);
 	mlx5e_dcbnl_initialize(priv);
 	return 0;
-
-err_destroy_tises:
-	mlx5e_destroy_tises(priv);
-	return err;
 }
 
 static void mlx5e_nic_enable(struct mlx5e_priv *priv)
@@ -5593,7 +5531,7 @@ static const struct mlx5e_profile mlx5e_nic_profile = {
 	.update_stats	   = mlx5e_stats_update_ndo_stats,
 	.update_carrier	   = mlx5e_update_carrier,
 	.rx_handlers       = &mlx5e_rx_handlers_nic,
-	.max_tc		   = MLX5E_MAX_NUM_TC,
+	.max_tc		   = MLX5_MAX_NUM_TC,
 	.stats_grps	   = mlx5e_nic_stats_grps,
 	.stats_grps_num	   = mlx5e_nic_stats_grps_num,
 	.features          = BIT(MLX5E_PROFILE_FEATURE_PTP_RX) |
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index fe0726c7b847..e3018a141b6f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1180,12 +1180,6 @@ static int mlx5e_init_rep_tx(struct mlx5e_priv *priv)
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	int err;
 
-	err = mlx5e_create_tises(priv);
-	if (err) {
-		mlx5_core_warn(priv->mdev, "create tises failed, %d\n", err);
-		return err;
-	}
-
 	err = mlx5e_rep_neigh_init(rpriv);
 	if (err)
 		goto err_neigh_init;
@@ -1208,7 +1202,6 @@ err_ht_init:
 err_init_tx:
 	mlx5e_rep_neigh_cleanup(rpriv);
 err_neigh_init:
-	mlx5e_destroy_tises(priv);
 	return err;
 }
 
@@ -1222,7 +1215,6 @@ static void mlx5e_cleanup_rep_tx(struct mlx5e_priv *priv)
 		mlx5e_cleanup_uplink_rep_tx(rpriv);
 
 	mlx5e_rep_neigh_cleanup(rpriv);
-	mlx5e_destroy_tises(priv);
 }
 
 static void mlx5e_rep_enable(struct mlx5e_priv *priv)
@@ -1452,7 +1444,7 @@ static const struct mlx5e_profile mlx5e_uplink_rep_profile = {
 	.update_stats           = mlx5e_stats_update_ndo_stats,
 	.update_carrier	        = mlx5e_update_carrier,
 	.rx_handlers            = &mlx5e_rx_handlers_rep,
-	.max_tc			= MLX5E_MAX_NUM_TC,
+	.max_tc			= MLX5_MAX_NUM_TC,
 	.stats_grps		= mlx5e_ul_rep_stats_grps,
 	.stats_grps_num		= mlx5e_ul_rep_stats_grps_num,
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 2bf77a5251b4..58845121954c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -339,7 +339,7 @@ static int mlx5i_init_tx(struct mlx5e_priv *priv)
 		return err;
 	}
 
-	err = mlx5i_create_tis(priv->mdev, ipriv->qpn, &priv->tisn[0][0]);
+	err = mlx5i_create_tis(priv->mdev, ipriv->qpn, &ipriv->tisn);
 	if (err) {
 		mlx5_core_warn(priv->mdev, "create tis failed, %d\n", err);
 		goto err_destroy_underlay_qp;
@@ -356,7 +356,7 @@ static void mlx5i_cleanup_tx(struct mlx5e_priv *priv)
 {
 	struct mlx5i_priv *ipriv = priv->ppriv;
 
-	mlx5e_destroy_tis(priv->mdev, priv->tisn[0][0]);
+	mlx5e_destroy_tis(priv->mdev, ipriv->tisn);
 	mlx5i_destroy_underlay_qp(priv->mdev, ipriv->qpn);
 }
 
@@ -483,6 +483,18 @@ static unsigned int mlx5i_stats_grps_num(struct mlx5e_priv *priv)
 	return ARRAY_SIZE(mlx5i_stats_grps);
 }
 
+u32 mlx5i_get_tisn(struct mlx5_core_dev *mdev, struct mlx5e_priv *priv, u8 lag_port, u8 tc)
+{
+	struct mlx5i_priv *ipriv = priv->ppriv;
+
+	if (WARN(lag_port || tc,
+		 "IPoIB unexpected non-zero value: lag_port (%u), tc (%u)\n",
+		 lag_port, tc))
+		return 0;
+
+	return ipriv->tisn;
+}
+
 static const struct mlx5e_profile mlx5i_nic_profile = {
 	.init		   = mlx5i_init,
 	.cleanup	   = mlx5i_cleanup,
@@ -499,6 +511,7 @@ static const struct mlx5e_profile mlx5i_nic_profile = {
 	.max_tc		   = MLX5I_MAX_NUM_TC,
 	.stats_grps        = mlx5i_stats_grps,
 	.stats_grps_num    = mlx5i_stats_grps_num,
+	.get_tisn          = mlx5i_get_tisn,
 };
 
 /* mlx5i netdev NDos */
@@ -829,7 +842,7 @@ int mlx5_rdma_rn_get_params(struct mlx5_core_dev *mdev,
 	*params = (struct rdma_netdev_alloc_params){
 		.sizeof_priv = sizeof(struct mlx5i_priv) +
 			       sizeof(struct mlx5e_priv),
-		.txqs = nch * MLX5E_MAX_NUM_TC,
+		.txqs = nch * MLX5_MAX_NUM_TC,
 		.rxqs = nch,
 		.param = mdev,
 		.initialize_rdma_netdev = mlx5_rdma_setup_rn,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
index f3f2af972020..2ab6437a1c49 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
@@ -53,6 +53,7 @@ extern const struct mlx5e_rx_handlers mlx5i_rx_handlers;
 struct mlx5i_priv {
 	struct rdma_netdev rn; /* keep this first */
 	u32 qpn;
+	u32 tisn;
 	bool   sub_interface;
 	u32    num_sub_interfaces;
 	u32    qkey;
@@ -63,6 +64,7 @@ struct mlx5i_priv {
 };
 
 int mlx5i_create_tis(struct mlx5_core_dev *mdev, u32 underlay_qpn, u32 *tisn);
+u32 mlx5i_get_tisn(struct mlx5_core_dev *mdev, struct mlx5e_priv *priv, u8 lag_port, u8 tc);
 
 /* Underlay QP create/destroy functions */
 int mlx5i_create_underlay_qp(struct mlx5e_priv *priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
index 03e681297937..f87471306f6b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
@@ -218,7 +218,7 @@ static int mlx5i_pkey_open(struct net_device *netdev)
 		goto err_unint_underlay_qp;
 	}
 
-	err = mlx5i_create_tis(mdev, ipriv->qpn, &epriv->tisn[0][0]);
+	err = mlx5i_create_tis(mdev, ipriv->qpn, &ipriv->tisn);
 	if (err) {
 		mlx5_core_warn(mdev, "create child tis failed, %d\n", err);
 		goto err_remove_rx_uderlay_qp;
@@ -240,7 +240,7 @@ static int mlx5i_pkey_open(struct net_device *netdev)
 err_close_channels:
 	mlx5e_close_channels(&epriv->channels);
 err_clear_state_opened_flag:
-	mlx5e_destroy_tis(mdev, epriv->tisn[0][0]);
+	mlx5e_destroy_tis(mdev, ipriv->tisn);
 err_remove_rx_uderlay_qp:
 	mlx5_fs_remove_rx_underlay_qpn(mdev, ipriv->qpn);
 err_unint_underlay_qp:
@@ -269,7 +269,7 @@ static int mlx5i_pkey_close(struct net_device *netdev)
 	mlx5i_uninit_underlay_qp(priv);
 	mlx5e_deactivate_priv_channels(priv);
 	mlx5e_close_channels(&priv->channels);
-	mlx5e_destroy_tis(mdev, priv->tisn[0][0]);
+	mlx5e_destroy_tis(mdev, ipriv->tisn);
 unlock:
 	mutex_unlock(&priv->state_lock);
 	return 0;
@@ -361,6 +361,7 @@ static const struct mlx5e_profile mlx5i_pkey_nic_profile = {
 	.update_stats	   = NULL,
 	.rx_handlers       = &mlx5i_rx_handlers,
 	.max_tc		   = MLX5I_MAX_NUM_TC,
+	.get_tisn          = mlx5i_get_tisn,
 };
 
 const struct mlx5e_profile *mlx5i_pkey_get_profile(void)
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 2f67cec1a898..7ee5b79ff3d6 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -679,6 +679,8 @@ struct mlx5e_resources {
 		struct mlx5_td             td;
 		u32			   mkey;
 		struct mlx5_sq_bfreg       bfreg;
+#define MLX5_MAX_NUM_TC 8
+		u32                        tisn[MLX5_MAX_PORTS][MLX5_MAX_NUM_TC];
 	} hw_objs;
 	struct net_device *uplink_netdev;
 	struct mutex uplink_netdev_lock;
-- 
cgit v1.2.3


From 50d73710715de7d1a2c88194562f520816af9c2a Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <aleksander.lobakin@intel.com>
Date: Tue, 12 Dec 2023 15:27:51 +0100
Subject: ethtool: add SET for TCP_DATA_SPLIT ringparam

Follow up commit 9690ae604290 ("ethtool: add header/data split
indication") and add the set part of Ethtool's header split, i.e.
ability to enable/disable header split via the Ethtool Netlink
interface. This might be helpful to optimize the setup for particular
workloads, for example, to avoid XDP frags, and so on.
A driver should advertise ``ETHTOOL_RING_USE_TCP_DATA_SPLIT`` in its
ops->supported_ring_params to allow doing that. "Unknown" passed from
the userspace when the header split is supported means the driver is
free to choose the preferred state.

Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Link: https://lore.kernel.org/r/20231212142752.935000-2-aleksander.lobakin@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/ethtool.h |  2 ++
 net/ethtool/rings.c     | 12 ++++++++++++
 2 files changed, 14 insertions(+)

(limited to 'include')

diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index deb683d3360f..67b30940234b 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -95,6 +95,7 @@ struct kernel_ethtool_ringparam {
  * @ETHTOOL_RING_USE_TX_PUSH: capture for setting tx_push
  * @ETHTOOL_RING_USE_RX_PUSH: capture for setting rx_push
  * @ETHTOOL_RING_USE_TX_PUSH_BUF_LEN: capture for setting tx_push_buf_len
+ * @ETHTOOL_RING_USE_TCP_DATA_SPLIT: capture for setting tcp_data_split
  */
 enum ethtool_supported_ring_param {
 	ETHTOOL_RING_USE_RX_BUF_LEN		= BIT(0),
@@ -102,6 +103,7 @@ enum ethtool_supported_ring_param {
 	ETHTOOL_RING_USE_TX_PUSH		= BIT(2),
 	ETHTOOL_RING_USE_RX_PUSH		= BIT(3),
 	ETHTOOL_RING_USE_TX_PUSH_BUF_LEN	= BIT(4),
+	ETHTOOL_RING_USE_TCP_DATA_SPLIT		= BIT(5),
 };
 
 #define __ETH_RSS_HASH_BIT(bit)	((u32)1 << (bit))
diff --git a/net/ethtool/rings.c b/net/ethtool/rings.c
index fb09f774ea01..b7865a14fdf8 100644
--- a/net/ethtool/rings.c
+++ b/net/ethtool/rings.c
@@ -124,6 +124,8 @@ const struct nla_policy ethnl_rings_set_policy[] = {
 	[ETHTOOL_A_RINGS_RX_JUMBO]		= { .type = NLA_U32 },
 	[ETHTOOL_A_RINGS_TX]			= { .type = NLA_U32 },
 	[ETHTOOL_A_RINGS_RX_BUF_LEN]            = NLA_POLICY_MIN(NLA_U32, 1),
+	[ETHTOOL_A_RINGS_TCP_DATA_SPLIT]	=
+		NLA_POLICY_MAX(NLA_U8, ETHTOOL_TCP_DATA_SPLIT_ENABLED),
 	[ETHTOOL_A_RINGS_CQE_SIZE]		= NLA_POLICY_MIN(NLA_U32, 1),
 	[ETHTOOL_A_RINGS_TX_PUSH]		= NLA_POLICY_MAX(NLA_U8, 1),
 	[ETHTOOL_A_RINGS_RX_PUSH]		= NLA_POLICY_MAX(NLA_U8, 1),
@@ -145,6 +147,14 @@ ethnl_set_rings_validate(struct ethnl_req_info *req_info,
 		return -EOPNOTSUPP;
 	}
 
+	if (tb[ETHTOOL_A_RINGS_TCP_DATA_SPLIT] &&
+	    !(ops->supported_ring_params & ETHTOOL_RING_USE_TCP_DATA_SPLIT)) {
+		NL_SET_ERR_MSG_ATTR(info->extack,
+				    tb[ETHTOOL_A_RINGS_TCP_DATA_SPLIT],
+				    "setting TCP data split is not supported");
+		return -EOPNOTSUPP;
+	}
+
 	if (tb[ETHTOOL_A_RINGS_CQE_SIZE] &&
 	    !(ops->supported_ring_params & ETHTOOL_RING_USE_CQE_SIZE)) {
 		NL_SET_ERR_MSG_ATTR(info->extack,
@@ -202,6 +212,8 @@ ethnl_set_rings(struct ethnl_req_info *req_info, struct genl_info *info)
 	ethnl_update_u32(&ringparam.tx_pending, tb[ETHTOOL_A_RINGS_TX], &mod);
 	ethnl_update_u32(&kernel_ringparam.rx_buf_len,
 			 tb[ETHTOOL_A_RINGS_RX_BUF_LEN], &mod);
+	ethnl_update_u8(&kernel_ringparam.tcp_data_split,
+			tb[ETHTOOL_A_RINGS_TCP_DATA_SPLIT], &mod);
 	ethnl_update_u32(&kernel_ringparam.cqe_size,
 			 tb[ETHTOOL_A_RINGS_CQE_SIZE], &mod);
 	ethnl_update_u8(&kernel_ringparam.tx_push,
-- 
cgit v1.2.3


From 0a149ab78ee220c75eef797abea7a29f4490e226 Mon Sep 17 00:00:00 2001
From: Liang Chen <liangchen.linux@gmail.com>
Date: Tue, 12 Dec 2023 12:46:11 +0800
Subject: page_pool: transition to reference count management after page
 draining

To support multiple users referencing the same fragment,
'pp_frag_count' is renamed to 'pp_ref_count', transitioning pp pages
from fragment management to reference count management after draining
based on the suggestion from [1].

The idea is that the concept of fragmenting exists before the page is
drained, and all related functions retain their current names.
However, once the page is drained, its management shifts to being
governed by 'pp_ref_count'. Therefore, all functions associated with
that lifecycle stage of a pp page are renamed.

[1]
http://lore.kernel.org/netdev/f71d9448-70c8-8793-dc9a-0eb48a570300@huawei.com

Signed-off-by: Liang Chen <liangchen.linux@gmail.com>
Reviewed-by: Yunsheng Lin <linyunsheng@huawei.com>
Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Reviewed-by: Mina Almasry <almasrymina@google.com>
Link: https://lore.kernel.org/r/20231212044614.42733-2-liangchen.linux@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c |  4 +-
 include/linux/mm_types.h                        |  2 +-
 include/net/page_pool/helpers.h                 | 60 ++++++++++++++-----------
 include/net/page_pool/types.h                   |  6 +--
 net/core/page_pool.c                            | 12 ++---
 5 files changed, 46 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 8d9743a5e42c..98d33ac7ec64 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -298,8 +298,8 @@ static void mlx5e_page_release_fragmented(struct mlx5e_rq *rq,
 	u16 drain_count = MLX5E_PAGECNT_BIAS_MAX - frag_page->frags;
 	struct page *page = frag_page->page;
 
-	if (page_pool_defrag_page(page, drain_count) == 0)
-		page_pool_put_defragged_page(rq->page_pool, page, -1, true);
+	if (page_pool_unref_page(page, drain_count) == 0)
+		page_pool_put_unrefed_page(rq->page_pool, page, -1, true);
 }
 
 static inline int mlx5e_get_rx_frag(struct mlx5e_rq *rq,
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 957ce38768b2..64e4572ef06d 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -125,7 +125,7 @@ struct page {
 			struct page_pool *pp;
 			unsigned long _pp_mapping_pad;
 			unsigned long dma_addr;
-			atomic_long_t pp_frag_count;
+			atomic_long_t pp_ref_count;
 		};
 		struct {	/* Tail pages of compound page */
 			unsigned long compound_head;	/* Bit zero is set */
diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h
index 7dc65774cde5..841e0a930bd7 100644
--- a/include/net/page_pool/helpers.h
+++ b/include/net/page_pool/helpers.h
@@ -29,7 +29,7 @@
  * page allocated from page pool. Page splitting enables memory saving and thus
  * avoids TLB/cache miss for data access, but there also is some cost to
  * implement page splitting, mainly some cache line dirtying/bouncing for
- * 'struct page' and atomic operation for page->pp_frag_count.
+ * 'struct page' and atomic operation for page->pp_ref_count.
  *
  * The API keeps track of in-flight pages, in order to let API users know when
  * it is safe to free a page_pool object, the API users must call
@@ -210,69 +210,77 @@ inline enum dma_data_direction page_pool_get_dma_dir(struct page_pool *pool)
 	return pool->p.dma_dir;
 }
 
-/* pp_frag_count represents the number of writers who can update the page
- * either by updating skb->data or via DMA mappings for the device.
- * We can't rely on the page refcnt for that as we don't know who might be
- * holding page references and we can't reliably destroy or sync DMA mappings
- * of the fragments.
+/**
+ * page_pool_fragment_page() - split a fresh page into fragments
+ * @page:	page to split
+ * @nr:		references to set
+ *
+ * pp_ref_count represents the number of outstanding references to the page,
+ * which will be freed using page_pool APIs (rather than page allocator APIs
+ * like put_page()). Such references are usually held by page_pool-aware
+ * objects like skbs marked for page pool recycling.
  *
- * When pp_frag_count reaches 0 we can either recycle the page if the page
- * refcnt is 1 or return it back to the memory allocator and destroy any
- * mappings we have.
+ * This helper allows the caller to take (set) multiple references to a
+ * freshly allocated page. The page must be freshly allocated (have a
+ * pp_ref_count of 1). This is commonly done by drivers and
+ * "fragment allocators" to save atomic operations - either when they know
+ * upfront how many references they will need; or to take MAX references and
+ * return the unused ones with a single atomic dec(), instead of performing
+ * multiple atomic inc() operations.
  */
 static inline void page_pool_fragment_page(struct page *page, long nr)
 {
-	atomic_long_set(&page->pp_frag_count, nr);
+	atomic_long_set(&page->pp_ref_count, nr);
 }
 
-static inline long page_pool_defrag_page(struct page *page, long nr)
+static inline long page_pool_unref_page(struct page *page, long nr)
 {
 	long ret;
 
-	/* If nr == pp_frag_count then we have cleared all remaining
+	/* If nr == pp_ref_count then we have cleared all remaining
 	 * references to the page:
 	 * 1. 'n == 1': no need to actually overwrite it.
 	 * 2. 'n != 1': overwrite it with one, which is the rare case
-	 *              for pp_frag_count draining.
+	 *              for pp_ref_count draining.
 	 *
 	 * The main advantage to doing this is that not only we avoid a atomic
 	 * update, as an atomic_read is generally a much cheaper operation than
 	 * an atomic update, especially when dealing with a page that may be
-	 * partitioned into only 2 or 3 pieces; but also unify the pp_frag_count
+	 * referenced by only 2 or 3 users; but also unify the pp_ref_count
 	 * handling by ensuring all pages have partitioned into only 1 piece
 	 * initially, and only overwrite it when the page is partitioned into
 	 * more than one piece.
 	 */
-	if (atomic_long_read(&page->pp_frag_count) == nr) {
+	if (atomic_long_read(&page->pp_ref_count) == nr) {
 		/* As we have ensured nr is always one for constant case using
 		 * the BUILD_BUG_ON(), only need to handle the non-constant case
-		 * here for pp_frag_count draining, which is a rare case.
+		 * here for pp_ref_count draining, which is a rare case.
 		 */
 		BUILD_BUG_ON(__builtin_constant_p(nr) && nr != 1);
 		if (!__builtin_constant_p(nr))
-			atomic_long_set(&page->pp_frag_count, 1);
+			atomic_long_set(&page->pp_ref_count, 1);
 
 		return 0;
 	}
 
-	ret = atomic_long_sub_return(nr, &page->pp_frag_count);
+	ret = atomic_long_sub_return(nr, &page->pp_ref_count);
 	WARN_ON(ret < 0);
 
-	/* We are the last user here too, reset pp_frag_count back to 1 to
+	/* We are the last user here too, reset pp_ref_count back to 1 to
 	 * ensure all pages have been partitioned into 1 piece initially,
 	 * this should be the rare case when the last two fragment users call
-	 * page_pool_defrag_page() currently.
+	 * page_pool_unref_page() currently.
 	 */
 	if (unlikely(!ret))
-		atomic_long_set(&page->pp_frag_count, 1);
+		atomic_long_set(&page->pp_ref_count, 1);
 
 	return ret;
 }
 
-static inline bool page_pool_is_last_frag(struct page *page)
+static inline bool page_pool_is_last_ref(struct page *page)
 {
-	/* If page_pool_defrag_page() returns 0, we were the last user */
-	return page_pool_defrag_page(page, 1) == 0;
+	/* If page_pool_unref_page() returns 0, we were the last user */
+	return page_pool_unref_page(page, 1) == 0;
 }
 
 /**
@@ -297,10 +305,10 @@ static inline void page_pool_put_page(struct page_pool *pool,
 	 * allow registering MEM_TYPE_PAGE_POOL, but shield linker.
 	 */
 #ifdef CONFIG_PAGE_POOL
-	if (!page_pool_is_last_frag(page))
+	if (!page_pool_is_last_ref(page))
 		return;
 
-	page_pool_put_defragged_page(pool, page, dma_sync_size, allow_direct);
+	page_pool_put_unrefed_page(pool, page, dma_sync_size, allow_direct);
 #endif
 }
 
diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index ac286ea8ce2d..76481c465375 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -234,9 +234,9 @@ static inline void page_pool_put_page_bulk(struct page_pool *pool, void **data,
 }
 #endif
 
-void page_pool_put_defragged_page(struct page_pool *pool, struct page *page,
-				  unsigned int dma_sync_size,
-				  bool allow_direct);
+void page_pool_put_unrefed_page(struct page_pool *pool, struct page *page,
+				unsigned int dma_sync_size,
+				bool allow_direct);
 
 static inline bool is_page_pool_compiled_in(void)
 {
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index c2e7c9a6efbe..c92b757369f2 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -677,8 +677,8 @@ __page_pool_put_page(struct page_pool *pool, struct page *page,
 	return NULL;
 }
 
-void page_pool_put_defragged_page(struct page_pool *pool, struct page *page,
-				  unsigned int dma_sync_size, bool allow_direct)
+void page_pool_put_unrefed_page(struct page_pool *pool, struct page *page,
+				unsigned int dma_sync_size, bool allow_direct)
 {
 	page = __page_pool_put_page(pool, page, dma_sync_size, allow_direct);
 	if (page && !page_pool_recycle_in_ring(pool, page)) {
@@ -687,7 +687,7 @@ void page_pool_put_defragged_page(struct page_pool *pool, struct page *page,
 		page_pool_return_page(pool, page);
 	}
 }
-EXPORT_SYMBOL(page_pool_put_defragged_page);
+EXPORT_SYMBOL(page_pool_put_unrefed_page);
 
 /**
  * page_pool_put_page_bulk() - release references on multiple pages
@@ -714,7 +714,7 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data,
 		struct page *page = virt_to_head_page(data[i]);
 
 		/* It is not the last user for the page frag case */
-		if (!page_pool_is_last_frag(page))
+		if (!page_pool_is_last_ref(page))
 			continue;
 
 		page = __page_pool_put_page(pool, page, -1, false);
@@ -756,7 +756,7 @@ static struct page *page_pool_drain_frag(struct page_pool *pool,
 	long drain_count = BIAS_MAX - pool->frag_users;
 
 	/* Some user is still using the page frag */
-	if (likely(page_pool_defrag_page(page, drain_count)))
+	if (likely(page_pool_unref_page(page, drain_count)))
 		return NULL;
 
 	if (page_ref_count(page) == 1 && !page_is_pfmemalloc(page)) {
@@ -777,7 +777,7 @@ static void page_pool_free_frag(struct page_pool *pool)
 
 	pool->frag_page = NULL;
 
-	if (!page || page_pool_defrag_page(page, drain_count))
+	if (!page || page_pool_unref_page(page, drain_count))
 		return;
 
 	page_pool_return_page(pool, page);
-- 
cgit v1.2.3


From 0ae7a02726bca95ee9d17de0ccfcd1de0ff4e429 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Fri, 8 Dec 2023 12:28:51 +0530
Subject: scsi: ufs: qcom: Export ufshcd_{enable/disable}_irq helpers and make
 use of them

Instead of duplicating the enable/disable IRQ part, let's export the
helpers available in ufshcd driver and make use of them. This also fixes
the possible redundant IRQ disable before asserting reset (when IRQ was
already disabled).

Fixes: 4a791574a0cc ("scsi: ufs: ufs-qcom: Disable interrupt in reset path")
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20231208065902.11006-7-manivannan.sadhasivam@linaro.org
Tested-by: Andrew Halaney <ahalaney@redhat.com> # sa8775p-ride
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c   | 6 ++++--
 drivers/ufs/host/ufs-qcom.c | 9 +++------
 include/ufs/ufshcd.h        | 2 ++
 3 files changed, 9 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 8b1031fb0a44..671facc73921 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -289,21 +289,23 @@ static void ufshcd_wb_toggle_buf_flush_during_h8(struct ufs_hba *hba,
 static void ufshcd_hba_vreg_set_lpm(struct ufs_hba *hba);
 static void ufshcd_hba_vreg_set_hpm(struct ufs_hba *hba);
 
-static inline void ufshcd_enable_irq(struct ufs_hba *hba)
+void ufshcd_enable_irq(struct ufs_hba *hba)
 {
 	if (!hba->is_irq_enabled) {
 		enable_irq(hba->irq);
 		hba->is_irq_enabled = true;
 	}
 }
+EXPORT_SYMBOL_GPL(ufshcd_enable_irq);
 
-static inline void ufshcd_disable_irq(struct ufs_hba *hba)
+void ufshcd_disable_irq(struct ufs_hba *hba)
 {
 	if (hba->is_irq_enabled) {
 		disable_irq(hba->irq);
 		hba->is_irq_enabled = false;
 	}
 }
+EXPORT_SYMBOL_GPL(ufshcd_disable_irq);
 
 static void ufshcd_configure_wb(struct ufs_hba *hba)
 {
diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c
index d474de0739e4..604273a22afd 100644
--- a/drivers/ufs/host/ufs-qcom.c
+++ b/drivers/ufs/host/ufs-qcom.c
@@ -300,8 +300,7 @@ static int ufs_qcom_host_reset(struct ufs_hba *hba)
 		return 0;
 
 	reenable_intr = hba->is_irq_enabled;
-	disable_irq(hba->irq);
-	hba->is_irq_enabled = false;
+	ufshcd_disable_irq(hba);
 
 	ret = reset_control_assert(host->core_reset);
 	if (ret) {
@@ -324,10 +323,8 @@ static int ufs_qcom_host_reset(struct ufs_hba *hba)
 
 	usleep_range(1000, 1100);
 
-	if (reenable_intr) {
-		enable_irq(hba->irq);
-		hba->is_irq_enabled = true;
-	}
+	if (reenable_intr)
+		ufshcd_enable_irq(hba);
 
 	return 0;
 }
diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h
index 7f0b2c5599cd..f1fc16ac6af2 100644
--- a/include/ufs/ufshcd.h
+++ b/include/ufs/ufshcd.h
@@ -1231,6 +1231,8 @@ static inline void ufshcd_rmwl(struct ufs_hba *hba, u32 mask, u32 val, u32 reg)
 	ufshcd_writel(hba, tmp, reg);
 }
 
+void ufshcd_enable_irq(struct ufs_hba *hba);
+void ufshcd_disable_irq(struct ufs_hba *hba);
 int ufshcd_alloc_host(struct device *, struct ufs_hba **);
 void ufshcd_dealloc_host(struct ufs_hba *);
 int ufshcd_hba_enable(struct ufs_hba *hba);
-- 
cgit v1.2.3


From 6bf999e0eb41850d5c857102535d5c53b2ede224 Mon Sep 17 00:00:00 2001
From: Bean Huo <beanhuo@micron.com>
Date: Tue, 12 Dec 2023 23:08:24 +0100
Subject: scsi: ufs: core: Add UFS RTC support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add Real Time Clock (RTC) support for UFS device. This enhancement is
crucial for the internal maintenance operations of the UFS device. The
patch enables the device to handle both absolute and relative time
information. Furthermore, it includes periodic task to update the RTC in
accordance with the UFS Spec, ensuring the accuracy of RTC information for
the device's internal processes.

RTC and qTimestamp serve distinct purposes. The RTC provides a coarse level
of granularity with, at best, approximate single-second resolution. This
makes the RTC well-suited for the device to determine the approximate age
of programmed blocks after being updated by the host. On the other hand,
qTimestamp offers nanosecond granularity and is specifically designed for
synchronizing Device Error Log entries with corresponding host-side logs.

Given that the RTC has been a standard feature since UFS Spec 2.0, and
qTimestamp was introduced in UFS Spec 4.0, the majority of UFS devices
currently on the market rely on RTC. Therefore, it is advisable to continue
supporting RTC in the Linux kernel. This ensures compatibility with the
prevailing UFS device implementations and facilitates seamless integration
with existing hardware.  By maintaining support for RTC, we ensure broad
compatibility and avoid potential issues arising from deviations in device
specifications across different UFS versions.

Signed-off-by: Bean Huo <beanhuo@micron.com>
Signed-off-by: Mike Bi <mikebi@micron.com>
Signed-off-by: Luca Porzio <lporzio@micron.com>
Link: https://lore.kernel.org/r/20231212220825.85255-3-beanhuo@iokpp.de
Acked-by: Avri Altman <avri.altman@wdc.com>
Reviewed-by: Thomas Weißschuh <linux@weissschuh.net>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 83 +++++++++++++++++++++++++++++++++++++++++++++--
 include/ufs/ufs.h         | 13 ++++++++
 include/ufs/ufshcd.h      |  4 +++
 3 files changed, 98 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index fbe76a872530..99ad9b769048 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -99,6 +99,9 @@
 /* Polling time to wait for fDeviceInit */
 #define FDEVICEINIT_COMPL_TIMEOUT 1500 /* millisecs */
 
+/* Default RTC update every 10 seconds */
+#define UFS_RTC_UPDATE_INTERVAL_MS (10 * MSEC_PER_SEC)
+
 /* UFSHC 4.0 compliant HC support this mode. */
 static bool use_mcq_mode = true;
 
@@ -683,6 +686,8 @@ static void ufshcd_device_reset(struct ufs_hba *hba)
 			hba->dev_info.wb_enabled = false;
 			hba->dev_info.wb_buf_flush_enabled = false;
 		}
+		if (hba->dev_info.rtc_type == UFS_RTC_RELATIVE)
+			hba->dev_info.rtc_time_baseline = 0;
 	}
 	if (err != -EOPNOTSUPP)
 		ufshcd_update_evt_hist(hba, UFS_EVT_DEV_RESET, err);
@@ -8188,6 +8193,72 @@ static void ufs_fixup_device_setup(struct ufs_hba *hba)
 	ufshcd_vops_fixup_dev_quirks(hba);
 }
 
+static void ufshcd_update_rtc(struct ufs_hba *hba)
+{
+	struct timespec64 ts64;
+	int err;
+	u32 val;
+
+	ktime_get_real_ts64(&ts64);
+
+	if (ts64.tv_sec < hba->dev_info.rtc_time_baseline) {
+		dev_warn_once(hba->dev, "%s: Current time precedes previous setting!\n", __func__);
+		return;
+	}
+
+	/*
+	 * The Absolute RTC mode has a 136-year limit, spanning from 2010 to 2146. If a time beyond
+	 * 2146 is required, it is recommended to choose the relative RTC mode.
+	 */
+	val = ts64.tv_sec - hba->dev_info.rtc_time_baseline;
+
+	ufshcd_rpm_get_sync(hba);
+	err = ufshcd_query_attr(hba, UPIU_QUERY_OPCODE_WRITE_ATTR, QUERY_ATTR_IDN_SECONDS_PASSED,
+				0, 0, &val);
+	ufshcd_rpm_put_sync(hba);
+
+	if (err)
+		dev_err(hba->dev, "%s: Failed to update rtc %d\n", __func__, err);
+	else if (hba->dev_info.rtc_type == UFS_RTC_RELATIVE)
+		hba->dev_info.rtc_time_baseline = ts64.tv_sec;
+}
+
+static void ufshcd_rtc_work(struct work_struct *work)
+{
+	struct ufs_hba *hba;
+
+	hba = container_of(to_delayed_work(work), struct ufs_hba, ufs_rtc_update_work);
+
+	 /* Update RTC only when there are no requests in progress and UFSHCI is operational */
+	if (!ufshcd_is_ufs_dev_busy(hba) && hba->ufshcd_state == UFSHCD_STATE_OPERATIONAL)
+		ufshcd_update_rtc(hba);
+
+	if (ufshcd_is_ufs_dev_active(hba))
+		schedule_delayed_work(&hba->ufs_rtc_update_work,
+				      msecs_to_jiffies(UFS_RTC_UPDATE_INTERVAL_MS));
+}
+
+static void ufs_init_rtc(struct ufs_hba *hba, u8 *desc_buf)
+{
+	u16 periodic_rtc_update = get_unaligned_be16(&desc_buf[DEVICE_DESC_PARAM_FRQ_RTC]);
+	struct ufs_dev_info *dev_info = &hba->dev_info;
+
+	if (periodic_rtc_update & UFS_RTC_TIME_BASELINE) {
+		dev_info->rtc_type = UFS_RTC_ABSOLUTE;
+
+		/*
+		 * The concept of measuring time in Linux as the number of seconds elapsed since
+		 * 00:00:00 UTC on January 1, 1970, and UFS ABS RTC is elapsed from January 1st
+		 * 2010 00:00, here we need to adjust ABS baseline.
+		 */
+		dev_info->rtc_time_baseline = mktime64(2010, 1, 1, 0, 0, 0) -
+							mktime64(1970, 1, 1, 0, 0, 0);
+	} else {
+		dev_info->rtc_type = UFS_RTC_RELATIVE;
+		dev_info->rtc_time_baseline = 0;
+	}
+}
+
 static int ufs_get_device_desc(struct ufs_hba *hba)
 {
 	int err;
@@ -8240,6 +8311,8 @@ static int ufs_get_device_desc(struct ufs_hba *hba)
 
 	ufshcd_temp_notif_probe(hba, desc_buf);
 
+	ufs_init_rtc(hba, desc_buf);
+
 	if (hba->ext_iid_sup)
 		ufshcd_ext_iid_probe(hba, desc_buf);
 
@@ -8793,6 +8866,8 @@ static int ufshcd_device_init(struct ufs_hba *hba, bool init_dev_params)
 	ufshcd_force_reset_auto_bkops(hba);
 
 	ufshcd_set_timestamp_attr(hba);
+	schedule_delayed_work(&hba->ufs_rtc_update_work,
+			      msecs_to_jiffies(UFS_RTC_UPDATE_INTERVAL_MS));
 
 	/* Gear up to HS gear if supported */
 	if (hba->max_pwr_info.is_valid) {
@@ -9749,6 +9824,8 @@ vops_suspend:
 	ret = ufshcd_vops_suspend(hba, pm_op, POST_CHANGE);
 	if (ret)
 		goto set_link_active;
+
+	cancel_delayed_work_sync(&hba->ufs_rtc_update_work);
 	goto out;
 
 set_link_active:
@@ -9843,6 +9920,8 @@ static int __ufshcd_wl_resume(struct ufs_hba *hba, enum ufs_pm_op pm_op)
 		if (ret)
 			goto set_old_link_state;
 		ufshcd_set_timestamp_attr(hba);
+		schedule_delayed_work(&hba->ufs_rtc_update_work,
+				      msecs_to_jiffies(UFS_RTC_UPDATE_INTERVAL_MS));
 	}
 
 	if (ufshcd_keep_autobkops_enabled_except_suspend(hba))
@@ -10539,8 +10618,8 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 						UFS_SLEEP_PWR_MODE,
 						UIC_LINK_HIBERN8_STATE);
 
-	INIT_DELAYED_WORK(&hba->rpm_dev_flush_recheck_work,
-			  ufshcd_rpm_dev_flush_recheck_work);
+	INIT_DELAYED_WORK(&hba->rpm_dev_flush_recheck_work, ufshcd_rpm_dev_flush_recheck_work);
+	INIT_DELAYED_WORK(&hba->ufs_rtc_update_work, ufshcd_rtc_work);
 
 	/* Set the default auto-hiberate idle timer value to 150 ms */
 	if (ufshcd_is_auto_hibern8_supported(hba) && !hba->ahit) {
diff --git a/include/ufs/ufs.h b/include/ufs/ufs.h
index e77ab1786856..7e7169d94596 100644
--- a/include/ufs/ufs.h
+++ b/include/ufs/ufs.h
@@ -14,6 +14,7 @@
 #include <linux/bitops.h>
 #include <linux/types.h>
 #include <uapi/scsi/scsi_bsg_ufs.h>
+#include <linux/time64.h>
 
 /*
  * Using static_assert() is not allowed in UAPI header files. Hence the check
@@ -551,6 +552,14 @@ struct ufs_vreg_info {
 	struct ufs_vreg *vdd_hba;
 };
 
+/* UFS device descriptor wPeriodicRTCUpdate bit9 defines RTC time baseline */
+#define UFS_RTC_TIME_BASELINE BIT(9)
+
+enum ufs_rtc_time {
+	UFS_RTC_RELATIVE,
+	UFS_RTC_ABSOLUTE
+};
+
 struct ufs_dev_info {
 	bool	f_power_on_wp_en;
 	/* Keeps information if any of the LU is power on write protected */
@@ -578,6 +587,10 @@ struct ufs_dev_info {
 
 	/* UFS EXT_IID Enable */
 	bool	b_ext_iid_en;
+
+	/* UFS RTC */
+	enum ufs_rtc_time rtc_type;
+	time64_t rtc_time_baseline;
 };
 
 /*
diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h
index 7f0b2c5599cd..7bdda92fcb1c 100644
--- a/include/ufs/ufshcd.h
+++ b/include/ufs/ufshcd.h
@@ -911,6 +911,8 @@ enum ufshcd_mcq_opr {
  * @mcq_base: Multi circular queue registers base address
  * @uhq: array of supported hardware queues
  * @dev_cmd_queue: Queue for issuing device management commands
+ * @mcq_opr: MCQ operation and runtime registers
+ * @ufs_rtc_update_work: A work for UFS RTC periodic update
  */
 struct ufs_hba {
 	void __iomem *mmio_base;
@@ -1071,6 +1073,8 @@ struct ufs_hba {
 	struct ufs_hw_queue *uhq;
 	struct ufs_hw_queue *dev_cmd_queue;
 	struct ufshcd_mcq_opr_info_t mcq_opr[OPR_MAX];
+
+	struct delayed_work ufs_rtc_update_work;
 };
 
 /**
-- 
cgit v1.2.3


From 838f595a567257e3ac0ac33cdb6bb644ca326cc1 Mon Sep 17 00:00:00 2001
From: Bean Huo <beanhuo@micron.com>
Date: Tue, 12 Dec 2023 23:08:25 +0100
Subject: scsi: ufs: core: Add sysfs node for UFS RTC update
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Introduce a sysfs node named 'rtc_update_ms' within the kernel, enabling
user to adjust the RTC periodic update frequency to suit the specific
requirements of the system and UFS. Also, this patch allows the user to
disable/enable periodic update RTC in the UFS idle time.

Signed-off-by: Bean Huo <beanhuo@micron.com>
Link: https://lore.kernel.org/r/20231212220825.85255-4-beanhuo@iokpp.de
Acked-by: Avri Altman <avri.altman@wdc.com>
Reviewed-by: Thomas Weißschuh <linux@weissschuh.net>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 Documentation/ABI/testing/sysfs-driver-ufs |  7 +++++++
 drivers/ufs/core/ufs-sysfs.c               | 31 ++++++++++++++++++++++++++++++
 drivers/ufs/core/ufshcd.c                  | 11 +++++++++--
 include/ufs/ufs.h                          |  1 +
 4 files changed, 48 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/Documentation/ABI/testing/sysfs-driver-ufs b/Documentation/ABI/testing/sysfs-driver-ufs
index 0c7efaf62de0..ef1e27584fff 100644
--- a/Documentation/ABI/testing/sysfs-driver-ufs
+++ b/Documentation/ABI/testing/sysfs-driver-ufs
@@ -1474,3 +1474,10 @@ Description:	Indicates status of Write Booster.
 
 		The file is read only.
 
+What:		/sys/bus/platform/drivers/ufshcd/*/rtc_update_ms
+What:		/sys/bus/platform/devices/*.ufs/rtc_update_ms
+Date:		November 2023
+Contact:	Bean Huo <beanhuo@micron.com>
+Description:
+		rtc_update_ms indicates how often the host should synchronize or update the
+		UFS RTC. If set to 0, this will disable UFS RTC periodic update.
diff --git a/drivers/ufs/core/ufs-sysfs.c b/drivers/ufs/core/ufs-sysfs.c
index c95906443d5f..4ead1e3bdb12 100644
--- a/drivers/ufs/core/ufs-sysfs.c
+++ b/drivers/ufs/core/ufs-sysfs.c
@@ -255,6 +255,35 @@ out:
 	return res < 0 ? res : count;
 }
 
+static ssize_t rtc_update_ms_show(struct device *dev, struct device_attribute *attr,
+				  char *buf)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "%d\n", hba->dev_info.rtc_update_period);
+}
+
+static ssize_t rtc_update_ms_store(struct device *dev, struct device_attribute *attr,
+				   const char *buf, size_t count)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+	unsigned int ms;
+	bool resume_period_update = false;
+
+	if (kstrtouint(buf, 0, &ms))
+		return -EINVAL;
+
+	if (!hba->dev_info.rtc_update_period && ms > 0)
+		resume_period_update =  true;
+	/* Minimum and maximum update frequency should be synchronized with all UFS vendors */
+	hba->dev_info.rtc_update_period = ms;
+
+	if (resume_period_update)
+		schedule_delayed_work(&hba->ufs_rtc_update_work,
+				      msecs_to_jiffies(hba->dev_info.rtc_update_period));
+	return count;
+}
+
 static ssize_t enable_wb_buf_flush_show(struct device *dev,
 				    struct device_attribute *attr,
 				    char *buf)
@@ -339,6 +368,7 @@ static DEVICE_ATTR_RW(auto_hibern8);
 static DEVICE_ATTR_RW(wb_on);
 static DEVICE_ATTR_RW(enable_wb_buf_flush);
 static DEVICE_ATTR_RW(wb_flush_threshold);
+static DEVICE_ATTR_RW(rtc_update_ms);
 
 static struct attribute *ufs_sysfs_ufshcd_attrs[] = {
 	&dev_attr_rpm_lvl.attr,
@@ -351,6 +381,7 @@ static struct attribute *ufs_sysfs_ufshcd_attrs[] = {
 	&dev_attr_wb_on.attr,
 	&dev_attr_enable_wb_buf_flush.attr,
 	&dev_attr_wb_flush_threshold.attr,
+	&dev_attr_rtc_update_ms.attr,
 	NULL
 };
 
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 99ad9b769048..5c4ef4b072c3 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -8233,9 +8233,9 @@ static void ufshcd_rtc_work(struct work_struct *work)
 	if (!ufshcd_is_ufs_dev_busy(hba) && hba->ufshcd_state == UFSHCD_STATE_OPERATIONAL)
 		ufshcd_update_rtc(hba);
 
-	if (ufshcd_is_ufs_dev_active(hba))
+	if (ufshcd_is_ufs_dev_active(hba) && hba->dev_info.rtc_update_period)
 		schedule_delayed_work(&hba->ufs_rtc_update_work,
-				      msecs_to_jiffies(UFS_RTC_UPDATE_INTERVAL_MS));
+				      msecs_to_jiffies(hba->dev_info.rtc_update_period));
 }
 
 static void ufs_init_rtc(struct ufs_hba *hba, u8 *desc_buf)
@@ -8257,6 +8257,13 @@ static void ufs_init_rtc(struct ufs_hba *hba, u8 *desc_buf)
 		dev_info->rtc_type = UFS_RTC_RELATIVE;
 		dev_info->rtc_time_baseline = 0;
 	}
+
+	/*
+	 * We ignore TIME_PERIOD defined in wPeriodicRTCUpdate because Spec does not clearly state
+	 * how to calculate the specific update period for each time unit. And we disable periodic
+	 * RTC update work, let user configure by sysfs node according to specific circumstance.
+	 */
+	dev_info->rtc_update_period = 0;
 }
 
 static int ufs_get_device_desc(struct ufs_hba *hba)
diff --git a/include/ufs/ufs.h b/include/ufs/ufs.h
index 7e7169d94596..b6003749bc83 100644
--- a/include/ufs/ufs.h
+++ b/include/ufs/ufs.h
@@ -591,6 +591,7 @@ struct ufs_dev_info {
 	/* UFS RTC */
 	enum ufs_rtc_time rtc_type;
 	time64_t rtc_time_baseline;
+	u32 rtc_update_period;
 };
 
 /*
-- 
cgit v1.2.3


From 6caa290684255991ffeebf228b2fd9e7e4da8f34 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Tue, 12 Dec 2023 23:02:56 -0800
Subject: Input: navpoint - convert to use GPIO descriptor

The Navpoint driver uses a GPIO line, convert this to use
a GPIO descriptor. There are no in-kernel users but out of tree
users can easily be added or converted using a GPIO descriptor
table as with numerous other drivers.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231129-descriptors-input-v1-1-9433162914a3@linaro.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/mouse/navpoint.c | 41 +++++++++++++++--------------------------
 include/linux/input/navpoint.h |  1 -
 2 files changed, 15 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/drivers/input/mouse/navpoint.c b/drivers/input/mouse/navpoint.c
index c00dc1275da2..ba757783c258 100644
--- a/drivers/input/mouse/navpoint.c
+++ b/drivers/input/mouse/navpoint.c
@@ -10,7 +10,7 @@
 #include <linux/platform_device.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/input.h>
 #include <linux/input/navpoint.h>
 #include <linux/interrupt.h>
@@ -32,7 +32,7 @@ struct navpoint {
 	struct ssp_device	*ssp;
 	struct input_dev	*input;
 	struct device		*dev;
-	int			gpio;
+	struct gpio_desc	*gpiod;
 	int			index;
 	u8			data[1 + HEADER_LENGTH(0xff)];
 };
@@ -170,16 +170,14 @@ static void navpoint_up(struct navpoint *navpoint)
 		dev_err(navpoint->dev,
 			"timeout waiting for SSSR[CSS] to clear\n");
 
-	if (gpio_is_valid(navpoint->gpio))
-		gpio_set_value(navpoint->gpio, 1);
+	gpiod_set_value(navpoint->gpiod, 1);
 }
 
 static void navpoint_down(struct navpoint *navpoint)
 {
 	struct ssp_device *ssp = navpoint->ssp;
 
-	if (gpio_is_valid(navpoint->gpio))
-		gpio_set_value(navpoint->gpio, 0);
+	gpiod_set_value(navpoint->gpiod, 0);
 
 	pxa_ssp_write_reg(ssp, SSCR0, 0);
 
@@ -216,18 +214,9 @@ static int navpoint_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
-	if (gpio_is_valid(pdata->gpio)) {
-		error = gpio_request_one(pdata->gpio, GPIOF_OUT_INIT_LOW,
-					 "SYNAPTICS_ON");
-		if (error)
-			return error;
-	}
-
 	ssp = pxa_ssp_request(pdata->port, pdev->name);
-	if (!ssp) {
-		error = -ENODEV;
-		goto err_free_gpio;
-	}
+	if (!ssp)
+		return -ENODEV;
 
 	/* HaRET does not disable devices before jumping into Linux */
 	if (pxa_ssp_read_reg(ssp, SSCR0) & SSCR0_SSE) {
@@ -242,10 +231,18 @@ static int navpoint_probe(struct platform_device *pdev)
 		goto err_free_mem;
 	}
 
+	navpoint->gpiod = gpiod_get_optional(&pdev->dev,
+					     NULL, GPIOD_OUT_LOW);
+	if (IS_ERR(navpoint->gpiod)) {
+		error = PTR_ERR(navpoint->gpiod);
+		dev_err(&pdev->dev, "error getting GPIO\n");
+		goto err_free_mem;
+	}
+	gpiod_set_consumer_name(navpoint->gpiod, "SYNAPTICS_ON");
+
 	navpoint->ssp = ssp;
 	navpoint->input = input;
 	navpoint->dev = &pdev->dev;
-	navpoint->gpio = pdata->gpio;
 
 	input->name = pdev->name;
 	input->dev.parent = &pdev->dev;
@@ -288,17 +285,12 @@ err_free_mem:
 	input_free_device(input);
 	kfree(navpoint);
 	pxa_ssp_free(ssp);
-err_free_gpio:
-	if (gpio_is_valid(pdata->gpio))
-		gpio_free(pdata->gpio);
 
 	return error;
 }
 
 static void navpoint_remove(struct platform_device *pdev)
 {
-	const struct navpoint_platform_data *pdata =
-					dev_get_platdata(&pdev->dev);
 	struct navpoint *navpoint = platform_get_drvdata(pdev);
 	struct ssp_device *ssp = navpoint->ssp;
 
@@ -308,9 +300,6 @@ static void navpoint_remove(struct platform_device *pdev)
 	kfree(navpoint);
 
 	pxa_ssp_free(ssp);
-
-	if (gpio_is_valid(pdata->gpio))
-		gpio_free(pdata->gpio);
 }
 
 static int navpoint_suspend(struct device *dev)
diff --git a/include/linux/input/navpoint.h b/include/linux/input/navpoint.h
index d464ffb4db52..5192ae3f5ec1 100644
--- a/include/linux/input/navpoint.h
+++ b/include/linux/input/navpoint.h
@@ -5,5 +5,4 @@
 
 struct navpoint_platform_data {
 	int		port;		/* PXA SSP port for pxa_ssp_request() */
-	int		gpio;		/* GPIO for power on/off */
 };
-- 
cgit v1.2.3


From e53c18da99c75f080bd99436c57824f2ab657f03 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Tue, 12 Dec 2023 23:06:55 -0800
Subject: Input: omap-keypad - drop optional GPIO support

The driver supports passing some GPIO lines for rows and columns
through the driver data, but there is no in-kernel user of this.

Further the use seems convoluted because the GPIO lines are unused
in the driver, then explicitly free:ed when removing it without
being requested when probing it, which is assymetric and just
a recepie for disaster.

Remove the support for these unused GPIOs, if need be support can
be reestablished in an organized fashion using GPIO descriptors.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Tony Lindgren <tony@atomide.com>
Link: https://lore.kernel.org/r/20231129-descriptors-input-v1-3-9433162914a3@linaro.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/omap-keypad.c      | 19 +------------------
 include/linux/platform_data/keypad-omap.h |  3 ---
 2 files changed, 1 insertion(+), 21 deletions(-)

(limited to 'include')

diff --git a/drivers/input/keyboard/omap-keypad.c b/drivers/input/keyboard/omap-keypad.c
index 454fb8675657..16f936db7305 100644
--- a/drivers/input/keyboard/omap-keypad.c
+++ b/drivers/input/keyboard/omap-keypad.c
@@ -21,7 +21,6 @@
 #include <linux/mutex.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
-#include <linux/gpio.h>
 #include <linux/platform_data/gpio-omap.h>
 #include <linux/platform_data/keypad-omap.h>
 #include <linux/soc/ti/omap1-io.h>
@@ -49,9 +48,6 @@ struct omap_kp {
 
 static DECLARE_TASKLET_DISABLED_OLD(kp_tasklet, omap_kp_tasklet);
 
-static unsigned int *row_gpios;
-static unsigned int *col_gpios;
-
 static irqreturn_t omap_kp_interrupt(int irq, void *dev_id)
 {
 	/* disable keyboard interrupt and schedule for handling */
@@ -180,7 +176,7 @@ static int omap_kp_probe(struct platform_device *pdev)
 	struct omap_kp *omap_kp;
 	struct input_dev *input_dev;
 	struct omap_kp_platform_data *pdata = dev_get_platdata(&pdev->dev);
-	int i, col_idx, row_idx, ret;
+	int ret;
 	unsigned int row_shift, keycodemax;
 
 	if (!pdata->rows || !pdata->cols || !pdata->keymap_data) {
@@ -209,17 +205,9 @@ static int omap_kp_probe(struct platform_device *pdev)
 	if (pdata->delay)
 		omap_kp->delay = pdata->delay;
 
-	if (pdata->row_gpios && pdata->col_gpios) {
-		row_gpios = pdata->row_gpios;
-		col_gpios = pdata->col_gpios;
-	}
-
 	omap_kp->rows = pdata->rows;
 	omap_kp->cols = pdata->cols;
 
-	col_idx = 0;
-	row_idx = 0;
-
 	timer_setup(&omap_kp->timer, omap_kp_timer, 0);
 
 	/* get the irq and init timer*/
@@ -276,11 +264,6 @@ err4:
 err3:
 	device_remove_file(&pdev->dev, &dev_attr_enable);
 err2:
-	for (i = row_idx - 1; i >= 0; i--)
-		gpio_free(row_gpios[i]);
-	for (i = col_idx - 1; i >= 0; i--)
-		gpio_free(col_gpios[i]);
-
 	kfree(omap_kp);
 	input_free_device(input_dev);
 
diff --git a/include/linux/platform_data/keypad-omap.h b/include/linux/platform_data/keypad-omap.h
index 3e7c64c854f4..f3f1311cdf3a 100644
--- a/include/linux/platform_data/keypad-omap.h
+++ b/include/linux/platform_data/keypad-omap.h
@@ -19,9 +19,6 @@ struct omap_kp_platform_data {
 	bool rep;
 	unsigned long delay;
 	bool dbounce;
-	/* specific to OMAP242x*/
-	unsigned int *row_gpios;
-	unsigned int *col_gpios;
 };
 
 /* Group (0..3) -- when multiple keys are pressed, only the
-- 
cgit v1.2.3


From 7395de647e87476f5b5d2f9a9fe80cee86b4e7cc Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Tue, 12 Dec 2023 23:04:47 -0800
Subject: Input: as5011 - convert to GPIO descriptor

This driver does not have any in-tree users but is passing a
legacy GPIO number through platform data.

Convert it to use a GPIO descriptor, new users or outoftree
users can easily be implemented using GPIO descriptor tables
or software nodes.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231129-descriptors-input-v1-4-9433162914a3@linaro.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/joystick/as5011.c | 24 +++++++++++-------------
 include/linux/input/as5011.h    |  1 -
 2 files changed, 11 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/input/joystick/as5011.c b/drivers/input/joystick/as5011.c
index bf8b1cc0ea9c..f1822c19a289 100644
--- a/drivers/input/joystick/as5011.c
+++ b/drivers/input/joystick/as5011.c
@@ -13,7 +13,7 @@
 #include <linux/i2c.h>
 #include <linux/interrupt.h>
 #include <linux/input.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/delay.h>
 #include <linux/input/as5011.h>
 #include <linux/slab.h>
@@ -61,7 +61,7 @@ MODULE_LICENSE("GPL");
 struct as5011_device {
 	struct input_dev *input_dev;
 	struct i2c_client *i2c_client;
-	unsigned int button_gpio;
+	struct gpio_desc *button_gpiod;
 	unsigned int button_irq;
 	unsigned int axis_irq;
 };
@@ -114,7 +114,7 @@ static int as5011_i2c_read(struct i2c_client *client,
 static irqreturn_t as5011_button_interrupt(int irq, void *dev_id)
 {
 	struct as5011_device *as5011 = dev_id;
-	int val = gpio_get_value_cansleep(as5011->button_gpio);
+	int val = gpiod_get_value_cansleep(as5011->button_gpiod);
 
 	input_report_key(as5011->input_dev, BTN_JOYSTICK, !val);
 	input_sync(as5011->input_dev);
@@ -248,7 +248,6 @@ static int as5011_probe(struct i2c_client *client)
 
 	as5011->i2c_client = client;
 	as5011->input_dev = input_dev;
-	as5011->button_gpio = plat_data->button_gpio;
 	as5011->axis_irq = plat_data->axis_irq;
 
 	input_dev->name = "Austria Microsystem as5011 joystick";
@@ -262,18 +261,20 @@ static int as5011_probe(struct i2c_client *client)
 	input_set_abs_params(as5011->input_dev, ABS_Y,
 		AS5011_MIN_AXIS, AS5011_MAX_AXIS, AS5011_FUZZ, AS5011_FLAT);
 
-	error = gpio_request(as5011->button_gpio, "AS5011 button");
-	if (error < 0) {
-		dev_err(&client->dev, "Failed to request button gpio\n");
+	as5011->button_gpiod = devm_gpiod_get(&client->dev, NULL, GPIOD_IN);
+	if (IS_ERR(as5011->button_gpiod)) {
+		error = PTR_ERR(as5011->button_gpiod);
+		dev_err(&client->dev, "Failed to request button GPIO\n");
 		goto err_free_mem;
 	}
+	gpiod_set_consumer_name(as5011->button_gpiod, "AS5011 button");
 
-	irq = gpio_to_irq(as5011->button_gpio);
+	irq = gpiod_to_irq(as5011->button_gpiod);
 	if (irq < 0) {
 		dev_err(&client->dev,
 			"Failed to get irq number for button gpio\n");
 		error = irq;
-		goto err_free_button_gpio;
+		goto err_free_mem;
 	}
 
 	as5011->button_irq = irq;
@@ -286,7 +287,7 @@ static int as5011_probe(struct i2c_client *client)
 	if (error < 0) {
 		dev_err(&client->dev,
 			"Can't allocate button irq %d\n", as5011->button_irq);
-		goto err_free_button_gpio;
+		goto err_free_mem;
 	}
 
 	error = as5011_configure_chip(as5011, plat_data);
@@ -317,8 +318,6 @@ err_free_axis_irq:
 	free_irq(as5011->axis_irq, as5011);
 err_free_button_irq:
 	free_irq(as5011->button_irq, as5011);
-err_free_button_gpio:
-	gpio_free(as5011->button_gpio);
 err_free_mem:
 	input_free_device(input_dev);
 	kfree(as5011);
@@ -332,7 +331,6 @@ static void as5011_remove(struct i2c_client *client)
 
 	free_irq(as5011->axis_irq, as5011);
 	free_irq(as5011->button_irq, as5011);
-	gpio_free(as5011->button_gpio);
 
 	input_unregister_device(as5011->input_dev);
 	kfree(as5011);
diff --git a/include/linux/input/as5011.h b/include/linux/input/as5011.h
index 5fba52a56cd6..5705d5de3aea 100644
--- a/include/linux/input/as5011.h
+++ b/include/linux/input/as5011.h
@@ -7,7 +7,6 @@
  */
 
 struct as5011_platform_data {
-	unsigned int button_gpio;
 	unsigned int axis_irq; /* irq number */
 	unsigned long axis_irqflags;
 	char xp, xn; /* threshold for x axis */
-- 
cgit v1.2.3


From 6ab3d50b106c9aea123a80551a6c9deace83b914 Mon Sep 17 00:00:00 2001
From: Qiang Yu <quic_qianyu@quicinc.com>
Date: Tue, 7 Nov 2023 16:14:49 +0800
Subject: bus: mhi: host: Add a separate timeout parameter for waiting ready

Some devices(eg. SDX75) take longer than expected (default, 8 seconds) to
set ready after reboot. Hence add optional ready timeout parameter and pass
the appropriate timeout value to mhi_poll_reg_field() to wait enough for
device ready as part of power up sequence.

Signed-off-by: Qiang Yu <quic_qianyu@quicinc.com>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/1699344890-87076-2-git-send-email-quic_qianyu@quicinc.com
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/bus/mhi/host/init.c     |  1 +
 drivers/bus/mhi/host/internal.h |  2 +-
 drivers/bus/mhi/host/main.c     |  5 +++--
 drivers/bus/mhi/host/pm.c       | 24 +++++++++++++++++-------
 include/linux/mhi.h             |  4 ++++
 5 files changed, 26 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/bus/mhi/host/init.c b/drivers/bus/mhi/host/init.c
index f78aefd2d7a3..65ceac1837f9 100644
--- a/drivers/bus/mhi/host/init.c
+++ b/drivers/bus/mhi/host/init.c
@@ -881,6 +881,7 @@ static int parse_config(struct mhi_controller *mhi_cntrl,
 	if (!mhi_cntrl->timeout_ms)
 		mhi_cntrl->timeout_ms = MHI_TIMEOUT_MS;
 
+	mhi_cntrl->ready_timeout_ms = config->ready_timeout_ms;
 	mhi_cntrl->bounce_buf = config->use_bounce_buf;
 	mhi_cntrl->buffer_len = config->buf_len;
 	if (!mhi_cntrl->buffer_len)
diff --git a/drivers/bus/mhi/host/internal.h b/drivers/bus/mhi/host/internal.h
index 2e139e76de4c..30ac415a3000 100644
--- a/drivers/bus/mhi/host/internal.h
+++ b/drivers/bus/mhi/host/internal.h
@@ -321,7 +321,7 @@ int __must_check mhi_read_reg_field(struct mhi_controller *mhi_cntrl,
 				    u32 *out);
 int __must_check mhi_poll_reg_field(struct mhi_controller *mhi_cntrl,
 				    void __iomem *base, u32 offset, u32 mask,
-				    u32 val, u32 delayus);
+				    u32 val, u32 delayus, u32 timeout_ms);
 void mhi_write_reg(struct mhi_controller *mhi_cntrl, void __iomem *base,
 		   u32 offset, u32 val);
 int __must_check mhi_write_reg_field(struct mhi_controller *mhi_cntrl,
diff --git a/drivers/bus/mhi/host/main.c b/drivers/bus/mhi/host/main.c
index dcf627b36e82..6cf11457380b 100644
--- a/drivers/bus/mhi/host/main.c
+++ b/drivers/bus/mhi/host/main.c
@@ -40,10 +40,11 @@ int __must_check mhi_read_reg_field(struct mhi_controller *mhi_cntrl,
 
 int __must_check mhi_poll_reg_field(struct mhi_controller *mhi_cntrl,
 				    void __iomem *base, u32 offset,
-				    u32 mask, u32 val, u32 delayus)
+				    u32 mask, u32 val, u32 delayus,
+				    u32 timeout_ms)
 {
 	int ret;
-	u32 out, retry = (mhi_cntrl->timeout_ms * 1000) / delayus;
+	u32 out, retry = (timeout_ms * 1000) / delayus;
 
 	while (retry--) {
 		ret = mhi_read_reg_field(mhi_cntrl, base, offset, mask, &out);
diff --git a/drivers/bus/mhi/host/pm.c b/drivers/bus/mhi/host/pm.c
index 8a4362d75fc4..a2f2feef1476 100644
--- a/drivers/bus/mhi/host/pm.c
+++ b/drivers/bus/mhi/host/pm.c
@@ -163,6 +163,7 @@ int mhi_ready_state_transition(struct mhi_controller *mhi_cntrl)
 	enum mhi_pm_state cur_state;
 	struct device *dev = &mhi_cntrl->mhi_dev->dev;
 	u32 interval_us = 25000; /* poll register field every 25 milliseconds */
+	u32 timeout_ms;
 	int ret, i;
 
 	/* Check if device entered error state */
@@ -173,14 +174,18 @@ int mhi_ready_state_transition(struct mhi_controller *mhi_cntrl)
 
 	/* Wait for RESET to be cleared and READY bit to be set by the device */
 	ret = mhi_poll_reg_field(mhi_cntrl, mhi_cntrl->regs, MHICTRL,
-				 MHICTRL_RESET_MASK, 0, interval_us);
+				 MHICTRL_RESET_MASK, 0, interval_us,
+				 mhi_cntrl->timeout_ms);
 	if (ret) {
 		dev_err(dev, "Device failed to clear MHI Reset\n");
 		return ret;
 	}
 
+	timeout_ms = mhi_cntrl->ready_timeout_ms ?
+		mhi_cntrl->ready_timeout_ms : mhi_cntrl->timeout_ms;
 	ret = mhi_poll_reg_field(mhi_cntrl, mhi_cntrl->regs, MHISTATUS,
-				 MHISTATUS_READY_MASK, 1, interval_us);
+				 MHISTATUS_READY_MASK, 1, interval_us,
+				 timeout_ms);
 	if (ret) {
 		dev_err(dev, "Device failed to enter MHI Ready\n");
 		return ret;
@@ -479,7 +484,7 @@ static void mhi_pm_disable_transition(struct mhi_controller *mhi_cntrl)
 
 		/* Wait for the reset bit to be cleared by the device */
 		ret = mhi_poll_reg_field(mhi_cntrl, mhi_cntrl->regs, MHICTRL,
-				 MHICTRL_RESET_MASK, 0, 25000);
+				 MHICTRL_RESET_MASK, 0, 25000, mhi_cntrl->timeout_ms);
 		if (ret)
 			dev_err(dev, "Device failed to clear MHI Reset\n");
 
@@ -492,8 +497,8 @@ static void mhi_pm_disable_transition(struct mhi_controller *mhi_cntrl)
 		if (!MHI_IN_PBL(mhi_get_exec_env(mhi_cntrl))) {
 			/* wait for ready to be set */
 			ret = mhi_poll_reg_field(mhi_cntrl, mhi_cntrl->regs,
-						 MHISTATUS,
-						 MHISTATUS_READY_MASK, 1, 25000);
+						 MHISTATUS, MHISTATUS_READY_MASK,
+						 1, 25000, mhi_cntrl->timeout_ms);
 			if (ret)
 				dev_err(dev, "Device failed to enter READY state\n");
 		}
@@ -1111,7 +1116,8 @@ int mhi_async_power_up(struct mhi_controller *mhi_cntrl)
 	if (state == MHI_STATE_SYS_ERR) {
 		mhi_set_mhi_state(mhi_cntrl, MHI_STATE_RESET);
 		ret = mhi_poll_reg_field(mhi_cntrl, mhi_cntrl->regs, MHICTRL,
-				 MHICTRL_RESET_MASK, 0, interval_us);
+				 MHICTRL_RESET_MASK, 0, interval_us,
+				 mhi_cntrl->timeout_ms);
 		if (ret) {
 			dev_info(dev, "Failed to reset MHI due to syserr state\n");
 			goto error_exit;
@@ -1202,14 +1208,18 @@ EXPORT_SYMBOL_GPL(mhi_power_down);
 int mhi_sync_power_up(struct mhi_controller *mhi_cntrl)
 {
 	int ret = mhi_async_power_up(mhi_cntrl);
+	u32 timeout_ms;
 
 	if (ret)
 		return ret;
 
+	/* Some devices need more time to set ready during power up */
+	timeout_ms = mhi_cntrl->ready_timeout_ms ?
+		mhi_cntrl->ready_timeout_ms : mhi_cntrl->timeout_ms;
 	wait_event_timeout(mhi_cntrl->state_event,
 			   MHI_IN_MISSION_MODE(mhi_cntrl->ee) ||
 			   MHI_PM_IN_ERROR_STATE(mhi_cntrl->pm_state),
-			   msecs_to_jiffies(mhi_cntrl->timeout_ms));
+			   msecs_to_jiffies(timeout_ms));
 
 	ret = (MHI_IN_MISSION_MODE(mhi_cntrl->ee)) ? 0 : -ETIMEDOUT;
 	if (ret)
diff --git a/include/linux/mhi.h b/include/linux/mhi.h
index 039943ec4d4e..d0f9b522f328 100644
--- a/include/linux/mhi.h
+++ b/include/linux/mhi.h
@@ -266,6 +266,7 @@ struct mhi_event_config {
  * struct mhi_controller_config - Root MHI controller configuration
  * @max_channels: Maximum number of channels supported
  * @timeout_ms: Timeout value for operations. 0 means use default
+ * @ready_timeout_ms: Timeout value for waiting device to be ready (optional)
  * @buf_len: Size of automatically allocated buffers. 0 means use default
  * @num_channels: Number of channels defined in @ch_cfg
  * @ch_cfg: Array of defined channels
@@ -277,6 +278,7 @@ struct mhi_event_config {
 struct mhi_controller_config {
 	u32 max_channels;
 	u32 timeout_ms;
+	u32 ready_timeout_ms;
 	u32 buf_len;
 	u32 num_channels;
 	const struct mhi_channel_config *ch_cfg;
@@ -330,6 +332,7 @@ struct mhi_controller_config {
  * @pm_mutex: Mutex for suspend/resume operation
  * @pm_lock: Lock for protecting MHI power management state
  * @timeout_ms: Timeout in ms for state transitions
+ * @ready_timeout_ms: Timeout in ms for waiting device to be ready (optional)
  * @pm_state: MHI power management state
  * @db_access: DB access states
  * @ee: MHI device execution environment
@@ -419,6 +422,7 @@ struct mhi_controller {
 	struct mutex pm_mutex;
 	rwlock_t pm_lock;
 	u32 timeout_ms;
+	u32 ready_timeout_ms;
 	u32 pm_state;
 	u32 db_access;
 	enum mhi_ee_type ee;
-- 
cgit v1.2.3


From fb6e30a72539ce28c1323aef4190d35aac106f6f Mon Sep 17 00:00:00 2001
From: Ahmed Zaki <ahmed.zaki@intel.com>
Date: Tue, 12 Dec 2023 17:33:14 -0700
Subject: net: ethtool: pass a pointer to parameters to get/set_rxfh ethtool
 ops

The get/set_rxfh ethtool ops currently takes the rxfh (RSS) parameters
as direct function arguments. This will force us to change the API (and
all drivers' functions) every time some new parameters are added.

This is part 1/2 of the fix, as suggested in [1]:

- First simplify the code by always providing a pointer to all params
   (indir, key and func); the fact that some of them may be NULL seems
   like a weird historic thing or a premature optimization.
   It will simplify the drivers if all pointers are always present.

 - Then make the functions take a dev pointer, and a pointer to a
   single struct wrapping all arguments. The set_* should also take
   an extack.

Link: https://lore.kernel.org/netdev/20231121152906.2dd5f487@kernel.org/ [1]
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Suggested-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
Link: https://lore.kernel.org/r/20231213003321.605376-2-ahmed.zaki@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/amazon/ena/ena_ethtool.c      |  28 ++---
 drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c       |  33 +++---
 .../net/ethernet/aquantia/atlantic/aq_ethtool.c    |  31 ++---
 .../net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c    |  25 ++--
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c  |  28 ++---
 drivers/net/ethernet/broadcom/tg3.c                |  22 ++--
 .../net/ethernet/cavium/thunder/nicvf_ethtool.c    |  31 ++---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c |  24 ++--
 drivers/net/ethernet/cisco/enic/enic_ethtool.c     |  25 ++--
 drivers/net/ethernet/emulex/benet/be_ethtool.c     |  28 ++---
 .../net/ethernet/freescale/enetc/enetc_ethtool.c   |  31 ++---
 .../net/ethernet/fungible/funeth/funeth_ethtool.c  |  40 +++----
 drivers/net/ethernet/hisilicon/hns/hns_ethtool.c   |  17 +--
 drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c |  23 ++--
 drivers/net/ethernet/huawei/hinic/hinic_ethtool.c  |  40 +++----
 drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c   |  26 +++--
 drivers/net/ethernet/intel/i40e/i40e_ethtool.c     |  38 +++----
 drivers/net/ethernet/intel/iavf/iavf_ethtool.c     |  42 ++++---
 drivers/net/ethernet/intel/ice/ice_ethtool.c       |  44 ++++---
 drivers/net/ethernet/intel/idpf/idpf_ethtool.c     |  40 ++++---
 drivers/net/ethernet/intel/igb/igb_ethtool.c       |  27 ++---
 drivers/net/ethernet/intel/igc/igc_ethtool.c       |  27 ++---
 drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c   |  35 +++---
 drivers/net/ethernet/intel/ixgbevf/ethtool.c       |  27 ++---
 drivers/net/ethernet/marvell/mvneta.c              |  25 ++--
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c    |  50 ++++----
 .../ethernet/marvell/octeontx2/nic/otx2_ethtool.c  |  41 +++----
 drivers/net/ethernet/mellanox/mlx4/en_ethtool.c    |  40 +++----
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |   6 +-
 .../net/ethernet/mellanox/mlx5/core/en_ethtool.c   |  28 +++--
 drivers/net/ethernet/microchip/lan743x_ethtool.c   |  34 +++---
 drivers/net/ethernet/microsoft/mana/mana_ethtool.c |  33 +++---
 .../net/ethernet/netronome/nfp/nfp_net_ethtool.c   |  38 +++----
 .../net/ethernet/pensando/ionic/ionic_ethtool.c    |  26 +++--
 drivers/net/ethernet/qlogic/qede/qede_ethtool.c    |  32 +++---
 drivers/net/ethernet/sfc/ethtool_common.c          |  53 +++++----
 drivers/net/ethernet/sfc/ethtool_common.h          |  17 +--
 drivers/net/ethernet/sfc/falcon/ethtool.c          |  26 +++--
 drivers/net/ethernet/sfc/siena/ethtool_common.c    |  53 +++++----
 drivers/net/ethernet/sfc/siena/ethtool_common.h    |  17 +--
 .../net/ethernet/stmicro/stmmac/stmmac_ethtool.c   |  31 ++---
 drivers/net/hyperv/netvsc_drv.c                    |  32 +++---
 drivers/net/virtio_net.c                           |  29 ++---
 drivers/net/vmxnet3/vmxnet3_ethtool.c              |  22 ++--
 include/linux/ethtool.h                            |  38 +++++--
 net/ethtool/common.c                               |  12 +-
 net/ethtool/ioctl.c                                | 126 +++++++++++----------
 net/ethtool/rss.c                                  |  16 +--
 48 files changed, 827 insertions(+), 730 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
index e3ef081aa42b..2d8c5a2841b8 100644
--- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c
+++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
@@ -802,15 +802,15 @@ static int ena_indirection_table_get(struct ena_adapter *adapter, u32 *indir)
 	return rc;
 }
 
-static int ena_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
-			u8 *hfunc)
+static int ena_get_rxfh(struct net_device *netdev,
+			struct ethtool_rxfh_param *rxfh)
 {
 	struct ena_adapter *adapter = netdev_priv(netdev);
 	enum ena_admin_hash_functions ena_func;
 	u8 func;
 	int rc;
 
-	rc = ena_indirection_table_get(adapter, indir);
+	rc = ena_indirection_table_get(adapter, rxfh->indir);
 	if (rc)
 		return rc;
 
@@ -825,7 +825,7 @@ static int ena_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 		return rc;
 	}
 
-	rc = ena_com_get_hash_key(adapter->ena_dev, key);
+	rc = ena_com_get_hash_key(adapter->ena_dev, rxfh->key);
 	if (rc)
 		return rc;
 
@@ -842,27 +842,27 @@ static int ena_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 		return -EOPNOTSUPP;
 	}
 
-	if (hfunc)
-		*hfunc = func;
+	rxfh->hfunc = func;
 
 	return 0;
 }
 
-static int ena_set_rxfh(struct net_device *netdev, const u32 *indir,
-			const u8 *key, const u8 hfunc)
+static int ena_set_rxfh(struct net_device *netdev,
+			struct ethtool_rxfh_param *rxfh,
+			struct netlink_ext_ack *extack)
 {
 	struct ena_adapter *adapter = netdev_priv(netdev);
 	struct ena_com_dev *ena_dev = adapter->ena_dev;
 	enum ena_admin_hash_functions func = 0;
 	int rc;
 
-	if (indir) {
-		rc = ena_indirection_table_set(adapter, indir);
+	if (rxfh->indir) {
+		rc = ena_indirection_table_set(adapter, rxfh->indir);
 		if (rc)
 			return rc;
 	}
 
-	switch (hfunc) {
+	switch (rxfh->hfunc) {
 	case ETH_RSS_HASH_NO_CHANGE:
 		func = ena_com_get_current_hash_function(ena_dev);
 		break;
@@ -874,12 +874,12 @@ static int ena_set_rxfh(struct net_device *netdev, const u32 *indir,
 		break;
 	default:
 		netif_err(adapter, drv, netdev, "Unsupported hfunc %d\n",
-			  hfunc);
+			  rxfh->hfunc);
 		return -EOPNOTSUPP;
 	}
 
-	if (key || func) {
-		rc = ena_com_fill_hash_function(ena_dev, func, key,
+	if (rxfh->key || func) {
+		rc = ena_com_fill_hash_function(ena_dev, func, rxfh->key,
 						ENA_HASH_KEY_SIZE,
 						0xFFFFFFFF);
 		if (unlikely(rc)) {
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c
index 32fab5e77246..58e7e88aae5b 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c
@@ -527,47 +527,48 @@ static u32 xgbe_get_rxfh_indir_size(struct net_device *netdev)
 	return ARRAY_SIZE(pdata->rss_table);
 }
 
-static int xgbe_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
-			 u8 *hfunc)
+static int xgbe_get_rxfh(struct net_device *netdev,
+			 struct ethtool_rxfh_param *rxfh)
 {
 	struct xgbe_prv_data *pdata = netdev_priv(netdev);
 	unsigned int i;
 
-	if (indir) {
+	if (rxfh->indir) {
 		for (i = 0; i < ARRAY_SIZE(pdata->rss_table); i++)
-			indir[i] = XGMAC_GET_BITS(pdata->rss_table[i],
-						  MAC_RSSDR, DMCH);
+			rxfh->indir[i] = XGMAC_GET_BITS(pdata->rss_table[i],
+							MAC_RSSDR, DMCH);
 	}
 
-	if (key)
-		memcpy(key, pdata->rss_key, sizeof(pdata->rss_key));
+	if (rxfh->key)
+		memcpy(rxfh->key, pdata->rss_key, sizeof(pdata->rss_key));
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
 	return 0;
 }
 
-static int xgbe_set_rxfh(struct net_device *netdev, const u32 *indir,
-			 const u8 *key, const u8 hfunc)
+static int xgbe_set_rxfh(struct net_device *netdev,
+			 struct ethtool_rxfh_param *rxfh,
+			 struct netlink_ext_ack *extack)
 {
 	struct xgbe_prv_data *pdata = netdev_priv(netdev);
 	struct xgbe_hw_if *hw_if = &pdata->hw_if;
 	unsigned int ret;
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP) {
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP) {
 		netdev_err(netdev, "unsupported hash function\n");
 		return -EOPNOTSUPP;
 	}
 
-	if (indir) {
-		ret = hw_if->set_rss_lookup_table(pdata, indir);
+	if (rxfh->indir) {
+		ret = hw_if->set_rss_lookup_table(pdata, rxfh->indir);
 		if (ret)
 			return ret;
 	}
 
-	if (key) {
-		ret = hw_if->set_rss_hash_key(pdata, key);
+	if (rxfh->key) {
+		ret = hw_if->set_rss_hash_key(pdata, rxfh->key);
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
index ac4ea93bd8dd..18a6c8d99fa0 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
@@ -447,8 +447,8 @@ static u32 aq_ethtool_get_rss_key_size(struct net_device *ndev)
 	return sizeof(cfg->aq_rss.hash_secret_key);
 }
 
-static int aq_ethtool_get_rss(struct net_device *ndev, u32 *indir, u8 *key,
-			      u8 *hfunc)
+static int aq_ethtool_get_rss(struct net_device *ndev,
+			      struct ethtool_rxfh_param *rxfh)
 {
 	struct aq_nic_s *aq_nic = netdev_priv(ndev);
 	struct aq_nic_cfg_s *cfg;
@@ -456,21 +456,21 @@ static int aq_ethtool_get_rss(struct net_device *ndev, u32 *indir, u8 *key,
 
 	cfg = aq_nic_get_cfg(aq_nic);
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP; /* Toeplitz */
-	if (indir) {
+	rxfh->hfunc = ETH_RSS_HASH_TOP; /* Toeplitz */
+	if (rxfh->indir) {
 		for (i = 0; i < AQ_CFG_RSS_INDIRECTION_TABLE_MAX; i++)
-			indir[i] = cfg->aq_rss.indirection_table[i];
+			rxfh->indir[i] = cfg->aq_rss.indirection_table[i];
 	}
-	if (key)
-		memcpy(key, cfg->aq_rss.hash_secret_key,
+	if (rxfh->key)
+		memcpy(rxfh->key, cfg->aq_rss.hash_secret_key,
 		       sizeof(cfg->aq_rss.hash_secret_key));
 
 	return 0;
 }
 
-static int aq_ethtool_set_rss(struct net_device *netdev, const u32 *indir,
-			      const u8 *key, const u8 hfunc)
+static int aq_ethtool_set_rss(struct net_device *netdev,
+			      struct ethtool_rxfh_param *rxfh,
+			      struct netlink_ext_ack *extack)
 {
 	struct aq_nic_s *aq_nic = netdev_priv(netdev);
 	struct aq_nic_cfg_s *cfg;
@@ -482,16 +482,17 @@ static int aq_ethtool_set_rss(struct net_device *netdev, const u32 *indir,
 	rss_entries = cfg->aq_rss.indirection_table_size;
 
 	/* We do not allow change in unsupported parameters */
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 	/* Fill out the redirection table */
-	if (indir)
+	if (rxfh->indir)
 		for (i = 0; i < rss_entries; i++)
-			cfg->aq_rss.indirection_table[i] = indir[i];
+			cfg->aq_rss.indirection_table[i] = rxfh->indir[i];
 
 	/* Fill out the rss hash key */
-	if (key) {
-		memcpy(cfg->aq_rss.hash_secret_key, key,
+	if (rxfh->key) {
+		memcpy(cfg->aq_rss.hash_secret_key, rxfh->key,
 		       sizeof(cfg->aq_rss.hash_secret_key));
 		err = aq_nic->aq_hw_ops->hw_rss_hash_set(aq_nic->aq_hw,
 			&cfg->aq_rss);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
index bda3ccc28eca..81d232e6d05f 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
@@ -3486,16 +3486,15 @@ static u32 bnx2x_get_rxfh_indir_size(struct net_device *dev)
 	return T_ETH_INDIRECTION_TABLE_SIZE;
 }
 
-static int bnx2x_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
-			  u8 *hfunc)
+static int bnx2x_get_rxfh(struct net_device *dev,
+			  struct ethtool_rxfh_param *rxfh)
 {
 	struct bnx2x *bp = netdev_priv(dev);
 	u8 ind_table[T_ETH_INDIRECTION_TABLE_SIZE] = {0};
 	size_t i;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
-	if (!indir)
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+	if (!rxfh->indir)
 		return 0;
 
 	/* Get the current configuration of the RSS indirection table */
@@ -3511,13 +3510,14 @@ static int bnx2x_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
 	 * queue.
 	 */
 	for (i = 0; i < T_ETH_INDIRECTION_TABLE_SIZE; i++)
-		indir[i] = ind_table[i] - bp->fp->cl_id;
+		rxfh->indir[i] = ind_table[i] - bp->fp->cl_id;
 
 	return 0;
 }
 
-static int bnx2x_set_rxfh(struct net_device *dev, const u32 *indir,
-			  const u8 *key, const u8 hfunc)
+static int bnx2x_set_rxfh(struct net_device *dev,
+			  struct ethtool_rxfh_param *rxfh,
+			  struct netlink_ext_ack *extack)
 {
 	struct bnx2x *bp = netdev_priv(dev);
 	size_t i;
@@ -3525,11 +3525,12 @@ static int bnx2x_set_rxfh(struct net_device *dev, const u32 *indir,
 	/* We require at least one supported parameter to be changed and no
 	 * change in any of the unsupported parameters
 	 */
-	if (key ||
-	    (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP))
+	if (rxfh->key ||
+	    (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	     rxfh->hfunc != ETH_RSS_HASH_TOP))
 		return -EOPNOTSUPP;
 
-	if (!indir)
+	if (!rxfh->indir)
 		return 0;
 
 	for (i = 0; i < T_ETH_INDIRECTION_TABLE_SIZE; i++) {
@@ -3542,7 +3543,7 @@ static int bnx2x_set_rxfh(struct net_device *dev, const u32 *indir,
 		 * align the received table to the Client ID of the leading RSS
 		 * queue
 		 */
-		bp->rss_conf_obj.ind_table[i] = indir[i] + bp->fp->cl_id;
+		bp->rss_conf_obj.ind_table[i] = rxfh->indir[i] + bp->fp->cl_id;
 	}
 
 	if (bp->state == BNX2X_STATE_OPEN)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 45ce7e2e3662..2742d9decc73 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -1333,49 +1333,49 @@ static u32 bnxt_get_rxfh_key_size(struct net_device *dev)
 	return HW_HASH_KEY_SIZE;
 }
 
-static int bnxt_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
-			 u8 *hfunc)
+static int bnxt_get_rxfh(struct net_device *dev,
+			 struct ethtool_rxfh_param *rxfh)
 {
 	struct bnxt *bp = netdev_priv(dev);
 	struct bnxt_vnic_info *vnic;
 	u32 i, tbl_size;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
 	if (!bp->vnic_info)
 		return 0;
 
 	vnic = &bp->vnic_info[0];
-	if (indir && bp->rss_indir_tbl) {
+	if (rxfh->indir && bp->rss_indir_tbl) {
 		tbl_size = bnxt_get_rxfh_indir_size(dev);
 		for (i = 0; i < tbl_size; i++)
-			indir[i] = bp->rss_indir_tbl[i];
+			rxfh->indir[i] = bp->rss_indir_tbl[i];
 	}
 
-	if (key && vnic->rss_hash_key)
-		memcpy(key, vnic->rss_hash_key, HW_HASH_KEY_SIZE);
+	if (rxfh->key && vnic->rss_hash_key)
+		memcpy(rxfh->key, vnic->rss_hash_key, HW_HASH_KEY_SIZE);
 
 	return 0;
 }
 
-static int bnxt_set_rxfh(struct net_device *dev, const u32 *indir,
-			 const u8 *key, const u8 hfunc)
+static int bnxt_set_rxfh(struct net_device *dev,
+			 struct ethtool_rxfh_param *rxfh,
+			 struct netlink_ext_ack *extack)
 {
 	struct bnxt *bp = netdev_priv(dev);
 	int rc = 0;
 
-	if (hfunc && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc && rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
-	if (key)
+	if (rxfh->key)
 		return -EOPNOTSUPP;
 
-	if (indir) {
+	if (rxfh->indir) {
 		u32 i, pad, tbl_size = bnxt_get_rxfh_indir_size(dev);
 
 		for (i = 0; i < tbl_size; i++)
-			bp->rss_indir_tbl[i] = indir[i];
+			bp->rss_indir_tbl[i] = rxfh->indir[i];
 		pad = bp->rss_indir_tbl_entries - tbl_size;
 		if (pad)
 			memset(&bp->rss_indir_tbl[i], 0, pad * sizeof(u16));
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index f52830dfb26a..04964bbe08cf 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -12745,24 +12745,23 @@ static u32 tg3_get_rxfh_indir_size(struct net_device *dev)
 	return size;
 }
 
-static int tg3_get_rxfh(struct net_device *dev, u32 *indir, u8 *key, u8 *hfunc)
+static int tg3_get_rxfh(struct net_device *dev, struct ethtool_rxfh_param *rxfh)
 {
 	struct tg3 *tp = netdev_priv(dev);
 	int i;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
-	if (!indir)
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+	if (!rxfh->indir)
 		return 0;
 
 	for (i = 0; i < TG3_RSS_INDIR_TBL_SIZE; i++)
-		indir[i] = tp->rss_ind_tbl[i];
+		rxfh->indir[i] = tp->rss_ind_tbl[i];
 
 	return 0;
 }
 
-static int tg3_set_rxfh(struct net_device *dev, const u32 *indir, const u8 *key,
-			const u8 hfunc)
+static int tg3_set_rxfh(struct net_device *dev, struct ethtool_rxfh_param *rxfh,
+			struct netlink_ext_ack *extack)
 {
 	struct tg3 *tp = netdev_priv(dev);
 	size_t i;
@@ -12770,15 +12769,16 @@ static int tg3_set_rxfh(struct net_device *dev, const u32 *indir, const u8 *key,
 	/* We require at least one supported parameter to be changed and no
 	 * change in any of the unsupported parameters
 	 */
-	if (key ||
-	    (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP))
+	if (rxfh->key ||
+	    (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	     rxfh->hfunc != ETH_RSS_HASH_TOP))
 		return -EOPNOTSUPP;
 
-	if (!indir)
+	if (!rxfh->indir)
 		return 0;
 
 	for (i = 0; i < TG3_RSS_INDIR_TBL_SIZE; i++)
-		tp->rss_ind_tbl[i] = indir[i];
+		tp->rss_ind_tbl[i] = rxfh->indir[i];
 
 	if (!netif_running(dev) || !tg3_flag(tp, ENABLE_RSS))
 		return 0;
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
index d8d71bf97983..34125b8cd935 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
@@ -653,35 +653,36 @@ static u32 nicvf_get_rxfh_indir_size(struct net_device *dev)
 	return nic->rss_info.rss_size;
 }
 
-static int nicvf_get_rxfh(struct net_device *dev, u32 *indir, u8 *hkey,
-			  u8 *hfunc)
+static int nicvf_get_rxfh(struct net_device *dev,
+			  struct ethtool_rxfh_param *rxfh)
 {
 	struct nicvf *nic = netdev_priv(dev);
 	struct nicvf_rss_info *rss = &nic->rss_info;
 	int idx;
 
-	if (indir) {
+	if (rxfh->indir) {
 		for (idx = 0; idx < rss->rss_size; idx++)
-			indir[idx] = rss->ind_tbl[idx];
+			rxfh->indir[idx] = rss->ind_tbl[idx];
 	}
 
-	if (hkey)
-		memcpy(hkey, rss->key, RSS_HASH_KEY_SIZE * sizeof(u64));
+	if (rxfh->key)
+		memcpy(rxfh->key, rss->key, RSS_HASH_KEY_SIZE * sizeof(u64));
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
 	return 0;
 }
 
-static int nicvf_set_rxfh(struct net_device *dev, const u32 *indir,
-			  const u8 *hkey, const u8 hfunc)
+static int nicvf_set_rxfh(struct net_device *dev,
+			  struct ethtool_rxfh_param *rxfh,
+			  struct netlink_ext_ack *extack)
 {
 	struct nicvf *nic = netdev_priv(dev);
 	struct nicvf_rss_info *rss = &nic->rss_info;
 	int idx;
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
 	if (!rss->enable) {
@@ -690,13 +691,13 @@ static int nicvf_set_rxfh(struct net_device *dev, const u32 *indir,
 		return -EIO;
 	}
 
-	if (indir) {
+	if (rxfh->indir) {
 		for (idx = 0; idx < rss->rss_size; idx++)
-			rss->ind_tbl[idx] = indir[idx];
+			rss->ind_tbl[idx] = rxfh->indir[idx];
 	}
 
-	if (hkey) {
-		memcpy(rss->key, hkey, RSS_HASH_KEY_SIZE * sizeof(u64));
+	if (rxfh->key) {
+		memcpy(rss->key, rxfh->key, RSS_HASH_KEY_SIZE * sizeof(u64));
 		nicvf_set_rss_key(nic);
 	}
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
index 8477a93cee6b..47eecde36285 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
@@ -1588,22 +1588,23 @@ static u32 get_rss_table_size(struct net_device *dev)
 	return pi->rss_size;
 }
 
-static int get_rss_table(struct net_device *dev, u32 *p, u8 *key, u8 *hfunc)
+static int get_rss_table(struct net_device *dev,
+			 struct ethtool_rxfh_param *rxfh)
 {
 	const struct port_info *pi = netdev_priv(dev);
 	unsigned int n = pi->rss_size;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
-	if (!p)
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+	if (!rxfh->indir)
 		return 0;
 	while (n--)
-		p[n] = pi->rss[n];
+		rxfh->indir[n] = pi->rss[n];
 	return 0;
 }
 
-static int set_rss_table(struct net_device *dev, const u32 *p, const u8 *key,
-			 const u8 hfunc)
+static int set_rss_table(struct net_device *dev,
+			 struct ethtool_rxfh_param *rxfh,
+			 struct netlink_ext_ack *extack)
 {
 	unsigned int i;
 	struct port_info *pi = netdev_priv(dev);
@@ -1611,16 +1612,17 @@ static int set_rss_table(struct net_device *dev, const u32 *p, const u8 *key,
 	/* We require at least one supported parameter to be changed and no
 	 * change in any of the unsupported parameters
 	 */
-	if (key ||
-	    (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP))
+	if (rxfh->key ||
+	    (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	     rxfh->hfunc != ETH_RSS_HASH_TOP))
 		return -EOPNOTSUPP;
-	if (!p)
+	if (!rxfh->indir)
 		return 0;
 
 	/* Interface must be brought up atleast once */
 	if (pi->adapter->flags & CXGB4_FULL_INIT_DONE) {
 		for (i = 0; i < pi->rss_size; i++)
-			pi->rss[i] = p[i];
+			pi->rss[i] = rxfh->indir[i];
 
 		return cxgb4_write_rss(pi, pi->rss);
 	}
diff --git a/drivers/net/ethernet/cisco/enic/enic_ethtool.c b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
index 08b7cc0a1809..241906697019 100644
--- a/drivers/net/ethernet/cisco/enic/enic_ethtool.c
+++ b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
@@ -568,31 +568,32 @@ static u32 enic_get_rxfh_key_size(struct net_device *netdev)
 	return ENIC_RSS_LEN;
 }
 
-static int enic_get_rxfh(struct net_device *netdev, u32 *indir, u8 *hkey,
-			 u8 *hfunc)
+static int enic_get_rxfh(struct net_device *netdev,
+			 struct ethtool_rxfh_param *rxfh)
 {
 	struct enic *enic = netdev_priv(netdev);
 
-	if (hkey)
-		memcpy(hkey, enic->rss_key, ENIC_RSS_LEN);
+	if (rxfh->key)
+		memcpy(rxfh->key, enic->rss_key, ENIC_RSS_LEN);
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
 	return 0;
 }
 
-static int enic_set_rxfh(struct net_device *netdev, const u32 *indir,
-			 const u8 *hkey, const u8 hfunc)
+static int enic_set_rxfh(struct net_device *netdev,
+			 struct ethtool_rxfh_param *rxfh,
+			 struct netlink_ext_ack *extack)
 {
 	struct enic *enic = netdev_priv(netdev);
 
-	if ((hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP) ||
-	    indir)
+	if (rxfh->indir ||
+	    (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	     rxfh->hfunc != ETH_RSS_HASH_TOP))
 		return -EINVAL;
 
-	if (hkey)
-		memcpy(enic->rss_key, hkey, ENIC_RSS_LEN);
+	if (rxfh->key)
+		memcpy(enic->rss_key, rxfh->key, ENIC_RSS_LEN);
 
 	return __enic_set_rsskey(enic);
 }
diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c
index a29de29bdf23..f001a649f58f 100644
--- a/drivers/net/ethernet/emulex/benet/be_ethtool.c
+++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c
@@ -1271,43 +1271,45 @@ static u32 be_get_rxfh_key_size(struct net_device *netdev)
 	return RSS_HASH_KEY_LEN;
 }
 
-static int be_get_rxfh(struct net_device *netdev, u32 *indir, u8 *hkey,
-		       u8 *hfunc)
+static int be_get_rxfh(struct net_device *netdev,
+		       struct ethtool_rxfh_param *rxfh)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 	int i;
 	struct rss_info *rss = &adapter->rss_info;
 
-	if (indir) {
+	if (rxfh->indir) {
 		for (i = 0; i < RSS_INDIR_TABLE_LEN; i++)
-			indir[i] = rss->rss_queue[i];
+			rxfh->indir[i] = rss->rss_queue[i];
 	}
 
-	if (hkey)
-		memcpy(hkey, rss->rss_hkey, RSS_HASH_KEY_LEN);
+	if (rxfh->key)
+		memcpy(rxfh->key, rss->rss_hkey, RSS_HASH_KEY_LEN);
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
 	return 0;
 }
 
-static int be_set_rxfh(struct net_device *netdev, const u32 *indir,
-		       const u8 *hkey, const u8 hfunc)
+static int be_set_rxfh(struct net_device *netdev,
+		       struct ethtool_rxfh_param *rxfh,
+		       struct netlink_ext_ack *extack)
 {
 	int rc = 0, i, j;
 	struct be_adapter *adapter = netdev_priv(netdev);
+	u8 *hkey = rxfh->key;
 	u8 rsstable[RSS_INDIR_TABLE_LEN];
 
 	/* We do not allow change in unsupported parameters */
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
-	if (indir) {
+	if (rxfh->indir) {
 		struct be_rx_obj *rxo;
 
 		for (i = 0; i < RSS_INDIR_TABLE_LEN; i++) {
-			j = indir[i];
+			j = rxfh->indir[i];
 			rxo = &adapter->rx_obj[j];
 			rsstable[i] = rxo->rss_id;
 			adapter->rss_info.rss_queue[i] = j;
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
index e993ed04ab57..f7753ea5b57e 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
@@ -690,25 +690,26 @@ static u32 enetc_get_rxfh_indir_size(struct net_device *ndev)
 	return priv->si->num_rss;
 }
 
-static int enetc_get_rxfh(struct net_device *ndev, u32 *indir, u8 *key,
-			  u8 *hfunc)
+static int enetc_get_rxfh(struct net_device *ndev,
+			  struct ethtool_rxfh_param *rxfh)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
 	struct enetc_hw *hw = &priv->si->hw;
 	int err = 0, i;
 
 	/* return hash function */
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
 	/* return hash key */
-	if (key && hw->port)
+	if (rxfh->key && hw->port)
 		for (i = 0; i < ENETC_RSSHASH_KEY_SIZE / 4; i++)
-			((u32 *)key)[i] = enetc_port_rd(hw, ENETC_PRSSK(i));
+			((u32 *)rxfh->key)[i] = enetc_port_rd(hw,
+							      ENETC_PRSSK(i));
 
 	/* return RSS table */
-	if (indir)
-		err = enetc_get_rss_table(priv->si, indir, priv->si->num_rss);
+	if (rxfh->indir)
+		err = enetc_get_rss_table(priv->si, rxfh->indir,
+					  priv->si->num_rss);
 
 	return err;
 }
@@ -722,20 +723,22 @@ void enetc_set_rss_key(struct enetc_hw *hw, const u8 *bytes)
 }
 EXPORT_SYMBOL_GPL(enetc_set_rss_key);
 
-static int enetc_set_rxfh(struct net_device *ndev, const u32 *indir,
-			  const u8 *key, const u8 hfunc)
+static int enetc_set_rxfh(struct net_device *ndev,
+			  struct ethtool_rxfh_param *rxfh,
+			  struct netlink_ext_ack *extack)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
 	struct enetc_hw *hw = &priv->si->hw;
 	int err = 0;
 
 	/* set hash key, if PF */
-	if (key && hw->port)
-		enetc_set_rss_key(hw, key);
+	if (rxfh->key && hw->port)
+		enetc_set_rss_key(hw, rxfh->key);
 
 	/* set RSS table */
-	if (indir)
-		err = enetc_set_rss_table(priv->si, indir, priv->si->num_rss);
+	if (rxfh->indir)
+		err = enetc_set_rss_table(priv->si, rxfh->indir,
+					  priv->si->num_rss);
 
 	return err;
 }
diff --git a/drivers/net/ethernet/fungible/funeth/funeth_ethtool.c b/drivers/net/ethernet/fungible/funeth/funeth_ethtool.c
index 091c93bd7587..4edd0adfc6c7 100644
--- a/drivers/net/ethernet/fungible/funeth/funeth_ethtool.c
+++ b/drivers/net/ethernet/fungible/funeth/funeth_ethtool.c
@@ -977,44 +977,44 @@ static u32 fun_get_rxfh_key_size(struct net_device *netdev)
 	return sizeof(fp->rss_key);
 }
 
-static int fun_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
-			u8 *hfunc)
+static int fun_get_rxfh(struct net_device *netdev,
+			struct ethtool_rxfh_param *rxfh)
 {
 	const struct funeth_priv *fp = netdev_priv(netdev);
 
 	if (!fp->rss_cfg)
 		return -EOPNOTSUPP;
 
-	if (indir)
-		memcpy(indir, fp->indir_table,
+	if (rxfh->indir)
+		memcpy(rxfh->indir, fp->indir_table,
 		       sizeof(u32) * fp->indir_table_nentries);
 
-	if (key)
-		memcpy(key, fp->rss_key, sizeof(fp->rss_key));
+	if (rxfh->key)
+		memcpy(rxfh->key, fp->rss_key, sizeof(fp->rss_key));
 
-	if (hfunc)
-		*hfunc = fp->hash_algo == FUN_ETH_RSS_ALG_TOEPLITZ ?
-				ETH_RSS_HASH_TOP : ETH_RSS_HASH_CRC32;
+	rxfh->hfunc = fp->hash_algo == FUN_ETH_RSS_ALG_TOEPLITZ ?
+			ETH_RSS_HASH_TOP : ETH_RSS_HASH_CRC32;
 
 	return 0;
 }
 
-static int fun_set_rxfh(struct net_device *netdev, const u32 *indir,
-			const u8 *key, const u8 hfunc)
+static int fun_set_rxfh(struct net_device *netdev,
+			struct ethtool_rxfh_param *rxfh,
+			struct netlink_ext_ack *extack)
 {
 	struct funeth_priv *fp = netdev_priv(netdev);
-	const u32 *rss_indir = indir ? indir : fp->indir_table;
-	const u8 *rss_key = key ? key : fp->rss_key;
+	const u32 *rss_indir = rxfh->indir ? rxfh->indir : fp->indir_table;
+	const u8 *rss_key = rxfh->key ? rxfh->key : fp->rss_key;
 	enum fun_eth_hash_alg algo;
 
 	if (!fp->rss_cfg)
 		return -EOPNOTSUPP;
 
-	if (hfunc == ETH_RSS_HASH_NO_CHANGE)
+	if (rxfh->hfunc == ETH_RSS_HASH_NO_CHANGE)
 		algo = fp->hash_algo;
-	else if (hfunc == ETH_RSS_HASH_CRC32)
+	else if (rxfh->hfunc == ETH_RSS_HASH_CRC32)
 		algo = FUN_ETH_RSS_ALG_CRC32;
-	else if (hfunc == ETH_RSS_HASH_TOP)
+	else if (rxfh->hfunc == ETH_RSS_HASH_TOP)
 		algo = FUN_ETH_RSS_ALG_TOEPLITZ;
 	else
 		return -EINVAL;
@@ -1031,10 +1031,10 @@ static int fun_set_rxfh(struct net_device *netdev, const u32 *indir,
 	}
 
 	fp->hash_algo = algo;
-	if (key)
-		memcpy(fp->rss_key, key, sizeof(fp->rss_key));
-	if (indir)
-		memcpy(fp->indir_table, indir,
+	if (rxfh->key)
+		memcpy(fp->rss_key, rxfh->key, sizeof(fp->rss_key));
+	if (rxfh->indir)
+		memcpy(fp->indir_table, rxfh->indir,
 		       sizeof(u32) * fp->indir_table_nentries);
 	return 0;
 }
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
index fe40cceb0f79..a5bb306b2cf1 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
@@ -1186,7 +1186,7 @@ hns_get_rss_indir_size(struct net_device *netdev)
 }
 
 static int
-hns_get_rss(struct net_device *netdev, u32 *indir, u8 *key, u8 *hfunc)
+hns_get_rss(struct net_device *netdev, struct ethtool_rxfh_param *rxfh)
 {
 	struct hns_nic_priv *priv = netdev_priv(netdev);
 	struct hnae_ae_ops *ops;
@@ -1199,15 +1199,16 @@ hns_get_rss(struct net_device *netdev, u32 *indir, u8 *key, u8 *hfunc)
 
 	ops = priv->ae_handle->dev->ops;
 
-	if (!indir)
+	if (!rxfh->indir)
 		return 0;
 
-	return ops->get_rss(priv->ae_handle, indir, key, hfunc);
+	return ops->get_rss(priv->ae_handle,
+			    rxfh->indir, rxfh->key, &rxfh->hfunc);
 }
 
 static int
-hns_set_rss(struct net_device *netdev, const u32 *indir, const u8 *key,
-	    const u8 hfunc)
+hns_set_rss(struct net_device *netdev, struct ethtool_rxfh_param *rxfh,
+	    struct netlink_ext_ack *extack)
 {
 	struct hns_nic_priv *priv = netdev_priv(netdev);
 	struct hnae_ae_ops *ops;
@@ -1220,12 +1221,14 @@ hns_set_rss(struct net_device *netdev, const u32 *indir, const u8 *key,
 
 	ops = priv->ae_handle->dev->ops;
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP) {
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP) {
 		netdev_err(netdev, "Invalid hfunc!\n");
 		return -EOPNOTSUPP;
 	}
 
-	return ops->set_rss(priv->ae_handle, indir, key, hfunc);
+	return ops->set_rss(priv->ae_handle,
+			    rxfh->indir, rxfh->key, rxfh->hfunc);
 }
 
 static int hns_get_rxnfc(struct net_device *netdev,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index 682239f33082..999a0ee162a6 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -941,19 +941,21 @@ static u32 hns3_get_rss_indir_size(struct net_device *netdev)
 	return ae_dev->dev_specs.rss_ind_tbl_size;
 }
 
-static int hns3_get_rss(struct net_device *netdev, u32 *indir, u8 *key,
-			u8 *hfunc)
+static int hns3_get_rss(struct net_device *netdev,
+			struct ethtool_rxfh_param *rxfh)
 {
 	struct hnae3_handle *h = hns3_get_handle(netdev);
 
 	if (!h->ae_algo->ops->get_rss)
 		return -EOPNOTSUPP;
 
-	return h->ae_algo->ops->get_rss(h, indir, key, hfunc);
+	return h->ae_algo->ops->get_rss(h, rxfh->indir, rxfh->key,
+					&rxfh->hfunc);
 }
 
-static int hns3_set_rss(struct net_device *netdev, const u32 *indir,
-			const u8 *key, const u8 hfunc)
+static int hns3_set_rss(struct net_device *netdev,
+			struct ethtool_rxfh_param *rxfh,
+			struct netlink_ext_ack *extack)
 {
 	struct hnae3_handle *h = hns3_get_handle(netdev);
 	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev);
@@ -962,19 +964,22 @@ static int hns3_set_rss(struct net_device *netdev, const u32 *indir,
 		return -EOPNOTSUPP;
 
 	if ((ae_dev->dev_version < HNAE3_DEVICE_VERSION_V2 &&
-	     hfunc != ETH_RSS_HASH_TOP) || (hfunc != ETH_RSS_HASH_NO_CHANGE &&
-	     hfunc != ETH_RSS_HASH_TOP && hfunc != ETH_RSS_HASH_XOR)) {
+	     rxfh->hfunc != ETH_RSS_HASH_TOP) ||
+	    (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	     rxfh->hfunc != ETH_RSS_HASH_TOP &&
+	     rxfh->hfunc != ETH_RSS_HASH_XOR)) {
 		netdev_err(netdev, "hash func not supported\n");
 		return -EOPNOTSUPP;
 	}
 
-	if (!indir) {
+	if (!rxfh->indir) {
 		netdev_err(netdev,
 			   "set rss failed for indir is empty\n");
 		return -EOPNOTSUPP;
 	}
 
-	return h->ae_algo->ops->set_rss(h, indir, key, hfunc);
+	return h->ae_algo->ops->set_rss(h, rxfh->indir, rxfh->key,
+					rxfh->hfunc);
 }
 
 static int hns3_get_rxnfc(struct net_device *netdev,
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c
index f4b680286911..0304f03d4093 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c
@@ -1137,7 +1137,7 @@ static int hinic_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd)
 }
 
 static int hinic_get_rxfh(struct net_device *netdev,
-			  u32 *indir, u8 *key, u8 *hfunc)
+			  struct ethtool_rxfh_param *rxfh)
 {
 	struct hinic_dev *nic_dev = netdev_priv(netdev);
 	u8 hash_engine_type = 0;
@@ -1146,32 +1146,33 @@ static int hinic_get_rxfh(struct net_device *netdev,
 	if (!(nic_dev->flags & HINIC_RSS_ENABLE))
 		return -EOPNOTSUPP;
 
-	if (hfunc) {
-		err = hinic_rss_get_hash_engine(nic_dev,
-						nic_dev->rss_tmpl_idx,
-						&hash_engine_type);
-		if (err)
-			return -EFAULT;
+	err = hinic_rss_get_hash_engine(nic_dev,
+					nic_dev->rss_tmpl_idx,
+					&hash_engine_type);
+	if (err)
+		return -EFAULT;
 
-		*hfunc = hash_engine_type ? ETH_RSS_HASH_TOP : ETH_RSS_HASH_XOR;
-	}
+	rxfh->hfunc = hash_engine_type ? ETH_RSS_HASH_TOP : ETH_RSS_HASH_XOR;
 
-	if (indir) {
+	if (rxfh->indir) {
 		err = hinic_rss_get_indir_tbl(nic_dev,
-					      nic_dev->rss_tmpl_idx, indir);
+					      nic_dev->rss_tmpl_idx,
+					      rxfh->indir);
 		if (err)
 			return -EFAULT;
 	}
 
-	if (key)
+	if (rxfh->key)
 		err = hinic_rss_get_template_tbl(nic_dev,
-						 nic_dev->rss_tmpl_idx, key);
+						 nic_dev->rss_tmpl_idx,
+						 rxfh->key);
 
 	return err;
 }
 
-static int hinic_set_rxfh(struct net_device *netdev, const u32 *indir,
-			  const u8 *key, const u8 hfunc)
+static int hinic_set_rxfh(struct net_device *netdev,
+			  struct ethtool_rxfh_param *rxfh,
+			  struct netlink_ext_ack *extack)
 {
 	struct hinic_dev *nic_dev = netdev_priv(netdev);
 	int err = 0;
@@ -1179,11 +1180,12 @@ static int hinic_set_rxfh(struct net_device *netdev, const u32 *indir,
 	if (!(nic_dev->flags & HINIC_RSS_ENABLE))
 		return -EOPNOTSUPP;
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE) {
-		if (hfunc != ETH_RSS_HASH_TOP && hfunc != ETH_RSS_HASH_XOR)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE) {
+		if (rxfh->hfunc != ETH_RSS_HASH_TOP &&
+		    rxfh->hfunc != ETH_RSS_HASH_XOR)
 			return -EOPNOTSUPP;
 
-		nic_dev->rss_hash_engine = (hfunc == ETH_RSS_HASH_XOR) ?
+		nic_dev->rss_hash_engine = (rxfh->hfunc == ETH_RSS_HASH_XOR) ?
 			HINIC_RSS_HASH_ENGINE_TYPE_XOR :
 			HINIC_RSS_HASH_ENGINE_TYPE_TOEP;
 		err = hinic_rss_set_hash_engine
@@ -1193,7 +1195,7 @@ static int hinic_set_rxfh(struct net_device *netdev, const u32 *indir,
 			return -EFAULT;
 	}
 
-	err = __set_rss_rxfh(netdev, indir, key);
+	err = __set_rss_rxfh(netdev, rxfh->indir, rxfh->key);
 
 	return err;
 }
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
index 13a05604dcc0..1bc5b6c0b897 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
@@ -1057,16 +1057,16 @@ static u32 fm10k_get_rssrk_size(struct net_device __always_unused *netdev)
 	return FM10K_RSSRK_SIZE * FM10K_RSSRK_ENTRIES_PER_REG;
 }
 
-static int fm10k_get_rssh(struct net_device *netdev, u32 *indir, u8 *key,
-			  u8 *hfunc)
+static int fm10k_get_rssh(struct net_device *netdev,
+			  struct ethtool_rxfh_param *rxfh)
 {
 	struct fm10k_intfc *interface = netdev_priv(netdev);
+	u8 *key = rxfh->key;
 	int i, err;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
-	err = fm10k_get_reta(netdev, indir);
+	err = fm10k_get_reta(netdev, rxfh->indir);
 	if (err || !key)
 		return err;
 
@@ -1076,23 +1076,25 @@ static int fm10k_get_rssh(struct net_device *netdev, u32 *indir, u8 *key,
 	return 0;
 }
 
-static int fm10k_set_rssh(struct net_device *netdev, const u32 *indir,
-			  const u8 *key, const u8 hfunc)
+static int fm10k_set_rssh(struct net_device *netdev,
+			  struct ethtool_rxfh_param *rxfh,
+			  struct netlink_ext_ack *extack)
 {
 	struct fm10k_intfc *interface = netdev_priv(netdev);
 	struct fm10k_hw *hw = &interface->hw;
 	int i, err;
 
 	/* We do not allow change in unsupported parameters */
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
-	err = fm10k_set_reta(netdev, indir);
-	if (err || !key)
+	err = fm10k_set_reta(netdev, rxfh->indir);
+	if (err || !rxfh->key)
 		return err;
 
-	for (i = 0; i < FM10K_RSSRK_SIZE; i++, key += 4) {
-		u32 rssrk = le32_to_cpu(*(__le32 *)key);
+	for (i = 0; i < FM10K_RSSRK_SIZE; i++, rxfh->key += 4) {
+		u32 rssrk = le32_to_cpu(*(__le32 *)rxfh->key);
 
 		if (interface->rssrk[i] == rssrk)
 			continue;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index a0b10230268d..53820d63e6fa 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -5120,15 +5120,13 @@ static u32 i40e_get_rxfh_indir_size(struct net_device *netdev)
 /**
  * i40e_get_rxfh - get the rx flow hash indirection table
  * @netdev: network interface device structure
- * @indir: indirection table
- * @key: hash key
- * @hfunc: hash function
+ * @rxfh: pointer to param struct (indir, key, hfunc)
  *
  * Reads the indirection table directly from the hardware. Returns 0 on
  * success.
  **/
-static int i40e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
-			 u8 *hfunc)
+static int i40e_get_rxfh(struct net_device *netdev,
+			 struct ethtool_rxfh_param *rxfh)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
@@ -5136,13 +5134,12 @@ static int i40e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 	int ret;
 	u16 i;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
-	if (!indir)
+	if (!rxfh->indir)
 		return 0;
 
-	seed = key;
+	seed = rxfh->key;
 	lut = kzalloc(I40E_HLUT_ARRAY_SIZE, GFP_KERNEL);
 	if (!lut)
 		return -ENOMEM;
@@ -5150,7 +5147,7 @@ static int i40e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 	if (ret)
 		goto out;
 	for (i = 0; i < I40E_HLUT_ARRAY_SIZE; i++)
-		indir[i] = (u32)(lut[i]);
+		rxfh->indir[i] = (u32)(lut[i]);
 
 out:
 	kfree(lut);
@@ -5161,15 +5158,15 @@ out:
 /**
  * i40e_set_rxfh - set the rx flow hash indirection table
  * @netdev: network interface device structure
- * @indir: indirection table
- * @key: hash key
- * @hfunc: hash function to use
+ * @rxfh: pointer to param struct (indir, key, hfunc)
+ * @extack: extended ACK from the Netlink message
  *
  * Returns -EINVAL if the table specifies an invalid queue id, otherwise
  * returns 0 after programming the table.
  **/
-static int i40e_set_rxfh(struct net_device *netdev, const u32 *indir,
-			 const u8 *key, const u8 hfunc)
+static int i40e_set_rxfh(struct net_device *netdev,
+			 struct ethtool_rxfh_param *rxfh,
+			 struct netlink_ext_ack *extack)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
@@ -5177,17 +5174,18 @@ static int i40e_set_rxfh(struct net_device *netdev, const u32 *indir,
 	u8 *seed = NULL;
 	u16 i;
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
-	if (key) {
+	if (rxfh->key) {
 		if (!vsi->rss_hkey_user) {
 			vsi->rss_hkey_user = kzalloc(I40E_HKEY_ARRAY_SIZE,
 						     GFP_KERNEL);
 			if (!vsi->rss_hkey_user)
 				return -ENOMEM;
 		}
-		memcpy(vsi->rss_hkey_user, key, I40E_HKEY_ARRAY_SIZE);
+		memcpy(vsi->rss_hkey_user, rxfh->key, I40E_HKEY_ARRAY_SIZE);
 		seed = vsi->rss_hkey_user;
 	}
 	if (!vsi->rss_lut_user) {
@@ -5197,9 +5195,9 @@ static int i40e_set_rxfh(struct net_device *netdev, const u32 *indir,
 	}
 
 	/* Each 32 bits pointed by 'indir' is stored with a lut entry */
-	if (indir)
+	if (rxfh->indir)
 		for (i = 0; i < I40E_HLUT_ARRAY_SIZE; i++)
-			vsi->rss_lut_user[i] = (u8)(indir[i]);
+			vsi->rss_lut_user[i] = (u8)(rxfh->indir[i]);
 	else
 		i40e_fill_rss_lut(pf, vsi->rss_lut_user, I40E_HLUT_ARRAY_SIZE,
 				  vsi->rss_size);
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
index 631c7cfdc814..c376a489e4c2 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
@@ -1894,27 +1894,24 @@ static u32 iavf_get_rxfh_indir_size(struct net_device *netdev)
 /**
  * iavf_get_rxfh - get the rx flow hash indirection table
  * @netdev: network interface device structure
- * @indir: indirection table
- * @key: hash key
- * @hfunc: hash function in use
+ * @rxfh: pointer to param struct (indir, key, hfunc)
  *
  * Reads the indirection table directly from the hardware. Always returns 0.
  **/
-static int iavf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
-			 u8 *hfunc)
+static int iavf_get_rxfh(struct net_device *netdev,
+			 struct ethtool_rxfh_param *rxfh)
 {
 	struct iavf_adapter *adapter = netdev_priv(netdev);
 	u16 i;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
-	if (key)
-		memcpy(key, adapter->rss_key, adapter->rss_key_size);
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+	if (rxfh->key)
+		memcpy(rxfh->key, adapter->rss_key, adapter->rss_key_size);
 
-	if (indir)
+	if (rxfh->indir)
 		/* Each 32 bits pointed by 'indir' is stored with a lut entry */
 		for (i = 0; i < adapter->rss_lut_size; i++)
-			indir[i] = (u32)adapter->rss_lut[i];
+			rxfh->indir[i] = (u32)adapter->rss_lut[i];
 
 	return 0;
 }
@@ -1922,33 +1919,34 @@ static int iavf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 /**
  * iavf_set_rxfh - set the rx flow hash indirection table
  * @netdev: network interface device structure
- * @indir: indirection table
- * @key: hash key
- * @hfunc: hash function to use
+ * @rxfh: pointer to param struct (indir, key, hfunc)
+ * @extack: extended ACK from the Netlink message
  *
  * Returns -EINVAL if the table specifies an invalid queue id, otherwise
  * returns 0 after programming the table.
  **/
-static int iavf_set_rxfh(struct net_device *netdev, const u32 *indir,
-			 const u8 *key, const u8 hfunc)
+static int iavf_set_rxfh(struct net_device *netdev,
+			 struct ethtool_rxfh_param *rxfh,
+			 struct netlink_ext_ack *extack)
 {
 	struct iavf_adapter *adapter = netdev_priv(netdev);
 	u16 i;
 
 	/* Only support toeplitz hash function */
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
-	if (!key && !indir)
+	if (!rxfh->key && !rxfh->indir)
 		return 0;
 
-	if (key)
-		memcpy(adapter->rss_key, key, adapter->rss_key_size);
+	if (rxfh->key)
+		memcpy(adapter->rss_key, rxfh->key, adapter->rss_key_size);
 
-	if (indir) {
+	if (rxfh->indir) {
 		/* Each 32 bits pointed by 'indir' is stored with a lut entry */
 		for (i = 0; i < adapter->rss_lut_size; i++)
-			adapter->rss_lut[i] = (u8)(indir[i]);
+			adapter->rss_lut[i] = (u8)(rxfh->indir[i]);
 	}
 
 	return iavf_config_rss(adapter);
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 98c9317581e0..70cbd8092aea 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -3196,8 +3196,8 @@ static u32 ice_get_rxfh_indir_size(struct net_device *netdev)
 }
 
 static int
-ice_get_rxfh_context(struct net_device *netdev, u32 *indir,
-		     u8 *key, u8 *hfunc, u32 rss_context)
+ice_get_rxfh_context(struct net_device *netdev,
+		     struct ethtool_rxfh_param *rxfh, u32 rss_context)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ice_vsi *vsi = np->vsi;
@@ -3230,17 +3230,16 @@ ice_get_rxfh_context(struct net_device *netdev, u32 *indir,
 		vsi = vsi->tc_map_vsi[rss_context];
 	}
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
-	if (!indir)
+	if (!rxfh->indir)
 		return 0;
 
 	lut = kzalloc(vsi->rss_table_size, GFP_KERNEL);
 	if (!lut)
 		return -ENOMEM;
 
-	err = ice_get_rss_key(vsi, key);
+	err = ice_get_rss_key(vsi, rxfh->key);
 	if (err)
 		goto out;
 
@@ -3250,12 +3249,12 @@ ice_get_rxfh_context(struct net_device *netdev, u32 *indir,
 
 	if (ice_is_adq_active(pf)) {
 		for (i = 0; i < vsi->rss_table_size; i++)
-			indir[i] = offset + lut[i] % qcount;
+			rxfh->indir[i] = offset + lut[i] % qcount;
 		goto out;
 	}
 
 	for (i = 0; i < vsi->rss_table_size; i++)
-		indir[i] = lut[i];
+		rxfh->indir[i] = lut[i];
 
 out:
 	kfree(lut);
@@ -3265,31 +3264,28 @@ out:
 /**
  * ice_get_rxfh - get the Rx flow hash indirection table
  * @netdev: network interface device structure
- * @indir: indirection table
- * @key: hash key
- * @hfunc: hash function
+ * @rxfh: pointer to param struct (indir, key, hfunc)
  *
  * Reads the indirection table directly from the hardware.
  */
 static int
-ice_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, u8 *hfunc)
+ice_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh)
 {
-	return ice_get_rxfh_context(netdev, indir, key, hfunc, 0);
+	return ice_get_rxfh_context(netdev, rxfh, 0);
 }
 
 /**
  * ice_set_rxfh - set the Rx flow hash indirection table
  * @netdev: network interface device structure
- * @indir: indirection table
- * @key: hash key
- * @hfunc: hash function
+ * @rxfh: pointer to param struct (indir, key, hfunc)
+ * @extack: extended ACK from the Netlink message
  *
  * Returns -EINVAL if the table specifies an invalid queue ID, otherwise
  * returns 0 after programming the table.
  */
 static int
-ice_set_rxfh(struct net_device *netdev, const u32 *indir, const u8 *key,
-	     const u8 hfunc)
+ice_set_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh,
+	     struct netlink_ext_ack *extack)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ice_vsi *vsi = np->vsi;
@@ -3298,7 +3294,8 @@ ice_set_rxfh(struct net_device *netdev, const u32 *indir, const u8 *key,
 	int err;
 
 	dev = ice_pf_to_dev(pf);
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
 	if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags)) {
@@ -3312,7 +3309,7 @@ ice_set_rxfh(struct net_device *netdev, const u32 *indir, const u8 *key,
 		return -EOPNOTSUPP;
 	}
 
-	if (key) {
+	if (rxfh->key) {
 		if (!vsi->rss_hkey_user) {
 			vsi->rss_hkey_user =
 				devm_kzalloc(dev, ICE_VSIQF_HKEY_ARRAY_SIZE,
@@ -3320,7 +3317,8 @@ ice_set_rxfh(struct net_device *netdev, const u32 *indir, const u8 *key,
 			if (!vsi->rss_hkey_user)
 				return -ENOMEM;
 		}
-		memcpy(vsi->rss_hkey_user, key, ICE_VSIQF_HKEY_ARRAY_SIZE);
+		memcpy(vsi->rss_hkey_user, rxfh->key,
+		       ICE_VSIQF_HKEY_ARRAY_SIZE);
 
 		err = ice_set_rss_key(vsi, vsi->rss_hkey_user);
 		if (err)
@@ -3335,11 +3333,11 @@ ice_set_rxfh(struct net_device *netdev, const u32 *indir, const u8 *key,
 	}
 
 	/* Each 32 bits pointed by 'indir' is stored with a lut entry */
-	if (indir) {
+	if (rxfh->indir) {
 		int i;
 
 		for (i = 0; i < vsi->rss_table_size; i++)
-			vsi->rss_lut_user[i] = (u8)(indir[i]);
+			vsi->rss_lut_user[i] = (u8)(rxfh->indir[i]);
 	} else {
 		ice_fill_rss_lut(vsi->rss_lut_user, vsi->rss_table_size,
 				 vsi->rss_size);
diff --git a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
index d549d3c5910d..986d429d1175 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
@@ -75,14 +75,12 @@ static u32 idpf_get_rxfh_indir_size(struct net_device *netdev)
 /**
  * idpf_get_rxfh - get the rx flow hash indirection table
  * @netdev: network interface device structure
- * @indir: indirection table
- * @key: hash key
- * @hfunc: hash function in use
+ * @rxfh: pointer to param struct (indir, key, hfunc)
  *
  * Reads the indirection table directly from the hardware. Always returns 0.
  */
-static int idpf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
-			 u8 *hfunc)
+static int idpf_get_rxfh(struct net_device *netdev,
+			 struct ethtool_rxfh_param *rxfh)
 {
 	struct idpf_netdev_priv *np = netdev_priv(netdev);
 	struct idpf_rss_data *rss_data;
@@ -103,15 +101,14 @@ static int idpf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 	if (np->state != __IDPF_VPORT_UP)
 		goto unlock_mutex;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
-	if (key)
-		memcpy(key, rss_data->rss_key, rss_data->rss_key_size);
+	if (rxfh->key)
+		memcpy(rxfh->key, rss_data->rss_key, rss_data->rss_key_size);
 
-	if (indir) {
+	if (rxfh->indir) {
 		for (i = 0; i < rss_data->rss_lut_size; i++)
-			indir[i] = rss_data->rss_lut[i];
+			rxfh->indir[i] = rss_data->rss_lut[i];
 	}
 
 unlock_mutex:
@@ -123,15 +120,15 @@ unlock_mutex:
 /**
  * idpf_set_rxfh - set the rx flow hash indirection table
  * @netdev: network interface device structure
- * @indir: indirection table
- * @key: hash key
- * @hfunc: hash function to use
+ * @rxfh: pointer to param struct (indir, key, hfunc)
+ * @extack: extended ACK from the Netlink message
  *
  * Returns -EINVAL if the table specifies an invalid queue id, otherwise
  * returns 0 after programming the table.
  */
-static int idpf_set_rxfh(struct net_device *netdev, const u32 *indir,
-			 const u8 *key, const u8 hfunc)
+static int idpf_set_rxfh(struct net_device *netdev,
+			 struct ethtool_rxfh_param *rxfh,
+			 struct netlink_ext_ack *extack)
 {
 	struct idpf_netdev_priv *np = netdev_priv(netdev);
 	struct idpf_rss_data *rss_data;
@@ -154,17 +151,18 @@ static int idpf_set_rxfh(struct net_device *netdev, const u32 *indir,
 	if (np->state != __IDPF_VPORT_UP)
 		goto unlock_mutex;
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP) {
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP) {
 		err = -EOPNOTSUPP;
 		goto unlock_mutex;
 	}
 
-	if (key)
-		memcpy(rss_data->rss_key, key, rss_data->rss_key_size);
+	if (rxfh->key)
+		memcpy(rss_data->rss_key, rxfh->key, rss_data->rss_key_size);
 
-	if (indir) {
+	if (rxfh->indir) {
 		for (lut = 0; lut < rss_data->rss_lut_size; lut++)
-			rss_data->rss_lut[lut] = indir[lut];
+			rss_data->rss_lut[lut] = rxfh->indir[lut];
 	}
 
 	err = idpf_config_rss(vport);
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index 89dac7b215e5..d868a70732f4 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -3280,18 +3280,17 @@ static u32 igb_get_rxfh_indir_size(struct net_device *netdev)
 	return IGB_RETA_SIZE;
 }
 
-static int igb_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
-			u8 *hfunc)
+static int igb_get_rxfh(struct net_device *netdev,
+			struct ethtool_rxfh_param *rxfh)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	int i;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
-	if (!indir)
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+	if (!rxfh->indir)
 		return 0;
 	for (i = 0; i < IGB_RETA_SIZE; i++)
-		indir[i] = adapter->rss_indir_tbl[i];
+		rxfh->indir[i] = adapter->rss_indir_tbl[i];
 
 	return 0;
 }
@@ -3331,8 +3330,9 @@ void igb_write_rss_indir_tbl(struct igb_adapter *adapter)
 	}
 }
 
-static int igb_set_rxfh(struct net_device *netdev, const u32 *indir,
-			const u8 *key, const u8 hfunc)
+static int igb_set_rxfh(struct net_device *netdev,
+			struct ethtool_rxfh_param *rxfh,
+			struct netlink_ext_ack *extack)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
@@ -3340,10 +3340,11 @@ static int igb_set_rxfh(struct net_device *netdev, const u32 *indir,
 	u32 num_queues;
 
 	/* We do not allow change in unsupported parameters */
-	if (key ||
-	    (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP))
+	if (rxfh->key ||
+	    (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	     rxfh->hfunc != ETH_RSS_HASH_TOP))
 		return -EOPNOTSUPP;
-	if (!indir)
+	if (!rxfh->indir)
 		return 0;
 
 	num_queues = adapter->rss_queues;
@@ -3360,12 +3361,12 @@ static int igb_set_rxfh(struct net_device *netdev, const u32 *indir,
 
 	/* Verify user input. */
 	for (i = 0; i < IGB_RETA_SIZE; i++)
-		if (indir[i] >= num_queues)
+		if (rxfh->indir[i] >= num_queues)
 			return -EINVAL;
 
 
 	for (i = 0; i < IGB_RETA_SIZE; i++)
-		adapter->rss_indir_tbl[i] = indir[i];
+		adapter->rss_indir_tbl[i] = rxfh->indir[i];
 
 	igb_write_rss_indir_tbl(adapter);
 
diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index 2ed92bf34059..684f6f2a0572 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -1426,45 +1426,46 @@ static u32 igc_ethtool_get_rxfh_indir_size(struct net_device *netdev)
 	return IGC_RETA_SIZE;
 }
 
-static int igc_ethtool_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
-				u8 *hfunc)
+static int igc_ethtool_get_rxfh(struct net_device *netdev,
+				struct ethtool_rxfh_param *rxfh)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 	int i;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
-	if (!indir)
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+	if (!rxfh->indir)
 		return 0;
 	for (i = 0; i < IGC_RETA_SIZE; i++)
-		indir[i] = adapter->rss_indir_tbl[i];
+		rxfh->indir[i] = adapter->rss_indir_tbl[i];
 
 	return 0;
 }
 
-static int igc_ethtool_set_rxfh(struct net_device *netdev, const u32 *indir,
-				const u8 *key, const u8 hfunc)
+static int igc_ethtool_set_rxfh(struct net_device *netdev,
+				struct ethtool_rxfh_param *rxfh,
+				struct netlink_ext_ack *extack)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 	u32 num_queues;
 	int i;
 
 	/* We do not allow change in unsupported parameters */
-	if (key ||
-	    (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP))
+	if (rxfh->key ||
+	    (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	     rxfh->hfunc != ETH_RSS_HASH_TOP))
 		return -EOPNOTSUPP;
-	if (!indir)
+	if (!rxfh->indir)
 		return 0;
 
 	num_queues = adapter->rss_queues;
 
 	/* Verify user input. */
 	for (i = 0; i < IGC_RETA_SIZE; i++)
-		if (indir[i] >= num_queues)
+		if (rxfh->indir[i] >= num_queues)
 			return -EINVAL;
 
 	for (i = 0; i < IGC_RETA_SIZE; i++)
-		adapter->rss_indir_tbl[i] = indir[i];
+		adapter->rss_indir_tbl[i] = rxfh->indir[i];
 
 	igc_write_rss_indir_tbl(adapter);
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index dd722b0381e0..af55f19d5bba 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -3107,35 +3107,37 @@ static void ixgbe_get_reta(struct ixgbe_adapter *adapter, u32 *indir)
 		indir[i] = adapter->rss_indir_tbl[i] & rss_m;
 }
 
-static int ixgbe_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
-			  u8 *hfunc)
+static int ixgbe_get_rxfh(struct net_device *netdev,
+			  struct ethtool_rxfh_param *rxfh)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
-	if (indir)
-		ixgbe_get_reta(adapter, indir);
+	if (rxfh->indir)
+		ixgbe_get_reta(adapter, rxfh->indir);
 
-	if (key)
-		memcpy(key, adapter->rss_key, ixgbe_get_rxfh_key_size(netdev));
+	if (rxfh->key)
+		memcpy(rxfh->key, adapter->rss_key,
+		       ixgbe_get_rxfh_key_size(netdev));
 
 	return 0;
 }
 
-static int ixgbe_set_rxfh(struct net_device *netdev, const u32 *indir,
-			  const u8 *key, const u8 hfunc)
+static int ixgbe_set_rxfh(struct net_device *netdev,
+			  struct ethtool_rxfh_param *rxfh,
+			  struct netlink_ext_ack *extack)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 	int i;
 	u32 reta_entries = ixgbe_rss_indir_tbl_entries(adapter);
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
 	/* Fill out the redirection table */
-	if (indir) {
+	if (rxfh->indir) {
 		int max_queues = min_t(int, adapter->num_rx_queues,
 				       ixgbe_rss_indir_tbl_max(adapter));
 
@@ -3146,18 +3148,19 @@ static int ixgbe_set_rxfh(struct net_device *netdev, const u32 *indir,
 
 		/* Verify user input. */
 		for (i = 0; i < reta_entries; i++)
-			if (indir[i] >= max_queues)
+			if (rxfh->indir[i] >= max_queues)
 				return -EINVAL;
 
 		for (i = 0; i < reta_entries; i++)
-			adapter->rss_indir_tbl[i] = indir[i];
+			adapter->rss_indir_tbl[i] = rxfh->indir[i];
 
 		ixgbe_store_reta(adapter);
 	}
 
 	/* Fill out the rss hash key */
-	if (key) {
-		memcpy(adapter->rss_key, key, ixgbe_get_rxfh_key_size(netdev));
+	if (rxfh->key) {
+		memcpy(adapter->rss_key, rxfh->key,
+		       ixgbe_get_rxfh_key_size(netdev));
 		ixgbe_store_key(adapter);
 	}
 
diff --git a/drivers/net/ethernet/intel/ixgbevf/ethtool.c b/drivers/net/ethernet/intel/ixgbevf/ethtool.c
index 296915414a7c..7ac53171b041 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ethtool.c
@@ -897,40 +897,41 @@ static u32 ixgbevf_get_rxfh_key_size(struct net_device *netdev)
 	return IXGBEVF_RSS_HASH_KEY_SIZE;
 }
 
-static int ixgbevf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
-			    u8 *hfunc)
+static int ixgbevf_get_rxfh(struct net_device *netdev,
+			    struct ethtool_rxfh_param *rxfh)
 {
 	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
 	int err = 0;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
 	if (adapter->hw.mac.type >= ixgbe_mac_X550_vf) {
-		if (key)
-			memcpy(key, adapter->rss_key,
+		if (rxfh->key)
+			memcpy(rxfh->key, adapter->rss_key,
 			       ixgbevf_get_rxfh_key_size(netdev));
 
-		if (indir) {
+		if (rxfh->indir) {
 			int i;
 
 			for (i = 0; i < IXGBEVF_X550_VFRETA_SIZE; i++)
-				indir[i] = adapter->rss_indir_tbl[i];
+				rxfh->indir[i] = adapter->rss_indir_tbl[i];
 		}
 	} else {
 		/* If neither indirection table nor hash key was requested
 		 *  - just return a success avoiding taking any locks.
 		 */
-		if (!indir && !key)
+		if (!rxfh->indir && !rxfh->key)
 			return 0;
 
 		spin_lock_bh(&adapter->mbx_lock);
-		if (indir)
-			err = ixgbevf_get_reta_locked(&adapter->hw, indir,
+		if (rxfh->indir)
+			err = ixgbevf_get_reta_locked(&adapter->hw,
+						      rxfh->indir,
 						      adapter->num_rx_queues);
 
-		if (!err && key)
-			err = ixgbevf_get_rss_key_locked(&adapter->hw, key);
+		if (!err && rxfh->key)
+			err = ixgbevf_get_rss_key_locked(&adapter->hw,
+							 rxfh->key);
 
 		spin_unlock_bh(&adapter->mbx_lock);
 	}
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 29aac327574d..a641b3534ca3 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -5030,8 +5030,9 @@ static int  mvneta_config_rss(struct mvneta_port *pp)
 	return 0;
 }
 
-static int mvneta_ethtool_set_rxfh(struct net_device *dev, const u32 *indir,
-				   const u8 *key, const u8 hfunc)
+static int mvneta_ethtool_set_rxfh(struct net_device *dev,
+				   struct ethtool_rxfh_param *rxfh,
+				   struct netlink_ext_ack *extack)
 {
 	struct mvneta_port *pp = netdev_priv(dev);
 
@@ -5042,20 +5043,21 @@ static int mvneta_ethtool_set_rxfh(struct net_device *dev, const u32 *indir,
 	/* We require at least one supported parameter to be changed
 	 * and no change in any of the unsupported parameters
 	 */
-	if (key ||
-	    (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP))
+	if (rxfh->key ||
+	    (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	     rxfh->hfunc != ETH_RSS_HASH_TOP))
 		return -EOPNOTSUPP;
 
-	if (!indir)
+	if (!rxfh->indir)
 		return 0;
 
-	memcpy(pp->indir, indir, MVNETA_RSS_LU_TABLE_SIZE);
+	memcpy(pp->indir, rxfh->indir, MVNETA_RSS_LU_TABLE_SIZE);
 
 	return mvneta_config_rss(pp);
 }
 
-static int mvneta_ethtool_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
-				   u8 *hfunc)
+static int mvneta_ethtool_get_rxfh(struct net_device *dev,
+				   struct ethtool_rxfh_param *rxfh)
 {
 	struct mvneta_port *pp = netdev_priv(dev);
 
@@ -5063,13 +5065,12 @@ static int mvneta_ethtool_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
 	if (pp->neta_armada3700)
 		return -EOPNOTSUPP;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
-	if (!indir)
+	if (!rxfh->indir)
 		return 0;
 
-	memcpy(indir, pp->indir, MVNETA_RSS_LU_TABLE_SIZE);
+	memcpy(rxfh->indir, pp->indir, MVNETA_RSS_LU_TABLE_SIZE);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 93137606869e..ceef48ddd26e 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -5634,8 +5634,8 @@ static u32 mvpp2_ethtool_get_rxfh_indir_size(struct net_device *dev)
 	return mvpp22_rss_is_supported(port) ? MVPP22_RSS_TABLE_ENTRIES : 0;
 }
 
-static int mvpp2_ethtool_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
-				  u8 *hfunc)
+static int mvpp2_ethtool_get_rxfh(struct net_device *dev,
+				  struct ethtool_rxfh_param *rxfh)
 {
 	struct mvpp2_port *port = netdev_priv(dev);
 	int ret = 0;
@@ -5643,17 +5643,17 @@ static int mvpp2_ethtool_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
 	if (!mvpp22_rss_is_supported(port))
 		return -EOPNOTSUPP;
 
-	if (indir)
-		ret = mvpp22_port_rss_ctx_indir_get(port, 0, indir);
+	if (rxfh->indir)
+		ret = mvpp22_port_rss_ctx_indir_get(port, 0, rxfh->indir);
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_CRC32;
+	rxfh->hfunc = ETH_RSS_HASH_CRC32;
 
 	return ret;
 }
 
-static int mvpp2_ethtool_set_rxfh(struct net_device *dev, const u32 *indir,
-				  const u8 *key, const u8 hfunc)
+static int mvpp2_ethtool_set_rxfh(struct net_device *dev,
+				  struct ethtool_rxfh_param *rxfh,
+				  struct netlink_ext_ack *extack)
 {
 	struct mvpp2_port *port = netdev_priv(dev);
 	int ret = 0;
@@ -5661,20 +5661,22 @@ static int mvpp2_ethtool_set_rxfh(struct net_device *dev, const u32 *indir,
 	if (!mvpp22_rss_is_supported(port))
 		return -EOPNOTSUPP;
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_CRC32)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_CRC32)
 		return -EOPNOTSUPP;
 
-	if (key)
+	if (rxfh->key)
 		return -EOPNOTSUPP;
 
-	if (indir)
-		ret = mvpp22_port_rss_ctx_indir_set(port, 0, indir);
+	if (rxfh->indir)
+		ret = mvpp22_port_rss_ctx_indir_set(port, 0, rxfh->indir);
 
 	return ret;
 }
 
-static int mvpp2_ethtool_get_rxfh_context(struct net_device *dev, u32 *indir,
-					  u8 *key, u8 *hfunc, u32 rss_context)
+static int mvpp2_ethtool_get_rxfh_context(struct net_device *dev,
+					  struct ethtool_rxfh_param *rxfh,
+					  u32 rss_context)
 {
 	struct mvpp2_port *port = netdev_priv(dev);
 	int ret = 0;
@@ -5684,19 +5686,18 @@ static int mvpp2_ethtool_get_rxfh_context(struct net_device *dev, u32 *indir,
 	if (rss_context >= MVPP22_N_RSS_TABLES)
 		return -EINVAL;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_CRC32;
+	rxfh->hfunc = ETH_RSS_HASH_CRC32;
 
-	if (indir)
-		ret = mvpp22_port_rss_ctx_indir_get(port, rss_context, indir);
+	if (rxfh->indir)
+		ret = mvpp22_port_rss_ctx_indir_get(port, rss_context,
+						    rxfh->indir);
 
 	return ret;
 }
 
 static int mvpp2_ethtool_set_rxfh_context(struct net_device *dev,
-					  const u32 *indir, const u8 *key,
-					  const u8 hfunc, u32 *rss_context,
-					  bool delete)
+					  struct ethtool_rxfh_param *rxfh,
+					  u32 *rss_context, bool delete)
 {
 	struct mvpp2_port *port = netdev_priv(dev);
 	int ret;
@@ -5704,10 +5705,11 @@ static int mvpp2_ethtool_set_rxfh_context(struct net_device *dev,
 	if (!mvpp22_rss_is_supported(port))
 		return -EOPNOTSUPP;
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_CRC32)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_CRC32)
 		return -EOPNOTSUPP;
 
-	if (key)
+	if (rxfh->key)
 		return -EOPNOTSUPP;
 
 	if (delete)
@@ -5719,7 +5721,7 @@ static int mvpp2_ethtool_set_rxfh_context(struct net_device *dev,
 			return ret;
 	}
 
-	return mvpp22_port_rss_ctx_indir_set(port, *rss_context, indir);
+	return mvpp22_port_rss_ctx_indir_set(port, *rss_context, rxfh->indir);
 }
 /* Device ops */
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
index 53f6258a973c..a2c182d7bfc4 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
@@ -836,8 +836,8 @@ static int otx2_rss_ctx_create(struct otx2_nic *pfvf,
 }
 
 /* RSS context configuration */
-static int otx2_set_rxfh_context(struct net_device *dev, const u32 *indir,
-				 const u8 *hkey, const u8 hfunc,
+static int otx2_set_rxfh_context(struct net_device *dev,
+				 struct ethtool_rxfh_param *rxfh,
 				 u32 *rss_context, bool delete)
 {
 	struct otx2_nic *pfvf = netdev_priv(dev);
@@ -845,7 +845,8 @@ static int otx2_set_rxfh_context(struct net_device *dev, const u32 *indir,
 	struct otx2_rss_info *rss;
 	int ret, idx;
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
 	if (*rss_context != ETH_RXFH_CONTEXT_ALLOC &&
@@ -859,8 +860,8 @@ static int otx2_set_rxfh_context(struct net_device *dev, const u32 *indir,
 		return -EIO;
 	}
 
-	if (hkey) {
-		memcpy(rss->key, hkey, sizeof(rss->key));
+	if (rxfh->key) {
+		memcpy(rss->key, rxfh->key, sizeof(rss->key));
 		otx2_set_rss_key(pfvf);
 	}
 	if (delete)
@@ -871,28 +872,29 @@ static int otx2_set_rxfh_context(struct net_device *dev, const u32 *indir,
 		if (ret)
 			return ret;
 	}
-	if (indir) {
+	if (rxfh->indir) {
 		rss_ctx = rss->rss_ctx[*rss_context];
 		for (idx = 0; idx < rss->rss_size; idx++)
-			rss_ctx->ind_tbl[idx] = indir[idx];
+			rss_ctx->ind_tbl[idx] = rxfh->indir[idx];
 	}
 	otx2_set_rss_table(pfvf, *rss_context);
 
 	return 0;
 }
 
-static int otx2_get_rxfh_context(struct net_device *dev, u32 *indir,
-				 u8 *hkey, u8 *hfunc, u32 rss_context)
+static int otx2_get_rxfh_context(struct net_device *dev,
+				 struct ethtool_rxfh_param *rxfh,
+				 u32 rss_context)
 {
 	struct otx2_nic *pfvf = netdev_priv(dev);
 	struct otx2_rss_ctx *rss_ctx;
 	struct otx2_rss_info *rss;
+	u32 *indir = rxfh->indir;
 	int idx, rx_queues;
 
 	rss = &pfvf->hw.rss_info;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
 	if (!indir)
 		return 0;
@@ -914,28 +916,29 @@ static int otx2_get_rxfh_context(struct net_device *dev, u32 *indir,
 		for (idx = 0; idx < rss->rss_size; idx++)
 			indir[idx] = rss_ctx->ind_tbl[idx];
 	}
-	if (hkey)
-		memcpy(hkey, rss->key, sizeof(rss->key));
+	if (rxfh->key)
+		memcpy(rxfh->key, rss->key, sizeof(rss->key));
 
 	return 0;
 }
 
 /* Get RSS configuration */
-static int otx2_get_rxfh(struct net_device *dev, u32 *indir,
-			 u8 *hkey, u8 *hfunc)
+static int otx2_get_rxfh(struct net_device *dev,
+			 struct ethtool_rxfh_param *rxfh)
 {
-	return otx2_get_rxfh_context(dev, indir, hkey, hfunc,
+	return otx2_get_rxfh_context(dev, rxfh,
 				     DEFAULT_RSS_CONTEXT_GROUP);
 }
 
 /* Configure RSS table and hash key */
-static int otx2_set_rxfh(struct net_device *dev, const u32 *indir,
-			 const u8 *hkey, const u8 hfunc)
+static int otx2_set_rxfh(struct net_device *dev,
+			 struct ethtool_rxfh_param *rxfh,
+			 struct netlink_ext_ack *extack)
 {
 
 	u32 rss_context = DEFAULT_RSS_CONTEXT_GROUP;
 
-	return otx2_set_rxfh_context(dev, indir, hkey, hfunc, &rss_context, 0);
+	return otx2_set_rxfh_context(dev, rxfh, &rss_context, 0);
 }
 
 static u32 otx2_get_msglevel(struct net_device *netdev)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 164a13272faa..619e1c3ef7f9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1258,8 +1258,8 @@ static int mlx4_en_check_rxfh_func(struct net_device *dev, u8 hfunc)
 	return -EINVAL;
 }
 
-static int mlx4_en_get_rxfh(struct net_device *dev, u32 *ring_index, u8 *key,
-			    u8 *hfunc)
+static int mlx4_en_get_rxfh(struct net_device *dev,
+			    struct ethtool_rxfh_param *rxfh)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	u32 n = mlx4_en_get_rxfh_indir_size(dev);
@@ -1269,19 +1269,19 @@ static int mlx4_en_get_rxfh(struct net_device *dev, u32 *ring_index, u8 *key,
 	rss_rings = rounddown_pow_of_two(rss_rings);
 
 	for (i = 0; i < n; i++) {
-		if (!ring_index)
+		if (!rxfh->indir)
 			break;
-		ring_index[i] = i % rss_rings;
+		rxfh->indir[i] = i % rss_rings;
 	}
-	if (key)
-		memcpy(key, priv->rss_key, MLX4_EN_RSS_KEY_SIZE);
-	if (hfunc)
-		*hfunc = priv->rss_hash_fn;
+	if (rxfh->key)
+		memcpy(rxfh->key, priv->rss_key, MLX4_EN_RSS_KEY_SIZE);
+	rxfh->hfunc = priv->rss_hash_fn;
 	return 0;
 }
 
-static int mlx4_en_set_rxfh(struct net_device *dev, const u32 *ring_index,
-			    const u8 *key, const u8 hfunc)
+static int mlx4_en_set_rxfh(struct net_device *dev,
+			    struct ethtool_rxfh_param *rxfh,
+			    struct netlink_ext_ack *extack)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	u32 n = mlx4_en_get_rxfh_indir_size(dev);
@@ -1295,12 +1295,12 @@ static int mlx4_en_set_rxfh(struct net_device *dev, const u32 *ring_index,
 	 * between rings
 	 */
 	for (i = 0; i < n; i++) {
-		if (!ring_index)
+		if (!rxfh->indir)
 			break;
-		if (i > 0 && !ring_index[i] && !rss_rings)
+		if (i > 0 && !rxfh->indir[i] && !rss_rings)
 			rss_rings = i;
 
-		if (ring_index[i] != (i % (rss_rings ?: n)))
+		if (rxfh->indir[i] != (i % (rss_rings ?: n)))
 			return -EINVAL;
 	}
 
@@ -1311,8 +1311,8 @@ static int mlx4_en_set_rxfh(struct net_device *dev, const u32 *ring_index,
 	if (!is_power_of_2(rss_rings))
 		return -EINVAL;
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE) {
-		err = mlx4_en_check_rxfh_func(dev, hfunc);
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE) {
+		err = mlx4_en_check_rxfh_func(dev, rxfh->hfunc);
 		if (err)
 			return err;
 	}
@@ -1323,12 +1323,12 @@ static int mlx4_en_set_rxfh(struct net_device *dev, const u32 *ring_index,
 		mlx4_en_stop_port(dev, 1);
 	}
 
-	if (ring_index)
+	if (rxfh->indir)
 		priv->prof->rss_rings = rss_rings;
-	if (key)
-		memcpy(priv->rss_key, key, MLX4_EN_RSS_KEY_SIZE);
-	if (hfunc !=  ETH_RSS_HASH_NO_CHANGE)
-		priv->rss_hash_fn = hfunc;
+	if (rxfh->key)
+		memcpy(priv->rss_key, rxfh->key, MLX4_EN_RSS_KEY_SIZE);
+	if (rxfh->hfunc !=  ETH_RSS_HASH_NO_CHANGE)
+		priv->rss_hash_fn = rxfh->hfunc;
 
 	if (port_up) {
 		err = mlx4_en_start_port(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 43f027bf2da3..2cb47268bac6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -1175,9 +1175,9 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv,
 				     struct ethtool_link_ksettings *link_ksettings);
 int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 				     const struct ethtool_link_ksettings *link_ksettings);
-int mlx5e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, u8 *hfunc);
-int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir, const u8 *key,
-		   const u8 hfunc);
+int mlx5e_get_rxfh(struct net_device *dev, struct ethtool_rxfh_param *rxfh);
+int mlx5e_set_rxfh(struct net_device *dev, struct ethtool_rxfh_param *rxfh,
+		   struct netlink_ext_ack *extack);
 u32 mlx5e_ethtool_get_rxfh_key_size(struct mlx5e_priv *priv);
 u32 mlx5e_ethtool_get_rxfh_indir_size(struct mlx5e_priv *priv);
 int mlx5e_ethtool_get_ts_info(struct mlx5e_priv *priv,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 792a0ea544cd..110cb7973eae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1262,23 +1262,26 @@ static u32 mlx5e_get_rxfh_indir_size(struct net_device *netdev)
 	return mlx5e_ethtool_get_rxfh_indir_size(priv);
 }
 
-static int mlx5e_get_rxfh_context(struct net_device *dev, u32 *indir,
-				  u8 *key, u8 *hfunc, u32 rss_context)
+static int mlx5e_get_rxfh_context(struct net_device *dev,
+				  struct ethtool_rxfh_param *rxfh,
+				  u32 rss_context)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	int err;
 
 	mutex_lock(&priv->state_lock);
-	err = mlx5e_rx_res_rss_get_rxfh(priv->rx_res, rss_context, indir, key, hfunc);
+	err = mlx5e_rx_res_rss_get_rxfh(priv->rx_res, rss_context,
+					rxfh->indir, rxfh->key, &rxfh->hfunc);
 	mutex_unlock(&priv->state_lock);
 	return err;
 }
 
-static int mlx5e_set_rxfh_context(struct net_device *dev, const u32 *indir,
-				  const u8 *key, const u8 hfunc,
+static int mlx5e_set_rxfh_context(struct net_device *dev,
+				  struct ethtool_rxfh_param *rxfh,
 				  u32 *rss_context, bool delete)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
+	u8 hfunc = rxfh->hfunc;
 	int err;
 
 	mutex_lock(&priv->state_lock);
@@ -1295,7 +1298,8 @@ static int mlx5e_set_rxfh_context(struct net_device *dev, const u32 *indir,
 			goto unlock;
 	}
 
-	err = mlx5e_rx_res_rss_set_rxfh(priv->rx_res, *rss_context, indir, key,
+	err = mlx5e_rx_res_rss_set_rxfh(priv->rx_res, *rss_context,
+					rxfh->indir, rxfh->key,
 					hfunc == ETH_RSS_HASH_NO_CHANGE ? NULL : &hfunc);
 
 unlock:
@@ -1303,20 +1307,20 @@ unlock:
 	return err;
 }
 
-int mlx5e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
-		   u8 *hfunc)
+int mlx5e_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh)
 {
-	return mlx5e_get_rxfh_context(netdev, indir, key, hfunc, 0);
+	return mlx5e_get_rxfh_context(netdev, rxfh, 0);
 }
 
-int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
-		   const u8 *key, const u8 hfunc)
+int mlx5e_set_rxfh(struct net_device *dev, struct ethtool_rxfh_param *rxfh,
+		   struct netlink_ext_ack *extack)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
+	u8 hfunc = rxfh->hfunc;
 	int err;
 
 	mutex_lock(&priv->state_lock);
-	err = mlx5e_rx_res_rss_set_rxfh(priv->rx_res, 0, indir, key,
+	err = mlx5e_rx_res_rss_set_rxfh(priv->rx_res, 0, rxfh->indir, rxfh->key,
 					hfunc == ETH_RSS_HASH_NO_CHANGE ? NULL : &hfunc);
 	mutex_unlock(&priv->state_lock);
 	return err;
diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c
index 6961cfc55fb9..8c4a2bb6a537 100644
--- a/drivers/net/ethernet/microchip/lan743x_ethtool.c
+++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c
@@ -934,11 +934,11 @@ static u32 lan743x_ethtool_get_rxfh_indir_size(struct net_device *netdev)
 }
 
 static int lan743x_ethtool_get_rxfh(struct net_device *netdev,
-				    u32 *indir, u8 *key, u8 *hfunc)
+				    struct ethtool_rxfh_param *rxfh)
 {
 	struct lan743x_adapter *adapter = netdev_priv(netdev);
 
-	if (indir) {
+	if (rxfh->indir) {
 		int dw_index;
 		int byte_index = 0;
 
@@ -947,17 +947,17 @@ static int lan743x_ethtool_get_rxfh(struct net_device *netdev,
 				lan743x_csr_read(adapter, RFE_INDX(dw_index));
 
 			byte_index = dw_index << 2;
-			indir[byte_index + 0] =
+			rxfh->indir[byte_index + 0] =
 				((four_entries >> 0) & 0x000000FF);
-			indir[byte_index + 1] =
+			rxfh->indir[byte_index + 1] =
 				((four_entries >> 8) & 0x000000FF);
-			indir[byte_index + 2] =
+			rxfh->indir[byte_index + 2] =
 				((four_entries >> 16) & 0x000000FF);
-			indir[byte_index + 3] =
+			rxfh->indir[byte_index + 3] =
 				((four_entries >> 24) & 0x000000FF);
 		}
 	}
-	if (key) {
+	if (rxfh->key) {
 		int dword_index;
 		int byte_index = 0;
 
@@ -967,28 +967,30 @@ static int lan743x_ethtool_get_rxfh(struct net_device *netdev,
 						 RFE_HASH_KEY(dword_index));
 
 			byte_index = dword_index << 2;
-			key[byte_index + 0] =
+			rxfh->key[byte_index + 0] =
 				((four_entries >> 0) & 0x000000FF);
-			key[byte_index + 1] =
+			rxfh->key[byte_index + 1] =
 				((four_entries >> 8) & 0x000000FF);
-			key[byte_index + 2] =
+			rxfh->key[byte_index + 2] =
 				((four_entries >> 16) & 0x000000FF);
-			key[byte_index + 3] =
+			rxfh->key[byte_index + 3] =
 				((four_entries >> 24) & 0x000000FF);
 		}
 	}
-	if (hfunc)
-		(*hfunc) = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 	return 0;
 }
 
 static int lan743x_ethtool_set_rxfh(struct net_device *netdev,
-				    const u32 *indir, const u8 *key,
-				    const u8 hfunc)
+				    struct ethtool_rxfh_param *rxfh,
+				    struct netlink_ext_ack *extack)
 {
 	struct lan743x_adapter *adapter = netdev_priv(netdev);
+	u32 *indir = rxfh->indir;
+	u8 *key = rxfh->key;
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
 	if (indir) {
diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
index 777e65b8223d..ab2413d71f6c 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
@@ -248,28 +248,28 @@ static u32 mana_rss_indir_size(struct net_device *ndev)
 	return MANA_INDIRECT_TABLE_SIZE;
 }
 
-static int mana_get_rxfh(struct net_device *ndev, u32 *indir, u8 *key,
-			 u8 *hfunc)
+static int mana_get_rxfh(struct net_device *ndev,
+			 struct ethtool_rxfh_param *rxfh)
 {
 	struct mana_port_context *apc = netdev_priv(ndev);
 	int i;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP; /* Toeplitz */
+	rxfh->hfunc = ETH_RSS_HASH_TOP; /* Toeplitz */
 
-	if (indir) {
+	if (rxfh->indir) {
 		for (i = 0; i < MANA_INDIRECT_TABLE_SIZE; i++)
-			indir[i] = apc->indir_table[i];
+			rxfh->indir[i] = apc->indir_table[i];
 	}
 
-	if (key)
-		memcpy(key, apc->hashkey, MANA_HASH_KEY_SIZE);
+	if (rxfh->key)
+		memcpy(rxfh->key, apc->hashkey, MANA_HASH_KEY_SIZE);
 
 	return 0;
 }
 
-static int mana_set_rxfh(struct net_device *ndev, const u32 *indir,
-			 const u8 *key, const u8 hfunc)
+static int mana_set_rxfh(struct net_device *ndev,
+			 struct ethtool_rxfh_param *rxfh,
+			 struct netlink_ext_ack *extack)
 {
 	struct mana_port_context *apc = netdev_priv(ndev);
 	bool update_hash = false, update_table = false;
@@ -280,25 +280,26 @@ static int mana_set_rxfh(struct net_device *ndev, const u32 *indir,
 	if (!apc->port_is_up)
 		return -EOPNOTSUPP;
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
-	if (indir) {
+	if (rxfh->indir) {
 		for (i = 0; i < MANA_INDIRECT_TABLE_SIZE; i++)
-			if (indir[i] >= apc->num_queues)
+			if (rxfh->indir[i] >= apc->num_queues)
 				return -EINVAL;
 
 		update_table = true;
 		for (i = 0; i < MANA_INDIRECT_TABLE_SIZE; i++) {
 			save_table[i] = apc->indir_table[i];
-			apc->indir_table[i] = indir[i];
+			apc->indir_table[i] = rxfh->indir[i];
 		}
 	}
 
-	if (key) {
+	if (rxfh->key) {
 		update_hash = true;
 		memcpy(save_key, apc->hashkey, MANA_HASH_KEY_SIZE);
-		memcpy(apc->hashkey, key, MANA_HASH_KEY_SIZE);
+		memcpy(apc->hashkey, rxfh->key, MANA_HASH_KEY_SIZE);
 	}
 
 	err = mana_config_rss(apc, TRI_STATE_TRUE, update_hash, update_table);
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
index ff9f39969215..fbca8d0efd85 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
@@ -1794,8 +1794,8 @@ static u32 nfp_net_get_rxfh_key_size(struct net_device *netdev)
 	return nfp_net_rss_key_sz(nn);
 }
 
-static int nfp_net_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
-			    u8 *hfunc)
+static int nfp_net_get_rxfh(struct net_device *netdev,
+			    struct ethtool_rxfh_param *rxfh)
 {
 	struct nfp_net *nn = netdev_priv(netdev);
 	int i;
@@ -1803,41 +1803,41 @@ static int nfp_net_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 	if (!(nn->cap & NFP_NET_CFG_CTRL_RSS_ANY))
 		return -EOPNOTSUPP;
 
-	if (indir)
+	if (rxfh->indir)
 		for (i = 0; i < ARRAY_SIZE(nn->rss_itbl); i++)
-			indir[i] = nn->rss_itbl[i];
-	if (key)
-		memcpy(key, nn->rss_key, nfp_net_rss_key_sz(nn));
-	if (hfunc) {
-		*hfunc = nn->rss_hfunc;
-		if (*hfunc >= 1 << ETH_RSS_HASH_FUNCS_COUNT)
-			*hfunc = ETH_RSS_HASH_UNKNOWN;
-	}
+			rxfh->indir[i] = nn->rss_itbl[i];
+	if (rxfh->key)
+		memcpy(rxfh->key, nn->rss_key, nfp_net_rss_key_sz(nn));
+
+	rxfh->hfunc = nn->rss_hfunc;
+	if (rxfh->hfunc >= 1 << ETH_RSS_HASH_FUNCS_COUNT)
+		rxfh->hfunc = ETH_RSS_HASH_UNKNOWN;
 
 	return 0;
 }
 
 static int nfp_net_set_rxfh(struct net_device *netdev,
-			    const u32 *indir, const u8 *key,
-			    const u8 hfunc)
+			    struct ethtool_rxfh_param *rxfh,
+			    struct netlink_ext_ack *extack)
 {
 	struct nfp_net *nn = netdev_priv(netdev);
 	int i;
 
 	if (!(nn->cap & NFP_NET_CFG_CTRL_RSS_ANY) ||
-	    !(hfunc == ETH_RSS_HASH_NO_CHANGE || hfunc == nn->rss_hfunc))
+	    !(rxfh->hfunc == ETH_RSS_HASH_NO_CHANGE ||
+	      rxfh->hfunc == nn->rss_hfunc))
 		return -EOPNOTSUPP;
 
-	if (!key && !indir)
+	if (!rxfh->key && !rxfh->indir)
 		return 0;
 
-	if (key) {
-		memcpy(nn->rss_key, key, nfp_net_rss_key_sz(nn));
+	if (rxfh->key) {
+		memcpy(nn->rss_key, rxfh->key, nfp_net_rss_key_sz(nn));
 		nfp_net_rss_write_key(nn);
 	}
-	if (indir) {
+	if (rxfh->indir) {
 		for (i = 0; i < ARRAY_SIZE(nn->rss_itbl); i++)
-			nn->rss_itbl[i] = indir[i];
+			nn->rss_itbl[i] = rxfh->indir[i];
 
 		nfp_net_rss_write_itbl(nn);
 	}
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
index 3a6b0a9bc241..cd3c0b01402e 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
@@ -823,36 +823,38 @@ static u32 ionic_get_rxfh_key_size(struct net_device *netdev)
 	return IONIC_RSS_HASH_KEY_SIZE;
 }
 
-static int ionic_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
-			  u8 *hfunc)
+static int ionic_get_rxfh(struct net_device *netdev,
+			  struct ethtool_rxfh_param *rxfh)
 {
 	struct ionic_lif *lif = netdev_priv(netdev);
 	unsigned int i, tbl_sz;
 
-	if (indir) {
+	if (rxfh->indir) {
 		tbl_sz = le16_to_cpu(lif->ionic->ident.lif.eth.rss_ind_tbl_sz);
 		for (i = 0; i < tbl_sz; i++)
-			indir[i] = lif->rss_ind_tbl[i];
+			rxfh->indir[i] = lif->rss_ind_tbl[i];
 	}
 
-	if (key)
-		memcpy(key, lif->rss_hash_key, IONIC_RSS_HASH_KEY_SIZE);
+	if (rxfh->key)
+		memcpy(rxfh->key, lif->rss_hash_key, IONIC_RSS_HASH_KEY_SIZE);
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
 	return 0;
 }
 
-static int ionic_set_rxfh(struct net_device *netdev, const u32 *indir,
-			  const u8 *key, const u8 hfunc)
+static int ionic_set_rxfh(struct net_device *netdev,
+			  struct ethtool_rxfh_param *rxfh,
+			  struct netlink_ext_ack *extack)
 {
 	struct ionic_lif *lif = netdev_priv(netdev);
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
-	return ionic_lif_rss_config(lif, lif->rss_types, key, indir);
+	return ionic_lif_rss_config(lif, lif->rss_types,
+				    rxfh->key, rxfh->indir);
 }
 
 static int ionic_set_tunable(struct net_device *dev,
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
index b6b849a079ed..0e240b5ab8d4 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
@@ -1370,28 +1370,29 @@ static u32 qede_get_rxfh_key_size(struct net_device *dev)
 	return sizeof(edev->rss_key);
 }
 
-static int qede_get_rxfh(struct net_device *dev, u32 *indir, u8 *key, u8 *hfunc)
+static int qede_get_rxfh(struct net_device *dev,
+			 struct ethtool_rxfh_param *rxfh)
 {
 	struct qede_dev *edev = netdev_priv(dev);
 	int i;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
-	if (!indir)
+	if (!rxfh->indir)
 		return 0;
 
 	for (i = 0; i < QED_RSS_IND_TABLE_SIZE; i++)
-		indir[i] = edev->rss_ind_table[i];
+		rxfh->indir[i] = edev->rss_ind_table[i];
 
-	if (key)
-		memcpy(key, edev->rss_key, qede_get_rxfh_key_size(dev));
+	if (rxfh->key)
+		memcpy(rxfh->key, edev->rss_key, qede_get_rxfh_key_size(dev));
 
 	return 0;
 }
 
-static int qede_set_rxfh(struct net_device *dev, const u32 *indir,
-			 const u8 *key, const u8 hfunc)
+static int qede_set_rxfh(struct net_device *dev,
+			 struct ethtool_rxfh_param *rxfh,
+			 struct netlink_ext_ack *extack)
 {
 	struct qed_update_vport_params *vport_update_params;
 	struct qede_dev *edev = netdev_priv(dev);
@@ -1403,20 +1404,21 @@ static int qede_set_rxfh(struct net_device *dev, const u32 *indir,
 		return -EOPNOTSUPP;
 	}
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
-	if (!indir && !key)
+	if (!rxfh->indir && !rxfh->key)
 		return 0;
 
-	if (indir) {
+	if (rxfh->indir) {
 		for (i = 0; i < QED_RSS_IND_TABLE_SIZE; i++)
-			edev->rss_ind_table[i] = indir[i];
+			edev->rss_ind_table[i] = rxfh->indir[i];
 		edev->rss_params_inited |= QEDE_RSS_INDIR_INITED;
 	}
 
-	if (key) {
-		memcpy(&edev->rss_key, key, qede_get_rxfh_key_size(dev));
+	if (rxfh->key) {
+		memcpy(&edev->rss_key, rxfh->key, qede_get_rxfh_key_size(dev));
 		edev->rss_params_inited |= QEDE_RSS_KEY_INITED;
 	}
 
diff --git a/drivers/net/ethernet/sfc/ethtool_common.c b/drivers/net/ethernet/sfc/ethtool_common.c
index a8cbceeb301b..e32ae9038d9e 100644
--- a/drivers/net/ethernet/sfc/ethtool_common.c
+++ b/drivers/net/ethernet/sfc/ethtool_common.c
@@ -1163,8 +1163,8 @@ u32 efx_ethtool_get_rxfh_key_size(struct net_device *net_dev)
 	return efx->type->rx_hash_key_size;
 }
 
-int efx_ethtool_get_rxfh(struct net_device *net_dev, u32 *indir, u8 *key,
-			 u8 *hfunc)
+int efx_ethtool_get_rxfh(struct net_device *net_dev,
+			 struct ethtool_rxfh_param *rxfh)
 {
 	struct efx_nic *efx = efx_netdev_priv(net_dev);
 	int rc;
@@ -1173,24 +1173,27 @@ int efx_ethtool_get_rxfh(struct net_device *net_dev, u32 *indir, u8 *key,
 	if (rc)
 		return rc;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
-	if (indir)
-		memcpy(indir, efx->rss_context.rx_indir_table,
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+	if (rxfh->indir)
+		memcpy(rxfh->indir, efx->rss_context.rx_indir_table,
 		       sizeof(efx->rss_context.rx_indir_table));
-	if (key)
-		memcpy(key, efx->rss_context.rx_hash_key,
+	if (rxfh->key)
+		memcpy(rxfh->key, efx->rss_context.rx_hash_key,
 		       efx->type->rx_hash_key_size);
 	return 0;
 }
 
-int efx_ethtool_set_rxfh(struct net_device *net_dev, const u32 *indir,
-			 const u8 *key, const u8 hfunc)
+int efx_ethtool_set_rxfh(struct net_device *net_dev,
+			 struct ethtool_rxfh_param *rxfh,
+			 struct netlink_ext_ack *extack)
 {
 	struct efx_nic *efx = efx_netdev_priv(net_dev);
+	u32 *indir = rxfh->indir;
+	u8 *key = rxfh->key;
 
 	/* Hash function is Toeplitz, cannot be changed */
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 	if (!indir && !key)
 		return 0;
@@ -1203,8 +1206,9 @@ int efx_ethtool_set_rxfh(struct net_device *net_dev, const u32 *indir,
 	return efx->type->rx_push_rss_config(efx, true, indir, key);
 }
 
-int efx_ethtool_get_rxfh_context(struct net_device *net_dev, u32 *indir,
-				 u8 *key, u8 *hfunc, u32 rss_context)
+int efx_ethtool_get_rxfh_context(struct net_device *net_dev,
+				 struct ethtool_rxfh_param *rxfh,
+				 u32 rss_context)
 {
 	struct efx_nic *efx = efx_netdev_priv(net_dev);
 	struct efx_rss_context *ctx;
@@ -1223,31 +1227,34 @@ int efx_ethtool_get_rxfh_context(struct net_device *net_dev, u32 *indir,
 	if (rc)
 		goto out_unlock;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
-	if (indir)
-		memcpy(indir, ctx->rx_indir_table, sizeof(ctx->rx_indir_table));
-	if (key)
-		memcpy(key, ctx->rx_hash_key, efx->type->rx_hash_key_size);
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+	if (rxfh->indir)
+		memcpy(rxfh->indir, ctx->rx_indir_table,
+		       sizeof(ctx->rx_indir_table));
+	if (rxfh->key)
+		memcpy(rxfh->key, ctx->rx_hash_key,
+		       efx->type->rx_hash_key_size);
 out_unlock:
 	mutex_unlock(&efx->rss_lock);
 	return rc;
 }
 
 int efx_ethtool_set_rxfh_context(struct net_device *net_dev,
-				 const u32 *indir, const u8 *key,
-				 const u8 hfunc, u32 *rss_context,
-				 bool delete)
+				 struct ethtool_rxfh_param *rxfh,
+				 u32 *rss_context, bool delete)
 {
 	struct efx_nic *efx = efx_netdev_priv(net_dev);
 	struct efx_rss_context *ctx;
+	u32 *indir = rxfh->indir;
 	bool allocated = false;
+	u8 *key = rxfh->key;
 	int rc;
 
 	if (!efx->type->rx_push_rss_context_config)
 		return -EOPNOTSUPP;
 	/* Hash function is Toeplitz, cannot be changed */
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
 	mutex_lock(&efx->rss_lock);
diff --git a/drivers/net/ethernet/sfc/ethtool_common.h b/drivers/net/ethernet/sfc/ethtool_common.h
index 659491932101..384318ee1127 100644
--- a/drivers/net/ethernet/sfc/ethtool_common.h
+++ b/drivers/net/ethernet/sfc/ethtool_common.h
@@ -44,16 +44,17 @@ int efx_ethtool_set_rxnfc(struct net_device *net_dev,
 			  struct ethtool_rxnfc *info);
 u32 efx_ethtool_get_rxfh_indir_size(struct net_device *net_dev);
 u32 efx_ethtool_get_rxfh_key_size(struct net_device *net_dev);
-int efx_ethtool_get_rxfh(struct net_device *net_dev, u32 *indir, u8 *key,
-			 u8 *hfunc);
+int efx_ethtool_get_rxfh(struct net_device *net_dev,
+			 struct ethtool_rxfh_param *rxfh);
 int efx_ethtool_set_rxfh(struct net_device *net_dev,
-			 const u32 *indir, const u8 *key, const u8 hfunc);
-int efx_ethtool_get_rxfh_context(struct net_device *net_dev, u32 *indir,
-				 u8 *key, u8 *hfunc, u32 rss_context);
+			 struct ethtool_rxfh_param *rxfh,
+			 struct netlink_ext_ack *extack);
+int efx_ethtool_get_rxfh_context(struct net_device *net_dev,
+				 struct ethtool_rxfh_param *rxfh,
+				 u32 rss_context);
 int efx_ethtool_set_rxfh_context(struct net_device *net_dev,
-				 const u32 *indir, const u8 *key,
-				 const u8 hfunc, u32 *rss_context,
-				 bool delete);
+				 struct ethtool_rxfh_param *rxfh,
+				 u32 *rss_context, bool delete);
 int efx_ethtool_reset(struct net_device *net_dev, u32 *flags);
 int efx_ethtool_get_module_eeprom(struct net_device *net_dev,
 				  struct ethtool_eeprom *ee,
diff --git a/drivers/net/ethernet/sfc/falcon/ethtool.c b/drivers/net/ethernet/sfc/falcon/ethtool.c
index 3976a333f7e3..f4db683b80f7 100644
--- a/drivers/net/ethernet/sfc/falcon/ethtool.c
+++ b/drivers/net/ethernet/sfc/falcon/ethtool.c
@@ -1257,31 +1257,33 @@ static u32 ef4_ethtool_get_rxfh_indir_size(struct net_device *net_dev)
 		0 : ARRAY_SIZE(efx->rx_indir_table));
 }
 
-static int ef4_ethtool_get_rxfh(struct net_device *net_dev, u32 *indir, u8 *key,
-				u8 *hfunc)
+static int ef4_ethtool_get_rxfh(struct net_device *net_dev,
+				struct ethtool_rxfh_param *rxfh)
 {
 	struct ef4_nic *efx = netdev_priv(net_dev);
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
-	if (indir)
-		memcpy(indir, efx->rx_indir_table, sizeof(efx->rx_indir_table));
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+	if (rxfh->indir)
+		memcpy(rxfh->indir, efx->rx_indir_table,
+		       sizeof(efx->rx_indir_table));
 	return 0;
 }
 
-static int ef4_ethtool_set_rxfh(struct net_device *net_dev, const u32 *indir,
-				const u8 *key, const u8 hfunc)
+static int ef4_ethtool_set_rxfh(struct net_device *net_dev,
+				struct ethtool_rxfh_param *rxfh,
+				struct netlink_ext_ack *extack)
 {
 	struct ef4_nic *efx = netdev_priv(net_dev);
 
 	/* We do not allow change in unsupported parameters */
-	if (key ||
-	    (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP))
+	if (rxfh->key ||
+	    (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	     rxfh->hfunc != ETH_RSS_HASH_TOP))
 		return -EOPNOTSUPP;
-	if (!indir)
+	if (!rxfh->indir)
 		return 0;
 
-	return efx->type->rx_push_rss_config(efx, true, indir);
+	return efx->type->rx_push_rss_config(efx, true, rxfh->indir);
 }
 
 static int ef4_ethtool_get_module_eeprom(struct net_device *net_dev,
diff --git a/drivers/net/ethernet/sfc/siena/ethtool_common.c b/drivers/net/ethernet/sfc/siena/ethtool_common.c
index f590e87e5a23..20b64e3521cb 100644
--- a/drivers/net/ethernet/sfc/siena/ethtool_common.c
+++ b/drivers/net/ethernet/sfc/siena/ethtool_common.c
@@ -1164,8 +1164,8 @@ u32 efx_siena_ethtool_get_rxfh_key_size(struct net_device *net_dev)
 	return efx->type->rx_hash_key_size;
 }
 
-int efx_siena_ethtool_get_rxfh(struct net_device *net_dev, u32 *indir, u8 *key,
-			       u8 *hfunc)
+int efx_siena_ethtool_get_rxfh(struct net_device *net_dev,
+			       struct ethtool_rxfh_param *rxfh)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
 	int rc;
@@ -1174,24 +1174,27 @@ int efx_siena_ethtool_get_rxfh(struct net_device *net_dev, u32 *indir, u8 *key,
 	if (rc)
 		return rc;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
-	if (indir)
-		memcpy(indir, efx->rss_context.rx_indir_table,
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+	if (rxfh->indir)
+		memcpy(rxfh->indir, efx->rss_context.rx_indir_table,
 		       sizeof(efx->rss_context.rx_indir_table));
-	if (key)
-		memcpy(key, efx->rss_context.rx_hash_key,
+	if (rxfh->key)
+		memcpy(rxfh->key, efx->rss_context.rx_hash_key,
 		       efx->type->rx_hash_key_size);
 	return 0;
 }
 
-int efx_siena_ethtool_set_rxfh(struct net_device *net_dev, const u32 *indir,
-			       const u8 *key, const u8 hfunc)
+int efx_siena_ethtool_set_rxfh(struct net_device *net_dev,
+			       struct ethtool_rxfh_param *rxfh,
+			       struct netlink_ext_ack *extack)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
+	u32 *indir = rxfh->indir;
+	u8 *key = rxfh->key;
 
 	/* Hash function is Toeplitz, cannot be changed */
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 	if (!indir && !key)
 		return 0;
@@ -1204,8 +1207,9 @@ int efx_siena_ethtool_set_rxfh(struct net_device *net_dev, const u32 *indir,
 	return efx->type->rx_push_rss_config(efx, true, indir, key);
 }
 
-int efx_siena_ethtool_get_rxfh_context(struct net_device *net_dev, u32 *indir,
-				       u8 *key, u8 *hfunc, u32 rss_context)
+int efx_siena_ethtool_get_rxfh_context(struct net_device *net_dev,
+				       struct ethtool_rxfh_param *rxfh,
+				       u32 rss_context)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
 	struct efx_rss_context *ctx;
@@ -1224,31 +1228,34 @@ int efx_siena_ethtool_get_rxfh_context(struct net_device *net_dev, u32 *indir,
 	if (rc)
 		goto out_unlock;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
-	if (indir)
-		memcpy(indir, ctx->rx_indir_table, sizeof(ctx->rx_indir_table));
-	if (key)
-		memcpy(key, ctx->rx_hash_key, efx->type->rx_hash_key_size);
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+	if (rxfh->indir)
+		memcpy(rxfh->indir, ctx->rx_indir_table,
+		       sizeof(ctx->rx_indir_table));
+	if (rxfh->key)
+		memcpy(rxfh->key, ctx->rx_hash_key,
+		       efx->type->rx_hash_key_size);
 out_unlock:
 	mutex_unlock(&efx->rss_lock);
 	return rc;
 }
 
 int efx_siena_ethtool_set_rxfh_context(struct net_device *net_dev,
-				       const u32 *indir, const u8 *key,
-				       const u8 hfunc, u32 *rss_context,
-				       bool delete)
+				       struct ethtool_rxfh_param *rxfh,
+				       u32 *rss_context, bool delete)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
 	struct efx_rss_context *ctx;
+	u32 *indir = rxfh->indir;
 	bool allocated = false;
+	u8 *key = rxfh->key;
 	int rc;
 
 	if (!efx->type->rx_push_rss_context_config)
 		return -EOPNOTSUPP;
 	/* Hash function is Toeplitz, cannot be changed */
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
 	mutex_lock(&efx->rss_lock);
diff --git a/drivers/net/ethernet/sfc/siena/ethtool_common.h b/drivers/net/ethernet/sfc/siena/ethtool_common.h
index 04b375dc6800..2f892f8eff70 100644
--- a/drivers/net/ethernet/sfc/siena/ethtool_common.h
+++ b/drivers/net/ethernet/sfc/siena/ethtool_common.h
@@ -41,16 +41,17 @@ int efx_siena_ethtool_set_rxnfc(struct net_device *net_dev,
 				struct ethtool_rxnfc *info);
 u32 efx_siena_ethtool_get_rxfh_indir_size(struct net_device *net_dev);
 u32 efx_siena_ethtool_get_rxfh_key_size(struct net_device *net_dev);
-int efx_siena_ethtool_get_rxfh(struct net_device *net_dev, u32 *indir, u8 *key,
-			       u8 *hfunc);
+int efx_siena_ethtool_get_rxfh(struct net_device *net_dev,
+			       struct ethtool_rxfh_param *rxfh);
 int efx_siena_ethtool_set_rxfh(struct net_device *net_dev,
-			       const u32 *indir, const u8 *key, const u8 hfunc);
-int efx_siena_ethtool_get_rxfh_context(struct net_device *net_dev, u32 *indir,
-				       u8 *key, u8 *hfunc, u32 rss_context);
+			       struct ethtool_rxfh_param *rxfh,
+			       struct netlink_ext_ack *extack);
+int efx_siena_ethtool_get_rxfh_context(struct net_device *net_dev,
+				       struct ethtool_rxfh_param *rxfh,
+				       u32 rss_context);
 int efx_siena_ethtool_set_rxfh_context(struct net_device *net_dev,
-				       const u32 *indir, const u8 *key,
-				       const u8 hfunc, u32 *rss_context,
-				       bool delete);
+				       struct ethtool_rxfh_param *rxfh,
+				       u32 *rss_context, bool delete);
 int efx_siena_ethtool_reset(struct net_device *net_dev, u32 *flags);
 int efx_siena_ethtool_get_module_eeprom(struct net_device *net_dev,
 					struct ethtool_eeprom *ee,
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index b9b80e0fceeb..8105ce47c6ad 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -1087,41 +1087,42 @@ static u32 stmmac_get_rxfh_indir_size(struct net_device *dev)
 	return ARRAY_SIZE(priv->rss.table);
 }
 
-static int stmmac_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
-			   u8 *hfunc)
+static int stmmac_get_rxfh(struct net_device *dev,
+			   struct ethtool_rxfh_param *rxfh)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
 	int i;
 
-	if (indir) {
+	if (rxfh->indir) {
 		for (i = 0; i < ARRAY_SIZE(priv->rss.table); i++)
-			indir[i] = priv->rss.table[i];
+			rxfh->indir[i] = priv->rss.table[i];
 	}
 
-	if (key)
-		memcpy(key, priv->rss.key, sizeof(priv->rss.key));
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	if (rxfh->key)
+		memcpy(rxfh->key, priv->rss.key, sizeof(priv->rss.key));
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
 	return 0;
 }
 
-static int stmmac_set_rxfh(struct net_device *dev, const u32 *indir,
-			   const u8 *key, const u8 hfunc)
+static int stmmac_set_rxfh(struct net_device *dev,
+			   struct ethtool_rxfh_param *rxfh,
+			   struct netlink_ext_ack *extack)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
 	int i;
 
-	if ((hfunc != ETH_RSS_HASH_NO_CHANGE) && (hfunc != ETH_RSS_HASH_TOP))
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
-	if (indir) {
+	if (rxfh->indir) {
 		for (i = 0; i < ARRAY_SIZE(priv->rss.table); i++)
-			priv->rss.table[i] = indir[i];
+			priv->rss.table[i] = rxfh->indir[i];
 	}
 
-	if (key)
-		memcpy(priv->rss.key, key, sizeof(priv->rss.key));
+	if (rxfh->key)
+		memcpy(priv->rss.key, rxfh->key, sizeof(priv->rss.key));
 
 	return stmmac_rss_configure(priv, priv->hw, &priv->rss,
 				    priv->plat->rx_queues_to_use);
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 1e2fa0ec2327..4406427d4617 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -1752,8 +1752,8 @@ static u32 netvsc_rss_indir_size(struct net_device *dev)
 	return ndc->rx_table_sz;
 }
 
-static int netvsc_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
-			   u8 *hfunc)
+static int netvsc_get_rxfh(struct net_device *dev,
+			   struct ethtool_rxfh_param *rxfh)
 {
 	struct net_device_context *ndc = netdev_priv(dev);
 	struct netvsc_device *ndev = rtnl_dereference(ndc->nvdev);
@@ -1763,47 +1763,49 @@ static int netvsc_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
 	if (!ndev)
 		return -ENODEV;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;	/* Toeplitz */
+	rxfh->hfunc = ETH_RSS_HASH_TOP;	/* Toeplitz */
 
 	rndis_dev = ndev->extension;
-	if (indir) {
+	if (rxfh->indir) {
 		for (i = 0; i < ndc->rx_table_sz; i++)
-			indir[i] = ndc->rx_table[i];
+			rxfh->indir[i] = ndc->rx_table[i];
 	}
 
-	if (key)
-		memcpy(key, rndis_dev->rss_key, NETVSC_HASH_KEYLEN);
+	if (rxfh->key)
+		memcpy(rxfh->key, rndis_dev->rss_key, NETVSC_HASH_KEYLEN);
 
 	return 0;
 }
 
-static int netvsc_set_rxfh(struct net_device *dev, const u32 *indir,
-			   const u8 *key, const u8 hfunc)
+static int netvsc_set_rxfh(struct net_device *dev,
+			   struct ethtool_rxfh_param *rxfh,
+			   struct netlink_ext_ack *extack)
 {
 	struct net_device_context *ndc = netdev_priv(dev);
 	struct netvsc_device *ndev = rtnl_dereference(ndc->nvdev);
 	struct rndis_device *rndis_dev;
+	u8 *key = rxfh->key;
 	int i;
 
 	if (!ndev)
 		return -ENODEV;
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
 	rndis_dev = ndev->extension;
-	if (indir) {
+	if (rxfh->indir) {
 		for (i = 0; i < ndc->rx_table_sz; i++)
-			if (indir[i] >= ndev->num_chn)
+			if (rxfh->indir[i] >= ndev->num_chn)
 				return -EINVAL;
 
 		for (i = 0; i < ndc->rx_table_sz; i++)
-			ndc->rx_table[i] = indir[i];
+			ndc->rx_table[i] = rxfh->indir[i];
 	}
 
 	if (!key) {
-		if (!indir)
+		if (!rxfh->indir)
 			return 0;
 
 		key = rndis_dev->rss_key;
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 10614e9f7cad..25cf44ce95dd 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -3731,39 +3731,42 @@ static u32 virtnet_get_rxfh_indir_size(struct net_device *dev)
 	return ((struct virtnet_info *)netdev_priv(dev))->rss_indir_table_size;
 }
 
-static int virtnet_get_rxfh(struct net_device *dev, u32 *indir, u8 *key, u8 *hfunc)
+static int virtnet_get_rxfh(struct net_device *dev,
+			    struct ethtool_rxfh_param *rxfh)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
 	int i;
 
-	if (indir) {
+	if (rxfh->indir) {
 		for (i = 0; i < vi->rss_indir_table_size; ++i)
-			indir[i] = vi->ctrl->rss.indirection_table[i];
+			rxfh->indir[i] = vi->ctrl->rss.indirection_table[i];
 	}
 
-	if (key)
-		memcpy(key, vi->ctrl->rss.key, vi->rss_key_size);
+	if (rxfh->key)
+		memcpy(rxfh->key, vi->ctrl->rss.key, vi->rss_key_size);
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
 	return 0;
 }
 
-static int virtnet_set_rxfh(struct net_device *dev, const u32 *indir, const u8 *key, const u8 hfunc)
+static int virtnet_set_rxfh(struct net_device *dev,
+			    struct ethtool_rxfh_param *rxfh,
+			    struct netlink_ext_ack *extack)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
 	int i;
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
-	if (indir) {
+	if (rxfh->indir) {
 		for (i = 0; i < vi->rss_indir_table_size; ++i)
-			vi->ctrl->rss.indirection_table[i] = indir[i];
+			vi->ctrl->rss.indirection_table[i] = rxfh->indir[i];
 	}
-	if (key)
-		memcpy(vi->ctrl->rss.key, key, vi->rss_key_size);
+	if (rxfh->key)
+		memcpy(vi->ctrl->rss.key, rxfh->key, vi->rss_key_size);
 
 	virtnet_commit_rss_command(vi);
 
diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c
index 8f5f202cde39..7e8008d5378a 100644
--- a/drivers/net/vmxnet3/vmxnet3_ethtool.c
+++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c
@@ -1136,27 +1136,26 @@ vmxnet3_get_rss_indir_size(struct net_device *netdev)
 }
 
 static int
-vmxnet3_get_rss(struct net_device *netdev, u32 *p, u8 *key, u8 *hfunc)
+vmxnet3_get_rss(struct net_device *netdev, struct ethtool_rxfh_param *rxfh)
 {
 	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
 	struct UPT1_RSSConf *rssConf = adapter->rss_conf;
 	unsigned int n = rssConf->indTableSize;
 
-	if (hfunc)
-		*hfunc = ETH_RSS_HASH_TOP;
-	if (!p)
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+	if (!rxfh->indir)
 		return 0;
 	if (n > UPT1_RSS_MAX_IND_TABLE_SIZE)
 		return 0;
 	while (n--)
-		p[n] = rssConf->indTable[n];
+		rxfh->indir[n] = rssConf->indTable[n];
 	return 0;
 
 }
 
 static int
-vmxnet3_set_rss(struct net_device *netdev, const u32 *p, const u8 *key,
-		const u8 hfunc)
+vmxnet3_set_rss(struct net_device *netdev, struct ethtool_rxfh_param *rxfh,
+		struct netlink_ext_ack *extack)
 {
 	unsigned int i;
 	unsigned long flags;
@@ -1164,13 +1163,14 @@ vmxnet3_set_rss(struct net_device *netdev, const u32 *p, const u8 *key,
 	struct UPT1_RSSConf *rssConf = adapter->rss_conf;
 
 	/* We do not allow change in unsupported parameters */
-	if (key ||
-	    (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP))
+	if (rxfh->key ||
+	    (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	     rxfh->hfunc != ETH_RSS_HASH_TOP))
 		return -EOPNOTSUPP;
-	if (!p)
+	if (!rxfh->indir)
 		return 0;
 	for (i = 0; i < rssConf->indTableSize; i++)
-		rssConf->indTable[i] = p[i];
+		rssConf->indTable[i] = rxfh->indir[i];
 
 	spin_lock_irqsave(&adapter->cmd_lock, flags);
 	VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 67b30940234b..3ab2b6a90419 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -596,6 +596,28 @@ struct ethtool_mm_stats {
 	u64 MACMergeHoldCount;
 };
 
+/**
+ * struct ethtool_rxfh_param - RXFH (RSS) parameters
+ * @hfunc: Defines the current RSS hash function used by HW (or to be set to).
+ *	Valid values are one of the %ETH_RSS_HASH_*.
+ * @indir_size: On SET, the array size of the user buffer for the
+ *	indirection table, which may be zero, or
+ *	%ETH_RXFH_INDIR_NO_CHANGE.  On GET (read from the driver),
+ *	the array size of the hardware indirection table.
+ * @indir: The indirection table of size @indir_size entries.
+ * @key_size: On SET, the array size of the user buffer for the hash key,
+ *	which may be zero.  On GET (read from the driver), the size of the
+ *	hardware hash key.
+ * @key: The hash key of size @key_size bytes.
+ */
+struct ethtool_rxfh_param {
+	u8	hfunc;
+	u32	indir_size;
+	u32	*indir;
+	u32	key_size;
+	u8	*key;
+};
+
 /**
  * struct ethtool_ops - optional netdev operations
  * @cap_link_lanes_supported: indicates if the driver supports lanes
@@ -846,14 +868,14 @@ struct ethtool_ops {
 	int	(*reset)(struct net_device *, u32 *);
 	u32	(*get_rxfh_key_size)(struct net_device *);
 	u32	(*get_rxfh_indir_size)(struct net_device *);
-	int	(*get_rxfh)(struct net_device *, u32 *indir, u8 *key,
-			    u8 *hfunc);
-	int	(*set_rxfh)(struct net_device *, const u32 *indir,
-			    const u8 *key, const u8 hfunc);
-	int	(*get_rxfh_context)(struct net_device *, u32 *indir, u8 *key,
-				    u8 *hfunc, u32 rss_context);
-	int	(*set_rxfh_context)(struct net_device *, const u32 *indir,
-				    const u8 *key, const u8 hfunc,
+	int	(*get_rxfh)(struct net_device *, struct ethtool_rxfh_param *);
+	int	(*set_rxfh)(struct net_device *, struct ethtool_rxfh_param *,
+			    struct netlink_ext_ack *extack);
+	int	(*get_rxfh_context)(struct net_device *,
+				    struct ethtool_rxfh_param *,
+				    u32 rss_context);
+	int	(*set_rxfh_context)(struct net_device *,
+				    struct ethtool_rxfh_param *,
 				    u32 *rss_context, bool delete);
 	void	(*get_channels)(struct net_device *, struct ethtool_channels *);
 	int	(*set_channels)(struct net_device *, struct ethtool_channels *);
diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index 11d8797f63f6..6b2a360dcdf0 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -589,8 +589,8 @@ err_free_info:
 
 int ethtool_get_max_rxfh_channel(struct net_device *dev, u32 *max)
 {
+	struct ethtool_rxfh_param rxfh = {};
 	u32 dev_size, current_max = 0;
-	u32 *indir;
 	int ret;
 
 	if (!dev->ethtool_ops->get_rxfh_indir_size ||
@@ -600,21 +600,21 @@ int ethtool_get_max_rxfh_channel(struct net_device *dev, u32 *max)
 	if (dev_size == 0)
 		return -EOPNOTSUPP;
 
-	indir = kcalloc(dev_size, sizeof(indir[0]), GFP_USER);
-	if (!indir)
+	rxfh.indir = kcalloc(dev_size, sizeof(rxfh.indir[0]), GFP_USER);
+	if (!rxfh.indir)
 		return -ENOMEM;
 
-	ret = dev->ethtool_ops->get_rxfh(dev, indir, NULL, NULL);
+	ret = dev->ethtool_ops->get_rxfh(dev, &rxfh);
 	if (ret)
 		goto out;
 
 	while (dev_size--)
-		current_max = max(current_max, indir[dev_size]);
+		current_max = max(current_max, rxfh.indir[dev_size]);
 
 	*max = current_max;
 
 out:
-	kfree(indir);
+	kfree(rxfh.indir);
 	return ret;
 }
 
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 755a4be01bef..5f49a105fc73 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -1061,15 +1061,15 @@ EXPORT_SYMBOL(netdev_rss_key_fill);
 static noinline_for_stack int ethtool_get_rxfh_indir(struct net_device *dev,
 						     void __user *useraddr)
 {
-	u32 user_size, dev_size;
-	u32 *indir;
+	struct ethtool_rxfh_param rxfh = {};
+	u32 user_size;
 	int ret;
 
 	if (!dev->ethtool_ops->get_rxfh_indir_size ||
 	    !dev->ethtool_ops->get_rxfh)
 		return -EOPNOTSUPP;
-	dev_size = dev->ethtool_ops->get_rxfh_indir_size(dev);
-	if (dev_size == 0)
+	rxfh.indir_size = dev->ethtool_ops->get_rxfh_indir_size(dev);
+	if (rxfh.indir_size == 0)
 		return -EOPNOTSUPP;
 
 	if (copy_from_user(&user_size,
@@ -1078,41 +1078,41 @@ static noinline_for_stack int ethtool_get_rxfh_indir(struct net_device *dev,
 		return -EFAULT;
 
 	if (copy_to_user(useraddr + offsetof(struct ethtool_rxfh_indir, size),
-			 &dev_size, sizeof(dev_size)))
+			 &rxfh.indir_size, sizeof(rxfh.indir_size)))
 		return -EFAULT;
 
 	/* If the user buffer size is 0, this is just a query for the
 	 * device table size.  Otherwise, if it's smaller than the
 	 * device table size it's an error.
 	 */
-	if (user_size < dev_size)
+	if (user_size < rxfh.indir_size)
 		return user_size == 0 ? 0 : -EINVAL;
 
-	indir = kcalloc(dev_size, sizeof(indir[0]), GFP_USER);
-	if (!indir)
+	rxfh.indir = kcalloc(rxfh.indir_size, sizeof(rxfh.indir[0]), GFP_USER);
+	if (!rxfh.indir)
 		return -ENOMEM;
 
-	ret = dev->ethtool_ops->get_rxfh(dev, indir, NULL, NULL);
+	ret = dev->ethtool_ops->get_rxfh(dev, &rxfh);
 	if (ret)
 		goto out;
-
 	if (copy_to_user(useraddr +
 			 offsetof(struct ethtool_rxfh_indir, ring_index[0]),
-			 indir, dev_size * sizeof(indir[0])))
+			 rxfh.indir, rxfh.indir_size * sizeof(*rxfh.indir)))
 		ret = -EFAULT;
 
 out:
-	kfree(indir);
+	kfree(rxfh.indir);
 	return ret;
 }
 
 static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev,
 						     void __user *useraddr)
 {
-	struct ethtool_rxnfc rx_rings;
-	u32 user_size, dev_size, i;
-	u32 *indir;
 	const struct ethtool_ops *ops = dev->ethtool_ops;
+	struct ethtool_rxfh_param rxfh_dev = {};
+	struct netlink_ext_ack *extack = NULL;
+	struct ethtool_rxnfc rx_rings;
+	u32 user_size, i;
 	int ret;
 	u32 ringidx_offset = offsetof(struct ethtool_rxfh_indir, ring_index[0]);
 
@@ -1120,8 +1120,8 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev,
 	    !ops->get_rxnfc)
 		return -EOPNOTSUPP;
 
-	dev_size = ops->get_rxfh_indir_size(dev);
-	if (dev_size == 0)
+	rxfh_dev.indir_size = ops->get_rxfh_indir_size(dev);
+	if (rxfh_dev.indir_size == 0)
 		return -EOPNOTSUPP;
 
 	if (copy_from_user(&user_size,
@@ -1129,11 +1129,12 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev,
 			   sizeof(user_size)))
 		return -EFAULT;
 
-	if (user_size != 0 && user_size != dev_size)
+	if (user_size != 0 && user_size != rxfh_dev.indir_size)
 		return -EINVAL;
 
-	indir = kcalloc(dev_size, sizeof(indir[0]), GFP_USER);
-	if (!indir)
+	rxfh_dev.indir = kcalloc(rxfh_dev.indir_size,
+				 sizeof(rxfh_dev.indir[0]), GFP_USER);
+	if (!rxfh_dev.indir)
 		return -ENOMEM;
 
 	rx_rings.cmd = ETHTOOL_GRXRINGS;
@@ -1142,18 +1143,21 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev,
 		goto out;
 
 	if (user_size == 0) {
-		for (i = 0; i < dev_size; i++)
+		u32 *indir = rxfh_dev.indir;
+
+		for (i = 0; i < rxfh_dev.indir_size; i++)
 			indir[i] = ethtool_rxfh_indir_default(i, rx_rings.data);
 	} else {
-		ret = ethtool_copy_validate_indir(indir,
+		ret = ethtool_copy_validate_indir(rxfh_dev.indir,
 						  useraddr + ringidx_offset,
 						  &rx_rings,
-						  dev_size);
+						  rxfh_dev.indir_size);
 		if (ret)
 			goto out;
 	}
 
-	ret = ops->set_rxfh(dev, indir, NULL, ETH_RSS_HASH_NO_CHANGE);
+	rxfh_dev.hfunc = ETH_RSS_HASH_NO_CHANGE;
+	ret = ops->set_rxfh(dev, &rxfh_dev, extack);
 	if (ret)
 		goto out;
 
@@ -1164,32 +1168,29 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev,
 		dev->priv_flags |= IFF_RXFH_CONFIGURED;
 
 out:
-	kfree(indir);
+	kfree(rxfh_dev.indir);
 	return ret;
 }
 
 static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev,
 					       void __user *useraddr)
 {
-	int ret;
 	const struct ethtool_ops *ops = dev->ethtool_ops;
+	struct ethtool_rxfh_param rxfh_dev = {};
 	u32 user_indir_size, user_key_size;
-	u32 dev_indir_size = 0, dev_key_size = 0;
 	struct ethtool_rxfh rxfh;
-	u32 total_size;
 	u32 indir_bytes;
-	u32 *indir = NULL;
-	u8 dev_hfunc = 0;
-	u8 *hkey = NULL;
 	u8 *rss_config;
+	u32 total_size;
+	int ret;
 
 	if (!ops->get_rxfh)
 		return -EOPNOTSUPP;
 
 	if (ops->get_rxfh_indir_size)
-		dev_indir_size = ops->get_rxfh_indir_size(dev);
+		rxfh_dev.indir_size = ops->get_rxfh_indir_size(dev);
 	if (ops->get_rxfh_key_size)
-		dev_key_size = ops->get_rxfh_key_size(dev);
+		rxfh_dev.key_size = ops->get_rxfh_key_size(dev);
 
 	if (copy_from_user(&rxfh, useraddr, sizeof(rxfh)))
 		return -EFAULT;
@@ -1203,38 +1204,37 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev,
 	if (rxfh.rss_context && !ops->get_rxfh_context)
 		return -EOPNOTSUPP;
 
-	rxfh.indir_size = dev_indir_size;
-	rxfh.key_size = dev_key_size;
+	rxfh.indir_size = rxfh_dev.indir_size;
+	rxfh.key_size = rxfh_dev.key_size;
 	if (copy_to_user(useraddr, &rxfh, sizeof(rxfh)))
 		return -EFAULT;
 
-	if ((user_indir_size && (user_indir_size != dev_indir_size)) ||
-	    (user_key_size && (user_key_size != dev_key_size)))
+	if ((user_indir_size && user_indir_size != rxfh_dev.indir_size) ||
+	    (user_key_size && user_key_size != rxfh_dev.key_size))
 		return -EINVAL;
 
-	indir_bytes = user_indir_size * sizeof(indir[0]);
+	indir_bytes = user_indir_size * sizeof(rxfh_dev.indir[0]);
 	total_size = indir_bytes + user_key_size;
 	rss_config = kzalloc(total_size, GFP_USER);
 	if (!rss_config)
 		return -ENOMEM;
 
 	if (user_indir_size)
-		indir = (u32 *)rss_config;
+		rxfh_dev.indir = (u32 *)rss_config;
 
 	if (user_key_size)
-		hkey = rss_config + indir_bytes;
+		rxfh_dev.key = rss_config + indir_bytes;
 
 	if (rxfh.rss_context)
-		ret = dev->ethtool_ops->get_rxfh_context(dev, indir, hkey,
-							 &dev_hfunc,
+		ret = dev->ethtool_ops->get_rxfh_context(dev, &rxfh_dev,
 							 rxfh.rss_context);
 	else
-		ret = dev->ethtool_ops->get_rxfh(dev, indir, hkey, &dev_hfunc);
+		ret = dev->ethtool_ops->get_rxfh(dev, &rxfh_dev);
 	if (ret)
 		goto out;
 
 	if (copy_to_user(useraddr + offsetof(struct ethtool_rxfh, hfunc),
-			 &dev_hfunc, sizeof(rxfh.hfunc))) {
+			 &rxfh_dev.hfunc, sizeof(rxfh.hfunc))) {
 		ret = -EFAULT;
 	} else if (copy_to_user(useraddr +
 			      offsetof(struct ethtool_rxfh, rss_config[0]),
@@ -1250,16 +1250,17 @@ out:
 static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 					       void __user *useraddr)
 {
-	int ret;
+	u32 rss_cfg_offset = offsetof(struct ethtool_rxfh, rss_config[0]);
 	const struct ethtool_ops *ops = dev->ethtool_ops;
+	u32 dev_indir_size = 0, dev_key_size = 0, i;
+	struct ethtool_rxfh_param rxfh_dev = {};
+	struct netlink_ext_ack *extack = NULL;
 	struct ethtool_rxnfc rx_rings;
 	struct ethtool_rxfh rxfh;
-	u32 dev_indir_size = 0, dev_key_size = 0, i;
-	u32 *indir = NULL, indir_bytes = 0;
-	u8 *hkey = NULL;
-	u8 *rss_config;
-	u32 rss_cfg_offset = offsetof(struct ethtool_rxfh, rss_config[0]);
 	bool delete = false;
+	u32 indir_bytes = 0;
+	u8 *rss_config;
+	int ret;
 
 	if (!ops->get_rxnfc || !ops->set_rxfh)
 		return -EOPNOTSUPP;
@@ -1291,7 +1292,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 		return -EINVAL;
 
 	if (rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE)
-		indir_bytes = dev_indir_size * sizeof(indir[0]);
+		indir_bytes = dev_indir_size * sizeof(rxfh_dev.indir[0]);
 
 	rss_config = kzalloc(indir_bytes + rxfh.key_size, GFP_USER);
 	if (!rss_config)
@@ -1308,8 +1309,9 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 	 */
 	if (rxfh.indir_size &&
 	    rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE) {
-		indir = (u32 *)rss_config;
-		ret = ethtool_copy_validate_indir(indir,
+		rxfh_dev.indir = (u32 *)rss_config;
+		rxfh_dev.indir_size = dev_indir_size;
+		ret = ethtool_copy_validate_indir(rxfh_dev.indir,
 						  useraddr + rss_cfg_offset,
 						  &rx_rings,
 						  rxfh.indir_size);
@@ -1317,7 +1319,11 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 			goto out;
 	} else if (rxfh.indir_size == 0) {
 		if (rxfh.rss_context == 0) {
-			indir = (u32 *)rss_config;
+			u32 *indir;
+
+			rxfh_dev.indir = (u32 *)rss_config;
+			rxfh_dev.indir_size = dev_indir_size;
+			indir = rxfh_dev.indir;
 			for (i = 0; i < dev_indir_size; i++)
 				indir[i] = ethtool_rxfh_indir_default(i, rx_rings.data);
 		} else {
@@ -1326,8 +1332,9 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 	}
 
 	if (rxfh.key_size) {
-		hkey = rss_config + indir_bytes;
-		if (copy_from_user(hkey,
+		rxfh_dev.key_size = dev_key_size;
+		rxfh_dev.key = rss_config + indir_bytes;
+		if (copy_from_user(rxfh_dev.key,
 				   useraddr + rss_cfg_offset + indir_bytes,
 				   rxfh.key_size)) {
 			ret = -EFAULT;
@@ -1335,11 +1342,14 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 		}
 	}
 
+	rxfh_dev.hfunc = rxfh.hfunc;
+
 	if (rxfh.rss_context)
-		ret = ops->set_rxfh_context(dev, indir, hkey, rxfh.hfunc,
+		ret = ops->set_rxfh_context(dev, &rxfh_dev,
 					    &rxfh.rss_context, delete);
 	else
-		ret = ops->set_rxfh(dev, indir, hkey, rxfh.hfunc);
+		ret = ops->set_rxfh(dev, &rxfh_dev, extack);
+
 	if (ret)
 		goto out;
 
diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c
index 5764202e6cb6..56fae7d5c0f7 100644
--- a/net/ethtool/rss.c
+++ b/net/ethtool/rss.c
@@ -48,9 +48,9 @@ rss_prepare_data(const struct ethnl_req_info *req_base,
 	struct rss_reply_data *data = RSS_REPDATA(reply_base);
 	struct rss_req_info *request = RSS_REQINFO(req_base);
 	struct net_device *dev = reply_base->dev;
+	struct ethtool_rxfh_param rxfh = {};
 	const struct ethtool_ops *ops;
 	u32 total_size, indir_bytes;
-	u8 dev_hfunc = 0;
 	u8 *rss_config;
 	int ret;
 
@@ -83,21 +83,23 @@ rss_prepare_data(const struct ethnl_req_info *req_base,
 
 	if (data->indir_size)
 		data->indir_table = (u32 *)rss_config;
-
 	if (data->hkey_size)
 		data->hkey = rss_config + indir_bytes;
 
+	rxfh.indir_size = data->indir_size;
+	rxfh.indir = data->indir_table;
+	rxfh.key_size = data->hkey_size;
+	rxfh.key = data->hkey;
+
 	if (request->rss_context)
-		ret = ops->get_rxfh_context(dev, data->indir_table, data->hkey,
-					    &dev_hfunc, request->rss_context);
+		ret = ops->get_rxfh_context(dev, &rxfh, request->rss_context);
 	else
-		ret = ops->get_rxfh(dev, data->indir_table, data->hkey,
-				    &dev_hfunc);
+		ret = ops->get_rxfh(dev, &rxfh);
 
 	if (ret)
 		goto out_ops;
 
-	data->hfunc = dev_hfunc;
+	data->hfunc = rxfh.hfunc;
 out_ops:
 	ethnl_ops_complete(dev);
 	return ret;
-- 
cgit v1.2.3


From dcd8dbf9e734eb334113ea43186c1c26e9f497bb Mon Sep 17 00:00:00 2001
From: Ahmed Zaki <ahmed.zaki@intel.com>
Date: Tue, 12 Dec 2023 17:33:15 -0700
Subject: net: ethtool: get rid of get/set_rxfh_context functions

Add the RSS context parameters to struct ethtool_rxfh_param and use the
get/set_rxfh to handle the RSS contexts as well.

This is part 2/2 of the fix suggested in [1]:

 - Add a rss_context member to the argument struct and a capability
   like cap_link_lanes_supported to indicate whether driver supports
   rss contexts, then you can remove *et_rxfh_context functions,
   and instead call *et_rxfh() with a non-zero rss_context.

Link: https://lore.kernel.org/netdev/20231121152906.2dd5f487@kernel.org/ [1]
CC: Jesse Brandeburg <jesse.brandeburg@intel.com>
CC: Tony Nguyen <anthony.l.nguyen@intel.com>
CC: Marcin Wojtas <mw@semihalf.com>
CC: Russell King <linux@armlinux.org.uk>
CC: Sunil Goutham <sgoutham@marvell.com>
CC: Geetha sowjanya <gakula@marvell.com>
CC: Subbaraya Sundeep <sbhatta@marvell.com>
CC: hariprasad <hkelam@marvell.com>
CC: Saeed Mahameed <saeedm@nvidia.com>
CC: Leon Romanovsky <leon@kernel.org>
CC: Edward Cree <ecree.xilinx@gmail.com>
CC: Martin Habets <habetsm.xilinx@gmail.com>
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
Link: https://lore.kernel.org/r/20231213003321.605376-3-ahmed.zaki@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_ethtool.c       |  29 +++---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c    |  63 +++--------
 .../ethernet/marvell/octeontx2/nic/otx2_ethtool.c  |  63 +++++------
 .../net/ethernet/mellanox/mlx5/core/en_ethtool.c   |  37 ++-----
 drivers/net/ethernet/sfc/ef100_ethtool.c           |   3 +-
 drivers/net/ethernet/sfc/ethtool.c                 |   3 +-
 drivers/net/ethernet/sfc/ethtool_common.c          | 115 +++++++++++----------
 drivers/net/ethernet/sfc/ethtool_common.h          |   6 --
 drivers/net/ethernet/sfc/siena/ethtool.c           |   3 +-
 drivers/net/ethernet/sfc/siena/ethtool_common.c    | 115 +++++++++++----------
 drivers/net/ethernet/sfc/siena/ethtool_common.h    |   6 --
 include/linux/ethtool.h                            |  26 ++---
 net/ethtool/ioctl.c                                |  27 ++---
 net/ethtool/rss.c                                  |   9 +-
 14 files changed, 205 insertions(+), 300 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 70cbd8092aea..c77605b42833 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -3195,11 +3195,18 @@ static u32 ice_get_rxfh_indir_size(struct net_device *netdev)
 	return np->vsi->rss_table_size;
 }
 
+/**
+ * ice_get_rxfh - get the Rx flow hash indirection table
+ * @netdev: network interface device structure
+ * @rxfh: pointer to param struct (indir, key, hfunc)
+ *
+ * Reads the indirection table directly from the hardware.
+ */
 static int
-ice_get_rxfh_context(struct net_device *netdev,
-		     struct ethtool_rxfh_param *rxfh, u32 rss_context)
+ice_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
+	u32 rss_context = rxfh->rss_context;
 	struct ice_vsi *vsi = np->vsi;
 	struct ice_pf *pf = vsi->back;
 	u16 qcount, offset;
@@ -3261,19 +3268,6 @@ out:
 	return err;
 }
 
-/**
- * ice_get_rxfh - get the Rx flow hash indirection table
- * @netdev: network interface device structure
- * @rxfh: pointer to param struct (indir, key, hfunc)
- *
- * Reads the indirection table directly from the hardware.
- */
-static int
-ice_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh)
-{
-	return ice_get_rxfh_context(netdev, rxfh, 0);
-}
-
 /**
  * ice_set_rxfh - set the Rx flow hash indirection table
  * @netdev: network interface device structure
@@ -3298,6 +3292,9 @@ ice_set_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh,
 	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
+	if (rxfh->rss_context)
+		return -EOPNOTSUPP;
+
 	if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags)) {
 		/* RSS not supported return error here */
 		netdev_warn(netdev, "RSS is not configured on this VSI!\n");
@@ -4215,6 +4212,7 @@ ice_get_module_eeprom(struct net_device *netdev,
 }
 
 static const struct ethtool_ops ice_ethtool_ops = {
+	.cap_rss_ctx_supported  = true,
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE |
 				     ETHTOOL_COALESCE_RX_USECS_HIGH,
@@ -4248,7 +4246,6 @@ static const struct ethtool_ops ice_ethtool_ops = {
 	.set_pauseparam		= ice_set_pauseparam,
 	.get_rxfh_key_size	= ice_get_rxfh_key_size,
 	.get_rxfh_indir_size	= ice_get_rxfh_indir_size,
-	.get_rxfh_context	= ice_get_rxfh_context,
 	.get_rxfh		= ice_get_rxfh,
 	.set_rxfh		= ice_set_rxfh,
 	.get_channels		= ice_get_channels,
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index ceef48ddd26e..9193cf61de26 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -5638,47 +5638,7 @@ static int mvpp2_ethtool_get_rxfh(struct net_device *dev,
 				  struct ethtool_rxfh_param *rxfh)
 {
 	struct mvpp2_port *port = netdev_priv(dev);
-	int ret = 0;
-
-	if (!mvpp22_rss_is_supported(port))
-		return -EOPNOTSUPP;
-
-	if (rxfh->indir)
-		ret = mvpp22_port_rss_ctx_indir_get(port, 0, rxfh->indir);
-
-	rxfh->hfunc = ETH_RSS_HASH_CRC32;
-
-	return ret;
-}
-
-static int mvpp2_ethtool_set_rxfh(struct net_device *dev,
-				  struct ethtool_rxfh_param *rxfh,
-				  struct netlink_ext_ack *extack)
-{
-	struct mvpp2_port *port = netdev_priv(dev);
-	int ret = 0;
-
-	if (!mvpp22_rss_is_supported(port))
-		return -EOPNOTSUPP;
-
-	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
-	    rxfh->hfunc != ETH_RSS_HASH_CRC32)
-		return -EOPNOTSUPP;
-
-	if (rxfh->key)
-		return -EOPNOTSUPP;
-
-	if (rxfh->indir)
-		ret = mvpp22_port_rss_ctx_indir_set(port, 0, rxfh->indir);
-
-	return ret;
-}
-
-static int mvpp2_ethtool_get_rxfh_context(struct net_device *dev,
-					  struct ethtool_rxfh_param *rxfh,
-					  u32 rss_context)
-{
-	struct mvpp2_port *port = netdev_priv(dev);
+	u32 rss_context = rxfh->rss_context;
 	int ret = 0;
 
 	if (!mvpp22_rss_is_supported(port))
@@ -5695,12 +5655,13 @@ static int mvpp2_ethtool_get_rxfh_context(struct net_device *dev,
 	return ret;
 }
 
-static int mvpp2_ethtool_set_rxfh_context(struct net_device *dev,
-					  struct ethtool_rxfh_param *rxfh,
-					  u32 *rss_context, bool delete)
+static int mvpp2_ethtool_set_rxfh(struct net_device *dev,
+				  struct ethtool_rxfh_param *rxfh,
+				  struct netlink_ext_ack *extack)
 {
 	struct mvpp2_port *port = netdev_priv(dev);
-	int ret;
+	u32 *rss_context = &rxfh->rss_context;
+	int ret = 0;
 
 	if (!mvpp22_rss_is_supported(port))
 		return -EOPNOTSUPP;
@@ -5712,7 +5673,7 @@ static int mvpp2_ethtool_set_rxfh_context(struct net_device *dev,
 	if (rxfh->key)
 		return -EOPNOTSUPP;
 
-	if (delete)
+	if (*rss_context && rxfh->rss_delete)
 		return mvpp22_port_rss_ctx_delete(port, *rss_context);
 
 	if (*rss_context == ETH_RXFH_CONTEXT_ALLOC) {
@@ -5721,8 +5682,13 @@ static int mvpp2_ethtool_set_rxfh_context(struct net_device *dev,
 			return ret;
 	}
 
-	return mvpp22_port_rss_ctx_indir_set(port, *rss_context, rxfh->indir);
+	if (rxfh->indir)
+		ret = mvpp22_port_rss_ctx_indir_set(port, *rss_context,
+						    rxfh->indir);
+
+	return ret;
 }
+
 /* Device ops */
 
 static const struct net_device_ops mvpp2_netdev_ops = {
@@ -5742,6 +5708,7 @@ static const struct net_device_ops mvpp2_netdev_ops = {
 };
 
 static const struct ethtool_ops mvpp2_eth_tool_ops = {
+	.cap_rss_ctx_supported	= true,
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_MAX_FRAMES,
 	.nway_reset		= mvpp2_ethtool_nway_reset,
@@ -5764,8 +5731,6 @@ static const struct ethtool_ops mvpp2_eth_tool_ops = {
 	.get_rxfh_indir_size	= mvpp2_ethtool_get_rxfh_indir_size,
 	.get_rxfh		= mvpp2_ethtool_get_rxfh,
 	.set_rxfh		= mvpp2_ethtool_set_rxfh,
-	.get_rxfh_context	= mvpp2_ethtool_get_rxfh_context,
-	.set_rxfh_context	= mvpp2_ethtool_set_rxfh_context,
 };
 
 /* Used for PPv2.1, or PPv2.2 with the old Device Tree binding that
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
index a2c182d7bfc4..2928898c7f8d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
@@ -835,11 +835,12 @@ static int otx2_rss_ctx_create(struct otx2_nic *pfvf,
 	return 0;
 }
 
-/* RSS context configuration */
-static int otx2_set_rxfh_context(struct net_device *dev,
-				 struct ethtool_rxfh_param *rxfh,
-				 u32 *rss_context, bool delete)
+/* Configure RSS table and hash key */
+static int otx2_set_rxfh(struct net_device *dev,
+			 struct ethtool_rxfh_param *rxfh,
+			 struct netlink_ext_ack *extack)
 {
+	u32 rss_context = DEFAULT_RSS_CONTEXT_GROUP;
 	struct otx2_nic *pfvf = netdev_priv(dev);
 	struct otx2_rss_ctx *rss_ctx;
 	struct otx2_rss_info *rss;
@@ -849,8 +850,11 @@ static int otx2_set_rxfh_context(struct net_device *dev,
 	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
-	if (*rss_context != ETH_RXFH_CONTEXT_ALLOC &&
-	    *rss_context >= MAX_RSS_GROUPS)
+	if (rxfh->rss_context)
+		rss_context = rxfh->rss_context;
+
+	if (rss_context != ETH_RXFH_CONTEXT_ALLOC &&
+	    rss_context >= MAX_RSS_GROUPS)
 		return -EINVAL;
 
 	rss = &pfvf->hw.rss_info;
@@ -864,28 +868,30 @@ static int otx2_set_rxfh_context(struct net_device *dev,
 		memcpy(rss->key, rxfh->key, sizeof(rss->key));
 		otx2_set_rss_key(pfvf);
 	}
-	if (delete)
-		return otx2_rss_ctx_delete(pfvf, *rss_context);
+	if (rxfh->rss_delete)
+		return otx2_rss_ctx_delete(pfvf, rss_context);
 
-	if (*rss_context == ETH_RXFH_CONTEXT_ALLOC) {
-		ret = otx2_rss_ctx_create(pfvf, rss_context);
+	if (rss_context == ETH_RXFH_CONTEXT_ALLOC) {
+		ret = otx2_rss_ctx_create(pfvf, &rss_context);
+		rxfh->rss_context = rss_context;
 		if (ret)
 			return ret;
 	}
 	if (rxfh->indir) {
-		rss_ctx = rss->rss_ctx[*rss_context];
+		rss_ctx = rss->rss_ctx[rss_context];
 		for (idx = 0; idx < rss->rss_size; idx++)
 			rss_ctx->ind_tbl[idx] = rxfh->indir[idx];
 	}
-	otx2_set_rss_table(pfvf, *rss_context);
+	otx2_set_rss_table(pfvf, rss_context);
 
 	return 0;
 }
 
-static int otx2_get_rxfh_context(struct net_device *dev,
-				 struct ethtool_rxfh_param *rxfh,
-				 u32 rss_context)
+/* Get RSS configuration */
+static int otx2_get_rxfh(struct net_device *dev,
+			 struct ethtool_rxfh_param *rxfh)
 {
+	u32 rss_context = DEFAULT_RSS_CONTEXT_GROUP;
 	struct otx2_nic *pfvf = netdev_priv(dev);
 	struct otx2_rss_ctx *rss_ctx;
 	struct otx2_rss_info *rss;
@@ -895,6 +901,8 @@ static int otx2_get_rxfh_context(struct net_device *dev,
 	rss = &pfvf->hw.rss_info;
 
 	rxfh->hfunc = ETH_RSS_HASH_TOP;
+	if (rxfh->rss_context)
+		rss_context = rxfh->rss_context;
 
 	if (!indir)
 		return 0;
@@ -922,25 +930,6 @@ static int otx2_get_rxfh_context(struct net_device *dev,
 	return 0;
 }
 
-/* Get RSS configuration */
-static int otx2_get_rxfh(struct net_device *dev,
-			 struct ethtool_rxfh_param *rxfh)
-{
-	return otx2_get_rxfh_context(dev, rxfh,
-				     DEFAULT_RSS_CONTEXT_GROUP);
-}
-
-/* Configure RSS table and hash key */
-static int otx2_set_rxfh(struct net_device *dev,
-			 struct ethtool_rxfh_param *rxfh,
-			 struct netlink_ext_ack *extack)
-{
-
-	u32 rss_context = DEFAULT_RSS_CONTEXT_GROUP;
-
-	return otx2_set_rxfh_context(dev, rxfh, &rss_context, 0);
-}
-
 static u32 otx2_get_msglevel(struct net_device *netdev)
 {
 	struct otx2_nic *pfvf = netdev_priv(netdev);
@@ -1321,6 +1310,7 @@ static void otx2_get_fec_stats(struct net_device *netdev,
 }
 
 static const struct ethtool_ops otx2_ethtool_ops = {
+	.cap_rss_ctx_supported	= true,
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_MAX_FRAMES |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE,
@@ -1343,8 +1333,6 @@ static const struct ethtool_ops otx2_ethtool_ops = {
 	.get_rxfh_indir_size	= otx2_get_rxfh_indir_size,
 	.get_rxfh		= otx2_get_rxfh,
 	.set_rxfh		= otx2_set_rxfh,
-	.get_rxfh_context	= otx2_get_rxfh_context,
-	.set_rxfh_context	= otx2_set_rxfh_context,
 	.get_msglevel		= otx2_get_msglevel,
 	.set_msglevel		= otx2_set_msglevel,
 	.get_pauseparam		= otx2_get_pauseparam,
@@ -1444,6 +1432,7 @@ static int otx2vf_get_link_ksettings(struct net_device *netdev,
 }
 
 static const struct ethtool_ops otx2vf_ethtool_ops = {
+	.cap_rss_ctx_supported	= true,
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_MAX_FRAMES |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE,
@@ -1462,8 +1451,6 @@ static const struct ethtool_ops otx2vf_ethtool_ops = {
 	.get_rxfh_indir_size	= otx2_get_rxfh_indir_size,
 	.get_rxfh		= otx2_get_rxfh,
 	.set_rxfh		= otx2_set_rxfh,
-	.get_rxfh_context	= otx2_get_rxfh_context,
-	.set_rxfh_context	= otx2_set_rxfh_context,
 	.get_ringparam		= otx2_get_ringparam,
 	.set_ringparam		= otx2_set_ringparam,
 	.get_coalesce		= otx2_get_coalesce,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 110cb7973eae..0fe7ea88d567 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1262,11 +1262,10 @@ static u32 mlx5e_get_rxfh_indir_size(struct net_device *netdev)
 	return mlx5e_ethtool_get_rxfh_indir_size(priv);
 }
 
-static int mlx5e_get_rxfh_context(struct net_device *dev,
-				  struct ethtool_rxfh_param *rxfh,
-				  u32 rss_context)
+int mlx5e_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh)
 {
-	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	u32 rss_context = rxfh->rss_context;
 	int err;
 
 	mutex_lock(&priv->state_lock);
@@ -1276,16 +1275,16 @@ static int mlx5e_get_rxfh_context(struct net_device *dev,
 	return err;
 }
 
-static int mlx5e_set_rxfh_context(struct net_device *dev,
-				  struct ethtool_rxfh_param *rxfh,
-				  u32 *rss_context, bool delete)
+int mlx5e_set_rxfh(struct net_device *dev, struct ethtool_rxfh_param *rxfh,
+		   struct netlink_ext_ack *extack)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
+	u32 *rss_context = &rxfh->rss_context;
 	u8 hfunc = rxfh->hfunc;
 	int err;
 
 	mutex_lock(&priv->state_lock);
-	if (delete) {
+	if (*rss_context && rxfh->rss_delete) {
 		err = mlx5e_rx_res_rss_destroy(priv->rx_res, *rss_context);
 		goto unlock;
 	}
@@ -1307,25 +1306,6 @@ unlock:
 	return err;
 }
 
-int mlx5e_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh)
-{
-	return mlx5e_get_rxfh_context(netdev, rxfh, 0);
-}
-
-int mlx5e_set_rxfh(struct net_device *dev, struct ethtool_rxfh_param *rxfh,
-		   struct netlink_ext_ack *extack)
-{
-	struct mlx5e_priv *priv = netdev_priv(dev);
-	u8 hfunc = rxfh->hfunc;
-	int err;
-
-	mutex_lock(&priv->state_lock);
-	err = mlx5e_rx_res_rss_set_rxfh(priv->rx_res, 0, rxfh->indir, rxfh->key,
-					hfunc == ETH_RSS_HASH_NO_CHANGE ? NULL : &hfunc);
-	mutex_unlock(&priv->state_lock);
-	return err;
-}
-
 #define MLX5E_PFC_PREVEN_AUTO_TOUT_MSEC		100
 #define MLX5E_PFC_PREVEN_TOUT_MAX_MSEC		8000
 #define MLX5E_PFC_PREVEN_MINOR_PRECENT		85
@@ -2402,6 +2382,7 @@ static void mlx5e_get_rmon_stats(struct net_device *netdev,
 }
 
 const struct ethtool_ops mlx5e_ethtool_ops = {
+	.cap_rss_ctx_supported	= true,
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_MAX_FRAMES |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE |
@@ -2424,8 +2405,6 @@ const struct ethtool_ops mlx5e_ethtool_ops = {
 	.get_rxfh_indir_size = mlx5e_get_rxfh_indir_size,
 	.get_rxfh          = mlx5e_get_rxfh,
 	.set_rxfh          = mlx5e_set_rxfh,
-	.get_rxfh_context  = mlx5e_get_rxfh_context,
-	.set_rxfh_context  = mlx5e_set_rxfh_context,
 	.get_rxnfc         = mlx5e_get_rxnfc,
 	.set_rxnfc         = mlx5e_set_rxnfc,
 	.get_tunable       = mlx5e_get_tunable,
diff --git a/drivers/net/ethernet/sfc/ef100_ethtool.c b/drivers/net/ethernet/sfc/ef100_ethtool.c
index 702abbe59b76..cf55202b3a7b 100644
--- a/drivers/net/ethernet/sfc/ef100_ethtool.c
+++ b/drivers/net/ethernet/sfc/ef100_ethtool.c
@@ -37,6 +37,7 @@ ef100_ethtool_get_ringparam(struct net_device *net_dev,
 /*	Ethtool options available
  */
 const struct ethtool_ops ef100_ethtool_ops = {
+	.cap_rss_ctx_supported	= true,
 	.get_drvinfo		= efx_ethtool_get_drvinfo,
 	.get_msglevel		= efx_ethtool_get_msglevel,
 	.set_msglevel		= efx_ethtool_set_msglevel,
@@ -60,8 +61,6 @@ const struct ethtool_ops ef100_ethtool_ops = {
 	.get_rxfh_key_size	= efx_ethtool_get_rxfh_key_size,
 	.get_rxfh		= efx_ethtool_get_rxfh,
 	.set_rxfh		= efx_ethtool_set_rxfh,
-	.get_rxfh_context	= efx_ethtool_get_rxfh_context,
-	.set_rxfh_context	= efx_ethtool_set_rxfh_context,
 
 	.get_module_info	= efx_ethtool_get_module_info,
 	.get_module_eeprom	= efx_ethtool_get_module_eeprom,
diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c
index 364323599f7b..37c69c8d90b1 100644
--- a/drivers/net/ethernet/sfc/ethtool.c
+++ b/drivers/net/ethernet/sfc/ethtool.c
@@ -240,6 +240,7 @@ static int efx_ethtool_get_ts_info(struct net_device *net_dev,
 }
 
 const struct ethtool_ops efx_ethtool_ops = {
+	.cap_rss_ctx_supported	= true,
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_USECS_IRQ |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE_RX,
@@ -269,8 +270,6 @@ const struct ethtool_ops efx_ethtool_ops = {
 	.get_rxfh_key_size	= efx_ethtool_get_rxfh_key_size,
 	.get_rxfh		= efx_ethtool_get_rxfh,
 	.set_rxfh		= efx_ethtool_set_rxfh,
-	.get_rxfh_context	= efx_ethtool_get_rxfh_context,
-	.set_rxfh_context	= efx_ethtool_set_rxfh_context,
 	.get_ts_info		= efx_ethtool_get_ts_info,
 	.get_module_info	= efx_ethtool_get_module_info,
 	.get_module_eeprom	= efx_ethtool_get_module_eeprom,
diff --git a/drivers/net/ethernet/sfc/ethtool_common.c b/drivers/net/ethernet/sfc/ethtool_common.c
index e32ae9038d9e..7d5e5db4eac5 100644
--- a/drivers/net/ethernet/sfc/ethtool_common.c
+++ b/drivers/net/ethernet/sfc/ethtool_common.c
@@ -1163,52 +1163,8 @@ u32 efx_ethtool_get_rxfh_key_size(struct net_device *net_dev)
 	return efx->type->rx_hash_key_size;
 }
 
-int efx_ethtool_get_rxfh(struct net_device *net_dev,
-			 struct ethtool_rxfh_param *rxfh)
-{
-	struct efx_nic *efx = efx_netdev_priv(net_dev);
-	int rc;
-
-	rc = efx->type->rx_pull_rss_config(efx);
-	if (rc)
-		return rc;
-
-	rxfh->hfunc = ETH_RSS_HASH_TOP;
-	if (rxfh->indir)
-		memcpy(rxfh->indir, efx->rss_context.rx_indir_table,
-		       sizeof(efx->rss_context.rx_indir_table));
-	if (rxfh->key)
-		memcpy(rxfh->key, efx->rss_context.rx_hash_key,
-		       efx->type->rx_hash_key_size);
-	return 0;
-}
-
-int efx_ethtool_set_rxfh(struct net_device *net_dev,
-			 struct ethtool_rxfh_param *rxfh,
-			 struct netlink_ext_ack *extack)
-{
-	struct efx_nic *efx = efx_netdev_priv(net_dev);
-	u32 *indir = rxfh->indir;
-	u8 *key = rxfh->key;
-
-	/* Hash function is Toeplitz, cannot be changed */
-	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
-	    rxfh->hfunc != ETH_RSS_HASH_TOP)
-		return -EOPNOTSUPP;
-	if (!indir && !key)
-		return 0;
-
-	if (!key)
-		key = efx->rss_context.rx_hash_key;
-	if (!indir)
-		indir = efx->rss_context.rx_indir_table;
-
-	return efx->type->rx_push_rss_config(efx, true, indir, key);
-}
-
-int efx_ethtool_get_rxfh_context(struct net_device *net_dev,
-				 struct ethtool_rxfh_param *rxfh,
-				 u32 rss_context)
+static int efx_ethtool_get_rxfh_context(struct net_device *net_dev,
+					struct ethtool_rxfh_param *rxfh)
 {
 	struct efx_nic *efx = efx_netdev_priv(net_dev);
 	struct efx_rss_context *ctx;
@@ -1218,7 +1174,7 @@ int efx_ethtool_get_rxfh_context(struct net_device *net_dev,
 		return -EOPNOTSUPP;
 
 	mutex_lock(&efx->rss_lock);
-	ctx = efx_find_rss_context_entry(efx, rss_context);
+	ctx = efx_find_rss_context_entry(efx, rxfh->rss_context);
 	if (!ctx) {
 		rc = -ENOENT;
 		goto out_unlock;
@@ -1239,11 +1195,35 @@ out_unlock:
 	return rc;
 }
 
-int efx_ethtool_set_rxfh_context(struct net_device *net_dev,
-				 struct ethtool_rxfh_param *rxfh,
-				 u32 *rss_context, bool delete)
+int efx_ethtool_get_rxfh(struct net_device *net_dev,
+			 struct ethtool_rxfh_param *rxfh)
 {
 	struct efx_nic *efx = efx_netdev_priv(net_dev);
+	int rc;
+
+	if (rxfh->rss_context)
+		return efx_ethtool_get_rxfh_context(net_dev, rxfh);
+
+	rc = efx->type->rx_pull_rss_config(efx);
+	if (rc)
+		return rc;
+
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+	if (rxfh->indir)
+		memcpy(rxfh->indir, efx->rss_context.rx_indir_table,
+		       sizeof(efx->rss_context.rx_indir_table));
+	if (rxfh->key)
+		memcpy(rxfh->key, efx->rss_context.rx_hash_key,
+		       efx->type->rx_hash_key_size);
+	return 0;
+}
+
+static int efx_ethtool_set_rxfh_context(struct net_device *net_dev,
+					struct ethtool_rxfh_param *rxfh,
+					struct netlink_ext_ack *extack)
+{
+	struct efx_nic *efx = efx_netdev_priv(net_dev);
+	u32 *rss_context = &rxfh->rss_context;
 	struct efx_rss_context *ctx;
 	u32 *indir = rxfh->indir;
 	bool allocated = false;
@@ -1252,15 +1232,11 @@ int efx_ethtool_set_rxfh_context(struct net_device *net_dev,
 
 	if (!efx->type->rx_push_rss_context_config)
 		return -EOPNOTSUPP;
-	/* Hash function is Toeplitz, cannot be changed */
-	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
-	    rxfh->hfunc != ETH_RSS_HASH_TOP)
-		return -EOPNOTSUPP;
 
 	mutex_lock(&efx->rss_lock);
 
 	if (*rss_context == ETH_RXFH_CONTEXT_ALLOC) {
-		if (delete) {
+		if (rxfh->rss_delete) {
 			/* alloc + delete == Nothing to do */
 			rc = -EINVAL;
 			goto out_unlock;
@@ -1283,7 +1259,7 @@ int efx_ethtool_set_rxfh_context(struct net_device *net_dev,
 		}
 	}
 
-	if (delete) {
+	if (rxfh->rss_delete) {
 		/* delete this context */
 		rc = efx->type->rx_push_rss_context_config(efx, ctx, NULL, NULL);
 		if (!rc)
@@ -1306,6 +1282,33 @@ out_unlock:
 	return rc;
 }
 
+int efx_ethtool_set_rxfh(struct net_device *net_dev,
+			 struct ethtool_rxfh_param *rxfh,
+			 struct netlink_ext_ack *extack)
+{
+	struct efx_nic *efx = efx_netdev_priv(net_dev);
+	u32 *indir = rxfh->indir;
+	u8 *key = rxfh->key;
+
+	/* Hash function is Toeplitz, cannot be changed */
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
+		return -EOPNOTSUPP;
+
+	if (rxfh->rss_context)
+		return efx_ethtool_set_rxfh_context(net_dev, rxfh, extack);
+
+	if (!indir && !key)
+		return 0;
+
+	if (!key)
+		key = efx->rss_context.rx_hash_key;
+	if (!indir)
+		indir = efx->rss_context.rx_indir_table;
+
+	return efx->type->rx_push_rss_config(efx, true, indir, key);
+}
+
 int efx_ethtool_reset(struct net_device *net_dev, u32 *flags)
 {
 	struct efx_nic *efx = efx_netdev_priv(net_dev);
diff --git a/drivers/net/ethernet/sfc/ethtool_common.h b/drivers/net/ethernet/sfc/ethtool_common.h
index 384318ee1127..a680e5980213 100644
--- a/drivers/net/ethernet/sfc/ethtool_common.h
+++ b/drivers/net/ethernet/sfc/ethtool_common.h
@@ -49,12 +49,6 @@ int efx_ethtool_get_rxfh(struct net_device *net_dev,
 int efx_ethtool_set_rxfh(struct net_device *net_dev,
 			 struct ethtool_rxfh_param *rxfh,
 			 struct netlink_ext_ack *extack);
-int efx_ethtool_get_rxfh_context(struct net_device *net_dev,
-				 struct ethtool_rxfh_param *rxfh,
-				 u32 rss_context);
-int efx_ethtool_set_rxfh_context(struct net_device *net_dev,
-				 struct ethtool_rxfh_param *rxfh,
-				 u32 *rss_context, bool delete);
 int efx_ethtool_reset(struct net_device *net_dev, u32 *flags);
 int efx_ethtool_get_module_eeprom(struct net_device *net_dev,
 				  struct ethtool_eeprom *ee,
diff --git a/drivers/net/ethernet/sfc/siena/ethtool.c b/drivers/net/ethernet/sfc/siena/ethtool.c
index e4ec589216c1..14dd3893bdef 100644
--- a/drivers/net/ethernet/sfc/siena/ethtool.c
+++ b/drivers/net/ethernet/sfc/siena/ethtool.c
@@ -240,6 +240,7 @@ static int efx_ethtool_get_ts_info(struct net_device *net_dev,
 }
 
 const struct ethtool_ops efx_siena_ethtool_ops = {
+	.cap_rss_ctx_supported	= true,
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_USECS_IRQ |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE_RX,
@@ -269,8 +270,6 @@ const struct ethtool_ops efx_siena_ethtool_ops = {
 	.get_rxfh_key_size	= efx_siena_ethtool_get_rxfh_key_size,
 	.get_rxfh		= efx_siena_ethtool_get_rxfh,
 	.set_rxfh		= efx_siena_ethtool_set_rxfh,
-	.get_rxfh_context	= efx_siena_ethtool_get_rxfh_context,
-	.set_rxfh_context	= efx_siena_ethtool_set_rxfh_context,
 	.get_ts_info		= efx_ethtool_get_ts_info,
 	.get_module_info	= efx_siena_ethtool_get_module_info,
 	.get_module_eeprom	= efx_siena_ethtool_get_module_eeprom,
diff --git a/drivers/net/ethernet/sfc/siena/ethtool_common.c b/drivers/net/ethernet/sfc/siena/ethtool_common.c
index 20b64e3521cb..5f0a8127e967 100644
--- a/drivers/net/ethernet/sfc/siena/ethtool_common.c
+++ b/drivers/net/ethernet/sfc/siena/ethtool_common.c
@@ -1164,52 +1164,8 @@ u32 efx_siena_ethtool_get_rxfh_key_size(struct net_device *net_dev)
 	return efx->type->rx_hash_key_size;
 }
 
-int efx_siena_ethtool_get_rxfh(struct net_device *net_dev,
-			       struct ethtool_rxfh_param *rxfh)
-{
-	struct efx_nic *efx = netdev_priv(net_dev);
-	int rc;
-
-	rc = efx->type->rx_pull_rss_config(efx);
-	if (rc)
-		return rc;
-
-	rxfh->hfunc = ETH_RSS_HASH_TOP;
-	if (rxfh->indir)
-		memcpy(rxfh->indir, efx->rss_context.rx_indir_table,
-		       sizeof(efx->rss_context.rx_indir_table));
-	if (rxfh->key)
-		memcpy(rxfh->key, efx->rss_context.rx_hash_key,
-		       efx->type->rx_hash_key_size);
-	return 0;
-}
-
-int efx_siena_ethtool_set_rxfh(struct net_device *net_dev,
-			       struct ethtool_rxfh_param *rxfh,
-			       struct netlink_ext_ack *extack)
-{
-	struct efx_nic *efx = netdev_priv(net_dev);
-	u32 *indir = rxfh->indir;
-	u8 *key = rxfh->key;
-
-	/* Hash function is Toeplitz, cannot be changed */
-	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
-	    rxfh->hfunc != ETH_RSS_HASH_TOP)
-		return -EOPNOTSUPP;
-	if (!indir && !key)
-		return 0;
-
-	if (!key)
-		key = efx->rss_context.rx_hash_key;
-	if (!indir)
-		indir = efx->rss_context.rx_indir_table;
-
-	return efx->type->rx_push_rss_config(efx, true, indir, key);
-}
-
-int efx_siena_ethtool_get_rxfh_context(struct net_device *net_dev,
-				       struct ethtool_rxfh_param *rxfh,
-				       u32 rss_context)
+static int efx_siena_ethtool_get_rxfh_context(struct net_device *net_dev,
+					      struct ethtool_rxfh_param *rxfh)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
 	struct efx_rss_context *ctx;
@@ -1219,7 +1175,7 @@ int efx_siena_ethtool_get_rxfh_context(struct net_device *net_dev,
 		return -EOPNOTSUPP;
 
 	mutex_lock(&efx->rss_lock);
-	ctx = efx_siena_find_rss_context_entry(efx, rss_context);
+	ctx = efx_siena_find_rss_context_entry(efx, rxfh->rss_context);
 	if (!ctx) {
 		rc = -ENOENT;
 		goto out_unlock;
@@ -1240,11 +1196,35 @@ out_unlock:
 	return rc;
 }
 
-int efx_siena_ethtool_set_rxfh_context(struct net_device *net_dev,
-				       struct ethtool_rxfh_param *rxfh,
-				       u32 *rss_context, bool delete)
+int efx_siena_ethtool_get_rxfh(struct net_device *net_dev,
+			       struct ethtool_rxfh_param *rxfh)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
+	int rc;
+
+	if (rxfh->rss_context)
+		return efx_siena_ethtool_get_rxfh_context(net_dev, rxfh);
+
+	rc = efx->type->rx_pull_rss_config(efx);
+	if (rc)
+		return rc;
+
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+	if (rxfh->indir)
+		memcpy(rxfh->indir, efx->rss_context.rx_indir_table,
+		       sizeof(efx->rss_context.rx_indir_table));
+	if (rxfh->key)
+		memcpy(rxfh->key, efx->rss_context.rx_hash_key,
+		       efx->type->rx_hash_key_size);
+	return 0;
+}
+
+static int efx_siena_ethtool_set_rxfh_context(struct net_device *net_dev,
+					      struct ethtool_rxfh_param *rxfh,
+					      struct netlink_ext_ack *extack)
+{
+	struct efx_nic *efx = netdev_priv(net_dev);
+	u32 *rss_context = &rxfh->rss_context;
 	struct efx_rss_context *ctx;
 	u32 *indir = rxfh->indir;
 	bool allocated = false;
@@ -1253,15 +1233,11 @@ int efx_siena_ethtool_set_rxfh_context(struct net_device *net_dev,
 
 	if (!efx->type->rx_push_rss_context_config)
 		return -EOPNOTSUPP;
-	/* Hash function is Toeplitz, cannot be changed */
-	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
-	    rxfh->hfunc != ETH_RSS_HASH_TOP)
-		return -EOPNOTSUPP;
 
 	mutex_lock(&efx->rss_lock);
 
 	if (*rss_context == ETH_RXFH_CONTEXT_ALLOC) {
-		if (delete) {
+		if (rxfh->rss_delete) {
 			/* alloc + delete == Nothing to do */
 			rc = -EINVAL;
 			goto out_unlock;
@@ -1284,7 +1260,7 @@ int efx_siena_ethtool_set_rxfh_context(struct net_device *net_dev,
 		}
 	}
 
-	if (delete) {
+	if (rxfh->rss_delete) {
 		/* delete this context */
 		rc = efx->type->rx_push_rss_context_config(efx, ctx, NULL, NULL);
 		if (!rc)
@@ -1307,6 +1283,33 @@ out_unlock:
 	return rc;
 }
 
+int efx_siena_ethtool_set_rxfh(struct net_device *net_dev,
+			       struct ethtool_rxfh_param *rxfh,
+			       struct netlink_ext_ack *extack)
+{
+	struct efx_nic *efx = netdev_priv(net_dev);
+	u32 *indir = rxfh->indir;
+	u8 *key = rxfh->key;
+
+	/* Hash function is Toeplitz, cannot be changed */
+	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    rxfh->hfunc != ETH_RSS_HASH_TOP)
+		return -EOPNOTSUPP;
+
+	if (rxfh->rss_context)
+		efx_siena_ethtool_set_rxfh_context(net_dev, rxfh, extack);
+
+	if (!indir && !key)
+		return 0;
+
+	if (!key)
+		key = efx->rss_context.rx_hash_key;
+	if (!indir)
+		indir = efx->rss_context.rx_indir_table;
+
+	return efx->type->rx_push_rss_config(efx, true, indir, key);
+}
+
 int efx_siena_ethtool_reset(struct net_device *net_dev, u32 *flags)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
diff --git a/drivers/net/ethernet/sfc/siena/ethtool_common.h b/drivers/net/ethernet/sfc/siena/ethtool_common.h
index 2f892f8eff70..d674bab0f65b 100644
--- a/drivers/net/ethernet/sfc/siena/ethtool_common.h
+++ b/drivers/net/ethernet/sfc/siena/ethtool_common.h
@@ -46,12 +46,6 @@ int efx_siena_ethtool_get_rxfh(struct net_device *net_dev,
 int efx_siena_ethtool_set_rxfh(struct net_device *net_dev,
 			       struct ethtool_rxfh_param *rxfh,
 			       struct netlink_ext_ack *extack);
-int efx_siena_ethtool_get_rxfh_context(struct net_device *net_dev,
-				       struct ethtool_rxfh_param *rxfh,
-				       u32 rss_context);
-int efx_siena_ethtool_set_rxfh_context(struct net_device *net_dev,
-				       struct ethtool_rxfh_param *rxfh,
-				       u32 *rss_context, bool delete);
 int efx_siena_ethtool_reset(struct net_device *net_dev, u32 *flags);
 int efx_siena_ethtool_get_module_eeprom(struct net_device *net_dev,
 					struct ethtool_eeprom *ee,
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 3ab2b6a90419..66fe254c3e51 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -609,6 +609,12 @@ struct ethtool_mm_stats {
  *	which may be zero.  On GET (read from the driver), the size of the
  *	hardware hash key.
  * @key: The hash key of size @key_size bytes.
+ * @rss_context: RSS context identifier.  Context 0 is the default for normal
+ *	traffic; other contexts can be referenced as the destination for RX flow
+ *	classification rules.  On SET, %ETH_RXFH_CONTEXT_ALLOC is used
+ *	to allocate a new RSS context; on return this field will
+ *	contain the ID of the newly allocated context.
+ * @rss_delete: Set to non-ZERO to remove the @rss_context context.
  */
 struct ethtool_rxfh_param {
 	u8	hfunc;
@@ -616,12 +622,16 @@ struct ethtool_rxfh_param {
 	u32	*indir;
 	u32	key_size;
 	u8	*key;
+	u32	rss_context;
+	u8	rss_delete;
 };
 
 /**
  * struct ethtool_ops - optional netdev operations
  * @cap_link_lanes_supported: indicates if the driver supports lanes
  *	parameter.
+ * @cap_rss_ctx_supported: indicates if the driver supports RSS
+ *	contexts.
  * @supported_coalesce_params: supported types of interrupt coalescing.
  * @supported_ring_params: supported ring params.
  * @get_drvinfo: Report driver/device information. Modern drivers no
@@ -718,15 +728,6 @@ struct ethtool_rxfh_param {
  *	will remain unchanged.
  *	Returns a negative error code or zero. An error code must be returned
  *	if at least one unsupported change was requested.
- * @get_rxfh_context: Get the contents of the RX flow hash indirection table,
- *	hash key, and/or hash function assiciated to the given rss context.
- *	Returns a negative error code or zero.
- * @set_rxfh_context: Create, remove and configure RSS contexts. Allows setting
- *	the contents of the RX flow hash indirection table, hash key, and/or
- *	hash function associated to the given context. Arguments which are set
- *	to %NULL or zero will remain unchanged.
- *	Returns a negative error code or zero. An error code must be returned
- *	if at least one unsupported change was requested.
  * @get_channels: Get number of channels.
  * @set_channels: Set number of channels.  Returns a negative error code or
  *	zero.
@@ -809,6 +810,7 @@ struct ethtool_rxfh_param {
  */
 struct ethtool_ops {
 	u32     cap_link_lanes_supported:1;
+	u32     cap_rss_ctx_supported:1;
 	u32	supported_coalesce_params;
 	u32	supported_ring_params;
 	void	(*get_drvinfo)(struct net_device *, struct ethtool_drvinfo *);
@@ -871,12 +873,6 @@ struct ethtool_ops {
 	int	(*get_rxfh)(struct net_device *, struct ethtool_rxfh_param *);
 	int	(*set_rxfh)(struct net_device *, struct ethtool_rxfh_param *,
 			    struct netlink_ext_ack *extack);
-	int	(*get_rxfh_context)(struct net_device *,
-				    struct ethtool_rxfh_param *,
-				    u32 rss_context);
-	int	(*set_rxfh_context)(struct net_device *,
-				    struct ethtool_rxfh_param *,
-				    u32 *rss_context, bool delete);
 	void	(*get_channels)(struct net_device *, struct ethtool_channels *);
 	int	(*set_channels)(struct net_device *, struct ethtool_channels *);
 	int	(*get_dump_flag)(struct net_device *, struct ethtool_dump *);
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 5f49a105fc73..86e5fc64b711 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -1201,7 +1201,7 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev,
 	if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd8[2] || rxfh.rsvd32)
 		return -EINVAL;
 	/* Most drivers don't handle rss_context, check it's 0 as well */
-	if (rxfh.rss_context && !ops->get_rxfh_context)
+	if (rxfh.rss_context && !ops->cap_rss_ctx_supported)
 		return -EOPNOTSUPP;
 
 	rxfh.indir_size = rxfh_dev.indir_size;
@@ -1225,11 +1225,9 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev,
 	if (user_key_size)
 		rxfh_dev.key = rss_config + indir_bytes;
 
-	if (rxfh.rss_context)
-		ret = dev->ethtool_ops->get_rxfh_context(dev, &rxfh_dev,
-							 rxfh.rss_context);
-	else
-		ret = dev->ethtool_ops->get_rxfh(dev, &rxfh_dev);
+	rxfh_dev.rss_context = rxfh.rss_context;
+
+	ret = dev->ethtool_ops->get_rxfh(dev, &rxfh_dev);
 	if (ret)
 		goto out;
 
@@ -1257,7 +1255,6 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 	struct netlink_ext_ack *extack = NULL;
 	struct ethtool_rxnfc rx_rings;
 	struct ethtool_rxfh rxfh;
-	bool delete = false;
 	u32 indir_bytes = 0;
 	u8 *rss_config;
 	int ret;
@@ -1277,7 +1274,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 	if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd8[2] || rxfh.rsvd32)
 		return -EINVAL;
 	/* Most drivers don't handle rss_context, check it's 0 as well */
-	if (rxfh.rss_context && !ops->set_rxfh_context)
+	if (rxfh.rss_context && !ops->cap_rss_ctx_supported)
 		return -EOPNOTSUPP;
 
 	/* If either indir, hash key or function is valid, proceed further.
@@ -1327,7 +1324,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 			for (i = 0; i < dev_indir_size; i++)
 				indir[i] = ethtool_rxfh_indir_default(i, rx_rings.data);
 		} else {
-			delete = true;
+			rxfh_dev.rss_delete = true;
 		}
 	}
 
@@ -1343,21 +1340,17 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 	}
 
 	rxfh_dev.hfunc = rxfh.hfunc;
+	rxfh_dev.rss_context = rxfh.rss_context;
 
-	if (rxfh.rss_context)
-		ret = ops->set_rxfh_context(dev, &rxfh_dev,
-					    &rxfh.rss_context, delete);
-	else
-		ret = ops->set_rxfh(dev, &rxfh_dev, extack);
-
+	ret = ops->set_rxfh(dev, &rxfh_dev, extack);
 	if (ret)
 		goto out;
 
 	if (copy_to_user(useraddr + offsetof(struct ethtool_rxfh, rss_context),
-			 &rxfh.rss_context, sizeof(rxfh.rss_context)))
+			 &rxfh_dev.rss_context, sizeof(rxfh_dev.rss_context)))
 		ret = -EFAULT;
 
-	if (!rxfh.rss_context) {
+	if (!rxfh_dev.rss_context) {
 		/* indicate whether rxfh was set to default */
 		if (rxfh.indir_size == 0)
 			dev->priv_flags &= ~IFF_RXFH_CONFIGURED;
diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c
index 56fae7d5c0f7..efc9f4409e40 100644
--- a/net/ethtool/rss.c
+++ b/net/ethtool/rss.c
@@ -59,7 +59,7 @@ rss_prepare_data(const struct ethnl_req_info *req_base,
 		return -EOPNOTSUPP;
 
 	/* Some drivers don't handle rss_context */
-	if (request->rss_context && !ops->get_rxfh_context)
+	if (request->rss_context && !ops->cap_rss_ctx_supported)
 		return -EOPNOTSUPP;
 
 	ret = ethnl_ops_begin(dev);
@@ -90,12 +90,9 @@ rss_prepare_data(const struct ethnl_req_info *req_base,
 	rxfh.indir = data->indir_table;
 	rxfh.key_size = data->hkey_size;
 	rxfh.key = data->hkey;
+	rxfh.rss_context = request->rss_context;
 
-	if (request->rss_context)
-		ret = ops->get_rxfh_context(dev, &rxfh, request->rss_context);
-	else
-		ret = ops->get_rxfh(dev, &rxfh);
-
+	ret = ops->get_rxfh(dev, &rxfh);
 	if (ret)
 		goto out_ops;
 
-- 
cgit v1.2.3


From 13e59344fb9d3c9d3acd138ae320b5b67b658694 Mon Sep 17 00:00:00 2001
From: Ahmed Zaki <ahmed.zaki@intel.com>
Date: Tue, 12 Dec 2023 17:33:16 -0700
Subject: net: ethtool: add support for symmetric-xor RSS hash

Symmetric RSS hash functions are beneficial in applications that monitor
both Tx and Rx packets of the same flow (IDS, software firewalls, ..etc).
Getting all traffic of the same flow on the same RX queue results in
higher CPU cache efficiency.

A NIC that supports "symmetric-xor" can achieve this RSS hash symmetry
by XORing the source and destination fields and pass the values to the
RSS hash algorithm.

The user may request RSS hash symmetry for a specific algorithm, via:

    # ethtool -X eth0 hfunc <hash_alg> symmetric-xor

or turn symmetry off (asymmetric) by:

    # ethtool -X eth0 hfunc <hash_alg>

The specific fields for each flow type should then be specified as usual
via:
    # ethtool -N|-U eth0 rx-flow-hash <flow_type> s|d|f|n

Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
Link: https://lore.kernel.org/r/20231213003321.605376-4-ahmed.zaki@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/ethtool.yaml     |  4 ++++
 Documentation/networking/ethtool-netlink.rst |  6 +++++-
 Documentation/networking/scaling.rst         | 15 ++++++++++++++
 include/linux/ethtool.h                      |  6 ++++++
 include/uapi/linux/ethtool.h                 | 13 +++++++++++-
 include/uapi/linux/ethtool_netlink.h         |  1 +
 net/ethtool/ioctl.c                          | 30 ++++++++++++++++++++++++----
 net/ethtool/rss.c                            |  5 +++++
 8 files changed, 74 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml
index 5c7a65b009b4..197208f419dc 100644
--- a/Documentation/netlink/specs/ethtool.yaml
+++ b/Documentation/netlink/specs/ethtool.yaml
@@ -908,6 +908,9 @@ attribute-sets:
       -
         name: hkey
         type: binary
+      -
+        name: input_xfrm
+        type: u32
   -
     name: plca
     attributes:
@@ -1598,6 +1601,7 @@ operations:
             - hfunc
             - indir
             - hkey
+            - input_xfrm
       dump: *rss-get-op
     -
       name: plca-get-cfg
diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst
index 6a49624a9cbf..d583d9abf2f8 100644
--- a/Documentation/networking/ethtool-netlink.rst
+++ b/Documentation/networking/ethtool-netlink.rst
@@ -1774,12 +1774,16 @@ Kernel response contents:
   ``ETHTOOL_A_RSS_HFUNC``              u32     RSS hash func
   ``ETHTOOL_A_RSS_INDIR``              binary  Indir table bytes
   ``ETHTOOL_A_RSS_HKEY``               binary  Hash key bytes
+  ``ETHTOOL_A_RSS_INPUT_XFRM``         u32     RSS input data transformation
 =====================================  ======  ==========================
 
 ETHTOOL_A_RSS_HFUNC attribute is bitmap indicating the hash function
 being used. Current supported options are toeplitz, xor or crc32.
-ETHTOOL_A_RSS_INDIR attribute returns RSS indrection table where each byte
+ETHTOOL_A_RSS_INDIR attribute returns RSS indirection table where each byte
 indicates queue number.
+ETHTOOL_A_RSS_INPUT_XFRM attribute is a bitmap indicating the type of
+transformation applied to the input protocol fields before given to the RSS
+hfunc. Current supported option is symmetric-xor.
 
 PLCA_GET_CFG
 ============
diff --git a/Documentation/networking/scaling.rst b/Documentation/networking/scaling.rst
index 03ae19a689fc..4eb50bcb9d42 100644
--- a/Documentation/networking/scaling.rst
+++ b/Documentation/networking/scaling.rst
@@ -44,6 +44,21 @@ by masking out the low order seven bits of the computed hash for the
 packet (usually a Toeplitz hash), taking this number as a key into the
 indirection table and reading the corresponding value.
 
+Some NICs support symmetric RSS hashing where, if the IP (source address,
+destination address) and TCP/UDP (source port, destination port) tuples
+are swapped, the computed hash is the same. This is beneficial in some
+applications that monitor TCP/IP flows (IDS, firewalls, ...etc) and need
+both directions of the flow to land on the same Rx queue (and CPU). The
+"Symmetric-XOR" is a type of RSS algorithms that achieves this hash
+symmetry by XORing the input source and destination fields of the IP
+and/or L4 protocols. This, however, results in reduced input entropy and
+could potentially be exploited. Specifically, the algorithm XORs the input
+as follows::
+
+    # (SRC_IP ^ DST_IP, SRC_IP ^ DST_IP, SRC_PORT ^ DST_PORT, SRC_PORT ^ DST_PORT)
+
+The result is then fed to the underlying RSS algorithm.
+
 Some advanced NICs allow steering packets to queues based on
 programmable filters. For example, webserver bound TCP port 80 packets
 can be directed to their own receive queue. Such “n-tuple” filters can
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 66fe254c3e51..cfcd952a1d4f 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -615,6 +615,8 @@ struct ethtool_mm_stats {
  *	to allocate a new RSS context; on return this field will
  *	contain the ID of the newly allocated context.
  * @rss_delete: Set to non-ZERO to remove the @rss_context context.
+ * @input_xfrm: Defines how the input data is transformed. Valid values are one
+ *	of %RXH_XFRM_*.
  */
 struct ethtool_rxfh_param {
 	u8	hfunc;
@@ -624,6 +626,7 @@ struct ethtool_rxfh_param {
 	u8	*key;
 	u32	rss_context;
 	u8	rss_delete;
+	u8	input_xfrm;
 };
 
 /**
@@ -632,6 +635,8 @@ struct ethtool_rxfh_param {
  *	parameter.
  * @cap_rss_ctx_supported: indicates if the driver supports RSS
  *	contexts.
+ * @cap_rss_sym_xor_supported: indicates if the driver supports symmetric-xor
+ *	RSS.
  * @supported_coalesce_params: supported types of interrupt coalescing.
  * @supported_ring_params: supported ring params.
  * @get_drvinfo: Report driver/device information. Modern drivers no
@@ -811,6 +816,7 @@ struct ethtool_rxfh_param {
 struct ethtool_ops {
 	u32     cap_link_lanes_supported:1;
 	u32     cap_rss_ctx_supported:1;
+	u32	cap_rss_sym_xor_supported:1;
 	u32	supported_coalesce_params;
 	u32	supported_ring_params;
 	void	(*get_drvinfo)(struct net_device *, struct ethtool_drvinfo *);
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index f7fba0dc87e5..0787d561ace0 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -1266,6 +1266,8 @@ struct ethtool_rxfh_indir {
  *	hardware hash key.
  * @hfunc: Defines the current RSS hash function used by HW (or to be set to).
  *	Valid values are one of the %ETH_RSS_HASH_*.
+ * @input_xfrm: Defines how the input data is transformed. Valid values are one
+ *	of %RXH_XFRM_*.
  * @rsvd8: Reserved for future use; see the note on reserved space.
  * @rsvd32: Reserved for future use; see the note on reserved space.
  * @rss_config: RX ring/queue index for each hash value i.e., indirection table
@@ -1285,7 +1287,8 @@ struct ethtool_rxfh {
 	__u32   indir_size;
 	__u32   key_size;
 	__u8	hfunc;
-	__u8	rsvd8[3];
+	__u8	input_xfrm;
+	__u8	rsvd8[2];
 	__u32	rsvd32;
 	__u32   rss_config[];
 };
@@ -1992,6 +1995,14 @@ static inline int ethtool_validate_duplex(__u8 duplex)
 
 #define WOL_MODE_COUNT		8
 
+/* RSS hash function data
+ * XOR the corresponding source and destination fields of each specified
+ * protocol. Both copies of the XOR'ed fields are fed into the RSS and RXHASH
+ * calculation. Note that this XORing reduces the input set entropy and could
+ * be exploited to reduce the RSS queue spread.
+ */
+#define	RXH_XFRM_SYM_XOR	(1 << 0)
+
 /* L2-L4 network traffic flow types */
 #define	TCP_V4_FLOW	0x01	/* hash or spec (tcp_ip4_spec) */
 #define	UDP_V4_FLOW	0x02	/* hash or spec (udp_ip4_spec) */
diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h
index 73e2c10dc2cc..3f89074aa06c 100644
--- a/include/uapi/linux/ethtool_netlink.h
+++ b/include/uapi/linux/ethtool_netlink.h
@@ -908,6 +908,7 @@ enum {
 	ETHTOOL_A_RSS_HFUNC,		/* u32 */
 	ETHTOOL_A_RSS_INDIR,		/* binary */
 	ETHTOOL_A_RSS_HKEY,		/* binary */
+	ETHTOOL_A_RSS_INPUT_XFRM,	/* u32 */
 
 	__ETHTOOL_A_RSS_CNT,
 	ETHTOOL_A_RSS_MAX = (__ETHTOOL_A_RSS_CNT - 1),
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 86e5fc64b711..86d47425038b 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -972,18 +972,35 @@ static int ethtool_rxnfc_copy_to_user(void __user *useraddr,
 static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev,
 						u32 cmd, void __user *useraddr)
 {
+	const struct ethtool_ops *ops = dev->ethtool_ops;
+	struct ethtool_rxfh_param rxfh = {};
 	struct ethtool_rxnfc info;
 	size_t info_size = sizeof(info);
 	int rc;
 
-	if (!dev->ethtool_ops->set_rxnfc)
+	if (!ops->set_rxnfc || !ops->get_rxfh)
 		return -EOPNOTSUPP;
 
 	rc = ethtool_rxnfc_copy_struct(cmd, &info, &info_size, useraddr);
 	if (rc)
 		return rc;
 
-	rc = dev->ethtool_ops->set_rxnfc(dev, &info);
+	rc = ops->get_rxfh(dev, &rxfh);
+	if (rc)
+		return rc;
+
+	/* Sanity check: if symmetric-xor is set, then:
+	 * 1 - no other fields besides IP src/dst and/or L4 src/dst
+	 * 2 - If src is set, dst must also be set
+	 */
+	if ((rxfh.input_xfrm & RXH_XFRM_SYM_XOR) &&
+	    ((info.data & ~(RXH_IP_SRC | RXH_IP_DST |
+			    RXH_L4_B_0_1 | RXH_L4_B_2_3)) ||
+	     (!!(info.data & RXH_IP_SRC) ^ !!(info.data & RXH_IP_DST)) ||
+	     (!!(info.data & RXH_L4_B_0_1) ^ !!(info.data & RXH_L4_B_2_3))))
+		return -EINVAL;
+
+	rc = ops->set_rxnfc(dev, &info);
 	if (rc)
 		return rc;
 
@@ -1198,7 +1215,7 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev,
 	user_key_size = rxfh.key_size;
 
 	/* Check that reserved fields are 0 for now */
-	if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd8[2] || rxfh.rsvd32)
+	if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd32)
 		return -EINVAL;
 	/* Most drivers don't handle rss_context, check it's 0 as well */
 	if (rxfh.rss_context && !ops->cap_rss_ctx_supported)
@@ -1271,11 +1288,15 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 		return -EFAULT;
 
 	/* Check that reserved fields are 0 for now */
-	if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd8[2] || rxfh.rsvd32)
+	if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd32)
 		return -EINVAL;
 	/* Most drivers don't handle rss_context, check it's 0 as well */
 	if (rxfh.rss_context && !ops->cap_rss_ctx_supported)
 		return -EOPNOTSUPP;
+	/* Check input data transformation capabilities */
+	if ((rxfh.input_xfrm & RXH_XFRM_SYM_XOR) &&
+	    !ops->cap_rss_sym_xor_supported)
+		return -EOPNOTSUPP;
 
 	/* If either indir, hash key or function is valid, proceed further.
 	 * Must request at least one change: indir size, hash key or function.
@@ -1341,6 +1362,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 
 	rxfh_dev.hfunc = rxfh.hfunc;
 	rxfh_dev.rss_context = rxfh.rss_context;
+	rxfh_dev.input_xfrm = rxfh.input_xfrm;
 
 	ret = ops->set_rxfh(dev, &rxfh_dev, extack);
 	if (ret)
diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c
index efc9f4409e40..71679137eff2 100644
--- a/net/ethtool/rss.c
+++ b/net/ethtool/rss.c
@@ -13,6 +13,7 @@ struct rss_reply_data {
 	u32				indir_size;
 	u32				hkey_size;
 	u32				hfunc;
+	u32				input_xfrm;
 	u32				*indir_table;
 	u8				*hkey;
 };
@@ -97,6 +98,7 @@ rss_prepare_data(const struct ethnl_req_info *req_base,
 		goto out_ops;
 
 	data->hfunc = rxfh.hfunc;
+	data->input_xfrm = rxfh.input_xfrm;
 out_ops:
 	ethnl_ops_complete(dev);
 	return ret;
@@ -110,6 +112,7 @@ rss_reply_size(const struct ethnl_req_info *req_base,
 	int len;
 
 	len = nla_total_size(sizeof(u32)) +	/* _RSS_HFUNC */
+	      nla_total_size(sizeof(u32)) +	/* _RSS_INPUT_XFRM */
 	      nla_total_size(sizeof(u32) * data->indir_size) + /* _RSS_INDIR */
 	      nla_total_size(data->hkey_size);	/* _RSS_HKEY */
 
@@ -124,6 +127,8 @@ rss_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base,
 
 	if ((data->hfunc &&
 	     nla_put_u32(skb, ETHTOOL_A_RSS_HFUNC, data->hfunc)) ||
+	    (data->input_xfrm &&
+	     nla_put_u32(skb, ETHTOOL_A_RSS_INPUT_XFRM, data->input_xfrm)) ||
 	    (data->indir_size &&
 	     nla_put(skb, ETHTOOL_A_RSS_INDIR,
 		     sizeof(u32) * data->indir_size, data->indir_table)) ||
-- 
cgit v1.2.3


From dc6e44c9d6d68e8aa5de78d15f43f93145719b72 Mon Sep 17 00:00:00 2001
From: Qi Zhang <qi.z.zhang@intel.com>
Date: Tue, 12 Dec 2023 17:33:18 -0700
Subject: ice: refactor RSS configuration

Refactor the driver to use a communication data structure for RSS
config. To do so we introduce the new ice_rss_hash_cfg struct, and then
pass it as an argument to several functions.

Also introduce enum ice_rss_cfg_hdr_type to specify a more granular and
flexible RSS configuration:

ICE_RSS_OUTER_HEADERS - take outer layer as RSS input set
ICE_RSS_INNER_HEADERS - take inner layer as RSS input set
ICE_RSS_INNER_HEADERS_W_OUTER_IPV4 - take inner layer as RSS input set for
                                     packet with outer IPV4
ICE_RSS_INNER_HEADERS_W_OUTER_IPV6 - take inner layer as RSS input set for
                                     packet with outer IPV6
ICE_RSS_ANY_HEADERS - try with outer first then inner (same as the
		      behaviour without this change)

Finally, move the virtchnl_rss_algorithm enum to be with the other RSS
related structures in the virtchnl.h file.

There should be no functional change due to this patch.

Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Co-developed-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Co-developed-by: Ahmed Zaki <ahmed.zaki@intel.com>
Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
Link: https://lore.kernel.org/r/20231213003321.605376-6-ahmed.zaki@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_ethtool.c  |   6 +-
 drivers/net/ethernet/intel/ice/ice_flow.c     | 232 ++++++++++++++++----------
 drivers/net/ethernet/intel/ice/ice_flow.h     |  33 +++-
 drivers/net/ethernet/intel/ice/ice_lib.c      | 100 +++++------
 drivers/net/ethernet/intel/ice/ice_virtchnl.c |  36 ++--
 include/linux/avf/virtchnl.h                  |  16 +-
 6 files changed, 246 insertions(+), 177 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index c77605b42833..fcd8678bea66 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -2591,6 +2591,7 @@ static int
 ice_set_rss_hash_opt(struct ice_vsi *vsi, struct ethtool_rxnfc *nfc)
 {
 	struct ice_pf *pf = vsi->back;
+	struct ice_rss_hash_cfg cfg;
 	struct device *dev;
 	u64 hashed_flds;
 	int status;
@@ -2617,7 +2618,10 @@ ice_set_rss_hash_opt(struct ice_vsi *vsi, struct ethtool_rxnfc *nfc)
 		return -EINVAL;
 	}
 
-	status = ice_add_rss_cfg(&pf->hw, vsi->idx, hashed_flds, hdrs);
+	cfg.hash_flds = hashed_flds;
+	cfg.addl_hdrs = hdrs;
+	cfg.hdr_type = ICE_RSS_ANY_HEADERS;
+	status = ice_add_rss_cfg(&pf->hw, vsi->idx, &cfg);
 	if (status) {
 		dev_dbg(dev, "ice_add_rss_cfg failed, vsi num = %d, error = %d\n",
 			vsi->vsi_num, status);
diff --git a/drivers/net/ethernet/intel/ice/ice_flow.c b/drivers/net/ethernet/intel/ice/ice_flow.c
index fb8b925aaf8b..c34be72f99b3 100644
--- a/drivers/net/ethernet/intel/ice/ice_flow.c
+++ b/drivers/net/ethernet/intel/ice/ice_flow.c
@@ -1855,37 +1855,49 @@ int ice_flow_rem_vsi_prof(struct ice_hw *hw, u16 vsi_handle, u64 prof_id)
 /**
  * ice_flow_set_rss_seg_info - setup packet segments for RSS
  * @segs: pointer to the flow field segment(s)
- * @hash_fields: fields to be hashed on for the segment(s)
- * @flow_hdr: protocol header fields within a packet segment
+ * @seg_cnt: segment count
+ * @cfg: configure parameters
  *
  * Helper function to extract fields from hash bitmap and use flow
  * header value to set flow field segment for further use in flow
  * profile entry or removal.
  */
 static int
-ice_flow_set_rss_seg_info(struct ice_flow_seg_info *segs, u64 hash_fields,
-			  u32 flow_hdr)
+ice_flow_set_rss_seg_info(struct ice_flow_seg_info *segs, u8 seg_cnt,
+			  const struct ice_rss_hash_cfg *cfg)
 {
+	struct ice_flow_seg_info *seg;
 	u64 val;
-	u8 i;
+	u16 i;
+
+	/* set inner most segment */
+	seg = &segs[seg_cnt - 1];
 
-	for_each_set_bit(i, (unsigned long *)&hash_fields,
-			 ICE_FLOW_FIELD_IDX_MAX)
-		ice_flow_set_fld(segs, (enum ice_flow_field)i,
+	for_each_set_bit(i, (const unsigned long *)&cfg->hash_flds,
+			 (u16)ICE_FLOW_FIELD_IDX_MAX)
+		ice_flow_set_fld(seg, (enum ice_flow_field)i,
 				 ICE_FLOW_FLD_OFF_INVAL, ICE_FLOW_FLD_OFF_INVAL,
 				 ICE_FLOW_FLD_OFF_INVAL, false);
 
-	ICE_FLOW_SET_HDRS(segs, flow_hdr);
+	ICE_FLOW_SET_HDRS(seg, cfg->addl_hdrs);
 
-	if (segs->hdrs & ~ICE_FLOW_RSS_SEG_HDR_VAL_MASKS &
+	/* set outer most header */
+	if (cfg->hdr_type == ICE_RSS_INNER_HEADERS_W_OUTER_IPV4)
+		segs[ICE_RSS_OUTER_HEADERS].hdrs |= ICE_FLOW_SEG_HDR_IPV4 |
+						    ICE_FLOW_SEG_HDR_IPV_OTHER;
+	else if (cfg->hdr_type == ICE_RSS_INNER_HEADERS_W_OUTER_IPV6)
+		segs[ICE_RSS_OUTER_HEADERS].hdrs |= ICE_FLOW_SEG_HDR_IPV6 |
+						    ICE_FLOW_SEG_HDR_IPV_OTHER;
+
+	if (seg->hdrs & ~ICE_FLOW_RSS_SEG_HDR_VAL_MASKS &
 	    ~ICE_FLOW_RSS_HDRS_INNER_MASK & ~ICE_FLOW_SEG_HDR_IPV_OTHER)
 		return -EINVAL;
 
-	val = (u64)(segs->hdrs & ICE_FLOW_RSS_SEG_HDR_L3_MASKS);
+	val = (u64)(seg->hdrs & ICE_FLOW_RSS_SEG_HDR_L3_MASKS);
 	if (val && !is_power_of_2(val))
 		return -EIO;
 
-	val = (u64)(segs->hdrs & ICE_FLOW_RSS_SEG_HDR_L4_MASKS);
+	val = (u64)(seg->hdrs & ICE_FLOW_RSS_SEG_HDR_L4_MASKS);
 	if (val && !is_power_of_2(val))
 		return -EIO;
 
@@ -1955,6 +1967,39 @@ int ice_rem_vsi_rss_cfg(struct ice_hw *hw, u16 vsi_handle)
 	return status;
 }
 
+/**
+ * ice_get_rss_hdr_type - get a RSS profile's header type
+ * @prof: RSS flow profile
+ */
+static enum ice_rss_cfg_hdr_type
+ice_get_rss_hdr_type(struct ice_flow_prof *prof)
+{
+	if (prof->segs_cnt == ICE_FLOW_SEG_SINGLE) {
+		return ICE_RSS_OUTER_HEADERS;
+	} else if (prof->segs_cnt == ICE_FLOW_SEG_MAX) {
+		const struct ice_flow_seg_info *s;
+
+		s = &prof->segs[ICE_RSS_OUTER_HEADERS];
+		if (s->hdrs == ICE_FLOW_SEG_HDR_NONE)
+			return ICE_RSS_INNER_HEADERS;
+		if (s->hdrs & ICE_FLOW_SEG_HDR_IPV4)
+			return ICE_RSS_INNER_HEADERS_W_OUTER_IPV4;
+		if (s->hdrs & ICE_FLOW_SEG_HDR_IPV6)
+			return ICE_RSS_INNER_HEADERS_W_OUTER_IPV6;
+	}
+
+	return ICE_RSS_ANY_HEADERS;
+}
+
+static bool
+ice_rss_match_prof(struct ice_rss_cfg *r, struct ice_flow_prof *prof,
+		   enum ice_rss_cfg_hdr_type hdr_type)
+{
+	return (r->hash.hdr_type == hdr_type &&
+		r->hash.hash_flds == prof->segs[prof->segs_cnt - 1].match &&
+		r->hash.addl_hdrs == prof->segs[prof->segs_cnt - 1].hdrs);
+}
+
 /**
  * ice_rem_rss_list - remove RSS configuration from list
  * @hw: pointer to the hardware structure
@@ -1966,15 +2011,16 @@ int ice_rem_vsi_rss_cfg(struct ice_hw *hw, u16 vsi_handle)
 static void
 ice_rem_rss_list(struct ice_hw *hw, u16 vsi_handle, struct ice_flow_prof *prof)
 {
+	enum ice_rss_cfg_hdr_type hdr_type;
 	struct ice_rss_cfg *r, *tmp;
 
 	/* Search for RSS hash fields associated to the VSI that match the
 	 * hash configurations associated to the flow profile. If found
 	 * remove from the RSS entry list of the VSI context and delete entry.
 	 */
+	hdr_type = ice_get_rss_hdr_type(prof);
 	list_for_each_entry_safe(r, tmp, &hw->rss_list_head, l_entry)
-		if (r->hashed_flds == prof->segs[prof->segs_cnt - 1].match &&
-		    r->packet_hdr == prof->segs[prof->segs_cnt - 1].hdrs) {
+		if (ice_rss_match_prof(r, prof, hdr_type)) {
 			clear_bit(vsi_handle, r->vsis);
 			if (bitmap_empty(r->vsis, ICE_MAX_VSI)) {
 				list_del(&r->l_entry);
@@ -1995,11 +2041,12 @@ ice_rem_rss_list(struct ice_hw *hw, u16 vsi_handle, struct ice_flow_prof *prof)
 static int
 ice_add_rss_list(struct ice_hw *hw, u16 vsi_handle, struct ice_flow_prof *prof)
 {
+	enum ice_rss_cfg_hdr_type hdr_type;
 	struct ice_rss_cfg *r, *rss_cfg;
 
+	hdr_type = ice_get_rss_hdr_type(prof);
 	list_for_each_entry(r, &hw->rss_list_head, l_entry)
-		if (r->hashed_flds == prof->segs[prof->segs_cnt - 1].match &&
-		    r->packet_hdr == prof->segs[prof->segs_cnt - 1].hdrs) {
+		if (ice_rss_match_prof(r, prof, hdr_type)) {
 			set_bit(vsi_handle, r->vsis);
 			return 0;
 		}
@@ -2009,8 +2056,9 @@ ice_add_rss_list(struct ice_hw *hw, u16 vsi_handle, struct ice_flow_prof *prof)
 	if (!rss_cfg)
 		return -ENOMEM;
 
-	rss_cfg->hashed_flds = prof->segs[prof->segs_cnt - 1].match;
-	rss_cfg->packet_hdr = prof->segs[prof->segs_cnt - 1].hdrs;
+	rss_cfg->hash.hash_flds = prof->segs[prof->segs_cnt - 1].match;
+	rss_cfg->hash.addl_hdrs = prof->segs[prof->segs_cnt - 1].hdrs;
+	rss_cfg->hash.hdr_type = hdr_type;
 	set_bit(vsi_handle, rss_cfg->vsis);
 
 	list_add_tail(&rss_cfg->l_entry, &hw->rss_list_head);
@@ -2019,54 +2067,55 @@ ice_add_rss_list(struct ice_hw *hw, u16 vsi_handle, struct ice_flow_prof *prof)
 }
 
 #define ICE_FLOW_PROF_HASH_S	0
-#define ICE_FLOW_PROF_HASH_M	(0xFFFFFFFFULL << ICE_FLOW_PROF_HASH_S)
+#define ICE_FLOW_PROF_HASH_M	GENMASK_ULL(31, 0)
 #define ICE_FLOW_PROF_HDR_S	32
-#define ICE_FLOW_PROF_HDR_M	(0x3FFFFFFFULL << ICE_FLOW_PROF_HDR_S)
-#define ICE_FLOW_PROF_ENCAP_S	63
-#define ICE_FLOW_PROF_ENCAP_M	(BIT_ULL(ICE_FLOW_PROF_ENCAP_S))
-
-#define ICE_RSS_OUTER_HEADERS	1
-#define ICE_RSS_INNER_HEADERS	2
+#define ICE_FLOW_PROF_HDR_M	GENMASK_ULL(61, 32)
+#define ICE_FLOW_PROF_ENCAP_S	62
+#define ICE_FLOW_PROF_ENCAP_M	GENMASK_ULL(63, 62)
 
 /* Flow profile ID format:
  * [0:31] - Packet match fields
- * [32:62] - Protocol header
- * [63] - Encapsulation flag, 0 if non-tunneled, 1 if tunneled
+ * [32:61] - Protocol header
+ * [62:63] - Encapsulation flag:
+ *	     0 if non-tunneled
+ *	     1 if tunneled
+ *	     2 for tunneled with outer ipv4
+ *	     3 for tunneled with outer ipv6
  */
-#define ICE_FLOW_GEN_PROFID(hash, hdr, segs_cnt) \
-	((u64)(((u64)(hash) & ICE_FLOW_PROF_HASH_M) | \
+#define ICE_FLOW_GEN_PROFID(hash, hdr, encap)                                \
+	((u64)(((u64)(hash) & ICE_FLOW_PROF_HASH_M) |                        \
 	       (((u64)(hdr) << ICE_FLOW_PROF_HDR_S) & ICE_FLOW_PROF_HDR_M) | \
-	       ((u8)((segs_cnt) - 1) ? ICE_FLOW_PROF_ENCAP_M : 0)))
+	       (((u64)(encap) << ICE_FLOW_PROF_ENCAP_S) &                    \
+		ICE_FLOW_PROF_ENCAP_M)))
 
 /**
  * ice_add_rss_cfg_sync - add an RSS configuration
  * @hw: pointer to the hardware structure
  * @vsi_handle: software VSI handle
- * @hashed_flds: hash bit fields (ICE_FLOW_HASH_*) to configure
- * @addl_hdrs: protocol header fields
- * @segs_cnt: packet segment count
+ * @cfg: configure parameters
  *
  * Assumption: lock has already been acquired for RSS list
  */
 static int
-ice_add_rss_cfg_sync(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds,
-		     u32 addl_hdrs, u8 segs_cnt)
+ice_add_rss_cfg_sync(struct ice_hw *hw, u16 vsi_handle,
+		     const struct ice_rss_hash_cfg *cfg)
 {
 	const enum ice_block blk = ICE_BLK_RSS;
 	struct ice_flow_prof *prof = NULL;
 	struct ice_flow_seg_info *segs;
+	u8 segs_cnt;
 	int status;
 
-	if (!segs_cnt || segs_cnt > ICE_FLOW_SEG_MAX)
-		return -EINVAL;
+	segs_cnt = (cfg->hdr_type == ICE_RSS_OUTER_HEADERS) ?
+			   ICE_FLOW_SEG_SINGLE :
+			   ICE_FLOW_SEG_MAX;
 
 	segs = kcalloc(segs_cnt, sizeof(*segs), GFP_KERNEL);
 	if (!segs)
 		return -ENOMEM;
 
 	/* Construct the packet segment info from the hashed fields */
-	status = ice_flow_set_rss_seg_info(&segs[segs_cnt - 1], hashed_flds,
-					   addl_hdrs);
+	status = ice_flow_set_rss_seg_info(segs, segs_cnt, cfg);
 	if (status)
 		goto exit;
 
@@ -2120,9 +2169,9 @@ ice_add_rss_cfg_sync(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds,
 	 * segment information.
 	 */
 	status = ice_flow_add_prof(hw, blk, ICE_FLOW_RX,
-				   ICE_FLOW_GEN_PROFID(hashed_flds,
+				   ICE_FLOW_GEN_PROFID(cfg->hash_flds,
 						       segs[segs_cnt - 1].hdrs,
-						       segs_cnt),
+						       cfg->hdr_type),
 				   segs, segs_cnt, &prof);
 	if (status)
 		goto exit;
@@ -2147,29 +2196,37 @@ exit:
  * ice_add_rss_cfg - add an RSS configuration with specified hashed fields
  * @hw: pointer to the hardware structure
  * @vsi_handle: software VSI handle
- * @hashed_flds: hash bit fields (ICE_FLOW_HASH_*) to configure
- * @addl_hdrs: protocol header fields
+ * @cfg: configure parameters
  *
  * This function will generate a flow profile based on fields associated with
  * the input fields to hash on, the flow type and use the VSI number to add
  * a flow entry to the profile.
  */
 int
-ice_add_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds,
-		u32 addl_hdrs)
+ice_add_rss_cfg(struct ice_hw *hw, u16 vsi_handle,
+		const struct ice_rss_hash_cfg *cfg)
 {
+	struct ice_rss_hash_cfg local_cfg;
 	int status;
 
-	if (hashed_flds == ICE_HASH_INVALID ||
-	    !ice_is_vsi_valid(hw, vsi_handle))
+	if (!ice_is_vsi_valid(hw, vsi_handle) || !cfg ||
+	    cfg->hdr_type > ICE_RSS_ANY_HEADERS ||
+	    cfg->hash_flds == ICE_HASH_INVALID)
 		return -EINVAL;
 
 	mutex_lock(&hw->rss_locks);
-	status = ice_add_rss_cfg_sync(hw, vsi_handle, hashed_flds, addl_hdrs,
-				      ICE_RSS_OUTER_HEADERS);
-	if (!status)
-		status = ice_add_rss_cfg_sync(hw, vsi_handle, hashed_flds,
-					      addl_hdrs, ICE_RSS_INNER_HEADERS);
+	local_cfg = *cfg;
+	if (cfg->hdr_type < ICE_RSS_ANY_HEADERS) {
+		status = ice_add_rss_cfg_sync(hw, vsi_handle, &local_cfg);
+	} else {
+		local_cfg.hdr_type = ICE_RSS_OUTER_HEADERS;
+		status = ice_add_rss_cfg_sync(hw, vsi_handle, &local_cfg);
+		if (!status) {
+			local_cfg.hdr_type = ICE_RSS_INNER_HEADERS;
+			status = ice_add_rss_cfg_sync(hw, vsi_handle,
+						      &local_cfg);
+		}
+	}
 	mutex_unlock(&hw->rss_locks);
 
 	return status;
@@ -2179,28 +2236,29 @@ ice_add_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds,
  * ice_rem_rss_cfg_sync - remove an existing RSS configuration
  * @hw: pointer to the hardware structure
  * @vsi_handle: software VSI handle
- * @hashed_flds: Packet hash types (ICE_FLOW_HASH_*) to remove
- * @addl_hdrs: Protocol header fields within a packet segment
- * @segs_cnt: packet segment count
+ * @cfg: configure parameters
  *
  * Assumption: lock has already been acquired for RSS list
  */
 static int
-ice_rem_rss_cfg_sync(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds,
-		     u32 addl_hdrs, u8 segs_cnt)
+ice_rem_rss_cfg_sync(struct ice_hw *hw, u16 vsi_handle,
+		     const struct ice_rss_hash_cfg *cfg)
 {
 	const enum ice_block blk = ICE_BLK_RSS;
 	struct ice_flow_seg_info *segs;
 	struct ice_flow_prof *prof;
+	u8 segs_cnt;
 	int status;
 
+	segs_cnt = (cfg->hdr_type == ICE_RSS_OUTER_HEADERS) ?
+			   ICE_FLOW_SEG_SINGLE :
+			   ICE_FLOW_SEG_MAX;
 	segs = kcalloc(segs_cnt, sizeof(*segs), GFP_KERNEL);
 	if (!segs)
 		return -ENOMEM;
 
 	/* Construct the packet segment info from the hashed fields */
-	status = ice_flow_set_rss_seg_info(&segs[segs_cnt - 1], hashed_flds,
-					   addl_hdrs);
+	status = ice_flow_set_rss_seg_info(segs, segs_cnt, cfg);
 	if (status)
 		goto out;
 
@@ -2233,31 +2291,39 @@ out:
  * ice_rem_rss_cfg - remove an existing RSS config with matching hashed fields
  * @hw: pointer to the hardware structure
  * @vsi_handle: software VSI handle
- * @hashed_flds: Packet hash types (ICE_FLOW_HASH_*) to remove
- * @addl_hdrs: Protocol header fields within a packet segment
+ * @cfg: configure parameters
  *
  * This function will lookup the flow profile based on the input
  * hash field bitmap, iterate through the profile entry list of
  * that profile and find entry associated with input VSI to be
- * removed. Calls are made to underlying flow s which will APIs
+ * removed. Calls are made to underlying flow apis which will in
  * turn build or update buffers for RSS XLT1 section.
  */
-int __maybe_unused
-ice_rem_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds,
-		u32 addl_hdrs)
+int
+ice_rem_rss_cfg(struct ice_hw *hw, u16 vsi_handle,
+		const struct ice_rss_hash_cfg *cfg)
 {
+	struct ice_rss_hash_cfg local_cfg;
 	int status;
 
-	if (hashed_flds == ICE_HASH_INVALID ||
-	    !ice_is_vsi_valid(hw, vsi_handle))
+	if (!ice_is_vsi_valid(hw, vsi_handle) || !cfg ||
+	    cfg->hdr_type > ICE_RSS_ANY_HEADERS ||
+	    cfg->hash_flds == ICE_HASH_INVALID)
 		return -EINVAL;
 
 	mutex_lock(&hw->rss_locks);
-	status = ice_rem_rss_cfg_sync(hw, vsi_handle, hashed_flds, addl_hdrs,
-				      ICE_RSS_OUTER_HEADERS);
-	if (!status)
-		status = ice_rem_rss_cfg_sync(hw, vsi_handle, hashed_flds,
-					      addl_hdrs, ICE_RSS_INNER_HEADERS);
+	local_cfg = *cfg;
+	if (cfg->hdr_type < ICE_RSS_ANY_HEADERS) {
+		status = ice_rem_rss_cfg_sync(hw, vsi_handle, &local_cfg);
+	} else {
+		local_cfg.hdr_type = ICE_RSS_OUTER_HEADERS;
+		status = ice_rem_rss_cfg_sync(hw, vsi_handle, &local_cfg);
+		if (!status) {
+			local_cfg.hdr_type = ICE_RSS_INNER_HEADERS;
+			status = ice_rem_rss_cfg_sync(hw, vsi_handle,
+						      &local_cfg);
+		}
+	}
 	mutex_unlock(&hw->rss_locks);
 
 	return status;
@@ -2307,6 +2373,7 @@ ice_rem_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds,
  */
 int ice_add_avf_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 avf_hash)
 {
+	struct ice_rss_hash_cfg hcfg;
 	int status = 0;
 	u64 hash_flds;
 
@@ -2379,8 +2446,10 @@ int ice_add_avf_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 avf_hash)
 		if (rss_hash == ICE_HASH_INVALID)
 			return -EIO;
 
-		status = ice_add_rss_cfg(hw, vsi_handle, rss_hash,
-					 ICE_FLOW_SEG_HDR_NONE);
+		hcfg.addl_hdrs = ICE_FLOW_SEG_HDR_NONE;
+		hcfg.hash_flds = rss_hash;
+		hcfg.hdr_type = ICE_RSS_ANY_HEADERS;
+		status = ice_add_rss_cfg(hw, vsi_handle, &hcfg);
 		if (status)
 			break;
 	}
@@ -2404,16 +2473,7 @@ int ice_replay_rss_cfg(struct ice_hw *hw, u16 vsi_handle)
 	mutex_lock(&hw->rss_locks);
 	list_for_each_entry(r, &hw->rss_list_head, l_entry) {
 		if (test_bit(vsi_handle, r->vsis)) {
-			status = ice_add_rss_cfg_sync(hw, vsi_handle,
-						      r->hashed_flds,
-						      r->packet_hdr,
-						      ICE_RSS_OUTER_HEADERS);
-			if (status)
-				break;
-			status = ice_add_rss_cfg_sync(hw, vsi_handle,
-						      r->hashed_flds,
-						      r->packet_hdr,
-						      ICE_RSS_INNER_HEADERS);
+			status = ice_add_rss_cfg_sync(hw, vsi_handle, &r->hash);
 			if (status)
 				break;
 		}
@@ -2444,8 +2504,8 @@ u64 ice_get_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u32 hdrs)
 	mutex_lock(&hw->rss_locks);
 	list_for_each_entry(r, &hw->rss_list_head, l_entry)
 		if (test_bit(vsi_handle, r->vsis) &&
-		    r->packet_hdr == hdrs) {
-			rss_hash = r->hashed_flds;
+		    r->hash.addl_hdrs == hdrs) {
+			rss_hash = r->hash.hash_flds;
 			break;
 		}
 	mutex_unlock(&hw->rss_locks);
diff --git a/drivers/net/ethernet/intel/ice/ice_flow.h b/drivers/net/ethernet/intel/ice/ice_flow.h
index 96923ef0a5a8..d1de84b78386 100644
--- a/drivers/net/ethernet/intel/ice/ice_flow.h
+++ b/drivers/net/ethernet/intel/ice/ice_flow.h
@@ -34,6 +34,8 @@
 #define ICE_HASH_TCP_IPV6	(ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_TCP_PORT)
 #define ICE_HASH_UDP_IPV4	(ICE_FLOW_HASH_IPV4 | ICE_FLOW_HASH_UDP_PORT)
 #define ICE_HASH_UDP_IPV6	(ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_UDP_PORT)
+#define ICE_HASH_SCTP_IPV4	(ICE_FLOW_HASH_IPV4 | ICE_FLOW_HASH_SCTP_PORT)
+#define ICE_HASH_SCTP_IPV6	(ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_SCTP_PORT)
 
 #define ICE_FLOW_HASH_GTP_TEID \
 	(BIT_ULL(ICE_FLOW_FIELD_IDX_GTPC_TEID))
@@ -279,6 +281,23 @@ enum ice_flow_avf_hdr_field {
 	BIT_ULL(ICE_AVF_FLOW_FIELD_UNICAST_IPV6_UDP) | \
 	BIT_ULL(ICE_AVF_FLOW_FIELD_MULTICAST_IPV6_UDP))
 
+enum ice_rss_cfg_hdr_type {
+	ICE_RSS_OUTER_HEADERS, /* take outer headers as inputset. */
+	ICE_RSS_INNER_HEADERS, /* take inner headers as inputset. */
+	/* take inner headers as inputset for packet with outer ipv4. */
+	ICE_RSS_INNER_HEADERS_W_OUTER_IPV4,
+	/* take inner headers as inputset for packet with outer ipv6. */
+	ICE_RSS_INNER_HEADERS_W_OUTER_IPV6,
+	/* take outer headers first then inner headers as inputset */
+	ICE_RSS_ANY_HEADERS
+};
+
+struct ice_rss_hash_cfg {
+	u32 addl_hdrs; /* protocol header fields */
+	u64 hash_flds; /* hash bit field (ICE_FLOW_HASH_*) to configure */
+	enum ice_rss_cfg_hdr_type hdr_type; /* to specify inner or outer */
+};
+
 enum ice_flow_dir {
 	ICE_FLOW_RX		= 0x02,
 };
@@ -289,6 +308,7 @@ enum ice_flow_priority {
 	ICE_FLOW_PRIO_HIGH
 };
 
+#define ICE_FLOW_SEG_SINGLE		1
 #define ICE_FLOW_SEG_MAX		2
 #define ICE_FLOW_SEG_RAW_FLD_MAX	2
 #define ICE_FLOW_FV_EXTRACT_SZ		2
@@ -378,8 +398,7 @@ struct ice_rss_cfg {
 	struct list_head l_entry;
 	/* bitmap of VSIs added to the RSS entry */
 	DECLARE_BITMAP(vsis, ICE_MAX_VSI);
-	u64 hashed_flds;
-	u32 packet_hdr;
+	struct ice_rss_hash_cfg hash;
 };
 
 int
@@ -403,11 +422,9 @@ void ice_rem_vsi_rss_list(struct ice_hw *hw, u16 vsi_handle);
 int ice_replay_rss_cfg(struct ice_hw *hw, u16 vsi_handle);
 int ice_add_avf_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds);
 int ice_rem_vsi_rss_cfg(struct ice_hw *hw, u16 vsi_handle);
-int
-ice_add_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds,
-		u32 addl_hdrs);
-int
-ice_rem_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds,
-		u32 addl_hdrs);
+int ice_add_rss_cfg(struct ice_hw *hw, u16 vsi_handle,
+		    const struct ice_rss_hash_cfg *cfg);
+int ice_rem_rss_cfg(struct ice_hw *hw, u16 vsi_handle,
+		    const struct ice_rss_hash_cfg *cfg);
 u64 ice_get_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u32 hdrs);
 #endif /* _ICE_FLOW_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index bb6151e798e4..b22f1b861831 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -1611,6 +1611,38 @@ static void ice_vsi_set_vf_rss_flow_fld(struct ice_vsi *vsi)
 			vsi->vsi_num, status);
 }
 
+static const struct ice_rss_hash_cfg default_rss_cfgs[] = {
+	/* configure RSS for IPv4 with input set IP src/dst */
+	{ICE_FLOW_SEG_HDR_IPV4, ICE_FLOW_HASH_IPV4, ICE_RSS_ANY_HEADERS},
+	/* configure RSS for IPv6 with input set IPv6 src/dst */
+	{ICE_FLOW_SEG_HDR_IPV6, ICE_FLOW_HASH_IPV6, ICE_RSS_ANY_HEADERS},
+	/* configure RSS for tcp4 with input set IP src/dst, TCP src/dst */
+	{ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_IPV4,
+				ICE_HASH_TCP_IPV4,  ICE_RSS_ANY_HEADERS},
+	/* configure RSS for udp4 with input set IP src/dst, UDP src/dst */
+	{ICE_FLOW_SEG_HDR_UDP | ICE_FLOW_SEG_HDR_IPV4,
+				ICE_HASH_UDP_IPV4,  ICE_RSS_ANY_HEADERS},
+	/* configure RSS for sctp4 with input set IP src/dst - only support
+	 * RSS on SCTPv4 on outer headers (non-tunneled)
+	 */
+	{ICE_FLOW_SEG_HDR_SCTP | ICE_FLOW_SEG_HDR_IPV4,
+		ICE_HASH_SCTP_IPV4, ICE_RSS_OUTER_HEADERS},
+	/* configure RSS for tcp6 with input set IPv6 src/dst, TCP src/dst */
+	{ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_IPV6,
+				ICE_HASH_TCP_IPV6,  ICE_RSS_ANY_HEADERS},
+	/* configure RSS for udp6 with input set IPv6 src/dst, UDP src/dst */
+	{ICE_FLOW_SEG_HDR_UDP | ICE_FLOW_SEG_HDR_IPV6,
+				ICE_HASH_UDP_IPV6,  ICE_RSS_ANY_HEADERS},
+	/* configure RSS for sctp6 with input set IPv6 src/dst - only support
+	 * RSS on SCTPv6 on outer headers (non-tunneled)
+	 */
+	{ICE_FLOW_SEG_HDR_SCTP | ICE_FLOW_SEG_HDR_IPV6,
+		ICE_HASH_SCTP_IPV6, ICE_RSS_OUTER_HEADERS},
+	/* configure RSS for IPSEC ESP SPI with input set MAC_IPV4_SPI */
+	{ICE_FLOW_SEG_HDR_ESP,
+		ICE_FLOW_HASH_ESP_SPI, ICE_RSS_OUTER_HEADERS},
+};
+
 /**
  * ice_vsi_set_rss_flow_fld - Sets RSS input set for different flows
  * @vsi: VSI to be configured
@@ -1629,6 +1661,7 @@ static void ice_vsi_set_rss_flow_fld(struct ice_vsi *vsi)
 	struct ice_hw *hw = &pf->hw;
 	struct device *dev;
 	int status;
+	u32 i;
 
 	dev = ice_pf_to_dev(pf);
 	if (ice_is_safe_mode(pf)) {
@@ -1636,67 +1669,14 @@ static void ice_vsi_set_rss_flow_fld(struct ice_vsi *vsi)
 			vsi_num);
 		return;
 	}
-	/* configure RSS for IPv4 with input set IP src/dst */
-	status = ice_add_rss_cfg(hw, vsi_handle, ICE_FLOW_HASH_IPV4,
-				 ICE_FLOW_SEG_HDR_IPV4);
-	if (status)
-		dev_dbg(dev, "ice_add_rss_cfg failed for ipv4 flow, vsi = %d, error = %d\n",
-			vsi_num, status);
-
-	/* configure RSS for IPv6 with input set IPv6 src/dst */
-	status = ice_add_rss_cfg(hw, vsi_handle, ICE_FLOW_HASH_IPV6,
-				 ICE_FLOW_SEG_HDR_IPV6);
-	if (status)
-		dev_dbg(dev, "ice_add_rss_cfg failed for ipv6 flow, vsi = %d, error = %d\n",
-			vsi_num, status);
-
-	/* configure RSS for tcp4 with input set IP src/dst, TCP src/dst */
-	status = ice_add_rss_cfg(hw, vsi_handle, ICE_HASH_TCP_IPV4,
-				 ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_IPV4);
-	if (status)
-		dev_dbg(dev, "ice_add_rss_cfg failed for tcp4 flow, vsi = %d, error = %d\n",
-			vsi_num, status);
+	for (i = 0; i < ARRAY_SIZE(default_rss_cfgs); i++) {
+		const struct ice_rss_hash_cfg *cfg = &default_rss_cfgs[i];
 
-	/* configure RSS for udp4 with input set IP src/dst, UDP src/dst */
-	status = ice_add_rss_cfg(hw, vsi_handle, ICE_HASH_UDP_IPV4,
-				 ICE_FLOW_SEG_HDR_UDP | ICE_FLOW_SEG_HDR_IPV4);
-	if (status)
-		dev_dbg(dev, "ice_add_rss_cfg failed for udp4 flow, vsi = %d, error = %d\n",
-			vsi_num, status);
-
-	/* configure RSS for sctp4 with input set IP src/dst */
-	status = ice_add_rss_cfg(hw, vsi_handle, ICE_FLOW_HASH_IPV4,
-				 ICE_FLOW_SEG_HDR_SCTP | ICE_FLOW_SEG_HDR_IPV4);
-	if (status)
-		dev_dbg(dev, "ice_add_rss_cfg failed for sctp4 flow, vsi = %d, error = %d\n",
-			vsi_num, status);
-
-	/* configure RSS for tcp6 with input set IPv6 src/dst, TCP src/dst */
-	status = ice_add_rss_cfg(hw, vsi_handle, ICE_HASH_TCP_IPV6,
-				 ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_IPV6);
-	if (status)
-		dev_dbg(dev, "ice_add_rss_cfg failed for tcp6 flow, vsi = %d, error = %d\n",
-			vsi_num, status);
-
-	/* configure RSS for udp6 with input set IPv6 src/dst, UDP src/dst */
-	status = ice_add_rss_cfg(hw, vsi_handle, ICE_HASH_UDP_IPV6,
-				 ICE_FLOW_SEG_HDR_UDP | ICE_FLOW_SEG_HDR_IPV6);
-	if (status)
-		dev_dbg(dev, "ice_add_rss_cfg failed for udp6 flow, vsi = %d, error = %d\n",
-			vsi_num, status);
-
-	/* configure RSS for sctp6 with input set IPv6 src/dst */
-	status = ice_add_rss_cfg(hw, vsi_handle, ICE_FLOW_HASH_IPV6,
-				 ICE_FLOW_SEG_HDR_SCTP | ICE_FLOW_SEG_HDR_IPV6);
-	if (status)
-		dev_dbg(dev, "ice_add_rss_cfg failed for sctp6 flow, vsi = %d, error = %d\n",
-			vsi_num, status);
-
-	status = ice_add_rss_cfg(hw, vsi_handle, ICE_FLOW_HASH_ESP_SPI,
-				 ICE_FLOW_SEG_HDR_ESP);
-	if (status)
-		dev_dbg(dev, "ice_add_rss_cfg failed for esp/spi flow, vsi = %d, error = %d\n",
-			vsi_num, status);
+		status = ice_add_rss_cfg(hw, vsi_handle, cfg);
+		if (status)
+			dev_dbg(dev, "ice_add_rss_cfg failed, addl_hdrs = %x, hash_flds = %llx, hdr_type = %d\n",
+				cfg->addl_hdrs, cfg->hash_flds, cfg->hdr_type);
+	}
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
index 8872f7a4f432..0e7b5984a7c7 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
@@ -689,9 +689,7 @@ out:
  * a specific virtchnl RSS cfg
  * @hw: pointer to the hardware
  * @rss_cfg: pointer to the virtchnl RSS cfg
- * @addl_hdrs: pointer to the protocol header fields (ICE_FLOW_SEG_HDR_*)
- * to configure
- * @hash_flds: pointer to the hash bit fields (ICE_FLOW_HASH_*) to configure
+ * @hash_cfg: pointer to the HW hash configuration
  *
  * Return true if all the protocol header and hash fields in the RSS cfg could
  * be parsed, else return false
@@ -699,13 +697,18 @@ out:
  * This function parses the virtchnl RSS cfg to be the intended
  * hash fields and the intended header for RSS configuration
  */
-static bool
-ice_vc_parse_rss_cfg(struct ice_hw *hw, struct virtchnl_rss_cfg *rss_cfg,
-		     u32 *addl_hdrs, u64 *hash_flds)
+static bool ice_vc_parse_rss_cfg(struct ice_hw *hw,
+				 struct virtchnl_rss_cfg *rss_cfg,
+				 struct ice_rss_hash_cfg *hash_cfg)
 {
 	const struct ice_vc_hash_field_match_type *hf_list;
 	const struct ice_vc_hdr_match_type *hdr_list;
 	int i, hf_list_len, hdr_list_len;
+	u32 *addl_hdrs = &hash_cfg->addl_hdrs;
+	u64 *hash_flds = &hash_cfg->hash_flds;
+
+	/* set outer layer RSS as default */
+	hash_cfg->hdr_type = ICE_RSS_OUTER_HEADERS;
 
 	hf_list = ice_vc_hash_field_list;
 	hf_list_len = ARRAY_SIZE(ice_vc_hash_field_list);
@@ -856,18 +859,24 @@ static int ice_vc_handle_rss_cfg(struct ice_vf *vf, u8 *msg, bool add)
 
 		kfree(ctx);
 	} else {
-		u32 addl_hdrs = ICE_FLOW_SEG_HDR_NONE;
-		u64 hash_flds = ICE_HASH_INVALID;
+		struct ice_rss_hash_cfg cfg;
+
+		/* Only check for none raw pattern case */
+		if (!ice_vc_validate_pattern(vf, &rss_cfg->proto_hdrs)) {
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+			goto error_param;
+		}
+		cfg.addl_hdrs = ICE_FLOW_SEG_HDR_NONE;
+		cfg.hash_flds = ICE_HASH_INVALID;
+		cfg.hdr_type = ICE_RSS_ANY_HEADERS;
 
-		if (!ice_vc_parse_rss_cfg(hw, rss_cfg, &addl_hdrs,
-					  &hash_flds)) {
+		if (!ice_vc_parse_rss_cfg(hw, rss_cfg, &cfg)) {
 			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 			goto error_param;
 		}
 
 		if (add) {
-			if (ice_add_rss_cfg(hw, vsi->idx, hash_flds,
-					    addl_hdrs)) {
+			if (ice_add_rss_cfg(hw, vsi->idx, &cfg)) {
 				v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 				dev_err(dev, "ice_add_rss_cfg failed for vsi = %d, v_ret = %d\n",
 					vsi->vsi_num, v_ret);
@@ -875,8 +884,7 @@ static int ice_vc_handle_rss_cfg(struct ice_vf *vf, u8 *msg, bool add)
 		} else {
 			int status;
 
-			status = ice_rem_rss_cfg(hw, vsi->idx, hash_flds,
-						 addl_hdrs);
+			status = ice_rem_rss_cfg(hw, vsi->idx, &cfg);
 			/* We just ignore -ENOENT, because if two configurations
 			 * share the same profile remove one of them actually
 			 * removes both, since the profile is deleted.
diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h
index 6b3acf15be5c..b0e060cc79ac 100644
--- a/include/linux/avf/virtchnl.h
+++ b/include/linux/avf/virtchnl.h
@@ -911,6 +911,14 @@ struct virtchnl_rss_hena {
 
 VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_rss_hena);
 
+/* Type of RSS algorithm */
+enum virtchnl_rss_algorithm {
+	VIRTCHNL_RSS_ALG_TOEPLITZ_ASYMMETRIC	= 0,
+	VIRTCHNL_RSS_ALG_R_ASYMMETRIC		= 1,
+	VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC	= 2,
+	VIRTCHNL_RSS_ALG_XOR_SYMMETRIC		= 3,
+};
+
 /* VIRTCHNL_OP_ENABLE_CHANNELS
  * VIRTCHNL_OP_DISABLE_CHANNELS
  * VF sends these messages to enable or disable channels based on
@@ -1095,14 +1103,6 @@ enum virtchnl_vfr_states {
 	VIRTCHNL_VFR_VFACTIVE,
 };
 
-/* Type of RSS algorithm */
-enum virtchnl_rss_algorithm {
-	VIRTCHNL_RSS_ALG_TOEPLITZ_ASYMMETRIC	= 0,
-	VIRTCHNL_RSS_ALG_R_ASYMMETRIC		= 1,
-	VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC	= 2,
-	VIRTCHNL_RSS_ALG_XOR_SYMMETRIC		= 3,
-};
-
 #define VIRTCHNL_MAX_NUM_PROTO_HDRS	32
 #define PROTO_HDR_SHIFT			5
 #define PROTO_HDR_FIELD_START(proto_hdr_type) ((proto_hdr_type) << PROTO_HDR_SHIFT)
-- 
cgit v1.2.3


From 4a3de3fb0eb6897488dd510006abd9673f1fb34c Mon Sep 17 00:00:00 2001
From: Ahmed Zaki <ahmed.zaki@intel.com>
Date: Tue, 12 Dec 2023 17:33:21 -0700
Subject: iavf: enable symmetric-xor RSS for Toeplitz hash function

Allow the user to set the symmetric Toeplitz hash function via:

    # ethtool -X eth0 hfunc toeplitz symmetric-xor

The driver will reject any new RSS configuration if a field other than
(IP src/dst and L4 src/dst ports) is requested for hashing.

The symmetric RSS will not be supported on PFs not advertising the ADV RSS
Offload flag (ADV_RSS_SUPPORT()), for example the E700 series (i40e).

Reviewed-by: Madhu Chittim <madhu.chittim@intel.com>
Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
Link: https://lore.kernel.org/r/20231213003321.605376-9-ahmed.zaki@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/iavf/iavf.h             |  5 ++-
 drivers/net/ethernet/intel/iavf/iavf_adv_rss.c     |  8 +++-
 drivers/net/ethernet/intel/iavf/iavf_adv_rss.h     |  3 +-
 drivers/net/ethernet/intel/iavf/iavf_ethtool.c     | 32 ++++++++++++--
 drivers/net/ethernet/intel/iavf/iavf_main.c        |  4 ++
 drivers/net/ethernet/intel/iavf/iavf_virtchnl.c    | 41 ++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_virtchnl.c      | 50 ++++++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_virtchnl.h      |  1 +
 .../ethernet/intel/ice/ice_virtchnl_allowlist.c    |  1 +
 include/linux/avf/virtchnl.h                       | 19 ++++++++
 10 files changed, 156 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h
index e7ab89dc883a..f83fbcc72075 100644
--- a/drivers/net/ethernet/intel/iavf/iavf.h
+++ b/drivers/net/ethernet/intel/iavf/iavf.h
@@ -312,7 +312,8 @@ struct iavf_adapter {
 #define IAVF_FLAG_AQ_SET_HENA			BIT_ULL(12)
 #define IAVF_FLAG_AQ_SET_RSS_KEY		BIT_ULL(13)
 #define IAVF_FLAG_AQ_SET_RSS_LUT		BIT_ULL(14)
-#define IAVF_FLAG_AQ_CONFIGURE_PROMISC_MODE	BIT_ULL(15)
+#define IAVF_FLAG_AQ_SET_RSS_HFUNC		BIT_ULL(15)
+#define IAVF_FLAG_AQ_CONFIGURE_PROMISC_MODE	BIT_ULL(16)
 #define IAVF_FLAG_AQ_ENABLE_VLAN_STRIPPING	BIT_ULL(19)
 #define IAVF_FLAG_AQ_DISABLE_VLAN_STRIPPING	BIT_ULL(20)
 #define IAVF_FLAG_AQ_ENABLE_CHANNELS		BIT_ULL(21)
@@ -414,6 +415,7 @@ struct iavf_adapter {
 	struct iavf_vsi vsi;
 	u32 aq_wait_count;
 	/* RSS stuff */
+	enum virtchnl_rss_algorithm hfunc;
 	u64 hena;
 	u16 rss_key_size;
 	u16 rss_lut_size;
@@ -539,6 +541,7 @@ void iavf_get_hena(struct iavf_adapter *adapter);
 void iavf_set_hena(struct iavf_adapter *adapter);
 void iavf_set_rss_key(struct iavf_adapter *adapter);
 void iavf_set_rss_lut(struct iavf_adapter *adapter);
+void iavf_set_rss_hfunc(struct iavf_adapter *adapter);
 void iavf_enable_vlan_stripping(struct iavf_adapter *adapter);
 void iavf_disable_vlan_stripping(struct iavf_adapter *adapter);
 void iavf_virtchnl_completion(struct iavf_adapter *adapter,
diff --git a/drivers/net/ethernet/intel/iavf/iavf_adv_rss.c b/drivers/net/ethernet/intel/iavf/iavf_adv_rss.c
index 6edbf134b73f..a9e1da35e248 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_adv_rss.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_adv_rss.c
@@ -95,17 +95,21 @@ iavf_fill_adv_rss_sctp_hdr(struct virtchnl_proto_hdr *hdr, u64 hash_flds)
  * @rss_cfg: the virtchnl message to be filled with RSS configuration setting
  * @packet_hdrs: the RSS configuration protocol header types
  * @hash_flds: the RSS configuration protocol hash fields
+ * @symm: if true, symmetric hash is required
  *
  * Returns 0 if the RSS configuration virtchnl message is filled successfully
  */
 int
 iavf_fill_adv_rss_cfg_msg(struct virtchnl_rss_cfg *rss_cfg,
-			  u32 packet_hdrs, u64 hash_flds)
+			  u32 packet_hdrs, u64 hash_flds, bool symm)
 {
 	struct virtchnl_proto_hdrs *proto_hdrs = &rss_cfg->proto_hdrs;
 	struct virtchnl_proto_hdr *hdr;
 
-	rss_cfg->rss_algorithm = VIRTCHNL_RSS_ALG_TOEPLITZ_ASYMMETRIC;
+	if (symm)
+		rss_cfg->rss_algorithm = VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC;
+	else
+		rss_cfg->rss_algorithm = VIRTCHNL_RSS_ALG_TOEPLITZ_ASYMMETRIC;
 
 	proto_hdrs->tunnel_level = 0;	/* always outer layer */
 
diff --git a/drivers/net/ethernet/intel/iavf/iavf_adv_rss.h b/drivers/net/ethernet/intel/iavf/iavf_adv_rss.h
index 4d3be11af7aa..e31eb2afebea 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_adv_rss.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_adv_rss.h
@@ -80,13 +80,14 @@ struct iavf_adv_rss {
 
 	u32 packet_hdrs;
 	u64 hash_flds;
+	bool symm;
 
 	struct virtchnl_rss_cfg cfg_msg;
 };
 
 int
 iavf_fill_adv_rss_cfg_msg(struct virtchnl_rss_cfg *rss_cfg,
-			  u32 packet_hdrs, u64 hash_flds);
+			  u32 packet_hdrs, u64 hash_flds, bool symm);
 struct iavf_adv_rss *
 iavf_find_adv_rss_cfg_by_hdrs(struct iavf_adapter *adapter, u32 packet_hdrs);
 void
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
index c376a489e4c2..f147743792fb 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
@@ -1529,11 +1529,12 @@ static u32 iavf_adv_rss_parse_hdrs(struct ethtool_rxnfc *cmd)
 /**
  * iavf_adv_rss_parse_hash_flds - parses hash fields from RSS hash input
  * @cmd: ethtool rxnfc command
+ * @symm: true if Symmetric Topelitz is set
  *
  * This function parses the rxnfc command and returns intended hash fields for
  * RSS configuration
  */
-static u64 iavf_adv_rss_parse_hash_flds(struct ethtool_rxnfc *cmd)
+static u64 iavf_adv_rss_parse_hash_flds(struct ethtool_rxnfc *cmd, bool symm)
 {
 	u64 hfld = IAVF_ADV_RSS_HASH_INVALID;
 
@@ -1605,17 +1606,20 @@ iavf_set_adv_rss_hash_opt(struct iavf_adapter *adapter,
 	struct iavf_adv_rss *rss_old, *rss_new;
 	bool rss_new_add = false;
 	int count = 50, err = 0;
+	bool symm = false;
 	u64 hash_flds;
 	u32 hdrs;
 
 	if (!ADV_RSS_SUPPORT(adapter))
 		return -EOPNOTSUPP;
 
+	symm = !!(adapter->hfunc == VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC);
+
 	hdrs = iavf_adv_rss_parse_hdrs(cmd);
 	if (hdrs == IAVF_ADV_RSS_FLOW_SEG_HDR_NONE)
 		return -EINVAL;
 
-	hash_flds = iavf_adv_rss_parse_hash_flds(cmd);
+	hash_flds = iavf_adv_rss_parse_hash_flds(cmd, symm);
 	if (hash_flds == IAVF_ADV_RSS_HASH_INVALID)
 		return -EINVAL;
 
@@ -1623,7 +1627,8 @@ iavf_set_adv_rss_hash_opt(struct iavf_adapter *adapter,
 	if (!rss_new)
 		return -ENOMEM;
 
-	if (iavf_fill_adv_rss_cfg_msg(&rss_new->cfg_msg, hdrs, hash_flds)) {
+	if (iavf_fill_adv_rss_cfg_msg(&rss_new->cfg_msg, hdrs, hash_flds,
+				      symm)) {
 		kfree(rss_new);
 		return -EINVAL;
 	}
@@ -1642,9 +1647,11 @@ iavf_set_adv_rss_hash_opt(struct iavf_adapter *adapter,
 	if (rss_old) {
 		if (rss_old->state != IAVF_ADV_RSS_ACTIVE) {
 			err = -EBUSY;
-		} else if (rss_old->hash_flds != hash_flds) {
+		} else if (rss_old->hash_flds != hash_flds ||
+			   rss_old->symm != symm) {
 			rss_old->state = IAVF_ADV_RSS_ADD_REQUEST;
 			rss_old->hash_flds = hash_flds;
+			rss_old->symm = symm;
 			memcpy(&rss_old->cfg_msg, &rss_new->cfg_msg,
 			       sizeof(rss_new->cfg_msg));
 		} else {
@@ -1655,6 +1662,7 @@ iavf_set_adv_rss_hash_opt(struct iavf_adapter *adapter,
 		rss_new->state = IAVF_ADV_RSS_ADD_REQUEST;
 		rss_new->packet_hdrs = hdrs;
 		rss_new->hash_flds = hash_flds;
+		rss_new->symm = symm;
 		list_add_tail(&rss_new->list, &adapter->adv_rss_list_head);
 	}
 	spin_unlock_bh(&adapter->adv_rss_lock);
@@ -1905,6 +1913,9 @@ static int iavf_get_rxfh(struct net_device *netdev,
 	u16 i;
 
 	rxfh->hfunc = ETH_RSS_HASH_TOP;
+	if (adapter->hfunc == VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC)
+		rxfh->input_xfrm |= RXH_XFRM_SYM_XOR;
+
 	if (rxfh->key)
 		memcpy(rxfh->key, adapter->rss_key, adapter->rss_key_size);
 
@@ -1937,6 +1948,18 @@ static int iavf_set_rxfh(struct net_device *netdev,
 	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
+	if ((rxfh->input_xfrm & RXH_XFRM_SYM_XOR) &&
+	    adapter->hfunc != VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC) {
+		if (!ADV_RSS_SUPPORT(adapter))
+			return -EOPNOTSUPP;
+		adapter->hfunc = VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC;
+		adapter->aq_required |= IAVF_FLAG_AQ_SET_RSS_HFUNC;
+	} else if (!(rxfh->input_xfrm & RXH_XFRM_SYM_XOR) &&
+		    adapter->hfunc != VIRTCHNL_RSS_ALG_TOEPLITZ_ASYMMETRIC) {
+		adapter->hfunc = VIRTCHNL_RSS_ALG_TOEPLITZ_ASYMMETRIC;
+		adapter->aq_required |= IAVF_FLAG_AQ_SET_RSS_HFUNC;
+	}
+
 	if (!rxfh->key && !rxfh->indir)
 		return 0;
 
@@ -1955,6 +1978,7 @@ static int iavf_set_rxfh(struct net_device *netdev,
 static const struct ethtool_ops iavf_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE,
+	.cap_rss_sym_xor_supported = true,
 	.get_drvinfo		= iavf_get_drvinfo,
 	.get_link		= ethtool_op_get_link,
 	.get_ringparam		= iavf_get_ringparam,
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 06a87030c163..0b3b33acf1bd 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -2166,6 +2166,10 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter)
 		iavf_set_rss_lut(adapter);
 		return 0;
 	}
+	if (adapter->aq_required & IAVF_FLAG_AQ_SET_RSS_HFUNC) {
+		iavf_set_rss_hfunc(adapter);
+		return 0;
+	}
 
 	if (adapter->aq_required & IAVF_FLAG_AQ_CONFIGURE_PROMISC_MODE) {
 		iavf_set_promiscuous(adapter);
diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index 64c4443dbef9..64a351e70a56 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -1141,6 +1141,34 @@ void iavf_set_rss_lut(struct iavf_adapter *adapter)
 	kfree(vrl);
 }
 
+/**
+ * iavf_set_rss_hfunc
+ * @adapter: adapter structure
+ *
+ * Request the PF to set our RSS Hash function
+ **/
+void iavf_set_rss_hfunc(struct iavf_adapter *adapter)
+{
+	struct virtchnl_rss_hfunc *vrh;
+	int len = sizeof(*vrh);
+
+	if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
+		/* bail because we already have a command pending */
+		dev_err(&adapter->pdev->dev, "Cannot set RSS Hash function, command %d pending\n",
+			adapter->current_op);
+		return;
+	}
+	vrh = kzalloc(len, GFP_KERNEL);
+	if (!vrh)
+		return;
+	vrh->vsi_id = adapter->vsi.id;
+	vrh->rss_algorithm = adapter->hfunc;
+	adapter->current_op = VIRTCHNL_OP_CONFIG_RSS_HFUNC;
+	adapter->aq_required &= ~IAVF_FLAG_AQ_SET_RSS_HFUNC;
+	iavf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_RSS_HFUNC, (u8 *)vrh, len);
+	kfree(vrh);
+}
+
 /**
  * iavf_enable_vlan_stripping
  * @adapter: adapter structure
@@ -2142,6 +2170,19 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 			dev_warn(&adapter->pdev->dev, "Failed to add VLAN filter, error %s\n",
 				 iavf_stat_str(&adapter->hw, v_retval));
 			break;
+		case VIRTCHNL_OP_CONFIG_RSS_HFUNC:
+			dev_warn(&adapter->pdev->dev, "Failed to configure hash function, error %s\n",
+				 iavf_stat_str(&adapter->hw, v_retval));
+
+			if (adapter->hfunc ==
+					VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC)
+				adapter->hfunc =
+					VIRTCHNL_RSS_ALG_TOEPLITZ_ASYMMETRIC;
+			else
+				adapter->hfunc =
+					VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC;
+
+			break;
 		default:
 			dev_err(&adapter->pdev->dev, "PF returned error %d (%s) to our request %d\n",
 				v_retval, iavf_stat_str(&adapter->hw, v_retval),
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
index 482f8e8b1951..d4ad0739b57b 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
@@ -999,6 +999,51 @@ error_param:
 				     NULL, 0);
 }
 
+/**
+ * ice_vc_config_rss_hfunc
+ * @vf: pointer to the VF info
+ * @msg: pointer to the msg buffer
+ *
+ * Configure the VF's RSS Hash function
+ */
+static int ice_vc_config_rss_hfunc(struct ice_vf *vf, u8 *msg)
+{
+	struct virtchnl_rss_hfunc *vrh = (struct virtchnl_rss_hfunc *)msg;
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+	u8 hfunc = ICE_AQ_VSI_Q_OPT_RSS_HASH_TPLZ;
+	struct ice_vsi *vsi;
+
+	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	if (!ice_vc_isvalid_vsi_id(vf, vrh->vsi_id)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	vsi = ice_get_vf_vsi(vf);
+	if (!vsi) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	if (vrh->rss_algorithm == VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC)
+		hfunc = ICE_AQ_VSI_Q_OPT_RSS_HASH_SYM_TPLZ;
+
+	if (ice_set_rss_hfunc(vsi, hfunc))
+		v_ret = VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR;
+error_param:
+	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_RSS_HFUNC, v_ret,
+				     NULL, 0);
+}
+
 /**
  * ice_vc_cfg_promiscuous_mode_msg
  * @vf: pointer to the VF info
@@ -3766,6 +3811,7 @@ static const struct ice_virtchnl_ops ice_virtchnl_dflt_ops = {
 	.cfg_irq_map_msg = ice_vc_cfg_irq_map_msg,
 	.config_rss_key = ice_vc_config_rss_key,
 	.config_rss_lut = ice_vc_config_rss_lut,
+	.config_rss_hfunc = ice_vc_config_rss_hfunc,
 	.get_stats_msg = ice_vc_get_stats_msg,
 	.cfg_promiscuous_mode_msg = ice_vc_cfg_promiscuous_mode_msg,
 	.add_vlan_msg = ice_vc_add_vlan_msg,
@@ -3895,6 +3941,7 @@ static const struct ice_virtchnl_ops ice_virtchnl_repr_ops = {
 	.cfg_irq_map_msg = ice_vc_cfg_irq_map_msg,
 	.config_rss_key = ice_vc_config_rss_key,
 	.config_rss_lut = ice_vc_config_rss_lut,
+	.config_rss_hfunc = ice_vc_config_rss_hfunc,
 	.get_stats_msg = ice_vc_get_stats_msg,
 	.cfg_promiscuous_mode_msg = ice_vc_repr_cfg_promiscuous_mode,
 	.add_vlan_msg = ice_vc_add_vlan_msg,
@@ -4077,6 +4124,9 @@ error_handler:
 	case VIRTCHNL_OP_CONFIG_RSS_LUT:
 		err = ops->config_rss_lut(vf, msg);
 		break;
+	case VIRTCHNL_OP_CONFIG_RSS_HFUNC:
+		err = ops->config_rss_hfunc(vf, msg);
+		break;
 	case VIRTCHNL_OP_GET_STATS:
 		err = ops->get_stats_msg(vf, msg);
 		break;
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.h b/drivers/net/ethernet/intel/ice/ice_virtchnl.h
index cd747718de73..60dfbe05980a 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.h
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.h
@@ -32,6 +32,7 @@ struct ice_virtchnl_ops {
 	int (*cfg_irq_map_msg)(struct ice_vf *vf, u8 *msg);
 	int (*config_rss_key)(struct ice_vf *vf, u8 *msg);
 	int (*config_rss_lut)(struct ice_vf *vf, u8 *msg);
+	int (*config_rss_hfunc)(struct ice_vf *vf, u8 *msg);
 	int (*get_stats_msg)(struct ice_vf *vf, u8 *msg);
 	int (*cfg_promiscuous_mode_msg)(struct ice_vf *vf, u8 *msg);
 	int (*add_vlan_msg)(struct ice_vf *vf, u8 *msg);
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c
index 7d547fa616fa..5e19d48a05b4 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c
@@ -68,6 +68,7 @@ static const u32 vlan_v2_allowlist_opcodes[] = {
 static const u32 rss_pf_allowlist_opcodes[] = {
 	VIRTCHNL_OP_CONFIG_RSS_KEY, VIRTCHNL_OP_CONFIG_RSS_LUT,
 	VIRTCHNL_OP_GET_RSS_HENA_CAPS, VIRTCHNL_OP_SET_RSS_HENA,
+	VIRTCHNL_OP_CONFIG_RSS_HFUNC,
 };
 
 /* VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC */
diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h
index b0e060cc79ac..a44d9dc7e3eb 100644
--- a/include/linux/avf/virtchnl.h
+++ b/include/linux/avf/virtchnl.h
@@ -118,6 +118,7 @@ enum virtchnl_ops {
 	VIRTCHNL_OP_GET_STATS = 15,
 	VIRTCHNL_OP_RSVD = 16,
 	VIRTCHNL_OP_EVENT = 17, /* must ALWAYS be 17 */
+	VIRTCHNL_OP_CONFIG_RSS_HFUNC = 18,
 	/* opcode 19 is reserved */
 	VIRTCHNL_OP_IWARP = 20, /* advanced opcode */
 	VIRTCHNL_OP_RDMA = VIRTCHNL_OP_IWARP,
@@ -919,6 +920,21 @@ enum virtchnl_rss_algorithm {
 	VIRTCHNL_RSS_ALG_XOR_SYMMETRIC		= 3,
 };
 
+/* VIRTCHNL_OP_CONFIG_RSS_HFUNC
+ * VF sends this message to configure the RSS hash function. Only supported
+ * if both PF and VF drivers set the VIRTCHNL_VF_OFFLOAD_RSS_PF bit during
+ * configuration negotiation.
+ * The hash function is initialized to VIRTCHNL_RSS_ALG_TOEPLITZ_ASYMMETRIC
+ * by the PF.
+ */
+struct virtchnl_rss_hfunc {
+	u16 vsi_id;
+	u16 rss_algorithm; /* enum virtchnl_rss_algorithm */
+	u32 reserved;
+};
+
+VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_rss_hfunc);
+
 /* VIRTCHNL_OP_ENABLE_CHANNELS
  * VIRTCHNL_OP_DISABLE_CHANNELS
  * VF sends these messages to enable or disable channels based on
@@ -1542,6 +1558,9 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode,
 							 vrl->lut_entries);
 		}
 		break;
+	case VIRTCHNL_OP_CONFIG_RSS_HFUNC:
+		valid_len = sizeof(struct virtchnl_rss_hfunc);
+		break;
 	case VIRTCHNL_OP_GET_RSS_HENA_CAPS:
 		break;
 	case VIRTCHNL_OP_SET_RSS_HENA:
-- 
cgit v1.2.3


From 62210a26cd4f8ad52683a71c0226dfe85de1144d Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Wed, 18 Oct 2023 17:58:12 +0530
Subject: bus: mhi: ep: Use slab allocator where applicable

Use slab allocator for allocating the memory for objects used frequently
and are of fixed size. This reduces the overheard associated with
kmalloc().

Suggested-by: Alex Elder <elder@linaro.org>
Link: https://lore.kernel.org/r/20231018122812.47261-1-manivannan.sadhasivam@linaro.org
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/bus/mhi/ep/main.c | 66 +++++++++++++++++++++++++++++++++++------------
 include/linux/mhi_ep.h    |  3 +++
 2 files changed, 52 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/drivers/bus/mhi/ep/main.c b/drivers/bus/mhi/ep/main.c
index e2513f5f47a6..517279600645 100644
--- a/drivers/bus/mhi/ep/main.c
+++ b/drivers/bus/mhi/ep/main.c
@@ -74,7 +74,7 @@ static int mhi_ep_send_completion_event(struct mhi_ep_cntrl *mhi_cntrl, struct m
 	struct mhi_ring_element *event;
 	int ret;
 
-	event = kzalloc(sizeof(struct mhi_ring_element), GFP_KERNEL);
+	event = kmem_cache_zalloc(mhi_cntrl->ev_ring_el_cache, GFP_KERNEL | GFP_DMA);
 	if (!event)
 		return -ENOMEM;
 
@@ -83,7 +83,7 @@ static int mhi_ep_send_completion_event(struct mhi_ep_cntrl *mhi_cntrl, struct m
 	event->dword[1] = MHI_TRE_EV_DWORD1(ring->ch_id, MHI_PKT_TYPE_TX_EVENT);
 
 	ret = mhi_ep_send_event(mhi_cntrl, ring->er_index, event, MHI_TRE_DATA_GET_BEI(tre));
-	kfree(event);
+	kmem_cache_free(mhi_cntrl->ev_ring_el_cache, event);
 
 	return ret;
 }
@@ -93,7 +93,7 @@ int mhi_ep_send_state_change_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_stat
 	struct mhi_ring_element *event;
 	int ret;
 
-	event = kzalloc(sizeof(struct mhi_ring_element), GFP_KERNEL);
+	event = kmem_cache_zalloc(mhi_cntrl->ev_ring_el_cache, GFP_KERNEL | GFP_DMA);
 	if (!event)
 		return -ENOMEM;
 
@@ -101,7 +101,7 @@ int mhi_ep_send_state_change_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_stat
 	event->dword[1] = MHI_SC_EV_DWORD1(MHI_PKT_TYPE_STATE_CHANGE_EVENT);
 
 	ret = mhi_ep_send_event(mhi_cntrl, 0, event, 0);
-	kfree(event);
+	kmem_cache_free(mhi_cntrl->ev_ring_el_cache, event);
 
 	return ret;
 }
@@ -111,7 +111,7 @@ int mhi_ep_send_ee_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_ee_type exec_e
 	struct mhi_ring_element *event;
 	int ret;
 
-	event = kzalloc(sizeof(struct mhi_ring_element), GFP_KERNEL);
+	event = kmem_cache_zalloc(mhi_cntrl->ev_ring_el_cache, GFP_KERNEL | GFP_DMA);
 	if (!event)
 		return -ENOMEM;
 
@@ -119,7 +119,7 @@ int mhi_ep_send_ee_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_ee_type exec_e
 	event->dword[1] = MHI_SC_EV_DWORD1(MHI_PKT_TYPE_EE_EVENT);
 
 	ret = mhi_ep_send_event(mhi_cntrl, 0, event, 0);
-	kfree(event);
+	kmem_cache_free(mhi_cntrl->ev_ring_el_cache, event);
 
 	return ret;
 }
@@ -130,7 +130,7 @@ static int mhi_ep_send_cmd_comp_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_e
 	struct mhi_ring_element *event;
 	int ret;
 
-	event = kzalloc(sizeof(struct mhi_ring_element), GFP_KERNEL);
+	event = kmem_cache_zalloc(mhi_cntrl->ev_ring_el_cache, GFP_KERNEL | GFP_DMA);
 	if (!event)
 		return -ENOMEM;
 
@@ -139,7 +139,7 @@ static int mhi_ep_send_cmd_comp_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_e
 	event->dword[1] = MHI_CC_EV_DWORD1(MHI_PKT_TYPE_CMD_COMPLETION_EVENT);
 
 	ret = mhi_ep_send_event(mhi_cntrl, 0, event, 0);
-	kfree(event);
+	kmem_cache_free(mhi_cntrl->ev_ring_el_cache, event);
 
 	return ret;
 }
@@ -451,7 +451,7 @@ static int mhi_ep_process_ch_ring(struct mhi_ep_ring *ring, struct mhi_ring_elem
 		mhi_chan->xfer_cb(mhi_chan->mhi_dev, &result);
 	} else {
 		/* UL channel */
-		result.buf_addr = kzalloc(len, GFP_KERNEL);
+		result.buf_addr = kmem_cache_zalloc(mhi_cntrl->tre_buf_cache, GFP_KERNEL | GFP_DMA);
 		if (!result.buf_addr)
 			return -ENOMEM;
 
@@ -459,7 +459,7 @@ static int mhi_ep_process_ch_ring(struct mhi_ep_ring *ring, struct mhi_ring_elem
 			ret = mhi_ep_read_channel(mhi_cntrl, ring, &result, len);
 			if (ret < 0) {
 				dev_err(&mhi_chan->mhi_dev->dev, "Failed to read channel\n");
-				kfree(result.buf_addr);
+				kmem_cache_free(mhi_cntrl->tre_buf_cache, result.buf_addr);
 				return ret;
 			}
 
@@ -471,7 +471,7 @@ static int mhi_ep_process_ch_ring(struct mhi_ep_ring *ring, struct mhi_ring_elem
 			/* Read until the ring becomes empty */
 		} while (!mhi_ep_queue_is_empty(mhi_chan->mhi_dev, DMA_TO_DEVICE));
 
-		kfree(result.buf_addr);
+		kmem_cache_free(mhi_cntrl->tre_buf_cache, result.buf_addr);
 	}
 
 	return 0;
@@ -780,14 +780,14 @@ static void mhi_ep_ch_ring_worker(struct work_struct *work)
 		if (ret) {
 			dev_err(dev, "Error updating write offset for ring\n");
 			mutex_unlock(&chan->lock);
-			kfree(itr);
+			kmem_cache_free(mhi_cntrl->ring_item_cache, itr);
 			continue;
 		}
 
 		/* Sanity check to make sure there are elements in the ring */
 		if (ring->rd_offset == ring->wr_offset) {
 			mutex_unlock(&chan->lock);
-			kfree(itr);
+			kmem_cache_free(mhi_cntrl->ring_item_cache, itr);
 			continue;
 		}
 
@@ -799,12 +799,12 @@ static void mhi_ep_ch_ring_worker(struct work_struct *work)
 			dev_err(dev, "Error processing ring for channel (%u): %d\n",
 				ring->ch_id, ret);
 			mutex_unlock(&chan->lock);
-			kfree(itr);
+			kmem_cache_free(mhi_cntrl->ring_item_cache, itr);
 			continue;
 		}
 
 		mutex_unlock(&chan->lock);
-		kfree(itr);
+		kmem_cache_free(mhi_cntrl->ring_item_cache, itr);
 	}
 }
 
@@ -860,7 +860,7 @@ static void mhi_ep_queue_channel_db(struct mhi_ep_cntrl *mhi_cntrl, unsigned lon
 		u32 ch_id = ch_idx + i;
 
 		ring = &mhi_cntrl->mhi_chan[ch_id].ring;
-		item = kzalloc(sizeof(*item), GFP_ATOMIC);
+		item = kmem_cache_zalloc(mhi_cntrl->ring_item_cache, GFP_ATOMIC);
 		if (!item)
 			return;
 
@@ -1407,6 +1407,29 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl,
 		goto err_free_ch;
 	}
 
+	mhi_cntrl->ev_ring_el_cache = kmem_cache_create("mhi_ep_event_ring_el",
+							sizeof(struct mhi_ring_element), 0,
+							SLAB_CACHE_DMA, NULL);
+	if (!mhi_cntrl->ev_ring_el_cache) {
+		ret = -ENOMEM;
+		goto err_free_cmd;
+	}
+
+	mhi_cntrl->tre_buf_cache = kmem_cache_create("mhi_ep_tre_buf", MHI_EP_DEFAULT_MTU, 0,
+						      SLAB_CACHE_DMA, NULL);
+	if (!mhi_cntrl->tre_buf_cache) {
+		ret = -ENOMEM;
+		goto err_destroy_ev_ring_el_cache;
+	}
+
+	mhi_cntrl->ring_item_cache = kmem_cache_create("mhi_ep_ring_item",
+							sizeof(struct mhi_ep_ring_item), 0,
+							0, NULL);
+	if (!mhi_cntrl->ev_ring_el_cache) {
+		ret = -ENOMEM;
+		goto err_destroy_tre_buf_cache;
+	}
+
 	INIT_WORK(&mhi_cntrl->state_work, mhi_ep_state_worker);
 	INIT_WORK(&mhi_cntrl->reset_work, mhi_ep_reset_worker);
 	INIT_WORK(&mhi_cntrl->cmd_ring_work, mhi_ep_cmd_ring_worker);
@@ -1415,7 +1438,7 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl,
 	mhi_cntrl->wq = alloc_workqueue("mhi_ep_wq", 0, 0);
 	if (!mhi_cntrl->wq) {
 		ret = -ENOMEM;
-		goto err_free_cmd;
+		goto err_destroy_ring_item_cache;
 	}
 
 	INIT_LIST_HEAD(&mhi_cntrl->st_transition_list);
@@ -1474,6 +1497,12 @@ err_ida_free:
 	ida_free(&mhi_ep_cntrl_ida, mhi_cntrl->index);
 err_destroy_wq:
 	destroy_workqueue(mhi_cntrl->wq);
+err_destroy_ring_item_cache:
+	kmem_cache_destroy(mhi_cntrl->ring_item_cache);
+err_destroy_ev_ring_el_cache:
+	kmem_cache_destroy(mhi_cntrl->ev_ring_el_cache);
+err_destroy_tre_buf_cache:
+	kmem_cache_destroy(mhi_cntrl->tre_buf_cache);
 err_free_cmd:
 	kfree(mhi_cntrl->mhi_cmd);
 err_free_ch:
@@ -1495,6 +1524,9 @@ void mhi_ep_unregister_controller(struct mhi_ep_cntrl *mhi_cntrl)
 
 	free_irq(mhi_cntrl->irq, mhi_cntrl);
 
+	kmem_cache_destroy(mhi_cntrl->tre_buf_cache);
+	kmem_cache_destroy(mhi_cntrl->ev_ring_el_cache);
+	kmem_cache_destroy(mhi_cntrl->ring_item_cache);
 	kfree(mhi_cntrl->mhi_cmd);
 	kfree(mhi_cntrl->mhi_chan);
 
diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h
index f198a8ac7ee7..ce85d42b685d 100644
--- a/include/linux/mhi_ep.h
+++ b/include/linux/mhi_ep.h
@@ -128,6 +128,9 @@ struct mhi_ep_cntrl {
 	struct work_struct reset_work;
 	struct work_struct cmd_ring_work;
 	struct work_struct ch_ring_work;
+	struct kmem_cache *ring_item_cache;
+	struct kmem_cache *ev_ring_el_cache;
+	struct kmem_cache *tre_buf_cache;
 
 	void (*raise_irq)(struct mhi_ep_cntrl *mhi_cntrl, u32 vector);
 	int (*alloc_map)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t *phys_ptr,
-- 
cgit v1.2.3


From b08ded2ef2e98768d5ee5f71da8fe768b1f7774b Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Thu, 17 Aug 2023 23:24:52 +0530
Subject: bus: mhi: ep: Pass mhi_ep_buf_info struct to read/write APIs

In the preparation of DMA async support, let's pass the parameters to
read_from_host() and write_to_host() APIs using mhi_ep_buf_info structure.

No functional change.

Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/bus/mhi/ep/main.c                    | 23 +++++-----
 drivers/bus/mhi/ep/ring.c                    | 41 +++++++++--------
 drivers/pci/endpoint/functions/pci-epf-mhi.c | 66 +++++++++++++++-------------
 include/linux/mhi_ep.h                       | 16 ++++++-
 4 files changed, 84 insertions(+), 62 deletions(-)

(limited to 'include')

diff --git a/drivers/bus/mhi/ep/main.c b/drivers/bus/mhi/ep/main.c
index c759183943ed..b9334d548c41 100644
--- a/drivers/bus/mhi/ep/main.c
+++ b/drivers/bus/mhi/ep/main.c
@@ -340,10 +340,9 @@ static int mhi_ep_read_channel(struct mhi_ep_cntrl *mhi_cntrl,
 	struct mhi_ep_chan *mhi_chan = &mhi_cntrl->mhi_chan[ring->ch_id];
 	struct device *dev = &mhi_cntrl->mhi_dev->dev;
 	size_t tr_len, read_offset, write_offset;
+	struct mhi_ep_buf_info buf_info = {};
 	struct mhi_ring_element *el;
 	bool tr_done = false;
-	void *write_addr;
-	u64 read_addr;
 	u32 buf_left;
 	int ret;
 
@@ -372,11 +371,13 @@ static int mhi_ep_read_channel(struct mhi_ep_cntrl *mhi_cntrl,
 
 		read_offset = mhi_chan->tre_size - mhi_chan->tre_bytes_left;
 		write_offset = len - buf_left;
-		read_addr = mhi_chan->tre_loc + read_offset;
-		write_addr = result->buf_addr + write_offset;
+
+		buf_info.host_addr = mhi_chan->tre_loc + read_offset;
+		buf_info.dev_addr = result->buf_addr + write_offset;
+		buf_info.size = tr_len;
 
 		dev_dbg(dev, "Reading %zd bytes from channel (%u)\n", tr_len, ring->ch_id);
-		ret = mhi_cntrl->read_from_host(mhi_cntrl, read_addr, write_addr, tr_len);
+		ret = mhi_cntrl->read_from_host(mhi_cntrl, &buf_info);
 		if (ret < 0) {
 			dev_err(&mhi_chan->mhi_dev->dev, "Error reading from channel\n");
 			return ret;
@@ -499,12 +500,11 @@ int mhi_ep_queue_skb(struct mhi_ep_device *mhi_dev, struct sk_buff *skb)
 	struct mhi_ep_cntrl *mhi_cntrl = mhi_dev->mhi_cntrl;
 	struct mhi_ep_chan *mhi_chan = mhi_dev->dl_chan;
 	struct device *dev = &mhi_chan->mhi_dev->dev;
+	struct mhi_ep_buf_info buf_info = {};
 	struct mhi_ring_element *el;
 	u32 buf_left, read_offset;
 	struct mhi_ep_ring *ring;
 	enum mhi_ev_ccs code;
-	void *read_addr;
-	u64 write_addr;
 	size_t tr_len;
 	u32 tre_len;
 	int ret;
@@ -533,11 +533,13 @@ int mhi_ep_queue_skb(struct mhi_ep_device *mhi_dev, struct sk_buff *skb)
 
 		tr_len = min(buf_left, tre_len);
 		read_offset = skb->len - buf_left;
-		read_addr = skb->data + read_offset;
-		write_addr = MHI_TRE_DATA_GET_PTR(el);
+
+		buf_info.dev_addr = skb->data + read_offset;
+		buf_info.host_addr = MHI_TRE_DATA_GET_PTR(el);
+		buf_info.size = tr_len;
 
 		dev_dbg(dev, "Writing %zd bytes to channel (%u)\n", tr_len, ring->ch_id);
-		ret = mhi_cntrl->write_to_host(mhi_cntrl, read_addr, write_addr, tr_len);
+		ret = mhi_cntrl->write_to_host(mhi_cntrl, &buf_info);
 		if (ret < 0) {
 			dev_err(dev, "Error writing to the channel\n");
 			goto err_exit;
@@ -1445,7 +1447,6 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl,
 		ret = -ENOMEM;
 		goto err_destroy_tre_buf_cache;
 	}
-
 	INIT_WORK(&mhi_cntrl->state_work, mhi_ep_state_worker);
 	INIT_WORK(&mhi_cntrl->reset_work, mhi_ep_reset_worker);
 	INIT_WORK(&mhi_cntrl->cmd_ring_work, mhi_ep_cmd_ring_worker);
diff --git a/drivers/bus/mhi/ep/ring.c b/drivers/bus/mhi/ep/ring.c
index a1071c13761b..7ea952860def 100644
--- a/drivers/bus/mhi/ep/ring.c
+++ b/drivers/bus/mhi/ep/ring.c
@@ -30,7 +30,8 @@ static int __mhi_ep_cache_ring(struct mhi_ep_ring *ring, size_t end)
 {
 	struct mhi_ep_cntrl *mhi_cntrl = ring->mhi_cntrl;
 	struct device *dev = &mhi_cntrl->mhi_dev->dev;
-	size_t start, copy_size;
+	struct mhi_ep_buf_info buf_info = {};
+	size_t start;
 	int ret;
 
 	/* Don't proceed in the case of event ring. This happens during mhi_ep_ring_start(). */
@@ -43,30 +44,34 @@ static int __mhi_ep_cache_ring(struct mhi_ep_ring *ring, size_t end)
 
 	start = ring->wr_offset;
 	if (start < end) {
-		copy_size = (end - start) * sizeof(struct mhi_ring_element);
-		ret = mhi_cntrl->read_from_host(mhi_cntrl, ring->rbase +
-						(start * sizeof(struct mhi_ring_element)),
-						&ring->ring_cache[start], copy_size);
+		buf_info.size = (end - start) * sizeof(struct mhi_ring_element);
+		buf_info.host_addr = ring->rbase + (start * sizeof(struct mhi_ring_element));
+		buf_info.dev_addr = &ring->ring_cache[start];
+
+		ret = mhi_cntrl->read_from_host(mhi_cntrl, &buf_info);
 		if (ret < 0)
 			return ret;
 	} else {
-		copy_size = (ring->ring_size - start) * sizeof(struct mhi_ring_element);
-		ret = mhi_cntrl->read_from_host(mhi_cntrl, ring->rbase +
-						(start * sizeof(struct mhi_ring_element)),
-						&ring->ring_cache[start], copy_size);
+		buf_info.size = (ring->ring_size - start) * sizeof(struct mhi_ring_element);
+		buf_info.host_addr = ring->rbase + (start * sizeof(struct mhi_ring_element));
+		buf_info.dev_addr = &ring->ring_cache[start];
+
+		ret = mhi_cntrl->read_from_host(mhi_cntrl, &buf_info);
 		if (ret < 0)
 			return ret;
 
 		if (end) {
-			ret = mhi_cntrl->read_from_host(mhi_cntrl, ring->rbase,
-							&ring->ring_cache[0],
-							end * sizeof(struct mhi_ring_element));
+			buf_info.host_addr = ring->rbase;
+			buf_info.dev_addr = &ring->ring_cache[0];
+			buf_info.size = end * sizeof(struct mhi_ring_element);
+
+			ret = mhi_cntrl->read_from_host(mhi_cntrl, &buf_info);
 			if (ret < 0)
 				return ret;
 		}
 	}
 
-	dev_dbg(dev, "Cached ring: start %zu end %zu size %zu\n", start, end, copy_size);
+	dev_dbg(dev, "Cached ring: start %zu end %zu size %zu\n", start, end, buf_info.size);
 
 	return 0;
 }
@@ -102,6 +107,7 @@ int mhi_ep_ring_add_element(struct mhi_ep_ring *ring, struct mhi_ring_element *e
 {
 	struct mhi_ep_cntrl *mhi_cntrl = ring->mhi_cntrl;
 	struct device *dev = &mhi_cntrl->mhi_dev->dev;
+	struct mhi_ep_buf_info buf_info = {};
 	size_t old_offset = 0;
 	u32 num_free_elem;
 	__le64 rp;
@@ -133,12 +139,11 @@ int mhi_ep_ring_add_element(struct mhi_ep_ring *ring, struct mhi_ring_element *e
 	rp = cpu_to_le64(ring->rd_offset * sizeof(*el) + ring->rbase);
 	memcpy_toio((void __iomem *) &ring->ring_ctx->generic.rp, &rp, sizeof(u64));
 
-	ret = mhi_cntrl->write_to_host(mhi_cntrl, el, ring->rbase + (old_offset * sizeof(*el)),
-				       sizeof(*el));
-	if (ret < 0)
-		return ret;
+	buf_info.host_addr = ring->rbase + (old_offset * sizeof(*el));
+	buf_info.dev_addr = el;
+	buf_info.size = sizeof(*el);
 
-	return 0;
+	return mhi_cntrl->write_to_host(mhi_cntrl, &buf_info);
 }
 
 void mhi_ep_ring_init(struct mhi_ep_ring *ring, enum mhi_ep_ring_type type, u32 id)
diff --git a/drivers/pci/endpoint/functions/pci-epf-mhi.c b/drivers/pci/endpoint/functions/pci-epf-mhi.c
index b7b9d3e21f97..ec5f4a38178b 100644
--- a/drivers/pci/endpoint/functions/pci-epf-mhi.c
+++ b/drivers/pci/endpoint/functions/pci-epf-mhi.c
@@ -209,28 +209,28 @@ static void pci_epf_mhi_raise_irq(struct mhi_ep_cntrl *mhi_cntrl, u32 vector)
 			  vector + 1);
 }
 
-static int pci_epf_mhi_iatu_read(struct mhi_ep_cntrl *mhi_cntrl, u64 from,
-				 void *to, size_t size)
+static int pci_epf_mhi_iatu_read(struct mhi_ep_cntrl *mhi_cntrl,
+				 struct mhi_ep_buf_info *buf_info)
 {
 	struct pci_epf_mhi *epf_mhi = to_epf_mhi(mhi_cntrl);
-	size_t offset = get_align_offset(epf_mhi, from);
+	size_t offset = get_align_offset(epf_mhi, buf_info->host_addr);
 	void __iomem *tre_buf;
 	phys_addr_t tre_phys;
 	int ret;
 
 	mutex_lock(&epf_mhi->lock);
 
-	ret = __pci_epf_mhi_alloc_map(mhi_cntrl, from, &tre_phys, &tre_buf,
-				      offset, size);
+	ret = __pci_epf_mhi_alloc_map(mhi_cntrl, buf_info->host_addr, &tre_phys,
+				      &tre_buf, offset, buf_info->size);
 	if (ret) {
 		mutex_unlock(&epf_mhi->lock);
 		return ret;
 	}
 
-	memcpy_fromio(to, tre_buf, size);
+	memcpy_fromio(buf_info->dev_addr, tre_buf, buf_info->size);
 
-	__pci_epf_mhi_unmap_free(mhi_cntrl, from, tre_phys, tre_buf, offset,
-				 size);
+	__pci_epf_mhi_unmap_free(mhi_cntrl, buf_info->host_addr, tre_phys,
+				 tre_buf, offset, buf_info->size);
 
 	mutex_unlock(&epf_mhi->lock);
 
@@ -238,27 +238,27 @@ static int pci_epf_mhi_iatu_read(struct mhi_ep_cntrl *mhi_cntrl, u64 from,
 }
 
 static int pci_epf_mhi_iatu_write(struct mhi_ep_cntrl *mhi_cntrl,
-				  void *from, u64 to, size_t size)
+				  struct mhi_ep_buf_info *buf_info)
 {
 	struct pci_epf_mhi *epf_mhi = to_epf_mhi(mhi_cntrl);
-	size_t offset = get_align_offset(epf_mhi, to);
+	size_t offset = get_align_offset(epf_mhi, buf_info->host_addr);
 	void __iomem *tre_buf;
 	phys_addr_t tre_phys;
 	int ret;
 
 	mutex_lock(&epf_mhi->lock);
 
-	ret = __pci_epf_mhi_alloc_map(mhi_cntrl, to, &tre_phys, &tre_buf,
-				      offset, size);
+	ret = __pci_epf_mhi_alloc_map(mhi_cntrl, buf_info->host_addr, &tre_phys,
+				      &tre_buf, offset, buf_info->size);
 	if (ret) {
 		mutex_unlock(&epf_mhi->lock);
 		return ret;
 	}
 
-	memcpy_toio(tre_buf, from, size);
+	memcpy_toio(tre_buf, buf_info->dev_addr, buf_info->size);
 
-	__pci_epf_mhi_unmap_free(mhi_cntrl, to, tre_phys, tre_buf, offset,
-				 size);
+	__pci_epf_mhi_unmap_free(mhi_cntrl, buf_info->host_addr, tre_phys,
+				 tre_buf, offset, buf_info->size);
 
 	mutex_unlock(&epf_mhi->lock);
 
@@ -270,8 +270,8 @@ static void pci_epf_mhi_dma_callback(void *param)
 	complete(param);
 }
 
-static int pci_epf_mhi_edma_read(struct mhi_ep_cntrl *mhi_cntrl, u64 from,
-				 void *to, size_t size)
+static int pci_epf_mhi_edma_read(struct mhi_ep_cntrl *mhi_cntrl,
+				 struct mhi_ep_buf_info *buf_info)
 {
 	struct pci_epf_mhi *epf_mhi = to_epf_mhi(mhi_cntrl);
 	struct device *dma_dev = epf_mhi->epf->epc->dev.parent;
@@ -284,13 +284,13 @@ static int pci_epf_mhi_edma_read(struct mhi_ep_cntrl *mhi_cntrl, u64 from,
 	dma_addr_t dst_addr;
 	int ret;
 
-	if (size < SZ_4K)
-		return pci_epf_mhi_iatu_read(mhi_cntrl, from, to, size);
+	if (buf_info->size < SZ_4K)
+		return pci_epf_mhi_iatu_read(mhi_cntrl, buf_info);
 
 	mutex_lock(&epf_mhi->lock);
 
 	config.direction = DMA_DEV_TO_MEM;
-	config.src_addr = from;
+	config.src_addr = buf_info->host_addr;
 
 	ret = dmaengine_slave_config(chan, &config);
 	if (ret) {
@@ -298,14 +298,16 @@ static int pci_epf_mhi_edma_read(struct mhi_ep_cntrl *mhi_cntrl, u64 from,
 		goto err_unlock;
 	}
 
-	dst_addr = dma_map_single(dma_dev, to, size, DMA_FROM_DEVICE);
+	dst_addr = dma_map_single(dma_dev, buf_info->dev_addr, buf_info->size,
+				  DMA_FROM_DEVICE);
 	ret = dma_mapping_error(dma_dev, dst_addr);
 	if (ret) {
 		dev_err(dev, "Failed to map remote memory\n");
 		goto err_unlock;
 	}
 
-	desc = dmaengine_prep_slave_single(chan, dst_addr, size, DMA_DEV_TO_MEM,
+	desc = dmaengine_prep_slave_single(chan, dst_addr, buf_info->size,
+					   DMA_DEV_TO_MEM,
 					   DMA_CTRL_ACK | DMA_PREP_INTERRUPT);
 	if (!desc) {
 		dev_err(dev, "Failed to prepare DMA\n");
@@ -332,15 +334,15 @@ static int pci_epf_mhi_edma_read(struct mhi_ep_cntrl *mhi_cntrl, u64 from,
 	}
 
 err_unmap:
-	dma_unmap_single(dma_dev, dst_addr, size, DMA_FROM_DEVICE);
+	dma_unmap_single(dma_dev, dst_addr, buf_info->size, DMA_FROM_DEVICE);
 err_unlock:
 	mutex_unlock(&epf_mhi->lock);
 
 	return ret;
 }
 
-static int pci_epf_mhi_edma_write(struct mhi_ep_cntrl *mhi_cntrl, void *from,
-				  u64 to, size_t size)
+static int pci_epf_mhi_edma_write(struct mhi_ep_cntrl *mhi_cntrl,
+				  struct mhi_ep_buf_info *buf_info)
 {
 	struct pci_epf_mhi *epf_mhi = to_epf_mhi(mhi_cntrl);
 	struct device *dma_dev = epf_mhi->epf->epc->dev.parent;
@@ -353,13 +355,13 @@ static int pci_epf_mhi_edma_write(struct mhi_ep_cntrl *mhi_cntrl, void *from,
 	dma_addr_t src_addr;
 	int ret;
 
-	if (size < SZ_4K)
-		return pci_epf_mhi_iatu_write(mhi_cntrl, from, to, size);
+	if (buf_info->size < SZ_4K)
+		return pci_epf_mhi_iatu_write(mhi_cntrl, buf_info);
 
 	mutex_lock(&epf_mhi->lock);
 
 	config.direction = DMA_MEM_TO_DEV;
-	config.dst_addr = to;
+	config.dst_addr = buf_info->host_addr;
 
 	ret = dmaengine_slave_config(chan, &config);
 	if (ret) {
@@ -367,14 +369,16 @@ static int pci_epf_mhi_edma_write(struct mhi_ep_cntrl *mhi_cntrl, void *from,
 		goto err_unlock;
 	}
 
-	src_addr = dma_map_single(dma_dev, from, size, DMA_TO_DEVICE);
+	src_addr = dma_map_single(dma_dev, buf_info->dev_addr, buf_info->size,
+				  DMA_TO_DEVICE);
 	ret = dma_mapping_error(dma_dev, src_addr);
 	if (ret) {
 		dev_err(dev, "Failed to map remote memory\n");
 		goto err_unlock;
 	}
 
-	desc = dmaengine_prep_slave_single(chan, src_addr, size, DMA_MEM_TO_DEV,
+	desc = dmaengine_prep_slave_single(chan, src_addr, buf_info->size,
+					   DMA_MEM_TO_DEV,
 					   DMA_CTRL_ACK | DMA_PREP_INTERRUPT);
 	if (!desc) {
 		dev_err(dev, "Failed to prepare DMA\n");
@@ -401,7 +405,7 @@ static int pci_epf_mhi_edma_write(struct mhi_ep_cntrl *mhi_cntrl, void *from,
 	}
 
 err_unmap:
-	dma_unmap_single(dma_dev, src_addr, size, DMA_FROM_DEVICE);
+	dma_unmap_single(dma_dev, src_addr, buf_info->size, DMA_FROM_DEVICE);
 err_unlock:
 	mutex_unlock(&epf_mhi->lock);
 
diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h
index ce85d42b685d..96f3a133540d 100644
--- a/include/linux/mhi_ep.h
+++ b/include/linux/mhi_ep.h
@@ -49,6 +49,18 @@ struct mhi_ep_db_info {
 	u32 status;
 };
 
+/**
+ * struct mhi_ep_buf_info - MHI Endpoint transfer buffer info
+ * @dev_addr: Address of the buffer in endpoint
+ * @host_addr: Address of the bufffer in host
+ * @size: Size of the buffer
+ */
+struct mhi_ep_buf_info {
+	void *dev_addr;
+	u64 host_addr;
+	size_t size;
+};
+
 /**
  * struct mhi_ep_cntrl - MHI Endpoint controller structure
  * @cntrl_dev: Pointer to the struct device of physical bus acting as the MHI
@@ -137,8 +149,8 @@ struct mhi_ep_cntrl {
 			 void __iomem **virt, size_t size);
 	void (*unmap_free)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t phys,
 			   void __iomem *virt, size_t size);
-	int (*read_from_host)(struct mhi_ep_cntrl *mhi_cntrl, u64 from, void *to, size_t size);
-	int (*write_to_host)(struct mhi_ep_cntrl *mhi_cntrl, void *from, u64 to, size_t size);
+	int (*read_from_host)(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_buf_info *buf_info);
+	int (*write_to_host)(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_buf_info *buf_info);
 
 	enum mhi_state mhi_state;
 
-- 
cgit v1.2.3


From 927105244f8bc48e6841826a5644c6a961e03b5d Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Mon, 27 Nov 2023 13:57:37 +0530
Subject: bus: mhi: ep: Rename read_from_host() and write_to_host() APIs

In the preparation for adding async API support, let's rename the existing
APIs to read_sync() and write_sync() to make it explicit that these APIs
are used for synchronous read/write.

Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/bus/mhi/ep/main.c                    | 4 ++--
 drivers/bus/mhi/ep/ring.c                    | 8 ++++----
 drivers/pci/endpoint/functions/pci-epf-mhi.c | 8 ++++----
 include/linux/mhi_ep.h                       | 8 ++++----
 4 files changed, 14 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/bus/mhi/ep/main.c b/drivers/bus/mhi/ep/main.c
index b9334d548c41..88e189a8463a 100644
--- a/drivers/bus/mhi/ep/main.c
+++ b/drivers/bus/mhi/ep/main.c
@@ -377,7 +377,7 @@ static int mhi_ep_read_channel(struct mhi_ep_cntrl *mhi_cntrl,
 		buf_info.size = tr_len;
 
 		dev_dbg(dev, "Reading %zd bytes from channel (%u)\n", tr_len, ring->ch_id);
-		ret = mhi_cntrl->read_from_host(mhi_cntrl, &buf_info);
+		ret = mhi_cntrl->read_sync(mhi_cntrl, &buf_info);
 		if (ret < 0) {
 			dev_err(&mhi_chan->mhi_dev->dev, "Error reading from channel\n");
 			return ret;
@@ -539,7 +539,7 @@ int mhi_ep_queue_skb(struct mhi_ep_device *mhi_dev, struct sk_buff *skb)
 		buf_info.size = tr_len;
 
 		dev_dbg(dev, "Writing %zd bytes to channel (%u)\n", tr_len, ring->ch_id);
-		ret = mhi_cntrl->write_to_host(mhi_cntrl, &buf_info);
+		ret = mhi_cntrl->write_sync(mhi_cntrl, &buf_info);
 		if (ret < 0) {
 			dev_err(dev, "Error writing to the channel\n");
 			goto err_exit;
diff --git a/drivers/bus/mhi/ep/ring.c b/drivers/bus/mhi/ep/ring.c
index 7ea952860def..aeb53b2c34a8 100644
--- a/drivers/bus/mhi/ep/ring.c
+++ b/drivers/bus/mhi/ep/ring.c
@@ -48,7 +48,7 @@ static int __mhi_ep_cache_ring(struct mhi_ep_ring *ring, size_t end)
 		buf_info.host_addr = ring->rbase + (start * sizeof(struct mhi_ring_element));
 		buf_info.dev_addr = &ring->ring_cache[start];
 
-		ret = mhi_cntrl->read_from_host(mhi_cntrl, &buf_info);
+		ret = mhi_cntrl->read_sync(mhi_cntrl, &buf_info);
 		if (ret < 0)
 			return ret;
 	} else {
@@ -56,7 +56,7 @@ static int __mhi_ep_cache_ring(struct mhi_ep_ring *ring, size_t end)
 		buf_info.host_addr = ring->rbase + (start * sizeof(struct mhi_ring_element));
 		buf_info.dev_addr = &ring->ring_cache[start];
 
-		ret = mhi_cntrl->read_from_host(mhi_cntrl, &buf_info);
+		ret = mhi_cntrl->read_sync(mhi_cntrl, &buf_info);
 		if (ret < 0)
 			return ret;
 
@@ -65,7 +65,7 @@ static int __mhi_ep_cache_ring(struct mhi_ep_ring *ring, size_t end)
 			buf_info.dev_addr = &ring->ring_cache[0];
 			buf_info.size = end * sizeof(struct mhi_ring_element);
 
-			ret = mhi_cntrl->read_from_host(mhi_cntrl, &buf_info);
+			ret = mhi_cntrl->read_sync(mhi_cntrl, &buf_info);
 			if (ret < 0)
 				return ret;
 		}
@@ -143,7 +143,7 @@ int mhi_ep_ring_add_element(struct mhi_ep_ring *ring, struct mhi_ring_element *e
 	buf_info.dev_addr = el;
 	buf_info.size = sizeof(*el);
 
-	return mhi_cntrl->write_to_host(mhi_cntrl, &buf_info);
+	return mhi_cntrl->write_sync(mhi_cntrl, &buf_info);
 }
 
 void mhi_ep_ring_init(struct mhi_ep_ring *ring, enum mhi_ep_ring_type type, u32 id)
diff --git a/drivers/pci/endpoint/functions/pci-epf-mhi.c b/drivers/pci/endpoint/functions/pci-epf-mhi.c
index ec5f4a38178b..2c5b627eb5ee 100644
--- a/drivers/pci/endpoint/functions/pci-epf-mhi.c
+++ b/drivers/pci/endpoint/functions/pci-epf-mhi.c
@@ -536,11 +536,11 @@ static int pci_epf_mhi_link_up(struct pci_epf *epf)
 	mhi_cntrl->alloc_map = pci_epf_mhi_alloc_map;
 	mhi_cntrl->unmap_free = pci_epf_mhi_unmap_free;
 	if (info->flags & MHI_EPF_USE_DMA) {
-		mhi_cntrl->read_from_host = pci_epf_mhi_edma_read;
-		mhi_cntrl->write_to_host = pci_epf_mhi_edma_write;
+		mhi_cntrl->read_sync = pci_epf_mhi_edma_read;
+		mhi_cntrl->write_sync = pci_epf_mhi_edma_write;
 	} else {
-		mhi_cntrl->read_from_host = pci_epf_mhi_iatu_read;
-		mhi_cntrl->write_to_host = pci_epf_mhi_iatu_write;
+		mhi_cntrl->read_sync = pci_epf_mhi_iatu_read;
+		mhi_cntrl->write_sync = pci_epf_mhi_iatu_write;
 	}
 
 	/* Register the MHI EP controller */
diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h
index 96f3a133540d..b96b543bf2f6 100644
--- a/include/linux/mhi_ep.h
+++ b/include/linux/mhi_ep.h
@@ -94,8 +94,8 @@ struct mhi_ep_buf_info {
  * @raise_irq: CB function for raising IRQ to the host
  * @alloc_map: CB function for allocating memory in endpoint for storing host context and mapping it
  * @unmap_free: CB function to unmap and free the allocated memory in endpoint for storing host context
- * @read_from_host: CB function for reading from host memory from endpoint
- * @write_to_host: CB function for writing to host memory from endpoint
+ * @read_sync: CB function for reading from host memory synchronously
+ * @write_sync: CB function for writing to host memory synchronously
  * @mhi_state: MHI Endpoint state
  * @max_chan: Maximum channels supported by the endpoint controller
  * @mru: MRU (Maximum Receive Unit) value of the endpoint controller
@@ -149,8 +149,8 @@ struct mhi_ep_cntrl {
 			 void __iomem **virt, size_t size);
 	void (*unmap_free)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t phys,
 			   void __iomem *virt, size_t size);
-	int (*read_from_host)(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_buf_info *buf_info);
-	int (*write_to_host)(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_buf_info *buf_info);
+	int (*read_sync)(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_buf_info *buf_info);
+	int (*write_sync)(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_buf_info *buf_info);
 
 	enum mhi_state mhi_state;
 
-- 
cgit v1.2.3


From 8b786ed8fb089e347af21d13ba5677325fcd4cd8 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Mon, 27 Nov 2023 15:35:50 +0530
Subject: bus: mhi: ep: Introduce async read/write callbacks

These callbacks can be implemented by the controller drivers to perform
async read/write operation that increases the throughput.

For aiding the async operation, a completion callback is also introduced.

Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 include/linux/mhi_ep.h | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'include')

diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h
index b96b543bf2f6..14c6e8d3f573 100644
--- a/include/linux/mhi_ep.h
+++ b/include/linux/mhi_ep.h
@@ -54,11 +54,16 @@ struct mhi_ep_db_info {
  * @dev_addr: Address of the buffer in endpoint
  * @host_addr: Address of the bufffer in host
  * @size: Size of the buffer
+ * @cb: Callback to be executed by controller drivers after transfer completion (async)
+ * @cb_buf: Opaque buffer to be passed to the callback
  */
 struct mhi_ep_buf_info {
 	void *dev_addr;
 	u64 host_addr;
 	size_t size;
+
+	void (*cb)(struct mhi_ep_buf_info *buf_info);
+	void *cb_buf;
 };
 
 /**
@@ -96,6 +101,8 @@ struct mhi_ep_buf_info {
  * @unmap_free: CB function to unmap and free the allocated memory in endpoint for storing host context
  * @read_sync: CB function for reading from host memory synchronously
  * @write_sync: CB function for writing to host memory synchronously
+ * @read_async: CB function for reading from host memory asynchronously
+ * @write_async: CB function for writing to host memory asynchronously
  * @mhi_state: MHI Endpoint state
  * @max_chan: Maximum channels supported by the endpoint controller
  * @mru: MRU (Maximum Receive Unit) value of the endpoint controller
@@ -151,6 +158,8 @@ struct mhi_ep_cntrl {
 			   void __iomem *virt, size_t size);
 	int (*read_sync)(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_buf_info *buf_info);
 	int (*write_sync)(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_buf_info *buf_info);
+	int (*read_async)(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_buf_info *buf_info);
+	int (*write_async)(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_buf_info *buf_info);
 
 	enum mhi_state mhi_state;
 
-- 
cgit v1.2.3


From 7a92fc8b4d20680e4c20289a670d8fca2d1f2c1b Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Tue, 12 Dec 2023 22:34:56 +0100
Subject: mm: Introduce flush_cache_vmap_early()

The pcpu setup when using the page allocator sets up a new vmalloc
mapping very early in the boot process, so early that it cannot use the
flush_cache_vmap() function which may depend on structures not yet
initialized (for example in riscv, we currently send an IPI to flush
other cpus TLB).

But on some architectures, we must call flush_cache_vmap(): for example,
in riscv, some uarchs can cache invalid TLB entries so we need to flush
the new established mapping to avoid taking an exception.

So fix this by introducing a new function flush_cache_vmap_early() which
is called right after setting the new page table entry and before
accessing this new mapping. This new function implements a local flush
tlb on riscv and is no-op for other architectures (same as today).

Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Dennis Zhou <dennis@kernel.org>
---
 arch/arc/include/asm/cacheflush.h      | 1 +
 arch/arm/include/asm/cacheflush.h      | 2 ++
 arch/csky/abiv1/inc/abi/cacheflush.h   | 1 +
 arch/csky/abiv2/inc/abi/cacheflush.h   | 1 +
 arch/m68k/include/asm/cacheflush_mm.h  | 1 +
 arch/mips/include/asm/cacheflush.h     | 2 ++
 arch/nios2/include/asm/cacheflush.h    | 1 +
 arch/parisc/include/asm/cacheflush.h   | 1 +
 arch/riscv/include/asm/cacheflush.h    | 3 ++-
 arch/riscv/include/asm/tlbflush.h      | 1 +
 arch/riscv/mm/tlbflush.c               | 5 +++++
 arch/sh/include/asm/cacheflush.h       | 1 +
 arch/sparc/include/asm/cacheflush_32.h | 1 +
 arch/sparc/include/asm/cacheflush_64.h | 1 +
 arch/xtensa/include/asm/cacheflush.h   | 6 ++++--
 include/asm-generic/cacheflush.h       | 6 ++++++
 mm/percpu.c                            | 8 +-------
 17 files changed, 32 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/arch/arc/include/asm/cacheflush.h b/arch/arc/include/asm/cacheflush.h
index bd5b1a9a0544..6fc74500a9f5 100644
--- a/arch/arc/include/asm/cacheflush.h
+++ b/arch/arc/include/asm/cacheflush.h
@@ -40,6 +40,7 @@ void dma_cache_wback(phys_addr_t start, unsigned long sz);
 
 /* TBD: optimize this */
 #define flush_cache_vmap(start, end)		flush_cache_all()
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		flush_cache_all()
 
 #define flush_cache_dup_mm(mm)			/* called on fork (VIVT only) */
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index f6181f69577f..1075534b0a2e 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -340,6 +340,8 @@ static inline void flush_cache_vmap(unsigned long start, unsigned long end)
 		dsb(ishst);
 }
 
+#define flush_cache_vmap_early(start, end)	do { } while (0)
+
 static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
 {
 	if (!cache_is_vipt_nonaliasing())
diff --git a/arch/csky/abiv1/inc/abi/cacheflush.h b/arch/csky/abiv1/inc/abi/cacheflush.h
index 908d8b0bc4fd..d011a81575d2 100644
--- a/arch/csky/abiv1/inc/abi/cacheflush.h
+++ b/arch/csky/abiv1/inc/abi/cacheflush.h
@@ -43,6 +43,7 @@ static inline void flush_anon_page(struct vm_area_struct *vma,
  */
 extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
 #define flush_cache_vmap(start, end)		cache_wbinv_all()
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		cache_wbinv_all()
 
 #define flush_icache_range(start, end)		cache_wbinv_range(start, end)
diff --git a/arch/csky/abiv2/inc/abi/cacheflush.h b/arch/csky/abiv2/inc/abi/cacheflush.h
index 40be16907267..6513ac5d2578 100644
--- a/arch/csky/abiv2/inc/abi/cacheflush.h
+++ b/arch/csky/abiv2/inc/abi/cacheflush.h
@@ -41,6 +41,7 @@ void flush_icache_mm_range(struct mm_struct *mm,
 void flush_icache_deferred(struct mm_struct *mm);
 
 #define flush_cache_vmap(start, end)		do { } while (0)
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		do { } while (0)
 
 #define copy_to_user_page(vma, page, vaddr, dst, src, len) \
diff --git a/arch/m68k/include/asm/cacheflush_mm.h b/arch/m68k/include/asm/cacheflush_mm.h
index ed12358c4783..9a71b0148461 100644
--- a/arch/m68k/include/asm/cacheflush_mm.h
+++ b/arch/m68k/include/asm/cacheflush_mm.h
@@ -191,6 +191,7 @@ extern void cache_push_v(unsigned long vaddr, int len);
 #define flush_cache_all() __flush_cache_all()
 
 #define flush_cache_vmap(start, end)		flush_cache_all()
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		flush_cache_all()
 
 static inline void flush_cache_mm(struct mm_struct *mm)
diff --git a/arch/mips/include/asm/cacheflush.h b/arch/mips/include/asm/cacheflush.h
index f36c2519ed97..1f14132b3fc9 100644
--- a/arch/mips/include/asm/cacheflush.h
+++ b/arch/mips/include/asm/cacheflush.h
@@ -97,6 +97,8 @@ static inline void flush_cache_vmap(unsigned long start, unsigned long end)
 		__flush_cache_vmap();
 }
 
+#define flush_cache_vmap_early(start, end)     do { } while (0)
+
 extern void (*__flush_cache_vunmap)(void);
 
 static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
diff --git a/arch/nios2/include/asm/cacheflush.h b/arch/nios2/include/asm/cacheflush.h
index 348cea097792..81484a776b33 100644
--- a/arch/nios2/include/asm/cacheflush.h
+++ b/arch/nios2/include/asm/cacheflush.h
@@ -38,6 +38,7 @@ void flush_icache_pages(struct vm_area_struct *vma, struct page *page,
 #define flush_icache_pages flush_icache_pages
 
 #define flush_cache_vmap(start, end)		flush_dcache_range(start, end)
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		flush_dcache_range(start, end)
 
 extern void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h
index b4006f2a9705..ba4c05bc24d6 100644
--- a/arch/parisc/include/asm/cacheflush.h
+++ b/arch/parisc/include/asm/cacheflush.h
@@ -41,6 +41,7 @@ void flush_kernel_vmap_range(void *vaddr, int size);
 void invalidate_kernel_vmap_range(void *vaddr, int size);
 
 #define flush_cache_vmap(start, end)		flush_cache_all()
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		flush_cache_all()
 
 void flush_dcache_folio(struct folio *folio);
diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h
index 3cb53c4df27c..a129dac4521d 100644
--- a/arch/riscv/include/asm/cacheflush.h
+++ b/arch/riscv/include/asm/cacheflush.h
@@ -37,7 +37,8 @@ static inline void flush_dcache_page(struct page *page)
 	flush_icache_mm(vma->vm_mm, 0)
 
 #ifdef CONFIG_64BIT
-#define flush_cache_vmap(start, end)	flush_tlb_kernel_range(start, end)
+#define flush_cache_vmap(start, end)		flush_tlb_kernel_range(start, end)
+#define flush_cache_vmap_early(start, end)	local_flush_tlb_kernel_range(start, end)
 #endif
 
 #ifndef CONFIG_SMP
diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
index 8f3418c5f172..a60416bbe190 100644
--- a/arch/riscv/include/asm/tlbflush.h
+++ b/arch/riscv/include/asm/tlbflush.h
@@ -41,6 +41,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr);
 void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 		     unsigned long end);
 void flush_tlb_kernel_range(unsigned long start, unsigned long end);
+void local_flush_tlb_kernel_range(unsigned long start, unsigned long end);
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
 void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index e6659d7368b3..8aadc5f71c93 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -66,6 +66,11 @@ static inline void local_flush_tlb_range_asid(unsigned long start,
 		local_flush_tlb_range_threshold_asid(start, size, stride, asid);
 }
 
+void local_flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+	local_flush_tlb_range_asid(start, end, PAGE_SIZE, FLUSH_TLB_NO_ASID);
+}
+
 static void __ipi_flush_tlb_all(void *info)
 {
 	local_flush_tlb_all();
diff --git a/arch/sh/include/asm/cacheflush.h b/arch/sh/include/asm/cacheflush.h
index 878b6b551bd2..51112f54552b 100644
--- a/arch/sh/include/asm/cacheflush.h
+++ b/arch/sh/include/asm/cacheflush.h
@@ -90,6 +90,7 @@ extern void copy_from_user_page(struct vm_area_struct *vma,
 	unsigned long len);
 
 #define flush_cache_vmap(start, end)		local_flush_cache_all(NULL)
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		local_flush_cache_all(NULL)
 
 #define flush_dcache_mmap_lock(mapping)		do { } while (0)
diff --git a/arch/sparc/include/asm/cacheflush_32.h b/arch/sparc/include/asm/cacheflush_32.h
index f3b7270bf71b..9fee0ccfccb8 100644
--- a/arch/sparc/include/asm/cacheflush_32.h
+++ b/arch/sparc/include/asm/cacheflush_32.h
@@ -48,6 +48,7 @@ static inline void flush_dcache_page(struct page *page)
 #define flush_dcache_mmap_unlock(mapping)	do { } while (0)
 
 #define flush_cache_vmap(start, end)		flush_cache_all()
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		flush_cache_all()
 
 /* When a context switch happens we must flush all user windows so that
diff --git a/arch/sparc/include/asm/cacheflush_64.h b/arch/sparc/include/asm/cacheflush_64.h
index 0e879004efff..2b1261b77ecd 100644
--- a/arch/sparc/include/asm/cacheflush_64.h
+++ b/arch/sparc/include/asm/cacheflush_64.h
@@ -75,6 +75,7 @@ void flush_ptrace_access(struct vm_area_struct *, struct page *,
 #define flush_dcache_mmap_unlock(mapping)	do { } while (0)
 
 #define flush_cache_vmap(start, end)		do { } while (0)
+#define flush_cache_vmap_early(start, end)	do { } while (0)
 #define flush_cache_vunmap(start, end)		do { } while (0)
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/xtensa/include/asm/cacheflush.h b/arch/xtensa/include/asm/cacheflush.h
index 785a00ce83c1..38bcecb0e457 100644
--- a/arch/xtensa/include/asm/cacheflush.h
+++ b/arch/xtensa/include/asm/cacheflush.h
@@ -116,8 +116,9 @@ void flush_cache_page(struct vm_area_struct*,
 #define flush_cache_mm(mm)		flush_cache_all()
 #define flush_cache_dup_mm(mm)		flush_cache_mm(mm)
 
-#define flush_cache_vmap(start,end)	flush_cache_all()
-#define flush_cache_vunmap(start,end)	flush_cache_all()
+#define flush_cache_vmap(start,end)		flush_cache_all()
+#define flush_cache_vmap_early(start,end)	do { } while (0)
+#define flush_cache_vunmap(start,end)		flush_cache_all()
 
 void flush_dcache_folio(struct folio *folio);
 #define flush_dcache_folio flush_dcache_folio
@@ -140,6 +141,7 @@ void local_flush_cache_page(struct vm_area_struct *vma,
 #define flush_cache_dup_mm(mm)				do { } while (0)
 
 #define flush_cache_vmap(start,end)			do { } while (0)
+#define flush_cache_vmap_early(start,end)		do { } while (0)
 #define flush_cache_vunmap(start,end)			do { } while (0)
 
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
diff --git a/include/asm-generic/cacheflush.h b/include/asm-generic/cacheflush.h
index 84ec53ccc450..7ee8a179d103 100644
--- a/include/asm-generic/cacheflush.h
+++ b/include/asm-generic/cacheflush.h
@@ -91,6 +91,12 @@ static inline void flush_cache_vmap(unsigned long start, unsigned long end)
 }
 #endif
 
+#ifndef flush_cache_vmap_early
+static inline void flush_cache_vmap_early(unsigned long start, unsigned long end)
+{
+}
+#endif
+
 #ifndef flush_cache_vunmap
 static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
 {
diff --git a/mm/percpu.c b/mm/percpu.c
index 7b97d31df767..4e11fc1e6def 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -3333,13 +3333,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_cpu_to_node_fn_t
 		if (rc < 0)
 			panic("failed to map percpu area, err=%d\n", rc);
 
-		/*
-		 * FIXME: Archs with virtual cache should flush local
-		 * cache for the linear mapping here - something
-		 * equivalent to flush_cache_vmap() on the local cpu.
-		 * flush_cache_vmap() can't be used as most supporting
-		 * data structures are not set up yet.
-		 */
+		flush_cache_vmap_early(unit_addr, unit_addr + ai->unit_size);
 
 		/* copy static data */
 		memcpy((void *)unit_addr, __per_cpu_load, ai->static_size);
-- 
cgit v1.2.3


From afa5cf3175a22b719a65fc0b13dbf78196a60869 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 12 Dec 2023 20:40:14 -0800
Subject: drm/i915/uapi: fix typos/spellos and punctuation

Use "its" for possessive form instead of "it's".
Hyphenate multi-word adjectives.
Correct some spelling.
End one line of code with ';' instead of ','. The before and after
  object files are identical.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: intel-gfx@lists.freedesktop.org
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231213044014.21410-1-rdunlap@infradead.org
---
 include/uapi/drm/i915_drm.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 218edb0a96f8..fd4f9574d177 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -693,7 +693,7 @@ typedef struct drm_i915_irq_wait {
 #define I915_PARAM_HAS_EXEC_FENCE	 44
 
 /* Query whether DRM_I915_GEM_EXECBUFFER2 supports the ability to capture
- * user specified bufffers for post-mortem debugging of GPU hangs. See
+ * user-specified buffers for post-mortem debugging of GPU hangs. See
  * EXEC_OBJECT_CAPTURE.
  */
 #define I915_PARAM_HAS_EXEC_CAPTURE	 45
@@ -1606,7 +1606,7 @@ struct drm_i915_gem_busy {
 	 * is accurate.
 	 *
 	 * The returned dword is split into two fields to indicate both
-	 * the engine classess on which the object is being read, and the
+	 * the engine classes on which the object is being read, and the
 	 * engine class on which it is currently being written (if any).
 	 *
 	 * The low word (bits 0:15) indicate if the object is being written
@@ -1815,7 +1815,7 @@ struct drm_i915_gem_madvise {
 	__u32 handle;
 
 	/* Advice: either the buffer will be needed again in the near future,
-	 *         or wont be and could be discarded under memory pressure.
+	 *         or won't be and could be discarded under memory pressure.
 	 */
 	__u32 madv;
 
@@ -3246,7 +3246,7 @@ struct drm_i915_query_topology_info {
  * 	// enough to hold our array of engines. The kernel will fill out the
  * 	// item.length for us, which is the number of bytes we need.
  * 	//
- * 	// Alternatively a large buffer can be allocated straight away enabling
+ *	// Alternatively a large buffer can be allocated straightaway enabling
  * 	// querying in one pass, in which case item.length should contain the
  * 	// length of the provided buffer.
  * 	err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query);
@@ -3256,7 +3256,7 @@ struct drm_i915_query_topology_info {
  * 	// Now that we allocated the required number of bytes, we call the ioctl
  * 	// again, this time with the data_ptr pointing to our newly allocated
  * 	// blob, which the kernel can then populate with info on all engines.
- * 	item.data_ptr = (uintptr_t)&info,
+ *	item.data_ptr = (uintptr_t)&info;
  *
  * 	err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query);
  * 	if (err) ...
@@ -3286,7 +3286,7 @@ struct drm_i915_query_topology_info {
 /**
  * struct drm_i915_engine_info
  *
- * Describes one engine and it's capabilities as known to the driver.
+ * Describes one engine and its capabilities as known to the driver.
  */
 struct drm_i915_engine_info {
 	/** @engine: Engine class and instance. */
-- 
cgit v1.2.3


From b4c2bea8ceaa50cd42a8f73667389d801a3ecf2d Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@redhat.com>
Date: Wed, 25 Oct 2023 16:02:03 +0200
Subject: add listmount(2) syscall

Add way to query the children of a particular mount.  This is a more
flexible way to iterate the mount tree than having to parse
/proc/self/mountinfo.

Lookup the mount by the new 64bit mount ID. If a mount needs to be
queried based on path, then statx(2) can be used to first query the
mount ID belonging to the path.

Return an array of new (64bit) mount ID's. Without privileges only
mounts are listed which are reachable from the task's root.

Folded into this patch are several later improvements. Keeping them
separate would make the history pointlessly confusing:

* Recursive listing of mounts is the default now (cf. [1]).
* Remove explicit LISTMOUNT_UNREACHABLE flag (cf. [1]) and fail if mount
  is unreachable from current root. This also makes permission checking
  consistent with statmount() (cf. [3]).
* Start listing mounts in unique mount ID order (cf. [2]) to allow
  continuing listmount() from a midpoint.
* Allow to continue listmount(). The @request_mask parameter is renamed
  and to @param to be usable by both statmount() and listmount().
  If @param is set to a mount id then listmount() will continue listing
  mounts from that id on. This allows listing mounts in multiple
  listmount invocations without having to resize the buffer. If @param
  is zero then the listing starts from the beginning (cf. [4]).
* Don't return EOVERFLOW, instead return the buffer size which allows to
  detect a full buffer as well (cf. [4]).

Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Link: https://lore.kernel.org/r/20231025140205.3586473-6-mszeredi@redhat.com
Reviewed-by: Ian Kent <raven@themaw.net>
Link: https://lore.kernel.org/r/20231128160337.29094-2-mszeredi@redhat.com [1] (folded)
Link: https://lore.kernel.org/r/20231128160337.29094-3-mszeredi@redhat.com [2] (folded)
Link: https://lore.kernel.org/r/20231128160337.29094-4-mszeredi@redhat.com [3] (folded)
Link: https://lore.kernel.org/r/20231128160337.29094-5-mszeredi@redhat.com [4] (folded)
[Christian Brauner <brauner@kernel.org>: various smaller fixes]
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/namespace.c             | 86 ++++++++++++++++++++++++++++++++++++++++++++--
 include/linux/syscalls.h   |  3 ++
 include/uapi/linux/mount.h | 14 +++++++-
 3 files changed, 100 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/fs/namespace.c b/fs/namespace.c
index 7f1618ed2aba..873185b8a84b 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -32,6 +32,7 @@
 #include <linux/fs_context.h>
 #include <linux/shmem_fs.h>
 #include <linux/mnt_idmapping.h>
+#include <linux/nospec.h>
 
 #include "pnode.h"
 #include "internal.h"
@@ -1009,7 +1010,7 @@ void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct m
 
 static inline struct mount *node_to_mount(struct rb_node *node)
 {
-	return rb_entry(node, struct mount, mnt_node);
+	return node ? rb_entry(node, struct mount, mnt_node) : NULL;
 }
 
 static void mnt_add_to_ns(struct mnt_namespace *ns, struct mount *mnt)
@@ -4945,7 +4946,7 @@ static int prepare_kstatmount(struct kstatmount *ks, struct mnt_id_req *kreq,
 		return -EFAULT;
 
 	memset(ks, 0, sizeof(*ks));
-	ks->mask = kreq->request_mask;
+	ks->mask = kreq->param;
 	ks->buf = buf;
 	ks->bufsize = bufsize;
 	ks->seq.size = seq_size;
@@ -4999,6 +5000,87 @@ retry:
 	return ret;
 }
 
+static struct mount *listmnt_next(struct mount *curr)
+{
+	return node_to_mount(rb_next(&curr->mnt_node));
+}
+
+static ssize_t do_listmount(struct mount *first, struct path *orig, u64 mnt_id,
+			    u64 __user *buf, size_t bufsize,
+			    const struct path *root)
+{
+	struct mount *r;
+	ssize_t ctr;
+	int err;
+
+	/*
+	 * Don't trigger audit denials. We just want to determine what
+	 * mounts to show users.
+	 */
+	if (!is_path_reachable(real_mount(orig->mnt), orig->dentry, root) &&
+	    !ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN))
+		return -EPERM;
+
+	err = security_sb_statfs(orig->dentry);
+	if (err)
+		return err;
+
+	for (ctr = 0, r = first; r && ctr < bufsize; r = listmnt_next(r)) {
+		if (r->mnt_id_unique == mnt_id)
+			continue;
+		if (!is_path_reachable(r, r->mnt.mnt_root, orig))
+			continue;
+		ctr = array_index_nospec(ctr, bufsize);
+		if (put_user(r->mnt_id_unique, buf + ctr))
+			return -EFAULT;
+		if (check_add_overflow(ctr, 1, &ctr))
+			return -ERANGE;
+	}
+	return ctr;
+}
+
+SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req,
+		u64 __user *, buf, size_t, bufsize, unsigned int, flags)
+{
+	struct mnt_namespace *ns = current->nsproxy->mnt_ns;
+	struct mnt_id_req kreq;
+	struct mount *first;
+	struct path root, orig;
+	u64 mnt_id, last_mnt_id;
+	ssize_t ret;
+
+	if (flags)
+		return -EINVAL;
+
+	if (copy_from_user(&kreq, req, sizeof(kreq)))
+		return -EFAULT;
+	mnt_id = kreq.mnt_id;
+	last_mnt_id = kreq.param;
+
+	down_read(&namespace_sem);
+	get_fs_root(current->fs, &root);
+	if (mnt_id == LSMT_ROOT) {
+		orig = root;
+	} else {
+		ret = -ENOENT;
+		orig.mnt  = lookup_mnt_in_ns(mnt_id, ns);
+		if (!orig.mnt)
+			goto err;
+		orig.dentry = orig.mnt->mnt_root;
+	}
+	if (!last_mnt_id)
+		first = node_to_mount(rb_first(&ns->mounts));
+	else
+		first = mnt_find_id_at(ns, last_mnt_id + 1);
+
+	ret = do_listmount(first, &orig, mnt_id, buf, bufsize, &root);
+err:
+	path_put(&root);
+	up_read(&namespace_sem);
+	return ret;
+}
+
+
 static void __init init_mount_tree(void)
 {
 	struct vfsmount *mnt;
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 530ca9adf5f1..2d6d3e76e3f7 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -412,6 +412,9 @@ asmlinkage long sys_fstatfs64(unsigned int fd, size_t sz,
 asmlinkage long sys_statmount(const struct mnt_id_req __user *req,
 			      struct statmount __user *buf, size_t bufsize,
 			      unsigned int flags);
+asmlinkage long sys_listmount(const struct mnt_id_req __user *req,
+			      u64 __user *buf, size_t bufsize,
+			      unsigned int flags);
 asmlinkage long sys_truncate(const char __user *path, long length);
 asmlinkage long sys_ftruncate(unsigned int fd, unsigned long length);
 #if BITS_PER_LONG == 32
diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h
index afdf4f2f6672..dc9a0112d819 100644
--- a/include/uapi/linux/mount.h
+++ b/include/uapi/linux/mount.h
@@ -176,9 +176,16 @@ struct statmount {
 	char str[];		/* Variable size part containing strings */
 };
 
+/*
+ * Structure for passing mount ID and miscellaneous parameters to statmount(2)
+ * and listmount(2).
+ *
+ * For statmount(2) @param represents the request mask.
+ * For listmount(2) @param represents the last listed mount id (or zero).
+ */
 struct mnt_id_req {
 	__u64 mnt_id;
-	__u64 request_mask;
+	__u64 param;
 };
 
 /*
@@ -191,4 +198,9 @@ struct mnt_id_req {
 #define STATMOUNT_MNT_POINT		0x00000010U	/* Want/got mnt_point */
 #define STATMOUNT_FS_TYPE		0x00000020U	/* Want/got fs_type */
 
+/*
+ * Special @mnt_id values that can be passed to listmount
+ */
+#define LSMT_ROOT		0xffffffffffffffff	/* root mount */
+
 #endif /* _UAPI_LINUX_MOUNT_H */
-- 
cgit v1.2.3


From d8b0f5465012538cc4bb10ddc4affadbab73465b Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@redhat.com>
Date: Wed, 25 Oct 2023 16:02:04 +0200
Subject: wire up syscalls for statmount/listmount

Wire up all archs.

Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Link: https://lore.kernel.org/r/20231025140205.3586473-7-mszeredi@redhat.com
Reviewed-by: Ian Kent <raven@themaw.net>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 arch/alpha/kernel/syscalls/syscall.tbl      | 2 ++
 arch/arm/tools/syscall.tbl                  | 2 ++
 arch/arm64/include/asm/unistd32.h           | 4 ++++
 arch/m68k/kernel/syscalls/syscall.tbl       | 2 ++
 arch/microblaze/kernel/syscalls/syscall.tbl | 2 ++
 arch/mips/kernel/syscalls/syscall_n32.tbl   | 2 ++
 arch/mips/kernel/syscalls/syscall_n64.tbl   | 2 ++
 arch/mips/kernel/syscalls/syscall_o32.tbl   | 2 ++
 arch/parisc/kernel/syscalls/syscall.tbl     | 2 ++
 arch/powerpc/kernel/syscalls/syscall.tbl    | 2 ++
 arch/s390/kernel/syscalls/syscall.tbl       | 2 ++
 arch/sh/kernel/syscalls/syscall.tbl         | 2 ++
 arch/sparc/kernel/syscalls/syscall.tbl      | 2 ++
 arch/x86/entry/syscalls/syscall_32.tbl      | 2 ++
 arch/x86/entry/syscalls/syscall_64.tbl      | 2 ++
 arch/xtensa/kernel/syscalls/syscall.tbl     | 2 ++
 include/uapi/asm-generic/unistd.h           | 8 +++++++-
 17 files changed, 41 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index 18c842ca6c32..186e785f5b56 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -496,3 +496,5 @@
 564	common	futex_wake			sys_futex_wake
 565	common	futex_wait			sys_futex_wait
 566	common	futex_requeue			sys_futex_requeue
+567	common	statmount			sys_statmount
+568	common	listmount			sys_listmount
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index 584f9528c996..d6a324dbff2e 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -470,3 +470,5 @@
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
 456	common	futex_requeue			sys_futex_requeue
+457	common	statmount			sys_statmount
+458	common	listmount			sys_listmount
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 9f7c1bf99526..8a191423c316 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -919,6 +919,10 @@ __SYSCALL(__NR_futex_wake, sys_futex_wake)
 __SYSCALL(__NR_futex_wait, sys_futex_wait)
 #define __NR_futex_requeue 456
 __SYSCALL(__NR_futex_requeue, sys_futex_requeue)
+#define __NR_statmount 457
+__SYSCALL(__NR_statmount, sys_statmount)
+#define __NR_listmount 458
+__SYSCALL(__NR_listmount, sys_listmount)
 
 /*
  * Please add new compat syscalls above this comment and update
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index 7a4b780e82cb..37db1a810b67 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -456,3 +456,5 @@
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
 456	common	futex_requeue			sys_futex_requeue
+457	common	statmount			sys_statmount
+458	common	listmount			sys_listmount
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl
index 5b6a0b02b7de..07fff5ad1c9c 100644
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -462,3 +462,5 @@
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
 456	common	futex_requeue			sys_futex_requeue
+457	common	statmount			sys_statmount
+458	common	listmount			sys_listmount
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index a842b41c8e06..134ea054b1c7 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -395,3 +395,5 @@
 454	n32	futex_wake			sys_futex_wake
 455	n32	futex_wait			sys_futex_wait
 456	n32	futex_requeue			sys_futex_requeue
+457	n32	statmount			sys_statmount
+458	n32	listmount			sys_listmount
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index 116ff501bf92..959a21664703 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -371,3 +371,5 @@
 454	n64	futex_wake			sys_futex_wake
 455	n64	futex_wait			sys_futex_wait
 456	n64	futex_requeue			sys_futex_requeue
+457	n64	statmount			sys_statmount
+458	n64	listmount			sys_listmount
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index 525cc54bc63b..e55bc1d4bf0f 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -444,3 +444,5 @@
 454	o32	futex_wake			sys_futex_wake
 455	o32	futex_wait			sys_futex_wait
 456	o32	futex_requeue			sys_futex_requeue
+457	o32	statmount			sys_statmount
+458	o32	listmount			sys_listmount
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index a47798fed54e..9c84470c31c7 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -455,3 +455,5 @@
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
 456	common	futex_requeue			sys_futex_requeue
+457	common	statmount			sys_statmount
+458	common	listmount			sys_listmount
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index 7fab411378f2..6988ecbc316e 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -543,3 +543,5 @@
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
 456	common	futex_requeue			sys_futex_requeue
+457	common	statmount			sys_statmount
+458	common	listmount			sys_listmount
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index 86fec9b080f6..5f5cd20ebb34 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -459,3 +459,5 @@
 454  common	futex_wake		sys_futex_wake			sys_futex_wake
 455  common	futex_wait		sys_futex_wait			sys_futex_wait
 456  common	futex_requeue		sys_futex_requeue		sys_futex_requeue
+457  common	statmount		sys_statmount			sys_statmount
+458  common	listmount		sys_listmount			sys_listmount
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index 363fae0fe9bf..3103ebd2e4cb 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -459,3 +459,5 @@
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
 456	common	futex_requeue			sys_futex_requeue
+457	common	statmount			sys_statmount
+458	common	listmount			sys_listmount
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index 7bcaa3d5ea44..ba147d7ad19a 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -502,3 +502,5 @@
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
 456	common	futex_requeue			sys_futex_requeue
+457	common	statmount			sys_statmount
+458	common	listmount			sys_listmount
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index c8fac5205803..56e6c2f3ee9c 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -461,3 +461,5 @@
 454	i386	futex_wake		sys_futex_wake
 455	i386	futex_wait		sys_futex_wait
 456	i386	futex_requeue		sys_futex_requeue
+457	i386	statmount		sys_statmount
+458	i386	listmount		sys_listmount
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 8cb8bf68721c..3a22eef585c2 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -378,6 +378,8 @@
 454	common	futex_wake		sys_futex_wake
 455	common	futex_wait		sys_futex_wait
 456	common	futex_requeue		sys_futex_requeue
+457	common	statmount		sys_statmount
+458	common	listmount		sys_listmount
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl
index 06eefa9c1458..497b5d32f457 100644
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -427,3 +427,5 @@
 454	common	futex_wake			sys_futex_wake
 455	common	futex_wait			sys_futex_wait
 456	common	futex_requeue			sys_futex_requeue
+457	common	statmount			sys_statmount
+458	common	listmount			sys_listmount
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 756b013fb832..b67b18e71fbd 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -829,8 +829,14 @@ __SYSCALL(__NR_futex_wait, sys_futex_wait)
 #define __NR_futex_requeue 456
 __SYSCALL(__NR_futex_requeue, sys_futex_requeue)
 
+#define __NR_statmount   457
+__SYSCALL(__NR_statmount, sys_statmount)
+
+#define __NR_listmount   458
+__SYSCALL(__NR_listmount, sys_listmount)
+
 #undef __NR_syscalls
-#define __NR_syscalls 457
+#define __NR_syscalls 459
 
 /*
  * 32 bit systems traditionally used different
-- 
cgit v1.2.3


From 35e27a5744131996061e6e323f1bcb4c827ae867 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Wed, 29 Nov 2023 12:27:15 +0100
Subject: fs: keep struct mnt_id_req extensible

Make it extensible so that we have the liberty to reuse it in future
mount-id based apis. Treat zero size as the first published struct.

Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/namespace.c             | 34 ++++++++++++++++++++++++++++++----
 include/uapi/linux/mount.h |  5 +++++
 2 files changed, 35 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/fs/namespace.c b/fs/namespace.c
index 873185b8a84b..918e8f89ce35 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -4956,6 +4956,30 @@ static int prepare_kstatmount(struct kstatmount *ks, struct mnt_id_req *kreq,
 	return 0;
 }
 
+static int copy_mnt_id_req(const struct mnt_id_req __user *req,
+			   struct mnt_id_req *kreq)
+{
+	int ret;
+	size_t usize;
+
+	BUILD_BUG_ON(sizeof(struct mnt_id_req) != MNT_ID_REQ_SIZE_VER0);
+
+	ret = get_user(usize, &req->size);
+	if (ret)
+		return -EFAULT;
+	if (unlikely(usize > PAGE_SIZE))
+		return -E2BIG;
+	if (unlikely(usize < MNT_ID_REQ_SIZE_VER0))
+		return -EINVAL;
+	memset(kreq, 0, sizeof(*kreq));
+	ret = copy_struct_from_user(kreq, sizeof(*kreq), req, usize);
+	if (ret)
+		return ret;
+	if (kreq->spare != 0)
+		return -EINVAL;
+	return 0;
+}
+
 SYSCALL_DEFINE4(statmount, const struct mnt_id_req __user *, req,
 		struct statmount __user *, buf, size_t, bufsize,
 		unsigned int, flags)
@@ -4970,8 +4994,9 @@ SYSCALL_DEFINE4(statmount, const struct mnt_id_req __user *, req,
 	if (flags)
 		return -EINVAL;
 
-	if (copy_from_user(&kreq, req, sizeof(kreq)))
-		return -EFAULT;
+	ret = copy_mnt_id_req(req, &kreq);
+	if (ret)
+		return ret;
 
 retry:
 	ret = prepare_kstatmount(&ks, &kreq, buf, bufsize, seq_size);
@@ -5052,8 +5077,9 @@ SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req,
 	if (flags)
 		return -EINVAL;
 
-	if (copy_from_user(&kreq, req, sizeof(kreq)))
-		return -EFAULT;
+	ret = copy_mnt_id_req(req, &kreq);
+	if (ret)
+		return ret;
 	mnt_id = kreq.mnt_id;
 	last_mnt_id = kreq.param;
 
diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h
index dc9a0112d819..ad5478dbad00 100644
--- a/include/uapi/linux/mount.h
+++ b/include/uapi/linux/mount.h
@@ -184,10 +184,15 @@ struct statmount {
  * For listmount(2) @param represents the last listed mount id (or zero).
  */
 struct mnt_id_req {
+	__u32 size;
+	__u32 spare;
 	__u64 mnt_id;
 	__u64 param;
 };
 
+/* List of all mnt_id_req versions. */
+#define MNT_ID_REQ_SIZE_VER0	24 /* sizeof first published struct */
+
 /*
  * @mask bits for statmount(2)
  */
-- 
cgit v1.2.3


From d29351e8c20d61a852bbdfcab7bb7166bd916558 Mon Sep 17 00:00:00 2001
From: Daniel Baluta <daniel.baluta@nxp.com>
Date: Tue, 28 Nov 2023 10:11:18 +0200
Subject: ASoC: audio-graph-card2: Introduce playback-only/capture-only DAI
 link flags

We need this to support MICFIL PDM found on i.MX8MP where the DAI link
supports only capture direction.

Signed-off-by: Daniel Baluta <daniel.baluta@nxp.com>
Link: https://msgid.link/r/20231128081119.106360-2-daniel.baluta@oss.nxp.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/simple_card_utils.h     |  3 +++
 sound/soc/generic/audio-graph-card2.c |  6 ++++++
 sound/soc/generic/simple-card-utils.c | 19 +++++++++++++++++++
 3 files changed, 28 insertions(+)

(limited to 'include')

diff --git a/include/sound/simple_card_utils.h b/include/sound/simple_card_utils.h
index e5da10b4c43b..ad67957b7b48 100644
--- a/include/sound/simple_card_utils.h
+++ b/include/sound/simple_card_utils.h
@@ -195,6 +195,9 @@ int graph_util_is_ports0(struct device_node *port);
 int graph_util_parse_dai(struct device *dev, struct device_node *ep,
 			 struct snd_soc_dai_link_component *dlc, int *is_single_link);
 
+int graph_util_parse_link_direction(struct device_node *np,
+				    bool *is_playback_only, bool *is_capture_only);
+
 #ifdef DEBUG
 static inline void simple_util_debug_dai(struct simple_util_priv *priv,
 					 char *name,
diff --git a/sound/soc/generic/audio-graph-card2.c b/sound/soc/generic/audio-graph-card2.c
index 78d9679decda..f880a7f73522 100644
--- a/sound/soc/generic/audio-graph-card2.c
+++ b/sound/soc/generic/audio-graph-card2.c
@@ -760,6 +760,7 @@ static void graph_link_init(struct simple_util_priv *priv,
 	struct device_node *ep;
 	struct device_node *ports;
 	unsigned int daifmt = 0, daiclk = 0;
+	bool playback_only = 0, capture_only = 0;
 	unsigned int bit_frame = 0;
 
 	if (graph_lnk_is_multi(port)) {
@@ -798,6 +799,11 @@ static void graph_link_init(struct simple_util_priv *priv,
 	if (is_cpu_node)
 		daiclk = snd_soc_daifmt_clock_provider_flipped(daiclk);
 
+	graph_util_parse_link_direction(port, &playback_only, &capture_only);
+
+	dai_link->playback_only = playback_only;
+	dai_link->capture_only = capture_only;
+
 	dai_link->dai_fmt	= daifmt | daiclk;
 	dai_link->init		= simple_util_dai_init;
 	dai_link->ops		= &graph_ops;
diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c
index cfa70a56ff0f..9006ef5e95f5 100644
--- a/sound/soc/generic/simple-card-utils.c
+++ b/sound/soc/generic/simple-card-utils.c
@@ -1129,6 +1129,25 @@ parse_dai_end:
 }
 EXPORT_SYMBOL_GPL(graph_util_parse_dai);
 
+int graph_util_parse_link_direction(struct device_node *np,
+				    bool *playback_only, bool *capture_only)
+{
+	bool is_playback_only = false;
+	bool is_capture_only = false;
+
+	is_playback_only = of_property_read_bool(np, "playback-only");
+	is_capture_only = of_property_read_bool(np, "capture-only");
+
+	if (is_playback_only && is_capture_only)
+		return -EINVAL;
+
+	*playback_only = is_playback_only;
+	*capture_only = is_capture_only;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(graph_util_parse_link_direction);
+
 /* Module information */
 MODULE_AUTHOR("Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>");
 MODULE_DESCRIPTION("ALSA SoC Simple Card Utils");
-- 
cgit v1.2.3


From 05b234565e02ec51df75ec48eb7370e64ed05e04 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 12 Dec 2023 20:35:58 -0800
Subject: wifi: cfg80211: fix spelling & punctutation

Correct spelling and run-on sentences.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: linux-wireless@vger.kernel.org
Cc: Kalle Valo <kvalo@kernel.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Link: https://msgid.link/20231213043558.10409-1-rdunlap@infradead.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 4d6b9d801c2f..602960dafe0f 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -52,7 +52,7 @@
  * such wiphy can have zero, one, or many virtual interfaces associated with
  * it, which need to be identified as such by pointing the network interface's
  * @ieee80211_ptr pointer to a &struct wireless_dev which further describes
- * the wireless part of the interface, normally this struct is embedded in the
+ * the wireless part of the interface. Normally this struct is embedded in the
  * network interface's private data area. Drivers can optionally allow creating
  * or destroying virtual interfaces on the fly, but without at least one or the
  * ability to create some the wireless device isn't useful.
@@ -2584,7 +2584,7 @@ struct cfg80211_scan_info {
  * @short_ssid: short ssid to scan for
  * @bssid: bssid to scan for
  * @channel_idx: idx of the channel in the channel array in the scan request
- *	 which the above info relvant to
+ *	 which the above info is relevant to
  * @unsolicited_probe: the AP transmits unsolicited probe response every 20 TU
  * @short_ssid_valid: @short_ssid is valid and can be used
  * @psc_no_listen: when set, and the channel is a PSC channel, no need to wait
@@ -7504,7 +7504,7 @@ void cfg80211_notify_new_peer_candidate(struct net_device *dev,
  * RFkill integration in cfg80211 is almost invisible to drivers,
  * as cfg80211 automatically registers an rfkill instance for each
  * wireless device it knows about. Soft kill is also translated
- * into disconnecting and turning all interfaces off, drivers are
+ * into disconnecting and turning all interfaces off. Drivers are
  * expected to turn off the device when all interfaces are down.
  *
  * However, devices may have a hard RFkill line, in which case they
@@ -7552,7 +7552,7 @@ static inline void wiphy_rfkill_stop_polling(struct wiphy *wiphy)
  * the configuration mechanism.
  *
  * A driver supporting vendor commands must register them as an array
- * in struct wiphy, with handlers for each one, each command has an
+ * in struct wiphy, with handlers for each one. Each command has an
  * OUI and sub command ID to identify it.
  *
  * Note that this feature should not be (ab)used to implement protocol
@@ -7716,7 +7716,7 @@ static inline void cfg80211_vendor_event(struct sk_buff *skb, gfp_t gfp)
  * interact with driver-specific tools to aid, for instance,
  * factory programming.
  *
- * This chapter describes how drivers interact with it, for more
+ * This chapter describes how drivers interact with it. For more
  * information see the nl80211 book's chapter on it.
  */
 
-- 
cgit v1.2.3


From 074b3cf442c518631f4b6d11d7fdfe143e17e955 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 12 Dec 2023 20:43:15 -0800
Subject: wifi: nl80211: fix grammar & spellos

Correct spelling as reported by codespell.
Correct run-on sentences and other grammar issues.
Add hyphenation of adjectives.
Correct some punctuation.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: linux-wireless@vger.kernel.org
Cc: Kalle Valo <kvalo@kernel.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Link: https://msgid.link/20231213044315.19459-1-rdunlap@infradead.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/uapi/linux/nl80211.h | 74 ++++++++++++++++++++++----------------------
 1 file changed, 37 insertions(+), 37 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 2d8468cbc457..a682b54bd3ba 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -72,7 +72,7 @@
  * For drivers supporting TDLS with external setup (WIPHY_FLAG_SUPPORTS_TDLS
  * and WIPHY_FLAG_TDLS_EXTERNAL_SETUP), the station lifetime is as follows:
  *  - a setup station entry is added, not yet authorized, without any rate
- *    or capability information, this just exists to avoid race conditions
+ *    or capability information; this just exists to avoid race conditions
  *  - when the TDLS setup is done, a single NL80211_CMD_SET_STATION is valid
  *    to add rate and capability information to the station and at the same
  *    time mark it authorized.
@@ -87,7 +87,7 @@
  * DOC: Frame transmission/registration support
  *
  * Frame transmission and registration support exists to allow userspace
- * management entities such as wpa_supplicant react to management frames
+ * management entities such as wpa_supplicant to react to management frames
  * that are not being handled by the kernel. This includes, for example,
  * certain classes of action frames that cannot be handled in the kernel
  * for various reasons.
@@ -113,7 +113,7 @@
  *
  * Frame transmission allows userspace to send for example the required
  * responses to action frames. It is subject to some sanity checking,
- * but many frames can be transmitted. When a frame was transmitted, its
+ * but many frames can be transmitted. When a frame is transmitted, its
  * status is indicated to the sending socket.
  *
  * For more technical details, see the corresponding command descriptions
@@ -123,7 +123,7 @@
 /**
  * DOC: Virtual interface / concurrency capabilities
  *
- * Some devices are able to operate with virtual MACs, they can have
+ * Some devices are able to operate with virtual MACs; they can have
  * more than one virtual interface. The capability handling for this
  * is a bit complex though, as there may be a number of restrictions
  * on the types of concurrency that are supported.
@@ -135,7 +135,7 @@
  * Once concurrency is desired, more attributes must be observed:
  * To start with, since some interface types are purely managed in
  * software, like the AP-VLAN type in mac80211 for example, there's
- * an additional list of these, they can be added at any time and
+ * an additional list of these; they can be added at any time and
  * are only restricted by some semantic restrictions (e.g. AP-VLAN
  * cannot be added without a corresponding AP interface). This list
  * is exported in the %NL80211_ATTR_SOFTWARE_IFTYPES attribute.
@@ -164,7 +164,7 @@
  * Packet coalesce feature helps to reduce number of received interrupts
  * to host by buffering these packets in firmware/hardware for some
  * predefined time. Received interrupt will be generated when one of the
- * following events occur.
+ * following events occurs.
  * a) Expiration of hardware timer whose expiration time is set to maximum
  * coalescing delay of matching coalesce rule.
  * b) Coalescing buffer in hardware reaches its limit.
@@ -174,7 +174,7 @@
  * rule.
  * a) Maximum coalescing delay
  * b) List of packet patterns which needs to be matched
- * c) Condition for coalescence. pattern 'match' or 'no match'
+ * c) Condition for coalescence: pattern 'match' or 'no match'
  * Multiple such rules can be created.
  */
 
@@ -213,7 +213,7 @@
 /**
  * DOC: FILS shared key authentication offload
  *
- * FILS shared key authentication offload can be advertized by drivers by
+ * FILS shared key authentication offload can be advertised by drivers by
  * setting @NL80211_EXT_FEATURE_FILS_SK_OFFLOAD flag. The drivers that support
  * FILS shared key authentication offload should be able to construct the
  * authentication and association frames for FILS shared key authentication and
@@ -239,7 +239,7 @@
  * The PMKSA can be maintained in userspace persistently so that it can be used
  * later after reboots or wifi turn off/on also.
  *
- * %NL80211_ATTR_FILS_CACHE_ID is the cache identifier advertized by a FILS
+ * %NL80211_ATTR_FILS_CACHE_ID is the cache identifier advertised by a FILS
  * capable AP supporting PMK caching. It specifies the scope within which the
  * PMKSAs are cached in an ESS. %NL80211_CMD_SET_PMKSA and
  * %NL80211_CMD_DEL_PMKSA are enhanced to allow support for PMKSA caching based
@@ -290,12 +290,12 @@
  * If the configuration needs to be applied for specific peer then the MAC
  * address of the peer needs to be passed in %NL80211_ATTR_MAC, otherwise the
  * configuration will be applied for all the connected peers in the vif except
- * any peers that have peer specific configuration for the TID by default; if
- * the %NL80211_TID_CONFIG_ATTR_OVERRIDE flag is set, peer specific values
+ * any peers that have peer-specific configuration for the TID by default; if
+ * the %NL80211_TID_CONFIG_ATTR_OVERRIDE flag is set, peer-specific values
  * will be overwritten.
  *
- * All this configuration is valid only for STA's current connection
- * i.e. the configuration will be reset to default when the STA connects back
+ * All this configuration is valid only for STA's current connection,
+ * i.e., the configuration will be reset to default when the STA connects back
  * after disconnection/roaming, and this configuration will be cleared when
  * the interface goes down.
  */
@@ -521,7 +521,7 @@
  *	%NL80211_ATTR_SCHED_SCAN_PLANS. If %NL80211_ATTR_SCHED_SCAN_PLANS is
  *	not specified and only %NL80211_ATTR_SCHED_SCAN_INTERVAL is specified,
  *	scheduled scan will run in an infinite loop with the specified interval.
- *	These attributes are mutually exculsive,
+ *	These attributes are mutually exclusive,
  *	i.e. NL80211_ATTR_SCHED_SCAN_INTERVAL must not be passed if
  *	NL80211_ATTR_SCHED_SCAN_PLANS is defined.
  *	If for some reason scheduled scan is aborted by the driver, all scan
@@ -552,7 +552,7 @@
  *	%NL80211_CMD_STOP_SCHED_SCAN command is received or when the interface
  *	is brought down while a scheduled scan was running.
  *
- * @NL80211_CMD_GET_SURVEY: get survey resuls, e.g. channel occupation
+ * @NL80211_CMD_GET_SURVEY: get survey results, e.g. channel occupation
  *      or noise level
  * @NL80211_CMD_NEW_SURVEY_RESULTS: survey data notification (as a reply to
  *	NL80211_CMD_GET_SURVEY and on the "scan" multicast group)
@@ -563,7 +563,7 @@
  *	using %NL80211_ATTR_SSID, %NL80211_ATTR_FILS_CACHE_ID,
  *	%NL80211_ATTR_PMKID, and %NL80211_ATTR_PMK in case of FILS
  *	authentication where %NL80211_ATTR_FILS_CACHE_ID is the identifier
- *	advertized by a FILS capable AP identifying the scope of PMKSA in an
+ *	advertised by a FILS capable AP identifying the scope of PMKSA in an
  *	ESS.
  * @NL80211_CMD_DEL_PMKSA: Delete a PMKSA cache entry, using %NL80211_ATTR_MAC
  *	(for the BSSID) and %NL80211_ATTR_PMKID or using %NL80211_ATTR_SSID,
@@ -608,7 +608,7 @@
  *	BSSID in case of station mode). %NL80211_ATTR_SSID is used to specify
  *	the SSID (mainly for association, but is included in authentication
  *	request, too, to help BSS selection. %NL80211_ATTR_WIPHY_FREQ +
- *	%NL80211_ATTR_WIPHY_FREQ_OFFSET is used to specify the frequence of the
+ *	%NL80211_ATTR_WIPHY_FREQ_OFFSET is used to specify the frequency of the
  *	channel in MHz. %NL80211_ATTR_AUTH_TYPE is used to specify the
  *	authentication type. %NL80211_ATTR_IE is used to define IEs
  *	(VendorSpecificInfo, but also including RSN IE and FT IEs) to be added
@@ -817,7 +817,7 @@
  *	reached.
  * @NL80211_CMD_SET_CHANNEL: Set the channel (using %NL80211_ATTR_WIPHY_FREQ
  *	and the attributes determining channel width) the given interface
- *	(identifed by %NL80211_ATTR_IFINDEX) shall operate on.
+ *	(identified by %NL80211_ATTR_IFINDEX) shall operate on.
  *	In case multiple channels are supported by the device, the mechanism
  *	with which it switches channels is implementation-defined.
  *	When a monitor interface is given, it can only switch channel while
@@ -889,7 +889,7 @@
  *	inform userspace of the new replay counter.
  *
  * @NL80211_CMD_PMKSA_CANDIDATE: This is used as an event to inform userspace
- *	of PMKSA caching dandidates.
+ *	of PMKSA caching candidates.
  *
  * @NL80211_CMD_TDLS_OPER: Perform a high-level TDLS command (e.g. link setup).
  *	In addition, this can be used as an event to request userspace to take
@@ -925,7 +925,7 @@
  *
  * @NL80211_CMD_PROBE_CLIENT: Probe an associated station on an AP interface
  *	by sending a null data frame to it and reporting when the frame is
- *	acknowleged. This is used to allow timing out inactive clients. Uses
+ *	acknowledged. This is used to allow timing out inactive clients. Uses
  *	%NL80211_ATTR_IFINDEX and %NL80211_ATTR_MAC. The command returns a
  *	direct reply with an %NL80211_ATTR_COOKIE that is later used to match
  *	up the event with the request. The event includes the same data and
@@ -1847,7 +1847,7 @@ enum nl80211_commands {
  *	using %CMD_CONTROL_PORT_FRAME.  If control port routing over NL80211 is
  *	to be used then userspace must also use the %NL80211_ATTR_SOCKET_OWNER
  *	flag. When used with %NL80211_ATTR_CONTROL_PORT_NO_PREAUTH, pre-auth
- *	frames are not forwared over the control port.
+ *	frames are not forwarded over the control port.
  *
  * @NL80211_ATTR_TESTDATA: Testmode data blob, passed through to the driver.
  *	We recommend using nested, driver-specific attributes within this.
@@ -1984,10 +1984,10 @@ enum nl80211_commands {
  *	bit. Depending on which antennas are selected in the bitmap, 802.11n
  *	drivers can derive which chainmasks to use (if all antennas belonging to
  *	a particular chain are disabled this chain should be disabled) and if
- *	a chain has diversity antennas wether diversity should be used or not.
+ *	a chain has diversity antennas whether diversity should be used or not.
  *	HT capabilities (STBC, TX Beamforming, Antenna selection) can be
  *	derived from the available chains after applying the antenna mask.
- *	Non-802.11n drivers can derive wether to use diversity or not.
+ *	Non-802.11n drivers can derive whether to use diversity or not.
  *	Drivers may reject configurations or RX/TX mask combinations they cannot
  *	support by returning -EINVAL.
  *
@@ -2557,7 +2557,7 @@ enum nl80211_commands {
  *	from successful FILS authentication and is used with
  *	%NL80211_CMD_CONNECT.
  *
- * @NL80211_ATTR_FILS_CACHE_ID: A 2-octet identifier advertized by a FILS AP
+ * @NL80211_ATTR_FILS_CACHE_ID: A 2-octet identifier advertised by a FILS AP
  *	identifying the scope of PMKSAs. This is used with
  *	@NL80211_CMD_SET_PMKSA and @NL80211_CMD_DEL_PMKSA.
  *
@@ -4200,7 +4200,7 @@ enum nl80211_wmm_rule {
  *	(100 * dBm).
  * @NL80211_FREQUENCY_ATTR_DFS_STATE: current state for DFS
  *	(enum nl80211_dfs_state)
- * @NL80211_FREQUENCY_ATTR_DFS_TIME: time in miliseconds for how long
+ * @NL80211_FREQUENCY_ATTR_DFS_TIME: time in milliseconds for how long
  *	this channel is in this DFS state.
  * @NL80211_FREQUENCY_ATTR_NO_HT40_MINUS: HT40- isn't possible with this
  *	channel as the control channel
@@ -5518,7 +5518,7 @@ enum nl80211_tx_rate_setting {
  *	(%NL80211_TID_CONFIG_ATTR_TIDS, %NL80211_TID_CONFIG_ATTR_OVERRIDE).
  * @NL80211_TID_CONFIG_ATTR_PEER_SUPP: same as the previous per-vif one, but
  *	per peer instead.
- * @NL80211_TID_CONFIG_ATTR_OVERRIDE: flag attribue, if set indicates
+ * @NL80211_TID_CONFIG_ATTR_OVERRIDE: flag attribute, if set indicates
  *	that the new configuration overrides all previous peer
  *	configurations, otherwise previous peer specific configurations
  *	should be left untouched.
@@ -5901,7 +5901,7 @@ enum nl80211_attr_coalesce_rule {
 
 /**
  * enum nl80211_coalesce_condition - coalesce rule conditions
- * @NL80211_COALESCE_CONDITION_MATCH: coalaesce Rx packets when patterns
+ * @NL80211_COALESCE_CONDITION_MATCH: coalesce Rx packets when patterns
  *	in a rule are matched.
  * @NL80211_COALESCE_CONDITION_NO_MATCH: coalesce Rx packets when patterns
  *	in a rule are not matched.
@@ -6000,7 +6000,7 @@ enum nl80211_if_combination_attrs {
  * enum nl80211_plink_state - state of a mesh peer link finite state machine
  *
  * @NL80211_PLINK_LISTEN: initial state, considered the implicit
- *	state of non existent mesh peer links
+ *	state of non-existent mesh peer links
  * @NL80211_PLINK_OPN_SNT: mesh plink open frame has been sent to
  *	this mesh peer
  * @NL80211_PLINK_OPN_RCVD: mesh plink open frame has been received
@@ -6293,7 +6293,7 @@ enum nl80211_feature_flags {
  *	request to use RRM (see %NL80211_ATTR_USE_RRM) with
  *	%NL80211_CMD_ASSOCIATE and %NL80211_CMD_CONNECT requests, which will set
  *	the ASSOC_REQ_USE_RRM flag in the association request even if
- *	NL80211_FEATURE_QUIET is not advertized.
+ *	NL80211_FEATURE_QUIET is not advertised.
  * @NL80211_EXT_FEATURE_MU_MIMO_AIR_SNIFFER: This device supports MU-MIMO air
  *	sniffer which means that it can be configured to hear packets from
  *	certain groups which can be configured by the
@@ -6305,7 +6305,7 @@ enum nl80211_feature_flags {
  *	the BSS that the interface that requested the scan is connected to
  *	(if available).
  * @NL80211_EXT_FEATURE_BSS_PARENT_TSF: Per BSS, this driver reports the
- *	time the last beacon/probe was received. For a non MLO connection, the
+ *	time the last beacon/probe was received. For a non-MLO connection, the
  *	time is the TSF of the BSS that the interface that requested the scan is
  *	connected to (if available). For an MLO connection, the time is the TSF
  *	of the BSS corresponding with link ID specified in the scan request (if
@@ -6313,7 +6313,7 @@ enum nl80211_feature_flags {
  * @NL80211_EXT_FEATURE_SET_SCAN_DWELL: This driver supports configuration of
  *	channel dwell time.
  * @NL80211_EXT_FEATURE_BEACON_RATE_LEGACY: Driver supports beacon rate
- *	configuration (AP/mesh), supporting a legacy (non HT/VHT) rate.
+ *	configuration (AP/mesh), supporting a legacy (non-HT/VHT) rate.
  * @NL80211_EXT_FEATURE_BEACON_RATE_HT: Driver supports beacon rate
  *	configuration (AP/mesh) with HT rates.
  * @NL80211_EXT_FEATURE_BEACON_RATE_VHT: Driver supports beacon rate
@@ -6649,7 +6649,7 @@ enum nl80211_timeout_reason {
  *	request parameters IE in the probe request
  * @NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP: accept broadcast probe responses
  * @NL80211_SCAN_FLAG_OCE_PROBE_REQ_HIGH_TX_RATE: send probe request frames at
- *	rate of at least 5.5M. In case non OCE AP is discovered in the channel,
+ *	rate of at least 5.5M. In case non-OCE AP is discovered in the channel,
  *	only the first probe req in the channel will be sent in high rate.
  * @NL80211_SCAN_FLAG_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION: allow probe request
  *	tx deferral (dot11FILSProbeDelay shall be set to 15ms)
@@ -6685,7 +6685,7 @@ enum nl80211_timeout_reason {
  *	received on the 2.4/5 GHz channels to actively scan only the 6GHz
  *	channels on which APs are expected to be found. Note that when not set,
  *	the scan logic would scan all 6GHz channels, but since transmission of
- *	probe requests on non PSC channels is limited, it is highly likely that
+ *	probe requests on non-PSC channels is limited, it is highly likely that
  *	these channels would passively be scanned. Also note that when the flag
  *	is set, in addition to the colocated APs, PSC channels would also be
  *	scanned if the user space has asked for it.
@@ -7017,7 +7017,7 @@ enum nl80211_nan_func_term_reason {
  *	The instance ID for the follow up Service Discovery Frame. This is u8.
  * @NL80211_NAN_FUNC_FOLLOW_UP_REQ_ID: relevant if the function's type
  *	is follow up. This is a u8.
- *	The requestor instance ID for the follow up Service Discovery Frame.
+ *	The requester instance ID for the follow up Service Discovery Frame.
  * @NL80211_NAN_FUNC_FOLLOW_UP_DEST: the MAC address of the recipient of the
  *	follow up Service Discovery Frame. This is a binary attribute.
  * @NL80211_NAN_FUNC_CLOSE_RANGE: is this function limited for devices in a
@@ -7407,7 +7407,7 @@ enum nl80211_peer_measurement_attrs {
  * @NL80211_PMSR_FTM_CAPA_ATTR_TRIGGER_BASED: flag attribute indicating if
  *	trigger based ranging measurement is supported
  * @NL80211_PMSR_FTM_CAPA_ATTR_NON_TRIGGER_BASED: flag attribute indicating
- *	if non trigger based ranging measurement is supported
+ *	if non-trigger-based ranging measurement is supported
  *
  * @NUM_NL80211_PMSR_FTM_CAPA_ATTR: internal
  * @NL80211_PMSR_FTM_CAPA_ATTR_MAX: highest attribute number
@@ -7461,7 +7461,7 @@ enum nl80211_peer_measurement_ftm_capa {
  *      if neither %NL80211_PMSR_FTM_REQ_ATTR_TRIGGER_BASED nor
  *	%NL80211_PMSR_FTM_REQ_ATTR_NON_TRIGGER_BASED is set, EDCA based
  *	ranging will be used.
- * @NL80211_PMSR_FTM_REQ_ATTR_NON_TRIGGER_BASED: request non trigger based
+ * @NL80211_PMSR_FTM_REQ_ATTR_NON_TRIGGER_BASED: request non-trigger-based
  *	ranging measurement (flag)
  *	This attribute and %NL80211_PMSR_FTM_REQ_ATTR_TRIGGER_BASED are
  *	mutually exclusive.
@@ -7539,7 +7539,7 @@ enum nl80211_peer_measurement_ftm_failure_reasons {
  * @NL80211_PMSR_FTM_RESP_ATTR_NUM_FTMR_ATTEMPTS: number of FTM Request frames
  *	transmitted (u32, optional)
  * @NL80211_PMSR_FTM_RESP_ATTR_NUM_FTMR_SUCCESSES: number of FTM Request frames
- *	that were acknowleged (u32, optional)
+ *	that were acknowledged (u32, optional)
  * @NL80211_PMSR_FTM_RESP_ATTR_BUSY_RETRY_TIME: retry time received from the
  *	busy peer (u32, seconds)
  * @NL80211_PMSR_FTM_RESP_ATTR_NUM_BURSTS_EXP: actual number of bursts exponent
-- 
cgit v1.2.3


From 04d25ccea2b3199269b7e500da33023b51418fde Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 12 Dec 2023 20:37:35 -0800
Subject: net, xdp: Correct grammar

Use the correct verb form in 2 places in the XDP rx-queue comment.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Link: https://lore.kernel.org/bpf/20231213043735.30208-1-rdunlap@infradead.org
---
 include/net/xdp.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/xdp.h b/include/net/xdp.h
index 8cd04a74dba5..e6770dd40c91 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -16,7 +16,7 @@
  *
  * The XDP RX-queue info (xdp_rxq_info) is associated with the driver
  * level RX-ring queues.  It is information that is specific to how
- * the driver have configured a given RX-ring queue.
+ * the driver has configured a given RX-ring queue.
  *
  * Each xdp_buff frame received in the driver carries a (pointer)
  * reference to this xdp_rxq_info structure.  This provides the XDP
@@ -32,7 +32,7 @@
  * The struct is not directly tied to the XDP prog.  A new XDP prog
  * can be attached as long as it doesn't change the underlying
  * RX-ring.  If the RX-ring does change significantly, the NIC driver
- * naturally need to stop the RX-ring before purging and reallocating
+ * naturally needs to stop the RX-ring before purging and reallocating
  * memory.  In that process the driver MUST call unregister (which
  * also applies for driver shutdown and unload).  The register API is
  * also mandatory during RX-ring setup.
-- 
cgit v1.2.3


From 6872a189be508b9383bc081d462a5d99cbb8319d Mon Sep 17 00:00:00 2001
From: Joshua Ashton <joshua@froggi.es>
Date: Thu, 16 Nov 2023 18:58:12 -0100
Subject: drm/amd/display: Add 3x4 CTM support for plane CTM

Create drm_color_ctm_3x4 to support 3x4-dimension plane CTM matrix and
convert DRM CTM to DC CSC float matrix.

v3:
- rename ctm2 to ctm_3x4 (Harry)

Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Joshua Ashton <joshua@froggi.es>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/amdgpu_dm/amdgpu_dm_color.c    | 28 +++++++++++++++++++---
 .../drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c    |  2 +-
 include/uapi/drm/drm_mode.h                        |  8 +++++++
 3 files changed, 34 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
index d52c3333ea13..96aecc1a71a3 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
@@ -434,6 +434,28 @@ static void __drm_ctm_to_dc_matrix(const struct drm_color_ctm *ctm,
 	}
 }
 
+/**
+ * __drm_ctm_3x4_to_dc_matrix - converts a DRM CTM 3x4 to a DC CSC float matrix
+ * @ctm: DRM color transformation matrix with 3x4 dimensions
+ * @matrix: DC CSC float matrix
+ *
+ * The matrix needs to be a 3x4 (12 entry) matrix.
+ */
+static void __drm_ctm_3x4_to_dc_matrix(const struct drm_color_ctm_3x4 *ctm,
+				       struct fixed31_32 *matrix)
+{
+	int i;
+
+	/* The format provided is S31.32, using signed-magnitude representation.
+	 * Our fixed31_32 is also S31.32, but is using 2's complement. We have
+	 * to convert from signed-magnitude to 2's complement.
+	 */
+	for (i = 0; i < 12; i++) {
+		/* gamut_remap_matrix[i] = ctm[i - floor(i/4)] */
+		matrix[i] = dc_fixpt_from_s3132(ctm->matrix[i]);
+	}
+}
+
 /**
  * __set_legacy_tf - Calculates the legacy transfer function
  * @func: transfer function
@@ -1173,7 +1195,7 @@ int amdgpu_dm_update_plane_color_mgmt(struct dm_crtc_state *crtc,
 {
 	struct amdgpu_device *adev = drm_to_adev(crtc->base.state->dev);
 	struct dm_plane_state *dm_plane_state = to_dm_plane_state(plane_state);
-	struct drm_color_ctm *ctm = NULL;
+	struct drm_color_ctm_3x4 *ctm = NULL;
 	struct dc_color_caps *color_caps = NULL;
 	bool has_crtc_cm_degamma;
 	int ret;
@@ -1228,7 +1250,7 @@ int amdgpu_dm_update_plane_color_mgmt(struct dm_crtc_state *crtc,
 
 	/* Setup CRTC CTM. */
 	if (dm_plane_state->ctm) {
-		ctm = (struct drm_color_ctm *)dm_plane_state->ctm->data;
+		ctm = (struct drm_color_ctm_3x4 *)dm_plane_state->ctm->data;
 		/*
 		 * DCN2 and older don't support both pre-blending and
 		 * post-blending gamut remap. For this HW family, if we have
@@ -1240,7 +1262,7 @@ int amdgpu_dm_update_plane_color_mgmt(struct dm_crtc_state *crtc,
 		 * mapping CRTC CTM to MPC and keeping plane CTM setup at DPP,
 		 * as it's done by dcn30_program_gamut_remap().
 		 */
-		__drm_ctm_to_dc_matrix(ctm, dc_plane_state->gamut_remap_matrix.matrix);
+		__drm_ctm_3x4_to_dc_matrix(ctm, dc_plane_state->gamut_remap_matrix.matrix);
 
 		dc_plane_state->gamut_remap_matrix.enable_remap = true;
 		dc_plane_state->input_csc_color_matrix.enable_adjustment = false;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
index f10c5154d06a..8a4c40b4c27e 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
@@ -1561,7 +1561,7 @@ dm_atomic_plane_set_property(struct drm_plane *plane,
 		ret = drm_property_replace_blob_from_id(plane->dev,
 							&dm_plane_state->ctm,
 							val,
-							sizeof(struct drm_color_ctm), -1,
+							sizeof(struct drm_color_ctm_3x4), -1,
 							&replaced);
 		dm_plane_state->base.color_mgmt_changed |= replaced;
 		return ret;
diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h
index 95630f170110..39d9ac0c0a80 100644
--- a/include/uapi/drm/drm_mode.h
+++ b/include/uapi/drm/drm_mode.h
@@ -846,6 +846,14 @@ struct drm_color_ctm {
 	__u64 matrix[9];
 };
 
+struct drm_color_ctm_3x4 {
+	/*
+	 * Conversion matrix with 3x4 dimensions in S31.32 sign-magnitude
+	 * (not two's complement!) format.
+	 */
+	__u64 matrix[12];
+};
+
 struct drm_color_lut {
 	/*
 	 * Values are mapped linearly to 0.0 - 1.0 range, with 0x0 == 0.0 and
-- 
cgit v1.2.3


From 8f0ec8c681755f523cf842bfe350ea40609b83a9 Mon Sep 17 00:00:00 2001
From: Daniel Xu <dxu@dxuuu.xyz>
Date: Thu, 14 Dec 2023 15:49:02 -0700
Subject: bpf: xfrm: Add bpf_xdp_get_xfrm_state() kfunc

This commit adds an unstable kfunc helper to access internal xfrm_state
associated with an SA. This is intended to be used for the upcoming
IPsec pcpu work to assign special pcpu SAs to a particular CPU. In other
words: for custom software RSS.

That being said, the function that this kfunc wraps is fairly generic
and used for a lot of xfrm tasks. I'm sure people will find uses
elsewhere over time.

This commit also adds a corresponding bpf_xdp_xfrm_state_release() kfunc
to release the refcnt acquired by bpf_xdp_get_xfrm_state(). The verifier
will require that all acquired xfrm_state's are released.

Co-developed-by: Antony Antony <antony.antony@secunet.com>
Signed-off-by: Antony Antony <antony.antony@secunet.com>
Acked-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: Daniel Xu <dxu@dxuuu.xyz>
Link: https://lore.kernel.org/r/a29699c42f5fad456b875c98dd11c6afc3ffb707.1702593901.git.dxu@dxuuu.xyz
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/net/xfrm.h        |   9 ++++
 net/xfrm/Makefile         |   1 +
 net/xfrm/xfrm_policy.c    |   2 +
 net/xfrm/xfrm_state_bpf.c | 134 ++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 146 insertions(+)
 create mode 100644 net/xfrm/xfrm_state_bpf.c

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index c9bb0f892f55..1d107241b901 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -2190,4 +2190,13 @@ static inline int register_xfrm_interface_bpf(void)
 
 #endif
 
+#if IS_ENABLED(CONFIG_DEBUG_INFO_BTF)
+int register_xfrm_state_bpf(void);
+#else
+static inline int register_xfrm_state_bpf(void)
+{
+	return 0;
+}
+#endif
+
 #endif	/* _NET_XFRM_H */
diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile
index cd47f88921f5..547cec77ba03 100644
--- a/net/xfrm/Makefile
+++ b/net/xfrm/Makefile
@@ -21,3 +21,4 @@ obj-$(CONFIG_XFRM_USER_COMPAT) += xfrm_compat.o
 obj-$(CONFIG_XFRM_IPCOMP) += xfrm_ipcomp.o
 obj-$(CONFIG_XFRM_INTERFACE) += xfrm_interface.o
 obj-$(CONFIG_XFRM_ESPINTCP) += espintcp.o
+obj-$(CONFIG_DEBUG_INFO_BTF) += xfrm_state_bpf.o
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index c13dc3ef7910..1b7e75159727 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -4218,6 +4218,8 @@ void __init xfrm_init(void)
 #ifdef CONFIG_XFRM_ESPINTCP
 	espintcp_init();
 #endif
+
+	register_xfrm_state_bpf();
 }
 
 #ifdef CONFIG_AUDITSYSCALL
diff --git a/net/xfrm/xfrm_state_bpf.c b/net/xfrm/xfrm_state_bpf.c
new file mode 100644
index 000000000000..9e20d4a377f7
--- /dev/null
+++ b/net/xfrm/xfrm_state_bpf.c
@@ -0,0 +1,134 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Unstable XFRM state BPF helpers.
+ *
+ * Note that it is allowed to break compatibility for these functions since the
+ * interface they are exposed through to BPF programs is explicitly unstable.
+ */
+
+#include <linux/bpf.h>
+#include <linux/btf.h>
+#include <linux/btf_ids.h>
+#include <net/xdp.h>
+#include <net/xfrm.h>
+
+/* bpf_xfrm_state_opts - Options for XFRM state lookup helpers
+ *
+ * Members:
+ * @error      - Out parameter, set for any errors encountered
+ *		 Values:
+ *		   -EINVAL - netns_id is less than -1
+ *		   -EINVAL - opts__sz isn't BPF_XFRM_STATE_OPTS_SZ
+ *		   -ENONET - No network namespace found for netns_id
+ *		   -ENOENT - No xfrm_state found
+ * @netns_id	- Specify the network namespace for lookup
+ *		 Values:
+ *		   BPF_F_CURRENT_NETNS (-1)
+ *		     Use namespace associated with ctx
+ *		   [0, S32_MAX]
+ *		     Network Namespace ID
+ * @mark	- XFRM mark to match on
+ * @daddr	- Destination address to match on
+ * @spi		- Security parameter index to match on
+ * @proto	- IP protocol to match on (eg. IPPROTO_ESP)
+ * @family	- Protocol family to match on (AF_INET/AF_INET6)
+ */
+struct bpf_xfrm_state_opts {
+	s32 error;
+	s32 netns_id;
+	u32 mark;
+	xfrm_address_t daddr;
+	__be32 spi;
+	u8 proto;
+	u16 family;
+};
+
+enum {
+	BPF_XFRM_STATE_OPTS_SZ = sizeof(struct bpf_xfrm_state_opts),
+};
+
+__bpf_kfunc_start_defs();
+
+/* bpf_xdp_get_xfrm_state - Get XFRM state
+ *
+ * A `struct xfrm_state *`, if found, must be released with a corresponding
+ * bpf_xdp_xfrm_state_release.
+ *
+ * Parameters:
+ * @ctx	- Pointer to ctx (xdp_md) in XDP program
+ *		    Cannot be NULL
+ * @opts	- Options for lookup (documented above)
+ *		    Cannot be NULL
+ * @opts__sz	- Length of the bpf_xfrm_state_opts structure
+ *		    Must be BPF_XFRM_STATE_OPTS_SZ
+ */
+__bpf_kfunc struct xfrm_state *
+bpf_xdp_get_xfrm_state(struct xdp_md *ctx, struct bpf_xfrm_state_opts *opts, u32 opts__sz)
+{
+	struct xdp_buff *xdp = (struct xdp_buff *)ctx;
+	struct net *net = dev_net(xdp->rxq->dev);
+	struct xfrm_state *x;
+
+	if (!opts || opts__sz < sizeof(opts->error))
+		return NULL;
+
+	if (opts__sz != BPF_XFRM_STATE_OPTS_SZ) {
+		opts->error = -EINVAL;
+		return NULL;
+	}
+
+	if (unlikely(opts->netns_id < BPF_F_CURRENT_NETNS)) {
+		opts->error = -EINVAL;
+		return NULL;
+	}
+
+	if (opts->netns_id >= 0) {
+		net = get_net_ns_by_id(net, opts->netns_id);
+		if (unlikely(!net)) {
+			opts->error = -ENONET;
+			return NULL;
+		}
+	}
+
+	x = xfrm_state_lookup(net, opts->mark, &opts->daddr, opts->spi,
+			      opts->proto, opts->family);
+
+	if (opts->netns_id >= 0)
+		put_net(net);
+	if (!x)
+		opts->error = -ENOENT;
+
+	return x;
+}
+
+/* bpf_xdp_xfrm_state_release - Release acquired xfrm_state object
+ *
+ * This must be invoked for referenced PTR_TO_BTF_ID, and the verifier rejects
+ * the program if any references remain in the program in all of the explored
+ * states.
+ *
+ * Parameters:
+ * @x		- Pointer to referenced xfrm_state object, obtained using
+ *		  bpf_xdp_get_xfrm_state.
+ */
+__bpf_kfunc void bpf_xdp_xfrm_state_release(struct xfrm_state *x)
+{
+	xfrm_state_put(x);
+}
+
+__bpf_kfunc_end_defs();
+
+BTF_SET8_START(xfrm_state_kfunc_set)
+BTF_ID_FLAGS(func, bpf_xdp_get_xfrm_state, KF_RET_NULL | KF_ACQUIRE)
+BTF_ID_FLAGS(func, bpf_xdp_xfrm_state_release, KF_RELEASE)
+BTF_SET8_END(xfrm_state_kfunc_set)
+
+static const struct btf_kfunc_id_set xfrm_state_xdp_kfunc_set = {
+	.owner = THIS_MODULE,
+	.set   = &xfrm_state_kfunc_set,
+};
+
+int __init register_xfrm_state_bpf(void)
+{
+	return register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP,
+					 &xfrm_state_xdp_kfunc_set);
+}
-- 
cgit v1.2.3


From bf873a800ac3234eba991603a450eaa517d27022 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 12 Dec 2023 20:35:11 -0800
Subject: net: skbuff: fix spelling errors

Correct spelling as reported by codespell.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20231213043511.10357-1-rdunlap@infradead.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/skbuff.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index b370eb8d70f7..7ce38874dbd1 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1069,7 +1069,7 @@ struct sk_buff {
 	refcount_t		users;
 
 #ifdef CONFIG_SKB_EXTENSIONS
-	/* only useable after checking ->active_extensions != 0 */
+	/* only usable after checking ->active_extensions != 0 */
 	struct skb_ext		*extensions;
 #endif
 };
@@ -3311,7 +3311,7 @@ static inline struct page *__dev_alloc_pages(gfp_t gfp_mask,
 					     unsigned int order)
 {
 	/* This piece of code contains several assumptions.
-	 * 1.  This is for device Rx, therefor a cold page is preferred.
+	 * 1.  This is for device Rx, therefore a cold page is preferred.
 	 * 2.  The expectation is the user wants a compound page.
 	 * 3.  If requesting a order 0 page it will not be compound
 	 *     due to the check to see if order has a value in prep_new_page
@@ -4247,7 +4247,7 @@ static inline bool __skb_metadata_differs(const struct sk_buff *skb_a,
 {
 	const void *a = skb_metadata_end(skb_a);
 	const void *b = skb_metadata_end(skb_b);
-	/* Using more efficient varaiant than plain call to memcmp(). */
+	/* Using more efficient variant than plain call to memcmp(). */
 #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
 	u64 diffs = 0;
 
-- 
cgit v1.2.3


From fcb29877f7e18a1f27d7d6871f5f7bb6aaade575 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 12 Dec 2023 20:36:50 -0800
Subject: page_pool: fix typos and punctuation

Correct spelling (s/and/any) and a run-on sentence.
Spell out "multi".

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Acked-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Link: https://lore.kernel.org/r/20231213043650.12672-1-rdunlap@infradead.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/page_pool/helpers.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h
index 841e0a930bd7..ead2c0d24b2c 100644
--- a/include/net/page_pool/helpers.h
+++ b/include/net/page_pool/helpers.h
@@ -11,7 +11,7 @@
  * The page_pool allocator is optimized for recycling page or page fragment used
  * by skb packet and xdp frame.
  *
- * Basic use involves replacing and alloc_pages() calls with page_pool_alloc(),
+ * Basic use involves replacing any alloc_pages() calls with page_pool_alloc(),
  * which allocate memory with or without page splitting depending on the
  * requested memory size.
  *
@@ -37,15 +37,15 @@
  * attach the page_pool object to a page_pool-aware object like skbs marked with
  * skb_mark_for_recycle().
  *
- * page_pool_put_page() may be called multi times on the same page if a page is
- * split into multi fragments. For the last fragment, it will either recycle the
- * page, or in case of page->_refcount > 1, it will release the DMA mapping and
- * in-flight state accounting.
+ * page_pool_put_page() may be called multiple times on the same page if a page
+ * is split into multiple fragments. For the last fragment, it will either
+ * recycle the page, or in case of page->_refcount > 1, it will release the DMA
+ * mapping and in-flight state accounting.
  *
  * dma_sync_single_range_for_device() is only called for the last fragment when
  * page_pool is created with PP_FLAG_DMA_SYNC_DEV flag, so it depends on the
  * last freed fragment to do the sync_for_device operation for all fragments in
- * the same page when a page is split, the API user must setup pool->p.max_len
+ * the same page when a page is split. The API user must setup pool->p.max_len
  * and pool->p.offset correctly and ensure that page_pool_put_page() is called
  * with dma_sync_size being -1 for fragment API.
  */
-- 
cgit v1.2.3


From ee08acb58fe47fc3bc2c137965985cdb1df40b35 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Thu, 2 Nov 2023 20:33:18 +0530
Subject: bus: mhi: ep: Add support for async DMA write operation

In order to optimize the data transfer, let's use the async DMA operation
for writing (queuing) data to the host.

In the async path, the completion event for the transfer ring will only be
sent to the host when the controller driver notifies the MHI stack of the
actual transfer completion using the callback (mhi_ep_skb_completion)
supplied in "struct mhi_ep_buf_info".

Also to accommodate the async operation, the transfer ring read offset
(ring->rd_offset) is cached in the "struct mhi_ep_chan" and updated locally
to let the stack queue further ring items to the controller driver. But the
actual read offset of the transfer ring will only be updated in the
completion callback.

Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/bus/mhi/ep/internal.h |  1 +
 drivers/bus/mhi/ep/main.c     | 74 +++++++++++++++++++++++++++++++------------
 include/linux/mhi_ep.h        |  4 +++
 3 files changed, 59 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/drivers/bus/mhi/ep/internal.h b/drivers/bus/mhi/ep/internal.h
index 8c5cf2b67951..577965f95fda 100644
--- a/drivers/bus/mhi/ep/internal.h
+++ b/drivers/bus/mhi/ep/internal.h
@@ -162,6 +162,7 @@ struct mhi_ep_chan {
 	void (*xfer_cb)(struct mhi_ep_device *mhi_dev, struct mhi_result *result);
 	enum mhi_ch_state state;
 	enum dma_data_direction dir;
+	size_t rd_offset;
 	u64 tre_loc;
 	u32 tre_size;
 	u32 tre_bytes_left;
diff --git a/drivers/bus/mhi/ep/main.c b/drivers/bus/mhi/ep/main.c
index 88e189a8463a..48ef61ccf737 100644
--- a/drivers/bus/mhi/ep/main.c
+++ b/drivers/bus/mhi/ep/main.c
@@ -199,6 +199,8 @@ static int mhi_ep_process_cmd_ring(struct mhi_ep_ring *ring, struct mhi_ring_ele
 
 				goto err_unlock;
 			}
+
+			mhi_chan->rd_offset = ch_ring->rd_offset;
 		}
 
 		/* Set channel state to RUNNING */
@@ -328,7 +330,7 @@ bool mhi_ep_queue_is_empty(struct mhi_ep_device *mhi_dev, enum dma_data_directio
 	struct mhi_ep_cntrl *mhi_cntrl = mhi_dev->mhi_cntrl;
 	struct mhi_ep_ring *ring = &mhi_cntrl->mhi_chan[mhi_chan->chan].ring;
 
-	return !!(ring->rd_offset == ring->wr_offset);
+	return !!(mhi_chan->rd_offset == ring->wr_offset);
 }
 EXPORT_SYMBOL_GPL(mhi_ep_queue_is_empty);
 
@@ -355,7 +357,7 @@ static int mhi_ep_read_channel(struct mhi_ep_cntrl *mhi_cntrl,
 			return -ENODEV;
 		}
 
-		el = &ring->ring_cache[ring->rd_offset];
+		el = &ring->ring_cache[mhi_chan->rd_offset];
 
 		/* Check if there is data pending to be read from previous read operation */
 		if (mhi_chan->tre_bytes_left) {
@@ -434,6 +436,7 @@ static int mhi_ep_read_channel(struct mhi_ep_cntrl *mhi_cntrl,
 				tr_done = true;
 			}
 
+			mhi_chan->rd_offset = (mhi_chan->rd_offset + 1) % ring->ring_size;
 			mhi_ep_ring_inc_index(ring);
 		}
 
@@ -494,6 +497,35 @@ static int mhi_ep_process_ch_ring(struct mhi_ep_ring *ring, struct mhi_ring_elem
 	return 0;
 }
 
+static void mhi_ep_skb_completion(struct mhi_ep_buf_info *buf_info)
+{
+	struct mhi_ep_device *mhi_dev = buf_info->mhi_dev;
+	struct mhi_ep_cntrl *mhi_cntrl = mhi_dev->mhi_cntrl;
+	struct mhi_ep_chan *mhi_chan = mhi_dev->dl_chan;
+	struct mhi_ep_ring *ring = &mhi_cntrl->mhi_chan[mhi_chan->chan].ring;
+	struct mhi_ring_element *el = &ring->ring_cache[ring->rd_offset];
+	struct device *dev = &mhi_dev->dev;
+	struct mhi_result result = {};
+	int ret;
+
+	if (mhi_chan->xfer_cb) {
+		result.buf_addr = buf_info->cb_buf;
+		result.dir = mhi_chan->dir;
+		result.bytes_xferd = buf_info->size;
+
+		mhi_chan->xfer_cb(mhi_dev, &result);
+	}
+
+	ret = mhi_ep_send_completion_event(mhi_cntrl, ring, el, buf_info->size,
+					   buf_info->code);
+	if (ret) {
+		dev_err(dev, "Error sending transfer completion event\n");
+		return;
+	}
+
+	mhi_ep_ring_inc_index(ring);
+}
+
 /* TODO: Handle partially formed TDs */
 int mhi_ep_queue_skb(struct mhi_ep_device *mhi_dev, struct sk_buff *skb)
 {
@@ -504,7 +536,6 @@ int mhi_ep_queue_skb(struct mhi_ep_device *mhi_dev, struct sk_buff *skb)
 	struct mhi_ring_element *el;
 	u32 buf_left, read_offset;
 	struct mhi_ep_ring *ring;
-	enum mhi_ev_ccs code;
 	size_t tr_len;
 	u32 tre_len;
 	int ret;
@@ -528,7 +559,7 @@ int mhi_ep_queue_skb(struct mhi_ep_device *mhi_dev, struct sk_buff *skb)
 			goto err_exit;
 		}
 
-		el = &ring->ring_cache[ring->rd_offset];
+		el = &ring->ring_cache[mhi_chan->rd_offset];
 		tre_len = MHI_TRE_DATA_GET_LEN(el);
 
 		tr_len = min(buf_left, tre_len);
@@ -537,33 +568,35 @@ int mhi_ep_queue_skb(struct mhi_ep_device *mhi_dev, struct sk_buff *skb)
 		buf_info.dev_addr = skb->data + read_offset;
 		buf_info.host_addr = MHI_TRE_DATA_GET_PTR(el);
 		buf_info.size = tr_len;
+		buf_info.cb = mhi_ep_skb_completion;
+		buf_info.cb_buf = skb;
+		buf_info.mhi_dev = mhi_dev;
 
-		dev_dbg(dev, "Writing %zd bytes to channel (%u)\n", tr_len, ring->ch_id);
-		ret = mhi_cntrl->write_sync(mhi_cntrl, &buf_info);
-		if (ret < 0) {
-			dev_err(dev, "Error writing to the channel\n");
-			goto err_exit;
-		}
-
-		buf_left -= tr_len;
 		/*
 		 * For all TREs queued by the host for DL channel, only the EOT flag will be set.
 		 * If the packet doesn't fit into a single TRE, send the OVERFLOW event to
 		 * the host so that the host can adjust the packet boundary to next TREs. Else send
 		 * the EOT event to the host indicating the packet boundary.
 		 */
-		if (buf_left)
-			code = MHI_EV_CC_OVERFLOW;
+		if (buf_left - tr_len)
+			buf_info.code = MHI_EV_CC_OVERFLOW;
 		else
-			code = MHI_EV_CC_EOT;
+			buf_info.code = MHI_EV_CC_EOT;
 
-		ret = mhi_ep_send_completion_event(mhi_cntrl, ring, el, tr_len, code);
-		if (ret) {
-			dev_err(dev, "Error sending transfer completion event\n");
+		dev_dbg(dev, "Writing %zd bytes to channel (%u)\n", tr_len, ring->ch_id);
+		ret = mhi_cntrl->write_async(mhi_cntrl, &buf_info);
+		if (ret < 0) {
+			dev_err(dev, "Error writing to the channel\n");
 			goto err_exit;
 		}
 
-		mhi_ep_ring_inc_index(ring);
+		buf_left -= tr_len;
+
+		/*
+		 * Update the read offset cached in mhi_chan. Actual read offset
+		 * will be updated by the completion handler.
+		 */
+		mhi_chan->rd_offset = (mhi_chan->rd_offset + 1) % ring->ring_size;
 	} while (buf_left);
 
 	mutex_unlock(&mhi_chan->lock);
@@ -803,7 +836,7 @@ static void mhi_ep_ch_ring_worker(struct work_struct *work)
 		}
 
 		/* Sanity check to make sure there are elements in the ring */
-		if (ring->rd_offset == ring->wr_offset) {
+		if (chan->rd_offset == ring->wr_offset) {
 			mutex_unlock(&chan->lock);
 			kmem_cache_free(mhi_cntrl->ring_item_cache, itr);
 			continue;
@@ -1447,6 +1480,7 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl,
 		ret = -ENOMEM;
 		goto err_destroy_tre_buf_cache;
 	}
+
 	INIT_WORK(&mhi_cntrl->state_work, mhi_ep_state_worker);
 	INIT_WORK(&mhi_cntrl->reset_work, mhi_ep_reset_worker);
 	INIT_WORK(&mhi_cntrl->cmd_ring_work, mhi_ep_cmd_ring_worker);
diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h
index 14c6e8d3f573..11bf3212f782 100644
--- a/include/linux/mhi_ep.h
+++ b/include/linux/mhi_ep.h
@@ -51,16 +51,20 @@ struct mhi_ep_db_info {
 
 /**
  * struct mhi_ep_buf_info - MHI Endpoint transfer buffer info
+ * @mhi_dev: MHI device associated with this buffer
  * @dev_addr: Address of the buffer in endpoint
  * @host_addr: Address of the bufffer in host
  * @size: Size of the buffer
+ * @code: Transfer completion code
  * @cb: Callback to be executed by controller drivers after transfer completion (async)
  * @cb_buf: Opaque buffer to be passed to the callback
  */
 struct mhi_ep_buf_info {
+	struct mhi_ep_device *mhi_dev;
 	void *dev_addr;
 	u64 host_addr;
 	size_t size;
+	int code;
 
 	void (*cb)(struct mhi_ep_buf_info *buf_info);
 	void *cb_buf;
-- 
cgit v1.2.3


From 6909e0f322b0527fee9fdc54685e6cad69008713 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Fri, 8 Dec 2023 21:06:04 +0100
Subject: ACPI: utils: Return bool from acpi_evaluate_reference()

There are only 4 users of acpi_evaluate_reference() and none of them
actually cares about the reason why it fails.  All of them are only
interested in whether or not it is successful, so it can return a bool
value indicating that.

Modify acpi_evaluate_reference() as per the observation above and update
its callers accordingly so as to get rid of useless code and local
variables.

The observable behavior of the kernel is not expected to change after
this modification of the code.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpi_lpss.c                       |  5 +---
 drivers/acpi/scan.c                            |  5 ++--
 drivers/acpi/thermal.c                         |  4 +---
 drivers/acpi/utils.c                           | 32 ++++++++++----------------
 drivers/platform/surface/surface_acpi_notify.c |  4 +---
 include/acpi/acpi_bus.h                        |  8 +++----
 6 files changed, 20 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index 79f4fc7d6871..1623af8d62bc 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -565,16 +565,13 @@ static struct device *acpi_lpss_find_device(const char *hid, const char *uid)
 static bool acpi_lpss_dep(struct acpi_device *adev, acpi_handle handle)
 {
 	struct acpi_handle_list dep_devices;
-	acpi_status status;
 	bool ret = false;
 	int i;
 
 	if (!acpi_has_method(adev->handle, "_DEP"))
 		return false;
 
-	status = acpi_evaluate_reference(adev->handle, "_DEP", NULL,
-					 &dep_devices);
-	if (ACPI_FAILURE(status)) {
+	if (!acpi_evaluate_reference(adev->handle, "_DEP", NULL, &dep_devices)) {
 		dev_dbg(&adev->dev, "Failed to evaluate _DEP.\n");
 		return false;
 	}
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 02bb2cce423f..7b731958af5e 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1984,7 +1984,6 @@ static void acpi_scan_init_hotplug(struct acpi_device *adev)
 static u32 acpi_scan_check_dep(acpi_handle handle, bool check_dep)
 {
 	struct acpi_handle_list dep_devices;
-	acpi_status status;
 	u32 count;
 	int i;
 
@@ -1998,8 +1997,7 @@ static u32 acpi_scan_check_dep(acpi_handle handle, bool check_dep)
 	    !acpi_has_method(handle, "_HID"))
 		return 0;
 
-	status = acpi_evaluate_reference(handle, "_DEP", NULL, &dep_devices);
-	if (ACPI_FAILURE(status)) {
+	if (!acpi_evaluate_reference(handle, "_DEP", NULL, &dep_devices)) {
 		acpi_handle_debug(handle, "Failed to evaluate _DEP.\n");
 		return 0;
 	}
@@ -2008,6 +2006,7 @@ static u32 acpi_scan_check_dep(acpi_handle handle, bool check_dep)
 		struct acpi_device_info *info;
 		struct acpi_dep_data *dep;
 		bool skip, honor_dep;
+		acpi_status status;
 
 		status = acpi_get_object_info(dep_devices.handles[i], &info);
 		if (ACPI_FAILURE(status)) {
diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c
index f74d81abdbfc..15f09c71a5ec 100644
--- a/drivers/acpi/thermal.c
+++ b/drivers/acpi/thermal.c
@@ -247,7 +247,6 @@ static bool update_trip_devices(struct acpi_thermal *tz,
 {
 	struct acpi_handle_list devices = { 0 };
 	char method[] = "_PSL";
-	acpi_status status;
 
 	if (index != ACPI_THERMAL_TRIP_PASSIVE) {
 		method[1] = 'A';
@@ -255,8 +254,7 @@ static bool update_trip_devices(struct acpi_thermal *tz,
 		method[3] = '0' + index;
 	}
 
-	status = acpi_evaluate_reference(tz->device->handle, method, NULL, &devices);
-	if (ACPI_FAILURE(status)) {
+	if (!acpi_evaluate_reference(tz->device->handle, method, NULL, &devices)) {
 		acpi_handle_info(tz->device->handle, "%s evaluation failure\n", method);
 		return false;
 	}
diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c
index 5a7766c3fbbd..958dc651d467 100644
--- a/drivers/acpi/utils.c
+++ b/drivers/acpi/utils.c
@@ -329,19 +329,18 @@ const char *acpi_get_subsystem_id(acpi_handle handle)
 }
 EXPORT_SYMBOL_GPL(acpi_get_subsystem_id);
 
-acpi_status
-acpi_evaluate_reference(acpi_handle handle,
-			acpi_string pathname,
-			struct acpi_object_list *arguments,
-			struct acpi_handle_list *list)
+bool acpi_evaluate_reference(acpi_handle handle, acpi_string pathname,
+			     struct acpi_object_list *arguments,
+			     struct acpi_handle_list *list)
 {
 	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
 	union acpi_object *package;
 	acpi_status status;
+	bool ret = false;
 	u32 i;
 
 	if (!list)
-		return AE_BAD_PARAMETER;
+		return false;
 
 	/* Evaluate object. */
 
@@ -352,42 +351,35 @@ acpi_evaluate_reference(acpi_handle handle,
 	package = buffer.pointer;
 
 	if (buffer.length == 0 || !package ||
-	    package->type != ACPI_TYPE_PACKAGE || !package->package.count) {
-		status = AE_BAD_DATA;
+	    package->type != ACPI_TYPE_PACKAGE || !package->package.count)
 		goto err;
-	}
 
 	list->count = package->package.count;
 	list->handles = kcalloc(list->count, sizeof(*list->handles), GFP_KERNEL);
-	if (!list->handles) {
-		status = AE_NO_MEMORY;
+	if (!list->handles)
 		goto err_clear;
-	}
 
 	/* Extract package data. */
 
 	for (i = 0; i < list->count; i++) {
 		union acpi_object *element = &(package->package.elements[i]);
 
-		if (element->type != ACPI_TYPE_LOCAL_REFERENCE) {
-			status = AE_BAD_DATA;
+		if (element->type != ACPI_TYPE_LOCAL_REFERENCE ||
+		    !element->reference.handle)
 			goto err_free;
-		}
 
-		if (!element->reference.handle) {
-			status = AE_NULL_ENTRY;
-			goto err_free;
-		}
 		/* Get the  acpi_handle. */
 
 		list->handles[i] = element->reference.handle;
 		acpi_handle_debug(list->handles[i], "Found in reference list\n");
 	}
 
+	ret = true;
+
 end:
 	kfree(buffer.pointer);
 
-	return status;
+	return ret;
 
 err_free:
 	kfree(list->handles);
diff --git a/drivers/platform/surface/surface_acpi_notify.c b/drivers/platform/surface/surface_acpi_notify.c
index e4dee920da18..96ec052d0940 100644
--- a/drivers/platform/surface/surface_acpi_notify.c
+++ b/drivers/platform/surface/surface_acpi_notify.c
@@ -740,15 +740,13 @@ static bool is_san_consumer(struct platform_device *pdev, acpi_handle handle)
 {
 	struct acpi_handle_list dep_devices;
 	acpi_handle supplier = ACPI_HANDLE(&pdev->dev);
-	acpi_status status;
 	bool ret = false;
 	int i;
 
 	if (!acpi_has_method(handle, "_DEP"))
 		return false;
 
-	status = acpi_evaluate_reference(handle, "_DEP", NULL, &dep_devices);
-	if (ACPI_FAILURE(status)) {
+	if (!acpi_evaluate_reference(handle, "_DEP", NULL, &dep_devices)) {
 		san_consumer_dbg(&pdev->dev, handle, "failed to evaluate _DEP\n");
 		return false;
 	}
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index aae31552c574..fbe60af56b34 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -25,11 +25,9 @@ acpi_status
 acpi_evaluate_integer(acpi_handle handle,
 		      acpi_string pathname,
 		      struct acpi_object_list *arguments, unsigned long long *data);
-acpi_status
-acpi_evaluate_reference(acpi_handle handle,
-			acpi_string pathname,
-			struct acpi_object_list *arguments,
-			struct acpi_handle_list *list);
+bool acpi_evaluate_reference(acpi_handle handle, acpi_string pathname,
+			     struct acpi_object_list *arguments,
+			     struct acpi_handle_list *list);
 bool acpi_handle_list_equal(struct acpi_handle_list *list1,
 			    struct acpi_handle_list *list2);
 void acpi_handle_list_replace(struct acpi_handle_list *dst,
-- 
cgit v1.2.3


From 4c660ffef34b7d645ae3144369bc50257f295212 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Fri, 8 Dec 2023 21:07:41 +0100
Subject: ACPI: utils: Fix white space in struct acpi_handle_list definition

Fix inadvertently introduced white space damage in the struct
acpi_handle_list definition.

No functional impact.

Fixes: 2e57d10a6591 ("ACPI: utils: Dynamically determine acpi_handle_list size")
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/acpi_bus.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index fbe60af56b34..3dcf07b41428 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -14,7 +14,7 @@
 
 struct acpi_handle_list {
 	u32 count;
-	acpi_handle* handles;
+	acpi_handle *handles;
 };
 
 /* acpi_utils.h */
-- 
cgit v1.2.3


From 2373699560a754079579b7722b50d1d38de1960e Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Tue, 28 Nov 2023 12:16:55 +0100
Subject: mac802154: Avoid new associations while disassociating

While disassociating from a PAN ourselves, let's set the maximum number
of associations temporarily to zero to be sure no new device tries to
associate with us.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Acked-by: Stefan Schmidt <stefan@datenfreihafen.org>
Acked-by: Alexander Aring <aahringo@redhat.com>
Link: https://lore.kernel.org/linux-wpan/20231128111655.507479-6-miquel.raynal@bootlin.com
---
 include/net/cfg802154.h |  4 +++-
 net/ieee802154/pan.c    |  8 +++++++-
 net/mac802154/cfg.c     | 11 ++++++++---
 3 files changed, 18 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index a64bbcd71f10..cd95711b12b8 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -589,8 +589,10 @@ cfg802154_device_is_child(struct wpan_dev *wpan_dev,
  * cfg802154_set_max_associations - Limit the number of future associations
  * @wpan_dev: the wpan device
  * @max: the maximum number of devices we accept to associate
+ * @return: the old maximum value
  */
-void cfg802154_set_max_associations(struct wpan_dev *wpan_dev, unsigned int max);
+unsigned int cfg802154_set_max_associations(struct wpan_dev *wpan_dev,
+					    unsigned int max);
 
 /**
  * cfg802154_get_free_short_addr - Get a free address among the known devices
diff --git a/net/ieee802154/pan.c b/net/ieee802154/pan.c
index fb5b0af2ef68..249df7364b3e 100644
--- a/net/ieee802154/pan.c
+++ b/net/ieee802154/pan.c
@@ -94,10 +94,16 @@ __le16 cfg802154_get_free_short_addr(struct wpan_dev *wpan_dev)
 }
 EXPORT_SYMBOL_GPL(cfg802154_get_free_short_addr);
 
-void cfg802154_set_max_associations(struct wpan_dev *wpan_dev, unsigned int max)
+unsigned int cfg802154_set_max_associations(struct wpan_dev *wpan_dev,
+					    unsigned int max)
 {
+	unsigned int old_max;
+
 	lockdep_assert_held(&wpan_dev->association_lock);
 
+	old_max = wpan_dev->max_associations;
 	wpan_dev->max_associations = max;
+
+	return old_max;
 }
 EXPORT_SYMBOL_GPL(cfg802154_set_max_associations);
diff --git a/net/mac802154/cfg.c b/net/mac802154/cfg.c
index 17e2032fac24..ef7f23af043f 100644
--- a/net/mac802154/cfg.c
+++ b/net/mac802154/cfg.c
@@ -389,6 +389,7 @@ static int mac802154_disassociate_from_parent(struct wpan_phy *wpan_phy,
 	struct ieee802154_local *local = wpan_phy_priv(wpan_phy);
 	struct ieee802154_pan_device *child, *tmp;
 	struct ieee802154_sub_if_data *sdata;
+	unsigned int max_assoc;
 	u64 eaddr;
 	int ret;
 
@@ -397,6 +398,7 @@ static int mac802154_disassociate_from_parent(struct wpan_phy *wpan_phy,
 	/* Start by disassociating all the children and preventing new ones to
 	 * attempt associations.
 	 */
+	max_assoc = cfg802154_set_max_associations(wpan_dev, 0);
 	list_for_each_entry_safe(child, tmp, &wpan_dev->children, node) {
 		ret = mac802154_send_disassociation_notif(sdata, child,
 							  IEEE802154_COORD_WISHES_DEVICE_TO_LEAVE);
@@ -429,14 +431,17 @@ static int mac802154_disassociate_from_parent(struct wpan_phy *wpan_phy,
 	if (local->hw.flags & IEEE802154_HW_AFILT) {
 		ret = drv_set_pan_id(local, wpan_dev->pan_id);
 		if (ret < 0)
-			return ret;
+			goto reset_mac_assoc;
 
 		ret = drv_set_short_addr(local, wpan_dev->short_addr);
 		if (ret < 0)
-			return ret;
+			goto reset_mac_assoc;
 	}
 
-	return 0;
+reset_mac_assoc:
+	cfg802154_set_max_associations(wpan_dev, max_assoc);
+
+	return ret;
 }
 
 static int mac802154_disassociate_child(struct wpan_phy *wpan_phy,
-- 
cgit v1.2.3


From 02fed6d92badf08e2ac2cd1755d14c45c8f3d0ca Mon Sep 17 00:00:00 2001
From: Konstantin Taranov <kotaranov@microsoft.com>
Date: Wed, 13 Dec 2023 02:01:47 -0800
Subject: net: mana: add msix index sharing between EQs

This patch allows to assign and poll more than one EQ on the same
msix index.
It is achieved by introducing a list of attached EQs in each IRQ context.
It also removes the existing msix_index map that tried to ensure that there
is only one EQ at each msix_index.
This patch exports symbols for creating EQs from other MANA kernel modules.

Signed-off-by: Konstantin Taranov <kotaranov@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microsoft/mana/gdma_main.c  | 76 +++++++++++-------------
 drivers/net/ethernet/microsoft/mana/hw_channel.c |  1 +
 drivers/net/ethernet/microsoft/mana/mana_en.c    |  1 +
 include/net/mana/gdma.h                          |  7 ++-
 4 files changed, 43 insertions(+), 42 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index 6367de0c2c2e..a6863011d682 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -414,8 +414,12 @@ static void mana_gd_process_eq_events(void *arg)
 
 		old_bits = (eq->head / num_eqe - 1) & GDMA_EQE_OWNER_MASK;
 		/* No more entries */
-		if (owner_bits == old_bits)
+		if (owner_bits == old_bits) {
+			/* return here without ringing the doorbell */
+			if (i == 0)
+				return;
 			break;
+		}
 
 		new_bits = (eq->head / num_eqe) & GDMA_EQE_OWNER_MASK;
 		if (owner_bits != new_bits) {
@@ -445,42 +449,29 @@ static int mana_gd_register_irq(struct gdma_queue *queue,
 	struct gdma_dev *gd = queue->gdma_dev;
 	struct gdma_irq_context *gic;
 	struct gdma_context *gc;
-	struct gdma_resource *r;
 	unsigned int msi_index;
 	unsigned long flags;
 	struct device *dev;
 	int err = 0;
 
 	gc = gd->gdma_context;
-	r = &gc->msix_resource;
 	dev = gc->dev;
+	msi_index = spec->eq.msix_index;
 
-	spin_lock_irqsave(&r->lock, flags);
-
-	msi_index = find_first_zero_bit(r->map, r->size);
-	if (msi_index >= r->size || msi_index >= gc->num_msix_usable) {
+	if (msi_index >= gc->num_msix_usable) {
 		err = -ENOSPC;
-	} else {
-		bitmap_set(r->map, msi_index, 1);
-		queue->eq.msix_index = msi_index;
-	}
-
-	spin_unlock_irqrestore(&r->lock, flags);
-
-	if (err) {
-		dev_err(dev, "Register IRQ err:%d, msi:%u rsize:%u, nMSI:%u",
-			err, msi_index, r->size, gc->num_msix_usable);
+		dev_err(dev, "Register IRQ err:%d, msi:%u nMSI:%u",
+			err, msi_index, gc->num_msix_usable);
 
 		return err;
 	}
 
+	queue->eq.msix_index = msi_index;
 	gic = &gc->irq_contexts[msi_index];
 
-	WARN_ON(gic->handler || gic->arg);
-
-	gic->arg = queue;
-
-	gic->handler = mana_gd_process_eq_events;
+	spin_lock_irqsave(&gic->lock, flags);
+	list_add_rcu(&queue->entry, &gic->eq_list);
+	spin_unlock_irqrestore(&gic->lock, flags);
 
 	return 0;
 }
@@ -490,12 +481,11 @@ static void mana_gd_deregiser_irq(struct gdma_queue *queue)
 	struct gdma_dev *gd = queue->gdma_dev;
 	struct gdma_irq_context *gic;
 	struct gdma_context *gc;
-	struct gdma_resource *r;
 	unsigned int msix_index;
 	unsigned long flags;
+	struct gdma_queue *eq;
 
 	gc = gd->gdma_context;
-	r = &gc->msix_resource;
 
 	/* At most num_online_cpus() + 1 interrupts are used. */
 	msix_index = queue->eq.msix_index;
@@ -503,14 +493,17 @@ static void mana_gd_deregiser_irq(struct gdma_queue *queue)
 		return;
 
 	gic = &gc->irq_contexts[msix_index];
-	gic->handler = NULL;
-	gic->arg = NULL;
-
-	spin_lock_irqsave(&r->lock, flags);
-	bitmap_clear(r->map, msix_index, 1);
-	spin_unlock_irqrestore(&r->lock, flags);
+	spin_lock_irqsave(&gic->lock, flags);
+	list_for_each_entry_rcu(eq, &gic->eq_list, entry) {
+		if (queue == eq) {
+			list_del_rcu(&eq->entry);
+			break;
+		}
+	}
+	spin_unlock_irqrestore(&gic->lock, flags);
 
 	queue->eq.msix_index = INVALID_PCI_MSIX_INDEX;
+	synchronize_rcu();
 }
 
 int mana_gd_test_eq(struct gdma_context *gc, struct gdma_queue *eq)
@@ -588,6 +581,7 @@ static int mana_gd_create_eq(struct gdma_dev *gd,
 	int err;
 
 	queue->eq.msix_index = INVALID_PCI_MSIX_INDEX;
+	queue->id = INVALID_QUEUE_ID;
 
 	log2_num_entries = ilog2(queue->queue_size / GDMA_EQE_SIZE);
 
@@ -819,6 +813,7 @@ free_q:
 	kfree(queue);
 	return err;
 }
+EXPORT_SYMBOL_NS(mana_gd_create_mana_eq, NET_MANA);
 
 int mana_gd_create_mana_wq_cq(struct gdma_dev *gd,
 			      const struct gdma_queue_spec *spec,
@@ -895,6 +890,7 @@ void mana_gd_destroy_queue(struct gdma_context *gc, struct gdma_queue *queue)
 	mana_gd_free_memory(gmi);
 	kfree(queue);
 }
+EXPORT_SYMBOL_NS(mana_gd_destroy_queue, NET_MANA);
 
 int mana_gd_verify_vf_version(struct pci_dev *pdev)
 {
@@ -1217,9 +1213,14 @@ int mana_gd_poll_cq(struct gdma_queue *cq, struct gdma_comp *comp, int num_cqe)
 static irqreturn_t mana_gd_intr(int irq, void *arg)
 {
 	struct gdma_irq_context *gic = arg;
+	struct list_head *eq_list = &gic->eq_list;
+	struct gdma_queue *eq;
 
-	if (gic->handler)
-		gic->handler(gic->arg);
+	rcu_read_lock();
+	list_for_each_entry_rcu(eq, eq_list, entry) {
+		gic->handler(eq);
+	}
+	rcu_read_unlock();
 
 	return IRQ_HANDLED;
 }
@@ -1271,8 +1272,9 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev)
 
 	for (i = 0; i < nvec; i++) {
 		gic = &gc->irq_contexts[i];
-		gic->handler = NULL;
-		gic->arg = NULL;
+		gic->handler = mana_gd_process_eq_events;
+		INIT_LIST_HEAD(&gic->eq_list);
+		spin_lock_init(&gic->lock);
 
 		if (!i)
 			snprintf(gic->name, MANA_IRQ_NAME_SZ, "mana_hwc@pci:%s",
@@ -1295,10 +1297,6 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev)
 		irq_set_affinity_and_hint(irq, cpumask_of(cpu));
 	}
 
-	err = mana_gd_alloc_res_map(nvec, &gc->msix_resource);
-	if (err)
-		goto free_irq;
-
 	gc->max_num_msix = nvec;
 	gc->num_msix_usable = nvec;
 
@@ -1329,8 +1327,6 @@ static void mana_gd_remove_irqs(struct pci_dev *pdev)
 	if (gc->max_num_msix < 1)
 		return;
 
-	mana_gd_free_res_map(&gc->msix_resource);
-
 	for (i = 0; i < gc->max_num_msix; i++) {
 		irq = pci_irq_vector(pdev, i);
 		if (irq < 0)
diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c
index 9d1cd3bfcf66..2729a2c5acf9 100644
--- a/drivers/net/ethernet/microsoft/mana/hw_channel.c
+++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c
@@ -300,6 +300,7 @@ static int mana_hwc_create_gdma_eq(struct hw_channel_context *hwc,
 	spec.eq.context = ctx;
 	spec.eq.callback = cb;
 	spec.eq.log2_throttle_limit = DEFAULT_LOG2_THROTTLING_FOR_ERROR_EQ;
+	spec.eq.msix_index = 0;
 
 	return mana_gd_create_hwc_queue(hwc->gdma_dev, &spec, queue);
 }
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index cb7b9d8ef618..59287c6e6cee 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -1244,6 +1244,7 @@ static int mana_create_eq(struct mana_context *ac)
 	spec.eq.log2_throttle_limit = LOG2_EQ_THROTTLE;
 
 	for (i = 0; i < gc->max_num_queues; i++) {
+		spec.eq.msix_index = (i + 1) % gc->num_msix_usable;
 		err = mana_gd_create_mana_eq(gd, &spec, &ac->eqs[i].eq);
 		if (err)
 			goto out;
diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h
index 88b6ef7ce1a6..76f2fd2645b7 100644
--- a/include/net/mana/gdma.h
+++ b/include/net/mana/gdma.h
@@ -293,6 +293,7 @@ struct gdma_queue {
 
 	u32 head;
 	u32 tail;
+	struct list_head entry;
 
 	/* Extra fields specific to EQ/CQ. */
 	union {
@@ -328,6 +329,7 @@ struct gdma_queue_spec {
 			void *context;
 
 			unsigned long log2_throttle_limit;
+			unsigned int msix_index;
 		} eq;
 
 		struct {
@@ -344,7 +346,9 @@ struct gdma_queue_spec {
 
 struct gdma_irq_context {
 	void (*handler)(void *arg);
-	void *arg;
+	/* Protect the eq_list */
+	spinlock_t lock;
+	struct list_head eq_list;
 	char name[MANA_IRQ_NAME_SZ];
 };
 
@@ -355,7 +359,6 @@ struct gdma_context {
 	unsigned int		max_num_queues;
 	unsigned int		max_num_msix;
 	unsigned int		num_msix_usable;
-	struct gdma_resource	msix_resource;
 	struct gdma_irq_context	*irq_contexts;
 
 	/* L2 MTU */
-- 
cgit v1.2.3


From 0fe1798968115488c0c02f4633032a015b1faf97 Mon Sep 17 00:00:00 2001
From: Arseniy Krasnov <avkrasnov@salutedevices.com>
Date: Thu, 14 Dec 2023 15:52:29 +0300
Subject: virtio/vsock: send credit update during setting SO_RCVLOWAT

Send credit update message when SO_RCVLOWAT is updated and it is bigger
than number of bytes in rx queue. It is needed, because 'poll()' will
wait until number of bytes in rx queue will be not smaller than
O_RCVLOWAT, so kick sender to send more data. Otherwise mutual hungup
for tx/rx is possible: sender waits for free space and receiver is
waiting data in 'poll()'.

Rename 'set_rcvlowat' callback to 'notify_set_rcvlowat' and set
'sk->sk_rcvlowat' only in one place (i.e. 'vsock_set_rcvlowat'), so the
transport doesn't need to do it.

Fixes: b89d882dc9fc ("vsock/virtio: reduce credit update messages")
Signed-off-by: Arseniy Krasnov <avkrasnov@salutedevices.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/vsock.c                   |  1 +
 include/linux/virtio_vsock.h            |  1 +
 include/net/af_vsock.h                  |  2 +-
 net/vmw_vsock/af_vsock.c                |  9 +++++++--
 net/vmw_vsock/hyperv_transport.c        |  4 ++--
 net/vmw_vsock/virtio_transport.c        |  1 +
 net/vmw_vsock/virtio_transport_common.c | 30 ++++++++++++++++++++++++++++++
 net/vmw_vsock/vsock_loopback.c          |  1 +
 8 files changed, 44 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index f75731396b7e..ec20ecff85c7 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -449,6 +449,7 @@ static struct virtio_transport vhost_transport = {
 		.notify_send_pre_enqueue  = virtio_transport_notify_send_pre_enqueue,
 		.notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue,
 		.notify_buffer_size       = virtio_transport_notify_buffer_size,
+		.notify_set_rcvlowat      = virtio_transport_notify_set_rcvlowat,
 
 		.read_skb = virtio_transport_read_skb,
 	},
diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index ebb3ce63d64d..c82089dee0c8 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -256,4 +256,5 @@ void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit);
 void virtio_transport_deliver_tap_pkt(struct sk_buff *skb);
 int virtio_transport_purge_skbs(void *vsk, struct sk_buff_head *list);
 int virtio_transport_read_skb(struct vsock_sock *vsk, skb_read_actor_t read_actor);
+int virtio_transport_notify_set_rcvlowat(struct vsock_sock *vsk, int val);
 #endif /* _LINUX_VIRTIO_VSOCK_H */
diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index e302c0e804d0..535701efc1e5 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -137,7 +137,6 @@ struct vsock_transport {
 	u64 (*stream_rcvhiwat)(struct vsock_sock *);
 	bool (*stream_is_active)(struct vsock_sock *);
 	bool (*stream_allow)(u32 cid, u32 port);
-	int (*set_rcvlowat)(struct vsock_sock *vsk, int val);
 
 	/* SEQ_PACKET. */
 	ssize_t (*seqpacket_dequeue)(struct vsock_sock *vsk, struct msghdr *msg,
@@ -168,6 +167,7 @@ struct vsock_transport {
 		struct vsock_transport_send_notify_data *);
 	/* sk_lock held by the caller */
 	void (*notify_buffer_size)(struct vsock_sock *, u64 *);
+	int (*notify_set_rcvlowat)(struct vsock_sock *vsk, int val);
 
 	/* Shutdown. */
 	int (*shutdown)(struct vsock_sock *, int);
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 816725af281f..54ba7316f808 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -2264,8 +2264,13 @@ static int vsock_set_rcvlowat(struct sock *sk, int val)
 
 	transport = vsk->transport;
 
-	if (transport && transport->set_rcvlowat)
-		return transport->set_rcvlowat(vsk, val);
+	if (transport && transport->notify_set_rcvlowat) {
+		int err;
+
+		err = transport->notify_set_rcvlowat(vsk, val);
+		if (err)
+			return err;
+	}
 
 	WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
 	return 0;
diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c
index 7cb1a9d2cdb4..e2157e387217 100644
--- a/net/vmw_vsock/hyperv_transport.c
+++ b/net/vmw_vsock/hyperv_transport.c
@@ -816,7 +816,7 @@ int hvs_notify_send_post_enqueue(struct vsock_sock *vsk, ssize_t written,
 }
 
 static
-int hvs_set_rcvlowat(struct vsock_sock *vsk, int val)
+int hvs_notify_set_rcvlowat(struct vsock_sock *vsk, int val)
 {
 	return -EOPNOTSUPP;
 }
@@ -856,7 +856,7 @@ static struct vsock_transport hvs_transport = {
 	.notify_send_pre_enqueue  = hvs_notify_send_pre_enqueue,
 	.notify_send_post_enqueue = hvs_notify_send_post_enqueue,
 
-	.set_rcvlowat             = hvs_set_rcvlowat
+	.notify_set_rcvlowat      = hvs_notify_set_rcvlowat
 };
 
 static bool hvs_check_transport(struct vsock_sock *vsk)
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index af5bab1acee1..f495b9e5186b 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -537,6 +537,7 @@ static struct virtio_transport virtio_transport = {
 		.notify_send_pre_enqueue  = virtio_transport_notify_send_pre_enqueue,
 		.notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue,
 		.notify_buffer_size       = virtio_transport_notify_buffer_size,
+		.notify_set_rcvlowat      = virtio_transport_notify_set_rcvlowat,
 
 		.read_skb = virtio_transport_read_skb,
 	},
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index b35306dfcebe..16ff976a86e3 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -1690,6 +1690,36 @@ int virtio_transport_read_skb(struct vsock_sock *vsk, skb_read_actor_t recv_acto
 }
 EXPORT_SYMBOL_GPL(virtio_transport_read_skb);
 
+int virtio_transport_notify_set_rcvlowat(struct vsock_sock *vsk, int val)
+{
+	struct virtio_vsock_sock *vvs = vsk->trans;
+	bool send_update;
+
+	spin_lock_bh(&vvs->rx_lock);
+
+	/* If number of available bytes is less than new SO_RCVLOWAT value,
+	 * kick sender to send more data, because sender may sleep in its
+	 * 'send()' syscall waiting for enough space at our side. Also
+	 * don't send credit update when peer already knows actual value -
+	 * such transmission will be useless.
+	 */
+	send_update = (vvs->rx_bytes < val) &&
+		      (vvs->fwd_cnt != vvs->last_fwd_cnt);
+
+	spin_unlock_bh(&vvs->rx_lock);
+
+	if (send_update) {
+		int err;
+
+		err = virtio_transport_send_credit_update(vsk);
+		if (err < 0)
+			return err;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_notify_set_rcvlowat);
+
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Asias He");
 MODULE_DESCRIPTION("common code for virtio vsock");
diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c
index 048640167411..6dea6119f5b2 100644
--- a/net/vmw_vsock/vsock_loopback.c
+++ b/net/vmw_vsock/vsock_loopback.c
@@ -96,6 +96,7 @@ static struct virtio_transport loopback_transport = {
 		.notify_send_pre_enqueue  = virtio_transport_notify_send_pre_enqueue,
 		.notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue,
 		.notify_buffer_size       = virtio_transport_notify_buffer_size,
+		.notify_set_rcvlowat      = virtio_transport_notify_set_rcvlowat,
 
 		.read_skb = virtio_transport_read_skb,
 	},
-- 
cgit v1.2.3


From f5769faeec36b9d5b9df2c3e4f05a76d04ffd9c9 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 14 Dec 2023 10:49:00 +0000
Subject: net: Namespace-ify sysctl_optmem_max

optmem_max being used in tx zerocopy,
we want to be able to control it on a netns basis.

Following patch changes two tests.

Tested:

oqq130:~# cat /proc/sys/net/core/optmem_max
131072
oqq130:~# echo 1000000 >/proc/sys/net/core/optmem_max
oqq130:~# cat /proc/sys/net/core/optmem_max
1000000
oqq130:~# unshare -n
oqq130:~# cat /proc/sys/net/core/optmem_max
131072
oqq130:~# exit
logout
oqq130:~# cat /proc/sys/net/core/optmem_max
1000000

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netns/core.h   |  1 +
 include/net/sock.h         |  1 -
 net/core/bpf_sk_storage.c  |  3 ++-
 net/core/filter.c          | 12 +++++++-----
 net/core/net_namespace.c   |  4 ++++
 net/core/sock.c            | 10 ++--------
 net/core/sysctl_net_core.c | 15 ++++++++-------
 net/ipv4/ip_sockglue.c     |  6 +++---
 net/ipv6/ipv6_sockglue.c   |  4 ++--
 9 files changed, 29 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/include/net/netns/core.h b/include/net/netns/core.h
index a91ef9f8de60..78214f1b43a2 100644
--- a/include/net/netns/core.h
+++ b/include/net/netns/core.h
@@ -13,6 +13,7 @@ struct netns_core {
 	struct ctl_table_header	*sysctl_hdr;
 
 	int	sysctl_somaxconn;
+	int	sysctl_optmem_max;
 	u8	sysctl_txrehash;
 
 #ifdef CONFIG_PROC_FS
diff --git a/include/net/sock.h b/include/net/sock.h
index 1d6931caf0c3..8b6fe164b218 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2920,7 +2920,6 @@ extern __u32 sysctl_wmem_max;
 extern __u32 sysctl_rmem_max;
 
 extern int sysctl_tstamp_allow_data;
-extern int sysctl_optmem_max;
 
 extern __u32 sysctl_wmem_default;
 extern __u32 sysctl_rmem_default;
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index cca7594be92e..6c4d90b24d46 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -275,9 +275,10 @@ BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk)
 static int bpf_sk_storage_charge(struct bpf_local_storage_map *smap,
 				 void *owner, u32 size)
 {
-	int optmem_max = READ_ONCE(sysctl_optmem_max);
 	struct sock *sk = (struct sock *)owner;
+	int optmem_max;
 
+	optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max);
 	/* same check as in sock_kmalloc() */
 	if (size <= optmem_max &&
 	    atomic_read(&sk->sk_omem_alloc) + size < optmem_max) {
diff --git a/net/core/filter.c b/net/core/filter.c
index eedb33f3e998..6d89a9cf33c9 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1219,8 +1219,8 @@ void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
  */
 static bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp)
 {
+	int optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max);
 	u32 filter_size = bpf_prog_size(fp->prog->len);
-	int optmem_max = READ_ONCE(sysctl_optmem_max);
 
 	/* same check as in sock_kmalloc() */
 	if (filter_size <= optmem_max &&
@@ -1550,12 +1550,13 @@ EXPORT_SYMBOL_GPL(sk_attach_filter);
 int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 {
 	struct bpf_prog *prog = __get_filter(fprog, sk);
-	int err;
+	int err, optmem_max;
 
 	if (IS_ERR(prog))
 		return PTR_ERR(prog);
 
-	if (bpf_prog_size(prog->len) > READ_ONCE(sysctl_optmem_max))
+	optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max);
+	if (bpf_prog_size(prog->len) > optmem_max)
 		err = -ENOMEM;
 	else
 		err = reuseport_attach_prog(sk, prog);
@@ -1594,7 +1595,7 @@ int sk_attach_bpf(u32 ufd, struct sock *sk)
 int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk)
 {
 	struct bpf_prog *prog;
-	int err;
+	int err, optmem_max;
 
 	if (sock_flag(sk, SOCK_FILTER_LOCKED))
 		return -EPERM;
@@ -1622,7 +1623,8 @@ int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk)
 		}
 	} else {
 		/* BPF_PROG_TYPE_SOCKET_FILTER */
-		if (bpf_prog_size(prog->len) > READ_ONCE(sysctl_optmem_max)) {
+		optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max);
+		if (bpf_prog_size(prog->len) > optmem_max) {
 			err = -ENOMEM;
 			goto err_prog_put;
 		}
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index cb8bcbff9e83..72799533426b 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -372,6 +372,10 @@ out_undo:
 static int __net_init net_defaults_init_net(struct net *net)
 {
 	net->core.sysctl_somaxconn = SOMAXCONN;
+	/* Limits per socket sk_omem_alloc usage.
+	 * TCP zerocopy regular usage needs 128 KB.
+	 */
+	net->core.sysctl_optmem_max = 128 * 1024;
 	net->core.sysctl_txrehash = SOCK_TXREHASH_ENABLED;
 
 	return 0;
diff --git a/net/core/sock.c b/net/core/sock.c
index 08ecdc68d2df..446e945f736b 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -283,12 +283,6 @@ EXPORT_SYMBOL(sysctl_rmem_max);
 __u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX;
 __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX;
 
-/* Limits per socket sk_omem_alloc usage.
- * TCP zerocopy regular usage needs 128 KB.
- */
-int sysctl_optmem_max __read_mostly = 128 * 1024;
-EXPORT_SYMBOL(sysctl_optmem_max);
-
 int sysctl_tstamp_allow_data __read_mostly = 1;
 
 DEFINE_STATIC_KEY_FALSE(memalloc_socks_key);
@@ -2653,7 +2647,7 @@ struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size,
 
 	/* small safe race: SKB_TRUESIZE may differ from final skb->truesize */
 	if (atomic_read(&sk->sk_omem_alloc) + SKB_TRUESIZE(size) >
-	    READ_ONCE(sysctl_optmem_max))
+	    READ_ONCE(sock_net(sk)->core.sysctl_optmem_max))
 		return NULL;
 
 	skb = alloc_skb(size, priority);
@@ -2671,7 +2665,7 @@ struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size,
  */
 void *sock_kmalloc(struct sock *sk, int size, gfp_t priority)
 {
-	int optmem_max = READ_ONCE(sysctl_optmem_max);
+	int optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max);
 
 	if ((unsigned int)size <= optmem_max &&
 	    atomic_read(&sk->sk_omem_alloc) + size < optmem_max) {
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 03f1edb948d7..0f0cb1465e08 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -508,13 +508,6 @@ static struct ctl_table net_core_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
-	{
-		.procname	= "optmem_max",
-		.data		= &sysctl_optmem_max,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec
-	},
 	{
 		.procname	= "tstamp_allow_data",
 		.data		= &sysctl_tstamp_allow_data,
@@ -673,6 +666,14 @@ static struct ctl_table netns_core_table[] = {
 		.extra1		= SYSCTL_ZERO,
 		.proc_handler	= proc_dointvec_minmax
 	},
+	{
+		.procname	= "optmem_max",
+		.data		= &init_net.core.sysctl_optmem_max,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.extra1		= SYSCTL_ZERO,
+		.proc_handler	= proc_dointvec_minmax
+	},
 	{
 		.procname	= "txrehash",
 		.data		= &init_net.core.sysctl_txrehash,
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index d7d13940774e..66247e8b429e 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -775,7 +775,7 @@ static int ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, int optlen)
 
 	if (optlen < GROUP_FILTER_SIZE(0))
 		return -EINVAL;
-	if (optlen > READ_ONCE(sysctl_optmem_max))
+	if (optlen > READ_ONCE(sock_net(sk)->core.sysctl_optmem_max))
 		return -ENOBUFS;
 
 	gsf = memdup_sockptr(optval, optlen);
@@ -811,7 +811,7 @@ static int compat_ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval,
 
 	if (optlen < size0)
 		return -EINVAL;
-	if (optlen > READ_ONCE(sysctl_optmem_max) - 4)
+	if (optlen > READ_ONCE(sock_net(sk)->core.sysctl_optmem_max) - 4)
 		return -ENOBUFS;
 
 	p = kmalloc(optlen + 4, GFP_KERNEL);
@@ -1254,7 +1254,7 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
 
 		if (optlen < IP_MSFILTER_SIZE(0))
 			goto e_inval;
-		if (optlen > READ_ONCE(sysctl_optmem_max)) {
+		if (optlen > READ_ONCE(net->core.sysctl_optmem_max)) {
 			err = -ENOBUFS;
 			break;
 		}
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 9e8ebda170f1..56c3c467f9de 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -210,7 +210,7 @@ static int ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval,
 
 	if (optlen < GROUP_FILTER_SIZE(0))
 		return -EINVAL;
-	if (optlen > READ_ONCE(sysctl_optmem_max))
+	if (optlen > READ_ONCE(sock_net(sk)->core.sysctl_optmem_max))
 		return -ENOBUFS;
 
 	gsf = memdup_sockptr(optval, optlen);
@@ -244,7 +244,7 @@ static int compat_ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval,
 
 	if (optlen < size0)
 		return -EINVAL;
-	if (optlen > READ_ONCE(sysctl_optmem_max) - 4)
+	if (optlen > READ_ONCE(sock_net(sk)->core.sysctl_optmem_max) - 4)
 		return -ENOBUFS;
 
 	p = kmalloc(optlen + 4, GFP_KERNEL);
-- 
cgit v1.2.3


From 4ad4c1f394b84f9941a10aa8aaf11102478a390b Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Fri, 24 Nov 2023 18:10:03 +0000
Subject: dma-mapping: don't store redundant offsets

A bus_dma_region necessarily stores both CPU and DMA base addresses for
a range, so there's no need to also store the difference between them.

Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/acpi/scan.c        |  1 -
 drivers/of/address.c       |  1 -
 include/linux/dma-direct.h | 19 ++++++++++++-------
 kernel/dma/direct.c        |  1 -
 4 files changed, 12 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 02bb2cce423f..ee88a727f200 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1532,7 +1532,6 @@ int acpi_dma_get_range(struct device *dev, const struct bus_dma_region **map)
 			r->cpu_start = rentry->res->start;
 			r->dma_start = rentry->res->start - rentry->offset;
 			r->size = resource_size(rentry->res);
-			r->offset = rentry->offset;
 			r++;
 		}
 	}
diff --git a/drivers/of/address.c b/drivers/of/address.c
index b59956310f66..ae46a3605904 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -955,7 +955,6 @@ int of_dma_get_range(struct device_node *np, const struct bus_dma_region **map)
 		r->cpu_start = range.cpu_addr;
 		r->dma_start = range.bus_addr;
 		r->size = range.size;
-		r->offset = range.cpu_addr - range.bus_addr;
 		r++;
 	}
 out:
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 18aade195884..3eb3589ff43e 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -21,7 +21,6 @@ struct bus_dma_region {
 	phys_addr_t	cpu_start;
 	dma_addr_t	dma_start;
 	u64		size;
-	u64		offset;
 };
 
 static inline dma_addr_t translate_phys_to_dma(struct device *dev,
@@ -29,9 +28,12 @@ static inline dma_addr_t translate_phys_to_dma(struct device *dev,
 {
 	const struct bus_dma_region *m;
 
-	for (m = dev->dma_range_map; m->size; m++)
-		if (paddr >= m->cpu_start && paddr - m->cpu_start < m->size)
-			return (dma_addr_t)paddr - m->offset;
+	for (m = dev->dma_range_map; m->size; m++) {
+		u64 offset = paddr - m->cpu_start;
+
+		if (paddr >= m->cpu_start && offset < m->size)
+			return m->dma_start + offset;
+	}
 
 	/* make sure dma_capable fails when no translation is available */
 	return DMA_MAPPING_ERROR;
@@ -42,9 +44,12 @@ static inline phys_addr_t translate_dma_to_phys(struct device *dev,
 {
 	const struct bus_dma_region *m;
 
-	for (m = dev->dma_range_map; m->size; m++)
-		if (dma_addr >= m->dma_start && dma_addr - m->dma_start < m->size)
-			return (phys_addr_t)dma_addr + m->offset;
+	for (m = dev->dma_range_map; m->size; m++) {
+		u64 offset = dma_addr - m->dma_start;
+
+		if (dma_addr >= m->dma_start && offset < m->size)
+			return m->cpu_start + offset;
+	}
 
 	return (phys_addr_t)-1;
 }
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 73c95815789a..98b2e192fd69 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -677,7 +677,6 @@ int dma_direct_set_offset(struct device *dev, phys_addr_t cpu_start,
 		return -ENOMEM;
 	map[0].cpu_start = cpu_start;
 	map[0].dma_start = dma_start;
-	map[0].offset = offset;
 	map[0].size = size;
 	dev->dma_range_map = map;
 	return 0;
-- 
cgit v1.2.3


From 134c6eaa6087d78c0e289931ca15ae7a5007670d Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Wed, 13 Dec 2023 15:02:35 -0800
Subject: driver core: Add a guard() definition for the device_lock()

At present there are ~200 usages of device_lock() in the kernel. Some of
those usages lead to "goto unlock;" patterns which have proven to be
error prone. Define a "device" guard() definition to allow for those to
be cleaned up and prevent new ones from appearing.

Link: http://lore.kernel.org/r/657897453dda8_269bd29492@dwillia2-mobl3.amr.corp.intel.com.notmuch
Link: http://lore.kernel.org/r/6577b0c2a02df_a04c5294bb@dwillia2-xfh.jf.intel.com.notmuch
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Vishal Verma <vishal.l.verma@intel.com>
Link: https://lore.kernel.org/r/170250854466.1522182.17555361077409628655.stgit@dwillia2-xfh.jf.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/device.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/device.h b/include/linux/device.h
index d7a72a8749ea..6c83294395ac 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -1007,6 +1007,8 @@ static inline void device_unlock(struct device *dev)
 	mutex_unlock(&dev->mutex);
 }
 
+DEFINE_GUARD(device, struct device *, device_lock(_T), device_unlock(_T))
+
 static inline void device_lock_assert(struct device *dev)
 {
 	lockdep_assert_held(&dev->mutex);
-- 
cgit v1.2.3


From b059aef76c519226730dd18777c0e15dad4fae21 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 14 Dec 2023 17:57:35 -0800
Subject: netlink: specs: mptcp: rename the MPTCP path management spec

We assume in handful of places that the name of the spec is
the same as the name of the family. We could fix that but
it seems like a fair assumption to make. Rename the MPTCP
spec instead.

Reviewed-by: Mat Martineau <martineau@kernel.org>
Reviewed-by: Donald Hunter <donald.hunter@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/netlink/specs/mptcp.yaml    | 393 ------------------------------
 Documentation/netlink/specs/mptcp_pm.yaml | 393 ++++++++++++++++++++++++++++++
 MAINTAINERS                               |   2 +-
 include/uapi/linux/mptcp_pm.h             |   2 +-
 net/mptcp/mptcp_pm_gen.c                  |   2 +-
 net/mptcp/mptcp_pm_gen.h                  |   2 +-
 6 files changed, 397 insertions(+), 397 deletions(-)
 delete mode 100644 Documentation/netlink/specs/mptcp.yaml
 create mode 100644 Documentation/netlink/specs/mptcp_pm.yaml

(limited to 'include')

diff --git a/Documentation/netlink/specs/mptcp.yaml b/Documentation/netlink/specs/mptcp.yaml
deleted file mode 100644
index 49f90cfb4698..000000000000
--- a/Documentation/netlink/specs/mptcp.yaml
+++ /dev/null
@@ -1,393 +0,0 @@
-# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
-
-name: mptcp_pm
-protocol: genetlink-legacy
-doc: Multipath TCP.
-
-c-family-name: mptcp-pm-name
-c-version-name: mptcp-pm-ver
-max-by-define: true
-kernel-policy: per-op
-cmd-cnt-name: --mptcp-pm-cmd-after-last
-
-definitions:
-  -
-    type: enum
-    name: event-type
-    enum-name: mptcp-event-type
-    name-prefix: mptcp-event-
-    entries:
-     -
-      name: unspec
-      doc: unused event
-     -
-      name: created
-      doc:
-        token, family, saddr4 | saddr6, daddr4 | daddr6, sport, dport
-        A new MPTCP connection has been created. It is the good time to
-        allocate memory and send ADD_ADDR if needed. Depending on the
-        traffic-patterns it can take a long time until the
-        MPTCP_EVENT_ESTABLISHED is sent.
-     -
-      name: established
-      doc:
-        token, family, saddr4 | saddr6, daddr4 | daddr6, sport, dport
-        A MPTCP connection is established (can start new subflows).
-     -
-      name: closed
-      doc:
-        token
-        A MPTCP connection has stopped.
-     -
-      name: announced
-      value: 6
-      doc:
-        token, rem_id, family, daddr4 | daddr6 [, dport]
-        A new address has been announced by the peer.
-     -
-      name: removed
-      doc:
-        token, rem_id
-        An address has been lost by the peer.
-     -
-      name: sub-established
-      value: 10
-      doc:
-        token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 | daddr6, sport,
-        dport, backup, if_idx [, error]
-        A new subflow has been established. 'error' should not be set.
-     -
-      name: sub-closed
-      doc:
-        token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 | daddr6, sport,
-        dport, backup, if_idx [, error]
-        A subflow has been closed. An error (copy of sk_err) could be set if an
-        error has been detected for this subflow.
-     -
-      name: sub-priority
-      value: 13
-      doc:
-        token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 | daddr6, sport,
-        dport, backup, if_idx [, error]
-        The priority of a subflow has changed. 'error' should not be set.
-     -
-      name: listener-created
-      value: 15
-      doc:
-        family, sport, saddr4 | saddr6
-        A new PM listener is created.
-     -
-      name: listener-closed
-      doc:
-        family, sport, saddr4 | saddr6
-        A PM listener is closed.
-
-attribute-sets:
-  -
-    name: address
-    name-prefix: mptcp-pm-addr-attr-
-    attributes:
-      -
-        name: unspec
-        type: unused
-        value: 0
-      -
-        name: family
-        type: u16
-      -
-        name: id
-        type: u8
-      -
-        name: addr4
-        type: u32
-        byte-order: big-endian
-      -
-        name: addr6
-        type: binary
-        checks:
-          exact-len: 16
-      -
-        name: port
-        type: u16
-        byte-order: big-endian
-      -
-        name: flags
-        type: u32
-      -
-        name: if-idx
-        type: s32
-  -
-    name: subflow-attribute
-    name-prefix: mptcp-subflow-attr-
-    attributes:
-      -
-        name: unspec
-        type: unused
-        value: 0
-      -
-        name: token-rem
-        type: u32
-      -
-        name: token-loc
-        type: u32
-      -
-        name: relwrite-seq
-        type: u32
-      -
-        name: map-seq
-        type: u64
-      -
-        name: map-sfseq
-        type: u32
-      -
-        name: ssn-offset
-        type: u32
-      -
-        name: map-datalen
-        type: u16
-      -
-        name: flags
-        type: u32
-      -
-        name: id-rem
-        type: u8
-      -
-        name: id-loc
-        type: u8
-      -
-        name: pad
-        type: pad
-  -
-    name: endpoint
-    name-prefix: mptcp-pm-endpoint-
-    attributes:
-      -
-        name: addr
-        type: nest
-        nested-attributes: address
-  -
-    name: attr
-    name-prefix: mptcp-pm-attr-
-    attr-cnt-name: --mptcp-attr-after-last
-    attributes:
-      -
-        name: unspec
-        type: unused
-        value: 0
-      -
-        name: addr
-        type: nest
-        nested-attributes: address
-      -
-        name: rcv-add-addrs
-        type: u32
-      -
-        name: subflows
-        type: u32
-      -
-        name: token
-        type: u32
-      -
-        name: loc-id
-        type: u8
-      -
-        name: addr-remote
-        type: nest
-        nested-attributes: address
-  -
-    name: event-attr
-    enum-name: mptcp-event-attr
-    name-prefix: mptcp-attr-
-    attributes:
-      -
-        name: unspec
-        type: unused
-        value: 0
-      -
-        name: token
-        type: u32
-      -
-        name: family
-        type: u16
-      -
-        name: loc-id
-        type: u8
-      -
-        name: rem-id
-        type: u8
-      -
-        name: saddr4
-        type: u32
-        byte-order: big-endian
-      -
-        name: saddr6
-        type: binary
-        checks:
-          min-len: 16
-      -
-        name: daddr4
-        type: u32
-        byte-order: big-endian
-      -
-        name: daddr6
-        type: binary
-        checks:
-          min-len: 16
-      -
-        name: sport
-        type: u16
-        byte-order: big-endian
-      -
-        name: dport
-        type: u16
-        byte-order: big-endian
-      -
-        name: backup
-        type: u8
-      -
-        name: error
-        type: u8
-      -
-        name: flags
-        type: u16
-      -
-        name: timeout
-        type: u32
-      -
-        name: if_idx
-        type: u32
-      -
-        name: reset-reason
-        type: u32
-      -
-        name: reset-flags
-        type: u32
-      -
-        name: server-side
-        type: u8
-
-operations:
-  list:
-    -
-      name: unspec
-      doc: unused
-      value: 0
-    -
-      name: add-addr
-      doc: Add endpoint
-      attribute-set: endpoint
-      dont-validate: [ strict ]
-      flags: [ uns-admin-perm ]
-      do: &add-addr-attrs
-        request:
-          attributes:
-            - addr
-    -
-      name: del-addr
-      doc: Delete endpoint
-      attribute-set: endpoint
-      dont-validate: [ strict ]
-      flags: [ uns-admin-perm ]
-      do: *add-addr-attrs
-    -
-      name: get-addr
-      doc: Get endpoint information
-      attribute-set: endpoint
-      dont-validate: [ strict ]
-      flags: [ uns-admin-perm ]
-      do: &get-addr-attrs
-        request:
-          attributes:
-           - addr
-        reply:
-          attributes:
-           - addr
-      dump:
-        reply:
-         attributes:
-           - addr
-    -
-      name:  flush-addrs
-      doc: flush addresses
-      attribute-set: endpoint
-      dont-validate: [ strict ]
-      flags: [ uns-admin-perm ]
-      do: *add-addr-attrs
-    -
-      name: set-limits
-      doc: Set protocol limits
-      attribute-set: attr
-      dont-validate: [ strict ]
-      flags: [ uns-admin-perm ]
-      do: &mptcp-limits
-        request:
-          attributes:
-            - rcv-add-addrs
-            - subflows
-    -
-      name: get-limits
-      doc: Get protocol limits
-      attribute-set: attr
-      dont-validate: [ strict ]
-      do: &mptcp-get-limits
-        request:
-           attributes:
-            - rcv-add-addrs
-            - subflows
-        reply:
-          attributes:
-            - rcv-add-addrs
-            - subflows
-    -
-      name: set-flags
-      doc: Change endpoint flags
-      attribute-set: attr
-      dont-validate: [ strict ]
-      flags: [ uns-admin-perm ]
-      do: &mptcp-set-flags
-        request:
-          attributes:
-            - addr
-            - token
-            - addr-remote
-    -
-      name: announce
-      doc: announce new sf
-      attribute-set: attr
-      dont-validate: [ strict ]
-      flags: [ uns-admin-perm ]
-      do: &announce-add
-        request:
-          attributes:
-            - addr
-            - token
-    -
-      name: remove
-      doc: announce removal
-      attribute-set: attr
-      dont-validate: [ strict ]
-      flags: [ uns-admin-perm ]
-      do:
-        request:
-         attributes:
-           - token
-           - loc-id
-    -
-      name: subflow-create
-      doc: todo
-      attribute-set: attr
-      dont-validate: [ strict ]
-      flags: [ uns-admin-perm ]
-      do: &sf-create
-        request:
-          attributes:
-            - addr
-            - token
-            - addr-remote
-    -
-      name: subflow-destroy
-      doc: todo
-      attribute-set: attr
-      dont-validate: [ strict ]
-      flags: [ uns-admin-perm ]
-      do: *sf-create
diff --git a/Documentation/netlink/specs/mptcp_pm.yaml b/Documentation/netlink/specs/mptcp_pm.yaml
new file mode 100644
index 000000000000..49f90cfb4698
--- /dev/null
+++ b/Documentation/netlink/specs/mptcp_pm.yaml
@@ -0,0 +1,393 @@
+# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
+
+name: mptcp_pm
+protocol: genetlink-legacy
+doc: Multipath TCP.
+
+c-family-name: mptcp-pm-name
+c-version-name: mptcp-pm-ver
+max-by-define: true
+kernel-policy: per-op
+cmd-cnt-name: --mptcp-pm-cmd-after-last
+
+definitions:
+  -
+    type: enum
+    name: event-type
+    enum-name: mptcp-event-type
+    name-prefix: mptcp-event-
+    entries:
+     -
+      name: unspec
+      doc: unused event
+     -
+      name: created
+      doc:
+        token, family, saddr4 | saddr6, daddr4 | daddr6, sport, dport
+        A new MPTCP connection has been created. It is the good time to
+        allocate memory and send ADD_ADDR if needed. Depending on the
+        traffic-patterns it can take a long time until the
+        MPTCP_EVENT_ESTABLISHED is sent.
+     -
+      name: established
+      doc:
+        token, family, saddr4 | saddr6, daddr4 | daddr6, sport, dport
+        A MPTCP connection is established (can start new subflows).
+     -
+      name: closed
+      doc:
+        token
+        A MPTCP connection has stopped.
+     -
+      name: announced
+      value: 6
+      doc:
+        token, rem_id, family, daddr4 | daddr6 [, dport]
+        A new address has been announced by the peer.
+     -
+      name: removed
+      doc:
+        token, rem_id
+        An address has been lost by the peer.
+     -
+      name: sub-established
+      value: 10
+      doc:
+        token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 | daddr6, sport,
+        dport, backup, if_idx [, error]
+        A new subflow has been established. 'error' should not be set.
+     -
+      name: sub-closed
+      doc:
+        token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 | daddr6, sport,
+        dport, backup, if_idx [, error]
+        A subflow has been closed. An error (copy of sk_err) could be set if an
+        error has been detected for this subflow.
+     -
+      name: sub-priority
+      value: 13
+      doc:
+        token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 | daddr6, sport,
+        dport, backup, if_idx [, error]
+        The priority of a subflow has changed. 'error' should not be set.
+     -
+      name: listener-created
+      value: 15
+      doc:
+        family, sport, saddr4 | saddr6
+        A new PM listener is created.
+     -
+      name: listener-closed
+      doc:
+        family, sport, saddr4 | saddr6
+        A PM listener is closed.
+
+attribute-sets:
+  -
+    name: address
+    name-prefix: mptcp-pm-addr-attr-
+    attributes:
+      -
+        name: unspec
+        type: unused
+        value: 0
+      -
+        name: family
+        type: u16
+      -
+        name: id
+        type: u8
+      -
+        name: addr4
+        type: u32
+        byte-order: big-endian
+      -
+        name: addr6
+        type: binary
+        checks:
+          exact-len: 16
+      -
+        name: port
+        type: u16
+        byte-order: big-endian
+      -
+        name: flags
+        type: u32
+      -
+        name: if-idx
+        type: s32
+  -
+    name: subflow-attribute
+    name-prefix: mptcp-subflow-attr-
+    attributes:
+      -
+        name: unspec
+        type: unused
+        value: 0
+      -
+        name: token-rem
+        type: u32
+      -
+        name: token-loc
+        type: u32
+      -
+        name: relwrite-seq
+        type: u32
+      -
+        name: map-seq
+        type: u64
+      -
+        name: map-sfseq
+        type: u32
+      -
+        name: ssn-offset
+        type: u32
+      -
+        name: map-datalen
+        type: u16
+      -
+        name: flags
+        type: u32
+      -
+        name: id-rem
+        type: u8
+      -
+        name: id-loc
+        type: u8
+      -
+        name: pad
+        type: pad
+  -
+    name: endpoint
+    name-prefix: mptcp-pm-endpoint-
+    attributes:
+      -
+        name: addr
+        type: nest
+        nested-attributes: address
+  -
+    name: attr
+    name-prefix: mptcp-pm-attr-
+    attr-cnt-name: --mptcp-attr-after-last
+    attributes:
+      -
+        name: unspec
+        type: unused
+        value: 0
+      -
+        name: addr
+        type: nest
+        nested-attributes: address
+      -
+        name: rcv-add-addrs
+        type: u32
+      -
+        name: subflows
+        type: u32
+      -
+        name: token
+        type: u32
+      -
+        name: loc-id
+        type: u8
+      -
+        name: addr-remote
+        type: nest
+        nested-attributes: address
+  -
+    name: event-attr
+    enum-name: mptcp-event-attr
+    name-prefix: mptcp-attr-
+    attributes:
+      -
+        name: unspec
+        type: unused
+        value: 0
+      -
+        name: token
+        type: u32
+      -
+        name: family
+        type: u16
+      -
+        name: loc-id
+        type: u8
+      -
+        name: rem-id
+        type: u8
+      -
+        name: saddr4
+        type: u32
+        byte-order: big-endian
+      -
+        name: saddr6
+        type: binary
+        checks:
+          min-len: 16
+      -
+        name: daddr4
+        type: u32
+        byte-order: big-endian
+      -
+        name: daddr6
+        type: binary
+        checks:
+          min-len: 16
+      -
+        name: sport
+        type: u16
+        byte-order: big-endian
+      -
+        name: dport
+        type: u16
+        byte-order: big-endian
+      -
+        name: backup
+        type: u8
+      -
+        name: error
+        type: u8
+      -
+        name: flags
+        type: u16
+      -
+        name: timeout
+        type: u32
+      -
+        name: if_idx
+        type: u32
+      -
+        name: reset-reason
+        type: u32
+      -
+        name: reset-flags
+        type: u32
+      -
+        name: server-side
+        type: u8
+
+operations:
+  list:
+    -
+      name: unspec
+      doc: unused
+      value: 0
+    -
+      name: add-addr
+      doc: Add endpoint
+      attribute-set: endpoint
+      dont-validate: [ strict ]
+      flags: [ uns-admin-perm ]
+      do: &add-addr-attrs
+        request:
+          attributes:
+            - addr
+    -
+      name: del-addr
+      doc: Delete endpoint
+      attribute-set: endpoint
+      dont-validate: [ strict ]
+      flags: [ uns-admin-perm ]
+      do: *add-addr-attrs
+    -
+      name: get-addr
+      doc: Get endpoint information
+      attribute-set: endpoint
+      dont-validate: [ strict ]
+      flags: [ uns-admin-perm ]
+      do: &get-addr-attrs
+        request:
+          attributes:
+           - addr
+        reply:
+          attributes:
+           - addr
+      dump:
+        reply:
+         attributes:
+           - addr
+    -
+      name:  flush-addrs
+      doc: flush addresses
+      attribute-set: endpoint
+      dont-validate: [ strict ]
+      flags: [ uns-admin-perm ]
+      do: *add-addr-attrs
+    -
+      name: set-limits
+      doc: Set protocol limits
+      attribute-set: attr
+      dont-validate: [ strict ]
+      flags: [ uns-admin-perm ]
+      do: &mptcp-limits
+        request:
+          attributes:
+            - rcv-add-addrs
+            - subflows
+    -
+      name: get-limits
+      doc: Get protocol limits
+      attribute-set: attr
+      dont-validate: [ strict ]
+      do: &mptcp-get-limits
+        request:
+           attributes:
+            - rcv-add-addrs
+            - subflows
+        reply:
+          attributes:
+            - rcv-add-addrs
+            - subflows
+    -
+      name: set-flags
+      doc: Change endpoint flags
+      attribute-set: attr
+      dont-validate: [ strict ]
+      flags: [ uns-admin-perm ]
+      do: &mptcp-set-flags
+        request:
+          attributes:
+            - addr
+            - token
+            - addr-remote
+    -
+      name: announce
+      doc: announce new sf
+      attribute-set: attr
+      dont-validate: [ strict ]
+      flags: [ uns-admin-perm ]
+      do: &announce-add
+        request:
+          attributes:
+            - addr
+            - token
+    -
+      name: remove
+      doc: announce removal
+      attribute-set: attr
+      dont-validate: [ strict ]
+      flags: [ uns-admin-perm ]
+      do:
+        request:
+         attributes:
+           - token
+           - loc-id
+    -
+      name: subflow-create
+      doc: todo
+      attribute-set: attr
+      dont-validate: [ strict ]
+      flags: [ uns-admin-perm ]
+      do: &sf-create
+        request:
+          attributes:
+            - addr
+            - token
+            - addr-remote
+    -
+      name: subflow-destroy
+      doc: todo
+      attribute-set: attr
+      dont-validate: [ strict ]
+      flags: [ uns-admin-perm ]
+      do: *sf-create
diff --git a/MAINTAINERS b/MAINTAINERS
index daf440129535..dda78b4ce707 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15099,7 +15099,7 @@ W:	https://github.com/multipath-tcp/mptcp_net-next/wiki
 B:	https://github.com/multipath-tcp/mptcp_net-next/issues
 T:	git https://github.com/multipath-tcp/mptcp_net-next.git export-net
 T:	git https://github.com/multipath-tcp/mptcp_net-next.git export
-F:	Documentation/netlink/specs/mptcp.yaml
+F:	Documentation/netlink/specs/mptcp_pm.yaml
 F:	Documentation/networking/mptcp-sysctl.rst
 F:	include/net/mptcp.h
 F:	include/trace/events/mptcp.h
diff --git a/include/uapi/linux/mptcp_pm.h b/include/uapi/linux/mptcp_pm.h
index b5d11aece408..50589e5dd6a3 100644
--- a/include/uapi/linux/mptcp_pm.h
+++ b/include/uapi/linux/mptcp_pm.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
 /* Do not edit directly, auto-generated from: */
-/*	Documentation/netlink/specs/mptcp.yaml */
+/*	Documentation/netlink/specs/mptcp_pm.yaml */
 /* YNL-GEN uapi header */
 
 #ifndef _UAPI_LINUX_MPTCP_PM_H
diff --git a/net/mptcp/mptcp_pm_gen.c b/net/mptcp/mptcp_pm_gen.c
index a2325e70ddab..670da7822e6c 100644
--- a/net/mptcp/mptcp_pm_gen.c
+++ b/net/mptcp/mptcp_pm_gen.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
 /* Do not edit directly, auto-generated from: */
-/*	Documentation/netlink/specs/mptcp.yaml */
+/*	Documentation/netlink/specs/mptcp_pm.yaml */
 /* YNL-GEN kernel source */
 
 #include <net/netlink.h>
diff --git a/net/mptcp/mptcp_pm_gen.h b/net/mptcp/mptcp_pm_gen.h
index 10579d184587..ac9fc7225b6a 100644
--- a/net/mptcp/mptcp_pm_gen.h
+++ b/net/mptcp/mptcp_pm_gen.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
 /* Do not edit directly, auto-generated from: */
-/*	Documentation/netlink/specs/mptcp.yaml */
+/*	Documentation/netlink/specs/mptcp_pm.yaml */
 /* YNL-GEN kernel header */
 
 #ifndef _LINUX_MPTCP_PM_GEN_H
-- 
cgit v1.2.3


From 7f38b70042fcaa49219045bd1a9a2836e27a58ac Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 15 Dec 2023 11:15:27 +0000
Subject: of: device: Export of_device_make_bus_id()

This helper is really handy to create unique device names based on their
device tree path, we may need it outside of the OF core (in the NVMEM
subsystem) so let's export it. As this helper has nothing patform
specific, let's move it to of/device.c instead of of/platform.c so we
can add its prototype to of_device.h.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/20231215111536.316972-2-srinivas.kandagatla@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/of/device.c       | 41 +++++++++++++++++++++++++++++++++++++++++
 drivers/of/platform.c     | 40 ----------------------------------------
 include/linux/of_device.h |  6 ++++++
 3 files changed, 47 insertions(+), 40 deletions(-)

(limited to 'include')

diff --git a/drivers/of/device.c b/drivers/of/device.c
index 1ca42ad9dd15..6e9572c4af83 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -304,3 +304,44 @@ int of_device_uevent_modalias(const struct device *dev, struct kobj_uevent_env *
 	return 0;
 }
 EXPORT_SYMBOL_GPL(of_device_uevent_modalias);
+
+/**
+ * of_device_make_bus_id - Use the device node data to assign a unique name
+ * @dev: pointer to device structure that is linked to a device tree node
+ *
+ * This routine will first try using the translated bus address to
+ * derive a unique name. If it cannot, then it will prepend names from
+ * parent nodes until a unique name can be derived.
+ */
+void of_device_make_bus_id(struct device *dev)
+{
+	struct device_node *node = dev->of_node;
+	const __be32 *reg;
+	u64 addr;
+	u32 mask;
+
+	/* Construct the name, using parent nodes if necessary to ensure uniqueness */
+	while (node->parent) {
+		/*
+		 * If the address can be translated, then that is as much
+		 * uniqueness as we need. Make it the first component and return
+		 */
+		reg = of_get_property(node, "reg", NULL);
+		if (reg && (addr = of_translate_address(node, reg)) != OF_BAD_ADDR) {
+			if (!of_property_read_u32(node, "mask", &mask))
+				dev_set_name(dev, dev_name(dev) ? "%llx.%x.%pOFn:%s" : "%llx.%x.%pOFn",
+					     addr, ffs(mask) - 1, node, dev_name(dev));
+
+			else
+				dev_set_name(dev, dev_name(dev) ? "%llx.%pOFn:%s" : "%llx.%pOFn",
+					     addr, node, dev_name(dev));
+			return;
+		}
+
+		/* format arguments only used if dev_name() resolves to NULL */
+		dev_set_name(dev, dev_name(dev) ? "%s:%s" : "%s",
+			     kbasename(node->full_name), dev_name(dev));
+		node = node->parent;
+	}
+}
+EXPORT_SYMBOL_GPL(of_device_make_bus_id);
diff --git a/drivers/of/platform.c b/drivers/of/platform.c
index 126d265aa7d8..c39e49a1eba0 100644
--- a/drivers/of/platform.c
+++ b/drivers/of/platform.c
@@ -97,46 +97,6 @@ static const struct of_device_id of_skipped_node_table[] = {
  * mechanism for creating devices from device tree nodes.
  */
 
-/**
- * of_device_make_bus_id - Use the device node data to assign a unique name
- * @dev: pointer to device structure that is linked to a device tree node
- *
- * This routine will first try using the translated bus address to
- * derive a unique name. If it cannot, then it will prepend names from
- * parent nodes until a unique name can be derived.
- */
-static void of_device_make_bus_id(struct device *dev)
-{
-	struct device_node *node = dev->of_node;
-	const __be32 *reg;
-	u64 addr;
-	u32 mask;
-
-	/* Construct the name, using parent nodes if necessary to ensure uniqueness */
-	while (node->parent) {
-		/*
-		 * If the address can be translated, then that is as much
-		 * uniqueness as we need. Make it the first component and return
-		 */
-		reg = of_get_property(node, "reg", NULL);
-		if (reg && (addr = of_translate_address(node, reg)) != OF_BAD_ADDR) {
-			if (!of_property_read_u32(node, "mask", &mask))
-				dev_set_name(dev, dev_name(dev) ? "%llx.%x.%pOFn:%s" : "%llx.%x.%pOFn",
-					     addr, ffs(mask) - 1, node, dev_name(dev));
-
-			else
-				dev_set_name(dev, dev_name(dev) ? "%llx.%pOFn:%s" : "%llx.%pOFn",
-					     addr, node, dev_name(dev));
-			return;
-		}
-
-		/* format arguments only used if dev_name() resolves to NULL */
-		dev_set_name(dev, dev_name(dev) ? "%s:%s" : "%s",
-			     kbasename(node->full_name), dev_name(dev));
-		node = node->parent;
-	}
-}
-
 /**
  * of_device_alloc - Allocate and initialize an of_device
  * @np: device node to assign to device
diff --git a/include/linux/of_device.h b/include/linux/of_device.h
index 2c7a3d4bc775..a72661e47faa 100644
--- a/include/linux/of_device.h
+++ b/include/linux/of_device.h
@@ -40,6 +40,9 @@ static inline int of_dma_configure(struct device *dev,
 {
 	return of_dma_configure_id(dev, np, force_dma, NULL);
 }
+
+void of_device_make_bus_id(struct device *dev);
+
 #else /* CONFIG_OF */
 
 static inline int of_driver_match_device(struct device *dev,
@@ -82,6 +85,9 @@ static inline int of_dma_configure(struct device *dev,
 {
 	return 0;
 }
+
+static inline void of_device_make_bus_id(struct device *dev) {}
+
 #endif /* CONFIG_OF */
 
 #endif /* _LINUX_OF_DEVICE_H */
-- 
cgit v1.2.3


From 4a1a40233b4a9fc159a5c7a27dc34c5c7bc5be55 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 15 Dec 2023 11:15:28 +0000
Subject: nvmem: Move of_nvmem_layout_get_container() in another header

nvmem-consumer.h is included by consumer devices, extracting data from
NVMEM devices whereas nvmem-provider.h is included by devices providing
NVMEM content.

The only users of of_nvmem_layout_get_container() outside of the core
are layout drivers, so better move its prototype to nvmem-provider.h.

While we do so, we also move the kdoc associated with the function to
the header rather than the .c file.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/20231215111536.316972-3-srinivas.kandagatla@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/nvmem/core.c           |  8 --------
 include/linux/nvmem-consumer.h |  7 -------
 include/linux/nvmem-provider.h | 21 +++++++++++++++++++++
 3 files changed, 21 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index 608b352a7d91..b5b6ec8e04bb 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -847,14 +847,6 @@ static int nvmem_add_cells_from_layout(struct nvmem_device *nvmem)
 }
 
 #if IS_ENABLED(CONFIG_OF)
-/**
- * of_nvmem_layout_get_container() - Get OF node to layout container.
- *
- * @nvmem: nvmem device.
- *
- * Return: a node pointer with refcount incremented or NULL if no
- * container exists. Use of_node_put() on it when done.
- */
 struct device_node *of_nvmem_layout_get_container(struct nvmem_device *nvmem)
 {
 	return of_get_child_by_name(nvmem->dev.of_node, "nvmem-layout");
diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h
index 6ec4b9743e25..2d306fa13b1a 100644
--- a/include/linux/nvmem-consumer.h
+++ b/include/linux/nvmem-consumer.h
@@ -247,7 +247,6 @@ struct nvmem_cell *of_nvmem_cell_get(struct device_node *np,
 				     const char *id);
 struct nvmem_device *of_nvmem_device_get(struct device_node *np,
 					 const char *name);
-struct device_node *of_nvmem_layout_get_container(struct nvmem_device *nvmem);
 #else
 static inline struct nvmem_cell *of_nvmem_cell_get(struct device_node *np,
 						   const char *id)
@@ -260,12 +259,6 @@ static inline struct nvmem_device *of_nvmem_device_get(struct device_node *np,
 {
 	return ERR_PTR(-EOPNOTSUPP);
 }
-
-static inline struct device_node *
-of_nvmem_layout_get_container(struct nvmem_device *nvmem)
-{
-	return NULL;
-}
 #endif /* CONFIG_NVMEM && CONFIG_OF */
 
 #endif  /* ifndef _LINUX_NVMEM_CONSUMER_H */
diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h
index e3930835235b..e5de21516387 100644
--- a/include/linux/nvmem-provider.h
+++ b/include/linux/nvmem-provider.h
@@ -244,6 +244,27 @@ nvmem_layout_get_match_data(struct nvmem_device *nvmem,
 
 #endif /* CONFIG_NVMEM */
 
+#if IS_ENABLED(CONFIG_NVMEM) && IS_ENABLED(CONFIG_OF)
+
+/**
+ * of_nvmem_layout_get_container() - Get OF node of layout container
+ *
+ * @nvmem: nvmem device
+ *
+ * Return: a node pointer with refcount incremented or NULL if no
+ * container exists. Use of_node_put() on it when done.
+ */
+struct device_node *of_nvmem_layout_get_container(struct nvmem_device *nvmem);
+
+#else  /* CONFIG_NVMEM && CONFIG_OF */
+
+static inline struct device_node *of_nvmem_layout_get_container(struct nvmem_device *nvmem)
+{
+	return NULL;
+}
+
+#endif /* CONFIG_NVMEM && CONFIG_OF */
+
 #define module_nvmem_layout_driver(__layout_driver)		\
 	module_driver(__layout_driver, nvmem_layout_register,	\
 		      nvmem_layout_unregister)
-- 
cgit v1.2.3


From 1b7c298a4ecbc28cc6ee94005734bff55eb83d22 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 15 Dec 2023 11:15:30 +0000
Subject: nvmem: Simplify the ->add_cells() hook

The layout entry is not used and will anyway be made useless by the new
layout bus infrastructure coming next, so drop it. While at it, clarify
the kdoc entry.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/20231215111536.316972-5-srinivas.kandagatla@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/nvmem/core.c             | 2 +-
 drivers/nvmem/layouts/onie-tlv.c | 3 +--
 drivers/nvmem/layouts/sl28vpd.c  | 3 +--
 include/linux/nvmem-provider.h   | 8 +++-----
 4 files changed, 6 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index b5e5ce67398f..f63db5e01fca 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -816,7 +816,7 @@ static int nvmem_add_cells_from_layout(struct nvmem_device *nvmem)
 	int ret;
 
 	if (layout && layout->add_cells) {
-		ret = layout->add_cells(&nvmem->dev, nvmem, layout);
+		ret = layout->add_cells(&nvmem->dev, nvmem);
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/nvmem/layouts/onie-tlv.c b/drivers/nvmem/layouts/onie-tlv.c
index 59fc87ccfcff..defd42d4375c 100644
--- a/drivers/nvmem/layouts/onie-tlv.c
+++ b/drivers/nvmem/layouts/onie-tlv.c
@@ -182,8 +182,7 @@ static bool onie_tlv_crc_is_valid(struct device *dev, size_t table_len, u8 *tabl
 	return true;
 }
 
-static int onie_tlv_parse_table(struct device *dev, struct nvmem_device *nvmem,
-				struct nvmem_layout *layout)
+static int onie_tlv_parse_table(struct device *dev, struct nvmem_device *nvmem)
 {
 	struct onie_tlv_hdr hdr;
 	size_t table_len, data_len, hdr_len;
diff --git a/drivers/nvmem/layouts/sl28vpd.c b/drivers/nvmem/layouts/sl28vpd.c
index 05671371f631..26c7cf21b523 100644
--- a/drivers/nvmem/layouts/sl28vpd.c
+++ b/drivers/nvmem/layouts/sl28vpd.c
@@ -80,8 +80,7 @@ static int sl28vpd_v1_check_crc(struct device *dev, struct nvmem_device *nvmem)
 	return 0;
 }
 
-static int sl28vpd_add_cells(struct device *dev, struct nvmem_device *nvmem,
-			     struct nvmem_layout *layout)
+static int sl28vpd_add_cells(struct device *dev, struct nvmem_device *nvmem)
 {
 	const struct nvmem_cell_info *pinfo;
 	struct nvmem_cell_info info = {0};
diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h
index e5de21516387..3939991b3c5f 100644
--- a/include/linux/nvmem-provider.h
+++ b/include/linux/nvmem-provider.h
@@ -156,9 +156,8 @@ struct nvmem_cell_table {
  *
  * @name:		Layout name.
  * @of_match_table:	Open firmware match table.
- * @add_cells:		Will be called if a nvmem device is found which
- *			has this layout. The function will add layout
- *			specific cells with nvmem_add_one_cell().
+ * @add_cells:		Called to populate the layout using
+ *			nvmem_add_one_cell().
  * @fixup_cell_info:	Will be called before a cell is added. Can be
  *			used to modify the nvmem_cell_info.
  * @owner:		Pointer to struct module.
@@ -172,8 +171,7 @@ struct nvmem_cell_table {
 struct nvmem_layout {
 	const char *name;
 	const struct of_device_id *of_match_table;
-	int (*add_cells)(struct device *dev, struct nvmem_device *nvmem,
-			 struct nvmem_layout *layout);
+	int (*add_cells)(struct device *dev, struct nvmem_device *nvmem);
 	void (*fixup_cell_info)(struct nvmem_device *nvmem,
 				struct nvmem_layout *layout,
 				struct nvmem_cell_info *cell);
-- 
cgit v1.2.3


From 1172460e716784ac7e1049a537bdca8edbf97360 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 15 Dec 2023 11:15:31 +0000
Subject: nvmem: Move and rename ->fixup_cell_info()

This hook is meant to be used by any provider and instantiating a layout
just for this is useless. Let's instead move this hook to the nvmem
device and add it to the config structure to be easily shared by the
providers.

While at moving this hook, rename it ->fixup_dt_cell_info() to clarify
its main intended purpose.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/20231215111536.316972-6-srinivas.kandagatla@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/nvmem/core.c           |  6 +++---
 drivers/nvmem/imx-ocotp.c      | 11 +++--------
 drivers/nvmem/internals.h      |  2 ++
 drivers/nvmem/mtk-efuse.c      | 11 +++--------
 include/linux/nvmem-provider.h |  9 ++++-----
 5 files changed, 15 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index f63db5e01fca..a885713d6b4b 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -675,7 +675,6 @@ static int nvmem_validate_keepouts(struct nvmem_device *nvmem)
 
 static int nvmem_add_cells_from_dt(struct nvmem_device *nvmem, struct device_node *np)
 {
-	struct nvmem_layout *layout = nvmem->layout;
 	struct device *dev = &nvmem->dev;
 	struct device_node *child;
 	const __be32 *addr;
@@ -705,8 +704,8 @@ static int nvmem_add_cells_from_dt(struct nvmem_device *nvmem, struct device_nod
 
 		info.np = of_node_get(child);
 
-		if (layout && layout->fixup_cell_info)
-			layout->fixup_cell_info(nvmem, layout, &info);
+		if (nvmem->fixup_dt_cell_info)
+			nvmem->fixup_dt_cell_info(nvmem, &info);
 
 		ret = nvmem_add_one_cell(nvmem, &info);
 		kfree(info.name);
@@ -895,6 +894,7 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config)
 
 	kref_init(&nvmem->refcnt);
 	INIT_LIST_HEAD(&nvmem->cells);
+	nvmem->fixup_dt_cell_info = config->fixup_dt_cell_info;
 
 	nvmem->owner = config->owner;
 	if (!nvmem->owner && config->dev->driver)
diff --git a/drivers/nvmem/imx-ocotp.c b/drivers/nvmem/imx-ocotp.c
index f1e202efaa49..79dd4fda0329 100644
--- a/drivers/nvmem/imx-ocotp.c
+++ b/drivers/nvmem/imx-ocotp.c
@@ -583,17 +583,12 @@ static const struct of_device_id imx_ocotp_dt_ids[] = {
 };
 MODULE_DEVICE_TABLE(of, imx_ocotp_dt_ids);
 
-static void imx_ocotp_fixup_cell_info(struct nvmem_device *nvmem,
-				      struct nvmem_layout *layout,
-				      struct nvmem_cell_info *cell)
+static void imx_ocotp_fixup_dt_cell_info(struct nvmem_device *nvmem,
+					 struct nvmem_cell_info *cell)
 {
 	cell->read_post_process = imx_ocotp_cell_pp;
 }
 
-static struct nvmem_layout imx_ocotp_layout = {
-	.fixup_cell_info = imx_ocotp_fixup_cell_info,
-};
-
 static int imx_ocotp_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -619,7 +614,7 @@ static int imx_ocotp_probe(struct platform_device *pdev)
 	imx_ocotp_nvmem_config.size = 4 * priv->params->nregs;
 	imx_ocotp_nvmem_config.dev = dev;
 	imx_ocotp_nvmem_config.priv = priv;
-	imx_ocotp_nvmem_config.layout = &imx_ocotp_layout;
+	imx_ocotp_nvmem_config.fixup_dt_cell_info = &imx_ocotp_fixup_dt_cell_info;
 
 	priv->config = &imx_ocotp_nvmem_config;
 
diff --git a/drivers/nvmem/internals.h b/drivers/nvmem/internals.h
index ce353831cd65..893553fbdf51 100644
--- a/drivers/nvmem/internals.h
+++ b/drivers/nvmem/internals.h
@@ -23,6 +23,8 @@ struct nvmem_device {
 	struct bin_attribute	eeprom;
 	struct device		*base_dev;
 	struct list_head	cells;
+	void (*fixup_dt_cell_info)(struct nvmem_device *nvmem,
+				   struct nvmem_cell_info *cell);
 	const struct nvmem_keepout *keepout;
 	unsigned int		nkeepout;
 	nvmem_reg_read_t	reg_read;
diff --git a/drivers/nvmem/mtk-efuse.c b/drivers/nvmem/mtk-efuse.c
index 87c94686cfd2..84f05b40a411 100644
--- a/drivers/nvmem/mtk-efuse.c
+++ b/drivers/nvmem/mtk-efuse.c
@@ -45,9 +45,8 @@ static int mtk_efuse_gpu_speedbin_pp(void *context, const char *id, int index,
 	return 0;
 }
 
-static void mtk_efuse_fixup_cell_info(struct nvmem_device *nvmem,
-				      struct nvmem_layout *layout,
-				      struct nvmem_cell_info *cell)
+static void mtk_efuse_fixup_dt_cell_info(struct nvmem_device *nvmem,
+					 struct nvmem_cell_info *cell)
 {
 	size_t sz = strlen(cell->name);
 
@@ -61,10 +60,6 @@ static void mtk_efuse_fixup_cell_info(struct nvmem_device *nvmem,
 		cell->read_post_process = mtk_efuse_gpu_speedbin_pp;
 }
 
-static struct nvmem_layout mtk_efuse_layout = {
-	.fixup_cell_info = mtk_efuse_fixup_cell_info,
-};
-
 static int mtk_efuse_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -91,7 +86,7 @@ static int mtk_efuse_probe(struct platform_device *pdev)
 	econfig.priv = priv;
 	econfig.dev = dev;
 	if (pdata->uses_post_processing)
-		econfig.layout = &mtk_efuse_layout;
+		econfig.fixup_dt_cell_info = &mtk_efuse_fixup_dt_cell_info;
 	nvmem = devm_nvmem_register(dev, &econfig);
 
 	return PTR_ERR_OR_ZERO(nvmem);
diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h
index 3939991b3c5f..36415a602d9e 100644
--- a/include/linux/nvmem-provider.h
+++ b/include/linux/nvmem-provider.h
@@ -83,6 +83,8 @@ struct nvmem_cell_info {
  * @cells:	Optional array of pre-defined NVMEM cells.
  * @ncells:	Number of elements in cells.
  * @add_legacy_fixed_of_cells:	Read fixed NVMEM cells from old OF syntax.
+ * @fixup_dt_cell_info: Will be called before a cell is added. Can be
+ *		used to modify the nvmem_cell_info.
  * @keepout:	Optional array of keepout ranges (sorted ascending by start).
  * @nkeepout:	Number of elements in the keepout array.
  * @type:	Type of the nvmem storage
@@ -113,6 +115,8 @@ struct nvmem_config {
 	const struct nvmem_cell_info	*cells;
 	int			ncells;
 	bool			add_legacy_fixed_of_cells;
+	void (*fixup_dt_cell_info)(struct nvmem_device *nvmem,
+				   struct nvmem_cell_info *cell);
 	const struct nvmem_keepout *keepout;
 	unsigned int		nkeepout;
 	enum nvmem_type		type;
@@ -158,8 +162,6 @@ struct nvmem_cell_table {
  * @of_match_table:	Open firmware match table.
  * @add_cells:		Called to populate the layout using
  *			nvmem_add_one_cell().
- * @fixup_cell_info:	Will be called before a cell is added. Can be
- *			used to modify the nvmem_cell_info.
  * @owner:		Pointer to struct module.
  * @node:		List node.
  *
@@ -172,9 +174,6 @@ struct nvmem_layout {
 	const char *name;
 	const struct of_device_id *of_match_table;
 	int (*add_cells)(struct device *dev, struct nvmem_device *nvmem);
-	void (*fixup_cell_info)(struct nvmem_device *nvmem,
-				struct nvmem_layout *layout,
-				struct nvmem_cell_info *cell);
 
 	/* private */
 	struct module *owner;
-- 
cgit v1.2.3


From fc29fd821d9ac2ae3d32a722fac39ce874efb883 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 15 Dec 2023 11:15:32 +0000
Subject: nvmem: core: Rework layouts to become regular devices
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Current layout support was initially written without modules support in
mind. When the requirement for module support rose, the existing base
was improved to adopt modularization support, but kind of a design flaw
was introduced. With the existing implementation, when a storage device
registers into NVMEM, the core tries to hook a layout (if any) and
populates its cells immediately. This means, if the hardware description
expects a layout to be hooked up, but no driver was provided for that,
the storage medium will fail to probe and try later from
scratch. Even if we consider that the hardware description shall be
correct, we could still probe the storage device (especially if it
contains the rootfs).

One way to overcome this situation is to consider the layouts as
devices, and leverage the native notifier mechanism. When a new NVMEM
device is registered, we can populate its nvmem-layout child, if any,
and wait for the matching to be done in order to get the cells (the
waiting can be easily done with the NVMEM notifiers). If the layout
driver is compiled as a module, it should automatically be loaded. This
way, there is no strong order to enforce, any NVMEM device creation
or NVMEM layout driver insertion will be observed as a new event which
may lead to the creation of additional cells, without disturbing the
probes with costly (and sometimes endless) deferrals.

In order to achieve that goal we create a new bus for the nvmem-layouts
with minimal logic to match nvmem-layout devices with nvmem-layout
drivers. All this infrastructure code is created in the layouts.c file.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Tested-by: Rafał Miłecki <rafal@milecki.pl>
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/20231215111536.316972-7-srinivas.kandagatla@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/nvmem/Kconfig            |   1 +
 drivers/nvmem/Makefile           |   2 +
 drivers/nvmem/core.c             | 170 ++++++++++++---------------------
 drivers/nvmem/internals.h        |  21 ++++
 drivers/nvmem/layouts.c          | 201 +++++++++++++++++++++++++++++++++++++++
 drivers/nvmem/layouts/Kconfig    |   8 ++
 drivers/nvmem/layouts/onie-tlv.c |  24 ++++-
 drivers/nvmem/layouts/sl28vpd.c  |  24 ++++-
 include/linux/nvmem-provider.h   |  38 ++++----
 9 files changed, 354 insertions(+), 135 deletions(-)
 create mode 100644 drivers/nvmem/layouts.c

(limited to 'include')

diff --git a/drivers/nvmem/Kconfig b/drivers/nvmem/Kconfig
index 5bc9c4874fe3..283134498fbc 100644
--- a/drivers/nvmem/Kconfig
+++ b/drivers/nvmem/Kconfig
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 menuconfig NVMEM
 	bool "NVMEM Support"
+	imply NVMEM_LAYOUTS
 	help
 	  Support for NVMEM(Non Volatile Memory) devices like EEPROM, EFUSES...
 
diff --git a/drivers/nvmem/Makefile b/drivers/nvmem/Makefile
index 423baf089515..cdd01fbf1313 100644
--- a/drivers/nvmem/Makefile
+++ b/drivers/nvmem/Makefile
@@ -5,6 +5,8 @@
 
 obj-$(CONFIG_NVMEM)		+= nvmem_core.o
 nvmem_core-y			:= core.o
+obj-$(CONFIG_NVMEM_LAYOUTS)	+= nvmem_layouts.o
+nvmem_layouts-y			:= layouts.o
 obj-y				+= layouts/
 
 # Devices
diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index a885713d6b4b..4c2154ddf8a7 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -55,9 +55,6 @@ static LIST_HEAD(nvmem_lookup_list);
 
 static BLOCKING_NOTIFIER_HEAD(nvmem_notifier);
 
-static DEFINE_SPINLOCK(nvmem_layout_lock);
-static LIST_HEAD(nvmem_layouts);
-
 static int __nvmem_reg_read(struct nvmem_device *nvmem, unsigned int offset,
 			    void *val, size_t bytes)
 {
@@ -740,97 +737,22 @@ static int nvmem_add_cells_from_fixed_layout(struct nvmem_device *nvmem)
 	return err;
 }
 
-int __nvmem_layout_register(struct nvmem_layout *layout, struct module *owner)
+int nvmem_layout_register(struct nvmem_layout *layout)
 {
-	layout->owner = owner;
-
-	spin_lock(&nvmem_layout_lock);
-	list_add(&layout->node, &nvmem_layouts);
-	spin_unlock(&nvmem_layout_lock);
-
-	blocking_notifier_call_chain(&nvmem_notifier, NVMEM_LAYOUT_ADD, layout);
+	if (!layout->add_cells)
+		return -EINVAL;
 
-	return 0;
+	/* Populate the cells */
+	return layout->add_cells(&layout->nvmem->dev, layout->nvmem);
 }
-EXPORT_SYMBOL_GPL(__nvmem_layout_register);
+EXPORT_SYMBOL_GPL(nvmem_layout_register);
 
 void nvmem_layout_unregister(struct nvmem_layout *layout)
 {
-	blocking_notifier_call_chain(&nvmem_notifier, NVMEM_LAYOUT_REMOVE, layout);
-
-	spin_lock(&nvmem_layout_lock);
-	list_del(&layout->node);
-	spin_unlock(&nvmem_layout_lock);
+	/* Keep the API even with an empty stub in case we need it later */
 }
 EXPORT_SYMBOL_GPL(nvmem_layout_unregister);
 
-static struct nvmem_layout *nvmem_layout_get(struct nvmem_device *nvmem)
-{
-	struct device_node *layout_np;
-	struct nvmem_layout *l, *layout = ERR_PTR(-EPROBE_DEFER);
-
-	layout_np = of_nvmem_layout_get_container(nvmem);
-	if (!layout_np)
-		return NULL;
-
-	/* Fixed layouts don't have a matching driver */
-	if (of_device_is_compatible(layout_np, "fixed-layout")) {
-		of_node_put(layout_np);
-		return NULL;
-	}
-
-	/*
-	 * In case the nvmem device was built-in while the layout was built as a
-	 * module, we shall manually request the layout driver loading otherwise
-	 * we'll never have any match.
-	 */
-	of_request_module(layout_np);
-
-	spin_lock(&nvmem_layout_lock);
-
-	list_for_each_entry(l, &nvmem_layouts, node) {
-		if (of_match_node(l->of_match_table, layout_np)) {
-			if (try_module_get(l->owner))
-				layout = l;
-
-			break;
-		}
-	}
-
-	spin_unlock(&nvmem_layout_lock);
-	of_node_put(layout_np);
-
-	return layout;
-}
-
-static void nvmem_layout_put(struct nvmem_layout *layout)
-{
-	if (layout)
-		module_put(layout->owner);
-}
-
-static int nvmem_add_cells_from_layout(struct nvmem_device *nvmem)
-{
-	struct nvmem_layout *layout = nvmem->layout;
-	int ret;
-
-	if (layout && layout->add_cells) {
-		ret = layout->add_cells(&nvmem->dev, nvmem);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-
-#if IS_ENABLED(CONFIG_OF)
-struct device_node *of_nvmem_layout_get_container(struct nvmem_device *nvmem)
-{
-	return of_get_child_by_name(nvmem->dev.of_node, "nvmem-layout");
-}
-EXPORT_SYMBOL_GPL(of_nvmem_layout_get_container);
-#endif
-
 const void *nvmem_layout_get_match_data(struct nvmem_device *nvmem,
 					struct nvmem_layout *layout)
 {
@@ -838,7 +760,7 @@ const void *nvmem_layout_get_match_data(struct nvmem_device *nvmem,
 	const struct of_device_id *match;
 
 	layout_np = of_nvmem_layout_get_container(nvmem);
-	match = of_match_node(layout->of_match_table, layout_np);
+	match = of_match_node(layout->dev.driver->of_match_table, layout_np);
 
 	return match ? match->data : NULL;
 }
@@ -950,19 +872,6 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config)
 			goto err_put_device;
 	}
 
-	/*
-	 * If the driver supplied a layout by config->layout, the module
-	 * pointer will be NULL and nvmem_layout_put() will be a noop.
-	 */
-	nvmem->layout = config->layout ?: nvmem_layout_get(nvmem);
-	if (IS_ERR(nvmem->layout)) {
-		rval = PTR_ERR(nvmem->layout);
-		nvmem->layout = NULL;
-
-		if (rval == -EPROBE_DEFER)
-			goto err_teardown_compat;
-	}
-
 	if (config->cells) {
 		rval = nvmem_add_cells(nvmem, config->cells, config->ncells);
 		if (rval)
@@ -983,24 +892,24 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config)
 	if (rval)
 		goto err_remove_cells;
 
-	rval = nvmem_add_cells_from_layout(nvmem);
-	if (rval)
-		goto err_remove_cells;
-
 	dev_dbg(&nvmem->dev, "Registering nvmem device %s\n", config->name);
 
 	rval = device_add(&nvmem->dev);
 	if (rval)
 		goto err_remove_cells;
 
+	rval = nvmem_populate_layout(nvmem);
+	if (rval)
+		goto err_remove_dev;
+
 	blocking_notifier_call_chain(&nvmem_notifier, NVMEM_ADD, nvmem);
 
 	return nvmem;
 
+err_remove_dev:
+	device_del(&nvmem->dev);
 err_remove_cells:
 	nvmem_device_remove_all_cells(nvmem);
-	nvmem_layout_put(nvmem->layout);
-err_teardown_compat:
 	if (config->compat)
 		nvmem_sysfs_remove_compat(nvmem, config);
 err_put_device:
@@ -1022,7 +931,7 @@ static void nvmem_device_release(struct kref *kref)
 		device_remove_bin_file(nvmem->base_dev, &nvmem->eeprom);
 
 	nvmem_device_remove_all_cells(nvmem);
-	nvmem_layout_put(nvmem->layout);
+	nvmem_destroy_layout(nvmem);
 	device_unregister(&nvmem->dev);
 }
 
@@ -1324,6 +1233,12 @@ nvmem_cell_get_from_lookup(struct device *dev, const char *con_id)
 	return cell;
 }
 
+static void nvmem_layout_module_put(struct nvmem_device *nvmem)
+{
+	if (nvmem->layout && nvmem->layout->dev.driver)
+		module_put(nvmem->layout->dev.driver->owner);
+}
+
 #if IS_ENABLED(CONFIG_OF)
 static struct nvmem_cell_entry *
 nvmem_find_cell_entry_by_node(struct nvmem_device *nvmem, struct device_node *np)
@@ -1342,6 +1257,18 @@ nvmem_find_cell_entry_by_node(struct nvmem_device *nvmem, struct device_node *np
 	return cell;
 }
 
+static int nvmem_layout_module_get_optional(struct nvmem_device *nvmem)
+{
+	if (!nvmem->layout)
+		return 0;
+
+	if (!nvmem->layout->dev.driver ||
+	    !try_module_get(nvmem->layout->dev.driver->owner))
+		return -EPROBE_DEFER;
+
+	return 0;
+}
+
 /**
  * of_nvmem_cell_get() - Get a nvmem cell from given device node and cell id
  *
@@ -1404,16 +1331,29 @@ struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, const char *id)
 		return ERR_CAST(nvmem);
 	}
 
+	ret = nvmem_layout_module_get_optional(nvmem);
+	if (ret) {
+		of_node_put(cell_np);
+		__nvmem_device_put(nvmem);
+		return ERR_PTR(ret);
+	}
+
 	cell_entry = nvmem_find_cell_entry_by_node(nvmem, cell_np);
 	of_node_put(cell_np);
 	if (!cell_entry) {
 		__nvmem_device_put(nvmem);
-		return ERR_PTR(-ENOENT);
+		nvmem_layout_module_put(nvmem);
+		if (nvmem->layout)
+			return ERR_PTR(-EPROBE_DEFER);
+		else
+			return ERR_PTR(-ENOENT);
 	}
 
 	cell = nvmem_create_cell(cell_entry, id, cell_index);
-	if (IS_ERR(cell))
+	if (IS_ERR(cell)) {
 		__nvmem_device_put(nvmem);
+		nvmem_layout_module_put(nvmem);
+	}
 
 	return cell;
 }
@@ -1527,6 +1467,7 @@ void nvmem_cell_put(struct nvmem_cell *cell)
 
 	kfree(cell);
 	__nvmem_device_put(nvmem);
+	nvmem_layout_module_put(nvmem);
 }
 EXPORT_SYMBOL_GPL(nvmem_cell_put);
 
@@ -2104,11 +2045,22 @@ EXPORT_SYMBOL_GPL(nvmem_dev_name);
 
 static int __init nvmem_init(void)
 {
-	return bus_register(&nvmem_bus_type);
+	int ret;
+
+	ret = bus_register(&nvmem_bus_type);
+	if (ret)
+		return ret;
+
+	ret = nvmem_layout_bus_register();
+	if (ret)
+		bus_unregister(&nvmem_bus_type);
+
+	return ret;
 }
 
 static void __exit nvmem_exit(void)
 {
+	nvmem_layout_bus_unregister();
 	bus_unregister(&nvmem_bus_type);
 }
 
diff --git a/drivers/nvmem/internals.h b/drivers/nvmem/internals.h
index 893553fbdf51..4946456c76c7 100644
--- a/drivers/nvmem/internals.h
+++ b/drivers/nvmem/internals.h
@@ -34,4 +34,25 @@ struct nvmem_device {
 	void *priv;
 };
 
+#if IS_ENABLED(CONFIG_OF)
+int nvmem_layout_bus_register(void);
+void nvmem_layout_bus_unregister(void);
+int nvmem_populate_layout(struct nvmem_device *nvmem);
+void nvmem_destroy_layout(struct nvmem_device *nvmem);
+#else /* CONFIG_OF */
+static inline int nvmem_layout_bus_register(void)
+{
+	return 0;
+}
+
+static inline void nvmem_layout_bus_unregister(void) {}
+
+static inline int nvmem_populate_layout(struct nvmem_device *nvmem)
+{
+	return 0;
+}
+
+static inline void nvmem_destroy_layout(struct nvmem_device *nvmem) { }
+#endif /* CONFIG_OF */
+
 #endif  /* ifndef _LINUX_NVMEM_INTERNALS_H */
diff --git a/drivers/nvmem/layouts.c b/drivers/nvmem/layouts.c
new file mode 100644
index 000000000000..6a6aa58369ff
--- /dev/null
+++ b/drivers/nvmem/layouts.c
@@ -0,0 +1,201 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * NVMEM layout bus handling
+ *
+ * Copyright (C) 2023 Bootlin
+ * Author: Miquel Raynal <miquel.raynal@bootlin.com
+ */
+
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/nvmem-consumer.h>
+#include <linux/nvmem-provider.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_irq.h>
+
+#include "internals.h"
+
+#define to_nvmem_layout_driver(drv) \
+	(container_of((drv), struct nvmem_layout_driver, driver))
+#define to_nvmem_layout_device(_dev) \
+	container_of((_dev), struct nvmem_layout, dev)
+
+static int nvmem_layout_bus_match(struct device *dev, struct device_driver *drv)
+{
+	return of_driver_match_device(dev, drv);
+}
+
+static int nvmem_layout_bus_probe(struct device *dev)
+{
+	struct nvmem_layout_driver *drv = to_nvmem_layout_driver(dev->driver);
+	struct nvmem_layout *layout = to_nvmem_layout_device(dev);
+
+	if (!drv->probe || !drv->remove)
+		return -EINVAL;
+
+	return drv->probe(layout);
+}
+
+static void nvmem_layout_bus_remove(struct device *dev)
+{
+	struct nvmem_layout_driver *drv = to_nvmem_layout_driver(dev->driver);
+	struct nvmem_layout *layout = to_nvmem_layout_device(dev);
+
+	return drv->remove(layout);
+}
+
+static struct bus_type nvmem_layout_bus_type = {
+	.name		= "nvmem-layout",
+	.match		= nvmem_layout_bus_match,
+	.probe		= nvmem_layout_bus_probe,
+	.remove		= nvmem_layout_bus_remove,
+};
+
+int nvmem_layout_driver_register(struct nvmem_layout_driver *drv)
+{
+	drv->driver.bus = &nvmem_layout_bus_type;
+
+	return driver_register(&drv->driver);
+}
+EXPORT_SYMBOL_GPL(nvmem_layout_driver_register);
+
+void nvmem_layout_driver_unregister(struct nvmem_layout_driver *drv)
+{
+	driver_unregister(&drv->driver);
+}
+EXPORT_SYMBOL_GPL(nvmem_layout_driver_unregister);
+
+static void nvmem_layout_release_device(struct device *dev)
+{
+	struct nvmem_layout *layout = to_nvmem_layout_device(dev);
+
+	of_node_put(layout->dev.of_node);
+	kfree(layout);
+}
+
+static int nvmem_layout_create_device(struct nvmem_device *nvmem,
+				      struct device_node *np)
+{
+	struct nvmem_layout *layout;
+	struct device *dev;
+	int ret;
+
+	layout = kzalloc(sizeof(*layout), GFP_KERNEL);
+	if (!layout)
+		return -ENOMEM;
+
+	/* Create a bidirectional link */
+	layout->nvmem = nvmem;
+	nvmem->layout = layout;
+
+	/* Device model registration */
+	dev = &layout->dev;
+	device_initialize(dev);
+	dev->parent = &nvmem->dev;
+	dev->bus = &nvmem_layout_bus_type;
+	dev->release = nvmem_layout_release_device;
+	dev->coherent_dma_mask = DMA_BIT_MASK(32);
+	dev->dma_mask = &dev->coherent_dma_mask;
+	device_set_node(dev, of_fwnode_handle(of_node_get(np)));
+	of_device_make_bus_id(dev);
+	of_msi_configure(dev, dev->of_node);
+
+	ret = device_add(dev);
+	if (ret) {
+		put_device(dev);
+		return ret;
+	}
+
+	return 0;
+}
+
+static const struct of_device_id of_nvmem_layout_skip_table[] = {
+	{ .compatible = "fixed-layout", },
+	{}
+};
+
+static int nvmem_layout_bus_populate(struct nvmem_device *nvmem,
+				     struct device_node *layout_dn)
+{
+	int ret;
+
+	/* Make sure it has a compatible property */
+	if (!of_get_property(layout_dn, "compatible", NULL)) {
+		pr_debug("%s() - skipping %pOF, no compatible prop\n",
+			 __func__, layout_dn);
+		return 0;
+	}
+
+	/* Fixed layouts are parsed manually somewhere else for now */
+	if (of_match_node(of_nvmem_layout_skip_table, layout_dn)) {
+		pr_debug("%s() - skipping %pOF node\n", __func__, layout_dn);
+		return 0;
+	}
+
+	if (of_node_check_flag(layout_dn, OF_POPULATED_BUS)) {
+		pr_debug("%s() - skipping %pOF, already populated\n",
+			 __func__, layout_dn);
+
+		return 0;
+	}
+
+	/* NVMEM layout buses expect only a single device representing the layout */
+	ret = nvmem_layout_create_device(nvmem, layout_dn);
+	if (ret)
+		return ret;
+
+	of_node_set_flag(layout_dn, OF_POPULATED_BUS);
+
+	return 0;
+}
+
+struct device_node *of_nvmem_layout_get_container(struct nvmem_device *nvmem)
+{
+	return of_get_child_by_name(nvmem->dev.of_node, "nvmem-layout");
+}
+EXPORT_SYMBOL_GPL(of_nvmem_layout_get_container);
+
+/*
+ * Returns the number of devices populated, 0 if the operation was not relevant
+ * for this nvmem device, an error code otherwise.
+ */
+int nvmem_populate_layout(struct nvmem_device *nvmem)
+{
+	struct device_node *layout_dn;
+	int ret;
+
+	layout_dn = of_nvmem_layout_get_container(nvmem);
+	if (!layout_dn)
+		return 0;
+
+	/* Populate the layout device */
+	device_links_supplier_sync_state_pause();
+	ret = nvmem_layout_bus_populate(nvmem, layout_dn);
+	device_links_supplier_sync_state_resume();
+
+	of_node_put(layout_dn);
+	return ret;
+}
+
+void nvmem_destroy_layout(struct nvmem_device *nvmem)
+{
+	struct device *dev;
+
+	if (!nvmem->layout)
+		return;
+
+	dev = &nvmem->layout->dev;
+	of_node_clear_flag(dev->of_node, OF_POPULATED_BUS);
+	device_unregister(dev);
+}
+
+int nvmem_layout_bus_register(void)
+{
+	return bus_register(&nvmem_layout_bus_type);
+}
+
+void nvmem_layout_bus_unregister(void)
+{
+	bus_unregister(&nvmem_layout_bus_type);
+}
diff --git a/drivers/nvmem/layouts/Kconfig b/drivers/nvmem/layouts/Kconfig
index 7ff1ee1c1f05..9c6e672fc350 100644
--- a/drivers/nvmem/layouts/Kconfig
+++ b/drivers/nvmem/layouts/Kconfig
@@ -1,5 +1,11 @@
 # SPDX-License-Identifier: GPL-2.0
 
+config NVMEM_LAYOUTS
+	bool
+	depends on OF
+
+if NVMEM_LAYOUTS
+
 menu "Layout Types"
 
 config NVMEM_LAYOUT_SL28_VPD
@@ -21,3 +27,5 @@ config NVMEM_LAYOUT_ONIE_TLV
 	  If unsure, say N.
 
 endmenu
+
+endif
diff --git a/drivers/nvmem/layouts/onie-tlv.c b/drivers/nvmem/layouts/onie-tlv.c
index defd42d4375c..b24cc5dcc6ee 100644
--- a/drivers/nvmem/layouts/onie-tlv.c
+++ b/drivers/nvmem/layouts/onie-tlv.c
@@ -225,16 +225,32 @@ static int onie_tlv_parse_table(struct device *dev, struct nvmem_device *nvmem)
 	return 0;
 }
 
+static int onie_tlv_probe(struct nvmem_layout *layout)
+{
+	layout->add_cells = onie_tlv_parse_table;
+
+	return nvmem_layout_register(layout);
+}
+
+static void onie_tlv_remove(struct nvmem_layout *layout)
+{
+	nvmem_layout_unregister(layout);
+}
+
 static const struct of_device_id onie_tlv_of_match_table[] = {
 	{ .compatible = "onie,tlv-layout", },
 	{},
 };
 MODULE_DEVICE_TABLE(of, onie_tlv_of_match_table);
 
-static struct nvmem_layout onie_tlv_layout = {
-	.name = "ONIE tlv layout",
-	.of_match_table = onie_tlv_of_match_table,
-	.add_cells = onie_tlv_parse_table,
+static struct nvmem_layout_driver onie_tlv_layout = {
+	.driver = {
+		.owner = THIS_MODULE,
+		.name = "onie-tlv-layout",
+		.of_match_table = onie_tlv_of_match_table,
+	},
+	.probe = onie_tlv_probe,
+	.remove = onie_tlv_remove,
 };
 module_nvmem_layout_driver(onie_tlv_layout);
 
diff --git a/drivers/nvmem/layouts/sl28vpd.c b/drivers/nvmem/layouts/sl28vpd.c
index 26c7cf21b523..b8ffae646cc2 100644
--- a/drivers/nvmem/layouts/sl28vpd.c
+++ b/drivers/nvmem/layouts/sl28vpd.c
@@ -134,16 +134,32 @@ static int sl28vpd_add_cells(struct device *dev, struct nvmem_device *nvmem)
 	return 0;
 }
 
+static int sl28vpd_probe(struct nvmem_layout *layout)
+{
+	layout->add_cells = sl28vpd_add_cells;
+
+	return nvmem_layout_register(layout);
+}
+
+static void sl28vpd_remove(struct nvmem_layout *layout)
+{
+	nvmem_layout_unregister(layout);
+}
+
 static const struct of_device_id sl28vpd_of_match_table[] = {
 	{ .compatible = "kontron,sl28-vpd" },
 	{},
 };
 MODULE_DEVICE_TABLE(of, sl28vpd_of_match_table);
 
-static struct nvmem_layout sl28vpd_layout = {
-	.name = "sl28-vpd",
-	.of_match_table = sl28vpd_of_match_table,
-	.add_cells = sl28vpd_add_cells,
+static struct nvmem_layout_driver sl28vpd_layout = {
+	.driver = {
+		.owner = THIS_MODULE,
+		.name = "kontron-sl28vpd-layout",
+		.of_match_table = sl28vpd_of_match_table,
+	},
+	.probe = sl28vpd_probe,
+	.remove = sl28vpd_remove,
 };
 module_nvmem_layout_driver(sl28vpd_layout);
 
diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h
index 36415a602d9e..6fe65b35ea97 100644
--- a/include/linux/nvmem-provider.h
+++ b/include/linux/nvmem-provider.h
@@ -9,6 +9,7 @@
 #ifndef _LINUX_NVMEM_PROVIDER_H
 #define _LINUX_NVMEM_PROVIDER_H
 
+#include <linux/device.h>
 #include <linux/device/driver.h>
 #include <linux/err.h>
 #include <linux/errno.h>
@@ -158,12 +159,11 @@ struct nvmem_cell_table {
 /**
  * struct nvmem_layout - NVMEM layout definitions
  *
- * @name:		Layout name.
- * @of_match_table:	Open firmware match table.
- * @add_cells:		Called to populate the layout using
- *			nvmem_add_one_cell().
- * @owner:		Pointer to struct module.
- * @node:		List node.
+ * @dev:		Device-model layout device.
+ * @nvmem:		The underlying NVMEM device
+ * @add_cells:		Will be called if a nvmem device is found which
+ *			has this layout. The function will add layout
+ *			specific cells with nvmem_add_one_cell().
  *
  * A nvmem device can hold a well defined structure which can just be
  * evaluated during runtime. For example a TLV list, or a list of "name=val"
@@ -171,13 +171,15 @@ struct nvmem_cell_table {
  * cells.
  */
 struct nvmem_layout {
-	const char *name;
-	const struct of_device_id *of_match_table;
+	struct device dev;
+	struct nvmem_device *nvmem;
 	int (*add_cells)(struct device *dev, struct nvmem_device *nvmem);
+};
 
-	/* private */
-	struct module *owner;
-	struct list_head node;
+struct nvmem_layout_driver {
+	struct device_driver driver;
+	int (*probe)(struct nvmem_layout *layout);
+	void (*remove)(struct nvmem_layout *layout);
 };
 
 #if IS_ENABLED(CONFIG_NVMEM)
@@ -194,11 +196,15 @@ void nvmem_del_cell_table(struct nvmem_cell_table *table);
 int nvmem_add_one_cell(struct nvmem_device *nvmem,
 		       const struct nvmem_cell_info *info);
 
-int __nvmem_layout_register(struct nvmem_layout *layout, struct module *owner);
-#define nvmem_layout_register(layout) \
-	__nvmem_layout_register(layout, THIS_MODULE)
+int nvmem_layout_register(struct nvmem_layout *layout);
 void nvmem_layout_unregister(struct nvmem_layout *layout);
 
+int nvmem_layout_driver_register(struct nvmem_layout_driver *drv);
+void nvmem_layout_driver_unregister(struct nvmem_layout_driver *drv);
+#define module_nvmem_layout_driver(__nvmem_layout_driver)		\
+	module_driver(__nvmem_layout_driver, nvmem_layout_driver_register, \
+		      nvmem_layout_driver_unregister)
+
 const void *nvmem_layout_get_match_data(struct nvmem_device *nvmem,
 					struct nvmem_layout *layout);
 
@@ -262,8 +268,4 @@ static inline struct device_node *of_nvmem_layout_get_container(struct nvmem_dev
 
 #endif /* CONFIG_NVMEM && CONFIG_OF */
 
-#define module_nvmem_layout_driver(__layout_driver)		\
-	module_driver(__layout_driver, nvmem_layout_register,	\
-		      nvmem_layout_unregister)
-
 #endif  /* ifndef _LINUX_NVMEM_PROVIDER_H */
-- 
cgit v1.2.3


From 61fbf20312bdd1394a9cac67ed8f706e205511af Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Thu, 14 Dec 2023 12:04:15 +0300
Subject: usb: gadget: f_fs: fix fortify warning

When compiling with gcc version 14.0.0 20231206 (experimental)
and CONFIG_FORTIFY_SOURCE=y, I've noticed the following warning:

...
In function 'fortify_memcpy_chk',
    inlined from '__ffs_func_bind_do_os_desc' at drivers/usb/gadget/function/f_fs.c:2934:3:
./include/linux/fortify-string.h:588:25: warning: call to '__read_overflow2_field'
declared with attribute warning: detected read beyond size of field (2nd parameter);
maybe use struct_group()? [-Wattribute-warning]
  588 |                         __read_overflow2_field(q_size_field, size);
      |                         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

This call to 'memcpy()' is interpreted as an attempt to copy both
'CompatibleID' and 'SubCompatibleID' of 'struct usb_ext_compat_desc'
from an address of the first one, which causes an overread warning.
Since we actually want to copy both of them at once, use the
convenient 'struct_group()' and 'sizeof_field()' here.

Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Link: https://lore.kernel.org/r/20231214090428.27292-1-dmantipov@yandex.ru
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_fs.c  | 5 ++---
 include/uapi/linux/usb/functionfs.h | 6 ++++--
 2 files changed, 6 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index efe3e3b85769..dafedc33928d 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -2931,9 +2931,8 @@ static int __ffs_func_bind_do_os_desc(enum ffs_os_desc_type type,
 
 		t = &func->function.os_desc_table[desc->bFirstInterfaceNumber];
 		t->if_id = func->interfaces_nums[desc->bFirstInterfaceNumber];
-		memcpy(t->os_desc->ext_compat_id, &desc->CompatibleID,
-		       ARRAY_SIZE(desc->CompatibleID) +
-		       ARRAY_SIZE(desc->SubCompatibleID));
+		memcpy(t->os_desc->ext_compat_id, &desc->IDs,
+		       sizeof_field(struct usb_ext_compat_desc, IDs));
 		length = sizeof(*desc);
 	}
 		break;
diff --git a/include/uapi/linux/usb/functionfs.h b/include/uapi/linux/usb/functionfs.h
index d77ee6b65328..078098e73fd3 100644
--- a/include/uapi/linux/usb/functionfs.h
+++ b/include/uapi/linux/usb/functionfs.h
@@ -73,8 +73,10 @@ struct usb_os_desc_header {
 struct usb_ext_compat_desc {
 	__u8	bFirstInterfaceNumber;
 	__u8	Reserved1;
-	__u8	CompatibleID[8];
-	__u8	SubCompatibleID[8];
+	__struct_group(/* no tag */, IDs, /* no attrs */,
+		__u8	CompatibleID[8];
+		__u8	SubCompatibleID[8];
+	);
 	__u8	Reserved2[6];
 };
 
-- 
cgit v1.2.3


From 57cd29a82574b0e9d99ed5789801c96f765e8fcb Mon Sep 17 00:00:00 2001
From: Rander Wang <rander.wang@intel.com>
Date: Fri, 15 Dec 2023 16:31:00 +0800
Subject: ASoC: SOF: IPC4: synchronize fw_config_params with fw definitions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Update fw_config_params in driver.

Signed-off-by: Rander Wang <rander.wang@intel.com>
Reviewed-by: Péter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://msgid.link/r/20231215083102.3064200-2-yung-chuan.liao@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/sof/ipc4/header.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'include')

diff --git a/include/sound/sof/ipc4/header.h b/include/sound/sof/ipc4/header.h
index 2c81d6dde577..1eb538e18236 100644
--- a/include/sound/sof/ipc4/header.h
+++ b/include/sound/sof/ipc4/header.h
@@ -423,6 +423,12 @@ enum sof_ipc4_fw_config_params {
 	SOF_IPC4_FW_CFG_RESERVED,
 	SOF_IPC4_FW_CFG_POWER_GATING_POLICY,
 	SOF_IPC4_FW_CFG_ASSERT_MODE,
+	SOF_IPC4_FW_RESERVED1,
+	SOF_IPC4_FW_RESERVED2,
+	SOF_IPC4_FW_RESERVED3,
+	SOF_IPC4_FW_RESERVED4,
+	SOF_IPC4_FW_RESERVED5,
+	SOF_IPC4_FW_CONTEXT_SAVE
 };
 
 struct sof_ipc4_fw_version {
-- 
cgit v1.2.3


From 1f78c56007ba61b7b8c3f7dbb6787b6af116d3f0 Mon Sep 17 00:00:00 2001
From: Théo Lebrun <theo.lebrun@bootlin.com>
Date: Thu, 7 Dec 2023 18:56:06 +0100
Subject: tty: serial: amba: Use linux/{bits,bitfield}.h macros
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The driver uses bit shifts and hexadecimal expressions to declare
constants. Replace that with the BIT(), GENMASK() & FIELD_PREP_CONST()
macros to clarify intent.

include/linux/amba/serial.h gets included from arch/arm/include/debug/pl01x.S.
Avoid includes and macro tricks for the four defines that are involved:
UART01x_DR, UART01x_FR, UART01x_FR_TXFF and UART01x_FR_BUSY.

Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Théo Lebrun <theo.lebrun@bootlin.com>
Link: https://lore.kernel.org/r/20231207-mbly-uart-v6-1-e384afa5e78c@bootlin.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/amba/serial.h | 251 +++++++++++++++++++++++---------------------
 1 file changed, 130 insertions(+), 121 deletions(-)

(limited to 'include')

diff --git a/include/linux/amba/serial.h b/include/linux/amba/serial.h
index 27003ec52114..9120de05ead0 100644
--- a/include/linux/amba/serial.h
+++ b/include/linux/amba/serial.h
@@ -10,6 +10,11 @@
 #ifndef ASM_ARM_HARDWARE_SERIAL_AMBA_H
 #define ASM_ARM_HARDWARE_SERIAL_AMBA_H
 
+#ifndef __ASSEMBLY__
+#include <linux/bitfield.h>
+#include <linux/bits.h>
+#endif
+
 #include <linux/types.h>
 
 /* -------------------------------------------------------------------------------
@@ -70,138 +75,142 @@
 #define ZX_UART011_ICR		0x4c
 #define ZX_UART011_DMACR	0x50
 
-#define UART011_DR_OE		(1 << 11)
-#define UART011_DR_BE		(1 << 10)
-#define UART011_DR_PE		(1 << 9)
-#define UART011_DR_FE		(1 << 8)
-
-#define UART01x_RSR_OE		0x08
-#define UART01x_RSR_BE		0x04
-#define UART01x_RSR_PE		0x02
-#define UART01x_RSR_FE		0x01
-
-#define UART011_FR_RI		0x100
-#define UART011_FR_TXFE		0x080
-#define UART011_FR_RXFF		0x040
-#define UART01x_FR_TXFF		0x020
-#define UART01x_FR_RXFE		0x010
-#define UART01x_FR_BUSY		0x008
-#define UART01x_FR_DCD		0x004
-#define UART01x_FR_DSR		0x002
-#define UART01x_FR_CTS		0x001
+#define UART011_DR_OE		BIT(11)
+#define UART011_DR_BE		BIT(10)
+#define UART011_DR_PE		BIT(9)
+#define UART011_DR_FE		BIT(8)
+
+#define UART01x_RSR_OE		BIT(3)
+#define UART01x_RSR_BE		BIT(2)
+#define UART01x_RSR_PE		BIT(1)
+#define UART01x_RSR_FE		BIT(0)
+
+#define UART011_FR_RI		BIT(8)
+#define UART011_FR_TXFE		BIT(7)
+#define UART011_FR_RXFF		BIT(6)
+#define UART01x_FR_TXFF		(1 << 5)	/* used in ASM */
+#define UART01x_FR_RXFE		BIT(4)
+#define UART01x_FR_BUSY		(1 << 3)	/* used in ASM */
+#define UART01x_FR_DCD		BIT(2)
+#define UART01x_FR_DSR		BIT(1)
+#define UART01x_FR_CTS		BIT(0)
 #define UART01x_FR_TMSK		(UART01x_FR_TXFF + UART01x_FR_BUSY)
 
 /*
  * Some bits of Flag Register on ZTE device have different position from
  * standard ones.
  */
-#define ZX_UART01x_FR_BUSY	0x100
-#define ZX_UART01x_FR_DSR	0x008
-#define ZX_UART01x_FR_CTS	0x002
-#define ZX_UART011_FR_RI	0x001
-
-#define UART011_CR_CTSEN	0x8000	/* CTS hardware flow control */
-#define UART011_CR_RTSEN	0x4000	/* RTS hardware flow control */
-#define UART011_CR_OUT2		0x2000	/* OUT2 */
-#define UART011_CR_OUT1		0x1000	/* OUT1 */
-#define UART011_CR_RTS		0x0800	/* RTS */
-#define UART011_CR_DTR		0x0400	/* DTR */
-#define UART011_CR_RXE		0x0200	/* receive enable */
-#define UART011_CR_TXE		0x0100	/* transmit enable */
-#define UART011_CR_LBE		0x0080	/* loopback enable */
-#define UART010_CR_RTIE		0x0040
-#define UART010_CR_TIE		0x0020
-#define UART010_CR_RIE		0x0010
-#define UART010_CR_MSIE		0x0008
-#define ST_UART011_CR_OVSFACT	0x0008	/* Oversampling factor */
-#define UART01x_CR_IIRLP	0x0004	/* SIR low power mode */
-#define UART01x_CR_SIREN	0x0002	/* SIR enable */
-#define UART01x_CR_UARTEN	0x0001	/* UART enable */
-
-#define UART011_LCRH_SPS	0x80
+#define ZX_UART01x_FR_BUSY	BIT(8)
+#define ZX_UART01x_FR_DSR	BIT(3)
+#define ZX_UART01x_FR_CTS	BIT(1)
+#define ZX_UART011_FR_RI	BIT(0)
+
+#define UART011_CR_CTSEN	BIT(15)	/* CTS hardware flow control */
+#define UART011_CR_RTSEN	BIT(14)	/* RTS hardware flow control */
+#define UART011_CR_OUT2		BIT(13)	/* OUT2 */
+#define UART011_CR_OUT1		BIT(12)	/* OUT1 */
+#define UART011_CR_RTS		BIT(11)	/* RTS */
+#define UART011_CR_DTR		BIT(10)	/* DTR */
+#define UART011_CR_RXE		BIT(9)	/* receive enable */
+#define UART011_CR_TXE		BIT(8)	/* transmit enable */
+#define UART011_CR_LBE		BIT(7)	/* loopback enable */
+#define UART010_CR_RTIE		BIT(6)
+#define UART010_CR_TIE		BIT(5)
+#define UART010_CR_RIE		BIT(4)
+#define UART010_CR_MSIE		BIT(3)
+#define ST_UART011_CR_OVSFACT	BIT(3)	/* Oversampling factor */
+#define UART01x_CR_IIRLP	BIT(2)	/* SIR low power mode */
+#define UART01x_CR_SIREN	BIT(1)	/* SIR enable */
+#define UART01x_CR_UARTEN	BIT(0)	/* UART enable */
+
+#define UART011_LCRH_SPS	BIT(7)
 #define UART01x_LCRH_WLEN_8	0x60
 #define UART01x_LCRH_WLEN_7	0x40
 #define UART01x_LCRH_WLEN_6	0x20
 #define UART01x_LCRH_WLEN_5	0x00
-#define UART01x_LCRH_FEN	0x10
-#define UART01x_LCRH_STP2	0x08
-#define UART01x_LCRH_EPS	0x04
-#define UART01x_LCRH_PEN	0x02
-#define UART01x_LCRH_BRK	0x01
-
-#define ST_UART011_DMAWM_RX_1	(0 << 3)
-#define ST_UART011_DMAWM_RX_2	(1 << 3)
-#define ST_UART011_DMAWM_RX_4	(2 << 3)
-#define ST_UART011_DMAWM_RX_8	(3 << 3)
-#define ST_UART011_DMAWM_RX_16	(4 << 3)
-#define ST_UART011_DMAWM_RX_32	(5 << 3)
-#define ST_UART011_DMAWM_RX_48	(6 << 3)
-#define ST_UART011_DMAWM_TX_1	0
-#define ST_UART011_DMAWM_TX_2	1
-#define ST_UART011_DMAWM_TX_4	2
-#define ST_UART011_DMAWM_TX_8	3
-#define ST_UART011_DMAWM_TX_16	4
-#define ST_UART011_DMAWM_TX_32	5
-#define ST_UART011_DMAWM_TX_48	6
-
-#define UART010_IIR_RTIS	0x08
-#define UART010_IIR_TIS		0x04
-#define UART010_IIR_RIS		0x02
-#define UART010_IIR_MIS		0x01
-
-#define UART011_IFLS_RX1_8	(0 << 3)
-#define UART011_IFLS_RX2_8	(1 << 3)
-#define UART011_IFLS_RX4_8	(2 << 3)
-#define UART011_IFLS_RX6_8	(3 << 3)
-#define UART011_IFLS_RX7_8	(4 << 3)
-#define UART011_IFLS_TX1_8	(0 << 0)
-#define UART011_IFLS_TX2_8	(1 << 0)
-#define UART011_IFLS_TX4_8	(2 << 0)
-#define UART011_IFLS_TX6_8	(3 << 0)
-#define UART011_IFLS_TX7_8	(4 << 0)
+#define UART01x_LCRH_FEN	BIT(4)
+#define UART01x_LCRH_STP2	BIT(3)
+#define UART01x_LCRH_EPS	BIT(2)
+#define UART01x_LCRH_PEN	BIT(1)
+#define UART01x_LCRH_BRK	BIT(0)
+
+#define ST_UART011_DMAWM_RX	GENMASK(5, 3)
+#define ST_UART011_DMAWM_RX_1	FIELD_PREP_CONST(ST_UART011_DMAWM_RX, 0)
+#define ST_UART011_DMAWM_RX_2	FIELD_PREP_CONST(ST_UART011_DMAWM_RX, 1)
+#define ST_UART011_DMAWM_RX_4	FIELD_PREP_CONST(ST_UART011_DMAWM_RX, 2)
+#define ST_UART011_DMAWM_RX_8	FIELD_PREP_CONST(ST_UART011_DMAWM_RX, 3)
+#define ST_UART011_DMAWM_RX_16	FIELD_PREP_CONST(ST_UART011_DMAWM_RX, 4)
+#define ST_UART011_DMAWM_RX_32	FIELD_PREP_CONST(ST_UART011_DMAWM_RX, 5)
+#define ST_UART011_DMAWM_RX_48	FIELD_PREP_CONST(ST_UART011_DMAWM_RX, 6)
+#define ST_UART011_DMAWM_TX	GENMASK(2, 0)
+#define ST_UART011_DMAWM_TX_1	FIELD_PREP_CONST(ST_UART011_DMAWM_TX, 0)
+#define ST_UART011_DMAWM_TX_2	FIELD_PREP_CONST(ST_UART011_DMAWM_TX, 1)
+#define ST_UART011_DMAWM_TX_4	FIELD_PREP_CONST(ST_UART011_DMAWM_TX, 2)
+#define ST_UART011_DMAWM_TX_8	FIELD_PREP_CONST(ST_UART011_DMAWM_TX, 3)
+#define ST_UART011_DMAWM_TX_16	FIELD_PREP_CONST(ST_UART011_DMAWM_TX, 4)
+#define ST_UART011_DMAWM_TX_32	FIELD_PREP_CONST(ST_UART011_DMAWM_TX, 5)
+#define ST_UART011_DMAWM_TX_48	FIELD_PREP_CONST(ST_UART011_DMAWM_TX, 6)
+
+#define UART010_IIR_RTIS	BIT(3)
+#define UART010_IIR_TIS		BIT(2)
+#define UART010_IIR_RIS		BIT(1)
+#define UART010_IIR_MIS		BIT(0)
+
+#define UART011_IFLS_RXIFLSEL	GENMASK(5, 3)
+#define UART011_IFLS_RX1_8	FIELD_PREP_CONST(UART011_IFLS_RXIFLSEL, 0)
+#define UART011_IFLS_RX2_8	FIELD_PREP_CONST(UART011_IFLS_RXIFLSEL, 1)
+#define UART011_IFLS_RX4_8	FIELD_PREP_CONST(UART011_IFLS_RXIFLSEL, 2)
+#define UART011_IFLS_RX6_8	FIELD_PREP_CONST(UART011_IFLS_RXIFLSEL, 3)
+#define UART011_IFLS_RX7_8	FIELD_PREP_CONST(UART011_IFLS_RXIFLSEL, 4)
+#define UART011_IFLS_TXIFLSEL	GENMASK(2, 0)
+#define UART011_IFLS_TX1_8	FIELD_PREP_CONST(UART011_IFLS_TXIFLSEL, 0)
+#define UART011_IFLS_TX2_8	FIELD_PREP_CONST(UART011_IFLS_TXIFLSEL, 1)
+#define UART011_IFLS_TX4_8	FIELD_PREP_CONST(UART011_IFLS_TXIFLSEL, 2)
+#define UART011_IFLS_TX6_8	FIELD_PREP_CONST(UART011_IFLS_TXIFLSEL, 3)
+#define UART011_IFLS_TX7_8	FIELD_PREP_CONST(UART011_IFLS_TXIFLSEL, 4)
 /* special values for ST vendor with deeper fifo */
-#define UART011_IFLS_RX_HALF	(5 << 3)
-#define UART011_IFLS_TX_HALF	(5 << 0)
-
-#define UART011_OEIM		(1 << 10)	/* overrun error interrupt mask */
-#define UART011_BEIM		(1 << 9)	/* break error interrupt mask */
-#define UART011_PEIM		(1 << 8)	/* parity error interrupt mask */
-#define UART011_FEIM		(1 << 7)	/* framing error interrupt mask */
-#define UART011_RTIM		(1 << 6)	/* receive timeout interrupt mask */
-#define UART011_TXIM		(1 << 5)	/* transmit interrupt mask */
-#define UART011_RXIM		(1 << 4)	/* receive interrupt mask */
-#define UART011_DSRMIM		(1 << 3)	/* DSR interrupt mask */
-#define UART011_DCDMIM		(1 << 2)	/* DCD interrupt mask */
-#define UART011_CTSMIM		(1 << 1)	/* CTS interrupt mask */
-#define UART011_RIMIM		(1 << 0)	/* RI interrupt mask */
-
-#define UART011_OEIS		(1 << 10)	/* overrun error interrupt status */
-#define UART011_BEIS		(1 << 9)	/* break error interrupt status */
-#define UART011_PEIS		(1 << 8)	/* parity error interrupt status */
-#define UART011_FEIS		(1 << 7)	/* framing error interrupt status */
-#define UART011_RTIS		(1 << 6)	/* receive timeout interrupt status */
-#define UART011_TXIS		(1 << 5)	/* transmit interrupt status */
-#define UART011_RXIS		(1 << 4)	/* receive interrupt status */
-#define UART011_DSRMIS		(1 << 3)	/* DSR interrupt status */
-#define UART011_DCDMIS		(1 << 2)	/* DCD interrupt status */
-#define UART011_CTSMIS		(1 << 1)	/* CTS interrupt status */
-#define UART011_RIMIS		(1 << 0)	/* RI interrupt status */
-
-#define UART011_OEIC		(1 << 10)	/* overrun error interrupt clear */
-#define UART011_BEIC		(1 << 9)	/* break error interrupt clear */
-#define UART011_PEIC		(1 << 8)	/* parity error interrupt clear */
-#define UART011_FEIC		(1 << 7)	/* framing error interrupt clear */
-#define UART011_RTIC		(1 << 6)	/* receive timeout interrupt clear */
-#define UART011_TXIC		(1 << 5)	/* transmit interrupt clear */
-#define UART011_RXIC		(1 << 4)	/* receive interrupt clear */
-#define UART011_DSRMIC		(1 << 3)	/* DSR interrupt clear */
-#define UART011_DCDMIC		(1 << 2)	/* DCD interrupt clear */
-#define UART011_CTSMIC		(1 << 1)	/* CTS interrupt clear */
-#define UART011_RIMIC		(1 << 0)	/* RI interrupt clear */
-
-#define UART011_DMAONERR	(1 << 2)	/* disable dma on error */
-#define UART011_TXDMAE		(1 << 1)	/* enable transmit dma */
-#define UART011_RXDMAE		(1 << 0)	/* enable receive dma */
+#define UART011_IFLS_RX_HALF	FIELD_PREP_CONST(UART011_IFLS_RXIFLSEL, 5)
+#define UART011_IFLS_TX_HALF	FIELD_PREP_CONST(UART011_IFLS_TXIFLSEL, 5)
+
+#define UART011_OEIM		BIT(10)	/* overrun error interrupt mask */
+#define UART011_BEIM		BIT(9)	/* break error interrupt mask */
+#define UART011_PEIM		BIT(8)	/* parity error interrupt mask */
+#define UART011_FEIM		BIT(7)	/* framing error interrupt mask */
+#define UART011_RTIM		BIT(6)	/* receive timeout interrupt mask */
+#define UART011_TXIM		BIT(5)	/* transmit interrupt mask */
+#define UART011_RXIM		BIT(4)	/* receive interrupt mask */
+#define UART011_DSRMIM		BIT(3)	/* DSR interrupt mask */
+#define UART011_DCDMIM		BIT(2)	/* DCD interrupt mask */
+#define UART011_CTSMIM		BIT(1)	/* CTS interrupt mask */
+#define UART011_RIMIM		BIT(0)	/* RI interrupt mask */
+
+#define UART011_OEIS		BIT(10)	/* overrun error interrupt status */
+#define UART011_BEIS		BIT(9)	/* break error interrupt status */
+#define UART011_PEIS		BIT(8)	/* parity error interrupt status */
+#define UART011_FEIS		BIT(7)	/* framing error interrupt status */
+#define UART011_RTIS		BIT(6)	/* receive timeout interrupt status */
+#define UART011_TXIS		BIT(5)	/* transmit interrupt status */
+#define UART011_RXIS		BIT(4)	/* receive interrupt status */
+#define UART011_DSRMIS		BIT(3)	/* DSR interrupt status */
+#define UART011_DCDMIS		BIT(2)	/* DCD interrupt status */
+#define UART011_CTSMIS		BIT(1)	/* CTS interrupt status */
+#define UART011_RIMIS		BIT(0)	/* RI interrupt status */
+
+#define UART011_OEIC		BIT(10)	/* overrun error interrupt clear */
+#define UART011_BEIC		BIT(9)	/* break error interrupt clear */
+#define UART011_PEIC		BIT(8)	/* parity error interrupt clear */
+#define UART011_FEIC		BIT(7)	/* framing error interrupt clear */
+#define UART011_RTIC		BIT(6)	/* receive timeout interrupt clear */
+#define UART011_TXIC		BIT(5)	/* transmit interrupt clear */
+#define UART011_RXIC		BIT(4)	/* receive interrupt clear */
+#define UART011_DSRMIC		BIT(3)	/* DSR interrupt clear */
+#define UART011_DCDMIC		BIT(2)	/* DCD interrupt clear */
+#define UART011_CTSMIC		BIT(1)	/* CTS interrupt clear */
+#define UART011_RIMIC		BIT(0)	/* RI interrupt clear */
+
+#define UART011_DMAONERR	BIT(2)	/* disable dma on error */
+#define UART011_TXDMAE		BIT(1)	/* enable transmit dma */
+#define UART011_RXDMAE		BIT(0)	/* enable receive dma */
 
 #define UART01x_RSR_ANY		(UART01x_RSR_OE | UART01x_RSR_BE | UART01x_RSR_PE | UART01x_RSR_FE)
 #define UART01x_FR_MODEM_ANY	(UART01x_FR_DCD | UART01x_FR_DSR | UART01x_FR_CTS)
-- 
cgit v1.2.3


From 0c734c5ea76e333fbb8dd83b5bab46291b38096b Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 14 Dec 2023 11:08:15 -0700
Subject: block: improve struct request_queue layout

It's clearly been a while since someone looked at this, so I gave it a
quick shot. There are few issues in here:

- Random bundling of members that are mostly read-only and often written
- Random holes that need not be there

This moves the most frequently used bits into cacheline 1 and 2, with
the 2nd one being more write intensive than the first one, which is
basically read-only.

Outside of making this work a bit more efficiently, it also reduces the
size of struct request_queue for my test setup from 864 bytes (spanning
14 cachelines!) to 832 bytes and 13 cachelines.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/d2b7b61c-4868-45c0-9060-4f9c73de9d7e@kernel.dk
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blkdev.h | 89 ++++++++++++++++++++++++++------------------------
 1 file changed, 46 insertions(+), 43 deletions(-)

(limited to 'include')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 17c0a7d0d319..185ed3770e3a 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -367,59 +367,51 @@ struct blk_independent_access_ranges {
 };
 
 struct request_queue {
-	struct request		*last_merge;
-	struct elevator_queue	*elevator;
-
-	struct percpu_ref	q_usage_counter;
+	/*
+	 * The queue owner gets to use this for whatever they like.
+	 * ll_rw_blk doesn't touch it.
+	 */
+	void			*queuedata;
 
-	struct blk_queue_stats	*stats;
-	struct rq_qos		*rq_qos;
-	struct mutex		rq_qos_mutex;
+	struct elevator_queue	*elevator;
 
 	const struct blk_mq_ops	*mq_ops;
 
 	/* sw queues */
 	struct blk_mq_ctx __percpu	*queue_ctx;
 
+	/*
+	 * various queue flags, see QUEUE_* below
+	 */
+	unsigned long		queue_flags;
+
+	unsigned int		rq_timeout;
+
 	unsigned int		queue_depth;
 
+	refcount_t		refs;
+
 	/* hw dispatch queues */
-	struct xarray		hctx_table;
 	unsigned int		nr_hw_queues;
+	struct xarray		hctx_table;
 
-	/*
-	 * The queue owner gets to use this for whatever they like.
-	 * ll_rw_blk doesn't touch it.
-	 */
-	void			*queuedata;
-
-	/*
-	 * various queue flags, see QUEUE_* below
-	 */
-	unsigned long		queue_flags;
-	/*
-	 * Number of contexts that have called blk_set_pm_only(). If this
-	 * counter is above zero then only RQF_PM requests are processed.
-	 */
-	atomic_t		pm_only;
+	struct percpu_ref	q_usage_counter;
 
-	/*
-	 * ida allocated id for this queue.  Used to index queues from
-	 * ioctx.
-	 */
-	int			id;
+	struct request		*last_merge;
 
 	spinlock_t		queue_lock;
 
-	struct gendisk		*disk;
+	int			quiesce_depth;
 
-	refcount_t		refs;
+	struct gendisk		*disk;
 
 	/*
 	 * mq queue kobject
 	 */
 	struct kobject *mq_kobj;
 
+	struct queue_limits	limits;
+
 #ifdef  CONFIG_BLK_DEV_INTEGRITY
 	struct blk_integrity integrity;
 #endif	/* CONFIG_BLK_DEV_INTEGRITY */
@@ -430,24 +422,40 @@ struct request_queue {
 #endif
 
 	/*
-	 * queue settings
+	 * Number of contexts that have called blk_set_pm_only(). If this
+	 * counter is above zero then only RQF_PM requests are processed.
 	 */
-	unsigned long		nr_requests;	/* Max # of requests */
+	atomic_t		pm_only;
+
+	struct blk_queue_stats	*stats;
+	struct rq_qos		*rq_qos;
+	struct mutex		rq_qos_mutex;
+
+	/*
+	 * ida allocated id for this queue.  Used to index queues from
+	 * ioctx.
+	 */
+	int			id;
 
 	unsigned int		dma_pad_mask;
 
+	/*
+	 * queue settings
+	 */
+	unsigned long		nr_requests;	/* Max # of requests */
+
 #ifdef CONFIG_BLK_INLINE_ENCRYPTION
 	struct blk_crypto_profile *crypto_profile;
 	struct kobject *crypto_kobject;
 #endif
 
-	unsigned int		rq_timeout;
-
 	struct timer_list	timeout;
 	struct work_struct	timeout_work;
 
 	atomic_t		nr_active_requests_shared_tags;
 
+	unsigned int		required_elevator_features;
+
 	struct blk_mq_tags	*sched_shared_tags;
 
 	struct list_head	icq_list;
@@ -458,11 +466,12 @@ struct request_queue {
 	struct mutex		blkcg_mutex;
 #endif
 
-	struct queue_limits	limits;
+	int			node;
 
-	unsigned int		required_elevator_features;
+	spinlock_t		requeue_lock;
+	struct list_head	requeue_list;
+	struct delayed_work	requeue_work;
 
-	int			node;
 #ifdef CONFIG_BLK_DEV_IO_TRACE
 	struct blk_trace __rcu	*blk_trace;
 #endif
@@ -472,10 +481,6 @@ struct request_queue {
 	struct blk_flush_queue	*fq;
 	struct list_head	flush_list;
 
-	struct list_head	requeue_list;
-	spinlock_t		requeue_lock;
-	struct delayed_work	requeue_work;
-
 	struct mutex		sysfs_lock;
 	struct mutex		sysfs_dir_lock;
 
@@ -500,8 +505,6 @@ struct request_queue {
 	 */
 	struct mutex		mq_freeze_lock;
 
-	int			quiesce_depth;
-
 	struct blk_mq_tag_set	*tag_set;
 	struct list_head	tag_set_list;
 
-- 
cgit v1.2.3


From 826a5d8c9df9605fb4fdefa45432f95580241a1f Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 25 Oct 2023 21:42:57 +0300
Subject: device property: Implement device_is_big_endian()

Some users want to use the struct device pointer to see if the
device is big endian in terms of Open Firmware specifications,
i.e. if it has a "big-endian" property, or if the kernel was
compiled for BE *and* the device has a "native-endian" property.

Provide inline helper for the users.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20231025184259.250588-2-andriy.shevchenko@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/property.h | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

(limited to 'include')

diff --git a/include/linux/property.h b/include/linux/property.h
index 9f2585d705a8..55c2692ffa8c 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -80,12 +80,38 @@ int fwnode_property_match_string(const struct fwnode_handle *fwnode,
 
 bool fwnode_device_is_available(const struct fwnode_handle *fwnode);
 
+static inline bool fwnode_device_is_big_endian(const struct fwnode_handle *fwnode)
+{
+	if (fwnode_property_present(fwnode, "big-endian"))
+		return true;
+	if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN) &&
+	    fwnode_property_present(fwnode, "native-endian"))
+		return true;
+	return false;
+}
+
 static inline
 bool fwnode_device_is_compatible(const struct fwnode_handle *fwnode, const char *compat)
 {
 	return fwnode_property_match_string(fwnode, "compatible", compat) >= 0;
 }
 
+/**
+ * device_is_big_endian - check if a device has BE registers
+ * @dev: Pointer to the struct device
+ *
+ * Returns: true if the device has a "big-endian" property, or if the kernel
+ * was compiled for BE *and* the device has a "native-endian" property.
+ * Returns false otherwise.
+ *
+ * Callers would nominally use ioread32be/iowrite32be if
+ * device_is_big_endian() == true, or readl/writel otherwise.
+ */
+static inline bool device_is_big_endian(const struct device *dev)
+{
+	return fwnode_device_is_big_endian(dev_fwnode(dev));
+}
+
 /**
  * device_is_compatible - match 'compatible' property of the device with a given string
  * @dev: Pointer to the struct device
-- 
cgit v1.2.3


From a7565fc8399725d00cc006c35d0621a5cb5f9554 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 13 Dec 2023 14:40:14 -0800
Subject: mei: fix spellos in mei.h

For include/uapi/linux/mei.h, correct spellos reported by codespell.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Tomas Winkler <tomas.winkler@intel.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/20231213224014.23187-1-rdunlap@infradead.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/uapi/linux/mei.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/mei.h b/include/uapi/linux/mei.h
index 171c5cce3641..68a0272e99b7 100644
--- a/include/uapi/linux/mei.h
+++ b/include/uapi/linux/mei.h
@@ -100,14 +100,14 @@ struct mei_connect_client_data_vtag {
  * a FW client on a tagged channel. From this point on, every read
  * and write will communicate with the associated FW client
  * on the tagged channel.
- * Upone close() the communication is terminated.
+ * Upon close() the communication is terminated.
  *
  * The IOCTL argument is a struct with a union that contains
  * the input parameter and the output parameter for this IOCTL.
  *
  * The input parameter is UUID of the FW Client, a vtag [0,255].
  * The output parameter is the properties of the FW client
- * (FW protocool version and max message size).
+ * (FW protocol version and max message size).
  *
  * Clients that do not support tagged connection
  * will respond with -EOPNOTSUPP.
-- 
cgit v1.2.3


From 3634783be125381c6d390938d08cbcc47fed3b73 Mon Sep 17 00:00:00 2001
From: Alice Ryhl <aliceryhl@google.com>
Date: Fri, 8 Dec 2023 15:28:01 +0000
Subject: binder: use enum for binder ioctls

All of the other constants in this file are defined using enums, so make
the constants more consistent by defining the ioctls in an enum as well.

This is necessary for Rust Binder since the _IO macros are too
complicated for bindgen to see that they expand to integer constants.
Replacing the #defines with an enum forces bindgen to evaluate them
properly, which allows us to access them from Rust.

I originally intended to include this change in the first patch of the
Rust Binder patchset [1], but at plumbers Carlos Llamas told me that
this change has been discussed previously [2] and suggested that I send
it upstream separately.

Link: https://lore.kernel.org/rust-for-linux/20231101-rust-binder-v1-1-08ba9197f637@google.com/ [1]
Link: https://lore.kernel.org/all/YoIK2l6xbQMPGZHy@kroah.com/ [2]
Signed-off-by: Alice Ryhl <aliceryhl@google.com>
Acked-by: Carlos Llamas <cmllamas@google.com>
Link: https://lore.kernel.org/r/20231208152801.3425772-1-aliceryhl@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/uapi/linux/android/binder.h | 30 ++++++++++++++++--------------
 1 file changed, 16 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/android/binder.h b/include/uapi/linux/android/binder.h
index 5f636b5afcd7..d44a8118b2ed 100644
--- a/include/uapi/linux/android/binder.h
+++ b/include/uapi/linux/android/binder.h
@@ -251,20 +251,22 @@ struct binder_extended_error {
 	__s32	param;
 };
 
-#define BINDER_WRITE_READ		_IOWR('b', 1, struct binder_write_read)
-#define BINDER_SET_IDLE_TIMEOUT		_IOW('b', 3, __s64)
-#define BINDER_SET_MAX_THREADS		_IOW('b', 5, __u32)
-#define BINDER_SET_IDLE_PRIORITY	_IOW('b', 6, __s32)
-#define BINDER_SET_CONTEXT_MGR		_IOW('b', 7, __s32)
-#define BINDER_THREAD_EXIT		_IOW('b', 8, __s32)
-#define BINDER_VERSION			_IOWR('b', 9, struct binder_version)
-#define BINDER_GET_NODE_DEBUG_INFO	_IOWR('b', 11, struct binder_node_debug_info)
-#define BINDER_GET_NODE_INFO_FOR_REF	_IOWR('b', 12, struct binder_node_info_for_ref)
-#define BINDER_SET_CONTEXT_MGR_EXT	_IOW('b', 13, struct flat_binder_object)
-#define BINDER_FREEZE			_IOW('b', 14, struct binder_freeze_info)
-#define BINDER_GET_FROZEN_INFO		_IOWR('b', 15, struct binder_frozen_status_info)
-#define BINDER_ENABLE_ONEWAY_SPAM_DETECTION	_IOW('b', 16, __u32)
-#define BINDER_GET_EXTENDED_ERROR	_IOWR('b', 17, struct binder_extended_error)
+enum {
+	BINDER_WRITE_READ		= _IOWR('b', 1, struct binder_write_read),
+	BINDER_SET_IDLE_TIMEOUT		= _IOW('b', 3, __s64),
+	BINDER_SET_MAX_THREADS		= _IOW('b', 5, __u32),
+	BINDER_SET_IDLE_PRIORITY	= _IOW('b', 6, __s32),
+	BINDER_SET_CONTEXT_MGR		= _IOW('b', 7, __s32),
+	BINDER_THREAD_EXIT		= _IOW('b', 8, __s32),
+	BINDER_VERSION			= _IOWR('b', 9, struct binder_version),
+	BINDER_GET_NODE_DEBUG_INFO	= _IOWR('b', 11, struct binder_node_debug_info),
+	BINDER_GET_NODE_INFO_FOR_REF	= _IOWR('b', 12, struct binder_node_info_for_ref),
+	BINDER_SET_CONTEXT_MGR_EXT	= _IOW('b', 13, struct flat_binder_object),
+	BINDER_FREEZE			= _IOW('b', 14, struct binder_freeze_info),
+	BINDER_GET_FROZEN_INFO		= _IOWR('b', 15, struct binder_frozen_status_info),
+	BINDER_ENABLE_ONEWAY_SPAM_DETECTION	= _IOW('b', 16, __u32),
+	BINDER_GET_EXTENDED_ERROR	= _IOWR('b', 17, struct binder_extended_error),
+};
 
 /*
  * NOTE: Two special error codes you should check for when calling
-- 
cgit v1.2.3


From c27dfca4555bf74dd7dd7161d8ef2790ec1c7283 Mon Sep 17 00:00:00 2001
From: Ricky Wu <ricky_wu@realtek.com>
Date: Fri, 8 Dec 2023 11:21:43 +0800
Subject: misc: rtsx: add to support new card reader rts5264 new definition and
 function

in order to support NEW chip rts5264, the definitions of some internal
registers are define in new file rts5264.h, and some callback functions
and the workflow for rts5264 are define in new file rts5264.c

also add rts5264.o to Makefile

Signed-off-by: Ricky Wu <ricky_wu@realtek.com>
Link: https://lore.kernel.org/r/20231208032145.2143580-2-ricky_wu@realtek.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/cardreader/Makefile  |   2 +-
 drivers/misc/cardreader/rts5264.c | 886 ++++++++++++++++++++++++++++++++++++++
 drivers/misc/cardreader/rts5264.h | 278 ++++++++++++
 include/linux/rtsx_pci.h          |   8 +
 4 files changed, 1173 insertions(+), 1 deletion(-)
 create mode 100644 drivers/misc/cardreader/rts5264.c
 create mode 100644 drivers/misc/cardreader/rts5264.h

(limited to 'include')

diff --git a/drivers/misc/cardreader/Makefile b/drivers/misc/cardreader/Makefile
index 895128475d83..1e1bca6b0b22 100644
--- a/drivers/misc/cardreader/Makefile
+++ b/drivers/misc/cardreader/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_MISC_ALCOR_PCI)	+= alcor_pci.o
 obj-$(CONFIG_MISC_RTSX_PCI)	+= rtsx_pci.o
-rtsx_pci-objs := rtsx_pcr.o rts5209.o rts5229.o rtl8411.o rts5227.o rts5249.o rts5260.o rts5261.o rts5228.o
+rtsx_pci-objs := rtsx_pcr.o rts5209.o rts5229.o rtl8411.o rts5227.o rts5249.o rts5260.o rts5261.o rts5228.o rts5264.o
 obj-$(CONFIG_MISC_RTSX_USB)	+= rtsx_usb.o
diff --git a/drivers/misc/cardreader/rts5264.c b/drivers/misc/cardreader/rts5264.c
new file mode 100644
index 000000000000..8be4ed7d9d47
--- /dev/null
+++ b/drivers/misc/cardreader/rts5264.c
@@ -0,0 +1,886 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Driver for Realtek PCI-Express card reader
+ *
+ * Copyright(c) 2009-2013 Realtek Semiconductor Corp. All rights reserved.
+ *
+ * Author:
+ *   Ricky Wu <ricky_wu@realtek.com>
+ */
+
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/rtsx_pci.h>
+
+#include "rts5264.h"
+#include "rtsx_pcr.h"
+
+static u8 rts5264_get_ic_version(struct rtsx_pcr *pcr)
+{
+	u8 val;
+
+	rtsx_pci_read_register(pcr, DUMMY_REG_RESET_0, &val);
+	return val & 0x0F;
+}
+
+static void rts5264_fill_driving(struct rtsx_pcr *pcr, u8 voltage)
+{
+	u8 driving_3v3[4][3] = {
+		{0x88, 0x88, 0x88},
+		{0x77, 0x77, 0x77},
+		{0x99, 0x99, 0x99},
+		{0x66, 0x66, 0x66},
+	};
+	u8 driving_1v8[4][3] = {
+		{0x99, 0x99, 0x99},
+		{0x77, 0x77, 0x77},
+		{0xBB, 0xBB, 0xBB},
+		{0x65, 0x65, 0x65},
+	};
+	u8 (*driving)[3], drive_sel;
+
+	if (voltage == OUTPUT_3V3) {
+		driving = driving_3v3;
+		drive_sel = pcr->sd30_drive_sel_3v3;
+	} else {
+		driving = driving_1v8;
+		drive_sel = pcr->sd30_drive_sel_1v8;
+	}
+
+	rtsx_pci_write_register(pcr, SD30_CLK_DRIVE_SEL,
+			0xFF, driving[drive_sel][0]);
+	rtsx_pci_write_register(pcr, SD30_CMD_DRIVE_SEL,
+			0xFF, driving[drive_sel][1]);
+	rtsx_pci_write_register(pcr, SD30_DAT_DRIVE_SEL,
+			0xFF, driving[drive_sel][2]);
+}
+
+static void rts5264_force_power_down(struct rtsx_pcr *pcr, u8 pm_state, bool runtime)
+{
+	/* Set relink_time to 0 */
+	rtsx_pci_write_register(pcr, AUTOLOAD_CFG_BASE + 1, MASK_8_BIT_DEF, 0);
+	rtsx_pci_write_register(pcr, AUTOLOAD_CFG_BASE + 2, MASK_8_BIT_DEF, 0);
+	rtsx_pci_write_register(pcr, AUTOLOAD_CFG_BASE + 3,
+				RELINK_TIME_MASK, 0);
+
+	if (pm_state == HOST_ENTER_S3)
+		rtsx_pci_write_register(pcr, pcr->reg_pm_ctrl3,
+					D3_DELINK_MODE_EN, D3_DELINK_MODE_EN);
+
+	if (!runtime) {
+		rtsx_pci_write_register(pcr, RTS5264_AUTOLOAD_CFG1,
+				CD_RESUME_EN_MASK, 0);
+		rtsx_pci_write_register(pcr, pcr->reg_pm_ctrl3, 0x01, 0x00);
+		rtsx_pci_write_register(pcr, RTS5264_REG_PME_FORCE_CTL,
+				FORCE_PM_CONTROL | FORCE_PM_VALUE, FORCE_PM_CONTROL);
+	} else {
+		rtsx_pci_write_register(pcr, RTS5264_REG_PME_FORCE_CTL,
+				FORCE_PM_CONTROL | FORCE_PM_VALUE, 0);
+		rtsx_pci_write_register(pcr, pcr->reg_pm_ctrl3, 0x01, 0x01);
+		rtsx_pci_write_register(pcr, pcr->reg_pm_ctrl3,
+					D3_DELINK_MODE_EN, 0);
+		rtsx_pci_write_register(pcr, RTS5264_FW_CTL,
+				RTS5264_INFORM_RTD3_COLD, RTS5264_INFORM_RTD3_COLD);
+		rtsx_pci_write_register(pcr, RTS5264_AUTOLOAD_CFG4,
+				RTS5264_FORCE_PRSNT_LOW, RTS5264_FORCE_PRSNT_LOW);
+	}
+
+	rtsx_pci_write_register(pcr, RTS5264_REG_FPDCTL,
+		SSC_POWER_DOWN, SSC_POWER_DOWN);
+}
+
+static int rts5264_enable_auto_blink(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, OLT_LED_CTL,
+		LED_SHINE_MASK, LED_SHINE_EN);
+}
+
+static int rts5264_disable_auto_blink(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, OLT_LED_CTL,
+		LED_SHINE_MASK, LED_SHINE_DISABLE);
+}
+
+static int rts5264_turn_on_led(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, GPIO_CTL,
+		0x02, 0x02);
+}
+
+static int rts5264_turn_off_led(struct rtsx_pcr *pcr)
+{
+	return rtsx_pci_write_register(pcr, GPIO_CTL,
+		0x02, 0x00);
+}
+
+/* SD Pull Control Enable:
+ *     SD_DAT[3:0] ==> pull up
+ *     SD_CD       ==> pull up
+ *     SD_WP       ==> pull up
+ *     SD_CMD      ==> pull up
+ *     SD_CLK      ==> pull down
+ */
+static const u32 rts5264_sd_pull_ctl_enable_tbl[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL2, 0xAA),
+	RTSX_REG_PAIR(CARD_PULL_CTL3, 0xE9),
+	0,
+};
+
+/* SD Pull Control Disable:
+ *     SD_DAT[3:0] ==> pull down
+ *     SD_CD       ==> pull up
+ *     SD_WP       ==> pull down
+ *     SD_CMD      ==> pull down
+ *     SD_CLK      ==> pull down
+ */
+static const u32 rts5264_sd_pull_ctl_disable_tbl[] = {
+	RTSX_REG_PAIR(CARD_PULL_CTL2, 0x55),
+	RTSX_REG_PAIR(CARD_PULL_CTL3, 0xD5),
+	0,
+};
+
+static int rts5264_sd_set_sample_push_timing_sd30(struct rtsx_pcr *pcr)
+{
+	rtsx_pci_write_register(pcr, SD_CFG1, SD_MODE_SELECT_MASK
+		| SD_ASYNC_FIFO_NOT_RST, SD_30_MODE | SD_ASYNC_FIFO_NOT_RST);
+	rtsx_pci_write_register(pcr, CLK_CTL, CLK_LOW_FREQ, CLK_LOW_FREQ);
+	rtsx_pci_write_register(pcr, CARD_CLK_SOURCE, 0xFF,
+			CRC_VAR_CLK0 | SD30_FIX_CLK | SAMPLE_VAR_CLK1);
+	rtsx_pci_write_register(pcr, CLK_CTL, CLK_LOW_FREQ, 0);
+
+	return 0;
+}
+
+static int rts5264_card_power_on(struct rtsx_pcr *pcr, int card)
+{
+	struct rtsx_cr_option *option = &pcr->option;
+
+	if (option->ocp_en)
+		rtsx_pci_enable_ocp(pcr);
+
+	rtsx_pci_write_register(pcr, REG_CRC_DUMMY_0,
+		CFG_SD_POW_AUTO_PD, CFG_SD_POW_AUTO_PD);
+
+	rtsx_pci_write_register(pcr, RTS5264_LDO1_CFG1,
+			RTS5264_LDO1_TUNE_MASK, RTS5264_LDO1_33);
+	rtsx_pci_write_register(pcr, RTS5264_LDO1233318_POW_CTL,
+			RTS5264_LDO1_POWERON, RTS5264_LDO1_POWERON);
+	rtsx_pci_write_register(pcr, RTS5264_LDO1233318_POW_CTL,
+			RTS5264_LDO3318_POWERON, RTS5264_LDO3318_POWERON);
+
+	msleep(20);
+
+	rtsx_pci_write_register(pcr, CARD_OE, SD_OUTPUT_EN, SD_OUTPUT_EN);
+
+	/* Initialize SD_CFG1 register */
+	rtsx_pci_write_register(pcr, SD_CFG1, 0xFF,
+			SD_CLK_DIVIDE_128 | SD_20_MODE | SD_BUS_WIDTH_1BIT);
+	rtsx_pci_write_register(pcr, SD_SAMPLE_POINT_CTL,
+			0xFF, SD20_RX_POS_EDGE);
+	rtsx_pci_write_register(pcr, SD_PUSH_POINT_CTL, 0xFF, 0);
+	rtsx_pci_write_register(pcr, CARD_STOP, SD_STOP | SD_CLR_ERR,
+			SD_STOP | SD_CLR_ERR);
+
+	/* Reset SD_CFG3 register */
+	rtsx_pci_write_register(pcr, SD_CFG3, SD30_CLK_END_EN, 0);
+	rtsx_pci_write_register(pcr, REG_SD_STOP_SDCLK_CFG,
+			SD30_CLK_STOP_CFG_EN | SD30_CLK_STOP_CFG1 |
+			SD30_CLK_STOP_CFG0, 0);
+
+	if (pcr->extra_caps & EXTRA_CAPS_SD_SDR50 ||
+	    pcr->extra_caps & EXTRA_CAPS_SD_SDR104)
+		rts5264_sd_set_sample_push_timing_sd30(pcr);
+
+	return 0;
+}
+
+static int rts5264_switch_output_voltage(struct rtsx_pcr *pcr, u8 voltage)
+{
+	rtsx_pci_write_register(pcr, RTS5264_CARD_PWR_CTL,
+			RTS5264_PUPDC, RTS5264_PUPDC);
+
+	switch (voltage) {
+	case OUTPUT_3V3:
+		rtsx_pci_write_register(pcr, RTS5264_LDO1233318_POW_CTL,
+				RTS5264_TUNE_REF_LDO3318, RTS5264_TUNE_REF_LDO3318);
+		rtsx_pci_write_register(pcr, RTS5264_DV3318_CFG,
+				RTS5264_DV3318_TUNE_MASK, RTS5264_DV3318_33);
+		rtsx_pci_write_register(pcr, SD_PAD_CTL,
+				SD_IO_USING_1V8, 0);
+		break;
+	case OUTPUT_1V8:
+		rtsx_pci_write_register(pcr, RTS5264_LDO1233318_POW_CTL,
+				RTS5264_TUNE_REF_LDO3318, RTS5264_TUNE_REF_LDO3318_DFT);
+		rtsx_pci_write_register(pcr, RTS5264_DV3318_CFG,
+				RTS5264_DV3318_TUNE_MASK, RTS5264_DV3318_18);
+		rtsx_pci_write_register(pcr, SD_PAD_CTL,
+				SD_IO_USING_1V8, SD_IO_USING_1V8);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* set pad drive */
+	rts5264_fill_driving(pcr, voltage);
+
+	return 0;
+}
+
+static void rts5264_stop_cmd(struct rtsx_pcr *pcr)
+{
+	rtsx_pci_writel(pcr, RTSX_HCBCTLR, STOP_CMD);
+	rtsx_pci_writel(pcr, RTSX_HDBCTLR, STOP_DMA);
+	rtsx_pci_write_register(pcr, DMACTL, DMA_RST, DMA_RST);
+	rtsx_pci_write_register(pcr, RBCTL, RB_FLUSH, RB_FLUSH);
+}
+
+static void rts5264_card_before_power_off(struct rtsx_pcr *pcr)
+{
+	rts5264_stop_cmd(pcr);
+	rts5264_switch_output_voltage(pcr, OUTPUT_3V3);
+}
+
+static int rts5264_card_power_off(struct rtsx_pcr *pcr, int card)
+{
+	int err = 0;
+
+	rts5264_card_before_power_off(pcr);
+	err = rtsx_pci_write_register(pcr, RTS5264_LDO1233318_POW_CTL,
+				RTS5264_LDO_POWERON_MASK, 0);
+
+	rtsx_pci_write_register(pcr, REG_CRC_DUMMY_0,
+		CFG_SD_POW_AUTO_PD, 0);
+	if (pcr->option.ocp_en)
+		rtsx_pci_disable_ocp(pcr);
+
+	return err;
+}
+
+static void rts5264_enable_ocp(struct rtsx_pcr *pcr)
+{
+	u8 mask = 0;
+	u8 val = 0;
+
+	rtsx_pci_write_register(pcr, RTS5264_LDO1_CFG0,
+			RTS5264_LDO1_OCP_EN | RTS5264_LDO1_OCP_LMT_EN,
+			RTS5264_LDO1_OCP_EN | RTS5264_LDO1_OCP_LMT_EN);
+	rtsx_pci_write_register(pcr, RTS5264_LDO2_CFG0,
+			RTS5264_LDO2_OCP_EN | RTS5264_LDO2_OCP_LMT_EN,
+			RTS5264_LDO2_OCP_EN | RTS5264_LDO2_OCP_LMT_EN);
+	rtsx_pci_write_register(pcr, RTS5264_LDO3_CFG0,
+			RTS5264_LDO3_OCP_EN | RTS5264_LDO3_OCP_LMT_EN,
+			RTS5264_LDO3_OCP_EN | RTS5264_LDO3_OCP_LMT_EN);
+	rtsx_pci_write_register(pcr, RTS5264_OVP_DET,
+			RTS5264_POW_VDET, RTS5264_POW_VDET);
+
+	mask = SD_OCP_INT_EN | SD_DETECT_EN;
+	mask |= SDVIO_OCP_INT_EN | SDVIO_DETECT_EN;
+	val = mask;
+	rtsx_pci_write_register(pcr, REG_OCPCTL, mask, val);
+
+	mask = SD_VDD3_OCP_INT_EN | SD_VDD3_DETECT_EN;
+	val = mask;
+	rtsx_pci_write_register(pcr, RTS5264_OCP_VDD3_CTL, mask, val);
+
+	mask = RTS5264_OVP_INT_EN | RTS5264_OVP_DETECT_EN;
+	val = mask;
+	rtsx_pci_write_register(pcr, RTS5264_OVP_CTL, mask, val);
+}
+
+static void rts5264_disable_ocp(struct rtsx_pcr *pcr)
+{
+	u8 mask = 0;
+
+	mask = SD_OCP_INT_EN | SD_DETECT_EN;
+	mask |= SDVIO_OCP_INT_EN | SDVIO_DETECT_EN;
+	rtsx_pci_write_register(pcr, REG_OCPCTL, mask, 0);
+
+	mask = SD_VDD3_OCP_INT_EN | SD_VDD3_DETECT_EN;
+	rtsx_pci_write_register(pcr, RTS5264_OCP_VDD3_CTL, mask, 0);
+
+	mask = RTS5264_OVP_INT_EN | RTS5264_OVP_DETECT_EN;
+	rtsx_pci_write_register(pcr, RTS5264_OVP_CTL, mask, 0);
+
+	rtsx_pci_write_register(pcr, RTS5264_LDO1_CFG0,
+			RTS5264_LDO1_OCP_EN | RTS5264_LDO1_OCP_LMT_EN, 0);
+	rtsx_pci_write_register(pcr, RTS5264_LDO2_CFG0,
+			RTS5264_LDO2_OCP_EN | RTS5264_LDO2_OCP_LMT_EN, 0);
+	rtsx_pci_write_register(pcr, RTS5264_LDO3_CFG0,
+			RTS5264_LDO3_OCP_EN | RTS5264_LDO3_OCP_LMT_EN, 0);
+	rtsx_pci_write_register(pcr, RTS5264_OVP_DET, RTS5264_POW_VDET, 0);
+}
+
+static void rts5264_init_ocp(struct rtsx_pcr *pcr)
+{
+	struct rtsx_cr_option *option = &pcr->option;
+
+	if (option->ocp_en) {
+		u8 mask, val;
+
+		rtsx_pci_write_register(pcr, RTS5264_LDO1_CFG0,
+			RTS5264_LDO1_OCP_THD_MASK, option->sd_800mA_ocp_thd);
+		rtsx_pci_write_register(pcr, RTS5264_LDO1_CFG0,
+			RTS5264_LDO1_OCP_LMT_THD_MASK,
+			RTS5264_LDO1_LMT_THD_2000);
+
+		rtsx_pci_write_register(pcr, RTS5264_LDO2_CFG0,
+			RTS5264_LDO2_OCP_THD_MASK, RTS5264_LDO2_OCP_THD_950);
+		rtsx_pci_write_register(pcr, RTS5264_LDO2_CFG0,
+			RTS5264_LDO2_OCP_LMT_THD_MASK,
+			RTS5264_LDO2_LMT_THD_2000);
+
+		rtsx_pci_write_register(pcr, RTS5264_LDO3_CFG0,
+			RTS5264_LDO3_OCP_THD_MASK, RTS5264_LDO3_OCP_THD_710);
+		rtsx_pci_write_register(pcr, RTS5264_LDO3_CFG0,
+			RTS5264_LDO3_OCP_LMT_THD_MASK,
+			RTS5264_LDO3_LMT_THD_1500);
+
+		rtsx_pci_write_register(pcr, RTS5264_OVP_DET,
+			RTS5264_TUNE_VROV_MASK, RTS5264_TUNE_VROV_1V6);
+
+		mask = SD_OCP_GLITCH_MASK | SDVIO_OCP_GLITCH_MASK;
+		val = pcr->hw_param.ocp_glitch;
+		rtsx_pci_write_register(pcr, REG_OCPGLITCH, mask, val);
+
+	} else {
+		rtsx_pci_write_register(pcr, RTS5264_LDO1_CFG0,
+			RTS5264_LDO1_OCP_EN | RTS5264_LDO1_OCP_LMT_EN, 0);
+		rtsx_pci_write_register(pcr, RTS5264_LDO2_CFG0,
+			RTS5264_LDO2_OCP_EN | RTS5264_LDO2_OCP_LMT_EN, 0);
+		rtsx_pci_write_register(pcr, RTS5264_LDO3_CFG0,
+			RTS5264_LDO3_OCP_EN | RTS5264_LDO3_OCP_LMT_EN, 0);
+		rtsx_pci_write_register(pcr, RTS5264_OVP_DET,
+			RTS5264_POW_VDET, 0);
+	}
+}
+
+static int rts5264_get_ocpstat2(struct rtsx_pcr *pcr, u8 *val)
+{
+	return rtsx_pci_read_register(pcr, RTS5264_OCP_VDD3_STS, val);
+}
+
+static int rts5264_get_ovpstat(struct rtsx_pcr *pcr, u8 *val)
+{
+	return rtsx_pci_read_register(pcr, RTS5264_OVP_STS, val);
+}
+
+static void rts5264_clear_ocpstat(struct rtsx_pcr *pcr)
+{
+	u8 mask = 0;
+	u8 val = 0;
+
+	mask = SD_OCP_INT_CLR | SD_OC_CLR;
+	mask |= SDVIO_OCP_INT_CLR | SDVIO_OC_CLR;
+	val = mask;
+	rtsx_pci_write_register(pcr, REG_OCPCTL, mask, val);
+	rtsx_pci_write_register(pcr, RTS5264_OCP_VDD3_CTL,
+		SD_VDD3_OCP_INT_CLR | SD_VDD3_OC_CLR,
+		SD_VDD3_OCP_INT_CLR | SD_VDD3_OC_CLR);
+	rtsx_pci_write_register(pcr, RTS5264_OVP_CTL,
+		RTS5264_OVP_INT_CLR | RTS5264_OVP_CLR,
+		RTS5264_OVP_INT_CLR | RTS5264_OVP_CLR);
+
+	udelay(1000);
+
+	rtsx_pci_write_register(pcr, REG_OCPCTL, mask, 0);
+	rtsx_pci_write_register(pcr, RTS5264_OCP_VDD3_CTL,
+		SD_VDD3_OCP_INT_CLR | SD_VDD3_OC_CLR, 0);
+	rtsx_pci_write_register(pcr, RTS5264_OVP_CTL,
+		RTS5264_OVP_INT_CLR | RTS5264_OVP_CLR, 0);
+}
+
+static void rts5264_process_ocp(struct rtsx_pcr *pcr)
+{
+	if (!pcr->option.ocp_en)
+		return;
+
+	rtsx_pci_get_ocpstat(pcr, &pcr->ocp_stat);
+	rts5264_get_ocpstat2(pcr, &pcr->ocp_stat2);
+	rts5264_get_ovpstat(pcr, &pcr->ovp_stat);
+
+	if ((pcr->ocp_stat & (SD_OC_NOW | SD_OC_EVER | SDVIO_OC_NOW | SDVIO_OC_EVER)) ||
+			(pcr->ocp_stat2 & (SD_VDD3_OC_NOW | SD_VDD3_OC_EVER)) ||
+			(pcr->ovp_stat & (RTS5264_OVP_NOW | RTS5264_OVP_EVER))) {
+		rts5264_clear_ocpstat(pcr);
+		rts5264_card_power_off(pcr, RTSX_SD_CARD);
+		rtsx_pci_write_register(pcr, CARD_OE, SD_OUTPUT_EN, 0);
+		pcr->ocp_stat = 0;
+		pcr->ocp_stat2 = 0;
+		pcr->ovp_stat = 0;
+	}
+}
+
+static void rts5264_init_from_hw(struct rtsx_pcr *pcr)
+{
+	struct pci_dev *pdev = pcr->pci;
+	u32 lval1, lval2, i;
+	u16 setting_reg1, setting_reg2;
+	u8 valid, efuse_valid, tmp;
+
+	rtsx_pci_write_register(pcr, RTS5264_REG_PME_FORCE_CTL,
+		REG_EFUSE_POR | REG_EFUSE_POWER_MASK,
+		REG_EFUSE_POR | REG_EFUSE_POWERON);
+	udelay(1);
+	rtsx_pci_write_register(pcr, RTS5264_EFUSE_ADDR,
+		RTS5264_EFUSE_ADDR_MASK, 0x00);
+	rtsx_pci_write_register(pcr, RTS5264_EFUSE_CTL,
+		RTS5264_EFUSE_ENABLE | RTS5264_EFUSE_MODE_MASK,
+		RTS5264_EFUSE_ENABLE);
+
+	/* Wait transfer end */
+	for (i = 0; i < MAX_RW_REG_CNT; i++) {
+		rtsx_pci_read_register(pcr, RTS5264_EFUSE_CTL, &tmp);
+		if ((tmp & 0x80) == 0)
+			break;
+	}
+	rtsx_pci_read_register(pcr, RTS5264_EFUSE_READ_DATA, &tmp);
+	efuse_valid = ((tmp & 0x0C) >> 2);
+	pcr_dbg(pcr, "Load efuse valid: 0x%x\n", efuse_valid);
+
+	pci_read_config_dword(pdev, PCR_SETTING_REG2, &lval2);
+	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", PCR_SETTING_REG2, lval2);
+	/* 0x816 */
+	valid = (u8)((lval2 >> 16) & 0x03);
+
+	rtsx_pci_write_register(pcr, RTS5264_REG_PME_FORCE_CTL,
+		REG_EFUSE_POR, 0);
+	pcr_dbg(pcr, "Disable efuse por!\n");
+
+	if (efuse_valid == 2 || efuse_valid == 3) {
+		if (valid == 3) {
+			/* Bypass efuse */
+			setting_reg1 = PCR_SETTING_REG1;
+			setting_reg2 = PCR_SETTING_REG2;
+		} else {
+			/* Use efuse data */
+			setting_reg1 = PCR_SETTING_REG4;
+			setting_reg2 = PCR_SETTING_REG5;
+		}
+	} else if (efuse_valid == 0) {
+		// default
+		setting_reg1 = PCR_SETTING_REG1;
+		setting_reg2 = PCR_SETTING_REG2;
+	} else {
+		return;
+	}
+
+	pci_read_config_dword(pdev, setting_reg2, &lval2);
+	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", setting_reg2, lval2);
+
+	if (!rts5264_vendor_setting_valid(lval2)) {
+		pcr_dbg(pcr, "skip fetch vendor setting\n");
+		return;
+	}
+
+	pcr->rtd3_en = rts5264_reg_to_rtd3(lval2);
+
+	if (rts5264_reg_check_reverse_socket(lval2))
+		pcr->flags |= PCR_REVERSE_SOCKET;
+
+	pci_read_config_dword(pdev, setting_reg1, &lval1);
+	pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", setting_reg1, lval1);
+
+	pcr->aspm_en = rts5264_reg_to_aspm(lval1);
+	pcr->sd30_drive_sel_1v8 = rts5264_reg_to_sd30_drive_sel_1v8(lval1);
+	pcr->sd30_drive_sel_3v3 = rts5264_reg_to_sd30_drive_sel_3v3(lval1);
+
+	if (setting_reg1 == PCR_SETTING_REG1) {
+		/* store setting */
+		rtsx_pci_write_register(pcr, 0xFF0C, 0xFF, (u8)(lval1 & 0xFF));
+		rtsx_pci_write_register(pcr, 0xFF0D, 0xFF, (u8)((lval1 >> 8) & 0xFF));
+		rtsx_pci_write_register(pcr, 0xFF0E, 0xFF, (u8)((lval1 >> 16) & 0xFF));
+		rtsx_pci_write_register(pcr, 0xFF0F, 0xFF, (u8)((lval1 >> 24) & 0xFF));
+		rtsx_pci_write_register(pcr, 0xFF10, 0xFF, (u8)(lval2 & 0xFF));
+		rtsx_pci_write_register(pcr, 0xFF11, 0xFF, (u8)((lval2 >> 8) & 0xFF));
+		rtsx_pci_write_register(pcr, 0xFF12, 0xFF, (u8)((lval2 >> 16) & 0xFF));
+
+		pci_write_config_dword(pdev, PCR_SETTING_REG4, lval1);
+		lval2 = lval2 & 0x00FFFFFF;
+		pci_write_config_dword(pdev, PCR_SETTING_REG5, lval2);
+	}
+}
+
+static void rts5264_init_from_cfg(struct rtsx_pcr *pcr)
+{
+	struct rtsx_cr_option *option = &pcr->option;
+
+	if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN
+				| PM_L1_1_EN | PM_L1_2_EN))
+		rtsx_pci_disable_oobs_polling(pcr);
+	else
+		rtsx_pci_enable_oobs_polling(pcr);
+
+	rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, 0xFF, 0);
+
+	if (option->ltr_en) {
+		if (option->ltr_enabled)
+			rtsx_set_ltr_latency(pcr, option->ltr_active_latency);
+	}
+}
+
+static int rts5264_extra_init_hw(struct rtsx_pcr *pcr)
+{
+	struct rtsx_cr_option *option = &pcr->option;
+
+	rtsx_pci_write_register(pcr, RTS5264_AUTOLOAD_CFG1,
+			CD_RESUME_EN_MASK, CD_RESUME_EN_MASK);
+	rtsx_pci_write_register(pcr, REG_VREF, PWD_SUSPND_EN, PWD_SUSPND_EN);
+
+	rts5264_init_from_cfg(pcr);
+	rts5264_init_from_hw(pcr);
+
+	/* power off efuse */
+	rtsx_pci_write_register(pcr, RTS5264_REG_PME_FORCE_CTL,
+			REG_EFUSE_POWER_MASK, REG_EFUSE_POWEROFF);
+	rtsx_pci_write_register(pcr, RTS5264_AUTOLOAD_CFG2,
+			RTS5264_CHIP_RST_N_SEL, 0);
+	rtsx_pci_write_register(pcr, RTS5264_REG_LDO12_CFG,
+			RTS5264_LDO12_SR_MASK, RTS5264_LDO12_SR_0_0_MS);
+	rtsx_pci_write_register(pcr, CDGW, 0xFF, 0x01);
+	rtsx_pci_write_register(pcr, RTS5264_CKMUX_MBIAS_PWR,
+			RTS5264_POW_CKMUX, RTS5264_POW_CKMUX);
+	rtsx_pci_write_register(pcr, RTS5264_CMD_OE_START_EARLY,
+			RTS5264_CMD_OE_EARLY_EN | RTS5264_CMD_OE_EARLY_CYCLE_MASK,
+			RTS5264_CMD_OE_EARLY_EN);
+	rtsx_pci_write_register(pcr, RTS5264_DAT_OE_START_EARLY,
+			RTS5264_DAT_OE_EARLY_EN | RTS5264_DAT_OE_EARLY_CYCLE_MASK,
+			RTS5264_DAT_OE_EARLY_EN);
+	rtsx_pci_write_register(pcr, SSC_DIV_N_0, 0xFF, 0x5D);
+
+	rtsx_pci_write_register(pcr, RTS5264_PWR_CUT,
+			RTS5264_CFG_MEM_PD, RTS5264_CFG_MEM_PD);
+	rtsx_pci_write_register(pcr, L1SUB_CONFIG1,
+			AUX_CLK_ACTIVE_SEL_MASK, MAC_CKSW_DONE);
+	rtsx_pci_write_register(pcr, L1SUB_CONFIG3, 0xFF, 0);
+	rtsx_pci_write_register(pcr, RTS5264_AUTOLOAD_CFG4,
+			RTS5264_AUX_CLK_16M_EN, 0);
+
+	/* Release PRSNT# */
+	rtsx_pci_write_register(pcr, RTS5264_AUTOLOAD_CFG4,
+			RTS5264_FORCE_PRSNT_LOW, 0);
+	rtsx_pci_write_register(pcr, PCLK_CTL,
+			PCLK_MODE_SEL, PCLK_MODE_SEL);
+
+	/* LED shine disabled, set initial shine cycle period */
+	rtsx_pci_write_register(pcr, OLT_LED_CTL, 0x0F, 0x02);
+
+	/* Configure driving */
+	rts5264_fill_driving(pcr, OUTPUT_3V3);
+
+	if (pcr->flags & PCR_REVERSE_SOCKET)
+		rtsx_pci_write_register(pcr, PETXCFG, 0x30, 0x30);
+	else
+		rtsx_pci_write_register(pcr, PETXCFG, 0x30, 0x00);
+
+	/*
+	 * If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced
+	 * to drive low, and we forcibly request clock.
+	 */
+	if (option->force_clkreq_0)
+		rtsx_pci_write_register(pcr, PETXCFG,
+				 FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW);
+	else
+		rtsx_pci_write_register(pcr, PETXCFG,
+				 FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_HIGH);
+
+	rtsx_pci_write_register(pcr, PWD_SUSPEND_EN, 0xFF, 0xFF);
+	rtsx_pci_write_register(pcr, RBCTL, U_AUTO_DMA_EN_MASK, 0);
+	rtsx_pci_write_register(pcr, RTS5264_AUTOLOAD_CFG4,
+			RTS5264_F_HIGH_RC_MASK, RTS5264_F_HIGH_RC_400K);
+
+	if (pcr->rtd3_en) {
+		rtsx_pci_write_register(pcr, pcr->reg_pm_ctrl3, 0x01, 0x00);
+		rtsx_pci_write_register(pcr, RTS5264_REG_PME_FORCE_CTL,
+				FORCE_PM_CONTROL | FORCE_PM_VALUE, 0);
+	} else {
+		rtsx_pci_write_register(pcr, pcr->reg_pm_ctrl3, 0x01, 0x00);
+		rtsx_pci_write_register(pcr, RTS5264_REG_PME_FORCE_CTL,
+				FORCE_PM_CONTROL | FORCE_PM_VALUE, FORCE_PM_CONTROL);
+	}
+	rtsx_pci_write_register(pcr, pcr->reg_pm_ctrl3, D3_DELINK_MODE_EN, 0x00);
+
+	/* Clear Enter RTD3_cold Information*/
+	rtsx_pci_write_register(pcr, RTS5264_FW_CTL,
+		RTS5264_INFORM_RTD3_COLD, 0);
+
+	return 0;
+}
+
+static void rts5264_enable_aspm(struct rtsx_pcr *pcr, bool enable)
+{
+	u8 val = FORCE_ASPM_CTL0 | FORCE_ASPM_CTL1;
+	u8 mask = FORCE_ASPM_VAL_MASK | FORCE_ASPM_CTL0 | FORCE_ASPM_CTL1;
+
+	if (pcr->aspm_enabled == enable)
+		return;
+
+	val |= (pcr->aspm_en & 0x02);
+	rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, mask, val);
+	pcie_capability_clear_and_set_word(pcr->pci, PCI_EXP_LNKCTL,
+					   PCI_EXP_LNKCTL_ASPMC, pcr->aspm_en);
+	pcr->aspm_enabled = enable;
+}
+
+static void rts5264_disable_aspm(struct rtsx_pcr *pcr, bool enable)
+{
+	u8 val = FORCE_ASPM_CTL0 | FORCE_ASPM_CTL1;
+	u8 mask = FORCE_ASPM_VAL_MASK | FORCE_ASPM_CTL0 | FORCE_ASPM_CTL1;
+
+	if (pcr->aspm_enabled == enable)
+		return;
+
+	pcie_capability_clear_and_set_word(pcr->pci, PCI_EXP_LNKCTL,
+					   PCI_EXP_LNKCTL_ASPMC, 0);
+	rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, mask, val);
+	rtsx_pci_write_register(pcr, SD_CFG1, SD_ASYNC_FIFO_NOT_RST, 0);
+	udelay(10);
+	pcr->aspm_enabled = enable;
+}
+
+static void rts5264_set_aspm(struct rtsx_pcr *pcr, bool enable)
+{
+	if (enable)
+		rts5264_enable_aspm(pcr, true);
+	else
+		rts5264_disable_aspm(pcr, false);
+}
+
+static void rts5264_set_l1off_cfg_sub_d0(struct rtsx_pcr *pcr, int active)
+{
+	struct rtsx_cr_option *option = &(pcr->option);
+
+	u32 interrupt = rtsx_pci_readl(pcr, RTSX_BIPR);
+	int card_exist = (interrupt & SD_EXIST);
+	int aspm_L1_1, aspm_L1_2;
+	u8 val = 0;
+
+	aspm_L1_1 = rtsx_check_dev_flag(pcr, ASPM_L1_1_EN);
+	aspm_L1_2 = rtsx_check_dev_flag(pcr, ASPM_L1_2_EN);
+
+	if (active) {
+		/* Run, latency: 60us */
+		if (aspm_L1_1)
+			val = option->ltr_l1off_snooze_sspwrgate;
+	} else {
+		/* L1off, latency: 300us */
+		if (aspm_L1_2)
+			val = option->ltr_l1off_sspwrgate;
+	}
+
+	if (aspm_L1_1 || aspm_L1_2) {
+		if (rtsx_check_dev_flag(pcr,
+					LTR_L1SS_PWR_GATE_CHECK_CARD_EN)) {
+			if (card_exist)
+				val &= ~L1OFF_MBIAS2_EN_5250;
+			else
+				val |= L1OFF_MBIAS2_EN_5250;
+		}
+	}
+	rtsx_set_l1off_sub(pcr, val);
+}
+
+static const struct pcr_ops rts5264_pcr_ops = {
+	.turn_on_led = rts5264_turn_on_led,
+	.turn_off_led = rts5264_turn_off_led,
+	.extra_init_hw = rts5264_extra_init_hw,
+	.enable_auto_blink = rts5264_enable_auto_blink,
+	.disable_auto_blink = rts5264_disable_auto_blink,
+	.card_power_on = rts5264_card_power_on,
+	.card_power_off = rts5264_card_power_off,
+	.switch_output_voltage = rts5264_switch_output_voltage,
+	.force_power_down = rts5264_force_power_down,
+	.stop_cmd = rts5264_stop_cmd,
+	.set_aspm = rts5264_set_aspm,
+	.set_l1off_cfg_sub_d0 = rts5264_set_l1off_cfg_sub_d0,
+	.enable_ocp = rts5264_enable_ocp,
+	.disable_ocp = rts5264_disable_ocp,
+	.init_ocp = rts5264_init_ocp,
+	.process_ocp = rts5264_process_ocp,
+	.clear_ocpstat = rts5264_clear_ocpstat,
+};
+
+static inline u8 double_ssc_depth(u8 depth)
+{
+	return ((depth > 1) ? (depth - 1) : depth);
+}
+
+int rts5264_pci_switch_clock(struct rtsx_pcr *pcr, unsigned int card_clock,
+		u8 ssc_depth, bool initial_mode, bool double_clk, bool vpclk)
+{
+	int err, clk;
+	u16 n;
+	u8 clk_divider, mcu_cnt, div;
+	static const u8 depth[] = {
+		[RTSX_SSC_DEPTH_4M] = RTS5264_SSC_DEPTH_4M,
+		[RTSX_SSC_DEPTH_2M] = RTS5264_SSC_DEPTH_2M,
+		[RTSX_SSC_DEPTH_1M] = RTS5264_SSC_DEPTH_1M,
+		[RTSX_SSC_DEPTH_500K] = RTS5264_SSC_DEPTH_512K,
+	};
+
+	if (initial_mode) {
+		/* We use 250k(around) here, in initial stage */
+		clk_divider = SD_CLK_DIVIDE_128;
+		card_clock = 30000000;
+	} else {
+		clk_divider = SD_CLK_DIVIDE_0;
+	}
+	err = rtsx_pci_write_register(pcr, SD_CFG1,
+			SD_CLK_DIVIDE_MASK, clk_divider);
+	if (err < 0)
+		return err;
+
+	card_clock /= 1000000;
+	pcr_dbg(pcr, "Switch card clock to %dMHz\n", card_clock);
+
+	clk = card_clock;
+	if (!initial_mode && double_clk)
+		clk = card_clock * 2;
+	pcr_dbg(pcr, "Internal SSC clock: %dMHz (cur_clock = %d)\n",
+		clk, pcr->cur_clock);
+
+	if (clk == pcr->cur_clock)
+		return 0;
+
+	if (pcr->ops->conv_clk_and_div_n)
+		n = pcr->ops->conv_clk_and_div_n(clk, CLK_TO_DIV_N);
+	else
+		n = clk - 4;
+	if ((clk <= 4) || (n > 396))
+		return -EINVAL;
+
+	mcu_cnt = 125/clk + 3;
+	if (mcu_cnt > 15)
+		mcu_cnt = 15;
+
+	div = CLK_DIV_1;
+	while ((n < MIN_DIV_N_PCR - 4) && (div < CLK_DIV_8)) {
+		if (pcr->ops->conv_clk_and_div_n) {
+			int dbl_clk = pcr->ops->conv_clk_and_div_n(n,
+					DIV_N_TO_CLK) * 2;
+			n = pcr->ops->conv_clk_and_div_n(dbl_clk,
+					CLK_TO_DIV_N);
+		} else {
+			n = (n + 4) * 2 - 4;
+		}
+		div++;
+	}
+
+	n = (n / 2) - 1;
+	pcr_dbg(pcr, "n = %d, div = %d\n", n, div);
+
+	ssc_depth = depth[ssc_depth];
+	if (double_clk)
+		ssc_depth = double_ssc_depth(ssc_depth);
+
+	if (ssc_depth) {
+		if (div == CLK_DIV_2) {
+			if (ssc_depth > 1)
+				ssc_depth -= 1;
+			else
+				ssc_depth = RTS5264_SSC_DEPTH_8M;
+		} else if (div == CLK_DIV_4) {
+			if (ssc_depth > 2)
+				ssc_depth -= 2;
+			else
+				ssc_depth = RTS5264_SSC_DEPTH_8M;
+		} else if (div == CLK_DIV_8) {
+			if (ssc_depth > 3)
+				ssc_depth -= 3;
+			else
+				ssc_depth = RTS5264_SSC_DEPTH_8M;
+		}
+	} else {
+		ssc_depth = 0;
+	}
+	pcr_dbg(pcr, "ssc_depth = %d\n", ssc_depth);
+
+	rtsx_pci_init_cmd(pcr);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CLK_CTL,
+				CHANGE_CLK, CHANGE_CLK);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CLK_DIV,
+			0xFF, (div << 4) | mcu_cnt);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL1, SSC_RSTB, 0);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL2,
+			SSC_DEPTH_MASK, ssc_depth);
+	rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_DIV_N_0, 0xFF, n);
+
+	if (is_version(pcr, 0x5264, IC_VER_A)) {
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL1, SSC_RSTB, 0);
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, RTS5264_CARD_CLK_SRC2,
+			RTS5264_REG_BIG_KVCO_A, 0);
+	} else {
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL1, SSC_RSTB, SSC_RSTB);
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, RTS5264_SYS_DUMMY_1,
+			RTS5264_REG_BIG_KVCO, 0);
+	}
+
+	if (vpclk) {
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SD_VPCLK0_CTL,
+				PHASE_NOT_RESET, 0);
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SD_VPCLK1_CTL,
+				PHASE_NOT_RESET, 0);
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SD_VPCLK0_CTL,
+				PHASE_NOT_RESET, PHASE_NOT_RESET);
+		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SD_VPCLK1_CTL,
+				PHASE_NOT_RESET, PHASE_NOT_RESET);
+	}
+
+	err = rtsx_pci_send_cmd(pcr, 2000);
+	if (err < 0)
+		return err;
+
+	/* Wait SSC clock stable */
+	udelay(SSC_CLOCK_STABLE_WAIT);
+	err = rtsx_pci_write_register(pcr, CLK_CTL, CHANGE_CLK, 0);
+	if (err < 0)
+		return err;
+
+	pcr->cur_clock = clk;
+	return 0;
+}
+
+void rts5264_init_params(struct rtsx_pcr *pcr)
+{
+	struct rtsx_cr_option *option = &pcr->option;
+	struct rtsx_hw_param *hw_param = &pcr->hw_param;
+	u8 val;
+
+	pcr->extra_caps = EXTRA_CAPS_SD_SDR50 | EXTRA_CAPS_SD_SDR104;
+	pcr->extra_caps |= EXTRA_CAPS_NO_MMC;
+	rtsx_pci_read_register(pcr, RTS5264_FW_STATUS, &val);
+	if (!(val & RTS5264_EXPRESS_LINK_FAIL_MASK))
+		pcr->extra_caps |= EXTRA_CAPS_SD_EXPRESS;
+	pcr->num_slots = 1;
+	pcr->ops = &rts5264_pcr_ops;
+
+	pcr->flags = 0;
+	pcr->card_drive_sel = RTSX_CARD_DRIVE_DEFAULT;
+	pcr->sd30_drive_sel_1v8 = 0x00;
+	pcr->sd30_drive_sel_3v3 = 0x00;
+	pcr->aspm_en = ASPM_L1_EN;
+	pcr->aspm_mode = ASPM_MODE_REG;
+	pcr->tx_initial_phase = SET_CLOCK_PHASE(24, 24, 11);
+	pcr->rx_initial_phase = SET_CLOCK_PHASE(24, 6, 5);
+
+	pcr->ic_version = rts5264_get_ic_version(pcr);
+	pcr->sd_pull_ctl_enable_tbl = rts5264_sd_pull_ctl_enable_tbl;
+	pcr->sd_pull_ctl_disable_tbl = rts5264_sd_pull_ctl_disable_tbl;
+
+	pcr->reg_pm_ctrl3 = RTS5264_AUTOLOAD_CFG3;
+
+	option->dev_flags = (LTR_L1SS_PWR_GATE_CHECK_CARD_EN
+				| LTR_L1SS_PWR_GATE_EN);
+	option->ltr_en = true;
+
+	/* init latency of active, idle, L1OFF to 60us, 300us, 3ms */
+	option->ltr_active_latency = LTR_ACTIVE_LATENCY_DEF;
+	option->ltr_idle_latency = LTR_IDLE_LATENCY_DEF;
+	option->ltr_l1off_latency = LTR_L1OFF_LATENCY_DEF;
+	option->l1_snooze_delay = L1_SNOOZE_DELAY_DEF;
+	option->ltr_l1off_sspwrgate = 0x7F;
+	option->ltr_l1off_snooze_sspwrgate = 0x78;
+
+	option->ocp_en = 1;
+	hw_param->interrupt_en |= (SD_OC_INT_EN | SD_OVP_INT_EN);
+	hw_param->ocp_glitch =  SD_OCP_GLITCH_800U | SDVIO_OCP_GLITCH_800U;
+	option->sd_800mA_ocp_thd =  RTS5264_LDO1_OCP_THD_1150;
+}
diff --git a/drivers/misc/cardreader/rts5264.h b/drivers/misc/cardreader/rts5264.h
new file mode 100644
index 000000000000..e3cbbf2fe1a4
--- /dev/null
+++ b/drivers/misc/cardreader/rts5264.h
@@ -0,0 +1,278 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Driver for Realtek PCI-Express card reader
+ *
+ * Copyright(c) 2018-2019 Realtek Semiconductor Corp. All rights reserved.
+ *
+ * Author:
+ *   Ricky Wu <ricky_wu@realtek.com>
+ */
+#ifndef RTS5264_H
+#define RTS5264_H
+
+/*New add*/
+#define rts5264_vendor_setting_valid(reg)	((reg) & 0x010000)
+#define rts5264_reg_to_aspm(reg) \
+	(((~(reg) >> 28) & 0x02) | (((reg) >> 28) & 0x01))
+#define rts5264_reg_check_reverse_socket(reg)	((reg) & 0x04)
+#define rts5264_reg_to_sd30_drive_sel_1v8(reg)	(((reg) >> 22) & 0x03)
+#define rts5264_reg_to_sd30_drive_sel_3v3(reg)	(((reg) >> 16) & 0x03)
+#define rts5264_reg_to_rtd3(reg)		((reg) & 0x08)
+
+#define RTS5264_AUTOLOAD_CFG0		0xFF7B
+#define RTS5264_AUTOLOAD_CFG1		0xFF7C
+#define RTS5264_AUTOLOAD_CFG3		0xFF7E
+#define RTS5264_AUTOLOAD_CFG4		0xFF7F
+#define RTS5264_FORCE_PRSNT_LOW		(1 << 6)
+#define RTS5264_AUX_CLK_16M_EN		(1 << 5)
+#define RTS5264_F_HIGH_RC_MASK		(1 << 4)
+#define RTS5264_F_HIGH_RC_1_6M		(1 << 4)
+#define RTS5264_F_HIGH_RC_400K		(0 << 4)
+
+/* SSC_CTL2 0xFC12 */
+#define RTS5264_SSC_DEPTH_MASK		0x07
+#define RTS5264_SSC_DEPTH_DISALBE	0x00
+#define RTS5264_SSC_DEPTH_8M		0x01
+#define RTS5264_SSC_DEPTH_4M		0x02
+#define RTS5264_SSC_DEPTH_2M		0x03
+#define RTS5264_SSC_DEPTH_1M		0x04
+#define RTS5264_SSC_DEPTH_512K		0x05
+#define RTS5264_SSC_DEPTH_256K		0x06
+#define RTS5264_SSC_DEPTH_128K		0x07
+
+#define RTS5264_CARD_CLK_SRC2		0xFC2F
+#define RTS5264_REG_BIG_KVCO_A		0x20
+
+/* efuse control register*/
+#define RTS5264_EFUSE_CTL		0xFC30
+#define RTS5264_EFUSE_ENABLE		0x80
+/* EFUSE_MODE: 0=READ 1=PROGRAM */
+#define RTS5264_EFUSE_MODE_MASK		0x40
+#define RTS5264_EFUSE_PROGRAM		0x40
+
+#define RTS5264_EFUSE_ADDR		0xFC31
+#define	RTS5264_EFUSE_ADDR_MASK		0x3F
+
+#define RTS5264_EFUSE_WRITE_DATA	0xFC32
+#define RTS5264_EFUSE_READ_DATA		0xFC34
+
+#define RTS5264_SYS_DUMMY_1		0xFC35
+#define RTS5264_REG_BIG_KVCO		0x04
+
+/* DMACTL 0xFE2C */
+#define RTS5264_DMA_PACK_SIZE_MASK	0x70
+
+#define RTS5264_FW_CFG1			0xFF55
+#define RTS5264_SYS_CLK_SEL_MCU_CLK	(0x01<<7)
+#define RTS5264_CRC_CLK_SEL_MCU_CLK	(0x01<<6)
+#define RTS5264_FAKE_MCU_CLOCK_GATING	(0x01<<5)
+#define RTS5264_MCU_BUS_SEL_MASK	(0x01<<4)
+
+/* FW status register */
+#define RTS5264_FW_STATUS		0xFF56
+#define RTS5264_EXPRESS_LINK_FAIL_MASK	(0x01<<7)
+
+/* FW control register */
+#define RTS5264_FW_CTL			0xFF5F
+#define RTS5264_INFORM_RTD3_COLD	(0x01<<5)
+
+#define RTS5264_REG_FPDCTL		0xFF60
+
+#define RTS5264_REG_LDO12_CFG		0xFF6E
+#define RTS5264_LDO12_SR_MASK		(0x03<<6)
+#define RTS5264_LDO12_SR_1_0_MS		(0x03<<6)
+#define RTS5264_LDO12_SR_0_5_MS		(0x02<<6)
+#define RTS5264_LDO12_SR_0_2_5_MS	(0x01<<6)
+#define RTS5264_LDO12_SR_0_0_MS		(0x00<<6)
+#define RTS5264_LDO12_VO_TUNE_MASK	(0x07<<1)
+#define RTS5264_LDO12_115		(0x03<<1)
+#define RTS5264_LDO12_120		(0x04<<1)
+#define RTS5264_LDO12_125		(0x05<<1)
+#define RTS5264_LDO12_130		(0x06<<1)
+#define RTS5264_LDO12_135		(0x07<<1)
+
+/* LDO control register */
+#define RTS5264_CARD_PWR_CTL		0xFD50
+#define RTS5264_SD_CLK_ISO		(0x01<<7)
+#define RTS5264_PAD_SD_DAT_FW_CTRL	(0x01<<6)
+#define RTS5264_PUPDC			(0x01<<5)
+#define RTS5264_SD_CMD_ISO		(0x01<<4)
+
+#define RTS5264_OCP_VDD3_CTL		0xFD89
+#define SD_VDD3_DETECT_EN		0x08
+#define SD_VDD3_OCP_INT_EN		0x04
+#define SD_VDD3_OCP_INT_CLR		0x02
+#define SD_VDD3_OC_CLR			0x01
+
+#define RTS5264_OCP_VDD3_STS		0xFD8A
+#define SD_VDD3_OCP_DETECT		0x08
+#define SD_VDD3_OC_NOW			0x04
+#define SD_VDD3_OC_EVER			0x02
+
+#define RTS5264_OVP_CTL			0xFD8D
+#define RTS5264_OVP_TIME_MASK		0xF0
+#define RTS5264_OVP_TIME_DFT		0x50
+#define RTS5264_OVP_DETECT_EN		0x08
+#define RTS5264_OVP_INT_EN		0x04
+#define RTS5264_OVP_INT_CLR		0x02
+#define RTS5264_OVP_CLR			0x01
+
+#define RTS5264_OVP_STS			0xFD8E
+#define RTS5264_OVP_GLTCH_TIME_MASK	0xF0
+#define RTS5264_OVP_GLTCH_TIME_DFT	0x50
+#define RTS5264_VOVER_DET		0x08
+#define RTS5264_OVP_NOW			0x04
+#define RTS5264_OVP_EVER		0x02
+
+#define RTS5264_CMD_OE_START_EARLY		0xFDCB
+#define RTS5264_CMD_OE_EARLY_LEAVE		0x08
+#define RTS5264_CMD_OE_EARLY_CYCLE_MASK		0x06
+#define RTS5264_CMD_OE_EARLY_4CYCLE		0x06
+#define RTS5264_CMD_OE_EARLY_3CYCLE		0x04
+#define RTS5264_CMD_OE_EARLY_2CYCLE		0x02
+#define RTS5264_CMD_OE_EARLY_1CYCLE		0x00
+#define RTS5264_CMD_OE_EARLY_EN			0x01
+
+#define RTS5264_DAT_OE_START_EARLY		0xFDCC
+#define RTS5264_DAT_OE_EARLY_LEAVE		0x08
+#define RTS5264_DAT_OE_EARLY_CYCLE_MASK		0x06
+#define RTS5264_DAT_OE_EARLY_4CYCLE		0x06
+#define RTS5264_DAT_OE_EARLY_3CYCLE		0x04
+#define RTS5264_DAT_OE_EARLY_2CYCLE		0x02
+#define RTS5264_DAT_OE_EARLY_1CYCLE		0x00
+#define RTS5264_DAT_OE_EARLY_EN			0x01
+
+#define RTS5264_LDO1233318_POW_CTL	0xFF70
+#define RTS5264_TUNE_REF_LDO3318	(0x03<<6)
+#define RTS5264_TUNE_REF_LDO3318_DFT	(0x02<<6)
+#define RTS5264_LDO3318_POWERON		(0x01<<3)
+#define RTS5264_LDO3_POWERON		(0x01<<2)
+#define RTS5264_LDO2_POWERON		(0x01<<1)
+#define RTS5264_LDO1_POWERON		(0x01<<0)
+#define RTS5264_LDO_POWERON_MASK	(0x0F<<0)
+
+#define RTS5264_DV3318_CFG		0xFF71
+#define RTS5264_DV3318_TUNE_MASK	(0x07<<4)
+#define RTS5264_DV3318_18		(0x02<<4)
+#define RTS5264_DV3318_19		(0x04<<4)
+#define RTS5264_DV3318_33		(0x07<<4)
+
+#define RTS5264_LDO1_CFG0		0xFF72
+#define RTS5264_LDO1_OCP_THD_MASK	(0x07 << 5)
+#define RTS5264_LDO1_OCP_EN		(0x01 << 4)
+#define RTS5264_LDO1_OCP_LMT_THD_MASK	(0x03 << 2)
+#define RTS5264_LDO1_OCP_LMT_EN		(0x01 << 1)
+
+#define RTS5264_LDO1_OCP_THD_850	(0x00<<5)
+#define RTS5264_LDO1_OCP_THD_950	(0x01<<5)
+#define RTS5264_LDO1_OCP_THD_1050	(0x02<<5)
+#define RTS5264_LDO1_OCP_THD_1100	(0x03<<5)
+#define RTS5264_LDO1_OCP_THD_1150	(0x04<<5)
+#define RTS5264_LDO1_OCP_THD_1200	(0x05<<5)
+#define RTS5264_LDO1_OCP_THD_1300	(0x06<<5)
+#define RTS5264_LDO1_OCP_THD_1350	(0x07<<5)
+
+#define RTS5264_LDO1_LMT_THD_1700	(0x00<<2)
+#define RTS5264_LDO1_LMT_THD_1800	(0x01<<2)
+#define RTS5264_LDO1_LMT_THD_1900	(0x02<<2)
+#define RTS5264_LDO1_LMT_THD_2000	(0x03<<2)
+
+#define RTS5264_LDO1_CFG1		0xFF73
+#define RTS5264_LDO1_TUNE_MASK		(0x07<<1)
+#define RTS5264_LDO1_18			(0x05<<1)
+#define RTS5264_LDO1_33			(0x07<<1)
+#define RTS5264_LDO1_PWD_MASK		(0x01<<0)
+
+#define RTS5264_LDO2_CFG0		0xFF74
+#define RTS5264_LDO2_OCP_THD_MASK	(0x07<<5)
+#define RTS5264_LDO2_OCP_EN		(0x01<<4)
+#define RTS5264_LDO2_OCP_LMT_THD_MASK	(0x03<<2)
+#define RTS5264_LDO2_OCP_LMT_EN		(0x01<<1)
+
+#define RTS5264_LDO2_OCP_THD_750	(0x00<<5)
+#define RTS5264_LDO2_OCP_THD_850	(0x01<<5)
+#define RTS5264_LDO2_OCP_THD_900	(0x02<<5)
+#define RTS5264_LDO2_OCP_THD_950	(0x03<<5)
+#define RTS5264_LDO2_OCP_THD_1050	(0x04<<5)
+#define RTS5264_LDO2_OCP_THD_1100	(0x05<<5)
+#define RTS5264_LDO2_OCP_THD_1150	(0x06<<5)
+#define RTS5264_LDO2_OCP_THD_1200	(0x07<<5)
+
+#define RTS5264_LDO2_LMT_THD_1700	(0x00<<2)
+#define RTS5264_LDO2_LMT_THD_1800	(0x01<<2)
+#define RTS5264_LDO2_LMT_THD_1900	(0x02<<2)
+#define RTS5264_LDO2_LMT_THD_2000	(0x03<<2)
+
+#define RTS5264_LDO2_CFG1		0xFF75
+#define RTS5264_LDO2_TUNE_MASK		(0x07<<1)
+#define RTS5264_LDO2_18			(0x02<<1)
+#define RTS5264_LDO2_185		(0x03<<1)
+#define RTS5264_LDO2_19			(0x04<<1)
+#define RTS5264_LDO2_195		(0x05<<1)
+#define RTS5264_LDO2_33			(0x07<<1)
+#define RTS5264_LDO2_PWD_MASK		(0x01<<0)
+
+#define RTS5264_LDO3_CFG0		0xFF76
+#define RTS5264_LDO3_OCP_THD_MASK	(0x07<<5)
+#define RTS5264_LDO3_OCP_EN		(0x01<<4)
+#define RTS5264_LDO3_OCP_LMT_THD_MASK	(0x03<<2)
+#define RTS5264_LDO3_OCP_LMT_EN		(0x01<<1)
+
+#define RTS5264_LDO3_OCP_THD_610	(0x00<<5)
+#define RTS5264_LDO3_OCP_THD_630	(0x01<<5)
+#define RTS5264_LDO3_OCP_THD_670	(0x02<<5)
+#define RTS5264_LDO3_OCP_THD_710	(0x03<<5)
+#define RTS5264_LDO3_OCP_THD_750	(0x04<<5)
+#define RTS5264_LDO3_OCP_THD_770	(0x05<<5)
+#define RTS5264_LDO3_OCP_THD_810	(0x06<<5)
+#define RTS5264_LDO3_OCP_THD_850	(0x07<<5)
+
+#define RTS5264_LDO3_LMT_THD_1200	(0x00<<2)
+#define RTS5264_LDO3_LMT_THD_1300	(0x01<<2)
+#define RTS5264_LDO3_LMT_THD_1400	(0x02<<2)
+#define RTS5264_LDO3_LMT_THD_1500	(0x03<<2)
+
+#define RTS5264_LDO3_CFG1		0xFF77
+#define RTS5264_LDO3_TUNE_MASK		(0x07<<1)
+#define RTS5264_LDO3_12			(0x02<<1)
+#define RTS5264_LDO3_125		(0x03<<1)
+#define RTS5264_LDO3_13			(0x04<<1)
+#define RTS5264_LDO3_135		(0x05<<1)
+#define RTS5264_LDO3_33			(0x07<<1)
+#define RTS5264_LDO3_PWD_MASK		(0x01<<0)
+
+#define RTS5264_REG_PME_FORCE_CTL	0xFF78
+#define FORCE_PM_CONTROL		0x20
+#define FORCE_PM_VALUE			0x10
+#define REG_EFUSE_BYPASS		0x08
+#define REG_EFUSE_POR			0x04
+#define REG_EFUSE_POWER_MASK		0x03
+#define REG_EFUSE_POWERON		0x03
+#define REG_EFUSE_POWEROFF		0x00
+
+#define RTS5264_PWR_CUT			0xFF81
+#define RTS5264_CFG_MEM_PD		0xF0
+
+#define RTS5264_OVP_DET			0xFF8A
+#define RTS5264_POW_VDET		0x04
+#define RTS5264_TUNE_VROV_MASK		0x03
+#define RTS5264_TUNE_VROV_2V		0x03
+#define RTS5264_TUNE_VROV_1V8		0x02
+#define RTS5264_TUNE_VROV_1V6		0x01
+#define RTS5264_TUNE_VROV_1V4		0x00
+
+#define RTS5264_CKMUX_MBIAS_PWR		0xFF8B
+#define RTS5264_NON_XTAL_SEL		0x80
+#define RTS5264_POW_CKMUX		0x40
+#define RTS5264_LVD_MASK		0x04
+#define RTS5264_POW_PSW_MASK		0x03
+#define RTS5264_POW_PSW_DFT		0x03
+
+/* Single LUN, support SD/SD EXPRESS */
+#define DEFAULT_SINGLE		0
+#define SD_LUN			1
+#define SD_EXPRESS_LUN		2
+
+int rts5264_pci_switch_clock(struct rtsx_pcr *pcr, unsigned int card_clock,
+		u8 ssc_depth, bool initial_mode, bool double_clk, bool vpclk);
+
+#endif /* RTS5264_H */
diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h
index 534038d962e4..4612ef09a0c7 100644
--- a/include/linux/rtsx_pci.h
+++ b/include/linux/rtsx_pci.h
@@ -60,6 +60,7 @@
 #define   SD_EXIST			(1 << 16)
 #define   DELINK_INT			GPIO0_INT
 #define   MS_OC_INT			(1 << 23)
+#define   SD_OVP_INT		(1 << 23)
 #define   SD_OC_INT			(1 << 22)
 
 #define CARD_INT		(XD_INT | MS_INT | SD_INT)
@@ -80,6 +81,7 @@
 #define   OC_INT_EN			(1 << 23)
 #define   DELINK_INT_EN			GPIO0_INT_EN
 #define   MS_OC_INT_EN			(1 << 23)
+#define   SD_OVP_INT_EN			(1 << 23)
 #define   SD_OC_INT_EN			(1 << 22)
 
 #define RTSX_DUM_REG			0x1C
@@ -583,6 +585,7 @@
 #define   OBFF_DISABLE			0x00
 
 #define CDRESUMECTL			0xFE52
+#define CDGW				0xFE53
 #define WAKE_SEL_CTL			0xFE54
 #define PCLK_CTL			0xFE55
 #define   PCLK_MODE_SEL			0x20
@@ -764,6 +767,9 @@
 #define   SD_VIO_LDO_1V8		0x40
 #define   SD_VIO_LDO_3V3		0x70
 
+#define RTS5264_AUTOLOAD_CFG2		0xFF7D
+#define RTS5264_CHIP_RST_N_SEL		(1 << 6)
+
 #define RTS5260_AUTOLOAD_CFG4		0xFF7F
 #define   RTS5260_MIMO_DISABLE		0x8A
 /*RTS5261*/
@@ -1261,6 +1267,7 @@ struct rtsx_pcr {
 	u8				dma_error_count;
 	u8			ocp_stat;
 	u8			ocp_stat2;
+	u8			ovp_stat;
 	u8			rtd3_en;
 };
 
@@ -1271,6 +1278,7 @@ struct rtsx_pcr {
 #define PID_5260	0x5260
 #define PID_5261	0x5261
 #define PID_5228	0x5228
+#define PID_5264	0x5264
 
 #define CHK_PCI_PID(pcr, pid)		((pcr)->pci->device == (pid))
 #define PCI_VID(pcr)			((pcr)->pci->vendor)
-- 
cgit v1.2.3


From b6e53731e07db7e8d35b789fd83565fe75540180 Mon Sep 17 00:00:00 2001
From: Fei Shao <fshao@chromium.org>
Date: Wed, 6 Dec 2023 15:17:26 -0800
Subject: spmi: Introduce device-managed functions

Utilize the managed resource (devres) framework and add the following
devm_* helpers for the SPMI driver:

- devm_spmi_controller_alloc()
- devm_spmi_controller_add()

[sboyd@kernel.org: Rename to spmi-devres for module niceness, slap on
GPL module license]

Signed-off-by: Fei Shao <fshao@chromium.org>
Link: https://lore.kernel.org/r/20230824104101.4083400-2-fshao@chromium.org
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
Link: https://lore.kernel.org/r/20231206231733.4031901-4-sboyd@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/spmi/Makefile      |  2 +-
 drivers/spmi/spmi-devres.c | 64 ++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/spmi.h       |  3 +++
 3 files changed, 68 insertions(+), 1 deletion(-)
 create mode 100644 drivers/spmi/spmi-devres.c

(limited to 'include')

diff --git a/drivers/spmi/Makefile b/drivers/spmi/Makefile
index 9d974424c8c1..7f152167bb05 100644
--- a/drivers/spmi/Makefile
+++ b/drivers/spmi/Makefile
@@ -2,7 +2,7 @@
 #
 # Makefile for kernel SPMI framework.
 #
-obj-$(CONFIG_SPMI)	+= spmi.o
+obj-$(CONFIG_SPMI)	+= spmi.o spmi-devres.o
 
 obj-$(CONFIG_SPMI_HISI3670)	+= hisi-spmi-controller.o
 obj-$(CONFIG_SPMI_MSM_PMIC_ARB)	+= spmi-pmic-arb.o
diff --git a/drivers/spmi/spmi-devres.c b/drivers/spmi/spmi-devres.c
new file mode 100644
index 000000000000..7683e6fdb18f
--- /dev/null
+++ b/drivers/spmi/spmi-devres.c
@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2023 Google LLC.
+ */
+
+#include <linux/device.h>
+#include <linux/spmi.h>
+
+static void devm_spmi_controller_release(struct device *parent, void *res)
+{
+	spmi_controller_put(*(struct spmi_controller **)res);
+}
+
+struct spmi_controller *devm_spmi_controller_alloc(struct device *parent, size_t size)
+{
+	struct spmi_controller **ptr, *ctrl;
+
+	ptr = devres_alloc(devm_spmi_controller_release, sizeof(*ptr), GFP_KERNEL);
+	if (!ptr)
+		return ERR_PTR(-ENOMEM);
+
+	ctrl = spmi_controller_alloc(parent, size);
+	if (!ctrl) {
+		devres_free(ptr);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	*ptr = ctrl;
+	devres_add(parent, ptr);
+
+	return ctrl;
+}
+EXPORT_SYMBOL_GPL(devm_spmi_controller_alloc);
+
+static void devm_spmi_controller_remove(struct device *parent, void *res)
+{
+	spmi_controller_remove(*(struct spmi_controller **)res);
+}
+
+int devm_spmi_controller_add(struct device *parent, struct spmi_controller *ctrl)
+{
+	struct spmi_controller **ptr;
+	int ret;
+
+	ptr = devres_alloc(devm_spmi_controller_remove, sizeof(*ptr), GFP_KERNEL);
+	if (!ptr)
+		return -ENOMEM;
+
+	ret = spmi_controller_add(ctrl);
+	if (ret) {
+		devres_free(ptr);
+		return ret;
+	}
+
+	*ptr = ctrl;
+	devres_add(parent, ptr);
+
+	return 0;
+
+}
+EXPORT_SYMBOL_GPL(devm_spmi_controller_add);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SPMI devres helpers");
diff --git a/include/linux/spmi.h b/include/linux/spmi.h
index 2a4ce4144f9f..28e8c8bd3944 100644
--- a/include/linux/spmi.h
+++ b/include/linux/spmi.h
@@ -120,6 +120,9 @@ static inline void spmi_controller_put(struct spmi_controller *ctrl)
 int spmi_controller_add(struct spmi_controller *ctrl);
 void spmi_controller_remove(struct spmi_controller *ctrl);
 
+struct spmi_controller *devm_spmi_controller_alloc(struct device *parent, size_t size);
+int devm_spmi_controller_add(struct device *parent, struct spmi_controller *ctrl);
+
 /**
  * struct spmi_driver - SPMI slave device driver
  * @driver:	SPMI device drivers should initialize name and owner field of
-- 
cgit v1.2.3


From 8d6608e4f89a0a21caadcf32fb5ed700e2f5682d Mon Sep 17 00:00:00 2001
From: Michal Simek <michal.simek@amd.com>
Date: Thu, 14 Dec 2023 15:53:47 +0100
Subject: firmware: xilinx: Remove clock_setrate and clock_getrate api

As per the current code base, PM_CLOCK_SETRATE and PM_CLOCK_GETRATE
APIs are not supported for the runtime operations. In the case of
ZynqMP returning an error from TF-A when there is any request to
access these APIs and for Versal also it is returning an error like
NO_ACCESS from the firmware. So, just removing the unused code to
avoid the confusion around these APIs.

Also, there is no issue with the backward compatibility as these APIs
were never used since implemented. Hence no need to bump up the
version of the feature check API as well.

Signed-off-by: Ronak Jain <ronak.jain@amd.com>
Signed-off-by: Michal Simek <michal.simek@amd.com>
Link: https://lore.kernel.org/r/6ccbffbafd1f0f48f6574d5a3bf2db6a5603fdb0.1702565618.git.michal.simek@amd.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/xilinx/zynqmp.c     | 38 ------------------------------------
 include/linux/firmware/xlnx-zynqmp.h | 14 -------------
 2 files changed, 52 deletions(-)

(limited to 'include')

diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c
index caa0952bfc42..2ae9da268215 100644
--- a/drivers/firmware/xilinx/zynqmp.c
+++ b/drivers/firmware/xilinx/zynqmp.c
@@ -657,44 +657,6 @@ int zynqmp_pm_clock_getdivider(u32 clock_id, u32 *divider)
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_clock_getdivider);
 
-/**
- * zynqmp_pm_clock_setrate() - Set the clock rate for given id
- * @clock_id:	ID of the clock
- * @rate:	rate value in hz
- *
- * This function is used by master to set rate for any clock.
- *
- * Return: Returns status, either success or error+reason
- */
-int zynqmp_pm_clock_setrate(u32 clock_id, u64 rate)
-{
-	return zynqmp_pm_invoke_fn(PM_CLOCK_SETRATE, NULL, 3, clock_id, lower_32_bits(rate),
-				   upper_32_bits(rate));
-}
-EXPORT_SYMBOL_GPL(zynqmp_pm_clock_setrate);
-
-/**
- * zynqmp_pm_clock_getrate() - Get the clock rate for given id
- * @clock_id:	ID of the clock
- * @rate:	rate value in hz
- *
- * This function is used by master to get rate
- * for any clock.
- *
- * Return: Returns status, either success or error+reason
- */
-int zynqmp_pm_clock_getrate(u32 clock_id, u64 *rate)
-{
-	u32 ret_payload[PAYLOAD_ARG_CNT];
-	int ret;
-
-	ret = zynqmp_pm_invoke_fn(PM_CLOCK_GETRATE, ret_payload, 1, clock_id);
-	*rate = ((u64)ret_payload[2] << 32) | ret_payload[1];
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(zynqmp_pm_clock_getrate);
-
 /**
  * zynqmp_pm_clock_setparent() - Set the clock parent for given id
  * @clock_id:	ID of the clock
diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h
index 6b48294f3c92..c6a7fb1f980b 100644
--- a/include/linux/firmware/xlnx-zynqmp.h
+++ b/include/linux/firmware/xlnx-zynqmp.h
@@ -160,8 +160,6 @@ enum pm_api_id {
 	PM_CLOCK_GETSTATE = 38,
 	PM_CLOCK_SETDIVIDER = 39,
 	PM_CLOCK_GETDIVIDER = 40,
-	PM_CLOCK_SETRATE = 41,
-	PM_CLOCK_GETRATE = 42,
 	PM_CLOCK_SETPARENT = 43,
 	PM_CLOCK_GETPARENT = 44,
 	PM_FPGA_READ = 46,
@@ -533,8 +531,6 @@ int zynqmp_pm_clock_disable(u32 clock_id);
 int zynqmp_pm_clock_getstate(u32 clock_id, u32 *state);
 int zynqmp_pm_clock_setdivider(u32 clock_id, u32 divider);
 int zynqmp_pm_clock_getdivider(u32 clock_id, u32 *divider);
-int zynqmp_pm_clock_setrate(u32 clock_id, u64 rate);
-int zynqmp_pm_clock_getrate(u32 clock_id, u64 *rate);
 int zynqmp_pm_clock_setparent(u32 clock_id, u32 parent_id);
 int zynqmp_pm_clock_getparent(u32 clock_id, u32 *parent_id);
 int zynqmp_pm_set_pll_frac_mode(u32 clk_id, u32 mode);
@@ -639,16 +635,6 @@ static inline int zynqmp_pm_clock_getdivider(u32 clock_id, u32 *divider)
 	return -ENODEV;
 }
 
-static inline int zynqmp_pm_clock_setrate(u32 clock_id, u64 rate)
-{
-	return -ENODEV;
-}
-
-static inline int zynqmp_pm_clock_getrate(u32 clock_id, u64 *rate)
-{
-	return -ENODEV;
-}
-
 static inline int zynqmp_pm_clock_setparent(u32 clock_id, u32 parent_id)
 {
 	return -ENODEV;
-- 
cgit v1.2.3


From b9ae996210163e89a2a9aece7c582fb43694485a Mon Sep 17 00:00:00 2001
From: Michal Simek <michal.simek@amd.com>
Date: Thu, 14 Dec 2023 15:53:48 +0100
Subject: firmware: xilinx: Remove zynqmp_pm_pinctrl_get_function()

There is no user for this interface that's why remove it.

Signed-off-by: Michal Simek <michal.simek@amd.com>
Link: https://lore.kernel.org/r/e52a415a004e28a43e6d08e9e22d9e8fef3737df.1702565618.git.michal.simek@amd.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/xilinx/zynqmp.c     | 24 ------------------------
 include/linux/firmware/xlnx-zynqmp.h |  7 -------
 2 files changed, 31 deletions(-)

(limited to 'include')

diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c
index 2ae9da268215..a55dfd9bae6b 100644
--- a/drivers/firmware/xilinx/zynqmp.c
+++ b/drivers/firmware/xilinx/zynqmp.c
@@ -1060,30 +1060,6 @@ int zynqmp_pm_pinctrl_release(const u32 pin)
 }
 EXPORT_SYMBOL_GPL(zynqmp_pm_pinctrl_release);
 
-/**
- * zynqmp_pm_pinctrl_get_function - Read function id set for the given pin
- * @pin: Pin number
- * @id: Buffer to store function ID
- *
- * This function provides the function currently set for the given pin.
- *
- * Return: Returns status, either success or error+reason
- */
-int zynqmp_pm_pinctrl_get_function(const u32 pin, u32 *id)
-{
-	u32 ret_payload[PAYLOAD_ARG_CNT];
-	int ret;
-
-	if (!id)
-		return -EINVAL;
-
-	ret = zynqmp_pm_invoke_fn(PM_PINCTRL_GET_FUNCTION, ret_payload, 1, pin);
-	*id = ret_payload[1];
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(zynqmp_pm_pinctrl_get_function);
-
 /**
  * zynqmp_pm_pinctrl_set_function - Set requested function for the pin
  * @pin: Pin number
diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h
index c6a7fb1f980b..1478f691cc10 100644
--- a/include/linux/firmware/xlnx-zynqmp.h
+++ b/include/linux/firmware/xlnx-zynqmp.h
@@ -149,7 +149,6 @@ enum pm_api_id {
 	PM_SECURE_SHA = 26,
 	PM_PINCTRL_REQUEST = 28,
 	PM_PINCTRL_RELEASE = 29,
-	PM_PINCTRL_GET_FUNCTION = 30,
 	PM_PINCTRL_SET_FUNCTION = 31,
 	PM_PINCTRL_CONFIG_PARAM_GET = 32,
 	PM_PINCTRL_CONFIG_PARAM_SET = 33,
@@ -567,7 +566,6 @@ int zynqmp_pm_system_shutdown(const u32 type, const u32 subtype);
 int zynqmp_pm_set_boot_health_status(u32 value);
 int zynqmp_pm_pinctrl_request(const u32 pin);
 int zynqmp_pm_pinctrl_release(const u32 pin);
-int zynqmp_pm_pinctrl_get_function(const u32 pin, u32 *id);
 int zynqmp_pm_pinctrl_set_function(const u32 pin, const u32 id);
 int zynqmp_pm_pinctrl_get_config(const u32 pin, const u32 param,
 				 u32 *value);
@@ -804,11 +802,6 @@ static inline int zynqmp_pm_pinctrl_release(const u32 pin)
 	return -ENODEV;
 }
 
-static inline int zynqmp_pm_pinctrl_get_function(const u32 pin, u32 *id)
-{
-	return -ENODEV;
-}
-
 static inline int zynqmp_pm_is_function_supported(const u32 api_id, const u32 id)
 {
 	return -ENODEV;
-- 
cgit v1.2.3


From 50efc63d1a7a7b9a6ed21adae1b9a7123ec8abc0 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Fri, 8 Dec 2023 17:22:29 -0500
Subject: Bluetooth: hci_core: Fix hci_conn_hash_lookup_cis

hci_conn_hash_lookup_cis shall always match the requested CIG and CIS
ids even when they are unset as otherwise it result in not being able
to bind/connect different sockets to the same address as that would
result in having multiple sockets mapping to the same hci_conn which
doesn't really work and prevents BAP audio configuration such as
AC 6(i) when CIG and CIS are left unset.

Fixes: c14516faede3 ("Bluetooth: hci_conn: Fix not matching by CIS ID")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci_core.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 20988623c5cc..fb5e3ef3ec2f 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1227,11 +1227,11 @@ static inline struct hci_conn *hci_conn_hash_lookup_cis(struct hci_dev *hdev,
 			continue;
 
 		/* Match CIG ID if set */
-		if (cig != BT_ISO_QOS_CIG_UNSET && cig != c->iso_qos.ucast.cig)
+		if (cig != c->iso_qos.ucast.cig)
 			continue;
 
 		/* Match CIS ID if set */
-		if (id != BT_ISO_QOS_CIS_UNSET && id != c->iso_qos.ucast.cis)
+		if (id != c->iso_qos.ucast.cis)
 			continue;
 
 		/* Match destination address if set */
-- 
cgit v1.2.3


From 59b047bc98084f8af2c41483e4d68a5adf2fa7f7 Mon Sep 17 00:00:00 2001
From: Xiao Yao <xiaoyao@rock-chips.com>
Date: Tue, 12 Dec 2023 00:27:18 +0800
Subject: Bluetooth: MGMT/SMP: Fix address type when using SMP over BREDR/LE

If two Bluetooth devices both support BR/EDR and BLE, and also
support Secure Connections, then they only need to pair once.
The LTK generated during the LE pairing process may be converted
into a BR/EDR link key for BR/EDR transport, and conversely, a
link key generated during the BR/EDR SSP pairing process can be
converted into an LTK for LE transport. Hence, the link type of
the link key and LTK is not fixed, they can be either an LE LINK
or an ACL LINK.

Currently, in the mgmt_new_irk/ltk/crsk/link_key functions, the
link type is fixed, which could lead to incorrect address types
being reported to the application layer. Therefore, it is necessary
to add link_type/addr_type to the smp_irk/ltk/crsk and link_key,
to ensure the generation of the correct address type.

SMP over BREDR:
Before Fix:
> ACL Data RX: Handle 11 flags 0x02 dlen 12
        BR/EDR SMP: Identity Address Information (0x09) len 7
        Address: F8:7D:76:F2:12:F3 (OUI F8-7D-76)
@ MGMT Event: New Identity Resolving Key (0x0018) plen 30
        Random address: 00:00:00:00:00:00 (Non-Resolvable)
        LE Address: F8:7D:76:F2:12:F3 (OUI F8-7D-76)
@ MGMT Event: New Long Term Key (0x000a) plen 37
        LE Address: F8:7D:76:F2:12:F3 (OUI F8-7D-76)
        Key type: Authenticated key from P-256 (0x03)

After Fix:
> ACL Data RX: Handle 11 flags 0x02 dlen 12
      BR/EDR SMP: Identity Address Information (0x09) len 7
        Address: F8:7D:76:F2:12:F3 (OUI F8-7D-76)
@ MGMT Event: New Identity Resolving Key (0x0018) plen 30
        Random address: 00:00:00:00:00:00 (Non-Resolvable)
        BR/EDR Address: F8:7D:76:F2:12:F3 (OUI F8-7D-76)
@ MGMT Event: New Long Term Key (0x000a) plen 37
        BR/EDR Address: F8:7D:76:F2:12:F3 (OUI F8-7D-76)
        Key type: Authenticated key from P-256 (0x03)

SMP over LE:
Before Fix:
@ MGMT Event: New Identity Resolving Key (0x0018) plen 30
        Random address: 5F:5C:07:37:47:D5 (Resolvable)
        LE Address: F8:7D:76:F2:12:F3 (OUI F8-7D-76)
@ MGMT Event: New Long Term Key (0x000a) plen 37
        LE Address: F8:7D:76:F2:12:F3 (OUI F8-7D-76)
        Key type: Authenticated key from P-256 (0x03)
@ MGMT Event: New Link Key (0x0009) plen 26
        BR/EDR Address: F8:7D:76:F2:12:F3 (OUI F8-7D-76)
        Key type: Authenticated Combination key from P-256 (0x08)

After Fix:
@ MGMT Event: New Identity Resolving Key (0x0018) plen 30
        Random address: 5E:03:1C:00:38:21 (Resolvable)
        LE Address: F8:7D:76:F2:12:F3 (OUI F8-7D-76)
@ MGMT Event: New Long Term Key (0x000a) plen 37
        LE Address: F8:7D:76:F2:12:F3 (OUI F8-7D-76)
        Key type: Authenticated key from P-256 (0x03)
@ MGMT Event: New Link Key (0x0009) plen 26
        Store hint: Yes (0x01)
        LE Address: F8:7D:76:F2:12:F3 (OUI F8-7D-76)
        Key type: Authenticated Combination key from P-256 (0x08)

Cc: stable@vger.kernel.org
Signed-off-by: Xiao Yao <xiaoyao@rock-chips.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci_core.h |  5 +++++
 net/bluetooth/mgmt.c             | 25 ++++++++++++++++++-------
 net/bluetooth/smp.c              |  7 +++++++
 3 files changed, 30 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index fb5e3ef3ec2f..a3a1ea2696a8 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -189,6 +189,7 @@ struct blocked_key {
 struct smp_csrk {
 	bdaddr_t bdaddr;
 	u8 bdaddr_type;
+	u8 link_type;
 	u8 type;
 	u8 val[16];
 };
@@ -198,6 +199,7 @@ struct smp_ltk {
 	struct rcu_head rcu;
 	bdaddr_t bdaddr;
 	u8 bdaddr_type;
+	u8 link_type;
 	u8 authenticated;
 	u8 type;
 	u8 enc_size;
@@ -212,6 +214,7 @@ struct smp_irk {
 	bdaddr_t rpa;
 	bdaddr_t bdaddr;
 	u8 addr_type;
+	u8 link_type;
 	u8 val[16];
 };
 
@@ -219,6 +222,8 @@ struct link_key {
 	struct list_head list;
 	struct rcu_head rcu;
 	bdaddr_t bdaddr;
+	u8 bdaddr_type;
+	u8 link_type;
 	u8 type;
 	u8 val[HCI_LINK_KEY_SIZE];
 	u8 pin_len;
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index ba2e00646e8e..9dd815b6603f 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -2897,7 +2897,8 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data,
 	for (i = 0; i < key_count; i++) {
 		struct mgmt_link_key_info *key = &cp->keys[i];
 
-		if (key->addr.type != BDADDR_BREDR || key->type > 0x08)
+		/* Considering SMP over BREDR/LE, there is no need to check addr_type */
+		if (key->type > 0x08)
 			return mgmt_cmd_status(sk, hdev->id,
 					       MGMT_OP_LOAD_LINK_KEYS,
 					       MGMT_STATUS_INVALID_PARAMS);
@@ -7130,6 +7131,7 @@ static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data,
 
 	for (i = 0; i < irk_count; i++) {
 		struct mgmt_irk_info *irk = &cp->irks[i];
+		u8 addr_type = le_addr_type(irk->addr.type);
 
 		if (hci_is_blocked_key(hdev,
 				       HCI_BLOCKED_KEY_TYPE_IRK,
@@ -7139,8 +7141,12 @@ static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data,
 			continue;
 		}
 
+		/* When using SMP over BR/EDR, the addr type should be set to BREDR */
+		if (irk->addr.type == BDADDR_BREDR)
+			addr_type = BDADDR_BREDR;
+
 		hci_add_irk(hdev, &irk->addr.bdaddr,
-			    le_addr_type(irk->addr.type), irk->val,
+			    addr_type, irk->val,
 			    BDADDR_ANY);
 	}
 
@@ -7221,6 +7227,7 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev,
 	for (i = 0; i < key_count; i++) {
 		struct mgmt_ltk_info *key = &cp->keys[i];
 		u8 type, authenticated;
+		u8 addr_type = le_addr_type(key->addr.type);
 
 		if (hci_is_blocked_key(hdev,
 				       HCI_BLOCKED_KEY_TYPE_LTK,
@@ -7255,8 +7262,12 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev,
 			continue;
 		}
 
+		/* When using SMP over BR/EDR, the addr type should be set to BREDR */
+		if (key->addr.type == BDADDR_BREDR)
+			addr_type = BDADDR_BREDR;
+
 		hci_add_ltk(hdev, &key->addr.bdaddr,
-			    le_addr_type(key->addr.type), type, authenticated,
+			    addr_type, type, authenticated,
 			    key->val, key->enc_size, key->ediv, key->rand);
 	}
 
@@ -9523,7 +9534,7 @@ void mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key,
 
 	ev.store_hint = persistent;
 	bacpy(&ev.key.addr.bdaddr, &key->bdaddr);
-	ev.key.addr.type = BDADDR_BREDR;
+	ev.key.addr.type = link_to_bdaddr(key->link_type, key->bdaddr_type);
 	ev.key.type = key->type;
 	memcpy(ev.key.val, key->val, HCI_LINK_KEY_SIZE);
 	ev.key.pin_len = key->pin_len;
@@ -9574,7 +9585,7 @@ void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, bool persistent)
 		ev.store_hint = persistent;
 
 	bacpy(&ev.key.addr.bdaddr, &key->bdaddr);
-	ev.key.addr.type = link_to_bdaddr(LE_LINK, key->bdaddr_type);
+	ev.key.addr.type = link_to_bdaddr(key->link_type, key->bdaddr_type);
 	ev.key.type = mgmt_ltk_type(key);
 	ev.key.enc_size = key->enc_size;
 	ev.key.ediv = key->ediv;
@@ -9603,7 +9614,7 @@ void mgmt_new_irk(struct hci_dev *hdev, struct smp_irk *irk, bool persistent)
 
 	bacpy(&ev.rpa, &irk->rpa);
 	bacpy(&ev.irk.addr.bdaddr, &irk->bdaddr);
-	ev.irk.addr.type = link_to_bdaddr(LE_LINK, irk->addr_type);
+	ev.irk.addr.type = link_to_bdaddr(irk->link_type, irk->addr_type);
 	memcpy(ev.irk.val, irk->val, sizeof(irk->val));
 
 	mgmt_event(MGMT_EV_NEW_IRK, hdev, &ev, sizeof(ev), NULL);
@@ -9632,7 +9643,7 @@ void mgmt_new_csrk(struct hci_dev *hdev, struct smp_csrk *csrk,
 		ev.store_hint = persistent;
 
 	bacpy(&ev.key.addr.bdaddr, &csrk->bdaddr);
-	ev.key.addr.type = link_to_bdaddr(LE_LINK, csrk->bdaddr_type);
+	ev.key.addr.type = link_to_bdaddr(csrk->link_type, csrk->bdaddr_type);
 	ev.key.type = csrk->type;
 	memcpy(ev.key.val, csrk->val, sizeof(csrk->val));
 
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 5f2f97de295e..1e7ea3a4b7ef 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -1059,6 +1059,7 @@ static void smp_notify_keys(struct l2cap_conn *conn)
 	}
 
 	if (smp->remote_irk) {
+		smp->remote_irk->link_type = hcon->type;
 		mgmt_new_irk(hdev, smp->remote_irk, persistent);
 
 		/* Now that user space can be considered to know the
@@ -1078,24 +1079,28 @@ static void smp_notify_keys(struct l2cap_conn *conn)
 	}
 
 	if (smp->csrk) {
+		smp->csrk->link_type = hcon->type;
 		smp->csrk->bdaddr_type = hcon->dst_type;
 		bacpy(&smp->csrk->bdaddr, &hcon->dst);
 		mgmt_new_csrk(hdev, smp->csrk, persistent);
 	}
 
 	if (smp->responder_csrk) {
+		smp->responder_csrk->link_type = hcon->type;
 		smp->responder_csrk->bdaddr_type = hcon->dst_type;
 		bacpy(&smp->responder_csrk->bdaddr, &hcon->dst);
 		mgmt_new_csrk(hdev, smp->responder_csrk, persistent);
 	}
 
 	if (smp->ltk) {
+		smp->ltk->link_type = hcon->type;
 		smp->ltk->bdaddr_type = hcon->dst_type;
 		bacpy(&smp->ltk->bdaddr, &hcon->dst);
 		mgmt_new_ltk(hdev, smp->ltk, persistent);
 	}
 
 	if (smp->responder_ltk) {
+		smp->responder_ltk->link_type = hcon->type;
 		smp->responder_ltk->bdaddr_type = hcon->dst_type;
 		bacpy(&smp->responder_ltk->bdaddr, &hcon->dst);
 		mgmt_new_ltk(hdev, smp->responder_ltk, persistent);
@@ -1115,6 +1120,8 @@ static void smp_notify_keys(struct l2cap_conn *conn)
 		key = hci_add_link_key(hdev, smp->conn->hcon, &hcon->dst,
 				       smp->link_key, type, 0, &persistent);
 		if (key) {
+			key->link_type = hcon->type;
+			key->bdaddr_type = hcon->dst_type;
 			mgmt_new_link_key(hdev, key, persistent);
 
 			/* Don't keep debug keys around if the relevant
-- 
cgit v1.2.3


From 7dc66abb5a47778d7db327783a0ba172b8cff0b5 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Tue, 21 Nov 2023 13:38:38 +0000
Subject: btrfs: use a dedicated data structure for chunk maps

Currently we abuse the extent_map structure for two purposes:

1) To actually represent extents for inodes;
2) To represent chunk mappings.

This is odd and has several disadvantages:

1) To create a chunk map, we need to do two memory allocations: one for
   an extent_map structure and another one for a map_lookup structure, so
   more potential for an allocation failure and more complicated code to
   manage and link two structures;

2) For a chunk map we actually only use 3 fields (24 bytes) of the
   respective extent map structure: the 'start' field to have the logical
   start address of the chunk, the 'len' field to have the chunk's size,
   and the 'orig_block_len' field to contain the chunk's stripe size.

   Besides wasting a memory, it's also odd and not intuitive at all to
   have the stripe size in a field named 'orig_block_len'.

   We are also using 'block_len' of the extent_map structure to contain
   the chunk size, so we have 2 fields for the same value, 'len' and
   'block_len', which is pointless;

3) When an extent map is associated to a chunk mapping, we set the bit
   EXTENT_FLAG_FS_MAPPING on its flags and then make its member named
   'map_lookup' point to the associated map_lookup structure. This means
   that for an extent map associated to an inode extent, we are not using
   this 'map_lookup' pointer, so wasting 8 bytes (on a 64 bits platform);

4) Extent maps associated to a chunk mapping are never merged or split so
   it's pointless to use the existing extent map infrastructure.

So add a dedicated data structure named 'btrfs_chunk_map' to represent
chunk mappings, this is basically the existing map_lookup structure with
some extra fields:

1) 'start' to contain the chunk logical address;
2) 'chunk_len' to contain the chunk's length;
3) 'stripe_size' for the stripe size;
4) 'rb_node' for insertion into a rb tree;
5) 'refs' for reference counting.

This way we do a single memory allocation for chunk mappings and we don't
waste memory for them with unused/unnecessary fields from an extent_map.

We also save 8 bytes from the extent_map structure by removing the
'map_lookup' pointer, so the size of struct extent_map is reduced from
144 bytes down to 136 bytes, and we can now have 30 extents map per 4K
page instead of 28.

Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/block-group.c            | 165 +++++-------
 fs/btrfs/block-group.h            |   6 +-
 fs/btrfs/dev-replace.c            |  28 +-
 fs/btrfs/disk-io.c                |   7 +-
 fs/btrfs/extent_map.c             |  46 ----
 fs/btrfs/extent_map.h             |   4 -
 fs/btrfs/fs.h                     |   3 +-
 fs/btrfs/inode.c                  |  25 +-
 fs/btrfs/raid56.h                 |   2 +-
 fs/btrfs/scrub.c                  |  39 ++-
 fs/btrfs/tests/btrfs-tests.c      |   3 +-
 fs/btrfs/tests/btrfs-tests.h      |   1 +
 fs/btrfs/tests/extent-map-tests.c |  40 +--
 fs/btrfs/volumes.c                | 540 ++++++++++++++++++++++----------------
 fs/btrfs/volumes.h                |  45 +++-
 fs/btrfs/zoned.c                  |  35 +--
 include/trace/events/btrfs.h      |  11 +-
 17 files changed, 506 insertions(+), 494 deletions(-)

(limited to 'include')

diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index fca653cc977c..0fea258eea15 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -168,7 +168,7 @@ void btrfs_put_block_group(struct btrfs_block_group *cache)
 						  cache);
 
 		kfree(cache->free_space_ctl);
-		kfree(cache->physical_map);
+		btrfs_free_chunk_map(cache->physical_map);
 		kfree(cache);
 	}
 }
@@ -1047,7 +1047,7 @@ static int remove_block_group_item(struct btrfs_trans_handle *trans,
 }
 
 int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
-			     u64 group_start, struct extent_map *em)
+			     struct btrfs_chunk_map *map)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_path *path;
@@ -1059,10 +1059,10 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	int index;
 	int factor;
 	struct btrfs_caching_control *caching_ctl = NULL;
-	bool remove_em;
+	bool remove_map;
 	bool remove_rsv = false;
 
-	block_group = btrfs_lookup_block_group(fs_info, group_start);
+	block_group = btrfs_lookup_block_group(fs_info, map->start);
 	BUG_ON(!block_group);
 	BUG_ON(!block_group->ro);
 
@@ -1252,7 +1252,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	 * entries because we already removed them all when we called
 	 * btrfs_remove_free_space_cache().
 	 *
-	 * And we must not remove the extent map from the fs_info->mapping_tree
+	 * And we must not remove the chunk map from the fs_info->mapping_tree
 	 * to prevent the same logical address range and physical device space
 	 * ranges from being reused for a new block group. This is needed to
 	 * avoid races with trimming and scrub.
@@ -1268,19 +1268,11 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	 * in place until the extents have been discarded completely when
 	 * the transaction commit has completed.
 	 */
-	remove_em = (atomic_read(&block_group->frozen) == 0);
+	remove_map = (atomic_read(&block_group->frozen) == 0);
 	spin_unlock(&block_group->lock);
 
-	if (remove_em) {
-		struct extent_map_tree *em_tree;
-
-		em_tree = &fs_info->mapping_tree;
-		write_lock(&em_tree->lock);
-		remove_extent_mapping(em_tree, em);
-		write_unlock(&em_tree->lock);
-		/* once for the tree */
-		free_extent_map(em);
-	}
+	if (remove_map)
+		btrfs_remove_chunk_map(fs_info, map);
 
 out:
 	/* Once for the lookup reference */
@@ -1295,16 +1287,12 @@ struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
 		struct btrfs_fs_info *fs_info, const u64 chunk_offset)
 {
 	struct btrfs_root *root = btrfs_block_group_root(fs_info);
-	struct extent_map_tree *em_tree = &fs_info->mapping_tree;
-	struct extent_map *em;
-	struct map_lookup *map;
+	struct btrfs_chunk_map *map;
 	unsigned int num_items;
 
-	read_lock(&em_tree->lock);
-	em = lookup_extent_mapping(em_tree, chunk_offset, 1);
-	read_unlock(&em_tree->lock);
-	ASSERT(em != NULL);
-	ASSERT(em->start == chunk_offset);
+	map = btrfs_find_chunk_map(fs_info, chunk_offset, 1);
+	ASSERT(map != NULL);
+	ASSERT(map->start == chunk_offset);
 
 	/*
 	 * We need to reserve 3 + N units from the metadata space info in order
@@ -1325,9 +1313,8 @@ struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
 	 * more device items and remove one chunk item), but this is done at
 	 * btrfs_remove_chunk() through a call to check_system_chunk().
 	 */
-	map = em->map_lookup;
 	num_items = 3 + map->num_stripes;
-	free_extent_map(em);
+	btrfs_free_chunk_map(map);
 
 	return btrfs_start_transaction_fallback_global_rsv(root, num_items);
 }
@@ -1928,8 +1915,7 @@ void btrfs_mark_bg_to_reclaim(struct btrfs_block_group *bg)
 static int read_bg_from_eb(struct btrfs_fs_info *fs_info, struct btrfs_key *key,
 			   struct btrfs_path *path)
 {
-	struct extent_map_tree *em_tree;
-	struct extent_map *em;
+	struct btrfs_chunk_map *map;
 	struct btrfs_block_group_item bg;
 	struct extent_buffer *leaf;
 	int slot;
@@ -1939,23 +1925,20 @@ static int read_bg_from_eb(struct btrfs_fs_info *fs_info, struct btrfs_key *key,
 	slot = path->slots[0];
 	leaf = path->nodes[0];
 
-	em_tree = &fs_info->mapping_tree;
-	read_lock(&em_tree->lock);
-	em = lookup_extent_mapping(em_tree, key->objectid, key->offset);
-	read_unlock(&em_tree->lock);
-	if (!em) {
+	map = btrfs_find_chunk_map(fs_info, key->objectid, key->offset);
+	if (!map) {
 		btrfs_err(fs_info,
 			  "logical %llu len %llu found bg but no related chunk",
 			  key->objectid, key->offset);
 		return -ENOENT;
 	}
 
-	if (em->start != key->objectid || em->len != key->offset) {
+	if (map->start != key->objectid || map->chunk_len != key->offset) {
 		btrfs_err(fs_info,
 			"block group %llu len %llu mismatch with chunk %llu len %llu",
-			key->objectid, key->offset, em->start, em->len);
+			  key->objectid, key->offset, map->start, map->chunk_len);
 		ret = -EUCLEAN;
-		goto out_free_em;
+		goto out_free_map;
 	}
 
 	read_extent_buffer(leaf, &bg, btrfs_item_ptr_offset(leaf, slot),
@@ -1963,16 +1946,16 @@ static int read_bg_from_eb(struct btrfs_fs_info *fs_info, struct btrfs_key *key,
 	flags = btrfs_stack_block_group_flags(&bg) &
 		BTRFS_BLOCK_GROUP_TYPE_MASK;
 
-	if (flags != (em->map_lookup->type & BTRFS_BLOCK_GROUP_TYPE_MASK)) {
+	if (flags != (map->type & BTRFS_BLOCK_GROUP_TYPE_MASK)) {
 		btrfs_err(fs_info,
 "block group %llu len %llu type flags 0x%llx mismatch with chunk type flags 0x%llx",
 			  key->objectid, key->offset, flags,
-			  (BTRFS_BLOCK_GROUP_TYPE_MASK & em->map_lookup->type));
+			  (BTRFS_BLOCK_GROUP_TYPE_MASK & map->type));
 		ret = -EUCLEAN;
 	}
 
-out_free_em:
-	free_extent_map(em);
+out_free_map:
+	btrfs_free_chunk_map(map);
 	return ret;
 }
 
@@ -2025,8 +2008,7 @@ static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
 int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start,
 		     u64 physical, u64 **logical, int *naddrs, int *stripe_len)
 {
-	struct extent_map *em;
-	struct map_lookup *map;
+	struct btrfs_chunk_map *map;
 	u64 *buf;
 	u64 bytenr;
 	u64 data_stripe_length;
@@ -2034,14 +2016,13 @@ int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start,
 	int i, nr = 0;
 	int ret = 0;
 
-	em = btrfs_get_chunk_map(fs_info, chunk_start, 1);
-	if (IS_ERR(em))
+	map = btrfs_get_chunk_map(fs_info, chunk_start, 1);
+	if (IS_ERR(map))
 		return -EIO;
 
-	map = em->map_lookup;
-	data_stripe_length = em->orig_block_len;
+	data_stripe_length = map->stripe_size;
 	io_stripe_size = BTRFS_STRIPE_LEN;
-	chunk_start = em->start;
+	chunk_start = map->start;
 
 	/* For RAID5/6 adjust to a full IO stripe length */
 	if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK)
@@ -2095,7 +2076,7 @@ int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start,
 	*naddrs = nr;
 	*stripe_len = io_stripe_size;
 out:
-	free_extent_map(em);
+	btrfs_free_chunk_map(map);
 	return ret;
 }
 
@@ -2200,49 +2181,47 @@ static struct btrfs_block_group *btrfs_create_block_group_cache(
  */
 static int check_chunk_block_group_mappings(struct btrfs_fs_info *fs_info)
 {
-	struct extent_map_tree *map_tree = &fs_info->mapping_tree;
-	struct extent_map *em;
-	struct btrfs_block_group *bg;
 	u64 start = 0;
 	int ret = 0;
 
 	while (1) {
-		read_lock(&map_tree->lock);
+		struct btrfs_chunk_map *map;
+		struct btrfs_block_group *bg;
+
 		/*
-		 * lookup_extent_mapping will return the first extent map
-		 * intersecting the range, so setting @len to 1 is enough to
+		 * btrfs_find_chunk_map() will return the first chunk map
+		 * intersecting the range, so setting @length to 1 is enough to
 		 * get the first chunk.
 		 */
-		em = lookup_extent_mapping(map_tree, start, 1);
-		read_unlock(&map_tree->lock);
-		if (!em)
+		map = btrfs_find_chunk_map(fs_info, start, 1);
+		if (!map)
 			break;
 
-		bg = btrfs_lookup_block_group(fs_info, em->start);
+		bg = btrfs_lookup_block_group(fs_info, map->start);
 		if (!bg) {
 			btrfs_err(fs_info,
 	"chunk start=%llu len=%llu doesn't have corresponding block group",
-				     em->start, em->len);
+				     map->start, map->chunk_len);
 			ret = -EUCLEAN;
-			free_extent_map(em);
+			btrfs_free_chunk_map(map);
 			break;
 		}
-		if (bg->start != em->start || bg->length != em->len ||
+		if (bg->start != map->start || bg->length != map->chunk_len ||
 		    (bg->flags & BTRFS_BLOCK_GROUP_TYPE_MASK) !=
-		    (em->map_lookup->type & BTRFS_BLOCK_GROUP_TYPE_MASK)) {
+		    (map->type & BTRFS_BLOCK_GROUP_TYPE_MASK)) {
 			btrfs_err(fs_info,
 "chunk start=%llu len=%llu flags=0x%llx doesn't match block group start=%llu len=%llu flags=0x%llx",
-				em->start, em->len,
-				em->map_lookup->type & BTRFS_BLOCK_GROUP_TYPE_MASK,
+				map->start, map->chunk_len,
+				map->type & BTRFS_BLOCK_GROUP_TYPE_MASK,
 				bg->start, bg->length,
 				bg->flags & BTRFS_BLOCK_GROUP_TYPE_MASK);
 			ret = -EUCLEAN;
-			free_extent_map(em);
+			btrfs_free_chunk_map(map);
 			btrfs_put_block_group(bg);
 			break;
 		}
-		start = em->start + em->len;
-		free_extent_map(em);
+		start = map->start + map->chunk_len;
+		btrfs_free_chunk_map(map);
 		btrfs_put_block_group(bg);
 	}
 	return ret;
@@ -2370,28 +2349,25 @@ error:
 
 static int fill_dummy_bgs(struct btrfs_fs_info *fs_info)
 {
-	struct extent_map_tree *em_tree = &fs_info->mapping_tree;
 	struct rb_node *node;
 	int ret = 0;
 
-	for (node = rb_first_cached(&em_tree->map); node; node = rb_next(node)) {
-		struct extent_map *em;
-		struct map_lookup *map;
+	for (node = rb_first_cached(&fs_info->mapping_tree); node; node = rb_next(node)) {
+		struct btrfs_chunk_map *map;
 		struct btrfs_block_group *bg;
 
-		em = rb_entry(node, struct extent_map, rb_node);
-		map = em->map_lookup;
-		bg = btrfs_create_block_group_cache(fs_info, em->start);
+		map = rb_entry(node, struct btrfs_chunk_map, rb_node);
+		bg = btrfs_create_block_group_cache(fs_info, map->start);
 		if (!bg) {
 			ret = -ENOMEM;
 			break;
 		}
 
 		/* Fill dummy cache as FULL */
-		bg->length = em->len;
+		bg->length = map->chunk_len;
 		bg->flags = map->type;
 		bg->cached = BTRFS_CACHE_FINISHED;
-		bg->used = em->len;
+		bg->used = map->chunk_len;
 		bg->flags = map->type;
 		ret = btrfs_add_block_group_cache(fs_info, bg);
 		/*
@@ -2619,19 +2595,17 @@ static int insert_dev_extents(struct btrfs_trans_handle *trans,
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_device *device;
-	struct extent_map *em;
-	struct map_lookup *map;
+	struct btrfs_chunk_map *map;
 	u64 dev_offset;
 	u64 stripe_size;
 	int i;
 	int ret = 0;
 
-	em = btrfs_get_chunk_map(fs_info, chunk_offset, chunk_size);
-	if (IS_ERR(em))
-		return PTR_ERR(em);
+	map = btrfs_get_chunk_map(fs_info, chunk_offset, chunk_size);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
 
-	map = em->map_lookup;
-	stripe_size = em->orig_block_len;
+	stripe_size = map->stripe_size;
 
 	/*
 	 * Take the device list mutex to prevent races with the final phase of
@@ -2654,7 +2628,7 @@ static int insert_dev_extents(struct btrfs_trans_handle *trans,
 	}
 	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
 
-	free_extent_map(em);
+	btrfs_free_chunk_map(map);
 	return ret;
 }
 
@@ -4407,8 +4381,6 @@ void btrfs_freeze_block_group(struct btrfs_block_group *cache)
 void btrfs_unfreeze_block_group(struct btrfs_block_group *block_group)
 {
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
-	struct extent_map_tree *em_tree;
-	struct extent_map *em;
 	bool cleanup;
 
 	spin_lock(&block_group->lock);
@@ -4417,17 +4389,16 @@ void btrfs_unfreeze_block_group(struct btrfs_block_group *block_group)
 	spin_unlock(&block_group->lock);
 
 	if (cleanup) {
-		em_tree = &fs_info->mapping_tree;
-		write_lock(&em_tree->lock);
-		em = lookup_extent_mapping(em_tree, block_group->start,
-					   1);
-		BUG_ON(!em); /* logic error, can't happen */
-		remove_extent_mapping(em_tree, em);
-		write_unlock(&em_tree->lock);
-
-		/* once for us and once for the tree */
-		free_extent_map(em);
-		free_extent_map(em);
+		struct btrfs_chunk_map *map;
+
+		map = btrfs_find_chunk_map(fs_info, block_group->start, 1);
+		/* Logic error, can't happen. */
+		ASSERT(map);
+
+		btrfs_remove_chunk_map(fs_info, map);
+
+		/* Once for our lookup reference. */
+		btrfs_free_chunk_map(map);
 
 		/*
 		 * We may have left one free space entry and other possible
diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h
index 2bdbcb834f95..c4a1f01cc1c2 100644
--- a/fs/btrfs/block-group.h
+++ b/fs/btrfs/block-group.h
@@ -5,6 +5,8 @@
 
 #include "free-space-cache.h"
 
+struct btrfs_chunk_map;
+
 enum btrfs_disk_cache_state {
 	BTRFS_DC_WRITTEN,
 	BTRFS_DC_ERROR,
@@ -243,7 +245,7 @@ struct btrfs_block_group {
 	u64 zone_unusable;
 	u64 zone_capacity;
 	u64 meta_write_pointer;
-	struct map_lookup *physical_map;
+	struct btrfs_chunk_map *physical_map;
 	struct list_head active_bg_list;
 	struct work_struct zone_finish_work;
 	struct extent_buffer *last_eb;
@@ -297,7 +299,7 @@ struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
 				struct btrfs_fs_info *fs_info,
 				const u64 chunk_offset);
 int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
-			     u64 group_start, struct extent_map *em);
+			     struct btrfs_chunk_map *map);
 void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info);
 void btrfs_mark_bg_unused(struct btrfs_block_group *bg);
 void btrfs_reclaim_bgs_work(struct work_struct *work);
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index f9544fda38e9..1502d664c892 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -550,8 +550,7 @@ bool btrfs_finish_block_group_to_copy(struct btrfs_device *srcdev,
 				      u64 physical)
 {
 	struct btrfs_fs_info *fs_info = cache->fs_info;
-	struct extent_map *em;
-	struct map_lookup *map;
+	struct btrfs_chunk_map *map;
 	u64 chunk_offset = cache->start;
 	int num_extents, cur_extent;
 	int i;
@@ -567,9 +566,8 @@ bool btrfs_finish_block_group_to_copy(struct btrfs_device *srcdev,
 	}
 	spin_unlock(&cache->lock);
 
-	em = btrfs_get_chunk_map(fs_info, chunk_offset, 1);
-	ASSERT(!IS_ERR(em));
-	map = em->map_lookup;
+	map = btrfs_get_chunk_map(fs_info, chunk_offset, 1);
+	ASSERT(!IS_ERR(map));
 
 	num_extents = 0;
 	cur_extent = 0;
@@ -583,7 +581,7 @@ bool btrfs_finish_block_group_to_copy(struct btrfs_device *srcdev,
 			cur_extent = i;
 	}
 
-	free_extent_map(em);
+	btrfs_free_chunk_map(map);
 
 	if (num_extents > 1 && cur_extent < num_extents - 1) {
 		/*
@@ -812,25 +810,23 @@ static void btrfs_dev_replace_update_device_in_mapping_tree(
 						struct btrfs_device *srcdev,
 						struct btrfs_device *tgtdev)
 {
-	struct extent_map_tree *em_tree = &fs_info->mapping_tree;
-	struct extent_map *em;
-	struct map_lookup *map;
 	u64 start = 0;
 	int i;
 
-	write_lock(&em_tree->lock);
+	write_lock(&fs_info->mapping_tree_lock);
 	do {
-		em = lookup_extent_mapping(em_tree, start, (u64)-1);
-		if (!em)
+		struct btrfs_chunk_map *map;
+
+		map = btrfs_find_chunk_map_nolock(fs_info, start, U64_MAX);
+		if (!map)
 			break;
-		map = em->map_lookup;
 		for (i = 0; i < map->num_stripes; i++)
 			if (srcdev == map->stripes[i].dev)
 				map->stripes[i].dev = tgtdev;
-		start = em->start + em->len;
-		free_extent_map(em);
+		start = map->start + map->chunk_len;
+		btrfs_free_chunk_map(map);
 	} while (start);
-	write_unlock(&em_tree->lock);
+	write_unlock(&fs_info->mapping_tree_lock);
 }
 
 static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 7d8d175d5a59..17ec983ea672 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2720,7 +2720,8 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
 	INIT_LIST_HEAD(&fs_info->allocated_ebs);
 	spin_lock_init(&fs_info->eb_leak_lock);
 #endif
-	extent_map_tree_init(&fs_info->mapping_tree);
+	fs_info->mapping_tree = RB_ROOT_CACHED;
+	rwlock_init(&fs_info->mapping_tree_lock);
 	btrfs_init_block_rsv(&fs_info->global_block_rsv,
 			     BTRFS_BLOCK_RSV_GLOBAL);
 	btrfs_init_block_rsv(&fs_info->trans_block_rsv, BTRFS_BLOCK_RSV_TRANS);
@@ -3604,7 +3605,7 @@ fail_sb_buffer:
 	btrfs_stop_all_workers(fs_info);
 	btrfs_free_block_groups(fs_info);
 fail_alloc:
-	btrfs_mapping_tree_free(&fs_info->mapping_tree);
+	btrfs_mapping_tree_free(fs_info);
 
 	iput(fs_info->btree_inode);
 fail:
@@ -4387,7 +4388,7 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info)
 
 	iput(fs_info->btree_inode);
 
-	btrfs_mapping_tree_free(&fs_info->mapping_tree);
+	btrfs_mapping_tree_free(fs_info);
 	btrfs_close_devices(fs_info->fs_devices);
 }
 
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index bced39dc0da8..c956b1ced69f 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -67,8 +67,6 @@ void free_extent_map(struct extent_map *em)
 	if (refcount_dec_and_test(&em->refs)) {
 		WARN_ON(extent_map_in_tree(em));
 		WARN_ON(!list_empty(&em->list));
-		if (test_bit(EXTENT_FLAG_FS_MAPPING, &em->flags))
-			kfree(em->map_lookup);
 		kmem_cache_free(extent_map_cache, em);
 	}
 }
@@ -217,13 +215,8 @@ static int mergable_maps(struct extent_map *prev, struct extent_map *next)
 	ASSERT(next->block_start != EXTENT_MAP_DELALLOC &&
 	       prev->block_start != EXTENT_MAP_DELALLOC);
 
-	if (prev->map_lookup || next->map_lookup)
-		ASSERT(test_bit(EXTENT_FLAG_FS_MAPPING, &prev->flags) &&
-		       test_bit(EXTENT_FLAG_FS_MAPPING, &next->flags));
-
 	if (extent_map_end(prev) == next->start &&
 	    prev->flags == next->flags &&
-	    prev->map_lookup == next->map_lookup &&
 	    ((next->block_start == EXTENT_MAP_HOLE &&
 	      prev->block_start == EXTENT_MAP_HOLE) ||
 	     (next->block_start == EXTENT_MAP_INLINE &&
@@ -361,39 +354,6 @@ static inline void setup_extent_mapping(struct extent_map_tree *tree,
 		try_merge_map(tree, em);
 }
 
-static void extent_map_device_set_bits(struct extent_map *em, unsigned bits)
-{
-	struct map_lookup *map = em->map_lookup;
-	u64 stripe_size = em->orig_block_len;
-	int i;
-
-	for (i = 0; i < map->num_stripes; i++) {
-		struct btrfs_io_stripe *stripe = &map->stripes[i];
-		struct btrfs_device *device = stripe->dev;
-
-		set_extent_bit(&device->alloc_state, stripe->physical,
-			       stripe->physical + stripe_size - 1,
-			       bits | EXTENT_NOWAIT, NULL);
-	}
-}
-
-static void extent_map_device_clear_bits(struct extent_map *em, unsigned bits)
-{
-	struct map_lookup *map = em->map_lookup;
-	u64 stripe_size = em->orig_block_len;
-	int i;
-
-	for (i = 0; i < map->num_stripes; i++) {
-		struct btrfs_io_stripe *stripe = &map->stripes[i];
-		struct btrfs_device *device = stripe->dev;
-
-		__clear_extent_bit(&device->alloc_state, stripe->physical,
-				   stripe->physical + stripe_size - 1,
-				   bits | EXTENT_NOWAIT,
-				   NULL, NULL);
-	}
-}
-
 /*
  * Add new extent map to the extent tree
  *
@@ -419,10 +379,6 @@ int add_extent_mapping(struct extent_map_tree *tree,
 		goto out;
 
 	setup_extent_mapping(tree, em, modified);
-	if (test_bit(EXTENT_FLAG_FS_MAPPING, &em->flags)) {
-		extent_map_device_set_bits(em, CHUNK_ALLOCATED);
-		extent_map_device_clear_bits(em, CHUNK_TRIMMED);
-	}
 out:
 	return ret;
 }
@@ -506,8 +462,6 @@ void remove_extent_mapping(struct extent_map_tree *tree, struct extent_map *em)
 	rb_erase_cached(&em->rb_node, &tree->map);
 	if (!test_bit(EXTENT_FLAG_LOGGING, &em->flags))
 		list_del_init(&em->list);
-	if (test_bit(EXTENT_FLAG_FS_MAPPING, &em->flags))
-		extent_map_device_clear_bits(em, CHUNK_ALLOCATED);
 	RB_CLEAR_NODE(&em->rb_node);
 }
 
diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h
index d0328127f89c..bae14af197ef 100644
--- a/fs/btrfs/extent_map.h
+++ b/fs/btrfs/extent_map.h
@@ -23,8 +23,6 @@ enum {
 	EXTENT_FLAG_LOGGING,
 	/* Filling in a preallocated extent */
 	EXTENT_FLAG_FILLING,
-	/* filesystem extent mapping type */
-	EXTENT_FLAG_FS_MAPPING,
 	/* This em is merged from two or more physically adjacent ems */
 	EXTENT_FLAG_MERGED,
 };
@@ -50,8 +48,6 @@ struct extent_map {
 	 */
 	u64 generation;
 	unsigned long flags;
-	/* Used for chunk mappings, flag EXTENT_FLAG_FS_MAPPING must be set */
-	struct map_lookup *map_lookup;
 	refcount_t refs;
 	unsigned int compress_type;
 	struct list_head list;
diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h
index 318df6f9d9cb..a3debac2819a 100644
--- a/fs/btrfs/fs.h
+++ b/fs/btrfs/fs.h
@@ -398,7 +398,8 @@ struct btrfs_fs_info {
 	struct extent_io_tree excluded_extents;
 
 	/* logical->physical extent mapping */
-	struct extent_map_tree mapping_tree;
+	struct rb_root_cached mapping_tree;
+	rwlock_t mapping_tree_lock;
 
 	/*
 	 * Block reservation for extent, checksum, root tree and delayed dir
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index dfef726e84e8..140e9c045cf1 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -10565,6 +10565,7 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
 	struct extent_state *cached_state = NULL;
 	struct extent_map *em = NULL;
+	struct btrfs_chunk_map *map = NULL;
 	struct btrfs_device *device = NULL;
 	struct btrfs_swap_info bsi = {
 		.lowest_ppage = (sector_t)-1ULL,
@@ -10704,13 +10705,13 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 			goto out;
 		}
 
-		em = btrfs_get_chunk_map(fs_info, logical_block_start, len);
-		if (IS_ERR(em)) {
-			ret = PTR_ERR(em);
+		map = btrfs_get_chunk_map(fs_info, logical_block_start, len);
+		if (IS_ERR(map)) {
+			ret = PTR_ERR(map);
 			goto out;
 		}
 
-		if (em->map_lookup->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
+		if (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
 			btrfs_warn(fs_info,
 				   "swapfile must have single data profile");
 			ret = -EINVAL;
@@ -10718,23 +10719,23 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 		}
 
 		if (device == NULL) {
-			device = em->map_lookup->stripes[0].dev;
+			device = map->stripes[0].dev;
 			ret = btrfs_add_swapfile_pin(inode, device, false);
 			if (ret == 1)
 				ret = 0;
 			else if (ret)
 				goto out;
-		} else if (device != em->map_lookup->stripes[0].dev) {
+		} else if (device != map->stripes[0].dev) {
 			btrfs_warn(fs_info, "swapfile must be on one device");
 			ret = -EINVAL;
 			goto out;
 		}
 
-		physical_block_start = (em->map_lookup->stripes[0].physical +
-					(logical_block_start - em->start));
-		len = min(len, em->len - (logical_block_start - em->start));
-		free_extent_map(em);
-		em = NULL;
+		physical_block_start = (map->stripes[0].physical +
+					(logical_block_start - map->start));
+		len = min(len, map->chunk_len - (logical_block_start - map->start));
+		btrfs_free_chunk_map(map);
+		map = NULL;
 
 		bg = btrfs_lookup_block_group(fs_info, logical_block_start);
 		if (!bg) {
@@ -10787,6 +10788,8 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 out:
 	if (!IS_ERR_OR_NULL(em))
 		free_extent_map(em);
+	if (!IS_ERR_OR_NULL(map))
+		btrfs_free_chunk_map(map);
 
 	unlock_extent(io_tree, 0, isize - 1, &cached_state);
 
diff --git a/fs/btrfs/raid56.h b/fs/btrfs/raid56.h
index 45e6ff78316f..470213688872 100644
--- a/fs/btrfs/raid56.h
+++ b/fs/btrfs/raid56.h
@@ -164,7 +164,7 @@ struct raid56_bio_trace_info {
 	u8 stripe_nr;
 };
 
-static inline int nr_data_stripes(const struct map_lookup *map)
+static inline int nr_data_stripes(const struct btrfs_chunk_map *map)
 {
 	return map->num_stripes - btrfs_nr_parity_stripes(map->type);
 }
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 2b04cdb3c4e9..061d54148568 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -1279,7 +1279,7 @@ static void scrub_throttle_dev_io(struct scrub_ctx *sctx, struct btrfs_device *d
  * return 0 if it is a data stripe, 1 means parity stripe.
  */
 static int get_raid56_logic_offset(u64 physical, int num,
-				   struct map_lookup *map, u64 *offset,
+				   struct btrfs_chunk_map *map, u64 *offset,
 				   u64 *stripe_start)
 {
 	int i;
@@ -1894,7 +1894,7 @@ static int queue_scrub_stripe(struct scrub_ctx *sctx, struct btrfs_block_group *
 static int scrub_raid56_parity_stripe(struct scrub_ctx *sctx,
 				      struct btrfs_device *scrub_dev,
 				      struct btrfs_block_group *bg,
-				      struct map_lookup *map,
+				      struct btrfs_chunk_map *map,
 				      u64 full_stripe_start)
 {
 	DECLARE_COMPLETION_ONSTACK(io_done);
@@ -2063,7 +2063,7 @@ out:
  */
 static int scrub_simple_mirror(struct scrub_ctx *sctx,
 			       struct btrfs_block_group *bg,
-			       struct map_lookup *map,
+			       struct btrfs_chunk_map *map,
 			       u64 logical_start, u64 logical_length,
 			       struct btrfs_device *device,
 			       u64 physical, int mirror_num)
@@ -2124,7 +2124,7 @@ static int scrub_simple_mirror(struct scrub_ctx *sctx,
 }
 
 /* Calculate the full stripe length for simple stripe based profiles */
-static u64 simple_stripe_full_stripe_len(const struct map_lookup *map)
+static u64 simple_stripe_full_stripe_len(const struct btrfs_chunk_map *map)
 {
 	ASSERT(map->type & (BTRFS_BLOCK_GROUP_RAID0 |
 			    BTRFS_BLOCK_GROUP_RAID10));
@@ -2133,7 +2133,7 @@ static u64 simple_stripe_full_stripe_len(const struct map_lookup *map)
 }
 
 /* Get the logical bytenr for the stripe */
-static u64 simple_stripe_get_logical(struct map_lookup *map,
+static u64 simple_stripe_get_logical(struct btrfs_chunk_map *map,
 				     struct btrfs_block_group *bg,
 				     int stripe_index)
 {
@@ -2150,7 +2150,7 @@ static u64 simple_stripe_get_logical(struct map_lookup *map,
 }
 
 /* Get the mirror number for the stripe */
-static int simple_stripe_mirror_num(struct map_lookup *map, int stripe_index)
+static int simple_stripe_mirror_num(struct btrfs_chunk_map *map, int stripe_index)
 {
 	ASSERT(map->type & (BTRFS_BLOCK_GROUP_RAID0 |
 			    BTRFS_BLOCK_GROUP_RAID10));
@@ -2162,7 +2162,7 @@ static int simple_stripe_mirror_num(struct map_lookup *map, int stripe_index)
 
 static int scrub_simple_stripe(struct scrub_ctx *sctx,
 			       struct btrfs_block_group *bg,
-			       struct map_lookup *map,
+			       struct btrfs_chunk_map *map,
 			       struct btrfs_device *device,
 			       int stripe_index)
 {
@@ -2195,18 +2195,17 @@ static int scrub_simple_stripe(struct scrub_ctx *sctx,
 
 static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
 					   struct btrfs_block_group *bg,
-					   struct extent_map *em,
+					   struct btrfs_chunk_map *map,
 					   struct btrfs_device *scrub_dev,
 					   int stripe_index)
 {
 	struct btrfs_fs_info *fs_info = sctx->fs_info;
-	struct map_lookup *map = em->map_lookup;
 	const u64 profile = map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK;
 	const u64 chunk_logical = bg->start;
 	int ret;
 	int ret2;
 	u64 physical = map->stripes[stripe_index].physical;
-	const u64 dev_stripe_len = btrfs_calc_stripe_length(em);
+	const u64 dev_stripe_len = btrfs_calc_stripe_length(map);
 	const u64 physical_end = physical + dev_stripe_len;
 	u64 logical;
 	u64 logic_end;
@@ -2369,17 +2368,12 @@ static noinline_for_stack int scrub_chunk(struct scrub_ctx *sctx,
 					  u64 dev_extent_len)
 {
 	struct btrfs_fs_info *fs_info = sctx->fs_info;
-	struct extent_map_tree *map_tree = &fs_info->mapping_tree;
-	struct map_lookup *map;
-	struct extent_map *em;
+	struct btrfs_chunk_map *map;
 	int i;
 	int ret = 0;
 
-	read_lock(&map_tree->lock);
-	em = lookup_extent_mapping(map_tree, bg->start, bg->length);
-	read_unlock(&map_tree->lock);
-
-	if (!em) {
+	map = btrfs_find_chunk_map(fs_info, bg->start, bg->length);
+	if (!map) {
 		/*
 		 * Might have been an unused block group deleted by the cleaner
 		 * kthread or relocation.
@@ -2391,22 +2385,21 @@ static noinline_for_stack int scrub_chunk(struct scrub_ctx *sctx,
 
 		return ret;
 	}
-	if (em->start != bg->start)
+	if (map->start != bg->start)
 		goto out;
-	if (em->len < dev_extent_len)
+	if (map->chunk_len < dev_extent_len)
 		goto out;
 
-	map = em->map_lookup;
 	for (i = 0; i < map->num_stripes; ++i) {
 		if (map->stripes[i].dev->bdev == scrub_dev->bdev &&
 		    map->stripes[i].physical == dev_offset) {
-			ret = scrub_stripe(sctx, bg, em, scrub_dev, i);
+			ret = scrub_stripe(sctx, bg, map, scrub_dev, i);
 			if (ret)
 				goto out;
 		}
 	}
 out:
-	free_extent_map(em);
+	btrfs_free_chunk_map(map);
 
 	return ret;
 }
diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c
index ca09cf9afce8..b50cfac7ad4e 100644
--- a/fs/btrfs/tests/btrfs-tests.c
+++ b/fs/btrfs/tests/btrfs-tests.c
@@ -28,6 +28,7 @@ const char *test_error[] = {
 	[TEST_ALLOC_INODE]	     = "cannot allocate inode",
 	[TEST_ALLOC_BLOCK_GROUP]     = "cannot allocate block group",
 	[TEST_ALLOC_EXTENT_MAP]      = "cannot allocate extent map",
+	[TEST_ALLOC_CHUNK_MAP]       = "cannot allocate chunk map",
 };
 
 static const struct super_operations btrfs_test_super_ops = {
@@ -185,7 +186,7 @@ void btrfs_free_dummy_fs_info(struct btrfs_fs_info *fs_info)
 	}
 	spin_unlock(&fs_info->buffer_lock);
 
-	btrfs_mapping_tree_free(&fs_info->mapping_tree);
+	btrfs_mapping_tree_free(fs_info);
 	list_for_each_entry_safe(dev, tmp, &fs_info->fs_devices->devices,
 				 dev_list) {
 		btrfs_free_dummy_device(dev);
diff --git a/fs/btrfs/tests/btrfs-tests.h b/fs/btrfs/tests/btrfs-tests.h
index 7a2d7ffbe30e..dc2f2ab15fa5 100644
--- a/fs/btrfs/tests/btrfs-tests.h
+++ b/fs/btrfs/tests/btrfs-tests.h
@@ -23,6 +23,7 @@ enum {
 	TEST_ALLOC_INODE,
 	TEST_ALLOC_BLOCK_GROUP,
 	TEST_ALLOC_EXTENT_MAP,
+	TEST_ALLOC_CHUNK_MAP,
 };
 
 extern const char *test_error[];
diff --git a/fs/btrfs/tests/extent-map-tests.c b/fs/btrfs/tests/extent-map-tests.c
index 29bdd08b241f..8602f94cc29d 100644
--- a/fs/btrfs/tests/extent-map-tests.c
+++ b/fs/btrfs/tests/extent-map-tests.c
@@ -859,33 +859,21 @@ struct rmap_test_vector {
 static int test_rmap_block(struct btrfs_fs_info *fs_info,
 			   struct rmap_test_vector *test)
 {
-	struct extent_map *em;
-	struct map_lookup *map = NULL;
+	struct btrfs_chunk_map *map;
 	u64 *logical = NULL;
 	int i, out_ndaddrs, out_stripe_len;
 	int ret;
 
-	em = alloc_extent_map();
-	if (!em) {
-		test_std_err(TEST_ALLOC_EXTENT_MAP);
-		return -ENOMEM;
-	}
-
-	map = kmalloc(map_lookup_size(test->num_stripes), GFP_KERNEL);
+	map = btrfs_alloc_chunk_map(test->num_stripes, GFP_KERNEL);
 	if (!map) {
-		kfree(em);
-		test_std_err(TEST_ALLOC_EXTENT_MAP);
+		test_std_err(TEST_ALLOC_CHUNK_MAP);
 		return -ENOMEM;
 	}
 
-	set_bit(EXTENT_FLAG_FS_MAPPING, &em->flags);
 	/* Start at 4GiB logical address */
-	em->start = SZ_4G;
-	em->len = test->data_stripe_size * test->num_data_stripes;
-	em->block_len = em->len;
-	em->orig_block_len = test->data_stripe_size;
-	em->map_lookup = map;
-
+	map->start = SZ_4G;
+	map->chunk_len = test->data_stripe_size * test->num_data_stripes;
+	map->stripe_size = test->data_stripe_size;
 	map->num_stripes = test->num_stripes;
 	map->type = test->raid_type;
 
@@ -901,15 +889,13 @@ static int test_rmap_block(struct btrfs_fs_info *fs_info,
 		map->stripes[i].physical = test->data_stripe_phys_start[i];
 	}
 
-	write_lock(&fs_info->mapping_tree.lock);
-	ret = add_extent_mapping(&fs_info->mapping_tree, em, 0);
-	write_unlock(&fs_info->mapping_tree.lock);
+	ret = btrfs_add_chunk_map(fs_info, map);
 	if (ret) {
-		test_err("error adding block group mapping to mapping tree");
+		test_err("error adding chunk map to mapping tree");
 		goto out_free;
 	}
 
-	ret = btrfs_rmap_block(fs_info, em->start, btrfs_sb_offset(1),
+	ret = btrfs_rmap_block(fs_info, map->start, btrfs_sb_offset(1),
 			       &logical, &out_ndaddrs, &out_stripe_len);
 	if (ret || (out_ndaddrs == 0 && test->expected_mapped_addr)) {
 		test_err("didn't rmap anything but expected %d",
@@ -938,14 +924,8 @@ static int test_rmap_block(struct btrfs_fs_info *fs_info,
 
 	ret = 0;
 out:
-	write_lock(&fs_info->mapping_tree.lock);
-	remove_extent_mapping(&fs_info->mapping_tree, em);
-	write_unlock(&fs_info->mapping_tree.lock);
-	/* For us */
-	free_extent_map(em);
+	btrfs_remove_chunk_map(fs_info, map);
 out_free:
-	/* For the tree */
-	free_extent_map(em);
 	kfree(logical);
 	return ret;
 }
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index c66e1c6c0410..1cc6b5d5eb61 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1742,19 +1742,18 @@ out:
 
 static u64 find_next_chunk(struct btrfs_fs_info *fs_info)
 {
-	struct extent_map_tree *em_tree;
-	struct extent_map *em;
 	struct rb_node *n;
 	u64 ret = 0;
 
-	em_tree = &fs_info->mapping_tree;
-	read_lock(&em_tree->lock);
-	n = rb_last(&em_tree->map.rb_root);
+	read_lock(&fs_info->mapping_tree_lock);
+	n = rb_last(&fs_info->mapping_tree.rb_root);
 	if (n) {
-		em = rb_entry(n, struct extent_map, rb_node);
-		ret = em->start + em->len;
+		struct btrfs_chunk_map *map;
+
+		map = rb_entry(n, struct btrfs_chunk_map, rb_node);
+		ret = map->start + map->chunk_len;
 	}
-	read_unlock(&em_tree->lock);
+	read_unlock(&fs_info->mapping_tree_lock);
 
 	return ret;
 }
@@ -2986,6 +2985,81 @@ static int btrfs_del_sys_chunk(struct btrfs_fs_info *fs_info, u64 chunk_offset)
 	return ret;
 }
 
+struct btrfs_chunk_map *btrfs_find_chunk_map_nolock(struct btrfs_fs_info *fs_info,
+						    u64 logical, u64 length)
+{
+	struct rb_node *node = fs_info->mapping_tree.rb_root.rb_node;
+	struct rb_node *prev = NULL;
+	struct rb_node *orig_prev;
+	struct btrfs_chunk_map *map;
+	struct btrfs_chunk_map *prev_map = NULL;
+
+	while (node) {
+		map = rb_entry(node, struct btrfs_chunk_map, rb_node);
+		prev = node;
+		prev_map = map;
+
+		if (logical < map->start) {
+			node = node->rb_left;
+		} else if (logical >= map->start + map->chunk_len) {
+			node = node->rb_right;
+		} else {
+			refcount_inc(&map->refs);
+			return map;
+		}
+	}
+
+	if (!prev)
+		return NULL;
+
+	orig_prev = prev;
+	while (prev && logical >= prev_map->start + prev_map->chunk_len) {
+		prev = rb_next(prev);
+		prev_map = rb_entry(prev, struct btrfs_chunk_map, rb_node);
+	}
+
+	if (!prev) {
+		prev = orig_prev;
+		prev_map = rb_entry(prev, struct btrfs_chunk_map, rb_node);
+		while (prev && logical < prev_map->start) {
+			prev = rb_prev(prev);
+			prev_map = rb_entry(prev, struct btrfs_chunk_map, rb_node);
+		}
+	}
+
+	if (prev) {
+		u64 end = logical + length;
+
+		/*
+		 * Caller can pass a U64_MAX length when it wants to get any
+		 * chunk starting at an offset of 'logical' or higher, so deal
+		 * with underflow by resetting the end offset to U64_MAX.
+		 */
+		if (end < logical)
+			end = U64_MAX;
+
+		if (end > prev_map->start &&
+		    logical < prev_map->start + prev_map->chunk_len) {
+			refcount_inc(&prev_map->refs);
+			return prev_map;
+		}
+	}
+
+	return NULL;
+}
+
+struct btrfs_chunk_map *btrfs_find_chunk_map(struct btrfs_fs_info *fs_info,
+					     u64 logical, u64 length)
+{
+	struct btrfs_chunk_map *map;
+
+	read_lock(&fs_info->mapping_tree_lock);
+	map = btrfs_find_chunk_map_nolock(fs_info, logical, length);
+	read_unlock(&fs_info->mapping_tree_lock);
+
+	return map;
+}
+
 /*
  * Find the mapping containing the given logical extent.
  *
@@ -2994,38 +3068,37 @@ static int btrfs_del_sys_chunk(struct btrfs_fs_info *fs_info, u64 chunk_offset)
  *
  * Return: Chunk mapping or ERR_PTR.
  */
-struct extent_map *btrfs_get_chunk_map(struct btrfs_fs_info *fs_info,
-				       u64 logical, u64 length)
+struct btrfs_chunk_map *btrfs_get_chunk_map(struct btrfs_fs_info *fs_info,
+					    u64 logical, u64 length)
 {
-	struct extent_map_tree *em_tree;
-	struct extent_map *em;
+	struct btrfs_chunk_map *map;
 
-	em_tree = &fs_info->mapping_tree;
-	read_lock(&em_tree->lock);
-	em = lookup_extent_mapping(em_tree, logical, length);
-	read_unlock(&em_tree->lock);
+	map = btrfs_find_chunk_map(fs_info, logical, length);
 
-	if (unlikely(!em)) {
+	if (unlikely(!map)) {
+		read_unlock(&fs_info->mapping_tree_lock);
 		btrfs_crit(fs_info,
 			   "unable to find chunk map for logical %llu length %llu",
 			   logical, length);
 		return ERR_PTR(-EINVAL);
 	}
 
-	if (unlikely(em->start > logical || em->start + em->len <= logical)) {
+	if (unlikely(map->start > logical || map->start + map->chunk_len <= logical)) {
+		read_unlock(&fs_info->mapping_tree_lock);
 		btrfs_crit(fs_info,
 			   "found a bad chunk map, wanted %llu-%llu, found %llu-%llu",
-			   logical, logical + length, em->start, em->start + em->len);
-		free_extent_map(em);
+			   logical, logical + length, map->start,
+			   map->start + map->chunk_len);
+		btrfs_free_chunk_map(map);
 		return ERR_PTR(-EINVAL);
 	}
 
-	/* callers are responsible for dropping em's ref. */
-	return em;
+	/* Callers are responsible for dropping the reference. */
+	return map;
 }
 
 static int remove_chunk_item(struct btrfs_trans_handle *trans,
-			     struct map_lookup *map, u64 chunk_offset)
+			     struct btrfs_chunk_map *map, u64 chunk_offset)
 {
 	int i;
 
@@ -3050,23 +3123,21 @@ static int remove_chunk_item(struct btrfs_trans_handle *trans,
 int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
-	struct extent_map *em;
-	struct map_lookup *map;
+	struct btrfs_chunk_map *map;
 	u64 dev_extent_len = 0;
 	int i, ret = 0;
 	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
 
-	em = btrfs_get_chunk_map(fs_info, chunk_offset, 1);
-	if (IS_ERR(em)) {
+	map = btrfs_get_chunk_map(fs_info, chunk_offset, 1);
+	if (IS_ERR(map)) {
 		/*
 		 * This is a logic error, but we don't want to just rely on the
 		 * user having built with ASSERT enabled, so if ASSERT doesn't
 		 * do anything we still error out.
 		 */
 		ASSERT(0);
-		return PTR_ERR(em);
+		return PTR_ERR(map);
 	}
-	map = em->map_lookup;
 
 	/*
 	 * First delete the device extent items from the devices btree.
@@ -3169,7 +3240,7 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset)
 		goto out;
 	}
 
-	trace_btrfs_chunk_free(fs_info, map, chunk_offset, em->len);
+	trace_btrfs_chunk_free(fs_info, map, chunk_offset, map->chunk_len);
 
 	if (map->type & BTRFS_BLOCK_GROUP_SYSTEM) {
 		ret = btrfs_del_sys_chunk(fs_info, chunk_offset);
@@ -3188,7 +3259,7 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset)
 	 */
 	btrfs_trans_release_chunk_metadata(trans);
 
-	ret = btrfs_remove_block_group(trans, chunk_offset, em);
+	ret = btrfs_remove_block_group(trans, map);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
 		goto out;
@@ -3200,7 +3271,7 @@ out:
 		trans->removing_chunk = false;
 	}
 	/* once for us */
-	free_extent_map(em);
+	btrfs_free_chunk_map(map);
 	return ret;
 }
 
@@ -5347,24 +5418,131 @@ static int decide_stripe_size(struct btrfs_fs_devices *fs_devices,
 	}
 }
 
+static void chunk_map_device_set_bits(struct btrfs_chunk_map *map, unsigned int bits)
+{
+	for (int i = 0; i < map->num_stripes; i++) {
+		struct btrfs_io_stripe *stripe = &map->stripes[i];
+		struct btrfs_device *device = stripe->dev;
+
+		set_extent_bit(&device->alloc_state, stripe->physical,
+			       stripe->physical + map->stripe_size - 1,
+			       bits | EXTENT_NOWAIT, NULL);
+	}
+}
+
+static void chunk_map_device_clear_bits(struct btrfs_chunk_map *map, unsigned int bits)
+{
+	for (int i = 0; i < map->num_stripes; i++) {
+		struct btrfs_io_stripe *stripe = &map->stripes[i];
+		struct btrfs_device *device = stripe->dev;
+
+		__clear_extent_bit(&device->alloc_state, stripe->physical,
+				   stripe->physical + map->stripe_size - 1,
+				   bits | EXTENT_NOWAIT,
+				   NULL, NULL);
+	}
+}
+
+void btrfs_remove_chunk_map(struct btrfs_fs_info *fs_info, struct btrfs_chunk_map *map)
+{
+	write_lock(&fs_info->mapping_tree_lock);
+	rb_erase_cached(&map->rb_node, &fs_info->mapping_tree);
+	RB_CLEAR_NODE(&map->rb_node);
+	chunk_map_device_clear_bits(map, CHUNK_ALLOCATED);
+	write_unlock(&fs_info->mapping_tree_lock);
+
+	/* Once for the tree reference. */
+	btrfs_free_chunk_map(map);
+}
+
+EXPORT_FOR_TESTS
+int btrfs_add_chunk_map(struct btrfs_fs_info *fs_info, struct btrfs_chunk_map *map)
+{
+	struct rb_node **p;
+	struct rb_node *parent = NULL;
+	bool leftmost = true;
+
+	write_lock(&fs_info->mapping_tree_lock);
+	p = &fs_info->mapping_tree.rb_root.rb_node;
+	while (*p) {
+		struct btrfs_chunk_map *entry;
+
+		parent = *p;
+		entry = rb_entry(parent, struct btrfs_chunk_map, rb_node);
+
+		if (map->start < entry->start) {
+			p = &(*p)->rb_left;
+		} else if (map->start > entry->start) {
+			p = &(*p)->rb_right;
+			leftmost = false;
+		} else {
+			write_unlock(&fs_info->mapping_tree_lock);
+			return -EEXIST;
+		}
+	}
+	rb_link_node(&map->rb_node, parent, p);
+	rb_insert_color_cached(&map->rb_node, &fs_info->mapping_tree, leftmost);
+	chunk_map_device_set_bits(map, CHUNK_ALLOCATED);
+	chunk_map_device_clear_bits(map, CHUNK_TRIMMED);
+	write_unlock(&fs_info->mapping_tree_lock);
+
+	return 0;
+}
+
+EXPORT_FOR_TESTS
+struct btrfs_chunk_map *btrfs_alloc_chunk_map(int num_stripes, gfp_t gfp)
+{
+	struct btrfs_chunk_map *map;
+
+	map = kmalloc(btrfs_chunk_map_size(num_stripes), gfp);
+	if (!map)
+		return NULL;
+
+	refcount_set(&map->refs, 1);
+	RB_CLEAR_NODE(&map->rb_node);
+
+	return map;
+}
+
+struct btrfs_chunk_map *btrfs_clone_chunk_map(struct btrfs_chunk_map *map, gfp_t gfp)
+{
+	const int size = btrfs_chunk_map_size(map->num_stripes);
+	struct btrfs_chunk_map *clone;
+
+	clone = kmemdup(map, size, gfp);
+	if (!clone)
+		return NULL;
+
+	refcount_set(&clone->refs, 1);
+	RB_CLEAR_NODE(&clone->rb_node);
+
+	return clone;
+}
+
 static struct btrfs_block_group *create_chunk(struct btrfs_trans_handle *trans,
 			struct alloc_chunk_ctl *ctl,
 			struct btrfs_device_info *devices_info)
 {
 	struct btrfs_fs_info *info = trans->fs_info;
-	struct map_lookup *map = NULL;
-	struct extent_map_tree *em_tree;
+	struct btrfs_chunk_map *map;
 	struct btrfs_block_group *block_group;
-	struct extent_map *em;
 	u64 start = ctl->start;
 	u64 type = ctl->type;
 	int ret;
 	int i;
 	int j;
 
-	map = kmalloc(map_lookup_size(ctl->num_stripes), GFP_NOFS);
+	map = btrfs_alloc_chunk_map(ctl->num_stripes, GFP_NOFS);
 	if (!map)
 		return ERR_PTR(-ENOMEM);
+
+	map->start = start;
+	map->chunk_len = ctl->chunk_size;
+	map->stripe_size = ctl->stripe_size;
+	map->type = type;
+	map->io_align = BTRFS_STRIPE_LEN;
+	map->io_width = BTRFS_STRIPE_LEN;
+	map->sub_stripes = ctl->sub_stripes;
 	map->num_stripes = ctl->num_stripes;
 
 	for (i = 0; i < ctl->ndevs; ++i) {
@@ -5375,41 +5553,22 @@ static struct btrfs_block_group *create_chunk(struct btrfs_trans_handle *trans,
 						   j * ctl->stripe_size;
 		}
 	}
-	map->io_align = BTRFS_STRIPE_LEN;
-	map->io_width = BTRFS_STRIPE_LEN;
-	map->type = type;
-	map->sub_stripes = ctl->sub_stripes;
 
 	trace_btrfs_chunk_alloc(info, map, start, ctl->chunk_size);
 
-	em = alloc_extent_map();
-	if (!em) {
-		kfree(map);
-		return ERR_PTR(-ENOMEM);
-	}
-	set_bit(EXTENT_FLAG_FS_MAPPING, &em->flags);
-	em->map_lookup = map;
-	em->start = start;
-	em->len = ctl->chunk_size;
-	em->block_start = 0;
-	em->block_len = em->len;
-	em->orig_block_len = ctl->stripe_size;
-
-	em_tree = &info->mapping_tree;
-	write_lock(&em_tree->lock);
-	ret = add_extent_mapping(em_tree, em, 0);
+	ret = btrfs_add_chunk_map(info, map);
 	if (ret) {
-		write_unlock(&em_tree->lock);
-		free_extent_map(em);
+		btrfs_free_chunk_map(map);
 		return ERR_PTR(ret);
 	}
-	write_unlock(&em_tree->lock);
 
 	block_group = btrfs_make_block_group(trans, type, start, ctl->chunk_size);
-	if (IS_ERR(block_group))
-		goto error_del_extent;
+	if (IS_ERR(block_group)) {
+		btrfs_remove_chunk_map(info, map);
+		return block_group;
+	}
 
-	for (i = 0; i < map->num_stripes; i++) {
+	for (int i = 0; i < map->num_stripes; i++) {
 		struct btrfs_device *dev = map->stripes[i].dev;
 
 		btrfs_device_set_bytes_used(dev,
@@ -5422,22 +5581,9 @@ static struct btrfs_block_group *create_chunk(struct btrfs_trans_handle *trans,
 	atomic64_sub(ctl->stripe_size * map->num_stripes,
 		     &info->free_chunk_space);
 
-	free_extent_map(em);
 	check_raid56_incompat_flag(info, type);
 	check_raid1c34_incompat_flag(info, type);
 
-	return block_group;
-
-error_del_extent:
-	write_lock(&em_tree->lock);
-	remove_extent_mapping(em_tree, em);
-	write_unlock(&em_tree->lock);
-
-	/* One for our allocation */
-	free_extent_map(em);
-	/* One for the tree reference */
-	free_extent_map(em);
-
 	return block_group;
 }
 
@@ -5514,8 +5660,7 @@ int btrfs_chunk_alloc_add_chunk_item(struct btrfs_trans_handle *trans,
 	struct btrfs_key key;
 	struct btrfs_chunk *chunk;
 	struct btrfs_stripe *stripe;
-	struct extent_map *em;
-	struct map_lookup *map;
+	struct btrfs_chunk_map *map;
 	size_t item_size;
 	int i;
 	int ret;
@@ -5544,14 +5689,13 @@ int btrfs_chunk_alloc_add_chunk_item(struct btrfs_trans_handle *trans,
 	 */
 	lockdep_assert_held(&fs_info->chunk_mutex);
 
-	em = btrfs_get_chunk_map(fs_info, bg->start, bg->length);
-	if (IS_ERR(em)) {
-		ret = PTR_ERR(em);
+	map = btrfs_get_chunk_map(fs_info, bg->start, bg->length);
+	if (IS_ERR(map)) {
+		ret = PTR_ERR(map);
 		btrfs_abort_transaction(trans, ret);
 		return ret;
 	}
 
-	map = em->map_lookup;
 	item_size = btrfs_chunk_item_size(map->num_stripes);
 
 	chunk = kzalloc(item_size, GFP_NOFS);
@@ -5608,7 +5752,7 @@ int btrfs_chunk_alloc_add_chunk_item(struct btrfs_trans_handle *trans,
 
 out:
 	kfree(chunk);
-	free_extent_map(em);
+	btrfs_free_chunk_map(map);
 	return ret;
 }
 
@@ -5653,7 +5797,7 @@ static noinline int init_first_rw_device(struct btrfs_trans_handle *trans)
 	return 0;
 }
 
-static inline int btrfs_chunk_max_errors(struct map_lookup *map)
+static inline int btrfs_chunk_max_errors(struct btrfs_chunk_map *map)
 {
 	const int index = btrfs_bg_flags_to_raid_index(map->type);
 
@@ -5662,17 +5806,15 @@ static inline int btrfs_chunk_max_errors(struct map_lookup *map)
 
 bool btrfs_chunk_writeable(struct btrfs_fs_info *fs_info, u64 chunk_offset)
 {
-	struct extent_map *em;
-	struct map_lookup *map;
+	struct btrfs_chunk_map *map;
 	int miss_ndevs = 0;
 	int i;
 	bool ret = true;
 
-	em = btrfs_get_chunk_map(fs_info, chunk_offset, 1);
-	if (IS_ERR(em))
+	map = btrfs_get_chunk_map(fs_info, chunk_offset, 1);
+	if (IS_ERR(map))
 		return false;
 
-	map = em->map_lookup;
 	for (i = 0; i < map->num_stripes; i++) {
 		if (test_bit(BTRFS_DEV_STATE_MISSING,
 					&map->stripes[i].dev->dev_state)) {
@@ -5693,38 +5835,37 @@ bool btrfs_chunk_writeable(struct btrfs_fs_info *fs_info, u64 chunk_offset)
 	if (miss_ndevs > btrfs_chunk_max_errors(map))
 		ret = false;
 end:
-	free_extent_map(em);
+	btrfs_free_chunk_map(map);
 	return ret;
 }
 
-void btrfs_mapping_tree_free(struct extent_map_tree *tree)
+void btrfs_mapping_tree_free(struct btrfs_fs_info *fs_info)
 {
-	struct extent_map *em;
+	write_lock(&fs_info->mapping_tree_lock);
+	while (!RB_EMPTY_ROOT(&fs_info->mapping_tree.rb_root)) {
+		struct btrfs_chunk_map *map;
+		struct rb_node *node;
 
-	while (1) {
-		write_lock(&tree->lock);
-		em = lookup_extent_mapping(tree, 0, (u64)-1);
-		if (em)
-			remove_extent_mapping(tree, em);
-		write_unlock(&tree->lock);
-		if (!em)
-			break;
-		/* once for us */
-		free_extent_map(em);
-		/* once for the tree */
-		free_extent_map(em);
+		node = rb_first_cached(&fs_info->mapping_tree);
+		map = rb_entry(node, struct btrfs_chunk_map, rb_node);
+		rb_erase_cached(&map->rb_node, &fs_info->mapping_tree);
+		RB_CLEAR_NODE(&map->rb_node);
+		chunk_map_device_clear_bits(map, CHUNK_ALLOCATED);
+		/* Once for the tree ref. */
+		btrfs_free_chunk_map(map);
+		cond_resched_rwlock_write(&fs_info->mapping_tree_lock);
 	}
+	write_unlock(&fs_info->mapping_tree_lock);
 }
 
 int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len)
 {
-	struct extent_map *em;
-	struct map_lookup *map;
+	struct btrfs_chunk_map *map;
 	enum btrfs_raid_types index;
 	int ret = 1;
 
-	em = btrfs_get_chunk_map(fs_info, logical, len);
-	if (IS_ERR(em))
+	map = btrfs_get_chunk_map(fs_info, logical, len);
+	if (IS_ERR(map))
 		/*
 		 * We could return errors for these cases, but that could get
 		 * ugly and we'd probably do the same thing which is just not do
@@ -5733,7 +5874,6 @@ int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len)
 		 */
 		return 1;
 
-	map = em->map_lookup;
 	index = btrfs_bg_flags_to_raid_index(map->type);
 
 	/* Non-RAID56, use their ncopies from btrfs_raid_array. */
@@ -5750,53 +5890,49 @@ int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len)
 		 * stripe under reconstruction.
 		 */
 		ret = map->num_stripes;
-	free_extent_map(em);
+	btrfs_free_chunk_map(map);
 	return ret;
 }
 
 unsigned long btrfs_full_stripe_len(struct btrfs_fs_info *fs_info,
 				    u64 logical)
 {
-	struct extent_map *em;
-	struct map_lookup *map;
+	struct btrfs_chunk_map *map;
 	unsigned long len = fs_info->sectorsize;
 
 	if (!btrfs_fs_incompat(fs_info, RAID56))
 		return len;
 
-	em = btrfs_get_chunk_map(fs_info, logical, len);
+	map = btrfs_get_chunk_map(fs_info, logical, len);
 
-	if (!WARN_ON(IS_ERR(em))) {
-		map = em->map_lookup;
+	if (!WARN_ON(IS_ERR(map))) {
 		if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK)
 			len = btrfs_stripe_nr_to_offset(nr_data_stripes(map));
-		free_extent_map(em);
+		btrfs_free_chunk_map(map);
 	}
 	return len;
 }
 
 int btrfs_is_parity_mirror(struct btrfs_fs_info *fs_info, u64 logical, u64 len)
 {
-	struct extent_map *em;
-	struct map_lookup *map;
+	struct btrfs_chunk_map *map;
 	int ret = 0;
 
 	if (!btrfs_fs_incompat(fs_info, RAID56))
 		return 0;
 
-	em = btrfs_get_chunk_map(fs_info, logical, len);
+	map = btrfs_get_chunk_map(fs_info, logical, len);
 
-	if(!WARN_ON(IS_ERR(em))) {
-		map = em->map_lookup;
+	if (!WARN_ON(IS_ERR(map))) {
 		if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK)
 			ret = 1;
-		free_extent_map(em);
+		btrfs_free_chunk_map(map);
 	}
 	return ret;
 }
 
 static int find_live_mirror(struct btrfs_fs_info *fs_info,
-			    struct map_lookup *map, int first,
+			    struct btrfs_chunk_map *map, int first,
 			    int dev_replace_is_ongoing)
 {
 	int i;
@@ -5903,8 +6039,7 @@ struct btrfs_discard_stripe *btrfs_map_discard(struct btrfs_fs_info *fs_info,
 					       u64 logical, u64 *length_ret,
 					       u32 *num_stripes)
 {
-	struct extent_map *em;
-	struct map_lookup *map;
+	struct btrfs_chunk_map *map;
 	struct btrfs_discard_stripe *stripes;
 	u64 length = *length_ret;
 	u64 offset;
@@ -5922,11 +6057,9 @@ struct btrfs_discard_stripe *btrfs_map_discard(struct btrfs_fs_info *fs_info,
 	int ret;
 	int i;
 
-	em = btrfs_get_chunk_map(fs_info, logical, length);
-	if (IS_ERR(em))
-		return ERR_CAST(em);
-
-	map = em->map_lookup;
+	map = btrfs_get_chunk_map(fs_info, logical, length);
+	if (IS_ERR(map))
+		return ERR_CAST(map);
 
 	/* we don't discard raid56 yet */
 	if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
@@ -5934,8 +6067,8 @@ struct btrfs_discard_stripe *btrfs_map_discard(struct btrfs_fs_info *fs_info,
 		goto out_free_map;
 	}
 
-	offset = logical - em->start;
-	length = min_t(u64, em->start + em->len - logical, length);
+	offset = logical - map->start;
+	length = min_t(u64, map->start + map->chunk_len - logical, length);
 	*length_ret = length;
 
 	/*
@@ -6032,10 +6165,10 @@ struct btrfs_discard_stripe *btrfs_map_discard(struct btrfs_fs_info *fs_info,
 		}
 	}
 
-	free_extent_map(em);
+	btrfs_free_chunk_map(map);
 	return stripes;
 out_free_map:
-	free_extent_map(em);
+	btrfs_free_chunk_map(map);
 	return ERR_PTR(ret);
 }
 
@@ -6133,7 +6266,7 @@ static void handle_ops_on_dev_replace(enum btrfs_map_op op,
 	bioc->replace_nr_stripes = nr_extra_stripes;
 }
 
-static u64 btrfs_max_io_len(struct map_lookup *map, enum btrfs_map_op op,
+static u64 btrfs_max_io_len(struct btrfs_chunk_map *map, enum btrfs_map_op op,
 			    u64 offset, u32 *stripe_nr, u64 *stripe_offset,
 			    u64 *full_stripe_start)
 {
@@ -6183,7 +6316,7 @@ static u64 btrfs_max_io_len(struct map_lookup *map, enum btrfs_map_op op,
 
 static int set_io_stripe(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 			 u64 logical, u64 *length, struct btrfs_io_stripe *dst,
-			 struct map_lookup *map, u32 stripe_index,
+			 struct btrfs_chunk_map *map, u32 stripe_index,
 			 u64 stripe_offset, u64 stripe_nr)
 {
 	dst->dev = map->stripes[stripe_index].dev;
@@ -6237,8 +6370,7 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 		    struct btrfs_io_context **bioc_ret,
 		    struct btrfs_io_stripe *smap, int *mirror_num_ret)
 {
-	struct extent_map *em;
-	struct map_lookup *map;
+	struct btrfs_chunk_map *map;
 	u64 map_offset;
 	u64 stripe_offset;
 	u32 stripe_nr;
@@ -6263,17 +6395,16 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 	if (mirror_num > num_copies)
 		return -EINVAL;
 
-	em = btrfs_get_chunk_map(fs_info, logical, *length);
-	if (IS_ERR(em))
-		return PTR_ERR(em);
+	map = btrfs_get_chunk_map(fs_info, logical, *length);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
 
-	map = em->map_lookup;
 	data_stripes = nr_data_stripes(map);
 
-	map_offset = logical - em->start;
+	map_offset = logical - map->start;
 	max_len = btrfs_max_io_len(map, op, map_offset, &stripe_nr,
 				   &stripe_offset, &raid56_full_stripe_start);
-	*length = min_t(u64, em->len - map_offset, max_len);
+	*length = min_t(u64, map->chunk_len - map_offset, max_len);
 
 	down_read(&dev_replace->rwsem);
 	dev_replace_is_ongoing = btrfs_dev_replace_is_ongoing(dev_replace);
@@ -6350,7 +6481,7 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 
 			/* Return the length to the full stripe end */
 			*length = min(logical + *length,
-				      raid56_full_stripe_start + em->start +
+				      raid56_full_stripe_start + map->start +
 				      btrfs_stripe_nr_to_offset(data_stripes)) -
 				  logical;
 			stripe_index = 0;
@@ -6437,7 +6568,7 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 		 * In this case, we just add @stripe_nr with @i, then do the
 		 * modulo, to reduce one modulo call.
 		 */
-		bioc->full_stripe_logical = em->start +
+		bioc->full_stripe_logical = map->start +
 			btrfs_stripe_nr_to_offset(stripe_nr * data_stripes);
 		for (int i = 0; i < num_stripes; i++) {
 			ret = set_io_stripe(fs_info, op, logical, length,
@@ -6488,7 +6619,7 @@ out:
 		/* Unlock and let waiting writers proceed */
 		up_read(&dev_replace->rwsem);
 	}
-	free_extent_map(em);
+	btrfs_free_chunk_map(map);
 	return ret;
 }
 
@@ -6660,12 +6791,11 @@ static void btrfs_report_missing_device(struct btrfs_fs_info *fs_info,
 			      devid, uuid);
 }
 
-u64 btrfs_calc_stripe_length(const struct extent_map *em)
+u64 btrfs_calc_stripe_length(const struct btrfs_chunk_map *map)
 {
-	const struct map_lookup *map = em->map_lookup;
 	const int data_stripes = calc_data_stripes(map->type, map->num_stripes);
 
-	return div_u64(em->len, data_stripes);
+	return div_u64(map->chunk_len, data_stripes);
 }
 
 #if BITS_PER_LONG == 32
@@ -6734,9 +6864,7 @@ static int read_one_chunk(struct btrfs_key *key, struct extent_buffer *leaf,
 {
 	BTRFS_DEV_LOOKUP_ARGS(args);
 	struct btrfs_fs_info *fs_info = leaf->fs_info;
-	struct extent_map_tree *map_tree = &fs_info->mapping_tree;
-	struct map_lookup *map;
-	struct extent_map *em;
+	struct btrfs_chunk_map *map;
 	u64 logical;
 	u64 length;
 	u64 devid;
@@ -6770,35 +6898,22 @@ static int read_one_chunk(struct btrfs_key *key, struct extent_buffer *leaf,
 			return ret;
 	}
 
-	read_lock(&map_tree->lock);
-	em = lookup_extent_mapping(map_tree, logical, 1);
-	read_unlock(&map_tree->lock);
+	map = btrfs_find_chunk_map(fs_info, logical, 1);
 
 	/* already mapped? */
-	if (em && em->start <= logical && em->start + em->len > logical) {
-		free_extent_map(em);
+	if (map && map->start <= logical && map->start + map->chunk_len > logical) {
+		btrfs_free_chunk_map(map);
 		return 0;
-	} else if (em) {
-		free_extent_map(em);
+	} else if (map) {
+		btrfs_free_chunk_map(map);
 	}
 
-	em = alloc_extent_map();
-	if (!em)
-		return -ENOMEM;
-	map = kmalloc(map_lookup_size(num_stripes), GFP_NOFS);
-	if (!map) {
-		free_extent_map(em);
+	map = btrfs_alloc_chunk_map(num_stripes, GFP_NOFS);
+	if (!map)
 		return -ENOMEM;
-	}
-
-	set_bit(EXTENT_FLAG_FS_MAPPING, &em->flags);
-	em->map_lookup = map;
-	em->start = logical;
-	em->len = length;
-	em->orig_start = 0;
-	em->block_start = 0;
-	em->block_len = em->len;
 
+	map->start = logical;
+	map->chunk_len = length;
 	map->num_stripes = num_stripes;
 	map->io_width = btrfs_chunk_io_width(leaf, chunk);
 	map->io_align = btrfs_chunk_io_align(leaf, chunk);
@@ -6813,7 +6928,7 @@ static int read_one_chunk(struct btrfs_key *key, struct extent_buffer *leaf,
 	 */
 	map->sub_stripes = btrfs_raid_array[index].sub_stripes;
 	map->verified_stripes = 0;
-	em->orig_block_len = btrfs_calc_stripe_length(em);
+	map->stripe_size = btrfs_calc_stripe_length(map);
 	for (i = 0; i < num_stripes; i++) {
 		map->stripes[i].physical =
 			btrfs_stripe_offset_nr(leaf, chunk, i);
@@ -6829,7 +6944,7 @@ static int read_one_chunk(struct btrfs_key *key, struct extent_buffer *leaf,
 								    devid, uuid);
 			if (IS_ERR(map->stripes[i].dev)) {
 				ret = PTR_ERR(map->stripes[i].dev);
-				free_extent_map(em);
+				btrfs_free_chunk_map(map);
 				return ret;
 			}
 		}
@@ -6838,15 +6953,12 @@ static int read_one_chunk(struct btrfs_key *key, struct extent_buffer *leaf,
 				&(map->stripes[i].dev->dev_state));
 	}
 
-	write_lock(&map_tree->lock);
-	ret = add_extent_mapping(map_tree, em, 0);
-	write_unlock(&map_tree->lock);
+	ret = btrfs_add_chunk_map(fs_info, map);
 	if (ret < 0) {
 		btrfs_err(fs_info,
 			  "failed to add chunk map, start=%llu len=%llu: %d",
-			  em->start, em->len, ret);
+			  map->start, map->chunk_len, ret);
 	}
-	free_extent_map(em);
 
 	return ret;
 }
@@ -7156,26 +7268,21 @@ out_short_read:
 bool btrfs_check_rw_degradable(struct btrfs_fs_info *fs_info,
 					struct btrfs_device *failing_dev)
 {
-	struct extent_map_tree *map_tree = &fs_info->mapping_tree;
-	struct extent_map *em;
-	u64 next_start = 0;
+	struct btrfs_chunk_map *map;
+	u64 next_start;
 	bool ret = true;
 
-	read_lock(&map_tree->lock);
-	em = lookup_extent_mapping(map_tree, 0, (u64)-1);
-	read_unlock(&map_tree->lock);
+	map = btrfs_find_chunk_map(fs_info, 0, U64_MAX);
 	/* No chunk at all? Return false anyway */
-	if (!em) {
+	if (!map) {
 		ret = false;
 		goto out;
 	}
-	while (em) {
-		struct map_lookup *map;
+	while (map) {
 		int missing = 0;
 		int max_tolerated;
 		int i;
 
-		map = em->map_lookup;
 		max_tolerated =
 			btrfs_get_num_tolerated_disk_barrier_failures(
 					map->type);
@@ -7193,18 +7300,15 @@ bool btrfs_check_rw_degradable(struct btrfs_fs_info *fs_info,
 			if (!failing_dev)
 				btrfs_warn(fs_info,
 	"chunk %llu missing %d devices, max tolerance is %d for writable mount",
-				   em->start, missing, max_tolerated);
-			free_extent_map(em);
+				   map->start, missing, max_tolerated);
+			btrfs_free_chunk_map(map);
 			ret = false;
 			goto out;
 		}
-		next_start = extent_map_end(em);
-		free_extent_map(em);
+		next_start = map->start + map->chunk_len;
+		btrfs_free_chunk_map(map);
 
-		read_lock(&map_tree->lock);
-		em = lookup_extent_mapping(map_tree, next_start,
-					   (u64)(-1) - next_start);
-		read_unlock(&map_tree->lock);
+		map = btrfs_find_chunk_map(fs_info, next_start, U64_MAX - next_start);
 	}
 out:
 	return ret;
@@ -7697,20 +7801,15 @@ static int verify_one_dev_extent(struct btrfs_fs_info *fs_info,
 				 u64 physical_offset, u64 physical_len)
 {
 	struct btrfs_dev_lookup_args args = { .devid = devid };
-	struct extent_map_tree *em_tree = &fs_info->mapping_tree;
-	struct extent_map *em;
-	struct map_lookup *map;
+	struct btrfs_chunk_map *map;
 	struct btrfs_device *dev;
 	u64 stripe_len;
 	bool found = false;
 	int ret = 0;
 	int i;
 
-	read_lock(&em_tree->lock);
-	em = lookup_extent_mapping(em_tree, chunk_offset, 1);
-	read_unlock(&em_tree->lock);
-
-	if (!em) {
+	map = btrfs_find_chunk_map(fs_info, chunk_offset, 1);
+	if (!map) {
 		btrfs_err(fs_info,
 "dev extent physical offset %llu on devid %llu doesn't have corresponding chunk",
 			  physical_offset, devid);
@@ -7718,12 +7817,11 @@ static int verify_one_dev_extent(struct btrfs_fs_info *fs_info,
 		goto out;
 	}
 
-	map = em->map_lookup;
-	stripe_len = btrfs_calc_stripe_length(em);
+	stripe_len = btrfs_calc_stripe_length(map);
 	if (physical_len != stripe_len) {
 		btrfs_err(fs_info,
 "dev extent physical offset %llu on devid %llu length doesn't match chunk %llu, have %llu expect %llu",
-			  physical_offset, devid, em->start, physical_len,
+			  physical_offset, devid, map->start, physical_len,
 			  stripe_len);
 		ret = -EUCLEAN;
 		goto out;
@@ -7746,7 +7844,7 @@ static int verify_one_dev_extent(struct btrfs_fs_info *fs_info,
 			if (map->verified_stripes >= map->num_stripes) {
 				btrfs_err(fs_info,
 				"too many dev extents for chunk %llu found",
-					  em->start);
+					  map->start);
 				ret = -EUCLEAN;
 				goto out;
 			}
@@ -7792,32 +7890,30 @@ static int verify_one_dev_extent(struct btrfs_fs_info *fs_info,
 	}
 
 out:
-	free_extent_map(em);
+	btrfs_free_chunk_map(map);
 	return ret;
 }
 
 static int verify_chunk_dev_extent_mapping(struct btrfs_fs_info *fs_info)
 {
-	struct extent_map_tree *em_tree = &fs_info->mapping_tree;
-	struct extent_map *em;
 	struct rb_node *node;
 	int ret = 0;
 
-	read_lock(&em_tree->lock);
-	for (node = rb_first_cached(&em_tree->map); node; node = rb_next(node)) {
-		em = rb_entry(node, struct extent_map, rb_node);
-		if (em->map_lookup->num_stripes !=
-		    em->map_lookup->verified_stripes) {
+	read_lock(&fs_info->mapping_tree_lock);
+	for (node = rb_first_cached(&fs_info->mapping_tree); node; node = rb_next(node)) {
+		struct btrfs_chunk_map *map;
+
+		map = rb_entry(node, struct btrfs_chunk_map, rb_node);
+		if (map->num_stripes != map->verified_stripes) {
 			btrfs_err(fs_info,
 			"chunk %llu has missing dev extent, have %d expect %d",
-				  em->start, em->map_lookup->verified_stripes,
-				  em->map_lookup->num_stripes);
+				  map->start, map->verified_stripes, map->num_stripes);
 			ret = -EUCLEAN;
 			goto out;
 		}
 	}
 out:
-	read_unlock(&em_tree->lock);
+	read_unlock(&fs_info->mapping_tree_lock);
 	return ret;
 }
 
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 9cc374864a79..6c6faed2468a 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -426,7 +426,8 @@ struct btrfs_discard_stripe {
 struct btrfs_io_context {
 	refcount_t refs;
 	struct btrfs_fs_info *fs_info;
-	u64 map_type; /* get from map_lookup->type */
+	/* Taken from struct btrfs_chunk_map::type. */
+	u64 map_type;
 	struct bio *orig_bio;
 	atomic_t error;
 	u16 max_errors;
@@ -529,18 +530,32 @@ struct btrfs_raid_attr {
 
 extern const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES];
 
-struct map_lookup {
+struct btrfs_chunk_map {
+	struct rb_node rb_node;
+	/* For mount time dev extent verification. */
+	int verified_stripes;
+	refcount_t refs;
+	u64 start;
+	u64 chunk_len;
+	u64 stripe_size;
 	u64 type;
 	int io_align;
 	int io_width;
 	int num_stripes;
 	int sub_stripes;
-	int verified_stripes; /* For mount time dev extent verification */
 	struct btrfs_io_stripe stripes[];
 };
 
-#define map_lookup_size(n) (sizeof(struct map_lookup) + \
-			    (sizeof(struct btrfs_io_stripe) * (n)))
+#define btrfs_chunk_map_size(n) (sizeof(struct btrfs_chunk_map) + \
+				 (sizeof(struct btrfs_io_stripe) * (n)))
+
+static inline void btrfs_free_chunk_map(struct btrfs_chunk_map *map)
+{
+	if (map && refcount_dec_and_test(&map->refs)) {
+		ASSERT(RB_EMPTY_NODE(&map->rb_node));
+		kfree(map);
+	}
+}
 
 struct btrfs_balance_args;
 struct btrfs_balance_progress;
@@ -624,7 +639,7 @@ int btrfs_read_sys_array(struct btrfs_fs_info *fs_info);
 int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info);
 struct btrfs_block_group *btrfs_create_chunk(struct btrfs_trans_handle *trans,
 					    u64 type);
-void btrfs_mapping_tree_free(struct extent_map_tree *tree);
+void btrfs_mapping_tree_free(struct btrfs_fs_info *fs_info);
 int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 		       blk_mode_t flags, void *holder);
 struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags,
@@ -680,13 +695,25 @@ int btrfs_is_parity_mirror(struct btrfs_fs_info *fs_info,
 			   u64 logical, u64 len);
 unsigned long btrfs_full_stripe_len(struct btrfs_fs_info *fs_info,
 				    u64 logical);
-u64 btrfs_calc_stripe_length(const struct extent_map *em);
+u64 btrfs_calc_stripe_length(const struct btrfs_chunk_map *map);
 int btrfs_nr_parity_stripes(u64 type);
 int btrfs_chunk_alloc_add_chunk_item(struct btrfs_trans_handle *trans,
 				     struct btrfs_block_group *bg);
 int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset);
-struct extent_map *btrfs_get_chunk_map(struct btrfs_fs_info *fs_info,
-				       u64 logical, u64 length);
+
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+struct btrfs_chunk_map *btrfs_alloc_chunk_map(int num_stripes, gfp_t gfp);
+int btrfs_add_chunk_map(struct btrfs_fs_info *fs_info, struct btrfs_chunk_map *map);
+#endif
+
+struct btrfs_chunk_map *btrfs_clone_chunk_map(struct btrfs_chunk_map *map, gfp_t gfp);
+struct btrfs_chunk_map *btrfs_find_chunk_map(struct btrfs_fs_info *fs_info,
+					     u64 logical, u64 length);
+struct btrfs_chunk_map *btrfs_find_chunk_map_nolock(struct btrfs_fs_info *fs_info,
+						    u64 logical, u64 length);
+struct btrfs_chunk_map *btrfs_get_chunk_map(struct btrfs_fs_info *fs_info,
+					    u64 logical, u64 length);
+void btrfs_remove_chunk_map(struct btrfs_fs_info *fs_info, struct btrfs_chunk_map *map);
 void btrfs_release_disk_super(struct btrfs_super_block *super);
 
 static inline void btrfs_dev_stat_inc(struct btrfs_device *dev,
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 188378ca19c7..830f0b6ec89e 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -1290,7 +1290,7 @@ struct zone_info {
 
 static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx,
 				struct zone_info *info, unsigned long *active,
-				struct map_lookup *map)
+				struct btrfs_chunk_map *map)
 {
 	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
 	struct btrfs_device *device = map->stripes[zone_idx].dev;
@@ -1393,7 +1393,7 @@ static int btrfs_load_block_group_single(struct btrfs_block_group *bg,
 }
 
 static int btrfs_load_block_group_dup(struct btrfs_block_group *bg,
-				      struct map_lookup *map,
+				      struct btrfs_chunk_map *map,
 				      struct zone_info *zone_info,
 				      unsigned long *active)
 {
@@ -1435,7 +1435,7 @@ static int btrfs_load_block_group_dup(struct btrfs_block_group *bg,
 }
 
 static int btrfs_load_block_group_raid1(struct btrfs_block_group *bg,
-					struct map_lookup *map,
+					struct btrfs_chunk_map *map,
 					struct zone_info *zone_info,
 					unsigned long *active)
 {
@@ -1483,7 +1483,7 @@ static int btrfs_load_block_group_raid1(struct btrfs_block_group *bg,
 }
 
 static int btrfs_load_block_group_raid0(struct btrfs_block_group *bg,
-					struct map_lookup *map,
+					struct btrfs_chunk_map *map,
 					struct zone_info *zone_info,
 					unsigned long *active)
 {
@@ -1515,7 +1515,7 @@ static int btrfs_load_block_group_raid0(struct btrfs_block_group *bg,
 }
 
 static int btrfs_load_block_group_raid10(struct btrfs_block_group *bg,
-					 struct map_lookup *map,
+					 struct btrfs_chunk_map *map,
 					 struct zone_info *zone_info,
 					 unsigned long *active)
 {
@@ -1552,9 +1552,7 @@ static int btrfs_load_block_group_raid10(struct btrfs_block_group *bg,
 int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 {
 	struct btrfs_fs_info *fs_info = cache->fs_info;
-	struct extent_map_tree *em_tree = &fs_info->mapping_tree;
-	struct extent_map *em;
-	struct map_lookup *map;
+	struct btrfs_chunk_map *map;
 	u64 logical = cache->start;
 	u64 length = cache->length;
 	struct zone_info *zone_info = NULL;
@@ -1575,17 +1573,11 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 		return -EIO;
 	}
 
-	/* Get the chunk mapping */
-	read_lock(&em_tree->lock);
-	em = lookup_extent_mapping(em_tree, logical, length);
-	read_unlock(&em_tree->lock);
-
-	if (!em)
+	map = btrfs_find_chunk_map(fs_info, logical, length);
+	if (!map)
 		return -EINVAL;
 
-	map = em->map_lookup;
-
-	cache->physical_map = kmemdup(map, map_lookup_size(map->num_stripes), GFP_NOFS);
+	cache->physical_map = btrfs_clone_chunk_map(map, GFP_NOFS);
 	if (!cache->physical_map) {
 		ret = -ENOMEM;
 		goto out;
@@ -1687,12 +1679,11 @@ out:
 			spin_unlock(&fs_info->zone_active_bgs_lock);
 		}
 	} else {
-		kfree(cache->physical_map);
+		btrfs_free_chunk_map(cache->physical_map);
 		cache->physical_map = NULL;
 	}
 	bitmap_free(active);
 	kfree(zone_info);
-	free_extent_map(em);
 
 	return ret;
 }
@@ -2082,7 +2073,7 @@ int btrfs_sync_zone_write_pointer(struct btrfs_device *tgt_dev, u64 logical,
 bool btrfs_zone_activate(struct btrfs_block_group *block_group)
 {
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
-	struct map_lookup *map;
+	struct btrfs_chunk_map *map;
 	struct btrfs_device *device;
 	u64 physical;
 	const bool is_data = (block_group->flags & BTRFS_BLOCK_GROUP_DATA);
@@ -2194,7 +2185,7 @@ static void wait_eb_writebacks(struct btrfs_block_group *block_group)
 static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_written)
 {
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
-	struct map_lookup *map;
+	struct btrfs_chunk_map *map;
 	const bool is_metadata = (block_group->flags &
 			(BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_SYSTEM));
 	int ret = 0;
@@ -2643,7 +2634,7 @@ void btrfs_check_active_zone_reservation(struct btrfs_fs_info *fs_info)
 	/* Release reservation for currently active block groups. */
 	spin_lock(&fs_info->zone_active_bgs_lock);
 	list_for_each_entry(block_group, &fs_info->zone_active_bgs, active_bg_list) {
-		struct map_lookup *map = block_group->physical_map;
+		struct btrfs_chunk_map *map = block_group->physical_map;
 
 		if (!(block_group->flags &
 		      (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_SYSTEM)))
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index 279a7a0c90c0..4a95097ab590 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -21,7 +21,7 @@ struct btrfs_delayed_data_ref;
 struct btrfs_delayed_ref_head;
 struct btrfs_block_group;
 struct btrfs_free_cluster;
-struct map_lookup;
+struct btrfs_chunk_map;
 struct extent_buffer;
 struct btrfs_work;
 struct btrfs_workqueue;
@@ -277,8 +277,7 @@ DEFINE_EVENT(btrfs__inode, btrfs_inode_evict,
 		{ (1 << EXTENT_FLAG_COMPRESSED), 	"COMPRESSED" 	},\
 		{ (1 << EXTENT_FLAG_PREALLOC), 		"PREALLOC" 	},\
 		{ (1 << EXTENT_FLAG_LOGGING),	 	"LOGGING" 	},\
-		{ (1 << EXTENT_FLAG_FILLING),	 	"FILLING" 	},\
-		{ (1 << EXTENT_FLAG_FS_MAPPING),	"FS_MAPPING"	})
+		{ (1 << EXTENT_FLAG_FILLING),		"FILLING"	})
 
 TRACE_EVENT_CONDITION(btrfs_get_extent,
 
@@ -1061,7 +1060,7 @@ DEFINE_EVENT(btrfs_delayed_ref_head,  run_delayed_ref_head,
 DECLARE_EVENT_CLASS(btrfs__chunk,
 
 	TP_PROTO(const struct btrfs_fs_info *fs_info,
-		 const struct map_lookup *map, u64 offset, u64 size),
+		 const struct btrfs_chunk_map *map, u64 offset, u64 size),
 
 	TP_ARGS(fs_info, map, offset, size),
 
@@ -1095,7 +1094,7 @@ DECLARE_EVENT_CLASS(btrfs__chunk,
 DEFINE_EVENT(btrfs__chunk,  btrfs_chunk_alloc,
 
 	TP_PROTO(const struct btrfs_fs_info *fs_info,
-		 const struct map_lookup *map, u64 offset, u64 size),
+		 const struct btrfs_chunk_map *map, u64 offset, u64 size),
 
 	TP_ARGS(fs_info, map, offset, size)
 );
@@ -1103,7 +1102,7 @@ DEFINE_EVENT(btrfs__chunk,  btrfs_chunk_alloc,
 DEFINE_EVENT(btrfs__chunk,  btrfs_chunk_free,
 
 	TP_PROTO(const struct btrfs_fs_info *fs_info,
-		 const struct map_lookup *map, u64 offset, u64 size),
+		 const struct btrfs_chunk_map *map, u64 offset, u64 size),
 
 	TP_ARGS(fs_info, map, offset, size)
 );
-- 
cgit v1.2.3


From 738290c056e28d83177ecbed3894e094e161939e Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Tue, 21 Nov 2023 14:20:24 +0100
Subject: btrfs: always set extent_io_tree::inode and drop fs_info

The extent_io_tree is embedded in several structures, notably in struct
btrfs_inode.  The fs_info is only used for reporting errors and for
reference in trace points. We can get to the pointer through the inode,
but not all io trees set it. However, we always know the owner and
can recognize if inode is valid.  For access helpers are provided, const
variant for the trace points.

This reduces size of extent_io_tree by 8 bytes and following structures
in turn:

- btrfs_inode		1104 -> 1088
- btrfs_device		 520 ->  512
- btrfs_root		1360 -> 1344
- btrfs_transaction	 456 ->  440
- btrfs_fs_info		3600 -> 3592
- reloc_control		1520 -> 1512

Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-io-tree.c    | 80 ++++++++++++++++++++++++++++++++------------
 fs/btrfs/extent-io-tree.h    | 18 ++++++++--
 fs/btrfs/inode.c             |  3 ++
 fs/btrfs/tests/btrfs-tests.c |  2 +-
 include/trace/events/btrfs.h | 47 +++++++++-----------------
 5 files changed, 94 insertions(+), 56 deletions(-)

(limited to 'include')

diff --git a/fs/btrfs/extent-io-tree.c b/fs/btrfs/extent-io-tree.c
index 2d564ead9dbe..dbd201a99693 100644
--- a/fs/btrfs/extent-io-tree.c
+++ b/fs/btrfs/extent-io-tree.c
@@ -58,12 +58,13 @@ static inline void __btrfs_debug_check_extent_io_range(const char *caller,
 						       struct extent_io_tree *tree,
 						       u64 start, u64 end)
 {
-	struct btrfs_inode *inode = tree->inode;
+	const struct btrfs_inode *inode;
 	u64 isize;
 
-	if (!inode)
+	if (tree->owner != IO_TREE_INODE_IO)
 		return;
 
+	inode = extent_io_tree_to_inode_const(tree);
 	isize = i_size_read(&inode->vfs_inode);
 	if (end >= PAGE_SIZE && (end % 2) == 0 && end != isize - 1) {
 		btrfs_debug_rl(inode->root->fs_info,
@@ -79,13 +80,44 @@ static inline void __btrfs_debug_check_extent_io_range(const char *caller,
 #endif
 
 
+/*
+ * The only tree allowed to set the inode is IO_TREE_INODE_IO.
+ */
+static bool is_inode_io_tree(const struct extent_io_tree *tree)
+{
+	return tree->owner == IO_TREE_INODE_IO;
+}
+
+/* Return the inode if it's valid for the given tree, otherwise NULL. */
+struct btrfs_inode *extent_io_tree_to_inode(struct extent_io_tree *tree)
+{
+	if (tree->owner == IO_TREE_INODE_IO)
+		return tree->inode;
+	return NULL;
+}
+
+/* Read-only access to the inode. */
+const struct btrfs_inode *extent_io_tree_to_inode_const(const struct extent_io_tree *tree)
+{
+	if (tree->owner == IO_TREE_INODE_IO)
+		return tree->inode;
+	return NULL;
+}
+
+/* For read-only access to fs_info. */
+const struct btrfs_fs_info *extent_io_tree_to_fs_info(const struct extent_io_tree *tree)
+{
+	if (tree->owner == IO_TREE_INODE_IO)
+		return tree->inode->root->fs_info;
+	return tree->fs_info;
+}
+
 void extent_io_tree_init(struct btrfs_fs_info *fs_info,
 			 struct extent_io_tree *tree, unsigned int owner)
 {
-	tree->fs_info = fs_info;
 	tree->state = RB_ROOT;
 	spin_lock_init(&tree->lock);
-	tree->inode = NULL;
+	tree->fs_info = fs_info;
 	tree->owner = owner;
 }
 
@@ -318,7 +350,7 @@ static void extent_io_tree_panic(const struct extent_io_tree *tree,
 				 const char *opname,
 				 int err)
 {
-	btrfs_panic(tree->fs_info, err,
+	btrfs_panic(extent_io_tree_to_fs_info(tree), err,
 		    "extent io tree error on %s state start %llu end %llu",
 		    opname, state->start, state->end);
 }
@@ -329,8 +361,9 @@ static void merge_prev_state(struct extent_io_tree *tree, struct extent_state *s
 
 	prev = prev_state(state);
 	if (prev && prev->end == state->start - 1 && prev->state == state->state) {
-		if (tree->inode)
-			btrfs_merge_delalloc_extent(tree->inode, state, prev);
+		if (is_inode_io_tree(tree))
+			btrfs_merge_delalloc_extent(extent_io_tree_to_inode(tree),
+						    state, prev);
 		state->start = prev->start;
 		rb_erase(&prev->rb_node, &tree->state);
 		RB_CLEAR_NODE(&prev->rb_node);
@@ -344,8 +377,9 @@ static void merge_next_state(struct extent_io_tree *tree, struct extent_state *s
 
 	next = next_state(state);
 	if (next && next->start == state->end + 1 && next->state == state->state) {
-		if (tree->inode)
-			btrfs_merge_delalloc_extent(tree->inode, state, next);
+		if (is_inode_io_tree(tree))
+			btrfs_merge_delalloc_extent(extent_io_tree_to_inode(tree),
+						    state, next);
 		state->end = next->end;
 		rb_erase(&next->rb_node, &tree->state);
 		RB_CLEAR_NODE(&next->rb_node);
@@ -378,8 +412,8 @@ static void set_state_bits(struct extent_io_tree *tree,
 	u32 bits_to_set = bits & ~EXTENT_CTLBITS;
 	int ret;
 
-	if (tree->inode)
-		btrfs_set_delalloc_extent(tree->inode, state, bits);
+	if (is_inode_io_tree(tree))
+		btrfs_set_delalloc_extent(extent_io_tree_to_inode(tree), state, bits);
 
 	ret = add_extent_changeset(state, bits_to_set, changeset, 1);
 	BUG_ON(ret < 0);
@@ -424,9 +458,10 @@ static struct extent_state *insert_state(struct extent_io_tree *tree,
 		if (state->end < entry->start) {
 			if (try_merge && end == entry->start &&
 			    state->state == entry->state) {
-				if (tree->inode)
-					btrfs_merge_delalloc_extent(tree->inode,
-								    state, entry);
+				if (is_inode_io_tree(tree))
+					btrfs_merge_delalloc_extent(
+							extent_io_tree_to_inode(tree),
+							state, entry);
 				entry->start = state->start;
 				merge_prev_state(tree, entry);
 				state->state = 0;
@@ -436,9 +471,10 @@ static struct extent_state *insert_state(struct extent_io_tree *tree,
 		} else if (state->end > entry->end) {
 			if (try_merge && entry->end == start &&
 			    state->state == entry->state) {
-				if (tree->inode)
-					btrfs_merge_delalloc_extent(tree->inode,
-								    state, entry);
+				if (is_inode_io_tree(tree))
+					btrfs_merge_delalloc_extent(
+							extent_io_tree_to_inode(tree),
+							state, entry);
 				entry->end = state->end;
 				merge_next_state(tree, entry);
 				state->state = 0;
@@ -490,8 +526,9 @@ static int split_state(struct extent_io_tree *tree, struct extent_state *orig,
 	struct rb_node *parent = NULL;
 	struct rb_node **node;
 
-	if (tree->inode)
-		btrfs_split_delalloc_extent(tree->inode, orig, split);
+	if (is_inode_io_tree(tree))
+		btrfs_split_delalloc_extent(extent_io_tree_to_inode(tree), orig,
+					    split);
 
 	prealloc->start = orig->start;
 	prealloc->end = split - 1;
@@ -538,8 +575,9 @@ static struct extent_state *clear_state_bit(struct extent_io_tree *tree,
 	u32 bits_to_clear = bits & ~EXTENT_CTLBITS;
 	int ret;
 
-	if (tree->inode)
-		btrfs_clear_delalloc_extent(tree->inode, state, bits);
+	if (is_inode_io_tree(tree))
+		btrfs_clear_delalloc_extent(extent_io_tree_to_inode(tree), state,
+					    bits);
 
 	ret = add_extent_changeset(state, bits_to_clear, changeset, 0);
 	BUG_ON(ret < 0);
diff --git a/fs/btrfs/extent-io-tree.h b/fs/btrfs/extent-io-tree.h
index 5602b0137fcd..ebe6390d65e9 100644
--- a/fs/btrfs/extent-io-tree.h
+++ b/fs/btrfs/extent-io-tree.h
@@ -87,9 +87,17 @@ enum {
 
 struct extent_io_tree {
 	struct rb_root state;
-	struct btrfs_fs_info *fs_info;
-	/* Inode associated with this tree, or NULL. */
-	struct btrfs_inode *inode;
+	/*
+	 * The fs_info is needed for trace points, a tree attached to an inode
+	 * needs the inode.
+	 *
+	 * owner == IO_TREE_INODE_IO - then inode is valid and fs_info can be
+	 *                             accessed as inode->root->fs_info
+	 */
+	union {
+		struct btrfs_fs_info *fs_info;
+		struct btrfs_inode *inode;
+	};
 
 	/* Who owns this io tree, should be one of IO_TREE_* */
 	u8 owner;
@@ -112,6 +120,10 @@ struct extent_state {
 #endif
 };
 
+struct btrfs_inode *extent_io_tree_to_inode(struct extent_io_tree *tree);
+const struct btrfs_inode *extent_io_tree_to_inode_const(const struct extent_io_tree *tree);
+const struct btrfs_fs_info *extent_io_tree_to_fs_info(const struct extent_io_tree *tree);
+
 void extent_io_tree_init(struct btrfs_fs_info *fs_info,
 			 struct extent_io_tree *tree, unsigned int owner);
 void extent_io_tree_release(struct extent_io_tree *tree);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 7cb5139e3d7f..7320c1ea7926 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -8511,8 +8511,11 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 
 	inode = &ei->vfs_inode;
 	extent_map_tree_init(&ei->extent_tree);
+
+	/* This io tree sets the valid inode. */
 	extent_io_tree_init(fs_info, &ei->io_tree, IO_TREE_INODE_IO);
 	ei->io_tree.inode = ei;
+
 	extent_io_tree_init(fs_info, &ei->file_extent_tree,
 			    IO_TREE_INODE_FILE_EXTENT);
 	/* Lockdep class is set only for the file extent tree. */
diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c
index b50cfac7ad4e..709c6cc9706a 100644
--- a/fs/btrfs/tests/btrfs-tests.c
+++ b/fs/btrfs/tests/btrfs-tests.c
@@ -103,7 +103,7 @@ struct btrfs_device *btrfs_alloc_dummy_device(struct btrfs_fs_info *fs_info)
 	if (!dev)
 		return ERR_PTR(-ENOMEM);
 
-	extent_io_tree_init(NULL, &dev->alloc_state, 0);
+	extent_io_tree_init(fs_info, &dev->alloc_state, 0);
 	INIT_LIST_HEAD(&dev->dev_list);
 	list_add(&dev->dev_list, &fs_info->fs_devices->devices);
 
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index 4a95097ab590..856109048999 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -2098,17 +2098,12 @@ TRACE_EVENT(btrfs_set_extent_bit,
 		__field(	unsigned,	set_bits)
 	),
 
-	TP_fast_assign_btrfs(tree->fs_info,
-		__entry->owner = tree->owner;
-		if (tree->inode) {
-			const struct btrfs_inode *inode = tree->inode;
-
-			__entry->ino	= btrfs_ino(inode);
-			__entry->rootid	= inode->root->root_key.objectid;
-		} else {
-			__entry->ino	= 0;
-			__entry->rootid	= 0;
-		}
+	TP_fast_assign_btrfs(extent_io_tree_to_fs_info(tree),
+		const struct btrfs_inode *inode = extent_io_tree_to_inode_const(tree);
+
+		__entry->owner		= tree->owner;
+		__entry->ino		= inode ? btrfs_ino(inode) : 0;
+		__entry->rootid		= inode ? inode->root->root_key.objectid : 0;
 		__entry->start		= start;
 		__entry->len		= len;
 		__entry->set_bits	= set_bits;
@@ -2136,17 +2131,12 @@ TRACE_EVENT(btrfs_clear_extent_bit,
 		__field(	unsigned,	clear_bits)
 	),
 
-	TP_fast_assign_btrfs(tree->fs_info,
-		__entry->owner = tree->owner;
-		if (tree->inode) {
-			const struct btrfs_inode *inode = tree->inode;
+	TP_fast_assign_btrfs(extent_io_tree_to_fs_info(tree),
+		const struct btrfs_inode *inode = extent_io_tree_to_inode_const(tree);
 
-			__entry->ino	= btrfs_ino(inode);
-			__entry->rootid	= inode->root->root_key.objectid;
-		} else {
-			__entry->ino	= 0;
-			__entry->rootid	= 0;
-		}
+		__entry->owner		= tree->owner;
+		__entry->ino		= inode ? btrfs_ino(inode) : 0;
+		__entry->rootid		= inode ? inode->root->root_key.objectid : 0;
 		__entry->start		= start;
 		__entry->len		= len;
 		__entry->clear_bits	= clear_bits;
@@ -2175,17 +2165,12 @@ TRACE_EVENT(btrfs_convert_extent_bit,
 		__field(	unsigned,	clear_bits)
 	),
 
-	TP_fast_assign_btrfs(tree->fs_info,
-		__entry->owner = tree->owner;
-		if (tree->inode) {
-			const struct btrfs_inode *inode = tree->inode;
+	TP_fast_assign_btrfs(extent_io_tree_to_fs_info(tree),
+		const struct btrfs_inode *inode = extent_io_tree_to_inode_const(tree);
 
-			__entry->ino	= btrfs_ino(inode);
-			__entry->rootid	= inode->root->root_key.objectid;
-		} else {
-			__entry->ino	= 0;
-			__entry->rootid	= 0;
-		}
+		__entry->owner		= tree->owner;
+		__entry->ino		= inode ? btrfs_ino(inode) : 0;
+		__entry->rootid		= inode ? inode->root->root_key.objectid : 0;
 		__entry->start		= start;
 		__entry->len		= len;
 		__entry->set_bits	= set_bits;
-- 
cgit v1.2.3


From 3c0e918b8fb3a6a7da1558913302a3e89cf87343 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Thu, 23 Nov 2023 23:53:51 +0000
Subject: btrfs: remove no longer used EXTENT_MAP_DELALLOC block start value

After commit ac3c0d36a2a2 ("btrfs: make fiemap more efficient and accurate
reporting extent sharedness") we no longer need to create special extent
maps during fiemap that have a block start with the EXTENT_MAP_DELALLOC
value. So this block start value for extent maps is no longer used since
then, therefore remove it.

Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/defrag.c            | 3 +--
 fs/btrfs/extent_map.c        | 3 ---
 fs/btrfs/extent_map.h        | 2 --
 include/trace/events/btrfs.h | 3 +--
 4 files changed, 2 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/fs/btrfs/defrag.c b/fs/btrfs/defrag.c
index 5244561e2016..9bcb60c68c58 100644
--- a/fs/btrfs/defrag.c
+++ b/fs/btrfs/defrag.c
@@ -996,9 +996,8 @@ static int defrag_collect_targets(struct btrfs_inode *inode,
 		    em->len <= inode->root->fs_info->max_inline)
 			goto next;
 
-		/* Skip hole/delalloc/preallocated extents */
+		/* Skip holes and preallocated extents. */
 		if (em->block_start == EXTENT_MAP_HOLE ||
-		    em->block_start == EXTENT_MAP_DELALLOC ||
 		    test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
 			goto next;
 
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index c956b1ced69f..80f86503a5cd 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -212,9 +212,6 @@ static int mergable_maps(struct extent_map *prev, struct extent_map *next)
 	if (!list_empty(&prev->list) || !list_empty(&next->list))
 		return 0;
 
-	ASSERT(next->block_start != EXTENT_MAP_DELALLOC &&
-	       prev->block_start != EXTENT_MAP_DELALLOC);
-
 	if (extent_map_end(prev) == next->start &&
 	    prev->flags == next->flags &&
 	    ((next->block_start == EXTENT_MAP_HOLE &&
diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h
index bae14af197ef..66f8dd26487b 100644
--- a/fs/btrfs/extent_map.h
+++ b/fs/btrfs/extent_map.h
@@ -9,8 +9,6 @@
 #define EXTENT_MAP_LAST_BYTE ((u64)-4)
 #define EXTENT_MAP_HOLE ((u64)-3)
 #define EXTENT_MAP_INLINE ((u64)-2)
-/* used only during fiemap calls */
-#define EXTENT_MAP_DELALLOC ((u64)-1)
 
 /* bits for the extent_map::flags field */
 enum {
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index 856109048999..31da1456f953 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -265,8 +265,7 @@ DEFINE_EVENT(btrfs__inode, btrfs_inode_evict,
 	__print_symbolic_u64(type,					\
 		{ EXTENT_MAP_LAST_BYTE, "LAST_BYTE" 	},		\
 		{ EXTENT_MAP_HOLE, 	"HOLE" 		},		\
-		{ EXTENT_MAP_INLINE, 	"INLINE" 	},		\
-		{ EXTENT_MAP_DELALLOC,	"DELALLOC" 	})
+		{ EXTENT_MAP_INLINE,	"INLINE"	})
 
 #define show_map_type(type)			\
 	type, (type >= EXTENT_MAP_LAST_BYTE) ? "-" :  __show_map_type(type)
-- 
cgit v1.2.3


From f86f7a75e2fb5fd7d31d00eab8a392f97ba42ce9 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Mon, 4 Dec 2023 16:20:33 +0000
Subject: btrfs: use the flags of an extent map to identify the compression
 type

Currently, in struct extent_map, we use an unsigned int (32 bits) to
identify the compression type of an extent and an unsigned long (64 bits
on a 64 bits platform, 32 bits otherwise) for flags. We are only using
6 different flags, so an unsigned long is excessive and we can use flags
to identify the compression type instead of using a dedicated 32 bits
field.

We can easily have tens or hundreds of thousands (or more) of extent maps
on busy and large filesystems, specially with compression enabled or many
or large files with tons of small extents. So it's convenient to have the
extent_map structure as small as possible in order to use less memory.

So remove the compression type field from struct extent_map, use flags
to identify the compression type and shorten the flags field from an
unsigned long to a u32. This saves 8 bytes (on 64 bits platforms) and
reduces the size of the structure from 136 bytes down to 128 bytes, using
now only two cache lines, and increases the number of extent maps we can
have per 4K page from 30 to 32. By using a u32 for the flags instead of
an unsigned long, we no longer use test_bit(), set_bit() and clear_bit(),
but that level of atomicity is not needed as most flags are never cleared
once set (before adding an extent map to the tree), and the ones that can
be cleared or set after an extent map is added to the tree, are always
performed while holding the write lock on the extent map tree, while the
reader holds a lock on the tree or tests for a flag that never changes
once the extent map is in the tree (such as compression flags).

Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/compression.c            |  4 +--
 fs/btrfs/defrag.c                 |  8 +++---
 fs/btrfs/extent_io.c              | 13 ++++-----
 fs/btrfs/extent_map.c             | 51 ++++++++++++++-------------------
 fs/btrfs/extent_map.h             | 58 +++++++++++++++++++++++++++++++------
 fs/btrfs/file-item.c              |  9 ++----
 fs/btrfs/file.c                   | 10 +++----
 fs/btrfs/inode.c                  | 33 ++++++++++-----------
 fs/btrfs/relocation.c             |  2 +-
 fs/btrfs/tests/extent-map-tests.c |  4 +--
 fs/btrfs/tests/inode-tests.c      | 60 +++++++++++++++++++--------------------
 fs/btrfs/tree-log.c               | 16 ++++++-----
 include/trace/events/btrfs.h      | 21 +++++++-------
 13 files changed, 158 insertions(+), 131 deletions(-)

(limited to 'include')

diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 05595d113ff8..2d9974c283c6 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -584,7 +584,7 @@ void btrfs_submit_compressed_read(struct btrfs_bio *bbio)
 		goto out;
 	}
 
-	ASSERT(em->compress_type != BTRFS_COMPRESS_NONE);
+	ASSERT(extent_map_is_compressed(em));
 	compressed_len = em->block_len;
 
 	cb = alloc_compressed_bio(inode, file_offset, REQ_OP_READ,
@@ -596,7 +596,7 @@ void btrfs_submit_compressed_read(struct btrfs_bio *bbio)
 
 	cb->len = bbio->bio.bi_iter.bi_size;
 	cb->compressed_len = compressed_len;
-	cb->compress_type = em->compress_type;
+	cb->compress_type = extent_map_compression(em);
 	cb->orig_bbio = bbio;
 
 	free_extent_map(em);
diff --git a/fs/btrfs/defrag.c b/fs/btrfs/defrag.c
index 9bcb60c68c58..a9a068af8d6e 100644
--- a/fs/btrfs/defrag.c
+++ b/fs/btrfs/defrag.c
@@ -775,7 +775,7 @@ static struct extent_map *defrag_lookup_extent(struct inode *inode, u64 start,
 	 * this em, as either we don't care about the generation, or the
 	 * merged extent map will be rejected anyway.
 	 */
-	if (em && test_bit(EXTENT_FLAG_MERGED, &em->flags) &&
+	if (em && (em->flags & EXTENT_FLAG_MERGED) &&
 	    newer_than && em->generation >= newer_than) {
 		free_extent_map(em);
 		em = NULL;
@@ -802,7 +802,7 @@ static struct extent_map *defrag_lookup_extent(struct inode *inode, u64 start,
 static u32 get_extent_max_capacity(const struct btrfs_fs_info *fs_info,
 				   const struct extent_map *em)
 {
-	if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags))
+	if (extent_map_is_compressed(em))
 		return BTRFS_MAX_COMPRESSED;
 	return fs_info->max_extent_size;
 }
@@ -828,7 +828,7 @@ static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em,
 	/* No more em or hole */
 	if (!next || next->block_start >= EXTENT_MAP_LAST_BYTE)
 		goto out;
-	if (test_bit(EXTENT_FLAG_PREALLOC, &next->flags))
+	if (next->flags & EXTENT_FLAG_PREALLOC)
 		goto out;
 	/*
 	 * If the next extent is at its max capacity, defragging current extent
@@ -998,7 +998,7 @@ static int defrag_collect_targets(struct btrfs_inode *inode,
 
 		/* Skip holes and preallocated extents. */
 		if (em->block_start == EXTENT_MAP_HOLE ||
-		    test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
+		    (em->flags & EXTENT_FLAG_PREALLOC))
 			goto next;
 
 		/* Skip older extent */
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 7f7ecee9e048..bf13aebe2384 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1032,8 +1032,7 @@ static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached,
 		BUG_ON(extent_map_end(em) <= cur);
 		BUG_ON(end < cur);
 
-		if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags))
-			compress_type = em->compress_type;
+		compress_type = extent_map_compression(em);
 
 		iosize = min(extent_map_end(em) - cur, end - cur + 1);
 		iosize = ALIGN(iosize, blocksize);
@@ -1042,7 +1041,7 @@ static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached,
 		else
 			disk_bytenr = em->block_start + extent_offset;
 		block_start = em->block_start;
-		if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
+		if (em->flags & EXTENT_FLAG_PREALLOC)
 			block_start = EXTENT_MAP_HOLE;
 
 		/*
@@ -1079,7 +1078,7 @@ static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached,
 		 * is a corner case so we prioritize correctness over
 		 * non-optimal behavior (submitting 2 bios for the same extent).
 		 */
-		if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags) &&
+		if (compress_type != BTRFS_COMPRESS_NONE &&
 		    prev_em_start && *prev_em_start != (u64)-1 &&
 		    *prev_em_start != em->start)
 			force_bio_submit = true;
@@ -1358,7 +1357,7 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode,
 		block_start = em->block_start;
 		disk_bytenr = em->block_start + extent_offset;
 
-		ASSERT(!test_bit(EXTENT_FLAG_COMPRESSED, &em->flags));
+		ASSERT(!extent_map_is_compressed(em));
 		ASSERT(block_start != EXTENT_MAP_HOLE);
 		ASSERT(block_start != EXTENT_MAP_INLINE);
 
@@ -2360,7 +2359,7 @@ int try_release_extent_mapping(struct page *page, gfp_t mask)
 				write_unlock(&map->lock);
 				break;
 			}
-			if (test_bit(EXTENT_FLAG_PINNED, &em->flags) ||
+			if ((em->flags & EXTENT_FLAG_PINNED) ||
 			    em->start != start) {
 				write_unlock(&map->lock);
 				free_extent_map(em);
@@ -2377,7 +2376,7 @@ int try_release_extent_mapping(struct page *page, gfp_t mask)
 			 * extra reference on the em.
 			 */
 			if (list_empty(&em->list) ||
-			    test_bit(EXTENT_FLAG_LOGGING, &em->flags))
+			    (em->flags & EXTENT_FLAG_LOGGING))
 				goto remove_em;
 			/*
 			 * If it's in the list of modified extents, remove it
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 0d1167f454d2..b61099bf97a8 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -50,7 +50,6 @@ struct extent_map *alloc_extent_map(void)
 	if (!em)
 		return NULL;
 	RB_CLEAR_NODE(&em->rb_node);
-	em->compress_type = BTRFS_COMPRESS_NONE;
 	refcount_set(&em->refs, 1);
 	INIT_LIST_HEAD(&em->list);
 	return em;
@@ -189,14 +188,14 @@ static inline u64 extent_map_block_end(const struct extent_map *em)
 
 static bool can_merge_extent_map(const struct extent_map *em)
 {
-	if (test_bit(EXTENT_FLAG_PINNED, &em->flags))
+	if (em->flags & EXTENT_FLAG_PINNED)
 		return false;
 
 	/* Don't merge compressed extents, we need to know their actual size. */
-	if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags))
+	if (extent_map_is_compressed(em))
 		return false;
 
-	if (test_bit(EXTENT_FLAG_LOGGING, &em->flags))
+	if (em->flags & EXTENT_FLAG_LOGGING)
 		return false;
 
 	/*
@@ -258,7 +257,7 @@ static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em)
 			em->mod_len = (em->mod_len + em->mod_start) - merge->mod_start;
 			em->mod_start = merge->mod_start;
 			em->generation = max(em->generation, merge->generation);
-			set_bit(EXTENT_FLAG_MERGED, &em->flags);
+			em->flags |= EXTENT_FLAG_MERGED;
 
 			rb_erase_cached(&merge->rb_node, &tree->map);
 			RB_CLEAR_NODE(&merge->rb_node);
@@ -276,7 +275,7 @@ static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em)
 		RB_CLEAR_NODE(&merge->rb_node);
 		em->mod_len = (merge->mod_start + merge->mod_len) - em->mod_start;
 		em->generation = max(em->generation, merge->generation);
-		set_bit(EXTENT_FLAG_MERGED, &em->flags);
+		em->flags |= EXTENT_FLAG_MERGED;
 		free_extent_map(merge);
 	}
 }
@@ -319,13 +318,13 @@ int unpin_extent_cache(struct btrfs_inode *inode, u64 start, u64 len, u64 gen)
 			   em->start, start, len, gen);
 
 	em->generation = gen;
-	clear_bit(EXTENT_FLAG_PINNED, &em->flags);
+	em->flags &= ~EXTENT_FLAG_PINNED;
 	em->mod_start = em->start;
 	em->mod_len = em->len;
 
-	if (test_bit(EXTENT_FLAG_FILLING, &em->flags)) {
+	if (em->flags & EXTENT_FLAG_FILLING) {
 		prealloc = true;
-		clear_bit(EXTENT_FLAG_FILLING, &em->flags);
+		em->flags &= ~EXTENT_FLAG_FILLING;
 	}
 
 	try_merge_map(tree, em);
@@ -346,7 +345,7 @@ void clear_em_logging(struct extent_map_tree *tree, struct extent_map *em)
 {
 	lockdep_assert_held_write(&tree->lock);
 
-	clear_bit(EXTENT_FLAG_LOGGING, &em->flags);
+	em->flags &= ~EXTENT_FLAG_LOGGING;
 	if (extent_map_in_tree(em))
 		try_merge_map(tree, em);
 }
@@ -471,9 +470,9 @@ void remove_extent_mapping(struct extent_map_tree *tree, struct extent_map *em)
 {
 	lockdep_assert_held_write(&tree->lock);
 
-	WARN_ON(test_bit(EXTENT_FLAG_PINNED, &em->flags));
+	WARN_ON(em->flags & EXTENT_FLAG_PINNED);
 	rb_erase_cached(&em->rb_node, &tree->map);
-	if (!test_bit(EXTENT_FLAG_LOGGING, &em->flags))
+	if (!(em->flags & EXTENT_FLAG_LOGGING))
 		list_del_init(&em->list);
 	RB_CLEAR_NODE(&em->rb_node);
 }
@@ -485,9 +484,9 @@ static void replace_extent_mapping(struct extent_map_tree *tree,
 {
 	lockdep_assert_held_write(&tree->lock);
 
-	WARN_ON(test_bit(EXTENT_FLAG_PINNED, &cur->flags));
+	WARN_ON(cur->flags & EXTENT_FLAG_PINNED);
 	ASSERT(extent_map_in_tree(cur));
-	if (!test_bit(EXTENT_FLAG_LOGGING, &cur->flags))
+	if (!(cur->flags & EXTENT_FLAG_LOGGING))
 		list_del_init(&cur->list);
 	rb_replace_node_cached(&cur->rb_node, &new->rb_node, &tree->map);
 	RB_CLEAR_NODE(&cur->rb_node);
@@ -550,7 +549,7 @@ static noinline int merge_extent_mapping(struct extent_map_tree *em_tree,
 	em->start = start;
 	em->len = end - start;
 	if (em->block_start < EXTENT_MAP_LAST_BYTE &&
-	    !test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) {
+	    !extent_map_is_compressed(em)) {
 		em->block_start += start_diff;
 		em->block_len = em->len;
 	}
@@ -653,8 +652,7 @@ static void drop_all_extent_maps_fast(struct extent_map_tree *tree)
 
 		node = rb_first_cached(&tree->map);
 		em = rb_entry(node, struct extent_map, rb_node);
-		clear_bit(EXTENT_FLAG_PINNED, &em->flags);
-		clear_bit(EXTENT_FLAG_LOGGING, &em->flags);
+		em->flags &= ~(EXTENT_FLAG_PINNED | EXTENT_FLAG_LOGGING);
 		remove_extent_mapping(tree, em);
 		free_extent_map(em);
 		cond_resched_rwlock_write(&tree->lock);
@@ -730,19 +728,18 @@ void btrfs_drop_extent_map_range(struct btrfs_inode *inode, u64 start, u64 end,
 			}
 		}
 
-		if (skip_pinned && test_bit(EXTENT_FLAG_PINNED, &em->flags)) {
+		if (skip_pinned && (em->flags & EXTENT_FLAG_PINNED)) {
 			start = em_end;
 			goto next;
 		}
 
 		flags = em->flags;
-		clear_bit(EXTENT_FLAG_PINNED, &em->flags);
 		/*
 		 * In case we split the extent map, we want to preserve the
 		 * EXTENT_FLAG_LOGGING flag on our extent map, but we don't want
 		 * it on the new extent maps.
 		 */
-		clear_bit(EXTENT_FLAG_LOGGING, &flags);
+		em->flags &= ~(EXTENT_FLAG_PINNED | EXTENT_FLAG_LOGGING);
 		modified = !list_empty(&em->list);
 
 		/*
@@ -753,7 +750,7 @@ void btrfs_drop_extent_map_range(struct btrfs_inode *inode, u64 start, u64 end,
 			goto remove_em;
 
 		gen = em->generation;
-		compressed = test_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
+		compressed = extent_map_is_compressed(em);
 
 		if (em->start < start) {
 			if (!split) {
@@ -786,7 +783,6 @@ void btrfs_drop_extent_map_range(struct btrfs_inode *inode, u64 start, u64 end,
 
 			split->generation = gen;
 			split->flags = flags;
-			split->compress_type = em->compress_type;
 			replace_extent_mapping(em_tree, em, split, modified);
 			free_extent_map(split);
 			split = split2;
@@ -803,7 +799,6 @@ void btrfs_drop_extent_map_range(struct btrfs_inode *inode, u64 start, u64 end,
 			split->len = em_end - end;
 			split->block_start = em->block_start;
 			split->flags = flags;
-			split->compress_type = em->compress_type;
 			split->generation = gen;
 
 			if (em->block_start < EXTENT_MAP_LAST_BYTE) {
@@ -969,14 +964,14 @@ int split_extent_map(struct btrfs_inode *inode, u64 start, u64 len, u64 pre,
 	}
 
 	ASSERT(em->len == len);
-	ASSERT(!test_bit(EXTENT_FLAG_COMPRESSED, &em->flags));
+	ASSERT(!extent_map_is_compressed(em));
 	ASSERT(em->block_start < EXTENT_MAP_LAST_BYTE);
-	ASSERT(test_bit(EXTENT_FLAG_PINNED, &em->flags));
-	ASSERT(!test_bit(EXTENT_FLAG_LOGGING, &em->flags));
+	ASSERT(em->flags & EXTENT_FLAG_PINNED);
+	ASSERT(!(em->flags & EXTENT_FLAG_LOGGING));
 	ASSERT(!list_empty(&em->list));
 
 	flags = em->flags;
-	clear_bit(EXTENT_FLAG_PINNED, &em->flags);
+	em->flags &= ~EXTENT_FLAG_PINNED;
 
 	/* First, replace the em with a new extent_map starting from * em->start */
 	split_pre->start = em->start;
@@ -987,7 +982,6 @@ int split_extent_map(struct btrfs_inode *inode, u64 start, u64 len, u64 pre,
 	split_pre->orig_block_len = split_pre->block_len;
 	split_pre->ram_bytes = split_pre->len;
 	split_pre->flags = flags;
-	split_pre->compress_type = em->compress_type;
 	split_pre->generation = em->generation;
 
 	replace_extent_mapping(em_tree, em, split_pre, 1);
@@ -1006,7 +1000,6 @@ int split_extent_map(struct btrfs_inode *inode, u64 start, u64 len, u64 pre,
 	split_mid->orig_block_len = split_mid->block_len;
 	split_mid->ram_bytes = split_mid->len;
 	split_mid->flags = flags;
-	split_mid->compress_type = em->compress_type;
 	split_mid->generation = em->generation;
 	add_extent_mapping(em_tree, split_mid, 1);
 
diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h
index 44dc0cb310ea..e380fc08bbe4 100644
--- a/fs/btrfs/extent_map.h
+++ b/fs/btrfs/extent_map.h
@@ -5,6 +5,7 @@
 
 #include <linux/rbtree.h>
 #include <linux/refcount.h>
+#include "compression.h"
 
 #define EXTENT_MAP_LAST_BYTE ((u64)-4)
 #define EXTENT_MAP_HOLE ((u64)-3)
@@ -13,18 +14,24 @@
 /* bits for the extent_map::flags field */
 enum {
 	/* this entry not yet on disk, don't free it */
-	EXTENT_FLAG_PINNED,
-	EXTENT_FLAG_COMPRESSED,
+	ENUM_BIT(EXTENT_FLAG_PINNED),
+	ENUM_BIT(EXTENT_FLAG_COMPRESS_ZLIB),
+	ENUM_BIT(EXTENT_FLAG_COMPRESS_LZO),
+	ENUM_BIT(EXTENT_FLAG_COMPRESS_ZSTD),
 	/* pre-allocated extent */
-	EXTENT_FLAG_PREALLOC,
+	ENUM_BIT(EXTENT_FLAG_PREALLOC),
 	/* Logging this extent */
-	EXTENT_FLAG_LOGGING,
+	ENUM_BIT(EXTENT_FLAG_LOGGING),
 	/* Filling in a preallocated extent */
-	EXTENT_FLAG_FILLING,
+	ENUM_BIT(EXTENT_FLAG_FILLING),
 	/* This em is merged from two or more physically adjacent ems */
-	EXTENT_FLAG_MERGED,
+	ENUM_BIT(EXTENT_FLAG_MERGED),
 };
 
+/*
+ * Keep this structure as compact as possible, as we can have really large
+ * amounts of allocated extent maps at any time.
+ */
 struct extent_map {
 	struct rb_node rb_node;
 
@@ -45,9 +52,8 @@ struct extent_map {
 	 * For non-merged extents, it's from btrfs_file_extent_item::generation.
 	 */
 	u64 generation;
-	unsigned long flags;
+	u32 flags;
 	refcount_t refs;
-	unsigned int compress_type;
 	struct list_head list;
 };
 
@@ -59,6 +65,42 @@ struct extent_map_tree {
 
 struct btrfs_inode;
 
+static inline void extent_map_set_compression(struct extent_map *em,
+					      enum btrfs_compression_type type)
+{
+	if (type == BTRFS_COMPRESS_ZLIB)
+		em->flags |= EXTENT_FLAG_COMPRESS_ZLIB;
+	else if (type == BTRFS_COMPRESS_LZO)
+		em->flags |= EXTENT_FLAG_COMPRESS_LZO;
+	else if (type == BTRFS_COMPRESS_ZSTD)
+		em->flags |= EXTENT_FLAG_COMPRESS_ZSTD;
+}
+
+static inline enum btrfs_compression_type extent_map_compression(const struct extent_map *em)
+{
+	if (em->flags & EXTENT_FLAG_COMPRESS_ZLIB)
+		return BTRFS_COMPRESS_ZLIB;
+
+	if (em->flags & EXTENT_FLAG_COMPRESS_LZO)
+		return BTRFS_COMPRESS_LZO;
+
+	if (em->flags & EXTENT_FLAG_COMPRESS_ZSTD)
+		return BTRFS_COMPRESS_ZSTD;
+
+	return BTRFS_COMPRESS_NONE;
+}
+
+/*
+ * More efficient way to determine if extent is compressed, instead of using
+ * 'extent_map_compression() != BTRFS_COMPRESS_NONE'.
+ */
+static inline bool extent_map_is_compressed(const struct extent_map *em)
+{
+	return (em->flags & (EXTENT_FLAG_COMPRESS_ZLIB |
+			     EXTENT_FLAG_COMPRESS_LZO |
+			     EXTENT_FLAG_COMPRESS_ZSTD)) != 0;
+}
+
 static inline int extent_map_in_tree(const struct extent_map *em)
 {
 	return !RB_EMPTY_NODE(&em->rb_node);
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 1f0110f48353..81ac1d474bf1 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -1294,8 +1294,7 @@ void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode,
 			return;
 		}
 		if (compress_type != BTRFS_COMPRESS_NONE) {
-			set_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
-			em->compress_type = compress_type;
+			extent_map_set_compression(em, compress_type);
 			em->block_start = bytenr;
 			em->block_len = em->orig_block_len;
 		} else {
@@ -1303,7 +1302,7 @@ void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode,
 			em->block_start = bytenr;
 			em->block_len = em->len;
 			if (type == BTRFS_FILE_EXTENT_PREALLOC)
-				set_bit(EXTENT_FLAG_PREALLOC, &em->flags);
+				em->flags |= EXTENT_FLAG_PREALLOC;
 		}
 	} else if (type == BTRFS_FILE_EXTENT_INLINE) {
 		em->block_start = EXTENT_MAP_INLINE;
@@ -1315,9 +1314,7 @@ void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode,
 		 */
 		em->orig_start = EXTENT_MAP_HOLE;
 		em->block_len = (u64)-1;
-		em->compress_type = compress_type;
-		if (compress_type != BTRFS_COMPRESS_NONE)
-			set_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
+		extent_map_set_compression(em, compress_type);
 	} else {
 		btrfs_err(fs_info,
 			  "unknown file extent item type %d, inode %llu, offset %llu, "
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 7a71720aaed2..98ef859f8938 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2150,7 +2150,6 @@ out:
 		hole_em->block_start = EXTENT_MAP_HOLE;
 		hole_em->block_len = 0;
 		hole_em->orig_block_len = 0;
-		hole_em->compress_type = BTRFS_COMPRESS_NONE;
 		hole_em->generation = trans->transid;
 
 		ret = btrfs_replace_extent_map_range(inode, hole_em, true);
@@ -2839,7 +2838,7 @@ static int btrfs_zero_range_check_range_boundary(struct btrfs_inode *inode,
 
 	if (em->block_start == EXTENT_MAP_HOLE)
 		ret = RANGE_BOUNDARY_HOLE;
-	else if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
+	else if (em->flags & EXTENT_FLAG_PREALLOC)
 		ret = RANGE_BOUNDARY_PREALLOC_EXTENT;
 	else
 		ret = RANGE_BOUNDARY_WRITTEN_EXTENT;
@@ -2879,8 +2878,7 @@ static int btrfs_zero_range(struct inode *inode,
 	 * extents and holes, we drop all the existing extents and allocate a
 	 * new prealloc extent, so that we get a larger contiguous disk extent.
 	 */
-	if (em->start <= alloc_start &&
-	    test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) {
+	if (em->start <= alloc_start && (em->flags & EXTENT_FLAG_PREALLOC)) {
 		const u64 em_end = em->start + em->len;
 
 		if (em_end >= offset + len) {
@@ -2915,7 +2913,7 @@ static int btrfs_zero_range(struct inode *inode,
 			goto out;
 		}
 
-		if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) {
+		if (em->flags & EXTENT_FLAG_PREALLOC) {
 			free_extent_map(em);
 			ret = btrfs_fallocate_update_isize(inode, offset + len,
 							   mode);
@@ -3136,7 +3134,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 		last_byte = ALIGN(last_byte, blocksize);
 		if (em->block_start == EXTENT_MAP_HOLE ||
 		    (cur_offset >= inode->i_size &&
-		     !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) {
+		     !(em->flags & EXTENT_FLAG_PREALLOC))) {
 			const u64 range_len = last_byte - cur_offset;
 
 			ret = add_falloc_range(&reserve_list, cur_offset, range_len);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 88614bb87b95..a1f6e8d3b546 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4898,7 +4898,7 @@ int btrfs_cont_expand(struct btrfs_inode *inode, loff_t oldsize, loff_t size)
 		last_byte = ALIGN(last_byte, fs_info->sectorsize);
 		hole_size = last_byte - cur_offset;
 
-		if (!test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) {
+		if (!(em->flags & EXTENT_FLAG_PREALLOC)) {
 			struct extent_map *hole_em;
 
 			err = maybe_insert_hole(inode, cur_offset, hole_size);
@@ -4926,7 +4926,6 @@ int btrfs_cont_expand(struct btrfs_inode *inode, loff_t oldsize, loff_t size)
 			hole_em->block_len = 0;
 			hole_em->orig_block_len = 0;
 			hole_em->ram_bytes = hole_size;
-			hole_em->compress_type = BTRFS_COMPRESS_NONE;
 			hole_em->generation = btrfs_get_fs_generation(fs_info);
 
 			err = btrfs_replace_extent_map_range(inode, hole_em, true);
@@ -7274,13 +7273,11 @@ static struct extent_map *create_io_em(struct btrfs_inode *inode, u64 start,
 	em->orig_block_len = orig_block_len;
 	em->ram_bytes = ram_bytes;
 	em->generation = -1;
-	set_bit(EXTENT_FLAG_PINNED, &em->flags);
-	if (type == BTRFS_ORDERED_PREALLOC) {
-		set_bit(EXTENT_FLAG_FILLING, &em->flags);
-	} else if (type == BTRFS_ORDERED_COMPRESSED) {
-		set_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
-		em->compress_type = compress_type;
-	}
+	em->flags |= EXTENT_FLAG_PINNED;
+	if (type == BTRFS_ORDERED_PREALLOC)
+		em->flags |= EXTENT_FLAG_FILLING;
+	else if (type == BTRFS_ORDERED_COMPRESSED)
+		extent_map_set_compression(em, compress_type);
 
 	ret = btrfs_replace_extent_map_range(inode, em, true);
 	if (ret) {
@@ -7320,10 +7317,10 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map,
 	 * just use the extent.
 	 *
 	 */
-	if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags) ||
+	if ((em->flags & EXTENT_FLAG_PREALLOC) ||
 	    ((BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) &&
 	     em->block_start != EXTENT_MAP_HOLE)) {
-		if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
+		if (em->flags & EXTENT_FLAG_PREALLOC)
 			type = BTRFS_ORDERED_PREALLOC;
 		else
 			type = BTRFS_ORDERED_NOCOW;
@@ -7558,7 +7555,7 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start,
 	 * to buffered IO.  Don't blame me, this is the price we pay for using
 	 * the generic code.
 	 */
-	if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags) ||
+	if (extent_map_is_compressed(em) ||
 	    em->block_start == EXTENT_MAP_INLINE) {
 		free_extent_map(em);
 		/*
@@ -7654,7 +7651,7 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start,
 	 * that, since we have locked only the parts we are performing I/O in.
 	 */
 	if ((em->block_start == EXTENT_MAP_HOLE) ||
-	    (test_bit(EXTENT_FLAG_PREALLOC, &em->flags) && !write)) {
+	    ((em->flags & EXTENT_FLAG_PREALLOC) && !write)) {
 		iomap->addr = IOMAP_NULL_ADDR;
 		iomap->type = IOMAP_HOLE;
 	} else {
@@ -9669,7 +9666,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
 		em->block_len = ins.offset;
 		em->orig_block_len = ins.offset;
 		em->ram_bytes = ins.offset;
-		set_bit(EXTENT_FLAG_PREALLOC, &em->flags);
+		em->flags |= EXTENT_FLAG_PREALLOC;
 		em->generation = trans->transid;
 
 		ret = btrfs_replace_extent_map_range(BTRFS_I(inode), em, true);
@@ -10150,12 +10147,12 @@ ssize_t btrfs_encoded_read(struct kiocb *iocb, struct iov_iter *iter,
 	encoded->len = min_t(u64, extent_map_end(em),
 			     inode->vfs_inode.i_size) - iocb->ki_pos;
 	if (em->block_start == EXTENT_MAP_HOLE ||
-	    test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) {
+	    (em->flags & EXTENT_FLAG_PREALLOC)) {
 		disk_bytenr = EXTENT_MAP_HOLE;
 		count = min_t(u64, count, encoded->len);
 		encoded->len = count;
 		encoded->unencoded_len = count;
-	} else if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) {
+	} else if (extent_map_is_compressed(em)) {
 		disk_bytenr = em->block_start;
 		/*
 		 * Bail if the buffer isn't large enough to return the whole
@@ -10170,7 +10167,7 @@ ssize_t btrfs_encoded_read(struct kiocb *iocb, struct iov_iter *iter,
 		encoded->unencoded_len = em->ram_bytes;
 		encoded->unencoded_offset = iocb->ki_pos - em->orig_start;
 		ret = btrfs_encoded_io_compression_from_extent(fs_info,
-							     em->compress_type);
+							       extent_map_compression(em));
 		if (ret < 0)
 			goto out_em;
 		encoded->compression = ret;
@@ -10718,7 +10715,7 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 			ret = -EINVAL;
 			goto out;
 		}
-		if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) {
+		if (extent_map_is_compressed(em)) {
 			btrfs_warn(fs_info, "swapfile must not be compressed");
 			ret = -EINVAL;
 			goto out;
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index f5d9e5f74a52..78c2770eb52f 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -2951,7 +2951,7 @@ static noinline_for_stack int setup_relocation_extent_mapping(struct inode *inod
 	em->len = end + 1 - start;
 	em->block_len = em->len;
 	em->block_start = block_start;
-	set_bit(EXTENT_FLAG_PINNED, &em->flags);
+	em->flags |= EXTENT_FLAG_PINNED;
 
 	lock_extent(&BTRFS_I(inode)->io_tree, start, end, &cached_state);
 	ret = btrfs_replace_extent_map_range(BTRFS_I(inode), em, false);
diff --git a/fs/btrfs/tests/extent-map-tests.c b/fs/btrfs/tests/extent-map-tests.c
index 59bbf714225c..253cce7ffecf 100644
--- a/fs/btrfs/tests/extent-map-tests.c
+++ b/fs/btrfs/tests/extent-map-tests.c
@@ -480,7 +480,7 @@ static int add_compressed_extent(struct btrfs_fs_info *fs_info,
 	em->len = len;
 	em->block_start = block_start;
 	em->block_len = SZ_4K;
-	set_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
+	em->flags |= EXTENT_FLAG_COMPRESS_ZLIB;
 	write_lock(&em_tree->lock);
 	ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, em->start, em->len);
 	write_unlock(&em_tree->lock);
@@ -763,7 +763,7 @@ static int test_case_7(struct btrfs_fs_info *fs_info)
 	em->len = SZ_16K;
 	em->block_start = 0;
 	em->block_len = SZ_4K;
-	set_bit(EXTENT_FLAG_PINNED, &em->flags);
+	em->flags |= EXTENT_FLAG_PINNED;
 	write_lock(&em_tree->lock);
 	ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, em->start, em->len);
 	write_unlock(&em_tree->lock);
diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c
index 492d69d2fa73..9957de9f7806 100644
--- a/fs/btrfs/tests/inode-tests.c
+++ b/fs/btrfs/tests/inode-tests.c
@@ -211,9 +211,9 @@ static void setup_file_extents(struct btrfs_root *root, u32 sectorsize)
 		      sectorsize, BTRFS_FILE_EXTENT_REG, 0, slot);
 }
 
-static unsigned long prealloc_only = 0;
-static unsigned long compressed_only = 0;
-static unsigned long vacancy_only = 0;
+static u32 prealloc_only = 0;
+static u32 compressed_only = 0;
+static u32 vacancy_only = 0;
 
 static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 {
@@ -305,7 +305,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != 0) {
-		test_err("unexpected flags set, want 0 have %lu", em->flags);
+		test_err("unexpected flags set, want 0 have %u", em->flags);
 		goto out;
 	}
 	/*
@@ -332,7 +332,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != 0) {
-		test_err("unexpected flags set, want 0 have %lu", em->flags);
+		test_err("unexpected flags set, want 0 have %u", em->flags);
 		goto out;
 	}
 	offset = em->start + em->len;
@@ -355,7 +355,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != 0) {
-		test_err("unexpected flags set, want 0 have %lu", em->flags);
+		test_err("unexpected flags set, want 0 have %u", em->flags);
 		goto out;
 	}
 	if (em->orig_start != em->start) {
@@ -383,7 +383,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != 0) {
-		test_err("unexpected flags set, want 0 have %lu", em->flags);
+		test_err("unexpected flags set, want 0 have %u", em->flags);
 		goto out;
 	}
 	if (em->orig_start != em->start) {
@@ -412,7 +412,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != 0) {
-		test_err("unexpected flags set, want 0 have %lu", em->flags);
+		test_err("unexpected flags set, want 0 have %u", em->flags);
 		goto out;
 	}
 	offset = em->start + em->len;
@@ -434,7 +434,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != 0) {
-		test_err("unexpected flags set, want 0 have %lu", em->flags);
+		test_err("unexpected flags set, want 0 have %u", em->flags);
 		goto out;
 	}
 	if (em->orig_start != orig_start) {
@@ -468,7 +468,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != prealloc_only) {
-		test_err("unexpected flags set, want %lu have %lu",
+		test_err("unexpected flags set, want %u have %u",
 			 prealloc_only, em->flags);
 		goto out;
 	}
@@ -497,7 +497,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != prealloc_only) {
-		test_err("unexpected flags set, want %lu have %lu",
+		test_err("unexpected flags set, want %u have %u",
 			 prealloc_only, em->flags);
 		goto out;
 	}
@@ -527,7 +527,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != 0) {
-		test_err("unexpected flags set, want 0 have %lu", em->flags);
+		test_err("unexpected flags set, want 0 have %u", em->flags);
 		goto out;
 	}
 	if (em->orig_start != orig_start) {
@@ -560,7 +560,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != prealloc_only) {
-		test_err("unexpected flags set, want %lu have %lu",
+		test_err("unexpected flags set, want %u have %u",
 			 prealloc_only, em->flags);
 		goto out;
 	}
@@ -595,7 +595,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != compressed_only) {
-		test_err("unexpected flags set, want %lu have %lu",
+		test_err("unexpected flags set, want %u have %u",
 			 compressed_only, em->flags);
 		goto out;
 	}
@@ -604,9 +604,9 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 			 em->start, em->orig_start);
 		goto out;
 	}
-	if (em->compress_type != BTRFS_COMPRESS_ZLIB) {
+	if (extent_map_compression(em) != BTRFS_COMPRESS_ZLIB) {
 		test_err("unexpected compress type, wanted %d, got %d",
-			 BTRFS_COMPRESS_ZLIB, em->compress_type);
+			 BTRFS_COMPRESS_ZLIB, extent_map_compression(em));
 		goto out;
 	}
 	offset = em->start + em->len;
@@ -629,7 +629,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != compressed_only) {
-		test_err("unexpected flags set, want %lu have %lu",
+		test_err("unexpected flags set, want %u have %u",
 			 compressed_only, em->flags);
 		goto out;
 	}
@@ -638,9 +638,9 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 			 em->start, em->orig_start);
 		goto out;
 	}
-	if (em->compress_type != BTRFS_COMPRESS_ZLIB) {
+	if (extent_map_compression(em) != BTRFS_COMPRESS_ZLIB) {
 		test_err("unexpected compress type, wanted %d, got %d",
-			 BTRFS_COMPRESS_ZLIB, em->compress_type);
+			 BTRFS_COMPRESS_ZLIB, extent_map_compression(em));
 		goto out;
 	}
 	disk_bytenr = em->block_start;
@@ -664,7 +664,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != 0) {
-		test_err("unexpected flags set, want 0 have %lu", em->flags);
+		test_err("unexpected flags set, want 0 have %u", em->flags);
 		goto out;
 	}
 	if (em->orig_start != em->start) {
@@ -692,7 +692,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != compressed_only) {
-		test_err("unexpected flags set, want %lu have %lu",
+		test_err("unexpected flags set, want %u have %u",
 			 compressed_only, em->flags);
 		goto out;
 	}
@@ -701,9 +701,9 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 			 em->start, orig_start);
 		goto out;
 	}
-	if (em->compress_type != BTRFS_COMPRESS_ZLIB) {
+	if (extent_map_compression(em) != BTRFS_COMPRESS_ZLIB) {
 		test_err("unexpected compress type, wanted %d, got %d",
-			 BTRFS_COMPRESS_ZLIB, em->compress_type);
+			 BTRFS_COMPRESS_ZLIB, extent_map_compression(em));
 		goto out;
 	}
 	offset = em->start + em->len;
@@ -726,7 +726,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != 0) {
-		test_err("unexpected flags set, want 0 have %lu", em->flags);
+		test_err("unexpected flags set, want 0 have %u", em->flags);
 		goto out;
 	}
 	if (em->orig_start != em->start) {
@@ -758,7 +758,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != vacancy_only) {
-		test_err("unexpected flags set, want %lu have %lu",
+		test_err("unexpected flags set, want %u have %u",
 			 vacancy_only, em->flags);
 		goto out;
 	}
@@ -786,7 +786,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != 0) {
-		test_err("unexpected flags set, want 0 have %lu", em->flags);
+		test_err("unexpected flags set, want 0 have %u", em->flags);
 		goto out;
 	}
 	if (em->orig_start != em->start) {
@@ -866,7 +866,7 @@ static int test_hole_first(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != vacancy_only) {
-		test_err("wrong flags, wanted %lu, have %lu", vacancy_only,
+		test_err("wrong flags, wanted %u, have %u", vacancy_only,
 			 em->flags);
 		goto out;
 	}
@@ -888,7 +888,7 @@ static int test_hole_first(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	if (em->flags != 0) {
-		test_err("unexpected flags set, wanted 0 got %lu",
+		test_err("unexpected flags set, wanted 0 got %u",
 			 em->flags);
 		goto out;
 	}
@@ -1095,8 +1095,8 @@ int btrfs_test_inodes(u32 sectorsize, u32 nodesize)
 
 	test_msg("running inode tests");
 
-	set_bit(EXTENT_FLAG_COMPRESSED, &compressed_only);
-	set_bit(EXTENT_FLAG_PREALLOC, &prealloc_only);
+	compressed_only |= EXTENT_FLAG_COMPRESS_ZLIB;
+	prealloc_only |= EXTENT_FLAG_PREALLOC;
 
 	ret = test_btrfs_get_extent(sectorsize, nodesize);
 	if (ret)
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index bee065851185..331fc7429952 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -4519,7 +4519,7 @@ static int log_extent_csums(struct btrfs_trans_handle *trans,
 	int ret = 0;
 
 	if (inode->flags & BTRFS_INODE_NODATASUM ||
-	    test_bit(EXTENT_FLAG_PREALLOC, &em->flags) ||
+	    (em->flags & EXTENT_FLAG_PREALLOC) ||
 	    em->block_start == EXTENT_MAP_HOLE)
 		return 0;
 
@@ -4582,7 +4582,7 @@ static int log_extent_csums(struct btrfs_trans_handle *trans,
 		return 0;
 
 	/* If we're compressed we have to save the entire range of csums. */
-	if (em->compress_type) {
+	if (extent_map_is_compressed(em)) {
 		csum_offset = 0;
 		csum_len = max(em->block_len, em->orig_block_len);
 	} else {
@@ -4622,18 +4622,20 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
 	struct btrfs_file_extent_item fi = { 0 };
 	struct extent_buffer *leaf;
 	struct btrfs_key key;
+	enum btrfs_compression_type compress_type;
 	u64 extent_offset = em->start - em->orig_start;
 	u64 block_len;
 	int ret;
 
 	btrfs_set_stack_file_extent_generation(&fi, trans->transid);
-	if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
+	if (em->flags & EXTENT_FLAG_PREALLOC)
 		btrfs_set_stack_file_extent_type(&fi, BTRFS_FILE_EXTENT_PREALLOC);
 	else
 		btrfs_set_stack_file_extent_type(&fi, BTRFS_FILE_EXTENT_REG);
 
 	block_len = max(em->block_len, em->orig_block_len);
-	if (em->compress_type != BTRFS_COMPRESS_NONE) {
+	compress_type = extent_map_compression(em);
+	if (compress_type != BTRFS_COMPRESS_NONE) {
 		btrfs_set_stack_file_extent_disk_bytenr(&fi, em->block_start);
 		btrfs_set_stack_file_extent_disk_num_bytes(&fi, block_len);
 	} else if (em->block_start < EXTENT_MAP_LAST_BYTE) {
@@ -4645,7 +4647,7 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
 	btrfs_set_stack_file_extent_offset(&fi, extent_offset);
 	btrfs_set_stack_file_extent_num_bytes(&fi, em->len);
 	btrfs_set_stack_file_extent_ram_bytes(&fi, em->ram_bytes);
-	btrfs_set_stack_file_extent_compression(&fi, em->compress_type);
+	btrfs_set_stack_file_extent_compression(&fi, compress_type);
 
 	ret = log_extent_csums(trans, inode, log, em, ctx);
 	if (ret)
@@ -4858,13 +4860,13 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 			continue;
 
 		/* We log prealloc extents beyond eof later. */
-		if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags) &&
+		if ((em->flags & EXTENT_FLAG_PREALLOC) &&
 		    em->start >= i_size_read(&inode->vfs_inode))
 			continue;
 
 		/* Need a ref to keep it from getting evicted from cache */
 		refcount_inc(&em->refs);
-		set_bit(EXTENT_FLAG_LOGGING, &em->flags);
+		em->flags |= EXTENT_FLAG_LOGGING;
 		list_add_tail(&em->list, &extents);
 		num++;
 	}
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index 31da1456f953..90b0222390e5 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -272,11 +272,13 @@ DEFINE_EVENT(btrfs__inode, btrfs_inode_evict,
 
 #define show_map_flags(flag)						\
 	__print_flags(flag, "|",					\
-		{ (1 << EXTENT_FLAG_PINNED), 		"PINNED" 	},\
-		{ (1 << EXTENT_FLAG_COMPRESSED), 	"COMPRESSED" 	},\
-		{ (1 << EXTENT_FLAG_PREALLOC), 		"PREALLOC" 	},\
-		{ (1 << EXTENT_FLAG_LOGGING),	 	"LOGGING" 	},\
-		{ (1 << EXTENT_FLAG_FILLING),		"FILLING"	})
+		{ EXTENT_FLAG_PINNED,		"PINNED"	},\
+		{ EXTENT_FLAG_COMPRESS_ZLIB,	"COMPRESS_ZLIB"	},\
+		{ EXTENT_FLAG_COMPRESS_LZO,	"COMPRESS_LZO"	},\
+		{ EXTENT_FLAG_COMPRESS_ZSTD,	"COMPRESS_ZSTD"	},\
+		{ EXTENT_FLAG_PREALLOC,		"PREALLOC"	},\
+		{ EXTENT_FLAG_LOGGING,		"LOGGING"	},\
+		{ EXTENT_FLAG_FILLING,		"FILLING"	})
 
 TRACE_EVENT_CONDITION(btrfs_get_extent,
 
@@ -295,9 +297,8 @@ TRACE_EVENT_CONDITION(btrfs_get_extent,
 		__field(	u64,  orig_start	)
 		__field(	u64,  block_start	)
 		__field(	u64,  block_len		)
-		__field(	unsigned long,  flags	)
+		__field(	u32,  flags		)
 		__field(	int,  refs		)
-		__field(	unsigned int,  compress_type	)
 	),
 
 	TP_fast_assign_btrfs(root->fs_info,
@@ -310,13 +311,11 @@ TRACE_EVENT_CONDITION(btrfs_get_extent,
 		__entry->block_len	= map->block_len;
 		__entry->flags		= map->flags;
 		__entry->refs		= refcount_read(&map->refs);
-		__entry->compress_type	= map->compress_type;
 	),
 
 	TP_printk_btrfs("root=%llu(%s) ino=%llu start=%llu len=%llu "
 		  "orig_start=%llu block_start=%llu(%s) "
-		  "block_len=%llu flags=%s refs=%u "
-		  "compress_type=%u",
+		  "block_len=%llu flags=%s refs=%u",
 		  show_root_type(__entry->root_objectid),
 		  __entry->ino,
 		  __entry->start,
@@ -325,7 +324,7 @@ TRACE_EVENT_CONDITION(btrfs_get_extent,
 		  show_map_type(__entry->block_start),
 		  __entry->block_len,
 		  show_map_flags(__entry->flags),
-		  __entry->refs, __entry->compress_type)
+		  __entry->refs)
 );
 
 TRACE_EVENT(btrfs_handle_em_exist,
-- 
cgit v1.2.3


From f8fa5d76925991976b3e7076f9d1052515ec1fca Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Fri, 15 Dec 2023 13:24:10 -0700
Subject: cred: switch to using atomic_long_t

There are multiple ways to grab references to credentials, and the only
protection we have against overflowing it is the memory required to do
so.

With memory sizes only moving in one direction, let's bump the reference
count to 64-bit and move it outside the realm of feasibly overflowing.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/cred.h |  8 +++----
 kernel/cred.c        | 64 ++++++++++++++++++++++++++--------------------------
 2 files changed, 36 insertions(+), 36 deletions(-)

(limited to 'include')

diff --git a/include/linux/cred.h b/include/linux/cred.h
index af8d353a4b86..a3383f8efb8f 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -109,7 +109,7 @@ static inline int groups_search(const struct group_info *group_info, kgid_t grp)
  * same context as task->real_cred.
  */
 struct cred {
-	atomic_t	usage;
+	atomic_long_t	usage;
 #ifdef CONFIG_DEBUG_CREDENTIALS
 	atomic_t	subscribers;	/* number of processes subscribed */
 	void		*put_addr;
@@ -229,7 +229,7 @@ static inline bool cap_ambient_invariant_ok(const struct cred *cred)
  */
 static inline struct cred *get_new_cred_many(struct cred *cred, int nr)
 {
-	atomic_add(nr, &cred->usage);
+	atomic_long_add(nr, &cred->usage);
 	return cred;
 }
 
@@ -288,7 +288,7 @@ static inline const struct cred *get_cred_rcu(const struct cred *cred)
 	struct cred *nonconst_cred = (struct cred *) cred;
 	if (!cred)
 		return NULL;
-	if (!atomic_inc_not_zero(&nonconst_cred->usage))
+	if (!atomic_long_inc_not_zero(&nonconst_cred->usage))
 		return NULL;
 	validate_creds(cred);
 	nonconst_cred->non_rcu = 0;
@@ -313,7 +313,7 @@ static inline void put_cred_many(const struct cred *_cred, int nr)
 
 	if (cred) {
 		validate_creds(cred);
-		if (atomic_sub_and_test(nr, &cred->usage))
+		if (atomic_long_sub_and_test(nr, &cred->usage))
 			__put_cred(cred);
 	}
 }
diff --git a/kernel/cred.c b/kernel/cred.c
index 3c714cb31660..4a6cd0f0fef5 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -102,17 +102,17 @@ static void put_cred_rcu(struct rcu_head *rcu)
 
 #ifdef CONFIG_DEBUG_CREDENTIALS
 	if (cred->magic != CRED_MAGIC_DEAD ||
-	    atomic_read(&cred->usage) != 0 ||
+	    atomic_long_read(&cred->usage) != 0 ||
 	    read_cred_subscribers(cred) != 0)
 		panic("CRED: put_cred_rcu() sees %p with"
-		      " mag %x, put %p, usage %d, subscr %d\n",
+		      " mag %x, put %p, usage %ld, subscr %d\n",
 		      cred, cred->magic, cred->put_addr,
-		      atomic_read(&cred->usage),
+		      atomic_long_read(&cred->usage),
 		      read_cred_subscribers(cred));
 #else
-	if (atomic_read(&cred->usage) != 0)
-		panic("CRED: put_cred_rcu() sees %p with usage %d\n",
-		      cred, atomic_read(&cred->usage));
+	if (atomic_long_read(&cred->usage) != 0)
+		panic("CRED: put_cred_rcu() sees %p with usage %ld\n",
+		      cred, atomic_long_read(&cred->usage));
 #endif
 
 	security_cred_free(cred);
@@ -137,11 +137,11 @@ static void put_cred_rcu(struct rcu_head *rcu)
  */
 void __put_cred(struct cred *cred)
 {
-	kdebug("__put_cred(%p{%d,%d})", cred,
-	       atomic_read(&cred->usage),
+	kdebug("__put_cred(%p{%ld,%d})", cred,
+	       atomic_long_read(&cred->usage),
 	       read_cred_subscribers(cred));
 
-	BUG_ON(atomic_read(&cred->usage) != 0);
+	BUG_ON(atomic_long_read(&cred->usage) != 0);
 #ifdef CONFIG_DEBUG_CREDENTIALS
 	BUG_ON(read_cred_subscribers(cred) != 0);
 	cred->magic = CRED_MAGIC_DEAD;
@@ -164,8 +164,8 @@ void exit_creds(struct task_struct *tsk)
 {
 	struct cred *real_cred, *cred;
 
-	kdebug("exit_creds(%u,%p,%p,{%d,%d})", tsk->pid, tsk->real_cred, tsk->cred,
-	       atomic_read(&tsk->cred->usage),
+	kdebug("exit_creds(%u,%p,%p,{%ld,%d})", tsk->pid, tsk->real_cred, tsk->cred,
+	       atomic_long_read(&tsk->cred->usage),
 	       read_cred_subscribers(tsk->cred));
 
 	real_cred = (struct cred *) tsk->real_cred;
@@ -230,7 +230,7 @@ struct cred *cred_alloc_blank(void)
 	if (!new)
 		return NULL;
 
-	atomic_set(&new->usage, 1);
+	atomic_long_set(&new->usage, 1);
 #ifdef CONFIG_DEBUG_CREDENTIALS
 	new->magic = CRED_MAGIC;
 #endif
@@ -276,7 +276,7 @@ struct cred *prepare_creds(void)
 	memcpy(new, old, sizeof(struct cred));
 
 	new->non_rcu = 0;
-	atomic_set(&new->usage, 1);
+	atomic_long_set(&new->usage, 1);
 	set_cred_subscribers(new, 0);
 	get_group_info(new->group_info);
 	get_uid(new->user);
@@ -363,8 +363,8 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
 	    ) {
 		p->real_cred = get_cred_many(p->cred, 2);
 		alter_cred_subscribers(p->cred, 2);
-		kdebug("share_creds(%p{%d,%d})",
-		       p->cred, atomic_read(&p->cred->usage),
+		kdebug("share_creds(%p{%ld,%d})",
+		       p->cred, atomic_long_read(&p->cred->usage),
 		       read_cred_subscribers(p->cred));
 		inc_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1);
 		return 0;
@@ -457,8 +457,8 @@ int commit_creds(struct cred *new)
 	struct task_struct *task = current;
 	const struct cred *old = task->real_cred;
 
-	kdebug("commit_creds(%p{%d,%d})", new,
-	       atomic_read(&new->usage),
+	kdebug("commit_creds(%p{%ld,%d})", new,
+	       atomic_long_read(&new->usage),
 	       read_cred_subscribers(new));
 
 	BUG_ON(task->cred != old);
@@ -467,7 +467,7 @@ int commit_creds(struct cred *new)
 	validate_creds(old);
 	validate_creds(new);
 #endif
-	BUG_ON(atomic_read(&new->usage) < 1);
+	BUG_ON(atomic_long_read(&new->usage) < 1);
 
 	get_cred(new); /* we will require a ref for the subj creds too */
 
@@ -539,14 +539,14 @@ EXPORT_SYMBOL(commit_creds);
  */
 void abort_creds(struct cred *new)
 {
-	kdebug("abort_creds(%p{%d,%d})", new,
-	       atomic_read(&new->usage),
+	kdebug("abort_creds(%p{%ld,%d})", new,
+	       atomic_long_read(&new->usage),
 	       read_cred_subscribers(new));
 
 #ifdef CONFIG_DEBUG_CREDENTIALS
 	BUG_ON(read_cred_subscribers(new) != 0);
 #endif
-	BUG_ON(atomic_read(&new->usage) < 1);
+	BUG_ON(atomic_long_read(&new->usage) < 1);
 	put_cred(new);
 }
 EXPORT_SYMBOL(abort_creds);
@@ -562,8 +562,8 @@ const struct cred *override_creds(const struct cred *new)
 {
 	const struct cred *old = current->cred;
 
-	kdebug("override_creds(%p{%d,%d})", new,
-	       atomic_read(&new->usage),
+	kdebug("override_creds(%p{%ld,%d})", new,
+	       atomic_long_read(&new->usage),
 	       read_cred_subscribers(new));
 
 	validate_creds(old);
@@ -585,8 +585,8 @@ const struct cred *override_creds(const struct cred *new)
 	rcu_assign_pointer(current->cred, new);
 	alter_cred_subscribers(old, -1);
 
-	kdebug("override_creds() = %p{%d,%d}", old,
-	       atomic_read(&old->usage),
+	kdebug("override_creds() = %p{%ld,%d}", old,
+	       atomic_long_read(&old->usage),
 	       read_cred_subscribers(old));
 	return old;
 }
@@ -603,8 +603,8 @@ void revert_creds(const struct cred *old)
 {
 	const struct cred *override = current->cred;
 
-	kdebug("revert_creds(%p{%d,%d})", old,
-	       atomic_read(&old->usage),
+	kdebug("revert_creds(%p{%ld,%d})", old,
+	       atomic_long_read(&old->usage),
 	       read_cred_subscribers(old));
 
 	validate_creds(old);
@@ -735,7 +735,7 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
 
 	*new = *old;
 	new->non_rcu = 0;
-	atomic_set(&new->usage, 1);
+	atomic_long_set(&new->usage, 1);
 	set_cred_subscribers(new, 0);
 	get_uid(new->user);
 	get_user_ns(new->user_ns);
@@ -849,8 +849,8 @@ static void dump_invalid_creds(const struct cred *cred, const char *label,
 	       cred == tsk->cred ? "[eff]" : "");
 	pr_err("->magic=%x, put_addr=%p\n",
 	       cred->magic, cred->put_addr);
-	pr_err("->usage=%d, subscr=%d\n",
-	       atomic_read(&cred->usage),
+	pr_err("->usage=%ld, subscr=%d\n",
+	       atomic_long_read(&cred->usage),
 	       read_cred_subscribers(cred));
 	pr_err("->*uid = { %d,%d,%d,%d }\n",
 		from_kuid_munged(&init_user_ns, cred->uid),
@@ -922,9 +922,9 @@ EXPORT_SYMBOL(__validate_process_creds);
  */
 void validate_creds_for_do_exit(struct task_struct *tsk)
 {
-	kdebug("validate_creds_for_do_exit(%p,%p{%d,%d})",
+	kdebug("validate_creds_for_do_exit(%p,%p{%ld,%d})",
 	       tsk->real_cred, tsk->cred,
-	       atomic_read(&tsk->cred->usage),
+	       atomic_long_read(&tsk->cred->usage),
 	       read_cred_subscribers(tsk->cred));
 
 	__validate_process_creds(tsk, __FILE__, __LINE__);
-- 
cgit v1.2.3


From ae1914174a63a558113e80d24ccac2773f9f7b2b Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Fri, 15 Dec 2023 13:40:57 -0700
Subject: cred: get rid of CONFIG_DEBUG_CREDENTIALS

This code is rarely (never?) enabled by distros, and it hasn't caught
anything in decades. Let's kill off this legacy debug code.

Suggested-by: Linus Torvalds <torvalds@linuxfoundation.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/powerpc/configs/skiroot_defconfig    |   1 -
 arch/s390/configs/debug_defconfig         |   1 -
 fs/nfsd/auth.c                            |   4 -
 fs/nfsd/nfssvc.c                          |   1 -
 fs/nfsd/vfs.c                             |   9 +-
 fs/open.c                                 |   3 -
 include/linux/cred.h                      |  50 -------
 kernel/cred.c                             | 231 +++---------------------------
 kernel/exit.c                             |   3 -
 lib/Kconfig.debug                         |  15 --
 net/sunrpc/auth.c                         |   3 -
 security/selinux/hooks.c                  |   6 -
 tools/objtool/noreturns.h                 |   1 -
 tools/testing/selftests/bpf/config.x86_64 |   1 -
 tools/testing/selftests/hid/config.common |   1 -
 15 files changed, 17 insertions(+), 313 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig
index 8d3eacb50d56..9d44e6630908 100644
--- a/arch/powerpc/configs/skiroot_defconfig
+++ b/arch/powerpc/configs/skiroot_defconfig
@@ -301,7 +301,6 @@ CONFIG_WQ_WATCHDOG=y
 CONFIG_DEBUG_SG=y
 CONFIG_DEBUG_NOTIFIERS=y
 CONFIG_BUG_ON_DATA_CORRUPTION=y
-CONFIG_DEBUG_CREDENTIALS=y
 # CONFIG_FTRACE is not set
 CONFIG_XMON=y
 # CONFIG_RUNTIME_TESTING_MENU is not set
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index 438cd92e6080..dd0608629310 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -834,7 +834,6 @@ CONFIG_DEBUG_IRQFLAGS=y
 CONFIG_DEBUG_LIST=y
 CONFIG_DEBUG_SG=y
 CONFIG_DEBUG_NOTIFIERS=y
-CONFIG_DEBUG_CREDENTIALS=y
 CONFIG_RCU_TORTURE_TEST=m
 CONFIG_RCU_REF_SCALE_TEST=m
 CONFIG_RCU_CPU_STALL_TIMEOUT=300
diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c
index fdf2aad73470..e6beaaf4f170 100644
--- a/fs/nfsd/auth.c
+++ b/fs/nfsd/auth.c
@@ -26,8 +26,6 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp)
 	int i;
 	int flags = nfsexp_flags(rqstp, exp);
 
-	validate_process_creds();
-
 	/* discard any old override before preparing the new set */
 	revert_creds(get_cred(current_real_cred()));
 	new = prepare_creds();
@@ -81,10 +79,8 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp)
 	else
 		new->cap_effective = cap_raise_nfsd_set(new->cap_effective,
 							new->cap_permitted);
-	validate_process_creds();
 	put_cred(override_creds(new));
 	put_cred(new);
-	validate_process_creds();
 	return 0;
 
 oom:
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index fe61d9bbcc1f..5014ab87d313 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -955,7 +955,6 @@ nfsd(void *vrqstp)
 		rqstp->rq_server->sv_maxconn = nn->max_connections;
 
 		svc_recv(rqstp);
-		validate_process_creds();
 	}
 
 	atomic_dec(&nfsdstats.th_cnt);
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index fbbea7498f02..e01e4e2acbd9 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -901,7 +901,6 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type,
 	int host_err;
 	bool retried = false;
 
-	validate_process_creds();
 	/*
 	 * If we get here, then the client has already done an "open",
 	 * and (hopefully) checked permission - so allow OWNER_OVERRIDE
@@ -926,7 +925,6 @@ retry:
 		}
 		err = nfserrno(host_err);
 	}
-	validate_process_creds();
 	return err;
 }
 
@@ -943,12 +941,7 @@ int
 nfsd_open_verified(struct svc_rqst *rqstp, struct svc_fh *fhp, int may_flags,
 		   struct file **filp)
 {
-	int err;
-
-	validate_process_creds();
-	err = __nfsd_open(rqstp, fhp, S_IFREG, may_flags, filp);
-	validate_process_creds();
-	return err;
+	return __nfsd_open(rqstp, fhp, S_IFREG, may_flags, filp);
 }
 
 /*
diff --git a/fs/open.c b/fs/open.c
index 02dc608d40d8..3494a9cd8046 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -1088,8 +1088,6 @@ struct file *dentry_open(const struct path *path, int flags,
 	int error;
 	struct file *f;
 
-	validate_creds(cred);
-
 	/* We must always pass in a valid mount pointer. */
 	BUG_ON(!path->mnt);
 
@@ -1128,7 +1126,6 @@ struct file *dentry_create(const struct path *path, int flags, umode_t mode,
 	struct file *f;
 	int error;
 
-	validate_creds(cred);
 	f = alloc_empty_file(flags, cred);
 	if (IS_ERR(f))
 		return f;
diff --git a/include/linux/cred.h b/include/linux/cred.h
index a3383f8efb8f..2976f534a7a3 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -110,13 +110,6 @@ static inline int groups_search(const struct group_info *group_info, kgid_t grp)
  */
 struct cred {
 	atomic_long_t	usage;
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	atomic_t	subscribers;	/* number of processes subscribed */
-	void		*put_addr;
-	unsigned	magic;
-#define CRED_MAGIC	0x43736564
-#define CRED_MAGIC_DEAD	0x44656144
-#endif
 	kuid_t		uid;		/* real UID of the task */
 	kgid_t		gid;		/* real GID of the task */
 	kuid_t		suid;		/* saved UID of the task */
@@ -172,46 +165,6 @@ extern int cred_fscmp(const struct cred *, const struct cred *);
 extern void __init cred_init(void);
 extern int set_cred_ucounts(struct cred *);
 
-/*
- * check for validity of credentials
- */
-#ifdef CONFIG_DEBUG_CREDENTIALS
-extern void __noreturn __invalid_creds(const struct cred *, const char *, unsigned);
-extern void __validate_process_creds(struct task_struct *,
-				     const char *, unsigned);
-
-extern bool creds_are_invalid(const struct cred *cred);
-
-static inline void __validate_creds(const struct cred *cred,
-				    const char *file, unsigned line)
-{
-	if (unlikely(creds_are_invalid(cred)))
-		__invalid_creds(cred, file, line);
-}
-
-#define validate_creds(cred)				\
-do {							\
-	__validate_creds((cred), __FILE__, __LINE__);	\
-} while(0)
-
-#define validate_process_creds()				\
-do {								\
-	__validate_process_creds(current, __FILE__, __LINE__);	\
-} while(0)
-
-extern void validate_creds_for_do_exit(struct task_struct *);
-#else
-static inline void validate_creds(const struct cred *cred)
-{
-}
-static inline void validate_creds_for_do_exit(struct task_struct *tsk)
-{
-}
-static inline void validate_process_creds(void)
-{
-}
-#endif
-
 static inline bool cap_ambient_invariant_ok(const struct cred *cred)
 {
 	return cap_issubset(cred->cap_ambient,
@@ -264,7 +217,6 @@ static inline const struct cred *get_cred_many(const struct cred *cred, int nr)
 	struct cred *nonconst_cred = (struct cred *) cred;
 	if (!cred)
 		return cred;
-	validate_creds(cred);
 	nonconst_cred->non_rcu = 0;
 	return get_new_cred_many(nonconst_cred, nr);
 }
@@ -290,7 +242,6 @@ static inline const struct cred *get_cred_rcu(const struct cred *cred)
 		return NULL;
 	if (!atomic_long_inc_not_zero(&nonconst_cred->usage))
 		return NULL;
-	validate_creds(cred);
 	nonconst_cred->non_rcu = 0;
 	return cred;
 }
@@ -312,7 +263,6 @@ static inline void put_cred_many(const struct cred *_cred, int nr)
 	struct cred *cred = (struct cred *) _cred;
 
 	if (cred) {
-		validate_creds(cred);
 		if (atomic_long_sub_and_test(nr, &cred->usage))
 			__put_cred(cred);
 	}
diff --git a/kernel/cred.c b/kernel/cred.c
index 4a6cd0f0fef5..c033a201c808 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -43,10 +43,6 @@ static struct group_info init_groups = { .usage = REFCOUNT_INIT(2) };
  */
 struct cred init_cred = {
 	.usage			= ATOMIC_INIT(4),
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	.subscribers		= ATOMIC_INIT(2),
-	.magic			= CRED_MAGIC,
-#endif
 	.uid			= GLOBAL_ROOT_UID,
 	.gid			= GLOBAL_ROOT_GID,
 	.suid			= GLOBAL_ROOT_UID,
@@ -66,31 +62,6 @@ struct cred init_cred = {
 	.ucounts		= &init_ucounts,
 };
 
-static inline void set_cred_subscribers(struct cred *cred, int n)
-{
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	atomic_set(&cred->subscribers, n);
-#endif
-}
-
-static inline int read_cred_subscribers(const struct cred *cred)
-{
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	return atomic_read(&cred->subscribers);
-#else
-	return 0;
-#endif
-}
-
-static inline void alter_cred_subscribers(const struct cred *_cred, int n)
-{
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	struct cred *cred = (struct cred *) _cred;
-
-	atomic_add(n, &cred->subscribers);
-#endif
-}
-
 /*
  * The RCU callback to actually dispose of a set of credentials
  */
@@ -100,20 +71,9 @@ static void put_cred_rcu(struct rcu_head *rcu)
 
 	kdebug("put_cred_rcu(%p)", cred);
 
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	if (cred->magic != CRED_MAGIC_DEAD ||
-	    atomic_long_read(&cred->usage) != 0 ||
-	    read_cred_subscribers(cred) != 0)
-		panic("CRED: put_cred_rcu() sees %p with"
-		      " mag %x, put %p, usage %ld, subscr %d\n",
-		      cred, cred->magic, cred->put_addr,
-		      atomic_long_read(&cred->usage),
-		      read_cred_subscribers(cred));
-#else
 	if (atomic_long_read(&cred->usage) != 0)
 		panic("CRED: put_cred_rcu() sees %p with usage %ld\n",
 		      cred, atomic_long_read(&cred->usage));
-#endif
 
 	security_cred_free(cred);
 	key_put(cred->session_keyring);
@@ -137,16 +97,10 @@ static void put_cred_rcu(struct rcu_head *rcu)
  */
 void __put_cred(struct cred *cred)
 {
-	kdebug("__put_cred(%p{%ld,%d})", cred,
-	       atomic_long_read(&cred->usage),
-	       read_cred_subscribers(cred));
+	kdebug("__put_cred(%p{%ld})", cred,
+	       atomic_long_read(&cred->usage));
 
 	BUG_ON(atomic_long_read(&cred->usage) != 0);
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	BUG_ON(read_cred_subscribers(cred) != 0);
-	cred->magic = CRED_MAGIC_DEAD;
-	cred->put_addr = __builtin_return_address(0);
-#endif
 	BUG_ON(cred == current->cred);
 	BUG_ON(cred == current->real_cred);
 
@@ -164,9 +118,8 @@ void exit_creds(struct task_struct *tsk)
 {
 	struct cred *real_cred, *cred;
 
-	kdebug("exit_creds(%u,%p,%p,{%ld,%d})", tsk->pid, tsk->real_cred, tsk->cred,
-	       atomic_long_read(&tsk->cred->usage),
-	       read_cred_subscribers(tsk->cred));
+	kdebug("exit_creds(%u,%p,%p,{%ld})", tsk->pid, tsk->real_cred, tsk->cred,
+	       atomic_long_read(&tsk->cred->usage));
 
 	real_cred = (struct cred *) tsk->real_cred;
 	tsk->real_cred = NULL;
@@ -174,15 +127,10 @@ void exit_creds(struct task_struct *tsk)
 	cred = (struct cred *) tsk->cred;
 	tsk->cred = NULL;
 
-	validate_creds(cred);
 	if (real_cred == cred) {
-		alter_cred_subscribers(cred, -2);
 		put_cred_many(cred, 2);
 	} else {
-		validate_creds(real_cred);
-		alter_cred_subscribers(real_cred, -1);
 		put_cred(real_cred);
-		alter_cred_subscribers(cred, -1);
 		put_cred(cred);
 	}
 
@@ -231,9 +179,6 @@ struct cred *cred_alloc_blank(void)
 		return NULL;
 
 	atomic_long_set(&new->usage, 1);
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	new->magic = CRED_MAGIC;
-#endif
 	if (security_cred_alloc_blank(new, GFP_KERNEL_ACCOUNT) < 0)
 		goto error;
 
@@ -264,8 +209,6 @@ struct cred *prepare_creds(void)
 	const struct cred *old;
 	struct cred *new;
 
-	validate_process_creds();
-
 	new = kmem_cache_alloc(cred_jar, GFP_KERNEL);
 	if (!new)
 		return NULL;
@@ -277,7 +220,6 @@ struct cred *prepare_creds(void)
 
 	new->non_rcu = 0;
 	atomic_long_set(&new->usage, 1);
-	set_cred_subscribers(new, 0);
 	get_group_info(new->group_info);
 	get_uid(new->user);
 	get_user_ns(new->user_ns);
@@ -300,7 +242,6 @@ struct cred *prepare_creds(void)
 	if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0)
 		goto error;
 
-	validate_creds(new);
 	return new;
 
 error:
@@ -362,10 +303,8 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
 		clone_flags & CLONE_THREAD
 	    ) {
 		p->real_cred = get_cred_many(p->cred, 2);
-		alter_cred_subscribers(p->cred, 2);
-		kdebug("share_creds(%p{%ld,%d})",
-		       p->cred, atomic_long_read(&p->cred->usage),
-		       read_cred_subscribers(p->cred));
+		kdebug("share_creds(%p{%ld})",
+		       p->cred, atomic_long_read(&p->cred->usage));
 		inc_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1);
 		return 0;
 	}
@@ -404,8 +343,6 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
 
 	p->cred = p->real_cred = get_cred(new);
 	inc_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1);
-	alter_cred_subscribers(new, 2);
-	validate_creds(new);
 	return 0;
 
 error_put:
@@ -457,16 +394,10 @@ int commit_creds(struct cred *new)
 	struct task_struct *task = current;
 	const struct cred *old = task->real_cred;
 
-	kdebug("commit_creds(%p{%ld,%d})", new,
-	       atomic_long_read(&new->usage),
-	       read_cred_subscribers(new));
+	kdebug("commit_creds(%p{%ld})", new,
+	       atomic_long_read(&new->usage));
 
 	BUG_ON(task->cred != old);
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	BUG_ON(read_cred_subscribers(old) < 2);
-	validate_creds(old);
-	validate_creds(new);
-#endif
 	BUG_ON(atomic_long_read(&new->usage) < 1);
 
 	get_cred(new); /* we will require a ref for the subj creds too */
@@ -502,14 +433,12 @@ int commit_creds(struct cred *new)
 	 * RLIMIT_NPROC limits on user->processes have already been checked
 	 * in set_user().
 	 */
-	alter_cred_subscribers(new, 2);
 	if (new->user != old->user || new->user_ns != old->user_ns)
 		inc_rlimit_ucounts(new->ucounts, UCOUNT_RLIMIT_NPROC, 1);
 	rcu_assign_pointer(task->real_cred, new);
 	rcu_assign_pointer(task->cred, new);
 	if (new->user != old->user || new->user_ns != old->user_ns)
 		dec_rlimit_ucounts(old->ucounts, UCOUNT_RLIMIT_NPROC, 1);
-	alter_cred_subscribers(old, -2);
 
 	/* send notifications */
 	if (!uid_eq(new->uid,   old->uid)  ||
@@ -539,13 +468,9 @@ EXPORT_SYMBOL(commit_creds);
  */
 void abort_creds(struct cred *new)
 {
-	kdebug("abort_creds(%p{%ld,%d})", new,
-	       atomic_long_read(&new->usage),
-	       read_cred_subscribers(new));
+	kdebug("abort_creds(%p{%ld})", new,
+	       atomic_long_read(&new->usage));
 
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	BUG_ON(read_cred_subscribers(new) != 0);
-#endif
 	BUG_ON(atomic_long_read(&new->usage) < 1);
 	put_cred(new);
 }
@@ -562,12 +487,8 @@ const struct cred *override_creds(const struct cred *new)
 {
 	const struct cred *old = current->cred;
 
-	kdebug("override_creds(%p{%ld,%d})", new,
-	       atomic_long_read(&new->usage),
-	       read_cred_subscribers(new));
-
-	validate_creds(old);
-	validate_creds(new);
+	kdebug("override_creds(%p{%ld})", new,
+	       atomic_long_read(&new->usage));
 
 	/*
 	 * NOTE! This uses 'get_new_cred()' rather than 'get_cred()'.
@@ -576,18 +497,12 @@ const struct cred *override_creds(const struct cred *new)
 	 * we are only installing the cred into the thread-synchronous
 	 * '->cred' pointer, not the '->real_cred' pointer that is
 	 * visible to other threads under RCU.
-	 *
-	 * Also note that we did validate_creds() manually, not depending
-	 * on the validation in 'get_cred()'.
 	 */
 	get_new_cred((struct cred *)new);
-	alter_cred_subscribers(new, 1);
 	rcu_assign_pointer(current->cred, new);
-	alter_cred_subscribers(old, -1);
 
-	kdebug("override_creds() = %p{%ld,%d}", old,
-	       atomic_long_read(&old->usage),
-	       read_cred_subscribers(old));
+	kdebug("override_creds() = %p{%ld}", old,
+	       atomic_long_read(&old->usage));
 	return old;
 }
 EXPORT_SYMBOL(override_creds);
@@ -603,15 +518,10 @@ void revert_creds(const struct cred *old)
 {
 	const struct cred *override = current->cred;
 
-	kdebug("revert_creds(%p{%ld,%d})", old,
-	       atomic_long_read(&old->usage),
-	       read_cred_subscribers(old));
+	kdebug("revert_creds(%p{%ld})", old,
+	       atomic_long_read(&old->usage));
 
-	validate_creds(old);
-	validate_creds(override);
-	alter_cred_subscribers(old, 1);
 	rcu_assign_pointer(current->cred, old);
-	alter_cred_subscribers(override, -1);
 	put_cred(override);
 }
 EXPORT_SYMBOL(revert_creds);
@@ -731,12 +641,10 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
 	kdebug("prepare_kernel_cred() alloc %p", new);
 
 	old = get_task_cred(daemon);
-	validate_creds(old);
 
 	*new = *old;
 	new->non_rcu = 0;
 	atomic_long_set(&new->usage, 1);
-	set_cred_subscribers(new, 0);
 	get_uid(new->user);
 	get_user_ns(new->user_ns);
 	get_group_info(new->group_info);
@@ -760,7 +668,6 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
 		goto error;
 
 	put_cred(old);
-	validate_creds(new);
 	return new;
 
 error:
@@ -825,109 +732,3 @@ int set_create_files_as(struct cred *new, struct inode *inode)
 	return security_kernel_create_files_as(new, inode);
 }
 EXPORT_SYMBOL(set_create_files_as);
-
-#ifdef CONFIG_DEBUG_CREDENTIALS
-
-bool creds_are_invalid(const struct cred *cred)
-{
-	if (cred->magic != CRED_MAGIC)
-		return true;
-	return false;
-}
-EXPORT_SYMBOL(creds_are_invalid);
-
-/*
- * dump invalid credentials
- */
-static void dump_invalid_creds(const struct cred *cred, const char *label,
-			       const struct task_struct *tsk)
-{
-	pr_err("%s credentials: %p %s%s%s\n",
-	       label, cred,
-	       cred == &init_cred ? "[init]" : "",
-	       cred == tsk->real_cred ? "[real]" : "",
-	       cred == tsk->cred ? "[eff]" : "");
-	pr_err("->magic=%x, put_addr=%p\n",
-	       cred->magic, cred->put_addr);
-	pr_err("->usage=%ld, subscr=%d\n",
-	       atomic_long_read(&cred->usage),
-	       read_cred_subscribers(cred));
-	pr_err("->*uid = { %d,%d,%d,%d }\n",
-		from_kuid_munged(&init_user_ns, cred->uid),
-		from_kuid_munged(&init_user_ns, cred->euid),
-		from_kuid_munged(&init_user_ns, cred->suid),
-		from_kuid_munged(&init_user_ns, cred->fsuid));
-	pr_err("->*gid = { %d,%d,%d,%d }\n",
-		from_kgid_munged(&init_user_ns, cred->gid),
-		from_kgid_munged(&init_user_ns, cred->egid),
-		from_kgid_munged(&init_user_ns, cred->sgid),
-		from_kgid_munged(&init_user_ns, cred->fsgid));
-#ifdef CONFIG_SECURITY
-	pr_err("->security is %p\n", cred->security);
-	if ((unsigned long) cred->security >= PAGE_SIZE &&
-	    (((unsigned long) cred->security & 0xffffff00) !=
-	     (POISON_FREE << 24 | POISON_FREE << 16 | POISON_FREE << 8)))
-		pr_err("->security {%x, %x}\n",
-		       ((u32*)cred->security)[0],
-		       ((u32*)cred->security)[1]);
-#endif
-}
-
-/*
- * report use of invalid credentials
- */
-void __noreturn __invalid_creds(const struct cred *cred, const char *file, unsigned line)
-{
-	pr_err("Invalid credentials\n");
-	pr_err("At %s:%u\n", file, line);
-	dump_invalid_creds(cred, "Specified", current);
-	BUG();
-}
-EXPORT_SYMBOL(__invalid_creds);
-
-/*
- * check the credentials on a process
- */
-void __validate_process_creds(struct task_struct *tsk,
-			      const char *file, unsigned line)
-{
-	if (tsk->cred == tsk->real_cred) {
-		if (unlikely(read_cred_subscribers(tsk->cred) < 2 ||
-			     creds_are_invalid(tsk->cred)))
-			goto invalid_creds;
-	} else {
-		if (unlikely(read_cred_subscribers(tsk->real_cred) < 1 ||
-			     read_cred_subscribers(tsk->cred) < 1 ||
-			     creds_are_invalid(tsk->real_cred) ||
-			     creds_are_invalid(tsk->cred)))
-			goto invalid_creds;
-	}
-	return;
-
-invalid_creds:
-	pr_err("Invalid process credentials\n");
-	pr_err("At %s:%u\n", file, line);
-
-	dump_invalid_creds(tsk->real_cred, "Real", tsk);
-	if (tsk->cred != tsk->real_cred)
-		dump_invalid_creds(tsk->cred, "Effective", tsk);
-	else
-		pr_err("Effective creds == Real creds\n");
-	BUG();
-}
-EXPORT_SYMBOL(__validate_process_creds);
-
-/*
- * check creds for do_exit()
- */
-void validate_creds_for_do_exit(struct task_struct *tsk)
-{
-	kdebug("validate_creds_for_do_exit(%p,%p{%ld,%d})",
-	       tsk->real_cred, tsk->cred,
-	       atomic_long_read(&tsk->cred->usage),
-	       read_cred_subscribers(tsk->cred));
-
-	__validate_process_creds(tsk, __FILE__, __LINE__);
-}
-
-#endif /* CONFIG_DEBUG_CREDENTIALS */
diff --git a/kernel/exit.c b/kernel/exit.c
index ee9f43bed49a..aedc0832c9f4 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -824,8 +824,6 @@ void __noreturn do_exit(long code)
 	ptrace_event(PTRACE_EVENT_EXIT, code);
 	user_events_exit(tsk);
 
-	validate_creds_for_do_exit(tsk);
-
 	io_uring_files_cancel();
 	exit_signals(tsk);  /* sets PF_EXITING */
 
@@ -909,7 +907,6 @@ void __noreturn do_exit(long code)
 	if (tsk->task_frag.page)
 		put_page(tsk->task_frag.page);
 
-	validate_creds_for_do_exit(tsk);
 	exit_task_stack_account(tsk);
 
 	check_stack_usage();
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index cc7d53d9dc01..4405f81248fb 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1739,21 +1739,6 @@ config DEBUG_MAPLE_TREE
 
 endmenu
 
-config DEBUG_CREDENTIALS
-	bool "Debug credential management"
-	depends on DEBUG_KERNEL
-	help
-	  Enable this to turn on some debug checking for credential
-	  management.  The additional code keeps track of the number of
-	  pointers from task_structs to any given cred struct, and checks to
-	  see that this number never exceeds the usage count of the cred
-	  struct.
-
-	  Furthermore, if SELinux is enabled, this also checks that the
-	  security pointer in the cred struct is never seen to be invalid.
-
-	  If unsure, say N.
-
 source "kernel/rcu/Kconfig.debug"
 
 config DEBUG_WQ_FORCE_RR_CPU
diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c
index 7bfe7d9a32aa..04534ea537c8 100644
--- a/net/sunrpc/auth.c
+++ b/net/sunrpc/auth.c
@@ -40,9 +40,6 @@ static unsigned long number_cred_unused;
 
 static struct cred machine_cred = {
 	.usage = ATOMIC_INIT(1),
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	.magic = CRED_MAGIC,
-#endif
 };
 
 /*
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index feda711c6b7b..340b2bbbb2dd 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -1660,8 +1660,6 @@ static int inode_has_perm(const struct cred *cred,
 	struct inode_security_struct *isec;
 	u32 sid;
 
-	validate_creds(cred);
-
 	if (unlikely(IS_PRIVATE(inode)))
 		return 0;
 
@@ -3056,8 +3054,6 @@ static int selinux_inode_follow_link(struct dentry *dentry, struct inode *inode,
 	struct inode_security_struct *isec;
 	u32 sid;
 
-	validate_creds(cred);
-
 	ad.type = LSM_AUDIT_DATA_DENTRY;
 	ad.u.dentry = dentry;
 	sid = cred_sid(cred);
@@ -3101,8 +3097,6 @@ static int selinux_inode_permission(struct inode *inode, int mask)
 	if (!mask)
 		return 0;
 
-	validate_creds(cred);
-
 	if (unlikely(IS_PRIVATE(inode)))
 		return 0;
 
diff --git a/tools/objtool/noreturns.h b/tools/objtool/noreturns.h
index 649ebdef9c3f..1685d7ea6a9f 100644
--- a/tools/objtool/noreturns.h
+++ b/tools/objtool/noreturns.h
@@ -6,7 +6,6 @@
  *
  * Yes, this is unfortunate.  A better solution is in the works.
  */
-NORETURN(__invalid_creds)
 NORETURN(__kunit_abort)
 NORETURN(__module_put_and_kthread_exit)
 NORETURN(__reiserfs_panic)
diff --git a/tools/testing/selftests/bpf/config.x86_64 b/tools/testing/selftests/bpf/config.x86_64
index 2e70a6048278..49a29dbc1910 100644
--- a/tools/testing/selftests/bpf/config.x86_64
+++ b/tools/testing/selftests/bpf/config.x86_64
@@ -50,7 +50,6 @@ CONFIG_CRYPTO_SEQIV=y
 CONFIG_CRYPTO_XXHASH=y
 CONFIG_DCB=y
 CONFIG_DEBUG_ATOMIC_SLEEP=y
-CONFIG_DEBUG_CREDENTIALS=y
 CONFIG_DEBUG_INFO_BTF=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
 CONFIG_DEBUG_MEMORY_INIT=y
diff --git a/tools/testing/selftests/hid/config.common b/tools/testing/selftests/hid/config.common
index 0617275d93cc..0f456dbab62f 100644
--- a/tools/testing/selftests/hid/config.common
+++ b/tools/testing/selftests/hid/config.common
@@ -46,7 +46,6 @@ CONFIG_CRYPTO_SEQIV=y
 CONFIG_CRYPTO_XXHASH=y
 CONFIG_DCB=y
 CONFIG_DEBUG_ATOMIC_SLEEP=y
-CONFIG_DEBUG_CREDENTIALS=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
 CONFIG_DEBUG_MEMORY_INIT=y
 CONFIG_DEFAULT_FQ_CODEL=y
-- 
cgit v1.2.3


From 4382159696c9af67ee047ed55f2dbf05480f52f6 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 15 Dec 2023 10:12:17 +0100
Subject: cfi: Flip headers

Normal include order is that linux/foo.h should include asm/foo.h, CFI has it
the wrong way around.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Link: https://lore.kernel.org/r/20231215092707.231038174@infradead.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/riscv/include/asm/cfi.h | 3 ++-
 arch/riscv/kernel/cfi.c      | 2 +-
 arch/x86/include/asm/cfi.h   | 3 ++-
 arch/x86/kernel/cfi.c        | 4 ++--
 include/asm-generic/Kbuild   | 1 +
 include/asm-generic/cfi.h    | 5 +++++
 include/linux/cfi.h          | 1 +
 7 files changed, 14 insertions(+), 5 deletions(-)
 create mode 100644 include/asm-generic/cfi.h

(limited to 'include')

diff --git a/arch/riscv/include/asm/cfi.h b/arch/riscv/include/asm/cfi.h
index 56bf9d69d5e3..8f7a62257044 100644
--- a/arch/riscv/include/asm/cfi.h
+++ b/arch/riscv/include/asm/cfi.h
@@ -7,8 +7,9 @@
  *
  * Copyright (C) 2023 Google LLC
  */
+#include <linux/bug.h>
 
-#include <linux/cfi.h>
+struct pt_regs;
 
 #ifdef CONFIG_CFI_CLANG
 enum bug_trap_type handle_cfi_failure(struct pt_regs *regs);
diff --git a/arch/riscv/kernel/cfi.c b/arch/riscv/kernel/cfi.c
index 820158d7a291..6ec9dbd7292e 100644
--- a/arch/riscv/kernel/cfi.c
+++ b/arch/riscv/kernel/cfi.c
@@ -4,7 +4,7 @@
  *
  * Copyright (C) 2023 Google LLC
  */
-#include <asm/cfi.h>
+#include <linux/cfi.h>
 #include <asm/insn.h>
 
 /*
diff --git a/arch/x86/include/asm/cfi.h b/arch/x86/include/asm/cfi.h
index 58dacd90daef..2a494643089d 100644
--- a/arch/x86/include/asm/cfi.h
+++ b/arch/x86/include/asm/cfi.h
@@ -7,8 +7,9 @@
  *
  * Copyright (C) 2022 Google LLC
  */
+#include <linux/bug.h>
 
-#include <linux/cfi.h>
+struct pt_regs;
 
 #ifdef CONFIG_CFI_CLANG
 enum bug_trap_type handle_cfi_failure(struct pt_regs *regs);
diff --git a/arch/x86/kernel/cfi.c b/arch/x86/kernel/cfi.c
index 8674a5c0c031..e6bf78fac146 100644
--- a/arch/x86/kernel/cfi.c
+++ b/arch/x86/kernel/cfi.c
@@ -4,10 +4,10 @@
  *
  * Copyright (C) 2022 Google LLC
  */
-#include <asm/cfi.h>
+#include <linux/string.h>
+#include <linux/cfi.h>
 #include <asm/insn.h>
 #include <asm/insn-eval.h>
-#include <linux/string.h>
 
 /*
  * Returns the target address and the expected type when regs->ip points
diff --git a/include/asm-generic/Kbuild b/include/asm-generic/Kbuild
index def242528b1d..d436bee4d129 100644
--- a/include/asm-generic/Kbuild
+++ b/include/asm-generic/Kbuild
@@ -11,6 +11,7 @@ mandatory-y += bitops.h
 mandatory-y += bug.h
 mandatory-y += bugs.h
 mandatory-y += cacheflush.h
+mandatory-y += cfi.h
 mandatory-y += checksum.h
 mandatory-y += compat.h
 mandatory-y += current.h
diff --git a/include/asm-generic/cfi.h b/include/asm-generic/cfi.h
new file mode 100644
index 000000000000..41fac3537bf9
--- /dev/null
+++ b/include/asm-generic/cfi.h
@@ -0,0 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_GENERIC_CFI_H
+#define __ASM_GENERIC_CFI_H
+
+#endif /* __ASM_GENERIC_CFI_H */
diff --git a/include/linux/cfi.h b/include/linux/cfi.h
index 3552ec82b725..2309d74e77e6 100644
--- a/include/linux/cfi.h
+++ b/include/linux/cfi.h
@@ -9,6 +9,7 @@
 
 #include <linux/bug.h>
 #include <linux/module.h>
+#include <asm/cfi.h>
 
 #ifdef CONFIG_CFI_CLANG
 enum bug_trap_type report_cfi_failure(struct pt_regs *regs, unsigned long addr,
-- 
cgit v1.2.3


From 4f9087f16651aca4a5f32da840a53f6660f0579a Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 15 Dec 2023 10:12:18 +0100
Subject: x86/cfi,bpf: Fix BPF JIT call

The current BPF call convention is __nocfi, except when it calls !JIT things,
then it calls regular C functions.

It so happens that with FineIBT the __nocfi and C calling conventions are
incompatible. Specifically __nocfi will call at func+0, while FineIBT will have
endbr-poison there, which is not a valid indirect target. Causing #CP.

Notably this only triggers on IBT enabled hardware, which is probably why this
hasn't been reported (also, most people will have JIT on anyway).

Implement proper CFI prologues for the BPF JIT codegen and drop __nocfi for
x86.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231215092707.345270396@infradead.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/x86/include/asm/cfi.h    | 110 ++++++++++++++++++++++++++++++++++++++++++
 arch/x86/kernel/alternative.c |  47 +++++++++++++++---
 arch/x86/net/bpf_jit_comp.c   |  82 +++++++++++++++++++++++++++++--
 include/linux/bpf.h           |  12 ++++-
 include/linux/cfi.h           |   7 +++
 kernel/bpf/core.c             |  25 ++++++++++
 6 files changed, 269 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/arch/x86/include/asm/cfi.h b/arch/x86/include/asm/cfi.h
index 2a494643089d..7a7b0b823a98 100644
--- a/arch/x86/include/asm/cfi.h
+++ b/arch/x86/include/asm/cfi.h
@@ -9,15 +9,125 @@
  */
 #include <linux/bug.h>
 
+/*
+ * An overview of the various calling conventions...
+ *
+ * Traditional:
+ *
+ * foo:
+ *   ... code here ...
+ *   ret
+ *
+ * direct caller:
+ *   call foo
+ *
+ * indirect caller:
+ *   lea foo(%rip), %r11
+ *   ...
+ *   call *%r11
+ *
+ *
+ * IBT:
+ *
+ * foo:
+ *   endbr64
+ *   ... code here ...
+ *   ret
+ *
+ * direct caller:
+ *   call foo / call foo+4
+ *
+ * indirect caller:
+ *   lea foo(%rip), %r11
+ *   ...
+ *   call *%r11
+ *
+ *
+ * kCFI:
+ *
+ * __cfi_foo:
+ *   movl $0x12345678, %eax
+ *				# 11 nops when CONFIG_CALL_PADDING
+ * foo:
+ *   endbr64			# when IBT
+ *   ... code here ...
+ *   ret
+ *
+ * direct call:
+ *   call foo			# / call foo+4 when IBT
+ *
+ * indirect call:
+ *   lea foo(%rip), %r11
+ *   ...
+ *   movl $(-0x12345678), %r10d
+ *   addl -4(%r11), %r10d	# -15 when CONFIG_CALL_PADDING
+ *   jz   1f
+ *   ud2
+ * 1:call *%r11
+ *
+ *
+ * FineIBT (builds as kCFI + CALL_PADDING + IBT + RETPOLINE and runtime patches into):
+ *
+ * __cfi_foo:
+ *   endbr64
+ *   subl 0x12345678, %r10d
+ *   jz   foo
+ *   ud2
+ *   nop
+ * foo:
+ *   osp nop3			# was endbr64
+ *   ... code here ...
+ *   ret
+ *
+ * direct caller:
+ *   call foo / call foo+4
+ *
+ * indirect caller:
+ *   lea foo(%rip), %r11
+ *   ...
+ *   movl $0x12345678, %r10d
+ *   subl $16, %r11
+ *   nop4
+ *   call *%r11
+ *
+ */
+enum cfi_mode {
+	CFI_DEFAULT,	/* FineIBT if hardware has IBT, otherwise kCFI */
+	CFI_OFF,	/* Taditional / IBT depending on .config */
+	CFI_KCFI,	/* Optionally CALL_PADDING, IBT, RETPOLINE */
+	CFI_FINEIBT,	/* see arch/x86/kernel/alternative.c */
+};
+
+extern enum cfi_mode cfi_mode;
+
 struct pt_regs;
 
 #ifdef CONFIG_CFI_CLANG
 enum bug_trap_type handle_cfi_failure(struct pt_regs *regs);
+#define __bpfcall
+extern u32 cfi_bpf_hash;
+
+static inline int cfi_get_offset(void)
+{
+	switch (cfi_mode) {
+	case CFI_FINEIBT:
+		return 16;
+	case CFI_KCFI:
+		if (IS_ENABLED(CONFIG_CALL_PADDING))
+			return 16;
+		return 5;
+	default:
+		return 0;
+	}
+}
+#define cfi_get_offset cfi_get_offset
+
 #else
 static inline enum bug_trap_type handle_cfi_failure(struct pt_regs *regs)
 {
 	return BUG_TRAP_TYPE_NONE;
 }
+#define cfi_bpf_hash 0U
 #endif /* CONFIG_CFI_CLANG */
 
 #endif /* _ASM_X86_CFI_H */
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 73be3931e4f0..d808d3aaec7e 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -30,6 +30,7 @@
 #include <asm/fixmap.h>
 #include <asm/paravirt.h>
 #include <asm/asm-prototypes.h>
+#include <asm/cfi.h>
 
 int __read_mostly alternatives_patched;
 
@@ -832,15 +833,43 @@ void __init_or_module apply_seal_endbr(s32 *start, s32 *end) { }
 #endif /* CONFIG_X86_KERNEL_IBT */
 
 #ifdef CONFIG_FINEIBT
+#define __CFI_DEFAULT	CFI_DEFAULT
+#elif defined(CONFIG_CFI_CLANG)
+#define __CFI_DEFAULT	CFI_KCFI
+#else
+#define __CFI_DEFAULT	CFI_OFF
+#endif
 
-enum cfi_mode {
-	CFI_DEFAULT,
-	CFI_OFF,
-	CFI_KCFI,
-	CFI_FINEIBT,
-};
+enum cfi_mode cfi_mode __ro_after_init = __CFI_DEFAULT;
+
+#ifdef CONFIG_CFI_CLANG
+struct bpf_insn;
+
+/* Must match bpf_func_t / DEFINE_BPF_PROG_RUN() */
+extern unsigned int __bpf_prog_runX(const void *ctx,
+				    const struct bpf_insn *insn);
+
+/*
+ * Force a reference to the external symbol so the compiler generates
+ * __kcfi_typid.
+ */
+__ADDRESSABLE(__bpf_prog_runX);
+
+/* u32 __ro_after_init cfi_bpf_hash = __kcfi_typeid___bpf_prog_runX; */
+asm (
+"	.pushsection	.data..ro_after_init,\"aw\",@progbits	\n"
+"	.type	cfi_bpf_hash,@object				\n"
+"	.globl	cfi_bpf_hash					\n"
+"	.p2align	2, 0x0					\n"
+"cfi_bpf_hash:							\n"
+"	.long	__kcfi_typeid___bpf_prog_runX			\n"
+"	.size	cfi_bpf_hash, 4					\n"
+"	.popsection						\n"
+);
+#endif
+
+#ifdef CONFIG_FINEIBT
 
-static enum cfi_mode cfi_mode __ro_after_init = CFI_DEFAULT;
 static bool cfi_rand __ro_after_init = true;
 static u32  cfi_seed __ro_after_init;
 
@@ -1149,8 +1178,10 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 		goto err;
 
 	if (cfi_rand) {
-		if (builtin)
+		if (builtin) {
 			cfi_seed = get_random_u32();
+			cfi_bpf_hash = cfi_rehash(cfi_bpf_hash);
+		}
 
 		ret = cfi_rand_preamble(start_cfi, end_cfi);
 		if (ret)
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index af4a5de7d93a..5d5b967b111d 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -17,6 +17,7 @@
 #include <asm/nospec-branch.h>
 #include <asm/text-patching.h>
 #include <asm/unwind.h>
+#include <asm/cfi.h>
 
 static bool all_callee_regs_used[4] = {true, true, true, true};
 
@@ -51,9 +52,11 @@ static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
 	do { EMIT4(b1, b2, b3, b4); EMIT(off, 4); } while (0)
 
 #ifdef CONFIG_X86_KERNEL_IBT
-#define EMIT_ENDBR()	EMIT(gen_endbr(), 4)
+#define EMIT_ENDBR()		EMIT(gen_endbr(), 4)
+#define EMIT_ENDBR_POISON()	EMIT(gen_endbr_poison(), 4)
 #else
 #define EMIT_ENDBR()
+#define EMIT_ENDBR_POISON()
 #endif
 
 static bool is_imm8(int value)
@@ -304,6 +307,69 @@ static void pop_callee_regs(u8 **pprog, bool *callee_regs_used)
 	*pprog = prog;
 }
 
+/*
+ * Emit the various CFI preambles, see asm/cfi.h and the comments about FineIBT
+ * in arch/x86/kernel/alternative.c
+ */
+
+static void emit_fineibt(u8 **pprog)
+{
+	u8 *prog = *pprog;
+
+	EMIT_ENDBR();
+	EMIT3_off32(0x41, 0x81, 0xea, cfi_bpf_hash);	/* subl $hash, %r10d	*/
+	EMIT2(0x74, 0x07);				/* jz.d8 +7		*/
+	EMIT2(0x0f, 0x0b);				/* ud2			*/
+	EMIT1(0x90);					/* nop			*/
+	EMIT_ENDBR_POISON();
+
+	*pprog = prog;
+}
+
+static void emit_kcfi(u8 **pprog)
+{
+	u8 *prog = *pprog;
+
+	EMIT1_off32(0xb8, cfi_bpf_hash);		/* movl $hash, %eax	*/
+#ifdef CONFIG_CALL_PADDING
+	EMIT1(0x90);
+	EMIT1(0x90);
+	EMIT1(0x90);
+	EMIT1(0x90);
+	EMIT1(0x90);
+	EMIT1(0x90);
+	EMIT1(0x90);
+	EMIT1(0x90);
+	EMIT1(0x90);
+	EMIT1(0x90);
+	EMIT1(0x90);
+#endif
+	EMIT_ENDBR();
+
+	*pprog = prog;
+}
+
+static void emit_cfi(u8 **pprog)
+{
+	u8 *prog = *pprog;
+
+	switch (cfi_mode) {
+	case CFI_FINEIBT:
+		emit_fineibt(&prog);
+		break;
+
+	case CFI_KCFI:
+		emit_kcfi(&prog);
+		break;
+
+	default:
+		EMIT_ENDBR();
+		break;
+	}
+
+	*pprog = prog;
+}
+
 /*
  * Emit x86-64 prologue code for BPF program.
  * bpf_tail_call helper will skip the first X86_TAIL_CALL_OFFSET bytes
@@ -315,10 +381,10 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf,
 {
 	u8 *prog = *pprog;
 
+	emit_cfi(&prog);
 	/* BPF trampoline can be made to work without these nops,
 	 * but let's waste 5 bytes for now and optimize later
 	 */
-	EMIT_ENDBR();
 	memcpy(prog, x86_nops[5], X86_PATCH_SIZE);
 	prog += X86_PATCH_SIZE;
 	if (!ebpf_from_cbpf) {
@@ -3013,9 +3079,16 @@ out_image:
 			jit_data->header = header;
 			jit_data->rw_header = rw_header;
 		}
-		prog->bpf_func = (void *)image;
+		/*
+		 * ctx.prog_offset is used when CFI preambles put code *before*
+		 * the function. See emit_cfi(). For FineIBT specifically this code
+		 * can also be executed and bpf_prog_kallsyms_add() will
+		 * generate an additional symbol to cover this, hence also
+		 * decrement proglen.
+		 */
+		prog->bpf_func = (void *)image + cfi_get_offset();
 		prog->jited = 1;
-		prog->jited_len = proglen;
+		prog->jited_len = proglen - cfi_get_offset();
 	} else {
 		prog = orig_prog;
 	}
@@ -3070,6 +3143,7 @@ void bpf_jit_free(struct bpf_prog *prog)
 			kvfree(jit_data->addrs);
 			kfree(jit_data);
 		}
+		prog->bpf_func = (void *)prog->bpf_func - cfi_get_offset();
 		hdr = bpf_jit_binary_pack_hdr(prog);
 		bpf_jit_binary_pack_free(hdr, NULL);
 		WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(prog));
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index c87c608a3689..9d84c376851a 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -29,6 +29,7 @@
 #include <linux/rcupdate_trace.h>
 #include <linux/static_call.h>
 #include <linux/memcontrol.h>
+#include <linux/cfi.h>
 
 struct bpf_verifier_env;
 struct bpf_verifier_log;
@@ -1211,7 +1212,11 @@ struct bpf_dispatcher {
 #endif
 };
 
-static __always_inline __nocfi unsigned int bpf_dispatcher_nop_func(
+#ifndef __bpfcall
+#define __bpfcall __nocfi
+#endif
+
+static __always_inline __bpfcall unsigned int bpf_dispatcher_nop_func(
 	const void *ctx,
 	const struct bpf_insn *insnsi,
 	bpf_func_t bpf_func)
@@ -1303,7 +1308,7 @@ int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_func
 
 #define DEFINE_BPF_DISPATCHER(name)					\
 	__BPF_DISPATCHER_SC(name);					\
-	noinline __nocfi unsigned int bpf_dispatcher_##name##_func(	\
+	noinline __bpfcall unsigned int bpf_dispatcher_##name##_func(	\
 		const void *ctx,					\
 		const struct bpf_insn *insnsi,				\
 		bpf_func_t bpf_func)					\
@@ -1453,6 +1458,9 @@ struct bpf_prog_aux {
 	struct bpf_kfunc_desc_tab *kfunc_tab;
 	struct bpf_kfunc_btf_tab *kfunc_btf_tab;
 	u32 size_poke_tab;
+#ifdef CONFIG_FINEIBT
+	struct bpf_ksym ksym_prefix;
+#endif
 	struct bpf_ksym ksym;
 	const struct bpf_prog_ops *ops;
 	struct bpf_map **used_maps;
diff --git a/include/linux/cfi.h b/include/linux/cfi.h
index 2309d74e77e6..1ed2d96c0cfc 100644
--- a/include/linux/cfi.h
+++ b/include/linux/cfi.h
@@ -11,6 +11,13 @@
 #include <linux/module.h>
 #include <asm/cfi.h>
 
+#ifndef cfi_get_offset
+static inline int cfi_get_offset(void)
+{
+	return 0;
+}
+#endif
+
 #ifdef CONFIG_CFI_CLANG
 enum bug_trap_type report_cfi_failure(struct pt_regs *regs, unsigned long addr,
 				      unsigned long *target, u32 type);
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index c34513d645c4..5aa6863ac33b 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -121,6 +121,9 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag
 #endif
 
 	INIT_LIST_HEAD_RCU(&fp->aux->ksym.lnode);
+#ifdef CONFIG_FINEIBT
+	INIT_LIST_HEAD_RCU(&fp->aux->ksym_prefix.lnode);
+#endif
 	mutex_init(&fp->aux->used_maps_mutex);
 	mutex_init(&fp->aux->dst_mutex);
 
@@ -683,6 +686,23 @@ void bpf_prog_kallsyms_add(struct bpf_prog *fp)
 	fp->aux->ksym.prog = true;
 
 	bpf_ksym_add(&fp->aux->ksym);
+
+#ifdef CONFIG_FINEIBT
+	/*
+	 * When FineIBT, code in the __cfi_foo() symbols can get executed
+	 * and hence unwinder needs help.
+	 */
+	if (cfi_mode != CFI_FINEIBT)
+		return;
+
+	snprintf(fp->aux->ksym_prefix.name, KSYM_NAME_LEN,
+		 "__cfi_%s", fp->aux->ksym.name);
+
+	fp->aux->ksym_prefix.start = (unsigned long) fp->bpf_func - 16;
+	fp->aux->ksym_prefix.end   = (unsigned long) fp->bpf_func;
+
+	bpf_ksym_add(&fp->aux->ksym_prefix);
+#endif
 }
 
 void bpf_prog_kallsyms_del(struct bpf_prog *fp)
@@ -691,6 +711,11 @@ void bpf_prog_kallsyms_del(struct bpf_prog *fp)
 		return;
 
 	bpf_ksym_del(&fp->aux->ksym);
+#ifdef CONFIG_FINEIBT
+	if (cfi_mode != CFI_FINEIBT)
+		return;
+	bpf_ksym_del(&fp->aux->ksym_prefix);
+#endif
 }
 
 static struct bpf_ksym *bpf_ksym_find(unsigned long addr)
-- 
cgit v1.2.3


From 2cd3e3772e41377f32d6eea643e0590774e9187c Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 15 Dec 2023 10:12:20 +0100
Subject: x86/cfi,bpf: Fix bpf_struct_ops CFI

BPF struct_ops uses __arch_prepare_bpf_trampoline() to write
trampolines for indirect function calls. These tramplines much have
matching CFI.

In order to obtain the correct CFI hash for the various methods, add a
matching structure that contains stub functions, the compiler will
generate correct CFI which we can pilfer for the trampolines.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231215092707.566977112@infradead.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/x86/include/asm/cfi.h     |  6 ++++
 arch/x86/kernel/alternative.c  | 22 ++++++++++++++
 arch/x86/net/bpf_jit_comp.c    | 66 ++++++++++++++++++++++++++--------------
 include/linux/bpf.h            | 13 ++++++++
 kernel/bpf/bpf_struct_ops.c    | 16 +++++-----
 net/bpf/bpf_dummy_struct_ops.c | 31 ++++++++++++++++++-
 net/ipv4/bpf_tcp_ca.c          | 69 ++++++++++++++++++++++++++++++++++++++++++
 7 files changed, 191 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/arch/x86/include/asm/cfi.h b/arch/x86/include/asm/cfi.h
index 8779abd217b7..1a50b2cd4713 100644
--- a/arch/x86/include/asm/cfi.h
+++ b/arch/x86/include/asm/cfi.h
@@ -123,6 +123,8 @@ static inline int cfi_get_offset(void)
 }
 #define cfi_get_offset cfi_get_offset
 
+extern u32 cfi_get_func_hash(void *func);
+
 #else
 static inline enum bug_trap_type handle_cfi_failure(struct pt_regs *regs)
 {
@@ -130,6 +132,10 @@ static inline enum bug_trap_type handle_cfi_failure(struct pt_regs *regs)
 }
 #define cfi_bpf_hash 0U
 #define cfi_bpf_subprog_hash 0U
+static inline u32 cfi_get_func_hash(void *func)
+{
+	return 0;
+}
 #endif /* CONFIG_CFI_CLANG */
 
 #endif /* _ASM_X86_CFI_H */
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index cb393efd5ccd..49c2a62ba5e4 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -883,6 +883,28 @@ asm (
 "	.size	cfi_bpf_subprog_hash, 4				\n"
 "	.popsection						\n"
 );
+
+u32 cfi_get_func_hash(void *func)
+{
+	u32 hash;
+
+	func -= cfi_get_offset();
+	switch (cfi_mode) {
+	case CFI_FINEIBT:
+		func += 7;
+		break;
+	case CFI_KCFI:
+		func += 1;
+		break;
+	default:
+		return 0;
+	}
+
+	if (get_kernel_nofault(hash, func))
+		return 0;
+
+	return hash;
+}
 #endif
 
 #ifdef CONFIG_FINEIBT
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 43b8c08fdf8d..c89a4abdd726 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -312,9 +312,8 @@ static void pop_callee_regs(u8 **pprog, bool *callee_regs_used)
  * in arch/x86/kernel/alternative.c
  */
 
-static void emit_fineibt(u8 **pprog, bool is_subprog)
+static void emit_fineibt(u8 **pprog, u32 hash)
 {
-	u32 hash = is_subprog ? cfi_bpf_subprog_hash : cfi_bpf_hash;
 	u8 *prog = *pprog;
 
 	EMIT_ENDBR();
@@ -327,9 +326,8 @@ static void emit_fineibt(u8 **pprog, bool is_subprog)
 	*pprog = prog;
 }
 
-static void emit_kcfi(u8 **pprog, bool is_subprog)
+static void emit_kcfi(u8 **pprog, u32 hash)
 {
-	u32 hash = is_subprog ? cfi_bpf_subprog_hash : cfi_bpf_hash;
 	u8 *prog = *pprog;
 
 	EMIT1_off32(0xb8, hash);			/* movl $hash, %eax	*/
@@ -351,17 +349,17 @@ static void emit_kcfi(u8 **pprog, bool is_subprog)
 	*pprog = prog;
 }
 
-static void emit_cfi(u8 **pprog, bool is_subprog)
+static void emit_cfi(u8 **pprog, u32 hash)
 {
 	u8 *prog = *pprog;
 
 	switch (cfi_mode) {
 	case CFI_FINEIBT:
-		emit_fineibt(&prog, is_subprog);
+		emit_fineibt(&prog, hash);
 		break;
 
 	case CFI_KCFI:
-		emit_kcfi(&prog, is_subprog);
+		emit_kcfi(&prog, hash);
 		break;
 
 	default:
@@ -383,7 +381,7 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf,
 {
 	u8 *prog = *pprog;
 
-	emit_cfi(&prog, is_subprog);
+	emit_cfi(&prog, is_subprog ? cfi_bpf_subprog_hash : cfi_bpf_hash);
 	/* BPF trampoline can be made to work without these nops,
 	 * but let's waste 5 bytes for now and optimize later
 	 */
@@ -2510,10 +2508,19 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 	u8 *prog;
 	bool save_ret;
 
+	/*
+	 * F_INDIRECT is only compatible with F_RET_FENTRY_RET, it is
+	 * explicitly incompatible with F_CALL_ORIG | F_SKIP_FRAME | F_IP_ARG
+	 * because @func_addr.
+	 */
+	WARN_ON_ONCE((flags & BPF_TRAMP_F_INDIRECT) &&
+		     (flags & ~(BPF_TRAMP_F_INDIRECT | BPF_TRAMP_F_RET_FENTRY_RET)));
+
 	/* extra registers for struct arguments */
-	for (i = 0; i < m->nr_args; i++)
+	for (i = 0; i < m->nr_args; i++) {
 		if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG)
 			nr_regs += (m->arg_size[i] + 7) / 8 - 1;
+	}
 
 	/* x86-64 supports up to MAX_BPF_FUNC_ARGS arguments. 1-6
 	 * are passed through regs, the remains are through stack.
@@ -2596,20 +2603,27 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 
 	prog = rw_image;
 
-	EMIT_ENDBR();
-	/*
-	 * This is the direct-call trampoline, as such it needs accounting
-	 * for the __fentry__ call.
-	 */
-	x86_call_depth_emit_accounting(&prog, NULL);
+	if (flags & BPF_TRAMP_F_INDIRECT) {
+		/*
+		 * Indirect call for bpf_struct_ops
+		 */
+		emit_cfi(&prog, cfi_get_func_hash(func_addr));
+	} else {
+		/*
+		 * Direct-call fentry stub, as such it needs accounting for the
+		 * __fentry__ call.
+		 */
+		x86_call_depth_emit_accounting(&prog, NULL);
+	}
 	EMIT1(0x55);		 /* push rbp */
 	EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
-	if (!is_imm8(stack_size))
+	if (!is_imm8(stack_size)) {
 		/* sub rsp, stack_size */
 		EMIT3_off32(0x48, 0x81, 0xEC, stack_size);
-	else
+	} else {
 		/* sub rsp, stack_size */
 		EMIT4(0x48, 0x83, 0xEC, stack_size);
+	}
 	if (flags & BPF_TRAMP_F_TAIL_CALL_CTX)
 		EMIT1(0x50);		/* push rax */
 	/* mov QWORD PTR [rbp - rbx_off], rbx */
@@ -2643,10 +2657,11 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 		}
 	}
 
-	if (fentry->nr_links)
+	if (fentry->nr_links) {
 		if (invoke_bpf(m, &prog, fentry, regs_off, run_ctx_off,
 			       flags & BPF_TRAMP_F_RET_FENTRY_RET, image, rw_image))
 			return -EINVAL;
+	}
 
 	if (fmod_ret->nr_links) {
 		branches = kcalloc(fmod_ret->nr_links, sizeof(u8 *),
@@ -2665,11 +2680,12 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 		restore_regs(m, &prog, regs_off);
 		save_args(m, &prog, arg_stack_off, true);
 
-		if (flags & BPF_TRAMP_F_TAIL_CALL_CTX)
+		if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) {
 			/* Before calling the original function, restore the
 			 * tail_call_cnt from stack to rax.
 			 */
 			RESTORE_TAIL_CALL_CNT(stack_size);
+		}
 
 		if (flags & BPF_TRAMP_F_ORIG_STACK) {
 			emit_ldx(&prog, BPF_DW, BPF_REG_6, BPF_REG_FP, 8);
@@ -2698,17 +2714,19 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 		/* Update the branches saved in invoke_bpf_mod_ret with the
 		 * aligned address of do_fexit.
 		 */
-		for (i = 0; i < fmod_ret->nr_links; i++)
+		for (i = 0; i < fmod_ret->nr_links; i++) {
 			emit_cond_near_jump(&branches[i], image + (prog - (u8 *)rw_image),
 					    image + (branches[i] - (u8 *)rw_image), X86_JNE);
+		}
 	}
 
-	if (fexit->nr_links)
+	if (fexit->nr_links) {
 		if (invoke_bpf(m, &prog, fexit, regs_off, run_ctx_off,
 			       false, image, rw_image)) {
 			ret = -EINVAL;
 			goto cleanup;
 		}
+	}
 
 	if (flags & BPF_TRAMP_F_RESTORE_REGS)
 		restore_regs(m, &prog, regs_off);
@@ -2725,11 +2743,12 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 			ret = -EINVAL;
 			goto cleanup;
 		}
-	} else if (flags & BPF_TRAMP_F_TAIL_CALL_CTX)
+	} else if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) {
 		/* Before running the original function, restore the
 		 * tail_call_cnt from stack to rax.
 		 */
 		RESTORE_TAIL_CALL_CNT(stack_size);
+	}
 
 	/* restore return value of orig_call or fentry prog back into RAX */
 	if (save_ret)
@@ -2737,9 +2756,10 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 
 	emit_ldx(&prog, BPF_DW, BPF_REG_6, BPF_REG_FP, -rbx_off);
 	EMIT1(0xC9); /* leave */
-	if (flags & BPF_TRAMP_F_SKIP_FRAME)
+	if (flags & BPF_TRAMP_F_SKIP_FRAME) {
 		/* skip our return address and return to parent */
 		EMIT4(0x48, 0x83, 0xC4, 8); /* add rsp, 8 */
+	}
 	emit_return(&prog, image + (prog - (u8 *)rw_image));
 	/* Make sure the trampoline generation logic doesn't overflow */
 	if (WARN_ON_ONCE(prog > (u8 *)rw_image_end - BPF_INSN_SAFETY)) {
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 9d84c376851a..db46b3359bf5 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1060,6 +1060,17 @@ struct btf_func_model {
  */
 #define BPF_TRAMP_F_TAIL_CALL_CTX	BIT(7)
 
+/*
+ * Indicate the trampoline should be suitable to receive indirect calls;
+ * without this indirectly calling the generated code can result in #UD/#CP,
+ * depending on the CFI options.
+ *
+ * Used by bpf_struct_ops.
+ *
+ * Incompatible with FENTRY usage, overloads @func_addr argument.
+ */
+#define BPF_TRAMP_F_INDIRECT		BIT(8)
+
 /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50
  * bytes on x86.
  */
@@ -1697,6 +1708,7 @@ struct bpf_struct_ops {
 	struct btf_func_model func_models[BPF_STRUCT_OPS_MAX_NR_MEMBERS];
 	u32 type_id;
 	u32 value_id;
+	void *cfi_stubs;
 };
 
 #if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL)
@@ -1710,6 +1722,7 @@ int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key,
 int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks,
 				      struct bpf_tramp_link *link,
 				      const struct btf_func_model *model,
+				      void *stub_func,
 				      void *image, void *image_end);
 static inline bool bpf_try_module_get(const void *data, struct module *owner)
 {
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index 4d53c53fc5aa..02068bd0e4d9 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -352,17 +352,16 @@ const struct bpf_link_ops bpf_struct_ops_link_lops = {
 int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks,
 				      struct bpf_tramp_link *link,
 				      const struct btf_func_model *model,
-				      void *image, void *image_end)
+				      void *stub_func, void *image, void *image_end)
 {
-	u32 flags;
+	u32 flags = BPF_TRAMP_F_INDIRECT;
 	int size;
 
 	tlinks[BPF_TRAMP_FENTRY].links[0] = link;
 	tlinks[BPF_TRAMP_FENTRY].nr_links = 1;
-	/* BPF_TRAMP_F_RET_FENTRY_RET is only used by bpf_struct_ops,
-	 * and it must be used alone.
-	 */
-	flags = model->ret_size > 0 ? BPF_TRAMP_F_RET_FENTRY_RET : 0;
+
+	if (model->ret_size > 0)
+		flags |= BPF_TRAMP_F_RET_FENTRY_RET;
 
 	size = arch_bpf_trampoline_size(model, flags, tlinks, NULL);
 	if (size < 0)
@@ -370,7 +369,7 @@ int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks,
 	if (size > (unsigned long)image_end - (unsigned long)image)
 		return -E2BIG;
 	return arch_prepare_bpf_trampoline(NULL, image, image_end,
-					   model, flags, tlinks, NULL);
+					   model, flags, tlinks, stub_func);
 }
 
 static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
@@ -504,11 +503,12 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 
 		err = bpf_struct_ops_prepare_trampoline(tlinks, link,
 							&st_ops->func_models[i],
+							*(void **)(st_ops->cfi_stubs + moff),
 							image, image_end);
 		if (err < 0)
 			goto reset_unlock;
 
-		*(void **)(kdata + moff) = image;
+		*(void **)(kdata + moff) = image + cfi_get_offset();
 		image += err;
 
 		/* put prog_id to udata */
diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c
index 2748f9d77b18..8906f7bdf4a9 100644
--- a/net/bpf/bpf_dummy_struct_ops.c
+++ b/net/bpf/bpf_dummy_struct_ops.c
@@ -12,6 +12,11 @@ extern struct bpf_struct_ops bpf_bpf_dummy_ops;
 /* A common type for test_N with return value in bpf_dummy_ops */
 typedef int (*dummy_ops_test_ret_fn)(struct bpf_dummy_ops_state *state, ...);
 
+static int dummy_ops_test_ret_function(struct bpf_dummy_ops_state *state, ...)
+{
+	return 0;
+}
+
 struct bpf_dummy_ops_test_args {
 	u64 args[MAX_BPF_FUNC_ARGS];
 	struct bpf_dummy_ops_state state;
@@ -62,7 +67,7 @@ static int dummy_ops_copy_args(struct bpf_dummy_ops_test_args *args)
 
 static int dummy_ops_call_op(void *image, struct bpf_dummy_ops_test_args *args)
 {
-	dummy_ops_test_ret_fn test = (void *)image;
+	dummy_ops_test_ret_fn test = (void *)image + cfi_get_offset();
 	struct bpf_dummy_ops_state *state = NULL;
 
 	/* state needs to be NULL if args[0] is 0 */
@@ -119,6 +124,7 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr,
 	op_idx = prog->expected_attach_type;
 	err = bpf_struct_ops_prepare_trampoline(tlinks, link,
 						&st_ops->func_models[op_idx],
+						&dummy_ops_test_ret_function,
 						image, image + PAGE_SIZE);
 	if (err < 0)
 		goto out;
@@ -219,6 +225,28 @@ static void bpf_dummy_unreg(void *kdata)
 {
 }
 
+static int bpf_dummy_test_1(struct bpf_dummy_ops_state *cb)
+{
+	return 0;
+}
+
+static int bpf_dummy_test_2(struct bpf_dummy_ops_state *cb, int a1, unsigned short a2,
+			    char a3, unsigned long a4)
+{
+	return 0;
+}
+
+static int bpf_dummy_test_sleepable(struct bpf_dummy_ops_state *cb)
+{
+	return 0;
+}
+
+static struct bpf_dummy_ops __bpf_bpf_dummy_ops = {
+	.test_1 = bpf_dummy_test_1,
+	.test_2 = bpf_dummy_test_2,
+	.test_sleepable = bpf_dummy_test_sleepable,
+};
+
 struct bpf_struct_ops bpf_bpf_dummy_ops = {
 	.verifier_ops = &bpf_dummy_verifier_ops,
 	.init = bpf_dummy_init,
@@ -227,4 +255,5 @@ struct bpf_struct_ops bpf_bpf_dummy_ops = {
 	.reg = bpf_dummy_reg,
 	.unreg = bpf_dummy_unreg,
 	.name = "bpf_dummy_ops",
+	.cfi_stubs = &__bpf_bpf_dummy_ops,
 };
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index c7bbd8f3c708..634cfafa583d 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -271,6 +271,74 @@ static int bpf_tcp_ca_validate(void *kdata)
 	return tcp_validate_congestion_control(kdata);
 }
 
+static u32 bpf_tcp_ca_ssthresh(struct sock *sk)
+{
+	return 0;
+}
+
+static void bpf_tcp_ca_cong_avoid(struct sock *sk, u32 ack, u32 acked)
+{
+}
+
+static void bpf_tcp_ca_set_state(struct sock *sk, u8 new_state)
+{
+}
+
+static void bpf_tcp_ca_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
+{
+}
+
+static void bpf_tcp_ca_in_ack_event(struct sock *sk, u32 flags)
+{
+}
+
+static void bpf_tcp_ca_pkts_acked(struct sock *sk, const struct ack_sample *sample)
+{
+}
+
+static u32 bpf_tcp_ca_min_tso_segs(struct sock *sk)
+{
+	return 0;
+}
+
+static void bpf_tcp_ca_cong_control(struct sock *sk, const struct rate_sample *rs)
+{
+}
+
+static u32 bpf_tcp_ca_undo_cwnd(struct sock *sk)
+{
+	return 0;
+}
+
+static u32 bpf_tcp_ca_sndbuf_expand(struct sock *sk)
+{
+	return 0;
+}
+
+static void __bpf_tcp_ca_init(struct sock *sk)
+{
+}
+
+static void __bpf_tcp_ca_release(struct sock *sk)
+{
+}
+
+static struct tcp_congestion_ops __bpf_ops_tcp_congestion_ops = {
+	.ssthresh = bpf_tcp_ca_ssthresh,
+	.cong_avoid = bpf_tcp_ca_cong_avoid,
+	.set_state = bpf_tcp_ca_set_state,
+	.cwnd_event = bpf_tcp_ca_cwnd_event,
+	.in_ack_event = bpf_tcp_ca_in_ack_event,
+	.pkts_acked = bpf_tcp_ca_pkts_acked,
+	.min_tso_segs = bpf_tcp_ca_min_tso_segs,
+	.cong_control = bpf_tcp_ca_cong_control,
+	.undo_cwnd = bpf_tcp_ca_undo_cwnd,
+	.sndbuf_expand = bpf_tcp_ca_sndbuf_expand,
+
+	.init = __bpf_tcp_ca_init,
+	.release = __bpf_tcp_ca_release,
+};
+
 struct bpf_struct_ops bpf_tcp_congestion_ops = {
 	.verifier_ops = &bpf_tcp_ca_verifier_ops,
 	.reg = bpf_tcp_ca_reg,
@@ -281,6 +349,7 @@ struct bpf_struct_ops bpf_tcp_congestion_ops = {
 	.init = bpf_tcp_ca_init,
 	.validate = bpf_tcp_ca_validate,
 	.name = "tcp_congestion_ops",
+	.cfi_stubs = &__bpf_ops_tcp_congestion_ops,
 };
 
 static int __init bpf_tcp_ca_kfunc_init(void)
-- 
cgit v1.2.3


From e9d13b9d2f99ccf7afeab490d97eaa5ac9846598 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 15 Dec 2023 10:12:21 +0100
Subject: cfi: Add CFI_NOSEAL()

Add a CFI_NOSEAL() helper to mark functions that need to retain their
CFI information, despite not otherwise leaking their address.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20231215092707.669401084@infradead.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/x86/include/asm/cfi.h | 5 +++++
 include/linux/cfi.h        | 4 ++++
 2 files changed, 9 insertions(+)

(limited to 'include')

diff --git a/arch/x86/include/asm/cfi.h b/arch/x86/include/asm/cfi.h
index 1a50b2cd4713..7cd752557905 100644
--- a/arch/x86/include/asm/cfi.h
+++ b/arch/x86/include/asm/cfi.h
@@ -8,6 +8,7 @@
  * Copyright (C) 2022 Google LLC
  */
 #include <linux/bug.h>
+#include <asm/ibt.h>
 
 /*
  * An overview of the various calling conventions...
@@ -138,4 +139,8 @@ static inline u32 cfi_get_func_hash(void *func)
 }
 #endif /* CONFIG_CFI_CLANG */
 
+#if HAS_KERNEL_IBT == 1
+#define CFI_NOSEAL(x)	asm(IBT_NOSEAL(__stringify(x)))
+#endif
+
 #endif /* _ASM_X86_CFI_H */
diff --git a/include/linux/cfi.h b/include/linux/cfi.h
index 1ed2d96c0cfc..f0df518e11dd 100644
--- a/include/linux/cfi.h
+++ b/include/linux/cfi.h
@@ -46,4 +46,8 @@ static inline void module_cfi_finalize(const Elf_Ehdr *hdr,
 #endif /* CONFIG_ARCH_USES_CFI_TRAPS */
 #endif /* CONFIG_MODULES */
 
+#ifndef CFI_NOSEAL
+#define CFI_NOSEAL(x)
+#endif
+
 #endif /* _LINUX_CFI_H */
-- 
cgit v1.2.3


From 852486b35f344887786d63250946dd921a05d7e8 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Date: Fri, 15 Dec 2023 10:12:23 +0100
Subject: x86/cfi,bpf: Fix bpf_exception_cb() signature

As per the earlier patches, BPF sub-programs have bpf_callback_t
signature and CFI expects callers to have matching signature. This is
violated by bpf_prog_aux::bpf_exception_cb().

[peterz: Changelog]
Reported-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/CAADnVQ+Z7UcXXBBhMubhcMM=R-dExk-uHtfOLtoLxQ1XxEpqEA@mail.gmail.com
Link: https://lore.kernel.org/r/20231215092707.910319166@infradead.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h  | 2 +-
 kernel/bpf/helpers.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index db46b3359bf5..5e694934cf37 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1484,7 +1484,7 @@ struct bpf_prog_aux {
 	int cgroup_atype; /* enum cgroup_bpf_attach_type */
 	struct bpf_map *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE];
 	char name[BPF_OBJ_NAME_LEN];
-	unsigned int (*bpf_exception_cb)(u64 cookie, u64 sp, u64 bp);
+	u64 (*bpf_exception_cb)(u64 cookie, u64 sp, u64 bp, u64, u64);
 #ifdef CONFIG_SECURITY
 	void *security;
 #endif
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index e0c0e3676df8..07fd4b5704f3 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -2537,7 +2537,7 @@ __bpf_kfunc void bpf_throw(u64 cookie)
 	 * which skips compiler generated instrumentation to do the same.
 	 */
 	kasan_unpoison_task_stack_below((void *)(long)ctx.sp);
-	ctx.aux->bpf_exception_cb(cookie, ctx.sp, ctx.bp);
+	ctx.aux->bpf_exception_cb(cookie, ctx.sp, ctx.bp, 0, 0);
 	WARN(1, "A call to BPF exception callback should never return\n");
 }
 
-- 
cgit v1.2.3


From 117211aa739a926e6555cfea883be84bee6f1695 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Sat, 16 Dec 2023 00:05:02 +0100
Subject: bpf: Add missing BPF_LINK_TYPE invocations

Pengfei Xu reported [1] Syzkaller/KASAN issue found in bpf_link_show_fdinfo.

The reason is missing BPF_LINK_TYPE invocation for uprobe multi
link and for several other links, adding that.

[1] https://lore.kernel.org/bpf/ZXptoKRSLspnk2ie@xpf.sh.intel.com/

Fixes: 89ae89f53d20 ("bpf: Add multi uprobe link")
Fixes: e420bed02507 ("bpf: Add fd-based tcx multi-prog infra with link support")
Fixes: 84601d6ee68a ("bpf: add bpf_link support for BPF_NETFILTER programs")
Fixes: 35dfaad7188c ("netkit, bpf: Add bpf programmable net device")
Reported-by: Pengfei Xu <pengfei.xu@intel.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Tested-by: Pengfei Xu <pengfei.xu@intel.com>
Acked-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/bpf/20231215230502.2769743-1-jolsa@kernel.org
---
 include/linux/bpf_types.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index fc0d6f32c687..94baced5a1ad 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -142,9 +142,13 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_ITER, iter)
 #ifdef CONFIG_NET
 BPF_LINK_TYPE(BPF_LINK_TYPE_NETNS, netns)
 BPF_LINK_TYPE(BPF_LINK_TYPE_XDP, xdp)
+BPF_LINK_TYPE(BPF_LINK_TYPE_NETFILTER, netfilter)
+BPF_LINK_TYPE(BPF_LINK_TYPE_TCX, tcx)
+BPF_LINK_TYPE(BPF_LINK_TYPE_NETKIT, netkit)
 #endif
 #ifdef CONFIG_PERF_EVENTS
 BPF_LINK_TYPE(BPF_LINK_TYPE_PERF_EVENT, perf)
 #endif
 BPF_LINK_TYPE(BPF_LINK_TYPE_KPROBE_MULTI, kprobe_multi)
 BPF_LINK_TYPE(BPF_LINK_TYPE_STRUCT_OPS, struct_ops)
+BPF_LINK_TYPE(BPF_LINK_TYPE_UPROBE_MULTI, uprobe_multi)
-- 
cgit v1.2.3


From 41db7626b73210cb99eea9cf672dcfce58c68ab2 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 14 Dec 2023 19:29:38 +0000
Subject: inet: returns a bool from inet_sk_get_local_port_range()

Change inet_sk_get_local_port_range() to return a boolean,
telling the callers if the port range was provided by
IP_LOCAL_PORT_RANGE socket option.

Adds documentation while we are at it.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20231214192939.1962891-2-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/ip.h                |  2 +-
 net/ipv4/inet_connection_sock.c | 21 ++++++++++++++++-----
 2 files changed, 17 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/ip.h b/include/net/ip.h
index b31be912489a..de0c69c57e3c 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -356,7 +356,7 @@ static inline void inet_get_local_port_range(const struct net *net, int *low, in
 	*low = range & 0xffff;
 	*high = range >> 16;
 }
-void inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high);
+bool inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high);
 
 #ifdef CONFIG_SYSCTL
 static inline bool inet_is_local_reserved_port(struct net *net, unsigned short port)
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 70be0f6fe879..bd325b029dd1 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -117,16 +117,25 @@ bool inet_rcv_saddr_any(const struct sock *sk)
 	return !sk->sk_rcv_saddr;
 }
 
-void inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high)
+/**
+ *	inet_sk_get_local_port_range - fetch ephemeral ports range
+ *	@sk: socket
+ *	@low: pointer to low port
+ *	@high: pointer to high port
+ *
+ *	Fetch netns port range (/proc/sys/net/ipv4/ip_local_port_range)
+ *	Range can be overridden if socket got IP_LOCAL_PORT_RANGE option.
+ *	Returns true if IP_LOCAL_PORT_RANGE was set on this socket.
+ */
+bool inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high)
 {
-	const struct inet_sock *inet = inet_sk(sk);
-	const struct net *net = sock_net(sk);
 	int lo, hi, sk_lo, sk_hi;
+	bool local_range = false;
 	u32 sk_range;
 
-	inet_get_local_port_range(net, &lo, &hi);
+	inet_get_local_port_range(sock_net(sk), &lo, &hi);
 
-	sk_range = READ_ONCE(inet->local_port_range);
+	sk_range = READ_ONCE(inet_sk(sk)->local_port_range);
 	if (unlikely(sk_range)) {
 		sk_lo = sk_range & 0xffff;
 		sk_hi = sk_range >> 16;
@@ -135,10 +144,12 @@ void inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high)
 			lo = sk_lo;
 		if (lo <= sk_hi && sk_hi <= hi)
 			hi = sk_hi;
+		local_range = true;
 	}
 
 	*low = lo;
 	*high = hi;
+	return local_range;
 }
 EXPORT_SYMBOL(inet_sk_get_local_port_range);
 
-- 
cgit v1.2.3


From 3185f96968eedd117ec72ee7b87ead44b6d1bbbd Mon Sep 17 00:00:00 2001
From: Satya Priya Kakitapalli <quic_skakitap@quicinc.com>
Date: Fri, 1 Dec 2023 15:20:24 +0530
Subject: dt-bindings: clock: Update the videocc resets for sm8150

Add all the available resets for the video clock controller
on sm8150.

Signed-off-by: Satya Priya Kakitapalli <quic_skakitap@quicinc.com>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231201-videocc-8150-v3-1-56bec3a5e443@quicinc.com
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 include/dt-bindings/clock/qcom,videocc-sm8150.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/dt-bindings/clock/qcom,videocc-sm8150.h b/include/dt-bindings/clock/qcom,videocc-sm8150.h
index e24ee840cfdb..c557b78dc572 100644
--- a/include/dt-bindings/clock/qcom,videocc-sm8150.h
+++ b/include/dt-bindings/clock/qcom,videocc-sm8150.h
@@ -16,6 +16,10 @@
 
 /* VIDEO_CC Resets */
 #define VIDEO_CC_MVSC_CORE_CLK_BCR	0
+#define VIDEO_CC_INTERFACE_BCR		1
+#define VIDEO_CC_MVS0_BCR		2
+#define VIDEO_CC_MVS1_BCR		3
+#define VIDEO_CC_MVSC_BCR		4
 
 /* VIDEO_CC GDSCRs */
 #define VENUS_GDSC			0
-- 
cgit v1.2.3


From f7dc3248dcfbdd81b5be64272f38b87a8e8085e7 Mon Sep 17 00:00:00 2001
From: Liang Chen <liangchen.linux@gmail.com>
Date: Fri, 15 Dec 2023 11:30:11 +0800
Subject: skbuff: Optimization of SKB coalescing for page pool

In order to address the issues encountered with commit 1effe8ca4e34
("skbuff: fix coalescing for page_pool fragment recycling"), the
combination of the following condition was excluded from skb coalescing:

from->pp_recycle = 1
from->cloned = 1
to->pp_recycle = 1

However, with page pool environments, the aforementioned combination can
be quite common(ex. NetworkMananger may lead to the additional
packet_type being registered, thus the cloning). In scenarios with a
higher number of small packets, it can significantly affect the success
rate of coalescing. For example, considering packets of 256 bytes size,
our comparison of coalescing success rate is as follows:

Without page pool: 70%
With page pool: 13%

Consequently, this has an impact on performance:

Without page pool: 2.57 Gbits/sec
With page pool: 2.26 Gbits/sec

Therefore, it seems worthwhile to optimize this scenario and enable
coalescing of this particular combination. To achieve this, we need to
ensure the correct increment of the "from" SKB page's page pool
reference count (pp_ref_count).

Following this optimization, the success rate of coalescing measured in
our environment has improved as follows:

With page pool: 60%

This success rate is approaching the rate achieved without using page
pool, and the performance has also been improved:

With page pool: 2.52 Gbits/sec

Below is the performance comparison for small packets before and after
this optimization. We observe no impact to packets larger than 4K.

packet size     before      after       improved
(bytes)         (Gbits/sec) (Gbits/sec)
128             1.19        1.27        7.13%
256             2.26        2.52        11.75%
512             4.13        4.81        16.50%
1024            6.17        6.73        9.05%
2048            14.54       15.47       6.45%
4096            25.44       27.87       9.52%

Signed-off-by: Liang Chen <liangchen.linux@gmail.com>
Reviewed-by: Yunsheng Lin <linyunsheng@huawei.com>
Suggested-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Mina Almasry <almasrymina@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/page_pool/helpers.h |  5 ++++
 net/core/skbuff.c               | 52 +++++++++++++++++++++++++++++++----------
 2 files changed, 45 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h
index ead2c0d24b2c..1d397c1a0043 100644
--- a/include/net/page_pool/helpers.h
+++ b/include/net/page_pool/helpers.h
@@ -277,6 +277,11 @@ static inline long page_pool_unref_page(struct page *page, long nr)
 	return ret;
 }
 
+static inline void page_pool_ref_page(struct page *page)
+{
+	atomic_long_inc(&page->pp_ref_count);
+}
+
 static inline bool page_pool_is_last_ref(struct page *page)
 {
 	/* If page_pool_unref_page() returns 0, we were the last user */
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 2f977fffd3ec..4d4b11b0a83d 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -947,6 +947,37 @@ static bool skb_pp_recycle(struct sk_buff *skb, void *data, bool napi_safe)
 	return napi_pp_put_page(virt_to_page(data), napi_safe);
 }
 
+/**
+ * skb_pp_frag_ref() - Increase fragment references of a page pool aware skb
+ * @skb:	page pool aware skb
+ *
+ * Increase the fragment reference count (pp_ref_count) of a skb. This is
+ * intended to gain fragment references only for page pool aware skbs,
+ * i.e. when skb->pp_recycle is true, and not for fragments in a
+ * non-pp-recycling skb. It has a fallback to increase references on normal
+ * pages, as page pool aware skbs may also have normal page fragments.
+ */
+static int skb_pp_frag_ref(struct sk_buff *skb)
+{
+	struct skb_shared_info *shinfo;
+	struct page *head_page;
+	int i;
+
+	if (!skb->pp_recycle)
+		return -EINVAL;
+
+	shinfo = skb_shinfo(skb);
+
+	for (i = 0; i < shinfo->nr_frags; i++) {
+		head_page = compound_head(skb_frag_page(&shinfo->frags[i]));
+		if (likely(is_pp_page(head_page)))
+			page_pool_ref_page(head_page);
+		else
+			page_ref_inc(head_page);
+	}
+	return 0;
+}
+
 static void skb_kfree_head(void *head, unsigned int end_offset)
 {
 	if (end_offset == SKB_SMALL_HEAD_HEADROOM)
@@ -5770,17 +5801,12 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
 		return false;
 
 	/* In general, avoid mixing page_pool and non-page_pool allocated
-	 * pages within the same SKB. Additionally avoid dealing with clones
-	 * with page_pool pages, in case the SKB is using page_pool fragment
-	 * references (page_pool_alloc_frag()). Since we only take full page
-	 * references for cloned SKBs at the moment that would result in
-	 * inconsistent reference counts.
-	 * In theory we could take full references if @from is cloned and
-	 * !@to->pp_recycle but its tricky (due to potential race with
-	 * the clone disappearing) and rare, so not worth dealing with.
+	 * pages within the same SKB. In theory we could take full
+	 * references if @from is cloned and !@to->pp_recycle but its
+	 * tricky (due to potential race with the clone disappearing) and
+	 * rare, so not worth dealing with.
 	 */
-	if (to->pp_recycle != from->pp_recycle ||
-	    (from->pp_recycle && skb_cloned(from)))
+	if (to->pp_recycle != from->pp_recycle)
 		return false;
 
 	if (len <= skb_tailroom(to)) {
@@ -5837,8 +5863,10 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
 	/* if the skb is not cloned this does nothing
 	 * since we set nr_frags to 0.
 	 */
-	for (i = 0; i < from_shinfo->nr_frags; i++)
-		__skb_frag_ref(&from_shinfo->frags[i]);
+	if (skb_pp_frag_ref(from)) {
+		for (i = 0; i < from_shinfo->nr_frags; i++)
+			__skb_frag_ref(&from_shinfo->frags[i]);
+	}
 
 	to->truesize += delta;
 	to->len += len;
-- 
cgit v1.2.3


From bb339db4d363c84e0a8d70827df591397ccd7312 Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@arm.com>
Date: Fri, 15 Dec 2023 17:56:48 +0000
Subject: arm: perf: Fix ARCH=arm build with GCC
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

LLVM ignores everything inside the if statement and doesn't generate
errors, but GCC doesn't ignore it, resulting in the following error:

  drivers/perf/arm_pmuv3.c: In function ‘armv8pmu_write_evtype’:
  include/linux/bits.h:34:29: error: left shift count >= width of type [-Werror=shift-count-overflow]
  34 |         (((~UL(0)) - (UL(1) << (l)) + 1) & \

Fix it by using GENMASK_ULL which doesn't overflow on arm32 (even though
the value is never used there).

Fixes: 3115ee021bfb ("arm64: perf: Include threshold control fields in PMEVTYPER mask")
Reported-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Closes: https://lore.kernel.org/linux-arm-kernel/20231215120817.h2f3akgv72zhrtqo@pengutronix.de/
Signed-off-by: James Clark <james.clark@arm.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Link: https://lore.kernel.org/r/20231215175648.3397170-2-james.clark@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 include/linux/perf/arm_pmuv3.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/perf/arm_pmuv3.h b/include/linux/perf/arm_pmuv3.h
index 0f4d62ef3a9a..46377e134d67 100644
--- a/include/linux/perf/arm_pmuv3.h
+++ b/include/linux/perf/arm_pmuv3.h
@@ -234,8 +234,8 @@
  * PMXEVTYPER: Event selection reg
  */
 #define ARMV8_PMU_EVTYPE_EVENT	GENMASK(15, 0)	/* Mask for EVENT bits */
-#define ARMV8_PMU_EVTYPE_TH	GENMASK(43, 32)
-#define ARMV8_PMU_EVTYPE_TC	GENMASK(63, 61)
+#define ARMV8_PMU_EVTYPE_TH	GENMASK_ULL(43, 32) /* arm64 only */
+#define ARMV8_PMU_EVTYPE_TC	GENMASK_ULL(63, 61) /* arm64 only */
 
 /*
  * Event filters for PMUv3
-- 
cgit v1.2.3


From 9b0a7a2cb87d9c430a3588d7d2b6e471200b86ad Mon Sep 17 00:00:00 2001
From: Selvin Xavier <selvin.xavier@broadcom.com>
Date: Wed, 13 Dec 2023 22:31:23 -0800
Subject: RDMA/bnxt_re: Add UAPI to share a page with user space

Gen P7 adapters require to share a toggle value for CQ
and SRQ. This is received by the driver as part of
interrupt notifications and needs to be shared with the
user space. Add a new UAPI infrastructure to get the
shared page for CQ and SRQ.

Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://lore.kernel.org/r/1702535484-26844-2-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/bnxt_re/ib_verbs.c | 105 +++++++++++++++++++++++++++++++
 drivers/infiniband/hw/bnxt_re/ib_verbs.h |   1 +
 include/uapi/rdma/bnxt_re-abi.h          |  26 ++++++++
 3 files changed, 132 insertions(+)

(limited to 'include')

diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index e7ef099c3edd..758ea02e1d13 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -567,6 +567,7 @@ bnxt_re_mmap_entry_insert(struct bnxt_re_ucontext *uctx, u64 mem_offset,
 	case BNXT_RE_MMAP_WC_DB:
 	case BNXT_RE_MMAP_DBR_BAR:
 	case BNXT_RE_MMAP_DBR_PAGE:
+	case BNXT_RE_MMAP_TOGGLE_PAGE:
 		ret = rdma_user_mmap_entry_insert(&uctx->ib_uctx,
 						  &entry->rdma_entry, PAGE_SIZE);
 		break;
@@ -4254,6 +4255,7 @@ int bnxt_re_mmap(struct ib_ucontext *ib_uctx, struct vm_area_struct *vma)
 					rdma_entry);
 		break;
 	case BNXT_RE_MMAP_DBR_PAGE:
+	case BNXT_RE_MMAP_TOGGLE_PAGE:
 		/* Driver doesn't expect write access for user space */
 		if (vma->vm_flags & VM_WRITE)
 			return -EFAULT;
@@ -4430,8 +4432,111 @@ DECLARE_UVERBS_NAMED_METHOD(BNXT_RE_METHOD_NOTIFY_DRV);
 DECLARE_UVERBS_GLOBAL_METHODS(BNXT_RE_OBJECT_NOTIFY_DRV,
 			      &UVERBS_METHOD(BNXT_RE_METHOD_NOTIFY_DRV));
 
+/* Toggle MEM */
+static int UVERBS_HANDLER(BNXT_RE_METHOD_GET_TOGGLE_MEM)(struct uverbs_attr_bundle *attrs)
+{
+	struct ib_uobject *uobj = uverbs_attr_get_uobject(attrs, BNXT_RE_TOGGLE_MEM_HANDLE);
+	enum bnxt_re_mmap_flag mmap_flag = BNXT_RE_MMAP_TOGGLE_PAGE;
+	enum bnxt_re_get_toggle_mem_type res_type;
+	struct bnxt_re_user_mmap_entry *entry;
+	struct bnxt_re_ucontext *uctx;
+	struct ib_ucontext *ib_uctx;
+	struct bnxt_re_dev *rdev;
+	u64 mem_offset;
+	u64 addr = 0;
+	u32 length;
+	u32 offset;
+	int err;
+
+	ib_uctx = ib_uverbs_get_ucontext(attrs);
+	if (IS_ERR(ib_uctx))
+		return PTR_ERR(ib_uctx);
+
+	err = uverbs_get_const(&res_type, attrs, BNXT_RE_TOGGLE_MEM_TYPE);
+	if (err)
+		return err;
+
+	uctx = container_of(ib_uctx, struct bnxt_re_ucontext, ib_uctx);
+	rdev = uctx->rdev;
+
+	switch (res_type) {
+	case BNXT_RE_CQ_TOGGLE_MEM:
+	case BNXT_RE_SRQ_TOGGLE_MEM:
+		break;
+
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	entry = bnxt_re_mmap_entry_insert(uctx, addr, mmap_flag, &mem_offset);
+	if (!entry)
+		return -ENOMEM;
+
+	uobj->object = entry;
+	uverbs_finalize_uobj_create(attrs, BNXT_RE_TOGGLE_MEM_HANDLE);
+	err = uverbs_copy_to(attrs, BNXT_RE_TOGGLE_MEM_MMAP_PAGE,
+			     &mem_offset, sizeof(mem_offset));
+	if (err)
+		return err;
+
+	err = uverbs_copy_to(attrs, BNXT_RE_TOGGLE_MEM_MMAP_LENGTH,
+			     &length, sizeof(length));
+	if (err)
+		return err;
+
+	err = uverbs_copy_to(attrs, BNXT_RE_TOGGLE_MEM_MMAP_OFFSET,
+			     &offset, sizeof(length));
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static int get_toggle_mem_obj_cleanup(struct ib_uobject *uobject,
+				      enum rdma_remove_reason why,
+				      struct uverbs_attr_bundle *attrs)
+{
+	struct  bnxt_re_user_mmap_entry *entry = uobject->object;
+
+	rdma_user_mmap_entry_remove(&entry->rdma_entry);
+	return 0;
+}
+
+DECLARE_UVERBS_NAMED_METHOD(BNXT_RE_METHOD_GET_TOGGLE_MEM,
+			    UVERBS_ATTR_IDR(BNXT_RE_TOGGLE_MEM_HANDLE,
+					    BNXT_RE_OBJECT_GET_TOGGLE_MEM,
+					    UVERBS_ACCESS_NEW,
+					    UA_MANDATORY),
+			    UVERBS_ATTR_CONST_IN(BNXT_RE_TOGGLE_MEM_TYPE,
+						 enum bnxt_re_get_toggle_mem_type,
+						 UA_MANDATORY),
+			    UVERBS_ATTR_PTR_IN(BNXT_RE_TOGGLE_MEM_RES_ID,
+					       UVERBS_ATTR_TYPE(u32),
+					       UA_MANDATORY),
+			    UVERBS_ATTR_PTR_OUT(BNXT_RE_TOGGLE_MEM_MMAP_PAGE,
+						UVERBS_ATTR_TYPE(u64),
+						UA_MANDATORY),
+			    UVERBS_ATTR_PTR_OUT(BNXT_RE_TOGGLE_MEM_MMAP_OFFSET,
+						UVERBS_ATTR_TYPE(u32),
+						UA_MANDATORY),
+			    UVERBS_ATTR_PTR_OUT(BNXT_RE_TOGGLE_MEM_MMAP_LENGTH,
+						UVERBS_ATTR_TYPE(u32),
+						UA_MANDATORY));
+
+DECLARE_UVERBS_NAMED_METHOD_DESTROY(BNXT_RE_METHOD_RELEASE_TOGGLE_MEM,
+				    UVERBS_ATTR_IDR(BNXT_RE_RELEASE_TOGGLE_MEM_HANDLE,
+						    BNXT_RE_OBJECT_GET_TOGGLE_MEM,
+						    UVERBS_ACCESS_DESTROY,
+						    UA_MANDATORY));
+
+DECLARE_UVERBS_NAMED_OBJECT(BNXT_RE_OBJECT_GET_TOGGLE_MEM,
+			    UVERBS_TYPE_ALLOC_IDR(get_toggle_mem_obj_cleanup),
+			    &UVERBS_METHOD(BNXT_RE_METHOD_GET_TOGGLE_MEM),
+			    &UVERBS_METHOD(BNXT_RE_METHOD_RELEASE_TOGGLE_MEM));
+
 const struct uapi_definition bnxt_re_uapi_defs[] = {
 	UAPI_DEF_CHAIN_OBJ_TREE_NAMED(BNXT_RE_OBJECT_ALLOC_PAGE),
 	UAPI_DEF_CHAIN_OBJ_TREE_NAMED(BNXT_RE_OBJECT_NOTIFY_DRV),
+	UAPI_DEF_CHAIN_OBJ_TREE_NAMED(BNXT_RE_OBJECT_GET_TOGGLE_MEM),
 	{}
 };
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.h b/drivers/infiniband/hw/bnxt_re/ib_verbs.h
index 98baea98fc17..da3fe018f255 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.h
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.h
@@ -149,6 +149,7 @@ enum bnxt_re_mmap_flag {
 	BNXT_RE_MMAP_WC_DB,
 	BNXT_RE_MMAP_DBR_PAGE,
 	BNXT_RE_MMAP_DBR_BAR,
+	BNXT_RE_MMAP_TOGGLE_PAGE,
 };
 
 struct bnxt_re_user_mmap_entry {
diff --git a/include/uapi/rdma/bnxt_re-abi.h b/include/uapi/rdma/bnxt_re-abi.h
index 3342276aeac1..9b9eb10cb5e5 100644
--- a/include/uapi/rdma/bnxt_re-abi.h
+++ b/include/uapi/rdma/bnxt_re-abi.h
@@ -143,6 +143,7 @@ enum bnxt_re_shpg_offt {
 enum bnxt_re_objects {
 	BNXT_RE_OBJECT_ALLOC_PAGE = (1U << UVERBS_ID_NS_SHIFT),
 	BNXT_RE_OBJECT_NOTIFY_DRV,
+	BNXT_RE_OBJECT_GET_TOGGLE_MEM,
 };
 
 enum bnxt_re_alloc_page_type {
@@ -171,4 +172,29 @@ enum bnxt_re_alloc_page_methods {
 enum bnxt_re_notify_drv_methods {
 	BNXT_RE_METHOD_NOTIFY_DRV = (1U << UVERBS_ID_NS_SHIFT),
 };
+
+/* Toggle mem */
+
+enum bnxt_re_get_toggle_mem_type {
+	BNXT_RE_CQ_TOGGLE_MEM = 0,
+	BNXT_RE_SRQ_TOGGLE_MEM,
+};
+
+enum bnxt_re_var_toggle_mem_attrs {
+	BNXT_RE_TOGGLE_MEM_HANDLE = (1U << UVERBS_ID_NS_SHIFT),
+	BNXT_RE_TOGGLE_MEM_TYPE,
+	BNXT_RE_TOGGLE_MEM_RES_ID,
+	BNXT_RE_TOGGLE_MEM_MMAP_PAGE,
+	BNXT_RE_TOGGLE_MEM_MMAP_OFFSET,
+	BNXT_RE_TOGGLE_MEM_MMAP_LENGTH,
+};
+
+enum bnxt_re_toggle_mem_attrs {
+	BNXT_RE_RELEASE_TOGGLE_MEM_HANDLE = (1U << UVERBS_ID_NS_SHIFT),
+};
+
+enum bnxt_re_toggle_mem_methods {
+	BNXT_RE_METHOD_GET_TOGGLE_MEM = (1U << UVERBS_ID_NS_SHIFT),
+	BNXT_RE_METHOD_RELEASE_TOGGLE_MEM,
+};
 #endif /* __BNXT_RE_UVERBS_ABI_H__*/
-- 
cgit v1.2.3


From e275919d96693c5ca964b20d73a33d52a7e57f04 Mon Sep 17 00:00:00 2001
From: Selvin Xavier <selvin.xavier@broadcom.com>
Date: Wed, 13 Dec 2023 22:31:24 -0800
Subject: RDMA/bnxt_re: Share a page to expose per CQ info with userspace

Gen P7 adapters needs to share a toggle bits information received
in kernel driver with the user space. User space needs this
info during the request notify call back to arm the CQ.

User space application can get this page using the
UAPI routines. Library will mmap this page and get the
toggle bits to be used in the next ARM Doorbell.

Uses a hash list to map the CQ structure from the CQ ID.
CQ structure is retrieved from the hash list while the
library calls the UAPI routine to get the toggle page
mapping. Currently the full page is mapped per CQ. This
can be optimized to enable multiple CQs from the same
application share the same page and different offsets
in the page.

Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://lore.kernel.org/r/1702535484-26844-3-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/bnxt_re/bnxt_re.h   |  3 ++
 drivers/infiniband/hw/bnxt_re/ib_verbs.c  | 61 +++++++++++++++++++++++++++----
 drivers/infiniband/hw/bnxt_re/ib_verbs.h  |  2 +
 drivers/infiniband/hw/bnxt_re/main.c      | 10 ++++-
 drivers/infiniband/hw/bnxt_re/qplib_res.h |  6 +++
 include/uapi/rdma/bnxt_re-abi.h           |  5 +++
 6 files changed, 79 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/bnxt_re/bnxt_re.h b/drivers/infiniband/hw/bnxt_re/bnxt_re.h
index 9fd9849ebdd1..9dca451ed522 100644
--- a/drivers/infiniband/hw/bnxt_re/bnxt_re.h
+++ b/drivers/infiniband/hw/bnxt_re/bnxt_re.h
@@ -41,6 +41,7 @@
 #define __BNXT_RE_H__
 #include <rdma/uverbs_ioctl.h>
 #include "hw_counters.h"
+#include <linux/hashtable.h>
 #define ROCE_DRV_MODULE_NAME		"bnxt_re"
 
 #define BNXT_RE_DESC	"Broadcom NetXtreme-C/E RoCE Driver"
@@ -135,6 +136,7 @@ struct bnxt_re_pacing {
 #define BNXT_RE_DB_FIFO_ROOM_SHIFT 15
 #define BNXT_RE_GRC_FIFO_REG_BASE 0x2000
 
+#define MAX_CQ_HASH_BITS		(16)
 struct bnxt_re_dev {
 	struct ib_device		ibdev;
 	struct list_head		list;
@@ -189,6 +191,7 @@ struct bnxt_re_dev {
 	struct bnxt_re_pacing pacing;
 	struct work_struct dbq_fifo_check_work;
 	struct delayed_work dbq_pacing_work;
+	DECLARE_HASHTABLE(cq_hash, MAX_CQ_HASH_BITS);
 };
 
 #define to_bnxt_re_dev(ptr, member)	\
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index 758ea02e1d13..7213dc7574d0 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -50,6 +50,7 @@
 #include <rdma/ib_mad.h>
 #include <rdma/ib_cache.h>
 #include <rdma/uverbs_ioctl.h>
+#include <linux/hashtable.h>
 
 #include "bnxt_ulp.h"
 
@@ -2910,14 +2911,20 @@ int bnxt_re_post_recv(struct ib_qp *ib_qp, const struct ib_recv_wr *wr,
 /* Completion Queues */
 int bnxt_re_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata)
 {
-	struct bnxt_re_cq *cq;
+	struct bnxt_qplib_chip_ctx *cctx;
 	struct bnxt_qplib_nq *nq;
 	struct bnxt_re_dev *rdev;
+	struct bnxt_re_cq *cq;
 
 	cq = container_of(ib_cq, struct bnxt_re_cq, ib_cq);
 	rdev = cq->rdev;
 	nq = cq->qplib_cq.nq;
+	cctx = rdev->chip_ctx;
 
+	if (cctx->modes.toggle_bits & BNXT_QPLIB_CQ_TOGGLE_BIT) {
+		free_page((unsigned long)cq->uctx_cq_page);
+		hash_del(&cq->hash_entry);
+	}
 	bnxt_qplib_destroy_cq(&rdev->qplib_res, &cq->qplib_cq);
 	ib_umem_release(cq->umem);
 
@@ -2935,10 +2942,11 @@ int bnxt_re_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 	struct bnxt_re_ucontext *uctx =
 		rdma_udata_to_drv_context(udata, struct bnxt_re_ucontext, ib_uctx);
 	struct bnxt_qplib_dev_attr *dev_attr = &rdev->dev_attr;
-	int rc, entries;
-	int cqe = attr->cqe;
+	struct bnxt_qplib_chip_ctx *cctx;
 	struct bnxt_qplib_nq *nq = NULL;
+	int rc = -ENOMEM, entries;
 	unsigned int nq_alloc_cnt;
+	int cqe = attr->cqe;
 	u32 active_cqs;
 
 	if (attr->flags)
@@ -2951,6 +2959,7 @@ int bnxt_re_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 	}
 
 	cq->rdev = rdev;
+	cctx = rdev->chip_ctx;
 	cq->qplib_cq.cq_handle = (u64)(unsigned long)(&cq->qplib_cq);
 
 	entries = bnxt_re_init_depth(cqe + 1, uctx);
@@ -3012,22 +3021,32 @@ int bnxt_re_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 	spin_lock_init(&cq->cq_lock);
 
 	if (udata) {
-		struct bnxt_re_cq_resp resp;
-
+		struct bnxt_re_cq_resp resp = {};
+
+		if (cctx->modes.toggle_bits & BNXT_QPLIB_CQ_TOGGLE_BIT) {
+			hash_add(rdev->cq_hash, &cq->hash_entry, cq->qplib_cq.id);
+			/* Allocate a page */
+			cq->uctx_cq_page = (void *)get_zeroed_page(GFP_KERNEL);
+			if (!cq->uctx_cq_page)
+				goto c2fail;
+			resp.comp_mask |= BNXT_RE_CQ_TOGGLE_PAGE_SUPPORT;
+		}
 		resp.cqid = cq->qplib_cq.id;
 		resp.tail = cq->qplib_cq.hwq.cons;
 		resp.phase = cq->qplib_cq.period;
 		resp.rsvd = 0;
-		rc = ib_copy_to_udata(udata, &resp, sizeof(resp));
+		rc = ib_copy_to_udata(udata, &resp, min(sizeof(resp), udata->outlen));
 		if (rc) {
 			ibdev_err(&rdev->ibdev, "Failed to copy CQ udata");
 			bnxt_qplib_destroy_cq(&rdev->qplib_res, &cq->qplib_cq);
-			goto c2fail;
+			goto free_mem;
 		}
 	}
 
 	return 0;
 
+free_mem:
+	free_page((unsigned long)cq->uctx_cq_page);
 c2fail:
 	ib_umem_release(cq->umem);
 fail:
@@ -4214,6 +4233,19 @@ void bnxt_re_dealloc_ucontext(struct ib_ucontext *ib_uctx)
 	}
 }
 
+static struct bnxt_re_cq *bnxt_re_search_for_cq(struct bnxt_re_dev *rdev, u32 cq_id)
+{
+	struct bnxt_re_cq *cq = NULL, *tmp_cq;
+
+	hash_for_each_possible(rdev->cq_hash, tmp_cq, hash_entry, cq_id) {
+		if (tmp_cq->qplib_cq.id == cq_id) {
+			cq = tmp_cq;
+			break;
+		}
+	}
+	return cq;
+}
+
 /* Helper function to mmap the virtual memory from user app */
 int bnxt_re_mmap(struct ib_ucontext *ib_uctx, struct vm_area_struct *vma)
 {
@@ -4442,10 +4474,12 @@ static int UVERBS_HANDLER(BNXT_RE_METHOD_GET_TOGGLE_MEM)(struct uverbs_attr_bund
 	struct bnxt_re_ucontext *uctx;
 	struct ib_ucontext *ib_uctx;
 	struct bnxt_re_dev *rdev;
+	struct bnxt_re_cq *cq;
 	u64 mem_offset;
 	u64 addr = 0;
 	u32 length;
 	u32 offset;
+	u32 cq_id;
 	int err;
 
 	ib_uctx = ib_uverbs_get_ucontext(attrs);
@@ -4461,6 +4495,19 @@ static int UVERBS_HANDLER(BNXT_RE_METHOD_GET_TOGGLE_MEM)(struct uverbs_attr_bund
 
 	switch (res_type) {
 	case BNXT_RE_CQ_TOGGLE_MEM:
+		err = uverbs_copy_from(&cq_id, attrs, BNXT_RE_TOGGLE_MEM_RES_ID);
+		if (err)
+			return err;
+
+		cq = bnxt_re_search_for_cq(rdev, cq_id);
+		if (!cq)
+			return -EINVAL;
+
+		length = PAGE_SIZE;
+		addr = (u64)cq->uctx_cq_page;
+		mmap_flag = BNXT_RE_MMAP_TOGGLE_PAGE;
+		offset = 0;
+		break;
 	case BNXT_RE_SRQ_TOGGLE_MEM:
 		break;
 
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.h b/drivers/infiniband/hw/bnxt_re/ib_verbs.h
index da3fe018f255..b267d6d5975f 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.h
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.h
@@ -108,6 +108,8 @@ struct bnxt_re_cq {
 	struct ib_umem		*umem;
 	struct ib_umem		*resize_umem;
 	int			resize_cqe;
+	void			*uctx_cq_page;
+	struct hlist_node	hash_entry;
 };
 
 struct bnxt_re_mr {
diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index 7f4f6db1392c..eb03ebad2e5a 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -54,6 +54,7 @@
 #include <rdma/ib_user_verbs.h>
 #include <rdma/ib_umem.h>
 #include <rdma/ib_addr.h>
+#include <linux/hashtable.h>
 
 #include "bnxt_ulp.h"
 #include "roce_hsi.h"
@@ -136,6 +137,8 @@ static void bnxt_re_set_drv_mode(struct bnxt_re_dev *rdev, u8 mode)
 	if (bnxt_re_hwrm_qcaps(rdev))
 		dev_err(rdev_to_dev(rdev),
 			"Failed to query hwrm qcaps\n");
+	if (bnxt_qplib_is_chip_gen_p7(rdev->chip_ctx))
+		cctx->modes.toggle_bits |= BNXT_QPLIB_CQ_TOGGLE_BIT;
 }
 
 static void bnxt_re_destroy_chip_ctx(struct bnxt_re_dev *rdev)
@@ -1206,9 +1209,13 @@ static int bnxt_re_cqn_handler(struct bnxt_qplib_nq *nq,
 {
 	struct bnxt_re_cq *cq = container_of(handle, struct bnxt_re_cq,
 					     qplib_cq);
+	u32 *cq_ptr;
 
 	if (cq->ib_cq.comp_handler) {
-		/* Lock comp_handler? */
+		if (cq->uctx_cq_page) {
+			cq_ptr = (u32 *)cq->uctx_cq_page;
+			*cq_ptr = cq->qplib_cq.toggle;
+		}
 		(*cq->ib_cq.comp_handler)(&cq->ib_cq, cq->ib_cq.cq_context);
 	}
 
@@ -1730,6 +1737,7 @@ static int bnxt_re_dev_init(struct bnxt_re_dev *rdev, u8 wqe_mode)
 		 */
 		bnxt_re_vf_res_config(rdev);
 	}
+	hash_init(rdev->cq_hash);
 
 	return 0;
 free_sctx:
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.h b/drivers/infiniband/hw/bnxt_re/qplib_res.h
index 382d89fa7d16..61628f7f1253 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_res.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_res.h
@@ -55,6 +55,12 @@ struct bnxt_qplib_drv_modes {
 	u8	wqe_mode;
 	bool db_push;
 	bool dbr_pacing;
+	u32 toggle_bits;
+};
+
+enum bnxt_re_toggle_modes {
+	BNXT_QPLIB_CQ_TOGGLE_BIT = 0x1,
+	BNXT_QPLIB_SRQ_TOGGLE_BIT = 0x2,
 };
 
 struct bnxt_qplib_chip_ctx {
diff --git a/include/uapi/rdma/bnxt_re-abi.h b/include/uapi/rdma/bnxt_re-abi.h
index 9b9eb10cb5e5..c0c34aca90ec 100644
--- a/include/uapi/rdma/bnxt_re-abi.h
+++ b/include/uapi/rdma/bnxt_re-abi.h
@@ -102,11 +102,16 @@ struct bnxt_re_cq_req {
 	__aligned_u64 cq_handle;
 };
 
+enum bnxt_re_cq_mask {
+	BNXT_RE_CQ_TOGGLE_PAGE_SUPPORT = 0x1,
+};
+
 struct bnxt_re_cq_resp {
 	__u32 cqid;
 	__u32 tail;
 	__u32 phase;
 	__u32 rsvd;
+	__aligned_u64 comp_mask;
 };
 
 struct bnxt_re_resize_cq_req {
-- 
cgit v1.2.3


From ebb30ccbbdbd6fae5177b676da4f4ac92bb4f635 Mon Sep 17 00:00:00 2001
From: Christian Marangi <ansuelsmth@gmail.com>
Date: Fri, 15 Dec 2023 14:15:31 +0100
Subject: net: phy: make addr type u8 in phy_package_shared struct

Switch addr type in phy_package_shared struct to u8.

The value is already checked to be non negative and to be less than
PHY_MAX_ADDR, hence u8 is better suited than using int.

Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/phy.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/phy.h b/include/linux/phy.h
index dbb5e13e3e1b..4b13cc85c4f5 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -338,7 +338,7 @@ struct mdio_bus_stats {
  * phy_package_leave().
  */
 struct phy_package_shared {
-	int addr;
+	u8 addr;
 	refcount_t refcnt;
 	unsigned long flags;
 	size_t priv_size;
-- 
cgit v1.2.3


From 9eea577eb1155fe4a183bc5e7bf269b0b2e7a6ba Mon Sep 17 00:00:00 2001
From: Christian Marangi <ansuelsmth@gmail.com>
Date: Fri, 15 Dec 2023 14:15:32 +0100
Subject: net: phy: extend PHY package API to support multiple global address

Current API for PHY package are limited to single address to configure
global settings for the PHY package.

It was found that some PHY package (for example the qca807x, a PHY
package that is shipped with a bundle of 5 PHY) requires multiple PHY
address to configure global settings. An example scenario is a PHY that
have a dedicated PHY for PSGMII/serdes calibrarion and have a specific
PHY in the package where the global PHY mode is set and affects every
other PHY in the package.

Change the API in the following way:
- Change phy_package_join() to take the base addr of the PHY package
  instead of the global PHY addr.
- Make __/phy_package_write/read() require an additional arg that
  select what global PHY address to use by passing the offset from the
  base addr passed on phy_package_join().

Each user of this API is updated to follow this new implementation
following a pattern where an enum is defined to declare the offset of the
addr.

We also drop the check if shared is defined as any user of the
phy_package_read/write is expected to use phy_package_join first. Misuse
of this will correctly trigger a kernel panic for NULL pointer
exception.

Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/bcm54140.c       | 16 +++++++---
 drivers/net/phy/mscc/mscc.h      |  5 ++++
 drivers/net/phy/mscc/mscc_main.c |  4 +--
 drivers/net/phy/phy_device.c     | 35 ++++++++++++----------
 include/linux/phy.h              | 64 ++++++++++++++++++++++++++--------------
 5 files changed, 80 insertions(+), 44 deletions(-)

(limited to 'include')

diff --git a/drivers/net/phy/bcm54140.c b/drivers/net/phy/bcm54140.c
index d43076592f81..2eea3d09b1e6 100644
--- a/drivers/net/phy/bcm54140.c
+++ b/drivers/net/phy/bcm54140.c
@@ -128,6 +128,10 @@
 #define BCM54140_DEFAULT_DOWNSHIFT 5
 #define BCM54140_MAX_DOWNSHIFT 9
 
+enum bcm54140_global_phy {
+	BCM54140_BASE_ADDR = 0,
+};
+
 struct bcm54140_priv {
 	int port;
 	int base_addr;
@@ -429,11 +433,13 @@ static int bcm54140_base_read_rdb(struct phy_device *phydev, u16 rdb)
 	int ret;
 
 	phy_lock_mdio_bus(phydev);
-	ret = __phy_package_write(phydev, MII_BCM54XX_RDB_ADDR, rdb);
+	ret = __phy_package_write(phydev, BCM54140_BASE_ADDR,
+				  MII_BCM54XX_RDB_ADDR, rdb);
 	if (ret < 0)
 		goto out;
 
-	ret = __phy_package_read(phydev, MII_BCM54XX_RDB_DATA);
+	ret = __phy_package_read(phydev, BCM54140_BASE_ADDR,
+				 MII_BCM54XX_RDB_DATA);
 
 out:
 	phy_unlock_mdio_bus(phydev);
@@ -446,11 +452,13 @@ static int bcm54140_base_write_rdb(struct phy_device *phydev,
 	int ret;
 
 	phy_lock_mdio_bus(phydev);
-	ret = __phy_package_write(phydev, MII_BCM54XX_RDB_ADDR, rdb);
+	ret = __phy_package_write(phydev, BCM54140_BASE_ADDR,
+				  MII_BCM54XX_RDB_ADDR, rdb);
 	if (ret < 0)
 		goto out;
 
-	ret = __phy_package_write(phydev, MII_BCM54XX_RDB_DATA, val);
+	ret = __phy_package_write(phydev, BCM54140_BASE_ADDR,
+				  MII_BCM54XX_RDB_DATA, val);
 
 out:
 	phy_unlock_mdio_bus(phydev);
diff --git a/drivers/net/phy/mscc/mscc.h b/drivers/net/phy/mscc/mscc.h
index 7a962050a4d4..6a3d8a754eb8 100644
--- a/drivers/net/phy/mscc/mscc.h
+++ b/drivers/net/phy/mscc/mscc.h
@@ -416,6 +416,11 @@ struct vsc8531_private {
  * gpio_lock: used for PHC operations. Common for all PHYs as the load/save GPIO
  * is shared.
  */
+
+enum vsc85xx_global_phy {
+	VSC88XX_BASE_ADDR = 0,
+};
+
 struct vsc85xx_shared_private {
 	struct mutex gpio_lock;
 };
diff --git a/drivers/net/phy/mscc/mscc_main.c b/drivers/net/phy/mscc/mscc_main.c
index 4171f01d34e5..6f74ce0ab1aa 100644
--- a/drivers/net/phy/mscc/mscc_main.c
+++ b/drivers/net/phy/mscc/mscc_main.c
@@ -711,7 +711,7 @@ int phy_base_write(struct phy_device *phydev, u32 regnum, u16 val)
 		dump_stack();
 	}
 
-	return __phy_package_write(phydev, regnum, val);
+	return __phy_package_write(phydev, VSC88XX_BASE_ADDR, regnum, val);
 }
 
 /* phydev->bus->mdio_lock should be locked when using this function */
@@ -722,7 +722,7 @@ int phy_base_read(struct phy_device *phydev, u32 regnum)
 		dump_stack();
 	}
 
-	return __phy_package_read(phydev, regnum);
+	return __phy_package_read(phydev, VSC88XX_BASE_ADDR, regnum);
 }
 
 u32 vsc85xx_csr_read(struct phy_device *phydev,
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index d8e9335d415c..0c52a9eff188 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1651,20 +1651,22 @@ EXPORT_SYMBOL_GPL(phy_driver_is_genphy_10g);
 /**
  * phy_package_join - join a common PHY group
  * @phydev: target phy_device struct
- * @addr: cookie and PHY address for global register access
+ * @base_addr: cookie and base PHY address of PHY package for offset
+ *   calculation of global register access
  * @priv_size: if non-zero allocate this amount of bytes for private data
  *
  * This joins a PHY group and provides a shared storage for all phydevs in
  * this group. This is intended to be used for packages which contain
  * more than one PHY, for example a quad PHY transceiver.
  *
- * The addr parameter serves as a cookie which has to have the same value
- * for all members of one group and as a PHY address to access generic
- * registers of a PHY package. Usually, one of the PHY addresses of the
- * different PHYs in the package provides access to these global registers.
+ * The base_addr parameter serves as cookie which has to have the same values
+ * for all members of one group and as the base PHY address of the PHY package
+ * for offset calculation to access generic registers of a PHY package.
+ * Usually, one of the PHY addresses of the different PHYs in the package
+ * provides access to these global registers.
  * The address which is given here, will be used in the phy_package_read()
- * and phy_package_write() convenience functions. If your PHY doesn't have
- * global registers you can just pick any of the PHY addresses.
+ * and phy_package_write() convenience functions as base and added to the
+ * passed offset in those functions.
  *
  * This will set the shared pointer of the phydev to the shared storage.
  * If this is the first call for a this cookie the shared storage will be
@@ -1674,17 +1676,17 @@ EXPORT_SYMBOL_GPL(phy_driver_is_genphy_10g);
  * Returns < 1 on error, 0 on success. Esp. calling phy_package_join()
  * with the same cookie but a different priv_size is an error.
  */
-int phy_package_join(struct phy_device *phydev, int addr, size_t priv_size)
+int phy_package_join(struct phy_device *phydev, int base_addr, size_t priv_size)
 {
 	struct mii_bus *bus = phydev->mdio.bus;
 	struct phy_package_shared *shared;
 	int ret;
 
-	if (addr < 0 || addr >= PHY_MAX_ADDR)
+	if (base_addr < 0 || base_addr >= PHY_MAX_ADDR)
 		return -EINVAL;
 
 	mutex_lock(&bus->shared_lock);
-	shared = bus->shared[addr];
+	shared = bus->shared[base_addr];
 	if (!shared) {
 		ret = -ENOMEM;
 		shared = kzalloc(sizeof(*shared), GFP_KERNEL);
@@ -1696,9 +1698,9 @@ int phy_package_join(struct phy_device *phydev, int addr, size_t priv_size)
 				goto err_free;
 			shared->priv_size = priv_size;
 		}
-		shared->addr = addr;
+		shared->base_addr = base_addr;
 		refcount_set(&shared->refcnt, 1);
-		bus->shared[addr] = shared;
+		bus->shared[base_addr] = shared;
 	} else {
 		ret = -EINVAL;
 		if (priv_size && priv_size != shared->priv_size)
@@ -1736,7 +1738,7 @@ void phy_package_leave(struct phy_device *phydev)
 		return;
 
 	if (refcount_dec_and_mutex_lock(&shared->refcnt, &bus->shared_lock)) {
-		bus->shared[shared->addr] = NULL;
+		bus->shared[shared->base_addr] = NULL;
 		mutex_unlock(&bus->shared_lock);
 		kfree(shared->priv);
 		kfree(shared);
@@ -1755,7 +1757,8 @@ static void devm_phy_package_leave(struct device *dev, void *res)
  * devm_phy_package_join - resource managed phy_package_join()
  * @dev: device that is registering this PHY package
  * @phydev: target phy_device struct
- * @addr: cookie and PHY address for global register access
+ * @base_addr: cookie and base PHY address of PHY package for offset
+ *   calculation of global register access
  * @priv_size: if non-zero allocate this amount of bytes for private data
  *
  * Managed phy_package_join(). Shared storage fetched by this function,
@@ -1763,7 +1766,7 @@ static void devm_phy_package_leave(struct device *dev, void *res)
  * phy_package_join() for more information.
  */
 int devm_phy_package_join(struct device *dev, struct phy_device *phydev,
-			  int addr, size_t priv_size)
+			  int base_addr, size_t priv_size)
 {
 	struct phy_device **ptr;
 	int ret;
@@ -1773,7 +1776,7 @@ int devm_phy_package_join(struct device *dev, struct phy_device *phydev,
 	if (!ptr)
 		return -ENOMEM;
 
-	ret = phy_package_join(phydev, addr, priv_size);
+	ret = phy_package_join(phydev, base_addr, priv_size);
 
 	if (!ret) {
 		*ptr = phydev;
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 4b13cc85c4f5..d653f660c39d 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -327,7 +327,8 @@ struct mdio_bus_stats {
 
 /**
  * struct phy_package_shared - Shared information in PHY packages
- * @addr: Common PHY address used to combine PHYs in one package
+ * @base_addr: Base PHY address of PHY package used to combine PHYs
+ *   in one package and for offset calculation of phy_package_read/write
  * @refcnt: Number of PHYs connected to this shared data
  * @flags: Initialization of PHY package
  * @priv_size: Size of the shared private data @priv
@@ -338,7 +339,7 @@ struct mdio_bus_stats {
  * phy_package_leave().
  */
 struct phy_package_shared {
-	u8 addr;
+	u8 base_addr;
 	refcount_t refcnt;
 	unsigned long flags;
 	size_t priv_size;
@@ -1976,10 +1977,10 @@ int phy_ethtool_get_link_ksettings(struct net_device *ndev,
 int phy_ethtool_set_link_ksettings(struct net_device *ndev,
 				   const struct ethtool_link_ksettings *cmd);
 int phy_ethtool_nway_reset(struct net_device *ndev);
-int phy_package_join(struct phy_device *phydev, int addr, size_t priv_size);
+int phy_package_join(struct phy_device *phydev, int base_addr, size_t priv_size);
 void phy_package_leave(struct phy_device *phydev);
 int devm_phy_package_join(struct device *dev, struct phy_device *phydev,
-			  int addr, size_t priv_size);
+			  int base_addr, size_t priv_size);
 
 int __init mdio_bus_init(void);
 void mdio_bus_exit(void);
@@ -2002,46 +2003,65 @@ int __phy_hwtstamp_set(struct phy_device *phydev,
 		       struct kernel_hwtstamp_config *config,
 		       struct netlink_ext_ack *extack);
 
-static inline int phy_package_read(struct phy_device *phydev, u32 regnum)
+static inline int phy_package_address(struct phy_device *phydev,
+				      unsigned int addr_offset)
 {
 	struct phy_package_shared *shared = phydev->shared;
+	u8 base_addr = shared->base_addr;
 
-	if (!shared)
+	if (addr_offset >= PHY_MAX_ADDR - base_addr)
 		return -EIO;
 
-	return mdiobus_read(phydev->mdio.bus, shared->addr, regnum);
+	/* we know that addr will be in the range 0..31 and thus the
+	 * implicit cast to a signed int is not a problem.
+	 */
+	return base_addr + addr_offset;
 }
 
-static inline int __phy_package_read(struct phy_device *phydev, u32 regnum)
+static inline int phy_package_read(struct phy_device *phydev,
+				   unsigned int addr_offset, u32 regnum)
 {
-	struct phy_package_shared *shared = phydev->shared;
+	int addr = phy_package_address(phydev, addr_offset);
 
-	if (!shared)
-		return -EIO;
+	if (addr < 0)
+		return addr;
+
+	return mdiobus_read(phydev->mdio.bus, addr, regnum);
+}
+
+static inline int __phy_package_read(struct phy_device *phydev,
+				     unsigned int addr_offset, u32 regnum)
+{
+	int addr = phy_package_address(phydev, addr_offset);
+
+	if (addr < 0)
+		return addr;
 
-	return __mdiobus_read(phydev->mdio.bus, shared->addr, regnum);
+	return __mdiobus_read(phydev->mdio.bus, addr, regnum);
 }
 
 static inline int phy_package_write(struct phy_device *phydev,
-				    u32 regnum, u16 val)
+				    unsigned int addr_offset, u32 regnum,
+				    u16 val)
 {
-	struct phy_package_shared *shared = phydev->shared;
+	int addr = phy_package_address(phydev, addr_offset);
 
-	if (!shared)
-		return -EIO;
+	if (addr < 0)
+		return addr;
 
-	return mdiobus_write(phydev->mdio.bus, shared->addr, regnum, val);
+	return mdiobus_write(phydev->mdio.bus, addr, regnum, val);
 }
 
 static inline int __phy_package_write(struct phy_device *phydev,
-				      u32 regnum, u16 val)
+				      unsigned int addr_offset, u32 regnum,
+				      u16 val)
 {
-	struct phy_package_shared *shared = phydev->shared;
+	int addr = phy_package_address(phydev, addr_offset);
 
-	if (!shared)
-		return -EIO;
+	if (addr < 0)
+		return addr;
 
-	return __mdiobus_write(phydev->mdio.bus, shared->addr, regnum, val);
+	return __mdiobus_write(phydev->mdio.bus, addr, regnum, val);
 }
 
 static inline bool __phy_package_set_once(struct phy_device *phydev,
-- 
cgit v1.2.3


From d63710fc0f1a501fd75a7025e3070a96ffa1645f Mon Sep 17 00:00:00 2001
From: Christian Marangi <ansuelsmth@gmail.com>
Date: Fri, 15 Dec 2023 14:15:34 +0100
Subject: net: phy: add support for PHY package MMD read/write

Some PHY in PHY package may require to read/write MMD regs to correctly
configure the PHY package.

Add support for these additional required function in both lock and no
lock variant.

It's assumed that the entire PHY package is either C22 or C45. We use
C22 or C45 way of writing/reading to mmd regs based on the passed phydev
whether it's C22 or C45.

Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy-core.c | 140 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/phy.h        |  16 ++++++
 2 files changed, 156 insertions(+)

(limited to 'include')

diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c
index b729ac8b2640..15f349e5995a 100644
--- a/drivers/net/phy/phy-core.c
+++ b/drivers/net/phy/phy-core.c
@@ -650,6 +650,146 @@ int phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val)
 }
 EXPORT_SYMBOL(phy_write_mmd);
 
+/**
+ * __phy_package_read_mmd - read MMD reg relative to PHY package base addr
+ * @phydev: The phy_device struct
+ * @addr_offset: The offset to be added to PHY package base_addr
+ * @devad: The MMD to read from
+ * @regnum: The register on the MMD to read
+ *
+ * Convenience helper for reading a register of an MMD on a given PHY
+ * using the PHY package base address. The base address is added to
+ * the addr_offset value.
+ *
+ * Same calling rules as for __phy_read();
+ *
+ * NOTE: It's assumed that the entire PHY package is either C22 or C45.
+ */
+int __phy_package_read_mmd(struct phy_device *phydev,
+			   unsigned int addr_offset, int devad,
+			   u32 regnum)
+{
+	int addr = phy_package_address(phydev, addr_offset);
+
+	if (addr < 0)
+		return addr;
+
+	if (regnum > (u16)~0 || devad > 32)
+		return -EINVAL;
+
+	return mmd_phy_read(phydev->mdio.bus, addr, phydev->is_c45, devad,
+			    regnum);
+}
+EXPORT_SYMBOL(__phy_package_read_mmd);
+
+/**
+ * phy_package_read_mmd - read MMD reg relative to PHY package base addr
+ * @phydev: The phy_device struct
+ * @addr_offset: The offset to be added to PHY package base_addr
+ * @devad: The MMD to read from
+ * @regnum: The register on the MMD to read
+ *
+ * Convenience helper for reading a register of an MMD on a given PHY
+ * using the PHY package base address. The base address is added to
+ * the addr_offset value.
+ *
+ * Same calling rules as for phy_read();
+ *
+ * NOTE: It's assumed that the entire PHY package is either C22 or C45.
+ */
+int phy_package_read_mmd(struct phy_device *phydev,
+			 unsigned int addr_offset, int devad,
+			 u32 regnum)
+{
+	int addr = phy_package_address(phydev, addr_offset);
+	int val;
+
+	if (addr < 0)
+		return addr;
+
+	if (regnum > (u16)~0 || devad > 32)
+		return -EINVAL;
+
+	phy_lock_mdio_bus(phydev);
+	val = mmd_phy_read(phydev->mdio.bus, addr, phydev->is_c45, devad,
+			   regnum);
+	phy_unlock_mdio_bus(phydev);
+
+	return val;
+}
+EXPORT_SYMBOL(phy_package_read_mmd);
+
+/**
+ * __phy_package_write_mmd - write MMD reg relative to PHY package base addr
+ * @phydev: The phy_device struct
+ * @addr_offset: The offset to be added to PHY package base_addr
+ * @devad: The MMD to write to
+ * @regnum: The register on the MMD to write
+ * @val: value to write to @regnum
+ *
+ * Convenience helper for writing a register of an MMD on a given PHY
+ * using the PHY package base address. The base address is added to
+ * the addr_offset value.
+ *
+ * Same calling rules as for __phy_write();
+ *
+ * NOTE: It's assumed that the entire PHY package is either C22 or C45.
+ */
+int __phy_package_write_mmd(struct phy_device *phydev,
+			    unsigned int addr_offset, int devad,
+			    u32 regnum, u16 val)
+{
+	int addr = phy_package_address(phydev, addr_offset);
+
+	if (addr < 0)
+		return addr;
+
+	if (regnum > (u16)~0 || devad > 32)
+		return -EINVAL;
+
+	return mmd_phy_write(phydev->mdio.bus, addr, phydev->is_c45, devad,
+			     regnum, val);
+}
+EXPORT_SYMBOL(__phy_package_write_mmd);
+
+/**
+ * phy_package_write_mmd - write MMD reg relative to PHY package base addr
+ * @phydev: The phy_device struct
+ * @addr_offset: The offset to be added to PHY package base_addr
+ * @devad: The MMD to write to
+ * @regnum: The register on the MMD to write
+ * @val: value to write to @regnum
+ *
+ * Convenience helper for writing a register of an MMD on a given PHY
+ * using the PHY package base address. The base address is added to
+ * the addr_offset value.
+ *
+ * Same calling rules as for phy_write();
+ *
+ * NOTE: It's assumed that the entire PHY package is either C22 or C45.
+ */
+int phy_package_write_mmd(struct phy_device *phydev,
+			  unsigned int addr_offset, int devad,
+			  u32 regnum, u16 val)
+{
+	int addr = phy_package_address(phydev, addr_offset);
+	int ret;
+
+	if (addr < 0)
+		return addr;
+
+	if (regnum > (u16)~0 || devad > 32)
+		return -EINVAL;
+
+	phy_lock_mdio_bus(phydev);
+	ret = mmd_phy_write(phydev->mdio.bus, addr, phydev->is_c45, devad,
+			    regnum, val);
+	phy_unlock_mdio_bus(phydev);
+
+	return ret;
+}
+EXPORT_SYMBOL(phy_package_write_mmd);
+
 /**
  * phy_modify_changed - Function for modifying a PHY register
  * @phydev: the phy_device struct
diff --git a/include/linux/phy.h b/include/linux/phy.h
index d653f660c39d..e9e85d347587 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -2064,6 +2064,22 @@ static inline int __phy_package_write(struct phy_device *phydev,
 	return __mdiobus_write(phydev->mdio.bus, addr, regnum, val);
 }
 
+int __phy_package_read_mmd(struct phy_device *phydev,
+			   unsigned int addr_offset, int devad,
+			   u32 regnum);
+
+int phy_package_read_mmd(struct phy_device *phydev,
+			 unsigned int addr_offset, int devad,
+			 u32 regnum);
+
+int __phy_package_write_mmd(struct phy_device *phydev,
+			    unsigned int addr_offset, int devad,
+			    u32 regnum, u16 val);
+
+int phy_package_write_mmd(struct phy_device *phydev,
+			  unsigned int addr_offset, int devad,
+			  u32 regnum, u16 val);
+
 static inline bool __phy_package_set_once(struct phy_device *phydev,
 					  unsigned int b)
 {
-- 
cgit v1.2.3


From 120931db07b49252aba2073096b595482d71857c Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Mon, 27 Nov 2023 23:36:52 -0600
Subject: rtc: Add support for configuring the UIP timeout for RTC reads
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The UIP timeout is hardcoded to 10ms for all RTC reads, but in some
contexts this might not be enough time. Add a timeout parameter to
mc146818_get_time() and mc146818_get_time_callback().

If UIP timeout is configured by caller to be >=100 ms and a call
takes this long, log a warning.

Make all callers use 10ms to ensure no functional changes.

Cc:  <stable@vger.kernel.org> # 6.1.y
Fixes: ec5895c0f2d8 ("rtc: mc146818-lib: extract mc146818_avoid_UIP")
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Tested-by: Mateusz Jończyk <mat.jonczyk@o2.pl>
Reviewed-by: Mateusz Jończyk <mat.jonczyk@o2.pl>
Acked-by: Mateusz Jończyk <mat.jonczyk@o2.pl>
Link: https://lore.kernel.org/r/20231128053653.101798-4-mario.limonciello@amd.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 arch/alpha/kernel/rtc.c        |  2 +-
 arch/x86/kernel/hpet.c         |  2 +-
 arch/x86/kernel/rtc.c          |  2 +-
 drivers/base/power/trace.c     |  2 +-
 drivers/rtc/rtc-cmos.c         |  6 +++---
 drivers/rtc/rtc-mc146818-lib.c | 37 +++++++++++++++++++++++++++++--------
 include/linux/mc146818rtc.h    |  3 ++-
 7 files changed, 38 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/kernel/rtc.c b/arch/alpha/kernel/rtc.c
index fb3025396ac9..cfdf90bc8b3f 100644
--- a/arch/alpha/kernel/rtc.c
+++ b/arch/alpha/kernel/rtc.c
@@ -80,7 +80,7 @@ init_rtc_epoch(void)
 static int
 alpha_rtc_read_time(struct device *dev, struct rtc_time *tm)
 {
-	int ret = mc146818_get_time(tm);
+	int ret = mc146818_get_time(tm, 10);
 
 	if (ret < 0) {
 		dev_err_ratelimited(dev, "unable to read current time\n");
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 41eecf180b7f..17adad4cbe78 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -1438,7 +1438,7 @@ irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id)
 	memset(&curr_time, 0, sizeof(struct rtc_time));
 
 	if (hpet_rtc_flags & (RTC_UIE | RTC_AIE)) {
-		if (unlikely(mc146818_get_time(&curr_time) < 0)) {
+		if (unlikely(mc146818_get_time(&curr_time, 10) < 0)) {
 			pr_err_ratelimited("unable to read current time from RTC\n");
 			return IRQ_HANDLED;
 		}
diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index 1309b9b05338..961ebc7f1872 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -67,7 +67,7 @@ void mach_get_cmos_time(struct timespec64 *now)
 		return;
 	}
 
-	if (mc146818_get_time(&tm)) {
+	if (mc146818_get_time(&tm, 10)) {
 		pr_err("Unable to read current time from RTC\n");
 		now->tv_sec = now->tv_nsec = 0;
 		return;
diff --git a/drivers/base/power/trace.c b/drivers/base/power/trace.c
index 72b7a92337b1..c2e925357474 100644
--- a/drivers/base/power/trace.c
+++ b/drivers/base/power/trace.c
@@ -120,7 +120,7 @@ static unsigned int read_magic_time(void)
 	struct rtc_time time;
 	unsigned int val;
 
-	if (mc146818_get_time(&time) < 0) {
+	if (mc146818_get_time(&time, 10) < 0) {
 		pr_err("Unable to read current time from RTC\n");
 		return 0;
 	}
diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index 2a1a83caf081..468ccd99f218 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -231,7 +231,7 @@ static int cmos_read_time(struct device *dev, struct rtc_time *t)
 	if (!pm_trace_rtc_valid())
 		return -EIO;
 
-	ret = mc146818_get_time(t);
+	ret = mc146818_get_time(t, 10);
 	if (ret < 0) {
 		dev_err_ratelimited(dev, "unable to read current time\n");
 		return ret;
@@ -307,7 +307,7 @@ static int cmos_read_alarm(struct device *dev, struct rtc_wkalrm *t)
 	 *
 	 * Use the mc146818_avoid_UIP() function to avoid this.
 	 */
-	if (!mc146818_avoid_UIP(cmos_read_alarm_callback, &p))
+	if (!mc146818_avoid_UIP(cmos_read_alarm_callback, 10, &p))
 		return -EIO;
 
 	if (!(p.rtc_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) {
@@ -556,7 +556,7 @@ static int cmos_set_alarm(struct device *dev, struct rtc_wkalrm *t)
 	 *
 	 * Use mc146818_avoid_UIP() to avoid this.
 	 */
-	if (!mc146818_avoid_UIP(cmos_set_alarm_callback, &p))
+	if (!mc146818_avoid_UIP(cmos_set_alarm_callback, 10, &p))
 		return -ETIMEDOUT;
 
 	cmos->alarm_expires = rtc_tm_to_time64(&t->time);
diff --git a/drivers/rtc/rtc-mc146818-lib.c b/drivers/rtc/rtc-mc146818-lib.c
index 43a28e82674e..4c17b3cef11e 100644
--- a/drivers/rtc/rtc-mc146818-lib.c
+++ b/drivers/rtc/rtc-mc146818-lib.c
@@ -8,26 +8,31 @@
 #include <linux/acpi.h>
 #endif
 
+#define UIP_RECHECK_DELAY		100	/* usec */
+#define UIP_RECHECK_DELAY_MS		(USEC_PER_MSEC / UIP_RECHECK_DELAY)
+#define UIP_RECHECK_LOOPS_MS(x)		(x / UIP_RECHECK_DELAY_MS)
+
 /*
  * Execute a function while the UIP (Update-in-progress) bit of the RTC is
- * unset.
+ * unset. The timeout is configurable by the caller in ms.
  *
  * Warning: callback may be executed more then once.
  */
 bool mc146818_avoid_UIP(void (*callback)(unsigned char seconds, void *param),
+			int timeout,
 			void *param)
 {
 	int i;
 	unsigned long flags;
 	unsigned char seconds;
 
-	for (i = 0; i < 100; i++) {
+	for (i = 0; UIP_RECHECK_LOOPS_MS(i) < timeout; i++) {
 		spin_lock_irqsave(&rtc_lock, flags);
 
 		/*
 		 * Check whether there is an update in progress during which the
 		 * readout is unspecified. The maximum update time is ~2ms. Poll
-		 * every 100 usec for completion.
+		 * for completion.
 		 *
 		 * Store the second value before checking UIP so a long lasting
 		 * NMI which happens to hit after the UIP check cannot make
@@ -37,7 +42,7 @@ bool mc146818_avoid_UIP(void (*callback)(unsigned char seconds, void *param),
 
 		if (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP) {
 			spin_unlock_irqrestore(&rtc_lock, flags);
-			udelay(100);
+			udelay(UIP_RECHECK_DELAY);
 			continue;
 		}
 
@@ -56,7 +61,7 @@ bool mc146818_avoid_UIP(void (*callback)(unsigned char seconds, void *param),
 		 */
 		if (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP) {
 			spin_unlock_irqrestore(&rtc_lock, flags);
-			udelay(100);
+			udelay(UIP_RECHECK_DELAY);
 			continue;
 		}
 
@@ -72,6 +77,10 @@ bool mc146818_avoid_UIP(void (*callback)(unsigned char seconds, void *param),
 		}
 		spin_unlock_irqrestore(&rtc_lock, flags);
 
+		if (UIP_RECHECK_LOOPS_MS(i) >= 100)
+			pr_warn("Reading current time from RTC took around %li ms\n",
+				UIP_RECHECK_LOOPS_MS(i));
+
 		return true;
 	}
 	return false;
@@ -84,7 +93,7 @@ EXPORT_SYMBOL_GPL(mc146818_avoid_UIP);
  */
 bool mc146818_does_rtc_work(void)
 {
-	return mc146818_avoid_UIP(NULL, NULL);
+	return mc146818_avoid_UIP(NULL, 10, NULL);
 }
 EXPORT_SYMBOL_GPL(mc146818_does_rtc_work);
 
@@ -130,13 +139,25 @@ static void mc146818_get_time_callback(unsigned char seconds, void *param_in)
 	p->ctrl = CMOS_READ(RTC_CONTROL);
 }
 
-int mc146818_get_time(struct rtc_time *time)
+/**
+ * mc146818_get_time - Get the current time from the RTC
+ * @time: pointer to struct rtc_time to store the current time
+ * @timeout: timeout value in ms
+ *
+ * This function reads the current time from the RTC and stores it in the
+ * provided struct rtc_time. The timeout parameter specifies the maximum
+ * time to wait for the RTC to become ready.
+ *
+ * Return: 0 on success, -ETIMEDOUT if the RTC did not become ready within
+ * the specified timeout, or another error code if an error occurred.
+ */
+int mc146818_get_time(struct rtc_time *time, int timeout)
 {
 	struct mc146818_get_time_callback_param p = {
 		.time = time
 	};
 
-	if (!mc146818_avoid_UIP(mc146818_get_time_callback, &p)) {
+	if (!mc146818_avoid_UIP(mc146818_get_time_callback, timeout, &p)) {
 		memset(time, 0, sizeof(*time));
 		return -ETIMEDOUT;
 	}
diff --git a/include/linux/mc146818rtc.h b/include/linux/mc146818rtc.h
index b0da04fe087b..34dfcc77f505 100644
--- a/include/linux/mc146818rtc.h
+++ b/include/linux/mc146818rtc.h
@@ -126,10 +126,11 @@ struct cmos_rtc_board_info {
 #endif /* ARCH_RTC_LOCATION */
 
 bool mc146818_does_rtc_work(void);
-int mc146818_get_time(struct rtc_time *time);
+int mc146818_get_time(struct rtc_time *time, int timeout);
 int mc146818_set_time(struct rtc_time *time);
 
 bool mc146818_avoid_UIP(void (*callback)(unsigned char seconds, void *param),
+			int timeout,
 			void *param);
 
 #endif /* _MC146818RTC_H */
-- 
cgit v1.2.3


From b5be49db3d47eae30998174410a0eaac9816c0cf Mon Sep 17 00:00:00 2001
From: Gabriel Fernandez <gabriel.fernandez@foss.st.com>
Date: Fri, 8 Dec 2023 15:36:58 +0100
Subject: dt-bindings: stm32: add clocks and reset binding for stm32mp25
 platform

Adds clock and reset binding entries for STM32MP25 SoC family

Signed-off-by: Gabriel Fernandez <gabriel.fernandez@foss.st.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20231208143700.354785-4-gabriel.fernandez@foss.st.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 .../bindings/clock/st,stm32mp25-rcc.yaml           |  76 ++++
 include/dt-bindings/clock/st,stm32mp25-rcc.h       | 492 +++++++++++++++++++++
 include/dt-bindings/reset/st,stm32mp25-rcc.h       | 167 +++++++
 3 files changed, 735 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/clock/st,stm32mp25-rcc.yaml
 create mode 100644 include/dt-bindings/clock/st,stm32mp25-rcc.h
 create mode 100644 include/dt-bindings/reset/st,stm32mp25-rcc.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/clock/st,stm32mp25-rcc.yaml b/Documentation/devicetree/bindings/clock/st,stm32mp25-rcc.yaml
new file mode 100644
index 000000000000..7732e79a42b9
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/st,stm32mp25-rcc.yaml
@@ -0,0 +1,76 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/st,stm32mp25-rcc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: STM32MP25 Reset Clock Controller
+
+maintainers:
+  - Gabriel Fernandez <gabriel.fernandez@foss.st.com>
+
+description: |
+  The RCC hardware block is both a reset and a clock controller.
+  RCC makes also power management (resume/supend).
+
+  See also::
+    include/dt-bindings/clock/st,stm32mp25-rcc.h
+    include/dt-bindings/reset/st,stm32mp25-rcc.h
+
+properties:
+  compatible:
+    enum:
+      - st,stm32mp25-rcc
+
+  reg:
+    maxItems: 1
+
+  '#clock-cells':
+    const: 1
+
+  '#reset-cells':
+    const: 1
+
+  clocks:
+    items:
+      - description: CK_SCMI_HSE High Speed External oscillator (8 to 48 MHz)
+      - description: CK_SCMI_HSI High Speed Internal oscillator (~ 64 MHz)
+      - description: CK_SCMI_MSI Low Power Internal oscillator (~ 4 MHz or ~ 16 MHz)
+      - description: CK_SCMI_LSE Low Speed External oscillator (32 KHz)
+      - description: CK_SCMI_LSI Low Speed Internal oscillator (~ 32 KHz)
+
+  clock-names:
+    items:
+      - const: hse
+      - const: hsi
+      - const: msi
+      - const: lse
+      - const: lsi
+
+required:
+  - compatible
+  - reg
+  - '#clock-cells'
+  - '#reset-cells'
+  - clocks
+  - clock-names
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/st,stm32mp25-rcc.h>
+
+    rcc: clock-controller@44200000 {
+        compatible = "st,stm32mp25-rcc";
+        reg = <0x44200000 0x10000>;
+        #clock-cells = <1>;
+        #reset-cells = <1>;
+        clock-names = "hse", "hsi", "msi", "lse", "lsi";
+        clocks = <&scmi_clk CK_SCMI_HSE>,
+                 <&scmi_clk CK_SCMI_HSI>,
+                 <&scmi_clk CK_SCMI_MSI>,
+                 <&scmi_clk CK_SCMI_LSE>,
+                 <&scmi_clk CK_SCMI_LSI>;
+    };
+...
diff --git a/include/dt-bindings/clock/st,stm32mp25-rcc.h b/include/dt-bindings/clock/st,stm32mp25-rcc.h
new file mode 100644
index 000000000000..b6cf05ad4be6
--- /dev/null
+++ b/include/dt-bindings/clock/st,stm32mp25-rcc.h
@@ -0,0 +1,492 @@
+/* SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause */
+/*
+ * Copyright (C) STMicroelectronics 2023 - All Rights Reserved
+ * Author: Gabriel Fernandez <gabriel.fernandez@foss.st.com>
+ */
+
+#ifndef _DT_BINDINGS_STM32MP25_CLKS_H_
+#define _DT_BINDINGS_STM32MP25_CLKS_H_
+
+/* INTERNAL/EXTERNAL OSCILLATORS */
+#define HSI_CK			0
+#define HSE_CK			1
+#define MSI_CK			2
+#define LSI_CK			3
+#define LSE_CK			4
+#define I2S_CK			5
+#define RTC_CK			6
+#define SPDIF_CK_SYMB		7
+
+/* PLL CLOCKS */
+#define PLL1_CK			8
+#define PLL2_CK			9
+#define PLL3_CK			10
+#define PLL4_CK			11
+#define PLL5_CK			12
+#define PLL6_CK			13
+#define PLL7_CK			14
+#define PLL8_CK			15
+
+#define CK_CPU1			16
+
+/* APB DIV CLOCKS */
+#define CK_ICN_APB1		17
+#define CK_ICN_APB2		18
+#define CK_ICN_APB3		19
+#define CK_ICN_APB4		20
+#define CK_ICN_APBDBG		21
+
+/* GLOBAL TIMER */
+#define TIMG1_CK		22
+#define TIMG2_CK		23
+
+/* FLEXGEN CLOCKS */
+#define CK_ICN_HS_MCU		24
+#define CK_ICN_SDMMC		25
+#define CK_ICN_DDR		26
+#define CK_ICN_DISPLAY		27
+#define CK_ICN_HSL		28
+#define CK_ICN_NIC		29
+#define CK_ICN_VID		30
+#define CK_FLEXGEN_07		31
+#define CK_FLEXGEN_08		32
+#define CK_FLEXGEN_09		33
+#define CK_FLEXGEN_10		34
+#define CK_FLEXGEN_11		35
+#define CK_FLEXGEN_12		36
+#define CK_FLEXGEN_13		37
+#define CK_FLEXGEN_14		38
+#define CK_FLEXGEN_15		39
+#define CK_FLEXGEN_16		40
+#define CK_FLEXGEN_17		41
+#define CK_FLEXGEN_18		42
+#define CK_FLEXGEN_19		43
+#define CK_FLEXGEN_20		44
+#define CK_FLEXGEN_21		45
+#define CK_FLEXGEN_22		46
+#define CK_FLEXGEN_23		47
+#define CK_FLEXGEN_24		48
+#define CK_FLEXGEN_25		49
+#define CK_FLEXGEN_26		50
+#define CK_FLEXGEN_27		51
+#define CK_FLEXGEN_28		52
+#define CK_FLEXGEN_29		53
+#define CK_FLEXGEN_30		54
+#define CK_FLEXGEN_31		55
+#define CK_FLEXGEN_32		56
+#define CK_FLEXGEN_33		57
+#define CK_FLEXGEN_34		58
+#define CK_FLEXGEN_35		59
+#define CK_FLEXGEN_36		60
+#define CK_FLEXGEN_37		61
+#define CK_FLEXGEN_38		62
+#define CK_FLEXGEN_39		63
+#define CK_FLEXGEN_40		64
+#define CK_FLEXGEN_41		65
+#define CK_FLEXGEN_42		66
+#define CK_FLEXGEN_43		67
+#define CK_FLEXGEN_44		68
+#define CK_FLEXGEN_45		69
+#define CK_FLEXGEN_46		70
+#define CK_FLEXGEN_47		71
+#define CK_FLEXGEN_48		72
+#define CK_FLEXGEN_49		73
+#define CK_FLEXGEN_50		74
+#define CK_FLEXGEN_51		75
+#define CK_FLEXGEN_52		76
+#define CK_FLEXGEN_53		77
+#define CK_FLEXGEN_54		78
+#define CK_FLEXGEN_55		79
+#define CK_FLEXGEN_56		80
+#define CK_FLEXGEN_57		81
+#define CK_FLEXGEN_58		82
+#define CK_FLEXGEN_59		83
+#define CK_FLEXGEN_60		84
+#define CK_FLEXGEN_61		85
+#define CK_FLEXGEN_62		86
+#define CK_FLEXGEN_63		87
+
+/* LOW SPEED MCU CLOCK */
+#define CK_ICN_LS_MCU		88
+
+#define CK_BUS_STM500		89
+#define CK_BUS_FMC		90
+#define CK_BUS_GPU		91
+#define CK_BUS_ETH1		92
+#define CK_BUS_ETH2		93
+#define CK_BUS_PCIE		94
+#define CK_BUS_DDRPHYC		95
+#define CK_BUS_SYSCPU1		96
+#define CK_BUS_ETHSW		97
+#define CK_BUS_HPDMA1		98
+#define CK_BUS_HPDMA2		99
+#define CK_BUS_HPDMA3		100
+#define CK_BUS_ADC12		101
+#define CK_BUS_ADC3		102
+#define CK_BUS_IPCC1		103
+#define CK_BUS_CCI		104
+#define CK_BUS_CRC		105
+#define CK_BUS_MDF1		106
+#define CK_BUS_OSPIIOM		107
+#define CK_BUS_BKPSRAM		108
+#define CK_BUS_HASH		109
+#define CK_BUS_RNG		110
+#define CK_BUS_CRYP1		111
+#define CK_BUS_CRYP2		112
+#define CK_BUS_SAES		113
+#define CK_BUS_PKA		114
+#define CK_BUS_GPIOA		115
+#define CK_BUS_GPIOB		116
+#define CK_BUS_GPIOC		117
+#define CK_BUS_GPIOD		118
+#define CK_BUS_GPIOE		119
+#define CK_BUS_GPIOF		120
+#define CK_BUS_GPIOG		121
+#define CK_BUS_GPIOH		122
+#define CK_BUS_GPIOI		123
+#define CK_BUS_GPIOJ		124
+#define CK_BUS_GPIOK		125
+#define CK_BUS_LPSRAM1		126
+#define CK_BUS_LPSRAM2		127
+#define CK_BUS_LPSRAM3		128
+#define CK_BUS_GPIOZ		129
+#define CK_BUS_LPDMA		130
+#define CK_BUS_HSEM		131
+#define CK_BUS_IPCC2		132
+#define CK_BUS_RTC		133
+#define CK_BUS_SPI8		134
+#define CK_BUS_LPUART1		135
+#define CK_BUS_I2C8		136
+#define CK_BUS_LPTIM3		137
+#define CK_BUS_LPTIM4		138
+#define CK_BUS_LPTIM5		139
+#define CK_BUS_IWDG5		140
+#define CK_BUS_WWDG2		141
+#define CK_BUS_I3C4		142
+#define CK_BUS_TIM2		143
+#define CK_BUS_TIM3		144
+#define CK_BUS_TIM4		145
+#define CK_BUS_TIM5		146
+#define CK_BUS_TIM6		147
+#define CK_BUS_TIM7		148
+#define CK_BUS_TIM10		149
+#define CK_BUS_TIM11		150
+#define CK_BUS_TIM12		151
+#define CK_BUS_TIM13		152
+#define CK_BUS_TIM14		153
+#define CK_BUS_LPTIM1		154
+#define CK_BUS_LPTIM2		155
+#define CK_BUS_SPI2		156
+#define CK_BUS_SPI3		157
+#define CK_BUS_SPDIFRX		158
+#define CK_BUS_USART2		159
+#define CK_BUS_USART3		160
+#define CK_BUS_UART4		161
+#define CK_BUS_UART5		162
+#define CK_BUS_I2C1		163
+#define CK_BUS_I2C2		164
+#define CK_BUS_I2C3		165
+#define CK_BUS_I2C4		166
+#define CK_BUS_I2C5		167
+#define CK_BUS_I2C6		168
+#define CK_BUS_I2C7		169
+#define CK_BUS_I3C1		170
+#define CK_BUS_I3C2		171
+#define CK_BUS_I3C3		172
+#define CK_BUS_TIM1		173
+#define CK_BUS_TIM8		174
+#define CK_BUS_TIM15		175
+#define CK_BUS_TIM16		176
+#define CK_BUS_TIM17		177
+#define CK_BUS_TIM20		178
+#define CK_BUS_SAI1		179
+#define CK_BUS_SAI2		180
+#define CK_BUS_SAI3		181
+#define CK_BUS_SAI4		182
+#define CK_BUS_USART1		183
+#define CK_BUS_USART6		184
+#define CK_BUS_UART7		185
+#define CK_BUS_UART8		186
+#define CK_BUS_UART9		187
+#define CK_BUS_FDCAN		188
+#define CK_BUS_SPI1		189
+#define CK_BUS_SPI4		190
+#define CK_BUS_SPI5		191
+#define CK_BUS_SPI6		192
+#define CK_BUS_SPI7		193
+#define CK_BUS_BSEC		194
+#define CK_BUS_IWDG1		195
+#define CK_BUS_IWDG2		196
+#define CK_BUS_IWDG3		197
+#define CK_BUS_IWDG4		198
+#define CK_BUS_WWDG1		199
+#define CK_BUS_VREF		200
+#define CK_BUS_DTS		201
+#define CK_BUS_SERC		202
+#define CK_BUS_HDP		203
+#define CK_BUS_IS2M		204
+#define CK_BUS_DSI		205
+#define CK_BUS_LTDC		206
+#define CK_BUS_CSI		207
+#define CK_BUS_DCMIPP		208
+#define CK_BUS_DDRC		209
+#define CK_BUS_DDRCFG		210
+#define CK_BUS_GICV2M		211
+#define CK_BUS_USBTC		212
+#define CK_BUS_USB3PCIEPHY	214
+#define CK_BUS_STGEN		215
+#define CK_BUS_VDEC		216
+#define CK_BUS_VENC		217
+#define CK_SYSDBG		218
+#define CK_KER_TIM2		219
+#define CK_KER_TIM3		220
+#define CK_KER_TIM4		221
+#define CK_KER_TIM5		222
+#define CK_KER_TIM6		223
+#define CK_KER_TIM7		224
+#define CK_KER_TIM10		225
+#define CK_KER_TIM11		226
+#define CK_KER_TIM12		227
+#define CK_KER_TIM13		228
+#define CK_KER_TIM14		229
+#define CK_KER_TIM1		230
+#define CK_KER_TIM8		231
+#define CK_KER_TIM15		232
+#define CK_KER_TIM16		233
+#define CK_KER_TIM17		234
+#define CK_KER_TIM20		235
+#define CK_BUS_SYSRAM		236
+#define CK_BUS_VDERAM		237
+#define CK_BUS_RETRAM		238
+#define CK_BUS_OSPI1		239
+#define CK_BUS_OSPI2		240
+#define CK_BUS_OTFD1		241
+#define CK_BUS_OTFD2		242
+#define CK_BUS_SRAM1		243
+#define CK_BUS_SRAM2		244
+#define CK_BUS_SDMMC1		245
+#define CK_BUS_SDMMC2		246
+#define CK_BUS_SDMMC3		247
+#define CK_BUS_DDR		248
+#define CK_BUS_RISAF4		249
+#define CK_BUS_USB2OHCI		250
+#define CK_BUS_USB2EHCI		251
+#define CK_BUS_USB3DR		252
+#define CK_KER_LPTIM1		253
+#define CK_KER_LPTIM2		254
+#define CK_KER_USART2		255
+#define CK_KER_UART4		256
+#define CK_KER_USART3		257
+#define CK_KER_UART5		258
+#define CK_KER_SPI2		259
+#define CK_KER_SPI3		260
+#define CK_KER_SPDIFRX		261
+#define CK_KER_I2C1		262
+#define CK_KER_I2C2		263
+#define CK_KER_I3C1		264
+#define CK_KER_I3C2		265
+#define CK_KER_I2C3		266
+#define CK_KER_I2C5		267
+#define CK_KER_I3C3		268
+#define CK_KER_I2C4		269
+#define CK_KER_I2C6		270
+#define CK_KER_I2C7		271
+#define CK_KER_SPI1		272
+#define CK_KER_SPI4		273
+#define CK_KER_SPI5		274
+#define CK_KER_SPI6		275
+#define CK_KER_SPI7		276
+#define CK_KER_USART1		277
+#define CK_KER_USART6		278
+#define CK_KER_UART7		279
+#define CK_KER_UART8		280
+#define CK_KER_UART9		281
+#define CK_KER_MDF1		282
+#define CK_KER_SAI1		283
+#define CK_KER_SAI2		284
+#define CK_KER_SAI3		285
+#define CK_KER_SAI4		286
+#define CK_KER_FDCAN		287
+#define CK_KER_DSIBLANE		288
+#define CK_KER_DSIPHY		289
+#define CK_KER_CSI		290
+#define CK_KER_CSITXESC		291
+#define CK_KER_CSIPHY		292
+#define CK_KER_LVDSPHY		293
+#define CK_KER_STGEN		294
+#define CK_KER_USB3PCIEPHY	295
+#define CK_KER_USB2PHY2EN	296
+#define CK_KER_I3C4		297
+#define CK_KER_SPI8		298
+#define CK_KER_I2C8		299
+#define CK_KER_LPUART1		300
+#define CK_KER_LPTIM3		301
+#define CK_KER_LPTIM4		302
+#define CK_KER_LPTIM5		303
+#define CK_KER_TSDBG		304
+#define CK_KER_TPIU		305
+#define CK_BUS_ETR		306
+#define CK_BUS_SYSATB		307
+#define CK_KER_ADC12		308
+#define CK_KER_ADC3		309
+#define CK_KER_OSPI1		310
+#define CK_KER_OSPI2		311
+#define CK_KER_FMC		312
+#define CK_KER_SDMMC1		313
+#define CK_KER_SDMMC2		314
+#define CK_KER_SDMMC3		315
+#define CK_KER_ETH1		316
+#define CK_KER_ETH2		317
+#define CK_KER_ETH1PTP		318
+#define CK_KER_ETH2PTP		319
+#define CK_KER_USB2PHY1		320
+#define CK_KER_USB2PHY2		321
+#define CK_KER_ETHSW		322
+#define CK_KER_ETHSWREF		323
+#define CK_MCO1			324
+#define CK_MCO2			325
+#define CK_KER_DTS		326
+#define CK_ETH1_RX		327
+#define CK_ETH1_TX		328
+#define CK_ETH1_MAC		329
+#define CK_ETH2_RX		330
+#define CK_ETH2_TX		331
+#define CK_ETH2_MAC		332
+#define CK_ETH1_STP		333
+#define CK_ETH2_STP		334
+#define CK_KER_USBTC		335
+#define CK_BUS_ADF1		336
+#define CK_KER_ADF1		337
+#define CK_BUS_LVDS		338
+#define CK_KER_LTDC		339
+#define CK_KER_GPU		340
+#define CK_BUS_ETHSWACMCFG	341
+#define CK_BUS_ETHSWACMMSG	342
+#define HSE_DIV2_CK		343
+
+#define STM32MP25_LAST_CLK	344
+
+#define CK_SCMI_ICN_HS_MCU	0
+#define CK_SCMI_ICN_SDMMC	1
+#define CK_SCMI_ICN_DDR		2
+#define CK_SCMI_ICN_DISPLAY	3
+#define CK_SCMI_ICN_HSL		4
+#define CK_SCMI_ICN_NIC		5
+#define CK_SCMI_ICN_VID		6
+#define CK_SCMI_FLEXGEN_07	7
+#define CK_SCMI_FLEXGEN_08	8
+#define CK_SCMI_FLEXGEN_09	9
+#define CK_SCMI_FLEXGEN_10	10
+#define CK_SCMI_FLEXGEN_11	11
+#define CK_SCMI_FLEXGEN_12	12
+#define CK_SCMI_FLEXGEN_13	13
+#define CK_SCMI_FLEXGEN_14	14
+#define CK_SCMI_FLEXGEN_15	15
+#define CK_SCMI_FLEXGEN_16	16
+#define CK_SCMI_FLEXGEN_17	17
+#define CK_SCMI_FLEXGEN_18	18
+#define CK_SCMI_FLEXGEN_19	19
+#define CK_SCMI_FLEXGEN_20	20
+#define CK_SCMI_FLEXGEN_21	21
+#define CK_SCMI_FLEXGEN_22	22
+#define CK_SCMI_FLEXGEN_23	23
+#define CK_SCMI_FLEXGEN_24	24
+#define CK_SCMI_FLEXGEN_25	25
+#define CK_SCMI_FLEXGEN_26	26
+#define CK_SCMI_FLEXGEN_27	27
+#define CK_SCMI_FLEXGEN_28	28
+#define CK_SCMI_FLEXGEN_29	29
+#define CK_SCMI_FLEXGEN_30	30
+#define CK_SCMI_FLEXGEN_31	31
+#define CK_SCMI_FLEXGEN_32	32
+#define CK_SCMI_FLEXGEN_33	33
+#define CK_SCMI_FLEXGEN_34	34
+#define CK_SCMI_FLEXGEN_35	35
+#define CK_SCMI_FLEXGEN_36	36
+#define CK_SCMI_FLEXGEN_37	37
+#define CK_SCMI_FLEXGEN_38	38
+#define CK_SCMI_FLEXGEN_39	39
+#define CK_SCMI_FLEXGEN_40	40
+#define CK_SCMI_FLEXGEN_41	41
+#define CK_SCMI_FLEXGEN_42	42
+#define CK_SCMI_FLEXGEN_43	43
+#define CK_SCMI_FLEXGEN_44	44
+#define CK_SCMI_FLEXGEN_45	45
+#define CK_SCMI_FLEXGEN_46	46
+#define CK_SCMI_FLEXGEN_47	47
+#define CK_SCMI_FLEXGEN_48	48
+#define CK_SCMI_FLEXGEN_49	49
+#define CK_SCMI_FLEXGEN_50	50
+#define CK_SCMI_FLEXGEN_51	51
+#define CK_SCMI_FLEXGEN_52	52
+#define CK_SCMI_FLEXGEN_53	53
+#define CK_SCMI_FLEXGEN_54	54
+#define CK_SCMI_FLEXGEN_55	55
+#define CK_SCMI_FLEXGEN_56	56
+#define CK_SCMI_FLEXGEN_57	57
+#define CK_SCMI_FLEXGEN_58	58
+#define CK_SCMI_FLEXGEN_59	59
+#define CK_SCMI_FLEXGEN_60	60
+#define CK_SCMI_FLEXGEN_61	61
+#define CK_SCMI_FLEXGEN_62	62
+#define CK_SCMI_FLEXGEN_63	63
+#define CK_SCMI_ICN_LS_MCU	64
+#define CK_SCMI_HSE		65
+#define CK_SCMI_LSE		66
+#define CK_SCMI_HSI		67
+#define CK_SCMI_LSI		68
+#define CK_SCMI_MSI		69
+#define CK_SCMI_HSE_DIV2	70
+#define CK_SCMI_CPU1		71
+#define CK_SCMI_SYSCPU1		72
+#define CK_SCMI_PLL2		73
+#define CK_SCMI_PLL3		74
+#define CK_SCMI_RTC		75
+#define CK_SCMI_RTCCK		76
+#define CK_SCMI_ICN_APB1	77
+#define CK_SCMI_ICN_APB2	78
+#define CK_SCMI_ICN_APB3	79
+#define CK_SCMI_ICN_APB4	80
+#define CK_SCMI_ICN_APBDBG	81
+#define CK_SCMI_TIMG1		82
+#define CK_SCMI_TIMG2		83
+#define CK_SCMI_BKPSRAM		84
+#define CK_SCMI_BSEC		85
+#define CK_SCMI_ETR		87
+#define CK_SCMI_FMC		88
+#define CK_SCMI_GPIOA		89
+#define CK_SCMI_GPIOB		90
+#define CK_SCMI_GPIOC		91
+#define CK_SCMI_GPIOD		92
+#define CK_SCMI_GPIOE		93
+#define CK_SCMI_GPIOF		94
+#define CK_SCMI_GPIOG		95
+#define CK_SCMI_GPIOH		96
+#define CK_SCMI_GPIOI		97
+#define CK_SCMI_GPIOJ		98
+#define CK_SCMI_GPIOK		99
+#define CK_SCMI_GPIOZ		100
+#define CK_SCMI_HPDMA1		101
+#define CK_SCMI_HPDMA2		102
+#define CK_SCMI_HPDMA3		103
+#define CK_SCMI_HSEM		104
+#define CK_SCMI_IPCC1		105
+#define CK_SCMI_IPCC2		106
+#define CK_SCMI_LPDMA		107
+#define CK_SCMI_RETRAM		108
+#define CK_SCMI_SRAM1		109
+#define CK_SCMI_SRAM2		110
+#define CK_SCMI_LPSRAM1		111
+#define CK_SCMI_LPSRAM2		112
+#define CK_SCMI_LPSRAM3		113
+#define CK_SCMI_VDERAM		114
+#define CK_SCMI_SYSRAM		115
+#define CK_SCMI_OSPI1		116
+#define CK_SCMI_OSPI2		117
+#define CK_SCMI_TPIU		118
+#define CK_SCMI_SYSDBG		119
+#define CK_SCMI_SYSATB		120
+#define CK_SCMI_TSDBG		121
+#define CK_SCMI_STM500		122
+
+#endif /* _DT_BINDINGS_STM32MP25_CLKS_H_ */
diff --git a/include/dt-bindings/reset/st,stm32mp25-rcc.h b/include/dt-bindings/reset/st,stm32mp25-rcc.h
new file mode 100644
index 000000000000..d5615930bcc8
--- /dev/null
+++ b/include/dt-bindings/reset/st,stm32mp25-rcc.h
@@ -0,0 +1,167 @@
+/* SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause */
+/*
+ * Copyright (C) STMicroelectronics 2023 - All Rights Reserved
+ * Author(s): Gabriel Fernandez <gabriel.fernandez@foss.st.com>
+ */
+
+#ifndef _DT_BINDINGS_STM32MP25_RESET_H_
+#define _DT_BINDINGS_STM32MP25_RESET_H_
+
+#define TIM1_R		0
+#define TIM2_R		1
+#define TIM3_R		2
+#define TIM4_R		3
+#define TIM5_R		4
+#define TIM6_R		5
+#define TIM7_R		6
+#define TIM8_R		7
+#define TIM10_R		8
+#define TIM11_R		9
+#define TIM12_R		10
+#define TIM13_R		11
+#define TIM14_R		12
+#define TIM15_R		13
+#define TIM16_R		14
+#define TIM17_R		15
+#define TIM20_R		16
+#define LPTIM1_R	17
+#define LPTIM2_R	18
+#define LPTIM3_R	19
+#define LPTIM4_R	20
+#define LPTIM5_R	21
+#define SPI1_R		22
+#define SPI2_R		23
+#define SPI3_R		24
+#define SPI4_R		25
+#define SPI5_R		26
+#define SPI6_R		27
+#define SPI7_R		28
+#define SPI8_R		29
+#define SPDIFRX_R	30
+#define USART1_R	31
+#define USART2_R	32
+#define USART3_R	33
+#define UART4_R		34
+#define UART5_R		35
+#define USART6_R	36
+#define UART7_R		37
+#define UART8_R		38
+#define UART9_R		39
+#define LPUART1_R	40
+#define IS2M_R		41
+#define I2C1_R		42
+#define I2C2_R		43
+#define I2C3_R		44
+#define I2C4_R		45
+#define I2C5_R		46
+#define I2C6_R		47
+#define I2C7_R		48
+#define I2C8_R		49
+#define SAI1_R		50
+#define SAI2_R		51
+#define SAI3_R		52
+#define SAI4_R		53
+#define MDF1_R		54
+#define MDF2_R		55
+#define FDCAN_R		56
+#define HDP_R		57
+#define ADC12_R		58
+#define ADC3_R		59
+#define ETH1_R		60
+#define ETH2_R		61
+#define USB2_R		62
+#define USB2PHY1_R	63
+#define USB2PHY2_R	64
+#define USB3DR_R	65
+#define USB3PCIEPHY_R	66
+#define USBTC_R		67
+#define ETHSW_R		68
+#define SDMMC1_R	69
+#define SDMMC1DLL_R	70
+#define SDMMC2_R	71
+#define SDMMC2DLL_R	72
+#define SDMMC3_R	73
+#define SDMMC3DLL_R	74
+#define GPU_R		75
+#define LTDC_R		76
+#define DSI_R		77
+#define LVDS_R		78
+#define CSI_R		79
+#define DCMIPP_R	80
+#define CCI_R		81
+#define VDEC_R		82
+#define VENC_R		83
+#define WWDG1_R		84
+#define WWDG2_R		85
+#define VREF_R		86
+#define DTS_R		87
+#define CRC_R		88
+#define SERC_R		89
+#define OSPIIOM_R	90
+#define I3C1_R		91
+#define I3C2_R		92
+#define I3C3_R		93
+#define I3C4_R		94
+#define IWDG2_KER_R	95
+#define IWDG4_KER_R	96
+#define RNG_R		97
+#define PKA_R		98
+#define SAES_R		99
+#define HASH_R		100
+#define CRYP1_R		101
+#define CRYP2_R		102
+#define PCIE_R		103
+#define OSPI1_R		104
+#define OSPI1DLL_R	105
+#define OSPI2_R		106
+#define OSPI2DLL_R	107
+#define FMC_R		108
+#define DBG_R		109
+#define GPIOA_R		110
+#define GPIOB_R		111
+#define GPIOC_R		112
+#define GPIOD_R		113
+#define GPIOE_R		114
+#define GPIOF_R		115
+#define GPIOG_R		116
+#define GPIOH_R		117
+#define GPIOI_R		118
+#define GPIOJ_R		119
+#define GPIOK_R		120
+#define GPIOZ_R		121
+#define HPDMA1_R	122
+#define HPDMA2_R	123
+#define HPDMA3_R	124
+#define LPDMA_R		125
+#define HSEM_R		126
+#define IPCC1_R		127
+#define IPCC2_R		128
+#define C2_HOLDBOOT_R	129
+#define C1_HOLDBOOT_R	130
+#define C1_R		131
+#define C1P1POR_R	132
+#define C1P1_R		133
+#define C2_R		134
+#define C3_R		135
+#define SYS_R		136
+#define VSW_R		137
+#define C1MS_R		138
+#define DDRCP_R		139
+#define DDRCAPB_R	140
+#define DDRPHYCAPB_R	141
+#define DDRCFG_R	142
+#define DDR_R		143
+
+#define STM32MP25_LAST_RESET	144
+
+#define RST_SCMI_C1_R		0
+#define RST_SCMI_C2_R		1
+#define RST_SCMI_C1_HOLDBOOT_R	2
+#define RST_SCMI_C2_HOLDBOOT_R	3
+#define RST_SCMI_FMC		4
+#define RST_SCMI_OSPI1		5
+#define RST_SCMI_OSPI1DLL	6
+#define RST_SCMI_OSPI2		7
+#define RST_SCMI_OSPI2DLL	8
+
+#endif /* _DT_BINDINGS_STM32MP25_RESET_H_ */
-- 
cgit v1.2.3


From 32da0f00ddcb101730cf242289b2b10ede0e1156 Mon Sep 17 00:00:00 2001
From: Jamal Hadi Salim <jhs@mojatatu.com>
Date: Fri, 15 Dec 2023 14:57:10 -0300
Subject: net: rtnl: introduce rcu_replace_pointer_rtnl

Introduce the rcu_replace_pointer_rtnl helper to lockdep check rtnl lock
rcu replacements, alongside the already existing helpers.

This is a quality of life helper so instead of using:
   rcu_replace_pointer(rp, p, lockdep_rtnl_is_held())
   .. or the open coded..
   rtnl_dereference() / rcu_assign_pointer()
   .. or the lazy check version ..
   rcu_replace_pointer(rp, p, 1)
Use:
   rcu_replace_pointer_rtnl(rp, p)

Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Victor Nogueira <victor@mojatatu.com>
Signed-off-by: Pedro Tammela <pctammela@mojatatu.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rtnetlink.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

(limited to 'include')

diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index 6a8543b34e2c..410529fca18b 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -79,6 +79,18 @@ static inline bool lockdep_rtnl_is_held(void)
 #define rtnl_dereference(p)					\
 	rcu_dereference_protected(p, lockdep_rtnl_is_held())
 
+/**
+ * rcu_replace_pointer_rtnl - replace an RCU pointer under rtnl_lock, returning
+ * its old value
+ * @rp: RCU pointer, whose value is returned
+ * @p: regular pointer
+ *
+ * Perform a replacement under rtnl_lock, where @rp is an RCU-annotated
+ * pointer. The old value of @rp is returned, and @rp is set to @p
+ */
+#define rcu_replace_pointer_rtnl(rp, p)			\
+	rcu_replace_pointer(rp, p, lockdep_rtnl_is_held())
+
 static inline struct netdev_queue *dev_ingress_queue(struct net_device *dev)
 {
 	return rtnl_dereference(dev->ingress_queue);
-- 
cgit v1.2.3


From b2adbc9cea752539f6421e9d4642408f666c1251 Mon Sep 17 00:00:00 2001
From: Alvin Šipraga <alsi@bang-olufsen.dk>
Date: Fri, 24 Nov 2023 14:17:44 +0100
Subject: clk: si5351: allow PLLs to be adjusted without reset
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Introduce a new PLL reset mode flag which controls whether or not to
reset a PLL after adjusting its rate. The mode can be configured through
platform data or device tree.

Since commit 6dc669a22c77 ("clk: si5351: Add PLL soft reset"), the
driver unconditionally resets a PLL whenever its rate is adjusted.
The rationale was that a PLL reset was required to get three outputs
working at the same time. Before this change, the driver never reset the
PLLs.

Commit b26ff127c52c ("clk: si5351: Apply PLL soft reset before enabling
the outputs") subsequently introduced an option to reset the PLL when
enabling a clock output that sourced it. Here, the rationale was that
this is required to get a deterministic phase relationship between
multiple output clocks.

This clearly shows that it is useful to reset the PLLs in applications
where multiple clock outputs are used. However, the Si5351 also allows
for glitch-free rate adjustment of its PLLs if one avoids resetting the
PLL. In our audio application where a single Si5351 clock output is used
to supply a runtime adjustable bit clock, this unconditional PLL reset
behaviour introduces unwanted glitches in the clock output.

It would appear that the problem being solved in the former commit
may be solved by using the optional device tree property introduced in
the latter commit, obviating the need for an unconditional PLL reset
after rate adjustment. But it's not OK to break the default behaviour of
the driver, and it cannot be assumed that all device trees are using the
property introduced in the latter commit. Hence, the new behaviour is
made opt-in.

Cc: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
Cc: Rabeeh Khoury <rabeeh@solid-run.com>
Cc: Jacob Siverskog <jacob@teenage.engineering>
Cc: Sergej Sawazki <sergej@taudac.com>
Signed-off-by: Alvin Šipraga <alsi@bang-olufsen.dk>
Acked-by: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
Link: https://lore.kernel.org/r/20231124-alvin-clk-si5351-no-pll-reset-v6-3-69b82311cb90@bang-olufsen.dk
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/clk-si5351.c             | 47 +++++++++++++++++++++++++++++++++---
 include/linux/platform_data/si5351.h |  2 ++
 2 files changed, 46 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/clk/clk-si5351.c b/drivers/clk/clk-si5351.c
index a9a0bc448a4b..4ce83c5265b8 100644
--- a/drivers/clk/clk-si5351.c
+++ b/drivers/clk/clk-si5351.c
@@ -506,6 +506,8 @@ static int si5351_pll_set_rate(struct clk_hw *hw, unsigned long rate,
 {
 	struct si5351_hw_data *hwdata =
 		container_of(hw, struct si5351_hw_data, hw);
+	struct si5351_platform_data *pdata =
+		hwdata->drvdata->client->dev.platform_data;
 	u8 reg = (hwdata->num == 0) ? SI5351_PLLA_PARAMETERS :
 		SI5351_PLLB_PARAMETERS;
 
@@ -518,9 +520,10 @@ static int si5351_pll_set_rate(struct clk_hw *hw, unsigned long rate,
 		(hwdata->params.p2 == 0) ? SI5351_CLK_INTEGER_MODE : 0);
 
 	/* Do a pll soft reset on the affected pll */
-	si5351_reg_write(hwdata->drvdata, SI5351_PLL_RESET,
-			 hwdata->num == 0 ? SI5351_PLL_RESET_A :
-					    SI5351_PLL_RESET_B);
+	if (pdata->pll_reset[hwdata->num])
+		si5351_reg_write(hwdata->drvdata, SI5351_PLL_RESET,
+				 hwdata->num == 0 ? SI5351_PLL_RESET_A :
+						    SI5351_PLL_RESET_B);
 
 	dev_dbg(&hwdata->drvdata->client->dev,
 		"%s - %s: p1 = %lu, p2 = %lu, p3 = %lu, parent_rate = %lu, rate = %lu\n",
@@ -1222,6 +1225,44 @@ static int si5351_dt_parse(struct i2c_client *client,
 		}
 	}
 
+	/*
+	 * Parse PLL reset mode. For compatibility with older device trees, the
+	 * default is to always reset a PLL after setting its rate.
+	 */
+	pdata->pll_reset[0] = true;
+	pdata->pll_reset[1] = true;
+
+	of_property_for_each_u32(np, "silabs,pll-reset-mode", prop, p, num) {
+		if (num >= 2) {
+			dev_err(&client->dev,
+				"invalid pll %d on pll-reset-mode prop\n", num);
+			return -EINVAL;
+		}
+
+		p = of_prop_next_u32(prop, p, &val);
+		if (!p) {
+			dev_err(&client->dev,
+				"missing pll-reset-mode for pll %d\n", num);
+			return -EINVAL;
+		}
+
+		switch (val) {
+		case 0:
+			/* Reset PLL whenever its rate is adjusted */
+			pdata->pll_reset[num] = true;
+			break;
+		case 1:
+			/* Don't reset PLL whenever its rate is adjusted */
+			pdata->pll_reset[num] = false;
+			break;
+		default:
+			dev_err(&client->dev,
+				"invalid pll-reset-mode %d for pll %d\n", val,
+				num);
+			return -EINVAL;
+		}
+	}
+
 	/* per clkout properties */
 	for_each_child_of_node(np, child) {
 		if (of_property_read_u32(child, "reg", &num)) {
diff --git a/include/linux/platform_data/si5351.h b/include/linux/platform_data/si5351.h
index c71a2dd66143..5f412a615532 100644
--- a/include/linux/platform_data/si5351.h
+++ b/include/linux/platform_data/si5351.h
@@ -105,10 +105,12 @@ struct si5351_clkout_config {
  * @clk_xtal: xtal input clock
  * @clk_clkin: clkin input clock
  * @pll_src: array of pll source clock setting
+ * @pll_reset: array indicating if plls should be reset after setting the rate
  * @clkout: array of clkout configuration
  */
 struct si5351_platform_data {
 	enum si5351_pll_src pll_src[2];
+	bool pll_reset[2];
 	struct si5351_clkout_config clkout[8];
 };
 
-- 
cgit v1.2.3


From 5a2a2cda916335fff4d804e58f36b2305926841e Mon Sep 17 00:00:00 2001
From: Wang Jinchao <wangjinchao@xfusion.com>
Date: Mon, 18 Dec 2023 15:16:16 +0800
Subject: gpiolib: remove duplicate inclusions

Remove second `#include <linux/err.h>`. Remove `#include <asm/errno.h>`
too as it's included by `err.h`.

Signed-off-by: Wang Jinchao <wangjinchao@xfusion.com>
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 include/linux/gpio/driver.h | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index bd9bea7cb270..e846bd4e7559 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -722,7 +722,6 @@ int gpiochip_irqchip_add_domain(struct gpio_chip *gc,
 #else
 
 #include <asm/bug.h>
-#include <asm/errno.h>
 
 static inline int gpiochip_irqchip_add_domain(struct gpio_chip *gc,
 					      struct irq_domain *domain)
@@ -811,8 +810,6 @@ const char *gpio_device_get_label(struct gpio_device *gdev);
 
 #else /* CONFIG_GPIOLIB */
 
-#include <linux/err.h>
-
 #include <asm/bug.h>
 
 static inline struct gpio_chip *gpiod_to_chip(const struct gpio_desc *desc)
-- 
cgit v1.2.3


From 35f32e39b4d9b436354c2a37623c393a2ac7cf87 Mon Sep 17 00:00:00 2001
From: Tudor Ambarus <tudor.ambarus@linaro.org>
Date: Mon, 18 Dec 2023 06:43:33 +0000
Subject: dt-bindings: clock: google,gs101: rename CMU_TOP gate defines

The gs101 clock defines from the bindings header are derived from the
clock register names found in the datasheet under some certain rules.

The CMU TOP gate clock defines missed to include the required "CMU"
differentiator which will cause collisions with the gate clock defines
of other clock units. Rename the TOP gate clock defines to include "CMU".

Update the clock driver to use the new defines in order to not break
compilation and bisect-ability. There are no device trees that use the
previous defines.

Fixes: 0a910f160638 ("dt-bindings: clock: Add Google gs101 clock management unit bindings")
Signed-off-by: Tudor Ambarus <tudor.ambarus@linaro.org>
Reviewed-by: Sam Protsenko <semen.protsenko@linaro.org>
Reviewed-by: Peter Griffin <peter.griffin@linaro.org>
Link: https://lore.kernel.org/r/20231218064333.479885-1-tudor.ambarus@linaro.org
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 drivers/clk/samsung/clk-gs101.c          | 167 ++++++++++++++++---------------
 include/dt-bindings/clock/google,gs101.h | 144 +++++++++++++-------------
 2 files changed, 159 insertions(+), 152 deletions(-)

(limited to 'include')

diff --git a/drivers/clk/samsung/clk-gs101.c b/drivers/clk/samsung/clk-gs101.c
index a3dda97f5eb9..0964bb11657f 100644
--- a/drivers/clk/samsung/clk-gs101.c
+++ b/drivers/clk/samsung/clk-gs101.c
@@ -17,7 +17,7 @@
 #include "clk-exynos-arm64.h"
 
 /* NOTE: Must be equal to the last clock ID increased by one */
-#define CLKS_NR_TOP	(CLK_GOUT_TPU_UART + 1)
+#define CLKS_NR_TOP	(CLK_GOUT_CMU_TPU_UART + 1)
 #define CLKS_NR_APM	(CLK_APM_PLL_DIV16_APM + 1)
 #define CLKS_NR_MISC	(CLK_GOUT_MISC_XIU_D_MISC_ACLK + 1)
 
@@ -1259,160 +1259,167 @@ static const struct samsung_fixed_factor_clock cmu_top_ffactor[] __initconst = {
 };
 
 static const struct samsung_gate_clock cmu_top_gate_clks[] __initconst = {
-	GATE(CLK_GOUT_BUS0_BOOST, "gout_cmu_bus0_boost",
+	GATE(CLK_GOUT_CMU_BUS0_BOOST, "gout_cmu_bus0_boost",
 	     "mout_cmu_boost_option1", CLK_CON_GAT_CLKCMU_BUS0_BOOST, 21, 0, 0),
-	GATE(CLK_GOUT_BUS1_BOOST, "gout_cmu_bus1_boost",
+	GATE(CLK_GOUT_CMU_BUS1_BOOST, "gout_cmu_bus1_boost",
 	     "mout_cmu_boost_option1", CLK_CON_GAT_CLKCMU_BUS1_BOOST, 21, 0, 0),
-	GATE(CLK_GOUT_BUS2_BOOST, "gout_cmu_bus2_boost",
+	GATE(CLK_GOUT_CMU_BUS2_BOOST, "gout_cmu_bus2_boost",
 	     "mout_cmu_boost_option1", CLK_CON_GAT_CLKCMU_BUS2_BOOST, 21, 0, 0),
-	GATE(CLK_GOUT_CORE_BOOST, "gout_cmu_core_boost",
+	GATE(CLK_GOUT_CMU_CORE_BOOST, "gout_cmu_core_boost",
 	     "mout_cmu_boost_option1", CLK_CON_GAT_CLKCMU_CORE_BOOST, 21, 0, 0),
-	GATE(CLK_GOUT_CPUCL0_BOOST, "gout_cmu_cpucl0_boost",
+	GATE(CLK_GOUT_CMU_CPUCL0_BOOST, "gout_cmu_cpucl0_boost",
 	     "mout_cmu_boost_option1", CLK_CON_GAT_CLKCMU_CPUCL0_BOOST,
 	     21, 0, 0),
-	GATE(CLK_GOUT_CPUCL1_BOOST, "gout_cmu_cpucl1_boost",
+	GATE(CLK_GOUT_CMU_CPUCL1_BOOST, "gout_cmu_cpucl1_boost",
 	     "mout_cmu_boost_option1", CLK_CON_GAT_CLKCMU_CPUCL1_BOOST,
 	     21, 0, 0),
-	GATE(CLK_GOUT_CPUCL2_BOOST, "gout_cmu_cpucl2_boost",
+	GATE(CLK_GOUT_CMU_CPUCL2_BOOST, "gout_cmu_cpucl2_boost",
 	     "mout_cmu_boost_option1", CLK_CON_GAT_CLKCMU_CPUCL2_BOOST,
 	     21, 0, 0),
-	GATE(CLK_GOUT_MIF_BOOST, "gout_cmu_mif_boost",
+	GATE(CLK_GOUT_CMU_MIF_BOOST, "gout_cmu_mif_boost",
 	     "mout_cmu_boost_option1", CLK_CON_GAT_CLKCMU_MIF_BOOST,
 	     21, 0, 0),
-	GATE(CLK_GOUT_MIF_SWITCH, "gout_cmu_mif_switch", "mout_cmu_mif_switch",
-	     CLK_CON_GAT_CLKCMU_MIF_SWITCH, 21, 0, 0),
-	GATE(CLK_GOUT_BO_BUS, "gout_cmu_bo_bus", "mout_cmu_bo_bus",
+	GATE(CLK_GOUT_CMU_MIF_SWITCH, "gout_cmu_mif_switch",
+	     "mout_cmu_mif_switch", CLK_CON_GAT_CLKCMU_MIF_SWITCH, 21, 0, 0),
+	GATE(CLK_GOUT_CMU_BO_BUS, "gout_cmu_bo_bus", "mout_cmu_bo_bus",
 	     CLK_CON_GAT_GATE_CLKCMU_BO_BUS, 21, 0, 0),
-	GATE(CLK_GOUT_BUS0_BUS, "gout_cmu_bus0_bus", "mout_cmu_bus0_bus",
+	GATE(CLK_GOUT_CMU_BUS0_BUS, "gout_cmu_bus0_bus", "mout_cmu_bus0_bus",
 	     CLK_CON_GAT_GATE_CLKCMU_BUS0_BUS, 21, 0, 0),
-	GATE(CLK_GOUT_BUS1_BUS, "gout_cmu_bus1_bus", "mout_cmu_bus1_bus",
+	GATE(CLK_GOUT_CMU_BUS1_BUS, "gout_cmu_bus1_bus", "mout_cmu_bus1_bus",
 	     CLK_CON_GAT_GATE_CLKCMU_BUS1_BUS, 21, 0, 0),
-	GATE(CLK_GOUT_BUS2_BUS, "gout_cmu_bus2_bus", "mout_cmu_bus2_bus",
+	GATE(CLK_GOUT_CMU_BUS2_BUS, "gout_cmu_bus2_bus", "mout_cmu_bus2_bus",
 	     CLK_CON_GAT_GATE_CLKCMU_BUS2_BUS, 21, 0, 0),
-	GATE(CLK_GOUT_CIS_CLK0, "gout_cmu_cis_clk0", "mout_cmu_cis_clk0",
+	GATE(CLK_GOUT_CMU_CIS_CLK0, "gout_cmu_cis_clk0", "mout_cmu_cis_clk0",
 	     CLK_CON_GAT_GATE_CLKCMU_CIS_CLK0, 21, 0, 0),
-	GATE(CLK_GOUT_CIS_CLK1, "gout_cmu_cis_clk1", "mout_cmu_cis_clk1",
+	GATE(CLK_GOUT_CMU_CIS_CLK1, "gout_cmu_cis_clk1", "mout_cmu_cis_clk1",
 	     CLK_CON_GAT_GATE_CLKCMU_CIS_CLK1, 21, 0, 0),
-	GATE(CLK_GOUT_CIS_CLK2, "gout_cmu_cis_clk2", "mout_cmu_cis_clk2",
+	GATE(CLK_GOUT_CMU_CIS_CLK2, "gout_cmu_cis_clk2", "mout_cmu_cis_clk2",
 	     CLK_CON_GAT_GATE_CLKCMU_CIS_CLK2, 21, 0, 0),
-	GATE(CLK_GOUT_CIS_CLK3, "gout_cmu_cis_clk3", "mout_cmu_cis_clk3",
+	GATE(CLK_GOUT_CMU_CIS_CLK3, "gout_cmu_cis_clk3", "mout_cmu_cis_clk3",
 	     CLK_CON_GAT_GATE_CLKCMU_CIS_CLK3, 21, 0, 0),
-	GATE(CLK_GOUT_CIS_CLK4, "gout_cmu_cis_clk4", "mout_cmu_cis_clk4",
+	GATE(CLK_GOUT_CMU_CIS_CLK4, "gout_cmu_cis_clk4", "mout_cmu_cis_clk4",
 	     CLK_CON_GAT_GATE_CLKCMU_CIS_CLK4, 21, 0, 0),
-	GATE(CLK_GOUT_CIS_CLK5, "gout_cmu_cis_clk5", "mout_cmu_cis_clk5",
+	GATE(CLK_GOUT_CMU_CIS_CLK5, "gout_cmu_cis_clk5", "mout_cmu_cis_clk5",
 	     CLK_CON_GAT_GATE_CLKCMU_CIS_CLK5, 21, 0, 0),
-	GATE(CLK_GOUT_CIS_CLK6, "gout_cmu_cis_clk6", "mout_cmu_cis_clk6",
+	GATE(CLK_GOUT_CMU_CIS_CLK6, "gout_cmu_cis_clk6", "mout_cmu_cis_clk6",
 	     CLK_CON_GAT_GATE_CLKCMU_CIS_CLK6, 21, 0, 0),
-	GATE(CLK_GOUT_CIS_CLK7, "gout_cmu_cis_clk7", "mout_cmu_cis_clk7",
+	GATE(CLK_GOUT_CMU_CIS_CLK7, "gout_cmu_cis_clk7", "mout_cmu_cis_clk7",
 	     CLK_CON_GAT_GATE_CLKCMU_CIS_CLK7, 21, 0, 0),
-	GATE(CLK_GOUT_CMU_BOOST, "gout_cmu_cmu_boost", "mout_cmu_cmu_boost",
+	GATE(CLK_GOUT_CMU_CMU_BOOST, "gout_cmu_cmu_boost", "mout_cmu_cmu_boost",
 	     CLK_CON_GAT_GATE_CLKCMU_CMU_BOOST, 21, 0, 0),
-	GATE(CLK_GOUT_CORE_BUS, "gout_cmu_core_bus", "mout_cmu_core_bus",
+	GATE(CLK_GOUT_CMU_CORE_BUS, "gout_cmu_core_bus", "mout_cmu_core_bus",
 	     CLK_CON_GAT_GATE_CLKCMU_CORE_BUS, 21, 0, 0),
-	GATE(CLK_GOUT_CPUCL0_DBG, "gout_cmu_cpucl0_dbg", "mout_cmu_cpucl0_dbg",
-	     CLK_CON_GAT_GATE_CLKCMU_CPUCL0_DBG_BUS, 21, 0, 0),
-	GATE(CLK_GOUT_CPUCL0_SWITCH, "gout_cmu_cpucl0_switch",
+	GATE(CLK_GOUT_CMU_CPUCL0_DBG, "gout_cmu_cpucl0_dbg",
+	     "mout_cmu_cpucl0_dbg", CLK_CON_GAT_GATE_CLKCMU_CPUCL0_DBG_BUS,
+	     21, 0, 0),
+	GATE(CLK_GOUT_CMU_CPUCL0_SWITCH, "gout_cmu_cpucl0_switch",
 	     "mout_cmu_cpucl0_switch", CLK_CON_GAT_GATE_CLKCMU_CPUCL0_SWITCH,
 	     21, 0, 0),
-	GATE(CLK_GOUT_CPUCL1_SWITCH, "gout_cmu_cpucl1_switch",
+	GATE(CLK_GOUT_CMU_CPUCL1_SWITCH, "gout_cmu_cpucl1_switch",
 	     "mout_cmu_cpucl1_switch", CLK_CON_GAT_GATE_CLKCMU_CPUCL1_SWITCH,
 	     21, 0, 0),
-	GATE(CLK_GOUT_CPUCL2_SWITCH, "gout_cmu_cpucl2_switch",
+	GATE(CLK_GOUT_CMU_CPUCL2_SWITCH, "gout_cmu_cpucl2_switch",
 	     "mout_cmu_cpucl2_switch", CLK_CON_GAT_GATE_CLKCMU_CPUCL2_SWITCH,
 	     21, 0, 0),
-	GATE(CLK_GOUT_CSIS_BUS, "gout_cmu_csis_bus", "mout_cmu_csis_bus",
+	GATE(CLK_GOUT_CMU_CSIS_BUS, "gout_cmu_csis_bus", "mout_cmu_csis_bus",
 	     CLK_CON_GAT_GATE_CLKCMU_CSIS_BUS, 21, 0, 0),
-	GATE(CLK_GOUT_DISP_BUS, "gout_cmu_disp_bus", "mout_cmu_disp_bus",
+	GATE(CLK_GOUT_CMU_DISP_BUS, "gout_cmu_disp_bus", "mout_cmu_disp_bus",
 	     CLK_CON_GAT_GATE_CLKCMU_DISP_BUS, 21, 0, 0),
-	GATE(CLK_GOUT_DNS_BUS, "gout_cmu_dns_bus", "mout_cmu_dns_bus",
+	GATE(CLK_GOUT_CMU_DNS_BUS, "gout_cmu_dns_bus", "mout_cmu_dns_bus",
 	     CLK_CON_GAT_GATE_CLKCMU_DNS_BUS, 21, 0, 0),
-	GATE(CLK_GOUT_DPU_BUS, "gout_cmu_dpu_bus", "mout_cmu_dpu_bus",
+	GATE(CLK_GOUT_CMU_DPU_BUS, "gout_cmu_dpu_bus", "mout_cmu_dpu_bus",
 	     CLK_CON_GAT_GATE_CLKCMU_DPU_BUS, 21, 0, 0),
-	GATE(CLK_GOUT_EH_BUS, "gout_cmu_eh_bus", "mout_cmu_eh_bus",
+	GATE(CLK_GOUT_CMU_EH_BUS, "gout_cmu_eh_bus", "mout_cmu_eh_bus",
 	     CLK_CON_GAT_GATE_CLKCMU_EH_BUS, 21, 0, 0),
-	GATE(CLK_GOUT_G2D_G2D, "gout_cmu_g2d_g2d", "mout_cmu_g2d_g2d",
+	GATE(CLK_GOUT_CMU_G2D_G2D, "gout_cmu_g2d_g2d", "mout_cmu_g2d_g2d",
 	     CLK_CON_GAT_GATE_CLKCMU_G2D_G2D, 21, 0, 0),
-	GATE(CLK_GOUT_G2D_MSCL, "gout_cmu_g2d_mscl", "mout_cmu_g2d_mscl",
+	GATE(CLK_GOUT_CMU_G2D_MSCL, "gout_cmu_g2d_mscl", "mout_cmu_g2d_mscl",
 	     CLK_CON_GAT_GATE_CLKCMU_G2D_MSCL, 21, 0, 0),
-	GATE(CLK_GOUT_G3AA_G3AA, "gout_cmu_g3aa_g3aa", "mout_cmu_g3aa_g3aa",
+	GATE(CLK_GOUT_CMU_G3AA_G3AA, "gout_cmu_g3aa_g3aa", "mout_cmu_g3aa_g3aa",
 	     CLK_CON_MUX_MUX_CLKCMU_G3AA_G3AA, 21, 0, 0),
-	GATE(CLK_GOUT_G3D_BUSD, "gout_cmu_g3d_busd", "mout_cmu_g3d_busd",
+	GATE(CLK_GOUT_CMU_G3D_BUSD, "gout_cmu_g3d_busd", "mout_cmu_g3d_busd",
 	     CLK_CON_GAT_GATE_CLKCMU_G3D_BUSD, 21, 0, 0),
-	GATE(CLK_GOUT_G3D_GLB, "gout_cmu_g3d_glb", "mout_cmu_g3d_glb",
+	GATE(CLK_GOUT_CMU_G3D_GLB, "gout_cmu_g3d_glb", "mout_cmu_g3d_glb",
 	     CLK_CON_GAT_GATE_CLKCMU_G3D_GLB, 21, 0, 0),
-	GATE(CLK_GOUT_G3D_SWITCH, "gout_cmu_g3d_switch", "mout_cmu_g3d_switch",
-	     CLK_CON_GAT_GATE_CLKCMU_G3D_SWITCH, 21, 0, 0),
-	GATE(CLK_GOUT_GDC_GDC0, "gout_cmu_gdc_gdc0", "mout_cmu_gdc_gdc0",
+	GATE(CLK_GOUT_CMU_G3D_SWITCH, "gout_cmu_g3d_switch",
+	     "mout_cmu_g3d_switch", CLK_CON_GAT_GATE_CLKCMU_G3D_SWITCH,
+	     21, 0, 0),
+	GATE(CLK_GOUT_CMU_GDC_GDC0, "gout_cmu_gdc_gdc0", "mout_cmu_gdc_gdc0",
 	     CLK_CON_GAT_GATE_CLKCMU_GDC_GDC0, 21, 0, 0),
-	GATE(CLK_GOUT_GDC_GDC1, "gout_cmu_gdc_gdc1", "mout_cmu_gdc_gdc1",
+	GATE(CLK_GOUT_CMU_GDC_GDC1, "gout_cmu_gdc_gdc1", "mout_cmu_gdc_gdc1",
 	     CLK_CON_GAT_GATE_CLKCMU_GDC_GDC1, 21, 0, 0),
-	GATE(CLK_GOUT_GDC_SCSC, "gout_cmu_gdc_scsc", "mout_cmu_gdc_scsc",
+	GATE(CLK_GOUT_CMU_GDC_SCSC, "gout_cmu_gdc_scsc", "mout_cmu_gdc_scsc",
 	     CLK_CON_GAT_GATE_CLKCMU_GDC_SCSC, 21, 0, 0),
 	GATE(CLK_GOUT_CMU_HPM, "gout_cmu_hpm", "mout_cmu_hpm",
 	     CLK_CON_GAT_GATE_CLKCMU_HPM, 21, 0, 0),
-	GATE(CLK_GOUT_HSI0_BUS, "gout_cmu_hsi0_bus", "mout_cmu_hsi0_bus",
+	GATE(CLK_GOUT_CMU_HSI0_BUS, "gout_cmu_hsi0_bus", "mout_cmu_hsi0_bus",
 	     CLK_CON_GAT_GATE_CLKCMU_HSI0_BUS, 21, 0, 0),
-	GATE(CLK_GOUT_HSI0_DPGTC, "gout_cmu_hsi0_dpgtc", "mout_cmu_hsi0_dpgtc",
-	     CLK_CON_GAT_GATE_CLKCMU_HSI0_DPGTC, 21, 0, 0),
-	GATE(CLK_GOUT_HSI0_USB31DRD, "gout_cmu_hsi0_usb31drd",
+	GATE(CLK_GOUT_CMU_HSI0_DPGTC, "gout_cmu_hsi0_dpgtc",
+	     "mout_cmu_hsi0_dpgtc", CLK_CON_GAT_GATE_CLKCMU_HSI0_DPGTC,
+	     21, 0, 0),
+	GATE(CLK_GOUT_CMU_HSI0_USB31DRD, "gout_cmu_hsi0_usb31drd",
 	     "mout_cmu_hsi0_usb31drd", CLK_CON_GAT_GATE_CLKCMU_HSI0_USB31DRD,
 	     21, 0, 0),
-	GATE(CLK_GOUT_HSI0_USBDPDBG, "gout_cmu_hsi0_usbdpdbg",
+	GATE(CLK_GOUT_CMU_HSI0_USBDPDBG, "gout_cmu_hsi0_usbdpdbg",
 	     "mout_cmu_hsi0_usbdpdbg", CLK_CON_GAT_GATE_CLKCMU_HSI0_USBDPDBG,
 	     21, 0, 0),
-	GATE(CLK_GOUT_HSI1_BUS, "gout_cmu_hsi1_bus", "mout_cmu_hsi1_bus",
+	GATE(CLK_GOUT_CMU_HSI1_BUS, "gout_cmu_hsi1_bus", "mout_cmu_hsi1_bus",
 	     CLK_CON_GAT_GATE_CLKCMU_HSI1_BUS, 21, 0, 0),
-	GATE(CLK_GOUT_HSI1_PCIE, "gout_cmu_hsi1_pcie", "mout_cmu_hsi1_pcie",
+	GATE(CLK_GOUT_CMU_HSI1_PCIE, "gout_cmu_hsi1_pcie", "mout_cmu_hsi1_pcie",
 	     CLK_CON_GAT_GATE_CLKCMU_HSI1_PCIE, 21, 0, 0),
-	GATE(CLK_GOUT_HSI2_BUS, "gout_cmu_hsi2_bus", "mout_cmu_hsi2_bus",
+	GATE(CLK_GOUT_CMU_HSI2_BUS, "gout_cmu_hsi2_bus", "mout_cmu_hsi2_bus",
 	     CLK_CON_GAT_GATE_CLKCMU_HSI2_BUS, 21, 0, 0),
-	GATE(CLK_GOUT_HSI2_MMC_CARD, "gout_cmu_hsi2_mmc_card",
+	GATE(CLK_GOUT_CMU_HSI2_MMC_CARD, "gout_cmu_hsi2_mmc_card",
 	     "mout_cmu_hsi2_mmc_card", CLK_CON_GAT_GATE_CLKCMU_HSI2_MMCCARD,
 	     21, 0, 0),
-	GATE(CLK_GOUT_HSI2_PCIE, "gout_cmu_hsi2_pcie", "mout_cmu_hsi2_pcie",
+	GATE(CLK_GOUT_CMU_HSI2_PCIE, "gout_cmu_hsi2_pcie", "mout_cmu_hsi2_pcie",
 	     CLK_CON_GAT_GATE_CLKCMU_HSI2_PCIE, 21, 0, 0),
-	GATE(CLK_GOUT_HSI2_UFS_EMBD, "gout_cmu_hsi2_ufs_embd",
+	GATE(CLK_GOUT_CMU_HSI2_UFS_EMBD, "gout_cmu_hsi2_ufs_embd",
 	     "mout_cmu_hsi2_ufs_embd", CLK_CON_GAT_GATE_CLKCMU_HSI2_UFS_EMBD,
 	     21, 0, 0),
-	GATE(CLK_GOUT_IPP_BUS, "gout_cmu_ipp_bus", "mout_cmu_ipp_bus",
+	GATE(CLK_GOUT_CMU_IPP_BUS, "gout_cmu_ipp_bus", "mout_cmu_ipp_bus",
 	     CLK_CON_GAT_GATE_CLKCMU_IPP_BUS, 21, 0, 0),
-	GATE(CLK_GOUT_ITP_BUS, "gout_cmu_itp_bus", "mout_cmu_itp_bus",
+	GATE(CLK_GOUT_CMU_ITP_BUS, "gout_cmu_itp_bus", "mout_cmu_itp_bus",
 	     CLK_CON_GAT_GATE_CLKCMU_ITP_BUS, 21, 0, 0),
-	GATE(CLK_GOUT_MCSC_ITSC, "gout_cmu_mcsc_itsc", "mout_cmu_mcsc_itsc",
+	GATE(CLK_GOUT_CMU_MCSC_ITSC, "gout_cmu_mcsc_itsc", "mout_cmu_mcsc_itsc",
 	     CLK_CON_GAT_GATE_CLKCMU_MCSC_ITSC, 21, 0, 0),
-	GATE(CLK_GOUT_MCSC_MCSC, "gout_cmu_mcsc_mcsc", "mout_cmu_mcsc_mcsc",
+	GATE(CLK_GOUT_CMU_MCSC_MCSC, "gout_cmu_mcsc_mcsc", "mout_cmu_mcsc_mcsc",
 	     CLK_CON_GAT_GATE_CLKCMU_MCSC_MCSC, 21, 0, 0),
-	GATE(CLK_GOUT_MFC_MFC, "gout_cmu_mfc_mfc", "mout_cmu_mfc_mfc",
+	GATE(CLK_GOUT_CMU_MFC_MFC, "gout_cmu_mfc_mfc", "mout_cmu_mfc_mfc",
 	     CLK_CON_GAT_GATE_CLKCMU_MFC_MFC, 21, 0, 0),
-	GATE(CLK_GOUT_MIF_BUSP, "gout_cmu_mif_busp", "mout_cmu_mif_busp",
+	GATE(CLK_GOUT_CMU_MIF_BUSP, "gout_cmu_mif_busp", "mout_cmu_mif_busp",
 	     CLK_CON_GAT_GATE_CLKCMU_MIF_BUSP, 21, 0, 0),
-	GATE(CLK_GOUT_MISC_BUS, "gout_cmu_misc_bus", "mout_cmu_misc_bus",
+	GATE(CLK_GOUT_CMU_MISC_BUS, "gout_cmu_misc_bus", "mout_cmu_misc_bus",
 	     CLK_CON_GAT_GATE_CLKCMU_MISC_BUS, 21, 0, 0),
-	GATE(CLK_GOUT_MISC_SSS, "gout_cmu_misc_sss", "mout_cmu_misc_sss",
+	GATE(CLK_GOUT_CMU_MISC_SSS, "gout_cmu_misc_sss", "mout_cmu_misc_sss",
 	     CLK_CON_GAT_GATE_CLKCMU_MISC_SSS, 21, 0, 0),
-	GATE(CLK_GOUT_PDP_BUS, "gout_cmu_pdp_bus", "mout_cmu_pdp_bus",
+	GATE(CLK_GOUT_CMU_PDP_BUS, "gout_cmu_pdp_bus", "mout_cmu_pdp_bus",
 	     CLK_CON_GAT_GATE_CLKCMU_PDP_BUS, 21, 0, 0),
-	GATE(CLK_GOUT_PDP_VRA, "gout_cmu_pdp_vra", "mout_cmu_pdp_vra",
+	GATE(CLK_GOUT_CMU_PDP_VRA, "gout_cmu_pdp_vra", "mout_cmu_pdp_vra",
 	     CLK_CON_GAT_GATE_CLKCMU_PDP_BUS, 21, 0, 0),
-	GATE(CLK_GOUT_PERIC0_BUS, "gout_cmu_peric0_bus", "mout_cmu_peric0_bus",
-	     CLK_CON_GAT_GATE_CLKCMU_PERIC0_BUS, 21, 0, 0),
-	GATE(CLK_GOUT_PERIC0_IP, "gout_cmu_peric0_ip", "mout_cmu_peric0_ip",
+	GATE(CLK_GOUT_CMU_PERIC0_BUS, "gout_cmu_peric0_bus",
+	     "mout_cmu_peric0_bus", CLK_CON_GAT_GATE_CLKCMU_PERIC0_BUS,
+	     21, 0, 0),
+	GATE(CLK_GOUT_CMU_PERIC0_IP, "gout_cmu_peric0_ip", "mout_cmu_peric0_ip",
 	     CLK_CON_GAT_GATE_CLKCMU_PERIC0_IP, 21, 0, 0),
-	GATE(CLK_GOUT_PERIC1_BUS, "gout_cmu_peric1_bus", "mout_cmu_peric1_bus",
-	     CLK_CON_GAT_GATE_CLKCMU_PERIC1_BUS, 21, 0, 0),
-	GATE(CLK_GOUT_PERIC1_IP, "gout_cmu_peric1_ip", "mout_cmu_peric1_ip",
+	GATE(CLK_GOUT_CMU_PERIC1_BUS, "gout_cmu_peric1_bus",
+	     "mout_cmu_peric1_bus", CLK_CON_GAT_GATE_CLKCMU_PERIC1_BUS,
+	     21, 0, 0),
+	GATE(CLK_GOUT_CMU_PERIC1_IP, "gout_cmu_peric1_ip", "mout_cmu_peric1_ip",
 	     CLK_CON_GAT_GATE_CLKCMU_PERIC1_IP, 21, 0, 0),
-	GATE(CLK_GOUT_TNR_BUS, "gout_cmu_tnr_bus", "mout_cmu_tnr_bus",
+	GATE(CLK_GOUT_CMU_TNR_BUS, "gout_cmu_tnr_bus", "mout_cmu_tnr_bus",
 	     CLK_CON_GAT_GATE_CLKCMU_TNR_BUS, 21, 0, 0),
-	GATE(CLK_GOUT_TOP_CMUREF, "gout_cmu_top_cmuref", "mout_cmu_top_cmuref",
-	     CLK_CON_GAT_GATE_CLKCMU_TOP_CMUREF, 21, 0, 0),
-	GATE(CLK_GOUT_TPU_BUS, "gout_cmu_tpu_bus", "mout_cmu_tpu_bus",
+	GATE(CLK_GOUT_CMU_TOP_CMUREF, "gout_cmu_top_cmuref",
+	     "mout_cmu_top_cmuref", CLK_CON_GAT_GATE_CLKCMU_TOP_CMUREF,
+	     21, 0, 0),
+	GATE(CLK_GOUT_CMU_TPU_BUS, "gout_cmu_tpu_bus", "mout_cmu_tpu_bus",
 	     CLK_CON_GAT_GATE_CLKCMU_TPU_BUS, 21, 0, 0),
-	GATE(CLK_GOUT_TPU_TPU, "gout_cmu_tpu_tpu", "mout_cmu_tpu_tpu",
+	GATE(CLK_GOUT_CMU_TPU_TPU, "gout_cmu_tpu_tpu", "mout_cmu_tpu_tpu",
 	     CLK_CON_GAT_GATE_CLKCMU_TPU_TPU, 21, 0, 0),
-	GATE(CLK_GOUT_TPU_TPUCTL, "gout_cmu_tpu_tpuctl", "mout_cmu_tpu_tpuctl",
-	     CLK_CON_GAT_GATE_CLKCMU_TPU_TPUCTL, 21, 0, 0),
-	GATE(CLK_GOUT_TPU_UART, "gout_cmu_tpu_uart", "mout_cmu_tpu_uart",
+	GATE(CLK_GOUT_CMU_TPU_TPUCTL, "gout_cmu_tpu_tpuctl",
+	     "mout_cmu_tpu_tpuctl", CLK_CON_GAT_GATE_CLKCMU_TPU_TPUCTL,
+	     21, 0, 0),
+	GATE(CLK_GOUT_CMU_TPU_UART, "gout_cmu_tpu_uart", "mout_cmu_tpu_uart",
 	     CLK_CON_GAT_GATE_CLKCMU_TPU_UART, 21, 0, 0),
 };
 
diff --git a/include/dt-bindings/clock/google,gs101.h b/include/dt-bindings/clock/google,gs101.h
index 9761c0b24e66..21adec22387c 100644
--- a/include/dt-bindings/clock/google,gs101.h
+++ b/include/dt-bindings/clock/google,gs101.h
@@ -166,79 +166,79 @@
 #define CLK_DOUT_CMU_SHARED3_DIV2	150
 
 /* CMU_TOP Gates */
-#define CLK_GOUT_BUS0_BOOST		151
-#define CLK_GOUT_BUS1_BOOST		152
-#define CLK_GOUT_BUS2_BOOST		153
-#define CLK_GOUT_CORE_BOOST		154
-#define CLK_GOUT_CPUCL0_BOOST		155
-#define CLK_GOUT_CPUCL1_BOOST		156
-#define CLK_GOUT_CPUCL2_BOOST		157
-#define CLK_GOUT_MIF_BOOST		158
-#define CLK_GOUT_MIF_SWITCH		159
-#define CLK_GOUT_BO_BUS			160
-#define CLK_GOUT_BUS0_BUS		161
-#define CLK_GOUT_BUS1_BUS		162
-#define CLK_GOUT_BUS2_BUS		163
-#define CLK_GOUT_CIS_CLK0		164
-#define CLK_GOUT_CIS_CLK1		165
-#define CLK_GOUT_CIS_CLK2		166
-#define CLK_GOUT_CIS_CLK3		167
-#define CLK_GOUT_CIS_CLK4		168
-#define CLK_GOUT_CIS_CLK5		169
-#define CLK_GOUT_CIS_CLK6		170
-#define CLK_GOUT_CIS_CLK7		171
-#define CLK_GOUT_CMU_BOOST		172
-#define CLK_GOUT_CORE_BUS		173
-#define CLK_GOUT_CPUCL0_DBG		174
-#define CLK_GOUT_CPUCL0_SWITCH		175
-#define CLK_GOUT_CPUCL1_SWITCH		176
-#define CLK_GOUT_CPUCL2_SWITCH		177
-#define CLK_GOUT_CSIS_BUS		178
-#define CLK_GOUT_DISP_BUS		179
-#define CLK_GOUT_DNS_BUS		180
-#define CLK_GOUT_DPU_BUS		181
-#define CLK_GOUT_EH_BUS			182
-#define CLK_GOUT_G2D_G2D		183
-#define CLK_GOUT_G2D_MSCL		184
-#define CLK_GOUT_G3AA_G3AA		185
-#define CLK_GOUT_G3D_BUSD		186
-#define CLK_GOUT_G3D_GLB		187
-#define CLK_GOUT_G3D_SWITCH		188
-#define CLK_GOUT_GDC_GDC0		189
-#define CLK_GOUT_GDC_GDC1		190
-#define CLK_GOUT_GDC_SCSC		191
+#define CLK_GOUT_CMU_BUS0_BOOST		151
+#define CLK_GOUT_CMU_BUS1_BOOST		152
+#define CLK_GOUT_CMU_BUS2_BOOST		153
+#define CLK_GOUT_CMU_CORE_BOOST		154
+#define CLK_GOUT_CMU_CPUCL0_BOOST	155
+#define CLK_GOUT_CMU_CPUCL1_BOOST	156
+#define CLK_GOUT_CMU_CPUCL2_BOOST	157
+#define CLK_GOUT_CMU_MIF_BOOST		158
+#define CLK_GOUT_CMU_MIF_SWITCH		159
+#define CLK_GOUT_CMU_BO_BUS		160
+#define CLK_GOUT_CMU_BUS0_BUS		161
+#define CLK_GOUT_CMU_BUS1_BUS		162
+#define CLK_GOUT_CMU_BUS2_BUS		163
+#define CLK_GOUT_CMU_CIS_CLK0		164
+#define CLK_GOUT_CMU_CIS_CLK1		165
+#define CLK_GOUT_CMU_CIS_CLK2		166
+#define CLK_GOUT_CMU_CIS_CLK3		167
+#define CLK_GOUT_CMU_CIS_CLK4		168
+#define CLK_GOUT_CMU_CIS_CLK5		169
+#define CLK_GOUT_CMU_CIS_CLK6		170
+#define CLK_GOUT_CMU_CIS_CLK7		171
+#define CLK_GOUT_CMU_CMU_BOOST		172
+#define CLK_GOUT_CMU_CORE_BUS		173
+#define CLK_GOUT_CMU_CPUCL0_DBG		174
+#define CLK_GOUT_CMU_CPUCL0_SWITCH	175
+#define CLK_GOUT_CMU_CPUCL1_SWITCH	176
+#define CLK_GOUT_CMU_CPUCL2_SWITCH	177
+#define CLK_GOUT_CMU_CSIS_BUS		178
+#define CLK_GOUT_CMU_DISP_BUS		179
+#define CLK_GOUT_CMU_DNS_BUS		180
+#define CLK_GOUT_CMU_DPU_BUS		181
+#define CLK_GOUT_CMU_EH_BUS		182
+#define CLK_GOUT_CMU_G2D_G2D		183
+#define CLK_GOUT_CMU_G2D_MSCL		184
+#define CLK_GOUT_CMU_G3AA_G3AA		185
+#define CLK_GOUT_CMU_G3D_BUSD		186
+#define CLK_GOUT_CMU_G3D_GLB		187
+#define CLK_GOUT_CMU_G3D_SWITCH		188
+#define CLK_GOUT_CMU_GDC_GDC0		189
+#define CLK_GOUT_CMU_GDC_GDC1		190
+#define CLK_GOUT_CMU_GDC_SCSC		191
 #define CLK_GOUT_CMU_HPM		192
-#define CLK_GOUT_HSI0_BUS		193
-#define CLK_GOUT_HSI0_DPGTC		194
-#define CLK_GOUT_HSI0_USB31DRD		195
-#define CLK_GOUT_HSI0_USBDPDBG		196
-#define CLK_GOUT_HSI1_BUS		197
-#define CLK_GOUT_HSI1_PCIE		198
-#define CLK_GOUT_HSI2_BUS		199
-#define CLK_GOUT_HSI2_MMC_CARD		200
-#define CLK_GOUT_HSI2_PCIE		201
-#define CLK_GOUT_HSI2_UFS_EMBD		202
-#define CLK_GOUT_IPP_BUS		203
-#define CLK_GOUT_ITP_BUS		204
-#define CLK_GOUT_MCSC_ITSC		205
-#define CLK_GOUT_MCSC_MCSC		206
-#define CLK_GOUT_MFC_MFC		207
-#define CLK_GOUT_MIF_BUSP		208
-#define CLK_GOUT_MISC_BUS		209
-#define CLK_GOUT_MISC_SSS		210
-#define CLK_GOUT_PDP_BUS		211
-#define CLK_GOUT_PDP_VRA		212
-#define CLK_GOUT_G3AA			213
-#define CLK_GOUT_PERIC0_BUS		214
-#define CLK_GOUT_PERIC0_IP		215
-#define CLK_GOUT_PERIC1_BUS		216
-#define CLK_GOUT_PERIC1_IP		217
-#define CLK_GOUT_TNR_BUS		218
-#define CLK_GOUT_TOP_CMUREF		219
-#define CLK_GOUT_TPU_BUS		220
-#define CLK_GOUT_TPU_TPU		221
-#define CLK_GOUT_TPU_TPUCTL		222
-#define CLK_GOUT_TPU_UART		223
+#define CLK_GOUT_CMU_HSI0_BUS		193
+#define CLK_GOUT_CMU_HSI0_DPGTC		194
+#define CLK_GOUT_CMU_HSI0_USB31DRD	195
+#define CLK_GOUT_CMU_HSI0_USBDPDBG	196
+#define CLK_GOUT_CMU_HSI1_BUS		197
+#define CLK_GOUT_CMU_HSI1_PCIE		198
+#define CLK_GOUT_CMU_HSI2_BUS		199
+#define CLK_GOUT_CMU_HSI2_MMC_CARD	200
+#define CLK_GOUT_CMU_HSI2_PCIE		201
+#define CLK_GOUT_CMU_HSI2_UFS_EMBD	202
+#define CLK_GOUT_CMU_IPP_BUS		203
+#define CLK_GOUT_CMU_ITP_BUS		204
+#define CLK_GOUT_CMU_MCSC_ITSC		205
+#define CLK_GOUT_CMU_MCSC_MCSC		206
+#define CLK_GOUT_CMU_MFC_MFC		207
+#define CLK_GOUT_CMU_MIF_BUSP		208
+#define CLK_GOUT_CMU_MISC_BUS		209
+#define CLK_GOUT_CMU_MISC_SSS		210
+#define CLK_GOUT_CMU_PDP_BUS		211
+#define CLK_GOUT_CMU_PDP_VRA		212
+#define CLK_GOUT_CMU_G3AA		213
+#define CLK_GOUT_CMU_PERIC0_BUS		214
+#define CLK_GOUT_CMU_PERIC0_IP		215
+#define CLK_GOUT_CMU_PERIC1_BUS		216
+#define CLK_GOUT_CMU_PERIC1_IP		217
+#define CLK_GOUT_CMU_TNR_BUS		218
+#define CLK_GOUT_CMU_TOP_CMUREF		219
+#define CLK_GOUT_CMU_TPU_BUS		220
+#define CLK_GOUT_CMU_TPU_TPU		221
+#define CLK_GOUT_CMU_TPU_TPUCTL		222
+#define CLK_GOUT_CMU_TPU_UART		223
 
 /* CMU_APM */
 #define CLK_MOUT_APM_FUNC				1
-- 
cgit v1.2.3


From 58ff9c5acb4aef58e118bbf39736cc4d6c11a3d3 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Wed, 22 Nov 2023 15:03:51 +0900
Subject: PCI: Rename PCI_IRQ_LEGACY to PCI_IRQ_INTX

Rename PCI_IRQ_LEGACY to PCI_IRQ_INTX to be more explicit about the type
of IRQ being referenced as well as to match the PCI specifications
terms. Redefine PCI_IRQ_LEGACY as an alias to PCI_IRQ_INTX to avoid the
need for doing the renaming tree-wide. New drivers and new code should
now prefer using PCI_IRQ_INTX instead of PCI_IRQ_LEGACY.

Link: https://lore.kernel.org/r/20231122060406.14695-2-dlemoal@kernel.org
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Reviewed-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Acked-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 include/linux/pci.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/pci.h b/include/linux/pci.h
index 60ca768bc867..9ab4b46c0d19 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1073,11 +1073,13 @@ enum {
 	PCI_SCAN_ALL_PCIE_DEVS	= 0x00000040,	/* Scan all, not just dev 0 */
 };
 
-#define PCI_IRQ_LEGACY		(1 << 0) /* Allow legacy interrupts */
+#define PCI_IRQ_INTX		(1 << 0) /* Allow INTx interrupts */
 #define PCI_IRQ_MSI		(1 << 1) /* Allow MSI interrupts */
 #define PCI_IRQ_MSIX		(1 << 2) /* Allow MSI-X interrupts */
 #define PCI_IRQ_AFFINITY	(1 << 3) /* Auto-assign affinity */
 
+#define PCI_IRQ_LEGACY		PCI_IRQ_INTX /* Deprecated! Use PCI_IRQ_INTX */
+
 /* These external functions are only available when PCI support is enabled */
 #ifdef CONFIG_PCI
 
-- 
cgit v1.2.3


From 74955cb8ccc38539f8c029336e07e6b43b6a942e Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Wed, 22 Nov 2023 15:03:52 +0900
Subject: PCI: endpoint: Drop PCI_EPC_IRQ_XXX definitions

linux/pci.h defines the IRQ flags PCI_IRQ_INTX, PCI_IRQ_MSI and
PCI_IRQ_MSIX. Let's use these flags directly instead of the endpoint
definitions provided by enum pci_epc_irq_type. This removes the need
for defining this enum type completely.

Link: https://lore.kernel.org/r/20231122060406.14695-3-dlemoal@kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Acked-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/pci/controller/cadence/pcie-cadence-ep.c  |  9 ++++-----
 drivers/pci/controller/dwc/pci-dra7xx.c           |  6 +++---
 drivers/pci/controller/dwc/pci-imx6.c             |  9 ++++-----
 drivers/pci/controller/dwc/pci-keystone.c         |  9 ++++-----
 drivers/pci/controller/dwc/pci-layerscape-ep.c    |  8 ++++----
 drivers/pci/controller/dwc/pcie-artpec6.c         |  8 ++++----
 drivers/pci/controller/dwc/pcie-designware-ep.c   |  2 +-
 drivers/pci/controller/dwc/pcie-designware-plat.c |  9 ++++-----
 drivers/pci/controller/dwc/pcie-designware.h      |  2 +-
 drivers/pci/controller/dwc/pcie-keembay.c         | 13 ++++++-------
 drivers/pci/controller/dwc/pcie-qcom-ep.c         |  6 +++---
 drivers/pci/controller/dwc/pcie-rcar-gen4.c       |  7 +++----
 drivers/pci/controller/dwc/pcie-tegra194.c        |  9 ++++-----
 drivers/pci/controller/dwc/pcie-uniphier-ep.c     |  7 +++----
 drivers/pci/controller/pcie-rcar-ep.c             |  7 +++----
 drivers/pci/controller/pcie-rockchip-ep.c         |  7 +++----
 drivers/pci/endpoint/functions/pci-epf-mhi.c      |  2 +-
 drivers/pci/endpoint/functions/pci-epf-ntb.c      |  4 ++--
 drivers/pci/endpoint/functions/pci-epf-test.c     |  6 +++---
 drivers/pci/endpoint/functions/pci-epf-vntb.c     |  7 ++-----
 drivers/pci/endpoint/pci-epc-core.c               |  2 +-
 include/linux/pci-epc.h                           | 11 ++---------
 22 files changed, 65 insertions(+), 85 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/controller/cadence/pcie-cadence-ep.c b/drivers/pci/controller/cadence/pcie-cadence-ep.c
index 3142feb8ac19..3d71d687ea64 100644
--- a/drivers/pci/controller/cadence/pcie-cadence-ep.c
+++ b/drivers/pci/controller/cadence/pcie-cadence-ep.c
@@ -532,25 +532,24 @@ static int cdns_pcie_ep_send_msix_irq(struct cdns_pcie_ep *ep, u8 fn, u8 vfn,
 }
 
 static int cdns_pcie_ep_raise_irq(struct pci_epc *epc, u8 fn, u8 vfn,
-				  enum pci_epc_irq_type type,
-				  u16 interrupt_num)
+				  unsigned int type, u16 interrupt_num)
 {
 	struct cdns_pcie_ep *ep = epc_get_drvdata(epc);
 	struct cdns_pcie *pcie = &ep->pcie;
 	struct device *dev = pcie->dev;
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
+	case PCI_IRQ_INTX:
 		if (vfn > 0) {
 			dev_err(dev, "Cannot raise legacy interrupts for VF\n");
 			return -EINVAL;
 		}
 		return cdns_pcie_ep_send_legacy_irq(ep, fn, vfn, 0);
 
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_MSI:
 		return cdns_pcie_ep_send_msi_irq(ep, fn, vfn, interrupt_num);
 
-	case PCI_EPC_IRQ_MSIX:
+	case PCI_IRQ_MSIX:
 		return cdns_pcie_ep_send_msix_irq(ep, fn, vfn, interrupt_num);
 
 	default:
diff --git a/drivers/pci/controller/dwc/pci-dra7xx.c b/drivers/pci/controller/dwc/pci-dra7xx.c
index b445ffe95e3f..f257a42f3314 100644
--- a/drivers/pci/controller/dwc/pci-dra7xx.c
+++ b/drivers/pci/controller/dwc/pci-dra7xx.c
@@ -404,16 +404,16 @@ static void dra7xx_pcie_raise_msi_irq(struct dra7xx_pcie *dra7xx,
 }
 
 static int dra7xx_pcie_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				 enum pci_epc_irq_type type, u16 interrupt_num)
+				 unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 	struct dra7xx_pcie *dra7xx = to_dra7xx_pcie(pci);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
+	case PCI_IRQ_INTX:
 		dra7xx_pcie_raise_legacy_irq(dra7xx);
 		break;
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_MSI:
 		dra7xx_pcie_raise_msi_irq(dra7xx, interrupt_num);
 		break;
 	default:
diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c
index 74703362aeec..a5365ab8897e 100644
--- a/drivers/pci/controller/dwc/pci-imx6.c
+++ b/drivers/pci/controller/dwc/pci-imx6.c
@@ -1058,17 +1058,16 @@ static void imx6_pcie_ep_init(struct dw_pcie_ep *ep)
 }
 
 static int imx6_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				  enum pci_epc_irq_type type,
-				  u16 interrupt_num)
+				  unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
+	case PCI_IRQ_INTX:
 		return dw_pcie_ep_raise_legacy_irq(ep, func_no);
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_MSI:
 		return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num);
-	case PCI_EPC_IRQ_MSIX:
+	case PCI_IRQ_MSIX:
 		return dw_pcie_ep_raise_msix_irq(ep, func_no, interrupt_num);
 	default:
 		dev_err(pci->dev, "UNKNOWN IRQ type\n");
diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c
index 0def919f89fa..84f6a4acee07 100644
--- a/drivers/pci/controller/dwc/pci-keystone.c
+++ b/drivers/pci/controller/dwc/pci-keystone.c
@@ -900,20 +900,19 @@ static void ks_pcie_am654_raise_legacy_irq(struct keystone_pcie *ks_pcie)
 }
 
 static int ks_pcie_am654_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				   enum pci_epc_irq_type type,
-				   u16 interrupt_num)
+				   unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 	struct keystone_pcie *ks_pcie = to_keystone_pcie(pci);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
+	case PCI_IRQ_INTX:
 		ks_pcie_am654_raise_legacy_irq(ks_pcie);
 		break;
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_MSI:
 		dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num);
 		break;
-	case PCI_EPC_IRQ_MSIX:
+	case PCI_IRQ_MSIX:
 		dw_pcie_ep_raise_msix_irq(ep, func_no, interrupt_num);
 		break;
 	default:
diff --git a/drivers/pci/controller/dwc/pci-layerscape-ep.c b/drivers/pci/controller/dwc/pci-layerscape-ep.c
index 3d3c50ef4b6f..5f78a9415286 100644
--- a/drivers/pci/controller/dwc/pci-layerscape-ep.c
+++ b/drivers/pci/controller/dwc/pci-layerscape-ep.c
@@ -166,16 +166,16 @@ static void ls_pcie_ep_init(struct dw_pcie_ep *ep)
 }
 
 static int ls_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				enum pci_epc_irq_type type, u16 interrupt_num)
+				unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
+	case PCI_IRQ_INTX:
 		return dw_pcie_ep_raise_legacy_irq(ep, func_no);
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_MSI:
 		return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num);
-	case PCI_EPC_IRQ_MSIX:
+	case PCI_IRQ_MSIX:
 		return dw_pcie_ep_raise_msix_irq_doorbell(ep, func_no,
 							  interrupt_num);
 	default:
diff --git a/drivers/pci/controller/dwc/pcie-artpec6.c b/drivers/pci/controller/dwc/pcie-artpec6.c
index 9b572a2b2c9a..fc426182443a 100644
--- a/drivers/pci/controller/dwc/pcie-artpec6.c
+++ b/drivers/pci/controller/dwc/pcie-artpec6.c
@@ -352,15 +352,15 @@ static void artpec6_pcie_ep_init(struct dw_pcie_ep *ep)
 }
 
 static int artpec6_pcie_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				  enum pci_epc_irq_type type, u16 interrupt_num)
+				  unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
-		dev_err(pci->dev, "EP cannot trigger legacy IRQs\n");
+	case PCI_IRQ_INTX:
+		dev_err(pci->dev, "EP cannot trigger INTx IRQs\n");
 		return -EINVAL;
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_MSI:
 		return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num);
 	default:
 		dev_err(pci->dev, "UNKNOWN IRQ type\n");
diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index f6207989fc6a..87759c899fab 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -443,7 +443,7 @@ static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 }
 
 static int dw_pcie_ep_raise_irq(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
-				enum pci_epc_irq_type type, u16 interrupt_num)
+				unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
 
diff --git a/drivers/pci/controller/dwc/pcie-designware-plat.c b/drivers/pci/controller/dwc/pcie-designware-plat.c
index b625841e98aa..c83968aa0149 100644
--- a/drivers/pci/controller/dwc/pcie-designware-plat.c
+++ b/drivers/pci/controller/dwc/pcie-designware-plat.c
@@ -42,17 +42,16 @@ static void dw_plat_pcie_ep_init(struct dw_pcie_ep *ep)
 }
 
 static int dw_plat_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				     enum pci_epc_irq_type type,
-				     u16 interrupt_num)
+				     unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
+	case PCI_IRQ_INTX:
 		return dw_pcie_ep_raise_legacy_irq(ep, func_no);
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_MSI:
 		return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num);
-	case PCI_EPC_IRQ_MSIX:
+	case PCI_IRQ_MSIX:
 		return dw_pcie_ep_raise_msix_irq(ep, func_no, interrupt_num);
 	default:
 		dev_err(pci->dev, "UNKNOWN IRQ type\n");
diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h
index 55ff76e3d384..ffb9a62f3179 100644
--- a/drivers/pci/controller/dwc/pcie-designware.h
+++ b/drivers/pci/controller/dwc/pcie-designware.h
@@ -335,7 +335,7 @@ struct dw_pcie_ep_ops {
 	void	(*ep_init)(struct dw_pcie_ep *ep);
 	void	(*deinit)(struct dw_pcie_ep *ep);
 	int	(*raise_irq)(struct dw_pcie_ep *ep, u8 func_no,
-			     enum pci_epc_irq_type type, u16 interrupt_num);
+			     unsigned int type, u16 interrupt_num);
 	const struct pci_epc_features* (*get_features)(struct dw_pcie_ep *ep);
 	/*
 	 * Provide a method to implement the different func config space
diff --git a/drivers/pci/controller/dwc/pcie-keembay.c b/drivers/pci/controller/dwc/pcie-keembay.c
index 289bff99d762..8e0e2e28ef67 100644
--- a/drivers/pci/controller/dwc/pcie-keembay.c
+++ b/drivers/pci/controller/dwc/pcie-keembay.c
@@ -289,19 +289,18 @@ static void keembay_pcie_ep_init(struct dw_pcie_ep *ep)
 }
 
 static int keembay_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				     enum pci_epc_irq_type type,
-				     u16 interrupt_num)
+				     unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
-		/* Legacy interrupts are not supported in Keem Bay */
-		dev_err(pci->dev, "Legacy IRQ is not supported\n");
+	case PCI_IRQ_INTX:
+		/* INTx interrupts are not supported in Keem Bay */
+		dev_err(pci->dev, "INTx IRQ is not supported\n");
 		return -EINVAL;
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_MSI:
 		return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num);
-	case PCI_EPC_IRQ_MSIX:
+	case PCI_IRQ_MSIX:
 		return dw_pcie_ep_raise_msix_irq(ep, func_no, interrupt_num);
 	default:
 		dev_err(pci->dev, "Unknown IRQ type %d\n", type);
diff --git a/drivers/pci/controller/dwc/pcie-qcom-ep.c b/drivers/pci/controller/dwc/pcie-qcom-ep.c
index 9e58f055199a..2e5ab5fef310 100644
--- a/drivers/pci/controller/dwc/pcie-qcom-ep.c
+++ b/drivers/pci/controller/dwc/pcie-qcom-ep.c
@@ -726,14 +726,14 @@ static int qcom_pcie_ep_enable_irq_resources(struct platform_device *pdev,
 }
 
 static int qcom_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				  enum pci_epc_irq_type type, u16 interrupt_num)
+				  unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
+	case PCI_IRQ_INTX:
 		return dw_pcie_ep_raise_legacy_irq(ep, func_no);
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_MSI:
 		return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num);
 	default:
 		dev_err(pci->dev, "Unknown IRQ type\n");
diff --git a/drivers/pci/controller/dwc/pcie-rcar-gen4.c b/drivers/pci/controller/dwc/pcie-rcar-gen4.c
index 3bc45e513b3d..25354a82674d 100644
--- a/drivers/pci/controller/dwc/pcie-rcar-gen4.c
+++ b/drivers/pci/controller/dwc/pcie-rcar-gen4.c
@@ -362,15 +362,14 @@ static void rcar_gen4_pcie_ep_deinit(struct dw_pcie_ep *ep)
 }
 
 static int rcar_gen4_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				       enum pci_epc_irq_type type,
-				       u16 interrupt_num)
+				       unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie *dw = to_dw_pcie_from_ep(ep);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
+	case PCI_IRQ_INTX:
 		return dw_pcie_ep_raise_legacy_irq(ep, func_no);
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_MSI:
 		return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num);
 	default:
 		dev_err(dw->dev, "Unknown IRQ type\n");
diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c
index 0fe113598ebb..a1f37d2d7798 100644
--- a/drivers/pci/controller/dwc/pcie-tegra194.c
+++ b/drivers/pci/controller/dwc/pcie-tegra194.c
@@ -1979,20 +1979,19 @@ static int tegra_pcie_ep_raise_msix_irq(struct tegra_pcie_dw *pcie, u16 irq)
 }
 
 static int tegra_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				   enum pci_epc_irq_type type,
-				   u16 interrupt_num)
+				   unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 	struct tegra_pcie_dw *pcie = to_tegra_pcie(pci);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
+	case PCI_IRQ_INTX:
 		return tegra_pcie_ep_raise_legacy_irq(pcie, interrupt_num);
 
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_MSI:
 		return tegra_pcie_ep_raise_msi_irq(pcie, interrupt_num);
 
-	case PCI_EPC_IRQ_MSIX:
+	case PCI_IRQ_MSIX:
 		return tegra_pcie_ep_raise_msix_irq(pcie, interrupt_num);
 
 	default:
diff --git a/drivers/pci/controller/dwc/pcie-uniphier-ep.c b/drivers/pci/controller/dwc/pcie-uniphier-ep.c
index cba3c88fcf39..d47236d5678d 100644
--- a/drivers/pci/controller/dwc/pcie-uniphier-ep.c
+++ b/drivers/pci/controller/dwc/pcie-uniphier-ep.c
@@ -256,15 +256,14 @@ static int uniphier_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep,
 }
 
 static int uniphier_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				      enum pci_epc_irq_type type,
-				      u16 interrupt_num)
+				      unsigned int type, u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
+	case PCI_IRQ_INTX:
 		return uniphier_pcie_ep_raise_legacy_irq(ep);
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_MSI:
 		return uniphier_pcie_ep_raise_msi_irq(ep, func_no,
 						      interrupt_num);
 	default:
diff --git a/drivers/pci/controller/pcie-rcar-ep.c b/drivers/pci/controller/pcie-rcar-ep.c
index 7034c0ff23d0..e6909271def7 100644
--- a/drivers/pci/controller/pcie-rcar-ep.c
+++ b/drivers/pci/controller/pcie-rcar-ep.c
@@ -402,16 +402,15 @@ static int rcar_pcie_ep_assert_msi(struct rcar_pcie *pcie,
 }
 
 static int rcar_pcie_ep_raise_irq(struct pci_epc *epc, u8 fn, u8 vfn,
-				  enum pci_epc_irq_type type,
-				  u16 interrupt_num)
+				  unsigned int type, u16 interrupt_num)
 {
 	struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
+	case PCI_IRQ_INTX:
 		return rcar_pcie_ep_assert_intx(ep, fn, 0);
 
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_MSI:
 		return rcar_pcie_ep_assert_msi(&ep->pcie, fn, interrupt_num);
 
 	default:
diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c
index 0af0e965fb57..95b1c8ef59c3 100644
--- a/drivers/pci/controller/pcie-rockchip-ep.c
+++ b/drivers/pci/controller/pcie-rockchip-ep.c
@@ -407,15 +407,14 @@ static int rockchip_pcie_ep_send_msi_irq(struct rockchip_pcie_ep *ep, u8 fn,
 }
 
 static int rockchip_pcie_ep_raise_irq(struct pci_epc *epc, u8 fn, u8 vfn,
-				      enum pci_epc_irq_type type,
-				      u16 interrupt_num)
+				      unsigned int type, u16 interrupt_num)
 {
 	struct rockchip_pcie_ep *ep = epc_get_drvdata(epc);
 
 	switch (type) {
-	case PCI_EPC_IRQ_LEGACY:
+	case PCI_IRQ_INTX:
 		return rockchip_pcie_ep_send_legacy_irq(ep, fn, 0);
-	case PCI_EPC_IRQ_MSI:
+	case PCI_IRQ_MSI:
 		return rockchip_pcie_ep_send_msi_irq(ep, fn, interrupt_num);
 	default:
 		return -EINVAL;
diff --git a/drivers/pci/endpoint/functions/pci-epf-mhi.c b/drivers/pci/endpoint/functions/pci-epf-mhi.c
index b7b9d3e21f97..b9f8d2858cb7 100644
--- a/drivers/pci/endpoint/functions/pci-epf-mhi.c
+++ b/drivers/pci/endpoint/functions/pci-epf-mhi.c
@@ -205,7 +205,7 @@ static void pci_epf_mhi_raise_irq(struct mhi_ep_cntrl *mhi_cntrl, u32 vector)
 	 * MHI supplies 0 based MSI vectors but the API expects the vector
 	 * number to start from 1, so we need to increment the vector by 1.
 	 */
-	pci_epc_raise_irq(epc, epf->func_no, epf->vfunc_no, PCI_EPC_IRQ_MSI,
+	pci_epc_raise_irq(epc, epf->func_no, epf->vfunc_no, PCI_IRQ_MSI,
 			  vector + 1);
 }
 
diff --git a/drivers/pci/endpoint/functions/pci-epf-ntb.c b/drivers/pci/endpoint/functions/pci-epf-ntb.c
index 9aac2c6f3bb9..fad00b1a8335 100644
--- a/drivers/pci/endpoint/functions/pci-epf-ntb.c
+++ b/drivers/pci/endpoint/functions/pci-epf-ntb.c
@@ -140,9 +140,9 @@ static struct pci_epf_header epf_ntb_header = {
 static int epf_ntb_link_up(struct epf_ntb *ntb, bool link_up)
 {
 	enum pci_epc_interface_type type;
-	enum pci_epc_irq_type irq_type;
 	struct epf_ntb_epc *ntb_epc;
 	struct epf_ntb_ctrl *ctrl;
+	unsigned int irq_type;
 	struct pci_epc *epc;
 	u8 func_no, vfunc_no;
 	bool is_msix;
@@ -159,7 +159,7 @@ static int epf_ntb_link_up(struct epf_ntb *ntb, bool link_up)
 			ctrl->link_status |= LINK_STATUS_UP;
 		else
 			ctrl->link_status &= ~LINK_STATUS_UP;
-		irq_type = is_msix ? PCI_EPC_IRQ_MSIX : PCI_EPC_IRQ_MSI;
+		irq_type = is_msix ? PCI_IRQ_MSIX : PCI_IRQ_MSI;
 		ret = pci_epc_raise_irq(epc, func_no, vfunc_no, irq_type, 1);
 		if (ret) {
 			dev_err(&epc->dev,
diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c
index 1f0d2b84296a..9d39fda5c348 100644
--- a/drivers/pci/endpoint/functions/pci-epf-test.c
+++ b/drivers/pci/endpoint/functions/pci-epf-test.c
@@ -602,7 +602,7 @@ static void pci_epf_test_raise_irq(struct pci_epf_test *epf_test,
 	switch (reg->irq_type) {
 	case IRQ_TYPE_LEGACY:
 		pci_epc_raise_irq(epc, epf->func_no, epf->vfunc_no,
-				  PCI_EPC_IRQ_LEGACY, 0);
+				  PCI_IRQ_INTX, 0);
 		break;
 	case IRQ_TYPE_MSI:
 		count = pci_epc_get_msi(epc, epf->func_no, epf->vfunc_no);
@@ -612,7 +612,7 @@ static void pci_epf_test_raise_irq(struct pci_epf_test *epf_test,
 			return;
 		}
 		pci_epc_raise_irq(epc, epf->func_no, epf->vfunc_no,
-				  PCI_EPC_IRQ_MSI, reg->irq_number);
+				  PCI_IRQ_MSI, reg->irq_number);
 		break;
 	case IRQ_TYPE_MSIX:
 		count = pci_epc_get_msix(epc, epf->func_no, epf->vfunc_no);
@@ -622,7 +622,7 @@ static void pci_epf_test_raise_irq(struct pci_epf_test *epf_test,
 			return;
 		}
 		pci_epc_raise_irq(epc, epf->func_no, epf->vfunc_no,
-				  PCI_EPC_IRQ_MSIX, reg->irq_number);
+				  PCI_IRQ_MSIX, reg->irq_number);
 		break;
 	default:
 		dev_err(dev, "Failed to raise IRQ, unknown type\n");
diff --git a/drivers/pci/endpoint/functions/pci-epf-vntb.c b/drivers/pci/endpoint/functions/pci-epf-vntb.c
index 3f60128560ed..e6a0bcc177e4 100644
--- a/drivers/pci/endpoint/functions/pci-epf-vntb.c
+++ b/drivers/pci/endpoint/functions/pci-epf-vntb.c
@@ -1172,11 +1172,8 @@ static int vntb_epf_peer_db_set(struct ntb_dev *ndev, u64 db_bits)
 	func_no = ntb->epf->func_no;
 	vfunc_no = ntb->epf->vfunc_no;
 
-	ret = pci_epc_raise_irq(ntb->epf->epc,
-				func_no,
-				vfunc_no,
-				PCI_EPC_IRQ_MSI,
-				interrupt_num + 1);
+	ret = pci_epc_raise_irq(ntb->epf->epc, func_no, vfunc_no,
+				PCI_IRQ_MSI, interrupt_num + 1);
 	if (ret)
 		dev_err(&ntb->ntb.dev, "Failed to raise IRQ\n");
 
diff --git a/drivers/pci/endpoint/pci-epc-core.c b/drivers/pci/endpoint/pci-epc-core.c
index 56e1184bc6c2..0810420df42c 100644
--- a/drivers/pci/endpoint/pci-epc-core.c
+++ b/drivers/pci/endpoint/pci-epc-core.c
@@ -217,7 +217,7 @@ EXPORT_SYMBOL_GPL(pci_epc_start);
  * Invoke to raise an legacy, MSI or MSI-X interrupt
  */
 int pci_epc_raise_irq(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
-		      enum pci_epc_irq_type type, u16 interrupt_num)
+		      unsigned int type, u16 interrupt_num)
 {
 	int ret;
 
diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h
index 5cb694031072..f498f9aa2ab0 100644
--- a/include/linux/pci-epc.h
+++ b/include/linux/pci-epc.h
@@ -19,13 +19,6 @@ enum pci_epc_interface_type {
 	SECONDARY_INTERFACE,
 };
 
-enum pci_epc_irq_type {
-	PCI_EPC_IRQ_UNKNOWN,
-	PCI_EPC_IRQ_LEGACY,
-	PCI_EPC_IRQ_MSI,
-	PCI_EPC_IRQ_MSIX,
-};
-
 static inline const char *
 pci_epc_interface_string(enum pci_epc_interface_type type)
 {
@@ -79,7 +72,7 @@ struct pci_epc_ops {
 			    u16 interrupts, enum pci_barno, u32 offset);
 	int	(*get_msix)(struct pci_epc *epc, u8 func_no, u8 vfunc_no);
 	int	(*raise_irq)(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
-			     enum pci_epc_irq_type type, u16 interrupt_num);
+			     unsigned int type, u16 interrupt_num);
 	int	(*map_msi_irq)(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 			       phys_addr_t phys_addr, u8 interrupt_num,
 			       u32 entry_size, u32 *msi_data,
@@ -229,7 +222,7 @@ int pci_epc_map_msi_irq(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 			phys_addr_t phys_addr, u8 interrupt_num,
 			u32 entry_size, u32 *msi_data, u32 *msi_addr_offset);
 int pci_epc_raise_irq(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
-		      enum pci_epc_irq_type type, u16 interrupt_num);
+		      unsigned int type, u16 interrupt_num);
 int pci_epc_start(struct pci_epc *epc);
 void pci_epc_stop(struct pci_epc *epc);
 const struct pci_epc_features *pci_epc_get_features(struct pci_epc *epc,
-- 
cgit v1.2.3


From acd288666979a49538d70e0c0d86e1118b445058 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Wed, 22 Nov 2023 15:03:55 +0900
Subject: misc: pci_endpoint_test: Use INTX instead of LEGACY

In the root complex pci endpoint test function driver, change macros and
functions names using the term "legacy" to use "intx" instead to
match the term used in the PCI specifications.

Link: https://lore.kernel.org/r/20231122060406.14695-6-dlemoal@kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 drivers/misc/pci_endpoint_test.c | 30 +++++++++++++++---------------
 include/uapi/linux/pcitest.h     |  3 ++-
 2 files changed, 17 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/misc/pci_endpoint_test.c b/drivers/misc/pci_endpoint_test.c
index af519088732d..2d7822d9dfe9 100644
--- a/drivers/misc/pci_endpoint_test.c
+++ b/drivers/misc/pci_endpoint_test.c
@@ -28,14 +28,14 @@
 #define DRV_MODULE_NAME				"pci-endpoint-test"
 
 #define IRQ_TYPE_UNDEFINED			-1
-#define IRQ_TYPE_LEGACY				0
+#define IRQ_TYPE_INTX				0
 #define IRQ_TYPE_MSI				1
 #define IRQ_TYPE_MSIX				2
 
 #define PCI_ENDPOINT_TEST_MAGIC			0x0
 
 #define PCI_ENDPOINT_TEST_COMMAND		0x4
-#define COMMAND_RAISE_LEGACY_IRQ		BIT(0)
+#define COMMAND_RAISE_INTX_IRQ			BIT(0)
 #define COMMAND_RAISE_MSI_IRQ			BIT(1)
 #define COMMAND_RAISE_MSIX_IRQ			BIT(2)
 #define COMMAND_READ				BIT(3)
@@ -183,8 +183,8 @@ static bool pci_endpoint_test_alloc_irq_vectors(struct pci_endpoint_test *test,
 	bool res = true;
 
 	switch (type) {
-	case IRQ_TYPE_LEGACY:
-		irq = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_LEGACY);
+	case IRQ_TYPE_INTX:
+		irq = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_INTX);
 		if (irq < 0)
 			dev_err(dev, "Failed to get Legacy interrupt\n");
 		break;
@@ -244,7 +244,7 @@ static bool pci_endpoint_test_request_irq(struct pci_endpoint_test *test)
 
 fail:
 	switch (irq_type) {
-	case IRQ_TYPE_LEGACY:
+	case IRQ_TYPE_INTX:
 		dev_err(dev, "Failed to request IRQ %d for Legacy\n",
 			pci_irq_vector(pdev, i));
 		break;
@@ -291,15 +291,15 @@ static bool pci_endpoint_test_bar(struct pci_endpoint_test *test,
 	return true;
 }
 
-static bool pci_endpoint_test_legacy_irq(struct pci_endpoint_test *test)
+static bool pci_endpoint_test_intx_irq(struct pci_endpoint_test *test)
 {
 	u32 val;
 
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_TYPE,
-				 IRQ_TYPE_LEGACY);
+				 IRQ_TYPE_INTX);
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_NUMBER, 0);
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_COMMAND,
-				 COMMAND_RAISE_LEGACY_IRQ);
+				 COMMAND_RAISE_INTX_IRQ);
 	val = wait_for_completion_timeout(&test->irq_raised,
 					  msecs_to_jiffies(1000));
 	if (!val)
@@ -385,7 +385,7 @@ static bool pci_endpoint_test_copy(struct pci_endpoint_test *test,
 	if (use_dma)
 		flags |= FLAG_USE_DMA;
 
-	if (irq_type < IRQ_TYPE_LEGACY || irq_type > IRQ_TYPE_MSIX) {
+	if (irq_type < IRQ_TYPE_INTX || irq_type > IRQ_TYPE_MSIX) {
 		dev_err(dev, "Invalid IRQ type option\n");
 		goto err;
 	}
@@ -521,7 +521,7 @@ static bool pci_endpoint_test_write(struct pci_endpoint_test *test,
 	if (use_dma)
 		flags |= FLAG_USE_DMA;
 
-	if (irq_type < IRQ_TYPE_LEGACY || irq_type > IRQ_TYPE_MSIX) {
+	if (irq_type < IRQ_TYPE_INTX || irq_type > IRQ_TYPE_MSIX) {
 		dev_err(dev, "Invalid IRQ type option\n");
 		goto err;
 	}
@@ -621,7 +621,7 @@ static bool pci_endpoint_test_read(struct pci_endpoint_test *test,
 	if (use_dma)
 		flags |= FLAG_USE_DMA;
 
-	if (irq_type < IRQ_TYPE_LEGACY || irq_type > IRQ_TYPE_MSIX) {
+	if (irq_type < IRQ_TYPE_INTX || irq_type > IRQ_TYPE_MSIX) {
 		dev_err(dev, "Invalid IRQ type option\n");
 		goto err;
 	}
@@ -691,7 +691,7 @@ static bool pci_endpoint_test_set_irq(struct pci_endpoint_test *test,
 	struct pci_dev *pdev = test->pdev;
 	struct device *dev = &pdev->dev;
 
-	if (req_irq_type < IRQ_TYPE_LEGACY || req_irq_type > IRQ_TYPE_MSIX) {
+	if (req_irq_type < IRQ_TYPE_INTX || req_irq_type > IRQ_TYPE_MSIX) {
 		dev_err(dev, "Invalid IRQ type option\n");
 		return false;
 	}
@@ -737,8 +737,8 @@ static long pci_endpoint_test_ioctl(struct file *file, unsigned int cmd,
 			goto ret;
 		ret = pci_endpoint_test_bar(test, bar);
 		break;
-	case PCITEST_LEGACY_IRQ:
-		ret = pci_endpoint_test_legacy_irq(test);
+	case PCITEST_INTX_IRQ:
+		ret = pci_endpoint_test_intx_irq(test);
 		break;
 	case PCITEST_MSI:
 	case PCITEST_MSIX:
@@ -801,7 +801,7 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev,
 	test->irq_type = IRQ_TYPE_UNDEFINED;
 
 	if (no_msi)
-		irq_type = IRQ_TYPE_LEGACY;
+		irq_type = IRQ_TYPE_INTX;
 
 	data = (struct pci_endpoint_test_data *)ent->driver_data;
 	if (data) {
diff --git a/include/uapi/linux/pcitest.h b/include/uapi/linux/pcitest.h
index f9c1af8d141b..94b46b043b53 100644
--- a/include/uapi/linux/pcitest.h
+++ b/include/uapi/linux/pcitest.h
@@ -11,7 +11,8 @@
 #define __UAPI_LINUX_PCITEST_H
 
 #define PCITEST_BAR		_IO('P', 0x1)
-#define PCITEST_LEGACY_IRQ	_IO('P', 0x2)
+#define PCITEST_INTX_IRQ	_IO('P', 0x2)
+#define PCITEST_LEGACY_IRQ	PCITEST_INTX_IRQ
 #define PCITEST_MSI		_IOW('P', 0x3, int)
 #define PCITEST_WRITE		_IOW('P', 0x4, unsigned long)
 #define PCITEST_READ		_IOW('P', 0x5, unsigned long)
-- 
cgit v1.2.3


From 3314f2097dee43defc20554f961a8b17f4787e2d Mon Sep 17 00:00:00 2001
From: Jesse Brandeburg <jesse.brandeburg@intel.com>
Date: Tue, 5 Dec 2023 17:01:01 -0800
Subject: intel: add bit macro includes where needed

This series is introducing the use of FIELD_GET and FIELD_PREP which
requires bitfield.h to be included. Fix all the includes in this one
change, and rearrange includes into alphabetical order to ease
readability and future maintenance.

virtchnl.h and it's usage was modified to have it's own includes as it
should. This required including bits.h for virtchnl.h.

Reviewed-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/e1000/e1000_hw.c    |  1 +
 drivers/net/ethernet/intel/fm10k/fm10k_pf.c    |  1 +
 drivers/net/ethernet/intel/fm10k/fm10k_vf.c    |  1 +
 drivers/net/ethernet/intel/i40e/i40e_common.c  |  1 +
 drivers/net/ethernet/intel/i40e/i40e_dcb.c     |  2 ++
 drivers/net/ethernet/intel/i40e/i40e_nvm.c     |  1 +
 drivers/net/ethernet/intel/iavf/iavf_common.c  |  3 ++-
 drivers/net/ethernet/intel/iavf/iavf_ethtool.c |  5 +++--
 drivers/net/ethernet/intel/iavf/iavf_fdir.c    |  1 +
 drivers/net/ethernet/intel/iavf/iavf_txrx.c    |  1 +
 drivers/net/ethernet/intel/igb/e1000_i210.c    |  4 ++--
 drivers/net/ethernet/intel/igb/e1000_nvm.c     |  4 ++--
 drivers/net/ethernet/intel/igb/e1000_phy.c     |  4 ++--
 drivers/net/ethernet/intel/igbvf/netdev.c      | 28 +++++++++++++-------------
 drivers/net/ethernet/intel/igc/igc_i225.c      |  1 +
 drivers/net/ethernet/intel/igc/igc_phy.c       |  1 +
 include/linux/avf/virtchnl.h                   |  1 +
 17 files changed, 37 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/intel/e1000/e1000_hw.c b/drivers/net/ethernet/intel/e1000/e1000_hw.c
index 4542e2bc28e8..4576511c99f5 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_hw.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_hw.c
@@ -5,6 +5,7 @@
  * Shared functions for accessing and configuring the MAC
  */
 
+#include <linux/bitfield.h>
 #include "e1000.h"
 
 static s32 e1000_check_downshift(struct e1000_hw *hw);
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c
index af1b0cde3670..ae700a1807c6 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright(c) 2013 - 2019 Intel Corporation. */
 
+#include <linux/bitfield.h>
 #include "fm10k_pf.h"
 #include "fm10k_vf.h"
 
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_vf.c b/drivers/net/ethernet/intel/fm10k/fm10k_vf.c
index dc8ccd378ec9..c50928ec14ff 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_vf.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_vf.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright(c) 2013 - 2019 Intel Corporation. */
 
+#include <linux/bitfield.h>
 #include "fm10k_vf.h"
 
 /**
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index bd52b73cf61f..522cf2e5f365 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -2,6 +2,7 @@
 /* Copyright(c) 2013 - 2021 Intel Corporation. */
 
 #include <linux/avf/virtchnl.h>
+#include <linux/bitfield.h>
 #include <linux/delay.h>
 #include <linux/etherdevice.h>
 #include <linux/pci.h>
diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.c b/drivers/net/ethernet/intel/i40e/i40e_dcb.c
index 498728e16a37..0d334036ab8b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_dcb.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.c
@@ -1,6 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright(c) 2013 - 2021 Intel Corporation. */
 
+#include <linux/bitfield.h>
+#include "i40e_adminq.h"
 #include "i40e_alloc.h"
 #include "i40e_dcb.h"
 #include "i40e_prototype.h"
diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
index 62eb34871094..157eacfdc918 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright(c) 2013 - 2018 Intel Corporation. */
 
+#include <linux/bitfield.h>
 #include <linux/delay.h>
 #include "i40e_alloc.h"
 #include "i40e_prototype.h"
diff --git a/drivers/net/ethernet/intel/iavf/iavf_common.c b/drivers/net/ethernet/intel/iavf/iavf_common.c
index 89d2bce529ae..af5cc69f26e3 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_common.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_common.c
@@ -1,10 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright(c) 2013 - 2018 Intel Corporation. */
 
+#include <linux/avf/virtchnl.h>
+#include <linux/bitfield.h>
 #include "iavf_type.h"
 #include "iavf_adminq.h"
 #include "iavf_prototype.h"
-#include <linux/avf/virtchnl.h>
 
 /**
  * iavf_aq_str - convert AQ err code to a string
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
index cdb4849f5db4..bffb45802dab 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
@@ -1,11 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright(c) 2013 - 2018 Intel Corporation. */
 
+#include <linux/bitfield.h>
+#include <linux/uaccess.h>
+
 /* ethtool support for iavf */
 #include "iavf.h"
 
-#include <linux/uaccess.h>
-
 /* ethtool statistics helpers */
 
 /**
diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.c b/drivers/net/ethernet/intel/iavf/iavf_fdir.c
index 03e774bd2a5b..65ddcd81c993 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_fdir.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.c
@@ -3,6 +3,7 @@
 
 /* flow director ethtool support for iavf */
 
+#include <linux/bitfield.h>
 #include "iavf.h"
 
 #define GTPU_PORT	2152
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
index d64c4997136b..fb7edba9c2f8 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright(c) 2013 - 2018 Intel Corporation. */
 
+#include <linux/bitfield.h>
 #include <linux/prefetch.h>
 
 #include "iavf.h"
diff --git a/drivers/net/ethernet/intel/igb/e1000_i210.c b/drivers/net/ethernet/intel/igb/e1000_i210.c
index b9b9d35494d2..53b396fd194a 100644
--- a/drivers/net/ethernet/intel/igb/e1000_i210.c
+++ b/drivers/net/ethernet/intel/igb/e1000_i210.c
@@ -5,9 +5,9 @@
  * e1000_i211
  */
 
-#include <linux/types.h>
+#include <linux/bitfield.h>
 #include <linux/if_ether.h>
-
+#include <linux/types.h>
 #include "e1000_hw.h"
 #include "e1000_i210.h"
 
diff --git a/drivers/net/ethernet/intel/igb/e1000_nvm.c b/drivers/net/ethernet/intel/igb/e1000_nvm.c
index fa136e6e9328..0da57e89593a 100644
--- a/drivers/net/ethernet/intel/igb/e1000_nvm.c
+++ b/drivers/net/ethernet/intel/igb/e1000_nvm.c
@@ -1,9 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright(c) 2007 - 2018 Intel Corporation. */
 
-#include <linux/if_ether.h>
+#include <linux/bitfield.h>
 #include <linux/delay.h>
-
+#include <linux/if_ether.h>
 #include "e1000_mac.h"
 #include "e1000_nvm.h"
 
diff --git a/drivers/net/ethernet/intel/igb/e1000_phy.c b/drivers/net/ethernet/intel/igb/e1000_phy.c
index a018000f7db9..3c1b562a3271 100644
--- a/drivers/net/ethernet/intel/igb/e1000_phy.c
+++ b/drivers/net/ethernet/intel/igb/e1000_phy.c
@@ -1,9 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright(c) 2007 - 2018 Intel Corporation. */
 
-#include <linux/if_ether.h>
+#include <linux/bitfield.h>
 #include <linux/delay.h>
-
+#include <linux/if_ether.h>
 #include "e1000_mac.h"
 #include "e1000_phy.h"
 
diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c
index fd712585af27..e6c1fbee049e 100644
--- a/drivers/net/ethernet/intel/igbvf/netdev.c
+++ b/drivers/net/ethernet/intel/igbvf/netdev.c
@@ -3,25 +3,25 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <linux/module.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/pci.h>
-#include <linux/vmalloc.h>
-#include <linux/pagemap.h>
+#include <linux/bitfield.h>
 #include <linux/delay.h>
-#include <linux/netdevice.h>
-#include <linux/tcp.h>
-#include <linux/ipv6.h>
-#include <linux/slab.h>
-#include <net/checksum.h>
-#include <net/ip6_checksum.h>
-#include <linux/mii.h>
 #include <linux/ethtool.h>
 #include <linux/if_vlan.h>
+#include <linux/init.h>
+#include <linux/ipv6.h>
+#include <linux/mii.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/pagemap.h>
+#include <linux/pci.h>
 #include <linux/prefetch.h>
 #include <linux/sctp.h>
-
+#include <linux/slab.h>
+#include <linux/tcp.h>
+#include <linux/types.h>
+#include <linux/vmalloc.h>
+#include <net/checksum.h>
+#include <net/ip6_checksum.h>
 #include "igbvf.h"
 
 char igbvf_driver_name[] = "igbvf";
diff --git a/drivers/net/ethernet/intel/igc/igc_i225.c b/drivers/net/ethernet/intel/igc/igc_i225.c
index 17546a035ab1..d2562c8e8015 100644
--- a/drivers/net/ethernet/intel/igc/igc_i225.c
+++ b/drivers/net/ethernet/intel/igc/igc_i225.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c)  2018 Intel Corporation */
 
+#include <linux/bitfield.h>
 #include <linux/delay.h>
 
 #include "igc_hw.h"
diff --git a/drivers/net/ethernet/intel/igc/igc_phy.c b/drivers/net/ethernet/intel/igc/igc_phy.c
index 53b77c969c85..d0d9e7170154 100644
--- a/drivers/net/ethernet/intel/igc/igc_phy.c
+++ b/drivers/net/ethernet/intel/igc/igc_phy.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c)  2018 Intel Corporation */
 
+#include <linux/bitfield.h>
 #include "igc_phy.h"
 
 /**
diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h
index a44d9dc7e3eb..8e177b67e82f 100644
--- a/include/linux/avf/virtchnl.h
+++ b/include/linux/avf/virtchnl.h
@@ -5,6 +5,7 @@
 #define _VIRTCHNL_H_
 
 #include <linux/bitops.h>
+#include <linux/bits.h>
 #include <linux/overflow.h>
 #include <uapi/linux/if_ether.h>
 
-- 
cgit v1.2.3


From 56778b49c9a2cbc32c6b0fbd3ba1a9d64192d3af Mon Sep 17 00:00:00 2001
From: David Gow <davidgow@google.com>
Date: Tue, 28 Nov 2023 15:24:05 +0800
Subject: kunit: Add a macro to wrap a deferred action function

KUnit's deferred action API accepts a void(*)(void *) function pointer
which is called when the test is exited. However, we very frequently
want to use existing functions which accept a single pointer, but which
may not be of type void*. While this is probably dodgy enough to be on
the wrong side of the C standard, it's been often used for similar
callbacks, and gcc's -Wcast-function-type seems to ignore cases where
the only difference is the type of the argument, assuming it's
compatible (i.e., they're both pointers to data).

However, clang 16 has introduced -Wcast-function-type-strict, which no
longer permits any deviation in function pointer type. This seems to be
because it'd break CFI, which validates the type of function calls.

This rather ruins our attempts to cast functions to defer them, and
leaves us with a few options. The one we've chosen is to implement a
macro which will generate a wrapper function which accepts a void*, and
casts the argument to the appropriate type.

For example, if you were trying to wrap:
void foo_close(struct foo *handle);
you could use:
KUNIT_DEFINE_ACTION_WRAPPER(kunit_action_foo_close,
			    foo_close,
			    struct foo *);

This would create a new kunit_action_foo_close() function, of type
kunit_action_t, which could be passed into kunit_add_action() and
similar functions.

In addition to defining this macro, update KUnit and its tests to use
it.

Link: https://github.com/ClangBuiltLinux/linux/issues/1750
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Tested-by: Nathan Chancellor <nathan@kernel.org>
Acked-by: Daniel Vetter <daniel@ffwll.ch>
Reviewed-by: Maxime Ripard <mripard@kernel.org>
Signed-off-by: David Gow <davidgow@google.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 Documentation/dev-tools/kunit/usage.rst | 10 +++++++---
 include/kunit/resource.h                | 21 +++++++++++++++++++++
 lib/kunit/kunit-test.c                  |  5 +----
 lib/kunit/test.c                        |  6 ++++--
 4 files changed, 33 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/Documentation/dev-tools/kunit/usage.rst b/Documentation/dev-tools/kunit/usage.rst
index c27e1646ecd9..9db12e91668e 100644
--- a/Documentation/dev-tools/kunit/usage.rst
+++ b/Documentation/dev-tools/kunit/usage.rst
@@ -651,12 +651,16 @@ For example:
 	}
 
 Note that, for functions like device_unregister which only accept a single
-pointer-sized argument, it's possible to directly cast that function to
-a ``kunit_action_t`` rather than writing a wrapper function, for example:
+pointer-sized argument, it's possible to automatically generate a wrapper
+with the ``KUNIT_DEFINE_ACTION_WRAPPER()`` macro, for example:
 
 .. code-block:: C
 
-	kunit_add_action(test, (kunit_action_t *)&device_unregister, &dev);
+	KUNIT_DEFINE_ACTION_WRAPPER(device_unregister, device_unregister_wrapper, struct device *);
+	kunit_add_action(test, &device_unregister_wrapper, &dev);
+
+You should do this in preference to manually casting to the ``kunit_action_t`` type,
+as casting function pointers will break Control Flow Integrity (CFI).
 
 ``kunit_add_action`` can fail if, for example, the system is out of memory.
 You can use ``kunit_add_action_or_reset`` instead which runs the action
diff --git a/include/kunit/resource.h b/include/kunit/resource.h
index c7383e90f5c9..4ad69a2642a5 100644
--- a/include/kunit/resource.h
+++ b/include/kunit/resource.h
@@ -390,6 +390,27 @@ void kunit_remove_resource(struct kunit *test, struct kunit_resource *res);
 /* A 'deferred action' function to be used with kunit_add_action. */
 typedef void (kunit_action_t)(void *);
 
+/**
+ * KUNIT_DEFINE_ACTION_WRAPPER() - Wrap a function for use as a deferred action.
+ *
+ * @wrapper: The name of the new wrapper function define.
+ * @orig: The original function to wrap.
+ * @arg_type: The type of the argument accepted by @orig.
+ *
+ * Defines a wrapper for a function which accepts a single, pointer-sized
+ * argument. This wrapper can then be passed to kunit_add_action() and
+ * similar. This should be used in preference to casting a function
+ * directly to kunit_action_t, as casting function pointers will break
+ * control flow integrity (CFI), leading to crashes.
+ */
+#define KUNIT_DEFINE_ACTION_WRAPPER(wrapper, orig, arg_type)	\
+	static void wrapper(void *in)				\
+	{							\
+		arg_type arg = (arg_type)in;			\
+		orig(arg);					\
+	}
+
+
 /**
  * kunit_add_action() - Call a function when the test ends.
  * @test: Test case to associate the action with.
diff --git a/lib/kunit/kunit-test.c b/lib/kunit/kunit-test.c
index de2113a58fa0..ee6927c60979 100644
--- a/lib/kunit/kunit-test.c
+++ b/lib/kunit/kunit-test.c
@@ -538,10 +538,7 @@ static struct kunit_suite kunit_resource_test_suite = {
 #if IS_BUILTIN(CONFIG_KUNIT_TEST)
 
 /* This avoids a cast warning if kfree() is passed direct to kunit_add_action(). */
-static void kfree_wrapper(void *p)
-{
-	kfree(p);
-}
+KUNIT_DEFINE_ACTION_WRAPPER(kfree_wrapper, kfree, const void *);
 
 static void kunit_log_test(struct kunit *test)
 {
diff --git a/lib/kunit/test.c b/lib/kunit/test.c
index 7aceb07a1af9..7deee3701d20 100644
--- a/lib/kunit/test.c
+++ b/lib/kunit/test.c
@@ -810,6 +810,8 @@ static struct notifier_block kunit_mod_nb = {
 };
 #endif
 
+KUNIT_DEFINE_ACTION_WRAPPER(kfree_action_wrapper, kfree, const void *)
+
 void *kunit_kmalloc_array(struct kunit *test, size_t n, size_t size, gfp_t gfp)
 {
 	void *data;
@@ -819,7 +821,7 @@ void *kunit_kmalloc_array(struct kunit *test, size_t n, size_t size, gfp_t gfp)
 	if (!data)
 		return NULL;
 
-	if (kunit_add_action_or_reset(test, (kunit_action_t *)kfree, data) != 0)
+	if (kunit_add_action_or_reset(test, kfree_action_wrapper, data) != 0)
 		return NULL;
 
 	return data;
@@ -831,7 +833,7 @@ void kunit_kfree(struct kunit *test, const void *ptr)
 	if (!ptr)
 		return;
 
-	kunit_release_action(test, (kunit_action_t *)kfree, (void *)ptr);
+	kunit_release_action(test, kfree_action_wrapper, (void *)ptr);
 }
 EXPORT_SYMBOL_GPL(kunit_kfree);
 
-- 
cgit v1.2.3


From 69dfdce1c5161a37a14720e5f6f62a36e387aa33 Mon Sep 17 00:00:00 2001
From: Rae Moar <rmoar@google.com>
Date: Wed, 13 Dec 2023 19:44:16 +0000
Subject: kunit: move KUNIT_TABLE out of INIT_DATA

Alter the linker section of KUNIT_TABLE to move it out of INIT_DATA and
into DATA_DATA.

Data for KUnit tests does not need to be in the init section.

In order to run tests again after boot the KUnit data cannot be labeled as
init data as the kernel could write over it.

Add a KUNIT_INIT_TABLE in the next patch for KUnit tests that test init
data/functions.

Reviewed-by: David Gow <davidgow@google.com>
Signed-off-by: Rae Moar <rmoar@google.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 include/asm-generic/vmlinux.lds.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index bae0fe4d499b..1107905d37fc 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -370,7 +370,8 @@
 	BRANCH_PROFILE()						\
 	TRACE_PRINTKS()							\
 	BPF_RAW_TP()							\
-	TRACEPOINT_STR()
+	TRACEPOINT_STR()						\
+	KUNIT_TABLE()
 
 /*
  * Data section helpers
@@ -699,8 +700,7 @@
 	THERMAL_TABLE(governor)						\
 	EARLYCON_TABLE()						\
 	LSM_TABLE()							\
-	EARLY_LSM_TABLE()						\
-	KUNIT_TABLE()
+	EARLY_LSM_TABLE()
 
 #define INIT_TEXT							\
 	*(.init.text .init.text.*)					\
-- 
cgit v1.2.3


From d81f0d7b8b23ec79f80be602ed6129ded27862e8 Mon Sep 17 00:00:00 2001
From: Rae Moar <rmoar@google.com>
Date: Wed, 13 Dec 2023 19:44:17 +0000
Subject: kunit: add KUNIT_INIT_TABLE to init linker section

Add KUNIT_INIT_TABLE to the INIT_DATA linker section.

Alter the KUnit macros to create init tests:
kunit_test_init_section_suites

Update lib/kunit/executor.c to run both the suites in KUNIT_TABLE and
KUNIT_INIT_TABLE.

Reviewed-by: David Gow <davidgow@google.com>
Signed-off-by: Rae Moar <rmoar@google.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 include/asm-generic/vmlinux.lds.h |  9 +++++-
 include/kunit/test.h              | 30 +++++++++++-------
 include/linux/module.h            |  2 ++
 kernel/module/main.c              |  3 ++
 lib/kunit/executor.c              | 64 +++++++++++++++++++++++++++++++++++----
 lib/kunit/test.c                  | 26 +++++++++++-----
 6 files changed, 109 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 1107905d37fc..5dd3a61d673d 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -700,7 +700,8 @@
 	THERMAL_TABLE(governor)						\
 	EARLYCON_TABLE()						\
 	LSM_TABLE()							\
-	EARLY_LSM_TABLE()
+	EARLY_LSM_TABLE()						\
+	KUNIT_INIT_TABLE()
 
 #define INIT_TEXT							\
 	*(.init.text .init.text.*)					\
@@ -926,6 +927,12 @@
 		. = ALIGN(8);						\
 		BOUNDED_SECTION_POST_LABEL(.kunit_test_suites, __kunit_suites, _start, _end)
 
+/* Alignment must be consistent with (kunit_suite *) in include/kunit/test.h */
+#define KUNIT_INIT_TABLE()						\
+		. = ALIGN(8);						\
+		BOUNDED_SECTION_POST_LABEL(.kunit_init_test_suites, \
+				__kunit_init_suites, _start, _end)
+
 #ifdef CONFIG_BLK_DEV_INITRD
 #define INIT_RAM_FS							\
 	. = ALIGN(4);							\
diff --git a/include/kunit/test.h b/include/kunit/test.h
index 20ed9f9275c9..fe79cd736e94 100644
--- a/include/kunit/test.h
+++ b/include/kunit/test.h
@@ -337,6 +337,9 @@ void __kunit_test_suites_exit(struct kunit_suite **suites, int num_suites);
 void kunit_exec_run_tests(struct kunit_suite_set *suite_set, bool builtin);
 void kunit_exec_list_tests(struct kunit_suite_set *suite_set, bool include_attr);
 
+struct kunit_suite_set kunit_merge_suite_sets(struct kunit_suite_set init_suite_set,
+		struct kunit_suite_set suite_set);
+
 #if IS_BUILTIN(CONFIG_KUNIT)
 int kunit_run_all_tests(void);
 #else
@@ -371,6 +374,11 @@ static inline int kunit_run_all_tests(void)
 
 #define kunit_test_suite(suite)	kunit_test_suites(&suite)
 
+#define __kunit_init_test_suites(unique_array, ...)			       \
+	static struct kunit_suite *unique_array[]			       \
+	__aligned(sizeof(struct kunit_suite *))				       \
+	__used __section(".kunit_init_test_suites") = { __VA_ARGS__ }
+
 /**
  * kunit_test_init_section_suites() - used to register one or more &struct
  *				      kunit_suite containing init functions or
@@ -378,21 +386,21 @@ static inline int kunit_run_all_tests(void)
  *
  * @__suites: a statically allocated list of &struct kunit_suite.
  *
- * This functions identically as kunit_test_suites() except that it suppresses
- * modpost warnings for referencing functions marked __init or data marked
- * __initdata; this is OK because currently KUnit only runs tests upon boot
- * during the init phase or upon loading a module during the init phase.
+ * This functions similar to kunit_test_suites() except that it compiles the
+ * list of suites during init phase.
+ *
+ * This macro also suffixes the array and suite declarations it makes with
+ * _probe; so that modpost suppresses warnings about referencing init data
+ * for symbols named in this manner.
  *
- * NOTE TO KUNIT DEVS: If we ever allow KUnit tests to be run after boot, these
- * tests must be excluded.
+ * Note: these init tests are not able to be run after boot so there is no
+ * "run" debugfs file generated for these tests.
  *
- * The only thing this macro does that's different from kunit_test_suites is
- * that it suffixes the array and suite declarations it makes with _probe;
- * modpost suppresses warnings about referencing init data for symbols named in
- * this manner.
+ * Also, do not mark the suite or test case structs with __initdata because
+ * they will be used after the init phase with debugfs.
  */
 #define kunit_test_init_section_suites(__suites...)			\
-	__kunit_test_suites(CONCATENATE(__UNIQUE_ID(array), _probe),	\
+	__kunit_init_test_suites(CONCATENATE(__UNIQUE_ID(array), _probe), \
 			    ##__suites)
 
 #define kunit_test_init_section_suite(suite)	\
diff --git a/include/linux/module.h b/include/linux/module.h
index a98e188cf37b..9cd0009bd050 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -540,6 +540,8 @@ struct module {
 	struct static_call_site *static_call_sites;
 #endif
 #if IS_ENABLED(CONFIG_KUNIT)
+	int num_kunit_init_suites;
+	struct kunit_suite **kunit_init_suites;
 	int num_kunit_suites;
 	struct kunit_suite **kunit_suites;
 #endif
diff --git a/kernel/module/main.c b/kernel/module/main.c
index 98fedfdb8db5..36681911c05a 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -2199,6 +2199,9 @@ static int find_module_sections(struct module *mod, struct load_info *info)
 	mod->kunit_suites = section_objs(info, ".kunit_test_suites",
 					      sizeof(*mod->kunit_suites),
 					      &mod->num_kunit_suites);
+	mod->kunit_init_suites = section_objs(info, ".kunit_init_test_suites",
+					      sizeof(*mod->kunit_init_suites),
+					      &mod->num_kunit_init_suites);
 #endif
 
 	mod->extable = section_objs(info, "__ex_table",
diff --git a/lib/kunit/executor.c b/lib/kunit/executor.c
index 1236b3cd2fbb..847329c51e91 100644
--- a/lib/kunit/executor.c
+++ b/lib/kunit/executor.c
@@ -12,6 +12,8 @@
  */
 extern struct kunit_suite * const __kunit_suites_start[];
 extern struct kunit_suite * const __kunit_suites_end[];
+extern struct kunit_suite * const __kunit_init_suites_start[];
+extern struct kunit_suite * const __kunit_init_suites_end[];
 
 static char *action_param;
 
@@ -292,6 +294,33 @@ void kunit_exec_list_tests(struct kunit_suite_set *suite_set, bool include_attr)
 	}
 }
 
+struct kunit_suite_set kunit_merge_suite_sets(struct kunit_suite_set init_suite_set,
+		struct kunit_suite_set suite_set)
+{
+	struct kunit_suite_set total_suite_set = {NULL, NULL};
+	struct kunit_suite **total_suite_start = NULL;
+	size_t init_num_suites, num_suites, suite_size;
+
+	init_num_suites = init_suite_set.end - init_suite_set.start;
+	num_suites = suite_set.end - suite_set.start;
+	suite_size = sizeof(suite_set.start);
+
+	/* Allocate memory for array of all kunit suites */
+	total_suite_start = kmalloc_array(init_num_suites + num_suites, suite_size, GFP_KERNEL);
+	if (!total_suite_start)
+		return total_suite_set;
+
+	/* Append init suites and then all other kunit suites */
+	memcpy(total_suite_start, init_suite_set.start, init_num_suites * suite_size);
+	memcpy(total_suite_start + init_num_suites, suite_set.start, num_suites * suite_size);
+
+	/* Set kunit suite set start and end */
+	total_suite_set.start = total_suite_start;
+	total_suite_set.end = total_suite_start + (init_num_suites + num_suites);
+
+	return total_suite_set;
+}
+
 #if IS_BUILTIN(CONFIG_KUNIT)
 
 static char *kunit_shutdown;
@@ -313,21 +342,41 @@ static void kunit_handle_shutdown(void)
 
 int kunit_run_all_tests(void)
 {
-	struct kunit_suite_set suite_set = {
+	struct kunit_suite_set suite_set = {NULL, NULL};
+	struct kunit_suite_set filtered_suite_set = {NULL, NULL};
+	struct kunit_suite_set init_suite_set = {
+		__kunit_init_suites_start, __kunit_init_suites_end,
+	};
+	struct kunit_suite_set normal_suite_set = {
 		__kunit_suites_start, __kunit_suites_end,
 	};
+	size_t init_num_suites = init_suite_set.end - init_suite_set.start;
 	int err = 0;
+
+	if (init_num_suites > 0) {
+		suite_set = kunit_merge_suite_sets(init_suite_set, normal_suite_set);
+		if (!suite_set.start)
+			goto out;
+	} else
+		suite_set = normal_suite_set;
+
 	if (!kunit_enabled()) {
 		pr_info("kunit: disabled\n");
-		goto out;
+		goto free_out;
 	}
 
 	if (filter_glob_param || filter_param) {
-		suite_set = kunit_filter_suites(&suite_set, filter_glob_param,
+		filtered_suite_set = kunit_filter_suites(&suite_set, filter_glob_param,
 				filter_param, filter_action_param, &err);
+
+		/* Free original suite set before using filtered suite set */
+		if (init_num_suites > 0)
+			kfree(suite_set.start);
+		suite_set = filtered_suite_set;
+
 		if (err) {
 			pr_err("kunit executor: error filtering suites: %d\n", err);
-			goto out;
+			goto free_out;
 		}
 	}
 
@@ -340,9 +389,12 @@ int kunit_run_all_tests(void)
 	else
 		pr_err("kunit executor: unknown action '%s'\n", action_param);
 
-	if (filter_glob_param || filter_param) { /* a copy was made of each suite */
+free_out:
+	if (filter_glob_param || filter_param)
 		kunit_free_suite_set(suite_set);
-	}
+	else if (init_num_suites > 0)
+		/* Don't use kunit_free_suite_set because suites aren't individually allocated */
+		kfree(suite_set.start);
 
 out:
 	kunit_handle_shutdown();
diff --git a/lib/kunit/test.c b/lib/kunit/test.c
index 7deee3701d20..6b60d85ce108 100644
--- a/lib/kunit/test.c
+++ b/lib/kunit/test.c
@@ -742,28 +742,40 @@ EXPORT_SYMBOL_GPL(__kunit_test_suites_exit);
 #ifdef CONFIG_MODULES
 static void kunit_module_init(struct module *mod)
 {
-	struct kunit_suite_set suite_set = {
+	struct kunit_suite_set suite_set, filtered_set;
+	struct kunit_suite_set normal_suite_set = {
 		mod->kunit_suites, mod->kunit_suites + mod->num_kunit_suites,
 	};
+	struct kunit_suite_set init_suite_set = {
+		mod->kunit_init_suites, mod->kunit_init_suites + mod->num_kunit_init_suites,
+	};
 	const char *action = kunit_action();
 	int err = 0;
 
-	suite_set = kunit_filter_suites(&suite_set,
+	if (mod->num_kunit_init_suites > 0)
+		suite_set = kunit_merge_suite_sets(init_suite_set, normal_suite_set);
+	else
+		suite_set = normal_suite_set;
+
+	filtered_set = kunit_filter_suites(&suite_set,
 					kunit_filter_glob() ?: "*.*",
 					kunit_filter(), kunit_filter_action(),
 					&err);
 	if (err)
 		pr_err("kunit module: error filtering suites: %d\n", err);
 
-	mod->kunit_suites = (struct kunit_suite **)suite_set.start;
-	mod->num_kunit_suites = suite_set.end - suite_set.start;
+	mod->kunit_suites = (struct kunit_suite **)filtered_set.start;
+	mod->num_kunit_suites = filtered_set.end - filtered_set.start;
+
+	if (mod->num_kunit_init_suites > 0)
+		kfree(suite_set.start);
 
 	if (!action)
-		kunit_exec_run_tests(&suite_set, false);
+		kunit_exec_run_tests(&filtered_set, false);
 	else if (!strcmp(action, "list"))
-		kunit_exec_list_tests(&suite_set, false);
+		kunit_exec_list_tests(&filtered_set, false);
 	else if (!strcmp(action, "list_attr"))
-		kunit_exec_list_tests(&suite_set, true);
+		kunit_exec_list_tests(&filtered_set, true);
 	else
 		pr_err("kunit: unknown action '%s'\n", action);
 }
-- 
cgit v1.2.3


From 6c4ea2f48de9860217ddfedee081d485dbeea7e8 Mon Sep 17 00:00:00 2001
From: Rae Moar <rmoar@google.com>
Date: Wed, 13 Dec 2023 19:44:19 +0000
Subject: kunit: add is_init test attribute

Add is_init test attribute of type bool. Add to_string, get, and filter
methods to lib/kunit/attributes.c.

Mark each of the tests in the init section with the is_init=true attribute.

Add is_init to the attributes documentation.

Reviewed-by: David Gow <davidgow@google.com>
Signed-off-by: Rae Moar <rmoar@google.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 Documentation/dev-tools/kunit/running_tips.rst |  7 +++
 include/kunit/test.h                           |  1 +
 lib/kunit/attributes.c                         | 60 ++++++++++++++++++++++++++
 lib/kunit/executor.c                           |  6 ++-
 4 files changed, 73 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/Documentation/dev-tools/kunit/running_tips.rst b/Documentation/dev-tools/kunit/running_tips.rst
index 766f9cdea0fa..024e9ad1d1e9 100644
--- a/Documentation/dev-tools/kunit/running_tips.rst
+++ b/Documentation/dev-tools/kunit/running_tips.rst
@@ -428,3 +428,10 @@ This attribute indicates the name of the module associated with the test.
 
 This attribute is automatically saved as a string and is printed for each suite.
 Tests can also be filtered using this attribute.
+
+``is_init``
+
+This attribute indicates whether the test uses init data or functions.
+
+This attribute is automatically saved as a boolean and tests can also be
+filtered using this attribute.
diff --git a/include/kunit/test.h b/include/kunit/test.h
index fe79cd736e94..b163b9984b33 100644
--- a/include/kunit/test.h
+++ b/include/kunit/test.h
@@ -253,6 +253,7 @@ struct kunit_suite {
 	struct dentry *debugfs;
 	struct string_stream *log;
 	int suite_init_err;
+	bool is_init;
 };
 
 /* Stores an array of suites, end points one past the end */
diff --git a/lib/kunit/attributes.c b/lib/kunit/attributes.c
index 1b512f7e1838..2cf04cc09372 100644
--- a/lib/kunit/attributes.c
+++ b/lib/kunit/attributes.c
@@ -58,6 +58,16 @@ static const char *attr_enum_to_string(void *attr, const char * const str_list[]
 	return str_list[val];
 }
 
+static const char *attr_bool_to_string(void *attr, bool *to_free)
+{
+	bool val = (bool)attr;
+
+	*to_free = false;
+	if (val)
+		return "true";
+	return "false";
+}
+
 static const char *attr_speed_to_string(void *attr, bool *to_free)
 {
 	return attr_enum_to_string(attr, speed_str_list, to_free);
@@ -166,6 +176,37 @@ static int attr_string_filter(void *attr, const char *input, int *err)
 	return false;
 }
 
+static int attr_bool_filter(void *attr, const char *input, int *err)
+{
+	int i, input_int = -1;
+	long val = (long)attr;
+	const char *input_str = NULL;
+
+	for (i = 0; input[i]; i++) {
+		if (!strchr(op_list, input[i])) {
+			input_str = input + i;
+			break;
+		}
+	}
+
+	if (!input_str) {
+		*err = -EINVAL;
+		pr_err("kunit executor: filter value not found: %s\n", input);
+		return false;
+	}
+
+	if (!strcmp(input_str, "true"))
+		input_int = (int)true;
+	else if (!strcmp(input_str, "false"))
+		input_int = (int)false;
+	else {
+		*err = -EINVAL;
+		pr_err("kunit executor: invalid filter input: %s\n", input);
+		return false;
+	}
+
+	return int_filter(val, input, input_int, err);
+}
 
 /* Get Attribute Methods */
 
@@ -194,6 +235,17 @@ static void *attr_module_get(void *test_or_suite, bool is_test)
 		return (void *) "";
 }
 
+static void *attr_is_init_get(void *test_or_suite, bool is_test)
+{
+	struct kunit_suite *suite = is_test ? NULL : test_or_suite;
+	struct kunit_case *test = is_test ? test_or_suite : NULL;
+
+	if (test)
+		return ((void *) NULL);
+	else
+		return ((void *) suite->is_init);
+}
+
 /* List of all Test Attributes */
 
 static struct kunit_attr kunit_attr_list[] = {
@@ -212,6 +264,14 @@ static struct kunit_attr kunit_attr_list[] = {
 		.filter = attr_string_filter,
 		.attr_default = (void *)"",
 		.print = PRINT_SUITE,
+	},
+	{
+		.name = "is_init",
+		.get_attr = attr_is_init_get,
+		.to_string = attr_bool_to_string,
+		.filter = attr_bool_filter,
+		.attr_default = (void *)false,
+		.print = PRINT_SUITE,
 	}
 };
 
diff --git a/lib/kunit/executor.c b/lib/kunit/executor.c
index 847329c51e91..717b9599036b 100644
--- a/lib/kunit/executor.c
+++ b/lib/kunit/executor.c
@@ -300,6 +300,7 @@ struct kunit_suite_set kunit_merge_suite_sets(struct kunit_suite_set init_suite_
 	struct kunit_suite_set total_suite_set = {NULL, NULL};
 	struct kunit_suite **total_suite_start = NULL;
 	size_t init_num_suites, num_suites, suite_size;
+	int i = 0;
 
 	init_num_suites = init_suite_set.end - init_suite_set.start;
 	num_suites = suite_set.end - suite_set.start;
@@ -310,8 +311,11 @@ struct kunit_suite_set kunit_merge_suite_sets(struct kunit_suite_set init_suite_
 	if (!total_suite_start)
 		return total_suite_set;
 
-	/* Append init suites and then all other kunit suites */
+	/* Append and mark init suites and then append all other kunit suites */
 	memcpy(total_suite_start, init_suite_set.start, init_num_suites * suite_size);
+	for (i = 0; i < init_num_suites; i++)
+		total_suite_start[i]->is_init = true;
+
 	memcpy(total_suite_start + init_num_suites, suite_set.start, num_suites * suite_size);
 
 	/* Set kunit suite set start and end */
-- 
cgit v1.2.3


From d03c720e03bd9bf0b784d80b5d3ede7e2daf3b6e Mon Sep 17 00:00:00 2001
From: "davidgow@google.com" <davidgow@google.com>
Date: Fri, 15 Dec 2023 15:39:08 +0800
Subject: kunit: Add APIs for managing devices

Tests for drivers often require a struct device to pass to other
functions. While it's possible to create these with
root_device_register(), or to use something like a platform device, this
is both a misuse of those APIs, and can be difficult to clean up after,
for example, a failed assertion.

Add some KUnit-specific functions for registering and unregistering a
struct device:
- kunit_device_register()
- kunit_device_register_with_driver()
- kunit_device_unregister()

These helpers allocate a on a 'kunit' bus which will either probe the
driver passed in (kunit_device_register_with_driver), or will create a
stub driver (kunit_device_register) which is cleaned up on test shutdown.

Devices are automatically unregistered on test shutdown, but can be
manually unregistered earlier with kunit_device_unregister() in order
to, for example, test device release code.

Reviewed-by: Matti Vaittinen <mazziesaccount@gmail.com>
Reviewed-by: Maxime Ripard <mripard@kernel.org>
Signed-off-by: David Gow <davidgow@google.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 Documentation/dev-tools/kunit/api/resource.rst |   9 ++
 Documentation/dev-tools/kunit/usage.rst        |  50 +++++++
 include/kunit/device.h                         |  80 +++++++++++
 lib/kunit/Makefile                             |   3 +-
 lib/kunit/device-impl.h                        |  17 +++
 lib/kunit/device.c                             | 181 +++++++++++++++++++++++++
 lib/kunit/kunit-test.c                         | 134 +++++++++++++++++-
 lib/kunit/test.c                               |   3 +
 8 files changed, 475 insertions(+), 2 deletions(-)
 create mode 100644 include/kunit/device.h
 create mode 100644 lib/kunit/device-impl.h
 create mode 100644 lib/kunit/device.c

(limited to 'include')

diff --git a/Documentation/dev-tools/kunit/api/resource.rst b/Documentation/dev-tools/kunit/api/resource.rst
index 0a94f831259e..ec6002a6b0db 100644
--- a/Documentation/dev-tools/kunit/api/resource.rst
+++ b/Documentation/dev-tools/kunit/api/resource.rst
@@ -11,3 +11,12 @@ state on a per-test basis, register custom cleanup actions, and more.
 
 .. kernel-doc:: include/kunit/resource.h
    :internal:
+
+Managed Devices
+---------------
+
+Functions for using KUnit-managed struct device and struct device_driver.
+Include ``kunit/device.h`` to use these.
+
+.. kernel-doc:: include/kunit/device.h
+   :internal:
diff --git a/Documentation/dev-tools/kunit/usage.rst b/Documentation/dev-tools/kunit/usage.rst
index 9db12e91668e..53c6f7dc8a42 100644
--- a/Documentation/dev-tools/kunit/usage.rst
+++ b/Documentation/dev-tools/kunit/usage.rst
@@ -797,3 +797,53 @@ structures as shown below:
 KUnit is not enabled, or if no test is running in the current task, it will do
 nothing. This compiles down to either a no-op or a static key check, so will
 have a negligible performance impact when no test is running.
+
+Managing Fake Devices and Drivers
+---------------------------------
+
+When testing drivers or code which interacts with drivers, many functions will
+require a ``struct device`` or ``struct device_driver``. In many cases, setting
+up a real device is not required to test any given function, so a fake device
+can be used instead.
+
+KUnit provides helper functions to create and manage these fake devices, which
+are internally of type ``struct kunit_device``, and are attached to a special
+``kunit_bus``. These devices support managed device resources (devres), as
+described in Documentation/driver-api/driver-model/devres.rst
+
+To create a KUnit-managed ``struct device_driver``, use ``kunit_driver_create()``,
+which will create a driver with the given name, on the ``kunit_bus``. This driver
+will automatically be destroyed when the corresponding test finishes, but can also
+be manually destroyed with ``driver_unregister()``.
+
+To create a fake device, use the ``kunit_device_register()``, which will create
+and register a device, using a new KUnit-managed driver created with ``kunit_driver_create()``.
+To provide a specific, non-KUnit-managed driver, use ``kunit_device_register_with_driver()``
+instead. Like with managed drivers, KUnit-managed fake devices are automatically
+cleaned up when the test finishes, but can be manually cleaned up early with
+``kunit_device_unregister()``.
+
+The KUnit devices should be used in preference to ``root_device_register()``, and
+instead of ``platform_device_register()`` in cases where the device is not otherwise
+a platform device.
+
+For example:
+
+.. code-block:: c
+
+	#include <kunit/device.h>
+
+	static void test_my_device(struct kunit *test)
+	{
+		struct device *fake_device;
+		const char *dev_managed_string;
+
+		// Create a fake device.
+		fake_device = kunit_device_register(test, "my_device");
+		KUNIT_ASSERT_NOT_ERR_OR_NULL(test, fake_device)
+
+		// Pass it to functions which need a device.
+		dev_managed_string = devm_kstrdup(fake_device, "Hello, World!");
+
+		// Everything is cleaned up automatically when the test ends.
+	}
\ No newline at end of file
diff --git a/include/kunit/device.h b/include/kunit/device.h
new file mode 100644
index 000000000000..2450110ad64e
--- /dev/null
+++ b/include/kunit/device.h
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * KUnit basic device implementation
+ *
+ * Helpers for creating and managing fake devices for KUnit tests.
+ *
+ * Copyright (C) 2023, Google LLC.
+ * Author: David Gow <davidgow@google.com>
+ */
+
+#ifndef _KUNIT_DEVICE_H
+#define _KUNIT_DEVICE_H
+
+#if IS_ENABLED(CONFIG_KUNIT)
+
+#include <kunit/test.h>
+
+struct device;
+struct device_driver;
+
+/**
+ * kunit_driver_create() - Create a struct device_driver attached to the kunit_bus
+ * @test: The test context object.
+ * @name: The name to give the created driver.
+ *
+ * Creates a struct device_driver attached to the kunit_bus, with the name @name.
+ * This driver will automatically be cleaned up on test exit.
+ *
+ * Return: a stub struct device_driver, managed by KUnit, with the name @name.
+ */
+struct device_driver *kunit_driver_create(struct kunit *test, const char *name);
+
+/**
+ * kunit_device_register() - Create a struct device for use in KUnit tests
+ * @test: The test context object.
+ * @name: The name to give the created device.
+ *
+ * Creates a struct kunit_device (which is a struct device) with the given name,
+ * and a corresponding driver. The device and driver will be cleaned up on test
+ * exit, or when kunit_device_unregister is called. See also
+ * kunit_device_register_with_driver, if you wish to provide your own
+ * struct device_driver.
+ *
+ * Return: a pointer to a struct device which will be cleaned up when the test
+ * exits, or an error pointer if the device could not be allocated or registered.
+ */
+struct device *kunit_device_register(struct kunit *test, const char *name);
+
+/**
+ * kunit_device_register_with_driver() - Create a struct device for use in KUnit tests
+ * @test: The test context object.
+ * @name: The name to give the created device.
+ * @drv: The struct device_driver to associate with the device.
+ *
+ * Creates a struct kunit_device (which is a struct device) with the given
+ * name, and driver. The device will be cleaned up on test exit, or when
+ * kunit_device_unregister is called. See also kunit_device_register, if you
+ * wish KUnit to create and manage a driver for you.
+ *
+ * Return: a pointer to a struct device which will be cleaned up when the test
+ * exits, or an error pointer if the device could not be allocated or registered.
+ */
+struct device *kunit_device_register_with_driver(struct kunit *test,
+						 const char *name,
+						 const struct device_driver *drv);
+
+/**
+ * kunit_device_unregister() - Unregister a KUnit-managed device
+ * @test: The test context object which created the device
+ * @dev: The device.
+ *
+ * Unregisters and destroys a struct device which was created with
+ * kunit_device_register or kunit_device_register_with_driver. If KUnit created
+ * a driver, cleans it up as well.
+ */
+void kunit_device_unregister(struct kunit *test, struct device *dev);
+
+#endif
+
+#endif
diff --git a/lib/kunit/Makefile b/lib/kunit/Makefile
index 46f75f23dfe4..309659a32a78 100644
--- a/lib/kunit/Makefile
+++ b/lib/kunit/Makefile
@@ -7,7 +7,8 @@ kunit-objs +=				test.o \
 					assert.o \
 					try-catch.o \
 					executor.o \
-					attributes.o
+					attributes.o \
+					device.o
 
 ifeq ($(CONFIG_KUNIT_DEBUGFS),y)
 kunit-objs +=				debugfs.o
diff --git a/lib/kunit/device-impl.h b/lib/kunit/device-impl.h
new file mode 100644
index 000000000000..54bd55836405
--- /dev/null
+++ b/lib/kunit/device-impl.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * KUnit internal header for device helpers
+ *
+ * Header for KUnit-internal driver / bus management.
+ *
+ * Copyright (C) 2023, Google LLC.
+ * Author: David Gow <davidgow@google.com>
+ */
+
+#ifndef _KUNIT_DEVICE_IMPL_H
+#define _KUNIT_DEVICE_IMPL_H
+
+// For internal use only -- registers the kunit_bus.
+int kunit_bus_init(void);
+
+#endif //_KUNIT_DEVICE_IMPL_H
diff --git a/lib/kunit/device.c b/lib/kunit/device.c
new file mode 100644
index 000000000000..1db4305b615a
--- /dev/null
+++ b/lib/kunit/device.c
@@ -0,0 +1,181 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KUnit-managed device implementation
+ *
+ * Implementation of struct kunit_device helpers for fake devices whose
+ * lifecycle is managed by KUnit.
+ *
+ * Copyright (C) 2023, Google LLC.
+ * Author: David Gow <davidgow@google.com>
+ */
+
+#include <linux/device.h>
+
+#include <kunit/test.h>
+#include <kunit/device.h>
+#include <kunit/resource.h>
+
+#include "device-impl.h"
+
+/* Wrappers for use with kunit_add_action() */
+KUNIT_DEFINE_ACTION_WRAPPER(device_unregister_wrapper, device_unregister, struct device *);
+KUNIT_DEFINE_ACTION_WRAPPER(driver_unregister_wrapper, driver_unregister, struct device_driver *);
+
+/* The root device for the KUnit bus, parent of all kunit_devices. */
+static struct device *kunit_bus_device;
+
+/* A device owned by a KUnit test. */
+struct kunit_device {
+	struct device dev;
+	/* The KUnit test which owns this device. */
+	struct kunit *owner;
+	/* If the driver is managed by KUnit and unique to this device. */
+	const struct device_driver *driver;
+};
+
+#define to_kunit_device(d) container_of_const(d, struct kunit_device, dev)
+
+static struct bus_type kunit_bus_type = {
+	.name		= "kunit",
+};
+
+/* Register the 'kunit_bus' used for fake devices. */
+int kunit_bus_init(void)
+{
+	int error;
+
+	kunit_bus_device = root_device_register("kunit");
+	if (!kunit_bus_device)
+		return -ENOMEM;
+
+	error = bus_register(&kunit_bus_type);
+	if (error)
+		bus_unregister(&kunit_bus_type);
+	return error;
+}
+
+/* Release a 'fake' KUnit device. */
+static void kunit_device_release(struct device *d)
+{
+	kfree(to_kunit_device(d));
+}
+
+/**
+ * Create and register a KUnit-managed struct device_driver on the kunit_bus.
+ * Returns an error pointer on failure.
+ */
+struct device_driver *kunit_driver_create(struct kunit *test, const char *name)
+{
+	struct device_driver *driver;
+	int err = -ENOMEM;
+
+	driver = kunit_kzalloc(test, sizeof(*driver), GFP_KERNEL);
+
+	if (!driver)
+		return ERR_PTR(err);
+
+	driver->name = name;
+	driver->bus = &kunit_bus_type;
+	driver->owner = THIS_MODULE;
+
+	err = driver_register(driver);
+	if (err) {
+		kunit_kfree(test, driver);
+		return ERR_PTR(err);
+	}
+
+	kunit_add_action(test, driver_unregister_wrapper, driver);
+	return driver;
+}
+EXPORT_SYMBOL_GPL(kunit_driver_create);
+
+/* Helper which creates a kunit_device, attaches it to the kunit_bus*/
+static struct kunit_device *kunit_device_register_internal(struct kunit *test,
+							   const char *name,
+							   const struct device_driver *drv)
+{
+	struct kunit_device *kunit_dev;
+	int err = -ENOMEM;
+
+	kunit_dev = kzalloc(sizeof(*kunit_dev), GFP_KERNEL);
+	if (!kunit_dev)
+		return ERR_PTR(err);
+
+	kunit_dev->owner = test;
+
+	err = dev_set_name(&kunit_dev->dev, "%s.%s", test->name, name);
+	if (err) {
+		kfree(kunit_dev);
+		return ERR_PTR(err);
+	}
+
+	kunit_dev->dev.release = kunit_device_release;
+	kunit_dev->dev.bus = &kunit_bus_type;
+	kunit_dev->dev.parent = kunit_bus_device;
+
+	err = device_register(&kunit_dev->dev);
+	if (err) {
+		put_device(&kunit_dev->dev);
+		return ERR_PTR(err);
+	}
+
+	kunit_add_action(test, device_unregister_wrapper, &kunit_dev->dev);
+
+	return kunit_dev;
+}
+
+/**
+ * Create and register a new KUnit-managed device, using the user-supplied device_driver.
+ * On failure, returns an error pointer.
+ */
+struct device *kunit_device_register_with_driver(struct kunit *test,
+						 const char *name,
+						 const struct device_driver *drv)
+{
+	struct kunit_device *kunit_dev = kunit_device_register_internal(test, name, drv);
+
+	if (IS_ERR_OR_NULL(kunit_dev))
+		return ERR_CAST(kunit_dev);
+
+	return &kunit_dev->dev;
+}
+EXPORT_SYMBOL_GPL(kunit_device_register_with_driver);
+
+/**
+ * Create and register a new KUnit-managed device, including a matching device_driver.
+ * On failure, returns an error pointer.
+ */
+struct device *kunit_device_register(struct kunit *test, const char *name)
+{
+	struct device_driver *drv;
+	struct kunit_device *dev;
+
+	drv = kunit_driver_create(test, name);
+	if (IS_ERR(drv))
+		return ERR_CAST(drv);
+
+	dev = kunit_device_register_internal(test, name, drv);
+	if (IS_ERR(dev)) {
+		kunit_release_action(test, driver_unregister_wrapper, (void *)drv);
+		return ERR_CAST(dev);
+	}
+
+	/* Request the driver be freed. */
+	dev->driver = drv;
+
+
+	return &dev->dev;
+}
+EXPORT_SYMBOL_GPL(kunit_device_register);
+
+/* Unregisters a KUnit-managed device early (including the driver, if automatically created). */
+void kunit_device_unregister(struct kunit *test, struct device *dev)
+{
+	const struct device_driver *driver = to_kunit_device(dev)->driver;
+
+	kunit_release_action(test, device_unregister_wrapper, dev);
+	if (driver)
+		kunit_release_action(test, driver_unregister_wrapper, (void *)driver);
+}
+EXPORT_SYMBOL_GPL(kunit_device_unregister);
+
diff --git a/lib/kunit/kunit-test.c b/lib/kunit/kunit-test.c
index ee6927c60979..c4259d910356 100644
--- a/lib/kunit/kunit-test.c
+++ b/lib/kunit/kunit-test.c
@@ -5,9 +5,13 @@
  * Copyright (C) 2019, Google LLC.
  * Author: Brendan Higgins <brendanhiggins@google.com>
  */
+#include "linux/gfp_types.h"
 #include <kunit/test.h>
 #include <kunit/test-bug.h>
 
+#include <linux/device.h>
+#include <kunit/device.h>
+
 #include "string-stream.h"
 #include "try-catch-impl.h"
 
@@ -687,6 +691,134 @@ static struct kunit_case kunit_current_test_cases[] = {
 	{}
 };
 
+static void test_dev_action(void *priv)
+{
+	*(void **)priv = (void *)1;
+}
+
+static void kunit_device_test(struct kunit *test)
+{
+	struct device *test_device;
+	long action_was_run = 0;
+
+	test_device = kunit_device_register(test, "my_device");
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, test_device);
+
+	// Add an action to verify cleanup.
+	devm_add_action(test_device, test_dev_action, &action_was_run);
+
+	KUNIT_EXPECT_EQ(test, action_was_run, 0);
+
+	kunit_device_unregister(test, test_device);
+
+	KUNIT_EXPECT_EQ(test, action_was_run, 1);
+}
+
+static void kunit_device_cleanup_test(struct kunit *test)
+{
+	struct device *test_device;
+	long action_was_run = 0;
+
+	test_device = kunit_device_register(test, "my_device");
+	KUNIT_ASSERT_NOT_NULL(test, test_device);
+
+	/* Add an action to verify cleanup. */
+	devm_add_action(test_device, test_dev_action, &action_was_run);
+
+	KUNIT_EXPECT_EQ(test, action_was_run, 0);
+
+	/* Force KUnit to run cleanup early. */
+	kunit_cleanup(test);
+
+	KUNIT_EXPECT_EQ(test, action_was_run, 1);
+}
+
+struct driver_test_state {
+	bool driver_device_probed;
+	bool driver_device_removed;
+	long action_was_run;
+};
+
+static int driver_probe_hook(struct device *dev)
+{
+	struct kunit *test = kunit_get_current_test();
+	struct driver_test_state *state = (struct driver_test_state *)test->priv;
+
+	state->driver_device_probed = true;
+	return 0;
+}
+
+static int driver_remove_hook(struct device *dev)
+{
+	struct kunit *test = kunit_get_current_test();
+	struct driver_test_state *state = (struct driver_test_state *)test->priv;
+
+	state->driver_device_removed = true;
+	return 0;
+}
+
+static void kunit_device_driver_test(struct kunit *test)
+{
+	struct device_driver *test_driver;
+	struct device *test_device;
+	struct driver_test_state *test_state = kunit_kzalloc(test, sizeof(*test_state), GFP_KERNEL);
+
+	test->priv = test_state;
+	test_driver = kunit_driver_create(test, "my_driver");
+
+	// This can fail with an error pointer.
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, test_driver);
+
+	test_driver->probe = driver_probe_hook;
+	test_driver->remove = driver_remove_hook;
+
+	test_device = kunit_device_register_with_driver(test, "my_device", test_driver);
+
+	// This can fail with an error pointer.
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, test_device);
+
+	// Make sure the probe function was called.
+	KUNIT_ASSERT_TRUE(test, test_state->driver_device_probed);
+
+	// Add an action to verify cleanup.
+	devm_add_action(test_device, test_dev_action, &test_state->action_was_run);
+
+	KUNIT_EXPECT_EQ(test, test_state->action_was_run, 0);
+
+	kunit_device_unregister(test, test_device);
+	test_device = NULL;
+
+	// Make sure the remove hook was called.
+	KUNIT_ASSERT_TRUE(test, test_state->driver_device_removed);
+
+	// We're going to test this again.
+	test_state->driver_device_probed = false;
+
+	// The driver should not automatically be destroyed by
+	// kunit_device_unregister, so we can re-use it.
+	test_device = kunit_device_register_with_driver(test, "my_device", test_driver);
+
+	// This can fail with an error pointer.
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, test_device);
+
+	// Probe was called again.
+	KUNIT_ASSERT_TRUE(test, test_state->driver_device_probed);
+
+	// Everything is automatically freed here.
+}
+
+static struct kunit_case kunit_device_test_cases[] = {
+	KUNIT_CASE(kunit_device_test),
+	KUNIT_CASE(kunit_device_cleanup_test),
+	KUNIT_CASE(kunit_device_driver_test),
+	{}
+};
+
+static struct kunit_suite kunit_device_test_suite = {
+	.name = "kunit_device",
+	.test_cases = kunit_device_test_cases,
+};
+
 static struct kunit_suite kunit_current_test_suite = {
 	.name = "kunit_current",
 	.test_cases = kunit_current_test_cases,
@@ -694,6 +826,6 @@ static struct kunit_suite kunit_current_test_suite = {
 
 kunit_test_suites(&kunit_try_catch_test_suite, &kunit_resource_test_suite,
 		  &kunit_log_test_suite, &kunit_status_test_suite,
-		  &kunit_current_test_suite);
+		  &kunit_current_test_suite, &kunit_device_test_suite);
 
 MODULE_LICENSE("GPL v2");
diff --git a/lib/kunit/test.c b/lib/kunit/test.c
index 088489856db8..14a77b2d702a 100644
--- a/lib/kunit/test.c
+++ b/lib/kunit/test.c
@@ -19,6 +19,7 @@
 #include <linux/sched.h>
 
 #include "debugfs.h"
+#include "device-impl.h"
 #include "hooks-impl.h"
 #include "string-stream.h"
 #include "try-catch-impl.h"
@@ -900,6 +901,8 @@ static int __init kunit_init(void)
 	kunit_install_hooks();
 
 	kunit_debugfs_init();
+
+	kunit_bus_init();
 #ifdef CONFIG_MODULES
 	return register_module_notifier(&kunit_mod_nb);
 #else
-- 
cgit v1.2.3


From 86362293044b382aece355f9e4e3f7116dcd1eae Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Sat, 22 Jul 2023 16:08:44 -0700
Subject: PCI: endpoint: Make struct pci_epf_ops in pci_epf_driver const
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The pci_epf_ops struct contains a set of callbacks that are used by the
pci_epf_driver, and is never modified by the EPF core itself.

Marking the struct pointer const allows EPF drivers to declare their
pci_epf_ops struct to be const.

This allows the struct to be placed in the read-only section. Which
for example brings some security benefits as the callbacks can not be
overwritten.

[kwilczynski: commit log]
Link: https://lore.kernel.org/linux-pci/20230722230848.589428-1-lars@metafoo.de
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Krzysztof Wilczyński <kwilczynski@kernel.org>
Reviewed-by: Manivannan Sadhasivam <mani@kernel.org>
---
 include/linux/pci-epf.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h
index 3f44b6aec477..764dc62b3acc 100644
--- a/include/linux/pci-epf.h
+++ b/include/linux/pci-epf.h
@@ -98,7 +98,7 @@ struct pci_epf_driver {
 	void	(*remove)(struct pci_epf *epf);
 
 	struct device_driver	driver;
-	struct pci_epf_ops	*ops;
+	const struct pci_epf_ops *ops;
 	struct module		*owner;
 	struct list_head	epf_group;
 	const struct pci_epf_device_id	*id_table;
-- 
cgit v1.2.3


From bdf5c0bb4dd9e7a8a4423643e6c73a7114bd58d8 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Thu, 14 Dec 2023 11:23:57 -0800
Subject: scsi: ufs: core: Rename ufshcd_auto_hibern8_enable() and make it
 static

Rename ufshcd_auto_hibern8_enable() into ufshcd_configure_auto_hibern8()
since this function can enable or disable auto-hibernation. Since
ufshcd_auto_hibern8_enable() is only used inside the UFSHCI driver core,
declare it static. Additionally, move the definition of this function to
just before its first caller.

Suggested-by: Bao D. Nguyen <quic_nguyenb@quicinc.com>
Reviewed-by: Bao D. Nguyen <quic_nguyenb@quicinc.com>
Reviewed-by: Can Guo <quic_cang@quicinc.com>
Cc: Avri Altman <avri.altman@wdc.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20231214192416.3638077-2-bvanassche@acm.org
Reviewed-by: Peter Wang <peter.wang@mediatek.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 24 +++++++++++-------------
 include/ufs/ufshcd.h      |  1 -
 2 files changed, 11 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 219ba7b0501b..608dba595beb 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -4413,6 +4413,14 @@ int ufshcd_uic_hibern8_exit(struct ufs_hba *hba)
 }
 EXPORT_SYMBOL_GPL(ufshcd_uic_hibern8_exit);
 
+static void ufshcd_configure_auto_hibern8(struct ufs_hba *hba)
+{
+	if (!ufshcd_is_auto_hibern8_supported(hba))
+		return;
+
+	ufshcd_writel(hba, hba->ahit, REG_AUTO_HIBERNATE_IDLE_TIMER);
+}
+
 void ufshcd_auto_hibern8_update(struct ufs_hba *hba, u32 ahit)
 {
 	unsigned long flags;
@@ -4432,21 +4440,13 @@ void ufshcd_auto_hibern8_update(struct ufs_hba *hba, u32 ahit)
 	    !pm_runtime_suspended(&hba->ufs_device_wlun->sdev_gendev)) {
 		ufshcd_rpm_get_sync(hba);
 		ufshcd_hold(hba);
-		ufshcd_auto_hibern8_enable(hba);
+		ufshcd_configure_auto_hibern8(hba);
 		ufshcd_release(hba);
 		ufshcd_rpm_put_sync(hba);
 	}
 }
 EXPORT_SYMBOL_GPL(ufshcd_auto_hibern8_update);
 
-void ufshcd_auto_hibern8_enable(struct ufs_hba *hba)
-{
-	if (!ufshcd_is_auto_hibern8_supported(hba))
-		return;
-
-	ufshcd_writel(hba, hba->ahit, REG_AUTO_HIBERNATE_IDLE_TIMER);
-}
-
  /**
  * ufshcd_init_pwr_info - setting the POR (power on reset)
  * values in hba power info
@@ -8953,8 +8953,7 @@ static int ufshcd_probe_hba(struct ufs_hba *hba, bool init_dev_params)
 
 	if (hba->ee_usr_mask)
 		ufshcd_write_ee_control(hba);
-	/* Enable Auto-Hibernate if configured */
-	ufshcd_auto_hibern8_enable(hba);
+	ufshcd_configure_auto_hibern8(hba);
 
 out:
 	spin_lock_irqsave(hba->host->host_lock, flags);
@@ -9956,8 +9955,7 @@ static int __ufshcd_wl_resume(struct ufs_hba *hba, enum ufs_pm_op pm_op)
 		cancel_delayed_work(&hba->rpm_dev_flush_recheck_work);
 	}
 
-	/* Enable Auto-Hibernate if configured */
-	ufshcd_auto_hibern8_enable(hba);
+	ufshcd_configure_auto_hibern8(hba);
 
 	goto out;
 
diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h
index 38637bea9a52..8e2bce9a4f21 100644
--- a/include/ufs/ufshcd.h
+++ b/include/ufs/ufshcd.h
@@ -1371,7 +1371,6 @@ static inline int ufshcd_disable_host_tx_lcc(struct ufs_hba *hba)
 	return ufshcd_dme_set(hba, UIC_ARG_MIB(PA_LOCAL_TX_LCC_ENABLE), 0);
 }
 
-void ufshcd_auto_hibern8_enable(struct ufs_hba *hba);
 void ufshcd_auto_hibern8_update(struct ufs_hba *hba, u32 ahit);
 void ufshcd_fixup_dev_quirks(struct ufs_hba *hba,
 			     const struct ufs_dev_quirk *fixups);
-- 
cgit v1.2.3


From d23569979ca1cd139a42c410e0c7b9e6014c3b3a Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Wed, 13 Dec 2023 09:37:01 -0500
Subject: tracing: Allow creating instances with specified system events

A trace instance may only need to enable specific events. As the eventfs
directory of an instance currently creates all events which adds overhead,
allow internal instances to be created with just the events in systems
that they care about. This currently only deals with systems and not
individual events, but this should bring down the overhead of creating
instances for specific use cases quite bit.

The trace_array_get_by_name() now has another parameter "systems". This
parameter is a const string pointer of a comma/space separated list of
event systems that should be created by the trace_array. (Note if the
trace_array already exists, this parameter is ignored).

The list of systems is saved and if a module is loaded, its events will
not be added unless the system for those events also match the systems
string.

Link: https://lore.kernel.org/linux-trace-kernel/20231213093701.03fddec0@gandalf.local.home

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Sean Paul <seanpaul@chromium.org>
Cc: Arun Easi   <aeasi@marvell.com>
Cc: Daniel Wagner <dwagner@suse.de>
Tested-by: Dmytro Maluka <dmaluka@chromium.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 drivers/scsi/qla2xxx/qla_os.c       |  2 +-
 include/linux/trace.h               |  4 ++--
 kernel/trace/trace.c                | 23 ++++++++++++++----
 kernel/trace/trace.h                |  1 +
 kernel/trace/trace_boot.c           |  2 +-
 kernel/trace/trace_events.c         | 48 ++++++++++++++++++++++++++++++++++---
 samples/ftrace/sample-trace-array.c |  2 +-
 7 files changed, 70 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 03348f605c2e..dd674378f2f3 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -2889,7 +2889,7 @@ static void qla2x00_iocb_work_fn(struct work_struct *work)
 static void
 qla_trace_init(void)
 {
-	qla_trc_array = trace_array_get_by_name("qla2xxx");
+	qla_trc_array = trace_array_get_by_name("qla2xxx", NULL);
 	if (!qla_trc_array) {
 		ql_log(ql_log_fatal, NULL, 0x0001,
 		       "Unable to create qla2xxx trace instance, instance logging will be disabled.\n");
diff --git a/include/linux/trace.h b/include/linux/trace.h
index 2a70a447184c..fdcd76b7be83 100644
--- a/include/linux/trace.h
+++ b/include/linux/trace.h
@@ -51,7 +51,7 @@ int trace_array_printk(struct trace_array *tr, unsigned long ip,
 		       const char *fmt, ...);
 int trace_array_init_printk(struct trace_array *tr);
 void trace_array_put(struct trace_array *tr);
-struct trace_array *trace_array_get_by_name(const char *name);
+struct trace_array *trace_array_get_by_name(const char *name, const char *systems);
 int trace_array_destroy(struct trace_array *tr);
 
 /* For osnoise tracer */
@@ -84,7 +84,7 @@ static inline int trace_array_init_printk(struct trace_array *tr)
 static inline void trace_array_put(struct trace_array *tr)
 {
 }
-static inline struct trace_array *trace_array_get_by_name(const char *name)
+static inline struct trace_array *trace_array_get_by_name(const char *name, const char *systems)
 {
 	return NULL;
 }
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 199df497db07..59e39b652afb 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -9490,7 +9490,8 @@ static int trace_array_create_dir(struct trace_array *tr)
 	return ret;
 }
 
-static struct trace_array *trace_array_create(const char *name)
+static struct trace_array *
+trace_array_create_systems(const char *name, const char *systems)
 {
 	struct trace_array *tr;
 	int ret;
@@ -9510,6 +9511,12 @@ static struct trace_array *trace_array_create(const char *name)
 	if (!zalloc_cpumask_var(&tr->pipe_cpumask, GFP_KERNEL))
 		goto out_free_tr;
 
+	if (systems) {
+		tr->system_names = kstrdup_const(systems, GFP_KERNEL);
+		if (!tr->system_names)
+			goto out_free_tr;
+	}
+
 	tr->trace_flags = global_trace.trace_flags & ~ZEROED_TRACE_FLAGS;
 
 	cpumask_copy(tr->tracing_cpumask, cpu_all_mask);
@@ -9556,12 +9563,18 @@ static struct trace_array *trace_array_create(const char *name)
 	free_trace_buffers(tr);
 	free_cpumask_var(tr->pipe_cpumask);
 	free_cpumask_var(tr->tracing_cpumask);
+	kfree_const(tr->system_names);
 	kfree(tr->name);
 	kfree(tr);
 
 	return ERR_PTR(ret);
 }
 
+static struct trace_array *trace_array_create(const char *name)
+{
+	return trace_array_create_systems(name, NULL);
+}
+
 static int instance_mkdir(const char *name)
 {
 	struct trace_array *tr;
@@ -9587,6 +9600,7 @@ out_unlock:
 /**
  * trace_array_get_by_name - Create/Lookup a trace array, given its name.
  * @name: The name of the trace array to be looked up/created.
+ * @systems: A list of systems to create event directories for (NULL for all)
  *
  * Returns pointer to trace array with given name.
  * NULL, if it cannot be created.
@@ -9600,7 +9614,7 @@ out_unlock:
  * trace_array_put() is called, user space can not delete it.
  *
  */
-struct trace_array *trace_array_get_by_name(const char *name)
+struct trace_array *trace_array_get_by_name(const char *name, const char *systems)
 {
 	struct trace_array *tr;
 
@@ -9612,7 +9626,7 @@ struct trace_array *trace_array_get_by_name(const char *name)
 			goto out_unlock;
 	}
 
-	tr = trace_array_create(name);
+	tr = trace_array_create_systems(name, systems);
 
 	if (IS_ERR(tr))
 		tr = NULL;
@@ -9659,6 +9673,7 @@ static int __remove_instance(struct trace_array *tr)
 
 	free_cpumask_var(tr->pipe_cpumask);
 	free_cpumask_var(tr->tracing_cpumask);
+	kfree_const(tr->system_names);
 	kfree(tr->name);
 	kfree(tr);
 
@@ -10377,7 +10392,7 @@ __init static void enable_instances(void)
 		if (IS_ENABLED(CONFIG_TRACER_MAX_TRACE))
 			do_allocate_snapshot(tok);
 
-		tr = trace_array_get_by_name(tok);
+		tr = trace_array_get_by_name(tok, NULL);
 		if (!tr) {
 			pr_warn("Failed to create instance buffer %s\n", curr_str);
 			continue;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 0489e72c8169..79180aed13ee 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -377,6 +377,7 @@ struct trace_array {
 	unsigned char		trace_flags_index[TRACE_FLAGS_MAX_SIZE];
 	unsigned int		flags;
 	raw_spinlock_t		start_lock;
+	const char		*system_names;
 	struct list_head	err_log;
 	struct dentry		*dir;
 	struct dentry		*options;
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
index 7ccc7a8e155b..dbe29b4c6a7a 100644
--- a/kernel/trace/trace_boot.c
+++ b/kernel/trace/trace_boot.c
@@ -633,7 +633,7 @@ trace_boot_init_instances(struct xbc_node *node)
 		if (!p || *p == '\0')
 			continue;
 
-		tr = trace_array_get_by_name(p);
+		tr = trace_array_get_by_name(p, NULL);
 		if (!tr) {
 			pr_err("Failed to get trace instance %s\n", p);
 			continue;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index f29e815ca5b2..b70d03818038 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2896,6 +2896,27 @@ void trace_event_eval_update(struct trace_eval_map **map, int len)
 	up_write(&trace_event_sem);
 }
 
+static bool event_in_systems(struct trace_event_call *call,
+			     const char *systems)
+{
+	const char *system;
+	const char *p;
+
+	if (!systems)
+		return true;
+
+	system = call->class->system;
+	p = strstr(systems, system);
+	if (!p)
+		return false;
+
+	if (p != systems && !isspace(*(p - 1)) && *(p - 1) != ',')
+		return false;
+
+	p += strlen(system);
+	return !*p || isspace(*p) || *p == ',';
+}
+
 static struct trace_event_file *
 trace_create_new_event(struct trace_event_call *call,
 		       struct trace_array *tr)
@@ -2905,9 +2926,12 @@ trace_create_new_event(struct trace_event_call *call,
 	struct trace_event_file *file;
 	unsigned int first;
 
+	if (!event_in_systems(call, tr->system_names))
+		return NULL;
+
 	file = kmem_cache_alloc(file_cachep, GFP_TRACE);
 	if (!file)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	pid_list = rcu_dereference_protected(tr->filtered_pids,
 					     lockdep_is_held(&event_mutex));
@@ -2972,8 +2996,17 @@ __trace_add_new_event(struct trace_event_call *call, struct trace_array *tr)
 	struct trace_event_file *file;
 
 	file = trace_create_new_event(call, tr);
+	/*
+	 * trace_create_new_event() returns ERR_PTR(-ENOMEM) if failed
+	 * allocation, or NULL if the event is not part of the tr->system_names.
+	 * When the event is not part of the tr->system_names, return zero, not
+	 * an error.
+	 */
 	if (!file)
-		return -ENOMEM;
+		return 0;
+
+	if (IS_ERR(file))
+		return PTR_ERR(file);
 
 	if (eventdir_initialized)
 		return event_create_dir(tr->event_dir, file);
@@ -3012,8 +3045,17 @@ __trace_early_add_new_event(struct trace_event_call *call,
 	int ret;
 
 	file = trace_create_new_event(call, tr);
+	/*
+	 * trace_create_new_event() returns ERR_PTR(-ENOMEM) if failed
+	 * allocation, or NULL if the event is not part of the tr->system_names.
+	 * When the event is not part of the tr->system_names, return zero, not
+	 * an error.
+	 */
 	if (!file)
-		return -ENOMEM;
+		return 0;
+
+	if (IS_ERR(file))
+		return PTR_ERR(file);
 
 	ret = event_define_fields(call);
 	if (ret)
diff --git a/samples/ftrace/sample-trace-array.c b/samples/ftrace/sample-trace-array.c
index 6aba02a31c96..d0ee9001c7b3 100644
--- a/samples/ftrace/sample-trace-array.c
+++ b/samples/ftrace/sample-trace-array.c
@@ -105,7 +105,7 @@ static int __init sample_trace_array_init(void)
 	 * NOTE: This function increments the reference counter
 	 * associated with the trace array - "tr".
 	 */
-	tr = trace_array_get_by_name("sample-instance");
+	tr = trace_array_get_by_name("sample-instance", "sched,timer,kprobes");
 
 	if (!tr)
 		return -1;
-- 
cgit v1.2.3


From 8ec90be7f15fac42992ea821be929d3b06cd0fd9 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Tue, 12 Dec 2023 13:19:01 -0500
Subject: tracing: Allow for max buffer data size trace_marker writes

Allow a trace write to be as big as the ring buffer tracing data will
allow. Currently, it only allows writes of 1KB in size, but there's no
reason that it cannot allow what the ring buffer can hold.

Link: https://lore.kernel.org/linux-trace-kernel/20231212131901.5f501e72@gandalf.local.home

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/ring_buffer.h |  1 +
 kernel/trace/ring_buffer.c  | 15 +++++++++++++++
 kernel/trace/trace.c        | 31 ++++++++++++++++++++++++-------
 3 files changed, 40 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 782e14f62201..b1b03b2c0f08 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -141,6 +141,7 @@ int ring_buffer_iter_empty(struct ring_buffer_iter *iter);
 bool ring_buffer_iter_dropped(struct ring_buffer_iter *iter);
 
 unsigned long ring_buffer_size(struct trace_buffer *buffer, int cpu);
+unsigned long ring_buffer_max_event_size(struct trace_buffer *buffer);
 
 void ring_buffer_reset_cpu(struct trace_buffer *buffer, int cpu);
 void ring_buffer_reset_online_cpus(struct trace_buffer *buffer);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index bfe2697a92ee..16b640d824f9 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -5190,6 +5190,21 @@ unsigned long ring_buffer_size(struct trace_buffer *buffer, int cpu)
 }
 EXPORT_SYMBOL_GPL(ring_buffer_size);
 
+/**
+ * ring_buffer_max_event_size - return the max data size of an event
+ * @buffer: The ring buffer.
+ *
+ * Returns the maximum size an event can be.
+ */
+unsigned long ring_buffer_max_event_size(struct trace_buffer *buffer)
+{
+	/* If abs timestamp is requested, events have a timestamp too */
+	if (ring_buffer_time_stamp_abs(buffer))
+		return BUF_MAX_DATA_SIZE - RB_LEN_TIME_EXTEND;
+	return BUF_MAX_DATA_SIZE;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_max_event_size);
+
 static void rb_clear_buffer_page(struct buffer_page *page)
 {
 	local_set(&page->write, 0);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 59e39b652afb..dba1328e454b 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -7278,8 +7278,9 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	enum event_trigger_type tt = ETT_NONE;
 	struct trace_buffer *buffer;
 	struct print_entry *entry;
+	int meta_size;
 	ssize_t written;
-	int size;
+	size_t size;
 	int len;
 
 /* Used in tracing_mark_raw_write() as well */
@@ -7292,12 +7293,12 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	if (!(tr->trace_flags & TRACE_ITER_MARKERS))
 		return -EINVAL;
 
-	if (cnt > TRACE_BUF_SIZE)
-		cnt = TRACE_BUF_SIZE;
-
-	BUILD_BUG_ON(TRACE_BUF_SIZE >= PAGE_SIZE);
+	if ((ssize_t)cnt < 0)
+		return -EINVAL;
 
-	size = sizeof(*entry) + cnt + 2; /* add '\0' and possible '\n' */
+	meta_size = sizeof(*entry) + 2;  /* add '\0' and possible '\n' */
+ again:
+	size = cnt + meta_size;
 
 	/* If less than "<faulted>", then make sure we can still add that */
 	if (cnt < FAULTED_SIZE)
@@ -7306,9 +7307,25 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	buffer = tr->array_buffer.buffer;
 	event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
 					    tracing_gen_ctx());
-	if (unlikely(!event))
+	if (unlikely(!event)) {
+		/*
+		 * If the size was greater than what was allowed, then
+		 * make it smaller and try again.
+		 */
+		if (size > ring_buffer_max_event_size(buffer)) {
+			/* cnt < FAULTED size should never be bigger than max */
+			if (WARN_ON_ONCE(cnt < FAULTED_SIZE))
+				return -EBADF;
+			cnt = ring_buffer_max_event_size(buffer) - meta_size;
+			/* The above should only happen once */
+			if (WARN_ON_ONCE(cnt + meta_size == size))
+				return -EBADF;
+			goto again;
+		}
+
 		/* Ring buffer disabled, return as if not open for write */
 		return -EBADF;
+	}
 
 	entry = ring_buffer_event_data(event);
 	entry->ip = _THIS_IP_;
-- 
cgit v1.2.3


From 40fc60e36c60ba85b2974e507b67df40c94e9578 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Sat, 9 Dec 2023 17:52:20 -0500
Subject: trace_seq: Increase the buffer size to almost two pages

Now that trace_marker can hold more than 1KB string, and can write as much
as the ring buffer can hold, the trace_seq is not big enough to hold
writes:

 ~# a="1234567890"
 ~# cnt=4080
 ~# s=""
 ~# while [ $cnt -gt 10 ]; do
 ~#	s="${s}${a}"
 ~#	cnt=$((cnt-10))
 ~# done
 ~# echo $s > trace_marker
 ~# cat trace
 # tracer: nop
 #
 # entries-in-buffer/entries-written: 2/2   #P:8
 #
 #                                _-----=> irqs-off/BH-disabled
 #                               / _----=> need-resched
 #                              | / _---=> hardirq/softirq
 #                              || / _--=> preempt-depth
 #                              ||| / _-=> migrate-disable
 #                              |||| /     delay
 #           TASK-PID     CPU#  |||||  TIMESTAMP  FUNCTION
 #              | |         |   |||||     |         |
            <...>-860     [002] .....   105.543465: tracing_mark_write[LINE TOO BIG]
            <...>-860     [002] .....   105.543496: tracing_mark_write: 789012345678901234567890

By increasing the trace_seq buffer to almost two pages, it can now print
out the first line.

This also subtracts the rest of the trace_seq fields from the buffer, so
that the entire trace_seq is now PAGE_SIZE aligned.

Link: https://lore.kernel.org/linux-trace-kernel/20231209175220.19867af4@gandalf.local.home

Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/trace_seq.h | 9 ++++++---
 kernel/trace/trace.c      | 6 +++---
 kernel/trace/trace_seq.c  | 3 ---
 3 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/trace_seq.h b/include/linux/trace_seq.h
index 3691e0e76a1a..9ec229dfddaa 100644
--- a/include/linux/trace_seq.h
+++ b/include/linux/trace_seq.h
@@ -8,11 +8,14 @@
 
 /*
  * Trace sequences are used to allow a function to call several other functions
- * to create a string of data to use (up to a max of PAGE_SIZE).
+ * to create a string of data to use.
  */
 
+#define TRACE_SEQ_BUFFER_SIZE	(PAGE_SIZE * 2 - \
+	(sizeof(struct seq_buf) + sizeof(size_t) + sizeof(int)))
+
 struct trace_seq {
-	char			buffer[PAGE_SIZE];
+	char			buffer[TRACE_SEQ_BUFFER_SIZE];
 	struct seq_buf		seq;
 	size_t			readpos;
 	int			full;
@@ -21,7 +24,7 @@ struct trace_seq {
 static inline void
 trace_seq_init(struct trace_seq *s)
 {
-	seq_buf_init(&s->seq, s->buffer, PAGE_SIZE);
+	seq_buf_init(&s->seq, s->buffer, TRACE_SEQ_BUFFER_SIZE);
 	s->full = 0;
 	s->readpos = 0;
 }
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index dba1328e454b..0be30cccabb4 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3753,7 +3753,7 @@ static bool trace_safe_str(struct trace_iterator *iter, const char *str,
 
 	/* OK if part of the temp seq buffer */
 	if ((addr >= (unsigned long)iter->tmp_seq.buffer) &&
-	    (addr < (unsigned long)iter->tmp_seq.buffer + PAGE_SIZE))
+	    (addr < (unsigned long)iter->tmp_seq.buffer + TRACE_SEQ_BUFFER_SIZE))
 		return true;
 
 	/* Core rodata can not be freed */
@@ -6932,8 +6932,8 @@ waitagain:
 		goto out;
 	}
 
-	if (cnt >= PAGE_SIZE)
-		cnt = PAGE_SIZE - 1;
+	if (cnt >= TRACE_SEQ_BUFFER_SIZE)
+		cnt = TRACE_SEQ_BUFFER_SIZE - 1;
 
 	/* reset all but tr, trace, and overruns */
 	trace_iterator_reset(iter);
diff --git a/kernel/trace/trace_seq.c b/kernel/trace/trace_seq.c
index 7be97229ddf8..c158d65a8a88 100644
--- a/kernel/trace/trace_seq.c
+++ b/kernel/trace/trace_seq.c
@@ -13,9 +13,6 @@
  * trace_seq_init() more than once to reset the trace_seq to start
  * from scratch.
  * 
- * The buffer size is currently PAGE_SIZE, although it may become dynamic
- * in the future.
- *
  * A write to the buffer will either succeed or fail. That is, unlike
  * sprintf() there will not be a partial write (well it may write into
  * the buffer but it wont update the pointers). This allows users to
-- 
cgit v1.2.3


From b9670ee2e975e1cb6751019d5dc5c193aecd8ba2 Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Sun, 17 Dec 2023 12:07:02 -0800
Subject: Revert "iio: hid-sensor-als: Add light chromaticity support"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This reverts commit ee3710f39f9d0ae5137a866138d005fe1ad18132.

This commit assumes that every HID descriptor for ALS sensor has
presence of usage id ID HID_USAGE_SENSOR_LIGHT_CHROMATICITY_X and
HID_USAGE_SENSOR_LIGHT_CHROMATICITY_Y. When the above usage ids are
absent,  driver probe fails. This breaks ALS sensor functionality on
many platforms.

Till we have a good solution, revert this commit.

Reported-by: Thomas Weißschuh <thomas@t-8ch.de>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=218223
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Cc:  <stable@vger.kernel.org>
Acked-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Link: https://lore.kernel.org/r/20231217200703.719876-2-srinivas.pandruvada@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/iio/light/hid-sensor-als.c | 63 --------------------------------------
 include/linux/hid-sensor-ids.h     |  3 --
 2 files changed, 66 deletions(-)

(limited to 'include')

diff --git a/drivers/iio/light/hid-sensor-als.c b/drivers/iio/light/hid-sensor-als.c
index f17304b54468..d44b3f30ae4a 100644
--- a/drivers/iio/light/hid-sensor-als.c
+++ b/drivers/iio/light/hid-sensor-als.c
@@ -17,8 +17,6 @@ enum {
 	CHANNEL_SCAN_INDEX_INTENSITY,
 	CHANNEL_SCAN_INDEX_ILLUM,
 	CHANNEL_SCAN_INDEX_COLOR_TEMP,
-	CHANNEL_SCAN_INDEX_CHROMATICITY_X,
-	CHANNEL_SCAN_INDEX_CHROMATICITY_Y,
 	CHANNEL_SCAN_INDEX_MAX
 };
 
@@ -78,30 +76,6 @@ static const struct iio_chan_spec als_channels[] = {
 		BIT(IIO_CHAN_INFO_HYSTERESIS_RELATIVE),
 		.scan_index = CHANNEL_SCAN_INDEX_COLOR_TEMP,
 	},
-	{
-		.type = IIO_CHROMATICITY,
-		.modified = 1,
-		.channel2 = IIO_MOD_X,
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_OFFSET) |
-		BIT(IIO_CHAN_INFO_SCALE) |
-		BIT(IIO_CHAN_INFO_SAMP_FREQ) |
-		BIT(IIO_CHAN_INFO_HYSTERESIS) |
-		BIT(IIO_CHAN_INFO_HYSTERESIS_RELATIVE),
-		.scan_index = CHANNEL_SCAN_INDEX_CHROMATICITY_X,
-	},
-	{
-		.type = IIO_CHROMATICITY,
-		.modified = 1,
-		.channel2 = IIO_MOD_Y,
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_OFFSET) |
-		BIT(IIO_CHAN_INFO_SCALE) |
-		BIT(IIO_CHAN_INFO_SAMP_FREQ) |
-		BIT(IIO_CHAN_INFO_HYSTERESIS) |
-		BIT(IIO_CHAN_INFO_HYSTERESIS_RELATIVE),
-		.scan_index = CHANNEL_SCAN_INDEX_CHROMATICITY_Y,
-	},
 	IIO_CHAN_SOFT_TIMESTAMP(CHANNEL_SCAN_INDEX_TIMESTAMP)
 };
 
@@ -145,16 +119,6 @@ static int als_read_raw(struct iio_dev *indio_dev,
 			min = als_state->als[chan->scan_index].logical_minimum;
 			address = HID_USAGE_SENSOR_LIGHT_COLOR_TEMPERATURE;
 			break;
-		case  CHANNEL_SCAN_INDEX_CHROMATICITY_X:
-			report_id = als_state->als[chan->scan_index].report_id;
-			min = als_state->als[chan->scan_index].logical_minimum;
-			address = HID_USAGE_SENSOR_LIGHT_CHROMATICITY_X;
-			break;
-		case  CHANNEL_SCAN_INDEX_CHROMATICITY_Y:
-			report_id = als_state->als[chan->scan_index].report_id;
-			min = als_state->als[chan->scan_index].logical_minimum;
-			address = HID_USAGE_SENSOR_LIGHT_CHROMATICITY_Y;
-			break;
 		default:
 			report_id = -1;
 			break;
@@ -279,14 +243,6 @@ static int als_capture_sample(struct hid_sensor_hub_device *hsdev,
 		als_state->scan.illum[CHANNEL_SCAN_INDEX_COLOR_TEMP] = sample_data;
 		ret = 0;
 		break;
-	case HID_USAGE_SENSOR_LIGHT_CHROMATICITY_X:
-		als_state->scan.illum[CHANNEL_SCAN_INDEX_CHROMATICITY_X] = sample_data;
-		ret = 0;
-		break;
-	case HID_USAGE_SENSOR_LIGHT_CHROMATICITY_Y:
-		als_state->scan.illum[CHANNEL_SCAN_INDEX_CHROMATICITY_Y] = sample_data;
-		ret = 0;
-		break;
 	case HID_USAGE_SENSOR_TIME_TIMESTAMP:
 		als_state->timestamp = hid_sensor_convert_timestamp(&als_state->common_attributes,
 								    *(s64 *)raw_data);
@@ -335,25 +291,6 @@ static int als_parse_report(struct platform_device *pdev,
 		st->als[CHANNEL_SCAN_INDEX_COLOR_TEMP].index,
 		st->als[CHANNEL_SCAN_INDEX_COLOR_TEMP].report_id);
 
-	for (i = 0; i < 2; i++) {
-		int next_scan_index = CHANNEL_SCAN_INDEX_CHROMATICITY_X + i;
-
-		ret = sensor_hub_input_get_attribute_info(hsdev,
-				HID_INPUT_REPORT, usage_id,
-				HID_USAGE_SENSOR_LIGHT_CHROMATICITY_X + i,
-				&st->als[next_scan_index]);
-		if (ret < 0)
-			return ret;
-
-		als_adjust_channel_bit_mask(channels,
-					CHANNEL_SCAN_INDEX_CHROMATICITY_X + i,
-					st->als[next_scan_index].size);
-
-		dev_dbg(&pdev->dev, "als %x:%x\n",
-			st->als[next_scan_index].index,
-			st->als[next_scan_index].report_id);
-	}
-
 	st->scale_precision = hid_sensor_format_scale(usage_id,
 				&st->als[CHANNEL_SCAN_INDEX_INTENSITY],
 				&st->scale_pre_decml, &st->scale_post_decml);
diff --git a/include/linux/hid-sensor-ids.h b/include/linux/hid-sensor-ids.h
index 6730ee900ee1..8af4fb3e0254 100644
--- a/include/linux/hid-sensor-ids.h
+++ b/include/linux/hid-sensor-ids.h
@@ -22,9 +22,6 @@
 #define HID_USAGE_SENSOR_DATA_LIGHT				0x2004d0
 #define HID_USAGE_SENSOR_LIGHT_ILLUM				0x2004d1
 #define HID_USAGE_SENSOR_LIGHT_COLOR_TEMPERATURE		0x2004d2
-#define HID_USAGE_SENSOR_LIGHT_CHROMATICITY			0x2004d3
-#define HID_USAGE_SENSOR_LIGHT_CHROMATICITY_X			0x2004d4
-#define HID_USAGE_SENSOR_LIGHT_CHROMATICITY_Y			0x2004d5
 
 /* PROX (200011) */
 #define HID_USAGE_SENSOR_PROX                                   0x200011
-- 
cgit v1.2.3


From d4005431673929a1259ad791db87408fcf85d2cc Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Sun, 17 Dec 2023 12:07:03 -0800
Subject: Revert "iio: hid-sensor-als: Add light color temperature support"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This reverts commit 5f05285df691b1e82108eead7165feae238c95ef.

This commit assumes that every HID descriptor for ALS sensor has
presence of usage id ID HID_USAGE_SENSOR_LIGHT_COLOR_TEMPERATURE.
When the above usage id is absent,  driver probe fails. This breaks
ALS sensor functionality on many platforms.

Till we have a good solution, revert this commit.

Reported-by: Thomas Weißschuh <thomas@t-8ch.de>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=218223
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Cc:  <stable@vger.kernel.org>
Acked-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Link: https://lore.kernel.org/r/20231217200703.719876-3-srinivas.pandruvada@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/iio/light/hid-sensor-als.c | 37 ++-----------------------------------
 include/linux/hid-sensor-ids.h     |  1 -
 2 files changed, 2 insertions(+), 36 deletions(-)

(limited to 'include')

diff --git a/drivers/iio/light/hid-sensor-als.c b/drivers/iio/light/hid-sensor-als.c
index d44b3f30ae4a..5cd27f04b45e 100644
--- a/drivers/iio/light/hid-sensor-als.c
+++ b/drivers/iio/light/hid-sensor-als.c
@@ -14,9 +14,8 @@
 #include "../common/hid-sensors/hid-sensor-trigger.h"
 
 enum {
-	CHANNEL_SCAN_INDEX_INTENSITY,
-	CHANNEL_SCAN_INDEX_ILLUM,
-	CHANNEL_SCAN_INDEX_COLOR_TEMP,
+	CHANNEL_SCAN_INDEX_INTENSITY = 0,
+	CHANNEL_SCAN_INDEX_ILLUM = 1,
 	CHANNEL_SCAN_INDEX_MAX
 };
 
@@ -66,16 +65,6 @@ static const struct iio_chan_spec als_channels[] = {
 		BIT(IIO_CHAN_INFO_HYSTERESIS_RELATIVE),
 		.scan_index = CHANNEL_SCAN_INDEX_ILLUM,
 	},
-	{
-		.type = IIO_COLORTEMP,
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_OFFSET) |
-		BIT(IIO_CHAN_INFO_SCALE) |
-		BIT(IIO_CHAN_INFO_SAMP_FREQ) |
-		BIT(IIO_CHAN_INFO_HYSTERESIS) |
-		BIT(IIO_CHAN_INFO_HYSTERESIS_RELATIVE),
-		.scan_index = CHANNEL_SCAN_INDEX_COLOR_TEMP,
-	},
 	IIO_CHAN_SOFT_TIMESTAMP(CHANNEL_SCAN_INDEX_TIMESTAMP)
 };
 
@@ -114,11 +103,6 @@ static int als_read_raw(struct iio_dev *indio_dev,
 			min = als_state->als[chan->scan_index].logical_minimum;
 			address = HID_USAGE_SENSOR_LIGHT_ILLUM;
 			break;
-		case  CHANNEL_SCAN_INDEX_COLOR_TEMP:
-			report_id = als_state->als[chan->scan_index].report_id;
-			min = als_state->als[chan->scan_index].logical_minimum;
-			address = HID_USAGE_SENSOR_LIGHT_COLOR_TEMPERATURE;
-			break;
 		default:
 			report_id = -1;
 			break;
@@ -239,10 +223,6 @@ static int als_capture_sample(struct hid_sensor_hub_device *hsdev,
 		als_state->scan.illum[CHANNEL_SCAN_INDEX_ILLUM] = sample_data;
 		ret = 0;
 		break;
-	case HID_USAGE_SENSOR_LIGHT_COLOR_TEMPERATURE:
-		als_state->scan.illum[CHANNEL_SCAN_INDEX_COLOR_TEMP] = sample_data;
-		ret = 0;
-		break;
 	case HID_USAGE_SENSOR_TIME_TIMESTAMP:
 		als_state->timestamp = hid_sensor_convert_timestamp(&als_state->common_attributes,
 								    *(s64 *)raw_data);
@@ -278,19 +258,6 @@ static int als_parse_report(struct platform_device *pdev,
 			st->als[i].report_id);
 	}
 
-	ret = sensor_hub_input_get_attribute_info(hsdev, HID_INPUT_REPORT,
-				usage_id,
-				HID_USAGE_SENSOR_LIGHT_COLOR_TEMPERATURE,
-				&st->als[CHANNEL_SCAN_INDEX_COLOR_TEMP]);
-	if (ret < 0)
-		return ret;
-	als_adjust_channel_bit_mask(channels, CHANNEL_SCAN_INDEX_COLOR_TEMP,
-				st->als[CHANNEL_SCAN_INDEX_COLOR_TEMP].size);
-
-	dev_dbg(&pdev->dev, "als %x:%x\n",
-		st->als[CHANNEL_SCAN_INDEX_COLOR_TEMP].index,
-		st->als[CHANNEL_SCAN_INDEX_COLOR_TEMP].report_id);
-
 	st->scale_precision = hid_sensor_format_scale(usage_id,
 				&st->als[CHANNEL_SCAN_INDEX_INTENSITY],
 				&st->scale_pre_decml, &st->scale_post_decml);
diff --git a/include/linux/hid-sensor-ids.h b/include/linux/hid-sensor-ids.h
index 8af4fb3e0254..13b1e65fbdcc 100644
--- a/include/linux/hid-sensor-ids.h
+++ b/include/linux/hid-sensor-ids.h
@@ -21,7 +21,6 @@
 #define HID_USAGE_SENSOR_ALS					0x200041
 #define HID_USAGE_SENSOR_DATA_LIGHT				0x2004d0
 #define HID_USAGE_SENSOR_LIGHT_ILLUM				0x2004d1
-#define HID_USAGE_SENSOR_LIGHT_COLOR_TEMPERATURE		0x2004d2
 
 /* PROX (200011) */
 #define HID_USAGE_SENSOR_PROX                                   0x200011
-- 
cgit v1.2.3


From 7259eb7b534735b9c1153654c0bb4c5f059c0dd3 Mon Sep 17 00:00:00 2001
From: Moti Haimovski <mhaimovski@habana.ai>
Date: Sun, 12 Nov 2023 18:07:10 +0200
Subject: accel/habanalabs/gaudi2: add signed dev info uAPI

User will provide a nonce via the INFO ioctl, and will retrieve
the signed device info generated using given nonce.

Signed-off-by: Moti Haimovski <mhaimovski@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
 drivers/accel/habanalabs/common/firmware_if.c      |  8 ++++
 drivers/accel/habanalabs/common/habanalabs.h       |  2 +
 drivers/accel/habanalabs/common/habanalabs_ioctl.c | 53 ++++++++++++++++++++++
 include/linux/habanalabs/cpucp_if.h                |  8 +++-
 include/uapi/drm/habanalabs_accel.h                | 28 ++++++++++++
 5 files changed, 98 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/accel/habanalabs/common/firmware_if.c b/drivers/accel/habanalabs/common/firmware_if.c
index 9e9dfe013659..3558a6a8e192 100644
--- a/drivers/accel/habanalabs/common/firmware_if.c
+++ b/drivers/accel/habanalabs/common/firmware_if.c
@@ -3244,6 +3244,14 @@ int hl_fw_get_sec_attest_info(struct hl_device *hdev, struct cpucp_sec_attest_in
 					HL_CPUCP_SEC_ATTEST_INFO_TINEOUT_USEC);
 }
 
+int hl_fw_get_dev_info_signed(struct hl_device *hdev,
+			      struct cpucp_dev_info_signed *dev_info_signed, u32 nonce)
+{
+	return hl_fw_get_sec_attest_data(hdev, CPUCP_PACKET_INFO_SIGNED_GET, dev_info_signed,
+					 sizeof(struct cpucp_dev_info_signed), nonce,
+					 HL_CPUCP_SEC_ATTEST_INFO_TINEOUT_USEC);
+}
+
 int hl_fw_send_generic_request(struct hl_device *hdev, enum hl_passthrough_type sub_opcode,
 						dma_addr_t buff, u32 *size)
 {
diff --git a/drivers/accel/habanalabs/common/habanalabs.h b/drivers/accel/habanalabs/common/habanalabs.h
index 7b0209e5bad6..dd3fe3ddc00a 100644
--- a/drivers/accel/habanalabs/common/habanalabs.h
+++ b/drivers/accel/habanalabs/common/habanalabs.h
@@ -3964,6 +3964,8 @@ long hl_fw_get_max_power(struct hl_device *hdev);
 void hl_fw_set_max_power(struct hl_device *hdev);
 int hl_fw_get_sec_attest_info(struct hl_device *hdev, struct cpucp_sec_attest_info *sec_attest_info,
 				u32 nonce);
+int hl_fw_get_dev_info_signed(struct hl_device *hdev,
+			      struct cpucp_dev_info_signed *dev_info_signed, u32 nonce);
 int hl_set_voltage(struct hl_device *hdev, int sensor_index, u32 attr, long value);
 int hl_set_current(struct hl_device *hdev, int sensor_index, u32 attr, long value);
 int hl_set_power(struct hl_device *hdev, int sensor_index, u32 attr, long value);
diff --git a/drivers/accel/habanalabs/common/habanalabs_ioctl.c b/drivers/accel/habanalabs/common/habanalabs_ioctl.c
index 8ef36effb95b..a92713e0e580 100644
--- a/drivers/accel/habanalabs/common/habanalabs_ioctl.c
+++ b/drivers/accel/habanalabs/common/habanalabs_ioctl.c
@@ -19,6 +19,9 @@
 
 #include <asm/msr.h>
 
+/* make sure there is space for all the signed info */
+static_assert(sizeof(struct cpucp_info) <= SEC_DEV_INFO_BUF_SZ);
+
 static u32 hl_debug_struct_size[HL_DEBUG_OP_TIMESTAMP + 1] = {
 	[HL_DEBUG_OP_ETR] = sizeof(struct hl_debug_params_etr),
 	[HL_DEBUG_OP_ETF] = sizeof(struct hl_debug_params_etf),
@@ -719,6 +722,53 @@ free_sec_attest_info:
 	return rc;
 }
 
+static int dev_info_signed(struct hl_fpriv *hpriv, struct hl_info_args *args)
+{
+	void __user *out = (void __user *) (uintptr_t) args->return_pointer;
+	struct cpucp_dev_info_signed *dev_info_signed;
+	struct hl_info_signed *info;
+	u32 max_size = args->return_size;
+	int rc;
+
+	if ((!max_size) || (!out))
+		return -EINVAL;
+
+	dev_info_signed = kzalloc(sizeof(*dev_info_signed), GFP_KERNEL);
+	if (!dev_info_signed)
+		return -ENOMEM;
+
+	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	if (!info) {
+		rc = -ENOMEM;
+		goto free_dev_info_signed;
+	}
+
+	rc = hl_fw_get_dev_info_signed(hpriv->hdev,
+					dev_info_signed, args->sec_attest_nonce);
+	if (rc)
+		goto free_info;
+
+	info->nonce = le32_to_cpu(dev_info_signed->nonce);
+	info->info_sig_len = dev_info_signed->info_sig_len;
+	info->pub_data_len = le16_to_cpu(dev_info_signed->pub_data_len);
+	info->certificate_len = le16_to_cpu(dev_info_signed->certificate_len);
+	info->dev_info_len = sizeof(struct cpucp_info);
+	memcpy(&info->info_sig, &dev_info_signed->info_sig, sizeof(info->info_sig));
+	memcpy(&info->public_data, &dev_info_signed->public_data, sizeof(info->public_data));
+	memcpy(&info->certificate, &dev_info_signed->certificate, sizeof(info->certificate));
+	memcpy(&info->dev_info, &dev_info_signed->info, info->dev_info_len);
+
+	rc = copy_to_user(out, info, min_t(size_t, max_size, sizeof(*info))) ? -EFAULT : 0;
+
+free_info:
+	kfree(info);
+free_dev_info_signed:
+	kfree(dev_info_signed);
+
+	return rc;
+}
+
+
 static int eventfd_register(struct hl_fpriv *hpriv, struct hl_info_args *args)
 {
 	int rc;
@@ -1089,6 +1139,9 @@ static int _hl_info_ioctl(struct hl_fpriv *hpriv, void *data,
 	case HL_INFO_FW_GENERIC_REQ:
 		return send_fw_generic_request(hdev, args);
 
+	case HL_INFO_DEV_SIGNED:
+		return dev_info_signed(hpriv, args);
+
 	default:
 		dev_err(dev, "Invalid request %d\n", args->op);
 		rc = -EINVAL;
diff --git a/include/linux/habanalabs/cpucp_if.h b/include/linux/habanalabs/cpucp_if.h
index 86ea7c63a0d2..f316c8d0f3fc 100644
--- a/include/linux/habanalabs/cpucp_if.h
+++ b/include/linux/habanalabs/cpucp_if.h
@@ -659,6 +659,12 @@ enum pq_init_status {
  *       number (nonce) provided by the host to prevent replay attacks.
  *       public key and certificate also provided as part of the FW response.
  *
+ * CPUCP_PACKET_INFO_SIGNED_GET -
+ *       Get the device information signed by the Trusted Platform device.
+ *       device info data is also hashed with some unique number (nonce) provided
+ *       by the host to prevent replay attacks. public key and certificate also
+ *       provided as part of the FW response.
+ *
  * CPUCP_PACKET_MONITOR_DUMP_GET -
  *       Get monitors registers dump from the CpuCP kernel.
  *       The CPU will put the registers dump in the a buffer allocated by the driver
@@ -733,7 +739,7 @@ enum cpucp_packet_id {
 	CPUCP_PACKET_ENGINE_CORE_ASID_SET,	/* internal */
 	CPUCP_PACKET_RESERVED2,			/* not used */
 	CPUCP_PACKET_SEC_ATTEST_GET,		/* internal */
-	CPUCP_PACKET_RESERVED3,			/* not used */
+	CPUCP_PACKET_INFO_SIGNED_GET,		/* internal */
 	CPUCP_PACKET_RESERVED4,			/* not used */
 	CPUCP_PACKET_MONITOR_DUMP_GET,		/* debugfs */
 	CPUCP_PACKET_RESERVED5,			/* not used */
diff --git a/include/uapi/drm/habanalabs_accel.h b/include/uapi/drm/habanalabs_accel.h
index 347c7b62e60e..a512dc4cffd0 100644
--- a/include/uapi/drm/habanalabs_accel.h
+++ b/include/uapi/drm/habanalabs_accel.h
@@ -846,6 +846,7 @@ enum hl_server_type {
 #define HL_INFO_HW_ERR_EVENT			36
 #define HL_INFO_FW_ERR_EVENT			37
 #define HL_INFO_USER_ENGINE_ERR_EVENT		38
+#define HL_INFO_DEV_SIGNED			40
 
 #define HL_INFO_VERSION_MAX_LEN			128
 #define HL_INFO_CARD_NAME_MAX_LEN		16
@@ -1256,6 +1257,7 @@ struct hl_info_dev_memalloc_page_sizes {
 #define SEC_SIGNATURE_BUF_SZ	255	/* (256 - 1) 1 byte used for size */
 #define SEC_PUB_DATA_BUF_SZ	510	/* (512 - 2) 2 bytes used for size */
 #define SEC_CERTIFICATE_BUF_SZ	2046	/* (2048 - 2) 2 bytes used for size */
+#define SEC_DEV_INFO_BUF_SZ	5120
 
 /*
  * struct hl_info_sec_attest - attestation report of the boot
@@ -1290,6 +1292,32 @@ struct hl_info_sec_attest {
 	__u8 pad0[2];
 };
 
+/*
+ * struct hl_info_signed - device information signed by a secured device.
+ * @nonce: number only used once. random number provided by host. this also passed to the quote
+ *         command as a qualifying data.
+ * @pub_data_len: length of the public data (bytes)
+ * @certificate_len: length of the certificate (bytes)
+ * @info_sig_len: length of the attestation signature (bytes)
+ * @public_data: public key info signed info data (outPublic + name + qualifiedName)
+ * @certificate: certificate for the signing key
+ * @info_sig: signature of the info + nonce data.
+ * @dev_info_len: length of device info (bytes)
+ * @dev_info: device info as byte array.
+ */
+struct hl_info_signed {
+	__u32 nonce;
+	__u16 pub_data_len;
+	__u16 certificate_len;
+	__u8 info_sig_len;
+	__u8 public_data[SEC_PUB_DATA_BUF_SZ];
+	__u8 certificate[SEC_CERTIFICATE_BUF_SZ];
+	__u8 info_sig[SEC_SIGNATURE_BUF_SZ];
+	__u16 dev_info_len;
+	__u8 dev_info[SEC_DEV_INFO_BUF_SZ];
+	__u8 pad[2];
+};
+
 /**
  * struct hl_page_fault_info - page fault information.
  * @timestamp: timestamp of page fault.
-- 
cgit v1.2.3


From 13f58267cda3d6946c8f4de368ad5d4a003baa61 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Tue, 19 Dec 2023 05:10:33 +0000
Subject: ASoC: soc.h: don't create dummy Component via COMP_DUMMY()

Many ASoC drivers define CPU/Codec/Platform dai_link by below macro.

	SND_SOC_DAILINK_DEFS(link,
(A)		     DAILINK_COMP_ARRAY(COMP_CPU("cpu_dai")),
(B)		     DAILINK_COMP_ARRAY(COMP_CODEC("codec", "dai1"),
(B)					COMP_CODEC("codec", "dai2")),
(C)		     DAILINK_COMP_ARRAY(COMP_EMPTY()));

In this case, this macro will be converted to like below

	[o] = static struct snd_soc_dai_link_component

(A)	[o] link_cpus[]      = {{ .dai_name = "cpu_dai" }};
(B)	[o] link_codecs[]    = {{ .dai_name = "dai1", .name = "codec" },
				{ .dai_name = "dai2", .name = "codec" }}
(C)	[o] link_platforms[] = {{ }};

CPU and Codec info will be filled by COMP_CPU() / COMP_CODEC (= A,B),
and Platform will have empty data by COMP_EMPTY() (= C) in this case.

Platform empty info will be filled when driver probe()
(most of case, CPU info will be copied to use soc-generic-dmaengine-pcm).

For example in case of DPCM FE/BE, it will be like below.
Codec will be dummy Component / DAI in this case (X).

	SND_SOC_DAILINK_DEFS(link,
		     DAILINK_COMP_ARRAY(COMP_CPU(...)),
(X)		     DAILINK_COMP_ARRAY(COMP_DUMMY()),
		     DAILINK_COMP_ARRAY(COMP_EMPTY()));

(X) part will converted like below

	[o] link_codecs[]    = {{ .name = "snd-soc-dummy",
				  .dai_name = "snd-soc-dummy-dai", }}

Even though we already have common asoc_dummy_dlc for dummy
Component / DAI, this macro will re-create new dummy dlc.
Some drivers defines many dai_link info via SND_SOC_DAILINK_DEFS(),
this means many dummy dlc also will be re-created. This is waste of
memory.

If we can use existing common asoc_dummy_dlc at (X),
we can avoid to re-creating dummy dlc, then, we can save the memory.

At that time, we want to keep existing code as much as possible, because
too many drivers are using this macro. But because of its original style,
using common asoc_dummy_dlc from it is very difficult or impossible.

So let's change the mind. The macro is used like below

	SND_SOC_DAILINK_DEFS(link,
		     DAILINK_COMP_ARRAY(COMP_CPU(...)),
(x)		     DAILINK_COMP_ARRAY(COMP_DUMMY()),
		     DAILINK_COMP_ARRAY(COMP_EMPTY()));

	static struct snd_soc_dai_link dai_links[] = {
	{
		.name = ...,
		.stream_name = ...,
(y)		SND_SOC_DAILINK_REG(link),
	},

(y) part will be like below

        static struct snd_soc_dai_link dai_links[] = {
        {
                .name = ...,
                .stream_name = ...,
 ^		...
 |		.codecs		= link_codecs,
(y)		.num_codecs	= ARRAY_SIZE(link_codecs),
 v		...
	}

This patch try to use trick on COMP_DUMMY()

-	#define COMP_DUMMY()	{ .name = "snd-soc-dummy", .dai_name = "snd-soc-dummy-dai", }
+	#define COMP_DUMMY()

By this tric, (x) part will be like below.

before
	[o] link_codecs[] = {{ .name = "snd-soc-dummy", .dai_name = "snd-soc-dummy-dai", }}
after
	[o] link_codecs[] = { };

This is same as below

	[o] link_codecs[0];

This means it has pointer (link_codecs), but the array size is 0.
(y) part will be like below.

	static struct snd_soc_dai_link dai_links[] = {
	{
		...
		.codecs		= link_codecs,
		.num_codecs	= 0,
		...
	},

This is very special settings that normal use usually not do,
but new macro do.
We can find this special settings on soc-core.c and fill it as
"dummy DAI" (= asoc_dummy_dlc). By this tric, we can avoid to re-create
dummy dlc and save the memory.

This patch add tric at COMP_DUMMY() and add snd_soc_fill_dummy_dai()
to fill dummy DAI.

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Link: https://msgid.link/r/871qbi93qu.wl-kuninori.morimoto.gx@renesas.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc.h  |  2 +-
 sound/soc/soc-core.c | 24 ++++++++++++++++++++++++
 2 files changed, 25 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/sound/soc.h b/include/sound/soc.h
index f3803c2dc349..7cbe85ca040d 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -938,7 +938,7 @@ snd_soc_link_to_platform(struct snd_soc_dai_link *link, int n) {
 #define COMP_PLATFORM(_name)		{ .name = _name }
 #define COMP_AUX(_name)			{ .name = _name }
 #define COMP_CODEC_CONF(_name)		{ .name = _name }
-#define COMP_DUMMY()			{ .name = "snd-soc-dummy", .dai_name = "snd-soc-dummy-dai", }
+#define COMP_DUMMY()			/* see snd_soc_fill_dummy_dai() */
 
 extern struct snd_soc_dai_link_component null_dailink_component[0];
 extern struct snd_soc_dai_link_component snd_soc_dummy_dlc;
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 132946f82a29..f8524b5bfb33 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -576,6 +576,28 @@ free_rtd:
 	return NULL;
 }
 
+static void snd_soc_fill_dummy_dai(struct snd_soc_card *card)
+{
+	struct snd_soc_dai_link *dai_link;
+	int i;
+
+	/*
+	 * COMP_DUMMY() creates size 0 array on dai_link.
+	 * Fill it as dummy DAI in case of CPU/Codec here.
+	 * Do nothing for Platform.
+	 */
+	for_each_card_prelinks(card, i, dai_link) {
+		if (dai_link->num_cpus == 0 && dai_link->cpus) {
+			dai_link->num_cpus	= 1;
+			dai_link->cpus		= &snd_soc_dummy_dlc;
+		}
+		if (dai_link->num_codecs == 0 && dai_link->codecs) {
+			dai_link->num_codecs	= 1;
+			dai_link->codecs	= &snd_soc_dummy_dlc;
+		}
+	}
+}
+
 static void snd_soc_flush_all_delayed_work(struct snd_soc_card *card)
 {
 	struct snd_soc_pcm_runtime *rtd;
@@ -2131,6 +2153,8 @@ static int snd_soc_bind_card(struct snd_soc_card *card)
 	mutex_lock(&client_mutex);
 	snd_soc_card_mutex_lock_root(card);
 
+	snd_soc_fill_dummy_dai(card);
+
 	snd_soc_dapm_init(&card->dapm, card, NULL);
 
 	/* check whether any platform is ignore machine FE and using topology */
-- 
cgit v1.2.3


From 933a2a376fb3f22ba4774f74233571504ac56b02 Mon Sep 17 00:00:00 2001
From: Stephen Rothwell <sfr@canb.auug.org.au>
Date: Tue, 19 Dec 2023 14:57:34 +1100
Subject: drm: using mul_u32_u32() requires linux/math64.h
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Some pending include file cleanups produced this error:

In file included from include/linux/kernel.h:27,
                 from drivers/gpu/ipu-v3/ipu-dp.c:7:
include/drm/drm_color_mgmt.h: In function 'drm_color_lut_extract':
include/drm/drm_color_mgmt.h:45:46: error: implicit declaration of function 'mul_u32_u32' [-Werror=implicit-function-declaration]
   45 |                 return DIV_ROUND_CLOSEST_ULL(mul_u32_u32(user_input, (1 << bit_precision) - 1),
      |                                              ^~~~~~~~~~~

Fixes: c6fbb6bca108 ("drm: Fix color LUT rounding")
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231219145734.13e40e1e@canb.auug.org.au
---
 include/drm/drm_color_mgmt.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/drm/drm_color_mgmt.h b/include/drm/drm_color_mgmt.h
index 54b2b2467bfd..ed81741036d7 100644
--- a/include/drm/drm_color_mgmt.h
+++ b/include/drm/drm_color_mgmt.h
@@ -24,6 +24,7 @@
 #define __DRM_COLOR_MGMT_H__
 
 #include <linux/ctype.h>
+#include <linux/math64.h>
 #include <drm/drm_property.h>
 
 struct drm_crtc;
-- 
cgit v1.2.3


From a731132424adeda4d5383ef61afae2e804063fb7 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Sat, 16 Dec 2023 13:29:57 +0100
Subject: genetlink: introduce per-sock family private storage

Introduce an xarray for Generic netlink family to store per-socket
private. Initialize this xarray only if family uses per-socket privs.

Introduce genl_sk_priv_get() to get the socket priv pointer for a family
and initialize it in case it does not exist.
Introduce __genl_sk_priv_get() to obtain socket priv pointer for a
family under RCU read lock.

Allow family to specify the priv size, init() and destroy() callbacks.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/genetlink.h |  11 ++++
 net/netlink/genetlink.c | 144 +++++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 154 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index c53244f20437..6bc37f392a9a 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -51,6 +51,9 @@ struct genl_info;
  * @split_ops: the split do/dump form of operation definition
  * @n_split_ops: number of entries in @split_ops, not that with split do/dump
  *	ops the number of entries is not the same as number of commands
+ * @sock_priv_size: the size of per-socket private memory
+ * @sock_priv_init: the per-socket private memory initializer
+ * @sock_priv_destroy: the per-socket private memory destructor
  *
  * Attribute policies (the combination of @policy and @maxattr fields)
  * can be attached at the family level or at the operation level.
@@ -84,11 +87,17 @@ struct genl_family {
 	const struct genl_multicast_group *mcgrps;
 	struct module		*module;
 
+	size_t			sock_priv_size;
+	void			(*sock_priv_init)(void *priv);
+	void			(*sock_priv_destroy)(void *priv);
+
 /* private: internal use only */
 	/* protocol family identifier */
 	int			id;
 	/* starting number of multicast group IDs in this family */
 	unsigned int		mcgrp_offset;
+	/* list of per-socket privs */
+	struct xarray		*sock_privs;
 };
 
 /**
@@ -298,6 +307,8 @@ static inline bool genl_info_is_ntf(const struct genl_info *info)
 	return !info->nlhdr;
 }
 
+void *__genl_sk_priv_get(struct genl_family *family, struct sock *sk);
+void *genl_sk_priv_get(struct genl_family *family, struct sock *sk);
 int genl_register_family(struct genl_family *family);
 int genl_unregister_family(const struct genl_family *family);
 void genl_notify(const struct genl_family *family, struct sk_buff *skb,
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 9c7ffd10df2a..c0d15470a10b 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -631,6 +631,138 @@ static int genl_validate_ops(const struct genl_family *family)
 	return 0;
 }
 
+static void *genl_sk_priv_alloc(struct genl_family *family)
+{
+	void *priv;
+
+	priv = kzalloc(family->sock_priv_size, GFP_KERNEL);
+	if (!priv)
+		return ERR_PTR(-ENOMEM);
+
+	if (family->sock_priv_init)
+		family->sock_priv_init(priv);
+
+	return priv;
+}
+
+static void genl_sk_priv_free(const struct genl_family *family, void *priv)
+{
+	if (family->sock_priv_destroy)
+		family->sock_priv_destroy(priv);
+	kfree(priv);
+}
+
+static int genl_sk_privs_alloc(struct genl_family *family)
+{
+	if (!family->sock_priv_size)
+		return 0;
+
+	family->sock_privs = kzalloc(sizeof(*family->sock_privs), GFP_KERNEL);
+	if (!family->sock_privs)
+		return -ENOMEM;
+	xa_init(family->sock_privs);
+	return 0;
+}
+
+static void genl_sk_privs_free(const struct genl_family *family)
+{
+	unsigned long id;
+	void *priv;
+
+	if (!family->sock_priv_size)
+		return;
+
+	xa_for_each(family->sock_privs, id, priv)
+		genl_sk_priv_free(family, priv);
+
+	xa_destroy(family->sock_privs);
+	kfree(family->sock_privs);
+}
+
+static void genl_sk_priv_free_by_sock(struct genl_family *family,
+				      struct sock *sk)
+{
+	void *priv;
+
+	if (!family->sock_priv_size)
+		return;
+	priv = xa_erase(family->sock_privs, (unsigned long) sk);
+	if (!priv)
+		return;
+	genl_sk_priv_free(family, priv);
+}
+
+static void genl_release(struct sock *sk, unsigned long *groups)
+{
+	struct genl_family *family;
+	unsigned int id;
+
+	down_read(&cb_lock);
+
+	idr_for_each_entry(&genl_fam_idr, family, id)
+		genl_sk_priv_free_by_sock(family, sk);
+
+	up_read(&cb_lock);
+}
+
+/**
+ * __genl_sk_priv_get - Get family private pointer for socket, if exists
+ *
+ * @family: family
+ * @sk: socket
+ *
+ * Lookup a private memory for a Generic netlink family and specified socket.
+ *
+ * Caller should make sure this is called in RCU read locked section.
+ *
+ * Return: valid pointer on success, otherwise negative error value
+ * encoded by ERR_PTR(), NULL in case priv does not exist.
+ */
+void *__genl_sk_priv_get(struct genl_family *family, struct sock *sk)
+{
+	if (WARN_ON_ONCE(!family->sock_privs))
+		return ERR_PTR(-EINVAL);
+	return xa_load(family->sock_privs, (unsigned long) sk);
+}
+
+/**
+ * genl_sk_priv_get - Get family private pointer for socket
+ *
+ * @family: family
+ * @sk: socket
+ *
+ * Lookup a private memory for a Generic netlink family and specified socket.
+ * Allocate the private memory in case it was not already done.
+ *
+ * Return: valid pointer on success, otherwise negative error value
+ * encoded by ERR_PTR().
+ */
+void *genl_sk_priv_get(struct genl_family *family, struct sock *sk)
+{
+	void *priv, *old_priv;
+
+	priv = __genl_sk_priv_get(family, sk);
+	if (priv)
+		return priv;
+
+	/* priv for the family does not exist so far, create it. */
+
+	priv = genl_sk_priv_alloc(family);
+	if (IS_ERR(priv))
+		return ERR_CAST(priv);
+
+	old_priv = xa_cmpxchg(family->sock_privs, (unsigned long) sk, NULL,
+			      priv, GFP_KERNEL);
+	if (old_priv) {
+		genl_sk_priv_free(family, priv);
+		if (xa_is_err(old_priv))
+			return ERR_PTR(xa_err(old_priv));
+		/* Race happened, priv for the socket was already inserted. */
+		return old_priv;
+	}
+	return priv;
+}
+
 /**
  * genl_register_family - register a generic netlink family
  * @family: generic netlink family
@@ -659,6 +791,10 @@ int genl_register_family(struct genl_family *family)
 		goto errout_locked;
 	}
 
+	err = genl_sk_privs_alloc(family);
+	if (err)
+		goto errout_locked;
+
 	/*
 	 * Sadly, a few cases need to be special-cased
 	 * due to them having previously abused the API
@@ -679,7 +815,7 @@ int genl_register_family(struct genl_family *family)
 				      start, end + 1, GFP_KERNEL);
 	if (family->id < 0) {
 		err = family->id;
-		goto errout_locked;
+		goto errout_sk_privs_free;
 	}
 
 	err = genl_validate_assign_mc_groups(family);
@@ -698,6 +834,8 @@ int genl_register_family(struct genl_family *family)
 
 errout_remove:
 	idr_remove(&genl_fam_idr, family->id);
+errout_sk_privs_free:
+	genl_sk_privs_free(family);
 errout_locked:
 	genl_unlock_all();
 	return err;
@@ -728,6 +866,9 @@ int genl_unregister_family(const struct genl_family *family)
 	up_write(&cb_lock);
 	wait_event(genl_sk_destructing_waitq,
 		   atomic_read(&genl_sk_destructing_cnt) == 0);
+
+	genl_sk_privs_free(family);
+
 	genl_unlock();
 
 	genl_ctrl_event(CTRL_CMD_DELFAMILY, family, NULL, 0);
@@ -1708,6 +1849,7 @@ static int __net_init genl_pernet_init(struct net *net)
 		.input		= genl_rcv,
 		.flags		= NL_CFG_F_NONROOT_RECV,
 		.bind		= genl_bind,
+		.release	= genl_release,
 	};
 
 	/* we'll bump the group number right afterwards */
-- 
cgit v1.2.3


From 403863e985e8eba608d53b2907caaf37b6176290 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Sat, 16 Dec 2023 13:29:58 +0100
Subject: netlink: introduce typedef for filter function

Make the code using filter function a bit nicer by consolidating the
filter function arguments using typedef.

Suggested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/connector/connector.c | 5 ++---
 include/linux/connector.h     | 3 +--
 include/linux/netlink.h       | 6 ++++--
 net/netlink/af_netlink.c      | 3 +--
 4 files changed, 8 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c
index 7f7b94f616a6..4028e8eeba82 100644
--- a/drivers/connector/connector.c
+++ b/drivers/connector/connector.c
@@ -59,9 +59,8 @@ static int cn_already_initialized;
  * both, or if both are zero then the group is looked up and sent there.
  */
 int cn_netlink_send_mult(struct cn_msg *msg, u16 len, u32 portid, u32 __group,
-	gfp_t gfp_mask,
-	int (*filter)(struct sock *dsk, struct sk_buff *skb, void *data),
-	void *filter_data)
+			 gfp_t gfp_mask, netlink_filter_fn filter,
+			 void *filter_data)
 {
 	struct cn_callback_entry *__cbq;
 	unsigned int size;
diff --git a/include/linux/connector.h b/include/linux/connector.h
index cec2d99ae902..70bc1160f3d8 100644
--- a/include/linux/connector.h
+++ b/include/linux/connector.h
@@ -100,8 +100,7 @@ void cn_del_callback(const struct cb_id *id);
  */
 int cn_netlink_send_mult(struct cn_msg *msg, u16 len, u32 portid,
 			 u32 group, gfp_t gfp_mask,
-			 int (*filter)(struct sock *dsk, struct sk_buff *skb,
-				       void *data),
+			 netlink_filter_fn filter,
 			 void *filter_data);
 
 /**
diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index abe91ed6b9aa..1a4445bf2ab9 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -228,10 +228,12 @@ bool netlink_strict_get_check(struct sk_buff *skb);
 int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 portid, int nonblock);
 int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 portid,
 		      __u32 group, gfp_t allocation);
+
+typedef int (*netlink_filter_fn)(struct sock *dsk, struct sk_buff *skb, void *data);
+
 int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb,
 			       __u32 portid, __u32 group, gfp_t allocation,
-			       int (*filter)(struct sock *dsk,
-					     struct sk_buff *skb, void *data),
+			       netlink_filter_fn filter,
 			       void *filter_data);
 int netlink_set_err(struct sock *ssk, __u32 portid, __u32 group, int code);
 int netlink_register_notifier(struct notifier_block *nb);
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 177126fb0484..4ed8ffd58ff3 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1519,8 +1519,7 @@ out:
 int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb,
 			       u32 portid,
 			       u32 group, gfp_t allocation,
-			       int (*filter)(struct sock *dsk,
-					     struct sk_buff *skb, void *data),
+			       netlink_filter_fn filter,
 			       void *filter_data)
 {
 	struct net *net = sock_net(ssk);
-- 
cgit v1.2.3


From 971b4ad88293bef00160e1d38659077fe3a93af6 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Sat, 16 Dec 2023 13:29:59 +0100
Subject: genetlink: introduce helpers to do filtered multicast

Currently it is possible for netlink kernel user to pass custom
filter function to broadcast send function netlink_broadcast_filtered().
However, this is not exposed to multicast send and to generic
netlink users.

Extend the api and introduce a netlink helper nlmsg_multicast_filtered()
and a generic netlink helper genlmsg_multicast_netns_filtered()
to allow generic netlink families to specify filter function
while sending multicast messages.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/genetlink.h | 35 +++++++++++++++++++++++++++++++----
 include/net/netlink.h   | 31 +++++++++++++++++++++++++++----
 2 files changed, 58 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 6bc37f392a9a..85c63d4f16dd 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -448,6 +448,35 @@ static inline void genlmsg_cancel(struct sk_buff *skb, void *hdr)
 		nlmsg_cancel(skb, hdr - GENL_HDRLEN - NLMSG_HDRLEN);
 }
 
+/**
+ * genlmsg_multicast_netns_filtered - multicast a netlink message
+ *				      to a specific netns with filter
+ *				      function
+ * @family: the generic netlink family
+ * @net: the net namespace
+ * @skb: netlink message as socket buffer
+ * @portid: own netlink portid to avoid sending to yourself
+ * @group: offset of multicast group in groups array
+ * @flags: allocation flags
+ * @filter: filter function
+ * @filter_data: filter function private data
+ *
+ * Return: 0 on success, negative error code for failure.
+ */
+static inline int
+genlmsg_multicast_netns_filtered(const struct genl_family *family,
+				 struct net *net, struct sk_buff *skb,
+				 u32 portid, unsigned int group, gfp_t flags,
+				 netlink_filter_fn filter,
+				 void *filter_data)
+{
+	if (WARN_ON_ONCE(group >= family->n_mcgrps))
+		return -EINVAL;
+	group = family->mcgrp_offset + group;
+	return nlmsg_multicast_filtered(net->genl_sock, skb, portid, group,
+					flags, filter, filter_data);
+}
+
 /**
  * genlmsg_multicast_netns - multicast a netlink message to a specific netns
  * @family: the generic netlink family
@@ -461,10 +490,8 @@ static inline int genlmsg_multicast_netns(const struct genl_family *family,
 					  struct net *net, struct sk_buff *skb,
 					  u32 portid, unsigned int group, gfp_t flags)
 {
-	if (WARN_ON_ONCE(group >= family->n_mcgrps))
-		return -EINVAL;
-	group = family->mcgrp_offset + group;
-	return nlmsg_multicast(net->genl_sock, skb, portid, group, flags);
+	return genlmsg_multicast_netns_filtered(family, net, skb, portid,
+						group, flags, NULL, NULL);
 }
 
 /**
diff --git a/include/net/netlink.h b/include/net/netlink.h
index 28039e57070a..c19ff921b661 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -1087,27 +1087,50 @@ static inline void nlmsg_free(struct sk_buff *skb)
 }
 
 /**
- * nlmsg_multicast - multicast a netlink message
+ * nlmsg_multicast_filtered - multicast a netlink message with filter function
  * @sk: netlink socket to spread messages to
  * @skb: netlink message as socket buffer
  * @portid: own netlink portid to avoid sending to yourself
  * @group: multicast group id
  * @flags: allocation flags
+ * @filter: filter function
+ * @filter_data: filter function private data
+ *
+ * Return: 0 on success, negative error code for failure.
  */
-static inline int nlmsg_multicast(struct sock *sk, struct sk_buff *skb,
-				  u32 portid, unsigned int group, gfp_t flags)
+static inline int nlmsg_multicast_filtered(struct sock *sk, struct sk_buff *skb,
+					   u32 portid, unsigned int group,
+					   gfp_t flags,
+					   netlink_filter_fn filter,
+					   void *filter_data)
 {
 	int err;
 
 	NETLINK_CB(skb).dst_group = group;
 
-	err = netlink_broadcast(sk, skb, portid, group, flags);
+	err = netlink_broadcast_filtered(sk, skb, portid, group, flags,
+					 filter, filter_data);
 	if (err > 0)
 		err = 0;
 
 	return err;
 }
 
+/**
+ * nlmsg_multicast - multicast a netlink message
+ * @sk: netlink socket to spread messages to
+ * @skb: netlink message as socket buffer
+ * @portid: own netlink portid to avoid sending to yourself
+ * @group: multicast group id
+ * @flags: allocation flags
+ */
+static inline int nlmsg_multicast(struct sock *sk, struct sk_buff *skb,
+				  u32 portid, unsigned int group, gfp_t flags)
+{
+	return nlmsg_multicast_filtered(sk, skb, portid, group, flags,
+					NULL, NULL);
+}
+
 /**
  * nlmsg_unicast - unicast a netlink message
  * @sk: netlink socket to spread message to
-- 
cgit v1.2.3


From 13b127d2578432e1e521310b69944c5a1b30679c Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Sat, 16 Dec 2023 13:30:00 +0100
Subject: devlink: add a command to set notification filter and use it for
 multicasts

Currently the user listening on a socket for devlink notifications
gets always all messages for all existing instances, even if he is
interested only in one of those. That may cause unnecessary overhead
on setups with thousands of instances present.

User is currently able to narrow down the devlink objects replies
to dump commands by specifying select attributes.

Allow similar approach for notifications. Introduce a new devlink
NOTIFY_FILTER_SET which the user passes the select attributes. Store
these per-socket and use them for filtering messages
during multicast send.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 Documentation/netlink/specs/devlink.yaml |  10 +++
 include/uapi/linux/devlink.h             |   2 +
 net/devlink/devl_internal.h              |  34 +++++++++-
 net/devlink/netlink.c                    | 108 +++++++++++++++++++++++++++++++
 net/devlink/netlink_gen.c                |  15 ++++-
 net/devlink/netlink_gen.h                |   4 +-
 6 files changed, 169 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/Documentation/netlink/specs/devlink.yaml b/Documentation/netlink/specs/devlink.yaml
index c3a438197964..88bfcb3c3346 100644
--- a/Documentation/netlink/specs/devlink.yaml
+++ b/Documentation/netlink/specs/devlink.yaml
@@ -2254,3 +2254,13 @@ operations:
             - bus-name
             - dev-name
             - selftests
+
+    -
+      name: notify-filter-set
+      doc: Set notification messages socket filter.
+      attribute-set: devlink
+      do:
+        request:
+          attributes:
+            - bus-name
+            - dev-name
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index b3c8383d342d..130cae0d3e20 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -139,6 +139,8 @@ enum devlink_command {
 	DEVLINK_CMD_SELFTESTS_GET,	/* can dump */
 	DEVLINK_CMD_SELFTESTS_RUN,
 
+	DEVLINK_CMD_NOTIFY_FILTER_SET,
+
 	/* add new commands above here */
 	__DEVLINK_CMD_MAX,
 	DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1
diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h
index 84dc9628d3f2..82e0fb3bbebf 100644
--- a/net/devlink/devl_internal.h
+++ b/net/devlink/devl_internal.h
@@ -191,11 +191,41 @@ static inline bool devlink_nl_notify_need(struct devlink *devlink)
 				  DEVLINK_MCGRP_CONFIG);
 }
 
+struct devlink_obj_desc {
+	struct rcu_head rcu;
+	const char *bus_name;
+	const char *dev_name;
+	long data[];
+};
+
+static inline void devlink_nl_obj_desc_init(struct devlink_obj_desc *desc,
+					    struct devlink *devlink)
+{
+	memset(desc, 0, sizeof(*desc));
+	desc->bus_name = devlink->dev->bus->name;
+	desc->dev_name = dev_name(devlink->dev);
+}
+
+int devlink_nl_notify_filter(struct sock *dsk, struct sk_buff *skb, void *data);
+
+static inline void devlink_nl_notify_send_desc(struct devlink *devlink,
+					       struct sk_buff *msg,
+					       struct devlink_obj_desc *desc)
+{
+	genlmsg_multicast_netns_filtered(&devlink_nl_family,
+					 devlink_net(devlink),
+					 msg, 0, DEVLINK_MCGRP_CONFIG,
+					 GFP_KERNEL,
+					 devlink_nl_notify_filter, desc);
+}
+
 static inline void devlink_nl_notify_send(struct devlink *devlink,
 					  struct sk_buff *msg)
 {
-	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
-				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+	struct devlink_obj_desc desc;
+
+	devlink_nl_obj_desc_init(&desc, devlink);
+	devlink_nl_notify_send_desc(devlink, msg, &desc);
 }
 
 /* Notify */
diff --git a/net/devlink/netlink.c b/net/devlink/netlink.c
index fa9afe3e6d9b..3176be2585cb 100644
--- a/net/devlink/netlink.c
+++ b/net/devlink/netlink.c
@@ -17,6 +17,111 @@ static const struct genl_multicast_group devlink_nl_mcgrps[] = {
 	[DEVLINK_MCGRP_CONFIG] = { .name = DEVLINK_GENL_MCGRP_CONFIG_NAME },
 };
 
+struct devlink_nl_sock_priv {
+	struct devlink_obj_desc __rcu *flt;
+	spinlock_t flt_lock; /* Protects flt. */
+};
+
+static void devlink_nl_sock_priv_init(void *priv)
+{
+	struct devlink_nl_sock_priv *sk_priv = priv;
+
+	spin_lock_init(&sk_priv->flt_lock);
+}
+
+static void devlink_nl_sock_priv_destroy(void *priv)
+{
+	struct devlink_nl_sock_priv *sk_priv = priv;
+	struct devlink_obj_desc *flt;
+
+	flt = rcu_dereference_protected(sk_priv->flt, true);
+	kfree_rcu(flt, rcu);
+}
+
+int devlink_nl_notify_filter_set_doit(struct sk_buff *skb,
+				      struct genl_info *info)
+{
+	struct devlink_nl_sock_priv *sk_priv;
+	struct nlattr **attrs = info->attrs;
+	struct devlink_obj_desc *flt;
+	size_t data_offset = 0;
+	size_t data_size = 0;
+	char *pos;
+
+	if (attrs[DEVLINK_ATTR_BUS_NAME])
+		data_size = size_add(data_size,
+				     nla_len(attrs[DEVLINK_ATTR_BUS_NAME]) + 1);
+	if (attrs[DEVLINK_ATTR_DEV_NAME])
+		data_size = size_add(data_size,
+				     nla_len(attrs[DEVLINK_ATTR_DEV_NAME]) + 1);
+
+	flt = kzalloc(size_add(sizeof(*flt), data_size), GFP_KERNEL);
+	if (!flt)
+		return -ENOMEM;
+
+	pos = (char *) flt->data;
+	if (attrs[DEVLINK_ATTR_BUS_NAME]) {
+		data_offset += nla_strscpy(pos,
+					   attrs[DEVLINK_ATTR_BUS_NAME],
+					   data_size) + 1;
+		flt->bus_name = pos;
+		pos += data_offset;
+	}
+	if (attrs[DEVLINK_ATTR_DEV_NAME]) {
+		nla_strscpy(pos, attrs[DEVLINK_ATTR_DEV_NAME],
+			    data_size - data_offset);
+		flt->dev_name = pos;
+	}
+
+	/* Don't attach empty filter. */
+	if (!flt->bus_name && !flt->dev_name) {
+		kfree(flt);
+		flt = NULL;
+	}
+
+	sk_priv = genl_sk_priv_get(&devlink_nl_family, NETLINK_CB(skb).sk);
+	if (IS_ERR(sk_priv)) {
+		kfree(flt);
+		return PTR_ERR(sk_priv);
+	}
+	spin_lock(&sk_priv->flt_lock);
+	flt = rcu_replace_pointer(sk_priv->flt, flt,
+				  lockdep_is_held(&sk_priv->flt_lock));
+	spin_unlock(&sk_priv->flt_lock);
+	kfree_rcu(flt, rcu);
+	return 0;
+}
+
+static bool devlink_obj_desc_match(const struct devlink_obj_desc *desc,
+				   const struct devlink_obj_desc *flt)
+{
+	if (desc->bus_name && flt->bus_name &&
+	    strcmp(desc->bus_name, flt->bus_name))
+		return false;
+	if (desc->dev_name && flt->dev_name &&
+	    strcmp(desc->dev_name, flt->dev_name))
+		return false;
+	return true;
+}
+
+int devlink_nl_notify_filter(struct sock *dsk, struct sk_buff *skb, void *data)
+{
+	struct devlink_obj_desc *desc = data;
+	struct devlink_nl_sock_priv *sk_priv;
+	struct devlink_obj_desc *flt;
+	int ret = 0;
+
+	rcu_read_lock();
+	sk_priv = __genl_sk_priv_get(&devlink_nl_family, dsk);
+	if (!IS_ERR_OR_NULL(sk_priv)) {
+		flt = rcu_dereference(sk_priv->flt);
+		if (flt)
+			ret = !devlink_obj_desc_match(desc, flt);
+	}
+	rcu_read_unlock();
+	return ret;
+}
+
 int devlink_nl_put_nested_handle(struct sk_buff *msg, struct net *net,
 				 struct devlink *devlink, int attrtype)
 {
@@ -256,4 +361,7 @@ struct genl_family devlink_nl_family __ro_after_init = {
 	.resv_start_op	= DEVLINK_CMD_SELFTESTS_RUN + 1,
 	.mcgrps		= devlink_nl_mcgrps,
 	.n_mcgrps	= ARRAY_SIZE(devlink_nl_mcgrps),
+	.sock_priv_size		= sizeof(struct devlink_nl_sock_priv),
+	.sock_priv_init		= devlink_nl_sock_priv_init,
+	.sock_priv_destroy	= devlink_nl_sock_priv_destroy,
 };
diff --git a/net/devlink/netlink_gen.c b/net/devlink/netlink_gen.c
index 95f9b4350ab7..1cb0e05305d2 100644
--- a/net/devlink/netlink_gen.c
+++ b/net/devlink/netlink_gen.c
@@ -560,8 +560,14 @@ static const struct nla_policy devlink_selftests_run_nl_policy[DEVLINK_ATTR_SELF
 	[DEVLINK_ATTR_SELFTESTS] = NLA_POLICY_NESTED(devlink_dl_selftest_id_nl_policy),
 };
 
+/* DEVLINK_CMD_NOTIFY_FILTER_SET - do */
+static const struct nla_policy devlink_notify_filter_set_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = {
+	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, },
+	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, },
+};
+
 /* Ops table for devlink */
-const struct genl_split_ops devlink_nl_ops[73] = {
+const struct genl_split_ops devlink_nl_ops[74] = {
 	{
 		.cmd		= DEVLINK_CMD_GET,
 		.validate	= GENL_DONT_VALIDATE_STRICT,
@@ -1233,4 +1239,11 @@ const struct genl_split_ops devlink_nl_ops[73] = {
 		.maxattr	= DEVLINK_ATTR_SELFTESTS,
 		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
 	},
+	{
+		.cmd		= DEVLINK_CMD_NOTIFY_FILTER_SET,
+		.doit		= devlink_nl_notify_filter_set_doit,
+		.policy		= devlink_notify_filter_set_nl_policy,
+		.maxattr	= DEVLINK_ATTR_DEV_NAME,
+		.flags		= GENL_CMD_CAP_DO,
+	},
 };
diff --git a/net/devlink/netlink_gen.h b/net/devlink/netlink_gen.h
index 02f3c0bfae0e..8f2bd50ddf5e 100644
--- a/net/devlink/netlink_gen.h
+++ b/net/devlink/netlink_gen.h
@@ -16,7 +16,7 @@ extern const struct nla_policy devlink_dl_port_function_nl_policy[DEVLINK_PORT_F
 extern const struct nla_policy devlink_dl_selftest_id_nl_policy[DEVLINK_ATTR_SELFTEST_ID_FLASH + 1];
 
 /* Ops table for devlink */
-extern const struct genl_split_ops devlink_nl_ops[73];
+extern const struct genl_split_ops devlink_nl_ops[74];
 
 int devlink_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
 			struct genl_info *info);
@@ -142,5 +142,7 @@ int devlink_nl_selftests_get_doit(struct sk_buff *skb, struct genl_info *info);
 int devlink_nl_selftests_get_dumpit(struct sk_buff *skb,
 				    struct netlink_callback *cb);
 int devlink_nl_selftests_run_doit(struct sk_buff *skb, struct genl_info *info);
+int devlink_nl_notify_filter_set_doit(struct sk_buff *skb,
+				      struct genl_info *info);
 
 #endif /* _LINUX_DEVLINK_GEN_H */
-- 
cgit v1.2.3


From 67ba055dd7758c34f6e64c9d35132362c1e1f0b5 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 19 Dec 2023 17:40:12 +0200
Subject: regulator: Reuse LINEAR_RANGE() in REGULATOR_LINEAR_RANGE()

REGULATOR_LINEAR_RANGE() repeats what LINEAR_RANGE() provides.
Deduplicate the former by using the latter. No functional change
intended.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://msgid.link/r/20231219154012.2478688-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/regulator/driver.h | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h
index 4b7eceb3828b..22a07c0900a4 100644
--- a/include/linux/regulator/driver.h
+++ b/include/linux/regulator/driver.h
@@ -51,12 +51,7 @@ enum regulator_detection_severity {
 
 /* Initialize struct linear_range for regulators */
 #define REGULATOR_LINEAR_RANGE(_min_uV, _min_sel, _max_sel, _step_uV)	\
-{									\
-	.min		= _min_uV,					\
-	.min_sel	= _min_sel,					\
-	.max_sel	= _max_sel,					\
-	.step		= _step_uV,					\
-}
+	LINEAR_RANGE(_min_uV, _min_sel, _max_sel, _step_uV)
 
 /**
  * struct regulator_ops - regulator operations.
-- 
cgit v1.2.3


From d17aff807f845cf93926c28705216639c7279110 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 19 Dec 2023 07:37:35 -0800
Subject: Revert BPF token-related functionality

This patch includes the following revert (one  conflicting BPF FS
patch and three token patch sets, represented by merge commits):
  - revert 0f5d5454c723 "Merge branch 'bpf-fs-mount-options-parsing-follow-ups'";
  - revert 750e785796bb "bpf: Support uid and gid when mounting bpffs";
  - revert 733763285acf "Merge branch 'bpf-token-support-in-libbpf-s-bpf-object'";
  - revert c35919dcce28 "Merge branch 'bpf-token-and-bpf-fs-based-delegation'".

Link: https://lore.kernel.org/bpf/CAHk-=wg7JuFYwGy=GOMbRCtOL+jwSQsdUaBsRWkDVYbxipbM5A@mail.gmail.com
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
---
 drivers/media/rc/bpf-lirc.c                        |    2 +-
 include/linux/bpf.h                                |   85 +-
 include/linux/filter.h                             |    2 +-
 include/linux/lsm_hook_defs.h                      |   15 +-
 include/linux/security.h                           |   43 +-
 include/uapi/linux/bpf.h                           |   42 -
 kernel/bpf/Makefile                                |    2 +-
 kernel/bpf/arraymap.c                              |    2 +-
 kernel/bpf/bpf_lsm.c                               |   15 +-
 kernel/bpf/cgroup.c                                |    6 +-
 kernel/bpf/core.c                                  |    3 +-
 kernel/bpf/helpers.c                               |    6 +-
 kernel/bpf/inode.c                                 |  326 +------
 kernel/bpf/syscall.c                               |  215 ++--
 kernel/bpf/token.c                                 |  271 -----
 kernel/bpf/verifier.c                              |   13 +-
 kernel/trace/bpf_trace.c                           |    2 +-
 net/core/filter.c                                  |   36 +-
 net/ipv4/bpf_tcp_ca.c                              |    2 +-
 net/netfilter/nf_bpf_link.c                        |    2 +-
 security/security.c                                |  101 +-
 security/selinux/hooks.c                           |   47 +-
 tools/include/uapi/linux/bpf.h                     |   42 -
 tools/lib/bpf/Build                                |    2 +-
 tools/lib/bpf/bpf.c                                |   37 +-
 tools/lib/bpf/bpf.h                                |   35 +-
 tools/lib/bpf/btf.c                                |    7 +-
 tools/lib/bpf/elf.c                                |    2 +
 tools/lib/bpf/features.c                           |  478 ---------
 tools/lib/bpf/libbpf.c                             |  573 ++++++++---
 tools/lib/bpf/libbpf.h                             |   37 +-
 tools/lib/bpf/libbpf.map                           |    1 -
 tools/lib/bpf/libbpf_internal.h                    |   36 +-
 tools/lib/bpf/libbpf_probes.c                      |    8 +-
 tools/lib/bpf/str_error.h                          |    3 -
 .../selftests/bpf/prog_tests/libbpf_probes.c       |    4 -
 .../testing/selftests/bpf/prog_tests/libbpf_str.c  |    6 -
 tools/testing/selftests/bpf/prog_tests/token.c     | 1031 --------------------
 tools/testing/selftests/bpf/progs/priv_map.c       |   13 -
 tools/testing/selftests/bpf/progs/priv_prog.c      |   13 -
 40 files changed, 641 insertions(+), 2925 deletions(-)
 delete mode 100644 kernel/bpf/token.c
 delete mode 100644 tools/lib/bpf/features.c
 delete mode 100644 tools/testing/selftests/bpf/prog_tests/token.c
 delete mode 100644 tools/testing/selftests/bpf/progs/priv_map.c
 delete mode 100644 tools/testing/selftests/bpf/progs/priv_prog.c

(limited to 'include')

diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c
index 6d07693c6b9f..fe17c7f98e81 100644
--- a/drivers/media/rc/bpf-lirc.c
+++ b/drivers/media/rc/bpf-lirc.c
@@ -110,7 +110,7 @@ lirc_mode2_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_get_prandom_u32:
 		return &bpf_get_prandom_u32_proto;
 	case BPF_FUNC_trace_printk:
-		if (bpf_token_capable(prog->aux->token, CAP_PERFMON))
+		if (perfmon_capable())
 			return bpf_get_trace_printk_proto();
 		fallthrough;
 	default:
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 2f54cc0436c4..7a8d4c81a39a 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -52,10 +52,6 @@ struct module;
 struct bpf_func_state;
 struct ftrace_ops;
 struct cgroup;
-struct bpf_token;
-struct user_namespace;
-struct super_block;
-struct inode;
 
 extern struct idr btf_idr;
 extern spinlock_t btf_idr_lock;
@@ -1488,7 +1484,6 @@ struct bpf_prog_aux {
 #ifdef CONFIG_SECURITY
 	void *security;
 #endif
-	struct bpf_token *token;
 	struct bpf_prog_offload *offload;
 	struct btf *btf;
 	struct bpf_func_info *func_info;
@@ -1613,31 +1608,6 @@ struct bpf_link_primer {
 	u32 id;
 };
 
-struct bpf_mount_opts {
-	kuid_t uid;
-	kgid_t gid;
-	umode_t mode;
-
-	/* BPF token-related delegation options */
-	u64 delegate_cmds;
-	u64 delegate_maps;
-	u64 delegate_progs;
-	u64 delegate_attachs;
-};
-
-struct bpf_token {
-	struct work_struct work;
-	atomic64_t refcnt;
-	struct user_namespace *userns;
-	u64 allowed_cmds;
-	u64 allowed_maps;
-	u64 allowed_progs;
-	u64 allowed_attachs;
-#ifdef CONFIG_SECURITY
-	void *security;
-#endif
-};
-
 struct bpf_struct_ops_value;
 struct btf_member;
 
@@ -2097,7 +2067,6 @@ static inline void bpf_enable_instrumentation(void)
 	migrate_enable();
 }
 
-extern const struct super_operations bpf_super_ops;
 extern const struct file_operations bpf_map_fops;
 extern const struct file_operations bpf_prog_fops;
 extern const struct file_operations bpf_iter_fops;
@@ -2232,26 +2201,24 @@ static inline void bpf_map_dec_elem_count(struct bpf_map *map)
 
 extern int sysctl_unprivileged_bpf_disabled;
 
-bool bpf_token_capable(const struct bpf_token *token, int cap);
-
-static inline bool bpf_allow_ptr_leaks(const struct bpf_token *token)
+static inline bool bpf_allow_ptr_leaks(void)
 {
-	return bpf_token_capable(token, CAP_PERFMON);
+	return perfmon_capable();
 }
 
-static inline bool bpf_allow_uninit_stack(const struct bpf_token *token)
+static inline bool bpf_allow_uninit_stack(void)
 {
-	return bpf_token_capable(token, CAP_PERFMON);
+	return perfmon_capable();
 }
 
-static inline bool bpf_bypass_spec_v1(const struct bpf_token *token)
+static inline bool bpf_bypass_spec_v1(void)
 {
-	return cpu_mitigations_off() || bpf_token_capable(token, CAP_PERFMON);
+	return cpu_mitigations_off() || perfmon_capable();
 }
 
-static inline bool bpf_bypass_spec_v4(const struct bpf_token *token)
+static inline bool bpf_bypass_spec_v4(void)
 {
-	return cpu_mitigations_off() || bpf_token_capable(token, CAP_PERFMON);
+	return cpu_mitigations_off() || perfmon_capable();
 }
 
 int bpf_map_new_fd(struct bpf_map *map, int flags);
@@ -2268,21 +2235,8 @@ int bpf_link_new_fd(struct bpf_link *link);
 struct bpf_link *bpf_link_get_from_fd(u32 ufd);
 struct bpf_link *bpf_link_get_curr_or_next(u32 *id);
 
-void bpf_token_inc(struct bpf_token *token);
-void bpf_token_put(struct bpf_token *token);
-int bpf_token_create(union bpf_attr *attr);
-struct bpf_token *bpf_token_get_from_fd(u32 ufd);
-
-bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd);
-bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type);
-bool bpf_token_allow_prog_type(const struct bpf_token *token,
-			       enum bpf_prog_type prog_type,
-			       enum bpf_attach_type attach_type);
-
 int bpf_obj_pin_user(u32 ufd, int path_fd, const char __user *pathname);
 int bpf_obj_get_user(int path_fd, const char __user *pathname, int flags);
-struct inode *bpf_get_inode(struct super_block *sb, const struct inode *dir,
-			    umode_t mode);
 
 #define BPF_ITER_FUNC_PREFIX "bpf_iter_"
 #define DEFINE_BPF_ITER_FUNC(target, args...)			\
@@ -2526,8 +2480,7 @@ const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type
 struct bpf_prog *bpf_prog_by_id(u32 id);
 struct bpf_link *bpf_link_by_id(u32 id);
 
-const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id,
-						 const struct bpf_prog *prog);
+const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id);
 void bpf_task_storage_free(struct task_struct *task);
 void bpf_cgrp_storage_free(struct cgroup *cgroup);
 bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog);
@@ -2646,24 +2599,6 @@ static inline int bpf_obj_get_user(const char __user *pathname, int flags)
 	return -EOPNOTSUPP;
 }
 
-static inline bool bpf_token_capable(const struct bpf_token *token, int cap)
-{
-	return capable(cap) || (cap != CAP_SYS_ADMIN && capable(CAP_SYS_ADMIN));
-}
-
-static inline void bpf_token_inc(struct bpf_token *token)
-{
-}
-
-static inline void bpf_token_put(struct bpf_token *token)
-{
-}
-
-static inline struct bpf_token *bpf_token_get_from_fd(u32 ufd)
-{
-	return ERR_PTR(-EOPNOTSUPP);
-}
-
 static inline void __dev_flush(void)
 {
 }
@@ -2787,7 +2722,7 @@ static inline int btf_struct_access(struct bpf_verifier_log *log,
 }
 
 static inline const struct bpf_func_proto *
-bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+bpf_base_func_proto(enum bpf_func_id func_id)
 {
 	return NULL;
 }
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 12d907f17d36..68fb6c8142fe 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1139,7 +1139,7 @@ static inline bool bpf_jit_blinding_enabled(struct bpf_prog *prog)
 		return false;
 	if (!bpf_jit_harden)
 		return false;
-	if (bpf_jit_harden == 1 && bpf_token_capable(prog->aux->token, CAP_BPF))
+	if (bpf_jit_harden == 1 && bpf_capable())
 		return false;
 
 	return true;
diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index 3fdd00b452ac..ff217a5ce552 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -398,17 +398,10 @@ LSM_HOOK(void, LSM_RET_VOID, audit_rule_free, void *lsmrule)
 LSM_HOOK(int, 0, bpf, int cmd, union bpf_attr *attr, unsigned int size)
 LSM_HOOK(int, 0, bpf_map, struct bpf_map *map, fmode_t fmode)
 LSM_HOOK(int, 0, bpf_prog, struct bpf_prog *prog)
-LSM_HOOK(int, 0, bpf_map_create, struct bpf_map *map, union bpf_attr *attr,
-	 struct bpf_token *token)
-LSM_HOOK(void, LSM_RET_VOID, bpf_map_free, struct bpf_map *map)
-LSM_HOOK(int, 0, bpf_prog_load, struct bpf_prog *prog, union bpf_attr *attr,
-	 struct bpf_token *token)
-LSM_HOOK(void, LSM_RET_VOID, bpf_prog_free, struct bpf_prog *prog)
-LSM_HOOK(int, 0, bpf_token_create, struct bpf_token *token, union bpf_attr *attr,
-	 struct path *path)
-LSM_HOOK(void, LSM_RET_VOID, bpf_token_free, struct bpf_token *token)
-LSM_HOOK(int, 0, bpf_token_cmd, const struct bpf_token *token, enum bpf_cmd cmd)
-LSM_HOOK(int, 0, bpf_token_capable, const struct bpf_token *token, int cap)
+LSM_HOOK(int, 0, bpf_map_alloc_security, struct bpf_map *map)
+LSM_HOOK(void, LSM_RET_VOID, bpf_map_free_security, struct bpf_map *map)
+LSM_HOOK(int, 0, bpf_prog_alloc_security, struct bpf_prog_aux *aux)
+LSM_HOOK(void, LSM_RET_VOID, bpf_prog_free_security, struct bpf_prog_aux *aux)
 #endif /* CONFIG_BPF_SYSCALL */
 
 LSM_HOOK(int, 0, locked_down, enum lockdown_reason what)
diff --git a/include/linux/security.h b/include/linux/security.h
index 00809d2d5c38..1d1df326c881 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -32,7 +32,6 @@
 #include <linux/string.h>
 #include <linux/mm.h>
 #include <linux/sockptr.h>
-#include <linux/bpf.h>
 
 struct linux_binprm;
 struct cred;
@@ -2021,22 +2020,15 @@ static inline void securityfs_remove(struct dentry *dentry)
 union bpf_attr;
 struct bpf_map;
 struct bpf_prog;
-struct bpf_token;
+struct bpf_prog_aux;
 #ifdef CONFIG_SECURITY
 extern int security_bpf(int cmd, union bpf_attr *attr, unsigned int size);
 extern int security_bpf_map(struct bpf_map *map, fmode_t fmode);
 extern int security_bpf_prog(struct bpf_prog *prog);
-extern int security_bpf_map_create(struct bpf_map *map, union bpf_attr *attr,
-				   struct bpf_token *token);
+extern int security_bpf_map_alloc(struct bpf_map *map);
 extern void security_bpf_map_free(struct bpf_map *map);
-extern int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr,
-				  struct bpf_token *token);
-extern void security_bpf_prog_free(struct bpf_prog *prog);
-extern int security_bpf_token_create(struct bpf_token *token, union bpf_attr *attr,
-				     struct path *path);
-extern void security_bpf_token_free(struct bpf_token *token);
-extern int security_bpf_token_cmd(const struct bpf_token *token, enum bpf_cmd cmd);
-extern int security_bpf_token_capable(const struct bpf_token *token, int cap);
+extern int security_bpf_prog_alloc(struct bpf_prog_aux *aux);
+extern void security_bpf_prog_free(struct bpf_prog_aux *aux);
 #else
 static inline int security_bpf(int cmd, union bpf_attr *attr,
 					     unsigned int size)
@@ -2054,8 +2046,7 @@ static inline int security_bpf_prog(struct bpf_prog *prog)
 	return 0;
 }
 
-static inline int security_bpf_map_create(struct bpf_map *map, union bpf_attr *attr,
-					  struct bpf_token *token)
+static inline int security_bpf_map_alloc(struct bpf_map *map)
 {
 	return 0;
 }
@@ -2063,33 +2054,13 @@ static inline int security_bpf_map_create(struct bpf_map *map, union bpf_attr *a
 static inline void security_bpf_map_free(struct bpf_map *map)
 { }
 
-static inline int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr,
-					 struct bpf_token *token)
+static inline int security_bpf_prog_alloc(struct bpf_prog_aux *aux)
 {
 	return 0;
 }
 
-static inline void security_bpf_prog_free(struct bpf_prog *prog)
+static inline void security_bpf_prog_free(struct bpf_prog_aux *aux)
 { }
-
-static inline int security_bpf_token_create(struct bpf_token *token, union bpf_attr *attr,
-				     struct path *path)
-{
-	return 0;
-}
-
-static inline void security_bpf_token_free(struct bpf_token *token)
-{ }
-
-static inline int security_bpf_token_cmd(const struct bpf_token *token, enum bpf_cmd cmd)
-{
-	return 0;
-}
-
-static inline int security_bpf_token_capable(const struct bpf_token *token, int cap)
-{
-	return 0;
-}
 #endif /* CONFIG_SECURITY */
 #endif /* CONFIG_BPF_SYSCALL */
 
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 42f4d3090efe..754e68ca8744 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -847,36 +847,6 @@ union bpf_iter_link_info {
  *		Returns zero on success. On error, -1 is returned and *errno*
  *		is set appropriately.
  *
- * BPF_TOKEN_CREATE
- *	Description
- *		Create BPF token with embedded information about what
- *		BPF-related functionality it allows:
- *		- a set of allowed bpf() syscall commands;
- *		- a set of allowed BPF map types to be created with
- *		BPF_MAP_CREATE command, if BPF_MAP_CREATE itself is allowed;
- *		- a set of allowed BPF program types and BPF program attach
- *		types to be loaded with BPF_PROG_LOAD command, if
- *		BPF_PROG_LOAD itself is allowed.
- *
- *		BPF token is created (derived) from an instance of BPF FS,
- *		assuming it has necessary delegation mount options specified.
- *		This BPF token can be passed as an extra parameter to various
- *		bpf() syscall commands to grant BPF subsystem functionality to
- *		unprivileged processes.
- *
- *		When created, BPF token is "associated" with the owning
- *		user namespace of BPF FS instance (super block) that it was
- *		derived from, and subsequent BPF operations performed with
- *		BPF token would be performing capabilities checks (i.e.,
- *		CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN, CAP_SYS_ADMIN) within
- *		that user namespace. Without BPF token, such capabilities
- *		have to be granted in init user namespace, making bpf()
- *		syscall incompatible with user namespace, for the most part.
- *
- *	Return
- *		A new file descriptor (a nonnegative integer), or -1 if an
- *		error occurred (in which case, *errno* is set appropriately).
- *
  * NOTES
  *	eBPF objects (maps and programs) can be shared between processes.
  *
@@ -931,8 +901,6 @@ enum bpf_cmd {
 	BPF_ITER_CREATE,
 	BPF_LINK_DETACH,
 	BPF_PROG_BIND_MAP,
-	BPF_TOKEN_CREATE,
-	__MAX_BPF_CMD,
 };
 
 enum bpf_map_type {
@@ -983,7 +951,6 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_BLOOM_FILTER,
 	BPF_MAP_TYPE_USER_RINGBUF,
 	BPF_MAP_TYPE_CGRP_STORAGE,
-	__MAX_BPF_MAP_TYPE
 };
 
 /* Note that tracing related programs such as
@@ -1028,7 +995,6 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_SK_LOOKUP,
 	BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */
 	BPF_PROG_TYPE_NETFILTER,
-	__MAX_BPF_PROG_TYPE
 };
 
 enum bpf_attach_type {
@@ -1437,7 +1403,6 @@ union bpf_attr {
 		 * to using 5 hash functions).
 		 */
 		__u64	map_extra;
-		__u32	map_token_fd;
 	};
 
 	struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -1507,7 +1472,6 @@ union bpf_attr {
 		 * truncated), or smaller (if log buffer wasn't filled completely).
 		 */
 		__u32		log_true_size;
-		__u32		prog_token_fd;
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -1620,7 +1584,6 @@ union bpf_attr {
 		 * truncated), or smaller (if log buffer wasn't filled completely).
 		 */
 		__u32		btf_log_true_size;
-		__u32		btf_token_fd;
 	};
 
 	struct {
@@ -1751,11 +1714,6 @@ union bpf_attr {
 		__u32		flags;		/* extra flags */
 	} prog_bind_map;
 
-	struct { /* struct used by BPF_TOKEN_CREATE command */
-		__u32		flags;
-		__u32		bpffs_fd;
-	} token_create;
-
 } __attribute__((aligned(8)));
 
 /* The description below is an attempt at providing documentation to eBPF
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 4ce95acfcaa7..f526b7573e97 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -6,7 +6,7 @@ cflags-nogcse-$(CONFIG_X86)$(CONFIG_CC_IS_GCC) := -fno-gcse
 endif
 CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy)
 
-obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o log.o token.o
+obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o log.o
 obj-$(CONFIG_BPF_SYSCALL) += bpf_iter.o map_iter.o task_iter.o prog_iter.o link_iter.o
 obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o bloom_filter.o
 obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 13358675ff2e..0bdbbbeab155 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -82,7 +82,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 	bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY;
 	int numa_node = bpf_map_attr_numa_node(attr);
 	u32 elem_size, index_mask, max_entries;
-	bool bypass_spec_v1 = bpf_bypass_spec_v1(NULL);
+	bool bypass_spec_v1 = bpf_bypass_spec_v1();
 	u64 array_size, mask64;
 	struct bpf_array *array;
 
diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c
index 63b4dc495125..e8e910395bf6 100644
--- a/kernel/bpf/bpf_lsm.c
+++ b/kernel/bpf/bpf_lsm.c
@@ -260,15 +260,9 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 BTF_SET_START(sleepable_lsm_hooks)
 BTF_ID(func, bpf_lsm_bpf)
 BTF_ID(func, bpf_lsm_bpf_map)
-BTF_ID(func, bpf_lsm_bpf_map_create)
-BTF_ID(func, bpf_lsm_bpf_map_free)
+BTF_ID(func, bpf_lsm_bpf_map_alloc_security)
+BTF_ID(func, bpf_lsm_bpf_map_free_security)
 BTF_ID(func, bpf_lsm_bpf_prog)
-BTF_ID(func, bpf_lsm_bpf_prog_load)
-BTF_ID(func, bpf_lsm_bpf_prog_free)
-BTF_ID(func, bpf_lsm_bpf_token_create)
-BTF_ID(func, bpf_lsm_bpf_token_free)
-BTF_ID(func, bpf_lsm_bpf_token_cmd)
-BTF_ID(func, bpf_lsm_bpf_token_capable)
 BTF_ID(func, bpf_lsm_bprm_check_security)
 BTF_ID(func, bpf_lsm_bprm_committed_creds)
 BTF_ID(func, bpf_lsm_bprm_committing_creds)
@@ -363,8 +357,9 @@ BTF_ID(func, bpf_lsm_userns_create)
 BTF_SET_END(sleepable_lsm_hooks)
 
 BTF_SET_START(untrusted_lsm_hooks)
-BTF_ID(func, bpf_lsm_bpf_map_free)
-BTF_ID(func, bpf_lsm_bpf_prog_free)
+BTF_ID(func, bpf_lsm_bpf_map_free_security)
+BTF_ID(func, bpf_lsm_bpf_prog_alloc_security)
+BTF_ID(func, bpf_lsm_bpf_prog_free_security)
 BTF_ID(func, bpf_lsm_file_alloc_security)
 BTF_ID(func, bpf_lsm_file_free_security)
 #ifdef CONFIG_SECURITY_NETWORK
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 98e0e3835b28..491d20038cbe 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -1630,7 +1630,7 @@ cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_perf_event_output:
 		return &bpf_event_output_data_proto;
 	default:
-		return bpf_base_func_proto(func_id, prog);
+		return bpf_base_func_proto(func_id);
 	}
 }
 
@@ -2191,7 +2191,7 @@ sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_perf_event_output:
 		return &bpf_event_output_data_proto;
 	default:
-		return bpf_base_func_proto(func_id, prog);
+		return bpf_base_func_proto(func_id);
 	}
 }
 
@@ -2348,7 +2348,7 @@ cg_sockopt_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_perf_event_output:
 		return &bpf_event_output_data_proto;
 	default:
-		return bpf_base_func_proto(func_id, prog);
+		return bpf_base_func_proto(func_id);
 	}
 }
 
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 14ace23d517b..ea6843be2616 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -682,7 +682,7 @@ static bool bpf_prog_kallsyms_candidate(const struct bpf_prog *fp)
 void bpf_prog_kallsyms_add(struct bpf_prog *fp)
 {
 	if (!bpf_prog_kallsyms_candidate(fp) ||
-	    !bpf_token_capable(fp->aux->token, CAP_BPF))
+	    !bpf_capable())
 		return;
 
 	bpf_prog_ksym_set_addr(fp);
@@ -2779,7 +2779,6 @@ void bpf_prog_free(struct bpf_prog *fp)
 
 	if (aux->dst_prog)
 		bpf_prog_put(aux->dst_prog);
-	bpf_token_put(aux->token);
 	INIT_WORK(&aux->work, bpf_prog_free_deferred);
 	schedule_work(&aux->work);
 }
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 07fd4b5704f3..be72824f32b2 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1679,7 +1679,7 @@ const struct bpf_func_proto bpf_probe_read_kernel_str_proto __weak;
 const struct bpf_func_proto bpf_task_pt_regs_proto __weak;
 
 const struct bpf_func_proto *
-bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+bpf_base_func_proto(enum bpf_func_id func_id)
 {
 	switch (func_id) {
 	case BPF_FUNC_map_lookup_elem:
@@ -1730,7 +1730,7 @@ bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		break;
 	}
 
-	if (!bpf_token_capable(prog->aux->token, CAP_BPF))
+	if (!bpf_capable())
 		return NULL;
 
 	switch (func_id) {
@@ -1788,7 +1788,7 @@ bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		break;
 	}
 
-	if (!bpf_token_capable(prog->aux->token, CAP_PERFMON))
+	if (!perfmon_capable())
 		return NULL;
 
 	switch (func_id) {
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 4383b3d13a55..1aafb2ff2e95 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -20,7 +20,6 @@
 #include <linux/filter.h>
 #include <linux/bpf.h>
 #include <linux/bpf_trace.h>
-#include <linux/kstrtox.h>
 #include "preload/bpf_preload.h"
 
 enum bpf_type {
@@ -99,9 +98,9 @@ static const struct inode_operations bpf_prog_iops = { };
 static const struct inode_operations bpf_map_iops  = { };
 static const struct inode_operations bpf_link_iops  = { };
 
-struct inode *bpf_get_inode(struct super_block *sb,
-			    const struct inode *dir,
-			    umode_t mode)
+static struct inode *bpf_get_inode(struct super_block *sb,
+				   const struct inode *dir,
+				   umode_t mode)
 {
 	struct inode *inode;
 
@@ -595,183 +594,15 @@ struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type typ
 }
 EXPORT_SYMBOL(bpf_prog_get_type_path);
 
-struct bpffs_btf_enums {
-	const struct btf *btf;
-	const struct btf_type *cmd_t;
-	const struct btf_type *map_t;
-	const struct btf_type *prog_t;
-	const struct btf_type *attach_t;
-};
-
-static int find_bpffs_btf_enums(struct bpffs_btf_enums *info)
-{
-	const struct btf *btf;
-	const struct btf_type *t;
-	const char *name;
-	int i, n;
-
-	memset(info, 0, sizeof(*info));
-
-	btf = bpf_get_btf_vmlinux();
-	if (IS_ERR(btf))
-		return PTR_ERR(btf);
-	if (!btf)
-		return -ENOENT;
-
-	info->btf = btf;
-
-	for (i = 1, n = btf_nr_types(btf); i < n; i++) {
-		t = btf_type_by_id(btf, i);
-		if (!btf_type_is_enum(t))
-			continue;
-
-		name = btf_name_by_offset(btf, t->name_off);
-		if (!name)
-			continue;
-
-		if (strcmp(name, "bpf_cmd") == 0)
-			info->cmd_t = t;
-		else if (strcmp(name, "bpf_map_type") == 0)
-			info->map_t = t;
-		else if (strcmp(name, "bpf_prog_type") == 0)
-			info->prog_t = t;
-		else if (strcmp(name, "bpf_attach_type") == 0)
-			info->attach_t = t;
-		else
-			continue;
-
-		if (info->cmd_t && info->map_t && info->prog_t && info->attach_t)
-			return 0;
-	}
-
-	return -ESRCH;
-}
-
-static bool find_btf_enum_const(const struct btf *btf, const struct btf_type *enum_t,
-				const char *prefix, const char *str, int *value)
-{
-	const struct btf_enum *e;
-	const char *name;
-	int i, n, pfx_len = strlen(prefix);
-
-	*value = 0;
-
-	if (!btf || !enum_t)
-		return false;
-
-	for (i = 0, n = btf_vlen(enum_t); i < n; i++) {
-		e = &btf_enum(enum_t)[i];
-
-		name = btf_name_by_offset(btf, e->name_off);
-		if (!name || strncasecmp(name, prefix, pfx_len) != 0)
-			continue;
-
-		/* match symbolic name case insensitive and ignoring prefix */
-		if (strcasecmp(name + pfx_len, str) == 0) {
-			*value = e->val;
-			return true;
-		}
-	}
-
-	return false;
-}
-
-static void seq_print_delegate_opts(struct seq_file *m,
-				    const char *opt_name,
-				    const struct btf *btf,
-				    const struct btf_type *enum_t,
-				    const char *prefix,
-				    u64 delegate_msk, u64 any_msk)
-{
-	const struct btf_enum *e;
-	bool first = true;
-	const char *name;
-	u64 msk;
-	int i, n, pfx_len = strlen(prefix);
-
-	delegate_msk &= any_msk; /* clear unknown bits */
-
-	if (delegate_msk == 0)
-		return;
-
-	seq_printf(m, ",%s", opt_name);
-	if (delegate_msk == any_msk) {
-		seq_printf(m, "=any");
-		return;
-	}
-
-	if (btf && enum_t) {
-		for (i = 0, n = btf_vlen(enum_t); i < n; i++) {
-			e = &btf_enum(enum_t)[i];
-			name = btf_name_by_offset(btf, e->name_off);
-			if (!name || strncasecmp(name, prefix, pfx_len) != 0)
-				continue;
-			msk = 1ULL << e->val;
-			if (delegate_msk & msk) {
-				/* emit lower-case name without prefix */
-				seq_printf(m, "%c", first ? '=' : ':');
-				name += pfx_len;
-				while (*name) {
-					seq_printf(m, "%c", tolower(*name));
-					name++;
-				}
-
-				delegate_msk &= ~msk;
-				first = false;
-			}
-		}
-	}
-	if (delegate_msk)
-		seq_printf(m, "%c0x%llx", first ? '=' : ':', delegate_msk);
-}
-
 /*
  * Display the mount options in /proc/mounts.
  */
 static int bpf_show_options(struct seq_file *m, struct dentry *root)
 {
-	struct bpf_mount_opts *opts = root->d_sb->s_fs_info;
-	struct inode *inode = d_inode(root);
-	umode_t mode = inode->i_mode & S_IALLUGO & ~S_ISVTX;
-	u64 mask;
-
-	if (!uid_eq(inode->i_uid, GLOBAL_ROOT_UID))
-		seq_printf(m, ",uid=%u",
-			   from_kuid_munged(&init_user_ns, inode->i_uid));
-	if (!gid_eq(inode->i_gid, GLOBAL_ROOT_GID))
-		seq_printf(m, ",gid=%u",
-			   from_kgid_munged(&init_user_ns, inode->i_gid));
+	umode_t mode = d_inode(root)->i_mode & S_IALLUGO & ~S_ISVTX;
+
 	if (mode != S_IRWXUGO)
 		seq_printf(m, ",mode=%o", mode);
-
-	if (opts->delegate_cmds || opts->delegate_maps ||
-	    opts->delegate_progs || opts->delegate_attachs) {
-		struct bpffs_btf_enums info;
-
-		/* ignore errors, fallback to hex */
-		(void)find_bpffs_btf_enums(&info);
-
-		mask = (1ULL << __MAX_BPF_CMD) - 1;
-		seq_print_delegate_opts(m, "delegate_cmds",
-					info.btf, info.cmd_t, "BPF_",
-					opts->delegate_cmds, mask);
-
-		mask = (1ULL << __MAX_BPF_MAP_TYPE) - 1;
-		seq_print_delegate_opts(m, "delegate_maps",
-					info.btf, info.map_t, "BPF_MAP_TYPE_",
-					opts->delegate_maps, mask);
-
-		mask = (1ULL << __MAX_BPF_PROG_TYPE) - 1;
-		seq_print_delegate_opts(m, "delegate_progs",
-					info.btf, info.prog_t, "BPF_PROG_TYPE_",
-					opts->delegate_progs, mask);
-
-		mask = (1ULL << __MAX_BPF_ATTACH_TYPE) - 1;
-		seq_print_delegate_opts(m, "delegate_attachs",
-					info.btf, info.attach_t, "BPF_",
-					opts->delegate_attachs, mask);
-	}
-
 	return 0;
 }
 
@@ -786,7 +617,7 @@ static void bpf_free_inode(struct inode *inode)
 	free_inode_nonrcu(inode);
 }
 
-const struct super_operations bpf_super_ops = {
+static const struct super_operations bpf_super_ops = {
 	.statfs		= simple_statfs,
 	.drop_inode	= generic_delete_inode,
 	.show_options	= bpf_show_options,
@@ -794,33 +625,23 @@ const struct super_operations bpf_super_ops = {
 };
 
 enum {
-	OPT_UID,
-	OPT_GID,
 	OPT_MODE,
-	OPT_DELEGATE_CMDS,
-	OPT_DELEGATE_MAPS,
-	OPT_DELEGATE_PROGS,
-	OPT_DELEGATE_ATTACHS,
 };
 
 static const struct fs_parameter_spec bpf_fs_parameters[] = {
-	fsparam_u32	("uid",				OPT_UID),
-	fsparam_u32	("gid",				OPT_GID),
 	fsparam_u32oct	("mode",			OPT_MODE),
-	fsparam_string	("delegate_cmds",		OPT_DELEGATE_CMDS),
-	fsparam_string	("delegate_maps",		OPT_DELEGATE_MAPS),
-	fsparam_string	("delegate_progs",		OPT_DELEGATE_PROGS),
-	fsparam_string	("delegate_attachs",		OPT_DELEGATE_ATTACHS),
 	{}
 };
 
+struct bpf_mount_opts {
+	umode_t mode;
+};
+
 static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param)
 {
-	struct bpf_mount_opts *opts = fc->s_fs_info;
+	struct bpf_mount_opts *opts = fc->fs_private;
 	struct fs_parse_result result;
-	kuid_t uid;
-	kgid_t gid;
-	int opt, err;
+	int opt;
 
 	opt = fs_parse(fc, bpf_fs_parameters, param, &result);
 	if (opt < 0) {
@@ -841,104 +662,12 @@ static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param)
 	}
 
 	switch (opt) {
-	case OPT_UID:
-		uid = make_kuid(current_user_ns(), result.uint_32);
-		if (!uid_valid(uid))
-			goto bad_value;
-
-		/*
-		 * The requested uid must be representable in the
-		 * filesystem's idmapping.
-		 */
-		if (!kuid_has_mapping(fc->user_ns, uid))
-			goto bad_value;
-
-		opts->uid = uid;
-		break;
-	case OPT_GID:
-		gid = make_kgid(current_user_ns(), result.uint_32);
-		if (!gid_valid(gid))
-			goto bad_value;
-
-		/*
-		 * The requested gid must be representable in the
-		 * filesystem's idmapping.
-		 */
-		if (!kgid_has_mapping(fc->user_ns, gid))
-			goto bad_value;
-
-		opts->gid = gid;
-		break;
 	case OPT_MODE:
 		opts->mode = result.uint_32 & S_IALLUGO;
 		break;
-	case OPT_DELEGATE_CMDS:
-	case OPT_DELEGATE_MAPS:
-	case OPT_DELEGATE_PROGS:
-	case OPT_DELEGATE_ATTACHS: {
-		struct bpffs_btf_enums info;
-		const struct btf_type *enum_t;
-		const char *enum_pfx;
-		u64 *delegate_msk, msk = 0;
-		char *p;
-		int val;
-
-		/* ignore errors, fallback to hex */
-		(void)find_bpffs_btf_enums(&info);
-
-		switch (opt) {
-		case OPT_DELEGATE_CMDS:
-			delegate_msk = &opts->delegate_cmds;
-			enum_t = info.cmd_t;
-			enum_pfx = "BPF_";
-			break;
-		case OPT_DELEGATE_MAPS:
-			delegate_msk = &opts->delegate_maps;
-			enum_t = info.map_t;
-			enum_pfx = "BPF_MAP_TYPE_";
-			break;
-		case OPT_DELEGATE_PROGS:
-			delegate_msk = &opts->delegate_progs;
-			enum_t = info.prog_t;
-			enum_pfx = "BPF_PROG_TYPE_";
-			break;
-		case OPT_DELEGATE_ATTACHS:
-			delegate_msk = &opts->delegate_attachs;
-			enum_t = info.attach_t;
-			enum_pfx = "BPF_";
-			break;
-		default:
-			return -EINVAL;
-		}
-
-		while ((p = strsep(&param->string, ":"))) {
-			if (strcmp(p, "any") == 0) {
-				msk |= ~0ULL;
-			} else if (find_btf_enum_const(info.btf, enum_t, enum_pfx, p, &val)) {
-				msk |= 1ULL << val;
-			} else {
-				err = kstrtou64(p, 0, &msk);
-				if (err)
-					return err;
-			}
-		}
-
-		/* Setting delegation mount options requires privileges */
-		if (msk && !capable(CAP_SYS_ADMIN))
-			return -EPERM;
-
-		*delegate_msk |= msk;
-		break;
-	}
-	default:
-		/* ignore unknown mount options */
-		break;
 	}
 
 	return 0;
-
-bad_value:
-	return invalfc(fc, "Bad value for '%s'", param->key);
 }
 
 struct bpf_preload_ops *bpf_preload_ops;
@@ -1010,14 +739,10 @@ out:
 static int bpf_fill_super(struct super_block *sb, struct fs_context *fc)
 {
 	static const struct tree_descr bpf_rfiles[] = { { "" } };
-	struct bpf_mount_opts *opts = sb->s_fs_info;
+	struct bpf_mount_opts *opts = fc->fs_private;
 	struct inode *inode;
 	int ret;
 
-	/* Mounting an instance of BPF FS requires privileges */
-	if (fc->user_ns != &init_user_ns && !capable(CAP_SYS_ADMIN))
-		return -EPERM;
-
 	ret = simple_fill_super(sb, BPF_FS_MAGIC, bpf_rfiles);
 	if (ret)
 		return ret;
@@ -1025,8 +750,6 @@ static int bpf_fill_super(struct super_block *sb, struct fs_context *fc)
 	sb->s_op = &bpf_super_ops;
 
 	inode = sb->s_root->d_inode;
-	inode->i_uid = opts->uid;
-	inode->i_gid = opts->gid;
 	inode->i_op = &bpf_dir_iops;
 	inode->i_mode &= ~S_IALLUGO;
 	populate_bpffs(sb->s_root);
@@ -1041,7 +764,7 @@ static int bpf_get_tree(struct fs_context *fc)
 
 static void bpf_free_fc(struct fs_context *fc)
 {
-	kfree(fc->s_fs_info);
+	kfree(fc->fs_private);
 }
 
 static const struct fs_context_operations bpf_context_ops = {
@@ -1062,35 +785,18 @@ static int bpf_init_fs_context(struct fs_context *fc)
 		return -ENOMEM;
 
 	opts->mode = S_IRWXUGO;
-	opts->uid = current_fsuid();
-	opts->gid = current_fsgid();
-
-	/* start out with no BPF token delegation enabled */
-	opts->delegate_cmds = 0;
-	opts->delegate_maps = 0;
-	opts->delegate_progs = 0;
-	opts->delegate_attachs = 0;
 
-	fc->s_fs_info = opts;
+	fc->fs_private = opts;
 	fc->ops = &bpf_context_ops;
 	return 0;
 }
 
-static void bpf_kill_super(struct super_block *sb)
-{
-	struct bpf_mount_opts *opts = sb->s_fs_info;
-
-	kill_litter_super(sb);
-	kfree(opts);
-}
-
 static struct file_system_type bpf_fs_type = {
 	.owner		= THIS_MODULE,
 	.name		= "bpf",
 	.init_fs_context = bpf_init_fs_context,
 	.parameters	= bpf_fs_parameters,
-	.kill_sb	= bpf_kill_super,
-	.fs_flags	= FS_USERNS_MOUNT,
+	.kill_sb	= kill_litter_super,
 };
 
 static int __init bpf_init(void)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 8faa1a20edf8..1bf9805ee185 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1011,8 +1011,8 @@ int map_check_no_btf(const struct bpf_map *map,
 	return -ENOTSUPP;
 }
 
-static int map_check_btf(struct bpf_map *map, struct bpf_token *token,
-			 const struct btf *btf, u32 btf_key_id, u32 btf_value_id)
+static int map_check_btf(struct bpf_map *map, const struct btf *btf,
+			 u32 btf_key_id, u32 btf_value_id)
 {
 	const struct btf_type *key_type, *value_type;
 	u32 key_size, value_size;
@@ -1040,7 +1040,7 @@ static int map_check_btf(struct bpf_map *map, struct bpf_token *token,
 	if (!IS_ERR_OR_NULL(map->record)) {
 		int i;
 
-		if (!bpf_token_capable(token, CAP_BPF)) {
+		if (!bpf_capable()) {
 			ret = -EPERM;
 			goto free_map_tab;
 		}
@@ -1123,17 +1123,11 @@ free_map_tab:
 	return ret;
 }
 
-static bool bpf_net_capable(void)
-{
-	return capable(CAP_NET_ADMIN) || capable(CAP_SYS_ADMIN);
-}
-
-#define BPF_MAP_CREATE_LAST_FIELD map_token_fd
+#define BPF_MAP_CREATE_LAST_FIELD map_extra
 /* called via syscall */
 static int map_create(union bpf_attr *attr)
 {
 	const struct bpf_map_ops *ops;
-	struct bpf_token *token = NULL;
 	int numa_node = bpf_map_attr_numa_node(attr);
 	u32 map_type = attr->map_type;
 	struct bpf_map *map;
@@ -1184,32 +1178,14 @@ static int map_create(union bpf_attr *attr)
 	if (!ops->map_mem_usage)
 		return -EINVAL;
 
-	if (attr->map_token_fd) {
-		token = bpf_token_get_from_fd(attr->map_token_fd);
-		if (IS_ERR(token))
-			return PTR_ERR(token);
-
-		/* if current token doesn't grant map creation permissions,
-		 * then we can't use this token, so ignore it and rely on
-		 * system-wide capabilities checks
-		 */
-		if (!bpf_token_allow_cmd(token, BPF_MAP_CREATE) ||
-		    !bpf_token_allow_map_type(token, attr->map_type)) {
-			bpf_token_put(token);
-			token = NULL;
-		}
-	}
-
-	err = -EPERM;
-
 	/* Intent here is for unprivileged_bpf_disabled to block BPF map
 	 * creation for unprivileged users; other actions depend
 	 * on fd availability and access to bpffs, so are dependent on
 	 * object creation success. Even with unprivileged BPF disabled,
 	 * capability checks are still carried out.
 	 */
-	if (sysctl_unprivileged_bpf_disabled && !bpf_token_capable(token, CAP_BPF))
-		goto put_token;
+	if (sysctl_unprivileged_bpf_disabled && !bpf_capable())
+		return -EPERM;
 
 	/* check privileged map type permissions */
 	switch (map_type) {
@@ -1242,27 +1218,25 @@ static int map_create(union bpf_attr *attr)
 	case BPF_MAP_TYPE_LRU_PERCPU_HASH:
 	case BPF_MAP_TYPE_STRUCT_OPS:
 	case BPF_MAP_TYPE_CPUMAP:
-		if (!bpf_token_capable(token, CAP_BPF))
-			goto put_token;
+		if (!bpf_capable())
+			return -EPERM;
 		break;
 	case BPF_MAP_TYPE_SOCKMAP:
 	case BPF_MAP_TYPE_SOCKHASH:
 	case BPF_MAP_TYPE_DEVMAP:
 	case BPF_MAP_TYPE_DEVMAP_HASH:
 	case BPF_MAP_TYPE_XSKMAP:
-		if (!bpf_token_capable(token, CAP_NET_ADMIN))
-			goto put_token;
+		if (!capable(CAP_NET_ADMIN))
+			return -EPERM;
 		break;
 	default:
 		WARN(1, "unsupported map type %d", map_type);
-		goto put_token;
+		return -EPERM;
 	}
 
 	map = ops->map_alloc(attr);
-	if (IS_ERR(map)) {
-		err = PTR_ERR(map);
-		goto put_token;
-	}
+	if (IS_ERR(map))
+		return PTR_ERR(map);
 	map->ops = ops;
 	map->map_type = map_type;
 
@@ -1299,7 +1273,7 @@ static int map_create(union bpf_attr *attr)
 		map->btf = btf;
 
 		if (attr->btf_value_type_id) {
-			err = map_check_btf(map, token, btf, attr->btf_key_type_id,
+			err = map_check_btf(map, btf, attr->btf_key_type_id,
 					    attr->btf_value_type_id);
 			if (err)
 				goto free_map;
@@ -1311,16 +1285,15 @@ static int map_create(union bpf_attr *attr)
 			attr->btf_vmlinux_value_type_id;
 	}
 
-	err = security_bpf_map_create(map, attr, token);
+	err = security_bpf_map_alloc(map);
 	if (err)
-		goto free_map_sec;
+		goto free_map;
 
 	err = bpf_map_alloc_id(map);
 	if (err)
 		goto free_map_sec;
 
 	bpf_map_save_memcg(map);
-	bpf_token_put(token);
 
 	err = bpf_map_new_fd(map, f_flags);
 	if (err < 0) {
@@ -1341,8 +1314,6 @@ free_map_sec:
 free_map:
 	btf_put(map->btf);
 	map->ops->map_free(map);
-put_token:
-	bpf_token_put(token);
 	return err;
 }
 
@@ -2173,7 +2144,7 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu)
 	kvfree(aux->func_info);
 	kfree(aux->func_info_aux);
 	free_uid(aux->user);
-	security_bpf_prog_free(aux->prog);
+	security_bpf_prog_free(aux);
 	bpf_prog_free(aux->prog);
 }
 
@@ -2619,15 +2590,13 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type)
 }
 
 /* last field in 'union bpf_attr' used by this command */
-#define BPF_PROG_LOAD_LAST_FIELD prog_token_fd
+#define	BPF_PROG_LOAD_LAST_FIELD log_true_size
 
 static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
 {
 	enum bpf_prog_type type = attr->prog_type;
 	struct bpf_prog *prog, *dst_prog = NULL;
 	struct btf *attach_btf = NULL;
-	struct bpf_token *token = NULL;
-	bool bpf_cap;
 	int err;
 	char license[128];
 
@@ -2644,31 +2613,10 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
 				 BPF_F_TEST_REG_INVARIANTS))
 		return -EINVAL;
 
-	bpf_prog_load_fixup_attach_type(attr);
-
-	if (attr->prog_token_fd) {
-		token = bpf_token_get_from_fd(attr->prog_token_fd);
-		if (IS_ERR(token))
-			return PTR_ERR(token);
-		/* if current token doesn't grant prog loading permissions,
-		 * then we can't use this token, so ignore it and rely on
-		 * system-wide capabilities checks
-		 */
-		if (!bpf_token_allow_cmd(token, BPF_PROG_LOAD) ||
-		    !bpf_token_allow_prog_type(token, attr->prog_type,
-					       attr->expected_attach_type)) {
-			bpf_token_put(token);
-			token = NULL;
-		}
-	}
-
-	bpf_cap = bpf_token_capable(token, CAP_BPF);
-	err = -EPERM;
-
 	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) &&
 	    (attr->prog_flags & BPF_F_ANY_ALIGNMENT) &&
-	    !bpf_cap)
-		goto put_token;
+	    !bpf_capable())
+		return -EPERM;
 
 	/* Intent here is for unprivileged_bpf_disabled to block BPF program
 	 * creation for unprivileged users; other actions depend
@@ -2677,23 +2625,21 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
 	 * capability checks are still carried out for these
 	 * and other operations.
 	 */
-	if (sysctl_unprivileged_bpf_disabled && !bpf_cap)
-		goto put_token;
+	if (sysctl_unprivileged_bpf_disabled && !bpf_capable())
+		return -EPERM;
 
 	if (attr->insn_cnt == 0 ||
-	    attr->insn_cnt > (bpf_cap ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS)) {
-		err = -E2BIG;
-		goto put_token;
-	}
+	    attr->insn_cnt > (bpf_capable() ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS))
+		return -E2BIG;
 	if (type != BPF_PROG_TYPE_SOCKET_FILTER &&
 	    type != BPF_PROG_TYPE_CGROUP_SKB &&
-	    !bpf_cap)
-		goto put_token;
+	    !bpf_capable())
+		return -EPERM;
 
-	if (is_net_admin_prog_type(type) && !bpf_token_capable(token, CAP_NET_ADMIN))
-		goto put_token;
-	if (is_perfmon_prog_type(type) && !bpf_token_capable(token, CAP_PERFMON))
-		goto put_token;
+	if (is_net_admin_prog_type(type) && !capable(CAP_NET_ADMIN) && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	if (is_perfmon_prog_type(type) && !perfmon_capable())
+		return -EPERM;
 
 	/* attach_prog_fd/attach_btf_obj_fd can specify fd of either bpf_prog
 	 * or btf, we need to check which one it is
@@ -2703,33 +2649,27 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
 		if (IS_ERR(dst_prog)) {
 			dst_prog = NULL;
 			attach_btf = btf_get_by_fd(attr->attach_btf_obj_fd);
-			if (IS_ERR(attach_btf)) {
-				err = -EINVAL;
-				goto put_token;
-			}
+			if (IS_ERR(attach_btf))
+				return -EINVAL;
 			if (!btf_is_kernel(attach_btf)) {
 				/* attaching through specifying bpf_prog's BTF
 				 * objects directly might be supported eventually
 				 */
 				btf_put(attach_btf);
-				err = -ENOTSUPP;
-				goto put_token;
+				return -ENOTSUPP;
 			}
 		}
 	} else if (attr->attach_btf_id) {
 		/* fall back to vmlinux BTF, if BTF type ID is specified */
 		attach_btf = bpf_get_btf_vmlinux();
-		if (IS_ERR(attach_btf)) {
-			err = PTR_ERR(attach_btf);
-			goto put_token;
-		}
-		if (!attach_btf) {
-			err = -EINVAL;
-			goto put_token;
-		}
+		if (IS_ERR(attach_btf))
+			return PTR_ERR(attach_btf);
+		if (!attach_btf)
+			return -EINVAL;
 		btf_get(attach_btf);
 	}
 
+	bpf_prog_load_fixup_attach_type(attr);
 	if (bpf_prog_load_check_attach(type, attr->expected_attach_type,
 				       attach_btf, attr->attach_btf_id,
 				       dst_prog)) {
@@ -2737,8 +2677,7 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
 			bpf_prog_put(dst_prog);
 		if (attach_btf)
 			btf_put(attach_btf);
-		err = -EINVAL;
-		goto put_token;
+		return -EINVAL;
 	}
 
 	/* plain bpf_prog allocation */
@@ -2748,8 +2687,7 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
 			bpf_prog_put(dst_prog);
 		if (attach_btf)
 			btf_put(attach_btf);
-		err = -EINVAL;
-		goto put_token;
+		return -ENOMEM;
 	}
 
 	prog->expected_attach_type = attr->expected_attach_type;
@@ -2760,9 +2698,9 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
 	prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE;
 	prog->aux->xdp_has_frags = attr->prog_flags & BPF_F_XDP_HAS_FRAGS;
 
-	/* move token into prog->aux, reuse taken refcnt */
-	prog->aux->token = token;
-	token = NULL;
+	err = security_bpf_prog_alloc(prog->aux);
+	if (err)
+		goto free_prog;
 
 	prog->aux->user = get_current_user();
 	prog->len = attr->insn_cnt;
@@ -2771,12 +2709,12 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
 	if (copy_from_bpfptr(prog->insns,
 			     make_bpfptr(attr->insns, uattr.is_kernel),
 			     bpf_prog_insn_size(prog)) != 0)
-		goto free_prog;
+		goto free_prog_sec;
 	/* copy eBPF program license from user space */
 	if (strncpy_from_bpfptr(license,
 				make_bpfptr(attr->license, uattr.is_kernel),
 				sizeof(license) - 1) < 0)
-		goto free_prog;
+		goto free_prog_sec;
 	license[sizeof(license) - 1] = 0;
 
 	/* eBPF programs must be GPL compatible to use GPL-ed functions */
@@ -2790,29 +2728,25 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
 	if (bpf_prog_is_dev_bound(prog->aux)) {
 		err = bpf_prog_dev_bound_init(prog, attr);
 		if (err)
-			goto free_prog;
+			goto free_prog_sec;
 	}
 
 	if (type == BPF_PROG_TYPE_EXT && dst_prog &&
 	    bpf_prog_is_dev_bound(dst_prog->aux)) {
 		err = bpf_prog_dev_bound_inherit(prog, dst_prog);
 		if (err)
-			goto free_prog;
+			goto free_prog_sec;
 	}
 
 	/* find program type: socket_filter vs tracing_filter */
 	err = find_prog_type(type, prog);
 	if (err < 0)
-		goto free_prog;
+		goto free_prog_sec;
 
 	prog->aux->load_time = ktime_get_boottime_ns();
 	err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name,
 			       sizeof(attr->prog_name));
 	if (err < 0)
-		goto free_prog;
-
-	err = security_bpf_prog_load(prog, attr, token);
-	if (err)
 		goto free_prog_sec;
 
 	/* run eBPF verifier */
@@ -2858,16 +2792,13 @@ free_used_maps:
 	 */
 	__bpf_prog_put_noref(prog, prog->aux->real_func_cnt);
 	return err;
-
 free_prog_sec:
-	security_bpf_prog_free(prog);
-free_prog:
 	free_uid(prog->aux->user);
+	security_bpf_prog_free(prog->aux);
+free_prog:
 	if (prog->aux->attach_btf)
 		btf_put(prog->aux->attach_btf);
 	bpf_prog_free(prog);
-put_token:
-	bpf_token_put(token);
 	return err;
 }
 
@@ -3857,7 +3788,7 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
 	case BPF_PROG_TYPE_SK_LOOKUP:
 		return attach_type == prog->expected_attach_type ? 0 : -EINVAL;
 	case BPF_PROG_TYPE_CGROUP_SKB:
-		if (!bpf_token_capable(prog->aux->token, CAP_NET_ADMIN))
+		if (!capable(CAP_NET_ADMIN))
 			/* cg-skb progs can be loaded by unpriv user.
 			 * check permissions at attach time.
 			 */
@@ -4060,7 +3991,7 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 static int bpf_prog_query(const union bpf_attr *attr,
 			  union bpf_attr __user *uattr)
 {
-	if (!bpf_net_capable())
+	if (!capable(CAP_NET_ADMIN))
 		return -EPERM;
 	if (CHECK_ATTR(BPF_PROG_QUERY))
 		return -EINVAL;
@@ -4828,31 +4759,15 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr,
 	return err;
 }
 
-#define BPF_BTF_LOAD_LAST_FIELD btf_token_fd
+#define BPF_BTF_LOAD_LAST_FIELD btf_log_true_size
 
 static int bpf_btf_load(const union bpf_attr *attr, bpfptr_t uattr, __u32 uattr_size)
 {
-	struct bpf_token *token = NULL;
-
 	if (CHECK_ATTR(BPF_BTF_LOAD))
 		return -EINVAL;
 
-	if (attr->btf_token_fd) {
-		token = bpf_token_get_from_fd(attr->btf_token_fd);
-		if (IS_ERR(token))
-			return PTR_ERR(token);
-		if (!bpf_token_allow_cmd(token, BPF_BTF_LOAD)) {
-			bpf_token_put(token);
-			token = NULL;
-		}
-	}
-
-	if (!bpf_token_capable(token, CAP_BPF)) {
-		bpf_token_put(token);
+	if (!bpf_capable())
 		return -EPERM;
-	}
-
-	bpf_token_put(token);
 
 	return btf_new_fd(attr, uattr, uattr_size);
 }
@@ -5470,20 +5385,6 @@ out_prog_put:
 	return ret;
 }
 
-#define BPF_TOKEN_CREATE_LAST_FIELD token_create.bpffs_fd
-
-static int token_create(union bpf_attr *attr)
-{
-	if (CHECK_ATTR(BPF_TOKEN_CREATE))
-		return -EINVAL;
-
-	/* no flags are supported yet */
-	if (attr->token_create.flags)
-		return -EINVAL;
-
-	return bpf_token_create(attr);
-}
-
 static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size)
 {
 	union bpf_attr attr;
@@ -5617,9 +5518,6 @@ static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size)
 	case BPF_PROG_BIND_MAP:
 		err = bpf_prog_bind_map(&attr);
 		break;
-	case BPF_TOKEN_CREATE:
-		err = token_create(&attr);
-		break;
 	default:
 		err = -EINVAL;
 		break;
@@ -5726,7 +5624,7 @@ static const struct bpf_func_proto bpf_sys_bpf_proto = {
 const struct bpf_func_proto * __weak
 tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
-	return bpf_base_func_proto(func_id, prog);
+	return bpf_base_func_proto(func_id);
 }
 
 BPF_CALL_1(bpf_sys_close, u32, fd)
@@ -5776,8 +5674,7 @@ syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
 	switch (func_id) {
 	case BPF_FUNC_sys_bpf:
-		return !bpf_token_capable(prog->aux->token, CAP_PERFMON)
-		       ? NULL : &bpf_sys_bpf_proto;
+		return !perfmon_capable() ? NULL : &bpf_sys_bpf_proto;
 	case BPF_FUNC_btf_find_by_name_kind:
 		return &bpf_btf_find_by_name_kind_proto;
 	case BPF_FUNC_sys_close:
diff --git a/kernel/bpf/token.c b/kernel/bpf/token.c
deleted file mode 100644
index a86fccd57e2d..000000000000
--- a/kernel/bpf/token.c
+++ /dev/null
@@ -1,271 +0,0 @@
-#include <linux/bpf.h>
-#include <linux/vmalloc.h>
-#include <linux/fdtable.h>
-#include <linux/file.h>
-#include <linux/fs.h>
-#include <linux/kernel.h>
-#include <linux/idr.h>
-#include <linux/namei.h>
-#include <linux/user_namespace.h>
-#include <linux/security.h>
-
-bool bpf_token_capable(const struct bpf_token *token, int cap)
-{
-	/* BPF token allows ns_capable() level of capabilities, but only if
-	 * token's userns is *exactly* the same as current user's userns
-	 */
-	if (token && current_user_ns() == token->userns) {
-		if (ns_capable(token->userns, cap) ||
-		    (cap != CAP_SYS_ADMIN && ns_capable(token->userns, CAP_SYS_ADMIN)))
-			return security_bpf_token_capable(token, cap) == 0;
-	}
-	/* otherwise fallback to capable() checks */
-	return capable(cap) || (cap != CAP_SYS_ADMIN && capable(CAP_SYS_ADMIN));
-}
-
-void bpf_token_inc(struct bpf_token *token)
-{
-	atomic64_inc(&token->refcnt);
-}
-
-static void bpf_token_free(struct bpf_token *token)
-{
-	security_bpf_token_free(token);
-	put_user_ns(token->userns);
-	kvfree(token);
-}
-
-static void bpf_token_put_deferred(struct work_struct *work)
-{
-	struct bpf_token *token = container_of(work, struct bpf_token, work);
-
-	bpf_token_free(token);
-}
-
-void bpf_token_put(struct bpf_token *token)
-{
-	if (!token)
-		return;
-
-	if (!atomic64_dec_and_test(&token->refcnt))
-		return;
-
-	INIT_WORK(&token->work, bpf_token_put_deferred);
-	schedule_work(&token->work);
-}
-
-static int bpf_token_release(struct inode *inode, struct file *filp)
-{
-	struct bpf_token *token = filp->private_data;
-
-	bpf_token_put(token);
-	return 0;
-}
-
-static void bpf_token_show_fdinfo(struct seq_file *m, struct file *filp)
-{
-	struct bpf_token *token = filp->private_data;
-	u64 mask;
-
-	BUILD_BUG_ON(__MAX_BPF_CMD >= 64);
-	mask = (1ULL << __MAX_BPF_CMD) - 1;
-	if ((token->allowed_cmds & mask) == mask)
-		seq_printf(m, "allowed_cmds:\tany\n");
-	else
-		seq_printf(m, "allowed_cmds:\t0x%llx\n", token->allowed_cmds);
-
-	BUILD_BUG_ON(__MAX_BPF_MAP_TYPE >= 64);
-	mask = (1ULL << __MAX_BPF_MAP_TYPE) - 1;
-	if ((token->allowed_maps & mask) == mask)
-		seq_printf(m, "allowed_maps:\tany\n");
-	else
-		seq_printf(m, "allowed_maps:\t0x%llx\n", token->allowed_maps);
-
-	BUILD_BUG_ON(__MAX_BPF_PROG_TYPE >= 64);
-	mask = (1ULL << __MAX_BPF_PROG_TYPE) - 1;
-	if ((token->allowed_progs & mask) == mask)
-		seq_printf(m, "allowed_progs:\tany\n");
-	else
-		seq_printf(m, "allowed_progs:\t0x%llx\n", token->allowed_progs);
-
-	BUILD_BUG_ON(__MAX_BPF_ATTACH_TYPE >= 64);
-	mask = (1ULL << __MAX_BPF_ATTACH_TYPE) - 1;
-	if ((token->allowed_attachs & mask) == mask)
-		seq_printf(m, "allowed_attachs:\tany\n");
-	else
-		seq_printf(m, "allowed_attachs:\t0x%llx\n", token->allowed_attachs);
-}
-
-#define BPF_TOKEN_INODE_NAME "bpf-token"
-
-static const struct inode_operations bpf_token_iops = { };
-
-static const struct file_operations bpf_token_fops = {
-	.release	= bpf_token_release,
-	.show_fdinfo	= bpf_token_show_fdinfo,
-};
-
-int bpf_token_create(union bpf_attr *attr)
-{
-	struct bpf_mount_opts *mnt_opts;
-	struct bpf_token *token = NULL;
-	struct user_namespace *userns;
-	struct inode *inode;
-	struct file *file;
-	struct path path;
-	struct fd f;
-	umode_t mode;
-	int err, fd;
-
-	f = fdget(attr->token_create.bpffs_fd);
-	if (!f.file)
-		return -EBADF;
-
-	path = f.file->f_path;
-	path_get(&path);
-	fdput(f);
-
-	if (path.dentry != path.mnt->mnt_sb->s_root) {
-		err = -EINVAL;
-		goto out_path;
-	}
-	if (path.mnt->mnt_sb->s_op != &bpf_super_ops) {
-		err = -EINVAL;
-		goto out_path;
-	}
-	err = path_permission(&path, MAY_ACCESS);
-	if (err)
-		goto out_path;
-
-	userns = path.dentry->d_sb->s_user_ns;
-	/*
-	 * Enforce that creators of BPF tokens are in the same user
-	 * namespace as the BPF FS instance. This makes reasoning about
-	 * permissions a lot easier and we can always relax this later.
-	 */
-	if (current_user_ns() != userns) {
-		err = -EPERM;
-		goto out_path;
-	}
-	if (!ns_capable(userns, CAP_BPF)) {
-		err = -EPERM;
-		goto out_path;
-	}
-
-	mnt_opts = path.dentry->d_sb->s_fs_info;
-	if (mnt_opts->delegate_cmds == 0 &&
-	    mnt_opts->delegate_maps == 0 &&
-	    mnt_opts->delegate_progs == 0 &&
-	    mnt_opts->delegate_attachs == 0) {
-		err = -ENOENT; /* no BPF token delegation is set up */
-		goto out_path;
-	}
-
-	mode = S_IFREG | ((S_IRUSR | S_IWUSR) & ~current_umask());
-	inode = bpf_get_inode(path.mnt->mnt_sb, NULL, mode);
-	if (IS_ERR(inode)) {
-		err = PTR_ERR(inode);
-		goto out_path;
-	}
-
-	inode->i_op = &bpf_token_iops;
-	inode->i_fop = &bpf_token_fops;
-	clear_nlink(inode); /* make sure it is unlinked */
-
-	file = alloc_file_pseudo(inode, path.mnt, BPF_TOKEN_INODE_NAME, O_RDWR, &bpf_token_fops);
-	if (IS_ERR(file)) {
-		iput(inode);
-		err = PTR_ERR(file);
-		goto out_path;
-	}
-
-	token = kvzalloc(sizeof(*token), GFP_USER);
-	if (!token) {
-		err = -ENOMEM;
-		goto out_file;
-	}
-
-	atomic64_set(&token->refcnt, 1);
-
-	/* remember bpffs owning userns for future ns_capable() checks */
-	token->userns = get_user_ns(userns);
-
-	token->allowed_cmds = mnt_opts->delegate_cmds;
-	token->allowed_maps = mnt_opts->delegate_maps;
-	token->allowed_progs = mnt_opts->delegate_progs;
-	token->allowed_attachs = mnt_opts->delegate_attachs;
-
-	err = security_bpf_token_create(token, attr, &path);
-	if (err)
-		goto out_token;
-
-	fd = get_unused_fd_flags(O_CLOEXEC);
-	if (fd < 0) {
-		err = fd;
-		goto out_token;
-	}
-
-	file->private_data = token;
-	fd_install(fd, file);
-
-	path_put(&path);
-	return fd;
-
-out_token:
-	bpf_token_free(token);
-out_file:
-	fput(file);
-out_path:
-	path_put(&path);
-	return err;
-}
-
-struct bpf_token *bpf_token_get_from_fd(u32 ufd)
-{
-	struct fd f = fdget(ufd);
-	struct bpf_token *token;
-
-	if (!f.file)
-		return ERR_PTR(-EBADF);
-	if (f.file->f_op != &bpf_token_fops) {
-		fdput(f);
-		return ERR_PTR(-EINVAL);
-	}
-
-	token = f.file->private_data;
-	bpf_token_inc(token);
-	fdput(f);
-
-	return token;
-}
-
-bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd)
-{
-	/* BPF token can be used only within exactly the same userns in which
-	 * it was created
-	 */
-	if (!token || current_user_ns() != token->userns)
-		return false;
-	if (!(token->allowed_cmds & (1ULL << cmd)))
-		return false;
-	return security_bpf_token_cmd(token, cmd) == 0;
-}
-
-bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type)
-{
-	if (!token || type >= __MAX_BPF_MAP_TYPE)
-		return false;
-
-	return token->allowed_maps & (1ULL << type);
-}
-
-bool bpf_token_allow_prog_type(const struct bpf_token *token,
-			       enum bpf_prog_type prog_type,
-			       enum bpf_attach_type attach_type)
-{
-	if (!token || prog_type >= __MAX_BPF_PROG_TYPE || attach_type >= __MAX_BPF_ATTACH_TYPE)
-		return false;
-
-	return (token->allowed_progs & (1ULL << prog_type)) &&
-	       (token->allowed_attachs & (1ULL << attach_type));
-}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 9456ee0ad129..4ceec8c2a484 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -20594,12 +20594,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
 	env->prog = *prog;
 	env->ops = bpf_verifier_ops[env->prog->type];
 	env->fd_array = make_bpfptr(attr->fd_array, uattr.is_kernel);
-
-	env->allow_ptr_leaks = bpf_allow_ptr_leaks(env->prog->aux->token);
-	env->allow_uninit_stack = bpf_allow_uninit_stack(env->prog->aux->token);
-	env->bypass_spec_v1 = bpf_bypass_spec_v1(env->prog->aux->token);
-	env->bypass_spec_v4 = bpf_bypass_spec_v4(env->prog->aux->token);
-	env->bpf_capable = is_priv = bpf_token_capable(env->prog->aux->token, CAP_BPF);
+	is_priv = bpf_capable();
 
 	bpf_get_btf_vmlinux();
 
@@ -20631,6 +20626,12 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
 	if (attr->prog_flags & BPF_F_ANY_ALIGNMENT)
 		env->strict_alignment = false;
 
+	env->allow_ptr_leaks = bpf_allow_ptr_leaks();
+	env->allow_uninit_stack = bpf_allow_uninit_stack();
+	env->bypass_spec_v1 = bpf_bypass_spec_v1();
+	env->bypass_spec_v4 = bpf_bypass_spec_v4();
+	env->bpf_capable = bpf_capable();
+
 	if (is_priv)
 		env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ;
 	env->test_reg_invariants = attr->prog_flags & BPF_F_TEST_REG_INVARIANTS;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 492d60e9c480..7ac6c52b25eb 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1629,7 +1629,7 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_trace_vprintk:
 		return bpf_get_trace_vprintk_proto();
 	default:
-		return bpf_base_func_proto(func_id, prog);
+		return bpf_base_func_proto(func_id);
 	}
 }
 
diff --git a/net/core/filter.c b/net/core/filter.c
index 3cc52b82bab8..24061f29c9dd 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -87,7 +87,7 @@
 #include "dev.h"
 
 static const struct bpf_func_proto *
-bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog);
+bpf_sk_base_func_proto(enum bpf_func_id func_id);
 
 int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len)
 {
@@ -7862,7 +7862,7 @@ sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_ktime_get_coarse_ns:
 		return &bpf_ktime_get_coarse_ns_proto;
 	default:
-		return bpf_base_func_proto(func_id, prog);
+		return bpf_base_func_proto(func_id);
 	}
 }
 
@@ -7955,7 +7955,7 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 			return NULL;
 		}
 	default:
-		return bpf_sk_base_func_proto(func_id, prog);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -7974,7 +7974,7 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_perf_event_output:
 		return &bpf_skb_event_output_proto;
 	default:
-		return bpf_sk_base_func_proto(func_id, prog);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -8161,7 +8161,7 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 #endif
 #endif
 	default:
-		return bpf_sk_base_func_proto(func_id, prog);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -8220,7 +8220,7 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 #endif
 #endif
 	default:
-		return bpf_sk_base_func_proto(func_id, prog);
+		return bpf_sk_base_func_proto(func_id);
 	}
 
 #if IS_MODULE(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)
@@ -8281,7 +8281,7 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_tcp_sock_proto;
 #endif /* CONFIG_INET */
 	default:
-		return bpf_sk_base_func_proto(func_id, prog);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -8323,7 +8323,7 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_cgroup_classid_curr_proto;
 #endif
 	default:
-		return bpf_sk_base_func_proto(func_id, prog);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -8367,7 +8367,7 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_skc_lookup_tcp_proto;
 #endif
 	default:
-		return bpf_sk_base_func_proto(func_id, prog);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -8378,7 +8378,7 @@ flow_dissector_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_skb_load_bytes:
 		return &bpf_flow_dissector_load_bytes_proto;
 	default:
-		return bpf_sk_base_func_proto(func_id, prog);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -8405,7 +8405,7 @@ lwt_out_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_skb_under_cgroup:
 		return &bpf_skb_under_cgroup_proto;
 	default:
-		return bpf_sk_base_func_proto(func_id, prog);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -8580,7 +8580,7 @@ static bool cg_skb_is_valid_access(int off, int size,
 		return false;
 	case bpf_ctx_range(struct __sk_buff, data):
 	case bpf_ctx_range(struct __sk_buff, data_end):
-		if (!bpf_token_capable(prog->aux->token, CAP_BPF))
+		if (!bpf_capable())
 			return false;
 		break;
 	}
@@ -8592,7 +8592,7 @@ static bool cg_skb_is_valid_access(int off, int size,
 		case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]):
 			break;
 		case bpf_ctx_range(struct __sk_buff, tstamp):
-			if (!bpf_token_capable(prog->aux->token, CAP_BPF))
+			if (!bpf_capable())
 				return false;
 			break;
 		default:
@@ -11236,7 +11236,7 @@ sk_reuseport_func_proto(enum bpf_func_id func_id,
 	case BPF_FUNC_ktime_get_coarse_ns:
 		return &bpf_ktime_get_coarse_ns_proto;
 	default:
-		return bpf_base_func_proto(func_id, prog);
+		return bpf_base_func_proto(func_id);
 	}
 }
 
@@ -11418,7 +11418,7 @@ sk_lookup_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_sk_release:
 		return &bpf_sk_release_proto;
 	default:
-		return bpf_sk_base_func_proto(func_id, prog);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -11752,7 +11752,7 @@ const struct bpf_func_proto bpf_sock_from_file_proto = {
 };
 
 static const struct bpf_func_proto *
-bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+bpf_sk_base_func_proto(enum bpf_func_id func_id)
 {
 	const struct bpf_func_proto *func;
 
@@ -11781,10 +11781,10 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_ktime_get_coarse_ns:
 		return &bpf_ktime_get_coarse_ns_proto;
 	default:
-		return bpf_base_func_proto(func_id, prog);
+		return bpf_base_func_proto(func_id);
 	}
 
-	if (!bpf_token_capable(prog->aux->token, CAP_PERFMON))
+	if (!perfmon_capable())
 		return NULL;
 
 	return func;
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index 634cfafa583d..ae8b15e6896f 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -191,7 +191,7 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id,
 	case BPF_FUNC_ktime_get_coarse_ns:
 		return &bpf_ktime_get_coarse_ns_proto;
 	default:
-		return bpf_base_func_proto(func_id, prog);
+		return bpf_base_func_proto(func_id);
 	}
 }
 
diff --git a/net/netfilter/nf_bpf_link.c b/net/netfilter/nf_bpf_link.c
index 5257d5e7eb09..0e4beae421f8 100644
--- a/net/netfilter/nf_bpf_link.c
+++ b/net/netfilter/nf_bpf_link.c
@@ -314,7 +314,7 @@ static bool nf_is_valid_access(int off, int size, enum bpf_access_type type,
 static const struct bpf_func_proto *
 bpf_nf_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
-	return bpf_base_func_proto(func_id, prog);
+	return bpf_base_func_proto(func_id);
 }
 
 const struct bpf_verifier_ops netfilter_verifier_ops = {
diff --git a/security/security.c b/security/security.c
index 088a79c35c26..dcb3e7014f9b 100644
--- a/security/security.c
+++ b/security/security.c
@@ -5167,87 +5167,29 @@ int security_bpf_prog(struct bpf_prog *prog)
 }
 
 /**
- * security_bpf_map_create() - Check if BPF map creation is allowed
- * @map: BPF map object
- * @attr: BPF syscall attributes used to create BPF map
- * @token: BPF token used to grant user access
- *
- * Do a check when the kernel creates a new BPF map. This is also the
- * point where LSM blob is allocated for LSMs that need them.
- *
- * Return: Returns 0 on success, error on failure.
- */
-int security_bpf_map_create(struct bpf_map *map, union bpf_attr *attr,
-			    struct bpf_token *token)
-{
-	return call_int_hook(bpf_map_create, 0, map, attr, token);
-}
-
-/**
- * security_bpf_prog_load() - Check if loading of BPF program is allowed
- * @prog: BPF program object
- * @attr: BPF syscall attributes used to create BPF program
- * @token: BPF token used to grant user access to BPF subsystem
- *
- * Perform an access control check when the kernel loads a BPF program and
- * allocates associated BPF program object. This hook is also responsible for
- * allocating any required LSM state for the BPF program.
- *
- * Return: Returns 0 on success, error on failure.
- */
-int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr,
-			   struct bpf_token *token)
-{
-	return call_int_hook(bpf_prog_load, 0, prog, attr, token);
-}
-
-/**
- * security_bpf_token_create() - Check if creating of BPF token is allowed
- * @token: BPF token object
- * @attr: BPF syscall attributes used to create BPF token
- * @path: path pointing to BPF FS mount point from which BPF token is created
- *
- * Do a check when the kernel instantiates a new BPF token object from BPF FS
- * instance. This is also the point where LSM blob can be allocated for LSMs.
- *
- * Return: Returns 0 on success, error on failure.
- */
-int security_bpf_token_create(struct bpf_token *token, union bpf_attr *attr,
-			      struct path *path)
-{
-	return call_int_hook(bpf_token_create, 0, token, attr, path);
-}
-
-/**
- * security_bpf_token_cmd() - Check if BPF token is allowed to delegate
- * requested BPF syscall command
- * @token: BPF token object
- * @cmd: BPF syscall command requested to be delegated by BPF token
+ * security_bpf_map_alloc() - Allocate a bpf map LSM blob
+ * @map: bpf map
  *
- * Do a check when the kernel decides whether provided BPF token should allow
- * delegation of requested BPF syscall command.
+ * Initialize the security field inside bpf map.
  *
  * Return: Returns 0 on success, error on failure.
  */
-int security_bpf_token_cmd(const struct bpf_token *token, enum bpf_cmd cmd)
+int security_bpf_map_alloc(struct bpf_map *map)
 {
-	return call_int_hook(bpf_token_cmd, 0, token, cmd);
+	return call_int_hook(bpf_map_alloc_security, 0, map);
 }
 
 /**
- * security_bpf_token_capable() - Check if BPF token is allowed to delegate
- * requested BPF-related capability
- * @token: BPF token object
- * @cap: capabilities requested to be delegated by BPF token
+ * security_bpf_prog_alloc() - Allocate a bpf program LSM blob
+ * @aux: bpf program aux info struct
  *
- * Do a check when the kernel decides whether provided BPF token should allow
- * delegation of requested BPF-related capabilities.
+ * Initialize the security field inside bpf program.
  *
  * Return: Returns 0 on success, error on failure.
  */
-int security_bpf_token_capable(const struct bpf_token *token, int cap)
+int security_bpf_prog_alloc(struct bpf_prog_aux *aux)
 {
-	return call_int_hook(bpf_token_capable, 0, token, cap);
+	return call_int_hook(bpf_prog_alloc_security, 0, aux);
 }
 
 /**
@@ -5258,29 +5200,18 @@ int security_bpf_token_capable(const struct bpf_token *token, int cap)
  */
 void security_bpf_map_free(struct bpf_map *map)
 {
-	call_void_hook(bpf_map_free, map);
-}
-
-/**
- * security_bpf_prog_free() - Free a BPF program's LSM blob
- * @prog: BPF program struct
- *
- * Clean up the security information stored inside BPF program.
- */
-void security_bpf_prog_free(struct bpf_prog *prog)
-{
-	call_void_hook(bpf_prog_free, prog);
+	call_void_hook(bpf_map_free_security, map);
 }
 
 /**
- * security_bpf_token_free() - Free a BPF token's LSM blob
- * @token: BPF token struct
+ * security_bpf_prog_free() - Free a bpf program's LSM blob
+ * @aux: bpf program aux info struct
  *
- * Clean up the security information stored inside BPF token.
+ * Clean up the security information stored inside bpf prog.
  */
-void security_bpf_token_free(struct bpf_token *token)
+void security_bpf_prog_free(struct bpf_prog_aux *aux)
 {
-	call_void_hook(bpf_token_free, token);
+	call_void_hook(bpf_prog_free_security, aux);
 }
 #endif /* CONFIG_BPF_SYSCALL */
 
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 1501e95366a1..feda711c6b7b 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -6783,8 +6783,7 @@ static int selinux_bpf_prog(struct bpf_prog *prog)
 			    BPF__PROG_RUN, NULL);
 }
 
-static int selinux_bpf_map_create(struct bpf_map *map, union bpf_attr *attr,
-				  struct bpf_token *token)
+static int selinux_bpf_map_alloc(struct bpf_map *map)
 {
 	struct bpf_security_struct *bpfsec;
 
@@ -6806,8 +6805,7 @@ static void selinux_bpf_map_free(struct bpf_map *map)
 	kfree(bpfsec);
 }
 
-static int selinux_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr,
-				 struct bpf_token *token)
+static int selinux_bpf_prog_alloc(struct bpf_prog_aux *aux)
 {
 	struct bpf_security_struct *bpfsec;
 
@@ -6816,39 +6814,16 @@ static int selinux_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr,
 		return -ENOMEM;
 
 	bpfsec->sid = current_sid();
-	prog->aux->security = bpfsec;
+	aux->security = bpfsec;
 
 	return 0;
 }
 
-static void selinux_bpf_prog_free(struct bpf_prog *prog)
+static void selinux_bpf_prog_free(struct bpf_prog_aux *aux)
 {
-	struct bpf_security_struct *bpfsec = prog->aux->security;
+	struct bpf_security_struct *bpfsec = aux->security;
 
-	prog->aux->security = NULL;
-	kfree(bpfsec);
-}
-
-static int selinux_bpf_token_create(struct bpf_token *token, union bpf_attr *attr,
-				    struct path *path)
-{
-	struct bpf_security_struct *bpfsec;
-
-	bpfsec = kzalloc(sizeof(*bpfsec), GFP_KERNEL);
-	if (!bpfsec)
-		return -ENOMEM;
-
-	bpfsec->sid = current_sid();
-	token->security = bpfsec;
-
-	return 0;
-}
-
-static void selinux_bpf_token_free(struct bpf_token *token)
-{
-	struct bpf_security_struct *bpfsec = token->security;
-
-	token->security = NULL;
+	aux->security = NULL;
 	kfree(bpfsec);
 }
 #endif
@@ -7204,9 +7179,8 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = {
 	LSM_HOOK_INIT(bpf, selinux_bpf),
 	LSM_HOOK_INIT(bpf_map, selinux_bpf_map),
 	LSM_HOOK_INIT(bpf_prog, selinux_bpf_prog),
-	LSM_HOOK_INIT(bpf_map_free, selinux_bpf_map_free),
-	LSM_HOOK_INIT(bpf_prog_free, selinux_bpf_prog_free),
-	LSM_HOOK_INIT(bpf_token_free, selinux_bpf_token_free),
+	LSM_HOOK_INIT(bpf_map_free_security, selinux_bpf_map_free),
+	LSM_HOOK_INIT(bpf_prog_free_security, selinux_bpf_prog_free),
 #endif
 
 #ifdef CONFIG_PERF_EVENTS
@@ -7263,9 +7237,8 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = {
 	LSM_HOOK_INIT(audit_rule_init, selinux_audit_rule_init),
 #endif
 #ifdef CONFIG_BPF_SYSCALL
-	LSM_HOOK_INIT(bpf_map_create, selinux_bpf_map_create),
-	LSM_HOOK_INIT(bpf_prog_load, selinux_bpf_prog_load),
-	LSM_HOOK_INIT(bpf_token_create, selinux_bpf_token_create),
+	LSM_HOOK_INIT(bpf_map_alloc_security, selinux_bpf_map_alloc),
+	LSM_HOOK_INIT(bpf_prog_alloc_security, selinux_bpf_prog_alloc),
 #endif
 #ifdef CONFIG_PERF_EVENTS
 	LSM_HOOK_INIT(perf_event_alloc, selinux_perf_event_alloc),
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index e0545201b55f..7f24d898efbb 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -847,36 +847,6 @@ union bpf_iter_link_info {
  *		Returns zero on success. On error, -1 is returned and *errno*
  *		is set appropriately.
  *
- * BPF_TOKEN_CREATE
- *	Description
- *		Create BPF token with embedded information about what
- *		BPF-related functionality it allows:
- *		- a set of allowed bpf() syscall commands;
- *		- a set of allowed BPF map types to be created with
- *		BPF_MAP_CREATE command, if BPF_MAP_CREATE itself is allowed;
- *		- a set of allowed BPF program types and BPF program attach
- *		types to be loaded with BPF_PROG_LOAD command, if
- *		BPF_PROG_LOAD itself is allowed.
- *
- *		BPF token is created (derived) from an instance of BPF FS,
- *		assuming it has necessary delegation mount options specified.
- *		This BPF token can be passed as an extra parameter to various
- *		bpf() syscall commands to grant BPF subsystem functionality to
- *		unprivileged processes.
- *
- *		When created, BPF token is "associated" with the owning
- *		user namespace of BPF FS instance (super block) that it was
- *		derived from, and subsequent BPF operations performed with
- *		BPF token would be performing capabilities checks (i.e.,
- *		CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN, CAP_SYS_ADMIN) within
- *		that user namespace. Without BPF token, such capabilities
- *		have to be granted in init user namespace, making bpf()
- *		syscall incompatible with user namespace, for the most part.
- *
- *	Return
- *		A new file descriptor (a nonnegative integer), or -1 if an
- *		error occurred (in which case, *errno* is set appropriately).
- *
  * NOTES
  *	eBPF objects (maps and programs) can be shared between processes.
  *
@@ -931,8 +901,6 @@ enum bpf_cmd {
 	BPF_ITER_CREATE,
 	BPF_LINK_DETACH,
 	BPF_PROG_BIND_MAP,
-	BPF_TOKEN_CREATE,
-	__MAX_BPF_CMD,
 };
 
 enum bpf_map_type {
@@ -983,7 +951,6 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_BLOOM_FILTER,
 	BPF_MAP_TYPE_USER_RINGBUF,
 	BPF_MAP_TYPE_CGRP_STORAGE,
-	__MAX_BPF_MAP_TYPE
 };
 
 /* Note that tracing related programs such as
@@ -1028,7 +995,6 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_SK_LOOKUP,
 	BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */
 	BPF_PROG_TYPE_NETFILTER,
-	__MAX_BPF_PROG_TYPE
 };
 
 enum bpf_attach_type {
@@ -1437,7 +1403,6 @@ union bpf_attr {
 		 * to using 5 hash functions).
 		 */
 		__u64	map_extra;
-		__u32	map_token_fd;
 	};
 
 	struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -1507,7 +1472,6 @@ union bpf_attr {
 		 * truncated), or smaller (if log buffer wasn't filled completely).
 		 */
 		__u32		log_true_size;
-		__u32		prog_token_fd;
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -1620,7 +1584,6 @@ union bpf_attr {
 		 * truncated), or smaller (if log buffer wasn't filled completely).
 		 */
 		__u32		btf_log_true_size;
-		__u32		btf_token_fd;
 	};
 
 	struct {
@@ -1751,11 +1714,6 @@ union bpf_attr {
 		__u32		flags;		/* extra flags */
 	} prog_bind_map;
 
-	struct { /* struct used by BPF_TOKEN_CREATE command */
-		__u32		flags;
-		__u32		bpffs_fd;
-	} token_create;
-
 } __attribute__((aligned(8)));
 
 /* The description below is an attempt at providing documentation to eBPF
diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
index b6619199a706..2d0c282c8588 100644
--- a/tools/lib/bpf/Build
+++ b/tools/lib/bpf/Build
@@ -1,4 +1,4 @@
 libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o \
 	    netlink.o bpf_prog_linfo.o libbpf_probes.o hashmap.o \
 	    btf_dump.o ringbuf.o strset.o linker.o gen_loader.o relo_core.o \
-	    usdt.o zip.o elf.o features.o
+	    usdt.o zip.o elf.o
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 0ad8e532b3cf..9dc9625651dc 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -103,7 +103,7 @@ int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts)
  *   [0] https://lore.kernel.org/bpf/20201201215900.3569844-1-guro@fb.com/
  *   [1] d05512618056 ("bpf: Add bpf_ktime_get_coarse_ns helper")
  */
-int probe_memcg_account(int token_fd)
+int probe_memcg_account(void)
 {
 	const size_t attr_sz = offsetofend(union bpf_attr, attach_btf_obj_fd);
 	struct bpf_insn insns[] = {
@@ -120,7 +120,6 @@ int probe_memcg_account(int token_fd)
 	attr.insns = ptr_to_u64(insns);
 	attr.insn_cnt = insn_cnt;
 	attr.license = ptr_to_u64("GPL");
-	attr.prog_token_fd = token_fd;
 
 	prog_fd = sys_bpf_fd(BPF_PROG_LOAD, &attr, attr_sz);
 	if (prog_fd >= 0) {
@@ -147,7 +146,7 @@ int bump_rlimit_memlock(void)
 	struct rlimit rlim;
 
 	/* if kernel supports memcg-based accounting, skip bumping RLIMIT_MEMLOCK */
-	if (memlock_bumped || feat_supported(NULL, FEAT_MEMCG_ACCOUNT))
+	if (memlock_bumped || kernel_supports(NULL, FEAT_MEMCG_ACCOUNT))
 		return 0;
 
 	memlock_bumped = true;
@@ -170,7 +169,7 @@ int bpf_map_create(enum bpf_map_type map_type,
 		   __u32 max_entries,
 		   const struct bpf_map_create_opts *opts)
 {
-	const size_t attr_sz = offsetofend(union bpf_attr, map_token_fd);
+	const size_t attr_sz = offsetofend(union bpf_attr, map_extra);
 	union bpf_attr attr;
 	int fd;
 
@@ -182,7 +181,7 @@ int bpf_map_create(enum bpf_map_type map_type,
 		return libbpf_err(-EINVAL);
 
 	attr.map_type = map_type;
-	if (map_name && feat_supported(NULL, FEAT_PROG_NAME))
+	if (map_name && kernel_supports(NULL, FEAT_PROG_NAME))
 		libbpf_strlcpy(attr.map_name, map_name, sizeof(attr.map_name));
 	attr.key_size = key_size;
 	attr.value_size = value_size;
@@ -199,8 +198,6 @@ int bpf_map_create(enum bpf_map_type map_type,
 	attr.numa_node = OPTS_GET(opts, numa_node, 0);
 	attr.map_ifindex = OPTS_GET(opts, map_ifindex, 0);
 
-	attr.map_token_fd = OPTS_GET(opts, token_fd, 0);
-
 	fd = sys_bpf_fd(BPF_MAP_CREATE, &attr, attr_sz);
 	return libbpf_err_errno(fd);
 }
@@ -235,7 +232,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
 		  const struct bpf_insn *insns, size_t insn_cnt,
 		  struct bpf_prog_load_opts *opts)
 {
-	const size_t attr_sz = offsetofend(union bpf_attr, prog_token_fd);
+	const size_t attr_sz = offsetofend(union bpf_attr, log_true_size);
 	void *finfo = NULL, *linfo = NULL;
 	const char *func_info, *line_info;
 	__u32 log_size, log_level, attach_prog_fd, attach_btf_obj_fd;
@@ -264,9 +261,8 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
 	attr.prog_flags = OPTS_GET(opts, prog_flags, 0);
 	attr.prog_ifindex = OPTS_GET(opts, prog_ifindex, 0);
 	attr.kern_version = OPTS_GET(opts, kern_version, 0);
-	attr.prog_token_fd = OPTS_GET(opts, token_fd, 0);
 
-	if (prog_name && feat_supported(NULL, FEAT_PROG_NAME))
+	if (prog_name && kernel_supports(NULL, FEAT_PROG_NAME))
 		libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name));
 	attr.license = ptr_to_u64(license);
 
@@ -1186,7 +1182,7 @@ int bpf_raw_tracepoint_open(const char *name, int prog_fd)
 
 int bpf_btf_load(const void *btf_data, size_t btf_size, struct bpf_btf_load_opts *opts)
 {
-	const size_t attr_sz = offsetofend(union bpf_attr, btf_token_fd);
+	const size_t attr_sz = offsetofend(union bpf_attr, btf_log_true_size);
 	union bpf_attr attr;
 	char *log_buf;
 	size_t log_size;
@@ -1211,8 +1207,6 @@ int bpf_btf_load(const void *btf_data, size_t btf_size, struct bpf_btf_load_opts
 
 	attr.btf = ptr_to_u64(btf_data);
 	attr.btf_size = btf_size;
-	attr.btf_token_fd = OPTS_GET(opts, token_fd, 0);
-
 	/* log_level == 0 and log_buf != NULL means "try loading without
 	 * log_buf, but retry with log_buf and log_level=1 on error", which is
 	 * consistent across low-level and high-level BTF and program loading
@@ -1293,20 +1287,3 @@ int bpf_prog_bind_map(int prog_fd, int map_fd,
 	ret = sys_bpf(BPF_PROG_BIND_MAP, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
-
-int bpf_token_create(int bpffs_fd, struct bpf_token_create_opts *opts)
-{
-	const size_t attr_sz = offsetofend(union bpf_attr, token_create);
-	union bpf_attr attr;
-	int fd;
-
-	if (!OPTS_VALID(opts, bpf_token_create_opts))
-		return libbpf_err(-EINVAL);
-
-	memset(&attr, 0, attr_sz);
-	attr.token_create.bpffs_fd = bpffs_fd;
-	attr.token_create.flags = OPTS_GET(opts, flags, 0);
-
-	fd = sys_bpf_fd(BPF_TOKEN_CREATE, &attr, attr_sz);
-	return libbpf_err_errno(fd);
-}
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 991b86bfe7e4..d0f53772bdc0 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -51,11 +51,8 @@ struct bpf_map_create_opts {
 
 	__u32 numa_node;
 	__u32 map_ifindex;
-
-	__u32 token_fd;
-	size_t :0;
 };
-#define bpf_map_create_opts__last_field token_fd
+#define bpf_map_create_opts__last_field map_ifindex
 
 LIBBPF_API int bpf_map_create(enum bpf_map_type map_type,
 			      const char *map_name,
@@ -105,10 +102,9 @@ struct bpf_prog_load_opts {
 	 * If kernel doesn't support this feature, log_size is left unchanged.
 	 */
 	__u32 log_true_size;
-	__u32 token_fd;
 	size_t :0;
 };
-#define bpf_prog_load_opts__last_field token_fd
+#define bpf_prog_load_opts__last_field log_true_size
 
 LIBBPF_API int bpf_prog_load(enum bpf_prog_type prog_type,
 			     const char *prog_name, const char *license,
@@ -134,10 +130,9 @@ struct bpf_btf_load_opts {
 	 * If kernel doesn't support this feature, log_size is left unchanged.
 	 */
 	__u32 log_true_size;
-	__u32 token_fd;
 	size_t :0;
 };
-#define bpf_btf_load_opts__last_field token_fd
+#define bpf_btf_load_opts__last_field log_true_size
 
 LIBBPF_API int bpf_btf_load(const void *btf_data, size_t btf_size,
 			    struct bpf_btf_load_opts *opts);
@@ -645,30 +640,6 @@ struct bpf_test_run_opts {
 LIBBPF_API int bpf_prog_test_run_opts(int prog_fd,
 				      struct bpf_test_run_opts *opts);
 
-struct bpf_token_create_opts {
-	size_t sz; /* size of this struct for forward/backward compatibility */
-	__u32 flags;
-	size_t :0;
-};
-#define bpf_token_create_opts__last_field flags
-
-/**
- * @brief **bpf_token_create()** creates a new instance of BPF token derived
- * from specified BPF FS mount point.
- *
- * BPF token created with this API can be passed to bpf() syscall for
- * commands like BPF_PROG_LOAD, BPF_MAP_CREATE, etc.
- *
- * @param bpffs_fd FD for BPF FS instance from which to derive a BPF token
- * instance.
- * @param opts optional BPF token creation options, can be NULL
- *
- * @return BPF token FD > 0, on success; negative error code, otherwise (errno
- * is also set to the error code)
- */
-LIBBPF_API int bpf_token_create(int bpffs_fd,
-				struct bpf_token_create_opts *opts);
-
 #ifdef __cplusplus
 } /* extern "C" */
 #endif
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 63033c334320..ee95fd379d4d 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -1317,9 +1317,7 @@ struct btf *btf__parse_split(const char *path, struct btf *base_btf)
 
 static void *btf_get_raw_data(const struct btf *btf, __u32 *size, bool swap_endian);
 
-int btf_load_into_kernel(struct btf *btf,
-			 char *log_buf, size_t log_sz, __u32 log_level,
-			 int token_fd)
+int btf_load_into_kernel(struct btf *btf, char *log_buf, size_t log_sz, __u32 log_level)
 {
 	LIBBPF_OPTS(bpf_btf_load_opts, opts);
 	__u32 buf_sz = 0, raw_size;
@@ -1369,7 +1367,6 @@ retry_load:
 		opts.log_level = log_level;
 	}
 
-	opts.token_fd = token_fd;
 	btf->fd = bpf_btf_load(raw_data, raw_size, &opts);
 	if (btf->fd < 0) {
 		/* time to turn on verbose mode and try again */
@@ -1397,7 +1394,7 @@ done:
 
 int btf__load_into_kernel(struct btf *btf)
 {
-	return btf_load_into_kernel(btf, NULL, 0, 0, 0);
+	return btf_load_into_kernel(btf, NULL, 0, 0);
 }
 
 int btf__fd(const struct btf *btf)
diff --git a/tools/lib/bpf/elf.c b/tools/lib/bpf/elf.c
index c92e02394159..b02faec748a5 100644
--- a/tools/lib/bpf/elf.c
+++ b/tools/lib/bpf/elf.c
@@ -11,6 +11,8 @@
 #include "libbpf_internal.h"
 #include "str_error.h"
 
+#define STRERR_BUFSIZE  128
+
 /* A SHT_GNU_versym section holds 16-bit words. This bit is set if
  * the symbol is hidden and can only be seen when referenced using an
  * explicit version number. This is a GNU extension.
diff --git a/tools/lib/bpf/features.c b/tools/lib/bpf/features.c
deleted file mode 100644
index ce98a334be21..000000000000
--- a/tools/lib/bpf/features.c
+++ /dev/null
@@ -1,478 +0,0 @@
-// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
-/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
-#include <linux/kernel.h>
-#include <linux/filter.h>
-#include "bpf.h"
-#include "libbpf.h"
-#include "libbpf_common.h"
-#include "libbpf_internal.h"
-#include "str_error.h"
-
-static inline __u64 ptr_to_u64(const void *ptr)
-{
-	return (__u64)(unsigned long)ptr;
-}
-
-static int probe_fd(int fd)
-{
-	if (fd >= 0)
-		close(fd);
-	return fd >= 0;
-}
-
-static int probe_kern_prog_name(int token_fd)
-{
-	const size_t attr_sz = offsetofend(union bpf_attr, prog_name);
-	struct bpf_insn insns[] = {
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_EXIT_INSN(),
-	};
-	union bpf_attr attr;
-	int ret;
-
-	memset(&attr, 0, attr_sz);
-	attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
-	attr.license = ptr_to_u64("GPL");
-	attr.insns = ptr_to_u64(insns);
-	attr.insn_cnt = (__u32)ARRAY_SIZE(insns);
-	attr.prog_token_fd = token_fd;
-	libbpf_strlcpy(attr.prog_name, "libbpf_nametest", sizeof(attr.prog_name));
-
-	/* make sure loading with name works */
-	ret = sys_bpf_prog_load(&attr, attr_sz, PROG_LOAD_ATTEMPTS);
-	return probe_fd(ret);
-}
-
-static int probe_kern_global_data(int token_fd)
-{
-	char *cp, errmsg[STRERR_BUFSIZE];
-	struct bpf_insn insns[] = {
-		BPF_LD_MAP_VALUE(BPF_REG_1, 0, 16),
-		BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 42),
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_EXIT_INSN(),
-	};
-	LIBBPF_OPTS(bpf_map_create_opts, map_opts, .token_fd = token_fd);
-	LIBBPF_OPTS(bpf_prog_load_opts, prog_opts, .token_fd = token_fd);
-	int ret, map, insn_cnt = ARRAY_SIZE(insns);
-
-	map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_global", sizeof(int), 32, 1, &map_opts);
-	if (map < 0) {
-		ret = -errno;
-		cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg));
-		pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n",
-			__func__, cp, -ret);
-		return ret;
-	}
-
-	insns[0].imm = map;
-
-	ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, &prog_opts);
-	close(map);
-	return probe_fd(ret);
-}
-
-static int probe_kern_btf(int token_fd)
-{
-	static const char strs[] = "\0int";
-	__u32 types[] = {
-		/* int */
-		BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4),
-	};
-
-	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
-					     strs, sizeof(strs), token_fd));
-}
-
-static int probe_kern_btf_func(int token_fd)
-{
-	static const char strs[] = "\0int\0x\0a";
-	/* void x(int a) {} */
-	__u32 types[] = {
-		/* int */
-		BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
-		/* FUNC_PROTO */                                /* [2] */
-		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0),
-		BTF_PARAM_ENC(7, 1),
-		/* FUNC x */                                    /* [3] */
-		BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), 2),
-	};
-
-	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
-					     strs, sizeof(strs), token_fd));
-}
-
-static int probe_kern_btf_func_global(int token_fd)
-{
-	static const char strs[] = "\0int\0x\0a";
-	/* static void x(int a) {} */
-	__u32 types[] = {
-		/* int */
-		BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
-		/* FUNC_PROTO */                                /* [2] */
-		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0),
-		BTF_PARAM_ENC(7, 1),
-		/* FUNC x BTF_FUNC_GLOBAL */                    /* [3] */
-		BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 2),
-	};
-
-	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
-					     strs, sizeof(strs), token_fd));
-}
-
-static int probe_kern_btf_datasec(int token_fd)
-{
-	static const char strs[] = "\0x\0.data";
-	/* static int a; */
-	__u32 types[] = {
-		/* int */
-		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
-		/* VAR x */                                     /* [2] */
-		BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1),
-		BTF_VAR_STATIC,
-		/* DATASEC val */                               /* [3] */
-		BTF_TYPE_ENC(3, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
-		BTF_VAR_SECINFO_ENC(2, 0, 4),
-	};
-
-	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
-					     strs, sizeof(strs), token_fd));
-}
-
-static int probe_kern_btf_float(int token_fd)
-{
-	static const char strs[] = "\0float";
-	__u32 types[] = {
-		/* float */
-		BTF_TYPE_FLOAT_ENC(1, 4),
-	};
-
-	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
-					     strs, sizeof(strs), token_fd));
-}
-
-static int probe_kern_btf_decl_tag(int token_fd)
-{
-	static const char strs[] = "\0tag";
-	__u32 types[] = {
-		/* int */
-		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
-		/* VAR x */                                     /* [2] */
-		BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1),
-		BTF_VAR_STATIC,
-		/* attr */
-		BTF_TYPE_DECL_TAG_ENC(1, 2, -1),
-	};
-
-	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
-					     strs, sizeof(strs), token_fd));
-}
-
-static int probe_kern_btf_type_tag(int token_fd)
-{
-	static const char strs[] = "\0tag";
-	__u32 types[] = {
-		/* int */
-		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),		/* [1] */
-		/* attr */
-		BTF_TYPE_TYPE_TAG_ENC(1, 1),				/* [2] */
-		/* ptr */
-		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 2),	/* [3] */
-	};
-
-	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
-					     strs, sizeof(strs), token_fd));
-}
-
-static int probe_kern_array_mmap(int token_fd)
-{
-	LIBBPF_OPTS(bpf_map_create_opts, opts,
-		.map_flags = BPF_F_MMAPABLE,
-		.token_fd = token_fd,
-	);
-	int fd;
-
-	fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_mmap", sizeof(int), sizeof(int), 1, &opts);
-	return probe_fd(fd);
-}
-
-static int probe_kern_exp_attach_type(int token_fd)
-{
-	LIBBPF_OPTS(bpf_prog_load_opts, opts,
-		.expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE,
-		.token_fd = token_fd,
-	);
-	struct bpf_insn insns[] = {
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_EXIT_INSN(),
-	};
-	int fd, insn_cnt = ARRAY_SIZE(insns);
-
-	/* use any valid combination of program type and (optional)
-	 * non-zero expected attach type (i.e., not a BPF_CGROUP_INET_INGRESS)
-	 * to see if kernel supports expected_attach_type field for
-	 * BPF_PROG_LOAD command
-	 */
-	fd = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCK, NULL, "GPL", insns, insn_cnt, &opts);
-	return probe_fd(fd);
-}
-
-static int probe_kern_probe_read_kernel(int token_fd)
-{
-	LIBBPF_OPTS(bpf_prog_load_opts, opts, .token_fd = token_fd);
-	struct bpf_insn insns[] = {
-		BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),	/* r1 = r10 (fp) */
-		BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),	/* r1 += -8 */
-		BPF_MOV64_IMM(BPF_REG_2, 8),		/* r2 = 8 */
-		BPF_MOV64_IMM(BPF_REG_3, 0),		/* r3 = 0 */
-		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_probe_read_kernel),
-		BPF_EXIT_INSN(),
-	};
-	int fd, insn_cnt = ARRAY_SIZE(insns);
-
-	fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, &opts);
-	return probe_fd(fd);
-}
-
-static int probe_prog_bind_map(int token_fd)
-{
-	char *cp, errmsg[STRERR_BUFSIZE];
-	struct bpf_insn insns[] = {
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_EXIT_INSN(),
-	};
-	LIBBPF_OPTS(bpf_map_create_opts, map_opts, .token_fd = token_fd);
-	LIBBPF_OPTS(bpf_prog_load_opts, prog_opts, .token_fd = token_fd);
-	int ret, map, prog, insn_cnt = ARRAY_SIZE(insns);
-
-	map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_det_bind", sizeof(int), 32, 1, &map_opts);
-	if (map < 0) {
-		ret = -errno;
-		cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg));
-		pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n",
-			__func__, cp, -ret);
-		return ret;
-	}
-
-	prog = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, &prog_opts);
-	if (prog < 0) {
-		close(map);
-		return 0;
-	}
-
-	ret = bpf_prog_bind_map(prog, map, NULL);
-
-	close(map);
-	close(prog);
-
-	return ret >= 0;
-}
-
-static int probe_module_btf(int token_fd)
-{
-	static const char strs[] = "\0int";
-	__u32 types[] = {
-		/* int */
-		BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4),
-	};
-	struct bpf_btf_info info;
-	__u32 len = sizeof(info);
-	char name[16];
-	int fd, err;
-
-	fd = libbpf__load_raw_btf((char *)types, sizeof(types), strs, sizeof(strs), token_fd);
-	if (fd < 0)
-		return 0; /* BTF not supported at all */
-
-	memset(&info, 0, sizeof(info));
-	info.name = ptr_to_u64(name);
-	info.name_len = sizeof(name);
-
-	/* check that BPF_OBJ_GET_INFO_BY_FD supports specifying name pointer;
-	 * kernel's module BTF support coincides with support for
-	 * name/name_len fields in struct bpf_btf_info.
-	 */
-	err = bpf_btf_get_info_by_fd(fd, &info, &len);
-	close(fd);
-	return !err;
-}
-
-static int probe_perf_link(int token_fd)
-{
-	struct bpf_insn insns[] = {
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_EXIT_INSN(),
-	};
-	LIBBPF_OPTS(bpf_prog_load_opts, opts, .token_fd = token_fd);
-	int prog_fd, link_fd, err;
-
-	prog_fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL",
-				insns, ARRAY_SIZE(insns), &opts);
-	if (prog_fd < 0)
-		return -errno;
-
-	/* use invalid perf_event FD to get EBADF, if link is supported;
-	 * otherwise EINVAL should be returned
-	 */
-	link_fd = bpf_link_create(prog_fd, -1, BPF_PERF_EVENT, NULL);
-	err = -errno; /* close() can clobber errno */
-
-	if (link_fd >= 0)
-		close(link_fd);
-	close(prog_fd);
-
-	return link_fd < 0 && err == -EBADF;
-}
-
-static int probe_uprobe_multi_link(int token_fd)
-{
-	LIBBPF_OPTS(bpf_prog_load_opts, load_opts,
-		.expected_attach_type = BPF_TRACE_UPROBE_MULTI,
-		.token_fd = token_fd,
-	);
-	LIBBPF_OPTS(bpf_link_create_opts, link_opts);
-	struct bpf_insn insns[] = {
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_EXIT_INSN(),
-	};
-	int prog_fd, link_fd, err;
-	unsigned long offset = 0;
-
-	prog_fd = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL",
-				insns, ARRAY_SIZE(insns), &load_opts);
-	if (prog_fd < 0)
-		return -errno;
-
-	/* Creating uprobe in '/' binary should fail with -EBADF. */
-	link_opts.uprobe_multi.path = "/";
-	link_opts.uprobe_multi.offsets = &offset;
-	link_opts.uprobe_multi.cnt = 1;
-
-	link_fd = bpf_link_create(prog_fd, -1, BPF_TRACE_UPROBE_MULTI, &link_opts);
-	err = -errno; /* close() can clobber errno */
-
-	if (link_fd >= 0)
-		close(link_fd);
-	close(prog_fd);
-
-	return link_fd < 0 && err == -EBADF;
-}
-
-static int probe_kern_bpf_cookie(int token_fd)
-{
-	struct bpf_insn insns[] = {
-		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_attach_cookie),
-		BPF_EXIT_INSN(),
-	};
-	LIBBPF_OPTS(bpf_prog_load_opts, opts, .token_fd = token_fd);
-	int ret, insn_cnt = ARRAY_SIZE(insns);
-
-	ret = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, &opts);
-	return probe_fd(ret);
-}
-
-static int probe_kern_btf_enum64(int token_fd)
-{
-	static const char strs[] = "\0enum64";
-	__u32 types[] = {
-		BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 0), 8),
-	};
-
-	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
-					     strs, sizeof(strs), token_fd));
-}
-
-typedef int (*feature_probe_fn)(int /* token_fd */);
-
-static struct kern_feature_cache feature_cache;
-
-static struct kern_feature_desc {
-	const char *desc;
-	feature_probe_fn probe;
-} feature_probes[__FEAT_CNT] = {
-	[FEAT_PROG_NAME] = {
-		"BPF program name", probe_kern_prog_name,
-	},
-	[FEAT_GLOBAL_DATA] = {
-		"global variables", probe_kern_global_data,
-	},
-	[FEAT_BTF] = {
-		"minimal BTF", probe_kern_btf,
-	},
-	[FEAT_BTF_FUNC] = {
-		"BTF functions", probe_kern_btf_func,
-	},
-	[FEAT_BTF_GLOBAL_FUNC] = {
-		"BTF global function", probe_kern_btf_func_global,
-	},
-	[FEAT_BTF_DATASEC] = {
-		"BTF data section and variable", probe_kern_btf_datasec,
-	},
-	[FEAT_ARRAY_MMAP] = {
-		"ARRAY map mmap()", probe_kern_array_mmap,
-	},
-	[FEAT_EXP_ATTACH_TYPE] = {
-		"BPF_PROG_LOAD expected_attach_type attribute",
-		probe_kern_exp_attach_type,
-	},
-	[FEAT_PROBE_READ_KERN] = {
-		"bpf_probe_read_kernel() helper", probe_kern_probe_read_kernel,
-	},
-	[FEAT_PROG_BIND_MAP] = {
-		"BPF_PROG_BIND_MAP support", probe_prog_bind_map,
-	},
-	[FEAT_MODULE_BTF] = {
-		"module BTF support", probe_module_btf,
-	},
-	[FEAT_BTF_FLOAT] = {
-		"BTF_KIND_FLOAT support", probe_kern_btf_float,
-	},
-	[FEAT_PERF_LINK] = {
-		"BPF perf link support", probe_perf_link,
-	},
-	[FEAT_BTF_DECL_TAG] = {
-		"BTF_KIND_DECL_TAG support", probe_kern_btf_decl_tag,
-	},
-	[FEAT_BTF_TYPE_TAG] = {
-		"BTF_KIND_TYPE_TAG support", probe_kern_btf_type_tag,
-	},
-	[FEAT_MEMCG_ACCOUNT] = {
-		"memcg-based memory accounting", probe_memcg_account,
-	},
-	[FEAT_BPF_COOKIE] = {
-		"BPF cookie support", probe_kern_bpf_cookie,
-	},
-	[FEAT_BTF_ENUM64] = {
-		"BTF_KIND_ENUM64 support", probe_kern_btf_enum64,
-	},
-	[FEAT_SYSCALL_WRAPPER] = {
-		"Kernel using syscall wrapper", probe_kern_syscall_wrapper,
-	},
-	[FEAT_UPROBE_MULTI_LINK] = {
-		"BPF multi-uprobe link support", probe_uprobe_multi_link,
-	},
-};
-
-bool feat_supported(struct kern_feature_cache *cache, enum kern_feature_id feat_id)
-{
-	struct kern_feature_desc *feat = &feature_probes[feat_id];
-	int ret;
-
-	/* assume global feature cache, unless custom one is provided */
-	if (!cache)
-		cache = &feature_cache;
-
-	if (READ_ONCE(cache->res[feat_id]) == FEAT_UNKNOWN) {
-		ret = feat->probe(cache->token_fd);
-		if (ret > 0) {
-			WRITE_ONCE(cache->res[feat_id], FEAT_SUPPORTED);
-		} else if (ret == 0) {
-			WRITE_ONCE(cache->res[feat_id], FEAT_MISSING);
-		} else {
-			pr_warn("Detection of kernel %s support failed: %d\n", feat->desc, ret);
-			WRITE_ONCE(cache->res[feat_id], FEAT_MISSING);
-		}
-	}
-
-	return READ_ONCE(cache->res[feat_id]) == FEAT_SUPPORTED;
-}
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 4b5ff9508e18..ac54ebc0629f 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -59,8 +59,6 @@
 #define BPF_FS_MAGIC		0xcafe4a11
 #endif
 
-#define BPF_FS_DEFAULT_PATH "/sys/fs/bpf"
-
 #define BPF_INSN_SZ (sizeof(struct bpf_insn))
 
 /* vsprintf() in __base_pr() uses nonliteral format string. It may break
@@ -695,10 +693,6 @@ struct bpf_object {
 
 	struct usdt_manager *usdt_man;
 
-	struct kern_feature_cache *feat_cache;
-	char *token_path;
-	int token_fd;
-
 	char path[];
 };
 
@@ -2198,7 +2192,7 @@ static int build_map_pin_path(struct bpf_map *map, const char *path)
 	int err;
 
 	if (!path)
-		path = BPF_FS_DEFAULT_PATH;
+		path = "/sys/fs/bpf";
 
 	err = pathname_concat(buf, sizeof(buf), path, bpf_map__name(map));
 	if (err)
@@ -3285,7 +3279,7 @@ skip_exception_cb:
 	} else {
 		/* currently BPF_BTF_LOAD only supports log_level 1 */
 		err = btf_load_into_kernel(kern_btf, obj->log_buf, obj->log_size,
-					   obj->log_level ? 1 : 0, obj->token_fd);
+					   obj->log_level ? 1 : 0);
 	}
 	if (sanitize) {
 		if (!err) {
@@ -4608,63 +4602,6 @@ int bpf_map__set_max_entries(struct bpf_map *map, __u32 max_entries)
 	return 0;
 }
 
-static int bpf_object_prepare_token(struct bpf_object *obj)
-{
-	const char *bpffs_path;
-	int bpffs_fd = -1, token_fd, err;
-	bool mandatory;
-	enum libbpf_print_level level;
-
-	/* token is already set up */
-	if (obj->token_fd > 0)
-		return 0;
-	/* token is explicitly prevented */
-	if (obj->token_fd < 0) {
-		pr_debug("object '%s': token is prevented, skipping...\n", obj->name);
-		/* reset to zero to avoid extra checks during map_create and prog_load steps */
-		obj->token_fd = 0;
-		return 0;
-	}
-
-	mandatory = obj->token_path != NULL;
-	level = mandatory ? LIBBPF_WARN : LIBBPF_DEBUG;
-
-	bpffs_path = obj->token_path ?: BPF_FS_DEFAULT_PATH;
-	bpffs_fd = open(bpffs_path, O_DIRECTORY, O_RDWR);
-	if (bpffs_fd < 0) {
-		err = -errno;
-		__pr(level, "object '%s': failed (%d) to open BPF FS mount at '%s'%s\n",
-		     obj->name, err, bpffs_path,
-		     mandatory ? "" : ", skipping optional step...");
-		return mandatory ? err : 0;
-	}
-
-	token_fd = bpf_token_create(bpffs_fd, 0);
-	close(bpffs_fd);
-	if (token_fd < 0) {
-		if (!mandatory && token_fd == -ENOENT) {
-			pr_debug("object '%s': BPF FS at '%s' doesn't have BPF token delegation set up, skipping...\n",
-				 obj->name, bpffs_path);
-			return 0;
-		}
-		__pr(level, "object '%s': failed (%d) to create BPF token from '%s'%s\n",
-		     obj->name, token_fd, bpffs_path,
-		     mandatory ? "" : ", skipping optional step...");
-		return mandatory ? token_fd : 0;
-	}
-
-	obj->feat_cache = calloc(1, sizeof(*obj->feat_cache));
-	if (!obj->feat_cache) {
-		close(token_fd);
-		return -ENOMEM;
-	}
-
-	obj->token_fd = token_fd;
-	obj->feat_cache->token_fd = token_fd;
-
-	return 0;
-}
-
 static int
 bpf_object__probe_loading(struct bpf_object *obj)
 {
@@ -4674,7 +4611,6 @@ bpf_object__probe_loading(struct bpf_object *obj)
 		BPF_EXIT_INSN(),
 	};
 	int ret, insn_cnt = ARRAY_SIZE(insns);
-	LIBBPF_OPTS(bpf_prog_load_opts, opts, .token_fd = obj->token_fd);
 
 	if (obj->gen_loader)
 		return 0;
@@ -4684,9 +4620,9 @@ bpf_object__probe_loading(struct bpf_object *obj)
 		pr_warn("Failed to bump RLIMIT_MEMLOCK (err = %d), you might need to do it explicitly!\n", ret);
 
 	/* make sure basic loading works */
-	ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, &opts);
+	ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL);
 	if (ret < 0)
-		ret = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, &opts);
+		ret = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, NULL);
 	if (ret < 0) {
 		ret = errno;
 		cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg));
@@ -4701,18 +4637,462 @@ bpf_object__probe_loading(struct bpf_object *obj)
 	return 0;
 }
 
+static int probe_fd(int fd)
+{
+	if (fd >= 0)
+		close(fd);
+	return fd >= 0;
+}
+
+static int probe_kern_prog_name(void)
+{
+	const size_t attr_sz = offsetofend(union bpf_attr, prog_name);
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	union bpf_attr attr;
+	int ret;
+
+	memset(&attr, 0, attr_sz);
+	attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
+	attr.license = ptr_to_u64("GPL");
+	attr.insns = ptr_to_u64(insns);
+	attr.insn_cnt = (__u32)ARRAY_SIZE(insns);
+	libbpf_strlcpy(attr.prog_name, "libbpf_nametest", sizeof(attr.prog_name));
+
+	/* make sure loading with name works */
+	ret = sys_bpf_prog_load(&attr, attr_sz, PROG_LOAD_ATTEMPTS);
+	return probe_fd(ret);
+}
+
+static int probe_kern_global_data(void)
+{
+	char *cp, errmsg[STRERR_BUFSIZE];
+	struct bpf_insn insns[] = {
+		BPF_LD_MAP_VALUE(BPF_REG_1, 0, 16),
+		BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 42),
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	int ret, map, insn_cnt = ARRAY_SIZE(insns);
+
+	map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_global", sizeof(int), 32, 1, NULL);
+	if (map < 0) {
+		ret = -errno;
+		cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg));
+		pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n",
+			__func__, cp, -ret);
+		return ret;
+	}
+
+	insns[0].imm = map;
+
+	ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL);
+	close(map);
+	return probe_fd(ret);
+}
+
+static int probe_kern_btf(void)
+{
+	static const char strs[] = "\0int";
+	__u32 types[] = {
+		/* int */
+		BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4),
+	};
+
+	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
+					     strs, sizeof(strs)));
+}
+
+static int probe_kern_btf_func(void)
+{
+	static const char strs[] = "\0int\0x\0a";
+	/* void x(int a) {} */
+	__u32 types[] = {
+		/* int */
+		BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
+		/* FUNC_PROTO */                                /* [2] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0),
+		BTF_PARAM_ENC(7, 1),
+		/* FUNC x */                                    /* [3] */
+		BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), 2),
+	};
+
+	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
+					     strs, sizeof(strs)));
+}
+
+static int probe_kern_btf_func_global(void)
+{
+	static const char strs[] = "\0int\0x\0a";
+	/* static void x(int a) {} */
+	__u32 types[] = {
+		/* int */
+		BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
+		/* FUNC_PROTO */                                /* [2] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0),
+		BTF_PARAM_ENC(7, 1),
+		/* FUNC x BTF_FUNC_GLOBAL */                    /* [3] */
+		BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 2),
+	};
+
+	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
+					     strs, sizeof(strs)));
+}
+
+static int probe_kern_btf_datasec(void)
+{
+	static const char strs[] = "\0x\0.data";
+	/* static int a; */
+	__u32 types[] = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
+		/* VAR x */                                     /* [2] */
+		BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1),
+		BTF_VAR_STATIC,
+		/* DATASEC val */                               /* [3] */
+		BTF_TYPE_ENC(3, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
+		BTF_VAR_SECINFO_ENC(2, 0, 4),
+	};
+
+	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
+					     strs, sizeof(strs)));
+}
+
+static int probe_kern_btf_float(void)
+{
+	static const char strs[] = "\0float";
+	__u32 types[] = {
+		/* float */
+		BTF_TYPE_FLOAT_ENC(1, 4),
+	};
+
+	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
+					     strs, sizeof(strs)));
+}
+
+static int probe_kern_btf_decl_tag(void)
+{
+	static const char strs[] = "\0tag";
+	__u32 types[] = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
+		/* VAR x */                                     /* [2] */
+		BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1),
+		BTF_VAR_STATIC,
+		/* attr */
+		BTF_TYPE_DECL_TAG_ENC(1, 2, -1),
+	};
+
+	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
+					     strs, sizeof(strs)));
+}
+
+static int probe_kern_btf_type_tag(void)
+{
+	static const char strs[] = "\0tag";
+	__u32 types[] = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),		/* [1] */
+		/* attr */
+		BTF_TYPE_TYPE_TAG_ENC(1, 1),				/* [2] */
+		/* ptr */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 2),	/* [3] */
+	};
+
+	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
+					     strs, sizeof(strs)));
+}
+
+static int probe_kern_array_mmap(void)
+{
+	LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_MMAPABLE);
+	int fd;
+
+	fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_mmap", sizeof(int), sizeof(int), 1, &opts);
+	return probe_fd(fd);
+}
+
+static int probe_kern_exp_attach_type(void)
+{
+	LIBBPF_OPTS(bpf_prog_load_opts, opts, .expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE);
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	int fd, insn_cnt = ARRAY_SIZE(insns);
+
+	/* use any valid combination of program type and (optional)
+	 * non-zero expected attach type (i.e., not a BPF_CGROUP_INET_INGRESS)
+	 * to see if kernel supports expected_attach_type field for
+	 * BPF_PROG_LOAD command
+	 */
+	fd = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCK, NULL, "GPL", insns, insn_cnt, &opts);
+	return probe_fd(fd);
+}
+
+static int probe_kern_probe_read_kernel(void)
+{
+	struct bpf_insn insns[] = {
+		BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),	/* r1 = r10 (fp) */
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),	/* r1 += -8 */
+		BPF_MOV64_IMM(BPF_REG_2, 8),		/* r2 = 8 */
+		BPF_MOV64_IMM(BPF_REG_3, 0),		/* r3 = 0 */
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_probe_read_kernel),
+		BPF_EXIT_INSN(),
+	};
+	int fd, insn_cnt = ARRAY_SIZE(insns);
+
+	fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, NULL);
+	return probe_fd(fd);
+}
+
+static int probe_prog_bind_map(void)
+{
+	char *cp, errmsg[STRERR_BUFSIZE];
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	int ret, map, prog, insn_cnt = ARRAY_SIZE(insns);
+
+	map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_det_bind", sizeof(int), 32, 1, NULL);
+	if (map < 0) {
+		ret = -errno;
+		cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg));
+		pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n",
+			__func__, cp, -ret);
+		return ret;
+	}
+
+	prog = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL);
+	if (prog < 0) {
+		close(map);
+		return 0;
+	}
+
+	ret = bpf_prog_bind_map(prog, map, NULL);
+
+	close(map);
+	close(prog);
+
+	return ret >= 0;
+}
+
+static int probe_module_btf(void)
+{
+	static const char strs[] = "\0int";
+	__u32 types[] = {
+		/* int */
+		BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4),
+	};
+	struct bpf_btf_info info;
+	__u32 len = sizeof(info);
+	char name[16];
+	int fd, err;
+
+	fd = libbpf__load_raw_btf((char *)types, sizeof(types), strs, sizeof(strs));
+	if (fd < 0)
+		return 0; /* BTF not supported at all */
+
+	memset(&info, 0, sizeof(info));
+	info.name = ptr_to_u64(name);
+	info.name_len = sizeof(name);
+
+	/* check that BPF_OBJ_GET_INFO_BY_FD supports specifying name pointer;
+	 * kernel's module BTF support coincides with support for
+	 * name/name_len fields in struct bpf_btf_info.
+	 */
+	err = bpf_btf_get_info_by_fd(fd, &info, &len);
+	close(fd);
+	return !err;
+}
+
+static int probe_perf_link(void)
+{
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	int prog_fd, link_fd, err;
+
+	prog_fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL",
+				insns, ARRAY_SIZE(insns), NULL);
+	if (prog_fd < 0)
+		return -errno;
+
+	/* use invalid perf_event FD to get EBADF, if link is supported;
+	 * otherwise EINVAL should be returned
+	 */
+	link_fd = bpf_link_create(prog_fd, -1, BPF_PERF_EVENT, NULL);
+	err = -errno; /* close() can clobber errno */
+
+	if (link_fd >= 0)
+		close(link_fd);
+	close(prog_fd);
+
+	return link_fd < 0 && err == -EBADF;
+}
+
+static int probe_uprobe_multi_link(void)
+{
+	LIBBPF_OPTS(bpf_prog_load_opts, load_opts,
+		.expected_attach_type = BPF_TRACE_UPROBE_MULTI,
+	);
+	LIBBPF_OPTS(bpf_link_create_opts, link_opts);
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	int prog_fd, link_fd, err;
+	unsigned long offset = 0;
+
+	prog_fd = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL",
+				insns, ARRAY_SIZE(insns), &load_opts);
+	if (prog_fd < 0)
+		return -errno;
+
+	/* Creating uprobe in '/' binary should fail with -EBADF. */
+	link_opts.uprobe_multi.path = "/";
+	link_opts.uprobe_multi.offsets = &offset;
+	link_opts.uprobe_multi.cnt = 1;
+
+	link_fd = bpf_link_create(prog_fd, -1, BPF_TRACE_UPROBE_MULTI, &link_opts);
+	err = -errno; /* close() can clobber errno */
+
+	if (link_fd >= 0)
+		close(link_fd);
+	close(prog_fd);
+
+	return link_fd < 0 && err == -EBADF;
+}
+
+static int probe_kern_bpf_cookie(void)
+{
+	struct bpf_insn insns[] = {
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_attach_cookie),
+		BPF_EXIT_INSN(),
+	};
+	int ret, insn_cnt = ARRAY_SIZE(insns);
+
+	ret = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL", insns, insn_cnt, NULL);
+	return probe_fd(ret);
+}
+
+static int probe_kern_btf_enum64(void)
+{
+	static const char strs[] = "\0enum64";
+	__u32 types[] = {
+		BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 0), 8),
+	};
+
+	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
+					     strs, sizeof(strs)));
+}
+
+static int probe_kern_syscall_wrapper(void);
+
+enum kern_feature_result {
+	FEAT_UNKNOWN = 0,
+	FEAT_SUPPORTED = 1,
+	FEAT_MISSING = 2,
+};
+
+typedef int (*feature_probe_fn)(void);
+
+static struct kern_feature_desc {
+	const char *desc;
+	feature_probe_fn probe;
+	enum kern_feature_result res;
+} feature_probes[__FEAT_CNT] = {
+	[FEAT_PROG_NAME] = {
+		"BPF program name", probe_kern_prog_name,
+	},
+	[FEAT_GLOBAL_DATA] = {
+		"global variables", probe_kern_global_data,
+	},
+	[FEAT_BTF] = {
+		"minimal BTF", probe_kern_btf,
+	},
+	[FEAT_BTF_FUNC] = {
+		"BTF functions", probe_kern_btf_func,
+	},
+	[FEAT_BTF_GLOBAL_FUNC] = {
+		"BTF global function", probe_kern_btf_func_global,
+	},
+	[FEAT_BTF_DATASEC] = {
+		"BTF data section and variable", probe_kern_btf_datasec,
+	},
+	[FEAT_ARRAY_MMAP] = {
+		"ARRAY map mmap()", probe_kern_array_mmap,
+	},
+	[FEAT_EXP_ATTACH_TYPE] = {
+		"BPF_PROG_LOAD expected_attach_type attribute",
+		probe_kern_exp_attach_type,
+	},
+	[FEAT_PROBE_READ_KERN] = {
+		"bpf_probe_read_kernel() helper", probe_kern_probe_read_kernel,
+	},
+	[FEAT_PROG_BIND_MAP] = {
+		"BPF_PROG_BIND_MAP support", probe_prog_bind_map,
+	},
+	[FEAT_MODULE_BTF] = {
+		"module BTF support", probe_module_btf,
+	},
+	[FEAT_BTF_FLOAT] = {
+		"BTF_KIND_FLOAT support", probe_kern_btf_float,
+	},
+	[FEAT_PERF_LINK] = {
+		"BPF perf link support", probe_perf_link,
+	},
+	[FEAT_BTF_DECL_TAG] = {
+		"BTF_KIND_DECL_TAG support", probe_kern_btf_decl_tag,
+	},
+	[FEAT_BTF_TYPE_TAG] = {
+		"BTF_KIND_TYPE_TAG support", probe_kern_btf_type_tag,
+	},
+	[FEAT_MEMCG_ACCOUNT] = {
+		"memcg-based memory accounting", probe_memcg_account,
+	},
+	[FEAT_BPF_COOKIE] = {
+		"BPF cookie support", probe_kern_bpf_cookie,
+	},
+	[FEAT_BTF_ENUM64] = {
+		"BTF_KIND_ENUM64 support", probe_kern_btf_enum64,
+	},
+	[FEAT_SYSCALL_WRAPPER] = {
+		"Kernel using syscall wrapper", probe_kern_syscall_wrapper,
+	},
+	[FEAT_UPROBE_MULTI_LINK] = {
+		"BPF multi-uprobe link support", probe_uprobe_multi_link,
+	},
+};
+
 bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id)
 {
+	struct kern_feature_desc *feat = &feature_probes[feat_id];
+	int ret;
+
 	if (obj && obj->gen_loader)
 		/* To generate loader program assume the latest kernel
 		 * to avoid doing extra prog_load, map_create syscalls.
 		 */
 		return true;
 
-	if (obj->token_fd)
-		return feat_supported(obj->feat_cache, feat_id);
+	if (READ_ONCE(feat->res) == FEAT_UNKNOWN) {
+		ret = feat->probe();
+		if (ret > 0) {
+			WRITE_ONCE(feat->res, FEAT_SUPPORTED);
+		} else if (ret == 0) {
+			WRITE_ONCE(feat->res, FEAT_MISSING);
+		} else {
+			pr_warn("Detection of kernel %s support failed: %d\n", feat->desc, ret);
+			WRITE_ONCE(feat->res, FEAT_MISSING);
+		}
+	}
 
-	return feat_supported(NULL, feat_id);
+	return READ_ONCE(feat->res) == FEAT_SUPPORTED;
 }
 
 static bool map_is_reuse_compat(const struct bpf_map *map, int map_fd)
@@ -4831,7 +5211,6 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
 	create_attr.map_flags = def->map_flags;
 	create_attr.numa_node = map->numa_node;
 	create_attr.map_extra = map->map_extra;
-	create_attr.token_fd = obj->token_fd;
 
 	if (bpf_map__is_struct_ops(map))
 		create_attr.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id;
@@ -6667,7 +7046,6 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog
 	load_attr.attach_btf_id = prog->attach_btf_id;
 	load_attr.kern_version = kern_version;
 	load_attr.prog_ifindex = prog->prog_ifindex;
-	load_attr.token_fd = obj->token_fd;
 
 	/* specify func_info/line_info only if kernel supports them */
 	btf_fd = bpf_object__btf_fd(obj);
@@ -7129,10 +7507,10 @@ static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object
 static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf, size_t obj_buf_sz,
 					  const struct bpf_object_open_opts *opts)
 {
-	const char *obj_name, *kconfig, *btf_tmp_path, *token_path;
+	const char *obj_name, *kconfig, *btf_tmp_path;
 	struct bpf_object *obj;
 	char tmp_name[64];
-	int err, token_fd;
+	int err;
 	char *log_buf;
 	size_t log_size;
 	__u32 log_level;
@@ -7166,28 +7544,6 @@ static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf,
 	if (log_size && !log_buf)
 		return ERR_PTR(-EINVAL);
 
-	token_path = OPTS_GET(opts, bpf_token_path, NULL);
-	token_fd = OPTS_GET(opts, bpf_token_fd, -1);
-	/* non-empty token path can't be combined with invalid token FD */
-	if (token_path && token_path[0] != '\0' && token_fd < 0)
-		return ERR_PTR(-EINVAL);
-	/* empty token path can't be combined with valid token FD */
-	if (token_path && token_path[0] == '\0' && token_fd > 0)
-		return ERR_PTR(-EINVAL);
-	/* if user didn't specify bpf_token_path/bpf_token_fd explicitly,
-	 * check if LIBBPF_BPF_TOKEN_PATH envvar was set and treat it as
-	 * bpf_token_path option
-	 */
-	if (token_fd == 0 && !token_path)
-		token_path = getenv("LIBBPF_BPF_TOKEN_PATH");
-	/* empty token_path is equivalent to invalid token_fd */
-	if (token_path && token_path[0] == '\0') {
-		token_path = NULL;
-		token_fd = -1;
-	}
-	if (token_path && strlen(token_path) >= PATH_MAX)
-		return ERR_PTR(-ENAMETOOLONG);
-
 	obj = bpf_object__new(path, obj_buf, obj_buf_sz, obj_name);
 	if (IS_ERR(obj))
 		return obj;
@@ -7196,19 +7552,6 @@ static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf,
 	obj->log_size = log_size;
 	obj->log_level = log_level;
 
-	obj->token_fd = token_fd <= 0 ? token_fd : dup_good_fd(token_fd);
-	if (token_fd > 0 && obj->token_fd < 0) {
-		err = -errno;
-		goto out;
-	}
-	if (token_path) {
-		obj->token_path = strdup(token_path);
-		if (!obj->token_path) {
-			err = -ENOMEM;
-			goto out;
-		}
-	}
-
 	btf_tmp_path = OPTS_GET(opts, btf_custom_path, NULL);
 	if (btf_tmp_path) {
 		if (strlen(btf_tmp_path) >= PATH_MAX) {
@@ -7719,8 +8062,7 @@ static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const ch
 	if (obj->gen_loader)
 		bpf_gen__init(obj->gen_loader, extra_log_level, obj->nr_programs, obj->nr_maps);
 
-	err = bpf_object_prepare_token(obj);
-	err = err ? : bpf_object__probe_loading(obj);
+	err = bpf_object__probe_loading(obj);
 	err = err ? : bpf_object__load_vmlinux_btf(obj, false);
 	err = err ? : bpf_object__resolve_externs(obj, obj->kconfig);
 	err = err ? : bpf_object__sanitize_and_load_btf(obj);
@@ -8257,11 +8599,6 @@ void bpf_object__close(struct bpf_object *obj)
 	}
 	zfree(&obj->programs);
 
-	zfree(&obj->feat_cache);
-	zfree(&obj->token_path);
-	if (obj->token_fd > 0)
-		close(obj->token_fd);
-
 	free(obj);
 }
 
@@ -10275,7 +10612,7 @@ static const char *arch_specific_syscall_pfx(void)
 #endif
 }
 
-int probe_kern_syscall_wrapper(int token_fd)
+static int probe_kern_syscall_wrapper(void)
 {
 	char syscall_name[64];
 	const char *ksys_pfx;
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 916904bd2a7a..6cd9c501624f 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -177,45 +177,10 @@ struct bpf_object_open_opts {
 	 * logs through its print callback.
 	 */
 	__u32 kernel_log_level;
-	/* FD of a BPF token instantiated by user through bpf_token_create()
-	 * API. BPF object will keep dup()'ed FD internally, so passed token
-	 * FD can be closed after BPF object/skeleton open step.
-	 *
-	 * Setting bpf_token_fd to negative value disables libbpf's automatic
-	 * attempt to create BPF token from default BPF FS mount point
-	 * (/sys/fs/bpf), in case this default behavior is undesirable.
-	 *
-	 * If bpf_token_path and bpf_token_fd are not specified, libbpf will
-	 * consult LIBBPF_BPF_TOKEN_PATH environment variable. If set, it will
-	 * be taken as a value of bpf_token_path option and will force libbpf
-	 * to either create BPF token from provided custom BPF FS path, or
-	 * will disable implicit BPF token creation, if envvar value is an
-	 * empty string.
-	 *
-	 * bpf_token_path and bpf_token_fd are mutually exclusive and only one
-	 * of those options should be set. Either of them overrides
-	 * LIBBPF_BPF_TOKEN_PATH envvar.
-	 */
-	int bpf_token_fd;
-	/* Path to BPF FS mount point to derive BPF token from.
-	 *
-	 * Created BPF token will be used for all bpf() syscall operations
-	 * that accept BPF token (e.g., map creation, BTF and program loads,
-	 * etc) automatically within instantiated BPF object.
-	 *
-	 * Setting bpf_token_path option to empty string disables libbpf's
-	 * automatic attempt to create BPF token from default BPF FS mount
-	 * point (/sys/fs/bpf), in case this default behavior is undesirable.
-	 *
-	 * bpf_token_path and bpf_token_fd are mutually exclusive and only one
-	 * of those options should be set. Either of them overrides
-	 * LIBBPF_BPF_TOKEN_PATH envvar.
-	 */
-	const char *bpf_token_path;
 
 	size_t :0;
 };
-#define bpf_object_open_opts__last_field bpf_token_path
+#define bpf_object_open_opts__last_field kernel_log_level
 
 /**
  * @brief **bpf_object__open()** creates a bpf_object by opening
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index df7657b65c47..91c5aef7dae7 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -401,7 +401,6 @@ LIBBPF_1.3.0 {
 		bpf_program__attach_netkit;
 		bpf_program__attach_tcx;
 		bpf_program__attach_uprobe_multi;
-		bpf_token_create;
 		ring__avail_data_size;
 		ring__consume;
 		ring__consumer_pos;
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index 4cda32298c49..b5d334754e5d 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -360,32 +360,15 @@ enum kern_feature_id {
 	__FEAT_CNT,
 };
 
-enum kern_feature_result {
-	FEAT_UNKNOWN = 0,
-	FEAT_SUPPORTED = 1,
-	FEAT_MISSING = 2,
-};
-
-struct kern_feature_cache {
-	enum kern_feature_result res[__FEAT_CNT];
-	int token_fd;
-};
-
-bool feat_supported(struct kern_feature_cache *cache, enum kern_feature_id feat_id);
+int probe_memcg_account(void);
 bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id);
-
-int probe_kern_syscall_wrapper(int token_fd);
-int probe_memcg_account(int token_fd);
 int bump_rlimit_memlock(void);
 
 int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz);
 int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz);
 int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
-			 const char *str_sec, size_t str_len,
-			 int token_fd);
-int btf_load_into_kernel(struct btf *btf,
-			 char *log_buf, size_t log_sz, __u32 log_level,
-			 int token_fd);
+			 const char *str_sec, size_t str_len);
+int btf_load_into_kernel(struct btf *btf, char *log_buf, size_t log_sz, __u32 log_level);
 
 struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf);
 void btf_get_kernel_prefix_kind(enum bpf_attach_type attach_type,
@@ -549,17 +532,6 @@ static inline bool is_ldimm64_insn(struct bpf_insn *insn)
 	return insn->code == (BPF_LD | BPF_IMM | BPF_DW);
 }
 
-/* Unconditionally dup FD, ensuring it doesn't use [0, 2] range.
- * Original FD is not closed or altered in any other way.
- * Preserves original FD value, if it's invalid (negative).
- */
-static inline int dup_good_fd(int fd)
-{
-	if (fd < 0)
-		return fd;
-	return fcntl(fd, F_DUPFD_CLOEXEC, 3);
-}
-
 /* if fd is stdin, stdout, or stderr, dup to a fd greater than 2
  * Takes ownership of the fd passed in, and closes it if calling
  * fcntl(fd, F_DUPFD_CLOEXEC, 3).
@@ -571,7 +543,7 @@ static inline int ensure_good_fd(int fd)
 	if (fd < 0)
 		return fd;
 	if (fd < 3) {
-		fd = dup_good_fd(fd);
+		fd = fcntl(fd, F_DUPFD_CLOEXEC, 3);
 		saved_errno = errno;
 		close(old_fd);
 		errno = saved_errno;
diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c
index 8e7437006639..9c4db90b92b6 100644
--- a/tools/lib/bpf/libbpf_probes.c
+++ b/tools/lib/bpf/libbpf_probes.c
@@ -219,8 +219,7 @@ int libbpf_probe_bpf_prog_type(enum bpf_prog_type prog_type, const void *opts)
 }
 
 int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
-			 const char *str_sec, size_t str_len,
-			 int token_fd)
+			 const char *str_sec, size_t str_len)
 {
 	struct btf_header hdr = {
 		.magic = BTF_MAGIC,
@@ -230,7 +229,6 @@ int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
 		.str_off = types_len,
 		.str_len = str_len,
 	};
-	LIBBPF_OPTS(bpf_btf_load_opts, opts, .token_fd = token_fd);
 	int btf_fd, btf_len;
 	__u8 *raw_btf;
 
@@ -243,7 +241,7 @@ int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
 	memcpy(raw_btf + hdr.hdr_len, raw_types, hdr.type_len);
 	memcpy(raw_btf + hdr.hdr_len + hdr.type_len, str_sec, hdr.str_len);
 
-	btf_fd = bpf_btf_load(raw_btf, btf_len, &opts);
+	btf_fd = bpf_btf_load(raw_btf, btf_len, NULL);
 
 	free(raw_btf);
 	return btf_fd;
@@ -273,7 +271,7 @@ static int load_local_storage_btf(void)
 	};
 
 	return libbpf__load_raw_btf((char *)types, sizeof(types),
-				     strs, sizeof(strs), 0);
+				     strs, sizeof(strs));
 }
 
 static int probe_map_create(enum bpf_map_type map_type)
diff --git a/tools/lib/bpf/str_error.h b/tools/lib/bpf/str_error.h
index 626d7ffb03d6..a139334d57b6 100644
--- a/tools/lib/bpf/str_error.h
+++ b/tools/lib/bpf/str_error.h
@@ -2,8 +2,5 @@
 #ifndef __LIBBPF_STR_ERROR_H
 #define __LIBBPF_STR_ERROR_H
 
-#define STRERR_BUFSIZE  128
-
 char *libbpf_strerror_r(int err, char *dst, int len);
-
 #endif /* __LIBBPF_STR_ERROR_H */
diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c
index 4ed46ed58a7b..9f766ddd946a 100644
--- a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c
+++ b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c
@@ -30,8 +30,6 @@ void test_libbpf_probe_prog_types(void)
 
 		if (prog_type == BPF_PROG_TYPE_UNSPEC)
 			continue;
-		if (strcmp(prog_type_name, "__MAX_BPF_PROG_TYPE") == 0)
-			continue;
 
 		if (!test__start_subtest(prog_type_name))
 			continue;
@@ -70,8 +68,6 @@ void test_libbpf_probe_map_types(void)
 
 		if (map_type == BPF_MAP_TYPE_UNSPEC)
 			continue;
-		if (strcmp(map_type_name, "__MAX_BPF_MAP_TYPE") == 0)
-			continue;
 
 		if (!test__start_subtest(map_type_name))
 			continue;
diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c
index 62ea855ec4d0..eb34d612d6f8 100644
--- a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c
+++ b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c
@@ -132,9 +132,6 @@ static void test_libbpf_bpf_map_type_str(void)
 		const char *map_type_str;
 		char buf[256];
 
-		if (map_type == __MAX_BPF_MAP_TYPE)
-			continue;
-
 		map_type_name = btf__str_by_offset(btf, e->name_off);
 		map_type_str = libbpf_bpf_map_type_str(map_type);
 		ASSERT_OK_PTR(map_type_str, map_type_name);
@@ -189,9 +186,6 @@ static void test_libbpf_bpf_prog_type_str(void)
 		const char *prog_type_str;
 		char buf[256];
 
-		if (prog_type == __MAX_BPF_PROG_TYPE)
-			continue;
-
 		prog_type_name = btf__str_by_offset(btf, e->name_off);
 		prog_type_str = libbpf_bpf_prog_type_str(prog_type);
 		ASSERT_OK_PTR(prog_type_str, prog_type_name);
diff --git a/tools/testing/selftests/bpf/prog_tests/token.c b/tools/testing/selftests/bpf/prog_tests/token.c
deleted file mode 100644
index b5dce630e0e1..000000000000
--- a/tools/testing/selftests/bpf/prog_tests/token.c
+++ /dev/null
@@ -1,1031 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
-#define _GNU_SOURCE
-#include <test_progs.h>
-#include <bpf/btf.h>
-#include "cap_helpers.h"
-#include <fcntl.h>
-#include <sched.h>
-#include <signal.h>
-#include <unistd.h>
-#include <linux/filter.h>
-#include <linux/unistd.h>
-#include <linux/mount.h>
-#include <sys/socket.h>
-#include <sys/stat.h>
-#include <sys/syscall.h>
-#include <sys/un.h>
-#include "priv_map.skel.h"
-#include "priv_prog.skel.h"
-#include "dummy_st_ops_success.skel.h"
-
-static inline int sys_mount(const char *dev_name, const char *dir_name,
-			    const char *type, unsigned long flags,
-			    const void *data)
-{
-	return syscall(__NR_mount, dev_name, dir_name, type, flags, data);
-}
-
-static inline int sys_fsopen(const char *fsname, unsigned flags)
-{
-	return syscall(__NR_fsopen, fsname, flags);
-}
-
-static inline int sys_fspick(int dfd, const char *path, unsigned flags)
-{
-	return syscall(__NR_fspick, dfd, path, flags);
-}
-
-static inline int sys_fsconfig(int fs_fd, unsigned cmd, const char *key, const void *val, int aux)
-{
-	return syscall(__NR_fsconfig, fs_fd, cmd, key, val, aux);
-}
-
-static inline int sys_fsmount(int fs_fd, unsigned flags, unsigned ms_flags)
-{
-	return syscall(__NR_fsmount, fs_fd, flags, ms_flags);
-}
-
-static inline int sys_move_mount(int from_dfd, const char *from_path,
-				 int to_dfd, const char *to_path,
-				 unsigned flags)
-{
-	return syscall(__NR_move_mount, from_dfd, from_path, to_dfd, to_path, flags);
-}
-
-static int drop_priv_caps(__u64 *old_caps)
-{
-	return cap_disable_effective((1ULL << CAP_BPF) |
-				     (1ULL << CAP_PERFMON) |
-				     (1ULL << CAP_NET_ADMIN) |
-				     (1ULL << CAP_SYS_ADMIN), old_caps);
-}
-
-static int restore_priv_caps(__u64 old_caps)
-{
-	return cap_enable_effective(old_caps, NULL);
-}
-
-static int set_delegate_mask(int fs_fd, const char *key, __u64 mask, const char *mask_str)
-{
-	char buf[32];
-	int err;
-
-	if (!mask_str) {
-		if (mask == ~0ULL) {
-			mask_str = "any";
-		} else {
-			snprintf(buf, sizeof(buf), "0x%llx", (unsigned long long)mask);
-			mask_str = buf;
-		}
-	}
-
-	err = sys_fsconfig(fs_fd, FSCONFIG_SET_STRING, key,
-			   mask_str, 0);
-	if (err < 0)
-		err = -errno;
-	return err;
-}
-
-#define zclose(fd) do { if (fd >= 0) close(fd); fd = -1; } while (0)
-
-struct bpffs_opts {
-	__u64 cmds;
-	__u64 maps;
-	__u64 progs;
-	__u64 attachs;
-	const char *cmds_str;
-	const char *maps_str;
-	const char *progs_str;
-	const char *attachs_str;
-};
-
-static int create_bpffs_fd(void)
-{
-	int fs_fd;
-
-	/* create VFS context */
-	fs_fd = sys_fsopen("bpf", 0);
-	ASSERT_GE(fs_fd, 0, "fs_fd");
-
-	return fs_fd;
-}
-
-static int materialize_bpffs_fd(int fs_fd, struct bpffs_opts *opts)
-{
-	int mnt_fd, err;
-
-	/* set up token delegation mount options */
-	err = set_delegate_mask(fs_fd, "delegate_cmds", opts->cmds, opts->cmds_str);
-	if (!ASSERT_OK(err, "fs_cfg_cmds"))
-		return err;
-	err = set_delegate_mask(fs_fd, "delegate_maps", opts->maps, opts->maps_str);
-	if (!ASSERT_OK(err, "fs_cfg_maps"))
-		return err;
-	err = set_delegate_mask(fs_fd, "delegate_progs", opts->progs, opts->progs_str);
-	if (!ASSERT_OK(err, "fs_cfg_progs"))
-		return err;
-	err = set_delegate_mask(fs_fd, "delegate_attachs", opts->attachs, opts->attachs_str);
-	if (!ASSERT_OK(err, "fs_cfg_attachs"))
-		return err;
-
-	/* instantiate FS object */
-	err = sys_fsconfig(fs_fd, FSCONFIG_CMD_CREATE, NULL, NULL, 0);
-	if (err < 0)
-		return -errno;
-
-	/* create O_PATH fd for detached mount */
-	mnt_fd = sys_fsmount(fs_fd, 0, 0);
-	if (err < 0)
-		return -errno;
-
-	return mnt_fd;
-}
-
-/* send FD over Unix domain (AF_UNIX) socket */
-static int sendfd(int sockfd, int fd)
-{
-	struct msghdr msg = {};
-	struct cmsghdr *cmsg;
-	int fds[1] = { fd }, err;
-	char iobuf[1];
-	struct iovec io = {
-		.iov_base = iobuf,
-		.iov_len = sizeof(iobuf),
-	};
-	union {
-		char buf[CMSG_SPACE(sizeof(fds))];
-		struct cmsghdr align;
-	} u;
-
-	msg.msg_iov = &io;
-	msg.msg_iovlen = 1;
-	msg.msg_control = u.buf;
-	msg.msg_controllen = sizeof(u.buf);
-	cmsg = CMSG_FIRSTHDR(&msg);
-	cmsg->cmsg_level = SOL_SOCKET;
-	cmsg->cmsg_type = SCM_RIGHTS;
-	cmsg->cmsg_len = CMSG_LEN(sizeof(fds));
-	memcpy(CMSG_DATA(cmsg), fds, sizeof(fds));
-
-	err = sendmsg(sockfd, &msg, 0);
-	if (err < 0)
-		err = -errno;
-	if (!ASSERT_EQ(err, 1, "sendmsg"))
-		return -EINVAL;
-
-	return 0;
-}
-
-/* receive FD over Unix domain (AF_UNIX) socket */
-static int recvfd(int sockfd, int *fd)
-{
-	struct msghdr msg = {};
-	struct cmsghdr *cmsg;
-	int fds[1], err;
-	char iobuf[1];
-	struct iovec io = {
-		.iov_base = iobuf,
-		.iov_len = sizeof(iobuf),
-	};
-	union {
-		char buf[CMSG_SPACE(sizeof(fds))];
-		struct cmsghdr align;
-	} u;
-
-	msg.msg_iov = &io;
-	msg.msg_iovlen = 1;
-	msg.msg_control = u.buf;
-	msg.msg_controllen = sizeof(u.buf);
-
-	err = recvmsg(sockfd, &msg, 0);
-	if (err < 0)
-		err = -errno;
-	if (!ASSERT_EQ(err, 1, "recvmsg"))
-		return -EINVAL;
-
-	cmsg = CMSG_FIRSTHDR(&msg);
-	if (!ASSERT_OK_PTR(cmsg, "cmsg_null") ||
-	    !ASSERT_EQ(cmsg->cmsg_len, CMSG_LEN(sizeof(fds)), "cmsg_len") ||
-	    !ASSERT_EQ(cmsg->cmsg_level, SOL_SOCKET, "cmsg_level") ||
-	    !ASSERT_EQ(cmsg->cmsg_type, SCM_RIGHTS, "cmsg_type"))
-		return -EINVAL;
-
-	memcpy(fds, CMSG_DATA(cmsg), sizeof(fds));
-	*fd = fds[0];
-
-	return 0;
-}
-
-static ssize_t write_nointr(int fd, const void *buf, size_t count)
-{
-	ssize_t ret;
-
-	do {
-		ret = write(fd, buf, count);
-	} while (ret < 0 && errno == EINTR);
-
-	return ret;
-}
-
-static int write_file(const char *path, const void *buf, size_t count)
-{
-	int fd;
-	ssize_t ret;
-
-	fd = open(path, O_WRONLY | O_CLOEXEC | O_NOCTTY | O_NOFOLLOW);
-	if (fd < 0)
-		return -1;
-
-	ret = write_nointr(fd, buf, count);
-	close(fd);
-	if (ret < 0 || (size_t)ret != count)
-		return -1;
-
-	return 0;
-}
-
-static int create_and_enter_userns(void)
-{
-	uid_t uid;
-	gid_t gid;
-	char map[100];
-
-	uid = getuid();
-	gid = getgid();
-
-	if (unshare(CLONE_NEWUSER))
-		return -1;
-
-	if (write_file("/proc/self/setgroups", "deny", sizeof("deny") - 1) &&
-	    errno != ENOENT)
-		return -1;
-
-	snprintf(map, sizeof(map), "0 %d 1", uid);
-	if (write_file("/proc/self/uid_map", map, strlen(map)))
-		return -1;
-
-
-	snprintf(map, sizeof(map), "0 %d 1", gid);
-	if (write_file("/proc/self/gid_map", map, strlen(map)))
-		return -1;
-
-	if (setgid(0))
-		return -1;
-
-	if (setuid(0))
-		return -1;
-
-	return 0;
-}
-
-typedef int (*child_callback_fn)(int);
-
-static void child(int sock_fd, struct bpffs_opts *opts, child_callback_fn callback)
-{
-	LIBBPF_OPTS(bpf_map_create_opts, map_opts);
-	int mnt_fd = -1, fs_fd = -1, err = 0, bpffs_fd = -1;
-
-	/* setup userns with root mappings */
-	err = create_and_enter_userns();
-	if (!ASSERT_OK(err, "create_and_enter_userns"))
-		goto cleanup;
-
-	/* setup mountns to allow creating BPF FS (fsopen("bpf")) from unpriv process */
-	err = unshare(CLONE_NEWNS);
-	if (!ASSERT_OK(err, "create_mountns"))
-		goto cleanup;
-
-	err = sys_mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, 0);
-	if (!ASSERT_OK(err, "remount_root"))
-		goto cleanup;
-
-	fs_fd = create_bpffs_fd();
-	if (!ASSERT_GE(fs_fd, 0, "create_bpffs_fd")) {
-		err = -EINVAL;
-		goto cleanup;
-	}
-
-	/* ensure unprivileged child cannot set delegation options */
-	err = set_delegate_mask(fs_fd, "delegate_cmds", 0x1, NULL);
-	ASSERT_EQ(err, -EPERM, "delegate_cmd_eperm");
-	err = set_delegate_mask(fs_fd, "delegate_maps", 0x1, NULL);
-	ASSERT_EQ(err, -EPERM, "delegate_maps_eperm");
-	err = set_delegate_mask(fs_fd, "delegate_progs", 0x1, NULL);
-	ASSERT_EQ(err, -EPERM, "delegate_progs_eperm");
-	err = set_delegate_mask(fs_fd, "delegate_attachs", 0x1, NULL);
-	ASSERT_EQ(err, -EPERM, "delegate_attachs_eperm");
-
-	/* pass BPF FS context object to parent */
-	err = sendfd(sock_fd, fs_fd);
-	if (!ASSERT_OK(err, "send_fs_fd"))
-		goto cleanup;
-	zclose(fs_fd);
-
-	/* avoid mucking around with mount namespaces and mounting at
-	 * well-known path, just get detach-mounted BPF FS fd back from parent
-	 */
-	err = recvfd(sock_fd, &mnt_fd);
-	if (!ASSERT_OK(err, "recv_mnt_fd"))
-		goto cleanup;
-
-	/* try to fspick() BPF FS and try to add some delegation options */
-	fs_fd = sys_fspick(mnt_fd, "", FSPICK_EMPTY_PATH);
-	if (!ASSERT_GE(fs_fd, 0, "bpffs_fspick")) {
-		err = -EINVAL;
-		goto cleanup;
-	}
-
-	/* ensure unprivileged child cannot reconfigure to set delegation options */
-	err = set_delegate_mask(fs_fd, "delegate_cmds", 0, "any");
-	if (!ASSERT_EQ(err, -EPERM, "delegate_cmd_eperm_reconfig")) {
-		err = -EINVAL;
-		goto cleanup;
-	}
-	err = set_delegate_mask(fs_fd, "delegate_maps", 0, "any");
-	if (!ASSERT_EQ(err, -EPERM, "delegate_maps_eperm_reconfig")) {
-		err = -EINVAL;
-		goto cleanup;
-	}
-	err = set_delegate_mask(fs_fd, "delegate_progs", 0, "any");
-	if (!ASSERT_EQ(err, -EPERM, "delegate_progs_eperm_reconfig")) {
-		err = -EINVAL;
-		goto cleanup;
-	}
-	err = set_delegate_mask(fs_fd, "delegate_attachs", 0, "any");
-	if (!ASSERT_EQ(err, -EPERM, "delegate_attachs_eperm_reconfig")) {
-		err = -EINVAL;
-		goto cleanup;
-	}
-	zclose(fs_fd);
-
-	bpffs_fd = openat(mnt_fd, ".", 0, O_RDWR);
-	if (!ASSERT_GE(bpffs_fd, 0, "bpffs_open")) {
-		err = -EINVAL;
-		goto cleanup;
-	}
-
-	/* do custom test logic with customly set up BPF FS instance */
-	err = callback(bpffs_fd);
-	if (!ASSERT_OK(err, "test_callback"))
-		goto cleanup;
-
-	err = 0;
-cleanup:
-	zclose(sock_fd);
-	zclose(mnt_fd);
-	zclose(fs_fd);
-	zclose(bpffs_fd);
-
-	exit(-err);
-}
-
-static int wait_for_pid(pid_t pid)
-{
-	int status, ret;
-
-again:
-	ret = waitpid(pid, &status, 0);
-	if (ret == -1) {
-		if (errno == EINTR)
-			goto again;
-
-		return -1;
-	}
-
-	if (!WIFEXITED(status))
-		return -1;
-
-	return WEXITSTATUS(status);
-}
-
-static void parent(int child_pid, struct bpffs_opts *bpffs_opts, int sock_fd)
-{
-	int fs_fd = -1, mnt_fd = -1, err;
-
-	err = recvfd(sock_fd, &fs_fd);
-	if (!ASSERT_OK(err, "recv_bpffs_fd"))
-		goto cleanup;
-
-	mnt_fd = materialize_bpffs_fd(fs_fd, bpffs_opts);
-	if (!ASSERT_GE(mnt_fd, 0, "materialize_bpffs_fd")) {
-		err = -EINVAL;
-		goto cleanup;
-	}
-	zclose(fs_fd);
-
-	/* pass BPF FS context object to parent */
-	err = sendfd(sock_fd, mnt_fd);
-	if (!ASSERT_OK(err, "send_mnt_fd"))
-		goto cleanup;
-	zclose(mnt_fd);
-
-	err = wait_for_pid(child_pid);
-	ASSERT_OK(err, "waitpid_child");
-
-cleanup:
-	zclose(sock_fd);
-	zclose(fs_fd);
-	zclose(mnt_fd);
-
-	if (child_pid > 0)
-		(void)kill(child_pid, SIGKILL);
-}
-
-static void subtest_userns(struct bpffs_opts *bpffs_opts, child_callback_fn cb)
-{
-	int sock_fds[2] = { -1, -1 };
-	int child_pid = 0, err;
-
-	err = socketpair(AF_UNIX, SOCK_STREAM, 0, sock_fds);
-	if (!ASSERT_OK(err, "socketpair"))
-		goto cleanup;
-
-	child_pid = fork();
-	if (!ASSERT_GE(child_pid, 0, "fork"))
-		goto cleanup;
-
-	if (child_pid == 0) {
-		zclose(sock_fds[0]);
-		return child(sock_fds[1], bpffs_opts, cb);
-
-	} else {
-		zclose(sock_fds[1]);
-		return parent(child_pid, bpffs_opts, sock_fds[0]);
-	}
-
-cleanup:
-	zclose(sock_fds[0]);
-	zclose(sock_fds[1]);
-	if (child_pid > 0)
-		(void)kill(child_pid, SIGKILL);
-}
-
-static int userns_map_create(int mnt_fd)
-{
-	LIBBPF_OPTS(bpf_map_create_opts, map_opts);
-	int err, token_fd = -1, map_fd = -1;
-	__u64 old_caps = 0;
-
-	/* create BPF token from BPF FS mount */
-	token_fd = bpf_token_create(mnt_fd, NULL);
-	if (!ASSERT_GT(token_fd, 0, "token_create")) {
-		err = -EINVAL;
-		goto cleanup;
-	}
-
-	/* while inside non-init userns, we need both a BPF token *and*
-	 * CAP_BPF inside current userns to create privileged map; let's test
-	 * that neither BPF token alone nor namespaced CAP_BPF is sufficient
-	 */
-	err = drop_priv_caps(&old_caps);
-	if (!ASSERT_OK(err, "drop_caps"))
-		goto cleanup;
-
-	/* no token, no CAP_BPF -> fail */
-	map_opts.token_fd = 0;
-	map_fd = bpf_map_create(BPF_MAP_TYPE_STACK, "wo_token_wo_bpf", 0, 8, 1, &map_opts);
-	if (!ASSERT_LT(map_fd, 0, "stack_map_wo_token_wo_cap_bpf_should_fail")) {
-		err = -EINVAL;
-		goto cleanup;
-	}
-
-	/* token without CAP_BPF -> fail */
-	map_opts.token_fd = token_fd;
-	map_fd = bpf_map_create(BPF_MAP_TYPE_STACK, "w_token_wo_bpf", 0, 8, 1, &map_opts);
-	if (!ASSERT_LT(map_fd, 0, "stack_map_w_token_wo_cap_bpf_should_fail")) {
-		err = -EINVAL;
-		goto cleanup;
-	}
-
-	/* get back effective local CAP_BPF (and CAP_SYS_ADMIN) */
-	err = restore_priv_caps(old_caps);
-	if (!ASSERT_OK(err, "restore_caps"))
-		goto cleanup;
-
-	/* CAP_BPF without token -> fail */
-	map_opts.token_fd = 0;
-	map_fd = bpf_map_create(BPF_MAP_TYPE_STACK, "wo_token_w_bpf", 0, 8, 1, &map_opts);
-	if (!ASSERT_LT(map_fd, 0, "stack_map_wo_token_w_cap_bpf_should_fail")) {
-		err = -EINVAL;
-		goto cleanup;
-	}
-
-	/* finally, namespaced CAP_BPF + token -> success */
-	map_opts.token_fd = token_fd;
-	map_fd = bpf_map_create(BPF_MAP_TYPE_STACK, "w_token_w_bpf", 0, 8, 1, &map_opts);
-	if (!ASSERT_GT(map_fd, 0, "stack_map_w_token_w_cap_bpf")) {
-		err = -EINVAL;
-		goto cleanup;
-	}
-
-cleanup:
-	zclose(token_fd);
-	zclose(map_fd);
-	return err;
-}
-
-static int userns_btf_load(int mnt_fd)
-{
-	LIBBPF_OPTS(bpf_btf_load_opts, btf_opts);
-	int err, token_fd = -1, btf_fd = -1;
-	const void *raw_btf_data;
-	struct btf *btf = NULL;
-	__u32 raw_btf_size;
-	__u64 old_caps = 0;
-
-	/* create BPF token from BPF FS mount */
-	token_fd = bpf_token_create(mnt_fd, NULL);
-	if (!ASSERT_GT(token_fd, 0, "token_create")) {
-		err = -EINVAL;
-		goto cleanup;
-	}
-
-	/* while inside non-init userns, we need both a BPF token *and*
-	 * CAP_BPF inside current userns to create privileged map; let's test
-	 * that neither BPF token alone nor namespaced CAP_BPF is sufficient
-	 */
-	err = drop_priv_caps(&old_caps);
-	if (!ASSERT_OK(err, "drop_caps"))
-		goto cleanup;
-
-	/* setup a trivial BTF data to load to the kernel */
-	btf = btf__new_empty();
-	if (!ASSERT_OK_PTR(btf, "empty_btf"))
-		goto cleanup;
-
-	ASSERT_GT(btf__add_int(btf, "int", 4, 0), 0, "int_type");
-
-	raw_btf_data = btf__raw_data(btf, &raw_btf_size);
-	if (!ASSERT_OK_PTR(raw_btf_data, "raw_btf_data"))
-		goto cleanup;
-
-	/* no token + no CAP_BPF -> failure */
-	btf_opts.token_fd = 0;
-	btf_fd = bpf_btf_load(raw_btf_data, raw_btf_size, &btf_opts);
-	if (!ASSERT_LT(btf_fd, 0, "no_token_no_cap_should_fail"))
-		goto cleanup;
-
-	/* token + no CAP_BPF -> failure */
-	btf_opts.token_fd = token_fd;
-	btf_fd = bpf_btf_load(raw_btf_data, raw_btf_size, &btf_opts);
-	if (!ASSERT_LT(btf_fd, 0, "token_no_cap_should_fail"))
-		goto cleanup;
-
-	/* get back effective local CAP_BPF (and CAP_SYS_ADMIN) */
-	err = restore_priv_caps(old_caps);
-	if (!ASSERT_OK(err, "restore_caps"))
-		goto cleanup;
-
-	/* token + CAP_BPF -> success */
-	btf_opts.token_fd = token_fd;
-	btf_fd = bpf_btf_load(raw_btf_data, raw_btf_size, &btf_opts);
-	if (!ASSERT_GT(btf_fd, 0, "token_and_cap_success"))
-		goto cleanup;
-
-	err = 0;
-cleanup:
-	btf__free(btf);
-	zclose(btf_fd);
-	zclose(token_fd);
-	return err;
-}
-
-static int userns_prog_load(int mnt_fd)
-{
-	LIBBPF_OPTS(bpf_prog_load_opts, prog_opts);
-	int err, token_fd = -1, prog_fd = -1;
-	struct bpf_insn insns[] = {
-		/* bpf_jiffies64() requires CAP_BPF */
-		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_jiffies64),
-		/* bpf_get_current_task() requires CAP_PERFMON */
-		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_current_task),
-		/* r0 = 0; exit; */
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_EXIT_INSN(),
-	};
-	size_t insn_cnt = ARRAY_SIZE(insns);
-	__u64 old_caps = 0;
-
-	/* create BPF token from BPF FS mount */
-	token_fd = bpf_token_create(mnt_fd, NULL);
-	if (!ASSERT_GT(token_fd, 0, "token_create")) {
-		err = -EINVAL;
-		goto cleanup;
-	}
-
-	/* validate we can successfully load BPF program with token; this
-	 * being XDP program (CAP_NET_ADMIN) using bpf_jiffies64() (CAP_BPF)
-	 * and bpf_get_current_task() (CAP_PERFMON) helpers validates we have
-	 * BPF token wired properly in a bunch of places in the kernel
-	 */
-	prog_opts.token_fd = token_fd;
-	prog_opts.expected_attach_type = BPF_XDP;
-	prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, "token_prog", "GPL",
-				insns, insn_cnt, &prog_opts);
-	if (!ASSERT_GT(prog_fd, 0, "prog_fd")) {
-		err = -EPERM;
-		goto cleanup;
-	}
-
-	/* no token + caps -> failure */
-	prog_opts.token_fd = 0;
-	prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, "token_prog", "GPL",
-				insns, insn_cnt, &prog_opts);
-	if (!ASSERT_EQ(prog_fd, -EPERM, "prog_fd_eperm")) {
-		err = -EPERM;
-		goto cleanup;
-	}
-
-	err = drop_priv_caps(&old_caps);
-	if (!ASSERT_OK(err, "drop_caps"))
-		goto cleanup;
-
-	/* no caps + token -> failure */
-	prog_opts.token_fd = token_fd;
-	prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, "token_prog", "GPL",
-				insns, insn_cnt, &prog_opts);
-	if (!ASSERT_EQ(prog_fd, -EPERM, "prog_fd_eperm")) {
-		err = -EPERM;
-		goto cleanup;
-	}
-
-	/* no caps + no token -> definitely a failure */
-	prog_opts.token_fd = 0;
-	prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, "token_prog", "GPL",
-				insns, insn_cnt, &prog_opts);
-	if (!ASSERT_EQ(prog_fd, -EPERM, "prog_fd_eperm")) {
-		err = -EPERM;
-		goto cleanup;
-	}
-
-	err = 0;
-cleanup:
-	zclose(prog_fd);
-	zclose(token_fd);
-	return err;
-}
-
-static int userns_obj_priv_map(int mnt_fd)
-{
-	LIBBPF_OPTS(bpf_object_open_opts, opts);
-	char buf[256];
-	struct priv_map *skel;
-	int err, token_fd;
-
-	skel = priv_map__open_and_load();
-	if (!ASSERT_ERR_PTR(skel, "obj_tokenless_load")) {
-		priv_map__destroy(skel);
-		return -EINVAL;
-	}
-
-	/* use bpf_token_path to provide BPF FS path */
-	snprintf(buf, sizeof(buf), "/proc/self/fd/%d", mnt_fd);
-	opts.bpf_token_path = buf;
-	skel = priv_map__open_opts(&opts);
-	if (!ASSERT_OK_PTR(skel, "obj_token_path_open"))
-		return -EINVAL;
-
-	err = priv_map__load(skel);
-	priv_map__destroy(skel);
-	if (!ASSERT_OK(err, "obj_token_path_load"))
-		return -EINVAL;
-
-	/* create token and pass it through bpf_token_fd */
-	token_fd = bpf_token_create(mnt_fd, NULL);
-	if (!ASSERT_GT(token_fd, 0, "create_token"))
-		return -EINVAL;
-
-	opts.bpf_token_path = NULL;
-	opts.bpf_token_fd = token_fd;
-	skel = priv_map__open_opts(&opts);
-	if (!ASSERT_OK_PTR(skel, "obj_token_fd_open"))
-		return -EINVAL;
-
-	/* we can close our token FD, bpf_object owns dup()'ed FD now */
-	close(token_fd);
-
-	err = priv_map__load(skel);
-	priv_map__destroy(skel);
-	if (!ASSERT_OK(err, "obj_token_fd_load"))
-		return -EINVAL;
-
-	return 0;
-}
-
-static int userns_obj_priv_prog(int mnt_fd)
-{
-	LIBBPF_OPTS(bpf_object_open_opts, opts);
-	char buf[256];
-	struct priv_prog *skel;
-	int err;
-
-	skel = priv_prog__open_and_load();
-	if (!ASSERT_ERR_PTR(skel, "obj_tokenless_load")) {
-		priv_prog__destroy(skel);
-		return -EINVAL;
-	}
-
-	/* use bpf_token_path to provide BPF FS path */
-	snprintf(buf, sizeof(buf), "/proc/self/fd/%d", mnt_fd);
-	opts.bpf_token_path = buf;
-	skel = priv_prog__open_opts(&opts);
-	if (!ASSERT_OK_PTR(skel, "obj_token_path_open"))
-		return -EINVAL;
-
-	err = priv_prog__load(skel);
-	priv_prog__destroy(skel);
-	if (!ASSERT_OK(err, "obj_token_path_load"))
-		return -EINVAL;
-
-	return 0;
-}
-
-/* this test is called with BPF FS that doesn't delegate BPF_BTF_LOAD command,
- * which should cause struct_ops application to fail, as BTF won't be uploaded
- * into the kernel, even if STRUCT_OPS programs themselves are allowed
- */
-static int validate_struct_ops_load(int mnt_fd, bool expect_success)
-{
-	LIBBPF_OPTS(bpf_object_open_opts, opts);
-	char buf[256];
-	struct dummy_st_ops_success *skel;
-	int err;
-
-	snprintf(buf, sizeof(buf), "/proc/self/fd/%d", mnt_fd);
-	opts.bpf_token_path = buf;
-	skel = dummy_st_ops_success__open_opts(&opts);
-	if (!ASSERT_OK_PTR(skel, "obj_token_path_open"))
-		return -EINVAL;
-
-	err = dummy_st_ops_success__load(skel);
-	dummy_st_ops_success__destroy(skel);
-	if (expect_success) {
-		if (!ASSERT_OK(err, "obj_token_path_load"))
-			return -EINVAL;
-	} else /* expect failure */ {
-		if (!ASSERT_ERR(err, "obj_token_path_load"))
-			return -EINVAL;
-	}
-
-	return 0;
-}
-
-static int userns_obj_priv_btf_fail(int mnt_fd)
-{
-	return validate_struct_ops_load(mnt_fd, false /* should fail */);
-}
-
-static int userns_obj_priv_btf_success(int mnt_fd)
-{
-	return validate_struct_ops_load(mnt_fd, true /* should succeed */);
-}
-
-#define TOKEN_ENVVAR "LIBBPF_BPF_TOKEN_PATH"
-#define TOKEN_BPFFS_CUSTOM "/bpf-token-fs"
-
-static int userns_obj_priv_implicit_token(int mnt_fd)
-{
-	LIBBPF_OPTS(bpf_object_open_opts, opts);
-	struct dummy_st_ops_success *skel;
-	int err;
-
-	/* before we mount BPF FS with token delegation, struct_ops skeleton
-	 * should fail to load
-	 */
-	skel = dummy_st_ops_success__open_and_load();
-	if (!ASSERT_ERR_PTR(skel, "obj_tokenless_load")) {
-		dummy_st_ops_success__destroy(skel);
-		return -EINVAL;
-	}
-
-	/* mount custom BPF FS over /sys/fs/bpf so that libbpf can create BPF
-	 * token automatically and implicitly
-	 */
-	err = sys_move_mount(mnt_fd, "", AT_FDCWD, "/sys/fs/bpf", MOVE_MOUNT_F_EMPTY_PATH);
-	if (!ASSERT_OK(err, "move_mount_bpffs"))
-		return -EINVAL;
-
-	/* disable implicit BPF token creation by setting
-	 * LIBBPF_BPF_TOKEN_PATH envvar to empty value, load should fail
-	 */
-	err = setenv(TOKEN_ENVVAR, "", 1 /*overwrite*/);
-	if (!ASSERT_OK(err, "setenv_token_path"))
-		return -EINVAL;
-	skel = dummy_st_ops_success__open_and_load();
-	if (!ASSERT_ERR_PTR(skel, "obj_token_envvar_disabled_load")) {
-		unsetenv(TOKEN_ENVVAR);
-		dummy_st_ops_success__destroy(skel);
-		return -EINVAL;
-	}
-	unsetenv(TOKEN_ENVVAR);
-
-	/* now the same struct_ops skeleton should succeed thanks to libppf
-	 * creating BPF token from /sys/fs/bpf mount point
-	 */
-	skel = dummy_st_ops_success__open_and_load();
-	if (!ASSERT_OK_PTR(skel, "obj_implicit_token_load"))
-		return -EINVAL;
-
-	dummy_st_ops_success__destroy(skel);
-
-	/* now disable implicit token through empty bpf_token_path, should fail */
-	opts.bpf_token_path = "";
-	skel = dummy_st_ops_success__open_opts(&opts);
-	if (!ASSERT_OK_PTR(skel, "obj_empty_token_path_open"))
-		return -EINVAL;
-
-	err = dummy_st_ops_success__load(skel);
-	dummy_st_ops_success__destroy(skel);
-	if (!ASSERT_ERR(err, "obj_empty_token_path_load"))
-		return -EINVAL;
-
-	/* now disable implicit token through negative bpf_token_fd, should fail */
-	opts.bpf_token_path = NULL;
-	opts.bpf_token_fd = -1;
-	skel = dummy_st_ops_success__open_opts(&opts);
-	if (!ASSERT_OK_PTR(skel, "obj_neg_token_fd_open"))
-		return -EINVAL;
-
-	err = dummy_st_ops_success__load(skel);
-	dummy_st_ops_success__destroy(skel);
-	if (!ASSERT_ERR(err, "obj_neg_token_fd_load"))
-		return -EINVAL;
-
-	return 0;
-}
-
-static int userns_obj_priv_implicit_token_envvar(int mnt_fd)
-{
-	LIBBPF_OPTS(bpf_object_open_opts, opts);
-	struct dummy_st_ops_success *skel;
-	int err;
-
-	/* before we mount BPF FS with token delegation, struct_ops skeleton
-	 * should fail to load
-	 */
-	skel = dummy_st_ops_success__open_and_load();
-	if (!ASSERT_ERR_PTR(skel, "obj_tokenless_load")) {
-		dummy_st_ops_success__destroy(skel);
-		return -EINVAL;
-	}
-
-	/* mount custom BPF FS over custom location, so libbpf can't create
-	 * BPF token implicitly, unless pointed to it through
-	 * LIBBPF_BPF_TOKEN_PATH envvar
-	 */
-	rmdir(TOKEN_BPFFS_CUSTOM);
-	if (!ASSERT_OK(mkdir(TOKEN_BPFFS_CUSTOM, 0777), "mkdir_bpffs_custom"))
-		goto err_out;
-	err = sys_move_mount(mnt_fd, "", AT_FDCWD, TOKEN_BPFFS_CUSTOM, MOVE_MOUNT_F_EMPTY_PATH);
-	if (!ASSERT_OK(err, "move_mount_bpffs"))
-		goto err_out;
-
-	/* even though we have BPF FS with delegation, it's not at default
-	 * /sys/fs/bpf location, so we still fail to load until envvar is set up
-	 */
-	skel = dummy_st_ops_success__open_and_load();
-	if (!ASSERT_ERR_PTR(skel, "obj_tokenless_load2")) {
-		dummy_st_ops_success__destroy(skel);
-		goto err_out;
-	}
-
-	err = setenv(TOKEN_ENVVAR, TOKEN_BPFFS_CUSTOM, 1 /*overwrite*/);
-	if (!ASSERT_OK(err, "setenv_token_path"))
-		goto err_out;
-
-	/* now the same struct_ops skeleton should succeed thanks to libppf
-	 * creating BPF token from custom mount point
-	 */
-	skel = dummy_st_ops_success__open_and_load();
-	if (!ASSERT_OK_PTR(skel, "obj_implicit_token_load"))
-		goto err_out;
-
-	dummy_st_ops_success__destroy(skel);
-
-	/* now disable implicit token through empty bpf_token_path, envvar
-	 * will be ignored, should fail
-	 */
-	opts.bpf_token_path = "";
-	skel = dummy_st_ops_success__open_opts(&opts);
-	if (!ASSERT_OK_PTR(skel, "obj_empty_token_path_open"))
-		goto err_out;
-
-	err = dummy_st_ops_success__load(skel);
-	dummy_st_ops_success__destroy(skel);
-	if (!ASSERT_ERR(err, "obj_empty_token_path_load"))
-		goto err_out;
-
-	/* now disable implicit token through negative bpf_token_fd, envvar
-	 * will be ignored, should fail
-	 */
-	opts.bpf_token_path = NULL;
-	opts.bpf_token_fd = -1;
-	skel = dummy_st_ops_success__open_opts(&opts);
-	if (!ASSERT_OK_PTR(skel, "obj_neg_token_fd_open"))
-		goto err_out;
-
-	err = dummy_st_ops_success__load(skel);
-	dummy_st_ops_success__destroy(skel);
-	if (!ASSERT_ERR(err, "obj_neg_token_fd_load"))
-		goto err_out;
-
-	rmdir(TOKEN_BPFFS_CUSTOM);
-	unsetenv(TOKEN_ENVVAR);
-	return 0;
-err_out:
-	rmdir(TOKEN_BPFFS_CUSTOM);
-	unsetenv(TOKEN_ENVVAR);
-	return -EINVAL;
-}
-
-#define bit(n) (1ULL << (n))
-
-void test_token(void)
-{
-	if (test__start_subtest("map_token")) {
-		struct bpffs_opts opts = {
-			.cmds_str = "map_create",
-			.maps_str = "stack",
-		};
-
-		subtest_userns(&opts, userns_map_create);
-	}
-	if (test__start_subtest("btf_token")) {
-		struct bpffs_opts opts = {
-			.cmds = 1ULL << BPF_BTF_LOAD,
-		};
-
-		subtest_userns(&opts, userns_btf_load);
-	}
-	if (test__start_subtest("prog_token")) {
-		struct bpffs_opts opts = {
-			.cmds_str = "PROG_LOAD",
-			.progs_str = "XDP",
-			.attachs_str = "xdp",
-		};
-
-		subtest_userns(&opts, userns_prog_load);
-	}
-	if (test__start_subtest("obj_priv_map")) {
-		struct bpffs_opts opts = {
-			.cmds = bit(BPF_MAP_CREATE),
-			.maps = bit(BPF_MAP_TYPE_QUEUE),
-		};
-
-		subtest_userns(&opts, userns_obj_priv_map);
-	}
-	if (test__start_subtest("obj_priv_prog")) {
-		struct bpffs_opts opts = {
-			.cmds = bit(BPF_PROG_LOAD),
-			.progs = bit(BPF_PROG_TYPE_KPROBE),
-			.attachs = ~0ULL,
-		};
-
-		subtest_userns(&opts, userns_obj_priv_prog);
-	}
-	if (test__start_subtest("obj_priv_btf_fail")) {
-		struct bpffs_opts opts = {
-			/* disallow BTF loading */
-			.cmds = bit(BPF_MAP_CREATE) | bit(BPF_PROG_LOAD),
-			.maps = bit(BPF_MAP_TYPE_STRUCT_OPS),
-			.progs = bit(BPF_PROG_TYPE_STRUCT_OPS),
-			.attachs = ~0ULL,
-		};
-
-		subtest_userns(&opts, userns_obj_priv_btf_fail);
-	}
-	if (test__start_subtest("obj_priv_btf_success")) {
-		struct bpffs_opts opts = {
-			/* allow BTF loading */
-			.cmds = bit(BPF_BTF_LOAD) | bit(BPF_MAP_CREATE) | bit(BPF_PROG_LOAD),
-			.maps = bit(BPF_MAP_TYPE_STRUCT_OPS),
-			.progs = bit(BPF_PROG_TYPE_STRUCT_OPS),
-			.attachs = ~0ULL,
-		};
-
-		subtest_userns(&opts, userns_obj_priv_btf_success);
-	}
-	if (test__start_subtest("obj_priv_implicit_token")) {
-		struct bpffs_opts opts = {
-			/* allow BTF loading */
-			.cmds = bit(BPF_BTF_LOAD) | bit(BPF_MAP_CREATE) | bit(BPF_PROG_LOAD),
-			.maps = bit(BPF_MAP_TYPE_STRUCT_OPS),
-			.progs = bit(BPF_PROG_TYPE_STRUCT_OPS),
-			.attachs = ~0ULL,
-		};
-
-		subtest_userns(&opts, userns_obj_priv_implicit_token);
-	}
-	if (test__start_subtest("obj_priv_implicit_token_envvar")) {
-		struct bpffs_opts opts = {
-			/* allow BTF loading */
-			.cmds = bit(BPF_BTF_LOAD) | bit(BPF_MAP_CREATE) | bit(BPF_PROG_LOAD),
-			.maps = bit(BPF_MAP_TYPE_STRUCT_OPS),
-			.progs = bit(BPF_PROG_TYPE_STRUCT_OPS),
-			.attachs = ~0ULL,
-		};
-
-		subtest_userns(&opts, userns_obj_priv_implicit_token_envvar);
-	}
-}
diff --git a/tools/testing/selftests/bpf/progs/priv_map.c b/tools/testing/selftests/bpf/progs/priv_map.c
deleted file mode 100644
index 9085be50f03b..000000000000
--- a/tools/testing/selftests/bpf/progs/priv_map.c
+++ /dev/null
@@ -1,13 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
-
-#include "vmlinux.h"
-#include <bpf/bpf_helpers.h>
-
-char _license[] SEC("license") = "GPL";
-
-struct {
-	__uint(type, BPF_MAP_TYPE_QUEUE);
-	__uint(max_entries, 1);
-	__type(value, __u32);
-} priv_map SEC(".maps");
diff --git a/tools/testing/selftests/bpf/progs/priv_prog.c b/tools/testing/selftests/bpf/progs/priv_prog.c
deleted file mode 100644
index 3c7b2b618c8a..000000000000
--- a/tools/testing/selftests/bpf/progs/priv_prog.c
+++ /dev/null
@@ -1,13 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
-
-#include "vmlinux.h"
-#include <bpf/bpf_helpers.h>
-
-char _license[] SEC("license") = "GPL";
-
-SEC("kprobe")
-int kprobe_prog(void *ctx)
-{
-	return 1;
-}
-- 
cgit v1.2.3


From 1c1c2b37325934b4318c46966feb03ad9fe83d8a Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Fri, 15 Dec 2023 15:38:51 +0300
Subject: wifi: cfg80211: introduce cfg80211_ssid_eq()

Since SSIDs comparison is commonly used across many drivers, introduce
generic 'cfg80211_ssid_eq()' to replace driver-private implementations.

Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Link: https://msgid.link/20231215123859.196350-1-dmantipov@yandex.ru
[fix kernel-doc return docs]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index ac1fb326dcda..033a0a25397f 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -7165,6 +7165,23 @@ enum cfg80211_bss_frame_type {
 int cfg80211_get_ies_channel_number(const u8 *ie, size_t ielen,
 				    enum nl80211_band band);
 
+/**
+ * cfg80211_ssid_eq - compare two SSIDs
+ * @a: first SSID
+ * @b: second SSID
+ *
+ * Return: %true if SSIDs are equal, %false otherwise.
+ */
+static inline bool
+cfg80211_ssid_eq(struct cfg80211_ssid *a, struct cfg80211_ssid *b)
+{
+	if (WARN_ON(!a || !b))
+		return false;
+	if (a->ssid_len != b->ssid_len)
+		return false;
+	return memcmp(a->ssid, b->ssid, a->ssid_len) ? false : true;
+}
+
 /**
  * cfg80211_inform_bss_data - inform cfg80211 of a new BSS
  *
-- 
cgit v1.2.3


From d70d141bb15f328528f94557ddf754abeb027365 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Thu, 14 Dec 2023 12:07:55 +0100
Subject: ACPI: utils: Introduce helper for _DEP list lookup

The ACPI LPSS driver and the Surface platform driver code use almost the
same code pattern for checking if one ACPI device is present in the list
returned by _DEP for another ACPI device.

To reduce the resulting code duplication, introduce a helper for that
called acpi_device_dep() and invoke it from both places.

No intentional functional impact.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/acpi/acpi_lpss.c                       | 29 ++--------------------
 drivers/acpi/utils.c                           | 34 ++++++++++++++++++++++++++
 drivers/platform/surface/surface_acpi_notify.c | 28 +--------------------
 include/acpi/acpi_bus.h                        |  1 +
 4 files changed, 38 insertions(+), 54 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index 1623af8d62bc..920402dfe1ad 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -562,31 +562,6 @@ static struct device *acpi_lpss_find_device(const char *hid, const char *uid)
 	return bus_find_device(&pci_bus_type, NULL, &data, match_hid_uid);
 }
 
-static bool acpi_lpss_dep(struct acpi_device *adev, acpi_handle handle)
-{
-	struct acpi_handle_list dep_devices;
-	bool ret = false;
-	int i;
-
-	if (!acpi_has_method(adev->handle, "_DEP"))
-		return false;
-
-	if (!acpi_evaluate_reference(adev->handle, "_DEP", NULL, &dep_devices)) {
-		dev_dbg(&adev->dev, "Failed to evaluate _DEP.\n");
-		return false;
-	}
-
-	for (i = 0; i < dep_devices.count; i++) {
-		if (dep_devices.handles[i] == handle) {
-			ret = true;
-			break;
-		}
-	}
-
-	acpi_handle_list_free(&dep_devices);
-	return ret;
-}
-
 static void acpi_lpss_link_consumer(struct device *dev1,
 				    const struct lpss_device_links *link)
 {
@@ -597,7 +572,7 @@ static void acpi_lpss_link_consumer(struct device *dev1,
 		return;
 
 	if ((link->dep_missing_ids && dmi_check_system(link->dep_missing_ids))
-	    || acpi_lpss_dep(ACPI_COMPANION(dev2), ACPI_HANDLE(dev1)))
+	    || acpi_device_dep(ACPI_HANDLE(dev2), ACPI_HANDLE(dev1)))
 		device_link_add(dev2, dev1, link->flags);
 
 	put_device(dev2);
@@ -613,7 +588,7 @@ static void acpi_lpss_link_supplier(struct device *dev1,
 		return;
 
 	if ((link->dep_missing_ids && dmi_check_system(link->dep_missing_ids))
-	    || acpi_lpss_dep(ACPI_COMPANION(dev1), ACPI_HANDLE(dev2)))
+	    || acpi_device_dep(ACPI_HANDLE(dev1), ACPI_HANDLE(dev2)))
 		device_link_add(dev1, dev2, link->flags);
 
 	put_device(dev2);
diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c
index 57663065dbf6..abac5cc25477 100644
--- a/drivers/acpi/utils.c
+++ b/drivers/acpi/utils.c
@@ -450,6 +450,40 @@ void acpi_handle_list_free(struct acpi_handle_list *list)
 }
 EXPORT_SYMBOL_GPL(acpi_handle_list_free);
 
+/**
+ * acpi_device_dep - Check ACPI device dependency
+ * @target: ACPI handle of the target ACPI device.
+ * @match: ACPI handle to look up in the target's _DEP list.
+ *
+ * Return true if @match is present in the list returned by _DEP for
+ * @target or false otherwise.
+ */
+bool acpi_device_dep(acpi_handle target, acpi_handle match)
+{
+	struct acpi_handle_list dep_devices;
+	bool ret = false;
+	int i;
+
+	if (!acpi_has_method(target, "_DEP"))
+		return false;
+
+	if (!acpi_evaluate_reference(target, "_DEP", NULL, &dep_devices)) {
+		acpi_handle_debug(target, "Failed to evaluate _DEP.\n");
+		return false;
+	}
+
+	for (i = 0; i < dep_devices.count; i++) {
+		if (dep_devices.handles[i] == match) {
+			ret = true;
+			break;
+		}
+	}
+
+	acpi_handle_list_free(&dep_devices);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(acpi_device_dep);
+
 acpi_status
 acpi_get_physical_device_location(acpi_handle handle, struct acpi_pld_info **pld)
 {
diff --git a/drivers/platform/surface/surface_acpi_notify.c b/drivers/platform/surface/surface_acpi_notify.c
index 96ec052d0940..20f3870915d2 100644
--- a/drivers/platform/surface/surface_acpi_notify.c
+++ b/drivers/platform/surface/surface_acpi_notify.c
@@ -736,32 +736,6 @@ do {										\
 #define san_consumer_warn(dev, handle, fmt, ...) \
 	san_consumer_printk(warn, dev, handle, fmt, ##__VA_ARGS__)
 
-static bool is_san_consumer(struct platform_device *pdev, acpi_handle handle)
-{
-	struct acpi_handle_list dep_devices;
-	acpi_handle supplier = ACPI_HANDLE(&pdev->dev);
-	bool ret = false;
-	int i;
-
-	if (!acpi_has_method(handle, "_DEP"))
-		return false;
-
-	if (!acpi_evaluate_reference(handle, "_DEP", NULL, &dep_devices)) {
-		san_consumer_dbg(&pdev->dev, handle, "failed to evaluate _DEP\n");
-		return false;
-	}
-
-	for (i = 0; i < dep_devices.count; i++) {
-		if (dep_devices.handles[i] == supplier) {
-			ret = true;
-			break;
-		}
-	}
-
-	acpi_handle_list_free(&dep_devices);
-	return ret;
-}
-
 static acpi_status san_consumer_setup(acpi_handle handle, u32 lvl,
 				      void *context, void **rv)
 {
@@ -770,7 +744,7 @@ static acpi_status san_consumer_setup(acpi_handle handle, u32 lvl,
 	struct acpi_device *adev;
 	struct device_link *link;
 
-	if (!is_san_consumer(pdev, handle))
+	if (!acpi_device_dep(handle, ACPI_HANDLE(&pdev->dev)))
 		return AE_OK;
 
 	/* Ignore ACPI devices that are not present. */
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 3dcf07b41428..b5c082e34539 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -33,6 +33,7 @@ bool acpi_handle_list_equal(struct acpi_handle_list *list1,
 void acpi_handle_list_replace(struct acpi_handle_list *dst,
 			      struct acpi_handle_list *src);
 void acpi_handle_list_free(struct acpi_handle_list *list);
+bool acpi_device_dep(acpi_handle target, acpi_handle match);
 acpi_status
 acpi_evaluate_ost(acpi_handle handle, u32 source_event, u32 status_code,
 		  struct acpi_buffer *status_buf);
-- 
cgit v1.2.3


From 849d18e27be9a1253f2318cb4549cc857219d991 Mon Sep 17 00:00:00 2001
From: Song Liu <song@kernel.org>
Date: Thu, 14 Dec 2023 14:21:05 -0800
Subject: md: Remove deprecated CONFIG_MD_LINEAR

md-linear has been marked as deprecated for 2.5 years. Remove it.

Cc: Christoph Hellwig <hch@lst.de>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Neil Brown <neilb@suse.de>
Cc: Guoqing Jiang <guoqing.jiang@linux.dev>
Cc: Mateusz Grzonka <mateusz.grzonka@intel.com>
Cc: Jes Sorensen <jes@trained-monkey.org>
Signed-off-by: Song Liu <song@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Link: https://lore.kernel.org/r/20231214222107.2016042-2-song@kernel.org
---
 drivers/md/Kconfig             |  13 --
 drivers/md/Makefile            |   6 +-
 drivers/md/md-autodetect.c     |   8 +-
 drivers/md/md-linear.c         | 318 -----------------------------------------
 drivers/md/md.c                |   2 +-
 include/uapi/linux/raid/md_p.h |   8 +-
 include/uapi/linux/raid/md_u.h |   7 +-
 7 files changed, 8 insertions(+), 354 deletions(-)
 delete mode 100644 drivers/md/md-linear.c

(limited to 'include')

diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 2a8b081bce7d..0c721e0e5921 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -61,19 +61,6 @@ config MD_BITMAP_FILE
 	  various kernel APIs and can only work with files on a file system not
 	  actually sitting on the MD device.
 
-config MD_LINEAR
-	tristate "Linear (append) mode (deprecated)"
-	depends on BLK_DEV_MD
-	help
-	  If you say Y here, then your multiple devices driver will be able to
-	  use the so-called linear mode, i.e. it will combine the hard disk
-	  partitions by simply appending one to the other.
-
-	  To compile this as a module, choose M here: the module
-	  will be called linear.
-
-	  If unsure, say Y.
-
 config MD_RAID0
 	tristate "RAID-0 (striping) mode"
 	depends on BLK_DEV_MD
diff --git a/drivers/md/Makefile b/drivers/md/Makefile
index 84291e38dca8..c72f76cf7b63 100644
--- a/drivers/md/Makefile
+++ b/drivers/md/Makefile
@@ -29,16 +29,14 @@ dm-zoned-y	+= dm-zoned-target.o dm-zoned-metadata.o dm-zoned-reclaim.o
 
 md-mod-y	+= md.o md-bitmap.o
 raid456-y	+= raid5.o raid5-cache.o raid5-ppl.o
-linear-y	+= md-linear.o
 multipath-y	+= md-multipath.o
 faulty-y	+= md-faulty.o
 
 # Note: link order is important.  All raid personalities
-# and must come before md.o, as they each initialise 
-# themselves, and md.o may use the personalities when it 
+# and must come before md.o, as they each initialise
+# themselves, and md.o may use the personalities when it
 # auto-initialised.
 
-obj-$(CONFIG_MD_LINEAR)		+= linear.o
 obj-$(CONFIG_MD_RAID0)		+= raid0.o
 obj-$(CONFIG_MD_RAID1)		+= raid1.o
 obj-$(CONFIG_MD_RAID10)		+= raid10.o
diff --git a/drivers/md/md-autodetect.c b/drivers/md/md-autodetect.c
index 4b80165afd23..b2a00f213c2c 100644
--- a/drivers/md/md-autodetect.c
+++ b/drivers/md/md-autodetect.c
@@ -49,7 +49,6 @@ static int md_setup_ents __initdata;
  *             instead of just one.  -- KTK
  * 18May2000: Added support for persistent-superblock arrays:
  *             md=n,0,factor,fault,device-list   uses RAID0 for device n
- *             md=n,-1,factor,fault,device-list  uses LINEAR for device n
  *             md=n,device-list      reads a RAID superblock from the devices
  *             elements in device-list are read by name_to_kdev_t so can be
  *             a hex number or something like /dev/hda1 /dev/sdb
@@ -88,7 +87,7 @@ static int __init md_setup(char *str)
 		md_setup_ents++;
 	switch (get_option(&str, &level)) {	/* RAID level */
 	case 2: /* could be 0 or -1.. */
-		if (level == 0 || level == LEVEL_LINEAR) {
+		if (level == 0) {
 			if (get_option(&str, &factor) != 2 ||	/* Chunk Size */
 					get_option(&str, &fault) != 2) {
 				printk(KERN_WARNING "md: Too few arguments supplied to md=.\n");
@@ -96,10 +95,7 @@ static int __init md_setup(char *str)
 			}
 			md_setup_args[ent].level = level;
 			md_setup_args[ent].chunk = 1 << (factor+12);
-			if (level ==  LEVEL_LINEAR)
-				pername = "linear";
-			else
-				pername = "raid0";
+			pername = "raid0";
 			break;
 		}
 		fallthrough;
diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c
deleted file mode 100644
index 8eca7693b793..000000000000
--- a/drivers/md/md-linear.c
+++ /dev/null
@@ -1,318 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
-   linear.c : Multiple Devices driver for Linux
-	      Copyright (C) 1994-96 Marc ZYNGIER
-	      <zyngier@ufr-info-p7.ibp.fr> or
-	      <maz@gloups.fdn.fr>
-
-   Linear mode management functions.
-
-*/
-
-#include <linux/blkdev.h>
-#include <linux/raid/md_u.h>
-#include <linux/seq_file.h>
-#include <linux/module.h>
-#include <linux/slab.h>
-#include <trace/events/block.h>
-#include "md.h"
-#include "md-linear.h"
-
-/*
- * find which device holds a particular offset
- */
-static inline struct dev_info *which_dev(struct mddev *mddev, sector_t sector)
-{
-	int lo, mid, hi;
-	struct linear_conf *conf;
-
-	lo = 0;
-	hi = mddev->raid_disks - 1;
-	conf = mddev->private;
-
-	/*
-	 * Binary Search
-	 */
-
-	while (hi > lo) {
-
-		mid = (hi + lo) / 2;
-		if (sector < conf->disks[mid].end_sector)
-			hi = mid;
-		else
-			lo = mid + 1;
-	}
-
-	return conf->disks + lo;
-}
-
-static sector_t linear_size(struct mddev *mddev, sector_t sectors, int raid_disks)
-{
-	struct linear_conf *conf;
-	sector_t array_sectors;
-
-	conf = mddev->private;
-	WARN_ONCE(sectors || raid_disks,
-		  "%s does not support generic reshape\n", __func__);
-	array_sectors = conf->array_sectors;
-
-	return array_sectors;
-}
-
-static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks)
-{
-	struct linear_conf *conf;
-	struct md_rdev *rdev;
-	int i, cnt;
-
-	conf = kzalloc(struct_size(conf, disks, raid_disks), GFP_KERNEL);
-	if (!conf)
-		return NULL;
-
-	/*
-	 * conf->raid_disks is copy of mddev->raid_disks. The reason to
-	 * keep a copy of mddev->raid_disks in struct linear_conf is,
-	 * mddev->raid_disks may not be consistent with pointers number of
-	 * conf->disks[] when it is updated in linear_add() and used to
-	 * iterate old conf->disks[] earray in linear_congested().
-	 * Here conf->raid_disks is always consitent with number of
-	 * pointers in conf->disks[] array, and mddev->private is updated
-	 * with rcu_assign_pointer() in linear_addr(), such race can be
-	 * avoided.
-	 */
-	conf->raid_disks = raid_disks;
-
-	cnt = 0;
-	conf->array_sectors = 0;
-
-	rdev_for_each(rdev, mddev) {
-		int j = rdev->raid_disk;
-		struct dev_info *disk = conf->disks + j;
-		sector_t sectors;
-
-		if (j < 0 || j >= raid_disks || disk->rdev) {
-			pr_warn("md/linear:%s: disk numbering problem. Aborting!\n",
-				mdname(mddev));
-			goto out;
-		}
-
-		disk->rdev = rdev;
-		if (mddev->chunk_sectors) {
-			sectors = rdev->sectors;
-			sector_div(sectors, mddev->chunk_sectors);
-			rdev->sectors = sectors * mddev->chunk_sectors;
-		}
-
-		disk_stack_limits(mddev->gendisk, rdev->bdev,
-				  rdev->data_offset << 9);
-
-		conf->array_sectors += rdev->sectors;
-		cnt++;
-	}
-	if (cnt != raid_disks) {
-		pr_warn("md/linear:%s: not enough drives present. Aborting!\n",
-			mdname(mddev));
-		goto out;
-	}
-
-	/*
-	 * Here we calculate the device offsets.
-	 */
-	conf->disks[0].end_sector = conf->disks[0].rdev->sectors;
-
-	for (i = 1; i < raid_disks; i++)
-		conf->disks[i].end_sector =
-			conf->disks[i-1].end_sector +
-			conf->disks[i].rdev->sectors;
-
-	return conf;
-
-out:
-	kfree(conf);
-	return NULL;
-}
-
-static int linear_run (struct mddev *mddev)
-{
-	struct linear_conf *conf;
-	int ret;
-
-	if (md_check_no_bitmap(mddev))
-		return -EINVAL;
-	conf = linear_conf(mddev, mddev->raid_disks);
-
-	if (!conf)
-		return 1;
-	mddev->private = conf;
-	md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
-
-	ret =  md_integrity_register(mddev);
-	if (ret) {
-		kfree(conf);
-		mddev->private = NULL;
-	}
-	return ret;
-}
-
-static int linear_add(struct mddev *mddev, struct md_rdev *rdev)
-{
-	/* Adding a drive to a linear array allows the array to grow.
-	 * It is permitted if the new drive has a matching superblock
-	 * already on it, with raid_disk equal to raid_disks.
-	 * It is achieved by creating a new linear_private_data structure
-	 * and swapping it in in-place of the current one.
-	 * The current one is never freed until the array is stopped.
-	 * This avoids races.
-	 */
-	struct linear_conf *newconf, *oldconf;
-
-	if (rdev->saved_raid_disk != mddev->raid_disks)
-		return -EINVAL;
-
-	rdev->raid_disk = rdev->saved_raid_disk;
-	rdev->saved_raid_disk = -1;
-
-	newconf = linear_conf(mddev,mddev->raid_disks+1);
-
-	if (!newconf)
-		return -ENOMEM;
-
-	/* newconf->raid_disks already keeps a copy of * the increased
-	 * value of mddev->raid_disks, WARN_ONCE() is just used to make
-	 * sure of this. It is possible that oldconf is still referenced
-	 * in linear_congested(), therefore kfree_rcu() is used to free
-	 * oldconf until no one uses it anymore.
-	 */
-	oldconf = rcu_dereference_protected(mddev->private,
-			lockdep_is_held(&mddev->reconfig_mutex));
-	mddev->raid_disks++;
-	WARN_ONCE(mddev->raid_disks != newconf->raid_disks,
-		"copied raid_disks doesn't match mddev->raid_disks");
-	rcu_assign_pointer(mddev->private, newconf);
-	md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
-	set_capacity_and_notify(mddev->gendisk, mddev->array_sectors);
-	kfree_rcu(oldconf, rcu);
-	return 0;
-}
-
-static void linear_free(struct mddev *mddev, void *priv)
-{
-	struct linear_conf *conf = priv;
-
-	kfree(conf);
-}
-
-static bool linear_make_request(struct mddev *mddev, struct bio *bio)
-{
-	struct dev_info *tmp_dev;
-	sector_t start_sector, end_sector, data_offset;
-	sector_t bio_sector = bio->bi_iter.bi_sector;
-
-	if (unlikely(bio->bi_opf & REQ_PREFLUSH)
-	    && md_flush_request(mddev, bio))
-		return true;
-
-	tmp_dev = which_dev(mddev, bio_sector);
-	start_sector = tmp_dev->end_sector - tmp_dev->rdev->sectors;
-	end_sector = tmp_dev->end_sector;
-	data_offset = tmp_dev->rdev->data_offset;
-
-	if (unlikely(bio_sector >= end_sector ||
-		     bio_sector < start_sector))
-		goto out_of_bounds;
-
-	if (unlikely(is_rdev_broken(tmp_dev->rdev))) {
-		md_error(mddev, tmp_dev->rdev);
-		bio_io_error(bio);
-		return true;
-	}
-
-	if (unlikely(bio_end_sector(bio) > end_sector)) {
-		/* This bio crosses a device boundary, so we have to split it */
-		struct bio *split = bio_split(bio, end_sector - bio_sector,
-					      GFP_NOIO, &mddev->bio_set);
-		bio_chain(split, bio);
-		submit_bio_noacct(bio);
-		bio = split;
-	}
-
-	md_account_bio(mddev, &bio);
-	bio_set_dev(bio, tmp_dev->rdev->bdev);
-	bio->bi_iter.bi_sector = bio->bi_iter.bi_sector -
-		start_sector + data_offset;
-
-	if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
-		     !bdev_max_discard_sectors(bio->bi_bdev))) {
-		/* Just ignore it */
-		bio_endio(bio);
-	} else {
-		if (mddev->gendisk)
-			trace_block_bio_remap(bio, disk_devt(mddev->gendisk),
-					      bio_sector);
-		mddev_check_write_zeroes(mddev, bio);
-		submit_bio_noacct(bio);
-	}
-	return true;
-
-out_of_bounds:
-	pr_err("md/linear:%s: make_request: Sector %llu out of bounds on dev %pg: %llu sectors, offset %llu\n",
-	       mdname(mddev),
-	       (unsigned long long)bio->bi_iter.bi_sector,
-	       tmp_dev->rdev->bdev,
-	       (unsigned long long)tmp_dev->rdev->sectors,
-	       (unsigned long long)start_sector);
-	bio_io_error(bio);
-	return true;
-}
-
-static void linear_status (struct seq_file *seq, struct mddev *mddev)
-{
-	seq_printf(seq, " %dk rounding", mddev->chunk_sectors / 2);
-}
-
-static void linear_error(struct mddev *mddev, struct md_rdev *rdev)
-{
-	if (!test_and_set_bit(MD_BROKEN, &mddev->flags)) {
-		char *md_name = mdname(mddev);
-
-		pr_crit("md/linear%s: Disk failure on %pg detected, failing array.\n",
-			md_name, rdev->bdev);
-	}
-}
-
-static void linear_quiesce(struct mddev *mddev, int state)
-{
-}
-
-static struct md_personality linear_personality =
-{
-	.name		= "linear",
-	.level		= LEVEL_LINEAR,
-	.owner		= THIS_MODULE,
-	.make_request	= linear_make_request,
-	.run		= linear_run,
-	.free		= linear_free,
-	.status		= linear_status,
-	.hot_add_disk	= linear_add,
-	.size		= linear_size,
-	.quiesce	= linear_quiesce,
-	.error_handler	= linear_error,
-};
-
-static int __init linear_init (void)
-{
-	return register_md_personality (&linear_personality);
-}
-
-static void linear_exit (void)
-{
-	unregister_md_personality (&linear_personality);
-}
-
-module_init(linear_init);
-module_exit(linear_exit);
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("Linear device concatenation personality for MD (deprecated)");
-MODULE_ALIAS("md-personality-1"); /* LINEAR - deprecated*/
-MODULE_ALIAS("md-linear");
-MODULE_ALIAS("md-level--1");
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 66b9e60b15c6..83f5a785c782 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -8124,7 +8124,7 @@ void md_error(struct mddev *mddev, struct md_rdev *rdev)
 		return;
 	mddev->pers->error_handler(mddev, rdev);
 
-	if (mddev->pers->level == 0 || mddev->pers->level == LEVEL_LINEAR)
+	if (mddev->pers->level == 0)
 		return;
 
 	if (mddev->degraded && !test_bit(MD_BROKEN, &mddev->flags))
diff --git a/include/uapi/linux/raid/md_p.h b/include/uapi/linux/raid/md_p.h
index 6c0aa577730f..b36e282a413d 100644
--- a/include/uapi/linux/raid/md_p.h
+++ b/include/uapi/linux/raid/md_p.h
@@ -2,15 +2,11 @@
 /*
    md_p.h : physical layout of Linux RAID devices
           Copyright (C) 1996-98 Ingo Molnar, Gadi Oxman
-	  
+
    This program is free software; you can redistribute it and/or modify
    it under the terms of the GNU General Public License as published by
    the Free Software Foundation; either version 2, or (at your option)
    any later version.
-   
-   You should have received a copy of the GNU General Public License
-   (for example /usr/src/linux/COPYING); if not, write to the Free
-   Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.  
 */
 
 #ifndef _MD_P_H
@@ -237,7 +233,7 @@ struct mdp_superblock_1 {
 	char	set_name[32];	/* set and interpreted by user-space */
 
 	__le64	ctime;		/* lo 40 bits are seconds, top 24 are microseconds or 0*/
-	__le32	level;		/* -4 (multipath), -1 (linear), 0,1,4,5 */
+	__le32	level;		/* -4 (multipath), 0,1,4,5 */
 	__le32	layout;		/* only for raid5 and raid10 currently */
 	__le64	size;		/* used size of component devices, in 512byte sectors */
 
diff --git a/include/uapi/linux/raid/md_u.h b/include/uapi/linux/raid/md_u.h
index 105307244961..c285f76e5d8d 100644
--- a/include/uapi/linux/raid/md_u.h
+++ b/include/uapi/linux/raid/md_u.h
@@ -2,15 +2,11 @@
 /*
    md_u.h : user <=> kernel API between Linux raidtools and RAID drivers
           Copyright (C) 1998 Ingo Molnar
-	  
+
    This program is free software; you can redistribute it and/or modify
    it under the terms of the GNU General Public License as published by
    the Free Software Foundation; either version 2, or (at your option)
    any later version.
-   
-   You should have received a copy of the GNU General Public License
-   (for example /usr/src/linux/COPYING); if not, write to the Free
-   Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.  
 */
 
 #ifndef _UAPI_MD_U_H
@@ -109,7 +105,6 @@ typedef struct mdu_array_info_s {
 
 /* non-obvious values for 'level' */
 #define	LEVEL_MULTIPATH		(-4)
-#define	LEVEL_LINEAR		(-1)
 #define	LEVEL_FAULTY		(-5)
 
 /* we need a value for 'no level specified' and 0
-- 
cgit v1.2.3


From d8730f0cf4effa015bc5e8840d8f8fb3cdb01aab Mon Sep 17 00:00:00 2001
From: Song Liu <song@kernel.org>
Date: Thu, 14 Dec 2023 14:21:06 -0800
Subject: md: Remove deprecated CONFIG_MD_MULTIPATH

md-multipath has been marked as deprecated for 2.5 years. Remove it.

Cc: Christoph Hellwig <hch@lst.de>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Neil Brown <neilb@suse.de>
Cc: Guoqing Jiang <guoqing.jiang@linux.dev>
Cc: Mateusz Grzonka <mateusz.grzonka@intel.com>
Cc: Jes Sorensen <jes@trained-monkey.org>
Signed-off-by: Song Liu <song@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Link: https://lore.kernel.org/r/20231214222107.2016042-3-song@kernel.org
---
 drivers/md/Kconfig             |  11 -
 drivers/md/Makefile            |   2 -
 drivers/md/md-multipath.c      | 463 -----------------------------------------
 drivers/md/md.c                | 241 ++++++++++-----------
 include/uapi/linux/raid/md_p.h |   2 +-
 include/uapi/linux/raid/md_u.h |   1 -
 6 files changed, 109 insertions(+), 611 deletions(-)
 delete mode 100644 drivers/md/md-multipath.c

(limited to 'include')

diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 0c721e0e5921..de4f47fe5a03 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -159,17 +159,6 @@ config MD_RAID456
 
 	  If unsure, say Y.
 
-config MD_MULTIPATH
-	tristate "Multipath I/O support (deprecated)"
-	depends on BLK_DEV_MD
-	help
-	  MD_MULTIPATH provides a simple multi-path personality for use
-	  the MD framework.  It is not under active development.  New
-	  projects should consider using DM_MULTIPATH which has more
-	  features and more testing.
-
-	  If unsure, say N.
-
 config MD_FAULTY
 	tristate "Faulty test module for MD (deprecated)"
 	depends on BLK_DEV_MD
diff --git a/drivers/md/Makefile b/drivers/md/Makefile
index c72f76cf7b63..6287c73399e7 100644
--- a/drivers/md/Makefile
+++ b/drivers/md/Makefile
@@ -29,7 +29,6 @@ dm-zoned-y	+= dm-zoned-target.o dm-zoned-metadata.o dm-zoned-reclaim.o
 
 md-mod-y	+= md.o md-bitmap.o
 raid456-y	+= raid5.o raid5-cache.o raid5-ppl.o
-multipath-y	+= md-multipath.o
 faulty-y	+= md-faulty.o
 
 # Note: link order is important.  All raid personalities
@@ -41,7 +40,6 @@ obj-$(CONFIG_MD_RAID0)		+= raid0.o
 obj-$(CONFIG_MD_RAID1)		+= raid1.o
 obj-$(CONFIG_MD_RAID10)		+= raid10.o
 obj-$(CONFIG_MD_RAID456)	+= raid456.o
-obj-$(CONFIG_MD_MULTIPATH)	+= multipath.o
 obj-$(CONFIG_MD_FAULTY)		+= faulty.o
 obj-$(CONFIG_MD_CLUSTER)	+= md-cluster.o
 obj-$(CONFIG_BCACHE)		+= bcache/
diff --git a/drivers/md/md-multipath.c b/drivers/md/md-multipath.c
deleted file mode 100644
index 19c8625ea642..000000000000
--- a/drivers/md/md-multipath.c
+++ /dev/null
@@ -1,463 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * multipath.c : Multiple Devices driver for Linux
- *
- * Copyright (C) 1999, 2000, 2001 Ingo Molnar, Red Hat
- *
- * Copyright (C) 1996, 1997, 1998 Ingo Molnar, Miguel de Icaza, Gadi Oxman
- *
- * MULTIPATH management functions.
- *
- * derived from raid1.c.
- */
-
-#include <linux/blkdev.h>
-#include <linux/module.h>
-#include <linux/raid/md_u.h>
-#include <linux/seq_file.h>
-#include <linux/slab.h>
-#include "md.h"
-#include "md-multipath.h"
-
-#define MAX_WORK_PER_DISK 128
-
-#define	NR_RESERVED_BUFS	32
-
-static int multipath_map (struct mpconf *conf)
-{
-	int i, disks = conf->raid_disks;
-
-	/*
-	 * Later we do read balancing on the read side
-	 * now we use the first available disk.
-	 */
-
-	for (i = 0; i < disks; i++) {
-		struct md_rdev *rdev = conf->multipaths[i].rdev;
-
-		if (rdev && test_bit(In_sync, &rdev->flags) &&
-		    !test_bit(Faulty, &rdev->flags)) {
-			atomic_inc(&rdev->nr_pending);
-			return i;
-		}
-	}
-
-	pr_crit_ratelimited("multipath_map(): no more operational IO paths?\n");
-	return (-1);
-}
-
-static void multipath_reschedule_retry (struct multipath_bh *mp_bh)
-{
-	unsigned long flags;
-	struct mddev *mddev = mp_bh->mddev;
-	struct mpconf *conf = mddev->private;
-
-	spin_lock_irqsave(&conf->device_lock, flags);
-	list_add(&mp_bh->retry_list, &conf->retry_list);
-	spin_unlock_irqrestore(&conf->device_lock, flags);
-	md_wakeup_thread(mddev->thread);
-}
-
-/*
- * multipath_end_bh_io() is called when we have finished servicing a multipathed
- * operation and are ready to return a success/failure code to the buffer
- * cache layer.
- */
-static void multipath_end_bh_io(struct multipath_bh *mp_bh, blk_status_t status)
-{
-	struct bio *bio = mp_bh->master_bio;
-	struct mpconf *conf = mp_bh->mddev->private;
-
-	bio->bi_status = status;
-	bio_endio(bio);
-	mempool_free(mp_bh, &conf->pool);
-}
-
-static void multipath_end_request(struct bio *bio)
-{
-	struct multipath_bh *mp_bh = bio->bi_private;
-	struct mpconf *conf = mp_bh->mddev->private;
-	struct md_rdev *rdev = conf->multipaths[mp_bh->path].rdev;
-
-	if (!bio->bi_status)
-		multipath_end_bh_io(mp_bh, 0);
-	else if (!(bio->bi_opf & REQ_RAHEAD)) {
-		/*
-		 * oops, IO error:
-		 */
-		md_error (mp_bh->mddev, rdev);
-		pr_info("multipath: %pg: rescheduling sector %llu\n",
-			rdev->bdev,
-			(unsigned long long)bio->bi_iter.bi_sector);
-		multipath_reschedule_retry(mp_bh);
-	} else
-		multipath_end_bh_io(mp_bh, bio->bi_status);
-	rdev_dec_pending(rdev, conf->mddev);
-}
-
-static bool multipath_make_request(struct mddev *mddev, struct bio * bio)
-{
-	struct mpconf *conf = mddev->private;
-	struct multipath_bh * mp_bh;
-	struct multipath_info *multipath;
-
-	if (unlikely(bio->bi_opf & REQ_PREFLUSH)
-	    && md_flush_request(mddev, bio))
-		return true;
-
-	md_account_bio(mddev, &bio);
-	mp_bh = mempool_alloc(&conf->pool, GFP_NOIO);
-
-	mp_bh->master_bio = bio;
-	mp_bh->mddev = mddev;
-
-	mp_bh->path = multipath_map(conf);
-	if (mp_bh->path < 0) {
-		bio_io_error(bio);
-		mempool_free(mp_bh, &conf->pool);
-		return true;
-	}
-	multipath = conf->multipaths + mp_bh->path;
-
-	bio_init_clone(multipath->rdev->bdev, &mp_bh->bio, bio, GFP_NOIO);
-
-	mp_bh->bio.bi_iter.bi_sector += multipath->rdev->data_offset;
-	mp_bh->bio.bi_opf |= REQ_FAILFAST_TRANSPORT;
-	mp_bh->bio.bi_end_io = multipath_end_request;
-	mp_bh->bio.bi_private = mp_bh;
-	mddev_check_write_zeroes(mddev, &mp_bh->bio);
-	submit_bio_noacct(&mp_bh->bio);
-	return true;
-}
-
-static void multipath_status(struct seq_file *seq, struct mddev *mddev)
-{
-	struct mpconf *conf = mddev->private;
-	int i;
-
-	lockdep_assert_held(&mddev->lock);
-
-	seq_printf (seq, " [%d/%d] [", conf->raid_disks,
-		    conf->raid_disks - mddev->degraded);
-	for (i = 0; i < conf->raid_disks; i++) {
-		struct md_rdev *rdev = READ_ONCE(conf->multipaths[i].rdev);
-
-		seq_printf(seq, "%s",
-			   rdev && test_bit(In_sync, &rdev->flags) ? "U" : "_");
-	}
-	seq_putc(seq, ']');
-}
-
-/*
- * Careful, this can execute in IRQ contexts as well!
- */
-static void multipath_error (struct mddev *mddev, struct md_rdev *rdev)
-{
-	struct mpconf *conf = mddev->private;
-
-	if (conf->raid_disks - mddev->degraded <= 1) {
-		/*
-		 * Uh oh, we can do nothing if this is our last path, but
-		 * first check if this is a queued request for a device
-		 * which has just failed.
-		 */
-		pr_warn("multipath: only one IO path left and IO error.\n");
-		/* leave it active... it's all we have */
-		return;
-	}
-	/*
-	 * Mark disk as unusable
-	 */
-	if (test_and_clear_bit(In_sync, &rdev->flags)) {
-		unsigned long flags;
-		spin_lock_irqsave(&conf->device_lock, flags);
-		mddev->degraded++;
-		spin_unlock_irqrestore(&conf->device_lock, flags);
-	}
-	set_bit(Faulty, &rdev->flags);
-	set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
-	pr_err("multipath: IO failure on %pg, disabling IO path.\n"
-	       "multipath: Operation continuing on %d IO paths.\n",
-	       rdev->bdev,
-	       conf->raid_disks - mddev->degraded);
-}
-
-static void print_multipath_conf(struct mpconf *conf)
-{
-	int i;
-	struct multipath_info *tmp;
-
-	pr_debug("MULTIPATH conf printout:\n");
-	if (!conf) {
-		pr_debug("(conf==NULL)\n");
-		return;
-	}
-	pr_debug(" --- wd:%d rd:%d\n", conf->raid_disks - conf->mddev->degraded,
-		 conf->raid_disks);
-
-	lockdep_assert_held(&conf->mddev->reconfig_mutex);
-	for (i = 0; i < conf->raid_disks; i++) {
-		tmp = conf->multipaths + i;
-		if (tmp->rdev)
-			pr_debug(" disk%d, o:%d, dev:%pg\n",
-				 i,!test_bit(Faulty, &tmp->rdev->flags),
-				 tmp->rdev->bdev);
-	}
-}
-
-static int multipath_add_disk(struct mddev *mddev, struct md_rdev *rdev)
-{
-	struct mpconf *conf = mddev->private;
-	int err = -EEXIST;
-	int path;
-	struct multipath_info *p;
-	int first = 0;
-	int last = mddev->raid_disks - 1;
-
-	if (rdev->raid_disk >= 0)
-		first = last = rdev->raid_disk;
-
-	print_multipath_conf(conf);
-
-	for (path = first; path <= last; path++)
-		if ((p=conf->multipaths+path)->rdev == NULL) {
-			disk_stack_limits(mddev->gendisk, rdev->bdev,
-					  rdev->data_offset << 9);
-
-			err = md_integrity_add_rdev(rdev, mddev);
-			if (err)
-				break;
-			spin_lock_irq(&conf->device_lock);
-			mddev->degraded--;
-			rdev->raid_disk = path;
-			set_bit(In_sync, &rdev->flags);
-			spin_unlock_irq(&conf->device_lock);
-			WRITE_ONCE(p->rdev, rdev);
-			err = 0;
-			break;
-		}
-
-	print_multipath_conf(conf);
-
-	return err;
-}
-
-static int multipath_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
-{
-	struct mpconf *conf = mddev->private;
-	int err = 0;
-	int number = rdev->raid_disk;
-	struct multipath_info *p = conf->multipaths + number;
-
-	print_multipath_conf(conf);
-
-	if (rdev == p->rdev) {
-		if (test_bit(In_sync, &rdev->flags) ||
-		    atomic_read(&rdev->nr_pending)) {
-			pr_warn("hot-remove-disk, slot %d is identified but is still operational!\n", number);
-			err = -EBUSY;
-			goto abort;
-		}
-		WRITE_ONCE(p->rdev, NULL);
-		err = md_integrity_register(mddev);
-	}
-abort:
-
-	print_multipath_conf(conf);
-	return err;
-}
-
-/*
- * This is a kernel thread which:
- *
- *	1.	Retries failed read operations on working multipaths.
- *	2.	Updates the raid superblock when problems encounter.
- *	3.	Performs writes following reads for array syncronising.
- */
-
-static void multipathd(struct md_thread *thread)
-{
-	struct mddev *mddev = thread->mddev;
-	struct multipath_bh *mp_bh;
-	struct bio *bio;
-	unsigned long flags;
-	struct mpconf *conf = mddev->private;
-	struct list_head *head = &conf->retry_list;
-
-	md_check_recovery(mddev);
-	for (;;) {
-		spin_lock_irqsave(&conf->device_lock, flags);
-		if (list_empty(head))
-			break;
-		mp_bh = list_entry(head->prev, struct multipath_bh, retry_list);
-		list_del(head->prev);
-		spin_unlock_irqrestore(&conf->device_lock, flags);
-
-		bio = &mp_bh->bio;
-		bio->bi_iter.bi_sector = mp_bh->master_bio->bi_iter.bi_sector;
-
-		if ((mp_bh->path = multipath_map (conf))<0) {
-			pr_err("multipath: %pg: unrecoverable IO read error for block %llu\n",
-			       bio->bi_bdev,
-			       (unsigned long long)bio->bi_iter.bi_sector);
-			multipath_end_bh_io(mp_bh, BLK_STS_IOERR);
-		} else {
-			pr_err("multipath: %pg: redirecting sector %llu to another IO path\n",
-			       bio->bi_bdev,
-			       (unsigned long long)bio->bi_iter.bi_sector);
-			*bio = *(mp_bh->master_bio);
-			bio->bi_iter.bi_sector +=
-				conf->multipaths[mp_bh->path].rdev->data_offset;
-			bio_set_dev(bio, conf->multipaths[mp_bh->path].rdev->bdev);
-			bio->bi_opf |= REQ_FAILFAST_TRANSPORT;
-			bio->bi_end_io = multipath_end_request;
-			bio->bi_private = mp_bh;
-			submit_bio_noacct(bio);
-		}
-	}
-	spin_unlock_irqrestore(&conf->device_lock, flags);
-}
-
-static sector_t multipath_size(struct mddev *mddev, sector_t sectors, int raid_disks)
-{
-	WARN_ONCE(sectors || raid_disks,
-		  "%s does not support generic reshape\n", __func__);
-
-	return mddev->dev_sectors;
-}
-
-static int multipath_run (struct mddev *mddev)
-{
-	struct mpconf *conf;
-	int disk_idx;
-	struct multipath_info *disk;
-	struct md_rdev *rdev;
-	int working_disks;
-	int ret;
-
-	if (md_check_no_bitmap(mddev))
-		return -EINVAL;
-
-	if (mddev->level != LEVEL_MULTIPATH) {
-		pr_warn("multipath: %s: raid level not set to multipath IO (%d)\n",
-			mdname(mddev), mddev->level);
-		goto out;
-	}
-	/*
-	 * copy the already verified devices into our private MULTIPATH
-	 * bookkeeping area. [whatever we allocate in multipath_run(),
-	 * should be freed in multipath_free()]
-	 */
-
-	conf = kzalloc(sizeof(struct mpconf), GFP_KERNEL);
-	mddev->private = conf;
-	if (!conf)
-		goto out;
-
-	conf->multipaths = kcalloc(mddev->raid_disks,
-				   sizeof(struct multipath_info),
-				   GFP_KERNEL);
-	if (!conf->multipaths)
-		goto out_free_conf;
-
-	working_disks = 0;
-	rdev_for_each(rdev, mddev) {
-		disk_idx = rdev->raid_disk;
-		if (disk_idx < 0 ||
-		    disk_idx >= mddev->raid_disks)
-			continue;
-
-		disk = conf->multipaths + disk_idx;
-		disk->rdev = rdev;
-		disk_stack_limits(mddev->gendisk, rdev->bdev,
-				  rdev->data_offset << 9);
-
-		if (!test_bit(Faulty, &rdev->flags))
-			working_disks++;
-	}
-
-	conf->raid_disks = mddev->raid_disks;
-	conf->mddev = mddev;
-	spin_lock_init(&conf->device_lock);
-	INIT_LIST_HEAD(&conf->retry_list);
-
-	if (!working_disks) {
-		pr_warn("multipath: no operational IO paths for %s\n",
-			mdname(mddev));
-		goto out_free_conf;
-	}
-	mddev->degraded = conf->raid_disks - working_disks;
-
-	ret = mempool_init_kmalloc_pool(&conf->pool, NR_RESERVED_BUFS,
-					sizeof(struct multipath_bh));
-	if (ret)
-		goto out_free_conf;
-
-	rcu_assign_pointer(mddev->thread,
-			   md_register_thread(multipathd, mddev, "multipath"));
-	if (!mddev->thread)
-		goto out_free_conf;
-
-	pr_info("multipath: array %s active with %d out of %d IO paths\n",
-		mdname(mddev), conf->raid_disks - mddev->degraded,
-		mddev->raid_disks);
-	/*
-	 * Ok, everything is just fine now
-	 */
-	md_set_array_sectors(mddev, multipath_size(mddev, 0, 0));
-
-	if (md_integrity_register(mddev))
-		goto out_free_conf;
-
-	return 0;
-
-out_free_conf:
-	mempool_exit(&conf->pool);
-	kfree(conf->multipaths);
-	kfree(conf);
-	mddev->private = NULL;
-out:
-	return -EIO;
-}
-
-static void multipath_free(struct mddev *mddev, void *priv)
-{
-	struct mpconf *conf = priv;
-
-	mempool_exit(&conf->pool);
-	kfree(conf->multipaths);
-	kfree(conf);
-}
-
-static struct md_personality multipath_personality =
-{
-	.name		= "multipath",
-	.level		= LEVEL_MULTIPATH,
-	.owner		= THIS_MODULE,
-	.make_request	= multipath_make_request,
-	.run		= multipath_run,
-	.free		= multipath_free,
-	.status		= multipath_status,
-	.error_handler	= multipath_error,
-	.hot_add_disk	= multipath_add_disk,
-	.hot_remove_disk= multipath_remove_disk,
-	.size		= multipath_size,
-};
-
-static int __init multipath_init (void)
-{
-	return register_md_personality (&multipath_personality);
-}
-
-static void __exit multipath_exit (void)
-{
-	unregister_md_personality (&multipath_personality);
-}
-
-module_init(multipath_init);
-module_exit(multipath_exit);
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("simple multi-path personality for MD (deprecated)");
-MODULE_ALIAS("md-personality-7"); /* MULTIPATH */
-MODULE_ALIAS("md-multipath");
-MODULE_ALIAS("md-level--4");
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 83f5a785c782..e351e6c51cc7 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -1287,17 +1287,11 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor
 	rdev->sb_size = MD_SB_BYTES;
 	rdev->badblocks.shift = -1;
 
-	if (sb->level == LEVEL_MULTIPATH)
-		rdev->desc_nr = -1;
-	else
-		rdev->desc_nr = sb->this_disk.number;
-
-	/* not spare disk, or LEVEL_MULTIPATH */
-	if (sb->level == LEVEL_MULTIPATH ||
-		(rdev->desc_nr >= 0 &&
-		 rdev->desc_nr < MD_SB_DISKS &&
-		 sb->disks[rdev->desc_nr].state &
-		 ((1<<MD_DISK_SYNC) | (1 << MD_DISK_ACTIVE))))
+	rdev->desc_nr = sb->this_disk.number;
+
+	/* not spare disk */
+	if (rdev->desc_nr >= 0 && rdev->desc_nr < MD_SB_DISKS &&
+	    sb->disks[rdev->desc_nr].state & ((1<<MD_DISK_SYNC) | (1 << MD_DISK_ACTIVE)))
 		spare_disk = false;
 
 	if (!refdev) {
@@ -1444,31 +1438,28 @@ static int super_90_validate(struct mddev *mddev, struct md_rdev *freshest, stru
 			return 0;
 	}
 
-	if (mddev->level != LEVEL_MULTIPATH) {
-		desc = sb->disks + rdev->desc_nr;
+	desc = sb->disks + rdev->desc_nr;
 
-		if (desc->state & (1<<MD_DISK_FAULTY))
-			set_bit(Faulty, &rdev->flags);
-		else if (desc->state & (1<<MD_DISK_SYNC) /* &&
-			    desc->raid_disk < mddev->raid_disks */) {
-			set_bit(In_sync, &rdev->flags);
+	if (desc->state & (1<<MD_DISK_FAULTY))
+		set_bit(Faulty, &rdev->flags);
+	else if (desc->state & (1<<MD_DISK_SYNC)) {
+		set_bit(In_sync, &rdev->flags);
+		rdev->raid_disk = desc->raid_disk;
+		rdev->saved_raid_disk = desc->raid_disk;
+	} else if (desc->state & (1<<MD_DISK_ACTIVE)) {
+		/* active but not in sync implies recovery up to
+		 * reshape position.  We don't know exactly where
+		 * that is, so set to zero for now
+		 */
+		if (mddev->minor_version >= 91) {
+			rdev->recovery_offset = 0;
 			rdev->raid_disk = desc->raid_disk;
-			rdev->saved_raid_disk = desc->raid_disk;
-		} else if (desc->state & (1<<MD_DISK_ACTIVE)) {
-			/* active but not in sync implies recovery up to
-			 * reshape position.  We don't know exactly where
-			 * that is, so set to zero for now */
-			if (mddev->minor_version >= 91) {
-				rdev->recovery_offset = 0;
-				rdev->raid_disk = desc->raid_disk;
-			}
 		}
-		if (desc->state & (1<<MD_DISK_WRITEMOSTLY))
-			set_bit(WriteMostly, &rdev->flags);
-		if (desc->state & (1<<MD_DISK_FAILFAST))
-			set_bit(FailFast, &rdev->flags);
-	} else /* MULTIPATH are always insync */
-		set_bit(In_sync, &rdev->flags);
+	}
+	if (desc->state & (1<<MD_DISK_WRITEMOSTLY))
+		set_bit(WriteMostly, &rdev->flags);
+	if (desc->state & (1<<MD_DISK_FAILFAST))
+		set_bit(FailFast, &rdev->flags);
 	return 0;
 }
 
@@ -1758,10 +1749,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
 	    && rdev->new_data_offset < sb_start + (rdev->sb_size/512))
 		return -EINVAL;
 
-	if (sb->level == cpu_to_le32(LEVEL_MULTIPATH))
-		rdev->desc_nr = -1;
-	else
-		rdev->desc_nr = le32_to_cpu(sb->dev_number);
+	rdev->desc_nr = le32_to_cpu(sb->dev_number);
 
 	if (!rdev->bb_page) {
 		rdev->bb_page = alloc_page(GFP_KERNEL);
@@ -1814,12 +1802,10 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
 	    sb->level != 0)
 		return -EINVAL;
 
-	/* not spare disk, or LEVEL_MULTIPATH */
-	if (sb->level == cpu_to_le32(LEVEL_MULTIPATH) ||
-		(rdev->desc_nr >= 0 &&
-		rdev->desc_nr < le32_to_cpu(sb->max_dev) &&
-		(le16_to_cpu(sb->dev_roles[rdev->desc_nr]) < MD_DISK_ROLE_MAX ||
-		 le16_to_cpu(sb->dev_roles[rdev->desc_nr]) == MD_DISK_ROLE_JOURNAL)))
+	/* not spare disk */
+	if (rdev->desc_nr >= 0 && rdev->desc_nr < le32_to_cpu(sb->max_dev) &&
+	    (le16_to_cpu(sb->dev_roles[rdev->desc_nr]) < MD_DISK_ROLE_MAX ||
+	     le16_to_cpu(sb->dev_roles[rdev->desc_nr]) == MD_DISK_ROLE_JOURNAL))
 		spare_disk = false;
 
 	if (!refdev) {
@@ -1862,6 +1848,7 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *freshest, struc
 {
 	struct mdp_superblock_1 *sb = page_address(rdev->sb_page);
 	__u64 ev1 = le64_to_cpu(sb->events);
+	int role;
 
 	rdev->raid_disk = -1;
 	clear_bit(Faulty, &rdev->flags);
@@ -1977,88 +1964,85 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *freshest, struc
 			/* just a hot-add of a new device, leave raid_disk at -1 */
 			return 0;
 	}
-	if (mddev->level != LEVEL_MULTIPATH) {
-		int role;
-		if (rdev->desc_nr < 0 ||
-		    rdev->desc_nr >= le32_to_cpu(sb->max_dev)) {
-			role = MD_DISK_ROLE_SPARE;
-			rdev->desc_nr = -1;
-		} else if (mddev->pers == NULL && freshest && ev1 < mddev->events) {
-			/*
-			 * If we are assembling, and our event counter is smaller than the
-			 * highest event counter, we cannot trust our superblock about the role.
-			 * It could happen that our rdev was marked as Faulty, and all other
-			 * superblocks were updated with +1 event counter.
-			 * Then, before the next superblock update, which typically happens when
-			 * remove_and_add_spares() removes the device from the array, there was
-			 * a crash or reboot.
-			 * If we allow current rdev without consulting the freshest superblock,
-			 * we could cause data corruption.
-			 * Note that in this case our event counter is smaller by 1 than the
-			 * highest, otherwise, this rdev would not be allowed into array;
-			 * both kernel and mdadm allow event counter difference of 1.
-			 */
-			struct mdp_superblock_1 *freshest_sb = page_address(freshest->sb_page);
-			u32 freshest_max_dev = le32_to_cpu(freshest_sb->max_dev);
-
-			if (rdev->desc_nr >= freshest_max_dev) {
-				/* this is unexpected, better not proceed */
-				pr_warn("md: %s: rdev[%pg]: desc_nr(%d) >= freshest(%pg)->sb->max_dev(%u)\n",
-						mdname(mddev), rdev->bdev, rdev->desc_nr,
-						freshest->bdev, freshest_max_dev);
-				return -EUCLEAN;
-			}
 
-			role = le16_to_cpu(freshest_sb->dev_roles[rdev->desc_nr]);
-			pr_debug("md: %s: rdev[%pg]: role=%d(0x%x) according to freshest %pg\n",
-				     mdname(mddev), rdev->bdev, role, role, freshest->bdev);
-		} else {
-			role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]);
+	if (rdev->desc_nr < 0 ||
+	    rdev->desc_nr >= le32_to_cpu(sb->max_dev)) {
+		role = MD_DISK_ROLE_SPARE;
+		rdev->desc_nr = -1;
+	} else if (mddev->pers == NULL && freshest && ev1 < mddev->events) {
+		/*
+		 * If we are assembling, and our event counter is smaller than the
+		 * highest event counter, we cannot trust our superblock about the role.
+		 * It could happen that our rdev was marked as Faulty, and all other
+		 * superblocks were updated with +1 event counter.
+		 * Then, before the next superblock update, which typically happens when
+		 * remove_and_add_spares() removes the device from the array, there was
+		 * a crash or reboot.
+		 * If we allow current rdev without consulting the freshest superblock,
+		 * we could cause data corruption.
+		 * Note that in this case our event counter is smaller by 1 than the
+		 * highest, otherwise, this rdev would not be allowed into array;
+		 * both kernel and mdadm allow event counter difference of 1.
+		 */
+		struct mdp_superblock_1 *freshest_sb = page_address(freshest->sb_page);
+		u32 freshest_max_dev = le32_to_cpu(freshest_sb->max_dev);
+
+		if (rdev->desc_nr >= freshest_max_dev) {
+			/* this is unexpected, better not proceed */
+			pr_warn("md: %s: rdev[%pg]: desc_nr(%d) >= freshest(%pg)->sb->max_dev(%u)\n",
+				mdname(mddev), rdev->bdev, rdev->desc_nr,
+				freshest->bdev, freshest_max_dev);
+			return -EUCLEAN;
 		}
-		switch(role) {
-		case MD_DISK_ROLE_SPARE: /* spare */
-			break;
-		case MD_DISK_ROLE_FAULTY: /* faulty */
-			set_bit(Faulty, &rdev->flags);
-			break;
-		case MD_DISK_ROLE_JOURNAL: /* journal device */
-			if (!(le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL)) {
-				/* journal device without journal feature */
-				pr_warn("md: journal device provided without journal feature, ignoring the device\n");
-				return -EINVAL;
-			}
-			set_bit(Journal, &rdev->flags);
-			rdev->journal_tail = le64_to_cpu(sb->journal_tail);
-			rdev->raid_disk = 0;
-			break;
-		default:
-			rdev->saved_raid_disk = role;
-			if ((le32_to_cpu(sb->feature_map) &
-			     MD_FEATURE_RECOVERY_OFFSET)) {
-				rdev->recovery_offset = le64_to_cpu(sb->recovery_offset);
-				if (!(le32_to_cpu(sb->feature_map) &
-				      MD_FEATURE_RECOVERY_BITMAP))
-					rdev->saved_raid_disk = -1;
-			} else {
-				/*
-				 * If the array is FROZEN, then the device can't
-				 * be in_sync with rest of array.
-				 */
-				if (!test_bit(MD_RECOVERY_FROZEN,
-					      &mddev->recovery))
-					set_bit(In_sync, &rdev->flags);
-			}
-			rdev->raid_disk = role;
-			break;
+
+		role = le16_to_cpu(freshest_sb->dev_roles[rdev->desc_nr]);
+		pr_debug("md: %s: rdev[%pg]: role=%d(0x%x) according to freshest %pg\n",
+			 mdname(mddev), rdev->bdev, role, role, freshest->bdev);
+	} else {
+		role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]);
+	}
+	switch (role) {
+	case MD_DISK_ROLE_SPARE: /* spare */
+		break;
+	case MD_DISK_ROLE_FAULTY: /* faulty */
+		set_bit(Faulty, &rdev->flags);
+		break;
+	case MD_DISK_ROLE_JOURNAL: /* journal device */
+		if (!(le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL)) {
+			/* journal device without journal feature */
+			pr_warn("md: journal device provided without journal feature, ignoring the device\n");
+			return -EINVAL;
 		}
-		if (sb->devflags & WriteMostly1)
-			set_bit(WriteMostly, &rdev->flags);
-		if (sb->devflags & FailFast1)
-			set_bit(FailFast, &rdev->flags);
-		if (le32_to_cpu(sb->feature_map) & MD_FEATURE_REPLACEMENT)
-			set_bit(Replacement, &rdev->flags);
-	} else /* MULTIPATH are always insync */
-		set_bit(In_sync, &rdev->flags);
+		set_bit(Journal, &rdev->flags);
+		rdev->journal_tail = le64_to_cpu(sb->journal_tail);
+		rdev->raid_disk = 0;
+		break;
+	default:
+		rdev->saved_raid_disk = role;
+		if ((le32_to_cpu(sb->feature_map) &
+		     MD_FEATURE_RECOVERY_OFFSET)) {
+			rdev->recovery_offset = le64_to_cpu(sb->recovery_offset);
+			if (!(le32_to_cpu(sb->feature_map) &
+			      MD_FEATURE_RECOVERY_BITMAP))
+				rdev->saved_raid_disk = -1;
+		} else {
+			/*
+			 * If the array is FROZEN, then the device can't
+			 * be in_sync with rest of array.
+			 */
+			if (!test_bit(MD_RECOVERY_FROZEN,
+				      &mddev->recovery))
+				set_bit(In_sync, &rdev->flags);
+		}
+		rdev->raid_disk = role;
+		break;
+	}
+	if (sb->devflags & WriteMostly1)
+		set_bit(WriteMostly, &rdev->flags);
+	if (sb->devflags & FailFast1)
+		set_bit(FailFast, &rdev->flags);
+	if (le32_to_cpu(sb->feature_map) & MD_FEATURE_REPLACEMENT)
+		set_bit(Replacement, &rdev->flags);
 
 	return 0;
 }
@@ -2876,10 +2860,6 @@ rewrite:
 		} else
 			pr_debug("md: %pg (skipping faulty)\n",
 				 rdev->bdev);
-
-		if (mddev->level == LEVEL_MULTIPATH)
-			/* only need to write one superblock... */
-			break;
 	}
 	if (md_super_wait(mddev) < 0)
 		goto rewrite;
@@ -3880,13 +3860,8 @@ static int analyze_sbs(struct mddev *mddev)
 				continue;
 			}
 		}
-		if (mddev->level == LEVEL_MULTIPATH) {
-			rdev->desc_nr = i++;
-			rdev->raid_disk = rdev->desc_nr;
-			set_bit(In_sync, &rdev->flags);
-		} else if (rdev->raid_disk >=
-			    (mddev->raid_disks - min(0, mddev->delta_disks)) &&
-			   !test_bit(Journal, &rdev->flags)) {
+		if (rdev->raid_disk >= (mddev->raid_disks - min(0, mddev->delta_disks)) &&
+		    !test_bit(Journal, &rdev->flags)) {
 			rdev->raid_disk = -1;
 			clear_bit(In_sync, &rdev->flags);
 		}
diff --git a/include/uapi/linux/raid/md_p.h b/include/uapi/linux/raid/md_p.h
index b36e282a413d..5a43c23f53bf 100644
--- a/include/uapi/linux/raid/md_p.h
+++ b/include/uapi/linux/raid/md_p.h
@@ -233,7 +233,7 @@ struct mdp_superblock_1 {
 	char	set_name[32];	/* set and interpreted by user-space */
 
 	__le64	ctime;		/* lo 40 bits are seconds, top 24 are microseconds or 0*/
-	__le32	level;		/* -4 (multipath), 0,1,4,5 */
+	__le32	level;		/* 0,1,4,5 */
 	__le32	layout;		/* only for raid5 and raid10 currently */
 	__le64	size;		/* used size of component devices, in 512byte sectors */
 
diff --git a/include/uapi/linux/raid/md_u.h b/include/uapi/linux/raid/md_u.h
index c285f76e5d8d..b44bbc356643 100644
--- a/include/uapi/linux/raid/md_u.h
+++ b/include/uapi/linux/raid/md_u.h
@@ -104,7 +104,6 @@ typedef struct mdu_array_info_s {
 } mdu_array_info_t;
 
 /* non-obvious values for 'level' */
-#define	LEVEL_MULTIPATH		(-4)
 #define	LEVEL_FAULTY		(-5)
 
 /* we need a value for 'no level specified' and 0
-- 
cgit v1.2.3


From 415c7451872b0d037760795edd3961eaa63276ea Mon Sep 17 00:00:00 2001
From: Song Liu <song@kernel.org>
Date: Thu, 14 Dec 2023 14:21:07 -0800
Subject: md: Remove deprecated CONFIG_MD_FAULTY

md-faulty has been marked as deprecated for 2.5 years. Remove it.

Cc: Christoph Hellwig <hch@lst.de>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Neil Brown <neilb@suse.de>
Cc: Guoqing Jiang <guoqing.jiang@linux.dev>
Cc: Mateusz Grzonka <mateusz.grzonka@intel.com>
Cc: Jes Sorensen <jes@trained-monkey.org>
Signed-off-by: Song Liu <song@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Link: https://lore.kernel.org/r/20231214222107.2016042-4-song@kernel.org
---
 drivers/md/Kconfig             |  10 --
 drivers/md/Makefile            |   2 -
 drivers/md/md-faulty.c         | 365 -----------------------------------------
 include/uapi/linux/raid/md_u.h |   3 -
 4 files changed, 380 deletions(-)
 delete mode 100644 drivers/md/md-faulty.c

(limited to 'include')

diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index de4f47fe5a03..f6dc2acdf1ed 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -159,16 +159,6 @@ config MD_RAID456
 
 	  If unsure, say Y.
 
-config MD_FAULTY
-	tristate "Faulty test module for MD (deprecated)"
-	depends on BLK_DEV_MD
-	help
-	  The "faulty" module allows for a block device that occasionally returns
-	  read or write errors.  It is useful for testing.
-
-	  In unsure, say N.
-
-
 config MD_CLUSTER
 	tristate "Cluster Support for MD"
 	depends on BLK_DEV_MD
diff --git a/drivers/md/Makefile b/drivers/md/Makefile
index 6287c73399e7..027d7cfeca3f 100644
--- a/drivers/md/Makefile
+++ b/drivers/md/Makefile
@@ -29,7 +29,6 @@ dm-zoned-y	+= dm-zoned-target.o dm-zoned-metadata.o dm-zoned-reclaim.o
 
 md-mod-y	+= md.o md-bitmap.o
 raid456-y	+= raid5.o raid5-cache.o raid5-ppl.o
-faulty-y	+= md-faulty.o
 
 # Note: link order is important.  All raid personalities
 # and must come before md.o, as they each initialise
@@ -40,7 +39,6 @@ obj-$(CONFIG_MD_RAID0)		+= raid0.o
 obj-$(CONFIG_MD_RAID1)		+= raid1.o
 obj-$(CONFIG_MD_RAID10)		+= raid10.o
 obj-$(CONFIG_MD_RAID456)	+= raid456.o
-obj-$(CONFIG_MD_FAULTY)		+= faulty.o
 obj-$(CONFIG_MD_CLUSTER)	+= md-cluster.o
 obj-$(CONFIG_BCACHE)		+= bcache/
 obj-$(CONFIG_BLK_DEV_MD)	+= md-mod.o
diff --git a/drivers/md/md-faulty.c b/drivers/md/md-faulty.c
deleted file mode 100644
index a039e8e20f55..000000000000
--- a/drivers/md/md-faulty.c
+++ /dev/null
@@ -1,365 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * faulty.c : Multiple Devices driver for Linux
- *
- * Copyright (C) 2004 Neil Brown
- *
- * fautly-device-simulator personality for md
- */
-
-
-/*
- * The "faulty" personality causes some requests to fail.
- *
- * Possible failure modes are:
- *   reads fail "randomly" but succeed on retry
- *   writes fail "randomly" but succeed on retry
- *   reads for some address fail and then persist until a write
- *   reads for some address fail and then persist irrespective of write
- *   writes for some address fail and persist
- *   all writes fail
- *
- * Different modes can be active at a time, but only
- * one can be set at array creation.  Others can be added later.
- * A mode can be one-shot or recurrent with the recurrence being
- * once in every N requests.
- * The bottom 5 bits of the "layout" indicate the mode.  The
- * remainder indicate a period, or 0 for one-shot.
- *
- * There is an implementation limit on the number of concurrently
- * persisting-faulty blocks. When a new fault is requested that would
- * exceed the limit, it is ignored.
- * All current faults can be clear using a layout of "0".
- *
- * Requests are always sent to the device.  If they are to fail,
- * we clone the bio and insert a new b_end_io into the chain.
- */
-
-#define	WriteTransient	0
-#define	ReadTransient	1
-#define	WritePersistent	2
-#define	ReadPersistent	3
-#define	WriteAll	4 /* doesn't go to device */
-#define	ReadFixable	5
-#define	Modes	6
-
-#define	ClearErrors	31
-#define	ClearFaults	30
-
-#define AllPersist	100 /* internal use only */
-#define	NoPersist	101
-
-#define	ModeMask	0x1f
-#define	ModeShift	5
-
-#define MaxFault	50
-#include <linux/blkdev.h>
-#include <linux/module.h>
-#include <linux/raid/md_u.h>
-#include <linux/slab.h>
-#include "md.h"
-#include <linux/seq_file.h>
-
-
-static void faulty_fail(struct bio *bio)
-{
-	struct bio *b = bio->bi_private;
-
-	b->bi_iter.bi_size = bio->bi_iter.bi_size;
-	b->bi_iter.bi_sector = bio->bi_iter.bi_sector;
-
-	bio_put(bio);
-
-	bio_io_error(b);
-}
-
-struct faulty_conf {
-	int period[Modes];
-	atomic_t counters[Modes];
-	sector_t faults[MaxFault];
-	int	modes[MaxFault];
-	int nfaults;
-	struct md_rdev *rdev;
-};
-
-static int check_mode(struct faulty_conf *conf, int mode)
-{
-	if (conf->period[mode] == 0 &&
-	    atomic_read(&conf->counters[mode]) <= 0)
-		return 0; /* no failure, no decrement */
-
-
-	if (atomic_dec_and_test(&conf->counters[mode])) {
-		if (conf->period[mode])
-			atomic_set(&conf->counters[mode], conf->period[mode]);
-		return 1;
-	}
-	return 0;
-}
-
-static int check_sector(struct faulty_conf *conf, sector_t start, sector_t end, int dir)
-{
-	/* If we find a ReadFixable sector, we fix it ... */
-	int i;
-	for (i=0; i<conf->nfaults; i++)
-		if (conf->faults[i] >= start &&
-		    conf->faults[i] < end) {
-			/* found it ... */
-			switch (conf->modes[i] * 2 + dir) {
-			case WritePersistent*2+WRITE: return 1;
-			case ReadPersistent*2+READ: return 1;
-			case ReadFixable*2+READ: return 1;
-			case ReadFixable*2+WRITE:
-				conf->modes[i] = NoPersist;
-				return 0;
-			case AllPersist*2+READ:
-			case AllPersist*2+WRITE: return 1;
-			default:
-				return 0;
-			}
-		}
-	return 0;
-}
-
-static void add_sector(struct faulty_conf *conf, sector_t start, int mode)
-{
-	int i;
-	int n = conf->nfaults;
-	for (i=0; i<conf->nfaults; i++)
-		if (conf->faults[i] == start) {
-			switch(mode) {
-			case NoPersist: conf->modes[i] = mode; return;
-			case WritePersistent:
-				if (conf->modes[i] == ReadPersistent ||
-				    conf->modes[i] == ReadFixable)
-					conf->modes[i] = AllPersist;
-				else
-					conf->modes[i] = WritePersistent;
-				return;
-			case ReadPersistent:
-				if (conf->modes[i] == WritePersistent)
-					conf->modes[i] = AllPersist;
-				else
-					conf->modes[i] = ReadPersistent;
-				return;
-			case ReadFixable:
-				if (conf->modes[i] == WritePersistent ||
-				    conf->modes[i] == ReadPersistent)
-					conf->modes[i] = AllPersist;
-				else
-					conf->modes[i] = ReadFixable;
-				return;
-			}
-		} else if (conf->modes[i] == NoPersist)
-			n = i;
-
-	if (n >= MaxFault)
-		return;
-	conf->faults[n] = start;
-	conf->modes[n] = mode;
-	if (conf->nfaults == n)
-		conf->nfaults = n+1;
-}
-
-static bool faulty_make_request(struct mddev *mddev, struct bio *bio)
-{
-	struct faulty_conf *conf = mddev->private;
-	int failit = 0;
-
-	if (bio_data_dir(bio) == WRITE) {
-		/* write request */
-		if (atomic_read(&conf->counters[WriteAll])) {
-			/* special case - don't decrement, don't submit_bio_noacct,
-			 * just fail immediately
-			 */
-			bio_io_error(bio);
-			return true;
-		}
-
-		if (check_sector(conf, bio->bi_iter.bi_sector,
-				 bio_end_sector(bio), WRITE))
-			failit = 1;
-		if (check_mode(conf, WritePersistent)) {
-			add_sector(conf, bio->bi_iter.bi_sector,
-				   WritePersistent);
-			failit = 1;
-		}
-		if (check_mode(conf, WriteTransient))
-			failit = 1;
-	} else {
-		/* read request */
-		if (check_sector(conf, bio->bi_iter.bi_sector,
-				 bio_end_sector(bio), READ))
-			failit = 1;
-		if (check_mode(conf, ReadTransient))
-			failit = 1;
-		if (check_mode(conf, ReadPersistent)) {
-			add_sector(conf, bio->bi_iter.bi_sector,
-				   ReadPersistent);
-			failit = 1;
-		}
-		if (check_mode(conf, ReadFixable)) {
-			add_sector(conf, bio->bi_iter.bi_sector,
-				   ReadFixable);
-			failit = 1;
-		}
-	}
-
-	md_account_bio(mddev, &bio);
-	if (failit) {
-		struct bio *b = bio_alloc_clone(conf->rdev->bdev, bio, GFP_NOIO,
-						&mddev->bio_set);
-
-		b->bi_private = bio;
-		b->bi_end_io = faulty_fail;
-		bio = b;
-	} else
-		bio_set_dev(bio, conf->rdev->bdev);
-
-	submit_bio_noacct(bio);
-	return true;
-}
-
-static void faulty_status(struct seq_file *seq, struct mddev *mddev)
-{
-	struct faulty_conf *conf = mddev->private;
-	int n;
-
-	if ((n=atomic_read(&conf->counters[WriteTransient])) != 0)
-		seq_printf(seq, " WriteTransient=%d(%d)",
-			   n, conf->period[WriteTransient]);
-
-	if ((n=atomic_read(&conf->counters[ReadTransient])) != 0)
-		seq_printf(seq, " ReadTransient=%d(%d)",
-			   n, conf->period[ReadTransient]);
-
-	if ((n=atomic_read(&conf->counters[WritePersistent])) != 0)
-		seq_printf(seq, " WritePersistent=%d(%d)",
-			   n, conf->period[WritePersistent]);
-
-	if ((n=atomic_read(&conf->counters[ReadPersistent])) != 0)
-		seq_printf(seq, " ReadPersistent=%d(%d)",
-			   n, conf->period[ReadPersistent]);
-
-
-	if ((n=atomic_read(&conf->counters[ReadFixable])) != 0)
-		seq_printf(seq, " ReadFixable=%d(%d)",
-			   n, conf->period[ReadFixable]);
-
-	if ((n=atomic_read(&conf->counters[WriteAll])) != 0)
-		seq_printf(seq, " WriteAll");
-
-	seq_printf(seq, " nfaults=%d", conf->nfaults);
-}
-
-
-static int faulty_reshape(struct mddev *mddev)
-{
-	int mode = mddev->new_layout & ModeMask;
-	int count = mddev->new_layout >> ModeShift;
-	struct faulty_conf *conf = mddev->private;
-
-	if (mddev->new_layout < 0)
-		return 0;
-
-	/* new layout */
-	if (mode == ClearFaults)
-		conf->nfaults = 0;
-	else if (mode == ClearErrors) {
-		int i;
-		for (i=0 ; i < Modes ; i++) {
-			conf->period[i] = 0;
-			atomic_set(&conf->counters[i], 0);
-		}
-	} else if (mode < Modes) {
-		conf->period[mode] = count;
-		if (!count) count++;
-		atomic_set(&conf->counters[mode], count);
-	} else
-		return -EINVAL;
-	mddev->new_layout = -1;
-	mddev->layout = -1; /* makes sure further changes come through */
-	return 0;
-}
-
-static sector_t faulty_size(struct mddev *mddev, sector_t sectors, int raid_disks)
-{
-	WARN_ONCE(raid_disks,
-		  "%s does not support generic reshape\n", __func__);
-
-	if (sectors == 0)
-		return mddev->dev_sectors;
-
-	return sectors;
-}
-
-static int faulty_run(struct mddev *mddev)
-{
-	struct md_rdev *rdev;
-	int i;
-	struct faulty_conf *conf;
-
-	if (md_check_no_bitmap(mddev))
-		return -EINVAL;
-
-	conf = kmalloc(sizeof(*conf), GFP_KERNEL);
-	if (!conf)
-		return -ENOMEM;
-
-	for (i=0; i<Modes; i++) {
-		atomic_set(&conf->counters[i], 0);
-		conf->period[i] = 0;
-	}
-	conf->nfaults = 0;
-
-	rdev_for_each(rdev, mddev) {
-		conf->rdev = rdev;
-		disk_stack_limits(mddev->gendisk, rdev->bdev,
-				  rdev->data_offset << 9);
-	}
-
-	md_set_array_sectors(mddev, faulty_size(mddev, 0, 0));
-	mddev->private = conf;
-
-	faulty_reshape(mddev);
-
-	return 0;
-}
-
-static void faulty_free(struct mddev *mddev, void *priv)
-{
-	struct faulty_conf *conf = priv;
-
-	kfree(conf);
-}
-
-static struct md_personality faulty_personality =
-{
-	.name		= "faulty",
-	.level		= LEVEL_FAULTY,
-	.owner		= THIS_MODULE,
-	.make_request	= faulty_make_request,
-	.run		= faulty_run,
-	.free		= faulty_free,
-	.status		= faulty_status,
-	.check_reshape	= faulty_reshape,
-	.size		= faulty_size,
-};
-
-static int __init raid_init(void)
-{
-	return register_md_personality(&faulty_personality);
-}
-
-static void raid_exit(void)
-{
-	unregister_md_personality(&faulty_personality);
-}
-
-module_init(raid_init);
-module_exit(raid_exit);
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("Fault injection personality for MD (deprecated)");
-MODULE_ALIAS("md-personality-10"); /* faulty */
-MODULE_ALIAS("md-faulty");
-MODULE_ALIAS("md-level--5");
diff --git a/include/uapi/linux/raid/md_u.h b/include/uapi/linux/raid/md_u.h
index b44bbc356643..7be89a4906e7 100644
--- a/include/uapi/linux/raid/md_u.h
+++ b/include/uapi/linux/raid/md_u.h
@@ -103,9 +103,6 @@ typedef struct mdu_array_info_s {
 
 } mdu_array_info_t;
 
-/* non-obvious values for 'level' */
-#define	LEVEL_FAULTY		(-5)
-
 /* we need a value for 'no level specified' and 0
  * means 'raid0', so we need something else.  This is
  * for internal use only
-- 
cgit v1.2.3


From 838bebb4c926a573839ff1bfe1b654a6ed0f9779 Mon Sep 17 00:00:00 2001
From: Feng Liu <feliu@nvidia.com>
Date: Tue, 19 Dec 2023 11:32:39 +0200
Subject: virtio: Define feature bit for administration virtqueue

Introduce VIRTIO_F_ADMIN_VQ which is used for administration virtqueue
support.

Signed-off-by: Feng Liu <feliu@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Link: https://lore.kernel.org/r/20231219093247.170936-2-yishaih@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 include/uapi/linux/virtio_config.h | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/virtio_config.h b/include/uapi/linux/virtio_config.h
index 8881aea60f6f..2445f365bce7 100644
--- a/include/uapi/linux/virtio_config.h
+++ b/include/uapi/linux/virtio_config.h
@@ -52,7 +52,7 @@
  * rest are per-device feature bits.
  */
 #define VIRTIO_TRANSPORT_F_START	28
-#define VIRTIO_TRANSPORT_F_END		41
+#define VIRTIO_TRANSPORT_F_END		42
 
 #ifndef VIRTIO_CONFIG_NO_LEGACY
 /* Do we get callbacks when the ring is completely used, even if we've
@@ -114,4 +114,10 @@
  * This feature indicates that the driver can reset a queue individually.
  */
 #define VIRTIO_F_RING_RESET		40
+
+/*
+ * This feature indicates that the device support administration virtqueues.
+ */
+#define VIRTIO_F_ADMIN_VQ		41
+
 #endif /* _UAPI_LINUX_VIRTIO_CONFIG_H */
-- 
cgit v1.2.3


From fd27ef6b44bec26915c5b2b22c13856d9f0ba17a Mon Sep 17 00:00:00 2001
From: Feng Liu <feliu@nvidia.com>
Date: Tue, 19 Dec 2023 11:32:40 +0200
Subject: virtio-pci: Introduce admin virtqueue

Introduce support for the admin virtqueue. By negotiating
VIRTIO_F_ADMIN_VQ feature, driver detects capability and creates one
administration virtqueue. Administration virtqueue implementation in
virtio pci generic layer, enables multiple types of upper layer
drivers such as vfio, net, blk to utilize it.

Signed-off-by: Feng Liu <feliu@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Link: https://lore.kernel.org/r/20231219093247.170936-3-yishaih@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/virtio/virtio.c                | 37 +++++++++++++++--
 drivers/virtio/virtio_pci_common.c     |  3 ++
 drivers/virtio/virtio_pci_common.h     | 15 ++++++-
 drivers/virtio/virtio_pci_modern.c     | 75 +++++++++++++++++++++++++++++++++-
 drivers/virtio/virtio_pci_modern_dev.c | 24 ++++++++++-
 include/linux/virtio_config.h          |  4 ++
 include/linux/virtio_pci_modern.h      |  2 +
 include/uapi/linux/virtio_pci.h        |  5 +++
 8 files changed, 157 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index 3893dc29eb26..f4080692b351 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -302,9 +302,15 @@ static int virtio_dev_probe(struct device *_d)
 	if (err)
 		goto err;
 
+	if (dev->config->create_avq) {
+		err = dev->config->create_avq(dev);
+		if (err)
+			goto err;
+	}
+
 	err = drv->probe(dev);
 	if (err)
-		goto err;
+		goto err_probe;
 
 	/* If probe didn't do it, mark device DRIVER_OK ourselves. */
 	if (!(dev->config->get_status(dev) & VIRTIO_CONFIG_S_DRIVER_OK))
@@ -316,6 +322,10 @@ static int virtio_dev_probe(struct device *_d)
 	virtio_config_enable(dev);
 
 	return 0;
+
+err_probe:
+	if (dev->config->destroy_avq)
+		dev->config->destroy_avq(dev);
 err:
 	virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED);
 	return err;
@@ -331,6 +341,9 @@ static void virtio_dev_remove(struct device *_d)
 
 	drv->remove(dev);
 
+	if (dev->config->destroy_avq)
+		dev->config->destroy_avq(dev);
+
 	/* Driver should have reset device. */
 	WARN_ON_ONCE(dev->config->get_status(dev));
 
@@ -489,13 +502,20 @@ EXPORT_SYMBOL_GPL(unregister_virtio_device);
 int virtio_device_freeze(struct virtio_device *dev)
 {
 	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+	int ret;
 
 	virtio_config_disable(dev);
 
 	dev->failed = dev->config->get_status(dev) & VIRTIO_CONFIG_S_FAILED;
 
-	if (drv && drv->freeze)
-		return drv->freeze(dev);
+	if (drv && drv->freeze) {
+		ret = drv->freeze(dev);
+		if (ret)
+			return ret;
+	}
+
+	if (dev->config->destroy_avq)
+		dev->config->destroy_avq(dev);
 
 	return 0;
 }
@@ -532,10 +552,16 @@ int virtio_device_restore(struct virtio_device *dev)
 	if (ret)
 		goto err;
 
+	if (dev->config->create_avq) {
+		ret = dev->config->create_avq(dev);
+		if (ret)
+			goto err;
+	}
+
 	if (drv->restore) {
 		ret = drv->restore(dev);
 		if (ret)
-			goto err;
+			goto err_restore;
 	}
 
 	/* If restore didn't do it, mark device DRIVER_OK ourselves. */
@@ -546,6 +572,9 @@ int virtio_device_restore(struct virtio_device *dev)
 
 	return 0;
 
+err_restore:
+	if (dev->config->destroy_avq)
+		dev->config->destroy_avq(dev);
 err:
 	virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED);
 	return ret;
diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
index 7a5593997e0e..fafd13d0e4d4 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -236,6 +236,9 @@ void vp_del_vqs(struct virtio_device *vdev)
 	int i;
 
 	list_for_each_entry_safe(vq, n, &vdev->vqs, list) {
+		if (vp_dev->is_avq(vdev, vq->index))
+			continue;
+
 		if (vp_dev->per_vq_vectors) {
 			int v = vp_dev->vqs[vq->index]->msix_vector;
 
diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h
index 4b773bd7c58c..7306128e63e9 100644
--- a/drivers/virtio/virtio_pci_common.h
+++ b/drivers/virtio/virtio_pci_common.h
@@ -41,6 +41,14 @@ struct virtio_pci_vq_info {
 	unsigned int msix_vector;
 };
 
+struct virtio_pci_admin_vq {
+	/* Virtqueue info associated with this admin queue. */
+	struct virtio_pci_vq_info info;
+	/* Name of the admin queue: avq.$vq_index. */
+	char name[10];
+	u16 vq_index;
+};
+
 /* Our device structure */
 struct virtio_pci_device {
 	struct virtio_device vdev;
@@ -58,9 +66,13 @@ struct virtio_pci_device {
 	spinlock_t lock;
 	struct list_head virtqueues;
 
-	/* array of all queues for house-keeping */
+	/* Array of all virtqueues reported in the
+	 * PCI common config num_queues field
+	 */
 	struct virtio_pci_vq_info **vqs;
 
+	struct virtio_pci_admin_vq admin_vq;
+
 	/* MSI-X support */
 	int msix_enabled;
 	int intx_enabled;
@@ -86,6 +98,7 @@ struct virtio_pci_device {
 	void (*del_vq)(struct virtio_pci_vq_info *info);
 
 	u16 (*config_vector)(struct virtio_pci_device *vp_dev, u16 vector);
+	bool (*is_avq)(struct virtio_device *vdev, unsigned int index);
 };
 
 /* Constants for MSI-X */
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index ee6a386d250b..ce915018b5b0 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -19,6 +19,8 @@
 #define VIRTIO_RING_NO_LEGACY
 #include "virtio_pci_common.h"
 
+#define VIRTIO_AVQ_SGS_MAX	4
+
 static u64 vp_get_features(struct virtio_device *vdev)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
@@ -26,6 +28,16 @@ static u64 vp_get_features(struct virtio_device *vdev)
 	return vp_modern_get_features(&vp_dev->mdev);
 }
 
+static bool vp_is_avq(struct virtio_device *vdev, unsigned int index)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+	if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ))
+		return false;
+
+	return index == vp_dev->admin_vq.vq_index;
+}
+
 static void vp_transport_features(struct virtio_device *vdev, u64 features)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
@@ -37,6 +49,9 @@ static void vp_transport_features(struct virtio_device *vdev, u64 features)
 
 	if (features & BIT_ULL(VIRTIO_F_RING_RESET))
 		__virtio_set_bit(vdev, VIRTIO_F_RING_RESET);
+
+	if (features & BIT_ULL(VIRTIO_F_ADMIN_VQ))
+		__virtio_set_bit(vdev, VIRTIO_F_ADMIN_VQ);
 }
 
 static int __vp_check_common_size_one_feature(struct virtio_device *vdev, u32 fbit,
@@ -69,6 +84,9 @@ static int vp_check_common_size(struct virtio_device *vdev)
 	if (vp_check_common_size_one_feature(vdev, VIRTIO_F_RING_RESET, queue_reset))
 		return -EINVAL;
 
+	if (vp_check_common_size_one_feature(vdev, VIRTIO_F_ADMIN_VQ, admin_queue_num))
+		return -EINVAL;
+
 	return 0;
 }
 
@@ -345,6 +363,7 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
 	bool (*notify)(struct virtqueue *vq);
 	struct virtqueue *vq;
+	bool is_avq;
 	u16 num;
 	int err;
 
@@ -353,11 +372,13 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	else
 		notify = vp_notify;
 
-	if (index >= vp_modern_get_num_queues(mdev))
+	is_avq = vp_is_avq(&vp_dev->vdev, index);
+	if (index >= vp_modern_get_num_queues(mdev) && !is_avq)
 		return ERR_PTR(-EINVAL);
 
+	num = is_avq ?
+		VIRTIO_AVQ_SGS_MAX : vp_modern_get_queue_size(mdev, index);
 	/* Check if queue is either not available or already active. */
-	num = vp_modern_get_queue_size(mdev, index);
 	if (!num || vp_modern_get_queue_enable(mdev, index))
 		return ERR_PTR(-ENOENT);
 
@@ -383,6 +404,9 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 		goto err;
 	}
 
+	if (is_avq)
+		vp_dev->admin_vq.info.vq = vq;
+
 	return vq;
 
 err:
@@ -418,6 +442,9 @@ static void del_vq(struct virtio_pci_vq_info *info)
 	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
 	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
 
+	if (vp_is_avq(&vp_dev->vdev, vq->index))
+		vp_dev->admin_vq.info.vq = NULL;
+
 	if (vp_dev->msix_enabled)
 		vp_modern_queue_vector(mdev, vq->index,
 				       VIRTIO_MSI_NO_VECTOR);
@@ -527,6 +554,45 @@ static bool vp_get_shm_region(struct virtio_device *vdev,
 	return true;
 }
 
+static int vp_modern_create_avq(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_pci_admin_vq *avq;
+	struct virtqueue *vq;
+	u16 admin_q_num;
+
+	if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ))
+		return 0;
+
+	admin_q_num = vp_modern_avq_num(&vp_dev->mdev);
+	if (!admin_q_num)
+		return -EINVAL;
+
+	avq = &vp_dev->admin_vq;
+	avq->vq_index = vp_modern_avq_index(&vp_dev->mdev);
+	sprintf(avq->name, "avq.%u", avq->vq_index);
+	vq = vp_dev->setup_vq(vp_dev, &vp_dev->admin_vq.info, avq->vq_index, NULL,
+			      avq->name, NULL, VIRTIO_MSI_NO_VECTOR);
+	if (IS_ERR(vq)) {
+		dev_err(&vdev->dev, "failed to setup admin virtqueue, err=%ld",
+			PTR_ERR(vq));
+		return PTR_ERR(vq);
+	}
+
+	vp_modern_set_queue_enable(&vp_dev->mdev, avq->info.vq->index, true);
+	return 0;
+}
+
+static void vp_modern_destroy_avq(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+	if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ))
+		return;
+
+	vp_dev->del_vq(&vp_dev->admin_vq.info);
+}
+
 static const struct virtio_config_ops virtio_pci_config_nodev_ops = {
 	.get		= NULL,
 	.set		= NULL,
@@ -545,6 +611,8 @@ static const struct virtio_config_ops virtio_pci_config_nodev_ops = {
 	.get_shm_region  = vp_get_shm_region,
 	.disable_vq_and_reset = vp_modern_disable_vq_and_reset,
 	.enable_vq_after_reset = vp_modern_enable_vq_after_reset,
+	.create_avq = vp_modern_create_avq,
+	.destroy_avq = vp_modern_destroy_avq,
 };
 
 static const struct virtio_config_ops virtio_pci_config_ops = {
@@ -565,6 +633,8 @@ static const struct virtio_config_ops virtio_pci_config_ops = {
 	.get_shm_region  = vp_get_shm_region,
 	.disable_vq_and_reset = vp_modern_disable_vq_and_reset,
 	.enable_vq_after_reset = vp_modern_enable_vq_after_reset,
+	.create_avq = vp_modern_create_avq,
+	.destroy_avq = vp_modern_destroy_avq,
 };
 
 /* the PCI probing function */
@@ -588,6 +658,7 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
 	vp_dev->config_vector = vp_config_vector;
 	vp_dev->setup_vq = setup_vq;
 	vp_dev->del_vq = del_vq;
+	vp_dev->is_avq = vp_is_avq;
 	vp_dev->isr = mdev->isr;
 	vp_dev->vdev.id = mdev->id;
 
diff --git a/drivers/virtio/virtio_pci_modern_dev.c b/drivers/virtio/virtio_pci_modern_dev.c
index 7de8b1ebabac..0d3dbfaf4b23 100644
--- a/drivers/virtio/virtio_pci_modern_dev.c
+++ b/drivers/virtio/virtio_pci_modern_dev.c
@@ -207,6 +207,10 @@ static inline void check_offsets(void)
 		     offsetof(struct virtio_pci_modern_common_cfg, queue_notify_data));
 	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_RESET !=
 		     offsetof(struct virtio_pci_modern_common_cfg, queue_reset));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_ADM_Q_IDX !=
+		     offsetof(struct virtio_pci_modern_common_cfg, admin_queue_index));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_ADM_Q_NUM !=
+		     offsetof(struct virtio_pci_modern_common_cfg, admin_queue_num));
 }
 
 /*
@@ -296,7 +300,7 @@ int vp_modern_probe(struct virtio_pci_modern_device *mdev)
 	mdev->common = vp_modern_map_capability(mdev, common,
 			      sizeof(struct virtio_pci_common_cfg), 4, 0,
 			      offsetofend(struct virtio_pci_modern_common_cfg,
-					  queue_reset),
+					  admin_queue_num),
 			      &mdev->common_len, NULL);
 	if (!mdev->common)
 		goto err_map_common;
@@ -719,6 +723,24 @@ void __iomem *vp_modern_map_vq_notify(struct virtio_pci_modern_device *mdev,
 }
 EXPORT_SYMBOL_GPL(vp_modern_map_vq_notify);
 
+u16 vp_modern_avq_num(struct virtio_pci_modern_device *mdev)
+{
+	struct virtio_pci_modern_common_cfg __iomem *cfg;
+
+	cfg = (struct virtio_pci_modern_common_cfg __iomem *)mdev->common;
+	return vp_ioread16(&cfg->admin_queue_num);
+}
+EXPORT_SYMBOL_GPL(vp_modern_avq_num);
+
+u16 vp_modern_avq_index(struct virtio_pci_modern_device *mdev)
+{
+	struct virtio_pci_modern_common_cfg __iomem *cfg;
+
+	cfg = (struct virtio_pci_modern_common_cfg __iomem *)mdev->common;
+	return vp_ioread16(&cfg->admin_queue_index);
+}
+EXPORT_SYMBOL_GPL(vp_modern_avq_index);
+
 MODULE_VERSION("0.1");
 MODULE_DESCRIPTION("Modern Virtio PCI Device");
 MODULE_AUTHOR("Jason Wang <jasowang@redhat.com>");
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 2b3438de2c4d..da9b271b54db 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -93,6 +93,8 @@ typedef void vq_callback_t(struct virtqueue *);
  *	Returns 0 on success or error status
  *	If disable_vq_and_reset is set, then enable_vq_after_reset must also be
  *	set.
+ * @create_avq: create admin virtqueue resource.
+ * @destroy_avq: destroy admin virtqueue resource.
  */
 struct virtio_config_ops {
 	void (*get)(struct virtio_device *vdev, unsigned offset,
@@ -120,6 +122,8 @@ struct virtio_config_ops {
 			       struct virtio_shm_region *region, u8 id);
 	int (*disable_vq_and_reset)(struct virtqueue *vq);
 	int (*enable_vq_after_reset)(struct virtqueue *vq);
+	int (*create_avq)(struct virtio_device *vdev);
+	void (*destroy_avq)(struct virtio_device *vdev);
 };
 
 /* If driver didn't advertise the feature, it will never appear. */
diff --git a/include/linux/virtio_pci_modern.h b/include/linux/virtio_pci_modern.h
index a09e13a577a9..c0b1b1ca1163 100644
--- a/include/linux/virtio_pci_modern.h
+++ b/include/linux/virtio_pci_modern.h
@@ -125,4 +125,6 @@ int vp_modern_probe(struct virtio_pci_modern_device *mdev);
 void vp_modern_remove(struct virtio_pci_modern_device *mdev);
 int vp_modern_get_queue_reset(struct virtio_pci_modern_device *mdev, u16 index);
 void vp_modern_set_queue_reset(struct virtio_pci_modern_device *mdev, u16 index);
+u16 vp_modern_avq_num(struct virtio_pci_modern_device *mdev);
+u16 vp_modern_avq_index(struct virtio_pci_modern_device *mdev);
 #endif
diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h
index 44f4dd2add18..240ddeef7eae 100644
--- a/include/uapi/linux/virtio_pci.h
+++ b/include/uapi/linux/virtio_pci.h
@@ -175,6 +175,9 @@ struct virtio_pci_modern_common_cfg {
 
 	__le16 queue_notify_data;	/* read-write */
 	__le16 queue_reset;		/* read-write */
+
+	__le16 admin_queue_index;	/* read-only */
+	__le16 admin_queue_num;		/* read-only */
 };
 
 /* Fields in VIRTIO_PCI_CAP_PCI_CFG: */
@@ -215,6 +218,8 @@ struct virtio_pci_cfg_cap {
 #define VIRTIO_PCI_COMMON_Q_USEDHI	52
 #define VIRTIO_PCI_COMMON_Q_NDATA	56
 #define VIRTIO_PCI_COMMON_Q_RESET	58
+#define VIRTIO_PCI_COMMON_ADM_Q_IDX	60
+#define VIRTIO_PCI_COMMON_ADM_Q_NUM	62
 
 #endif /* VIRTIO_PCI_NO_MODERN */
 
-- 
cgit v1.2.3


From 92792ac752aa80d5ee71bc291d90edd06cd76bd1 Mon Sep 17 00:00:00 2001
From: Feng Liu <feliu@nvidia.com>
Date: Tue, 19 Dec 2023 11:32:41 +0200
Subject: virtio-pci: Introduce admin command sending function

Add support for sending admin command through admin virtqueue interface.
Abort any inflight admin commands once device reset completes. Activate
admin queue when device becomes ready; deactivate on device reset.

To comply to the below specification statement [1], the admin virtqueue
is activated for upper layer users only after setting DRIVER_OK status.

[1] The driver MUST NOT send any buffer available notifications to the
device before setting DRIVER_OK.

Signed-off-by: Feng Liu <feliu@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Link: https://lore.kernel.org/r/20231219093247.170936-4-yishaih@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/virtio/virtio_pci_common.h |   6 ++
 drivers/virtio/virtio_pci_modern.c | 143 ++++++++++++++++++++++++++++++++++++-
 include/linux/virtio.h             |   8 +++
 include/uapi/linux/virtio_pci.h    |  22 ++++++
 4 files changed, 177 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h
index 7306128e63e9..282d087a9266 100644
--- a/drivers/virtio/virtio_pci_common.h
+++ b/drivers/virtio/virtio_pci_common.h
@@ -29,6 +29,7 @@
 #include <linux/virtio_pci_modern.h>
 #include <linux/highmem.h>
 #include <linux/spinlock.h>
+#include <linux/mutex.h>
 
 struct virtio_pci_vq_info {
 	/* the actual virtqueue */
@@ -44,6 +45,8 @@ struct virtio_pci_vq_info {
 struct virtio_pci_admin_vq {
 	/* Virtqueue info associated with this admin queue. */
 	struct virtio_pci_vq_info info;
+	/* serializing admin commands execution and virtqueue deletion */
+	struct mutex cmd_lock;
 	/* Name of the admin queue: avq.$vq_index. */
 	char name[10];
 	u16 vq_index;
@@ -152,4 +155,7 @@ static inline void virtio_pci_legacy_remove(struct virtio_pci_device *vp_dev)
 int virtio_pci_modern_probe(struct virtio_pci_device *);
 void virtio_pci_modern_remove(struct virtio_pci_device *);
 
+int vp_modern_admin_cmd_exec(struct virtio_device *vdev,
+			     struct virtio_admin_cmd *cmd);
+
 #endif
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index ce915018b5b0..9bd66300a80a 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -38,6 +38,132 @@ static bool vp_is_avq(struct virtio_device *vdev, unsigned int index)
 	return index == vp_dev->admin_vq.vq_index;
 }
 
+static int virtqueue_exec_admin_cmd(struct virtio_pci_admin_vq *admin_vq,
+				    struct scatterlist **sgs,
+				    unsigned int out_num,
+				    unsigned int in_num,
+				    void *data)
+{
+	struct virtqueue *vq;
+	int ret, len;
+
+	vq = admin_vq->info.vq;
+	if (!vq)
+		return -EIO;
+
+	ret = virtqueue_add_sgs(vq, sgs, out_num, in_num, data, GFP_KERNEL);
+	if (ret < 0)
+		return -EIO;
+
+	if (unlikely(!virtqueue_kick(vq)))
+		return -EIO;
+
+	while (!virtqueue_get_buf(vq, &len) &&
+	       !virtqueue_is_broken(vq))
+		cpu_relax();
+
+	if (virtqueue_is_broken(vq))
+		return -EIO;
+
+	return 0;
+}
+
+int vp_modern_admin_cmd_exec(struct virtio_device *vdev,
+			     struct virtio_admin_cmd *cmd)
+{
+	struct scatterlist *sgs[VIRTIO_AVQ_SGS_MAX], hdr, stat;
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_admin_cmd_status *va_status;
+	unsigned int out_num = 0, in_num = 0;
+	struct virtio_admin_cmd_hdr *va_hdr;
+	u16 status;
+	int ret;
+
+	if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ))
+		return -EOPNOTSUPP;
+
+	va_status = kzalloc(sizeof(*va_status), GFP_KERNEL);
+	if (!va_status)
+		return -ENOMEM;
+
+	va_hdr = kzalloc(sizeof(*va_hdr), GFP_KERNEL);
+	if (!va_hdr) {
+		ret = -ENOMEM;
+		goto err_alloc;
+	}
+
+	va_hdr->opcode = cmd->opcode;
+	va_hdr->group_type = cmd->group_type;
+	va_hdr->group_member_id = cmd->group_member_id;
+
+	/* Add header */
+	sg_init_one(&hdr, va_hdr, sizeof(*va_hdr));
+	sgs[out_num] = &hdr;
+	out_num++;
+
+	if (cmd->data_sg) {
+		sgs[out_num] = cmd->data_sg;
+		out_num++;
+	}
+
+	/* Add return status */
+	sg_init_one(&stat, va_status, sizeof(*va_status));
+	sgs[out_num + in_num] = &stat;
+	in_num++;
+
+	if (cmd->result_sg) {
+		sgs[out_num + in_num] = cmd->result_sg;
+		in_num++;
+	}
+
+	mutex_lock(&vp_dev->admin_vq.cmd_lock);
+	ret = virtqueue_exec_admin_cmd(&vp_dev->admin_vq, sgs,
+				       out_num, in_num, sgs);
+	mutex_unlock(&vp_dev->admin_vq.cmd_lock);
+
+	if (ret) {
+		dev_err(&vdev->dev,
+			"Failed to execute command on admin vq: %d\n.", ret);
+		goto err_cmd_exec;
+	}
+
+	status = le16_to_cpu(va_status->status);
+	if (status != VIRTIO_ADMIN_STATUS_OK) {
+		dev_err(&vdev->dev,
+			"admin command error: status(%#x) qualifier(%#x)\n",
+			status, le16_to_cpu(va_status->status_qualifier));
+		ret = -status;
+	}
+
+err_cmd_exec:
+	kfree(va_hdr);
+err_alloc:
+	kfree(va_status);
+	return ret;
+}
+
+static void vp_modern_avq_activate(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_pci_admin_vq *admin_vq = &vp_dev->admin_vq;
+
+	if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ))
+		return;
+
+	__virtqueue_unbreak(admin_vq->info.vq);
+}
+
+static void vp_modern_avq_deactivate(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_pci_admin_vq *admin_vq = &vp_dev->admin_vq;
+
+	if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ))
+		return;
+
+	__virtqueue_break(admin_vq->info.vq);
+}
+
 static void vp_transport_features(struct virtio_device *vdev, u64 features)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
@@ -213,6 +339,8 @@ static void vp_set_status(struct virtio_device *vdev, u8 status)
 	/* We should never be setting status to 0. */
 	BUG_ON(status == 0);
 	vp_modern_set_status(&vp_dev->mdev, status);
+	if (status & VIRTIO_CONFIG_S_DRIVER_OK)
+		vp_modern_avq_activate(vdev);
 }
 
 static void vp_reset(struct virtio_device *vdev)
@@ -229,6 +357,9 @@ static void vp_reset(struct virtio_device *vdev)
 	 */
 	while (vp_modern_get_status(mdev))
 		msleep(1);
+
+	vp_modern_avq_deactivate(vdev);
+
 	/* Flush pending VQ/configuration callbacks. */
 	vp_synchronize_vectors(vdev);
 }
@@ -404,8 +535,11 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 		goto err;
 	}
 
-	if (is_avq)
+	if (is_avq) {
+		mutex_lock(&vp_dev->admin_vq.cmd_lock);
 		vp_dev->admin_vq.info.vq = vq;
+		mutex_unlock(&vp_dev->admin_vq.cmd_lock);
+	}
 
 	return vq;
 
@@ -442,8 +576,11 @@ static void del_vq(struct virtio_pci_vq_info *info)
 	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
 	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
 
-	if (vp_is_avq(&vp_dev->vdev, vq->index))
+	if (vp_is_avq(&vp_dev->vdev, vq->index)) {
+		mutex_lock(&vp_dev->admin_vq.cmd_lock);
 		vp_dev->admin_vq.info.vq = NULL;
+		mutex_unlock(&vp_dev->admin_vq.cmd_lock);
+	}
 
 	if (vp_dev->msix_enabled)
 		vp_modern_queue_vector(mdev, vq->index,
@@ -662,6 +799,7 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
 	vp_dev->isr = mdev->isr;
 	vp_dev->vdev.id = mdev->id;
 
+	mutex_init(&vp_dev->admin_vq.cmd_lock);
 	return 0;
 }
 
@@ -669,5 +807,6 @@ void virtio_pci_modern_remove(struct virtio_pci_device *vp_dev)
 {
 	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
 
+	mutex_destroy(&vp_dev->admin_vq.cmd_lock);
 	vp_modern_remove(mdev);
 }
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 4cc614a38376..b0201747a263 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -103,6 +103,14 @@ int virtqueue_resize(struct virtqueue *vq, u32 num,
 int virtqueue_reset(struct virtqueue *vq,
 		    void (*recycle)(struct virtqueue *vq, void *buf));
 
+struct virtio_admin_cmd {
+	__le16 opcode;
+	__le16 group_type;
+	__le64 group_member_id;
+	struct scatterlist *data_sg;
+	struct scatterlist *result_sg;
+};
+
 /**
  * struct virtio_device - representation of a device using virtio
  * @index: unique position on the virtio bus
diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h
index 240ddeef7eae..187fd9e34a30 100644
--- a/include/uapi/linux/virtio_pci.h
+++ b/include/uapi/linux/virtio_pci.h
@@ -223,4 +223,26 @@ struct virtio_pci_cfg_cap {
 
 #endif /* VIRTIO_PCI_NO_MODERN */
 
+/* Admin command status. */
+#define VIRTIO_ADMIN_STATUS_OK		0
+
+struct __packed virtio_admin_cmd_hdr {
+	__le16 opcode;
+	/*
+	 * 1 - SR-IOV
+	 * 2-65535 - reserved
+	 */
+	__le16 group_type;
+	/* Unused, reserved for future extensions. */
+	__u8 reserved1[12];
+	__le64 group_member_id;
+};
+
+struct __packed virtio_admin_cmd_status {
+	__le16 status;
+	__le16 status_qualifier;
+	/* Unused, reserved for future extensions. */
+	__u8 reserved2[4];
+};
+
 #endif
-- 
cgit v1.2.3


From 388431b9f59bbfde2b5f2fe032b0836158b09ad0 Mon Sep 17 00:00:00 2001
From: Feng Liu <feliu@nvidia.com>
Date: Tue, 19 Dec 2023 11:32:42 +0200
Subject: virtio-pci: Introduce admin commands

Introduces admin commands, as follow:

The "list query" command can be used by the driver to query the
set of admin commands supported by the virtio device.
The "list use" command is used to inform the virtio device which
admin commands the driver will use.
The "legacy common cfg rd/wr" commands are used to read from/write
into the legacy common configuration structure.
The "legacy dev cfg rd/wr" commands are used to read from/write
into the legacy device configuration structure.
The "notify info" command is used to query the notification region
information.

Signed-off-by: Feng Liu <feliu@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Link: https://lore.kernel.org/r/20231219093247.170936-5-yishaih@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 include/uapi/linux/virtio_pci.h | 41 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 41 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h
index 187fd9e34a30..ef3810dee7ef 100644
--- a/include/uapi/linux/virtio_pci.h
+++ b/include/uapi/linux/virtio_pci.h
@@ -226,6 +226,20 @@ struct virtio_pci_cfg_cap {
 /* Admin command status. */
 #define VIRTIO_ADMIN_STATUS_OK		0
 
+/* Admin command opcode. */
+#define VIRTIO_ADMIN_CMD_LIST_QUERY	0x0
+#define VIRTIO_ADMIN_CMD_LIST_USE	0x1
+
+/* Admin command group type. */
+#define VIRTIO_ADMIN_GROUP_TYPE_SRIOV	0x1
+
+/* Transitional device admin command. */
+#define VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_WRITE	0x2
+#define VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_READ		0x3
+#define VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_WRITE		0x4
+#define VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_READ		0x5
+#define VIRTIO_ADMIN_CMD_LEGACY_NOTIFY_INFO		0x6
+
 struct __packed virtio_admin_cmd_hdr {
 	__le16 opcode;
 	/*
@@ -245,4 +259,31 @@ struct __packed virtio_admin_cmd_status {
 	__u8 reserved2[4];
 };
 
+struct __packed virtio_admin_cmd_legacy_wr_data {
+	__u8 offset; /* Starting offset of the register(s) to write. */
+	__u8 reserved[7];
+	__u8 registers[];
+};
+
+struct __packed virtio_admin_cmd_legacy_rd_data {
+	__u8 offset; /* Starting offset of the register(s) to read. */
+};
+
+#define VIRTIO_ADMIN_CMD_NOTIFY_INFO_FLAGS_END 0
+#define VIRTIO_ADMIN_CMD_NOTIFY_INFO_FLAGS_OWNER_DEV 0x1
+#define VIRTIO_ADMIN_CMD_NOTIFY_INFO_FLAGS_OWNER_MEM 0x2
+
+#define VIRTIO_ADMIN_CMD_MAX_NOTIFY_INFO 4
+
+struct __packed virtio_admin_cmd_notify_info_data {
+	__u8 flags; /* 0 = end of list, 1 = owner device, 2 = member device */
+	__u8 bar; /* BAR of the member or the owner device */
+	__u8 padding[6];
+	__le64 offset; /* Offset within bar. */
+};
+
+struct virtio_admin_cmd_notify_info_result {
+	struct virtio_admin_cmd_notify_info_data entries[VIRTIO_ADMIN_CMD_MAX_NOTIFY_INFO];
+};
+
 #endif
-- 
cgit v1.2.3


From c3fc3e098bd64c560dde49a6e72b21b055150abe Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Tue, 19 Dec 2023 11:32:44 +0200
Subject: virtio-pci: Introduce APIs to execute legacy IO admin commands

Introduce APIs to execute legacy IO admin commands.

It includes: io_legacy_read/write for both common and the device
configuration, io_legacy_notify_info.

In addition, exposing an API to check whether the legacy IO commands are
supported. (i.e. virtio_pci_admin_has_legacy_io()).

Those APIs will be used by the next patches from this series.

Note:
Unlike modern drivers which support hardware virtio devices, legacy
drivers assume software-based devices: e.g. they don't use proper memory
barriers on ARM, use big endian on PPC, etc. X86 drivers are mostly ok
though, more or less by chance. For now, only support legacy IO on X86.

Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Link: https://lore.kernel.org/r/20231219093247.170936-7-yishaih@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/virtio/Makefile                     |   1 +
 drivers/virtio/virtio_pci_admin_legacy_io.c | 244 ++++++++++++++++++++++++++++
 drivers/virtio/virtio_pci_common.c          |  11 ++
 drivers/virtio/virtio_pci_common.h          |   2 +
 include/linux/virtio_pci_admin.h            |  23 +++
 5 files changed, 281 insertions(+)
 create mode 100644 drivers/virtio/virtio_pci_admin_legacy_io.c
 create mode 100644 include/linux/virtio_pci_admin.h

(limited to 'include')

diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile
index 8e98d24917cc..73ace62af440 100644
--- a/drivers/virtio/Makefile
+++ b/drivers/virtio/Makefile
@@ -7,6 +7,7 @@ obj-$(CONFIG_VIRTIO_MMIO) += virtio_mmio.o
 obj-$(CONFIG_VIRTIO_PCI) += virtio_pci.o
 virtio_pci-y := virtio_pci_modern.o virtio_pci_common.o
 virtio_pci-$(CONFIG_VIRTIO_PCI_LEGACY) += virtio_pci_legacy.o
+virtio_pci-$(CONFIG_VIRTIO_PCI_ADMIN_LEGACY) += virtio_pci_admin_legacy_io.o
 obj-$(CONFIG_VIRTIO_BALLOON) += virtio_balloon.o
 obj-$(CONFIG_VIRTIO_INPUT) += virtio_input.o
 obj-$(CONFIG_VIRTIO_VDPA) += virtio_vdpa.o
diff --git a/drivers/virtio/virtio_pci_admin_legacy_io.c b/drivers/virtio/virtio_pci_admin_legacy_io.c
new file mode 100644
index 000000000000..819cfbbc67c3
--- /dev/null
+++ b/drivers/virtio/virtio_pci_admin_legacy_io.c
@@ -0,0 +1,244 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved
+ */
+
+#include <linux/virtio_pci_admin.h>
+#include "virtio_pci_common.h"
+
+/*
+ * virtio_pci_admin_has_legacy_io - Checks whether the legacy IO
+ * commands are supported
+ * @dev: VF pci_dev
+ *
+ * Returns true on success.
+ */
+bool virtio_pci_admin_has_legacy_io(struct pci_dev *pdev)
+{
+	struct virtio_device *virtio_dev = virtio_pci_vf_get_pf_dev(pdev);
+	struct virtio_pci_device *vp_dev;
+
+	if (!virtio_dev)
+		return false;
+
+	if (!virtio_has_feature(virtio_dev, VIRTIO_F_ADMIN_VQ))
+		return false;
+
+	vp_dev = to_vp_device(virtio_dev);
+
+	if ((vp_dev->admin_vq.supported_cmds & VIRTIO_LEGACY_ADMIN_CMD_BITMAP) ==
+		VIRTIO_LEGACY_ADMIN_CMD_BITMAP)
+		return true;
+	return false;
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_has_legacy_io);
+
+static int virtio_pci_admin_legacy_io_write(struct pci_dev *pdev, u16 opcode,
+					    u8 offset, u8 size, u8 *buf)
+{
+	struct virtio_device *virtio_dev = virtio_pci_vf_get_pf_dev(pdev);
+	struct virtio_admin_cmd_legacy_wr_data *data;
+	struct virtio_admin_cmd cmd = {};
+	struct scatterlist data_sg;
+	int vf_id;
+	int ret;
+
+	if (!virtio_dev)
+		return -ENODEV;
+
+	vf_id = pci_iov_vf_id(pdev);
+	if (vf_id < 0)
+		return vf_id;
+
+	data = kzalloc(sizeof(*data) + size, GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->offset = offset;
+	memcpy(data->registers, buf, size);
+	sg_init_one(&data_sg, data, sizeof(*data) + size);
+	cmd.opcode = cpu_to_le16(opcode);
+	cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV);
+	cmd.group_member_id = cpu_to_le64(vf_id + 1);
+	cmd.data_sg = &data_sg;
+	ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
+
+	kfree(data);
+	return ret;
+}
+
+/*
+ * virtio_pci_admin_legacy_io_write_common - Write legacy common configuration
+ * of a member device
+ * @dev: VF pci_dev
+ * @offset: starting byte offset within the common configuration area to write to
+ * @size: size of the data to write
+ * @buf: buffer which holds the data
+ *
+ * Note: caller must serialize access for the given device.
+ * Returns 0 on success, or negative on failure.
+ */
+int virtio_pci_admin_legacy_common_io_write(struct pci_dev *pdev, u8 offset,
+					    u8 size, u8 *buf)
+{
+	return virtio_pci_admin_legacy_io_write(pdev,
+					VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_WRITE,
+					offset, size, buf);
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_legacy_common_io_write);
+
+/*
+ * virtio_pci_admin_legacy_io_write_device - Write legacy device configuration
+ * of a member device
+ * @dev: VF pci_dev
+ * @offset: starting byte offset within the device configuration area to write to
+ * @size: size of the data to write
+ * @buf: buffer which holds the data
+ *
+ * Note: caller must serialize access for the given device.
+ * Returns 0 on success, or negative on failure.
+ */
+int virtio_pci_admin_legacy_device_io_write(struct pci_dev *pdev, u8 offset,
+					    u8 size, u8 *buf)
+{
+	return virtio_pci_admin_legacy_io_write(pdev,
+					VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_WRITE,
+					offset, size, buf);
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_legacy_device_io_write);
+
+static int virtio_pci_admin_legacy_io_read(struct pci_dev *pdev, u16 opcode,
+					   u8 offset, u8 size, u8 *buf)
+{
+	struct virtio_device *virtio_dev = virtio_pci_vf_get_pf_dev(pdev);
+	struct virtio_admin_cmd_legacy_rd_data *data;
+	struct scatterlist data_sg, result_sg;
+	struct virtio_admin_cmd cmd = {};
+	int vf_id;
+	int ret;
+
+	if (!virtio_dev)
+		return -ENODEV;
+
+	vf_id = pci_iov_vf_id(pdev);
+	if (vf_id < 0)
+		return vf_id;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->offset = offset;
+	sg_init_one(&data_sg, data, sizeof(*data));
+	sg_init_one(&result_sg, buf, size);
+	cmd.opcode = cpu_to_le16(opcode);
+	cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV);
+	cmd.group_member_id = cpu_to_le64(vf_id + 1);
+	cmd.data_sg = &data_sg;
+	cmd.result_sg = &result_sg;
+	ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
+
+	kfree(data);
+	return ret;
+}
+
+/*
+ * virtio_pci_admin_legacy_device_io_read - Read legacy device configuration of
+ * a member device
+ * @dev: VF pci_dev
+ * @offset: starting byte offset within the device configuration area to read from
+ * @size: size of the data to be read
+ * @buf: buffer to hold the returned data
+ *
+ * Note: caller must serialize access for the given device.
+ * Returns 0 on success, or negative on failure.
+ */
+int virtio_pci_admin_legacy_device_io_read(struct pci_dev *pdev, u8 offset,
+					   u8 size, u8 *buf)
+{
+	return virtio_pci_admin_legacy_io_read(pdev,
+					VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_READ,
+					offset, size, buf);
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_legacy_device_io_read);
+
+/*
+ * virtio_pci_admin_legacy_common_io_read - Read legacy common configuration of
+ * a member device
+ * @dev: VF pci_dev
+ * @offset: starting byte offset within the common configuration area to read from
+ * @size: size of the data to be read
+ * @buf: buffer to hold the returned data
+ *
+ * Note: caller must serialize access for the given device.
+ * Returns 0 on success, or negative on failure.
+ */
+int virtio_pci_admin_legacy_common_io_read(struct pci_dev *pdev, u8 offset,
+					   u8 size, u8 *buf)
+{
+	return virtio_pci_admin_legacy_io_read(pdev,
+					VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_READ,
+					offset, size, buf);
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_legacy_common_io_read);
+
+/*
+ * virtio_pci_admin_legacy_io_notify_info - Read the queue notification
+ * information for legacy interface
+ * @dev: VF pci_dev
+ * @req_bar_flags: requested bar flags
+ * @bar: on output the BAR number of the owner or member device
+ * @bar_offset: on output the offset within bar
+ *
+ * Returns 0 on success, or negative on failure.
+ */
+int virtio_pci_admin_legacy_io_notify_info(struct pci_dev *pdev,
+					   u8 req_bar_flags, u8 *bar,
+					   u64 *bar_offset)
+{
+	struct virtio_device *virtio_dev = virtio_pci_vf_get_pf_dev(pdev);
+	struct virtio_admin_cmd_notify_info_result *result;
+	struct virtio_admin_cmd cmd = {};
+	struct scatterlist result_sg;
+	int vf_id;
+	int ret;
+
+	if (!virtio_dev)
+		return -ENODEV;
+
+	vf_id = pci_iov_vf_id(pdev);
+	if (vf_id < 0)
+		return vf_id;
+
+	result = kzalloc(sizeof(*result), GFP_KERNEL);
+	if (!result)
+		return -ENOMEM;
+
+	sg_init_one(&result_sg, result, sizeof(*result));
+	cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_LEGACY_NOTIFY_INFO);
+	cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV);
+	cmd.group_member_id = cpu_to_le64(vf_id + 1);
+	cmd.result_sg = &result_sg;
+	ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
+	if (!ret) {
+		struct virtio_admin_cmd_notify_info_data *entry;
+		int i;
+
+		ret = -ENOENT;
+		for (i = 0; i < VIRTIO_ADMIN_CMD_MAX_NOTIFY_INFO; i++) {
+			entry = &result->entries[i];
+			if (entry->flags == VIRTIO_ADMIN_CMD_NOTIFY_INFO_FLAGS_END)
+				break;
+			if (entry->flags != req_bar_flags)
+				continue;
+			*bar = entry->bar;
+			*bar_offset = le64_to_cpu(entry->offset);
+			ret = 0;
+			break;
+		}
+	}
+
+	kfree(result);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(virtio_pci_admin_legacy_io_notify_info);
diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
index fafd13d0e4d4..9f93330fc2cc 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -645,6 +645,17 @@ static struct pci_driver virtio_pci_driver = {
 	.sriov_configure = virtio_pci_sriov_configure,
 };
 
+struct virtio_device *virtio_pci_vf_get_pf_dev(struct pci_dev *pdev)
+{
+	struct virtio_pci_device *pf_vp_dev;
+
+	pf_vp_dev = pci_iov_get_pf_drvdata(pdev, &virtio_pci_driver);
+	if (IS_ERR(pf_vp_dev))
+		return NULL;
+
+	return &pf_vp_dev->vdev;
+}
+
 module_pci_driver(virtio_pci_driver);
 
 MODULE_AUTHOR("Anthony Liguori <aliguori@us.ibm.com>");
diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h
index a39bffd5fd46..7fef52bee455 100644
--- a/drivers/virtio/virtio_pci_common.h
+++ b/drivers/virtio/virtio_pci_common.h
@@ -156,6 +156,8 @@ static inline void virtio_pci_legacy_remove(struct virtio_pci_device *vp_dev)
 int virtio_pci_modern_probe(struct virtio_pci_device *);
 void virtio_pci_modern_remove(struct virtio_pci_device *);
 
+struct virtio_device *virtio_pci_vf_get_pf_dev(struct pci_dev *pdev);
+
 #define VIRTIO_LEGACY_ADMIN_CMD_BITMAP \
 	(BIT_ULL(VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_WRITE) | \
 	 BIT_ULL(VIRTIO_ADMIN_CMD_LEGACY_COMMON_CFG_READ) | \
diff --git a/include/linux/virtio_pci_admin.h b/include/linux/virtio_pci_admin.h
new file mode 100644
index 000000000000..f4a100a0fe2e
--- /dev/null
+++ b/include/linux/virtio_pci_admin.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_VIRTIO_PCI_ADMIN_H
+#define _LINUX_VIRTIO_PCI_ADMIN_H
+
+#include <linux/types.h>
+#include <linux/pci.h>
+
+#ifdef CONFIG_VIRTIO_PCI_ADMIN_LEGACY
+bool virtio_pci_admin_has_legacy_io(struct pci_dev *pdev);
+int virtio_pci_admin_legacy_common_io_write(struct pci_dev *pdev, u8 offset,
+					    u8 size, u8 *buf);
+int virtio_pci_admin_legacy_common_io_read(struct pci_dev *pdev, u8 offset,
+					   u8 size, u8 *buf);
+int virtio_pci_admin_legacy_device_io_write(struct pci_dev *pdev, u8 offset,
+					    u8 size, u8 *buf);
+int virtio_pci_admin_legacy_device_io_read(struct pci_dev *pdev, u8 offset,
+					   u8 size, u8 *buf);
+int virtio_pci_admin_legacy_io_notify_info(struct pci_dev *pdev,
+					   u8 req_bar_flags, u8 *bar,
+					   u64 *bar_offset);
+#endif
+
+#endif /* _LINUX_VIRTIO_PCI_ADMIN_H */
-- 
cgit v1.2.3


From 8bccc5b80678c69f7729ce4cd232c0aa98fa6277 Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Tue, 19 Dec 2023 11:32:45 +0200
Subject: vfio/pci: Expose vfio_pci_core_setup_barmap()

Expose vfio_pci_core_setup_barmap() to be used by drivers.

This will let drivers to mmap a BAR and re-use it from both vfio and the
driver when it's applicable.

This API will be used in the next patches by the vfio/virtio coming
driver.

Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Link: https://lore.kernel.org/r/20231219093247.170936-8-yishaih@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/pci/vfio_pci_rdwr.c | 7 ++++---
 include/linux/vfio_pci_core.h    | 1 +
 2 files changed, 5 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c
index e27de61ac9fe..a9887fd6de46 100644
--- a/drivers/vfio/pci/vfio_pci_rdwr.c
+++ b/drivers/vfio/pci/vfio_pci_rdwr.c
@@ -200,7 +200,7 @@ static ssize_t do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem,
 	return done;
 }
 
-static int vfio_pci_setup_barmap(struct vfio_pci_core_device *vdev, int bar)
+int vfio_pci_core_setup_barmap(struct vfio_pci_core_device *vdev, int bar)
 {
 	struct pci_dev *pdev = vdev->pdev;
 	int ret;
@@ -223,6 +223,7 @@ static int vfio_pci_setup_barmap(struct vfio_pci_core_device *vdev, int bar)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(vfio_pci_core_setup_barmap);
 
 ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf,
 			size_t count, loff_t *ppos, bool iswrite)
@@ -262,7 +263,7 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf,
 		}
 		x_end = end;
 	} else {
-		int ret = vfio_pci_setup_barmap(vdev, bar);
+		int ret = vfio_pci_core_setup_barmap(vdev, bar);
 		if (ret) {
 			done = ret;
 			goto out;
@@ -438,7 +439,7 @@ int vfio_pci_ioeventfd(struct vfio_pci_core_device *vdev, loff_t offset,
 		return -EINVAL;
 #endif
 
-	ret = vfio_pci_setup_barmap(vdev, bar);
+	ret = vfio_pci_core_setup_barmap(vdev, bar);
 	if (ret)
 		return ret;
 
diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h
index 562e8754869d..67ac58e20e1d 100644
--- a/include/linux/vfio_pci_core.h
+++ b/include/linux/vfio_pci_core.h
@@ -127,6 +127,7 @@ int vfio_pci_core_match(struct vfio_device *core_vdev, char *buf);
 int vfio_pci_core_enable(struct vfio_pci_core_device *vdev);
 void vfio_pci_core_disable(struct vfio_pci_core_device *vdev);
 void vfio_pci_core_finish_enable(struct vfio_pci_core_device *vdev);
+int vfio_pci_core_setup_barmap(struct vfio_pci_core_device *vdev, int bar);
 pci_ers_result_t vfio_pci_core_aer_err_detected(struct pci_dev *pdev,
 						pci_channel_state_t state);
 
-- 
cgit v1.2.3


From 8486ae162b3b6cc1055366f044495cf1966231f1 Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Tue, 19 Dec 2023 11:32:46 +0200
Subject: vfio/pci: Expose vfio_pci_core_iowrite/read##size()

Expose vfio_pci_core_iowrite/read##size() to let it be used by drivers.

This functionality is needed to enable direct access to some physical
BAR of the device with the proper locks/checks in place.

The next patches from this series will use this functionality on a data
path flow when a direct access to the BAR is needed.

Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Link: https://lore.kernel.org/r/20231219093247.170936-9-yishaih@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/pci/vfio_pci_rdwr.c | 50 +++++++++++++++++++++-------------------
 include/linux/vfio_pci_core.h    | 19 +++++++++++++++
 2 files changed, 45 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c
index a9887fd6de46..07fea08ea8a2 100644
--- a/drivers/vfio/pci/vfio_pci_rdwr.c
+++ b/drivers/vfio/pci/vfio_pci_rdwr.c
@@ -38,7 +38,7 @@
 #define vfio_iowrite8	iowrite8
 
 #define VFIO_IOWRITE(size) \
-static int vfio_pci_iowrite##size(struct vfio_pci_core_device *vdev,		\
+int vfio_pci_core_iowrite##size(struct vfio_pci_core_device *vdev,	\
 			bool test_mem, u##size val, void __iomem *io)	\
 {									\
 	if (test_mem) {							\
@@ -55,7 +55,8 @@ static int vfio_pci_iowrite##size(struct vfio_pci_core_device *vdev,		\
 		up_read(&vdev->memory_lock);				\
 									\
 	return 0;							\
-}
+}									\
+EXPORT_SYMBOL_GPL(vfio_pci_core_iowrite##size);
 
 VFIO_IOWRITE(8)
 VFIO_IOWRITE(16)
@@ -65,7 +66,7 @@ VFIO_IOWRITE(64)
 #endif
 
 #define VFIO_IOREAD(size) \
-static int vfio_pci_ioread##size(struct vfio_pci_core_device *vdev,		\
+int vfio_pci_core_ioread##size(struct vfio_pci_core_device *vdev,	\
 			bool test_mem, u##size *val, void __iomem *io)	\
 {									\
 	if (test_mem) {							\
@@ -82,7 +83,8 @@ static int vfio_pci_ioread##size(struct vfio_pci_core_device *vdev,		\
 		up_read(&vdev->memory_lock);				\
 									\
 	return 0;							\
-}
+}									\
+EXPORT_SYMBOL_GPL(vfio_pci_core_ioread##size);
 
 VFIO_IOREAD(8)
 VFIO_IOREAD(16)
@@ -119,13 +121,13 @@ static ssize_t do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem,
 				if (copy_from_user(&val, buf, 4))
 					return -EFAULT;
 
-				ret = vfio_pci_iowrite32(vdev, test_mem,
-							 val, io + off);
+				ret = vfio_pci_core_iowrite32(vdev, test_mem,
+							      val, io + off);
 				if (ret)
 					return ret;
 			} else {
-				ret = vfio_pci_ioread32(vdev, test_mem,
-							&val, io + off);
+				ret = vfio_pci_core_ioread32(vdev, test_mem,
+							     &val, io + off);
 				if (ret)
 					return ret;
 
@@ -141,13 +143,13 @@ static ssize_t do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem,
 				if (copy_from_user(&val, buf, 2))
 					return -EFAULT;
 
-				ret = vfio_pci_iowrite16(vdev, test_mem,
-							 val, io + off);
+				ret = vfio_pci_core_iowrite16(vdev, test_mem,
+							      val, io + off);
 				if (ret)
 					return ret;
 			} else {
-				ret = vfio_pci_ioread16(vdev, test_mem,
-							&val, io + off);
+				ret = vfio_pci_core_ioread16(vdev, test_mem,
+							     &val, io + off);
 				if (ret)
 					return ret;
 
@@ -163,13 +165,13 @@ static ssize_t do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem,
 				if (copy_from_user(&val, buf, 1))
 					return -EFAULT;
 
-				ret = vfio_pci_iowrite8(vdev, test_mem,
-							val, io + off);
+				ret = vfio_pci_core_iowrite8(vdev, test_mem,
+							     val, io + off);
 				if (ret)
 					return ret;
 			} else {
-				ret = vfio_pci_ioread8(vdev, test_mem,
-						       &val, io + off);
+				ret = vfio_pci_core_ioread8(vdev, test_mem,
+							    &val, io + off);
 				if (ret)
 					return ret;
 
@@ -364,21 +366,21 @@ static void vfio_pci_ioeventfd_do_write(struct vfio_pci_ioeventfd *ioeventfd,
 {
 	switch (ioeventfd->count) {
 	case 1:
-		vfio_pci_iowrite8(ioeventfd->vdev, test_mem,
-				  ioeventfd->data, ioeventfd->addr);
+		vfio_pci_core_iowrite8(ioeventfd->vdev, test_mem,
+				       ioeventfd->data, ioeventfd->addr);
 		break;
 	case 2:
-		vfio_pci_iowrite16(ioeventfd->vdev, test_mem,
-				   ioeventfd->data, ioeventfd->addr);
+		vfio_pci_core_iowrite16(ioeventfd->vdev, test_mem,
+					ioeventfd->data, ioeventfd->addr);
 		break;
 	case 4:
-		vfio_pci_iowrite32(ioeventfd->vdev, test_mem,
-				   ioeventfd->data, ioeventfd->addr);
+		vfio_pci_core_iowrite32(ioeventfd->vdev, test_mem,
+					ioeventfd->data, ioeventfd->addr);
 		break;
 #ifdef iowrite64
 	case 8:
-		vfio_pci_iowrite64(ioeventfd->vdev, test_mem,
-				   ioeventfd->data, ioeventfd->addr);
+		vfio_pci_core_iowrite64(ioeventfd->vdev, test_mem,
+					ioeventfd->data, ioeventfd->addr);
 		break;
 #endif
 	}
diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h
index 67ac58e20e1d..85e84b92751b 100644
--- a/include/linux/vfio_pci_core.h
+++ b/include/linux/vfio_pci_core.h
@@ -131,4 +131,23 @@ int vfio_pci_core_setup_barmap(struct vfio_pci_core_device *vdev, int bar);
 pci_ers_result_t vfio_pci_core_aer_err_detected(struct pci_dev *pdev,
 						pci_channel_state_t state);
 
+#define VFIO_IOWRITE_DECLATION(size) \
+int vfio_pci_core_iowrite##size(struct vfio_pci_core_device *vdev,	\
+			bool test_mem, u##size val, void __iomem *io);
+
+VFIO_IOWRITE_DECLATION(8)
+VFIO_IOWRITE_DECLATION(16)
+VFIO_IOWRITE_DECLATION(32)
+#ifdef iowrite64
+VFIO_IOWRITE_DECLATION(64)
+#endif
+
+#define VFIO_IOREAD_DECLATION(size) \
+int vfio_pci_core_ioread##size(struct vfio_pci_core_device *vdev,	\
+			bool test_mem, u##size *val, void __iomem *io);
+
+VFIO_IOREAD_DECLATION(8)
+VFIO_IOREAD_DECLATION(16)
+VFIO_IOREAD_DECLATION(32)
+
 #endif /* VFIO_PCI_CORE_H */
-- 
cgit v1.2.3


From a4104821ad651d8a0b374f0b2474c345bbb42f82 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Tue, 19 Dec 2023 12:30:43 -0700
Subject: io_uring/unix: drop usage of io_uring socket

Since we no longer allow sending io_uring fds over SCM_RIGHTS, move to
using io_is_uring_fops() to detect whether this is a io_uring fd or not.
With that done, kill off io_uring_get_socket() as nobody calls it
anymore.

This is in preparation to yanking out the rest of the core related to
unix gc with io_uring.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/io_uring.h | 10 +++++-----
 io_uring/io_uring.c      | 13 -------------
 io_uring/io_uring.h      |  1 -
 net/core/scm.c           |  2 +-
 net/unix/scm.c           |  4 +---
 5 files changed, 7 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index d8fc93492dc5..68ed6697fece 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -7,12 +7,12 @@
 #include <uapi/linux/io_uring.h>
 
 #if defined(CONFIG_IO_URING)
-struct sock *io_uring_get_socket(struct file *file);
 void __io_uring_cancel(bool cancel_all);
 void __io_uring_free(struct task_struct *tsk);
 void io_uring_unreg_ringfd(void);
 const char *io_uring_get_opcode(u8 opcode);
 int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags);
+bool io_is_uring_fops(struct file *file);
 
 static inline void io_uring_files_cancel(void)
 {
@@ -32,10 +32,6 @@ static inline void io_uring_free(struct task_struct *tsk)
 		__io_uring_free(tsk);
 }
 #else
-static inline struct sock *io_uring_get_socket(struct file *file)
-{
-	return NULL;
-}
 static inline void io_uring_task_cancel(void)
 {
 }
@@ -54,6 +50,10 @@ static inline int io_uring_cmd_sock(struct io_uring_cmd *cmd,
 {
 	return -EOPNOTSUPP;
 }
+static inline bool io_is_uring_fops(struct file *file)
+{
+	return false;
+}
 #endif
 
 #endif
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 2b24ce692b0b..a9acccd45880 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -171,19 +171,6 @@ static struct ctl_table kernel_io_uring_disabled_table[] = {
 };
 #endif
 
-struct sock *io_uring_get_socket(struct file *file)
-{
-#if defined(CONFIG_UNIX)
-	if (io_is_uring_fops(file)) {
-		struct io_ring_ctx *ctx = file->private_data;
-
-		return ctx->ring_sock->sk;
-	}
-#endif
-	return NULL;
-}
-EXPORT_SYMBOL(io_uring_get_socket);
-
 static inline void io_submit_flush_completions(struct io_ring_ctx *ctx)
 {
 	if (!wq_list_empty(&ctx->submit_state.compl_reqs) ||
diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index 1112c198e516..04e33f25919c 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -44,7 +44,6 @@ struct file *io_file_get_fixed(struct io_kiocb *req, int fd,
 			       unsigned issue_flags);
 
 void __io_req_task_work_add(struct io_kiocb *req, unsigned flags);
-bool io_is_uring_fops(struct file *file);
 bool io_alloc_async_data(struct io_kiocb *req);
 void io_req_task_queue(struct io_kiocb *req);
 void io_queue_iowq(struct io_kiocb *req, struct io_tw_state *ts_dont_use);
diff --git a/net/core/scm.c b/net/core/scm.c
index db3f7cd519c2..d0e0852a24d5 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -105,7 +105,7 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp)
 		if (fd < 0 || !(file = fget_raw(fd)))
 			return -EBADF;
 		/* don't allow io_uring files */
-		if (io_uring_get_socket(file)) {
+		if (io_is_uring_fops(file)) {
 			fput(file);
 			return -EINVAL;
 		}
diff --git a/net/unix/scm.c b/net/unix/scm.c
index 6ff628f2349f..822ce0d0d791 100644
--- a/net/unix/scm.c
+++ b/net/unix/scm.c
@@ -35,10 +35,8 @@ struct sock *unix_get_socket(struct file *filp)
 		/* PF_UNIX ? */
 		if (s && ops && ops->family == PF_UNIX)
 			u_sock = s;
-	} else {
-		/* Could be an io_uring instance */
-		u_sock = io_uring_get_socket(filp);
 	}
+
 	return u_sock;
 }
 EXPORT_SYMBOL(unix_get_socket);
-- 
cgit v1.2.3


From 6e5e6d274956305f1fc0340522b38f5f5be74bdb Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Tue, 19 Dec 2023 12:36:34 -0700
Subject: io_uring: drop any code related to SCM_RIGHTS

This is dead code after we dropped support for passing io_uring fds
over SCM_RIGHTS, get rid of it.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/io_uring_types.h |   3 -
 io_uring/filetable.c           |  11 +--
 io_uring/io_uring.c            |  32 +-------
 io_uring/rsrc.c                | 169 +----------------------------------------
 io_uring/rsrc.h                |  15 ----
 5 files changed, 10 insertions(+), 220 deletions(-)

(limited to 'include')

diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index bebab36abce8..fc8f2570b92b 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -389,9 +389,6 @@ struct io_ring_ctx {
 	struct wait_queue_head		rsrc_quiesce_wq;
 	unsigned			rsrc_quiesce;
 
-	#if defined(CONFIG_UNIX)
-		struct socket		*ring_sock;
-	#endif
 	/* hashed buffered write serialization */
 	struct io_wq_hash		*hash_map;
 
diff --git a/io_uring/filetable.c b/io_uring/filetable.c
index e7d749991de4..6e86e6188dbe 100644
--- a/io_uring/filetable.c
+++ b/io_uring/filetable.c
@@ -87,13 +87,10 @@ static int io_install_fixed_file(struct io_ring_ctx *ctx, struct file *file,
 		io_file_bitmap_clear(&ctx->file_table, slot_index);
 	}
 
-	ret = io_scm_file_account(ctx, file);
-	if (!ret) {
-		*io_get_tag_slot(ctx->file_data, slot_index) = 0;
-		io_fixed_file_set(file_slot, file);
-		io_file_bitmap_set(&ctx->file_table, slot_index);
-	}
-	return ret;
+	*io_get_tag_slot(ctx->file_data, slot_index) = 0;
+	io_fixed_file_set(file_slot, file);
+	io_file_bitmap_set(&ctx->file_table, slot_index);
+	return 0;
 }
 
 int __io_fixed_fd_install(struct io_ring_ctx *ctx, struct file *file,
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index a9acccd45880..a9a519fa9926 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -60,7 +60,6 @@
 #include <linux/net.h>
 #include <net/sock.h>
 #include <net/af_unix.h>
-#include <net/scm.h>
 #include <linux/anon_inodes.h>
 #include <linux/sched/mm.h>
 #include <linux/uaccess.h>
@@ -2866,13 +2865,6 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx)
 		io_rsrc_node_destroy(ctx, ctx->rsrc_node);
 
 	WARN_ON_ONCE(!list_empty(&ctx->rsrc_ref_list));
-
-#if defined(CONFIG_UNIX)
-	if (ctx->ring_sock) {
-		ctx->ring_sock->file = NULL; /* so that iput() is called */
-		sock_release(ctx->ring_sock);
-	}
-#endif
 	WARN_ON_ONCE(!list_empty(&ctx->ltimeout_list));
 
 	io_alloc_cache_free(&ctx->rsrc_node_cache, io_rsrc_node_cache_free);
@@ -3781,32 +3773,12 @@ static int io_uring_install_fd(struct file *file)
 /*
  * Allocate an anonymous fd, this is what constitutes the application
  * visible backing of an io_uring instance. The application mmaps this
- * fd to gain access to the SQ/CQ ring details. If UNIX sockets are enabled,
- * we have to tie this fd to a socket for file garbage collection purposes.
+ * fd to gain access to the SQ/CQ ring details.
  */
 static struct file *io_uring_get_file(struct io_ring_ctx *ctx)
 {
-	struct file *file;
-#if defined(CONFIG_UNIX)
-	int ret;
-
-	ret = sock_create_kern(&init_net, PF_UNIX, SOCK_RAW, IPPROTO_IP,
-				&ctx->ring_sock);
-	if (ret)
-		return ERR_PTR(ret);
-#endif
-
-	file = anon_inode_getfile_secure("[io_uring]", &io_uring_fops, ctx,
+	return anon_inode_getfile_secure("[io_uring]", &io_uring_fops, ctx,
 					 O_RDWR | O_CLOEXEC, NULL);
-#if defined(CONFIG_UNIX)
-	if (IS_ERR(file)) {
-		sock_release(ctx->ring_sock);
-		ctx->ring_sock = NULL;
-	} else {
-		ctx->ring_sock->file = file;
-	}
-#endif
-	return file;
 }
 
 static __cold int io_uring_create(unsigned entries, struct io_uring_params *p,
diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index f521c5965a93..4818b79231dd 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -24,7 +24,6 @@ struct io_rsrc_update {
 };
 
 static void io_rsrc_buf_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc);
-static void io_rsrc_file_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc);
 static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov,
 				  struct io_mapped_ubuf **pimu,
 				  struct page **last_hpage);
@@ -157,7 +156,7 @@ static void io_rsrc_put_work(struct io_rsrc_node *node)
 
 	switch (node->type) {
 	case IORING_RSRC_FILE:
-		io_rsrc_file_put(node->ctx, prsrc);
+		fput(prsrc->file);
 		break;
 	case IORING_RSRC_BUFFER:
 		io_rsrc_buf_put(node->ctx, prsrc);
@@ -402,23 +401,13 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx,
 				break;
 			}
 			/*
-			 * Don't allow io_uring instances to be registered. If
-			 * UNIX isn't enabled, then this causes a reference
-			 * cycle and this instance can never get freed. If UNIX
-			 * is enabled we'll handle it just fine, but there's
-			 * still no point in allowing a ring fd as it doesn't
-			 * support regular read/write anyway.
+			 * Don't allow io_uring instances to be registered.
 			 */
 			if (io_is_uring_fops(file)) {
 				fput(file);
 				err = -EBADF;
 				break;
 			}
-			err = io_scm_file_account(ctx, file);
-			if (err) {
-				fput(file);
-				break;
-			}
 			*io_get_tag_slot(data, i) = tag;
 			io_fixed_file_set(file_slot, file);
 			io_file_bitmap_set(&ctx->file_table, i);
@@ -675,22 +664,12 @@ void __io_sqe_files_unregister(struct io_ring_ctx *ctx)
 	for (i = 0; i < ctx->nr_user_files; i++) {
 		struct file *file = io_file_from_index(&ctx->file_table, i);
 
-		/* skip scm accounted files, they'll be freed by ->ring_sock */
-		if (!file || io_file_need_scm(file))
+		if (!file)
 			continue;
 		io_file_bitmap_clear(&ctx->file_table, i);
 		fput(file);
 	}
 
-#if defined(CONFIG_UNIX)
-	if (ctx->ring_sock) {
-		struct sock *sock = ctx->ring_sock->sk;
-		struct sk_buff *skb;
-
-		while ((skb = skb_dequeue(&sock->sk_receive_queue)) != NULL)
-			kfree_skb(skb);
-	}
-#endif
 	io_free_file_tables(&ctx->file_table);
 	io_file_table_set_alloc_range(ctx, 0, 0);
 	io_rsrc_data_free(ctx->file_data);
@@ -718,137 +697,6 @@ int io_sqe_files_unregister(struct io_ring_ctx *ctx)
 	return ret;
 }
 
-/*
- * Ensure the UNIX gc is aware of our file set, so we are certain that
- * the io_uring can be safely unregistered on process exit, even if we have
- * loops in the file referencing. We account only files that can hold other
- * files because otherwise they can't form a loop and so are not interesting
- * for GC.
- */
-int __io_scm_file_account(struct io_ring_ctx *ctx, struct file *file)
-{
-#if defined(CONFIG_UNIX)
-	struct sock *sk = ctx->ring_sock->sk;
-	struct sk_buff_head *head = &sk->sk_receive_queue;
-	struct scm_fp_list *fpl;
-	struct sk_buff *skb;
-
-	if (likely(!io_file_need_scm(file)))
-		return 0;
-
-	/*
-	 * See if we can merge this file into an existing skb SCM_RIGHTS
-	 * file set. If there's no room, fall back to allocating a new skb
-	 * and filling it in.
-	 */
-	spin_lock_irq(&head->lock);
-	skb = skb_peek(head);
-	if (skb && UNIXCB(skb).fp->count < SCM_MAX_FD)
-		__skb_unlink(skb, head);
-	else
-		skb = NULL;
-	spin_unlock_irq(&head->lock);
-
-	if (!skb) {
-		fpl = kzalloc(sizeof(*fpl), GFP_KERNEL);
-		if (!fpl)
-			return -ENOMEM;
-
-		skb = alloc_skb(0, GFP_KERNEL);
-		if (!skb) {
-			kfree(fpl);
-			return -ENOMEM;
-		}
-
-		fpl->user = get_uid(current_user());
-		fpl->max = SCM_MAX_FD;
-		fpl->count = 0;
-
-		UNIXCB(skb).fp = fpl;
-		skb->sk = sk;
-		skb->destructor = io_uring_destruct_scm;
-		refcount_add(skb->truesize, &sk->sk_wmem_alloc);
-	}
-
-	fpl = UNIXCB(skb).fp;
-	fpl->fp[fpl->count++] = get_file(file);
-	unix_inflight(fpl->user, file);
-	skb_queue_head(head, skb);
-	fput(file);
-#endif
-	return 0;
-}
-
-static __cold void io_rsrc_file_scm_put(struct io_ring_ctx *ctx, struct file *file)
-{
-#if defined(CONFIG_UNIX)
-	struct sock *sock = ctx->ring_sock->sk;
-	struct sk_buff_head list, *head = &sock->sk_receive_queue;
-	struct sk_buff *skb;
-	int i;
-
-	__skb_queue_head_init(&list);
-
-	/*
-	 * Find the skb that holds this file in its SCM_RIGHTS. When found,
-	 * remove this entry and rearrange the file array.
-	 */
-	skb = skb_dequeue(head);
-	while (skb) {
-		struct scm_fp_list *fp;
-
-		fp = UNIXCB(skb).fp;
-		for (i = 0; i < fp->count; i++) {
-			int left;
-
-			if (fp->fp[i] != file)
-				continue;
-
-			unix_notinflight(fp->user, fp->fp[i]);
-			left = fp->count - 1 - i;
-			if (left) {
-				memmove(&fp->fp[i], &fp->fp[i + 1],
-						left * sizeof(struct file *));
-			}
-			fp->count--;
-			if (!fp->count) {
-				kfree_skb(skb);
-				skb = NULL;
-			} else {
-				__skb_queue_tail(&list, skb);
-			}
-			fput(file);
-			file = NULL;
-			break;
-		}
-
-		if (!file)
-			break;
-
-		__skb_queue_tail(&list, skb);
-
-		skb = skb_dequeue(head);
-	}
-
-	if (skb_peek(&list)) {
-		spin_lock_irq(&head->lock);
-		while ((skb = __skb_dequeue(&list)) != NULL)
-			__skb_queue_tail(head, skb);
-		spin_unlock_irq(&head->lock);
-	}
-#endif
-}
-
-static void io_rsrc_file_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc)
-{
-	struct file *file = prsrc->file;
-
-	if (likely(!io_file_need_scm(file)))
-		fput(file);
-	else
-		io_rsrc_file_scm_put(ctx, file);
-}
-
 int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
 			  unsigned nr_args, u64 __user *tags)
 {
@@ -897,21 +745,12 @@ int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
 			goto fail;
 
 		/*
-		 * Don't allow io_uring instances to be registered. If UNIX
-		 * isn't enabled, then this causes a reference cycle and this
-		 * instance can never get freed. If UNIX is enabled we'll
-		 * handle it just fine, but there's still no point in allowing
-		 * a ring fd as it doesn't support regular read/write anyway.
+		 * Don't allow io_uring instances to be registered.
 		 */
 		if (io_is_uring_fops(file)) {
 			fput(file);
 			goto fail;
 		}
-		ret = io_scm_file_account(ctx, file);
-		if (ret) {
-			fput(file);
-			goto fail;
-		}
 		file_slot = io_fixed_file_slot(&ctx->file_table, i);
 		io_fixed_file_set(file_slot, file);
 		io_file_bitmap_set(&ctx->file_table, i);
diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h
index 08ac0d8e07ef..7238b9cfe33b 100644
--- a/io_uring/rsrc.h
+++ b/io_uring/rsrc.h
@@ -75,21 +75,6 @@ int io_sqe_files_unregister(struct io_ring_ctx *ctx);
 int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
 			  unsigned nr_args, u64 __user *tags);
 
-int __io_scm_file_account(struct io_ring_ctx *ctx, struct file *file);
-
-static inline bool io_file_need_scm(struct file *filp)
-{
-	return false;
-}
-
-static inline int io_scm_file_account(struct io_ring_ctx *ctx,
-				      struct file *file)
-{
-	if (likely(!io_file_need_scm(file)))
-		return 0;
-	return __io_scm_file_account(ctx, file);
-}
-
 int io_register_files_update(struct io_ring_ctx *ctx, void __user *arg,
 			     unsigned nr_args);
 int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg,
-- 
cgit v1.2.3


From ee0cf5e07f44a10fce8f1bfa9db226c0b5ecf880 Mon Sep 17 00:00:00 2001
From: Théo Lebrun <theo.lebrun@bootlin.com>
Date: Mon, 18 Dec 2023 18:14:16 +0100
Subject: clk: fixed-rate: fix
 clk_hw_register_fixed_rate_with_accuracy_parent_hw
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add missing comma and remove extraneous NULL argument. The macro is
currently used by no one which explains why the typo slipped by.

Fixes: 2d34f09e79c9 ("clk: fixed-rate: Add support for specifying parents via DT/pointers")
Signed-off-by: Théo Lebrun <theo.lebrun@bootlin.com>
Link: https://lore.kernel.org/r/20231218-mbly-clk-v1-1-44ce54108f06@bootlin.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 include/linux/clk-provider.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index ace3a4ce2fc9..1293c38ddb7f 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -448,8 +448,8 @@ struct clk *clk_register_fixed_rate(struct device *dev, const char *name,
  */
 #define clk_hw_register_fixed_rate_with_accuracy_parent_hw(dev, name,	      \
 		parent_hw, flags, fixed_rate, fixed_accuracy)		      \
-	__clk_hw_register_fixed_rate((dev), NULL, (name), NULL, (parent_hw)   \
-				     NULL, NULL, (flags), (fixed_rate),	      \
+	__clk_hw_register_fixed_rate((dev), NULL, (name), NULL, (parent_hw),  \
+				     NULL, (flags), (fixed_rate),	      \
 				     (fixed_accuracy), 0, false)
 /**
  * clk_hw_register_fixed_rate_with_accuracy_parent_data - register fixed-rate
-- 
cgit v1.2.3


From 4ba1d0f23414135e4f426dae4cb5cdc2ce246f89 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Thu, 14 Dec 2023 17:13:25 -0800
Subject: bpf: abstract away global subprog arg preparation logic from reg
 state setup

btf_prepare_func_args() is used to understand expectations and
restrictions on global subprog arguments. But current implementation is
hard to extend, as it intermixes BTF-based func prototype parsing and
interpretation logic with setting up register state at subprog entry.

Worse still, those registers are not completely set up inside
btf_prepare_func_args(), requiring some more logic later in
do_check_common(). Like calling mark_reg_unknown() and similar
initialization operations.

This intermixing of BTF interpretation and register state setup is
problematic. First, it causes duplication of BTF parsing logic for global
subprog verification (to set up initial state of global subprog) and
global subprog call sites analysis (when we need to check that whatever
is being passed into global subprog matches expectations), performed in
btf_check_subprog_call().

Given we want to extend global func argument with tags later, this
duplication is problematic. So refactor btf_prepare_func_args() to do
only BTF-based func proto and args parsing, returning high-level
argument "expectations" only, with no regard to specifics of register
state. I.e., if it's a context argument, instead of setting register
state to PTR_TO_CTX, we return ARG_PTR_TO_CTX enum for that argument as
"an argument specification" for further processing inside
do_check_common(). Similarly for SCALAR arguments, PTR_TO_MEM, etc.

This allows to reuse btf_prepare_func_args() in following patches at
global subprog call site analysis time. It also keeps register setup
code consistently in one place, do_check_common().

Besides all this, we cache this argument specs information inside
env->subprog_info, eliminating the need to redo these potentially
expensive BTF traversals, especially if BPF program's BTF is big and/or
there are lots of global subprog calls.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20231215011334.2307144-2-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h          |  3 +--
 include/linux/bpf_verifier.h | 16 ++++++++++++++++
 kernel/bpf/btf.c             | 38 ++++++++++++++++++++------------------
 kernel/bpf/verifier.c        | 43 +++++++++++++++++++++++++++----------------
 4 files changed, 64 insertions(+), 36 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 7a8d4c81a39a..c050c82cc9a5 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2470,8 +2470,7 @@ int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog,
 				struct bpf_reg_state *regs);
 int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog,
 			   struct bpf_reg_state *regs);
-int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
-			  struct bpf_reg_state *reg, u32 *nargs);
+int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog);
 int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog,
 			 struct btf *btf, const struct btf_type *t);
 const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type *pt,
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index c2819a6579a5..5742e9c0a7b8 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -606,6 +606,13 @@ static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log)
 
 #define BPF_MAX_SUBPROGS 256
 
+struct bpf_subprog_arg_info {
+	enum bpf_arg_type arg_type;
+	union {
+		u32 mem_size;
+	};
+};
+
 struct bpf_subprog_info {
 	/* 'start' has to be the first field otherwise find_subprog() won't work */
 	u32 start; /* insn idx of function entry point */
@@ -617,6 +624,10 @@ struct bpf_subprog_info {
 	bool is_cb: 1;
 	bool is_async_cb: 1;
 	bool is_exception_cb: 1;
+	bool args_cached: 1;
+
+	u8 arg_cnt;
+	struct bpf_subprog_arg_info args[MAX_BPF_FUNC_REG_ARGS];
 };
 
 struct bpf_verifier_env;
@@ -727,6 +738,11 @@ struct bpf_verifier_env {
 	char tmp_str_buf[TMP_STR_BUF_LEN];
 };
 
+static inline struct bpf_subprog_info *subprog_info(struct bpf_verifier_env *env, int subprog)
+{
+	return &env->subprog_info[subprog];
+}
+
 __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log,
 				      const char *fmt, va_list args);
 __printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env,
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index d56433bf8aba..be2104e5f2f5 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -6948,16 +6948,17 @@ int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog,
 	return err;
 }
 
-/* Convert BTF of a function into bpf_reg_state if possible
+/* Process BTF of a function to produce high-level expectation of function
+ * arguments (like ARG_PTR_TO_CTX, or ARG_PTR_TO_MEM, etc). This information
+ * is cached in subprog info for reuse.
  * Returns:
  * EFAULT - there is a verifier bug. Abort verification.
  * EINVAL - cannot convert BTF.
- * 0 - Successfully converted BTF into bpf_reg_state
- * (either PTR_TO_CTX or SCALAR_VALUE).
+ * 0 - Successfully processed BTF and constructed argument expectations.
  */
-int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
-			  struct bpf_reg_state *regs, u32 *arg_cnt)
+int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog)
 {
+	struct bpf_subprog_info *sub = subprog_info(env, subprog);
 	struct bpf_verifier_log *log = &env->log;
 	struct bpf_prog *prog = env->prog;
 	enum bpf_prog_type prog_type = prog->type;
@@ -6967,6 +6968,9 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
 	u32 i, nargs, btf_id;
 	const char *tname;
 
+	if (sub->args_cached)
+		return 0;
+
 	if (!prog->aux->func_info ||
 	    prog->aux->func_info_aux[subprog].linkage != BTF_FUNC_GLOBAL) {
 		bpf_log(log, "Verifier bug\n");
@@ -6990,10 +6994,6 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
 	}
 	tname = btf_name_by_offset(btf, t->name_off);
 
-	if (log->level & BPF_LOG_LEVEL)
-		bpf_log(log, "Validating %s() func#%d...\n",
-			tname, subprog);
-
 	if (prog->aux->func_info_aux[subprog].unreliable) {
 		bpf_log(log, "Verifier bug in function %s()\n", tname);
 		return -EFAULT;
@@ -7013,7 +7013,6 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
 			tname, nargs, MAX_BPF_FUNC_REG_ARGS);
 		return -EINVAL;
 	}
-	*arg_cnt = nargs;
 	/* check that function returns int, exception cb also requires this */
 	t = btf_type_by_id(btf, t->type);
 	while (btf_type_is_modifier(t))
@@ -7028,24 +7027,24 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
 	 * Only PTR_TO_CTX and SCALAR are supported atm.
 	 */
 	for (i = 0; i < nargs; i++) {
-		struct bpf_reg_state *reg = &regs[i + 1];
-
 		t = btf_type_by_id(btf, args[i].type);
 		while (btf_type_is_modifier(t))
 			t = btf_type_by_id(btf, t->type);
 		if (btf_type_is_int(t) || btf_is_any_enum(t)) {
-			reg->type = SCALAR_VALUE;
+			sub->args[i].arg_type = ARG_ANYTHING;
 			continue;
 		}
 		if (btf_type_is_ptr(t)) {
+			u32 mem_size;
+
 			if (btf_get_prog_ctx_type(log, btf, t, prog_type, i)) {
-				reg->type = PTR_TO_CTX;
+				sub->args[i].arg_type = ARG_PTR_TO_CTX;
 				continue;
 			}
 
 			t = btf_type_skip_modifiers(btf, t->type, NULL);
 
-			ref_t = btf_resolve_size(btf, t, &reg->mem_size);
+			ref_t = btf_resolve_size(btf, t, &mem_size);
 			if (IS_ERR(ref_t)) {
 				bpf_log(log,
 				    "arg#%d reference type('%s %s') size cannot be determined: %ld\n",
@@ -7054,15 +7053,18 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
 				return -EINVAL;
 			}
 
-			reg->type = PTR_TO_MEM | PTR_MAYBE_NULL;
-			reg->id = ++env->id_gen;
-
+			sub->args[i].arg_type = ARG_PTR_TO_MEM_OR_NULL;
+			sub->args[i].mem_size = mem_size;
 			continue;
 		}
 		bpf_log(log, "Arg#%d type %s in %s() is not supported yet.\n",
 			i, btf_type_str(t), tname);
 		return -EINVAL;
 	}
+
+	sub->arg_cnt = nargs;
+	sub->args_cached = true;
+
 	return 0;
 }
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index df1cae459c77..6555785b9f63 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -442,11 +442,6 @@ static struct bpf_func_info_aux *subprog_aux(const struct bpf_verifier_env *env,
 	return &env->prog->aux->func_info_aux[subprog];
 }
 
-static struct bpf_subprog_info *subprog_info(struct bpf_verifier_env *env, int subprog)
-{
-	return &env->subprog_info[subprog];
-}
-
 static void mark_subprog_exc_cb(struct bpf_verifier_env *env, int subprog)
 {
 	struct bpf_subprog_info *info = subprog_info(env, subprog);
@@ -19937,34 +19932,50 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog)
 
 	regs = state->frame[state->curframe]->regs;
 	if (subprog || env->prog->type == BPF_PROG_TYPE_EXT) {
-		u32 nargs;
+		struct bpf_subprog_info *sub = subprog_info(env, subprog);
+		const char *sub_name = subprog_name(env, subprog);
+		struct bpf_subprog_arg_info *arg;
+		struct bpf_reg_state *reg;
 
-		ret = btf_prepare_func_args(env, subprog, regs, &nargs);
+		verbose(env, "Validating %s() func#%d...\n", sub_name, subprog);
+		ret = btf_prepare_func_args(env, subprog);
 		if (ret)
 			goto out;
+
 		if (subprog_is_exc_cb(env, subprog)) {
 			state->frame[0]->in_exception_callback_fn = true;
 			/* We have already ensured that the callback returns an integer, just
 			 * like all global subprogs. We need to determine it only has a single
 			 * scalar argument.
 			 */
-			if (nargs != 1 || regs[BPF_REG_1].type != SCALAR_VALUE) {
+			if (sub->arg_cnt != 1 || sub->args[0].arg_type != ARG_ANYTHING) {
 				verbose(env, "exception cb only supports single integer argument\n");
 				ret = -EINVAL;
 				goto out;
 			}
 		}
-		for (i = BPF_REG_1; i <= BPF_REG_5; i++) {
-			if (regs[i].type == PTR_TO_CTX)
+		for (i = BPF_REG_1; i <= sub->arg_cnt; i++) {
+			arg = &sub->args[i - BPF_REG_1];
+			reg = &regs[i];
+
+			if (arg->arg_type == ARG_PTR_TO_CTX) {
+				reg->type = PTR_TO_CTX;
 				mark_reg_known_zero(env, regs, i);
-			else if (regs[i].type == SCALAR_VALUE)
+			} else if (arg->arg_type == ARG_ANYTHING) {
+				reg->type = SCALAR_VALUE;
 				mark_reg_unknown(env, regs, i);
-			else if (base_type(regs[i].type) == PTR_TO_MEM) {
-				const u32 mem_size = regs[i].mem_size;
-
+			} else if (base_type(arg->arg_type) == ARG_PTR_TO_MEM) {
+				reg->type = PTR_TO_MEM;
+				if (arg->arg_type & PTR_MAYBE_NULL)
+					reg->type |= PTR_MAYBE_NULL;
 				mark_reg_known_zero(env, regs, i);
-				regs[i].mem_size = mem_size;
-				regs[i].id = ++env->id_gen;
+				reg->mem_size = arg->mem_size;
+				reg->id = ++env->id_gen;
+			} else {
+				WARN_ONCE(1, "BUG: unhandled arg#%d type %d\n",
+					  i - BPF_REG_1, arg->arg_type);
+				ret = -EFAULT;
+				goto out;
 			}
 		}
 	} else {
-- 
cgit v1.2.3


From 5eccd2db42d77e3570619c32d39e39bf486607cf Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Thu, 14 Dec 2023 17:13:26 -0800
Subject: bpf: reuse btf_prepare_func_args() check for main program BTF
 validation

Instead of btf_check_subprog_arg_match(), use btf_prepare_func_args()
logic to validate "trustworthiness" of main BPF program's BTF information,
if it is present.

We ignored results of original BTF check anyway, often times producing
confusing and ominously-sounding "reg type unsupported for arg#0
function" message, which has no apparent effect on program correctness
and verification process.

All the -EFAULT returning sanity checks are already performed in
check_btf_info_early(), so there is zero reason to have this duplication
of logic between btf_check_subprog_call() and btf_check_subprog_arg_match().
Dropping btf_check_subprog_arg_match() simplifies
btf_check_func_arg_match() further removing `bool processing_call` flag.

One subtle bit that was done by btf_check_subprog_arg_match() was
potentially marking main program's BTF as unreliable. We do this
explicitly now with a dedicated simple check, preserving the original
behavior, but now based on well factored btf_prepare_func_args() logic.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20231215011334.2307144-3-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h                                |  2 -
 kernel/bpf/btf.c                                   | 50 ++--------------------
 kernel/bpf/verifier.c                              | 25 ++++++-----
 tools/testing/selftests/bpf/prog_tests/log_fixup.c |  4 +-
 .../selftests/bpf/progs/cgrp_kfunc_failure.c       |  2 +-
 .../selftests/bpf/progs/task_kfunc_failure.c       |  2 +-
 6 files changed, 19 insertions(+), 66 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index c050c82cc9a5..d0d7eff22b8a 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2466,8 +2466,6 @@ int btf_distill_func_proto(struct bpf_verifier_log *log,
 			   struct btf_func_model *m);
 
 struct bpf_reg_state;
-int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog,
-				struct bpf_reg_state *regs);
 int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog,
 			   struct bpf_reg_state *regs);
 int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog);
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index be2104e5f2f5..33d9a1c73f6e 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -6768,8 +6768,7 @@ int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *pr
 static int btf_check_func_arg_match(struct bpf_verifier_env *env,
 				    const struct btf *btf, u32 func_id,
 				    struct bpf_reg_state *regs,
-				    bool ptr_to_mem_ok,
-				    bool processing_call)
+				    bool ptr_to_mem_ok)
 {
 	enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
 	struct bpf_verifier_log *log = &env->log;
@@ -6842,7 +6841,7 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
 					i, btf_type_str(t));
 				return -EINVAL;
 			}
-		} else if (ptr_to_mem_ok && processing_call) {
+		} else if (ptr_to_mem_ok) {
 			const struct btf_type *resolve_ret;
 			u32 type_size;
 
@@ -6867,55 +6866,12 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
 	return 0;
 }
 
-/* Compare BTF of a function declaration with given bpf_reg_state.
- * Returns:
- * EFAULT - there is a verifier bug. Abort verification.
- * EINVAL - there is a type mismatch or BTF is not available.
- * 0 - BTF matches with what bpf_reg_state expects.
- * Only PTR_TO_CTX and SCALAR_VALUE states are recognized.
- */
-int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog,
-				struct bpf_reg_state *regs)
-{
-	struct bpf_prog *prog = env->prog;
-	struct btf *btf = prog->aux->btf;
-	bool is_global;
-	u32 btf_id;
-	int err;
-
-	if (!prog->aux->func_info)
-		return -EINVAL;
-
-	btf_id = prog->aux->func_info[subprog].type_id;
-	if (!btf_id)
-		return -EFAULT;
-
-	if (prog->aux->func_info_aux[subprog].unreliable)
-		return -EINVAL;
-
-	is_global = prog->aux->func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL;
-	err = btf_check_func_arg_match(env, btf, btf_id, regs, is_global, false);
-
-	/* Compiler optimizations can remove arguments from static functions
-	 * or mismatched type can be passed into a global function.
-	 * In such cases mark the function as unreliable from BTF point of view.
-	 */
-	if (err)
-		prog->aux->func_info_aux[subprog].unreliable = true;
-	return err;
-}
-
 /* Compare BTF of a function call with given bpf_reg_state.
  * Returns:
  * EFAULT - there is a verifier bug. Abort verification.
  * EINVAL - there is a type mismatch or BTF is not available.
  * 0 - BTF matches with what bpf_reg_state expects.
  * Only PTR_TO_CTX and SCALAR_VALUE states are recognized.
- *
- * NOTE: the code is duplicated from btf_check_subprog_arg_match()
- * because btf_check_func_arg_match() is still doing both. Once that
- * function is split in 2, we can call from here btf_check_subprog_arg_match()
- * first, and then treat the calling part in a new code path.
  */
 int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog,
 			   struct bpf_reg_state *regs)
@@ -6937,7 +6893,7 @@ int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog,
 		return -EINVAL;
 
 	is_global = prog->aux->func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL;
-	err = btf_check_func_arg_match(env, btf, btf_id, regs, is_global, true);
+	err = btf_check_func_arg_match(env, btf, btf_id, regs, is_global);
 
 	/* Compiler optimizations can remove arguments from static functions
 	 * or mismatched type can be passed into a global function.
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 6555785b9f63..c26e9ab5226c 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -19904,6 +19904,7 @@ static void free_states(struct bpf_verifier_env *env)
 static int do_check_common(struct bpf_verifier_env *env, int subprog)
 {
 	bool pop_log = !(env->log.level & BPF_LOG_LEVEL2);
+	struct bpf_subprog_info *sub = subprog_info(env, subprog);
 	struct bpf_verifier_state *state;
 	struct bpf_reg_state *regs;
 	int ret, i;
@@ -19930,9 +19931,9 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog)
 	state->first_insn_idx = env->subprog_info[subprog].start;
 	state->last_insn_idx = -1;
 
+
 	regs = state->frame[state->curframe]->regs;
 	if (subprog || env->prog->type == BPF_PROG_TYPE_EXT) {
-		struct bpf_subprog_info *sub = subprog_info(env, subprog);
 		const char *sub_name = subprog_name(env, subprog);
 		struct bpf_subprog_arg_info *arg;
 		struct bpf_reg_state *reg;
@@ -19979,21 +19980,19 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog)
 			}
 		}
 	} else {
+		/* if main BPF program has associated BTF info, validate that
+		 * it's matching expected signature, and otherwise mark BTF
+		 * info for main program as unreliable
+		 */
+		if (env->prog->aux->func_info_aux) {
+			ret = btf_prepare_func_args(env, 0);
+			if (ret || sub->arg_cnt != 1 || sub->args[0].arg_type != ARG_PTR_TO_CTX)
+				env->prog->aux->func_info_aux[0].unreliable = true;
+		}
+
 		/* 1st arg to a function */
 		regs[BPF_REG_1].type = PTR_TO_CTX;
 		mark_reg_known_zero(env, regs, BPF_REG_1);
-		ret = btf_check_subprog_arg_match(env, subprog, regs);
-		if (ret == -EFAULT)
-			/* unlikely verifier bug. abort.
-			 * ret == 0 and ret < 0 are sadly acceptable for
-			 * main() function due to backward compatibility.
-			 * Like socket filter program may be written as:
-			 * int bpf_prog(struct pt_regs *ctx)
-			 * and never dereference that ctx in the program.
-			 * 'struct pt_regs' is a type mismatch for socket
-			 * filter that should be using 'struct __sk_buff'.
-			 */
-			goto out;
 	}
 
 	ret = do_check(env);
diff --git a/tools/testing/selftests/bpf/prog_tests/log_fixup.c b/tools/testing/selftests/bpf/prog_tests/log_fixup.c
index effd78b2a657..7a3fa2ff567b 100644
--- a/tools/testing/selftests/bpf/prog_tests/log_fixup.c
+++ b/tools/testing/selftests/bpf/prog_tests/log_fixup.c
@@ -169,9 +169,9 @@ void test_log_fixup(void)
 	if (test__start_subtest("bad_core_relo_trunc_none"))
 		bad_core_relo(0, TRUNC_NONE /* full buf */);
 	if (test__start_subtest("bad_core_relo_trunc_partial"))
-		bad_core_relo(300, TRUNC_PARTIAL /* truncate original log a bit */);
+		bad_core_relo(280, TRUNC_PARTIAL /* truncate original log a bit */);
 	if (test__start_subtest("bad_core_relo_trunc_full"))
-		bad_core_relo(210, TRUNC_FULL  /* truncate also libbpf's message patch */);
+		bad_core_relo(220, TRUNC_FULL  /* truncate also libbpf's message patch */);
 	if (test__start_subtest("bad_core_relo_subprog"))
 		bad_core_relo_subprog();
 	if (test__start_subtest("missing_map"))
diff --git a/tools/testing/selftests/bpf/progs/cgrp_kfunc_failure.c b/tools/testing/selftests/bpf/progs/cgrp_kfunc_failure.c
index 0fa564a5cc5b..9fe9c4a4e8f6 100644
--- a/tools/testing/selftests/bpf/progs/cgrp_kfunc_failure.c
+++ b/tools/testing/selftests/bpf/progs/cgrp_kfunc_failure.c
@@ -78,7 +78,7 @@ int BPF_PROG(cgrp_kfunc_acquire_fp, struct cgroup *cgrp, const char *path)
 }
 
 SEC("kretprobe/cgroup_destroy_locked")
-__failure __msg("reg type unsupported for arg#0 function")
+__failure __msg("calling kernel function bpf_cgroup_acquire is not allowed")
 int BPF_PROG(cgrp_kfunc_acquire_unsafe_kretprobe, struct cgroup *cgrp)
 {
 	struct cgroup *acquired;
diff --git a/tools/testing/selftests/bpf/progs/task_kfunc_failure.c b/tools/testing/selftests/bpf/progs/task_kfunc_failure.c
index dcdea3127086..ad88a3796ddf 100644
--- a/tools/testing/selftests/bpf/progs/task_kfunc_failure.c
+++ b/tools/testing/selftests/bpf/progs/task_kfunc_failure.c
@@ -248,7 +248,7 @@ int BPF_PROG(task_kfunc_from_pid_no_null_check, struct task_struct *task, u64 cl
 }
 
 SEC("lsm/task_free")
-__failure __msg("reg type unsupported for arg#0 function")
+__failure __msg("R1 must be a rcu pointer")
 int BPF_PROG(task_kfunc_from_lsm_task_free, struct task_struct *task)
 {
 	struct task_struct *acquired;
-- 
cgit v1.2.3


From e26080d0da87f20222ca6712b65f95a856fadee0 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Thu, 14 Dec 2023 17:13:27 -0800
Subject: bpf: prepare btf_prepare_func_args() for handling static subprogs

Generalize btf_prepare_func_args() to support both global and static
subprogs. We are going to utilize this property in the next patch,
reusing btf_prepare_func_args() for subprog call logic instead of
reparsing BTF information in a completely separate implementation.

btf_prepare_func_args() now detects whether subprog is global or static
makes slight logic adjustments for static func cases, like not failing
fatally (-EFAULT) for conditions that are allowable for static subprogs.

Somewhat subtle (but major!) difference is the handling of pointer arguments.
Both global and static functions need to handle special context
arguments (which are pointers to predefined type names), but static
subprogs give up on any other pointers, falling back to marking subprog
as "unreliable", disabling the use of BTF type information altogether.

For global functions, though, we are assuming that such pointers to
unrecognized types are just pointers to fixed-sized memory region (or
error out if size cannot be established, like for `void *` pointers).

This patch accommodates these small differences and sets up a stage for
refactoring in the next patch, eliminating a separate BTF-based parsing
logic in btf_check_func_arg_match().

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20231215011334.2307144-4-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf_verifier.h |  5 +++++
 kernel/bpf/btf.c             | 18 +++++++++---------
 kernel/bpf/verifier.c        |  5 -----
 3 files changed, 14 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 5742e9c0a7b8..d3ea9ef04767 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -738,6 +738,11 @@ struct bpf_verifier_env {
 	char tmp_str_buf[TMP_STR_BUF_LEN];
 };
 
+static inline struct bpf_func_info_aux *subprog_aux(struct bpf_verifier_env *env, int subprog)
+{
+	return &env->prog->aux->func_info_aux[subprog];
+}
+
 static inline struct bpf_subprog_info *subprog_info(struct bpf_verifier_env *env, int subprog)
 {
 	return &env->subprog_info[subprog];
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 33d9a1c73f6e..d321340e16f1 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -6914,6 +6914,7 @@ int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog,
  */
 int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog)
 {
+	bool is_global = subprog_aux(env, subprog)->linkage == BTF_FUNC_GLOBAL;
 	struct bpf_subprog_info *sub = subprog_info(env, subprog);
 	struct bpf_verifier_log *log = &env->log;
 	struct bpf_prog *prog = env->prog;
@@ -6927,14 +6928,15 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog)
 	if (sub->args_cached)
 		return 0;
 
-	if (!prog->aux->func_info ||
-	    prog->aux->func_info_aux[subprog].linkage != BTF_FUNC_GLOBAL) {
+	if (!prog->aux->func_info) {
 		bpf_log(log, "Verifier bug\n");
 		return -EFAULT;
 	}
 
 	btf_id = prog->aux->func_info[subprog].type_id;
 	if (!btf_id) {
+		if (!is_global) /* not fatal for static funcs */
+			return -EINVAL;
 		bpf_log(log, "Global functions need valid BTF\n");
 		return -EFAULT;
 	}
@@ -6990,16 +6992,14 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog)
 			sub->args[i].arg_type = ARG_ANYTHING;
 			continue;
 		}
-		if (btf_type_is_ptr(t)) {
+		if (btf_type_is_ptr(t) && btf_get_prog_ctx_type(log, btf, t, prog_type, i)) {
+			sub->args[i].arg_type = ARG_PTR_TO_CTX;
+			continue;
+		}
+		if (is_global && btf_type_is_ptr(t)) {
 			u32 mem_size;
 
-			if (btf_get_prog_ctx_type(log, btf, t, prog_type, i)) {
-				sub->args[i].arg_type = ARG_PTR_TO_CTX;
-				continue;
-			}
-
 			t = btf_type_skip_modifiers(btf, t->type, NULL);
-
 			ref_t = btf_resolve_size(btf, t, &mem_size);
 			if (IS_ERR(ref_t)) {
 				bpf_log(log,
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c26e9ab5226c..6c9ecb86a8d9 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -437,11 +437,6 @@ static const char *subprog_name(const struct bpf_verifier_env *env, int subprog)
 	return btf_type_name(env->prog->aux->btf, info->type_id);
 }
 
-static struct bpf_func_info_aux *subprog_aux(const struct bpf_verifier_env *env, int subprog)
-{
-	return &env->prog->aux->func_info_aux[subprog];
-}
-
 static void mark_subprog_exc_cb(struct bpf_verifier_env *env, int subprog)
 {
 	struct bpf_subprog_info *info = subprog_info(env, subprog);
-- 
cgit v1.2.3


From c5a7244759b1eeacc59d0426fb73859afa942d0d Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Thu, 14 Dec 2023 17:13:28 -0800
Subject: bpf: move subprog call logic back to verifier.c

Subprog call logic in btf_check_subprog_call() currently has both a lot
of BTF parsing logic (which is, presumably, what justified putting it
into btf.c), but also a bunch of register state checks, some of each
utilize deep verifier logic helpers, necessarily exported from
verifier.c: check_ptr_off_reg(), check_func_arg_reg_off(),
and check_mem_reg().

Going forward, btf_check_subprog_call() will have a minimum of
BTF-related logic, but will get more internal verifier logic related to
register state manipulation. So move it into verifier.c to minimize
amount of verifier-specific logic exposed to btf.c.

We do this move before refactoring btf_check_func_arg_match() to
preserve as much history post-refactoring as possible.

No functional changes.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20231215011334.2307144-5-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h          |   2 -
 include/linux/bpf_verifier.h |   8 ---
 kernel/bpf/btf.c             | 139 ---------------------------------------
 kernel/bpf/verifier.c        | 153 +++++++++++++++++++++++++++++++++++++++++--
 4 files changed, 146 insertions(+), 156 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index d0d7eff22b8a..7671530d6e4e 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2466,8 +2466,6 @@ int btf_distill_func_proto(struct bpf_verifier_log *log,
 			   struct btf_func_model *m);
 
 struct bpf_reg_state;
-int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog,
-			   struct bpf_reg_state *regs);
 int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog);
 int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog,
 			 struct btf *btf, const struct btf_type *t);
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index d3ea9ef04767..d07d857ca67f 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -785,14 +785,6 @@ bpf_prog_offload_replace_insn(struct bpf_verifier_env *env, u32 off,
 void
 bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt);
 
-int check_ptr_off_reg(struct bpf_verifier_env *env,
-		      const struct bpf_reg_state *reg, int regno);
-int check_func_arg_reg_off(struct bpf_verifier_env *env,
-			   const struct bpf_reg_state *reg, int regno,
-			   enum bpf_arg_type arg_type);
-int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
-		   u32 regno, u32 mem_size);
-
 /* this lives here instead of in bpf.h because it needs to dereference tgt_prog */
 static inline u64 bpf_trampoline_compute_key(const struct bpf_prog *tgt_prog,
 					     struct btf *btf, u32 btf_id)
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index d321340e16f1..341811bcca53 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -6765,145 +6765,6 @@ int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *pr
 	return btf_check_func_type_match(log, btf1, t1, btf2, t2);
 }
 
-static int btf_check_func_arg_match(struct bpf_verifier_env *env,
-				    const struct btf *btf, u32 func_id,
-				    struct bpf_reg_state *regs,
-				    bool ptr_to_mem_ok)
-{
-	enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
-	struct bpf_verifier_log *log = &env->log;
-	const char *func_name, *ref_tname;
-	const struct btf_type *t, *ref_t;
-	const struct btf_param *args;
-	u32 i, nargs, ref_id;
-	int ret;
-
-	t = btf_type_by_id(btf, func_id);
-	if (!t || !btf_type_is_func(t)) {
-		/* These checks were already done by the verifier while loading
-		 * struct bpf_func_info or in add_kfunc_call().
-		 */
-		bpf_log(log, "BTF of func_id %u doesn't point to KIND_FUNC\n",
-			func_id);
-		return -EFAULT;
-	}
-	func_name = btf_name_by_offset(btf, t->name_off);
-
-	t = btf_type_by_id(btf, t->type);
-	if (!t || !btf_type_is_func_proto(t)) {
-		bpf_log(log, "Invalid BTF of func %s\n", func_name);
-		return -EFAULT;
-	}
-	args = (const struct btf_param *)(t + 1);
-	nargs = btf_type_vlen(t);
-	if (nargs > MAX_BPF_FUNC_REG_ARGS) {
-		bpf_log(log, "Function %s has %d > %d args\n", func_name, nargs,
-			MAX_BPF_FUNC_REG_ARGS);
-		return -EINVAL;
-	}
-
-	/* check that BTF function arguments match actual types that the
-	 * verifier sees.
-	 */
-	for (i = 0; i < nargs; i++) {
-		enum bpf_arg_type arg_type = ARG_DONTCARE;
-		u32 regno = i + 1;
-		struct bpf_reg_state *reg = &regs[regno];
-
-		t = btf_type_skip_modifiers(btf, args[i].type, NULL);
-		if (btf_type_is_scalar(t)) {
-			if (reg->type == SCALAR_VALUE)
-				continue;
-			bpf_log(log, "R%d is not a scalar\n", regno);
-			return -EINVAL;
-		}
-
-		if (!btf_type_is_ptr(t)) {
-			bpf_log(log, "Unrecognized arg#%d type %s\n",
-				i, btf_type_str(t));
-			return -EINVAL;
-		}
-
-		ref_t = btf_type_skip_modifiers(btf, t->type, &ref_id);
-		ref_tname = btf_name_by_offset(btf, ref_t->name_off);
-
-		ret = check_func_arg_reg_off(env, reg, regno, arg_type);
-		if (ret < 0)
-			return ret;
-
-		if (btf_get_prog_ctx_type(log, btf, t, prog_type, i)) {
-			/* If function expects ctx type in BTF check that caller
-			 * is passing PTR_TO_CTX.
-			 */
-			if (reg->type != PTR_TO_CTX) {
-				bpf_log(log,
-					"arg#%d expected pointer to ctx, but got %s\n",
-					i, btf_type_str(t));
-				return -EINVAL;
-			}
-		} else if (ptr_to_mem_ok) {
-			const struct btf_type *resolve_ret;
-			u32 type_size;
-
-			resolve_ret = btf_resolve_size(btf, ref_t, &type_size);
-			if (IS_ERR(resolve_ret)) {
-				bpf_log(log,
-					"arg#%d reference type('%s %s') size cannot be determined: %ld\n",
-					i, btf_type_str(ref_t), ref_tname,
-					PTR_ERR(resolve_ret));
-				return -EINVAL;
-			}
-
-			if (check_mem_reg(env, reg, regno, type_size))
-				return -EINVAL;
-		} else {
-			bpf_log(log, "reg type unsupported for arg#%d function %s#%d\n", i,
-				func_name, func_id);
-			return -EINVAL;
-		}
-	}
-
-	return 0;
-}
-
-/* Compare BTF of a function call with given bpf_reg_state.
- * Returns:
- * EFAULT - there is a verifier bug. Abort verification.
- * EINVAL - there is a type mismatch or BTF is not available.
- * 0 - BTF matches with what bpf_reg_state expects.
- * Only PTR_TO_CTX and SCALAR_VALUE states are recognized.
- */
-int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog,
-			   struct bpf_reg_state *regs)
-{
-	struct bpf_prog *prog = env->prog;
-	struct btf *btf = prog->aux->btf;
-	bool is_global;
-	u32 btf_id;
-	int err;
-
-	if (!prog->aux->func_info)
-		return -EINVAL;
-
-	btf_id = prog->aux->func_info[subprog].type_id;
-	if (!btf_id)
-		return -EFAULT;
-
-	if (prog->aux->func_info_aux[subprog].unreliable)
-		return -EINVAL;
-
-	is_global = prog->aux->func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL;
-	err = btf_check_func_arg_match(env, btf, btf_id, regs, is_global);
-
-	/* Compiler optimizations can remove arguments from static functions
-	 * or mismatched type can be passed into a global function.
-	 * In such cases mark the function as unreliable from BTF point of view.
-	 */
-	if (err)
-		prog->aux->func_info_aux[subprog].unreliable = true;
-	return err;
-}
-
 /* Process BTF of a function to produce high-level expectation of function
  * arguments (like ARG_PTR_TO_CTX, or ARG_PTR_TO_MEM, etc). This information
  * is cached in subprog info for reuse.
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 6c9ecb86a8d9..f48e49f2d482 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5127,8 +5127,8 @@ static int __check_ptr_off_reg(struct bpf_verifier_env *env,
 	return 0;
 }
 
-int check_ptr_off_reg(struct bpf_verifier_env *env,
-		      const struct bpf_reg_state *reg, int regno)
+static int check_ptr_off_reg(struct bpf_verifier_env *env,
+		             const struct bpf_reg_state *reg, int regno)
 {
 	return __check_ptr_off_reg(env, reg, regno, false);
 }
@@ -7300,8 +7300,8 @@ static int check_mem_size_reg(struct bpf_verifier_env *env,
 	return err;
 }
 
-int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
-		   u32 regno, u32 mem_size)
+static int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
+			 u32 regno, u32 mem_size)
 {
 	bool may_be_null = type_may_be_null(reg->type);
 	struct bpf_reg_state saved_reg;
@@ -8286,9 +8286,9 @@ reg_find_field_offset(const struct bpf_reg_state *reg, s32 off, u32 fields)
 	return field;
 }
 
-int check_func_arg_reg_off(struct bpf_verifier_env *env,
-			   const struct bpf_reg_state *reg, int regno,
-			   enum bpf_arg_type arg_type)
+static int check_func_arg_reg_off(struct bpf_verifier_env *env,
+				  const struct bpf_reg_state *reg, int regno,
+				  enum bpf_arg_type arg_type)
 {
 	u32 type = reg->type;
 
@@ -9249,6 +9249,145 @@ err_out:
 	return err;
 }
 
+static int btf_check_func_arg_match(struct bpf_verifier_env *env,
+				    const struct btf *btf, u32 func_id,
+				    struct bpf_reg_state *regs,
+				    bool ptr_to_mem_ok)
+{
+	enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
+	struct bpf_verifier_log *log = &env->log;
+	const char *func_name, *ref_tname;
+	const struct btf_type *t, *ref_t;
+	const struct btf_param *args;
+	u32 i, nargs, ref_id;
+	int ret;
+
+	t = btf_type_by_id(btf, func_id);
+	if (!t || !btf_type_is_func(t)) {
+		/* These checks were already done by the verifier while loading
+		 * struct bpf_func_info or in add_kfunc_call().
+		 */
+		bpf_log(log, "BTF of func_id %u doesn't point to KIND_FUNC\n",
+			func_id);
+		return -EFAULT;
+	}
+	func_name = btf_name_by_offset(btf, t->name_off);
+
+	t = btf_type_by_id(btf, t->type);
+	if (!t || !btf_type_is_func_proto(t)) {
+		bpf_log(log, "Invalid BTF of func %s\n", func_name);
+		return -EFAULT;
+	}
+	args = (const struct btf_param *)(t + 1);
+	nargs = btf_type_vlen(t);
+	if (nargs > MAX_BPF_FUNC_REG_ARGS) {
+		bpf_log(log, "Function %s has %d > %d args\n", func_name, nargs,
+			MAX_BPF_FUNC_REG_ARGS);
+		return -EINVAL;
+	}
+
+	/* check that BTF function arguments match actual types that the
+	 * verifier sees.
+	 */
+	for (i = 0; i < nargs; i++) {
+		enum bpf_arg_type arg_type = ARG_DONTCARE;
+		u32 regno = i + 1;
+		struct bpf_reg_state *reg = &regs[regno];
+
+		t = btf_type_skip_modifiers(btf, args[i].type, NULL);
+		if (btf_type_is_scalar(t)) {
+			if (reg->type == SCALAR_VALUE)
+				continue;
+			bpf_log(log, "R%d is not a scalar\n", regno);
+			return -EINVAL;
+		}
+
+		if (!btf_type_is_ptr(t)) {
+			bpf_log(log, "Unrecognized arg#%d type %s\n",
+				i, btf_type_str(t));
+			return -EINVAL;
+		}
+
+		ref_t = btf_type_skip_modifiers(btf, t->type, &ref_id);
+		ref_tname = btf_name_by_offset(btf, ref_t->name_off);
+
+		ret = check_func_arg_reg_off(env, reg, regno, arg_type);
+		if (ret < 0)
+			return ret;
+
+		if (btf_get_prog_ctx_type(log, btf, t, prog_type, i)) {
+			/* If function expects ctx type in BTF check that caller
+			 * is passing PTR_TO_CTX.
+			 */
+			if (reg->type != PTR_TO_CTX) {
+				bpf_log(log,
+					"arg#%d expected pointer to ctx, but got %s\n",
+					i, btf_type_str(t));
+				return -EINVAL;
+			}
+		} else if (ptr_to_mem_ok) {
+			const struct btf_type *resolve_ret;
+			u32 type_size;
+
+			resolve_ret = btf_resolve_size(btf, ref_t, &type_size);
+			if (IS_ERR(resolve_ret)) {
+				bpf_log(log,
+					"arg#%d reference type('%s %s') size cannot be determined: %ld\n",
+					i, btf_type_str(ref_t), ref_tname,
+					PTR_ERR(resolve_ret));
+				return -EINVAL;
+			}
+
+			if (check_mem_reg(env, reg, regno, type_size))
+				return -EINVAL;
+		} else {
+			bpf_log(log, "reg type unsupported for arg#%d function %s#%d\n", i,
+				func_name, func_id);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+/* Compare BTF of a function call with given bpf_reg_state.
+ * Returns:
+ * EFAULT - there is a verifier bug. Abort verification.
+ * EINVAL - there is a type mismatch or BTF is not available.
+ * 0 - BTF matches with what bpf_reg_state expects.
+ * Only PTR_TO_CTX and SCALAR_VALUE states are recognized.
+ */
+static int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog,
+			          struct bpf_reg_state *regs)
+{
+	struct bpf_prog *prog = env->prog;
+	struct btf *btf = prog->aux->btf;
+	bool is_global;
+	u32 btf_id;
+	int err;
+
+	if (!prog->aux->func_info)
+		return -EINVAL;
+
+	btf_id = prog->aux->func_info[subprog].type_id;
+	if (!btf_id)
+		return -EFAULT;
+
+	if (prog->aux->func_info_aux[subprog].unreliable)
+		return -EINVAL;
+
+	is_global = prog->aux->func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL;
+	err = btf_check_func_arg_match(env, btf, btf_id, regs, is_global);
+
+	/* Compiler optimizations can remove arguments from static functions
+	 * or mismatched type can be passed into a global function.
+	 * In such cases mark the function as unreliable from BTF point of view.
+	 */
+	if (err)
+		prog->aux->func_info_aux[subprog].unreliable = true;
+	return err;
+}
+
 static int push_callback_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 			      int insn_idx, int subprog,
 			      set_callee_state_fn set_callee_state_cb)
-- 
cgit v1.2.3


From 7437bb73f087e5f216f9c6603f5149d354e315af Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 17 Dec 2023 17:53:57 +0100
Subject: block: remove support for the host aware zone model

When zones were first added the SCSI and ATA specs, two different
models were supported (in addition to the drive managed one that
is invisible to the host):

 - host managed where non-conventional zones there is strict requirement
   to write at the write pointer, or else an error is returned
 - host aware where a write point is maintained if writes always happen
   at it, otherwise it is left in an under-defined state and the
   sequential write preferred zones behave like conventional zones
   (probably very badly performing ones, though)

Not surprisingly this lukewarm model didn't prove to be very useful and
was finally removed from the ZBC and SBC specs (NVMe never implemented
it).  Due to to the easily disappearing write pointer host software
could never rely on the write pointer to actually be useful for say
recovery.

Fortunately only a few HDD prototypes shipped using this model which
never made it to mass production.  Drop the support before it is too
late.  Note that any such host aware prototype HDD can still be used
with Linux as we'll now treat it as a conventional HDD.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Link: https://lore.kernel.org/r/20231217165359.604246-4-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-settings.c           | 67 ++++++------------------------------------
 block/blk-sysfs.c              |  9 ++----
 block/partitions/core.c        | 12 ++------
 drivers/block/null_blk/zoned.c |  2 +-
 drivers/block/ublk_drv.c       |  2 +-
 drivers/block/virtio_blk.c     |  2 +-
 drivers/md/dm-kcopyd.c         |  2 +-
 drivers/md/dm-table.c          | 45 +++++++++++++---------------
 drivers/md/dm-zoned-metadata.c |  7 ++---
 drivers/md/dm-zoned-target.c   |  4 +--
 drivers/nvme/host/zns.c        |  2 +-
 drivers/scsi/scsi_debug.c      | 27 ++++++++---------
 drivers/scsi/sd.c              | 45 +++++++++++++---------------
 drivers/scsi/sd_zbc.c          | 16 +---------
 fs/btrfs/zoned.c               | 23 ++-------------
 fs/btrfs/zoned.h               |  2 +-
 fs/f2fs/data.c                 |  2 +-
 fs/f2fs/super.c                | 17 +++++------
 include/linux/blkdev.h         | 37 ++---------------------
 19 files changed, 92 insertions(+), 231 deletions(-)

(limited to 'include')

diff --git a/block/blk-settings.c b/block/blk-settings.c
index 09e3a4d5e4d2..50e9efb59f67 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -56,7 +56,7 @@ void blk_set_default_limits(struct queue_limits *lim)
 	lim->alignment_offset = 0;
 	lim->io_opt = 0;
 	lim->misaligned = 0;
-	lim->zoned = BLK_ZONED_NONE;
+	lim->zoned = false;
 	lim->zone_write_granularity = 0;
 	lim->dma_alignment = 511;
 }
@@ -880,79 +880,30 @@ bool blk_queue_can_use_dma_map_merging(struct request_queue *q,
 }
 EXPORT_SYMBOL_GPL(blk_queue_can_use_dma_map_merging);
 
-static bool disk_has_partitions(struct gendisk *disk)
-{
-	unsigned long idx;
-	struct block_device *part;
-	bool ret = false;
-
-	rcu_read_lock();
-	xa_for_each(&disk->part_tbl, idx, part) {
-		if (bdev_is_partition(part)) {
-			ret = true;
-			break;
-		}
-	}
-	rcu_read_unlock();
-
-	return ret;
-}
-
 /**
  * disk_set_zoned - configure the zoned model for a disk
  * @disk:	the gendisk of the queue to configure
- * @model:	the zoned model to set
- *
- * Set the zoned model of @disk to @model.
+ * @zoned:	zoned or not.
  *
- * When @model is BLK_ZONED_HM (host managed), this should be called only
- * if zoned block device support is enabled (CONFIG_BLK_DEV_ZONED option).
- * If @model specifies BLK_ZONED_HA (host aware), the effective model used
- * depends on CONFIG_BLK_DEV_ZONED settings and on the existence of partitions
- * on the disk.
+ * When @zoned is %true, this should be called only if zoned block device
+ * support is enabled (CONFIG_BLK_DEV_ZONED option).
  */
-void disk_set_zoned(struct gendisk *disk, enum blk_zoned_model model)
+void disk_set_zoned(struct gendisk *disk, bool zoned)
 {
 	struct request_queue *q = disk->queue;
-	unsigned int old_model = q->limits.zoned;
 
-	switch (model) {
-	case BLK_ZONED_HM:
-		/*
-		 * Host managed devices are supported only if
-		 * CONFIG_BLK_DEV_ZONED is enabled.
-		 */
+	if (zoned) {
 		WARN_ON_ONCE(!IS_ENABLED(CONFIG_BLK_DEV_ZONED));
-		break;
-	case BLK_ZONED_HA:
-		/*
-		 * Host aware devices can be treated either as regular block
-		 * devices (similar to drive managed devices) or as zoned block
-		 * devices to take advantage of the zone command set, similarly
-		 * to host managed devices. We try the latter if there are no
-		 * partitions and zoned block device support is enabled, else
-		 * we do nothing special as far as the block layer is concerned.
-		 */
-		if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED) ||
-		    disk_has_partitions(disk))
-			model = BLK_ZONED_NONE;
-		break;
-	case BLK_ZONED_NONE:
-	default:
-		if (WARN_ON_ONCE(model != BLK_ZONED_NONE))
-			model = BLK_ZONED_NONE;
-		break;
-	}
 
-	q->limits.zoned = model;
-	if (model != BLK_ZONED_NONE) {
 		/*
 		 * Set the zone write granularity to the device logical block
 		 * size by default. The driver can change this value if needed.
 		 */
+		q->limits.zoned = true;
 		blk_queue_zone_write_granularity(q,
 						queue_logical_block_size(q));
-	} else if (old_model != BLK_ZONED_NONE) {
+	} else if (q->limits.zoned) {
+		q->limits.zoned = false;
 		disk_clear_zone_settings(disk);
 	}
 }
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 63e481262336..d5e669a401b0 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -309,14 +309,9 @@ QUEUE_SYSFS_BIT_FNS(stable_writes, STABLE_WRITES, 0);
 
 static ssize_t queue_zoned_show(struct request_queue *q, char *page)
 {
-	switch (blk_queue_zoned_model(q)) {
-	case BLK_ZONED_HA:
-		return sprintf(page, "host-aware\n");
-	case BLK_ZONED_HM:
+	if (blk_queue_is_zoned(q))
 		return sprintf(page, "host-managed\n");
-	default:
-		return sprintf(page, "none\n");
-	}
+	return sprintf(page, "none\n");
 }
 
 static ssize_t queue_nr_zones_show(struct request_queue *q, char *page)
diff --git a/block/partitions/core.c b/block/partitions/core.c
index f47ffcfdfcec..e6ac73617f3e 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -305,18 +305,10 @@ static struct block_device *add_partition(struct gendisk *disk, int partno,
 	 * Partitions are not supported on zoned block devices that are used as
 	 * such.
 	 */
-	switch (disk->queue->limits.zoned) {
-	case BLK_ZONED_HM:
+	if (bdev_is_zoned(disk->part0)) {
 		pr_warn("%s: partitions not supported on host managed zoned block device\n",
 			disk->disk_name);
 		return ERR_PTR(-ENXIO);
-	case BLK_ZONED_HA:
-		pr_info("%s: disabling host aware zoned block device support due to partitions\n",
-			disk->disk_name);
-		disk_set_zoned(disk, BLK_ZONED_NONE);
-		break;
-	case BLK_ZONED_NONE:
-		break;
 	}
 
 	if (xa_load(&disk->part_tbl, partno))
@@ -613,7 +605,7 @@ static int blk_add_partitions(struct gendisk *disk)
 	/*
 	 * Partitions are not supported on host managed zoned block devices.
 	 */
-	if (disk->queue->limits.zoned == BLK_ZONED_HM) {
+	if (bdev_is_zoned(disk->part0)) {
 		pr_warn("%s: ignoring partition table on host managed zoned block device\n",
 			disk->disk_name);
 		ret = 0;
diff --git a/drivers/block/null_blk/zoned.c b/drivers/block/null_blk/zoned.c
index 55c5b48bc276..369eb1e78bb5 100644
--- a/drivers/block/null_blk/zoned.c
+++ b/drivers/block/null_blk/zoned.c
@@ -159,7 +159,7 @@ int null_register_zoned_dev(struct nullb *nullb)
 	struct nullb_device *dev = nullb->dev;
 	struct request_queue *q = nullb->q;
 
-	disk_set_zoned(nullb->disk, BLK_ZONED_HM);
+	disk_set_zoned(nullb->disk, true);
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
 	blk_queue_required_elevator_features(q, ELEVATOR_F_ZBD_SEQ_WRITE);
 	blk_queue_chunk_sectors(q, dev->zone_size_sects);
diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 83600b45e12a..24fb95f19d52 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -250,7 +250,7 @@ static int ublk_dev_param_zoned_apply(struct ublk_device *ub)
 {
 	const struct ublk_param_zoned *p = &ub->params.zoned;
 
-	disk_set_zoned(ub->ub_disk, BLK_ZONED_HM);
+	disk_set_zoned(ub->ub_disk, true);
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, ub->ub_disk->queue);
 	blk_queue_required_elevator_features(ub->ub_disk->queue,
 					     ELEVATOR_F_ZBD_SEQ_WRITE);
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index a28f1687066b..19a4f20bd1c2 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -730,7 +730,7 @@ static int virtblk_probe_zoned_device(struct virtio_device *vdev,
 
 	dev_dbg(&vdev->dev, "probing host-managed zoned device\n");
 
-	disk_set_zoned(vblk->disk, BLK_ZONED_HM);
+	disk_set_zoned(vblk->disk, true);
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
 
 	virtio_cread(vdev, struct virtio_blk_config,
diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c
index d01807c50f20..36bcfdccae04 100644
--- a/drivers/md/dm-kcopyd.c
+++ b/drivers/md/dm-kcopyd.c
@@ -807,7 +807,7 @@ void dm_kcopyd_copy(struct dm_kcopyd_client *kc, struct dm_io_region *from,
 	 */
 	if (!(job->flags & BIT(DM_KCOPYD_WRITE_SEQ))) {
 		for (i = 0; i < job->num_dests; i++) {
-			if (bdev_zoned_model(dests[i].bdev) == BLK_ZONED_HM) {
+			if (bdev_is_zoned(dests[i].bdev)) {
 				job->flags |= BIT(DM_KCOPYD_WRITE_SEQ);
 				break;
 			}
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 198d38b53322..260b5b8f2b0d 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1579,21 +1579,18 @@ bool dm_table_has_no_data_devices(struct dm_table *t)
 	return true;
 }
 
-static int device_not_zoned_model(struct dm_target *ti, struct dm_dev *dev,
-				  sector_t start, sector_t len, void *data)
+static int device_not_zoned(struct dm_target *ti, struct dm_dev *dev,
+			    sector_t start, sector_t len, void *data)
 {
-	struct request_queue *q = bdev_get_queue(dev->bdev);
-	enum blk_zoned_model *zoned_model = data;
+	bool *zoned = data;
 
-	return blk_queue_zoned_model(q) != *zoned_model;
+	return bdev_is_zoned(dev->bdev) != *zoned;
 }
 
 static int device_is_zoned_model(struct dm_target *ti, struct dm_dev *dev,
 				 sector_t start, sector_t len, void *data)
 {
-	struct request_queue *q = bdev_get_queue(dev->bdev);
-
-	return blk_queue_zoned_model(q) != BLK_ZONED_NONE;
+	return bdev_is_zoned(dev->bdev);
 }
 
 /*
@@ -1603,8 +1600,7 @@ static int device_is_zoned_model(struct dm_target *ti, struct dm_dev *dev,
  * has the DM_TARGET_MIXED_ZONED_MODEL feature set, the devices can have any
  * zoned model with all zoned devices having the same zone size.
  */
-static bool dm_table_supports_zoned_model(struct dm_table *t,
-					  enum blk_zoned_model zoned_model)
+static bool dm_table_supports_zoned(struct dm_table *t, bool zoned)
 {
 	for (unsigned int i = 0; i < t->num_targets; i++) {
 		struct dm_target *ti = dm_table_get_target(t, i);
@@ -1623,11 +1619,11 @@ static bool dm_table_supports_zoned_model(struct dm_table *t,
 
 		if (dm_target_supports_zoned_hm(ti->type)) {
 			if (!ti->type->iterate_devices ||
-			    ti->type->iterate_devices(ti, device_not_zoned_model,
-						      &zoned_model))
+			    ti->type->iterate_devices(ti, device_not_zoned,
+						      &zoned))
 				return false;
 		} else if (!dm_target_supports_mixed_zoned_model(ti->type)) {
-			if (zoned_model == BLK_ZONED_HM)
+			if (zoned)
 				return false;
 		}
 	}
@@ -1650,14 +1646,13 @@ static int device_not_matches_zone_sectors(struct dm_target *ti, struct dm_dev *
  * zone sectors, if the destination device is a zoned block device, it shall
  * have the specified zone_sectors.
  */
-static int validate_hardware_zoned_model(struct dm_table *t,
-					 enum blk_zoned_model zoned_model,
-					 unsigned int zone_sectors)
+static int validate_hardware_zoned(struct dm_table *t, bool zoned,
+				   unsigned int zone_sectors)
 {
-	if (zoned_model == BLK_ZONED_NONE)
+	if (!zoned)
 		return 0;
 
-	if (!dm_table_supports_zoned_model(t, zoned_model)) {
+	if (!dm_table_supports_zoned(t, zoned)) {
 		DMERR("%s: zoned model is not consistent across all devices",
 		      dm_device_name(t->md));
 		return -EINVAL;
@@ -1683,8 +1678,8 @@ int dm_calculate_queue_limits(struct dm_table *t,
 			      struct queue_limits *limits)
 {
 	struct queue_limits ti_limits;
-	enum blk_zoned_model zoned_model = BLK_ZONED_NONE;
 	unsigned int zone_sectors = 0;
+	bool zoned = false;
 
 	blk_set_stacking_limits(limits);
 
@@ -1706,12 +1701,12 @@ int dm_calculate_queue_limits(struct dm_table *t,
 		ti->type->iterate_devices(ti, dm_set_device_limits,
 					  &ti_limits);
 
-		if (zoned_model == BLK_ZONED_NONE && ti_limits.zoned != BLK_ZONED_NONE) {
+		if (!zoned && ti_limits.zoned) {
 			/*
 			 * After stacking all limits, validate all devices
 			 * in table support this zoned model and zone sectors.
 			 */
-			zoned_model = ti_limits.zoned;
+			zoned = ti_limits.zoned;
 			zone_sectors = ti_limits.chunk_sectors;
 		}
 
@@ -1744,18 +1739,18 @@ combine_limits:
 	 * Verify that the zoned model and zone sectors, as determined before
 	 * any .io_hints override, are the same across all devices in the table.
 	 * - this is especially relevant if .io_hints is emulating a disk-managed
-	 *   zoned model (aka BLK_ZONED_NONE) on host-managed zoned block devices.
+	 *   zoned model on host-managed zoned block devices.
 	 * BUT...
 	 */
-	if (limits->zoned != BLK_ZONED_NONE) {
+	if (limits->zoned) {
 		/*
 		 * ...IF the above limits stacking determined a zoned model
 		 * validate that all of the table's devices conform to it.
 		 */
-		zoned_model = limits->zoned;
+		zoned = limits->zoned;
 		zone_sectors = limits->chunk_sectors;
 	}
-	if (validate_hardware_zoned_model(t, zoned_model, zone_sectors))
+	if (validate_hardware_zoned(t, zoned, zone_sectors))
 		return -EINVAL;
 
 	return validate_hardware_logical_block_alignment(t, limits);
diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c
index 60a4dc01ea18..fdfe30f7b697 100644
--- a/drivers/md/dm-zoned-metadata.c
+++ b/drivers/md/dm-zoned-metadata.c
@@ -2836,12 +2836,11 @@ static void dmz_print_dev(struct dmz_metadata *zmd, int num)
 {
 	struct dmz_dev *dev = &zmd->dev[num];
 
-	if (bdev_zoned_model(dev->bdev) == BLK_ZONED_NONE)
+	if (!bdev_is_zoned(dev->bdev))
 		dmz_dev_info(dev, "Regular block device");
 	else
-		dmz_dev_info(dev, "Host-%s zoned block device",
-			     bdev_zoned_model(dev->bdev) == BLK_ZONED_HA ?
-			     "aware" : "managed");
+		dmz_dev_info(dev, "Host-managed zoned block device");
+
 	if (zmd->sb_version > 1) {
 		sector_t sector_offset =
 			dev->zone_offset << zmd->zone_nr_sectors_shift;
diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c
index b487f7acc860..621794a9edd6 100644
--- a/drivers/md/dm-zoned-target.c
+++ b/drivers/md/dm-zoned-target.c
@@ -702,7 +702,7 @@ static int dmz_get_zoned_device(struct dm_target *ti, char *path,
 	}
 
 	bdev = ddev->bdev;
-	if (bdev_zoned_model(bdev) == BLK_ZONED_NONE) {
+	if (!bdev_is_zoned(bdev)) {
 		if (nr_devs == 1) {
 			ti->error = "Invalid regular device";
 			goto err;
@@ -1010,7 +1010,7 @@ static void dmz_io_hints(struct dm_target *ti, struct queue_limits *limits)
 	limits->max_sectors = chunk_sectors;
 
 	/* We are exposing a drive-managed zoned block device */
-	limits->zoned = BLK_ZONED_NONE;
+	limits->zoned = false;
 }
 
 /*
diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c
index ec8557810c21..6d4c440e97e2 100644
--- a/drivers/nvme/host/zns.c
+++ b/drivers/nvme/host/zns.c
@@ -108,7 +108,7 @@ int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf)
 		goto free_data;
 	}
 
-	disk_set_zoned(ns->disk, BLK_ZONED_HM);
+	disk_set_zoned(ns->disk, true);
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
 	disk_set_max_open_zones(ns->disk, le32_to_cpu(id->mor) + 1);
 	disk_set_max_active_zones(ns->disk, le32_to_cpu(id->mar) + 1);
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 6d8218a44122..d03d66f11493 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -339,7 +339,7 @@ struct sdebug_dev_info {
 	bool used;
 
 	/* For ZBC devices */
-	enum blk_zoned_model zmodel;
+	bool zoned;
 	unsigned int zcap;
 	unsigned int zsize;
 	unsigned int zsize_shift;
@@ -844,8 +844,11 @@ static bool write_since_sync;
 static bool sdebug_statistics = DEF_STATISTICS;
 static bool sdebug_wp;
 static bool sdebug_allow_restart;
-/* Following enum: 0: no zbc, def; 1: host aware; 2: host managed */
-static enum blk_zoned_model sdeb_zbc_model = BLK_ZONED_NONE;
+static enum {
+	BLK_ZONED_NONE	= 0,
+	BLK_ZONED_HA	= 1,
+	BLK_ZONED_HM	= 2,
+} sdeb_zbc_model = BLK_ZONED_NONE;
 static char *sdeb_zbc_model_s;
 
 enum sam_lun_addr_method {SAM_LUN_AM_PERIPHERAL = 0x0,
@@ -1815,8 +1818,6 @@ static int inquiry_vpd_b1(struct sdebug_dev_info *devip, unsigned char *arr)
 	arr[1] = 1;	/* non rotating medium (e.g. solid state) */
 	arr[2] = 0;
 	arr[3] = 5;	/* less than 1.8" */
-	if (devip->zmodel == BLK_ZONED_HA)
-		arr[4] = 1 << 4;	/* zoned field = 01b */
 
 	return 0x3c;
 }
@@ -1883,7 +1884,7 @@ static int resp_inquiry(struct scsi_cmnd *scp, struct sdebug_dev_info *devip)
 	if (! arr)
 		return DID_REQUEUE << 16;
 	is_disk = (sdebug_ptype == TYPE_DISK);
-	is_zbc = (devip->zmodel != BLK_ZONED_NONE);
+	is_zbc = devip->zoned;
 	is_disk_zbc = (is_disk || is_zbc);
 	have_wlun = scsi_is_wlun(scp->device->lun);
 	if (have_wlun)
@@ -2195,7 +2196,7 @@ static int resp_readcap16(struct scsi_cmnd *scp,
 	 * Since the scsi_debug READ CAPACITY implementation always reports the
 	 * total disk capacity, set RC BASIS = 1 for host-managed ZBC devices.
 	 */
-	if (devip->zmodel == BLK_ZONED_HM)
+	if (devip->zoned)
 		arr[12] |= 1 << 4;
 
 	arr[15] = sdebug_lowest_aligned & 0xff;
@@ -2648,7 +2649,7 @@ static int resp_mode_sense(struct scsi_cmnd *scp,
 	msense_6 = (MODE_SENSE == cmd[0]);
 	llbaa = msense_6 ? false : !!(cmd[1] & 0x10);
 	is_disk = (sdebug_ptype == TYPE_DISK);
-	is_zbc = (devip->zmodel != BLK_ZONED_NONE);
+	is_zbc = devip->zoned;
 	if ((is_disk || is_zbc) && !dbd)
 		bd_len = llbaa ? 16 : 8;
 	else
@@ -3194,8 +3195,6 @@ static int check_zbc_access_params(struct scsi_cmnd *scp,
 	struct sdeb_zone_state *zsp_end = zbc_zone(devip, lba + num - 1);
 
 	if (!write) {
-		if (devip->zmodel == BLK_ZONED_HA)
-			return 0;
 		/* For host-managed, reads cannot cross zone types boundaries */
 		if (zsp->z_type != zsp_end->z_type) {
 			mk_sense_buffer(scp, ILLEGAL_REQUEST,
@@ -5322,7 +5321,7 @@ static int sdebug_device_create_zones(struct sdebug_dev_info *devip)
 	if (devip->zcap < devip->zsize)
 		devip->nr_zones += devip->nr_seq_zones;
 
-	if (devip->zmodel == BLK_ZONED_HM) {
+	if (devip->zoned) {
 		/* zbc_max_open_zones can be 0, meaning "not reported" */
 		if (sdeb_zbc_max_open >= devip->nr_zones - 1)
 			devip->max_open = (devip->nr_zones - 1) / 2;
@@ -5347,7 +5346,7 @@ static int sdebug_device_create_zones(struct sdebug_dev_info *devip)
 			zsp->z_size =
 				min_t(u64, devip->zsize, capacity - zstart);
 		} else if ((zstart & (devip->zsize - 1)) == 0) {
-			if (devip->zmodel == BLK_ZONED_HM)
+			if (devip->zoned)
 				zsp->z_type = ZBC_ZTYPE_SWR;
 			else
 				zsp->z_type = ZBC_ZTYPE_SWP;
@@ -5390,13 +5389,13 @@ static struct sdebug_dev_info *sdebug_device_create(
 		}
 		devip->sdbg_host = sdbg_host;
 		if (sdeb_zbc_in_use) {
-			devip->zmodel = sdeb_zbc_model;
+			devip->zoned = sdeb_zbc_model == BLK_ZONED_HM;
 			if (sdebug_device_create_zones(devip)) {
 				kfree(devip);
 				return NULL;
 			}
 		} else {
-			devip->zmodel = BLK_ZONED_NONE;
+			devip->zoned = false;
 		}
 		devip->create_ts = ktime_get_boottime();
 		atomic_set(&devip->stopped, (sdeb_tur_ms_to_ready > 0 ? 2 : 0));
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index fa00dd503cbf..19a19eb277f5 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -3117,7 +3117,6 @@ static void sd_read_block_characteristics(struct scsi_disk *sdkp)
 	struct request_queue *q = sdkp->disk->queue;
 	struct scsi_vpd *vpd;
 	u16 rot;
-	u8 zoned;
 
 	rcu_read_lock();
 	vpd = rcu_dereference(sdkp->device->vpd_pgb1);
@@ -3128,7 +3127,7 @@ static void sd_read_block_characteristics(struct scsi_disk *sdkp)
 	}
 
 	rot = get_unaligned_be16(&vpd->data[4]);
-	zoned = (vpd->data[8] >> 4) & 3;
+	sdkp->zoned = (vpd->data[8] >> 4) & 3;
 	rcu_read_unlock();
 
 	if (rot == 1) {
@@ -3138,37 +3137,33 @@ static void sd_read_block_characteristics(struct scsi_disk *sdkp)
 
 	if (sdkp->device->type == TYPE_ZBC) {
 		/*
-		 * Host-managed: Per ZBC and ZAC specifications, writes in
-		 * sequential write required zones of host-managed devices must
-		 * be aligned to the device physical block size.
+		 * Host-managed.
+		 */
+		disk_set_zoned(sdkp->disk, true);
+
+		/*
+		 * Per ZBC and ZAC specifications, writes in sequential write
+		 * required zones of host-managed devices must be aligned to
+		 * the device physical block size.
 		 */
-		disk_set_zoned(sdkp->disk, BLK_ZONED_HM);
 		blk_queue_zone_write_granularity(q, sdkp->physical_block_size);
 	} else {
-		sdkp->zoned = zoned;
-		if (sdkp->zoned == 1) {
-			/* Host-aware */
-			disk_set_zoned(sdkp->disk, BLK_ZONED_HA);
-		} else {
-			/* Regular disk or drive managed disk */
-			disk_set_zoned(sdkp->disk, BLK_ZONED_NONE);
-		}
+		/*
+		 * Anything else.  This includes host-aware device that we treat
+		 * as conventional.
+		 */
+		disk_set_zoned(sdkp->disk, false);
 	}
 
 	if (!sdkp->first_scan)
 		return;
 
-	if (blk_queue_is_zoned(q)) {
-		sd_printk(KERN_NOTICE, sdkp, "Host-%s zoned block device\n",
-		      q->limits.zoned == BLK_ZONED_HM ? "managed" : "aware");
-	} else {
-		if (sdkp->zoned == 1)
-			sd_printk(KERN_NOTICE, sdkp,
-				  "Host-aware SMR disk used as regular disk\n");
-		else if (sdkp->zoned == 2)
-			sd_printk(KERN_NOTICE, sdkp,
-				  "Drive-managed SMR disk\n");
-	}
+	if (blk_queue_is_zoned(q))
+		sd_printk(KERN_NOTICE, sdkp, "Host-managed zoned block device\n");
+	else if (sdkp->zoned == 1)
+		sd_printk(KERN_NOTICE, sdkp, "Host-aware SMR disk used as regular disk\n");
+	else if (sdkp->zoned == 2)
+		sd_printk(KERN_NOTICE, sdkp, "Drive-managed SMR disk\n");
 }
 
 /**
diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c
index a25215507668..26af5ab7d7c1 100644
--- a/drivers/scsi/sd_zbc.c
+++ b/drivers/scsi/sd_zbc.c
@@ -836,10 +836,7 @@ int sd_zbc_revalidate_zones(struct scsi_disk *sdkp)
 
 	/*
 	 * For all zoned disks, initialize zone append emulation data if not
-	 * already done. This is necessary also for host-aware disks used as
-	 * regular disks due to the presence of partitions as these partitions
-	 * may be deleted and the disk zoned model changed back from
-	 * BLK_ZONED_NONE to BLK_ZONED_HA.
+	 * already done.
 	 */
 	if (sd_is_zoned(sdkp) && !sdkp->zone_wp_update_buf) {
 		ret = sd_zbc_init_disk(sdkp);
@@ -932,17 +929,6 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, u8 buf[SD_BUF_SIZE])
 	sdkp->device->use_10_for_rw = 0;
 	sdkp->device->use_16_for_sync = 1;
 
-	if (!blk_queue_is_zoned(q)) {
-		/*
-		 * This can happen for a host aware disk with partitions.
-		 * The block device zone model was already cleared by
-		 * disk_set_zoned(). Only free the scsi disk zone
-		 * information and exit early.
-		 */
-		sd_zbc_free_zone_info(sdkp);
-		return 0;
-	}
-
 	/* Check zoned block device characteristics (unconstrained reads) */
 	ret = sd_zbc_check_zoned_characteristics(sdkp, buf);
 	if (ret)
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 188378ca19c7..23c1e6b19a65 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -578,26 +578,12 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache)
 
 	kvfree(zones);
 
-	switch (bdev_zoned_model(bdev)) {
-	case BLK_ZONED_HM:
+	if (bdev_is_zoned(bdev)) {
 		model = "host-managed zoned";
 		emulated = "";
-		break;
-	case BLK_ZONED_HA:
-		model = "host-aware zoned";
-		emulated = "";
-		break;
-	case BLK_ZONED_NONE:
+	} else {
 		model = "regular";
 		emulated = "emulated ";
-		break;
-	default:
-		/* Just in case */
-		btrfs_err_in_rcu(fs_info, "zoned: unsupported model %d on %s",
-				 bdev_zoned_model(bdev),
-				 rcu_str_deref(device->name));
-		ret = -EOPNOTSUPP;
-		goto out_free_zone_info;
 	}
 
 	btrfs_info_in_rcu(fs_info,
@@ -609,9 +595,7 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache)
 
 out:
 	kvfree(zones);
-out_free_zone_info:
 	btrfs_destroy_dev_zone_info(device);
-
 	return ret;
 }
 
@@ -688,8 +672,7 @@ static int btrfs_check_for_zoned_device(struct btrfs_fs_info *fs_info)
 	struct btrfs_device *device;
 
 	list_for_each_entry(device, &fs_info->fs_devices->devices, dev_list) {
-		if (device->bdev &&
-		    bdev_zoned_model(device->bdev) == BLK_ZONED_HM) {
+		if (device->bdev && bdev_is_zoned(device->bdev)) {
 			btrfs_err(fs_info,
 				"zoned: mode not enabled but zoned device found: %pg",
 				device->bdev);
diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h
index b9cec523b778..bc1b540c1597 100644
--- a/fs/btrfs/zoned.h
+++ b/fs/btrfs/zoned.h
@@ -324,7 +324,7 @@ static inline bool btrfs_check_device_zone_type(const struct btrfs_fs_info *fs_i
 	}
 
 	/* Do not allow Host Manged zoned device */
-	return bdev_zoned_model(bdev) != BLK_ZONED_HM;
+	return !bdev_is_zoned(bdev);
 }
 
 static inline bool btrfs_check_super_location(struct btrfs_device *device, u64 pos)
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 4e42b5f24deb..9b62549a29ce 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -995,7 +995,7 @@ static bool is_end_zone_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr)
 		}
 		blkaddr -= FDEV(devi).start_blk;
 	}
-	return bdev_zoned_model(FDEV(devi).bdev) == BLK_ZONED_HM &&
+	return bdev_is_zoned(FDEV(devi).bdev) &&
 		f2fs_blkz_is_seq(sbi, devi, blkaddr) &&
 		(blkaddr % sbi->blocks_per_blkz == sbi->blocks_per_blkz - 1);
 }
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 033af907c3b1..850c87ae7d98 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -4282,24 +4282,21 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 			sbi->aligned_blksize = false;
 
 #ifdef CONFIG_BLK_DEV_ZONED
-		if (bdev_zoned_model(FDEV(i).bdev) == BLK_ZONED_HM &&
-				!f2fs_sb_has_blkzoned(sbi)) {
-			f2fs_err(sbi, "Zoned block device feature not enabled");
-			return -EINVAL;
-		}
-		if (bdev_zoned_model(FDEV(i).bdev) != BLK_ZONED_NONE) {
+		if (bdev_is_zoned(FDEV(i).bdev)) {
+			if (!f2fs_sb_has_blkzoned(sbi)) {
+				f2fs_err(sbi, "Zoned block device feature not enabled");
+				return -EINVAL;
+			}
 			if (init_blkz_info(sbi, i)) {
 				f2fs_err(sbi, "Failed to initialize F2FS blkzone information");
 				return -EINVAL;
 			}
 			if (max_devices == 1)
 				break;
-			f2fs_info(sbi, "Mount Device [%2d]: %20s, %8u, %8x - %8x (zone: %s)",
+			f2fs_info(sbi, "Mount Device [%2d]: %20s, %8u, %8x - %8x (zone: Host-managed)",
 				  i, FDEV(i).path,
 				  FDEV(i).total_segments,
-				  FDEV(i).start_blk, FDEV(i).end_blk,
-				  bdev_zoned_model(FDEV(i).bdev) == BLK_ZONED_HA ?
-				  "Host-aware" : "Host-managed");
+				  FDEV(i).start_blk, FDEV(i).end_blk);
 			continue;
 		}
 #endif
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 185ed3770e3a..28cda9fb239e 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -263,18 +263,6 @@ static inline bool blk_op_is_passthrough(blk_opf_t op)
 	return op == REQ_OP_DRV_IN || op == REQ_OP_DRV_OUT;
 }
 
-/*
- * Zoned block device models (zoned limit).
- *
- * Note: This needs to be ordered from the least to the most severe
- * restrictions for the inheritance in blk_stack_limits() to work.
- */
-enum blk_zoned_model {
-	BLK_ZONED_NONE = 0,	/* Regular block device */
-	BLK_ZONED_HA,		/* Host-aware zoned block device */
-	BLK_ZONED_HM,		/* Host-managed zoned block device */
-};
-
 /*
  * BLK_BOUNCE_NONE:	never bounce (default)
  * BLK_BOUNCE_HIGH:	bounce all highmem pages
@@ -316,7 +304,7 @@ struct queue_limits {
 	unsigned char		misaligned;
 	unsigned char		discard_misaligned;
 	unsigned char		raid_partial_stripes_expensive;
-	enum blk_zoned_model	zoned;
+	bool			zoned;
 
 	/*
 	 * Drivers that set dma_alignment to less than 511 must be prepared to
@@ -329,7 +317,7 @@ struct queue_limits {
 typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx,
 			       void *data);
 
-void disk_set_zoned(struct gendisk *disk, enum blk_zoned_model model);
+void disk_set_zoned(struct gendisk *disk, bool zoned);
 
 #define BLK_ALL_ZONES  ((unsigned int)-1)
 int blkdev_report_zones(struct block_device *bdev, sector_t sector,
@@ -617,23 +605,9 @@ static inline enum rpm_status queue_rpm_status(struct request_queue *q)
 }
 #endif
 
-static inline enum blk_zoned_model
-blk_queue_zoned_model(struct request_queue *q)
-{
-	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED))
-		return q->limits.zoned;
-	return BLK_ZONED_NONE;
-}
-
 static inline bool blk_queue_is_zoned(struct request_queue *q)
 {
-	switch (blk_queue_zoned_model(q)) {
-	case BLK_ZONED_HA:
-	case BLK_ZONED_HM:
-		return true;
-	default:
-		return false;
-	}
+	return IS_ENABLED(CONFIG_BLK_DEV_ZONED) && q->limits.zoned;
 }
 
 #ifdef CONFIG_BLK_DEV_ZONED
@@ -1260,11 +1234,6 @@ static inline bool bdev_nowait(struct block_device *bdev)
 	return test_bit(QUEUE_FLAG_NOWAIT, &bdev_get_queue(bdev)->queue_flags);
 }
 
-static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev)
-{
-	return blk_queue_zoned_model(bdev_get_queue(bdev));
-}
-
 static inline bool bdev_is_zoned(struct block_device *bdev)
 {
 	return blk_queue_is_zoned(bdev_get_queue(bdev));
-- 
cgit v1.2.3


From d73e93b4dfab10c80688b061c30048df05585c7e Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 17 Dec 2023 17:53:58 +0100
Subject: block: simplify disk_set_zoned

Only use disk_set_zoned to actually enable zoned device support.
For clearing it, call disk_clear_zoned, which is renamed from
disk_clear_zone_settings and now directly clears the zoned flag as
well.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Link: https://lore.kernel.org/r/20231217165359.604246-5-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-settings.c           | 32 +++++++++++---------------------
 block/blk-zoned.c              |  3 ++-
 block/blk.h                    |  2 --
 drivers/block/null_blk/zoned.c |  2 +-
 drivers/block/ublk_drv.c       |  2 +-
 drivers/block/virtio_blk.c     |  2 +-
 drivers/nvme/host/zns.c        |  2 +-
 drivers/scsi/sd.c              |  7 +++++--
 include/linux/blkdev.h         |  3 ++-
 9 files changed, 24 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/block/blk-settings.c b/block/blk-settings.c
index 50e9efb59f67..bb94a3d471f4 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -881,31 +881,21 @@ bool blk_queue_can_use_dma_map_merging(struct request_queue *q,
 EXPORT_SYMBOL_GPL(blk_queue_can_use_dma_map_merging);
 
 /**
- * disk_set_zoned - configure the zoned model for a disk
- * @disk:	the gendisk of the queue to configure
- * @zoned:	zoned or not.
- *
- * When @zoned is %true, this should be called only if zoned block device
- * support is enabled (CONFIG_BLK_DEV_ZONED option).
+ * disk_set_zoned - inidicate a zoned device
+ * @disk:	gendisk to configure
  */
-void disk_set_zoned(struct gendisk *disk, bool zoned)
+void disk_set_zoned(struct gendisk *disk)
 {
 	struct request_queue *q = disk->queue;
 
-	if (zoned) {
-		WARN_ON_ONCE(!IS_ENABLED(CONFIG_BLK_DEV_ZONED));
-
-		/*
-		 * Set the zone write granularity to the device logical block
-		 * size by default. The driver can change this value if needed.
-		 */
-		q->limits.zoned = true;
-		blk_queue_zone_write_granularity(q,
-						queue_logical_block_size(q));
-	} else if (q->limits.zoned) {
-		q->limits.zoned = false;
-		disk_clear_zone_settings(disk);
-	}
+	WARN_ON_ONCE(!IS_ENABLED(CONFIG_BLK_DEV_ZONED));
+
+	/*
+	 * Set the zone write granularity to the device logical block
+	 * size by default. The driver can change this value if needed.
+	 */
+	q->limits.zoned = true;
+	blk_queue_zone_write_granularity(q, queue_logical_block_size(q));
 }
 EXPORT_SYMBOL_GPL(disk_set_zoned);
 
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 619ee41a51cc..580a58e53efd 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -616,12 +616,13 @@ int blk_revalidate_disk_zones(struct gendisk *disk,
 }
 EXPORT_SYMBOL_GPL(blk_revalidate_disk_zones);
 
-void disk_clear_zone_settings(struct gendisk *disk)
+void disk_clear_zoned(struct gendisk *disk)
 {
 	struct request_queue *q = disk->queue;
 
 	blk_mq_freeze_queue(q);
 
+	q->limits.zoned = false;
 	disk_free_zone_bitmaps(disk);
 	blk_queue_flag_clear(QUEUE_FLAG_ZONE_RESETALL, q);
 	q->required_elevator_features &= ~ELEVATOR_F_ZBD_SEQ_WRITE;
diff --git a/block/blk.h b/block/blk.h
index 08a358bc0919..1ef920f72e0f 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -395,14 +395,12 @@ static inline struct bio *blk_queue_bounce(struct bio *bio,
 
 #ifdef CONFIG_BLK_DEV_ZONED
 void disk_free_zone_bitmaps(struct gendisk *disk);
-void disk_clear_zone_settings(struct gendisk *disk);
 int blkdev_report_zones_ioctl(struct block_device *bdev, unsigned int cmd,
 		unsigned long arg);
 int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode,
 		unsigned int cmd, unsigned long arg);
 #else /* CONFIG_BLK_DEV_ZONED */
 static inline void disk_free_zone_bitmaps(struct gendisk *disk) {}
-static inline void disk_clear_zone_settings(struct gendisk *disk) {}
 static inline int blkdev_report_zones_ioctl(struct block_device *bdev,
 		unsigned int cmd, unsigned long arg)
 {
diff --git a/drivers/block/null_blk/zoned.c b/drivers/block/null_blk/zoned.c
index 369eb1e78bb5..6f5e0994862e 100644
--- a/drivers/block/null_blk/zoned.c
+++ b/drivers/block/null_blk/zoned.c
@@ -159,7 +159,7 @@ int null_register_zoned_dev(struct nullb *nullb)
 	struct nullb_device *dev = nullb->dev;
 	struct request_queue *q = nullb->q;
 
-	disk_set_zoned(nullb->disk, true);
+	disk_set_zoned(nullb->disk);
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
 	blk_queue_required_elevator_features(q, ELEVATOR_F_ZBD_SEQ_WRITE);
 	blk_queue_chunk_sectors(q, dev->zone_size_sects);
diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 24fb95f19d52..d50d69b2c023 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -250,7 +250,7 @@ static int ublk_dev_param_zoned_apply(struct ublk_device *ub)
 {
 	const struct ublk_param_zoned *p = &ub->params.zoned;
 
-	disk_set_zoned(ub->ub_disk, true);
+	disk_set_zoned(ub->ub_disk);
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, ub->ub_disk->queue);
 	blk_queue_required_elevator_features(ub->ub_disk->queue,
 					     ELEVATOR_F_ZBD_SEQ_WRITE);
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 19a4f20bd1c2..7d7a19b2b9a8 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -730,7 +730,7 @@ static int virtblk_probe_zoned_device(struct virtio_device *vdev,
 
 	dev_dbg(&vdev->dev, "probing host-managed zoned device\n");
 
-	disk_set_zoned(vblk->disk, true);
+	disk_set_zoned(vblk->disk);
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
 
 	virtio_cread(vdev, struct virtio_blk_config,
diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c
index 6d4c440e97e2..3d98e435821e 100644
--- a/drivers/nvme/host/zns.c
+++ b/drivers/nvme/host/zns.c
@@ -108,7 +108,7 @@ int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf)
 		goto free_data;
 	}
 
-	disk_set_zoned(ns->disk, true);
+	disk_set_zoned(ns->disk);
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
 	disk_set_max_open_zones(ns->disk, le32_to_cpu(id->mor) + 1);
 	disk_set_max_active_zones(ns->disk, le32_to_cpu(id->mar) + 1);
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 19a19eb277f5..dbed075cdb98 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -3135,11 +3135,13 @@ static void sd_read_block_characteristics(struct scsi_disk *sdkp)
 		blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, q);
 	}
 
+
+#ifdef CONFIG_BLK_DEV_ZONED /* sd_probe rejects ZBD devices early otherwise */
 	if (sdkp->device->type == TYPE_ZBC) {
 		/*
 		 * Host-managed.
 		 */
-		disk_set_zoned(sdkp->disk, true);
+		disk_set_zoned(sdkp->disk);
 
 		/*
 		 * Per ZBC and ZAC specifications, writes in sequential write
@@ -3152,8 +3154,9 @@ static void sd_read_block_characteristics(struct scsi_disk *sdkp)
 		 * Anything else.  This includes host-aware device that we treat
 		 * as conventional.
 		 */
-		disk_set_zoned(sdkp->disk, false);
+		disk_clear_zoned(sdkp->disk);
 	}
+#endif /* CONFIG_BLK_DEV_ZONED */
 
 	if (!sdkp->first_scan)
 		return;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 28cda9fb239e..bc236e77d85e 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -317,7 +317,8 @@ struct queue_limits {
 typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx,
 			       void *data);
 
-void disk_set_zoned(struct gendisk *disk, bool zoned);
+void disk_set_zoned(struct gendisk *disk);
+void disk_clear_zoned(struct gendisk *disk);
 
 #define BLK_ALL_ZONES  ((unsigned int)-1)
 int blkdev_report_zones(struct block_device *bdev, sector_t sector,
-- 
cgit v1.2.3


From 8be0c877fb3b671dac0cf56d1f1f9e65f9a9fb81 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 19 Dec 2023 16:43:05 +0100
Subject: thunderbolt: make tb_bus_type const

Now that the driver core can properly handle constant struct bus_type,
move the tb_bus_type variable to be a constant structure as well,
placing it into read-only memory which can not be modified at runtime.

Cc: Andreas Noever <andreas.noever@gmail.com>
Cc: Michael Jamet <michael.jamet@intel.com>
Cc: Yehezkel Bernat <YehezkelShB@gmail.com>
Cc:  <linux-usb@vger.kernel.org>
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Link: https://lore.kernel.org/r/2023121904-utopia-broadcast-06d1@gregkh
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/thunderbolt/domain.c | 2 +-
 include/linux/thunderbolt.h  | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/thunderbolt/domain.c b/drivers/thunderbolt/domain.c
index ec7b5f65804e..9fb1a64f3300 100644
--- a/drivers/thunderbolt/domain.c
+++ b/drivers/thunderbolt/domain.c
@@ -307,7 +307,7 @@ static const struct attribute_group *domain_attr_groups[] = {
 	NULL,
 };
 
-struct bus_type tb_bus_type = {
+const struct bus_type tb_bus_type = {
 	.name = "thunderbolt",
 	.match = tb_service_match,
 	.probe = tb_service_probe,
diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h
index 6151c210d987..2c835e5c41f6 100644
--- a/include/linux/thunderbolt.h
+++ b/include/linux/thunderbolt.h
@@ -86,7 +86,7 @@ struct tb {
 	unsigned long privdata[];
 };
 
-extern struct bus_type tb_bus_type;
+extern const struct bus_type tb_bus_type;
 extern struct device_type tb_service_type;
 extern struct device_type tb_xdomain_type;
 
-- 
cgit v1.2.3


From a7f0636d223ca9d074eb5b4ae71425e082c5c1e1 Mon Sep 17 00:00:00 2001
From: Long Li <longli@microsoft.com>
Date: Fri, 15 Dec 2023 18:04:13 -0800
Subject: RDMA/mana_ib: register RDMA device with GDMA

Software client needs to register with the RDMA management interface on
the SoC to access more features, including querying device capabilities
and RC queue pair.

Signed-off-by: Long Li <longli@microsoft.com>
Link: https://lore.kernel.org/r/1702692255-23640-2-git-send-email-longli@linuxonhyperv.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/mana/device.c             | 24 +++++++++++++++++++-----
 drivers/infiniband/hw/mana/main.c               |  4 ++--
 drivers/infiniband/hw/mana/qp.c                 | 15 ++++++++-------
 drivers/net/ethernet/microsoft/mana/gdma_main.c |  5 +++++
 include/net/mana/gdma.h                         |  4 ++++
 5 files changed, 38 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mana/device.c b/drivers/infiniband/hw/mana/device.c
index d4541b8707e4..fe025e13a45c 100644
--- a/drivers/infiniband/hw/mana/device.c
+++ b/drivers/infiniband/hw/mana/device.c
@@ -68,7 +68,6 @@ static int mana_ib_probe(struct auxiliary_device *adev,
 	ibdev_dbg(&dev->ib_dev, "mdev=%p id=%d num_ports=%d\n", mdev,
 		  mdev->dev_id.as_uint32, dev->ib_dev.phys_port_cnt);
 
-	dev->gdma_dev = mdev;
 	dev->ib_dev.node_type = RDMA_NODE_IB_CA;
 
 	/*
@@ -78,16 +77,28 @@ static int mana_ib_probe(struct auxiliary_device *adev,
 	dev->ib_dev.num_comp_vectors = 1;
 	dev->ib_dev.dev.parent = mdev->gdma_context->dev;
 
-	ret = ib_register_device(&dev->ib_dev, "mana_%d",
-				 mdev->gdma_context->dev);
+	ret = mana_gd_register_device(&mdev->gdma_context->mana_ib);
 	if (ret) {
-		ib_dealloc_device(&dev->ib_dev);
-		return ret;
+		ibdev_err(&dev->ib_dev, "Failed to register device, ret %d",
+			  ret);
+		goto free_ib_device;
 	}
+	dev->gdma_dev = &mdev->gdma_context->mana_ib;
+
+	ret = ib_register_device(&dev->ib_dev, "mana_%d",
+				 mdev->gdma_context->dev);
+	if (ret)
+		goto deregister_device;
 
 	dev_set_drvdata(&adev->dev, dev);
 
 	return 0;
+
+deregister_device:
+	mana_gd_deregister_device(dev->gdma_dev);
+free_ib_device:
+	ib_dealloc_device(&dev->ib_dev);
+	return ret;
 }
 
 static void mana_ib_remove(struct auxiliary_device *adev)
@@ -95,6 +106,9 @@ static void mana_ib_remove(struct auxiliary_device *adev)
 	struct mana_ib_dev *dev = dev_get_drvdata(&adev->dev);
 
 	ib_unregister_device(&dev->ib_dev);
+
+	mana_gd_deregister_device(dev->gdma_dev);
+
 	ib_dealloc_device(&dev->ib_dev);
 }
 
diff --git a/drivers/infiniband/hw/mana/main.c b/drivers/infiniband/hw/mana/main.c
index 7be4c3adb4e2..53730306ed9b 100644
--- a/drivers/infiniband/hw/mana/main.c
+++ b/drivers/infiniband/hw/mana/main.c
@@ -8,7 +8,7 @@
 void mana_ib_uncfg_vport(struct mana_ib_dev *dev, struct mana_ib_pd *pd,
 			 u32 port)
 {
-	struct gdma_dev *gd = dev->gdma_dev;
+	struct gdma_dev *gd = &dev->gdma_dev->gdma_context->mana;
 	struct mana_port_context *mpc;
 	struct net_device *ndev;
 	struct mana_context *mc;
@@ -31,7 +31,7 @@ void mana_ib_uncfg_vport(struct mana_ib_dev *dev, struct mana_ib_pd *pd,
 int mana_ib_cfg_vport(struct mana_ib_dev *dev, u32 port, struct mana_ib_pd *pd,
 		      u32 doorbell_id)
 {
-	struct gdma_dev *mdev = dev->gdma_dev;
+	struct gdma_dev *mdev = &dev->gdma_dev->gdma_context->mana;
 	struct mana_port_context *mpc;
 	struct mana_context *mc;
 	struct net_device *ndev;
diff --git a/drivers/infiniband/hw/mana/qp.c b/drivers/infiniband/hw/mana/qp.c
index 4b3b5b274e84..ae45d28eef5e 100644
--- a/drivers/infiniband/hw/mana/qp.c
+++ b/drivers/infiniband/hw/mana/qp.c
@@ -21,8 +21,8 @@ static int mana_ib_cfg_vport_steering(struct mana_ib_dev *dev,
 	u32 req_buf_size;
 	int i, err;
 
-	mdev = dev->gdma_dev;
-	gc = mdev->gdma_context;
+	gc = dev->gdma_dev->gdma_context;
+	mdev = &gc->mana;
 
 	req_buf_size =
 		sizeof(*req) + sizeof(mana_handle_t) * MANA_INDIRECT_TABLE_SIZE;
@@ -102,20 +102,21 @@ static int mana_ib_create_qp_rss(struct ib_qp *ibqp, struct ib_pd *pd,
 	struct ib_rwq_ind_table *ind_tbl = attr->rwq_ind_tbl;
 	struct mana_ib_create_qp_rss_resp resp = {};
 	struct mana_ib_create_qp_rss ucmd = {};
-	struct gdma_dev *gd = mdev->gdma_dev;
 	mana_handle_t *mana_ind_table;
 	struct mana_port_context *mpc;
+	unsigned int ind_tbl_size;
 	struct mana_context *mc;
 	struct net_device *ndev;
 	struct mana_ib_cq *cq;
 	struct mana_ib_wq *wq;
-	unsigned int ind_tbl_size;
+	struct gdma_dev *gd;
 	struct ib_cq *ibcq;
 	struct ib_wq *ibwq;
 	int i = 0;
 	u32 port;
 	int ret;
 
+	gd = &mdev->gdma_dev->gdma_context->mana;
 	mc = gd->driver_data;
 
 	if (!udata || udata->inlen < sizeof(ucmd))
@@ -266,8 +267,8 @@ static int mana_ib_create_qp_raw(struct ib_qp *ibqp, struct ib_pd *ibpd,
 	struct mana_ib_ucontext *mana_ucontext =
 		rdma_udata_to_drv_context(udata, struct mana_ib_ucontext,
 					  ibucontext);
+	struct gdma_dev *gd = &mdev->gdma_dev->gdma_context->mana;
 	struct mana_ib_create_qp_resp resp = {};
-	struct gdma_dev *gd = mdev->gdma_dev;
 	struct mana_ib_create_qp ucmd = {};
 	struct mana_obj_spec wq_spec = {};
 	struct mana_obj_spec cq_spec = {};
@@ -437,7 +438,7 @@ static int mana_ib_destroy_qp_rss(struct mana_ib_qp *qp,
 {
 	struct mana_ib_dev *mdev =
 		container_of(qp->ibqp.device, struct mana_ib_dev, ib_dev);
-	struct gdma_dev *gd = mdev->gdma_dev;
+	struct gdma_dev *gd = &mdev->gdma_dev->gdma_context->mana;
 	struct mana_port_context *mpc;
 	struct mana_context *mc;
 	struct net_device *ndev;
@@ -464,7 +465,7 @@ static int mana_ib_destroy_qp_raw(struct mana_ib_qp *qp, struct ib_udata *udata)
 {
 	struct mana_ib_dev *mdev =
 		container_of(qp->ibqp.device, struct mana_ib_dev, ib_dev);
-	struct gdma_dev *gd = mdev->gdma_dev;
+	struct gdma_dev *gd = &mdev->gdma_dev->gdma_context->mana;
 	struct ib_pd *ibpd = qp->ibqp.pd;
 	struct mana_port_context *mpc;
 	struct mana_context *mc;
diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index 6367de0c2c2e..e6e71e3c357c 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -158,6 +158,9 @@ static int mana_gd_detect_devices(struct pci_dev *pdev)
 		if (dev_type == GDMA_DEVICE_MANA) {
 			gc->mana.gdma_context = gc;
 			gc->mana.dev_id = dev;
+		} else if (dev_type == GDMA_DEVICE_MANA_IB) {
+			gc->mana_ib.dev_id = dev;
+			gc->mana_ib.gdma_context = gc;
 		}
 	}
 
@@ -971,6 +974,7 @@ int mana_gd_register_device(struct gdma_dev *gd)
 
 	return 0;
 }
+EXPORT_SYMBOL_NS(mana_gd_register_device, NET_MANA);
 
 int mana_gd_deregister_device(struct gdma_dev *gd)
 {
@@ -1001,6 +1005,7 @@ int mana_gd_deregister_device(struct gdma_dev *gd)
 
 	return err;
 }
+EXPORT_SYMBOL_NS(mana_gd_deregister_device, NET_MANA);
 
 u32 mana_gd_wq_avail_space(struct gdma_queue *wq)
 {
diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h
index 88b6ef7ce1a6..000f0d7670f7 100644
--- a/include/net/mana/gdma.h
+++ b/include/net/mana/gdma.h
@@ -66,6 +66,7 @@ enum {
 	GDMA_DEVICE_NONE	= 0,
 	GDMA_DEVICE_HWC		= 1,
 	GDMA_DEVICE_MANA	= 2,
+	GDMA_DEVICE_MANA_IB	= 3,
 };
 
 struct gdma_resource {
@@ -387,6 +388,9 @@ struct gdma_context {
 
 	/* Azure network adapter */
 	struct gdma_dev		mana;
+
+	/* Azure RDMA adapter */
+	struct gdma_dev		mana_ib;
 };
 
 #define MAX_NUM_GDMA_DEVICES	4
-- 
cgit v1.2.3


From 2c20e20b22d9fc64072e3445ae3ca244cbd523a2 Mon Sep 17 00:00:00 2001
From: Long Li <longli@microsoft.com>
Date: Fri, 15 Dec 2023 18:04:14 -0800
Subject: RDMA/mana_ib: query device capabilities

With RDMA device registered, use it to query on hardware capabilities and
cache this information for future query requests to the driver.

Signed-off-by: Long Li <longli@microsoft.com>
Link: https://lore.kernel.org/r/1702692255-23640-3-git-send-email-longli@linuxonhyperv.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/mana/cq.c      |  2 +-
 drivers/infiniband/hw/mana/device.c  |  7 ++++
 drivers/infiniband/hw/mana/main.c    | 65 ++++++++++++++++++++++++++++--------
 drivers/infiniband/hw/mana/mana_ib.h | 50 +++++++++++++++++++++++++++
 drivers/infiniband/hw/mana/qp.c      |  4 +--
 include/net/mana/gdma.h              |  1 +
 6 files changed, 113 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mana/cq.c b/drivers/infiniband/hw/mana/cq.c
index d141cab8a1e6..09a2c263e39b 100644
--- a/drivers/infiniband/hw/mana/cq.c
+++ b/drivers/infiniband/hw/mana/cq.c
@@ -26,7 +26,7 @@ int mana_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 		return err;
 	}
 
-	if (attr->cqe > MAX_SEND_BUFFERS_PER_QUEUE) {
+	if (attr->cqe > mdev->adapter_caps.max_qp_wr) {
 		ibdev_dbg(ibdev, "CQE %d exceeding limit\n", attr->cqe);
 		return -EINVAL;
 	}
diff --git a/drivers/infiniband/hw/mana/device.c b/drivers/infiniband/hw/mana/device.c
index fe025e13a45c..6fa902ee80a6 100644
--- a/drivers/infiniband/hw/mana/device.c
+++ b/drivers/infiniband/hw/mana/device.c
@@ -85,6 +85,13 @@ static int mana_ib_probe(struct auxiliary_device *adev,
 	}
 	dev->gdma_dev = &mdev->gdma_context->mana_ib;
 
+	ret = mana_ib_gd_query_adapter_caps(dev);
+	if (ret) {
+		ibdev_err(&dev->ib_dev, "Failed to query device caps, ret %d",
+			  ret);
+		goto deregister_device;
+	}
+
 	ret = ib_register_device(&dev->ib_dev, "mana_%d",
 				 mdev->gdma_context->dev);
 	if (ret)
diff --git a/drivers/infiniband/hw/mana/main.c b/drivers/infiniband/hw/mana/main.c
index 53730306ed9b..faca092456fa 100644
--- a/drivers/infiniband/hw/mana/main.c
+++ b/drivers/infiniband/hw/mana/main.c
@@ -486,20 +486,17 @@ int mana_ib_get_port_immutable(struct ib_device *ibdev, u32 port_num,
 int mana_ib_query_device(struct ib_device *ibdev, struct ib_device_attr *props,
 			 struct ib_udata *uhw)
 {
-	props->max_qp = MANA_MAX_NUM_QUEUES;
-	props->max_qp_wr = MAX_SEND_BUFFERS_PER_QUEUE;
-
-	/*
-	 * max_cqe could be potentially much bigger.
-	 * As this version of driver only support RAW QP, set it to the same
-	 * value as max_qp_wr
-	 */
-	props->max_cqe = MAX_SEND_BUFFERS_PER_QUEUE;
-
+	struct mana_ib_dev *dev = container_of(ibdev,
+			struct mana_ib_dev, ib_dev);
+
+	props->max_qp = dev->adapter_caps.max_qp_count;
+	props->max_qp_wr = dev->adapter_caps.max_qp_wr;
+	props->max_cq = dev->adapter_caps.max_cq_count;
+	props->max_cqe = dev->adapter_caps.max_qp_wr;
+	props->max_mr = dev->adapter_caps.max_mr_count;
 	props->max_mr_size = MANA_IB_MAX_MR_SIZE;
-	props->max_mr = MANA_IB_MAX_MR;
-	props->max_send_sge = MAX_TX_WQE_SGL_ENTRIES;
-	props->max_recv_sge = MAX_RX_WQE_SGL_ENTRIES;
+	props->max_send_sge = dev->adapter_caps.max_send_sge_count;
+	props->max_recv_sge = dev->adapter_caps.max_recv_sge_count;
 
 	return 0;
 }
@@ -521,3 +518,45 @@ int mana_ib_query_gid(struct ib_device *ibdev, u32 port, int index,
 void mana_ib_disassociate_ucontext(struct ib_ucontext *ibcontext)
 {
 }
+
+int mana_ib_gd_query_adapter_caps(struct mana_ib_dev *dev)
+{
+	struct mana_ib_adapter_caps *caps = &dev->adapter_caps;
+	struct mana_ib_query_adapter_caps_resp resp = {};
+	struct mana_ib_query_adapter_caps_req req = {};
+	int err;
+
+	mana_gd_init_req_hdr(&req.hdr, MANA_IB_GET_ADAPTER_CAP, sizeof(req),
+			     sizeof(resp));
+	req.hdr.resp.msg_version = GDMA_MESSAGE_V3;
+	req.hdr.dev_id = dev->gdma_dev->dev_id;
+
+	err = mana_gd_send_request(dev->gdma_dev->gdma_context, sizeof(req),
+				   &req, sizeof(resp), &resp);
+
+	if (err) {
+		ibdev_err(&dev->ib_dev,
+			  "Failed to query adapter caps err %d", err);
+		return err;
+	}
+
+	caps->max_sq_id = resp.max_sq_id;
+	caps->max_rq_id = resp.max_rq_id;
+	caps->max_cq_id = resp.max_cq_id;
+	caps->max_qp_count = resp.max_qp_count;
+	caps->max_cq_count = resp.max_cq_count;
+	caps->max_mr_count = resp.max_mr_count;
+	caps->max_pd_count = resp.max_pd_count;
+	caps->max_inbound_read_limit = resp.max_inbound_read_limit;
+	caps->max_outbound_read_limit = resp.max_outbound_read_limit;
+	caps->mw_count = resp.mw_count;
+	caps->max_srq_count = resp.max_srq_count;
+	caps->max_qp_wr = min_t(u32,
+				resp.max_requester_sq_size / GDMA_MAX_SQE_SIZE,
+				resp.max_requester_rq_size / GDMA_MAX_RQE_SIZE);
+	caps->max_inline_data_size = resp.max_inline_data_size;
+	caps->max_send_sge_count = resp.max_send_sge_count;
+	caps->max_recv_sge_count = resp.max_recv_sge_count;
+
+	return 0;
+}
diff --git a/drivers/infiniband/hw/mana/mana_ib.h b/drivers/infiniband/hw/mana/mana_ib.h
index 502cc8672eef..3329eaacc94e 100644
--- a/drivers/infiniband/hw/mana/mana_ib.h
+++ b/drivers/infiniband/hw/mana/mana_ib.h
@@ -27,9 +27,28 @@
  */
 #define MANA_IB_MAX_MR		0xFFFFFFu
 
+struct mana_ib_adapter_caps {
+	u32 max_sq_id;
+	u32 max_rq_id;
+	u32 max_cq_id;
+	u32 max_qp_count;
+	u32 max_cq_count;
+	u32 max_mr_count;
+	u32 max_pd_count;
+	u32 max_inbound_read_limit;
+	u32 max_outbound_read_limit;
+	u32 mw_count;
+	u32 max_srq_count;
+	u32 max_qp_wr;
+	u32 max_send_sge_count;
+	u32 max_recv_sge_count;
+	u32 max_inline_data_size;
+};
+
 struct mana_ib_dev {
 	struct ib_device ib_dev;
 	struct gdma_dev *gdma_dev;
+	struct mana_ib_adapter_caps adapter_caps;
 };
 
 struct mana_ib_wq {
@@ -92,6 +111,36 @@ struct mana_ib_rwq_ind_table {
 	struct ib_rwq_ind_table ib_ind_table;
 };
 
+enum mana_ib_command_code {
+	MANA_IB_GET_ADAPTER_CAP = 0x30001,
+};
+
+struct mana_ib_query_adapter_caps_req {
+	struct gdma_req_hdr hdr;
+}; /*HW Data */
+
+struct mana_ib_query_adapter_caps_resp {
+	struct gdma_resp_hdr hdr;
+	u32 max_sq_id;
+	u32 max_rq_id;
+	u32 max_cq_id;
+	u32 max_qp_count;
+	u32 max_cq_count;
+	u32 max_mr_count;
+	u32 max_pd_count;
+	u32 max_inbound_read_limit;
+	u32 max_outbound_read_limit;
+	u32 mw_count;
+	u32 max_srq_count;
+	u32 max_requester_sq_size;
+	u32 max_responder_sq_size;
+	u32 max_requester_rq_size;
+	u32 max_responder_rq_size;
+	u32 max_send_sge_count;
+	u32 max_recv_sge_count;
+	u32 max_inline_data_size;
+}; /* HW Data */
+
 int mana_ib_gd_create_dma_region(struct mana_ib_dev *dev, struct ib_umem *umem,
 				 mana_handle_t *gdma_region);
 
@@ -159,4 +208,5 @@ int mana_ib_query_gid(struct ib_device *ibdev, u32 port, int index,
 
 void mana_ib_disassociate_ucontext(struct ib_ucontext *ibcontext);
 
+int mana_ib_gd_query_adapter_caps(struct mana_ib_dev *mdev);
 #endif
diff --git a/drivers/infiniband/hw/mana/qp.c b/drivers/infiniband/hw/mana/qp.c
index ae45d28eef5e..4667b18ec1dd 100644
--- a/drivers/infiniband/hw/mana/qp.c
+++ b/drivers/infiniband/hw/mana/qp.c
@@ -130,7 +130,7 @@ static int mana_ib_create_qp_rss(struct ib_qp *ibqp, struct ib_pd *pd,
 		return ret;
 	}
 
-	if (attr->cap.max_recv_wr > MAX_SEND_BUFFERS_PER_QUEUE) {
+	if (attr->cap.max_recv_wr > mdev->adapter_caps.max_qp_wr) {
 		ibdev_dbg(&mdev->ib_dev,
 			  "Requested max_recv_wr %d exceeding limit\n",
 			  attr->cap.max_recv_wr);
@@ -296,7 +296,7 @@ static int mana_ib_create_qp_raw(struct ib_qp *ibqp, struct ib_pd *ibpd,
 	if (port < 1 || port > mc->num_ports)
 		return -EINVAL;
 
-	if (attr->cap.max_send_wr > MAX_SEND_BUFFERS_PER_QUEUE) {
+	if (attr->cap.max_send_wr > mdev->adapter_caps.max_qp_wr) {
 		ibdev_dbg(&mdev->ib_dev,
 			  "Requested max_send_wr %d exceeding limit\n",
 			  attr->cap.max_send_wr);
diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h
index 000f0d7670f7..797971e2d5a5 100644
--- a/include/net/mana/gdma.h
+++ b/include/net/mana/gdma.h
@@ -150,6 +150,7 @@ struct gdma_general_req {
 
 #define GDMA_MESSAGE_V1 1
 #define GDMA_MESSAGE_V2 2
+#define GDMA_MESSAGE_V3 3
 
 struct gdma_general_resp {
 	struct gdma_resp_hdr hdr;
-- 
cgit v1.2.3


From 0ae8e4cca78781401b17721bfb72718fdf7b4912 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Thu, 14 Dec 2023 11:50:12 +0100
Subject: netfilter: nf_tables: set transport offset from mac header for
 netdev/egress

Before this patch, transport offset (pkt->thoff) provides an offset
relative to the network header. This is fine for the inet families
because skb->data points to the network header in such case. However,
from netdev/egress, skb->data points to the mac header (if available),
thus, pkt->thoff is missing the mac header length.

Add skb_network_offset() to the transport offset (pkt->thoff) for
netdev, so transport header mangling works as expected. Adjust payload
fast eval function to use skb->data now that pkt->thoff provides an
absolute offset. This explains why users report that matching on
egress/netdev works but payload mangling does not.

This patch implicitly fixes payload mangling for IPv4 packets in
netdev/egress given skb_store_bits() requires an offset from skb->data
to reach the transport header.

I suspect that nft_exthdr and the trace infra were also broken from
netdev/egress because they also take skb->data as start, and pkt->thoff
was not correct.

Note that IPv6 is fine because ipv6_find_hdr() already provides a
transport offset starting from skb->data, which includes
skb_network_offset().

The bridge family also uses nft_set_pktinfo_ipv4_validate(), but there
skb_network_offset() is zero, so the update in this patch does not alter
the existing behaviour.

Fixes: 42df6e1d221d ("netfilter: Introduce egress hook")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables_ipv4.h | 2 +-
 net/netfilter/nf_tables_core.c         | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_tables_ipv4.h b/include/net/netfilter/nf_tables_ipv4.h
index 947973623dc7..60a7d0ce3080 100644
--- a/include/net/netfilter/nf_tables_ipv4.h
+++ b/include/net/netfilter/nf_tables_ipv4.h
@@ -30,7 +30,7 @@ static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt)
 		return -1;
 
 	len = iph_totlen(pkt->skb, iph);
-	thoff = iph->ihl * 4;
+	thoff = skb_network_offset(pkt->skb) + (iph->ihl * 4);
 	if (pkt->skb->len < len)
 		return -1;
 	else if (len < thoff)
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index 8b536d7ef6c2..c3e635364701 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -158,7 +158,7 @@ static bool nft_payload_fast_eval(const struct nft_expr *expr,
 	else {
 		if (!(pkt->flags & NFT_PKTINFO_L4PROTO))
 			return false;
-		ptr = skb_network_header(skb) + nft_thoff(pkt);
+		ptr = skb->data + nft_thoff(pkt);
 	}
 
 	ptr += priv->offset;
-- 
cgit v1.2.3


From e37a11fca41864c9f652ff81296b82e6f65a4242 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Sun, 17 Dec 2023 10:32:36 +0200
Subject: bridge: add MDB state mask uAPI attribute

Currently, the 'state' field in 'struct br_port_msg' can be set to 1 if
the MDB entry is permanent or 0 if it is temporary. Additional states
might be added in the future.

In a similar fashion to 'NDA_NDM_STATE_MASK', add an MDB state mask uAPI
attribute that will allow the upcoming bulk deletion API to bulk delete
MDB entries with a certain state or any state.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_bridge.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h
index 2e23f99dc0f1..a5b743a2f775 100644
--- a/include/uapi/linux/if_bridge.h
+++ b/include/uapi/linux/if_bridge.h
@@ -757,6 +757,7 @@ enum {
 	MDBE_ATTR_VNI,
 	MDBE_ATTR_IFINDEX,
 	MDBE_ATTR_SRC_VNI,
+	MDBE_ATTR_STATE_MASK,
 	__MDBE_ATTR_MAX,
 };
 #define MDBE_ATTR_MAX (__MDBE_ATTR_MAX - 1)
-- 
cgit v1.2.3


From 1a36e0f50f963465e9b2b980d250ab38b8fcd7a3 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Sun, 17 Dec 2023 10:32:38 +0200
Subject: net: Add MDB bulk deletion device operation

Add MDB net device operation that will be invoked by rtnetlink code in
response to received 'RTM_DELMDB' messages with the 'NLM_F_BULK' flag
set. Subsequent patches will implement the operation in the bridge and
VXLAN drivers.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 1b935ee341b4..75c7725e5e4f 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1329,6 +1329,9 @@ struct netdev_net_notifier {
  * int (*ndo_mdb_del)(struct net_device *dev, struct nlattr *tb[],
  *		      struct netlink_ext_ack *extack);
  *	Deletes the MDB entry from dev.
+ * int (*ndo_mdb_del_bulk)(struct net_device *dev, struct nlattr *tb[],
+ *			   struct netlink_ext_ack *extack);
+ *	Bulk deletes MDB entries from dev.
  * int (*ndo_mdb_dump)(struct net_device *dev, struct sk_buff *skb,
  *		       struct netlink_callback *cb);
  *	Dumps MDB entries from dev. The first argument (marker) in the netlink
@@ -1611,6 +1614,9 @@ struct net_device_ops {
 	int			(*ndo_mdb_del)(struct net_device *dev,
 					       struct nlattr *tb[],
 					       struct netlink_ext_ack *extack);
+	int			(*ndo_mdb_del_bulk)(struct net_device *dev,
+						    struct nlattr *tb[],
+						    struct netlink_ext_ack *extack);
 	int			(*ndo_mdb_dump)(struct net_device *dev,
 						struct sk_buff *skb,
 						struct netlink_callback *cb);
-- 
cgit v1.2.3


From fb2780721ca5e9f78bbe4544b819b929a982df9c Mon Sep 17 00:00:00 2001
From: Victor Nogueira <victor@mojatatu.com>
Date: Sat, 16 Dec 2023 17:44:34 -0300
Subject: net: sched: Move drop_reason to struct tc_skb_cb

Move drop_reason from struct tcf_result to skb cb - more specifically to
struct tc_skb_cb. With that, we'll be able to also set the drop reason for
the remaining qdiscs (aside from clsact) that do not have access to
tcf_result when time comes to set the skb drop reason.

Signed-off-by: Victor Nogueira <victor@mojatatu.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/pkt_cls.h     | 14 ++++++++++++--
 include/net/pkt_sched.h   |  3 ++-
 include/net/sch_generic.h |  1 -
 net/core/dev.c            |  4 ++--
 net/sched/act_api.c       |  2 +-
 net/sched/cls_api.c       | 23 ++++++++---------------
 6 files changed, 25 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index a76c9171db0e..761e4500cca0 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -154,10 +154,20 @@ __cls_set_class(unsigned long *clp, unsigned long cl)
 	return xchg(clp, cl);
 }
 
-static inline void tcf_set_drop_reason(struct tcf_result *res,
+struct tc_skb_cb;
+
+static inline struct tc_skb_cb *tc_skb_cb(const struct sk_buff *skb);
+
+static inline enum skb_drop_reason
+tcf_get_drop_reason(const struct sk_buff *skb)
+{
+	return tc_skb_cb(skb)->drop_reason;
+}
+
+static inline void tcf_set_drop_reason(const struct sk_buff *skb,
 				       enum skb_drop_reason reason)
 {
-	res->drop_reason = reason;
+	tc_skb_cb(skb)->drop_reason = reason;
 }
 
 static inline void
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index 9fa1d0794dfa..9b559aa5c079 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -277,12 +277,13 @@ static inline void skb_txtime_consumed(struct sk_buff *skb)
 
 struct tc_skb_cb {
 	struct qdisc_skb_cb qdisc_cb;
+	u32 drop_reason;
 
+	u16 zone; /* Only valid if post_ct = true */
 	u16 mru;
 	u8 post_ct:1;
 	u8 post_ct_snat:1;
 	u8 post_ct_dnat:1;
-	u16 zone; /* Only valid if post_ct = true */
 };
 
 static inline struct tc_skb_cb *tc_skb_cb(const struct sk_buff *skb)
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index dcb9160e6467..c499b56bb215 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -332,7 +332,6 @@ struct tcf_result {
 		};
 		const struct tcf_proto *goto_tp;
 	};
-	enum skb_drop_reason		drop_reason;
 };
 
 struct tcf_chain;
diff --git a/net/core/dev.c b/net/core/dev.c
index 0432b04cf9b0..16af89a733e4 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3923,14 +3923,14 @@ static int tc_run(struct tcx_entry *entry, struct sk_buff *skb,
 
 	tc_skb_cb(skb)->mru = 0;
 	tc_skb_cb(skb)->post_ct = false;
-	res.drop_reason = *drop_reason;
+	tcf_set_drop_reason(skb, *drop_reason);
 
 	mini_qdisc_bstats_cpu_update(miniq, skb);
 	ret = tcf_classify(skb, miniq->block, miniq->filter_list, &res, false);
 	/* Only tcf related quirks below. */
 	switch (ret) {
 	case TC_ACT_SHOT:
-		*drop_reason = res.drop_reason;
+		*drop_reason = tcf_get_drop_reason(skb);
 		mini_qdisc_qstats_cpu_drop(miniq);
 		break;
 	case TC_ACT_OK:
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 3a7770eff52d..db500aa9f841 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -1119,7 +1119,7 @@ repeat:
 			}
 		} else if (TC_ACT_EXT_CMP(ret, TC_ACT_GOTO_CHAIN)) {
 			if (unlikely(!rcu_access_pointer(a->goto_chain))) {
-				tcf_set_drop_reason(res, SKB_DROP_REASON_TC_ERROR);
+				tcf_set_drop_reason(skb, SKB_DROP_REASON_TC_ERROR);
 				return TC_ACT_SHOT;
 			}
 			tcf_action_goto_chain_exec(a, res);
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index dc1c19a25882..199406e4bcdd 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1657,7 +1657,6 @@ static inline int __tcf_classify(struct sk_buff *skb,
 				 int act_index,
 				 u32 *last_executed_chain)
 {
-	u32 orig_reason = res->drop_reason;
 #ifdef CONFIG_NET_CLS_ACT
 	const int max_reclassify_loop = 16;
 	const struct tcf_proto *first_tp;
@@ -1682,13 +1681,13 @@ reclassify:
 			 */
 			if (unlikely(n->tp != tp || n->tp->chain != n->chain ||
 				     !tp->ops->get_exts)) {
-				tcf_set_drop_reason(res, SKB_DROP_REASON_TC_ERROR);
+				tcf_set_drop_reason(skb, SKB_DROP_REASON_TC_ERROR);
 				return TC_ACT_SHOT;
 			}
 
 			exts = tp->ops->get_exts(tp, n->handle);
 			if (unlikely(!exts || n->exts != exts)) {
-				tcf_set_drop_reason(res, SKB_DROP_REASON_TC_ERROR);
+				tcf_set_drop_reason(skb, SKB_DROP_REASON_TC_ERROR);
 				return TC_ACT_SHOT;
 			}
 
@@ -1712,18 +1711,12 @@ reclassify:
 			goto reset;
 		}
 #endif
-		if (err >= 0) {
-			/* Policy drop or drop reason is over-written by
-			 * classifiers with a bogus value(0) */
-			if (err == TC_ACT_SHOT &&
-			    res->drop_reason == SKB_NOT_DROPPED_YET)
-				tcf_set_drop_reason(res, orig_reason);
+		if (err >= 0)
 			return err;
-		}
 	}
 
 	if (unlikely(n)) {
-		tcf_set_drop_reason(res, SKB_DROP_REASON_TC_ERROR);
+		tcf_set_drop_reason(skb, SKB_DROP_REASON_TC_ERROR);
 		return TC_ACT_SHOT;
 	}
 
@@ -1735,7 +1728,7 @@ reset:
 				       tp->chain->block->index,
 				       tp->prio & 0xffff,
 				       ntohs(tp->protocol));
-		tcf_set_drop_reason(res, SKB_DROP_REASON_TC_ERROR);
+		tcf_set_drop_reason(skb, SKB_DROP_REASON_TC_ERROR);
 		return TC_ACT_SHOT;
 	}
 
@@ -1773,7 +1766,7 @@ int tcf_classify(struct sk_buff *skb,
 				n = tcf_exts_miss_cookie_lookup(ext->act_miss_cookie,
 								&act_index);
 				if (!n) {
-					tcf_set_drop_reason(res, SKB_DROP_REASON_TC_ERROR);
+					tcf_set_drop_reason(skb, SKB_DROP_REASON_TC_ERROR);
 					return TC_ACT_SHOT;
 				}
 
@@ -1784,7 +1777,7 @@ int tcf_classify(struct sk_buff *skb,
 
 			fchain = tcf_chain_lookup_rcu(block, chain);
 			if (!fchain) {
-				tcf_set_drop_reason(res, SKB_DROP_REASON_TC_ERROR);
+				tcf_set_drop_reason(skb, SKB_DROP_REASON_TC_ERROR);
 				return TC_ACT_SHOT;
 			}
 
@@ -1806,7 +1799,7 @@ int tcf_classify(struct sk_buff *skb,
 
 			ext = tc_skb_ext_alloc(skb);
 			if (WARN_ON_ONCE(!ext)) {
-				tcf_set_drop_reason(res, SKB_DROP_REASON_TC_ERROR);
+				tcf_set_drop_reason(skb, SKB_DROP_REASON_TC_ERROR);
 				return TC_ACT_SHOT;
 			}
 
-- 
cgit v1.2.3


From b6a3c6066afc2cb7b92f45c67ab0b12ded81cb11 Mon Sep 17 00:00:00 2001
From: Victor Nogueira <victor@mojatatu.com>
Date: Sat, 16 Dec 2023 17:44:35 -0300
Subject: net: sched: Make tc-related drop reason more flexible for remaining
 qdiscs

Incrementing on Daniel's patch[1], make tc-related drop reason more
flexible for remaining qdiscs - that is, all qdiscs aside from clsact.
In essence, the drop reason will be set by cls_api and act_api in case
any error occurred in the data path. With that, we can give the user more
detailed information so that they can distinguish between a policy drop
or an error drop.

[1] https://lore.kernel.org/all/20231009092655.22025-1-daniel@iogearbox.net

Signed-off-by: Victor Nogueira <victor@mojatatu.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/pkt_cls.h     | 16 ----------------
 include/net/pkt_sched.h   | 19 -------------------
 include/net/sch_generic.h | 31 +++++++++++++++++++++++++++++++
 net/core/dev.c            |  7 +++++--
 4 files changed, 36 insertions(+), 37 deletions(-)

(limited to 'include')

diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 761e4500cca0..f308e8268651 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -154,22 +154,6 @@ __cls_set_class(unsigned long *clp, unsigned long cl)
 	return xchg(clp, cl);
 }
 
-struct tc_skb_cb;
-
-static inline struct tc_skb_cb *tc_skb_cb(const struct sk_buff *skb);
-
-static inline enum skb_drop_reason
-tcf_get_drop_reason(const struct sk_buff *skb)
-{
-	return tc_skb_cb(skb)->drop_reason;
-}
-
-static inline void tcf_set_drop_reason(const struct sk_buff *skb,
-				       enum skb_drop_reason reason)
-{
-	tc_skb_cb(skb)->drop_reason = reason;
-}
-
 static inline void
 __tcf_bind_filter(struct Qdisc *q, struct tcf_result *r, unsigned long base)
 {
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index 9b559aa5c079..1e200d9a066d 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -275,25 +275,6 @@ static inline void skb_txtime_consumed(struct sk_buff *skb)
 	skb->tstamp = ktime_set(0, 0);
 }
 
-struct tc_skb_cb {
-	struct qdisc_skb_cb qdisc_cb;
-	u32 drop_reason;
-
-	u16 zone; /* Only valid if post_ct = true */
-	u16 mru;
-	u8 post_ct:1;
-	u8 post_ct_snat:1;
-	u8 post_ct_dnat:1;
-};
-
-static inline struct tc_skb_cb *tc_skb_cb(const struct sk_buff *skb)
-{
-	struct tc_skb_cb *cb = (struct tc_skb_cb *)skb->cb;
-
-	BUILD_BUG_ON(sizeof(*cb) > sizeof_field(struct sk_buff, cb));
-	return cb;
-}
-
 static inline bool tc_qdisc_stats_dump(struct Qdisc *sch,
 				       unsigned long cl,
 				       struct qdisc_walker *arg)
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index c499b56bb215..1d70c2c1572f 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -1036,6 +1036,37 @@ static inline struct sk_buff *qdisc_dequeue_head(struct Qdisc *sch)
 	return skb;
 }
 
+struct tc_skb_cb {
+	struct qdisc_skb_cb qdisc_cb;
+	u32 drop_reason;
+
+	u16 zone; /* Only valid if post_ct = true */
+	u16 mru;
+	u8 post_ct:1;
+	u8 post_ct_snat:1;
+	u8 post_ct_dnat:1;
+};
+
+static inline struct tc_skb_cb *tc_skb_cb(const struct sk_buff *skb)
+{
+	struct tc_skb_cb *cb = (struct tc_skb_cb *)skb->cb;
+
+	BUILD_BUG_ON(sizeof(*cb) > sizeof_field(struct sk_buff, cb));
+	return cb;
+}
+
+static inline enum skb_drop_reason
+tcf_get_drop_reason(const struct sk_buff *skb)
+{
+	return tc_skb_cb(skb)->drop_reason;
+}
+
+static inline void tcf_set_drop_reason(const struct sk_buff *skb,
+				       enum skb_drop_reason reason)
+{
+	tc_skb_cb(skb)->drop_reason = reason;
+}
+
 /* Instead of calling kfree_skb() while root qdisc lock is held,
  * queue the skb for future freeing at end of __dev_xmit_skb()
  */
diff --git a/net/core/dev.c b/net/core/dev.c
index 16af89a733e4..b87504078320 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3753,6 +3753,8 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 
 	qdisc_calculate_pkt_len(skb, q);
 
+	tcf_set_drop_reason(skb, SKB_DROP_REASON_QDISC_DROP);
+
 	if (q->flags & TCQ_F_NOLOCK) {
 		if (q->flags & TCQ_F_CAN_BYPASS && nolock_qdisc_is_empty(q) &&
 		    qdisc_run_begin(q)) {
@@ -3782,7 +3784,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 no_lock_out:
 		if (unlikely(to_free))
 			kfree_skb_list_reason(to_free,
-					      SKB_DROP_REASON_QDISC_DROP);
+					      tcf_get_drop_reason(to_free));
 		return rc;
 	}
 
@@ -3837,7 +3839,8 @@ no_lock_out:
 	}
 	spin_unlock(root_lock);
 	if (unlikely(to_free))
-		kfree_skb_list_reason(to_free, SKB_DROP_REASON_QDISC_DROP);
+		kfree_skb_list_reason(to_free,
+				      tcf_get_drop_reason(to_free));
 	if (unlikely(contended))
 		spin_unlock(&q->busylock);
 	return rc;
-- 
cgit v1.2.3


From 4cf24dc8934074725042c0bd10b91f4d4b5269bb Mon Sep 17 00:00:00 2001
From: Victor Nogueira <victor@mojatatu.com>
Date: Sat, 16 Dec 2023 17:44:36 -0300
Subject: net: sched: Add initial TC error skb drop reasons

Continue expanding Daniel's patch by adding new skb drop reasons that
are idiosyncratic to TC.

More specifically:

- SKB_DROP_REASON_TC_COOKIE_ERROR: An error occurred whilst
  processing a tc ext cookie.

- SKB_DROP_REASON_TC_CHAIN_NOTFOUND: tc chain lookup failed.

- SKB_DROP_REASON_TC_RECLASSIFY_LOOP: tc exceeded max reclassify loop
  iterations

Signed-off-by: Victor Nogueira <victor@mojatatu.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dropreason-core.h | 18 +++++++++++++++---
 net/sched/act_api.c           |  3 ++-
 net/sched/cls_api.c           | 22 ++++++++++++++--------
 3 files changed, 31 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/net/dropreason-core.h b/include/net/dropreason-core.h
index 278e4c7d465c..6d3a20163260 100644
--- a/include/net/dropreason-core.h
+++ b/include/net/dropreason-core.h
@@ -85,8 +85,10 @@
 	FN(IPV6_NDISC_BAD_OPTIONS)	\
 	FN(IPV6_NDISC_NS_OTHERHOST)	\
 	FN(QUEUE_PURGE)			\
-	FN(TC_ERROR)			\
+	FN(TC_COOKIE_ERROR)		\
 	FN(PACKET_SOCK_ERROR)		\
+	FN(TC_CHAIN_NOTFOUND)		\
+	FN(TC_RECLASSIFY_LOOP)		\
 	FNe(MAX)
 
 /**
@@ -377,13 +379,23 @@ enum skb_drop_reason {
 	SKB_DROP_REASON_IPV6_NDISC_NS_OTHERHOST,
 	/** @SKB_DROP_REASON_QUEUE_PURGE: bulk free. */
 	SKB_DROP_REASON_QUEUE_PURGE,
-	/** @SKB_DROP_REASON_TC_ERROR: generic internal tc error. */
-	SKB_DROP_REASON_TC_ERROR,
+	/**
+	 * @SKB_DROP_REASON_TC_COOKIE_ERROR: An error occurred whilst
+	 * processing a tc ext cookie.
+	 */
+	SKB_DROP_REASON_TC_COOKIE_ERROR,
 	/**
 	 * @SKB_DROP_REASON_PACKET_SOCK_ERROR: generic packet socket errors
 	 * after its filter matches an incoming packet.
 	 */
 	SKB_DROP_REASON_PACKET_SOCK_ERROR,
+	/** @SKB_DROP_REASON_TC_CHAIN_NOTFOUND: tc chain lookup failed. */
+	SKB_DROP_REASON_TC_CHAIN_NOTFOUND,
+	/**
+	 * @SKB_DROP_REASON_TC_RECLASSIFY_LOOP: tc exceeded max reclassify loop
+	 * iterations.
+	 */
+	SKB_DROP_REASON_TC_RECLASSIFY_LOOP,
 	/**
 	 * @SKB_DROP_REASON_MAX: the maximum of core drop reasons, which
 	 * shouldn't be used as a real 'reason' - only for tracing code gen
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index db500aa9f841..a44c097a880d 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -1119,7 +1119,8 @@ repeat:
 			}
 		} else if (TC_ACT_EXT_CMP(ret, TC_ACT_GOTO_CHAIN)) {
 			if (unlikely(!rcu_access_pointer(a->goto_chain))) {
-				tcf_set_drop_reason(skb, SKB_DROP_REASON_TC_ERROR);
+				tcf_set_drop_reason(skb,
+						    SKB_DROP_REASON_TC_CHAIN_NOTFOUND);
 				return TC_ACT_SHOT;
 			}
 			tcf_action_goto_chain_exec(a, res);
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 199406e4bcdd..8978cf5531d0 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1681,13 +1681,15 @@ reclassify:
 			 */
 			if (unlikely(n->tp != tp || n->tp->chain != n->chain ||
 				     !tp->ops->get_exts)) {
-				tcf_set_drop_reason(skb, SKB_DROP_REASON_TC_ERROR);
+				tcf_set_drop_reason(skb,
+						    SKB_DROP_REASON_TC_COOKIE_ERROR);
 				return TC_ACT_SHOT;
 			}
 
 			exts = tp->ops->get_exts(tp, n->handle);
 			if (unlikely(!exts || n->exts != exts)) {
-				tcf_set_drop_reason(skb, SKB_DROP_REASON_TC_ERROR);
+				tcf_set_drop_reason(skb,
+						    SKB_DROP_REASON_TC_COOKIE_ERROR);
 				return TC_ACT_SHOT;
 			}
 
@@ -1716,7 +1718,8 @@ reclassify:
 	}
 
 	if (unlikely(n)) {
-		tcf_set_drop_reason(skb, SKB_DROP_REASON_TC_ERROR);
+		tcf_set_drop_reason(skb,
+				    SKB_DROP_REASON_TC_COOKIE_ERROR);
 		return TC_ACT_SHOT;
 	}
 
@@ -1728,7 +1731,8 @@ reset:
 				       tp->chain->block->index,
 				       tp->prio & 0xffff,
 				       ntohs(tp->protocol));
-		tcf_set_drop_reason(skb, SKB_DROP_REASON_TC_ERROR);
+		tcf_set_drop_reason(skb,
+				    SKB_DROP_REASON_TC_RECLASSIFY_LOOP);
 		return TC_ACT_SHOT;
 	}
 
@@ -1766,7 +1770,8 @@ int tcf_classify(struct sk_buff *skb,
 				n = tcf_exts_miss_cookie_lookup(ext->act_miss_cookie,
 								&act_index);
 				if (!n) {
-					tcf_set_drop_reason(skb, SKB_DROP_REASON_TC_ERROR);
+					tcf_set_drop_reason(skb,
+							    SKB_DROP_REASON_TC_COOKIE_ERROR);
 					return TC_ACT_SHOT;
 				}
 
@@ -1777,7 +1782,9 @@ int tcf_classify(struct sk_buff *skb,
 
 			fchain = tcf_chain_lookup_rcu(block, chain);
 			if (!fchain) {
-				tcf_set_drop_reason(skb, SKB_DROP_REASON_TC_ERROR);
+				tcf_set_drop_reason(skb,
+						    SKB_DROP_REASON_TC_CHAIN_NOTFOUND);
+
 				return TC_ACT_SHOT;
 			}
 
@@ -1799,10 +1806,9 @@ int tcf_classify(struct sk_buff *skb,
 
 			ext = tc_skb_ext_alloc(skb);
 			if (WARN_ON_ONCE(!ext)) {
-				tcf_set_drop_reason(skb, SKB_DROP_REASON_TC_ERROR);
+				tcf_set_drop_reason(skb, SKB_DROP_REASON_NOMEM);
 				return TC_ACT_SHOT;
 			}
-
 			ext->chain = last_executed_chain;
 			ext->mru = cb->mru;
 			ext->post_ct = cb->post_ct;
-- 
cgit v1.2.3


From 40ca4ee3136d2d09977d1cab8c0c0e1582c3359d Mon Sep 17 00:00:00 2001
From: Mimi Zohar <zohar@linux.ibm.com>
Date: Tue, 12 Dec 2023 06:12:43 -0500
Subject: evm: don't copy up 'security.evm' xattr

The security.evm HMAC and the original file signatures contain
filesystem specific data.  As a result, the HMAC and signature
are not the same on the stacked and backing filesystems.

Don't copy up 'security.evm'.

Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
---
 include/linux/evm.h               | 6 ++++++
 security/integrity/evm/evm_main.c | 7 +++++++
 security/security.c               | 2 +-
 3 files changed, 14 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/evm.h b/include/linux/evm.h
index 01fc495a83e2..36ec884320d9 100644
--- a/include/linux/evm.h
+++ b/include/linux/evm.h
@@ -31,6 +31,7 @@ extern void evm_inode_post_setxattr(struct dentry *dentry,
 				    const char *xattr_name,
 				    const void *xattr_value,
 				    size_t xattr_value_len);
+extern int evm_inode_copy_up_xattr(const char *name);
 extern int evm_inode_removexattr(struct mnt_idmap *idmap,
 				 struct dentry *dentry, const char *xattr_name);
 extern void evm_inode_post_removexattr(struct dentry *dentry,
@@ -117,6 +118,11 @@ static inline void evm_inode_post_setxattr(struct dentry *dentry,
 	return;
 }
 
+static inline int  evm_inode_copy_up_xattr(const char *name)
+{
+	return 0;
+}
+
 static inline int evm_inode_removexattr(struct mnt_idmap *idmap,
 					struct dentry *dentry,
 					const char *xattr_name)
diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c
index 894570fe39bc..02adba635b02 100644
--- a/security/integrity/evm/evm_main.c
+++ b/security/integrity/evm/evm_main.c
@@ -863,6 +863,13 @@ void evm_inode_post_setattr(struct dentry *dentry, int ia_valid)
 		evm_update_evmxattr(dentry, NULL, NULL, 0);
 }
 
+int evm_inode_copy_up_xattr(const char *name)
+{
+	if (strcmp(name, XATTR_NAME_EVM) == 0)
+		return 1; /* Discard */
+	return -EOPNOTSUPP;
+}
+
 /*
  * evm_inode_init_security - initializes security.evm HMAC value
  */
diff --git a/security/security.c b/security/security.c
index dcb3e7014f9b..f00ec4d988b8 100644
--- a/security/security.c
+++ b/security/security.c
@@ -2539,7 +2539,7 @@ int security_inode_copy_up_xattr(const char *name)
 			return rc;
 	}
 
-	return LSM_RET_DEFAULT(inode_copy_up_xattr);
+	return evm_inode_copy_up_xattr(name);
 }
 EXPORT_SYMBOL(security_inode_copy_up_xattr);
 
-- 
cgit v1.2.3


From cd708c938f055c9eb5a366ec1c8edcefa28afc28 Mon Sep 17 00:00:00 2001
From: Mimi Zohar <zohar@linux.ibm.com>
Date: Mon, 18 Dec 2023 08:06:40 -0500
Subject: evm: add support to disable EVM on unsupported filesystems

Identify EVM unsupported filesystems by defining a new flag
SB_I_EVM_UNSUPPORTED.

Don't verify, write, remove or update 'security.evm' on unsupported
filesystems.

Acked-by: Amir Goldstein <amir73il@gmail.com>
Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
---
 include/linux/fs.h                |  1 +
 security/integrity/evm/evm_main.c | 35 ++++++++++++++++++++++++++++++++++-
 2 files changed, 35 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 98b7a7a8c42e..1474f36e9b38 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1164,6 +1164,7 @@ extern int send_sigurg(struct fown_struct *fown);
 #define SB_I_USERNS_VISIBLE		0x00000010 /* fstype already mounted */
 #define SB_I_IMA_UNVERIFIABLE_SIGNATURE	0x00000020
 #define SB_I_UNTRUSTED_MOUNTER		0x00000040
+#define SB_I_EVM_UNSUPPORTED		0x00000080
 
 #define SB_I_SKIP_SYNC	0x00000100	/* Skip superblock at global sync */
 #define SB_I_PERSB_BDI	0x00000200	/* has a per-sb bdi */
diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c
index 02adba635b02..cc7956d7878b 100644
--- a/security/integrity/evm/evm_main.c
+++ b/security/integrity/evm/evm_main.c
@@ -151,6 +151,17 @@ static int evm_find_protected_xattrs(struct dentry *dentry)
 	return count;
 }
 
+static int is_unsupported_fs(struct dentry *dentry)
+{
+	struct inode *inode = d_backing_inode(dentry);
+
+	if (inode->i_sb->s_iflags & SB_I_EVM_UNSUPPORTED) {
+		pr_info_once("%s not supported\n", inode->i_sb->s_type->name);
+		return 1;
+	}
+	return 0;
+}
+
 /*
  * evm_verify_hmac - calculate and compare the HMAC with the EVM xattr
  *
@@ -181,6 +192,9 @@ static enum integrity_status evm_verify_hmac(struct dentry *dentry,
 		     iint->evm_status == INTEGRITY_PASS_IMMUTABLE))
 		return iint->evm_status;
 
+	if (is_unsupported_fs(dentry))
+		return INTEGRITY_UNKNOWN;
+
 	/* if status is not PASS, try to check again - against -ENOMEM */
 
 	/* first need to know the sig type */
@@ -408,6 +422,9 @@ enum integrity_status evm_verifyxattr(struct dentry *dentry,
 	if (!evm_key_loaded() || !evm_protected_xattr(xattr_name))
 		return INTEGRITY_UNKNOWN;
 
+	if (is_unsupported_fs(dentry))
+		return INTEGRITY_UNKNOWN;
+
 	if (!iint) {
 		iint = integrity_iint_find(d_backing_inode(dentry));
 		if (!iint)
@@ -491,15 +508,21 @@ static int evm_protect_xattr(struct mnt_idmap *idmap,
 	if (strcmp(xattr_name, XATTR_NAME_EVM) == 0) {
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
+		if (is_unsupported_fs(dentry))
+			return -EPERM;
 	} else if (!evm_protected_xattr(xattr_name)) {
 		if (!posix_xattr_acl(xattr_name))
 			return 0;
+		if (is_unsupported_fs(dentry))
+			return 0;
+
 		evm_status = evm_verify_current_integrity(dentry);
 		if ((evm_status == INTEGRITY_PASS) ||
 		    (evm_status == INTEGRITY_NOXATTRS))
 			return 0;
 		goto out;
-	}
+	} else if (is_unsupported_fs(dentry))
+		return 0;
 
 	evm_status = evm_verify_current_integrity(dentry);
 	if (evm_status == INTEGRITY_NOXATTRS) {
@@ -750,6 +773,9 @@ void evm_inode_post_setxattr(struct dentry *dentry, const char *xattr_name,
 	if (!(evm_initialized & EVM_INIT_HMAC))
 		return;
 
+	if (is_unsupported_fs(dentry))
+		return;
+
 	evm_update_evmxattr(dentry, xattr_name, xattr_value, xattr_value_len);
 }
 
@@ -814,8 +840,12 @@ int evm_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 	if (evm_initialized & EVM_ALLOW_METADATA_WRITES)
 		return 0;
 
+	if (is_unsupported_fs(dentry))
+		return 0;
+
 	if (!(ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID)))
 		return 0;
+
 	evm_status = evm_verify_current_integrity(dentry);
 	/*
 	 * Writing attrs is safe for portable signatures, as portable signatures
@@ -859,6 +889,9 @@ void evm_inode_post_setattr(struct dentry *dentry, int ia_valid)
 	if (!(evm_initialized & EVM_INIT_HMAC))
 		return;
 
+	if (is_unsupported_fs(dentry))
+		return;
+
 	if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID))
 		evm_update_evmxattr(dentry, NULL, NULL, 0);
 }
-- 
cgit v1.2.3


From 139f84002145d8624f0195fb090b3a7670744a13 Mon Sep 17 00:00:00 2001
From: "Tzvetomir Stoyanov (VMware)" <tz.stoyanov@gmail.com>
Date: Tue, 19 Dec 2023 13:54:16 -0500
Subject: ring-buffer: Page size per ring buffer

Currently the size of one sub buffer page is global for all buffers and
it is hard coded to one system page. In order to introduce configurable
ring buffer sub page size, the internal logic should be refactored to
work with sub page size per ring buffer.

Link: https://lore.kernel.org/linux-trace-devel/20211213094825.61876-3-tz.stoyanov@gmail.com
Link: https://lore.kernel.org/linux-trace-kernel/20231219185628.009147038@goodmis.org

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Vincent Donnefort <vdonnefort@google.com>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/ring_buffer.h |  2 +-
 kernel/trace/ring_buffer.c  | 68 +++++++++++++++++++++++++--------------------
 kernel/trace/trace.c        |  2 +-
 kernel/trace/trace.h        |  1 +
 kernel/trace/trace_events.c | 59 +++++++++++++++++++++++++++++----------
 5 files changed, 86 insertions(+), 46 deletions(-)

(limited to 'include')

diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index b1b03b2c0f08..ce46218ce46d 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -200,7 +200,7 @@ int ring_buffer_read_page(struct trace_buffer *buffer, void **data_page,
 struct trace_seq;
 
 int ring_buffer_print_entry_header(struct trace_seq *s);
-int ring_buffer_print_page_header(struct trace_seq *s);
+int ring_buffer_print_page_header(struct trace_buffer *buffer, struct trace_seq *s);
 
 enum ring_buffer_flags {
 	RB_FL_OVERWRITE		= 1 << 0,
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 2400c8e68fd3..d9f656502400 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -374,11 +374,6 @@ static inline bool test_time_stamp(u64 delta)
 	return !!(delta & TS_DELTA_TEST);
 }
 
-#define BUF_PAGE_SIZE (PAGE_SIZE - BUF_PAGE_HDR_SIZE)
-
-/* Max payload is BUF_PAGE_SIZE - header (8bytes) */
-#define BUF_MAX_DATA_SIZE (BUF_PAGE_SIZE - (sizeof(u32) * 2))
-
 struct rb_irq_work {
 	struct irq_work			work;
 	wait_queue_head_t		waiters;
@@ -510,6 +505,9 @@ struct trace_buffer {
 
 	struct rb_irq_work		irq_work;
 	bool				time_stamp_abs;
+
+	unsigned int			subbuf_size;
+	unsigned int			max_data_size;
 };
 
 struct ring_buffer_iter {
@@ -523,10 +521,11 @@ struct ring_buffer_iter {
 	u64				read_stamp;
 	u64				page_stamp;
 	struct ring_buffer_event	*event;
+	size_t				event_size;
 	int				missed_events;
 };
 
-int ring_buffer_print_page_header(struct trace_seq *s)
+int ring_buffer_print_page_header(struct trace_buffer *buffer, struct trace_seq *s)
 {
 	struct buffer_data_page field;
 
@@ -550,7 +549,7 @@ int ring_buffer_print_page_header(struct trace_seq *s)
 	trace_seq_printf(s, "\tfield: char data;\t"
 			 "offset:%u;\tsize:%u;\tsigned:%u;\n",
 			 (unsigned int)offsetof(typeof(field), data),
-			 (unsigned int)BUF_PAGE_SIZE,
+			 (unsigned int)buffer->subbuf_size,
 			 (unsigned int)is_signed_type(char));
 
 	return !trace_seq_has_overflowed(s);
@@ -1625,7 +1624,13 @@ struct trace_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
 	if (!zalloc_cpumask_var(&buffer->cpumask, GFP_KERNEL))
 		goto fail_free_buffer;
 
-	nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
+	/* Default buffer page size - one system page */
+	buffer->subbuf_size = PAGE_SIZE - BUF_PAGE_HDR_SIZE;
+
+	/* Max payload is buffer page size - header (8bytes) */
+	buffer->max_data_size = buffer->subbuf_size - (sizeof(u32) * 2);
+
+	nr_pages = DIV_ROUND_UP(size, buffer->subbuf_size);
 	buffer->flags = flags;
 	buffer->clock = trace_clock_local;
 	buffer->reader_lock_key = key;
@@ -1944,7 +1949,7 @@ static void update_pages_handler(struct work_struct *work)
  * @size: the new size.
  * @cpu_id: the cpu buffer to resize
  *
- * Minimum size is 2 * BUF_PAGE_SIZE.
+ * Minimum size is 2 * buffer->subbuf_size.
  *
  * Returns 0 on success and < 0 on failure.
  */
@@ -1966,7 +1971,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
 	    !cpumask_test_cpu(cpu_id, buffer->cpumask))
 		return 0;
 
-	nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
+	nr_pages = DIV_ROUND_UP(size, buffer->subbuf_size);
 
 	/* we need a minimum of two pages */
 	if (nr_pages < 2)
@@ -2213,7 +2218,7 @@ rb_iter_head_event(struct ring_buffer_iter *iter)
 	 */
 	barrier();
 
-	if ((iter->head + length) > commit || length > BUF_PAGE_SIZE)
+	if ((iter->head + length) > commit || length > iter->event_size)
 		/* Writer corrupted the read? */
 		goto reset;
 
@@ -2446,6 +2451,7 @@ static inline void
 rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	      unsigned long tail, struct rb_event_info *info)
 {
+	unsigned long bsize = READ_ONCE(cpu_buffer->buffer->subbuf_size);
 	struct buffer_page *tail_page = info->tail_page;
 	struct ring_buffer_event *event;
 	unsigned long length = info->length;
@@ -2454,13 +2460,13 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	 * Only the event that crossed the page boundary
 	 * must fill the old tail_page with padding.
 	 */
-	if (tail >= BUF_PAGE_SIZE) {
+	if (tail >= bsize) {
 		/*
 		 * If the page was filled, then we still need
 		 * to update the real_end. Reset it to zero
 		 * and the reader will ignore it.
 		 */
-		if (tail == BUF_PAGE_SIZE)
+		if (tail == bsize)
 			tail_page->real_end = 0;
 
 		local_sub(length, &tail_page->write);
@@ -2488,7 +2494,7 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	 * If we are less than the minimum size, we don't need to
 	 * worry about it.
 	 */
-	if (tail > (BUF_PAGE_SIZE - RB_EVNT_MIN_SIZE)) {
+	if (tail > (bsize - RB_EVNT_MIN_SIZE)) {
 		/* No room for any events */
 
 		/* Mark the rest of the page with padding */
@@ -2503,19 +2509,19 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	}
 
 	/* Put in a discarded event */
-	event->array[0] = (BUF_PAGE_SIZE - tail) - RB_EVNT_HDR_SIZE;
+	event->array[0] = (bsize - tail) - RB_EVNT_HDR_SIZE;
 	event->type_len = RINGBUF_TYPE_PADDING;
 	/* time delta must be non zero */
 	event->time_delta = 1;
 
 	/* account for padding bytes */
-	local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes);
+	local_add(bsize - tail, &cpu_buffer->entries_bytes);
 
 	/* Make sure the padding is visible before the tail_page->write update */
 	smp_wmb();
 
 	/* Set write to end of buffer */
-	length = (tail + length) - BUF_PAGE_SIZE;
+	length = (tail + length) - bsize;
 	local_sub(length, &tail_page->write);
 }
 
@@ -3469,7 +3475,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 	tail = write - info->length;
 
 	/* See if we shot pass the end of this buffer page */
-	if (unlikely(write > BUF_PAGE_SIZE)) {
+	if (unlikely(write > cpu_buffer->buffer->subbuf_size)) {
 		check_buffer(cpu_buffer, info, CHECK_FULL_PAGE);
 		return rb_move_tail(cpu_buffer, tail, info);
 	}
@@ -3600,7 +3606,7 @@ rb_reserve_next_event(struct trace_buffer *buffer,
 	if (ring_buffer_time_stamp_abs(cpu_buffer->buffer)) {
 		add_ts_default = RB_ADD_STAMP_ABSOLUTE;
 		info.length += RB_LEN_TIME_EXTEND;
-		if (info.length > BUF_MAX_DATA_SIZE)
+		if (info.length > cpu_buffer->buffer->max_data_size)
 			goto out_fail;
 	} else {
 		add_ts_default = RB_ADD_STAMP_NONE;
@@ -3675,7 +3681,7 @@ ring_buffer_lock_reserve(struct trace_buffer *buffer, unsigned long length)
 	if (unlikely(atomic_read(&cpu_buffer->record_disabled)))
 		goto out;
 
-	if (unlikely(length > BUF_MAX_DATA_SIZE))
+	if (unlikely(length > buffer->max_data_size))
 		goto out;
 
 	if (unlikely(trace_recursive_lock(cpu_buffer)))
@@ -3825,7 +3831,7 @@ int ring_buffer_write(struct trace_buffer *buffer,
 	if (atomic_read(&cpu_buffer->record_disabled))
 		goto out;
 
-	if (length > BUF_MAX_DATA_SIZE)
+	if (length > buffer->max_data_size)
 		goto out;
 
 	if (unlikely(trace_recursive_lock(cpu_buffer)))
@@ -4405,6 +4411,7 @@ static struct buffer_page *
 rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 {
 	struct buffer_page *reader = NULL;
+	unsigned long bsize = READ_ONCE(cpu_buffer->buffer->subbuf_size);
 	unsigned long overwrite;
 	unsigned long flags;
 	int nr_loops = 0;
@@ -4540,7 +4547,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 #define USECS_WAIT	1000000
         for (nr_loops = 0; nr_loops < USECS_WAIT; nr_loops++) {
 		/* If the write is past the end of page, a writer is still updating it */
-		if (likely(!reader || rb_page_write(reader) <= BUF_PAGE_SIZE))
+		if (likely(!reader || rb_page_write(reader) <= bsize))
 			break;
 
 		udelay(1);
@@ -4984,7 +4991,8 @@ ring_buffer_read_prepare(struct trace_buffer *buffer, int cpu, gfp_t flags)
 		return NULL;
 
 	/* Holds the entire event: data and meta data */
-	iter->event = kmalloc(BUF_PAGE_SIZE, flags);
+	iter->event_size = buffer->subbuf_size;
+	iter->event = kmalloc(iter->event_size, flags);
 	if (!iter->event) {
 		kfree(iter);
 		return NULL;
@@ -5102,14 +5110,14 @@ unsigned long ring_buffer_size(struct trace_buffer *buffer, int cpu)
 {
 	/*
 	 * Earlier, this method returned
-	 *	BUF_PAGE_SIZE * buffer->nr_pages
+	 *	buffer->subbuf_size * buffer->nr_pages
 	 * Since the nr_pages field is now removed, we have converted this to
 	 * return the per cpu buffer value.
 	 */
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return 0;
 
-	return BUF_PAGE_SIZE * buffer->buffers[cpu]->nr_pages;
+	return buffer->subbuf_size * buffer->buffers[cpu]->nr_pages;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_size);
 
@@ -5123,8 +5131,8 @@ unsigned long ring_buffer_max_event_size(struct trace_buffer *buffer)
 {
 	/* If abs timestamp is requested, events have a timestamp too */
 	if (ring_buffer_time_stamp_abs(buffer))
-		return BUF_MAX_DATA_SIZE - RB_LEN_TIME_EXTEND;
-	return BUF_MAX_DATA_SIZE;
+		return buffer->max_data_size - RB_LEN_TIME_EXTEND;
+	return buffer->max_data_size;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_max_event_size);
 
@@ -5730,7 +5738,7 @@ int ring_buffer_read_page(struct trace_buffer *buffer,
 		/* If there is room at the end of the page to save the
 		 * missed events, then record it there.
 		 */
-		if (BUF_PAGE_SIZE - commit >= sizeof(missed_events)) {
+		if (buffer->subbuf_size - commit >= sizeof(missed_events)) {
 			memcpy(&bpage->data[commit], &missed_events,
 			       sizeof(missed_events));
 			local_add(RB_MISSED_STORED, &bpage->commit);
@@ -5742,8 +5750,8 @@ int ring_buffer_read_page(struct trace_buffer *buffer,
 	/*
 	 * This page may be off to user land. Zero it out here.
 	 */
-	if (commit < BUF_PAGE_SIZE)
-		memset(&bpage->data[commit], 0, BUF_PAGE_SIZE - commit);
+	if (commit < buffer->subbuf_size)
+		memset(&bpage->data[commit], 0, buffer->subbuf_size - commit);
 
  out_unlock:
 	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 55dabee4c78b..76dd0a4c8cb5 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -5018,7 +5018,7 @@ static int tracing_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static int tracing_release_generic_tr(struct inode *inode, struct file *file)
+int tracing_release_generic_tr(struct inode *inode, struct file *file)
 {
 	struct trace_array *tr = inode->i_private;
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 79180aed13ee..00f873910c5d 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -616,6 +616,7 @@ void tracing_reset_all_online_cpus(void);
 void tracing_reset_all_online_cpus_unlocked(void);
 int tracing_open_generic(struct inode *inode, struct file *filp);
 int tracing_open_generic_tr(struct inode *inode, struct file *filp);
+int tracing_release_generic_tr(struct inode *inode, struct file *file);
 int tracing_open_file_tr(struct inode *inode, struct file *filp);
 int tracing_release_file_tr(struct inode *inode, struct file *filp);
 int tracing_single_release_file_tr(struct inode *inode, struct file *filp);
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index b70d03818038..7c364b87352e 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1893,9 +1893,9 @@ subsystem_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
 }
 
 static ssize_t
-show_header(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
+show_header_page_file(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
 {
-	int (*func)(struct trace_seq *s) = filp->private_data;
+	struct trace_array *tr = filp->private_data;
 	struct trace_seq *s;
 	int r;
 
@@ -1908,7 +1908,31 @@ show_header(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
 
 	trace_seq_init(s);
 
-	func(s);
+	ring_buffer_print_page_header(tr->array_buffer.buffer, s);
+	r = simple_read_from_buffer(ubuf, cnt, ppos,
+				    s->buffer, trace_seq_used(s));
+
+	kfree(s);
+
+	return r;
+}
+
+static ssize_t
+show_header_event_file(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
+{
+	struct trace_seq *s;
+	int r;
+
+	if (*ppos)
+		return 0;
+
+	s = kmalloc(sizeof(*s), GFP_KERNEL);
+	if (!s)
+		return -ENOMEM;
+
+	trace_seq_init(s);
+
+	ring_buffer_print_entry_header(s);
 	r = simple_read_from_buffer(ubuf, cnt, ppos,
 				    s->buffer, trace_seq_used(s));
 
@@ -2165,10 +2189,18 @@ static const struct file_operations ftrace_tr_enable_fops = {
 	.release = subsystem_release,
 };
 
-static const struct file_operations ftrace_show_header_fops = {
-	.open = tracing_open_generic,
-	.read = show_header,
+static const struct file_operations ftrace_show_header_page_fops = {
+	.open = tracing_open_generic_tr,
+	.read = show_header_page_file,
 	.llseek = default_llseek,
+	.release = tracing_release_generic_tr,
+};
+
+static const struct file_operations ftrace_show_header_event_fops = {
+	.open = tracing_open_generic_tr,
+	.read = show_header_event_file,
+	.llseek = default_llseek,
+	.release = tracing_release_generic_tr,
 };
 
 static int
@@ -3794,17 +3826,16 @@ static int events_callback(const char *name, umode_t *mode, void **data,
 		return 1;
 	}
 
-	if (strcmp(name, "header_page") == 0)
-		*data = ring_buffer_print_page_header;
-
-	else if (strcmp(name, "header_event") == 0)
-		*data = ring_buffer_print_entry_header;
+	if (strcmp(name, "header_page") == 0) {
+		*mode = TRACE_MODE_READ;
+		*fops = &ftrace_show_header_page_fops;
 
-	else
+	} else if (strcmp(name, "header_event") == 0) {
+		*mode = TRACE_MODE_READ;
+		*fops = &ftrace_show_header_event_fops;
+	} else
 		return 0;
 
-	*mode = TRACE_MODE_READ;
-	*fops = &ftrace_show_header_fops;
 	return 1;
 }
 
-- 
cgit v1.2.3


From 2808e31ec12e5fbe2ae25acc027fcdc67b1fb7f0 Mon Sep 17 00:00:00 2001
From: "Tzvetomir Stoyanov (VMware)" <tz.stoyanov@gmail.com>
Date: Tue, 19 Dec 2023 13:54:17 -0500
Subject: ring-buffer: Add interface for configuring trace sub buffer size

The trace ring buffer sub page size can be configured, per trace
instance. A new ftrace file "buffer_subbuf_order" is added to get and
set the size of the ring buffer sub page for current trace instance.
The size must be an order of system page size, that's why the new
interface works with system page order, instead of absolute page size:
0 means the ring buffer sub page is equal to 1 system page and so
forth:
0 - 1 system page
1 - 2 system pages
2 - 4 system pages
...
The ring buffer sub page size is limited between 1 and 128 system
pages. The default value is 1 system page.
New ring buffer APIs are introduced:
 ring_buffer_subbuf_order_set()
 ring_buffer_subbuf_order_get()
 ring_buffer_subbuf_size_get()

Link: https://lore.kernel.org/linux-trace-devel/20211213094825.61876-4-tz.stoyanov@gmail.com
Link: https://lore.kernel.org/linux-trace-kernel/20231219185628.298324722@goodmis.org

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Vincent Donnefort <vdonnefort@google.com>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/ring_buffer.h |  4 +++
 kernel/trace/ring_buffer.c  | 73 +++++++++++++++++++++++++++++++++++++++++++++
 kernel/trace/trace.c        | 48 +++++++++++++++++++++++++++++
 3 files changed, 125 insertions(+)

(limited to 'include')

diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index ce46218ce46d..12573306b889 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -202,6 +202,10 @@ struct trace_seq;
 int ring_buffer_print_entry_header(struct trace_seq *s);
 int ring_buffer_print_page_header(struct trace_buffer *buffer, struct trace_seq *s);
 
+int ring_buffer_subbuf_order_get(struct trace_buffer *buffer);
+int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order);
+int ring_buffer_subbuf_size_get(struct trace_buffer *buffer);
+
 enum ring_buffer_flags {
 	RB_FL_OVERWRITE		= 1 << 0,
 };
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index d9f656502400..20fc0121735d 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -507,6 +507,7 @@ struct trace_buffer {
 	bool				time_stamp_abs;
 
 	unsigned int			subbuf_size;
+	unsigned int			subbuf_order;
 	unsigned int			max_data_size;
 };
 
@@ -5761,6 +5762,78 @@ int ring_buffer_read_page(struct trace_buffer *buffer,
 }
 EXPORT_SYMBOL_GPL(ring_buffer_read_page);
 
+/**
+ * ring_buffer_subbuf_size_get - get size of the sub buffer.
+ * @buffer: the buffer to get the sub buffer size from
+ *
+ * Returns size of the sub buffer, in bytes.
+ */
+int ring_buffer_subbuf_size_get(struct trace_buffer *buffer)
+{
+	return buffer->subbuf_size + BUF_PAGE_HDR_SIZE;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_subbuf_size_get);
+
+/**
+ * ring_buffer_subbuf_order_get - get order of system sub pages in one buffer page.
+ * @buffer: The ring_buffer to get the system sub page order from
+ *
+ * By default, one ring buffer sub page equals to one system page. This parameter
+ * is configurable, per ring buffer. The size of the ring buffer sub page can be
+ * extended, but must be an order of system page size.
+ *
+ * Returns the order of buffer sub page size, in system pages:
+ * 0 means the sub buffer size is 1 system page and so forth.
+ * In case of an error < 0 is returned.
+ */
+int ring_buffer_subbuf_order_get(struct trace_buffer *buffer)
+{
+	if (!buffer)
+		return -EINVAL;
+
+	return buffer->subbuf_order;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_subbuf_order_get);
+
+/**
+ * ring_buffer_subbuf_order_set - set the size of ring buffer sub page.
+ * @buffer: The ring_buffer to set the new page size.
+ * @order: Order of the system pages in one sub buffer page
+ *
+ * By default, one ring buffer pages equals to one system page. This API can be
+ * used to set new size of the ring buffer page. The size must be order of
+ * system page size, that's why the input parameter @order is the order of
+ * system pages that are allocated for one ring buffer page:
+ *  0 - 1 system page
+ *  1 - 2 system pages
+ *  3 - 4 system pages
+ *  ...
+ *
+ * Returns 0 on success or < 0 in case of an error.
+ */
+int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order)
+{
+	int psize;
+
+	if (!buffer || order < 0)
+		return -EINVAL;
+
+	if (buffer->subbuf_order == order)
+		return 0;
+
+	psize = (1 << order) * PAGE_SIZE;
+	if (psize <= BUF_PAGE_HDR_SIZE)
+		return -EINVAL;
+
+	buffer->subbuf_order = order;
+	buffer->subbuf_size = psize - BUF_PAGE_HDR_SIZE;
+
+	/* Todo: reset the buffer with the new page size */
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_subbuf_order_set);
+
 /*
  * We only allocate new buffers, never free them if the CPU goes down.
  * If we were to free the buffer, then the user would lose any trace that was in
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 76dd0a4c8cb5..a010aba4c4a4 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -9358,6 +9358,51 @@ static const struct file_operations buffer_percent_fops = {
 	.llseek		= default_llseek,
 };
 
+static ssize_t
+buffer_order_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
+{
+	struct trace_array *tr = filp->private_data;
+	char buf[64];
+	int r;
+
+	r = sprintf(buf, "%d\n", ring_buffer_subbuf_order_get(tr->array_buffer.buffer));
+
+	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
+static ssize_t
+buffer_order_write(struct file *filp, const char __user *ubuf,
+		   size_t cnt, loff_t *ppos)
+{
+	struct trace_array *tr = filp->private_data;
+	unsigned long val;
+	int ret;
+
+	ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+	if (ret)
+		return ret;
+
+	/* limit between 1 and 128 system pages */
+	if (val < 0 || val > 7)
+		return -EINVAL;
+
+	ret = ring_buffer_subbuf_order_set(tr->array_buffer.buffer, val);
+	if (ret)
+		return ret;
+
+	(*ppos)++;
+
+	return cnt;
+}
+
+static const struct file_operations buffer_order_fops = {
+	.open		= tracing_open_generic_tr,
+	.read		= buffer_order_read,
+	.write		= buffer_order_write,
+	.release	= tracing_release_generic_tr,
+	.llseek		= default_llseek,
+};
+
 static struct dentry *trace_instance_dir;
 
 static void
@@ -9824,6 +9869,9 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
 	trace_create_file("buffer_percent", TRACE_MODE_WRITE, d_tracer,
 			tr, &buffer_percent_fops);
 
+	trace_create_file("buffer_subbuf_order", TRACE_MODE_WRITE, d_tracer,
+			  tr, &buffer_order_fops);
+
 	create_trace_options_dir(tr);
 
 #ifdef CONFIG_TRACER_MAX_TRACE
-- 
cgit v1.2.3


From bce761d757452ba5eb77e11fecc37a04b67494e7 Mon Sep 17 00:00:00 2001
From: "Tzvetomir Stoyanov (VMware)" <tz.stoyanov@gmail.com>
Date: Tue, 19 Dec 2023 13:54:19 -0500
Subject: ring-buffer: Read and write to ring buffers with custom sub buffer
 size

As the size of the ring sub buffer page can be changed dynamically,
the logic that reads and writes to the buffer should be fixed to take
that into account. Some internal ring buffer APIs are changed:
 ring_buffer_alloc_read_page()
 ring_buffer_free_read_page()
 ring_buffer_read_page()
A new API is introduced:
 ring_buffer_read_page_data()

Link: https://lore.kernel.org/linux-trace-devel/20211213094825.61876-6-tz.stoyanov@gmail.com
Link: https://lore.kernel.org/linux-trace-kernel/20231219185628.875145995@goodmis.org

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Vincent Donnefort <vdonnefort@google.com>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
[ Fixed kerneldoc on data_page parameter in ring_buffer_free_read_page() ]
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/ring_buffer.h          | 11 ++++--
 kernel/trace/ring_buffer.c           | 75 ++++++++++++++++++++++++++----------
 kernel/trace/ring_buffer_benchmark.c | 10 +++--
 kernel/trace/trace.c                 | 34 +++++++++-------
 4 files changed, 89 insertions(+), 41 deletions(-)

(limited to 'include')

diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 12573306b889..fa802db216f9 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -192,10 +192,15 @@ bool ring_buffer_time_stamp_abs(struct trace_buffer *buffer);
 size_t ring_buffer_nr_pages(struct trace_buffer *buffer, int cpu);
 size_t ring_buffer_nr_dirty_pages(struct trace_buffer *buffer, int cpu);
 
-void *ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu);
-void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, void *data);
-int ring_buffer_read_page(struct trace_buffer *buffer, void **data_page,
+struct buffer_data_read_page;
+struct buffer_data_read_page *
+ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu);
+void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu,
+				struct buffer_data_read_page *page);
+int ring_buffer_read_page(struct trace_buffer *buffer,
+			  struct buffer_data_read_page *data_page,
 			  size_t len, int cpu, int full);
+void *ring_buffer_read_page_data(struct buffer_data_read_page *page);
 
 struct trace_seq;
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index b928bd03dd0e..c2afcf98ea91 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -318,6 +318,11 @@ struct buffer_data_page {
 	unsigned char	 data[] RB_ALIGN_DATA;	/* data of buffer page */
 };
 
+struct buffer_data_read_page {
+	unsigned		order;	/* order of the page */
+	struct buffer_data_page	*data;	/* actual data, stored in this page */
+};
+
 /*
  * Note, the buffer_page list must be first. The buffer pages
  * are allocated in cache lines, which means that each buffer
@@ -5483,40 +5488,48 @@ EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu);
  * Returns:
  *  The page allocated, or ERR_PTR
  */
-void *ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu)
+struct buffer_data_read_page *
+ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
-	struct buffer_data_page *bpage = NULL;
+	struct buffer_data_read_page *bpage = NULL;
 	unsigned long flags;
 	struct page *page;
 
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return ERR_PTR(-ENODEV);
 
+	bpage = kzalloc(sizeof(*bpage), GFP_KERNEL);
+	if (!bpage)
+		return ERR_PTR(-ENOMEM);
+
+	bpage->order = buffer->subbuf_order;
 	cpu_buffer = buffer->buffers[cpu];
 	local_irq_save(flags);
 	arch_spin_lock(&cpu_buffer->lock);
 
 	if (cpu_buffer->free_page) {
-		bpage = cpu_buffer->free_page;
+		bpage->data = cpu_buffer->free_page;
 		cpu_buffer->free_page = NULL;
 	}
 
 	arch_spin_unlock(&cpu_buffer->lock);
 	local_irq_restore(flags);
 
-	if (bpage)
+	if (bpage->data)
 		goto out;
 
 	page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL | __GFP_NORETRY,
 				cpu_buffer->buffer->subbuf_order);
-	if (!page)
+	if (!page) {
+		kfree(bpage);
 		return ERR_PTR(-ENOMEM);
+	}
 
-	bpage = page_address(page);
+	bpage->data = page_address(page);
 
  out:
-	rb_init_page(bpage);
+	rb_init_page(bpage->data);
 
 	return bpage;
 }
@@ -5526,14 +5539,15 @@ EXPORT_SYMBOL_GPL(ring_buffer_alloc_read_page);
  * ring_buffer_free_read_page - free an allocated read page
  * @buffer: the buffer the page was allocate for
  * @cpu: the cpu buffer the page came from
- * @data: the page to free
+ * @data_page: the page to free
  *
  * Free a page allocated from ring_buffer_alloc_read_page.
  */
-void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, void *data)
+void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu,
+				struct buffer_data_read_page *data_page)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
-	struct buffer_data_page *bpage = data;
+	struct buffer_data_page *bpage = data_page->data;
 	struct page *page = virt_to_page(bpage);
 	unsigned long flags;
 
@@ -5542,8 +5556,12 @@ void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, void *data
 
 	cpu_buffer = buffer->buffers[cpu];
 
-	/* If the page is still in use someplace else, we can't reuse it */
-	if (page_ref_count(page) > 1)
+	/*
+	 * If the page is still in use someplace else, or order of the page
+	 * is different from the subbuffer order of the buffer -
+	 * we can't reuse it
+	 */
+	if (page_ref_count(page) > 1 || data_page->order != buffer->subbuf_order)
 		goto out;
 
 	local_irq_save(flags);
@@ -5558,7 +5576,8 @@ void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, void *data
 	local_irq_restore(flags);
 
  out:
-	free_pages((unsigned long)bpage, buffer->subbuf_order);
+	free_pages((unsigned long)bpage, data_page->order);
+	kfree(data_page);
 }
 EXPORT_SYMBOL_GPL(ring_buffer_free_read_page);
 
@@ -5579,9 +5598,10 @@ EXPORT_SYMBOL_GPL(ring_buffer_free_read_page);
  *	rpage = ring_buffer_alloc_read_page(buffer, cpu);
  *	if (IS_ERR(rpage))
  *		return PTR_ERR(rpage);
- *	ret = ring_buffer_read_page(buffer, &rpage, len, cpu, 0);
+ *	ret = ring_buffer_read_page(buffer, rpage, len, cpu, 0);
  *	if (ret >= 0)
- *		process_page(rpage, ret);
+ *		process_page(ring_buffer_read_page_data(rpage), ret);
+ *	ring_buffer_free_read_page(buffer, cpu, rpage);
  *
  * When @full is set, the function will not return true unless
  * the writer is off the reader page.
@@ -5596,7 +5616,8 @@ EXPORT_SYMBOL_GPL(ring_buffer_free_read_page);
  *  <0 if no data has been transferred.
  */
 int ring_buffer_read_page(struct trace_buffer *buffer,
-			  void **data_page, size_t len, int cpu, int full)
+			  struct buffer_data_read_page *data_page,
+			  size_t len, int cpu, int full)
 {
 	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
 	struct ring_buffer_event *event;
@@ -5621,10 +5642,12 @@ int ring_buffer_read_page(struct trace_buffer *buffer,
 
 	len -= BUF_PAGE_HDR_SIZE;
 
-	if (!data_page)
+	if (!data_page || !data_page->data)
+		goto out;
+	if (data_page->order != buffer->subbuf_order)
 		goto out;
 
-	bpage = *data_page;
+	bpage = data_page->data;
 	if (!bpage)
 		goto out;
 
@@ -5718,11 +5741,11 @@ int ring_buffer_read_page(struct trace_buffer *buffer,
 		/* swap the pages */
 		rb_init_page(bpage);
 		bpage = reader->page;
-		reader->page = *data_page;
+		reader->page = data_page->data;
 		local_set(&reader->write, 0);
 		local_set(&reader->entries, 0);
 		reader->read = 0;
-		*data_page = bpage;
+		data_page->data = bpage;
 
 		/*
 		 * Use the real_end for the data size,
@@ -5767,6 +5790,18 @@ int ring_buffer_read_page(struct trace_buffer *buffer,
 }
 EXPORT_SYMBOL_GPL(ring_buffer_read_page);
 
+/**
+ * ring_buffer_read_page_data - get pointer to the data in the page.
+ * @page:  the page to get the data from
+ *
+ * Returns pointer to the actual data in this page.
+ */
+void *ring_buffer_read_page_data(struct buffer_data_read_page *page)
+{
+	return page->data;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_read_page_data);
+
 /**
  * ring_buffer_subbuf_size_get - get size of the sub buffer.
  * @buffer: the buffer to get the sub buffer size from
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index aef34673d79d..008187ebd7fe 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -104,10 +104,11 @@ static enum event_status read_event(int cpu)
 
 static enum event_status read_page(int cpu)
 {
+	struct buffer_data_read_page *bpage;
 	struct ring_buffer_event *event;
 	struct rb_page *rpage;
 	unsigned long commit;
-	void *bpage;
+	int page_size;
 	int *entry;
 	int ret;
 	int inc;
@@ -117,14 +118,15 @@ static enum event_status read_page(int cpu)
 	if (IS_ERR(bpage))
 		return EVENT_DROPPED;
 
-	ret = ring_buffer_read_page(buffer, &bpage, PAGE_SIZE, cpu, 1);
+	page_size = ring_buffer_subbuf_size_get(buffer);
+	ret = ring_buffer_read_page(buffer, bpage, page_size, cpu, 1);
 	if (ret >= 0) {
-		rpage = bpage;
+		rpage = ring_buffer_read_page_data(bpage);
 		/* The commit may have missed event flags set, clear them */
 		commit = local_read(&rpage->commit) & 0xfffff;
 		for (i = 0; i < commit && !test_error ; i += inc) {
 
-			if (i >= (PAGE_SIZE - offsetof(struct rb_page, data))) {
+			if (i >= (page_size - offsetof(struct rb_page, data))) {
 				TEST_ERROR();
 				break;
 			}
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index a010aba4c4a4..711095aa731d 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -8286,6 +8286,8 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 {
 	struct ftrace_buffer_info *info = filp->private_data;
 	struct trace_iterator *iter = &info->iter;
+	void *trace_data;
+	int page_size;
 	ssize_t ret = 0;
 	ssize_t size;
 
@@ -8297,6 +8299,8 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 		return -EBUSY;
 #endif
 
+	page_size = ring_buffer_subbuf_size_get(iter->array_buffer->buffer);
+
 	if (!info->spare) {
 		info->spare = ring_buffer_alloc_read_page(iter->array_buffer->buffer,
 							  iter->cpu_file);
@@ -8311,13 +8315,13 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 		return ret;
 
 	/* Do we have previous read data to read? */
-	if (info->read < PAGE_SIZE)
+	if (info->read < page_size)
 		goto read;
 
  again:
 	trace_access_lock(iter->cpu_file);
 	ret = ring_buffer_read_page(iter->array_buffer->buffer,
-				    &info->spare,
+				    info->spare,
 				    count,
 				    iter->cpu_file, 0);
 	trace_access_unlock(iter->cpu_file);
@@ -8338,11 +8342,11 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 
 	info->read = 0;
  read:
-	size = PAGE_SIZE - info->read;
+	size = page_size - info->read;
 	if (size > count)
 		size = count;
-
-	ret = copy_to_user(ubuf, info->spare + info->read, size);
+	trace_data = ring_buffer_read_page_data(info->spare);
+	ret = copy_to_user(ubuf, trace_data + info->read, size);
 	if (ret == size)
 		return -EFAULT;
 
@@ -8453,6 +8457,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		.spd_release	= buffer_spd_release,
 	};
 	struct buffer_ref *ref;
+	int page_size;
 	int entries, i;
 	ssize_t ret = 0;
 
@@ -8461,13 +8466,14 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		return -EBUSY;
 #endif
 
-	if (*ppos & (PAGE_SIZE - 1))
+	page_size = ring_buffer_subbuf_size_get(iter->array_buffer->buffer);
+	if (*ppos & (page_size - 1))
 		return -EINVAL;
 
-	if (len & (PAGE_SIZE - 1)) {
-		if (len < PAGE_SIZE)
+	if (len & (page_size - 1)) {
+		if (len < page_size)
 			return -EINVAL;
-		len &= PAGE_MASK;
+		len &= (~(page_size - 1));
 	}
 
 	if (splice_grow_spd(pipe, &spd))
@@ -8477,7 +8483,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 	trace_access_lock(iter->cpu_file);
 	entries = ring_buffer_entries_cpu(iter->array_buffer->buffer, iter->cpu_file);
 
-	for (i = 0; i < spd.nr_pages_max && len && entries; i++, len -= PAGE_SIZE) {
+	for (i = 0; i < spd.nr_pages_max && len && entries; i++, len -= page_size) {
 		struct page *page;
 		int r;
 
@@ -8498,7 +8504,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		}
 		ref->cpu = iter->cpu_file;
 
-		r = ring_buffer_read_page(ref->buffer, &ref->page,
+		r = ring_buffer_read_page(ref->buffer, ref->page,
 					  len, iter->cpu_file, 1);
 		if (r < 0) {
 			ring_buffer_free_read_page(ref->buffer, ref->cpu,
@@ -8507,14 +8513,14 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 			break;
 		}
 
-		page = virt_to_page(ref->page);
+		page = virt_to_page(ring_buffer_read_page_data(ref->page));
 
 		spd.pages[i] = page;
-		spd.partial[i].len = PAGE_SIZE;
+		spd.partial[i].len = page_size;
 		spd.partial[i].offset = 0;
 		spd.partial[i].private = (unsigned long)ref;
 		spd.nr_pages++;
-		*ppos += PAGE_SIZE;
+		*ppos += page_size;
 
 		entries = ring_buffer_entries_cpu(iter->array_buffer->buffer, iter->cpu_file);
 	}
-- 
cgit v1.2.3


From f3e25e68ceb2abaeefcac8f930c940c4494705d0 Mon Sep 17 00:00:00 2001
From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Date: Tue, 14 Nov 2023 12:20:11 +0100
Subject: pwm: Drop unused member "pwm" from struct pwm_device
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This member is only assigned to and never read. So drop it.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/core.c  | 1 -
 include/linux/pwm.h | 1 -
 2 files changed, 2 deletions(-)

(limited to 'include')

diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index 29078486534d..24bb796d15f6 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -265,7 +265,6 @@ int __pwmchip_add(struct pwm_chip *chip, struct module *owner)
 		pwm = &chip->pwms[i];
 
 		pwm->chip = chip;
-		pwm->pwm = chip->base + i;
 		pwm->hwpwm = i;
 	}
 
diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index cda3597b84f2..8cadf9ee8d26 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -79,7 +79,6 @@ struct pwm_device {
 	const char *label;
 	unsigned long flags;
 	unsigned int hwpwm;
-	unsigned int pwm;
 	struct pwm_chip *chip;
 
 	struct pwm_args args;
-- 
cgit v1.2.3


From 54c86dd20bba23109e32e4e2f94ff93dd9863bc3 Mon Sep 17 00:00:00 2001
From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Date: Tue, 14 Nov 2023 12:20:12 +0100
Subject: pwm: Replace PWM chip unique base by unique ID
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Traditionally each PWM device had a unique ID stored in the "pwm" member
of struct pwm_device. However this number was hardly used and dropped
in the previous commit. To identify a certain PWM you're supposed to use
the chip's ID and the hwpwm of the PWM device now.

With the PWM chip base gone PWM chips can get their IDs better and
simpler using an idr.

This is expected to change the numbering of PWM chips, but nothing
should rely on the numbering anyhow.

Other than that the side effects are:

 - The PWM chip IDs are smaller and in most cases consecutive.
 - The ordering in /sys/kernel/debug/pwm is ordered by ascending PWM
   chip ID.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 drivers/pwm/core.c  | 67 ++++++++++++++++++++---------------------------------
 drivers/pwm/sysfs.c |  2 +-
 include/linux/pwm.h |  3 +--
 3 files changed, 27 insertions(+), 45 deletions(-)

(limited to 'include')

diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index 24bb796d15f6..ebe404dfdf5b 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -8,6 +8,7 @@
 
 #include <linux/acpi.h>
 #include <linux/module.h>
+#include <linux/idr.h>
 #include <linux/of.h>
 #include <linux/pwm.h>
 #include <linux/list.h>
@@ -23,52 +24,25 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/pwm.h>
 
-#define MAX_PWMS 1024
-
 static DEFINE_MUTEX(pwm_lookup_lock);
 static LIST_HEAD(pwm_lookup_list);
 
-/* protects access to pwm_chips and allocated_pwms */
+/* protects access to pwm_chips */
 static DEFINE_MUTEX(pwm_lock);
 
-static LIST_HEAD(pwm_chips);
-static DECLARE_BITMAP(allocated_pwms, MAX_PWMS);
-
-/* Called with pwm_lock held */
-static int alloc_pwms(unsigned int count)
-{
-	unsigned int start;
-
-	start = bitmap_find_next_zero_area(allocated_pwms, MAX_PWMS, 0,
-					   count, 0);
-
-	if (start + count > MAX_PWMS)
-		return -ENOSPC;
-
-	bitmap_set(allocated_pwms, start, count);
-
-	return start;
-}
-
-/* Called with pwm_lock held */
-static void free_pwms(struct pwm_chip *chip)
-{
-	bitmap_clear(allocated_pwms, chip->base, chip->npwm);
-
-	kfree(chip->pwms);
-	chip->pwms = NULL;
-}
+static DEFINE_IDR(pwm_chips);
 
 static struct pwm_chip *pwmchip_find_by_name(const char *name)
 {
 	struct pwm_chip *chip;
+	unsigned long id, tmp;
 
 	if (!name)
 		return NULL;
 
 	mutex_lock(&pwm_lock);
 
-	list_for_each_entry(chip, &pwm_chips, list) {
+	idr_for_each_entry_ul(&pwm_chips, chip, tmp, id) {
 		const char *chip_name = dev_name(chip->dev);
 
 		if (chip_name && strcmp(chip_name, name) == 0) {
@@ -252,14 +226,14 @@ int __pwmchip_add(struct pwm_chip *chip, struct module *owner)
 
 	mutex_lock(&pwm_lock);
 
-	ret = alloc_pwms(chip->npwm);
+	ret = idr_alloc(&pwm_chips, chip, 0, 0, GFP_KERNEL);
 	if (ret < 0) {
 		mutex_unlock(&pwm_lock);
 		kfree(chip->pwms);
 		return ret;
 	}
 
-	chip->base = ret;
+	chip->id = ret;
 
 	for (i = 0; i < chip->npwm; i++) {
 		pwm = &chip->pwms[i];
@@ -268,8 +242,6 @@ int __pwmchip_add(struct pwm_chip *chip, struct module *owner)
 		pwm->hwpwm = i;
 	}
 
-	list_add(&chip->list, &pwm_chips);
-
 	mutex_unlock(&pwm_lock);
 
 	if (IS_ENABLED(CONFIG_OF))
@@ -296,11 +268,11 @@ void pwmchip_remove(struct pwm_chip *chip)
 
 	mutex_lock(&pwm_lock);
 
-	list_del_init(&chip->list);
-
-	free_pwms(chip);
+	idr_remove(&pwm_chips, chip->id);
 
 	mutex_unlock(&pwm_lock);
+
+	kfree(chip->pwms);
 }
 EXPORT_SYMBOL_GPL(pwmchip_remove);
 
@@ -596,10 +568,11 @@ EXPORT_SYMBOL_GPL(pwm_adjust_config);
 static struct pwm_chip *fwnode_to_pwmchip(struct fwnode_handle *fwnode)
 {
 	struct pwm_chip *chip;
+	unsigned long id, tmp;
 
 	mutex_lock(&pwm_lock);
 
-	list_for_each_entry(chip, &pwm_chips, list)
+	idr_for_each_entry_ul(&pwm_chips, chip, tmp, id)
 		if (chip->dev && device_match_fwnode(chip->dev, fwnode)) {
 			mutex_unlock(&pwm_lock);
 			return chip;
@@ -1057,17 +1030,27 @@ static void pwm_dbg_show(struct pwm_chip *chip, struct seq_file *s)
 
 static void *pwm_seq_start(struct seq_file *s, loff_t *pos)
 {
+	unsigned long id = *pos;
+	void *ret;
+
 	mutex_lock(&pwm_lock);
 	s->private = "";
 
-	return seq_list_start(&pwm_chips, *pos);
+	ret = idr_get_next_ul(&pwm_chips, &id);
+	*pos = id;
+	return ret;
 }
 
 static void *pwm_seq_next(struct seq_file *s, void *v, loff_t *pos)
 {
+	unsigned long id = *pos + 1;
+	void *ret;
+
 	s->private = "\n";
 
-	return seq_list_next(v, &pwm_chips, pos);
+	ret = idr_get_next_ul(&pwm_chips, &id);
+	*pos = id;
+	return ret;
 }
 
 static void pwm_seq_stop(struct seq_file *s, void *v)
@@ -1077,7 +1060,7 @@ static void pwm_seq_stop(struct seq_file *s, void *v)
 
 static int pwm_seq_show(struct seq_file *s, void *v)
 {
-	struct pwm_chip *chip = list_entry(v, struct pwm_chip, list);
+	struct pwm_chip *chip = v;
 
 	seq_printf(s, "%s%s/%s, %d PWM device%s\n", (char *)s->private,
 		   chip->dev->bus ? chip->dev->bus->name : "no-bus",
diff --git a/drivers/pwm/sysfs.c b/drivers/pwm/sysfs.c
index 8d1254761e4d..4edb994fa2e1 100644
--- a/drivers/pwm/sysfs.c
+++ b/drivers/pwm/sysfs.c
@@ -510,7 +510,7 @@ void pwmchip_sysfs_export(struct pwm_chip *chip)
 	 * the kernel it's just not exported.
 	 */
 	parent = device_create(&pwm_class, chip->dev, MKDEV(0, 0), chip,
-			       "pwmchip%d", chip->base);
+			       "pwmchip%d", chip->id);
 	if (IS_ERR(parent)) {
 		dev_warn(chip->dev,
 			 "device_create failed for pwm_chip sysfs export\n");
diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index 8cadf9ee8d26..c27a4bb76012 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -292,7 +292,7 @@ struct pwm_chip {
 	struct device *dev;
 	const struct pwm_ops *ops;
 	struct module *owner;
-	int base;
+	unsigned int id;
 	unsigned int npwm;
 
 	struct pwm_device * (*of_xlate)(struct pwm_chip *chip,
@@ -300,7 +300,6 @@ struct pwm_chip {
 	unsigned int of_pwm_n_cells;
 
 	/* only used internally by the PWM framework */
-	struct list_head list;
 	struct pwm_device *pwms;
 };
 
-- 
cgit v1.2.3


From 2d91123ae5614b8737abd3a519b81265309a1ac3 Mon Sep 17 00:00:00 2001
From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Date: Wed, 29 Nov 2023 11:18:32 +0100
Subject: pwm: Update kernel doc for struct pwm_chip
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit c572f3b9c8b7 ("pwm: Replace PWM chip unique base by unique ID")
changed the members of struct pwm_chip, but failed to update the
documentation accordingly. Catch up and document the new member and drop
description for the two removed ones.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 include/linux/pwm.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index c27a4bb76012..f87655c06c82 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -281,11 +281,10 @@ struct pwm_ops {
  * @dev: device providing the PWMs
  * @ops: callbacks for this PWM controller
  * @owner: module providing this chip
- * @base: number of first PWM controlled by this chip
+ * @id: unique number of this PWM chip
  * @npwm: number of PWMs controlled by this chip
  * @of_xlate: request a PWM device given a device tree PWM specifier
  * @of_pwm_n_cells: number of cells expected in the device tree PWM specifier
- * @list: list node for internal use
  * @pwms: array of PWM devices allocated by the framework
  */
 struct pwm_chip {
-- 
cgit v1.2.3


From c748a6d77c06a78651030e17da6beb278a1c9470 Mon Sep 17 00:00:00 2001
From: Sean Young <sean@mess.org>
Date: Tue, 19 Dec 2023 16:30:24 +0000
Subject: pwm: Rename pwm_apply_state() to pwm_apply_might_sleep()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In order to introduce a pwm api which can be used from atomic context,
we will need two functions for applying pwm changes:

	int pwm_apply_might_sleep(struct pwm *, struct pwm_state *);
	int pwm_apply_atomic(struct pwm *, struct pwm_state *);

This commit just deals with renaming pwm_apply_state(), a following
commit will introduce the pwm_apply_atomic() function.

Acked-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Guenter Roeck <linux@roeck-us.net>
Acked-by: Mark Brown <broonie@kernel.org>
Acked-by: Dmitry Torokhov <dmitry.torokhov@gmail.com> # for input
Acked-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Jani Nikula <jani.nikula@intel.com>
Acked-by: Lee Jones <lee@kernel.org>
Signed-off-by: Sean Young <sean@mess.org>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 Documentation/driver-api/pwm.rst               |  8 ++++----
 MAINTAINERS                                    |  2 +-
 drivers/gpu/drm/i915/display/intel_backlight.c |  6 +++---
 drivers/gpu/drm/solomon/ssd130x.c              |  2 +-
 drivers/hwmon/pwm-fan.c                        |  8 ++++----
 drivers/input/misc/da7280.c                    |  4 ++--
 drivers/input/misc/pwm-beeper.c                |  4 ++--
 drivers/input/misc/pwm-vibra.c                 |  8 ++++----
 drivers/leds/leds-pwm.c                        |  2 +-
 drivers/leds/rgb/leds-pwm-multicolor.c         |  4 ++--
 drivers/media/rc/pwm-ir-tx.c                   |  4 ++--
 drivers/platform/x86/lenovo-yogabook.c         |  2 +-
 drivers/pwm/core.c                             | 18 ++++++++---------
 drivers/pwm/pwm-twl-led.c                      |  2 +-
 drivers/pwm/pwm-vt8500.c                       |  2 +-
 drivers/pwm/sysfs.c                            | 10 ++++-----
 drivers/regulator/pwm-regulator.c              |  4 ++--
 drivers/video/backlight/lm3630a_bl.c           |  2 +-
 drivers/video/backlight/lp855x_bl.c            |  2 +-
 drivers/video/backlight/pwm_bl.c               | 12 +++++------
 drivers/video/fbdev/ssd1307fb.c                |  2 +-
 include/linux/pwm.h                            | 28 +++++++++++++-------------
 22 files changed, 68 insertions(+), 68 deletions(-)

(limited to 'include')

diff --git a/Documentation/driver-api/pwm.rst b/Documentation/driver-api/pwm.rst
index bb264490a87a..f1d8197c8c43 100644
--- a/Documentation/driver-api/pwm.rst
+++ b/Documentation/driver-api/pwm.rst
@@ -41,7 +41,7 @@ the getter, devm_pwm_get() and devm_fwnode_pwm_get(), also exist.
 
 After being requested, a PWM has to be configured using::
 
-	int pwm_apply_state(struct pwm_device *pwm, struct pwm_state *state);
+	int pwm_apply_might_sleep(struct pwm_device *pwm, struct pwm_state *state);
 
 This API controls both the PWM period/duty_cycle config and the
 enable/disable state.
@@ -57,13 +57,13 @@ If supported by the driver, the signal can be optimized, for example to improve
 EMI by phase shifting the individual channels of a chip.
 
 The pwm_config(), pwm_enable() and pwm_disable() functions are just wrappers
-around pwm_apply_state() and should not be used if the user wants to change
+around pwm_apply_might_sleep() and should not be used if the user wants to change
 several parameter at once. For example, if you see pwm_config() and
 pwm_{enable,disable}() calls in the same function, this probably means you
-should switch to pwm_apply_state().
+should switch to pwm_apply_might_sleep().
 
 The PWM user API also allows one to query the PWM state that was passed to the
-last invocation of pwm_apply_state() using pwm_get_state(). Note this is
+last invocation of pwm_apply_might_sleep() using pwm_get_state(). Note this is
 different to what the driver has actually implemented if the request cannot be
 satisfied exactly with the hardware in use. There is currently no way for
 consumers to get the actually implemented settings.
diff --git a/MAINTAINERS b/MAINTAINERS
index 97f51d5ec1cf..c58480595220 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -17576,7 +17576,7 @@ F:	drivers/video/backlight/pwm_bl.c
 F:	include/dt-bindings/pwm/
 F:	include/linux/pwm.h
 F:	include/linux/pwm_backlight.h
-K:	pwm_(config|apply_state|ops)
+K:	pwm_(config|apply_might_sleep|ops)
 
 PXA GPIO DRIVER
 M:	Robert Jarzmik <robert.jarzmik@free.fr>
diff --git a/drivers/gpu/drm/i915/display/intel_backlight.c b/drivers/gpu/drm/i915/display/intel_backlight.c
index 2e8f17c04522..ff9b9918b0a1 100644
--- a/drivers/gpu/drm/i915/display/intel_backlight.c
+++ b/drivers/gpu/drm/i915/display/intel_backlight.c
@@ -274,7 +274,7 @@ static void ext_pwm_set_backlight(const struct drm_connector_state *conn_state,
 	struct intel_panel *panel = &to_intel_connector(conn_state->connector)->panel;
 
 	pwm_set_relative_duty_cycle(&panel->backlight.pwm_state, level, 100);
-	pwm_apply_state(panel->backlight.pwm, &panel->backlight.pwm_state);
+	pwm_apply_might_sleep(panel->backlight.pwm, &panel->backlight.pwm_state);
 }
 
 static void
@@ -427,7 +427,7 @@ static void ext_pwm_disable_backlight(const struct drm_connector_state *old_conn
 	intel_backlight_set_pwm_level(old_conn_state, level);
 
 	panel->backlight.pwm_state.enabled = false;
-	pwm_apply_state(panel->backlight.pwm, &panel->backlight.pwm_state);
+	pwm_apply_might_sleep(panel->backlight.pwm, &panel->backlight.pwm_state);
 }
 
 void intel_backlight_disable(const struct drm_connector_state *old_conn_state)
@@ -749,7 +749,7 @@ static void ext_pwm_enable_backlight(const struct intel_crtc_state *crtc_state,
 
 	pwm_set_relative_duty_cycle(&panel->backlight.pwm_state, level, 100);
 	panel->backlight.pwm_state.enabled = true;
-	pwm_apply_state(panel->backlight.pwm, &panel->backlight.pwm_state);
+	pwm_apply_might_sleep(panel->backlight.pwm, &panel->backlight.pwm_state);
 }
 
 static void __intel_backlight_enable(const struct intel_crtc_state *crtc_state,
diff --git a/drivers/gpu/drm/solomon/ssd130x.c b/drivers/gpu/drm/solomon/ssd130x.c
index e0174f82e353..cce043a4a1dc 100644
--- a/drivers/gpu/drm/solomon/ssd130x.c
+++ b/drivers/gpu/drm/solomon/ssd130x.c
@@ -319,7 +319,7 @@ static int ssd130x_pwm_enable(struct ssd130x_device *ssd130x)
 
 	pwm_init_state(ssd130x->pwm, &pwmstate);
 	pwm_set_relative_duty_cycle(&pwmstate, 50, 100);
-	pwm_apply_state(ssd130x->pwm, &pwmstate);
+	pwm_apply_might_sleep(ssd130x->pwm, &pwmstate);
 
 	/* Enable the PWM */
 	pwm_enable(ssd130x->pwm);
diff --git a/drivers/hwmon/pwm-fan.c b/drivers/hwmon/pwm-fan.c
index 6e4516c2ab89..b67bc9e833c0 100644
--- a/drivers/hwmon/pwm-fan.c
+++ b/drivers/hwmon/pwm-fan.c
@@ -151,7 +151,7 @@ static int pwm_fan_power_on(struct pwm_fan_ctx *ctx)
 	}
 
 	state->enabled = true;
-	ret = pwm_apply_state(ctx->pwm, state);
+	ret = pwm_apply_might_sleep(ctx->pwm, state);
 	if (ret) {
 		dev_err(ctx->dev, "failed to enable PWM\n");
 		goto disable_regulator;
@@ -181,7 +181,7 @@ static int pwm_fan_power_off(struct pwm_fan_ctx *ctx)
 
 	state->enabled = false;
 	state->duty_cycle = 0;
-	ret = pwm_apply_state(ctx->pwm, state);
+	ret = pwm_apply_might_sleep(ctx->pwm, state);
 	if (ret) {
 		dev_err(ctx->dev, "failed to disable PWM\n");
 		return ret;
@@ -207,7 +207,7 @@ static int  __set_pwm(struct pwm_fan_ctx *ctx, unsigned long pwm)
 
 		period = state->period;
 		state->duty_cycle = DIV_ROUND_UP(pwm * (period - 1), MAX_PWM);
-		ret = pwm_apply_state(ctx->pwm, state);
+		ret = pwm_apply_might_sleep(ctx->pwm, state);
 		if (ret)
 			return ret;
 		ret = pwm_fan_power_on(ctx);
@@ -278,7 +278,7 @@ static int pwm_fan_update_enable(struct pwm_fan_ctx *ctx, long val)
 						    state,
 						    &enable_regulator);
 
-			pwm_apply_state(ctx->pwm, state);
+			pwm_apply_might_sleep(ctx->pwm, state);
 			pwm_fan_switch_power(ctx, enable_regulator);
 			pwm_fan_update_state(ctx, 0);
 		}
diff --git a/drivers/input/misc/da7280.c b/drivers/input/misc/da7280.c
index ce82548916bb..c1fa75c0f970 100644
--- a/drivers/input/misc/da7280.c
+++ b/drivers/input/misc/da7280.c
@@ -352,7 +352,7 @@ static int da7280_haptic_set_pwm(struct da7280_haptic *haptics, bool enabled)
 		state.duty_cycle = period_mag_multi;
 	}
 
-	error = pwm_apply_state(haptics->pwm_dev, &state);
+	error = pwm_apply_might_sleep(haptics->pwm_dev, &state);
 	if (error)
 		dev_err(haptics->dev, "Failed to apply pwm state: %d\n", error);
 
@@ -1175,7 +1175,7 @@ static int da7280_probe(struct i2c_client *client)
 		/* Sync up PWM state and ensure it is off. */
 		pwm_init_state(haptics->pwm_dev, &state);
 		state.enabled = false;
-		error = pwm_apply_state(haptics->pwm_dev, &state);
+		error = pwm_apply_might_sleep(haptics->pwm_dev, &state);
 		if (error) {
 			dev_err(dev, "Failed to apply PWM state: %d\n", error);
 			return error;
diff --git a/drivers/input/misc/pwm-beeper.c b/drivers/input/misc/pwm-beeper.c
index 1e731d8397c6..5b9aedf4362f 100644
--- a/drivers/input/misc/pwm-beeper.c
+++ b/drivers/input/misc/pwm-beeper.c
@@ -39,7 +39,7 @@ static int pwm_beeper_on(struct pwm_beeper *beeper, unsigned long period)
 	state.period = period;
 	pwm_set_relative_duty_cycle(&state, 50, 100);
 
-	error = pwm_apply_state(beeper->pwm, &state);
+	error = pwm_apply_might_sleep(beeper->pwm, &state);
 	if (error)
 		return error;
 
@@ -138,7 +138,7 @@ static int pwm_beeper_probe(struct platform_device *pdev)
 	/* Sync up PWM state and ensure it is off. */
 	pwm_init_state(beeper->pwm, &state);
 	state.enabled = false;
-	error = pwm_apply_state(beeper->pwm, &state);
+	error = pwm_apply_might_sleep(beeper->pwm, &state);
 	if (error) {
 		dev_err(dev, "failed to apply initial PWM state: %d\n",
 			error);
diff --git a/drivers/input/misc/pwm-vibra.c b/drivers/input/misc/pwm-vibra.c
index acac79c488aa..3e5ed685ed8f 100644
--- a/drivers/input/misc/pwm-vibra.c
+++ b/drivers/input/misc/pwm-vibra.c
@@ -56,7 +56,7 @@ static int pwm_vibrator_start(struct pwm_vibrator *vibrator)
 	pwm_set_relative_duty_cycle(&state, vibrator->level, 0xffff);
 	state.enabled = true;
 
-	err = pwm_apply_state(vibrator->pwm, &state);
+	err = pwm_apply_might_sleep(vibrator->pwm, &state);
 	if (err) {
 		dev_err(pdev, "failed to apply pwm state: %d\n", err);
 		return err;
@@ -67,7 +67,7 @@ static int pwm_vibrator_start(struct pwm_vibrator *vibrator)
 		state.duty_cycle = vibrator->direction_duty_cycle;
 		state.enabled = true;
 
-		err = pwm_apply_state(vibrator->pwm_dir, &state);
+		err = pwm_apply_might_sleep(vibrator->pwm_dir, &state);
 		if (err) {
 			dev_err(pdev, "failed to apply dir-pwm state: %d\n", err);
 			pwm_disable(vibrator->pwm);
@@ -160,7 +160,7 @@ static int pwm_vibrator_probe(struct platform_device *pdev)
 	/* Sync up PWM state and ensure it is off. */
 	pwm_init_state(vibrator->pwm, &state);
 	state.enabled = false;
-	err = pwm_apply_state(vibrator->pwm, &state);
+	err = pwm_apply_might_sleep(vibrator->pwm, &state);
 	if (err) {
 		dev_err(&pdev->dev, "failed to apply initial PWM state: %d\n",
 			err);
@@ -174,7 +174,7 @@ static int pwm_vibrator_probe(struct platform_device *pdev)
 		/* Sync up PWM state and ensure it is off. */
 		pwm_init_state(vibrator->pwm_dir, &state);
 		state.enabled = false;
-		err = pwm_apply_state(vibrator->pwm_dir, &state);
+		err = pwm_apply_might_sleep(vibrator->pwm_dir, &state);
 		if (err) {
 			dev_err(&pdev->dev, "failed to apply initial PWM state: %d\n",
 				err);
diff --git a/drivers/leds/leds-pwm.c b/drivers/leds/leds-pwm.c
index 2b3bf1353b70..4e3936a39d0e 100644
--- a/drivers/leds/leds-pwm.c
+++ b/drivers/leds/leds-pwm.c
@@ -54,7 +54,7 @@ static int led_pwm_set(struct led_classdev *led_cdev,
 
 	led_dat->pwmstate.duty_cycle = duty;
 	led_dat->pwmstate.enabled = true;
-	return pwm_apply_state(led_dat->pwm, &led_dat->pwmstate);
+	return pwm_apply_might_sleep(led_dat->pwm, &led_dat->pwmstate);
 }
 
 __attribute__((nonnull))
diff --git a/drivers/leds/rgb/leds-pwm-multicolor.c b/drivers/leds/rgb/leds-pwm-multicolor.c
index 46cd062b8b24..e1a81e0109e8 100644
--- a/drivers/leds/rgb/leds-pwm-multicolor.c
+++ b/drivers/leds/rgb/leds-pwm-multicolor.c
@@ -51,8 +51,8 @@ static int led_pwm_mc_set(struct led_classdev *cdev,
 
 		priv->leds[i].state.duty_cycle = duty;
 		priv->leds[i].state.enabled = duty > 0;
-		ret = pwm_apply_state(priv->leds[i].pwm,
-				      &priv->leds[i].state);
+		ret = pwm_apply_might_sleep(priv->leds[i].pwm,
+					    &priv->leds[i].state);
 		if (ret)
 			break;
 	}
diff --git a/drivers/media/rc/pwm-ir-tx.c b/drivers/media/rc/pwm-ir-tx.c
index c5f37c03af9c..cf51e2760975 100644
--- a/drivers/media/rc/pwm-ir-tx.c
+++ b/drivers/media/rc/pwm-ir-tx.c
@@ -68,7 +68,7 @@ static int pwm_ir_tx(struct rc_dev *dev, unsigned int *txbuf,
 
 	for (i = 0; i < count; i++) {
 		state.enabled = !(i % 2);
-		pwm_apply_state(pwm, &state);
+		pwm_apply_might_sleep(pwm, &state);
 
 		edge = ktime_add_us(edge, txbuf[i]);
 		delta = ktime_us_delta(edge, ktime_get());
@@ -77,7 +77,7 @@ static int pwm_ir_tx(struct rc_dev *dev, unsigned int *txbuf,
 	}
 
 	state.enabled = false;
-	pwm_apply_state(pwm, &state);
+	pwm_apply_might_sleep(pwm, &state);
 
 	return count;
 }
diff --git a/drivers/platform/x86/lenovo-yogabook.c b/drivers/platform/x86/lenovo-yogabook.c
index b8d0239192cb..fd62bf746ebd 100644
--- a/drivers/platform/x86/lenovo-yogabook.c
+++ b/drivers/platform/x86/lenovo-yogabook.c
@@ -435,7 +435,7 @@ static int yogabook_pdev_set_kbd_backlight(struct yogabook_data *data, u8 level)
 		.enabled = level,
 	};
 
-	pwm_apply_state(data->kbd_bl_pwm, &state);
+	pwm_apply_might_sleep(data->kbd_bl_pwm, &state);
 	gpiod_set_value(data->kbd_bl_led_enable, level ? 1 : 0);
 	return 0;
 }
diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index b0e50ca9398a..c6228843a1a7 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -326,8 +326,8 @@ struct pwm_device *pwm_request_from_chip(struct pwm_chip *chip,
 }
 EXPORT_SYMBOL_GPL(pwm_request_from_chip);
 
-static void pwm_apply_state_debug(struct pwm_device *pwm,
-				  const struct pwm_state *state)
+static void pwm_apply_debug(struct pwm_device *pwm,
+			    const struct pwm_state *state)
 {
 	struct pwm_state *last = &pwm->last;
 	struct pwm_chip *chip = pwm->chip;
@@ -433,11 +433,11 @@ static void pwm_apply_state_debug(struct pwm_device *pwm,
 }
 
 /**
- * pwm_apply_state() - atomically apply a new state to a PWM device
+ * pwm_apply_might_sleep() - atomically apply a new state to a PWM device
  * @pwm: PWM device
  * @state: new state to apply
  */
-int pwm_apply_state(struct pwm_device *pwm, const struct pwm_state *state)
+int pwm_apply_might_sleep(struct pwm_device *pwm, const struct pwm_state *state)
 {
 	struct pwm_chip *chip;
 	int err;
@@ -445,7 +445,7 @@ int pwm_apply_state(struct pwm_device *pwm, const struct pwm_state *state)
 	/*
 	 * Some lowlevel driver's implementations of .apply() make use of
 	 * mutexes, also with some drivers only returning when the new
-	 * configuration is active calling pwm_apply_state() from atomic context
+	 * configuration is active calling pwm_apply_might_sleep() from atomic context
 	 * is a bad idea. So make it explicit that calling this function might
 	 * sleep.
 	 */
@@ -475,11 +475,11 @@ int pwm_apply_state(struct pwm_device *pwm, const struct pwm_state *state)
 	 * only do this after pwm->state was applied as some
 	 * implementations of .get_state depend on this
 	 */
-	pwm_apply_state_debug(pwm, state);
+	pwm_apply_debug(pwm, state);
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(pwm_apply_state);
+EXPORT_SYMBOL_GPL(pwm_apply_might_sleep);
 
 /**
  * pwm_capture() - capture and report a PWM signal
@@ -537,7 +537,7 @@ int pwm_adjust_config(struct pwm_device *pwm)
 		state.period = pargs.period;
 		state.polarity = pargs.polarity;
 
-		return pwm_apply_state(pwm, &state);
+		return pwm_apply_might_sleep(pwm, &state);
 	}
 
 	/*
@@ -560,7 +560,7 @@ int pwm_adjust_config(struct pwm_device *pwm)
 		state.duty_cycle = state.period - state.duty_cycle;
 	}
 
-	return pwm_apply_state(pwm, &state);
+	return pwm_apply_might_sleep(pwm, &state);
 }
 EXPORT_SYMBOL_GPL(pwm_adjust_config);
 
diff --git a/drivers/pwm/pwm-twl-led.c b/drivers/pwm/pwm-twl-led.c
index 8a870d0db3c6..c670ccb81653 100644
--- a/drivers/pwm/pwm-twl-led.c
+++ b/drivers/pwm/pwm-twl-led.c
@@ -172,7 +172,7 @@ static int twl4030_pwmled_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 	 * We cannot skip calling ->config even if state->period ==
 	 * pwm->state.period && state->duty_cycle == pwm->state.duty_cycle
 	 * because we might have exited early in the last call to
-	 * pwm_apply_state because of !state->enabled and so the two values in
+	 * pwm_apply_might_sleep because of !state->enabled and so the two values in
 	 * pwm->state might not be configured in hardware.
 	 */
 	ret = twl4030_pwmled_config(chip, pwm,
diff --git a/drivers/pwm/pwm-vt8500.c b/drivers/pwm/pwm-vt8500.c
index bdea60389487..7bfeacee05d0 100644
--- a/drivers/pwm/pwm-vt8500.c
+++ b/drivers/pwm/pwm-vt8500.c
@@ -206,7 +206,7 @@ static int vt8500_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 	 * We cannot skip calling ->config even if state->period ==
 	 * pwm->state.period && state->duty_cycle == pwm->state.duty_cycle
 	 * because we might have exited early in the last call to
-	 * pwm_apply_state because of !state->enabled and so the two values in
+	 * pwm_apply_might_sleep because of !state->enabled and so the two values in
 	 * pwm->state might not be configured in hardware.
 	 */
 	err = vt8500_pwm_config(chip, pwm, state->duty_cycle, state->period);
diff --git a/drivers/pwm/sysfs.c b/drivers/pwm/sysfs.c
index 4edb994fa2e1..1698609d91c8 100644
--- a/drivers/pwm/sysfs.c
+++ b/drivers/pwm/sysfs.c
@@ -62,7 +62,7 @@ static ssize_t period_store(struct device *child,
 	mutex_lock(&export->lock);
 	pwm_get_state(pwm, &state);
 	state.period = val;
-	ret = pwm_apply_state(pwm, &state);
+	ret = pwm_apply_might_sleep(pwm, &state);
 	mutex_unlock(&export->lock);
 
 	return ret ? : size;
@@ -97,7 +97,7 @@ static ssize_t duty_cycle_store(struct device *child,
 	mutex_lock(&export->lock);
 	pwm_get_state(pwm, &state);
 	state.duty_cycle = val;
-	ret = pwm_apply_state(pwm, &state);
+	ret = pwm_apply_might_sleep(pwm, &state);
 	mutex_unlock(&export->lock);
 
 	return ret ? : size;
@@ -144,7 +144,7 @@ static ssize_t enable_store(struct device *child,
 		goto unlock;
 	}
 
-	ret = pwm_apply_state(pwm, &state);
+	ret = pwm_apply_might_sleep(pwm, &state);
 
 unlock:
 	mutex_unlock(&export->lock);
@@ -194,7 +194,7 @@ static ssize_t polarity_store(struct device *child,
 	mutex_lock(&export->lock);
 	pwm_get_state(pwm, &state);
 	state.polarity = polarity;
-	ret = pwm_apply_state(pwm, &state);
+	ret = pwm_apply_might_sleep(pwm, &state);
 	mutex_unlock(&export->lock);
 
 	return ret ? : size;
@@ -401,7 +401,7 @@ static int pwm_class_apply_state(struct pwm_export *export,
 				 struct pwm_device *pwm,
 				 struct pwm_state *state)
 {
-	int ret = pwm_apply_state(pwm, state);
+	int ret = pwm_apply_might_sleep(pwm, state);
 
 	/* release lock taken in pwm_class_get_state */
 	mutex_unlock(&export->lock);
diff --git a/drivers/regulator/pwm-regulator.c b/drivers/regulator/pwm-regulator.c
index 2aff6db748e2..698c420e0869 100644
--- a/drivers/regulator/pwm-regulator.c
+++ b/drivers/regulator/pwm-regulator.c
@@ -90,7 +90,7 @@ static int pwm_regulator_set_voltage_sel(struct regulator_dev *rdev,
 	pwm_set_relative_duty_cycle(&pstate,
 			drvdata->duty_cycle_table[selector].dutycycle, 100);
 
-	ret = pwm_apply_state(drvdata->pwm, &pstate);
+	ret = pwm_apply_might_sleep(drvdata->pwm, &pstate);
 	if (ret) {
 		dev_err(&rdev->dev, "Failed to configure PWM: %d\n", ret);
 		return ret;
@@ -216,7 +216,7 @@ static int pwm_regulator_set_voltage(struct regulator_dev *rdev,
 
 	pwm_set_relative_duty_cycle(&pstate, dutycycle, duty_unit);
 
-	ret = pwm_apply_state(drvdata->pwm, &pstate);
+	ret = pwm_apply_might_sleep(drvdata->pwm, &pstate);
 	if (ret) {
 		dev_err(&rdev->dev, "Failed to configure PWM: %d\n", ret);
 		return ret;
diff --git a/drivers/video/backlight/lm3630a_bl.c b/drivers/video/backlight/lm3630a_bl.c
index 8fcb62be597b..a3412c936ca2 100644
--- a/drivers/video/backlight/lm3630a_bl.c
+++ b/drivers/video/backlight/lm3630a_bl.c
@@ -180,7 +180,7 @@ static int lm3630a_pwm_ctrl(struct lm3630a_chip *pchip, int br, int br_max)
 
 	pchip->pwmd_state.enabled = pchip->pwmd_state.duty_cycle ? true : false;
 
-	return pwm_apply_state(pchip->pwmd, &pchip->pwmd_state);
+	return pwm_apply_might_sleep(pchip->pwmd, &pchip->pwmd_state);
 }
 
 /* update and get brightness */
diff --git a/drivers/video/backlight/lp855x_bl.c b/drivers/video/backlight/lp855x_bl.c
index da1f124db69c..7075bfab59c4 100644
--- a/drivers/video/backlight/lp855x_bl.c
+++ b/drivers/video/backlight/lp855x_bl.c
@@ -234,7 +234,7 @@ static int lp855x_pwm_ctrl(struct lp855x *lp, int br, int max_br)
 	state.duty_cycle = div_u64(br * state.period, max_br);
 	state.enabled = state.duty_cycle;
 
-	return pwm_apply_state(lp->pwm, &state);
+	return pwm_apply_might_sleep(lp->pwm, &state);
 }
 
 static int lp855x_bl_update_status(struct backlight_device *bl)
diff --git a/drivers/video/backlight/pwm_bl.c b/drivers/video/backlight/pwm_bl.c
index 289bd9ce4d36..35c716e9043c 100644
--- a/drivers/video/backlight/pwm_bl.c
+++ b/drivers/video/backlight/pwm_bl.c
@@ -103,7 +103,7 @@ static int pwm_backlight_update_status(struct backlight_device *bl)
 		pwm_get_state(pb->pwm, &state);
 		state.duty_cycle = compute_duty_cycle(pb, brightness, &state);
 		state.enabled = true;
-		pwm_apply_state(pb->pwm, &state);
+		pwm_apply_might_sleep(pb->pwm, &state);
 
 		pwm_backlight_power_on(pb);
 	} else {
@@ -120,7 +120,7 @@ static int pwm_backlight_update_status(struct backlight_device *bl)
 		 * inactive output.
 		 */
 		state.enabled = !pb->power_supply && !pb->enable_gpio;
-		pwm_apply_state(pb->pwm, &state);
+		pwm_apply_might_sleep(pb->pwm, &state);
 	}
 
 	if (pb->notify_after)
@@ -528,7 +528,7 @@ static int pwm_backlight_probe(struct platform_device *pdev)
 	if (!state.period && (data->pwm_period_ns > 0))
 		state.period = data->pwm_period_ns;
 
-	ret = pwm_apply_state(pb->pwm, &state);
+	ret = pwm_apply_might_sleep(pb->pwm, &state);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to apply initial PWM state: %d\n",
 			ret);
@@ -633,7 +633,7 @@ static void pwm_backlight_remove(struct platform_device *pdev)
 	pwm_get_state(pb->pwm, &state);
 	state.duty_cycle = 0;
 	state.enabled = false;
-	pwm_apply_state(pb->pwm, &state);
+	pwm_apply_might_sleep(pb->pwm, &state);
 
 	if (pb->exit)
 		pb->exit(&pdev->dev);
@@ -649,7 +649,7 @@ static void pwm_backlight_shutdown(struct platform_device *pdev)
 	pwm_get_state(pb->pwm, &state);
 	state.duty_cycle = 0;
 	state.enabled = false;
-	pwm_apply_state(pb->pwm, &state);
+	pwm_apply_might_sleep(pb->pwm, &state);
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -673,7 +673,7 @@ static int pwm_backlight_suspend(struct device *dev)
 	pwm_get_state(pb->pwm, &state);
 	state.duty_cycle = 0;
 	state.enabled = false;
-	pwm_apply_state(pb->pwm, &state);
+	pwm_apply_might_sleep(pb->pwm, &state);
 
 	if (pb->notify_after)
 		pb->notify_after(pb->dev, 0);
diff --git a/drivers/video/fbdev/ssd1307fb.c b/drivers/video/fbdev/ssd1307fb.c
index 5ae48e36fccb..1a4f90ea7d5a 100644
--- a/drivers/video/fbdev/ssd1307fb.c
+++ b/drivers/video/fbdev/ssd1307fb.c
@@ -347,7 +347,7 @@ static int ssd1307fb_init(struct ssd1307fb_par *par)
 
 		pwm_init_state(par->pwm, &pwmstate);
 		pwm_set_relative_duty_cycle(&pwmstate, 50, 100);
-		pwm_apply_state(par->pwm, &pwmstate);
+		pwm_apply_might_sleep(par->pwm, &pwmstate);
 
 		/* Enable the PWM */
 		pwm_enable(par->pwm);
diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index f87655c06c82..b64b8a82415c 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -92,8 +92,8 @@ struct pwm_device {
  * @state: state to fill with the current PWM state
  *
  * The returned PWM state represents the state that was applied by a previous call to
- * pwm_apply_state(). Drivers may have to slightly tweak that state before programming it to
- * hardware. If pwm_apply_state() was never called, this returns either the current hardware
+ * pwm_apply_might_sleep(). Drivers may have to slightly tweak that state before programming it to
+ * hardware. If pwm_apply_might_sleep() was never called, this returns either the current hardware
  * state (if supported) or the default settings.
  */
 static inline void pwm_get_state(const struct pwm_device *pwm,
@@ -157,20 +157,20 @@ static inline void pwm_get_args(const struct pwm_device *pwm,
 }
 
 /**
- * pwm_init_state() - prepare a new state to be applied with pwm_apply_state()
+ * pwm_init_state() - prepare a new state to be applied with pwm_apply_might_sleep()
  * @pwm: PWM device
  * @state: state to fill with the prepared PWM state
  *
  * This functions prepares a state that can later be tweaked and applied
- * to the PWM device with pwm_apply_state(). This is a convenient function
+ * to the PWM device with pwm_apply_might_sleep(). This is a convenient function
  * that first retrieves the current PWM state and the replaces the period
  * and polarity fields with the reference values defined in pwm->args.
  * Once the function returns, you can adjust the ->enabled and ->duty_cycle
- * fields according to your needs before calling pwm_apply_state().
+ * fields according to your needs before calling pwm_apply_might_sleep().
  *
  * ->duty_cycle is initially set to zero to avoid cases where the current
  * ->duty_cycle value exceed the pwm_args->period one, which would trigger
- * an error if the user calls pwm_apply_state() without adjusting ->duty_cycle
+ * an error if the user calls pwm_apply_might_sleep() without adjusting ->duty_cycle
  * first.
  */
 static inline void pwm_init_state(const struct pwm_device *pwm,
@@ -226,7 +226,7 @@ pwm_get_relative_duty_cycle(const struct pwm_state *state, unsigned int scale)
  *
  * pwm_init_state(pwm, &state);
  * pwm_set_relative_duty_cycle(&state, 50, 100);
- * pwm_apply_state(pwm, &state);
+ * pwm_apply_might_sleep(pwm, &state);
  *
  * This functions returns -EINVAL if @duty_cycle and/or @scale are
  * inconsistent (@scale == 0 or @duty_cycle > @scale).
@@ -304,7 +304,7 @@ struct pwm_chip {
 
 #if IS_ENABLED(CONFIG_PWM)
 /* PWM user APIs */
-int pwm_apply_state(struct pwm_device *pwm, const struct pwm_state *state);
+int pwm_apply_might_sleep(struct pwm_device *pwm, const struct pwm_state *state);
 int pwm_adjust_config(struct pwm_device *pwm);
 
 /**
@@ -332,7 +332,7 @@ static inline int pwm_config(struct pwm_device *pwm, int duty_ns,
 
 	state.duty_cycle = duty_ns;
 	state.period = period_ns;
-	return pwm_apply_state(pwm, &state);
+	return pwm_apply_might_sleep(pwm, &state);
 }
 
 /**
@@ -353,7 +353,7 @@ static inline int pwm_enable(struct pwm_device *pwm)
 		return 0;
 
 	state.enabled = true;
-	return pwm_apply_state(pwm, &state);
+	return pwm_apply_might_sleep(pwm, &state);
 }
 
 /**
@@ -372,7 +372,7 @@ static inline void pwm_disable(struct pwm_device *pwm)
 		return;
 
 	state.enabled = false;
-	pwm_apply_state(pwm, &state);
+	pwm_apply_might_sleep(pwm, &state);
 }
 
 /* PWM provider APIs */
@@ -403,8 +403,8 @@ struct pwm_device *devm_fwnode_pwm_get(struct device *dev,
 				       struct fwnode_handle *fwnode,
 				       const char *con_id);
 #else
-static inline int pwm_apply_state(struct pwm_device *pwm,
-				  const struct pwm_state *state)
+static inline int pwm_apply_might_sleep(struct pwm_device *pwm,
+					const struct pwm_state *state)
 {
 	might_sleep();
 	return -ENOTSUPP;
@@ -521,7 +521,7 @@ static inline void pwm_apply_args(struct pwm_device *pwm)
 	state.period = pwm->args.period;
 	state.usage_power = false;
 
-	pwm_apply_state(pwm, &state);
+	pwm_apply_might_sleep(pwm, &state);
 }
 
 struct pwm_lookup {
-- 
cgit v1.2.3


From dc518b378dced419baa95d76a85f4c8c405722bc Mon Sep 17 00:00:00 2001
From: Sean Young <sean@mess.org>
Date: Tue, 19 Dec 2023 16:30:25 +0000
Subject: pwm: Replace ENOTSUPP with EOPNOTSUPP
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

According to Documentation/dev-tools/checkpatch.rst ENOTSUPP is
not recommended and EOPNOTSUPP should be used instead.

Signed-off-by: Sean Young <sean@mess.org>
Acked-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 include/linux/pwm.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index b64b8a82415c..c9cb87b59ac8 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -407,12 +407,12 @@ static inline int pwm_apply_might_sleep(struct pwm_device *pwm,
 					const struct pwm_state *state)
 {
 	might_sleep();
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 
 static inline int pwm_adjust_config(struct pwm_device *pwm)
 {
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 
 static inline int pwm_config(struct pwm_device *pwm, int duty_ns,
-- 
cgit v1.2.3


From 7170d3beafc2373dd76b6b5d6e617d89e4e42b8b Mon Sep 17 00:00:00 2001
From: Sean Young <sean@mess.org>
Date: Tue, 19 Dec 2023 16:30:27 +0000
Subject: pwm: Make it possible to apply PWM changes in atomic context
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Some PWM devices require sleeping, for example if the pwm device is
connected over I2C. However, many PWM devices could be used from atomic
context, e.g. memory mapped PWM. This is useful for, for example, the
pwm-ir-tx driver which requires precise timing. Sleeping causes havoc
with the generated IR signal.

Since not all PWM devices can support atomic context, we also add a
pwm_might_sleep() function to check if is not supported.

Signed-off-by: Sean Young <sean@mess.org>
Reviewed-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 Documentation/driver-api/pwm.rst |  9 ++++++
 MAINTAINERS                      |  2 +-
 drivers/pwm/core.c               | 62 +++++++++++++++++++++++++++++++++-------
 include/linux/pwm.h              | 25 ++++++++++++++++
 4 files changed, 86 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/Documentation/driver-api/pwm.rst b/Documentation/driver-api/pwm.rst
index f1d8197c8c43..3c28ccc4b611 100644
--- a/Documentation/driver-api/pwm.rst
+++ b/Documentation/driver-api/pwm.rst
@@ -46,6 +46,15 @@ After being requested, a PWM has to be configured using::
 This API controls both the PWM period/duty_cycle config and the
 enable/disable state.
 
+PWM devices can be used from atomic context, if the PWM does not sleep. You
+can check if this the case with::
+
+        bool pwm_might_sleep(struct pwm_device *pwm);
+
+If false, the PWM can also be configured from atomic context with::
+
+	int pwm_apply_atomic(struct pwm_device *pwm, struct pwm_state *state);
+
 As a consumer, don't rely on the output's state for a disabled PWM. If it's
 easily possible, drivers are supposed to emit the inactive state, but some
 drivers cannot. If you rely on getting the inactive state, use .duty_cycle=0,
diff --git a/MAINTAINERS b/MAINTAINERS
index c58480595220..5342cf32d73f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -17576,7 +17576,7 @@ F:	drivers/video/backlight/pwm_bl.c
 F:	include/dt-bindings/pwm/
 F:	include/linux/pwm.h
 F:	include/linux/pwm_backlight.h
-K:	pwm_(config|apply_might_sleep|ops)
+K:	pwm_(config|apply_might_sleep|apply_atomic|ops)
 
 PXA GPIO DRIVER
 M:	Robert Jarzmik <robert.jarzmik@free.fr>
diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index c6228843a1a7..f1ded8ce5ea4 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -433,24 +433,15 @@ static void pwm_apply_debug(struct pwm_device *pwm,
 }
 
 /**
- * pwm_apply_might_sleep() - atomically apply a new state to a PWM device
+ * __pwm_apply() - atomically apply a new state to a PWM device
  * @pwm: PWM device
  * @state: new state to apply
  */
-int pwm_apply_might_sleep(struct pwm_device *pwm, const struct pwm_state *state)
+static int __pwm_apply(struct pwm_device *pwm, const struct pwm_state *state)
 {
 	struct pwm_chip *chip;
 	int err;
 
-	/*
-	 * Some lowlevel driver's implementations of .apply() make use of
-	 * mutexes, also with some drivers only returning when the new
-	 * configuration is active calling pwm_apply_might_sleep() from atomic context
-	 * is a bad idea. So make it explicit that calling this function might
-	 * sleep.
-	 */
-	might_sleep();
-
 	if (!pwm || !state || !state->period ||
 	    state->duty_cycle > state->period)
 		return -EINVAL;
@@ -479,8 +470,57 @@ int pwm_apply_might_sleep(struct pwm_device *pwm, const struct pwm_state *state)
 
 	return 0;
 }
+
+/**
+ * pwm_apply_might_sleep() - atomically apply a new state to a PWM device
+ * Cannot be used in atomic context.
+ * @pwm: PWM device
+ * @state: new state to apply
+ */
+int pwm_apply_might_sleep(struct pwm_device *pwm, const struct pwm_state *state)
+{
+	int err;
+
+	/*
+	 * Some lowlevel driver's implementations of .apply() make use of
+	 * mutexes, also with some drivers only returning when the new
+	 * configuration is active calling pwm_apply_might_sleep() from atomic context
+	 * is a bad idea. So make it explicit that calling this function might
+	 * sleep.
+	 */
+	might_sleep();
+
+	if (IS_ENABLED(CONFIG_PWM_DEBUG) && pwm->chip->atomic) {
+		/*
+		 * Catch any drivers that have been marked as atomic but
+		 * that will sleep anyway.
+		 */
+		non_block_start();
+		err = __pwm_apply(pwm, state);
+		non_block_end();
+	} else {
+		err = __pwm_apply(pwm, state);
+	}
+
+	return err;
+}
 EXPORT_SYMBOL_GPL(pwm_apply_might_sleep);
 
+/**
+ * pwm_apply_atomic() - apply a new state to a PWM device from atomic context
+ * Not all PWM devices support this function, check with pwm_might_sleep().
+ * @pwm: PWM device
+ * @state: new state to apply
+ */
+int pwm_apply_atomic(struct pwm_device *pwm, const struct pwm_state *state)
+{
+	WARN_ONCE(!pwm->chip->atomic,
+		  "sleeping PWM driver used in atomic context\n");
+
+	return __pwm_apply(pwm, state);
+}
+EXPORT_SYMBOL_GPL(pwm_apply_atomic);
+
 /**
  * pwm_capture() - capture and report a PWM signal
  * @pwm: PWM device
diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index c9cb87b59ac8..495af3627939 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -285,6 +285,7 @@ struct pwm_ops {
  * @npwm: number of PWMs controlled by this chip
  * @of_xlate: request a PWM device given a device tree PWM specifier
  * @of_pwm_n_cells: number of cells expected in the device tree PWM specifier
+ * @atomic: can the driver's ->apply() be called in atomic context
  * @pwms: array of PWM devices allocated by the framework
  */
 struct pwm_chip {
@@ -297,6 +298,7 @@ struct pwm_chip {
 	struct pwm_device * (*of_xlate)(struct pwm_chip *chip,
 					const struct of_phandle_args *args);
 	unsigned int of_pwm_n_cells;
+	bool atomic;
 
 	/* only used internally by the PWM framework */
 	struct pwm_device *pwms;
@@ -305,6 +307,7 @@ struct pwm_chip {
 #if IS_ENABLED(CONFIG_PWM)
 /* PWM user APIs */
 int pwm_apply_might_sleep(struct pwm_device *pwm, const struct pwm_state *state);
+int pwm_apply_atomic(struct pwm_device *pwm, const struct pwm_state *state);
 int pwm_adjust_config(struct pwm_device *pwm);
 
 /**
@@ -375,6 +378,17 @@ static inline void pwm_disable(struct pwm_device *pwm)
 	pwm_apply_might_sleep(pwm, &state);
 }
 
+/**
+ * pwm_might_sleep() - is pwm_apply_atomic() supported?
+ * @pwm: PWM device
+ *
+ * Returns: false if pwm_apply_atomic() can be called from atomic context.
+ */
+static inline bool pwm_might_sleep(struct pwm_device *pwm)
+{
+	return !pwm->chip->atomic;
+}
+
 /* PWM provider APIs */
 int pwm_capture(struct pwm_device *pwm, struct pwm_capture *result,
 		unsigned long timeout);
@@ -403,6 +417,11 @@ struct pwm_device *devm_fwnode_pwm_get(struct device *dev,
 				       struct fwnode_handle *fwnode,
 				       const char *con_id);
 #else
+static inline bool pwm_might_sleep(struct pwm_device *pwm)
+{
+	return true;
+}
+
 static inline int pwm_apply_might_sleep(struct pwm_device *pwm,
 					const struct pwm_state *state)
 {
@@ -410,6 +429,12 @@ static inline int pwm_apply_might_sleep(struct pwm_device *pwm,
 	return -EOPNOTSUPP;
 }
 
+static inline int pwm_apply_atomic(struct pwm_device *pwm,
+				   const struct pwm_state *state)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline int pwm_adjust_config(struct pwm_device *pwm)
 {
 	return -EOPNOTSUPP;
-- 
cgit v1.2.3


From fe22944cf05ede8e6f841cfecdb7093a53a3d9b3 Mon Sep 17 00:00:00 2001
From: xiaoming Wang <xiaoming.wang@intel.com>
Date: Tue, 19 Dec 2023 11:34:11 +0800
Subject: cpu/hotplug: Increase the number of dynamic states

The dynamically allocatable hotplug state space can be exhausted by
the existing drivers and infrastructure which install CPU hotplug
states dynamically. That prevents new drivers and infrastructure from
installing dynamically allocated states.

Increase the size of the CPUHP_AP_ONLINE_DYN state by 10 to make
room.

Signed-off-by: Xiaoming Wang <xiaoming.wang@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20231219033411.816100-1-xiaoming.wang@intel.com
---
 include/linux/cpuhotplug.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index af6c21aab985..8bd454dfe453 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -239,7 +239,7 @@ enum cpuhp_state {
 	CPUHP_AP_RCUTREE_ONLINE,
 	CPUHP_AP_BASE_CACHEINFO_ONLINE,
 	CPUHP_AP_ONLINE_DYN,
-	CPUHP_AP_ONLINE_DYN_END		= CPUHP_AP_ONLINE_DYN + 30,
+	CPUHP_AP_ONLINE_DYN_END		= CPUHP_AP_ONLINE_DYN + 40,
 	CPUHP_AP_X86_HPET_ONLINE,
 	CPUHP_AP_X86_KVM_CLK_ONLINE,
 	CPUHP_AP_ACTIVE,
-- 
cgit v1.2.3


From dbcdcb62b59db2cf6a24113873b90da15c6f0b19 Mon Sep 17 00:00:00 2001
From: Anna-Maria Behnsen <anna-maria@linutronix.de>
Date: Fri, 1 Dec 2023 10:26:26 +0100
Subject: tracing/timers: Enhance timer_start tracepoint

For starting a timer, the timer is enqueued into a bucket of the timer
wheel. The bucket expiry is the defacto expiry of the timer but it is not
equal the timer expiry because of increasing granularity when bucket is in
a higher level of the wheel. To be able to figure out in a trace whether a
timer expired in time or not, the bucket expiry time is required as well.

Add bucket expiry time to the timer_start tracepoint and thereby simplify
the arguments.

Signed-off-by: Anna-Maria Behnsen <anna-maria@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Link: https://lore.kernel.org/r/20231201092654.34614-5-anna-maria@linutronix.de
---
 include/trace/events/timer.h | 20 ++++++++++----------
 kernel/time/timer.c          |  2 +-
 2 files changed, 11 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h
index b4bc2828fa09..99ada928d445 100644
--- a/include/trace/events/timer.h
+++ b/include/trace/events/timer.h
@@ -46,22 +46,21 @@ DEFINE_EVENT(timer_class, timer_init,
 
 /**
  * timer_start - called when the timer is started
- * @timer:	pointer to struct timer_list
- * @expires:	the timers expiry time
- * @flags:	the timers flags
+ * @timer:		pointer to struct timer_list
+ * @bucket_expiry:	the bucket expiry time
  */
 TRACE_EVENT(timer_start,
 
 	TP_PROTO(struct timer_list *timer,
-		unsigned long expires,
-		unsigned int flags),
+		unsigned long bucket_expiry),
 
-	TP_ARGS(timer, expires, flags),
+	TP_ARGS(timer, bucket_expiry),
 
 	TP_STRUCT__entry(
 		__field( void *,	timer		)
 		__field( void *,	function	)
 		__field( unsigned long,	expires		)
+		__field( unsigned long,	bucket_expiry	)
 		__field( unsigned long,	now		)
 		__field( unsigned int,	flags		)
 	),
@@ -69,15 +68,16 @@ TRACE_EVENT(timer_start,
 	TP_fast_assign(
 		__entry->timer		= timer;
 		__entry->function	= timer->function;
-		__entry->expires	= expires;
+		__entry->expires	= timer->expires;
+		__entry->bucket_expiry	= bucket_expiry;
 		__entry->now		= jiffies;
-		__entry->flags		= flags;
+		__entry->flags		= timer->flags;
 	),
 
-	TP_printk("timer=%p function=%ps expires=%lu [timeout=%ld] cpu=%u idx=%u flags=%s",
+	TP_printk("timer=%p function=%ps expires=%lu [timeout=%ld] bucket_expiry=%lu cpu=%u idx=%u flags=%s",
 		  __entry->timer, __entry->function, __entry->expires,
 		  (long)__entry->expires - __entry->now,
-		  __entry->flags & TIMER_CPUMASK,
+		  __entry->bucket_expiry, __entry->flags & TIMER_CPUMASK,
 		  __entry->flags >> TIMER_ARRAYSHIFT,
 		  decode_timer_flags(__entry->flags & TIMER_TRACE_FLAGMASK))
 );
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 63a8ce7177dd..a81d793a43d0 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -606,7 +606,7 @@ static void enqueue_timer(struct timer_base *base, struct timer_list *timer,
 	__set_bit(idx, base->pending_map);
 	timer_set_idx(timer, idx);
 
-	trace_timer_start(timer, timer->expires, timer->flags);
+	trace_timer_start(timer, bucket_expiry);
 
 	/*
 	 * Check whether this is the new first expiring timer. The
-- 
cgit v1.2.3


From b573c73101d8786446535b2ab28cbc8907bda9a9 Mon Sep 17 00:00:00 2001
From: Anna-Maria Behnsen <anna-maria@linutronix.de>
Date: Fri, 1 Dec 2023 10:26:27 +0100
Subject: tracing/timers: Add tracepoint for tracking timer base is_idle flag

When debugging timer code the timer tracepoints are very important. There
is no tracepoint when the is_idle flag of the timer base changes. Instead
of always adding manually trace_printk(), add tracepoints which can be
easily enabled whenever required.

Signed-off-by: Anna-Maria Behnsen <anna-maria@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Link: https://lore.kernel.org/r/20231201092654.34614-6-anna-maria@linutronix.de
---
 include/trace/events/timer.h | 20 ++++++++++++++++++++
 kernel/time/timer.c          | 14 +++++++++++---
 2 files changed, 31 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h
index 99ada928d445..1ef58a04fc57 100644
--- a/include/trace/events/timer.h
+++ b/include/trace/events/timer.h
@@ -142,6 +142,26 @@ DEFINE_EVENT(timer_class, timer_cancel,
 	TP_ARGS(timer)
 );
 
+TRACE_EVENT(timer_base_idle,
+
+	TP_PROTO(bool is_idle, unsigned int cpu),
+
+	TP_ARGS(is_idle, cpu),
+
+	TP_STRUCT__entry(
+		__field( bool,		is_idle	)
+		__field( unsigned int,	cpu	)
+	),
+
+	TP_fast_assign(
+		__entry->is_idle	= is_idle;
+		__entry->cpu		= cpu;
+	),
+
+	TP_printk("is_idle=%d cpu=%d",
+		  __entry->is_idle, __entry->cpu)
+);
+
 #define decode_clockid(type)						\
 	__print_symbolic(type,						\
 		{ CLOCK_REALTIME,	"CLOCK_REALTIME"	},	\
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index a81d793a43d0..ed8d6063d9ef 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1950,7 +1950,10 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
 
 	if (time_before_eq(nextevt, basej)) {
 		expires = basem;
-		base->is_idle = false;
+		if (base->is_idle) {
+			base->is_idle = false;
+			trace_timer_base_idle(false, base->cpu);
+		}
 	} else {
 		if (base->timers_pending)
 			expires = basem + (u64)(nextevt - basej) * TICK_NSEC;
@@ -1961,8 +1964,10 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
 		 * logic is only maintained for the BASE_STD base, deferrable
 		 * timers may still see large granularity skew (by design).
 		 */
-		if ((expires - basem) > TICK_NSEC)
+		if ((expires - basem) > TICK_NSEC && !base->is_idle) {
 			base->is_idle = true;
+			trace_timer_base_idle(true, base->cpu);
+		}
 	}
 	raw_spin_unlock(&base->lock);
 
@@ -1984,7 +1989,10 @@ void timer_clear_idle(void)
 	 * sending the IPI a few instructions smaller for the cost of taking
 	 * the lock in the exit from idle path.
 	 */
-	base->is_idle = false;
+	if (base->is_idle) {
+		base->is_idle = false;
+		trace_timer_base_idle(false, smp_processor_id());
+	}
 }
 #endif
 
-- 
cgit v1.2.3


From 80e4a9987999e682366d60f43a7b2adefc48e222 Mon Sep 17 00:00:00 2001
From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Date: Sun, 10 Dec 2023 00:00:47 +0100
Subject: pwm: Drop two unused API functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

These functions are unused. Also I think there is no valid use case
where these are correct to be called. So drop them.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 include/linux/pwm.h | 12 ------------
 1 file changed, 12 deletions(-)

(limited to 'include')

diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index 495af3627939..5dd665d8c909 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -111,12 +111,6 @@ static inline bool pwm_is_enabled(const struct pwm_device *pwm)
 	return state.enabled;
 }
 
-static inline void pwm_set_period(struct pwm_device *pwm, u64 period)
-{
-	if (pwm)
-		pwm->state.period = period;
-}
-
 static inline u64 pwm_get_period(const struct pwm_device *pwm)
 {
 	struct pwm_state state;
@@ -126,12 +120,6 @@ static inline u64 pwm_get_period(const struct pwm_device *pwm)
 	return state.period;
 }
 
-static inline void pwm_set_duty_cycle(struct pwm_device *pwm, unsigned int duty)
-{
-	if (pwm)
-		pwm->state.duty_cycle = duty;
-}
-
 static inline u64 pwm_get_duty_cycle(const struct pwm_device *pwm)
 {
 	struct pwm_state state;
-- 
cgit v1.2.3


From eba2591d99d1f14a04c8a8a845ab0795b93f5646 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Wed, 13 Dec 2023 21:29:59 +0100
Subject: mm: Introduce pudp/p4dp/pgdp_get() functions

Instead of directly dereferencing page tables entries, which can cause
issues (see commit 20a004e7b017 ("arm64: mm: Use READ_ONCE/WRITE_ONCE when
accessing page tables"), let's introduce new functions to get the
pud/p4d/pgd entries (the pte and pmd versions already exist).

Note that arm pgd_t is actually an array so pgdp_get() is defined as a
macro to avoid a build error.

Those new functions will be used in subsequent commits by the riscv
architecture.

Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Link: https://lore.kernel.org/r/20231213203001.179237-3-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/arm/include/asm/pgtable.h |  2 ++
 include/linux/pgtable.h        | 21 +++++++++++++++++++++
 2 files changed, 23 insertions(+)

(limited to 'include')

diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index 16b02f44c7d3..d657b84b6bf7 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -151,6 +151,8 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 
 extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 
+#define pgdp_get(pgpd)		READ_ONCE(*pgdp)
+
 #define pud_page(pud)		pmd_page(__pmd(pud_val(pud)))
 #define pud_write(pud)		pmd_write(__pmd(pud_val(pud)))
 
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index af7639c3b0a3..8b7daccd11be 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -292,6 +292,27 @@ static inline pmd_t pmdp_get(pmd_t *pmdp)
 }
 #endif
 
+#ifndef pudp_get
+static inline pud_t pudp_get(pud_t *pudp)
+{
+	return READ_ONCE(*pudp);
+}
+#endif
+
+#ifndef p4dp_get
+static inline p4d_t p4dp_get(p4d_t *p4dp)
+{
+	return READ_ONCE(*p4dp);
+}
+#endif
+
+#ifndef pgdp_get
+static inline pgd_t pgdp_get(pgd_t *pgdp)
+{
+	return READ_ONCE(*pgdp);
+}
+#endif
+
 #ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
 static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
 					    unsigned long address,
-- 
cgit v1.2.3


From 7d7ef0a4686abe43cd76a141b340a348f45ecdf2 Mon Sep 17 00:00:00 2001
From: Yosry Ahmed <yosryahmed@google.com>
Date: Wed, 29 Nov 2023 03:21:53 +0000
Subject: mm: memcg: restore subtree stats flushing

Stats flushing for memcg currently follows the following rules:
- Always flush the entire memcg hierarchy (i.e. flush the root).
- Only one flusher is allowed at a time. If someone else tries to flush
  concurrently, they skip and return immediately.
- A periodic flusher flushes all the stats every 2 seconds.

The reason this approach is followed is because all flushes are serialized
by a global rstat spinlock.  On the memcg side, flushing is invoked from
userspace reads as well as in-kernel flushers (e.g.  reclaim, refault,
etc).  This approach aims to avoid serializing all flushers on the global
lock, which can cause a significant performance hit under high
concurrency.

This approach has the following problems:
- Occasionally a userspace read of the stats of a non-root cgroup will
  be too expensive as it has to flush the entire hierarchy [1].
- Sometimes the stats accuracy are compromised if there is an ongoing
  flush, and we skip and return before the subtree of interest is
  actually flushed, yielding stale stats (by up to 2s due to periodic
  flushing). This is more visible when reading stats from userspace,
  but can also affect in-kernel flushers.

The latter problem is particulary a concern when userspace reads stats
after an event occurs, but gets stats from before the event. Examples:
- When memory usage / pressure spikes, a userspace OOM handler may look
  at the stats of different memcgs to select a victim based on various
  heuristics (e.g. how much private memory will be freed by killing
  this). Reading stale stats from before the usage spike in this case
  may cause a wrongful OOM kill.
- A proactive reclaimer may read the stats after writing to
  memory.reclaim to measure the success of the reclaim operation. Stale
  stats from before reclaim may give a false negative.
- Reading the stats of a parent and a child memcg may be inconsistent
  (child larger than parent), if the flush doesn't happen when the
  parent is read, but happens when the child is read.

As for in-kernel flushers, they will occasionally get stale stats.  No
regressions are currently known from this, but if there are regressions,
they would be very difficult to debug and link to the source of the
problem.

This patch aims to fix these problems by restoring subtree flushing, and
removing the unified/coalesced flushing logic that skips flushing if there
is an ongoing flush.  This change would introduce a significant regression
with global stats flushing thresholds.  With per-memcg stats flushing
thresholds, this seems to perform really well.  The thresholds protect the
underlying lock from unnecessary contention.

This patch was tested in two ways to ensure the latency of flushing is
up to par, on a machine with 384 cpus:

- A synthetic test with 5000 concurrent workers in 500 cgroups doing
  allocations and reclaim, as well as 1000 readers for memory.stat
  (variation of [2]). No regressions were noticed in the total runtime.
  Note that significant regressions in this test are observed with
  global stats thresholds, but not with per-memcg thresholds.

- A synthetic stress test for concurrently reading memcg stats while
  memory allocation/freeing workers are running in the background,
  provided by Wei Xu [3]. With 250k threads reading the stats every
  100ms in 50k cgroups, 99.9% of reads take <= 50us. Less than 0.01%
  of reads take more than 1ms, and no reads take more than 100ms.

[1] https://lore.kernel.org/lkml/CABWYdi0c6__rh-K7dcM_pkf9BJdTRtAU08M43KO9ME4-dsgfoQ@mail.gmail.com/
[2] https://lore.kernel.org/lkml/CAJD7tka13M-zVZTyQJYL1iUAYvuQ1fcHbCjcOBZcz6POYTV-4g@mail.gmail.com/
[3] https://lore.kernel.org/lkml/CAAPL-u9D2b=iF5Lf_cRnKxUfkiEe0AMDTu6yhrUAzX0b6a6rDg@mail.gmail.com/

[akpm@linux-foundation.org: fix mm/zswap.c]
[yosryahmed@google.com: remove stats flushing mutex]
  Link: https://lkml.kernel.org/r/CAJD7tkZgP3m-VVPn+fF_YuvXeQYK=tZZjJHj=dzD=CcSSpp2qg@mail.gmail.com
Link: https://lkml.kernel.org/r/20231129032154.3710765-6-yosryahmed@google.com
Signed-off-by: Yosry Ahmed <yosryahmed@google.com>
Tested-by: Domenico Cerasuolo <cerasuolodomenico@gmail.com>
Acked-by: Shakeel Butt <shakeelb@google.com>
Cc: Chris Li <chrisl@kernel.org>
Cc: Greg Thelen <gthelen@google.com>
Cc: Ivan Babrou <ivan@cloudflare.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Michal Koutny <mkoutny@suse.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Tejun Heo <tj@kernel.org>
Cc: Waiman Long <longman@redhat.com>
Cc: Wei Xu <weixugc@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/memcontrol.h |  8 +++---
 mm/memcontrol.c            | 68 ++++++++++++++++++++++++++--------------------
 mm/vmscan.c                |  2 +-
 mm/workingset.c            | 10 +++++--
 mm/zswap.c                 |  2 +-
 5 files changed, 52 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index a308c8eacf20..43b77363ab8e 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -1051,8 +1051,8 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
 	return x;
 }
 
-void mem_cgroup_flush_stats(void);
-void mem_cgroup_flush_stats_ratelimited(void);
+void mem_cgroup_flush_stats(struct mem_cgroup *memcg);
+void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg);
 
 void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 			      int val);
@@ -1563,11 +1563,11 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
 	return node_page_state(lruvec_pgdat(lruvec), idx);
 }
 
-static inline void mem_cgroup_flush_stats(void)
+static inline void mem_cgroup_flush_stats(struct mem_cgroup *memcg)
 {
 }
 
-static inline void mem_cgroup_flush_stats_ratelimited(void)
+static inline void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg)
 {
 }
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c5aa0c2cb68b..b08b9cd4a3a8 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -670,7 +670,6 @@ struct memcg_vmstats {
  */
 static void flush_memcg_stats_dwork(struct work_struct *w);
 static DECLARE_DEFERRABLE_WORK(stats_flush_dwork, flush_memcg_stats_dwork);
-static atomic_t stats_flush_ongoing = ATOMIC_INIT(0);
 static u64 flush_last_time;
 
 #define FLUSH_TIME (2UL*HZ)
@@ -731,35 +730,40 @@ static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val)
 	}
 }
 
-static void do_flush_stats(void)
+static void do_flush_stats(struct mem_cgroup *memcg)
 {
-	/*
-	 * We always flush the entire tree, so concurrent flushers can just
-	 * skip. This avoids a thundering herd problem on the rstat global lock
-	 * from memcg flushers (e.g. reclaim, refault, etc).
-	 */
-	if (atomic_read(&stats_flush_ongoing) ||
-	    atomic_xchg(&stats_flush_ongoing, 1))
-		return;
-
-	WRITE_ONCE(flush_last_time, jiffies_64);
-
-	cgroup_rstat_flush(root_mem_cgroup->css.cgroup);
+	if (mem_cgroup_is_root(memcg))
+		WRITE_ONCE(flush_last_time, jiffies_64);
 
-	atomic_set(&stats_flush_ongoing, 0);
+	cgroup_rstat_flush(memcg->css.cgroup);
 }
 
-void mem_cgroup_flush_stats(void)
+/*
+ * mem_cgroup_flush_stats - flush the stats of a memory cgroup subtree
+ * @memcg: root of the subtree to flush
+ *
+ * Flushing is serialized by the underlying global rstat lock. There is also a
+ * minimum amount of work to be done even if there are no stat updates to flush.
+ * Hence, we only flush the stats if the updates delta exceeds a threshold. This
+ * avoids unnecessary work and contention on the underlying lock.
+ */
+void mem_cgroup_flush_stats(struct mem_cgroup *memcg)
 {
-	if (memcg_should_flush_stats(root_mem_cgroup))
-		do_flush_stats();
+	if (mem_cgroup_disabled())
+		return;
+
+	if (!memcg)
+		memcg = root_mem_cgroup;
+
+	if (memcg_should_flush_stats(memcg))
+		do_flush_stats(memcg);
 }
 
-void mem_cgroup_flush_stats_ratelimited(void)
+void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg)
 {
 	/* Only flush if the periodic flusher is one full cycle late */
 	if (time_after64(jiffies_64, READ_ONCE(flush_last_time) + 2*FLUSH_TIME))
-		mem_cgroup_flush_stats();
+		mem_cgroup_flush_stats(memcg);
 }
 
 static void flush_memcg_stats_dwork(struct work_struct *w)
@@ -768,7 +772,7 @@ static void flush_memcg_stats_dwork(struct work_struct *w)
 	 * Deliberately ignore memcg_should_flush_stats() here so that flushing
 	 * in latency-sensitive paths is as cheap as possible.
 	 */
-	do_flush_stats();
+	do_flush_stats(root_mem_cgroup);
 	queue_delayed_work(system_unbound_wq, &stats_flush_dwork, FLUSH_TIME);
 }
 
@@ -1643,7 +1647,7 @@ static void memcg_stat_format(struct mem_cgroup *memcg, struct seq_buf *s)
 	 *
 	 * Current memory state:
 	 */
-	mem_cgroup_flush_stats();
+	mem_cgroup_flush_stats(memcg);
 
 	for (i = 0; i < ARRAY_SIZE(memory_stats); i++) {
 		u64 size;
@@ -4193,7 +4197,7 @@ static int memcg_numa_stat_show(struct seq_file *m, void *v)
 	int nid;
 	struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
 
-	mem_cgroup_flush_stats();
+	mem_cgroup_flush_stats(memcg);
 
 	for (stat = stats; stat < stats + ARRAY_SIZE(stats); stat++) {
 		seq_printf(m, "%s=%lu", stat->name,
@@ -4274,7 +4278,7 @@ static void memcg1_stat_format(struct mem_cgroup *memcg, struct seq_buf *s)
 
 	BUILD_BUG_ON(ARRAY_SIZE(memcg1_stat_names) != ARRAY_SIZE(memcg1_stats));
 
-	mem_cgroup_flush_stats();
+	mem_cgroup_flush_stats(memcg);
 
 	for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) {
 		unsigned long nr;
@@ -4770,7 +4774,7 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
 	struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css);
 	struct mem_cgroup *parent;
 
-	mem_cgroup_flush_stats();
+	mem_cgroup_flush_stats(memcg);
 
 	*pdirty = memcg_page_state(memcg, NR_FILE_DIRTY);
 	*pwriteback = memcg_page_state(memcg, NR_WRITEBACK);
@@ -6865,7 +6869,7 @@ static int memory_numa_stat_show(struct seq_file *m, void *v)
 	int i;
 	struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
 
-	mem_cgroup_flush_stats();
+	mem_cgroup_flush_stats(memcg);
 
 	for (i = 0; i < ARRAY_SIZE(memory_stats); i++) {
 		int nid;
@@ -8096,7 +8100,11 @@ bool obj_cgroup_may_zswap(struct obj_cgroup *objcg)
 			break;
 		}
 
-		cgroup_rstat_flush(memcg->css.cgroup);
+		/*
+		 * mem_cgroup_flush_stats() ignores small changes. Use
+		 * do_flush_stats() directly to get accurate stats for charging.
+		 */
+		do_flush_stats(memcg);
 		pages = memcg_page_state(memcg, MEMCG_ZSWAP_B) / PAGE_SIZE;
 		if (pages < max)
 			continue;
@@ -8161,8 +8169,10 @@ void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size)
 static u64 zswap_current_read(struct cgroup_subsys_state *css,
 			      struct cftype *cft)
 {
-	cgroup_rstat_flush(css->cgroup);
-	return memcg_page_state(mem_cgroup_from_css(css), MEMCG_ZSWAP_B);
+	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+
+	mem_cgroup_flush_stats(memcg);
+	return memcg_page_state(memcg, MEMCG_ZSWAP_B);
 }
 
 static int zswap_max_show(struct seq_file *m, void *v)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index f0eba9ef3332..b4ca3563bcf4 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2226,7 +2226,7 @@ static void prepare_scan_control(pg_data_t *pgdat, struct scan_control *sc)
 	 * Flush the memory cgroup stats, so that we read accurate per-memcg
 	 * lruvec stats for heuristics.
 	 */
-	mem_cgroup_flush_stats();
+	mem_cgroup_flush_stats(sc->target_mem_cgroup);
 
 	/*
 	 * Determine the scan balance between anon and file LRUs.
diff --git a/mm/workingset.c b/mm/workingset.c
index 6b9871f5a2e8..2a2a34234df9 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -464,8 +464,12 @@ bool workingset_test_recent(void *shadow, bool file, bool *workingset)
 
 	rcu_read_unlock();
 
-	/* Flush stats (and potentially sleep) outside the RCU read section */
-	mem_cgroup_flush_stats_ratelimited();
+	/*
+	 * Flush stats (and potentially sleep) outside the RCU read section.
+	 * XXX: With per-memcg flushing and thresholding, is ratelimiting
+	 * still needed here?
+	 */
+	mem_cgroup_flush_stats_ratelimited(eviction_memcg);
 
 	eviction_lruvec = mem_cgroup_lruvec(eviction_memcg, pgdat);
 	refault = atomic_long_read(&eviction_lruvec->nonresident_age);
@@ -676,7 +680,7 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker,
 		struct lruvec *lruvec;
 		int i;
 
-		mem_cgroup_flush_stats();
+		mem_cgroup_flush_stats(sc->memcg);
 		lruvec = mem_cgroup_lruvec(sc->memcg, NODE_DATA(sc->nid));
 		for (pages = 0, i = 0; i < NR_LRU_LISTS; i++)
 			pages += lruvec_page_state_local(lruvec,
diff --git a/mm/zswap.c b/mm/zswap.c
index 015425ed9003..ac31fec176e9 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -641,7 +641,7 @@ static unsigned long zswap_shrinker_count(struct shrinker *shrinker,
 		return 0;
 
 #ifdef CONFIG_MEMCG_KMEM
-	mem_cgroup_flush_stats();
+	mem_cgroup_flush_stats(memcg);
 	nr_backing = memcg_page_state(memcg, MEMCG_ZSWAP_B) >> PAGE_SHIFT;
 	nr_stored = memcg_page_state(memcg, MEMCG_ZSWAPPED);
 #else
-- 
cgit v1.2.3


From 3485b88390b0af9e05dc2c3f57e9936f41e159a0 Mon Sep 17 00:00:00 2001
From: Ryan Roberts <ryan.roberts@arm.com>
Date: Thu, 7 Dec 2023 16:12:04 +0000
Subject: mm: thp: introduce multi-size THP sysfs interface

In preparation for adding support for anonymous multi-size THP, introduce
new sysfs structure that will be used to control the new behaviours.  A
new directory is added under transparent_hugepage for each supported THP
size, and contains an `enabled` file, which can be set to "inherit" (to
inherit the global setting), "always", "madvise" or "never".  For now, the
kernel still only supports PMD-sized anonymous THP, so only 1 directory is
populated.

The first half of the change converts transhuge_vma_suitable() and
hugepage_vma_check() so that they take a bitfield of orders for which the
user wants to determine support, and the functions filter out all the
orders that can't be supported, given the current sysfs configuration and
the VMA dimensions.  The resulting functions are renamed to
thp_vma_suitable_orders() and thp_vma_allowable_orders() respectively.
Convenience functions that take a single, unencoded order and return a
boolean are also defined as thp_vma_suitable_order() and
thp_vma_allowable_order().

The second half of the change implements the new sysfs interface.  It has
been done so that each supported THP size has a `struct thpsize`, which
describes the relevant metadata and is itself a kobject.  This is pretty
minimal for now, but should make it easy to add new per-thpsize files to
the interface if needed in future (e.g.  per-size defrag).  Rather than
keep the `enabled` state directly in the struct thpsize, I've elected to
directly encode it into huge_anon_orders_[always|madvise|inherit]
bitfields since this reduces the amount of work required in
thp_vma_allowable_orders() which is called for every page fault.

See Documentation/admin-guide/mm/transhuge.rst, as modified by this
commit, for details of how the new sysfs interface works.

[ryan.roberts@arm.com: fix build warning when CONFIG_SYSFS is disabled]
  Link: https://lkml.kernel.org/r/20231211125320.3997543-1-ryan.roberts@arm.com
Link: https://lkml.kernel.org/r/20231207161211.2374093-4-ryan.roberts@arm.com
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Reviewed-by: Barry Song <v-songbaohua@oppo.com>
Tested-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Tested-by: John Hubbard <jhubbard@nvidia.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: David Rientjes <rientjes@google.com>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Itaru Kitayama <itaru.kitayama@gmail.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Yin Fengwei <fengwei.yin@intel.com>
Cc: Yu Zhao <yuzhao@google.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 Documentation/admin-guide/mm/transhuge.rst |  97 +++++++++---
 Documentation/filesystems/proc.rst         |   6 +-
 fs/proc/task_mmu.c                         |   3 +-
 include/linux/huge_mm.h                    | 181 ++++++++++++++++++----
 mm/huge_memory.c                           | 231 +++++++++++++++++++++++++----
 mm/khugepaged.c                            |  20 ++-
 mm/memory.c                                |   6 +-
 mm/page_vma_mapped.c                       |   3 +-
 8 files changed, 459 insertions(+), 88 deletions(-)

(limited to 'include')

diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst
index b0cc8243e093..04eb45a2f940 100644
--- a/Documentation/admin-guide/mm/transhuge.rst
+++ b/Documentation/admin-guide/mm/transhuge.rst
@@ -45,10 +45,25 @@ components:
    the two is using hugepages just because of the fact the TLB miss is
    going to run faster.
 
+Modern kernels support "multi-size THP" (mTHP), which introduces the
+ability to allocate memory in blocks that are bigger than a base page
+but smaller than traditional PMD-size (as described above), in
+increments of a power-of-2 number of pages. mTHP can back anonymous
+memory (for example 16K, 32K, 64K, etc). These THPs continue to be
+PTE-mapped, but in many cases can still provide similar benefits to
+those outlined above: Page faults are significantly reduced (by a
+factor of e.g. 4, 8, 16, etc), but latency spikes are much less
+prominent because the size of each page isn't as huge as the PMD-sized
+variant and there is less memory to clear in each page fault. Some
+architectures also employ TLB compression mechanisms to squeeze more
+entries in when a set of PTEs are virtually and physically contiguous
+and approporiately aligned. In this case, TLB misses will occur less
+often.
+
 THP can be enabled system wide or restricted to certain tasks or even
 memory ranges inside task's address space. Unless THP is completely
 disabled, there is ``khugepaged`` daemon that scans memory and
-collapses sequences of basic pages into huge pages.
+collapses sequences of basic pages into PMD-sized huge pages.
 
 The THP behaviour is controlled via :ref:`sysfs <thp_sysfs>`
 interface and using madvise(2) and prctl(2) system calls.
@@ -95,12 +110,40 @@ Global THP controls
 Transparent Hugepage Support for anonymous memory can be entirely disabled
 (mostly for debugging purposes) or only enabled inside MADV_HUGEPAGE
 regions (to avoid the risk of consuming more memory resources) or enabled
-system wide. This can be achieved with one of::
+system wide. This can be achieved per-supported-THP-size with one of::
+
+	echo always >/sys/kernel/mm/transparent_hugepage/hugepages-<size>kB/enabled
+	echo madvise >/sys/kernel/mm/transparent_hugepage/hugepages-<size>kB/enabled
+	echo never >/sys/kernel/mm/transparent_hugepage/hugepages-<size>kB/enabled
+
+where <size> is the hugepage size being addressed, the available sizes
+for which vary by system.
+
+For example::
+
+	echo always >/sys/kernel/mm/transparent_hugepage/hugepages-2048kB/enabled
+
+Alternatively it is possible to specify that a given hugepage size
+will inherit the top-level "enabled" value::
+
+	echo inherit >/sys/kernel/mm/transparent_hugepage/hugepages-<size>kB/enabled
+
+For example::
+
+	echo inherit >/sys/kernel/mm/transparent_hugepage/hugepages-2048kB/enabled
+
+The top-level setting (for use with "inherit") can be set by issuing
+one of the following commands::
 
 	echo always >/sys/kernel/mm/transparent_hugepage/enabled
 	echo madvise >/sys/kernel/mm/transparent_hugepage/enabled
 	echo never >/sys/kernel/mm/transparent_hugepage/enabled
 
+By default, PMD-sized hugepages have enabled="inherit" and all other
+hugepage sizes have enabled="never". If enabling multiple hugepage
+sizes, the kernel will select the most appropriate enabled size for a
+given allocation.
+
 It's also possible to limit defrag efforts in the VM to generate
 anonymous hugepages in case they're not immediately free to madvise
 regions or to never try to defrag memory and simply fallback to regular
@@ -146,25 +189,34 @@ madvise
 never
 	should be self-explanatory.
 
-By default kernel tries to use huge zero page on read page fault to
-anonymous mapping. It's possible to disable huge zero page by writing 0
-or enable it back by writing 1::
+By default kernel tries to use huge, PMD-mappable zero page on read
+page fault to anonymous mapping. It's possible to disable huge zero
+page by writing 0 or enable it back by writing 1::
 
 	echo 0 >/sys/kernel/mm/transparent_hugepage/use_zero_page
 	echo 1 >/sys/kernel/mm/transparent_hugepage/use_zero_page
 
-Some userspace (such as a test program, or an optimized memory allocation
-library) may want to know the size (in bytes) of a transparent hugepage::
+Some userspace (such as a test program, or an optimized memory
+allocation library) may want to know the size (in bytes) of a
+PMD-mappable transparent hugepage::
 
 	cat /sys/kernel/mm/transparent_hugepage/hpage_pmd_size
 
-khugepaged will be automatically started when
-transparent_hugepage/enabled is set to "always" or "madvise, and it'll
-be automatically shutdown if it's set to "never".
+khugepaged will be automatically started when one or more hugepage
+sizes are enabled (either by directly setting "always" or "madvise",
+or by setting "inherit" while the top-level enabled is set to "always"
+or "madvise"), and it'll be automatically shutdown when the last
+hugepage size is disabled (either by directly setting "never", or by
+setting "inherit" while the top-level enabled is set to "never").
 
 Khugepaged controls
 -------------------
 
+.. note::
+   khugepaged currently only searches for opportunities to collapse to
+   PMD-sized THP and no attempt is made to collapse to other THP
+   sizes.
+
 khugepaged runs usually at low frequency so while one may not want to
 invoke defrag algorithms synchronously during the page faults, it
 should be worth invoking defrag at least in khugepaged. However it's
@@ -282,19 +334,26 @@ force
 Need of application restart
 ===========================
 
-The transparent_hugepage/enabled values and tmpfs mount option only affect
-future behavior. So to make them effective you need to restart any
-application that could have been using hugepages. This also applies to the
-regions registered in khugepaged.
+The transparent_hugepage/enabled and
+transparent_hugepage/hugepages-<size>kB/enabled values and tmpfs mount
+option only affect future behavior. So to make them effective you need
+to restart any application that could have been using hugepages. This
+also applies to the regions registered in khugepaged.
 
 Monitoring usage
 ================
 
-The number of anonymous transparent huge pages currently used by the
+.. note::
+   Currently the below counters only record events relating to
+   PMD-sized THP. Events relating to other THP sizes are not included.
+
+The number of PMD-sized anonymous transparent huge pages currently used by the
 system is available by reading the AnonHugePages field in ``/proc/meminfo``.
-To identify what applications are using anonymous transparent huge pages,
-it is necessary to read ``/proc/PID/smaps`` and count the AnonHugePages fields
-for each mapping.
+To identify what applications are using PMD-sized anonymous transparent huge
+pages, it is necessary to read ``/proc/PID/smaps`` and count the AnonHugePages
+fields for each mapping. (Note that AnonHugePages only applies to traditional
+PMD-sized THP for historical reasons and should have been called
+AnonHugePmdMapped).
 
 The number of file transparent huge pages mapped to userspace is available
 by reading ShmemPmdMapped and ShmemHugePages fields in ``/proc/meminfo``.
@@ -413,7 +472,7 @@ for huge pages.
 Optimizing the applications
 ===========================
 
-To be guaranteed that the kernel will map a 2M page immediately in any
+To be guaranteed that the kernel will map a THP immediately in any
 memory region, the mmap region has to be hugepage naturally
 aligned. posix_memalign() can provide that guarantee.
 
diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst
index 49ef12df631b..104c6d047d9b 100644
--- a/Documentation/filesystems/proc.rst
+++ b/Documentation/filesystems/proc.rst
@@ -528,9 +528,9 @@ replaced by copy-on-write) part of the underlying shmem object out on swap.
 does not take into account swapped out page of underlying shmem objects.
 "Locked" indicates whether the mapping is locked in memory or not.
 
-"THPeligible" indicates whether the mapping is eligible for allocating THP
-pages as well as the THP is PMD mappable or not - 1 if true, 0 otherwise.
-It just shows the current status.
+"THPeligible" indicates whether the mapping is eligible for allocating
+naturally aligned THP pages of any currently enabled size. 1 if true, 0
+otherwise.
 
 "VmFlags" field deserves a separate description. This member represents the
 kernel flags associated with the particular virtual memory area in two letter
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index d19924bf0a39..79855e1c5b57 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -865,7 +865,8 @@ static int show_smap(struct seq_file *m, void *v)
 	__show_smap(m, &mss, false);
 
 	seq_printf(m, "THPeligible:    %8u\n",
-		   hugepage_vma_check(vma, vma->vm_flags, true, false, true));
+		   !!thp_vma_allowable_orders(vma, vma->vm_flags, true, false,
+					      true, THP_ORDERS_ALL));
 
 	if (arch_pkeys_enabled())
 		seq_printf(m, "ProtectionKey:  %8u\n", vma_pkey(vma));
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index fa0350b0812a..609c153bae57 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -67,6 +67,24 @@ extern struct kobj_attribute shmem_enabled_attr;
 #define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT)
 #define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER)
 
+/*
+ * Mask of all large folio orders supported for anonymous THP.
+ */
+#define THP_ORDERS_ALL_ANON	BIT(PMD_ORDER)
+
+/*
+ * Mask of all large folio orders supported for file THP.
+ */
+#define THP_ORDERS_ALL_FILE	(BIT(PMD_ORDER) | BIT(PUD_ORDER))
+
+/*
+ * Mask of all large folio orders supported for THP.
+ */
+#define THP_ORDERS_ALL		(THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_FILE)
+
+#define thp_vma_allowable_order(vma, vm_flags, smaps, in_pf, enforce_sysfs, order) \
+	(!!thp_vma_allowable_orders(vma, vm_flags, smaps, in_pf, enforce_sysfs, BIT(order)))
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define HPAGE_PMD_SHIFT PMD_SHIFT
 #define HPAGE_PMD_SIZE	((1UL) << HPAGE_PMD_SHIFT)
@@ -77,45 +95,105 @@ extern struct kobj_attribute shmem_enabled_attr;
 #define HPAGE_PUD_MASK	(~(HPAGE_PUD_SIZE - 1))
 
 extern unsigned long transparent_hugepage_flags;
+extern unsigned long huge_anon_orders_always;
+extern unsigned long huge_anon_orders_madvise;
+extern unsigned long huge_anon_orders_inherit;
 
-#define hugepage_flags_enabled()					       \
-	(transparent_hugepage_flags &				       \
-	 ((1<<TRANSPARENT_HUGEPAGE_FLAG) |		       \
-	  (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)))
-#define hugepage_flags_always()				\
-	(transparent_hugepage_flags &			\
-	 (1<<TRANSPARENT_HUGEPAGE_FLAG))
+static inline bool hugepage_global_enabled(void)
+{
+	return transparent_hugepage_flags &
+			((1<<TRANSPARENT_HUGEPAGE_FLAG) |
+			(1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG));
+}
+
+static inline bool hugepage_global_always(void)
+{
+	return transparent_hugepage_flags &
+			(1<<TRANSPARENT_HUGEPAGE_FLAG);
+}
+
+static inline bool hugepage_flags_enabled(void)
+{
+	/*
+	 * We cover both the anon and the file-backed case here; we must return
+	 * true if globally enabled, even when all anon sizes are set to never.
+	 * So we don't need to look at huge_anon_orders_inherit.
+	 */
+	return hugepage_global_enabled() ||
+	       huge_anon_orders_always ||
+	       huge_anon_orders_madvise;
+}
+
+static inline int highest_order(unsigned long orders)
+{
+	return fls_long(orders) - 1;
+}
+
+static inline int next_order(unsigned long *orders, int prev)
+{
+	*orders &= ~BIT(prev);
+	return highest_order(*orders);
+}
 
 /*
  * Do the below checks:
  *   - For file vma, check if the linear page offset of vma is
- *     HPAGE_PMD_NR aligned within the file.  The hugepage is
- *     guaranteed to be hugepage-aligned within the file, but we must
- *     check that the PMD-aligned addresses in the VMA map to
- *     PMD-aligned offsets within the file, else the hugepage will
- *     not be PMD-mappable.
- *   - For all vmas, check if the haddr is in an aligned HPAGE_PMD_SIZE
+ *     order-aligned within the file.  The hugepage is
+ *     guaranteed to be order-aligned within the file, but we must
+ *     check that the order-aligned addresses in the VMA map to
+ *     order-aligned offsets within the file, else the hugepage will
+ *     not be mappable.
+ *   - For all vmas, check if the haddr is in an aligned hugepage
  *     area.
  */
-static inline bool transhuge_vma_suitable(struct vm_area_struct *vma,
-		unsigned long addr)
+static inline bool thp_vma_suitable_order(struct vm_area_struct *vma,
+		unsigned long addr, int order)
 {
+	unsigned long hpage_size = PAGE_SIZE << order;
 	unsigned long haddr;
 
 	/* Don't have to check pgoff for anonymous vma */
 	if (!vma_is_anonymous(vma)) {
 		if (!IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff,
-				HPAGE_PMD_NR))
+				hpage_size >> PAGE_SHIFT))
 			return false;
 	}
 
-	haddr = addr & HPAGE_PMD_MASK;
+	haddr = ALIGN_DOWN(addr, hpage_size);
 
-	if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end)
+	if (haddr < vma->vm_start || haddr + hpage_size > vma->vm_end)
 		return false;
 	return true;
 }
 
+/*
+ * Filter the bitfield of input orders to the ones suitable for use in the vma.
+ * See thp_vma_suitable_order().
+ * All orders that pass the checks are returned as a bitfield.
+ */
+static inline unsigned long thp_vma_suitable_orders(struct vm_area_struct *vma,
+		unsigned long addr, unsigned long orders)
+{
+	int order;
+
+	/*
+	 * Iterate over orders, highest to lowest, removing orders that don't
+	 * meet alignment requirements from the set. Exit loop at first order
+	 * that meets requirements, since all lower orders must also meet
+	 * requirements.
+	 */
+
+	order = highest_order(orders);
+
+	while (orders) {
+		if (thp_vma_suitable_order(vma, addr, order))
+			break;
+		order = next_order(&orders, order);
+	}
+
+	return orders;
+}
+
 static inline bool file_thp_enabled(struct vm_area_struct *vma)
 {
 	struct inode *inode;
@@ -130,8 +208,52 @@ static inline bool file_thp_enabled(struct vm_area_struct *vma)
 	       !inode_is_open_for_write(inode) && S_ISREG(inode->i_mode);
 }
 
-bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags,
-			bool smaps, bool in_pf, bool enforce_sysfs);
+unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma,
+					 unsigned long vm_flags, bool smaps,
+					 bool in_pf, bool enforce_sysfs,
+					 unsigned long orders);
+
+/**
+ * thp_vma_allowable_orders - determine hugepage orders that are allowed for vma
+ * @vma:  the vm area to check
+ * @vm_flags: use these vm_flags instead of vma->vm_flags
+ * @smaps: whether answer will be used for smaps file
+ * @in_pf: whether answer will be used by page fault handler
+ * @enforce_sysfs: whether sysfs config should be taken into account
+ * @orders: bitfield of all orders to consider
+ *
+ * Calculates the intersection of the requested hugepage orders and the allowed
+ * hugepage orders for the provided vma. Permitted orders are encoded as a set
+ * bit at the corresponding bit position (bit-2 corresponds to order-2, bit-3
+ * corresponds to order-3, etc). Order-0 is never considered a hugepage order.
+ *
+ * Return: bitfield of orders allowed for hugepage in the vma. 0 if no hugepage
+ * orders are allowed.
+ */
+static inline
+unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma,
+				       unsigned long vm_flags, bool smaps,
+				       bool in_pf, bool enforce_sysfs,
+				       unsigned long orders)
+{
+	/* Optimization to check if required orders are enabled early. */
+	if (enforce_sysfs && vma_is_anonymous(vma)) {
+		unsigned long mask = READ_ONCE(huge_anon_orders_always);
+
+		if (vm_flags & VM_HUGEPAGE)
+			mask |= READ_ONCE(huge_anon_orders_madvise);
+		if (hugepage_global_always() ||
+		    ((vm_flags & VM_HUGEPAGE) && hugepage_global_enabled()))
+			mask |= READ_ONCE(huge_anon_orders_inherit);
+
+		orders &= mask;
+		if (!orders)
+			return 0;
+	}
+
+	return __thp_vma_allowable_orders(vma, vm_flags, smaps, in_pf,
+					  enforce_sysfs, orders);
+}
 
 #define transparent_hugepage_use_zero_page()				\
 	(transparent_hugepage_flags &					\
@@ -267,17 +389,24 @@ static inline bool folio_test_pmd_mappable(struct folio *folio)
 	return false;
 }
 
-static inline bool transhuge_vma_suitable(struct vm_area_struct *vma,
-		unsigned long addr)
+static inline bool thp_vma_suitable_order(struct vm_area_struct *vma,
+		unsigned long addr, int order)
 {
 	return false;
 }
 
-static inline bool hugepage_vma_check(struct vm_area_struct *vma,
-				      unsigned long vm_flags, bool smaps,
-				      bool in_pf, bool enforce_sysfs)
+static inline unsigned long thp_vma_suitable_orders(struct vm_area_struct *vma,
+		unsigned long addr, unsigned long orders)
 {
-	return false;
+	return 0;
+}
+
+static inline unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma,
+					unsigned long vm_flags, bool smaps,
+					bool in_pf, bool enforce_sysfs,
+					unsigned long orders)
+{
+	return 0;
 }
 
 static inline void folio_prep_large_rmappable(struct folio *folio) {}
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index c848ea97ab02..387b030c7f15 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -74,12 +74,23 @@ static unsigned long deferred_split_scan(struct shrinker *shrink,
 static atomic_t huge_zero_refcount;
 struct page *huge_zero_page __read_mostly;
 unsigned long huge_zero_pfn __read_mostly = ~0UL;
+unsigned long huge_anon_orders_always __read_mostly;
+unsigned long huge_anon_orders_madvise __read_mostly;
+unsigned long huge_anon_orders_inherit __read_mostly;
+
+unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma,
+					 unsigned long vm_flags, bool smaps,
+					 bool in_pf, bool enforce_sysfs,
+					 unsigned long orders)
+{
+	/* Check the intersection of requested and supported orders. */
+	orders &= vma_is_anonymous(vma) ?
+			THP_ORDERS_ALL_ANON : THP_ORDERS_ALL_FILE;
+	if (!orders)
+		return 0;
 
-bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags,
-			bool smaps, bool in_pf, bool enforce_sysfs)
-{
 	if (!vma->vm_mm)		/* vdso */
-		return false;
+		return 0;
 
 	/*
 	 * Explicitly disabled through madvise or prctl, or some
@@ -88,16 +99,16 @@ bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags,
 	 * */
 	if ((vm_flags & VM_NOHUGEPAGE) ||
 	    test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))
-		return false;
+		return 0;
 	/*
 	 * If the hardware/firmware marked hugepage support disabled.
 	 */
 	if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED))
-		return false;
+		return 0;
 
 	/* khugepaged doesn't collapse DAX vma, but page fault is fine. */
 	if (vma_is_dax(vma))
-		return in_pf;
+		return in_pf ? orders : 0;
 
 	/*
 	 * khugepaged special VMA and hugetlb VMA.
@@ -105,17 +116,29 @@ bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags,
 	 * VM_MIXEDMAP set.
 	 */
 	if (!in_pf && !smaps && (vm_flags & VM_NO_KHUGEPAGED))
-		return false;
+		return 0;
 
 	/*
-	 * Check alignment for file vma and size for both file and anon vma.
+	 * Check alignment for file vma and size for both file and anon vma by
+	 * filtering out the unsuitable orders.
 	 *
 	 * Skip the check for page fault. Huge fault does the check in fault
-	 * handlers. And this check is not suitable for huge PUD fault.
+	 * handlers.
 	 */
-	if (!in_pf &&
-	    !transhuge_vma_suitable(vma, (vma->vm_end - HPAGE_PMD_SIZE)))
-		return false;
+	if (!in_pf) {
+		int order = highest_order(orders);
+		unsigned long addr;
+
+		while (orders) {
+			addr = vma->vm_end - (PAGE_SIZE << order);
+			if (thp_vma_suitable_order(vma, addr, order))
+				break;
+			order = next_order(&orders, order);
+		}
+
+		if (!orders)
+			return 0;
+	}
 
 	/*
 	 * Enabled via shmem mount options or sysfs settings.
@@ -124,29 +147,33 @@ bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags,
 	 */
 	if (!in_pf && shmem_file(vma->vm_file))
 		return shmem_is_huge(file_inode(vma->vm_file), vma->vm_pgoff,
-				     !enforce_sysfs, vma->vm_mm, vm_flags);
-
-	/* Enforce sysfs THP requirements as necessary */
-	if (enforce_sysfs &&
-	    (!hugepage_flags_enabled() || (!(vm_flags & VM_HUGEPAGE) &&
-					   !hugepage_flags_always())))
-		return false;
+				     !enforce_sysfs, vma->vm_mm, vm_flags)
+			? orders : 0;
 
 	if (!vma_is_anonymous(vma)) {
+		/*
+		 * Enforce sysfs THP requirements as necessary. Anonymous vmas
+		 * were already handled in thp_vma_allowable_orders().
+		 */
+		if (enforce_sysfs &&
+		    (!hugepage_global_enabled() || (!(vm_flags & VM_HUGEPAGE) &&
+						    !hugepage_global_always())))
+			return 0;
+
 		/*
 		 * Trust that ->huge_fault() handlers know what they are doing
 		 * in fault path.
 		 */
 		if (((in_pf || smaps)) && vma->vm_ops->huge_fault)
-			return true;
+			return orders;
 		/* Only regular file is valid in collapse path */
 		if (((!in_pf || smaps)) && file_thp_enabled(vma))
-			return true;
-		return false;
+			return orders;
+		return 0;
 	}
 
 	if (vma_is_temporary_stack(vma))
-		return false;
+		return 0;
 
 	/*
 	 * THPeligible bit of smaps should show 1 for proper VMAs even
@@ -156,9 +183,9 @@ bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags,
 	 * the first page fault.
 	 */
 	if (!vma->anon_vma)
-		return (smaps || in_pf);
+		return (smaps || in_pf) ? orders : 0;
 
-	return true;
+	return orders;
 }
 
 static bool get_huge_zero_page(void)
@@ -412,9 +439,136 @@ static const struct attribute_group hugepage_attr_group = {
 	.attrs = hugepage_attr,
 };
 
+static void hugepage_exit_sysfs(struct kobject *hugepage_kobj);
+static void thpsize_release(struct kobject *kobj);
+static DEFINE_SPINLOCK(huge_anon_orders_lock);
+static LIST_HEAD(thpsize_list);
+
+struct thpsize {
+	struct kobject kobj;
+	struct list_head node;
+	int order;
+};
+
+#define to_thpsize(kobj) container_of(kobj, struct thpsize, kobj)
+
+static ssize_t thpsize_enabled_show(struct kobject *kobj,
+				    struct kobj_attribute *attr, char *buf)
+{
+	int order = to_thpsize(kobj)->order;
+	const char *output;
+
+	if (test_bit(order, &huge_anon_orders_always))
+		output = "[always] inherit madvise never";
+	else if (test_bit(order, &huge_anon_orders_inherit))
+		output = "always [inherit] madvise never";
+	else if (test_bit(order, &huge_anon_orders_madvise))
+		output = "always inherit [madvise] never";
+	else
+		output = "always inherit madvise [never]";
+
+	return sysfs_emit(buf, "%s\n", output);
+}
+
+static ssize_t thpsize_enabled_store(struct kobject *kobj,
+				     struct kobj_attribute *attr,
+				     const char *buf, size_t count)
+{
+	int order = to_thpsize(kobj)->order;
+	ssize_t ret = count;
+
+	if (sysfs_streq(buf, "always")) {
+		spin_lock(&huge_anon_orders_lock);
+		clear_bit(order, &huge_anon_orders_inherit);
+		clear_bit(order, &huge_anon_orders_madvise);
+		set_bit(order, &huge_anon_orders_always);
+		spin_unlock(&huge_anon_orders_lock);
+	} else if (sysfs_streq(buf, "inherit")) {
+		spin_lock(&huge_anon_orders_lock);
+		clear_bit(order, &huge_anon_orders_always);
+		clear_bit(order, &huge_anon_orders_madvise);
+		set_bit(order, &huge_anon_orders_inherit);
+		spin_unlock(&huge_anon_orders_lock);
+	} else if (sysfs_streq(buf, "madvise")) {
+		spin_lock(&huge_anon_orders_lock);
+		clear_bit(order, &huge_anon_orders_always);
+		clear_bit(order, &huge_anon_orders_inherit);
+		set_bit(order, &huge_anon_orders_madvise);
+		spin_unlock(&huge_anon_orders_lock);
+	} else if (sysfs_streq(buf, "never")) {
+		spin_lock(&huge_anon_orders_lock);
+		clear_bit(order, &huge_anon_orders_always);
+		clear_bit(order, &huge_anon_orders_inherit);
+		clear_bit(order, &huge_anon_orders_madvise);
+		spin_unlock(&huge_anon_orders_lock);
+	} else
+		ret = -EINVAL;
+
+	return ret;
+}
+
+static struct kobj_attribute thpsize_enabled_attr =
+	__ATTR(enabled, 0644, thpsize_enabled_show, thpsize_enabled_store);
+
+static struct attribute *thpsize_attrs[] = {
+	&thpsize_enabled_attr.attr,
+	NULL,
+};
+
+static const struct attribute_group thpsize_attr_group = {
+	.attrs = thpsize_attrs,
+};
+
+static const struct kobj_type thpsize_ktype = {
+	.release = &thpsize_release,
+	.sysfs_ops = &kobj_sysfs_ops,
+};
+
+static struct thpsize *thpsize_create(int order, struct kobject *parent)
+{
+	unsigned long size = (PAGE_SIZE << order) / SZ_1K;
+	struct thpsize *thpsize;
+	int ret;
+
+	thpsize = kzalloc(sizeof(*thpsize), GFP_KERNEL);
+	if (!thpsize)
+		return ERR_PTR(-ENOMEM);
+
+	ret = kobject_init_and_add(&thpsize->kobj, &thpsize_ktype, parent,
+				   "hugepages-%lukB", size);
+	if (ret) {
+		kfree(thpsize);
+		return ERR_PTR(ret);
+	}
+
+	ret = sysfs_create_group(&thpsize->kobj, &thpsize_attr_group);
+	if (ret) {
+		kobject_put(&thpsize->kobj);
+		return ERR_PTR(ret);
+	}
+
+	thpsize->order = order;
+	return thpsize;
+}
+
+static void thpsize_release(struct kobject *kobj)
+{
+	kfree(to_thpsize(kobj));
+}
+
 static int __init hugepage_init_sysfs(struct kobject **hugepage_kobj)
 {
 	int err;
+	struct thpsize *thpsize;
+	unsigned long orders;
+	int order;
+
+	/*
+	 * Default to setting PMD-sized THP to inherit the global setting and
+	 * disable all other sizes. powerpc's PMD_ORDER isn't a compile-time
+	 * constant so we have to do this here.
+	 */
+	huge_anon_orders_inherit = BIT(PMD_ORDER);
 
 	*hugepage_kobj = kobject_create_and_add("transparent_hugepage", mm_kobj);
 	if (unlikely(!*hugepage_kobj)) {
@@ -434,8 +588,24 @@ static int __init hugepage_init_sysfs(struct kobject **hugepage_kobj)
 		goto remove_hp_group;
 	}
 
+	orders = THP_ORDERS_ALL_ANON;
+	order = highest_order(orders);
+	while (orders) {
+		thpsize = thpsize_create(order, *hugepage_kobj);
+		if (IS_ERR(thpsize)) {
+			pr_err("failed to create thpsize for order %d\n", order);
+			err = PTR_ERR(thpsize);
+			goto remove_all;
+		}
+		list_add(&thpsize->node, &thpsize_list);
+		order = next_order(&orders, order);
+	}
+
 	return 0;
 
+remove_all:
+	hugepage_exit_sysfs(*hugepage_kobj);
+	return err;
 remove_hp_group:
 	sysfs_remove_group(*hugepage_kobj, &hugepage_attr_group);
 delete_obj:
@@ -445,6 +615,13 @@ delete_obj:
 
 static void __init hugepage_exit_sysfs(struct kobject *hugepage_kobj)
 {
+	struct thpsize *thpsize, *tmp;
+
+	list_for_each_entry_safe(thpsize, tmp, &thpsize_list, node) {
+		list_del(&thpsize->node);
+		kobject_put(&thpsize->kobj);
+	}
+
 	sysfs_remove_group(hugepage_kobj, &khugepaged_attr_group);
 	sysfs_remove_group(hugepage_kobj, &hugepage_attr_group);
 	kobject_put(hugepage_kobj);
@@ -811,7 +988,7 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf)
 	struct folio *folio;
 	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
 
-	if (!transhuge_vma_suitable(vma, haddr))
+	if (!thp_vma_suitable_order(vma, haddr, PMD_ORDER))
 		return VM_FAULT_FALLBACK;
 	if (unlikely(anon_vma_prepare(vma)))
 		return VM_FAULT_OOM;
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 064654717843..d72aecd3624a 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -446,7 +446,8 @@ void khugepaged_enter_vma(struct vm_area_struct *vma,
 {
 	if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags) &&
 	    hugepage_flags_enabled()) {
-		if (hugepage_vma_check(vma, vm_flags, false, false, true))
+		if (thp_vma_allowable_order(vma, vm_flags, false, false, true,
+					    PMD_ORDER))
 			__khugepaged_enter(vma->vm_mm);
 	}
 }
@@ -922,16 +923,16 @@ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address,
 	if (!vma)
 		return SCAN_VMA_NULL;
 
-	if (!transhuge_vma_suitable(vma, address))
+	if (!thp_vma_suitable_order(vma, address, PMD_ORDER))
 		return SCAN_ADDRESS_RANGE;
-	if (!hugepage_vma_check(vma, vma->vm_flags, false, false,
-				cc->is_khugepaged))
+	if (!thp_vma_allowable_order(vma, vma->vm_flags, false, false,
+				     cc->is_khugepaged, PMD_ORDER))
 		return SCAN_VMA_CHECK;
 	/*
 	 * Anon VMA expected, the address may be unmapped then
 	 * remapped to file after khugepaged reaquired the mmap_lock.
 	 *
-	 * hugepage_vma_check may return true for qualified file
+	 * thp_vma_allowable_order may return true for qualified file
 	 * vmas.
 	 */
 	if (expect_anon && (!(*vmap)->anon_vma || !vma_is_anonymous(*vmap)))
@@ -1503,7 +1504,8 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
 	 * and map it by a PMD, regardless of sysfs THP settings. As such, let's
 	 * analogously elide sysfs THP settings here.
 	 */
-	if (!hugepage_vma_check(vma, vma->vm_flags, false, false, false))
+	if (!thp_vma_allowable_order(vma, vma->vm_flags, false, false, false,
+				     PMD_ORDER))
 		return SCAN_VMA_CHECK;
 
 	/* Keep pmd pgtable for uffd-wp; see comment in retract_page_tables() */
@@ -2368,7 +2370,8 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, int *result,
 			progress++;
 			break;
 		}
-		if (!hugepage_vma_check(vma, vma->vm_flags, false, false, true)) {
+		if (!thp_vma_allowable_order(vma, vma->vm_flags, false, false,
+					     true, PMD_ORDER)) {
 skip:
 			progress++;
 			continue;
@@ -2705,7 +2708,8 @@ int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev,
 
 	*prev = vma;
 
-	if (!hugepage_vma_check(vma, vma->vm_flags, false, false, false))
+	if (!thp_vma_allowable_order(vma, vma->vm_flags, false, false, false,
+				     PMD_ORDER))
 		return -EINVAL;
 
 	cc = kmalloc(sizeof(*cc), GFP_KERNEL);
diff --git a/mm/memory.c b/mm/memory.c
index 99582b188ed2..8ab2d994d997 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4322,7 +4322,7 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
 	pmd_t entry;
 	vm_fault_t ret = VM_FAULT_FALLBACK;
 
-	if (!transhuge_vma_suitable(vma, haddr))
+	if (!thp_vma_suitable_order(vma, haddr, PMD_ORDER))
 		return ret;
 
 	page = compound_head(page);
@@ -5116,7 +5116,7 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
 		return VM_FAULT_OOM;
 retry_pud:
 	if (pud_none(*vmf.pud) &&
-	    hugepage_vma_check(vma, vm_flags, false, true, true)) {
+	    thp_vma_allowable_order(vma, vm_flags, false, true, true, PUD_ORDER)) {
 		ret = create_huge_pud(&vmf);
 		if (!(ret & VM_FAULT_FALLBACK))
 			return ret;
@@ -5150,7 +5150,7 @@ retry_pud:
 		goto retry_pud;
 
 	if (pmd_none(*vmf.pmd) &&
-	    hugepage_vma_check(vma, vm_flags, false, true, true)) {
+	    thp_vma_allowable_order(vma, vm_flags, false, true, true, PMD_ORDER)) {
 		ret = create_huge_pmd(&vmf);
 		if (!(ret & VM_FAULT_FALLBACK))
 			return ret;
diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index e0b368e545ed..74d2de15fb5e 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -268,7 +268,8 @@ restart:
 			 * cleared *pmd but not decremented compound_mapcount().
 			 */
 			if ((pvmw->flags & PVMW_SYNC) &&
-			    transhuge_vma_suitable(vma, pvmw->address) &&
+			    thp_vma_suitable_order(vma, pvmw->address,
+						   PMD_ORDER) &&
 			    (pvmw->nr_pages >= HPAGE_PMD_NR)) {
 				spinlock_t *ptl = pmd_lock(mm, pvmw->pmd);
 
-- 
cgit v1.2.3


From 19eaf44954df64f9bc8dec398219e15ad0811497 Mon Sep 17 00:00:00 2001
From: Ryan Roberts <ryan.roberts@arm.com>
Date: Thu, 7 Dec 2023 16:12:05 +0000
Subject: mm: thp: support allocation of anonymous multi-size THP

Introduce the logic to allow THP to be configured (through the new sysfs
interface we just added) to allocate large folios to back anonymous
memory, which are larger than the base page size but smaller than
PMD-size.  We call this new THP extension "multi-size THP" (mTHP).

mTHP continues to be PTE-mapped, but in many cases can still provide
similar benefits to traditional PMD-sized THP: Page faults are
significantly reduced (by a factor of e.g.  4, 8, 16, etc.  depending on
the configured order), but latency spikes are much less prominent because
the size of each page isn't as huge as the PMD-sized variant and there is
less memory to clear in each page fault.  The number of per-page
operations (e.g.  ref counting, rmap management, lru list management) are
also significantly reduced since those ops now become per-folio.

Some architectures also employ TLB compression mechanisms to squeeze more
entries in when a set of PTEs are virtually and physically contiguous and
approporiately aligned.  In this case, TLB misses will occur less often.

The new behaviour is disabled by default, but can be enabled at runtime by
writing to /sys/kernel/mm/transparent_hugepage/hugepage-XXkb/enabled (see
documentation in previous commit).  The long term aim is to change the
default to include suitable lower orders, but there are some risks around
internal fragmentation that need to be better understood first.

[ryan.roberts@arm.com: resolve some multi-size THP review nits]
  Link: https://lkml.kernel.org/r/20231214160251.3574571-1-ryan.roberts@arm.com
Link: https://lkml.kernel.org/r/20231207161211.2374093-5-ryan.roberts@arm.com
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Tested-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Tested-by: John Hubbard <jhubbard@nvidia.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Barry Song <v-songbaohua@oppo.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: David Rientjes <rientjes@google.com>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Itaru Kitayama <itaru.kitayama@gmail.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Yin Fengwei <fengwei.yin@intel.com>
Cc: Yu Zhao <yuzhao@google.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/huge_mm.h |   6 ++-
 mm/memory.c             | 109 ++++++++++++++++++++++++++++++++++++++++++++----
 2 files changed, 104 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 609c153bae57..fa7a38a30fc6 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -68,9 +68,11 @@ extern struct kobj_attribute shmem_enabled_attr;
 #define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER)
 
 /*
- * Mask of all large folio orders supported for anonymous THP.
+ * Mask of all large folio orders supported for anonymous THP; all orders up to
+ * and including PMD_ORDER, except order-0 (which is not "huge") and order-1
+ * (which is a limitation of the THP implementation).
  */
-#define THP_ORDERS_ALL_ANON	BIT(PMD_ORDER)
+#define THP_ORDERS_ALL_ANON	((BIT(PMD_ORDER + 1) - 1) & ~(BIT(0) | BIT(1)))
 
 /*
  * Mask of all large folio orders supported for file THP.
diff --git a/mm/memory.c b/mm/memory.c
index 8ab2d994d997..3c530b639559 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4125,6 +4125,84 @@ out_release:
 	return ret;
 }
 
+static bool pte_range_none(pte_t *pte, int nr_pages)
+{
+	int i;
+
+	for (i = 0; i < nr_pages; i++) {
+		if (!pte_none(ptep_get_lockless(pte + i)))
+			return false;
+	}
+
+	return true;
+}
+
+static struct folio *alloc_anon_folio(struct vm_fault *vmf)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	struct vm_area_struct *vma = vmf->vma;
+	unsigned long orders;
+	struct folio *folio;
+	unsigned long addr;
+	pte_t *pte;
+	gfp_t gfp;
+	int order;
+
+	/*
+	 * If uffd is active for the vma we need per-page fault fidelity to
+	 * maintain the uffd semantics.
+	 */
+	if (unlikely(userfaultfd_armed(vma)))
+		goto fallback;
+
+	/*
+	 * Get a list of all the (large) orders below PMD_ORDER that are enabled
+	 * for this vma. Then filter out the orders that can't be allocated over
+	 * the faulting address and still be fully contained in the vma.
+	 */
+	orders = thp_vma_allowable_orders(vma, vma->vm_flags, false, true, true,
+					  BIT(PMD_ORDER) - 1);
+	orders = thp_vma_suitable_orders(vma, vmf->address, orders);
+
+	if (!orders)
+		goto fallback;
+
+	pte = pte_offset_map(vmf->pmd, vmf->address & PMD_MASK);
+	if (!pte)
+		return ERR_PTR(-EAGAIN);
+
+	/*
+	 * Find the highest order where the aligned range is completely
+	 * pte_none(). Note that all remaining orders will be completely
+	 * pte_none().
+	 */
+	order = highest_order(orders);
+	while (orders) {
+		addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order);
+		if (pte_range_none(pte + pte_index(addr), 1 << order))
+			break;
+		order = next_order(&orders, order);
+	}
+
+	pte_unmap(pte);
+
+	/* Try allocating the highest of the remaining orders. */
+	gfp = vma_thp_gfp_mask(vma);
+	while (orders) {
+		addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order);
+		folio = vma_alloc_folio(gfp, order, vma, addr, true);
+		if (folio) {
+			clear_huge_page(&folio->page, vmf->address, 1 << order);
+			return folio;
+		}
+		order = next_order(&orders, order);
+	}
+
+fallback:
+#endif
+	return vma_alloc_zeroed_movable_folio(vmf->vma, vmf->address);
+}
+
 /*
  * We enter with non-exclusive mmap_lock (to exclude vma changes,
  * but allow concurrent faults), and pte mapped but not yet locked.
@@ -4134,9 +4212,12 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 {
 	bool uffd_wp = vmf_orig_pte_uffd_wp(vmf);
 	struct vm_area_struct *vma = vmf->vma;
+	unsigned long addr = vmf->address;
 	struct folio *folio;
 	vm_fault_t ret = 0;
+	int nr_pages = 1;
 	pte_t entry;
+	int i;
 
 	/* File mapping without ->vm_ops ? */
 	if (vma->vm_flags & VM_SHARED)
@@ -4176,10 +4257,16 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 	/* Allocate our own private page. */
 	if (unlikely(anon_vma_prepare(vma)))
 		goto oom;
-	folio = vma_alloc_zeroed_movable_folio(vma, vmf->address);
+	/* Returns NULL on OOM or ERR_PTR(-EAGAIN) if we must retry the fault */
+	folio = alloc_anon_folio(vmf);
+	if (IS_ERR(folio))
+		return 0;
 	if (!folio)
 		goto oom;
 
+	nr_pages = folio_nr_pages(folio);
+	addr = ALIGN_DOWN(vmf->address, nr_pages * PAGE_SIZE);
+
 	if (mem_cgroup_charge(folio, vma->vm_mm, GFP_KERNEL))
 		goto oom_free_page;
 	folio_throttle_swaprate(folio, GFP_KERNEL);
@@ -4196,12 +4283,15 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 	if (vma->vm_flags & VM_WRITE)
 		entry = pte_mkwrite(pte_mkdirty(entry), vma);
 
-	vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
-			&vmf->ptl);
+	vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, addr, &vmf->ptl);
 	if (!vmf->pte)
 		goto release;
-	if (vmf_pte_changed(vmf)) {
-		update_mmu_tlb(vma, vmf->address, vmf->pte);
+	if (nr_pages == 1 && vmf_pte_changed(vmf)) {
+		update_mmu_tlb(vma, addr, vmf->pte);
+		goto release;
+	} else if (nr_pages > 1 && !pte_range_none(vmf->pte, nr_pages)) {
+		for (i = 0; i < nr_pages; i++)
+			update_mmu_tlb(vma, addr + PAGE_SIZE * i, vmf->pte + i);
 		goto release;
 	}
 
@@ -4216,16 +4306,17 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 		return handle_userfault(vmf, VM_UFFD_MISSING);
 	}
 
-	inc_mm_counter(vma->vm_mm, MM_ANONPAGES);
-	folio_add_new_anon_rmap(folio, vma, vmf->address);
+	folio_ref_add(folio, nr_pages - 1);
+	add_mm_counter(vma->vm_mm, MM_ANONPAGES, nr_pages);
+	folio_add_new_anon_rmap(folio, vma, addr);
 	folio_add_lru_vma(folio, vma);
 setpte:
 	if (uffd_wp)
 		entry = pte_mkuffd_wp(entry);
-	set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry);
+	set_ptes(vma->vm_mm, addr, vmf->pte, entry, nr_pages);
 
 	/* No need to invalidate - it was non-present before */
-	update_mmu_cache_range(vmf, vma, vmf->address, vmf->pte, 1);
+	update_mmu_cache_range(vmf, vma, addr, vmf->pte, nr_pages);
 unlock:
 	if (vmf->pte)
 		pte_unmap_unlock(vmf->pte, vmf->ptl);
-- 
cgit v1.2.3


From 6ad59a3838cd0a8536721e60b8e4fbe5fdeb233a Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Wed, 13 Dec 2023 19:03:33 +0000
Subject: mm/damon: update email of SeongJae

Patch series "mm/damon: misc updates for 6.8".

Update comments, tests, and documents for DAMON.


This patch (of 6):

SeongJae is using his kernel.org account for DAMON development.  Update
the old email addresses on the comments of DAMON source files.

Link: https://lkml.kernel.org/r/20231213190338.54146-1-sj@kernel.org
Link: https://lkml.kernel.org/r/20231213190338.54146-2-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/damon.h     | 2 +-
 mm/damon/core-test.h      | 2 +-
 mm/damon/core.c           | 2 +-
 mm/damon/dbgfs-test.h     | 2 +-
 mm/damon/dbgfs.c          | 2 +-
 mm/damon/modules-common.c | 2 +-
 mm/damon/vaddr-test.h     | 2 +-
 mm/damon/vaddr.c          | 2 +-
 8 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/damon.h b/include/linux/damon.h
index 12510d8c51c6..5881e4ac30be 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -2,7 +2,7 @@
 /*
  * DAMON api
  *
- * Author: SeongJae Park <sjpark@amazon.de>
+ * Author: SeongJae Park <sj@kernel.org>
  */
 
 #ifndef _DAMON_H_
diff --git a/mm/damon/core-test.h b/mm/damon/core-test.h
index 6e5e9502d648..876e398557b0 100644
--- a/mm/damon/core-test.h
+++ b/mm/damon/core-test.h
@@ -4,7 +4,7 @@
  *
  * Copyright 2019 Amazon.com, Inc. or its affiliates.  All rights reserved.
  *
- * Author: SeongJae Park <sjpark@amazon.de>
+ * Author: SeongJae Park <sj@kernel.org>
  */
 
 #ifdef CONFIG_DAMON_KUNIT_TEST
diff --git a/mm/damon/core.c b/mm/damon/core.c
index 2c0cc65d041e..36f6f1d21ff0 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -2,7 +2,7 @@
 /*
  * Data Access Monitor
  *
- * Author: SeongJae Park <sjpark@amazon.de>
+ * Author: SeongJae Park <sj@kernel.org>
  */
 
 #define pr_fmt(fmt) "damon: " fmt
diff --git a/mm/damon/dbgfs-test.h b/mm/damon/dbgfs-test.h
index 0bb0d532b159..2d85217f5ba4 100644
--- a/mm/damon/dbgfs-test.h
+++ b/mm/damon/dbgfs-test.h
@@ -2,7 +2,7 @@
 /*
  * DAMON Debugfs Interface Unit Tests
  *
- * Author: SeongJae Park <sjpark@amazon.de>
+ * Author: SeongJae Park <sj@kernel.org>
  */
 
 #ifdef CONFIG_DAMON_DBGFS_KUNIT_TEST
diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c
index dc0ea1fc30ca..7dac24e69e3b 100644
--- a/mm/damon/dbgfs.c
+++ b/mm/damon/dbgfs.c
@@ -2,7 +2,7 @@
 /*
  * DAMON Debugfs Interface
  *
- * Author: SeongJae Park <sjpark@amazon.de>
+ * Author: SeongJae Park <sj@kernel.org>
  */
 
 #define pr_fmt(fmt) "damon-dbgfs: " fmt
diff --git a/mm/damon/modules-common.c b/mm/damon/modules-common.c
index b2381a8466ec..7cf96574cde7 100644
--- a/mm/damon/modules-common.c
+++ b/mm/damon/modules-common.c
@@ -2,7 +2,7 @@
 /*
  * Common Primitives for DAMON Modules
  *
- * Author: SeongJae Park <sjpark@amazon.de>
+ * Author: SeongJae Park <sj@kernel.org>
  */
 
 #include <linux/damon.h>
diff --git a/mm/damon/vaddr-test.h b/mm/damon/vaddr-test.h
index dcf1ca6b31cc..83626483f82b 100644
--- a/mm/damon/vaddr-test.h
+++ b/mm/damon/vaddr-test.h
@@ -4,7 +4,7 @@
  *
  * Copyright 2019 Amazon.com, Inc. or its affiliates.  All rights reserved.
  *
- * Author: SeongJae Park <sjpark@amazon.de>
+ * Author: SeongJae Park <sj@kernel.org>
  */
 
 #ifdef CONFIG_DAMON_VADDR_KUNIT_TEST
diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c
index a4d1f63c5b23..a67454b825dc 100644
--- a/mm/damon/vaddr.c
+++ b/mm/damon/vaddr.c
@@ -2,7 +2,7 @@
 /*
  * DAMON Primitives for Virtual Address Spaces
  *
- * Author: SeongJae Park <sjpark@amazon.de>
+ * Author: SeongJae Park <sj@kernel.org>
  */
 
 #define pr_fmt(fmt) "damon-va: " fmt
-- 
cgit v1.2.3


From 0abfa8efad8dccc3899f64dafa985a251714a709 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 12 Dec 2023 20:33:16 -0800
Subject: gfp: gfp_types.h: fix typos & punctuation

Correct typos/spellos and punctutation.

Link: https://lkml.kernel.org/r/20231213043316.10128-1-rdunlap@infradead.org
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/gfp_types.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h
index ae994534a12a..1b6053da8754 100644
--- a/include/linux/gfp_types.h
+++ b/include/linux/gfp_types.h
@@ -162,25 +162,25 @@ typedef unsigned int __bitwise gfp_t;
  * %__GFP_RECLAIM is shorthand to allow/forbid both direct and kswapd reclaim.
  *
  * The default allocator behavior depends on the request size. We have a concept
- * of so called costly allocations (with order > %PAGE_ALLOC_COSTLY_ORDER).
+ * of so-called costly allocations (with order > %PAGE_ALLOC_COSTLY_ORDER).
  * !costly allocations are too essential to fail so they are implicitly
  * non-failing by default (with some exceptions like OOM victims might fail so
  * the caller still has to check for failures) while costly requests try to be
  * not disruptive and back off even without invoking the OOM killer.
  * The following three modifiers might be used to override some of these
- * implicit rules
+ * implicit rules.
  *
  * %__GFP_NORETRY: The VM implementation will try only very lightweight
  * memory direct reclaim to get some memory under memory pressure (thus
  * it can sleep). It will avoid disruptive actions like OOM killer. The
  * caller must handle the failure which is quite likely to happen under
  * heavy memory pressure. The flag is suitable when failure can easily be
- * handled at small cost, such as reduced throughput
+ * handled at small cost, such as reduced throughput.
  *
  * %__GFP_RETRY_MAYFAIL: The VM implementation will retry memory reclaim
  * procedures that have previously failed if there is some indication
- * that progress has been made else where.  It can wait for other
- * tasks to attempt high level approaches to freeing memory such as
+ * that progress has been made elsewhere.  It can wait for other
+ * tasks to attempt high-level approaches to freeing memory such as
  * compaction (which removes fragmentation) and page-out.
  * There is still a definite limit to the number of retries, but it is
  * a larger limit than with %__GFP_NORETRY.
@@ -230,7 +230,7 @@ typedef unsigned int __bitwise gfp_t;
  * is being zeroed (either via __GFP_ZERO or via init_on_alloc, provided that
  * __GFP_SKIP_ZERO is not set). This flag is intended for optimization: setting
  * memory tags at the same time as zeroing memory has minimal additional
- * performace impact.
+ * performance impact.
  *
  * %__GFP_SKIP_KASAN makes KASAN skip unpoisoning on page allocation.
  * Used for userspace and vmalloc pages; the latter are unpoisoned by
-- 
cgit v1.2.3


From cbc2fe9d9cb226347365753f50d81bc48cc3c52e Mon Sep 17 00:00:00 2001
From: Baoquan He <bhe@redhat.com>
Date: Wed, 13 Dec 2023 13:57:41 +0800
Subject: kexec_file: add kexec_file flag to control debug printing

Patch series "kexec_file: print out debugging message if required", v4.

Currently, specifying '-d' on kexec command will print a lot of debugging
informationabout kexec/kdump loading with kexec_load interface.

However, kexec_file_load prints nothing even though '-d' is specified.
It's very inconvenient to debug or analyze the kexec/kdump loading when
something wrong happened with kexec/kdump itself or develper want to check
the kexec/kdump loading.

In this patchset, a kexec_file flag is KEXEC_FILE_DEBUG added and checked
in code.  If it's passed in, debugging message of kexec_file code will be
printed out and can be seen from console and dmesg.  Otherwise, the
debugging message is printed like beofre when pr_debug() is taken.

Note:
****
=====
1) The code in kexec-tools utility also need be changed to support
passing KEXEC_FILE_DEBUG to kernel when 'kexec -s -d' is specified.
The patch link is here:
=========
[PATCH] kexec_file: add kexec_file flag to support debug printing
http://lists.infradead.org/pipermail/kexec/2023-November/028505.html

2) s390 also has kexec_file code, while I am not sure what debugging
information is necessary. So leave it to s390 developer.

Test:
****
====
Testing was done in v1 on x86_64 and arm64. For v4, tested on x86_64
again. And on x86_64, the printed messages look like below:
--------------------------------------------------------------
kexec measurement buffer for the loaded kernel at 0x207fffe000.
Loaded purgatory at 0x207fff9000
Loaded boot_param, command line and misc at 0x207fff3000 bufsz=0x1180 memsz=0x1180
Loaded 64bit kernel at 0x207c000000 bufsz=0xc88200 memsz=0x3c4a000
Loaded initrd at 0x2079e79000 bufsz=0x2186280 memsz=0x2186280
Final command line is: root=/dev/mapper/fedora_intel--knightslanding--lb--02-root ro
rd.lvm.lv=fedora_intel-knightslanding-lb-02/root console=ttyS0,115200N81 crashkernel=256M
E820 memmap:
0000000000000000-000000000009a3ff (1)
000000000009a400-000000000009ffff (2)
00000000000e0000-00000000000fffff (2)
0000000000100000-000000006ff83fff (1)
000000006ff84000-000000007ac50fff (2)
......
000000207fff6150-000000207fff615f (128)
000000207fff6160-000000207fff714f (1)
000000207fff7150-000000207fff715f (128)
000000207fff7160-000000207fff814f (1)
000000207fff8150-000000207fff815f (128)
000000207fff8160-000000207fffffff (1)
nr_segments = 5
segment[0]: buf=0x000000004e5ece74 bufsz=0x211 mem=0x207fffe000 memsz=0x1000
segment[1]: buf=0x000000009e871498 bufsz=0x4000 mem=0x207fff9000 memsz=0x5000
segment[2]: buf=0x00000000d879f1fe bufsz=0x1180 mem=0x207fff3000 memsz=0x2000
segment[3]: buf=0x000000001101cd86 bufsz=0xc88200 mem=0x207c000000 memsz=0x3c4a000
segment[4]: buf=0x00000000c6e38ac7 bufsz=0x2186280 mem=0x2079e79000 memsz=0x2187000
kexec_file_load: type:0, start:0x207fff91a0 head:0x109e004002 flags:0x8
---------------------------------------------------------------------------


This patch (of 7):

When specifying 'kexec -c -d', kexec_load interface will print loading
information, e.g the regions where kernel/initrd/purgatory/cmdline are
put, the memmap passed to 2nd kernel taken as system RAM ranges, and
printing all contents of struct kexec_segment, etc.  These are very
helpful for analyzing or positioning what's happening when kexec/kdump
itself failed.  The debugging printing for kexec_load interface is made in
user space utility kexec-tools.

Whereas, with kexec_file_load interface, 'kexec -s -d' print nothing.
Because kexec_file code is mostly implemented in kernel space, and the
debugging printing functionality is missed.  It's not convenient when
debugging kexec/kdump loading and jumping with kexec_file_load interface.

Now add KEXEC_FILE_DEBUG to kexec_file flag to control the debugging
message printing.  And add global variable kexec_file_dbg_print and macro
kexec_dprintk() to facilitate the printing.

This is a preparation, later kexec_dprintk() will be used to replace the
existing pr_debug().  Once 'kexec -s -d' is specified, it will print out
kexec/kdump loading information.  If '-d' is not specified, it regresses
to pr_debug().

Link: https://lkml.kernel.org/r/20231213055747.61826-1-bhe@redhat.com
Link: https://lkml.kernel.org/r/20231213055747.61826-2-bhe@redhat.com
Signed-off-by: Baoquan He <bhe@redhat.com>
Cc: Conor Dooley <conor@kernel.org>
Cc: Joe Perches <joe@perches.com>
Cc: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/kexec.h      | 9 ++++++++-
 include/uapi/linux/kexec.h | 1 +
 kernel/kexec_core.c        | 2 ++
 kernel/kexec_file.c        | 3 +++
 4 files changed, 14 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index 8227455192b7..400cb6c02176 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -403,7 +403,7 @@ bool kexec_load_permitted(int kexec_image_type);
 
 /* List of defined/legal kexec file flags */
 #define KEXEC_FILE_FLAGS	(KEXEC_FILE_UNLOAD | KEXEC_FILE_ON_CRASH | \
-				 KEXEC_FILE_NO_INITRAMFS)
+				 KEXEC_FILE_NO_INITRAMFS | KEXEC_FILE_DEBUG)
 
 /* flag to track if kexec reboot is in progress */
 extern bool kexec_in_progress;
@@ -500,6 +500,13 @@ static inline int crash_hotplug_memory_support(void) { return 0; }
 static inline unsigned int crash_get_elfcorehdr_size(void) { return 0; }
 #endif
 
+extern bool kexec_file_dbg_print;
+
+#define kexec_dprintk(fmt, ...)					\
+	printk("%s" fmt,					\
+	       kexec_file_dbg_print ? KERN_INFO : KERN_DEBUG,	\
+	       ##__VA_ARGS__)
+
 #else /* !CONFIG_KEXEC_CORE */
 struct pt_regs;
 struct task_struct;
diff --git a/include/uapi/linux/kexec.h b/include/uapi/linux/kexec.h
index 01766dd839b0..c17bb096ea68 100644
--- a/include/uapi/linux/kexec.h
+++ b/include/uapi/linux/kexec.h
@@ -25,6 +25,7 @@
 #define KEXEC_FILE_UNLOAD	0x00000001
 #define KEXEC_FILE_ON_CRASH	0x00000002
 #define KEXEC_FILE_NO_INITRAMFS	0x00000004
+#define KEXEC_FILE_DEBUG	0x00000008
 
 /* These values match the ELF architecture values.
  * Unless there is a good reason that should continue to be the case.
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index bc4c096ab1f3..64072acef2b6 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -52,6 +52,8 @@ atomic_t __kexec_lock = ATOMIC_INIT(0);
 /* Flag to indicate we are going to kexec a new kernel */
 bool kexec_in_progress = false;
 
+bool kexec_file_dbg_print;
+
 int kexec_should_crash(struct task_struct *p)
 {
 	/*
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index ba3ef30921b8..3ee204474de6 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -123,6 +123,8 @@ void kimage_file_post_load_cleanup(struct kimage *image)
 	 */
 	kfree(image->image_loader_data);
 	image->image_loader_data = NULL;
+
+	kexec_file_dbg_print = false;
 }
 
 #ifdef CONFIG_KEXEC_SIG
@@ -278,6 +280,7 @@ kimage_file_alloc_init(struct kimage **rimage, int kernel_fd,
 	if (!image)
 		return -ENOMEM;
 
+	kexec_file_dbg_print = !!(flags & KEXEC_FILE_DEBUG);
 	image->file_mode = 1;
 
 	if (kexec_on_panic) {
-- 
cgit v1.2.3


From f6120d527b8611aeaa1a34a33337f530d78a789c Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Fri, 15 Dec 2023 19:56:59 -0500
Subject: task_stack.h: add missing include

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 include/linux/sched/task_stack.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h
index f158b025c175..ccd72b978e1f 100644
--- a/include/linux/sched/task_stack.h
+++ b/include/linux/sched/task_stack.h
@@ -8,6 +8,7 @@
 
 #include <linux/sched.h>
 #include <linux/magic.h>
+#include <linux/refcount.h>
 
 #ifdef CONFIG_THREAD_INFO_IN_TASK
 
-- 
cgit v1.2.3


From 6a2623b17634688cfec58dd44041c5db2143719d Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Fri, 15 Dec 2023 20:00:15 -0500
Subject: nsproxy.h: add missing include

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 include/linux/nsproxy.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h
index 771cb0285872..5601d14e2886 100644
--- a/include/linux/nsproxy.h
+++ b/include/linux/nsproxy.h
@@ -2,6 +2,7 @@
 #ifndef _LINUX_NSPROXY_H
 #define _LINUX_NSPROXY_H
 
+#include <linux/refcount.h>
 #include <linux/spinlock.h>
 #include <linux/sched.h>
 
-- 
cgit v1.2.3


From 316aa04d1ffa61f73ce2679d1ae1dca8747aeb1f Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 11 Dec 2023 14:00:59 -0500
Subject: kmsan: add missing types.h dependency

more header dependency pruning/fixing

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 include/linux/kmsan_types.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/kmsan_types.h b/include/linux/kmsan_types.h
index 8bfa6c98176d..929287981afe 100644
--- a/include/linux/kmsan_types.h
+++ b/include/linux/kmsan_types.h
@@ -9,6 +9,8 @@
 #ifndef _LINUX_KMSAN_TYPES_H
 #define _LINUX_KMSAN_TYPES_H
 
+#include <linux/types.h>
+
 /* These constants are defined in the MSan LLVM instrumentation pass. */
 #define KMSAN_RETVAL_SIZE 800
 #define KMSAN_PARAM_SIZE 800
-- 
cgit v1.2.3


From 058e0529d12ae9fed34c6eeef700cd294f9622a1 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Fri, 15 Dec 2023 20:22:22 -0500
Subject: time_namespace.h: fix missing include

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 include/linux/time_namespace.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/time_namespace.h b/include/linux/time_namespace.h
index 03d9c5ac01d1..5258d81cef17 100644
--- a/include/linux/time_namespace.h
+++ b/include/linux/time_namespace.h
@@ -7,6 +7,7 @@
 #include <linux/nsproxy.h>
 #include <linux/ns_common.h>
 #include <linux/err.h>
+#include <linux/time64.h>
 
 struct user_namespace;
 extern struct user_namespace init_user_ns;
-- 
cgit v1.2.3


From ea115c248a478ce1acbf4776e4666fb663285b2f Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sun, 17 Dec 2023 20:01:01 -0500
Subject: torture: add missing dependency on hrtimer.h

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 include/linux/torture.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/torture.h b/include/linux/torture.h
index c98d0c83d117..1541454da03e 100644
--- a/include/linux/torture.h
+++ b/include/linux/torture.h
@@ -21,6 +21,7 @@
 #include <linux/debugobjects.h>
 #include <linux/bug.h>
 #include <linux/compiler.h>
+#include <linux/hrtimer.h>
 
 /* Definitions for a non-string torture-test module parameter. */
 #define torture_param(type, name, init, msg) \
-- 
cgit v1.2.3


From bea32141764bc76db2d75c9484b71ded56119ab4 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Tue, 6 Dec 2022 14:32:23 -0500
Subject: nodemask: Split out include/linux/nodemask_types.h

sched.h, which defines task_struct, needs nodemask_t - but sched.h is a
frequently used header and ideally shouldn't be pulling in any more code
that it needs to.

This splits out nodemask_types.h which has the definition sched.h needs,
which will avoid a circular header dependency in the alloc tagging patch
series, and as a bonus should speed up kernel build times.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
---
 include/linux/nodemask.h       |  2 +-
 include/linux/nodemask_types.h | 10 ++++++++++
 include/linux/sched.h          |  2 +-
 3 files changed, 12 insertions(+), 2 deletions(-)
 create mode 100644 include/linux/nodemask_types.h

(limited to 'include')

diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h
index 8d07116caaf1..b61438313a73 100644
--- a/include/linux/nodemask.h
+++ b/include/linux/nodemask.h
@@ -93,10 +93,10 @@
 #include <linux/threads.h>
 #include <linux/bitmap.h>
 #include <linux/minmax.h>
+#include <linux/nodemask_types.h>
 #include <linux/numa.h>
 #include <linux/random.h>
 
-typedef struct { DECLARE_BITMAP(bits, MAX_NUMNODES); } nodemask_t;
 extern nodemask_t _unused_nodemask_arg_;
 
 /**
diff --git a/include/linux/nodemask_types.h b/include/linux/nodemask_types.h
new file mode 100644
index 000000000000..6b28d97ea6ed
--- /dev/null
+++ b/include/linux/nodemask_types.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_NODEMASK_TYPES_H
+#define __LINUX_NODEMASK_TYPES_H
+
+#include <linux/bitops.h>
+#include <linux/numa.h>
+
+typedef struct { DECLARE_BITMAP(bits, MAX_NUMNODES); } nodemask_t;
+
+#endif /* __LINUX_NODEMASK_TYPES_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 292c31697248..5a5b7b122682 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -20,7 +20,7 @@
 #include <linux/hrtimer.h>
 #include <linux/irqflags.h>
 #include <linux/seccomp.h>
-#include <linux/nodemask.h>
+#include <linux/nodemask_types.h>
 #include <linux/rcupdate.h>
 #include <linux/refcount.h>
 #include <linux/resource.h>
-- 
cgit v1.2.3


From d9f29deb7fe8137fd1954871443cbbc1b6125832 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 23 Jan 2023 21:32:18 -0500
Subject: prandom: Remove unused include

prandom.h doesn't use percpu.h - this fixes some circular header issues.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
---
 include/linux/prandom.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/prandom.h b/include/linux/prandom.h
index f2ed5b72b3d6..f7f1e5251c67 100644
--- a/include/linux/prandom.h
+++ b/include/linux/prandom.h
@@ -10,7 +10,6 @@
 
 #include <linux/types.h>
 #include <linux/once.h>
-#include <linux/percpu.h>
 #include <linux/random.h>
 
 struct rnd_state {
-- 
cgit v1.2.3


From 6060ef31f1162fb91a1688fa5098b38c4b9c680c Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Fri, 2 Dec 2022 14:39:55 -0500
Subject: timekeeping: Kill percpu.h dependency

Slimming down recursive header includes.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Cc: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/hrtimer.h        | 2 +-
 include/linux/time_namespace.h | 2 ++
 2 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index f2044d5a652b..02d264ca9dce 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -16,7 +16,7 @@
 #include <linux/rbtree.h>
 #include <linux/init.h>
 #include <linux/list.h>
-#include <linux/percpu.h>
+#include <linux/percpu-defs.h>
 #include <linux/seqlock.h>
 #include <linux/timer.h>
 #include <linux/timerqueue.h>
diff --git a/include/linux/time_namespace.h b/include/linux/time_namespace.h
index 5258d81cef17..876e31b4461d 100644
--- a/include/linux/time_namespace.h
+++ b/include/linux/time_namespace.h
@@ -12,6 +12,8 @@
 struct user_namespace;
 extern struct user_namespace init_user_ns;
 
+struct vm_area_struct;
+
 struct timens_offsets {
 	struct timespec64 monotonic;
 	struct timespec64 boottime;
-- 
cgit v1.2.3


From d7a73e3f089204aee3393687e23fd45a22657b08 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 11 Dec 2023 13:27:00 -0500
Subject: kernel/numa.c: Move logging out of numa.h

Moving these stub functions to a .c file means we can kill a sched.h
dependency on printk.h.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 include/linux/numa.h | 19 ++++++-------------
 kernel/Makefile      |  1 +
 kernel/numa.c        | 26 ++++++++++++++++++++++++++
 3 files changed, 33 insertions(+), 13 deletions(-)
 create mode 100644 kernel/numa.c

(limited to 'include')

diff --git a/include/linux/numa.h b/include/linux/numa.h
index a904861de800..915033a75731 100644
--- a/include/linux/numa.h
+++ b/include/linux/numa.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LINUX_NUMA_H
 #define _LINUX_NUMA_H
+#include <linux/init.h>
 #include <linux/types.h>
 
 #ifdef CONFIG_NODES_SHIFT
@@ -22,34 +23,26 @@
 #endif
 
 #ifdef CONFIG_NUMA
-#include <linux/printk.h>
 #include <asm/sparsemem.h>
 
 /* Generic implementation available */
 int numa_nearest_node(int node, unsigned int state);
 
 #ifndef memory_add_physaddr_to_nid
-static inline int memory_add_physaddr_to_nid(u64 start)
-{
-	pr_info_once("Unknown online node for memory at 0x%llx, assuming node 0\n",
-			start);
-	return 0;
-}
+int memory_add_physaddr_to_nid(u64 start);
 #endif
+
 #ifndef phys_to_target_node
-static inline int phys_to_target_node(u64 start)
-{
-	pr_info_once("Unknown target node for memory at 0x%llx, assuming node 0\n",
-			start);
-	return 0;
-}
+int phys_to_target_node(u64 start);
 #endif
+
 #ifndef numa_fill_memblks
 static inline int __init numa_fill_memblks(u64 start, u64 end)
 {
 	return NUMA_NO_MEMBLK;
 }
 #endif
+
 #else /* !CONFIG_NUMA */
 static inline int numa_nearest_node(int node, unsigned int state)
 {
diff --git a/kernel/Makefile b/kernel/Makefile
index 3947122d618b..ce105a5558fc 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -114,6 +114,7 @@ obj-$(CONFIG_SHADOW_CALL_STACK) += scs.o
 obj-$(CONFIG_HAVE_STATIC_CALL) += static_call.o
 obj-$(CONFIG_HAVE_STATIC_CALL_INLINE) += static_call_inline.o
 obj-$(CONFIG_CFI_CLANG) += cfi.o
+obj-$(CONFIG_NUMA) += numa.o
 
 obj-$(CONFIG_PERF_EVENTS) += events/
 
diff --git a/kernel/numa.c b/kernel/numa.c
new file mode 100644
index 000000000000..67ca6b8585c0
--- /dev/null
+++ b/kernel/numa.c
@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/printk.h>
+#include <linux/numa.h>
+
+/* Stub functions: */
+
+#ifndef memory_add_physaddr_to_nid
+int memory_add_physaddr_to_nid(u64 start)
+{
+	pr_info_once("Unknown online node for memory at 0x%llx, assuming node 0\n",
+			start);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
+#endif
+
+#ifndef phys_to_target_node
+int phys_to_target_node(u64 start)
+{
+	pr_info_once("Unknown target node for memory at 0x%llx, assuming node 0\n",
+			start);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(phys_to_target_node);
+#endif
-- 
cgit v1.2.3


From d1d71b30e1f85e8b5d7c0d8edc16869bdc4d535f Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 11 Dec 2023 14:05:04 -0500
Subject: sched.h: Move (spin|rwlock)_needbreak() to spinlock.h

This lets us kill the dependency on spinlock.h.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 include/linux/sched.h    | 31 -------------------------------
 include/linux/spinlock.h | 31 +++++++++++++++++++++++++++++++
 2 files changed, 31 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5a5b7b122682..7501a3451a20 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2227,37 +2227,6 @@ static inline bool preempt_model_preemptible(void)
 	return preempt_model_full() || preempt_model_rt();
 }
 
-/*
- * Does a critical section need to be broken due to another
- * task waiting?: (technically does not depend on CONFIG_PREEMPTION,
- * but a general need for low latency)
- */
-static inline int spin_needbreak(spinlock_t *lock)
-{
-#ifdef CONFIG_PREEMPTION
-	return spin_is_contended(lock);
-#else
-	return 0;
-#endif
-}
-
-/*
- * Check if a rwlock is contended.
- * Returns non-zero if there is another task waiting on the rwlock.
- * Returns zero if the lock is not contended or the system / underlying
- * rwlock implementation does not support contention detection.
- * Technically does not depend on CONFIG_PREEMPTION, but a general need
- * for low latency.
- */
-static inline int rwlock_needbreak(rwlock_t *lock)
-{
-#ifdef CONFIG_PREEMPTION
-	return rwlock_is_contended(lock);
-#else
-	return 0;
-#endif
-}
-
 static __always_inline bool need_resched(void)
 {
 	return unlikely(tif_need_resched());
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 31d3d747a9db..0c71f06454d9 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -449,6 +449,37 @@ static __always_inline int spin_is_contended(spinlock_t *lock)
 	return raw_spin_is_contended(&lock->rlock);
 }
 
+/*
+ * Does a critical section need to be broken due to another
+ * task waiting?: (technically does not depend on CONFIG_PREEMPTION,
+ * but a general need for low latency)
+ */
+static inline int spin_needbreak(spinlock_t *lock)
+{
+#ifdef CONFIG_PREEMPTION
+	return spin_is_contended(lock);
+#else
+	return 0;
+#endif
+}
+
+/*
+ * Check if a rwlock is contended.
+ * Returns non-zero if there is another task waiting on the rwlock.
+ * Returns zero if the lock is not contended or the system / underlying
+ * rwlock implementation does not support contention detection.
+ * Technically does not depend on CONFIG_PREEMPTION, but a general need
+ * for low latency.
+ */
+static inline int rwlock_needbreak(rwlock_t *lock)
+{
+#ifdef CONFIG_PREEMPTION
+	return rwlock_is_contended(lock);
+#else
+	return 0;
+#endif
+}
+
 #define assert_spin_locked(lock)	assert_raw_spin_locked(&(lock)->rlock)
 
 #else  /* !CONFIG_PREEMPT_RT */
-- 
cgit v1.2.3


From 2e346b19aab9ee40e5e429667a0a515f1d68b714 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 11 Dec 2023 14:11:05 -0500
Subject: ktime.h: move ktime_t to types.h

ktime.h pulls in quite a few headers recursively (including printk.h) -
this is going to help with trimming sched.h dependencies.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 include/linux/ktime.h | 8 +++-----
 include/linux/types.h | 3 +++
 2 files changed, 6 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/ktime.h b/include/linux/ktime.h
index 73f20deb497d..3a4e723eae0f 100644
--- a/include/linux/ktime.h
+++ b/include/linux/ktime.h
@@ -21,12 +21,10 @@
 #ifndef _LINUX_KTIME_H
 #define _LINUX_KTIME_H
 
-#include <linux/time.h>
-#include <linux/jiffies.h>
 #include <asm/bug.h>
-
-/* Nanosecond scalar representation for kernel time values */
-typedef s64	ktime_t;
+#include <linux/jiffies.h>
+#include <linux/time.h>
+#include <linux/types.h>
 
 /**
  * ktime_set - Set a ktime_t variable from a seconds/nanoseconds value
diff --git a/include/linux/types.h b/include/linux/types.h
index 253168bb3fe1..2bc8766ba20c 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -120,6 +120,9 @@ typedef s64			int64_t;
 #define aligned_be64		__aligned_be64
 #define aligned_le64		__aligned_le64
 
+/* Nanosecond scalar representation for kernel time values */
+typedef s64	ktime_t;
+
 /**
  * The type used for indexing onto a disc or disc partition.
  *
-- 
cgit v1.2.3


From 50d91c76582513852e38eb80491f54d44cfb51fc Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 11 Dec 2023 11:52:02 -0500
Subject: hrtimers: Split out hrtimer_types.h

We need to reduce the scope of what's included in sched.h: task_struct
includes a hrtimer, so split out the core types into their own header.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Cc: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/hrtimer.h       | 44 ++-----------------------------------
 include/linux/hrtimer_types.h | 50 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/sched.h         |  2 +-
 3 files changed, 53 insertions(+), 43 deletions(-)
 create mode 100644 include/linux/hrtimer_types.h

(limited to 'include')

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 02d264ca9dce..87e3bedf8eb0 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -13,13 +13,13 @@
 #define _LINUX_HRTIMER_H
 
 #include <linux/hrtimer_defs.h>
-#include <linux/rbtree.h>
+#include <linux/hrtimer_types.h>
 #include <linux/init.h>
 #include <linux/list.h>
 #include <linux/percpu-defs.h>
+#include <linux/rbtree.h>
 #include <linux/seqlock.h>
 #include <linux/timer.h>
-#include <linux/timerqueue.h>
 
 struct hrtimer_clock_base;
 struct hrtimer_cpu_base;
@@ -59,14 +59,6 @@ enum hrtimer_mode {
 	HRTIMER_MODE_REL_PINNED_HARD = HRTIMER_MODE_REL_PINNED | HRTIMER_MODE_HARD,
 };
 
-/*
- * Return values for the callback function
- */
-enum hrtimer_restart {
-	HRTIMER_NORESTART,	/* Timer is not restarted */
-	HRTIMER_RESTART,	/* Timer must be restarted */
-};
-
 /*
  * Values to track state of the timer
  *
@@ -94,38 +86,6 @@ enum hrtimer_restart {
 #define HRTIMER_STATE_INACTIVE	0x00
 #define HRTIMER_STATE_ENQUEUED	0x01
 
-/**
- * struct hrtimer - the basic hrtimer structure
- * @node:	timerqueue node, which also manages node.expires,
- *		the absolute expiry time in the hrtimers internal
- *		representation. The time is related to the clock on
- *		which the timer is based. Is setup by adding
- *		slack to the _softexpires value. For non range timers
- *		identical to _softexpires.
- * @_softexpires: the absolute earliest expiry time of the hrtimer.
- *		The time which was given as expiry time when the timer
- *		was armed.
- * @function:	timer expiry callback function
- * @base:	pointer to the timer base (per cpu and per clock)
- * @state:	state information (See bit values above)
- * @is_rel:	Set if the timer was armed relative
- * @is_soft:	Set if hrtimer will be expired in soft interrupt context.
- * @is_hard:	Set if hrtimer will be expired in hard interrupt context
- *		even on RT.
- *
- * The hrtimer structure must be initialized by hrtimer_init()
- */
-struct hrtimer {
-	struct timerqueue_node		node;
-	ktime_t				_softexpires;
-	enum hrtimer_restart		(*function)(struct hrtimer *);
-	struct hrtimer_clock_base	*base;
-	u8				state;
-	u8				is_rel;
-	u8				is_soft;
-	u8				is_hard;
-};
-
 /**
  * struct hrtimer_sleeper - simple sleeper structure
  * @timer:	embedded timer structure
diff --git a/include/linux/hrtimer_types.h b/include/linux/hrtimer_types.h
new file mode 100644
index 000000000000..f4ef391b96a7
--- /dev/null
+++ b/include/linux/hrtimer_types.h
@@ -0,0 +1,50 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_HRTIMER_TYPES_H
+#define _LINUX_HRTIMER_TYPES_H
+
+#include <linux/types.h>
+#include <linux/timerqueue.h>
+
+struct hrtimer_clock_base;
+
+/*
+ * Return values for the callback function
+ */
+enum hrtimer_restart {
+	HRTIMER_NORESTART,	/* Timer is not restarted */
+	HRTIMER_RESTART,	/* Timer must be restarted */
+};
+
+/**
+ * struct hrtimer - the basic hrtimer structure
+ * @node:	timerqueue node, which also manages node.expires,
+ *		the absolute expiry time in the hrtimers internal
+ *		representation. The time is related to the clock on
+ *		which the timer is based. Is setup by adding
+ *		slack to the _softexpires value. For non range timers
+ *		identical to _softexpires.
+ * @_softexpires: the absolute earliest expiry time of the hrtimer.
+ *		The time which was given as expiry time when the timer
+ *		was armed.
+ * @function:	timer expiry callback function
+ * @base:	pointer to the timer base (per cpu and per clock)
+ * @state:	state information (See bit values above)
+ * @is_rel:	Set if the timer was armed relative
+ * @is_soft:	Set if hrtimer will be expired in soft interrupt context.
+ * @is_hard:	Set if hrtimer will be expired in hard interrupt context
+ *		even on RT.
+ *
+ * The hrtimer structure must be initialized by hrtimer_init()
+ */
+struct hrtimer {
+	struct timerqueue_node		node;
+	ktime_t				_softexpires;
+	enum hrtimer_restart		(*function)(struct hrtimer *);
+	struct hrtimer_clock_base	*base;
+	u8				state;
+	u8				is_rel;
+	u8				is_soft;
+	u8				is_hard;
+};
+
+#endif /* _LINUX_HRTIMER_TYPES_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 7501a3451a20..3762809652da 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -17,7 +17,7 @@
 #include <linux/kmsan_types.h>
 #include <linux/mutex.h>
 #include <linux/plist.h>
-#include <linux/hrtimer.h>
+#include <linux/hrtimer_types.h>
 #include <linux/irqflags.h>
 #include <linux/seccomp.h>
 #include <linux/nodemask_types.h>
-- 
cgit v1.2.3


From d84f317915172c6511fd6c14ea3f70c9d67fdf67 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 11 Dec 2023 12:35:44 -0500
Subject: locking/mutex: split out mutex_types.h

Trimming down sched.h dependencies: we don't want to include more than
the base types.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Will Deacon <will@kernel.org>
Cc: Waiman Long <longman@redhat.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 include/linux/mutex.h       | 52 +--------------------------------
 include/linux/mutex_types.h | 71 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/sched.h       |  2 +-
 3 files changed, 73 insertions(+), 52 deletions(-)
 create mode 100644 include/linux/mutex_types.h

(limited to 'include')

diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index a33aa9eb9fc3..0dfba5df6524 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -20,6 +20,7 @@
 #include <linux/osq_lock.h>
 #include <linux/debug_locks.h>
 #include <linux/cleanup.h>
+#include <linux/mutex_types.h>
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 # define __DEP_MAP_MUTEX_INITIALIZER(lockname)			\
@@ -33,49 +34,6 @@
 
 #ifndef CONFIG_PREEMPT_RT
 
-/*
- * Simple, straightforward mutexes with strict semantics:
- *
- * - only one task can hold the mutex at a time
- * - only the owner can unlock the mutex
- * - multiple unlocks are not permitted
- * - recursive locking is not permitted
- * - a mutex object must be initialized via the API
- * - a mutex object must not be initialized via memset or copying
- * - task may not exit with mutex held
- * - memory areas where held locks reside must not be freed
- * - held mutexes must not be reinitialized
- * - mutexes may not be used in hardware or software interrupt
- *   contexts such as tasklets and timers
- *
- * These semantics are fully enforced when DEBUG_MUTEXES is
- * enabled. Furthermore, besides enforcing the above rules, the mutex
- * debugging code also implements a number of additional features
- * that make lock debugging easier and faster:
- *
- * - uses symbolic names of mutexes, whenever they are printed in debug output
- * - point-of-acquire tracking, symbolic lookup of function names
- * - list of all locks held in the system, printout of them
- * - owner tracking
- * - detects self-recursing locks and prints out all relevant info
- * - detects multi-task circular deadlocks and prints out all affected
- *   locks and tasks (and only those tasks)
- */
-struct mutex {
-	atomic_long_t		owner;
-	raw_spinlock_t		wait_lock;
-#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
-	struct optimistic_spin_queue osq; /* Spinner MCS lock */
-#endif
-	struct list_head	wait_list;
-#ifdef CONFIG_DEBUG_MUTEXES
-	void			*magic;
-#endif
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map	dep_map;
-#endif
-};
-
 #ifdef CONFIG_DEBUG_MUTEXES
 
 #define __DEBUG_MUTEX_INITIALIZER(lockname)				\
@@ -131,14 +89,6 @@ extern bool mutex_is_locked(struct mutex *lock);
 /*
  * Preempt-RT variant based on rtmutexes.
  */
-#include <linux/rtmutex.h>
-
-struct mutex {
-	struct rt_mutex_base	rtmutex;
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map	dep_map;
-#endif
-};
 
 #define __MUTEX_INITIALIZER(mutexname)					\
 {									\
diff --git a/include/linux/mutex_types.h b/include/linux/mutex_types.h
new file mode 100644
index 000000000000..fdf7f515fde8
--- /dev/null
+++ b/include/linux/mutex_types.h
@@ -0,0 +1,71 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_MUTEX_TYPES_H
+#define __LINUX_MUTEX_TYPES_H
+
+#include <linux/atomic.h>
+#include <linux/lockdep_types.h>
+#include <linux/osq_lock.h>
+#include <linux/spinlock_types.h>
+#include <linux/types.h>
+
+#ifndef CONFIG_PREEMPT_RT
+
+/*
+ * Simple, straightforward mutexes with strict semantics:
+ *
+ * - only one task can hold the mutex at a time
+ * - only the owner can unlock the mutex
+ * - multiple unlocks are not permitted
+ * - recursive locking is not permitted
+ * - a mutex object must be initialized via the API
+ * - a mutex object must not be initialized via memset or copying
+ * - task may not exit with mutex held
+ * - memory areas where held locks reside must not be freed
+ * - held mutexes must not be reinitialized
+ * - mutexes may not be used in hardware or software interrupt
+ *   contexts such as tasklets and timers
+ *
+ * These semantics are fully enforced when DEBUG_MUTEXES is
+ * enabled. Furthermore, besides enforcing the above rules, the mutex
+ * debugging code also implements a number of additional features
+ * that make lock debugging easier and faster:
+ *
+ * - uses symbolic names of mutexes, whenever they are printed in debug output
+ * - point-of-acquire tracking, symbolic lookup of function names
+ * - list of all locks held in the system, printout of them
+ * - owner tracking
+ * - detects self-recursing locks and prints out all relevant info
+ * - detects multi-task circular deadlocks and prints out all affected
+ *   locks and tasks (and only those tasks)
+ */
+struct mutex {
+	atomic_long_t		owner;
+	raw_spinlock_t		wait_lock;
+#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
+	struct optimistic_spin_queue osq; /* Spinner MCS lock */
+#endif
+	struct list_head	wait_list;
+#ifdef CONFIG_DEBUG_MUTEXES
+	void			*magic;
+#endif
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map	dep_map;
+#endif
+};
+
+#else /* !CONFIG_PREEMPT_RT */
+/*
+ * Preempt-RT variant based on rtmutexes.
+ */
+#include <linux/rtmutex.h>
+
+struct mutex {
+	struct rt_mutex_base	rtmutex;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map	dep_map;
+#endif
+};
+
+#endif /* CONFIG_PREEMPT_RT */
+
+#endif /* __LINUX_MUTEX_TYPES_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 3762809652da..e8892789969b 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -15,7 +15,7 @@
 #include <linux/sem.h>
 #include <linux/shm.h>
 #include <linux/kmsan_types.h>
-#include <linux/mutex.h>
+#include <linux/mutex_types.h>
 #include <linux/plist.h>
 #include <linux/hrtimer_types.h>
 #include <linux/irqflags.h>
-- 
cgit v1.2.3


From 53d31ba842d9cc391032d051a210c3c9941f1529 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 11 Dec 2023 12:43:30 -0500
Subject: posix-cpu-timers: Split out posix-timers_types.h

Trimming down sched.h dependencies: we don't want to include more than
the base types.

Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 include/linux/posix-timers.h       | 69 ++------------------------------
 include/linux/posix-timers_types.h | 80 ++++++++++++++++++++++++++++++++++++++
 include/linux/sched.h              |  2 +-
 3 files changed, 84 insertions(+), 67 deletions(-)
 create mode 100644 include/linux/posix-timers_types.h

(limited to 'include')

diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index d607f51404fc..dc7b738de299 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -2,40 +2,16 @@
 #ifndef _linux_POSIX_TIMERS_H
 #define _linux_POSIX_TIMERS_H
 
-#include <linux/spinlock.h>
+#include <linux/alarmtimer.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
-#include <linux/alarmtimer.h>
+#include <linux/posix-timers_types.h>
+#include <linux/spinlock.h>
 #include <linux/timerqueue.h>
 
 struct kernel_siginfo;
 struct task_struct;
 
-/*
- * Bit fields within a clockid:
- *
- * The most significant 29 bits hold either a pid or a file descriptor.
- *
- * Bit 2 indicates whether a cpu clock refers to a thread or a process.
- *
- * Bits 1 and 0 give the type: PROF=0, VIRT=1, SCHED=2, or FD=3.
- *
- * A clockid is invalid if bits 2, 1, and 0 are all set.
- */
-#define CPUCLOCK_PID(clock)		((pid_t) ~((clock) >> 3))
-#define CPUCLOCK_PERTHREAD(clock) \
-	(((clock) & (clockid_t) CPUCLOCK_PERTHREAD_MASK) != 0)
-
-#define CPUCLOCK_PERTHREAD_MASK	4
-#define CPUCLOCK_WHICH(clock)	((clock) & (clockid_t) CPUCLOCK_CLOCK_MASK)
-#define CPUCLOCK_CLOCK_MASK	3
-#define CPUCLOCK_PROF		0
-#define CPUCLOCK_VIRT		1
-#define CPUCLOCK_SCHED		2
-#define CPUCLOCK_MAX		3
-#define CLOCKFD			CPUCLOCK_MAX
-#define CLOCKFD_MASK		(CPUCLOCK_PERTHREAD_MASK|CPUCLOCK_CLOCK_MASK)
-
 static inline clockid_t make_process_cpuclock(const unsigned int pid,
 		const clockid_t clock)
 {
@@ -109,44 +85,6 @@ static inline void cpu_timer_setexpires(struct cpu_timer *ctmr, u64 exp)
 	ctmr->node.expires = exp;
 }
 
-/**
- * posix_cputimer_base - Container per posix CPU clock
- * @nextevt:		Earliest-expiration cache
- * @tqhead:		timerqueue head for cpu_timers
- */
-struct posix_cputimer_base {
-	u64			nextevt;
-	struct timerqueue_head	tqhead;
-};
-
-/**
- * posix_cputimers - Container for posix CPU timer related data
- * @bases:		Base container for posix CPU clocks
- * @timers_active:	Timers are queued.
- * @expiry_active:	Timer expiry is active. Used for
- *			process wide timers to avoid multiple
- *			task trying to handle expiry concurrently
- *
- * Used in task_struct and signal_struct
- */
-struct posix_cputimers {
-	struct posix_cputimer_base	bases[CPUCLOCK_MAX];
-	unsigned int			timers_active;
-	unsigned int			expiry_active;
-};
-
-/**
- * posix_cputimers_work - Container for task work based posix CPU timer expiry
- * @work:	The task work to be scheduled
- * @mutex:	Mutex held around expiry in context of this task work
- * @scheduled:  @work has been scheduled already, no further processing
- */
-struct posix_cputimers_work {
-	struct callback_head	work;
-	struct mutex		mutex;
-	unsigned int		scheduled;
-};
-
 static inline void posix_cputimers_init(struct posix_cputimers *pct)
 {
 	memset(pct, 0, sizeof(*pct));
@@ -179,7 +117,6 @@ static inline void posix_cputimers_rt_watchdog(struct posix_cputimers *pct,
 		.bases = INIT_CPU_TIMERBASES(s.posix_cputimers.bases),	\
 	},
 #else
-struct posix_cputimers { };
 struct cpu_timer { };
 #define INIT_CPU_TIMERS(s)
 static inline void posix_cputimers_init(struct posix_cputimers *pct) { }
diff --git a/include/linux/posix-timers_types.h b/include/linux/posix-timers_types.h
new file mode 100644
index 000000000000..4783fa17bfeb
--- /dev/null
+++ b/include/linux/posix-timers_types.h
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _linux_POSIX_TIMERS_TYPES_H
+#define _linux_POSIX_TIMERS_TYPES_H
+
+#include <linux/mutex_types.h>
+#include <linux/timerqueue.h>
+#include <linux/types.h>
+
+/*
+ * Bit fields within a clockid:
+ *
+ * The most significant 29 bits hold either a pid or a file descriptor.
+ *
+ * Bit 2 indicates whether a cpu clock refers to a thread or a process.
+ *
+ * Bits 1 and 0 give the type: PROF=0, VIRT=1, SCHED=2, or FD=3.
+ *
+ * A clockid is invalid if bits 2, 1, and 0 are all set.
+ */
+#define CPUCLOCK_PID(clock)		((pid_t) ~((clock) >> 3))
+#define CPUCLOCK_PERTHREAD(clock) \
+	(((clock) & (clockid_t) CPUCLOCK_PERTHREAD_MASK) != 0)
+
+#define CPUCLOCK_PERTHREAD_MASK	4
+#define CPUCLOCK_WHICH(clock)	((clock) & (clockid_t) CPUCLOCK_CLOCK_MASK)
+#define CPUCLOCK_CLOCK_MASK	3
+#define CPUCLOCK_PROF		0
+#define CPUCLOCK_VIRT		1
+#define CPUCLOCK_SCHED		2
+#define CPUCLOCK_MAX		3
+#define CLOCKFD			CPUCLOCK_MAX
+#define CLOCKFD_MASK		(CPUCLOCK_PERTHREAD_MASK|CPUCLOCK_CLOCK_MASK)
+
+#ifdef CONFIG_POSIX_TIMERS
+
+/**
+ * posix_cputimer_base - Container per posix CPU clock
+ * @nextevt:		Earliest-expiration cache
+ * @tqhead:		timerqueue head for cpu_timers
+ */
+struct posix_cputimer_base {
+	u64			nextevt;
+	struct timerqueue_head	tqhead;
+};
+
+/**
+ * posix_cputimers - Container for posix CPU timer related data
+ * @bases:		Base container for posix CPU clocks
+ * @timers_active:	Timers are queued.
+ * @expiry_active:	Timer expiry is active. Used for
+ *			process wide timers to avoid multiple
+ *			task trying to handle expiry concurrently
+ *
+ * Used in task_struct and signal_struct
+ */
+struct posix_cputimers {
+	struct posix_cputimer_base	bases[CPUCLOCK_MAX];
+	unsigned int			timers_active;
+	unsigned int			expiry_active;
+};
+
+/**
+ * posix_cputimers_work - Container for task work based posix CPU timer expiry
+ * @work:	The task work to be scheduled
+ * @mutex:	Mutex held around expiry in context of this task work
+ * @scheduled:  @work has been scheduled already, no further processing
+ */
+struct posix_cputimers_work {
+	struct callback_head	work;
+	struct mutex		mutex;
+	unsigned int		scheduled;
+};
+
+#else /* CONFIG_POSIX_TIMERS */
+
+struct posix_cputimers { };
+
+#endif /* CONFIG_POSIX_TIMERS */
+
+#endif /* _linux_POSIX_TIMERS_TYPES_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index e8892789969b..6d803d0904d9 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -31,7 +31,7 @@
 #include <linux/syscall_user_dispatch.h>
 #include <linux/mm_types_task.h>
 #include <linux/task_io_accounting.h>
-#include <linux/posix-timers.h>
+#include <linux/posix-timers_types.h>
 #include <linux/rseq.h>
 #include <linux/seqlock.h>
 #include <linux/kcsan.h>
-- 
cgit v1.2.3


From f038cc1379c0ff462d83895cae8beb75a0f6bf02 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 11 Dec 2023 13:01:06 -0500
Subject: locking/seqlock: Split out seqlock_types.h

Trimming down sched.h dependencies: we don't want to include more than
the base types.

Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Will Deacon <will@kernel.org>
Cc: Waiman Long <longman@redhat.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 include/linux/sched.h         |  2 +-
 include/linux/seqlock.h       | 79 +-----------------------------------
 include/linux/seqlock_types.h | 93 +++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 96 insertions(+), 78 deletions(-)
 create mode 100644 include/linux/seqlock_types.h

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 6d803d0904d9..436f7ce1450a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -33,7 +33,7 @@
 #include <linux/task_io_accounting.h>
 #include <linux/posix-timers_types.h>
 #include <linux/rseq.h>
-#include <linux/seqlock.h>
+#include <linux/seqlock_types.h>
 #include <linux/kcsan.h>
 #include <linux/rv.h>
 #include <linux/livepatch_sched.h>
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index e92f9d5577ba..d90d8ee29d81 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -18,6 +18,7 @@
 #include <linux/lockdep.h>
 #include <linux/mutex.h>
 #include <linux/preempt.h>
+#include <linux/seqlock_types.h>
 #include <linux/spinlock.h>
 
 #include <asm/processor.h>
@@ -37,37 +38,6 @@
  */
 #define KCSAN_SEQLOCK_REGION_MAX 1000
 
-/*
- * Sequence counters (seqcount_t)
- *
- * This is the raw counting mechanism, without any writer protection.
- *
- * Write side critical sections must be serialized and non-preemptible.
- *
- * If readers can be invoked from hardirq or softirq contexts,
- * interrupts or bottom halves must also be respectively disabled before
- * entering the write section.
- *
- * This mechanism can't be used if the protected data contains pointers,
- * as the writer can invalidate a pointer that a reader is following.
- *
- * If the write serialization mechanism is one of the common kernel
- * locking primitives, use a sequence counter with associated lock
- * (seqcount_LOCKNAME_t) instead.
- *
- * If it's desired to automatically handle the sequence counter writer
- * serialization and non-preemptibility requirements, use a sequential
- * lock (seqlock_t) instead.
- *
- * See Documentation/locking/seqlock.rst
- */
-typedef struct seqcount {
-	unsigned sequence;
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map dep_map;
-#endif
-} seqcount_t;
-
 static inline void __seqcount_init(seqcount_t *s, const char *name,
 					  struct lock_class_key *key)
 {
@@ -131,28 +101,6 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
  * See Documentation/locking/seqlock.rst
  */
 
-/*
- * For PREEMPT_RT, seqcount_LOCKNAME_t write side critical sections cannot
- * disable preemption. It can lead to higher latencies, and the write side
- * sections will not be able to acquire locks which become sleeping locks
- * (e.g. spinlock_t).
- *
- * To remain preemptible while avoiding a possible livelock caused by the
- * reader preempting the writer, use a different technique: let the reader
- * detect if a seqcount_LOCKNAME_t writer is in progress. If that is the
- * case, acquire then release the associated LOCKNAME writer serialization
- * lock. This will allow any possibly-preempted writer to make progress
- * until the end of its writer serialization lock critical section.
- *
- * This lock-unlock technique must be implemented for all of PREEMPT_RT
- * sleeping locks.  See Documentation/locking/locktypes.rst
- */
-#if defined(CONFIG_LOCKDEP) || defined(CONFIG_PREEMPT_RT)
-#define __SEQ_LOCK(expr)	expr
-#else
-#define __SEQ_LOCK(expr)
-#endif
-
 /*
  * typedef seqcount_LOCKNAME_t - sequence counter with LOCKNAME associated
  * @seqcount:	The real sequence counter
@@ -194,11 +142,6 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
  * @lockbase:		prefix for associated lock/unlock
  */
 #define SEQCOUNT_LOCKNAME(lockname, locktype, preemptible, lockbase)	\
-typedef struct seqcount_##lockname {					\
-	seqcount_t		seqcount;				\
-	__SEQ_LOCK(locktype	*lock);					\
-} seqcount_##lockname##_t;						\
-									\
 static __always_inline seqcount_t *					\
 __seqprop_##lockname##_ptr(seqcount_##lockname##_t *s)			\
 {									\
@@ -284,6 +227,7 @@ SEQCOUNT_LOCKNAME(raw_spinlock, raw_spinlock_t,  false,    raw_spin)
 SEQCOUNT_LOCKNAME(spinlock,     spinlock_t,      __SEQ_RT, spin)
 SEQCOUNT_LOCKNAME(rwlock,       rwlock_t,        __SEQ_RT, read)
 SEQCOUNT_LOCKNAME(mutex,        struct mutex,    true,     mutex)
+#undef SEQCOUNT_LOCKNAME
 
 /*
  * SEQCNT_LOCKNAME_ZERO - static initializer for seqcount_LOCKNAME_t
@@ -794,25 +738,6 @@ static inline void raw_write_seqcount_latch(seqcount_latch_t *s)
 	smp_wmb();      /* increment "sequence" before following stores */
 }
 
-/*
- * Sequential locks (seqlock_t)
- *
- * Sequence counters with an embedded spinlock for writer serialization
- * and non-preemptibility.
- *
- * For more info, see:
- *    - Comments on top of seqcount_t
- *    - Documentation/locking/seqlock.rst
- */
-typedef struct {
-	/*
-	 * Make sure that readers don't starve writers on PREEMPT_RT: use
-	 * seqcount_spinlock_t instead of seqcount_t. Check __SEQ_LOCK().
-	 */
-	seqcount_spinlock_t seqcount;
-	spinlock_t lock;
-} seqlock_t;
-
 #define __SEQLOCK_UNLOCKED(lockname)					\
 	{								\
 		.seqcount = SEQCNT_SPINLOCK_ZERO(lockname, &(lockname).lock), \
diff --git a/include/linux/seqlock_types.h b/include/linux/seqlock_types.h
new file mode 100644
index 000000000000..dfdf43e3fa3d
--- /dev/null
+++ b/include/linux/seqlock_types.h
@@ -0,0 +1,93 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_SEQLOCK_TYPES_H
+#define __LINUX_SEQLOCK_TYPES_H
+
+#include <linux/lockdep_types.h>
+#include <linux/mutex_types.h>
+#include <linux/spinlock_types.h>
+
+/*
+ * Sequence counters (seqcount_t)
+ *
+ * This is the raw counting mechanism, without any writer protection.
+ *
+ * Write side critical sections must be serialized and non-preemptible.
+ *
+ * If readers can be invoked from hardirq or softirq contexts,
+ * interrupts or bottom halves must also be respectively disabled before
+ * entering the write section.
+ *
+ * This mechanism can't be used if the protected data contains pointers,
+ * as the writer can invalidate a pointer that a reader is following.
+ *
+ * If the write serialization mechanism is one of the common kernel
+ * locking primitives, use a sequence counter with associated lock
+ * (seqcount_LOCKNAME_t) instead.
+ *
+ * If it's desired to automatically handle the sequence counter writer
+ * serialization and non-preemptibility requirements, use a sequential
+ * lock (seqlock_t) instead.
+ *
+ * See Documentation/locking/seqlock.rst
+ */
+typedef struct seqcount {
+	unsigned sequence;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map dep_map;
+#endif
+} seqcount_t;
+
+/*
+ * For PREEMPT_RT, seqcount_LOCKNAME_t write side critical sections cannot
+ * disable preemption. It can lead to higher latencies, and the write side
+ * sections will not be able to acquire locks which become sleeping locks
+ * (e.g. spinlock_t).
+ *
+ * To remain preemptible while avoiding a possible livelock caused by the
+ * reader preempting the writer, use a different technique: let the reader
+ * detect if a seqcount_LOCKNAME_t writer is in progress. If that is the
+ * case, acquire then release the associated LOCKNAME writer serialization
+ * lock. This will allow any possibly-preempted writer to make progress
+ * until the end of its writer serialization lock critical section.
+ *
+ * This lock-unlock technique must be implemented for all of PREEMPT_RT
+ * sleeping locks.  See Documentation/locking/locktypes.rst
+ */
+#if defined(CONFIG_LOCKDEP) || defined(CONFIG_PREEMPT_RT)
+#define __SEQ_LOCK(expr)	expr
+#else
+#define __SEQ_LOCK(expr)
+#endif
+
+#define SEQCOUNT_LOCKNAME(lockname, locktype, preemptible, lockbase)	\
+typedef struct seqcount_##lockname {					\
+	seqcount_t		seqcount;				\
+	__SEQ_LOCK(locktype	*lock);					\
+} seqcount_##lockname##_t;
+
+SEQCOUNT_LOCKNAME(raw_spinlock, raw_spinlock_t,  false,    raw_spin)
+SEQCOUNT_LOCKNAME(spinlock,     spinlock_t,      __SEQ_RT, spin)
+SEQCOUNT_LOCKNAME(rwlock,       rwlock_t,        __SEQ_RT, read)
+SEQCOUNT_LOCKNAME(mutex,        struct mutex,    true,     mutex)
+#undef SEQCOUNT_LOCKNAME
+
+/*
+ * Sequential locks (seqlock_t)
+ *
+ * Sequence counters with an embedded spinlock for writer serialization
+ * and non-preemptibility.
+ *
+ * For more info, see:
+ *    - Comments on top of seqcount_t
+ *    - Documentation/locking/seqlock.rst
+ */
+typedef struct {
+	/*
+	 * Make sure that readers don't starve writers on PREEMPT_RT: use
+	 * seqcount_spinlock_t instead of seqcount_t. Check __SEQ_LOCK().
+	 */
+	seqcount_spinlock_t seqcount;
+	spinlock_t lock;
+} seqlock_t;
+
+#endif /* __LINUX_SEQLOCK_TYPES_H */
-- 
cgit v1.2.3


From 6d5e9d63683042a8d344cd5d6f9cf23613864a29 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 11 Dec 2023 13:03:22 -0500
Subject: pid: Split out pid_types.h

Trimming down sched.h dependencies: we dont't want to include more than
the base types.

Cc: Kees Cook <keescook@chromium.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Will Drewry <wad@chromium.org>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 drivers/target/target_core_xcopy.c |  1 +
 include/linux/pid.h                | 15 ++-------------
 include/linux/pid_types.h          | 16 ++++++++++++++++
 include/linux/sched.h              |  2 +-
 include/linux/seccomp.h            |  2 ++
 5 files changed, 22 insertions(+), 14 deletions(-)
 create mode 100644 include/linux/pid_types.h

(limited to 'include')

diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c
index 91ed015b588c..4128631c9dfd 100644
--- a/drivers/target/target_core_xcopy.c
+++ b/drivers/target/target_core_xcopy.c
@@ -15,6 +15,7 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/list.h>
+#include <linux/rculist.h>
 #include <linux/configfs.h>
 #include <linux/ratelimit.h>
 #include <scsi/scsi_proto.h>
diff --git a/include/linux/pid.h b/include/linux/pid.h
index 653a527574c4..f254c3a45b9b 100644
--- a/include/linux/pid.h
+++ b/include/linux/pid.h
@@ -2,18 +2,10 @@
 #ifndef _LINUX_PID_H
 #define _LINUX_PID_H
 
+#include <linux/pid_types.h>
 #include <linux/rculist.h>
-#include <linux/wait.h>
 #include <linux/refcount.h>
-
-enum pid_type
-{
-	PIDTYPE_PID,
-	PIDTYPE_TGID,
-	PIDTYPE_PGID,
-	PIDTYPE_SID,
-	PIDTYPE_MAX,
-};
+#include <linux/wait.h>
 
 /*
  * What is struct pid?
@@ -110,9 +102,6 @@ extern void exchange_tids(struct task_struct *task, struct task_struct *old);
 extern void transfer_pid(struct task_struct *old, struct task_struct *new,
 			 enum pid_type);
 
-struct pid_namespace;
-extern struct pid_namespace init_pid_ns;
-
 extern int pid_max;
 extern int pid_max_min, pid_max_max;
 
diff --git a/include/linux/pid_types.h b/include/linux/pid_types.h
new file mode 100644
index 000000000000..c2aee1d91dcf
--- /dev/null
+++ b/include/linux/pid_types.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_PID_TYPES_H
+#define _LINUX_PID_TYPES_H
+
+enum pid_type {
+	PIDTYPE_PID,
+	PIDTYPE_TGID,
+	PIDTYPE_PGID,
+	PIDTYPE_SID,
+	PIDTYPE_MAX,
+};
+
+struct pid_namespace;
+extern struct pid_namespace init_pid_ns;
+
+#endif /* _LINUX_PID_TYPES_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 436f7ce1450a..37cc9d257073 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -11,7 +11,7 @@
 
 #include <asm/current.h>
 
-#include <linux/pid.h>
+#include <linux/pid_types.h>
 #include <linux/sem.h>
 #include <linux/shm.h>
 #include <linux/kmsan_types.h>
diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index 175079552f68..1ec0d8dc4b69 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -126,6 +126,8 @@ static inline long seccomp_get_metadata(struct task_struct *task,
 
 #ifdef CONFIG_SECCOMP_CACHE_DEBUG
 struct seq_file;
+struct pid_namespace;
+struct pid;
 
 int proc_pid_seccomp_cache(struct seq_file *m, struct pid_namespace *ns,
 			   struct pid *pid, struct task_struct *task);
-- 
cgit v1.2.3


From f551103cb964e9e6f5c03b3b8723424723731e76 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Fri, 15 Dec 2023 17:49:24 -0500
Subject: sched.h: move pid helpers to pid.h

This is needed for killing the sched.h dependency on rcupdate.h, and
pid.h is a better place for this code anyways.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 arch/x86/um/sysrq_64.c          |   1 +
 drivers/gpu/drm/lima/lima_ctx.c |   1 +
 drivers/irqchip/irq-gic-v4.c    |   1 +
 include/linux/pid.h             | 125 ++++++++++++++++++++++++++++++++++++++++
 include/linux/sched.h           | 122 ---------------------------------------
 include/linux/sched/signal.h    |   1 +
 ipc/util.h                      |   1 +
 kernel/async.c                  |   5 +-
 kernel/locking/spinlock_debug.c |   1 +
 9 files changed, 134 insertions(+), 124 deletions(-)

(limited to 'include')

diff --git a/arch/x86/um/sysrq_64.c b/arch/x86/um/sysrq_64.c
index ef1eb4f4f612..0bf6de40abff 100644
--- a/arch/x86/um/sysrq_64.c
+++ b/arch/x86/um/sysrq_64.c
@@ -6,6 +6,7 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/pid.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/utsname.h>
diff --git a/drivers/gpu/drm/lima/lima_ctx.c b/drivers/gpu/drm/lima/lima_ctx.c
index 891d5cd5019a..8389f2d7d021 100644
--- a/drivers/gpu/drm/lima/lima_ctx.c
+++ b/drivers/gpu/drm/lima/lima_ctx.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0 OR MIT
 /* Copyright 2018-2019 Qiang Yu <yuq825@gmail.com> */
 
+#include <linux/pid.h>
 #include <linux/slab.h>
 
 #include "lima_device.h"
diff --git a/drivers/irqchip/irq-gic-v4.c b/drivers/irqchip/irq-gic-v4.c
index 94d56a03b175..ca32ac19d284 100644
--- a/drivers/irqchip/irq-gic-v4.c
+++ b/drivers/irqchip/irq-gic-v4.c
@@ -8,6 +8,7 @@
 #include <linux/irq.h>
 #include <linux/irqdomain.h>
 #include <linux/msi.h>
+#include <linux/pid.h>
 #include <linux/sched.h>
 
 #include <linux/irqchip/arm-gic-v4.h>
diff --git a/include/linux/pid.h b/include/linux/pid.h
index f254c3a45b9b..395cacce1179 100644
--- a/include/linux/pid.h
+++ b/include/linux/pid.h
@@ -4,7 +4,9 @@
 
 #include <linux/pid_types.h>
 #include <linux/rculist.h>
+#include <linux/rcupdate.h>
 #include <linux/refcount.h>
+#include <linux/sched.h>
 #include <linux/wait.h>
 
 /*
@@ -204,4 +206,127 @@ pid_t pid_vnr(struct pid *pid);
 		}							\
 		task = tg___;						\
 	} while_each_pid_task(pid, type, task)
+
+static inline struct pid *task_pid(struct task_struct *task)
+{
+	return task->thread_pid;
+}
+
+/*
+ * the helpers to get the task's different pids as they are seen
+ * from various namespaces
+ *
+ * task_xid_nr()     : global id, i.e. the id seen from the init namespace;
+ * task_xid_vnr()    : virtual id, i.e. the id seen from the pid namespace of
+ *                     current.
+ * task_xid_nr_ns()  : id seen from the ns specified;
+ *
+ * see also pid_nr() etc in include/linux/pid.h
+ */
+pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, struct pid_namespace *ns);
+
+static inline pid_t task_pid_nr(struct task_struct *tsk)
+{
+	return tsk->pid;
+}
+
+static inline pid_t task_pid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
+{
+	return __task_pid_nr_ns(tsk, PIDTYPE_PID, ns);
+}
+
+static inline pid_t task_pid_vnr(struct task_struct *tsk)
+{
+	return __task_pid_nr_ns(tsk, PIDTYPE_PID, NULL);
+}
+
+
+static inline pid_t task_tgid_nr(struct task_struct *tsk)
+{
+	return tsk->tgid;
+}
+
+/**
+ * pid_alive - check that a task structure is not stale
+ * @p: Task structure to be checked.
+ *
+ * Test if a process is not yet dead (at most zombie state)
+ * If pid_alive fails, then pointers within the task structure
+ * can be stale and must not be dereferenced.
+ *
+ * Return: 1 if the process is alive. 0 otherwise.
+ */
+static inline int pid_alive(const struct task_struct *p)
+{
+	return p->thread_pid != NULL;
+}
+
+static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
+{
+	return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns);
+}
+
+static inline pid_t task_pgrp_vnr(struct task_struct *tsk)
+{
+	return __task_pid_nr_ns(tsk, PIDTYPE_PGID, NULL);
+}
+
+
+static inline pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
+{
+	return __task_pid_nr_ns(tsk, PIDTYPE_SID, ns);
+}
+
+static inline pid_t task_session_vnr(struct task_struct *tsk)
+{
+	return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL);
+}
+
+static inline pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
+{
+	return __task_pid_nr_ns(tsk, PIDTYPE_TGID, ns);
+}
+
+static inline pid_t task_tgid_vnr(struct task_struct *tsk)
+{
+	return __task_pid_nr_ns(tsk, PIDTYPE_TGID, NULL);
+}
+
+static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns)
+{
+	pid_t pid = 0;
+
+	rcu_read_lock();
+	if (pid_alive(tsk))
+		pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns);
+	rcu_read_unlock();
+
+	return pid;
+}
+
+static inline pid_t task_ppid_nr(const struct task_struct *tsk)
+{
+	return task_ppid_nr_ns(tsk, &init_pid_ns);
+}
+
+/* Obsolete, do not use: */
+static inline pid_t task_pgrp_nr(struct task_struct *tsk)
+{
+	return task_pgrp_nr_ns(tsk, &init_pid_ns);
+}
+
+/**
+ * is_global_init - check if a task structure is init. Since init
+ * is free to have sub-threads we need to check tgid.
+ * @tsk: Task structure to be checked.
+ *
+ * Check if a task structure is the first user space task the kernel created.
+ *
+ * Return: 1 if the task structure is init. 0 otherwise.
+ */
+static inline int is_global_init(struct task_struct *tsk)
+{
+	return task_tgid_nr(tsk) == 1;
+}
+
 #endif /* _LINUX_PID_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 37cc9d257073..9e2708c2cfa6 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1561,114 +1561,6 @@ struct task_struct {
 	 */
 };
 
-static inline struct pid *task_pid(struct task_struct *task)
-{
-	return task->thread_pid;
-}
-
-/*
- * the helpers to get the task's different pids as they are seen
- * from various namespaces
- *
- * task_xid_nr()     : global id, i.e. the id seen from the init namespace;
- * task_xid_vnr()    : virtual id, i.e. the id seen from the pid namespace of
- *                     current.
- * task_xid_nr_ns()  : id seen from the ns specified;
- *
- * see also pid_nr() etc in include/linux/pid.h
- */
-pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, struct pid_namespace *ns);
-
-static inline pid_t task_pid_nr(struct task_struct *tsk)
-{
-	return tsk->pid;
-}
-
-static inline pid_t task_pid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
-{
-	return __task_pid_nr_ns(tsk, PIDTYPE_PID, ns);
-}
-
-static inline pid_t task_pid_vnr(struct task_struct *tsk)
-{
-	return __task_pid_nr_ns(tsk, PIDTYPE_PID, NULL);
-}
-
-
-static inline pid_t task_tgid_nr(struct task_struct *tsk)
-{
-	return tsk->tgid;
-}
-
-/**
- * pid_alive - check that a task structure is not stale
- * @p: Task structure to be checked.
- *
- * Test if a process is not yet dead (at most zombie state)
- * If pid_alive fails, then pointers within the task structure
- * can be stale and must not be dereferenced.
- *
- * Return: 1 if the process is alive. 0 otherwise.
- */
-static inline int pid_alive(const struct task_struct *p)
-{
-	return p->thread_pid != NULL;
-}
-
-static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
-{
-	return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns);
-}
-
-static inline pid_t task_pgrp_vnr(struct task_struct *tsk)
-{
-	return __task_pid_nr_ns(tsk, PIDTYPE_PGID, NULL);
-}
-
-
-static inline pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
-{
-	return __task_pid_nr_ns(tsk, PIDTYPE_SID, ns);
-}
-
-static inline pid_t task_session_vnr(struct task_struct *tsk)
-{
-	return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL);
-}
-
-static inline pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
-{
-	return __task_pid_nr_ns(tsk, PIDTYPE_TGID, ns);
-}
-
-static inline pid_t task_tgid_vnr(struct task_struct *tsk)
-{
-	return __task_pid_nr_ns(tsk, PIDTYPE_TGID, NULL);
-}
-
-static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns)
-{
-	pid_t pid = 0;
-
-	rcu_read_lock();
-	if (pid_alive(tsk))
-		pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns);
-	rcu_read_unlock();
-
-	return pid;
-}
-
-static inline pid_t task_ppid_nr(const struct task_struct *tsk)
-{
-	return task_ppid_nr_ns(tsk, &init_pid_ns);
-}
-
-/* Obsolete, do not use: */
-static inline pid_t task_pgrp_nr(struct task_struct *tsk)
-{
-	return task_pgrp_nr_ns(tsk, &init_pid_ns);
-}
-
 #define TASK_REPORT_IDLE	(TASK_REPORT + 1)
 #define TASK_REPORT_MAX		(TASK_REPORT_IDLE << 1)
 
@@ -1712,20 +1604,6 @@ static inline char task_state_to_char(struct task_struct *tsk)
 	return task_index_to_char(task_state_index(tsk));
 }
 
-/**
- * is_global_init - check if a task structure is init. Since init
- * is free to have sub-threads we need to check tgid.
- * @tsk: Task structure to be checked.
- *
- * Check if a task structure is the first user space task the kernel created.
- *
- * Return: 1 if the task structure is init. 0 otherwise.
- */
-static inline int is_global_init(struct task_struct *tsk)
-{
-	return task_tgid_nr(tsk) == 1;
-}
-
 extern struct pid *cad_pid;
 
 /*
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 3499c1a8b929..b847d8fa75a9 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -9,6 +9,7 @@
 #include <linux/sched/task.h>
 #include <linux/cred.h>
 #include <linux/refcount.h>
+#include <linux/pid.h>
 #include <linux/posix-timers.h>
 #include <linux/mm_types.h>
 #include <asm/ptrace.h>
diff --git a/ipc/util.h b/ipc/util.h
index 67bdd2aa2c28..a55d6cebe6d3 100644
--- a/ipc/util.h
+++ b/ipc/util.h
@@ -14,6 +14,7 @@
 #include <linux/unistd.h>
 #include <linux/err.h>
 #include <linux/ipc_namespace.h>
+#include <linux/pid.h>
 
 /*
  * The IPC ID contains 2 separate numbers - index and sequence number.
diff --git a/kernel/async.c b/kernel/async.c
index b2c4ba5686ee..79f6a3034b1f 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -46,11 +46,12 @@ asynchronous and synchronous parts of the kernel.
 
 #include <linux/async.h>
 #include <linux/atomic.h>
-#include <linux/ktime.h>
 #include <linux/export.h>
-#include <linux/wait.h>
+#include <linux/ktime.h>
+#include <linux/pid.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include <linux/wait.h>
 #include <linux/workqueue.h>
 
 #include "workqueue_internal.h"
diff --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c
index 14235671a1a7..87b03d2e41db 100644
--- a/kernel/locking/spinlock_debug.c
+++ b/kernel/locking/spinlock_debug.c
@@ -12,6 +12,7 @@
 #include <linux/debug_locks.h>
 #include <linux/delay.h>
 #include <linux/export.h>
+#include <linux/pid.h>
 
 void __raw_spin_lock_init(raw_spinlock_t *lock, const char *name,
 			  struct lock_class_key *key, short inner)
-- 
cgit v1.2.3


From 8b7787a543cde905e53eaf29172c9472fe8a6a75 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 11 Dec 2023 13:12:49 -0500
Subject: plist: Split out plist_types.h

Trimming down sched.h dependencies: we don't want to include more than
the base types.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 include/linux/plist.h       | 12 +-----------
 include/linux/plist_types.h | 17 +++++++++++++++++
 include/linux/sched.h       |  2 +-
 init/init_task.c            |  1 +
 kernel/futex/core.c         |  1 +
 kernel/futex/requeue.c      |  1 +
 kernel/futex/waitwake.c     |  1 +
 mm/swapfile.c               |  1 +
 8 files changed, 24 insertions(+), 12 deletions(-)
 create mode 100644 include/linux/plist_types.h

(limited to 'include')

diff --git a/include/linux/plist.h b/include/linux/plist.h
index 0f352c1d3c80..8c1c8adf7fe9 100644
--- a/include/linux/plist.h
+++ b/include/linux/plist.h
@@ -75,20 +75,10 @@
 
 #include <linux/container_of.h>
 #include <linux/list.h>
-#include <linux/types.h>
+#include <linux/plist_types.h>
 
 #include <asm/bug.h>
 
-struct plist_head {
-	struct list_head node_list;
-};
-
-struct plist_node {
-	int			prio;
-	struct list_head	prio_list;
-	struct list_head	node_list;
-};
-
 /**
  * PLIST_HEAD_INIT - static struct plist_head initializer
  * @head:	struct plist_head variable name
diff --git a/include/linux/plist_types.h b/include/linux/plist_types.h
new file mode 100644
index 000000000000..c37e784330af
--- /dev/null
+++ b/include/linux/plist_types.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _LINUX_PLIST_TYPES_H
+#define _LINUX_PLIST_TYPES_H
+
+#include <linux/types.h>
+
+struct plist_head {
+	struct list_head node_list;
+};
+
+struct plist_node {
+	int			prio;
+	struct list_head	prio_list;
+	struct list_head	node_list;
+};
+
+#endif /* _LINUX_PLIST_TYPES_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9e2708c2cfa6..8c230f24688b 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -16,7 +16,7 @@
 #include <linux/shm.h>
 #include <linux/kmsan_types.h>
 #include <linux/mutex_types.h>
-#include <linux/plist.h>
+#include <linux/plist_types.h>
 #include <linux/hrtimer_types.h>
 #include <linux/irqflags.h>
 #include <linux/seccomp.h>
diff --git a/init/init_task.c b/init/init_task.c
index 5727d42149c3..56220898a256 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -12,6 +12,7 @@
 #include <linux/audit.h>
 #include <linux/numa.h>
 #include <linux/scs.h>
+#include <linux/plist.h>
 
 #include <linux/uaccess.h>
 
diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index dad981a865b8..e0e853412c15 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -34,6 +34,7 @@
 #include <linux/compat.h>
 #include <linux/jhash.h>
 #include <linux/pagemap.h>
+#include <linux/plist.h>
 #include <linux/memblock.h>
 #include <linux/fault-inject.h>
 #include <linux/slab.h>
diff --git a/kernel/futex/requeue.c b/kernel/futex/requeue.c
index eb21f065816b..b47bb764b352 100644
--- a/kernel/futex/requeue.c
+++ b/kernel/futex/requeue.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 
+#include <linux/plist.h>
 #include <linux/sched/signal.h>
 
 #include "futex.h"
diff --git a/kernel/futex/waitwake.c b/kernel/futex/waitwake.c
index 61b112897a84..3a10375d9521 100644
--- a/kernel/futex/waitwake.c
+++ b/kernel/futex/waitwake.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 
+#include <linux/plist.h>
 #include <linux/sched/task.h>
 #include <linux/sched/signal.h>
 #include <linux/freezer.h>
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 4bc70f459164..25019af07181 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -42,6 +42,7 @@
 #include <linux/completion.h>
 #include <linux/suspend.h>
 #include <linux/zswap.h>
+#include <linux/plist.h>
 
 #include <asm/tlbflush.h>
 #include <linux/swapops.h>
-- 
cgit v1.2.3


From 6dfeff09d5ad331905c7066207053d286d58ac83 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Mon, 11 Dec 2023 18:14:41 +0000
Subject: wait: Remove uapi header file from main header file

There's really no overlap between uapi/linux/wait.h and linux/wait.h.
There are two files which rely on the uapi file being implcitly included,
so explicitly include it there and remove it from the main header file.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Reviewed-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/wait.h   | 1 -
 kernel/exit.c          | 4 +++-
 kernel/pid_namespace.c | 1 +
 3 files changed, 4 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/wait.h b/include/linux/wait.h
index 3473b663176f..8aa3372f21a0 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -9,7 +9,6 @@
 #include <linux/spinlock.h>
 
 #include <asm/current.h>
-#include <uapi/linux/wait.h>
 
 typedef struct wait_queue_entry wait_queue_entry_t;
 
diff --git a/kernel/exit.c b/kernel/exit.c
index ee9f43bed49a..2ef33047371b 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -69,8 +69,10 @@
 #include <linux/rethook.h>
 #include <linux/sysfs.h>
 #include <linux/user_events.h>
-
 #include <linux/uaccess.h>
+
+#include <uapi/linux/wait.h>
+
 #include <asm/unistd.h>
 #include <asm/mmu_context.h>
 
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 3028b2218aa4..7ade20e95232 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -23,6 +23,7 @@
 #include <linux/sched/task.h>
 #include <linux/sched/signal.h>
 #include <linux/idr.h>
+#include <uapi/linux/wait.h>
 #include "pid_sysctl.h"
 
 static DEFINE_MUTEX(pid_caches_mutex);
-- 
cgit v1.2.3


From 097691960f7084ca82adb2e866d03a81753f0cb7 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 11 Dec 2023 13:28:46 -0500
Subject: rslib: kill bogus dependency on list.h

list_head is defined in types.h, not list.h - this kills a sched.h
dependency.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 include/linux/rslib.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/rslib.h b/include/linux/rslib.h
index 238bb85243d3..a04dacbdc8ae 100644
--- a/include/linux/rslib.h
+++ b/include/linux/rslib.h
@@ -10,7 +10,6 @@
 #ifndef _RSLIB_H_
 #define _RSLIB_H_
 
-#include <linux/list.h>
 #include <linux/types.h>	/* for gfp_t */
 #include <linux/gfp.h>		/* for GFP_KERNEL */
 
-- 
cgit v1.2.3


From eee51b0ae5c52a77ed65ad59b55002d1397b40d5 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 11 Dec 2023 13:32:55 -0500
Subject: timerqueue: Split out timerqueue_types.h

Trimming down sched.h dependencies: timerqueue_types can include just
rbtree_types.h instead of pulling in rbtree.h.

Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 include/linux/hrtimer_types.h      |  2 +-
 include/linux/posix-timers_types.h |  2 +-
 include/linux/timerqueue.h         | 13 +------------
 include/linux/timerqueue_types.h   | 17 +++++++++++++++++
 4 files changed, 20 insertions(+), 14 deletions(-)
 create mode 100644 include/linux/timerqueue_types.h

(limited to 'include')

diff --git a/include/linux/hrtimer_types.h b/include/linux/hrtimer_types.h
index f4ef391b96a7..ad66a3081735 100644
--- a/include/linux/hrtimer_types.h
+++ b/include/linux/hrtimer_types.h
@@ -3,7 +3,7 @@
 #define _LINUX_HRTIMER_TYPES_H
 
 #include <linux/types.h>
-#include <linux/timerqueue.h>
+#include <linux/timerqueue_types.h>
 
 struct hrtimer_clock_base;
 
diff --git a/include/linux/posix-timers_types.h b/include/linux/posix-timers_types.h
index 4783fa17bfeb..a4712c1008c9 100644
--- a/include/linux/posix-timers_types.h
+++ b/include/linux/posix-timers_types.h
@@ -3,7 +3,7 @@
 #define _linux_POSIX_TIMERS_TYPES_H
 
 #include <linux/mutex_types.h>
-#include <linux/timerqueue.h>
+#include <linux/timerqueue_types.h>
 #include <linux/types.h>
 
 /*
diff --git a/include/linux/timerqueue.h b/include/linux/timerqueue.h
index adc80e29168e..62973f7d4610 100644
--- a/include/linux/timerqueue.h
+++ b/include/linux/timerqueue.h
@@ -3,18 +3,7 @@
 #define _LINUX_TIMERQUEUE_H
 
 #include <linux/rbtree.h>
-#include <linux/ktime.h>
-
-
-struct timerqueue_node {
-	struct rb_node node;
-	ktime_t expires;
-};
-
-struct timerqueue_head {
-	struct rb_root_cached rb_root;
-};
-
+#include <linux/timerqueue_types.h>
 
 extern bool timerqueue_add(struct timerqueue_head *head,
 			   struct timerqueue_node *node);
diff --git a/include/linux/timerqueue_types.h b/include/linux/timerqueue_types.h
new file mode 100644
index 000000000000..dc298d0923e3
--- /dev/null
+++ b/include/linux/timerqueue_types.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_TIMERQUEUE_TYPES_H
+#define _LINUX_TIMERQUEUE_TYPES_H
+
+#include <linux/rbtree_types.h>
+#include <linux/types.h>
+
+struct timerqueue_node {
+	struct rb_node node;
+	ktime_t expires;
+};
+
+struct timerqueue_head {
+	struct rb_root_cached rb_root;
+};
+
+#endif /* _LINUX_TIMERQUEUE_TYPES_H */
-- 
cgit v1.2.3


From 22c336d0d3118824fed08834069568c57c5641a6 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 11 Dec 2023 13:34:45 -0500
Subject: signal: Kill bogus dependency on list.h

list_head is in types.h, not list.h.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 include/linux/signal.h       | 1 +
 include/linux/signal_types.h | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/signal.h b/include/linux/signal.h
index 3b98e7a28538..f19816832f05 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -3,6 +3,7 @@
 #define _LINUX_SIGNAL_H
 
 #include <linux/bug.h>
+#include <linux/list.h>
 #include <linux/signal_types.h>
 #include <linux/string.h>
 
diff --git a/include/linux/signal_types.h b/include/linux/signal_types.h
index a70b2bdbf4d9..caf4f7a59ab9 100644
--- a/include/linux/signal_types.h
+++ b/include/linux/signal_types.h
@@ -6,7 +6,7 @@
  * Basic signal handling related data type definitions:
  */
 
-#include <linux/list.h>
+#include <linux/types.h>
 #include <uapi/linux/signal.h>
 
 typedef struct kernel_siginfo {
-- 
cgit v1.2.3


From dff0fd233a5104337069603d201f8cad74bc0e5a Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 11 Dec 2023 13:53:34 -0500
Subject: timers: Split out timer_types.h

Cutting down on sched.h dependencies: this is going to be used in
workqueue_types.h in the next patch, so we can kill the sched.h
dependency on workqueue.h.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 include/linux/timer.h       | 16 +---------------
 include/linux/timer_types.h | 23 +++++++++++++++++++++++
 2 files changed, 24 insertions(+), 15 deletions(-)
 create mode 100644 include/linux/timer_types.h

(limited to 'include')

diff --git a/include/linux/timer.h b/include/linux/timer.h
index 26a545bb0153..f18a2f1eb79e 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -7,21 +7,7 @@
 #include <linux/stddef.h>
 #include <linux/debugobjects.h>
 #include <linux/stringify.h>
-
-struct timer_list {
-	/*
-	 * All fields that change during normal runtime grouped to the
-	 * same cacheline
-	 */
-	struct hlist_node	entry;
-	unsigned long		expires;
-	void			(*function)(struct timer_list *);
-	u32			flags;
-
-#ifdef CONFIG_LOCKDEP
-	struct lockdep_map	lockdep_map;
-#endif
-};
+#include <linux/timer_types.h>
 
 #ifdef CONFIG_LOCKDEP
 /*
diff --git a/include/linux/timer_types.h b/include/linux/timer_types.h
new file mode 100644
index 000000000000..fae5a388f914
--- /dev/null
+++ b/include/linux/timer_types.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_TIMER_TYPES_H
+#define _LINUX_TIMER_TYPES_H
+
+#include <linux/lockdep_types.h>
+#include <linux/types.h>
+
+struct timer_list {
+	/*
+	 * All fields that change during normal runtime grouped to the
+	 * same cacheline
+	 */
+	struct hlist_node	entry;
+	unsigned long		expires;
+	void			(*function)(struct timer_list *);
+	u32			flags;
+
+#ifdef CONFIG_LOCKDEP
+	struct lockdep_map	lockdep_map;
+#endif
+};
+
+#endif /* _LINUX_TIMER_TYPES_H */
-- 
cgit v1.2.3


From b2fa8443db320c4873feca2588b957439e350890 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 11 Dec 2023 13:55:01 -0500
Subject: workqueue: Split out workqueue_types.h

More sched.h dependency culling - this lets us kill a rhashtable-types.h
dependency on workqueue.h.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 include/linux/dma-fence.h        |  1 +
 include/linux/rhashtable-types.h |  2 +-
 include/linux/timekeeping.h      |  1 +
 include/linux/workqueue.h        | 16 +---------------
 include/linux/workqueue_types.h  | 25 +++++++++++++++++++++++++
 5 files changed, 29 insertions(+), 16 deletions(-)
 create mode 100644 include/linux/workqueue_types.h

(limited to 'include')

diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h
index b3772edca2e6..e06bad467f55 100644
--- a/include/linux/dma-fence.h
+++ b/include/linux/dma-fence.h
@@ -21,6 +21,7 @@
 #include <linux/sched.h>
 #include <linux/printk.h>
 #include <linux/rcupdate.h>
+#include <linux/timekeeping.h>
 
 struct dma_fence;
 struct dma_fence_ops;
diff --git a/include/linux/rhashtable-types.h b/include/linux/rhashtable-types.h
index 57467cbf4c5b..b6f3797277ff 100644
--- a/include/linux/rhashtable-types.h
+++ b/include/linux/rhashtable-types.h
@@ -12,7 +12,7 @@
 #include <linux/atomic.h>
 #include <linux/compiler.h>
 #include <linux/mutex.h>
-#include <linux/workqueue.h>
+#include <linux/workqueue_types.h>
 
 struct rhash_head {
 	struct rhash_head __rcu		*next;
diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index fe1e467ba046..7c43e98cf211 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -4,6 +4,7 @@
 
 #include <linux/errno.h>
 #include <linux/clocksource_ids.h>
+#include <linux/ktime.h>
 
 /* Included from linux/ktime.h */
 
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 24b1e5070f4d..f1bb2e35301f 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -14,12 +14,7 @@
 #include <linux/atomic.h>
 #include <linux/cpumask.h>
 #include <linux/rcupdate.h>
-
-struct workqueue_struct;
-
-struct work_struct;
-typedef void (*work_func_t)(struct work_struct *work);
-void delayed_work_timer_fn(struct timer_list *t);
+#include <linux/workqueue_types.h>
 
 /*
  * The first word is the work queue pointer and the flags rolled into
@@ -95,15 +90,6 @@ enum {
 #define WORK_STRUCT_FLAG_MASK    ((1ul << WORK_STRUCT_FLAG_BITS) - 1)
 #define WORK_STRUCT_WQ_DATA_MASK (~WORK_STRUCT_FLAG_MASK)
 
-struct work_struct {
-	atomic_long_t data;
-	struct list_head entry;
-	work_func_t func;
-#ifdef CONFIG_LOCKDEP
-	struct lockdep_map lockdep_map;
-#endif
-};
-
 #define WORK_DATA_INIT()	ATOMIC_LONG_INIT((unsigned long)WORK_STRUCT_NO_POOL)
 #define WORK_DATA_STATIC_INIT()	\
 	ATOMIC_LONG_INIT((unsigned long)(WORK_STRUCT_NO_POOL | WORK_STRUCT_STATIC))
diff --git a/include/linux/workqueue_types.h b/include/linux/workqueue_types.h
new file mode 100644
index 000000000000..4c38824f3ab4
--- /dev/null
+++ b/include/linux/workqueue_types.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_WORKQUEUE_TYPES_H
+#define _LINUX_WORKQUEUE_TYPES_H
+
+#include <linux/atomic.h>
+#include <linux/lockdep_types.h>
+#include <linux/timer_types.h>
+#include <linux/types.h>
+
+struct workqueue_struct;
+
+struct work_struct;
+typedef void (*work_func_t)(struct work_struct *work);
+void delayed_work_timer_fn(struct timer_list *t);
+
+struct work_struct {
+	atomic_long_t data;
+	struct list_head entry;
+	work_func_t func;
+#ifdef CONFIG_LOCKDEP
+	struct lockdep_map lockdep_map;
+#endif
+};
+
+#endif /* _LINUX_WORKQUEUE_TYPES_H */
-- 
cgit v1.2.3


From bc46ef3cea3d6f63952d7e29a324e889c34970a8 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 11 Dec 2023 13:58:25 -0500
Subject: shm: Slim down dependencies

list_head is in types.h, not list.h., and the uapi header wasn't needed.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 arch/parisc/mm/init.c      | 1 +
 include/linux/shm.h        | 4 ++--
 ipc/shm.c                  | 1 +
 security/selinux/hooks.c   | 1 +
 security/smack/smack_lsm.c | 1 +
 5 files changed, 6 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index a2a3e89f2d9a..f876af56e13f 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -33,6 +33,7 @@
 #include <asm/msgbuf.h>
 #include <asm/sparsemem.h>
 #include <asm/asm-offsets.h>
+#include <asm/shmbuf.h>
 
 extern int  data_start;
 extern void parisc_kernel_start(void);	/* Kernel entry point in head.S */
diff --git a/include/linux/shm.h b/include/linux/shm.h
index d8e69aed3d32..c55bef0538e5 100644
--- a/include/linux/shm.h
+++ b/include/linux/shm.h
@@ -2,12 +2,12 @@
 #ifndef _LINUX_SHM_H_
 #define _LINUX_SHM_H_
 
-#include <linux/list.h>
+#include <linux/types.h>
 #include <asm/page.h>
-#include <uapi/linux/shm.h>
 #include <asm/shmparam.h>
 
 struct file;
+struct task_struct;
 
 #ifdef CONFIG_SYSVIPC
 struct sysv_shm {
diff --git a/ipc/shm.c b/ipc/shm.c
index 222aaf035afb..a89f001a8bf0 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -29,6 +29,7 @@
 #include <linux/mm.h>
 #include <linux/hugetlb.h>
 #include <linux/shm.h>
+#include <uapi/linux/shm.h>
 #include <linux/init.h>
 #include <linux/file.h>
 #include <linux/mman.h>
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index feda711c6b7b..b9ccc98421e9 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -85,6 +85,7 @@
 #include <linux/export.h>
 #include <linux/msg.h>
 #include <linux/shm.h>
+#include <uapi/linux/shm.h>
 #include <linux/bpf.h>
 #include <linux/kernfs.h>
 #include <linux/stringhash.h>	/* for hashlen_string() */
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index 65130a791f57..7a5600834f16 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -37,6 +37,7 @@
 #include <linux/personality.h>
 #include <linux/msg.h>
 #include <linux/shm.h>
+#include <uapi/linux/shm.h>
 #include <linux/binfmts.h>
 #include <linux/parser.h>
 #include <linux/fs_context.h>
-- 
cgit v1.2.3


From 72375a8864ebc0a20ca4a35f382441b01a0b85b9 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 11 Dec 2023 14:00:10 -0500
Subject: ipc: Kill bogus dependency on spinlock.h

pruning sched.h dependencies, headers shouldn't pull in more than they
need.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 include/linux/ipc.h   | 2 +-
 include/linux/sched.h | 2 ++
 2 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/ipc.h b/include/linux/ipc.h
index e1c9eea6015b..9b1434247aab 100644
--- a/include/linux/ipc.h
+++ b/include/linux/ipc.h
@@ -2,7 +2,7 @@
 #ifndef _LINUX_IPC_H
 #define _LINUX_IPC_H
 
-#include <linux/spinlock.h>
+#include <linux/spinlock_types.h>
 #include <linux/uidgid.h>
 #include <linux/rhashtable-types.h>
 #include <uapi/linux/ipc.h>
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8c230f24688b..34400b16e57c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2139,6 +2139,8 @@ extern bool sched_task_on_rq(struct task_struct *p);
 extern unsigned long get_wchan(struct task_struct *p);
 extern struct task_struct *cpu_curr_snapshot(int cpu);
 
+#include <linux/spinlock.h>
+
 /*
  * In order to reduce various lock holder preemption latencies provide an
  * interface to see if a vCPU is currently running or not.
-- 
cgit v1.2.3


From 9983deb26d9021aecd971d25abf4cd263c72c385 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 11 Dec 2023 14:01:25 -0500
Subject: Split out irqflags_types.h

We're working on only pulling in type definitions to sched.h whenever
possible.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 include/linux/irqflags.h       | 14 +-------------
 include/linux/irqflags_types.h | 22 ++++++++++++++++++++++
 include/linux/sched.h          |  2 +-
 3 files changed, 24 insertions(+), 14 deletions(-)
 create mode 100644 include/linux/irqflags_types.h

(limited to 'include')

diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h
index 2b665c32f5fe..147feebd508c 100644
--- a/include/linux/irqflags.h
+++ b/include/linux/irqflags.h
@@ -12,6 +12,7 @@
 #ifndef _LINUX_TRACE_IRQFLAGS_H
 #define _LINUX_TRACE_IRQFLAGS_H
 
+#include <linux/irqflags_types.h>
 #include <linux/typecheck.h>
 #include <linux/cleanup.h>
 #include <asm/irqflags.h>
@@ -34,19 +35,6 @@
 
 #ifdef CONFIG_TRACE_IRQFLAGS
 
-/* Per-task IRQ trace events information. */
-struct irqtrace_events {
-	unsigned int	irq_events;
-	unsigned long	hardirq_enable_ip;
-	unsigned long	hardirq_disable_ip;
-	unsigned int	hardirq_enable_event;
-	unsigned int	hardirq_disable_event;
-	unsigned long	softirq_disable_ip;
-	unsigned long	softirq_enable_ip;
-	unsigned int	softirq_disable_event;
-	unsigned int	softirq_enable_event;
-};
-
 DECLARE_PER_CPU(int, hardirqs_enabled);
 DECLARE_PER_CPU(int, hardirq_context);
 
diff --git a/include/linux/irqflags_types.h b/include/linux/irqflags_types.h
new file mode 100644
index 000000000000..c13f0d915097
--- /dev/null
+++ b/include/linux/irqflags_types.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_IRQFLAGS_TYPES_H
+#define _LINUX_IRQFLAGS_TYPES_H
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+
+/* Per-task IRQ trace events information. */
+struct irqtrace_events {
+	unsigned int	irq_events;
+	unsigned long	hardirq_enable_ip;
+	unsigned long	hardirq_disable_ip;
+	unsigned int	hardirq_enable_event;
+	unsigned int	hardirq_disable_event;
+	unsigned long	softirq_disable_ip;
+	unsigned long	softirq_enable_ip;
+	unsigned int	softirq_disable_event;
+	unsigned int	softirq_enable_event;
+};
+
+#endif
+
+#endif /* _LINUX_IRQFLAGS_TYPES_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 34400b16e57c..026390e6fe59 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -11,6 +11,7 @@
 
 #include <asm/current.h>
 
+#include <linux/irqflags_types.h>
 #include <linux/pid_types.h>
 #include <linux/sem.h>
 #include <linux/shm.h>
@@ -18,7 +19,6 @@
 #include <linux/mutex_types.h>
 #include <linux/plist_types.h>
 #include <linux/hrtimer_types.h>
-#include <linux/irqflags.h>
 #include <linux/seccomp.h>
 #include <linux/nodemask_types.h>
 #include <linux/rcupdate.h>
-- 
cgit v1.2.3


From 959d8dc8046186ffea5410f51fcb309880f0dfaa Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 11 Dec 2023 14:15:35 -0500
Subject: mm_types_task.h: Trim dependencies

more sched.h header dependency trimming

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 include/linux/mm_types_task.h | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h
index aa44fff8bb9d..a2f6179b672b 100644
--- a/include/linux/mm_types_task.h
+++ b/include/linux/mm_types_task.h
@@ -9,9 +9,6 @@
  */
 
 #include <linux/types.h>
-#include <linux/threads.h>
-#include <linux/atomic.h>
-#include <linux/cpumask.h>
 
 #include <asm/page.h>
 
@@ -36,6 +33,8 @@ enum {
 	NR_MM_COUNTERS
 };
 
+struct page;
+
 struct page_frag {
 	struct page *page;
 #if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536)
-- 
cgit v1.2.3


From 55b899aa3e7d0dc02ff9075b883d29eb2d0cb49a Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 11 Dec 2023 14:25:40 -0500
Subject: syscall_user_dispatch.h: split out *_types.h

thread_info.h pulls in a lot of junk that sched.h that we don't need; in
particular, this helps to kill the printk.h dependency.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 include/linux/sched.h                       |  2 +-
 include/linux/syscall_user_dispatch.h       |  9 +--------
 include/linux/syscall_user_dispatch_types.h | 22 ++++++++++++++++++++++
 3 files changed, 24 insertions(+), 9 deletions(-)
 create mode 100644 include/linux/syscall_user_dispatch_types.h

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 026390e6fe59..925711edd7f7 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -28,7 +28,7 @@
 #include <linux/sched/prio.h>
 #include <linux/sched/types.h>
 #include <linux/signal_types.h>
-#include <linux/syscall_user_dispatch.h>
+#include <linux/syscall_user_dispatch_types.h>
 #include <linux/mm_types_task.h>
 #include <linux/task_io_accounting.h>
 #include <linux/posix-timers_types.h>
diff --git a/include/linux/syscall_user_dispatch.h b/include/linux/syscall_user_dispatch.h
index 641ca8880995..3858a6ffdd5c 100644
--- a/include/linux/syscall_user_dispatch.h
+++ b/include/linux/syscall_user_dispatch.h
@@ -6,16 +6,10 @@
 #define _SYSCALL_USER_DISPATCH_H
 
 #include <linux/thread_info.h>
+#include <linux/syscall_user_dispatch_types.h>
 
 #ifdef CONFIG_GENERIC_ENTRY
 
-struct syscall_user_dispatch {
-	char __user	*selector;
-	unsigned long	offset;
-	unsigned long	len;
-	bool		on_dispatch;
-};
-
 int set_syscall_user_dispatch(unsigned long mode, unsigned long offset,
 			      unsigned long len, char __user *selector);
 
@@ -29,7 +23,6 @@ int syscall_user_dispatch_set_config(struct task_struct *task, unsigned long siz
 				     void __user *data);
 
 #else
-struct syscall_user_dispatch {};
 
 static inline int set_syscall_user_dispatch(unsigned long mode, unsigned long offset,
 					    unsigned long len, char __user *selector)
diff --git a/include/linux/syscall_user_dispatch_types.h b/include/linux/syscall_user_dispatch_types.h
new file mode 100644
index 000000000000..3be36b06c7d7
--- /dev/null
+++ b/include/linux/syscall_user_dispatch_types.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _SYSCALL_USER_DISPATCH_TYPES_H
+#define _SYSCALL_USER_DISPATCH_TYPES_H
+
+#include <linux/types.h>
+
+#ifdef CONFIG_GENERIC_ENTRY
+
+struct syscall_user_dispatch {
+	char __user	*selector;
+	unsigned long	offset;
+	unsigned long	len;
+	bool		on_dispatch;
+};
+
+#else
+
+struct syscall_user_dispatch {};
+
+#endif
+
+#endif /* _SYSCALL_USER_DISPATCH_TYPES_H */
-- 
cgit v1.2.3


From 1ef83969bb12e594fe44ceba406095e80a824c91 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 11 Dec 2023 15:12:04 -0500
Subject: uapi/linux/resource.h: fix include

We should't be depending on time.h; we should only be pulling in other
uapi headers.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 include/uapi/linux/resource.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/resource.h b/include/uapi/linux/resource.h
index ac5d6a3031db..4fc22908bc09 100644
--- a/include/uapi/linux/resource.h
+++ b/include/uapi/linux/resource.h
@@ -2,7 +2,7 @@
 #ifndef _UAPI_LINUX_RESOURCE_H
 #define _UAPI_LINUX_RESOURCE_H
 
-#include <linux/time.h>
+#include <linux/time_types.h>
 #include <linux/types.h>
 
 /*
-- 
cgit v1.2.3


From f9d6966b7f4182f612208f9dad9e2cfaaf667ba3 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 11 Dec 2023 15:15:38 -0500
Subject: refcount: Split out refcount_types.h

More trimming of sched.h dependencies.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 include/linux/refcount.h       | 13 +------------
 include/linux/refcount_types.h | 19 +++++++++++++++++++
 include/linux/sched.h          |  2 +-
 include/linux/sched/task.h     |  1 +
 4 files changed, 22 insertions(+), 13 deletions(-)
 create mode 100644 include/linux/refcount_types.h

(limited to 'include')

diff --git a/include/linux/refcount.h b/include/linux/refcount.h
index a62fcca97486..85c6df0d1bef 100644
--- a/include/linux/refcount.h
+++ b/include/linux/refcount.h
@@ -96,22 +96,11 @@
 #include <linux/bug.h>
 #include <linux/compiler.h>
 #include <linux/limits.h>
+#include <linux/refcount_types.h>
 #include <linux/spinlock_types.h>
 
 struct mutex;
 
-/**
- * typedef refcount_t - variant of atomic_t specialized for reference counts
- * @refs: atomic_t counter field
- *
- * The counter saturates at REFCOUNT_SATURATED and will not move once
- * there. This avoids wrapping the counter and causing 'spurious'
- * use-after-free bugs.
- */
-typedef struct refcount_struct {
-	atomic_t refs;
-} refcount_t;
-
 #define REFCOUNT_INIT(n)	{ .refs = ATOMIC_INIT(n), }
 #define REFCOUNT_MAX		INT_MAX
 #define REFCOUNT_SATURATED	(INT_MIN / 2)
diff --git a/include/linux/refcount_types.h b/include/linux/refcount_types.h
new file mode 100644
index 000000000000..162004f06edf
--- /dev/null
+++ b/include/linux/refcount_types.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_REFCOUNT_TYPES_H
+#define _LINUX_REFCOUNT_TYPES_H
+
+#include <linux/types.h>
+
+/**
+ * typedef refcount_t - variant of atomic_t specialized for reference counts
+ * @refs: atomic_t counter field
+ *
+ * The counter saturates at REFCOUNT_SATURATED and will not move once
+ * there. This avoids wrapping the counter and causing 'spurious'
+ * use-after-free bugs.
+ */
+typedef struct refcount_struct {
+	atomic_t refs;
+} refcount_t;
+
+#endif /* _LINUX_REFCOUNT_TYPES_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 925711edd7f7..414e4df701ec 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -22,7 +22,7 @@
 #include <linux/seccomp.h>
 #include <linux/nodemask_types.h>
 #include <linux/rcupdate.h>
-#include <linux/refcount.h>
+#include <linux/refcount_types.h>
 #include <linux/resource.h>
 #include <linux/latencytop.h>
 #include <linux/sched/prio.h>
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index a23af225c898..1880ae21a9cb 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -7,6 +7,7 @@
  * functionality:
  */
 
+#include <linux/refcount.h>
 #include <linux/sched.h>
 #include <linux/uaccess.h>
 
-- 
cgit v1.2.3


From a6e1420ce4fc91da56c0a2444c4482245e7617d4 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 11 Dec 2023 15:30:14 -0500
Subject: seccomp: Split out seccomp_types.h

More pruning of sched.h dependencies.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 include/linux/sched.h         |  2 +-
 include/linux/seccomp.h       | 22 +---------------------
 include/linux/seccomp_types.h | 35 +++++++++++++++++++++++++++++++++++
 3 files changed, 37 insertions(+), 22 deletions(-)
 create mode 100644 include/linux/seccomp_types.h

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 414e4df701ec..db6e3e629606 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -19,7 +19,7 @@
 #include <linux/mutex_types.h>
 #include <linux/plist_types.h>
 #include <linux/hrtimer_types.h>
-#include <linux/seccomp.h>
+#include <linux/seccomp_types.h>
 #include <linux/nodemask_types.h>
 #include <linux/rcupdate.h>
 #include <linux/refcount_types.h>
diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index 1ec0d8dc4b69..709ad84809e1 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -3,6 +3,7 @@
 #define _LINUX_SECCOMP_H
 
 #include <uapi/linux/seccomp.h>
+#include <linux/seccomp_types.h>
 
 #define SECCOMP_FILTER_FLAG_MASK	(SECCOMP_FILTER_FLAG_TSYNC | \
 					 SECCOMP_FILTER_FLAG_LOG | \
@@ -21,25 +22,6 @@
 #include <linux/atomic.h>
 #include <asm/seccomp.h>
 
-struct seccomp_filter;
-/**
- * struct seccomp - the state of a seccomp'ed process
- *
- * @mode:  indicates one of the valid values above for controlled
- *         system calls available to a process.
- * @filter_count: number of seccomp filters
- * @filter: must always point to a valid seccomp-filter or NULL as it is
- *          accessed without locking during system call entry.
- *
- *          @filter must only be accessed from the context of current as there
- *          is no read locking.
- */
-struct seccomp {
-	int mode;
-	atomic_t filter_count;
-	struct seccomp_filter *filter;
-};
-
 #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER
 extern int __secure_computing(const struct seccomp_data *sd);
 static inline int secure_computing(void)
@@ -64,8 +46,6 @@ static inline int seccomp_mode(struct seccomp *s)
 
 #include <linux/errno.h>
 
-struct seccomp { };
-struct seccomp_filter { };
 struct seccomp_data;
 
 #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER
diff --git a/include/linux/seccomp_types.h b/include/linux/seccomp_types.h
new file mode 100644
index 000000000000..cf0a0355024f
--- /dev/null
+++ b/include/linux/seccomp_types.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SECCOMP_TYPES_H
+#define _LINUX_SECCOMP_TYPES_H
+
+#include <linux/types.h>
+
+#ifdef CONFIG_SECCOMP
+
+struct seccomp_filter;
+/**
+ * struct seccomp - the state of a seccomp'ed process
+ *
+ * @mode:  indicates one of the valid values above for controlled
+ *         system calls available to a process.
+ * @filter_count: number of seccomp filters
+ * @filter: must always point to a valid seccomp-filter or NULL as it is
+ *          accessed without locking during system call entry.
+ *
+ *          @filter must only be accessed from the context of current as there
+ *          is no read locking.
+ */
+struct seccomp {
+	int mode;
+	atomic_t filter_count;
+	struct seccomp_filter *filter;
+};
+
+#else
+
+struct seccomp { };
+struct seccomp_filter { };
+
+#endif
+
+#endif /* _LINUX_SECCOMP_TYPES_H */
-- 
cgit v1.2.3


From af6da56a223831cb74d1cf006f5742db6403398e Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 11 Dec 2023 15:51:30 -0500
Subject: uidgid: Split out uidgid_types.h

More sched.h dependency pruning.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Reviewed-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/sched.h        |  1 +
 include/linux/uidgid.h       | 11 +----------
 include/linux/uidgid_types.h | 15 +++++++++++++++
 3 files changed, 17 insertions(+), 10 deletions(-)
 create mode 100644 include/linux/uidgid_types.h

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index db6e3e629606..10e25c7fc793 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -37,6 +37,7 @@
 #include <linux/kcsan.h>
 #include <linux/rv.h>
 #include <linux/livepatch_sched.h>
+#include <linux/uidgid_types.h>
 #include <asm/kmap_size.h>
 
 /* task_struct member predeclarations (sorted alphabetically): */
diff --git a/include/linux/uidgid.h b/include/linux/uidgid.h
index b0542cd11aeb..ba20b62f13e1 100644
--- a/include/linux/uidgid.h
+++ b/include/linux/uidgid.h
@@ -12,21 +12,12 @@
  * to detect when we overlook these differences.
  *
  */
-#include <linux/types.h>
+#include <linux/uidgid_types.h>
 #include <linux/highuid.h>
 
 struct user_namespace;
 extern struct user_namespace init_user_ns;
 
-typedef struct {
-	uid_t val;
-} kuid_t;
-
-
-typedef struct {
-	gid_t val;
-} kgid_t;
-
 #define KUIDT_INIT(value) (kuid_t){ value }
 #define KGIDT_INIT(value) (kgid_t){ value }
 
diff --git a/include/linux/uidgid_types.h b/include/linux/uidgid_types.h
new file mode 100644
index 000000000000..b35ac4955a33
--- /dev/null
+++ b/include/linux/uidgid_types.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_UIDGID_TYPES_H
+#define _LINUX_UIDGID_TYPES_H
+
+#include <linux/types.h>
+
+typedef struct {
+	uid_t val;
+} kuid_t;
+
+typedef struct {
+	gid_t val;
+} kgid_t;
+
+#endif /* _LINUX_UIDGID_TYPES_H */
-- 
cgit v1.2.3


From e034d49eb01c7c83a08a3ce2a1091b55f806b26b Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 11 Dec 2023 15:52:17 -0500
Subject: sem: Split out sem_types.h

More sched.h dependency pruning.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 include/linux/audit.h     |  1 +
 include/linux/sched.h     |  4 +++-
 include/linux/sem.h       | 10 +---------
 include/linux/sem_types.h | 13 +++++++++++++
 4 files changed, 18 insertions(+), 10 deletions(-)
 create mode 100644 include/linux/sem_types.h

(limited to 'include')

diff --git a/include/linux/audit.h b/include/linux/audit.h
index 51b1b7054a23..0050ef288ab3 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -36,6 +36,7 @@ struct mqstat;
 struct audit_watch;
 struct audit_tree;
 struct sk_buff;
+struct kern_ipc_perm;
 
 struct audit_krule {
 	u32			pflags;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 10e25c7fc793..d341a6c302d6 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -11,14 +11,16 @@
 
 #include <asm/current.h>
 
+#include <linux/cache.h>
 #include <linux/irqflags_types.h>
 #include <linux/pid_types.h>
-#include <linux/sem.h>
+#include <linux/sem_types.h>
 #include <linux/shm.h>
 #include <linux/kmsan_types.h>
 #include <linux/mutex_types.h>
 #include <linux/plist_types.h>
 #include <linux/hrtimer_types.h>
+#include <linux/timer_types.h>
 #include <linux/seccomp_types.h>
 #include <linux/nodemask_types.h>
 #include <linux/rcupdate.h>
diff --git a/include/linux/sem.h b/include/linux/sem.h
index 5608a500c43e..c4deefe42aeb 100644
--- a/include/linux/sem.h
+++ b/include/linux/sem.h
@@ -3,25 +3,17 @@
 #define _LINUX_SEM_H
 
 #include <uapi/linux/sem.h>
+#include <linux/sem_types.h>
 
 struct task_struct;
-struct sem_undo_list;
 
 #ifdef CONFIG_SYSVIPC
 
-struct sysv_sem {
-	struct sem_undo_list *undo_list;
-};
-
 extern int copy_semundo(unsigned long clone_flags, struct task_struct *tsk);
 extern void exit_sem(struct task_struct *tsk);
 
 #else
 
-struct sysv_sem {
-	/* empty */
-};
-
 static inline int copy_semundo(unsigned long clone_flags, struct task_struct *tsk)
 {
 	return 0;
diff --git a/include/linux/sem_types.h b/include/linux/sem_types.h
new file mode 100644
index 000000000000..73df1971a7ae
--- /dev/null
+++ b/include/linux/sem_types.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SEM_TYPES_H
+#define _LINUX_SEM_TYPES_H
+
+struct sem_undo_list;
+
+struct sysv_sem {
+#ifdef CONFIG_SYSVIPC
+	struct sem_undo_list *undo_list;
+#endif
+};
+
+#endif /* _LINUX_SEM_TYPES_H */
-- 
cgit v1.2.3


From 99bac36667b6b20b9b0a20dc976365d23f90628b Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 11 Dec 2023 16:58:51 -0500
Subject: lockdep: move held_lock to lockdep_types.h

held_lock is embedded in task_struct, and we don't want sched.h pulling
in all of lockdep.h

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Acked-by: Waiman Long <longman@redhat.com>
---
 include/linux/lockdep.h       | 57 -------------------------------------------
 include/linux/lockdep_types.h | 57 +++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 57 insertions(+), 57 deletions(-)

(limited to 'include')

diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index dc2844b071c2..08b0d1d9d78b 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -82,63 +82,6 @@ struct lock_chain {
 	u64				chain_key;
 };
 
-#define MAX_LOCKDEP_KEYS_BITS		13
-#define MAX_LOCKDEP_KEYS		(1UL << MAX_LOCKDEP_KEYS_BITS)
-#define INITIAL_CHAIN_KEY		-1
-
-struct held_lock {
-	/*
-	 * One-way hash of the dependency chain up to this point. We
-	 * hash the hashes step by step as the dependency chain grows.
-	 *
-	 * We use it for dependency-caching and we skip detection
-	 * passes and dependency-updates if there is a cache-hit, so
-	 * it is absolutely critical for 100% coverage of the validator
-	 * to have a unique key value for every unique dependency path
-	 * that can occur in the system, to make a unique hash value
-	 * as likely as possible - hence the 64-bit width.
-	 *
-	 * The task struct holds the current hash value (initialized
-	 * with zero), here we store the previous hash value:
-	 */
-	u64				prev_chain_key;
-	unsigned long			acquire_ip;
-	struct lockdep_map		*instance;
-	struct lockdep_map		*nest_lock;
-#ifdef CONFIG_LOCK_STAT
-	u64 				waittime_stamp;
-	u64				holdtime_stamp;
-#endif
-	/*
-	 * class_idx is zero-indexed; it points to the element in
-	 * lock_classes this held lock instance belongs to. class_idx is in
-	 * the range from 0 to (MAX_LOCKDEP_KEYS-1) inclusive.
-	 */
-	unsigned int			class_idx:MAX_LOCKDEP_KEYS_BITS;
-	/*
-	 * The lock-stack is unified in that the lock chains of interrupt
-	 * contexts nest ontop of process context chains, but we 'separate'
-	 * the hashes by starting with 0 if we cross into an interrupt
-	 * context, and we also keep do not add cross-context lock
-	 * dependencies - the lock usage graph walking covers that area
-	 * anyway, and we'd just unnecessarily increase the number of
-	 * dependencies otherwise. [Note: hardirq and softirq contexts
-	 * are separated from each other too.]
-	 *
-	 * The following field is used to detect when we cross into an
-	 * interrupt context:
-	 */
-	unsigned int irq_context:2; /* bit 0 - soft, bit 1 - hard */
-	unsigned int trylock:1;						/* 16 bits */
-
-	unsigned int read:2;        /* see lock_acquire() comment */
-	unsigned int check:1;       /* see lock_acquire() comment */
-	unsigned int hardirqs_off:1;
-	unsigned int sync:1;
-	unsigned int references:11;					/* 32 bits */
-	unsigned int pin_count;
-};
-
 /*
  * Initialization, self-test and debugging-output methods:
  */
diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h
index 2ebc323d345a..9c533c8d701e 100644
--- a/include/linux/lockdep_types.h
+++ b/include/linux/lockdep_types.h
@@ -198,6 +198,63 @@ struct lockdep_map {
 
 struct pin_cookie { unsigned int val; };
 
+#define MAX_LOCKDEP_KEYS_BITS		13
+#define MAX_LOCKDEP_KEYS		(1UL << MAX_LOCKDEP_KEYS_BITS)
+#define INITIAL_CHAIN_KEY		-1
+
+struct held_lock {
+	/*
+	 * One-way hash of the dependency chain up to this point. We
+	 * hash the hashes step by step as the dependency chain grows.
+	 *
+	 * We use it for dependency-caching and we skip detection
+	 * passes and dependency-updates if there is a cache-hit, so
+	 * it is absolutely critical for 100% coverage of the validator
+	 * to have a unique key value for every unique dependency path
+	 * that can occur in the system, to make a unique hash value
+	 * as likely as possible - hence the 64-bit width.
+	 *
+	 * The task struct holds the current hash value (initialized
+	 * with zero), here we store the previous hash value:
+	 */
+	u64				prev_chain_key;
+	unsigned long			acquire_ip;
+	struct lockdep_map		*instance;
+	struct lockdep_map		*nest_lock;
+#ifdef CONFIG_LOCK_STAT
+	u64 				waittime_stamp;
+	u64				holdtime_stamp;
+#endif
+	/*
+	 * class_idx is zero-indexed; it points to the element in
+	 * lock_classes this held lock instance belongs to. class_idx is in
+	 * the range from 0 to (MAX_LOCKDEP_KEYS-1) inclusive.
+	 */
+	unsigned int			class_idx:MAX_LOCKDEP_KEYS_BITS;
+	/*
+	 * The lock-stack is unified in that the lock chains of interrupt
+	 * contexts nest ontop of process context chains, but we 'separate'
+	 * the hashes by starting with 0 if we cross into an interrupt
+	 * context, and we also keep do not add cross-context lock
+	 * dependencies - the lock usage graph walking covers that area
+	 * anyway, and we'd just unnecessarily increase the number of
+	 * dependencies otherwise. [Note: hardirq and softirq contexts
+	 * are separated from each other too.]
+	 *
+	 * The following field is used to detect when we cross into an
+	 * interrupt context:
+	 */
+	unsigned int irq_context:2; /* bit 0 - soft, bit 1 - hard */
+	unsigned int trylock:1;						/* 16 bits */
+
+	unsigned int read:2;        /* see lock_acquire() comment */
+	unsigned int check:1;       /* see lock_acquire() comment */
+	unsigned int hardirqs_off:1;
+	unsigned int sync:1;
+	unsigned int references:11;					/* 32 bits */
+	unsigned int pin_count;
+};
+
 #else /* !CONFIG_LOCKDEP */
 
 /*
-- 
cgit v1.2.3


From cba6167f0adb07b6cd1b8758dd67718c772e108c Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 11 Dec 2023 17:00:41 -0500
Subject: restart_block: Trim includes

We don't actually use any timekeeping types, no need to pull in
time64.h.

Also, sched.h uses restart_block; add it as a direct dependency.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 include/linux/restart_block.h | 2 +-
 include/linux/sched.h         | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/restart_block.h b/include/linux/restart_block.h
index 980a65594412..13f17676c5f4 100644
--- a/include/linux/restart_block.h
+++ b/include/linux/restart_block.h
@@ -7,8 +7,8 @@
 
 #include <linux/compiler.h>
 #include <linux/types.h>
-#include <linux/time64.h>
 
+struct __kernel_timespec;
 struct timespec;
 struct old_timespec32;
 struct pollfd;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index d341a6c302d6..dd002d193726 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -34,6 +34,7 @@
 #include <linux/mm_types_task.h>
 #include <linux/task_io_accounting.h>
 #include <linux/posix-timers_types.h>
+#include <linux/restart_block.h>
 #include <linux/rseq.h>
 #include <linux/seqlock_types.h>
 #include <linux/kcsan.h>
-- 
cgit v1.2.3


From a7e7b40c4bc115dbf2a2bb453d7bbb2e0ea99703 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@nvidia.com>
Date: Fri, 15 Dec 2023 19:31:14 -0800
Subject: net/mlx5e: Use the correct lag ports number when creating TISes

The cited commit moved the code of mlx5e_create_tises() and changed the
loop to create TISes over MLX5_MAX_PORTS constant value, instead of
getting the correct lag ports supported by the device, which can cause
FW errors on devices with less than MLX5_MAX_PORTS ports.

Change that back to mlx5e_get_num_lag_ports(mdev).

Also IPoIB interfaces create there own TISes, they don't use the eth
TISes, pass a flag to indicate that.

Fixes: b25bd37c859f ("net/mlx5: Move TISes from priv to mdev HW resources")
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h        |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_common.c | 21 +++++++++++++--------
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c   |  2 +-
 .../net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c   |  2 +-
 include/linux/mlx5/driver.h                         |  1 +
 5 files changed, 17 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 0bfe1ca8a364..55c6ace0acd5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -1124,7 +1124,7 @@ static inline bool mlx5_tx_swp_supported(struct mlx5_core_dev *mdev)
 extern const struct ethtool_ops mlx5e_ethtool_ops;
 
 int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, u32 *mkey);
-int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev);
+int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev, bool create_tises);
 void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev);
 int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb,
 		       bool enable_mc_lb);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
index 67f546683e85..6ed3a32b7e22 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
@@ -95,7 +95,7 @@ static void mlx5e_destroy_tises(struct mlx5_core_dev *mdev, u32 tisn[MLX5_MAX_PO
 {
 	int tc, i;
 
-	for (i = 0; i < MLX5_MAX_PORTS; i++)
+	for (i = 0; i < mlx5e_get_num_lag_ports(mdev); i++)
 		for (tc = 0; tc < MLX5_MAX_NUM_TC; tc++)
 			mlx5e_destroy_tis(mdev, tisn[i][tc]);
 }
@@ -110,7 +110,7 @@ static int mlx5e_create_tises(struct mlx5_core_dev *mdev, u32 tisn[MLX5_MAX_PORT
 	int tc, i;
 	int err;
 
-	for (i = 0; i < MLX5_MAX_PORTS; i++) {
+	for (i = 0; i < mlx5e_get_num_lag_ports(mdev); i++) {
 		for (tc = 0; tc < MLX5_MAX_NUM_TC; tc++) {
 			u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {};
 			void *tisc;
@@ -140,7 +140,7 @@ err_close_tises:
 	return err;
 }
 
-int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev)
+int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev, bool create_tises)
 {
 	struct mlx5e_hw_objs *res = &mdev->mlx5e_res.hw_objs;
 	int err;
@@ -169,11 +169,15 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev)
 		goto err_destroy_mkey;
 	}
 
-	err = mlx5e_create_tises(mdev, res->tisn);
-	if (err) {
-		mlx5_core_err(mdev, "alloc tises failed, %d\n", err);
-		goto err_destroy_bfreg;
+	if (create_tises) {
+		err = mlx5e_create_tises(mdev, res->tisn);
+		if (err) {
+			mlx5_core_err(mdev, "alloc tises failed, %d\n", err);
+			goto err_destroy_bfreg;
+		}
+		res->tisn_valid = true;
 	}
+
 	INIT_LIST_HEAD(&res->td.tirs_list);
 	mutex_init(&res->td.list_lock);
 
@@ -203,7 +207,8 @@ void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev)
 
 	mlx5_crypto_dek_cleanup(mdev->mlx5e_res.dek_priv);
 	mdev->mlx5e_res.dek_priv = NULL;
-	mlx5e_destroy_tises(mdev, res->tisn);
+	if (res->tisn_valid)
+		mlx5e_destroy_tises(mdev, res->tisn);
 	mlx5_free_bfreg(mdev, &res->bfreg);
 	mlx5_core_destroy_mkey(mdev, res->mkey);
 	mlx5_core_dealloc_transport_domain(mdev, res->td.tdn);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index b5f1c4ca38ba..c8e8f512803e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -5992,7 +5992,7 @@ static int mlx5e_resume(struct auxiliary_device *adev)
 	if (netif_device_present(netdev))
 		return 0;
 
-	err = mlx5e_create_mdev_resources(mdev);
+	err = mlx5e_create_mdev_resources(mdev, true);
 	if (err)
 		return err;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 58845121954c..d77be1b4dd9c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -783,7 +783,7 @@ static int mlx5_rdma_setup_rn(struct ib_device *ibdev, u32 port_num,
 		}
 
 		/* This should only be called once per mdev */
-		err = mlx5e_create_mdev_resources(mdev);
+		err = mlx5e_create_mdev_resources(mdev, false);
 		if (err)
 			goto destroy_ht;
 	}
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 7ee5b79ff3d6..aafb36c9e5d9 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -681,6 +681,7 @@ struct mlx5e_resources {
 		struct mlx5_sq_bfreg       bfreg;
 #define MLX5_MAX_NUM_TC 8
 		u32                        tisn[MLX5_MAX_PORTS][MLX5_MAX_NUM_TC];
+		bool			   tisn_valid;
 	} hw_objs;
 	struct net_device *uplink_netdev;
 	struct mutex uplink_netdev_lock;
-- 
cgit v1.2.3


From e04984a37398b3f4f5a79c993b94c6b1224184cc Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@nvidia.com>
Date: Tue, 19 Dec 2023 14:46:20 +0200
Subject: net/mlx5: Fix query of sd_group field

The sd_group field moved in the HW spec from the MPIR register
to the vport context.
Align the query accordingly.

Fixes: f5e956329960 ("net/mlx5: Expose Management PCIe Index Register (MPIR)")
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/vport.c | 21 +++++++++++++++++++++
 include/linux/mlx5/mlx5_ifc.h                   | 10 +++++++---
 include/linux/mlx5/vport.h                      |  1 +
 3 files changed, 29 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index 5a31fb47ffa5..c95a84b7db3a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -440,6 +440,27 @@ out:
 }
 EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_system_image_guid);
 
+int mlx5_query_nic_vport_sd_group(struct mlx5_core_dev *mdev, u8 *sd_group)
+{
+	int outlen = MLX5_ST_SZ_BYTES(query_nic_vport_context_out);
+	u32 *out;
+	int err;
+
+	out = kvzalloc(outlen, GFP_KERNEL);
+	if (!out)
+		return -ENOMEM;
+
+	err = mlx5_query_nic_vport_context(mdev, 0, out);
+	if (err)
+		goto out;
+
+	*sd_group = MLX5_GET(query_nic_vport_context_out, out,
+			     nic_vport_context.sd_group);
+out:
+	kvfree(out);
+	return err;
+}
+
 int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid)
 {
 	u32 *out;
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index fee20fc010c2..bf2d51952e48 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -4030,8 +4030,13 @@ struct mlx5_ifc_nic_vport_context_bits {
 	u8	   affiliation_criteria[0x4];
 	u8	   affiliated_vhca_id[0x10];
 
-	u8	   reserved_at_60[0xd0];
+	u8	   reserved_at_60[0xa0];
 
+	u8	   reserved_at_100[0x1];
+	u8         sd_group[0x3];
+	u8	   reserved_at_104[0x1c];
+
+	u8	   reserved_at_120[0x10];
 	u8         mtu[0x10];
 
 	u8         system_image_guid[0x40];
@@ -10116,8 +10121,7 @@ struct mlx5_ifc_mpir_reg_bits {
 	u8         reserved_at_20[0x20];
 
 	u8         local_port[0x8];
-	u8         reserved_at_28[0x15];
-	u8         sd_group[0x3];
+	u8         reserved_at_28[0x18];
 
 	u8         reserved_at_60[0x20];
 };
diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h
index fbb9bf447889..c36cc6d82926 100644
--- a/include/linux/mlx5/vport.h
+++ b/include/linux/mlx5/vport.h
@@ -72,6 +72,7 @@ int mlx5_query_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 *mtu);
 int mlx5_modify_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 mtu);
 int mlx5_query_nic_vport_system_image_guid(struct mlx5_core_dev *mdev,
 					   u64 *system_image_guid);
+int mlx5_query_nic_vport_sd_group(struct mlx5_core_dev *mdev, u8 *sd_group);
 int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid);
 int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev,
 				    u16 vport, u64 node_guid);
-- 
cgit v1.2.3


From c88c49ac9c18fb7c3fa431126de1d8f8f555e912 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@nvidia.com>
Date: Tue, 5 Dec 2023 23:54:21 +0200
Subject: net/mlx5: Enable SD feature

Have an actual mlx5_sd instance in the core device, and fix the getter
accordingly. This allows SD stuff to flow, the feature becomes supported
only here.

Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Gal Pressman <gal@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h | 3 ++-
 include/linux/mlx5/driver.h                        | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
index 0810b92b48d0..37d5f445598c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
@@ -59,10 +59,11 @@ struct mlx5_sd;
 
 static inline struct mlx5_sd *mlx5_get_sd(struct mlx5_core_dev *dev)
 {
-	return NULL;
+	return dev->sd;
 }
 
 static inline void mlx5_set_sd(struct mlx5_core_dev *dev, struct mlx5_sd *sd)
 {
+	dev->sd = sd;
 }
 #endif
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index aafb36c9e5d9..cd286b681970 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -822,6 +822,7 @@ struct mlx5_core_dev {
 	struct blocking_notifier_head macsec_nh;
 #endif
 	u64 num_ipsec_offloads;
+	struct mlx5_sd          *sd;
 };
 
 struct mlx5_db {
-- 
cgit v1.2.3


From 22c4640698a1d47606b5a4264a584e8046641784 Mon Sep 17 00:00:00 2001
From: Armen Ratner <armeng@nvidia.com>
Date: Fri, 8 Sep 2023 14:53:09 -0500
Subject: net/mlx5: Implement management PF Ethernet profile

Add management PF modules, which introduce support for the structures
needed to create the resources for the MGMT PF to work.
Also, add the necessary calls and functions to establish this
functionality.

Signed-off-by: Armen Ratner <armeng@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Daniel Jurgens <danielj@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Makefile   |   2 +-
 drivers/net/ethernet/mellanox/mlx5/core/dev.c      |   3 +
 drivers/net/ethernet/mellanox/mlx5/core/ecpf.c     |   6 +
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |   4 +
 .../net/ethernet/mellanox/mlx5/core/en/mgmt_pf.c   | 268 +++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  |  24 +-
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c  |   2 +-
 include/linux/mlx5/driver.h                        |   8 +
 include/linux/mlx5/mlx5_ifc.h                      |  14 +-
 9 files changed, 323 insertions(+), 8 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/mgmt_pf.c

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 76dc5a9b9648..f36232dead1a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -29,7 +29,7 @@ mlx5_core-$(CONFIG_MLX5_CORE_EN) += en/rqt.o en/tir.o en/rss.o en/rx_res.o \
 		en/reporter_tx.o en/reporter_rx.o en/params.o en/xsk/pool.o \
 		en/xsk/setup.o en/xsk/rx.o en/xsk/tx.o en/devlink.o en/ptp.o \
 		en/qos.o en/htb.o en/trap.o en/fs_tt_redirect.o en/selq.o \
-		lib/crypto.o lib/sd.o
+		en/mgmt_pf.o lib/crypto.o lib/sd.o
 
 #
 # Netdev extra
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
index cf0477f53dc4..aa1b471e13fa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
@@ -190,6 +190,9 @@ bool mlx5_rdma_supported(struct mlx5_core_dev *dev)
 	if (is_mp_supported(dev))
 		return false;
 
+	if (mlx5_core_is_mgmt_pf(dev))
+		return false;
+
 	return true;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c
index d000236ddbac..aa397e3ebe6d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c
@@ -75,6 +75,9 @@ int mlx5_ec_init(struct mlx5_core_dev *dev)
 	if (!mlx5_core_is_ecpf(dev))
 		return 0;
 
+	if (mlx5_core_is_mgmt_pf(dev))
+		return 0;
+
 	return mlx5_host_pf_init(dev);
 }
 
@@ -85,6 +88,9 @@ void mlx5_ec_cleanup(struct mlx5_core_dev *dev)
 	if (!mlx5_core_is_ecpf(dev))
 		return;
 
+	if (mlx5_core_is_mgmt_pf(dev))
+		return;
+
 	mlx5_host_pf_cleanup(dev);
 
 	err = mlx5_wait_for_pages(dev, &dev->priv.page_counters[MLX5_HOST_PF]);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 84db05fb9389..922b63c25154 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -63,6 +63,7 @@
 #include "lib/sd.h"
 
 extern const struct net_device_ops mlx5e_netdev_ops;
+extern const struct net_device_ops mlx5e_mgmt_netdev_ops;
 struct page_pool;
 
 #define MLX5E_METADATA_ETHER_TYPE (0x8CE4)
@@ -1125,6 +1126,7 @@ static inline bool mlx5_tx_swp_supported(struct mlx5_core_dev *mdev)
 }
 
 extern const struct ethtool_ops mlx5e_ethtool_ops;
+extern const struct mlx5e_profile mlx5e_mgmt_pf_nic_profile;
 
 int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, u32 *mkey);
 int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev, bool create_tises);
@@ -1230,6 +1232,8 @@ netdev_features_t mlx5e_features_check(struct sk_buff *skb,
 				       struct net_device *netdev,
 				       netdev_features_t features);
 int mlx5e_set_features(struct net_device *netdev, netdev_features_t features);
+void mlx5e_nic_set_rx_mode(struct mlx5e_priv *priv);
+
 #ifdef CONFIG_MLX5_ESWITCH
 int mlx5e_set_vf_mac(struct net_device *dev, int vf, u8 *mac);
 int mlx5e_set_vf_rate(struct net_device *dev, int vf, int min_tx_rate, int max_tx_rate);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/mgmt_pf.c b/drivers/net/ethernet/mellanox/mlx5/core/en/mgmt_pf.c
new file mode 100644
index 000000000000..77b5805895b9
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/mgmt_pf.c
@@ -0,0 +1,268 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+// Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+
+#include <linux/kernel.h>
+#include "en/params.h"
+#include "en/health.h"
+#include "lib/eq.h"
+#include "en/dcbnl.h"
+#include "en_accel/ipsec.h"
+#include "en_accel/en_accel.h"
+#include "en/trap.h"
+#include "en/monitor_stats.h"
+#include "en/hv_vhca_stats.h"
+#include "en_rep.h"
+#include "en.h"
+
+static int mgmt_pf_async_event(struct notifier_block *nb, unsigned long event, void *data)
+{
+	struct mlx5e_priv *priv = container_of(nb, struct mlx5e_priv, events_nb);
+	struct mlx5_eqe   *eqe = data;
+
+	if (event != MLX5_EVENT_TYPE_PORT_CHANGE)
+		return NOTIFY_DONE;
+
+	switch (eqe->sub_type) {
+	case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
+	case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
+		queue_work(priv->wq, &priv->update_carrier_work);
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+
+	return NOTIFY_OK;
+}
+
+static void mlx5e_mgmt_pf_enable_async_events(struct mlx5e_priv *priv)
+{
+	priv->events_nb.notifier_call = mgmt_pf_async_event;
+	mlx5_notifier_register(priv->mdev, &priv->events_nb);
+}
+
+static void mlx5e_disable_mgmt_pf_async_events(struct mlx5e_priv *priv)
+{
+	mlx5_notifier_unregister(priv->mdev, &priv->events_nb);
+}
+
+static void mlx5e_modify_mgmt_pf_admin_state(struct mlx5_core_dev *mdev,
+					     enum mlx5_port_status state)
+{
+	struct mlx5_eswitch *esw = mdev->priv.eswitch;
+	int vport_admin_state;
+
+	mlx5_set_port_admin_status(mdev, state);
+
+	if (state == MLX5_PORT_UP)
+		vport_admin_state = MLX5_VPORT_ADMIN_STATE_AUTO;
+	else
+		vport_admin_state = MLX5_VPORT_ADMIN_STATE_DOWN;
+
+	mlx5_eswitch_set_vport_state(esw, MLX5_VPORT_UPLINK, vport_admin_state);
+}
+
+static void mlx5e_build_mgmt_pf_nic_params(struct mlx5e_priv *priv, u16 mtu)
+{
+	struct mlx5e_params *params = &priv->channels.params;
+	struct mlx5_core_dev *mdev = priv->mdev;
+	u8 rx_cq_period_mode;
+
+	params->sw_mtu = mtu;
+	params->hard_mtu = MLX5E_ETH_HARD_MTU;
+	params->num_channels = 1;
+
+	/* SQ */
+	params->log_sq_size = is_kdump_kernel() ?
+		MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE :
+		MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE;
+	MLX5E_SET_PFLAG(params, MLX5E_PFLAG_SKB_TX_MPWQE, mlx5e_tx_mpwqe_supported(mdev));
+
+	MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_NO_CSUM_COMPLETE, false);
+
+	/* RQ */
+	mlx5e_build_rq_params(mdev, params);
+
+	/* CQ moderation params */
+	rx_cq_period_mode = MLX5_CAP_GEN(mdev, cq_period_start_from_cqe) ?
+			MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
+			MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
+	params->rx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
+	params->tx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
+	mlx5e_set_rx_cq_mode_params(params, rx_cq_period_mode);
+	mlx5e_set_tx_cq_mode_params(params, MLX5_CQ_PERIOD_MODE_START_FROM_EQE);
+
+	/* TX inline */
+	mlx5_query_min_inline(mdev, &params->tx_min_inline_mode);
+}
+
+static int mlx5e_mgmt_pf_init(struct mlx5_core_dev *mdev,
+			      struct net_device *netdev)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5e_flow_steering *fs;
+	int err;
+
+	mlx5e_build_mgmt_pf_nic_params(priv, netdev->mtu);
+
+	mlx5e_timestamp_init(priv);
+
+	fs = mlx5e_fs_init(priv->profile, mdev,
+			   !test_bit(MLX5E_STATE_DESTROYING, &priv->state),
+			   priv->dfs_root);
+	if (!fs) {
+		err = -ENOMEM;
+		mlx5_core_err(mdev, "FS initialization failed, %d\n", err);
+		return err;
+	}
+	priv->fs = fs;
+
+	mlx5e_health_create_reporters(priv);
+
+	return 0;
+}
+
+static void mlx5e_mgmt_pf_cleanup(struct mlx5e_priv *priv)
+{
+	mlx5e_health_destroy_reporters(priv);
+	mlx5e_fs_cleanup(priv->fs);
+	priv->fs = NULL;
+}
+
+static int mlx5e_mgmt_pf_init_rx(struct mlx5e_priv *priv)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+	int err;
+
+	priv->rx_res = mlx5e_rx_res_create(mdev, 0, priv->max_nch, priv->drop_rq.rqn,
+					   &priv->channels.params.packet_merge,
+					   priv->channels.params.num_channels);
+	if (!priv->rx_res)
+		return -ENOMEM;
+
+	mlx5e_create_q_counters(priv);
+
+	err = mlx5e_open_drop_rq(priv, &priv->drop_rq);
+	if (err) {
+		mlx5_core_err(mdev, "open drop rq failed, %d\n", err);
+		goto err_destroy_q_counters;
+	}
+
+	err = mlx5e_create_flow_steering(priv->fs, priv->rx_res, priv->profile,
+					 priv->netdev);
+	if (err) {
+		mlx5_core_warn(mdev, "create flow steering failed, %d\n", err);
+		goto err_destroy_rx_res;
+	}
+
+	return 0;
+
+err_destroy_rx_res:
+	mlx5e_rx_res_destroy(priv->rx_res);
+	priv->rx_res = NULL;
+	mlx5e_close_drop_rq(&priv->drop_rq);
+err_destroy_q_counters:
+	mlx5e_destroy_q_counters(priv);
+	return err;
+}
+
+static void mlx5e_mgmt_pf_cleanup_rx(struct mlx5e_priv *priv)
+{
+	mlx5e_destroy_flow_steering(priv->fs, !!(priv->netdev->hw_features & NETIF_F_NTUPLE),
+				    priv->profile);
+	mlx5e_rx_res_destroy(priv->rx_res);
+	priv->rx_res = NULL;
+	mlx5e_close_drop_rq(&priv->drop_rq);
+	mlx5e_destroy_q_counters(priv);
+}
+
+static int mlx5e_mgmt_pf_init_tx(struct mlx5e_priv *priv)
+{
+	return 0;
+}
+
+static void mlx5e_mgmt_pf_cleanup_tx(struct mlx5e_priv *priv)
+{
+}
+
+static void mlx5e_mgmt_pf_enable(struct mlx5e_priv *priv)
+{
+	struct net_device *netdev = priv->netdev;
+	struct mlx5_core_dev *mdev = priv->mdev;
+
+	mlx5e_fs_init_l2_addr(priv->fs, netdev);
+
+	/* Marking the link as currently not needed by the Driver */
+	if (!netif_running(netdev))
+		mlx5e_modify_mgmt_pf_admin_state(mdev, MLX5_PORT_DOWN);
+
+	mlx5e_set_netdev_mtu_boundaries(priv);
+	mlx5e_set_dev_port_mtu(priv);
+
+	mlx5e_mgmt_pf_enable_async_events(priv);
+	if (mlx5e_monitor_counter_supported(priv))
+		mlx5e_monitor_counter_init(priv);
+
+	mlx5e_hv_vhca_stats_create(priv);
+	if (netdev->reg_state != NETREG_REGISTERED)
+		return;
+	mlx5e_dcbnl_init_app(priv);
+
+	mlx5e_nic_set_rx_mode(priv);
+
+	rtnl_lock();
+	if (netif_running(netdev))
+		mlx5e_open(netdev);
+	udp_tunnel_nic_reset_ntf(priv->netdev);
+	netif_device_attach(netdev);
+	rtnl_unlock();
+}
+
+static void mlx5e_mgmt_pf_disable(struct mlx5e_priv *priv)
+{
+	if (priv->netdev->reg_state == NETREG_REGISTERED)
+		mlx5e_dcbnl_delete_app(priv);
+
+	rtnl_lock();
+	if (netif_running(priv->netdev))
+		mlx5e_close(priv->netdev);
+	netif_device_detach(priv->netdev);
+	rtnl_unlock();
+
+	mlx5e_nic_set_rx_mode(priv);
+
+	mlx5e_hv_vhca_stats_destroy(priv);
+	if (mlx5e_monitor_counter_supported(priv))
+		mlx5e_monitor_counter_cleanup(priv);
+
+	mlx5e_disable_mgmt_pf_async_events(priv);
+	mlx5e_ipsec_cleanup(priv);
+}
+
+static int mlx5e_mgmt_pf_update_rx(struct mlx5e_priv *priv)
+{
+	return mlx5e_refresh_tirs(priv, false, false);
+}
+
+static int mlx5e_mgmt_pf_max_nch_limit(struct mlx5_core_dev *mdev)
+{
+	return 1;
+}
+
+const struct mlx5e_profile mlx5e_mgmt_pf_nic_profile = {
+	.init		   = mlx5e_mgmt_pf_init,
+	.cleanup	   = mlx5e_mgmt_pf_cleanup,
+	.init_rx	   = mlx5e_mgmt_pf_init_rx,
+	.cleanup_rx	   = mlx5e_mgmt_pf_cleanup_rx,
+	.init_tx	   = mlx5e_mgmt_pf_init_tx,
+	.cleanup_tx	   = mlx5e_mgmt_pf_cleanup_tx,
+	.enable		   = mlx5e_mgmt_pf_enable,
+	.disable	   = mlx5e_mgmt_pf_disable,
+	.update_rx	   = mlx5e_mgmt_pf_update_rx,
+	.update_stats	   = mlx5e_stats_update_ndo_stats,
+	.update_carrier	   = mlx5e_update_carrier,
+	.rx_handlers       = &mlx5e_rx_handlers_nic,
+	.max_tc		   = 1,
+	.max_nch_limit	   = mlx5e_mgmt_pf_max_nch_limit,
+	.stats_grps	   = mlx5e_nic_stats_grps,
+	.stats_grps_num	   = mlx5e_nic_stats_grps_num
+};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index b8f08d64f66b..40626b6108fb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3799,7 +3799,7 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	stats->tx_errors = stats->tx_aborted_errors + stats->tx_carrier_errors;
 }
 
-static void mlx5e_nic_set_rx_mode(struct mlx5e_priv *priv)
+void mlx5e_nic_set_rx_mode(struct mlx5e_priv *priv)
 {
 	if (mlx5e_is_uplink_rep(priv))
 		return; /* no rx mode for uplink rep */
@@ -5004,6 +5004,15 @@ const struct net_device_ops mlx5e_netdev_ops = {
 #endif
 };
 
+const struct net_device_ops mlx5e_mgmt_netdev_ops = {
+	.ndo_open		= mlx5e_open,
+	.ndo_stop		= mlx5e_close,
+	.ndo_start_xmit		= mlx5e_xmit,
+	.ndo_get_stats64	= mlx5e_get_stats,
+	.ndo_change_mtu		= mlx5e_change_nic_mtu,
+	.ndo_set_rx_mode	= mlx5e_set_rx_mode,
+};
+
 static u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout)
 {
 	int i;
@@ -5143,7 +5152,11 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 
 	SET_NETDEV_DEV(netdev, mdev->device);
 
-	netdev->netdev_ops = &mlx5e_netdev_ops;
+	if (mlx5_core_is_mgmt_pf(mdev))
+		netdev->netdev_ops = &mlx5e_mgmt_netdev_ops;
+	else
+		netdev->netdev_ops = &mlx5e_netdev_ops;
+
 	netdev->xdp_metadata_ops = &mlx5e_xdp_metadata_ops;
 	netdev->xsk_tx_metadata_ops = &mlx5e_xsk_tx_metadata_ops;
 
@@ -6094,13 +6107,18 @@ static int mlx5e_suspend(struct auxiliary_device *adev, pm_message_t state)
 static int _mlx5e_probe(struct auxiliary_device *adev)
 {
 	struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev);
-	const struct mlx5e_profile *profile = &mlx5e_nic_profile;
 	struct mlx5_core_dev *mdev = edev->mdev;
+	const struct mlx5e_profile *profile;
 	struct mlx5e_dev *mlx5e_dev;
 	struct net_device *netdev;
 	struct mlx5e_priv *priv;
 	int err;
 
+	if (mlx5_core_is_mgmt_pf(mdev))
+		profile = &mlx5e_mgmt_pf_nic_profile;
+	else
+		profile = &mlx5e_nic_profile;
+
 	mlx5e_dev = mlx5e_create_devlink(&adev->dev, mdev);
 	if (IS_ERR(mlx5e_dev))
 		return PTR_ERR(mlx5e_dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 3047d7015c52..3bf419d06d53 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1665,7 +1665,7 @@ int mlx5_esw_sf_max_hpf_functions(struct mlx5_core_dev *dev, u16 *max_sfs, u16 *
 	void *hca_caps;
 	int err;
 
-	if (!mlx5_core_is_ecpf(dev)) {
+	if (!mlx5_core_is_ecpf(dev) || mlx5_core_is_mgmt_pf(dev)) {
 		*max_sfs = 0;
 		return 0;
 	}
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index cd286b681970..2bba88c67f58 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1224,6 +1224,14 @@ static inline bool mlx5_core_is_ecpf(const struct mlx5_core_dev *dev)
 	return dev->caps.embedded_cpu;
 }
 
+static inline bool mlx5_core_is_mgmt_pf(const struct mlx5_core_dev *dev)
+{
+	if (!MLX5_CAP_GEN_2(dev, local_mng_port_valid))
+		return false;
+
+	return MLX5_CAP_GEN_2(dev, local_mng_port);
+}
+
 static inline bool
 mlx5_core_is_ecpf_esw_manager(const struct mlx5_core_dev *dev)
 {
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index bf2d51952e48..586569209254 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1954,8 +1954,10 @@ enum {
 struct mlx5_ifc_cmd_hca_cap_2_bits {
 	u8	   reserved_at_0[0x80];
 
-	u8         migratable[0x1];
-	u8         reserved_at_81[0x1f];
+	u8	   migratable[0x1];
+	u8	   reserved_at_81[0x19];
+	u8	   local_mng_port[0x1];
+	u8	   reserved_at_9b[0x5];
 
 	u8	   max_reformat_insert_size[0x8];
 	u8	   max_reformat_insert_offset[0x8];
@@ -1973,7 +1975,13 @@ struct mlx5_ifc_cmd_hca_cap_2_bits {
 
 	u8	   allowed_object_for_other_vhca_access[0x40];
 
-	u8	   reserved_at_140[0x60];
+	u8	   reserved_at_140[0x20];
+
+	u8	   reserved_at_160[0xa];
+	u8	   local_mng_port_valid[0x1];
+	u8	   reserved_at_16b[0x15];
+
+	u8	   reserved_at_180[0x20];
 
 	u8	   flow_table_type_2_type[0x8];
 	u8	   reserved_at_1a8[0x3];
-- 
cgit v1.2.3


From dade3f6a1e4e35a5ae916d5e78b3229ec34c78ec Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@kernel.org>
Date: Mon, 18 Dec 2023 20:02:43 -0700
Subject: net/ipv6: Revert remove expired routes with a separated list of
 routes

This reverts commit 3dec89b14d37ee635e772636dad3f09f78f1ab87.

The commit has some race conditions given how expires is managed on a
fib6_info in relation to gc start, adding the entry to the gc list and
setting the timer value leading to UAF. Revert the commit and try again
in a later release.

Fixes: 3dec89b14d37 ("net/ipv6: Remove expired routes with a separated list of routes")
Cc: Kui-Feng Lee <thinker.li@gmail.com>
Signed-off-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20231219030243.25687-1-dsahern@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/ip6_fib.h | 64 +++++++++++----------------------------------------
 net/ipv6/ip6_fib.c    | 55 +++++--------------------------------------
 net/ipv6/route.c      |  6 ++---
 3 files changed, 22 insertions(+), 103 deletions(-)

(limited to 'include')

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 1ba9f4ddf2f6..9ba6413fd2e3 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -179,9 +179,6 @@ struct fib6_info {
 
 	refcount_t			fib6_ref;
 	unsigned long			expires;
-
-	struct hlist_node		gc_link;
-
 	struct dst_metrics		*fib6_metrics;
 #define fib6_pmtu		fib6_metrics->metrics[RTAX_MTU-1]
 
@@ -250,6 +247,19 @@ static inline bool fib6_requires_src(const struct fib6_info *rt)
 	return rt->fib6_src.plen > 0;
 }
 
+static inline void fib6_clean_expires(struct fib6_info *f6i)
+{
+	f6i->fib6_flags &= ~RTF_EXPIRES;
+	f6i->expires = 0;
+}
+
+static inline void fib6_set_expires(struct fib6_info *f6i,
+				    unsigned long expires)
+{
+	f6i->expires = expires;
+	f6i->fib6_flags |= RTF_EXPIRES;
+}
+
 static inline bool fib6_check_expired(const struct fib6_info *f6i)
 {
 	if (f6i->fib6_flags & RTF_EXPIRES)
@@ -257,11 +267,6 @@ static inline bool fib6_check_expired(const struct fib6_info *f6i)
 	return false;
 }
 
-static inline bool fib6_has_expires(const struct fib6_info *f6i)
-{
-	return f6i->fib6_flags & RTF_EXPIRES;
-}
-
 /* Function to safely get fn->fn_sernum for passed in rt
  * and store result in passed in cookie.
  * Return true if we can get cookie safely
@@ -383,7 +388,6 @@ struct fib6_table {
 	struct inet_peer_base	tb6_peers;
 	unsigned int		flags;
 	unsigned int		fib_seq;
-	struct hlist_head       tb6_gc_hlist;	/* GC candidates */
 #define RT6_TABLE_HAS_DFLT_ROUTER	BIT(0)
 };
 
@@ -500,48 +504,6 @@ void fib6_gc_cleanup(void);
 
 int fib6_init(void);
 
-/* fib6_info must be locked by the caller, and fib6_info->fib6_table can be
- * NULL.
- */
-static inline void fib6_set_expires_locked(struct fib6_info *f6i,
-					   unsigned long expires)
-{
-	struct fib6_table *tb6;
-
-	tb6 = f6i->fib6_table;
-	f6i->expires = expires;
-	if (tb6 && !fib6_has_expires(f6i))
-		hlist_add_head(&f6i->gc_link, &tb6->tb6_gc_hlist);
-	f6i->fib6_flags |= RTF_EXPIRES;
-}
-
-/* fib6_info must be locked by the caller, and fib6_info->fib6_table can be
- * NULL.  If fib6_table is NULL, the fib6_info will no be inserted into the
- * list of GC candidates until it is inserted into a table.
- */
-static inline void fib6_set_expires(struct fib6_info *f6i,
-				    unsigned long expires)
-{
-	spin_lock_bh(&f6i->fib6_table->tb6_lock);
-	fib6_set_expires_locked(f6i, expires);
-	spin_unlock_bh(&f6i->fib6_table->tb6_lock);
-}
-
-static inline void fib6_clean_expires_locked(struct fib6_info *f6i)
-{
-	if (fib6_has_expires(f6i))
-		hlist_del_init(&f6i->gc_link);
-	f6i->fib6_flags &= ~RTF_EXPIRES;
-	f6i->expires = 0;
-}
-
-static inline void fib6_clean_expires(struct fib6_info *f6i)
-{
-	spin_lock_bh(&f6i->fib6_table->tb6_lock);
-	fib6_clean_expires_locked(f6i);
-	spin_unlock_bh(&f6i->fib6_table->tb6_lock);
-}
-
 struct ipv6_route_iter {
 	struct seq_net_private p;
 	struct fib6_walker w;
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 7772f42ff2b9..4fc2cae0d116 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -160,8 +160,6 @@ struct fib6_info *fib6_info_alloc(gfp_t gfp_flags, bool with_fib6_nh)
 	INIT_LIST_HEAD(&f6i->fib6_siblings);
 	refcount_set(&f6i->fib6_ref, 1);
 
-	INIT_HLIST_NODE(&f6i->gc_link);
-
 	return f6i;
 }
 
@@ -248,7 +246,6 @@ static struct fib6_table *fib6_alloc_table(struct net *net, u32 id)
 				   net->ipv6.fib6_null_entry);
 		table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
 		inet_peer_base_init(&table->tb6_peers);
-		INIT_HLIST_HEAD(&table->tb6_gc_hlist);
 	}
 
 	return table;
@@ -1060,8 +1057,6 @@ static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn,
 				    lockdep_is_held(&table->tb6_lock));
 		}
 	}
-
-	fib6_clean_expires_locked(rt);
 }
 
 /*
@@ -1123,10 +1118,9 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
 				if (!(iter->fib6_flags & RTF_EXPIRES))
 					return -EEXIST;
 				if (!(rt->fib6_flags & RTF_EXPIRES))
-					fib6_clean_expires_locked(iter);
+					fib6_clean_expires(iter);
 				else
-					fib6_set_expires_locked(iter,
-								rt->expires);
+					fib6_set_expires(iter, rt->expires);
 
 				if (rt->fib6_pmtu)
 					fib6_metric_set(iter, RTAX_MTU,
@@ -1485,10 +1479,6 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt,
 		if (rt->nh)
 			list_add(&rt->nh_list, &rt->nh->f6i_list);
 		__fib6_update_sernum_upto_root(rt, fib6_new_sernum(info->nl_net));
-
-		if (fib6_has_expires(rt))
-			hlist_add_head(&rt->gc_link, &table->tb6_gc_hlist);
-
 		fib6_start_gc(info->nl_net, rt);
 	}
 
@@ -2291,8 +2281,9 @@ static void fib6_flush_trees(struct net *net)
  *	Garbage collection
  */
 
-static int fib6_age(struct fib6_info *rt, struct fib6_gc_args *gc_args)
+static int fib6_age(struct fib6_info *rt, void *arg)
 {
+	struct fib6_gc_args *gc_args = arg;
 	unsigned long now = jiffies;
 
 	/*
@@ -2300,7 +2291,7 @@ static int fib6_age(struct fib6_info *rt, struct fib6_gc_args *gc_args)
 	 *	Routes are expired even if they are in use.
 	 */
 
-	if (fib6_has_expires(rt) && rt->expires) {
+	if (rt->fib6_flags & RTF_EXPIRES && rt->expires) {
 		if (time_after(now, rt->expires)) {
 			RT6_TRACE("expiring %p\n", rt);
 			return -1;
@@ -2317,40 +2308,6 @@ static int fib6_age(struct fib6_info *rt, struct fib6_gc_args *gc_args)
 	return 0;
 }
 
-static void fib6_gc_table(struct net *net,
-			  struct fib6_table *tb6,
-			  struct fib6_gc_args *gc_args)
-{
-	struct fib6_info *rt;
-	struct hlist_node *n;
-	struct nl_info info = {
-		.nl_net = net,
-		.skip_notify = false,
-	};
-
-	hlist_for_each_entry_safe(rt, n, &tb6->tb6_gc_hlist, gc_link)
-		if (fib6_age(rt, gc_args) == -1)
-			fib6_del(rt, &info);
-}
-
-static void fib6_gc_all(struct net *net, struct fib6_gc_args *gc_args)
-{
-	struct fib6_table *table;
-	struct hlist_head *head;
-	unsigned int h;
-
-	rcu_read_lock();
-	for (h = 0; h < FIB6_TABLE_HASHSZ; h++) {
-		head = &net->ipv6.fib_table_hash[h];
-		hlist_for_each_entry_rcu(table, head, tb6_hlist) {
-			spin_lock_bh(&table->tb6_lock);
-			fib6_gc_table(net, table, gc_args);
-			spin_unlock_bh(&table->tb6_lock);
-		}
-	}
-	rcu_read_unlock();
-}
-
 void fib6_run_gc(unsigned long expires, struct net *net, bool force)
 {
 	struct fib6_gc_args gc_args;
@@ -2366,7 +2323,7 @@ void fib6_run_gc(unsigned long expires, struct net *net, bool force)
 			  net->ipv6.sysctl.ip6_rt_gc_interval;
 	gc_args.more = 0;
 
-	fib6_gc_all(net, &gc_args);
+	fib6_clean_all(net, fib6_age, &gc_args);
 	now = jiffies;
 	net->ipv6.ip6_rt_last_gc = now;
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index b132feae3393..ea1dec8448fc 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3763,10 +3763,10 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 		rt->dst_nocount = true;
 
 	if (cfg->fc_flags & RTF_EXPIRES)
-		fib6_set_expires_locked(rt, jiffies +
-					clock_t_to_jiffies(cfg->fc_expires));
+		fib6_set_expires(rt, jiffies +
+				clock_t_to_jiffies(cfg->fc_expires));
 	else
-		fib6_clean_expires_locked(rt);
+		fib6_clean_expires(rt);
 
 	if (cfg->fc_protocol == RTPROT_UNSPEC)
 		cfg->fc_protocol = RTPROT_BOOT;
-- 
cgit v1.2.3


From ee9ec49046951eff704752669f0c388b506ddbdf Mon Sep 17 00:00:00 2001
From: Paul Cercueil <paul@crapouillou.net>
Date: Tue, 19 Dec 2023 18:50:02 +0100
Subject: iio: buffer-dma: Get rid of outgoing queue

The buffer-dma code was using two queues, incoming and outgoing, to
manage the state of the blocks in use.

While this totally works, it adds some complexity to the code,
especially since the code only manages 2 blocks. It is much easier to
just check each block's state manually, and keep a counter for the next
block to dequeue.

Since the new DMABUF based API wouldn't use the outgoing queue anyway,
getting rid of it now makes the upcoming changes simpler.

With this change, the IIO_BLOCK_STATE_DEQUEUED is now useless, and can
be removed.

Signed-off-by: Paul Cercueil <paul@crapouillou.net>
Link: https://lore.kernel.org/r/20231219175009.65482-2-paul@crapouillou.net
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/buffer/industrialio-buffer-dma.c | 44 +++++++++++++++-------------
 include/linux/iio/buffer-dma.h               |  7 ++---
 2 files changed, 26 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/drivers/iio/buffer/industrialio-buffer-dma.c b/drivers/iio/buffer/industrialio-buffer-dma.c
index d348af8b9705..1fc91467d1aa 100644
--- a/drivers/iio/buffer/industrialio-buffer-dma.c
+++ b/drivers/iio/buffer/industrialio-buffer-dma.c
@@ -179,7 +179,7 @@ static struct iio_dma_buffer_block *iio_dma_buffer_alloc_block(
 	}
 
 	block->size = size;
-	block->state = IIO_BLOCK_STATE_DEQUEUED;
+	block->state = IIO_BLOCK_STATE_DONE;
 	block->queue = queue;
 	INIT_LIST_HEAD(&block->head);
 	kref_init(&block->kref);
@@ -191,16 +191,8 @@ static struct iio_dma_buffer_block *iio_dma_buffer_alloc_block(
 
 static void _iio_dma_buffer_block_done(struct iio_dma_buffer_block *block)
 {
-	struct iio_dma_buffer_queue *queue = block->queue;
-
-	/*
-	 * The buffer has already been freed by the application, just drop the
-	 * reference.
-	 */
-	if (block->state != IIO_BLOCK_STATE_DEAD) {
+	if (block->state != IIO_BLOCK_STATE_DEAD)
 		block->state = IIO_BLOCK_STATE_DONE;
-		list_add_tail(&block->head, &queue->outgoing);
-	}
 }
 
 /**
@@ -261,7 +253,6 @@ static bool iio_dma_block_reusable(struct iio_dma_buffer_block *block)
 	 * not support abort and has not given back the block yet.
 	 */
 	switch (block->state) {
-	case IIO_BLOCK_STATE_DEQUEUED:
 	case IIO_BLOCK_STATE_QUEUED:
 	case IIO_BLOCK_STATE_DONE:
 		return true;
@@ -317,7 +308,6 @@ int iio_dma_buffer_request_update(struct iio_buffer *buffer)
 	 * dead. This means we can reset the lists without having to fear
 	 * corrution.
 	 */
-	INIT_LIST_HEAD(&queue->outgoing);
 	spin_unlock_irq(&queue->list_lock);
 
 	INIT_LIST_HEAD(&queue->incoming);
@@ -456,14 +446,20 @@ static struct iio_dma_buffer_block *iio_dma_buffer_dequeue(
 	struct iio_dma_buffer_queue *queue)
 {
 	struct iio_dma_buffer_block *block;
+	unsigned int idx;
 
 	spin_lock_irq(&queue->list_lock);
-	block = list_first_entry_or_null(&queue->outgoing, struct
-		iio_dma_buffer_block, head);
-	if (block != NULL) {
-		list_del(&block->head);
-		block->state = IIO_BLOCK_STATE_DEQUEUED;
+
+	idx = queue->fileio.next_dequeue;
+	block = queue->fileio.blocks[idx];
+
+	if (block->state == IIO_BLOCK_STATE_DONE) {
+		idx = (idx + 1) % ARRAY_SIZE(queue->fileio.blocks);
+		queue->fileio.next_dequeue = idx;
+	} else {
+		block = NULL;
 	}
+
 	spin_unlock_irq(&queue->list_lock);
 
 	return block;
@@ -539,6 +535,7 @@ size_t iio_dma_buffer_data_available(struct iio_buffer *buf)
 	struct iio_dma_buffer_queue *queue = iio_buffer_to_queue(buf);
 	struct iio_dma_buffer_block *block;
 	size_t data_available = 0;
+	unsigned int i;
 
 	/*
 	 * For counting the available bytes we'll use the size of the block not
@@ -552,8 +549,15 @@ size_t iio_dma_buffer_data_available(struct iio_buffer *buf)
 		data_available += queue->fileio.active_block->size;
 
 	spin_lock_irq(&queue->list_lock);
-	list_for_each_entry(block, &queue->outgoing, head)
-		data_available += block->size;
+
+	for (i = 0; i < ARRAY_SIZE(queue->fileio.blocks); i++) {
+		block = queue->fileio.blocks[i];
+
+		if (block != queue->fileio.active_block
+		    && block->state == IIO_BLOCK_STATE_DONE)
+			data_available += block->size;
+	}
+
 	spin_unlock_irq(&queue->list_lock);
 	mutex_unlock(&queue->lock);
 
@@ -617,7 +621,6 @@ int iio_dma_buffer_init(struct iio_dma_buffer_queue *queue,
 	queue->ops = ops;
 
 	INIT_LIST_HEAD(&queue->incoming);
-	INIT_LIST_HEAD(&queue->outgoing);
 
 	mutex_init(&queue->lock);
 	spin_lock_init(&queue->list_lock);
@@ -645,7 +648,6 @@ void iio_dma_buffer_exit(struct iio_dma_buffer_queue *queue)
 			continue;
 		queue->fileio.blocks[i]->state = IIO_BLOCK_STATE_DEAD;
 	}
-	INIT_LIST_HEAD(&queue->outgoing);
 	spin_unlock_irq(&queue->list_lock);
 
 	INIT_LIST_HEAD(&queue->incoming);
diff --git a/include/linux/iio/buffer-dma.h b/include/linux/iio/buffer-dma.h
index 6564bdcdac66..18d3702fa95d 100644
--- a/include/linux/iio/buffer-dma.h
+++ b/include/linux/iio/buffer-dma.h
@@ -19,14 +19,12 @@ struct device;
 
 /**
  * enum iio_block_state - State of a struct iio_dma_buffer_block
- * @IIO_BLOCK_STATE_DEQUEUED: Block is not queued
  * @IIO_BLOCK_STATE_QUEUED: Block is on the incoming queue
  * @IIO_BLOCK_STATE_ACTIVE: Block is currently being processed by the DMA
  * @IIO_BLOCK_STATE_DONE: Block is on the outgoing queue
  * @IIO_BLOCK_STATE_DEAD: Block has been marked as to be freed
  */
 enum iio_block_state {
-	IIO_BLOCK_STATE_DEQUEUED,
 	IIO_BLOCK_STATE_QUEUED,
 	IIO_BLOCK_STATE_ACTIVE,
 	IIO_BLOCK_STATE_DONE,
@@ -73,12 +71,15 @@ struct iio_dma_buffer_block {
  * @active_block: Block being used in read()
  * @pos: Read offset in the active block
  * @block_size: Size of each block
+ * @next_dequeue: index of next block that will be dequeued
  */
 struct iio_dma_buffer_queue_fileio {
 	struct iio_dma_buffer_block *blocks[2];
 	struct iio_dma_buffer_block *active_block;
 	size_t pos;
 	size_t block_size;
+
+	unsigned int next_dequeue;
 };
 
 /**
@@ -93,7 +94,6 @@ struct iio_dma_buffer_queue_fileio {
  *   list and typically also a list of active blocks in the part that handles
  *   the DMA controller
  * @incoming: List of buffers on the incoming queue
- * @outgoing: List of buffers on the outgoing queue
  * @active: Whether the buffer is currently active
  * @fileio: FileIO state
  */
@@ -105,7 +105,6 @@ struct iio_dma_buffer_queue {
 	struct mutex lock;
 	spinlock_t list_lock;
 	struct list_head incoming;
-	struct list_head outgoing;
 
 	bool active;
 
-- 
cgit v1.2.3


From 3efdc78fdc21ab82694707eb234ab93f28d13ba8 Mon Sep 17 00:00:00 2001
From: Andrei Vagin <avagin@google.com>
Date: Wed, 13 Dec 2023 22:44:38 -0800
Subject: fs/proc: show correct device and inode numbers in /proc/pid/maps

/proc/pid/maps shows device and inode numbers of vma->vm_file-s. Here is
an issue. If a mapped file is on a stackable file system (e.g.,
overlayfs), vma->vm_file is a backing file whose f_inode is on the
underlying filesystem. To show correct numbers, we need to get a user
file and shows its numbers. The same trick is used to show file paths in
/proc/pid/maps.

Cc: Alexander Mikhalitsyn <alexander@mihalicyn.com>
Suggested-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Andrei Vagin <avagin@google.com>
Link: https://lore.kernel.org/r/20231214064439.1023011-1-avagin@google.com
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/proc/task_mmu.c |  3 ++-
 include/linux/fs.h | 18 +++++++++++++-----
 2 files changed, 15 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index ef2eb12906da..5de0f70e52ff 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -273,7 +273,8 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
 	const char *name = NULL;
 
 	if (file) {
-		struct inode *inode = file_inode(vma->vm_file);
+		const struct inode *inode = file_user_inode(vma->vm_file);
+
 		dev = inode->i_sb->s_dev;
 		ino = inode->i_ino;
 		pgoff = ((loff_t)vma->vm_pgoff) << PAGE_SHIFT;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index f171505940ff..a3a48a5d8728 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2523,20 +2523,28 @@ struct file *backing_file_open(const struct path *user_path, int flags,
 struct path *backing_file_user_path(struct file *f);
 
 /*
- * file_user_path - get the path to display for memory mapped file
- *
  * When mmapping a file on a stackable filesystem (e.g., overlayfs), the file
  * stored in ->vm_file is a backing file whose f_inode is on the underlying
- * filesystem.  When the mapped file path is displayed to user (e.g. via
- * /proc/<pid>/maps), this helper should be used to get the path to display
- * to the user, which is the path of the fd that user has requested to map.
+ * filesystem.  When the mapped file path and inode number are displayed to
+ * user (e.g. via /proc/<pid>/maps), these helpers should be used to get the
+ * path and inode number to display to the user, which is the path of the fd
+ * that user has requested to map and the inode number that would be returned
+ * by fstat() on that same fd.
  */
+/* Get the path to display in /proc/<pid>/maps */
 static inline const struct path *file_user_path(struct file *f)
 {
 	if (unlikely(f->f_mode & FMODE_BACKING))
 		return backing_file_user_path(f);
 	return &f->f_path;
 }
+/* Get the inode whose inode number to display in /proc/<pid>/maps */
+static inline const struct inode *file_user_inode(struct file *f)
+{
+	if (unlikely(f->f_mode & FMODE_BACKING))
+		return d_inode(backing_file_user_path(f)->dentry);
+	return file_inode(f);
+}
 
 static inline struct file *file_clone_open(struct file *file)
 {
-- 
cgit v1.2.3


From 5ae81209491ed3718fee798db6fb2cc81214824c Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 19 Dec 2023 14:52:36 +0100
Subject: driver core: bus: make bus_sort_breadthfirst() take a const pointer

For some reason, during the big "clean up the driver core for a const
struct bus_type" work, the bus_sort_breadthfirst() call was missed.  Fix
this up by changing the type to be a const * as it should be.

Cc: Rafael J. Wysocki <rafael@kernel.org>
Link: https://lore.kernel.org/r/2023121935-stinking-ditzy-fd5d@gregkh
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/bus.c         | 2 +-
 include/linux/device/bus.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/base/bus.c b/drivers/base/bus.c
index 84a21084d67d..33d952695927 100644
--- a/drivers/base/bus.c
+++ b/drivers/base/bus.c
@@ -1030,7 +1030,7 @@ static void device_insertion_sort_klist(struct device *a, struct list_head *list
 	list_move_tail(&a->p->knode_bus.n_node, list);
 }
 
-void bus_sort_breadthfirst(struct bus_type *bus,
+void bus_sort_breadthfirst(const struct bus_type *bus,
 			   int (*compare)(const struct device *a,
 					  const struct device *b))
 {
diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h
index ae10c4322754..25127f750349 100644
--- a/include/linux/device/bus.h
+++ b/include/linux/device/bus.h
@@ -232,7 +232,7 @@ bus_find_device_by_acpi_dev(const struct bus_type *bus, const void *adev)
 
 int bus_for_each_drv(const struct bus_type *bus, struct device_driver *start,
 		     void *data, int (*fn)(struct device_driver *, void *));
-void bus_sort_breadthfirst(struct bus_type *bus,
+void bus_sort_breadthfirst(const struct bus_type *bus,
 			   int (*compare)(const struct device *a,
 					  const struct device *b));
 /*
-- 
cgit v1.2.3


From 32f78abe59c740b6ec34c89dc10a09208eae7e1f Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 19 Dec 2023 14:15:09 +0100
Subject: driver core: bus: constantify subsys_register() calls

The functions subsys_register() and subsys_virtual_register() should be
taking a constant pointer to a struct bus_type, as they do not actually
modify anything in it, so fix up the function definitions to do so
properly.

This also changes the pointer type in struct subsys_interface to be
constant as well, as again, that's the proper signature of it.

Cc: Rafael J. Wysocki <rafael@kernel.org>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/2023121908-grove-genetics-f8af@gregkh
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/bus.c     | 6 +++---
 include/linux/device.h | 6 +++---
 2 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/base/bus.c b/drivers/base/bus.c
index 33d952695927..daee55c9b2d9 100644
--- a/drivers/base/bus.c
+++ b/drivers/base/bus.c
@@ -1194,7 +1194,7 @@ static void system_root_device_release(struct device *dev)
 	kfree(dev);
 }
 
-static int subsys_register(struct bus_type *subsys,
+static int subsys_register(const struct bus_type *subsys,
 			   const struct attribute_group **groups,
 			   struct kobject *parent_of_root)
 {
@@ -1264,7 +1264,7 @@ err_sp:
  * directory itself and not some create fake root-device placed in
  * /sys/devices/system/<name>.
  */
-int subsys_system_register(struct bus_type *subsys,
+int subsys_system_register(const struct bus_type *subsys,
 			   const struct attribute_group **groups)
 {
 	return subsys_register(subsys, groups, &system_kset->kobj);
@@ -1282,7 +1282,7 @@ EXPORT_SYMBOL_GPL(subsys_system_register);
  * There's no restriction on device naming.  This is for kernel software
  * constructs which need sysfs interface.
  */
-int subsys_virtual_register(struct bus_type *subsys,
+int subsys_virtual_register(const struct bus_type *subsys,
 			    const struct attribute_group **groups)
 {
 	struct kobject *virtual_dir;
diff --git a/include/linux/device.h b/include/linux/device.h
index 4aa34c8d1361..aefc5ca7f1cf 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -63,7 +63,7 @@ struct msi_device_data;
  */
 struct subsys_interface {
 	const char *name;
-	struct bus_type *subsys;
+	const struct bus_type *subsys;
 	struct list_head node;
 	int (*add_dev)(struct device *dev, struct subsys_interface *sif);
 	void (*remove_dev)(struct device *dev, struct subsys_interface *sif);
@@ -72,9 +72,9 @@ struct subsys_interface {
 int subsys_interface_register(struct subsys_interface *sif);
 void subsys_interface_unregister(struct subsys_interface *sif);
 
-int subsys_system_register(struct bus_type *subsys,
+int subsys_system_register(const struct bus_type *subsys,
 			   const struct attribute_group **groups);
-int subsys_virtual_register(struct bus_type *subsys,
+int subsys_virtual_register(const struct bus_type *subsys,
 			    const struct attribute_group **groups);
 
 /*
-- 
cgit v1.2.3


From dedb868994d8308c6c4650203e190ec619005806 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 19 Dec 2023 16:03:20 +0100
Subject: driver core: container: make container_subsys const

Now that the driver core can properly handle constant struct bus_type,
move the container_subsys variable to be a constant structure as well,
placing it into read-only memory which can not be modified at runtime.

Cc: "Rafael J. Wysocki" <rafael@kernel.org>
Link: https://lore.kernel.org/r/2023121919-chatter-grumbling-9ef3@gregkh
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/container.c  | 2 +-
 include/linux/container.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/base/container.c b/drivers/base/container.c
index 1ba42d2d3532..f40588ebc3f5 100644
--- a/drivers/base/container.c
+++ b/drivers/base/container.c
@@ -24,7 +24,7 @@ static int container_offline(struct device *dev)
 	return cdev->offline ? cdev->offline(cdev) : 0;
 }
 
-struct bus_type container_subsys = {
+const struct bus_type container_subsys = {
 	.name = CONTAINER_BUS_NAME,
 	.dev_name = CONTAINER_BUS_NAME,
 	.online = trivial_online,
diff --git a/include/linux/container.h b/include/linux/container.h
index 2566a1baa736..dd00cc918a92 100644
--- a/include/linux/container.h
+++ b/include/linux/container.h
@@ -12,7 +12,7 @@
 #include <linux/device.h>
 
 /* drivers/base/power/container.c */
-extern struct bus_type container_subsys;
+extern const struct bus_type container_subsys;
 
 struct container_dev {
 	struct device dev;
-- 
cgit v1.2.3


From 39299bdd2546688d92ed9db4948f6219ca1b9542 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Sat, 9 Dec 2023 00:41:55 +0000
Subject: keys, dns: Allow key types (eg. DNS) to be reclaimed immediately on
 expiry

If a key has an expiration time, then when that time passes, the key is
left around for a certain amount of time before being collected (5 mins by
default) so that EKEYEXPIRED can be returned instead of ENOKEY.  This is a
problem for DNS keys because we want to redo the DNS lookup immediately at
that point.

Fix this by allowing key types to be marked such that keys of that type
don't have this extra period, but are reclaimed as soon as they expire and
turn this on for dns_resolver-type keys.  To make this easier to handle,
key->expiry is changed to be permanent if TIME64_MAX rather than 0.

Furthermore, give such new-style negative DNS results a 1s default expiry
if no other expiry time is set rather than allowing it to stick around
indefinitely.  This shouldn't be zero as ls will follow a failing stat call
immediately with a second with AT_SYMLINK_NOFOLLOW added.

Fixes: 1a4240f4764a ("DNS: Separate out CIFS DNS Resolver code")
Signed-off-by: David Howells <dhowells@redhat.com>
Tested-by: Markus Suvanto <markus.suvanto@gmail.com>
cc: Wang Lei <wang840925@gmail.com>
cc: Jeff Layton <jlayton@redhat.com>
cc: Steve French <smfrench@gmail.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Jarkko Sakkinen <jarkko@kernel.org>
cc: "David S. Miller" <davem@davemloft.net>
cc: Eric Dumazet <edumazet@google.com>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: linux-afs@lists.infradead.org
cc: linux-cifs@vger.kernel.org
cc: linux-nfs@vger.kernel.org
cc: ceph-devel@vger.kernel.org
cc: keyrings@vger.kernel.org
cc: netdev@vger.kernel.org
---
 include/linux/key-type.h   |  1 +
 net/dns_resolver/dns_key.c | 10 +++++++++-
 security/keys/gc.c         | 31 +++++++++++++++++++++----------
 security/keys/internal.h   | 11 ++++++++++-
 security/keys/key.c        | 15 +++++----------
 security/keys/proc.c       |  2 +-
 6 files changed, 47 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/linux/key-type.h b/include/linux/key-type.h
index 7d985a1dfe4a..5caf3ce82373 100644
--- a/include/linux/key-type.h
+++ b/include/linux/key-type.h
@@ -73,6 +73,7 @@ struct key_type {
 
 	unsigned int flags;
 #define KEY_TYPE_NET_DOMAIN	0x00000001 /* Keys of this type have a net namespace domain */
+#define KEY_TYPE_INSTANT_REAP	0x00000002 /* Keys of this type don't have a delay after expiring */
 
 	/* vet a description */
 	int (*vet_description)(const char *description);
diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c
index 01e54b46ae0b..2a6d363763a2 100644
--- a/net/dns_resolver/dns_key.c
+++ b/net/dns_resolver/dns_key.c
@@ -91,6 +91,7 @@ const struct cred *dns_resolver_cache;
 static int
 dns_resolver_preparse(struct key_preparsed_payload *prep)
 {
+	const struct dns_server_list_v1_header *v1;
 	const struct dns_payload_header *bin;
 	struct user_key_payload *upayload;
 	unsigned long derrno;
@@ -122,6 +123,13 @@ dns_resolver_preparse(struct key_preparsed_payload *prep)
 			return -EINVAL;
 		}
 
+		v1 = (const struct dns_server_list_v1_header *)bin;
+		if ((v1->status != DNS_LOOKUP_GOOD &&
+		     v1->status != DNS_LOOKUP_GOOD_WITH_BAD)) {
+			if (prep->expiry == TIME64_MAX)
+				prep->expiry = ktime_get_real_seconds() + 1;
+		}
+
 		result_len = datalen;
 		goto store_result;
 	}
@@ -314,7 +322,7 @@ static long dns_resolver_read(const struct key *key,
 
 struct key_type key_type_dns_resolver = {
 	.name		= "dns_resolver",
-	.flags		= KEY_TYPE_NET_DOMAIN,
+	.flags		= KEY_TYPE_NET_DOMAIN | KEY_TYPE_INSTANT_REAP,
 	.preparse	= dns_resolver_preparse,
 	.free_preparse	= dns_resolver_free_preparse,
 	.instantiate	= generic_key_instantiate,
diff --git a/security/keys/gc.c b/security/keys/gc.c
index 3c90807476eb..eaddaceda14e 100644
--- a/security/keys/gc.c
+++ b/security/keys/gc.c
@@ -66,6 +66,19 @@ void key_schedule_gc(time64_t gc_at)
 	}
 }
 
+/*
+ * Set the expiration time on a key.
+ */
+void key_set_expiry(struct key *key, time64_t expiry)
+{
+	key->expiry = expiry;
+	if (expiry != TIME64_MAX) {
+		if (!(key->type->flags & KEY_TYPE_INSTANT_REAP))
+			expiry += key_gc_delay;
+		key_schedule_gc(expiry);
+	}
+}
+
 /*
  * Schedule a dead links collection run.
  */
@@ -176,7 +189,6 @@ static void key_garbage_collector(struct work_struct *work)
 	static u8 gc_state;		/* Internal persistent state */
 #define KEY_GC_REAP_AGAIN	0x01	/* - Need another cycle */
 #define KEY_GC_REAPING_LINKS	0x02	/* - We need to reap links */
-#define KEY_GC_SET_TIMER	0x04	/* - We need to restart the timer */
 #define KEY_GC_REAPING_DEAD_1	0x10	/* - We need to mark dead keys */
 #define KEY_GC_REAPING_DEAD_2	0x20	/* - We need to reap dead key links */
 #define KEY_GC_REAPING_DEAD_3	0x40	/* - We need to reap dead keys */
@@ -184,21 +196,17 @@ static void key_garbage_collector(struct work_struct *work)
 
 	struct rb_node *cursor;
 	struct key *key;
-	time64_t new_timer, limit;
+	time64_t new_timer, limit, expiry;
 
 	kenter("[%lx,%x]", key_gc_flags, gc_state);
 
 	limit = ktime_get_real_seconds();
-	if (limit > key_gc_delay)
-		limit -= key_gc_delay;
-	else
-		limit = key_gc_delay;
 
 	/* Work out what we're going to be doing in this pass */
 	gc_state &= KEY_GC_REAPING_DEAD_1 | KEY_GC_REAPING_DEAD_2;
 	gc_state <<= 1;
 	if (test_and_clear_bit(KEY_GC_KEY_EXPIRED, &key_gc_flags))
-		gc_state |= KEY_GC_REAPING_LINKS | KEY_GC_SET_TIMER;
+		gc_state |= KEY_GC_REAPING_LINKS;
 
 	if (test_and_clear_bit(KEY_GC_REAP_KEYTYPE, &key_gc_flags))
 		gc_state |= KEY_GC_REAPING_DEAD_1;
@@ -233,8 +241,11 @@ continue_scanning:
 			}
 		}
 
-		if (gc_state & KEY_GC_SET_TIMER) {
-			if (key->expiry > limit && key->expiry < new_timer) {
+		expiry = key->expiry;
+		if (expiry != TIME64_MAX) {
+			if (!(key->type->flags & KEY_TYPE_INSTANT_REAP))
+				expiry += key_gc_delay;
+			if (expiry > limit && expiry < new_timer) {
 				kdebug("will expire %x in %lld",
 				       key_serial(key), key->expiry - limit);
 				new_timer = key->expiry;
@@ -276,7 +287,7 @@ maybe_resched:
 	 */
 	kdebug("pass complete");
 
-	if (gc_state & KEY_GC_SET_TIMER && new_timer != (time64_t)TIME64_MAX) {
+	if (new_timer != TIME64_MAX) {
 		new_timer += key_gc_delay;
 		key_schedule_gc(new_timer);
 	}
diff --git a/security/keys/internal.h b/security/keys/internal.h
index 471cf36dedc0..2cffa6dc8255 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -167,6 +167,7 @@ extern unsigned key_gc_delay;
 extern void keyring_gc(struct key *keyring, time64_t limit);
 extern void keyring_restriction_gc(struct key *keyring,
 				   struct key_type *dead_type);
+void key_set_expiry(struct key *key, time64_t expiry);
 extern void key_schedule_gc(time64_t gc_at);
 extern void key_schedule_gc_links(void);
 extern void key_gc_keytype(struct key_type *ktype);
@@ -215,10 +216,18 @@ extern struct key *key_get_instantiation_authkey(key_serial_t target_id);
  */
 static inline bool key_is_dead(const struct key *key, time64_t limit)
 {
+	time64_t expiry = key->expiry;
+
+	if (expiry != TIME64_MAX) {
+		if (!(key->type->flags & KEY_TYPE_INSTANT_REAP))
+			expiry += key_gc_delay;
+		if (expiry <= limit)
+			return true;
+	}
+
 	return
 		key->flags & ((1 << KEY_FLAG_DEAD) |
 			      (1 << KEY_FLAG_INVALIDATED)) ||
-		(key->expiry > 0 && key->expiry <= limit) ||
 		key->domain_tag->removed;
 }
 
diff --git a/security/keys/key.c b/security/keys/key.c
index 0260a1902922..5b10641debd5 100644
--- a/security/keys/key.c
+++ b/security/keys/key.c
@@ -294,6 +294,7 @@ struct key *key_alloc(struct key_type *type, const char *desc,
 	key->uid = uid;
 	key->gid = gid;
 	key->perm = perm;
+	key->expiry = TIME64_MAX;
 	key->restrict_link = restrict_link;
 	key->last_used_at = ktime_get_real_seconds();
 
@@ -463,10 +464,7 @@ static int __key_instantiate_and_link(struct key *key,
 			if (authkey)
 				key_invalidate(authkey);
 
-			if (prep->expiry != TIME64_MAX) {
-				key->expiry = prep->expiry;
-				key_schedule_gc(prep->expiry + key_gc_delay);
-			}
+			key_set_expiry(key, prep->expiry);
 		}
 	}
 
@@ -606,8 +604,7 @@ int key_reject_and_link(struct key *key,
 		atomic_inc(&key->user->nikeys);
 		mark_key_instantiated(key, -error);
 		notify_key(key, NOTIFY_KEY_INSTANTIATED, -error);
-		key->expiry = ktime_get_real_seconds() + timeout;
-		key_schedule_gc(key->expiry + key_gc_delay);
+		key_set_expiry(key, ktime_get_real_seconds() + timeout);
 
 		if (test_and_clear_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags))
 			awaken = 1;
@@ -723,16 +720,14 @@ found_kernel_type:
 
 void key_set_timeout(struct key *key, unsigned timeout)
 {
-	time64_t expiry = 0;
+	time64_t expiry = TIME64_MAX;
 
 	/* make the changes with the locks held to prevent races */
 	down_write(&key->sem);
 
 	if (timeout > 0)
 		expiry = ktime_get_real_seconds() + timeout;
-
-	key->expiry = expiry;
-	key_schedule_gc(key->expiry + key_gc_delay);
+	key_set_expiry(key, expiry);
 
 	up_write(&key->sem);
 }
diff --git a/security/keys/proc.c b/security/keys/proc.c
index d0cde6685627..4f4e2c1824f1 100644
--- a/security/keys/proc.c
+++ b/security/keys/proc.c
@@ -198,7 +198,7 @@ static int proc_keys_show(struct seq_file *m, void *v)
 
 	/* come up with a suitable timeout value */
 	expiry = READ_ONCE(key->expiry);
-	if (expiry == 0) {
+	if (expiry == TIME64_MAX) {
 		memcpy(xbuf, "perm", 5);
 	} else if (now >= expiry) {
 		memcpy(xbuf, "expd", 5);
-- 
cgit v1.2.3


From 1e9b05258271b76ccc04a4b535009d2cb596506a Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Tue, 14 Nov 2023 10:48:22 -0500
Subject: dt-bindings: dma: fsl-edma: Add fsl-edma.h to prevent hardcoding in
 dts

Introduce a common dt-bindings header file, fsl-edma.h, shared between
the driver and dts files. This addition aims to eliminate hardcoded values
in dts files, promoting maintainability and consistency.

DTS header file not support BIT() macro yet. Directly use 2^n number.

Signed-off-by: Frank Li <Frank.Li@nxp.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20231114154824.3617255-3-Frank.Li@nxp.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/dt-bindings/dma/fsl-edma.h | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)
 create mode 100644 include/dt-bindings/dma/fsl-edma.h

(limited to 'include')

diff --git a/include/dt-bindings/dma/fsl-edma.h b/include/dt-bindings/dma/fsl-edma.h
new file mode 100644
index 000000000000..fd11478cfe9c
--- /dev/null
+++ b/include/dt-bindings/dma/fsl-edma.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause */
+
+#ifndef _FSL_EDMA_DT_BINDING_H_
+#define _FSL_EDMA_DT_BINDING_H_
+
+/* Receive Channel */
+#define FSL_EDMA_RX		0x1
+
+/* iMX8 audio remote DMA */
+#define FSL_EDMA_REMOTE		0x2
+
+/* FIFO is continue memory region */
+#define FSL_EDMA_MULTI_FIFO	0x4
+
+/* Channel need stick to even channel */
+#define FSL_EDMA_EVEN_CH	0x8
+
+/* Channel need stick to odd channel */
+#define FSL_EDMA_ODD_CH		0x10
+
+#endif
-- 
cgit v1.2.3


From d293b1a89694fc4918d9a4330a71ba2458f9d581 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 21 Dec 2023 09:02:57 -0700
Subject: io_uring/kbuf: add method for returning provided buffer ring head

The tail of the provided ring buffer is shared between the kernel and
the application, but the head is private to the kernel as the
application doesn't need to see it. However, this also prevents the
application from knowing how many buffers the kernel has consumed.
Usually this is fine, as the information is inherently racy in that
the kernel could be consuming buffers continually, but for cleanup
purposes it may be relevant to know how many buffers are still left
in the ring.

Add IORING_REGISTER_PBUF_STATUS which will return status for a given
provided buffer ring. Right now it just returns the head, but space
is reserved for more information later in, if needed.

Link: https://github.com/axboe/liburing/discussions/1020
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/uapi/linux/io_uring.h | 10 ++++++++++
 io_uring/kbuf.c               | 26 ++++++++++++++++++++++++++
 io_uring/kbuf.h               |  1 +
 io_uring/register.c           |  6 ++++++
 4 files changed, 43 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index db4b913e6b39..7a673b52827b 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -567,6 +567,9 @@ enum {
 	/* register a range of fixed file slots for automatic slot allocation */
 	IORING_REGISTER_FILE_ALLOC_RANGE	= 25,
 
+	/* return status information for a buffer group */
+	IORING_REGISTER_PBUF_STATUS		= 26,
+
 	/* this goes last */
 	IORING_REGISTER_LAST,
 
@@ -693,6 +696,13 @@ struct io_uring_buf_reg {
 	__u64	resv[3];
 };
 
+/* argument for IORING_REGISTER_PBUF_STATUS */
+struct io_uring_buf_status {
+	__u32	buf_group;	/* input */
+	__u32	head;		/* output */
+	__u32	resv[8];
+};
+
 /*
  * io_uring_restriction->opcode values
  */
diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c
index 72b6af1d2ed3..18df5a9d2f5e 100644
--- a/io_uring/kbuf.c
+++ b/io_uring/kbuf.c
@@ -750,6 +750,32 @@ int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg)
 	return 0;
 }
 
+int io_register_pbuf_status(struct io_ring_ctx *ctx, void __user *arg)
+{
+	struct io_uring_buf_status buf_status;
+	struct io_buffer_list *bl;
+	int i;
+
+	if (copy_from_user(&buf_status, arg, sizeof(buf_status)))
+		return -EFAULT;
+
+	for (i = 0; i < ARRAY_SIZE(buf_status.resv); i++)
+		if (buf_status.resv[i])
+			return -EINVAL;
+
+	bl = io_buffer_get_list(ctx, buf_status.buf_group);
+	if (!bl)
+		return -ENOENT;
+	if (!bl->is_mapped)
+		return -EINVAL;
+
+	buf_status.head = bl->head;
+	if (copy_to_user(arg, &buf_status, sizeof(buf_status)))
+		return -EFAULT;
+
+	return 0;
+}
+
 void *io_pbuf_get_address(struct io_ring_ctx *ctx, unsigned long bgid)
 {
 	struct io_buffer_list *bl;
diff --git a/io_uring/kbuf.h b/io_uring/kbuf.h
index 9be5960817ea..53dfaa71a397 100644
--- a/io_uring/kbuf.h
+++ b/io_uring/kbuf.h
@@ -53,6 +53,7 @@ int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags);
 
 int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg);
 int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg);
+int io_register_pbuf_status(struct io_ring_ctx *ctx, void __user *arg);
 
 void io_kbuf_mmap_list_free(struct io_ring_ctx *ctx);
 
diff --git a/io_uring/register.c b/io_uring/register.c
index a4286029e920..708dd1d89add 100644
--- a/io_uring/register.c
+++ b/io_uring/register.c
@@ -542,6 +542,12 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
 			break;
 		ret = io_register_file_alloc_range(ctx, arg);
 		break;
+	case IORING_REGISTER_PBUF_STATUS:
+		ret = -EINVAL;
+		if (!arg || nr_args != 1)
+			break;
+		ret = io_register_pbuf_status(ctx, arg);
+		break;
 	default:
 		ret = -EINVAL;
 		break;
-- 
cgit v1.2.3


From 4515d08a742c76612b65d2f47a87d12860519842 Mon Sep 17 00:00:00 2001
From: Marco Pagani <marpagan@redhat.com>
Date: Thu, 21 Dec 2023 17:58:47 +0100
Subject: kernel/module: improve documentation for try_module_get()

The sentence "this call will fail if the module is already being
removed" is potentially confusing and may contradict the rest of the
documentation. If one tries to get a module that has already been
removed using a stale pointer, the kernel will crash.

Signed-off-by: Marco Pagani <marpagan@redhat.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 include/linux/module.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/module.h b/include/linux/module.h
index a98e188cf37b..08364d5cbc07 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -668,7 +668,7 @@ extern void __module_get(struct module *module);
  * @module: the module we should check for
  *
  * Only try to get a module reference count if the module is not being removed.
- * This call will fail if the module is already being removed.
+ * This call will fail if the module is in the process of being removed.
  *
  * Care must also be taken to ensure the module exists and is alive prior to
  * usage of this call. This can be gauranteed through two means:
-- 
cgit v1.2.3


From 3361597890ba901e4b666c2467b2cba349b0f63b Mon Sep 17 00:00:00 2001
From: Jonathan Corbet <corbet@lwn.net>
Date: Tue, 19 Dec 2023 17:01:39 -0700
Subject: wifi: cfg80211: address several kerneldoc warnings

include/net/cfg80211.h includes a number of kerneldoc entries for struct
members that do not exist, leading to these warnings:

  ./include/net/cfg80211.h:3192: warning: Excess struct member 'band_pref' description in 'cfg80211_bss_selection'
  ./include/net/cfg80211.h:3192: warning: Excess struct member 'adjust' description in 'cfg80211_bss_selection'
  ./include/net/cfg80211.h:6181: warning: Excess struct member 'bssid' description in 'wireless_dev'
  ./include/net/cfg80211.h:6181: warning: Excess struct member 'beacon_interval' description in 'wireless_dev'
  ./include/net/cfg80211.h:7299: warning: Excess struct member 'bss' description in 'cfg80211_rx_assoc_resp_data'

Remove and/or repair each entry to address the warnings and ensure a proper
docs build for the affected structures.

Signed-off-by: Jonathan Corbet <corbet@lwn.net>
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Link: https://msgid.link/87plz1g2sc.fsf@meer.lwn.net
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 033a0a25397f..92b956944c9f 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -3225,8 +3225,8 @@ struct cfg80211_ibss_params {
  *
  * @behaviour: requested BSS selection behaviour.
  * @param: parameters for requestion behaviour.
- * @band_pref: preferred band for %NL80211_BSS_SELECT_ATTR_BAND_PREF.
- * @adjust: parameters for %NL80211_BSS_SELECT_ATTR_RSSI_ADJUST.
+ * @param.band_pref: preferred band for %NL80211_BSS_SELECT_ATTR_BAND_PREF.
+ * @param.adjust: parameters for %NL80211_BSS_SELECT_ATTR_RSSI_ADJUST.
  */
 struct cfg80211_bss_selection {
 	enum nl80211_bss_select_attr behaviour;
@@ -6063,7 +6063,6 @@ void wiphy_delayed_work_flush(struct wiphy *wiphy,
  *	wireless device if it has no netdev
  * @u: union containing data specific to @iftype
  * @connected: indicates if connected or not (STA mode)
- * @bssid: (private) Used by the internal configuration code
  * @wext: (private) Used by the internal wireless extensions compat code
  * @wext.ibss: (private) IBSS data part of wext handling
  * @wext.connect: (private) connection handling data
@@ -6083,8 +6082,6 @@ void wiphy_delayed_work_flush(struct wiphy *wiphy,
  * @mgmt_registrations: list of registrations for management frames
  * @mgmt_registrations_need_update: mgmt registrations were updated,
  *	need to propagate the update to the driver
- * @beacon_interval: beacon interval used on this device for transmitting
- *	beacons, 0 when not valid
  * @address: The address for this device, valid only if @netdev is %NULL
  * @is_running: true if this is a non-netdev device that has been started, e.g.
  *	the P2P Device.
@@ -7363,8 +7360,6 @@ void cfg80211_auth_timeout(struct net_device *dev, const u8 *addr);
 
 /**
  * struct cfg80211_rx_assoc_resp_data - association response data
- * @bss: the BSS that association was requested with, ownership of the pointer
- *	moves to cfg80211 in the call to cfg80211_rx_assoc_resp()
  * @buf: (Re)Association Response frame (header + body)
  * @len: length of the frame data
  * @uapsd_queues: bitmap of queues configured for uapsd. Same format
@@ -7374,6 +7369,8 @@ void cfg80211_auth_timeout(struct net_device *dev, const u8 *addr);
  * @ap_mld_addr: AP MLD address (in case of MLO)
  * @links: per-link information indexed by link ID, use links[0] for
  *	non-MLO connections
+ * @links.bss: the BSS that association was requested with, ownership of the
+ *      pointer moves to cfg80211 in the call to cfg80211_rx_assoc_resp()
  * @links.status: Set this (along with a BSS pointer) for links that
  *	were rejected by the AP.
  */
-- 
cgit v1.2.3


From 756df9853491e28acbe7fca9f8146a784f026117 Mon Sep 17 00:00:00 2001
From: Jonathan Corbet <corbet@lwn.net>
Date: Wed, 20 Dec 2023 15:57:55 -0700
Subject: wifi: mac80211: address some kerneldoc warnings

include/net/mac80111.h contains a number of either excess or incorrect
kerneldoc entries for structure members, leading to these warnings:

  ./include/net/mac80211.h:491: warning: Excess struct member 'rssi' description in 'ieee80211_event'
  ./include/net/mac80211.h:491: warning: Excess struct member 'mlme' description in 'ieee80211_event'
  ./include/net/mac80211.h:491: warning: Excess struct member 'ba' description in 'ieee80211_event'
  ./include/net/mac80211.h:777: warning: Excess struct member 'ack_enabled' description in 'ieee80211_bss_conf'
  ./include/net/mac80211.h:1222: warning: Excess struct member 'ampdu_ack_len' description in 'ieee80211_tx_info'
  ./include/net/mac80211.h:1222: warning: Excess struct member 'ampdu_len' description in 'ieee80211_tx_info'
  ./include/net/mac80211.h:1222: warning: Excess struct member 'ack_signal' description in 'ieee80211_tx_info'
  ./include/net/mac80211.h:2920: warning: Excess struct member 'radiotap_he' description in 'ieee80211_hw'

Fix or remove the entries as needed.  This change removes 208 warnings from
a "make htmldocs" build.

Signed-off-by: Jonathan Corbet <corbet@lwn.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://msgid.link/87zfy4bhxo.fsf@meer.lwn.net
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h | 15 +++------------
 1 file changed, 3 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 77a71b1396b1..6d2e94bc841c 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -476,9 +476,9 @@ struct ieee80211_ba_event {
 /**
  * struct ieee80211_event - event to be sent to the driver
  * @type: The event itself. See &enum ieee80211_event_type.
- * @rssi: relevant if &type is %RSSI_EVENT
- * @mlme: relevant if &type is %AUTH_EVENT
- * @ba: relevant if &type is %BAR_RX_EVENT or %BA_FRAME_TIMEOUT
+ * @u.rssi: relevant if &type is %RSSI_EVENT
+ * @u.mlme: relevant if &type is %AUTH_EVENT
+ * @u.ba: relevant if &type is %BAR_RX_EVENT or %BA_FRAME_TIMEOUT
  * @u:union holding the fields above
  */
 struct ieee80211_event {
@@ -541,8 +541,6 @@ struct ieee80211_fils_discovery {
  * @link_id: link ID, or 0 for non-MLO
  * @htc_trig_based_pkt_ext: default PE in 4us units, if BSS supports HE
  * @uora_exists: is the UORA element advertised by AP
- * @ack_enabled: indicates support to receive a multi-TID that solicits either
- *	ACK, BACK or both
  * @uora_ocw_range: UORA element's OCW Range field
  * @frame_time_rts_th: HE duration RTS threshold, in units of 32us
  * @he_support: does this BSS support HE
@@ -1150,11 +1148,6 @@ ieee80211_rate_get_vht_nss(const struct ieee80211_tx_rate *rate)
  * @ack: union part for pure ACK data
  * @ack.cookie: cookie for the ACK
  * @driver_data: array of driver_data pointers
- * @ampdu_ack_len: number of acked aggregated frames.
- * 	relevant only if IEEE80211_TX_STAT_AMPDU was set.
- * @ampdu_len: number of aggregated frames.
- * 	relevant only if IEEE80211_TX_STAT_AMPDU was set.
- * @ack_signal: signal strength of the ACK frame
  */
 struct ieee80211_tx_info {
 	/* common information */
@@ -2835,8 +2828,6 @@ enum ieee80211_hw_flags {
  *	the default is _GI | _BANDWIDTH.
  *	Use the %IEEE80211_RADIOTAP_VHT_KNOWN_\* values.
  *
- * @radiotap_he: HE radiotap validity flags
- *
  * @radiotap_timestamp: Information for the radiotap timestamp field; if the
  *	@units_pos member is set to a non-negative value then the timestamp
  *	field will be added and populated from the &struct ieee80211_rx_status
-- 
cgit v1.2.3


From 41a313d875e0c5822efb50e8221b8d58811609bb Mon Sep 17 00:00:00 2001
From: Andrei Otcheretianski <andrei.otcheretianski@intel.com>
Date: Wed, 20 Dec 2023 13:41:34 +0200
Subject: wifi: cfg80211: reg: Support P2P operation on DFS channels

FCC-594280 D01 Section B.3 allows peer-to-peer and ad hoc devices to
operate on DFS channels while they operate under the control of a
concurrent DFS master. For example, it is possible to have a P2P GO on a
DFS channel as long as BSS connection is active on the same channel.
Allow such operation by adding additional regulatory flags to indicate
DFS concurrent channels and capable devices. Add the required
relaxations in DFS regulatory checks.

Signed-off-by: Andrei Otcheretianski <andrei.otcheretianski@intel.com>
Reviewed-by: Gregory Greenman <gregory.greenman@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20231220133549.bdfb8a9c7c54.I973563562969a27fea8ec5685b96a3a47afe142f@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       |  2 +
 include/uapi/linux/nl80211.h | 16 ++++++++
 net/wireless/chan.c          | 94 ++++++++++++++++++++++++++++++++++++++++----
 net/wireless/nl80211.c       |  3 ++
 net/wireless/reg.c           |  2 +
 5 files changed, 110 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 92b956944c9f..501d4421514f 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -117,6 +117,7 @@ struct wiphy;
  *	This may be due to the driver or due to regulatory bandwidth
  *	restrictions.
  * @IEEE80211_CHAN_NO_EHT: EHT operation is not permitted on this channel.
+ * @IEEE80211_CHAN_DFS_CONCURRENT: See %NL80211_RRF_DFS_CONCURRENT
  */
 enum ieee80211_channel_flags {
 	IEEE80211_CHAN_DISABLED		= 1<<0,
@@ -140,6 +141,7 @@ enum ieee80211_channel_flags {
 	IEEE80211_CHAN_16MHZ		= 1<<18,
 	IEEE80211_CHAN_NO_320MHZ	= 1<<19,
 	IEEE80211_CHAN_NO_EHT		= 1<<20,
+	IEEE80211_CHAN_DFS_CONCURRENT	= 1<<21,
 };
 
 #define IEEE80211_CHAN_NO_HT40 \
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index a682b54bd3ba..466da830e65f 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -4256,6 +4256,10 @@ enum nl80211_wmm_rule {
  *	in current regulatory domain.
  * @NL80211_FREQUENCY_ATTR_PSD: Power spectral density (in dBm) that
  *	is allowed on this channel in current regulatory domain.
+ * @NL80211_FREQUENCY_ATTR_DFS_CONCURRENT: Operation on this channel is
+ *	allowed for peer-to-peer or adhoc communication under the control
+ *	of a DFS master which operates on the same channel (FCC-594280 D01
+ *	Section B.3). Should be used together with %NL80211_RRF_DFS only.
  * @NL80211_FREQUENCY_ATTR_MAX: highest frequency attribute number
  *	currently defined
  * @__NL80211_FREQUENCY_ATTR_AFTER_LAST: internal use
@@ -4295,6 +4299,7 @@ enum nl80211_frequency_attr {
 	NL80211_FREQUENCY_ATTR_NO_320MHZ,
 	NL80211_FREQUENCY_ATTR_NO_EHT,
 	NL80211_FREQUENCY_ATTR_PSD,
+	NL80211_FREQUENCY_ATTR_DFS_CONCURRENT,
 
 	/* keep last */
 	__NL80211_FREQUENCY_ATTR_AFTER_LAST,
@@ -4500,6 +4505,10 @@ enum nl80211_sched_scan_match_attr {
  * @NL80211_RRF_NO_320MHZ: 320MHz operation not allowed
  * @NL80211_RRF_NO_EHT: EHT operation not allowed
  * @NL80211_RRF_PSD: Ruleset has power spectral density value
+ * @NL80211_RRF_DFS_CONCURRENT: Operation on this channel is allowed for
+	peer-to-peer or adhoc communication under the control of a DFS master
+	which operates on the same channel (FCC-594280 D01 Section B.3).
+	Should be used together with %NL80211_RRF_DFS only.
  */
 enum nl80211_reg_rule_flags {
 	NL80211_RRF_NO_OFDM		= 1<<0,
@@ -4521,6 +4530,7 @@ enum nl80211_reg_rule_flags {
 	NL80211_RRF_NO_320MHZ		= 1<<18,
 	NL80211_RRF_NO_EHT		= 1<<19,
 	NL80211_RRF_PSD			= 1<<20,
+	NL80211_RRF_DFS_CONCURRENT	= 1<<21,
 };
 
 #define NL80211_RRF_PASSIVE_SCAN	NL80211_RRF_NO_IR
@@ -6492,6 +6502,11 @@ enum nl80211_feature_flags {
  * @NL80211_EXT_FEATURE_OWE_OFFLOAD_AP: Driver/Device wants to do OWE DH IE
  *	handling in AP mode.
  *
+ * @NL80211_EXT_FEATURE_DFS_CONCURRENT: The device supports peer-to-peer or
+ *	ad hoc operation on DFS channels under the control of a concurrent
+ *	DFS master on the same channel as described in FCC-594280 D01
+ *	(Section B.3). This, for example, allows P2P GO and P2P clients to
+ *	operate on DFS channels as long as there's a concurrent BSS connection.
  * @NUM_NL80211_EXT_FEATURES: number of extended features.
  * @MAX_NL80211_EXT_FEATURES: highest extended feature index.
  */
@@ -6565,6 +6580,7 @@ enum nl80211_ext_feature_index {
 	NL80211_EXT_FEATURE_AUTH_AND_DEAUTH_RANDOM_TA,
 	NL80211_EXT_FEATURE_OWE_OFFLOAD,
 	NL80211_EXT_FEATURE_OWE_OFFLOAD_AP,
+	NL80211_EXT_FEATURE_DFS_CONCURRENT,
 
 	/* add new features before the definition below */
 	NUM_NL80211_EXT_FEATURES,
diff --git a/net/wireless/chan.c b/net/wireless/chan.c
index dfb4893421d7..ceb9174c5c3d 100644
--- a/net/wireless/chan.c
+++ b/net/wireless/chan.c
@@ -515,9 +515,83 @@ static u32 cfg80211_get_end_freq(u32 center_freq,
 	return end_freq;
 }
 
+static bool
+cfg80211_dfs_permissive_check_wdev(struct cfg80211_registered_device *rdev,
+				   enum nl80211_iftype iftype,
+				   struct wireless_dev *wdev,
+				   struct ieee80211_channel *chan)
+{
+	unsigned int link_id;
+
+	for_each_valid_link(wdev, link_id) {
+		struct ieee80211_channel *other_chan = NULL;
+		struct cfg80211_chan_def chandef = {};
+		int ret;
+
+		/* In order to avoid daisy chaining only allow BSS STA */
+		if (wdev->iftype != NL80211_IFTYPE_STATION ||
+		    !wdev->links[link_id].client.current_bss)
+			continue;
+
+		other_chan =
+			wdev->links[link_id].client.current_bss->pub.channel;
+
+		if (!other_chan)
+			continue;
+
+		if (chan == other_chan)
+			return true;
+
+		/* continue if we can't get the channel */
+		ret = rdev_get_channel(rdev, wdev, link_id, &chandef);
+		if (ret)
+			continue;
+
+		if (cfg80211_is_sub_chan(&chandef, chan, false))
+			return true;
+	}
+
+	return false;
+}
+
+/*
+ * Check if P2P GO is allowed to operate on a DFS channel
+ */
+static bool cfg80211_dfs_permissive_chan(struct wiphy *wiphy,
+					 enum nl80211_iftype iftype,
+					 struct ieee80211_channel *chan)
+{
+	struct wireless_dev *wdev;
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
+
+	lockdep_assert_held(&rdev->wiphy.mtx);
+
+	if (!wiphy_ext_feature_isset(&rdev->wiphy,
+				     NL80211_EXT_FEATURE_DFS_CONCURRENT) ||
+	    !(chan->flags & IEEE80211_CHAN_DFS_CONCURRENT))
+		return false;
+
+	/* only valid for P2P GO */
+	if (iftype != NL80211_IFTYPE_P2P_GO)
+		return false;
+
+	/*
+	 * Allow only if there's a concurrent BSS
+	 */
+	list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) {
+		bool ret = cfg80211_dfs_permissive_check_wdev(rdev, iftype,
+							      wdev, chan);
+		if (ret)
+			return ret;
+	}
+
+	return false;
+}
+
 static int cfg80211_get_chans_dfs_required(struct wiphy *wiphy,
 					    u32 center_freq,
-					    u32 bandwidth)
+					    u32 bandwidth,
+					    enum nl80211_iftype iftype)
 {
 	struct ieee80211_channel *c;
 	u32 freq, start_freq, end_freq;
@@ -530,9 +604,11 @@ static int cfg80211_get_chans_dfs_required(struct wiphy *wiphy,
 		if (!c)
 			return -EINVAL;
 
-		if (c->flags & IEEE80211_CHAN_RADAR)
+		if (c->flags & IEEE80211_CHAN_RADAR &&
+		    !cfg80211_dfs_permissive_chan(wiphy, iftype, c))
 			return 1;
 	}
+
 	return 0;
 }
 
@@ -558,7 +634,7 @@ int cfg80211_chandef_dfs_required(struct wiphy *wiphy,
 
 		ret = cfg80211_get_chans_dfs_required(wiphy,
 					ieee80211_chandef_to_khz(chandef),
-					width);
+					width, iftype);
 		if (ret < 0)
 			return ret;
 		else if (ret > 0)
@@ -569,7 +645,7 @@ int cfg80211_chandef_dfs_required(struct wiphy *wiphy,
 
 		ret = cfg80211_get_chans_dfs_required(wiphy,
 					MHZ_TO_KHZ(chandef->center_freq2),
-					width);
+					width, iftype);
 		if (ret < 0)
 			return ret;
 		else if (ret > 0)
@@ -1337,15 +1413,19 @@ static bool _cfg80211_reg_can_beacon(struct wiphy *wiphy,
 				     bool check_no_ir)
 {
 	bool res;
-	u32 prohibited_flags = IEEE80211_CHAN_DISABLED |
-			       IEEE80211_CHAN_RADAR;
+	u32 prohibited_flags = IEEE80211_CHAN_DISABLED;
+	int dfs_required;
 
 	trace_cfg80211_reg_can_beacon(wiphy, chandef, iftype, check_no_ir);
 
 	if (check_no_ir)
 		prohibited_flags |= IEEE80211_CHAN_NO_IR;
 
-	if (cfg80211_chandef_dfs_required(wiphy, chandef, iftype) > 0 &&
+	dfs_required = cfg80211_chandef_dfs_required(wiphy, chandef, iftype);
+	if (dfs_required != 0)
+		prohibited_flags |= IEEE80211_CHAN_RADAR;
+
+	if (dfs_required > 0 &&
 	    cfg80211_chandef_dfs_available(wiphy, chandef)) {
 		/* We can skip IEEE80211_CHAN_NO_IR if chandef dfs available */
 		prohibited_flags = IEEE80211_CHAN_DISABLED;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 8b45fb420f4c..bd65c3ccc5e7 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -1201,6 +1201,9 @@ static int nl80211_msg_put_channel(struct sk_buff *msg, struct wiphy *wiphy,
 		if ((chan->flags & IEEE80211_CHAN_NO_EHT) &&
 		    nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_EHT))
 			goto nla_put_failure;
+		if ((chan->flags & IEEE80211_CHAN_DFS_CONCURRENT) &&
+		    nla_put_flag(msg, NL80211_FREQUENCY_ATTR_DFS_CONCURRENT))
+			goto nla_put_failure;
 	}
 
 	if (nla_put_u32(msg, NL80211_FREQUENCY_ATTR_MAX_TX_POWER,
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 2ef4f6cc7a32..9a61b3322fd2 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -1593,6 +1593,8 @@ static u32 map_regdom_flags(u32 rd_flags)
 		channel_flags |= IEEE80211_CHAN_NO_320MHZ;
 	if (rd_flags & NL80211_RRF_NO_EHT)
 		channel_flags |= IEEE80211_CHAN_NO_EHT;
+	if (rd_flags & NL80211_RRF_DFS_CONCURRENT)
+		channel_flags |= IEEE80211_CHAN_DFS_CONCURRENT;
 	if (rd_flags & NL80211_RRF_PSD)
 		channel_flags |= IEEE80211_CHAN_PSD;
 	return channel_flags;
-- 
cgit v1.2.3


From 9be61558dec0af359ce3139c8450228de7f0796d Mon Sep 17 00:00:00 2001
From: Andrei Otcheretianski <andrei.otcheretianski@intel.com>
Date: Wed, 20 Dec 2023 13:41:35 +0200
Subject: wifi: cfg80211: Schedule regulatory check on BSS STA channel change

Due to different relaxation policies it may be needed to re-check
channels after a BSS station interface is disconnected or performed a
channel switch.

Signed-off-by: Andrei Otcheretianski <andrei.otcheretianski@intel.com>
Reviewed-by: Gregory Greenman <gregory.greenman@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20231220133549.1f2f8475bcf1.I1879d259d8d756159c8060f61f4bce172e6d323e@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 10 ++++++++++
 net/wireless/nl80211.c | 15 +++++++++++++++
 net/wireless/reg.c     |  2 +-
 net/wireless/reg.h     |  5 +++++
 net/wireless/sme.c     |  2 ++
 5 files changed, 33 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 501d4421514f..745974d45ea4 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -9391,6 +9391,16 @@ bool cfg80211_valid_disable_subchannel_bitmap(u16 *bitmap,
  */
 void cfg80211_links_removed(struct net_device *dev, u16 link_mask);
 
+/**
+ * cfg80211_schedule_channels_check - schedule regulatory check if needed
+ * @wdev: the wireless device to check
+ *
+ * In case the device supports NO_IR or DFS relaxations, schedule regulatory
+ * channels check, as previous concurrent operation conditions may not
+ * hold anymore.
+ */
+void cfg80211_schedule_channels_check(struct wireless_dev *wdev);
+
 #ifdef CONFIG_CFG80211_DEBUGFS
 /**
  * wiphy_locked_debugfs_read - do a locked read in debugfs
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index bd65c3ccc5e7..534ef3fe0696 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -19474,6 +19474,7 @@ void cfg80211_ch_switch_notify(struct net_device *dev,
 		break;
 	}
 
+	cfg80211_schedule_channels_check(wdev);
 	cfg80211_sched_dfs_chan_update(rdev);
 
 	nl80211_ch_switch_notify(rdev, dev, link_id, chandef, GFP_KERNEL,
@@ -20231,6 +20232,20 @@ nla_put_failure:
 }
 EXPORT_SYMBOL(cfg80211_update_owe_info_event);
 
+void cfg80211_schedule_channels_check(struct wireless_dev *wdev)
+{
+	struct wiphy *wiphy = wdev->wiphy;
+
+	/* Schedule channels check if NO_IR or DFS relaxations are supported */
+	if (wdev->iftype == NL80211_IFTYPE_STATION &&
+	    (wiphy_ext_feature_isset(wiphy,
+				     NL80211_EXT_FEATURE_DFS_CONCURRENT) ||
+	    (IS_ENABLED(CONFIG_CFG80211_REG_RELAX_NO_IR) &&
+	     wiphy->regulatory_flags & REGULATORY_ENABLE_RELAX_NO_IR)))
+		reg_check_channels();
+}
+EXPORT_SYMBOL(cfg80211_schedule_channels_check);
+
 /* initialisation/exit functions */
 
 int __init nl80211_init(void)
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 9a61b3322fd2..44684df64734 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -2480,7 +2480,7 @@ static void reg_check_chans_work(struct work_struct *work)
 	rtnl_unlock();
 }
 
-static void reg_check_channels(void)
+void reg_check_channels(void)
 {
 	/*
 	 * Give usermode a chance to do something nicer (move to another
diff --git a/net/wireless/reg.h b/net/wireless/reg.h
index a703e53c23ee..a02ef5609f52 100644
--- a/net/wireless/reg.h
+++ b/net/wireless/reg.h
@@ -181,6 +181,11 @@ bool reg_dfs_domain_same(struct wiphy *wiphy1, struct wiphy *wiphy2);
  */
 int reg_reload_regdb(void);
 
+/**
+ * reg_check_channels - schedule regulatory enforcement
+ */
+void reg_check_channels(void);
+
 extern const u8 shipped_regdb_certs[];
 extern unsigned int shipped_regdb_certs_len;
 extern const u8 extra_regdb_certs[];
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index acfe66da7109..195c8532734b 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -1394,6 +1394,8 @@ void __cfg80211_disconnected(struct net_device *dev, const u8 *ie,
 #endif
 
 	schedule_work(&cfg80211_disconnect_work);
+
+	cfg80211_schedule_channels_check(wdev);
 }
 
 void cfg80211_disconnected(struct net_device *dev, u16 reason,
-- 
cgit v1.2.3


From 645f3d85129d8aac3b896ba685fbc20a31c2c036 Mon Sep 17 00:00:00 2001
From: Mukesh Sisodiya <mukesh.sisodiya@intel.com>
Date: Wed, 20 Dec 2023 13:41:38 +0200
Subject: wifi: cfg80211: handle UHB AP and STA power type

UHB AP send supported power type(LPI, SP, VLP)
in beacon and probe response IE and STA should
connect to these AP only if their regulatory support
the AP power type.

Beacon/Probe response are reported to userspace
with reason "STA regulatory not supporting to connect to AP
based on transmitted power type" and it should
not connect to AP.

Signed-off-by: Mukesh Sisodiya <mukesh.sisodiya@intel.com>
Reviewed-by: Gregory Greenman <gregory.greenman@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20231220133549.cbfbef9170a9.I432f78438de18aa9f5c9006be12e41dc34cc47c5@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h    |  1 +
 include/net/cfg80211.h       |  6 ++++++
 include/uapi/linux/nl80211.h | 13 +++++++++++++
 net/wireless/nl80211.c       |  6 ++++++
 net/wireless/reg.c           |  4 ++++
 net/wireless/scan.c          | 38 ++++++++++++++++++++++++++++++++++++++
 6 files changed, 68 insertions(+)

(limited to 'include')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 8ad008591e32..2f5554482047 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -2720,6 +2720,7 @@ static inline bool ieee80211_he_capa_size_ok(const u8 *data, u8 len)
 
 #define IEEE80211_6GHZ_CTRL_REG_LPI_AP	0
 #define IEEE80211_6GHZ_CTRL_REG_SP_AP	1
+#define IEEE80211_6GHZ_CTRL_REG_VLP_AP	2
 
 /**
  * struct ieee80211_he_6ghz_oper - HE 6 GHz operation Information field
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 745974d45ea4..cf79656ce09c 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -118,6 +118,10 @@ struct wiphy;
  *	restrictions.
  * @IEEE80211_CHAN_NO_EHT: EHT operation is not permitted on this channel.
  * @IEEE80211_CHAN_DFS_CONCURRENT: See %NL80211_RRF_DFS_CONCURRENT
+ * @IEEE80211_CHAN_NO_UHB_VLP_CLIENT: Client connection with VLP AP
+ *	not permitted using this channel
+ * @IEEE80211_CHAN_NO_UHB_AFC_CLIENT: Client connection with AFC AP
+ *	not permitted using this channel
  */
 enum ieee80211_channel_flags {
 	IEEE80211_CHAN_DISABLED		= 1<<0,
@@ -142,6 +146,8 @@ enum ieee80211_channel_flags {
 	IEEE80211_CHAN_NO_320MHZ	= 1<<19,
 	IEEE80211_CHAN_NO_EHT		= 1<<20,
 	IEEE80211_CHAN_DFS_CONCURRENT	= 1<<21,
+	IEEE80211_CHAN_NO_UHB_VLP_CLIENT= 1<<22,
+	IEEE80211_CHAN_NO_UHB_AFC_CLIENT= 1<<23,
 };
 
 #define IEEE80211_CHAN_NO_HT40 \
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 466da830e65f..1ccdcae24372 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -4260,6 +4260,10 @@ enum nl80211_wmm_rule {
  *	allowed for peer-to-peer or adhoc communication under the control
  *	of a DFS master which operates on the same channel (FCC-594280 D01
  *	Section B.3). Should be used together with %NL80211_RRF_DFS only.
+ * @NL80211_FREQUENCY_ATTR_NO_UHB_VLP_CLIENT: Client connection to VLP AP
+ *	not allowed using this channel
+ * @NL80211_FREQUENCY_ATTR_NO_UHB_AFC_CLIENT: Client connection to AFC AP
+ *	not allowed using this channel
  * @NL80211_FREQUENCY_ATTR_MAX: highest frequency attribute number
  *	currently defined
  * @__NL80211_FREQUENCY_ATTR_AFTER_LAST: internal use
@@ -4300,6 +4304,8 @@ enum nl80211_frequency_attr {
 	NL80211_FREQUENCY_ATTR_NO_EHT,
 	NL80211_FREQUENCY_ATTR_PSD,
 	NL80211_FREQUENCY_ATTR_DFS_CONCURRENT,
+	NL80211_FREQUENCY_ATTR_NO_UHB_VLP_CLIENT,
+	NL80211_FREQUENCY_ATTR_NO_UHB_AFC_CLIENT,
 
 	/* keep last */
 	__NL80211_FREQUENCY_ATTR_AFTER_LAST,
@@ -4509,6 +4515,8 @@ enum nl80211_sched_scan_match_attr {
 	peer-to-peer or adhoc communication under the control of a DFS master
 	which operates on the same channel (FCC-594280 D01 Section B.3).
 	Should be used together with %NL80211_RRF_DFS only.
+ * @NL80211_RRF_NO_UHB_VLP_CLIENT: Client connection to VLP AP not allowed
+ * @NL80211_RRF_NO_UHB_AFC_CLIENT: Client connection to AFC AP not allowed
  */
 enum nl80211_reg_rule_flags {
 	NL80211_RRF_NO_OFDM		= 1<<0,
@@ -4531,6 +4539,8 @@ enum nl80211_reg_rule_flags {
 	NL80211_RRF_NO_EHT		= 1<<19,
 	NL80211_RRF_PSD			= 1<<20,
 	NL80211_RRF_DFS_CONCURRENT	= 1<<21,
+	NL80211_RRF_NO_UHB_VLP_CLIENT	= 1<<22,
+	NL80211_RRF_NO_UHB_AFC_CLIENT	= 1<<23,
 };
 
 #define NL80211_RRF_PASSIVE_SCAN	NL80211_RRF_NO_IR
@@ -5086,9 +5096,12 @@ enum nl80211_bss_use_for {
  *	BSS isn't possible
  * @NL80211_BSS_CANNOT_USE_NSTR_NONPRIMARY: NSTR nonprimary links aren't
  *	supported by the device, and this BSS entry represents one.
+ * @NL80211_BSS_CANNOT_USE_UHB_PWR_MISMATCH: STA is not supporting
+ *	the AP power type (SP, VLP, AP) that the AP uses.
  */
 enum nl80211_bss_cannot_use_reasons {
 	NL80211_BSS_CANNOT_USE_NSTR_NONPRIMARY	= 1 << 0,
+	NL80211_BSS_CANNOT_USE_UHB_PWR_MISMATCH	= 1 << 1,
 };
 
 /**
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 534ef3fe0696..60877b532993 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -1204,6 +1204,12 @@ static int nl80211_msg_put_channel(struct sk_buff *msg, struct wiphy *wiphy,
 		if ((chan->flags & IEEE80211_CHAN_DFS_CONCURRENT) &&
 		    nla_put_flag(msg, NL80211_FREQUENCY_ATTR_DFS_CONCURRENT))
 			goto nla_put_failure;
+		if ((chan->flags & IEEE80211_CHAN_NO_UHB_VLP_CLIENT) &&
+		    nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_UHB_VLP_CLIENT))
+			goto nla_put_failure;
+		if ((chan->flags & IEEE80211_CHAN_NO_UHB_AFC_CLIENT) &&
+		    nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_UHB_AFC_CLIENT))
+			goto nla_put_failure;
 	}
 
 	if (nla_put_u32(msg, NL80211_FREQUENCY_ATTR_MAX_TX_POWER,
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 44684df64734..2741b626919a 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -1595,6 +1595,10 @@ static u32 map_regdom_flags(u32 rd_flags)
 		channel_flags |= IEEE80211_CHAN_NO_EHT;
 	if (rd_flags & NL80211_RRF_DFS_CONCURRENT)
 		channel_flags |= IEEE80211_CHAN_DFS_CONCURRENT;
+	if (rd_flags & NL80211_RRF_NO_UHB_VLP_CLIENT)
+		channel_flags |= IEEE80211_CHAN_NO_UHB_VLP_CLIENT;
+	if (rd_flags & NL80211_RRF_NO_UHB_AFC_CLIENT)
+		channel_flags |= IEEE80211_CHAN_NO_UHB_AFC_CLIENT;
 	if (rd_flags & NL80211_RRF_PSD)
 		channel_flags |= IEEE80211_CHAN_PSD;
 	return channel_flags;
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 3d260c99c348..a601f1c7f835 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -2848,6 +2848,36 @@ cfg80211_inform_bss_data(struct wiphy *wiphy,
 }
 EXPORT_SYMBOL(cfg80211_inform_bss_data);
 
+static bool cfg80211_uhb_power_type_valid(const u8 *ie,
+					  size_t ielen,
+					  const u32 flags)
+{
+	const struct element *tmp;
+	struct ieee80211_he_operation *he_oper;
+
+	tmp = cfg80211_find_ext_elem(WLAN_EID_EXT_HE_OPERATION, ie, ielen);
+	if (tmp && tmp->datalen >= sizeof(*he_oper) + 1) {
+		const struct ieee80211_he_6ghz_oper *he_6ghz_oper;
+
+		he_oper = (void *)&tmp->data[1];
+		he_6ghz_oper = ieee80211_he_6ghz_oper(he_oper);
+
+		if (!he_6ghz_oper)
+			return false;
+
+		switch (u8_get_bits(he_6ghz_oper->control,
+				    IEEE80211_HE_6GHZ_OPER_CTRL_REG_INFO)) {
+		case IEEE80211_6GHZ_CTRL_REG_LPI_AP:
+			return true;
+		case IEEE80211_6GHZ_CTRL_REG_SP_AP:
+			return !(flags & IEEE80211_CHAN_NO_UHB_AFC_CLIENT);
+		case IEEE80211_6GHZ_CTRL_REG_VLP_AP:
+			return !(flags & IEEE80211_CHAN_NO_UHB_VLP_CLIENT);
+		}
+	}
+	return false;
+}
+
 /* cfg80211_inform_bss_width_frame helper */
 static struct cfg80211_bss *
 cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy,
@@ -2906,6 +2936,14 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy,
 	if (!channel)
 		return NULL;
 
+	if (channel->band == NL80211_BAND_6GHZ &&
+	    !cfg80211_uhb_power_type_valid(variable, ielen, channel->flags)) {
+		data->restrict_use = 1;
+		data->use_for = 0;
+		data->cannot_use_reasons =
+			NL80211_BSS_CANNOT_USE_UHB_PWR_MISMATCH;
+	}
+
 	if (ext) {
 		const struct ieee80211_s1g_bcn_compat_ie *compat;
 		const struct element *elem;
-- 
cgit v1.2.3


From d5b6f6d595b446c1693fdaa6aeb4a65b94d5fc90 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 20 Dec 2023 13:41:39 +0200
Subject: wifi: mac80211: rework RX timestamp flags

We only have a single flag free, and before using that for
another mactime flag, instead refactor the mactime flags
to use a 2-bit field.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Gregory Greenman <gregory.greenman@intel.com>
Reviewed-by: Benjamin Berg <benjamin.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20231220133549.d0e664832d14.I20c8900106f9bf81316bed778b1e3ce145785274@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ath/ath10k/htt_rx.c |  2 +-
 include/net/mac80211.h                   | 13 +++++++++----
 net/mac80211/ieee80211_i.h               |  5 +----
 net/mac80211/util.c                      | 16 ++++++++++------
 4 files changed, 21 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c
index fa0f598ed6bf..7d28ae5453cf 100644
--- a/drivers/net/wireless/ath/ath10k/htt_rx.c
+++ b/drivers/net/wireless/ath/ath10k/htt_rx.c
@@ -1295,7 +1295,7 @@ static void ath10k_htt_rx_h_ppdu(struct ath10k *ar,
 		status->encoding = RX_ENC_LEGACY;
 		status->bw = RATE_INFO_BW_20;
 
-		status->flag &= ~RX_FLAG_MACTIME_END;
+		status->flag &= ~RX_FLAG_MACTIME;
 		status->flag |= RX_FLAG_NO_SIGNAL_VAL;
 
 		status->flag &= ~(RX_FLAG_AMPDU_IS_LAST);
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 6d2e94bc841c..941980c7aa21 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1355,6 +1355,9 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info)
  *	the frame.
  * @RX_FLAG_FAILED_PLCP_CRC: Set this flag if the PCLP check failed on
  *	the frame.
+ * @RX_FLAG_MACTIME: The timestamp passed in the RX status (@mactime
+ *	field) is valid if this field is non-zero, and the position
+ *	where the timestamp was sampled depends on the value.
  * @RX_FLAG_MACTIME_START: The timestamp passed in the RX status (@mactime
  *	field) is valid and contains the time the first symbol of the MPDU
  *	was received. This is useful in monitor mode and for proper IBSS
@@ -1434,12 +1437,12 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info)
 enum mac80211_rx_flags {
 	RX_FLAG_MMIC_ERROR		= BIT(0),
 	RX_FLAG_DECRYPTED		= BIT(1),
-	RX_FLAG_MACTIME_PLCP_START	= BIT(2),
+	RX_FLAG_ONLY_MONITOR		= BIT(2),
 	RX_FLAG_MMIC_STRIPPED		= BIT(3),
 	RX_FLAG_IV_STRIPPED		= BIT(4),
 	RX_FLAG_FAILED_FCS_CRC		= BIT(5),
 	RX_FLAG_FAILED_PLCP_CRC 	= BIT(6),
-	RX_FLAG_MACTIME_START		= BIT(7),
+	/* one free bit at 7 */
 	RX_FLAG_NO_SIGNAL_VAL		= BIT(8),
 	RX_FLAG_AMPDU_DETAILS		= BIT(9),
 	RX_FLAG_PN_VALIDATED		= BIT(10),
@@ -1448,8 +1451,10 @@ enum mac80211_rx_flags {
 	RX_FLAG_AMPDU_IS_LAST		= BIT(13),
 	RX_FLAG_AMPDU_DELIM_CRC_ERROR	= BIT(14),
 	RX_FLAG_AMPDU_DELIM_CRC_KNOWN	= BIT(15),
-	RX_FLAG_MACTIME_END		= BIT(16),
-	RX_FLAG_ONLY_MONITOR		= BIT(17),
+	RX_FLAG_MACTIME			= BIT(16) | BIT(17),
+	RX_FLAG_MACTIME_PLCP_START	= 1 << 16,
+	RX_FLAG_MACTIME_START		= 2 << 16,
+	RX_FLAG_MACTIME_END		= 3 << 16,
 	RX_FLAG_SKIP_MONITOR		= BIT(18),
 	RX_FLAG_AMSDU_MORE		= BIT(19),
 	RX_FLAG_RADIOTAP_TLV_AT_END	= BIT(20),
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index f45bec3f562c..0ed82cc263f2 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1776,10 +1776,7 @@ static inline bool txq_has_queue(struct ieee80211_txq *txq)
 static inline bool
 ieee80211_have_rx_timestamp(struct ieee80211_rx_status *status)
 {
-	WARN_ON_ONCE(status->flag & RX_FLAG_MACTIME_START &&
-		     status->flag & RX_FLAG_MACTIME_END);
-	return !!(status->flag & (RX_FLAG_MACTIME_START | RX_FLAG_MACTIME_END |
-				  RX_FLAG_MACTIME_PLCP_START));
+	return status->flag & RX_FLAG_MACTIME;
 }
 
 void ieee80211_vif_inc_num_mcast(struct ieee80211_sub_if_data *sdata);
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index ed680120d5a7..643c54855be6 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -4176,6 +4176,7 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
 				     unsigned int mpdu_offset)
 {
 	u64 ts = status->mactime;
+	bool mactime_plcp_start;
 	struct rate_info ri;
 	u16 rate;
 	u8 n_ltf;
@@ -4183,6 +4184,9 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
 	if (WARN_ON(!ieee80211_have_rx_timestamp(status)))
 		return 0;
 
+	mactime_plcp_start = (status->flag & RX_FLAG_MACTIME) ==
+				RX_FLAG_MACTIME_PLCP_START;
+
 	memset(&ri, 0, sizeof(ri));
 
 	ri.bw = status->bw;
@@ -4197,7 +4201,7 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
 		if (status->enc_flags & RX_ENC_FLAG_SHORT_GI)
 			ri.flags |= RATE_INFO_FLAGS_SHORT_GI;
 		/* TODO/FIXME: is this right? handle other PPDUs */
-		if (status->flag & RX_FLAG_MACTIME_PLCP_START) {
+		if (mactime_plcp_start) {
 			mpdu_offset += 2;
 			ts += 36;
 		}
@@ -4214,7 +4218,7 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
 		 * See P802.11ax_D6.0, section 27.3.4 for
 		 * VHT PPDU format.
 		 */
-		if (status->flag & RX_FLAG_MACTIME_PLCP_START) {
+		if (mactime_plcp_start) {
 			mpdu_offset += 2;
 			ts += 36;
 
@@ -4238,7 +4242,7 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
 		 * See P802.11REVmd_D3.0, section 19.3.2 for
 		 * HT PPDU format.
 		 */
-		if (status->flag & RX_FLAG_MACTIME_PLCP_START) {
+		if (mactime_plcp_start) {
 			mpdu_offset += 2;
 			if (status->enc_flags & RX_ENC_FLAG_HT_GF)
 				ts += 24;
@@ -4266,7 +4270,7 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
 		 * See P802.11REVmd_D3.0, section 21.3.2 for
 		 * VHT PPDU format.
 		 */
-		if (status->flag & RX_FLAG_MACTIME_PLCP_START) {
+		if (mactime_plcp_start) {
 			mpdu_offset += 2;
 			ts += 36;
 
@@ -4288,7 +4292,7 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
 		sband = local->hw.wiphy->bands[status->band];
 		ri.legacy = sband->bitrates[status->rate_idx].bitrate;
 
-		if (status->flag & RX_FLAG_MACTIME_PLCP_START) {
+		if (mactime_plcp_start) {
 			if (status->band == NL80211_BAND_5GHZ) {
 				ts += 20;
 				mpdu_offset += 2;
@@ -4310,7 +4314,7 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
 		return 0;
 
 	/* rewind from end of MPDU */
-	if (status->flag & RX_FLAG_MACTIME_END)
+	if ((status->flag & RX_FLAG_MACTIME) == RX_FLAG_MACTIME_END)
 		ts -= mpdu_len * 8 * 10 / rate;
 
 	ts += mpdu_offset * 8 * 10 / rate;
-- 
cgit v1.2.3


From e62c0fcc0e06a36b40615885eb86eb407ac8d0dd Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 20 Dec 2023 13:41:40 +0200
Subject: wifi: mac80211: allow 64-bit radiotap timestamps

When reporting the radiotap timestamp, the mactime field is
usually unused, we take the data from the device_timestamp.
However, there can be cases where the radiotap timestamp is
better reported as a 64-bit value, so since the mactime is
free, add a flag to support using the mactime as a 64-bit
radiotap timestamp.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Gregory Greenman <gregory.greenman@intel.com>
Reviewed-by: Benjamin Berg <benjamin.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://msgid.link/20231220133549.00c8b9234f0c.Ie3ce5eae33cce88fa01178e7aea94661ded1ac24@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h |  7 ++++++-
 net/mac80211/rx.c      | 13 +++++++++++--
 2 files changed, 17 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 941980c7aa21..46cc44430216 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1367,6 +1367,11 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info)
  *	(including FCS) was received.
  * @RX_FLAG_MACTIME_PLCP_START: The timestamp passed in the RX status (@mactime
  *	field) is valid and contains the time the SYNC preamble was received.
+ * @RX_FLAG_MACTIME_IS_RTAP_TS64: The timestamp passed in the RX status @mactime
+ *	is only for use in the radiotap timestamp header, not otherwise a valid
+ *	@mactime value. Note this is a separate flag so that we continue to see
+ *	%RX_FLAG_MACTIME as unset. Also note that in this case the timestamp is
+ *	reported to be 64 bits wide, not just 32.
  * @RX_FLAG_NO_SIGNAL_VAL: The signal strength value is not present.
  *	Valid only for data frames (mainly A-MPDU)
  * @RX_FLAG_AMPDU_DETAILS: A-MPDU details are known, in particular the reference
@@ -1442,7 +1447,7 @@ enum mac80211_rx_flags {
 	RX_FLAG_IV_STRIPPED		= BIT(4),
 	RX_FLAG_FAILED_FCS_CRC		= BIT(5),
 	RX_FLAG_FAILED_PLCP_CRC 	= BIT(6),
-	/* one free bit at 7 */
+	RX_FLAG_MACTIME_IS_RTAP_TS64	= BIT(7),
 	RX_FLAG_NO_SIGNAL_VAL		= BIT(8),
 	RX_FLAG_AMPDU_DETAILS		= BIT(9),
 	RX_FLAG_PN_VALIDATED		= BIT(10),
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index bbfdcb0ade72..a57c8272c1dc 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -566,7 +566,8 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 
 	if (local->hw.radiotap_timestamp.units_pos >= 0) {
 		u16 accuracy = 0;
-		u8 flags = IEEE80211_RADIOTAP_TIMESTAMP_FLAG_32BIT;
+		u8 flags;
+		u64 ts;
 
 		rthdr->it_present |=
 			cpu_to_le32(BIT(IEEE80211_RADIOTAP_TIMESTAMP));
@@ -575,7 +576,15 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 		while ((pos - (u8 *)rthdr) & 7)
 			pos++;
 
-		put_unaligned_le64(status->device_timestamp, pos);
+		if (status->flag & RX_FLAG_MACTIME_IS_RTAP_TS64) {
+			flags = IEEE80211_RADIOTAP_TIMESTAMP_FLAG_64BIT;
+			ts = status->mactime;
+		} else {
+			flags = IEEE80211_RADIOTAP_TIMESTAMP_FLAG_32BIT;
+			ts = status->device_timestamp;
+		}
+
+		put_unaligned_le64(ts, pos);
 		pos += sizeof(u64);
 
 		if (local->hw.radiotap_timestamp.accuracy >= 0) {
-- 
cgit v1.2.3


From e993af2ed2882f5dade10474d7fd1e2403aa0ab7 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Wed, 20 Dec 2023 13:41:45 +0200
Subject: wifi: mac80211: add a driver callback to check active_links

During ieee80211_set_active_links() we do (among the others):
1. Call drv_change_vif_links() with both old_active and new_active
2. Unassign the chanctx for the removed link(s) (if any)
3. Assign chanctx to the added link(s) (if any)
4. Call drv_change_vif_links() with the new_active links bitmap

The problem here is that during step #1 the driver doesn't know whether
we will activate multiple links simultaneously or are just doing a link
switch, so it can't check there if multiple links are supported/enabled.
(Some of the drivers might enable/disable this option dynamically)

And during step #3, in which the driver already knows that,
returning an error code (for example when multiple links are not
supported or disabled), will cause a warning, and we will still complete
the transition to the new_active links.
(It is hard to undo things in that stage, since we released channels etc.)

Therefore add a driver callback to check if the desired new_active links
will be supported by the driver or not. This callback will be called
in the beginning of ieee80211_set_active_links() so we won't do anything
before we are sure it is supported.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Gregory Greenman <gregory.greenman@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Link: https://msgid.link/20231220133549.64c4d70b33b8.I79708619be76b8ecd4ef3975205b8f903e24a2cd@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h    |  5 +++++
 net/mac80211/driver-ops.h | 20 ++++++++++++++++++++
 net/mac80211/link.c       |  3 +++
 net/mac80211/trace.h      | 25 +++++++++++++++++++++++++
 4 files changed, 53 insertions(+)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 46cc44430216..d400fe2e8668 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -4272,6 +4272,8 @@ struct ieee80211_prep_tx_info {
  *	disable background CAC/radar detection.
  * @net_fill_forward_path: Called from .ndo_fill_forward_path in order to
  *	resolve a path for hardware flow offloading
+ * @can_activate_links: Checks if a specific active_links bitmap is
+ *	supported by the driver.
  * @change_vif_links: Change the valid links on an interface, note that while
  *	removing the old link information is still valid (link_conf pointer),
  *	but may immediately disappear after the function returns. The old or
@@ -4652,6 +4654,9 @@ struct ieee80211_ops {
 				     struct ieee80211_sta *sta,
 				     struct net_device_path_ctx *ctx,
 				     struct net_device_path *path);
+	bool (*can_activate_links)(struct ieee80211_hw *hw,
+				   struct ieee80211_vif *vif,
+				   u16 active_links);
 	int (*change_vif_links)(struct ieee80211_hw *hw,
 				struct ieee80211_vif *vif,
 				u16 old_links, u16 new_links,
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index e9219f927875..eb482fb8c3af 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -1666,6 +1666,26 @@ static inline int drv_net_setup_tc(struct ieee80211_local *local,
 	return ret;
 }
 
+static inline bool drv_can_activate_links(struct ieee80211_local *local,
+					  struct ieee80211_sub_if_data *sdata,
+					  u16 active_links)
+{
+	bool ret = true;
+
+	lockdep_assert_wiphy(local->hw.wiphy);
+
+	if (!check_sdata_in_driver(sdata))
+		return false;
+
+	trace_drv_can_activate_links(local, sdata, active_links);
+	if (local->ops->can_activate_links)
+		ret = local->ops->can_activate_links(&local->hw, &sdata->vif,
+						     active_links);
+	trace_drv_return_bool(local, ret);
+
+	return ret;
+}
+
 int drv_change_vif_links(struct ieee80211_local *local,
 			 struct ieee80211_sub_if_data *sdata,
 			 u16 old_links, u16 new_links,
diff --git a/net/mac80211/link.c b/net/mac80211/link.c
index bf7bd880d062..d4f86955afa6 100644
--- a/net/mac80211/link.c
+++ b/net/mac80211/link.c
@@ -444,6 +444,9 @@ int ieee80211_set_active_links(struct ieee80211_vif *vif, u16 active_links)
 
 	lockdep_assert_wiphy(local->hw.wiphy);
 
+	if (!drv_can_activate_links(local, sdata, active_links))
+		return -EINVAL;
+
 	old_active = sdata->vif.active_links;
 	if (old_active & active_links) {
 		/*
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index 032718d5b298..06835ed4c44f 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -2512,6 +2512,31 @@ TRACE_EVENT(drv_net_setup_tc,
 	)
 );
 
+TRACE_EVENT(drv_can_activate_links,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata,
+		 u16 active_links),
+
+	TP_ARGS(local, sdata, active_links),
+
+	TP_STRUCT__entry(
+		LOCAL_ENTRY
+		VIF_ENTRY
+		__field(u16, active_links)
+	),
+
+	TP_fast_assign(
+		LOCAL_ASSIGN;
+		VIF_ASSIGN;
+		__entry->active_links = active_links;
+	),
+
+	TP_printk(
+		LOCAL_PR_FMT VIF_PR_FMT " requested active_links:0x%04x\n",
+		LOCAL_PR_ARG, VIF_PR_ARG, __entry->active_links
+	)
+);
+
 TRACE_EVENT(drv_change_vif_links,
 	TP_PROTO(struct ieee80211_local *local,
 		 struct ieee80211_sub_if_data *sdata,
-- 
cgit v1.2.3


From 5a78a8121c4d8e37035274c094e3af15fb79f004 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@kernel.org>
Date: Mon, 18 Dec 2023 20:07:42 -0700
Subject: net/ipv6: Remove gc_link warn on in fib6_info_release

A revert of
   3dec89b14d37 ("net/ipv6: Remove expired routes with a separated list of routes")
was sent for net-next. Revert the remainder of 5a08d0065a915
which added a warn on if a fib entry is still on the gc_link list
to avoid compile failures when net is merged to net-next

Signed-off-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20231219030742.25715-1-dsahern@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/ip6_fib.h | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 95ed495c3a40..1ba9f4ddf2f6 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -328,10 +328,8 @@ static inline bool fib6_info_hold_safe(struct fib6_info *f6i)
 
 static inline void fib6_info_release(struct fib6_info *f6i)
 {
-	if (f6i && refcount_dec_and_test(&f6i->fib6_ref)) {
-		DEBUG_NET_WARN_ON_ONCE(!hlist_unhashed(&f6i->gc_link));
+	if (f6i && refcount_dec_and_test(&f6i->fib6_ref))
 		call_rcu(&f6i->rcu, fib6_info_destroy_rcu);
-	}
 }
 
 enum fib6_walk_state {
-- 
cgit v1.2.3


From d68019471995ba47e56a9da355df13a1cdb5bf7e Mon Sep 17 00:00:00 2001
From: Sven Schnelle <svens@linux.ibm.com>
Date: Mon, 18 Dec 2023 08:45:18 +0100
Subject: entry: Move exit to usermode functions to header file

To allow inlining, move exit_to_user_mode() to
entry-common.h.

Signed-off-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20231218074520.1998026-2-svens@linux.ibm.com
---
 include/linux/entry-common.h | 53 +++++++++++++++++++++++++++++++++++++++++++-
 kernel/entry/common.c        | 52 ++++++++-----------------------------------
 2 files changed, 61 insertions(+), 44 deletions(-)

(limited to 'include')

diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index d95ab85f96ba..6a6e98f3805f 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -7,6 +7,10 @@
 #include <linux/syscalls.h>
 #include <linux/seccomp.h>
 #include <linux/sched.h>
+#include <linux/context_tracking.h>
+#include <linux/livepatch.h>
+#include <linux/resume_user_mode.h>
+#include <linux/tick.h>
 
 #include <asm/entry-common.h>
 
@@ -258,6 +262,43 @@ static __always_inline void arch_exit_to_user_mode(void) { }
  */
 void arch_do_signal_or_restart(struct pt_regs *regs);
 
+/**
+ * exit_to_user_mode_loop - do any pending work before leaving to user space
+ */
+unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
+				     unsigned long ti_work);
+
+/**
+ * exit_to_user_mode_prepare - call exit_to_user_mode_loop() if required
+ * @regs:	Pointer to pt_regs on entry stack
+ *
+ * 1) check that interrupts are disabled
+ * 2) call tick_nohz_user_enter_prepare()
+ * 3) call exit_to_user_mode_loop() if any flags from
+ *    EXIT_TO_USER_MODE_WORK are set
+ * 4) check that interrupts are still disabled
+ */
+static __always_inline void exit_to_user_mode_prepare(struct pt_regs *regs)
+{
+	unsigned long ti_work;
+
+	lockdep_assert_irqs_disabled();
+
+	/* Flush pending rcuog wakeup before the last need_resched() check */
+	tick_nohz_user_enter_prepare();
+
+	ti_work = read_thread_flags();
+	if (unlikely(ti_work & EXIT_TO_USER_MODE_WORK))
+		ti_work = exit_to_user_mode_loop(regs, ti_work);
+
+	arch_exit_to_user_mode_prepare(regs, ti_work);
+
+	/* Ensure that kernel state is sane for a return to userspace */
+	kmap_assert_nomap();
+	lockdep_assert_irqs_disabled();
+	lockdep_sys_exit();
+}
+
 /**
  * exit_to_user_mode - Fixup state when exiting to user mode
  *
@@ -276,7 +317,17 @@ void arch_do_signal_or_restart(struct pt_regs *regs);
  * non-instrumentable.
  * The caller has to invoke syscall_exit_to_user_mode_work() before this.
  */
-void exit_to_user_mode(void);
+static __always_inline void exit_to_user_mode(void)
+{
+	instrumentation_begin();
+	trace_hardirqs_on_prepare();
+	lockdep_hardirqs_on_prepare();
+	instrumentation_end();
+
+	user_enter_irqoff();
+	arch_exit_to_user_mode();
+	lockdep_hardirqs_on(CALLER_ADDR0);
+}
 
 /**
  * syscall_exit_to_user_mode_work - Handle work before returning to user mode
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index d7ee4bc3f2ba..7f8f8c16140a 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -123,29 +123,16 @@ noinstr void syscall_enter_from_user_mode_prepare(struct pt_regs *regs)
 	instrumentation_end();
 }
 
-/* See comment for exit_to_user_mode() in entry-common.h */
-static __always_inline void __exit_to_user_mode(void)
-{
-	instrumentation_begin();
-	trace_hardirqs_on_prepare();
-	lockdep_hardirqs_on_prepare();
-	instrumentation_end();
-
-	user_enter_irqoff();
-	arch_exit_to_user_mode();
-	lockdep_hardirqs_on(CALLER_ADDR0);
-}
-
-void noinstr exit_to_user_mode(void)
-{
-	__exit_to_user_mode();
-}
-
 /* Workaround to allow gradual conversion of architecture code */
 void __weak arch_do_signal_or_restart(struct pt_regs *regs) { }
 
-static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
-					    unsigned long ti_work)
+/**
+ * exit_to_user_mode_loop - do any pending work before leaving to user space
+ * @regs:	Pointer to pt_regs on entry stack
+ * @ti_work:	TIF work flags as read by the caller
+ */
+__always_inline unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
+						     unsigned long ti_work)
 {
 	/*
 	 * Before returning to user space ensure that all pending work
@@ -190,27 +177,6 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
 	return ti_work;
 }
 
-static void exit_to_user_mode_prepare(struct pt_regs *regs)
-{
-	unsigned long ti_work;
-
-	lockdep_assert_irqs_disabled();
-
-	/* Flush pending rcuog wakeup before the last need_resched() check */
-	tick_nohz_user_enter_prepare();
-
-	ti_work = read_thread_flags();
-	if (unlikely(ti_work & EXIT_TO_USER_MODE_WORK))
-		ti_work = exit_to_user_mode_loop(regs, ti_work);
-
-	arch_exit_to_user_mode_prepare(regs, ti_work);
-
-	/* Ensure that kernel state is sane for a return to userspace */
-	kmap_assert_nomap();
-	lockdep_assert_irqs_disabled();
-	lockdep_sys_exit();
-}
-
 /*
  * If SYSCALL_EMU is set, then the only reason to report is when
  * SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP).  This syscall
@@ -295,7 +261,7 @@ __visible noinstr void syscall_exit_to_user_mode(struct pt_regs *regs)
 	instrumentation_begin();
 	__syscall_exit_to_user_mode_work(regs);
 	instrumentation_end();
-	__exit_to_user_mode();
+	exit_to_user_mode();
 }
 
 noinstr void irqentry_enter_from_user_mode(struct pt_regs *regs)
@@ -308,7 +274,7 @@ noinstr void irqentry_exit_to_user_mode(struct pt_regs *regs)
 	instrumentation_begin();
 	exit_to_user_mode_prepare(regs);
 	instrumentation_end();
-	__exit_to_user_mode();
+	exit_to_user_mode();
 }
 
 noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
-- 
cgit v1.2.3


From caf4062e35b21cd7d3d35ac2f58f9765d02d32a0 Mon Sep 17 00:00:00 2001
From: Sven Schnelle <svens@linux.ibm.com>
Date: Mon, 18 Dec 2023 08:45:19 +0100
Subject: entry: Move enter_from_user_mode() to header file

To allow inlining of enter_from_user_mode(), move it to
entry-common.h.

Signed-off-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20231218074520.1998026-3-svens@linux.ibm.com
---
 include/linux/entry-common.h | 15 ++++++++++++++-
 kernel/entry/common.c        | 26 +++-----------------------
 2 files changed, 17 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index 6a6e98f3805f..c4205390448e 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -11,6 +11,7 @@
 #include <linux/livepatch.h>
 #include <linux/resume_user_mode.h>
 #include <linux/tick.h>
+#include <linux/kmsan.h>
 
 #include <asm/entry-common.h>
 
@@ -102,7 +103,19 @@ static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs) {}
  * done between establishing state and enabling interrupts. The caller must
  * enable interrupts before invoking syscall_enter_from_user_mode_work().
  */
-void enter_from_user_mode(struct pt_regs *regs);
+static __always_inline void enter_from_user_mode(struct pt_regs *regs)
+{
+	arch_enter_from_user_mode(regs);
+	lockdep_hardirqs_off(CALLER_ADDR0);
+
+	CT_WARN_ON(__ct_state() != CONTEXT_USER);
+	user_exit_irqoff();
+
+	instrumentation_begin();
+	kmsan_unpoison_entry_regs(regs);
+	trace_hardirqs_off_finish();
+	instrumentation_end();
+}
 
 /**
  * syscall_enter_from_user_mode_prepare - Establish state and enable interrupts
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 7f8f8c16140a..0616f239da4b 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -15,26 +15,6 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
 
-/* See comment for enter_from_user_mode() in entry-common.h */
-static __always_inline void __enter_from_user_mode(struct pt_regs *regs)
-{
-	arch_enter_from_user_mode(regs);
-	lockdep_hardirqs_off(CALLER_ADDR0);
-
-	CT_WARN_ON(__ct_state() != CONTEXT_USER);
-	user_exit_irqoff();
-
-	instrumentation_begin();
-	kmsan_unpoison_entry_regs(regs);
-	trace_hardirqs_off_finish();
-	instrumentation_end();
-}
-
-void noinstr enter_from_user_mode(struct pt_regs *regs)
-{
-	__enter_from_user_mode(regs);
-}
-
 static inline void syscall_enter_audit(struct pt_regs *regs, long syscall)
 {
 	if (unlikely(audit_context())) {
@@ -105,7 +85,7 @@ noinstr long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall)
 {
 	long ret;
 
-	__enter_from_user_mode(regs);
+	enter_from_user_mode(regs);
 
 	instrumentation_begin();
 	local_irq_enable();
@@ -117,7 +97,7 @@ noinstr long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall)
 
 noinstr void syscall_enter_from_user_mode_prepare(struct pt_regs *regs)
 {
-	__enter_from_user_mode(regs);
+	enter_from_user_mode(regs);
 	instrumentation_begin();
 	local_irq_enable();
 	instrumentation_end();
@@ -266,7 +246,7 @@ __visible noinstr void syscall_exit_to_user_mode(struct pt_regs *regs)
 
 noinstr void irqentry_enter_from_user_mode(struct pt_regs *regs)
 {
-	__enter_from_user_mode(regs);
+	enter_from_user_mode(regs);
 }
 
 noinstr void irqentry_exit_to_user_mode(struct pt_regs *regs)
-- 
cgit v1.2.3


From 221a164035fd8b554a44bd7c4bf8e7715a497561 Mon Sep 17 00:00:00 2001
From: Sven Schnelle <svens@linux.ibm.com>
Date: Mon, 18 Dec 2023 08:45:20 +0100
Subject: entry: Move syscall_enter_from_user_mode() to header file

To allow inlining of syscall_enter_from_user_mode(), move it
to entry-common.h.

Signed-off-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20231218074520.1998026-4-svens@linux.ibm.com
---
 include/linux/entry-common.h | 27 +++++++++++++++++++++++++--
 kernel/entry/common.c        | 32 +-------------------------------
 2 files changed, 26 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index c4205390448e..b0fb775a600d 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -134,6 +134,9 @@ static __always_inline void enter_from_user_mode(struct pt_regs *regs)
  */
 void syscall_enter_from_user_mode_prepare(struct pt_regs *regs);
 
+long syscall_trace_enter(struct pt_regs *regs, long syscall,
+			 unsigned long work);
+
 /**
  * syscall_enter_from_user_mode_work - Check and handle work before invoking
  *				       a syscall
@@ -157,7 +160,15 @@ void syscall_enter_from_user_mode_prepare(struct pt_regs *regs);
  *     ptrace_report_syscall_entry(), __secure_computing(), trace_sys_enter()
  *  2) Invocation of audit_syscall_entry()
  */
-long syscall_enter_from_user_mode_work(struct pt_regs *regs, long syscall);
+static __always_inline long syscall_enter_from_user_mode_work(struct pt_regs *regs, long syscall)
+{
+	unsigned long work = READ_ONCE(current_thread_info()->syscall_work);
+
+	if (work & SYSCALL_WORK_ENTER)
+		syscall = syscall_trace_enter(regs, syscall, work);
+
+	return syscall;
+}
 
 /**
  * syscall_enter_from_user_mode - Establish state and check and handle work
@@ -176,7 +187,19 @@ long syscall_enter_from_user_mode_work(struct pt_regs *regs, long syscall);
  * Returns: The original or a modified syscall number. See
  * syscall_enter_from_user_mode_work() for further explanation.
  */
-long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall);
+static __always_inline long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall)
+{
+	long ret;
+
+	enter_from_user_mode(regs);
+
+	instrumentation_begin();
+	local_irq_enable();
+	ret = syscall_enter_from_user_mode_work(regs, syscall);
+	instrumentation_end();
+
+	return ret;
+}
 
 /**
  * local_irq_enable_exit_to_user - Exit to user variant of local_irq_enable()
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 0616f239da4b..88cb3c88aaa5 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -25,7 +25,7 @@ static inline void syscall_enter_audit(struct pt_regs *regs, long syscall)
 	}
 }
 
-static long syscall_trace_enter(struct pt_regs *regs, long syscall,
+long syscall_trace_enter(struct pt_regs *regs, long syscall,
 				unsigned long work)
 {
 	long ret = 0;
@@ -65,36 +65,6 @@ static long syscall_trace_enter(struct pt_regs *regs, long syscall,
 	return ret ? : syscall;
 }
 
-static __always_inline long
-__syscall_enter_from_user_work(struct pt_regs *regs, long syscall)
-{
-	unsigned long work = READ_ONCE(current_thread_info()->syscall_work);
-
-	if (work & SYSCALL_WORK_ENTER)
-		syscall = syscall_trace_enter(regs, syscall, work);
-
-	return syscall;
-}
-
-long syscall_enter_from_user_mode_work(struct pt_regs *regs, long syscall)
-{
-	return __syscall_enter_from_user_work(regs, syscall);
-}
-
-noinstr long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall)
-{
-	long ret;
-
-	enter_from_user_mode(regs);
-
-	instrumentation_begin();
-	local_irq_enable();
-	ret = __syscall_enter_from_user_work(regs, syscall);
-	instrumentation_end();
-
-	return ret;
-}
-
 noinstr void syscall_enter_from_user_mode_prepare(struct pt_regs *regs)
 {
 	enter_from_user_mode(regs);
-- 
cgit v1.2.3


From 3fde94b6e930f5a0fd4f6458da8d559c898f2322 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 20 Nov 2023 17:29:58 +0100
Subject: netfilter: flowtable: reorder nf_flowtable struct members

Place the read-mostly parts accessed by the datapath first.

In particular, we do access ->flags member (to see if HW offload
is enabled) for every single packet, but this is placed in the 5th
cacheline.

priority could stay where it is, but move it too to cover a hole.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_flow_table.h | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index 692d5955911c..956c752ceb31 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -74,12 +74,13 @@ enum nf_flowtable_flags {
 };
 
 struct nf_flowtable {
-	struct list_head		list;
-	struct rhashtable		rhashtable;
-	int				priority;
+	unsigned int			flags;		/* readonly in datapath */
+	int				priority;	/* control path (padding hole) */
+	struct rhashtable		rhashtable;	/* datapath, read-mostly members come first */
+
+	struct list_head		list;		/* slowpath parts */
 	const struct nf_flowtable_type	*type;
 	struct delayed_work		gc_work;
-	unsigned int			flags;
 	struct flow_block		flow_block;
 	struct rw_semaphore		flow_block_lock; /* Guards flow_block */
 	possible_net_t			net;
-- 
cgit v1.2.3


From bbcd80f53a5e8c27c2511f539fec8c373f500cf4 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 15 Dec 2023 13:32:05 +0100
Subject: mtd: rawnand: Prevent crossing LUN boundaries during sequential reads
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The ONFI specification states that devices do not need to support
sequential reads across LUN boundaries. In order to prevent such event
from happening and possibly failing, let's introduce the concept of
"pause" in the sequential read to handle these cases. The first/last
pages remain the same but any time we cross a LUN boundary we will end
and restart (if relevant) the sequential read operation.

Cc: stable@vger.kernel.org
Fixes: 003fe4b9545b ("mtd: rawnand: Support for sequential cache reads")
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Tested-by: Martin Hundebøll <martin@geanix.com>
Link: https://lore.kernel.org/linux-mtd/20231215123208.516590-2-miquel.raynal@bootlin.com
---
 drivers/mtd/nand/raw/nand_base.c | 43 ++++++++++++++++++++++++++++++++++------
 include/linux/mtd/rawnand.h      |  2 ++
 2 files changed, 39 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 9e24bedffd89..04e80ace4182 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -1207,6 +1207,23 @@ static int nand_lp_exec_read_page_op(struct nand_chip *chip, unsigned int page,
 	return nand_exec_op(chip, &op);
 }
 
+static void rawnand_cap_cont_reads(struct nand_chip *chip)
+{
+	struct nand_memory_organization *memorg;
+	unsigned int pages_per_lun, first_lun, last_lun;
+
+	memorg = nanddev_get_memorg(&chip->base);
+	pages_per_lun = memorg->pages_per_eraseblock * memorg->eraseblocks_per_lun;
+	first_lun = chip->cont_read.first_page / pages_per_lun;
+	last_lun = chip->cont_read.last_page / pages_per_lun;
+
+	/* Prevent sequential cache reads across LUN boundaries */
+	if (first_lun != last_lun)
+		chip->cont_read.pause_page = first_lun * pages_per_lun + pages_per_lun - 1;
+	else
+		chip->cont_read.pause_page = chip->cont_read.last_page;
+}
+
 static int nand_lp_exec_cont_read_page_op(struct nand_chip *chip, unsigned int page,
 					  unsigned int offset_in_page, void *buf,
 					  unsigned int len, bool check_only)
@@ -1225,7 +1242,7 @@ static int nand_lp_exec_cont_read_page_op(struct nand_chip *chip, unsigned int p
 		NAND_OP_DATA_IN(len, buf, 0),
 	};
 	struct nand_op_instr cont_instrs[] = {
-		NAND_OP_CMD(page == chip->cont_read.last_page ?
+		NAND_OP_CMD(page == chip->cont_read.pause_page ?
 			    NAND_CMD_READCACHEEND : NAND_CMD_READCACHESEQ,
 			    NAND_COMMON_TIMING_NS(conf, tWB_max)),
 		NAND_OP_WAIT_RDY(NAND_COMMON_TIMING_MS(conf, tR_max),
@@ -1262,16 +1279,29 @@ static int nand_lp_exec_cont_read_page_op(struct nand_chip *chip, unsigned int p
 	}
 
 	if (page == chip->cont_read.first_page)
-		return nand_exec_op(chip, &start_op);
+		ret = nand_exec_op(chip, &start_op);
 	else
-		return nand_exec_op(chip, &cont_op);
+		ret = nand_exec_op(chip, &cont_op);
+	if (ret)
+		return ret;
+
+	if (!chip->cont_read.ongoing)
+		return 0;
+
+	if (page == chip->cont_read.pause_page &&
+	    page != chip->cont_read.last_page) {
+		chip->cont_read.first_page = chip->cont_read.pause_page + 1;
+		rawnand_cap_cont_reads(chip);
+	} else if (page == chip->cont_read.last_page) {
+		chip->cont_read.ongoing = false;
+	}
+
+	return 0;
 }
 
 static bool rawnand_cont_read_ongoing(struct nand_chip *chip, unsigned int page)
 {
-	return chip->cont_read.ongoing &&
-		page >= chip->cont_read.first_page &&
-		page <= chip->cont_read.last_page;
+	return chip->cont_read.ongoing && page >= chip->cont_read.first_page;
 }
 
 /**
@@ -3445,6 +3475,7 @@ static void rawnand_enable_cont_reads(struct nand_chip *chip, unsigned int page,
 	if (col)
 		chip->cont_read.first_page++;
 	chip->cont_read.last_page = page + ((readlen >> chip->page_shift) & chip->pagemask);
+	rawnand_cap_cont_reads(chip);
 }
 
 /**
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index c29ace15a053..9d0fc5109af6 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -1265,6 +1265,7 @@ struct nand_secure_region {
  * @cont_read: Sequential page read internals
  * @cont_read.ongoing: Whether a continuous read is ongoing or not
  * @cont_read.first_page: Start of the continuous read operation
+ * @cont_read.pause_page: End of the current sequential cache read operation
  * @cont_read.last_page: End of the continuous read operation
  * @controller: The hardware controller	structure which is shared among multiple
  *              independent devices
@@ -1321,6 +1322,7 @@ struct nand_chip {
 	struct {
 		bool ongoing;
 		unsigned int first_page;
+		unsigned int pause_page;
 		unsigned int last_page;
 	} cont_read;
 
-- 
cgit v1.2.3


From 8e6e83d77227d9ba39e0c7b50693f1b4f8728006 Mon Sep 17 00:00:00 2001
From: Kundan Kumar <kundan.kumar@samsung.com>
Date: Fri, 22 Dec 2023 15:47:07 +0530
Subject: block: skip start/end time stamping for passthrough IO

commit 41fa722239b4 ("blk-mq: do not include passthrough requests in I/O
accounting")' disables I/O accounting for passthrough requests. Since tools
like 'iostat' do not show anything useful for passthrough I/O, it's
wasteful to do start/end time-stamping. So do away with that.

Avoiding the time-stamping improves the I/O performance by ~7%

Signed-off-by: Kundan Kumar <kundan.kumar@samsung.com>
Signed-off-by: Kanchan Joshi <joshi.k@samsung.com>
Link: https://lore.kernel.org/r/20231222101707.6921-1-kundan.kumar@samsung.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blk-mq.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'include')

diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 1ab3081c82ed..a676e116085f 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -830,6 +830,12 @@ void blk_mq_end_request_batch(struct io_comp_batch *ib);
  */
 static inline bool blk_mq_need_time_stamp(struct request *rq)
 {
+	/*
+	 * passthrough io doesn't use iostat accounting, cgroup stats
+	 * and io scheduler functionalities.
+	 */
+	if (blk_rq_is_passthrough(rq))
+		return false;
 	return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS | RQF_USE_SCHED));
 }
 
-- 
cgit v1.2.3


From fa224d0c094a458e9ebf5ea9b1c696136b7af427 Mon Sep 17 00:00:00 2001
From: Iulia Tanasescu <iulia.tanasescu@nxp.com>
Date: Mon, 13 Nov 2023 17:38:00 +0200
Subject: Bluetooth: ISO: Reassociate a socket with an active BIS

For ISO Broadcast, all BISes from a BIG have the same lifespan - they
cannot be created or terminated independently from each other.

This links together all BIS hcons that are part of the same BIG, so all
hcons are kept alive as long as the BIG is active.

If multiple BIS sockets are opened for a BIG handle, and only part of
them are closed at some point, the associated hcons will be marked as
open. If new sockets will later be opened for the same BIG, they will
be reassociated with the open BIS hcons.

All BIS hcons will be cleaned up and the BIG will be terminated when
the last BIS socket is closed from userspace.

Signed-off-by: Iulia Tanasescu <iulia.tanasescu@nxp.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci_core.h | 24 ++++++++++++
 net/bluetooth/hci_conn.c         | 32 +++++++++++++++-
 net/bluetooth/iso.c              | 79 +++++++++++++++++++++++++++++++++++++++-
 3 files changed, 131 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index a3a1ea2696a8..6a32c06d7fdc 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1297,6 +1297,30 @@ static inline struct hci_conn *hci_conn_hash_lookup_big(struct hci_dev *hdev,
 	return NULL;
 }
 
+static inline struct hci_conn *
+hci_conn_hash_lookup_big_state(struct hci_dev *hdev, __u8 handle,  __u16 state)
+{
+	struct hci_conn_hash *h = &hdev->conn_hash;
+	struct hci_conn  *c;
+
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(c, &h->list, list) {
+		if (bacmp(&c->dst, BDADDR_ANY) || c->type != ISO_LINK ||
+			c->state != state)
+			continue;
+
+		if (handle == c->iso_qos.bcast.big) {
+			rcu_read_unlock();
+			return c;
+		}
+	}
+
+	rcu_read_unlock();
+
+	return NULL;
+}
+
 static inline struct hci_conn *
 hci_conn_hash_lookup_pa_sync_big_handle(struct hci_dev *hdev, __u8 big)
 {
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 2cee330188ce..a09071059214 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -1086,8 +1086,9 @@ static void hci_conn_cleanup_child(struct hci_conn *conn, u8 reason)
 			hci_conn_failed(conn, reason);
 		break;
 	case ISO_LINK:
-		if (conn->state != BT_CONNECTED &&
-		    !test_bit(HCI_CONN_CREATE_CIS, &conn->flags))
+		if ((conn->state != BT_CONNECTED &&
+		    !test_bit(HCI_CONN_CREATE_CIS, &conn->flags)) ||
+		    test_bit(HCI_CONN_BIG_CREATED, &conn->flags))
 			hci_conn_failed(conn, reason);
 		break;
 	}
@@ -2228,7 +2229,17 @@ struct hci_conn *hci_bind_bis(struct hci_dev *hdev, bdaddr_t *dst,
 			      __u8 base_len, __u8 *base)
 {
 	struct hci_conn *conn;
+	struct hci_conn *parent;
 	__u8 eir[HCI_MAX_PER_AD_LENGTH];
+	struct hci_link *link;
+
+	/* Look for any BIS that is open for rebinding */
+	conn = hci_conn_hash_lookup_big_state(hdev, qos->bcast.big, BT_OPEN);
+	if (conn) {
+		memcpy(qos, &conn->iso_qos, sizeof(*qos));
+		conn->state = BT_CONNECTED;
+		return conn;
+	}
 
 	if (base_len && base)
 		base_len = eir_append_service_data(eir, 0,  0x1851,
@@ -2256,6 +2267,20 @@ struct hci_conn *hci_bind_bis(struct hci_dev *hdev, bdaddr_t *dst,
 	conn->iso_qos = *qos;
 	conn->state = BT_BOUND;
 
+	/* Link BISes together */
+	parent = hci_conn_hash_lookup_big(hdev,
+					  conn->iso_qos.bcast.big);
+	if (parent && parent != conn) {
+		link = hci_conn_link(parent, conn);
+		if (!link) {
+			hci_conn_drop(conn);
+			return ERR_PTR(-ENOLINK);
+		}
+
+		/* Link takes the refcount */
+		hci_conn_drop(conn);
+	}
+
 	return conn;
 }
 
@@ -2287,6 +2312,9 @@ struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst,
 	if (IS_ERR(conn))
 		return conn;
 
+	if (conn->state == BT_CONNECTED)
+		return conn;
+
 	data.big = qos->bcast.big;
 	data.bis = qos->bcast.bis;
 
diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c
index e01b6abe36fb..e49f00e8a6a6 100644
--- a/net/bluetooth/iso.c
+++ b/net/bluetooth/iso.c
@@ -574,19 +574,68 @@ static struct sock *iso_get_sock_listen(bdaddr_t *src, bdaddr_t *dst,
 			continue;
 
 		/* Exact match. */
-		if (!bacmp(&iso_pi(sk)->src, src))
+		if (!bacmp(&iso_pi(sk)->src, src)) {
+			sock_hold(sk);
 			break;
+		}
 
 		/* Closest match */
-		if (!bacmp(&iso_pi(sk)->src, BDADDR_ANY))
+		if (!bacmp(&iso_pi(sk)->src, BDADDR_ANY)) {
+			if (sk1)
+				sock_put(sk1);
+
 			sk1 = sk;
+			sock_hold(sk1);
+		}
 	}
 
+	if (sk && sk1)
+		sock_put(sk1);
+
 	read_unlock(&iso_sk_list.lock);
 
 	return sk ? sk : sk1;
 }
 
+static struct sock *iso_get_sock_big(struct sock *match_sk, bdaddr_t *src,
+				     bdaddr_t *dst, uint8_t big)
+{
+	struct sock *sk = NULL;
+
+	read_lock(&iso_sk_list.lock);
+
+	sk_for_each(sk, &iso_sk_list.head) {
+		if (match_sk == sk)
+			continue;
+
+		/* Look for sockets that have already been
+		 * connected to the BIG
+		 */
+		if (sk->sk_state != BT_CONNECTED &&
+		    sk->sk_state != BT_CONNECT)
+			continue;
+
+		/* Match Broadcast destination */
+		if (bacmp(&iso_pi(sk)->dst, dst))
+			continue;
+
+		/* Match BIG handle */
+		if (iso_pi(sk)->qos.bcast.big != big)
+			continue;
+
+		/* Match source address */
+		if (bacmp(&iso_pi(sk)->src, src))
+			continue;
+
+		sock_hold(sk);
+		break;
+	}
+
+	read_unlock(&iso_sk_list.lock);
+
+	return sk;
+}
+
 static void iso_sock_destruct(struct sock *sk)
 {
 	BT_DBG("sk %p", sk);
@@ -639,6 +688,28 @@ static void iso_sock_kill(struct sock *sk)
 
 static void iso_sock_disconn(struct sock *sk)
 {
+	struct sock *bis_sk;
+	struct hci_conn *hcon = iso_pi(sk)->conn->hcon;
+
+	if (test_bit(HCI_CONN_BIG_CREATED, &hcon->flags)) {
+		bis_sk = iso_get_sock_big(sk, &iso_pi(sk)->src,
+					  &iso_pi(sk)->dst,
+					  iso_pi(sk)->qos.bcast.big);
+
+		/* If there are any other connected sockets for the
+		 * same BIG, just delete the sk and leave the bis
+		 * hcon active, in case later rebinding is needed.
+		 */
+		if (bis_sk) {
+			hcon->state = BT_OPEN;
+			iso_pi(sk)->conn->hcon = NULL;
+			iso_sock_clear_timer(sk);
+			iso_chan_del(sk, bt_to_errno(hcon->abort_reason));
+			sock_put(bis_sk);
+			return;
+		}
+	}
+
 	sk->sk_state = BT_DISCONN;
 	iso_sock_set_timer(sk, ISO_DISCONN_TIMEOUT);
 	iso_conn_lock(iso_pi(sk)->conn);
@@ -1751,6 +1822,7 @@ static void iso_conn_ready(struct iso_conn *conn)
 		parent->sk_data_ready(parent);
 
 		release_sock(parent);
+		sock_put(parent);
 	}
 }
 
@@ -1835,6 +1907,7 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags)
 				if (err) {
 					bt_dev_err(hdev, "hci_le_big_create_sync: %d",
 						   err);
+					sock_put(sk);
 					sk = NULL;
 				}
 			}
@@ -1867,6 +1940,8 @@ done:
 	if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags))
 		*flags |= HCI_PROTO_DEFER;
 
+	sock_put(sk);
+
 	return lm;
 }
 
-- 
cgit v1.2.3


From 78db544b5d276b70c6ea2c2909ffed96b10229a3 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Wed, 6 Sep 2023 14:13:35 -0700
Subject: Bluetooth: hci_core: Remove le_restart_scan work

This removes le_restart_scan work and instead just disables controller
duplicate filtering when discovery result_filtering is enabled and
HCI_QUIRK_STRICT_DUPLICATE_FILTER is set.

Link: https://github.com/bluez/bluez/issues/573
Link: https://github.com/bluez/bluez/issues/572
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci_core.h |  1 -
 net/bluetooth/hci_sync.c         | 96 +++-------------------------------------
 net/bluetooth/mgmt.c             | 17 -------
 3 files changed, 7 insertions(+), 107 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 6a32c06d7fdc..cf560a9e16b6 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -539,7 +539,6 @@ struct hci_dev {
 	struct work_struct	tx_work;
 
 	struct delayed_work	le_scan_disable;
-	struct delayed_work	le_scan_restart;
 
 	struct sk_buff_head	rx_q;
 	struct sk_buff_head	raw_q;
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index d85a7091a116..3563a90ed2ac 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -348,8 +348,6 @@ static void le_scan_disable(struct work_struct *work)
 	if (!hci_dev_test_flag(hdev, HCI_LE_SCAN))
 		goto _return;
 
-	cancel_delayed_work(&hdev->le_scan_restart);
-
 	status = hci_cmd_sync_queue(hdev, scan_disable_sync, NULL, NULL);
 	if (status) {
 		bt_dev_err(hdev, "failed to disable LE scan: %d", status);
@@ -397,71 +395,6 @@ _return:
 
 static int hci_le_set_scan_enable_sync(struct hci_dev *hdev, u8 val,
 				       u8 filter_dup);
-static int hci_le_scan_restart_sync(struct hci_dev *hdev)
-{
-	/* If controller is not scanning we are done. */
-	if (!hci_dev_test_flag(hdev, HCI_LE_SCAN))
-		return 0;
-
-	if (hdev->scanning_paused) {
-		bt_dev_dbg(hdev, "Scanning is paused for suspend");
-		return 0;
-	}
-
-	hci_le_set_scan_enable_sync(hdev, LE_SCAN_DISABLE, 0x00);
-	return hci_le_set_scan_enable_sync(hdev, LE_SCAN_ENABLE,
-					   LE_SCAN_FILTER_DUP_ENABLE);
-}
-
-static void le_scan_restart(struct work_struct *work)
-{
-	struct hci_dev *hdev = container_of(work, struct hci_dev,
-					    le_scan_restart.work);
-	unsigned long timeout, duration, scan_start, now;
-	int status;
-
-	bt_dev_dbg(hdev, "");
-
-	status = hci_le_scan_restart_sync(hdev);
-	if (status) {
-		bt_dev_err(hdev, "failed to restart LE scan: status %d",
-			   status);
-		return;
-	}
-
-	hci_dev_lock(hdev);
-
-	if (!test_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks) ||
-	    !hdev->discovery.scan_start)
-		goto unlock;
-
-	/* When the scan was started, hdev->le_scan_disable has been queued
-	 * after duration from scan_start. During scan restart this job
-	 * has been canceled, and we need to queue it again after proper
-	 * timeout, to make sure that scan does not run indefinitely.
-	 */
-	duration = hdev->discovery.scan_duration;
-	scan_start = hdev->discovery.scan_start;
-	now = jiffies;
-	if (now - scan_start <= duration) {
-		int elapsed;
-
-		if (now >= scan_start)
-			elapsed = now - scan_start;
-		else
-			elapsed = ULONG_MAX - scan_start + now;
-
-		timeout = duration - elapsed;
-	} else {
-		timeout = 0;
-	}
-
-	queue_delayed_work(hdev->req_workqueue,
-			   &hdev->le_scan_disable, timeout);
-
-unlock:
-	hci_dev_unlock(hdev);
-}
 
 static int reenable_adv_sync(struct hci_dev *hdev, void *data)
 {
@@ -630,7 +563,6 @@ void hci_cmd_sync_init(struct hci_dev *hdev)
 	INIT_WORK(&hdev->cmd_sync_cancel_work, hci_cmd_sync_cancel_work);
 	INIT_WORK(&hdev->reenable_adv_work, reenable_adv);
 	INIT_DELAYED_WORK(&hdev->le_scan_disable, le_scan_disable);
-	INIT_DELAYED_WORK(&hdev->le_scan_restart, le_scan_restart);
 	INIT_DELAYED_WORK(&hdev->adv_instance_expire, adv_timeout_expire);
 }
 
@@ -4960,7 +4892,6 @@ int hci_dev_close_sync(struct hci_dev *hdev)
 	cancel_delayed_work(&hdev->power_off);
 	cancel_delayed_work(&hdev->ncmd_timer);
 	cancel_delayed_work(&hdev->le_scan_disable);
-	cancel_delayed_work(&hdev->le_scan_restart);
 
 	hci_request_cancel_all(hdev);
 
@@ -5178,7 +5109,6 @@ int hci_stop_discovery_sync(struct hci_dev *hdev)
 
 		if (hci_dev_test_flag(hdev, HCI_LE_SCAN)) {
 			cancel_delayed_work(&hdev->le_scan_disable);
-			cancel_delayed_work(&hdev->le_scan_restart);
 
 			err = hci_scan_disable_sync(hdev);
 			if (err)
@@ -5686,19 +5616,18 @@ static int hci_active_scan_sync(struct hci_dev *hdev, uint16_t interval)
 	if (err < 0)
 		own_addr_type = ADDR_LE_DEV_PUBLIC;
 
-	if (hci_is_adv_monitoring(hdev)) {
+	if (hci_is_adv_monitoring(hdev) ||
+	    (test_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks) &&
+	    hdev->discovery.result_filtering)) {
 		/* Duplicate filter should be disabled when some advertisement
 		 * monitor is activated, otherwise AdvMon can only receive one
 		 * advertisement for one peer(*) during active scanning, and
 		 * might report loss to these peers.
 		 *
-		 * Note that different controllers have different meanings of
-		 * |duplicate|. Some of them consider packets with the same
-		 * address as duplicate, and others consider packets with the
-		 * same address and the same RSSI as duplicate. Although in the
-		 * latter case we don't need to disable duplicate filter, but
-		 * it is common to have active scanning for a short period of
-		 * time, the power impact should be neglectable.
+		 * If controller does strict duplicate filtering and the
+		 * discovery requires result filtering disables controller based
+		 * filtering since that can cause reports that would match the
+		 * host filter to not be reported.
 		 */
 		filter_dup = LE_SCAN_FILTER_DUP_DISABLE;
 	}
@@ -5778,17 +5707,6 @@ int hci_start_discovery_sync(struct hci_dev *hdev)
 
 	bt_dev_dbg(hdev, "timeout %u ms", jiffies_to_msecs(timeout));
 
-	/* When service discovery is used and the controller has a
-	 * strict duplicate filter, it is important to remember the
-	 * start and duration of the scan. This is required for
-	 * restarting scanning during the discovery phase.
-	 */
-	if (test_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks) &&
-	    hdev->discovery.result_filtering) {
-		hdev->discovery.scan_start = jiffies;
-		hdev->discovery.scan_duration = timeout;
-	}
-
 	queue_delayed_work(hdev->req_workqueue, &hdev->le_scan_disable,
 			   timeout);
 	return 0;
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 9dd815b6603f..bb72ff6eb22f 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -10145,21 +10145,6 @@ static bool eir_has_uuids(u8 *eir, u16 eir_len, u16 uuid_count, u8 (*uuids)[16])
 	return false;
 }
 
-static void restart_le_scan(struct hci_dev *hdev)
-{
-	/* If controller is not scanning we are done. */
-	if (!hci_dev_test_flag(hdev, HCI_LE_SCAN))
-		return;
-
-	if (time_after(jiffies + DISCOV_LE_RESTART_DELAY,
-		       hdev->discovery.scan_start +
-		       hdev->discovery.scan_duration))
-		return;
-
-	queue_delayed_work(hdev->req_workqueue, &hdev->le_scan_restart,
-			   DISCOV_LE_RESTART_DELAY);
-}
-
 static bool is_filter_match(struct hci_dev *hdev, s8 rssi, u8 *eir,
 			    u16 eir_len, u8 *scan_rsp, u8 scan_rsp_len)
 {
@@ -10194,8 +10179,6 @@ static bool is_filter_match(struct hci_dev *hdev, s8 rssi, u8 *eir,
 	 * scanning to ensure updated result with updated RSSI values.
 	 */
 	if (test_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks)) {
-		restart_le_scan(hdev);
-
 		/* Validate RSSI value against the RSSI threshold once more. */
 		if (hdev->discovery.rssi != HCI_RSSI_INVALID &&
 		    rssi < hdev->discovery.rssi)
-- 
cgit v1.2.3


From d03376c185926098cb4d668d6458801eb785c0a5 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Thu, 30 Nov 2023 14:58:03 +0100
Subject: Bluetooth: Fix bogus check for re-auth no supported with non-ssp

This reverts 19f8def031bfa50c579149b200bfeeb919727b27
"Bluetooth: Fix auth_complete_evt for legacy units" which seems to be
working around a bug on a broken controller rather then any limitation
imposed by the Bluetooth spec, in fact if there ws not possible to
re-auth the command shall fail not succeed.

Fixes: 19f8def031bf ("Bluetooth: Fix auth_complete_evt for legacy units")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci_core.h |  1 -
 net/bluetooth/hci_conn.c         |  8 +++-----
 net/bluetooth/hci_event.c        | 11 ++---------
 3 files changed, 5 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index cf560a9e16b6..8f8dd9173714 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -956,7 +956,6 @@ void hci_inquiry_cache_flush(struct hci_dev *hdev);
 /* ----- HCI Connections ----- */
 enum {
 	HCI_CONN_AUTH_PEND,
-	HCI_CONN_REAUTH_PEND,
 	HCI_CONN_ENCRYPT_PEND,
 	HCI_CONN_RSWITCH_PEND,
 	HCI_CONN_MODE_CHANGE_PEND,
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index a09071059214..a13408183022 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -2449,12 +2449,10 @@ static int hci_conn_auth(struct hci_conn *conn, __u8 sec_level, __u8 auth_type)
 		hci_send_cmd(conn->hdev, HCI_OP_AUTH_REQUESTED,
 			     sizeof(cp), &cp);
 
-		/* If we're already encrypted set the REAUTH_PEND flag,
-		 * otherwise set the ENCRYPT_PEND.
+		/* Set the ENCRYPT_PEND to trigger encryption after
+		 * authentication.
 		 */
-		if (test_bit(HCI_CONN_ENCRYPT, &conn->flags))
-			set_bit(HCI_CONN_REAUTH_PEND, &conn->flags);
-		else
+		if (!test_bit(HCI_CONN_ENCRYPT, &conn->flags))
 			set_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags);
 	}
 
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index ebf17b51072f..ef8c3bed7361 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -3500,14 +3500,8 @@ static void hci_auth_complete_evt(struct hci_dev *hdev, void *data,
 
 	if (!ev->status) {
 		clear_bit(HCI_CONN_AUTH_FAILURE, &conn->flags);
-
-		if (!hci_conn_ssp_enabled(conn) &&
-		    test_bit(HCI_CONN_REAUTH_PEND, &conn->flags)) {
-			bt_dev_info(hdev, "re-auth of legacy device is not possible.");
-		} else {
-			set_bit(HCI_CONN_AUTH, &conn->flags);
-			conn->sec_level = conn->pending_sec_level;
-		}
+		set_bit(HCI_CONN_AUTH, &conn->flags);
+		conn->sec_level = conn->pending_sec_level;
 	} else {
 		if (ev->status == HCI_ERROR_PIN_OR_KEY_MISSING)
 			set_bit(HCI_CONN_AUTH_FAILURE, &conn->flags);
@@ -3516,7 +3510,6 @@ static void hci_auth_complete_evt(struct hci_dev *hdev, void *data,
 	}
 
 	clear_bit(HCI_CONN_AUTH_PEND, &conn->flags);
-	clear_bit(HCI_CONN_REAUTH_PEND, &conn->flags);
 
 	if (conn->state == BT_CONFIG) {
 		if (!ev->status && hci_conn_ssp_enabled(conn)) {
-- 
cgit v1.2.3


From 06a8c04f89949576b715f11350f1896b62cecb0a Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Tue, 19 Dec 2023 09:18:24 +0900
Subject: tcp: Save v4 address as v4-mapped-v6 in
 inet_bind2_bucket.v6_rcv_saddr.

In bhash2, IPv4/IPv6 addresses are saved in two union members,
which complicate address checks in inet_bind2_bucket_addr_match()
and inet_bind2_bucket_match_addr_any() considering uninitialised
memory and v4-mapped-v6 conflicts.

Let's simplify that by saving IPv4 address as v4-mapped-v6 address
and defining tb2.rcv_saddr as tb2.v6_rcv_saddr.s6_addr32[3].

Then, we can compare v6 address as is, and after checking v4-mapped-v6,
we can compare v4 address easily.  Also, we can remove tb2->family.

Note these functions will be further refactored in the next patch.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_hashtables.h | 11 ++++-------
 include/net/ipv6.h            |  5 -----
 net/ipv4/inet_hashtables.c    | 34 +++++++++++++++++-----------------
 3 files changed, 21 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 3ecfeadbfa06..171cc235d045 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -96,14 +96,11 @@ struct inet_bind2_bucket {
 	int			l3mdev;
 	unsigned short		port;
 #if IS_ENABLED(CONFIG_IPV6)
-	unsigned short		family;
-#endif
-	union {
-#if IS_ENABLED(CONFIG_IPV6)
-		struct in6_addr		v6_rcv_saddr;
+	struct in6_addr		v6_rcv_saddr;
+#define rcv_saddr		v6_rcv_saddr.s6_addr32[3]
+#else
+	__be32			rcv_saddr;
 #endif
-		__be32			rcv_saddr;
-	};
 	/* Node in the bhash2 inet_bind_hashbucket chain */
 	struct hlist_node	node;
 	/* List of sockets hashed to this bucket */
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 78d38dd88aba..cf25ea21d770 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -784,11 +784,6 @@ static inline bool ipv6_addr_v4mapped(const struct in6_addr *a)
 					cpu_to_be32(0x0000ffff))) == 0UL;
 }
 
-static inline bool ipv6_addr_v4mapped_any(const struct in6_addr *a)
-{
-	return ipv6_addr_v4mapped(a) && ipv4_is_zeronet(a->s6_addr32[3]);
-}
-
 static inline bool ipv6_addr_v4mapped_loopback(const struct in6_addr *a)
 {
 	return ipv6_addr_v4mapped(a) && ipv4_is_loopback(a->s6_addr32[3]);
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 896fcefc06c0..15594424e9f5 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -110,12 +110,13 @@ static void inet_bind2_bucket_init(struct inet_bind2_bucket *tb,
 	tb->l3mdev    = l3mdev;
 	tb->port      = port;
 #if IS_ENABLED(CONFIG_IPV6)
-	tb->family    = sk->sk_family;
 	if (sk->sk_family == AF_INET6)
 		tb->v6_rcv_saddr = sk->sk_v6_rcv_saddr;
 	else
+		ipv6_addr_set_v4mapped(sk->sk_rcv_saddr, &tb->v6_rcv_saddr);
+#else
+	tb->rcv_saddr = sk->sk_rcv_saddr;
 #endif
-		tb->rcv_saddr = sk->sk_rcv_saddr;
 	INIT_HLIST_HEAD(&tb->owners);
 	INIT_HLIST_HEAD(&tb->deathrow);
 	hlist_add_head(&tb->node, &head->chain);
@@ -149,17 +150,11 @@ static bool inet_bind2_bucket_addr_match(const struct inet_bind2_bucket *tb2,
 					 const struct sock *sk)
 {
 #if IS_ENABLED(CONFIG_IPV6)
-	if (sk->sk_family == AF_INET6) {
-		if (tb2->family == AF_INET6)
-			return ipv6_addr_equal(&tb2->v6_rcv_saddr, &sk->sk_v6_rcv_saddr);
-
-		return ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr) &&
-			sk->sk_v6_rcv_saddr.s6_addr32[3] == tb2->rcv_saddr;
-	}
+	if (sk->sk_family == AF_INET6)
+		return ipv6_addr_equal(&tb2->v6_rcv_saddr, &sk->sk_v6_rcv_saddr);
 
-	if (tb2->family == AF_INET6)
-		return ipv6_addr_v4mapped(&tb2->v6_rcv_saddr) &&
-			tb2->v6_rcv_saddr.s6_addr32[3] == sk->sk_rcv_saddr;
+	if (!ipv6_addr_v4mapped(&tb2->v6_rcv_saddr))
+		return false;
 #endif
 	return tb2->rcv_saddr == sk->sk_rcv_saddr;
 }
@@ -836,16 +831,21 @@ bool inet_bind2_bucket_match_addr_any(const struct inet_bind2_bucket *tb, const
 
 #if IS_ENABLED(CONFIG_IPV6)
 	if (sk->sk_family == AF_INET6) {
-		if (tb->family == AF_INET6)
-			return ipv6_addr_any(&tb->v6_rcv_saddr);
+		if (ipv6_addr_any(&tb->v6_rcv_saddr))
+			return true;
+
+		if (!ipv6_addr_v4mapped(&tb->v6_rcv_saddr))
+			return false;
 
 		return ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr) &&
 			tb->rcv_saddr == 0;
 	}
 
-	if (tb->family == AF_INET6)
-		return ipv6_addr_any(&tb->v6_rcv_saddr) ||
-			ipv6_addr_v4mapped_any(&tb->v6_rcv_saddr);
+	if (ipv6_addr_any(&tb->v6_rcv_saddr))
+		return true;
+
+	if (!ipv6_addr_v4mapped(&tb->v6_rcv_saddr))
+		return false;
 #endif
 	return tb->rcv_saddr == 0;
 }
-- 
cgit v1.2.3


From 5a22bba13d0162d278d6e31232259ddcce196b8e Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Tue, 19 Dec 2023 09:18:25 +0900
Subject: tcp: Save address type in inet_bind2_bucket.

inet_bind2_bucket_addr_match() and inet_bind2_bucket_match_addr_any()
are called for each bhash2 bucket to check conflicts.  Thus, we call
ipv6_addr_any() and ipv6_addr_v4mapped() over and over during bind().

Let's avoid calling them by saving the address type in inet_bind2_bucket.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_hashtables.h |  1 +
 net/ipv4/inet_hashtables.c    | 29 +++++++++++++----------------
 2 files changed, 14 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 171cc235d045..260e673ede22 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -96,6 +96,7 @@ struct inet_bind2_bucket {
 	int			l3mdev;
 	unsigned short		port;
 #if IS_ENABLED(CONFIG_IPV6)
+	unsigned short		addr_type;
 	struct in6_addr		v6_rcv_saddr;
 #define rcv_saddr		v6_rcv_saddr.s6_addr32[3]
 #else
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 15594424e9f5..4e39e3f905b4 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -110,10 +110,14 @@ static void inet_bind2_bucket_init(struct inet_bind2_bucket *tb,
 	tb->l3mdev    = l3mdev;
 	tb->port      = port;
 #if IS_ENABLED(CONFIG_IPV6)
-	if (sk->sk_family == AF_INET6)
+	BUILD_BUG_ON(USHRT_MAX < (IPV6_ADDR_ANY | IPV6_ADDR_MAPPED));
+	if (sk->sk_family == AF_INET6) {
+		tb->addr_type = ipv6_addr_type(&sk->sk_v6_rcv_saddr);
 		tb->v6_rcv_saddr = sk->sk_v6_rcv_saddr;
-	else
+	} else {
+		tb->addr_type = IPV6_ADDR_MAPPED;
 		ipv6_addr_set_v4mapped(sk->sk_rcv_saddr, &tb->v6_rcv_saddr);
+	}
 #else
 	tb->rcv_saddr = sk->sk_rcv_saddr;
 #endif
@@ -153,7 +157,7 @@ static bool inet_bind2_bucket_addr_match(const struct inet_bind2_bucket *tb2,
 	if (sk->sk_family == AF_INET6)
 		return ipv6_addr_equal(&tb2->v6_rcv_saddr, &sk->sk_v6_rcv_saddr);
 
-	if (!ipv6_addr_v4mapped(&tb2->v6_rcv_saddr))
+	if (tb2->addr_type != IPV6_ADDR_MAPPED)
 		return false;
 #endif
 	return tb2->rcv_saddr == sk->sk_rcv_saddr;
@@ -830,21 +834,14 @@ bool inet_bind2_bucket_match_addr_any(const struct inet_bind2_bucket *tb, const
 		return false;
 
 #if IS_ENABLED(CONFIG_IPV6)
-	if (sk->sk_family == AF_INET6) {
-		if (ipv6_addr_any(&tb->v6_rcv_saddr))
-			return true;
-
-		if (!ipv6_addr_v4mapped(&tb->v6_rcv_saddr))
-			return false;
-
-		return ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr) &&
-			tb->rcv_saddr == 0;
-	}
-
-	if (ipv6_addr_any(&tb->v6_rcv_saddr))
+	if (tb->addr_type == IPV6_ADDR_ANY)
 		return true;
 
-	if (!ipv6_addr_v4mapped(&tb->v6_rcv_saddr))
+	if (tb->addr_type != IPV6_ADDR_MAPPED)
+		return false;
+
+	if (sk->sk_family == AF_INET6 &&
+	    !ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
 		return false;
 #endif
 	return tb->rcv_saddr == 0;
-- 
cgit v1.2.3


From 822fb91fc724786372eed4f4397409c70afc08b8 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Tue, 19 Dec 2023 09:18:27 +0900
Subject: tcp: Link bhash2 to bhash.

bhash2 added a new member sk_bind2_node in struct sock to link
sockets to bhash2 in addition to bhash.

bhash is still needed to search conflicting sockets efficiently
from a port for the wildcard address.  However, bhash itself need
not have sockets.

If we link each bhash2 bucket to the corresponding bhash bucket,
we can iterate the same set of the sockets from bhash2 via bhash.

This patch links bhash2 to bhash only, and the actual use will be
in the later patches.  Finally, we will remove sk_bind2_node.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_hashtables.h   |  4 +++-
 net/ipv4/inet_connection_sock.c |  2 +-
 net/ipv4/inet_hashtables.c      | 21 +++++++++++----------
 3 files changed, 15 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 260e673ede22..25ba471ba161 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -89,6 +89,7 @@ struct inet_bind_bucket {
 	bool			fast_ipv6_only;
 	struct hlist_node	node;
 	struct hlist_head	owners;
+	struct hlist_head	bhash2;
 };
 
 struct inet_bind2_bucket {
@@ -104,6 +105,7 @@ struct inet_bind2_bucket {
 #endif
 	/* Node in the bhash2 inet_bind_hashbucket chain */
 	struct hlist_node	node;
+	struct hlist_node	bhash_node;
 	/* List of sockets hashed to this bucket */
 	struct hlist_head	owners;
 	/* bhash has twsk in owners, but bhash2 has twsk in
@@ -239,7 +241,7 @@ bool inet_bind_bucket_match(const struct inet_bind_bucket *tb,
 struct inet_bind2_bucket *
 inet_bind2_bucket_create(struct kmem_cache *cachep, struct net *net,
 			 struct inet_bind_hashbucket *head,
-			 unsigned short port, int l3mdev,
+			 struct inet_bind_bucket *tb,
 			 const struct sock *sk);
 
 void inet_bind2_bucket_destroy(struct kmem_cache *cachep,
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index d48255875f60..8b29056f454d 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -572,7 +572,7 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
 
 	if (!tb2) {
 		tb2 = inet_bind2_bucket_create(hinfo->bind2_bucket_cachep,
-					       net, head2, port, l3mdev, sk);
+					       net, head2, tb, sk);
 		if (!tb2)
 			goto fail_unlock;
 		bhash2_created = true;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 0a9919755709..7dc33dd1ba35 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -77,6 +77,7 @@ struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep,
 		tb->fastreuse = 0;
 		tb->fastreuseport = 0;
 		INIT_HLIST_HEAD(&tb->owners);
+		INIT_HLIST_HEAD(&tb->bhash2);
 		hlist_add_head(&tb->node, &head->chain);
 	}
 	return tb;
@@ -103,12 +104,12 @@ bool inet_bind_bucket_match(const struct inet_bind_bucket *tb, const struct net
 static void inet_bind2_bucket_init(struct inet_bind2_bucket *tb2,
 				   struct net *net,
 				   struct inet_bind_hashbucket *head,
-				   unsigned short port, int l3mdev,
+				   struct inet_bind_bucket *tb,
 				   const struct sock *sk)
 {
 	write_pnet(&tb2->ib_net, net);
-	tb2->l3mdev = l3mdev;
-	tb2->port = port;
+	tb2->l3mdev = tb->l3mdev;
+	tb2->port = tb->port;
 #if IS_ENABLED(CONFIG_IPV6)
 	BUILD_BUG_ON(USHRT_MAX < (IPV6_ADDR_ANY | IPV6_ADDR_MAPPED));
 	if (sk->sk_family == AF_INET6) {
@@ -124,19 +125,19 @@ static void inet_bind2_bucket_init(struct inet_bind2_bucket *tb2,
 	INIT_HLIST_HEAD(&tb2->owners);
 	INIT_HLIST_HEAD(&tb2->deathrow);
 	hlist_add_head(&tb2->node, &head->chain);
+	hlist_add_head(&tb2->bhash_node, &tb->bhash2);
 }
 
 struct inet_bind2_bucket *inet_bind2_bucket_create(struct kmem_cache *cachep,
 						   struct net *net,
 						   struct inet_bind_hashbucket *head,
-						   unsigned short port,
-						   int l3mdev,
+						   struct inet_bind_bucket *tb,
 						   const struct sock *sk)
 {
 	struct inet_bind2_bucket *tb2 = kmem_cache_alloc(cachep, GFP_ATOMIC);
 
 	if (tb2)
-		inet_bind2_bucket_init(tb2, net, head, port, l3mdev, sk);
+		inet_bind2_bucket_init(tb2, net, head, tb, sk);
 
 	return tb2;
 }
@@ -146,6 +147,7 @@ void inet_bind2_bucket_destroy(struct kmem_cache *cachep, struct inet_bind2_buck
 {
 	if (hlist_empty(&tb->owners) && hlist_empty(&tb->deathrow)) {
 		__hlist_del(&tb->node);
+		__hlist_del(&tb->bhash_node);
 		kmem_cache_free(cachep, tb);
 	}
 }
@@ -273,8 +275,7 @@ bhash2_find:
 		tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, child);
 		if (!tb2) {
 			tb2 = inet_bind2_bucket_create(table->bind2_bucket_cachep,
-						       net, head2, port,
-						       l3mdev, child);
+						       net, head2, tb, child);
 			if (!tb2)
 				goto error;
 		}
@@ -954,7 +955,7 @@ static int __inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family,
 	tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, sk);
 	if (!tb2) {
 		tb2 = new_tb2;
-		inet_bind2_bucket_init(tb2, net, head2, port, l3mdev, sk);
+		inet_bind2_bucket_init(tb2, net, head2, inet_csk(sk)->icsk_bind_hash, sk);
 	}
 	sk_add_bind2_node(sk, &tb2->owners);
 	inet_csk(sk)->icsk_bind2_hash = tb2;
@@ -1101,7 +1102,7 @@ ok:
 	tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, sk);
 	if (!tb2) {
 		tb2 = inet_bind2_bucket_create(hinfo->bind2_bucket_cachep, net,
-					       head2, port, l3mdev, sk);
+					       head2, tb, sk);
 		if (!tb2)
 			goto error;
 	}
-- 
cgit v1.2.3


From b2cb9f9ef240b4afaa1838b74fad077f17682f61 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Tue, 19 Dec 2023 09:18:31 +0900
Subject: tcp: Unlink sk from bhash.

Now we do not use tb->owners and can unlink sockets from bhash.

sk_bind_node/tw_bind_node are available for bhash2 and will be
used in the following patch.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_hashtables.h | 1 -
 net/ipv4/inet_hashtables.c    | 3 ---
 net/ipv4/inet_timewait_sock.c | 8 --------
 3 files changed, 12 deletions(-)

(limited to 'include')

diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 25ba471ba161..98ba728aec08 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -88,7 +88,6 @@ struct inet_bind_bucket {
 	unsigned short		fast_sk_family;
 	bool			fast_ipv6_only;
 	struct hlist_node	node;
-	struct hlist_head	owners;
 	struct hlist_head	bhash2;
 };
 
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 355cc6c0eaab..5c3ad37624f1 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -76,7 +76,6 @@ struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep,
 		tb->port      = snum;
 		tb->fastreuse = 0;
 		tb->fastreuseport = 0;
-		INIT_HLIST_HEAD(&tb->owners);
 		INIT_HLIST_HEAD(&tb->bhash2);
 		hlist_add_head(&tb->node, &head->chain);
 	}
@@ -169,7 +168,6 @@ void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb,
 		    struct inet_bind2_bucket *tb2, unsigned short port)
 {
 	inet_sk(sk)->inet_num = port;
-	sk_add_bind_node(sk, &tb->owners);
 	inet_csk(sk)->icsk_bind_hash = tb;
 	sk_add_bind2_node(sk, &tb2->owners);
 	inet_csk(sk)->icsk_bind2_hash = tb2;
@@ -192,7 +190,6 @@ static void __inet_put_port(struct sock *sk)
 
 	spin_lock(&head->lock);
 	tb = inet_csk(sk)->icsk_bind_hash;
-	__sk_del_bind_node(sk);
 	inet_csk(sk)->icsk_bind_hash = NULL;
 	inet_sk(sk)->inet_num = 0;
 
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 466d4faa9272..547583a87bd3 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -35,7 +35,6 @@ void inet_twsk_bind_unhash(struct inet_timewait_sock *tw,
 	if (!tb)
 		return;
 
-	__hlist_del(&tw->tw_bind_node);
 	tw->tw_tb = NULL;
 
 	__hlist_del(&tw->tw_bind2_node);
@@ -94,12 +93,6 @@ static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw,
 	hlist_nulls_add_head_rcu(&tw->tw_node, list);
 }
 
-static void inet_twsk_add_bind_node(struct inet_timewait_sock *tw,
-				    struct hlist_head *list)
-{
-	hlist_add_head(&tw->tw_bind_node, list);
-}
-
 static void inet_twsk_add_bind2_node(struct inet_timewait_sock *tw,
 				     struct hlist_head *list)
 {
@@ -133,7 +126,6 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
 
 	tw->tw_tb = icsk->icsk_bind_hash;
 	WARN_ON(!icsk->icsk_bind_hash);
-	inet_twsk_add_bind_node(tw, &tw->tw_tb->owners);
 
 	tw->tw_tb2 = icsk->icsk_bind2_hash;
 	WARN_ON(!icsk->icsk_bind2_hash);
-- 
cgit v1.2.3


From 770041d337a85923810dd3aeebea38037a28d534 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Tue, 19 Dec 2023 09:18:32 +0900
Subject: tcp: Link sk and twsk to tb2->owners using skc_bind_node.

Now we can use sk_bind_node/tw_bind_node for bhash2, which means
we need not link TIME_WAIT sockets separately.

The dead code and sk_bind2_node will be removed in the next patch.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h              | 10 ----------
 net/ipv4/inet_connection_sock.c |  4 ++--
 net/ipv4/inet_diag.c            |  2 +-
 net/ipv4/inet_hashtables.c      |  8 ++++----
 net/ipv4/inet_timewait_sock.c   | 11 ++---------
 5 files changed, 9 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/include/net/sock.h b/include/net/sock.h
index ba6642811db4..21c86e4c71fc 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -873,16 +873,6 @@ static inline void sk_add_bind_node(struct sock *sk,
 	hlist_add_head(&sk->sk_bind_node, list);
 }
 
-static inline void __sk_del_bind2_node(struct sock *sk)
-{
-	__hlist_del(&sk->sk_bind2_node);
-}
-
-static inline void sk_add_bind2_node(struct sock *sk, struct hlist_head *list)
-{
-	hlist_add_head(&sk->sk_bind2_node, list);
-}
-
 #define sk_for_each(__sk, list) \
 	hlist_for_each_entry(__sk, list, sk_node)
 #define sk_for_each_rcu(__sk, list) \
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 1bd13dcd45ae..1e19f85bce20 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -219,7 +219,7 @@ static bool inet_bhash2_conflict(const struct sock *sk,
 	struct inet_timewait_sock *tw2;
 	struct sock *sk2;
 
-	sk_for_each_bound_bhash2(sk2, &tb2->owners) {
+	sk_for_each_bound(sk2, &tb2->owners) {
 		if (__inet_bhash2_conflict(sk, sk2, sk_uid, relax,
 					   reuseport_cb_ok, reuseport_ok))
 			return true;
@@ -238,7 +238,7 @@ static bool inet_bhash2_conflict(const struct sock *sk,
 
 #define sk_for_each_bound_bhash(__sk, __tb2, __tb)			\
 	hlist_for_each_entry(__tb2, &(__tb)->bhash2, bhash_node)	\
-		sk_for_each_bound_bhash2(sk2, &(__tb2)->owners)
+		sk_for_each_bound(sk2, &(__tb2)->owners)
 
 #define twsk_for_each_bound_bhash(__sk, __tb2, __tb)			\
 	hlist_for_each_entry(__tb2, &(__tb)->bhash2, bhash_node)	\
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 46b13962ad02..8e6b6aa0579e 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -1104,7 +1104,7 @@ resume_bind_walk:
 				if (!net_eq(ib2_net(tb2), net))
 					continue;
 
-				sk_for_each_bound_bhash2(sk, &tb2->owners) {
+				sk_for_each_bound(sk, &tb2->owners) {
 					struct inet_sock *inet = inet_sk(sk);
 
 					if (num < s_num)
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 5c3ad37624f1..4ca726a71b9d 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -169,8 +169,8 @@ void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb,
 {
 	inet_sk(sk)->inet_num = port;
 	inet_csk(sk)->icsk_bind_hash = tb;
-	sk_add_bind2_node(sk, &tb2->owners);
 	inet_csk(sk)->icsk_bind2_hash = tb2;
+	sk_add_bind_node(sk, &tb2->owners);
 }
 
 /*
@@ -197,7 +197,7 @@ static void __inet_put_port(struct sock *sk)
 	if (inet_csk(sk)->icsk_bind2_hash) {
 		struct inet_bind2_bucket *tb2 = inet_csk(sk)->icsk_bind2_hash;
 
-		__sk_del_bind2_node(sk);
+		__sk_del_bind_node(sk);
 		inet_csk(sk)->icsk_bind2_hash = NULL;
 		inet_bind2_bucket_destroy(hashinfo->bind2_bucket_cachep, tb2);
 	}
@@ -937,7 +937,7 @@ static int __inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family,
 	spin_lock_bh(&head->lock);
 
 	spin_lock(&head2->lock);
-	__sk_del_bind2_node(sk);
+	__sk_del_bind_node(sk);
 	inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, inet_csk(sk)->icsk_bind2_hash);
 	spin_unlock(&head2->lock);
 
@@ -954,8 +954,8 @@ static int __inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family,
 		tb2 = new_tb2;
 		inet_bind2_bucket_init(tb2, net, head2, inet_csk(sk)->icsk_bind_hash, sk);
 	}
-	sk_add_bind2_node(sk, &tb2->owners);
 	inet_csk(sk)->icsk_bind2_hash = tb2;
+	sk_add_bind_node(sk, &tb2->owners);
 	spin_unlock(&head2->lock);
 
 	spin_unlock_bh(&head->lock);
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 547583a87bd3..5befa4de5b24 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -35,9 +35,8 @@ void inet_twsk_bind_unhash(struct inet_timewait_sock *tw,
 	if (!tb)
 		return;
 
+	__sk_del_bind_node((struct sock *)tw);
 	tw->tw_tb = NULL;
-
-	__hlist_del(&tw->tw_bind2_node);
 	tw->tw_tb2 = NULL;
 	inet_bind2_bucket_destroy(hashinfo->bind2_bucket_cachep, tb2);
 	inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb);
@@ -93,12 +92,6 @@ static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw,
 	hlist_nulls_add_head_rcu(&tw->tw_node, list);
 }
 
-static void inet_twsk_add_bind2_node(struct inet_timewait_sock *tw,
-				     struct hlist_head *list)
-{
-	hlist_add_head(&tw->tw_bind2_node, list);
-}
-
 /*
  * Enter the time wait state. This is called with locally disabled BH.
  * Essentially we whip up a timewait bucket, copy the relevant info into it
@@ -129,7 +122,7 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
 
 	tw->tw_tb2 = icsk->icsk_bind2_hash;
 	WARN_ON(!icsk->icsk_bind2_hash);
-	inet_twsk_add_bind2_node(tw, &tw->tw_tb2->deathrow);
+	sk_add_bind_node((struct sock *)tw, &tw->tw_tb2->owners);
 
 	spin_unlock(&bhead2->lock);
 	spin_unlock(&bhead->lock);
-- 
cgit v1.2.3


From 8191792c18c55ee444588100cf0464bd8c0bf5f3 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Tue, 19 Dec 2023 09:18:33 +0900
Subject: tcp: Remove dead code and fields for bhash2.

Now all sockets including TIME_WAIT are linked to bhash2 using
sock_common.skc_bind_node.

We no longer use inet_bind2_bucket.deathrow, sock.sk_bind2_node,
and inet_timewait_sock.tw_bind2_node.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_hashtables.h    |  4 ----
 include/net/inet_timewait_sock.h |  4 ----
 include/net/sock.h               |  4 ----
 net/ipv4/inet_connection_sock.c  | 21 ---------------------
 net/ipv4/inet_hashtables.c       |  3 +--
 5 files changed, 1 insertion(+), 35 deletions(-)

(limited to 'include')

diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 98ba728aec08..7f1b38458743 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -107,10 +107,6 @@ struct inet_bind2_bucket {
 	struct hlist_node	bhash_node;
 	/* List of sockets hashed to this bucket */
 	struct hlist_head	owners;
-	/* bhash has twsk in owners, but bhash2 has twsk in
-	 * deathrow not to add a member in struct sock_common.
-	 */
-	struct hlist_head	deathrow;
 };
 
 static inline struct net *ib_net(const struct inet_bind_bucket *ib)
diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h
index b14999ff55db..f28da08a37b4 100644
--- a/include/net/inet_timewait_sock.h
+++ b/include/net/inet_timewait_sock.h
@@ -75,13 +75,9 @@ struct inet_timewait_sock {
 	struct timer_list	tw_timer;
 	struct inet_bind_bucket	*tw_tb;
 	struct inet_bind2_bucket	*tw_tb2;
-	struct hlist_node		tw_bind2_node;
 };
 #define tw_tclass tw_tos
 
-#define twsk_for_each_bound_bhash2(__tw, list) \
-	hlist_for_each_entry(__tw, list, tw_bind2_node)
-
 static inline struct inet_timewait_sock *inet_twsk(const struct sock *sk)
 {
 	return (struct inet_timewait_sock *)sk;
diff --git a/include/net/sock.h b/include/net/sock.h
index 21c86e4c71fc..2fb3ea2d2ec3 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -352,7 +352,6 @@ struct sk_filter;
   *	@sk_txtime_report_errors: set report errors mode for SO_TXTIME
   *	@sk_txtime_unused: unused txtime flags
   *	@ns_tracker: tracker for netns reference
-  *	@sk_bind2_node: bind node in the bhash2 table
   */
 struct sock {
 	/*
@@ -544,7 +543,6 @@ struct sock {
 #endif
 	struct rcu_head		sk_rcu;
 	netns_tracker		ns_tracker;
-	struct hlist_node	sk_bind2_node;
 };
 
 enum sk_pacing {
@@ -890,8 +888,6 @@ static inline void sk_add_bind_node(struct sock *sk,
 	hlist_for_each_entry_safe(__sk, tmp, list, sk_node)
 #define sk_for_each_bound(__sk, list) \
 	hlist_for_each_entry(__sk, list, sk_bind_node)
-#define sk_for_each_bound_bhash2(__sk, list) \
-	hlist_for_each_entry(__sk, list, sk_bind2_node)
 
 /**
  * sk_for_each_entry_offset_rcu - iterate over a list at a given struct offset
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 1e19f85bce20..8e2eb1793685 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -216,7 +216,6 @@ static bool inet_bhash2_conflict(const struct sock *sk,
 				 bool relax, bool reuseport_cb_ok,
 				 bool reuseport_ok)
 {
-	struct inet_timewait_sock *tw2;
 	struct sock *sk2;
 
 	sk_for_each_bound(sk2, &tb2->owners) {
@@ -225,14 +224,6 @@ static bool inet_bhash2_conflict(const struct sock *sk,
 			return true;
 	}
 
-	twsk_for_each_bound_bhash2(tw2, &tb2->deathrow) {
-		sk2 = (struct sock *)tw2;
-
-		if (__inet_bhash2_conflict(sk, sk2, sk_uid, relax,
-					   reuseport_cb_ok, reuseport_ok))
-			return true;
-	}
-
 	return false;
 }
 
@@ -240,10 +231,6 @@ static bool inet_bhash2_conflict(const struct sock *sk,
 	hlist_for_each_entry(__tb2, &(__tb)->bhash2, bhash_node)	\
 		sk_for_each_bound(sk2, &(__tb2)->owners)
 
-#define twsk_for_each_bound_bhash(__sk, __tb2, __tb)			\
-	hlist_for_each_entry(__tb2, &(__tb)->bhash2, bhash_node)	\
-		sk_for_each_bound_bhash2(sk2, &(__tb2)->deathrow)
-
 /* This should be called only when the tb and tb2 hashbuckets' locks are held */
 static int inet_csk_bind_conflict(const struct sock *sk,
 				  const struct inet_bind_bucket *tb,
@@ -283,14 +270,6 @@ static int inet_csk_bind_conflict(const struct sock *sk,
 			return true;
 	}
 
-	twsk_for_each_bound_bhash(sk2, tb2, tb) {
-		if (!inet_bind_conflict(sk, sk2, uid, relax, reuseport_cb_ok, reuseport_ok))
-			continue;
-
-		if (inet_rcv_saddr_equal(sk, sk2, true))
-			return true;
-	}
-
 	return false;
 }
 
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 4ca726a71b9d..93e9193df544 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -122,7 +122,6 @@ static void inet_bind2_bucket_init(struct inet_bind2_bucket *tb2,
 	tb2->rcv_saddr = sk->sk_rcv_saddr;
 #endif
 	INIT_HLIST_HEAD(&tb2->owners);
-	INIT_HLIST_HEAD(&tb2->deathrow);
 	hlist_add_head(&tb2->node, &head->chain);
 	hlist_add_head(&tb2->bhash_node, &tb->bhash2);
 }
@@ -144,7 +143,7 @@ struct inet_bind2_bucket *inet_bind2_bucket_create(struct kmem_cache *cachep,
 /* Caller must hold hashbucket lock for this tb with local BH disabled */
 void inet_bind2_bucket_destroy(struct kmem_cache *cachep, struct inet_bind2_bucket *tb)
 {
-	if (hlist_empty(&tb->owners) && hlist_empty(&tb->deathrow)) {
+	if (hlist_empty(&tb->owners)) {
 		__hlist_del(&tb->node);
 		__hlist_del(&tb->bhash_node);
 		kmem_cache_free(cachep, tb);
-- 
cgit v1.2.3


From 60e43fe5285e2077ce9904d78cd42a230d03b788 Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Thu, 21 Dec 2023 15:02:31 -0700
Subject: lib/firmware_table: tables: Add CDAT table parsing support

The CDAT table is very similar to ACPI tables when it comes to sub-table
and entry structures. The helper functions can be also used to parse the
CDAT table. Add support to the helper functions to deal with an external
CDAT table, and also handle the endieness since CDAT can be processed by a
BE host. Export a function cdat_table_parse() for CXL driver to parse
a CDAT table.

In order to minimize ACPICA code changes, __force is being utilized to deal
with the case of a big endian (BE) host parsing a CDAT. All CDAT data
structure variables are being force casted to __leX as appropriate.

Cc: Rafael J. Wysocki <rafael@kernel.org>
Cc: Len Brown <lenb@kernel.org>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lore.kernel.org/r/170319615131.2212653.10932785667981494238.stgit@djiang5-mobl3
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/acpi/tables.c    |  5 ++--
 include/linux/fw_table.h | 21 +++++++++++++-
 lib/fw_table.c           | 75 ++++++++++++++++++++++++++++++++++++++++--------
 3 files changed, 86 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c
index c1516337f668..b07f7d091d13 100644
--- a/drivers/acpi/tables.c
+++ b/drivers/acpi/tables.c
@@ -251,8 +251,9 @@ int __init_or_acpilib acpi_table_parse_entries_array(
 		return -ENODEV;
 	}
 
-	count = acpi_parse_entries_array(id, table_size, table_header,
-			proc, proc_num, max_entries);
+	count = acpi_parse_entries_array(id, table_size,
+					 (union fw_table_header *)table_header,
+					 proc, proc_num, max_entries);
 
 	acpi_put_table(table_header);
 	return count;
diff --git a/include/linux/fw_table.h b/include/linux/fw_table.h
index ca49947f0a77..95421860397a 100644
--- a/include/linux/fw_table.h
+++ b/include/linux/fw_table.h
@@ -25,16 +25,35 @@ struct acpi_subtable_proc {
 	int count;
 };
 
+union fw_table_header {
+	struct acpi_table_header acpi;
+	struct acpi_table_cdat cdat;
+};
+
 union acpi_subtable_headers {
 	struct acpi_subtable_header common;
 	struct acpi_hmat_structure hmat;
 	struct acpi_prmt_module_header prmt;
 	struct acpi_cedt_header cedt;
+	struct acpi_cdat_header cdat;
 };
 
 int acpi_parse_entries_array(char *id, unsigned long table_size,
-			     struct acpi_table_header *table_header,
+			     union fw_table_header *table_header,
 			     struct acpi_subtable_proc *proc,
 			     int proc_num, unsigned int max_entries);
 
+int cdat_table_parse(enum acpi_cdat_type type,
+		     acpi_tbl_entry_handler_arg handler_arg, void *arg,
+		     struct acpi_table_cdat *table_header);
+
+/* CXL is the only non-ACPI consumer of the FIRMWARE_TABLE library */
+#if IS_ENABLED(CONFIG_ACPI) && !IS_ENABLED(CONFIG_CXL_BUS)
+#define EXPORT_SYMBOL_FWTBL_LIB(x) EXPORT_SYMBOL_ACPI_LIB(x)
+#define __init_or_fwtbl_lib __init_or_acpilib
+#else
+#define EXPORT_SYMBOL_FWTBL_LIB(x) EXPORT_SYMBOL_NS_GPL(x, CXL)
+#define __init_or_fwtbl_lib
+#endif
+
 #endif
diff --git a/lib/fw_table.c b/lib/fw_table.c
index 294df54e33b6..1e5e0b2f7012 100644
--- a/lib/fw_table.c
+++ b/lib/fw_table.c
@@ -12,12 +12,14 @@
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <linux/types.h>
+#include <linux/fw_table.h>
 
 enum acpi_subtable_type {
 	ACPI_SUBTABLE_COMMON,
 	ACPI_SUBTABLE_HMAT,
 	ACPI_SUBTABLE_PRMT,
 	ACPI_SUBTABLE_CEDT,
+	CDAT_SUBTABLE,
 };
 
 struct acpi_subtable_entry {
@@ -25,7 +27,7 @@ struct acpi_subtable_entry {
 	enum acpi_subtable_type type;
 };
 
-static unsigned long __init_or_acpilib
+static unsigned long __init_or_fwtbl_lib
 acpi_get_entry_type(struct acpi_subtable_entry *entry)
 {
 	switch (entry->type) {
@@ -37,11 +39,13 @@ acpi_get_entry_type(struct acpi_subtable_entry *entry)
 		return 0;
 	case ACPI_SUBTABLE_CEDT:
 		return entry->hdr->cedt.type;
+	case CDAT_SUBTABLE:
+		return entry->hdr->cdat.type;
 	}
 	return 0;
 }
 
-static unsigned long __init_or_acpilib
+static unsigned long __init_or_fwtbl_lib
 acpi_get_entry_length(struct acpi_subtable_entry *entry)
 {
 	switch (entry->type) {
@@ -53,11 +57,16 @@ acpi_get_entry_length(struct acpi_subtable_entry *entry)
 		return entry->hdr->prmt.length;
 	case ACPI_SUBTABLE_CEDT:
 		return entry->hdr->cedt.length;
+	case CDAT_SUBTABLE: {
+		__le16 length = (__force __le16)entry->hdr->cdat.length;
+
+		return le16_to_cpu(length);
+	}
 	}
 	return 0;
 }
 
-static unsigned long __init_or_acpilib
+static unsigned long __init_or_fwtbl_lib
 acpi_get_subtable_header_length(struct acpi_subtable_entry *entry)
 {
 	switch (entry->type) {
@@ -69,11 +78,13 @@ acpi_get_subtable_header_length(struct acpi_subtable_entry *entry)
 		return sizeof(entry->hdr->prmt);
 	case ACPI_SUBTABLE_CEDT:
 		return sizeof(entry->hdr->cedt);
+	case CDAT_SUBTABLE:
+		return sizeof(entry->hdr->cdat);
 	}
 	return 0;
 }
 
-static enum acpi_subtable_type __init_or_acpilib
+static enum acpi_subtable_type __init_or_fwtbl_lib
 acpi_get_subtable_type(char *id)
 {
 	if (strncmp(id, ACPI_SIG_HMAT, 4) == 0)
@@ -82,17 +93,32 @@ acpi_get_subtable_type(char *id)
 		return ACPI_SUBTABLE_PRMT;
 	if (strncmp(id, ACPI_SIG_CEDT, 4) == 0)
 		return ACPI_SUBTABLE_CEDT;
+	if (strncmp(id, ACPI_SIG_CDAT, 4) == 0)
+		return CDAT_SUBTABLE;
 	return ACPI_SUBTABLE_COMMON;
 }
 
-static __init_or_acpilib bool has_handler(struct acpi_subtable_proc *proc)
+static unsigned long __init_or_fwtbl_lib
+acpi_table_get_length(enum acpi_subtable_type type,
+		      union fw_table_header *header)
+{
+	if (type == CDAT_SUBTABLE) {
+		__le32 length = (__force __le32)header->cdat.length;
+
+		return le32_to_cpu(length);
+	}
+
+	return header->acpi.length;
+}
+
+static __init_or_fwtbl_lib bool has_handler(struct acpi_subtable_proc *proc)
 {
 	return proc->handler || proc->handler_arg;
 }
 
-static __init_or_acpilib int call_handler(struct acpi_subtable_proc *proc,
-					  union acpi_subtable_headers *hdr,
-					  unsigned long end)
+static __init_or_fwtbl_lib int call_handler(struct acpi_subtable_proc *proc,
+					    union acpi_subtable_headers *hdr,
+					    unsigned long end)
 {
 	if (proc->handler)
 		return proc->handler(hdr, end);
@@ -124,23 +150,26 @@ static __init_or_acpilib int call_handler(struct acpi_subtable_proc *proc,
  * On success returns sum of all matching entries for all proc handlers.
  * Otherwise, -ENODEV or -EINVAL is returned.
  */
-int __init_or_acpilib
+int __init_or_fwtbl_lib
 acpi_parse_entries_array(char *id, unsigned long table_size,
-			 struct acpi_table_header *table_header,
+			 union fw_table_header *table_header,
 			 struct acpi_subtable_proc *proc,
 			 int proc_num, unsigned int max_entries)
 {
 	unsigned long table_end, subtable_len, entry_len;
 	struct acpi_subtable_entry entry;
+	enum acpi_subtable_type type;
 	int count = 0;
 	int errs = 0;
 	int i;
 
-	table_end = (unsigned long)table_header + table_header->length;
+	type = acpi_get_subtable_type(id);
+	table_end = (unsigned long)table_header +
+		    acpi_table_get_length(type, table_header);
 
 	/* Parse all entries looking for a match. */
 
-	entry.type = acpi_get_subtable_type(id);
+	entry.type = type;
 	entry.hdr = (union acpi_subtable_headers *)
 	    ((unsigned long)table_header + table_size);
 	subtable_len = acpi_get_subtable_header_length(&entry);
@@ -186,3 +215,25 @@ acpi_parse_entries_array(char *id, unsigned long table_size,
 
 	return errs ? -EINVAL : count;
 }
+
+int __init_or_fwtbl_lib
+cdat_table_parse(enum acpi_cdat_type type,
+		 acpi_tbl_entry_handler_arg handler_arg,
+		 void *arg,
+		 struct acpi_table_cdat *table_header)
+{
+	struct acpi_subtable_proc proc = {
+		.id		= type,
+		.handler_arg	= handler_arg,
+		.arg		= arg,
+	};
+
+	if (!table_header)
+		return -EINVAL;
+
+	return acpi_parse_entries_array(ACPI_SIG_CDAT,
+					sizeof(struct acpi_table_cdat),
+					(union fw_table_header *)table_header,
+					&proc, 1, 0);
+}
+EXPORT_SYMBOL_FWTBL_LIB(cdat_table_parse);
-- 
cgit v1.2.3


From 6a954e94d038f41d79c4e04348c95774d1c9337d Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Thu, 21 Dec 2023 15:02:37 -0700
Subject: base/node / acpi: Change 'node_hmem_attrs' to 'access_coordinates'

Dan Williams suggested changing the struct 'node_hmem_attrs' to
'access_coordinates' [1]. The struct is a container of r/w-latency and
r/w-bandwidth numbers. Moving forward, this container will also be used by
CXL to store the performance characteristics of each link hop in
the PCIE/CXL topology. So, where node_hmem_attrs is just the access
parameters of a memory-node, access_coordinates applies more broadly
to hardware topology characteristics. The observation is that seemed like
an exercise in having the application identify "where" it falls on a
spectrum of bandwidth and latency needs. For the tuple of
read/write-latency and read/write-bandwidth, "coordinates" is not a perfect
fit. Sometimes it is just conveying values in isolation and not a
"location" relative to other performance points, but in the end this data
is used to identify the performance operation point of a given memory-node.
[2]

Link: http://lore.kernel.org/r/64471313421f7_1b66294d5@dwillia2-xfh.jf.intel.com.notmuch/
Link: https://lore.kernel.org/linux-cxl/645e6215ee0de_1e6f2945e@dwillia2-xfh.jf.intel.com.notmuch/
Suggested-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/170319615734.2212653.15319394025985499185.stgit@djiang5-mobl3
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/acpi/numa/hmat.c     | 28 ++++++++++++++--------------
 drivers/base/node.c          | 12 ++++++------
 include/linux/memory-tiers.h | 10 +++++-----
 include/linux/node.h         |  8 ++++----
 mm/memory-tiers.c            | 12 ++++++------
 5 files changed, 35 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c
index 9ef5f1bdcfdb..83bc2b69401b 100644
--- a/drivers/acpi/numa/hmat.c
+++ b/drivers/acpi/numa/hmat.c
@@ -63,7 +63,7 @@ struct memory_target {
 	unsigned int memory_pxm;
 	unsigned int processor_pxm;
 	struct resource memregions;
-	struct node_hmem_attrs hmem_attrs[2];
+	struct access_coordinate coord[2];
 	struct list_head caches;
 	struct node_cache_attrs cache_attrs;
 	bool registered;
@@ -228,24 +228,24 @@ static void hmat_update_target_access(struct memory_target *target,
 {
 	switch (type) {
 	case ACPI_HMAT_ACCESS_LATENCY:
-		target->hmem_attrs[access].read_latency = value;
-		target->hmem_attrs[access].write_latency = value;
+		target->coord[access].read_latency = value;
+		target->coord[access].write_latency = value;
 		break;
 	case ACPI_HMAT_READ_LATENCY:
-		target->hmem_attrs[access].read_latency = value;
+		target->coord[access].read_latency = value;
 		break;
 	case ACPI_HMAT_WRITE_LATENCY:
-		target->hmem_attrs[access].write_latency = value;
+		target->coord[access].write_latency = value;
 		break;
 	case ACPI_HMAT_ACCESS_BANDWIDTH:
-		target->hmem_attrs[access].read_bandwidth = value;
-		target->hmem_attrs[access].write_bandwidth = value;
+		target->coord[access].read_bandwidth = value;
+		target->coord[access].write_bandwidth = value;
 		break;
 	case ACPI_HMAT_READ_BANDWIDTH:
-		target->hmem_attrs[access].read_bandwidth = value;
+		target->coord[access].read_bandwidth = value;
 		break;
 	case ACPI_HMAT_WRITE_BANDWIDTH:
-		target->hmem_attrs[access].write_bandwidth = value;
+		target->coord[access].write_bandwidth = value;
 		break;
 	default:
 		break;
@@ -681,7 +681,7 @@ static void hmat_register_target_cache(struct memory_target *target)
 static void hmat_register_target_perf(struct memory_target *target, int access)
 {
 	unsigned mem_nid = pxm_to_node(target->memory_pxm);
-	node_set_perf_attrs(mem_nid, &target->hmem_attrs[access], access);
+	node_set_perf_attrs(mem_nid, &target->coord[access], access);
 }
 
 static void hmat_register_target_devices(struct memory_target *target)
@@ -765,7 +765,7 @@ static int hmat_set_default_dram_perf(void)
 	int rc;
 	int nid, pxm;
 	struct memory_target *target;
-	struct node_hmem_attrs *attrs;
+	struct access_coordinate *attrs;
 
 	if (!default_dram_type)
 		return -EIO;
@@ -775,7 +775,7 @@ static int hmat_set_default_dram_perf(void)
 		target = find_mem_target(pxm);
 		if (!target)
 			continue;
-		attrs = &target->hmem_attrs[1];
+		attrs = &target->coord[1];
 		rc = mt_set_default_dram_perf(nid, attrs, "ACPI HMAT");
 		if (rc)
 			return rc;
@@ -789,7 +789,7 @@ static int hmat_calculate_adistance(struct notifier_block *self,
 {
 	static DECLARE_BITMAP(p_nodes, MAX_NUMNODES);
 	struct memory_target *target;
-	struct node_hmem_attrs *perf;
+	struct access_coordinate *perf;
 	int *adist = data;
 	int pxm;
 
@@ -802,7 +802,7 @@ static int hmat_calculate_adistance(struct notifier_block *self,
 	hmat_update_target_attrs(target, p_nodes, 1);
 	mutex_unlock(&target_lock);
 
-	perf = &target->hmem_attrs[1];
+	perf = &target->coord[1];
 
 	if (mt_perf_to_adistance(perf, adist))
 		return NOTIFY_OK;
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 493d533f8375..cb2b6cc7f6e6 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -74,14 +74,14 @@ static BIN_ATTR_RO(cpulist, CPULIST_FILE_MAX_BYTES);
  * @dev:	Device for this memory access class
  * @list_node:	List element in the node's access list
  * @access:	The access class rank
- * @hmem_attrs: Heterogeneous memory performance attributes
+ * @coord:	Heterogeneous memory performance coordinates
  */
 struct node_access_nodes {
 	struct device		dev;
 	struct list_head	list_node;
 	unsigned int		access;
 #ifdef CONFIG_HMEM_REPORTING
-	struct node_hmem_attrs	hmem_attrs;
+	struct access_coordinate	coord;
 #endif
 };
 #define to_access_nodes(dev) container_of(dev, struct node_access_nodes, dev)
@@ -167,7 +167,7 @@ static ssize_t property##_show(struct device *dev,			\
 			   char *buf)					\
 {									\
 	return sysfs_emit(buf, "%u\n",					\
-			  to_access_nodes(dev)->hmem_attrs.property);	\
+			  to_access_nodes(dev)->coord.property);	\
 }									\
 static DEVICE_ATTR_RO(property)
 
@@ -187,10 +187,10 @@ static struct attribute *access_attrs[] = {
 /**
  * node_set_perf_attrs - Set the performance values for given access class
  * @nid: Node identifier to be set
- * @hmem_attrs: Heterogeneous memory performance attributes
+ * @coord: Heterogeneous memory performance coordinates
  * @access: The access class the for the given attributes
  */
-void node_set_perf_attrs(unsigned int nid, struct node_hmem_attrs *hmem_attrs,
+void node_set_perf_attrs(unsigned int nid, struct access_coordinate *coord,
 			 unsigned int access)
 {
 	struct node_access_nodes *c;
@@ -205,7 +205,7 @@ void node_set_perf_attrs(unsigned int nid, struct node_hmem_attrs *hmem_attrs,
 	if (!c)
 		return;
 
-	c->hmem_attrs = *hmem_attrs;
+	c->coord = *coord;
 	for (i = 0; access_attrs[i] != NULL; i++) {
 		if (sysfs_add_file_to_group(&c->dev.kobj, access_attrs[i],
 					    "initiators")) {
diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h
index 1e39d27bee41..69e781900082 100644
--- a/include/linux/memory-tiers.h
+++ b/include/linux/memory-tiers.h
@@ -33,7 +33,7 @@ struct memory_dev_type {
 	struct kref kref;
 };
 
-struct node_hmem_attrs;
+struct access_coordinate;
 
 #ifdef CONFIG_NUMA
 extern bool numa_demotion_enabled;
@@ -45,9 +45,9 @@ void clear_node_memory_type(int node, struct memory_dev_type *memtype);
 int register_mt_adistance_algorithm(struct notifier_block *nb);
 int unregister_mt_adistance_algorithm(struct notifier_block *nb);
 int mt_calc_adistance(int node, int *adist);
-int mt_set_default_dram_perf(int nid, struct node_hmem_attrs *perf,
+int mt_set_default_dram_perf(int nid, struct access_coordinate *perf,
 			     const char *source);
-int mt_perf_to_adistance(struct node_hmem_attrs *perf, int *adist);
+int mt_perf_to_adistance(struct access_coordinate *perf, int *adist);
 #ifdef CONFIG_MIGRATION
 int next_demotion_node(int node);
 void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets);
@@ -126,13 +126,13 @@ static inline int mt_calc_adistance(int node, int *adist)
 	return NOTIFY_DONE;
 }
 
-static inline int mt_set_default_dram_perf(int nid, struct node_hmem_attrs *perf,
+static inline int mt_set_default_dram_perf(int nid, struct access_coordinate *perf,
 					   const char *source)
 {
 	return -EIO;
 }
 
-static inline int mt_perf_to_adistance(struct node_hmem_attrs *perf, int *adist)
+static inline int mt_perf_to_adistance(struct access_coordinate *perf, int *adist)
 {
 	return -EIO;
 }
diff --git a/include/linux/node.h b/include/linux/node.h
index 427a5975cf40..25b66d705ee2 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -20,14 +20,14 @@
 #include <linux/list.h>
 
 /**
- * struct node_hmem_attrs - heterogeneous memory performance attributes
+ * struct access_coordinate - generic performance coordinates container
  *
  * @read_bandwidth:	Read bandwidth in MB/s
  * @write_bandwidth:	Write bandwidth in MB/s
  * @read_latency:	Read latency in nanoseconds
  * @write_latency:	Write latency in nanoseconds
  */
-struct node_hmem_attrs {
+struct access_coordinate {
 	unsigned int read_bandwidth;
 	unsigned int write_bandwidth;
 	unsigned int read_latency;
@@ -65,7 +65,7 @@ struct node_cache_attrs {
 
 #ifdef CONFIG_HMEM_REPORTING
 void node_add_cache(unsigned int nid, struct node_cache_attrs *cache_attrs);
-void node_set_perf_attrs(unsigned int nid, struct node_hmem_attrs *hmem_attrs,
+void node_set_perf_attrs(unsigned int nid, struct access_coordinate *coord,
 			 unsigned access);
 #else
 static inline void node_add_cache(unsigned int nid,
@@ -74,7 +74,7 @@ static inline void node_add_cache(unsigned int nid,
 }
 
 static inline void node_set_perf_attrs(unsigned int nid,
-				       struct node_hmem_attrs *hmem_attrs,
+				       struct access_coordinate *coord,
 				       unsigned access)
 {
 }
diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
index 8d5291add2bc..5462d9e3c84c 100644
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -109,7 +109,7 @@ static struct demotion_nodes *node_demotion __read_mostly;
 static BLOCKING_NOTIFIER_HEAD(mt_adistance_algorithms);
 
 static bool default_dram_perf_error;
-static struct node_hmem_attrs default_dram_perf;
+static struct access_coordinate default_dram_perf;
 static int default_dram_perf_ref_nid = NUMA_NO_NODE;
 static const char *default_dram_perf_ref_source;
 
@@ -601,15 +601,15 @@ void clear_node_memory_type(int node, struct memory_dev_type *memtype)
 }
 EXPORT_SYMBOL_GPL(clear_node_memory_type);
 
-static void dump_hmem_attrs(struct node_hmem_attrs *attrs, const char *prefix)
+static void dump_hmem_attrs(struct access_coordinate *coord, const char *prefix)
 {
 	pr_info(
 "%sread_latency: %u, write_latency: %u, read_bandwidth: %u, write_bandwidth: %u\n",
-		prefix, attrs->read_latency, attrs->write_latency,
-		attrs->read_bandwidth, attrs->write_bandwidth);
+		prefix, coord->read_latency, coord->write_latency,
+		coord->read_bandwidth, coord->write_bandwidth);
 }
 
-int mt_set_default_dram_perf(int nid, struct node_hmem_attrs *perf,
+int mt_set_default_dram_perf(int nid, struct access_coordinate *perf,
 			     const char *source)
 {
 	int rc = 0;
@@ -666,7 +666,7 @@ out:
 	return rc;
 }
 
-int mt_perf_to_adistance(struct node_hmem_attrs *perf, int *adist)
+int mt_perf_to_adistance(struct access_coordinate *perf, int *adist)
 {
 	if (default_dram_perf_error)
 		return -EIO;
-- 
cgit v1.2.3


From ca53543d8e340070fb37fde93f36ed9012c76b90 Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Thu, 21 Dec 2023 15:03:07 -0700
Subject: acpi: numa: Add helper function to retrieve the performance
 attributes

Add helper to retrieve the performance attributes based on the device
handle.  The helper function is exported so the CXL driver can use that
to acquire the performance data between the CPU and the CXL host bridge.

Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lore.kernel.org/r/170319618721.2212653.5552947472849081786.stgit@djiang5-mobl3
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/acpi/numa/hmat.c | 41 +++++++++++++++++++++++++++++++++++++++++
 include/linux/acpi.h     | 11 +++++++++++
 2 files changed, 52 insertions(+)

(limited to 'include')

diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c
index 8a1802e078f3..d6b85f0f6082 100644
--- a/drivers/acpi/numa/hmat.c
+++ b/drivers/acpi/numa/hmat.c
@@ -108,6 +108,47 @@ static struct memory_target *find_mem_target(unsigned int mem_pxm)
 	return NULL;
 }
 
+static struct memory_target *acpi_find_genport_target(u32 uid)
+{
+	struct memory_target *target;
+	u32 target_uid;
+	u8 *uid_ptr;
+
+	list_for_each_entry(target, &targets, node) {
+		uid_ptr = target->gen_port_device_handle + 8;
+		target_uid = *(u32 *)uid_ptr;
+		if (uid == target_uid)
+			return target;
+	}
+
+	return NULL;
+}
+
+/**
+ * acpi_get_genport_coordinates - Retrieve the access coordinates for a generic port
+ * @uid: ACPI unique id
+ * @coord: The access coordinates written back out for the generic port
+ *
+ * Return: 0 on success. Errno on failure.
+ *
+ * Only supports device handles that are ACPI. Assume ACPI0016 HID for CXL.
+ */
+int acpi_get_genport_coordinates(u32 uid,
+				 struct access_coordinate *coord)
+{
+	struct memory_target *target;
+
+	guard(mutex)(&target_lock);
+	target = acpi_find_genport_target(uid);
+	if (!target)
+		return -ENOENT;
+
+	*coord = target->coord[NODE_ACCESS_CLASS_GENPORT_SINK];
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(acpi_get_genport_coordinates, CXL);
+
 static __init void alloc_memory_initiator(unsigned int cpu_pxm)
 {
 	struct memory_initiator *initiator;
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 4db54e928b36..8b0761c682f9 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -15,6 +15,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/property.h>
 #include <linux/uuid.h>
+#include <linux/node.h>
 
 struct irq_domain;
 struct irq_domain_ops;
@@ -424,6 +425,16 @@ extern int acpi_blacklisted(void);
 extern void acpi_osi_setup(char *str);
 extern bool acpi_osi_is_win8(void);
 
+#ifdef CONFIG_ACPI_HMAT
+int acpi_get_genport_coordinates(u32 uid, struct access_coordinate *coord);
+#else
+static inline int acpi_get_genport_coordinates(u32 uid,
+					       struct access_coordinate *coord)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
 #ifdef CONFIG_ACPI_NUMA
 int acpi_map_pxm_to_node(int pxm);
 int acpi_get_node(acpi_handle handle);
-- 
cgit v1.2.3


From 4d07a05397c8c15c37c8c3abb7afaea1dcd2f0e7 Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Thu, 21 Dec 2023 15:03:39 -0700
Subject: cxl: Calculate and store PCI link latency for the downstream ports

The latency is calculated by dividing the flit size over the bandwidth. Add
support to retrieve the flit size for the CXL switch device and calculate
the latency of the PCIe link. Cache the latency number with cxl_dport.

Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/170319621931.2212653.6800240203604822886.stgit@djiang5-mobl3
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/core/core.h |  2 ++
 drivers/cxl/core/pci.c  | 36 ++++++++++++++++++++++++++++++++++++
 drivers/cxl/core/port.c |  6 ++++++
 drivers/cxl/cxl.h       |  4 ++++
 drivers/cxl/cxlpci.h    | 13 +++++++++++++
 drivers/pci/pci.c       | 38 ++++++++++++++++++++++++++++++++++++--
 include/linux/pci.h     |  1 +
 7 files changed, 98 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h
index 86d7ba23235e..3b64fb1b9ed0 100644
--- a/drivers/cxl/core/core.h
+++ b/drivers/cxl/core/core.h
@@ -88,4 +88,6 @@ enum cxl_poison_trace_type {
 	CXL_POISON_TRACE_CLEAR,
 };
 
+long cxl_pci_get_latency(struct pci_dev *pdev);
+
 #endif /* __CXL_CORE_H__ */
diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
index 37e1652afbc7..6c9c8d92f8f7 100644
--- a/drivers/cxl/core/pci.c
+++ b/drivers/cxl/core/pci.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /* Copyright(c) 2021 Intel Corporation. All rights reserved. */
+#include <linux/units.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
 #include <linux/device.h>
 #include <linux/delay.h>
@@ -979,3 +980,38 @@ pci_ers_result_t cxl_error_detected(struct pci_dev *pdev,
 	return PCI_ERS_RESULT_NEED_RESET;
 }
 EXPORT_SYMBOL_NS_GPL(cxl_error_detected, CXL);
+
+static int cxl_flit_size(struct pci_dev *pdev)
+{
+	if (cxl_pci_flit_256(pdev))
+		return 256;
+
+	return 68;
+}
+
+/**
+ * cxl_pci_get_latency - calculate the link latency for the PCIe link
+ * @pdev: PCI device
+ *
+ * return: calculated latency or 0 for no latency
+ *
+ * CXL Memory Device SW Guide v1.0 2.11.4 Link latency calculation
+ * Link latency = LinkPropagationLatency + FlitLatency + RetimerLatency
+ * LinkProgationLatency is negligible, so 0 will be used
+ * RetimerLatency is assumed to be negligible and 0 will be used
+ * FlitLatency = FlitSize / LinkBandwidth
+ * FlitSize is defined by spec. CXL rev3.0 4.2.1.
+ * 68B flit is used up to 32GT/s. >32GT/s, 256B flit size is used.
+ * The FlitLatency is converted to picoseconds.
+ */
+long cxl_pci_get_latency(struct pci_dev *pdev)
+{
+	long bw;
+
+	bw = pcie_link_speed_mbps(pdev);
+	if (bw < 0)
+		return 0;
+	bw /= BITS_PER_BYTE;
+
+	return cxl_flit_size(pdev) * MEGA / bw;
+}
diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index 9393cbf04652..b5ad227fe0d8 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -854,6 +854,9 @@ static struct cxl_port *__devm_cxl_add_port(struct device *host,
 	if (rc)
 		return ERR_PTR(rc);
 
+	if (parent_dport && dev_is_pci(uport_dev))
+		port->pci_latency = cxl_pci_get_latency(to_pci_dev(uport_dev));
+
 	return port;
 
 err:
@@ -1137,6 +1140,9 @@ __devm_cxl_add_dport(struct cxl_port *port, struct device *dport_dev,
 	if (rc)
 		return ERR_PTR(rc);
 
+	if (dev_is_pci(dport_dev))
+		dport->link_latency = cxl_pci_get_latency(to_pci_dev(dport_dev));
+
 	return dport;
 }
 
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index abbdcd3a7596..7da8db919a20 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -591,6 +591,7 @@ struct cxl_dax_region {
  * @depth: How deep this port is relative to the root. depth 0 is the root.
  * @cdat: Cached CDAT data
  * @cdat_available: Should a CDAT attribute be available in sysfs
+ * @pci_latency: Upstream latency in picoseconds
  */
 struct cxl_port {
 	struct device dev;
@@ -613,6 +614,7 @@ struct cxl_port {
 		size_t length;
 	} cdat;
 	bool cdat_available;
+	long pci_latency;
 };
 
 struct cxl_root_ops {
@@ -659,6 +661,7 @@ struct cxl_rcrb_info {
  * @port: reference to cxl_port that contains this downstream port
  * @regs: Dport parsed register blocks
  * @sw_coord: access coordinates (performance) for switch from CDAT
+ * @link_latency: calculated PCIe downstream latency
  */
 struct cxl_dport {
 	struct device *dport_dev;
@@ -669,6 +672,7 @@ struct cxl_dport {
 	struct cxl_port *port;
 	struct cxl_regs regs;
 	struct access_coordinate sw_coord;
+	long link_latency;
 };
 
 /**
diff --git a/drivers/cxl/cxlpci.h b/drivers/cxl/cxlpci.h
index 0fa4799ea316..711b05d9a370 100644
--- a/drivers/cxl/cxlpci.h
+++ b/drivers/cxl/cxlpci.h
@@ -85,6 +85,19 @@ struct cdat_entry_header {
 	__le16 length;
 } __packed;
 
+/*
+ * CXL v3.0 6.2.3 Table 6-4
+ * The table indicates that if PCIe Flit Mode is set, then CXL is in 256B flits
+ * mode, otherwise it's 68B flits mode.
+ */
+static inline bool cxl_pci_flit_256(struct pci_dev *pdev)
+{
+	u16 lnksta2;
+
+	pcie_capability_read_word(pdev, PCI_EXP_LNKSTA2, &lnksta2);
+	return lnksta2 & PCI_EXP_LNKSTA2_FLIT;
+}
+
 int devm_cxl_port_enumerate_dports(struct cxl_port *port);
 struct cxl_dev_state;
 int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm,
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 55bc3576a985..00817d403ad4 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -6224,6 +6224,41 @@ int pcie_set_mps(struct pci_dev *dev, int mps)
 }
 EXPORT_SYMBOL(pcie_set_mps);
 
+static enum pci_bus_speed to_pcie_link_speed(u16 lnksta)
+{
+	return pcie_link_speed[FIELD_GET(PCI_EXP_LNKSTA_CLS, lnksta)];
+}
+
+int pcie_link_speed_mbps(struct pci_dev *pdev)
+{
+	u16 lnksta;
+	int err;
+
+	err = pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnksta);
+	if (err)
+		return err;
+
+	switch (to_pcie_link_speed(lnksta)) {
+	case PCIE_SPEED_2_5GT:
+		return 2500;
+	case PCIE_SPEED_5_0GT:
+		return 5000;
+	case PCIE_SPEED_8_0GT:
+		return 8000;
+	case PCIE_SPEED_16_0GT:
+		return 16000;
+	case PCIE_SPEED_32_0GT:
+		return 32000;
+	case PCIE_SPEED_64_0GT:
+		return 64000;
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}
+EXPORT_SYMBOL(pcie_link_speed_mbps);
+
 /**
  * pcie_bandwidth_available - determine minimum link settings of a PCIe
  *			      device and its bandwidth limitation
@@ -6257,8 +6292,7 @@ u32 pcie_bandwidth_available(struct pci_dev *dev, struct pci_dev **limiting_dev,
 	while (dev) {
 		pcie_capability_read_word(dev, PCI_EXP_LNKSTA, &lnksta);
 
-		next_speed = pcie_link_speed[FIELD_GET(PCI_EXP_LNKSTA_CLS,
-						       lnksta)];
+		next_speed = to_pcie_link_speed(lnksta);
 		next_width = FIELD_GET(PCI_EXP_LNKSTA_NLW, lnksta);
 
 		next_bw = next_width * PCIE_SPEED2MBS_ENC(next_speed);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index dea043bc1e38..504a4ba2c29e 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1364,6 +1364,7 @@ int pcie_set_mps(struct pci_dev *dev, int mps);
 u32 pcie_bandwidth_available(struct pci_dev *dev, struct pci_dev **limiting_dev,
 			     enum pci_bus_speed *speed,
 			     enum pcie_link_width *width);
+int pcie_link_speed_mbps(struct pci_dev *pdev);
 void pcie_print_link_status(struct pci_dev *dev);
 int pcie_reset_flr(struct pci_dev *dev, bool probe);
 int pcie_flr(struct pci_dev *dev);
-- 
cgit v1.2.3


From ea67677dbb0d30b993b15790d6cee24c900dd597 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Fri, 22 Dec 2023 14:54:37 +0000
Subject: lsm: Add a __counted_by() annotation to lsm_ctx.ctx

The ctx in struct lsm_ctx is an array of size ctx_len, tell the compiler
about this using __counted_by() where supported to improve the ability to
detect overflow issues.

Reported-by: Aishwarya TCV <aishwarya.tcv@arm.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 include/uapi/linux/lsm.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/lsm.h b/include/uapi/linux/lsm.h
index f0386880a78e..f8aef9ade549 100644
--- a/include/uapi/linux/lsm.h
+++ b/include/uapi/linux/lsm.h
@@ -9,6 +9,7 @@
 #ifndef _UAPI_LINUX_LSM_H
 #define _UAPI_LINUX_LSM_H
 
+#include <linux/stddef.h>
 #include <linux/types.h>
 #include <linux/unistd.h>
 
@@ -36,7 +37,7 @@ struct lsm_ctx {
 	__u64 flags;
 	__u64 len;
 	__u64 ctx_len;
-	__u8 ctx[];
+	__u8 ctx[] __counted_by(ctx_len);
 };
 
 /*
-- 
cgit v1.2.3


From dcc3e46472d678f4af5ce1194a23649231c5d241 Mon Sep 17 00:00:00 2001
From: Jonathan Corbet <corbet@lwn.net>
Date: Mon, 18 Dec 2023 17:26:26 -0700
Subject: net: skbuff: Remove some excess struct-member documentation

Remove documentation for nonexistent structure members, addressing these
warnings:

  ./include/linux/skbuff.h:1063: warning: Excess struct member 'sp' description in 'sk_buff'
  ./include/linux/skbuff.h:1063: warning: Excess struct member 'nf_bridge' description in 'sk_buff'

Signed-off-by: Jonathan Corbet <corbet@lwn.net>
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index ea5c8ab3ed00..50e92c8471dc 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -754,7 +754,6 @@ typedef unsigned char *sk_buff_data_t;
  *	@dev_scratch: (aka @dev) alternate use of @dev when @dev would be %NULL
  *	@cb: Control buffer. Free for use by every layer. Put private vars here
  *	@_skb_refdst: destination entry (with norefcount bit)
- *	@sp: the security path, used for xfrm
  *	@len: Length of actual data
  *	@data_len: Data length
  *	@mac_len: Length of link layer header
@@ -788,7 +787,6 @@ typedef unsigned char *sk_buff_data_t;
  *	@tcp_tsorted_anchor: list structure for TCP (tp->tsorted_sent_queue)
  *	@_sk_redir: socket redirection information for skmsg
  *	@_nfct: Associated connection, if any (with nfctinfo bits)
- *	@nf_bridge: Saved data about a bridged frame - see br_netfilter.c
  *	@skb_iif: ifindex of device we arrived on
  *	@tc_index: Traffic control index
  *	@hash: the packet hash
-- 
cgit v1.2.3


From 520adf3ba4a4bdd41450c57b17ef01f8a069fbfe Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 22 Dec 2023 21:05:22 -0800
Subject: driver core: class: fix Excess kernel-doc description warning

Remove the @p: lines to prevent the kernel-doc warning:

include/linux/device/class.h:72: warning: Excess struct member 'p' description in 'class'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "Rafael J. Wysocki" <rafael@kernel.org>
Link: https://lore.kernel.org/r/20231223050522.13867-1-rdunlap@infradead.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/device/class.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/device/class.h b/include/linux/device/class.h
index abf3d3bfb6fe..c576b49c55c2 100644
--- a/include/linux/device/class.h
+++ b/include/linux/device/class.h
@@ -40,8 +40,6 @@ struct fwnode_handle;
  *		for the devices belonging to the class. Usually tied to
  *		device's namespace.
  * @pm:		The default device power management operations of this class.
- * @p:		The private data of the driver core, no one other than the
- *		driver core can touch this.
  *
  * A class is a higher-level view of a device that abstracts out low-level
  * implementation details. Drivers may see a SCSI disk or an ATA disk, but,
-- 
cgit v1.2.3


From ae4d90f7ca49eb71f8a3dca64d06d4c4e2193705 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 22 Dec 2023 21:05:32 -0800
Subject: driver core: device.h: fix Excess kernel-doc description warning

Remove the @knode_class: line to prevent the kernel-doc warning:

include/linux/device.h:807: warning: Excess struct member 'knode_class' description in 'device'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "Rafael J. Wysocki" <rafael@kernel.org>
Link: https://lore.kernel.org/r/20231223050532.13881-1-rdunlap@infradead.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/device.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/device.h b/include/linux/device.h
index aefc5ca7f1cf..ed600dbf950e 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -662,7 +662,6 @@ struct device_physical_location {
  * @id:		device instance
  * @devres_lock: Spinlock to protect the resource of the device.
  * @devres_head: The resources list of the device.
- * @knode_class: The node used to add the device to the class list.
  * @class:	The class of the device.
  * @groups:	Optional attribute groups.
  * @release:	Callback to free the device after all references have
-- 
cgit v1.2.3


From 1760bfa7d7ca490cf8a61fe50ddeb1769cadd89e Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 22 Dec 2023 21:06:36 -0800
Subject: usb: linux/usb.h: fix Excess kernel-doc description warning

Remove the @removable: line to prevent the kernel-doc warning:

include/linux/usb.h:732: warning: Excess struct member 'removable' description in 'usb_device'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: linux-usb@vger.kernel.org
Link: https://lore.kernel.org/r/20231223050636.14022-1-rdunlap@infradead.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/usb.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/usb.h b/include/linux/usb.h
index 618e5a0b1a22..07556341ba2b 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -632,7 +632,6 @@ struct usb3_lpm_parameters {
  * @reset_resume: needs reset instead of resume
  * @port_is_suspended: the upstream port is suspended (L2 or U3)
  * @slot_id: Slot ID assigned by xHCI
- * @removable: Device can be physically removed from this port
  * @l1_params: best effor service latency for USB2 L1 LPM state, and L1 timeout.
  * @u1_params: exit latencies for USB3 U1 LPM state, and hub-initiated timeout.
  * @u2_params: exit latencies for USB3 U2 LPM state, and hub-initiated timeout.
-- 
cgit v1.2.3


From f6847807c22f6944c71c981b630b9fff30801e73 Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Wed, 22 Nov 2023 23:18:11 +0100
Subject: linux/export: Fix alignment for 64-bit ksymtab entries

An alignment of 4 bytes is wrong for 64-bit platforms which don't define
CONFIG_HAVE_ARCH_PREL32_RELOCATIONS (which then store 64-bit pointers).
Fix their alignment to 8 bytes.

Fixes: ddb5cdbafaaa ("kbuild: generate KSYMTAB entries by modpost")
Signed-off-by: Helge Deller <deller@gmx.de>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 include/linux/export-internal.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/export-internal.h b/include/linux/export-internal.h
index 69501e0ec239..cd253eb51d6c 100644
--- a/include/linux/export-internal.h
+++ b/include/linux/export-internal.h
@@ -16,10 +16,13 @@
  * and eliminates the need for absolute relocations that require runtime
  * processing on relocatable kernels.
  */
+#define __KSYM_ALIGN		".balign 4"
 #define __KSYM_REF(sym)		".long " #sym "- ."
 #elif defined(CONFIG_64BIT)
+#define __KSYM_ALIGN		".balign 8"
 #define __KSYM_REF(sym)		".quad " #sym
 #else
+#define __KSYM_ALIGN		".balign 4"
 #define __KSYM_REF(sym)		".long " #sym
 #endif
 
@@ -42,7 +45,7 @@
 	    "	.asciz \"" ns "\""					"\n"	\
 	    "	.previous"						"\n"	\
 	    "	.section \"___ksymtab" sec "+" #name "\", \"a\""	"\n"	\
-	    "	.balign	4"						"\n"	\
+		__KSYM_ALIGN						"\n"	\
 	    "__ksymtab_" #name ":"					"\n"	\
 		__KSYM_REF(sym)						"\n"	\
 		__KSYM_REF(__kstrtab_ ##name)				"\n"	\
-- 
cgit v1.2.3


From f91a704f7161c2cf0fcd41fa9fbec4355b813fff Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Mon, 2 Oct 2023 17:19:46 +0300
Subject: fs: prepare for stackable filesystems backing file helpers

In preparation for factoring out some backing file io helpers from
overlayfs, move backing_file_open() into a new file fs/backing-file.c
and header.

Add a MAINTAINERS entry for stackable filesystems and add a Kconfig
FS_STACK which stackable filesystems need to select.

For now, the backing_file struct, the backing_file alloc/free functions
and the backing_file_real_path() accessor remain internal to file_table.c.
We may change that in the future.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
---
 MAINTAINERS                  |  9 +++++++++
 fs/Kconfig                   |  4 ++++
 fs/Makefile                  |  1 +
 fs/backing-file.c            | 48 ++++++++++++++++++++++++++++++++++++++++++++
 fs/open.c                    | 38 -----------------------------------
 fs/overlayfs/Kconfig         |  1 +
 fs/overlayfs/file.c          |  1 +
 include/linux/backing-file.h | 17 ++++++++++++++++
 include/linux/fs.h           |  3 ---
 9 files changed, 81 insertions(+), 41 deletions(-)
 create mode 100644 fs/backing-file.c
 create mode 100644 include/linux/backing-file.h

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index 97f51d5ec1cf..d9ae2688f5c8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8186,6 +8186,15 @@ S:	Supported
 F:	fs/iomap/
 F:	include/linux/iomap.h
 
+FILESYSTEMS [STACKABLE]
+M:	Miklos Szeredi <miklos@szeredi.hu>
+M:	Amir Goldstein <amir73il@gmail.com>
+L:	linux-fsdevel@vger.kernel.org
+L:	linux-unionfs@vger.kernel.org
+S:	Maintained
+F:	fs/backing-file.c
+F:	include/linux/backing-file.h
+
 FINTEK F75375S HARDWARE MONITOR AND FAN CONTROLLER DRIVER
 M:	Riku Voipio <riku.voipio@iki.fi>
 L:	linux-hwmon@vger.kernel.org
diff --git a/fs/Kconfig b/fs/Kconfig
index fd1f655b4f1f..c47fa4eb9282 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -18,6 +18,10 @@ config VALIDATE_FS_PARSER
 config FS_IOMAP
 	bool
 
+# Stackable filesystems
+config FS_STACK
+	bool
+
 config BUFFER_HEAD
 	bool
 
diff --git a/fs/Makefile b/fs/Makefile
index 75522f88e763..a6962c588962 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -39,6 +39,7 @@ obj-$(CONFIG_COMPAT_BINFMT_ELF)	+= compat_binfmt_elf.o
 obj-$(CONFIG_BINFMT_ELF_FDPIC)	+= binfmt_elf_fdpic.o
 obj-$(CONFIG_BINFMT_FLAT)	+= binfmt_flat.o
 
+obj-$(CONFIG_FS_STACK)		+= backing-file.o
 obj-$(CONFIG_FS_MBCACHE)	+= mbcache.o
 obj-$(CONFIG_FS_POSIX_ACL)	+= posix_acl.o
 obj-$(CONFIG_NFS_COMMON)	+= nfs_common/
diff --git a/fs/backing-file.c b/fs/backing-file.c
new file mode 100644
index 000000000000..04b33036f709
--- /dev/null
+++ b/fs/backing-file.c
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Common helpers for stackable filesystems and backing files.
+ *
+ * Copyright (C) 2023 CTERA Networks.
+ */
+
+#include <linux/fs.h>
+#include <linux/backing-file.h>
+
+#include "internal.h"
+
+/**
+ * backing_file_open - open a backing file for kernel internal use
+ * @user_path:	path that the user reuqested to open
+ * @flags:	open flags
+ * @real_path:	path of the backing file
+ * @cred:	credentials for open
+ *
+ * Open a backing file for a stackable filesystem (e.g., overlayfs).
+ * @user_path may be on the stackable filesystem and @real_path on the
+ * underlying filesystem.  In this case, we want to be able to return the
+ * @user_path of the stackable filesystem. This is done by embedding the
+ * returned file into a container structure that also stores the stacked
+ * file's path, which can be retrieved using backing_file_user_path().
+ */
+struct file *backing_file_open(const struct path *user_path, int flags,
+			       const struct path *real_path,
+			       const struct cred *cred)
+{
+	struct file *f;
+	int error;
+
+	f = alloc_empty_backing_file(flags, cred);
+	if (IS_ERR(f))
+		return f;
+
+	path_get(user_path);
+	*backing_file_user_path(f) = *user_path;
+	error = vfs_open(real_path, f);
+	if (error) {
+		fput(f);
+		f = ERR_PTR(error);
+	}
+
+	return f;
+}
+EXPORT_SYMBOL_GPL(backing_file_open);
diff --git a/fs/open.c b/fs/open.c
index d877228d5939..a75054237437 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -1184,44 +1184,6 @@ struct file *kernel_file_open(const struct path *path, int flags,
 }
 EXPORT_SYMBOL_GPL(kernel_file_open);
 
-/**
- * backing_file_open - open a backing file for kernel internal use
- * @user_path:	path that the user reuqested to open
- * @flags:	open flags
- * @real_path:	path of the backing file
- * @cred:	credentials for open
- *
- * Open a backing file for a stackable filesystem (e.g., overlayfs).
- * @user_path may be on the stackable filesystem and @real_path on the
- * underlying filesystem.  In this case, we want to be able to return the
- * @user_path of the stackable filesystem. This is done by embedding the
- * returned file into a container structure that also stores the stacked
- * file's path, which can be retrieved using backing_file_user_path().
- */
-struct file *backing_file_open(const struct path *user_path, int flags,
-			       const struct path *real_path,
-			       const struct cred *cred)
-{
-	struct file *f;
-	int error;
-
-	f = alloc_empty_backing_file(flags, cred);
-	if (IS_ERR(f))
-		return f;
-
-	path_get(user_path);
-	*backing_file_user_path(f) = *user_path;
-	f->f_path = *real_path;
-	error = do_dentry_open(f, d_inode(real_path->dentry), NULL);
-	if (error) {
-		fput(f);
-		f = ERR_PTR(error);
-	}
-
-	return f;
-}
-EXPORT_SYMBOL_GPL(backing_file_open);
-
 #define WILL_CREATE(flags)	(flags & (O_CREAT | __O_TMPFILE))
 #define O_PATH_FLAGS		(O_DIRECTORY | O_NOFOLLOW | O_PATH | O_CLOEXEC)
 
diff --git a/fs/overlayfs/Kconfig b/fs/overlayfs/Kconfig
index fec5020c3495..2ac67e04a6fb 100644
--- a/fs/overlayfs/Kconfig
+++ b/fs/overlayfs/Kconfig
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config OVERLAY_FS
 	tristate "Overlay filesystem support"
+	select FS_STACK
 	select EXPORTFS
 	help
 	  An overlay filesystem combines two filesystems - an 'upper' filesystem
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index 4e46420c8fdd..a6da3eaf6d4f 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -13,6 +13,7 @@
 #include <linux/security.h>
 #include <linux/mm.h>
 #include <linux/fs.h>
+#include <linux/backing-file.h>
 #include "overlayfs.h"
 
 #include "../internal.h"	/* for sb_init_dio_done_wq */
diff --git a/include/linux/backing-file.h b/include/linux/backing-file.h
new file mode 100644
index 000000000000..55c9e804f780
--- /dev/null
+++ b/include/linux/backing-file.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Common helpers for stackable filesystems and backing files.
+ *
+ * Copyright (C) 2023 CTERA Networks.
+ */
+
+#ifndef _LINUX_BACKING_FILE_H
+#define _LINUX_BACKING_FILE_H
+
+#include <linux/file.h>
+
+struct file *backing_file_open(const struct path *user_path, int flags,
+			       const struct path *real_path,
+			       const struct cred *cred);
+
+#endif /* _LINUX_BACKING_FILE_H */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 900d0cd55b50..db5d07e6e02e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2575,9 +2575,6 @@ struct file *dentry_open(const struct path *path, int flags,
 			 const struct cred *creds);
 struct file *dentry_create(const struct path *path, int flags, umode_t mode,
 			   const struct cred *cred);
-struct file *backing_file_open(const struct path *user_path, int flags,
-			       const struct path *real_path,
-			       const struct cred *cred);
 struct path *backing_file_user_path(struct file *f);
 
 /*
-- 
cgit v1.2.3


From a6293b3e285cd0d7692141d7981a5f144f0e2f0b Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Wed, 22 Nov 2023 17:48:52 +0200
Subject: fs: factor out backing_file_{read,write}_iter() helpers

Overlayfs submits files io to backing files on other filesystems.
Factor out some common helpers to perform io to backing files, into
fs/backing-file.c.

Suggested-by: Miklos Szeredi <miklos@szeredi.hu>
Link: https://lore.kernel.org/r/CAJfpeguhmZbjP3JLqtUy0AdWaHOkAPWeP827BBWwRFEAUgnUcQ@mail.gmail.com
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
---
 fs/backing-file.c            | 210 +++++++++++++++++++++++++++++++++++++++++++
 fs/overlayfs/file.c          | 188 +++-----------------------------------
 fs/overlayfs/overlayfs.h     |   8 +-
 fs/overlayfs/super.c         |  11 +--
 include/linux/backing-file.h |  15 ++++
 5 files changed, 247 insertions(+), 185 deletions(-)

(limited to 'include')

diff --git a/fs/backing-file.c b/fs/backing-file.c
index 04b33036f709..323187a49da3 100644
--- a/fs/backing-file.c
+++ b/fs/backing-file.c
@@ -2,6 +2,9 @@
 /*
  * Common helpers for stackable filesystems and backing files.
  *
+ * Forked from fs/overlayfs/file.c.
+ *
+ * Copyright (C) 2017 Red Hat, Inc.
  * Copyright (C) 2023 CTERA Networks.
  */
 
@@ -46,3 +49,210 @@ struct file *backing_file_open(const struct path *user_path, int flags,
 	return f;
 }
 EXPORT_SYMBOL_GPL(backing_file_open);
+
+struct backing_aio {
+	struct kiocb iocb;
+	refcount_t ref;
+	struct kiocb *orig_iocb;
+	/* used for aio completion */
+	void (*end_write)(struct file *);
+	struct work_struct work;
+	long res;
+};
+
+static struct kmem_cache *backing_aio_cachep;
+
+#define BACKING_IOCB_MASK \
+	(IOCB_NOWAIT | IOCB_HIPRI | IOCB_DSYNC | IOCB_SYNC | IOCB_APPEND)
+
+static rwf_t iocb_to_rw_flags(int flags)
+{
+	return (__force rwf_t)(flags & BACKING_IOCB_MASK);
+}
+
+static void backing_aio_put(struct backing_aio *aio)
+{
+	if (refcount_dec_and_test(&aio->ref)) {
+		fput(aio->iocb.ki_filp);
+		kmem_cache_free(backing_aio_cachep, aio);
+	}
+}
+
+static void backing_aio_cleanup(struct backing_aio *aio, long res)
+{
+	struct kiocb *iocb = &aio->iocb;
+	struct kiocb *orig_iocb = aio->orig_iocb;
+
+	if (aio->end_write)
+		aio->end_write(orig_iocb->ki_filp);
+
+	orig_iocb->ki_pos = iocb->ki_pos;
+	backing_aio_put(aio);
+}
+
+static void backing_aio_rw_complete(struct kiocb *iocb, long res)
+{
+	struct backing_aio *aio = container_of(iocb, struct backing_aio, iocb);
+	struct kiocb *orig_iocb = aio->orig_iocb;
+
+	if (iocb->ki_flags & IOCB_WRITE)
+		kiocb_end_write(iocb);
+
+	backing_aio_cleanup(aio, res);
+	orig_iocb->ki_complete(orig_iocb, res);
+}
+
+static void backing_aio_complete_work(struct work_struct *work)
+{
+	struct backing_aio *aio = container_of(work, struct backing_aio, work);
+
+	backing_aio_rw_complete(&aio->iocb, aio->res);
+}
+
+static void backing_aio_queue_completion(struct kiocb *iocb, long res)
+{
+	struct backing_aio *aio = container_of(iocb, struct backing_aio, iocb);
+
+	/*
+	 * Punt to a work queue to serialize updates of mtime/size.
+	 */
+	aio->res = res;
+	INIT_WORK(&aio->work, backing_aio_complete_work);
+	queue_work(file_inode(aio->orig_iocb->ki_filp)->i_sb->s_dio_done_wq,
+		   &aio->work);
+}
+
+static int backing_aio_init_wq(struct kiocb *iocb)
+{
+	struct super_block *sb = file_inode(iocb->ki_filp)->i_sb;
+
+	if (sb->s_dio_done_wq)
+		return 0;
+
+	return sb_init_dio_done_wq(sb);
+}
+
+
+ssize_t backing_file_read_iter(struct file *file, struct iov_iter *iter,
+			       struct kiocb *iocb, int flags,
+			       struct backing_file_ctx *ctx)
+{
+	struct backing_aio *aio = NULL;
+	const struct cred *old_cred;
+	ssize_t ret;
+
+	if (WARN_ON_ONCE(!(file->f_mode & FMODE_BACKING)))
+		return -EIO;
+
+	if (!iov_iter_count(iter))
+		return 0;
+
+	if (iocb->ki_flags & IOCB_DIRECT &&
+	    !(file->f_mode & FMODE_CAN_ODIRECT))
+		return -EINVAL;
+
+	old_cred = override_creds(ctx->cred);
+	if (is_sync_kiocb(iocb)) {
+		rwf_t rwf = iocb_to_rw_flags(flags);
+
+		ret = vfs_iter_read(file, iter, &iocb->ki_pos, rwf);
+	} else {
+		ret = -ENOMEM;
+		aio = kmem_cache_zalloc(backing_aio_cachep, GFP_KERNEL);
+		if (!aio)
+			goto out;
+
+		aio->orig_iocb = iocb;
+		kiocb_clone(&aio->iocb, iocb, get_file(file));
+		aio->iocb.ki_complete = backing_aio_rw_complete;
+		refcount_set(&aio->ref, 2);
+		ret = vfs_iocb_iter_read(file, &aio->iocb, iter);
+		backing_aio_put(aio);
+		if (ret != -EIOCBQUEUED)
+			backing_aio_cleanup(aio, ret);
+	}
+out:
+	revert_creds(old_cred);
+
+	if (ctx->accessed)
+		ctx->accessed(ctx->user_file);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(backing_file_read_iter);
+
+ssize_t backing_file_write_iter(struct file *file, struct iov_iter *iter,
+				struct kiocb *iocb, int flags,
+				struct backing_file_ctx *ctx)
+{
+	const struct cred *old_cred;
+	ssize_t ret;
+
+	if (WARN_ON_ONCE(!(file->f_mode & FMODE_BACKING)))
+		return -EIO;
+
+	if (!iov_iter_count(iter))
+		return 0;
+
+	ret = file_remove_privs(ctx->user_file);
+	if (ret)
+		return ret;
+
+	if (iocb->ki_flags & IOCB_DIRECT &&
+	    !(file->f_mode & FMODE_CAN_ODIRECT))
+		return -EINVAL;
+
+	/*
+	 * Stacked filesystems don't support deferred completions, don't copy
+	 * this property in case it is set by the issuer.
+	 */
+	flags &= ~IOCB_DIO_CALLER_COMP;
+
+	old_cred = override_creds(ctx->cred);
+	if (is_sync_kiocb(iocb)) {
+		rwf_t rwf = iocb_to_rw_flags(flags);
+
+		ret = vfs_iter_write(file, iter, &iocb->ki_pos, rwf);
+		if (ctx->end_write)
+			ctx->end_write(ctx->user_file);
+	} else {
+		struct backing_aio *aio;
+
+		ret = backing_aio_init_wq(iocb);
+		if (ret)
+			goto out;
+
+		ret = -ENOMEM;
+		aio = kmem_cache_zalloc(backing_aio_cachep, GFP_KERNEL);
+		if (!aio)
+			goto out;
+
+		aio->orig_iocb = iocb;
+		aio->end_write = ctx->end_write;
+		kiocb_clone(&aio->iocb, iocb, get_file(file));
+		aio->iocb.ki_flags = flags;
+		aio->iocb.ki_complete = backing_aio_queue_completion;
+		refcount_set(&aio->ref, 2);
+		ret = vfs_iocb_iter_write(file, &aio->iocb, iter);
+		backing_aio_put(aio);
+		if (ret != -EIOCBQUEUED)
+			backing_aio_cleanup(aio, ret);
+	}
+out:
+	revert_creds(old_cred);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(backing_file_write_iter);
+
+static int __init backing_aio_init(void)
+{
+	backing_aio_cachep = kmem_cache_create("backing_aio",
+					       sizeof(struct backing_aio),
+					       0, SLAB_HWCACHE_ALIGN, NULL);
+	if (!backing_aio_cachep)
+		return -ENOMEM;
+
+	return 0;
+}
+fs_initcall(backing_aio_init);
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index a6da3eaf6d4f..1b578cb27a26 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -16,19 +16,6 @@
 #include <linux/backing-file.h>
 #include "overlayfs.h"
 
-#include "../internal.h"	/* for sb_init_dio_done_wq */
-
-struct ovl_aio_req {
-	struct kiocb iocb;
-	refcount_t ref;
-	struct kiocb *orig_iocb;
-	/* used for aio completion */
-	struct work_struct work;
-	long res;
-};
-
-static struct kmem_cache *ovl_aio_request_cachep;
-
 static char ovl_whatisit(struct inode *inode, struct inode *realinode)
 {
 	if (realinode != ovl_inode_upper(inode))
@@ -275,84 +262,16 @@ static void ovl_file_accessed(struct file *file)
 	touch_atime(&file->f_path);
 }
 
-#define OVL_IOCB_MASK \
-	(IOCB_NOWAIT | IOCB_HIPRI | IOCB_DSYNC | IOCB_SYNC | IOCB_APPEND)
-
-static rwf_t iocb_to_rw_flags(int flags)
-{
-	return (__force rwf_t)(flags & OVL_IOCB_MASK);
-}
-
-static inline void ovl_aio_put(struct ovl_aio_req *aio_req)
-{
-	if (refcount_dec_and_test(&aio_req->ref)) {
-		fput(aio_req->iocb.ki_filp);
-		kmem_cache_free(ovl_aio_request_cachep, aio_req);
-	}
-}
-
-static void ovl_aio_cleanup_handler(struct ovl_aio_req *aio_req)
-{
-	struct kiocb *iocb = &aio_req->iocb;
-	struct kiocb *orig_iocb = aio_req->orig_iocb;
-
-	if (iocb->ki_flags & IOCB_WRITE)
-		ovl_file_modified(orig_iocb->ki_filp);
-
-	orig_iocb->ki_pos = iocb->ki_pos;
-	ovl_aio_put(aio_req);
-}
-
-static void ovl_aio_rw_complete(struct kiocb *iocb, long res)
-{
-	struct ovl_aio_req *aio_req = container_of(iocb,
-						   struct ovl_aio_req, iocb);
-	struct kiocb *orig_iocb = aio_req->orig_iocb;
-
-	if (iocb->ki_flags & IOCB_WRITE)
-		kiocb_end_write(iocb);
-
-	ovl_aio_cleanup_handler(aio_req);
-	orig_iocb->ki_complete(orig_iocb, res);
-}
-
-static void ovl_aio_complete_work(struct work_struct *work)
-{
-	struct ovl_aio_req *aio_req = container_of(work,
-						   struct ovl_aio_req, work);
-
-	ovl_aio_rw_complete(&aio_req->iocb, aio_req->res);
-}
-
-static void ovl_aio_queue_completion(struct kiocb *iocb, long res)
-{
-	struct ovl_aio_req *aio_req = container_of(iocb,
-						   struct ovl_aio_req, iocb);
-	struct kiocb *orig_iocb = aio_req->orig_iocb;
-
-	/*
-	 * Punt to a work queue to serialize updates of mtime/size.
-	 */
-	aio_req->res = res;
-	INIT_WORK(&aio_req->work, ovl_aio_complete_work);
-	queue_work(file_inode(orig_iocb->ki_filp)->i_sb->s_dio_done_wq,
-		   &aio_req->work);
-}
-
-static int ovl_init_aio_done_wq(struct super_block *sb)
-{
-	if (sb->s_dio_done_wq)
-		return 0;
-
-	return sb_init_dio_done_wq(sb);
-}
-
 static ssize_t ovl_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 {
 	struct file *file = iocb->ki_filp;
 	struct fd real;
-	const struct cred *old_cred;
 	ssize_t ret;
+	struct backing_file_ctx ctx = {
+		.cred = ovl_creds(file_inode(file)->i_sb),
+		.user_file = file,
+		.accessed = ovl_file_accessed,
+	};
 
 	if (!iov_iter_count(iter))
 		return 0;
@@ -361,37 +280,8 @@ static ssize_t ovl_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 	if (ret)
 		return ret;
 
-	ret = -EINVAL;
-	if (iocb->ki_flags & IOCB_DIRECT &&
-	    !(real.file->f_mode & FMODE_CAN_ODIRECT))
-		goto out_fdput;
-
-	old_cred = ovl_override_creds(file_inode(file)->i_sb);
-	if (is_sync_kiocb(iocb)) {
-		rwf_t rwf = iocb_to_rw_flags(iocb->ki_flags);
-
-		ret = vfs_iter_read(real.file, iter, &iocb->ki_pos, rwf);
-	} else {
-		struct ovl_aio_req *aio_req;
-
-		ret = -ENOMEM;
-		aio_req = kmem_cache_zalloc(ovl_aio_request_cachep, GFP_KERNEL);
-		if (!aio_req)
-			goto out;
-
-		aio_req->orig_iocb = iocb;
-		kiocb_clone(&aio_req->iocb, iocb, get_file(real.file));
-		aio_req->iocb.ki_complete = ovl_aio_rw_complete;
-		refcount_set(&aio_req->ref, 2);
-		ret = vfs_iocb_iter_read(real.file, &aio_req->iocb, iter);
-		ovl_aio_put(aio_req);
-		if (ret != -EIOCBQUEUED)
-			ovl_aio_cleanup_handler(aio_req);
-	}
-out:
-	revert_creds(old_cred);
-	ovl_file_accessed(file);
-out_fdput:
+	ret = backing_file_read_iter(real.file, iter, iocb, iocb->ki_flags,
+				     &ctx);
 	fdput(real);
 
 	return ret;
@@ -402,9 +292,13 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter)
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
 	struct fd real;
-	const struct cred *old_cred;
 	ssize_t ret;
 	int ifl = iocb->ki_flags;
+	struct backing_file_ctx ctx = {
+		.cred = ovl_creds(inode->i_sb),
+		.user_file = file,
+		.end_write = ovl_file_modified,
+	};
 
 	if (!iov_iter_count(iter))
 		return 0;
@@ -412,19 +306,11 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter)
 	inode_lock(inode);
 	/* Update mode */
 	ovl_copyattr(inode);
-	ret = file_remove_privs(file);
-	if (ret)
-		goto out_unlock;
 
 	ret = ovl_real_fdget(file, &real);
 	if (ret)
 		goto out_unlock;
 
-	ret = -EINVAL;
-	if (iocb->ki_flags & IOCB_DIRECT &&
-	    !(real.file->f_mode & FMODE_CAN_ODIRECT))
-		goto out_fdput;
-
 	if (!ovl_should_sync(OVL_FS(inode->i_sb)))
 		ifl &= ~(IOCB_DSYNC | IOCB_SYNC);
 
@@ -433,39 +319,7 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter)
 	 * this property in case it is set by the issuer.
 	 */
 	ifl &= ~IOCB_DIO_CALLER_COMP;
-
-	old_cred = ovl_override_creds(file_inode(file)->i_sb);
-	if (is_sync_kiocb(iocb)) {
-		rwf_t rwf = iocb_to_rw_flags(ifl);
-
-		ret = vfs_iter_write(real.file, iter, &iocb->ki_pos, rwf);
-		/* Update size */
-		ovl_file_modified(file);
-	} else {
-		struct ovl_aio_req *aio_req;
-
-		ret = ovl_init_aio_done_wq(inode->i_sb);
-		if (ret)
-			goto out;
-
-		ret = -ENOMEM;
-		aio_req = kmem_cache_zalloc(ovl_aio_request_cachep, GFP_KERNEL);
-		if (!aio_req)
-			goto out;
-
-		aio_req->orig_iocb = iocb;
-		kiocb_clone(&aio_req->iocb, iocb, get_file(real.file));
-		aio_req->iocb.ki_flags = ifl;
-		aio_req->iocb.ki_complete = ovl_aio_queue_completion;
-		refcount_set(&aio_req->ref, 2);
-		ret = vfs_iocb_iter_write(real.file, &aio_req->iocb, iter);
-		ovl_aio_put(aio_req);
-		if (ret != -EIOCBQUEUED)
-			ovl_aio_cleanup_handler(aio_req);
-	}
-out:
-	revert_creds(old_cred);
-out_fdput:
+	ret = backing_file_write_iter(real.file, iter, iocb, ifl, &ctx);
 	fdput(real);
 
 out_unlock:
@@ -777,19 +631,3 @@ const struct file_operations ovl_file_operations = {
 	.copy_file_range	= ovl_copy_file_range,
 	.remap_file_range	= ovl_remap_file_range,
 };
-
-int __init ovl_aio_request_cache_init(void)
-{
-	ovl_aio_request_cachep = kmem_cache_create("ovl_aio_req",
-						   sizeof(struct ovl_aio_req),
-						   0, SLAB_HWCACHE_ALIGN, NULL);
-	if (!ovl_aio_request_cachep)
-		return -ENOMEM;
-
-	return 0;
-}
-
-void ovl_aio_request_cache_destroy(void)
-{
-	kmem_cache_destroy(ovl_aio_request_cachep);
-}
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index ca88b2636a57..509a57c85fae 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -417,6 +417,12 @@ int ovl_want_write(struct dentry *dentry);
 void ovl_drop_write(struct dentry *dentry);
 struct dentry *ovl_workdir(struct dentry *dentry);
 const struct cred *ovl_override_creds(struct super_block *sb);
+
+static inline const struct cred *ovl_creds(struct super_block *sb)
+{
+	return OVL_FS(sb)->creator_cred;
+}
+
 int ovl_can_decode_fh(struct super_block *sb);
 struct dentry *ovl_indexdir(struct super_block *sb);
 bool ovl_index_all(struct super_block *sb);
@@ -829,8 +835,6 @@ struct dentry *ovl_create_temp(struct ovl_fs *ofs, struct dentry *workdir,
 
 /* file.c */
 extern const struct file_operations ovl_file_operations;
-int __init ovl_aio_request_cache_init(void);
-void ovl_aio_request_cache_destroy(void);
 int ovl_real_fileattr_get(const struct path *realpath, struct fileattr *fa);
 int ovl_real_fileattr_set(const struct path *realpath, struct fileattr *fa);
 int ovl_fileattr_get(struct dentry *dentry, struct fileattr *fa);
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index a0967bb25003..bcd4c314a7eb 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -1501,14 +1501,10 @@ static int __init ovl_init(void)
 	if (ovl_inode_cachep == NULL)
 		return -ENOMEM;
 
-	err = ovl_aio_request_cache_init();
-	if (!err) {
-		err = register_filesystem(&ovl_fs_type);
-		if (!err)
-			return 0;
+	err = register_filesystem(&ovl_fs_type);
+	if (!err)
+		return 0;
 
-		ovl_aio_request_cache_destroy();
-	}
 	kmem_cache_destroy(ovl_inode_cachep);
 
 	return err;
@@ -1524,7 +1520,6 @@ static void __exit ovl_exit(void)
 	 */
 	rcu_barrier();
 	kmem_cache_destroy(ovl_inode_cachep);
-	ovl_aio_request_cache_destroy();
 }
 
 module_init(ovl_init);
diff --git a/include/linux/backing-file.h b/include/linux/backing-file.h
index 55c9e804f780..0648d548a418 100644
--- a/include/linux/backing-file.h
+++ b/include/linux/backing-file.h
@@ -9,9 +9,24 @@
 #define _LINUX_BACKING_FILE_H
 
 #include <linux/file.h>
+#include <linux/uio.h>
+#include <linux/fs.h>
+
+struct backing_file_ctx {
+	const struct cred *cred;
+	struct file *user_file;
+	void (*accessed)(struct file *);
+	void (*end_write)(struct file *);
+};
 
 struct file *backing_file_open(const struct path *user_path, int flags,
 			       const struct path *real_path,
 			       const struct cred *cred);
+ssize_t backing_file_read_iter(struct file *file, struct iov_iter *iter,
+			       struct kiocb *iocb, int flags,
+			       struct backing_file_ctx *ctx);
+ssize_t backing_file_write_iter(struct file *file, struct iov_iter *iter,
+				struct kiocb *iocb, int flags,
+				struct backing_file_ctx *ctx);
 
 #endif /* _LINUX_BACKING_FILE_H */
-- 
cgit v1.2.3


From 9b7e9e2f5d5c3d079ec46bc71b114012e362ea6e Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Fri, 13 Oct 2023 12:13:12 +0300
Subject: fs: factor out backing_file_splice_{read,write}() helpers

There is not much in those helpers, but it makes sense to have them
logically next to the backing_file_{read,write}_iter() helpers as they
may grow more common logic in the future.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
---
 fs/backing-file.c            | 51 ++++++++++++++++++++++++++++++++++++++++++++
 fs/overlayfs/file.c          | 33 +++++++++++-----------------
 include/linux/backing-file.h |  8 +++++++
 3 files changed, 72 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/fs/backing-file.c b/fs/backing-file.c
index 323187a49da3..ddd35c1d6c71 100644
--- a/fs/backing-file.c
+++ b/fs/backing-file.c
@@ -10,6 +10,7 @@
 
 #include <linux/fs.h>
 #include <linux/backing-file.h>
+#include <linux/splice.h>
 
 #include "internal.h"
 
@@ -245,6 +246,56 @@ out:
 }
 EXPORT_SYMBOL_GPL(backing_file_write_iter);
 
+ssize_t backing_file_splice_read(struct file *in, loff_t *ppos,
+				 struct pipe_inode_info *pipe, size_t len,
+				 unsigned int flags,
+				 struct backing_file_ctx *ctx)
+{
+	const struct cred *old_cred;
+	ssize_t ret;
+
+	if (WARN_ON_ONCE(!(in->f_mode & FMODE_BACKING)))
+		return -EIO;
+
+	old_cred = override_creds(ctx->cred);
+	ret = vfs_splice_read(in, ppos, pipe, len, flags);
+	revert_creds(old_cred);
+
+	if (ctx->accessed)
+		ctx->accessed(ctx->user_file);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(backing_file_splice_read);
+
+ssize_t backing_file_splice_write(struct pipe_inode_info *pipe,
+				  struct file *out, loff_t *ppos, size_t len,
+				  unsigned int flags,
+				  struct backing_file_ctx *ctx)
+{
+	const struct cred *old_cred;
+	ssize_t ret;
+
+	if (WARN_ON_ONCE(!(out->f_mode & FMODE_BACKING)))
+		return -EIO;
+
+	ret = file_remove_privs(ctx->user_file);
+	if (ret)
+		return ret;
+
+	old_cred = override_creds(ctx->cred);
+	file_start_write(out);
+	ret = iter_file_splice_write(pipe, out, ppos, len, flags);
+	file_end_write(out);
+	revert_creds(old_cred);
+
+	if (ctx->end_write)
+		ctx->end_write(ctx->user_file);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(backing_file_splice_write);
+
 static int __init backing_aio_init(void)
 {
 	backing_aio_cachep = kmem_cache_create("backing_aio",
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index 1b578cb27a26..69b52d2f9c74 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -9,7 +9,6 @@
 #include <linux/xattr.h>
 #include <linux/uio.h>
 #include <linux/uaccess.h>
-#include <linux/splice.h>
 #include <linux/security.h>
 #include <linux/mm.h>
 #include <linux/fs.h>
@@ -332,20 +331,21 @@ static ssize_t ovl_splice_read(struct file *in, loff_t *ppos,
 			       struct pipe_inode_info *pipe, size_t len,
 			       unsigned int flags)
 {
-	const struct cred *old_cred;
 	struct fd real;
 	ssize_t ret;
+	struct backing_file_ctx ctx = {
+		.cred = ovl_creds(file_inode(in)->i_sb),
+		.user_file = in,
+		.accessed = ovl_file_accessed,
+	};
 
 	ret = ovl_real_fdget(in, &real);
 	if (ret)
 		return ret;
 
-	old_cred = ovl_override_creds(file_inode(in)->i_sb);
-	ret = vfs_splice_read(real.file, ppos, pipe, len, flags);
-	revert_creds(old_cred);
-	ovl_file_accessed(in);
-
+	ret = backing_file_splice_read(real.file, ppos, pipe, len, flags, &ctx);
 	fdput(real);
+
 	return ret;
 }
 
@@ -361,30 +361,23 @@ static ssize_t ovl_splice_write(struct pipe_inode_info *pipe, struct file *out,
 				loff_t *ppos, size_t len, unsigned int flags)
 {
 	struct fd real;
-	const struct cred *old_cred;
 	struct inode *inode = file_inode(out);
 	ssize_t ret;
+	struct backing_file_ctx ctx = {
+		.cred = ovl_creds(inode->i_sb),
+		.user_file = out,
+		.end_write = ovl_file_modified,
+	};
 
 	inode_lock(inode);
 	/* Update mode */
 	ovl_copyattr(inode);
-	ret = file_remove_privs(out);
-	if (ret)
-		goto out_unlock;
 
 	ret = ovl_real_fdget(out, &real);
 	if (ret)
 		goto out_unlock;
 
-	old_cred = ovl_override_creds(inode->i_sb);
-	file_start_write(real.file);
-
-	ret = iter_file_splice_write(pipe, real.file, ppos, len, flags);
-
-	file_end_write(real.file);
-	/* Update size */
-	ovl_file_modified(out);
-	revert_creds(old_cred);
+	ret = backing_file_splice_write(pipe, real.file, ppos, len, flags, &ctx);
 	fdput(real);
 
 out_unlock:
diff --git a/include/linux/backing-file.h b/include/linux/backing-file.h
index 0648d548a418..0546d5b1c9f5 100644
--- a/include/linux/backing-file.h
+++ b/include/linux/backing-file.h
@@ -28,5 +28,13 @@ ssize_t backing_file_read_iter(struct file *file, struct iov_iter *iter,
 ssize_t backing_file_write_iter(struct file *file, struct iov_iter *iter,
 				struct kiocb *iocb, int flags,
 				struct backing_file_ctx *ctx);
+ssize_t backing_file_splice_read(struct file *in, loff_t *ppos,
+				 struct pipe_inode_info *pipe, size_t len,
+				 unsigned int flags,
+				 struct backing_file_ctx *ctx);
+ssize_t backing_file_splice_write(struct pipe_inode_info *pipe,
+				  struct file *out, loff_t *ppos, size_t len,
+				  unsigned int flags,
+				  struct backing_file_ctx *ctx);
 
 #endif /* _LINUX_BACKING_FILE_H */
-- 
cgit v1.2.3


From f567377e406c032fff0799bde4fdf4a977529b84 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Fri, 13 Oct 2023 12:49:37 +0300
Subject: fs: factor out backing_file_mmap() helper

Assert that the file object is allocated in a backing_file container
so that file_user_path() could be used to display the user path and
not the backing file's path in /proc/<pid>/maps.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
---
 fs/backing-file.c            | 27 +++++++++++++++++++++++++++
 fs/overlayfs/file.c          | 23 ++++++-----------------
 include/linux/backing-file.h |  2 ++
 3 files changed, 35 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/fs/backing-file.c b/fs/backing-file.c
index ddd35c1d6c71..a681f38d84d8 100644
--- a/fs/backing-file.c
+++ b/fs/backing-file.c
@@ -11,6 +11,7 @@
 #include <linux/fs.h>
 #include <linux/backing-file.h>
 #include <linux/splice.h>
+#include <linux/mm.h>
 
 #include "internal.h"
 
@@ -296,6 +297,32 @@ ssize_t backing_file_splice_write(struct pipe_inode_info *pipe,
 }
 EXPORT_SYMBOL_GPL(backing_file_splice_write);
 
+int backing_file_mmap(struct file *file, struct vm_area_struct *vma,
+		      struct backing_file_ctx *ctx)
+{
+	const struct cred *old_cred;
+	int ret;
+
+	if (WARN_ON_ONCE(!(file->f_mode & FMODE_BACKING)) ||
+	    WARN_ON_ONCE(ctx->user_file != vma->vm_file))
+		return -EIO;
+
+	if (!file->f_op->mmap)
+		return -ENODEV;
+
+	vma_set_file(vma, file);
+
+	old_cred = override_creds(ctx->cred);
+	ret = call_mmap(vma->vm_file, vma);
+	revert_creds(old_cred);
+
+	if (ctx->accessed)
+		ctx->accessed(ctx->user_file);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(backing_file_mmap);
+
 static int __init backing_aio_init(void)
 {
 	backing_aio_cachep = kmem_cache_create("backing_aio",
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index 69b52d2f9c74..05536964d37f 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -10,7 +10,6 @@
 #include <linux/uio.h>
 #include <linux/uaccess.h>
 #include <linux/security.h>
-#include <linux/mm.h>
 #include <linux/fs.h>
 #include <linux/backing-file.h>
 #include "overlayfs.h"
@@ -415,23 +414,13 @@ static int ovl_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 static int ovl_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct file *realfile = file->private_data;
-	const struct cred *old_cred;
-	int ret;
-
-	if (!realfile->f_op->mmap)
-		return -ENODEV;
-
-	if (WARN_ON(file != vma->vm_file))
-		return -EIO;
-
-	vma_set_file(vma, realfile);
-
-	old_cred = ovl_override_creds(file_inode(file)->i_sb);
-	ret = call_mmap(vma->vm_file, vma);
-	revert_creds(old_cred);
-	ovl_file_accessed(file);
+	struct backing_file_ctx ctx = {
+		.cred = ovl_creds(file_inode(file)->i_sb),
+		.user_file = file,
+		.accessed = ovl_file_accessed,
+	};
 
-	return ret;
+	return backing_file_mmap(realfile, vma, &ctx);
 }
 
 static long ovl_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
diff --git a/include/linux/backing-file.h b/include/linux/backing-file.h
index 0546d5b1c9f5..3f1fe1774f1b 100644
--- a/include/linux/backing-file.h
+++ b/include/linux/backing-file.h
@@ -36,5 +36,7 @@ ssize_t backing_file_splice_write(struct pipe_inode_info *pipe,
 				  struct file *out, loff_t *ppos, size_t len,
 				  unsigned int flags,
 				  struct backing_file_ctx *ctx);
+int backing_file_mmap(struct file *file, struct vm_area_struct *vma,
+		      struct backing_file_ctx *ctx);
 
 #endif /* _LINUX_BACKING_FILE_H */
-- 
cgit v1.2.3


From 9942cb22ea458c34fa17b73d143ea32d4df1caca Mon Sep 17 00:00:00 2001
From: Vincent Guittot <vincent.guittot@linaro.org>
Date: Mon, 11 Dec 2023 11:48:49 +0100
Subject: sched/topology: Add a new arch_scale_freq_ref() method

Create a new method to get a unique and fixed max frequency. Currently
cpuinfo.max_freq or the highest (or last) state of performance domain are
used as the max frequency when computing the frequency for a level of
utilization, but:

  - cpuinfo_max_freq can change at runtime. boost is one example of
    such change.

  - cpuinfo.max_freq and last item of the PD can be different leading to
    different results between cpufreq and energy model.

We need to save the reference frequency that has been used when computing
the CPUs capacity and use this fixed and coherent value to convert between
frequency and CPU's capacity.

In fact, we already save the frequency that has been used when computing
the capacity of each CPU. We extend the precision to save kHz instead of
MHz currently and we modify the type to be aligned with other variables
used when converting frequency to capacity and the other way.

[ mingo: Minor edits. ]

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Lukasz Luba <lukasz.luba@arm.com>
Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
Acked-by: Sudeep Holla <sudeep.holla@arm.com>
Link: https://lore.kernel.org/r/20231211104855.558096-2-vincent.guittot@linaro.org
---
 arch/arm/include/asm/topology.h   |  1 +
 arch/arm64/include/asm/topology.h |  1 +
 arch/riscv/include/asm/topology.h |  1 +
 drivers/base/arch_topology.c      | 29 ++++++++++++++---------------
 include/linux/arch_topology.h     |  7 +++++++
 include/linux/sched/topology.h    |  8 ++++++++
 6 files changed, 32 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h
index c7d2510e5a78..853c4f81ba4a 100644
--- a/arch/arm/include/asm/topology.h
+++ b/arch/arm/include/asm/topology.h
@@ -13,6 +13,7 @@
 #define arch_set_freq_scale topology_set_freq_scale
 #define arch_scale_freq_capacity topology_get_freq_scale
 #define arch_scale_freq_invariant topology_scale_freq_invariant
+#define arch_scale_freq_ref topology_get_freq_ref
 #endif
 
 /* Replace task scheduler's default cpu-invariant accounting */
diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
index 9fab663dd2de..a323b109b9c4 100644
--- a/arch/arm64/include/asm/topology.h
+++ b/arch/arm64/include/asm/topology.h
@@ -23,6 +23,7 @@ void update_freq_counters_refs(void);
 #define arch_set_freq_scale topology_set_freq_scale
 #define arch_scale_freq_capacity topology_get_freq_scale
 #define arch_scale_freq_invariant topology_scale_freq_invariant
+#define arch_scale_freq_ref topology_get_freq_ref
 
 #ifdef CONFIG_ACPI_CPPC_LIB
 #define arch_init_invariance_cppc topology_init_cpu_capacity_cppc
diff --git a/arch/riscv/include/asm/topology.h b/arch/riscv/include/asm/topology.h
index e316ab3b77f3..61183688bdd5 100644
--- a/arch/riscv/include/asm/topology.h
+++ b/arch/riscv/include/asm/topology.h
@@ -9,6 +9,7 @@
 #define arch_set_freq_scale		topology_set_freq_scale
 #define arch_scale_freq_capacity	topology_get_freq_scale
 #define arch_scale_freq_invariant	topology_scale_freq_invariant
+#define arch_scale_freq_ref		topology_get_freq_ref
 
 /* Replace task scheduler's default cpu-invariant accounting */
 #define arch_scale_cpu_capacity	topology_get_cpu_scale
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index b741b5ba82bd..0c9ae5b157b1 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -19,6 +19,7 @@
 #include <linux/init.h>
 #include <linux/rcupdate.h>
 #include <linux/sched.h>
+#include <linux/units.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/thermal_pressure.h>
@@ -26,7 +27,8 @@
 static DEFINE_PER_CPU(struct scale_freq_data __rcu *, sft_data);
 static struct cpumask scale_freq_counters_mask;
 static bool scale_freq_invariant;
-static DEFINE_PER_CPU(u32, freq_factor) = 1;
+DEFINE_PER_CPU(unsigned long, capacity_freq_ref) = 1;
+EXPORT_PER_CPU_SYMBOL_GPL(capacity_freq_ref);
 
 static bool supports_scale_freq_counters(const struct cpumask *cpus)
 {
@@ -170,9 +172,9 @@ DEFINE_PER_CPU(unsigned long, thermal_pressure);
  * operating on stale data when hot-plug is used for some CPUs. The
  * @capped_freq reflects the currently allowed max CPUs frequency due to
  * thermal capping. It might be also a boost frequency value, which is bigger
- * than the internal 'freq_factor' max frequency. In such case the pressure
- * value should simply be removed, since this is an indication that there is
- * no thermal throttling. The @capped_freq must be provided in kHz.
+ * than the internal 'capacity_freq_ref' max frequency. In such case the
+ * pressure value should simply be removed, since this is an indication that
+ * there is no thermal throttling. The @capped_freq must be provided in kHz.
  */
 void topology_update_thermal_pressure(const struct cpumask *cpus,
 				      unsigned long capped_freq)
@@ -183,10 +185,7 @@ void topology_update_thermal_pressure(const struct cpumask *cpus,
 
 	cpu = cpumask_first(cpus);
 	max_capacity = arch_scale_cpu_capacity(cpu);
-	max_freq = per_cpu(freq_factor, cpu);
-
-	/* Convert to MHz scale which is used in 'freq_factor' */
-	capped_freq /= 1000;
+	max_freq = arch_scale_freq_ref(cpu);
 
 	/*
 	 * Handle properly the boost frequencies, which should simply clean
@@ -279,13 +278,13 @@ void topology_normalize_cpu_scale(void)
 
 	capacity_scale = 1;
 	for_each_possible_cpu(cpu) {
-		capacity = raw_capacity[cpu] * per_cpu(freq_factor, cpu);
+		capacity = raw_capacity[cpu] * per_cpu(capacity_freq_ref, cpu);
 		capacity_scale = max(capacity, capacity_scale);
 	}
 
 	pr_debug("cpu_capacity: capacity_scale=%llu\n", capacity_scale);
 	for_each_possible_cpu(cpu) {
-		capacity = raw_capacity[cpu] * per_cpu(freq_factor, cpu);
+		capacity = raw_capacity[cpu] * per_cpu(capacity_freq_ref, cpu);
 		capacity = div64_u64(capacity << SCHED_CAPACITY_SHIFT,
 			capacity_scale);
 		topology_set_cpu_scale(cpu, capacity);
@@ -321,15 +320,15 @@ bool __init topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu)
 			cpu_node, raw_capacity[cpu]);
 
 		/*
-		 * Update freq_factor for calculating early boot cpu capacities.
+		 * Update capacity_freq_ref for calculating early boot CPU capacities.
 		 * For non-clk CPU DVFS mechanism, there's no way to get the
 		 * frequency value now, assuming they are running at the same
-		 * frequency (by keeping the initial freq_factor value).
+		 * frequency (by keeping the initial capacity_freq_ref value).
 		 */
 		cpu_clk = of_clk_get(cpu_node, 0);
 		if (!PTR_ERR_OR_ZERO(cpu_clk)) {
-			per_cpu(freq_factor, cpu) =
-				clk_get_rate(cpu_clk) / 1000;
+			per_cpu(capacity_freq_ref, cpu) =
+				clk_get_rate(cpu_clk) / HZ_PER_KHZ;
 			clk_put(cpu_clk);
 		}
 	} else {
@@ -411,7 +410,7 @@ init_cpu_capacity_callback(struct notifier_block *nb,
 	cpumask_andnot(cpus_to_visit, cpus_to_visit, policy->related_cpus);
 
 	for_each_cpu(cpu, policy->related_cpus)
-		per_cpu(freq_factor, cpu) = policy->cpuinfo.max_freq / 1000;
+		per_cpu(capacity_freq_ref, cpu) = policy->cpuinfo.max_freq;
 
 	if (cpumask_empty(cpus_to_visit)) {
 		topology_normalize_cpu_scale();
diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h
index a07b510e7dc5..32c24ff4f2a8 100644
--- a/include/linux/arch_topology.h
+++ b/include/linux/arch_topology.h
@@ -27,6 +27,13 @@ static inline unsigned long topology_get_cpu_scale(int cpu)
 
 void topology_set_cpu_scale(unsigned int cpu, unsigned long capacity);
 
+DECLARE_PER_CPU(unsigned long, capacity_freq_ref);
+
+static inline unsigned long topology_get_freq_ref(int cpu)
+{
+	return per_cpu(capacity_freq_ref, cpu);
+}
+
 DECLARE_PER_CPU(unsigned long, arch_freq_scale);
 
 static inline unsigned long topology_get_freq_scale(int cpu)
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index de545ba85218..a6e04b4a21d7 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -279,6 +279,14 @@ void arch_update_thermal_pressure(const struct cpumask *cpus,
 { }
 #endif
 
+#ifndef arch_scale_freq_ref
+static __always_inline
+unsigned int arch_scale_freq_ref(int cpu)
+{
+	return 0;
+}
+#endif
+
 static inline int task_node(const struct task_struct *p)
 {
 	return cpu_to_node(task_cpu(p));
-- 
cgit v1.2.3


From 599457ba15403037b489fe536266a3d5f9efaed7 Mon Sep 17 00:00:00 2001
From: Vincent Guittot <vincent.guittot@linaro.org>
Date: Mon, 11 Dec 2023 11:48:50 +0100
Subject: cpufreq: Use the fixed and coherent frequency for scaling capacity

cpuinfo.max_freq can change at runtime because of boost as an example. This
implies that the value could be different from the frequency that has been
used to compute the capacity of a CPU.

The new arch_scale_freq_ref() returns a fixed and coherent frequency
that can be used to compute the capacity for a given frequency.

[ Also fix a arch_set_freq_scale()  newline style wart in <linux/cpufreq.h>. ]

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Lukasz Luba <lukasz.luba@arm.com>
Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Acked-by: Rafael J. Wysocki <rafael@kernel.org>
Link: https://lore.kernel.org/r/20231211104855.558096-3-vincent.guittot@linaro.org
---
 drivers/cpufreq/cpufreq.c | 4 ++--
 include/linux/cpufreq.h   | 1 +
 2 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 934d35f570b7..44db4f59c4cc 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -454,7 +454,7 @@ void cpufreq_freq_transition_end(struct cpufreq_policy *policy,
 
 	arch_set_freq_scale(policy->related_cpus,
 			    policy->cur,
-			    policy->cpuinfo.max_freq);
+			    arch_scale_freq_ref(policy->cpu));
 
 	spin_lock(&policy->transition_lock);
 	policy->transition_ongoing = false;
@@ -2174,7 +2174,7 @@ unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy,
 
 	policy->cur = freq;
 	arch_set_freq_scale(policy->related_cpus, freq,
-			    policy->cpuinfo.max_freq);
+			    arch_scale_freq_ref(policy->cpu));
 	cpufreq_stats_record_transition(policy, freq);
 
 	if (trace_cpu_frequency_enabled()) {
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 1c5ca92a0555..afda5f24d3dd 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -1203,6 +1203,7 @@ void arch_set_freq_scale(const struct cpumask *cpus,
 {
 }
 #endif
+
 /* the following are really really optional */
 extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs;
 extern struct freq_attr cpufreq_freq_attr_scaling_boost_freqs;
-- 
cgit v1.2.3


From 15cbbd1d317e07b4e5c6aca5d4c5579539a82784 Mon Sep 17 00:00:00 2001
From: Vincent Guittot <vincent.guittot@linaro.org>
Date: Mon, 11 Dec 2023 11:48:52 +0100
Subject: energy_model: Use a fixed reference frequency

The last item of a performance domain is not always the performance point
that has been used to compute CPU's capacity. This can lead to different
target frequency compared with other part of the system like schedutil and
would result in wrong energy estimation.

A new arch_scale_freq_ref() is available to return a fixed and coherent
frequency reference that can be used when computing the CPU's frequency
for an level of utilization. Use this function to get this reference
frequency.

Energy model is never used without defining arch_scale_freq_ref() but
can be compiled. Define a default arch_scale_freq_ref() returning 0
in such case.

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Lukasz Luba <lukasz.luba@arm.com>
Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
Link: https://lore.kernel.org/r/20231211104855.558096-5-vincent.guittot@linaro.org
---
 include/linux/energy_model.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h
index adec808b371a..88d91e087471 100644
--- a/include/linux/energy_model.h
+++ b/include/linux/energy_model.h
@@ -224,7 +224,7 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd,
 				unsigned long max_util, unsigned long sum_util,
 				unsigned long allowed_cpu_cap)
 {
-	unsigned long freq, scale_cpu;
+	unsigned long freq, ref_freq, scale_cpu;
 	struct em_perf_state *ps;
 	int cpu;
 
@@ -241,10 +241,10 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd,
 	 */
 	cpu = cpumask_first(to_cpumask(pd->cpus));
 	scale_cpu = arch_scale_cpu_capacity(cpu);
-	ps = &pd->table[pd->nr_perf_states - 1];
+	ref_freq = arch_scale_freq_ref(cpu);
 
 	max_util = min(max_util, allowed_cpu_cap);
-	freq = map_util_freq(max_util, ps->frequency, scale_cpu);
+	freq = map_util_freq(max_util, ref_freq, scale_cpu);
 
 	/*
 	 * Find the lowest performance state of the Energy Model above the
-- 
cgit v1.2.3


From 50b813b147e9eb6546a1fc49d4e703e6d23691f2 Mon Sep 17 00:00:00 2001
From: Vincent Guittot <vincent.guittot@linaro.org>
Date: Mon, 11 Dec 2023 11:48:53 +0100
Subject: cpufreq/cppc: Move and rename
 cppc_cpufreq_{perf_to_khz|khz_to_perf}()

Move and rename cppc_cpufreq_perf_to_khz() and cppc_cpufreq_khz_to_perf() to
use them outside cppc_cpufreq in topology_init_cpu_capacity_cppc().

Modify the interface to use struct cppc_perf_caps *caps instead of
struct cppc_cpudata *cpu_data as we only use the fields of cppc_perf_caps.

cppc_cpufreq was converting the lowest and nominal freq from MHz to kHz
before using them. We move this conversion inside cppc_perf_to_khz and
cppc_khz_to_perf to make them generic and usable outside cppc_cpufreq.

No functional change

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Pierre Gondois <pierre.gondois@arm.com>
Acked-by: Rafael J. Wysocki <rafael@kernel.org>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Link: https://lore.kernel.org/r/20231211104855.558096-6-vincent.guittot@linaro.org
---
 drivers/acpi/cppc_acpi.c       | 104 ++++++++++++++++++++++++++++++
 drivers/cpufreq/cppc_cpufreq.c | 139 +++++------------------------------------
 include/acpi/cppc_acpi.h       |   2 +
 3 files changed, 123 insertions(+), 122 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index 7ff269a78c20..d155a86a8614 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -39,6 +39,9 @@
 #include <linux/rwsem.h>
 #include <linux/wait.h>
 #include <linux/topology.h>
+#include <linux/dmi.h>
+#include <linux/units.h>
+#include <asm/unaligned.h>
 
 #include <acpi/cppc_acpi.h>
 
@@ -1760,3 +1763,104 @@ unsigned int cppc_get_transition_latency(int cpu_num)
 	return latency_ns;
 }
 EXPORT_SYMBOL_GPL(cppc_get_transition_latency);
+
+/* Minimum struct length needed for the DMI processor entry we want */
+#define DMI_ENTRY_PROCESSOR_MIN_LENGTH	48
+
+/* Offset in the DMI processor structure for the max frequency */
+#define DMI_PROCESSOR_MAX_SPEED		0x14
+
+/* Callback function used to retrieve the max frequency from DMI */
+static void cppc_find_dmi_mhz(const struct dmi_header *dm, void *private)
+{
+	const u8 *dmi_data = (const u8 *)dm;
+	u16 *mhz = (u16 *)private;
+
+	if (dm->type == DMI_ENTRY_PROCESSOR &&
+	    dm->length >= DMI_ENTRY_PROCESSOR_MIN_LENGTH) {
+		u16 val = (u16)get_unaligned((const u16 *)
+				(dmi_data + DMI_PROCESSOR_MAX_SPEED));
+		*mhz = val > *mhz ? val : *mhz;
+	}
+}
+
+/* Look up the max frequency in DMI */
+static u64 cppc_get_dmi_max_khz(void)
+{
+	u16 mhz = 0;
+
+	dmi_walk(cppc_find_dmi_mhz, &mhz);
+
+	/*
+	 * Real stupid fallback value, just in case there is no
+	 * actual value set.
+	 */
+	mhz = mhz ? mhz : 1;
+
+	return KHZ_PER_MHZ * mhz;
+}
+
+/*
+ * If CPPC lowest_freq and nominal_freq registers are exposed then we can
+ * use them to convert perf to freq and vice versa. The conversion is
+ * extrapolated as an affine function passing by the 2 points:
+ *  - (Low perf, Low freq)
+ *  - (Nominal perf, Nominal freq)
+ */
+unsigned int cppc_perf_to_khz(struct cppc_perf_caps *caps, unsigned int perf)
+{
+	s64 retval, offset = 0;
+	static u64 max_khz;
+	u64 mul, div;
+
+	if (caps->lowest_freq && caps->nominal_freq) {
+		mul = caps->nominal_freq - caps->lowest_freq;
+		mul *= KHZ_PER_MHZ;
+		div = caps->nominal_perf - caps->lowest_perf;
+		offset = caps->nominal_freq * KHZ_PER_MHZ -
+			 div64_u64(caps->nominal_perf * mul, div);
+	} else {
+		if (!max_khz)
+			max_khz = cppc_get_dmi_max_khz();
+		mul = max_khz;
+		div = caps->highest_perf;
+	}
+
+	retval = offset + div64_u64(perf * mul, div);
+	if (retval >= 0)
+		return retval;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cppc_perf_to_khz);
+
+unsigned int cppc_khz_to_perf(struct cppc_perf_caps *caps, unsigned int freq)
+{
+	s64 retval, offset = 0;
+	static u64 max_khz;
+	u64  mul, div;
+
+	if (caps->lowest_freq && caps->nominal_freq) {
+		mul = caps->nominal_perf - caps->lowest_perf;
+		div = caps->nominal_freq - caps->lowest_freq;
+		/*
+		 * We don't need to convert to kHz for computing offset and can
+		 * directly use nominal_freq and lowest_freq as the div64_u64
+		 * will remove the frequency unit.
+		 */
+		offset = caps->nominal_perf -
+			 div64_u64(caps->nominal_freq * mul, div);
+		/* But we need it for computing the perf level. */
+		div *= KHZ_PER_MHZ;
+	} else {
+		if (!max_khz)
+			max_khz = cppc_get_dmi_max_khz();
+		mul = caps->highest_perf;
+		div = max_khz;
+	}
+
+	retval = offset + div64_u64(freq * mul, div);
+	if (retval >= 0)
+		return retval;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cppc_khz_to_perf);
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index fe08ca419b3d..64420d9cfd1e 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -16,7 +16,6 @@
 #include <linux/delay.h>
 #include <linux/cpu.h>
 #include <linux/cpufreq.h>
-#include <linux/dmi.h>
 #include <linux/irq_work.h>
 #include <linux/kthread.h>
 #include <linux/time.h>
@@ -27,12 +26,6 @@
 
 #include <acpi/cppc_acpi.h>
 
-/* Minimum struct length needed for the DMI processor entry we want */
-#define DMI_ENTRY_PROCESSOR_MIN_LENGTH	48
-
-/* Offset in the DMI processor structure for the max frequency */
-#define DMI_PROCESSOR_MAX_SPEED		0x14
-
 /*
  * This list contains information parsed from per CPU ACPI _CPC and _PSD
  * structures: e.g. the highest and lowest supported performance, capabilities,
@@ -291,97 +284,9 @@ static inline void cppc_freq_invariance_exit(void)
 }
 #endif /* CONFIG_ACPI_CPPC_CPUFREQ_FIE */
 
-/* Callback function used to retrieve the max frequency from DMI */
-static void cppc_find_dmi_mhz(const struct dmi_header *dm, void *private)
-{
-	const u8 *dmi_data = (const u8 *)dm;
-	u16 *mhz = (u16 *)private;
-
-	if (dm->type == DMI_ENTRY_PROCESSOR &&
-	    dm->length >= DMI_ENTRY_PROCESSOR_MIN_LENGTH) {
-		u16 val = (u16)get_unaligned((const u16 *)
-				(dmi_data + DMI_PROCESSOR_MAX_SPEED));
-		*mhz = val > *mhz ? val : *mhz;
-	}
-}
-
-/* Look up the max frequency in DMI */
-static u64 cppc_get_dmi_max_khz(void)
-{
-	u16 mhz = 0;
-
-	dmi_walk(cppc_find_dmi_mhz, &mhz);
-
-	/*
-	 * Real stupid fallback value, just in case there is no
-	 * actual value set.
-	 */
-	mhz = mhz ? mhz : 1;
-
-	return (1000 * mhz);
-}
-
-/*
- * If CPPC lowest_freq and nominal_freq registers are exposed then we can
- * use them to convert perf to freq and vice versa. The conversion is
- * extrapolated as an affine function passing by the 2 points:
- *  - (Low perf, Low freq)
- *  - (Nominal perf, Nominal perf)
- */
-static unsigned int cppc_cpufreq_perf_to_khz(struct cppc_cpudata *cpu_data,
-					     unsigned int perf)
-{
-	struct cppc_perf_caps *caps = &cpu_data->perf_caps;
-	s64 retval, offset = 0;
-	static u64 max_khz;
-	u64 mul, div;
-
-	if (caps->lowest_freq && caps->nominal_freq) {
-		mul = caps->nominal_freq - caps->lowest_freq;
-		div = caps->nominal_perf - caps->lowest_perf;
-		offset = caps->nominal_freq - div64_u64(caps->nominal_perf * mul, div);
-	} else {
-		if (!max_khz)
-			max_khz = cppc_get_dmi_max_khz();
-		mul = max_khz;
-		div = caps->highest_perf;
-	}
-
-	retval = offset + div64_u64(perf * mul, div);
-	if (retval >= 0)
-		return retval;
-	return 0;
-}
-
-static unsigned int cppc_cpufreq_khz_to_perf(struct cppc_cpudata *cpu_data,
-					     unsigned int freq)
-{
-	struct cppc_perf_caps *caps = &cpu_data->perf_caps;
-	s64 retval, offset = 0;
-	static u64 max_khz;
-	u64  mul, div;
-
-	if (caps->lowest_freq && caps->nominal_freq) {
-		mul = caps->nominal_perf - caps->lowest_perf;
-		div = caps->nominal_freq - caps->lowest_freq;
-		offset = caps->nominal_perf - div64_u64(caps->nominal_freq * mul, div);
-	} else {
-		if (!max_khz)
-			max_khz = cppc_get_dmi_max_khz();
-		mul = caps->highest_perf;
-		div = max_khz;
-	}
-
-	retval = offset + div64_u64(freq * mul, div);
-	if (retval >= 0)
-		return retval;
-	return 0;
-}
-
 static int cppc_cpufreq_set_target(struct cpufreq_policy *policy,
 				   unsigned int target_freq,
 				   unsigned int relation)
-
 {
 	struct cppc_cpudata *cpu_data = policy->driver_data;
 	unsigned int cpu = policy->cpu;
@@ -389,7 +294,7 @@ static int cppc_cpufreq_set_target(struct cpufreq_policy *policy,
 	u32 desired_perf;
 	int ret = 0;
 
-	desired_perf = cppc_cpufreq_khz_to_perf(cpu_data, target_freq);
+	desired_perf = cppc_khz_to_perf(&cpu_data->perf_caps, target_freq);
 	/* Return if it is exactly the same perf */
 	if (desired_perf == cpu_data->perf_ctrls.desired_perf)
 		return ret;
@@ -417,7 +322,7 @@ static unsigned int cppc_cpufreq_fast_switch(struct cpufreq_policy *policy,
 	u32 desired_perf;
 	int ret;
 
-	desired_perf = cppc_cpufreq_khz_to_perf(cpu_data, target_freq);
+	desired_perf = cppc_khz_to_perf(&cpu_data->perf_caps, target_freq);
 	cpu_data->perf_ctrls.desired_perf = desired_perf;
 	ret = cppc_set_perf(cpu, &cpu_data->perf_ctrls);
 
@@ -530,7 +435,7 @@ static int cppc_get_cpu_power(struct device *cpu_dev,
 	min_step = min_cap / CPPC_EM_CAP_STEP;
 	max_step = max_cap / CPPC_EM_CAP_STEP;
 
-	perf_prev = cppc_cpufreq_khz_to_perf(cpu_data, *KHz);
+	perf_prev = cppc_khz_to_perf(perf_caps, *KHz);
 	step = perf_prev / perf_step;
 
 	if (step > max_step)
@@ -550,8 +455,8 @@ static int cppc_get_cpu_power(struct device *cpu_dev,
 			perf = step * perf_step;
 	}
 
-	*KHz = cppc_cpufreq_perf_to_khz(cpu_data, perf);
-	perf_check = cppc_cpufreq_khz_to_perf(cpu_data, *KHz);
+	*KHz = cppc_perf_to_khz(perf_caps, perf);
+	perf_check = cppc_khz_to_perf(perf_caps, *KHz);
 	step_check = perf_check / perf_step;
 
 	/*
@@ -561,8 +466,8 @@ static int cppc_get_cpu_power(struct device *cpu_dev,
 	 */
 	while ((*KHz == prev_freq) || (step_check != step)) {
 		perf++;
-		*KHz = cppc_cpufreq_perf_to_khz(cpu_data, perf);
-		perf_check = cppc_cpufreq_khz_to_perf(cpu_data, *KHz);
+		*KHz = cppc_perf_to_khz(perf_caps, perf);
+		perf_check = cppc_khz_to_perf(perf_caps, *KHz);
 		step_check = perf_check / perf_step;
 	}
 
@@ -591,7 +496,7 @@ static int cppc_get_cpu_cost(struct device *cpu_dev, unsigned long KHz,
 	perf_caps = &cpu_data->perf_caps;
 	max_cap = arch_scale_cpu_capacity(cpu_dev->id);
 
-	perf_prev = cppc_cpufreq_khz_to_perf(cpu_data, KHz);
+	perf_prev = cppc_khz_to_perf(perf_caps, KHz);
 	perf_step = CPPC_EM_CAP_STEP * perf_caps->highest_perf / max_cap;
 	step = perf_prev / perf_step;
 
@@ -679,10 +584,6 @@ static struct cppc_cpudata *cppc_cpufreq_get_cpu_data(unsigned int cpu)
 		goto free_mask;
 	}
 
-	/* Convert the lowest and nominal freq from MHz to KHz */
-	cpu_data->perf_caps.lowest_freq *= 1000;
-	cpu_data->perf_caps.nominal_freq *= 1000;
-
 	list_add(&cpu_data->node, &cpu_data_list);
 
 	return cpu_data;
@@ -724,20 +625,16 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	 * Set min to lowest nonlinear perf to avoid any efficiency penalty (see
 	 * Section 8.4.7.1.1.5 of ACPI 6.1 spec)
 	 */
-	policy->min = cppc_cpufreq_perf_to_khz(cpu_data,
-					       caps->lowest_nonlinear_perf);
-	policy->max = cppc_cpufreq_perf_to_khz(cpu_data,
-					       caps->nominal_perf);
+	policy->min = cppc_perf_to_khz(caps, caps->lowest_nonlinear_perf);
+	policy->max = cppc_perf_to_khz(caps, caps->nominal_perf);
 
 	/*
 	 * Set cpuinfo.min_freq to Lowest to make the full range of performance
 	 * available if userspace wants to use any perf between lowest & lowest
 	 * nonlinear perf
 	 */
-	policy->cpuinfo.min_freq = cppc_cpufreq_perf_to_khz(cpu_data,
-							    caps->lowest_perf);
-	policy->cpuinfo.max_freq = cppc_cpufreq_perf_to_khz(cpu_data,
-							    caps->nominal_perf);
+	policy->cpuinfo.min_freq = cppc_perf_to_khz(caps, caps->lowest_perf);
+	policy->cpuinfo.max_freq = cppc_perf_to_khz(caps, caps->nominal_perf);
 
 	policy->transition_delay_us = cppc_cpufreq_get_transition_delay_us(cpu);
 	policy->shared_type = cpu_data->shared_type;
@@ -773,7 +670,7 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		boost_supported = true;
 
 	/* Set policy->cur to max now. The governors will adjust later. */
-	policy->cur = cppc_cpufreq_perf_to_khz(cpu_data, caps->highest_perf);
+	policy->cur = cppc_perf_to_khz(caps, caps->highest_perf);
 	cpu_data->perf_ctrls.desired_perf =  caps->highest_perf;
 
 	ret = cppc_set_perf(cpu, &cpu_data->perf_ctrls);
@@ -863,7 +760,7 @@ static unsigned int cppc_cpufreq_get_rate(unsigned int cpu)
 	delivered_perf = cppc_perf_from_fbctrs(cpu_data, &fb_ctrs_t0,
 					       &fb_ctrs_t1);
 
-	return cppc_cpufreq_perf_to_khz(cpu_data, delivered_perf);
+	return cppc_perf_to_khz(&cpu_data->perf_caps, delivered_perf);
 }
 
 static int cppc_cpufreq_set_boost(struct cpufreq_policy *policy, int state)
@@ -878,11 +775,9 @@ static int cppc_cpufreq_set_boost(struct cpufreq_policy *policy, int state)
 	}
 
 	if (state)
-		policy->max = cppc_cpufreq_perf_to_khz(cpu_data,
-						       caps->highest_perf);
+		policy->max = cppc_perf_to_khz(caps, caps->highest_perf);
 	else
-		policy->max = cppc_cpufreq_perf_to_khz(cpu_data,
-						       caps->nominal_perf);
+		policy->max = cppc_perf_to_khz(caps, caps->nominal_perf);
 	policy->cpuinfo.max_freq = policy->max;
 
 	ret = freq_qos_update_request(policy->max_freq_req, policy->max);
@@ -937,7 +832,7 @@ static unsigned int hisi_cppc_cpufreq_get_rate(unsigned int cpu)
 	if (ret < 0)
 		return -EIO;
 
-	return cppc_cpufreq_perf_to_khz(cpu_data, desired_perf);
+	return cppc_perf_to_khz(&cpu_data->perf_caps, desired_perf);
 }
 
 static void cppc_check_hisi_workaround(void)
diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h
index 6126c977ece0..3a0995f8bce8 100644
--- a/include/acpi/cppc_acpi.h
+++ b/include/acpi/cppc_acpi.h
@@ -144,6 +144,8 @@ extern int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls);
 extern int cppc_set_enable(int cpu, bool enable);
 extern int cppc_get_perf_caps(int cpu, struct cppc_perf_caps *caps);
 extern bool cppc_perf_ctrs_in_pcc(void);
+extern unsigned int cppc_perf_to_khz(struct cppc_perf_caps *caps, unsigned int perf);
+extern unsigned int cppc_khz_to_perf(struct cppc_perf_caps *caps, unsigned int freq);
 extern bool acpi_cpc_valid(void);
 extern bool cppc_allow_fast_switch(void);
 extern int acpi_get_psd_map(unsigned int cpu, struct cppc_cpudata *cpu_data);
-- 
cgit v1.2.3


From 1f023007f5e782bda19ad9104830c404fd622c5d Mon Sep 17 00:00:00 2001
From: Vincent Guittot <vincent.guittot@linaro.org>
Date: Mon, 11 Dec 2023 11:48:55 +0100
Subject: arm64/amu: Use capacity_ref_freq() to set AMU ratio

Use the new capacity_ref_freq() method to set the ratio that is used by AMU for
computing the arch_scale_freq_capacity().
This helps to keep everything aligned using the same reference for
computing CPUs capacity.

The default value of the ratio (stored in per_cpu(arch_max_freq_scale))
ensures that arch_scale_freq_capacity() returns max capacity until it is
set to its correct value with the cpu capacity and capacity_ref_freq().

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Sudeep Holla <sudeep.holla@arm.com>
Acked-by: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20231211104855.558096-8-vincent.guittot@linaro.org
---
 arch/arm64/kernel/topology.c  | 26 +++++++++++++-------------
 drivers/base/arch_topology.c  | 12 +++++++++++-
 include/linux/arch_topology.h |  1 +
 3 files changed, 25 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 817d788cd866..1a2c72f3e7f8 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -82,7 +82,12 @@ int __init parse_acpi_topology(void)
 #undef pr_fmt
 #define pr_fmt(fmt) "AMU: " fmt
 
-static DEFINE_PER_CPU_READ_MOSTLY(unsigned long, arch_max_freq_scale);
+/*
+ * Ensure that amu_scale_freq_tick() will return SCHED_CAPACITY_SCALE until
+ * the CPU capacity and its associated frequency have been correctly
+ * initialized.
+ */
+static DEFINE_PER_CPU_READ_MOSTLY(unsigned long, arch_max_freq_scale) =  1UL << (2 * SCHED_CAPACITY_SHIFT);
 static DEFINE_PER_CPU(u64, arch_const_cycles_prev);
 static DEFINE_PER_CPU(u64, arch_core_cycles_prev);
 static cpumask_var_t amu_fie_cpus;
@@ -112,14 +117,14 @@ static inline bool freq_counters_valid(int cpu)
 	return true;
 }
 
-static int freq_inv_set_max_ratio(int cpu, u64 max_rate, u64 ref_rate)
+void freq_inv_set_max_ratio(int cpu, u64 max_rate)
 {
-	u64 ratio;
+	u64 ratio, ref_rate = arch_timer_get_rate();
 
 	if (unlikely(!max_rate || !ref_rate)) {
-		pr_debug("CPU%d: invalid maximum or reference frequency.\n",
+		WARN_ONCE(1, "CPU%d: invalid maximum or reference frequency.\n",
 			 cpu);
-		return -EINVAL;
+		return;
 	}
 
 	/*
@@ -139,12 +144,10 @@ static int freq_inv_set_max_ratio(int cpu, u64 max_rate, u64 ref_rate)
 	ratio = div64_u64(ratio, max_rate);
 	if (!ratio) {
 		WARN_ONCE(1, "Reference frequency too low.\n");
-		return -EINVAL;
+		return;
 	}
 
-	per_cpu(arch_max_freq_scale, cpu) = (unsigned long)ratio;
-
-	return 0;
+	WRITE_ONCE(per_cpu(arch_max_freq_scale, cpu), (unsigned long)ratio);
 }
 
 static void amu_scale_freq_tick(void)
@@ -195,10 +198,7 @@ static void amu_fie_setup(const struct cpumask *cpus)
 		return;
 
 	for_each_cpu(cpu, cpus) {
-		if (!freq_counters_valid(cpu) ||
-		    freq_inv_set_max_ratio(cpu,
-					   cpufreq_get_hw_max_freq(cpu) * 1000ULL,
-					   arch_timer_get_rate()))
+		if (!freq_counters_valid(cpu))
 			return;
 	}
 
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index 1aa76b5c96c2..5aaa0865625d 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -344,6 +344,10 @@ bool __init topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu)
 	return !ret;
 }
 
+void __weak freq_inv_set_max_ratio(int cpu, u64 max_rate)
+{
+}
+
 #ifdef CONFIG_ACPI_CPPC_LIB
 #include <acpi/cppc_acpi.h>
 
@@ -381,6 +385,9 @@ void topology_init_cpu_capacity_cppc(void)
 	}
 
 	for_each_possible_cpu(cpu) {
+		freq_inv_set_max_ratio(cpu,
+				       per_cpu(capacity_freq_ref, cpu) * HZ_PER_KHZ);
+
 		capacity = raw_capacity[cpu];
 		capacity = div64_u64(capacity << SCHED_CAPACITY_SHIFT,
 				     capacity_scale);
@@ -422,8 +429,11 @@ init_cpu_capacity_callback(struct notifier_block *nb,
 
 	cpumask_andnot(cpus_to_visit, cpus_to_visit, policy->related_cpus);
 
-	for_each_cpu(cpu, policy->related_cpus)
+	for_each_cpu(cpu, policy->related_cpus) {
 		per_cpu(capacity_freq_ref, cpu) = policy->cpuinfo.max_freq;
+		freq_inv_set_max_ratio(cpu,
+				       per_cpu(capacity_freq_ref, cpu) * HZ_PER_KHZ);
+	}
 
 	if (cpumask_empty(cpus_to_visit)) {
 		topology_normalize_cpu_scale();
diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h
index 32c24ff4f2a8..a63d61ca55af 100644
--- a/include/linux/arch_topology.h
+++ b/include/linux/arch_topology.h
@@ -99,6 +99,7 @@ void update_siblings_masks(unsigned int cpu);
 void remove_cpu_topology(unsigned int cpuid);
 void reset_cpu_topology(void);
 int parse_acpi_topology(void);
+void freq_inv_set_max_ratio(int cpu, u64 max_rate);
 #endif
 
 #endif /* _LINUX_ARCH_TOPOLOGY_H_ */
-- 
cgit v1.2.3


From 11137d384996bb05cf33c8163db271e1bac3f4bf Mon Sep 17 00:00:00 2001
From: Vincent Guittot <vincent.guittot@linaro.org>
Date: Fri, 1 Dec 2023 17:16:52 +0100
Subject: sched/fair: Simplify util_est

With UTIL_EST_FASTUP now being permanent, we can take advantage of the
fact that the ewma jumps directly to a higher utilization at dequeue to
simplify util_est and remove the enqueued field.

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Lukasz Luba <lukasz.luba@arm.com>
Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Reviewed-by: Hongyan Xia <hongyan.xia2@arm.com>
Reviewed-by: Alex Shi <alexs@kernel.org>
Link: https://lore.kernel.org/r/20231201161652.1241695-3-vincent.guittot@linaro.org
---
 include/linux/sched.h | 49 ++++++++----------------------
 kernel/sched/debug.c  |  7 ++---
 kernel/sched/fair.c   | 82 +++++++++++++++++++--------------------------------
 kernel/sched/pelt.h   |  4 +--
 4 files changed, 48 insertions(+), 94 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8d258162deb0..03bfe9ab2951 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -415,42 +415,6 @@ struct load_weight {
 	u32				inv_weight;
 };
 
-/**
- * struct util_est - Estimation utilization of FAIR tasks
- * @enqueued: instantaneous estimated utilization of a task/cpu
- * @ewma:     the Exponential Weighted Moving Average (EWMA)
- *            utilization of a task
- *
- * Support data structure to track an Exponential Weighted Moving Average
- * (EWMA) of a FAIR task's utilization. New samples are added to the moving
- * average each time a task completes an activation. Sample's weight is chosen
- * so that the EWMA will be relatively insensitive to transient changes to the
- * task's workload.
- *
- * The enqueued attribute has a slightly different meaning for tasks and cpus:
- * - task:   the task's util_avg at last task dequeue time
- * - cfs_rq: the sum of util_est.enqueued for each RUNNABLE task on that CPU
- * Thus, the util_est.enqueued of a task represents the contribution on the
- * estimated utilization of the CPU where that task is currently enqueued.
- *
- * Only for tasks we track a moving average of the past instantaneous
- * estimated utilization. This allows to absorb sporadic drops in utilization
- * of an otherwise almost periodic task.
- *
- * The UTIL_AVG_UNCHANGED flag is used to synchronize util_est with util_avg
- * updates. When a task is dequeued, its util_est should not be updated if its
- * util_avg has not been updated in the meantime.
- * This information is mapped into the MSB bit of util_est.enqueued at dequeue
- * time. Since max value of util_est.enqueued for a task is 1024 (PELT util_avg
- * for a task) it is safe to use MSB.
- */
-struct util_est {
-	unsigned int			enqueued;
-	unsigned int			ewma;
-#define UTIL_EST_WEIGHT_SHIFT		2
-#define UTIL_AVG_UNCHANGED		0x80000000
-} __attribute__((__aligned__(sizeof(u64))));
-
 /*
  * The load/runnable/util_avg accumulates an infinite geometric series
  * (see __update_load_avg_cfs_rq() in kernel/sched/pelt.c).
@@ -505,9 +469,20 @@ struct sched_avg {
 	unsigned long			load_avg;
 	unsigned long			runnable_avg;
 	unsigned long			util_avg;
-	struct util_est			util_est;
+	unsigned int			util_est;
 } ____cacheline_aligned;
 
+/*
+ * The UTIL_AVG_UNCHANGED flag is used to synchronize util_est with util_avg
+ * updates. When a task is dequeued, its util_est should not be updated if its
+ * util_avg has not been updated in the meantime.
+ * This information is mapped into the MSB bit of util_est at dequeue time.
+ * Since max value of util_est for a task is 1024 (PELT util_avg for a task)
+ * it is safe to use MSB.
+ */
+#define UTIL_EST_WEIGHT_SHIFT		2
+#define UTIL_AVG_UNCHANGED		0x80000000
+
 struct sched_statistics {
 #ifdef CONFIG_SCHEDSTATS
 	u64				wait_start;
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 168eecc209b4..8d5d98a5834d 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -684,8 +684,8 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 			cfs_rq->avg.runnable_avg);
 	SEQ_printf(m, "  .%-30s: %lu\n", "util_avg",
 			cfs_rq->avg.util_avg);
-	SEQ_printf(m, "  .%-30s: %u\n", "util_est_enqueued",
-			cfs_rq->avg.util_est.enqueued);
+	SEQ_printf(m, "  .%-30s: %u\n", "util_est",
+			cfs_rq->avg.util_est);
 	SEQ_printf(m, "  .%-30s: %ld\n", "removed.load_avg",
 			cfs_rq->removed.load_avg);
 	SEQ_printf(m, "  .%-30s: %ld\n", "removed.util_avg",
@@ -1075,8 +1075,7 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 	P(se.avg.runnable_avg);
 	P(se.avg.util_avg);
 	P(se.avg.last_update_time);
-	P(se.avg.util_est.ewma);
-	PM(se.avg.util_est.enqueued, ~UTIL_AVG_UNCHANGED);
+	PM(se.avg.util_est, ~UTIL_AVG_UNCHANGED);
 #endif
 #ifdef CONFIG_UCLAMP_TASK
 	__PS("uclamp.min", p->uclamp_req[UCLAMP_MIN].value);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e94d65da8d66..823dd76d0546 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4781,9 +4781,7 @@ static inline unsigned long task_runnable(struct task_struct *p)
 
 static inline unsigned long _task_util_est(struct task_struct *p)
 {
-	struct util_est ue = READ_ONCE(p->se.avg.util_est);
-
-	return max(ue.ewma, (ue.enqueued & ~UTIL_AVG_UNCHANGED));
+	return READ_ONCE(p->se.avg.util_est) & ~UTIL_AVG_UNCHANGED;
 }
 
 static inline unsigned long task_util_est(struct task_struct *p)
@@ -4800,9 +4798,9 @@ static inline void util_est_enqueue(struct cfs_rq *cfs_rq,
 		return;
 
 	/* Update root cfs_rq's estimated utilization */
-	enqueued  = cfs_rq->avg.util_est.enqueued;
+	enqueued  = cfs_rq->avg.util_est;
 	enqueued += _task_util_est(p);
-	WRITE_ONCE(cfs_rq->avg.util_est.enqueued, enqueued);
+	WRITE_ONCE(cfs_rq->avg.util_est, enqueued);
 
 	trace_sched_util_est_cfs_tp(cfs_rq);
 }
@@ -4816,34 +4814,20 @@ static inline void util_est_dequeue(struct cfs_rq *cfs_rq,
 		return;
 
 	/* Update root cfs_rq's estimated utilization */
-	enqueued  = cfs_rq->avg.util_est.enqueued;
+	enqueued  = cfs_rq->avg.util_est;
 	enqueued -= min_t(unsigned int, enqueued, _task_util_est(p));
-	WRITE_ONCE(cfs_rq->avg.util_est.enqueued, enqueued);
+	WRITE_ONCE(cfs_rq->avg.util_est, enqueued);
 
 	trace_sched_util_est_cfs_tp(cfs_rq);
 }
 
 #define UTIL_EST_MARGIN (SCHED_CAPACITY_SCALE / 100)
 
-/*
- * Check if a (signed) value is within a specified (unsigned) margin,
- * based on the observation that:
- *
- *     abs(x) < y := (unsigned)(x + y - 1) < (2 * y - 1)
- *
- * NOTE: this only works when value + margin < INT_MAX.
- */
-static inline bool within_margin(int value, int margin)
-{
-	return ((unsigned int)(value + margin - 1) < (2 * margin - 1));
-}
-
 static inline void util_est_update(struct cfs_rq *cfs_rq,
 				   struct task_struct *p,
 				   bool task_sleep)
 {
-	long last_ewma_diff, last_enqueued_diff;
-	struct util_est ue;
+	unsigned int ewma, dequeued, last_ewma_diff;
 
 	if (!sched_feat(UTIL_EST))
 		return;
@@ -4855,23 +4839,25 @@ static inline void util_est_update(struct cfs_rq *cfs_rq,
 	if (!task_sleep)
 		return;
 
+	/* Get current estimate of utilization */
+	ewma = READ_ONCE(p->se.avg.util_est);
+
 	/*
 	 * If the PELT values haven't changed since enqueue time,
 	 * skip the util_est update.
 	 */
-	ue = p->se.avg.util_est;
-	if (ue.enqueued & UTIL_AVG_UNCHANGED)
+	if (ewma & UTIL_AVG_UNCHANGED)
 		return;
 
-	last_enqueued_diff = ue.enqueued;
+	/* Get utilization at dequeue */
+	dequeued = task_util(p);
 
 	/*
 	 * Reset EWMA on utilization increases, the moving average is used only
 	 * to smooth utilization decreases.
 	 */
-	ue.enqueued = task_util(p);
-	if (ue.ewma < ue.enqueued) {
-		ue.ewma = ue.enqueued;
+	if (ewma <= dequeued) {
+		ewma = dequeued;
 		goto done;
 	}
 
@@ -4879,27 +4865,22 @@ static inline void util_est_update(struct cfs_rq *cfs_rq,
 	 * Skip update of task's estimated utilization when its members are
 	 * already ~1% close to its last activation value.
 	 */
-	last_ewma_diff = ue.enqueued - ue.ewma;
-	last_enqueued_diff -= ue.enqueued;
-	if (within_margin(last_ewma_diff, UTIL_EST_MARGIN)) {
-		if (!within_margin(last_enqueued_diff, UTIL_EST_MARGIN))
-			goto done;
-
-		return;
-	}
+	last_ewma_diff = ewma - dequeued;
+	if (last_ewma_diff < UTIL_EST_MARGIN)
+		goto done;
 
 	/*
 	 * To avoid overestimation of actual task utilization, skip updates if
 	 * we cannot grant there is idle time in this CPU.
 	 */
-	if (task_util(p) > arch_scale_cpu_capacity(cpu_of(rq_of(cfs_rq))))
+	if (dequeued > arch_scale_cpu_capacity(cpu_of(rq_of(cfs_rq))))
 		return;
 
 	/*
 	 * To avoid underestimate of task utilization, skip updates of EWMA if
 	 * we cannot grant that thread got all CPU time it wanted.
 	 */
-	if ((ue.enqueued + UTIL_EST_MARGIN) < task_runnable(p))
+	if ((dequeued + UTIL_EST_MARGIN) < task_runnable(p))
 		goto done;
 
 
@@ -4907,25 +4888,24 @@ static inline void util_est_update(struct cfs_rq *cfs_rq,
 	 * Update Task's estimated utilization
 	 *
 	 * When *p completes an activation we can consolidate another sample
-	 * of the task size. This is done by storing the current PELT value
-	 * as ue.enqueued and by using this value to update the Exponential
-	 * Weighted Moving Average (EWMA):
+	 * of the task size. This is done by using this value to update the
+	 * Exponential Weighted Moving Average (EWMA):
 	 *
 	 *  ewma(t) = w *  task_util(p) + (1-w) * ewma(t-1)
 	 *          = w *  task_util(p) +         ewma(t-1)  - w * ewma(t-1)
 	 *          = w * (task_util(p) -         ewma(t-1)) +     ewma(t-1)
-	 *          = w * (      last_ewma_diff            ) +     ewma(t-1)
-	 *          = w * (last_ewma_diff  +  ewma(t-1) / w)
+	 *          = w * (      -last_ewma_diff           ) +     ewma(t-1)
+	 *          = w * (-last_ewma_diff +  ewma(t-1) / w)
 	 *
 	 * Where 'w' is the weight of new samples, which is configured to be
 	 * 0.25, thus making w=1/4 ( >>= UTIL_EST_WEIGHT_SHIFT)
 	 */
-	ue.ewma <<= UTIL_EST_WEIGHT_SHIFT;
-	ue.ewma  += last_ewma_diff;
-	ue.ewma >>= UTIL_EST_WEIGHT_SHIFT;
+	ewma <<= UTIL_EST_WEIGHT_SHIFT;
+	ewma  -= last_ewma_diff;
+	ewma >>= UTIL_EST_WEIGHT_SHIFT;
 done:
-	ue.enqueued |= UTIL_AVG_UNCHANGED;
-	WRITE_ONCE(p->se.avg.util_est, ue);
+	ewma |= UTIL_AVG_UNCHANGED;
+	WRITE_ONCE(p->se.avg.util_est, ewma);
 
 	trace_sched_util_est_se_tp(&p->se);
 }
@@ -7653,16 +7633,16 @@ cpu_util(int cpu, struct task_struct *p, int dst_cpu, int boost)
 	if (sched_feat(UTIL_EST)) {
 		unsigned long util_est;
 
-		util_est = READ_ONCE(cfs_rq->avg.util_est.enqueued);
+		util_est = READ_ONCE(cfs_rq->avg.util_est);
 
 		/*
 		 * During wake-up @p isn't enqueued yet and doesn't contribute
-		 * to any cpu_rq(cpu)->cfs.avg.util_est.enqueued.
+		 * to any cpu_rq(cpu)->cfs.avg.util_est.
 		 * If @dst_cpu == @cpu add it to "simulate" cpu_util after @p
 		 * has been enqueued.
 		 *
 		 * During exec (@dst_cpu = -1) @p is enqueued and does
-		 * contribute to cpu_rq(cpu)->cfs.util_est.enqueued.
+		 * contribute to cpu_rq(cpu)->cfs.util_est.
 		 * Remove it to "simulate" cpu_util without @p's contribution.
 		 *
 		 * Despite the task_on_rq_queued(@p) check there is still a
diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h
index 3a0e0dc28721..9e1083465fbc 100644
--- a/kernel/sched/pelt.h
+++ b/kernel/sched/pelt.h
@@ -52,13 +52,13 @@ static inline void cfs_se_util_change(struct sched_avg *avg)
 		return;
 
 	/* Avoid store if the flag has been already reset */
-	enqueued = avg->util_est.enqueued;
+	enqueued = avg->util_est;
 	if (!(enqueued & UTIL_AVG_UNCHANGED))
 		return;
 
 	/* Reset flag to report util_avg has been updated */
 	enqueued &= ~UTIL_AVG_UNCHANGED;
-	WRITE_ONCE(avg->util_est.enqueued, enqueued);
+	WRITE_ONCE(avg->util_est, enqueued);
 }
 
 static inline u64 rq_clock_pelt(struct rq *rq)
-- 
cgit v1.2.3


From a790c2584c02c5ce60db07ab601d55b7f539db34 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 23 Feb 2023 15:11:42 +0000
Subject: afs: Remove whitespace before most ')' from the trace header

checkpatch objects to whitespace before ')', so remove most of it from the
afs trace header.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-afs@lists.infradead.org
cc: linux-fsdevel@vger.kernel.org
---
 include/trace/events/afs.h | 242 ++++++++++++++++++++++-----------------------
 1 file changed, 121 insertions(+), 121 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index e9d412d19dbb..cfcd6452c156 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -654,12 +654,12 @@ TRACE_EVENT(afs_receive_data,
 	    TP_ARGS(call, iter, want_more, ret),
 
 	    TP_STRUCT__entry(
-		    __field(loff_t,			remain		)
-		    __field(unsigned int,		call		)
-		    __field(enum afs_call_state,	state		)
-		    __field(unsigned short,		unmarshall	)
-		    __field(bool,			want_more	)
-		    __field(int,			ret		)
+		    __field(loff_t,			remain)
+		    __field(unsigned int,		call)
+		    __field(enum afs_call_state,	state)
+		    __field(unsigned short,		unmarshall)
+		    __field(bool,			want_more)
+		    __field(int,			ret)
 			     ),
 
 	    TP_fast_assign(
@@ -686,9 +686,9 @@ TRACE_EVENT(afs_notify_call,
 	    TP_ARGS(rxcall, call),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,		call		)
-		    __field(enum afs_call_state,	state		)
-		    __field(unsigned short,		unmarshall	)
+		    __field(unsigned int,		call)
+		    __field(enum afs_call_state,	state)
+		    __field(unsigned short,		unmarshall)
 			     ),
 
 	    TP_fast_assign(
@@ -708,9 +708,9 @@ TRACE_EVENT(afs_cb_call,
 	    TP_ARGS(call),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,		call		)
-		    __field(u32,			op		)
-		    __field(u16,			service_id	)
+		    __field(unsigned int,		call)
+		    __field(u32,			op)
+		    __field(u16,			service_id)
 			     ),
 
 	    TP_fast_assign(
@@ -733,11 +733,11 @@ TRACE_EVENT(afs_call,
 	    TP_ARGS(call_debug_id, op, ref, outstanding, where),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,		call		)
-		    __field(int,			op		)
-		    __field(int,			ref		)
-		    __field(int,			outstanding	)
-		    __field(const void *,		where		)
+		    __field(unsigned int,		call)
+		    __field(int,			op)
+		    __field(int,			ref)
+		    __field(int,			outstanding)
+		    __field(const void *,		where)
 			     ),
 
 	    TP_fast_assign(
@@ -762,9 +762,9 @@ TRACE_EVENT(afs_make_fs_call,
 	    TP_ARGS(call, fid),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,		call		)
-		    __field(enum afs_fs_operation,	op		)
-		    __field_struct(struct afs_fid,	fid		)
+		    __field(unsigned int,		call)
+		    __field(enum afs_fs_operation,	op)
+		    __field_struct(struct afs_fid,	fid)
 			     ),
 
 	    TP_fast_assign(
@@ -794,10 +794,10 @@ TRACE_EVENT(afs_make_fs_calli,
 	    TP_ARGS(call, fid, i),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,		call		)
-		    __field(unsigned int,		i		)
-		    __field(enum afs_fs_operation,	op		)
-		    __field_struct(struct afs_fid,	fid		)
+		    __field(unsigned int,		call)
+		    __field(unsigned int,		i)
+		    __field(enum afs_fs_operation,	op)
+		    __field_struct(struct afs_fid,	fid)
 			     ),
 
 	    TP_fast_assign(
@@ -829,10 +829,10 @@ TRACE_EVENT(afs_make_fs_call1,
 	    TP_ARGS(call, fid, name),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,		call		)
-		    __field(enum afs_fs_operation,	op		)
-		    __field_struct(struct afs_fid,	fid		)
-		    __array(char,			name, 24	)
+		    __field(unsigned int,		call)
+		    __field(enum afs_fs_operation,	op)
+		    __field_struct(struct afs_fid,	fid)
+		    __array(char,			name, 24)
 			     ),
 
 	    TP_fast_assign(
@@ -866,11 +866,11 @@ TRACE_EVENT(afs_make_fs_call2,
 	    TP_ARGS(call, fid, name, name2),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,		call		)
-		    __field(enum afs_fs_operation,	op		)
-		    __field_struct(struct afs_fid,	fid		)
-		    __array(char,			name, 24	)
-		    __array(char,			name2, 24	)
+		    __field(unsigned int,		call)
+		    __field(enum afs_fs_operation,	op)
+		    __field_struct(struct afs_fid,	fid)
+		    __array(char,			name, 24)
+		    __array(char,			name2, 24)
 			     ),
 
 	    TP_fast_assign(
@@ -907,8 +907,8 @@ TRACE_EVENT(afs_make_vl_call,
 	    TP_ARGS(call),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,		call		)
-		    __field(enum afs_vl_operation,	op		)
+		    __field(unsigned int,		call)
+		    __field(enum afs_vl_operation,	op)
 			     ),
 
 	    TP_fast_assign(
@@ -927,10 +927,10 @@ TRACE_EVENT(afs_call_done,
 	    TP_ARGS(call),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,		call		)
-		    __field(struct rxrpc_call *,	rx_call		)
-		    __field(int,			ret		)
-		    __field(u32,			abort_code	)
+		    __field(unsigned int,		call)
+		    __field(struct rxrpc_call *,	rx_call)
+		    __field(int,			ret)
+		    __field(u32,			abort_code)
 			     ),
 
 	    TP_fast_assign(
@@ -953,10 +953,10 @@ TRACE_EVENT(afs_send_data,
 	    TP_ARGS(call, msg),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,		call		)
-		    __field(unsigned int,		flags		)
-		    __field(loff_t,			offset		)
-		    __field(loff_t,			count		)
+		    __field(unsigned int,		call)
+		    __field(unsigned int,		flags)
+		    __field(loff_t,			offset)
+		    __field(loff_t,			count)
 			     ),
 
 	    TP_fast_assign(
@@ -977,10 +977,10 @@ TRACE_EVENT(afs_sent_data,
 	    TP_ARGS(call, msg, ret),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,		call		)
-		    __field(int,			ret		)
-		    __field(loff_t,			offset		)
-		    __field(loff_t,			count		)
+		    __field(unsigned int,		call)
+		    __field(int,			ret)
+		    __field(loff_t,			offset)
+		    __field(loff_t,			count)
 			     ),
 
 	    TP_fast_assign(
@@ -1001,9 +1001,9 @@ TRACE_EVENT(afs_dir_check_failed,
 	    TP_ARGS(vnode, off, i_size),
 
 	    TP_STRUCT__entry(
-		    __field(struct afs_vnode *,		vnode		)
-		    __field(loff_t,			off		)
-		    __field(loff_t,			i_size		)
+		    __field(struct afs_vnode *,		vnode)
+		    __field(loff_t,			off)
+		    __field(loff_t,			i_size)
 			     ),
 
 	    TP_fast_assign(
@@ -1022,11 +1022,11 @@ TRACE_EVENT(afs_folio_dirty,
 	    TP_ARGS(vnode, where, folio),
 
 	    TP_STRUCT__entry(
-		    __field(struct afs_vnode *,		vnode		)
-		    __field(const char *,		where		)
-		    __field(pgoff_t,			index		)
-		    __field(unsigned long,		from		)
-		    __field(unsigned long,		to		)
+		    __field(struct afs_vnode *,		vnode)
+		    __field(const char *,		where)
+		    __field(pgoff_t,			index)
+		    __field(unsigned long,		from)
+		    __field(unsigned long,		to)
 			     ),
 
 	    TP_fast_assign(
@@ -1056,11 +1056,11 @@ TRACE_EVENT(afs_call_state,
 	    TP_ARGS(call, from, to, ret, remote_abort),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,		call		)
-		    __field(enum afs_call_state,	from		)
-		    __field(enum afs_call_state,	to		)
-		    __field(int,			ret		)
-		    __field(u32,			abort		)
+		    __field(unsigned int,		call)
+		    __field(enum afs_call_state,	from)
+		    __field(enum afs_call_state,	to)
+		    __field(int,			ret)
+		    __field(u32,			abort)
 			     ),
 
 	    TP_fast_assign(
@@ -1084,9 +1084,9 @@ TRACE_EVENT(afs_lookup,
 	    TP_ARGS(dvnode, name, fid),
 
 	    TP_STRUCT__entry(
-		    __field_struct(struct afs_fid,	dfid		)
-		    __field_struct(struct afs_fid,	fid		)
-		    __array(char,			name, 24	)
+		    __field_struct(struct afs_fid,	dfid)
+		    __field_struct(struct afs_fid,	fid)
+		    __array(char,			name, 24)
 			     ),
 
 	    TP_fast_assign(
@@ -1116,15 +1116,15 @@ TRACE_EVENT(afs_edit_dir,
 	    TP_ARGS(dvnode, why, op, block, slot, f_vnode, f_unique, name),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,		vnode		)
-		    __field(unsigned int,		unique		)
-		    __field(enum afs_edit_dir_reason,	why		)
-		    __field(enum afs_edit_dir_op,	op		)
-		    __field(unsigned int,		block		)
-		    __field(unsigned short,		slot		)
-		    __field(unsigned int,		f_vnode		)
-		    __field(unsigned int,		f_unique	)
-		    __array(char,			name, 24	)
+		    __field(unsigned int,		vnode)
+		    __field(unsigned int,		unique)
+		    __field(enum afs_edit_dir_reason,	why)
+		    __field(enum afs_edit_dir_op,	op)
+		    __field(unsigned int,		block)
+		    __field(unsigned short,		slot)
+		    __field(unsigned int,		f_vnode)
+		    __field(unsigned int,		f_unique)
+		    __array(char,			name, 24)
 			     ),
 
 	    TP_fast_assign(
@@ -1157,8 +1157,8 @@ TRACE_EVENT(afs_protocol_error,
 	    TP_ARGS(call, cause),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,		call		)
-		    __field(enum afs_eproto_cause,	cause		)
+		    __field(unsigned int,		call)
+		    __field(enum afs_eproto_cause,	cause)
 			     ),
 
 	    TP_fast_assign(
@@ -1177,9 +1177,9 @@ TRACE_EVENT(afs_io_error,
 	    TP_ARGS(call, error, where),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,	call		)
-		    __field(int,		error		)
-		    __field(enum afs_io_error,	where		)
+		    __field(unsigned int,	call)
+		    __field(int,		error)
+		    __field(enum afs_io_error,	where)
 			     ),
 
 	    TP_fast_assign(
@@ -1199,9 +1199,9 @@ TRACE_EVENT(afs_file_error,
 	    TP_ARGS(vnode, error, where),
 
 	    TP_STRUCT__entry(
-		    __field_struct(struct afs_fid,	fid		)
-		    __field(int,			error		)
-		    __field(enum afs_file_error,	where		)
+		    __field_struct(struct afs_fid,	fid)
+		    __field(int,			error)
+		    __field(enum afs_file_error,	where)
 			     ),
 
 	    TP_fast_assign(
@@ -1222,9 +1222,9 @@ TRACE_EVENT(afs_cm_no_server,
 	    TP_ARGS(call, srx),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,			call	)
-		    __field(unsigned int,			op_id	)
-		    __field_struct(struct sockaddr_rxrpc,	srx	)
+		    __field(unsigned int,			call)
+		    __field(unsigned int,			op_id)
+		    __field_struct(struct sockaddr_rxrpc,	srx)
 			     ),
 
 	    TP_fast_assign(
@@ -1243,9 +1243,9 @@ TRACE_EVENT(afs_cm_no_server_u,
 	    TP_ARGS(call, uuid),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,			call	)
-		    __field(unsigned int,			op_id	)
-		    __field_struct(uuid_t,			uuid	)
+		    __field(unsigned int,			call)
+		    __field(unsigned int,			op_id)
+		    __field_struct(uuid_t,			uuid)
 			     ),
 
 	    TP_fast_assign(
@@ -1265,11 +1265,11 @@ TRACE_EVENT(afs_flock_ev,
 	    TP_ARGS(vnode, fl, event, error),
 
 	    TP_STRUCT__entry(
-		    __field_struct(struct afs_fid,	fid		)
-		    __field(enum afs_flock_event,	event		)
-		    __field(enum afs_lock_state,	state		)
-		    __field(int,			error		)
-		    __field(unsigned int,		debug_id	)
+		    __field_struct(struct afs_fid,	fid)
+		    __field(enum afs_flock_event,	event)
+		    __field(enum afs_lock_state,	state)
+		    __field(int,			error)
+		    __field(unsigned int,		debug_id)
 			     ),
 
 	    TP_fast_assign(
@@ -1295,13 +1295,13 @@ TRACE_EVENT(afs_flock_op,
 	    TP_ARGS(vnode, fl, op),
 
 	    TP_STRUCT__entry(
-		    __field_struct(struct afs_fid,	fid		)
-		    __field(loff_t,			from		)
-		    __field(loff_t,			len		)
-		    __field(enum afs_flock_operation,	op		)
-		    __field(unsigned char,		type		)
-		    __field(unsigned int,		flags		)
-		    __field(unsigned int,		debug_id	)
+		    __field_struct(struct afs_fid,	fid)
+		    __field(loff_t,			from)
+		    __field(loff_t,			len)
+		    __field(enum afs_flock_operation,	op)
+		    __field(unsigned char,		type)
+		    __field(unsigned int,		flags)
+		    __field(unsigned int,		debug_id)
 			     ),
 
 	    TP_fast_assign(
@@ -1328,7 +1328,7 @@ TRACE_EVENT(afs_reload_dir,
 	    TP_ARGS(vnode),
 
 	    TP_STRUCT__entry(
-		    __field_struct(struct afs_fid,	fid		)
+		    __field_struct(struct afs_fid,	fid)
 			     ),
 
 	    TP_fast_assign(
@@ -1345,8 +1345,8 @@ TRACE_EVENT(afs_silly_rename,
 	    TP_ARGS(vnode, done),
 
 	    TP_STRUCT__entry(
-		    __field_struct(struct afs_fid,	fid		)
-		    __field(bool,			done		)
+		    __field_struct(struct afs_fid,	fid)
+		    __field(bool,			done)
 			     ),
 
 	    TP_fast_assign(
@@ -1365,9 +1365,9 @@ TRACE_EVENT(afs_get_tree,
 	    TP_ARGS(cell, volume),
 
 	    TP_STRUCT__entry(
-		    __field(u64,			vid		)
-		    __array(char,			cell, 24	)
-		    __array(char,			volume, 24	)
+		    __field(u64,			vid)
+		    __array(char,			cell, 24)
+		    __array(char,			volume, 24)
 			     ),
 
 	    TP_fast_assign(
@@ -1392,10 +1392,10 @@ TRACE_EVENT(afs_cb_break,
 	    TP_ARGS(fid, cb_break, reason, skipped),
 
 	    TP_STRUCT__entry(
-		    __field_struct(struct afs_fid,	fid		)
-		    __field(unsigned int,		cb_break	)
-		    __field(enum afs_cb_break_reason,	reason		)
-		    __field(bool,			skipped		)
+		    __field_struct(struct afs_fid,	fid)
+		    __field(unsigned int,		cb_break)
+		    __field(enum afs_cb_break_reason,	reason)
+		    __field(bool,			skipped)
 			     ),
 
 	    TP_fast_assign(
@@ -1418,8 +1418,8 @@ TRACE_EVENT(afs_cb_miss,
 	    TP_ARGS(fid, reason),
 
 	    TP_STRUCT__entry(
-		    __field_struct(struct afs_fid,	fid		)
-		    __field(enum afs_cb_break_reason,	reason		)
+		    __field_struct(struct afs_fid,	fid)
+		    __field(enum afs_cb_break_reason,	reason)
 			     ),
 
 	    TP_fast_assign(
@@ -1439,10 +1439,10 @@ TRACE_EVENT(afs_server,
 	    TP_ARGS(server_debug_id, ref, active, reason),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,		server		)
-		    __field(int,			ref		)
-		    __field(int,			active		)
-		    __field(int,			reason		)
+		    __field(unsigned int,		server)
+		    __field(int,			ref)
+		    __field(int,			active)
+		    __field(int,			reason)
 			     ),
 
 	    TP_fast_assign(
@@ -1465,9 +1465,9 @@ TRACE_EVENT(afs_volume,
 	    TP_ARGS(vid, ref, reason),
 
 	    TP_STRUCT__entry(
-		    __field(afs_volid_t,		vid		)
-		    __field(int,			ref		)
-		    __field(enum afs_volume_trace,	reason		)
+		    __field(afs_volid_t,		vid)
+		    __field(int,			ref)
+		    __field(enum afs_volume_trace,	reason)
 			     ),
 
 	    TP_fast_assign(
@@ -1489,10 +1489,10 @@ TRACE_EVENT(afs_cell,
 	    TP_ARGS(cell_debug_id, ref, active, reason),
 
 	    TP_STRUCT__entry(
-		    __field(unsigned int,		cell		)
-		    __field(int,			ref		)
-		    __field(int,			active		)
-		    __field(int,			reason		)
+		    __field(unsigned int,		cell)
+		    __field(int,			ref)
+		    __field(int,			active)
+		    __field(int,			reason)
 			     ),
 
 	    TP_fast_assign(
-- 
cgit v1.2.3


From 2daa6404fd2f00985d5bfeb3c161f4630b46b6bf Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 23 Feb 2023 15:24:24 +0000
Subject: afs: Automatically generate trace tag enums

Automatically generate trace tag enums from the symbol -> string mapping
tables rather than having the enums as well, thereby reducing duplicated
data.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-afs@lists.infradead.org
cc: linux-fsdevel@vger.kernel.org
---
 include/trace/events/afs.h | 233 ++++++---------------------------------------
 1 file changed, 27 insertions(+), 206 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index cfcd6452c156..597677acc6b1 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -18,97 +18,6 @@
 #ifndef __AFS_DECLARE_TRACE_ENUMS_ONCE_ONLY
 #define __AFS_DECLARE_TRACE_ENUMS_ONCE_ONLY
 
-enum afs_call_trace {
-	afs_call_trace_alloc,
-	afs_call_trace_free,
-	afs_call_trace_get,
-	afs_call_trace_put,
-	afs_call_trace_wake,
-	afs_call_trace_work,
-};
-
-enum afs_server_trace {
-	afs_server_trace_alloc,
-	afs_server_trace_callback,
-	afs_server_trace_destroy,
-	afs_server_trace_free,
-	afs_server_trace_gc,
-	afs_server_trace_get_by_addr,
-	afs_server_trace_get_by_uuid,
-	afs_server_trace_get_caps,
-	afs_server_trace_get_install,
-	afs_server_trace_get_new_cbi,
-	afs_server_trace_get_probe,
-	afs_server_trace_give_up_cb,
-	afs_server_trace_purging,
-	afs_server_trace_put_call,
-	afs_server_trace_put_cbi,
-	afs_server_trace_put_find_rsq,
-	afs_server_trace_put_probe,
-	afs_server_trace_put_slist,
-	afs_server_trace_put_slist_isort,
-	afs_server_trace_put_uuid_rsq,
-	afs_server_trace_update,
-};
-
-
-enum afs_volume_trace {
-	afs_volume_trace_alloc,
-	afs_volume_trace_free,
-	afs_volume_trace_get_alloc_sbi,
-	afs_volume_trace_get_cell_insert,
-	afs_volume_trace_get_new_op,
-	afs_volume_trace_get_query_alias,
-	afs_volume_trace_put_cell_dup,
-	afs_volume_trace_put_cell_root,
-	afs_volume_trace_put_destroy_sbi,
-	afs_volume_trace_put_free_fc,
-	afs_volume_trace_put_put_op,
-	afs_volume_trace_put_query_alias,
-	afs_volume_trace_put_validate_fc,
-	afs_volume_trace_remove,
-};
-
-enum afs_cell_trace {
-	afs_cell_trace_alloc,
-	afs_cell_trace_free,
-	afs_cell_trace_get_queue_dns,
-	afs_cell_trace_get_queue_manage,
-	afs_cell_trace_get_queue_new,
-	afs_cell_trace_get_vol,
-	afs_cell_trace_insert,
-	afs_cell_trace_manage,
-	afs_cell_trace_put_candidate,
-	afs_cell_trace_put_destroy,
-	afs_cell_trace_put_queue_fail,
-	afs_cell_trace_put_queue_work,
-	afs_cell_trace_put_vol,
-	afs_cell_trace_see_source,
-	afs_cell_trace_see_ws,
-	afs_cell_trace_unuse_alias,
-	afs_cell_trace_unuse_check_alias,
-	afs_cell_trace_unuse_delete,
-	afs_cell_trace_unuse_fc,
-	afs_cell_trace_unuse_lookup,
-	afs_cell_trace_unuse_mntpt,
-	afs_cell_trace_unuse_no_pin,
-	afs_cell_trace_unuse_parse,
-	afs_cell_trace_unuse_pin,
-	afs_cell_trace_unuse_probe,
-	afs_cell_trace_unuse_sbi,
-	afs_cell_trace_unuse_ws,
-	afs_cell_trace_use_alias,
-	afs_cell_trace_use_check_alias,
-	afs_cell_trace_use_fc,
-	afs_cell_trace_use_fc_alias,
-	afs_cell_trace_use_lookup,
-	afs_cell_trace_use_mntpt,
-	afs_cell_trace_use_pin,
-	afs_cell_trace_use_probe,
-	afs_cell_trace_use_sbi,
-	afs_cell_trace_wait,
-};
-
 enum afs_fs_operation {
 	afs_FS_FetchData		= 130,	/* AFS Fetch file data */
 	afs_FS_FetchACL			= 131,	/* AFS Fetch file ACL */
@@ -202,121 +111,6 @@ enum yfs_cm_operation {
 	yfs_CB_CallBack			= 64204,
 };
 
-enum afs_edit_dir_op {
-	afs_edit_dir_create,
-	afs_edit_dir_create_error,
-	afs_edit_dir_create_inval,
-	afs_edit_dir_create_nospc,
-	afs_edit_dir_delete,
-	afs_edit_dir_delete_error,
-	afs_edit_dir_delete_inval,
-	afs_edit_dir_delete_noent,
-};
-
-enum afs_edit_dir_reason {
-	afs_edit_dir_for_create,
-	afs_edit_dir_for_link,
-	afs_edit_dir_for_mkdir,
-	afs_edit_dir_for_rename_0,
-	afs_edit_dir_for_rename_1,
-	afs_edit_dir_for_rename_2,
-	afs_edit_dir_for_rmdir,
-	afs_edit_dir_for_silly_0,
-	afs_edit_dir_for_silly_1,
-	afs_edit_dir_for_symlink,
-	afs_edit_dir_for_unlink,
-};
-
-enum afs_eproto_cause {
-	afs_eproto_bad_status,
-	afs_eproto_cb_count,
-	afs_eproto_cb_fid_count,
-	afs_eproto_cellname_len,
-	afs_eproto_file_type,
-	afs_eproto_ibulkst_cb_count,
-	afs_eproto_ibulkst_count,
-	afs_eproto_motd_len,
-	afs_eproto_offline_msg_len,
-	afs_eproto_volname_len,
-	afs_eproto_yvl_fsendpt4_len,
-	afs_eproto_yvl_fsendpt6_len,
-	afs_eproto_yvl_fsendpt_num,
-	afs_eproto_yvl_fsendpt_type,
-	afs_eproto_yvl_vlendpt4_len,
-	afs_eproto_yvl_vlendpt6_len,
-	afs_eproto_yvl_vlendpt_type,
-};
-
-enum afs_io_error {
-	afs_io_error_cm_reply,
-	afs_io_error_extract,
-	afs_io_error_fs_probe_fail,
-	afs_io_error_vl_lookup_fail,
-	afs_io_error_vl_probe_fail,
-};
-
-enum afs_file_error {
-	afs_file_error_dir_bad_magic,
-	afs_file_error_dir_big,
-	afs_file_error_dir_missing_page,
-	afs_file_error_dir_name_too_long,
-	afs_file_error_dir_over_end,
-	afs_file_error_dir_small,
-	afs_file_error_dir_unmarked_ext,
-	afs_file_error_mntpt,
-	afs_file_error_writeback_fail,
-};
-
-enum afs_flock_event {
-	afs_flock_acquired,
-	afs_flock_callback_break,
-	afs_flock_defer_unlock,
-	afs_flock_extend_fail,
-	afs_flock_fail_other,
-	afs_flock_fail_perm,
-	afs_flock_no_lockers,
-	afs_flock_release_fail,
-	afs_flock_silly_delete,
-	afs_flock_timestamp,
-	afs_flock_try_to_lock,
-	afs_flock_vfs_lock,
-	afs_flock_vfs_locking,
-	afs_flock_waited,
-	afs_flock_waiting,
-	afs_flock_work_extending,
-	afs_flock_work_retry,
-	afs_flock_work_unlocking,
-	afs_flock_would_block,
-};
-
-enum afs_flock_operation {
-	afs_flock_op_copy_lock,
-	afs_flock_op_flock,
-	afs_flock_op_grant,
-	afs_flock_op_lock,
-	afs_flock_op_release_lock,
-	afs_flock_op_return_ok,
-	afs_flock_op_return_eagain,
-	afs_flock_op_return_edeadlk,
-	afs_flock_op_return_error,
-	afs_flock_op_set_lock,
-	afs_flock_op_unlock,
-	afs_flock_op_wake,
-};
-
-enum afs_cb_break_reason {
-	afs_cb_break_no_break,
-	afs_cb_break_no_promise,
-	afs_cb_break_for_callback,
-	afs_cb_break_for_deleted,
-	afs_cb_break_for_lapsed,
-	afs_cb_break_for_s_reinit,
-	afs_cb_break_for_unlink,
-	afs_cb_break_for_v_break,
-	afs_cb_break_for_volume_callback,
-	afs_cb_break_for_zap,
-};
-
 #endif /* end __AFS_DECLARE_TRACE_ENUMS_ONCE_ONLY */
 
 /*
@@ -391,6 +185,7 @@ enum afs_cb_break_reason {
 	EM(afs_cell_trace_unuse_fc,		"UNU fc    ") \
 	EM(afs_cell_trace_unuse_lookup,		"UNU lookup") \
 	EM(afs_cell_trace_unuse_mntpt,		"UNU mntpt ") \
+	EM(afs_cell_trace_unuse_no_pin,		"UNU no-pin") \
 	EM(afs_cell_trace_unuse_parse,		"UNU parse ") \
 	EM(afs_cell_trace_unuse_pin,		"UNU pin   ") \
 	EM(afs_cell_trace_unuse_probe,		"UNU probe ") \
@@ -614,6 +409,32 @@ enum afs_cb_break_reason {
 	EM(afs_cb_break_for_volume_callback,	"break-v-cb")		\
 	E_(afs_cb_break_for_zap,		"break-zap")
 
+/*
+ * Generate enums for tracing information.
+ */
+#ifndef __AFS_GENERATE_TRACE_ENUMS_ONCE_ONLY
+#define __AFS_GENERATE_TRACE_ENUMS_ONCE_ONLY
+
+#undef EM
+#undef E_
+#define EM(a, b) a,
+#define E_(a, b) a
+
+enum afs_call_trace		{ afs_call_traces } __mode(byte);
+enum afs_cb_break_reason	{ afs_cb_break_reasons } __mode(byte);
+enum afs_cell_trace		{ afs_cell_traces } __mode(byte);
+enum afs_edit_dir_op		{ afs_edit_dir_ops } __mode(byte);
+enum afs_edit_dir_reason	{ afs_edit_dir_reasons } __mode(byte);
+enum afs_eproto_cause		{ afs_eproto_causes } __mode(byte);
+enum afs_file_error		{ afs_file_errors } __mode(byte);
+enum afs_flock_event		{ afs_flock_events } __mode(byte);
+enum afs_flock_operation	{ afs_flock_operations } __mode(byte);
+enum afs_io_error		{ afs_io_errors } __mode(byte);
+enum afs_server_trace		{ afs_server_traces } __mode(byte);
+enum afs_volume_trace		{ afs_volume_traces } __mode(byte);
+
+#endif /* end __AFS_GENERATE_TRACE_ENUMS_ONCE_ONLY */
+
 /*
  * Export enum symbols via userspace.
  */
-- 
cgit v1.2.3


From 4498a8eccc97de3d65f876b6fdeddb439ef73abc Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 20 Nov 2023 17:09:47 +0000
Subject: netfs, fscache: Remove ->begin_cache_operation

Remove ->begin_cache_operation() in favour of just calling fscache directly.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: Christian Brauner <christian@brauner.io>
cc: linux-fsdevel@vger.kernel.org
cc: linux-cachefs@redhat.com
---
 Documentation/filesystems/netfs_library.rst | 23 ++++----------------
 fs/9p/vfs_addr.c                            | 16 --------------
 fs/afs/file.c                               | 13 ------------
 fs/ceph/addr.c                              |  1 -
 fs/ceph/cache.h                             | 12 -----------
 fs/netfs/buffered_read.c                    | 33 ++++++++++++++++-------------
 fs/nfs/fscache.c                            |  7 ------
 include/linux/fscache.h                     |  3 ---
 include/linux/netfs.h                       |  4 +---
 9 files changed, 23 insertions(+), 89 deletions(-)

(limited to 'include')

diff --git a/Documentation/filesystems/netfs_library.rst b/Documentation/filesystems/netfs_library.rst
index 48b95d04f72d..4cc657d743f7 100644
--- a/Documentation/filesystems/netfs_library.rst
+++ b/Documentation/filesystems/netfs_library.rst
@@ -295,7 +295,6 @@ through which it can issue requests and negotiate::
 	struct netfs_request_ops {
 		void (*init_request)(struct netfs_io_request *rreq, struct file *file);
 		void (*free_request)(struct netfs_io_request *rreq);
-		int (*begin_cache_operation)(struct netfs_io_request *rreq);
 		void (*expand_readahead)(struct netfs_io_request *rreq);
 		bool (*clamp_length)(struct netfs_io_subrequest *subreq);
 		void (*issue_read)(struct netfs_io_subrequest *subreq);
@@ -317,20 +316,6 @@ The operations are as follows:
    [Optional] This is called as the request is being deallocated so that the
    filesystem can clean up any state it has attached there.
 
- * ``begin_cache_operation()``
-
-   [Optional] This is called to ask the network filesystem to call into the
-   cache (if present) to initialise the caching state for this read.  The netfs
-   library module cannot access the cache directly, so the cache should call
-   something like fscache_begin_read_operation() to do this.
-
-   The cache gets to store its state in ->cache_resources and must set a table
-   of operations of its own there (though of a different type).
-
-   This should return 0 on success and an error code otherwise.  If an error is
-   reported, the operation may proceed anyway, just without local caching (only
-   out of memory and interruption errors cause failure here).
-
  * ``expand_readahead()``
 
    [Optional] This is called to allow the filesystem to expand the size of a
@@ -460,14 +445,14 @@ When implementing a local cache to be used by the read helpers, two things are
 required: some way for the network filesystem to initialise the caching for a
 read request and a table of operations for the helpers to call.
 
-The network filesystem's ->begin_cache_operation() method is called to set up a
-cache and this must call into the cache to do the work.  If using fscache, for
-example, the cache would call::
+To begin a cache operation on an fscache object, the following function is
+called::
 
 	int fscache_begin_read_operation(struct netfs_io_request *rreq,
 					 struct fscache_cookie *cookie);
 
-passing in the request pointer and the cookie corresponding to the file.
+passing in the request pointer and the cookie corresponding to the file.  This
+fills in the cache resources mentioned below.
 
 The netfs_io_request object contains a place for the cache to hang its
 state::
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index 8a635999a7d6..39db7c01e30a 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -82,25 +82,9 @@ static void v9fs_free_request(struct netfs_io_request *rreq)
 	p9_fid_put(fid);
 }
 
-/**
- * v9fs_begin_cache_operation - Begin a cache operation for a read
- * @rreq: The read request
- */
-static int v9fs_begin_cache_operation(struct netfs_io_request *rreq)
-{
-#ifdef CONFIG_9P_FSCACHE
-	struct fscache_cookie *cookie = v9fs_inode_cookie(V9FS_I(rreq->inode));
-
-	return fscache_begin_read_operation(&rreq->cache_resources, cookie);
-#else
-	return -ENOBUFS;
-#endif
-}
-
 const struct netfs_request_ops v9fs_req_ops = {
 	.init_request		= v9fs_init_request,
 	.free_request		= v9fs_free_request,
-	.begin_cache_operation	= v9fs_begin_cache_operation,
 	.issue_read		= v9fs_issue_read,
 };
 
diff --git a/fs/afs/file.c b/fs/afs/file.c
index d37dd201752b..8c17e37c2e59 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -366,18 +366,6 @@ static int afs_init_request(struct netfs_io_request *rreq, struct file *file)
 	return 0;
 }
 
-static int afs_begin_cache_operation(struct netfs_io_request *rreq)
-{
-#ifdef CONFIG_AFS_FSCACHE
-	struct afs_vnode *vnode = AFS_FS_I(rreq->inode);
-
-	return fscache_begin_read_operation(&rreq->cache_resources,
-					    afs_vnode_cache(vnode));
-#else
-	return -ENOBUFS;
-#endif
-}
-
 static int afs_check_write_begin(struct file *file, loff_t pos, unsigned len,
 				 struct folio **foliop, void **_fsdata)
 {
@@ -394,7 +382,6 @@ static void afs_free_request(struct netfs_io_request *rreq)
 const struct netfs_request_ops afs_req_ops = {
 	.init_request		= afs_init_request,
 	.free_request		= afs_free_request,
-	.begin_cache_operation	= afs_begin_cache_operation,
 	.check_write_begin	= afs_check_write_begin,
 	.issue_read		= afs_issue_read,
 };
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 85be3bf18cdf..3b8641febeac 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -509,7 +509,6 @@ static void ceph_netfs_free_request(struct netfs_io_request *rreq)
 const struct netfs_request_ops ceph_netfs_ops = {
 	.init_request		= ceph_init_request,
 	.free_request		= ceph_netfs_free_request,
-	.begin_cache_operation	= ceph_begin_cache_operation,
 	.issue_read		= ceph_netfs_issue_read,
 	.expand_readahead	= ceph_netfs_expand_readahead,
 	.clamp_length		= ceph_netfs_clamp_length,
diff --git a/fs/ceph/cache.h b/fs/ceph/cache.h
index dc502daac49a..b804f1094764 100644
--- a/fs/ceph/cache.h
+++ b/fs/ceph/cache.h
@@ -57,13 +57,6 @@ static inline int ceph_fscache_dirty_folio(struct address_space *mapping,
 	return fscache_dirty_folio(mapping, folio, ceph_fscache_cookie(ci));
 }
 
-static inline int ceph_begin_cache_operation(struct netfs_io_request *rreq)
-{
-	struct fscache_cookie *cookie = ceph_fscache_cookie(ceph_inode(rreq->inode));
-
-	return fscache_begin_read_operation(&rreq->cache_resources, cookie);
-}
-
 static inline bool ceph_is_cache_enabled(struct inode *inode)
 {
 	return fscache_cookie_enabled(ceph_fscache_cookie(ceph_inode(inode)));
@@ -135,11 +128,6 @@ static inline bool ceph_is_cache_enabled(struct inode *inode)
 	return false;
 }
 
-static inline int ceph_begin_cache_operation(struct netfs_io_request *rreq)
-{
-	return -ENOBUFS;
-}
-
 static inline void ceph_fscache_note_page_release(struct inode *inode)
 {
 }
diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index 2cd3ccf4c439..d39d0ffe75d2 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -147,6 +147,15 @@ static void netfs_rreq_expand(struct netfs_io_request *rreq,
 	}
 }
 
+/*
+ * Begin an operation, and fetch the stored zero point value from the cookie if
+ * available.
+ */
+static int netfs_begin_cache_read(struct netfs_io_request *rreq, struct netfs_inode *ctx)
+{
+	return fscache_begin_read_operation(&rreq->cache_resources, netfs_i_cookie(ctx));
+}
+
 /**
  * netfs_readahead - Helper to manage a read request
  * @ractl: The description of the readahead request
@@ -180,11 +189,9 @@ void netfs_readahead(struct readahead_control *ractl)
 	if (IS_ERR(rreq))
 		return;
 
-	if (ctx->ops->begin_cache_operation) {
-		ret = ctx->ops->begin_cache_operation(rreq);
-		if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS)
-			goto cleanup_free;
-	}
+	ret = netfs_begin_cache_read(rreq, ctx);
+	if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS)
+		goto cleanup_free;
 
 	netfs_stat(&netfs_n_rh_readahead);
 	trace_netfs_read(rreq, readahead_pos(ractl), readahead_length(ractl),
@@ -238,11 +245,9 @@ int netfs_read_folio(struct file *file, struct folio *folio)
 		goto alloc_error;
 	}
 
-	if (ctx->ops->begin_cache_operation) {
-		ret = ctx->ops->begin_cache_operation(rreq);
-		if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS)
-			goto discard;
-	}
+	ret = netfs_begin_cache_read(rreq, ctx);
+	if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS)
+		goto discard;
 
 	netfs_stat(&netfs_n_rh_readpage);
 	trace_netfs_read(rreq, rreq->start, rreq->len, netfs_read_trace_readpage);
@@ -390,11 +395,9 @@ retry:
 	rreq->no_unlock_folio	= folio_index(folio);
 	__set_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags);
 
-	if (ctx->ops->begin_cache_operation) {
-		ret = ctx->ops->begin_cache_operation(rreq);
-		if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS)
-			goto error_put;
-	}
+	ret = netfs_begin_cache_read(rreq, ctx);
+	if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS)
+		goto error_put;
 
 	netfs_stat(&netfs_n_rh_write_begin);
 	trace_netfs_read(rreq, pos, len, netfs_read_trace_write_begin);
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index b05717fe0d4e..2d1bfee225c3 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -274,12 +274,6 @@ static void nfs_netfs_free_request(struct netfs_io_request *rreq)
 	put_nfs_open_context(rreq->netfs_priv);
 }
 
-static inline int nfs_netfs_begin_cache_operation(struct netfs_io_request *rreq)
-{
-	return fscache_begin_read_operation(&rreq->cache_resources,
-					    netfs_i_cookie(netfs_inode(rreq->inode)));
-}
-
 static struct nfs_netfs_io_data *nfs_netfs_alloc(struct netfs_io_subrequest *sreq)
 {
 	struct nfs_netfs_io_data *netfs;
@@ -387,7 +381,6 @@ void nfs_netfs_read_completion(struct nfs_pgio_header *hdr)
 const struct netfs_request_ops nfs_netfs_ops = {
 	.init_request		= nfs_netfs_init_request,
 	.free_request		= nfs_netfs_free_request,
-	.begin_cache_operation	= nfs_netfs_begin_cache_operation,
 	.issue_read		= nfs_netfs_issue_read,
 	.clamp_length		= nfs_netfs_clamp_length
 };
diff --git a/include/linux/fscache.h b/include/linux/fscache.h
index 8e312c8323a8..9ed6696aee7a 100644
--- a/include/linux/fscache.h
+++ b/include/linux/fscache.h
@@ -437,9 +437,6 @@ const struct netfs_cache_ops *fscache_operation_valid(const struct netfs_cache_r
  * indicates the cache resources to which the operation state should be
  * attached; @cookie indicates the cache object that will be accessed.
  *
- * This is intended to be called from the ->begin_cache_operation() netfs lib
- * operation as implemented by the network filesystem.
- *
  * @cres->inval_counter is set from @cookie->inval_counter for comparison at
  * the end of the operation.  This allows invalidation during the operation to
  * be detected by the caller.
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index b11a84f6c32b..d294ff8f9ae4 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -208,7 +208,6 @@ struct netfs_io_request {
 struct netfs_request_ops {
 	int (*init_request)(struct netfs_io_request *rreq, struct file *file);
 	void (*free_request)(struct netfs_io_request *rreq);
-	int (*begin_cache_operation)(struct netfs_io_request *rreq);
 
 	void (*expand_readahead)(struct netfs_io_request *rreq);
 	bool (*clamp_length)(struct netfs_io_subrequest *subreq);
@@ -229,8 +228,7 @@ enum netfs_read_from_hole {
 };
 
 /*
- * Table of operations for access to a cache.  This is obtained by
- * rreq->ops->begin_cache_operation().
+ * Table of operations for access to a cache.
  */
 struct netfs_cache_ops {
 	/* End an operation */
-- 
cgit v1.2.3


From 7eb5b3e3a0a55f2d166ca949ef47ca6e0c704aab Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 21 Nov 2023 15:43:52 +0000
Subject: netfs, fscache: Move /proc/fs/fscache to /proc/fs/netfs and put in a
 symlink

Rename /proc/fs/fscache to "netfs" and make a symlink from fscache to that.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: Christian Brauner <christian@brauner.io>
cc: linux-fsdevel@vger.kernel.org
cc: linux-cachefs@redhat.com
---
 fs/netfs/fscache_main.c  |  8 ++------
 fs/netfs/fscache_proc.c  | 23 ++++++++---------------
 fs/netfs/fscache_stats.c |  4 +---
 fs/netfs/internal.h      | 12 +++++++++++-
 fs/netfs/main.c          | 33 +++++++++++++++++++++++++++++++++
 fs/netfs/stats.c         | 13 +++++++------
 include/linux/netfs.h    |  1 -
 7 files changed, 62 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/fs/netfs/fscache_main.c b/fs/netfs/fscache_main.c
index 00600a4d9ce5..42e98bb523e3 100644
--- a/fs/netfs/fscache_main.c
+++ b/fs/netfs/fscache_main.c
@@ -62,7 +62,7 @@ unsigned int fscache_hash(unsigned int salt, const void *data, size_t len)
 /*
  * initialise the fs caching module
  */
-static int __init fscache_init(void)
+int __init fscache_init(void)
 {
 	int ret = -ENOMEM;
 
@@ -94,12 +94,10 @@ error_wq:
 	return ret;
 }
 
-fs_initcall(fscache_init);
-
 /*
  * clean up on module removal
  */
-static void __exit fscache_exit(void)
+void __exit fscache_exit(void)
 {
 	_enter("");
 
@@ -108,5 +106,3 @@ static void __exit fscache_exit(void)
 	destroy_workqueue(fscache_wq);
 	pr_notice("FS-Cache unloaded\n");
 }
-
-module_exit(fscache_exit);
diff --git a/fs/netfs/fscache_proc.c b/fs/netfs/fscache_proc.c
index dc3b0e9c8cce..ecd0d1edafaa 100644
--- a/fs/netfs/fscache_proc.c
+++ b/fs/netfs/fscache_proc.c
@@ -12,41 +12,34 @@
 #include "internal.h"
 
 /*
- * initialise the /proc/fs/fscache/ directory
+ * Add files to /proc/fs/netfs/.
  */
 int __init fscache_proc_init(void)
 {
-	if (!proc_mkdir("fs/fscache", NULL))
-		goto error_dir;
+	if (!proc_symlink("fs/fscache", NULL, "../netfs"))
+		goto error_sym;
 
-	if (!proc_create_seq("fs/fscache/caches", S_IFREG | 0444, NULL,
+	if (!proc_create_seq("fs/netfs/caches", S_IFREG | 0444, NULL,
 			     &fscache_caches_seq_ops))
 		goto error;
 
-	if (!proc_create_seq("fs/fscache/volumes", S_IFREG | 0444, NULL,
+	if (!proc_create_seq("fs/netfs/volumes", S_IFREG | 0444, NULL,
 			     &fscache_volumes_seq_ops))
 		goto error;
 
-	if (!proc_create_seq("fs/fscache/cookies", S_IFREG | 0444, NULL,
+	if (!proc_create_seq("fs/netfs/cookies", S_IFREG | 0444, NULL,
 			     &fscache_cookies_seq_ops))
 		goto error;
-
-#ifdef CONFIG_FSCACHE_STATS
-	if (!proc_create_single("fs/fscache/stats", S_IFREG | 0444, NULL,
-				fscache_stats_show))
-		goto error;
-#endif
-
 	return 0;
 
 error:
 	remove_proc_entry("fs/fscache", NULL);
-error_dir:
+error_sym:
 	return -ENOMEM;
 }
 
 /*
- * clean up the /proc/fs/fscache/ directory
+ * Clean up the /proc/fs/fscache symlink.
  */
 void fscache_proc_cleanup(void)
 {
diff --git a/fs/netfs/fscache_stats.c b/fs/netfs/fscache_stats.c
index fc94e5e79f1c..aad812ead398 100644
--- a/fs/netfs/fscache_stats.c
+++ b/fs/netfs/fscache_stats.c
@@ -52,7 +52,7 @@ EXPORT_SYMBOL(fscache_n_culled);
 /*
  * display the general statistics
  */
-int fscache_stats_show(struct seq_file *m, void *v)
+int fscache_stats_show(struct seq_file *m)
 {
 	seq_puts(m, "FS-Cache statistics\n");
 	seq_printf(m, "Cookies: n=%d v=%d vcol=%u voom=%u\n",
@@ -96,7 +96,5 @@ int fscache_stats_show(struct seq_file *m, void *v)
 	seq_printf(m, "IO     : rd=%u wr=%u\n",
 		   atomic_read(&fscache_n_read),
 		   atomic_read(&fscache_n_write));
-
-	netfs_stats_show(m);
 	return 0;
 }
diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index 43769ac606e8..3f6e22229433 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -76,6 +76,7 @@ extern atomic_t netfs_n_rh_write_done;
 extern atomic_t netfs_n_rh_write_failed;
 extern atomic_t netfs_n_rh_write_zskip;
 
+int netfs_stats_show(struct seq_file *m, void *v);
 
 static inline void netfs_stat(atomic_t *stat)
 {
@@ -166,6 +167,13 @@ static inline void fscache_see_cookie(struct fscache_cookie *cookie,
  * fscache-main.c
  */
 extern unsigned int fscache_hash(unsigned int salt, const void *data, size_t len);
+#ifdef CONFIG_FSCACHE
+int __init fscache_init(void);
+void __exit fscache_exit(void);
+#else
+static inline int fscache_init(void) { return 0; }
+static inline void fscache_exit(void) {}
+#endif
 
 /*
  * fscache-proc.c
@@ -216,12 +224,14 @@ static inline void fscache_stat_d(atomic_t *stat)
 
 #define __fscache_stat(stat) (stat)
 
-int fscache_stats_show(struct seq_file *m, void *v);
+int fscache_stats_show(struct seq_file *m);
 #else
 
 #define __fscache_stat(stat) (NULL)
 #define fscache_stat(stat) do {} while (0)
 #define fscache_stat_d(stat) do {} while (0)
+
+static inline int fscache_stats_show(struct seq_file *m) { return 0; }
 #endif
 
 /*
diff --git a/fs/netfs/main.c b/fs/netfs/main.c
index 1ba8091fcf3e..c9af6e0896d3 100644
--- a/fs/netfs/main.c
+++ b/fs/netfs/main.c
@@ -7,6 +7,8 @@
 
 #include <linux/module.h>
 #include <linux/export.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
 #include "internal.h"
 #define CREATE_TRACE_POINTS
 #include <trace/events/netfs.h>
@@ -19,3 +21,34 @@ unsigned netfs_debug;
 module_param_named(debug, netfs_debug, uint, S_IWUSR | S_IRUGO);
 MODULE_PARM_DESC(netfs_debug, "Netfs support debugging mask");
 
+static int __init netfs_init(void)
+{
+	int ret = -ENOMEM;
+
+	if (!proc_mkdir("fs/netfs", NULL))
+		goto error;
+
+#ifdef CONFIG_FSCACHE_STATS
+	if (!proc_create_single("fs/netfs/stats", S_IFREG | 0444, NULL,
+				netfs_stats_show))
+		goto error_proc;
+#endif
+
+	ret = fscache_init();
+	if (ret < 0)
+		goto error_proc;
+	return 0;
+
+error_proc:
+	remove_proc_entry("fs/netfs", NULL);
+error:
+	return ret;
+}
+fs_initcall(netfs_init);
+
+static void __exit netfs_exit(void)
+{
+	fscache_exit();
+	remove_proc_entry("fs/netfs", NULL);
+}
+module_exit(netfs_exit);
diff --git a/fs/netfs/stats.c b/fs/netfs/stats.c
index 5510a7a14a40..6025dc485f7e 100644
--- a/fs/netfs/stats.c
+++ b/fs/netfs/stats.c
@@ -28,31 +28,32 @@ atomic_t netfs_n_rh_write_done;
 atomic_t netfs_n_rh_write_failed;
 atomic_t netfs_n_rh_write_zskip;
 
-void netfs_stats_show(struct seq_file *m)
+int netfs_stats_show(struct seq_file *m, void *v)
 {
-	seq_printf(m, "RdHelp : RA=%u RP=%u WB=%u WBZ=%u rr=%u sr=%u\n",
+	seq_printf(m, "Netfs  : RA=%u RP=%u WB=%u WBZ=%u rr=%u sr=%u\n",
 		   atomic_read(&netfs_n_rh_readahead),
 		   atomic_read(&netfs_n_rh_readpage),
 		   atomic_read(&netfs_n_rh_write_begin),
 		   atomic_read(&netfs_n_rh_write_zskip),
 		   atomic_read(&netfs_n_rh_rreq),
 		   atomic_read(&netfs_n_rh_sreq));
-	seq_printf(m, "RdHelp : ZR=%u sh=%u sk=%u\n",
+	seq_printf(m, "Netfs  : ZR=%u sh=%u sk=%u\n",
 		   atomic_read(&netfs_n_rh_zero),
 		   atomic_read(&netfs_n_rh_short_read),
 		   atomic_read(&netfs_n_rh_write_zskip));
-	seq_printf(m, "RdHelp : DL=%u ds=%u df=%u di=%u\n",
+	seq_printf(m, "Netfs  : DL=%u ds=%u df=%u di=%u\n",
 		   atomic_read(&netfs_n_rh_download),
 		   atomic_read(&netfs_n_rh_download_done),
 		   atomic_read(&netfs_n_rh_download_failed),
 		   atomic_read(&netfs_n_rh_download_instead));
-	seq_printf(m, "RdHelp : RD=%u rs=%u rf=%u\n",
+	seq_printf(m, "Netfs  : RD=%u rs=%u rf=%u\n",
 		   atomic_read(&netfs_n_rh_read),
 		   atomic_read(&netfs_n_rh_read_done),
 		   atomic_read(&netfs_n_rh_read_failed));
-	seq_printf(m, "RdHelp : WR=%u ws=%u wf=%u\n",
+	seq_printf(m, "Netfs  : WR=%u ws=%u wf=%u\n",
 		   atomic_read(&netfs_n_rh_write),
 		   atomic_read(&netfs_n_rh_write_done),
 		   atomic_read(&netfs_n_rh_write_failed));
+	return fscache_stats_show(m);
 }
 EXPORT_SYMBOL(netfs_stats_show);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index d294ff8f9ae4..9bd91cd615d5 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -294,7 +294,6 @@ void netfs_get_subrequest(struct netfs_io_subrequest *subreq,
 			  enum netfs_sreq_ref_trace what);
 void netfs_put_subrequest(struct netfs_io_subrequest *subreq,
 			  bool was_async, enum netfs_sreq_ref_trace what);
-void netfs_stats_show(struct seq_file *);
 ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len,
 				struct iov_iter *new,
 				iov_iter_extraction_t extraction_flags);
-- 
cgit v1.2.3


From c9c4ff12df110feb1b91951010f673f4b16e49e8 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 27 Nov 2023 13:58:07 +0000
Subject: netfs: Move pinning-for-writeback from fscache to netfs

Move the resource pinning-for-writeback from fscache code to netfslib code.
This is used to keep a cache backing object pinned whilst we have dirty
pages on the netfs inode in the pagecache such that VM writeback will be
able to reach it.

Whilst we're at it, switch the parameters of netfs_unpin_writeback() to
match ->write_inode() so that it can be used for that directly.

Note that this mechanism could be more generically useful than that for
network filesystems.  Quite often they have to keep around other resources
(e.g. authentication tokens or network connections) until the writeback is
complete.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/9p/vfs_addr.c          | 33 +++++-------------
 fs/9p/vfs_inode.c         |  3 +-
 fs/9p/vfs_super.c         | 14 ++------
 fs/afs/file.c             |  8 +----
 fs/afs/inode.c            |  2 +-
 fs/afs/internal.h         |  6 ----
 fs/afs/super.c            |  2 +-
 fs/afs/write.c            |  9 -----
 fs/ceph/cache.h           | 23 ++++---------
 fs/ceph/inode.c           |  2 +-
 fs/fs-writeback.c         | 10 +++---
 fs/netfs/Makefile         |  1 +
 fs/netfs/fscache_io.c     | 40 ----------------------
 fs/netfs/misc.c           | 86 +++++++++++++++++++++++++++++++++++++++++++++++
 fs/smb/client/cifsfs.c    |  5 ++-
 fs/smb/client/file.c      | 18 ++--------
 include/linux/fs.h        |  2 +-
 include/linux/fscache.h   | 42 -----------------------
 include/linux/netfs.h     |  3 ++
 include/linux/writeback.h |  2 +-
 20 files changed, 124 insertions(+), 187 deletions(-)
 create mode 100644 fs/netfs/misc.c

(limited to 'include')

diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index 39db7c01e30a..131b83c31f85 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -317,30 +317,15 @@ out:
 	return copied;
 }
 
-#ifdef CONFIG_9P_FSCACHE
-/*
- * Mark a page as having been made dirty and thus needing writeback.  We also
- * need to pin the cache object to write back to.
- */
-static bool v9fs_dirty_folio(struct address_space *mapping, struct folio *folio)
-{
-	struct v9fs_inode *v9inode = V9FS_I(mapping->host);
-
-	return fscache_dirty_folio(mapping, folio, v9fs_inode_cookie(v9inode));
-}
-#else
-#define v9fs_dirty_folio filemap_dirty_folio
-#endif
-
 const struct address_space_operations v9fs_addr_operations = {
-	.read_folio = netfs_read_folio,
-	.readahead = netfs_readahead,
-	.dirty_folio = v9fs_dirty_folio,
-	.writepage = v9fs_vfs_writepage,
-	.write_begin = v9fs_write_begin,
-	.write_end = v9fs_write_end,
-	.release_folio = v9fs_release_folio,
+	.read_folio	= netfs_read_folio,
+	.readahead	= netfs_readahead,
+	.dirty_folio	= netfs_dirty_folio,
+	.writepage	= v9fs_vfs_writepage,
+	.write_begin	= v9fs_write_begin,
+	.write_end	= v9fs_write_end,
+	.release_folio	= v9fs_release_folio,
 	.invalidate_folio = v9fs_invalidate_folio,
-	.launder_folio = v9fs_launder_folio,
-	.direct_IO = v9fs_direct_IO,
+	.launder_folio	= v9fs_launder_folio,
+	.direct_IO	= v9fs_direct_IO,
 };
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index b845ee18a80b..74122540e00f 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -376,8 +376,7 @@ void v9fs_evict_inode(struct inode *inode)
 
 #ifdef CONFIG_9P_FSCACHE
 	version = cpu_to_le32(v9inode->qid.version);
-	fscache_clear_inode_writeback(v9fs_inode_cookie(v9inode), inode,
-				      &version);
+	netfs_clear_inode_writeback(inode, &version);
 #endif
 
 	clear_inode(inode);
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index 73db55c050bf..941f7d0e0bfa 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -289,31 +289,21 @@ static int v9fs_drop_inode(struct inode *inode)
 static int v9fs_write_inode(struct inode *inode,
 			    struct writeback_control *wbc)
 {
-	struct v9fs_inode *v9inode;
-
 	/*
 	 * send an fsync request to server irrespective of
 	 * wbc->sync_mode.
 	 */
 	p9_debug(P9_DEBUG_VFS, "%s: inode %p\n", __func__, inode);
-
-	v9inode = V9FS_I(inode);
-	fscache_unpin_writeback(wbc, v9fs_inode_cookie(v9inode));
-
-	return 0;
+	return netfs_unpin_writeback(inode, wbc);
 }
 
 static int v9fs_write_inode_dotl(struct inode *inode,
 				 struct writeback_control *wbc)
 {
-	struct v9fs_inode *v9inode;
 
-	v9inode = V9FS_I(inode);
 	p9_debug(P9_DEBUG_VFS, "%s: inode %p\n", __func__, inode);
 
-	fscache_unpin_writeback(wbc, v9fs_inode_cookie(v9inode));
-
-	return 0;
+	return netfs_unpin_writeback(inode, wbc);
 }
 
 static const struct super_operations v9fs_super_ops = {
diff --git a/fs/afs/file.c b/fs/afs/file.c
index 8c17e37c2e59..9142fda7dbd6 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -55,7 +55,7 @@ const struct inode_operations afs_file_inode_operations = {
 const struct address_space_operations afs_file_aops = {
 	.read_folio	= netfs_read_folio,
 	.readahead	= netfs_readahead,
-	.dirty_folio	= afs_dirty_folio,
+	.dirty_folio	= netfs_dirty_folio,
 	.launder_folio	= afs_launder_folio,
 	.release_folio	= afs_release_folio,
 	.invalidate_folio = afs_invalidate_folio,
@@ -386,12 +386,6 @@ const struct netfs_request_ops afs_req_ops = {
 	.issue_read		= afs_issue_read,
 };
 
-int afs_write_inode(struct inode *inode, struct writeback_control *wbc)
-{
-	fscache_unpin_writeback(wbc, afs_vnode_cache(AFS_FS_I(inode)));
-	return 0;
-}
-
 /*
  * Adjust the dirty region of the page on truncation or full invalidation,
  * getting rid of the markers altogether if the region is entirely invalidated.
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 78efc9719349..6f375f0cf650 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -823,7 +823,7 @@ void afs_evict_inode(struct inode *inode)
 	truncate_inode_pages_final(&inode->i_data);
 
 	afs_set_cache_aux(vnode, &aux);
-	fscache_clear_inode_writeback(afs_vnode_cache(vnode), inode, &aux);
+	netfs_clear_inode_writeback(inode, &aux);
 	clear_inode(inode);
 
 	while (!list_empty(&vnode->wb_keys)) {
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 7385d62c8cf5..b77797559e27 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -1073,7 +1073,6 @@ extern int afs_release(struct inode *, struct file *);
 extern int afs_fetch_data(struct afs_vnode *, struct afs_read *);
 extern struct afs_read *afs_alloc_read(gfp_t);
 extern void afs_put_read(struct afs_read *);
-extern int afs_write_inode(struct inode *, struct writeback_control *);
 
 static inline struct afs_read *afs_get_read(struct afs_read *req)
 {
@@ -1522,11 +1521,6 @@ extern int afs_check_volume_status(struct afs_volume *, struct afs_operation *);
 /*
  * write.c
  */
-#ifdef CONFIG_AFS_FSCACHE
-bool afs_dirty_folio(struct address_space *, struct folio *);
-#else
-#define afs_dirty_folio filemap_dirty_folio
-#endif
 extern int afs_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len,
 			struct page **pagep, void **fsdata);
diff --git a/fs/afs/super.c b/fs/afs/super.c
index a01a0fb2cdbb..4f1b0492f1c5 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -55,7 +55,7 @@ int afs_net_id;
 static const struct super_operations afs_super_ops = {
 	.statfs		= afs_statfs,
 	.alloc_inode	= afs_alloc_inode,
-	.write_inode	= afs_write_inode,
+	.write_inode	= netfs_unpin_writeback,
 	.drop_inode	= afs_drop_inode,
 	.destroy_inode	= afs_destroy_inode,
 	.free_inode	= afs_free_inode,
diff --git a/fs/afs/write.c b/fs/afs/write.c
index 4a168781936b..e40cf8e7543a 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -23,15 +23,6 @@ static void afs_write_to_cache(struct afs_vnode *vnode, loff_t start, size_t len
 			       loff_t i_size, bool caching);
 
 #ifdef CONFIG_AFS_FSCACHE
-/*
- * Mark a page as having been made dirty and thus needing writeback.  We also
- * need to pin the cache object to write back to.
- */
-bool afs_dirty_folio(struct address_space *mapping, struct folio *folio)
-{
-	return fscache_dirty_folio(mapping, folio,
-				afs_vnode_cache(AFS_FS_I(mapping->host)));
-}
 static void afs_folio_start_fscache(bool caching, struct folio *folio)
 {
 	if (caching)
diff --git a/fs/ceph/cache.h b/fs/ceph/cache.h
index b804f1094764..8fc7d828d990 100644
--- a/fs/ceph/cache.h
+++ b/fs/ceph/cache.h
@@ -43,19 +43,13 @@ static inline void ceph_fscache_resize(struct inode *inode, loff_t to)
 	}
 }
 
-static inline void ceph_fscache_unpin_writeback(struct inode *inode,
+static inline int ceph_fscache_unpin_writeback(struct inode *inode,
 						struct writeback_control *wbc)
 {
-	fscache_unpin_writeback(wbc, ceph_fscache_cookie(ceph_inode(inode)));
+	return netfs_unpin_writeback(inode, wbc);
 }
 
-static inline int ceph_fscache_dirty_folio(struct address_space *mapping,
-		struct folio *folio)
-{
-	struct ceph_inode_info *ci = ceph_inode(mapping->host);
-
-	return fscache_dirty_folio(mapping, folio, ceph_fscache_cookie(ci));
-}
+#define ceph_fscache_dirty_folio netfs_dirty_folio
 
 static inline bool ceph_is_cache_enabled(struct inode *inode)
 {
@@ -112,16 +106,13 @@ static inline void ceph_fscache_resize(struct inode *inode, loff_t to)
 {
 }
 
-static inline void ceph_fscache_unpin_writeback(struct inode *inode,
-						struct writeback_control *wbc)
+static inline int ceph_fscache_unpin_writeback(struct inode *inode,
+					       struct writeback_control *wbc)
 {
+	return 0;
 }
 
-static inline int ceph_fscache_dirty_folio(struct address_space *mapping,
-		struct folio *folio)
-{
-	return filemap_dirty_folio(mapping, folio);
-}
+#define ceph_fscache_dirty_folio filemap_dirty_folio
 
 static inline bool ceph_is_cache_enabled(struct inode *inode)
 {
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 0679240f06db..3149d79a9dbe 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -694,7 +694,7 @@ void ceph_evict_inode(struct inode *inode)
 	percpu_counter_dec(&mdsc->metric.total_inodes);
 
 	truncate_inode_pages_final(&inode->i_data);
-	if (inode->i_state & I_PINNING_FSCACHE_WB)
+	if (inode->i_state & I_PINNING_NETFS_WB)
 		ceph_fscache_unuse_cookie(inode, true);
 	clear_inode(inode);
 
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 1767493dffda..3d84fcc471c6 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -1675,11 +1675,11 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 
 	if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
 		inode->i_state |= I_DIRTY_PAGES;
-	else if (unlikely(inode->i_state & I_PINNING_FSCACHE_WB)) {
+	else if (unlikely(inode->i_state & I_PINNING_NETFS_WB)) {
 		if (!(inode->i_state & I_DIRTY_PAGES)) {
-			inode->i_state &= ~I_PINNING_FSCACHE_WB;
-			wbc->unpinned_fscache_wb = true;
-			dirty |= I_PINNING_FSCACHE_WB; /* Cause write_inode */
+			inode->i_state &= ~I_PINNING_NETFS_WB;
+			wbc->unpinned_netfs_wb = true;
+			dirty |= I_PINNING_NETFS_WB; /* Cause write_inode */
 		}
 	}
 
@@ -1691,7 +1691,7 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 		if (ret == 0)
 			ret = err;
 	}
-	wbc->unpinned_fscache_wb = false;
+	wbc->unpinned_netfs_wb = false;
 	trace_writeback_single_inode(inode, wbc, nr_to_write);
 	return ret;
 }
diff --git a/fs/netfs/Makefile b/fs/netfs/Makefile
index b57162ef9cfb..a84fe9bbd3c4 100644
--- a/fs/netfs/Makefile
+++ b/fs/netfs/Makefile
@@ -5,6 +5,7 @@ netfs-y := \
 	io.o \
 	iterator.o \
 	main.o \
+	misc.o \
 	objects.o
 
 netfs-$(CONFIG_NETFS_STATS) += stats.o
diff --git a/fs/netfs/fscache_io.c b/fs/netfs/fscache_io.c
index 0d2b8dec8f82..79171a687930 100644
--- a/fs/netfs/fscache_io.c
+++ b/fs/netfs/fscache_io.c
@@ -158,46 +158,6 @@ int __fscache_begin_write_operation(struct netfs_cache_resources *cres,
 }
 EXPORT_SYMBOL(__fscache_begin_write_operation);
 
-/**
- * fscache_dirty_folio - Mark folio dirty and pin a cache object for writeback
- * @mapping: The mapping the folio belongs to.
- * @folio: The folio being dirtied.
- * @cookie: The cookie referring to the cache object
- *
- * Set the dirty flag on a folio and pin an in-use cache object in memory
- * so that writeback can later write to it.  This is intended
- * to be called from the filesystem's ->dirty_folio() method.
- *
- * Return: true if the dirty flag was set on the folio, false otherwise.
- */
-bool fscache_dirty_folio(struct address_space *mapping, struct folio *folio,
-				struct fscache_cookie *cookie)
-{
-	struct inode *inode = mapping->host;
-	bool need_use = false;
-
-	_enter("");
-
-	if (!filemap_dirty_folio(mapping, folio))
-		return false;
-	if (!fscache_cookie_valid(cookie))
-		return true;
-
-	if (!(inode->i_state & I_PINNING_FSCACHE_WB)) {
-		spin_lock(&inode->i_lock);
-		if (!(inode->i_state & I_PINNING_FSCACHE_WB)) {
-			inode->i_state |= I_PINNING_FSCACHE_WB;
-			need_use = true;
-		}
-		spin_unlock(&inode->i_lock);
-
-		if (need_use)
-			fscache_use_cookie(cookie, true);
-	}
-	return true;
-}
-EXPORT_SYMBOL(fscache_dirty_folio);
-
 struct fscache_write_request {
 	struct netfs_cache_resources cache_resources;
 	struct address_space	*mapping;
diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c
new file mode 100644
index 000000000000..68baf55c47a4
--- /dev/null
+++ b/fs/netfs/misc.c
@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Miscellaneous routines.
+ *
+ * Copyright (C) 2023 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/swap.h>
+#include "internal.h"
+
+/**
+ * netfs_dirty_folio - Mark folio dirty and pin a cache object for writeback
+ * @mapping: The mapping the folio belongs to.
+ * @folio: The folio being dirtied.
+ *
+ * Set the dirty flag on a folio and pin an in-use cache object in memory so
+ * that writeback can later write to it.  This is intended to be called from
+ * the filesystem's ->dirty_folio() method.
+ *
+ * Return: true if the dirty flag was set on the folio, false otherwise.
+ */
+bool netfs_dirty_folio(struct address_space *mapping, struct folio *folio)
+{
+	struct inode *inode = mapping->host;
+	struct netfs_inode *ictx = netfs_inode(inode);
+	struct fscache_cookie *cookie = netfs_i_cookie(ictx);
+	bool need_use = false;
+
+	_enter("");
+
+	if (!filemap_dirty_folio(mapping, folio))
+		return false;
+	if (!fscache_cookie_valid(cookie))
+		return true;
+
+	if (!(inode->i_state & I_PINNING_NETFS_WB)) {
+		spin_lock(&inode->i_lock);
+		if (!(inode->i_state & I_PINNING_NETFS_WB)) {
+			inode->i_state |= I_PINNING_NETFS_WB;
+			need_use = true;
+		}
+		spin_unlock(&inode->i_lock);
+
+		if (need_use)
+			fscache_use_cookie(cookie, true);
+	}
+	return true;
+}
+EXPORT_SYMBOL(netfs_dirty_folio);
+
+/**
+ * netfs_unpin_writeback - Unpin writeback resources
+ * @inode: The inode on which the cookie resides
+ * @wbc: The writeback control
+ *
+ * Unpin the writeback resources pinned by netfs_dirty_folio().  This is
+ * intended to be called as/by the netfs's ->write_inode() method.
+ */
+int netfs_unpin_writeback(struct inode *inode, struct writeback_control *wbc)
+{
+	struct fscache_cookie *cookie = netfs_i_cookie(netfs_inode(inode));
+
+	if (wbc->unpinned_netfs_wb)
+		fscache_unuse_cookie(cookie, NULL, NULL);
+	return 0;
+}
+EXPORT_SYMBOL(netfs_unpin_writeback);
+
+/**
+ * netfs_clear_inode_writeback - Clear writeback resources pinned by an inode
+ * @inode: The inode to clean up
+ * @aux: Auxiliary data to apply to the inode
+ *
+ * Clear any writeback resources held by an inode when the inode is evicted.
+ * This must be called before clear_inode() is called.
+ */
+void netfs_clear_inode_writeback(struct inode *inode, const void *aux)
+{
+	struct fscache_cookie *cookie = netfs_i_cookie(netfs_inode(inode));
+
+	if (inode->i_state & I_PINNING_NETFS_WB) {
+		loff_t i_size = i_size_read(inode);
+		fscache_unuse_cookie(cookie, aux, &i_size);
+	}
+}
+EXPORT_SYMBOL(netfs_clear_inode_writeback);
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index 2131638f26d0..96a65cf9b5ec 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -429,7 +429,7 @@ static void
 cifs_evict_inode(struct inode *inode)
 {
 	truncate_inode_pages_final(&inode->i_data);
-	if (inode->i_state & I_PINNING_FSCACHE_WB)
+	if (inode->i_state & I_PINNING_NETFS_WB)
 		cifs_fscache_unuse_inode_cookie(inode, true);
 	cifs_fscache_release_inode_cookie(inode);
 	clear_inode(inode);
@@ -792,8 +792,7 @@ static int cifs_show_stats(struct seq_file *s, struct dentry *root)
 
 static int cifs_write_inode(struct inode *inode, struct writeback_control *wbc)
 {
-	fscache_unpin_writeback(wbc, cifs_inode_cookie(inode));
-	return 0;
+	return netfs_unpin_writeback(inode, wbc);
 }
 
 static int cifs_drop_inode(struct inode *inode)
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index 32a8525415d9..b02b7f0a47dc 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -5043,27 +5043,13 @@ static void cifs_swap_deactivate(struct file *file)
 	/* do we need to unpin (or unlock) the file */
 }
 
-/*
- * Mark a page as having been made dirty and thus needing writeback.  We also
- * need to pin the cache object to write back to.
- */
-#ifdef CONFIG_CIFS_FSCACHE
-static bool cifs_dirty_folio(struct address_space *mapping, struct folio *folio)
-{
-	return fscache_dirty_folio(mapping, folio,
-					cifs_inode_cookie(mapping->host));
-}
-#else
-#define cifs_dirty_folio filemap_dirty_folio
-#endif
-
 const struct address_space_operations cifs_addr_ops = {
 	.read_folio = cifs_read_folio,
 	.readahead = cifs_readahead,
 	.writepages = cifs_writepages,
 	.write_begin = cifs_write_begin,
 	.write_end = cifs_write_end,
-	.dirty_folio = cifs_dirty_folio,
+	.dirty_folio = netfs_dirty_folio,
 	.release_folio = cifs_release_folio,
 	.direct_IO = cifs_direct_io,
 	.invalidate_folio = cifs_invalidate_folio,
@@ -5087,7 +5073,7 @@ const struct address_space_operations cifs_addr_ops_smallbuf = {
 	.writepages = cifs_writepages,
 	.write_begin = cifs_write_begin,
 	.write_end = cifs_write_end,
-	.dirty_folio = cifs_dirty_folio,
+	.dirty_folio = netfs_dirty_folio,
 	.release_folio = cifs_release_folio,
 	.invalidate_folio = cifs_invalidate_folio,
 	.launder_folio = cifs_launder_folio,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 98b7a7a8c42e..68a957261694 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2294,7 +2294,7 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src,
 #define I_CREATING		(1 << 15)
 #define I_DONTCACHE		(1 << 16)
 #define I_SYNC_QUEUED		(1 << 17)
-#define I_PINNING_FSCACHE_WB	(1 << 18)
+#define I_PINNING_NETFS_WB	(1 << 18)
 
 #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC)
 #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES)
diff --git a/include/linux/fscache.h b/include/linux/fscache.h
index 9ed6696aee7a..6e8562cbcc43 100644
--- a/include/linux/fscache.h
+++ b/include/linux/fscache.h
@@ -626,48 +626,6 @@ static inline void fscache_write_to_cache(struct fscache_cookie *cookie,
 
 }
 
-#if __fscache_available
-bool fscache_dirty_folio(struct address_space *mapping, struct folio *folio,
-		struct fscache_cookie *cookie);
-#else
-#define fscache_dirty_folio(MAPPING, FOLIO, COOKIE) \
-		filemap_dirty_folio(MAPPING, FOLIO)
-#endif
-
-/**
- * fscache_unpin_writeback - Unpin writeback resources
- * @wbc: The writeback control
- * @cookie: The cookie referring to the cache object
- *
- * Unpin the writeback resources pinned by fscache_dirty_folio().  This is
- * intended to be called by the netfs's ->write_inode() method.
- */
-static inline void fscache_unpin_writeback(struct writeback_control *wbc,
-					   struct fscache_cookie *cookie)
-{
-	if (wbc->unpinned_fscache_wb)
-		fscache_unuse_cookie(cookie, NULL, NULL);
-}
-
-/**
- * fscache_clear_inode_writeback - Clear writeback resources pinned by an inode
- * @cookie: The cookie referring to the cache object
- * @inode: The inode to clean up
- * @aux: Auxiliary data to apply to the inode
- *
- * Clear any writeback resources held by an inode when the inode is evicted.
- * This must be called before clear_inode() is called.
- */
-static inline void fscache_clear_inode_writeback(struct fscache_cookie *cookie,
-						 struct inode *inode,
-						 const void *aux)
-{
-	if (inode->i_state & I_PINNING_FSCACHE_WB) {
-		loff_t i_size = i_size_read(inode);
-		fscache_unuse_cookie(cookie, aux, &i_size);
-	}
-}
-
 /**
  * fscache_note_page_release - Note that a netfs page got released
  * @cookie: The cookie corresponding to the file
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 9bd91cd615d5..32faf6c89702 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -288,6 +288,9 @@ int netfs_read_folio(struct file *, struct folio *);
 int netfs_write_begin(struct netfs_inode *, struct file *,
 		struct address_space *, loff_t pos, unsigned int len,
 		struct folio **, void **fsdata);
+bool netfs_dirty_folio(struct address_space *mapping, struct folio *folio);
+int netfs_unpin_writeback(struct inode *inode, struct writeback_control *wbc);
+void netfs_clear_inode_writeback(struct inode *inode, const void *aux);
 
 void netfs_subreq_terminated(struct netfs_io_subrequest *, ssize_t, bool);
 void netfs_get_subrequest(struct netfs_io_subrequest *subreq,
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 083387c00f0c..1e08392fb43e 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -60,7 +60,7 @@ struct writeback_control {
 	unsigned for_reclaim:1;		/* Invoked from the page allocator */
 	unsigned range_cyclic:1;	/* range_start is cyclic */
 	unsigned for_sync:1;		/* sync(2) WB_SYNC_ALL writeback */
-	unsigned unpinned_fscache_wb:1;	/* Cleared I_PINNING_FSCACHE_WB */
+	unsigned unpinned_netfs_wb:1;	/* Cleared I_PINNING_NETFS_WB */
 
 	/*
 	 * When writeback IOs are bounced through async layers, only the
-- 
cgit v1.2.3


From 87b57a048964abfd5f3d8b79bc55687327f5a380 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 4 Mar 2022 10:34:27 +0000
Subject: netfs: Add a procfile to list in-progress requests

Add a procfile, /proc/fs/netfs/requests, to list in-progress netfslib I/O
requests.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/internal.h   | 22 ++++++++++++++++
 fs/netfs/main.c       | 69 ++++++++++++++++++++++++++++++++++++++++++++++++++-
 fs/netfs/objects.c    |  4 ++-
 include/linux/netfs.h |  6 ++++-
 4 files changed, 98 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index 3f6e22229433..4708fb15446b 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -33,6 +33,28 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync);
  * main.c
  */
 extern unsigned int netfs_debug;
+extern struct list_head netfs_io_requests;
+extern spinlock_t netfs_proc_lock;
+
+#ifdef CONFIG_PROC_FS
+static inline void netfs_proc_add_rreq(struct netfs_io_request *rreq)
+{
+	spin_lock(&netfs_proc_lock);
+	list_add_tail_rcu(&rreq->proc_link, &netfs_io_requests);
+	spin_unlock(&netfs_proc_lock);
+}
+static inline void netfs_proc_del_rreq(struct netfs_io_request *rreq)
+{
+	if (!list_empty(&rreq->proc_link)) {
+		spin_lock(&netfs_proc_lock);
+		list_del_rcu(&rreq->proc_link);
+		spin_unlock(&netfs_proc_lock);
+	}
+}
+#else
+static inline void netfs_proc_add_rreq(struct netfs_io_request *rreq) {}
+static inline void netfs_proc_del_rreq(struct netfs_io_request *rreq) {}
+#endif
 
 /*
  * objects.c
diff --git a/fs/netfs/main.c b/fs/netfs/main.c
index c9af6e0896d3..97ce1436615b 100644
--- a/fs/netfs/main.c
+++ b/fs/netfs/main.c
@@ -21,13 +21,80 @@ unsigned netfs_debug;
 module_param_named(debug, netfs_debug, uint, S_IWUSR | S_IRUGO);
 MODULE_PARM_DESC(netfs_debug, "Netfs support debugging mask");
 
+#ifdef CONFIG_PROC_FS
+LIST_HEAD(netfs_io_requests);
+DEFINE_SPINLOCK(netfs_proc_lock);
+
+static const char *netfs_origins[] = {
+	[NETFS_READAHEAD]	= "RA",
+	[NETFS_READPAGE]	= "RP",
+	[NETFS_READ_FOR_WRITE]	= "RW",
+};
+
+/*
+ * Generate a list of I/O requests in /proc/fs/netfs/requests
+ */
+static int netfs_requests_seq_show(struct seq_file *m, void *v)
+{
+	struct netfs_io_request *rreq;
+
+	if (v == &netfs_io_requests) {
+		seq_puts(m,
+			 "REQUEST  OR REF FL ERR  OPS COVERAGE\n"
+			 "======== == === == ==== === =========\n"
+			 );
+		return 0;
+	}
+
+	rreq = list_entry(v, struct netfs_io_request, proc_link);
+	seq_printf(m,
+		   "%08x %s %3d %2lx %4d %3d @%04llx %zx/%zx",
+		   rreq->debug_id,
+		   netfs_origins[rreq->origin],
+		   refcount_read(&rreq->ref),
+		   rreq->flags,
+		   rreq->error,
+		   atomic_read(&rreq->nr_outstanding),
+		   rreq->start, rreq->submitted, rreq->len);
+	seq_putc(m, '\n');
+	return 0;
+}
+
+static void *netfs_requests_seq_start(struct seq_file *m, loff_t *_pos)
+	__acquires(rcu)
+{
+	rcu_read_lock();
+	return seq_list_start_head(&netfs_io_requests, *_pos);
+}
+
+static void *netfs_requests_seq_next(struct seq_file *m, void *v, loff_t *_pos)
+{
+	return seq_list_next(v, &netfs_io_requests, _pos);
+}
+
+static void netfs_requests_seq_stop(struct seq_file *m, void *v)
+	__releases(rcu)
+{
+	rcu_read_unlock();
+}
+
+static const struct seq_operations netfs_requests_seq_ops = {
+	.start  = netfs_requests_seq_start,
+	.next   = netfs_requests_seq_next,
+	.stop   = netfs_requests_seq_stop,
+	.show   = netfs_requests_seq_show,
+};
+#endif /* CONFIG_PROC_FS */
+
 static int __init netfs_init(void)
 {
 	int ret = -ENOMEM;
 
 	if (!proc_mkdir("fs/netfs", NULL))
 		goto error;
-
+	if (!proc_create_seq("fs/netfs/requests", S_IFREG | 0444, NULL,
+			     &netfs_requests_seq_ops))
+		goto error_proc;
 #ifdef CONFIG_FSCACHE_STATS
 	if (!proc_create_single("fs/netfs/stats", S_IFREG | 0444, NULL,
 				netfs_stats_show))
diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c
index e17cdf53f6a7..85f428fc52e6 100644
--- a/fs/netfs/objects.c
+++ b/fs/netfs/objects.c
@@ -45,6 +45,7 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
 		}
 	}
 
+	netfs_proc_add_rreq(rreq);
 	netfs_stat(&netfs_n_rh_rreq);
 	return rreq;
 }
@@ -76,12 +77,13 @@ static void netfs_free_request(struct work_struct *work)
 		container_of(work, struct netfs_io_request, work);
 
 	trace_netfs_rreq(rreq, netfs_rreq_trace_free);
+	netfs_proc_del_rreq(rreq);
 	netfs_clear_subrequests(rreq, false);
 	if (rreq->netfs_ops->free_request)
 		rreq->netfs_ops->free_request(rreq);
 	if (rreq->cache_resources.ops)
 		rreq->cache_resources.ops->end_operation(&rreq->cache_resources);
-	kfree(rreq);
+	kfree_rcu(rreq, rcu);
 	netfs_stat_d(&netfs_n_rh_rreq);
 }
 
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 32faf6c89702..7244ddebd974 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -175,10 +175,14 @@ enum netfs_io_origin {
  * operations to a variety of data stores and then stitch the result together.
  */
 struct netfs_io_request {
-	struct work_struct	work;
+	union {
+		struct work_struct work;
+		struct rcu_head rcu;
+	};
 	struct inode		*inode;		/* The file being accessed */
 	struct address_space	*mapping;	/* The mapping being accessed */
 	struct netfs_cache_resources cache_resources;
+	struct list_head	proc_link;	/* Link in netfs_iorequests */
 	struct list_head	subrequests;	/* Contributory I/O operations */
 	void			*netfs_priv;	/* Private data for the netfs */
 	unsigned int		debug_id;
-- 
cgit v1.2.3


From cc3cb0a18da46a51d9fc173155576ba1d068e536 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 9 Mar 2022 11:01:12 +0000
Subject: netfs: Allow the netfs to make the io (sub)request alloc larger

Allow the network filesystem to specify extra space to be allocated on the
end of the io (sub)request.  This allows cifs, for example, to use this
space rather than allocating its own cifs_readdata struct.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/objects.c    | 7 +++++--
 include/linux/netfs.h | 2 ++
 2 files changed, 7 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c
index 85f428fc52e6..c4229c5f3f54 100644
--- a/fs/netfs/objects.c
+++ b/fs/netfs/objects.c
@@ -22,7 +22,8 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
 	struct netfs_io_request *rreq;
 	int ret;
 
-	rreq = kzalloc(sizeof(struct netfs_io_request), GFP_KERNEL);
+	rreq = kzalloc(ctx->ops->io_request_size ?: sizeof(struct netfs_io_request),
+		       GFP_KERNEL);
 	if (!rreq)
 		return ERR_PTR(-ENOMEM);
 
@@ -114,7 +115,9 @@ struct netfs_io_subrequest *netfs_alloc_subrequest(struct netfs_io_request *rreq
 {
 	struct netfs_io_subrequest *subreq;
 
-	subreq = kzalloc(sizeof(struct netfs_io_subrequest), GFP_KERNEL);
+	subreq = kzalloc(rreq->netfs_ops->io_subrequest_size ?:
+			 sizeof(struct netfs_io_subrequest),
+			 GFP_KERNEL);
 	if (subreq) {
 		INIT_LIST_HEAD(&subreq->rreq_link);
 		refcount_set(&subreq->ref, 2);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 7244ddebd974..d6f27000eeb0 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -210,6 +210,8 @@ struct netfs_io_request {
  * Operations the network filesystem can/must provide to the helpers.
  */
 struct netfs_request_ops {
+	unsigned int	io_request_size;	/* Alloc size for netfs_io_request struct */
+	unsigned int	io_subrequest_size;	/* Alloc size for netfs_io_subrequest struct */
 	int (*init_request)(struct netfs_io_request *rreq, struct file *file);
 	void (*free_request)(struct netfs_io_request *rreq);
 
-- 
cgit v1.2.3


From 5f5ce7ba15e7e6a6539ac8e1f845757aaebecf0d Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 25 Feb 2022 11:19:14 +0000
Subject: netfs: Add a ->free_subrequest() op

Add a ->free_subrequest() op so that the netfs can clean up data attached
to a subrequest.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/objects.c    | 2 ++
 include/linux/netfs.h | 1 +
 2 files changed, 3 insertions(+)

(limited to 'include')

diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c
index c4229c5f3f54..1bd20bdad983 100644
--- a/fs/netfs/objects.c
+++ b/fs/netfs/objects.c
@@ -145,6 +145,8 @@ static void netfs_free_subrequest(struct netfs_io_subrequest *subreq,
 	struct netfs_io_request *rreq = subreq->rreq;
 
 	trace_netfs_sreq(subreq, netfs_sreq_trace_free);
+	if (rreq->netfs_ops->free_subrequest)
+		rreq->netfs_ops->free_subrequest(subreq);
 	kfree(subreq);
 	netfs_stat_d(&netfs_n_rh_sreq);
 	netfs_put_request(rreq, was_async, netfs_rreq_trace_put_subreq);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index d6f27000eeb0..06f57d9d09f6 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -214,6 +214,7 @@ struct netfs_request_ops {
 	unsigned int	io_subrequest_size;	/* Alloc size for netfs_io_subrequest struct */
 	int (*init_request)(struct netfs_io_request *rreq, struct file *file);
 	void (*free_request)(struct netfs_io_request *rreq);
+	void (*free_subrequest)(struct netfs_io_subrequest *rreq);
 
 	void (*expand_readahead)(struct netfs_io_request *rreq);
 	bool (*clamp_length)(struct netfs_io_subrequest *subreq);
-- 
cgit v1.2.3


From a34847d4b73c3a98b565b1d1cc6e1b70c661e18b Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 2 Dec 2022 14:12:41 +0000
Subject: afs: Don't use folio->private to record partial modification

AFS currently uses folio->private to store the range of bytes within a
folio that have been modified - the idea being that if we have, say, a 2MiB
folio and someone writes a single byte, we only have to write back that
single page and not the whole 2MiB folio - thereby saving on network
bandwidth.

Remove this, at least for now, and accept the extra network load (which
doesn't matter in the common case of writing a whole file at a time from
beginning to end).

This makes folio->private available for netfslib to use.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/afs/file.c              |  67 ----------------
 fs/afs/internal.h          |  56 --------------
 fs/afs/write.c             | 188 +++++++++------------------------------------
 include/trace/events/afs.h |  16 +---
 4 files changed, 42 insertions(+), 285 deletions(-)

(limited to 'include')

diff --git a/fs/afs/file.c b/fs/afs/file.c
index 9142fda7dbd6..0d783e5b2147 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -386,63 +386,6 @@ const struct netfs_request_ops afs_req_ops = {
 	.issue_read		= afs_issue_read,
 };
 
-/*
- * Adjust the dirty region of the page on truncation or full invalidation,
- * getting rid of the markers altogether if the region is entirely invalidated.
- */
-static void afs_invalidate_dirty(struct folio *folio, size_t offset,
-				 size_t length)
-{
-	struct afs_vnode *vnode = AFS_FS_I(folio_inode(folio));
-	unsigned long priv;
-	unsigned int f, t, end = offset + length;
-
-	priv = (unsigned long)folio_get_private(folio);
-
-	/* we clean up only if the entire page is being invalidated */
-	if (offset == 0 && length == folio_size(folio))
-		goto full_invalidate;
-
-	 /* If the page was dirtied by page_mkwrite(), the PTE stays writable
-	  * and we don't get another notification to tell us to expand it
-	  * again.
-	  */
-	if (afs_is_folio_dirty_mmapped(priv))
-		return;
-
-	/* We may need to shorten the dirty region */
-	f = afs_folio_dirty_from(folio, priv);
-	t = afs_folio_dirty_to(folio, priv);
-
-	if (t <= offset || f >= end)
-		return; /* Doesn't overlap */
-
-	if (f < offset && t > end)
-		return; /* Splits the dirty region - just absorb it */
-
-	if (f >= offset && t <= end)
-		goto undirty;
-
-	if (f < offset)
-		t = offset;
-	else
-		f = end;
-	if (f == t)
-		goto undirty;
-
-	priv = afs_folio_dirty(folio, f, t);
-	folio_change_private(folio, (void *)priv);
-	trace_afs_folio_dirty(vnode, tracepoint_string("trunc"), folio);
-	return;
-
-undirty:
-	trace_afs_folio_dirty(vnode, tracepoint_string("undirty"), folio);
-	folio_clear_dirty_for_io(folio);
-full_invalidate:
-	trace_afs_folio_dirty(vnode, tracepoint_string("inval"), folio);
-	folio_detach_private(folio);
-}
-
 /*
  * invalidate part or all of a page
  * - release a page and clean up its private data if offset is 0 (indicating
@@ -453,11 +396,6 @@ static void afs_invalidate_folio(struct folio *folio, size_t offset,
 {
 	_enter("{%lu},%zu,%zu", folio->index, offset, length);
 
-	BUG_ON(!folio_test_locked(folio));
-
-	if (folio_get_private(folio))
-		afs_invalidate_dirty(folio, offset, length);
-
 	folio_wait_fscache(folio);
 	_leave("");
 }
@@ -485,11 +423,6 @@ static bool afs_release_folio(struct folio *folio, gfp_t gfp)
 	fscache_note_page_release(afs_vnode_cache(vnode));
 #endif
 
-	if (folio_test_private(folio)) {
-		trace_afs_folio_dirty(vnode, tracepoint_string("rel"), folio);
-		folio_detach_private(folio);
-	}
-
 	/* Indicate that the folio can be released */
 	_leave(" = T");
 	return true;
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index b77797559e27..a7c8d1d702ee 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -894,62 +894,6 @@ static inline void afs_invalidate_cache(struct afs_vnode *vnode, unsigned int fl
 			   i_size_read(&vnode->netfs.inode), flags);
 }
 
-/*
- * We use folio->private to hold the amount of the folio that we've written to,
- * splitting the field into two parts.  However, we need to represent a range
- * 0...FOLIO_SIZE, so we reduce the resolution if the size of the folio
- * exceeds what we can encode.
- */
-#ifdef CONFIG_64BIT
-#define __AFS_FOLIO_PRIV_MASK		0x7fffffffUL
-#define __AFS_FOLIO_PRIV_SHIFT		32
-#define __AFS_FOLIO_PRIV_MMAPPED	0x80000000UL
-#else
-#define __AFS_FOLIO_PRIV_MASK		0x7fffUL
-#define __AFS_FOLIO_PRIV_SHIFT		16
-#define __AFS_FOLIO_PRIV_MMAPPED	0x8000UL
-#endif
-
-static inline unsigned int afs_folio_dirty_resolution(struct folio *folio)
-{
-	int shift = folio_shift(folio) - (__AFS_FOLIO_PRIV_SHIFT - 1);
-	return (shift > 0) ? shift : 0;
-}
-
-static inline size_t afs_folio_dirty_from(struct folio *folio, unsigned long priv)
-{
-	unsigned long x = priv & __AFS_FOLIO_PRIV_MASK;
-
-	/* The lower bound is inclusive */
-	return x << afs_folio_dirty_resolution(folio);
-}
-
-static inline size_t afs_folio_dirty_to(struct folio *folio, unsigned long priv)
-{
-	unsigned long x = (priv >> __AFS_FOLIO_PRIV_SHIFT) & __AFS_FOLIO_PRIV_MASK;
-
-	/* The upper bound is immediately beyond the region */
-	return (x + 1) << afs_folio_dirty_resolution(folio);
-}
-
-static inline unsigned long afs_folio_dirty(struct folio *folio, size_t from, size_t to)
-{
-	unsigned int res = afs_folio_dirty_resolution(folio);
-	from >>= res;
-	to = (to - 1) >> res;
-	return (to << __AFS_FOLIO_PRIV_SHIFT) | from;
-}
-
-static inline unsigned long afs_folio_dirty_mmapped(unsigned long priv)
-{
-	return priv | __AFS_FOLIO_PRIV_MMAPPED;
-}
-
-static inline bool afs_is_folio_dirty_mmapped(unsigned long priv)
-{
-	return priv & __AFS_FOLIO_PRIV_MMAPPED;
-}
-
 #include <trace/events/afs.h>
 
 /*****************************************************************************/
diff --git a/fs/afs/write.c b/fs/afs/write.c
index e40cf8e7543a..80daf28d8f8b 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -16,7 +16,8 @@
 
 static int afs_writepages_region(struct address_space *mapping,
 				 struct writeback_control *wbc,
-				 loff_t start, loff_t end, loff_t *_next,
+				 unsigned long long start,
+				 unsigned long long end, loff_t *_next,
 				 bool max_one_loop);
 
 static void afs_write_to_cache(struct afs_vnode *vnode, loff_t start, size_t len,
@@ -34,25 +35,6 @@ static void afs_folio_start_fscache(bool caching, struct folio *folio)
 }
 #endif
 
-/*
- * Flush out a conflicting write.  This may extend the write to the surrounding
- * pages if also dirty and contiguous to the conflicting region..
- */
-static int afs_flush_conflicting_write(struct address_space *mapping,
-				       struct folio *folio)
-{
-	struct writeback_control wbc = {
-		.sync_mode	= WB_SYNC_ALL,
-		.nr_to_write	= LONG_MAX,
-		.range_start	= folio_pos(folio),
-		.range_end	= LLONG_MAX,
-	};
-	loff_t next;
-
-	return afs_writepages_region(mapping, &wbc, folio_pos(folio), LLONG_MAX,
-				     &next, true);
-}
-
 /*
  * prepare to perform part of a write to a page
  */
@@ -62,10 +44,6 @@ int afs_write_begin(struct file *file, struct address_space *mapping,
 {
 	struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
 	struct folio *folio;
-	unsigned long priv;
-	unsigned f, from;
-	unsigned t, to;
-	pgoff_t index;
 	int ret;
 
 	_enter("{%llx:%llu},%llx,%x",
@@ -79,49 +57,20 @@ int afs_write_begin(struct file *file, struct address_space *mapping,
 	if (ret < 0)
 		return ret;
 
-	index = folio_index(folio);
-	from = pos - index * PAGE_SIZE;
-	to = from + len;
-
 try_again:
 	/* See if this page is already partially written in a way that we can
 	 * merge the new write with.
 	 */
-	if (folio_test_private(folio)) {
-		priv = (unsigned long)folio_get_private(folio);
-		f = afs_folio_dirty_from(folio, priv);
-		t = afs_folio_dirty_to(folio, priv);
-		ASSERTCMP(f, <=, t);
-
-		if (folio_test_writeback(folio)) {
-			trace_afs_folio_dirty(vnode, tracepoint_string("alrdy"), folio);
-			folio_unlock(folio);
-			goto wait_for_writeback;
-		}
-		/* If the file is being filled locally, allow inter-write
-		 * spaces to be merged into writes.  If it's not, only write
-		 * back what the user gives us.
-		 */
-		if (!test_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags) &&
-		    (to < f || from > t))
-			goto flush_conflicting_write;
+	if (folio_test_writeback(folio)) {
+		trace_afs_folio_dirty(vnode, tracepoint_string("alrdy"), folio);
+		folio_unlock(folio);
+		goto wait_for_writeback;
 	}
 
 	*_page = folio_file_page(folio, pos / PAGE_SIZE);
 	_leave(" = 0");
 	return 0;
 
-	/* The previous write and this write aren't adjacent or overlapping, so
-	 * flush the page out.
-	 */
-flush_conflicting_write:
-	trace_afs_folio_dirty(vnode, tracepoint_string("confl"), folio);
-	folio_unlock(folio);
-
-	ret = afs_flush_conflicting_write(mapping, folio);
-	if (ret < 0)
-		goto error;
-
 wait_for_writeback:
 	ret = folio_wait_writeback_killable(folio);
 	if (ret < 0)
@@ -147,9 +96,6 @@ int afs_write_end(struct file *file, struct address_space *mapping,
 {
 	struct folio *folio = page_folio(subpage);
 	struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
-	unsigned long priv;
-	unsigned int f, from = offset_in_folio(folio, pos);
-	unsigned int t, to = from + copied;
 	loff_t i_size, write_end_pos;
 
 	_enter("{%llx:%llu},{%lx}",
@@ -179,23 +125,6 @@ int afs_write_end(struct file *file, struct address_space *mapping,
 		fscache_update_cookie(afs_vnode_cache(vnode), NULL, &write_end_pos);
 	}
 
-	if (folio_test_private(folio)) {
-		priv = (unsigned long)folio_get_private(folio);
-		f = afs_folio_dirty_from(folio, priv);
-		t = afs_folio_dirty_to(folio, priv);
-		if (from < f)
-			f = from;
-		if (to > t)
-			t = to;
-		priv = afs_folio_dirty(folio, f, t);
-		folio_change_private(folio, (void *)priv);
-		trace_afs_folio_dirty(vnode, tracepoint_string("dirty+"), folio);
-	} else {
-		priv = afs_folio_dirty(folio, from, to);
-		folio_attach_private(folio, (void *)priv);
-		trace_afs_folio_dirty(vnode, tracepoint_string("dirty"), folio);
-	}
-
 	if (folio_mark_dirty(folio))
 		_debug("dirtied %lx", folio_index(folio));
 
@@ -300,7 +229,6 @@ static void afs_pages_written_back(struct afs_vnode *vnode, loff_t start, unsign
 		}
 
 		trace_afs_folio_dirty(vnode, tracepoint_string("clear"), folio);
-		folio_detach_private(folio);
 		folio_end_writeback(folio);
 	}
 
@@ -454,17 +382,12 @@ static void afs_extend_writeback(struct address_space *mapping,
 				 long *_count,
 				 loff_t start,
 				 loff_t max_len,
-				 bool new_content,
 				 bool caching,
-				 unsigned int *_len)
+				 size_t *_len)
 {
 	struct folio_batch fbatch;
 	struct folio *folio;
-	unsigned long priv;
-	unsigned int psize, filler = 0;
-	unsigned int f, t;
-	loff_t len = *_len;
-	pgoff_t index = (start + len) / PAGE_SIZE;
+	pgoff_t index = (start + *_len) / PAGE_SIZE;
 	bool stop = true;
 	unsigned int i;
 
@@ -492,7 +415,7 @@ static void afs_extend_writeback(struct address_space *mapping,
 				continue;
 			}
 
-			/* Has the page moved or been split? */
+			/* Has the folio moved or been split? */
 			if (unlikely(folio != xas_reload(&xas))) {
 				folio_put(folio);
 				break;
@@ -510,24 +433,13 @@ static void afs_extend_writeback(struct address_space *mapping,
 				break;
 			}
 
-			psize = folio_size(folio);
-			priv = (unsigned long)folio_get_private(folio);
-			f = afs_folio_dirty_from(folio, priv);
-			t = afs_folio_dirty_to(folio, priv);
-			if (f != 0 && !new_content) {
-				folio_unlock(folio);
-				folio_put(folio);
-				break;
-			}
-
-			len += filler + t;
-			filler = psize - t;
-			if (len >= max_len || *_count <= 0)
+			index += folio_nr_pages(folio);
+			*_count -= folio_nr_pages(folio);
+			*_len += folio_size(folio);
+			stop = false;
+			if (*_len >= max_len || *_count <= 0)
 				stop = true;
-			else if (t == psize || new_content)
-				stop = false;
 
-			index += folio_nr_pages(folio);
 			if (!folio_batch_add(&fbatch, folio))
 				break;
 			if (stop)
@@ -553,16 +465,12 @@ static void afs_extend_writeback(struct address_space *mapping,
 			if (folio_start_writeback(folio))
 				BUG();
 			afs_folio_start_fscache(caching, folio);
-
-			*_count -= folio_nr_pages(folio);
 			folio_unlock(folio);
 		}
 
 		folio_batch_release(&fbatch);
 		cond_resched();
 	} while (!stop);
-
-	*_len = len;
 }
 
 /*
@@ -572,14 +480,13 @@ static void afs_extend_writeback(struct address_space *mapping,
 static ssize_t afs_write_back_from_locked_folio(struct address_space *mapping,
 						struct writeback_control *wbc,
 						struct folio *folio,
-						loff_t start, loff_t end)
+						unsigned long long start,
+						unsigned long long end)
 {
 	struct afs_vnode *vnode = AFS_FS_I(mapping->host);
 	struct iov_iter iter;
-	unsigned long priv;
-	unsigned int offset, to, len, max_len;
-	loff_t i_size = i_size_read(&vnode->netfs.inode);
-	bool new_content = test_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags);
+	unsigned long long i_size = i_size_read(&vnode->netfs.inode);
+	size_t len, max_len;
 	bool caching = fscache_cookie_enabled(afs_vnode_cache(vnode));
 	long count = wbc->nr_to_write;
 	int ret;
@@ -597,13 +504,9 @@ static ssize_t afs_write_back_from_locked_folio(struct address_space *mapping,
 	 * immediately lockable, is not dirty or is missing, or we reach the
 	 * end of the range.
 	 */
-	priv = (unsigned long)folio_get_private(folio);
-	offset = afs_folio_dirty_from(folio, priv);
-	to = afs_folio_dirty_to(folio, priv);
 	trace_afs_folio_dirty(vnode, tracepoint_string("store"), folio);
 
-	len = to - offset;
-	start += offset;
+	len = folio_size(folio);
 	if (start < i_size) {
 		/* Trim the write to the EOF; the extra data is ignored.  Also
 		 * put an upper limit on the size of a single storedata op.
@@ -612,12 +515,10 @@ static ssize_t afs_write_back_from_locked_folio(struct address_space *mapping,
 		max_len = min_t(unsigned long long, max_len, end - start + 1);
 		max_len = min_t(unsigned long long, max_len, i_size - start);
 
-		if (len < max_len &&
-		    (to == folio_size(folio) || new_content))
+		if (len < max_len)
 			afs_extend_writeback(mapping, vnode, &count,
-					     start, max_len, new_content,
-					     caching, &len);
-		len = min_t(loff_t, len, max_len);
+					     start, max_len, caching, &len);
+		len = min_t(unsigned long long, len, i_size - start);
 	}
 
 	/* We now have a contiguous set of dirty pages, each with writeback
@@ -627,7 +528,7 @@ static ssize_t afs_write_back_from_locked_folio(struct address_space *mapping,
 	folio_unlock(folio);
 
 	if (start < i_size) {
-		_debug("write back %x @%llx [%llx]", len, start, i_size);
+		_debug("write back %zx @%llx [%llx]", len, start, i_size);
 
 		/* Speculatively write to the cache.  We have to fix this up
 		 * later if the store fails.
@@ -637,7 +538,7 @@ static ssize_t afs_write_back_from_locked_folio(struct address_space *mapping,
 		iov_iter_xarray(&iter, ITER_SOURCE, &mapping->i_pages, start, len);
 		ret = afs_store_data(vnode, &iter, start, false);
 	} else {
-		_debug("write discard %x @%llx [%llx]", len, start, i_size);
+		_debug("write discard %zx @%llx [%llx]", len, start, i_size);
 
 		/* The dirty region was entirely beyond the EOF. */
 		fscache_clear_page_bits(mapping, start, len, caching);
@@ -693,7 +594,8 @@ static ssize_t afs_write_back_from_locked_folio(struct address_space *mapping,
  */
 static int afs_writepages_region(struct address_space *mapping,
 				 struct writeback_control *wbc,
-				 loff_t start, loff_t end, loff_t *_next,
+				 unsigned long long start,
+				 unsigned long long end, loff_t *_next,
 				 bool max_one_loop)
 {
 	struct folio *folio;
@@ -905,7 +807,6 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf)
 	struct inode *inode = file_inode(file);
 	struct afs_vnode *vnode = AFS_FS_I(inode);
 	struct afs_file *af = file->private_data;
-	unsigned long priv;
 	vm_fault_t ret = VM_FAULT_RETRY;
 
 	_enter("{{%llx:%llu}},{%lx}", vnode->fid.vid, vnode->fid.vnode, folio_index(folio));
@@ -929,24 +830,15 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf)
 	if (folio_lock_killable(folio) < 0)
 		goto out;
 
-	/* We mustn't change folio->private until writeback is complete as that
-	 * details the portion of the page we need to write back and we might
-	 * need to redirty the page if there's a problem.
-	 */
 	if (folio_wait_writeback_killable(folio) < 0) {
 		folio_unlock(folio);
 		goto out;
 	}
 
-	priv = afs_folio_dirty(folio, 0, folio_size(folio));
-	priv = afs_folio_dirty_mmapped(priv);
-	if (folio_test_private(folio)) {
-		folio_change_private(folio, (void *)priv);
+	if (folio_test_dirty(folio))
 		trace_afs_folio_dirty(vnode, tracepoint_string("mkwrite+"), folio);
-	} else {
-		folio_attach_private(folio, (void *)priv);
+	else
 		trace_afs_folio_dirty(vnode, tracepoint_string("mkwrite"), folio);
-	}
 	file_update_time(file);
 
 	ret = VM_FAULT_LOCKED;
@@ -991,30 +883,26 @@ int afs_launder_folio(struct folio *folio)
 	struct afs_vnode *vnode = AFS_FS_I(folio_inode(folio));
 	struct iov_iter iter;
 	struct bio_vec bv;
-	unsigned long priv;
-	unsigned int f, t;
+	unsigned long long fend, i_size = vnode->netfs.inode.i_size;
+	size_t len;
 	int ret = 0;
 
 	_enter("{%lx}", folio->index);
 
-	priv = (unsigned long)folio_get_private(folio);
-	if (folio_clear_dirty_for_io(folio)) {
-		f = 0;
-		t = folio_size(folio);
-		if (folio_test_private(folio)) {
-			f = afs_folio_dirty_from(folio, priv);
-			t = afs_folio_dirty_to(folio, priv);
-		}
+	if (folio_clear_dirty_for_io(folio) && folio_pos(folio) < i_size) {
+		len = folio_size(folio);
+		fend = folio_pos(folio) + len;
+		if (vnode->netfs.inode.i_size < fend)
+			len = fend - i_size;
 
-		bvec_set_folio(&bv, folio, t - f, f);
-		iov_iter_bvec(&iter, ITER_SOURCE, &bv, 1, bv.bv_len);
+		bvec_set_folio(&bv, folio, len, 0);
+		iov_iter_bvec(&iter, WRITE, &bv, 1, len);
 
 		trace_afs_folio_dirty(vnode, tracepoint_string("launder"), folio);
-		ret = afs_store_data(vnode, &iter, folio_pos(folio) + f, true);
+		ret = afs_store_data(vnode, &iter, folio_pos(folio), true);
 	}
 
 	trace_afs_folio_dirty(vnode, tracepoint_string("laundered"), folio);
-	folio_detach_private(folio);
 	folio_wait_fscache(folio);
 	return ret;
 }
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index 597677acc6b1..08506680350c 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -846,26 +846,18 @@ TRACE_EVENT(afs_folio_dirty,
 		    __field(struct afs_vnode *,		vnode)
 		    __field(const char *,		where)
 		    __field(pgoff_t,			index)
-		    __field(unsigned long,		from)
-		    __field(unsigned long,		to)
+		    __field(size_t,			size)
 			     ),
 
 	    TP_fast_assign(
-		    unsigned long priv = (unsigned long)folio_get_private(folio);
 		    __entry->vnode = vnode;
 		    __entry->where = where;
 		    __entry->index = folio_index(folio);
-		    __entry->from  = afs_folio_dirty_from(folio, priv);
-		    __entry->to    = afs_folio_dirty_to(folio, priv);
-		    __entry->to   |= (afs_is_folio_dirty_mmapped(priv) ?
-				      (1UL << (BITS_PER_LONG - 1)) : 0);
+		    __entry->size = folio_size(folio);
 			   ),
 
-	    TP_printk("vn=%p %lx %s %lx-%lx%s",
-		      __entry->vnode, __entry->index, __entry->where,
-		      __entry->from,
-		      __entry->to & ~(1UL << (BITS_PER_LONG - 1)),
-		      __entry->to & (1UL << (BITS_PER_LONG - 1)) ? " M" : "")
+	    TP_printk("vn=%p ix=%05lx s=%05lx %s",
+		      __entry->vnode, __entry->index, __entry->size, __entry->where)
 	    );
 
 TRACE_EVENT(afs_call_state,
-- 
cgit v1.2.3


From c1ec4d7c2e13471558cfea302b7583856284f94c Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 20 Aug 2021 17:08:30 +0100
Subject: netfs: Provide invalidate_folio and release_folio calls

Provide default invalidate_folio and release_folio calls.  These will need
to interact with invalidation correctly at some point.  They will be needed
if netfslib is to make use of folio->private for its own purposes.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/9p/vfs_addr.c      | 33 ++------------------------------
 fs/afs/file.c         | 53 ++++-----------------------------------------------
 fs/ceph/addr.c        | 24 ++---------------------
 fs/ceph/cache.h       | 10 ----------
 fs/netfs/misc.c       | 42 ++++++++++++++++++++++++++++++++++++++++
 include/linux/netfs.h |  6 ++++--
 6 files changed, 54 insertions(+), 114 deletions(-)

(limited to 'include')

diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index 131b83c31f85..055b672a247d 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -88,35 +88,6 @@ const struct netfs_request_ops v9fs_req_ops = {
 	.issue_read		= v9fs_issue_read,
 };
 
-/**
- * v9fs_release_folio - release the private state associated with a folio
- * @folio: The folio to be released
- * @gfp: The caller's allocation restrictions
- *
- * Returns true if the page can be released, false otherwise.
- */
-
-static bool v9fs_release_folio(struct folio *folio, gfp_t gfp)
-{
-	if (folio_test_private(folio))
-		return false;
-#ifdef CONFIG_9P_FSCACHE
-	if (folio_test_fscache(folio)) {
-		if (current_is_kswapd() || !(gfp & __GFP_FS))
-			return false;
-		folio_wait_fscache(folio);
-	}
-	fscache_note_page_release(v9fs_inode_cookie(V9FS_I(folio_inode(folio))));
-#endif
-	return true;
-}
-
-static void v9fs_invalidate_folio(struct folio *folio, size_t offset,
-				 size_t length)
-{
-	folio_wait_fscache(folio);
-}
-
 #ifdef CONFIG_9P_FSCACHE
 static void v9fs_write_to_cache_done(void *priv, ssize_t transferred_or_error,
 				     bool was_async)
@@ -324,8 +295,8 @@ const struct address_space_operations v9fs_addr_operations = {
 	.writepage	= v9fs_vfs_writepage,
 	.write_begin	= v9fs_write_begin,
 	.write_end	= v9fs_write_end,
-	.release_folio	= v9fs_release_folio,
-	.invalidate_folio = v9fs_invalidate_folio,
+	.release_folio	= netfs_release_folio,
+	.invalidate_folio = netfs_invalidate_folio,
 	.launder_folio	= v9fs_launder_folio,
 	.direct_IO	= v9fs_direct_IO,
 };
diff --git a/fs/afs/file.c b/fs/afs/file.c
index 0d783e5b2147..d152ba451f0e 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -20,9 +20,6 @@
 
 static int afs_file_mmap(struct file *file, struct vm_area_struct *vma);
 static int afs_symlink_read_folio(struct file *file, struct folio *folio);
-static void afs_invalidate_folio(struct folio *folio, size_t offset,
-			       size_t length);
-static bool afs_release_folio(struct folio *folio, gfp_t gfp_flags);
 
 static ssize_t afs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter);
 static ssize_t afs_file_splice_read(struct file *in, loff_t *ppos,
@@ -57,8 +54,8 @@ const struct address_space_operations afs_file_aops = {
 	.readahead	= netfs_readahead,
 	.dirty_folio	= netfs_dirty_folio,
 	.launder_folio	= afs_launder_folio,
-	.release_folio	= afs_release_folio,
-	.invalidate_folio = afs_invalidate_folio,
+	.release_folio	= netfs_release_folio,
+	.invalidate_folio = netfs_invalidate_folio,
 	.write_begin	= afs_write_begin,
 	.write_end	= afs_write_end,
 	.writepages	= afs_writepages,
@@ -67,8 +64,8 @@ const struct address_space_operations afs_file_aops = {
 
 const struct address_space_operations afs_symlink_aops = {
 	.read_folio	= afs_symlink_read_folio,
-	.release_folio	= afs_release_folio,
-	.invalidate_folio = afs_invalidate_folio,
+	.release_folio	= netfs_release_folio,
+	.invalidate_folio = netfs_invalidate_folio,
 	.migrate_folio	= filemap_migrate_folio,
 };
 
@@ -386,48 +383,6 @@ const struct netfs_request_ops afs_req_ops = {
 	.issue_read		= afs_issue_read,
 };
 
-/*
- * invalidate part or all of a page
- * - release a page and clean up its private data if offset is 0 (indicating
- *   the entire page)
- */
-static void afs_invalidate_folio(struct folio *folio, size_t offset,
-			       size_t length)
-{
-	_enter("{%lu},%zu,%zu", folio->index, offset, length);
-
-	folio_wait_fscache(folio);
-	_leave("");
-}
-
-/*
- * release a page and clean up its private state if it's not busy
- * - return true if the page can now be released, false if not
- */
-static bool afs_release_folio(struct folio *folio, gfp_t gfp)
-{
-	struct afs_vnode *vnode = AFS_FS_I(folio_inode(folio));
-
-	_enter("{{%llx:%llu}[%lu],%lx},%x",
-	       vnode->fid.vid, vnode->fid.vnode, folio_index(folio), folio->flags,
-	       gfp);
-
-	/* deny if folio is being written to the cache and the caller hasn't
-	 * elected to wait */
-#ifdef CONFIG_AFS_FSCACHE
-	if (folio_test_fscache(folio)) {
-		if (current_is_kswapd() || !(gfp & __GFP_FS))
-			return false;
-		folio_wait_fscache(folio);
-	}
-	fscache_note_page_release(afs_vnode_cache(vnode));
-#endif
-
-	/* Indicate that the folio can be released */
-	_leave(" = T");
-	return true;
-}
-
 static void afs_add_open_mmap(struct afs_vnode *vnode)
 {
 	if (atomic_inc_return(&vnode->cb_nr_mmap) == 1) {
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 3b8641febeac..8eedc62e7ac4 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -159,27 +159,7 @@ static void ceph_invalidate_folio(struct folio *folio, size_t offset,
 		ceph_put_snap_context(snapc);
 	}
 
-	folio_wait_fscache(folio);
-}
-
-static bool ceph_release_folio(struct folio *folio, gfp_t gfp)
-{
-	struct inode *inode = folio->mapping->host;
-	struct ceph_client *cl = ceph_inode_to_client(inode);
-
-	doutc(cl, "%llx.%llx idx %lu (%sdirty)\n", ceph_vinop(inode),
-	      folio->index, folio_test_dirty(folio) ? "" : "not ");
-
-	if (folio_test_private(folio))
-		return false;
-
-	if (folio_test_fscache(folio)) {
-		if (current_is_kswapd() || !(gfp & __GFP_FS))
-			return false;
-		folio_wait_fscache(folio);
-	}
-	ceph_fscache_note_page_release(inode);
-	return true;
+	netfs_invalidate_folio(folio, offset, length);
 }
 
 static void ceph_netfs_expand_readahead(struct netfs_io_request *rreq)
@@ -1585,7 +1565,7 @@ const struct address_space_operations ceph_aops = {
 	.write_end = ceph_write_end,
 	.dirty_folio = ceph_dirty_folio,
 	.invalidate_folio = ceph_invalidate_folio,
-	.release_folio = ceph_release_folio,
+	.release_folio = netfs_release_folio,
 	.direct_IO = noop_direct_IO,
 };
 
diff --git a/fs/ceph/cache.h b/fs/ceph/cache.h
index 8fc7d828d990..20efac020394 100644
--- a/fs/ceph/cache.h
+++ b/fs/ceph/cache.h
@@ -56,12 +56,6 @@ static inline bool ceph_is_cache_enabled(struct inode *inode)
 	return fscache_cookie_enabled(ceph_fscache_cookie(ceph_inode(inode)));
 }
 
-static inline void ceph_fscache_note_page_release(struct inode *inode)
-{
-	struct ceph_inode_info *ci = ceph_inode(inode);
-
-	fscache_note_page_release(ceph_fscache_cookie(ci));
-}
 #else /* CONFIG_CEPH_FSCACHE */
 static inline int ceph_fscache_register_fs(struct ceph_fs_client* fsc,
 					   struct fs_context *fc)
@@ -118,10 +112,6 @@ static inline bool ceph_is_cache_enabled(struct inode *inode)
 {
 	return false;
 }
-
-static inline void ceph_fscache_note_page_release(struct inode *inode)
-{
-}
 #endif /* CONFIG_CEPH_FSCACHE */
 
 #endif
diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c
index 68baf55c47a4..45bb19ec9a63 100644
--- a/fs/netfs/misc.c
+++ b/fs/netfs/misc.c
@@ -84,3 +84,45 @@ void netfs_clear_inode_writeback(struct inode *inode, const void *aux)
 	}
 }
 EXPORT_SYMBOL(netfs_clear_inode_writeback);
+
+/**
+ * netfs_invalidate_folio - Invalidate or partially invalidate a folio
+ * @folio: Folio proposed for release
+ * @offset: Offset of the invalidated region
+ * @length: Length of the invalidated region
+ *
+ * Invalidate part or all of a folio for a network filesystem.  The folio will
+ * be removed afterwards if the invalidated region covers the entire folio.
+ */
+void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length)
+{
+	_enter("{%lx},%zx,%zx", folio_index(folio), offset, length);
+
+	folio_wait_fscache(folio);
+}
+EXPORT_SYMBOL(netfs_invalidate_folio);
+
+/**
+ * netfs_release_folio - Try to release a folio
+ * @folio: Folio proposed for release
+ * @gfp: Flags qualifying the release
+ *
+ * Request release of a folio and clean up its private state if it's not busy.
+ * Returns true if the folio can now be released, false if not
+ */
+bool netfs_release_folio(struct folio *folio, gfp_t gfp)
+{
+	struct netfs_inode *ctx = netfs_inode(folio_inode(folio));
+
+	if (folio_test_private(folio))
+		return false;
+	if (folio_test_fscache(folio)) {
+		if (current_is_kswapd() || !(gfp & __GFP_FS))
+			return false;
+		folio_wait_fscache(folio);
+	}
+
+	fscache_note_page_release(netfs_i_cookie(ctx));
+	return true;
+}
+EXPORT_SYMBOL(netfs_release_folio);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 06f57d9d09f6..8efbfd3b2820 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -293,11 +293,13 @@ struct readahead_control;
 void netfs_readahead(struct readahead_control *);
 int netfs_read_folio(struct file *, struct folio *);
 int netfs_write_begin(struct netfs_inode *, struct file *,
-		struct address_space *, loff_t pos, unsigned int len,
-		struct folio **, void **fsdata);
+		      struct address_space *, loff_t pos, unsigned int len,
+		      struct folio **, void **fsdata);
 bool netfs_dirty_folio(struct address_space *mapping, struct folio *folio);
 int netfs_unpin_writeback(struct inode *inode, struct writeback_control *wbc);
 void netfs_clear_inode_writeback(struct inode *inode, const void *aux);
+void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length);
+bool netfs_release_folio(struct folio *folio, gfp_t gfp);
 
 void netfs_subreq_terminated(struct netfs_io_subrequest *, ssize_t, bool);
 void netfs_get_subrequest(struct netfs_io_subrequest *subreq,
-- 
cgit v1.2.3


From 46ed60dcd4f2c94d27735743ce55cd8d6b93cc1d Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 11 Oct 2023 15:34:07 +0100
Subject: netfs: Implement unbuffered/DIO vs buffered I/O locking

Borrow NFS's direct-vs-buffered I/O locking into netfslib.  Similar code is
also used in ceph.

Modify it to have the correct checker annotations for i_rwsem lock
acquisition/release and to return -ERESTARTSYS if waits are interrupted.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/Makefile     |   1 +
 fs/netfs/locking.c    | 216 ++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/netfs.h |  10 +++
 3 files changed, 227 insertions(+)
 create mode 100644 fs/netfs/locking.c

(limited to 'include')

diff --git a/fs/netfs/Makefile b/fs/netfs/Makefile
index a84fe9bbd3c4..cf3fc847b8ac 100644
--- a/fs/netfs/Makefile
+++ b/fs/netfs/Makefile
@@ -4,6 +4,7 @@ netfs-y := \
 	buffered_read.o \
 	io.o \
 	iterator.o \
+	locking.o \
 	main.o \
 	misc.o \
 	objects.o
diff --git a/fs/netfs/locking.c b/fs/netfs/locking.c
new file mode 100644
index 000000000000..75dc52a49b3a
--- /dev/null
+++ b/fs/netfs/locking.c
@@ -0,0 +1,216 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * I/O and data path helper functionality.
+ *
+ * Borrowed from NFS Copyright (c) 2016 Trond Myklebust
+ */
+
+#include <linux/kernel.h>
+#include <linux/netfs.h>
+#include "internal.h"
+
+/*
+ * inode_dio_wait_interruptible - wait for outstanding DIO requests to finish
+ * @inode: inode to wait for
+ *
+ * Waits for all pending direct I/O requests to finish so that we can
+ * proceed with a truncate or equivalent operation.
+ *
+ * Must be called under a lock that serializes taking new references
+ * to i_dio_count, usually by inode->i_mutex.
+ */
+static int inode_dio_wait_interruptible(struct inode *inode)
+{
+	if (!atomic_read(&inode->i_dio_count))
+		return 0;
+
+	wait_queue_head_t *wq = bit_waitqueue(&inode->i_state, __I_DIO_WAKEUP);
+	DEFINE_WAIT_BIT(q, &inode->i_state, __I_DIO_WAKEUP);
+
+	for (;;) {
+		prepare_to_wait(wq, &q.wq_entry, TASK_INTERRUPTIBLE);
+		if (!atomic_read(&inode->i_dio_count))
+			break;
+		if (signal_pending(current))
+			break;
+		schedule();
+	}
+	finish_wait(wq, &q.wq_entry);
+
+	return atomic_read(&inode->i_dio_count) ? -ERESTARTSYS : 0;
+}
+
+/* Call with exclusively locked inode->i_rwsem */
+static int netfs_block_o_direct(struct netfs_inode *ictx)
+{
+	if (!test_bit(NETFS_ICTX_ODIRECT, &ictx->flags))
+		return 0;
+	clear_bit(NETFS_ICTX_ODIRECT, &ictx->flags);
+	return inode_dio_wait_interruptible(&ictx->inode);
+}
+
+/**
+ * netfs_start_io_read - declare the file is being used for buffered reads
+ * @inode: file inode
+ *
+ * Declare that a buffered read operation is about to start, and ensure
+ * that we block all direct I/O.
+ * On exit, the function ensures that the NETFS_ICTX_ODIRECT flag is unset,
+ * and holds a shared lock on inode->i_rwsem to ensure that the flag
+ * cannot be changed.
+ * In practice, this means that buffered read operations are allowed to
+ * execute in parallel, thanks to the shared lock, whereas direct I/O
+ * operations need to wait to grab an exclusive lock in order to set
+ * NETFS_ICTX_ODIRECT.
+ * Note that buffered writes and truncates both take a write lock on
+ * inode->i_rwsem, meaning that those are serialised w.r.t. the reads.
+ */
+int netfs_start_io_read(struct inode *inode)
+	__acquires(inode->i_rwsem)
+{
+	struct netfs_inode *ictx = netfs_inode(inode);
+
+	/* Be an optimist! */
+	if (down_read_interruptible(&inode->i_rwsem) < 0)
+		return -ERESTARTSYS;
+	if (test_bit(NETFS_ICTX_ODIRECT, &ictx->flags) == 0)
+		return 0;
+	up_read(&inode->i_rwsem);
+
+	/* Slow path.... */
+	if (down_write_killable(&inode->i_rwsem) < 0)
+		return -ERESTARTSYS;
+	if (netfs_block_o_direct(ictx) < 0) {
+		up_write(&inode->i_rwsem);
+		return -ERESTARTSYS;
+	}
+	downgrade_write(&inode->i_rwsem);
+	return 0;
+}
+EXPORT_SYMBOL(netfs_start_io_read);
+
+/**
+ * netfs_end_io_read - declare that the buffered read operation is done
+ * @inode: file inode
+ *
+ * Declare that a buffered read operation is done, and release the shared
+ * lock on inode->i_rwsem.
+ */
+void netfs_end_io_read(struct inode *inode)
+	__releases(inode->i_rwsem)
+{
+	up_read(&inode->i_rwsem);
+}
+EXPORT_SYMBOL(netfs_end_io_read);
+
+/**
+ * netfs_start_io_write - declare the file is being used for buffered writes
+ * @inode: file inode
+ *
+ * Declare that a buffered read operation is about to start, and ensure
+ * that we block all direct I/O.
+ */
+int netfs_start_io_write(struct inode *inode)
+	__acquires(inode->i_rwsem)
+{
+	struct netfs_inode *ictx = netfs_inode(inode);
+
+	if (down_write_killable(&inode->i_rwsem) < 0)
+		return -ERESTARTSYS;
+	if (netfs_block_o_direct(ictx) < 0) {
+		up_write(&inode->i_rwsem);
+		return -ERESTARTSYS;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(netfs_start_io_write);
+
+/**
+ * netfs_end_io_write - declare that the buffered write operation is done
+ * @inode: file inode
+ *
+ * Declare that a buffered write operation is done, and release the
+ * lock on inode->i_rwsem.
+ */
+void netfs_end_io_write(struct inode *inode)
+	__releases(inode->i_rwsem)
+{
+	up_write(&inode->i_rwsem);
+}
+EXPORT_SYMBOL(netfs_end_io_write);
+
+/* Call with exclusively locked inode->i_rwsem */
+static int netfs_block_buffered(struct inode *inode)
+{
+	struct netfs_inode *ictx = netfs_inode(inode);
+	int ret;
+
+	if (!test_bit(NETFS_ICTX_ODIRECT, &ictx->flags)) {
+		set_bit(NETFS_ICTX_ODIRECT, &ictx->flags);
+		if (inode->i_mapping->nrpages != 0) {
+			unmap_mapping_range(inode->i_mapping, 0, 0, 0);
+			ret = filemap_fdatawait(inode->i_mapping);
+			if (ret < 0) {
+				clear_bit(NETFS_ICTX_ODIRECT, &ictx->flags);
+				return ret;
+			}
+		}
+	}
+	return 0;
+}
+
+/**
+ * netfs_start_io_direct - declare the file is being used for direct i/o
+ * @inode: file inode
+ *
+ * Declare that a direct I/O operation is about to start, and ensure
+ * that we block all buffered I/O.
+ * On exit, the function ensures that the NETFS_ICTX_ODIRECT flag is set,
+ * and holds a shared lock on inode->i_rwsem to ensure that the flag
+ * cannot be changed.
+ * In practice, this means that direct I/O operations are allowed to
+ * execute in parallel, thanks to the shared lock, whereas buffered I/O
+ * operations need to wait to grab an exclusive lock in order to clear
+ * NETFS_ICTX_ODIRECT.
+ * Note that buffered writes and truncates both take a write lock on
+ * inode->i_rwsem, meaning that those are serialised w.r.t. O_DIRECT.
+ */
+int netfs_start_io_direct(struct inode *inode)
+	__acquires(inode->i_rwsem)
+{
+	struct netfs_inode *ictx = netfs_inode(inode);
+	int ret;
+
+	/* Be an optimist! */
+	if (down_read_interruptible(&inode->i_rwsem) < 0)
+		return -ERESTARTSYS;
+	if (test_bit(NETFS_ICTX_ODIRECT, &ictx->flags) != 0)
+		return 0;
+	up_read(&inode->i_rwsem);
+
+	/* Slow path.... */
+	if (down_write_killable(&inode->i_rwsem) < 0)
+		return -ERESTARTSYS;
+	ret = netfs_block_buffered(inode);
+	if (ret < 0) {
+		up_write(&inode->i_rwsem);
+		return ret;
+	}
+	downgrade_write(&inode->i_rwsem);
+	return 0;
+}
+EXPORT_SYMBOL(netfs_start_io_direct);
+
+/**
+ * netfs_end_io_direct - declare that the direct i/o operation is done
+ * @inode: file inode
+ *
+ * Declare that a direct I/O operation is done, and release the shared
+ * lock on inode->i_rwsem.
+ */
+void netfs_end_io_direct(struct inode *inode)
+	__releases(inode->i_rwsem)
+{
+	up_read(&inode->i_rwsem);
+}
+EXPORT_SYMBOL(netfs_end_io_direct);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 8efbfd3b2820..fc6d9756a029 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -129,6 +129,8 @@ struct netfs_inode {
 	struct fscache_cookie	*cache;
 #endif
 	loff_t			remote_i_size;	/* Size of the remote file */
+	unsigned long		flags;
+#define NETFS_ICTX_ODIRECT	0		/* The file has DIO in progress */
 };
 
 /*
@@ -310,6 +312,13 @@ ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len,
 				struct iov_iter *new,
 				iov_iter_extraction_t extraction_flags);
 
+int netfs_start_io_read(struct inode *inode);
+void netfs_end_io_read(struct inode *inode);
+int netfs_start_io_write(struct inode *inode);
+void netfs_end_io_write(struct inode *inode);
+int netfs_start_io_direct(struct inode *inode);
+void netfs_end_io_direct(struct inode *inode);
+
 /**
  * netfs_inode - Get the netfs inode context from the inode
  * @inode: The inode to query
@@ -335,6 +344,7 @@ static inline void netfs_inode_init(struct netfs_inode *ctx,
 {
 	ctx->ops = ops;
 	ctx->remote_i_size = i_size_read(&ctx->inode);
+	ctx->flags = 0;
 #if IS_ENABLED(CONFIG_FSCACHE)
 	ctx->cache = NULL;
 #endif
-- 
cgit v1.2.3


From 92b6cc5d1e7cbe569f00e9c1249ac8214fd5e2d2 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 26 Sep 2023 17:42:26 +0100
Subject: netfs: Add iov_iters to (sub)requests to describe various buffers

Add three iov_iter structs:

 (1) Add an iov_iter (->iter) to the I/O request to describe the
     unencrypted-side buffer.

 (2) Add an iov_iter (->io_iter) to the I/O request to describe the
     encrypted-side I/O buffer.  This may be a different size to the buffer
     in (1).

 (3) Add an iov_iter (->io_iter) to the I/O subrequest to describe the part
     of the I/O buffer for that subrequest.

This will allow future patches to point to a bounce buffer instead for
purposes of handling oversize writes, decryption (where we want to save the
encrypted data to the cache) and decompression.

These iov_iters persist for the lifetime of the (sub)request, and so can be
accessed multiple times without worrying about them being deallocated upon
return to the caller.

The network filesystem must appropriately advance the iterator before
terminating the request.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/afs/file.c            |  6 +----
 fs/netfs/buffered_read.c | 13 +++++++++
 fs/netfs/io.c            | 69 +++++++++++++++++++++++++++++++++++-------------
 include/linux/netfs.h    |  3 +++
 4 files changed, 67 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/fs/afs/file.c b/fs/afs/file.c
index d152ba451f0e..3403bb792deb 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -323,11 +323,7 @@ static void afs_issue_read(struct netfs_io_subrequest *subreq)
 	fsreq->len	= subreq->len   - subreq->transferred;
 	fsreq->key	= key_get(subreq->rreq->netfs_priv);
 	fsreq->vnode	= vnode;
-	fsreq->iter	= &fsreq->def_iter;
-
-	iov_iter_xarray(&fsreq->def_iter, ITER_DEST,
-			&fsreq->vnode->netfs.inode.i_mapping->i_pages,
-			fsreq->pos, fsreq->len);
+	fsreq->iter	= &subreq->io_iter;
 
 	afs_fetch_data(fsreq->vnode, fsreq);
 	afs_put_read(fsreq);
diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index d39d0ffe75d2..751556faa70b 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -199,6 +199,10 @@ void netfs_readahead(struct readahead_control *ractl)
 
 	netfs_rreq_expand(rreq, ractl);
 
+	/* Set up the output buffer */
+	iov_iter_xarray(&rreq->iter, ITER_DEST, &ractl->mapping->i_pages,
+			rreq->start, rreq->len);
+
 	/* Drop the refs on the folios here rather than in the cache or
 	 * filesystem.  The locks will be dropped in netfs_rreq_unlock().
 	 */
@@ -251,6 +255,11 @@ int netfs_read_folio(struct file *file, struct folio *folio)
 
 	netfs_stat(&netfs_n_rh_readpage);
 	trace_netfs_read(rreq, rreq->start, rreq->len, netfs_read_trace_readpage);
+
+	/* Set up the output buffer */
+	iov_iter_xarray(&rreq->iter, ITER_DEST, &mapping->i_pages,
+			rreq->start, rreq->len);
+
 	return netfs_begin_read(rreq, true);
 
 discard:
@@ -408,6 +417,10 @@ retry:
 	ractl._nr_pages = folio_nr_pages(folio);
 	netfs_rreq_expand(rreq, &ractl);
 
+	/* Set up the output buffer */
+	iov_iter_xarray(&rreq->iter, ITER_DEST, &mapping->i_pages,
+			rreq->start, rreq->len);
+
 	/* We hold the folio locks, so we can drop the references */
 	folio_get(folio);
 	while (readahead_folio(&ractl))
diff --git a/fs/netfs/io.c b/fs/netfs/io.c
index 7f753380e047..e9d408e211b8 100644
--- a/fs/netfs/io.c
+++ b/fs/netfs/io.c
@@ -21,12 +21,7 @@
  */
 static void netfs_clear_unread(struct netfs_io_subrequest *subreq)
 {
-	struct iov_iter iter;
-
-	iov_iter_xarray(&iter, ITER_DEST, &subreq->rreq->mapping->i_pages,
-			subreq->start + subreq->transferred,
-			subreq->len   - subreq->transferred);
-	iov_iter_zero(iov_iter_count(&iter), &iter);
+	iov_iter_zero(iov_iter_count(&subreq->io_iter), &subreq->io_iter);
 }
 
 static void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error,
@@ -46,14 +41,9 @@ static void netfs_read_from_cache(struct netfs_io_request *rreq,
 				  enum netfs_read_from_hole read_hole)
 {
 	struct netfs_cache_resources *cres = &rreq->cache_resources;
-	struct iov_iter iter;
 
 	netfs_stat(&netfs_n_rh_read);
-	iov_iter_xarray(&iter, ITER_DEST, &rreq->mapping->i_pages,
-			subreq->start + subreq->transferred,
-			subreq->len   - subreq->transferred);
-
-	cres->ops->read(cres, subreq->start, &iter, read_hole,
+	cres->ops->read(cres, subreq->start, &subreq->io_iter, read_hole,
 			netfs_cache_read_terminated, subreq);
 }
 
@@ -88,6 +78,11 @@ static void netfs_read_from_server(struct netfs_io_request *rreq,
 				   struct netfs_io_subrequest *subreq)
 {
 	netfs_stat(&netfs_n_rh_download);
+	if (iov_iter_count(&subreq->io_iter) != subreq->len - subreq->transferred)
+		pr_warn("R=%08x[%u] ITER PRE-MISMATCH %zx != %zx-%zx %lx\n",
+			rreq->debug_id, subreq->debug_index,
+			iov_iter_count(&subreq->io_iter), subreq->len,
+			subreq->transferred, subreq->flags);
 	rreq->netfs_ops->issue_read(subreq);
 }
 
@@ -259,6 +254,30 @@ static void netfs_rreq_short_read(struct netfs_io_request *rreq,
 		netfs_read_from_server(rreq, subreq);
 }
 
+/*
+ * Reset the subrequest iterator prior to resubmission.
+ */
+static void netfs_reset_subreq_iter(struct netfs_io_request *rreq,
+				    struct netfs_io_subrequest *subreq)
+{
+	size_t remaining = subreq->len - subreq->transferred;
+	size_t count = iov_iter_count(&subreq->io_iter);
+
+	if (count == remaining)
+		return;
+
+	_debug("R=%08x[%u] ITER RESUB-MISMATCH %zx != %zx-%zx-%llx %x\n",
+	       rreq->debug_id, subreq->debug_index,
+	       iov_iter_count(&subreq->io_iter), subreq->transferred,
+	       subreq->len, rreq->i_size,
+	       subreq->io_iter.iter_type);
+
+	if (count < remaining)
+		iov_iter_revert(&subreq->io_iter, remaining - count);
+	else
+		iov_iter_advance(&subreq->io_iter, count - remaining);
+}
+
 /*
  * Resubmit any short or failed operations.  Returns true if we got the rreq
  * ref back.
@@ -287,6 +306,7 @@ static bool netfs_rreq_perform_resubmissions(struct netfs_io_request *rreq)
 			trace_netfs_sreq(subreq, netfs_sreq_trace_download_instead);
 			netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit);
 			atomic_inc(&rreq->nr_outstanding);
+			netfs_reset_subreq_iter(rreq, subreq);
 			netfs_read_from_server(rreq, subreq);
 		} else if (test_bit(NETFS_SREQ_SHORT_IO, &subreq->flags)) {
 			netfs_rreq_short_read(rreq, subreq);
@@ -399,9 +419,9 @@ void netfs_subreq_terminated(struct netfs_io_subrequest *subreq,
 	struct netfs_io_request *rreq = subreq->rreq;
 	int u;
 
-	_enter("[%u]{%llx,%lx},%zd",
-	       subreq->debug_index, subreq->start, subreq->flags,
-	       transferred_or_error);
+	_enter("R=%x[%x]{%llx,%lx},%zd",
+	       rreq->debug_id, subreq->debug_index,
+	       subreq->start, subreq->flags, transferred_or_error);
 
 	switch (subreq->source) {
 	case NETFS_READ_FROM_CACHE:
@@ -501,7 +521,8 @@ static enum netfs_io_source netfs_cache_prepare_read(struct netfs_io_subrequest
  */
 static enum netfs_io_source
 netfs_rreq_prepare_read(struct netfs_io_request *rreq,
-			struct netfs_io_subrequest *subreq)
+			struct netfs_io_subrequest *subreq,
+			struct iov_iter *io_iter)
 {
 	enum netfs_io_source source;
 
@@ -528,9 +549,14 @@ netfs_rreq_prepare_read(struct netfs_io_request *rreq,
 		}
 	}
 
-	if (WARN_ON(subreq->len == 0))
+	if (WARN_ON(subreq->len == 0)) {
 		source = NETFS_INVALID_READ;
+		goto out;
+	}
 
+	subreq->io_iter = *io_iter;
+	iov_iter_truncate(&subreq->io_iter, subreq->len);
+	iov_iter_advance(io_iter, subreq->len);
 out:
 	subreq->source = source;
 	trace_netfs_sreq(subreq, netfs_sreq_trace_prepare);
@@ -541,6 +567,7 @@ out:
  * Slice off a piece of a read request and submit an I/O request for it.
  */
 static bool netfs_rreq_submit_slice(struct netfs_io_request *rreq,
+				    struct iov_iter *io_iter,
 				    unsigned int *_debug_index)
 {
 	struct netfs_io_subrequest *subreq;
@@ -565,7 +592,7 @@ static bool netfs_rreq_submit_slice(struct netfs_io_request *rreq,
 	 * (the starts must coincide), in which case, we go around the loop
 	 * again and ask it to download the next piece.
 	 */
-	source = netfs_rreq_prepare_read(rreq, subreq);
+	source = netfs_rreq_prepare_read(rreq, subreq, io_iter);
 	if (source == NETFS_INVALID_READ)
 		goto subreq_failed;
 
@@ -603,6 +630,7 @@ subreq_failed:
  */
 int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
 {
+	struct iov_iter io_iter;
 	unsigned int debug_index = 0;
 	int ret;
 
@@ -615,6 +643,8 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
 		return -EIO;
 	}
 
+	rreq->io_iter = rreq->iter;
+
 	INIT_WORK(&rreq->work, netfs_rreq_work);
 
 	if (sync)
@@ -624,8 +654,9 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
 	 * want and submit each one.
 	 */
 	atomic_set(&rreq->nr_outstanding, 1);
+	io_iter = rreq->io_iter;
 	do {
-		if (!netfs_rreq_submit_slice(rreq, &debug_index))
+		if (!netfs_rreq_submit_slice(rreq, &io_iter, &debug_index))
 			break;
 
 	} while (rreq->submitted < rreq->len);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index fc6d9756a029..3da962e977f5 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -150,6 +150,7 @@ struct netfs_cache_resources {
 struct netfs_io_subrequest {
 	struct netfs_io_request *rreq;		/* Supervising I/O request */
 	struct list_head	rreq_link;	/* Link in rreq->subrequests */
+	struct iov_iter		io_iter;	/* Iterator for this subrequest */
 	loff_t			start;		/* Where to start the I/O */
 	size_t			len;		/* Size of the I/O */
 	size_t			transferred;	/* Amount of data transferred */
@@ -186,6 +187,8 @@ struct netfs_io_request {
 	struct netfs_cache_resources cache_resources;
 	struct list_head	proc_link;	/* Link in netfs_iorequests */
 	struct list_head	subrequests;	/* Contributory I/O operations */
+	struct iov_iter		iter;		/* Unencrypted-side iterator */
+	struct iov_iter		io_iter;	/* I/O (Encrypted-side) iterator */
 	void			*netfs_priv;	/* Private data for the netfs */
 	unsigned int		debug_id;
 	atomic_t		nr_outstanding;	/* Number of ops in progress */
-- 
cgit v1.2.3


From 72904d7b9bfbf2dd146254edea93958bc35bbbfe Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 19 Oct 2023 12:55:11 +0100
Subject: rxrpc, afs: Allow afs to pin rxrpc_peer objects

Change rxrpc's API such that:

 (1) A new function, rxrpc_kernel_lookup_peer(), is provided to look up an
     rxrpc_peer record for a remote address and a corresponding function,
     rxrpc_kernel_put_peer(), is provided to dispose of it again.

 (2) When setting up a call, the rxrpc_peer object used during a call is
     now passed in rather than being set up by rxrpc_connect_call().  For
     afs, this meenat passing it to rxrpc_kernel_begin_call() rather than
     the full address (the service ID then has to be passed in as a
     separate parameter).

 (3) A new function, rxrpc_kernel_remote_addr(), is added so that afs can
     get a pointer to the transport address for display purposed, and
     another, rxrpc_kernel_remote_srx(), to gain a pointer to the full
     rxrpc address.

 (4) The function to retrieve the RTT from a call, rxrpc_kernel_get_srtt(),
     is then altered to take a peer.  This now returns the RTT or -1 if
     there are insufficient samples.

 (5) Rename rxrpc_kernel_get_peer() to rxrpc_kernel_call_get_peer().

 (6) Provide a new function, rxrpc_kernel_get_peer(), to get a ref on a
     peer the caller already has.

This allows the afs filesystem to pin the rxrpc_peer records that it is
using, allowing faster lookups and pointer comparisons rather than
comparing sockaddr_rxrpc contents.  It also makes it easier to get hold of
the RTT.  The following changes are made to afs:

 (1) The addr_list struct's addrs[] elements now hold a peer struct pointer
     and a service ID rather than a sockaddr_rxrpc.

 (2) When displaying the transport address, rxrpc_kernel_remote_addr() is
     used.

 (3) The port arg is removed from afs_alloc_addrlist() since it's always
     overridden.

 (4) afs_merge_fs_addr4() and afs_merge_fs_addr6() do peer lookup and may
     now return an error that must be handled.

 (5) afs_find_server() now takes a peer pointer to specify the address.

 (6) afs_find_server(), afs_compare_fs_alists() and afs_merge_fs_addr[46]{}
     now do peer pointer comparison rather than address comparison.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
---
 fs/afs/addr_list.c           | 125 +++++++++++++++++++++++--------------------
 fs/afs/cmservice.c           |   5 +-
 fs/afs/fs_probe.c            |  11 ++--
 fs/afs/internal.h            |  26 ++++-----
 fs/afs/proc.c                |   9 ++--
 fs/afs/rotate.c              |   6 +--
 fs/afs/rxrpc.c               |  10 ++--
 fs/afs/server.c              |  41 +++-----------
 fs/afs/vl_alias.c            |  55 ++-----------------
 fs/afs/vl_list.c             |  15 ++++--
 fs/afs/vl_probe.c            |  12 +++--
 fs/afs/vl_rotate.c           |   6 +--
 fs/afs/vlclient.c            |  22 +++++---
 include/net/af_rxrpc.h       |  15 ++++--
 include/trace/events/rxrpc.h |   3 ++
 net/rxrpc/af_rxrpc.c         |  62 ++++++++++++++++++---
 net/rxrpc/ar-internal.h      |   2 +-
 net/rxrpc/call_object.c      |  17 +++---
 net/rxrpc/peer_object.c      |  58 ++++++++++++--------
 net/rxrpc/sendmsg.c          |  11 +++-
 20 files changed, 273 insertions(+), 238 deletions(-)

(limited to 'include')

diff --git a/fs/afs/addr_list.c b/fs/afs/addr_list.c
index ac05a59e9d46..519821f5aedc 100644
--- a/fs/afs/addr_list.c
+++ b/fs/afs/addr_list.c
@@ -13,26 +13,33 @@
 #include "internal.h"
 #include "afs_fs.h"
 
+static void afs_free_addrlist(struct rcu_head *rcu)
+{
+	struct afs_addr_list *alist = container_of(rcu, struct afs_addr_list, rcu);
+	unsigned int i;
+
+	for (i = 0; i < alist->nr_addrs; i++)
+		rxrpc_kernel_put_peer(alist->addrs[i].peer);
+}
+
 /*
  * Release an address list.
  */
 void afs_put_addrlist(struct afs_addr_list *alist)
 {
 	if (alist && refcount_dec_and_test(&alist->usage))
-		kfree_rcu(alist, rcu);
+		call_rcu(&alist->rcu, afs_free_addrlist);
 }
 
 /*
  * Allocate an address list.
  */
-struct afs_addr_list *afs_alloc_addrlist(unsigned int nr,
-					 unsigned short service,
-					 unsigned short port)
+struct afs_addr_list *afs_alloc_addrlist(unsigned int nr, u16 service_id)
 {
 	struct afs_addr_list *alist;
 	unsigned int i;
 
-	_enter("%u,%u,%u", nr, service, port);
+	_enter("%u,%u", nr, service_id);
 
 	if (nr > AFS_MAX_ADDRESSES)
 		nr = AFS_MAX_ADDRESSES;
@@ -44,16 +51,8 @@ struct afs_addr_list *afs_alloc_addrlist(unsigned int nr,
 	refcount_set(&alist->usage, 1);
 	alist->max_addrs = nr;
 
-	for (i = 0; i < nr; i++) {
-		struct sockaddr_rxrpc *srx = &alist->addrs[i].srx;
-		srx->srx_family			= AF_RXRPC;
-		srx->srx_service		= service;
-		srx->transport_type		= SOCK_DGRAM;
-		srx->transport_len		= sizeof(srx->transport.sin6);
-		srx->transport.sin6.sin6_family	= AF_INET6;
-		srx->transport.sin6.sin6_port	= htons(port);
-	}
-
+	for (i = 0; i < nr; i++)
+		alist->addrs[i].service_id = service_id;
 	return alist;
 }
 
@@ -126,7 +125,7 @@ struct afs_vlserver_list *afs_parse_text_addrs(struct afs_net *net,
 	if (!vllist->servers[0].server)
 		goto error_vl;
 
-	alist = afs_alloc_addrlist(nr, service, AFS_VL_PORT);
+	alist = afs_alloc_addrlist(nr, service);
 	if (!alist)
 		goto error;
 
@@ -197,9 +196,11 @@ struct afs_vlserver_list *afs_parse_text_addrs(struct afs_net *net,
 		}
 
 		if (family == AF_INET)
-			afs_merge_fs_addr4(alist, x[0], xport);
+			ret = afs_merge_fs_addr4(net, alist, x[0], xport);
 		else
-			afs_merge_fs_addr6(alist, x, xport);
+			ret = afs_merge_fs_addr6(net, alist, x, xport);
+		if (ret < 0)
+			goto error;
 
 	} while (p < end);
 
@@ -271,25 +272,33 @@ struct afs_vlserver_list *afs_dns_query(struct afs_cell *cell, time64_t *_expiry
 /*
  * Merge an IPv4 entry into a fileserver address list.
  */
-void afs_merge_fs_addr4(struct afs_addr_list *alist, __be32 xdr, u16 port)
+int afs_merge_fs_addr4(struct afs_net *net, struct afs_addr_list *alist,
+		       __be32 xdr, u16 port)
 {
-	struct sockaddr_rxrpc *srx;
-	u32 addr = ntohl(xdr);
+	struct sockaddr_rxrpc srx;
+	struct rxrpc_peer *peer;
 	int i;
 
 	if (alist->nr_addrs >= alist->max_addrs)
-		return;
+		return 0;
 
-	for (i = 0; i < alist->nr_ipv4; i++) {
-		struct sockaddr_in *a = &alist->addrs[i].srx.transport.sin;
-		u32 a_addr = ntohl(a->sin_addr.s_addr);
-		u16 a_port = ntohs(a->sin_port);
+	srx.srx_family = AF_RXRPC;
+	srx.transport_type = SOCK_DGRAM;
+	srx.transport_len = sizeof(srx.transport.sin);
+	srx.transport.sin.sin_family = AF_INET;
+	srx.transport.sin.sin_port = htons(port);
+	srx.transport.sin.sin_addr.s_addr = xdr;
 
-		if (addr == a_addr && port == a_port)
-			return;
-		if (addr == a_addr && port < a_port)
-			break;
-		if (addr < a_addr)
+	peer = rxrpc_kernel_lookup_peer(net->socket, &srx, GFP_KERNEL);
+	if (!peer)
+		return -ENOMEM;
+
+	for (i = 0; i < alist->nr_ipv4; i++) {
+		if (peer == alist->addrs[i].peer) {
+			rxrpc_kernel_put_peer(peer);
+			return 0;
+		}
+		if (peer <= alist->addrs[i].peer)
 			break;
 	}
 
@@ -298,38 +307,42 @@ void afs_merge_fs_addr4(struct afs_addr_list *alist, __be32 xdr, u16 port)
 			alist->addrs + i,
 			sizeof(alist->addrs[0]) * (alist->nr_addrs - i));
 
-	srx = &alist->addrs[i].srx;
-	srx->srx_family = AF_RXRPC;
-	srx->transport_type = SOCK_DGRAM;
-	srx->transport_len = sizeof(srx->transport.sin);
-	srx->transport.sin.sin_family = AF_INET;
-	srx->transport.sin.sin_port = htons(port);
-	srx->transport.sin.sin_addr.s_addr = xdr;
+	alist->addrs[i].peer = peer;
 	alist->nr_ipv4++;
 	alist->nr_addrs++;
+	return 0;
 }
 
 /*
  * Merge an IPv6 entry into a fileserver address list.
  */
-void afs_merge_fs_addr6(struct afs_addr_list *alist, __be32 *xdr, u16 port)
+int afs_merge_fs_addr6(struct afs_net *net, struct afs_addr_list *alist,
+		       __be32 *xdr, u16 port)
 {
-	struct sockaddr_rxrpc *srx;
-	int i, diff;
+	struct sockaddr_rxrpc srx;
+	struct rxrpc_peer *peer;
+	int i;
 
 	if (alist->nr_addrs >= alist->max_addrs)
-		return;
+		return 0;
 
-	for (i = alist->nr_ipv4; i < alist->nr_addrs; i++) {
-		struct sockaddr_in6 *a = &alist->addrs[i].srx.transport.sin6;
-		u16 a_port = ntohs(a->sin6_port);
+	srx.srx_family = AF_RXRPC;
+	srx.transport_type = SOCK_DGRAM;
+	srx.transport_len = sizeof(srx.transport.sin6);
+	srx.transport.sin6.sin6_family = AF_INET6;
+	srx.transport.sin6.sin6_port = htons(port);
+	memcpy(&srx.transport.sin6.sin6_addr, xdr, 16);
 
-		diff = memcmp(xdr, &a->sin6_addr, 16);
-		if (diff == 0 && port == a_port)
-			return;
-		if (diff == 0 && port < a_port)
-			break;
-		if (diff < 0)
+	peer = rxrpc_kernel_lookup_peer(net->socket, &srx, GFP_KERNEL);
+	if (!peer)
+		return -ENOMEM;
+
+	for (i = alist->nr_ipv4; i < alist->nr_addrs; i++) {
+		if (peer == alist->addrs[i].peer) {
+			rxrpc_kernel_put_peer(peer);
+			return 0;
+		}
+		if (peer <= alist->addrs[i].peer)
 			break;
 	}
 
@@ -337,15 +350,9 @@ void afs_merge_fs_addr6(struct afs_addr_list *alist, __be32 *xdr, u16 port)
 		memmove(alist->addrs + i + 1,
 			alist->addrs + i,
 			sizeof(alist->addrs[0]) * (alist->nr_addrs - i));
-
-	srx = &alist->addrs[i].srx;
-	srx->srx_family = AF_RXRPC;
-	srx->transport_type = SOCK_DGRAM;
-	srx->transport_len = sizeof(srx->transport.sin6);
-	srx->transport.sin6.sin6_family = AF_INET6;
-	srx->transport.sin6.sin6_port = htons(port);
-	memcpy(&srx->transport.sin6.sin6_addr, xdr, 16);
+	alist->addrs[i].peer = peer;
 	alist->nr_addrs++;
+	return 0;
 }
 
 /*
diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c
index d4ddb20d6732..99a3f20bc786 100644
--- a/fs/afs/cmservice.c
+++ b/fs/afs/cmservice.c
@@ -146,10 +146,11 @@ static int afs_find_cm_server_by_peer(struct afs_call *call)
 {
 	struct sockaddr_rxrpc srx;
 	struct afs_server *server;
+	struct rxrpc_peer *peer;
 
-	rxrpc_kernel_get_peer(call->net->socket, call->rxcall, &srx);
+	peer = rxrpc_kernel_get_call_peer(call->net->socket, call->rxcall);
 
-	server = afs_find_server(call->net, &srx);
+	server = afs_find_server(call->net, peer);
 	if (!server) {
 		trace_afs_cm_no_server(call, &srx);
 		return 0;
diff --git a/fs/afs/fs_probe.c b/fs/afs/fs_probe.c
index 3dd24842f277..58d28b82571e 100644
--- a/fs/afs/fs_probe.c
+++ b/fs/afs/fs_probe.c
@@ -101,6 +101,7 @@ static void afs_fs_probe_not_done(struct afs_net *net,
 void afs_fileserver_probe_result(struct afs_call *call)
 {
 	struct afs_addr_list *alist = call->alist;
+	struct afs_address *addr = &alist->addrs[call->addr_ix];
 	struct afs_server *server = call->server;
 	unsigned int index = call->addr_ix;
 	unsigned int rtt_us = 0, cap0;
@@ -153,12 +154,12 @@ responded:
 	if (call->service_id == YFS_FS_SERVICE) {
 		server->probe.is_yfs = true;
 		set_bit(AFS_SERVER_FL_IS_YFS, &server->flags);
-		alist->addrs[index].srx.srx_service = call->service_id;
+		addr->service_id = call->service_id;
 	} else {
 		server->probe.not_yfs = true;
 		if (!server->probe.is_yfs) {
 			clear_bit(AFS_SERVER_FL_IS_YFS, &server->flags);
-			alist->addrs[index].srx.srx_service = call->service_id;
+			addr->service_id = call->service_id;
 		}
 		cap0 = ntohl(call->tmp);
 		if (cap0 & AFS3_VICED_CAPABILITY_64BITFILES)
@@ -167,7 +168,7 @@ responded:
 			clear_bit(AFS_SERVER_FL_HAS_FS64, &server->flags);
 	}
 
-	rxrpc_kernel_get_srtt(call->net->socket, call->rxcall, &rtt_us);
+	rtt_us = rxrpc_kernel_get_srtt(addr->peer);
 	if (rtt_us < server->probe.rtt) {
 		server->probe.rtt = rtt_us;
 		server->rtt = rtt_us;
@@ -181,8 +182,8 @@ responded:
 out:
 	spin_unlock(&server->probe_lock);
 
-	_debug("probe %pU [%u] %pISpc rtt=%u ret=%d",
-	       &server->uuid, index, &alist->addrs[index].srx.transport,
+	_debug("probe %pU [%u] %pISpc rtt=%d ret=%d",
+	       &server->uuid, index, rxrpc_kernel_remote_addr(alist->addrs[index].peer),
 	       rtt_us, ret);
 
 	return afs_done_one_fs_probe(call->net, server);
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index e2adb314ab6a..ec08b4a7e499 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -72,6 +72,11 @@ enum afs_call_state {
 	AFS_CALL_COMPLETE,		/* Completed or failed */
 };
 
+struct afs_address {
+	struct rxrpc_peer	*peer;
+	u16			service_id;
+};
+
 /*
  * List of server addresses.
  */
@@ -87,9 +92,7 @@ struct afs_addr_list {
 	enum dns_lookup_status	status:8;
 	unsigned long		failed;		/* Mask of addrs that failed locally/ICMP */
 	unsigned long		responded;	/* Mask of addrs that responded */
-	struct {
-		struct sockaddr_rxrpc	srx;
-	} addrs[] __counted_by(max_addrs);
+	struct afs_address	addrs[] __counted_by(max_addrs);
 #define AFS_MAX_ADDRESSES ((unsigned int)(sizeof(unsigned long) * 8))
 };
 
@@ -420,7 +423,7 @@ struct afs_vlserver {
 	atomic_t		probe_outstanding;
 	spinlock_t		probe_lock;
 	struct {
-		unsigned int	rtt;		/* RTT in uS */
+		unsigned int	rtt;		/* Best RTT in uS (or UINT_MAX) */
 		u32		abort_code;
 		short		error;
 		unsigned short	flags;
@@ -537,7 +540,7 @@ struct afs_server {
 	atomic_t		probe_outstanding;
 	spinlock_t		probe_lock;
 	struct {
-		unsigned int	rtt;		/* RTT in uS */
+		unsigned int	rtt;		/* Best RTT in uS (or UINT_MAX) */
 		u32		abort_code;
 		short		error;
 		bool		responded:1;
@@ -964,9 +967,7 @@ static inline struct afs_addr_list *afs_get_addrlist(struct afs_addr_list *alist
 		refcount_inc(&alist->usage);
 	return alist;
 }
-extern struct afs_addr_list *afs_alloc_addrlist(unsigned int,
-						unsigned short,
-						unsigned short);
+extern struct afs_addr_list *afs_alloc_addrlist(unsigned int nr, u16 service_id);
 extern void afs_put_addrlist(struct afs_addr_list *);
 extern struct afs_vlserver_list *afs_parse_text_addrs(struct afs_net *,
 						      const char *, size_t, char,
@@ -977,8 +978,10 @@ extern struct afs_vlserver_list *afs_dns_query(struct afs_cell *, time64_t *);
 extern bool afs_iterate_addresses(struct afs_addr_cursor *);
 extern int afs_end_cursor(struct afs_addr_cursor *);
 
-extern void afs_merge_fs_addr4(struct afs_addr_list *, __be32, u16);
-extern void afs_merge_fs_addr6(struct afs_addr_list *, __be32 *, u16);
+extern int afs_merge_fs_addr4(struct afs_net *net, struct afs_addr_list *addr,
+			      __be32 xdr, u16 port);
+extern int afs_merge_fs_addr6(struct afs_net *net, struct afs_addr_list *addr,
+			      __be32 *xdr, u16 port);
 
 /*
  * callback.c
@@ -1405,8 +1408,7 @@ extern void __exit afs_clean_up_permit_cache(void);
  */
 extern spinlock_t afs_server_peer_lock;
 
-extern struct afs_server *afs_find_server(struct afs_net *,
-					  const struct sockaddr_rxrpc *);
+extern struct afs_server *afs_find_server(struct afs_net *, const struct rxrpc_peer *);
 extern struct afs_server *afs_find_server_by_uuid(struct afs_net *, const uuid_t *);
 extern struct afs_server *afs_lookup_server(struct afs_cell *, struct key *, const uuid_t *, u32);
 extern struct afs_server *afs_get_server(struct afs_server *, enum afs_server_trace);
diff --git a/fs/afs/proc.c b/fs/afs/proc.c
index ab9cd986cfd9..8a65a06908d2 100644
--- a/fs/afs/proc.c
+++ b/fs/afs/proc.c
@@ -307,7 +307,7 @@ static int afs_proc_cell_vlservers_show(struct seq_file *m, void *v)
 		for (i = 0; i < alist->nr_addrs; i++)
 			seq_printf(m, " %c %pISpc\n",
 				   alist->preferred == i ? '>' : '-',
-				   &alist->addrs[i].srx.transport);
+				   rxrpc_kernel_remote_addr(alist->addrs[i].peer));
 	}
 	seq_printf(m, " info: fl=%lx rtt=%d\n", vlserver->flags, vlserver->rtt);
 	seq_printf(m, " probe: fl=%x e=%d ac=%d out=%d\n",
@@ -398,9 +398,10 @@ static int afs_proc_servers_show(struct seq_file *m, void *v)
 	seq_printf(m, "  - ALIST v=%u rsp=%lx f=%lx\n",
 		   alist->version, alist->responded, alist->failed);
 	for (i = 0; i < alist->nr_addrs; i++)
-		seq_printf(m, "    [%x] %pISpc%s\n",
-			   i, &alist->addrs[i].srx.transport,
-			   alist->preferred == i ? "*" : "");
+		seq_printf(m, "    [%x] %pISpc%s rtt=%d\n",
+			   i, rxrpc_kernel_remote_addr(alist->addrs[i].peer),
+			   alist->preferred == i ? "*" : "",
+			   rxrpc_kernel_get_srtt(alist->addrs[i].peer));
 	return 0;
 }
 
diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c
index 46081e5da6f5..59aed7a6dd11 100644
--- a/fs/afs/rotate.c
+++ b/fs/afs/rotate.c
@@ -113,7 +113,7 @@ bool afs_select_fileserver(struct afs_operation *op)
 	struct afs_server *server;
 	struct afs_vnode *vnode = op->file[0].vnode;
 	struct afs_error e;
-	u32 rtt;
+	unsigned int rtt;
 	int error = op->ac.error, i;
 
 	_enter("%lx[%d],%lx[%d],%d,%d",
@@ -420,7 +420,7 @@ pick_server:
 	}
 
 	op->index = -1;
-	rtt = U32_MAX;
+	rtt = UINT_MAX;
 	for (i = 0; i < op->server_list->nr_servers; i++) {
 		struct afs_server *s = op->server_list->servers[i].server;
 
@@ -488,7 +488,7 @@ iterate_address:
 
 	_debug("address [%u] %u/%u %pISp",
 	       op->index, op->ac.index, op->ac.alist->nr_addrs,
-	       &op->ac.alist->addrs[op->ac.index].srx.transport);
+	       rxrpc_kernel_remote_addr(op->ac.alist->addrs[op->ac.index].peer));
 
 	_leave(" = t");
 	return true;
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index 181317126e43..2603db03b7ff 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -296,7 +296,8 @@ static void afs_notify_end_request_tx(struct sock *sock,
  */
 void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp)
 {
-	struct sockaddr_rxrpc *srx = &ac->alist->addrs[ac->index].srx;
+	struct afs_address *addr = &ac->alist->addrs[ac->index];
+	struct rxrpc_peer *peer = addr->peer;
 	struct rxrpc_call *rxcall;
 	struct msghdr msg;
 	struct kvec iov[1];
@@ -304,7 +305,7 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp)
 	s64 tx_total_len;
 	int ret;
 
-	_enter(",{%pISp},", &srx->transport);
+	_enter(",{%pISp},", rxrpc_kernel_remote_addr(addr->peer));
 
 	ASSERT(call->type != NULL);
 	ASSERT(call->type->name != NULL);
@@ -333,7 +334,7 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp)
 	}
 
 	/* create a call */
-	rxcall = rxrpc_kernel_begin_call(call->net->socket, srx, call->key,
+	rxcall = rxrpc_kernel_begin_call(call->net->socket, peer, call->key,
 					 (unsigned long)call,
 					 tx_total_len,
 					 call->max_lifespan,
@@ -341,6 +342,7 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp)
 					 (call->async ?
 					  afs_wake_up_async_call :
 					  afs_wake_up_call_waiter),
+					 addr->service_id,
 					 call->upgrade,
 					 (call->intr ? RXRPC_PREINTERRUPTIBLE :
 					  RXRPC_UNINTERRUPTIBLE),
@@ -461,7 +463,7 @@ static void afs_log_error(struct afs_call *call, s32 remote_abort)
 		max = m + 1;
 		pr_notice("kAFS: Peer reported %s failure on %s [%pISp]\n",
 			  msg, call->type->name,
-			  &call->alist->addrs[call->addr_ix].srx.transport);
+			  rxrpc_kernel_remote_addr(call->alist->addrs[call->addr_ix].peer));
 	}
 }
 
diff --git a/fs/afs/server.c b/fs/afs/server.c
index b8e2d211d4a1..5b5fa94005c9 100644
--- a/fs/afs/server.c
+++ b/fs/afs/server.c
@@ -21,13 +21,12 @@ static void __afs_put_server(struct afs_net *, struct afs_server *);
 /*
  * Find a server by one of its addresses.
  */
-struct afs_server *afs_find_server(struct afs_net *net,
-				   const struct sockaddr_rxrpc *srx)
+struct afs_server *afs_find_server(struct afs_net *net, const struct rxrpc_peer *peer)
 {
 	const struct afs_addr_list *alist;
 	struct afs_server *server = NULL;
 	unsigned int i;
-	int seq = 1, diff;
+	int seq = 1;
 
 	rcu_read_lock();
 
@@ -38,37 +37,11 @@ struct afs_server *afs_find_server(struct afs_net *net,
 		seq++; /* 2 on the 1st/lockless path, otherwise odd */
 		read_seqbegin_or_lock(&net->fs_addr_lock, &seq);
 
-		if (srx->transport.family == AF_INET6) {
-			const struct sockaddr_in6 *a = &srx->transport.sin6, *b;
-			hlist_for_each_entry_rcu(server, &net->fs_addresses6, addr6_link) {
-				alist = rcu_dereference(server->addresses);
-				for (i = alist->nr_ipv4; i < alist->nr_addrs; i++) {
-					b = &alist->addrs[i].srx.transport.sin6;
-					diff = ((u16 __force)a->sin6_port -
-						(u16 __force)b->sin6_port);
-					if (diff == 0)
-						diff = memcmp(&a->sin6_addr,
-							      &b->sin6_addr,
-							      sizeof(struct in6_addr));
-					if (diff == 0)
-						goto found;
-				}
-			}
-		} else {
-			const struct sockaddr_in *a = &srx->transport.sin, *b;
-			hlist_for_each_entry_rcu(server, &net->fs_addresses4, addr4_link) {
-				alist = rcu_dereference(server->addresses);
-				for (i = 0; i < alist->nr_ipv4; i++) {
-					b = &alist->addrs[i].srx.transport.sin;
-					diff = ((u16 __force)a->sin_port -
-						(u16 __force)b->sin_port);
-					if (diff == 0)
-						diff = ((u32 __force)a->sin_addr.s_addr -
-							(u32 __force)b->sin_addr.s_addr);
-					if (diff == 0)
-						goto found;
-				}
-			}
+		hlist_for_each_entry_rcu(server, &net->fs_addresses6, addr6_link) {
+			alist = rcu_dereference(server->addresses);
+			for (i = 0; i < alist->nr_addrs; i++)
+				if (alist->addrs[i].peer == peer)
+					goto found;
 		}
 
 		server = NULL;
diff --git a/fs/afs/vl_alias.c b/fs/afs/vl_alias.c
index d3c0df70a1a5..6fdf9f1bedc0 100644
--- a/fs/afs/vl_alias.c
+++ b/fs/afs/vl_alias.c
@@ -32,55 +32,6 @@ static struct afs_volume *afs_sample_volume(struct afs_cell *cell, struct key *k
 	return volume;
 }
 
-/*
- * Compare two addresses.
- */
-static int afs_compare_addrs(const struct sockaddr_rxrpc *srx_a,
-			     const struct sockaddr_rxrpc *srx_b)
-{
-	short port_a, port_b;
-	int addr_a, addr_b, diff;
-
-	diff = (short)srx_a->transport_type - (short)srx_b->transport_type;
-	if (diff)
-		goto out;
-
-	switch (srx_a->transport_type) {
-	case AF_INET: {
-		const struct sockaddr_in *a = &srx_a->transport.sin;
-		const struct sockaddr_in *b = &srx_b->transport.sin;
-		addr_a = ntohl(a->sin_addr.s_addr);
-		addr_b = ntohl(b->sin_addr.s_addr);
-		diff = addr_a - addr_b;
-		if (diff == 0) {
-			port_a = ntohs(a->sin_port);
-			port_b = ntohs(b->sin_port);
-			diff = port_a - port_b;
-		}
-		break;
-	}
-
-	case AF_INET6: {
-		const struct sockaddr_in6 *a = &srx_a->transport.sin6;
-		const struct sockaddr_in6 *b = &srx_b->transport.sin6;
-		diff = memcmp(&a->sin6_addr, &b->sin6_addr, 16);
-		if (diff == 0) {
-			port_a = ntohs(a->sin6_port);
-			port_b = ntohs(b->sin6_port);
-			diff = port_a - port_b;
-		}
-		break;
-	}
-
-	default:
-		WARN_ON(1);
-		diff = 1;
-	}
-
-out:
-	return diff;
-}
-
 /*
  * Compare the address lists of a pair of fileservers.
  */
@@ -94,9 +45,9 @@ static int afs_compare_fs_alists(const struct afs_server *server_a,
 	lb = rcu_dereference(server_b->addresses);
 
 	while (a < la->nr_addrs && b < lb->nr_addrs) {
-		const struct sockaddr_rxrpc *srx_a = &la->addrs[a].srx;
-		const struct sockaddr_rxrpc *srx_b = &lb->addrs[b].srx;
-		int diff = afs_compare_addrs(srx_a, srx_b);
+		unsigned long pa = (unsigned long)la->addrs[a].peer;
+		unsigned long pb = (unsigned long)lb->addrs[b].peer;
+		long diff = pa - pb;
 
 		if (diff < 0) {
 			a++;
diff --git a/fs/afs/vl_list.c b/fs/afs/vl_list.c
index acc48216136a..ba89140eee9e 100644
--- a/fs/afs/vl_list.c
+++ b/fs/afs/vl_list.c
@@ -83,14 +83,15 @@ static u16 afs_extract_le16(const u8 **_b)
 /*
  * Build a VL server address list from a DNS queried server list.
  */
-static struct afs_addr_list *afs_extract_vl_addrs(const u8 **_b, const u8 *end,
+static struct afs_addr_list *afs_extract_vl_addrs(struct afs_net *net,
+						  const u8 **_b, const u8 *end,
 						  u8 nr_addrs, u16 port)
 {
 	struct afs_addr_list *alist;
 	const u8 *b = *_b;
 	int ret = -EINVAL;
 
-	alist = afs_alloc_addrlist(nr_addrs, VL_SERVICE, port);
+	alist = afs_alloc_addrlist(nr_addrs, VL_SERVICE);
 	if (!alist)
 		return ERR_PTR(-ENOMEM);
 	if (nr_addrs == 0)
@@ -109,7 +110,9 @@ static struct afs_addr_list *afs_extract_vl_addrs(const u8 **_b, const u8 *end,
 				goto error;
 			}
 			memcpy(x, b, 4);
-			afs_merge_fs_addr4(alist, x[0], port);
+			ret = afs_merge_fs_addr4(net, alist, x[0], port);
+			if (ret < 0)
+				goto error;
 			b += 4;
 			break;
 
@@ -119,7 +122,9 @@ static struct afs_addr_list *afs_extract_vl_addrs(const u8 **_b, const u8 *end,
 				goto error;
 			}
 			memcpy(x, b, 16);
-			afs_merge_fs_addr6(alist, x, port);
+			ret = afs_merge_fs_addr6(net, alist, x, port);
+			if (ret < 0)
+				goto error;
 			b += 16;
 			break;
 
@@ -247,7 +252,7 @@ struct afs_vlserver_list *afs_extract_vlserver_list(struct afs_cell *cell,
 		/* Extract the addresses - note that we can't skip this as we
 		 * have to advance the payload pointer.
 		 */
-		addrs = afs_extract_vl_addrs(&b, end, bs.nr_addrs, bs.port);
+		addrs = afs_extract_vl_addrs(cell->net, &b, end, bs.nr_addrs, bs.port);
 		if (IS_ERR(addrs)) {
 			ret = PTR_ERR(addrs);
 			goto error_2;
diff --git a/fs/afs/vl_probe.c b/fs/afs/vl_probe.c
index bdd9372e3fb2..9551aef07cee 100644
--- a/fs/afs/vl_probe.c
+++ b/fs/afs/vl_probe.c
@@ -48,6 +48,7 @@ void afs_vlserver_probe_result(struct afs_call *call)
 {
 	struct afs_addr_list *alist = call->alist;
 	struct afs_vlserver *server = call->vlserver;
+	struct afs_address *addr = &alist->addrs[call->addr_ix];
 	unsigned int server_index = call->server_index;
 	unsigned int rtt_us = 0;
 	unsigned int index = call->addr_ix;
@@ -106,16 +107,16 @@ responded:
 	if (call->service_id == YFS_VL_SERVICE) {
 		server->probe.flags |= AFS_VLSERVER_PROBE_IS_YFS;
 		set_bit(AFS_VLSERVER_FL_IS_YFS, &server->flags);
-		alist->addrs[index].srx.srx_service = call->service_id;
+		addr->service_id = call->service_id;
 	} else {
 		server->probe.flags |= AFS_VLSERVER_PROBE_NOT_YFS;
 		if (!(server->probe.flags & AFS_VLSERVER_PROBE_IS_YFS)) {
 			clear_bit(AFS_VLSERVER_FL_IS_YFS, &server->flags);
-			alist->addrs[index].srx.srx_service = call->service_id;
+			addr->service_id = call->service_id;
 		}
 	}
 
-	rxrpc_kernel_get_srtt(call->net->socket, call->rxcall, &rtt_us);
+	rtt_us = rxrpc_kernel_get_srtt(addr->peer);
 	if (rtt_us < server->probe.rtt) {
 		server->probe.rtt = rtt_us;
 		server->rtt = rtt_us;
@@ -130,8 +131,9 @@ responded:
 out:
 	spin_unlock(&server->probe_lock);
 
-	_debug("probe [%u][%u] %pISpc rtt=%u ret=%d",
-	       server_index, index, &alist->addrs[index].srx.transport, rtt_us, ret);
+	_debug("probe [%u][%u] %pISpc rtt=%d ret=%d",
+	       server_index, index, rxrpc_kernel_remote_addr(addr->peer),
+	       rtt_us, ret);
 
 	afs_done_one_vl_probe(server, have_result);
 }
diff --git a/fs/afs/vl_rotate.c b/fs/afs/vl_rotate.c
index e52b9d4c8a0a..f8f255c966ae 100644
--- a/fs/afs/vl_rotate.c
+++ b/fs/afs/vl_rotate.c
@@ -92,7 +92,7 @@ bool afs_select_vlserver(struct afs_vl_cursor *vc)
 	struct afs_addr_list *alist;
 	struct afs_vlserver *vlserver;
 	struct afs_error e;
-	u32 rtt;
+	unsigned int rtt;
 	int error = vc->ac.error, i;
 
 	_enter("%lx[%d],%lx[%d],%d,%d",
@@ -194,7 +194,7 @@ pick_server:
 		goto selected_server;
 
 	vc->index = -1;
-	rtt = U32_MAX;
+	rtt = UINT_MAX;
 	for (i = 0; i < vc->server_list->nr_servers; i++) {
 		struct afs_vlserver *s = vc->server_list->servers[i].server;
 
@@ -249,7 +249,7 @@ iterate_address:
 
 	_debug("VL address %d/%d", vc->ac.index, vc->ac.alist->nr_addrs);
 
-	_leave(" = t %pISpc", &vc->ac.alist->addrs[vc->ac.index].srx.transport);
+	_leave(" = t %pISpc", rxrpc_kernel_remote_addr(vc->ac.alist->addrs[vc->ac.index].peer));
 	return true;
 
 next_server:
diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c
index 00fca3c66ba6..41e7932d75c6 100644
--- a/fs/afs/vlclient.c
+++ b/fs/afs/vlclient.c
@@ -208,7 +208,7 @@ static int afs_deliver_vl_get_addrs_u(struct afs_call *call)
 		count		= ntohl(*bp);
 
 		nentries = min(nentries, count);
-		alist = afs_alloc_addrlist(nentries, FS_SERVICE, AFS_FS_PORT);
+		alist = afs_alloc_addrlist(nentries, FS_SERVICE);
 		if (!alist)
 			return -ENOMEM;
 		alist->version = uniquifier;
@@ -230,9 +230,13 @@ static int afs_deliver_vl_get_addrs_u(struct afs_call *call)
 		alist = call->ret_alist;
 		bp = call->buffer;
 		count = min(call->count, 4U);
-		for (i = 0; i < count; i++)
-			if (alist->nr_addrs < call->count2)
-				afs_merge_fs_addr4(alist, *bp++, AFS_FS_PORT);
+		for (i = 0; i < count; i++) {
+			if (alist->nr_addrs < call->count2) {
+				ret = afs_merge_fs_addr4(call->net, alist, *bp++, AFS_FS_PORT);
+				if (ret < 0)
+					return ret;
+			}
+		}
 
 		call->count -= count;
 		if (call->count > 0)
@@ -450,7 +454,7 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call)
 		if (call->count > YFS_MAXENDPOINTS)
 			return afs_protocol_error(call, afs_eproto_yvl_fsendpt_num);
 
-		alist = afs_alloc_addrlist(call->count, FS_SERVICE, AFS_FS_PORT);
+		alist = afs_alloc_addrlist(call->count, FS_SERVICE);
 		if (!alist)
 			return -ENOMEM;
 		alist->version = uniquifier;
@@ -488,14 +492,18 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call)
 			if (ntohl(bp[0]) != sizeof(__be32) * 2)
 				return afs_protocol_error(
 					call, afs_eproto_yvl_fsendpt4_len);
-			afs_merge_fs_addr4(alist, bp[1], ntohl(bp[2]));
+			ret = afs_merge_fs_addr4(call->net, alist, bp[1], ntohl(bp[2]));
+			if (ret < 0)
+				return ret;
 			bp += 3;
 			break;
 		case YFS_ENDPOINT_IPV6:
 			if (ntohl(bp[0]) != sizeof(__be32) * 5)
 				return afs_protocol_error(
 					call, afs_eproto_yvl_fsendpt6_len);
-			afs_merge_fs_addr6(alist, bp + 1, ntohl(bp[5]));
+			ret = afs_merge_fs_addr6(call->net, alist, bp + 1, ntohl(bp[5]));
+			if (ret < 0)
+				return ret;
 			bp += 6;
 			break;
 		default:
diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h
index 5531dd08061e..0754c463224a 100644
--- a/include/net/af_rxrpc.h
+++ b/include/net/af_rxrpc.h
@@ -15,6 +15,7 @@ struct key;
 struct sock;
 struct socket;
 struct rxrpc_call;
+struct rxrpc_peer;
 enum rxrpc_abort_reason;
 
 enum rxrpc_interruptibility {
@@ -41,13 +42,14 @@ void rxrpc_kernel_new_call_notification(struct socket *,
 					rxrpc_notify_new_call_t,
 					rxrpc_discard_new_call_t);
 struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock,
-					   struct sockaddr_rxrpc *srx,
+					   struct rxrpc_peer *peer,
 					   struct key *key,
 					   unsigned long user_call_ID,
 					   s64 tx_total_len,
 					   u32 hard_timeout,
 					   gfp_t gfp,
 					   rxrpc_notify_rx_t notify_rx,
+					   u16 service_id,
 					   bool upgrade,
 					   enum rxrpc_interruptibility interruptibility,
 					   unsigned int debug_id);
@@ -60,9 +62,14 @@ bool rxrpc_kernel_abort_call(struct socket *, struct rxrpc_call *,
 			     u32, int, enum rxrpc_abort_reason);
 void rxrpc_kernel_shutdown_call(struct socket *sock, struct rxrpc_call *call);
 void rxrpc_kernel_put_call(struct socket *sock, struct rxrpc_call *call);
-void rxrpc_kernel_get_peer(struct socket *, struct rxrpc_call *,
-			   struct sockaddr_rxrpc *);
-bool rxrpc_kernel_get_srtt(struct socket *, struct rxrpc_call *, u32 *);
+struct rxrpc_peer *rxrpc_kernel_lookup_peer(struct socket *sock,
+					    struct sockaddr_rxrpc *srx, gfp_t gfp);
+void rxrpc_kernel_put_peer(struct rxrpc_peer *peer);
+struct rxrpc_peer *rxrpc_kernel_get_peer(struct rxrpc_peer *peer);
+struct rxrpc_peer *rxrpc_kernel_get_call_peer(struct socket *sock, struct rxrpc_call *call);
+const struct sockaddr_rxrpc *rxrpc_kernel_remote_srx(const struct rxrpc_peer *peer);
+const struct sockaddr *rxrpc_kernel_remote_addr(const struct rxrpc_peer *peer);
+unsigned int rxrpc_kernel_get_srtt(const struct rxrpc_peer *);
 int rxrpc_kernel_charge_accept(struct socket *, rxrpc_notify_rx_t,
 			       rxrpc_user_attach_call_t, unsigned long, gfp_t,
 			       unsigned int);
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index f7e537f64db4..4c1ef7b3705c 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -178,7 +178,9 @@
 #define rxrpc_peer_traces \
 	EM(rxrpc_peer_free,			"FREE        ") \
 	EM(rxrpc_peer_get_accept,		"GET accept  ") \
+	EM(rxrpc_peer_get_application,		"GET app     ") \
 	EM(rxrpc_peer_get_bundle,		"GET bundle  ") \
+	EM(rxrpc_peer_get_call,			"GET call    ") \
 	EM(rxrpc_peer_get_client_conn,		"GET cln-conn") \
 	EM(rxrpc_peer_get_input,		"GET input   ") \
 	EM(rxrpc_peer_get_input_error,		"GET inpt-err") \
@@ -187,6 +189,7 @@
 	EM(rxrpc_peer_get_service_conn,		"GET srv-conn") \
 	EM(rxrpc_peer_new_client,		"NEW client  ") \
 	EM(rxrpc_peer_new_prealloc,		"NEW prealloc") \
+	EM(rxrpc_peer_put_application,		"PUT app     ") \
 	EM(rxrpc_peer_put_bundle,		"PUT bundle  ") \
 	EM(rxrpc_peer_put_call,			"PUT call    ") \
 	EM(rxrpc_peer_put_conn,			"PUT conn    ") \
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index fa8aec78f63d..465bfe5eb061 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -258,16 +258,62 @@ static int rxrpc_listen(struct socket *sock, int backlog)
 	return ret;
 }
 
+/**
+ * rxrpc_kernel_lookup_peer - Obtain remote transport endpoint for an address
+ * @sock: The socket through which it will be accessed
+ * @srx: The network address
+ * @gfp: Allocation flags
+ *
+ * Lookup or create a remote transport endpoint record for the specified
+ * address and return it with a ref held.
+ */
+struct rxrpc_peer *rxrpc_kernel_lookup_peer(struct socket *sock,
+					    struct sockaddr_rxrpc *srx, gfp_t gfp)
+{
+	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
+	int ret;
+
+	ret = rxrpc_validate_address(rx, srx, sizeof(*srx));
+	if (ret < 0)
+		return ERR_PTR(ret);
+
+	return rxrpc_lookup_peer(rx->local, srx, gfp);
+}
+EXPORT_SYMBOL(rxrpc_kernel_lookup_peer);
+
+/**
+ * rxrpc_kernel_get_peer - Get a reference on a peer
+ * @peer: The peer to get a reference on.
+ *
+ * Get a record for the remote peer in a call.
+ */
+struct rxrpc_peer *rxrpc_kernel_get_peer(struct rxrpc_peer *peer)
+{
+	return peer ? rxrpc_get_peer(peer, rxrpc_peer_get_application) : NULL;
+}
+EXPORT_SYMBOL(rxrpc_kernel_get_peer);
+
+/**
+ * rxrpc_kernel_put_peer - Allow a kernel app to drop a peer reference
+ * @peer: The peer to drop a ref on
+ */
+void rxrpc_kernel_put_peer(struct rxrpc_peer *peer)
+{
+	rxrpc_put_peer(peer, rxrpc_peer_put_application);
+}
+EXPORT_SYMBOL(rxrpc_kernel_put_peer);
+
 /**
  * rxrpc_kernel_begin_call - Allow a kernel service to begin a call
  * @sock: The socket on which to make the call
- * @srx: The address of the peer to contact
+ * @peer: The peer to contact
  * @key: The security context to use (defaults to socket setting)
  * @user_call_ID: The ID to use
  * @tx_total_len: Total length of data to transmit during the call (or -1)
  * @hard_timeout: The maximum lifespan of the call in sec
  * @gfp: The allocation constraints
  * @notify_rx: Where to send notifications instead of socket queue
+ * @service_id: The ID of the service to contact
  * @upgrade: Request service upgrade for call
  * @interruptibility: The call is interruptible, or can be canceled.
  * @debug_id: The debug ID for tracing to be assigned to the call
@@ -280,13 +326,14 @@ static int rxrpc_listen(struct socket *sock, int backlog)
  * supplying @srx and @key.
  */
 struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock,
-					   struct sockaddr_rxrpc *srx,
+					   struct rxrpc_peer *peer,
 					   struct key *key,
 					   unsigned long user_call_ID,
 					   s64 tx_total_len,
 					   u32 hard_timeout,
 					   gfp_t gfp,
 					   rxrpc_notify_rx_t notify_rx,
+					   u16 service_id,
 					   bool upgrade,
 					   enum rxrpc_interruptibility interruptibility,
 					   unsigned int debug_id)
@@ -295,13 +342,11 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock,
 	struct rxrpc_call_params p;
 	struct rxrpc_call *call;
 	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
-	int ret;
 
 	_enter(",,%x,%lx", key_serial(key), user_call_ID);
 
-	ret = rxrpc_validate_address(rx, srx, sizeof(*srx));
-	if (ret < 0)
-		return ERR_PTR(ret);
+	if (WARN_ON_ONCE(peer->local != rx->local))
+		return ERR_PTR(-EIO);
 
 	lock_sock(&rx->sk);
 
@@ -319,12 +364,13 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock,
 
 	memset(&cp, 0, sizeof(cp));
 	cp.local		= rx->local;
+	cp.peer			= peer;
 	cp.key			= key;
 	cp.security_level	= rx->min_sec_level;
 	cp.exclusive		= false;
 	cp.upgrade		= upgrade;
-	cp.service_id		= srx->srx_service;
-	call = rxrpc_new_client_call(rx, &cp, srx, &p, gfp, debug_id);
+	cp.service_id		= service_id;
+	call = rxrpc_new_client_call(rx, &cp, &p, gfp, debug_id);
 	/* The socket has been unlocked. */
 	if (!IS_ERR(call)) {
 		call->notify_rx = notify_rx;
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index e8e14c6f904d..8eea7a487380 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -364,6 +364,7 @@ struct rxrpc_conn_proto {
 
 struct rxrpc_conn_parameters {
 	struct rxrpc_local	*local;		/* Representation of local endpoint */
+	struct rxrpc_peer	*peer;		/* Representation of remote endpoint */
 	struct key		*key;		/* Security details */
 	bool			exclusive;	/* T if conn is exclusive */
 	bool			upgrade;	/* T if service ID can be upgraded */
@@ -867,7 +868,6 @@ struct rxrpc_call *rxrpc_find_call_by_user_ID(struct rxrpc_sock *, unsigned long
 struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *, gfp_t, unsigned int);
 struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *,
 					 struct rxrpc_conn_parameters *,
-					 struct sockaddr_rxrpc *,
 					 struct rxrpc_call_params *, gfp_t,
 					 unsigned int);
 void rxrpc_start_call_timer(struct rxrpc_call *call);
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 773eecd1e979..beea25ac88f5 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -193,7 +193,6 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp,
  * Allocate a new client call.
  */
 static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx,
-						  struct sockaddr_rxrpc *srx,
 						  struct rxrpc_conn_parameters *cp,
 						  struct rxrpc_call_params *p,
 						  gfp_t gfp,
@@ -211,10 +210,12 @@ static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx,
 	now = ktime_get_real();
 	call->acks_latest_ts	= now;
 	call->cong_tstamp	= now;
-	call->dest_srx		= *srx;
+	call->dest_srx		= cp->peer->srx;
+	call->dest_srx.srx_service = cp->service_id;
 	call->interruptibility	= p->interruptibility;
 	call->tx_total_len	= p->tx_total_len;
 	call->key		= key_get(cp->key);
+	call->peer		= rxrpc_get_peer(cp->peer, rxrpc_peer_get_call);
 	call->local		= rxrpc_get_local(cp->local, rxrpc_local_get_call);
 	call->security_level	= cp->security_level;
 	if (p->kernel)
@@ -306,10 +307,6 @@ static int rxrpc_connect_call(struct rxrpc_call *call, gfp_t gfp)
 
 	_enter("{%d,%lx},", call->debug_id, call->user_call_ID);
 
-	call->peer = rxrpc_lookup_peer(local, &call->dest_srx, gfp);
-	if (!call->peer)
-		goto error;
-
 	ret = rxrpc_look_up_bundle(call, gfp);
 	if (ret < 0)
 		goto error;
@@ -334,7 +331,6 @@ error:
  */
 struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
 					 struct rxrpc_conn_parameters *cp,
-					 struct sockaddr_rxrpc *srx,
 					 struct rxrpc_call_params *p,
 					 gfp_t gfp,
 					 unsigned int debug_id)
@@ -349,13 +345,18 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
 
 	_enter("%p,%lx", rx, p->user_call_ID);
 
+	if (WARN_ON_ONCE(!cp->peer)) {
+		release_sock(&rx->sk);
+		return ERR_PTR(-EIO);
+	}
+
 	limiter = rxrpc_get_call_slot(p, gfp);
 	if (!limiter) {
 		release_sock(&rx->sk);
 		return ERR_PTR(-ERESTARTSYS);
 	}
 
-	call = rxrpc_alloc_client_call(rx, srx, cp, p, gfp, debug_id);
+	call = rxrpc_alloc_client_call(rx, cp, p, gfp, debug_id);
 	if (IS_ERR(call)) {
 		release_sock(&rx->sk);
 		up(limiter);
diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
index 8d7a715a0bb1..49dcda67a0d5 100644
--- a/net/rxrpc/peer_object.c
+++ b/net/rxrpc/peer_object.c
@@ -22,6 +22,8 @@
 #include <net/ip6_route.h>
 #include "ar-internal.h"
 
+static const struct sockaddr_rxrpc rxrpc_null_addr;
+
 /*
  * Hash a peer key.
  */
@@ -457,39 +459,53 @@ void rxrpc_destroy_all_peers(struct rxrpc_net *rxnet)
 }
 
 /**
- * rxrpc_kernel_get_peer - Get the peer address of a call
+ * rxrpc_kernel_get_call_peer - Get the peer address of a call
  * @sock: The socket on which the call is in progress.
  * @call: The call to query
- * @_srx: Where to place the result
  *
- * Get the address of the remote peer in a call.
+ * Get a record for the remote peer in a call.
  */
-void rxrpc_kernel_get_peer(struct socket *sock, struct rxrpc_call *call,
-			   struct sockaddr_rxrpc *_srx)
+struct rxrpc_peer *rxrpc_kernel_get_call_peer(struct socket *sock, struct rxrpc_call *call)
 {
-	*_srx = call->peer->srx;
+	return call->peer;
 }
-EXPORT_SYMBOL(rxrpc_kernel_get_peer);
+EXPORT_SYMBOL(rxrpc_kernel_get_call_peer);
 
 /**
  * rxrpc_kernel_get_srtt - Get a call's peer smoothed RTT
- * @sock: The socket on which the call is in progress.
- * @call: The call to query
- * @_srtt: Where to store the SRTT value.
+ * @peer: The peer to query
  *
- * Get the call's peer smoothed RTT in uS.
+ * Get the call's peer smoothed RTT in uS or UINT_MAX if we have no samples.
  */
-bool rxrpc_kernel_get_srtt(struct socket *sock, struct rxrpc_call *call,
-			   u32 *_srtt)
+unsigned int rxrpc_kernel_get_srtt(const struct rxrpc_peer *peer)
 {
-	struct rxrpc_peer *peer = call->peer;
+	return peer->rtt_count > 0 ? peer->srtt_us >> 3 : UINT_MAX;
+}
+EXPORT_SYMBOL(rxrpc_kernel_get_srtt);
 
-	if (peer->rtt_count == 0) {
-		*_srtt = 1000000; /* 1S */
-		return false;
-	}
+/**
+ * rxrpc_kernel_remote_srx - Get the address of a peer
+ * @peer: The peer to query
+ *
+ * Get a pointer to the address from a peer record.  The caller is responsible
+ * for making sure that the address is not deallocated.
+ */
+const struct sockaddr_rxrpc *rxrpc_kernel_remote_srx(const struct rxrpc_peer *peer)
+{
+	return peer ? &peer->srx : &rxrpc_null_addr;
+}
+EXPORT_SYMBOL(rxrpc_kernel_remote_srx);
 
-	*_srtt = call->peer->srtt_us >> 3;
-	return true;
+/**
+ * rxrpc_kernel_remote_addr - Get the peer transport address of a call
+ * @peer: The peer to query
+ *
+ * Get a pointer to the transport address from a peer record.  The caller is
+ * responsible for making sure that the address is not deallocated.
+ */
+const struct sockaddr *rxrpc_kernel_remote_addr(const struct rxrpc_peer *peer)
+{
+	return (const struct sockaddr *)
+		(peer ? &peer->srx.transport : &rxrpc_null_addr.transport);
 }
-EXPORT_SYMBOL(rxrpc_kernel_get_srtt);
+EXPORT_SYMBOL(rxrpc_kernel_remote_addr);
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 8e0b94714e84..5677d5690a02 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -572,6 +572,7 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg,
 	__acquires(&call->user_mutex)
 {
 	struct rxrpc_conn_parameters cp;
+	struct rxrpc_peer *peer;
 	struct rxrpc_call *call;
 	struct key *key;
 
@@ -584,21 +585,29 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg,
 		return ERR_PTR(-EDESTADDRREQ);
 	}
 
+	peer = rxrpc_lookup_peer(rx->local, srx, GFP_KERNEL);
+	if (!peer) {
+		release_sock(&rx->sk);
+		return ERR_PTR(-ENOMEM);
+	}
+
 	key = rx->key;
 	if (key && !rx->key->payload.data[0])
 		key = NULL;
 
 	memset(&cp, 0, sizeof(cp));
 	cp.local		= rx->local;
+	cp.peer			= peer;
 	cp.key			= rx->key;
 	cp.security_level	= rx->min_sec_level;
 	cp.exclusive		= rx->exclusive | p->exclusive;
 	cp.upgrade		= p->upgrade;
 	cp.service_id		= srx->srx_service;
-	call = rxrpc_new_client_call(rx, &cp, srx, &p->call, GFP_KERNEL,
+	call = rxrpc_new_client_call(rx, &cp, &p->call, GFP_KERNEL,
 				     atomic_inc_return(&rxrpc_debug_id));
 	/* The socket is now unlocked */
 
+	rxrpc_put_peer(peer, rxrpc_peer_put_application);
 	_leave(" = %p\n", call);
 	return call;
 }
-- 
cgit v1.2.3


From 1e5d8493254db9b28d4dce4fed87e56d9a2fefa5 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 19 Oct 2023 13:59:03 +0100
Subject: afs: Add a tracepoint for struct afs_addr_list

Add a tracepoint to track the lifetime of the afs_addr_list struct.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
---
 fs/afs/addr_list.c         | 33 ++++++++++++++++++++++++++++----
 fs/afs/fs_probe.c          |  4 ++--
 fs/afs/internal.h          | 10 +++-------
 fs/afs/rotate.c            |  4 ++--
 fs/afs/rxrpc.c             |  4 ++--
 fs/afs/server.c            |  9 +++++----
 fs/afs/vl_list.c           | 11 ++++++-----
 fs/afs/vl_rotate.c         |  9 ++-------
 fs/afs/vlclient.c          |  4 ++--
 include/trace/events/afs.h | 47 ++++++++++++++++++++++++++++++++++++++++++++++
 10 files changed, 100 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/fs/afs/addr_list.c b/fs/afs/addr_list.c
index a1f3c995e328..41ef0c879239 100644
--- a/fs/afs/addr_list.c
+++ b/fs/afs/addr_list.c
@@ -20,17 +20,39 @@ static void afs_free_addrlist(struct rcu_head *rcu)
 
 	for (i = 0; i < alist->nr_addrs; i++)
 		rxrpc_kernel_put_peer(alist->addrs[i].peer);
+	trace_afs_alist(alist->debug_id, refcount_read(&alist->usage), afs_alist_trace_free);
+	kfree(alist);
 }
 
 /*
  * Release an address list.
  */
-void afs_put_addrlist(struct afs_addr_list *alist)
+void afs_put_addrlist(struct afs_addr_list *alist, enum afs_alist_trace reason)
 {
-	if (alist && refcount_dec_and_test(&alist->usage))
+	unsigned int debug_id;
+	bool dead;
+	int r;
+
+	if (!alist)
+		return;
+	debug_id = alist->debug_id;
+	dead = __refcount_dec_and_test(&alist->usage, &r);
+	trace_afs_alist(debug_id, r - 1, reason);
+	if (dead)
 		call_rcu(&alist->rcu, afs_free_addrlist);
 }
 
+struct afs_addr_list *afs_get_addrlist(struct afs_addr_list *alist, enum afs_alist_trace reason)
+{
+	int r;
+
+	if (alist) {
+		__refcount_inc(&alist->usage, &r);
+		trace_afs_alist(alist->debug_id, r + 1, reason);
+	}
+	return alist;
+}
+
 /*
  * Allocate an address list.
  */
@@ -38,6 +60,7 @@ struct afs_addr_list *afs_alloc_addrlist(unsigned int nr, u16 service_id)
 {
 	struct afs_addr_list *alist;
 	unsigned int i;
+	static atomic_t debug_id;
 
 	_enter("%u,%u", nr, service_id);
 
@@ -50,9 +73,11 @@ struct afs_addr_list *afs_alloc_addrlist(unsigned int nr, u16 service_id)
 
 	refcount_set(&alist->usage, 1);
 	alist->max_addrs = nr;
+	alist->debug_id = atomic_inc_return(&debug_id);
 
 	for (i = 0; i < nr; i++)
 		alist->addrs[i].service_id = service_id;
+	trace_afs_alist(alist->debug_id, 1, afs_alist_trace_alloc);
 	return alist;
 }
 
@@ -217,7 +242,7 @@ bad_address:
 	       problem, p - text, (int)len, (int)len, text);
 	ret = -EINVAL;
 error:
-	afs_put_addrlist(alist);
+	afs_put_addrlist(alist, afs_alist_trace_put_parse_error);
 error_vl:
 	afs_put_vlserverlist(net, vllist);
 	return ERR_PTR(ret);
@@ -403,7 +428,7 @@ void afs_end_cursor(struct afs_addr_cursor *ac)
 		    ac->index != alist->preferred &&
 		    test_bit(ac->alist->preferred, &ac->tried))
 			WRITE_ONCE(alist->preferred, ac->index);
-		afs_put_addrlist(alist);
+		afs_put_addrlist(alist, afs_alist_trace_put_end_cursor);
 		ac->alist = NULL;
 	}
 }
diff --git a/fs/afs/fs_probe.c b/fs/afs/fs_probe.c
index fbb91ad775b9..18891492c0b4 100644
--- a/fs/afs/fs_probe.c
+++ b/fs/afs/fs_probe.c
@@ -205,7 +205,7 @@ void afs_fs_probe_fileserver(struct afs_net *net, struct afs_server *server,
 	read_lock(&server->fs_lock);
 	ac.alist = rcu_dereference_protected(server->addresses,
 					     lockdep_is_held(&server->fs_lock));
-	afs_get_addrlist(ac.alist);
+	afs_get_addrlist(ac.alist, afs_alist_trace_get_probe);
 	read_unlock(&server->fs_lock);
 
 	server->probed_at = jiffies;
@@ -226,7 +226,7 @@ void afs_fs_probe_fileserver(struct afs_net *net, struct afs_server *server,
 			afs_fs_probe_not_done(net, server, &ac);
 	}
 
-	afs_put_addrlist(ac.alist);
+	afs_put_addrlist(ac.alist, afs_alist_trace_put_probe);
 }
 
 /*
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index d67c75d4d2bd..d00fda99f401 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -85,6 +85,7 @@ struct afs_addr_list {
 	struct rcu_head		rcu;
 	refcount_t		usage;
 	u32			version;	/* Version */
+	unsigned int		debug_id;
 	unsigned char		max_addrs;
 	unsigned char		nr_addrs;
 	unsigned char		preferred;	/* Preferred address */
@@ -969,14 +970,9 @@ static inline bool afs_is_folio_dirty_mmapped(unsigned long priv)
 /*
  * addr_list.c
  */
-static inline struct afs_addr_list *afs_get_addrlist(struct afs_addr_list *alist)
-{
-	if (alist)
-		refcount_inc(&alist->usage);
-	return alist;
-}
+struct afs_addr_list *afs_get_addrlist(struct afs_addr_list *alist, enum afs_alist_trace reason);
 extern struct afs_addr_list *afs_alloc_addrlist(unsigned int nr, u16 service_id);
-extern void afs_put_addrlist(struct afs_addr_list *);
+extern void afs_put_addrlist(struct afs_addr_list *alist, enum afs_alist_trace reason);
 extern struct afs_vlserver_list *afs_parse_text_addrs(struct afs_net *,
 						      const char *, size_t, char,
 						      unsigned short, unsigned short);
diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c
index a778d53681fe..fa2ba45a5941 100644
--- a/fs/afs/rotate.c
+++ b/fs/afs/rotate.c
@@ -484,7 +484,7 @@ selected_server:
 	read_lock(&server->fs_lock);
 	alist = rcu_dereference_protected(server->addresses,
 					  lockdep_is_held(&server->fs_lock));
-	afs_get_addrlist(alist);
+	afs_get_addrlist(alist, afs_alist_trace_get_fsrotate_set);
 	read_unlock(&server->fs_lock);
 
 retry_server:
@@ -493,7 +493,7 @@ retry_server:
 	if (!op->ac.alist)
 		op->ac.alist = alist;
 	else
-		afs_put_addrlist(alist);
+		afs_put_addrlist(alist, afs_alist_trace_put_retry_server);
 
 	op->ac.index = -1;
 
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index 0b3e2f20b0e0..5bbf5a23af85 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -187,7 +187,7 @@ void afs_put_call(struct afs_call *call)
 			call->type->destructor(call);
 
 		afs_unuse_server_notime(call->net, call->server, afs_server_trace_put_call);
-		afs_put_addrlist(call->alist);
+		afs_put_addrlist(call->alist, afs_alist_trace_put_call);
 		kfree(call->request);
 
 		trace_afs_call(call->debug_id, afs_call_trace_free, 0, o,
@@ -315,7 +315,7 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp)
 	       atomic_read(&call->net->nr_outstanding_calls));
 
 	call->addr_ix = ac->index;
-	call->alist = afs_get_addrlist(ac->alist);
+	call->alist = afs_get_addrlist(ac->alist, afs_alist_trace_get_make_call);
 
 	/* Work out the length we're going to transmit.  This is awkward for
 	 * calls such as FS.StoreData where there's an extra injection of data
diff --git a/fs/afs/server.c b/fs/afs/server.c
index f7791ef13618..6c13f00b10d8 100644
--- a/fs/afs/server.c
+++ b/fs/afs/server.c
@@ -275,13 +275,13 @@ struct afs_server *afs_lookup_server(struct afs_cell *cell, struct key *key,
 
 	candidate = afs_alloc_server(cell, uuid, alist);
 	if (!candidate) {
-		afs_put_addrlist(alist);
+		afs_put_addrlist(alist, afs_alist_trace_put_server_oom);
 		return ERR_PTR(-ENOMEM);
 	}
 
 	server = afs_install_server(cell, candidate);
 	if (server != candidate) {
-		afs_put_addrlist(alist);
+		afs_put_addrlist(alist, afs_alist_trace_put_server_dup);
 		kfree(candidate);
 	} else {
 		/* Immediately dispatch an asynchronous probe to each interface
@@ -421,7 +421,8 @@ static void afs_server_rcu(struct rcu_head *rcu)
 
 	trace_afs_server(server->debug_id, refcount_read(&server->ref),
 			 atomic_read(&server->active), afs_server_trace_free);
-	afs_put_addrlist(rcu_access_pointer(server->addresses));
+	afs_put_addrlist(rcu_access_pointer(server->addresses),
+			 afs_alist_trace_put_server);
 	kfree(server);
 }
 
@@ -643,7 +644,7 @@ static noinline bool afs_update_server_record(struct afs_operation *op,
 		write_unlock(&server->fs_lock);
 	}
 
-	afs_put_addrlist(discard);
+	afs_put_addrlist(discard, afs_alist_trace_put_server_update);
 	_leave(" = t");
 	return true;
 }
diff --git a/fs/afs/vl_list.c b/fs/afs/vl_list.c
index ba89140eee9e..3a2875933261 100644
--- a/fs/afs/vl_list.c
+++ b/fs/afs/vl_list.c
@@ -33,7 +33,8 @@ static void afs_vlserver_rcu(struct rcu_head *rcu)
 {
 	struct afs_vlserver *vlserver = container_of(rcu, struct afs_vlserver, rcu);
 
-	afs_put_addrlist(rcu_access_pointer(vlserver->addresses));
+	afs_put_addrlist(rcu_access_pointer(vlserver->addresses),
+			 afs_alist_trace_put_vlserver);
 	kfree_rcu(vlserver, rcu);
 }
 
@@ -145,7 +146,7 @@ static struct afs_addr_list *afs_extract_vl_addrs(struct afs_net *net,
 
 error:
 	*_b = b;
-	afs_put_addrlist(alist);
+	afs_put_addrlist(alist, afs_alist_trace_put_parse_error);
 	return ERR_PTR(ret);
 }
 
@@ -260,7 +261,7 @@ struct afs_vlserver_list *afs_extract_vlserver_list(struct afs_cell *cell,
 
 		if (vllist->nr_servers >= nr_servers) {
 			_debug("skip %u >= %u", vllist->nr_servers, nr_servers);
-			afs_put_addrlist(addrs);
+			afs_put_addrlist(addrs, afs_alist_trace_put_parse_empty);
 			afs_put_vlserver(cell->net, server);
 			continue;
 		}
@@ -269,7 +270,7 @@ struct afs_vlserver_list *afs_extract_vlserver_list(struct afs_cell *cell,
 		addrs->status = bs.status;
 
 		if (addrs->nr_addrs == 0) {
-			afs_put_addrlist(addrs);
+			afs_put_addrlist(addrs, afs_alist_trace_put_parse_empty);
 			if (!rcu_access_pointer(server->addresses)) {
 				afs_put_vlserver(cell->net, server);
 				continue;
@@ -281,7 +282,7 @@ struct afs_vlserver_list *afs_extract_vlserver_list(struct afs_cell *cell,
 			old = rcu_replace_pointer(server->addresses, old,
 						  lockdep_is_held(&server->lock));
 			write_unlock(&server->lock);
-			afs_put_addrlist(old);
+			afs_put_addrlist(old, afs_alist_trace_put_vlserver_old);
 		}
 
 
diff --git a/fs/afs/vl_rotate.c b/fs/afs/vl_rotate.c
index 7ae73418697d..e8fbbeb551bb 100644
--- a/fs/afs/vl_rotate.c
+++ b/fs/afs/vl_rotate.c
@@ -231,16 +231,11 @@ selected_server:
 	read_lock(&vlserver->lock);
 	alist = rcu_dereference_protected(vlserver->addresses,
 					  lockdep_is_held(&vlserver->lock));
-	afs_get_addrlist(alist);
+	afs_get_addrlist(alist, afs_alist_trace_get_vlrotate_set);
 	read_unlock(&vlserver->lock);
 
 	memset(&vc->ac, 0, sizeof(vc->ac));
-
-	if (!vc->ac.alist)
-		vc->ac.alist = alist;
-	else
-		afs_put_addrlist(alist);
-
+	vc->ac.alist = alist;
 	vc->ac.index = -1;
 
 iterate_address:
diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c
index db7e94584e87..8dea7b56b75a 100644
--- a/fs/afs/vlclient.c
+++ b/fs/afs/vlclient.c
@@ -314,7 +314,7 @@ struct afs_addr_list *afs_vl_get_addrs_u(struct afs_vl_cursor *vc,
 	alist			= call->ret_alist;
 	afs_put_call(call);
 	if (vc->call_error) {
-		afs_put_addrlist(alist);
+		afs_put_addrlist(alist, afs_alist_trace_put_getaddru);
 		return ERR_PTR(vc->call_error);
 	}
 	return alist;
@@ -668,7 +668,7 @@ struct afs_addr_list *afs_yfsvl_get_endpoints(struct afs_vl_cursor *vc,
 	alist			= call->ret_alist;
 	afs_put_call(call);
 	if (vc->call_error) {
-		afs_put_addrlist(alist);
+		afs_put_addrlist(alist, afs_alist_trace_put_getaddru);
 		return ERR_PTR(vc->call_error);
 	}
 	return alist;
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index 597677acc6b1..ed91666ca4cc 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -202,6 +202,27 @@ enum yfs_cm_operation {
 	EM(afs_cell_trace_use_sbi,		"USE sbi   ") \
 	E_(afs_cell_trace_wait,			"WAIT      ")
 
+#define afs_alist_traces \
+	EM(afs_alist_trace_alloc,		"ALLOC     ") \
+	EM(afs_alist_trace_get_fsrotate_set,	"GET fs-rot") \
+	EM(afs_alist_trace_get_make_call,	"GET mkcall") \
+	EM(afs_alist_trace_get_probe,		"GET probe ") \
+	EM(afs_alist_trace_get_vlrotate_set,	"GET vl-rot") \
+	EM(afs_alist_trace_put_call,		"PUT call  ") \
+	EM(afs_alist_trace_put_end_cursor,	"PUT endcur") \
+	EM(afs_alist_trace_put_getaddru,	"PUT GtAdrU") \
+	EM(afs_alist_trace_put_parse_empty,	"PUT p-empt") \
+	EM(afs_alist_trace_put_parse_error,	"PUT p-err ") \
+	EM(afs_alist_trace_put_probe,		"PUT probe ") \
+	EM(afs_alist_trace_put_retry_server,	"PUT retry ") \
+	EM(afs_alist_trace_put_server,		"PUT server") \
+	EM(afs_alist_trace_put_server_dup,	"PUT sv-dup") \
+	EM(afs_alist_trace_put_server_oom,	"PUT sv-oom") \
+	EM(afs_alist_trace_put_server_update,	"PUT sv-upd") \
+	EM(afs_alist_trace_put_vlserver,	"PUT vlsrvr") \
+	EM(afs_alist_trace_put_vlserver_old,	"PUT vs-old") \
+	E_(afs_alist_trace_free,		"FREE      ")
+
 #define afs_fs_operations \
 	EM(afs_FS_FetchData,			"FS.FetchData") \
 	EM(afs_FS_FetchStatus,			"FS.FetchStatus") \
@@ -420,6 +441,7 @@ enum yfs_cm_operation {
 #define EM(a, b) a,
 #define E_(a, b) a
 
+enum afs_alist_trace		{ afs_alist_traces } __mode(byte);
 enum afs_call_trace		{ afs_call_traces } __mode(byte);
 enum afs_cb_break_reason	{ afs_cb_break_reasons } __mode(byte);
 enum afs_cell_trace		{ afs_cell_traces } __mode(byte);
@@ -443,6 +465,7 @@ enum afs_volume_trace		{ afs_volume_traces } __mode(byte);
 #define EM(a, b) TRACE_DEFINE_ENUM(a);
 #define E_(a, b) TRACE_DEFINE_ENUM(a);
 
+afs_alist_traces;
 afs_call_traces;
 afs_server_traces;
 afs_cell_traces;
@@ -1330,6 +1353,30 @@ TRACE_EVENT(afs_cell,
 		      __entry->active)
 	    );
 
+TRACE_EVENT(afs_alist,
+	    TP_PROTO(unsigned int alist_debug_id, int ref, enum afs_alist_trace reason),
+
+	    TP_ARGS(alist_debug_id, ref, reason),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,		alist)
+		    __field(int,			ref)
+		    __field(int,			active)
+		    __field(int,			reason)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->alist = alist_debug_id;
+		    __entry->ref = ref;
+		    __entry->reason = reason;
+			   ),
+
+	    TP_printk("AL=%08x %s r=%d",
+		      __entry->alist,
+		      __print_symbolic(__entry->reason, afs_alist_traces),
+		      __entry->ref)
+	    );
+
 #endif /* _TRACE_AFS_H */
 
 /* This part must be outside protection */
-- 
cgit v1.2.3


From 98f9fda2057ba34b720c4d353351024d6dcee90f Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 20 Oct 2023 16:13:03 +0100
Subject: afs: Fold the afs_addr_cursor struct in

Fold the afs_addr_cursor struct into the afs_operation struct and the
afs_vl_cursor struct and fold its operations into their callers also.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
---
 fs/afs/addr_list.c         | 53 ----------------------------
 fs/afs/fs_operation.c      | 21 ++++++++---
 fs/afs/fs_probe.c          | 41 ++++++++++-----------
 fs/afs/fsclient.c          | 31 ++++++++++------
 fs/afs/internal.h          | 58 +++++++++++++++---------------
 fs/afs/rotate.c            | 71 +++++++++++++++++++++++--------------
 fs/afs/rxrpc.c             | 13 ++-----
 fs/afs/server.c            |  6 +---
 fs/afs/vl_probe.c          | 23 ++++++------
 fs/afs/vl_rotate.c         | 88 ++++++++++++++++++++++++++++++++++------------
 fs/afs/vlclient.c          | 34 ++++++++++--------
 include/trace/events/afs.h | 18 +++++++---
 12 files changed, 243 insertions(+), 214 deletions(-)

(limited to 'include')

diff --git a/fs/afs/addr_list.c b/fs/afs/addr_list.c
index 032e6963c5d8..18c286efa3a5 100644
--- a/fs/afs/addr_list.c
+++ b/fs/afs/addr_list.c
@@ -375,56 +375,3 @@ int afs_merge_fs_addr6(struct afs_net *net, struct afs_addr_list *alist,
 	alist->nr_addrs++;
 	return 0;
 }
-
-/*
- * Get an address to try.
- */
-bool afs_iterate_addresses(struct afs_addr_cursor *ac)
-{
-	unsigned long set, failed;
-	int index;
-
-	if (!ac->alist)
-		return false;
-
-	set = ac->alist->responded;
-	failed = ac->alist->probe_failed;
-	_enter("%lx-%lx-%lx,%d", set, failed, ac->tried, ac->index);
-
-	ac->nr_iterations++;
-
-	set &= ~(failed | ac->tried);
-
-	if (!set)
-		return false;
-
-	index = READ_ONCE(ac->alist->preferred);
-	if (test_bit(index, &set))
-		goto selected;
-
-	index = __ffs(set);
-
-selected:
-	ac->index = index;
-	set_bit(index, &ac->tried);
-	ac->call_responded = false;
-	return true;
-}
-
-/*
- * Release an address list cursor.
- */
-void afs_end_cursor(struct afs_addr_cursor *ac)
-{
-	struct afs_addr_list *alist;
-
-	alist = ac->alist;
-	if (alist) {
-		if (ac->call_responded &&
-		    ac->index != alist->preferred &&
-		    test_bit(ac->alist->preferred, &ac->tried))
-			WRITE_ONCE(alist->preferred, ac->index);
-		afs_put_addrlist(alist, afs_alist_trace_put_end_cursor);
-		ac->alist = NULL;
-	}
-}
diff --git a/fs/afs/fs_operation.c b/fs/afs/fs_operation.c
index cebe4fad8192..00e22259be36 100644
--- a/fs/afs/fs_operation.c
+++ b/fs/afs/fs_operation.c
@@ -179,6 +179,7 @@ void afs_wait_for_operation(struct afs_operation *op)
 	_enter("");
 
 	while (afs_select_fileserver(op)) {
+		op->call_responded = false;
 		op->call_error = 0;
 		op->call_abort_code = 0;
 		op->cb_s_break = op->server->cb_s_break;
@@ -191,17 +192,19 @@ void afs_wait_for_operation(struct afs_operation *op)
 			op->call_error = -ENOTSUPP;
 
 		if (op->call) {
-			afs_wait_for_call_to_complete(op->call, &op->ac);
+			afs_wait_for_call_to_complete(op->call);
 			op->call_abort_code = op->call->abort_code;
 			op->call_error = op->call->error;
 			op->call_responded = op->call->responded;
-			op->ac.call_responded = true;
-			WRITE_ONCE(op->ac.alist->addrs[op->ac.index].last_error,
+			WRITE_ONCE(op->alist->addrs[op->addr_index].last_error,
 				   op->call_error);
 			afs_put_call(op->call);
 		}
 	}
 
+	if (op->call_responded)
+		set_bit(AFS_SERVER_FL_RESPONDING, &op->server->flags);
+
 	if (!afs_op_error(op)) {
 		_debug("success");
 		op->ops->success(op);
@@ -227,6 +230,7 @@ void afs_wait_for_operation(struct afs_operation *op)
  */
 int afs_put_operation(struct afs_operation *op)
 {
+	struct afs_addr_list *alist;
 	int i, ret = afs_op_error(op);
 
 	_enter("op=%08x,%d", op->debug_id, ret);
@@ -249,7 +253,16 @@ int afs_put_operation(struct afs_operation *op)
 		kfree(op->more_files);
 	}
 
-	afs_end_cursor(&op->ac);
+	alist = op->alist;
+	if (alist) {
+		if (op->call_responded &&
+		    op->addr_index != alist->preferred &&
+		    test_bit(alist->preferred, &op->addr_tried))
+			WRITE_ONCE(alist->preferred, op->addr_index);
+		afs_put_addrlist(alist, afs_alist_trace_put_operation);
+		op->alist = NULL;
+	}
+
 	afs_put_serverlist(op->net, op->server_list);
 	afs_put_volume(op->net, op->volume, afs_volume_trace_put_put_op);
 	key_put(op->key);
diff --git a/fs/afs/fs_probe.c b/fs/afs/fs_probe.c
index 337673e65f87..aef16ac3f577 100644
--- a/fs/afs/fs_probe.c
+++ b/fs/afs/fs_probe.c
@@ -74,11 +74,9 @@ static void afs_done_one_fs_probe(struct afs_net *net, struct afs_server *server
  */
 static void afs_fs_probe_not_done(struct afs_net *net,
 				  struct afs_server *server,
-				  struct afs_addr_cursor *ac)
+				  struct afs_addr_list *alist,
+				  int index)
 {
-	struct afs_addr_list *alist = ac->alist;
-	unsigned int index = ac->index;
-
 	_enter("");
 
 	trace_afs_io_error(0, -ENOMEM, afs_io_error_fs_probe_fail);
@@ -100,10 +98,10 @@ static void afs_fs_probe_not_done(struct afs_net *net,
  */
 void afs_fileserver_probe_result(struct afs_call *call)
 {
-	struct afs_addr_list *alist = call->alist;
-	struct afs_address *addr = &alist->addrs[call->addr_ix];
+	struct afs_addr_list *alist = call->probe_alist;
+	struct afs_address *addr = &alist->addrs[call->probe_index];
 	struct afs_server *server = call->server;
-	unsigned int index = call->addr_ix;
+	unsigned int index = call->probe_index;
 	unsigned int rtt_us = 0, cap0;
 	int ret = call->error;
 
@@ -196,37 +194,36 @@ out:
 void afs_fs_probe_fileserver(struct afs_net *net, struct afs_server *server,
 			     struct key *key, bool all)
 {
-	struct afs_addr_cursor ac = {
-		.index = 0,
-	};
+	struct afs_addr_list *alist;
+	unsigned int index;
 
 	_enter("%pU", &server->uuid);
 
 	read_lock(&server->fs_lock);
-	ac.alist = rcu_dereference_protected(server->addresses,
-					     lockdep_is_held(&server->fs_lock));
-	afs_get_addrlist(ac.alist, afs_alist_trace_get_probe);
+	alist = rcu_dereference_protected(server->addresses,
+					  lockdep_is_held(&server->fs_lock));
+	afs_get_addrlist(alist, afs_alist_trace_get_probe);
 	read_unlock(&server->fs_lock);
 
 	server->probed_at = jiffies;
-	atomic_set(&server->probe_outstanding, all ? ac.alist->nr_addrs : 1);
+	atomic_set(&server->probe_outstanding, all ? alist->nr_addrs : 1);
 	memset(&server->probe, 0, sizeof(server->probe));
 	server->probe.rtt = UINT_MAX;
 
-	ac.index = ac.alist->preferred;
-	if (ac.index < 0 || ac.index >= ac.alist->nr_addrs)
+	index = alist->preferred;
+	if (index < 0 || index >= alist->nr_addrs)
 		all = true;
 
 	if (all) {
-		for (ac.index = 0; ac.index < ac.alist->nr_addrs; ac.index++)
-			if (!afs_fs_get_capabilities(net, server, &ac, key))
-				afs_fs_probe_not_done(net, server, &ac);
+		for (index = 0; index < alist->nr_addrs; index++)
+			if (!afs_fs_get_capabilities(net, server, alist, index, key))
+				afs_fs_probe_not_done(net, server, alist, index);
 	} else {
-		if (!afs_fs_get_capabilities(net, server, &ac, key))
-			afs_fs_probe_not_done(net, server, &ac);
+		if (!afs_fs_get_capabilities(net, server, alist, index, key))
+			afs_fs_probe_not_done(net, server, alist, index);
 	}
 
-	afs_put_addrlist(ac.alist, afs_alist_trace_put_probe);
+	afs_put_addrlist(alist, afs_alist_trace_put_probe);
 }
 
 /*
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index 2b64641b20a4..4f98b43b0dde 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -1605,10 +1605,8 @@ static const struct afs_call_type afs_RXFSGiveUpAllCallBacks = {
 /*
  * Flush all the callbacks we have on a server.
  */
-int afs_fs_give_up_all_callbacks(struct afs_net *net,
-				 struct afs_server *server,
-				 struct afs_addr_cursor *ac,
-				 struct key *key)
+int afs_fs_give_up_all_callbacks(struct afs_net *net, struct afs_server *server,
+				 struct afs_address *addr, struct key *key)
 {
 	struct afs_call *call;
 	__be32 *bp;
@@ -1621,7 +1619,7 @@ int afs_fs_give_up_all_callbacks(struct afs_net *net,
 		return -ENOMEM;
 
 	call->key	= key;
-	call->peer	= rxrpc_kernel_get_peer(ac->alist->addrs[ac->index].peer);
+	call->peer	= rxrpc_kernel_get_peer(addr->peer);
 	call->service_id = server->service_id;
 
 	/* marshall the parameters */
@@ -1629,9 +1627,11 @@ int afs_fs_give_up_all_callbacks(struct afs_net *net,
 	*bp++ = htonl(FSGIVEUPALLCALLBACKS);
 
 	call->server = afs_use_server(server, afs_server_trace_give_up_cb);
-	afs_make_call(ac, call, GFP_NOFS);
-	afs_wait_for_call_to_complete(call, ac);
+	afs_make_call(call, GFP_NOFS);
+	afs_wait_for_call_to_complete(call);
 	ret = call->error;
+	if (call->responded)
+		set_bit(AFS_SERVER_FL_RESPONDING, &server->flags);
 	afs_put_call(call);
 	return ret;
 }
@@ -1695,6 +1695,12 @@ static int afs_deliver_fs_get_capabilities(struct afs_call *call)
 	return 0;
 }
 
+static void afs_fs_get_capabilities_destructor(struct afs_call *call)
+{
+	afs_put_addrlist(call->probe_alist, afs_alist_trace_put_getcaps);
+	afs_flat_call_destructor(call);
+}
+
 /*
  * FS.GetCapabilities operation type
  */
@@ -1703,7 +1709,7 @@ static const struct afs_call_type afs_RXFSGetCapabilities = {
 	.op		= afs_FS_GetCapabilities,
 	.deliver	= afs_deliver_fs_get_capabilities,
 	.done		= afs_fileserver_probe_result,
-	.destructor	= afs_flat_call_destructor,
+	.destructor	= afs_fs_get_capabilities_destructor,
 };
 
 /*
@@ -1713,7 +1719,8 @@ static const struct afs_call_type afs_RXFSGetCapabilities = {
  * ->done() - otherwise we return false to indicate we didn't even try.
  */
 bool afs_fs_get_capabilities(struct afs_net *net, struct afs_server *server,
-			     struct afs_addr_cursor *ac, struct key *key)
+			     struct afs_addr_list *alist, unsigned int addr_index,
+			     struct key *key)
 {
 	struct afs_call *call;
 	__be32 *bp;
@@ -1726,7 +1733,9 @@ bool afs_fs_get_capabilities(struct afs_net *net, struct afs_server *server,
 
 	call->key	= key;
 	call->server	= afs_use_server(server, afs_server_trace_get_caps);
-	call->peer	= rxrpc_kernel_get_peer(ac->alist->addrs[ac->index].peer);
+	call->peer	= rxrpc_kernel_get_peer(alist->addrs[addr_index].peer);
+	call->probe_alist = afs_get_addrlist(alist, afs_alist_trace_get_getcaps);
+	call->probe_index = addr_index;
 	call->service_id = server->service_id;
 	call->upgrade	= true;
 	call->async	= true;
@@ -1737,7 +1746,7 @@ bool afs_fs_get_capabilities(struct afs_net *net, struct afs_server *server,
 	*bp++ = htonl(FSGETCAPABILITIES);
 
 	trace_afs_make_fs_call(call, NULL);
-	afs_make_call(ac, call, GFP_NOFS);
+	afs_make_call(call, GFP_NOFS);
 	afs_put_call(call);
 	return true;
 }
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 3a2aa2af072a..ae33dd8ae49b 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -102,7 +102,6 @@ struct afs_addr_list {
  */
 struct afs_call {
 	const struct afs_call_type *type;	/* type of call */
-	struct afs_addr_list	*alist;		/* Address is alist[addr_ix] */
 	wait_queue_head_t	waitq;		/* processes awaiting completion */
 	struct work_struct	async_work;	/* async I/O processor */
 	struct work_struct	work;		/* actual work processor */
@@ -123,6 +122,10 @@ struct afs_call {
 	};
 	void			*buffer;	/* reply receive buffer */
 	union {
+		struct {
+			struct afs_addr_list	*probe_alist;
+			unsigned char		probe_index;	/* Address in ->probe_alist */
+		};
 		struct afs_addr_list	*ret_alist;
 		struct afs_vldb_entry	*ret_vldb;
 		char			*ret_str;
@@ -139,7 +142,6 @@ struct afs_call {
 	unsigned		reply_max;	/* maximum size of reply */
 	unsigned		count2;		/* count used in unmarshalling */
 	unsigned char		unmarshall;	/* unmarshalling phase */
-	unsigned char		addr_ix;	/* Address in ->alist */
 	bool			drop_ref;	/* T if need to drop ref for incoming call */
 	bool			need_attention;	/* T if RxRPC poked us */
 	bool			async;		/* T if asynchronous */
@@ -729,31 +731,23 @@ struct afs_error {
 	bool	aborted;		/* T if ->error is from an abort */
 };
 
-/*
- * Cursor for iterating over a server's address list.
- */
-struct afs_addr_cursor {
-	struct afs_addr_list	*alist;		/* Current address list (pins ref) */
-	unsigned long		tried;		/* Tried addresses */
-	signed char		index;		/* Current address */
-	unsigned short		nr_iterations;	/* Number of address iterations */
-	bool			call_responded;
-};
-
 /*
  * Cursor for iterating over a set of volume location servers.
  */
 struct afs_vl_cursor {
-	struct afs_addr_cursor	ac;
 	struct afs_cell		*cell;		/* The cell we're querying */
 	struct afs_vlserver_list *server_list;	/* Current server list (pins ref) */
 	struct afs_vlserver	*server;	/* Server on which this resides */
+	struct afs_addr_list	*alist;		/* Current address list (pins ref) */
 	struct key		*key;		/* Key for the server */
 	unsigned long		untried_servers; /* Bitmask of untried servers */
+	unsigned long		addr_tried;	/* Tried addresses */
 	struct afs_error	cumul_error;	/* Cumulative error */
+	unsigned int		debug_id;
 	s32			call_abort_code;
 	short			call_error;	/* Error from single call */
 	short			server_index;	/* Current server */
+	signed char		addr_index;	/* Current address */
 	unsigned short		flags;
 #define AFS_VL_CURSOR_STOP	0x0001		/* Set to cease iteration */
 #define AFS_VL_CURSOR_RETRY	0x0002		/* Set to do a retry */
@@ -812,8 +806,6 @@ struct afs_operation {
 	struct timespec64	ctime;		/* Change time to set */
 	struct afs_error	cumul_error;	/* Cumulative error */
 	short			nr_files;	/* Number of entries in file[], more_files */
-	short			call_error;	/* Error from single call */
-	s32			call_abort_code; /* Abort code from single call */
 	unsigned int		debug_id;
 
 	unsigned int		cb_v_break;	/* Volume break counter before op */
@@ -862,16 +854,19 @@ struct afs_operation {
 	};
 
 	/* Fileserver iteration state */
-	struct afs_addr_cursor	ac;
 	struct afs_server_list	*server_list;	/* Current server list (pins ref) */
 	struct afs_server	*server;	/* Server we're using (ref pinned by server_list) */
+	struct afs_addr_list	*alist;		/* Current address list (pins ref) */
 	struct afs_call		*call;
 	unsigned long		untried_servers; /* Bitmask of untried servers */
+	unsigned long		addr_tried;	/* Tried addresses */
+	s32			call_abort_code; /* Abort code from single call */
+	short			call_error;	/* Error from single call */
 	short			server_index;	/* Current server */
 	short			nr_iterations;	/* Number of server iterations */
+	signed char		addr_index;	/* Current address */
 	bool			call_responded;	/* T if the current address responded */
 
-
 	unsigned int		flags;
 #define AFS_OPERATION_STOP		0x0001	/* Set to cease iteration */
 #define AFS_OPERATION_VBUSY		0x0002	/* Set if seen VBUSY */
@@ -981,8 +976,6 @@ extern struct afs_vlserver_list *afs_parse_text_addrs(struct afs_net *,
 bool afs_addr_list_same(const struct afs_addr_list *a,
 			const struct afs_addr_list *b);
 extern struct afs_vlserver_list *afs_dns_query(struct afs_cell *, time64_t *);
-extern bool afs_iterate_addresses(struct afs_addr_cursor *);
-extern void afs_end_cursor(struct afs_addr_cursor *ac);
 
 extern int afs_merge_fs_addr4(struct afs_net *net, struct afs_addr_list *addr,
 			      __be32 xdr, u16 port);
@@ -1123,10 +1116,11 @@ extern void afs_fs_get_volume_status(struct afs_operation *);
 extern void afs_fs_set_lock(struct afs_operation *);
 extern void afs_fs_extend_lock(struct afs_operation *);
 extern void afs_fs_release_lock(struct afs_operation *);
-extern int afs_fs_give_up_all_callbacks(struct afs_net *, struct afs_server *,
-					struct afs_addr_cursor *, struct key *);
-extern bool afs_fs_get_capabilities(struct afs_net *, struct afs_server *,
-				    struct afs_addr_cursor *, struct key *);
+int afs_fs_give_up_all_callbacks(struct afs_net *net, struct afs_server *server,
+				 struct afs_address *addr, struct key *key);
+bool afs_fs_get_capabilities(struct afs_net *net, struct afs_server *server,
+			     struct afs_addr_list *alist, unsigned int addr_index,
+			     struct key *key);
 extern void afs_fs_inline_bulk_status(struct afs_operation *);
 
 struct afs_acl {
@@ -1306,8 +1300,8 @@ extern int __net_init afs_open_socket(struct afs_net *);
 extern void __net_exit afs_close_socket(struct afs_net *);
 extern void afs_charge_preallocation(struct work_struct *);
 extern void afs_put_call(struct afs_call *);
-extern void afs_make_call(struct afs_addr_cursor *, struct afs_call *, gfp_t);
-void afs_wait_for_call_to_complete(struct afs_call *call, struct afs_addr_cursor *ac);
+void afs_make_call(struct afs_call *call, gfp_t gfp);
+void afs_wait_for_call_to_complete(struct afs_call *call);
 extern struct afs_call *afs_alloc_flat_call(struct afs_net *,
 					    const struct afs_call_type *,
 					    size_t, size_t);
@@ -1325,9 +1319,9 @@ static inline void afs_make_op_call(struct afs_operation *op, struct afs_call *c
 	call->op	= op;
 	call->key	= op->key;
 	call->intr	= !(op->flags & AFS_OPERATION_UNINTR);
-	call->peer	= rxrpc_kernel_get_peer(op->ac.alist->addrs[op->ac.index].peer);
+	call->peer	= rxrpc_kernel_get_peer(op->alist->addrs[op->addr_index].peer);
 	call->service_id = op->server->service_id;
-	afs_make_call(&op->ac, call, gfp);
+	afs_make_call(call, gfp);
 }
 
 static inline void afs_extract_begin(struct afs_call *call, void *buf, size_t size)
@@ -1493,8 +1487,12 @@ extern void afs_fs_exit(void);
 extern struct afs_vldb_entry *afs_vl_get_entry_by_name_u(struct afs_vl_cursor *,
 							 const char *, int);
 extern struct afs_addr_list *afs_vl_get_addrs_u(struct afs_vl_cursor *, const uuid_t *);
-extern struct afs_call *afs_vl_get_capabilities(struct afs_net *, struct afs_addr_cursor *,
-						struct key *, struct afs_vlserver *, unsigned int);
+struct afs_call *afs_vl_get_capabilities(struct afs_net *net,
+					 struct afs_addr_list *alist,
+					 unsigned int addr_index,
+					 struct key *key,
+					 struct afs_vlserver *server,
+					 unsigned int server_index);
 extern struct afs_addr_list *afs_yfsvl_get_endpoints(struct afs_vl_cursor *, const uuid_t *);
 extern char *afs_yfsvl_get_cell_name(struct afs_vl_cursor *);
 
diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c
index 6c1aa9bafc82..a6bda8f44c0f 100644
--- a/fs/afs/rotate.c
+++ b/fs/afs/rotate.c
@@ -109,19 +109,20 @@ static bool afs_sleep_and_retry(struct afs_operation *op)
  */
 bool afs_select_fileserver(struct afs_operation *op)
 {
-	struct afs_addr_list *alist;
+	struct afs_addr_list *alist = op->alist;
 	struct afs_server *server;
 	struct afs_vnode *vnode = op->file[0].vnode;
+	unsigned long set;
 	unsigned int rtt;
 	s32 abort_code = op->call_abort_code;
-	int error = op->call_error, i;
+	int error = op->call_error, addr_index, i;
 
 	op->nr_iterations++;
 
-	_enter("OP=%x+%x,%llx,%lx[%d],%lx[%d],%d,%d",
+	_enter("OP=%x+%x,%llx,%u{%lx},%u{%lx},%d,%d",
 	       op->debug_id, op->nr_iterations, op->volume->vid,
-	       op->untried_servers, op->server_index,
-	       op->ac.tried, op->ac.index,
+	       op->server_index, op->untried_servers,
+	       op->addr_index, op->addr_tried,
 	       error, abort_code);
 
 	if (op->flags & AFS_OPERATION_STOP) {
@@ -398,12 +399,14 @@ bool afs_select_fileserver(struct afs_operation *op)
 
 restart_from_beginning:
 	_debug("restart");
-	afs_end_cursor(&op->ac);
+	afs_put_addrlist(alist, afs_alist_trace_put_restart_rotate);
+	alist = op->alist = NULL;
 	op->server = NULL;
 	afs_put_serverlist(op->net, op->server_list);
 	op->server_list = NULL;
 start:
 	_debug("start");
+	ASSERTCMP(alist, ==, NULL);
 	/* See if we need to do an update of the volume record.  Note that the
 	 * volume may have moved or even have been deleted.
 	 */
@@ -420,6 +423,7 @@ start:
 
 pick_server:
 	_debug("pick [%lx]", op->untried_servers);
+	ASSERTCMP(alist, ==, NULL);
 
 	error = afs_wait_for_fs_probes(op->server_list, op->untried_servers);
 	if (error < 0) {
@@ -463,7 +467,7 @@ selected_server:
 	 * check it, create a callback intercept, find its address list and
 	 * probe its capabilities before we use it.
 	 */
-	ASSERTCMP(op->ac.alist, ==, NULL);
+	ASSERTCMP(alist, ==, NULL);
 	server = op->server_list->servers[op->server_index].server;
 
 	if (!afs_check_server_record(op, server))
@@ -484,32 +488,34 @@ selected_server:
 	read_lock(&server->fs_lock);
 	alist = rcu_dereference_protected(server->addresses,
 					  lockdep_is_held(&server->fs_lock));
-	afs_get_addrlist(alist, afs_alist_trace_get_fsrotate_set);
+	op->alist = afs_get_addrlist(alist, afs_alist_trace_get_fsrotate_set);
 	read_unlock(&server->fs_lock);
 
 retry_server:
-	memset(&op->ac, 0, sizeof(op->ac));
-
-	if (!op->ac.alist)
-		op->ac.alist = alist;
-	else
-		afs_put_addrlist(alist, afs_alist_trace_put_retry_server);
-
-	op->ac.index = -1;
+	op->addr_tried = 0;
+	op->addr_index = -1;
 
 iterate_address:
-	ASSERT(op->ac.alist);
 	/* Iterate over the current server's address list to try and find an
 	 * address on which it will respond to us.
 	 */
-	if (!afs_iterate_addresses(&op->ac))
+	set = READ_ONCE(alist->responded);
+	set &= ~(READ_ONCE(alist->probe_failed) | op->addr_tried);
+	if (!set)
 		goto out_of_addresses;
 
-	_debug("address [%u] %u/%u %pISp",
-	       op->server_index, op->ac.index, op->ac.alist->nr_addrs,
-	       rxrpc_kernel_remote_addr(op->ac.alist->addrs[op->ac.index].peer));
+	addr_index = READ_ONCE(alist->preferred);
+	if (!test_bit(addr_index, &set))
+		addr_index = __ffs(set);
+
+	op->addr_index = addr_index;
+	set_bit(addr_index, &op->addr_tried);
+	op->alist = alist;
 
 	op->call_responded = false;
+	_debug("address [%u] %u/%u %pISp",
+	       op->server_index, addr_index, alist->nr_addrs,
+	       rxrpc_kernel_remote_addr(alist->addrs[op->addr_index].peer));
 	_leave(" = t");
 	return true;
 
@@ -519,7 +525,6 @@ out_of_addresses:
 	 */
 	afs_probe_fileserver(op->net, op->server);
 	if (op->flags & AFS_OPERATION_RETRY_SERVER) {
-		alist = op->ac.alist;
 		error = afs_wait_for_one_fs_probe(
 			op->server, !(op->flags & AFS_OPERATION_UNINTR));
 		switch (error) {
@@ -537,7 +542,13 @@ out_of_addresses:
 
 next_server:
 	_debug("next");
-	afs_end_cursor(&op->ac);
+	ASSERT(alist);
+	if (op->call_responded &&
+	    op->addr_index != READ_ONCE(alist->preferred) &&
+	    test_bit(alist->preferred, &op->addr_tried))
+		WRITE_ONCE(alist->preferred, op->addr_index);
+	afs_put_addrlist(alist, afs_alist_trace_put_next_server);
+	alist = op->alist = NULL;
 	goto pick_server;
 
 no_more_servers:
@@ -557,7 +568,14 @@ no_more_servers:
 
 failed:
 	op->flags |= AFS_OPERATION_STOP;
-	afs_end_cursor(&op->ac);
+	if (alist) {
+		if (op->call_responded &&
+		    op->addr_index != READ_ONCE(alist->preferred) &&
+		    test_bit(alist->preferred, &op->addr_tried))
+			WRITE_ONCE(alist->preferred, op->addr_index);
+		afs_put_addrlist(alist, afs_alist_trace_put_op_failed);
+		op->alist = NULL;
+	}
 	_leave(" = f [failed %d]", afs_op_error(op));
 	return false;
 }
@@ -602,13 +620,12 @@ void afs_dump_edestaddrreq(const struct afs_operation *op)
 					  a->preferred);
 				pr_notice("FC:  - R=%lx F=%lx\n",
 					  a->responded, a->probe_failed);
-				if (a == op->ac.alist)
+				if (a == op->alist)
 					pr_notice("FC:  - current\n");
 			}
 		}
 	}
 
-	pr_notice("AC: t=%lx ax=%u ni=%u\n",
-		  op->ac.tried, op->ac.index, op->ac.nr_iterations);
+	pr_notice("AC: t=%lx ax=%u\n", op->addr_tried, op->addr_index);
 	rcu_read_unlock();
 }
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index e8490b3e9d37..81013bc8bbfd 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -189,7 +189,6 @@ void afs_put_call(struct afs_call *call)
 			call->type->destructor(call);
 
 		afs_unuse_server_notime(call->net, call->server, afs_server_trace_put_call);
-		afs_put_addrlist(call->alist, afs_alist_trace_put_call);
 		kfree(call->request);
 
 		trace_afs_call(call->debug_id, afs_call_trace_free, 0, o,
@@ -296,7 +295,7 @@ static void afs_notify_end_request_tx(struct sock *sock,
  * Initiate a call and synchronously queue up the parameters for dispatch.  Any
  * error is stored into the call struct, which the caller must check for.
  */
-void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp)
+void afs_make_call(struct afs_call *call, gfp_t gfp)
 {
 	struct rxrpc_call *rxcall;
 	struct msghdr msg;
@@ -314,9 +313,6 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp)
 	       call, call->type->name, key_serial(call->key),
 	       atomic_read(&call->net->nr_outstanding_calls));
 
-	call->addr_ix = ac->index;
-	call->alist = afs_get_addrlist(ac->alist, afs_alist_trace_get_make_call);
-
 	/* Work out the length we're going to transmit.  This is awkward for
 	 * calls such as FS.StoreData where there's an extra injection of data
 	 * after the initial fixed part.
@@ -392,7 +388,7 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp)
 	/* Note that at this point, we may have received the reply or an abort
 	 * - and an asynchronous call may already have completed.
 	 *
-	 * afs_wait_for_call_to_complete(call, ac)
+	 * afs_wait_for_call_to_complete(call)
 	 * must be called to synchronously clean up.
 	 */
 	return;
@@ -577,7 +573,7 @@ call_complete:
 /*
  * Wait synchronously for a call to complete.
  */
-void afs_wait_for_call_to_complete(struct afs_call *call, struct afs_addr_cursor *ac)
+void afs_wait_for_call_to_complete(struct afs_call *call)
 {
 	bool rxrpc_complete = false;
 
@@ -627,9 +623,6 @@ void afs_wait_for_call_to_complete(struct afs_call *call, struct afs_addr_cursor
 				afs_set_call_complete(call, -EINTR, 0);
 		}
 	}
-
-	if (call->error == 0 || call->error == -ECONNABORTED)
-		call->responded = true;
 }
 
 /*
diff --git a/fs/afs/server.c b/fs/afs/server.c
index e2c7f65eea33..62d453365689 100644
--- a/fs/afs/server.c
+++ b/fs/afs/server.c
@@ -436,12 +436,8 @@ static void __afs_put_server(struct afs_net *net, struct afs_server *server)
 static void afs_give_up_callbacks(struct afs_net *net, struct afs_server *server)
 {
 	struct afs_addr_list *alist = rcu_access_pointer(server->addresses);
-	struct afs_addr_cursor ac = {
-		.alist	= alist,
-		.index	= alist->preferred,
-	};
 
-	afs_fs_give_up_all_callbacks(net, server, &ac, NULL);
+	afs_fs_give_up_all_callbacks(net, server, &alist->addrs[alist->preferred], NULL);
 }
 
 /*
diff --git a/fs/afs/vl_probe.c b/fs/afs/vl_probe.c
index d9a99ba9fc78..f868ae5d40e5 100644
--- a/fs/afs/vl_probe.c
+++ b/fs/afs/vl_probe.c
@@ -46,12 +46,12 @@ static void afs_done_one_vl_probe(struct afs_vlserver *server, bool wake_up)
  */
 void afs_vlserver_probe_result(struct afs_call *call)
 {
-	struct afs_addr_list *alist = call->alist;
+	struct afs_addr_list *alist = call->probe_alist;
 	struct afs_vlserver *server = call->vlserver;
-	struct afs_address *addr = &alist->addrs[call->addr_ix];
+	struct afs_address *addr = &alist->addrs[call->probe_index];
 	unsigned int server_index = call->server_index;
 	unsigned int rtt_us = 0;
-	unsigned int index = call->addr_ix;
+	unsigned int index = call->probe_index;
 	bool have_result = false;
 	int ret = call->error;
 
@@ -148,25 +148,25 @@ static bool afs_do_probe_vlserver(struct afs_net *net,
 				  unsigned int server_index,
 				  struct afs_error *_e)
 {
-	struct afs_addr_cursor ac = {
-		.index = 0,
-	};
+	struct afs_addr_list *alist;
 	struct afs_call *call;
+	unsigned int index;
 	bool in_progress = false;
 
 	_enter("%s", server->name);
 
 	read_lock(&server->lock);
-	ac.alist = rcu_dereference_protected(server->addresses,
-					     lockdep_is_held(&server->lock));
+	alist = rcu_dereference_protected(server->addresses,
+					  lockdep_is_held(&server->lock));
+	afs_get_addrlist(alist, afs_alist_trace_get_vlprobe);
 	read_unlock(&server->lock);
 
-	atomic_set(&server->probe_outstanding, ac.alist->nr_addrs);
+	atomic_set(&server->probe_outstanding, alist->nr_addrs);
 	memset(&server->probe, 0, sizeof(server->probe));
 	server->probe.rtt = UINT_MAX;
 
-	for (ac.index = 0; ac.index < ac.alist->nr_addrs; ac.index++) {
-		call = afs_vl_get_capabilities(net, &ac, key, server,
+	for (index = 0; index < alist->nr_addrs; index++) {
+		call = afs_vl_get_capabilities(net, alist, index, key, server,
 					       server_index);
 		if (!IS_ERR(call)) {
 			afs_prioritise_error(_e, call->error, call->abort_code);
@@ -178,6 +178,7 @@ static bool afs_do_probe_vlserver(struct afs_net *net,
 		}
 	}
 
+	afs_put_addrlist(alist, afs_alist_trace_put_vlprobe);
 	return in_progress;
 }
 
diff --git a/fs/afs/vl_rotate.c b/fs/afs/vl_rotate.c
index f895eb94129e..91168528179c 100644
--- a/fs/afs/vl_rotate.c
+++ b/fs/afs/vl_rotate.c
@@ -17,6 +17,8 @@
 bool afs_begin_vlserver_operation(struct afs_vl_cursor *vc, struct afs_cell *cell,
 				  struct key *key)
 {
+	static atomic_t debug_ids;
+
 	memset(vc, 0, sizeof(*vc));
 	vc->cell = cell;
 	vc->key = key;
@@ -29,6 +31,7 @@ bool afs_begin_vlserver_operation(struct afs_vl_cursor *vc, struct afs_cell *cel
 		return false;
 	}
 
+	vc->debug_id = atomic_inc_return(&debug_ids);
 	return true;
 }
 
@@ -89,17 +92,18 @@ static bool afs_start_vl_iteration(struct afs_vl_cursor *vc)
  */
 bool afs_select_vlserver(struct afs_vl_cursor *vc)
 {
-	struct afs_addr_list *alist;
+	struct afs_addr_list *alist = vc->alist;
 	struct afs_vlserver *vlserver;
+	unsigned long set, failed;
 	unsigned int rtt;
 	s32 abort_code = vc->call_abort_code;
 	int error = vc->call_error, i;
 
 	vc->nr_iterations++;
 
-	_enter("%lx[%d],%lx[%d],%d,%d",
-	       vc->untried_servers, vc->server_index,
-	       vc->ac.tried, vc->ac.index,
+	_enter("VC=%x+%x,%d{%lx},%d{%lx},%d,%d",
+	       vc->debug_id, vc->nr_iterations, vc->server_index, vc->untried_servers,
+	       vc->addr_index, vc->addr_tried,
 	       error, abort_code);
 
 	if (vc->flags & AFS_VL_CURSOR_STOP) {
@@ -165,7 +169,13 @@ bool afs_select_vlserver(struct afs_vl_cursor *vc)
 
 restart_from_beginning:
 	_debug("restart");
-	afs_end_cursor(&vc->ac);
+	if (vc->call_responded &&
+	    vc->addr_index != vc->alist->preferred &&
+	    test_bit(alist->preferred, &vc->addr_tried))
+		WRITE_ONCE(alist->preferred, vc->addr_index);
+	afs_put_addrlist(alist, afs_alist_trace_put_vlrotate_restart);
+	alist = vc->alist = NULL;
+
 	afs_put_vlserverlist(vc->cell->net, vc->server_list);
 	vc->server_list = NULL;
 	if (vc->flags & AFS_VL_CURSOR_RETRIED)
@@ -173,6 +183,7 @@ restart_from_beginning:
 	vc->flags |= AFS_VL_CURSOR_RETRIED;
 start:
 	_debug("start");
+	ASSERTCMP(alist, ==, NULL);
 
 	if (!afs_start_vl_iteration(vc))
 		goto failed;
@@ -185,6 +196,7 @@ start:
 
 pick_server:
 	_debug("pick [%lx]", vc->untried_servers);
+	ASSERTCMP(alist, ==, NULL);
 
 	error = afs_wait_for_vl_probes(vc->server_list, vc->untried_servers);
 	if (error < 0) {
@@ -222,7 +234,6 @@ selected_server:
 	 * check it, find its address list and probe its capabilities before we
 	 * use it.
 	 */
-	ASSERTCMP(vc->ac.alist, ==, NULL);
 	vlserver = vc->server_list->servers[vc->server_index].server;
 	vc->server = vlserver;
 
@@ -231,30 +242,48 @@ selected_server:
 	read_lock(&vlserver->lock);
 	alist = rcu_dereference_protected(vlserver->addresses,
 					  lockdep_is_held(&vlserver->lock));
-	afs_get_addrlist(alist, afs_alist_trace_get_vlrotate_set);
+	vc->alist = afs_get_addrlist(alist, afs_alist_trace_get_vlrotate_set);
 	read_unlock(&vlserver->lock);
 
-	memset(&vc->ac, 0, sizeof(vc->ac));
-	vc->ac.alist = alist;
-	vc->ac.index = -1;
+	vc->addr_tried = 0;
+	vc->addr_index = -1;
 
 iterate_address:
-	ASSERT(vc->ac.alist);
 	/* Iterate over the current server's address list to try and find an
 	 * address on which it will respond to us.
 	 */
-	if (!afs_iterate_addresses(&vc->ac))
+	set = READ_ONCE(alist->responded);
+	failed = READ_ONCE(alist->probe_failed);
+	vc->addr_index = READ_ONCE(alist->preferred);
+
+	_debug("%lx-%lx-%lx,%d", set, failed, vc->addr_tried, vc->addr_index);
+
+	set &= ~(failed | vc->addr_tried);
+
+	if (!set)
 		goto next_server;
 
-	_debug("VL address %d/%d", vc->ac.index, vc->ac.alist->nr_addrs);
+	if (!test_bit(vc->addr_index, &set))
+		vc->addr_index = __ffs(set);
+
+	set_bit(vc->addr_index, &vc->addr_tried);
+	vc->alist = alist;
+
+	_debug("VL address %d/%d", vc->addr_index, alist->nr_addrs);
 
 	vc->call_responded = false;
-	_leave(" = t %pISpc", rxrpc_kernel_remote_addr(vc->ac.alist->addrs[vc->ac.index].peer));
+	_leave(" = t %pISpc", rxrpc_kernel_remote_addr(alist->addrs[vc->addr_index].peer));
 	return true;
 
 next_server:
 	_debug("next");
-	afs_end_cursor(&vc->ac);
+	ASSERT(alist);
+	if (vc->call_responded &&
+	    vc->addr_index != alist->preferred &&
+	    test_bit(alist->preferred, &vc->addr_tried))
+		WRITE_ONCE(alist->preferred, vc->addr_index);
+	afs_put_addrlist(alist, afs_alist_trace_put_vlrotate_next);
+	alist = vc->alist = NULL;
 	goto pick_server;
 
 no_more_servers:
@@ -274,8 +303,15 @@ no_more_servers:
 	}
 
 failed:
+	if (alist) {
+		if (vc->call_responded &&
+		    vc->addr_index != alist->preferred &&
+		    test_bit(alist->preferred, &vc->addr_tried))
+			WRITE_ONCE(alist->preferred, vc->addr_index);
+		afs_put_addrlist(alist, afs_alist_trace_put_vlrotate_fail);
+		alist = vc->alist = NULL;
+	}
 	vc->flags |= AFS_VL_CURSOR_STOP;
-	afs_end_cursor(&vc->ac);
 	_leave(" = f [failed %d]", vc->cumul_error.error);
 	return false;
 }
@@ -299,8 +335,8 @@ static void afs_vl_dump_edestaddrreq(const struct afs_vl_cursor *vc)
 	pr_notice("DNS: src=%u st=%u lc=%x\n",
 		  cell->dns_source, cell->dns_status, cell->dns_lookup_count);
 	pr_notice("VC: ut=%lx ix=%u ni=%hu fl=%hx err=%hd\n",
-		  vc->untried_servers, vc->server_index, vc->nr_iterations, vc->flags,
-		  vc->cumul_error.error);
+		  vc->untried_servers, vc->server_index, vc->nr_iterations,
+		  vc->flags, vc->cumul_error.error);
 	pr_notice("VC: call  er=%d ac=%d r=%u\n",
 		  vc->call_error, vc->call_abort_code, vc->call_responded);
 
@@ -320,14 +356,13 @@ static void afs_vl_dump_edestaddrreq(const struct afs_vl_cursor *vc)
 					  a->preferred);
 				pr_notice("VC:  - R=%lx F=%lx\n",
 					  a->responded, a->probe_failed);
-				if (a == vc->ac.alist)
+				if (a == vc->alist)
 					pr_notice("VC:  - current\n");
 			}
 		}
 	}
 
-	pr_notice("AC: t=%lx ax=%u ni=%u\n",
-		  vc->ac.tried, vc->ac.index, vc->ac.nr_iterations);
+	pr_notice("AC: t=%lx ax=%u\n", vc->addr_tried, vc->addr_index);
 	rcu_read_unlock();
 }
 
@@ -338,6 +373,8 @@ int afs_end_vlserver_operation(struct afs_vl_cursor *vc)
 {
 	struct afs_net *net = vc->cell->net;
 
+	_enter("VC=%x+%x", vc->debug_id, vc->nr_iterations);
+
 	switch (vc->cumul_error.error) {
 	case -EDESTADDRREQ:
 	case -EADDRNOTAVAIL:
@@ -347,7 +384,14 @@ int afs_end_vlserver_operation(struct afs_vl_cursor *vc)
 		break;
 	}
 
-	afs_end_cursor(&vc->ac);
+	if (vc->alist) {
+		if (vc->call_responded &&
+		    vc->addr_index != vc->alist->preferred &&
+		    test_bit(vc->alist->preferred, &vc->addr_tried))
+			WRITE_ONCE(vc->alist->preferred, vc->addr_index);
+		afs_put_addrlist(vc->alist, afs_alist_trace_put_vlrotate_end);
+		vc->alist = NULL;
+	}
 	afs_put_vlserverlist(net, vc->server_list);
 	return vc->cumul_error.error;
 }
diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c
index 4bf98a38c3a1..39a0b7614d05 100644
--- a/fs/afs/vlclient.c
+++ b/fs/afs/vlclient.c
@@ -149,7 +149,7 @@ struct afs_vldb_entry *afs_vl_get_entry_by_name_u(struct afs_vl_cursor *vc,
 	call->key = vc->key;
 	call->ret_vldb = entry;
 	call->max_lifespan = AFS_VL_MAX_LIFESPAN;
-	call->peer = rxrpc_kernel_get_peer(vc->ac.alist->addrs[vc->ac.index].peer);
+	call->peer = rxrpc_kernel_get_peer(vc->alist->addrs[vc->addr_index].peer);
 	call->service_id = vc->server->service_id;
 
 	/* Marshall the parameters */
@@ -161,8 +161,8 @@ struct afs_vldb_entry *afs_vl_get_entry_by_name_u(struct afs_vl_cursor *vc,
 		memset((void *)bp + volnamesz, 0, padsz);
 
 	trace_afs_make_vl_call(call);
-	afs_make_call(&vc->ac, call, GFP_KERNEL);
-	afs_wait_for_call_to_complete(call, &vc->ac);
+	afs_make_call(call, GFP_KERNEL);
+	afs_wait_for_call_to_complete(call);
 	vc->call_abort_code	= call->abort_code;
 	vc->call_error		= call->error;
 	vc->call_responded	= call->responded;
@@ -290,7 +290,7 @@ struct afs_addr_list *afs_vl_get_addrs_u(struct afs_vl_cursor *vc,
 	call->key = vc->key;
 	call->ret_alist = NULL;
 	call->max_lifespan = AFS_VL_MAX_LIFESPAN;
-	call->peer = rxrpc_kernel_get_peer(vc->ac.alist->addrs[vc->ac.index].peer);
+	call->peer = rxrpc_kernel_get_peer(vc->alist->addrs[vc->addr_index].peer);
 	call->service_id = vc->server->service_id;
 
 	/* Marshall the parameters */
@@ -310,8 +310,8 @@ struct afs_addr_list *afs_vl_get_addrs_u(struct afs_vl_cursor *vc,
 		r->uuid.node[i] = htonl(u->node[i]);
 
 	trace_afs_make_vl_call(call);
-	afs_make_call(&vc->ac, call, GFP_KERNEL);
-	afs_wait_for_call_to_complete(call, &vc->ac);
+	afs_make_call(call, GFP_KERNEL);
+	afs_wait_for_call_to_complete(call);
 	vc->call_abort_code	= call->abort_code;
 	vc->call_error		= call->error;
 	vc->call_responded	= call->responded;
@@ -371,6 +371,7 @@ static int afs_deliver_vl_get_capabilities(struct afs_call *call)
 
 static void afs_destroy_vl_get_capabilities(struct afs_call *call)
 {
+	afs_put_addrlist(call->probe_alist, afs_alist_trace_put_vlgetcaps);
 	afs_put_vlserver(call->net, call->vlserver);
 	afs_flat_call_destructor(call);
 }
@@ -394,7 +395,8 @@ static const struct afs_call_type afs_RXVLGetCapabilities = {
  * other end supports.
  */
 struct afs_call *afs_vl_get_capabilities(struct afs_net *net,
-					 struct afs_addr_cursor *ac,
+					 struct afs_addr_list *alist,
+					 unsigned int addr_index,
 					 struct key *key,
 					 struct afs_vlserver *server,
 					 unsigned int server_index)
@@ -411,7 +413,9 @@ struct afs_call *afs_vl_get_capabilities(struct afs_net *net,
 	call->key = key;
 	call->vlserver = afs_get_vlserver(server);
 	call->server_index = server_index;
-	call->peer = rxrpc_kernel_get_peer(ac->alist->addrs[ac->index].peer);
+	call->peer = rxrpc_kernel_get_peer(alist->addrs[addr_index].peer);
+	call->probe_alist = afs_get_addrlist(alist, afs_alist_trace_get_vlgetcaps);
+	call->probe_index = addr_index;
 	call->service_id = server->service_id;
 	call->upgrade = true;
 	call->async = true;
@@ -423,7 +427,7 @@ struct afs_call *afs_vl_get_capabilities(struct afs_net *net,
 
 	/* Can't take a ref on server */
 	trace_afs_make_vl_call(call);
-	afs_make_call(ac, call, GFP_KERNEL);
+	afs_make_call(call, GFP_KERNEL);
 	return call;
 }
 
@@ -658,7 +662,7 @@ struct afs_addr_list *afs_yfsvl_get_endpoints(struct afs_vl_cursor *vc,
 	call->key = vc->key;
 	call->ret_alist = NULL;
 	call->max_lifespan = AFS_VL_MAX_LIFESPAN;
-	call->peer = rxrpc_kernel_get_peer(vc->ac.alist->addrs[vc->ac.index].peer);
+	call->peer = rxrpc_kernel_get_peer(vc->alist->addrs[vc->addr_index].peer);
 	call->service_id = vc->server->service_id;
 
 	/* Marshall the parameters */
@@ -668,8 +672,8 @@ struct afs_addr_list *afs_yfsvl_get_endpoints(struct afs_vl_cursor *vc,
 	memcpy(bp, uuid, sizeof(*uuid)); /* Type opr_uuid */
 
 	trace_afs_make_vl_call(call);
-	afs_make_call(&vc->ac, call, GFP_KERNEL);
-	afs_wait_for_call_to_complete(call, &vc->ac);
+	afs_make_call(call, GFP_KERNEL);
+	afs_wait_for_call_to_complete(call);
 	vc->call_abort_code	= call->abort_code;
 	vc->call_error		= call->error;
 	vc->call_responded	= call->responded;
@@ -777,7 +781,7 @@ char *afs_yfsvl_get_cell_name(struct afs_vl_cursor *vc)
 	call->key = vc->key;
 	call->ret_str = NULL;
 	call->max_lifespan = AFS_VL_MAX_LIFESPAN;
-	call->peer = rxrpc_kernel_get_peer(vc->ac.alist->addrs[vc->ac.index].peer);
+	call->peer = rxrpc_kernel_get_peer(vc->alist->addrs[vc->addr_index].peer);
 	call->service_id = vc->server->service_id;
 
 	/* marshall the parameters */
@@ -786,8 +790,8 @@ char *afs_yfsvl_get_cell_name(struct afs_vl_cursor *vc)
 
 	/* Can't take a ref on server */
 	trace_afs_make_vl_call(call);
-	afs_make_call(&vc->ac, call, GFP_KERNEL);
-	afs_wait_for_call_to_complete(call, &vc->ac);
+	afs_make_call(call, GFP_KERNEL);
+	afs_wait_for_call_to_complete(call);
 	vc->call_abort_code	= call->abort_code;
 	vc->call_error		= call->error;
 	vc->call_responded	= call->responded;
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index ed91666ca4cc..0f68d67f52c8 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -204,21 +204,31 @@ enum yfs_cm_operation {
 
 #define afs_alist_traces \
 	EM(afs_alist_trace_alloc,		"ALLOC     ") \
+	EM(afs_alist_trace_get_getcaps,		"GET getcap") \
 	EM(afs_alist_trace_get_fsrotate_set,	"GET fs-rot") \
-	EM(afs_alist_trace_get_make_call,	"GET mkcall") \
 	EM(afs_alist_trace_get_probe,		"GET probe ") \
+	EM(afs_alist_trace_get_vlgetcaps,	"GET vgtcap") \
+	EM(afs_alist_trace_get_vlprobe,		"GET vprobe") \
 	EM(afs_alist_trace_get_vlrotate_set,	"GET vl-rot") \
-	EM(afs_alist_trace_put_call,		"PUT call  ") \
-	EM(afs_alist_trace_put_end_cursor,	"PUT endcur") \
 	EM(afs_alist_trace_put_getaddru,	"PUT GtAdrU") \
+	EM(afs_alist_trace_put_getcaps,		"PUT getcap") \
+	EM(afs_alist_trace_put_next_server,	"PUT nx-srv") \
+	EM(afs_alist_trace_put_op_failed,	"PUT op-fai") \
+	EM(afs_alist_trace_put_operation,	"PUT op    ") \
 	EM(afs_alist_trace_put_parse_empty,	"PUT p-empt") \
 	EM(afs_alist_trace_put_parse_error,	"PUT p-err ") \
 	EM(afs_alist_trace_put_probe,		"PUT probe ") \
-	EM(afs_alist_trace_put_retry_server,	"PUT retry ") \
+	EM(afs_alist_trace_put_restart_rotate,	"PUT rstrot") \
 	EM(afs_alist_trace_put_server,		"PUT server") \
 	EM(afs_alist_trace_put_server_dup,	"PUT sv-dup") \
 	EM(afs_alist_trace_put_server_oom,	"PUT sv-oom") \
 	EM(afs_alist_trace_put_server_update,	"PUT sv-upd") \
+	EM(afs_alist_trace_put_vlgetcaps,	"PUT vgtcap") \
+	EM(afs_alist_trace_put_vlprobe,		"PUT vprobe") \
+	EM(afs_alist_trace_put_vlrotate_end,	"PUT vr-end") \
+	EM(afs_alist_trace_put_vlrotate_fail,	"PUT vr-fai") \
+	EM(afs_alist_trace_put_vlrotate_next,	"PUT vr-nxt") \
+	EM(afs_alist_trace_put_vlrotate_restart,"PUT vr-rst") \
 	EM(afs_alist_trace_put_vlserver,	"PUT vlsrvr") \
 	EM(afs_alist_trace_put_vlserver_old,	"PUT vs-old") \
 	E_(afs_alist_trace_free,		"FREE      ")
-- 
cgit v1.2.3


From f1bb47a31dff6d4b34fb14e99850860ee74bb003 Mon Sep 17 00:00:00 2001
From: Alfred Piccioni <alpic@google.com>
Date: Tue, 19 Dec 2023 10:09:09 +0100
Subject: lsm: new security_file_ioctl_compat() hook

Some ioctl commands do not require ioctl permission, but are routed to
other permissions such as FILE_GETATTR or FILE_SETATTR. This routing is
done by comparing the ioctl cmd to a set of 64-bit flags (FS_IOC_*).

However, if a 32-bit process is running on a 64-bit kernel, it emits
32-bit flags (FS_IOC32_*) for certain ioctl operations. These flags are
being checked erroneously, which leads to these ioctl operations being
routed to the ioctl permission, rather than the correct file
permissions.

This was also noted in a RED-PEN finding from a while back -
"/* RED-PEN how should LSM module know it's handling 32bit? */".

This patch introduces a new hook, security_file_ioctl_compat(), that is
called from the compat ioctl syscall. All current LSMs have been changed
to support this hook.

Reviewing the three places where we are currently using
security_file_ioctl(), it appears that only SELinux needs a dedicated
compat change; TOMOYO and SMACK appear to be functional without any
change.

Cc: stable@vger.kernel.org
Fixes: 0b24dcb7f2f7 ("Revert "selinux: simplify ioctl checking"")
Signed-off-by: Alfred Piccioni <alpic@google.com>
Reviewed-by: Stephen Smalley <stephen.smalley.work@gmail.com>
[PM: subject tweak, line length fixes, and alignment corrections]
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 fs/ioctl.c                    |  3 +--
 include/linux/lsm_hook_defs.h |  2 ++
 include/linux/security.h      |  9 +++++++++
 security/security.c           | 18 ++++++++++++++++++
 security/selinux/hooks.c      | 28 ++++++++++++++++++++++++++++
 security/smack/smack_lsm.c    |  1 +
 security/tomoyo/tomoyo.c      |  1 +
 7 files changed, 60 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/fs/ioctl.c b/fs/ioctl.c
index f5fd99d6b0d4..76cf22ac97d7 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -920,8 +920,7 @@ COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd,
 	if (!f.file)
 		return -EBADF;
 
-	/* RED-PEN how should LSM module know it's handling 32bit? */
-	error = security_file_ioctl(f.file, cmd, arg);
+	error = security_file_ioctl_compat(f.file, cmd, arg);
 	if (error)
 		goto out;
 
diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index c925a0d26edf..185924c56378 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -171,6 +171,8 @@ LSM_HOOK(int, 0, file_alloc_security, struct file *file)
 LSM_HOOK(void, LSM_RET_VOID, file_free_security, struct file *file)
 LSM_HOOK(int, 0, file_ioctl, struct file *file, unsigned int cmd,
 	 unsigned long arg)
+LSM_HOOK(int, 0, file_ioctl_compat, struct file *file, unsigned int cmd,
+	 unsigned long arg)
 LSM_HOOK(int, 0, mmap_addr, unsigned long addr)
 LSM_HOOK(int, 0, mmap_file, struct file *file, unsigned long reqprot,
 	 unsigned long prot, unsigned long flags)
diff --git a/include/linux/security.h b/include/linux/security.h
index 750130a7b9dd..d0eb20f90b26 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -394,6 +394,8 @@ int security_file_permission(struct file *file, int mask);
 int security_file_alloc(struct file *file);
 void security_file_free(struct file *file);
 int security_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
+int security_file_ioctl_compat(struct file *file, unsigned int cmd,
+			       unsigned long arg);
 int security_mmap_file(struct file *file, unsigned long prot,
 			unsigned long flags);
 int security_mmap_addr(unsigned long addr);
@@ -1002,6 +1004,13 @@ static inline int security_file_ioctl(struct file *file, unsigned int cmd,
 	return 0;
 }
 
+static inline int security_file_ioctl_compat(struct file *file,
+					     unsigned int cmd,
+					     unsigned long arg)
+{
+	return 0;
+}
+
 static inline int security_mmap_file(struct file *file, unsigned long prot,
 				     unsigned long flags)
 {
diff --git a/security/security.c b/security/security.c
index d7b15ea67c3f..69148dfc90cd 100644
--- a/security/security.c
+++ b/security/security.c
@@ -2732,6 +2732,24 @@ int security_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 }
 EXPORT_SYMBOL_GPL(security_file_ioctl);
 
+/**
+ * security_file_ioctl_compat() - Check if an ioctl is allowed in compat mode
+ * @file: associated file
+ * @cmd: ioctl cmd
+ * @arg: ioctl arguments
+ *
+ * Compat version of security_file_ioctl() that correctly handles 32-bit
+ * processes running on 64-bit kernels.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_file_ioctl_compat(struct file *file, unsigned int cmd,
+			       unsigned long arg)
+{
+	return call_int_hook(file_ioctl_compat, 0, file, cmd, arg);
+}
+EXPORT_SYMBOL_GPL(security_file_ioctl_compat);
+
 static inline unsigned long mmap_prot(struct file *file, unsigned long prot)
 {
 	/*
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index b340425ccfae..179540441115 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -3732,6 +3732,33 @@ static int selinux_file_ioctl(struct file *file, unsigned int cmd,
 	return error;
 }
 
+static int selinux_file_ioctl_compat(struct file *file, unsigned int cmd,
+			      unsigned long arg)
+{
+	/*
+	 * If we are in a 64-bit kernel running 32-bit userspace, we need to
+	 * make sure we don't compare 32-bit flags to 64-bit flags.
+	 */
+	switch (cmd) {
+	case FS_IOC32_GETFLAGS:
+		cmd = FS_IOC_GETFLAGS;
+		break;
+	case FS_IOC32_SETFLAGS:
+		cmd = FS_IOC_SETFLAGS;
+		break;
+	case FS_IOC32_GETVERSION:
+		cmd = FS_IOC_GETVERSION;
+		break;
+	case FS_IOC32_SETVERSION:
+		cmd = FS_IOC_SETVERSION;
+		break;
+	default:
+		break;
+	}
+
+	return selinux_file_ioctl(file, cmd, arg);
+}
+
 static int default_noexec __ro_after_init;
 
 static int file_map_prot_check(struct file *file, unsigned long prot, int shared)
@@ -7122,6 +7149,7 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = {
 	LSM_HOOK_INIT(file_permission, selinux_file_permission),
 	LSM_HOOK_INIT(file_alloc_security, selinux_file_alloc_security),
 	LSM_HOOK_INIT(file_ioctl, selinux_file_ioctl),
+	LSM_HOOK_INIT(file_ioctl_compat, selinux_file_ioctl_compat),
 	LSM_HOOK_INIT(mmap_file, selinux_mmap_file),
 	LSM_HOOK_INIT(mmap_addr, selinux_mmap_addr),
 	LSM_HOOK_INIT(file_mprotect, selinux_file_mprotect),
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index 53336d7daa93..c126f6a16de4 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -5051,6 +5051,7 @@ static struct security_hook_list smack_hooks[] __ro_after_init = {
 
 	LSM_HOOK_INIT(file_alloc_security, smack_file_alloc_security),
 	LSM_HOOK_INIT(file_ioctl, smack_file_ioctl),
+	LSM_HOOK_INIT(file_ioctl_compat, smack_file_ioctl),
 	LSM_HOOK_INIT(file_lock, smack_file_lock),
 	LSM_HOOK_INIT(file_fcntl, smack_file_fcntl),
 	LSM_HOOK_INIT(mmap_file, smack_mmap_file),
diff --git a/security/tomoyo/tomoyo.c b/security/tomoyo/tomoyo.c
index e10491f155a5..3c3af149bf1c 100644
--- a/security/tomoyo/tomoyo.c
+++ b/security/tomoyo/tomoyo.c
@@ -574,6 +574,7 @@ static struct security_hook_list tomoyo_hooks[] __ro_after_init = {
 	LSM_HOOK_INIT(path_rename, tomoyo_path_rename),
 	LSM_HOOK_INIT(inode_getattr, tomoyo_inode_getattr),
 	LSM_HOOK_INIT(file_ioctl, tomoyo_file_ioctl),
+	LSM_HOOK_INIT(file_ioctl_compat, tomoyo_file_ioctl),
 	LSM_HOOK_INIT(path_chmod, tomoyo_path_chmod),
 	LSM_HOOK_INIT(path_chown, tomoyo_path_chown),
 	LSM_HOOK_INIT(path_chroot, tomoyo_path_chroot),
-- 
cgit v1.2.3


From 8645e659e2d227f6ce8fcea1ac640c324fbbb3e6 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 22 Dec 2023 21:05:56 -0800
Subject: iio: linux/iio.h: fix Excess kernel-doc description warning

Remove the @of_xlate: lines to prevent the kernel-doc warning:

include/linux/iio/iio.h:534: warning: Excess struct member 'of_xlate' description in 'iio_info'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Jonathan Cameron <jic23@kernel.org>
Cc: Lars-Peter Clausen <lars@metafoo.de>
Cc: linux-iio@vger.kernel.org
Link: https://lore.kernel.org/r/20231223050556.13948-1-rdunlap@infradead.org
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 include/linux/iio/iio.h | 6 ------
 1 file changed, 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index d0ce3b71106a..c5b36d2c1e73 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -434,13 +434,7 @@ struct iio_trigger; /* forward declaration */
  * @update_scan_mode:	function to configure device and scan buffer when
  *			channels have changed
  * @debugfs_reg_access:	function to read or write register value of device
- * @of_xlate:		function pointer to obtain channel specifier index.
- *			When #iio-cells is greater than '0', the driver could
- *			provide a custom of_xlate function that reads the
- *			*args* and returns the appropriate index in registered
- *			IIO channels array.
  * @fwnode_xlate:	fwnode based function pointer to obtain channel specifier index.
- *			Functionally the same as @of_xlate.
  * @hwfifo_set_watermark: function pointer to set the current hardware
  *			fifo watermark level; see hwfifo_* entries in
  *			Documentation/ABI/testing/sysfs-bus-iio for details on
-- 
cgit v1.2.3


From 02d374f3418df577c850f0cd45c3da9245ead547 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 26 Dec 2023 08:15:24 +0000
Subject: block: renumber QUEUE_FLAG_HW_WC

For the QUEUE_FLAG_HW_WC to actually work, it needs to have a separate
number from QUEUE_FLAG_FUA, doh.

Fixes: 43c9835b144c ("block: don't allow enabling a cache on devices that don't support it")
Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20231226081524.180289-1-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blkdev.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 51fa7ffdee83..88e9dd4b71fb 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -538,7 +538,7 @@ struct request_queue {
 #define QUEUE_FLAG_ADD_RANDOM	10	/* Contributes to random pool */
 #define QUEUE_FLAG_SYNCHRONOUS	11	/* always completes in submit context */
 #define QUEUE_FLAG_SAME_FORCE	12	/* force complete on same CPU */
-#define QUEUE_FLAG_HW_WC	18	/* Write back caching supported */
+#define QUEUE_FLAG_HW_WC	13	/* Write back caching supported */
 #define QUEUE_FLAG_INIT_DONE	14	/* queue is initialized */
 #define QUEUE_FLAG_STABLE_WRITES 15	/* don't modify blks until WB is done */
 #define QUEUE_FLAG_POLL		16	/* IO polling enabled if set */
-- 
cgit v1.2.3


From 1c042f8d4bc342b7985b1de3d76836f1a1083b65 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 21 Dec 2023 08:05:38 +0100
Subject: block: reject invalid operation in submit_bio_noacct

submit_bio_noacct allows completely invalid operations, or operations
that are not supported in the bio path.  Extent the existing switch
statement to rejcect all invalid types.

Move the code point for REQ_OP_ZONE_APPEND so that it's not right in the
middle of the zone management operations and the switch statement can
follow the numerical order of the operations.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20231221070538.1112446-1-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c          | 26 +++++++++++++++++++++-----
 include/linux/blk_types.h |  8 ++++----
 2 files changed, 25 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/block/blk-core.c b/block/blk-core.c
index fdf25b8d6e78..9520ccab3050 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -764,6 +764,15 @@ void submit_bio_noacct(struct bio *bio)
 		bio_clear_polled(bio);
 
 	switch (bio_op(bio)) {
+	case REQ_OP_READ:
+	case REQ_OP_WRITE:
+		break;
+	case REQ_OP_FLUSH:
+		/*
+		 * REQ_OP_FLUSH can't be submitted through bios, it is only
+		 * synthetized in struct request by the flush state machine.
+		 */
+		goto not_supported;
 	case REQ_OP_DISCARD:
 		if (!bdev_max_discard_sectors(bdev))
 			goto not_supported;
@@ -777,6 +786,10 @@ void submit_bio_noacct(struct bio *bio)
 		if (status != BLK_STS_OK)
 			goto end_io;
 		break;
+	case REQ_OP_WRITE_ZEROES:
+		if (!q->limits.max_write_zeroes_sectors)
+			goto not_supported;
+		break;
 	case REQ_OP_ZONE_RESET:
 	case REQ_OP_ZONE_OPEN:
 	case REQ_OP_ZONE_CLOSE:
@@ -788,12 +801,15 @@ void submit_bio_noacct(struct bio *bio)
 		if (!bdev_is_zoned(bio->bi_bdev) || !blk_queue_zone_resetall(q))
 			goto not_supported;
 		break;
-	case REQ_OP_WRITE_ZEROES:
-		if (!q->limits.max_write_zeroes_sectors)
-			goto not_supported;
-		break;
+	case REQ_OP_DRV_IN:
+	case REQ_OP_DRV_OUT:
+		/*
+		 * Driver private operations are only used with passthrough
+		 * requests.
+		 */
+		fallthrough;
 	default:
-		break;
+		goto not_supported;
 	}
 
 	if (blk_throtl_bio(bio))
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index d5c5e59ddbd2..68c9eb2374a4 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -378,6 +378,8 @@ enum req_op {
 	REQ_OP_DISCARD		= (__force blk_opf_t)3,
 	/* securely erase sectors */
 	REQ_OP_SECURE_ERASE	= (__force blk_opf_t)5,
+	/* write data at the current zone write pointer */
+	REQ_OP_ZONE_APPEND	= (__force blk_opf_t)7,
 	/* write the zero filled sector many times */
 	REQ_OP_WRITE_ZEROES	= (__force blk_opf_t)9,
 	/* Open a zone */
@@ -386,12 +388,10 @@ enum req_op {
 	REQ_OP_ZONE_CLOSE	= (__force blk_opf_t)11,
 	/* Transition a zone to full */
 	REQ_OP_ZONE_FINISH	= (__force blk_opf_t)12,
-	/* write data at the current zone write pointer */
-	REQ_OP_ZONE_APPEND	= (__force blk_opf_t)13,
 	/* reset a zone write pointer */
-	REQ_OP_ZONE_RESET	= (__force blk_opf_t)15,
+	REQ_OP_ZONE_RESET	= (__force blk_opf_t)13,
 	/* reset all the zone present on the device */
-	REQ_OP_ZONE_RESET_ALL	= (__force blk_opf_t)17,
+	REQ_OP_ZONE_RESET_ALL	= (__force blk_opf_t)15,
 
 	/* Driver private requests */
 	REQ_OP_DRV_IN		= (__force blk_opf_t)34,
-- 
cgit v1.2.3


From b40584d145700addc70cc29e4f0850a4ed955b1c Mon Sep 17 00:00:00 2001
From: Wen Gu <guwen@linux.alibaba.com>
Date: Tue, 19 Dec 2023 22:26:13 +0800
Subject: net/smc: compatible with 128-bits extended GID of virtual ISM device

According to virtual ISM support feature defined by SMCv2.1, GIDs of
virtual ISM device are UUIDs defined by RFC4122, which are 128-bits
long. So some adaptation work is required. And note that the GIDs of
existing platform firmware ISM devices still remain 64-bits long.

Signed-off-by: Wen Gu <guwen@linux.alibaba.com>
Reviewed-by: Alexandra Winter <wintera@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/ism_drv.c | 19 +++++++------
 include/net/smc.h          | 15 +++++++----
 net/smc/af_smc.c           | 66 +++++++++++++++++++++++++++++++++++++---------
 net/smc/smc.h              |  3 ---
 net/smc/smc_clc.c          | 43 ++++++++++++++++++++++--------
 net/smc/smc_clc.h          | 10 +++++--
 net/smc/smc_core.c         | 31 +++++++++++++++-------
 net/smc/smc_core.h         | 17 ++++++++----
 net/smc/smc_diag.c         |  7 +++--
 net/smc/smc_ism.c          | 17 +++++++-----
 net/smc/smc_ism.h          |  3 ++-
 net/smc/smc_pnet.c         |  4 +--
 12 files changed, 167 insertions(+), 68 deletions(-)

(limited to 'include')

diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c
index 81aabbfbbe2c..34dd06324e38 100644
--- a/drivers/s390/net/ism_drv.c
+++ b/drivers/s390/net/ism_drv.c
@@ -743,10 +743,10 @@ static int ism_query_rgid(struct ism_dev *ism, u64 rgid, u32 vid_valid,
 	return ism_cmd(ism, &cmd);
 }
 
-static int smcd_query_rgid(struct smcd_dev *smcd, u64 rgid, u32 vid_valid,
-			   u32 vid)
+static int smcd_query_rgid(struct smcd_dev *smcd, struct smcd_gid *rgid,
+			   u32 vid_valid, u32 vid)
 {
-	return ism_query_rgid(smcd->priv, rgid, vid_valid, vid);
+	return ism_query_rgid(smcd->priv, rgid->gid, vid_valid, vid);
 }
 
 static int smcd_register_dmb(struct smcd_dev *smcd, struct smcd_dmb *dmb,
@@ -797,10 +797,11 @@ static int ism_signal_ieq(struct ism_dev *ism, u64 rgid, u32 trigger_irq,
 	return ism_cmd(ism, &cmd);
 }
 
-static int smcd_signal_ieq(struct smcd_dev *smcd, u64 rgid, u32 trigger_irq,
-			   u32 event_code, u64 info)
+static int smcd_signal_ieq(struct smcd_dev *smcd, struct smcd_gid *rgid,
+			   u32 trigger_irq, u32 event_code, u64 info)
 {
-	return ism_signal_ieq(smcd->priv, rgid, trigger_irq, event_code, info);
+	return ism_signal_ieq(smcd->priv, rgid->gid,
+			      trigger_irq, event_code, info);
 }
 
 static int smcd_move(struct smcd_dev *smcd, u64 dmb_tok, unsigned int idx,
@@ -821,9 +822,11 @@ static u64 ism_get_local_gid(struct ism_dev *ism)
 	return ism->local_gid;
 }
 
-static u64 smcd_get_local_gid(struct smcd_dev *smcd)
+static void smcd_get_local_gid(struct smcd_dev *smcd,
+			       struct smcd_gid *smcd_gid)
 {
-	return ism_get_local_gid(smcd->priv);
+	smcd_gid->gid = ism_get_local_gid(smcd->priv);
+	smcd_gid->gid_ext = 0;
 }
 
 static u16 ism_get_chid(struct ism_dev *ism)
diff --git a/include/net/smc.h b/include/net/smc.h
index a002552be29c..a0dc1187e96e 100644
--- a/include/net/smc.h
+++ b/include/net/smc.h
@@ -52,9 +52,14 @@ struct smcd_dmb {
 struct smcd_dev;
 struct ism_client;
 
+struct smcd_gid {
+	u64	gid;
+	u64	gid_ext;
+};
+
 struct smcd_ops {
-	int (*query_remote_gid)(struct smcd_dev *dev, u64 rgid, u32 vid_valid,
-				u32 vid);
+	int (*query_remote_gid)(struct smcd_dev *dev, struct smcd_gid *rgid,
+				u32 vid_valid, u32 vid);
 	int (*register_dmb)(struct smcd_dev *dev, struct smcd_dmb *dmb,
 			    struct ism_client *client);
 	int (*unregister_dmb)(struct smcd_dev *dev, struct smcd_dmb *dmb);
@@ -62,14 +67,14 @@ struct smcd_ops {
 	int (*del_vlan_id)(struct smcd_dev *dev, u64 vlan_id);
 	int (*set_vlan_required)(struct smcd_dev *dev);
 	int (*reset_vlan_required)(struct smcd_dev *dev);
-	int (*signal_event)(struct smcd_dev *dev, u64 rgid, u32 trigger_irq,
-			    u32 event_code, u64 info);
+	int (*signal_event)(struct smcd_dev *dev, struct smcd_gid *rgid,
+			    u32 trigger_irq, u32 event_code, u64 info);
 	int (*move_data)(struct smcd_dev *dev, u64 dmb_tok, unsigned int idx,
 			 bool sf, unsigned int offset, void *data,
 			 unsigned int size);
 	int (*supports_v2)(void);
 	u8* (*get_system_eid)(void);
-	u64 (*get_local_gid)(struct smcd_dev *dev);
+	void (*get_local_gid)(struct smcd_dev *dev, struct smcd_gid *gid);
 	u16 (*get_chid)(struct smcd_dev *dev);
 	struct device* (*get_dev)(struct smcd_dev *dev);
 };
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index c0d3852fa429..a2cb30af46cb 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1044,7 +1044,8 @@ static int smc_find_ism_v2_device_clnt(struct smc_sock *smc,
 {
 	int rc = SMC_CLC_DECL_NOSMCDDEV;
 	struct smcd_dev *smcd;
-	int i = 1;
+	int i = 1, entry = 1;
+	bool is_virtual;
 	u16 chid;
 
 	if (smcd_indicated(ini->smc_type_v1))
@@ -1056,14 +1057,23 @@ static int smc_find_ism_v2_device_clnt(struct smc_sock *smc,
 		chid = smc_ism_get_chid(smcd);
 		if (!smc_find_ism_v2_is_unique_chid(chid, ini, i))
 			continue;
+		is_virtual = __smc_ism_is_virtual(chid);
 		if (!smc_pnet_is_pnetid_set(smcd->pnetid) ||
 		    smc_pnet_is_ndev_pnetid(sock_net(&smc->sk), smcd->pnetid)) {
+			if (is_virtual && entry == SMCD_CLC_MAX_V2_GID_ENTRIES)
+				/* It's the last GID-CHID entry left in CLC
+				 * Proposal SMC-Dv2 extension, but a virtual
+				 * ISM device will take two entries. So give
+				 * up it and try the next potential ISM device.
+				 */
+				continue;
 			ini->ism_dev[i] = smcd;
 			ini->ism_chid[i] = chid;
 			ini->is_smcd = true;
 			rc = 0;
 			i++;
-			if (i > SMC_MAX_ISM_DEVS)
+			entry = is_virtual ? entry + 2 : entry + 1;
+			if (entry > SMCD_CLC_MAX_V2_GID_ENTRIES)
 				break;
 		}
 	}
@@ -1402,8 +1412,13 @@ static int smc_connect_ism(struct smc_sock *smc,
 		rc = smc_v2_determine_accepted_chid(aclc, ini);
 		if (rc)
 			return rc;
+
+		if (__smc_ism_is_virtual(ini->ism_chid[ini->ism_selected]))
+			ini->ism_peer_gid[ini->ism_selected].gid_ext =
+						ntohll(aclc->d1.gid_ext);
+		/* for non-virtual ISM devices, peer gid_ext remains 0. */
 	}
-	ini->ism_peer_gid[ini->ism_selected] = ntohll(aclc->d0.gid);
+	ini->ism_peer_gid[ini->ism_selected].gid = ntohll(aclc->d0.gid);
 
 	/* there is only one lgr role for SMC-D; use server lock */
 	mutex_lock(&smc_server_lgr_pending);
@@ -2088,7 +2103,8 @@ static bool smc_is_already_selected(struct smcd_dev *smcd,
 
 /* check for ISM devices matching proposed ISM devices */
 static void smc_check_ism_v2_match(struct smc_init_info *ini,
-				   u16 proposed_chid, u64 proposed_gid,
+				   u16 proposed_chid,
+				   struct smcd_gid *proposed_gid,
 				   unsigned int *matches)
 {
 	struct smcd_dev *smcd;
@@ -2100,7 +2116,11 @@ static void smc_check_ism_v2_match(struct smc_init_info *ini,
 			continue;
 		if (smc_ism_get_chid(smcd) == proposed_chid &&
 		    !smc_ism_cantalk(proposed_gid, ISM_RESERVED_VLANID, smcd)) {
-			ini->ism_peer_gid[*matches] = proposed_gid;
+			ini->ism_peer_gid[*matches].gid = proposed_gid->gid;
+			if (__smc_ism_is_virtual(proposed_chid))
+				ini->ism_peer_gid[*matches].gid_ext =
+							proposed_gid->gid_ext;
+				/* non-virtual ISM's peer gid_ext remains 0. */
 			ini->ism_dev[*matches] = smcd;
 			(*matches)++;
 			break;
@@ -2122,9 +2142,11 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc,
 	struct smc_clc_v2_extension *smc_v2_ext;
 	struct smc_clc_msg_smcd *pclc_smcd;
 	unsigned int matches = 0;
+	struct smcd_gid smcd_gid;
 	u8 smcd_version;
 	u8 *eid = NULL;
 	int i, rc;
+	u16 chid;
 
 	if (!(ini->smcd_version & SMC_V2) || !smcd_indicated(ini->smc_type_v2))
 		goto not_found;
@@ -2134,18 +2156,35 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc,
 	smcd_v2_ext = smc_get_clc_smcd_v2_ext(smc_v2_ext);
 
 	mutex_lock(&smcd_dev_list.mutex);
-	if (pclc_smcd->ism.chid)
+	if (pclc_smcd->ism.chid) {
 		/* check for ISM device matching proposed native ISM device */
+		smcd_gid.gid = ntohll(pclc_smcd->ism.gid);
+		smcd_gid.gid_ext = 0;
 		smc_check_ism_v2_match(ini, ntohs(pclc_smcd->ism.chid),
-				       ntohll(pclc_smcd->ism.gid), &matches);
-	for (i = 1; i <= smc_v2_ext->hdr.ism_gid_cnt; i++) {
+				       &smcd_gid, &matches);
+	}
+	for (i = 0; i < smc_v2_ext->hdr.ism_gid_cnt; i++) {
 		/* check for ISM devices matching proposed non-native ISM
 		 * devices
 		 */
-		smc_check_ism_v2_match(ini,
-				       ntohs(smcd_v2_ext->gidchid[i - 1].chid),
-				       ntohll(smcd_v2_ext->gidchid[i - 1].gid),
-				       &matches);
+		smcd_gid.gid = ntohll(smcd_v2_ext->gidchid[i].gid);
+		smcd_gid.gid_ext = 0;
+		chid = ntohs(smcd_v2_ext->gidchid[i].chid);
+		if (__smc_ism_is_virtual(chid)) {
+			if ((i + 1) == smc_v2_ext->hdr.ism_gid_cnt ||
+			    chid != ntohs(smcd_v2_ext->gidchid[i + 1].chid))
+				/* each virtual ISM device takes two GID-CHID
+				 * entries and CHID of the second entry repeats
+				 * that of the first entry.
+				 *
+				 * So check if the next GID-CHID entry exists
+				 * and both two entries' CHIDs are the same.
+				 */
+				continue;
+			smcd_gid.gid_ext =
+				ntohll(smcd_v2_ext->gidchid[++i].gid);
+		}
+		smc_check_ism_v2_match(ini, chid, &smcd_gid, &matches);
 	}
 	mutex_unlock(&smcd_dev_list.mutex);
 
@@ -2194,7 +2233,8 @@ static void smc_find_ism_v1_device_serv(struct smc_sock *new_smc,
 	if (!(ini->smcd_version & SMC_V1) || !smcd_indicated(ini->smc_type_v1))
 		goto not_found;
 	ini->is_smcd = true; /* prepare ISM check */
-	ini->ism_peer_gid[0] = ntohll(pclc_smcd->ism.gid);
+	ini->ism_peer_gid[0].gid = ntohll(pclc_smcd->ism.gid);
+	ini->ism_peer_gid[0].gid_ext = 0;
 	rc = smc_find_ism_device(new_smc, ini);
 	if (rc)
 		goto not_found;
diff --git a/net/smc/smc.h b/net/smc/smc.h
index 0dc722bf6055..df64efd2dee8 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -29,9 +29,6 @@
 #define SMCPROTO_SMC		0	/* SMC protocol, IPv4 */
 #define SMCPROTO_SMC6		1	/* SMC protocol, IPv6 */
 
-#define SMC_MAX_ISM_DEVS	8	/* max # of proposed non-native ISM
-					 * devices
-					 */
 #define SMC_AUTOCORKING_DEFAULT_SIZE	0x10000	/* 64K by default */
 
 extern struct proto smc_proto;
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index 900d307c17a9..b43be3cafdcc 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -883,11 +883,13 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini)
 		       ETH_ALEN);
 	}
 	if (smcd_indicated(ini->smc_type_v1)) {
+		struct smcd_gid smcd_gid;
+
 		/* add SMC-D specifics */
 		if (ini->ism_dev[0]) {
 			smcd = ini->ism_dev[0];
-			pclc_smcd->ism.gid =
-				htonll(smcd->ops->get_local_gid(smcd));
+			smcd->ops->get_local_gid(smcd, &smcd_gid);
+			pclc_smcd->ism.gid = htonll(smcd_gid.gid);
 			pclc_smcd->ism.chid =
 				htons(smc_ism_get_chid(ini->ism_dev[0]));
 		}
@@ -920,10 +922,11 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini)
 		read_unlock(&smc_clc_eid_table.lock);
 	}
 	if (smcd_indicated(ini->smc_type_v2)) {
+		struct smcd_gid smcd_gid;
 		u8 *eid = NULL;
+		int entry = 0;
 
 		v2_ext->hdr.flag.seid = smc_clc_eid_table.seid_enabled;
-		v2_ext->hdr.ism_gid_cnt = ini->ism_offered_cnt;
 		v2_ext->hdr.smcd_v2_ext_offset = htons(sizeof(*v2_ext) -
 				offsetofend(struct smc_clnt_opts_area_hdr,
 					    smcd_v2_ext_offset) +
@@ -935,14 +938,26 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini)
 		if (ini->ism_offered_cnt) {
 			for (i = 1; i <= ini->ism_offered_cnt; i++) {
 				smcd = ini->ism_dev[i];
-				gidchids[i - 1].gid =
-					htonll(smcd->ops->get_local_gid(smcd));
-				gidchids[i - 1].chid =
+				smcd->ops->get_local_gid(smcd, &smcd_gid);
+				gidchids[entry].chid =
 					htons(smc_ism_get_chid(ini->ism_dev[i]));
+				gidchids[entry].gid = htonll(smcd_gid.gid);
+				if (smc_ism_is_virtual(smcd)) {
+					/* a virtual ISM device takes two
+					 * entries. CHID of the second entry
+					 * repeats that of the first entry.
+					 */
+					gidchids[entry + 1].chid =
+						gidchids[entry].chid;
+					gidchids[entry + 1].gid =
+						htonll(smcd_gid.gid_ext);
+					entry++;
+				}
+				entry++;
 			}
-			plen += ini->ism_offered_cnt *
-				sizeof(struct smc_clc_smcd_gid_chid);
+			plen += entry * sizeof(struct smc_clc_smcd_gid_chid);
 		}
+		v2_ext->hdr.ism_gid_cnt = entry;
 	}
 	if (smcr_indicated(ini->smc_type_v2)) {
 		memcpy(v2_ext->roce, ini->smcrv2.ib_gid_v2, SMC_GID_SIZE);
@@ -978,7 +993,7 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini)
 			vec[i++].iov_len = sizeof(*smcd_v2_ext);
 			if (ini->ism_offered_cnt) {
 				vec[i].iov_base = gidchids;
-				vec[i++].iov_len = ini->ism_offered_cnt *
+				vec[i++].iov_len = v2_ext->hdr.ism_gid_cnt *
 					sizeof(struct smc_clc_smcd_gid_chid);
 			}
 		}
@@ -1009,13 +1024,16 @@ smcd_clc_prep_confirm_accept(struct smc_connection *conn,
 			     struct smc_clc_msg_trail *trl)
 {
 	struct smcd_dev *smcd = conn->lgr->smcd;
+	struct smcd_gid smcd_gid;
+	u16 chid;
 	int len;
 
 	/* SMC-D specific settings */
 	memcpy(clc->hdr.eyecatcher, SMCD_EYECATCHER,
 	       sizeof(SMCD_EYECATCHER));
+	smcd->ops->get_local_gid(smcd, &smcd_gid);
 	clc->hdr.typev1 = SMC_TYPE_D;
-	clc->d0.gid = htonll(smcd->ops->get_local_gid(smcd));
+	clc->d0.gid = htonll(smcd_gid.gid);
 	clc->d0.token = htonll(conn->rmb_desc->token);
 	clc->d0.dmbe_size = conn->rmbe_size_comp;
 	clc->d0.dmbe_idx = 0;
@@ -1023,9 +1041,12 @@ smcd_clc_prep_confirm_accept(struct smc_connection *conn,
 	if (version == SMC_V1) {
 		clc->hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN);
 	} else {
-		clc->d1.chid = htons(smc_ism_get_chid(smcd));
+		chid = smc_ism_get_chid(smcd);
+		clc->d1.chid = htons(chid);
 		if (eid && eid[0])
 			memcpy(clc->d1.eid, eid, SMC_MAX_EID_LEN);
+		if (__smc_ism_is_virtual(chid))
+			clc->d1.gid_ext = htonll(smcd_gid.gid_ext);
 		len = SMCD_CLC_ACCEPT_CONFIRM_LEN_V2;
 		if (first_contact) {
 			*fce_len = smc_clc_fill_fce_v2x(fce_v2x, ini);
diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h
index c187d5f09d02..a9f9bdd26dcd 100644
--- a/net/smc/smc_clc.h
+++ b/net/smc/smc_clc.h
@@ -172,6 +172,11 @@ struct smc_clc_msg_proposal {	/* clc proposal message sent by Linux */
 
 #define SMC_CLC_MAX_V6_PREFIX		8
 #define SMC_CLC_MAX_UEID		8
+#define SMCD_CLC_MAX_V2_GID_ENTRIES	8 /* max # of CHID-GID entries in CLC
+					   * proposal SMC-Dv2 extension.
+					   * each ISM device takes one entry and
+					   * each virtual ISM takes two entries.
+					   */
 
 struct smc_clc_msg_proposal_area {
 	struct smc_clc_msg_proposal		pclc_base;
@@ -181,7 +186,8 @@ struct smc_clc_msg_proposal_area {
 	struct smc_clc_v2_extension		pclc_v2_ext;
 	u8			user_eids[SMC_CLC_MAX_UEID][SMC_MAX_EID_LEN];
 	struct smc_clc_smcd_v2_extension	pclc_smcd_v2_ext;
-	struct smc_clc_smcd_gid_chid		pclc_gidchids[SMC_MAX_ISM_DEVS];
+	struct smc_clc_smcd_gid_chid
+				pclc_gidchids[SMCD_CLC_MAX_V2_GID_ENTRIES];
 	struct smc_clc_msg_trail		pclc_trl;
 };
 
@@ -277,7 +283,7 @@ struct smc_clc_msg_accept_confirm {	/* clc accept / confirm message */
 			struct { /* v2 only, but 12 bytes reserved in v1 */
 				__be16 chid;
 				u8 eid[SMC_MAX_EID_LEN];
-				u8 reserved5[8];
+				__be64 gid_ext;
 			} __packed d1;
 		};
 	};
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index d520ee62c8ec..672eff087732 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -506,6 +506,7 @@ static int smc_nl_fill_smcd_lgr(struct smc_link_group *lgr,
 {
 	char smc_pnet[SMC_MAX_PNETID_LEN + 1];
 	struct smcd_dev *smcd = lgr->smcd;
+	struct smcd_gid smcd_gid;
 	struct nlattr *attrs;
 	void *nlh;
 
@@ -521,11 +522,11 @@ static int smc_nl_fill_smcd_lgr(struct smc_link_group *lgr,
 
 	if (nla_put_u32(skb, SMC_NLA_LGR_D_ID, *((u32 *)&lgr->id)))
 		goto errattr;
+	smcd->ops->get_local_gid(smcd, &smcd_gid);
 	if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_GID,
-			      smcd->ops->get_local_gid(smcd),
-				  SMC_NLA_LGR_D_PAD))
+			      smcd_gid.gid, SMC_NLA_LGR_D_PAD))
 		goto errattr;
-	if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_PEER_GID, lgr->peer_gid,
+	if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_PEER_GID, lgr->peer_gid.gid,
 			      SMC_NLA_LGR_D_PAD))
 		goto errattr;
 	if (nla_put_u8(skb, SMC_NLA_LGR_D_VLAN_ID, lgr->vlan_id))
@@ -876,7 +877,10 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini)
 		/* SMC-D specific settings */
 		smcd = ini->ism_dev[ini->ism_selected];
 		get_device(smcd->ops->get_dev(smcd));
-		lgr->peer_gid = ini->ism_peer_gid[ini->ism_selected];
+		lgr->peer_gid.gid =
+			ini->ism_peer_gid[ini->ism_selected].gid;
+		lgr->peer_gid.gid_ext =
+			ini->ism_peer_gid[ini->ism_selected].gid_ext;
 		lgr->smcd = ini->ism_dev[ini->ism_selected];
 		lgr_list = &ini->ism_dev[ini->ism_selected]->lgr_list;
 		lgr_lock = &lgr->smcd->lgr_lock;
@@ -1514,7 +1518,8 @@ void smc_lgr_terminate_sched(struct smc_link_group *lgr)
 }
 
 /* Called when peer lgr shutdown (regularly or abnormally) is received */
-void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid, unsigned short vlan)
+void smc_smcd_terminate(struct smcd_dev *dev, struct smcd_gid *peer_gid,
+			unsigned short vlan)
 {
 	struct smc_link_group *lgr, *l;
 	LIST_HEAD(lgr_free_list);
@@ -1522,9 +1527,12 @@ void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid, unsigned short vlan)
 	/* run common cleanup function and build free list */
 	spin_lock_bh(&dev->lgr_lock);
 	list_for_each_entry_safe(lgr, l, &dev->lgr_list, list) {
-		if ((!peer_gid || lgr->peer_gid == peer_gid) &&
+		if ((!peer_gid->gid ||
+		     (lgr->peer_gid.gid == peer_gid->gid &&
+		      !smc_ism_is_virtual(dev) ? 1 :
+		      lgr->peer_gid.gid_ext == peer_gid->gid_ext)) &&
 		    (vlan == VLAN_VID_MASK || lgr->vlan_id == vlan)) {
-			if (peer_gid) /* peer triggered termination */
+			if (peer_gid->gid) /* peer triggered termination */
 				lgr->peer_shutdown = 1;
 			list_move(&lgr->list, &lgr_free_list);
 			lgr->freeing = 1;
@@ -1860,9 +1868,12 @@ static bool smcr_lgr_match(struct smc_link_group *lgr, u8 smcr_version,
 }
 
 static bool smcd_lgr_match(struct smc_link_group *lgr,
-			   struct smcd_dev *smcismdev, u64 peer_gid)
+			   struct smcd_dev *smcismdev,
+			   struct smcd_gid *peer_gid)
 {
-	return lgr->peer_gid == peer_gid && lgr->smcd == smcismdev;
+	return lgr->peer_gid.gid == peer_gid->gid && lgr->smcd == smcismdev &&
+		smc_ism_is_virtual(smcismdev) ?
+		(lgr->peer_gid.gid_ext == peer_gid->gid_ext) : 1;
 }
 
 /* create a new SMC connection (and a new link group if necessary) */
@@ -1892,7 +1903,7 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini)
 		write_lock_bh(&lgr->conns_lock);
 		if ((ini->is_smcd ?
 		     smcd_lgr_match(lgr, ini->ism_dev[ini->ism_selected],
-				    ini->ism_peer_gid[ini->ism_selected]) :
+				    &ini->ism_peer_gid[ini->ism_selected]) :
 		     smcr_lgr_match(lgr, ini->smcr_version,
 				    ini->peer_systemid,
 				    ini->peer_gid, ini->peer_mac, role,
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index 9f656780d46c..1f175376037b 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -17,9 +17,11 @@
 #include <linux/pci.h>
 #include <rdma/ib_verbs.h>
 #include <net/genetlink.h>
+#include <net/smc.h>
 
 #include "smc.h"
 #include "smc_ib.h"
+#include "smc_clc.h"
 
 #define SMC_RMBS_PER_LGR_MAX	255	/* max. # of RMBs per link group */
 #define SMC_CONN_PER_LGR_MIN	16	/* min. # of connections per link group */
@@ -355,7 +357,7 @@ struct smc_link_group {
 						/* max links can be added in lgr */
 		};
 		struct { /* SMC-D */
-			u64			peer_gid;
+			struct smcd_gid		peer_gid;
 						/* Peer GID (remote) */
 			struct smcd_dev		*smcd;
 						/* ISM device for VLAN reg. */
@@ -392,6 +394,11 @@ struct smc_init_info_smcrv2 {
 	struct smc_gidlist	gidlist;
 };
 
+#define SMC_MAX_V2_ISM_DEVS	SMCD_CLC_MAX_V2_GID_ENTRIES
+				/* max # of proposed non-native ISM devices,
+				 * which can't exceed the max # of CHID-GID
+				 * entries in CLC proposal SMC-Dv2 extension.
+				 */
 struct smc_init_info {
 	u8			is_smcd;
 	u8			smc_type_v1;
@@ -417,9 +424,9 @@ struct smc_init_info {
 	u32			ib_clcqpn;
 	struct smc_init_info_smcrv2 smcrv2;
 	/* SMC-D */
-	u64			ism_peer_gid[SMC_MAX_ISM_DEVS + 1];
-	struct smcd_dev		*ism_dev[SMC_MAX_ISM_DEVS + 1];
-	u16			ism_chid[SMC_MAX_ISM_DEVS + 1];
+	struct smcd_gid		ism_peer_gid[SMC_MAX_V2_ISM_DEVS + 1];
+	struct smcd_dev		*ism_dev[SMC_MAX_V2_ISM_DEVS + 1];
+	u16			ism_chid[SMC_MAX_V2_ISM_DEVS + 1];
 	u8			ism_offered_cnt; /* # of ISM devices offered */
 	u8			ism_selected;    /* index of selected ISM dev*/
 	u8			smcd_version;
@@ -545,7 +552,7 @@ void smc_lgr_hold(struct smc_link_group *lgr);
 void smc_lgr_put(struct smc_link_group *lgr);
 void smcr_port_add(struct smc_ib_device *smcibdev, u8 ibport);
 void smcr_port_err(struct smc_ib_device *smcibdev, u8 ibport);
-void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid,
+void smc_smcd_terminate(struct smcd_dev *dev, struct smcd_gid *peer_gid,
 			unsigned short vlan);
 void smc_smcd_terminate_all(struct smcd_dev *dev);
 void smc_smcr_terminate_all(struct smc_ib_device *smcibdev);
diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c
index a584613aca12..c180c180d0d1 100644
--- a/net/smc/smc_diag.c
+++ b/net/smc/smc_diag.c
@@ -21,6 +21,7 @@
 
 #include "smc.h"
 #include "smc_core.h"
+#include "smc_ism.h"
 
 struct smc_diag_dump_ctx {
 	int pos[2];
@@ -168,12 +169,14 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb,
 		struct smc_connection *conn = &smc->conn;
 		struct smcd_diag_dmbinfo dinfo;
 		struct smcd_dev *smcd = conn->lgr->smcd;
+		struct smcd_gid smcd_gid;
 
 		memset(&dinfo, 0, sizeof(dinfo));
 
 		dinfo.linkid = *((u32 *)conn->lgr->id);
-		dinfo.peer_gid = conn->lgr->peer_gid;
-		dinfo.my_gid = smcd->ops->get_local_gid(smcd);
+		dinfo.peer_gid = conn->lgr->peer_gid.gid;
+		smcd->ops->get_local_gid(smcd, &smcd_gid);
+		dinfo.my_gid = smcd_gid.gid;
 		dinfo.token = conn->rmb_desc->token;
 		dinfo.peer_token = conn->peer_token;
 
diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c
index fbee2493091f..a33f861cf7c1 100644
--- a/net/smc/smc_ism.c
+++ b/net/smc/smc_ism.c
@@ -44,7 +44,8 @@ static struct ism_client smc_ism_client = {
 #endif
 
 /* Test if an ISM communication is possible - same CPC */
-int smc_ism_cantalk(u64 peer_gid, unsigned short vlan_id, struct smcd_dev *smcd)
+int smc_ism_cantalk(struct smcd_gid *peer_gid, unsigned short vlan_id,
+		    struct smcd_dev *smcd)
 {
 	return smcd->ops->query_remote_gid(smcd, peer_gid, vlan_id ? 1 : 0,
 					   vlan_id);
@@ -208,7 +209,7 @@ int smc_ism_register_dmb(struct smc_link_group *lgr, int dmb_len,
 	dmb.dmb_len = dmb_len;
 	dmb.sba_idx = dmb_desc->sba_idx;
 	dmb.vlan_id = lgr->vlan_id;
-	dmb.rgid = lgr->peer_gid;
+	dmb.rgid = lgr->peer_gid.gid;
 	rc = lgr->smcd->ops->register_dmb(lgr->smcd, &dmb, &smc_ism_client);
 	if (!rc) {
 		dmb_desc->sba_idx = dmb.sba_idx;
@@ -340,18 +341,20 @@ union smcd_sw_event_info {
 
 static void smcd_handle_sw_event(struct smc_ism_event_work *wrk)
 {
+	struct smcd_gid peer_gid = { .gid = wrk->event.tok,
+				     .gid_ext = 0 };
 	union smcd_sw_event_info ev_info;
 
 	ev_info.info = wrk->event.info;
 	switch (wrk->event.code) {
 	case ISM_EVENT_CODE_SHUTDOWN:	/* Peer shut down DMBs */
-		smc_smcd_terminate(wrk->smcd, wrk->event.tok, ev_info.vlan_id);
+		smc_smcd_terminate(wrk->smcd, &peer_gid, ev_info.vlan_id);
 		break;
 	case ISM_EVENT_CODE_TESTLINK:	/* Activity timer */
 		if (ev_info.code == ISM_EVENT_REQUEST) {
 			ev_info.code = ISM_EVENT_RESPONSE;
 			wrk->smcd->ops->signal_event(wrk->smcd,
-						     wrk->event.tok,
+						     &peer_gid,
 						     ISM_EVENT_REQUEST_IR,
 						     ISM_EVENT_CODE_TESTLINK,
 						     ev_info.info);
@@ -365,10 +368,12 @@ static void smc_ism_event_work(struct work_struct *work)
 {
 	struct smc_ism_event_work *wrk =
 		container_of(work, struct smc_ism_event_work, work);
+	struct smcd_gid smcd_gid = { .gid = wrk->event.tok,
+				     .gid_ext = 0 };
 
 	switch (wrk->event.type) {
 	case ISM_EVENT_GID:	/* GID event, token is peer GID */
-		smc_smcd_terminate(wrk->smcd, wrk->event.tok, VLAN_VID_MASK);
+		smc_smcd_terminate(wrk->smcd, &smcd_gid, VLAN_VID_MASK);
 		break;
 	case ISM_EVENT_DMB:
 		break;
@@ -525,7 +530,7 @@ int smc_ism_signal_shutdown(struct smc_link_group *lgr)
 	memcpy(ev_info.uid, lgr->id, SMC_LGR_ID_SIZE);
 	ev_info.vlan_id = lgr->vlan_id;
 	ev_info.code = ISM_EVENT_REQUEST;
-	rc = lgr->smcd->ops->signal_event(lgr->smcd, lgr->peer_gid,
+	rc = lgr->smcd->ops->signal_event(lgr->smcd, &lgr->peer_gid,
 					  ISM_EVENT_REQUEST_IR,
 					  ISM_EVENT_CODE_SHUTDOWN,
 					  ev_info.info);
diff --git a/net/smc/smc_ism.h b/net/smc/smc_ism.h
index d1228a615f23..0e5e563099ec 100644
--- a/net/smc/smc_ism.h
+++ b/net/smc/smc_ism.h
@@ -32,7 +32,8 @@ struct smc_ism_vlanid {			/* VLAN id set on ISM device */
 
 struct smcd_dev;
 
-int smc_ism_cantalk(u64 peer_gid, unsigned short vlan_id, struct smcd_dev *dev);
+int smc_ism_cantalk(struct smcd_gid *peer_gid, unsigned short vlan_id,
+		    struct smcd_dev *dev);
 void smc_ism_set_conn(struct smc_connection *conn);
 void smc_ism_unset_conn(struct smc_connection *conn);
 int smc_ism_get_vlan(struct smcd_dev *dev, unsigned short vlan_id);
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 11775401df68..9f2c58c5a86b 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -1103,8 +1103,8 @@ static void smc_pnet_find_ism_by_pnetid(struct net_device *ndev,
 	list_for_each_entry(ismdev, &smcd_dev_list.list, list) {
 		if (smc_pnet_match(ismdev->pnetid, ndev_pnetid) &&
 		    !ismdev->going_away &&
-		    (!ini->ism_peer_gid[0] ||
-		     !smc_ism_cantalk(ini->ism_peer_gid[0], ini->vlan_id,
+		    (!ini->ism_peer_gid[0].gid ||
+		     !smc_ism_cantalk(&ini->ism_peer_gid[0], ini->vlan_id,
 				      ismdev))) {
 			ini->ism_dev[0] = ismdev;
 			break;
-- 
cgit v1.2.3


From 01fd1617dbc6f558efd1811f2bc433659d1e8304 Mon Sep 17 00:00:00 2001
From: Wen Gu <guwen@linux.alibaba.com>
Date: Tue, 19 Dec 2023 22:26:14 +0800
Subject: net/smc: support extended GID in SMC-D lgr netlink attribute

Virtual ISM devices introduced in SMCv2.1 requires a 128 bit extended
GID vs. the existing ISM 64bit GID. So the 2nd 64 bit of extended GID
should be included in SMC-D linkgroup netlink attribute as well.

Signed-off-by: Wen Gu <guwen@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/smc.h      | 2 ++
 include/uapi/linux/smc_diag.h | 2 ++
 net/smc/smc_core.c            | 6 ++++++
 net/smc/smc_diag.c            | 2 ++
 4 files changed, 12 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h
index 837fcd4b0abc..b531e3ef011a 100644
--- a/include/uapi/linux/smc.h
+++ b/include/uapi/linux/smc.h
@@ -160,6 +160,8 @@ enum {
 	SMC_NLA_LGR_D_CHID,		/* u16 */
 	SMC_NLA_LGR_D_PAD,		/* flag */
 	SMC_NLA_LGR_D_V2_COMMON,	/* nest */
+	SMC_NLA_LGR_D_EXT_GID,		/* u64 */
+	SMC_NLA_LGR_D_PEER_EXT_GID,	/* u64 */
 	__SMC_NLA_LGR_D_MAX,
 	SMC_NLA_LGR_D_MAX = __SMC_NLA_LGR_D_MAX - 1
 };
diff --git a/include/uapi/linux/smc_diag.h b/include/uapi/linux/smc_diag.h
index 8cb3a6fef553..58eceb7f5df2 100644
--- a/include/uapi/linux/smc_diag.h
+++ b/include/uapi/linux/smc_diag.h
@@ -107,6 +107,8 @@ struct smcd_diag_dmbinfo {		/* SMC-D Socket internals */
 	__aligned_u64	my_gid;		/* My GID */
 	__aligned_u64	token;		/* Token of DMB */
 	__aligned_u64	peer_token;	/* Token of remote DMBE */
+	__aligned_u64	peer_gid_ext;	/* Peer GID (extended part) */
+	__aligned_u64	my_gid_ext;	/* My GID (extended part) */
 };
 
 #endif /* _UAPI_SMC_DIAG_H_ */
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 672eff087732..95cc95458e2d 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -526,9 +526,15 @@ static int smc_nl_fill_smcd_lgr(struct smc_link_group *lgr,
 	if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_GID,
 			      smcd_gid.gid, SMC_NLA_LGR_D_PAD))
 		goto errattr;
+	if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_EXT_GID,
+			      smcd_gid.gid_ext, SMC_NLA_LGR_D_PAD))
+		goto errattr;
 	if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_PEER_GID, lgr->peer_gid.gid,
 			      SMC_NLA_LGR_D_PAD))
 		goto errattr;
+	if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_PEER_EXT_GID,
+			      lgr->peer_gid.gid_ext, SMC_NLA_LGR_D_PAD))
+		goto errattr;
 	if (nla_put_u8(skb, SMC_NLA_LGR_D_VLAN_ID, lgr->vlan_id))
 		goto errattr;
 	if (nla_put_u32(skb, SMC_NLA_LGR_D_CONNS_NUM, lgr->conns_num))
diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c
index c180c180d0d1..3fbe14e09ad8 100644
--- a/net/smc/smc_diag.c
+++ b/net/smc/smc_diag.c
@@ -175,8 +175,10 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb,
 
 		dinfo.linkid = *((u32 *)conn->lgr->id);
 		dinfo.peer_gid = conn->lgr->peer_gid.gid;
+		dinfo.peer_gid_ext = conn->lgr->peer_gid.gid_ext;
 		smcd->ops->get_local_gid(smcd, &smcd_gid);
 		dinfo.my_gid = smcd_gid.gid;
+		dinfo.my_gid_ext = smcd_gid.gid_ext;
 		dinfo.token = conn->rmb_desc->token;
 		dinfo.peer_token = conn->peer_token;
 
-- 
cgit v1.2.3


From b3bf76024f645369e1fc45e0b08a2bd24f200d9b Mon Sep 17 00:00:00 2001
From: Wen Gu <guwen@linux.alibaba.com>
Date: Tue, 19 Dec 2023 22:26:16 +0800
Subject: net/smc: manage system EID in SMC stack instead of ISM driver

The System EID (SEID) is an internal EID that is used by the SMCv2
software stack that has a predefined and constant value representing
the s390 physical machine that the OS is executing on. So it should
be managed by SMC stack instead of ISM driver and be consistent for
all ISMv2 device (including virtual ISM devices) on s390 architecture.

Suggested-by: Alexandra Winter <wintera@linux.ibm.com>
Signed-off-by: Wen Gu <guwen@linux.alibaba.com>
Reviewed-and-tested-by: Wenjia Zhang <wenjia@linux.ibm.com>
Reviewed-by: Alexandra Winter <wintera@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/ism.h     |  7 -------
 drivers/s390/net/ism_drv.c | 38 ++++++--------------------------------
 include/linux/ism.h        |  1 -
 include/net/smc.h          |  1 -
 net/smc/smc_ism.c          | 33 ++++++++++++++++++++++++---------
 net/smc/smc_ism.h          |  7 +++++++
 6 files changed, 37 insertions(+), 50 deletions(-)

(limited to 'include')

diff --git a/drivers/s390/net/ism.h b/drivers/s390/net/ism.h
index 70c5bbda0fea..047fa6101555 100644
--- a/drivers/s390/net/ism.h
+++ b/drivers/s390/net/ism.h
@@ -16,7 +16,6 @@
  */
 #define ISM_DMB_WORD_OFFSET	1
 #define ISM_DMB_BIT_OFFSET	(ISM_DMB_WORD_OFFSET * 32)
-#define ISM_IDENT_MASK		0x00FFFF
 
 #define ISM_REG_SBA	0x1
 #define ISM_REG_IEQ	0x2
@@ -192,12 +191,6 @@ struct ism_sba {
 #define ISM_CREATE_REQ(dmb, idx, sf, offset)		\
 	((dmb) | (idx) << 24 | (sf) << 23 | (offset))
 
-struct ism_systemeid {
-	u8	seid_string[24];
-	u8	serial_number[4];
-	u8	type[4];
-};
-
 static inline void __ism_read_cmd(struct ism_dev *ism, void *data,
 				  unsigned long offset, unsigned long len)
 {
diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c
index 34dd06324e38..2c8e964425dc 100644
--- a/drivers/s390/net/ism_drv.c
+++ b/drivers/s390/net/ism_drv.c
@@ -36,6 +36,7 @@ static struct ism_client *clients[MAX_CLIENTS];	/* use an array rather than */
 						/* a list for fast mapping  */
 static u8 max_client;
 static DEFINE_MUTEX(clients_lock);
+static bool ism_v2_capable;
 struct ism_dev_list {
 	struct list_head list;
 	struct mutex mutex; /* protects ism device list */
@@ -443,32 +444,6 @@ int ism_move(struct ism_dev *ism, u64 dmb_tok, unsigned int idx, bool sf,
 }
 EXPORT_SYMBOL_GPL(ism_move);
 
-static struct ism_systemeid SYSTEM_EID = {
-	.seid_string = "IBM-SYSZ-ISMSEID00000000",
-	.serial_number = "0000",
-	.type = "0000",
-};
-
-static void ism_create_system_eid(void)
-{
-	struct cpuid id;
-	u16 ident_tail;
-	char tmp[5];
-
-	get_cpu_id(&id);
-	ident_tail = (u16)(id.ident & ISM_IDENT_MASK);
-	snprintf(tmp, 5, "%04X", ident_tail);
-	memcpy(&SYSTEM_EID.serial_number, tmp, 4);
-	snprintf(tmp, 5, "%04X", id.machine);
-	memcpy(&SYSTEM_EID.type, tmp, 4);
-}
-
-u8 *ism_get_seid(void)
-{
-	return SYSTEM_EID.seid_string;
-}
-EXPORT_SYMBOL_GPL(ism_get_seid);
-
 static void ism_handle_event(struct ism_dev *ism)
 {
 	struct ism_event *entry;
@@ -560,7 +535,9 @@ static int ism_dev_init(struct ism_dev *ism)
 
 	if (!ism_add_vlan_id(ism, ISM_RESERVED_VLANID))
 		/* hardware is V2 capable */
-		ism_create_system_eid();
+		ism_v2_capable = true;
+	else
+		ism_v2_capable = false;
 
 	mutex_lock(&ism_dev_list.mutex);
 	mutex_lock(&clients_lock);
@@ -665,8 +642,7 @@ static void ism_dev_exit(struct ism_dev *ism)
 	}
 	mutex_unlock(&clients_lock);
 
-	if (SYSTEM_EID.serial_number[0] != '0' ||
-	    SYSTEM_EID.type[0] != '0')
+	if (ism_v2_capable)
 		ism_del_vlan_id(ism, ISM_RESERVED_VLANID);
 	unregister_ieq(ism);
 	unregister_sba(ism);
@@ -813,8 +789,7 @@ static int smcd_move(struct smcd_dev *smcd, u64 dmb_tok, unsigned int idx,
 
 static int smcd_supports_v2(void)
 {
-	return SYSTEM_EID.serial_number[0] != '0' ||
-		SYSTEM_EID.type[0] != '0';
+	return ism_v2_capable;
 }
 
 static u64 ism_get_local_gid(struct ism_dev *ism)
@@ -860,7 +835,6 @@ static const struct smcd_ops ism_ops = {
 	.signal_event = smcd_signal_ieq,
 	.move_data = smcd_move,
 	.supports_v2 = smcd_supports_v2,
-	.get_system_eid = ism_get_seid,
 	.get_local_gid = smcd_get_local_gid,
 	.get_chid = smcd_get_chid,
 	.get_dev = smcd_get_dev,
diff --git a/include/linux/ism.h b/include/linux/ism.h
index 9a4c204df3da..5428edd90982 100644
--- a/include/linux/ism.h
+++ b/include/linux/ism.h
@@ -86,7 +86,6 @@ int  ism_register_dmb(struct ism_dev *dev, struct ism_dmb *dmb,
 int  ism_unregister_dmb(struct ism_dev *dev, struct ism_dmb *dmb);
 int  ism_move(struct ism_dev *dev, u64 dmb_tok, unsigned int idx, bool sf,
 	      unsigned int offset, void *data, unsigned int size);
-u8  *ism_get_seid(void);
 
 const struct smcd_ops *ism_get_smcd_ops(void);
 
diff --git a/include/net/smc.h b/include/net/smc.h
index a0dc1187e96e..c9dcb30e3fd9 100644
--- a/include/net/smc.h
+++ b/include/net/smc.h
@@ -73,7 +73,6 @@ struct smcd_ops {
 			 bool sf, unsigned int offset, void *data,
 			 unsigned int size);
 	int (*supports_v2)(void);
-	u8* (*get_system_eid)(void);
 	void (*get_local_gid)(struct smcd_dev *dev, struct smcd_gid *gid);
 	u16 (*get_chid)(struct smcd_dev *dev);
 	struct device* (*get_dev)(struct smcd_dev *dev);
diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c
index a33f861cf7c1..ac88de2a06a0 100644
--- a/net/smc/smc_ism.c
+++ b/net/smc/smc_ism.c
@@ -43,6 +43,27 @@ static struct ism_client smc_ism_client = {
 };
 #endif
 
+static void smc_ism_create_system_eid(void)
+{
+	struct smc_ism_seid *seid =
+		(struct smc_ism_seid *)smc_ism_v2_system_eid;
+#if IS_ENABLED(CONFIG_S390)
+	struct cpuid id;
+	u16 ident_tail;
+	char tmp[5];
+
+	memcpy(seid->seid_string, "IBM-SYSZ-ISMSEID00000000", 24);
+	get_cpu_id(&id);
+	ident_tail = (u16)(id.ident & SMC_ISM_IDENT_MASK);
+	snprintf(tmp, 5, "%04X", ident_tail);
+	memcpy(seid->serial_number, tmp, 4);
+	snprintf(tmp, 5, "%04X", id.machine);
+	memcpy(seid->type, tmp, 4);
+#else
+	memset(seid, 0, SMC_MAX_EID_LEN);
+#endif
+}
+
 /* Test if an ISM communication is possible - same CPC */
 int smc_ism_cantalk(struct smcd_gid *peer_gid, unsigned short vlan_id,
 		    struct smcd_dev *smcd)
@@ -431,14 +452,8 @@ static void smcd_register_dev(struct ism_dev *ism)
 
 	mutex_lock(&smcd_dev_list.mutex);
 	if (list_empty(&smcd_dev_list.list)) {
-		u8 *system_eid = NULL;
-
-		system_eid = smcd->ops->get_system_eid();
-		if (smcd->ops->supports_v2()) {
+		if (smcd->ops->supports_v2())
 			smc_ism_v2_capable = true;
-			memcpy(smc_ism_v2_system_eid, system_eid,
-			       SMC_MAX_EID_LEN);
-		}
 	}
 	/* sort list: devices without pnetid before devices with pnetid */
 	if (smcd->pnetid[0])
@@ -542,10 +557,10 @@ int smc_ism_init(void)
 {
 	int rc = 0;
 
-#if IS_ENABLED(CONFIG_ISM)
 	smc_ism_v2_capable = false;
-	memset(smc_ism_v2_system_eid, 0, SMC_MAX_EID_LEN);
+	smc_ism_create_system_eid();
 
+#if IS_ENABLED(CONFIG_ISM)
 	rc = ism_register_client(&smc_ism_client);
 #endif
 	return rc;
diff --git a/net/smc/smc_ism.h b/net/smc/smc_ism.h
index 0e5e563099ec..ffff40c30a06 100644
--- a/net/smc/smc_ism.h
+++ b/net/smc/smc_ism.h
@@ -16,6 +16,7 @@
 #include "smc.h"
 
 #define SMC_VIRTUAL_ISM_CHID_MASK	0xFF00
+#define SMC_ISM_IDENT_MASK		0x00FFFF
 
 struct smcd_dev_list {	/* List of SMCD devices */
 	struct list_head list;
@@ -30,6 +31,12 @@ struct smc_ism_vlanid {			/* VLAN id set on ISM device */
 	refcount_t refcnt;		/* Reference count */
 };
 
+struct smc_ism_seid {
+	u8 seid_string[24];
+	u8 serial_number[4];
+	u8 type[4];
+};
+
 struct smcd_dev;
 
 int smc_ism_cantalk(struct smcd_gid *peer_gid, unsigned short vlan_id,
-- 
cgit v1.2.3


From b1dffcf0da221d1f9d8007dfa2a41a325921d7fa Mon Sep 17 00:00:00 2001
From: Denis Kirjanov <kirjanov@gmail.com>
Date: Tue, 19 Dec 2023 17:38:20 +0300
Subject: net: remove SOCK_DEBUG macro

Since there are no more users of the macro let's finally
burn it

Signed-off-by: Denis Kirjanov <dkirjanov@suse.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h | 13 -------------
 1 file changed, 13 deletions(-)

(limited to 'include')

diff --git a/include/net/sock.h b/include/net/sock.h
index 2fb3ea2d2ec3..30d3980dd57c 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -76,19 +76,6 @@
  * the other protocols.
  */
 
-/* Define this to get the SOCK_DBG debugging facility. */
-#define SOCK_DEBUGGING
-#ifdef SOCK_DEBUGGING
-#define SOCK_DEBUG(sk, msg...) do { if ((sk) && sock_flag((sk), SOCK_DBG)) \
-					printk(KERN_DEBUG msg); } while (0)
-#else
-/* Validate arguments and do nothing */
-static inline __printf(2, 3)
-void SOCK_DEBUG(const struct sock *sk, const char *msg, ...)
-{
-}
-#endif
-
 /* This is the per-socket lock.  The spinlock provides a synchronization
  * between user contexts and software interrupt processing, whereas the
  * mini-semaphore synchronizes multiple users amongst themselves.
-- 
cgit v1.2.3


From 913b47d3424e7d99eaf34b798c47dfa840c64a08 Mon Sep 17 00:00:00 2001
From: Victor Nogueira <victor@mojatatu.com>
Date: Tue, 19 Dec 2023 15:16:19 -0300
Subject: net/sched: Introduce tc block netdev tracking infra

This commit makes tc blocks track which ports have been added to them.
And, with that, we'll be able to use this new information to send
packets to the block's ports. Which will be done in the patch #3 of this
series.

Suggested-by: Jiri Pirko <jiri@nvidia.com>
Co-developed-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Co-developed-by: Pedro Tammela <pctammela@mojatatu.com>
Signed-off-by: Pedro Tammela <pctammela@mojatatu.com>
Signed-off-by: Victor Nogueira <victor@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h |  2 ++
 net/sched/cls_api.c       |  2 ++
 net/sched/sch_api.c       | 41 +++++++++++++++++++++++++++++++++++++++++
 net/sched/sch_generic.c   | 18 +++++++++++++++++-
 4 files changed, 62 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 1d70c2c1572f..aca11127154f 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -19,6 +19,7 @@
 #include <net/gen_stats.h>
 #include <net/rtnetlink.h>
 #include <net/flow_offload.h>
+#include <linux/xarray.h>
 
 struct Qdisc_ops;
 struct qdisc_walker;
@@ -456,6 +457,7 @@ struct tcf_chain {
 };
 
 struct tcf_block {
+	struct xarray ports; /* datapath accessible */
 	/* Lock protects tcf_block and lifetime-management data of chains
 	 * attached to the block (refcnt, action_refcnt, explicitly_created).
 	 */
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 8978cf5531d0..421ea10bc82a 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -531,6 +531,7 @@ static void tcf_block_destroy(struct tcf_block *block)
 {
 	mutex_destroy(&block->lock);
 	mutex_destroy(&block->proto_destroy_lock);
+	xa_destroy(&block->ports);
 	kfree_rcu(block, rcu);
 }
 
@@ -1002,6 +1003,7 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q,
 	refcount_set(&block->refcnt, 1);
 	block->net = net;
 	block->index = block_index;
+	xa_init(&block->ports);
 
 	/* Don't store q pointer for blocks which are shared */
 	if (!tcf_block_shared(block))
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index e9eaf637220e..299086bb6205 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1180,6 +1180,43 @@ skip:
 	return 0;
 }
 
+static int qdisc_block_add_dev(struct Qdisc *sch, struct net_device *dev,
+			       struct netlink_ext_ack *extack)
+{
+	const struct Qdisc_class_ops *cl_ops = sch->ops->cl_ops;
+	struct tcf_block *block;
+	int err;
+
+	block = cl_ops->tcf_block(sch, TC_H_MIN_INGRESS, NULL);
+	if (block) {
+		err = xa_insert(&block->ports, dev->ifindex, dev, GFP_KERNEL);
+		if (err) {
+			NL_SET_ERR_MSG(extack,
+				       "ingress block dev insert failed");
+			return err;
+		}
+	}
+
+	block = cl_ops->tcf_block(sch, TC_H_MIN_EGRESS, NULL);
+	if (block) {
+		err = xa_insert(&block->ports, dev->ifindex, dev, GFP_KERNEL);
+		if (err) {
+			NL_SET_ERR_MSG(extack,
+				       "Egress block dev insert failed");
+			goto err_out;
+		}
+	}
+
+	return 0;
+
+err_out:
+	block = cl_ops->tcf_block(sch, TC_H_MIN_INGRESS, NULL);
+	if (block)
+		xa_erase(&block->ports, dev->ifindex);
+
+	return err;
+}
+
 static int qdisc_block_indexes_set(struct Qdisc *sch, struct nlattr **tca,
 				   struct netlink_ext_ack *extack)
 {
@@ -1350,6 +1387,10 @@ static struct Qdisc *qdisc_create(struct net_device *dev,
 	qdisc_hash_add(sch, false);
 	trace_qdisc_create(ops, dev, parent);
 
+	err = qdisc_block_add_dev(sch, dev, extack);
+	if (err)
+		goto err_out4;
+
 	return sch;
 
 err_out4:
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 8dd0e5925342..e33568df97a5 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -1051,6 +1051,9 @@ static void qdisc_free_cb(struct rcu_head *head)
 static void __qdisc_destroy(struct Qdisc *qdisc)
 {
 	const struct Qdisc_ops  *ops = qdisc->ops;
+	struct net_device *dev = qdisc_dev(qdisc);
+	const struct Qdisc_class_ops *cops;
+	struct tcf_block *block;
 
 #ifdef CONFIG_NET_SCHED
 	qdisc_hash_del(qdisc);
@@ -1061,11 +1064,24 @@ static void __qdisc_destroy(struct Qdisc *qdisc)
 
 	qdisc_reset(qdisc);
 
+	cops = ops->cl_ops;
+	if (ops->ingress_block_get) {
+		block = cops->tcf_block(qdisc, TC_H_MIN_INGRESS, NULL);
+		if (block)
+			xa_erase(&block->ports, dev->ifindex);
+	}
+
+	if (ops->egress_block_get) {
+		block = cops->tcf_block(qdisc, TC_H_MIN_EGRESS, NULL);
+		if (block)
+			xa_erase(&block->ports, dev->ifindex);
+	}
+
 	if (ops->destroy)
 		ops->destroy(qdisc);
 
 	module_put(ops->owner);
-	netdev_put(qdisc_dev(qdisc), &qdisc->dev_tracker);
+	netdev_put(dev, &qdisc->dev_tracker);
 
 	trace_qdisc_destroy(qdisc);
 
-- 
cgit v1.2.3


From a7042cf8f23191c3a460c627c0c39463afb5d335 Mon Sep 17 00:00:00 2001
From: Victor Nogueira <victor@mojatatu.com>
Date: Tue, 19 Dec 2023 15:16:20 -0300
Subject: net/sched: cls_api: Expose tc block to the datapath

The datapath can now find the block of the port in which the packet arrived
at.

In the next patch we show a possible usage of this patch in a new
version of mirred that multicasts to all ports except for the port in
which the packet arrived on.

Co-developed-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Co-developed-by: Pedro Tammela <pctammela@mojatatu.com>
Signed-off-by: Pedro Tammela <pctammela@mojatatu.com>
Signed-off-by: Victor Nogueira <victor@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h | 2 ++
 net/sched/cls_api.c       | 3 ++-
 2 files changed, 4 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index aca11127154f..ba3e1b315de8 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -484,6 +484,8 @@ struct tcf_block {
 	struct mutex proto_destroy_lock; /* Lock for proto_destroy hashtable. */
 };
 
+struct tcf_block *tcf_block_lookup(struct net *net, u32 block_index);
+
 static inline bool lockdep_tcf_chain_is_locked(struct tcf_chain *chain)
 {
 	return lockdep_is_held(&chain->filter_chain_lock);
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 421ea10bc82a..3c50b4037755 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1011,12 +1011,13 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q,
 	return block;
 }
 
-static struct tcf_block *tcf_block_lookup(struct net *net, u32 block_index)
+struct tcf_block *tcf_block_lookup(struct net *net, u32 block_index)
 {
 	struct tcf_net *tn = net_generic(net, tcf_net_id);
 
 	return idr_find(&tn->idr, block_index);
 }
+EXPORT_SYMBOL(tcf_block_lookup);
 
 static struct tcf_block *tcf_block_refcnt_get(struct net *net, u32 block_index)
 {
-- 
cgit v1.2.3


From 42f39036cda808d3de243192a2cf5125f12f3047 Mon Sep 17 00:00:00 2001
From: Victor Nogueira <victor@mojatatu.com>
Date: Tue, 19 Dec 2023 15:16:23 -0300
Subject: net/sched: act_mirred: Allow mirred to block

So far the mirred action has dealt with syntax that handles
mirror/redirection for netdev. A matching packet is redirected or mirrored
to a target netdev.

In this patch we enable mirred to mirror to a tc block as well.
IOW, the new syntax looks as follows:
... mirred <ingress | egress> <mirror | redirect> [index INDEX] < <blockid BLOCKID> | <dev <devname>> >

Examples of mirroring or redirecting to a tc block:
$ tc filter add block 22 protocol ip pref 25 \
  flower dst_ip 192.168.0.0/16 action mirred egress mirror blockid 22

$ tc filter add block 22 protocol ip pref 25 \
  flower dst_ip 10.10.10.10/32 action mirred egress redirect blockid 22

Co-developed-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Co-developed-by: Pedro Tammela <pctammela@mojatatu.com>
Signed-off-by: Pedro Tammela <pctammela@mojatatu.com>
Signed-off-by: Victor Nogueira <victor@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tc_act/tc_mirred.h        |   1 +
 include/uapi/linux/tc_act/tc_mirred.h |   1 +
 net/sched/act_mirred.c                | 119 +++++++++++++++++++++++++++++++++-
 3 files changed, 119 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/tc_act/tc_mirred.h b/include/net/tc_act/tc_mirred.h
index 32ce8ea36950..75722d967bf2 100644
--- a/include/net/tc_act/tc_mirred.h
+++ b/include/net/tc_act/tc_mirred.h
@@ -8,6 +8,7 @@
 struct tcf_mirred {
 	struct tc_action	common;
 	int			tcfm_eaction;
+	u32                     tcfm_blockid;
 	bool			tcfm_mac_header_xmit;
 	struct net_device __rcu	*tcfm_dev;
 	netdevice_tracker	tcfm_dev_tracker;
diff --git a/include/uapi/linux/tc_act/tc_mirred.h b/include/uapi/linux/tc_act/tc_mirred.h
index 2500a0005d05..c61e76f3c23b 100644
--- a/include/uapi/linux/tc_act/tc_mirred.h
+++ b/include/uapi/linux/tc_act/tc_mirred.h
@@ -21,6 +21,7 @@ enum {
 	TCA_MIRRED_TM,
 	TCA_MIRRED_PARMS,
 	TCA_MIRRED_PAD,
+	TCA_MIRRED_BLOCKID,
 	__TCA_MIRRED_MAX
 };
 #define TCA_MIRRED_MAX (__TCA_MIRRED_MAX - 1)
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index a1be8f3c4a8e..d1f9794ca9b7 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -85,6 +85,7 @@ static void tcf_mirred_release(struct tc_action *a)
 
 static const struct nla_policy mirred_policy[TCA_MIRRED_MAX + 1] = {
 	[TCA_MIRRED_PARMS]	= { .len = sizeof(struct tc_mirred) },
+	[TCA_MIRRED_BLOCKID]	= NLA_POLICY_MIN(NLA_U32, 1),
 };
 
 static struct tc_action_ops act_mirred_ops;
@@ -136,6 +137,17 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 	if (exists && bind)
 		return 0;
 
+	if (tb[TCA_MIRRED_BLOCKID] && parm->ifindex) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Cannot specify Block ID and dev simultaneously");
+		if (exists)
+			tcf_idr_release(*a, bind);
+		else
+			tcf_idr_cleanup(tn, index);
+
+		return -EINVAL;
+	}
+
 	switch (parm->eaction) {
 	case TCA_EGRESS_MIRROR:
 	case TCA_EGRESS_REDIR:
@@ -152,9 +164,10 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 	}
 
 	if (!exists) {
-		if (!parm->ifindex) {
+		if (!parm->ifindex && !tb[TCA_MIRRED_BLOCKID]) {
 			tcf_idr_cleanup(tn, index);
-			NL_SET_ERR_MSG_MOD(extack, "Specified device does not exist");
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Must specify device or block");
 			return -EINVAL;
 		}
 		ret = tcf_idr_create_from_flags(tn, index, est, a,
@@ -192,6 +205,11 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 		tcf_mirred_replace_dev(m, ndev);
 		netdev_tracker_alloc(ndev, &m->tcfm_dev_tracker, GFP_ATOMIC);
 		m->tcfm_mac_header_xmit = mac_header_xmit;
+		m->tcfm_blockid = 0;
+	} else if (tb[TCA_MIRRED_BLOCKID]) {
+		tcf_mirred_replace_dev(m, NULL);
+		m->tcfm_mac_header_xmit = false;
+		m->tcfm_blockid = nla_get_u32(tb[TCA_MIRRED_BLOCKID]);
 	}
 	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
 	m->tcfm_eaction = parm->eaction;
@@ -316,6 +334,89 @@ out:
 	return retval;
 }
 
+static int tcf_blockcast_redir(struct sk_buff *skb, struct tcf_mirred *m,
+			       struct tcf_block *block, int m_eaction,
+			       const u32 exception_ifindex, int retval)
+{
+	struct net_device *dev_prev = NULL;
+	struct net_device *dev = NULL;
+	unsigned long index;
+	int mirred_eaction;
+
+	mirred_eaction = tcf_mirred_act_wants_ingress(m_eaction) ?
+		TCA_INGRESS_MIRROR : TCA_EGRESS_MIRROR;
+
+	xa_for_each(&block->ports, index, dev) {
+		if (index == exception_ifindex)
+			continue;
+
+		if (!dev_prev)
+			goto assign_prev;
+
+		tcf_mirred_to_dev(skb, m, dev_prev,
+				  dev_is_mac_header_xmit(dev),
+				  mirred_eaction, retval);
+assign_prev:
+		dev_prev = dev;
+	}
+
+	if (dev_prev)
+		return tcf_mirred_to_dev(skb, m, dev_prev,
+					 dev_is_mac_header_xmit(dev_prev),
+					 m_eaction, retval);
+
+	return retval;
+}
+
+static int tcf_blockcast_mirror(struct sk_buff *skb, struct tcf_mirred *m,
+				struct tcf_block *block, int m_eaction,
+				const u32 exception_ifindex, int retval)
+{
+	struct net_device *dev = NULL;
+	unsigned long index;
+
+	xa_for_each(&block->ports, index, dev) {
+		if (index == exception_ifindex)
+			continue;
+
+		tcf_mirred_to_dev(skb, m, dev,
+				  dev_is_mac_header_xmit(dev),
+				  m_eaction, retval);
+	}
+
+	return retval;
+}
+
+static int tcf_blockcast(struct sk_buff *skb, struct tcf_mirred *m,
+			 const u32 blockid, struct tcf_result *res,
+			 int retval)
+{
+	const u32 exception_ifindex = skb->dev->ifindex;
+	struct tcf_block *block;
+	bool is_redirect;
+	int m_eaction;
+
+	m_eaction = READ_ONCE(m->tcfm_eaction);
+	is_redirect = tcf_mirred_is_act_redirect(m_eaction);
+
+	/* we are already under rcu protection, so can call block lookup
+	 * directly.
+	 */
+	block = tcf_block_lookup(dev_net(skb->dev), blockid);
+	if (!block || xa_empty(&block->ports)) {
+		tcf_action_inc_overlimit_qstats(&m->common);
+		return retval;
+	}
+
+	if (is_redirect)
+		return tcf_blockcast_redir(skb, m, block, m_eaction,
+					   exception_ifindex, retval);
+
+	/* If it's not redirect, it is mirror */
+	return tcf_blockcast_mirror(skb, m, block, m_eaction, exception_ifindex,
+				    retval);
+}
+
 TC_INDIRECT_SCOPE int tcf_mirred_act(struct sk_buff *skb,
 				     const struct tc_action *a,
 				     struct tcf_result *res)
@@ -326,6 +427,7 @@ TC_INDIRECT_SCOPE int tcf_mirred_act(struct sk_buff *skb,
 	bool m_mac_header_xmit;
 	struct net_device *dev;
 	int m_eaction;
+	u32 blockid;
 
 	nest_level = __this_cpu_inc_return(mirred_nest_level);
 	if (unlikely(nest_level > MIRRED_NEST_LIMIT)) {
@@ -338,6 +440,12 @@ TC_INDIRECT_SCOPE int tcf_mirred_act(struct sk_buff *skb,
 	tcf_lastuse_update(&m->tcf_tm);
 	tcf_action_update_bstats(&m->common, skb);
 
+	blockid = READ_ONCE(m->tcfm_blockid);
+	if (blockid) {
+		retval = tcf_blockcast(skb, m, blockid, res, retval);
+		goto dec_nest_level;
+	}
+
 	dev = rcu_dereference_bh(m->tcfm_dev);
 	if (unlikely(!dev)) {
 		pr_notice_once("tc mirred: target device is gone\n");
@@ -379,6 +487,7 @@ static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind,
 	};
 	struct net_device *dev;
 	struct tcf_t t;
+	u32 blockid;
 
 	spin_lock_bh(&m->tcf_lock);
 	opt.action = m->tcf_action;
@@ -390,6 +499,10 @@ static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind,
 	if (nla_put(skb, TCA_MIRRED_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;
 
+	blockid = m->tcfm_blockid;
+	if (blockid && nla_put_u32(skb, TCA_MIRRED_BLOCKID, blockid))
+		goto nla_put_failure;
+
 	tcf_tm_dump(&t, &m->tcf_tm);
 	if (nla_put_64bit(skb, TCA_MIRRED_TM, sizeof(t), &t, TCA_MIRRED_PAD))
 		goto nla_put_failure;
@@ -420,6 +533,8 @@ static int mirred_device_event(struct notifier_block *unused,
 				 * net_device are already rcu protected.
 				 */
 				RCU_INIT_POINTER(m->tcfm_dev, NULL);
+			} else if (m->tcfm_blockid) {
+				m->tcfm_blockid = 0;
 			}
 			spin_unlock_bh(&m->tcf_lock);
 		}
-- 
cgit v1.2.3


From 0942155a48e4cfc2c83e514c86a3de8f78f6af02 Mon Sep 17 00:00:00 2001
From: Mathias Krause <minipli@grsecurity.net>
Date: Wed, 20 Dec 2023 14:35:05 +0100
Subject: PCI: Remove unused 'node' member from struct pci_driver

Remove the unused 'node' member. It got replaced by device_driver chaining
more than 20 years ago in commit 4b4a837f2b57 ("PCI: start to use common
fields of struct device_driver more...") of the history.git tree.

Link: https://lore.kernel.org/r/20231220133505.8798-1-minipli@grsecurity.net
Signed-off-by: Mathias Krause <minipli@grsecurity.net>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Kalle Valo <kvalo@kernel.org>
---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c | 1 -
 include/linux/pci.h                                     | 2 --
 2 files changed, 3 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
index 80220685f5e4..d7fb88bb6ae1 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
@@ -2707,7 +2707,6 @@ MODULE_DEVICE_TABLE(pci, brcmf_pcie_devid_table);
 
 
 static struct pci_driver brcmf_pciedrvr = {
-	.node = {},
 	.name = KBUILD_MODNAME,
 	.id_table = brcmf_pcie_devid_table,
 	.probe = brcmf_pcie_probe,
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 60ca768bc867..1a89dc66f89a 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -885,7 +885,6 @@ struct module;
 
 /**
  * struct pci_driver - PCI driver structure
- * @node:	List of driver structures.
  * @name:	Driver name.
  * @id_table:	Pointer to table of device IDs the driver is
  *		interested in.  Most drivers should export this
@@ -940,7 +939,6 @@ struct module;
  *		own I/O address space.
  */
 struct pci_driver {
-	struct list_head	node;
 	const char		*name;
 	const struct pci_device_id *id_table;	/* Must be non-NULL for probe to be called */
 	int  (*probe)(struct pci_dev *dev, const struct pci_device_id *id);	/* New device inserted */
-- 
cgit v1.2.3


From ba367479c7ad0b870461024cd5ae7a1ea6e1e3db Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Tue, 19 Dec 2023 11:32:39 +0530
Subject: OPP: The level field is always of unsigned int type

By mistake, dev_pm_opp_find_level_floor() used the level parameter as
unsigned long instead of unsigned int. Fix it.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
---
 drivers/opp/core.c     | 9 +++++++--
 include/linux/pm_opp.h | 4 ++--
 2 files changed, 9 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index c022d548067d..49b429984bdb 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -842,9 +842,14 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_find_level_ceil);
  * use.
  */
 struct dev_pm_opp *dev_pm_opp_find_level_floor(struct device *dev,
-					       unsigned long *level)
+					       unsigned int *level)
 {
-	return _find_key_floor(dev, level, 0, true, _read_level, NULL);
+	unsigned long temp = *level;
+	struct dev_pm_opp *opp;
+
+	opp = _find_key_floor(dev, &temp, 0, true, _read_level, NULL);
+	*level = temp;
+	return opp;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_find_level_floor);
 
diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h
index 81dff7facdc9..74768c47d790 100644
--- a/include/linux/pm_opp.h
+++ b/include/linux/pm_opp.h
@@ -163,7 +163,7 @@ struct dev_pm_opp *dev_pm_opp_find_level_ceil(struct device *dev,
 					      unsigned int *level);
 
 struct dev_pm_opp *dev_pm_opp_find_level_floor(struct device *dev,
-					       unsigned long *level);
+					       unsigned int *level);
 
 struct dev_pm_opp *dev_pm_opp_find_bw_ceil(struct device *dev,
 					   unsigned int *bw, int index);
@@ -330,7 +330,7 @@ static inline struct dev_pm_opp *dev_pm_opp_find_level_ceil(struct device *dev,
 }
 
 static inline struct dev_pm_opp *dev_pm_opp_find_level_floor(struct device *dev,
-							     unsigned long *level)
+							     unsigned int *level)
 {
 	return ERR_PTR(-EOPNOTSUPP);
 }
-- 
cgit v1.2.3


From 90abde49ea85a8af9a56bbab8c419aefc77f919a Mon Sep 17 00:00:00 2001
From: "Radu Pirea (NXP OSS)" <radu-nicolae.pirea@oss.nxp.com>
Date: Tue, 19 Dec 2023 16:53:25 +0200
Subject: net: rename dsa_realloc_skb to skb_ensure_writable_head_tail

Rename dsa_realloc_skb to skb_ensure_writable_head_tail and move it to
skbuff.c to use it as helper.

Signed-off-by: Radu Pirea (NXP OSS) <radu-nicolae.pirea@oss.nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h |  1 +
 net/core/skbuff.c      | 25 +++++++++++++++++++++++++
 net/dsa/user.c         | 29 +++--------------------------
 3 files changed, 29 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 50e92c8471dc..a5ae952454c8 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -4007,6 +4007,7 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, netdev_features_t features
 				 unsigned int offset);
 struct sk_buff *skb_vlan_untag(struct sk_buff *skb);
 int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len);
+int skb_ensure_writable_head_tail(struct sk_buff *skb, struct net_device *dev);
 int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci);
 int skb_vlan_pop(struct sk_buff *skb);
 int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index ce5687ddb768..12d22c0b8551 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5995,6 +5995,31 @@ int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len)
 }
 EXPORT_SYMBOL(skb_ensure_writable);
 
+int skb_ensure_writable_head_tail(struct sk_buff *skb, struct net_device *dev)
+{
+	int needed_headroom = dev->needed_headroom;
+	int needed_tailroom = dev->needed_tailroom;
+
+	/* For tail taggers, we need to pad short frames ourselves, to ensure
+	 * that the tail tag does not fail at its role of being at the end of
+	 * the packet, once the conduit interface pads the frame. Account for
+	 * that pad length here, and pad later.
+	 */
+	if (unlikely(needed_tailroom && skb->len < ETH_ZLEN))
+		needed_tailroom += ETH_ZLEN - skb->len;
+	/* skb_headroom() returns unsigned int... */
+	needed_headroom = max_t(int, needed_headroom - skb_headroom(skb), 0);
+	needed_tailroom = max_t(int, needed_tailroom - skb_tailroom(skb), 0);
+
+	if (likely(!needed_headroom && !needed_tailroom && !skb_cloned(skb)))
+		/* No reallocation needed, yay! */
+		return 0;
+
+	return pskb_expand_head(skb, needed_headroom, needed_tailroom,
+				GFP_ATOMIC);
+}
+EXPORT_SYMBOL(skb_ensure_writable_head_tail);
+
 /* remove VLAN header from packet and update csum accordingly.
  * expects a non skb_vlan_tag_present skb with a vlan tag payload
  */
diff --git a/net/dsa/user.c b/net/dsa/user.c
index d438884a4eb0..b738a466e2dc 100644
--- a/net/dsa/user.c
+++ b/net/dsa/user.c
@@ -920,30 +920,6 @@ netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev)
 }
 EXPORT_SYMBOL_GPL(dsa_enqueue_skb);
 
-static int dsa_realloc_skb(struct sk_buff *skb, struct net_device *dev)
-{
-	int needed_headroom = dev->needed_headroom;
-	int needed_tailroom = dev->needed_tailroom;
-
-	/* For tail taggers, we need to pad short frames ourselves, to ensure
-	 * that the tail tag does not fail at its role of being at the end of
-	 * the packet, once the conduit interface pads the frame. Account for
-	 * that pad length here, and pad later.
-	 */
-	if (unlikely(needed_tailroom && skb->len < ETH_ZLEN))
-		needed_tailroom += ETH_ZLEN - skb->len;
-	/* skb_headroom() returns unsigned int... */
-	needed_headroom = max_t(int, needed_headroom - skb_headroom(skb), 0);
-	needed_tailroom = max_t(int, needed_tailroom - skb_tailroom(skb), 0);
-
-	if (likely(!needed_headroom && !needed_tailroom && !skb_cloned(skb)))
-		/* No reallocation needed, yay! */
-		return 0;
-
-	return pskb_expand_head(skb, needed_headroom, needed_tailroom,
-				GFP_ATOMIC);
-}
-
 static netdev_tx_t dsa_user_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct dsa_user_priv *p = netdev_priv(dev);
@@ -956,13 +932,14 @@ static netdev_tx_t dsa_user_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* Handle tx timestamp if any */
 	dsa_skb_tx_timestamp(p, skb);
 
-	if (dsa_realloc_skb(skb, dev)) {
+	if (skb_ensure_writable_head_tail(skb, dev)) {
 		dev_kfree_skb_any(skb);
 		return NETDEV_TX_OK;
 	}
 
 	/* needed_tailroom should still be 'warm' in the cache line from
-	 * dsa_realloc_skb(), which has also ensured that padding is safe.
+	 * skb_ensure_writable_head_tail(), which has also ensured that
+	 * padding is safe.
 	 */
 	if (dev->needed_tailroom)
 		eth_skb_pad(skb);
-- 
cgit v1.2.3


From b1c036e835b67320316e20e562cc3b4daf8fa08b Mon Sep 17 00:00:00 2001
From: "Radu Pirea (NXP OSS)" <radu-nicolae.pirea@oss.nxp.com>
Date: Tue, 19 Dec 2023 16:53:27 +0200
Subject: net: macsec: move sci_to_cpu to macsec header

Move sci_to_cpu to the MACsec header to use it in drivers.

Signed-off-by: Radu Pirea (NXP OSS) <radu-nicolae.pirea@oss.nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/netdevsim/macsec.c | 5 -----
 include/net/macsec.h           | 5 +++++
 2 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/net/netdevsim/macsec.c b/drivers/net/netdevsim/macsec.c
index 0d5f50430dd3..aa007b1e4b78 100644
--- a/drivers/net/netdevsim/macsec.c
+++ b/drivers/net/netdevsim/macsec.c
@@ -3,11 +3,6 @@
 #include <net/macsec.h>
 #include "netdevsim.h"
 
-static inline u64 sci_to_cpu(sci_t sci)
-{
-	return be64_to_cpu((__force __be64)sci);
-}
-
 static int nsim_macsec_find_secy(struct netdevsim *ns, sci_t sci)
 {
 	int i;
diff --git a/include/net/macsec.h b/include/net/macsec.h
index ebf9bc54036a..a5665e9623f2 100644
--- a/include/net/macsec.h
+++ b/include/net/macsec.h
@@ -325,4 +325,9 @@ static inline void *macsec_netdev_priv(const struct net_device *dev)
 	return netdev_priv(dev);
 }
 
+static inline u64 sci_to_cpu(sci_t sci)
+{
+	return be64_to_cpu((__force __be64)sci);
+}
+
 #endif /* _NET_MACSEC_H_ */
-- 
cgit v1.2.3


From eb97b9bd38f93ab7cab0be2a36a7f6180c004ac2 Mon Sep 17 00:00:00 2001
From: "Radu Pirea (NXP OSS)" <radu-nicolae.pirea@oss.nxp.com>
Date: Tue, 19 Dec 2023 16:53:28 +0200
Subject: net: macsec: documentation for macsec_context and macsec_ops

Add description for fields of struct macsec_context and struct
macsec_ops.

Signed-off-by: Radu Pirea (NXP OSS) <radu-nicolae.pirea@oss.nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/macsec.h | 39 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 39 insertions(+)

(limited to 'include')

diff --git a/include/net/macsec.h b/include/net/macsec.h
index a5665e9623f2..0821fa5088c0 100644
--- a/include/net/macsec.h
+++ b/include/net/macsec.h
@@ -247,6 +247,23 @@ struct macsec_secy {
 
 /**
  * struct macsec_context - MACsec context for hardware offloading
+ * @netdev: a valid pointer to a struct net_device if @offload ==
+ *	MACSEC_OFFLOAD_MAC
+ * @phydev: a valid pointer to a struct phy_device if @offload ==
+ *	MACSEC_OFFLOAD_PHY
+ * @offload: MACsec offload status
+ * @secy: pointer to a MACsec SecY
+ * @rx_sc: pointer to a RX SC
+ * @update_pn: when updating the SA, update the next PN
+ * @assoc_num: association number of the target SA
+ * @key: key of the target SA
+ * @rx_sa: pointer to an RX SA if a RX SA is added/updated/removed
+ * @tx_sa: pointer to an TX SA if a TX SA is added/updated/removed
+ * @tx_sc_stats: pointer to TX SC stats structure
+ * @tx_sa_stats: pointer to TX SA stats structure
+ * @rx_sc_stats: pointer to RX SC stats structure
+ * @rx_sa_stats: pointer to RX SA stats structure
+ * @dev_stats: pointer to dev stats structure
  */
 struct macsec_context {
 	union {
@@ -277,6 +294,28 @@ struct macsec_context {
 
 /**
  * struct macsec_ops - MACsec offloading operations
+ * @mdo_dev_open: called when the MACsec interface transitions to the up state
+ * @mdo_dev_stop: called when the MACsec interface transitions to the down
+ *	state
+ * @mdo_add_secy: called when a new SecY is added
+ * @mdo_upd_secy: called when the SecY flags are changed or the MAC address of
+ *	the MACsec interface is changed
+ * @mdo_del_secy: called when the hw offload is disabled or the MACsec
+ *	interface is removed
+ * @mdo_add_rxsc: called when a new RX SC is added
+ * @mdo_upd_rxsc: called when a certain RX SC is updated
+ * @mdo_del_rxsc: called when a certain RX SC is removed
+ * @mdo_add_rxsa: called when a new RX SA is added
+ * @mdo_upd_rxsa: called when a certain RX SA is updated
+ * @mdo_del_rxsa: called when a certain RX SA is removed
+ * @mdo_add_txsa: called when a new TX SA is added
+ * @mdo_upd_txsa: called when a certain TX SA is updated
+ * @mdo_del_txsa: called when a certain TX SA is removed
+ * @mdo_get_dev_stats: called when dev stats are read
+ * @mdo_get_tx_sc_stats: called when TX SC stats are read
+ * @mdo_get_tx_sa_stats: called when TX SA stats are read
+ * @mdo_get_rx_sc_stats: called when RX SC stats are read
+ * @mdo_get_rx_sa_stats: called when RX SA stats are read
  */
 struct macsec_ops {
 	/* Device wide */
-- 
cgit v1.2.3


From a73d8779d61ad99b966c932a1715bd4d9006a9de Mon Sep 17 00:00:00 2001
From: "Radu Pirea (NXP OSS)" <radu-nicolae.pirea@oss.nxp.com>
Date: Tue, 19 Dec 2023 16:53:30 +0200
Subject: net: macsec: introduce mdo_insert_tx_tag

Offloading MACsec in PHYs requires inserting the SecTAG and the ICV in
the ethernet frame. This operation will increase the frame size with up
to 32 bytes. If the frames are sent at line rate, the PHY will not have
enough room to insert the SecTAG and the ICV.

Some PHYs use a hardware buffer to store a number of ethernet frames and,
if it fills up, a pause frame is sent to the MAC to control the flow.
This HW implementation does not need any modification in the stack.

Other PHYs might offer to use a specific ethertype with some padding
bytes present in the ethernet frame. This ethertype and its associated
bytes will be replaced by the SecTAG and ICV.

mdo_insert_tx_tag allows the PHY drivers to add any specific tag in the
skb.

Signed-off-by: Radu Pirea (NXP OSS) <radu-nicolae.pirea@oss.nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macsec.c | 88 +++++++++++++++++++++++++++++++++++++++++++++++++---
 include/net/macsec.h | 10 ++++++
 2 files changed, 93 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index ff0c43936bef..e34816638569 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -93,6 +93,8 @@ struct pcpu_secy_stats {
  * @secys: linked list of SecY's on the underlying device
  * @gro_cells: pointer to the Generic Receive Offload cell
  * @offload: status of offloading on the MACsec device
+ * @insert_tx_tag: when offloading, device requires to insert an
+ *	additional tag
  */
 struct macsec_dev {
 	struct macsec_secy secy;
@@ -102,6 +104,7 @@ struct macsec_dev {
 	struct list_head secys;
 	struct gro_cells gro_cells;
 	enum macsec_offload offload;
+	bool insert_tx_tag;
 };
 
 /**
@@ -2568,6 +2571,33 @@ static bool macsec_is_configured(struct macsec_dev *macsec)
 	return false;
 }
 
+static bool macsec_needs_tx_tag(struct macsec_dev *macsec,
+				const struct macsec_ops *ops)
+{
+	return macsec->offload == MACSEC_OFFLOAD_PHY &&
+		ops->mdo_insert_tx_tag;
+}
+
+static void macsec_set_head_tail_room(struct net_device *dev)
+{
+	struct macsec_dev *macsec = macsec_priv(dev);
+	struct net_device *real_dev = macsec->real_dev;
+	int needed_headroom, needed_tailroom;
+	const struct macsec_ops *ops;
+
+	ops = macsec_get_ops(macsec, NULL);
+	if (ops) {
+		needed_headroom = ops->needed_headroom;
+		needed_tailroom = ops->needed_tailroom;
+	} else {
+		needed_headroom = MACSEC_NEEDED_HEADROOM;
+		needed_tailroom = MACSEC_NEEDED_TAILROOM;
+	}
+
+	dev->needed_headroom = real_dev->needed_headroom + needed_headroom;
+	dev->needed_tailroom = real_dev->needed_tailroom + needed_tailroom;
+}
+
 static int macsec_update_offload(struct net_device *dev, enum macsec_offload offload)
 {
 	enum macsec_offload prev_offload;
@@ -2605,8 +2635,13 @@ static int macsec_update_offload(struct net_device *dev, enum macsec_offload off
 	ctx.secy = &macsec->secy;
 	ret = offload == MACSEC_OFFLOAD_OFF ? macsec_offload(ops->mdo_del_secy, &ctx)
 					    : macsec_offload(ops->mdo_add_secy, &ctx);
-	if (ret)
+	if (ret) {
 		macsec->offload = prev_offload;
+		return ret;
+	}
+
+	macsec_set_head_tail_room(dev);
+	macsec->insert_tx_tag = macsec_needs_tx_tag(macsec, ops);
 
 	return ret;
 }
@@ -3364,6 +3399,40 @@ static struct genl_family macsec_fam __ro_after_init = {
 	.resv_start_op	= MACSEC_CMD_UPD_OFFLOAD + 1,
 };
 
+static struct sk_buff *macsec_insert_tx_tag(struct sk_buff *skb,
+					    struct net_device *dev)
+{
+	struct macsec_dev *macsec = macsec_priv(dev);
+	const struct macsec_ops *ops;
+	struct phy_device *phydev;
+	struct macsec_context ctx;
+	int skb_final_len;
+	int err;
+
+	ops = macsec_get_ops(macsec, &ctx);
+	skb_final_len = skb->len - ETH_HLEN + ops->needed_headroom +
+		ops->needed_tailroom;
+	if (unlikely(skb_final_len > macsec->real_dev->mtu)) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+
+	phydev = macsec->real_dev->phydev;
+
+	err = skb_ensure_writable_head_tail(skb, dev);
+	if (unlikely(err < 0))
+		goto cleanup;
+
+	err = ops->mdo_insert_tx_tag(phydev, skb);
+	if (unlikely(err))
+		goto cleanup;
+
+	return skb;
+cleanup:
+	kfree_skb(skb);
+	return ERR_PTR(err);
+}
+
 static netdev_tx_t macsec_start_xmit(struct sk_buff *skb,
 				     struct net_device *dev)
 {
@@ -3378,6 +3447,15 @@ static netdev_tx_t macsec_start_xmit(struct sk_buff *skb,
 		skb_dst_drop(skb);
 		dst_hold(&md_dst->dst);
 		skb_dst_set(skb, &md_dst->dst);
+
+		if (macsec->insert_tx_tag) {
+			skb = macsec_insert_tx_tag(skb, dev);
+			if (IS_ERR(skb)) {
+				DEV_STATS_INC(dev, tx_dropped);
+				return NETDEV_TX_OK;
+			}
+		}
+
 		skb->dev = macsec->real_dev;
 		return dev_queue_xmit(skb);
 	}
@@ -3439,10 +3517,7 @@ static int macsec_dev_init(struct net_device *dev)
 	dev->features = real_dev->features & MACSEC_FEATURES;
 	dev->features |= NETIF_F_LLTX | NETIF_F_GSO_SOFTWARE;
 
-	dev->needed_headroom = real_dev->needed_headroom +
-			       MACSEC_NEEDED_HEADROOM;
-	dev->needed_tailroom = real_dev->needed_tailroom +
-			       MACSEC_NEEDED_TAILROOM;
+	macsec_set_head_tail_room(dev);
 
 	if (is_zero_ether_addr(dev->dev_addr))
 		eth_hw_addr_inherit(dev, real_dev);
@@ -4125,6 +4200,9 @@ static int macsec_newlink(struct net *net, struct net_device *dev,
 			err = macsec_offload(ops->mdo_add_secy, &ctx);
 			if (err)
 				goto del_dev;
+
+			macsec->insert_tx_tag =
+				macsec_needs_tx_tag(macsec, ops);
 		}
 	}
 
diff --git a/include/net/macsec.h b/include/net/macsec.h
index 0821fa5088c0..dbd22180cc5c 100644
--- a/include/net/macsec.h
+++ b/include/net/macsec.h
@@ -316,6 +316,11 @@ struct macsec_context {
  * @mdo_get_tx_sa_stats: called when TX SA stats are read
  * @mdo_get_rx_sc_stats: called when RX SC stats are read
  * @mdo_get_rx_sa_stats: called when RX SA stats are read
+ * @mdo_insert_tx_tag: called to insert the TX tag
+ * @needed_headroom: number of bytes reserved at the beginning of the sk_buff
+ *	for the TX tag
+ * @needed_tailroom: number of bytes reserved at the end of the sk_buff for the
+ *	TX tag
  */
 struct macsec_ops {
 	/* Device wide */
@@ -342,6 +347,11 @@ struct macsec_ops {
 	int (*mdo_get_tx_sa_stats)(struct macsec_context *ctx);
 	int (*mdo_get_rx_sc_stats)(struct macsec_context *ctx);
 	int (*mdo_get_rx_sa_stats)(struct macsec_context *ctx);
+	/* Offload tag */
+	int (*mdo_insert_tx_tag)(struct phy_device *phydev,
+				 struct sk_buff *skb);
+	unsigned int needed_headroom;
+	unsigned int needed_tailroom;
 };
 
 void macsec_pn_wrapped(struct macsec_secy *secy, struct macsec_tx_sa *tx_sa);
-- 
cgit v1.2.3


From 932562a6045ed613d45bd100db37114273c22077 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Fri, 15 Dec 2023 15:58:20 -0500
Subject: rseq: Split out rseq.h from sched.h

We're trying to get sched.h down to more or less just types only, not
code - rseq can live in its own header.

This helps us kill the dependency on preempt.h in sched.h.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 arch/arm64/kernel/ptrace.c       |   1 +
 arch/powerpc/kernel/interrupt.c  |   1 +
 arch/s390/kernel/signal.c        |   1 +
 arch/x86/kernel/signal.c         |   1 +
 fs/exec.c                        |   1 +
 include/linux/resume_user_mode.h |   1 +
 include/linux/rseq.h             | 131 +++++++++++++++++++++++++++++++++++++++
 include/linux/sched.h            | 125 +------------------------------------
 kernel/fork.c                    |   1 +
 kernel/sched/core.c              |   1 +
 10 files changed, 140 insertions(+), 124 deletions(-)
 create mode 100644 include/linux/rseq.h

(limited to 'include')

diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 20d7ef82de90..09bb7fc7d3c2 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -28,6 +28,7 @@
 #include <linux/hw_breakpoint.h>
 #include <linux/regset.h>
 #include <linux/elf.h>
+#include <linux/rseq.h>
 
 #include <asm/compat.h>
 #include <asm/cpufeature.h>
diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index c4f6d3c69ba9..eca293794a1e 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -3,6 +3,7 @@
 #include <linux/context_tracking.h>
 #include <linux/err.h>
 #include <linux/compat.h>
+#include <linux/rseq.h>
 #include <linux/sched/debug.h> /* for show_regs */
 
 #include <asm/kup.h>
diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c
index d63557d3868c..48e46809ee27 100644
--- a/arch/s390/kernel/signal.c
+++ b/arch/s390/kernel/signal.c
@@ -12,6 +12,7 @@
 
 #include <linux/sched.h>
 #include <linux/sched/task_stack.h>
+#include <linux/rseq.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/kernel.h>
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 65fe2094da59..31b6f5dddfc2 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -27,6 +27,7 @@
 #include <linux/context_tracking.h>
 #include <linux/entry-common.h>
 #include <linux/syscalls.h>
+#include <linux/rseq.h>
 
 #include <asm/processor.h>
 #include <asm/ucontext.h>
diff --git a/fs/exec.c b/fs/exec.c
index 4aa19b24f281..41773af7e3dc 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -66,6 +66,7 @@
 #include <linux/coredump.h>
 #include <linux/time_namespace.h>
 #include <linux/user_events.h>
+#include <linux/rseq.h>
 
 #include <linux/uaccess.h>
 #include <asm/mmu_context.h>
diff --git a/include/linux/resume_user_mode.h b/include/linux/resume_user_mode.h
index f8f3e958e9cf..e0135e0adae0 100644
--- a/include/linux/resume_user_mode.h
+++ b/include/linux/resume_user_mode.h
@@ -6,6 +6,7 @@
 #include <linux/sched.h>
 #include <linux/task_work.h>
 #include <linux/memcontrol.h>
+#include <linux/rseq.h>
 #include <linux/blk-cgroup.h>
 
 /**
diff --git a/include/linux/rseq.h b/include/linux/rseq.h
new file mode 100644
index 000000000000..bc8af3eb5598
--- /dev/null
+++ b/include/linux/rseq.h
@@ -0,0 +1,131 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+#ifndef _LINUX_RSEQ_H
+#define _LINUX_RSEQ_H
+
+#ifdef CONFIG_RSEQ
+
+#include <linux/preempt.h>
+#include <linux/sched.h>
+
+/*
+ * Map the event mask on the user-space ABI enum rseq_cs_flags
+ * for direct mask checks.
+ */
+enum rseq_event_mask_bits {
+	RSEQ_EVENT_PREEMPT_BIT	= RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT,
+	RSEQ_EVENT_SIGNAL_BIT	= RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT,
+	RSEQ_EVENT_MIGRATE_BIT	= RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT,
+};
+
+enum rseq_event_mask {
+	RSEQ_EVENT_PREEMPT	= (1U << RSEQ_EVENT_PREEMPT_BIT),
+	RSEQ_EVENT_SIGNAL	= (1U << RSEQ_EVENT_SIGNAL_BIT),
+	RSEQ_EVENT_MIGRATE	= (1U << RSEQ_EVENT_MIGRATE_BIT),
+};
+
+static inline void rseq_set_notify_resume(struct task_struct *t)
+{
+	if (t->rseq)
+		set_tsk_thread_flag(t, TIF_NOTIFY_RESUME);
+}
+
+void __rseq_handle_notify_resume(struct ksignal *sig, struct pt_regs *regs);
+
+static inline void rseq_handle_notify_resume(struct ksignal *ksig,
+					     struct pt_regs *regs)
+{
+	if (current->rseq)
+		__rseq_handle_notify_resume(ksig, regs);
+}
+
+static inline void rseq_signal_deliver(struct ksignal *ksig,
+				       struct pt_regs *regs)
+{
+	preempt_disable();
+	__set_bit(RSEQ_EVENT_SIGNAL_BIT, &current->rseq_event_mask);
+	preempt_enable();
+	rseq_handle_notify_resume(ksig, regs);
+}
+
+/* rseq_preempt() requires preemption to be disabled. */
+static inline void rseq_preempt(struct task_struct *t)
+{
+	__set_bit(RSEQ_EVENT_PREEMPT_BIT, &t->rseq_event_mask);
+	rseq_set_notify_resume(t);
+}
+
+/* rseq_migrate() requires preemption to be disabled. */
+static inline void rseq_migrate(struct task_struct *t)
+{
+	__set_bit(RSEQ_EVENT_MIGRATE_BIT, &t->rseq_event_mask);
+	rseq_set_notify_resume(t);
+}
+
+/*
+ * If parent process has a registered restartable sequences area, the
+ * child inherits. Unregister rseq for a clone with CLONE_VM set.
+ */
+static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags)
+{
+	if (clone_flags & CLONE_VM) {
+		t->rseq = NULL;
+		t->rseq_len = 0;
+		t->rseq_sig = 0;
+		t->rseq_event_mask = 0;
+	} else {
+		t->rseq = current->rseq;
+		t->rseq_len = current->rseq_len;
+		t->rseq_sig = current->rseq_sig;
+		t->rseq_event_mask = current->rseq_event_mask;
+	}
+}
+
+static inline void rseq_execve(struct task_struct *t)
+{
+	t->rseq = NULL;
+	t->rseq_len = 0;
+	t->rseq_sig = 0;
+	t->rseq_event_mask = 0;
+}
+
+#else
+
+static inline void rseq_set_notify_resume(struct task_struct *t)
+{
+}
+static inline void rseq_handle_notify_resume(struct ksignal *ksig,
+					     struct pt_regs *regs)
+{
+}
+static inline void rseq_signal_deliver(struct ksignal *ksig,
+				       struct pt_regs *regs)
+{
+}
+static inline void rseq_preempt(struct task_struct *t)
+{
+}
+static inline void rseq_migrate(struct task_struct *t)
+{
+}
+static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags)
+{
+}
+static inline void rseq_execve(struct task_struct *t)
+{
+}
+
+#endif
+
+#ifdef CONFIG_DEBUG_RSEQ
+
+void rseq_syscall(struct pt_regs *regs);
+
+#else
+
+static inline void rseq_syscall(struct pt_regs *regs)
+{
+}
+
+#endif
+
+#endif /* _LINUX_RSEQ_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index dd002d193726..a588b94988bc 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -35,7 +35,7 @@
 #include <linux/task_io_accounting.h>
 #include <linux/posix-timers_types.h>
 #include <linux/restart_block.h>
-#include <linux/rseq.h>
+#include <uapi/linux/rseq.h>
 #include <linux/seqlock_types.h>
 #include <linux/kcsan.h>
 #include <linux/rv.h>
@@ -2181,129 +2181,6 @@ static inline bool owner_on_cpu(struct task_struct *owner)
 unsigned long sched_cpu_util(int cpu);
 #endif /* CONFIG_SMP */
 
-#ifdef CONFIG_RSEQ
-
-/*
- * Map the event mask on the user-space ABI enum rseq_cs_flags
- * for direct mask checks.
- */
-enum rseq_event_mask_bits {
-	RSEQ_EVENT_PREEMPT_BIT	= RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT,
-	RSEQ_EVENT_SIGNAL_BIT	= RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT,
-	RSEQ_EVENT_MIGRATE_BIT	= RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT,
-};
-
-enum rseq_event_mask {
-	RSEQ_EVENT_PREEMPT	= (1U << RSEQ_EVENT_PREEMPT_BIT),
-	RSEQ_EVENT_SIGNAL	= (1U << RSEQ_EVENT_SIGNAL_BIT),
-	RSEQ_EVENT_MIGRATE	= (1U << RSEQ_EVENT_MIGRATE_BIT),
-};
-
-static inline void rseq_set_notify_resume(struct task_struct *t)
-{
-	if (t->rseq)
-		set_tsk_thread_flag(t, TIF_NOTIFY_RESUME);
-}
-
-void __rseq_handle_notify_resume(struct ksignal *sig, struct pt_regs *regs);
-
-static inline void rseq_handle_notify_resume(struct ksignal *ksig,
-					     struct pt_regs *regs)
-{
-	if (current->rseq)
-		__rseq_handle_notify_resume(ksig, regs);
-}
-
-static inline void rseq_signal_deliver(struct ksignal *ksig,
-				       struct pt_regs *regs)
-{
-	preempt_disable();
-	__set_bit(RSEQ_EVENT_SIGNAL_BIT, &current->rseq_event_mask);
-	preempt_enable();
-	rseq_handle_notify_resume(ksig, regs);
-}
-
-/* rseq_preempt() requires preemption to be disabled. */
-static inline void rseq_preempt(struct task_struct *t)
-{
-	__set_bit(RSEQ_EVENT_PREEMPT_BIT, &t->rseq_event_mask);
-	rseq_set_notify_resume(t);
-}
-
-/* rseq_migrate() requires preemption to be disabled. */
-static inline void rseq_migrate(struct task_struct *t)
-{
-	__set_bit(RSEQ_EVENT_MIGRATE_BIT, &t->rseq_event_mask);
-	rseq_set_notify_resume(t);
-}
-
-/*
- * If parent process has a registered restartable sequences area, the
- * child inherits. Unregister rseq for a clone with CLONE_VM set.
- */
-static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags)
-{
-	if (clone_flags & CLONE_VM) {
-		t->rseq = NULL;
-		t->rseq_len = 0;
-		t->rseq_sig = 0;
-		t->rseq_event_mask = 0;
-	} else {
-		t->rseq = current->rseq;
-		t->rseq_len = current->rseq_len;
-		t->rseq_sig = current->rseq_sig;
-		t->rseq_event_mask = current->rseq_event_mask;
-	}
-}
-
-static inline void rseq_execve(struct task_struct *t)
-{
-	t->rseq = NULL;
-	t->rseq_len = 0;
-	t->rseq_sig = 0;
-	t->rseq_event_mask = 0;
-}
-
-#else
-
-static inline void rseq_set_notify_resume(struct task_struct *t)
-{
-}
-static inline void rseq_handle_notify_resume(struct ksignal *ksig,
-					     struct pt_regs *regs)
-{
-}
-static inline void rseq_signal_deliver(struct ksignal *ksig,
-				       struct pt_regs *regs)
-{
-}
-static inline void rseq_preempt(struct task_struct *t)
-{
-}
-static inline void rseq_migrate(struct task_struct *t)
-{
-}
-static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags)
-{
-}
-static inline void rseq_execve(struct task_struct *t)
-{
-}
-
-#endif
-
-#ifdef CONFIG_DEBUG_RSEQ
-
-void rseq_syscall(struct pt_regs *regs);
-
-#else
-
-static inline void rseq_syscall(struct pt_regs *regs)
-{
-}
-
-#endif
-
 #ifdef CONFIG_SCHED_CORE
 extern void sched_core_free(struct task_struct *tsk);
 extern void sched_core_fork(struct task_struct *p);
diff --git a/kernel/fork.c b/kernel/fork.c
index 319e61297bfb..53816393995b 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -100,6 +100,7 @@
 #include <linux/stackprotector.h>
 #include <linux/user_events.h>
 #include <linux/iommu.h>
+#include <linux/rseq.h>
 
 #include <asm/pgalloc.h>
 #include <linux/uaccess.h>
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a708d225c28e..d04cf3c47899 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -57,6 +57,7 @@
 #include <linux/profile.h>
 #include <linux/psi.h>
 #include <linux/rcuwait_api.h>
+#include <linux/rseq.h>
 #include <linux/sched/wake_q.h>
 #include <linux/scs.h>
 #include <linux/slab.h>
-- 
cgit v1.2.3


From 2b010a69350f2c995f40585fb801904874c85dd1 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Fri, 15 Dec 2023 16:04:03 -0500
Subject: preempt.h: Kill dependency on list.h

We really only need types.h, list.h is big.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 include/linux/preempt.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 9aa6358a1a16..7233e9cf1bab 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -9,7 +9,7 @@
 
 #include <linux/linkage.h>
 #include <linux/cleanup.h>
-#include <linux/list.h>
+#include <linux/types.h>
 
 /*
  * We put the hardirq and softirq counter into the preemption
@@ -360,7 +360,9 @@ void preempt_notifier_unregister(struct preempt_notifier *notifier);
 static inline void preempt_notifier_init(struct preempt_notifier *notifier,
 				     struct preempt_ops *ops)
 {
-	INIT_HLIST_NODE(&notifier->link);
+	/* INIT_HLIST_NODE() open coded, to avoid dependency on list.h */
+	notifier->link.next = NULL;
+	notifier->link.pprev = NULL;
 	notifier->ops = ops;
 }
 
-- 
cgit v1.2.3


From 1e2f2d31997a9496f99e2b43255d6a48b06fbcc2 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Fri, 15 Dec 2023 15:51:54 -0500
Subject: Kill sched.h dependency on rcupdate.h

by moving cond_resched_rcu() to rcupdate_wait.h, we can kill another big
sched.h dependency.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 arch/powerpc/kvm/book3s_64_vio.c        |  1 +
 include/linux/rcupdate_wait.h           | 10 ++++++++++
 include/linux/sched.h                   | 15 +++++----------
 include/linux/sched/task.h              |  1 +
 kernel/bpf/hashtab.c                    |  1 +
 lib/test_rhashtable.c                   |  1 +
 mm/filemap.c                            |  1 +
 mm/khugepaged.c                         |  1 +
 mm/shmem.c                              |  1 +
 net/ipv4/fib_trie.c                     |  1 +
 net/netfilter/ipset/ip_set_bitmap_gen.h |  2 ++
 net/netfilter/ipset/ip_set_hash_gen.h   |  1 +
 net/netfilter/ipvs/ip_vs_conn.c         |  1 +
 net/netfilter/ipvs/ip_vs_est.c          |  1 +
 14 files changed, 28 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index 14c6d7e318da..b569ebaa590e 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -20,6 +20,7 @@
 #include <linux/iommu.h>
 #include <linux/file.h>
 #include <linux/mm.h>
+#include <linux/rcupdate_wait.h>
 
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
diff --git a/include/linux/rcupdate_wait.h b/include/linux/rcupdate_wait.h
index 5e0f74f2f8ca..d07f0848802e 100644
--- a/include/linux/rcupdate_wait.h
+++ b/include/linux/rcupdate_wait.h
@@ -8,6 +8,7 @@
 
 #include <linux/rcupdate.h>
 #include <linux/completion.h>
+#include <linux/sched.h>
 
 /*
  * Structure allowing asynchronous waiting on RCU.
@@ -55,4 +56,13 @@ do {									\
 #define synchronize_rcu_mult(...) \
 	_wait_rcu_gp(IS_ENABLED(CONFIG_TINY_RCU), __VA_ARGS__)
 
+static inline void cond_resched_rcu(void)
+{
+#if defined(CONFIG_DEBUG_ATOMIC_SLEEP) || !defined(CONFIG_PREEMPT_RCU)
+	rcu_read_unlock();
+	cond_resched();
+	rcu_read_lock();
+#endif
+}
+
 #endif /* _LINUX_SCHED_RCUPDATE_WAIT_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index a588b94988bc..814bfdafbc1c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -10,9 +10,14 @@
 #include <uapi/linux/sched.h>
 
 #include <asm/current.h>
+#include <asm/processor.h>
+#include <linux/thread_info.h>
+#include <linux/preempt.h>
+#include <linux/cpumask.h>
 
 #include <linux/cache.h>
 #include <linux/irqflags_types.h>
+#include <linux/smp_types.h>
 #include <linux/pid_types.h>
 #include <linux/sem_types.h>
 #include <linux/shm.h>
@@ -23,7 +28,6 @@
 #include <linux/timer_types.h>
 #include <linux/seccomp_types.h>
 #include <linux/nodemask_types.h>
-#include <linux/rcupdate.h>
 #include <linux/refcount_types.h>
 #include <linux/resource.h>
 #include <linux/latencytop.h>
@@ -2059,15 +2063,6 @@ extern int __cond_resched_rwlock_write(rwlock_t *lock);
 	__cond_resched_rwlock_write(lock);					\
 })
 
-static inline void cond_resched_rcu(void)
-{
-#if defined(CONFIG_DEBUG_ATOMIC_SLEEP) || !defined(CONFIG_PREEMPT_RCU)
-	rcu_read_unlock();
-	cond_resched();
-	rcu_read_lock();
-#endif
-}
-
 #ifdef CONFIG_PREEMPT_DYNAMIC
 
 extern bool preempt_model_none(void);
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 1880ae21a9cb..538cdfbe895f 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -7,6 +7,7 @@
  * functionality:
  */
 
+#include <linux/rcupdate.h>
 #include <linux/refcount.h>
 #include <linux/sched.h>
 #include <linux/uaccess.h>
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index fd8d4b0addfc..3ba98ed2b3f9 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -7,6 +7,7 @@
 #include <linux/jhash.h>
 #include <linux/filter.h>
 #include <linux/rculist_nulls.h>
+#include <linux/rcupdate_wait.h>
 #include <linux/random.h>
 #include <uapi/linux/btf.h>
 #include <linux/rcupdate_trace.h>
diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c
index c20f6cb4bf55..42b585208249 100644
--- a/lib/test_rhashtable.c
+++ b/lib/test_rhashtable.c
@@ -16,6 +16,7 @@
 #include <linux/kthread.h>
 #include <linux/module.h>
 #include <linux/rcupdate.h>
+#include <linux/rcupdate_wait.h>
 #include <linux/rhashtable.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
diff --git a/mm/filemap.c b/mm/filemap.c
index f1c8c278310f..1219ffc04a26 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -45,6 +45,7 @@
 #include <linux/migrate.h>
 #include <linux/pipe_fs_i.h>
 #include <linux/splice.h>
+#include <linux/rcupdate_wait.h>
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 #include "internal.h"
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 064654717843..47a20a4ece09 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -17,6 +17,7 @@
 #include <linux/userfaultfd_k.h>
 #include <linux/page_idle.h>
 #include <linux/page_table_check.h>
+#include <linux/rcupdate_wait.h>
 #include <linux/swapops.h>
 #include <linux/shmem_fs.h>
 #include <linux/ksm.h>
diff --git a/mm/shmem.c b/mm/shmem.c
index 91e2620148b2..98f6ca7bdae1 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -79,6 +79,7 @@ static struct vfsmount *shm_mnt __ro_after_init;
 #include <linux/rmap.h>
 #include <linux/uuid.h>
 #include <linux/quotaops.h>
+#include <linux/rcupdate_wait.h>
 
 #include <linux/uaccess.h>
 
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 9bdfdab906fe..3ff35f811765 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -52,6 +52,7 @@
 #include <linux/if_arp.h>
 #include <linux/proc_fs.h>
 #include <linux/rcupdate.h>
+#include <linux/rcupdate_wait.h>
 #include <linux/skbuff.h>
 #include <linux/netlink.h>
 #include <linux/init.h>
diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h
index 26ab0e9612d8..21f7860e8fa1 100644
--- a/net/netfilter/ipset/ip_set_bitmap_gen.h
+++ b/net/netfilter/ipset/ip_set_bitmap_gen.h
@@ -4,6 +4,8 @@
 #ifndef __IP_SET_BITMAP_IP_GEN_H
 #define __IP_SET_BITMAP_IP_GEN_H
 
+#include <linux/rcupdate_wait.h>
+
 #define mtype_do_test		IPSET_TOKEN(MTYPE, _do_test)
 #define mtype_gc_test		IPSET_TOKEN(MTYPE, _gc_test)
 #define mtype_is_filled		IPSET_TOKEN(MTYPE, _is_filled)
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index 7c2399541771..cbf80da9a01c 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -5,6 +5,7 @@
 #define _IP_SET_HASH_GEN_H
 
 #include <linux/rcupdate.h>
+#include <linux/rcupdate_wait.h>
 #include <linux/jhash.h>
 #include <linux/types.h>
 #include <linux/netfilter/nfnetlink.h>
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 9065da3cdd12..a743db073887 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -31,6 +31,7 @@
 #include <linux/seq_file.h>
 #include <linux/jhash.h>
 #include <linux/random.h>
+#include <linux/rcupdate_wait.h>
 
 #include <net/net_namespace.h>
 #include <net/ip_vs.h>
diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c
index c5970ba416ae..f821ad2e19b3 100644
--- a/net/netfilter/ipvs/ip_vs_est.c
+++ b/net/netfilter/ipvs/ip_vs_est.c
@@ -21,6 +21,7 @@
 #include <linux/interrupt.h>
 #include <linux/sysctl.h>
 #include <linux/list.h>
+#include <linux/rcupdate_wait.h>
 
 #include <net/ip_vs.h>
 
-- 
cgit v1.2.3


From d6b9f4e6f7fb589d8024a31cc4883d15d0c8def4 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 27 Dec 2023 09:23:05 +0000
Subject: block: rename and document BLK_DEF_MAX_SECTORS

Give BLK_DEF_MAX_SECTORS a _CAP postfix and document what it is used for.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20231227092305.279567-5-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-settings.c   | 2 +-
 block/blk-sysfs.c      | 2 +-
 drivers/scsi/sd.c      | 2 +-
 include/linux/blkdev.h | 9 ++++++++-
 4 files changed, 11 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/block/blk-settings.c b/block/blk-settings.c
index 33b3f767b81e..ba6e0e97118c 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -139,7 +139,7 @@ void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_secto
 	if (limits->max_user_sectors)
 		max_sectors = min(max_sectors, limits->max_user_sectors);
 	else
-		max_sectors = min(max_sectors, BLK_DEF_MAX_SECTORS);
+		max_sectors = min(max_sectors, BLK_DEF_MAX_SECTORS_CAP);
 
 	max_sectors = round_down(max_sectors,
 				 limits->logical_block_size >> SECTOR_SHIFT);
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index d5e669a401b0..40bab5975c56 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -241,7 +241,7 @@ queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
 	if (max_sectors_kb == 0) {
 		q->limits.max_user_sectors = 0;
 		max_sectors_kb = min(max_hw_sectors_kb,
-				     BLK_DEF_MAX_SECTORS >> 1);
+				     BLK_DEF_MAX_SECTORS_CAP >> 1);
 	} else {
 		if (max_sectors_kb > max_hw_sectors_kb ||
 		    max_sectors_kb < page_kb)
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 8c8ac5cd1833..6bedd2d5298f 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -3500,7 +3500,7 @@ static int sd_revalidate_disk(struct gendisk *disk)
 	} else {
 		q->limits.io_opt = 0;
 		rw_max = min_not_zero(logical_to_sectors(sdp, dev_max),
-				      (sector_t)BLK_DEF_MAX_SECTORS);
+				      (sector_t)BLK_DEF_MAX_SECTORS_CAP);
 	}
 
 	/*
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index bc236e77d85e..94701a63ad8a 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1056,7 +1056,14 @@ enum blk_default_limits {
 	BLK_SEG_BOUNDARY_MASK	= 0xFFFFFFFFUL,
 };
 
-#define BLK_DEF_MAX_SECTORS 2560u
+/*
+ * Default upper limit for the software max_sectors limit used for
+ * regular file system I/O.  This can be increased through sysfs.
+ *
+ * Not to be confused with the max_hw_sector limit that is entirely
+ * controlled by the driver, usually based on hardware limits.
+ */
+#define BLK_DEF_MAX_SECTORS_CAP	2560u
 
 static inline unsigned long queue_segment_boundary(const struct request_queue *q)
 {
-- 
cgit v1.2.3


From 21d706d5cf570917594b21edee81893bdce09ab8 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 9 Jul 2021 08:41:17 +0100
Subject: netfs: Add support for DIO buffering

Add a bvec array pointer and an iterator to netfs_io_request for either
holding a copy of a DIO iterator or a list of all the bits of buffer
pointed to by a DIO iterator.

There are two problems:  Firstly, if an iovec-class iov_iter is passed to
->read_iter() or ->write_iter(), this cannot be passed directly to
kernel_sendmsg() or kernel_recvmsg() as that may cause locking recursion if
a fault is generated, so we need to keep track of the pages involved
separately.

Secondly, if the I/O is asynchronous, we must copy the iov_iter describing
the buffer before returning to the caller as it may be immediately
deallocated.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/objects.c    | 10 ++++++++++
 include/linux/netfs.h |  3 +++
 2 files changed, 13 insertions(+)

(limited to 'include')

diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c
index 1bd20bdad983..4df5e5eeada6 100644
--- a/fs/netfs/objects.c
+++ b/fs/netfs/objects.c
@@ -76,6 +76,7 @@ static void netfs_free_request(struct work_struct *work)
 {
 	struct netfs_io_request *rreq =
 		container_of(work, struct netfs_io_request, work);
+	unsigned int i;
 
 	trace_netfs_rreq(rreq, netfs_rreq_trace_free);
 	netfs_proc_del_rreq(rreq);
@@ -84,6 +85,15 @@ static void netfs_free_request(struct work_struct *work)
 		rreq->netfs_ops->free_request(rreq);
 	if (rreq->cache_resources.ops)
 		rreq->cache_resources.ops->end_operation(&rreq->cache_resources);
+	if (rreq->direct_bv) {
+		for (i = 0; i < rreq->direct_bv_count; i++) {
+			if (rreq->direct_bv[i].bv_page) {
+				if (rreq->direct_bv_unpin)
+					unpin_user_page(rreq->direct_bv[i].bv_page);
+			}
+		}
+		kvfree(rreq->direct_bv);
+	}
 	kfree_rcu(rreq, rcu);
 	netfs_stat_d(&netfs_n_rh_rreq);
 }
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 3da962e977f5..2bb1273b38f4 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -190,6 +190,8 @@ struct netfs_io_request {
 	struct iov_iter		iter;		/* Unencrypted-side iterator */
 	struct iov_iter		io_iter;	/* I/O (Encrypted-side) iterator */
 	void			*netfs_priv;	/* Private data for the netfs */
+	struct bio_vec		*direct_bv;	/* DIO buffer list (when handling iovec-iter) */
+	unsigned int		direct_bv_count; /* Number of elements in direct_bv[] */
 	unsigned int		debug_id;
 	atomic_t		nr_outstanding;	/* Number of ops in progress */
 	atomic_t		nr_copy_ops;	/* Number of copy-to-cache ops in progress */
@@ -197,6 +199,7 @@ struct netfs_io_request {
 	size_t			len;		/* Length of the request */
 	short			error;		/* 0 or error that occurred */
 	enum netfs_io_origin	origin;		/* Origin of the request */
+	bool			direct_bv_unpin; /* T if direct_bv[] must be unpinned */
 	loff_t			i_size;		/* Size of the file */
 	loff_t			start;		/* Start position */
 	pgoff_t			no_unlock_folio; /* Don't unlock this folio after read */
-- 
cgit v1.2.3


From 7d828a06634799aba0fa392913c7fe2953eb64a6 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 22 Sep 2023 13:25:22 +0100
Subject: netfs: Provide tools to create a buffer in an xarray

Provide tools to create a buffer in an xarray, with a function to add new
folios with a mark.  This will be used to create bounce buffer and can be
used more easily to create a list of folios the span of which would require
more than a page's worth of bio_vec structs.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/internal.h   | 13 +++++++++
 fs/netfs/misc.c       | 81 +++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/netfs.h |  4 +++
 3 files changed, 98 insertions(+)

(limited to 'include')

diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index 4708fb15446b..b908c7e0a901 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -56,6 +56,19 @@ static inline void netfs_proc_add_rreq(struct netfs_io_request *rreq) {}
 static inline void netfs_proc_del_rreq(struct netfs_io_request *rreq) {}
 #endif
 
+/*
+ * misc.c
+ */
+#define NETFS_FLAG_PUT_MARK		BIT(0)
+#define NETFS_FLAG_PAGECACHE_MARK	BIT(1)
+int netfs_xa_store_and_mark(struct xarray *xa, unsigned long index,
+			    struct folio *folio, unsigned int flags,
+			    gfp_t gfp_mask);
+int netfs_add_folios_to_buffer(struct xarray *buffer,
+			       struct address_space *mapping,
+			       pgoff_t index, pgoff_t to, gfp_t gfp_mask);
+void netfs_clear_buffer(struct xarray *buffer);
+
 /*
  * objects.c
  */
diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c
index 45bb19ec9a63..5d545073fe03 100644
--- a/fs/netfs/misc.c
+++ b/fs/netfs/misc.c
@@ -8,6 +8,87 @@
 #include <linux/swap.h>
 #include "internal.h"
 
+/*
+ * Attach a folio to the buffer and maybe set marks on it to say that we need
+ * to put the folio later and twiddle the pagecache flags.
+ */
+int netfs_xa_store_and_mark(struct xarray *xa, unsigned long index,
+			    struct folio *folio, unsigned int flags,
+			    gfp_t gfp_mask)
+{
+	XA_STATE_ORDER(xas, xa, index, folio_order(folio));
+
+retry:
+	xas_lock(&xas);
+	for (;;) {
+		xas_store(&xas, folio);
+		if (!xas_error(&xas))
+			break;
+		xas_unlock(&xas);
+		if (!xas_nomem(&xas, gfp_mask))
+			return xas_error(&xas);
+		goto retry;
+	}
+
+	if (flags & NETFS_FLAG_PUT_MARK)
+		xas_set_mark(&xas, NETFS_BUF_PUT_MARK);
+	if (flags & NETFS_FLAG_PAGECACHE_MARK)
+		xas_set_mark(&xas, NETFS_BUF_PAGECACHE_MARK);
+	xas_unlock(&xas);
+	return xas_error(&xas);
+}
+
+/*
+ * Create the specified range of folios in the buffer attached to the read
+ * request.  The folios are marked with NETFS_BUF_PUT_MARK so that we know that
+ * these need freeing later.
+ */
+int netfs_add_folios_to_buffer(struct xarray *buffer,
+			       struct address_space *mapping,
+			       pgoff_t index, pgoff_t to, gfp_t gfp_mask)
+{
+	struct folio *folio;
+	int ret;
+
+	if (to + 1 == index) /* Page range is inclusive */
+		return 0;
+
+	do {
+		/* TODO: Figure out what order folio can be allocated here */
+		folio = filemap_alloc_folio(readahead_gfp_mask(mapping), 0);
+		if (!folio)
+			return -ENOMEM;
+		folio->index = index;
+		ret = netfs_xa_store_and_mark(buffer, index, folio,
+					      NETFS_FLAG_PUT_MARK, gfp_mask);
+		if (ret < 0) {
+			folio_put(folio);
+			return ret;
+		}
+
+		index += folio_nr_pages(folio);
+	} while (index <= to && index != 0);
+
+	return 0;
+}
+
+/*
+ * Clear an xarray buffer, putting a ref on the folios that have
+ * NETFS_BUF_PUT_MARK set.
+ */
+void netfs_clear_buffer(struct xarray *buffer)
+{
+	struct folio *folio;
+	XA_STATE(xas, buffer, 0);
+
+	rcu_read_lock();
+	xas_for_each_marked(&xas, folio, ULONG_MAX, NETFS_BUF_PUT_MARK) {
+		folio_put(folio);
+	}
+	rcu_read_unlock();
+	xa_destroy(buffer);
+}
+
 /**
  * netfs_dirty_folio - Mark folio dirty and pin a cache object for writeback
  * @mapping: The mapping the folio belongs to.
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 2bb1273b38f4..c05365e3f428 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -109,6 +109,10 @@ static inline int wait_on_page_fscache_killable(struct page *page)
 	return folio_wait_private_2_killable(page_folio(page));
 }
 
+/* Marks used on xarray-based buffers */
+#define NETFS_BUF_PUT_MARK	XA_MARK_0	/* - Page needs putting  */
+#define NETFS_BUF_PAGECACHE_MARK XA_MARK_1	/* - Page needs wb/dirty flag wrangling */
+
 enum netfs_io_source {
 	NETFS_FILL_WITH_ZEROES,
 	NETFS_DOWNLOAD_FROM_SERVER,
-- 
cgit v1.2.3


From cae932d3aee55035a54415dcea8e7ecf2ec469b5 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 22 Sep 2023 14:49:47 +0100
Subject: netfs: Add func to calculate pagecount/size-limited span of an
 iterator

Add a function to work out how much of an ITER_BVEC or ITER_XARRAY iterator
we can use in a pagecount-limited and size-limited span.  This will be
used, for example, to limit the number of segments in a subrequest to the
maximum number of elements that an RDMA transfer can handle.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/iterator.c   | 97 +++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/netfs.h |  2 ++
 2 files changed, 99 insertions(+)

(limited to 'include')

diff --git a/fs/netfs/iterator.c b/fs/netfs/iterator.c
index 2ff07ba655a0..b781bbbf1d8d 100644
--- a/fs/netfs/iterator.c
+++ b/fs/netfs/iterator.c
@@ -101,3 +101,100 @@ ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len,
 	return npages;
 }
 EXPORT_SYMBOL_GPL(netfs_extract_user_iter);
+
+/*
+ * Select the span of a bvec iterator we're going to use.  Limit it by both maximum
+ * size and maximum number of segments.  Returns the size of the span in bytes.
+ */
+static size_t netfs_limit_bvec(const struct iov_iter *iter, size_t start_offset,
+			       size_t max_size, size_t max_segs)
+{
+	const struct bio_vec *bvecs = iter->bvec;
+	unsigned int nbv = iter->nr_segs, ix = 0, nsegs = 0;
+	size_t len, span = 0, n = iter->count;
+	size_t skip = iter->iov_offset + start_offset;
+
+	if (WARN_ON(!iov_iter_is_bvec(iter)) ||
+	    WARN_ON(start_offset > n) ||
+	    n == 0)
+		return 0;
+
+	while (n && ix < nbv && skip) {
+		len = bvecs[ix].bv_len;
+		if (skip < len)
+			break;
+		skip -= len;
+		n -= len;
+		ix++;
+	}
+
+	while (n && ix < nbv) {
+		len = min3(n, bvecs[ix].bv_len - skip, max_size);
+		span += len;
+		nsegs++;
+		ix++;
+		if (span >= max_size || nsegs >= max_segs)
+			break;
+		skip = 0;
+		n -= len;
+	}
+
+	return min(span, max_size);
+}
+
+/*
+ * Select the span of an xarray iterator we're going to use.  Limit it by both
+ * maximum size and maximum number of segments.  It is assumed that segments
+ * can be larger than a page in size, provided they're physically contiguous.
+ * Returns the size of the span in bytes.
+ */
+static size_t netfs_limit_xarray(const struct iov_iter *iter, size_t start_offset,
+				 size_t max_size, size_t max_segs)
+{
+	struct folio *folio;
+	unsigned int nsegs = 0;
+	loff_t pos = iter->xarray_start + iter->iov_offset;
+	pgoff_t index = pos / PAGE_SIZE;
+	size_t span = 0, n = iter->count;
+
+	XA_STATE(xas, iter->xarray, index);
+
+	if (WARN_ON(!iov_iter_is_xarray(iter)) ||
+	    WARN_ON(start_offset > n) ||
+	    n == 0)
+		return 0;
+	max_size = min(max_size, n - start_offset);
+
+	rcu_read_lock();
+	xas_for_each(&xas, folio, ULONG_MAX) {
+		size_t offset, flen, len;
+		if (xas_retry(&xas, folio))
+			continue;
+		if (WARN_ON(xa_is_value(folio)))
+			break;
+		if (WARN_ON(folio_test_hugetlb(folio)))
+			break;
+
+		flen = folio_size(folio);
+		offset = offset_in_folio(folio, pos);
+		len = min(max_size, flen - offset);
+		span += len;
+		nsegs++;
+		if (span >= max_size || nsegs >= max_segs)
+			break;
+	}
+
+	rcu_read_unlock();
+	return min(span, max_size);
+}
+
+size_t netfs_limit_iter(const struct iov_iter *iter, size_t start_offset,
+			size_t max_size, size_t max_segs)
+{
+	if (iov_iter_is_bvec(iter))
+		return netfs_limit_bvec(iter, start_offset, max_size, max_segs);
+	if (iov_iter_is_xarray(iter))
+		return netfs_limit_xarray(iter, start_offset, max_size, max_segs);
+	BUG();
+}
+EXPORT_SYMBOL(netfs_limit_iter);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index c05365e3f428..d673d0785b9d 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -321,6 +321,8 @@ void netfs_put_subrequest(struct netfs_io_subrequest *subreq,
 ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len,
 				struct iov_iter *new,
 				iov_iter_extraction_t extraction_flags);
+size_t netfs_limit_iter(const struct iov_iter *iter, size_t start_offset,
+			size_t max_size, size_t max_segs);
 
 int netfs_start_io_read(struct inode *inode);
 void netfs_end_io_read(struct inode *inode);
-- 
cgit v1.2.3


From 768ddb1eacf5dd997ecf393e7bab9796bad047e0 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 27 May 2022 13:45:28 +0100
Subject: netfs: Limit subrequest by size or number of segments

Limit a subrequest to a maximum size and/or a maximum number of contiguous
physical regions.  This permits, for instance, an subreq's iterator to be
limited to the number of DMA'able segments that a large RDMA request can
handle.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/io.c                | 18 ++++++++++++++++++
 include/linux/netfs.h        |  1 +
 include/trace/events/netfs.h |  1 +
 3 files changed, 20 insertions(+)

(limited to 'include')

diff --git a/fs/netfs/io.c b/fs/netfs/io.c
index e9d408e211b8..e228bfb530ea 100644
--- a/fs/netfs/io.c
+++ b/fs/netfs/io.c
@@ -525,6 +525,7 @@ netfs_rreq_prepare_read(struct netfs_io_request *rreq,
 			struct iov_iter *io_iter)
 {
 	enum netfs_io_source source;
+	size_t lsize;
 
 	_enter("%llx-%llx,%llx", subreq->start, subreq->start + subreq->len, rreq->i_size);
 
@@ -547,13 +548,30 @@ netfs_rreq_prepare_read(struct netfs_io_request *rreq,
 			source = NETFS_INVALID_READ;
 			goto out;
 		}
+
+		if (subreq->max_nr_segs) {
+			lsize = netfs_limit_iter(io_iter, 0, subreq->len,
+						 subreq->max_nr_segs);
+			if (subreq->len > lsize) {
+				subreq->len = lsize;
+				trace_netfs_sreq(subreq, netfs_sreq_trace_limited);
+			}
+		}
 	}
 
+	if (subreq->len > rreq->len)
+		pr_warn("R=%08x[%u] SREQ>RREQ %zx > %zx\n",
+			rreq->debug_id, subreq->debug_index,
+			subreq->len, rreq->len);
+
 	if (WARN_ON(subreq->len == 0)) {
 		source = NETFS_INVALID_READ;
 		goto out;
 	}
 
+	subreq->source = source;
+	trace_netfs_sreq(subreq, netfs_sreq_trace_prepare);
+
 	subreq->io_iter = *io_iter;
 	iov_iter_truncate(&subreq->io_iter, subreq->len);
 	iov_iter_advance(io_iter, subreq->len);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index d673d0785b9d..44cd13ad695a 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -161,6 +161,7 @@ struct netfs_io_subrequest {
 	refcount_t		ref;
 	short			error;		/* 0 or error that occurred */
 	unsigned short		debug_index;	/* Index in list (for debugging output) */
+	unsigned int		max_nr_segs;	/* 0 or max number of segments in an iterator */
 	enum netfs_io_source	source;		/* Where to read from/write to */
 	unsigned long		flags;
 #define NETFS_SREQ_COPY_TO_CACHE	0	/* Set if should copy the data to the cache */
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index beec534cbaab..fce6d0bc78e5 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -44,6 +44,7 @@
 #define netfs_sreq_traces					\
 	EM(netfs_sreq_trace_download_instead,	"RDOWN")	\
 	EM(netfs_sreq_trace_free,		"FREE ")	\
+	EM(netfs_sreq_trace_limited,		"LIMIT")	\
 	EM(netfs_sreq_trace_prepare,		"PREP ")	\
 	EM(netfs_sreq_trace_resubmit_short,	"SHORT")	\
 	EM(netfs_sreq_trace_submit,		"SUBMT")	\
-- 
cgit v1.2.3


From 16af134ca4b7051b1587108f2066ec90ae029f74 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 9 Feb 2022 19:52:13 +0000
Subject: netfs: Extend the netfs_io_*request structs to handle writes

Modify the netfs_io_request struct to act as a point around which writes
can be coordinated.  It represents and pins a range of pages that need
writing and a list of regions of dirty data in that range of pages.

If RMW is required, the original data can be downloaded into the bounce
buffer, decrypted if necessary, the modifications made, then the modified
data can be reencrypted/recompressed and sent back to the server.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/internal.h          |  6 ++++++
 fs/netfs/main.c              |  3 ++-
 fs/netfs/objects.c           |  6 ++++++
 fs/netfs/stats.c             | 16 +++++++++++++---
 include/linux/netfs.h        | 15 ++++++++++++++-
 include/trace/events/netfs.h |  8 ++++++--
 6 files changed, 47 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index b908c7e0a901..2bf2e82b2ad7 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -110,6 +110,12 @@ extern atomic_t netfs_n_rh_write_begin;
 extern atomic_t netfs_n_rh_write_done;
 extern atomic_t netfs_n_rh_write_failed;
 extern atomic_t netfs_n_rh_write_zskip;
+extern atomic_t netfs_n_wh_upload;
+extern atomic_t netfs_n_wh_upload_done;
+extern atomic_t netfs_n_wh_upload_failed;
+extern atomic_t netfs_n_wh_write;
+extern atomic_t netfs_n_wh_write_done;
+extern atomic_t netfs_n_wh_write_failed;
 
 int netfs_stats_show(struct seq_file *m, void *v);
 
diff --git a/fs/netfs/main.c b/fs/netfs/main.c
index 97ce1436615b..ab6cac110676 100644
--- a/fs/netfs/main.c
+++ b/fs/netfs/main.c
@@ -25,10 +25,11 @@ MODULE_PARM_DESC(netfs_debug, "Netfs support debugging mask");
 LIST_HEAD(netfs_io_requests);
 DEFINE_SPINLOCK(netfs_proc_lock);
 
-static const char *netfs_origins[] = {
+static const char *netfs_origins[nr__netfs_io_origin] = {
 	[NETFS_READAHEAD]	= "RA",
 	[NETFS_READPAGE]	= "RP",
 	[NETFS_READ_FOR_WRITE]	= "RW",
+	[NETFS_WRITEBACK]	= "WB",
 };
 
 /*
diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c
index 4df5e5eeada6..65a17dd4ab49 100644
--- a/fs/netfs/objects.c
+++ b/fs/netfs/objects.c
@@ -20,6 +20,7 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
 	struct inode *inode = file ? file_inode(file) : mapping->host;
 	struct netfs_inode *ctx = netfs_inode(inode);
 	struct netfs_io_request *rreq;
+	bool cached = netfs_is_cache_enabled(ctx);
 	int ret;
 
 	rreq = kzalloc(ctx->ops->io_request_size ?: sizeof(struct netfs_io_request),
@@ -37,7 +38,10 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
 	rreq->debug_id	= atomic_inc_return(&debug_ids);
 	INIT_LIST_HEAD(&rreq->subrequests);
 	refcount_set(&rreq->ref, 1);
+
 	__set_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags);
+	if (cached)
+		__set_bit(NETFS_RREQ_WRITE_TO_CACHE, &rreq->flags);
 	if (rreq->netfs_ops->init_request) {
 		ret = rreq->netfs_ops->init_request(rreq, file);
 		if (ret < 0) {
@@ -46,6 +50,7 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
 		}
 	}
 
+	trace_netfs_rreq_ref(rreq->debug_id, 1, netfs_rreq_trace_new);
 	netfs_proc_add_rreq(rreq);
 	netfs_stat(&netfs_n_rh_rreq);
 	return rreq;
@@ -129,6 +134,7 @@ struct netfs_io_subrequest *netfs_alloc_subrequest(struct netfs_io_request *rreq
 			 sizeof(struct netfs_io_subrequest),
 			 GFP_KERNEL);
 	if (subreq) {
+		INIT_WORK(&subreq->work, NULL);
 		INIT_LIST_HEAD(&subreq->rreq_link);
 		refcount_set(&subreq->ref, 2);
 		subreq->rreq = rreq;
diff --git a/fs/netfs/stats.c b/fs/netfs/stats.c
index 6025dc485f7e..c1f85cd595a4 100644
--- a/fs/netfs/stats.c
+++ b/fs/netfs/stats.c
@@ -27,6 +27,12 @@ atomic_t netfs_n_rh_write_begin;
 atomic_t netfs_n_rh_write_done;
 atomic_t netfs_n_rh_write_failed;
 atomic_t netfs_n_rh_write_zskip;
+atomic_t netfs_n_wh_upload;
+atomic_t netfs_n_wh_upload_done;
+atomic_t netfs_n_wh_upload_failed;
+atomic_t netfs_n_wh_write;
+atomic_t netfs_n_wh_write_done;
+atomic_t netfs_n_wh_write_failed;
 
 int netfs_stats_show(struct seq_file *m, void *v)
 {
@@ -50,10 +56,14 @@ int netfs_stats_show(struct seq_file *m, void *v)
 		   atomic_read(&netfs_n_rh_read),
 		   atomic_read(&netfs_n_rh_read_done),
 		   atomic_read(&netfs_n_rh_read_failed));
+	seq_printf(m, "Netfs  : UL=%u us=%u uf=%u\n",
+		   atomic_read(&netfs_n_wh_upload),
+		   atomic_read(&netfs_n_wh_upload_done),
+		   atomic_read(&netfs_n_wh_upload_failed));
 	seq_printf(m, "Netfs  : WR=%u ws=%u wf=%u\n",
-		   atomic_read(&netfs_n_rh_write),
-		   atomic_read(&netfs_n_rh_write_done),
-		   atomic_read(&netfs_n_rh_write_failed));
+		   atomic_read(&netfs_n_wh_write),
+		   atomic_read(&netfs_n_wh_write_done),
+		   atomic_read(&netfs_n_wh_write_failed));
 	return fscache_stats_show(m);
 }
 EXPORT_SYMBOL(netfs_stats_show);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 44cd13ad695a..f302123a3e38 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -118,6 +118,9 @@ enum netfs_io_source {
 	NETFS_DOWNLOAD_FROM_SERVER,
 	NETFS_READ_FROM_CACHE,
 	NETFS_INVALID_READ,
+	NETFS_UPLOAD_TO_SERVER,
+	NETFS_WRITE_TO_CACHE,
+	NETFS_INVALID_WRITE,
 } __mode(byte);
 
 typedef void (*netfs_io_terminated_t)(void *priv, ssize_t transferred_or_error,
@@ -149,9 +152,14 @@ struct netfs_cache_resources {
 };
 
 /*
- * Descriptor for a single component subrequest.
+ * Descriptor for a single component subrequest.  Each operation represents an
+ * individual read/write from/to a server, a cache, a journal, etc..
+ *
+ * The buffer iterator is persistent for the life of the subrequest struct and
+ * the pages it points to can be relied on to exist for the duration.
  */
 struct netfs_io_subrequest {
+	struct work_struct	work;
 	struct netfs_io_request *rreq;		/* Supervising I/O request */
 	struct list_head	rreq_link;	/* Link in rreq->subrequests */
 	struct iov_iter		io_iter;	/* Iterator for this subrequest */
@@ -176,6 +184,8 @@ enum netfs_io_origin {
 	NETFS_READAHEAD,		/* This read was triggered by readahead */
 	NETFS_READPAGE,			/* This read is a synchronous read */
 	NETFS_READ_FOR_WRITE,		/* This read is to prepare a write */
+	NETFS_WRITEBACK,		/* This write was triggered by writepages */
+	nr__netfs_io_origin
 } __mode(byte);
 
 /*
@@ -198,6 +208,7 @@ struct netfs_io_request {
 	struct bio_vec		*direct_bv;	/* DIO buffer list (when handling iovec-iter) */
 	unsigned int		direct_bv_count; /* Number of elements in direct_bv[] */
 	unsigned int		debug_id;
+	unsigned int		subreq_counter;	/* Next subreq->debug_index */
 	atomic_t		nr_outstanding;	/* Number of ops in progress */
 	atomic_t		nr_copy_ops;	/* Number of copy-to-cache ops in progress */
 	size_t			submitted;	/* Amount submitted for I/O so far */
@@ -216,6 +227,8 @@ struct netfs_io_request {
 #define NETFS_RREQ_DONT_UNLOCK_FOLIOS	3	/* Don't unlock the folios on completion */
 #define NETFS_RREQ_FAILED		4	/* The request failed */
 #define NETFS_RREQ_IN_PROGRESS		5	/* Unlocked when the request completes */
+#define NETFS_RREQ_WRITE_TO_CACHE	7	/* Need to write to the cache */
+#define NETFS_RREQ_UPLOAD_TO_SERVER	8	/* Need to write to the server */
 	const struct netfs_request_ops *netfs_ops;
 };
 
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index fce6d0bc78e5..4ea4e34d279f 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -24,7 +24,8 @@
 #define netfs_rreq_origins					\
 	EM(NETFS_READAHEAD,			"RA")		\
 	EM(NETFS_READPAGE,			"RP")		\
-	E_(NETFS_READ_FOR_WRITE,		"RW")
+	EM(NETFS_READ_FOR_WRITE,		"RW")		\
+	E_(NETFS_WRITEBACK,			"WB")
 
 #define netfs_rreq_traces					\
 	EM(netfs_rreq_trace_assess,		"ASSESS ")	\
@@ -39,7 +40,10 @@
 	EM(NETFS_FILL_WITH_ZEROES,		"ZERO")		\
 	EM(NETFS_DOWNLOAD_FROM_SERVER,		"DOWN")		\
 	EM(NETFS_READ_FROM_CACHE,		"READ")		\
-	E_(NETFS_INVALID_READ,			"INVL")		\
+	EM(NETFS_INVALID_READ,			"INVL")		\
+	EM(NETFS_UPLOAD_TO_SERVER,		"UPLD")		\
+	EM(NETFS_WRITE_TO_CACHE,		"WRIT")		\
+	E_(NETFS_INVALID_WRITE,			"INVL")
 
 #define netfs_sreq_traces					\
 	EM(netfs_sreq_trace_download_instead,	"RDOWN")	\
-- 
cgit v1.2.3


From c6dc54dd91bbf597942b4975b8adec660a16827d Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 25 Feb 2022 12:27:53 +0000
Subject: netfs: Add a hook to allow tell the netfs to update its i_size

Add a hook for netfslib's write helpers to call to tell the network
filesystem that it should update its i_size.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 include/linux/netfs.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index f302123a3e38..3fc41f616621 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -242,6 +242,7 @@ struct netfs_request_ops {
 	void (*free_request)(struct netfs_io_request *rreq);
 	void (*free_subrequest)(struct netfs_io_subrequest *rreq);
 
+	/* Read request handling */
 	void (*expand_readahead)(struct netfs_io_request *rreq);
 	bool (*clamp_length)(struct netfs_io_subrequest *subreq);
 	void (*issue_read)(struct netfs_io_subrequest *subreq);
@@ -249,6 +250,9 @@ struct netfs_request_ops {
 	int (*check_write_begin)(struct file *file, loff_t pos, unsigned len,
 				 struct folio **foliop, void **_fsdata);
 	void (*done)(struct netfs_io_request *rreq);
+
+	/* Modification handling */
+	void (*update_i_size)(struct inode *inode, loff_t i_size);
 };
 
 /*
-- 
cgit v1.2.3


From 4fcccc38ebbdcff74494701c50a8e2fe4689837e Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 4 Oct 2023 16:15:48 +0100
Subject: netfs: Make the refcounting of netfs_begin_read() easier to use

Make the refcounting of netfs_begin_read() easier to use by not eating the
caller's ref on the netfs_io_request it's given.  This makes it easier to
use when we need to look in the request struct after.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/buffered_read.c     |  6 +++++-
 fs/netfs/io.c                | 28 +++++++++++++---------------
 include/trace/events/netfs.h |  9 +++++----
 3 files changed, 23 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index 751556faa70b..6b9a44cafbac 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -210,6 +210,7 @@ void netfs_readahead(struct readahead_control *ractl)
 		;
 
 	netfs_begin_read(rreq, false);
+	netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
 	return;
 
 cleanup_free:
@@ -260,7 +261,9 @@ int netfs_read_folio(struct file *file, struct folio *folio)
 	iov_iter_xarray(&rreq->iter, ITER_DEST, &mapping->i_pages,
 			rreq->start, rreq->len);
 
-	return netfs_begin_read(rreq, true);
+	ret = netfs_begin_read(rreq, true);
+	netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
+	return ret;
 
 discard:
 	netfs_put_request(rreq, false, netfs_rreq_trace_put_discard);
@@ -429,6 +432,7 @@ retry:
 	ret = netfs_begin_read(rreq, true);
 	if (ret < 0)
 		goto error;
+	netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
 
 have_folio:
 	ret = folio_wait_fscache_killable(folio);
diff --git a/fs/netfs/io.c b/fs/netfs/io.c
index e228bfb530ea..e83ef5835d25 100644
--- a/fs/netfs/io.c
+++ b/fs/netfs/io.c
@@ -362,6 +362,7 @@ again:
 
 	netfs_rreq_unlock_folios(rreq);
 
+	trace_netfs_rreq(rreq, netfs_rreq_trace_wake_ip);
 	clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &rreq->flags);
 	wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS);
 
@@ -657,7 +658,6 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
 
 	if (rreq->len == 0) {
 		pr_err("Zero-sized read [R=%x]\n", rreq->debug_id);
-		netfs_put_request(rreq, false, netfs_rreq_trace_put_zero_len);
 		return -EIO;
 	}
 
@@ -665,12 +665,10 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
 
 	INIT_WORK(&rreq->work, netfs_rreq_work);
 
-	if (sync)
-		netfs_get_request(rreq, netfs_rreq_trace_get_hold);
-
 	/* Chop the read into slices according to what the cache and the netfs
 	 * want and submit each one.
 	 */
+	netfs_get_request(rreq, netfs_rreq_trace_get_for_outstanding);
 	atomic_set(&rreq->nr_outstanding, 1);
 	io_iter = rreq->io_iter;
 	do {
@@ -680,25 +678,25 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
 	} while (rreq->submitted < rreq->len);
 
 	if (sync) {
-		/* Keep nr_outstanding incremented so that the ref always belongs to
-		 * us, and the service code isn't punted off to a random thread pool to
-		 * process.
+		/* Keep nr_outstanding incremented so that the ref always
+		 * belongs to us, and the service code isn't punted off to a
+		 * random thread pool to process.  Note that this might start
+		 * further work, such as writing to the cache.
 		 */
-		for (;;) {
-			wait_var_event(&rreq->nr_outstanding,
-				       atomic_read(&rreq->nr_outstanding) == 1);
+		wait_var_event(&rreq->nr_outstanding,
+			       atomic_read(&rreq->nr_outstanding) == 1);
+		if (atomic_dec_and_test(&rreq->nr_outstanding))
 			netfs_rreq_assess(rreq, false);
-			if (!test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags))
-				break;
-			cond_resched();
-		}
+
+		trace_netfs_rreq(rreq, netfs_rreq_trace_wait_ip);
+		wait_on_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS,
+			    TASK_UNINTERRUPTIBLE);
 
 		ret = rreq->error;
 		if (ret == 0 && rreq->submitted < rreq->len) {
 			trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read);
 			ret = -EIO;
 		}
-		netfs_put_request(rreq, false, netfs_rreq_trace_put_hold);
 	} else {
 		/* If we decrement nr_outstanding to 0, the ref belongs to us. */
 		if (atomic_dec_and_test(&rreq->nr_outstanding))
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index 4ea4e34d279f..6daadf2aac8a 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -34,7 +34,9 @@
 	EM(netfs_rreq_trace_free,		"FREE   ")	\
 	EM(netfs_rreq_trace_resubmit,		"RESUBMT")	\
 	EM(netfs_rreq_trace_unlock,		"UNLOCK ")	\
-	E_(netfs_rreq_trace_unmark,		"UNMARK ")
+	EM(netfs_rreq_trace_unmark,		"UNMARK ")	\
+	EM(netfs_rreq_trace_wait_ip,		"WAIT-IP")	\
+	E_(netfs_rreq_trace_wake_ip,		"WAKE-IP")
 
 #define netfs_sreq_sources					\
 	EM(NETFS_FILL_WITH_ZEROES,		"ZERO")		\
@@ -65,14 +67,13 @@
 	E_(netfs_fail_prepare_write,		"prep-write")
 
 #define netfs_rreq_ref_traces					\
-	EM(netfs_rreq_trace_get_hold,		"GET HOLD   ")	\
+	EM(netfs_rreq_trace_get_for_outstanding,"GET OUTSTND")	\
 	EM(netfs_rreq_trace_get_subreq,		"GET SUBREQ ")	\
 	EM(netfs_rreq_trace_put_complete,	"PUT COMPLT ")	\
 	EM(netfs_rreq_trace_put_discard,	"PUT DISCARD")	\
 	EM(netfs_rreq_trace_put_failed,		"PUT FAILED ")	\
-	EM(netfs_rreq_trace_put_hold,		"PUT HOLD   ")	\
+	EM(netfs_rreq_trace_put_return,		"PUT RETURN ")	\
 	EM(netfs_rreq_trace_put_subreq,		"PUT SUBREQ ")	\
-	EM(netfs_rreq_trace_put_zero_len,	"PUT ZEROLEN")	\
 	E_(netfs_rreq_trace_new,		"NEW        ")
 
 #define netfs_sreq_ref_traces					\
-- 
cgit v1.2.3


From 9ebff83e648148b9ece97d4e4890dd84ca54d6ce Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 29 Sep 2023 17:28:25 +0100
Subject: netfs: Prep to use folio->private for write grouping and streaming
 write

Prepare to use folio->private to hold information write grouping and
streaming write.  These are implemented in the same commit as they both
make use of folio->private and will be both checked at the same time in
several places.

"Write grouping" involves ordering the writeback of groups of writes, such
as is needed for ceph snaps.  A group is represented by a
filesystem-supplied object which must contain a netfs_group struct.  This
contains just a refcount and a pointer to a destructor.

"Streaming write" is the storage of data in folios that are marked dirty,
but not uptodate, to avoid unnecessary reads of data.  This is represented
by a netfs_folio struct.  This contains the offset and length of the
modified region plus the otherwise displaced write grouping pointer.

The way folio->private is multiplexed is:

 (1) If private is NULL then neither is in operation on a dirty folio.

 (2) If private is set, with bit 0 clear, then this points to a group.

 (3) If private is set, with bit 0 set, then this points to a netfs_folio
     struct (with bit 0 AND'ed out).

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/internal.h   | 28 ++++++++++++++++++++++++++++
 fs/netfs/misc.c       | 46 ++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/netfs.h | 41 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 115 insertions(+)

(limited to 'include')

diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index 2bf2e82b2ad7..d72292e40f9b 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -149,6 +149,34 @@ static inline bool netfs_is_cache_enabled(struct netfs_inode *ctx)
 #endif
 }
 
+/*
+ * Get a ref on a netfs group attached to a dirty page (e.g. a ceph snap).
+ */
+static inline struct netfs_group *netfs_get_group(struct netfs_group *netfs_group)
+{
+	if (netfs_group)
+		refcount_inc(&netfs_group->ref);
+	return netfs_group;
+}
+
+/*
+ * Dispose of a netfs group attached to a dirty page (e.g. a ceph snap).
+ */
+static inline void netfs_put_group(struct netfs_group *netfs_group)
+{
+	if (netfs_group && refcount_dec_and_test(&netfs_group->ref))
+		netfs_group->free(netfs_group);
+}
+
+/*
+ * Dispose of a netfs group attached to a dirty page (e.g. a ceph snap).
+ */
+static inline void netfs_put_group_many(struct netfs_group *netfs_group, int nr)
+{
+	if (netfs_group && refcount_sub_and_test(nr, &netfs_group->ref))
+		netfs_group->free(netfs_group);
+}
+
 /*
  * fscache-cache.c
  */
diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c
index 5d545073fe03..eeb44abe59c5 100644
--- a/fs/netfs/misc.c
+++ b/fs/netfs/misc.c
@@ -177,9 +177,55 @@ EXPORT_SYMBOL(netfs_clear_inode_writeback);
  */
 void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length)
 {
+	struct netfs_folio *finfo = NULL;
+	size_t flen = folio_size(folio);
+
 	_enter("{%lx},%zx,%zx", folio_index(folio), offset, length);
 
 	folio_wait_fscache(folio);
+
+	if (!folio_test_private(folio))
+		return;
+
+	finfo = netfs_folio_info(folio);
+
+	if (offset == 0 && length >= flen)
+		goto erase_completely;
+
+	if (finfo) {
+		/* We have a partially uptodate page from a streaming write. */
+		unsigned int fstart = finfo->dirty_offset;
+		unsigned int fend = fstart + finfo->dirty_len;
+		unsigned int end = offset + length;
+
+		if (offset >= fend)
+			return;
+		if (end <= fstart)
+			return;
+		if (offset <= fstart && end >= fend)
+			goto erase_completely;
+		if (offset <= fstart && end > fstart)
+			goto reduce_len;
+		if (offset > fstart && end >= fend)
+			goto move_start;
+		/* A partial write was split.  The caller has already zeroed
+		 * it, so just absorb the hole.
+		 */
+	}
+	return;
+
+erase_completely:
+	netfs_put_group(netfs_folio_group(folio));
+	folio_detach_private(folio);
+	folio_clear_uptodate(folio);
+	kfree(finfo);
+	return;
+reduce_len:
+	finfo->dirty_len = offset + length - finfo->dirty_offset;
+	return;
+move_start:
+	finfo->dirty_len -= offset - finfo->dirty_offset;
+	finfo->dirty_offset = offset;
 }
 EXPORT_SYMBOL(netfs_invalidate_folio);
 
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 3fc41f616621..cfba83e3e3d2 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -140,6 +140,47 @@ struct netfs_inode {
 #define NETFS_ICTX_ODIRECT	0		/* The file has DIO in progress */
 };
 
+/*
+ * A netfs group - for instance a ceph snap.  This is marked on dirty pages and
+ * pages marked with a group must be flushed before they can be written under
+ * the domain of another group.
+ */
+struct netfs_group {
+	refcount_t		ref;
+	void (*free)(struct netfs_group *netfs_group);
+};
+
+/*
+ * Information about a dirty page (attached only if necessary).
+ * folio->private
+ */
+struct netfs_folio {
+	struct netfs_group	*netfs_group;	/* Filesystem's grouping marker (or NULL). */
+	unsigned int		dirty_offset;	/* Write-streaming dirty data offset */
+	unsigned int		dirty_len;	/* Write-streaming dirty data length */
+};
+#define NETFS_FOLIO_INFO	0x1UL	/* OR'd with folio->private. */
+
+static inline struct netfs_folio *netfs_folio_info(struct folio *folio)
+{
+	void *priv = folio_get_private(folio);
+
+	if ((unsigned long)priv & NETFS_FOLIO_INFO)
+		return (struct netfs_folio *)((unsigned long)priv & ~NETFS_FOLIO_INFO);
+	return NULL;
+}
+
+static inline struct netfs_group *netfs_folio_group(struct folio *folio)
+{
+	struct netfs_folio *finfo;
+	void *priv = folio_get_private(folio);
+
+	finfo = netfs_folio_info(folio);
+	if (finfo)
+		return finfo->netfs_group;
+	return priv;
+}
+
 /*
  * Resources required to do operations on a cache.
  */
-- 
cgit v1.2.3


From 0e0f2dfe880fb19e4b15a7ca468623eb0b4ba586 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 29 Jun 2021 22:31:48 +0100
Subject: netfs: Dispatch write requests to process a writeback slice

Dispatch one or more write reqeusts to process a writeback slice, where a
slice is tailored more to logical block divisions within the file (such as
crypto blocks, an object layout or cache granules) than the protocol RPC
maximum capacity.

The dispatch doesn't happen until throttling allows, at which point the
entire writeback slice is processed and queued.  A slice may be written to
multiple destinations (one or more servers and the local cache) and the
writes to each destination might be split up along different lines.

The writeback slice holds the required folios pinned.  An iov_iter is
provided in netfs_write_request that describes the buffer to be used.  This
may be part of the pagecache, may have auxiliary padding pages attached or
may be a bounce buffer resulting from crypto or compression.  Consequently,
the filesystem must not twiddle the folio markings directly.

The following API is available to the filesystem:

 (1) The ->create_write_requests() method is called to ask the filesystem
     to create the requests it needs.  This is passed the writeback slice
     to be processed.

 (2) The filesystem should then call netfs_create_write_request() to create
     the requests it needs.

 (3) Once a request is initialised, netfs_queue_write_request() can be
     called to dispatch it asynchronously, if not completed immediately.

 (4) netfs_write_request_completed() should be called to note the
     completion of a request.

 (5) netfs_get_write_request() and netfs_put_write_request() are provided
     to refcount a request.  These take constants from the netfs_wreq_trace
     enum for logging into ftrace.

 (6) The ->free_write_request is method is called to ask the filesystem to
     clean up a request.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/Makefile            |   3 +-
 fs/netfs/internal.h          |   6 +
 fs/netfs/output.c            | 363 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/netfs.h        |  13 ++
 include/trace/events/netfs.h |  50 +++++-
 5 files changed, 432 insertions(+), 3 deletions(-)
 create mode 100644 fs/netfs/output.c

(limited to 'include')

diff --git a/fs/netfs/Makefile b/fs/netfs/Makefile
index cf3fc847b8ac..c69c6775b8ac 100644
--- a/fs/netfs/Makefile
+++ b/fs/netfs/Makefile
@@ -7,7 +7,8 @@ netfs-y := \
 	locking.o \
 	main.o \
 	misc.o \
-	objects.o
+	objects.o \
+	output.o
 
 netfs-$(CONFIG_NETFS_STATS) += stats.o
 
diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index d72292e40f9b..0f20587f5a9b 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -88,6 +88,12 @@ static inline void netfs_see_request(struct netfs_io_request *rreq,
 	trace_netfs_rreq_ref(rreq->debug_id, refcount_read(&rreq->ref), what);
 }
 
+/*
+ * output.c
+ */
+int netfs_begin_write(struct netfs_io_request *wreq, bool may_wait,
+		      enum netfs_write_trace what);
+
 /*
  * stats.c
  */
diff --git a/fs/netfs/output.c b/fs/netfs/output.c
new file mode 100644
index 000000000000..2ad0fd8c32be
--- /dev/null
+++ b/fs/netfs/output.c
@@ -0,0 +1,363 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Network filesystem high-level write support.
+ *
+ * Copyright (C) 2023 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+#include <linux/slab.h>
+#include <linux/writeback.h>
+#include <linux/pagevec.h>
+#include "internal.h"
+
+/**
+ * netfs_create_write_request - Create a write operation.
+ * @wreq: The write request this is storing from.
+ * @dest: The destination type
+ * @start: Start of the region this write will modify
+ * @len: Length of the modification
+ * @worker: The worker function to handle the write(s)
+ *
+ * Allocate a write operation, set it up and add it to the list on a write
+ * request.
+ */
+struct netfs_io_subrequest *netfs_create_write_request(struct netfs_io_request *wreq,
+						       enum netfs_io_source dest,
+						       loff_t start, size_t len,
+						       work_func_t worker)
+{
+	struct netfs_io_subrequest *subreq;
+
+	subreq = netfs_alloc_subrequest(wreq);
+	if (subreq) {
+		INIT_WORK(&subreq->work, worker);
+		subreq->source	= dest;
+		subreq->start	= start;
+		subreq->len	= len;
+		subreq->debug_index = wreq->subreq_counter++;
+
+		switch (subreq->source) {
+		case NETFS_UPLOAD_TO_SERVER:
+			netfs_stat(&netfs_n_wh_upload);
+			break;
+		case NETFS_WRITE_TO_CACHE:
+			netfs_stat(&netfs_n_wh_write);
+			break;
+		default:
+			BUG();
+		}
+
+		subreq->io_iter = wreq->io_iter;
+		iov_iter_advance(&subreq->io_iter, subreq->start - wreq->start);
+		iov_iter_truncate(&subreq->io_iter, subreq->len);
+
+		trace_netfs_sreq_ref(wreq->debug_id, subreq->debug_index,
+				     refcount_read(&subreq->ref),
+				     netfs_sreq_trace_new);
+		atomic_inc(&wreq->nr_outstanding);
+		list_add_tail(&subreq->rreq_link, &wreq->subrequests);
+		trace_netfs_sreq(subreq, netfs_sreq_trace_prepare);
+	}
+
+	return subreq;
+}
+EXPORT_SYMBOL(netfs_create_write_request);
+
+/*
+ * Process a completed write request once all the component operations have
+ * been completed.
+ */
+static void netfs_write_terminated(struct netfs_io_request *wreq, bool was_async)
+{
+	struct netfs_io_subrequest *subreq;
+	struct netfs_inode *ctx = netfs_inode(wreq->inode);
+
+	_enter("R=%x[]", wreq->debug_id);
+
+	trace_netfs_rreq(wreq, netfs_rreq_trace_write_done);
+
+	list_for_each_entry(subreq, &wreq->subrequests, rreq_link) {
+		if (!subreq->error)
+			continue;
+		switch (subreq->source) {
+		case NETFS_UPLOAD_TO_SERVER:
+			/* Depending on the type of failure, this may prevent
+			 * writeback completion unless we're in disconnected
+			 * mode.
+			 */
+			if (!wreq->error)
+				wreq->error = subreq->error;
+			break;
+
+		case NETFS_WRITE_TO_CACHE:
+			/* Failure doesn't prevent writeback completion unless
+			 * we're in disconnected mode.
+			 */
+			if (subreq->error != -ENOBUFS)
+				ctx->ops->invalidate_cache(wreq);
+			break;
+
+		default:
+			WARN_ON_ONCE(1);
+			if (!wreq->error)
+				wreq->error = -EIO;
+			return;
+		}
+	}
+
+	wreq->cleanup(wreq);
+
+	_debug("finished");
+	trace_netfs_rreq(wreq, netfs_rreq_trace_wake_ip);
+	clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &wreq->flags);
+	wake_up_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS);
+
+	netfs_clear_subrequests(wreq, was_async);
+	netfs_put_request(wreq, was_async, netfs_rreq_trace_put_complete);
+}
+
+/*
+ * Deal with the completion of writing the data to the cache.
+ */
+void netfs_write_subrequest_terminated(void *_op, ssize_t transferred_or_error,
+				       bool was_async)
+{
+	struct netfs_io_subrequest *subreq = _op;
+	struct netfs_io_request *wreq = subreq->rreq;
+	unsigned int u;
+
+	_enter("%x[%x] %zd", wreq->debug_id, subreq->debug_index, transferred_or_error);
+
+	switch (subreq->source) {
+	case NETFS_UPLOAD_TO_SERVER:
+		netfs_stat(&netfs_n_wh_upload_done);
+		break;
+	case NETFS_WRITE_TO_CACHE:
+		netfs_stat(&netfs_n_wh_write_done);
+		break;
+	case NETFS_INVALID_WRITE:
+		break;
+	default:
+		BUG();
+	}
+
+	if (IS_ERR_VALUE(transferred_or_error)) {
+		subreq->error = transferred_or_error;
+		trace_netfs_failure(wreq, subreq, transferred_or_error,
+				    netfs_fail_write);
+		goto failed;
+	}
+
+	if (WARN(transferred_or_error > subreq->len - subreq->transferred,
+		 "Subreq excess write: R%x[%x] %zd > %zu - %zu",
+		 wreq->debug_id, subreq->debug_index,
+		 transferred_or_error, subreq->len, subreq->transferred))
+		transferred_or_error = subreq->len - subreq->transferred;
+
+	subreq->error = 0;
+	subreq->transferred += transferred_or_error;
+
+	if (iov_iter_count(&subreq->io_iter) != subreq->len - subreq->transferred)
+		pr_warn("R=%08x[%u] ITER POST-MISMATCH %zx != %zx-%zx %x\n",
+			wreq->debug_id, subreq->debug_index,
+			iov_iter_count(&subreq->io_iter), subreq->len,
+			subreq->transferred, subreq->io_iter.iter_type);
+
+	if (subreq->transferred < subreq->len)
+		goto incomplete;
+
+	__clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags);
+out:
+	trace_netfs_sreq(subreq, netfs_sreq_trace_terminated);
+
+	/* If we decrement nr_outstanding to 0, the ref belongs to us. */
+	u = atomic_dec_return(&wreq->nr_outstanding);
+	if (u == 0)
+		netfs_write_terminated(wreq, was_async);
+	else if (u == 1)
+		wake_up_var(&wreq->nr_outstanding);
+
+	netfs_put_subrequest(subreq, was_async, netfs_sreq_trace_put_terminated);
+	return;
+
+incomplete:
+	if (transferred_or_error == 0) {
+		if (__test_and_set_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags)) {
+			subreq->error = -ENODATA;
+			goto failed;
+		}
+	} else {
+		__clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags);
+	}
+
+	__set_bit(NETFS_SREQ_SHORT_IO, &subreq->flags);
+	set_bit(NETFS_RREQ_INCOMPLETE_IO, &wreq->flags);
+	goto out;
+
+failed:
+	switch (subreq->source) {
+	case NETFS_WRITE_TO_CACHE:
+		netfs_stat(&netfs_n_wh_write_failed);
+		set_bit(NETFS_RREQ_INCOMPLETE_IO, &wreq->flags);
+		break;
+	case NETFS_UPLOAD_TO_SERVER:
+		netfs_stat(&netfs_n_wh_upload_failed);
+		set_bit(NETFS_RREQ_FAILED, &wreq->flags);
+		wreq->error = subreq->error;
+		break;
+	default:
+		break;
+	}
+	goto out;
+}
+EXPORT_SYMBOL(netfs_write_subrequest_terminated);
+
+static void netfs_write_to_cache_op(struct netfs_io_subrequest *subreq)
+{
+	struct netfs_io_request *wreq = subreq->rreq;
+	struct netfs_cache_resources *cres = &wreq->cache_resources;
+
+	trace_netfs_sreq(subreq, netfs_sreq_trace_submit);
+
+	cres->ops->write(cres, subreq->start, &subreq->io_iter,
+			 netfs_write_subrequest_terminated, subreq);
+}
+
+static void netfs_write_to_cache_op_worker(struct work_struct *work)
+{
+	struct netfs_io_subrequest *subreq =
+		container_of(work, struct netfs_io_subrequest, work);
+
+	netfs_write_to_cache_op(subreq);
+}
+
+/**
+ * netfs_queue_write_request - Queue a write request for attention
+ * @subreq: The write request to be queued
+ *
+ * Queue the specified write request for processing by a worker thread.  We
+ * pass the caller's ref on the request to the worker thread.
+ */
+void netfs_queue_write_request(struct netfs_io_subrequest *subreq)
+{
+	if (!queue_work(system_unbound_wq, &subreq->work))
+		netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_wip);
+}
+EXPORT_SYMBOL(netfs_queue_write_request);
+
+/*
+ * Set up a op for writing to the cache.
+ */
+static void netfs_set_up_write_to_cache(struct netfs_io_request *wreq)
+{
+	struct netfs_cache_resources *cres;
+	struct netfs_io_subrequest *subreq;
+	struct netfs_inode *ctx = netfs_inode(wreq->inode);
+	struct fscache_cookie *cookie = netfs_i_cookie(ctx);
+	loff_t start = wreq->start;
+	size_t len = wreq->len;
+	int ret;
+
+	if (!fscache_cookie_enabled(cookie)) {
+		clear_bit(NETFS_RREQ_WRITE_TO_CACHE, &wreq->flags);
+		return;
+	}
+
+	_debug("write to cache");
+	subreq = netfs_create_write_request(wreq, NETFS_WRITE_TO_CACHE, start, len,
+					    netfs_write_to_cache_op_worker);
+	if (!subreq)
+		return;
+
+	cres = &wreq->cache_resources;
+	ret = fscache_begin_read_operation(cres, cookie);
+	if (ret < 0) {
+		netfs_write_subrequest_terminated(subreq, ret, false);
+		return;
+	}
+
+	ret = cres->ops->prepare_write(cres, &start, &len, i_size_read(wreq->inode),
+				       true);
+	if (ret < 0) {
+		netfs_write_subrequest_terminated(subreq, ret, false);
+		return;
+	}
+
+	netfs_queue_write_request(subreq);
+}
+
+/*
+ * Begin the process of writing out a chunk of data.
+ *
+ * We are given a write request that holds a series of dirty regions and
+ * (partially) covers a sequence of folios, all of which are present.  The
+ * pages must have been marked as writeback as appropriate.
+ *
+ * We need to perform the following steps:
+ *
+ * (1) If encrypting, create an output buffer and encrypt each block of the
+ *     data into it, otherwise the output buffer will point to the original
+ *     folios.
+ *
+ * (2) If the data is to be cached, set up a write op for the entire output
+ *     buffer to the cache, if the cache wants to accept it.
+ *
+ * (3) If the data is to be uploaded (ie. not merely cached):
+ *
+ *     (a) If the data is to be compressed, create a compression buffer and
+ *         compress the data into it.
+ *
+ *     (b) For each destination we want to upload to, set up write ops to write
+ *         to that destination.  We may need multiple writes if the data is not
+ *         contiguous or the span exceeds wsize for a server.
+ */
+int netfs_begin_write(struct netfs_io_request *wreq, bool may_wait,
+		      enum netfs_write_trace what)
+{
+	struct netfs_inode *ctx = netfs_inode(wreq->inode);
+
+	_enter("R=%x %llx-%llx f=%lx",
+	       wreq->debug_id, wreq->start, wreq->start + wreq->len - 1,
+	       wreq->flags);
+
+	trace_netfs_write(wreq, what);
+	if (wreq->len == 0 || wreq->iter.count == 0) {
+		pr_err("Zero-sized write [R=%x]\n", wreq->debug_id);
+		return -EIO;
+	}
+
+	wreq->io_iter = wreq->iter;
+
+	/* ->outstanding > 0 carries a ref */
+	netfs_get_request(wreq, netfs_rreq_trace_get_for_outstanding);
+	atomic_set(&wreq->nr_outstanding, 1);
+
+	/* Start the encryption/compression going.  We can do that in the
+	 * background whilst we generate a list of write ops that we want to
+	 * perform.
+	 */
+	// TODO: Encrypt or compress the region as appropriate
+
+	/* We need to write all of the region to the cache */
+	if (test_bit(NETFS_RREQ_WRITE_TO_CACHE, &wreq->flags))
+		netfs_set_up_write_to_cache(wreq);
+
+	/* However, we don't necessarily write all of the region to the server.
+	 * Caching of reads is being managed this way also.
+	 */
+	if (test_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags))
+		ctx->ops->create_write_requests(wreq, wreq->start, wreq->len);
+
+	if (atomic_dec_and_test(&wreq->nr_outstanding))
+		netfs_write_terminated(wreq, false);
+
+	if (!may_wait)
+		return -EIOCBQUEUED;
+
+	wait_on_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS,
+		    TASK_UNINTERRUPTIBLE);
+	return wreq->error;
+}
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index cfba83e3e3d2..890a5d8b2299 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -249,6 +249,7 @@ struct netfs_io_request {
 	struct bio_vec		*direct_bv;	/* DIO buffer list (when handling iovec-iter) */
 	unsigned int		direct_bv_count; /* Number of elements in direct_bv[] */
 	unsigned int		debug_id;
+	unsigned int		wsize;		/* Maximum write size (0 for none) */
 	unsigned int		subreq_counter;	/* Next subreq->debug_index */
 	atomic_t		nr_outstanding;	/* Number of ops in progress */
 	atomic_t		nr_copy_ops;	/* Number of copy-to-cache ops in progress */
@@ -271,6 +272,7 @@ struct netfs_io_request {
 #define NETFS_RREQ_WRITE_TO_CACHE	7	/* Need to write to the cache */
 #define NETFS_RREQ_UPLOAD_TO_SERVER	8	/* Need to write to the server */
 	const struct netfs_request_ops *netfs_ops;
+	void (*cleanup)(struct netfs_io_request *req);
 };
 
 /*
@@ -294,6 +296,11 @@ struct netfs_request_ops {
 
 	/* Modification handling */
 	void (*update_i_size)(struct inode *inode, loff_t i_size);
+
+	/* Write request handling */
+	void (*create_write_requests)(struct netfs_io_request *wreq,
+				      loff_t start, size_t len);
+	void (*invalidate_cache)(struct netfs_io_request *wreq);
 };
 
 /*
@@ -382,6 +389,12 @@ ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len,
 				iov_iter_extraction_t extraction_flags);
 size_t netfs_limit_iter(const struct iov_iter *iter, size_t start_offset,
 			size_t max_size, size_t max_segs);
+struct netfs_io_subrequest *netfs_create_write_request(
+	struct netfs_io_request *wreq, enum netfs_io_source dest,
+	loff_t start, size_t len, work_func_t worker);
+void netfs_write_subrequest_terminated(void *_op, ssize_t transferred_or_error,
+				       bool was_async);
+void netfs_queue_write_request(struct netfs_io_subrequest *subreq);
 
 int netfs_start_io_read(struct inode *inode);
 void netfs_end_io_read(struct inode *inode);
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index 6daadf2aac8a..e03635172760 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -21,6 +21,11 @@
 	EM(netfs_read_trace_readpage,		"READPAGE ")	\
 	E_(netfs_read_trace_write_begin,	"WRITEBEGN")
 
+#define netfs_write_traces					\
+	EM(netfs_write_trace_dio_write,		"DIO-WRITE")	\
+	EM(netfs_write_trace_unbuffered_write,	"UNB-WRITE")	\
+	E_(netfs_write_trace_writeback,		"WRITEBACK")
+
 #define netfs_rreq_origins					\
 	EM(NETFS_READAHEAD,			"RA")		\
 	EM(NETFS_READPAGE,			"RP")		\
@@ -32,11 +37,13 @@
 	EM(netfs_rreq_trace_copy,		"COPY   ")	\
 	EM(netfs_rreq_trace_done,		"DONE   ")	\
 	EM(netfs_rreq_trace_free,		"FREE   ")	\
+	EM(netfs_rreq_trace_redirty,		"REDIRTY")	\
 	EM(netfs_rreq_trace_resubmit,		"RESUBMT")	\
 	EM(netfs_rreq_trace_unlock,		"UNLOCK ")	\
 	EM(netfs_rreq_trace_unmark,		"UNMARK ")	\
 	EM(netfs_rreq_trace_wait_ip,		"WAIT-IP")	\
-	E_(netfs_rreq_trace_wake_ip,		"WAKE-IP")
+	EM(netfs_rreq_trace_wake_ip,		"WAKE-IP")	\
+	E_(netfs_rreq_trace_write_done,		"WR-DONE")
 
 #define netfs_sreq_sources					\
 	EM(NETFS_FILL_WITH_ZEROES,		"ZERO")		\
@@ -64,7 +71,8 @@
 	EM(netfs_fail_copy_to_cache,		"copy-to-cache")	\
 	EM(netfs_fail_read,			"read")			\
 	EM(netfs_fail_short_read,		"short-read")		\
-	E_(netfs_fail_prepare_write,		"prep-write")
+	EM(netfs_fail_prepare_write,		"prep-write")		\
+	E_(netfs_fail_write,			"write")
 
 #define netfs_rreq_ref_traces					\
 	EM(netfs_rreq_trace_get_for_outstanding,"GET OUTSTND")	\
@@ -74,6 +82,8 @@
 	EM(netfs_rreq_trace_put_failed,		"PUT FAILED ")	\
 	EM(netfs_rreq_trace_put_return,		"PUT RETURN ")	\
 	EM(netfs_rreq_trace_put_subreq,		"PUT SUBREQ ")	\
+	EM(netfs_rreq_trace_put_work,		"PUT WORK   ")	\
+	EM(netfs_rreq_trace_see_work,		"SEE WORK   ")	\
 	E_(netfs_rreq_trace_new,		"NEW        ")
 
 #define netfs_sreq_ref_traces					\
@@ -82,9 +92,12 @@
 	EM(netfs_sreq_trace_get_short_read,	"GET SHORTRD")	\
 	EM(netfs_sreq_trace_new,		"NEW        ")	\
 	EM(netfs_sreq_trace_put_clear,		"PUT CLEAR  ")	\
+	EM(netfs_sreq_trace_put_discard,	"PUT DISCARD")	\
 	EM(netfs_sreq_trace_put_failed,		"PUT FAILED ")	\
 	EM(netfs_sreq_trace_put_merged,		"PUT MERGED ")	\
 	EM(netfs_sreq_trace_put_no_copy,	"PUT NO COPY")	\
+	EM(netfs_sreq_trace_put_wip,		"PUT WIP    ")	\
+	EM(netfs_sreq_trace_put_work,		"PUT WORK   ")	\
 	E_(netfs_sreq_trace_put_terminated,	"PUT TERM   ")
 
 #ifndef __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY
@@ -96,6 +109,7 @@
 #define E_(a, b) a
 
 enum netfs_read_trace { netfs_read_traces } __mode(byte);
+enum netfs_write_trace { netfs_write_traces } __mode(byte);
 enum netfs_rreq_trace { netfs_rreq_traces } __mode(byte);
 enum netfs_sreq_trace { netfs_sreq_traces } __mode(byte);
 enum netfs_failure { netfs_failures } __mode(byte);
@@ -113,6 +127,7 @@ enum netfs_sreq_ref_trace { netfs_sreq_ref_traces } __mode(byte);
 #define E_(a, b) TRACE_DEFINE_ENUM(a);
 
 netfs_read_traces;
+netfs_write_traces;
 netfs_rreq_origins;
 netfs_rreq_traces;
 netfs_sreq_sources;
@@ -320,6 +335,37 @@ TRACE_EVENT(netfs_sreq_ref,
 		      __entry->ref)
 	    );
 
+TRACE_EVENT(netfs_write,
+	    TP_PROTO(const struct netfs_io_request *wreq,
+		     enum netfs_write_trace what),
+
+	    TP_ARGS(wreq, what),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,		wreq		)
+		    __field(unsigned int,		cookie		)
+		    __field(enum netfs_write_trace,	what		)
+		    __field(unsigned long long,		start		)
+		    __field(size_t,			len		)
+			     ),
+
+	    TP_fast_assign(
+		    struct netfs_inode *__ctx = netfs_inode(wreq->inode);
+		    struct fscache_cookie *__cookie = netfs_i_cookie(__ctx);
+		    __entry->wreq	= wreq->debug_id;
+		    __entry->cookie	= __cookie ? __cookie->debug_id : 0;
+		    __entry->what	= what;
+		    __entry->start	= wreq->start;
+		    __entry->len	= wreq->len;
+			   ),
+
+	    TP_printk("R=%08x %s c=%08x by=%llx-%llx",
+		      __entry->wreq,
+		      __print_symbolic(__entry->what, netfs_write_traces),
+		      __entry->cookie,
+		      __entry->start, __entry->start + __entry->len - 1)
+	    );
+
 #undef EM
 #undef E_
 #endif /* _TRACE_NETFS_H */
-- 
cgit v1.2.3


From c38f4e96e605f17990e871214e6ea1496bc4e65f Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 17 Jun 2021 13:09:21 +0100
Subject: netfs: Provide func to copy data to pagecache for buffered write

Provide a netfs write helper, netfs_perform_write() to buffer data to be
written in the pagecache and mark the modified folios dirty.

It will perform "streaming writes" for folios that aren't currently
resident, if possible, storing data in partially modified folios that are
marked dirty, but not uptodate.  It will also tag pages as belonging to
fs-specific write groups if so directed by the filesystem.

This is derived from generic_perform_write(), but doesn't use
->write_begin() and ->write_end(), having that logic rolled in instead.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/Makefile            |   1 +
 fs/netfs/buffered_read.c     |  49 +++++++
 fs/netfs/buffered_write.c    | 330 +++++++++++++++++++++++++++++++++++++++++++
 fs/netfs/internal.h          |   2 +
 fs/netfs/io.c                |   1 +
 include/linux/netfs.h        |   5 +
 include/trace/events/netfs.h |  73 ++++++++++
 7 files changed, 461 insertions(+)
 create mode 100644 fs/netfs/buffered_write.c

(limited to 'include')

diff --git a/fs/netfs/Makefile b/fs/netfs/Makefile
index c69c6775b8ac..85d8333a1ed4 100644
--- a/fs/netfs/Makefile
+++ b/fs/netfs/Makefile
@@ -2,6 +2,7 @@
 
 netfs-y := \
 	buffered_read.o \
+	buffered_write.o \
 	io.o \
 	iterator.o \
 	locking.o \
diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index 6b9a44cafbac..73a6e4d61f9d 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -63,6 +63,7 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq)
 				break;
 			}
 			if (!folio_started && test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) {
+				trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache);
 				folio_start_fscache(folio);
 				folio_started = true;
 			}
@@ -454,3 +455,51 @@ error:
 	return ret;
 }
 EXPORT_SYMBOL(netfs_write_begin);
+
+/*
+ * Preload the data into a page we're proposing to write into.
+ */
+int netfs_prefetch_for_write(struct file *file, struct folio *folio,
+			     size_t offset, size_t len)
+{
+	struct netfs_io_request *rreq;
+	struct address_space *mapping = folio_file_mapping(folio);
+	struct netfs_inode *ctx = netfs_inode(mapping->host);
+	unsigned long long start = folio_pos(folio);
+	size_t flen = folio_size(folio);
+	int ret;
+
+	_enter("%zx @%llx", flen, start);
+
+	ret = -ENOMEM;
+
+	rreq = netfs_alloc_request(mapping, file, start, flen,
+				   NETFS_READ_FOR_WRITE);
+	if (IS_ERR(rreq)) {
+		ret = PTR_ERR(rreq);
+		goto error;
+	}
+
+	rreq->no_unlock_folio = folio_index(folio);
+	__set_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags);
+	ret = netfs_begin_cache_read(rreq, ctx);
+	if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS)
+		goto error_put;
+
+	netfs_stat(&netfs_n_rh_write_begin);
+	trace_netfs_read(rreq, start, flen, netfs_read_trace_prefetch_for_write);
+
+	/* Set up the output buffer */
+	iov_iter_xarray(&rreq->iter, ITER_DEST, &mapping->i_pages,
+			rreq->start, rreq->len);
+
+	ret = netfs_begin_read(rreq, true);
+	netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
+	return ret;
+
+error_put:
+	netfs_put_request(rreq, false, netfs_rreq_trace_put_discard);
+error:
+	_leave(" = %d", ret);
+	return ret;
+}
diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
new file mode 100644
index 000000000000..6e7f06d9962d
--- /dev/null
+++ b/fs/netfs/buffered_write.c
@@ -0,0 +1,330 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Network filesystem high-level write support.
+ *
+ * Copyright (C) 2023 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/export.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+#include <linux/slab.h>
+#include <linux/pagevec.h>
+#include "internal.h"
+
+/*
+ * Determined write method.  Adjust netfs_folio_traces if this is changed.
+ */
+enum netfs_how_to_modify {
+	NETFS_FOLIO_IS_UPTODATE,	/* Folio is uptodate already */
+	NETFS_JUST_PREFETCH,		/* We have to read the folio anyway */
+	NETFS_WHOLE_FOLIO_MODIFY,	/* We're going to overwrite the whole folio */
+	NETFS_MODIFY_AND_CLEAR,		/* We can assume there is no data to be downloaded. */
+	NETFS_STREAMING_WRITE,		/* Store incomplete data in non-uptodate page. */
+	NETFS_STREAMING_WRITE_CONT,	/* Continue streaming write. */
+	NETFS_FLUSH_CONTENT,		/* Flush incompatible content. */
+};
+
+static void netfs_set_group(struct folio *folio, struct netfs_group *netfs_group)
+{
+	if (netfs_group && !folio_get_private(folio))
+		folio_attach_private(folio, netfs_get_group(netfs_group));
+}
+
+/*
+ * Decide how we should modify a folio.  We might be attempting to do
+ * write-streaming, in which case we don't want to a local RMW cycle if we can
+ * avoid it.  If we're doing local caching or content crypto, we award that
+ * priority over avoiding RMW.  If the file is open readably, then we also
+ * assume that we may want to read what we wrote.
+ */
+static enum netfs_how_to_modify netfs_how_to_modify(struct netfs_inode *ctx,
+						    struct file *file,
+						    struct folio *folio,
+						    void *netfs_group,
+						    size_t flen,
+						    size_t offset,
+						    size_t len,
+						    bool maybe_trouble)
+{
+	struct netfs_folio *finfo = netfs_folio_info(folio);
+	loff_t pos = folio_file_pos(folio);
+
+	_enter("");
+
+	if (netfs_folio_group(folio) != netfs_group)
+		return NETFS_FLUSH_CONTENT;
+
+	if (folio_test_uptodate(folio))
+		return NETFS_FOLIO_IS_UPTODATE;
+
+	if (pos >= ctx->remote_i_size)
+		return NETFS_MODIFY_AND_CLEAR;
+
+	if (!maybe_trouble && offset == 0 && len >= flen)
+		return NETFS_WHOLE_FOLIO_MODIFY;
+
+	if (file->f_mode & FMODE_READ)
+		return NETFS_JUST_PREFETCH;
+
+	if (netfs_is_cache_enabled(ctx))
+		return NETFS_JUST_PREFETCH;
+
+	if (!finfo)
+		return NETFS_STREAMING_WRITE;
+
+	/* We can continue a streaming write only if it continues on from the
+	 * previous.  If it overlaps, we must flush lest we suffer a partial
+	 * copy and disjoint dirty regions.
+	 */
+	if (offset == finfo->dirty_offset + finfo->dirty_len)
+		return NETFS_STREAMING_WRITE_CONT;
+	return NETFS_FLUSH_CONTENT;
+}
+
+/*
+ * Grab a folio for writing and lock it.
+ */
+static struct folio *netfs_grab_folio_for_write(struct address_space *mapping,
+						loff_t pos, size_t part)
+{
+	pgoff_t index = pos / PAGE_SIZE;
+
+	return __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
+				   mapping_gfp_mask(mapping));
+}
+
+/**
+ * netfs_perform_write - Copy data into the pagecache.
+ * @iocb: The operation parameters
+ * @iter: The source buffer
+ * @netfs_group: Grouping for dirty pages (eg. ceph snaps).
+ *
+ * Copy data into pagecache pages attached to the inode specified by @iocb.
+ * The caller must hold appropriate inode locks.
+ *
+ * Dirty pages are tagged with a netfs_folio struct if they're not up to date
+ * to indicate the range modified.  Dirty pages may also be tagged with a
+ * netfs-specific grouping such that data from an old group gets flushed before
+ * a new one is started.
+ */
+ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
+			    struct netfs_group *netfs_group)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file);
+	struct address_space *mapping = inode->i_mapping;
+	struct netfs_inode *ctx = netfs_inode(inode);
+	struct netfs_folio *finfo;
+	struct folio *folio;
+	enum netfs_how_to_modify howto;
+	enum netfs_folio_trace trace;
+	unsigned int bdp_flags = (iocb->ki_flags & IOCB_SYNC) ? 0: BDP_ASYNC;
+	ssize_t written = 0, ret;
+	loff_t i_size, pos = iocb->ki_pos, from, to;
+	size_t max_chunk = PAGE_SIZE << MAX_PAGECACHE_ORDER;
+	bool maybe_trouble = false;
+
+	do {
+		size_t flen;
+		size_t offset;	/* Offset into pagecache folio */
+		size_t part;	/* Bytes to write to folio */
+		size_t copied;	/* Bytes copied from user */
+
+		ret = balance_dirty_pages_ratelimited_flags(mapping, bdp_flags);
+		if (unlikely(ret < 0))
+			break;
+
+		offset = pos & (max_chunk - 1);
+		part = min(max_chunk - offset, iov_iter_count(iter));
+
+		/* Bring in the user pages that we will copy from _first_ lest
+		 * we hit a nasty deadlock on copying from the same page as
+		 * we're writing to, without it being marked uptodate.
+		 *
+		 * Not only is this an optimisation, but it is also required to
+		 * check that the address is actually valid, when atomic
+		 * usercopies are used below.
+		 *
+		 * We rely on the page being held onto long enough by the LRU
+		 * that we can grab it below if this causes it to be read.
+		 */
+		ret = -EFAULT;
+		if (unlikely(fault_in_iov_iter_readable(iter, part) == part))
+			break;
+
+		ret = -ENOMEM;
+		folio = netfs_grab_folio_for_write(mapping, pos, part);
+		if (!folio)
+			break;
+
+		flen = folio_size(folio);
+		offset = pos & (flen - 1);
+		part = min_t(size_t, flen - offset, part);
+
+		if (signal_pending(current)) {
+			ret = written ? -EINTR : -ERESTARTSYS;
+			goto error_folio_unlock;
+		}
+
+		/* See if we need to prefetch the area we're going to modify.
+		 * We need to do this before we get a lock on the folio in case
+		 * there's more than one writer competing for the same cache
+		 * block.
+		 */
+		howto = netfs_how_to_modify(ctx, file, folio, netfs_group,
+					    flen, offset, part, maybe_trouble);
+		_debug("howto %u", howto);
+		switch (howto) {
+		case NETFS_JUST_PREFETCH:
+			ret = netfs_prefetch_for_write(file, folio, offset, part);
+			if (ret < 0) {
+				_debug("prefetch = %zd", ret);
+				goto error_folio_unlock;
+			}
+			break;
+		case NETFS_FOLIO_IS_UPTODATE:
+		case NETFS_WHOLE_FOLIO_MODIFY:
+		case NETFS_STREAMING_WRITE_CONT:
+			break;
+		case NETFS_MODIFY_AND_CLEAR:
+			zero_user_segment(&folio->page, 0, offset);
+			break;
+		case NETFS_STREAMING_WRITE:
+			ret = -EIO;
+			if (WARN_ON(folio_get_private(folio)))
+				goto error_folio_unlock;
+			break;
+		case NETFS_FLUSH_CONTENT:
+			trace_netfs_folio(folio, netfs_flush_content);
+			from = folio_pos(folio);
+			to = from + folio_size(folio) - 1;
+			folio_unlock(folio);
+			folio_put(folio);
+			ret = filemap_write_and_wait_range(mapping, from, to);
+			if (ret < 0)
+				goto error_folio_unlock;
+			continue;
+		}
+
+		if (mapping_writably_mapped(mapping))
+			flush_dcache_folio(folio);
+
+		copied = copy_folio_from_iter_atomic(folio, offset, part, iter);
+
+		flush_dcache_folio(folio);
+
+		/* Deal with a (partially) failed copy */
+		if (copied == 0) {
+			ret = -EFAULT;
+			goto error_folio_unlock;
+		}
+
+		trace = (enum netfs_folio_trace)howto;
+		switch (howto) {
+		case NETFS_FOLIO_IS_UPTODATE:
+		case NETFS_JUST_PREFETCH:
+			netfs_set_group(folio, netfs_group);
+			break;
+		case NETFS_MODIFY_AND_CLEAR:
+			zero_user_segment(&folio->page, offset + copied, flen);
+			netfs_set_group(folio, netfs_group);
+			folio_mark_uptodate(folio);
+			break;
+		case NETFS_WHOLE_FOLIO_MODIFY:
+			if (unlikely(copied < part)) {
+				maybe_trouble = true;
+				iov_iter_revert(iter, copied);
+				copied = 0;
+				goto retry;
+			}
+			netfs_set_group(folio, netfs_group);
+			folio_mark_uptodate(folio);
+			break;
+		case NETFS_STREAMING_WRITE:
+			if (offset == 0 && copied == flen) {
+				netfs_set_group(folio, netfs_group);
+				folio_mark_uptodate(folio);
+				trace = netfs_streaming_filled_page;
+				break;
+			}
+			finfo = kzalloc(sizeof(*finfo), GFP_KERNEL);
+			if (!finfo) {
+				iov_iter_revert(iter, copied);
+				ret = -ENOMEM;
+				goto error_folio_unlock;
+			}
+			finfo->netfs_group = netfs_get_group(netfs_group);
+			finfo->dirty_offset = offset;
+			finfo->dirty_len = copied;
+			folio_attach_private(folio, (void *)((unsigned long)finfo |
+							     NETFS_FOLIO_INFO));
+			break;
+		case NETFS_STREAMING_WRITE_CONT:
+			finfo = netfs_folio_info(folio);
+			finfo->dirty_len += copied;
+			if (finfo->dirty_offset == 0 && finfo->dirty_len == flen) {
+				if (finfo->netfs_group)
+					folio_change_private(folio, finfo->netfs_group);
+				else
+					folio_detach_private(folio);
+				folio_mark_uptodate(folio);
+				kfree(finfo);
+				trace = netfs_streaming_cont_filled_page;
+			}
+			break;
+		default:
+			WARN(true, "Unexpected modify type %u ix=%lx\n",
+			     howto, folio_index(folio));
+			ret = -EIO;
+			goto error_folio_unlock;
+		}
+
+		trace_netfs_folio(folio, trace);
+
+		/* Update the inode size if we moved the EOF marker */
+		i_size = i_size_read(inode);
+		pos += copied;
+		if (pos > i_size) {
+			if (ctx->ops->update_i_size) {
+				ctx->ops->update_i_size(inode, pos);
+			} else {
+				i_size_write(inode, pos);
+#if IS_ENABLED(CONFIG_FSCACHE)
+				fscache_update_cookie(ctx->cache, NULL, &pos);
+#endif
+			}
+		}
+		written += copied;
+
+		folio_mark_dirty(folio);
+	retry:
+		folio_unlock(folio);
+		folio_put(folio);
+		folio = NULL;
+
+		cond_resched();
+	} while (iov_iter_count(iter));
+
+out:
+	if (likely(written)) {
+		/* Flush and wait for a write that requires immediate synchronisation. */
+		if (iocb->ki_flags & (IOCB_DSYNC | IOCB_SYNC)) {
+			_debug("dsync");
+			ret = filemap_fdatawait_range(mapping, iocb->ki_pos,
+						      iocb->ki_pos + written);
+		}
+
+		iocb->ki_pos += written;
+	}
+
+	_leave(" = %zd [%zd]", written, ret);
+	return written ? written : ret;
+
+error_folio_unlock:
+	folio_unlock(folio);
+	folio_put(folio);
+	goto out;
+}
+EXPORT_SYMBOL(netfs_perform_write);
diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index 0f20587f5a9b..17e4ea4456c7 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -23,6 +23,8 @@
  * buffered_read.c
  */
 void netfs_rreq_unlock_folios(struct netfs_io_request *rreq);
+int netfs_prefetch_for_write(struct file *file, struct folio *folio,
+			     size_t offset, size_t len);
 
 /*
  * io.c
diff --git a/fs/netfs/io.c b/fs/netfs/io.c
index e83ef5835d25..774aef6ea4cb 100644
--- a/fs/netfs/io.c
+++ b/fs/netfs/io.c
@@ -125,6 +125,7 @@ static void netfs_rreq_unmark_after_write(struct netfs_io_request *rreq,
 			if (have_unlocked && folio_index(folio) <= unlocked)
 				continue;
 			unlocked = folio_index(folio);
+			trace_netfs_folio(folio, netfs_folio_trace_end_copy);
 			folio_end_fscache(folio);
 			have_unlocked = true;
 		}
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 890a5d8b2299..70f578cf3715 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -367,6 +367,11 @@ struct netfs_cache_ops {
 			       loff_t *_data_start, size_t *_data_len);
 };
 
+/* High-level write API */
+ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
+			    struct netfs_group *netfs_group);
+
+/* Address operations API */
 struct readahead_control;
 void netfs_readahead(struct readahead_control *);
 int netfs_read_folio(struct file *, struct folio *);
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index e03635172760..8308b81f36be 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -19,6 +19,7 @@
 	EM(netfs_read_trace_expanded,		"EXPANDED ")	\
 	EM(netfs_read_trace_readahead,		"READAHEAD")	\
 	EM(netfs_read_trace_readpage,		"READPAGE ")	\
+	EM(netfs_read_trace_prefetch_for_write,	"PREFETCHW")	\
 	E_(netfs_read_trace_write_begin,	"WRITEBEGN")
 
 #define netfs_write_traces					\
@@ -100,6 +101,31 @@
 	EM(netfs_sreq_trace_put_work,		"PUT WORK   ")	\
 	E_(netfs_sreq_trace_put_terminated,	"PUT TERM   ")
 
+#define netfs_folio_traces					\
+	/* The first few correspond to enum netfs_how_to_modify */	\
+	EM(netfs_folio_is_uptodate,		"mod-uptodate")	\
+	EM(netfs_just_prefetch,			"mod-prefetch")	\
+	EM(netfs_whole_folio_modify,		"mod-whole-f")	\
+	EM(netfs_modify_and_clear,		"mod-n-clear")	\
+	EM(netfs_streaming_write,		"mod-streamw")	\
+	EM(netfs_streaming_write_cont,		"mod-streamw+")	\
+	EM(netfs_flush_content,			"flush")	\
+	EM(netfs_streaming_filled_page,		"mod-streamw-f") \
+	EM(netfs_streaming_cont_filled_page,	"mod-streamw-f+") \
+	/* The rest are for writeback */			\
+	EM(netfs_folio_trace_clear,		"clear")	\
+	EM(netfs_folio_trace_clear_s,		"clear-s")	\
+	EM(netfs_folio_trace_clear_g,		"clear-g")	\
+	EM(netfs_folio_trace_copy_to_cache,	"copy")		\
+	EM(netfs_folio_trace_end_copy,		"end-copy")	\
+	EM(netfs_folio_trace_kill,		"kill")		\
+	EM(netfs_folio_trace_mkwrite,		"mkwrite")	\
+	EM(netfs_folio_trace_mkwrite_plus,	"mkwrite+")	\
+	EM(netfs_folio_trace_redirty,		"redirty")	\
+	EM(netfs_folio_trace_redirtied,		"redirtied")	\
+	EM(netfs_folio_trace_store,		"store")	\
+	E_(netfs_folio_trace_store_plus,	"store+")
+
 #ifndef __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY
 #define __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY
 
@@ -115,6 +141,7 @@ enum netfs_sreq_trace { netfs_sreq_traces } __mode(byte);
 enum netfs_failure { netfs_failures } __mode(byte);
 enum netfs_rreq_ref_trace { netfs_rreq_ref_traces } __mode(byte);
 enum netfs_sreq_ref_trace { netfs_sreq_ref_traces } __mode(byte);
+enum netfs_folio_trace { netfs_folio_traces } __mode(byte);
 
 #endif
 
@@ -135,6 +162,7 @@ netfs_sreq_traces;
 netfs_failures;
 netfs_rreq_ref_traces;
 netfs_sreq_ref_traces;
+netfs_folio_traces;
 
 /*
  * Now redefine the EM() and E_() macros to map the enums to the strings that
@@ -335,6 +363,51 @@ TRACE_EVENT(netfs_sreq_ref,
 		      __entry->ref)
 	    );
 
+TRACE_EVENT(netfs_folio,
+	    TP_PROTO(struct folio *folio, enum netfs_folio_trace why),
+
+	    TP_ARGS(folio, why),
+
+	    TP_STRUCT__entry(
+		    __field(ino_t,			ino)
+		    __field(pgoff_t,			index)
+		    __field(unsigned int,		nr)
+		    __field(enum netfs_folio_trace,	why)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->ino = folio->mapping->host->i_ino;
+		    __entry->why = why;
+		    __entry->index = folio_index(folio);
+		    __entry->nr = folio_nr_pages(folio);
+			   ),
+
+	    TP_printk("i=%05lx ix=%05lx-%05lx %s",
+		      __entry->ino, __entry->index, __entry->index + __entry->nr - 1,
+		      __print_symbolic(__entry->why, netfs_folio_traces))
+	    );
+
+TRACE_EVENT(netfs_write_iter,
+	    TP_PROTO(const struct kiocb *iocb, const struct iov_iter *from),
+
+	    TP_ARGS(iocb, from),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned long long,		start		)
+		    __field(size_t,			len		)
+		    __field(unsigned int,		flags		)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->start	= iocb->ki_pos;
+		    __entry->len	= iov_iter_count(from);
+		    __entry->flags	= iocb->ki_flags;
+			   ),
+
+	    TP_printk("WRITE-ITER s=%llx l=%zx f=%x",
+		      __entry->start, __entry->len, __entry->flags)
+	    );
+
 TRACE_EVENT(netfs_write,
 	    TP_PROTO(const struct netfs_io_request *wreq,
 		     enum netfs_write_trace what),
-- 
cgit v1.2.3


From 7f84a7b9892d1c9429a6f5d6f67916c61b3fc183 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 2 Oct 2023 12:51:19 +0100
Subject: netfs: Make netfs_read_folio() handle streaming-write pages

netfs_read_folio() needs to handle partially-valid pages that are marked
dirty, but not uptodate in the event that someone tries to read a page was
used to cache data by a streaming write.

In such a case, make netfs_read_folio() set up a bvec iterator that points
to the parts of the folio that need filling and to a sink page for the data
that should be discarded and use that instead of i_pages as the iterator to
be written to.

This requires netfs_rreq_unlock_folios() to convert the page into a normal
dirty uptodate page, getting rid of the partial write record and bumping
the group pointer over to folio->private.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/buffered_read.c     | 61 +++++++++++++++++++++++++++++++++++++++++---
 include/trace/events/netfs.h |  2 ++
 2 files changed, 60 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index 73a6e4d61f9d..950f63fc156a 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -16,6 +16,7 @@
 void netfs_rreq_unlock_folios(struct netfs_io_request *rreq)
 {
 	struct netfs_io_subrequest *subreq;
+	struct netfs_folio *finfo;
 	struct folio *folio;
 	pgoff_t start_page = rreq->start / PAGE_SIZE;
 	pgoff_t last_page = ((rreq->start + rreq->len) / PAGE_SIZE) - 1;
@@ -87,6 +88,15 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq)
 
 		if (!pg_failed) {
 			flush_dcache_folio(folio);
+			finfo = netfs_folio_info(folio);
+			if (finfo) {
+				trace_netfs_folio(folio, netfs_folio_trace_filled_gaps);
+				if (finfo->netfs_group)
+					folio_change_private(folio, finfo->netfs_group);
+				else
+					folio_detach_private(folio);
+				kfree(finfo);
+			}
 			folio_mark_uptodate(folio);
 		}
 
@@ -239,6 +249,7 @@ int netfs_read_folio(struct file *file, struct folio *folio)
 	struct address_space *mapping = folio_file_mapping(folio);
 	struct netfs_io_request *rreq;
 	struct netfs_inode *ctx = netfs_inode(mapping->host);
+	struct folio *sink = NULL;
 	int ret;
 
 	_enter("%lx", folio_index(folio));
@@ -259,12 +270,56 @@ int netfs_read_folio(struct file *file, struct folio *folio)
 	trace_netfs_read(rreq, rreq->start, rreq->len, netfs_read_trace_readpage);
 
 	/* Set up the output buffer */
-	iov_iter_xarray(&rreq->iter, ITER_DEST, &mapping->i_pages,
-			rreq->start, rreq->len);
+	if (folio_test_dirty(folio)) {
+		/* Handle someone trying to read from an unflushed streaming
+		 * write.  We fiddle the buffer so that a gap at the beginning
+		 * and/or a gap at the end get copied to, but the middle is
+		 * discarded.
+		 */
+		struct netfs_folio *finfo = netfs_folio_info(folio);
+		struct bio_vec *bvec;
+		unsigned int from = finfo->dirty_offset;
+		unsigned int to = from + finfo->dirty_len;
+		unsigned int off = 0, i = 0;
+		size_t flen = folio_size(folio);
+		size_t nr_bvec = flen / PAGE_SIZE + 2;
+		size_t part;
+
+		ret = -ENOMEM;
+		bvec = kmalloc_array(nr_bvec, sizeof(*bvec), GFP_KERNEL);
+		if (!bvec)
+			goto discard;
+
+		sink = folio_alloc(GFP_KERNEL, 0);
+		if (!sink)
+			goto discard;
+
+		trace_netfs_folio(folio, netfs_folio_trace_read_gaps);
+
+		rreq->direct_bv = bvec;
+		rreq->direct_bv_count = nr_bvec;
+		if (from > 0) {
+			bvec_set_folio(&bvec[i++], folio, from, 0);
+			off = from;
+		}
+		while (off < to) {
+			part = min_t(size_t, to - off, PAGE_SIZE);
+			bvec_set_folio(&bvec[i++], sink, part, 0);
+			off += part;
+		}
+		if (to < flen)
+			bvec_set_folio(&bvec[i++], folio, flen - to, to);
+		iov_iter_bvec(&rreq->iter, ITER_DEST, bvec, i, rreq->len);
+	} else {
+		iov_iter_xarray(&rreq->iter, ITER_DEST, &mapping->i_pages,
+				rreq->start, rreq->len);
+	}
 
 	ret = netfs_begin_read(rreq, true);
+	if (sink)
+		folio_put(sink);
 	netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
-	return ret;
+	return ret < 0 ? ret : 0;
 
 discard:
 	netfs_put_request(rreq, false, netfs_rreq_trace_put_discard);
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index 8308b81f36be..082a5e717b58 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -118,9 +118,11 @@
 	EM(netfs_folio_trace_clear_g,		"clear-g")	\
 	EM(netfs_folio_trace_copy_to_cache,	"copy")		\
 	EM(netfs_folio_trace_end_copy,		"end-copy")	\
+	EM(netfs_folio_trace_filled_gaps,	"filled-gaps")	\
 	EM(netfs_folio_trace_kill,		"kill")		\
 	EM(netfs_folio_trace_mkwrite,		"mkwrite")	\
 	EM(netfs_folio_trace_mkwrite_plus,	"mkwrite+")	\
+	EM(netfs_folio_trace_read_gaps,		"read-gaps")	\
 	EM(netfs_folio_trace_redirty,		"redirty")	\
 	EM(netfs_folio_trace_redirtied,		"redirtied")	\
 	EM(netfs_folio_trace_store,		"store")	\
-- 
cgit v1.2.3


From 016dc8516aec8719641e7aaaacd78d344759178e Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 14 Jan 2022 17:39:55 +0000
Subject: netfs: Implement unbuffered/DIO read support

Implement support for unbuffered and DIO reads in the netfs library,
utilising the existing read helper code to do block splitting and
individual queuing.  The code also handles extraction of the destination
buffer from the supplied iterator, allowing async unbuffered reads to take
place.

The read will be split up according to the rsize setting and, if supplied,
the ->clamp_length() method.  Note that the next subrequest will be issued
as soon as issue_op returns, without waiting for previous ones to finish.
The network filesystem needs to pause or handle queuing them if it doesn't
want to fire them all at the server simultaneously.

Once all the subrequests have finished, the state will be assessed and the
amount of data to be indicated as having being obtained will be
determined.  As the subrequests may finish in any order, if an intermediate
subrequest is short, any further subrequests may be copied into the buffer
and then abandoned.

In the future, this will also take care of doing an unbuffered read from
encrypted content, with the decryption being done by the library.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/Makefile            |   1 +
 fs/netfs/direct_read.c       | 125 +++++++++++++++++++++++++++++++++++++++++++
 fs/netfs/internal.h          |   1 +
 fs/netfs/io.c                |  83 +++++++++++++++++++++++++---
 fs/netfs/main.c              |   1 +
 fs/netfs/objects.c           |   5 +-
 fs/netfs/stats.c             |   4 +-
 include/linux/netfs.h        |   9 ++++
 include/trace/events/netfs.h |   7 ++-
 mm/filemap.c                 |   1 +
 10 files changed, 226 insertions(+), 11 deletions(-)
 create mode 100644 fs/netfs/direct_read.c

(limited to 'include')

diff --git a/fs/netfs/Makefile b/fs/netfs/Makefile
index 85d8333a1ed4..e968ab1eca40 100644
--- a/fs/netfs/Makefile
+++ b/fs/netfs/Makefile
@@ -3,6 +3,7 @@
 netfs-y := \
 	buffered_read.o \
 	buffered_write.o \
+	direct_read.o \
 	io.o \
 	iterator.o \
 	locking.o \
diff --git a/fs/netfs/direct_read.c b/fs/netfs/direct_read.c
new file mode 100644
index 000000000000..ad4370b3935d
--- /dev/null
+++ b/fs/netfs/direct_read.c
@@ -0,0 +1,125 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Direct I/O support.
+ *
+ * Copyright (C) 2023 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/export.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+#include <linux/slab.h>
+#include <linux/uio.h>
+#include <linux/sched/mm.h>
+#include <linux/task_io_accounting_ops.h>
+#include <linux/netfs.h>
+#include "internal.h"
+
+/**
+ * netfs_unbuffered_read_iter_locked - Perform an unbuffered or direct I/O read
+ * @iocb: The I/O control descriptor describing the read
+ * @iter: The output buffer (also specifies read length)
+ *
+ * Perform an unbuffered I/O or direct I/O from the file in @iocb to the
+ * output buffer.  No use is made of the pagecache.
+ *
+ * The caller must hold any appropriate locks.
+ */
+static ssize_t netfs_unbuffered_read_iter_locked(struct kiocb *iocb, struct iov_iter *iter)
+{
+	struct netfs_io_request *rreq;
+	ssize_t ret;
+	size_t orig_count = iov_iter_count(iter);
+	bool async = !is_sync_kiocb(iocb);
+
+	_enter("");
+
+	if (!orig_count)
+		return 0; /* Don't update atime */
+
+	ret = kiocb_write_and_wait(iocb, orig_count);
+	if (ret < 0)
+		return ret;
+	file_accessed(iocb->ki_filp);
+
+	rreq = netfs_alloc_request(iocb->ki_filp->f_mapping, iocb->ki_filp,
+				   iocb->ki_pos, orig_count,
+				   NETFS_DIO_READ);
+	if (IS_ERR(rreq))
+		return PTR_ERR(rreq);
+
+	netfs_stat(&netfs_n_rh_dio_read);
+	trace_netfs_read(rreq, rreq->start, rreq->len, netfs_read_trace_dio_read);
+
+	/* If this is an async op, we have to keep track of the destination
+	 * buffer for ourselves as the caller's iterator will be trashed when
+	 * we return.
+	 *
+	 * In such a case, extract an iterator to represent as much of the the
+	 * output buffer as we can manage.  Note that the extraction might not
+	 * be able to allocate a sufficiently large bvec array and may shorten
+	 * the request.
+	 */
+	if (user_backed_iter(iter)) {
+		ret = netfs_extract_user_iter(iter, rreq->len, &rreq->iter, 0);
+		if (ret < 0)
+			goto out;
+		rreq->direct_bv = (struct bio_vec *)rreq->iter.bvec;
+		rreq->direct_bv_count = ret;
+		rreq->direct_bv_unpin = iov_iter_extract_will_pin(iter);
+		rreq->len = iov_iter_count(&rreq->iter);
+	} else {
+		rreq->iter = *iter;
+		rreq->len = orig_count;
+		rreq->direct_bv_unpin = false;
+		iov_iter_advance(iter, orig_count);
+	}
+
+	// TODO: Set up bounce buffer if needed
+
+	if (async)
+		rreq->iocb = iocb;
+
+	ret = netfs_begin_read(rreq, is_sync_kiocb(iocb));
+	if (ret < 0)
+		goto out; /* May be -EIOCBQUEUED */
+	if (!async) {
+		// TODO: Copy from bounce buffer
+		iocb->ki_pos += rreq->transferred;
+		ret = rreq->transferred;
+	}
+
+out:
+	netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
+	if (ret > 0)
+		orig_count -= ret;
+	if (ret != -EIOCBQUEUED)
+		iov_iter_revert(iter, orig_count - iov_iter_count(iter));
+	return ret;
+}
+
+/**
+ * netfs_unbuffered_read_iter - Perform an unbuffered or direct I/O read
+ * @iocb: The I/O control descriptor describing the read
+ * @iter: The output buffer (also specifies read length)
+ *
+ * Perform an unbuffered I/O or direct I/O from the file in @iocb to the
+ * output buffer.  No use is made of the pagecache.
+ */
+ssize_t netfs_unbuffered_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	ssize_t ret;
+
+	if (!iter->count)
+		return 0; /* Don't update atime */
+
+	ret = netfs_start_io_direct(inode);
+	if (ret == 0) {
+		ret = netfs_unbuffered_read_iter_locked(iocb, iter);
+		netfs_end_io_direct(inode);
+	}
+	return ret;
+}
+EXPORT_SYMBOL(netfs_unbuffered_read_iter);
diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index 17e4ea4456c7..886c2e8f841f 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -100,6 +100,7 @@ int netfs_begin_write(struct netfs_io_request *wreq, bool may_wait,
  * stats.c
  */
 #ifdef CONFIG_NETFS_STATS
+extern atomic_t netfs_n_rh_dio_read;
 extern atomic_t netfs_n_rh_readahead;
 extern atomic_t netfs_n_rh_readpage;
 extern atomic_t netfs_n_rh_rreq;
diff --git a/fs/netfs/io.c b/fs/netfs/io.c
index 774aef6ea4cb..c972415c8aad 100644
--- a/fs/netfs/io.c
+++ b/fs/netfs/io.c
@@ -78,7 +78,9 @@ static void netfs_read_from_server(struct netfs_io_request *rreq,
 				   struct netfs_io_subrequest *subreq)
 {
 	netfs_stat(&netfs_n_rh_download);
-	if (iov_iter_count(&subreq->io_iter) != subreq->len - subreq->transferred)
+
+	if (rreq->origin != NETFS_DIO_READ &&
+	    iov_iter_count(&subreq->io_iter) != subreq->len - subreq->transferred)
 		pr_warn("R=%08x[%u] ITER PRE-MISMATCH %zx != %zx-%zx %lx\n",
 			rreq->debug_id, subreq->debug_index,
 			iov_iter_count(&subreq->io_iter), subreq->len,
@@ -341,6 +343,43 @@ static void netfs_rreq_is_still_valid(struct netfs_io_request *rreq)
 	}
 }
 
+/*
+ * Determine how much we can admit to having read from a DIO read.
+ */
+static void netfs_rreq_assess_dio(struct netfs_io_request *rreq)
+{
+	struct netfs_io_subrequest *subreq;
+	unsigned int i;
+	size_t transferred = 0;
+
+	for (i = 0; i < rreq->direct_bv_count; i++)
+		flush_dcache_page(rreq->direct_bv[i].bv_page);
+
+	list_for_each_entry(subreq, &rreq->subrequests, rreq_link) {
+		if (subreq->error || subreq->transferred == 0)
+			break;
+		transferred += subreq->transferred;
+		if (subreq->transferred < subreq->len)
+			break;
+	}
+
+	for (i = 0; i < rreq->direct_bv_count; i++)
+		flush_dcache_page(rreq->direct_bv[i].bv_page);
+
+	rreq->transferred = transferred;
+	task_io_account_read(transferred);
+
+	if (rreq->iocb) {
+		rreq->iocb->ki_pos += transferred;
+		if (rreq->iocb->ki_complete)
+			rreq->iocb->ki_complete(
+				rreq->iocb, rreq->error ? rreq->error : transferred);
+	}
+	if (rreq->netfs_ops->done)
+		rreq->netfs_ops->done(rreq);
+	inode_dio_end(rreq->inode);
+}
+
 /*
  * Assess the state of a read request and decide what to do next.
  *
@@ -361,7 +400,10 @@ again:
 		return;
 	}
 
-	netfs_rreq_unlock_folios(rreq);
+	if (rreq->origin != NETFS_DIO_READ)
+		netfs_rreq_unlock_folios(rreq);
+	else
+		netfs_rreq_assess_dio(rreq);
 
 	trace_netfs_rreq(rreq, netfs_rreq_trace_wake_ip);
 	clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &rreq->flags);
@@ -526,14 +568,16 @@ netfs_rreq_prepare_read(struct netfs_io_request *rreq,
 			struct netfs_io_subrequest *subreq,
 			struct iov_iter *io_iter)
 {
-	enum netfs_io_source source;
+	enum netfs_io_source source = NETFS_DOWNLOAD_FROM_SERVER;
 	size_t lsize;
 
 	_enter("%llx-%llx,%llx", subreq->start, subreq->start + subreq->len, rreq->i_size);
 
-	source = netfs_cache_prepare_read(subreq, rreq->i_size);
-	if (source == NETFS_INVALID_READ)
-		goto out;
+	if (rreq->origin != NETFS_DIO_READ) {
+		source = netfs_cache_prepare_read(subreq, rreq->i_size);
+		if (source == NETFS_INVALID_READ)
+			goto out;
+	}
 
 	if (source == NETFS_DOWNLOAD_FROM_SERVER) {
 		/* Call out to the netfs to let it shrink the request to fit
@@ -544,6 +588,8 @@ netfs_rreq_prepare_read(struct netfs_io_request *rreq,
 		 */
 		if (subreq->len > rreq->i_size - subreq->start)
 			subreq->len = rreq->i_size - subreq->start;
+		if (rreq->rsize && subreq->len > rreq->rsize)
+			subreq->len = rreq->rsize;
 
 		if (rreq->netfs_ops->clamp_length &&
 		    !rreq->netfs_ops->clamp_length(subreq)) {
@@ -662,6 +708,10 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
 		return -EIO;
 	}
 
+	if (rreq->origin == NETFS_DIO_READ)
+		inode_dio_begin(rreq->inode);
+
+	// TODO: Use bounce buffer if requested
 	rreq->io_iter = rreq->iter;
 
 	INIT_WORK(&rreq->work, netfs_rreq_work);
@@ -673,11 +723,25 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
 	atomic_set(&rreq->nr_outstanding, 1);
 	io_iter = rreq->io_iter;
 	do {
+		_debug("submit %llx + %zx >= %llx",
+		       rreq->start, rreq->submitted, rreq->i_size);
+		if (rreq->origin == NETFS_DIO_READ &&
+		    rreq->start + rreq->submitted >= rreq->i_size)
+			break;
 		if (!netfs_rreq_submit_slice(rreq, &io_iter, &debug_index))
 			break;
+		if (test_bit(NETFS_RREQ_BLOCKED, &rreq->flags) &&
+		    test_bit(NETFS_RREQ_NONBLOCK, &rreq->flags))
+			break;
 
 	} while (rreq->submitted < rreq->len);
 
+	if (!rreq->submitted) {
+		netfs_put_request(rreq, false, netfs_rreq_trace_put_no_submit);
+		ret = 0;
+		goto out;
+	}
+
 	if (sync) {
 		/* Keep nr_outstanding incremented so that the ref always
 		 * belongs to us, and the service code isn't punted off to a
@@ -694,7 +758,8 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
 			    TASK_UNINTERRUPTIBLE);
 
 		ret = rreq->error;
-		if (ret == 0 && rreq->submitted < rreq->len) {
+		if (ret == 0 && rreq->submitted < rreq->len &&
+		    rreq->origin != NETFS_DIO_READ) {
 			trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read);
 			ret = -EIO;
 		}
@@ -702,7 +767,9 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
 		/* If we decrement nr_outstanding to 0, the ref belongs to us. */
 		if (atomic_dec_and_test(&rreq->nr_outstanding))
 			netfs_rreq_assess(rreq, false);
-		ret = 0;
+		ret = -EIOCBQUEUED;
 	}
+
+out:
 	return ret;
 }
diff --git a/fs/netfs/main.c b/fs/netfs/main.c
index ab6cac110676..abb8857486ee 100644
--- a/fs/netfs/main.c
+++ b/fs/netfs/main.c
@@ -30,6 +30,7 @@ static const char *netfs_origins[nr__netfs_io_origin] = {
 	[NETFS_READPAGE]	= "RP",
 	[NETFS_READ_FOR_WRITE]	= "RW",
 	[NETFS_WRITEBACK]	= "WB",
+	[NETFS_DIO_READ]	= "DR",
 };
 
 /*
diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c
index 3aa0bfbc04ec..7153f24e8034 100644
--- a/fs/netfs/objects.c
+++ b/fs/netfs/objects.c
@@ -20,7 +20,8 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
 	struct inode *inode = file ? file_inode(file) : mapping->host;
 	struct netfs_inode *ctx = netfs_inode(inode);
 	struct netfs_io_request *rreq;
-	bool cached = netfs_is_cache_enabled(ctx);
+	bool is_dio = (origin == NETFS_DIO_READ);
+	bool cached = is_dio && netfs_is_cache_enabled(ctx);
 	int ret;
 
 	rreq = kzalloc(ctx->ops->io_request_size ?: sizeof(struct netfs_io_request),
@@ -42,6 +43,8 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
 	__set_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags);
 	if (cached)
 		__set_bit(NETFS_RREQ_WRITE_TO_CACHE, &rreq->flags);
+	if (file && file->f_flags & O_NONBLOCK)
+		__set_bit(NETFS_RREQ_NONBLOCK, &rreq->flags);
 	if (rreq->netfs_ops->init_request) {
 		ret = rreq->netfs_ops->init_request(rreq, file);
 		if (ret < 0) {
diff --git a/fs/netfs/stats.c b/fs/netfs/stats.c
index c1f85cd595a4..15fd5c3f0f39 100644
--- a/fs/netfs/stats.c
+++ b/fs/netfs/stats.c
@@ -9,6 +9,7 @@
 #include <linux/seq_file.h>
 #include "internal.h"
 
+atomic_t netfs_n_rh_dio_read;
 atomic_t netfs_n_rh_readahead;
 atomic_t netfs_n_rh_readpage;
 atomic_t netfs_n_rh_rreq;
@@ -36,7 +37,8 @@ atomic_t netfs_n_wh_write_failed;
 
 int netfs_stats_show(struct seq_file *m, void *v)
 {
-	seq_printf(m, "Netfs  : RA=%u RP=%u WB=%u WBZ=%u rr=%u sr=%u\n",
+	seq_printf(m, "Netfs  : DR=%u RA=%u RP=%u WB=%u WBZ=%u rr=%u sr=%u\n",
+		   atomic_read(&netfs_n_rh_dio_read),
 		   atomic_read(&netfs_n_rh_readahead),
 		   atomic_read(&netfs_n_rh_readpage),
 		   atomic_read(&netfs_n_rh_write_begin),
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 70f578cf3715..7c1309568459 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -226,6 +226,7 @@ enum netfs_io_origin {
 	NETFS_READPAGE,			/* This read is a synchronous read */
 	NETFS_READ_FOR_WRITE,		/* This read is to prepare a write */
 	NETFS_WRITEBACK,		/* This write was triggered by writepages */
+	NETFS_DIO_READ,			/* This is a direct I/O read */
 	nr__netfs_io_origin
 } __mode(byte);
 
@@ -240,6 +241,7 @@ struct netfs_io_request {
 	};
 	struct inode		*inode;		/* The file being accessed */
 	struct address_space	*mapping;	/* The mapping being accessed */
+	struct kiocb		*iocb;		/* AIO completion vector */
 	struct netfs_cache_resources cache_resources;
 	struct list_head	proc_link;	/* Link in netfs_iorequests */
 	struct list_head	subrequests;	/* Contributory I/O operations */
@@ -249,12 +251,14 @@ struct netfs_io_request {
 	struct bio_vec		*direct_bv;	/* DIO buffer list (when handling iovec-iter) */
 	unsigned int		direct_bv_count; /* Number of elements in direct_bv[] */
 	unsigned int		debug_id;
+	unsigned int		rsize;		/* Maximum read size (0 for none) */
 	unsigned int		wsize;		/* Maximum write size (0 for none) */
 	unsigned int		subreq_counter;	/* Next subreq->debug_index */
 	atomic_t		nr_outstanding;	/* Number of ops in progress */
 	atomic_t		nr_copy_ops;	/* Number of copy-to-cache ops in progress */
 	size_t			submitted;	/* Amount submitted for I/O so far */
 	size_t			len;		/* Length of the request */
+	size_t			transferred;	/* Amount to be indicated as transferred */
 	short			error;		/* 0 or error that occurred */
 	enum netfs_io_origin	origin;		/* Origin of the request */
 	bool			direct_bv_unpin; /* T if direct_bv[] must be unpinned */
@@ -271,6 +275,8 @@ struct netfs_io_request {
 #define NETFS_RREQ_IN_PROGRESS		5	/* Unlocked when the request completes */
 #define NETFS_RREQ_WRITE_TO_CACHE	7	/* Need to write to the cache */
 #define NETFS_RREQ_UPLOAD_TO_SERVER	8	/* Need to write to the server */
+#define NETFS_RREQ_NONBLOCK		9	/* Don't block if possible (O_NONBLOCK) */
+#define NETFS_RREQ_BLOCKED		10	/* We blocked */
 	const struct netfs_request_ops *netfs_ops;
 	void (*cleanup)(struct netfs_io_request *req);
 };
@@ -367,6 +373,9 @@ struct netfs_cache_ops {
 			       loff_t *_data_start, size_t *_data_len);
 };
 
+/* High-level read API. */
+ssize_t netfs_unbuffered_read_iter(struct kiocb *iocb, struct iov_iter *iter);
+
 /* High-level write API */
 ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 			    struct netfs_group *netfs_group);
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index 082a5e717b58..5a4edadf0e59 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -16,6 +16,7 @@
  * Define enums for tracing information.
  */
 #define netfs_read_traces					\
+	EM(netfs_read_trace_dio_read,		"DIO-READ ")	\
 	EM(netfs_read_trace_expanded,		"EXPANDED ")	\
 	EM(netfs_read_trace_readahead,		"READAHEAD")	\
 	EM(netfs_read_trace_readpage,		"READPAGE ")	\
@@ -31,7 +32,8 @@
 	EM(NETFS_READAHEAD,			"RA")		\
 	EM(NETFS_READPAGE,			"RP")		\
 	EM(NETFS_READ_FOR_WRITE,		"RW")		\
-	E_(NETFS_WRITEBACK,			"WB")
+	EM(NETFS_WRITEBACK,			"WB")		\
+	E_(NETFS_DIO_READ,			"DR")
 
 #define netfs_rreq_traces					\
 	EM(netfs_rreq_trace_assess,		"ASSESS ")	\
@@ -70,6 +72,8 @@
 #define netfs_failures							\
 	EM(netfs_fail_check_write_begin,	"check-write-begin")	\
 	EM(netfs_fail_copy_to_cache,		"copy-to-cache")	\
+	EM(netfs_fail_dio_read_short,		"dio-read-short")	\
+	EM(netfs_fail_dio_read_zero,		"dio-read-zero")	\
 	EM(netfs_fail_read,			"read")			\
 	EM(netfs_fail_short_read,		"short-read")		\
 	EM(netfs_fail_prepare_write,		"prep-write")		\
@@ -81,6 +85,7 @@
 	EM(netfs_rreq_trace_put_complete,	"PUT COMPLT ")	\
 	EM(netfs_rreq_trace_put_discard,	"PUT DISCARD")	\
 	EM(netfs_rreq_trace_put_failed,		"PUT FAILED ")	\
+	EM(netfs_rreq_trace_put_no_submit,	"PUT NO-SUBM")	\
 	EM(netfs_rreq_trace_put_return,		"PUT RETURN ")	\
 	EM(netfs_rreq_trace_put_subreq,		"PUT SUBREQ ")	\
 	EM(netfs_rreq_trace_put_work,		"PUT WORK   ")	\
diff --git a/mm/filemap.c b/mm/filemap.c
index f1c8c278310f..1c5271ed0cc0 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2678,6 +2678,7 @@ int kiocb_write_and_wait(struct kiocb *iocb, size_t count)
 
 	return filemap_write_and_wait_range(mapping, pos, end);
 }
+EXPORT_SYMBOL_GPL(kiocb_write_and_wait);
 
 int kiocb_invalidate_pages(struct kiocb *iocb, size_t count)
 {
-- 
cgit v1.2.3


From 153a9961b551101cd38e94e26cd92fbfd198b19b Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 21 Feb 2022 11:38:17 +0000
Subject: netfs: Implement unbuffered/DIO write support

Implement support for unbuffered writes and direct I/O writes.  If the
write is misaligned with respect to the fscrypt block size, then RMW cycles
are performed if necessary.  DIO writes are a special case of unbuffered
writes with extra restriction imposed, such as block size alignment
requirements.

Also provide a field that can tell the code to add some extra space onto
the bounce buffer for use by the filesystem in the case of a
content-encrypted file.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/afs/inode.c               |   2 +-
 fs/netfs/Makefile            |   1 +
 fs/netfs/direct_write.c      | 166 +++++++++++++++++++++++++++++++++++++++++++
 fs/netfs/internal.h          |   6 ++
 fs/netfs/io.c                |   2 +-
 fs/netfs/main.c              |  12 ++--
 fs/netfs/objects.c           |   6 +-
 fs/netfs/output.c            |  30 ++++++++
 include/linux/netfs.h        |   4 ++
 include/trace/events/netfs.h |   4 +-
 mm/filemap.c                 |   1 +
 11 files changed, 224 insertions(+), 10 deletions(-)
 create mode 100644 fs/netfs/direct_write.c

(limited to 'include')

diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 6f375f0cf650..37485ae31471 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -250,7 +250,7 @@ static void afs_apply_status(struct afs_operation *op,
 		 * what's on the server.
 		 */
 		vnode->netfs.remote_i_size = status->size;
-		if (change_size) {
+		if (change_size || status->size > i_size_read(inode)) {
 			afs_set_i_size(vnode, status->size);
 			inode_set_ctime_to_ts(inode, t);
 			inode_set_atime_to_ts(inode, t);
diff --git a/fs/netfs/Makefile b/fs/netfs/Makefile
index e968ab1eca40..d4d1d799819e 100644
--- a/fs/netfs/Makefile
+++ b/fs/netfs/Makefile
@@ -4,6 +4,7 @@ netfs-y := \
 	buffered_read.o \
 	buffered_write.o \
 	direct_read.o \
+	direct_write.o \
 	io.o \
 	iterator.o \
 	locking.o \
diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c
new file mode 100644
index 000000000000..bb0c2718f57b
--- /dev/null
+++ b/fs/netfs/direct_write.c
@@ -0,0 +1,166 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Unbuffered and direct write support.
+ *
+ * Copyright (C) 2023 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/export.h>
+#include <linux/uio.h>
+#include "internal.h"
+
+static void netfs_cleanup_dio_write(struct netfs_io_request *wreq)
+{
+	struct inode *inode = wreq->inode;
+	unsigned long long end = wreq->start + wreq->len;
+
+	if (!wreq->error &&
+	    i_size_read(inode) < end) {
+		if (wreq->netfs_ops->update_i_size)
+			wreq->netfs_ops->update_i_size(inode, end);
+		else
+			i_size_write(inode, end);
+	}
+}
+
+/*
+ * Perform an unbuffered write where we may have to do an RMW operation on an
+ * encrypted file.  This can also be used for direct I/O writes.
+ */
+ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *iter,
+					   struct netfs_group *netfs_group)
+{
+	struct netfs_io_request *wreq;
+	unsigned long long start = iocb->ki_pos;
+	unsigned long long end = start + iov_iter_count(iter);
+	ssize_t ret, n;
+	bool async = !is_sync_kiocb(iocb);
+
+	_enter("");
+
+	/* We're going to need a bounce buffer if what we transmit is going to
+	 * be different in some way to the source buffer, e.g. because it gets
+	 * encrypted/compressed or because it needs expanding to a block size.
+	 */
+	// TODO
+
+	_debug("uw %llx-%llx", start, end);
+
+	wreq = netfs_alloc_request(iocb->ki_filp->f_mapping, iocb->ki_filp,
+				   start, end - start,
+				   iocb->ki_flags & IOCB_DIRECT ?
+				   NETFS_DIO_WRITE : NETFS_UNBUFFERED_WRITE);
+	if (IS_ERR(wreq))
+		return PTR_ERR(wreq);
+
+	{
+		/* If this is an async op and we're not using a bounce buffer,
+		 * we have to save the source buffer as the iterator is only
+		 * good until we return.  In such a case, extract an iterator
+		 * to represent as much of the the output buffer as we can
+		 * manage.  Note that the extraction might not be able to
+		 * allocate a sufficiently large bvec array and may shorten the
+		 * request.
+		 */
+		if (async || user_backed_iter(iter)) {
+			n = netfs_extract_user_iter(iter, wreq->len, &wreq->iter, 0);
+			if (n < 0) {
+				ret = n;
+				goto out;
+			}
+			wreq->direct_bv = (struct bio_vec *)wreq->iter.bvec;
+			wreq->direct_bv_count = n;
+			wreq->direct_bv_unpin = iov_iter_extract_will_pin(iter);
+			wreq->len = iov_iter_count(&wreq->iter);
+		} else {
+			wreq->iter = *iter;
+		}
+
+		wreq->io_iter = wreq->iter;
+	}
+
+	/* Copy the data into the bounce buffer and encrypt it. */
+	// TODO
+
+	/* Dispatch the write. */
+	__set_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags);
+	if (async)
+		wreq->iocb = iocb;
+	wreq->cleanup = netfs_cleanup_dio_write;
+	ret = netfs_begin_write(wreq, is_sync_kiocb(iocb),
+				iocb->ki_flags & IOCB_DIRECT ?
+				netfs_write_trace_dio_write :
+				netfs_write_trace_unbuffered_write);
+	if (ret < 0) {
+		_debug("begin = %zd", ret);
+		goto out;
+	}
+
+	if (!async) {
+		trace_netfs_rreq(wreq, netfs_rreq_trace_wait_ip);
+		wait_on_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS,
+			    TASK_UNINTERRUPTIBLE);
+
+		ret = wreq->error;
+		_debug("waited = %zd", ret);
+		if (ret == 0) {
+			ret = wreq->transferred;
+			iocb->ki_pos += ret;
+		}
+	} else {
+		ret = -EIOCBQUEUED;
+	}
+
+out:
+	netfs_put_request(wreq, false, netfs_rreq_trace_put_return);
+	return ret;
+}
+
+/**
+ * netfs_unbuffered_write_iter - Unbuffered write to a file
+ * @iocb: IO state structure
+ * @from: iov_iter with data to write
+ *
+ * Do an unbuffered write to a file, writing the data directly to the server
+ * and not lodging the data in the pagecache.
+ *
+ * Return:
+ * * Negative error code if no data has been written at all of
+ *   vfs_fsync_range() failed for a synchronous write
+ * * Number of bytes written, even for truncated writes
+ */
+ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file->f_mapping->host;
+	struct netfs_inode *ictx = netfs_inode(inode);
+	ssize_t ret;
+
+	_enter("%llx,%zx,%llx", iocb->ki_pos, iov_iter_count(from), i_size_read(inode));
+
+	trace_netfs_write_iter(iocb, from);
+
+	ret = netfs_start_io_direct(inode);
+	if (ret < 0)
+		return ret;
+	ret = generic_write_checks(iocb, from);
+	if (ret < 0)
+		goto out;
+	ret = file_remove_privs(file);
+	if (ret < 0)
+		goto out;
+	ret = file_update_time(file);
+	if (ret < 0)
+		goto out;
+	ret = kiocb_invalidate_pages(iocb, iov_iter_count(from));
+	if (ret < 0)
+		goto out;
+
+	fscache_invalidate(netfs_i_cookie(ictx), NULL, i_size_read(inode),
+			   FSCACHE_INVAL_DIO_WRITE);
+	ret = netfs_unbuffered_write_iter_locked(iocb, from, NULL);
+out:
+	netfs_end_io_direct(inode);
+	return ret;
+}
+EXPORT_SYMBOL(netfs_unbuffered_write_iter);
diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index 886c2e8f841f..2de4f826dbe4 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -26,6 +26,12 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq);
 int netfs_prefetch_for_write(struct file *file, struct folio *folio,
 			     size_t offset, size_t len);
 
+/*
+ * direct_write.c
+ */
+ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *iter,
+					   struct netfs_group *netfs_group);
+
 /*
  * io.c
  */
diff --git a/fs/netfs/io.c b/fs/netfs/io.c
index c972415c8aad..01c7ff27228e 100644
--- a/fs/netfs/io.c
+++ b/fs/netfs/io.c
@@ -645,7 +645,7 @@ static bool netfs_rreq_submit_slice(struct netfs_io_request *rreq,
 
 	subreq->debug_index	= (*_debug_index)++;
 	subreq->start		= rreq->start + rreq->submitted;
-	subreq->len		= rreq->len   - rreq->submitted;
+	subreq->len		= io_iter->count;
 
 	_debug("slice %llx,%zx,%zx", subreq->start, subreq->len, rreq->submitted);
 	list_add_tail(&subreq->rreq_link, &rreq->subrequests);
diff --git a/fs/netfs/main.c b/fs/netfs/main.c
index abb8857486ee..8e4db9ff40c4 100644
--- a/fs/netfs/main.c
+++ b/fs/netfs/main.c
@@ -26,11 +26,13 @@ LIST_HEAD(netfs_io_requests);
 DEFINE_SPINLOCK(netfs_proc_lock);
 
 static const char *netfs_origins[nr__netfs_io_origin] = {
-	[NETFS_READAHEAD]	= "RA",
-	[NETFS_READPAGE]	= "RP",
-	[NETFS_READ_FOR_WRITE]	= "RW",
-	[NETFS_WRITEBACK]	= "WB",
-	[NETFS_DIO_READ]	= "DR",
+	[NETFS_READAHEAD]		= "RA",
+	[NETFS_READPAGE]		= "RP",
+	[NETFS_READ_FOR_WRITE]		= "RW",
+	[NETFS_WRITEBACK]		= "WB",
+	[NETFS_UNBUFFERED_WRITE]	= "UW",
+	[NETFS_DIO_READ]		= "DR",
+	[NETFS_DIO_WRITE]		= "DW",
 };
 
 /*
diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c
index 7153f24e8034..93f1d7431199 100644
--- a/fs/netfs/objects.c
+++ b/fs/netfs/objects.c
@@ -20,8 +20,10 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
 	struct inode *inode = file ? file_inode(file) : mapping->host;
 	struct netfs_inode *ctx = netfs_inode(inode);
 	struct netfs_io_request *rreq;
-	bool is_dio = (origin == NETFS_DIO_READ);
-	bool cached = is_dio && netfs_is_cache_enabled(ctx);
+	bool is_unbuffered = (origin == NETFS_UNBUFFERED_WRITE ||
+			      origin == NETFS_DIO_READ ||
+			      origin == NETFS_DIO_WRITE);
+	bool cached = !is_unbuffered && netfs_is_cache_enabled(ctx);
 	int ret;
 
 	rreq = kzalloc(ctx->ops->io_request_size ?: sizeof(struct netfs_io_request),
diff --git a/fs/netfs/output.c b/fs/netfs/output.c
index 2ad0fd8c32be..560cbcea0c0a 100644
--- a/fs/netfs/output.c
+++ b/fs/netfs/output.c
@@ -74,11 +74,21 @@ static void netfs_write_terminated(struct netfs_io_request *wreq, bool was_async
 {
 	struct netfs_io_subrequest *subreq;
 	struct netfs_inode *ctx = netfs_inode(wreq->inode);
+	size_t transferred = 0;
 
 	_enter("R=%x[]", wreq->debug_id);
 
 	trace_netfs_rreq(wreq, netfs_rreq_trace_write_done);
 
+	list_for_each_entry(subreq, &wreq->subrequests, rreq_link) {
+		if (subreq->error || subreq->transferred == 0)
+			break;
+		transferred += subreq->transferred;
+		if (subreq->transferred < subreq->len)
+			break;
+	}
+	wreq->transferred = transferred;
+
 	list_for_each_entry(subreq, &wreq->subrequests, rreq_link) {
 		if (!subreq->error)
 			continue;
@@ -110,11 +120,28 @@ static void netfs_write_terminated(struct netfs_io_request *wreq, bool was_async
 
 	wreq->cleanup(wreq);
 
+	if (wreq->origin == NETFS_DIO_WRITE &&
+	    wreq->mapping->nrpages) {
+		pgoff_t first = wreq->start >> PAGE_SHIFT;
+		pgoff_t last = (wreq->start + wreq->transferred - 1) >> PAGE_SHIFT;
+		invalidate_inode_pages2_range(wreq->mapping, first, last);
+	}
+
+	if (wreq->origin == NETFS_DIO_WRITE)
+		inode_dio_end(wreq->inode);
+
 	_debug("finished");
 	trace_netfs_rreq(wreq, netfs_rreq_trace_wake_ip);
 	clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &wreq->flags);
 	wake_up_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS);
 
+	if (wreq->iocb) {
+		wreq->iocb->ki_pos += transferred;
+		if (wreq->iocb->ki_complete)
+			wreq->iocb->ki_complete(
+				wreq->iocb, wreq->error ? wreq->error : transferred);
+	}
+
 	netfs_clear_subrequests(wreq, was_async);
 	netfs_put_request(wreq, was_async, netfs_rreq_trace_put_complete);
 }
@@ -329,6 +356,9 @@ int netfs_begin_write(struct netfs_io_request *wreq, bool may_wait,
 		return -EIO;
 	}
 
+	if (wreq->origin == NETFS_DIO_WRITE)
+		inode_dio_begin(wreq->inode);
+
 	wreq->io_iter = wreq->iter;
 
 	/* ->outstanding > 0 carries a ref */
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 7c1309568459..e1dfd6775c2c 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -138,6 +138,7 @@ struct netfs_inode {
 	loff_t			remote_i_size;	/* Size of the remote file */
 	unsigned long		flags;
 #define NETFS_ICTX_ODIRECT	0		/* The file has DIO in progress */
+#define NETFS_ICTX_UNBUFFERED	1		/* I/O should not use the pagecache */
 };
 
 /*
@@ -226,7 +227,9 @@ enum netfs_io_origin {
 	NETFS_READPAGE,			/* This read is a synchronous read */
 	NETFS_READ_FOR_WRITE,		/* This read is to prepare a write */
 	NETFS_WRITEBACK,		/* This write was triggered by writepages */
+	NETFS_UNBUFFERED_WRITE,		/* This is an unbuffered write */
 	NETFS_DIO_READ,			/* This is a direct I/O read */
+	NETFS_DIO_WRITE,		/* This is a direct I/O write */
 	nr__netfs_io_origin
 } __mode(byte);
 
@@ -379,6 +382,7 @@ ssize_t netfs_unbuffered_read_iter(struct kiocb *iocb, struct iov_iter *iter);
 /* High-level write API */
 ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 			    struct netfs_group *netfs_group);
+ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from);
 
 /* Address operations API */
 struct readahead_control;
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index 5a4edadf0e59..914a24b03d08 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -33,7 +33,9 @@
 	EM(NETFS_READPAGE,			"RP")		\
 	EM(NETFS_READ_FOR_WRITE,		"RW")		\
 	EM(NETFS_WRITEBACK,			"WB")		\
-	E_(NETFS_DIO_READ,			"DR")
+	EM(NETFS_UNBUFFERED_WRITE,		"UW")		\
+	EM(NETFS_DIO_READ,			"DR")		\
+	E_(NETFS_DIO_WRITE,			"DW")
 
 #define netfs_rreq_traces					\
 	EM(netfs_rreq_trace_assess,		"ASSESS ")	\
diff --git a/mm/filemap.c b/mm/filemap.c
index 1c5271ed0cc0..73626eb323f3 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2706,6 +2706,7 @@ int kiocb_invalidate_pages(struct kiocb *iocb, size_t count)
 	return invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT,
 					     end >> PAGE_SHIFT);
 }
+EXPORT_SYMBOL_GPL(kiocb_invalidate_pages);
 
 /**
  * generic_file_read_iter - generic filesystem read routine
-- 
cgit v1.2.3


From 938e13a73b244278a3777f38fa915bd239b2efd2 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 17 Jun 2021 13:09:21 +0100
Subject: netfs: Implement buffered write API

Institute a netfs write helper, netfs_file_write_iter(), to be pointed at
by the network filesystem ->write_iter() call.  Make it handled buffered
writes by calling the previously defined netfs_perform_write() to copy the
source data into the pagecache.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/buffered_write.c | 83 +++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/netfs.h     |  3 ++
 2 files changed, 86 insertions(+)

(limited to 'include')

diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index b76688e98f81..f244123ab568 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -333,3 +333,86 @@ error_folio_unlock:
 	goto out;
 }
 EXPORT_SYMBOL(netfs_perform_write);
+
+/**
+ * netfs_buffered_write_iter_locked - write data to a file
+ * @iocb:	IO state structure (file, offset, etc.)
+ * @from:	iov_iter with data to write
+ * @netfs_group: Grouping for dirty pages (eg. ceph snaps).
+ *
+ * This function does all the work needed for actually writing data to a
+ * file. It does all basic checks, removes SUID from the file, updates
+ * modification times and calls proper subroutines depending on whether we
+ * do direct IO or a standard buffered write.
+ *
+ * The caller must hold appropriate locks around this function and have called
+ * generic_write_checks() already.  The caller is also responsible for doing
+ * any necessary syncing afterwards.
+ *
+ * This function does *not* take care of syncing data in case of O_SYNC write.
+ * A caller has to handle it. This is mainly due to the fact that we want to
+ * avoid syncing under i_rwsem.
+ *
+ * Return:
+ * * number of bytes written, even for truncated writes
+ * * negative error code if no data has been written at all
+ */
+ssize_t netfs_buffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *from,
+					 struct netfs_group *netfs_group)
+{
+	struct file *file = iocb->ki_filp;
+	ssize_t ret;
+
+	trace_netfs_write_iter(iocb, from);
+
+	ret = file_remove_privs(file);
+	if (ret)
+		return ret;
+
+	ret = file_update_time(file);
+	if (ret)
+		return ret;
+
+	return netfs_perform_write(iocb, from, netfs_group);
+}
+EXPORT_SYMBOL(netfs_buffered_write_iter_locked);
+
+/**
+ * netfs_file_write_iter - write data to a file
+ * @iocb: IO state structure
+ * @from: iov_iter with data to write
+ *
+ * Perform a write to a file, writing into the pagecache if possible and doing
+ * an unbuffered write instead if not.
+ *
+ * Return:
+ * * Negative error code if no data has been written at all of
+ *   vfs_fsync_range() failed for a synchronous write
+ * * Number of bytes written, even for truncated writes
+ */
+ssize_t netfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file->f_mapping->host;
+	struct netfs_inode *ictx = netfs_inode(inode);
+	ssize_t ret;
+
+	_enter("%llx,%zx,%llx", iocb->ki_pos, iov_iter_count(from), i_size_read(inode));
+
+	if ((iocb->ki_flags & IOCB_DIRECT) ||
+	    test_bit(NETFS_ICTX_UNBUFFERED, &ictx->flags))
+		return netfs_unbuffered_write_iter(iocb, from);
+
+	ret = netfs_start_io_write(inode);
+	if (ret < 0)
+		return ret;
+
+	ret = generic_write_checks(iocb, from);
+	if (ret > 0)
+		ret = netfs_buffered_write_iter_locked(iocb, from, NULL);
+	netfs_end_io_write(inode);
+	if (ret > 0)
+		ret = generic_write_sync(iocb, ret);
+	return ret;
+}
+EXPORT_SYMBOL(netfs_file_write_iter);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index e1dfd6775c2c..0948ecf69aa5 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -382,7 +382,10 @@ ssize_t netfs_unbuffered_read_iter(struct kiocb *iocb, struct iov_iter *iter);
 /* High-level write API */
 ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 			    struct netfs_group *netfs_group);
+ssize_t netfs_buffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *from,
+					 struct netfs_group *netfs_group);
 ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from);
+ssize_t netfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from);
 
 /* Address operations API */
 struct readahead_control;
-- 
cgit v1.2.3


From 102a7e2c598c22bd2621fa97eb1c93c89d469a12 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 15 Feb 2022 23:15:57 +0000
Subject: netfs: Allow buffered shared-writeable mmap through
 netfs_page_mkwrite()

Provide an entry point to delegate a filesystem's ->page_mkwrite() to.
This checks for conflicting writes, then attached any netfs-specific group
marking (e.g. ceph snap) to the page to be considered dirty.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/buffered_write.c | 59 +++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/netfs.h     |  4 ++++
 2 files changed, 63 insertions(+)

(limited to 'include')

diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index f244123ab568..70cb8e98d068 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -416,3 +416,62 @@ ssize_t netfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	return ret;
 }
 EXPORT_SYMBOL(netfs_file_write_iter);
+
+/*
+ * Notification that a previously read-only page is about to become writable.
+ * Note that the caller indicates a single page of a multipage folio.
+ */
+vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_group)
+{
+	struct folio *folio = page_folio(vmf->page);
+	struct file *file = vmf->vma->vm_file;
+	struct inode *inode = file_inode(file);
+	vm_fault_t ret = VM_FAULT_RETRY;
+	int err;
+
+	_enter("%lx", folio->index);
+
+	sb_start_pagefault(inode->i_sb);
+
+	if (folio_wait_writeback_killable(folio))
+		goto out;
+
+	if (folio_lock_killable(folio) < 0)
+		goto out;
+
+	/* Can we see a streaming write here? */
+	if (WARN_ON(!folio_test_uptodate(folio))) {
+		ret = VM_FAULT_SIGBUS | VM_FAULT_LOCKED;
+		goto out;
+	}
+
+	if (netfs_folio_group(folio) != netfs_group) {
+		folio_unlock(folio);
+		err = filemap_fdatawait_range(inode->i_mapping,
+					      folio_pos(folio),
+					      folio_pos(folio) + folio_size(folio));
+		switch (err) {
+		case 0:
+			ret = VM_FAULT_RETRY;
+			goto out;
+		case -ENOMEM:
+			ret = VM_FAULT_OOM;
+			goto out;
+		default:
+			ret = VM_FAULT_SIGBUS;
+			goto out;
+		}
+	}
+
+	if (folio_test_dirty(folio))
+		trace_netfs_folio(folio, netfs_folio_trace_mkwrite_plus);
+	else
+		trace_netfs_folio(folio, netfs_folio_trace_mkwrite);
+	netfs_set_group(folio, netfs_group);
+	file_update_time(file);
+	ret = VM_FAULT_LOCKED;
+out:
+	sb_end_pagefault(inode->i_sb);
+	return ret;
+}
+EXPORT_SYMBOL(netfs_page_mkwrite);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 0948ecf69aa5..d7f324c7c22a 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -400,6 +400,10 @@ void netfs_clear_inode_writeback(struct inode *inode, const void *aux);
 void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length);
 bool netfs_release_folio(struct folio *folio, gfp_t gfp);
 
+/* VMA operations API. */
+vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_group);
+
+/* (Sub)request management API. */
 void netfs_subreq_terminated(struct netfs_io_subrequest *, ssize_t, bool);
 void netfs_get_subrequest(struct netfs_io_subrequest *subreq,
 			  enum netfs_sreq_ref_trace what);
-- 
cgit v1.2.3


From 80645bd4aa33a5c325f11b8dc6b38b38410ad5c0 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 11 Oct 2023 09:29:43 +0100
Subject: netfs: Provide netfs_file_read_iter()

Provide a top-level-ish function that can be pointed to directly by
->read_iter file op.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/buffered_read.c | 73 ++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/netfs.h    |  2 ++
 2 files changed, 75 insertions(+)

(limited to 'include')

diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index 950f63fc156a..a59e7b2edaac 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -558,3 +558,76 @@ error:
 	_leave(" = %d", ret);
 	return ret;
 }
+
+/**
+ * netfs_buffered_read_iter - Filesystem buffered I/O read routine
+ * @iocb: kernel I/O control block
+ * @iter: destination for the data read
+ *
+ * This is the ->read_iter() routine for all filesystems that can use the page
+ * cache directly.
+ *
+ * The IOCB_NOWAIT flag in iocb->ki_flags indicates that -EAGAIN shall be
+ * returned when no data can be read without waiting for I/O requests to
+ * complete; it doesn't prevent readahead.
+ *
+ * The IOCB_NOIO flag in iocb->ki_flags indicates that no new I/O requests
+ * shall be made for the read or for readahead.  When no data can be read,
+ * -EAGAIN shall be returned.  When readahead would be triggered, a partial,
+ * possibly empty read shall be returned.
+ *
+ * Return:
+ * * number of bytes copied, even for partial reads
+ * * negative error code (or 0 if IOCB_NOIO) if nothing was read
+ */
+ssize_t netfs_buffered_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	struct netfs_inode *ictx = netfs_inode(inode);
+	ssize_t ret;
+
+	if (WARN_ON_ONCE((iocb->ki_flags & IOCB_DIRECT) ||
+			 test_bit(NETFS_ICTX_UNBUFFERED, &ictx->flags)))
+		return -EINVAL;
+
+	ret = netfs_start_io_read(inode);
+	if (ret == 0) {
+		ret = filemap_read(iocb, iter, 0);
+		netfs_end_io_read(inode);
+	}
+	return ret;
+}
+EXPORT_SYMBOL(netfs_buffered_read_iter);
+
+/**
+ * netfs_file_read_iter - Generic filesystem read routine
+ * @iocb: kernel I/O control block
+ * @iter: destination for the data read
+ *
+ * This is the ->read_iter() routine for all filesystems that can use the page
+ * cache directly.
+ *
+ * The IOCB_NOWAIT flag in iocb->ki_flags indicates that -EAGAIN shall be
+ * returned when no data can be read without waiting for I/O requests to
+ * complete; it doesn't prevent readahead.
+ *
+ * The IOCB_NOIO flag in iocb->ki_flags indicates that no new I/O requests
+ * shall be made for the read or for readahead.  When no data can be read,
+ * -EAGAIN shall be returned.  When readahead would be triggered, a partial,
+ * possibly empty read shall be returned.
+ *
+ * Return:
+ * * number of bytes copied, even for partial reads
+ * * negative error code (or 0 if IOCB_NOIO) if nothing was read
+ */
+ssize_t netfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+	struct netfs_inode *ictx = netfs_inode(iocb->ki_filp->f_mapping->host);
+
+	if ((iocb->ki_flags & IOCB_DIRECT) ||
+	    test_bit(NETFS_ICTX_UNBUFFERED, &ictx->flags))
+		return netfs_unbuffered_read_iter(iocb, iter);
+
+	return netfs_buffered_read_iter(iocb, iter);
+}
+EXPORT_SYMBOL(netfs_file_read_iter);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index d7f324c7c22a..19a41c437af3 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -378,6 +378,8 @@ struct netfs_cache_ops {
 
 /* High-level read API. */
 ssize_t netfs_unbuffered_read_iter(struct kiocb *iocb, struct iov_iter *iter);
+ssize_t netfs_buffered_read_iter(struct kiocb *iocb, struct iov_iter *iter);
+ssize_t netfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter);
 
 /* High-level write API */
 ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
-- 
cgit v1.2.3


From e0ace6ca98bef0d8d354040f13ffc0a498813ee9 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 22 Nov 2023 17:18:17 +0000
Subject: netfs, cachefiles: Pass upper bound length to allow expansion

Make netfslib pass the maximum length to the ->prepare_write() op to tell
the cache how much it can expand the length of a write to.  This allows a
write to the server at the end of a file to be limited to a few bytes
whilst writing an entire block to the cache (something required by direct
I/O).

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/cachefiles/internal.h |  2 +-
 fs/cachefiles/io.c       | 10 ++++++----
 fs/cachefiles/ondemand.c |  2 +-
 fs/netfs/fscache_io.c    |  2 +-
 fs/netfs/io.c            |  2 +-
 fs/netfs/objects.c       |  1 +
 fs/netfs/output.c        | 25 ++++++++++---------------
 fs/smb/client/fscache.c  |  2 +-
 include/linux/netfs.h    |  5 +++--
 9 files changed, 25 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h
index 2ad58c465208..1af48d576a34 100644
--- a/fs/cachefiles/internal.h
+++ b/fs/cachefiles/internal.h
@@ -233,7 +233,7 @@ extern bool cachefiles_begin_operation(struct netfs_cache_resources *cres,
 				       enum fscache_want_state want_state);
 extern int __cachefiles_prepare_write(struct cachefiles_object *object,
 				      struct file *file,
-				      loff_t *_start, size_t *_len,
+				      loff_t *_start, size_t *_len, size_t upper_len,
 				      bool no_space_allocated_yet);
 extern int __cachefiles_write(struct cachefiles_object *object,
 			      struct file *file,
diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c
index 009d23cd435b..bffffedce4a9 100644
--- a/fs/cachefiles/io.c
+++ b/fs/cachefiles/io.c
@@ -518,7 +518,7 @@ cachefiles_prepare_ondemand_read(struct netfs_cache_resources *cres,
  */
 int __cachefiles_prepare_write(struct cachefiles_object *object,
 			       struct file *file,
-			       loff_t *_start, size_t *_len,
+			       loff_t *_start, size_t *_len, size_t upper_len,
 			       bool no_space_allocated_yet)
 {
 	struct cachefiles_cache *cache = object->volume->cache;
@@ -530,6 +530,8 @@ int __cachefiles_prepare_write(struct cachefiles_object *object,
 	down = start - round_down(start, PAGE_SIZE);
 	*_start = start - down;
 	*_len = round_up(down + len, PAGE_SIZE);
+	if (down < start || *_len > upper_len)
+		return -ENOBUFS;
 
 	/* We need to work out whether there's sufficient disk space to perform
 	 * the write - but we can skip that check if we have space already
@@ -592,8 +594,8 @@ check_space:
 }
 
 static int cachefiles_prepare_write(struct netfs_cache_resources *cres,
-				    loff_t *_start, size_t *_len, loff_t i_size,
-				    bool no_space_allocated_yet)
+				    loff_t *_start, size_t *_len, size_t upper_len,
+				    loff_t i_size, bool no_space_allocated_yet)
 {
 	struct cachefiles_object *object = cachefiles_cres_object(cres);
 	struct cachefiles_cache *cache = object->volume->cache;
@@ -609,7 +611,7 @@ static int cachefiles_prepare_write(struct netfs_cache_resources *cres,
 
 	cachefiles_begin_secure(cache, &saved_cred);
 	ret = __cachefiles_prepare_write(object, cachefiles_cres_file(cres),
-					 _start, _len,
+					 _start, _len, upper_len,
 					 no_space_allocated_yet);
 	cachefiles_end_secure(cache, saved_cred);
 	return ret;
diff --git a/fs/cachefiles/ondemand.c b/fs/cachefiles/ondemand.c
index 0254ed39f68c..9301d1eb0504 100644
--- a/fs/cachefiles/ondemand.c
+++ b/fs/cachefiles/ondemand.c
@@ -52,7 +52,7 @@ static ssize_t cachefiles_ondemand_fd_write_iter(struct kiocb *kiocb,
 		return -ENOBUFS;
 
 	cachefiles_begin_secure(cache, &saved_cred);
-	ret = __cachefiles_prepare_write(object, file, &pos, &len, true);
+	ret = __cachefiles_prepare_write(object, file, &pos, &len, len, true);
 	cachefiles_end_secure(cache, saved_cred);
 	if (ret < 0)
 		return ret;
diff --git a/fs/netfs/fscache_io.c b/fs/netfs/fscache_io.c
index 79171a687930..ad572f7ee897 100644
--- a/fs/netfs/fscache_io.c
+++ b/fs/netfs/fscache_io.c
@@ -237,7 +237,7 @@ void __fscache_write_to_cache(struct fscache_cookie *cookie,
 				    fscache_access_io_write) < 0)
 		goto abandon_free;
 
-	ret = cres->ops->prepare_write(cres, &start, &len, i_size, false);
+	ret = cres->ops->prepare_write(cres, &start, &len, len, i_size, false);
 	if (ret < 0)
 		goto abandon_end;
 
diff --git a/fs/netfs/io.c b/fs/netfs/io.c
index 01c7ff27228e..14c18be5aca0 100644
--- a/fs/netfs/io.c
+++ b/fs/netfs/io.c
@@ -199,7 +199,7 @@ static void netfs_rreq_do_write_to_cache(struct netfs_io_request *rreq)
 		}
 
 		ret = cres->ops->prepare_write(cres, &subreq->start, &subreq->len,
-					       rreq->i_size, true);
+					       subreq->len, rreq->i_size, true);
 		if (ret < 0) {
 			trace_netfs_failure(rreq, subreq, ret, netfs_fail_prepare_write);
 			trace_netfs_sreq(subreq, netfs_sreq_trace_write_skip);
diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c
index 93f1d7431199..b4e3bd836e5d 100644
--- a/fs/netfs/objects.c
+++ b/fs/netfs/objects.c
@@ -33,6 +33,7 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
 
 	rreq->start	= start;
 	rreq->len	= len;
+	rreq->upper_len	= len;
 	rreq->origin	= origin;
 	rreq->netfs_ops	= ctx->ops;
 	rreq->mapping	= mapping;
diff --git a/fs/netfs/output.c b/fs/netfs/output.c
index 560cbcea0c0a..cc9065733b42 100644
--- a/fs/netfs/output.c
+++ b/fs/netfs/output.c
@@ -280,7 +280,7 @@ EXPORT_SYMBOL(netfs_queue_write_request);
  */
 static void netfs_set_up_write_to_cache(struct netfs_io_request *wreq)
 {
-	struct netfs_cache_resources *cres;
+	struct netfs_cache_resources *cres = &wreq->cache_resources;
 	struct netfs_io_subrequest *subreq;
 	struct netfs_inode *ctx = netfs_inode(wreq->inode);
 	struct fscache_cookie *cookie = netfs_i_cookie(ctx);
@@ -294,26 +294,21 @@ static void netfs_set_up_write_to_cache(struct netfs_io_request *wreq)
 	}
 
 	_debug("write to cache");
-	subreq = netfs_create_write_request(wreq, NETFS_WRITE_TO_CACHE, start, len,
-					    netfs_write_to_cache_op_worker);
-	if (!subreq)
+	ret = fscache_begin_write_operation(cres, cookie);
+	if (ret < 0)
 		return;
 
-	cres = &wreq->cache_resources;
-	ret = fscache_begin_read_operation(cres, cookie);
-	if (ret < 0) {
-		netfs_write_subrequest_terminated(subreq, ret, false);
+	ret = cres->ops->prepare_write(cres, &start, &len, wreq->upper_len,
+				       i_size_read(wreq->inode), true);
+	if (ret < 0)
 		return;
-	}
 
-	ret = cres->ops->prepare_write(cres, &start, &len, i_size_read(wreq->inode),
-				       true);
-	if (ret < 0) {
-		netfs_write_subrequest_terminated(subreq, ret, false);
+	subreq = netfs_create_write_request(wreq, NETFS_WRITE_TO_CACHE, start, len,
+					    netfs_write_to_cache_op_worker);
+	if (!subreq)
 		return;
-	}
 
-	netfs_queue_write_request(subreq);
+	netfs_write_to_cache_op(subreq);
 }
 
 /*
diff --git a/fs/smb/client/fscache.c b/fs/smb/client/fscache.c
index e5cad149f5a2..c4a3cb736881 100644
--- a/fs/smb/client/fscache.c
+++ b/fs/smb/client/fscache.c
@@ -180,7 +180,7 @@ static int fscache_fallback_write_pages(struct inode *inode, loff_t start, size_
 	if (ret < 0)
 		return ret;
 
-	ret = cres.ops->prepare_write(&cres, &start, &len, i_size_read(inode),
+	ret = cres.ops->prepare_write(&cres, &start, &len, len, i_size_read(inode),
 				      no_space_allocated_yet);
 	if (ret == 0)
 		ret = fscache_write(&cres, start, &iter, NULL, NULL);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 19a41c437af3..2856389f4694 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -261,6 +261,7 @@ struct netfs_io_request {
 	atomic_t		nr_copy_ops;	/* Number of copy-to-cache ops in progress */
 	size_t			submitted;	/* Amount submitted for I/O so far */
 	size_t			len;		/* Length of the request */
+	size_t			upper_len;	/* Length can be extended to here */
 	size_t			transferred;	/* Amount to be indicated as transferred */
 	short			error;		/* 0 or error that occurred */
 	enum netfs_io_origin	origin;		/* Origin of the request */
@@ -357,8 +358,8 @@ struct netfs_cache_ops {
 	 * actually do.
 	 */
 	int (*prepare_write)(struct netfs_cache_resources *cres,
-			     loff_t *_start, size_t *_len, loff_t i_size,
-			     bool no_space_allocated_yet);
+			     loff_t *_start, size_t *_len, size_t upper_len,
+			     loff_t i_size, bool no_space_allocated_yet);
 
 	/* Prepare an on-demand read operation, shortening it to a cached/uncached
 	 * boundary as appropriate.
-- 
cgit v1.2.3


From 62c3b7481b9a108cb99ef9438dba66bb4738768b Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 28 Sep 2023 11:46:49 +0100
Subject: netfs: Provide a writepages implementation

Provide an implementation of writepages for network filesystems to delegate
to.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/buffered_write.c | 636 ++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/netfs.h     |   2 +
 2 files changed, 638 insertions(+)

(limited to 'include')

diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index 70cb8e98d068..c078826f7fe6 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -32,6 +32,18 @@ static void netfs_set_group(struct folio *folio, struct netfs_group *netfs_group
 		folio_attach_private(folio, netfs_get_group(netfs_group));
 }
 
+#if IS_ENABLED(CONFIG_FSCACHE)
+static void netfs_folio_start_fscache(bool caching, struct folio *folio)
+{
+	if (caching)
+		folio_start_fscache(folio);
+}
+#else
+static void netfs_folio_start_fscache(bool caching, struct folio *folio)
+{
+}
+#endif
+
 /*
  * Decide how we should modify a folio.  We might be attempting to do
  * write-streaming, in which case we don't want to a local RMW cycle if we can
@@ -475,3 +487,627 @@ out:
 	return ret;
 }
 EXPORT_SYMBOL(netfs_page_mkwrite);
+
+/*
+ * Kill all the pages in the given range
+ */
+static void netfs_kill_pages(struct address_space *mapping,
+			     loff_t start, loff_t len)
+{
+	struct folio *folio;
+	pgoff_t index = start / PAGE_SIZE;
+	pgoff_t last = (start + len - 1) / PAGE_SIZE, next;
+
+	_enter("%llx-%llx", start, start + len - 1);
+
+	do {
+		_debug("kill %lx (to %lx)", index, last);
+
+		folio = filemap_get_folio(mapping, index);
+		if (IS_ERR(folio)) {
+			next = index + 1;
+			continue;
+		}
+
+		next = folio_next_index(folio);
+
+		trace_netfs_folio(folio, netfs_folio_trace_kill);
+		folio_clear_uptodate(folio);
+		if (folio_test_fscache(folio))
+			folio_end_fscache(folio);
+		folio_end_writeback(folio);
+		folio_lock(folio);
+		generic_error_remove_page(mapping, &folio->page);
+		folio_unlock(folio);
+		folio_put(folio);
+
+	} while (index = next, index <= last);
+
+	_leave("");
+}
+
+/*
+ * Redirty all the pages in a given range.
+ */
+static void netfs_redirty_pages(struct address_space *mapping,
+				loff_t start, loff_t len)
+{
+	struct folio *folio;
+	pgoff_t index = start / PAGE_SIZE;
+	pgoff_t last = (start + len - 1) / PAGE_SIZE, next;
+
+	_enter("%llx-%llx", start, start + len - 1);
+
+	do {
+		_debug("redirty %llx @%llx", len, start);
+
+		folio = filemap_get_folio(mapping, index);
+		if (IS_ERR(folio)) {
+			next = index + 1;
+			continue;
+		}
+
+		next = folio_next_index(folio);
+		trace_netfs_folio(folio, netfs_folio_trace_redirty);
+		filemap_dirty_folio(mapping, folio);
+		if (folio_test_fscache(folio))
+			folio_end_fscache(folio);
+		folio_end_writeback(folio);
+		folio_put(folio);
+	} while (index = next, index <= last);
+
+	balance_dirty_pages_ratelimited(mapping);
+
+	_leave("");
+}
+
+/*
+ * Completion of write to server
+ */
+static void netfs_pages_written_back(struct netfs_io_request *wreq)
+{
+	struct address_space *mapping = wreq->mapping;
+	struct netfs_folio *finfo;
+	struct netfs_group *group = NULL;
+	struct folio *folio;
+	pgoff_t last;
+	int gcount = 0;
+
+	XA_STATE(xas, &mapping->i_pages, wreq->start / PAGE_SIZE);
+
+	_enter("%llx-%llx", wreq->start, wreq->start + wreq->len);
+
+	rcu_read_lock();
+
+	last = (wreq->start + wreq->len - 1) / PAGE_SIZE;
+	xas_for_each(&xas, folio, last) {
+		WARN(!folio_test_writeback(folio),
+		     "bad %zx @%llx page %lx %lx\n",
+		     wreq->len, wreq->start, folio_index(folio), last);
+
+		if ((finfo = netfs_folio_info(folio))) {
+			/* Streaming writes cannot be redirtied whilst under
+			 * writeback, so discard the streaming record.
+			 */
+			folio_detach_private(folio);
+			group = finfo->netfs_group;
+			gcount++;
+			trace_netfs_folio(folio, netfs_folio_trace_clear_s);
+			kfree(finfo);
+		} else if ((group = netfs_folio_group(folio))) {
+			/* Need to detach the group pointer if the page didn't
+			 * get redirtied.  If it has been redirtied, then it
+			 * must be within the same group.
+			 */
+			if (folio_test_dirty(folio)) {
+				trace_netfs_folio(folio, netfs_folio_trace_redirtied);
+				goto end_wb;
+			}
+			if (folio_trylock(folio)) {
+				if (!folio_test_dirty(folio)) {
+					folio_detach_private(folio);
+					gcount++;
+					trace_netfs_folio(folio, netfs_folio_trace_clear_g);
+				} else {
+					trace_netfs_folio(folio, netfs_folio_trace_redirtied);
+				}
+				folio_unlock(folio);
+				goto end_wb;
+			}
+
+			xas_pause(&xas);
+			rcu_read_unlock();
+			folio_lock(folio);
+			if (!folio_test_dirty(folio)) {
+				folio_detach_private(folio);
+				gcount++;
+				trace_netfs_folio(folio, netfs_folio_trace_clear_g);
+			} else {
+				trace_netfs_folio(folio, netfs_folio_trace_redirtied);
+			}
+			folio_unlock(folio);
+			rcu_read_lock();
+		} else {
+			trace_netfs_folio(folio, netfs_folio_trace_clear);
+		}
+	end_wb:
+		if (folio_test_fscache(folio))
+			folio_end_fscache(folio);
+		folio_end_writeback(folio);
+	}
+
+	rcu_read_unlock();
+	netfs_put_group_many(group, gcount);
+	_leave("");
+}
+
+/*
+ * Deal with the disposition of the folios that are under writeback to close
+ * out the operation.
+ */
+static void netfs_cleanup_buffered_write(struct netfs_io_request *wreq)
+{
+	struct address_space *mapping = wreq->mapping;
+
+	_enter("");
+
+	switch (wreq->error) {
+	case 0:
+		netfs_pages_written_back(wreq);
+		break;
+
+	default:
+		pr_notice("R=%08x Unexpected error %d\n", wreq->debug_id, wreq->error);
+		fallthrough;
+	case -EACCES:
+	case -EPERM:
+	case -ENOKEY:
+	case -EKEYEXPIRED:
+	case -EKEYREJECTED:
+	case -EKEYREVOKED:
+	case -ENETRESET:
+	case -EDQUOT:
+	case -ENOSPC:
+		netfs_redirty_pages(mapping, wreq->start, wreq->len);
+		break;
+
+	case -EROFS:
+	case -EIO:
+	case -EREMOTEIO:
+	case -EFBIG:
+	case -ENOENT:
+	case -ENOMEDIUM:
+	case -ENXIO:
+		netfs_kill_pages(mapping, wreq->start, wreq->len);
+		break;
+	}
+
+	if (wreq->error)
+		mapping_set_error(mapping, wreq->error);
+	if (wreq->netfs_ops->done)
+		wreq->netfs_ops->done(wreq);
+}
+
+/*
+ * Extend the region to be written back to include subsequent contiguously
+ * dirty pages if possible, but don't sleep while doing so.
+ *
+ * If this page holds new content, then we can include filler zeros in the
+ * writeback.
+ */
+static void netfs_extend_writeback(struct address_space *mapping,
+				   struct netfs_group *group,
+				   struct xa_state *xas,
+				   long *_count,
+				   loff_t start,
+				   loff_t max_len,
+				   bool caching,
+				   size_t *_len,
+				   size_t *_top)
+{
+	struct netfs_folio *finfo;
+	struct folio_batch fbatch;
+	struct folio *folio;
+	unsigned int i;
+	pgoff_t index = (start + *_len) / PAGE_SIZE;
+	size_t len;
+	void *priv;
+	bool stop = true;
+
+	folio_batch_init(&fbatch);
+
+	do {
+		/* Firstly, we gather up a batch of contiguous dirty pages
+		 * under the RCU read lock - but we can't clear the dirty flags
+		 * there if any of those pages are mapped.
+		 */
+		rcu_read_lock();
+
+		xas_for_each(xas, folio, ULONG_MAX) {
+			stop = true;
+			if (xas_retry(xas, folio))
+				continue;
+			if (xa_is_value(folio))
+				break;
+			if (folio_index(folio) != index) {
+				xas_reset(xas);
+				break;
+			}
+
+			if (!folio_try_get_rcu(folio)) {
+				xas_reset(xas);
+				continue;
+			}
+
+			/* Has the folio moved or been split? */
+			if (unlikely(folio != xas_reload(xas))) {
+				folio_put(folio);
+				xas_reset(xas);
+				break;
+			}
+
+			if (!folio_trylock(folio)) {
+				folio_put(folio);
+				xas_reset(xas);
+				break;
+			}
+			if (!folio_test_dirty(folio) ||
+			    folio_test_writeback(folio) ||
+			    folio_test_fscache(folio)) {
+				folio_unlock(folio);
+				folio_put(folio);
+				xas_reset(xas);
+				break;
+			}
+
+			stop = false;
+			len = folio_size(folio);
+			priv = folio_get_private(folio);
+			if ((const struct netfs_group *)priv != group) {
+				stop = true;
+				finfo = netfs_folio_info(folio);
+				if (finfo->netfs_group != group ||
+				    finfo->dirty_offset > 0) {
+					folio_unlock(folio);
+					folio_put(folio);
+					xas_reset(xas);
+					break;
+				}
+				len = finfo->dirty_len;
+			}
+
+			*_top += folio_size(folio);
+			index += folio_nr_pages(folio);
+			*_count -= folio_nr_pages(folio);
+			*_len += len;
+			if (*_len >= max_len || *_count <= 0)
+				stop = true;
+
+			if (!folio_batch_add(&fbatch, folio))
+				break;
+			if (stop)
+				break;
+		}
+
+		xas_pause(xas);
+		rcu_read_unlock();
+
+		/* Now, if we obtained any folios, we can shift them to being
+		 * writable and mark them for caching.
+		 */
+		if (!folio_batch_count(&fbatch))
+			break;
+
+		for (i = 0; i < folio_batch_count(&fbatch); i++) {
+			folio = fbatch.folios[i];
+			trace_netfs_folio(folio, netfs_folio_trace_store_plus);
+
+			if (!folio_clear_dirty_for_io(folio))
+				BUG();
+			folio_start_writeback(folio);
+			netfs_folio_start_fscache(caching, folio);
+			folio_unlock(folio);
+		}
+
+		folio_batch_release(&fbatch);
+		cond_resched();
+	} while (!stop);
+}
+
+/*
+ * Synchronously write back the locked page and any subsequent non-locked dirty
+ * pages.
+ */
+static ssize_t netfs_write_back_from_locked_folio(struct address_space *mapping,
+						  struct writeback_control *wbc,
+						  struct netfs_group *group,
+						  struct xa_state *xas,
+						  struct folio *folio,
+						  unsigned long long start,
+						  unsigned long long end)
+{
+	struct netfs_io_request *wreq;
+	struct netfs_folio *finfo;
+	struct netfs_inode *ctx = netfs_inode(mapping->host);
+	unsigned long long i_size = i_size_read(&ctx->inode);
+	size_t len, max_len;
+	bool caching = netfs_is_cache_enabled(ctx);
+	long count = wbc->nr_to_write;
+	int ret;
+
+	_enter(",%lx,%llx-%llx,%u", folio_index(folio), start, end, caching);
+
+	wreq = netfs_alloc_request(mapping, NULL, start, folio_size(folio),
+				   NETFS_WRITEBACK);
+	if (IS_ERR(wreq)) {
+		folio_unlock(folio);
+		return PTR_ERR(wreq);
+	}
+
+	if (!folio_clear_dirty_for_io(folio))
+		BUG();
+	folio_start_writeback(folio);
+	netfs_folio_start_fscache(caching, folio);
+
+	count -= folio_nr_pages(folio);
+
+	/* Find all consecutive lockable dirty pages that have contiguous
+	 * written regions, stopping when we find a page that is not
+	 * immediately lockable, is not dirty or is missing, or we reach the
+	 * end of the range.
+	 */
+	trace_netfs_folio(folio, netfs_folio_trace_store);
+
+	len = wreq->len;
+	finfo = netfs_folio_info(folio);
+	if (finfo) {
+		start += finfo->dirty_offset;
+		if (finfo->dirty_offset + finfo->dirty_len != len) {
+			len = finfo->dirty_len;
+			goto cant_expand;
+		}
+		len = finfo->dirty_len;
+	}
+
+	if (start < i_size) {
+		/* Trim the write to the EOF; the extra data is ignored.  Also
+		 * put an upper limit on the size of a single storedata op.
+		 */
+		max_len = 65536 * 4096;
+		max_len = min_t(unsigned long long, max_len, end - start + 1);
+		max_len = min_t(unsigned long long, max_len, i_size - start);
+
+		if (len < max_len)
+			netfs_extend_writeback(mapping, group, xas, &count, start,
+					       max_len, caching, &len, &wreq->upper_len);
+	}
+
+cant_expand:
+	len = min_t(unsigned long long, len, i_size - start);
+
+	/* We now have a contiguous set of dirty pages, each with writeback
+	 * set; the first page is still locked at this point, but all the rest
+	 * have been unlocked.
+	 */
+	folio_unlock(folio);
+	wreq->start = start;
+	wreq->len = len;
+
+	if (start < i_size) {
+		_debug("write back %zx @%llx [%llx]", len, start, i_size);
+
+		/* Speculatively write to the cache.  We have to fix this up
+		 * later if the store fails.
+		 */
+		wreq->cleanup = netfs_cleanup_buffered_write;
+
+		iov_iter_xarray(&wreq->iter, ITER_SOURCE, &mapping->i_pages, start,
+				wreq->upper_len);
+		__set_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags);
+		ret = netfs_begin_write(wreq, true, netfs_write_trace_writeback);
+		if (ret == 0 || ret == -EIOCBQUEUED)
+			wbc->nr_to_write -= len / PAGE_SIZE;
+	} else {
+		_debug("write discard %zx @%llx [%llx]", len, start, i_size);
+
+		/* The dirty region was entirely beyond the EOF. */
+		fscache_clear_page_bits(mapping, start, len, caching);
+		netfs_pages_written_back(wreq);
+		ret = 0;
+	}
+
+	netfs_put_request(wreq, false, netfs_rreq_trace_put_return);
+	_leave(" = 1");
+	return 1;
+}
+
+/*
+ * Write a region of pages back to the server
+ */
+static ssize_t netfs_writepages_begin(struct address_space *mapping,
+				      struct writeback_control *wbc,
+				      struct netfs_group *group,
+				      struct xa_state *xas,
+				      unsigned long long *_start,
+				      unsigned long long end)
+{
+	const struct netfs_folio *finfo;
+	struct folio *folio;
+	unsigned long long start = *_start;
+	ssize_t ret;
+	void *priv;
+	int skips = 0;
+
+	_enter("%llx,%llx,", start, end);
+
+search_again:
+	/* Find the first dirty page in the group. */
+	rcu_read_lock();
+
+	for (;;) {
+		folio = xas_find_marked(xas, end / PAGE_SIZE, PAGECACHE_TAG_DIRTY);
+		if (xas_retry(xas, folio) || xa_is_value(folio))
+			continue;
+		if (!folio)
+			break;
+
+		if (!folio_try_get_rcu(folio)) {
+			xas_reset(xas);
+			continue;
+		}
+
+		if (unlikely(folio != xas_reload(xas))) {
+			folio_put(folio);
+			xas_reset(xas);
+			continue;
+		}
+
+		/* Skip any dirty folio that's not in the group of interest. */
+		priv = folio_get_private(folio);
+		if ((const struct netfs_group *)priv != group) {
+			finfo = netfs_folio_info(folio);
+			if (finfo->netfs_group != group) {
+				folio_put(folio);
+				continue;
+			}
+		}
+
+		xas_pause(xas);
+		break;
+	}
+	rcu_read_unlock();
+	if (!folio)
+		return 0;
+
+	start = folio_pos(folio); /* May regress with THPs */
+
+	_debug("wback %lx", folio_index(folio));
+
+	/* At this point we hold neither the i_pages lock nor the page lock:
+	 * the page may be truncated or invalidated (changing page->mapping to
+	 * NULL), or even swizzled back from swapper_space to tmpfs file
+	 * mapping
+	 */
+lock_again:
+	if (wbc->sync_mode != WB_SYNC_NONE) {
+		ret = folio_lock_killable(folio);
+		if (ret < 0)
+			return ret;
+	} else {
+		if (!folio_trylock(folio))
+			goto search_again;
+	}
+
+	if (folio->mapping != mapping ||
+	    !folio_test_dirty(folio)) {
+		start += folio_size(folio);
+		folio_unlock(folio);
+		goto search_again;
+	}
+
+	if (folio_test_writeback(folio) ||
+	    folio_test_fscache(folio)) {
+		folio_unlock(folio);
+		if (wbc->sync_mode != WB_SYNC_NONE) {
+			folio_wait_writeback(folio);
+#ifdef CONFIG_NETFS_FSCACHE
+			folio_wait_fscache(folio);
+#endif
+			goto lock_again;
+		}
+
+		start += folio_size(folio);
+		if (wbc->sync_mode == WB_SYNC_NONE) {
+			if (skips >= 5 || need_resched()) {
+				ret = 0;
+				goto out;
+			}
+			skips++;
+		}
+		goto search_again;
+	}
+
+	ret = netfs_write_back_from_locked_folio(mapping, wbc, group, xas,
+						 folio, start, end);
+out:
+	if (ret > 0)
+		*_start = start + ret;
+	_leave(" = %zd [%llx]", ret, *_start);
+	return ret;
+}
+
+/*
+ * Write a region of pages back to the server
+ */
+static int netfs_writepages_region(struct address_space *mapping,
+				   struct writeback_control *wbc,
+				   struct netfs_group *group,
+				   unsigned long long *_start,
+				   unsigned long long end)
+{
+	ssize_t ret;
+
+	XA_STATE(xas, &mapping->i_pages, *_start / PAGE_SIZE);
+
+	do {
+		ret = netfs_writepages_begin(mapping, wbc, group, &xas,
+					     _start, end);
+		if (ret > 0 && wbc->nr_to_write > 0)
+			cond_resched();
+	} while (ret > 0 && wbc->nr_to_write > 0);
+
+	return ret > 0 ? 0 : ret;
+}
+
+/*
+ * write some of the pending data back to the server
+ */
+int netfs_writepages(struct address_space *mapping,
+		     struct writeback_control *wbc)
+{
+	struct netfs_group *group = NULL;
+	loff_t start, end;
+	int ret;
+
+	_enter("");
+
+	/* We have to be careful as we can end up racing with setattr()
+	 * truncating the pagecache since the caller doesn't take a lock here
+	 * to prevent it.
+	 */
+
+	if (wbc->range_cyclic && mapping->writeback_index) {
+		start = mapping->writeback_index * PAGE_SIZE;
+		ret = netfs_writepages_region(mapping, wbc, group,
+					      &start, LLONG_MAX);
+		if (ret < 0)
+			goto out;
+
+		if (wbc->nr_to_write <= 0) {
+			mapping->writeback_index = start / PAGE_SIZE;
+			goto out;
+		}
+
+		start = 0;
+		end = mapping->writeback_index * PAGE_SIZE;
+		mapping->writeback_index = 0;
+		ret = netfs_writepages_region(mapping, wbc, group, &start, end);
+		if (ret == 0)
+			mapping->writeback_index = start / PAGE_SIZE;
+	} else if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) {
+		start = 0;
+		ret = netfs_writepages_region(mapping, wbc, group,
+					      &start, LLONG_MAX);
+		if (wbc->nr_to_write > 0 && ret == 0)
+			mapping->writeback_index = start / PAGE_SIZE;
+	} else {
+		start = wbc->range_start;
+		ret = netfs_writepages_region(mapping, wbc, group,
+					      &start, wbc->range_end);
+	}
+
+out:
+	_leave(" = %d", ret);
+	return ret;
+}
+EXPORT_SYMBOL(netfs_writepages);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 2856389f4694..86bb8cb7f8d0 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -397,6 +397,8 @@ int netfs_read_folio(struct file *, struct folio *);
 int netfs_write_begin(struct netfs_inode *, struct file *,
 		      struct address_space *, loff_t pos, unsigned int len,
 		      struct folio **, void **fsdata);
+int netfs_writepages(struct address_space *mapping,
+		     struct writeback_control *wbc);
 bool netfs_dirty_folio(struct address_space *mapping, struct folio *folio);
 int netfs_unpin_writeback(struct inode *inode, struct writeback_control *wbc);
 void netfs_clear_inode_writeback(struct inode *inode, const void *aux);
-- 
cgit v1.2.3


From 4a79616cfb27d76947ea37f0336745ef929d56be Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 5 Oct 2023 16:52:58 +0100
Subject: netfs: Provide a launder_folio implementation

Provide a launder_folio implementation for netfslib.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/buffered_write.c    | 74 ++++++++++++++++++++++++++++++++++++++++++++
 fs/netfs/main.c              |  1 +
 include/linux/netfs.h        |  2 ++
 include/trace/events/netfs.h |  3 ++
 4 files changed, 80 insertions(+)

(limited to 'include')

diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index c078826f7fe6..50be8fe3ca43 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -1111,3 +1111,77 @@ out:
 	return ret;
 }
 EXPORT_SYMBOL(netfs_writepages);
+
+/*
+ * Deal with the disposition of a laundered folio.
+ */
+static void netfs_cleanup_launder_folio(struct netfs_io_request *wreq)
+{
+	if (wreq->error) {
+		pr_notice("R=%08x Laundering error %d\n", wreq->debug_id, wreq->error);
+		mapping_set_error(wreq->mapping, wreq->error);
+	}
+}
+
+/**
+ * netfs_launder_folio - Clean up a dirty folio that's being invalidated
+ * @folio: The folio to clean
+ *
+ * This is called to write back a folio that's being invalidated when an inode
+ * is getting torn down.  Ideally, writepages would be used instead.
+ */
+int netfs_launder_folio(struct folio *folio)
+{
+	struct netfs_io_request *wreq;
+	struct address_space *mapping = folio->mapping;
+	struct netfs_folio *finfo = netfs_folio_info(folio);
+	struct netfs_group *group = netfs_folio_group(folio);
+	struct bio_vec bvec;
+	unsigned long long i_size = i_size_read(mapping->host);
+	unsigned long long start = folio_pos(folio);
+	size_t offset = 0, len;
+	int ret = 0;
+
+	if (finfo) {
+		offset = finfo->dirty_offset;
+		start += offset;
+		len = finfo->dirty_len;
+	} else {
+		len = folio_size(folio);
+	}
+	len = min_t(unsigned long long, len, i_size - start);
+
+	wreq = netfs_alloc_request(mapping, NULL, start, len, NETFS_LAUNDER_WRITE);
+	if (IS_ERR(wreq)) {
+		ret = PTR_ERR(wreq);
+		goto out;
+	}
+
+	if (!folio_clear_dirty_for_io(folio))
+		goto out_put;
+
+	trace_netfs_folio(folio, netfs_folio_trace_launder);
+
+	_debug("launder %llx-%llx", start, start + len - 1);
+
+	/* Speculatively write to the cache.  We have to fix this up later if
+	 * the store fails.
+	 */
+	wreq->cleanup = netfs_cleanup_launder_folio;
+
+	bvec_set_folio(&bvec, folio, len, offset);
+	iov_iter_bvec(&wreq->iter, ITER_SOURCE, &bvec, 1, len);
+	__set_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags);
+	ret = netfs_begin_write(wreq, true, netfs_write_trace_launder);
+
+out_put:
+	folio_detach_private(folio);
+	netfs_put_group(group);
+	kfree(finfo);
+	netfs_put_request(wreq, false, netfs_rreq_trace_put_return);
+out:
+	folio_wait_fscache(folio);
+	_leave(" = %d", ret);
+	return ret;
+}
+EXPORT_SYMBOL(netfs_launder_folio);
diff --git a/fs/netfs/main.c b/fs/netfs/main.c
index 8e4db9ff40c4..473f889e1bd1 100644
--- a/fs/netfs/main.c
+++ b/fs/netfs/main.c
@@ -30,6 +30,7 @@ static const char *netfs_origins[nr__netfs_io_origin] = {
 	[NETFS_READPAGE]		= "RP",
 	[NETFS_READ_FOR_WRITE]		= "RW",
 	[NETFS_WRITEBACK]		= "WB",
+	[NETFS_LAUNDER_WRITE]		= "LW",
 	[NETFS_UNBUFFERED_WRITE]	= "UW",
 	[NETFS_DIO_READ]		= "DR",
 	[NETFS_DIO_WRITE]		= "DW",
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 86bb8cb7f8d0..29c66acad925 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -227,6 +227,7 @@ enum netfs_io_origin {
 	NETFS_READPAGE,			/* This read is a synchronous read */
 	NETFS_READ_FOR_WRITE,		/* This read is to prepare a write */
 	NETFS_WRITEBACK,		/* This write was triggered by writepages */
+	NETFS_LAUNDER_WRITE,		/* This is triggered by ->launder_folio() */
 	NETFS_UNBUFFERED_WRITE,		/* This is an unbuffered write */
 	NETFS_DIO_READ,			/* This is a direct I/O read */
 	NETFS_DIO_WRITE,		/* This is a direct I/O write */
@@ -404,6 +405,7 @@ int netfs_unpin_writeback(struct inode *inode, struct writeback_control *wbc);
 void netfs_clear_inode_writeback(struct inode *inode, const void *aux);
 void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length);
 bool netfs_release_folio(struct folio *folio, gfp_t gfp);
+int netfs_launder_folio(struct folio *folio);
 
 /* VMA operations API. */
 vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_group);
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index 914a24b03d08..cc998798e20a 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -25,6 +25,7 @@
 
 #define netfs_write_traces					\
 	EM(netfs_write_trace_dio_write,		"DIO-WRITE")	\
+	EM(netfs_write_trace_launder,		"LAUNDER  ")	\
 	EM(netfs_write_trace_unbuffered_write,	"UNB-WRITE")	\
 	E_(netfs_write_trace_writeback,		"WRITEBACK")
 
@@ -33,6 +34,7 @@
 	EM(NETFS_READPAGE,			"RP")		\
 	EM(NETFS_READ_FOR_WRITE,		"RW")		\
 	EM(NETFS_WRITEBACK,			"WB")		\
+	EM(NETFS_LAUNDER_WRITE,			"LW")		\
 	EM(NETFS_UNBUFFERED_WRITE,		"UW")		\
 	EM(NETFS_DIO_READ,			"DR")		\
 	E_(NETFS_DIO_WRITE,			"DW")
@@ -127,6 +129,7 @@
 	EM(netfs_folio_trace_end_copy,		"end-copy")	\
 	EM(netfs_folio_trace_filled_gaps,	"filled-gaps")	\
 	EM(netfs_folio_trace_kill,		"kill")		\
+	EM(netfs_folio_trace_launder,		"launder")	\
 	EM(netfs_folio_trace_mkwrite,		"mkwrite")	\
 	EM(netfs_folio_trace_mkwrite_plus,	"mkwrite+")	\
 	EM(netfs_folio_trace_read_gaps,		"read-gaps")	\
-- 
cgit v1.2.3


From 41d8e7673a7726cba57cb8112d81c89cfb6c3e35 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 12 Oct 2023 09:06:24 +0100
Subject: netfs: Implement a write-through caching option

Provide a flag whereby a filesystem may request that cifs_perform_write()
perform write-through caching.  This involves putting pages directly into
writeback rather than dirty and attaching them to a write operation as we
go.

Further, the writes being made are limited to the byte range being written
rather than whole folios being written.  This can be used by cifs, for
example, to deal with strict byte-range locking.

This can't be used with content encryption as that may require expansion of
the write RPC beyond the write being made.

This doesn't affect writes via mmap - those are written back in the normal
way; similarly failed writethrough writes are marked dirty and left to
writeback to retry.  Another option would be to simply invalidate them, but
the contents can be simultaneously accessed by read() and through mmap.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/buffered_write.c    | 69 ++++++++++++++++++++++++++++-----
 fs/netfs/internal.h          |  3 ++
 fs/netfs/main.c              |  1 +
 fs/netfs/objects.c           |  1 +
 fs/netfs/output.c            | 90 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/netfs.h        |  2 +
 include/trace/events/netfs.h |  8 +++-
 7 files changed, 162 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index 50be8fe3ca43..6ca6c4bde5eb 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -26,6 +26,8 @@ enum netfs_how_to_modify {
 	NETFS_FLUSH_CONTENT,		/* Flush incompatible content. */
 };
 
+static void netfs_cleanup_buffered_write(struct netfs_io_request *wreq);
+
 static void netfs_set_group(struct folio *folio, struct netfs_group *netfs_group)
 {
 	if (netfs_group && !folio_get_private(folio))
@@ -133,6 +135,14 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 	struct inode *inode = file_inode(file);
 	struct address_space *mapping = inode->i_mapping;
 	struct netfs_inode *ctx = netfs_inode(inode);
+	struct writeback_control wbc = {
+		.sync_mode	= WB_SYNC_NONE,
+		.for_sync	= true,
+		.nr_to_write	= LONG_MAX,
+		.range_start	= iocb->ki_pos,
+		.range_end	= iocb->ki_pos + iter->count,
+	};
+	struct netfs_io_request *wreq = NULL;
 	struct netfs_folio *finfo;
 	struct folio *folio;
 	enum netfs_how_to_modify howto;
@@ -143,6 +153,30 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 	size_t max_chunk = PAGE_SIZE << MAX_PAGECACHE_ORDER;
 	bool maybe_trouble = false;
 
+	if (unlikely(test_bit(NETFS_ICTX_WRITETHROUGH, &ctx->flags) ||
+		     iocb->ki_flags & (IOCB_DSYNC | IOCB_SYNC))
+	    ) {
+		if (pos < i_size_read(inode)) {
+			ret = filemap_write_and_wait_range(mapping, pos, pos + iter->count);
+			if (ret < 0) {
+				goto out;
+			}
+		}
+
+		wbc_attach_fdatawrite_inode(&wbc, mapping->host);
+
+		wreq = netfs_begin_writethrough(iocb, iter->count);
+		if (IS_ERR(wreq)) {
+			wbc_detach_inode(&wbc);
+			ret = PTR_ERR(wreq);
+			wreq = NULL;
+			goto out;
+		}
+		if (!is_sync_kiocb(iocb))
+			wreq->iocb = iocb;
+		wreq->cleanup = netfs_cleanup_buffered_write;
+	}
+
 	do {
 		size_t flen;
 		size_t offset;	/* Offset into pagecache folio */
@@ -315,7 +349,25 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 		}
 		written += copied;
 
-		folio_mark_dirty(folio);
+		if (likely(!wreq)) {
+			folio_mark_dirty(folio);
+		} else {
+			if (folio_test_dirty(folio))
+				/* Sigh.  mmap. */
+				folio_clear_dirty_for_io(folio);
+			/* We make multiple writes to the folio... */
+			if (!folio_test_writeback(folio)) {
+				folio_wait_fscache(folio);
+				folio_start_writeback(folio);
+				folio_start_fscache(folio);
+				if (wreq->iter.count == 0)
+					trace_netfs_folio(folio, netfs_folio_trace_wthru);
+				else
+					trace_netfs_folio(folio, netfs_folio_trace_wthru_plus);
+			}
+			netfs_advance_writethrough(wreq, copied,
+						   offset + copied == flen);
+		}
 	retry:
 		folio_unlock(folio);
 		folio_put(folio);
@@ -325,17 +377,14 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 	} while (iov_iter_count(iter));
 
 out:
-	if (likely(written)) {
-		/* Flush and wait for a write that requires immediate synchronisation. */
-		if (iocb->ki_flags & (IOCB_DSYNC | IOCB_SYNC)) {
-			_debug("dsync");
-			ret = filemap_fdatawait_range(mapping, iocb->ki_pos,
-						      iocb->ki_pos + written);
-		}
-
-		iocb->ki_pos += written;
+	if (unlikely(wreq)) {
+		ret = netfs_end_writethrough(wreq, iocb);
+		wbc_detach_inode(&wbc);
+		if (ret == -EIOCBQUEUED)
+			return ret;
 	}
 
+	iocb->ki_pos += written;
 	_leave(" = %zd [%zd]", written, ret);
 	return written ? written : ret;
 
diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index 2de4f826dbe4..d2d63120ac60 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -101,6 +101,9 @@ static inline void netfs_see_request(struct netfs_io_request *rreq,
  */
 int netfs_begin_write(struct netfs_io_request *wreq, bool may_wait,
 		      enum netfs_write_trace what);
+struct netfs_io_request *netfs_begin_writethrough(struct kiocb *iocb, size_t len);
+int netfs_advance_writethrough(struct netfs_io_request *wreq, size_t copied, bool to_page_end);
+int netfs_end_writethrough(struct netfs_io_request *wreq, struct kiocb *iocb);
 
 /*
  * stats.c
diff --git a/fs/netfs/main.c b/fs/netfs/main.c
index 473f889e1bd1..81a13071b258 100644
--- a/fs/netfs/main.c
+++ b/fs/netfs/main.c
@@ -30,6 +30,7 @@ static const char *netfs_origins[nr__netfs_io_origin] = {
 	[NETFS_READPAGE]		= "RP",
 	[NETFS_READ_FOR_WRITE]		= "RW",
 	[NETFS_WRITEBACK]		= "WB",
+	[NETFS_WRITETHROUGH]		= "WT",
 	[NETFS_LAUNDER_WRITE]		= "LW",
 	[NETFS_UNBUFFERED_WRITE]	= "UW",
 	[NETFS_DIO_READ]		= "DR",
diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c
index b4e3bd836e5d..610ceb5bd86c 100644
--- a/fs/netfs/objects.c
+++ b/fs/netfs/objects.c
@@ -41,6 +41,7 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
 	rreq->i_size	= i_size_read(inode);
 	rreq->debug_id	= atomic_inc_return(&debug_ids);
 	INIT_LIST_HEAD(&rreq->subrequests);
+	INIT_WORK(&rreq->work, NULL);
 	refcount_set(&rreq->ref, 1);
 
 	__set_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags);
diff --git a/fs/netfs/output.c b/fs/netfs/output.c
index cc9065733b42..625eb68f3e5a 100644
--- a/fs/netfs/output.c
+++ b/fs/netfs/output.c
@@ -386,3 +386,93 @@ int netfs_begin_write(struct netfs_io_request *wreq, bool may_wait,
 		    TASK_UNINTERRUPTIBLE);
 	return wreq->error;
 }
+
+/*
+ * Begin a write operation for writing through the pagecache.
+ */
+struct netfs_io_request *netfs_begin_writethrough(struct kiocb *iocb, size_t len)
+{
+	struct netfs_io_request *wreq;
+	struct file *file = iocb->ki_filp;
+
+	wreq = netfs_alloc_request(file->f_mapping, file, iocb->ki_pos, len,
+				   NETFS_WRITETHROUGH);
+	if (IS_ERR(wreq))
+		return wreq;
+
+	trace_netfs_write(wreq, netfs_write_trace_writethrough);
+
+	__set_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags);
+	iov_iter_xarray(&wreq->iter, ITER_SOURCE, &wreq->mapping->i_pages, wreq->start, 0);
+	wreq->io_iter = wreq->iter;
+
+	/* ->outstanding > 0 carries a ref */
+	netfs_get_request(wreq, netfs_rreq_trace_get_for_outstanding);
+	atomic_set(&wreq->nr_outstanding, 1);
+	return wreq;
+}
+
+static void netfs_submit_writethrough(struct netfs_io_request *wreq, bool final)
+{
+	struct netfs_inode *ictx = netfs_inode(wreq->inode);
+	unsigned long long start;
+	size_t len;
+
+	if (!test_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags))
+		return;
+
+	start = wreq->start + wreq->submitted;
+	len = wreq->iter.count - wreq->submitted;
+	if (!final) {
+		len /= wreq->wsize; /* Round to number of maximum packets */
+		len *= wreq->wsize;
+	}
+
+	ictx->ops->create_write_requests(wreq, start, len);
+	wreq->submitted += len;
+}
+
+/*
+ * Advance the state of the write operation used when writing through the
+ * pagecache.  Data has been copied into the pagecache that we need to append
+ * to the request.  If we've added more than wsize then we need to create a new
+ * subrequest.
+ */
+int netfs_advance_writethrough(struct netfs_io_request *wreq, size_t copied, bool to_page_end)
+{
+	_enter("ic=%zu sb=%zu ws=%u cp=%zu tp=%u",
+	       wreq->iter.count, wreq->submitted, wreq->wsize, copied, to_page_end);
+
+	wreq->iter.count += copied;
+	wreq->io_iter.count += copied;
+	if (to_page_end && wreq->io_iter.count - wreq->submitted >= wreq->wsize)
+		netfs_submit_writethrough(wreq, false);
+
+	return wreq->error;
+}
+
+/*
+ * End a write operation used when writing through the pagecache.
+ */
+int netfs_end_writethrough(struct netfs_io_request *wreq, struct kiocb *iocb)
+{
+	int ret = -EIOCBQUEUED;
+
+	_enter("ic=%zu sb=%zu ws=%u",
+	       wreq->iter.count, wreq->submitted, wreq->wsize);
+
+	if (wreq->submitted < wreq->io_iter.count)
+		netfs_submit_writethrough(wreq, true);
+
+	if (atomic_dec_and_test(&wreq->nr_outstanding))
+		netfs_write_terminated(wreq, false);
+
+	if (is_sync_kiocb(iocb)) {
+		wait_on_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS,
+			    TASK_UNINTERRUPTIBLE);
+		ret = wreq->error;
+	}
+
+	netfs_put_request(wreq, false, netfs_rreq_trace_put_return);
+	return ret;
+}
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 29c66acad925..8a2dd882a781 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -139,6 +139,7 @@ struct netfs_inode {
 	unsigned long		flags;
 #define NETFS_ICTX_ODIRECT	0		/* The file has DIO in progress */
 #define NETFS_ICTX_UNBUFFERED	1		/* I/O should not use the pagecache */
+#define NETFS_ICTX_WRITETHROUGH	2		/* Write-through caching */
 };
 
 /*
@@ -227,6 +228,7 @@ enum netfs_io_origin {
 	NETFS_READPAGE,			/* This read is a synchronous read */
 	NETFS_READ_FOR_WRITE,		/* This read is to prepare a write */
 	NETFS_WRITEBACK,		/* This write was triggered by writepages */
+	NETFS_WRITETHROUGH,		/* This write was made by netfs_perform_write() */
 	NETFS_LAUNDER_WRITE,		/* This is triggered by ->launder_folio() */
 	NETFS_UNBUFFERED_WRITE,		/* This is an unbuffered write */
 	NETFS_DIO_READ,			/* This is a direct I/O read */
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index cc998798e20a..447a8c21cf57 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -27,13 +27,15 @@
 	EM(netfs_write_trace_dio_write,		"DIO-WRITE")	\
 	EM(netfs_write_trace_launder,		"LAUNDER  ")	\
 	EM(netfs_write_trace_unbuffered_write,	"UNB-WRITE")	\
-	E_(netfs_write_trace_writeback,		"WRITEBACK")
+	EM(netfs_write_trace_writeback,		"WRITEBACK")	\
+	E_(netfs_write_trace_writethrough,	"WRITETHRU")
 
 #define netfs_rreq_origins					\
 	EM(NETFS_READAHEAD,			"RA")		\
 	EM(NETFS_READPAGE,			"RP")		\
 	EM(NETFS_READ_FOR_WRITE,		"RW")		\
 	EM(NETFS_WRITEBACK,			"WB")		\
+	EM(NETFS_WRITETHROUGH,			"WT")		\
 	EM(NETFS_LAUNDER_WRITE,			"LW")		\
 	EM(NETFS_UNBUFFERED_WRITE,		"UW")		\
 	EM(NETFS_DIO_READ,			"DR")		\
@@ -136,7 +138,9 @@
 	EM(netfs_folio_trace_redirty,		"redirty")	\
 	EM(netfs_folio_trace_redirtied,		"redirtied")	\
 	EM(netfs_folio_trace_store,		"store")	\
-	E_(netfs_folio_trace_store_plus,	"store+")
+	EM(netfs_folio_trace_store_plus,	"store+")	\
+	EM(netfs_folio_trace_wthru,		"wthru")	\
+	E_(netfs_folio_trace_wthru_plus,	"wthru+")
 
 #ifndef __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY
 #define __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY
-- 
cgit v1.2.3


From 100ccd18bb41ea7abb4fbb419202c06079559501 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 24 Nov 2023 13:39:02 +0000
Subject: netfs: Optimise away reads above the point at which there can be no
 data

Track the file position above which the server is not expected to have any
data (the "zero point") and preemptively assume that we can satisfy
requests by filling them with zeroes locally rather than attempting to
download them if they're over that line - even if we've written data back
to the server.  Assume that any data that was written back above that
position is held in the local cache.  Note that we have to split requests
that straddle the line.

Make use of this to optimise away some reads from the server.  We need to
set the zero point in the following circumstances:

 (1) When we see an extant remote inode and have no cache for it, we set
     the zero_point to i_size.

 (2) On local inode creation, we set zero_point to 0.

 (3) On local truncation down, we reduce zero_point to the new i_size if
     the new i_size is lower.

 (4) On local truncation up, we don't change zero_point.

 (5) On local modification, we don't change zero_point.

 (6) On remote invalidation, we set zero_point to the new i_size.

 (7) If stored data is discarded from the pagecache or culled from fscache,
     we must set zero_point above that if the data also got written to the
     server.

 (8) If dirty data is written back to the server, but not fscache, we must
     set zero_point above that.

 (9) If a direct I/O write is made, set zero_point above that.

Assuming the above, any read from the server at or above the zero_point
position will return all zeroes.

The zero_point value can be stored in the cache, provided the above rules
are applied to it by any code that culls part of the local cache.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/9p/vfs_inode.c         |  2 +-
 fs/afs/dynroot.c          |  2 +-
 fs/afs/inode.c            | 24 ++++++++++++++----------
 fs/ceph/inode.c           |  2 +-
 fs/netfs/buffered_write.c |  2 +-
 fs/netfs/direct_write.c   |  4 ++++
 fs/netfs/io.c             | 10 ++++++++++
 fs/netfs/misc.c           |  5 +++++
 fs/nfs/fscache.h          |  2 +-
 fs/smb/client/cifsfs.c    |  4 ++--
 include/linux/netfs.h     | 21 ++++++++++++++++++---
 11 files changed, 58 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 74122540e00f..df7ae381a708 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -249,7 +249,7 @@ void v9fs_free_inode(struct inode *inode)
 static void v9fs_set_netfs_context(struct inode *inode)
 {
 	struct v9fs_inode *v9inode = V9FS_I(inode);
-	netfs_inode_init(&v9inode->netfs, &v9fs_req_ops);
+	netfs_inode_init(&v9inode->netfs, &v9fs_req_ops, true);
 }
 
 int v9fs_init_inode(struct v9fs_session_info *v9ses,
diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c
index 1f656005018e..9c517269ff95 100644
--- a/fs/afs/dynroot.c
+++ b/fs/afs/dynroot.c
@@ -76,7 +76,7 @@ struct inode *afs_iget_pseudo_dir(struct super_block *sb, bool root)
 	/* there shouldn't be an existing inode */
 	BUG_ON(!(inode->i_state & I_NEW));
 
-	netfs_inode_init(&vnode->netfs, NULL);
+	netfs_inode_init(&vnode->netfs, NULL, false);
 	inode->i_size		= 0;
 	inode->i_mode		= S_IFDIR | S_IRUGO | S_IXUGO;
 	if (root) {
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 37485ae31471..381521e9e118 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -58,7 +58,7 @@ static noinline void dump_vnode(struct afs_vnode *vnode, struct afs_vnode *paren
  */
 static void afs_set_netfs_context(struct afs_vnode *vnode)
 {
-	netfs_inode_init(&vnode->netfs, &afs_req_ops);
+	netfs_inode_init(&vnode->netfs, &afs_req_ops, true);
 }
 
 /*
@@ -168,6 +168,7 @@ static void afs_apply_status(struct afs_operation *op,
 	struct inode *inode = &vnode->netfs.inode;
 	struct timespec64 t;
 	umode_t mode;
+	bool unexpected_jump = false;
 	bool data_changed = false;
 	bool change_size = vp->set_size;
 
@@ -231,6 +232,7 @@ static void afs_apply_status(struct afs_operation *op,
 		}
 		change_size = true;
 		data_changed = true;
+		unexpected_jump = true;
 	} else if (vnode->status.type == AFS_FTYPE_DIR) {
 		/* Expected directory change is handled elsewhere so
 		 * that we can locally edit the directory and save on a
@@ -252,6 +254,8 @@ static void afs_apply_status(struct afs_operation *op,
 		vnode->netfs.remote_i_size = status->size;
 		if (change_size || status->size > i_size_read(inode)) {
 			afs_set_i_size(vnode, status->size);
+			if (unexpected_jump)
+				vnode->netfs.zero_point = status->size;
 			inode_set_ctime_to_ts(inode, t);
 			inode_set_atime_to_ts(inode, t);
 		}
@@ -865,17 +869,17 @@ static void afs_setattr_success(struct afs_operation *op)
 static void afs_setattr_edit_file(struct afs_operation *op)
 {
 	struct afs_vnode_param *vp = &op->file[0];
-	struct inode *inode = &vp->vnode->netfs.inode;
+	struct afs_vnode *vnode = vp->vnode;
 
 	if (op->setattr.attr->ia_valid & ATTR_SIZE) {
 		loff_t size = op->setattr.attr->ia_size;
 		loff_t i_size = op->setattr.old_i_size;
 
-		if (size < i_size)
-			truncate_pagecache(inode, size);
-		if (size != i_size)
-			fscache_resize_cookie(afs_vnode_cache(vp->vnode),
-					      vp->scb.status.size);
+		if (size != i_size) {
+			truncate_setsize(&vnode->netfs.inode, size);
+			netfs_resize_file(&vnode->netfs, size, true);
+			fscache_resize_cookie(afs_vnode_cache(vnode), size);
+		}
 	}
 }
 
@@ -943,11 +947,11 @@ int afs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 		 */
 		if (!(attr->ia_valid & (supported & ~ATTR_SIZE & ~ATTR_MTIME)) &&
 		    attr->ia_size < i_size &&
-		    attr->ia_size > vnode->status.size) {
-			truncate_pagecache(inode, attr->ia_size);
+		    attr->ia_size > vnode->netfs.remote_i_size) {
+			truncate_setsize(inode, attr->ia_size);
+			netfs_resize_file(&vnode->netfs, size, false);
 			fscache_resize_cookie(afs_vnode_cache(vnode),
 					      attr->ia_size);
-			i_size_write(inode, attr->ia_size);
 			ret = 0;
 			goto out_unlock;
 		}
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 3149d79a9dbe..0c25d326afc4 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -574,7 +574,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
 	doutc(fsc->client, "%p\n", &ci->netfs.inode);
 
 	/* Set parameters for the netfs library */
-	netfs_inode_init(&ci->netfs, &ceph_netfs_ops);
+	netfs_inode_init(&ci->netfs, &ceph_netfs_ops, false);
 
 	spin_lock_init(&ci->i_ceph_lock);
 
diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index 6ca6c4bde5eb..08f28800232c 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -73,7 +73,7 @@ static enum netfs_how_to_modify netfs_how_to_modify(struct netfs_inode *ctx,
 	if (folio_test_uptodate(folio))
 		return NETFS_FOLIO_IS_UPTODATE;
 
-	if (pos >= ctx->remote_i_size)
+	if (pos >= ctx->zero_point)
 		return NETFS_MODIFY_AND_CLEAR;
 
 	if (!maybe_trouble && offset == 0 && len >= flen)
diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c
index bb0c2718f57b..aad05f2349a4 100644
--- a/fs/netfs/direct_write.c
+++ b/fs/netfs/direct_write.c
@@ -134,6 +134,7 @@ ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
 	struct netfs_inode *ictx = netfs_inode(inode);
+	unsigned long long end;
 	ssize_t ret;
 
 	_enter("%llx,%zx,%llx", iocb->ki_pos, iov_iter_count(from), i_size_read(inode));
@@ -155,6 +156,9 @@ ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	ret = kiocb_invalidate_pages(iocb, iov_iter_count(from));
 	if (ret < 0)
 		goto out;
+	end = iocb->ki_pos + iov_iter_count(from);
+	if (end > ictx->zero_point)
+		ictx->zero_point = end;
 
 	fscache_invalidate(netfs_i_cookie(ictx), NULL, i_size_read(inode),
 			   FSCACHE_INVAL_DIO_WRITE);
diff --git a/fs/netfs/io.c b/fs/netfs/io.c
index 14c18be5aca0..5b5af96cd4b9 100644
--- a/fs/netfs/io.c
+++ b/fs/netfs/io.c
@@ -569,6 +569,7 @@ netfs_rreq_prepare_read(struct netfs_io_request *rreq,
 			struct iov_iter *io_iter)
 {
 	enum netfs_io_source source = NETFS_DOWNLOAD_FROM_SERVER;
+	struct netfs_inode *ictx = netfs_inode(rreq->inode);
 	size_t lsize;
 
 	_enter("%llx-%llx,%llx", subreq->start, subreq->start + subreq->len, rreq->i_size);
@@ -586,6 +587,14 @@ netfs_rreq_prepare_read(struct netfs_io_request *rreq,
 		 * to make serial calls, it can indicate a short read and then
 		 * we will call it again.
 		 */
+		if (rreq->origin != NETFS_DIO_READ) {
+			if (subreq->start >= ictx->zero_point) {
+				source = NETFS_FILL_WITH_ZEROES;
+				goto set;
+			}
+			if (subreq->len > ictx->zero_point - subreq->start)
+				subreq->len = ictx->zero_point - subreq->start;
+		}
 		if (subreq->len > rreq->i_size - subreq->start)
 			subreq->len = rreq->i_size - subreq->start;
 		if (rreq->rsize && subreq->len > rreq->rsize)
@@ -607,6 +616,7 @@ netfs_rreq_prepare_read(struct netfs_io_request *rreq,
 		}
 	}
 
+set:
 	if (subreq->len > rreq->len)
 		pr_warn("R=%08x[%u] SREQ>RREQ %zx > %zx\n",
 			rreq->debug_id, subreq->debug_index,
diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c
index eeb44abe59c5..0e3af37fc924 100644
--- a/fs/netfs/misc.c
+++ b/fs/netfs/misc.c
@@ -240,6 +240,11 @@ EXPORT_SYMBOL(netfs_invalidate_folio);
 bool netfs_release_folio(struct folio *folio, gfp_t gfp)
 {
 	struct netfs_inode *ctx = netfs_inode(folio_inode(folio));
+	unsigned long long end;
+
+	end = folio_pos(folio) + folio_size(folio);
+	if (end > ctx->zero_point)
+		ctx->zero_point = end;
 
 	if (folio_test_private(folio))
 		return false;
diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h
index 5407ab8c8783..e3cb4923316b 100644
--- a/fs/nfs/fscache.h
+++ b/fs/nfs/fscache.h
@@ -80,7 +80,7 @@ static inline void nfs_netfs_put(struct nfs_netfs_io_data *netfs)
 }
 static inline void nfs_netfs_inode_init(struct nfs_inode *nfsi)
 {
-	netfs_inode_init(&nfsi->netfs, &nfs_netfs_ops);
+	netfs_inode_init(&nfsi->netfs, &nfs_netfs_ops, false);
 }
 extern void nfs_netfs_initiate_read(struct nfs_pgio_header *hdr);
 extern void nfs_netfs_read_completion(struct nfs_pgio_header *hdr);
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index 96a65cf9b5ec..07cd88897c33 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -1220,7 +1220,7 @@ static int cifs_precopy_set_eof(struct inode *src_inode, struct cifsInodeInfo *s
 	if (rc < 0)
 		goto set_failed;
 
-	netfs_resize_file(&src_cifsi->netfs, src_end);
+	netfs_resize_file(&src_cifsi->netfs, src_end, true);
 	fscache_resize_cookie(cifs_inode_cookie(src_inode), src_end);
 	return 0;
 
@@ -1351,7 +1351,7 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off,
 			smb_file_src, smb_file_target, off, len, destoff);
 		if (rc == 0 && new_size > i_size_read(target_inode)) {
 			truncate_setsize(target_inode, new_size);
-			netfs_resize_file(&target_cifsi->netfs, new_size);
+			netfs_resize_file(&target_cifsi->netfs, new_size, true);
 			fscache_resize_cookie(cifs_inode_cookie(target_inode),
 					      new_size);
 		}
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 8a2dd882a781..852956aa3c4b 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -136,6 +136,8 @@ struct netfs_inode {
 	struct fscache_cookie	*cache;
 #endif
 	loff_t			remote_i_size;	/* Size of the remote file */
+	loff_t			zero_point;	/* Size after which we assume there's no data
+						 * on the server */
 	unsigned long		flags;
 #define NETFS_ICTX_ODIRECT	0		/* The file has DIO in progress */
 #define NETFS_ICTX_UNBUFFERED	1		/* I/O should not use the pagecache */
@@ -453,31 +455,44 @@ static inline struct netfs_inode *netfs_inode(struct inode *inode)
  * netfs_inode_init - Initialise a netfslib inode context
  * @ctx: The netfs inode to initialise
  * @ops: The netfs's operations list
+ * @use_zero_point: True to use the zero_point read optimisation
  *
  * Initialise the netfs library context struct.  This is expected to follow on
  * directly from the VFS inode struct.
  */
 static inline void netfs_inode_init(struct netfs_inode *ctx,
-				    const struct netfs_request_ops *ops)
+				    const struct netfs_request_ops *ops,
+				    bool use_zero_point)
 {
 	ctx->ops = ops;
 	ctx->remote_i_size = i_size_read(&ctx->inode);
+	ctx->zero_point = LLONG_MAX;
 	ctx->flags = 0;
 #if IS_ENABLED(CONFIG_FSCACHE)
 	ctx->cache = NULL;
 #endif
+	/* ->releasepage() drives zero_point */
+	if (use_zero_point) {
+		ctx->zero_point = ctx->remote_i_size;
+		mapping_set_release_always(ctx->inode.i_mapping);
+	}
 }
 
 /**
  * netfs_resize_file - Note that a file got resized
  * @ctx: The netfs inode being resized
  * @new_i_size: The new file size
+ * @changed_on_server: The change was applied to the server
  *
  * Inform the netfs lib that a file got resized so that it can adjust its state.
  */
-static inline void netfs_resize_file(struct netfs_inode *ctx, loff_t new_i_size)
+static inline void netfs_resize_file(struct netfs_inode *ctx, loff_t new_i_size,
+				     bool changed_on_server)
 {
-	ctx->remote_i_size = new_i_size;
+	if (changed_on_server)
+		ctx->remote_i_size = new_i_size;
+	if (new_i_size < ctx->zero_point)
+		ctx->zero_point = new_i_size;
 }
 
 /**
-- 
cgit v1.2.3


From 3560358a49569d0ade0ee5c9cecb3606dac863c2 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 15 Feb 2022 17:02:04 +0000
Subject: afs: Use the netfs write helpers

Make afs use the netfs write helpers.

Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/afs/file.c              |  70 ++++-
 fs/afs/internal.h          |  10 +-
 fs/afs/write.c             | 707 ++-------------------------------------------
 include/trace/events/afs.h |  23 --
 4 files changed, 84 insertions(+), 726 deletions(-)

(limited to 'include')

diff --git a/fs/afs/file.c b/fs/afs/file.c
index 3403bb792deb..833e7c2003e0 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -34,7 +34,7 @@ const struct file_operations afs_file_operations = {
 	.release	= afs_release,
 	.llseek		= generic_file_llseek,
 	.read_iter	= afs_file_read_iter,
-	.write_iter	= afs_file_write,
+	.write_iter	= netfs_file_write_iter,
 	.mmap		= afs_file_mmap,
 	.splice_read	= afs_file_splice_read,
 	.splice_write	= iter_file_splice_write,
@@ -50,16 +50,15 @@ const struct inode_operations afs_file_inode_operations = {
 };
 
 const struct address_space_operations afs_file_aops = {
+	.direct_IO	= noop_direct_IO,
 	.read_folio	= netfs_read_folio,
 	.readahead	= netfs_readahead,
 	.dirty_folio	= netfs_dirty_folio,
-	.launder_folio	= afs_launder_folio,
+	.launder_folio	= netfs_launder_folio,
 	.release_folio	= netfs_release_folio,
 	.invalidate_folio = netfs_invalidate_folio,
-	.write_begin	= afs_write_begin,
-	.write_end	= afs_write_end,
-	.writepages	= afs_writepages,
 	.migrate_folio	= filemap_migrate_folio,
+	.writepages	= afs_writepages,
 };
 
 const struct address_space_operations afs_symlink_aops = {
@@ -355,7 +354,10 @@ static int afs_symlink_read_folio(struct file *file, struct folio *folio)
 
 static int afs_init_request(struct netfs_io_request *rreq, struct file *file)
 {
-	rreq->netfs_priv = key_get(afs_file_key(file));
+	if (file)
+		rreq->netfs_priv = key_get(afs_file_key(file));
+	rreq->rsize = 256 * 1024;
+	rreq->wsize = 256 * 1024;
 	return 0;
 }
 
@@ -372,11 +374,36 @@ static void afs_free_request(struct netfs_io_request *rreq)
 	key_put(rreq->netfs_priv);
 }
 
+static void afs_update_i_size(struct inode *inode, loff_t new_i_size)
+{
+	struct afs_vnode *vnode = AFS_FS_I(inode);
+	loff_t i_size;
+
+	write_seqlock(&vnode->cb_lock);
+	i_size = i_size_read(&vnode->netfs.inode);
+	if (new_i_size > i_size) {
+		i_size_write(&vnode->netfs.inode, new_i_size);
+		inode_set_bytes(&vnode->netfs.inode, new_i_size);
+	}
+	write_sequnlock(&vnode->cb_lock);
+	fscache_update_cookie(afs_vnode_cache(vnode), NULL, &new_i_size);
+}
+
+static void afs_netfs_invalidate_cache(struct netfs_io_request *wreq)
+{
+	struct afs_vnode *vnode = AFS_FS_I(wreq->inode);
+
+	afs_invalidate_cache(vnode, 0);
+}
+
 const struct netfs_request_ops afs_req_ops = {
 	.init_request		= afs_init_request,
 	.free_request		= afs_free_request,
 	.check_write_begin	= afs_check_write_begin,
 	.issue_read		= afs_issue_read,
+	.update_i_size		= afs_update_i_size,
+	.invalidate_cache	= afs_netfs_invalidate_cache,
+	.create_write_requests	= afs_create_write_requests,
 };
 
 static void afs_add_open_mmap(struct afs_vnode *vnode)
@@ -445,28 +472,39 @@ static vm_fault_t afs_vm_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pg
 
 static ssize_t afs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 {
-	struct afs_vnode *vnode = AFS_FS_I(file_inode(iocb->ki_filp));
+	struct inode *inode = file_inode(iocb->ki_filp);
+	struct afs_vnode *vnode = AFS_FS_I(inode);
 	struct afs_file *af = iocb->ki_filp->private_data;
-	int ret;
+	ssize_t ret;
 
-	ret = afs_validate(vnode, af->key);
+	if (iocb->ki_flags & IOCB_DIRECT)
+		return netfs_unbuffered_read_iter(iocb, iter);
+
+	ret = netfs_start_io_read(inode);
 	if (ret < 0)
 		return ret;
-
-	return generic_file_read_iter(iocb, iter);
+	ret = afs_validate(vnode, af->key);
+	if (ret == 0)
+		ret = filemap_read(iocb, iter, 0);
+	netfs_end_io_read(inode);
+	return ret;
 }
 
 static ssize_t afs_file_splice_read(struct file *in, loff_t *ppos,
 				    struct pipe_inode_info *pipe,
 				    size_t len, unsigned int flags)
 {
-	struct afs_vnode *vnode = AFS_FS_I(file_inode(in));
+	struct inode *inode = file_inode(in);
+	struct afs_vnode *vnode = AFS_FS_I(inode);
 	struct afs_file *af = in->private_data;
-	int ret;
+	ssize_t ret;
 
-	ret = afs_validate(vnode, af->key);
+	ret = netfs_start_io_read(inode);
 	if (ret < 0)
 		return ret;
-
-	return filemap_splice_read(in, ppos, pipe, len, flags);
+	ret = afs_validate(vnode, af->key);
+	if (ret == 0)
+		ret = filemap_splice_read(in, ppos, pipe, len, flags);
+	netfs_end_io_read(inode);
+	return ret;
 }
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index a7c8d1d702ee..32f787f74e76 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -1465,19 +1465,11 @@ extern int afs_check_volume_status(struct afs_volume *, struct afs_operation *);
 /*
  * write.c
  */
-extern int afs_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len,
-			struct page **pagep, void **fsdata);
-extern int afs_write_end(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned copied,
-			struct page *page, void *fsdata);
-extern int afs_writepage(struct page *, struct writeback_control *);
 extern int afs_writepages(struct address_space *, struct writeback_control *);
-extern ssize_t afs_file_write(struct kiocb *, struct iov_iter *);
 extern int afs_fsync(struct file *, loff_t, loff_t, int);
 extern vm_fault_t afs_page_mkwrite(struct vm_fault *vmf);
 extern void afs_prune_wb_keys(struct afs_vnode *);
-int afs_launder_folio(struct folio *);
+void afs_create_write_requests(struct netfs_io_request *wreq, loff_t start, size_t len);
 
 /*
  * xattr.c
diff --git a/fs/afs/write.c b/fs/afs/write.c
index 80daf28d8f8b..09b6c0b9a28e 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -12,228 +12,17 @@
 #include <linux/writeback.h>
 #include <linux/pagevec.h>
 #include <linux/netfs.h>
+#include <trace/events/netfs.h>
 #include "internal.h"
 
-static int afs_writepages_region(struct address_space *mapping,
-				 struct writeback_control *wbc,
-				 unsigned long long start,
-				 unsigned long long end, loff_t *_next,
-				 bool max_one_loop);
-
-static void afs_write_to_cache(struct afs_vnode *vnode, loff_t start, size_t len,
-			       loff_t i_size, bool caching);
-
-#ifdef CONFIG_AFS_FSCACHE
-static void afs_folio_start_fscache(bool caching, struct folio *folio)
-{
-	if (caching)
-		folio_start_fscache(folio);
-}
-#else
-static void afs_folio_start_fscache(bool caching, struct folio *folio)
-{
-}
-#endif
-
-/*
- * prepare to perform part of a write to a page
- */
-int afs_write_begin(struct file *file, struct address_space *mapping,
-		    loff_t pos, unsigned len,
-		    struct page **_page, void **fsdata)
-{
-	struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
-	struct folio *folio;
-	int ret;
-
-	_enter("{%llx:%llu},%llx,%x",
-	       vnode->fid.vid, vnode->fid.vnode, pos, len);
-
-	/* Prefetch area to be written into the cache if we're caching this
-	 * file.  We need to do this before we get a lock on the page in case
-	 * there's more than one writer competing for the same cache block.
-	 */
-	ret = netfs_write_begin(&vnode->netfs, file, mapping, pos, len, &folio, fsdata);
-	if (ret < 0)
-		return ret;
-
-try_again:
-	/* See if this page is already partially written in a way that we can
-	 * merge the new write with.
-	 */
-	if (folio_test_writeback(folio)) {
-		trace_afs_folio_dirty(vnode, tracepoint_string("alrdy"), folio);
-		folio_unlock(folio);
-		goto wait_for_writeback;
-	}
-
-	*_page = folio_file_page(folio, pos / PAGE_SIZE);
-	_leave(" = 0");
-	return 0;
-
-wait_for_writeback:
-	ret = folio_wait_writeback_killable(folio);
-	if (ret < 0)
-		goto error;
-
-	ret = folio_lock_killable(folio);
-	if (ret < 0)
-		goto error;
-	goto try_again;
-
-error:
-	folio_put(folio);
-	_leave(" = %d", ret);
-	return ret;
-}
-
-/*
- * finalise part of a write to a page
- */
-int afs_write_end(struct file *file, struct address_space *mapping,
-		  loff_t pos, unsigned len, unsigned copied,
-		  struct page *subpage, void *fsdata)
-{
-	struct folio *folio = page_folio(subpage);
-	struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
-	loff_t i_size, write_end_pos;
-
-	_enter("{%llx:%llu},{%lx}",
-	       vnode->fid.vid, vnode->fid.vnode, folio_index(folio));
-
-	if (!folio_test_uptodate(folio)) {
-		if (copied < len) {
-			copied = 0;
-			goto out;
-		}
-
-		folio_mark_uptodate(folio);
-	}
-
-	if (copied == 0)
-		goto out;
-
-	write_end_pos = pos + copied;
-
-	i_size = i_size_read(&vnode->netfs.inode);
-	if (write_end_pos > i_size) {
-		write_seqlock(&vnode->cb_lock);
-		i_size = i_size_read(&vnode->netfs.inode);
-		if (write_end_pos > i_size)
-			afs_set_i_size(vnode, write_end_pos);
-		write_sequnlock(&vnode->cb_lock);
-		fscache_update_cookie(afs_vnode_cache(vnode), NULL, &write_end_pos);
-	}
-
-	if (folio_mark_dirty(folio))
-		_debug("dirtied %lx", folio_index(folio));
-
-out:
-	folio_unlock(folio);
-	folio_put(folio);
-	return copied;
-}
-
-/*
- * kill all the pages in the given range
- */
-static void afs_kill_pages(struct address_space *mapping,
-			   loff_t start, loff_t len)
-{
-	struct afs_vnode *vnode = AFS_FS_I(mapping->host);
-	struct folio *folio;
-	pgoff_t index = start / PAGE_SIZE;
-	pgoff_t last = (start + len - 1) / PAGE_SIZE, next;
-
-	_enter("{%llx:%llu},%llx @%llx",
-	       vnode->fid.vid, vnode->fid.vnode, len, start);
-
-	do {
-		_debug("kill %lx (to %lx)", index, last);
-
-		folio = filemap_get_folio(mapping, index);
-		if (IS_ERR(folio)) {
-			next = index + 1;
-			continue;
-		}
-
-		next = folio_next_index(folio);
-
-		folio_clear_uptodate(folio);
-		folio_end_writeback(folio);
-		folio_lock(folio);
-		generic_error_remove_page(mapping, &folio->page);
-		folio_unlock(folio);
-		folio_put(folio);
-
-	} while (index = next, index <= last);
-
-	_leave("");
-}
-
-/*
- * Redirty all the pages in a given range.
- */
-static void afs_redirty_pages(struct writeback_control *wbc,
-			      struct address_space *mapping,
-			      loff_t start, loff_t len)
-{
-	struct afs_vnode *vnode = AFS_FS_I(mapping->host);
-	struct folio *folio;
-	pgoff_t index = start / PAGE_SIZE;
-	pgoff_t last = (start + len - 1) / PAGE_SIZE, next;
-
-	_enter("{%llx:%llu},%llx @%llx",
-	       vnode->fid.vid, vnode->fid.vnode, len, start);
-
-	do {
-		_debug("redirty %llx @%llx", len, start);
-
-		folio = filemap_get_folio(mapping, index);
-		if (IS_ERR(folio)) {
-			next = index + 1;
-			continue;
-		}
-
-		next = index + folio_nr_pages(folio);
-		folio_redirty_for_writepage(wbc, folio);
-		folio_end_writeback(folio);
-		folio_put(folio);
-	} while (index = next, index <= last);
-
-	_leave("");
-}
-
 /*
  * completion of write to server
  */
 static void afs_pages_written_back(struct afs_vnode *vnode, loff_t start, unsigned int len)
 {
-	struct address_space *mapping = vnode->netfs.inode.i_mapping;
-	struct folio *folio;
-	pgoff_t end;
-
-	XA_STATE(xas, &mapping->i_pages, start / PAGE_SIZE);
-
 	_enter("{%llx:%llu},{%x @%llx}",
 	       vnode->fid.vid, vnode->fid.vnode, len, start);
 
-	rcu_read_lock();
-
-	end = (start + len - 1) / PAGE_SIZE;
-	xas_for_each(&xas, folio, end) {
-		if (!folio_test_writeback(folio)) {
-			kdebug("bad %x @%llx page %lx %lx",
-			       len, start, folio_index(folio), end);
-			ASSERT(folio_test_writeback(folio));
-		}
-
-		trace_afs_folio_dirty(vnode, tracepoint_string("clear"), folio);
-		folio_end_writeback(folio);
-	}
-
-	rcu_read_unlock();
-
 	afs_prune_wb_keys(vnode);
 	_leave("");
 }
@@ -370,339 +159,53 @@ try_next_key:
 	return afs_put_operation(op);
 }
 
-/*
- * Extend the region to be written back to include subsequent contiguously
- * dirty pages if possible, but don't sleep while doing so.
- *
- * If this page holds new content, then we can include filler zeros in the
- * writeback.
- */
-static void afs_extend_writeback(struct address_space *mapping,
-				 struct afs_vnode *vnode,
-				 long *_count,
-				 loff_t start,
-				 loff_t max_len,
-				 bool caching,
-				 size_t *_len)
+static void afs_upload_to_server(struct netfs_io_subrequest *subreq)
 {
-	struct folio_batch fbatch;
-	struct folio *folio;
-	pgoff_t index = (start + *_len) / PAGE_SIZE;
-	bool stop = true;
-	unsigned int i;
-
-	XA_STATE(xas, &mapping->i_pages, index);
-	folio_batch_init(&fbatch);
-
-	do {
-		/* Firstly, we gather up a batch of contiguous dirty pages
-		 * under the RCU read lock - but we can't clear the dirty flags
-		 * there if any of those pages are mapped.
-		 */
-		rcu_read_lock();
-
-		xas_for_each(&xas, folio, ULONG_MAX) {
-			stop = true;
-			if (xas_retry(&xas, folio))
-				continue;
-			if (xa_is_value(folio))
-				break;
-			if (folio_index(folio) != index)
-				break;
-
-			if (!folio_try_get_rcu(folio)) {
-				xas_reset(&xas);
-				continue;
-			}
-
-			/* Has the folio moved or been split? */
-			if (unlikely(folio != xas_reload(&xas))) {
-				folio_put(folio);
-				break;
-			}
-
-			if (!folio_trylock(folio)) {
-				folio_put(folio);
-				break;
-			}
-			if (!folio_test_dirty(folio) ||
-			    folio_test_writeback(folio) ||
-			    folio_test_fscache(folio)) {
-				folio_unlock(folio);
-				folio_put(folio);
-				break;
-			}
-
-			index += folio_nr_pages(folio);
-			*_count -= folio_nr_pages(folio);
-			*_len += folio_size(folio);
-			stop = false;
-			if (*_len >= max_len || *_count <= 0)
-				stop = true;
-
-			if (!folio_batch_add(&fbatch, folio))
-				break;
-			if (stop)
-				break;
-		}
-
-		if (!stop)
-			xas_pause(&xas);
-		rcu_read_unlock();
-
-		/* Now, if we obtained any folios, we can shift them to being
-		 * writable and mark them for caching.
-		 */
-		if (!folio_batch_count(&fbatch))
-			break;
-
-		for (i = 0; i < folio_batch_count(&fbatch); i++) {
-			folio = fbatch.folios[i];
-			trace_afs_folio_dirty(vnode, tracepoint_string("store+"), folio);
+	struct afs_vnode *vnode = AFS_FS_I(subreq->rreq->inode);
+	ssize_t ret;
 
-			if (!folio_clear_dirty_for_io(folio))
-				BUG();
-			if (folio_start_writeback(folio))
-				BUG();
-			afs_folio_start_fscache(caching, folio);
-			folio_unlock(folio);
-		}
+	_enter("%x[%x],%zx",
+	       subreq->rreq->debug_id, subreq->debug_index, subreq->io_iter.count);
 
-		folio_batch_release(&fbatch);
-		cond_resched();
-	} while (!stop);
+	trace_netfs_sreq(subreq, netfs_sreq_trace_submit);
+	ret = afs_store_data(vnode, &subreq->io_iter, subreq->start,
+			     subreq->rreq->origin == NETFS_LAUNDER_WRITE);
+	netfs_write_subrequest_terminated(subreq, ret < 0 ? ret : subreq->len,
+					  false);
 }
 
-/*
- * Synchronously write back the locked page and any subsequent non-locked dirty
- * pages.
- */
-static ssize_t afs_write_back_from_locked_folio(struct address_space *mapping,
-						struct writeback_control *wbc,
-						struct folio *folio,
-						unsigned long long start,
-						unsigned long long end)
+static void afs_upload_to_server_worker(struct work_struct *work)
 {
-	struct afs_vnode *vnode = AFS_FS_I(mapping->host);
-	struct iov_iter iter;
-	unsigned long long i_size = i_size_read(&vnode->netfs.inode);
-	size_t len, max_len;
-	bool caching = fscache_cookie_enabled(afs_vnode_cache(vnode));
-	long count = wbc->nr_to_write;
-	int ret;
-
-	_enter(",%lx,%llx-%llx", folio_index(folio), start, end);
-
-	if (folio_start_writeback(folio))
-		BUG();
-	afs_folio_start_fscache(caching, folio);
-
-	count -= folio_nr_pages(folio);
-
-	/* Find all consecutive lockable dirty pages that have contiguous
-	 * written regions, stopping when we find a page that is not
-	 * immediately lockable, is not dirty or is missing, or we reach the
-	 * end of the range.
-	 */
-	trace_afs_folio_dirty(vnode, tracepoint_string("store"), folio);
-
-	len = folio_size(folio);
-	if (start < i_size) {
-		/* Trim the write to the EOF; the extra data is ignored.  Also
-		 * put an upper limit on the size of a single storedata op.
-		 */
-		max_len = 65536 * 4096;
-		max_len = min_t(unsigned long long, max_len, end - start + 1);
-		max_len = min_t(unsigned long long, max_len, i_size - start);
-
-		if (len < max_len)
-			afs_extend_writeback(mapping, vnode, &count,
-					     start, max_len, caching, &len);
-		len = min_t(unsigned long long, len, i_size - start);
-	}
-
-	/* We now have a contiguous set of dirty pages, each with writeback
-	 * set; the first page is still locked at this point, but all the rest
-	 * have been unlocked.
-	 */
-	folio_unlock(folio);
-
-	if (start < i_size) {
-		_debug("write back %zx @%llx [%llx]", len, start, i_size);
-
-		/* Speculatively write to the cache.  We have to fix this up
-		 * later if the store fails.
-		 */
-		afs_write_to_cache(vnode, start, len, i_size, caching);
-
-		iov_iter_xarray(&iter, ITER_SOURCE, &mapping->i_pages, start, len);
-		ret = afs_store_data(vnode, &iter, start, false);
-	} else {
-		_debug("write discard %zx @%llx [%llx]", len, start, i_size);
-
-		/* The dirty region was entirely beyond the EOF. */
-		fscache_clear_page_bits(mapping, start, len, caching);
-		afs_pages_written_back(vnode, start, len);
-		ret = 0;
-	}
-
-	switch (ret) {
-	case 0:
-		wbc->nr_to_write = count;
-		ret = len;
-		break;
-
-	default:
-		pr_notice("kAFS: Unexpected error from FS.StoreData %d\n", ret);
-		fallthrough;
-	case -EACCES:
-	case -EPERM:
-	case -ENOKEY:
-	case -EKEYEXPIRED:
-	case -EKEYREJECTED:
-	case -EKEYREVOKED:
-	case -ENETRESET:
-		afs_redirty_pages(wbc, mapping, start, len);
-		mapping_set_error(mapping, ret);
-		break;
-
-	case -EDQUOT:
-	case -ENOSPC:
-		afs_redirty_pages(wbc, mapping, start, len);
-		mapping_set_error(mapping, -ENOSPC);
-		break;
-
-	case -EROFS:
-	case -EIO:
-	case -EREMOTEIO:
-	case -EFBIG:
-	case -ENOENT:
-	case -ENOMEDIUM:
-	case -ENXIO:
-		trace_afs_file_error(vnode, ret, afs_file_error_writeback_fail);
-		afs_kill_pages(mapping, start, len);
-		mapping_set_error(mapping, ret);
-		break;
-	}
+	struct netfs_io_subrequest *subreq =
+		container_of(work, struct netfs_io_subrequest, work);
 
-	_leave(" = %d", ret);
-	return ret;
+	afs_upload_to_server(subreq);
 }
 
 /*
- * write a region of pages back to the server
+ * Set up write requests for a writeback slice.  We need to add a write request
+ * for each write we want to make.
  */
-static int afs_writepages_region(struct address_space *mapping,
-				 struct writeback_control *wbc,
-				 unsigned long long start,
-				 unsigned long long end, loff_t *_next,
-				 bool max_one_loop)
+void afs_create_write_requests(struct netfs_io_request *wreq, loff_t start, size_t len)
 {
-	struct folio *folio;
-	struct folio_batch fbatch;
-	ssize_t ret;
-	unsigned int i;
-	int n, skips = 0;
-
-	_enter("%llx,%llx,", start, end);
-	folio_batch_init(&fbatch);
+	struct netfs_io_subrequest *subreq;
 
-	do {
-		pgoff_t index = start / PAGE_SIZE;
+	_enter("%x,%llx-%llx", wreq->debug_id, start, start + len);
 
-		n = filemap_get_folios_tag(mapping, &index, end / PAGE_SIZE,
-					PAGECACHE_TAG_DIRTY, &fbatch);
-
-		if (!n)
-			break;
-		for (i = 0; i < n; i++) {
-			folio = fbatch.folios[i];
-			start = folio_pos(folio); /* May regress with THPs */
-
-			_debug("wback %lx", folio_index(folio));
-
-			/* At this point we hold neither the i_pages lock nor the
-			 * page lock: the page may be truncated or invalidated
-			 * (changing page->mapping to NULL), or even swizzled
-			 * back from swapper_space to tmpfs file mapping
-			 */
-try_again:
-			if (wbc->sync_mode != WB_SYNC_NONE) {
-				ret = folio_lock_killable(folio);
-				if (ret < 0) {
-					folio_batch_release(&fbatch);
-					return ret;
-				}
-			} else {
-				if (!folio_trylock(folio))
-					continue;
-			}
-
-			if (folio->mapping != mapping ||
-			    !folio_test_dirty(folio)) {
-				start += folio_size(folio);
-				folio_unlock(folio);
-				continue;
-			}
-
-			if (folio_test_writeback(folio) ||
-			    folio_test_fscache(folio)) {
-				folio_unlock(folio);
-				if (wbc->sync_mode != WB_SYNC_NONE) {
-					folio_wait_writeback(folio);
-#ifdef CONFIG_AFS_FSCACHE
-					folio_wait_fscache(folio);
-#endif
-					goto try_again;
-				}
-
-				start += folio_size(folio);
-				if (wbc->sync_mode == WB_SYNC_NONE) {
-					if (skips >= 5 || need_resched()) {
-						*_next = start;
-						folio_batch_release(&fbatch);
-						_leave(" = 0 [%llx]", *_next);
-						return 0;
-					}
-					skips++;
-				}
-				continue;
-			}
-
-			if (!folio_clear_dirty_for_io(folio))
-				BUG();
-			ret = afs_write_back_from_locked_folio(mapping, wbc,
-					folio, start, end);
-			if (ret < 0) {
-				_leave(" = %zd", ret);
-				folio_batch_release(&fbatch);
-				return ret;
-			}
-
-			start += ret;
-		}
-
-		folio_batch_release(&fbatch);
-		cond_resched();
-	} while (wbc->nr_to_write > 0);
-
-	*_next = start;
-	_leave(" = 0 [%llx]", *_next);
-	return 0;
+	subreq = netfs_create_write_request(wreq, NETFS_UPLOAD_TO_SERVER,
+					    start, len, afs_upload_to_server_worker);
+	if (subreq)
+		netfs_queue_write_request(subreq);
 }
 
 /*
  * write some of the pending data back to the server
  */
-int afs_writepages(struct address_space *mapping,
-		   struct writeback_control *wbc)
+int afs_writepages(struct address_space *mapping, struct writeback_control *wbc)
 {
 	struct afs_vnode *vnode = AFS_FS_I(mapping->host);
-	loff_t start, next;
 	int ret;
 
-	_enter("");
-
 	/* We have to be careful as we can end up racing with setattr()
 	 * truncating the pagecache since the caller doesn't take a lock here
 	 * to prevent it.
@@ -712,68 +215,11 @@ int afs_writepages(struct address_space *mapping,
 	else if (!down_read_trylock(&vnode->validate_lock))
 		return 0;
 
-	if (wbc->range_cyclic) {
-		start = mapping->writeback_index * PAGE_SIZE;
-		ret = afs_writepages_region(mapping, wbc, start, LLONG_MAX,
-					    &next, false);
-		if (ret == 0) {
-			mapping->writeback_index = next / PAGE_SIZE;
-			if (start > 0 && wbc->nr_to_write > 0) {
-				ret = afs_writepages_region(mapping, wbc, 0,
-							    start, &next, false);
-				if (ret == 0)
-					mapping->writeback_index =
-						next / PAGE_SIZE;
-			}
-		}
-	} else if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) {
-		ret = afs_writepages_region(mapping, wbc, 0, LLONG_MAX,
-					    &next, false);
-		if (wbc->nr_to_write > 0 && ret == 0)
-			mapping->writeback_index = next / PAGE_SIZE;
-	} else {
-		ret = afs_writepages_region(mapping, wbc,
-					    wbc->range_start, wbc->range_end,
-					    &next, false);
-	}
-
+	ret = netfs_writepages(mapping, wbc);
 	up_read(&vnode->validate_lock);
-	_leave(" = %d", ret);
 	return ret;
 }
 
-/*
- * write to an AFS file
- */
-ssize_t afs_file_write(struct kiocb *iocb, struct iov_iter *from)
-{
-	struct afs_vnode *vnode = AFS_FS_I(file_inode(iocb->ki_filp));
-	struct afs_file *af = iocb->ki_filp->private_data;
-	ssize_t result;
-	size_t count = iov_iter_count(from);
-
-	_enter("{%llx:%llu},{%zu},",
-	       vnode->fid.vid, vnode->fid.vnode, count);
-
-	if (IS_SWAPFILE(&vnode->netfs.inode)) {
-		printk(KERN_INFO
-		       "AFS: Attempt to write to active swap file!\n");
-		return -EBUSY;
-	}
-
-	if (!count)
-		return 0;
-
-	result = afs_validate(vnode, af->key);
-	if (result < 0)
-		return result;
-
-	result = generic_file_write_iter(iocb, from);
-
-	_leave(" = %zd", result);
-	return result;
-}
-
 /*
  * flush any dirty pages for this process, and check for write errors.
  * - the return status from this call provides a reliable indication of
@@ -802,49 +248,11 @@ int afs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
  */
 vm_fault_t afs_page_mkwrite(struct vm_fault *vmf)
 {
-	struct folio *folio = page_folio(vmf->page);
 	struct file *file = vmf->vma->vm_file;
-	struct inode *inode = file_inode(file);
-	struct afs_vnode *vnode = AFS_FS_I(inode);
-	struct afs_file *af = file->private_data;
-	vm_fault_t ret = VM_FAULT_RETRY;
-
-	_enter("{{%llx:%llu}},{%lx}", vnode->fid.vid, vnode->fid.vnode, folio_index(folio));
-
-	afs_validate(vnode, af->key);
-
-	sb_start_pagefault(inode->i_sb);
-
-	/* Wait for the page to be written to the cache before we allow it to
-	 * be modified.  We then assume the entire page will need writing back.
-	 */
-#ifdef CONFIG_AFS_FSCACHE
-	if (folio_test_fscache(folio) &&
-	    folio_wait_fscache_killable(folio) < 0)
-		goto out;
-#endif
-
-	if (folio_wait_writeback_killable(folio))
-		goto out;
-
-	if (folio_lock_killable(folio) < 0)
-		goto out;
-
-	if (folio_wait_writeback_killable(folio) < 0) {
-		folio_unlock(folio);
-		goto out;
-	}
-
-	if (folio_test_dirty(folio))
-		trace_afs_folio_dirty(vnode, tracepoint_string("mkwrite+"), folio);
-	else
-		trace_afs_folio_dirty(vnode, tracepoint_string("mkwrite"), folio);
-	file_update_time(file);
 
-	ret = VM_FAULT_LOCKED;
-out:
-	sb_end_pagefault(inode->i_sb);
-	return ret;
+	if (afs_validate(AFS_FS_I(file_inode(file)), afs_file_key(file)) < 0)
+		return VM_FAULT_SIGBUS;
+	return netfs_page_mkwrite(vmf, NULL);
 }
 
 /*
@@ -874,60 +282,3 @@ void afs_prune_wb_keys(struct afs_vnode *vnode)
 		afs_put_wb_key(wbk);
 	}
 }
-
-/*
- * Clean up a page during invalidation.
- */
-int afs_launder_folio(struct folio *folio)
-{
-	struct afs_vnode *vnode = AFS_FS_I(folio_inode(folio));
-	struct iov_iter iter;
-	struct bio_vec bv;
-	unsigned long long fend, i_size = vnode->netfs.inode.i_size;
-	size_t len;
-	int ret = 0;
-
-	_enter("{%lx}", folio->index);
-
-	if (folio_clear_dirty_for_io(folio) && folio_pos(folio) < i_size) {
-		len = folio_size(folio);
-		fend = folio_pos(folio) + len;
-		if (vnode->netfs.inode.i_size < fend)
-			len = fend - i_size;
-
-		bvec_set_folio(&bv, folio, len, 0);
-		iov_iter_bvec(&iter, WRITE, &bv, 1, len);
-
-		trace_afs_folio_dirty(vnode, tracepoint_string("launder"), folio);
-		ret = afs_store_data(vnode, &iter, folio_pos(folio), true);
-	}
-
-	trace_afs_folio_dirty(vnode, tracepoint_string("laundered"), folio);
-	folio_wait_fscache(folio);
-	return ret;
-}
-
-/*
- * Deal with the completion of writing the data to the cache.
- */
-static void afs_write_to_cache_done(void *priv, ssize_t transferred_or_error,
-				    bool was_async)
-{
-	struct afs_vnode *vnode = priv;
-
-	if (IS_ERR_VALUE(transferred_or_error) &&
-	    transferred_or_error != -ENOBUFS)
-		afs_invalidate_cache(vnode, 0);
-}
-
-/*
- * Save the write to the cache also.
- */
-static void afs_write_to_cache(struct afs_vnode *vnode,
-			       loff_t start, size_t len, loff_t i_size,
-			       bool caching)
-{
-	fscache_write_to_cache(afs_vnode_cache(vnode),
-			       vnode->netfs.inode.i_mapping, start, len, i_size,
-			       afs_write_to_cache_done, vnode, caching);
-}
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index 08506680350c..754358149372 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -837,29 +837,6 @@ TRACE_EVENT(afs_dir_check_failed,
 		      __entry->vnode, __entry->off, __entry->i_size)
 	    );
 
-TRACE_EVENT(afs_folio_dirty,
-	    TP_PROTO(struct afs_vnode *vnode, const char *where, struct folio *folio),
-
-	    TP_ARGS(vnode, where, folio),
-
-	    TP_STRUCT__entry(
-		    __field(struct afs_vnode *,		vnode)
-		    __field(const char *,		where)
-		    __field(pgoff_t,			index)
-		    __field(size_t,			size)
-			     ),
-
-	    TP_fast_assign(
-		    __entry->vnode = vnode;
-		    __entry->where = where;
-		    __entry->index = folio_index(folio);
-		    __entry->size = folio_size(folio);
-			   ),
-
-	    TP_printk("vn=%p ix=%05lx s=%05lx %s",
-		      __entry->vnode, __entry->index, __entry->size, __entry->where)
-	    );
-
 TRACE_EVENT(afs_call_state,
 	    TP_PROTO(struct afs_call *call,
 		     enum afs_call_state from,
-- 
cgit v1.2.3


From c39e2ae3943d4ee278af4e1b1dcfd5946da1089b Mon Sep 17 00:00:00 2001
From: Vegard Nossum <vegard.nossum@oracle.com>
Date: Thu, 28 Dec 2023 11:06:08 +0100
Subject: fs: fix __sb_write_started() kerneldoc formatting

When running 'make htmldocs', I see the following warning:

  Documentation/filesystems/api-summary:14: ./include/linux/fs.h:1659: WARNING: Definition list ends without a blank line; unexpected unindent.

The official guidance [1] seems to be to use lists, which will prevent
both the "unexpected unindent" warning as well as ensure that each line
is formatted on a separate line in the HTML output instead of being
all considered a single paragraph.

[1]: https://docs.kernel.org/doc-guide/kernel-doc.html#return-values

Fixes: 8802e580ee64 ("fs: create __sb_write_started() helper")
Cc: Amir Goldstein <amir73il@gmail.com>
Cc: Josef Bacik <josef@toxicpanda.com>
Cc: Jan Kara <jack@suse.cz>
Signed-off-by: Vegard Nossum <vegard.nossum@oracle.com>
Link: https://lore.kernel.org/r/20231228100608.3123987-1-vegard.nossum@oracle.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/fs.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index db5d07e6e02e..473063f385e5 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1650,9 +1650,9 @@ static inline bool __sb_start_write_trylock(struct super_block *sb, int level)
  * @sb: the super we write to
  * @level: the freeze level
  *
- * > 0 sb freeze level is held
- *   0 sb freeze level is not held
- * < 0 !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN
+ * * > 0 - sb freeze level is held
+ * *   0 - sb freeze level is not held
+ * * < 0 - !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN
  */
 static inline int __sb_write_started(const struct super_block *sb, int level)
 {
-- 
cgit v1.2.3


From 0b68ab50b8101a35b51fb9ec203cd988e47dbed3 Mon Sep 17 00:00:00 2001
From: Thomas Weißschuh <linux@weissschuh.net>
Date: Sat, 23 Dec 2023 14:53:47 +0100
Subject: sysctl: delete unused define SYSCTL_PERM_EMPTY_DIR
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It seems it was never used.

Fixes: 2f2665c13af4 ("sysctl: replace child with an enumeration")
Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 include/linux/sysctl.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 61b40ea81f4d..26a38161c28f 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -255,8 +255,6 @@ extern int unaligned_enabled;
 extern int unaligned_dump_stack;
 extern int no_unaligned_warning;
 
-#define SYSCTL_PERM_EMPTY_DIR	(1 << 0)
-
 #else /* CONFIG_SYSCTL */
 
 static inline void register_sysctl_init(const char *path, struct ctl_table *table)
-- 
cgit v1.2.3


From 561429807d50aad76f1205b0b1d7b4aacf365d4e Mon Sep 17 00:00:00 2001
From: Thomas Weißschuh <linux@weissschuh.net>
Date: Wed, 20 Dec 2023 22:23:35 +0100
Subject: sysctl: remove struct ctl_path
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

All usages of this struct have been removed from the kernel tree.

The struct is still referenced by scripts/check-sysctl-docs but that
script is broken anyways as it only supports the register_sysctl_paths()
API and not the currently used register_sysctl() one.

Fixes: 0199849acd07 ("sysctl: remove register_sysctl_paths()")
Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Reviewed-by: Joel Granados <j.granados@samsung.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 include/linux/sysctl.h | 5 -----
 1 file changed, 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 26a38161c28f..ee7d33b89e9e 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -210,11 +210,6 @@ struct ctl_table_root {
 	int (*permissions)(struct ctl_table_header *head, struct ctl_table *table);
 };
 
-/* struct ctl_path describes where in the hierarchy a table is added */
-struct ctl_path {
-	const char *procname;
-};
-
 #define register_sysctl(path, table)	\
 	register_sysctl_sz(path, table, ARRAY_SIZE(table))
 
-- 
cgit v1.2.3


From 4e814173a8c4f432fd068b1c796f0416328c9d99 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Mon, 18 Dec 2023 20:25:02 +0100
Subject: thermal: core: Fix thermal zone suspend-resume synchronization

There are 3 synchronization issues with thermal zone suspend-resume
during system-wide transitions:

 1. The resume code runs in a PM notifier which is invoked after user
    space has been thawed, so it can run concurrently with user space
    which can trigger a thermal zone device removal.  If that happens,
    the thermal zone resume code may use a stale pointer to the next
    list element and crash, because it does not hold thermal_list_lock
    while walking thermal_tz_list.

 2. The thermal zone resume code calls thermal_zone_device_init()
    outside the zone lock, so user space or an update triggered by
    the platform firmware may see an inconsistent state of a
    thermal zone leading to unexpected behavior.

 3. Clearing the in_suspend global variable in thermal_pm_notify()
    allows __thermal_zone_device_update() to continue for all thermal
    zones and it may as well run before the thermal_tz_list walk (or
    at any point during the list walk for that matter) and attempt to
    operate on a thermal zone that has not been resumed yet.  It may
    also race destructively with thermal_zone_device_init().

To address these issues, add thermal_list_lock locking to
thermal_pm_notify(), especially arount the thermal_tz_list,
make it call thermal_zone_device_init() back-to-back with
__thermal_zone_device_update() under the zone lock and replace
in_suspend with per-zone bool "suspend" indicators set and unset
under the given zone's lock.

Link: https://lore.kernel.org/linux-pm/20231218162348.69101-1-bo.ye@mediatek.com/
Reported-by: Bo Ye <bo.ye@mediatek.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/thermal/thermal_core.c | 30 +++++++++++++++++++++++-------
 include/linux/thermal.h        |  2 ++
 2 files changed, 25 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 5e5fcbd81dda..7456335efaaa 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -37,8 +37,6 @@ static LIST_HEAD(thermal_governor_list);
 static DEFINE_MUTEX(thermal_list_lock);
 static DEFINE_MUTEX(thermal_governor_lock);
 
-static atomic_t in_suspend;
-
 static struct thermal_governor *def_governor;
 
 /*
@@ -431,7 +429,7 @@ void __thermal_zone_device_update(struct thermal_zone_device *tz,
 {
 	struct thermal_trip *trip;
 
-	if (atomic_read(&in_suspend))
+	if (tz->suspended)
 		return;
 
 	if (!thermal_zone_device_is_enabled(tz))
@@ -1542,17 +1540,35 @@ static int thermal_pm_notify(struct notifier_block *nb,
 	case PM_HIBERNATION_PREPARE:
 	case PM_RESTORE_PREPARE:
 	case PM_SUSPEND_PREPARE:
-		atomic_set(&in_suspend, 1);
+		mutex_lock(&thermal_list_lock);
+
+		list_for_each_entry(tz, &thermal_tz_list, node) {
+			mutex_lock(&tz->lock);
+
+			tz->suspended = true;
+
+			mutex_unlock(&tz->lock);
+		}
+
+		mutex_unlock(&thermal_list_lock);
 		break;
 	case PM_POST_HIBERNATION:
 	case PM_POST_RESTORE:
 	case PM_POST_SUSPEND:
-		atomic_set(&in_suspend, 0);
+		mutex_lock(&thermal_list_lock);
+
 		list_for_each_entry(tz, &thermal_tz_list, node) {
+			mutex_lock(&tz->lock);
+
+			tz->suspended = false;
+
 			thermal_zone_device_init(tz);
-			thermal_zone_device_update(tz,
-						   THERMAL_EVENT_UNSPECIFIED);
+			__thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED);
+
+			mutex_unlock(&tz->lock);
 		}
+
+		mutex_unlock(&thermal_list_lock);
 		break;
 	default:
 		break;
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 09f6eb82c191..d00622b64d50 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -152,6 +152,7 @@ struct thermal_cooling_device {
  * @node:	node in thermal_tz_list (in thermal_core.c)
  * @poll_queue:	delayed work for polling
  * @notify_event: Last notification event
+ * @suspended: thermal zone suspend indicator
  */
 struct thermal_zone_device {
 	int id;
@@ -185,6 +186,7 @@ struct thermal_zone_device {
 	struct list_head node;
 	struct delayed_work poll_queue;
 	enum thermal_notify_event notify_event;
+	bool suspended;
 };
 
 /**
-- 
cgit v1.2.3


From 753547de0daecbdbd1af3618987ddade325d9aaa Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Thu, 28 Dec 2023 11:36:03 +0100
Subject: linux/export: Ensure natural alignment of kcrctab array

The ___kcrctab section holds an array of 32-bit CRC values.
Add a .balign 4 to tell the linker the correct memory alignment.

Fixes: f3304ecd7f06 ("linux/export: use inline assembler to populate symbol CRCs")
Signed-off-by: Helge Deller <deller@gmx.de>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 include/linux/export-internal.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/export-internal.h b/include/linux/export-internal.h
index cd253eb51d6c..d445705ac13c 100644
--- a/include/linux/export-internal.h
+++ b/include/linux/export-internal.h
@@ -64,6 +64,7 @@
 
 #define SYMBOL_CRC(sym, crc, sec)   \
 	asm(".section \"___kcrctab" sec "+" #sym "\",\"a\""	"\n" \
+	    ".balign 4"						"\n" \
 	    "__crc_" #sym ":"					"\n" \
 	    ".long " #crc					"\n" \
 	    ".previous"						"\n")
-- 
cgit v1.2.3


From 144377c340f292c5d8c039eb790318754eec557e Mon Sep 17 00:00:00 2001
From: Jonathan Corbet <corbet@lwn.net>
Date: Tue, 19 Dec 2023 16:51:12 -0700
Subject: net: sock: remove excess structure-member documentation

Remove a couple of kerneldoc entries for struct members that do not exist,
addressing these warnings:

  ./include/net/sock.h:548: warning: Excess struct member '__sk_flags_offset' description in 'sock'
  ./include/net/sock.h:548: warning: Excess struct member 'sk_padding' description in 'sock'

Signed-off-by: Jonathan Corbet <corbet@lwn.net>
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include')

diff --git a/include/net/sock.h b/include/net/sock.h
index 30d3980dd57c..a7f815c7cfdf 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -264,8 +264,6 @@ struct sk_filter;
   *	@sk_pacing_status: Pacing status (requested, handled by sch_fq)
   *	@sk_max_pacing_rate: Maximum pacing rate (%SO_MAX_PACING_RATE)
   *	@sk_sndbuf: size of send buffer in bytes
-  *	@__sk_flags_offset: empty field used to determine location of bitfield
-  *	@sk_padding: unused element for alignment
   *	@sk_no_check_tx: %SO_NO_CHECK setting, set checksum in TX packets
   *	@sk_no_check_rx: allow zero checksum in RX packets
   *	@sk_route_caps: route capabilities (e.g. %NETIF_F_TSO)
-- 
cgit v1.2.3


From d0c3891db2d279b2f5ff8fd174e0b09e75dea039 Mon Sep 17 00:00:00 2001
From: Jonathan Corbet <corbet@lwn.net>
Date: Tue, 19 Dec 2023 16:53:46 -0700
Subject: ethtool: reformat kerneldoc for struct ethtool_link_settings

The kernel doc comments for struct ethtool_link_settings includes
documentation for three fields that were never present there, leading to
these docs-build warnings:

  ./include/uapi/linux/ethtool.h:2207: warning: Excess struct member 'supported' description in 'ethtool_link_settings'
  ./include/uapi/linux/ethtool.h:2207: warning: Excess struct member 'advertising' description in 'ethtool_link_settings'
  ./include/uapi/linux/ethtool.h:2207: warning: Excess struct member 'lp_advertising' description in 'ethtool_link_settings'

Remove the entries to make the warnings go away.  There was some
information there on how data in >link_mode_masks is formatted; move that
to the body of the comment to preserve it.

Signed-off-by: Jonathan Corbet <corbet@lwn.net>
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/ethtool.h | 27 +++++++++++++++------------
 1 file changed, 15 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 0787d561ace0..85c412c23ab5 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -2139,18 +2139,6 @@ enum ethtool_reset_flags {
  *	refused. For drivers: ignore this field (use kernel's
  *	__ETHTOOL_LINK_MODE_MASK_NBITS instead), any change to it will
  *	be overwritten by kernel.
- * @supported: Bitmap with each bit meaning given by
- *	%ethtool_link_mode_bit_indices for the link modes, physical
- *	connectors and other link features for which the interface
- *	supports autonegotiation or auto-detection.  Read-only.
- * @advertising: Bitmap with each bit meaning given by
- *	%ethtool_link_mode_bit_indices for the link modes, physical
- *	connectors and other link features that are advertised through
- *	autonegotiation or enabled for auto-detection.
- * @lp_advertising: Bitmap with each bit meaning given by
- *	%ethtool_link_mode_bit_indices for the link modes, and other
- *	link features that the link partner advertised through
- *	autonegotiation; 0 if unknown or not applicable.  Read-only.
  * @transceiver: Used to distinguish different possible PHY types,
  *	reported consistently by PHYLIB.  Read-only.
  * @master_slave_cfg: Master/slave port mode.
@@ -2192,6 +2180,21 @@ enum ethtool_reset_flags {
  * %set_link_ksettings() should validate all fields other than @cmd
  * and @link_mode_masks_nwords that are not described as read-only or
  * deprecated, and must ignore all fields described as read-only.
+ *
+ * @link_mode_masks is divided into three bitfields, each of length
+ * @link_mode_masks_nwords:
+ * - supported: Bitmap with each bit meaning given by
+ *	%ethtool_link_mode_bit_indices for the link modes, physical
+ *	connectors and other link features for which the interface
+ *	supports autonegotiation or auto-detection.  Read-only.
+ * - advertising: Bitmap with each bit meaning given by
+ *	%ethtool_link_mode_bit_indices for the link modes, physical
+ *	connectors and other link features that are advertised through
+ *	autonegotiation or enabled for auto-detection.
+ * - lp_advertising: Bitmap with each bit meaning given by
+ *	%ethtool_link_mode_bit_indices for the link modes, and other
+ *	link features that the link partner advertised through
+ *	autonegotiation; 0 if unknown or not applicable.  Read-only.
  */
 struct ethtool_link_settings {
 	__u32	cmd;
-- 
cgit v1.2.3


From 1271ca00aa7f9bb3fd94cb7ac8f654de71099580 Mon Sep 17 00:00:00 2001
From: Jonathan Corbet <corbet@lwn.net>
Date: Tue, 19 Dec 2023 16:55:31 -0700
Subject: ethtool: reformat kerneldoc for struct ethtool_fec_stats

The kerneldoc comment for struct ethtool_fec_stats attempts to describe the
"total" and "lanes" fields of the ethtool_fec_stat substructure in a way
leading to these warnings:

  ./include/linux/ethtool.h:424: warning: Excess struct member 'lane' description in 'ethtool_fec_stats'
  ./include/linux/ethtool.h:424: warning: Excess struct member 'total' description in 'ethtool_fec_stats'

Reformat the comment to retain the information while eliminating the
warnings.

Signed-off-by: Jonathan Corbet <corbet@lwn.net>
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ethtool.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index cfcd952a1d4f..325e0778e937 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -411,8 +411,10 @@ struct ethtool_pause_stats {
  *	not entire FEC data blocks. This is a non-standard statistic.
  *	Reported to user space as %ETHTOOL_A_FEC_STAT_CORR_BITS.
  *
- * @lane: per-lane/PCS-instance counts as defined by the standard
- * @total: error counts for the entire port, for drivers incapable of reporting
+ * For each of the above fields, the two substructure members are:
+ *
+ * - @lanes: per-lane/PCS-instance counts as defined by the standard
+ * - @total: error counts for the entire port, for drivers incapable of reporting
  *	per-lane stats
  *
  * Drivers should fill in either only total or per-lane statistics, core
-- 
cgit v1.2.3


From b590563e441c4ce7cf8e328ecd687c46bbe6529f Mon Sep 17 00:00:00 2001
From: Vegard Nossum <vegard.nossum@oracle.com>
Date: Sat, 23 Dec 2023 09:34:58 +0100
Subject: crypto: shash - remove excess kerneldoc members

Commit 42808e5dc602 ("crypto: hash - Count error stats differently")
moved some fields from 'struct shash_alg' into HASH_ALG_COMMON but
didn't remove the corresponding kerneldoc members, which results in
these warnings when running 'make htmldocs':

  ./include/crypto/hash.h:248: warning: Excess struct member 'digestsize' description in 'shash_alg'
  ./include/crypto/hash.h:248: warning: Excess struct member 'statesize' description in 'shash_alg'
  ./include/crypto/hash.h:248: warning: Excess struct member 'stat' description in 'shash_alg'
  ./include/crypto/hash.h:248: warning: Excess struct member 'base' description in 'shash_alg'

HASH_ALG_COMMON already has the documentation for all these fields.

Fixes: 42808e5dc602 ("crypto: hash - Count error stats differently")
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Vegard Nossum <vegard.nossum@oracle.com>
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/crypto/hash.h | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'include')

diff --git a/include/crypto/hash.h b/include/crypto/hash.h
index c7bdbece27cc..5d61f576cfc8 100644
--- a/include/crypto/hash.h
+++ b/include/crypto/hash.h
@@ -212,13 +212,9 @@ struct shash_desc {
  *	      This is a counterpart to @init_tfm, used to remove
  *	      various changes set in @init_tfm.
  * @clone_tfm: Copy transform into new object, may allocate memory.
- * @digestsize: see struct ahash_alg
- * @statesize: see struct ahash_alg
  * @descsize: Size of the operational state for the message digest. This state
  * 	      size is the memory size that needs to be allocated for
  *	      shash_desc.__ctx
- * @stat: Statistics for hash algorithm.
- * @base: internally used
  * @halg: see struct hash_alg_common
  * @HASH_ALG_COMMON: see struct hash_alg_common
  */
-- 
cgit v1.2.3


From 069579d0291cebda575a823ac1c85f0644e2ed95 Mon Sep 17 00:00:00 2001
From: Vegard Nossum <vegard.nossum@oracle.com>
Date: Sat, 23 Dec 2023 09:34:59 +0100
Subject: crypto: skcipher - remove excess kerneldoc members

Commit 31865c4c4db2 ("crypto: skcipher - Add lskcipher") moved some
fields from 'struct skcipher_alg' into SKCIPHER_ALG_COMMON but didn't
remove the corresponding kerneldoc members, which results in these
warnings when running 'make htmldocs':

  ./include/crypto/skcipher.h:182: warning: Excess struct member 'min_keysize' description in 'skcipher_alg'
  ./include/crypto/skcipher.h:182: warning: Excess struct member 'max_keysize' description in 'skcipher_alg'
  ./include/crypto/skcipher.h:182: warning: Excess struct member 'ivsize' description in 'skcipher_alg'
  ./include/crypto/skcipher.h:182: warning: Excess struct member 'chunksize' description in 'skcipher_alg'
  ./include/crypto/skcipher.h:182: warning: Excess struct member 'stat' description in 'skcipher_alg'
  ./include/crypto/skcipher.h:182: warning: Excess struct member 'base' description in 'skcipher_alg'

SKCIPHER_ALG_COMMON already has the documentation for all these fields.

Fixes: 31865c4c4db2 ("crypto: skcipher - Add lskcipher")
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Vegard Nossum <vegard.nossum@oracle.com>
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/crypto/skcipher.h | 16 ----------------
 1 file changed, 16 deletions(-)

(limited to 'include')

diff --git a/include/crypto/skcipher.h b/include/crypto/skcipher.h
index f881740df194..c8857d7bdb37 100644
--- a/include/crypto/skcipher.h
+++ b/include/crypto/skcipher.h
@@ -121,16 +121,6 @@ struct skcipher_alg_common SKCIPHER_ALG_COMMON;
 
 /**
  * struct skcipher_alg - symmetric key cipher definition
- * @min_keysize: Minimum key size supported by the transformation. This is the
- *		 smallest key length supported by this transformation algorithm.
- *		 This must be set to one of the pre-defined values as this is
- *		 not hardware specific. Possible values for this field can be
- *		 found via git grep "_MIN_KEY_SIZE" include/crypto/
- * @max_keysize: Maximum key size supported by the transformation. This is the
- *		 largest key length supported by this transformation algorithm.
- *		 This must be set to one of the pre-defined values as this is
- *		 not hardware specific. Possible values for this field can be
- *		 found via git grep "_MAX_KEY_SIZE" include/crypto/
  * @setkey: Set key for the transformation. This function is used to either
  *	    program a supplied key into the hardware or store the key in the
  *	    transformation context for programming it later. Note that this
@@ -176,15 +166,9 @@ struct skcipher_alg_common SKCIPHER_ALG_COMMON;
  * @exit: Deinitialize the cryptographic transformation object. This is a
  *	  counterpart to @init, used to remove various changes set in
  *	  @init.
- * @ivsize: IV size applicable for transformation. The consumer must provide an
- *	    IV of exactly that size to perform the encrypt or decrypt operation.
- * @chunksize: Equal to the block size except for stream ciphers such as
- *	       CTR where it is set to the underlying block size.
  * @walksize: Equal to the chunk size except in cases where the algorithm is
  * 	      considerably more efficient if it can operate on multiple chunks
  * 	      in parallel. Should be a multiple of chunksize.
- * @stat: Statistics for cipher algorithm
- * @base: Definition of a generic crypto algorithm.
  * @co: see struct skcipher_alg_common
  *
  * All fields except @ivsize are mandatory and must be filled.
-- 
cgit v1.2.3


From f732ba4ac9f3626e235cc33a4f1756f17884dd32 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Wed, 20 Dec 2023 08:41:18 +0100
Subject: iucv: make iucv_bus const

Now that the driver core can properly handle constant struct bus_type,
move the iucv_bus variable to be a constant structure as well, placing
it into read-only memory which can not be modified at runtime.

Cc: Wenjia Zhang <wenjia@linux.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: linux-s390@vger.kernel.org
Cc: netdev@vger.kernel.org
Acked-by: Alexandra Winter <wintera@linux.ibm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/iucv/iucv.h | 4 ++--
 net/iucv/iucv.c         | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/iucv/iucv.h b/include/net/iucv/iucv.h
index f9e88401d7da..8b2055d64a6b 100644
--- a/include/net/iucv/iucv.h
+++ b/include/net/iucv/iucv.h
@@ -80,7 +80,7 @@ struct iucv_array {
 	u32 length;
 } __attribute__ ((aligned (8)));
 
-extern struct bus_type iucv_bus;
+extern const struct bus_type iucv_bus;
 extern struct device *iucv_root;
 
 /*
@@ -489,7 +489,7 @@ struct iucv_interface {
 	int (*path_sever)(struct iucv_path *path, u8 userdata[16]);
 	int (*iucv_register)(struct iucv_handler *handler, int smp);
 	void (*iucv_unregister)(struct iucv_handler *handler, int smp);
-	struct bus_type *bus;
+	const struct bus_type *bus;
 	struct device *root;
 };
 
diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c
index 0ed6e34d6edd..6334f64f04d5 100644
--- a/net/iucv/iucv.c
+++ b/net/iucv/iucv.c
@@ -67,7 +67,7 @@ static int iucv_bus_match(struct device *dev, struct device_driver *drv)
 	return 0;
 }
 
-struct bus_type iucv_bus = {
+const struct bus_type iucv_bus = {
 	.name = "iucv",
 	.match = iucv_bus_match,
 };
-- 
cgit v1.2.3


From cd4d7263d58ab98fd4dee876776e4da6c328faa3 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 20 Dec 2023 17:43:58 +0200
Subject: genetlink: Use internal flags for multicast groups

As explained in commit e03781879a0d ("drop_monitor: Require
'CAP_SYS_ADMIN' when joining "events" group"), the "flags" field in the
multicast group structure reuses uAPI flags despite the field not being
exposed to user space. This makes it impossible to extend its use
without adding new uAPI flags, which is inappropriate for internal
kernel checks.

Solve this by adding internal flags (i.e., "GENL_MCAST_*") and convert
the existing users to use them instead of the uAPI flags.

Tested using the reproducers in commit 44ec98ea5ea9 ("psample: Require
'CAP_NET_ADMIN' when joining "packets" group") and commit e03781879a0d
("drop_monitor: Require 'CAP_SYS_ADMIN' when joining "events" group").

No functional changes intended.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/genetlink.h | 9 ++++++---
 net/core/drop_monitor.c | 2 +-
 net/mptcp/pm_netlink.c  | 2 +-
 net/netlink/genetlink.c | 4 ++--
 net/psample/psample.c   | 2 +-
 5 files changed, 11 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 85c63d4f16dd..e61469129402 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -8,16 +8,19 @@
 
 #define GENLMSG_DEFAULT_SIZE (NLMSG_DEFAULT_SIZE - GENL_HDRLEN)
 
+/* Binding to multicast group requires %CAP_NET_ADMIN */
+#define GENL_MCAST_CAP_NET_ADMIN	BIT(0)
+/* Binding to multicast group requires %CAP_SYS_ADMIN */
+#define GENL_MCAST_CAP_SYS_ADMIN	BIT(1)
+
 /**
  * struct genl_multicast_group - generic netlink multicast group
  * @name: name of the multicast group, names are per-family
- * @flags: GENL_* flags (%GENL_ADMIN_PERM or %GENL_UNS_ADMIN_PERM)
- * @cap_sys_admin: whether %CAP_SYS_ADMIN is required for binding
+ * @flags: GENL_MCAST_* flags
  */
 struct genl_multicast_group {
 	char			name[GENL_NAMSIZ];
 	u8			flags;
-	u8			cap_sys_admin:1;
 };
 
 struct genl_split_ops;
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index b240d9aae4a6..b0f221d658be 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -183,7 +183,7 @@ out:
 }
 
 static const struct genl_multicast_group dropmon_mcgrps[] = {
-	{ .name = "events", .cap_sys_admin = 1 },
+	{ .name = "events", .flags = GENL_MCAST_CAP_SYS_ADMIN, },
 };
 
 static void send_dm_alert(struct work_struct *work)
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index bf4d96f6f99a..272e93be1aad 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1100,7 +1100,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc
 static const struct genl_multicast_group mptcp_pm_mcgrps[] = {
 	[MPTCP_PM_CMD_GRP_OFFSET]	= { .name = MPTCP_PM_CMD_GRP_NAME, },
 	[MPTCP_PM_EV_GRP_OFFSET]        = { .name = MPTCP_PM_EV_GRP_NAME,
-					    .flags = GENL_UNS_ADMIN_PERM,
+					    .flags = GENL_MCAST_CAP_NET_ADMIN,
 					  },
 };
 
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index c0d15470a10b..8c7af02f8454 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -1829,10 +1829,10 @@ static int genl_bind(struct net *net, int group)
 			continue;
 
 		grp = &family->mcgrps[i];
-		if ((grp->flags & GENL_UNS_ADMIN_PERM) &&
+		if ((grp->flags & GENL_MCAST_CAP_NET_ADMIN) &&
 		    !ns_capable(net->user_ns, CAP_NET_ADMIN))
 			ret = -EPERM;
-		if (grp->cap_sys_admin &&
+		if ((grp->flags & GENL_MCAST_CAP_SYS_ADMIN) &&
 		    !ns_capable(net->user_ns, CAP_SYS_ADMIN))
 			ret = -EPERM;
 
diff --git a/net/psample/psample.c b/net/psample/psample.c
index c34e902855db..ddd211a151d0 100644
--- a/net/psample/psample.c
+++ b/net/psample/psample.c
@@ -32,7 +32,7 @@ enum psample_nl_multicast_groups {
 static const struct genl_multicast_group psample_nl_mcgrps[] = {
 	[PSAMPLE_NL_MCGRP_CONFIG] = { .name = PSAMPLE_NL_MCGRP_CONFIG_NAME },
 	[PSAMPLE_NL_MCGRP_SAMPLE] = { .name = PSAMPLE_NL_MCGRP_SAMPLE_NAME,
-				      .flags = GENL_UNS_ADMIN_PERM },
+				      .flags = GENL_MCAST_CAP_NET_ADMIN, },
 };
 
 static struct genl_family psample_nl_family __ro_after_init;
-- 
cgit v1.2.3


From 337b2f0e778f78f61972497994b70a05e8f6447d Mon Sep 17 00:00:00 2001
From: "Geoffrey D. Bennett" <g@b4.vu>
Date: Wed, 20 Dec 2023 04:09:23 +1030
Subject: ALSA: scarlett2: Add skeleton hwdep/ioctl interface

Add skeleton hwdep/ioctl interface, beginning with
SCARLETT2_IOCTL_PVERSION and SCARLETT2_IOCTL_REBOOT.

Signed-off-by: Geoffrey D. Bennett <g@b4.vu>
Link: https://lore.kernel.org/r/24ffcd47a8a02ebad3c8b2438104af8f0169164e.1703001053.git.g@b4.vu
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 MAINTAINERS                    |  1 +
 include/uapi/sound/scarlett2.h | 34 +++++++++++++++++++++
 sound/usb/mixer_scarlett2.c    | 67 +++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 101 insertions(+), 1 deletion(-)
 create mode 100644 include/uapi/sound/scarlett2.h

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index ae3f72f57854..80c65096538c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8279,6 +8279,7 @@ S:	Maintained
 W:	https://github.com/geoffreybennett/scarlett-gen2
 B:	https://github.com/geoffreybennett/scarlett-gen2/issues
 T:	git https://github.com/geoffreybennett/scarlett-gen2.git
+F:	include/uapi/sound/scarlett2.h
 F:	sound/usb/mixer_scarlett2.c
 
 FORCEDETH GIGABIT ETHERNET DRIVER
diff --git a/include/uapi/sound/scarlett2.h b/include/uapi/sound/scarlett2.h
new file mode 100644
index 000000000000..ec0b7da335ff
--- /dev/null
+++ b/include/uapi/sound/scarlett2.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ *   Focusrite Scarlett 2 Protocol Driver for ALSA
+ *   (including Scarlett 2nd Gen, 3rd Gen, Clarett USB, and Clarett+
+ *   series products)
+ *
+ *   Copyright (c) 2023 by Geoffrey D. Bennett <g at b4.vu>
+ */
+#ifndef __UAPI_SOUND_SCARLETT2_H
+#define __UAPI_SOUND_SCARLETT2_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+#define SCARLETT2_HWDEP_MAJOR 1
+#define SCARLETT2_HWDEP_MINOR 0
+#define SCARLETT2_HWDEP_SUBMINOR 0
+
+#define SCARLETT2_HWDEP_VERSION \
+	((SCARLETT2_HWDEP_MAJOR << 16) | \
+	 (SCARLETT2_HWDEP_MINOR << 8) | \
+	  SCARLETT2_HWDEP_SUBMINOR)
+
+#define SCARLETT2_HWDEP_VERSION_MAJOR(v) (((v) >> 16) & 0xFF)
+#define SCARLETT2_HWDEP_VERSION_MINOR(v) (((v) >> 8) & 0xFF)
+#define SCARLETT2_HWDEP_VERSION_SUBMINOR(v) ((v) & 0xFF)
+
+/* Get protocol version */
+#define SCARLETT2_IOCTL_PVERSION _IOR('S', 0x60, int)
+
+/* Reboot */
+#define SCARLETT2_IOCTL_REBOOT _IO('S', 0x61)
+
+#endif /* __UAPI_SOUND_SCARLETT2_H */
diff --git a/sound/usb/mixer_scarlett2.c b/sound/usb/mixer_scarlett2.c
index b62fc0038671..d27628e4bda8 100644
--- a/sound/usb/mixer_scarlett2.c
+++ b/sound/usb/mixer_scarlett2.c
@@ -146,6 +146,9 @@
 
 #include <sound/control.h>
 #include <sound/tlv.h>
+#include <sound/hwdep.h>
+
+#include <uapi/sound/scarlett2.h>
 
 #include "usbaudio.h"
 #include "mixer.h"
@@ -1439,6 +1442,16 @@ static int scarlett2_usb(
 	/* validate the response */
 
 	if (err != resp_buf_size) {
+
+		/* ESHUTDOWN and EPROTO are valid responses to a
+		 * reboot request
+		 */
+		if (cmd == SCARLETT2_USB_REBOOT &&
+		    (err == -ESHUTDOWN || err == -EPROTO)) {
+			err = 0;
+			goto unlock;
+		}
+
 		usb_audio_err(
 			mixer->chip,
 			"%s USB response result cmd %x was %d expected %zu\n",
@@ -4697,6 +4710,49 @@ static int snd_scarlett2_controls_create(
 	return 0;
 }
 
+/*** hwdep interface ***/
+
+/* Reboot the device. */
+static int scarlett2_reboot(struct usb_mixer_interface *mixer)
+{
+	return scarlett2_usb(mixer, SCARLETT2_USB_REBOOT, NULL, 0, NULL, 0);
+}
+
+static int scarlett2_hwdep_ioctl(struct snd_hwdep *hw, struct file *file,
+				 unsigned int cmd, unsigned long arg)
+{
+	struct usb_mixer_interface *mixer = hw->private_data;
+
+	switch (cmd) {
+
+	case SCARLETT2_IOCTL_PVERSION:
+		return put_user(SCARLETT2_HWDEP_VERSION,
+				(int __user *)arg) ? -EFAULT : 0;
+
+	case SCARLETT2_IOCTL_REBOOT:
+		return scarlett2_reboot(mixer);
+
+	default:
+		return -ENOIOCTLCMD;
+	}
+}
+
+static int scarlett2_hwdep_init(struct usb_mixer_interface *mixer)
+{
+	struct snd_hwdep *hw;
+	int err;
+
+	err = snd_hwdep_new(mixer->chip->card, "Focusrite Control", 0, &hw);
+	if (err < 0)
+		return err;
+
+	hw->private_data = mixer;
+	hw->exclusive = 1;
+	hw->ops.ioctl = scarlett2_hwdep_ioctl;
+
+	return 0;
+}
+
 int snd_scarlett2_init(struct usb_mixer_interface *mixer)
 {
 	struct snd_usb_audio *chip = mixer->chip;
@@ -4738,11 +4794,20 @@ int snd_scarlett2_init(struct usb_mixer_interface *mixer)
 		USB_ID_PRODUCT(chip->usb_id));
 
 	err = snd_scarlett2_controls_create(mixer, entry);
-	if (err < 0)
+	if (err < 0) {
 		usb_audio_err(mixer->chip,
 			      "Error initialising %s Mixer Driver: %d",
 			      entry->series_name,
 			      err);
+		return err;
+	}
+
+	err = scarlett2_hwdep_init(mixer);
+	if (err < 0)
+		usb_audio_err(mixer->chip,
+			      "Error creating %s hwdep device: %d",
+			      entry->series_name,
+			      err);
 
 	return err;
 }
-- 
cgit v1.2.3


From 6a7508e64ee3e8320c886020bcdcd70f7fcbff2c Mon Sep 17 00:00:00 2001
From: "Geoffrey D. Bennett" <g@b4.vu>
Date: Wed, 20 Dec 2023 04:20:29 +1030
Subject: ALSA: scarlett2: Add ioctl commands to erase flash segments

Add ioctls:
- SCARLETT2_IOCTL_SELECT_FLASH_SEGMENT
- SCARLETT2_IOCTL_ERASE_FLASH_SEGMENT
- SCARLETT2_IOCTL_GET_ERASE_PROGRESS

The settings or the firmware flash segment can be selected and then
erased (asynchronous operation), and the erase progress can be
monitored.

If the erase progress is not monitored, then subsequent hwdep
operations will block until the erase is complete.

Once the erase is started, ALSA controls that communicate with the
device will all return -EBUSY, and the device must be rebooted.

Signed-off-by: Geoffrey D. Bennett <g@b4.vu>
Link: https://lore.kernel.org/r/227409adb672f174bf3db211e9bda016fb4646ea.1703001053.git.g@b4.vu
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/uapi/sound/scarlett2.h |  20 ++
 sound/usb/mixer_scarlett2.c    | 428 ++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 442 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/uapi/sound/scarlett2.h b/include/uapi/sound/scarlett2.h
index ec0b7da335ff..d0ff38ffa154 100644
--- a/include/uapi/sound/scarlett2.h
+++ b/include/uapi/sound/scarlett2.h
@@ -31,4 +31,24 @@
 /* Reboot */
 #define SCARLETT2_IOCTL_REBOOT _IO('S', 0x61)
 
+/* Select flash segment */
+#define SCARLETT2_SEGMENT_ID_SETTINGS 0
+#define SCARLETT2_SEGMENT_ID_FIRMWARE 1
+#define SCARLETT2_SEGMENT_ID_COUNT 2
+
+#define SCARLETT2_IOCTL_SELECT_FLASH_SEGMENT _IOW('S', 0x62, int)
+
+/* Erase selected flash segment */
+#define SCARLETT2_IOCTL_ERASE_FLASH_SEGMENT _IO('S', 0x63)
+
+/* Get selected flash segment erase progress
+ * 1 through to num_blocks, or 255 for complete
+ */
+struct scarlett2_flash_segment_erase_progress {
+	unsigned char progress;
+	unsigned char num_blocks;
+};
+#define SCARLETT2_IOCTL_GET_ERASE_PROGRESS \
+	_IOR('S', 0x64, struct scarlett2_flash_segment_erase_progress)
+
 #endif /* __UAPI_SOUND_SCARLETT2_H */
diff --git a/sound/usb/mixer_scarlett2.c b/sound/usb/mixer_scarlett2.c
index d27628e4bda8..2d60fa607bd8 100644
--- a/sound/usb/mixer_scarlett2.c
+++ b/sound/usb/mixer_scarlett2.c
@@ -193,11 +193,6 @@ static const u16 scarlett2_mixer_values[SCARLETT2_MIXER_VALUE_COUNT] = {
 	16345
 };
 
-/* Flash segments that we may manipulate */
-#define SCARLETT2_SEGMENT_ID_SETTINGS 0
-#define SCARLETT2_SEGMENT_ID_FIRMWARE 1
-#define SCARLETT2_SEGMENT_ID_COUNT 2
-
 /* Maximum number of analogue outputs */
 #define SCARLETT2_ANALOGUE_MAX 10
 
@@ -267,6 +262,13 @@ enum {
 	SCARLETT2_DIM_MUTE_COUNT = 2,
 };
 
+/* Flash Write State */
+enum {
+	SCARLETT2_FLASH_WRITE_STATE_IDLE = 0,
+	SCARLETT2_FLASH_WRITE_STATE_SELECTED = 1,
+	SCARLETT2_FLASH_WRITE_STATE_ERASING = 2
+};
+
 static const char *const scarlett2_dim_mute_names[SCARLETT2_DIM_MUTE_COUNT] = {
 	"Mute Playback Switch", "Dim Playback Switch"
 };
@@ -427,6 +429,9 @@ struct scarlett2_data {
 	struct usb_mixer_interface *mixer;
 	struct mutex usb_mutex; /* prevent sending concurrent USB requests */
 	struct mutex data_mutex; /* lock access to this data */
+	u8 hwdep_in_use;
+	u8 selected_flash_segment_id;
+	u8 flash_write_state;
 	struct delayed_work work;
 	const struct scarlett2_device_info *info;
 	const char *series_name;
@@ -2137,6 +2142,11 @@ static int scarlett2_sync_ctl_get(struct snd_kcontrol *kctl,
 
 	mutex_lock(&private->data_mutex);
 
+	if (private->hwdep_in_use) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
 	if (private->sync_updated) {
 		err = scarlett2_update_sync(mixer);
 		if (err < 0)
@@ -2233,6 +2243,11 @@ static int scarlett2_master_volume_ctl_get(struct snd_kcontrol *kctl,
 
 	mutex_lock(&private->data_mutex);
 
+	if (private->hwdep_in_use) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
 	if (private->vol_updated) {
 		err = scarlett2_update_volumes(mixer);
 		if (err < 0)
@@ -2272,6 +2287,11 @@ static int scarlett2_volume_ctl_get(struct snd_kcontrol *kctl,
 
 	mutex_lock(&private->data_mutex);
 
+	if (private->hwdep_in_use) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
 	if (private->vol_updated) {
 		err = scarlett2_update_volumes(mixer);
 		if (err < 0)
@@ -2295,6 +2315,11 @@ static int scarlett2_volume_ctl_put(struct snd_kcontrol *kctl,
 
 	mutex_lock(&private->data_mutex);
 
+	if (private->hwdep_in_use) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
 	oval = private->vol[index];
 	val = ucontrol->value.integer.value[0];
 
@@ -2352,6 +2377,11 @@ static int scarlett2_mute_ctl_get(struct snd_kcontrol *kctl,
 
 	mutex_lock(&private->data_mutex);
 
+	if (private->hwdep_in_use) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
 	if (private->vol_updated) {
 		err = scarlett2_update_volumes(mixer);
 		if (err < 0)
@@ -2375,6 +2405,11 @@ static int scarlett2_mute_ctl_put(struct snd_kcontrol *kctl,
 
 	mutex_lock(&private->data_mutex);
 
+	if (private->hwdep_in_use) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
 	oval = private->mute_switch[index];
 	val = !!ucontrol->value.integer.value[0];
 
@@ -2514,6 +2549,11 @@ static int scarlett2_sw_hw_enum_ctl_put(struct snd_kcontrol *kctl,
 
 	mutex_lock(&private->data_mutex);
 
+	if (private->hwdep_in_use) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
 	oval = private->vol_sw_hw_switch[index];
 	val = !!ucontrol->value.enumerated.item[0];
 
@@ -2611,6 +2651,11 @@ static int scarlett2_level_enum_ctl_get(struct snd_kcontrol *kctl,
 
 	mutex_lock(&private->data_mutex);
 
+	if (private->hwdep_in_use) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
 	if (private->input_other_updated) {
 		err = scarlett2_update_input_other(mixer);
 		if (err < 0)
@@ -2636,6 +2681,11 @@ static int scarlett2_level_enum_ctl_put(struct snd_kcontrol *kctl,
 
 	mutex_lock(&private->data_mutex);
 
+	if (private->hwdep_in_use) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
 	oval = private->level_switch[index];
 	val = !!ucontrol->value.enumerated.item[0];
 
@@ -2675,6 +2725,11 @@ static int scarlett2_pad_ctl_get(struct snd_kcontrol *kctl,
 
 	mutex_lock(&private->data_mutex);
 
+	if (private->hwdep_in_use) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
 	if (private->input_other_updated) {
 		err = scarlett2_update_input_other(mixer);
 		if (err < 0)
@@ -2700,6 +2755,11 @@ static int scarlett2_pad_ctl_put(struct snd_kcontrol *kctl,
 
 	mutex_lock(&private->data_mutex);
 
+	if (private->hwdep_in_use) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
 	oval = private->pad_switch[index];
 	val = !!ucontrol->value.integer.value[0];
 
@@ -2739,6 +2799,11 @@ static int scarlett2_air_ctl_get(struct snd_kcontrol *kctl,
 
 	mutex_lock(&private->data_mutex);
 
+	if (private->hwdep_in_use) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
 	if (private->input_other_updated) {
 		err = scarlett2_update_input_other(mixer);
 		if (err < 0)
@@ -2763,6 +2828,11 @@ static int scarlett2_air_ctl_put(struct snd_kcontrol *kctl,
 
 	mutex_lock(&private->data_mutex);
 
+	if (private->hwdep_in_use) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
 	oval = private->air_switch[index];
 	val = !!ucontrol->value.integer.value[0];
 
@@ -2802,6 +2872,11 @@ static int scarlett2_phantom_ctl_get(struct snd_kcontrol *kctl,
 
 	mutex_lock(&private->data_mutex);
 
+	if (private->hwdep_in_use) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
 	if (private->input_other_updated) {
 		err = scarlett2_update_input_other(mixer);
 		if (err < 0)
@@ -2827,6 +2902,11 @@ static int scarlett2_phantom_ctl_put(struct snd_kcontrol *kctl,
 
 	mutex_lock(&private->data_mutex);
 
+	if (private->hwdep_in_use) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
 	oval = private->phantom_switch[index];
 	val = !!ucontrol->value.integer.value[0];
 
@@ -2878,6 +2958,11 @@ static int scarlett2_phantom_persistence_ctl_put(
 
 	mutex_lock(&private->data_mutex);
 
+	if (private->hwdep_in_use) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
 	oval = private->phantom_persistence;
 	val = !!ucontrol->value.integer.value[0];
 
@@ -2988,6 +3073,11 @@ static int scarlett2_direct_monitor_ctl_get(
 
 	mutex_lock(&private->data_mutex);
 
+	if (private->hwdep_in_use) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
 	if (private->monitor_other_updated) {
 		err = scarlett2_update_monitor_other(mixer);
 		if (err < 0)
@@ -3012,6 +3102,11 @@ static int scarlett2_direct_monitor_ctl_put(
 
 	mutex_lock(&private->data_mutex);
 
+	if (private->hwdep_in_use) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
 	oval = private->direct_monitor_switch;
 	val = min(ucontrol->value.enumerated.item[0], 2U);
 
@@ -3101,6 +3196,11 @@ static int scarlett2_speaker_switch_enum_ctl_get(
 
 	mutex_lock(&private->data_mutex);
 
+	if (private->hwdep_in_use) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
 	if (private->monitor_other_updated) {
 		err = scarlett2_update_monitor_other(mixer);
 		if (err < 0)
@@ -3181,6 +3281,11 @@ static int scarlett2_speaker_switch_enum_ctl_put(
 
 	mutex_lock(&private->data_mutex);
 
+	if (private->hwdep_in_use) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
 	oval = private->speaker_switching_switch;
 	val = min(ucontrol->value.enumerated.item[0], 2U);
 
@@ -3262,6 +3367,11 @@ static int scarlett2_talkback_enum_ctl_get(
 
 	mutex_lock(&private->data_mutex);
 
+	if (private->hwdep_in_use) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
 	if (private->monitor_other_updated) {
 		err = scarlett2_update_monitor_other(mixer);
 		if (err < 0)
@@ -3285,6 +3395,11 @@ static int scarlett2_talkback_enum_ctl_put(
 
 	mutex_lock(&private->data_mutex);
 
+	if (private->hwdep_in_use) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
 	oval = private->talkback_switch;
 	val = min(ucontrol->value.enumerated.item[0], 2U);
 
@@ -3349,6 +3464,11 @@ static int scarlett2_talkback_map_ctl_put(
 
 	mutex_lock(&private->data_mutex);
 
+	if (private->hwdep_in_use) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
 	oval = private->talkback_map[index];
 	val = !!ucontrol->value.integer.value[0];
 
@@ -3423,6 +3543,11 @@ static int scarlett2_dim_mute_ctl_get(struct snd_kcontrol *kctl,
 
 	mutex_lock(&private->data_mutex);
 
+	if (private->hwdep_in_use) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
 	if (private->vol_updated) {
 		err = scarlett2_update_volumes(mixer);
 		if (err < 0)
@@ -3451,6 +3576,11 @@ static int scarlett2_dim_mute_ctl_put(struct snd_kcontrol *kctl,
 
 	mutex_lock(&private->data_mutex);
 
+	if (private->hwdep_in_use) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
 	oval = private->dim_mute[index];
 	val = !!ucontrol->value.integer.value[0];
 
@@ -3695,6 +3825,11 @@ static int scarlett2_mixer_ctl_put(struct snd_kcontrol *kctl,
 
 	mutex_lock(&private->data_mutex);
 
+	if (private->hwdep_in_use) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
 	oval = private->mix[index];
 	val = clamp(ucontrol->value.integer.value[0],
 		    0L, (long)SCARLETT2_MIXER_MAX_VALUE);
@@ -3808,6 +3943,11 @@ static int scarlett2_mux_src_enum_ctl_get(struct snd_kcontrol *kctl,
 
 	mutex_lock(&private->data_mutex);
 
+	if (private->hwdep_in_use) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
 	if (private->mux_updated) {
 		err = scarlett2_usb_get_mux(mixer);
 		if (err < 0)
@@ -3831,6 +3971,11 @@ static int scarlett2_mux_src_enum_ctl_put(struct snd_kcontrol *kctl,
 
 	mutex_lock(&private->data_mutex);
 
+	if (private->hwdep_in_use) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
 	oval = private->mux[index];
 	val = min(ucontrol->value.enumerated.item[0],
 		  private->num_mux_srcs - 1U);
@@ -3915,6 +4060,11 @@ static int scarlett2_meter_ctl_get(struct snd_kcontrol *kctl,
 
 	mutex_lock(&private->data_mutex);
 
+	if (private->hwdep_in_use) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
 	err = scarlett2_usb_get_meter_levels(elem->head.mixer, elem->channels,
 					     meter_levels);
 	if (err < 0)
@@ -3983,6 +4133,11 @@ static int scarlett2_msd_ctl_put(struct snd_kcontrol *kctl,
 
 	mutex_lock(&private->data_mutex);
 
+	if (private->hwdep_in_use) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
 	oval = private->msd_switch;
 	val = !!ucontrol->value.integer.value[0];
 
@@ -4050,6 +4205,11 @@ static int scarlett2_standalone_ctl_put(struct snd_kcontrol *kctl,
 
 	mutex_lock(&private->data_mutex);
 
+	if (private->hwdep_in_use) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
 	oval = private->standalone_switch;
 	val = !!ucontrol->value.integer.value[0];
 
@@ -4712,12 +4872,241 @@ static int snd_scarlett2_controls_create(
 
 /*** hwdep interface ***/
 
-/* Reboot the device. */
+/* Set private->hwdep_in_use; prevents access to the ALSA controls
+ * while doing a config erase/firmware upgrade.
+ */
+static void scarlett2_lock(struct scarlett2_data *private)
+{
+	mutex_lock(&private->data_mutex);
+	private->hwdep_in_use = 1;
+	mutex_unlock(&private->data_mutex);
+}
+
+/* Call SCARLETT2_USB_GET_ERASE to get the erase progress */
+static int scarlett2_get_erase_progress(struct usb_mixer_interface *mixer)
+{
+	struct scarlett2_data *private = mixer->private_data;
+	int segment_id, segment_num, err;
+	u8 erase_resp;
+
+	struct {
+		__le32 segment_num;
+		__le32 pad;
+	} __packed erase_req;
+
+	segment_id = private->selected_flash_segment_id;
+	segment_num = private->flash_segment_nums[segment_id];
+
+	if (segment_num < SCARLETT2_SEGMENT_NUM_MIN ||
+	    segment_num > SCARLETT2_SEGMENT_NUM_MAX)
+		return -EFAULT;
+
+	/* Send the erase progress request */
+	erase_req.segment_num = cpu_to_le32(segment_num);
+	erase_req.pad = 0;
+
+	err = scarlett2_usb(mixer, SCARLETT2_USB_GET_ERASE,
+			    &erase_req, sizeof(erase_req),
+			    &erase_resp, sizeof(erase_resp));
+	if (err < 0)
+		return err;
+
+	return erase_resp;
+}
+
+/* Repeatedly call scarlett2_get_erase_progress() until it returns
+ * 0xff (erase complete) or we've waited 10 seconds (it usually takes
+ * <3 seconds).
+ */
+static int scarlett2_wait_for_erase(struct usb_mixer_interface *mixer)
+{
+	int i, err;
+
+	for (i = 0; i < 100; i++) {
+		err = scarlett2_get_erase_progress(mixer);
+		if (err < 0)
+			return err;
+
+		if (err == 0xff)
+			return 0;
+
+		msleep(100);
+	}
+
+	return -ETIMEDOUT;
+}
+
+/* Reboot the device; wait for the erase to complete if one is in
+ * progress.
+ */
 static int scarlett2_reboot(struct usb_mixer_interface *mixer)
 {
+	struct scarlett2_data *private = mixer->private_data;
+
+	if (private->flash_write_state ==
+	      SCARLETT2_FLASH_WRITE_STATE_ERASING) {
+		int err = scarlett2_wait_for_erase(mixer);
+
+		if (err < 0)
+			return err;
+	}
+
 	return scarlett2_usb(mixer, SCARLETT2_USB_REBOOT, NULL, 0, NULL, 0);
 }
 
+/* Select a flash segment for erasing (and possibly writing to) */
+static int scarlett2_ioctl_select_flash_segment(
+	struct usb_mixer_interface *mixer,
+	unsigned long arg)
+{
+	struct scarlett2_data *private = mixer->private_data;
+	int segment_id, segment_num;
+
+	if (get_user(segment_id, (int __user *)arg))
+		return -EFAULT;
+
+	/* Check the segment ID and segment number */
+	if (segment_id < 0 || segment_id >= SCARLETT2_SEGMENT_ID_COUNT)
+		return -EINVAL;
+
+	segment_num = private->flash_segment_nums[segment_id];
+	if (segment_num < SCARLETT2_SEGMENT_NUM_MIN ||
+	    segment_num > SCARLETT2_SEGMENT_NUM_MAX) {
+		usb_audio_err(mixer->chip,
+			      "%s: invalid segment number %d\n",
+			      __func__, segment_id);
+		return -EFAULT;
+	}
+
+	/* If erasing, wait for it to complete */
+	if (private->flash_write_state == SCARLETT2_FLASH_WRITE_STATE_ERASING) {
+		int err = scarlett2_wait_for_erase(mixer);
+
+		if (err < 0)
+			return err;
+	}
+
+	/* Save the selected segment ID and set the state to SELECTED */
+	private->selected_flash_segment_id = segment_id;
+	private->flash_write_state = SCARLETT2_FLASH_WRITE_STATE_SELECTED;
+
+	return 0;
+}
+
+/* Erase the previously-selected flash segment */
+static int scarlett2_ioctl_erase_flash_segment(
+	struct usb_mixer_interface *mixer)
+{
+	struct scarlett2_data *private = mixer->private_data;
+	int segment_id, segment_num, err;
+
+	struct {
+		__le32 segment_num;
+		__le32 pad;
+	} __packed erase_req;
+
+	if (private->flash_write_state != SCARLETT2_FLASH_WRITE_STATE_SELECTED)
+		return -EINVAL;
+
+	segment_id = private->selected_flash_segment_id;
+	segment_num = private->flash_segment_nums[segment_id];
+
+	if (segment_num < SCARLETT2_SEGMENT_NUM_MIN ||
+	    segment_num > SCARLETT2_SEGMENT_NUM_MAX)
+		return -EFAULT;
+
+	/* Prevent access to ALSA controls that access the device from
+	 * here on
+	 */
+	scarlett2_lock(private);
+
+	/* Send the erase request */
+	erase_req.segment_num = cpu_to_le32(segment_num);
+	erase_req.pad = 0;
+
+	err = scarlett2_usb(mixer, SCARLETT2_USB_ERASE_SEGMENT,
+			    &erase_req, sizeof(erase_req),
+			    NULL, 0);
+	if (err < 0)
+		return err;
+
+	/* On success, change the state from SELECTED to ERASING */
+	private->flash_write_state = SCARLETT2_FLASH_WRITE_STATE_ERASING;
+
+	return 0;
+}
+
+/* Get the erase progress from the device */
+static int scarlett2_ioctl_get_erase_progress(
+	struct usb_mixer_interface *mixer,
+	unsigned long arg)
+{
+	struct scarlett2_data *private = mixer->private_data;
+	struct scarlett2_flash_segment_erase_progress progress;
+	int segment_id, segment_num, err;
+	u8 erase_resp;
+
+	struct {
+		__le32 segment_num;
+		__le32 pad;
+	} __packed erase_req;
+
+	/* Check that we're erasing */
+	if (private->flash_write_state != SCARLETT2_FLASH_WRITE_STATE_ERASING)
+		return -EINVAL;
+
+	segment_id = private->selected_flash_segment_id;
+	segment_num = private->flash_segment_nums[segment_id];
+
+	if (segment_num < SCARLETT2_SEGMENT_NUM_MIN ||
+	    segment_num > SCARLETT2_SEGMENT_NUM_MAX)
+		return -EFAULT;
+
+	/* Send the erase progress request */
+	erase_req.segment_num = cpu_to_le32(segment_num);
+	erase_req.pad = 0;
+
+	err = scarlett2_usb(mixer, SCARLETT2_USB_GET_ERASE,
+			    &erase_req, sizeof(erase_req),
+			    &erase_resp, sizeof(erase_resp));
+	if (err < 0)
+		return err;
+
+	progress.progress = erase_resp;
+	progress.num_blocks = private->flash_segment_blocks[segment_id];
+
+	if (copy_to_user((void __user *)arg, &progress, sizeof(progress)))
+		return -EFAULT;
+
+	/* If the erase is complete, change the state from ERASING to
+	 * IDLE.
+	 */
+	if (progress.progress == 0xff)
+		private->flash_write_state = SCARLETT2_FLASH_WRITE_STATE_IDLE;
+
+	return 0;
+}
+
+static int scarlett2_hwdep_open(struct snd_hwdep *hw, struct file *file)
+{
+	struct usb_mixer_interface *mixer = hw->private_data;
+	struct scarlett2_data *private = mixer->private_data;
+
+	/* If erasing, wait for it to complete */
+	if (private->flash_write_state ==
+	      SCARLETT2_FLASH_WRITE_STATE_ERASING) {
+		int err = scarlett2_wait_for_erase(mixer);
+
+		if (err < 0)
+			return err;
+	}
+
+	/* Set the state to IDLE */
+	private->flash_write_state = SCARLETT2_FLASH_WRITE_STATE_IDLE;
+
+	return 0;
+}
+
 static int scarlett2_hwdep_ioctl(struct snd_hwdep *hw, struct file *file,
 				 unsigned int cmd, unsigned long arg)
 {
@@ -4732,11 +5121,36 @@ static int scarlett2_hwdep_ioctl(struct snd_hwdep *hw, struct file *file,
 	case SCARLETT2_IOCTL_REBOOT:
 		return scarlett2_reboot(mixer);
 
+	case SCARLETT2_IOCTL_SELECT_FLASH_SEGMENT:
+		return scarlett2_ioctl_select_flash_segment(mixer, arg);
+
+	case SCARLETT2_IOCTL_ERASE_FLASH_SEGMENT:
+		return scarlett2_ioctl_erase_flash_segment(mixer);
+
+	case SCARLETT2_IOCTL_GET_ERASE_PROGRESS:
+		return scarlett2_ioctl_get_erase_progress(mixer, arg);
+
 	default:
 		return -ENOIOCTLCMD;
 	}
 }
 
+static int scarlett2_hwdep_release(struct snd_hwdep *hw, struct file *file)
+{
+	struct usb_mixer_interface *mixer = hw->private_data;
+	struct scarlett2_data *private = mixer->private_data;
+
+	/* Return from the SELECTED or WRITE state to IDLE.
+	 * The ERASING state is left as-is, and checked on next open.
+	 */
+	if (private &&
+	    private->hwdep_in_use &&
+	    private->flash_write_state != SCARLETT2_FLASH_WRITE_STATE_ERASING)
+		private->flash_write_state = SCARLETT2_FLASH_WRITE_STATE_IDLE;
+
+	return 0;
+}
+
 static int scarlett2_hwdep_init(struct usb_mixer_interface *mixer)
 {
 	struct snd_hwdep *hw;
@@ -4748,7 +5162,9 @@ static int scarlett2_hwdep_init(struct usb_mixer_interface *mixer)
 
 	hw->private_data = mixer;
 	hw->exclusive = 1;
+	hw->ops.open = scarlett2_hwdep_open;
 	hw->ops.ioctl = scarlett2_hwdep_ioctl;
+	hw->ops.release = scarlett2_hwdep_release;
 
 	return 0;
 }
-- 
cgit v1.2.3


From 4e809a299677b8a9a239574a787620cb4f6c086a Mon Sep 17 00:00:00 2001
From: "Geoffrey D. Bennett" <g@b4.vu>
Date: Wed, 27 Dec 2023 04:38:58 +1030
Subject: ALSA: scarlett2: Add support for Solo, 2i2, and 4i4 Gen 4

Add new Focusrite Scarlett Gen 4 USB IDs, notification arrays, config
sets, and device info data.

Signed-off-by: Geoffrey D. Bennett <g@b4.vu>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://lore.kernel.org/r/b33526d3b7a56bb2c86aa4eb2137a415bd23f1ce.1703612638.git.g@b4.vu
---
 include/uapi/sound/scarlett2.h |   4 +-
 sound/usb/mixer_quirks.c       |   3 +
 sound/usb/mixer_scarlett2.c    | 361 +++++++++++++++++++++++++++++++++++++++--
 3 files changed, 351 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/uapi/sound/scarlett2.h b/include/uapi/sound/scarlett2.h
index d0ff38ffa154..91467ab0ed70 100644
--- a/include/uapi/sound/scarlett2.h
+++ b/include/uapi/sound/scarlett2.h
@@ -1,8 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
  *   Focusrite Scarlett 2 Protocol Driver for ALSA
- *   (including Scarlett 2nd Gen, 3rd Gen, Clarett USB, and Clarett+
- *   series products)
+ *   (including Scarlett 2nd Gen, 3rd Gen, 4th Gen, Clarett USB, and
+ *   Clarett+ series products)
  *
  *   Copyright (c) 2023 by Geoffrey D. Bennett <g at b4.vu>
  */
diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c
index c8d48566e175..065a4be0d771 100644
--- a/sound/usb/mixer_quirks.c
+++ b/sound/usb/mixer_quirks.c
@@ -3447,6 +3447,9 @@ int snd_usb_mixer_apply_create_quirk(struct usb_mixer_interface *mixer)
 	case USB_ID(0x1235, 0x8213): /* Focusrite Scarlett 8i6 3rd Gen */
 	case USB_ID(0x1235, 0x8214): /* Focusrite Scarlett 18i8 3rd Gen */
 	case USB_ID(0x1235, 0x8215): /* Focusrite Scarlett 18i20 3rd Gen */
+	case USB_ID(0x1235, 0x8218): /* Focusrite Scarlett Solo 4th Gen */
+	case USB_ID(0x1235, 0x8219): /* Focusrite Scarlett 2i2 4th Gen */
+	case USB_ID(0x1235, 0x821a): /* Focusrite Scarlett 4i4 4th Gen */
 	case USB_ID(0x1235, 0x8206): /* Focusrite Clarett 2Pre USB */
 	case USB_ID(0x1235, 0x8207): /* Focusrite Clarett 4Pre USB */
 	case USB_ID(0x1235, 0x8208): /* Focusrite Clarett 8Pre USB */
diff --git a/sound/usb/mixer_scarlett2.c b/sound/usb/mixer_scarlett2.c
index 94413fca2b6c..743054472184 100644
--- a/sound/usb/mixer_scarlett2.c
+++ b/sound/usb/mixer_scarlett2.c
@@ -1,12 +1,13 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
  *   Focusrite Scarlett 2 Protocol Driver for ALSA
- *   (including Scarlett 2nd Gen, 3rd Gen, Clarett USB, and Clarett+
- *   series products)
+ *   (including Scarlett 2nd Gen, 3rd Gen, 4th Gen, Clarett USB, and
+ *   Clarett+ series products)
  *
  *   Supported models:
  *   - 6i6/18i8/18i20 Gen 2
  *   - Solo/2i2/4i4/8i6/18i8/18i20 Gen 3
+ *   - Solo/2i2/4i4 Gen 4
  *   - Clarett 2Pre/4Pre/8Pre USB
  *   - Clarett+ 2Pre/4Pre/8Pre
  *
@@ -68,6 +69,12 @@
  *
  * Support for Clarett 2Pre and 4Pre USB added in Oct 2023.
  *
+ * Support for firmware updates added in Dec 2023.
+ *
+ * Support for Scarlett Solo/2i2/4i4 Gen 4 added in Dec 2023 (thanks
+ * to many LinuxMusicians people and to Focusrite for hardware
+ * donations).
+ *
  * This ALSA mixer gives access to (model-dependent):
  *  - input, output, mixer-matrix muxes
  *  - mixer-matrix gain stages
@@ -78,6 +85,8 @@
  *    controls
  *  - disable/enable MSD mode
  *  - disable/enable standalone mode
+ *  - input gain, autogain, safe mode
+ *  - direct monitor mixes
  *
  * <ditaa>
  *    /--------------\    18chn            20chn     /--------------\
@@ -130,7 +139,7 @@
  *  \--------------/
  * </ditaa>
  *
- * Gen 3 devices have a Mass Storage Device (MSD) mode where a small
+ * Gen 3/4 devices have a Mass Storage Device (MSD) mode where a small
  * disk with registration and driver download information is presented
  * to the host. To access the full functionality of the device without
  * proprietary software, MSD mode can be disabled by:
@@ -302,9 +311,19 @@ struct scarlett2_notification {
 static void scarlett2_notify_sync(struct usb_mixer_interface *mixer);
 static void scarlett2_notify_dim_mute(struct usb_mixer_interface *mixer);
 static void scarlett2_notify_monitor(struct usb_mixer_interface *mixer);
+static void scarlett2_notify_volume(struct usb_mixer_interface *mixer);
+static void scarlett2_notify_input_level(struct usb_mixer_interface *mixer);
+static void scarlett2_notify_input_pad(struct usb_mixer_interface *mixer);
+static void scarlett2_notify_input_air(struct usb_mixer_interface *mixer);
+static void scarlett2_notify_input_phantom(struct usb_mixer_interface *mixer);
 static void scarlett2_notify_input_other(struct usb_mixer_interface *mixer);
+static void scarlett2_notify_input_select(struct usb_mixer_interface *mixer);
+static void scarlett2_notify_input_gain(struct usb_mixer_interface *mixer);
+static void scarlett2_notify_autogain(struct usb_mixer_interface *mixer);
+static void scarlett2_notify_input_safe(struct usb_mixer_interface *mixer);
 static void scarlett2_notify_monitor_other(struct usb_mixer_interface *mixer);
 static void scarlett2_notify_direct_monitor(struct usb_mixer_interface *mixer);
+static void scarlett2_notify_power_status(struct usb_mixer_interface *mixer);
 
 /* Arrays of notification callback functions */
 
@@ -325,6 +344,48 @@ static const struct scarlett2_notification scarlett3a_notifications[] = {
 	{ 0, NULL }
 };
 
+static const struct scarlett2_notification scarlett4_solo_notifications[] = {
+	{ 0x00000001, NULL }, /* ack, gets ignored */
+	{ 0x00000008, scarlett2_notify_sync },
+	{ 0x00400000, scarlett2_notify_input_air },
+	{ 0x00800000, scarlett2_notify_direct_monitor },
+	{ 0x01000000, scarlett2_notify_input_level },
+	{ 0x02000000, scarlett2_notify_input_phantom },
+	{ 0, NULL }
+};
+
+static const struct scarlett2_notification scarlett4_2i2_notifications[] = {
+	{ 0x00000001, NULL }, /* ack, gets ignored */
+	{ 0x00000008, scarlett2_notify_sync },
+	{ 0x00200000, scarlett2_notify_input_safe },
+	{ 0x00400000, scarlett2_notify_autogain },
+	{ 0x00800000, scarlett2_notify_input_air },
+	{ 0x01000000, scarlett2_notify_direct_monitor },
+	{ 0x02000000, scarlett2_notify_input_select },
+	{ 0x04000000, scarlett2_notify_input_level },
+	{ 0x08000000, scarlett2_notify_input_phantom },
+	{ 0x10000000, NULL }, /* power status, ignored */
+	{ 0x40000000, scarlett2_notify_input_gain },
+	{ 0x80000000, NULL }, /* power status, ignored */
+	{ 0, NULL }
+};
+
+static const struct scarlett2_notification scarlett4_4i4_notifications[] = {
+	{ 0x00000001, NULL }, /* ack, gets ignored */
+	{ 0x00000008, scarlett2_notify_sync },
+	{ 0x00200000, scarlett2_notify_input_safe },
+	{ 0x00400000, scarlett2_notify_autogain },
+	{ 0x00800000, scarlett2_notify_input_air },
+	{ 0x01000000, scarlett2_notify_input_select },
+	{ 0x02000000, scarlett2_notify_input_level },
+	{ 0x04000000, scarlett2_notify_input_phantom },
+	{ 0x08000000, scarlett2_notify_power_status }, /* power external */
+	{ 0x20000000, scarlett2_notify_input_gain },
+	{ 0x40000000, scarlett2_notify_power_status }, /* power status */
+	{ 0x80000000, scarlett2_notify_volume },
+	{ 0, NULL }
+};
+
 /* Configuration parameters that can be read and written */
 enum {
 	SCARLETT2_CONFIG_DIM_MUTE,
@@ -543,6 +604,123 @@ static const struct scarlett2_config_set scarlett2_config_set_gen3c = {
 	}
 };
 
+/* Solo Gen 4 */
+static const struct scarlett2_config_set scarlett2_config_set_gen4_solo = {
+	.notifications = scarlett4_solo_notifications,
+	.gen4_write_addr = 0xd8,
+	.items = {
+		[SCARLETT2_CONFIG_MSD_SWITCH] = {
+			.offset = 0x47, .size = 8, .activate = 4 },
+
+		[SCARLETT2_CONFIG_DIRECT_MONITOR] = {
+			.offset = 0x108, .activate = 12 },
+
+		[SCARLETT2_CONFIG_PHANTOM_SWITCH] = {
+			.offset = 0x46, .activate = 9, .mute = 1 },
+
+		[SCARLETT2_CONFIG_LEVEL_SWITCH] = {
+			.offset = 0x3d, .activate = 10, .mute = 1 },
+
+		[SCARLETT2_CONFIG_AIR_SWITCH] = {
+			.offset = 0x3e, .activate = 11 },
+
+		[SCARLETT2_CONFIG_DIRECT_MONITOR_GAIN] = {
+			.offset = 0x232, .size = 16, .activate = 26 }
+	}
+};
+
+/* 2i2 Gen 4 */
+static const struct scarlett2_config_set scarlett2_config_set_gen4_2i2 = {
+	.notifications = scarlett4_2i2_notifications,
+	.gen4_write_addr = 0xfc,
+	.items = {
+		[SCARLETT2_CONFIG_MSD_SWITCH] = {
+			.offset = 0x49, .size = 8, .activate = 4 }, // 0x41 ??
+
+		[SCARLETT2_CONFIG_DIRECT_MONITOR] = {
+			.offset = 0x14a, .activate = 16 },
+
+		[SCARLETT2_CONFIG_AUTOGAIN_SWITCH] = {
+			.offset = 0x135, .activate = 10 },
+
+		[SCARLETT2_CONFIG_AUTOGAIN_STATUS] = {
+			.offset = 0x137 },
+
+		[SCARLETT2_CONFIG_PHANTOM_SWITCH] = {
+			.offset = 0x48, .activate = 11, .mute = 1 },
+
+		[SCARLETT2_CONFIG_INPUT_GAIN] = {
+			.offset = 0x4b, .activate = 12 },
+
+		[SCARLETT2_CONFIG_LEVEL_SWITCH] = {
+			.offset = 0x3c, .activate = 13, .mute = 1 },
+
+		[SCARLETT2_CONFIG_SAFE_SWITCH] = {
+			.offset = 0x147, .activate = 14 },
+
+		[SCARLETT2_CONFIG_AIR_SWITCH] = {
+			.offset = 0x3e, .activate = 15 },
+
+		[SCARLETT2_CONFIG_INPUT_SELECT_SWITCH] = {
+			.offset = 0x14b, .activate = 17 },
+
+		[SCARLETT2_CONFIG_INPUT_LINK_SWITCH] = {
+			.offset = 0x14e, .activate = 18 },
+
+		[SCARLETT2_CONFIG_DIRECT_MONITOR_GAIN] = {
+			.offset = 0x2a0, .size = 16, .activate = 36 }
+	}
+};
+
+/* 4i4 Gen 4 */
+static const struct scarlett2_config_set scarlett2_config_set_gen4_4i4 = {
+	.notifications = scarlett4_4i4_notifications,
+	.gen4_write_addr = 0x130,
+	.items = {
+		[SCARLETT2_CONFIG_MSD_SWITCH] = {
+			.offset = 0x5c, .size = 8, .activate = 4 },
+
+		[SCARLETT2_CONFIG_AUTOGAIN_SWITCH] = {
+			.offset = 0x13e, .activate = 10 },
+
+		[SCARLETT2_CONFIG_AUTOGAIN_STATUS] = {
+			.offset = 0x140 },
+
+		[SCARLETT2_CONFIG_PHANTOM_SWITCH] = {
+			.offset = 0x5a, .activate = 11, .mute = 1 },
+
+		[SCARLETT2_CONFIG_INPUT_GAIN] = {
+			.offset = 0x5e, .activate = 12 },
+
+		[SCARLETT2_CONFIG_LEVEL_SWITCH] = {
+			.offset = 0x4e, .activate = 13, .mute = 1 },
+
+		[SCARLETT2_CONFIG_SAFE_SWITCH] = {
+			.offset = 0x150, .activate = 14 },
+
+		[SCARLETT2_CONFIG_AIR_SWITCH] = {
+			.offset = 0x50, .activate = 15 },
+
+		[SCARLETT2_CONFIG_INPUT_SELECT_SWITCH] = {
+			.offset = 0x153, .activate = 16 },
+
+		[SCARLETT2_CONFIG_INPUT_LINK_SWITCH] = {
+			.offset = 0x156, .activate = 17 },
+
+		[SCARLETT2_CONFIG_MASTER_VOLUME] = {
+			.offset = 0x32, .size = 16 },
+
+		[SCARLETT2_CONFIG_HEADPHONE_VOLUME] = {
+			.offset = 0x3a, .size = 16 },
+
+		[SCARLETT2_CONFIG_POWER_EXT] = {
+			.offset = 0x168 },
+
+		[SCARLETT2_CONFIG_POWER_STATUS] = {
+			.offset = 0x66 }
+	}
+};
+
 /* Clarett USB and Clarett+ devices: 2Pre, 4Pre, 8Pre */
 static const struct scarlett2_config_set scarlett2_config_set_clarett = {
 	.notifications = scarlett2_notifications,
@@ -1274,6 +1452,160 @@ static const struct scarlett2_device_info s18i20_gen3_info = {
 	}
 };
 
+static const struct scarlett2_device_info solo_gen4_info = {
+	.config_set = &scarlett2_config_set_gen4_solo,
+	.min_firmware_version = 2115,
+
+	.level_input_count = 1,
+	.air_input_count = 1,
+	.air_input_first = 1,
+	.air_option = 1,
+	.phantom_count = 1,
+	.phantom_first = 1,
+	.inputs_per_phantom = 1,
+	.direct_monitor = 1,
+	.dsp_count = 2,
+
+	.port_count = {
+		[SCARLETT2_PORT_TYPE_NONE]     = { 1,  0 },
+		[SCARLETT2_PORT_TYPE_ANALOGUE] = { 2,  2 },
+		[SCARLETT2_PORT_TYPE_MIX]      = { 8,  6 },
+		[SCARLETT2_PORT_TYPE_PCM]      = { 2,  4 },
+	},
+
+	.mux_assignment = { {
+		{ SCARLETT2_PORT_TYPE_MIX,       4,  2 },
+		{ SCARLETT2_PORT_TYPE_MIX,       2,  2 },
+		{ SCARLETT2_PORT_TYPE_PCM,       0,  4 },
+		{ SCARLETT2_PORT_TYPE_MIX,       0,  2 },
+		{ SCARLETT2_PORT_TYPE_ANALOGUE,  0,  2 },
+		{ 0,                             0,  0 },
+	}, {
+		{ SCARLETT2_PORT_TYPE_MIX,       4,  2 },
+		{ SCARLETT2_PORT_TYPE_MIX,       2,  2 },
+		{ SCARLETT2_PORT_TYPE_PCM,       0,  4 },
+		{ SCARLETT2_PORT_TYPE_MIX,       0,  2 },
+		{ SCARLETT2_PORT_TYPE_ANALOGUE,  0,  2 },
+		{ 0,                             0,  0 },
+	}, {
+		{ SCARLETT2_PORT_TYPE_MIX,       4,  2 },
+		{ SCARLETT2_PORT_TYPE_MIX,       2,  2 },
+		{ SCARLETT2_PORT_TYPE_PCM,       0,  4 },
+		{ SCARLETT2_PORT_TYPE_MIX,       0,  2 },
+		{ SCARLETT2_PORT_TYPE_ANALOGUE,  0,  2 },
+		{ 0,                             0,  0 },
+	} },
+
+	.meter_map = {
+		{  6,  2 },
+		{  4,  2 },
+		{  8,  4 },
+		{  2,  2 },
+		{  0,  2 },
+		{  0,  0 }
+	}
+};
+
+static const struct scarlett2_device_info s2i2_gen4_info = {
+	.config_set = &scarlett2_config_set_gen4_2i2,
+	.min_firmware_version = 2115,
+
+	.level_input_count = 2,
+	.air_input_count = 2,
+	.air_option = 1,
+	.phantom_count = 1,
+	.inputs_per_phantom = 2,
+	.gain_input_count = 2,
+	.direct_monitor = 2,
+	.dsp_count = 2,
+
+	.port_count = {
+		[SCARLETT2_PORT_TYPE_NONE]     = { 1,  0 },
+		[SCARLETT2_PORT_TYPE_ANALOGUE] = { 2,  2 },
+		[SCARLETT2_PORT_TYPE_MIX]      = { 6,  6 },
+		[SCARLETT2_PORT_TYPE_PCM]      = { 2,  4 },
+	},
+
+	.mux_assignment = { {
+		{ SCARLETT2_PORT_TYPE_MIX,       4,  2 },
+		{ SCARLETT2_PORT_TYPE_MIX,       2,  2 },
+		{ SCARLETT2_PORT_TYPE_PCM,       0,  4 },
+		{ SCARLETT2_PORT_TYPE_MIX,       0,  2 },
+		{ SCARLETT2_PORT_TYPE_ANALOGUE,  0,  2 },
+		{ 0,                             0,  0 },
+	}, {
+		{ SCARLETT2_PORT_TYPE_MIX,       4,  2 },
+		{ SCARLETT2_PORT_TYPE_MIX,       2,  2 },
+		{ SCARLETT2_PORT_TYPE_PCM,       0,  4 },
+		{ SCARLETT2_PORT_TYPE_MIX,       0,  2 },
+		{ SCARLETT2_PORT_TYPE_ANALOGUE,  0,  2 },
+		{ 0,                             0,  0 },
+	}, {
+		{ SCARLETT2_PORT_TYPE_MIX,       4,  2 },
+		{ SCARLETT2_PORT_TYPE_MIX,       2,  2 },
+		{ SCARLETT2_PORT_TYPE_PCM,       0,  4 },
+		{ SCARLETT2_PORT_TYPE_MIX,       0,  2 },
+		{ SCARLETT2_PORT_TYPE_ANALOGUE,  0,  2 },
+		{ 0,                             0,  0 },
+	} },
+
+	.meter_map = {
+		{  6,  2 },
+		{  4,  2 },
+		{  8,  4 },
+		{  2,  2 },
+		{  0,  2 },
+		{  0,  0 }
+	}
+};
+
+static const struct scarlett2_device_info s4i4_gen4_info = {
+	.config_set = &scarlett2_config_set_gen4_4i4,
+	.min_firmware_version = 2089,
+
+	.level_input_count = 2,
+	.air_input_count = 2,
+	.air_option = 1,
+	.phantom_count = 2,
+	.inputs_per_phantom = 1,
+	.gain_input_count = 2,
+	.dsp_count = 2,
+
+	.port_count = {
+		[SCARLETT2_PORT_TYPE_NONE]     = { 1,  0 },
+		[SCARLETT2_PORT_TYPE_ANALOGUE] = { 4,  6 },
+		[SCARLETT2_PORT_TYPE_MIX]      = { 8, 12 },
+		[SCARLETT2_PORT_TYPE_PCM]      = { 6,  6 },
+	},
+
+	.mux_assignment = { {
+		{ SCARLETT2_PORT_TYPE_MIX,      10,  2 },
+		{ SCARLETT2_PORT_TYPE_PCM,       0,  6 },
+		{ SCARLETT2_PORT_TYPE_MIX,       0, 10 },
+		{ SCARLETT2_PORT_TYPE_ANALOGUE,  0,  6 },
+		{ 0,                             0,  0 },
+	}, {
+		{ SCARLETT2_PORT_TYPE_MIX,      10,  2 },
+		{ SCARLETT2_PORT_TYPE_PCM,       0,  6 },
+		{ SCARLETT2_PORT_TYPE_MIX,       0, 10 },
+		{ SCARLETT2_PORT_TYPE_ANALOGUE,  0,  6 },
+		{ 0,                             0,  0 },
+	}, {
+		{ SCARLETT2_PORT_TYPE_MIX,      10,  2 },
+		{ SCARLETT2_PORT_TYPE_PCM,       0,  6 },
+		{ SCARLETT2_PORT_TYPE_MIX,       0, 10 },
+		{ SCARLETT2_PORT_TYPE_ANALOGUE,  0,  6 },
+		{ 0,                             0,  0 },
+	} },
+
+	.meter_map = {
+		{ 16,  8 },
+		{  6, 10 },
+		{  0,  6 },
+		{  0,  0 }
+	}
+};
+
 static const struct scarlett2_device_info clarett_2pre_info = {
 	.config_set = &scarlett2_config_set_clarett,
 	.level_input_count = 2,
@@ -1451,6 +1783,11 @@ static const struct scarlett2_device_entry scarlett2_devices[] = {
 	{ USB_ID(0x1235, 0x8214), &s18i8_gen3_info, "Scarlett Gen 3" },
 	{ USB_ID(0x1235, 0x8215), &s18i20_gen3_info, "Scarlett Gen 3" },
 
+	/* Supported Gen 4 devices */
+	{ USB_ID(0x1235, 0x8218), &solo_gen4_info, "Scarlett Gen 4" },
+	{ USB_ID(0x1235, 0x8219), &s2i2_gen4_info, "Scarlett Gen 4" },
+	{ USB_ID(0x1235, 0x821a), &s4i4_gen4_info, "Scarlett Gen 4" },
+
 	/* Supported Clarett USB/Clarett+ devices */
 	{ USB_ID(0x1235, 0x8206), &clarett_2pre_info, "Clarett USB" },
 	{ USB_ID(0x1235, 0x8207), &clarett_4pre_info, "Clarett USB" },
@@ -6353,8 +6690,7 @@ static void scarlett2_notify_monitor(struct usb_mixer_interface *mixer)
 }
 
 /* Notify on volume change (Gen 4) */
-static __always_unused void scarlett2_notify_volume(
-	struct usb_mixer_interface *mixer)
+static void scarlett2_notify_volume(struct usb_mixer_interface *mixer)
 {
 	struct scarlett2_data *private = mixer->private_data;
 
@@ -6460,8 +6796,7 @@ static void scarlett2_notify_input_other(struct usb_mixer_interface *mixer)
 }
 
 /* Notify on input select change */
-static __always_unused void scarlett2_notify_input_select(
-	struct usb_mixer_interface *mixer)
+static void scarlett2_notify_input_select(struct usb_mixer_interface *mixer)
 {
 	struct snd_card *card = mixer->chip->card;
 	struct scarlett2_data *private = mixer->private_data;
@@ -6483,8 +6818,7 @@ static __always_unused void scarlett2_notify_input_select(
 }
 
 /* Notify on input gain change */
-static __always_unused void scarlett2_notify_input_gain(
-	struct usb_mixer_interface *mixer)
+static void scarlett2_notify_input_gain(struct usb_mixer_interface *mixer)
 {
 	struct snd_card *card = mixer->chip->card;
 	struct scarlett2_data *private = mixer->private_data;
@@ -6502,8 +6836,7 @@ static __always_unused void scarlett2_notify_input_gain(
 }
 
 /* Notify on autogain change */
-static __always_unused void scarlett2_notify_autogain(
-	struct usb_mixer_interface *mixer)
+static void scarlett2_notify_autogain(struct usb_mixer_interface *mixer)
 {
 	struct snd_card *card = mixer->chip->card;
 	struct scarlett2_data *private = mixer->private_data;
@@ -6526,8 +6859,7 @@ static __always_unused void scarlett2_notify_autogain(
 }
 
 /* Notify on input safe switch change */
-static __always_unused void scarlett2_notify_input_safe(
-	struct usb_mixer_interface *mixer)
+static void scarlett2_notify_input_safe(struct usb_mixer_interface *mixer)
 {
 	struct snd_card *card = mixer->chip->card;
 	struct scarlett2_data *private = mixer->private_data;
@@ -6603,8 +6935,7 @@ static void scarlett2_notify_direct_monitor(struct usb_mixer_interface *mixer)
 }
 
 /* Notify on power change */
-static __always_unused void scarlett2_notify_power_status(
-	struct usb_mixer_interface *mixer)
+static void scarlett2_notify_power_status(struct usb_mixer_interface *mixer)
 {
 	struct snd_card *card = mixer->chip->card;
 	struct scarlett2_data *private = mixer->private_data;
-- 
cgit v1.2.3


From a8c959402d4dd6823918b33828d79900ae58c700 Mon Sep 17 00:00:00 2001
From: Lukasz Luba <lukasz.luba@arm.com>
Date: Wed, 20 Dec 2023 23:17:45 +0000
Subject: thermal: core: Add governor callback for thermal zone change

Add a new callback to the struct thermal_governor. It can be used for
updating governors when there is a change in the thermal zone internals,
e.g. thermal cooling device is bind to the thermal zone.

That makes possible to move some heavy operations like memory allocations
related to the number of cooling instances out of the throttle() callback.

Both callback code paths (throttle() and update_tz()) are protected with
the same thermal zone lock, which guaranties the consistency.

Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/thermal/thermal_core.c | 14 ++++++++++++++
 drivers/thermal/thermal_core.h |  2 ++
 include/linux/thermal.h        |  6 ++++++
 3 files changed, 22 insertions(+)

(limited to 'include')

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 3ffccd73b19e..58958288b559 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -309,6 +309,15 @@ static void handle_non_critical_trips(struct thermal_zone_device *tz,
 		       def_governor->throttle(tz, trip);
 }
 
+void thermal_governor_update_tz(struct thermal_zone_device *tz,
+				enum thermal_notify_event reason)
+{
+	if (!tz->governor || !tz->governor->update_tz)
+		return;
+
+	tz->governor->update_tz(tz, reason);
+}
+
 void thermal_zone_device_critical(struct thermal_zone_device *tz)
 {
 	/*
@@ -715,6 +724,8 @@ int thermal_bind_cdev_to_trip(struct thermal_zone_device *tz,
 		list_add_tail(&dev->tz_node, &tz->thermal_instances);
 		list_add_tail(&dev->cdev_node, &cdev->thermal_instances);
 		atomic_set(&tz->need_update, 1);
+
+		thermal_governor_update_tz(tz, THERMAL_TZ_BIND_CDEV);
 	}
 	mutex_unlock(&cdev->lock);
 	mutex_unlock(&tz->lock);
@@ -773,6 +784,9 @@ int thermal_unbind_cdev_from_trip(struct thermal_zone_device *tz,
 		if (pos->tz == tz && pos->trip == trip && pos->cdev == cdev) {
 			list_del(&pos->tz_node);
 			list_del(&pos->cdev_node);
+
+			thermal_governor_update_tz(tz, THERMAL_TZ_UNBIND_CDEV);
+
 			mutex_unlock(&cdev->lock);
 			mutex_unlock(&tz->lock);
 			goto unbind;
diff --git a/drivers/thermal/thermal_core.h b/drivers/thermal/thermal_core.h
index fe2917a74054..479c3b6917e4 100644
--- a/drivers/thermal/thermal_core.h
+++ b/drivers/thermal/thermal_core.h
@@ -114,6 +114,8 @@ int thermal_zone_device_set_policy(struct thermal_zone_device *, char *);
 int thermal_build_list_of_policies(char *buf);
 void __thermal_zone_device_update(struct thermal_zone_device *tz,
 				  enum thermal_notify_event event);
+void thermal_governor_update_tz(struct thermal_zone_device *tz,
+				enum thermal_notify_event reason);
 
 /* Helpers */
 #define for_each_trip(__tz, __trip)	\
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index d00622b64d50..4d96fefb2767 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -51,6 +51,8 @@ enum thermal_notify_event {
 	THERMAL_DEVICE_POWER_CAPABILITY_CHANGED, /* power capability changed */
 	THERMAL_TABLE_CHANGED, /* Thermal table(s) changed */
 	THERMAL_EVENT_KEEP_ALIVE, /* Request for user space handler to respond */
+	THERMAL_TZ_BIND_CDEV, /* Cooling dev is bind to the thermal zone */
+	THERMAL_TZ_UNBIND_CDEV, /* Cooling dev is unbind from the thermal zone */
 };
 
 /**
@@ -199,6 +201,8 @@ struct thermal_zone_device {
  *			thermal zone.
  * @throttle:	callback called for every trip point even if temperature is
  *		below the trip point temperature
+ * @update_tz:	callback called when thermal zone internals have changed, e.g.
+ *		thermal cooling instance was added/removed
  * @governor_list:	node in thermal_governor_list (in thermal_core.c)
  */
 struct thermal_governor {
@@ -207,6 +211,8 @@ struct thermal_governor {
 	void (*unbind_from_tz)(struct thermal_zone_device *tz);
 	int (*throttle)(struct thermal_zone_device *tz,
 			const struct thermal_trip *trip);
+	void (*update_tz)(struct thermal_zone_device *tz,
+			  enum thermal_notify_event reason);
 	struct list_head	governor_list;
 };
 
-- 
cgit v1.2.3


From bfc57bd1685981730bfe9802d9de7603a0a43bc4 Mon Sep 17 00:00:00 2001
From: Lukasz Luba <lukasz.luba@arm.com>
Date: Wed, 20 Dec 2023 23:17:52 +0000
Subject: thermal/sysfs: Update governors when the 'weight' has changed

Support governors update when the thermal instance's weight has changed.
This allows to adjust internal state for the governor.

Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
[ rjw: Add two empty code lines aroung the locking ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/thermal/thermal_sysfs.c | 5 +++++
 include/linux/thermal.h         | 1 +
 2 files changed, 6 insertions(+)

(limited to 'include')

diff --git a/drivers/thermal/thermal_sysfs.c b/drivers/thermal/thermal_sysfs.c
index 299c0fb16593..f4033865b093 100644
--- a/drivers/thermal/thermal_sysfs.c
+++ b/drivers/thermal/thermal_sysfs.c
@@ -939,7 +939,12 @@ ssize_t weight_store(struct device *dev, struct device_attribute *attr,
 
 	/* Don't race with governors using the 'weight' value */
 	mutex_lock(&instance->tz->lock);
+
 	instance->weight = weight;
+
+	thermal_governor_update_tz(instance->tz,
+				   THERMAL_INSTANCE_WEIGHT_CHANGED);
+
 	mutex_unlock(&instance->tz->lock);
 
 	return count;
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 4d96fefb2767..9d0427da32af 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -53,6 +53,7 @@ enum thermal_notify_event {
 	THERMAL_EVENT_KEEP_ALIVE, /* Request for user space handler to respond */
 	THERMAL_TZ_BIND_CDEV, /* Cooling dev is bind to the thermal zone */
 	THERMAL_TZ_UNBIND_CDEV, /* Cooling dev is unbind from the thermal zone */
+	THERMAL_INSTANCE_WEIGHT_CHANGED, /* Thermal instance weight changed */
 };
 
 /**
-- 
cgit v1.2.3


From adef440691bab824e39c1b17382322d195e1fab0 Mon Sep 17 00:00:00 2001
From: Andrea Arcangeli <aarcange@redhat.com>
Date: Wed, 6 Dec 2023 02:36:56 -0800
Subject: userfaultfd: UFFDIO_MOVE uABI

Implement the uABI of UFFDIO_MOVE ioctl.
UFFDIO_COPY performs ~20% better than UFFDIO_MOVE when the application
needs pages to be allocated [1]. However, with UFFDIO_MOVE, if pages are
available (in userspace) for recycling, as is usually the case in heap
compaction algorithms, then we can avoid the page allocation and memcpy
(done by UFFDIO_COPY). Also, since the pages are recycled in the
userspace, we avoid the need to release (via madvise) the pages back to
the kernel [2].

We see over 40% reduction (on a Google pixel 6 device) in the compacting
thread's completion time by using UFFDIO_MOVE vs.  UFFDIO_COPY.  This was
measured using a benchmark that emulates a heap compaction implementation
using userfaultfd (to allow concurrent accesses by application threads).
More details of the usecase are explained in [2].  Furthermore,
UFFDIO_MOVE enables moving swapped-out pages without touching them within
the same vma.  Today, it can only be done by mremap, however it forces
splitting the vma.

[1] https://lore.kernel.org/all/1425575884-2574-1-git-send-email-aarcange@redhat.com/
[2] https://lore.kernel.org/linux-mm/CA+EESO4uO84SSnBhArH4HvLNhaUQ5nZKNKXqxRCyjniNVjp0Aw@mail.gmail.com/

Update for the ioctl_userfaultfd(2)  manpage:

   UFFDIO_MOVE
       (Since Linux xxx)  Move a continuous memory chunk into the
       userfault registered range and optionally wake up the blocked
       thread. The source and destination addresses and the number of
       bytes to move are specified by the src, dst, and len fields of
       the uffdio_move structure pointed to by argp:

           struct uffdio_move {
               __u64 dst;    /* Destination of move */
               __u64 src;    /* Source of move */
               __u64 len;    /* Number of bytes to move */
               __u64 mode;   /* Flags controlling behavior of move */
               __s64 move;   /* Number of bytes moved, or negated error */
           };

       The following value may be bitwise ORed in mode to change the
       behavior of the UFFDIO_MOVE operation:

       UFFDIO_MOVE_MODE_DONTWAKE
              Do not wake up the thread that waits for page-fault
              resolution

       UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES
              Allow holes in the source virtual range that is being moved.
              When not specified, the holes will result in ENOENT error.
              When specified, the holes will be accounted as successfully
              moved memory. This is mostly useful to move hugepage aligned
              virtual regions without knowing if there are transparent
              hugepages in the regions or not, but preventing the risk of
              having to split the hugepage during the operation.

       The move field is used by the kernel to return the number of
       bytes that was actually moved, or an error (a negated errno-
       style value).  If the value returned in move doesn't match the
       value that was specified in len, the operation fails with the
       error EAGAIN.  The move field is output-only; it is not read by
       the UFFDIO_MOVE operation.

       The operation may fail for various reasons. Usually, remapping of
       pages that are not exclusive to the given process fail; once KSM
       might deduplicate pages or fork() COW-shares pages during fork()
       with child processes, they are no longer exclusive. Further, the
       kernel might only perform lightweight checks for detecting whether
       the pages are exclusive, and return -EBUSY in case that check fails.
       To make the operation more likely to succeed, KSM should be
       disabled, fork() should be avoided or MADV_DONTFORK should be
       configured for the source VMA before fork().

       This ioctl(2) operation returns 0 on success.  In this case, the
       entire area was moved.  On error, -1 is returned and errno is
       set to indicate the error.  Possible errors include:

       EAGAIN The number of bytes moved (i.e., the value returned in
              the move field) does not equal the value that was
              specified in the len field.

       EINVAL Either dst or len was not a multiple of the system page
              size, or the range specified by src and len or dst and len
              was invalid.

       EINVAL An invalid bit was specified in the mode field.

       ENOENT
              The source virtual memory range has unmapped holes and
              UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES is not set.

       EEXIST
              The destination virtual memory range is fully or partially
              mapped.

       EBUSY
              The pages in the source virtual memory range are either
              pinned or not exclusive to the process. The kernel might
              only perform lightweight checks for detecting whether the
              pages are exclusive. To make the operation more likely to
              succeed, KSM should be disabled, fork() should be avoided
              or MADV_DONTFORK should be configured for the source virtual
              memory area before fork().

       ENOMEM Allocating memory needed for the operation failed.

       ESRCH
              The target process has exited at the time of a UFFDIO_MOVE
              operation.

Link: https://lkml.kernel.org/r/20231206103702.3873743-3-surenb@google.com
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Brian Geffon <bgeffon@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Kalesh Singh <kaleshsingh@google.com>
Cc: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Nicolas Geoffray <ngeoffray@google.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: ZhangPeng <zhangpeng362@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 Documentation/admin-guide/mm/userfaultfd.rst |   3 +
 fs/userfaultfd.c                             |  72 ++++
 include/linux/rmap.h                         |   5 +
 include/linux/userfaultfd_k.h                |  11 +
 include/uapi/linux/userfaultfd.h             |  29 +-
 mm/huge_memory.c                             | 122 ++++++
 mm/khugepaged.c                              |   3 +
 mm/rmap.c                                    |   6 +
 mm/userfaultfd.c                             | 614 +++++++++++++++++++++++++++
 9 files changed, 864 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/Documentation/admin-guide/mm/userfaultfd.rst b/Documentation/admin-guide/mm/userfaultfd.rst
index 203e26da5f92..e5cc8848dcb3 100644
--- a/Documentation/admin-guide/mm/userfaultfd.rst
+++ b/Documentation/admin-guide/mm/userfaultfd.rst
@@ -113,6 +113,9 @@ events, except page fault notifications, may be generated:
   areas. ``UFFD_FEATURE_MINOR_SHMEM`` is the analogous feature indicating
   support for shmem virtual memory areas.
 
+- ``UFFD_FEATURE_MOVE`` indicates that the kernel supports moving an
+  existing page contents from userspace.
+
 The userland application should set the feature flags it intends to use
 when invoking the ``UFFDIO_API`` ioctl, to request that those features be
 enabled if supported.
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index e8af40b05549..6e2a4d6a0d8f 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -2005,6 +2005,75 @@ static inline unsigned int uffd_ctx_features(__u64 user_features)
 	return (unsigned int)user_features | UFFD_FEATURE_INITIALIZED;
 }
 
+static int userfaultfd_move(struct userfaultfd_ctx *ctx,
+			    unsigned long arg)
+{
+	__s64 ret;
+	struct uffdio_move uffdio_move;
+	struct uffdio_move __user *user_uffdio_move;
+	struct userfaultfd_wake_range range;
+	struct mm_struct *mm = ctx->mm;
+
+	user_uffdio_move = (struct uffdio_move __user *) arg;
+
+	if (atomic_read(&ctx->mmap_changing))
+		return -EAGAIN;
+
+	if (copy_from_user(&uffdio_move, user_uffdio_move,
+			   /* don't copy "move" last field */
+			   sizeof(uffdio_move)-sizeof(__s64)))
+		return -EFAULT;
+
+	/* Do not allow cross-mm moves. */
+	if (mm != current->mm)
+		return -EINVAL;
+
+	ret = validate_range(mm, uffdio_move.dst, uffdio_move.len);
+	if (ret)
+		return ret;
+
+	ret = validate_range(mm, uffdio_move.src, uffdio_move.len);
+	if (ret)
+		return ret;
+
+	if (uffdio_move.mode & ~(UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES|
+				  UFFDIO_MOVE_MODE_DONTWAKE))
+		return -EINVAL;
+
+	if (mmget_not_zero(mm)) {
+		mmap_read_lock(mm);
+
+		/* Re-check after taking mmap_lock */
+		if (likely(!atomic_read(&ctx->mmap_changing)))
+			ret = move_pages(ctx, mm, uffdio_move.dst, uffdio_move.src,
+					 uffdio_move.len, uffdio_move.mode);
+		else
+			ret = -EINVAL;
+
+		mmap_read_unlock(mm);
+		mmput(mm);
+	} else {
+		return -ESRCH;
+	}
+
+	if (unlikely(put_user(ret, &user_uffdio_move->move)))
+		return -EFAULT;
+	if (ret < 0)
+		goto out;
+
+	/* len == 0 would wake all */
+	VM_WARN_ON(!ret);
+	range.len = ret;
+	if (!(uffdio_move.mode & UFFDIO_MOVE_MODE_DONTWAKE)) {
+		range.start = uffdio_move.dst;
+		wake_userfault(ctx, &range);
+	}
+	ret = range.len == uffdio_move.len ? 0 : -EAGAIN;
+
+out:
+	return ret;
+}
+
 /*
  * userland asks for a certain API version and we return which bits
  * and ioctl commands are implemented in this kernel for such API
@@ -2097,6 +2166,9 @@ static long userfaultfd_ioctl(struct file *file, unsigned cmd,
 	case UFFDIO_ZEROPAGE:
 		ret = userfaultfd_zeropage(ctx, arg);
 		break;
+	case UFFDIO_MOVE:
+		ret = userfaultfd_move(ctx, arg);
+		break;
 	case UFFDIO_WRITEPROTECT:
 		ret = userfaultfd_writeprotect(ctx, arg);
 		break;
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 3c2fc291b071..af6a32b6f3e7 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -121,6 +121,11 @@ static inline void anon_vma_lock_write(struct anon_vma *anon_vma)
 	down_write(&anon_vma->root->rwsem);
 }
 
+static inline int anon_vma_trylock_write(struct anon_vma *anon_vma)
+{
+	return down_write_trylock(&anon_vma->root->rwsem);
+}
+
 static inline void anon_vma_unlock_write(struct anon_vma *anon_vma)
 {
 	up_write(&anon_vma->root->rwsem);
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index f2dc19f40d05..e4056547fbe6 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -93,6 +93,17 @@ extern int mwriteprotect_range(struct mm_struct *dst_mm,
 extern long uffd_wp_range(struct vm_area_struct *vma,
 			  unsigned long start, unsigned long len, bool enable_wp);
 
+/* move_pages */
+void double_pt_lock(spinlock_t *ptl1, spinlock_t *ptl2);
+void double_pt_unlock(spinlock_t *ptl1, spinlock_t *ptl2);
+ssize_t move_pages(struct userfaultfd_ctx *ctx, struct mm_struct *mm,
+		   unsigned long dst_start, unsigned long src_start,
+		   unsigned long len, __u64 flags);
+int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pmd_t dst_pmdval,
+			struct vm_area_struct *dst_vma,
+			struct vm_area_struct *src_vma,
+			unsigned long dst_addr, unsigned long src_addr);
+
 /* mm helpers */
 static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma,
 					struct vm_userfaultfd_ctx vm_ctx)
diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h
index 0dbc81015018..2841e4ea8f2c 100644
--- a/include/uapi/linux/userfaultfd.h
+++ b/include/uapi/linux/userfaultfd.h
@@ -41,7 +41,8 @@
 			   UFFD_FEATURE_WP_HUGETLBFS_SHMEM |	\
 			   UFFD_FEATURE_WP_UNPOPULATED |	\
 			   UFFD_FEATURE_POISON |		\
-			   UFFD_FEATURE_WP_ASYNC)
+			   UFFD_FEATURE_WP_ASYNC |		\
+			   UFFD_FEATURE_MOVE)
 #define UFFD_API_IOCTLS				\
 	((__u64)1 << _UFFDIO_REGISTER |		\
 	 (__u64)1 << _UFFDIO_UNREGISTER |	\
@@ -50,6 +51,7 @@
 	((__u64)1 << _UFFDIO_WAKE |		\
 	 (__u64)1 << _UFFDIO_COPY |		\
 	 (__u64)1 << _UFFDIO_ZEROPAGE |		\
+	 (__u64)1 << _UFFDIO_MOVE |		\
 	 (__u64)1 << _UFFDIO_WRITEPROTECT |	\
 	 (__u64)1 << _UFFDIO_CONTINUE |		\
 	 (__u64)1 << _UFFDIO_POISON)
@@ -73,6 +75,7 @@
 #define _UFFDIO_WAKE			(0x02)
 #define _UFFDIO_COPY			(0x03)
 #define _UFFDIO_ZEROPAGE		(0x04)
+#define _UFFDIO_MOVE			(0x05)
 #define _UFFDIO_WRITEPROTECT		(0x06)
 #define _UFFDIO_CONTINUE		(0x07)
 #define _UFFDIO_POISON			(0x08)
@@ -92,6 +95,8 @@
 				      struct uffdio_copy)
 #define UFFDIO_ZEROPAGE		_IOWR(UFFDIO, _UFFDIO_ZEROPAGE,	\
 				      struct uffdio_zeropage)
+#define UFFDIO_MOVE		_IOWR(UFFDIO, _UFFDIO_MOVE,	\
+				      struct uffdio_move)
 #define UFFDIO_WRITEPROTECT	_IOWR(UFFDIO, _UFFDIO_WRITEPROTECT, \
 				      struct uffdio_writeprotect)
 #define UFFDIO_CONTINUE		_IOWR(UFFDIO, _UFFDIO_CONTINUE,	\
@@ -222,6 +227,9 @@ struct uffdio_api {
 	 * asynchronous mode is supported in which the write fault is
 	 * automatically resolved and write-protection is un-set.
 	 * It implies UFFD_FEATURE_WP_UNPOPULATED.
+	 *
+	 * UFFD_FEATURE_MOVE indicates that the kernel supports moving an
+	 * existing page contents from userspace.
 	 */
 #define UFFD_FEATURE_PAGEFAULT_FLAG_WP		(1<<0)
 #define UFFD_FEATURE_EVENT_FORK			(1<<1)
@@ -239,6 +247,7 @@ struct uffdio_api {
 #define UFFD_FEATURE_WP_UNPOPULATED		(1<<13)
 #define UFFD_FEATURE_POISON			(1<<14)
 #define UFFD_FEATURE_WP_ASYNC			(1<<15)
+#define UFFD_FEATURE_MOVE			(1<<16)
 	__u64 features;
 
 	__u64 ioctls;
@@ -347,6 +356,24 @@ struct uffdio_poison {
 	__s64 updated;
 };
 
+struct uffdio_move {
+	__u64 dst;
+	__u64 src;
+	__u64 len;
+	/*
+	 * Especially if used to atomically remove memory from the
+	 * address space the wake on the dst range is not needed.
+	 */
+#define UFFDIO_MOVE_MODE_DONTWAKE		((__u64)1<<0)
+#define UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES	((__u64)1<<1)
+	__u64 mode;
+	/*
+	 * "move" is written by the ioctl and must be at the end: the
+	 * copy_from_user will not read the last 8 bytes.
+	 */
+	__s64 move;
+};
+
 /*
  * Flags for the userfaultfd(2) system call itself.
  */
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 387b030c7f15..6be1a380a298 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2141,6 +2141,128 @@ unlock:
 	return ret;
 }
 
+#ifdef CONFIG_USERFAULTFD
+/*
+ * The PT lock for src_pmd and the mmap_lock for reading are held by
+ * the caller, but it must return after releasing the page_table_lock.
+ * Just move the page from src_pmd to dst_pmd if possible.
+ * Return zero if succeeded in moving the page, -EAGAIN if it needs to be
+ * repeated by the caller, or other errors in case of failure.
+ */
+int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pmd_t dst_pmdval,
+			struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
+			unsigned long dst_addr, unsigned long src_addr)
+{
+	pmd_t _dst_pmd, src_pmdval;
+	struct page *src_page;
+	struct folio *src_folio;
+	struct anon_vma *src_anon_vma;
+	spinlock_t *src_ptl, *dst_ptl;
+	pgtable_t src_pgtable;
+	struct mmu_notifier_range range;
+	int err = 0;
+
+	src_pmdval = *src_pmd;
+	src_ptl = pmd_lockptr(mm, src_pmd);
+
+	lockdep_assert_held(src_ptl);
+	mmap_assert_locked(mm);
+
+	/* Sanity checks before the operation */
+	if (WARN_ON_ONCE(!pmd_none(dst_pmdval)) || WARN_ON_ONCE(src_addr & ~HPAGE_PMD_MASK) ||
+	    WARN_ON_ONCE(dst_addr & ~HPAGE_PMD_MASK)) {
+		spin_unlock(src_ptl);
+		return -EINVAL;
+	}
+
+	if (!pmd_trans_huge(src_pmdval)) {
+		spin_unlock(src_ptl);
+		if (is_pmd_migration_entry(src_pmdval)) {
+			pmd_migration_entry_wait(mm, &src_pmdval);
+			return -EAGAIN;
+		}
+		return -ENOENT;
+	}
+
+	src_page = pmd_page(src_pmdval);
+	if (unlikely(!PageAnonExclusive(src_page))) {
+		spin_unlock(src_ptl);
+		return -EBUSY;
+	}
+
+	src_folio = page_folio(src_page);
+	folio_get(src_folio);
+	spin_unlock(src_ptl);
+
+	flush_cache_range(src_vma, src_addr, src_addr + HPAGE_PMD_SIZE);
+	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, src_addr,
+				src_addr + HPAGE_PMD_SIZE);
+	mmu_notifier_invalidate_range_start(&range);
+
+	folio_lock(src_folio);
+
+	/*
+	 * split_huge_page walks the anon_vma chain without the page
+	 * lock. Serialize against it with the anon_vma lock, the page
+	 * lock is not enough.
+	 */
+	src_anon_vma = folio_get_anon_vma(src_folio);
+	if (!src_anon_vma) {
+		err = -EAGAIN;
+		goto unlock_folio;
+	}
+	anon_vma_lock_write(src_anon_vma);
+
+	dst_ptl = pmd_lockptr(mm, dst_pmd);
+	double_pt_lock(src_ptl, dst_ptl);
+	if (unlikely(!pmd_same(*src_pmd, src_pmdval) ||
+		     !pmd_same(*dst_pmd, dst_pmdval))) {
+		err = -EAGAIN;
+		goto unlock_ptls;
+	}
+	if (folio_maybe_dma_pinned(src_folio) ||
+	    !PageAnonExclusive(&src_folio->page)) {
+		err = -EBUSY;
+		goto unlock_ptls;
+	}
+
+	if (WARN_ON_ONCE(!folio_test_head(src_folio)) ||
+	    WARN_ON_ONCE(!folio_test_anon(src_folio))) {
+		err = -EBUSY;
+		goto unlock_ptls;
+	}
+
+	folio_move_anon_rmap(src_folio, dst_vma);
+	WRITE_ONCE(src_folio->index, linear_page_index(dst_vma, dst_addr));
+
+	src_pmdval = pmdp_huge_clear_flush(src_vma, src_addr, src_pmd);
+	/* Folio got pinned from under us. Put it back and fail the move. */
+	if (folio_maybe_dma_pinned(src_folio)) {
+		set_pmd_at(mm, src_addr, src_pmd, src_pmdval);
+		err = -EBUSY;
+		goto unlock_ptls;
+	}
+
+	_dst_pmd = mk_huge_pmd(&src_folio->page, dst_vma->vm_page_prot);
+	/* Follow mremap() behavior and treat the entry dirty after the move */
+	_dst_pmd = pmd_mkwrite(pmd_mkdirty(_dst_pmd), dst_vma);
+	set_pmd_at(mm, dst_addr, dst_pmd, _dst_pmd);
+
+	src_pgtable = pgtable_trans_huge_withdraw(mm, src_pmd);
+	pgtable_trans_huge_deposit(mm, dst_pmd, src_pgtable);
+unlock_ptls:
+	double_pt_unlock(src_ptl, dst_ptl);
+	anon_vma_unlock_write(src_anon_vma);
+	put_anon_vma(src_anon_vma);
+unlock_folio:
+	/* unblock rmap walks */
+	folio_unlock(src_folio);
+	mmu_notifier_invalidate_range_end(&range);
+	folio_put(src_folio);
+	return err;
+}
+#endif /* CONFIG_USERFAULTFD */
+
 /*
  * Returns page table lock pointer if a given pmd maps a thp, NULL otherwise.
  *
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index d72aecd3624a..de174d049e71 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1140,6 +1140,9 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address,
 	 * Prevent all access to pagetables with the exception of
 	 * gup_fast later handled by the ptep_clear_flush and the VM
 	 * handled by the anon_vma lock + PG_lock.
+	 *
+	 * UFFDIO_MOVE is prevented to race as well thanks to the
+	 * mmap_lock.
 	 */
 	mmap_write_lock(mm);
 	result = hugepage_vma_revalidate(mm, address, true, &vma, cc);
diff --git a/mm/rmap.c b/mm/rmap.c
index 15a55304aa3b..846fc79f3ca9 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -490,6 +490,12 @@ void __init anon_vma_init(void)
  * page_remove_rmap() that the anon_vma pointer from page->mapping is valid
  * if there is a mapcount, we can dereference the anon_vma after observing
  * those.
+ *
+ * NOTE: the caller should normally hold folio lock when calling this.  If
+ * not, the caller needs to double check the anon_vma didn't change after
+ * taking the anon_vma lock for either read or write (UFFDIO_MOVE can modify it
+ * concurrently without folio lock protection). See folio_lock_anon_vma_read()
+ * which has already covered that, and comment above remap_pages().
  */
 struct anon_vma *folio_get_anon_vma(struct folio *folio)
 {
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 0b6ca553bebe..9ec814e47e99 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -842,3 +842,617 @@ out_unlock:
 	mmap_read_unlock(dst_mm);
 	return err;
 }
+
+
+void double_pt_lock(spinlock_t *ptl1,
+		    spinlock_t *ptl2)
+	__acquires(ptl1)
+	__acquires(ptl2)
+{
+	spinlock_t *ptl_tmp;
+
+	if (ptl1 > ptl2) {
+		/* exchange ptl1 and ptl2 */
+		ptl_tmp = ptl1;
+		ptl1 = ptl2;
+		ptl2 = ptl_tmp;
+	}
+	/* lock in virtual address order to avoid lock inversion */
+	spin_lock(ptl1);
+	if (ptl1 != ptl2)
+		spin_lock_nested(ptl2, SINGLE_DEPTH_NESTING);
+	else
+		__acquire(ptl2);
+}
+
+void double_pt_unlock(spinlock_t *ptl1,
+		      spinlock_t *ptl2)
+	__releases(ptl1)
+	__releases(ptl2)
+{
+	spin_unlock(ptl1);
+	if (ptl1 != ptl2)
+		spin_unlock(ptl2);
+	else
+		__release(ptl2);
+}
+
+
+static int move_present_pte(struct mm_struct *mm,
+			    struct vm_area_struct *dst_vma,
+			    struct vm_area_struct *src_vma,
+			    unsigned long dst_addr, unsigned long src_addr,
+			    pte_t *dst_pte, pte_t *src_pte,
+			    pte_t orig_dst_pte, pte_t orig_src_pte,
+			    spinlock_t *dst_ptl, spinlock_t *src_ptl,
+			    struct folio *src_folio)
+{
+	int err = 0;
+
+	double_pt_lock(dst_ptl, src_ptl);
+
+	if (!pte_same(*src_pte, orig_src_pte) ||
+	    !pte_same(*dst_pte, orig_dst_pte)) {
+		err = -EAGAIN;
+		goto out;
+	}
+	if (folio_test_large(src_folio) ||
+	    folio_maybe_dma_pinned(src_folio) ||
+	    !PageAnonExclusive(&src_folio->page)) {
+		err = -EBUSY;
+		goto out;
+	}
+
+	folio_move_anon_rmap(src_folio, dst_vma);
+	WRITE_ONCE(src_folio->index, linear_page_index(dst_vma, dst_addr));
+
+	orig_src_pte = ptep_clear_flush(src_vma, src_addr, src_pte);
+	/* Folio got pinned from under us. Put it back and fail the move. */
+	if (folio_maybe_dma_pinned(src_folio)) {
+		set_pte_at(mm, src_addr, src_pte, orig_src_pte);
+		err = -EBUSY;
+		goto out;
+	}
+
+	orig_dst_pte = mk_pte(&src_folio->page, dst_vma->vm_page_prot);
+	/* Follow mremap() behavior and treat the entry dirty after the move */
+	orig_dst_pte = pte_mkwrite(pte_mkdirty(orig_dst_pte), dst_vma);
+
+	set_pte_at(mm, dst_addr, dst_pte, orig_dst_pte);
+out:
+	double_pt_unlock(dst_ptl, src_ptl);
+	return err;
+}
+
+static int move_swap_pte(struct mm_struct *mm,
+			 unsigned long dst_addr, unsigned long src_addr,
+			 pte_t *dst_pte, pte_t *src_pte,
+			 pte_t orig_dst_pte, pte_t orig_src_pte,
+			 spinlock_t *dst_ptl, spinlock_t *src_ptl)
+{
+	if (!pte_swp_exclusive(orig_src_pte))
+		return -EBUSY;
+
+	double_pt_lock(dst_ptl, src_ptl);
+
+	if (!pte_same(*src_pte, orig_src_pte) ||
+	    !pte_same(*dst_pte, orig_dst_pte)) {
+		double_pt_unlock(dst_ptl, src_ptl);
+		return -EAGAIN;
+	}
+
+	orig_src_pte = ptep_get_and_clear(mm, src_addr, src_pte);
+	set_pte_at(mm, dst_addr, dst_pte, orig_src_pte);
+	double_pt_unlock(dst_ptl, src_ptl);
+
+	return 0;
+}
+
+/*
+ * The mmap_lock for reading is held by the caller. Just move the page
+ * from src_pmd to dst_pmd if possible, and return true if succeeded
+ * in moving the page.
+ */
+static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd,
+			  struct vm_area_struct *dst_vma,
+			  struct vm_area_struct *src_vma,
+			  unsigned long dst_addr, unsigned long src_addr,
+			  __u64 mode)
+{
+	swp_entry_t entry;
+	pte_t orig_src_pte, orig_dst_pte;
+	pte_t src_folio_pte;
+	spinlock_t *src_ptl, *dst_ptl;
+	pte_t *src_pte = NULL;
+	pte_t *dst_pte = NULL;
+
+	struct folio *src_folio = NULL;
+	struct anon_vma *src_anon_vma = NULL;
+	struct mmu_notifier_range range;
+	int err = 0;
+
+	flush_cache_range(src_vma, src_addr, src_addr + PAGE_SIZE);
+	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm,
+				src_addr, src_addr + PAGE_SIZE);
+	mmu_notifier_invalidate_range_start(&range);
+retry:
+	dst_pte = pte_offset_map_nolock(mm, dst_pmd, dst_addr, &dst_ptl);
+
+	/* Retry if a huge pmd materialized from under us */
+	if (unlikely(!dst_pte)) {
+		err = -EAGAIN;
+		goto out;
+	}
+
+	src_pte = pte_offset_map_nolock(mm, src_pmd, src_addr, &src_ptl);
+
+	/*
+	 * We held the mmap_lock for reading so MADV_DONTNEED
+	 * can zap transparent huge pages under us, or the
+	 * transparent huge page fault can establish new
+	 * transparent huge pages under us.
+	 */
+	if (unlikely(!src_pte)) {
+		err = -EAGAIN;
+		goto out;
+	}
+
+	/* Sanity checks before the operation */
+	if (WARN_ON_ONCE(pmd_none(*dst_pmd)) ||	WARN_ON_ONCE(pmd_none(*src_pmd)) ||
+	    WARN_ON_ONCE(pmd_trans_huge(*dst_pmd)) || WARN_ON_ONCE(pmd_trans_huge(*src_pmd))) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	spin_lock(dst_ptl);
+	orig_dst_pte = *dst_pte;
+	spin_unlock(dst_ptl);
+	if (!pte_none(orig_dst_pte)) {
+		err = -EEXIST;
+		goto out;
+	}
+
+	spin_lock(src_ptl);
+	orig_src_pte = *src_pte;
+	spin_unlock(src_ptl);
+	if (pte_none(orig_src_pte)) {
+		if (!(mode & UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES))
+			err = -ENOENT;
+		else /* nothing to do to move a hole */
+			err = 0;
+		goto out;
+	}
+
+	/* If PTE changed after we locked the folio them start over */
+	if (src_folio && unlikely(!pte_same(src_folio_pte, orig_src_pte))) {
+		err = -EAGAIN;
+		goto out;
+	}
+
+	if (pte_present(orig_src_pte)) {
+		/*
+		 * Pin and lock both source folio and anon_vma. Since we are in
+		 * RCU read section, we can't block, so on contention have to
+		 * unmap the ptes, obtain the lock and retry.
+		 */
+		if (!src_folio) {
+			struct folio *folio;
+
+			/*
+			 * Pin the page while holding the lock to be sure the
+			 * page isn't freed under us
+			 */
+			spin_lock(src_ptl);
+			if (!pte_same(orig_src_pte, *src_pte)) {
+				spin_unlock(src_ptl);
+				err = -EAGAIN;
+				goto out;
+			}
+
+			folio = vm_normal_folio(src_vma, src_addr, orig_src_pte);
+			if (!folio || !PageAnonExclusive(&folio->page)) {
+				spin_unlock(src_ptl);
+				err = -EBUSY;
+				goto out;
+			}
+
+			folio_get(folio);
+			src_folio = folio;
+			src_folio_pte = orig_src_pte;
+			spin_unlock(src_ptl);
+
+			if (!folio_trylock(src_folio)) {
+				pte_unmap(&orig_src_pte);
+				pte_unmap(&orig_dst_pte);
+				src_pte = dst_pte = NULL;
+				/* now we can block and wait */
+				folio_lock(src_folio);
+				goto retry;
+			}
+
+			if (WARN_ON_ONCE(!folio_test_anon(src_folio))) {
+				err = -EBUSY;
+				goto out;
+			}
+		}
+
+		/* at this point we have src_folio locked */
+		if (folio_test_large(src_folio)) {
+			err = split_folio(src_folio);
+			if (err)
+				goto out;
+		}
+
+		if (!src_anon_vma) {
+			/*
+			 * folio_referenced walks the anon_vma chain
+			 * without the folio lock. Serialize against it with
+			 * the anon_vma lock, the folio lock is not enough.
+			 */
+			src_anon_vma = folio_get_anon_vma(src_folio);
+			if (!src_anon_vma) {
+				/* page was unmapped from under us */
+				err = -EAGAIN;
+				goto out;
+			}
+			if (!anon_vma_trylock_write(src_anon_vma)) {
+				pte_unmap(&orig_src_pte);
+				pte_unmap(&orig_dst_pte);
+				src_pte = dst_pte = NULL;
+				/* now we can block and wait */
+				anon_vma_lock_write(src_anon_vma);
+				goto retry;
+			}
+		}
+
+		err = move_present_pte(mm,  dst_vma, src_vma,
+				       dst_addr, src_addr, dst_pte, src_pte,
+				       orig_dst_pte, orig_src_pte,
+				       dst_ptl, src_ptl, src_folio);
+	} else {
+		entry = pte_to_swp_entry(orig_src_pte);
+		if (non_swap_entry(entry)) {
+			if (is_migration_entry(entry)) {
+				pte_unmap(&orig_src_pte);
+				pte_unmap(&orig_dst_pte);
+				src_pte = dst_pte = NULL;
+				migration_entry_wait(mm, src_pmd, src_addr);
+				err = -EAGAIN;
+			} else
+				err = -EFAULT;
+			goto out;
+		}
+
+		err = move_swap_pte(mm, dst_addr, src_addr,
+				    dst_pte, src_pte,
+				    orig_dst_pte, orig_src_pte,
+				    dst_ptl, src_ptl);
+	}
+
+out:
+	if (src_anon_vma) {
+		anon_vma_unlock_write(src_anon_vma);
+		put_anon_vma(src_anon_vma);
+	}
+	if (src_folio) {
+		folio_unlock(src_folio);
+		folio_put(src_folio);
+	}
+	if (dst_pte)
+		pte_unmap(dst_pte);
+	if (src_pte)
+		pte_unmap(src_pte);
+	mmu_notifier_invalidate_range_end(&range);
+
+	return err;
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline bool move_splits_huge_pmd(unsigned long dst_addr,
+					unsigned long src_addr,
+					unsigned long src_end)
+{
+	return (src_addr & ~HPAGE_PMD_MASK) || (dst_addr & ~HPAGE_PMD_MASK) ||
+		src_end - src_addr < HPAGE_PMD_SIZE;
+}
+#else
+static inline bool move_splits_huge_pmd(unsigned long dst_addr,
+					unsigned long src_addr,
+					unsigned long src_end)
+{
+	/* This is unreachable anyway, just to avoid warnings when HPAGE_PMD_SIZE==0 */
+	return false;
+}
+#endif
+
+static inline bool vma_move_compatible(struct vm_area_struct *vma)
+{
+	return !(vma->vm_flags & (VM_PFNMAP | VM_IO |  VM_HUGETLB |
+				  VM_MIXEDMAP | VM_SHADOW_STACK));
+}
+
+static int validate_move_areas(struct userfaultfd_ctx *ctx,
+			       struct vm_area_struct *src_vma,
+			       struct vm_area_struct *dst_vma)
+{
+	/* Only allow moving if both have the same access and protection */
+	if ((src_vma->vm_flags & VM_ACCESS_FLAGS) != (dst_vma->vm_flags & VM_ACCESS_FLAGS) ||
+	    pgprot_val(src_vma->vm_page_prot) != pgprot_val(dst_vma->vm_page_prot))
+		return -EINVAL;
+
+	/* Only allow moving if both are mlocked or both aren't */
+	if ((src_vma->vm_flags & VM_LOCKED) != (dst_vma->vm_flags & VM_LOCKED))
+		return -EINVAL;
+
+	/*
+	 * For now, we keep it simple and only move between writable VMAs.
+	 * Access flags are equal, therefore cheching only the source is enough.
+	 */
+	if (!(src_vma->vm_flags & VM_WRITE))
+		return -EINVAL;
+
+	/* Check if vma flags indicate content which can be moved */
+	if (!vma_move_compatible(src_vma) || !vma_move_compatible(dst_vma))
+		return -EINVAL;
+
+	/* Ensure dst_vma is registered in uffd we are operating on */
+	if (!dst_vma->vm_userfaultfd_ctx.ctx ||
+	    dst_vma->vm_userfaultfd_ctx.ctx != ctx)
+		return -EINVAL;
+
+	/* Only allow moving across anonymous vmas */
+	if (!vma_is_anonymous(src_vma) || !vma_is_anonymous(dst_vma))
+		return -EINVAL;
+
+	/*
+	 * Ensure the dst_vma has a anon_vma or this page
+	 * would get a NULL anon_vma when moved in the
+	 * dst_vma.
+	 */
+	if (unlikely(anon_vma_prepare(dst_vma)))
+		return -ENOMEM;
+
+	return 0;
+}
+
+/**
+ * move_pages - move arbitrary anonymous pages of an existing vma
+ * @ctx: pointer to the userfaultfd context
+ * @mm: the address space to move pages
+ * @dst_start: start of the destination virtual memory range
+ * @src_start: start of the source virtual memory range
+ * @len: length of the virtual memory range
+ * @mode: flags from uffdio_move.mode
+ *
+ * Must be called with mmap_lock held for read.
+ *
+ * move_pages() remaps arbitrary anonymous pages atomically in zero
+ * copy. It only works on non shared anonymous pages because those can
+ * be relocated without generating non linear anon_vmas in the rmap
+ * code.
+ *
+ * It provides a zero copy mechanism to handle userspace page faults.
+ * The source vma pages should have mapcount == 1, which can be
+ * enforced by using madvise(MADV_DONTFORK) on src vma.
+ *
+ * The thread receiving the page during the userland page fault
+ * will receive the faulting page in the source vma through the network,
+ * storage or any other I/O device (MADV_DONTFORK in the source vma
+ * avoids move_pages() to fail with -EBUSY if the process forks before
+ * move_pages() is called), then it will call move_pages() to map the
+ * page in the faulting address in the destination vma.
+ *
+ * This userfaultfd command works purely via pagetables, so it's the
+ * most efficient way to move physical non shared anonymous pages
+ * across different virtual addresses. Unlike mremap()/mmap()/munmap()
+ * it does not create any new vmas. The mapping in the destination
+ * address is atomic.
+ *
+ * It only works if the vma protection bits are identical from the
+ * source and destination vma.
+ *
+ * It can remap non shared anonymous pages within the same vma too.
+ *
+ * If the source virtual memory range has any unmapped holes, or if
+ * the destination virtual memory range is not a whole unmapped hole,
+ * move_pages() will fail respectively with -ENOENT or -EEXIST. This
+ * provides a very strict behavior to avoid any chance of memory
+ * corruption going unnoticed if there are userland race conditions.
+ * Only one thread should resolve the userland page fault at any given
+ * time for any given faulting address. This means that if two threads
+ * try to both call move_pages() on the same destination address at the
+ * same time, the second thread will get an explicit error from this
+ * command.
+ *
+ * The command retval will return "len" is successful. The command
+ * however can be interrupted by fatal signals or errors. If
+ * interrupted it will return the number of bytes successfully
+ * remapped before the interruption if any, or the negative error if
+ * none. It will never return zero. Either it will return an error or
+ * an amount of bytes successfully moved. If the retval reports a
+ * "short" remap, the move_pages() command should be repeated by
+ * userland with src+retval, dst+reval, len-retval if it wants to know
+ * about the error that interrupted it.
+ *
+ * The UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES flag can be specified to
+ * prevent -ENOENT errors to materialize if there are holes in the
+ * source virtual range that is being remapped. The holes will be
+ * accounted as successfully remapped in the retval of the
+ * command. This is mostly useful to remap hugepage naturally aligned
+ * virtual regions without knowing if there are transparent hugepage
+ * in the regions or not, but preventing the risk of having to split
+ * the hugepmd during the remap.
+ *
+ * If there's any rmap walk that is taking the anon_vma locks without
+ * first obtaining the folio lock (the only current instance is
+ * folio_referenced), they will have to verify if the folio->mapping
+ * has changed after taking the anon_vma lock. If it changed they
+ * should release the lock and retry obtaining a new anon_vma, because
+ * it means the anon_vma was changed by move_pages() before the lock
+ * could be obtained. This is the only additional complexity added to
+ * the rmap code to provide this anonymous page remapping functionality.
+ */
+ssize_t move_pages(struct userfaultfd_ctx *ctx, struct mm_struct *mm,
+		   unsigned long dst_start, unsigned long src_start,
+		   unsigned long len, __u64 mode)
+{
+	struct vm_area_struct *src_vma, *dst_vma;
+	unsigned long src_addr, dst_addr;
+	pmd_t *src_pmd, *dst_pmd;
+	long err = -EINVAL;
+	ssize_t moved = 0;
+
+	/* Sanitize the command parameters. */
+	if (WARN_ON_ONCE(src_start & ~PAGE_MASK) ||
+	    WARN_ON_ONCE(dst_start & ~PAGE_MASK) ||
+	    WARN_ON_ONCE(len & ~PAGE_MASK))
+		goto out;
+
+	/* Does the address range wrap, or is the span zero-sized? */
+	if (WARN_ON_ONCE(src_start + len <= src_start) ||
+	    WARN_ON_ONCE(dst_start + len <= dst_start))
+		goto out;
+
+	/*
+	 * Make sure the vma is not shared, that the src and dst remap
+	 * ranges are both valid and fully within a single existing
+	 * vma.
+	 */
+	src_vma = find_vma(mm, src_start);
+	if (!src_vma || (src_vma->vm_flags & VM_SHARED))
+		goto out;
+	if (src_start < src_vma->vm_start ||
+	    src_start + len > src_vma->vm_end)
+		goto out;
+
+	dst_vma = find_vma(mm, dst_start);
+	if (!dst_vma || (dst_vma->vm_flags & VM_SHARED))
+		goto out;
+	if (dst_start < dst_vma->vm_start ||
+	    dst_start + len > dst_vma->vm_end)
+		goto out;
+
+	err = validate_move_areas(ctx, src_vma, dst_vma);
+	if (err)
+		goto out;
+
+	for (src_addr = src_start, dst_addr = dst_start;
+	     src_addr < src_start + len;) {
+		spinlock_t *ptl;
+		pmd_t dst_pmdval;
+		unsigned long step_size;
+
+		/*
+		 * Below works because anonymous area would not have a
+		 * transparent huge PUD. If file-backed support is added,
+		 * that case would need to be handled here.
+		 */
+		src_pmd = mm_find_pmd(mm, src_addr);
+		if (unlikely(!src_pmd)) {
+			if (!(mode & UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES)) {
+				err = -ENOENT;
+				break;
+			}
+			src_pmd = mm_alloc_pmd(mm, src_addr);
+			if (unlikely(!src_pmd)) {
+				err = -ENOMEM;
+				break;
+			}
+		}
+		dst_pmd = mm_alloc_pmd(mm, dst_addr);
+		if (unlikely(!dst_pmd)) {
+			err = -ENOMEM;
+			break;
+		}
+
+		dst_pmdval = pmdp_get_lockless(dst_pmd);
+		/*
+		 * If the dst_pmd is mapped as THP don't override it and just
+		 * be strict. If dst_pmd changes into TPH after this check, the
+		 * move_pages_huge_pmd() will detect the change and retry
+		 * while move_pages_pte() will detect the change and fail.
+		 */
+		if (unlikely(pmd_trans_huge(dst_pmdval))) {
+			err = -EEXIST;
+			break;
+		}
+
+		ptl = pmd_trans_huge_lock(src_pmd, src_vma);
+		if (ptl) {
+			if (pmd_devmap(*src_pmd)) {
+				spin_unlock(ptl);
+				err = -ENOENT;
+				break;
+			}
+
+			/* Check if we can move the pmd without splitting it. */
+			if (move_splits_huge_pmd(dst_addr, src_addr, src_start + len) ||
+			    !pmd_none(dst_pmdval)) {
+				struct folio *folio = pfn_folio(pmd_pfn(*src_pmd));
+
+				if (!folio || !PageAnonExclusive(&folio->page)) {
+					spin_unlock(ptl);
+					err = -EBUSY;
+					break;
+				}
+
+				spin_unlock(ptl);
+				split_huge_pmd(src_vma, src_pmd, src_addr);
+				/* The folio will be split by move_pages_pte() */
+				continue;
+			}
+
+			err = move_pages_huge_pmd(mm, dst_pmd, src_pmd,
+						  dst_pmdval, dst_vma, src_vma,
+						  dst_addr, src_addr);
+			step_size = HPAGE_PMD_SIZE;
+		} else {
+			if (pmd_none(*src_pmd)) {
+				if (!(mode & UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES)) {
+					err = -ENOENT;
+					break;
+				}
+				if (unlikely(__pte_alloc(mm, src_pmd))) {
+					err = -ENOMEM;
+					break;
+				}
+			}
+
+			if (unlikely(pte_alloc(mm, dst_pmd))) {
+				err = -ENOMEM;
+				break;
+			}
+
+			err = move_pages_pte(mm, dst_pmd, src_pmd,
+					     dst_vma, src_vma,
+					     dst_addr, src_addr, mode);
+			step_size = PAGE_SIZE;
+		}
+
+		cond_resched();
+
+		if (fatal_signal_pending(current)) {
+			/* Do not override an error */
+			if (!err || err == -EAGAIN)
+				err = -EINTR;
+			break;
+		}
+
+		if (err) {
+			if (err == -EAGAIN)
+				continue;
+			break;
+		}
+
+		/* Proceed to the next page */
+		dst_addr += step_size;
+		src_addr += step_size;
+		moved += step_size;
+	}
+
+out:
+	VM_WARN_ON(moved < 0);
+	VM_WARN_ON(err > 0);
+	VM_WARN_ON(!moved && !err);
+	return moved ? moved : err;
+}
-- 
cgit v1.2.3


From 96db66d9c8f3c1547325af01b1f328b85d6ee1b9 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Mon, 11 Dec 2023 16:22:06 +0000
Subject: mm: convert ksm_might_need_to_copy() to work on folios

Patch series "Finish two folio conversions".

Most callers of page_add_new_anon_rmap() and
lru_cache_add_inactive_or_unevictable() have been converted to their folio
equivalents, but there are still a few stragglers.  There's a bit of
preparatory work in ksm and unuse_pte(), but after that it's pretty
mechanical.


This patch (of 9):

Accept a folio as an argument and return a folio result.  Removes a call
to compound_head() in do_swap_page(), and prevents folio & page from
getting out of sync in unuse_pte().

Reviewed-by: David Hildenbrand <david@redhat.com>
[willy@infradead.org: fix smatch warning]
  Link: https://lkml.kernel.org/r/ZXnPtblC6A1IkyAB@casper.infradead.org
[david@redhat.com: only adjust the page if the folio changed]
  Link: https://lkml.kernel.org/r/6a8f2110-fa91-4c10-9eae-88315309a6e3@redhat.com
Link: https://lkml.kernel.org/r/20231211162214.2146080-1-willy@infradead.org
Link: https://lkml.kernel.org/r/20231211162214.2146080-2-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/ksm.h |  6 +++---
 mm/ksm.c            | 21 +++++++++++----------
 mm/memory.c         | 11 +++++++----
 mm/swapfile.c       |  8 +++++---
 4 files changed, 26 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/linux/ksm.h b/include/linux/ksm.h
index 4643d5244e77..401348e9f92b 100644
--- a/include/linux/ksm.h
+++ b/include/linux/ksm.h
@@ -76,7 +76,7 @@ static inline void ksm_exit(struct mm_struct *mm)
  * We'd like to make this conditional on vma->vm_flags & VM_MERGEABLE,
  * but what if the vma was unmerged while the page was swapped out?
  */
-struct page *ksm_might_need_to_copy(struct page *page,
+struct folio *ksm_might_need_to_copy(struct folio *folio,
 			struct vm_area_struct *vma, unsigned long addr);
 
 void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc);
@@ -129,10 +129,10 @@ static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
 	return 0;
 }
 
-static inline struct page *ksm_might_need_to_copy(struct page *page,
+static inline struct folio *ksm_might_need_to_copy(struct folio *folio,
 			struct vm_area_struct *vma, unsigned long addr)
 {
-	return page;
+	return folio;
 }
 
 static inline void rmap_walk_ksm(struct folio *folio,
diff --git a/mm/ksm.c b/mm/ksm.c
index c0e1995fb444..e2ce850c2739 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -2873,30 +2873,30 @@ void __ksm_exit(struct mm_struct *mm)
 	trace_ksm_exit(mm);
 }
 
-struct page *ksm_might_need_to_copy(struct page *page,
+struct folio *ksm_might_need_to_copy(struct folio *folio,
 			struct vm_area_struct *vma, unsigned long addr)
 {
-	struct folio *folio = page_folio(page);
+	struct page *page = folio_page(folio, 0);
 	struct anon_vma *anon_vma = folio_anon_vma(folio);
 	struct folio *new_folio;
 
 	if (folio_test_large(folio))
-		return page;
+		return folio;
 
 	if (folio_test_ksm(folio)) {
 		if (folio_stable_node(folio) &&
 		    !(ksm_run & KSM_RUN_UNMERGE))
-			return page;	/* no need to copy it */
+			return folio;	/* no need to copy it */
 	} else if (!anon_vma) {
-		return page;		/* no need to copy it */
+		return folio;		/* no need to copy it */
 	} else if (folio->index == linear_page_index(vma, addr) &&
 			anon_vma->root == vma->anon_vma->root) {
-		return page;		/* still no need to copy it */
+		return folio;		/* still no need to copy it */
 	}
 	if (PageHWPoison(page))
 		return ERR_PTR(-EHWPOISON);
 	if (!folio_test_uptodate(folio))
-		return page;		/* let do_swap_page report the error */
+		return folio;		/* let do_swap_page report the error */
 
 	new_folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, addr, false);
 	if (new_folio &&
@@ -2905,9 +2905,10 @@ struct page *ksm_might_need_to_copy(struct page *page,
 		new_folio = NULL;
 	}
 	if (new_folio) {
-		if (copy_mc_user_highpage(&new_folio->page, page, addr, vma)) {
+		if (copy_mc_user_highpage(folio_page(new_folio, 0), page,
+								addr, vma)) {
 			folio_put(new_folio);
-			memory_failure_queue(page_to_pfn(page), 0);
+			memory_failure_queue(folio_pfn(folio), 0);
 			return ERR_PTR(-EHWPOISON);
 		}
 		folio_set_dirty(new_folio);
@@ -2918,7 +2919,7 @@ struct page *ksm_might_need_to_copy(struct page *page,
 #endif
 	}
 
-	return new_folio ? &new_folio->page : NULL;
+	return new_folio;
 }
 
 void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc)
diff --git a/mm/memory.c b/mm/memory.c
index b9cc56a75f4b..7649cb9eb7f5 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3942,15 +3942,18 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 		 * page->index of !PageKSM() pages would be nonlinear inside the
 		 * anon VMA -- PageKSM() is lost on actual swapout.
 		 */
-		page = ksm_might_need_to_copy(page, vma, vmf->address);
-		if (unlikely(!page)) {
+		folio = ksm_might_need_to_copy(folio, vma, vmf->address);
+		if (unlikely(!folio)) {
 			ret = VM_FAULT_OOM;
+			folio = swapcache;
 			goto out_page;
-		} else if (unlikely(PTR_ERR(page) == -EHWPOISON)) {
+		} else if (unlikely(folio == ERR_PTR(-EHWPOISON))) {
 			ret = VM_FAULT_HWPOISON;
+			folio = swapcache;
 			goto out_page;
 		}
-		folio = page_folio(page);
+		if (folio != swapcache)
+			page = folio_page(folio, 0);
 
 		/*
 		 * If we want to map a page that's in the swapcache writable, we
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 8be70912e298..0371b7b3cd27 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1749,11 +1749,13 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 	int ret = 1;
 
 	swapcache = page;
-	page = ksm_might_need_to_copy(page, vma, addr);
-	if (unlikely(!page))
+	folio = ksm_might_need_to_copy(folio, vma, addr);
+	if (unlikely(!folio))
 		return -ENOMEM;
-	else if (unlikely(PTR_ERR(page) == -EHWPOISON))
+	else if (unlikely(folio == ERR_PTR(-EHWPOISON)))
 		hwpoisoned = true;
+	else
+		page = folio_file_page(folio, swp_offset(entry));
 
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	if (unlikely(!pte || !pte_same_as_swp(ptep_get(pte),
-- 
cgit v1.2.3


From cafa8e37a2ebd344ae0774324c21f46640bbaab3 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Mon, 11 Dec 2023 16:22:14 +0000
Subject: mm: remove page_add_new_anon_rmap and
 lru_cache_add_inactive_or_unevictable

All callers have now been converted to folio_add_new_anon_rmap() and
folio_add_lru_vma() so we can remove the wrapper.

Link: https://lkml.kernel.org/r/20231211162214.2146080-10-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/rmap.h |  2 --
 include/linux/swap.h |  3 ---
 mm/folio-compat.c    | 16 ----------------
 3 files changed, 21 deletions(-)

(limited to 'include')

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index af6a32b6f3e7..0ae2bb0e77f5 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -197,8 +197,6 @@ typedef int __bitwise rmap_t;
 void folio_move_anon_rmap(struct folio *, struct vm_area_struct *);
 void page_add_anon_rmap(struct page *, struct vm_area_struct *,
 		unsigned long address, rmap_t flags);
-void page_add_new_anon_rmap(struct page *, struct vm_area_struct *,
-		unsigned long address);
 void folio_add_new_anon_rmap(struct folio *, struct vm_area_struct *,
 		unsigned long address);
 void page_add_file_rmap(struct page *, struct vm_area_struct *,
diff --git a/include/linux/swap.h b/include/linux/swap.h
index f6dd6575b905..3e1909087f6a 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -397,9 +397,6 @@ void folio_deactivate(struct folio *folio);
 void folio_mark_lazyfree(struct folio *folio);
 extern void swap_setup(void);
 
-extern void lru_cache_add_inactive_or_unevictable(struct page *page,
-						struct vm_area_struct *vma);
-
 /* linux/mm/vmscan.c */
 extern unsigned long zone_reclaimable_pages(struct zone *zone);
 extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
diff --git a/mm/folio-compat.c b/mm/folio-compat.c
index aee3b9a16828..50412014f16f 100644
--- a/mm/folio-compat.c
+++ b/mm/folio-compat.c
@@ -77,12 +77,6 @@ bool redirty_page_for_writepage(struct writeback_control *wbc,
 }
 EXPORT_SYMBOL(redirty_page_for_writepage);
 
-void lru_cache_add_inactive_or_unevictable(struct page *page,
-		struct vm_area_struct *vma)
-{
-	folio_add_lru_vma(page_folio(page), vma);
-}
-
 int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
 		pgoff_t index, gfp_t gfp)
 {
@@ -122,13 +116,3 @@ void putback_lru_page(struct page *page)
 {
 	folio_putback_lru(page_folio(page));
 }
-
-#ifdef CONFIG_MMU
-void page_add_new_anon_rmap(struct page *page, struct vm_area_struct *vma,
-		unsigned long address)
-{
-	VM_BUG_ON_PAGE(PageTail(page), page);
-
-	return folio_add_new_anon_rmap((struct folio *)page, vma, address);
-}
-#endif
-- 
cgit v1.2.3


From 5088b49730afaaf3134d42705cfcff7ce8be082e Mon Sep 17 00:00:00 2001
From: Stefan Roesch <shr@devkernel.io>
Date: Mon, 18 Dec 2023 15:10:53 -0800
Subject: mm/ksm: add tracepoint for ksm advisor

This adds a new tracepoint for the ksm advisor.  It reports the last scan
time, the new setting of the pages_to_scan parameter and the average cpu
percent usage of the ksmd background thread for the last scan.

Link: https://lkml.kernel.org/r/20231218231054.1625219-4-shr@devkernel.io
Signed-off-by: Stefan Roesch <shr@devkernel.io>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Rik van Riel <riel@surriel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/trace/events/ksm.h | 33 +++++++++++++++++++++++++++++++++
 mm/ksm.c                   |  1 +
 2 files changed, 34 insertions(+)

(limited to 'include')

diff --git a/include/trace/events/ksm.h b/include/trace/events/ksm.h
index b5ac35c1d0e8..e728647b5d26 100644
--- a/include/trace/events/ksm.h
+++ b/include/trace/events/ksm.h
@@ -245,6 +245,39 @@ TRACE_EVENT(ksm_remove_rmap_item,
 			__entry->pfn, __entry->rmap_item, __entry->mm)
 );
 
+/**
+ * ksm_advisor - called after the advisor has run
+ *
+ * @scan_time:		scan time in seconds
+ * @pages_to_scan:	new pages_to_scan value
+ * @cpu_percent:	cpu usage in percent
+ *
+ * Allows to trace the ksm advisor.
+ */
+TRACE_EVENT(ksm_advisor,
+
+	TP_PROTO(s64 scan_time, unsigned long pages_to_scan,
+		 unsigned int cpu_percent),
+
+	TP_ARGS(scan_time, pages_to_scan, cpu_percent),
+
+	TP_STRUCT__entry(
+		__field(s64,		scan_time)
+		__field(unsigned long,	pages_to_scan)
+		__field(unsigned int,	cpu_percent)
+	),
+
+	TP_fast_assign(
+		__entry->scan_time	= scan_time;
+		__entry->pages_to_scan	= pages_to_scan;
+		__entry->cpu_percent	= cpu_percent;
+	),
+
+	TP_printk("ksm scan time %lld pages_to_scan %lu cpu percent %u",
+			__entry->scan_time, __entry->pages_to_scan,
+			__entry->cpu_percent)
+);
+
 #endif /* _TRACE_KSM_H */
 
 /* This part must be outside protection */
diff --git a/mm/ksm.c b/mm/ksm.c
index ce3001745562..8fa6053a225d 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -458,6 +458,7 @@ static void scan_time_advisor(void)
 	advisor_ctx.cpu_time = cpu_time;
 
 	ksm_thread_pages_to_scan = pages;
+	trace_ksm_advisor(scan_time, pages, cpu_percent);
 }
 
 static void advisor_stop_scan(void)
-- 
cgit v1.2.3


From 8ba2f844f050a82624ba3ad5146aa3c116f506f7 Mon Sep 17 00:00:00 2001
From: Chengming Zhou <zhouchengming@bytedance.com>
Date: Thu, 28 Dec 2023 09:45:46 +0000
Subject: mm/zswap: change per-cpu mutex and buffer to per-acomp_ctx

First of all, we need to rename acomp_ctx->dstmem field to buffer, since
we are now using for purposes other than compression.

Then we change per-cpu mutex and buffer to per-acomp_ctx, since them
belong to the acomp_ctx and are necessary parts when used in the
compress/decompress contexts.

So we can remove the old per-cpu mutex and dstmem.

Link: https://lkml.kernel.org/r/20231213-zswap-dstmem-v5-5-9382162bbf05@bytedance.com
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Acked-by: Chris Li <chrisl@kernel.org> (Google)
Reviewed-by: Nhat Pham <nphamcs@gmail.com>
Cc: Barry Song <21cnbao@gmail.com>
Cc: Dan Streetman <ddstreet@ieee.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Seth Jennings <sjenning@redhat.com>
Cc: Vitaly Wool <vitaly.wool@konsulko.com>
Cc: Yosry Ahmed <yosryahmed@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/cpuhotplug.h |   1 -
 mm/zswap.c                 | 104 ++++++++++++++-------------------------------
 2 files changed, 33 insertions(+), 72 deletions(-)

(limited to 'include')

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index efc0c0b07efb..c3e06e21766a 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -124,7 +124,6 @@ enum cpuhp_state {
 	CPUHP_ARM_BL_PREPARE,
 	CPUHP_TRACE_RB_PREPARE,
 	CPUHP_MM_ZS_PREPARE,
-	CPUHP_MM_ZSWP_MEM_PREPARE,
 	CPUHP_MM_ZSWP_POOL_PREPARE,
 	CPUHP_KVM_PPC_BOOK3S_PREPARE,
 	CPUHP_ZCOMP_PREPARE,
diff --git a/mm/zswap.c b/mm/zswap.c
index 880c33bbe146..12ce5a68da91 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -161,8 +161,8 @@ struct crypto_acomp_ctx {
 	struct crypto_acomp *acomp;
 	struct acomp_req *req;
 	struct crypto_wait wait;
-	u8 *dstmem;
-	struct mutex *mutex;
+	u8 *buffer;
+	struct mutex mutex;
 };
 
 /*
@@ -688,63 +688,26 @@ static void zswap_alloc_shrinker(struct zswap_pool *pool)
 /*********************************
 * per-cpu code
 **********************************/
-static DEFINE_PER_CPU(u8 *, zswap_dstmem);
-/*
- * If users dynamically change the zpool type and compressor at runtime, i.e.
- * zswap is running, zswap can have more than one zpool on one cpu, but they
- * are sharing dtsmem. So we need this mutex to be per-cpu.
- */
-static DEFINE_PER_CPU(struct mutex *, zswap_mutex);
-
-static int zswap_dstmem_prepare(unsigned int cpu)
-{
-	struct mutex *mutex;
-	u8 *dst;
-
-	dst = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu));
-	if (!dst)
-		return -ENOMEM;
-
-	mutex = kmalloc_node(sizeof(*mutex), GFP_KERNEL, cpu_to_node(cpu));
-	if (!mutex) {
-		kfree(dst);
-		return -ENOMEM;
-	}
-
-	mutex_init(mutex);
-	per_cpu(zswap_dstmem, cpu) = dst;
-	per_cpu(zswap_mutex, cpu) = mutex;
-	return 0;
-}
-
-static int zswap_dstmem_dead(unsigned int cpu)
-{
-	struct mutex *mutex;
-	u8 *dst;
-
-	mutex = per_cpu(zswap_mutex, cpu);
-	kfree(mutex);
-	per_cpu(zswap_mutex, cpu) = NULL;
-
-	dst = per_cpu(zswap_dstmem, cpu);
-	kfree(dst);
-	per_cpu(zswap_dstmem, cpu) = NULL;
-
-	return 0;
-}
-
 static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node)
 {
 	struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node);
 	struct crypto_acomp_ctx *acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu);
 	struct crypto_acomp *acomp;
 	struct acomp_req *req;
+	int ret;
+
+	mutex_init(&acomp_ctx->mutex);
+
+	acomp_ctx->buffer = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu));
+	if (!acomp_ctx->buffer)
+		return -ENOMEM;
 
 	acomp = crypto_alloc_acomp_node(pool->tfm_name, 0, 0, cpu_to_node(cpu));
 	if (IS_ERR(acomp)) {
 		pr_err("could not alloc crypto acomp %s : %ld\n",
 				pool->tfm_name, PTR_ERR(acomp));
-		return PTR_ERR(acomp);
+		ret = PTR_ERR(acomp);
+		goto acomp_fail;
 	}
 	acomp_ctx->acomp = acomp;
 
@@ -752,8 +715,8 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node)
 	if (!req) {
 		pr_err("could not alloc crypto acomp_request %s\n",
 		       pool->tfm_name);
-		crypto_free_acomp(acomp_ctx->acomp);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto req_fail;
 	}
 	acomp_ctx->req = req;
 
@@ -766,10 +729,13 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node)
 	acomp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
 				   crypto_req_done, &acomp_ctx->wait);
 
-	acomp_ctx->mutex = per_cpu(zswap_mutex, cpu);
-	acomp_ctx->dstmem = per_cpu(zswap_dstmem, cpu);
-
 	return 0;
+
+req_fail:
+	crypto_free_acomp(acomp_ctx->acomp);
+acomp_fail:
+	kfree(acomp_ctx->buffer);
+	return ret;
 }
 
 static int zswap_cpu_comp_dead(unsigned int cpu, struct hlist_node *node)
@@ -782,6 +748,7 @@ static int zswap_cpu_comp_dead(unsigned int cpu, struct hlist_node *node)
 			acomp_request_free(acomp_ctx->req);
 		if (!IS_ERR_OR_NULL(acomp_ctx->acomp))
 			crypto_free_acomp(acomp_ctx->acomp);
+		kfree(acomp_ctx->buffer);
 	}
 
 	return 0;
@@ -1391,12 +1358,12 @@ static void __zswap_load(struct zswap_entry *entry, struct page *page)
 	u8 *src;
 
 	acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
-	mutex_lock(acomp_ctx->mutex);
+	mutex_lock(&acomp_ctx->mutex);
 
 	src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO);
 	if (!zpool_can_sleep_mapped(zpool)) {
-		memcpy(acomp_ctx->dstmem, src, entry->length);
-		src = acomp_ctx->dstmem;
+		memcpy(acomp_ctx->buffer, src, entry->length);
+		src = acomp_ctx->buffer;
 		zpool_unmap_handle(zpool, entry->handle);
 	}
 
@@ -1406,7 +1373,7 @@ static void __zswap_load(struct zswap_entry *entry, struct page *page)
 	acomp_request_set_params(acomp_ctx->req, &input, &output, entry->length, PAGE_SIZE);
 	BUG_ON(crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req), &acomp_ctx->wait));
 	BUG_ON(acomp_ctx->req->dlen != PAGE_SIZE);
-	mutex_unlock(acomp_ctx->mutex);
+	mutex_unlock(&acomp_ctx->mutex);
 
 	if (zpool_can_sleep_mapped(zpool))
 		zpool_unmap_handle(zpool, entry->handle);
@@ -1622,13 +1589,17 @@ bool zswap_store(struct folio *folio)
 	/* compress */
 	acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
 
-	mutex_lock(acomp_ctx->mutex);
+	mutex_lock(&acomp_ctx->mutex);
 
-	dst = acomp_ctx->dstmem;
+	dst = acomp_ctx->buffer;
 	sg_init_table(&input, 1);
 	sg_set_page(&input, page, PAGE_SIZE, 0);
 
-	/* zswap_dstmem is of size (PAGE_SIZE * 2). Reflect same in sg_list */
+	/*
+	 * We need PAGE_SIZE * 2 here since there maybe over-compression case,
+	 * and hardware-accelerators may won't check the dst buffer size, so
+	 * giving the dst buffer with enough length to avoid buffer overflow.
+	 */
 	sg_init_one(&output, dst, PAGE_SIZE * 2);
 	acomp_request_set_params(acomp_ctx->req, &input, &output, PAGE_SIZE, dlen);
 	/*
@@ -1668,7 +1639,7 @@ bool zswap_store(struct folio *folio)
 	buf = zpool_map_handle(zpool, handle, ZPOOL_MM_WO);
 	memcpy(buf, dst, dlen);
 	zpool_unmap_handle(zpool, handle);
-	mutex_unlock(acomp_ctx->mutex);
+	mutex_unlock(&acomp_ctx->mutex);
 
 	/* populate entry */
 	entry->swpentry = swp_entry(type, offset);
@@ -1711,7 +1682,7 @@ insert_entry:
 	return true;
 
 put_dstmem:
-	mutex_unlock(acomp_ctx->mutex);
+	mutex_unlock(&acomp_ctx->mutex);
 put_pool:
 	zswap_pool_put(entry->pool);
 freepage:
@@ -1886,13 +1857,6 @@ static int zswap_setup(void)
 		goto cache_fail;
 	}
 
-	ret = cpuhp_setup_state(CPUHP_MM_ZSWP_MEM_PREPARE, "mm/zswap:prepare",
-				zswap_dstmem_prepare, zswap_dstmem_dead);
-	if (ret) {
-		pr_err("dstmem alloc failed\n");
-		goto dstmem_fail;
-	}
-
 	ret = cpuhp_setup_state_multi(CPUHP_MM_ZSWP_POOL_PREPARE,
 				      "mm/zswap_pool:prepare",
 				      zswap_cpu_comp_prepare,
@@ -1924,8 +1888,6 @@ fallback_fail:
 	if (pool)
 		zswap_pool_destroy(pool);
 hp_fail:
-	cpuhp_remove_state(CPUHP_MM_ZSWP_MEM_PREPARE);
-dstmem_fail:
 	kmem_cache_destroy(zswap_entry_cache);
 cache_fail:
 	/* if built-in, we aren't unloaded on failure; don't allow use */
-- 
cgit v1.2.3


From 96c7b0b42239e7b8987b2664b458dc74e825f760 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Wed, 13 Dec 2023 21:58:30 +0000
Subject: mm: return the folio from __read_swap_cache_async()

Patch series "More swap folio conversions".

These all seem like fairly straightforward conversions to me.  A lot of
compound_head() calls get removed.  And page_swap_info(), which is nice.


This patch (of 13):

Move the folio->page conversion into the callers that actually want that.
Most of the callers are happier with the folio anyway.  If the
page_allocated boolean is set, the folio allocated is of order-0, so it is
safe to pass the page directly to swap_readpage().

Link: https://lkml.kernel.org/r/20231213215842.671461-1-willy@infradead.org
Link: https://lkml.kernel.org/r/20231213215842.671461-2-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/zswap.h |  4 +--
 mm/swap.h             |  7 +++--
 mm/swap_state.c       | 75 ++++++++++++++++++++++++---------------------------
 mm/zswap.c            | 58 +++++++++++++++++++--------------------
 4 files changed, 69 insertions(+), 75 deletions(-)

(limited to 'include')

diff --git a/include/linux/zswap.h b/include/linux/zswap.h
index 08c240e16a01..e88572d4c720 100644
--- a/include/linux/zswap.h
+++ b/include/linux/zswap.h
@@ -34,7 +34,7 @@ void zswap_swapon(int type);
 void zswap_swapoff(int type);
 void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg);
 void zswap_lruvec_state_init(struct lruvec *lruvec);
-void zswap_page_swapin(struct page *page);
+void zswap_folio_swapin(struct folio *folio);
 #else
 
 struct zswap_lruvec_state {};
@@ -54,7 +54,7 @@ static inline void zswap_swapon(int type) {}
 static inline void zswap_swapoff(int type) {}
 static inline void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg) {}
 static inline void zswap_lruvec_state_init(struct lruvec *lruvec) {}
-static inline void zswap_page_swapin(struct page *page) {}
+static inline void zswap_folio_swapin(struct folio *folio) {}
 #endif
 
 #endif /* _LINUX_ZSWAP_H */
diff --git a/mm/swap.h b/mm/swap.h
index c0dc73e10e91..a60ab1cfcaf2 100644
--- a/mm/swap.h
+++ b/mm/swap.h
@@ -49,10 +49,9 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 				   struct vm_area_struct *vma,
 				   unsigned long addr,
 				   struct swap_iocb **plug);
-struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
-				     struct mempolicy *mpol, pgoff_t ilx,
-				     bool *new_page_allocated,
-				     bool skip_if_exists);
+struct folio *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_flags,
+		struct mempolicy *mpol, pgoff_t ilx, bool *new_page_allocated,
+		bool skip_if_exists);
 struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t flag,
 				    struct mempolicy *mpol, pgoff_t ilx);
 struct page *swapin_readahead(swp_entry_t entry, gfp_t flag,
diff --git a/mm/swap_state.c b/mm/swap_state.c
index c597cec606e4..874b40a1f502 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -410,14 +410,12 @@ struct folio *filemap_get_incore_folio(struct address_space *mapping,
 	return folio;
 }
 
-struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
-				     struct mempolicy *mpol, pgoff_t ilx,
-				     bool *new_page_allocated,
-				     bool skip_if_exists)
+struct folio *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
+		struct mempolicy *mpol, pgoff_t ilx, bool *new_page_allocated,
+		bool skip_if_exists)
 {
 	struct swap_info_struct *si;
 	struct folio *folio;
-	struct page *page;
 	void *shadow = NULL;
 
 	*new_page_allocated = false;
@@ -434,10 +432,8 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		 */
 		folio = filemap_get_folio(swap_address_space(entry),
 						swp_offset(entry));
-		if (!IS_ERR(folio)) {
-			page = folio_file_page(folio, swp_offset(entry));
-			goto got_page;
-		}
+		if (!IS_ERR(folio))
+			goto got_folio;
 
 		/*
 		 * Just skip read ahead for unused swap slot.
@@ -451,7 +447,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 			goto fail_put_swap;
 
 		/*
-		 * Get a new page to read into from swap.  Allocate it now,
+		 * Get a new folio to read into from swap.  Allocate it now,
 		 * before marking swap_map SWAP_HAS_CACHE, when -EEXIST will
 		 * cause any racers to loop around until we add it to cache.
 		 */
@@ -487,13 +483,13 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		 * stumble across a swap_map entry whose SWAP_HAS_CACHE
 		 * has not yet been cleared.  Or race against another
 		 * __read_swap_cache_async(), which has set SWAP_HAS_CACHE
-		 * in swap_map, but not yet added its page to swap cache.
+		 * in swap_map, but not yet added its folio to swap cache.
 		 */
 		schedule_timeout_uninterruptible(1);
 	}
 
 	/*
-	 * The swap entry is ours to swap in. Prepare the new page.
+	 * The swap entry is ours to swap in. Prepare the new folio.
 	 */
 
 	__folio_set_locked(folio);
@@ -514,10 +510,9 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 	/* Caller will initiate read into locked folio */
 	folio_add_lru(folio);
 	*new_page_allocated = true;
-	page = &folio->page;
-got_page:
+got_folio:
 	put_swap_device(si);
-	return page;
+	return folio;
 
 fail_unlock:
 	put_swap_folio(folio, entry);
@@ -545,16 +540,16 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 	bool page_allocated;
 	struct mempolicy *mpol;
 	pgoff_t ilx;
-	struct page *page;
+	struct folio *folio;
 
 	mpol = get_vma_policy(vma, addr, 0, &ilx);
-	page = __read_swap_cache_async(entry, gfp_mask, mpol, ilx,
+	folio = __read_swap_cache_async(entry, gfp_mask, mpol, ilx,
 					&page_allocated, false);
 	mpol_cond_put(mpol);
 
 	if (page_allocated)
-		swap_readpage(page, false, plug);
-	return page;
+		swap_readpage(&folio->page, false, plug);
+	return folio_file_page(folio, swp_offset(entry));
 }
 
 static unsigned int __swapin_nr_pages(unsigned long prev_offset,
@@ -639,7 +634,7 @@ static unsigned long swapin_nr_pages(unsigned long offset)
 struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
 				    struct mempolicy *mpol, pgoff_t ilx)
 {
-	struct page *page;
+	struct folio *folio;
 	unsigned long entry_offset = swp_offset(entry);
 	unsigned long offset = entry_offset;
 	unsigned long start_offset, end_offset;
@@ -664,31 +659,31 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
 	blk_start_plug(&plug);
 	for (offset = start_offset; offset <= end_offset ; offset++) {
 		/* Ok, do the async read-ahead now */
-		page = __read_swap_cache_async(
+		folio = __read_swap_cache_async(
 				swp_entry(swp_type(entry), offset),
 				gfp_mask, mpol, ilx, &page_allocated, false);
-		if (!page)
+		if (!folio)
 			continue;
 		if (page_allocated) {
-			swap_readpage(page, false, &splug);
+			swap_readpage(&folio->page, false, &splug);
 			if (offset != entry_offset) {
-				SetPageReadahead(page);
+				folio_set_readahead(folio);
 				count_vm_event(SWAP_RA);
 			}
 		}
-		put_page(page);
+		folio_put(folio);
 	}
 	blk_finish_plug(&plug);
 	swap_read_unplug(splug);
 	lru_add_drain();	/* Push any new pages onto the LRU now */
 skip:
 	/* The page was likely read above, so no need for plugging here */
-	page = __read_swap_cache_async(entry, gfp_mask, mpol, ilx,
+	folio = __read_swap_cache_async(entry, gfp_mask, mpol, ilx,
 					&page_allocated, false);
 	if (unlikely(page_allocated))
-		swap_readpage(page, false, NULL);
-	zswap_page_swapin(page);
-	return page;
+		swap_readpage(&folio->page, false, NULL);
+	zswap_folio_swapin(folio);
+	return folio_file_page(folio, swp_offset(entry));
 }
 
 int init_swap_address_space(unsigned int type, unsigned long nr_pages)
@@ -806,7 +801,7 @@ static struct page *swap_vma_readahead(swp_entry_t targ_entry, gfp_t gfp_mask,
 {
 	struct blk_plug plug;
 	struct swap_iocb *splug = NULL;
-	struct page *page;
+	struct folio *folio;
 	pte_t *pte = NULL, pentry;
 	unsigned long addr;
 	swp_entry_t entry;
@@ -839,18 +834,18 @@ static struct page *swap_vma_readahead(swp_entry_t targ_entry, gfp_t gfp_mask,
 			continue;
 		pte_unmap(pte);
 		pte = NULL;
-		page = __read_swap_cache_async(entry, gfp_mask, mpol, ilx,
+		folio = __read_swap_cache_async(entry, gfp_mask, mpol, ilx,
 						&page_allocated, false);
-		if (!page)
+		if (!folio)
 			continue;
 		if (page_allocated) {
-			swap_readpage(page, false, &splug);
+			swap_readpage(&folio->page, false, &splug);
 			if (i != ra_info.offset) {
-				SetPageReadahead(page);
+				folio_set_readahead(folio);
 				count_vm_event(SWAP_RA);
 			}
 		}
-		put_page(page);
+		folio_put(folio);
 	}
 	if (pte)
 		pte_unmap(pte);
@@ -858,13 +853,13 @@ static struct page *swap_vma_readahead(swp_entry_t targ_entry, gfp_t gfp_mask,
 	swap_read_unplug(splug);
 	lru_add_drain();
 skip:
-	/* The page was likely read above, so no need for plugging here */
-	page = __read_swap_cache_async(targ_entry, gfp_mask, mpol, targ_ilx,
+	/* The folio was likely read above, so no need for plugging here */
+	folio = __read_swap_cache_async(targ_entry, gfp_mask, mpol, targ_ilx,
 					&page_allocated, false);
 	if (unlikely(page_allocated))
-		swap_readpage(page, false, NULL);
-	zswap_page_swapin(page);
-	return page;
+		swap_readpage(&folio->page, false, NULL);
+	zswap_folio_swapin(folio);
+	return folio_file_page(folio, swp_offset(entry));
 }
 
 /**
diff --git a/mm/zswap.c b/mm/zswap.c
index 12ce5a68da91..6d9ee2a5334a 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -368,12 +368,12 @@ void zswap_lruvec_state_init(struct lruvec *lruvec)
 	atomic_long_set(&lruvec->zswap_lruvec_state.nr_zswap_protected, 0);
 }
 
-void zswap_page_swapin(struct page *page)
+void zswap_folio_swapin(struct folio *folio)
 {
 	struct lruvec *lruvec;
 
-	if (page) {
-		lruvec = folio_lruvec(page_folio(page));
+	if (folio) {
+		lruvec = folio_lruvec(folio);
 		atomic_long_inc(&lruvec->zswap_lruvec_state.nr_zswap_protected);
 	}
 }
@@ -1383,14 +1383,14 @@ static void __zswap_load(struct zswap_entry *entry, struct page *page)
 * writeback code
 **********************************/
 /*
- * Attempts to free an entry by adding a page to the swap cache,
- * decompressing the entry data into the page, and issuing a
- * bio write to write the page back to the swap device.
+ * Attempts to free an entry by adding a folio to the swap cache,
+ * decompressing the entry data into the folio, and issuing a
+ * bio write to write the folio back to the swap device.
  *
- * This can be thought of as a "resumed writeback" of the page
+ * This can be thought of as a "resumed writeback" of the folio
  * to the swap device.  We are basically resuming the same swap
  * writeback path that was intercepted with the zswap_store()
- * in the first place.  After the page has been decompressed into
+ * in the first place.  After the folio has been decompressed into
  * the swap cache, the compressed version stored by zswap can be
  * freed.
  */
@@ -1398,56 +1398,56 @@ static int zswap_writeback_entry(struct zswap_entry *entry,
 				 struct zswap_tree *tree)
 {
 	swp_entry_t swpentry = entry->swpentry;
-	struct page *page;
+	struct folio *folio;
 	struct mempolicy *mpol;
-	bool page_was_allocated;
+	bool folio_was_allocated;
 	struct writeback_control wbc = {
 		.sync_mode = WB_SYNC_NONE,
 	};
 
-	/* try to allocate swap cache page */
+	/* try to allocate swap cache folio */
 	mpol = get_task_policy(current);
-	page = __read_swap_cache_async(swpentry, GFP_KERNEL, mpol,
-				NO_INTERLEAVE_INDEX, &page_was_allocated, true);
-	if (!page)
+	folio = __read_swap_cache_async(swpentry, GFP_KERNEL, mpol,
+				NO_INTERLEAVE_INDEX, &folio_was_allocated, true);
+	if (!folio)
 		return -ENOMEM;
 
 	/*
-	 * Found an existing page, we raced with load/swapin. We generally
-	 * writeback cold pages from zswap, and swapin means the page just
-	 * became hot. Skip this page and let the caller find another one.
+	 * Found an existing folio, we raced with load/swapin. We generally
+	 * writeback cold folios from zswap, and swapin means the folio just
+	 * became hot. Skip this folio and let the caller find another one.
 	 */
-	if (!page_was_allocated) {
-		put_page(page);
+	if (!folio_was_allocated) {
+		folio_put(folio);
 		return -EEXIST;
 	}
 
 	/*
-	 * Page is locked, and the swapcache is now secured against
+	 * folio is locked, and the swapcache is now secured against
 	 * concurrent swapping to and from the slot. Verify that the
 	 * swap entry hasn't been invalidated and recycled behind our
 	 * backs (our zswap_entry reference doesn't prevent that), to
-	 * avoid overwriting a new swap page with old compressed data.
+	 * avoid overwriting a new swap folio with old compressed data.
 	 */
 	spin_lock(&tree->lock);
 	if (zswap_rb_search(&tree->rbroot, swp_offset(entry->swpentry)) != entry) {
 		spin_unlock(&tree->lock);
-		delete_from_swap_cache(page_folio(page));
+		delete_from_swap_cache(folio);
 		return -ENOMEM;
 	}
 	spin_unlock(&tree->lock);
 
-	__zswap_load(entry, page);
+	__zswap_load(entry, &folio->page);
 
-	/* page is up to date */
-	SetPageUptodate(page);
+	/* folio is up to date */
+	folio_mark_uptodate(folio);
 
 	/* move it to the tail of the inactive list after end_writeback */
-	SetPageReclaim(page);
+	folio_set_reclaim(folio);
 
 	/* start writeback */
-	__swap_writepage(page, &wbc);
-	put_page(page);
+	__swap_writepage(&folio->page, &wbc);
+	folio_put(folio);
 
 	return 0;
 }
@@ -1593,7 +1593,7 @@ bool zswap_store(struct folio *folio)
 
 	dst = acomp_ctx->buffer;
 	sg_init_table(&input, 1);
-	sg_set_page(&input, page, PAGE_SIZE, 0);
+	sg_set_page(&input, &folio->page, PAGE_SIZE, 0);
 
 	/*
 	 * We need PAGE_SIZE * 2 here since there maybe over-compression case,
-- 
cgit v1.2.3


From 3a61e6f668120ee2c7840b91891c858d575d07e2 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Wed, 13 Dec 2023 21:58:38 +0000
Subject: mm: convert swap_page_sector() to swap_folio_sector()

All callers have a folio, so pass it in.  Saves a couple of calls to
compound_head().

Link: https://lkml.kernel.org/r/20231213215842.671461-10-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/swap.h | 2 +-
 mm/page_io.c         | 8 ++++----
 mm/swapfile.c        | 6 +++---
 3 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 3e1909087f6a..2d09e9b7ee70 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -493,7 +493,7 @@ struct backing_dev_info;
 extern int init_swap_address_space(unsigned int type, unsigned long nr_pages);
 extern void exit_swap_address_space(unsigned int type);
 extern struct swap_info_struct *get_swap_device(swp_entry_t entry);
-sector_t swap_page_sector(struct page *page);
+sector_t swap_folio_sector(struct folio *folio);
 
 static inline void put_swap_device(struct swap_info_struct *si)
 {
diff --git a/mm/page_io.c b/mm/page_io.c
index e18afcd9c19a..6736c56526bf 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -334,7 +334,7 @@ static void swap_writepage_bdev_sync(struct folio *folio,
 
 	bio_init(&bio, sis->bdev, &bv, 1,
 		 REQ_OP_WRITE | REQ_SWAP | wbc_to_write_flags(wbc));
-	bio.bi_iter.bi_sector = swap_page_sector(&folio->page);
+	bio.bi_iter.bi_sector = swap_folio_sector(folio);
 	bio_add_folio_nofail(&bio, folio, folio_size(folio), 0);
 
 	bio_associate_blkg_from_page(&bio, folio);
@@ -355,7 +355,7 @@ static void swap_writepage_bdev_async(struct folio *folio,
 	bio = bio_alloc(sis->bdev, 1,
 			REQ_OP_WRITE | REQ_SWAP | wbc_to_write_flags(wbc),
 			GFP_NOIO);
-	bio->bi_iter.bi_sector = swap_page_sector(&folio->page);
+	bio->bi_iter.bi_sector = swap_folio_sector(folio);
 	bio->bi_end_io = end_swap_bio_write;
 	bio_add_folio_nofail(bio, folio, folio_size(folio), 0);
 
@@ -461,7 +461,7 @@ static void swap_readpage_bdev_sync(struct folio *folio,
 	struct bio bio;
 
 	bio_init(&bio, sis->bdev, &bv, 1, REQ_OP_READ);
-	bio.bi_iter.bi_sector = swap_page_sector(&folio->page);
+	bio.bi_iter.bi_sector = swap_folio_sector(folio);
 	bio_add_folio_nofail(&bio, folio, folio_size(folio), 0);
 	/*
 	 * Keep this task valid during swap readpage because the oom killer may
@@ -480,7 +480,7 @@ static void swap_readpage_bdev_async(struct folio *folio,
 	struct bio *bio;
 
 	bio = bio_alloc(sis->bdev, 1, REQ_OP_READ, GFP_KERNEL);
-	bio->bi_iter.bi_sector = swap_page_sector(&folio->page);
+	bio->bi_iter.bi_sector = swap_folio_sector(folio);
 	bio->bi_end_io = end_swap_bio_read;
 	bio_add_folio_nofail(bio, folio, folio_size(folio), 0);
 	count_vm_event(PSWPIN);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 1501bc956456..b22c47b11d65 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -227,14 +227,14 @@ offset_to_swap_extent(struct swap_info_struct *sis, unsigned long offset)
 	BUG();
 }
 
-sector_t swap_page_sector(struct page *page)
+sector_t swap_folio_sector(struct folio *folio)
 {
-	struct swap_info_struct *sis = page_swap_info(page);
+	struct swap_info_struct *sis = swp_swap_info(folio->swap);
 	struct swap_extent *se;
 	sector_t sector;
 	pgoff_t offset;
 
-	offset = __page_file_index(page);
+	offset = swp_offset(folio->swap);
 	se = offset_to_swap_extent(sis, offset);
 	sector = se->start_block + (offset - se->start_page);
 	return sector << (PAGE_SHIFT - 9);
-- 
cgit v1.2.3


From 69fe7d67cb0c6eeab3d4c9a3bf950f9d12af4719 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Wed, 13 Dec 2023 21:58:40 +0000
Subject: mm: remove page_swap_info()

It's more efficient to get the swap_info_struct by calling
swp_swap_info() directly.

Link: https://lkml.kernel.org/r/20231213215842.671461-12-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/swap.h | 3 +--
 mm/swap.h            | 2 +-
 mm/swapfile.c        | 8 +-------
 3 files changed, 3 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 2d09e9b7ee70..4db00ddad261 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -487,8 +487,7 @@ extern sector_t swapdev_block(int, pgoff_t);
 extern int __swap_count(swp_entry_t entry);
 extern int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry);
 extern int swp_swapcount(swp_entry_t entry);
-extern struct swap_info_struct *page_swap_info(struct page *);
-extern struct swap_info_struct *swp_swap_info(swp_entry_t entry);
+struct swap_info_struct *swp_swap_info(swp_entry_t entry);
 struct backing_dev_info;
 extern int init_swap_address_space(unsigned int type, unsigned long nr_pages);
 extern void exit_swap_address_space(unsigned int type);
diff --git a/mm/swap.h b/mm/swap.h
index 859ae8f0fd2d..6bf25342589f 100644
--- a/mm/swap.h
+++ b/mm/swap.h
@@ -60,7 +60,7 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t flag,
 
 static inline unsigned int folio_swap_flags(struct folio *folio)
 {
-	return page_swap_info(&folio->page)->flags;
+	return swp_swap_info(folio->swap)->flags;
 }
 #else /* CONFIG_SWAP */
 struct swap_iocb;
diff --git a/mm/swapfile.c b/mm/swapfile.c
index f3e23a3d26ae..2f877ca44513 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -3369,18 +3369,12 @@ struct swap_info_struct *swp_swap_info(swp_entry_t entry)
 	return swap_type_to_swap_info(swp_type(entry));
 }
 
-struct swap_info_struct *page_swap_info(struct page *page)
-{
-	swp_entry_t entry = page_swap_entry(page);
-	return swp_swap_info(entry);
-}
-
 /*
  * out-of-line methods to avoid include hell.
  */
 struct address_space *swapcache_mapping(struct folio *folio)
 {
-	return page_swap_info(&folio->page)->swap_file->f_mapping;
+	return swp_swap_info(folio->swap)->swap_file->f_mapping;
 }
 EXPORT_SYMBOL_GPL(swapcache_mapping);
 
-- 
cgit v1.2.3


From f099c961f4998ad7107b1c6a7d6efb225e9a4614 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Fri, 15 Dec 2023 20:02:32 +0000
Subject: fs: remove clean_page_buffers()

Patch series "Clean up the writeback paths".

Most of these patches verge on the trivial, converting filesystems that
just use block_write_full_page() to use mpage_writepages().  But as we saw
with Christoph's earlier patchset, there can be some "interesting"
gotchas, and I clearly haven't tested the majority of filesystems I've
touched here.

Patches 3 & 4 get rid of a lot of stack usage on architectures with larger
page sizes; 1024 bytes on 64-bit systems with 64KiB pages.  It starts to
open the door to larger folio sizes on all architectures, but it's
certainly not enough yet.

Patch 14 is kind of trivial, but it's nice to get that simplification in.


This patch (of 14):

This function has been unused since the removal of bdev_write_page().

Link: https://lkml.kernel.org/r/20231215200245.748418-1-willy@infradead.org
Link: https://lkml.kernel.org/r/20231215200245.748418-2-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/mpage.c                  | 10 ----------
 include/linux/buffer_head.h |  1 -
 2 files changed, 11 deletions(-)

(limited to 'include')

diff --git a/fs/mpage.c b/fs/mpage.c
index ffb064ed9d04..63bf99856024 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -455,16 +455,6 @@ static void clean_buffers(struct page *page, unsigned first_unmapped)
 		try_to_free_buffers(page_folio(page));
 }
 
-/*
- * For situations where we want to clean all buffers attached to a page.
- * We don't need to calculate how many buffers are attached to the page,
- * we just need to specify a number larger than the maximum number of buffers.
- */
-void clean_page_buffers(struct page *page)
-{
-	clean_buffers(page, ~0U);
-}
-
 static int __mpage_writepage(struct folio *folio, struct writeback_control *wbc,
 		      void *data)
 {
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 5f23ee599889..94f6161eb45e 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -270,7 +270,6 @@ int generic_write_end(struct file *, struct address_space *,
 				loff_t, unsigned, unsigned,
 				struct page *, void *);
 void folio_zero_new_buffers(struct folio *folio, size_t from, size_t to);
-void clean_page_buffers(struct page *page);
 int cont_write_begin(struct file *, struct address_space *, loff_t,
 			unsigned, struct page **, void **,
 			get_block_t *, loff_t *);
-- 
cgit v1.2.3


From 17bf23a981be9c6629198a76940c777eb5c8c521 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Fri, 15 Dec 2023 20:02:44 +0000
Subject: fs: convert block_write_full_page to block_write_full_folio

Convert the function to be compatible with writepage_t so that it can be
passed to write_cache_pages() by blkdev.  This removes a call to
compound_head().  We can also remove the function export as both callers
are built-in.

Link: https://lkml.kernel.org/r/20231215200245.748418-14-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 block/fops.c                | 21 ++++++++++++++++++---
 fs/buffer.c                 | 16 +++++++---------
 fs/ext4/page-io.c           |  2 +-
 fs/gfs2/aops.c              |  4 ++--
 fs/mpage.c                  |  2 +-
 fs/ntfs/aops.c              |  4 ++--
 fs/ocfs2/alloc.c            |  2 +-
 fs/ocfs2/file.c             |  2 +-
 include/linux/buffer_head.h |  4 ++--
 9 files changed, 35 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/block/fops.c b/block/fops.c
index 0bdad1e8d514..0cf8cf72cdfa 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -410,9 +410,24 @@ static int blkdev_get_block(struct inode *inode, sector_t iblock,
 	return 0;
 }
 
-static int blkdev_writepage(struct page *page, struct writeback_control *wbc)
+/*
+ * We cannot call mpage_writepages() as it does not take the buffer lock.
+ * We must use block_write_full_folio() directly which holds the buffer
+ * lock.  The buffer lock provides the synchronisation with writeback
+ * that filesystems rely on when they use the blockdev's mapping.
+ */
+static int blkdev_writepages(struct address_space *mapping,
+		struct writeback_control *wbc)
 {
-	return block_write_full_page(page, blkdev_get_block, wbc);
+	struct blk_plug plug;
+	int err;
+
+	blk_start_plug(&plug);
+	err = write_cache_pages(mapping, wbc, block_write_full_folio,
+			blkdev_get_block);
+	blk_finish_plug(&plug);
+
+	return err;
 }
 
 static int blkdev_read_folio(struct file *file, struct folio *folio)
@@ -449,7 +464,7 @@ const struct address_space_operations def_blk_aops = {
 	.invalidate_folio = block_invalidate_folio,
 	.read_folio	= blkdev_read_folio,
 	.readahead	= blkdev_readahead,
-	.writepage	= blkdev_writepage,
+	.writepages	= blkdev_writepages,
 	.write_begin	= blkdev_write_begin,
 	.write_end	= blkdev_write_end,
 	.migrate_folio	= buffer_migrate_folio_norefs,
diff --git a/fs/buffer.c b/fs/buffer.c
index 3a8c8322ed28..c838b4a31009 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -372,7 +372,7 @@ static void end_buffer_async_read_io(struct buffer_head *bh, int uptodate)
 }
 
 /*
- * Completion handler for block_write_full_page() - pages which are unlocked
+ * Completion handler for block_write_full_folio() - pages which are unlocked
  * during I/O, and which have PageWriteback cleared upon I/O completion.
  */
 void end_buffer_async_write(struct buffer_head *bh, int uptodate)
@@ -1771,18 +1771,18 @@ static struct buffer_head *folio_create_buffers(struct folio *folio,
  */
 
 /*
- * While block_write_full_page is writing back the dirty buffers under
+ * While block_write_full_folio is writing back the dirty buffers under
  * the page lock, whoever dirtied the buffers may decide to clean them
  * again at any time.  We handle that by only looking at the buffer
  * state inside lock_buffer().
  *
- * If block_write_full_page() is called for regular writeback
+ * If block_write_full_folio() is called for regular writeback
  * (wbc->sync_mode == WB_SYNC_NONE) then it will redirty a page which has a
  * locked buffer.   This only can happen if someone has written the buffer
  * directly, with submit_bh().  At the address_space level PageWriteback
  * prevents this contention from occurring.
  *
- * If block_write_full_page() is called with wbc->sync_mode ==
+ * If block_write_full_folio() is called with wbc->sync_mode ==
  * WB_SYNC_ALL, the writes are posted using REQ_SYNC; this
  * causes the writes to be flagged as synchronous writes.
  */
@@ -1829,7 +1829,7 @@ int __block_write_full_folio(struct inode *inode, struct folio *folio,
 			 * truncate in progress.
 			 */
 			/*
-			 * The buffer was zeroed by block_write_full_page()
+			 * The buffer was zeroed by block_write_full_folio()
 			 */
 			clear_buffer_dirty(bh);
 			set_buffer_uptodate(bh);
@@ -2696,10 +2696,9 @@ EXPORT_SYMBOL(block_truncate_page);
 /*
  * The generic ->writepage function for buffer-backed address_spaces
  */
-int block_write_full_page(struct page *page, get_block_t *get_block,
-			struct writeback_control *wbc)
+int block_write_full_folio(struct folio *folio, struct writeback_control *wbc,
+		void *get_block)
 {
-	struct folio *folio = page_folio(page);
 	struct inode * const inode = folio->mapping->host;
 	loff_t i_size = i_size_read(inode);
 
@@ -2726,7 +2725,6 @@ int block_write_full_page(struct page *page, get_block_t *get_block,
 	return __block_write_full_folio(inode, folio, get_block, wbc,
 			end_buffer_async_write);
 }
-EXPORT_SYMBOL(block_write_full_page);
 
 sector_t generic_block_bmap(struct address_space *mapping, sector_t block,
 			    get_block_t *get_block)
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index dfdd7e5cf038..312bc6813357 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -444,7 +444,7 @@ int ext4_bio_write_folio(struct ext4_io_submit *io, struct folio *folio,
 	folio_clear_error(folio);
 
 	/*
-	 * Comments copied from block_write_full_page:
+	 * Comments copied from block_write_full_folio:
 	 *
 	 * The folio straddles i_size.  It must be zeroed out on each and every
 	 * writepage invocation because it may be mmapped.  "A file is mapped
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 5cffb079b87c..f986cd032b76 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -82,11 +82,11 @@ static int gfs2_get_block_noalloc(struct inode *inode, sector_t lblock,
 }
 
 /**
- * gfs2_write_jdata_folio - gfs2 jdata-specific version of block_write_full_page
+ * gfs2_write_jdata_folio - gfs2 jdata-specific version of block_write_full_folio
  * @folio: The folio to write
  * @wbc: The writeback control
  *
- * This is the same as calling block_write_full_page, but it also
+ * This is the same as calling block_write_full_folio, but it also
  * writes pages outside of i_size
  */
 static int gfs2_write_jdata_folio(struct folio *folio,
diff --git a/fs/mpage.c b/fs/mpage.c
index d4963f3d8051..738882e0766d 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -642,7 +642,7 @@ confused:
 	/*
 	 * The caller has a ref on the inode, so *mapping is stable
 	 */
-	ret = block_write_full_page(&folio->page, mpd->get_block, wbc);
+	ret = block_write_full_folio(folio, wbc, mpd->get_block);
 	mapping_set_error(mapping, ret);
 out:
 	mpd->bio = bio;
diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c
index 70479ce915e8..6c414957e2c2 100644
--- a/fs/ntfs/aops.c
+++ b/fs/ntfs/aops.c
@@ -1304,7 +1304,7 @@ done:
  * page cleaned.  The VM has already locked the page and marked it clean.
  *
  * For non-resident attributes, ntfs_writepage() writes the @page by calling
- * the ntfs version of the generic block_write_full_page() function,
+ * the ntfs version of the generic block_write_full_folio() function,
  * ntfs_write_block(), which in turn if necessary creates and writes the
  * buffers associated with the page asynchronously.
  *
@@ -1314,7 +1314,7 @@ done:
  * vfs inode dirty code path for the inode the mft record belongs to or via the
  * vm page dirty code path for the page the mft record is in.
  *
- * Based on ntfs_read_folio() and fs/buffer.c::block_write_full_page().
+ * Based on ntfs_read_folio() and fs/buffer.c::block_write_full_folio().
  *
  * Return 0 on success and -errno on error.
  */
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index 91b32b2377ac..ea9127ba3208 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -6934,7 +6934,7 @@ static int ocfs2_grab_eof_pages(struct inode *inode, loff_t start, loff_t end,
  * nonzero data on subsequent file extends.
  *
  * We need to call this before i_size is updated on the inode because
- * otherwise block_write_full_page() will skip writeout of pages past
+ * otherwise block_write_full_folio() will skip writeout of pages past
  * i_size.
  */
 int ocfs2_zero_range_for_truncate(struct inode *inode, handle_t *handle,
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 94e2a1244442..8b6d15010703 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -818,7 +818,7 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
 	/*
 	 * fs-writeback will release the dirty pages without page lock
 	 * whose offset are over inode size, the release happens at
-	 * block_write_full_page().
+	 * block_write_full_folio().
 	 */
 	i_size_write(inode, abs_to);
 	inode->i_blocks = ocfs2_inode_sector_count(inode);
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 94f6161eb45e..396b2adf24bf 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -252,8 +252,8 @@ void __bh_read_batch(int nr, struct buffer_head *bhs[],
  * address_spaces.
  */
 void block_invalidate_folio(struct folio *folio, size_t offset, size_t length);
-int block_write_full_page(struct page *page, get_block_t *get_block,
-				struct writeback_control *wbc);
+int block_write_full_folio(struct folio *folio, struct writeback_control *wbc,
+		void *get_block);
 int __block_write_full_folio(struct inode *inode, struct folio *folio,
 			get_block_t *get_block, struct writeback_control *wbc,
 			bh_end_io_t *handler);
-- 
cgit v1.2.3


From 14059f66a959c760467ea2041e165f412845bcb8 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Fri, 15 Dec 2023 20:02:45 +0000
Subject: fs: remove the bh_end_io argument from __block_write_full_folio

All callers are passing end_buffer_async_write as this argument, so we can
hardcode references to it within __block_write_full_folio().  That lets us
make end_buffer_async_write() static.

Link: https://lkml.kernel.org/r/20231215200245.748418-15-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/buffer.c                 | 22 ++++++++++------------
 fs/gfs2/aops.c              |  2 +-
 include/linux/buffer_head.h |  4 +---
 3 files changed, 12 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/fs/buffer.c b/fs/buffer.c
index c838b4a31009..19548369bc6c 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -372,10 +372,10 @@ static void end_buffer_async_read_io(struct buffer_head *bh, int uptodate)
 }
 
 /*
- * Completion handler for block_write_full_folio() - pages which are unlocked
- * during I/O, and which have PageWriteback cleared upon I/O completion.
+ * Completion handler for block_write_full_folio() - folios which are unlocked
+ * during I/O, and which have the writeback flag cleared upon I/O completion.
  */
-void end_buffer_async_write(struct buffer_head *bh, int uptodate)
+static void end_buffer_async_write(struct buffer_head *bh, int uptodate)
 {
 	unsigned long flags;
 	struct buffer_head *first;
@@ -415,7 +415,6 @@ still_busy:
 	spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
 	return;
 }
-EXPORT_SYMBOL(end_buffer_async_write);
 
 /*
  * If a page's buffers are under async readin (end_buffer_async_read
@@ -1787,8 +1786,7 @@ static struct buffer_head *folio_create_buffers(struct folio *folio,
  * causes the writes to be flagged as synchronous writes.
  */
 int __block_write_full_folio(struct inode *inode, struct folio *folio,
-			get_block_t *get_block, struct writeback_control *wbc,
-			bh_end_io_t *handler)
+			get_block_t *get_block, struct writeback_control *wbc)
 {
 	int err;
 	sector_t block;
@@ -1867,7 +1865,8 @@ int __block_write_full_folio(struct inode *inode, struct folio *folio,
 			continue;
 		}
 		if (test_clear_buffer_dirty(bh)) {
-			mark_buffer_async_write_endio(bh, handler);
+			mark_buffer_async_write_endio(bh,
+				end_buffer_async_write);
 		} else {
 			unlock_buffer(bh);
 		}
@@ -1920,7 +1919,8 @@ recover:
 		if (buffer_mapped(bh) && buffer_dirty(bh) &&
 		    !buffer_delay(bh)) {
 			lock_buffer(bh);
-			mark_buffer_async_write_endio(bh, handler);
+			mark_buffer_async_write_endio(bh,
+				end_buffer_async_write);
 		} else {
 			/*
 			 * The buffer may have been set dirty during
@@ -2704,8 +2704,7 @@ int block_write_full_folio(struct folio *folio, struct writeback_control *wbc,
 
 	/* Is the folio fully inside i_size? */
 	if (folio_pos(folio) + folio_size(folio) <= i_size)
-		return __block_write_full_folio(inode, folio, get_block, wbc,
-					       end_buffer_async_write);
+		return __block_write_full_folio(inode, folio, get_block, wbc);
 
 	/* Is the folio fully outside i_size? (truncate in progress) */
 	if (folio_pos(folio) >= i_size) {
@@ -2722,8 +2721,7 @@ int block_write_full_folio(struct folio *folio, struct writeback_control *wbc,
 	 */
 	folio_zero_segment(folio, offset_in_folio(folio, i_size),
 			folio_size(folio));
-	return __block_write_full_folio(inode, folio, get_block, wbc,
-			end_buffer_async_write);
+	return __block_write_full_folio(inode, folio, get_block, wbc);
 }
 
 sector_t generic_block_bmap(struct address_space *mapping, sector_t block,
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index f986cd032b76..9914d7f54f7d 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -108,7 +108,7 @@ static int gfs2_write_jdata_folio(struct folio *folio,
 				folio_size(folio));
 
 	return __block_write_full_folio(inode, folio, gfs2_get_block_noalloc,
-			wbc, end_buffer_async_write);
+			wbc);
 }
 
 /**
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 396b2adf24bf..d78454a4dd1f 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -205,7 +205,6 @@ struct buffer_head *create_empty_buffers(struct folio *folio,
 		unsigned long blocksize, unsigned long b_state);
 void end_buffer_read_sync(struct buffer_head *bh, int uptodate);
 void end_buffer_write_sync(struct buffer_head *bh, int uptodate);
-void end_buffer_async_write(struct buffer_head *bh, int uptodate);
 
 /* Things to do with buffers at mapping->private_list */
 void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode);
@@ -255,8 +254,7 @@ void block_invalidate_folio(struct folio *folio, size_t offset, size_t length);
 int block_write_full_folio(struct folio *folio, struct writeback_control *wbc,
 		void *get_block);
 int __block_write_full_folio(struct inode *inode, struct folio *folio,
-			get_block_t *get_block, struct writeback_control *wbc,
-			bh_end_io_t *handler);
+		get_block_t *get_block, struct writeback_control *wbc);
 int block_read_full_folio(struct folio *, get_block_t *);
 bool block_is_partially_uptodate(struct folio *, size_t from, size_t count);
 int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
-- 
cgit v1.2.3


From 280ec6ccb6422aa4a04f9ac4216ddcf055acc95d Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Tue, 19 Dec 2023 23:28:45 +0100
Subject: kasan: rename kasan_slab_free_mempool to kasan_mempool_poison_object

Patch series "kasan: save mempool stack traces".

This series updates KASAN to save alloc and free stack traces for
secondary-level allocators that cache and reuse allocations internally
instead of giving them back to the underlying allocator (e.g.  mempool).

As a part of this change, introduce and document a set of KASAN hooks:

bool kasan_mempool_poison_pages(struct page *page, unsigned int order);
void kasan_mempool_unpoison_pages(struct page *page, unsigned int order);
bool kasan_mempool_poison_object(void *ptr);
void kasan_mempool_unpoison_object(void *ptr, size_t size);

and use them in the mempool code.

Besides mempool, skbuff and io_uring also cache allocations and already
use KASAN hooks to poison those.  Their code is updated to use the new
mempool hooks.

The new hooks save alloc and free stack traces (for normal kmalloc and
slab objects; stack traces for large kmalloc objects and page_alloc are
not supported by KASAN yet), improve the readability of the users' code,
and also allow the users to prevent double-free and invalid-free bugs; see
the patches for the details.


This patch (of 21):

Rename kasan_slab_free_mempool to kasan_mempool_poison_object.

kasan_slab_free_mempool is a slightly confusing name: it is unclear
whether this function poisons the object when it is freed into mempool or
does something when the object is freed from mempool to the underlying
allocator.

The new name also aligns with other mempool-related KASAN hooks added in
the following patches in this series.

Link: https://lkml.kernel.org/r/cover.1703024586.git.andreyknvl@google.com
Link: https://lkml.kernel.org/r/c5618685abb7cdbf9fb4897f565e7759f601da84.1703024586.git.andreyknvl@google.com
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Cc: Alexander Lobakin <alobakin@pm.me>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Breno Leitao <leitao@debian.org>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Marco Elver <elver@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/kasan.h  | 8 ++++----
 io_uring/alloc_cache.h | 3 +--
 mm/kasan/common.c      | 4 ++--
 mm/mempool.c           | 2 +-
 4 files changed, 8 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 72cb693b075b..6310435f528b 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -172,11 +172,11 @@ static __always_inline void kasan_kfree_large(void *ptr)
 		__kasan_kfree_large(ptr, _RET_IP_);
 }
 
-void __kasan_slab_free_mempool(void *ptr, unsigned long ip);
-static __always_inline void kasan_slab_free_mempool(void *ptr)
+void __kasan_mempool_poison_object(void *ptr, unsigned long ip);
+static __always_inline void kasan_mempool_poison_object(void *ptr)
 {
 	if (kasan_enabled())
-		__kasan_slab_free_mempool(ptr, _RET_IP_);
+		__kasan_mempool_poison_object(ptr, _RET_IP_);
 }
 
 void * __must_check __kasan_slab_alloc(struct kmem_cache *s,
@@ -256,7 +256,7 @@ static inline bool kasan_slab_free(struct kmem_cache *s, void *object, bool init
 	return false;
 }
 static inline void kasan_kfree_large(void *ptr) {}
-static inline void kasan_slab_free_mempool(void *ptr) {}
+static inline void kasan_mempool_poison_object(void *ptr) {}
 static inline void *kasan_slab_alloc(struct kmem_cache *s, void *object,
 				   gfp_t flags, bool init)
 {
diff --git a/io_uring/alloc_cache.h b/io_uring/alloc_cache.h
index 241245cb54a6..8de0414e8efe 100644
--- a/io_uring/alloc_cache.h
+++ b/io_uring/alloc_cache.h
@@ -16,8 +16,7 @@ static inline bool io_alloc_cache_put(struct io_alloc_cache *cache,
 	if (cache->nr_cached < cache->max_cached) {
 		cache->nr_cached++;
 		wq_stack_add_head(&entry->node, &cache->list);
-		/* KASAN poisons object */
-		kasan_slab_free_mempool(entry);
+		kasan_mempool_poison_object(entry);
 		return true;
 	}
 	return false;
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index fe6c4b43ad9f..e0394d0ee7f1 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -271,7 +271,7 @@ static inline bool ____kasan_kfree_large(void *ptr, unsigned long ip)
 
 	/*
 	 * The object will be poisoned by kasan_poison_pages() or
-	 * kasan_slab_free_mempool().
+	 * kasan_mempool_poison_object().
 	 */
 
 	return false;
@@ -282,7 +282,7 @@ void __kasan_kfree_large(void *ptr, unsigned long ip)
 	____kasan_kfree_large(ptr, ip);
 }
 
-void __kasan_slab_free_mempool(void *ptr, unsigned long ip)
+void __kasan_mempool_poison_object(void *ptr, unsigned long ip)
 {
 	struct folio *folio;
 
diff --git a/mm/mempool.c b/mm/mempool.c
index b3d2084fd989..7e1c729f292b 100644
--- a/mm/mempool.c
+++ b/mm/mempool.c
@@ -107,7 +107,7 @@ static inline void poison_element(mempool_t *pool, void *element)
 static __always_inline void kasan_poison_element(mempool_t *pool, void *element)
 {
 	if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc)
-		kasan_slab_free_mempool(element);
+		kasan_mempool_poison_object(element);
 	else if (pool->alloc == mempool_alloc_pages)
 		kasan_poison_pages(element, (unsigned long)pool->pool_data,
 				   false);
-- 
cgit v1.2.3


From 9b94fe91099cbf05606151ef05bea9632666f5d5 Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Tue, 19 Dec 2023 23:28:46 +0100
Subject: kasan: move kasan_mempool_poison_object

Move kasan_mempool_poison_object after all slab-related KASAN hooks.

This is a preparatory change for the following patches in this series.

No functional changes.

Link: https://lkml.kernel.org/r/23ea215409f43c13cdf9ecc454501a264c107d67.1703024586.git.andreyknvl@google.com
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Cc: Alexander Lobakin <alobakin@pm.me>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Breno Leitao <leitao@debian.org>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Marco Elver <elver@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/kasan.h | 16 ++++++++--------
 mm/kasan/common.c     | 46 +++++++++++++++++++++++-----------------------
 2 files changed, 31 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 6310435f528b..0d1f925c136d 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -172,13 +172,6 @@ static __always_inline void kasan_kfree_large(void *ptr)
 		__kasan_kfree_large(ptr, _RET_IP_);
 }
 
-void __kasan_mempool_poison_object(void *ptr, unsigned long ip);
-static __always_inline void kasan_mempool_poison_object(void *ptr)
-{
-	if (kasan_enabled())
-		__kasan_mempool_poison_object(ptr, _RET_IP_);
-}
-
 void * __must_check __kasan_slab_alloc(struct kmem_cache *s,
 				       void *object, gfp_t flags, bool init);
 static __always_inline void * __must_check kasan_slab_alloc(
@@ -219,6 +212,13 @@ static __always_inline void * __must_check kasan_krealloc(const void *object,
 	return (void *)object;
 }
 
+void __kasan_mempool_poison_object(void *ptr, unsigned long ip);
+static __always_inline void kasan_mempool_poison_object(void *ptr)
+{
+	if (kasan_enabled())
+		__kasan_mempool_poison_object(ptr, _RET_IP_);
+}
+
 /*
  * Unlike kasan_check_read/write(), kasan_check_byte() is performed even for
  * the hardware tag-based mode that doesn't rely on compiler instrumentation.
@@ -256,7 +256,6 @@ static inline bool kasan_slab_free(struct kmem_cache *s, void *object, bool init
 	return false;
 }
 static inline void kasan_kfree_large(void *ptr) {}
-static inline void kasan_mempool_poison_object(void *ptr) {}
 static inline void *kasan_slab_alloc(struct kmem_cache *s, void *object,
 				   gfp_t flags, bool init)
 {
@@ -276,6 +275,7 @@ static inline void *kasan_krealloc(const void *object, size_t new_size,
 {
 	return (void *)object;
 }
+static inline void kasan_mempool_poison_object(void *ptr) {}
 static inline bool kasan_check_byte(const void *address)
 {
 	return true;
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index e0394d0ee7f1..fc7f711607e1 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -282,29 +282,6 @@ void __kasan_kfree_large(void *ptr, unsigned long ip)
 	____kasan_kfree_large(ptr, ip);
 }
 
-void __kasan_mempool_poison_object(void *ptr, unsigned long ip)
-{
-	struct folio *folio;
-
-	folio = virt_to_folio(ptr);
-
-	/*
-	 * Even though this function is only called for kmem_cache_alloc and
-	 * kmalloc backed mempool allocations, those allocations can still be
-	 * !PageSlab() when the size provided to kmalloc is larger than
-	 * KMALLOC_MAX_SIZE, and kmalloc falls back onto page_alloc.
-	 */
-	if (unlikely(!folio_test_slab(folio))) {
-		if (____kasan_kfree_large(ptr, ip))
-			return;
-		kasan_poison(ptr, folio_size(folio), KASAN_PAGE_FREE, false);
-	} else {
-		struct slab *slab = folio_slab(folio);
-
-		____kasan_slab_free(slab->slab_cache, ptr, ip, false, false);
-	}
-}
-
 void * __must_check __kasan_slab_alloc(struct kmem_cache *cache,
 					void *object, gfp_t flags, bool init)
 {
@@ -452,6 +429,29 @@ void * __must_check __kasan_krealloc(const void *object, size_t size, gfp_t flag
 		return ____kasan_kmalloc(slab->slab_cache, object, size, flags);
 }
 
+void __kasan_mempool_poison_object(void *ptr, unsigned long ip)
+{
+	struct folio *folio;
+
+	folio = virt_to_folio(ptr);
+
+	/*
+	 * Even though this function is only called for kmem_cache_alloc and
+	 * kmalloc backed mempool allocations, those allocations can still be
+	 * !PageSlab() when the size provided to kmalloc is larger than
+	 * KMALLOC_MAX_SIZE, and kmalloc falls back onto page_alloc.
+	 */
+	if (unlikely(!folio_test_slab(folio))) {
+		if (____kasan_kfree_large(ptr, ip))
+			return;
+		kasan_poison(ptr, folio_size(folio), KASAN_PAGE_FREE, false);
+	} else {
+		struct slab *slab = folio_slab(folio);
+
+		____kasan_slab_free(slab->slab_cache, ptr, ip, false, false);
+	}
+}
+
 bool __kasan_check_byte(const void *address, unsigned long ip)
 {
 	if (!kasan_byte_accessible(address)) {
-- 
cgit v1.2.3


From 1bb843048d00050678c392dab87a15c8b756df6f Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Tue, 19 Dec 2023 23:28:47 +0100
Subject: kasan: document kasan_mempool_poison_object

Add documentation comment for kasan_mempool_poison_object.

Link: https://lkml.kernel.org/r/af33ba8cabfa1ad731fe23a3f874bfc8d3b7fed4.1703024586.git.andreyknvl@google.com
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Cc: Alexander Lobakin <alobakin@pm.me>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Breno Leitao <leitao@debian.org>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Marco Elver <elver@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/kasan.h | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

(limited to 'include')

diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 0d1f925c136d..bbf6e2fa4ffd 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -213,6 +213,24 @@ static __always_inline void * __must_check kasan_krealloc(const void *object,
 }
 
 void __kasan_mempool_poison_object(void *ptr, unsigned long ip);
+/**
+ * kasan_mempool_poison_object - Check and poison a mempool slab allocation.
+ * @ptr: Pointer to the slab allocation.
+ *
+ * This function is intended for kernel subsystems that cache slab allocations
+ * to reuse them instead of freeing them back to the slab allocator (e.g.
+ * mempool).
+ *
+ * This function poisons a slab allocation without initializing its memory and
+ * without putting it into the quarantine (for the Generic mode).
+ *
+ * This function also performs checks to detect double-free and invalid-free
+ * bugs and reports them.
+ *
+ * This function operates on all slab allocations including large kmalloc
+ * allocations (the ones returned by kmalloc_large() or by kmalloc() with the
+ * size > KMALLOC_MAX_SIZE).
+ */
 static __always_inline void kasan_mempool_poison_object(void *ptr)
 {
 	if (kasan_enabled())
-- 
cgit v1.2.3


From 2e7c954c11af96aa1e0566a706f22152ef91d759 Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Tue, 19 Dec 2023 23:28:48 +0100
Subject: kasan: add return value for kasan_mempool_poison_object

Add a return value for kasan_mempool_poison_object that lets the caller
know whether the allocation is affected by a double-free or an
invalid-free bug.  The caller can use this return value to stop operating
on the object.

Also introduce a check_page_allocation helper function to improve the code
readability.

Link: https://lkml.kernel.org/r/618af65273875fb9f56954285443279b15f1fcd9.1703024586.git.andreyknvl@google.com
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Cc: Alexander Lobakin <alobakin@pm.me>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Breno Leitao <leitao@debian.org>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Marco Elver <elver@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/kasan.h | 17 ++++++++++++-----
 mm/kasan/common.c     | 21 ++++++++++-----------
 2 files changed, 22 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index bbf6e2fa4ffd..33387e254caa 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -212,7 +212,7 @@ static __always_inline void * __must_check kasan_krealloc(const void *object,
 	return (void *)object;
 }
 
-void __kasan_mempool_poison_object(void *ptr, unsigned long ip);
+bool __kasan_mempool_poison_object(void *ptr, unsigned long ip);
 /**
  * kasan_mempool_poison_object - Check and poison a mempool slab allocation.
  * @ptr: Pointer to the slab allocation.
@@ -225,16 +225,20 @@ void __kasan_mempool_poison_object(void *ptr, unsigned long ip);
  * without putting it into the quarantine (for the Generic mode).
  *
  * This function also performs checks to detect double-free and invalid-free
- * bugs and reports them.
+ * bugs and reports them. The caller can use the return value of this function
+ * to find out if the allocation is buggy.
  *
  * This function operates on all slab allocations including large kmalloc
  * allocations (the ones returned by kmalloc_large() or by kmalloc() with the
  * size > KMALLOC_MAX_SIZE).
+ *
+ * Return: true if the allocation can be safely reused; false otherwise.
  */
-static __always_inline void kasan_mempool_poison_object(void *ptr)
+static __always_inline bool kasan_mempool_poison_object(void *ptr)
 {
 	if (kasan_enabled())
-		__kasan_mempool_poison_object(ptr, _RET_IP_);
+		return __kasan_mempool_poison_object(ptr, _RET_IP_);
+	return true;
 }
 
 /*
@@ -293,7 +297,10 @@ static inline void *kasan_krealloc(const void *object, size_t new_size,
 {
 	return (void *)object;
 }
-static inline void kasan_mempool_poison_object(void *ptr) {}
+static inline bool kasan_mempool_poison_object(void *ptr)
+{
+	return true;
+}
 static inline bool kasan_check_byte(const void *address)
 {
 	return true;
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index fc7f711607e1..2b4869de4985 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -254,7 +254,7 @@ bool __kasan_slab_free(struct kmem_cache *cache, void *object,
 	return ____kasan_slab_free(cache, object, ip, true, init);
 }
 
-static inline bool ____kasan_kfree_large(void *ptr, unsigned long ip)
+static inline bool check_page_allocation(void *ptr, unsigned long ip)
 {
 	if (!kasan_arch_is_ready())
 		return false;
@@ -269,17 +269,14 @@ static inline bool ____kasan_kfree_large(void *ptr, unsigned long ip)
 		return true;
 	}
 
-	/*
-	 * The object will be poisoned by kasan_poison_pages() or
-	 * kasan_mempool_poison_object().
-	 */
-
 	return false;
 }
 
 void __kasan_kfree_large(void *ptr, unsigned long ip)
 {
-	____kasan_kfree_large(ptr, ip);
+	check_page_allocation(ptr, ip);
+
+	/* The object will be poisoned by kasan_poison_pages(). */
 }
 
 void * __must_check __kasan_slab_alloc(struct kmem_cache *cache,
@@ -429,7 +426,7 @@ void * __must_check __kasan_krealloc(const void *object, size_t size, gfp_t flag
 		return ____kasan_kmalloc(slab->slab_cache, object, size, flags);
 }
 
-void __kasan_mempool_poison_object(void *ptr, unsigned long ip)
+bool __kasan_mempool_poison_object(void *ptr, unsigned long ip)
 {
 	struct folio *folio;
 
@@ -442,13 +439,15 @@ void __kasan_mempool_poison_object(void *ptr, unsigned long ip)
 	 * KMALLOC_MAX_SIZE, and kmalloc falls back onto page_alloc.
 	 */
 	if (unlikely(!folio_test_slab(folio))) {
-		if (____kasan_kfree_large(ptr, ip))
-			return;
+		if (check_page_allocation(ptr, ip))
+			return false;
 		kasan_poison(ptr, folio_size(folio), KASAN_PAGE_FREE, false);
+		return true;
 	} else {
 		struct slab *slab = folio_slab(folio);
 
-		____kasan_slab_free(slab->slab_cache, ptr, ip, false, false);
+		return !____kasan_slab_free(slab->slab_cache, ptr, ip,
+						false, false);
 	}
 }
 
-- 
cgit v1.2.3


From 1956832753735b1c399b86b2c66cb7c317dc9f31 Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Tue, 19 Dec 2023 23:28:49 +0100
Subject: kasan: introduce kasan_mempool_unpoison_object

Introduce and document a kasan_mempool_unpoison_object hook.

This hook serves as a replacement for the generic kasan_unpoison_range
that the mempool code relies on right now.  mempool will be updated to use
the new hook in one of the following patches.

For now, define the new hook to be identical to kasan_unpoison_range.  One
of the following patches will update it to add stack trace collection.

Link: https://lkml.kernel.org/r/dae25f0e18ed8fd50efe509c5b71a0592de5c18d.1703024586.git.andreyknvl@google.com
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Cc: Alexander Lobakin <alobakin@pm.me>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Breno Leitao <leitao@debian.org>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Marco Elver <elver@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/kasan.h | 31 +++++++++++++++++++++++++++++++
 mm/kasan/common.c     |  5 +++++
 2 files changed, 36 insertions(+)

(limited to 'include')

diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 33387e254caa..c5fe303bc1c2 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -228,6 +228,9 @@ bool __kasan_mempool_poison_object(void *ptr, unsigned long ip);
  * bugs and reports them. The caller can use the return value of this function
  * to find out if the allocation is buggy.
  *
+ * Before the poisoned allocation can be reused, it must be unpoisoned via
+ * kasan_mempool_unpoison_object().
+ *
  * This function operates on all slab allocations including large kmalloc
  * allocations (the ones returned by kmalloc_large() or by kmalloc() with the
  * size > KMALLOC_MAX_SIZE).
@@ -241,6 +244,32 @@ static __always_inline bool kasan_mempool_poison_object(void *ptr)
 	return true;
 }
 
+void __kasan_mempool_unpoison_object(void *ptr, size_t size, unsigned long ip);
+/**
+ * kasan_mempool_unpoison_object - Unpoison a mempool slab allocation.
+ * @ptr: Pointer to the slab allocation.
+ * @size: Size to be unpoisoned.
+ *
+ * This function is intended for kernel subsystems that cache slab allocations
+ * to reuse them instead of freeing them back to the slab allocator (e.g.
+ * mempool).
+ *
+ * This function unpoisons a slab allocation that was previously poisoned via
+ * kasan_mempool_poison_object() without initializing its memory. For the
+ * tag-based modes, this function does not assign a new tag to the allocation
+ * and instead restores the original tags based on the pointer value.
+ *
+ * This function operates on all slab allocations including large kmalloc
+ * allocations (the ones returned by kmalloc_large() or by kmalloc() with the
+ * size > KMALLOC_MAX_SIZE).
+ */
+static __always_inline void kasan_mempool_unpoison_object(void *ptr,
+							  size_t size)
+{
+	if (kasan_enabled())
+		__kasan_mempool_unpoison_object(ptr, size, _RET_IP_);
+}
+
 /*
  * Unlike kasan_check_read/write(), kasan_check_byte() is performed even for
  * the hardware tag-based mode that doesn't rely on compiler instrumentation.
@@ -301,6 +330,8 @@ static inline bool kasan_mempool_poison_object(void *ptr)
 {
 	return true;
 }
+static inline void kasan_mempool_unpoison_object(void *ptr, size_t size) {}
+
 static inline bool kasan_check_byte(const void *address)
 {
 	return true;
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index 2b4869de4985..4b85d35bb8ab 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -451,6 +451,11 @@ bool __kasan_mempool_poison_object(void *ptr, unsigned long ip)
 	}
 }
 
+void __kasan_mempool_unpoison_object(void *ptr, size_t size, unsigned long ip)
+{
+	kasan_unpoison(ptr, size, false);
+}
+
 bool __kasan_check_byte(const void *address, unsigned long ip)
 {
 	if (!kasan_byte_accessible(address)) {
-- 
cgit v1.2.3


From f129c31039283df884913142b0f3797d64d3a9d6 Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Tue, 19 Dec 2023 23:28:50 +0100
Subject: kasan: introduce kasan_mempool_poison_pages

Introduce and document a kasan_mempool_poison_pages hook to be used by the
mempool code instead of kasan_poison_pages.

Compated to kasan_poison_pages, the new hook:

1. For the tag-based modes, skips checking and poisoning allocations that
   were not tagged due to sampling.

2. Checks for double-free and invalid-free bugs.

In the future, kasan_poison_pages can also be updated to handle #2, but
this is out-of-scope of this series.

Link: https://lkml.kernel.org/r/88dc7340cce28249abf789f6e0c792c317df9ba5.1703024586.git.andreyknvl@google.com
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Cc: Alexander Lobakin <alobakin@pm.me>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Breno Leitao <leitao@debian.org>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Marco Elver <elver@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/kasan.h | 27 +++++++++++++++++++++++++++
 mm/kasan/common.c     | 23 +++++++++++++++++++++++
 2 files changed, 50 insertions(+)

(limited to 'include')

diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index c5fe303bc1c2..de2a695ad34d 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -212,6 +212,29 @@ static __always_inline void * __must_check kasan_krealloc(const void *object,
 	return (void *)object;
 }
 
+bool __kasan_mempool_poison_pages(struct page *page, unsigned int order,
+				  unsigned long ip);
+/**
+ * kasan_mempool_poison_pages - Check and poison a mempool page allocation.
+ * @page: Pointer to the page allocation.
+ * @order: Order of the allocation.
+ *
+ * This function is intended for kernel subsystems that cache page allocations
+ * to reuse them instead of freeing them back to page_alloc (e.g. mempool).
+ *
+ * This function is similar to kasan_mempool_poison_object() but operates on
+ * page allocations.
+ *
+ * Return: true if the allocation can be safely reused; false otherwise.
+ */
+static __always_inline bool kasan_mempool_poison_pages(struct page *page,
+						       unsigned int order)
+{
+	if (kasan_enabled())
+		return __kasan_mempool_poison_pages(page, order, _RET_IP_);
+	return true;
+}
+
 bool __kasan_mempool_poison_object(void *ptr, unsigned long ip);
 /**
  * kasan_mempool_poison_object - Check and poison a mempool slab allocation.
@@ -326,6 +349,10 @@ static inline void *kasan_krealloc(const void *object, size_t new_size,
 {
 	return (void *)object;
 }
+static inline bool kasan_mempool_poison_pages(struct page *page, unsigned int order)
+{
+	return true;
+}
 static inline bool kasan_mempool_poison_object(void *ptr)
 {
 	return true;
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index 4b85d35bb8ab..b416f4c265a4 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -426,6 +426,29 @@ void * __must_check __kasan_krealloc(const void *object, size_t size, gfp_t flag
 		return ____kasan_kmalloc(slab->slab_cache, object, size, flags);
 }
 
+bool __kasan_mempool_poison_pages(struct page *page, unsigned int order,
+				  unsigned long ip)
+{
+	unsigned long *ptr;
+
+	if (unlikely(PageHighMem(page)))
+		return true;
+
+	/* Bail out if allocation was excluded due to sampling. */
+	if (!IS_ENABLED(CONFIG_KASAN_GENERIC) &&
+	    page_kasan_tag(page) == KASAN_TAG_KERNEL)
+		return true;
+
+	ptr = page_address(page);
+
+	if (check_page_allocation(ptr, ip))
+		return false;
+
+	kasan_poison(ptr, PAGE_SIZE << order, KASAN_PAGE_FREE, false);
+
+	return true;
+}
+
 bool __kasan_mempool_poison_object(void *ptr, unsigned long ip)
 {
 	struct folio *folio;
-- 
cgit v1.2.3


From 9f41c59ae3163690868a32bd77e9e33c3bab555e Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Tue, 19 Dec 2023 23:28:51 +0100
Subject: kasan: introduce kasan_mempool_unpoison_pages

Introduce and document a new kasan_mempool_unpoison_pages hook to be used
by the mempool code instead of kasan_unpoison_pages.

This hook is not functionally different from kasan_unpoison_pages, but
using it improves the mempool code readability.

Link: https://lkml.kernel.org/r/239bd9af6176f2cc59f5c25893eb36143184daff.1703024586.git.andreyknvl@google.com
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Cc: Alexander Lobakin <alobakin@pm.me>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Breno Leitao <leitao@debian.org>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Marco Elver <elver@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/kasan.h | 25 +++++++++++++++++++++++++
 mm/kasan/common.c     |  6 ++++++
 2 files changed, 31 insertions(+)

(limited to 'include')

diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index de2a695ad34d..f8ebde384bd7 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -225,6 +225,9 @@ bool __kasan_mempool_poison_pages(struct page *page, unsigned int order,
  * This function is similar to kasan_mempool_poison_object() but operates on
  * page allocations.
  *
+ * Before the poisoned allocation can be reused, it must be unpoisoned via
+ * kasan_mempool_unpoison_pages().
+ *
  * Return: true if the allocation can be safely reused; false otherwise.
  */
 static __always_inline bool kasan_mempool_poison_pages(struct page *page,
@@ -235,6 +238,27 @@ static __always_inline bool kasan_mempool_poison_pages(struct page *page,
 	return true;
 }
 
+void __kasan_mempool_unpoison_pages(struct page *page, unsigned int order,
+				    unsigned long ip);
+/**
+ * kasan_mempool_unpoison_pages - Unpoison a mempool page allocation.
+ * @page: Pointer to the page allocation.
+ * @order: Order of the allocation.
+ *
+ * This function is intended for kernel subsystems that cache page allocations
+ * to reuse them instead of freeing them back to page_alloc (e.g. mempool).
+ *
+ * This function unpoisons a page allocation that was previously poisoned by
+ * kasan_mempool_poison_pages() without zeroing the allocation's memory. For
+ * the tag-based modes, this function assigns a new tag to the allocation.
+ */
+static __always_inline void kasan_mempool_unpoison_pages(struct page *page,
+							 unsigned int order)
+{
+	if (kasan_enabled())
+		__kasan_mempool_unpoison_pages(page, order, _RET_IP_);
+}
+
 bool __kasan_mempool_poison_object(void *ptr, unsigned long ip);
 /**
  * kasan_mempool_poison_object - Check and poison a mempool slab allocation.
@@ -353,6 +377,7 @@ static inline bool kasan_mempool_poison_pages(struct page *page, unsigned int or
 {
 	return true;
 }
+static inline void kasan_mempool_unpoison_pages(struct page *page, unsigned int order) {}
 static inline bool kasan_mempool_poison_object(void *ptr)
 {
 	return true;
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index b416f4c265a4..7ebc001d0fcd 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -449,6 +449,12 @@ bool __kasan_mempool_poison_pages(struct page *page, unsigned int order,
 	return true;
 }
 
+void __kasan_mempool_unpoison_pages(struct page *page, unsigned int order,
+				    unsigned long ip)
+{
+	__kasan_unpoison_pages(page, order, false);
+}
+
 bool __kasan_mempool_poison_object(void *ptr, unsigned long ip)
 {
 	struct folio *folio;
-- 
cgit v1.2.3


From b556a462eb8df6b6836c318d23f43409c40a7c7e Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Tue, 19 Dec 2023 23:28:53 +0100
Subject: kasan: save free stack traces for slab mempools

Make kasan_mempool_poison_object save free stack traces for slab and
kmalloc mempools when the object is freed into the mempool.

Also simplify and rename ____kasan_slab_free to poison_slab_object and do
a few other reability changes.

Link: https://lkml.kernel.org/r/413a7c7c3344fb56809853339ffaabc9e4905e94.1703024586.git.andreyknvl@google.com
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Cc: Alexander Lobakin <alobakin@pm.me>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Breno Leitao <leitao@debian.org>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Marco Elver <elver@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/kasan.h |  5 +++--
 mm/kasan/common.c     | 20 +++++++++-----------
 2 files changed, 12 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index f8ebde384bd7..e636a00e26ba 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -268,8 +268,9 @@ bool __kasan_mempool_poison_object(void *ptr, unsigned long ip);
  * to reuse them instead of freeing them back to the slab allocator (e.g.
  * mempool).
  *
- * This function poisons a slab allocation without initializing its memory and
- * without putting it into the quarantine (for the Generic mode).
+ * This function poisons a slab allocation and saves a free stack trace for it
+ * without initializing the allocation's memory and without putting it into the
+ * quarantine (for the Generic mode).
  *
  * This function also performs checks to detect double-free and invalid-free
  * bugs and reports them. The caller can use the return value of this function
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index 3f4a1ed69e03..59146886e57d 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -207,8 +207,8 @@ void * __must_check __kasan_init_slab_obj(struct kmem_cache *cache,
 	return (void *)object;
 }
 
-static inline bool ____kasan_slab_free(struct kmem_cache *cache, void *object,
-				unsigned long ip, bool quarantine, bool init)
+static inline bool poison_slab_object(struct kmem_cache *cache, void *object,
+				      unsigned long ip, bool init)
 {
 	void *tagged_object;
 
@@ -221,13 +221,12 @@ static inline bool ____kasan_slab_free(struct kmem_cache *cache, void *object,
 	if (is_kfence_address(object))
 		return false;
 
-	if (unlikely(nearest_obj(cache, virt_to_slab(object), object) !=
-	    object)) {
+	if (unlikely(nearest_obj(cache, virt_to_slab(object), object) != object)) {
 		kasan_report_invalid_free(tagged_object, ip, KASAN_REPORT_INVALID_FREE);
 		return true;
 	}
 
-	/* RCU slabs could be legally used after free within the RCU period */
+	/* RCU slabs could be legally used after free within the RCU period. */
 	if (unlikely(cache->flags & SLAB_TYPESAFE_BY_RCU))
 		return false;
 
@@ -239,19 +238,18 @@ static inline bool ____kasan_slab_free(struct kmem_cache *cache, void *object,
 	kasan_poison(object, round_up(cache->object_size, KASAN_GRANULE_SIZE),
 			KASAN_SLAB_FREE, init);
 
-	if ((IS_ENABLED(CONFIG_KASAN_GENERIC) && !quarantine))
-		return false;
-
 	if (kasan_stack_collection_enabled())
 		kasan_save_free_info(cache, tagged_object);
 
-	return kasan_quarantine_put(cache, object);
+	return false;
 }
 
 bool __kasan_slab_free(struct kmem_cache *cache, void *object,
 				unsigned long ip, bool init)
 {
-	return ____kasan_slab_free(cache, object, ip, true, init);
+	bool buggy_object = poison_slab_object(cache, object, ip, init);
+
+	return buggy_object ? true : kasan_quarantine_put(cache, object);
 }
 
 static inline bool check_page_allocation(void *ptr, unsigned long ip)
@@ -472,7 +470,7 @@ bool __kasan_mempool_poison_object(void *ptr, unsigned long ip)
 	}
 
 	slab = folio_slab(folio);
-	return !____kasan_slab_free(slab->slab_cache, ptr, ip, false, false);
+	return !poison_slab_object(slab->slab_cache, ptr, ip, false);
 }
 
 void __kasan_mempool_unpoison_object(void *ptr, size_t size, unsigned long ip)
-- 
cgit v1.2.3


From 29d7355a9d05de9a6e38cc4d1146fb96c43853fb Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Tue, 19 Dec 2023 23:28:56 +0100
Subject: kasan: save alloc stack traces for mempool

Update kasan_mempool_unpoison_object to properly poison the redzone and
save alloc strack traces for kmalloc and slab pools.

As a part of this change, split out and use a unpoison_slab_object helper
function from __kasan_slab_alloc.

[nathan@kernel.org: mark unpoison_slab_object() as static]
  Link: https://lkml.kernel.org/r/20231221180042.104694-1-andrey.konovalov@linux.dev
Link: https://lkml.kernel.org/r/05ad235da8347cfe14d496d01b2aaf074b4f607c.1703024586.git.andreyknvl@google.com
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Cc: Alexander Lobakin <alobakin@pm.me>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Breno Leitao <leitao@debian.org>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Marco Elver <elver@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/kasan.h |  7 ++++---
 mm/kasan/common.c     | 50 ++++++++++++++++++++++++++++++++++++++++----------
 2 files changed, 44 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index e636a00e26ba..7392c5d89b92 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -303,9 +303,10 @@ void __kasan_mempool_unpoison_object(void *ptr, size_t size, unsigned long ip);
  * mempool).
  *
  * This function unpoisons a slab allocation that was previously poisoned via
- * kasan_mempool_poison_object() without initializing its memory. For the
- * tag-based modes, this function does not assign a new tag to the allocation
- * and instead restores the original tags based on the pointer value.
+ * kasan_mempool_poison_object() and saves an alloc stack trace for it without
+ * initializing the allocation's memory. For the tag-based modes, this function
+ * does not assign a new tag to the allocation and instead restores the
+ * original tags based on the pointer value.
  *
  * This function operates on all slab allocations including large kmalloc
  * allocations (the ones returned by kmalloc_large() or by kmalloc() with the
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index 962805bf5f62..bf16c2dfa8e7 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -277,6 +277,20 @@ void __kasan_kfree_large(void *ptr, unsigned long ip)
 	/* The object will be poisoned by kasan_poison_pages(). */
 }
 
+static inline void unpoison_slab_object(struct kmem_cache *cache, void *object,
+					gfp_t flags, bool init)
+{
+	/*
+	 * Unpoison the whole object. For kmalloc() allocations,
+	 * poison_kmalloc_redzone() will do precise poisoning.
+	 */
+	kasan_unpoison(object, cache->object_size, init);
+
+	/* Save alloc info (if possible) for non-kmalloc() allocations. */
+	if (kasan_stack_collection_enabled() && !is_kmalloc_cache(cache))
+		kasan_save_alloc_info(cache, object, flags);
+}
+
 void * __must_check __kasan_slab_alloc(struct kmem_cache *cache,
 					void *object, gfp_t flags, bool init)
 {
@@ -299,15 +313,8 @@ void * __must_check __kasan_slab_alloc(struct kmem_cache *cache,
 	tag = assign_tag(cache, object, false);
 	tagged_object = set_tag(object, tag);
 
-	/*
-	 * Unpoison the whole object.
-	 * For kmalloc() allocations, kasan_kmalloc() will do precise poisoning.
-	 */
-	kasan_unpoison(tagged_object, cache->object_size, init);
-
-	/* Save alloc info (if possible) for non-kmalloc() allocations. */
-	if (kasan_stack_collection_enabled() && !is_kmalloc_cache(cache))
-		kasan_save_alloc_info(cache, tagged_object, flags);
+	/* Unpoison the object and save alloc info for non-kmalloc() allocations. */
+	unpoison_slab_object(cache, tagged_object, flags, init);
 
 	return tagged_object;
 }
@@ -482,7 +489,30 @@ bool __kasan_mempool_poison_object(void *ptr, unsigned long ip)
 
 void __kasan_mempool_unpoison_object(void *ptr, size_t size, unsigned long ip)
 {
-	kasan_unpoison(ptr, size, false);
+	struct slab *slab;
+	gfp_t flags = 0; /* Might be executing under a lock. */
+
+	if (is_kfence_address(kasan_reset_tag(ptr)))
+		return;
+
+	slab = virt_to_slab(ptr);
+
+	/*
+	 * This function can be called for large kmalloc allocation that get
+	 * their memory from page_alloc.
+	 */
+	if (unlikely(!slab)) {
+		kasan_unpoison(ptr, size, false);
+		poison_kmalloc_large_redzone(ptr, size, flags);
+		return;
+	}
+
+	/* Unpoison the object and save alloc info for non-kmalloc() allocations. */
+	unpoison_slab_object(slab->slab_cache, ptr, size, flags);
+
+	/* Poison the redzone and save alloc info for kmalloc() allocations. */
+	if (is_kmalloc_cache(slab->slab_cache))
+		poison_kmalloc_redzone(slab->slab_cache, ptr, size, flags);
 }
 
 bool __kasan_check_byte(const void *address, unsigned long ip)
-- 
cgit v1.2.3


From 37dcc69ad17a008d2b720bdc39f070ef2a959430 Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Tue, 19 Dec 2023 23:28:59 +0100
Subject: mempool: introduce mempool_use_prealloc_only

Introduce a new mempool_alloc_preallocated API that asks the mempool to
only use the elements preallocated during the mempool's creation when
allocating and to not attempt allocating new ones from the underlying
allocator.

This API is required to test the KASAN poisoning/unpoisoning functionality
in KASAN tests, but it might be also useful on its own.

Link: https://lkml.kernel.org/r/a14d809dbdfd04cc33bcacc632fee2abd6b83c00.1703024586.git.andreyknvl@google.com
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>

Cc: Alexander Lobakin <alobakin@pm.me>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Breno Leitao <leitao@debian.org>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Marco Elver <elver@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mempool.h |  1 +
 mm/mempool.c            | 37 +++++++++++++++++++++++++++++++++++++
 2 files changed, 38 insertions(+)

(limited to 'include')

diff --git a/include/linux/mempool.h b/include/linux/mempool.h
index 4aae6c06c5f2..7be1e32e6d42 100644
--- a/include/linux/mempool.h
+++ b/include/linux/mempool.h
@@ -51,6 +51,7 @@ extern mempool_t *mempool_create_node(int min_nr, mempool_alloc_t *alloc_fn,
 extern int mempool_resize(mempool_t *pool, int new_min_nr);
 extern void mempool_destroy(mempool_t *pool);
 extern void *mempool_alloc(mempool_t *pool, gfp_t gfp_mask) __malloc;
+extern void *mempool_alloc_preallocated(mempool_t *pool) __malloc;
 extern void mempool_free(void *element, mempool_t *pool);
 
 /*
diff --git a/mm/mempool.c b/mm/mempool.c
index 103dc4770cfb..cb7b4b56cec1 100644
--- a/mm/mempool.c
+++ b/mm/mempool.c
@@ -456,6 +456,43 @@ repeat_alloc:
 }
 EXPORT_SYMBOL(mempool_alloc);
 
+/**
+ * mempool_alloc_preallocated - allocate an element from preallocated elements
+ *                              belonging to a specific memory pool
+ * @pool:      pointer to the memory pool which was allocated via
+ *             mempool_create().
+ *
+ * This function is similar to mempool_alloc, but it only attempts allocating
+ * an element from the preallocated elements. It does not sleep and immediately
+ * returns if no preallocated elements are available.
+ *
+ * Return: pointer to the allocated element or %NULL if no elements are
+ * available.
+ */
+void *mempool_alloc_preallocated(mempool_t *pool)
+{
+	void *element;
+	unsigned long flags;
+
+	spin_lock_irqsave(&pool->lock, flags);
+	if (likely(pool->curr_nr)) {
+		element = remove_element(pool);
+		spin_unlock_irqrestore(&pool->lock, flags);
+		/* paired with rmb in mempool_free(), read comment there */
+		smp_wmb();
+		/*
+		 * Update the allocation stack trace as this is more useful
+		 * for debugging.
+		 */
+		kmemleak_update_trace(element);
+		return element;
+	}
+	spin_unlock_irqrestore(&pool->lock, flags);
+
+	return NULL;
+}
+EXPORT_SYMBOL(mempool_alloc_preallocated);
+
 /**
  * mempool_free - return an element to the pool.
  * @element:   pool element pointer.
-- 
cgit v1.2.3


From 1ce9a0523938f87dd8505233cc3445f8e2d8dcee Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Tue, 19 Dec 2023 23:29:03 +0100
Subject: kasan: rename and document kasan_(un)poison_object_data

Rename kasan_unpoison_object_data to kasan_unpoison_new_object and add a
documentation comment.  Do the same for kasan_poison_object_data.

The new names and the comments should suggest the users that these hooks
are intended for internal use by the slab allocator.

The following patch will remove non-slab-internal uses of these hooks.

No functional changes.

[andreyknvl@google.com: update references to renamed functions in comments]
  Link: https://lkml.kernel.org/r/20231221180637.105098-1-andrey.konovalov@linux.dev
Link: https://lkml.kernel.org/r/eab156ebbd635f9635ef67d1a4271f716994e628.1703024586.git.andreyknvl@google.com
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Reviewed-by: Marco Elver <elver@google.com>
Cc: Alexander Lobakin <alobakin@pm.me>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Breno Leitao <leitao@debian.org>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/kasan.h | 35 +++++++++++++++++++++++++++--------
 mm/kasan/common.c     |  4 ++--
 mm/kasan/shadow.c     |  4 ++--
 mm/slab.c             | 10 ++++------
 mm/slub.c             |  4 ++--
 net/core/skbuff.c     |  8 ++++----
 6 files changed, 41 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 7392c5d89b92..d49e3d4c099e 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -129,20 +129,39 @@ static __always_inline void kasan_poison_slab(struct slab *slab)
 		__kasan_poison_slab(slab);
 }
 
-void __kasan_unpoison_object_data(struct kmem_cache *cache, void *object);
-static __always_inline void kasan_unpoison_object_data(struct kmem_cache *cache,
+void __kasan_unpoison_new_object(struct kmem_cache *cache, void *object);
+/**
+ * kasan_unpoison_new_object - Temporarily unpoison a new slab object.
+ * @cache: Cache the object belong to.
+ * @object: Pointer to the object.
+ *
+ * This function is intended for the slab allocator's internal use. It
+ * temporarily unpoisons an object from a newly allocated slab without doing
+ * anything else. The object must later be repoisoned by
+ * kasan_poison_new_object().
+ */
+static __always_inline void kasan_unpoison_new_object(struct kmem_cache *cache,
 							void *object)
 {
 	if (kasan_enabled())
-		__kasan_unpoison_object_data(cache, object);
+		__kasan_unpoison_new_object(cache, object);
 }
 
-void __kasan_poison_object_data(struct kmem_cache *cache, void *object);
-static __always_inline void kasan_poison_object_data(struct kmem_cache *cache,
+void __kasan_poison_new_object(struct kmem_cache *cache, void *object);
+/**
+ * kasan_unpoison_new_object - Repoison a new slab object.
+ * @cache: Cache the object belong to.
+ * @object: Pointer to the object.
+ *
+ * This function is intended for the slab allocator's internal use. It
+ * repoisons an object that was previously unpoisoned by
+ * kasan_unpoison_new_object() without doing anything else.
+ */
+static __always_inline void kasan_poison_new_object(struct kmem_cache *cache,
 							void *object)
 {
 	if (kasan_enabled())
-		__kasan_poison_object_data(cache, object);
+		__kasan_poison_new_object(cache, object);
 }
 
 void * __must_check __kasan_init_slab_obj(struct kmem_cache *cache,
@@ -342,9 +361,9 @@ static inline bool kasan_unpoison_pages(struct page *page, unsigned int order,
 	return false;
 }
 static inline void kasan_poison_slab(struct slab *slab) {}
-static inline void kasan_unpoison_object_data(struct kmem_cache *cache,
+static inline void kasan_unpoison_new_object(struct kmem_cache *cache,
 					void *object) {}
-static inline void kasan_poison_object_data(struct kmem_cache *cache,
+static inline void kasan_poison_new_object(struct kmem_cache *cache,
 					void *object) {}
 static inline void *kasan_init_slab_obj(struct kmem_cache *cache,
 				const void *object)
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index bf16c2dfa8e7..f4255e807b74 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -143,12 +143,12 @@ void __kasan_poison_slab(struct slab *slab)
 		     KASAN_SLAB_REDZONE, false);
 }
 
-void __kasan_unpoison_object_data(struct kmem_cache *cache, void *object)
+void __kasan_unpoison_new_object(struct kmem_cache *cache, void *object)
 {
 	kasan_unpoison(object, cache->object_size, false);
 }
 
-void __kasan_poison_object_data(struct kmem_cache *cache, void *object)
+void __kasan_poison_new_object(struct kmem_cache *cache, void *object)
 {
 	kasan_poison(object, round_up(cache->object_size, KASAN_GRANULE_SIZE),
 			KASAN_SLAB_REDZONE, false);
diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c
index d687f09a7ae3..0154d200be40 100644
--- a/mm/kasan/shadow.c
+++ b/mm/kasan/shadow.c
@@ -130,7 +130,7 @@ void kasan_poison(const void *addr, size_t size, u8 value, bool init)
 
 	/*
 	 * Perform shadow offset calculation based on untagged address, as
-	 * some of the callers (e.g. kasan_poison_object_data) pass tagged
+	 * some of the callers (e.g. kasan_poison_new_object) pass tagged
 	 * addresses to this function.
 	 */
 	addr = kasan_reset_tag(addr);
@@ -170,7 +170,7 @@ void kasan_unpoison(const void *addr, size_t size, bool init)
 
 	/*
 	 * Perform shadow offset calculation based on untagged address, as
-	 * some of the callers (e.g. kasan_unpoison_object_data) pass tagged
+	 * some of the callers (e.g. kasan_unpoison_new_object) pass tagged
 	 * addresses to this function.
 	 */
 	addr = kasan_reset_tag(addr);
diff --git a/mm/slab.c b/mm/slab.c
index 9ad3d0f2d1a5..773c79e153f3 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -2327,11 +2327,9 @@ static void cache_init_objs_debug(struct kmem_cache *cachep, struct slab *slab)
 		 * They must also be threaded.
 		 */
 		if (cachep->ctor && !(cachep->flags & SLAB_POISON)) {
-			kasan_unpoison_object_data(cachep,
-						   objp + obj_offset(cachep));
+			kasan_unpoison_new_object(cachep, objp + obj_offset(cachep));
 			cachep->ctor(objp + obj_offset(cachep));
-			kasan_poison_object_data(
-				cachep, objp + obj_offset(cachep));
+			kasan_poison_new_object(cachep, objp + obj_offset(cachep));
 		}
 
 		if (cachep->flags & SLAB_RED_ZONE) {
@@ -2472,9 +2470,9 @@ static void cache_init_objs(struct kmem_cache *cachep,
 
 		/* constructor could break poison info */
 		if (DEBUG == 0 && cachep->ctor) {
-			kasan_unpoison_object_data(cachep, objp);
+			kasan_unpoison_new_object(cachep, objp);
 			cachep->ctor(objp);
-			kasan_poison_object_data(cachep, objp);
+			kasan_poison_new_object(cachep, objp);
 		}
 
 		if (!shuffled)
diff --git a/mm/slub.c b/mm/slub.c
index 782bd8a6bd34..891742e5932a 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1860,9 +1860,9 @@ static void *setup_object(struct kmem_cache *s, void *object)
 	setup_object_debug(s, object);
 	object = kasan_init_slab_obj(s, object);
 	if (unlikely(s->ctor)) {
-		kasan_unpoison_object_data(s, object);
+		kasan_unpoison_new_object(s, object);
 		s->ctor(object);
-		kasan_poison_object_data(s, object);
+		kasan_poison_new_object(s, object);
 	}
 	return object;
 }
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index b157efea5dea..63bb6526399d 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -337,7 +337,7 @@ static struct sk_buff *napi_skb_cache_get(void)
 	}
 
 	skb = nc->skb_cache[--nc->skb_count];
-	kasan_unpoison_object_data(skbuff_cache, skb);
+	kasan_unpoison_new_object(skbuff_cache, skb);
 
 	return skb;
 }
@@ -1309,13 +1309,13 @@ static void napi_skb_cache_put(struct sk_buff *skb)
 	struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
 	u32 i;
 
-	kasan_poison_object_data(skbuff_cache, skb);
+	kasan_poison_new_object(skbuff_cache, skb);
 	nc->skb_cache[nc->skb_count++] = skb;
 
 	if (unlikely(nc->skb_count == NAPI_SKB_CACHE_SIZE)) {
 		for (i = NAPI_SKB_CACHE_HALF; i < NAPI_SKB_CACHE_SIZE; i++)
-			kasan_unpoison_object_data(skbuff_cache,
-						   nc->skb_cache[i]);
+			kasan_unpoison_new_object(skbuff_cache,
+						  nc->skb_cache[i]);
 
 		kmem_cache_free_bulk(skbuff_cache, NAPI_SKB_CACHE_HALF,
 				     nc->skb_cache + NAPI_SKB_CACHE_HALF);
-- 
cgit v1.2.3


From 91349f541e7daa6cce15e01e7ffe4fd63731ead9 Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Tue, 19 Dec 2023 22:19:53 +0100
Subject: lib/stackdepot: fix comment in include/linux/stackdepot.h

As stack traces can now be evicted from the stack depot, remove the
comment saying that they are never removed.

Link: https://lkml.kernel.org/r/0ebe712d91f8d302a8947d3c9e9123bc2b1b8440.1703020707.git.andreyknvl@google.com
Fixes: 108be8def46e ("lib/stackdepot: allow users to evict stack traces")
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Reviewed-by: Marco Elver <elver@google.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/stackdepot.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h
index a6796f178913..adcbb8f23600 100644
--- a/include/linux/stackdepot.h
+++ b/include/linux/stackdepot.h
@@ -11,8 +11,6 @@
  * SLUB_DEBUG needs 256 bytes per object for that). Since allocation and free
  * stack traces often repeat, using stack depot allows to save about 100x space.
  *
- * Stack traces are never removed from the stack depot.
- *
  * Author: Alexander Potapenko <glider@google.com>
  * Copyright (C) 2016 Google, Inc.
  *
-- 
cgit v1.2.3


From 7fbb5e188248c50f737720825da1864ce42536d1 Mon Sep 17 00:00:00 2001
From: Fangrui Song <maskray@google.com>
Date: Tue, 19 Dec 2023 21:41:23 -0800
Subject: mm: remove VM_EXEC requirement for THP eligibility

Commit e6be37b2e7bd ("mm/huge_memory.c: add missing read-only THP checking
in transparent_hugepage_enabled()") introduced the VM_EXEC requirement,
which is not strictly needed.

lld's default --rosegment option and GNU ld's -z separate-code option
(default on Linux/x86 since binutils 2.31) create a read-only PT_LOAD
segment without the PF_X flag, which should be eligible for THP.

Certain architectures support medium and large code models, where .lrodata
may be placed in a separate read-only PT_LOAD segment, which should be
eligible for THP as well.

Link: https://lkml.kernel.org/r/20231220054123.1266001-1-maskray@google.com
Signed-off-by: Fangrui Song <maskray@google.com>
Acked-by: Yang Shi <shy828301@gmail.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Song Liu <songliubraving@fb.com>
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/huge_mm.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index fa7a38a30fc6..5adb86af35fc 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -206,7 +206,6 @@ static inline bool file_thp_enabled(struct vm_area_struct *vma)
 	inode = vma->vm_file->f_inode;
 
 	return (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS)) &&
-	       (vma->vm_flags & VM_EXEC) &&
 	       !inode_is_open_for_write(inode) && S_ISREG(inode->i_mode);
 }
 
-- 
cgit v1.2.3


From 5ec8e8ea8b7783fab150cf86404fc38cb4db8800 Mon Sep 17 00:00:00 2001
From: Charan Teja Kalla <quic_charante@quicinc.com>
Date: Fri, 13 Oct 2023 18:34:27 +0530
Subject: mm/sparsemem: fix race in accessing memory_section->usage

The below race is observed on a PFN which falls into the device memory
region with the system memory configuration where PFN's are such that
[ZONE_NORMAL ZONE_DEVICE ZONE_NORMAL].  Since normal zone start and end
pfn contains the device memory PFN's as well, the compaction triggered
will try on the device memory PFN's too though they end up in NOP(because
pfn_to_online_page() returns NULL for ZONE_DEVICE memory sections).  When
from other core, the section mappings are being removed for the
ZONE_DEVICE region, that the PFN in question belongs to, on which
compaction is currently being operated is resulting into the kernel crash
with CONFIG_SPASEMEM_VMEMAP enabled.  The crash logs can be seen at [1].

compact_zone()			memunmap_pages
-------------			---------------
__pageblock_pfn_to_page
   ......
 (a)pfn_valid():
     valid_section()//return true
			      (b)__remove_pages()->
				  sparse_remove_section()->
				    section_deactivate():
				    [Free the array ms->usage and set
				     ms->usage = NULL]
     pfn_section_valid()
     [Access ms->usage which
     is NULL]

NOTE: From the above it can be said that the race is reduced to between
the pfn_valid()/pfn_section_valid() and the section deactivate with
SPASEMEM_VMEMAP enabled.

The commit b943f045a9af("mm/sparse: fix kernel crash with
pfn_section_valid check") tried to address the same problem by clearing
the SECTION_HAS_MEM_MAP with the expectation of valid_section() returns
false thus ms->usage is not accessed.

Fix this issue by the below steps:

a) Clear SECTION_HAS_MEM_MAP before freeing the ->usage.

b) RCU protected read side critical section will either return NULL
   when SECTION_HAS_MEM_MAP is cleared or can successfully access ->usage.

c) Free the ->usage with kfree_rcu() and set ms->usage = NULL.  No
   attempt will be made to access ->usage after this as the
   SECTION_HAS_MEM_MAP is cleared thus valid_section() return false.

Thanks to David/Pavan for their inputs on this patch.

[1] https://lore.kernel.org/linux-mm/994410bb-89aa-d987-1f50-f514903c55aa@quicinc.com/

On Snapdragon SoC, with the mentioned memory configuration of PFN's as
[ZONE_NORMAL ZONE_DEVICE ZONE_NORMAL], we are able to see bunch of
issues daily while testing on a device farm.

For this particular issue below is the log.  Though the below log is
not directly pointing to the pfn_section_valid(){ ms->usage;}, when we
loaded this dump on T32 lauterbach tool, it is pointing.

[  540.578056] Unable to handle kernel NULL pointer dereference at
virtual address 0000000000000000
[  540.578068] Mem abort info:
[  540.578070]   ESR = 0x0000000096000005
[  540.578073]   EC = 0x25: DABT (current EL), IL = 32 bits
[  540.578077]   SET = 0, FnV = 0
[  540.578080]   EA = 0, S1PTW = 0
[  540.578082]   FSC = 0x05: level 1 translation fault
[  540.578085] Data abort info:
[  540.578086]   ISV = 0, ISS = 0x00000005
[  540.578088]   CM = 0, WnR = 0
[  540.579431] pstate: 82400005 (Nzcv daif +PAN -UAO +TCO -DIT -SSBSBTYPE=--)
[  540.579436] pc : __pageblock_pfn_to_page+0x6c/0x14c
[  540.579454] lr : compact_zone+0x994/0x1058
[  540.579460] sp : ffffffc03579b510
[  540.579463] x29: ffffffc03579b510 x28: 0000000000235800 x27:000000000000000c
[  540.579470] x26: 0000000000235c00 x25: 0000000000000068 x24:ffffffc03579b640
[  540.579477] x23: 0000000000000001 x22: ffffffc03579b660 x21:0000000000000000
[  540.579483] x20: 0000000000235bff x19: ffffffdebf7e3940 x18:ffffffdebf66d140
[  540.579489] x17: 00000000739ba063 x16: 00000000739ba063 x15:00000000009f4bff
[  540.579495] x14: 0000008000000000 x13: 0000000000000000 x12:0000000000000001
[  540.579501] x11: 0000000000000000 x10: 0000000000000000 x9 :ffffff897d2cd440
[  540.579507] x8 : 0000000000000000 x7 : 0000000000000000 x6 :ffffffc03579b5b4
[  540.579512] x5 : 0000000000027f25 x4 : ffffffc03579b5b8 x3 :0000000000000001
[  540.579518] x2 : ffffffdebf7e3940 x1 : 0000000000235c00 x0 :0000000000235800
[  540.579524] Call trace:
[  540.579527]  __pageblock_pfn_to_page+0x6c/0x14c
[  540.579533]  compact_zone+0x994/0x1058
[  540.579536]  try_to_compact_pages+0x128/0x378
[  540.579540]  __alloc_pages_direct_compact+0x80/0x2b0
[  540.579544]  __alloc_pages_slowpath+0x5c0/0xe10
[  540.579547]  __alloc_pages+0x250/0x2d0
[  540.579550]  __iommu_dma_alloc_noncontiguous+0x13c/0x3fc
[  540.579561]  iommu_dma_alloc+0xa0/0x320
[  540.579565]  dma_alloc_attrs+0xd4/0x108

[quic_charante@quicinc.com: use kfree_rcu() in place of synchronize_rcu(), per David]
  Link: https://lkml.kernel.org/r/1698403778-20938-1-git-send-email-quic_charante@quicinc.com
Link: https://lkml.kernel.org/r/1697202267-23600-1-git-send-email-quic_charante@quicinc.com
Fixes: f46edbd1b151 ("mm/sparsemem: add helpers track active portions of a section at boot")
Signed-off-by: Charan Teja Kalla <quic_charante@quicinc.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mmzone.h | 14 +++++++++++---
 mm/sparse.c            | 17 +++++++++--------
 2 files changed, 20 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index ec73582e7d27..2efd3be484fd 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1799,6 +1799,7 @@ static inline unsigned long section_nr_to_pfn(unsigned long sec)
 #define SUBSECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SUBSECTION_MASK)
 
 struct mem_section_usage {
+	struct rcu_head rcu;
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 	DECLARE_BITMAP(subsection_map, SUBSECTIONS_PER_SECTION);
 #endif
@@ -1992,7 +1993,7 @@ static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn)
 {
 	int idx = subsection_map_index(pfn);
 
-	return test_bit(idx, ms->usage->subsection_map);
+	return test_bit(idx, READ_ONCE(ms->usage)->subsection_map);
 }
 #else
 static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn)
@@ -2016,6 +2017,7 @@ static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn)
 static inline int pfn_valid(unsigned long pfn)
 {
 	struct mem_section *ms;
+	int ret;
 
 	/*
 	 * Ensure the upper PAGE_SHIFT bits are clear in the
@@ -2029,13 +2031,19 @@ static inline int pfn_valid(unsigned long pfn)
 	if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
 		return 0;
 	ms = __pfn_to_section(pfn);
-	if (!valid_section(ms))
+	rcu_read_lock();
+	if (!valid_section(ms)) {
+		rcu_read_unlock();
 		return 0;
+	}
 	/*
 	 * Traditionally early sections always returned pfn_valid() for
 	 * the entire section-sized span.
 	 */
-	return early_section(ms) || pfn_section_valid(ms, pfn);
+	ret = early_section(ms) || pfn_section_valid(ms, pfn);
+	rcu_read_unlock();
+
+	return ret;
 }
 #endif
 
diff --git a/mm/sparse.c b/mm/sparse.c
index 77d91e565045..338cf946dee8 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -791,6 +791,13 @@ static void section_deactivate(unsigned long pfn, unsigned long nr_pages,
 	if (empty) {
 		unsigned long section_nr = pfn_to_section_nr(pfn);
 
+		/*
+		 * Mark the section invalid so that valid_section()
+		 * return false. This prevents code from dereferencing
+		 * ms->usage array.
+		 */
+		ms->section_mem_map &= ~SECTION_HAS_MEM_MAP;
+
 		/*
 		 * When removing an early section, the usage map is kept (as the
 		 * usage maps of other sections fall into the same page). It
@@ -799,16 +806,10 @@ static void section_deactivate(unsigned long pfn, unsigned long nr_pages,
 		 * was allocated during boot.
 		 */
 		if (!PageReserved(virt_to_page(ms->usage))) {
-			kfree(ms->usage);
-			ms->usage = NULL;
+			kfree_rcu(ms->usage, rcu);
+			WRITE_ONCE(ms->usage, NULL);
 		}
 		memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
-		/*
-		 * Mark the section invalid so that valid_section()
-		 * return false. This prevents code from dereferencing
-		 * ms->usage array.
-		 */
-		ms->section_mem_map &= ~SECTION_HAS_MEM_MAP;
 	}
 
 	/*
-- 
cgit v1.2.3


From 5cb6674b694b84803cbee8bfccaa2bfdfeb6eae4 Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Thu, 21 Dec 2023 21:04:44 +0100
Subject: mm, kasan: use KASAN_TAG_KERNEL instead of 0xff

Use the KASAN_TAG_KERNEL marco instead of open-coding 0xff in the mm code.
This macro is provided by include/linux/kasan-tags.h, which does not
include any other headers, so it's safe to include it into mm.h without
causing circular include dependencies.

Link: https://lkml.kernel.org/r/71db9087b0aebb6c4dccbc609cc0cd50621533c7.1703188911.git.andreyknvl@google.com
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Marco Elver <elver@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/kasan.h | 1 +
 include/linux/mm.h    | 4 ++--
 mm/page_alloc.c       | 2 +-
 3 files changed, 4 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index d49e3d4c099e..dbb06d789e74 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -4,6 +4,7 @@
 
 #include <linux/bug.h>
 #include <linux/kasan-enabled.h>
+#include <linux/kasan-tags.h>
 #include <linux/kernel.h>
 #include <linux/static_key.h>
 #include <linux/types.h>
diff --git a/include/linux/mm.h b/include/linux/mm.h
index b72bf25a45cf..2563ffdb51bc 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1815,7 +1815,7 @@ static inline void vma_set_access_pid_bit(struct vm_area_struct *vma)
 
 static inline u8 page_kasan_tag(const struct page *page)
 {
-	u8 tag = 0xff;
+	u8 tag = KASAN_TAG_KERNEL;
 
 	if (kasan_enabled()) {
 		tag = (page->flags >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK;
@@ -1844,7 +1844,7 @@ static inline void page_kasan_tag_set(struct page *page, u8 tag)
 static inline void page_kasan_tag_reset(struct page *page)
 {
 	if (kasan_enabled())
-		page_kasan_tag_set(page, 0xff);
+		page_kasan_tag_set(page, KASAN_TAG_KERNEL);
 }
 
 #else /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 692f33c764d2..5526797b7f96 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1059,7 +1059,7 @@ static inline bool should_skip_kasan_poison(struct page *page, fpi_t fpi_flags)
 	if (IS_ENABLED(CONFIG_KASAN_GENERIC))
 		return deferred_pages_enabled();
 
-	return page_kasan_tag(page) == 0xff;
+	return page_kasan_tag(page) == KASAN_TAG_KERNEL;
 }
 
 static void kernel_init_pages(struct page *page, int numpages)
-- 
cgit v1.2.3


From 9d5fafd5d882446999366f673ab06edba453f862 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Wed, 20 Dec 2023 23:44:25 +0100
Subject: mm/rmap: rename hugepage_add* to hugetlb_add*

Patch series "mm/rmap: interface overhaul", v2.

This series overhauls the rmap interface, to get rid of the "bool
compound" / RMAP_COMPOUND parameter with the goal of making the interface
less error prone, more future proof, and more natural to extend to
"batching".  Also, this converts the interface to always consume
folio+subpage, which speeds up operations on large folios.

Further, this series adds PTE-batching variants for 4 rmap functions,
whereby only folio_add_anon_rmap_ptes() is used for batching in this
series when PTE-remapping a PMD-mapped THP.  folio_remove_rmap_ptes(),
folio_try_dup_anon_rmap_ptes() and folio_dup_file_rmap_ptes() will soon
come in handy[1,2].

This series performs a lot of folio conversion along the way.  Most of the
added LOC in the diff are only due to documentation.

As we're moving to a pte/pmd interface where we clearly express the
mapping granularity we are dealing with, we first get the remainder of
hugetlb out of the way, as it is special and expected to remain special:
it treats everything as a "single logical PTE" and only currently allows
entire mappings.

Even if we'd ever support partial mappings, I strongly assume the
interface and implementation will still differ heavily: hopefull we can
avoid working on subpages/subpage mapcounts completely and only add a
"count" parameter for them to enable batching.

New (extended) hugetlb interface that operates on entire folio:
 * hugetlb_add_new_anon_rmap() -> Already existed
 * hugetlb_add_anon_rmap() -> Already existed
 * hugetlb_try_dup_anon_rmap()
 * hugetlb_try_share_anon_rmap()
 * hugetlb_add_file_rmap()
 * hugetlb_remove_rmap()

New "ordinary" interface for small folios / THP::
 * folio_add_new_anon_rmap() -> Already existed
 * folio_add_anon_rmap_[pte|ptes|pmd]()
 * folio_try_dup_anon_rmap_[pte|ptes|pmd]()
 * folio_try_share_anon_rmap_[pte|pmd]()
 * folio_add_file_rmap_[pte|ptes|pmd]()
 * folio_dup_file_rmap_[pte|ptes|pmd]()
 * folio_remove_rmap_[pte|ptes|pmd]()

folio_add_new_anon_rmap() will always map at the largest granularity
possible (currently, a single PMD to cover a PMD-sized THP).  Could be
extended if ever required.

In the future, we might want "_pud" variants and eventually "_pmds"
variants for batching.

I ran some simple microbenchmarks on an Intel(R) Xeon(R) Silver 4210R:
measuring munmap(), fork(), cow, MADV_DONTNEED on each PTE ...  and PTE
remapping PMD-mapped THPs on 1 GiB of memory.

For small folios, there is barely a change (< 1% improvement for me).

For PTE-mapped THP:
* PTE-remapping a PMD-mapped THP is more than 10% faster.
* fork() is more than 4% faster.
* MADV_DONTNEED is 2% faster
* COW when writing only a single byte on a COW-shared PTE is 1% faster
* munmap() barely changes (< 1%).

[1] https://lkml.kernel.org/r/20230810103332.3062143-1-ryan.roberts@arm.com
[2] https://lkml.kernel.org/r/20231204105440.61448-1-ryan.roberts@arm.com


This patch (of 40):

Let's just call it "hugetlb_".

Yes, it's all already inconsistent and confusing because we have a lot of
"hugepage_" functions for legacy reasons.  But "hugetlb" cannot possibly
be confused with transparent huge pages, and it matches "hugetlb.c" and
"folio_test_hugetlb()".  So let's minimize confusion in rmap code.

Link: https://lkml.kernel.org/r/20231220224504.646757-1-david@redhat.com
Link: https://lkml.kernel.org/r/20231220224504.646757-2-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Muchun Song <songmuchun@bytedance.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Yin Fengwei <fengwei.yin@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/rmap.h | 4 ++--
 mm/hugetlb.c         | 8 ++++----
 mm/migrate.c         | 4 ++--
 mm/rmap.c            | 8 ++++----
 4 files changed, 12 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 0ae2bb0e77f5..36096ba69bdc 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -206,9 +206,9 @@ void folio_add_file_rmap_range(struct folio *, struct page *, unsigned int nr,
 void page_remove_rmap(struct page *, struct vm_area_struct *,
 		bool compound);
 
-void hugepage_add_anon_rmap(struct folio *, struct vm_area_struct *,
+void hugetlb_add_anon_rmap(struct folio *, struct vm_area_struct *,
 		unsigned long address, rmap_t flags);
-void hugepage_add_new_anon_rmap(struct folio *, struct vm_area_struct *,
+void hugetlb_add_new_anon_rmap(struct folio *, struct vm_area_struct *,
 		unsigned long address);
 
 static inline void __page_dup_rmap(struct page *page, bool compound)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 6feb3e0630d1..305f3ca1dee6 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5285,7 +5285,7 @@ hugetlb_install_folio(struct vm_area_struct *vma, pte_t *ptep, unsigned long add
 	pte_t newpte = make_huge_pte(vma, &new_folio->page, 1);
 
 	__folio_mark_uptodate(new_folio);
-	hugepage_add_new_anon_rmap(new_folio, vma, addr);
+	hugetlb_add_new_anon_rmap(new_folio, vma, addr);
 	if (userfaultfd_wp(vma) && huge_pte_uffd_wp(old))
 		newpte = huge_pte_mkuffd_wp(newpte);
 	set_huge_pte_at(vma->vm_mm, addr, ptep, newpte, sz);
@@ -5988,7 +5988,7 @@ retry_avoidcopy:
 		/* Break COW or unshare */
 		huge_ptep_clear_flush(vma, haddr, ptep);
 		page_remove_rmap(&old_folio->page, vma, true);
-		hugepage_add_new_anon_rmap(new_folio, vma, haddr);
+		hugetlb_add_new_anon_rmap(new_folio, vma, haddr);
 		if (huge_pte_uffd_wp(pte))
 			newpte = huge_pte_mkuffd_wp(newpte);
 		set_huge_pte_at(mm, haddr, ptep, newpte, huge_page_size(h));
@@ -6277,7 +6277,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 		goto backout;
 
 	if (anon_rmap)
-		hugepage_add_new_anon_rmap(folio, vma, haddr);
+		hugetlb_add_new_anon_rmap(folio, vma, haddr);
 	else
 		page_dup_file_rmap(&folio->page, true);
 	new_pte = make_huge_pte(vma, &folio->page, ((vma->vm_flags & VM_WRITE)
@@ -6732,7 +6732,7 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte,
 	if (folio_in_pagecache)
 		page_dup_file_rmap(&folio->page, true);
 	else
-		hugepage_add_new_anon_rmap(folio, dst_vma, dst_addr);
+		hugetlb_add_new_anon_rmap(folio, dst_vma, dst_addr);
 
 	/*
 	 * For either: (1) CONTINUE on a non-shared VMA, or (2) UFFDIO_COPY
diff --git a/mm/migrate.c b/mm/migrate.c
index bad3039d165e..7d1c3f292d24 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -249,8 +249,8 @@ static bool remove_migration_pte(struct folio *folio,
 
 			pte = arch_make_huge_pte(pte, shift, vma->vm_flags);
 			if (folio_test_anon(folio))
-				hugepage_add_anon_rmap(folio, vma, pvmw.address,
-						       rmap_flags);
+				hugetlb_add_anon_rmap(folio, vma, pvmw.address,
+						      rmap_flags);
 			else
 				page_dup_file_rmap(new, true);
 			set_huge_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte,
diff --git a/mm/rmap.c b/mm/rmap.c
index 23da5b1ac33b..9845499b22f8 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -2625,8 +2625,8 @@ void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc)
  *
  * RMAP_COMPOUND is ignored.
  */
-void hugepage_add_anon_rmap(struct folio *folio, struct vm_area_struct *vma,
-			    unsigned long address, rmap_t flags)
+void hugetlb_add_anon_rmap(struct folio *folio, struct vm_area_struct *vma,
+		unsigned long address, rmap_t flags)
 {
 	VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio);
 
@@ -2637,8 +2637,8 @@ void hugepage_add_anon_rmap(struct folio *folio, struct vm_area_struct *vma,
 			 PageAnonExclusive(&folio->page), folio);
 }
 
-void hugepage_add_new_anon_rmap(struct folio *folio,
-			struct vm_area_struct *vma, unsigned long address)
+void hugetlb_add_new_anon_rmap(struct folio *folio,
+		struct vm_area_struct *vma, unsigned long address)
 {
 	BUG_ON(address < vma->vm_start || address >= vma->vm_end);
 	/* increment count (starts at -1) */
-- 
cgit v1.2.3


From e135826b2da0cf25305086dc9ac1e91718a148e1 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Wed, 20 Dec 2023 23:44:26 +0100
Subject: mm/rmap: introduce and use hugetlb_remove_rmap()

hugetlb rmap handling differs quite a lot from "ordinary" rmap code.  For
example, hugetlb currently only supports entire mappings, and treats any
mapping as mapped using a single "logical PTE".  Let's move it out of the
way so we can overhaul our "ordinary" rmap.  implementation/interface.

Let's introduce and use hugetlb_remove_rmap() and remove the hugetlb code
from page_remove_rmap().  This effectively removes one check on the
small-folio path as well.

Add sanity checks that we end up with the right folios in the right
functions.

Note: all possible candidates that need care are page_remove_rmap() that
      pass compound=true.

Link: https://lkml.kernel.org/r/20231220224504.646757-3-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Yin Fengwei <fengwei.yin@intel.com>
Reviewed-by: Ryan Roberts <ryan.roberts@arm.com>
Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Muchun Song <songmuchun@bytedance.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/rmap.h |  7 +++++++
 mm/hugetlb.c         |  4 ++--
 mm/rmap.c            | 18 +++++++++---------
 3 files changed, 18 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 36096ba69bdc..64ae6c4d7272 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -211,6 +211,13 @@ void hugetlb_add_anon_rmap(struct folio *, struct vm_area_struct *,
 void hugetlb_add_new_anon_rmap(struct folio *, struct vm_area_struct *,
 		unsigned long address);
 
+static inline void hugetlb_remove_rmap(struct folio *folio)
+{
+	VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio);
+
+	atomic_dec(&folio->_entire_mapcount);
+}
+
 static inline void __page_dup_rmap(struct page *page, bool compound)
 {
 	if (compound) {
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 305f3ca1dee6..ef48ae673890 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5676,7 +5676,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 					make_pte_marker(PTE_MARKER_UFFD_WP),
 					sz);
 		hugetlb_count_sub(pages_per_huge_page(h), mm);
-		page_remove_rmap(page, vma, true);
+		hugetlb_remove_rmap(page_folio(page));
 
 		spin_unlock(ptl);
 		tlb_remove_page_size(tlb, page, huge_page_size(h));
@@ -5987,7 +5987,7 @@ retry_avoidcopy:
 
 		/* Break COW or unshare */
 		huge_ptep_clear_flush(vma, haddr, ptep);
-		page_remove_rmap(&old_folio->page, vma, true);
+		hugetlb_remove_rmap(old_folio);
 		hugetlb_add_new_anon_rmap(new_folio, vma, haddr);
 		if (huge_pte_uffd_wp(pte))
 			newpte = huge_pte_mkuffd_wp(newpte);
diff --git a/mm/rmap.c b/mm/rmap.c
index 9845499b22f8..261e1af0d254 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1480,15 +1480,9 @@ void page_remove_rmap(struct page *page, struct vm_area_struct *vma,
 	bool last;
 	enum node_stat_item idx;
 
+	VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio);
 	VM_BUG_ON_PAGE(compound && !PageHead(page), page);
 
-	/* Hugetlb pages are not counted in NR_*MAPPED */
-	if (unlikely(folio_test_hugetlb(folio))) {
-		/* hugetlb pages are always mapped with pmds */
-		atomic_dec(&folio->_entire_mapcount);
-		return;
-	}
-
 	/* Is page being unmapped by PTE? Is this its last map to be removed? */
 	if (likely(!compound)) {
 		last = atomic_add_negative(-1, &page->_mapcount);
@@ -1846,7 +1840,10 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 			dec_mm_counter(mm, mm_counter_file(&folio->page));
 		}
 discard:
-		page_remove_rmap(subpage, vma, folio_test_hugetlb(folio));
+		if (unlikely(folio_test_hugetlb(folio)))
+			hugetlb_remove_rmap(folio);
+		else
+			page_remove_rmap(subpage, vma, false);
 		if (vma->vm_flags & VM_LOCKED)
 			mlock_drain_local();
 		folio_put(folio);
@@ -2199,7 +2196,10 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 			 */
 		}
 
-		page_remove_rmap(subpage, vma, folio_test_hugetlb(folio));
+		if (unlikely(folio_test_hugetlb(folio)))
+			hugetlb_remove_rmap(folio);
+		else
+			page_remove_rmap(subpage, vma, false);
 		if (vma->vm_flags & VM_LOCKED)
 			mlock_drain_local();
 		folio_put(folio);
-- 
cgit v1.2.3


From 44887f39945519fa8405133b1acd098fda9c9746 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Wed, 20 Dec 2023 23:44:27 +0100
Subject: mm/rmap: introduce and use hugetlb_add_file_rmap()

hugetlb rmap handling differs quite a lot from "ordinary" rmap code.  For
example, hugetlb currently only supports entire mappings, and treats any
mapping as mapped using a single "logical PTE".  Let's move it out of the
way so we can overhaul our "ordinary" rmap.  implementation/interface.

Right now we're using page_dup_file_rmap() in some cases where "ordinary"
rmap code would have used page_add_file_rmap().  So let's introduce and
use hugetlb_add_file_rmap() instead.  We won't be adding a
"hugetlb_dup_file_rmap()" functon for the fork() case, as it would be
doing the same: "dup" is just an optimization for "add".

What remains is a single page_dup_file_rmap() call in fork() code.

Add sanity checks that we end up with the right folios in the right
functions.

Link: https://lkml.kernel.org/r/20231220224504.646757-4-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Yin Fengwei <fengwei.yin@intel.com>
Reviewed-by: Ryan Roberts <ryan.roberts@arm.com>
Reviewed-by: Muchun Song <songmuchun@bytedance.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/rmap.h | 8 ++++++++
 mm/hugetlb.c         | 6 +++---
 mm/migrate.c         | 2 +-
 mm/rmap.c            | 1 +
 4 files changed, 13 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 64ae6c4d7272..56900a16f41a 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -211,6 +211,14 @@ void hugetlb_add_anon_rmap(struct folio *, struct vm_area_struct *,
 void hugetlb_add_new_anon_rmap(struct folio *, struct vm_area_struct *,
 		unsigned long address);
 
+static inline void hugetlb_add_file_rmap(struct folio *folio)
+{
+	VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio);
+	VM_WARN_ON_FOLIO(folio_test_anon(folio), folio);
+
+	atomic_inc(&folio->_entire_mapcount);
+}
+
 static inline void hugetlb_remove_rmap(struct folio *folio)
 {
 	VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index ef48ae673890..57e898187931 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5408,7 +5408,7 @@ again:
 			 * sleep during the process.
 			 */
 			if (!folio_test_anon(pte_folio)) {
-				page_dup_file_rmap(&pte_folio->page, true);
+				hugetlb_add_file_rmap(pte_folio);
 			} else if (page_try_dup_anon_rmap(&pte_folio->page,
 							  true, src_vma)) {
 				pte_t src_pte_old = entry;
@@ -6279,7 +6279,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 	if (anon_rmap)
 		hugetlb_add_new_anon_rmap(folio, vma, haddr);
 	else
-		page_dup_file_rmap(&folio->page, true);
+		hugetlb_add_file_rmap(folio);
 	new_pte = make_huge_pte(vma, &folio->page, ((vma->vm_flags & VM_WRITE)
 				&& (vma->vm_flags & VM_SHARED)));
 	/*
@@ -6730,7 +6730,7 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte,
 		goto out_release_unlock;
 
 	if (folio_in_pagecache)
-		page_dup_file_rmap(&folio->page, true);
+		hugetlb_add_file_rmap(folio);
 	else
 		hugetlb_add_new_anon_rmap(folio, dst_vma, dst_addr);
 
diff --git a/mm/migrate.c b/mm/migrate.c
index 7d1c3f292d24..0e912443a18c 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -252,7 +252,7 @@ static bool remove_migration_pte(struct folio *folio,
 				hugetlb_add_anon_rmap(folio, vma, pvmw.address,
 						      rmap_flags);
 			else
-				page_dup_file_rmap(new, true);
+				hugetlb_add_file_rmap(folio);
 			set_huge_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte,
 					psize);
 		} else
diff --git a/mm/rmap.c b/mm/rmap.c
index 261e1af0d254..a57ec926daf0 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1395,6 +1395,7 @@ void folio_add_file_rmap_range(struct folio *folio, struct page *page,
 	unsigned int nr_pmdmapped = 0, first;
 	int nr = 0;
 
+	VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio);
 	VM_WARN_ON_FOLIO(compound && !folio_test_pmd_mappable(folio), folio);
 
 	/* Is page being mapped by PTE? Is this its first map to be added? */
-- 
cgit v1.2.3


From ebe2e35ec0f256372c158a18de459fb60070b313 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Wed, 20 Dec 2023 23:44:28 +0100
Subject: mm/rmap: introduce and use hugetlb_try_dup_anon_rmap()

hugetlb rmap handling differs quite a lot from "ordinary" rmap code.  For
example, hugetlb currently only supports entire mappings, and treats any
mapping as mapped using a single "logical PTE".  Let's move it out of the
way so we can overhaul our "ordinary" rmap.  implementation/interface.

So let's introduce and use hugetlb_try_dup_anon_rmap() to make all hugetlb
handling use dedicated hugetlb_* rmap functions.

Add sanity checks that we end up with the right folios in the right
functions.

Note that is_device_private_page() does not apply to hugetlb.

Link: https://lkml.kernel.org/r/20231220224504.646757-5-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Yin Fengwei <fengwei.yin@intel.com>
Reviewed-by: Ryan Roberts <ryan.roberts@arm.com>
Reviewed-by: Muchun Song <songmuchun@bytedance.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mm.h   | 12 +++++++++---
 include/linux/rmap.h | 18 ++++++++++++++++++
 mm/hugetlb.c         |  3 +--
 3 files changed, 28 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 2563ffdb51bc..75bba6102825 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1964,15 +1964,21 @@ static inline bool page_maybe_dma_pinned(struct page *page)
  *
  * The caller has to hold the PT lock and the vma->vm_mm->->write_protect_seq.
  */
-static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma,
-					  struct page *page)
+static inline bool folio_needs_cow_for_dma(struct vm_area_struct *vma,
+					  struct folio *folio)
 {
 	VM_BUG_ON(!(raw_read_seqcount(&vma->vm_mm->write_protect_seq) & 1));
 
 	if (!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags))
 		return false;
 
-	return page_maybe_dma_pinned(page);
+	return folio_maybe_dma_pinned(folio);
+}
+
+static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma,
+					  struct page *page)
+{
+	return folio_needs_cow_for_dma(vma, page_folio(page));
 }
 
 /**
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 56900a16f41a..5f26752de945 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -211,6 +211,22 @@ void hugetlb_add_anon_rmap(struct folio *, struct vm_area_struct *,
 void hugetlb_add_new_anon_rmap(struct folio *, struct vm_area_struct *,
 		unsigned long address);
 
+/* See page_try_dup_anon_rmap() */
+static inline int hugetlb_try_dup_anon_rmap(struct folio *folio,
+		struct vm_area_struct *vma)
+{
+	VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio);
+	VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio);
+
+	if (PageAnonExclusive(&folio->page)) {
+		if (unlikely(folio_needs_cow_for_dma(vma, folio)))
+			return -EBUSY;
+		ClearPageAnonExclusive(&folio->page);
+	}
+	atomic_inc(&folio->_entire_mapcount);
+	return 0;
+}
+
 static inline void hugetlb_add_file_rmap(struct folio *folio)
 {
 	VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio);
@@ -228,6 +244,8 @@ static inline void hugetlb_remove_rmap(struct folio *folio)
 
 static inline void __page_dup_rmap(struct page *page, bool compound)
 {
+	VM_WARN_ON(folio_test_hugetlb(page_folio(page)));
+
 	if (compound) {
 		struct folio *folio = (struct folio *)page;
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 57e898187931..378e460a6ab4 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5409,8 +5409,7 @@ again:
 			 */
 			if (!folio_test_anon(pte_folio)) {
 				hugetlb_add_file_rmap(pte_folio);
-			} else if (page_try_dup_anon_rmap(&pte_folio->page,
-							  true, src_vma)) {
+			} else if (hugetlb_try_dup_anon_rmap(pte_folio, src_vma)) {
 				pte_t src_pte_old = entry;
 				struct folio *new_folio;
 
-- 
cgit v1.2.3


From 0c2ec32bf0b2f0d7ccb98c53ee5d255d68e73595 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Wed, 20 Dec 2023 23:44:29 +0100
Subject: mm/rmap: introduce and use hugetlb_try_share_anon_rmap()

hugetlb rmap handling differs quite a lot from "ordinary" rmap code.  For
example, hugetlb currently only supports entire mappings, and treats any
mapping as mapped using a single "logical PTE".  Let's move it out of the
way so we can overhaul our "ordinary" rmap.  implementation/interface.

So let's introduce and use hugetlb_try_dup_anon_rmap() to make all hugetlb
handling use dedicated hugetlb_* rmap functions.

Add sanity checks that we end up with the right folios in the right
functions.

Note that try_to_unmap_one() does not need care.  Easy to spot because
among all that nasty hugetlb special-casing in that function, we're not
using set_huge_pte_at() on the anon path -- well, and that code assumes
that we would want to swapout.

Link: https://lkml.kernel.org/r/20231220224504.646757-6-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Yin Fengwei <fengwei.yin@intel.com>
Reviewed-by: Ryan Roberts <ryan.roberts@arm.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/rmap.h | 25 +++++++++++++++++++++++++
 mm/rmap.c            | 15 ++++++++++-----
 2 files changed, 35 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 5f26752de945..d6fefa0f0410 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -227,6 +227,30 @@ static inline int hugetlb_try_dup_anon_rmap(struct folio *folio,
 	return 0;
 }
 
+/* See page_try_share_anon_rmap() */
+static inline int hugetlb_try_share_anon_rmap(struct folio *folio)
+{
+	VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio);
+	VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio);
+	VM_WARN_ON_FOLIO(!PageAnonExclusive(&folio->page), folio);
+
+	/* Paired with the memory barrier in try_grab_folio(). */
+	if (IS_ENABLED(CONFIG_HAVE_FAST_GUP))
+		smp_mb();
+
+	if (unlikely(folio_maybe_dma_pinned(folio)))
+		return -EBUSY;
+	ClearPageAnonExclusive(&folio->page);
+
+	/*
+	 * This is conceptually a smp_wmb() paired with the smp_rmb() in
+	 * gup_must_unshare().
+	 */
+	if (IS_ENABLED(CONFIG_HAVE_FAST_GUP))
+		smp_mb__after_atomic();
+	return 0;
+}
+
 static inline void hugetlb_add_file_rmap(struct folio *folio)
 {
 	VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio);
@@ -331,6 +355,7 @@ dup:
  */
 static inline int page_try_share_anon_rmap(struct page *page)
 {
+	VM_WARN_ON(folio_test_hugetlb(page_folio(page)));
 	VM_BUG_ON_PAGE(!PageAnon(page) || !PageAnonExclusive(page), page);
 
 	/* device private pages cannot get pinned via GUP. */
diff --git a/mm/rmap.c b/mm/rmap.c
index a57ec926daf0..c229e48cf5a9 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -2149,13 +2149,18 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 				       !anon_exclusive, subpage);
 
 			/* See page_try_share_anon_rmap(): clear PTE first. */
-			if (anon_exclusive &&
-			    page_try_share_anon_rmap(subpage)) {
-				if (folio_test_hugetlb(folio))
+			if (folio_test_hugetlb(folio)) {
+				if (anon_exclusive &&
+				    hugetlb_try_share_anon_rmap(folio)) {
 					set_huge_pte_at(mm, address, pvmw.pte,
 							pteval, hsz);
-				else
-					set_pte_at(mm, address, pvmw.pte, pteval);
+					ret = false;
+					page_vma_mapped_walk_done(&pvmw);
+					break;
+				}
+			} else if (anon_exclusive &&
+				   page_try_share_anon_rmap(subpage)) {
+				set_pte_at(mm, address, pvmw.pte, pteval);
 				ret = false;
 				page_vma_mapped_walk_done(&pvmw);
 				break;
-- 
cgit v1.2.3


From 68f0320824fa59c5429cbc811e6c46e7a30ea32c Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Wed, 20 Dec 2023 23:44:31 +0100
Subject: mm/rmap: convert folio_add_file_rmap_range() into
 folio_add_file_rmap_[pte|ptes|pmd]()

Let's get rid of the compound parameter and instead define explicitly
which mappings we're adding.  That is more future proof, easier to read
and harder to mess up.

Use an enum to express the granularity internally.  Make the compiler
always special-case on the granularity by using __always_inline.  Replace
the "compound" check by a switch-case that will be removed by the compiler
completely.

Add plenty of sanity checks with CONFIG_DEBUG_VM.  Replace the
folio_test_pmd_mappable() check by a config check in the caller and sanity
checks.  Convert the single user of folio_add_file_rmap_range().

While at it, consistently use "int" instead of "unisgned int" in rmap code
when dealing with mapcounts and the number of pages.

This function design can later easily be extended to PUDs and to batch
PMDs.  Note that for now we don't support anything bigger than PMD-sized
folios (as we cleanly separated hugetlb handling).  Sanity checks will
catch if that ever changes.

Next up is removing page_remove_rmap() along with its "compound" parameter
and smilarly converting all other rmap functions.

Link: https://lkml.kernel.org/r/20231220224504.646757-8-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Yin Fengwei <fengwei.yin@intel.com>
Reviewed-by: Ryan Roberts <ryan.roberts@arm.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/rmap.h | 46 ++++++++++++++++++++++++++++--
 mm/memory.c          |  2 +-
 mm/rmap.c            | 79 +++++++++++++++++++++++++++++++++-------------------
 3 files changed, 95 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index d6fefa0f0410..3d86a76b2836 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -191,6 +191,44 @@ typedef int __bitwise rmap_t;
  */
 #define RMAP_COMPOUND		((__force rmap_t)BIT(1))
 
+/*
+ * Internally, we're using an enum to specify the granularity. We make the
+ * compiler emit specialized code for each granularity.
+ */
+enum rmap_level {
+	RMAP_LEVEL_PTE = 0,
+	RMAP_LEVEL_PMD,
+};
+
+static inline void __folio_rmap_sanity_checks(struct folio *folio,
+		struct page *page, int nr_pages, enum rmap_level level)
+{
+	/* hugetlb folios are handled separately. */
+	VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio);
+	VM_WARN_ON_FOLIO(folio_test_large(folio) &&
+			 !folio_test_large_rmappable(folio), folio);
+
+	VM_WARN_ON_ONCE(nr_pages <= 0);
+	VM_WARN_ON_FOLIO(page_folio(page) != folio, folio);
+	VM_WARN_ON_FOLIO(page_folio(page + nr_pages - 1) != folio, folio);
+
+	switch (level) {
+	case RMAP_LEVEL_PTE:
+		break;
+	case RMAP_LEVEL_PMD:
+		/*
+		 * We don't support folios larger than a single PMD yet. So
+		 * when RMAP_LEVEL_PMD is set, we assume that we are creating
+		 * a single "entire" mapping of the folio.
+		 */
+		VM_WARN_ON_FOLIO(folio_nr_pages(folio) != HPAGE_PMD_NR, folio);
+		VM_WARN_ON_FOLIO(nr_pages != HPAGE_PMD_NR, folio);
+		break;
+	default:
+		VM_WARN_ON_ONCE(true);
+	}
+}
+
 /*
  * rmap interfaces called when adding or removing pte of page
  */
@@ -201,8 +239,12 @@ void folio_add_new_anon_rmap(struct folio *, struct vm_area_struct *,
 		unsigned long address);
 void page_add_file_rmap(struct page *, struct vm_area_struct *,
 		bool compound);
-void folio_add_file_rmap_range(struct folio *, struct page *, unsigned int nr,
-		struct vm_area_struct *, bool compound);
+void folio_add_file_rmap_ptes(struct folio *, struct page *, int nr_pages,
+		struct vm_area_struct *);
+#define folio_add_file_rmap_pte(folio, page, vma) \
+	folio_add_file_rmap_ptes(folio, page, 1, vma)
+void folio_add_file_rmap_pmd(struct folio *, struct page *,
+		struct vm_area_struct *);
 void page_remove_rmap(struct page *, struct vm_area_struct *,
 		bool compound);
 
diff --git a/mm/memory.c b/mm/memory.c
index cfcaf4c0198c..9b977b2cf893 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4516,7 +4516,7 @@ void set_pte_range(struct vm_fault *vmf, struct folio *folio,
 		folio_add_lru_vma(folio, vma);
 	} else {
 		add_mm_counter(vma->vm_mm, mm_counter_file(page), nr);
-		folio_add_file_rmap_range(folio, page, nr, vma, false);
+		folio_add_file_rmap_ptes(folio, page, nr, vma);
 	}
 	set_ptes(vma->vm_mm, addr, vmf->pte, entry, nr);
 
diff --git a/mm/rmap.c b/mm/rmap.c
index 6a1829324053..cc1fc2d570f0 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1378,31 +1378,18 @@ void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma,
 	__lruvec_stat_mod_folio(folio, NR_ANON_MAPPED, nr);
 }
 
-/**
- * folio_add_file_rmap_range - add pte mapping to page range of a folio
- * @folio:	The folio to add the mapping to
- * @page:	The first page to add
- * @nr_pages:	The number of pages which will be mapped
- * @vma:	the vm area in which the mapping is added
- * @compound:	charge the page as compound or small page
- *
- * The page range of folio is defined by [first_page, first_page + nr_pages)
- *
- * The caller needs to hold the pte lock.
- */
-void folio_add_file_rmap_range(struct folio *folio, struct page *page,
-			unsigned int nr_pages, struct vm_area_struct *vma,
-			bool compound)
+static __always_inline void __folio_add_file_rmap(struct folio *folio,
+		struct page *page, int nr_pages, struct vm_area_struct *vma,
+		enum rmap_level level)
 {
 	atomic_t *mapped = &folio->_nr_pages_mapped;
-	unsigned int nr_pmdmapped = 0, first;
-	int nr = 0;
+	int nr = 0, nr_pmdmapped = 0, first;
 
-	VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio);
-	VM_WARN_ON_FOLIO(compound && !folio_test_pmd_mappable(folio), folio);
+	VM_WARN_ON_FOLIO(folio_test_anon(folio), folio);
+	__folio_rmap_sanity_checks(folio, page, nr_pages, level);
 
-	/* Is page being mapped by PTE? Is this its first map to be added? */
-	if (likely(!compound)) {
+	switch (level) {
+	case RMAP_LEVEL_PTE:
 		do {
 			first = atomic_inc_and_test(&page->_mapcount);
 			if (first && folio_test_large(folio)) {
@@ -1413,9 +1400,8 @@ void folio_add_file_rmap_range(struct folio *folio, struct page *page,
 			if (first)
 				nr++;
 		} while (page++, --nr_pages > 0);
-	} else if (folio_test_pmd_mappable(folio)) {
-		/* That test is redundant: it's for safety or to optimize out */
-
+		break;
+	case RMAP_LEVEL_PMD:
 		first = atomic_inc_and_test(&folio->_entire_mapcount);
 		if (first) {
 			nr = atomic_add_return_relaxed(COMPOUND_MAPPED, mapped);
@@ -1430,6 +1416,7 @@ void folio_add_file_rmap_range(struct folio *folio, struct page *page,
 				nr = 0;
 			}
 		}
+		break;
 	}
 
 	if (nr_pmdmapped)
@@ -1443,6 +1430,43 @@ void folio_add_file_rmap_range(struct folio *folio, struct page *page,
 		mlock_vma_folio(folio, vma);
 }
 
+/**
+ * folio_add_file_rmap_ptes - add PTE mappings to a page range of a folio
+ * @folio:	The folio to add the mappings to
+ * @page:	The first page to add
+ * @nr_pages:	The number of pages that will be mapped using PTEs
+ * @vma:	The vm area in which the mappings are added
+ *
+ * The page range of the folio is defined by [page, page + nr_pages)
+ *
+ * The caller needs to hold the page table lock.
+ */
+void folio_add_file_rmap_ptes(struct folio *folio, struct page *page,
+		int nr_pages, struct vm_area_struct *vma)
+{
+	__folio_add_file_rmap(folio, page, nr_pages, vma, RMAP_LEVEL_PTE);
+}
+
+/**
+ * folio_add_file_rmap_pmd - add a PMD mapping to a page range of a folio
+ * @folio:	The folio to add the mapping to
+ * @page:	The first page to add
+ * @vma:	The vm area in which the mapping is added
+ *
+ * The page range of the folio is defined by [page, page + HPAGE_PMD_NR)
+ *
+ * The caller needs to hold the page table lock.
+ */
+void folio_add_file_rmap_pmd(struct folio *folio, struct page *page,
+		struct vm_area_struct *vma)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	__folio_add_file_rmap(folio, page, HPAGE_PMD_NR, vma, RMAP_LEVEL_PMD);
+#else
+	WARN_ON_ONCE(true);
+#endif
+}
+
 /**
  * page_add_file_rmap - add pte mapping to a file page
  * @page:	the page to add the mapping to
@@ -1455,16 +1479,13 @@ void page_add_file_rmap(struct page *page, struct vm_area_struct *vma,
 		bool compound)
 {
 	struct folio *folio = page_folio(page);
-	unsigned int nr_pages;
 
 	VM_WARN_ON_ONCE_PAGE(compound && !PageTransHuge(page), page);
 
 	if (likely(!compound))
-		nr_pages = 1;
+		folio_add_file_rmap_pte(folio, page, vma);
 	else
-		nr_pages = folio_nr_pages(folio);
-
-	folio_add_file_rmap_range(folio, page, nr_pages, vma, compound);
+		folio_add_file_rmap_pmd(folio, page, vma);
 }
 
 /**
-- 
cgit v1.2.3


From be6e57cfabe99a5d3b3869103c4ea0ed4a9692d4 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Wed, 20 Dec 2023 23:44:36 +0100
Subject: mm/rmap: remove page_add_file_rmap()

All users are gone, let's remove it.

Link: https://lkml.kernel.org/r/20231220224504.646757-13-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Yin Fengwei <fengwei.yin@intel.com>
Reviewed-by: Ryan Roberts <ryan.roberts@arm.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/rmap.h |  2 --
 mm/rmap.c            | 21 ---------------------
 2 files changed, 23 deletions(-)

(limited to 'include')

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 3d86a76b2836..6a4db6933e7d 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -237,8 +237,6 @@ void page_add_anon_rmap(struct page *, struct vm_area_struct *,
 		unsigned long address, rmap_t flags);
 void folio_add_new_anon_rmap(struct folio *, struct vm_area_struct *,
 		unsigned long address);
-void page_add_file_rmap(struct page *, struct vm_area_struct *,
-		bool compound);
 void folio_add_file_rmap_ptes(struct folio *, struct page *, int nr_pages,
 		struct vm_area_struct *);
 #define folio_add_file_rmap_pte(folio, page, vma) \
diff --git a/mm/rmap.c b/mm/rmap.c
index cc1fc2d570f0..5ab5ef10fbf5 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1467,27 +1467,6 @@ void folio_add_file_rmap_pmd(struct folio *folio, struct page *page,
 #endif
 }
 
-/**
- * page_add_file_rmap - add pte mapping to a file page
- * @page:	the page to add the mapping to
- * @vma:	the vm area in which the mapping is added
- * @compound:	charge the page as compound or small page
- *
- * The caller needs to hold the pte lock.
- */
-void page_add_file_rmap(struct page *page, struct vm_area_struct *vma,
-		bool compound)
-{
-	struct folio *folio = page_folio(page);
-
-	VM_WARN_ON_ONCE_PAGE(compound && !PageTransHuge(page), page);
-
-	if (likely(!compound))
-		folio_add_file_rmap_pte(folio, page, vma);
-	else
-		folio_add_file_rmap_pmd(folio, page, vma);
-}
-
 /**
  * page_remove_rmap - take down pte mapping from a page
  * @page:	page to remove mapping from
-- 
cgit v1.2.3


From 8bd5130070fbf2247a97c5361427a810522ac98a Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Wed, 20 Dec 2023 23:44:38 +0100
Subject: mm/rmap: introduce folio_add_anon_rmap_[pte|ptes|pmd]()

Let's mimic what we did with folio_add_file_rmap_*() so we can similarly
replace page_add_anon_rmap() next.

Make the compiler always special-case on the granularity by using
__always_inline.

For the PageAnonExclusive sanity checks, when adding a PMD mapping, we're
now also checking each individual subpage covered by that PMD, instead of
only the head page.

Note that the new functions ignore the RMAP_COMPOUND flag, which we will
remove as soon as page_add_anon_rmap() is gone.

Link: https://lkml.kernel.org/r/20231220224504.646757-15-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Yin Fengwei <fengwei.yin@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/rmap.h |   6 +++
 mm/rmap.c            | 120 +++++++++++++++++++++++++++++++++++----------------
 2 files changed, 88 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 6a4db6933e7d..b5da3d86200e 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -233,6 +233,12 @@ static inline void __folio_rmap_sanity_checks(struct folio *folio,
  * rmap interfaces called when adding or removing pte of page
  */
 void folio_move_anon_rmap(struct folio *, struct vm_area_struct *);
+void folio_add_anon_rmap_ptes(struct folio *, struct page *, int nr_pages,
+		struct vm_area_struct *, unsigned long address, rmap_t flags);
+#define folio_add_anon_rmap_pte(folio, page, vma, address, flags) \
+	folio_add_anon_rmap_ptes(folio, page, 1, vma, address, flags)
+void folio_add_anon_rmap_pmd(struct folio *, struct page *,
+		struct vm_area_struct *, unsigned long address, rmap_t flags);
 void page_add_anon_rmap(struct page *, struct vm_area_struct *,
 		unsigned long address, rmap_t flags);
 void folio_add_new_anon_rmap(struct folio *, struct vm_area_struct *,
diff --git a/mm/rmap.c b/mm/rmap.c
index 895a8534a935..7f380f5a34c9 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1299,40 +1299,20 @@ void page_add_anon_rmap(struct page *page, struct vm_area_struct *vma,
 		unsigned long address, rmap_t flags)
 {
 	struct folio *folio = page_folio(page);
-	atomic_t *mapped = &folio->_nr_pages_mapped;
-	int nr = 0, nr_pmdmapped = 0;
-	bool compound = flags & RMAP_COMPOUND;
-	bool first;
-
-	VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio);
 
-	/* Is page being mapped by PTE? Is this its first map to be added? */
-	if (likely(!compound)) {
-		first = atomic_inc_and_test(&page->_mapcount);
-		nr = first;
-		if (first && folio_test_large(folio)) {
-			nr = atomic_inc_return_relaxed(mapped);
-			nr = (nr < COMPOUND_MAPPED);
-		}
-	} else if (folio_test_pmd_mappable(folio)) {
-		/* That test is redundant: it's for safety or to optimize out */
+	if (likely(!(flags & RMAP_COMPOUND)))
+		folio_add_anon_rmap_pte(folio, page, vma, address, flags);
+	else
+		folio_add_anon_rmap_pmd(folio, page, vma, address, flags);
+}
 
-		first = atomic_inc_and_test(&folio->_entire_mapcount);
-		if (first) {
-			nr = atomic_add_return_relaxed(COMPOUND_MAPPED, mapped);
-			if (likely(nr < COMPOUND_MAPPED + COMPOUND_MAPPED)) {
-				nr_pmdmapped = folio_nr_pages(folio);
-				nr = nr_pmdmapped - (nr & FOLIO_PAGES_MAPPED);
-				/* Raced ahead of a remove and another add? */
-				if (unlikely(nr < 0))
-					nr = 0;
-			} else {
-				/* Raced ahead of a remove of COMPOUND_MAPPED */
-				nr = 0;
-			}
-		}
-	}
+static __always_inline void __folio_add_anon_rmap(struct folio *folio,
+		struct page *page, int nr_pages, struct vm_area_struct *vma,
+		unsigned long address, rmap_t flags, enum rmap_level level)
+{
+	int i, nr, nr_pmdmapped = 0;
 
+	nr = __folio_add_rmap(folio, page, nr_pages, level, &nr_pmdmapped);
 	if (nr_pmdmapped)
 		__lruvec_stat_mod_folio(folio, NR_ANON_THPS, nr_pmdmapped);
 	if (nr)
@@ -1346,18 +1326,34 @@ void page_add_anon_rmap(struct page *page, struct vm_area_struct *vma,
 		 * folio->index right when not given the address of the head
 		 * page.
 		 */
-		VM_WARN_ON_FOLIO(folio_test_large(folio) && !compound, folio);
+		VM_WARN_ON_FOLIO(folio_test_large(folio) &&
+				 level != RMAP_LEVEL_PMD, folio);
 		__folio_set_anon(folio, vma, address,
 				 !!(flags & RMAP_EXCLUSIVE));
 	} else if (likely(!folio_test_ksm(folio))) {
 		__page_check_anon_rmap(folio, page, vma, address);
 	}
-	if (flags & RMAP_EXCLUSIVE)
-		SetPageAnonExclusive(page);
-	/* While PTE-mapping a THP we have a PMD and a PTE mapping. */
-	VM_WARN_ON_FOLIO((atomic_read(&page->_mapcount) > 0 ||
-			  (folio_test_large(folio) && folio_entire_mapcount(folio) > 1)) &&
-			 PageAnonExclusive(page), folio);
+
+	if (flags & RMAP_EXCLUSIVE) {
+		switch (level) {
+		case RMAP_LEVEL_PTE:
+			for (i = 0; i < nr_pages; i++)
+				SetPageAnonExclusive(page + i);
+			break;
+		case RMAP_LEVEL_PMD:
+			SetPageAnonExclusive(page);
+			break;
+		}
+	}
+	for (i = 0; i < nr_pages; i++) {
+		struct page *cur_page = page + i;
+
+		/* While PTE-mapping a THP we have a PMD and a PTE mapping. */
+		VM_WARN_ON_FOLIO((atomic_read(&cur_page->_mapcount) > 0 ||
+				  (folio_test_large(folio) &&
+				   folio_entire_mapcount(folio) > 1)) &&
+				 PageAnonExclusive(cur_page), folio);
+	}
 
 	/*
 	 * For large folio, only mlock it if it's fully mapped to VMA. It's
@@ -1369,6 +1365,54 @@ void page_add_anon_rmap(struct page *page, struct vm_area_struct *vma,
 		mlock_vma_folio(folio, vma);
 }
 
+/**
+ * folio_add_anon_rmap_ptes - add PTE mappings to a page range of an anon folio
+ * @folio:	The folio to add the mappings to
+ * @page:	The first page to add
+ * @nr_pages:	The number of pages which will be mapped
+ * @vma:	The vm area in which the mappings are added
+ * @address:	The user virtual address of the first page to map
+ * @flags:	The rmap flags
+ *
+ * The page range of folio is defined by [first_page, first_page + nr_pages)
+ *
+ * The caller needs to hold the page table lock, and the page must be locked in
+ * the anon_vma case: to serialize mapping,index checking after setting,
+ * and to ensure that an anon folio is not being upgraded racily to a KSM folio
+ * (but KSM folios are never downgraded).
+ */
+void folio_add_anon_rmap_ptes(struct folio *folio, struct page *page,
+		int nr_pages, struct vm_area_struct *vma, unsigned long address,
+		rmap_t flags)
+{
+	__folio_add_anon_rmap(folio, page, nr_pages, vma, address, flags,
+			      RMAP_LEVEL_PTE);
+}
+
+/**
+ * folio_add_anon_rmap_pmd - add a PMD mapping to a page range of an anon folio
+ * @folio:	The folio to add the mapping to
+ * @page:	The first page to add
+ * @vma:	The vm area in which the mapping is added
+ * @address:	The user virtual address of the first page to map
+ * @flags:	The rmap flags
+ *
+ * The page range of folio is defined by [first_page, first_page + HPAGE_PMD_NR)
+ *
+ * The caller needs to hold the page table lock, and the page must be locked in
+ * the anon_vma case: to serialize mapping,index checking after setting.
+ */
+void folio_add_anon_rmap_pmd(struct folio *folio, struct page *page,
+		struct vm_area_struct *vma, unsigned long address, rmap_t flags)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	__folio_add_anon_rmap(folio, page, HPAGE_PMD_NR, vma, address, flags,
+			      RMAP_LEVEL_PMD);
+#else
+	WARN_ON_ONCE(true);
+#endif
+}
+
 /**
  * folio_add_new_anon_rmap - Add mapping to a new anonymous folio.
  * @folio:	The folio to add the mapping to.
-- 
cgit v1.2.3


From 84f0169e6c8a613012722e0d63302f9da4a72099 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Wed, 20 Dec 2023 23:44:45 +0100
Subject: mm/rmap: remove page_add_anon_rmap()

All users are gone, remove it and all traces.

Link: https://lkml.kernel.org/r/20231220224504.646757-22-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Yin Fengwei <fengwei.yin@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/rmap.h |  2 --
 mm/rmap.c            | 31 ++++---------------------------
 2 files changed, 4 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index b5da3d86200e..fe7b5a8b0e75 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -239,8 +239,6 @@ void folio_add_anon_rmap_ptes(struct folio *, struct page *, int nr_pages,
 	folio_add_anon_rmap_ptes(folio, page, 1, vma, address, flags)
 void folio_add_anon_rmap_pmd(struct folio *, struct page *,
 		struct vm_area_struct *, unsigned long address, rmap_t flags);
-void page_add_anon_rmap(struct page *, struct vm_area_struct *,
-		unsigned long address, rmap_t flags);
 void folio_add_new_anon_rmap(struct folio *, struct vm_area_struct *,
 		unsigned long address);
 void folio_add_file_rmap_ptes(struct folio *, struct page *, int nr_pages,
diff --git a/mm/rmap.c b/mm/rmap.c
index 7f380f5a34c9..87415bbf2402 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1270,7 +1270,7 @@ static void __page_check_anon_rmap(struct folio *folio, struct page *page,
 	 * The page's anon-rmap details (mapping and index) are guaranteed to
 	 * be set up correctly at this point.
 	 *
-	 * We have exclusion against page_add_anon_rmap because the caller
+	 * We have exclusion against folio_add_anon_rmap_*() because the caller
 	 * always holds the page locked.
 	 *
 	 * We have exclusion against folio_add_new_anon_rmap because those pages
@@ -1283,29 +1283,6 @@ static void __page_check_anon_rmap(struct folio *folio, struct page *page,
 		       page);
 }
 
-/**
- * page_add_anon_rmap - add pte mapping to an anonymous page
- * @page:	the page to add the mapping to
- * @vma:	the vm area in which the mapping is added
- * @address:	the user virtual address mapped
- * @flags:	the rmap flags
- *
- * The caller needs to hold the pte lock, and the page must be locked in
- * the anon_vma case: to serialize mapping,index checking after setting,
- * and to ensure that PageAnon is not being upgraded racily to PageKsm
- * (but PageKsm is never downgraded to PageAnon).
- */
-void page_add_anon_rmap(struct page *page, struct vm_area_struct *vma,
-		unsigned long address, rmap_t flags)
-{
-	struct folio *folio = page_folio(page);
-
-	if (likely(!(flags & RMAP_COMPOUND)))
-		folio_add_anon_rmap_pte(folio, page, vma, address, flags);
-	else
-		folio_add_anon_rmap_pmd(folio, page, vma, address, flags);
-}
-
 static __always_inline void __folio_add_anon_rmap(struct folio *folio,
 		struct page *page, int nr_pages, struct vm_area_struct *vma,
 		unsigned long address, rmap_t flags, enum rmap_level level)
@@ -1419,7 +1396,7 @@ void folio_add_anon_rmap_pmd(struct folio *folio, struct page *page,
  * @vma:	the vm area in which the mapping is added
  * @address:	the user virtual address mapped
  *
- * Like page_add_anon_rmap() but must only be called on *new* folios.
+ * Like folio_add_anon_rmap_*() but must only be called on *new* folios.
  * This means the inc-and-test can be bypassed.
  * The folio does not have to be locked.
  *
@@ -1479,7 +1456,7 @@ static __always_inline void __folio_add_file_rmap(struct folio *folio,
 	if (nr)
 		__lruvec_stat_mod_folio(folio, NR_FILE_MAPPED, nr);
 
-	/* See comments in page_add_anon_rmap() */
+	/* See comments in folio_add_anon_rmap_*() */
 	if (!folio_test_large(folio))
 		mlock_vma_folio(folio, vma);
 }
@@ -1593,7 +1570,7 @@ void page_remove_rmap(struct page *page, struct vm_area_struct *vma,
 
 	/*
 	 * It would be tidy to reset folio_test_anon mapping when fully
-	 * unmapped, but that might overwrite a racing page_add_anon_rmap
+	 * unmapped, but that might overwrite a racing folio_add_anon_rmap_*()
 	 * which increments mapcount after us but sets mapping before us:
 	 * so leave the reset to free_pages_prepare, and remember that
 	 * it's only reliable while mapped.
-- 
cgit v1.2.3


From 0cae959e3abf19ba62805f6e6a8b42b6cd9ed3e3 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Wed, 20 Dec 2023 23:44:46 +0100
Subject: mm/rmap: remove RMAP_COMPOUND

No longer used, let's remove it and clarify RMAP_NONE/RMAP_EXCLUSIVE a
bit.

Link: https://lkml.kernel.org/r/20231220224504.646757-23-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Yin Fengwei <fengwei.yin@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/rmap.h | 12 +++---------
 mm/rmap.c            |  2 --
 2 files changed, 3 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index fe7b5a8b0e75..bf6cb79aa7a0 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -177,20 +177,14 @@ struct anon_vma *folio_get_anon_vma(struct folio *folio);
 typedef int __bitwise rmap_t;
 
 /*
- * No special request: if the page is a subpage of a compound page, it is
- * mapped via a PTE. The mapped (sub)page is possibly shared between processes.
+ * No special request: A mapped anonymous (sub)page is possibly shared between
+ * processes.
  */
 #define RMAP_NONE		((__force rmap_t)0)
 
-/* The (sub)page is exclusive to a single process. */
+/* The anonymous (sub)page is exclusive to a single process. */
 #define RMAP_EXCLUSIVE		((__force rmap_t)BIT(0))
 
-/*
- * The compound page is not mapped via PTEs, but instead via a single PMD and
- * should be accounted accordingly.
- */
-#define RMAP_COMPOUND		((__force rmap_t)BIT(1))
-
 /*
  * Internally, we're using an enum to specify the granularity. We make the
  * compiler emit specialized code for each granularity.
diff --git a/mm/rmap.c b/mm/rmap.c
index 87415bbf2402..2b386b9f6791 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -2662,8 +2662,6 @@ void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc)
  * The following two functions are for anonymous (private mapped) hugepages.
  * Unlike common anonymous pages, anonymous hugepages have no accounting code
  * and no lru code, because we handle hugepages differently from common pages.
- *
- * RMAP_COMPOUND is ignored.
  */
 void hugetlb_add_anon_rmap(struct folio *folio, struct vm_area_struct *vma,
 		unsigned long address, rmap_t flags)
-- 
cgit v1.2.3


From b06dc281aa9901076898d4d0a7bde588f11bc204 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Wed, 20 Dec 2023 23:44:47 +0100
Subject: mm/rmap: introduce folio_remove_rmap_[pte|ptes|pmd]()

Let's mimic what we did with folio_add_file_rmap_*() and
folio_add_anon_rmap_*() so we can similarly replace page_remove_rmap()
next.

Make the compiler always special-case on the granularity by using
__always_inline.

We're adding folio_remove_rmap_ptes() handling right away, as we want to
use that soon for batching rmap operations when unmapping PTE-mapped large
folios.

Link: https://lkml.kernel.org/r/20231220224504.646757-24-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Yin Fengwei <fengwei.yin@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/rmap.h |  6 ++++
 mm/rmap.c            | 82 ++++++++++++++++++++++++++++++++++++++++++----------
 2 files changed, 72 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index bf6cb79aa7a0..57e045093f04 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -243,6 +243,12 @@ void folio_add_file_rmap_pmd(struct folio *, struct page *,
 		struct vm_area_struct *);
 void page_remove_rmap(struct page *, struct vm_area_struct *,
 		bool compound);
+void folio_remove_rmap_ptes(struct folio *, struct page *, int nr_pages,
+		struct vm_area_struct *);
+#define folio_remove_rmap_pte(folio, page, vma) \
+	folio_remove_rmap_ptes(folio, page, 1, vma)
+void folio_remove_rmap_pmd(struct folio *, struct page *,
+		struct vm_area_struct *);
 
 void hugetlb_add_anon_rmap(struct folio *, struct vm_area_struct *,
 		unsigned long address, rmap_t flags);
diff --git a/mm/rmap.c b/mm/rmap.c
index 2b386b9f6791..127318075395 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1510,25 +1510,37 @@ void page_remove_rmap(struct page *page, struct vm_area_struct *vma,
 		bool compound)
 {
 	struct folio *folio = page_folio(page);
+
+	if (likely(!compound))
+		folio_remove_rmap_pte(folio, page, vma);
+	else
+		folio_remove_rmap_pmd(folio, page, vma);
+}
+
+static __always_inline void __folio_remove_rmap(struct folio *folio,
+		struct page *page, int nr_pages, struct vm_area_struct *vma,
+		enum rmap_level level)
+{
 	atomic_t *mapped = &folio->_nr_pages_mapped;
-	int nr = 0, nr_pmdmapped = 0;
-	bool last;
+	int last, nr = 0, nr_pmdmapped = 0;
 	enum node_stat_item idx;
 
-	VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio);
-	VM_BUG_ON_PAGE(compound && !PageHead(page), page);
-
-	/* Is page being unmapped by PTE? Is this its last map to be removed? */
-	if (likely(!compound)) {
-		last = atomic_add_negative(-1, &page->_mapcount);
-		nr = last;
-		if (last && folio_test_large(folio)) {
-			nr = atomic_dec_return_relaxed(mapped);
-			nr = (nr < COMPOUND_MAPPED);
-		}
-	} else if (folio_test_pmd_mappable(folio)) {
-		/* That test is redundant: it's for safety or to optimize out */
+	__folio_rmap_sanity_checks(folio, page, nr_pages, level);
+
+	switch (level) {
+	case RMAP_LEVEL_PTE:
+		do {
+			last = atomic_add_negative(-1, &page->_mapcount);
+			if (last && folio_test_large(folio)) {
+				last = atomic_dec_return_relaxed(mapped);
+				last = (last < COMPOUND_MAPPED);
+			}
 
+			if (last)
+				nr++;
+		} while (page++, --nr_pages > 0);
+		break;
+	case RMAP_LEVEL_PMD:
 		last = atomic_add_negative(-1, &folio->_entire_mapcount);
 		if (last) {
 			nr = atomic_sub_return_relaxed(COMPOUND_MAPPED, mapped);
@@ -1543,6 +1555,7 @@ void page_remove_rmap(struct page *page, struct vm_area_struct *vma,
 				nr = 0;
 			}
 		}
+		break;
 	}
 
 	if (nr_pmdmapped) {
@@ -1564,7 +1577,7 @@ void page_remove_rmap(struct page *page, struct vm_area_struct *vma,
 		 * is still mapped.
 		 */
 		if (folio_test_large(folio) && folio_test_anon(folio))
-			if (!compound || nr < nr_pmdmapped)
+			if (level == RMAP_LEVEL_PTE || nr < nr_pmdmapped)
 				deferred_split_folio(folio);
 	}
 
@@ -1579,6 +1592,43 @@ void page_remove_rmap(struct page *page, struct vm_area_struct *vma,
 	munlock_vma_folio(folio, vma);
 }
 
+/**
+ * folio_remove_rmap_ptes - remove PTE mappings from a page range of a folio
+ * @folio:	The folio to remove the mappings from
+ * @page:	The first page to remove
+ * @nr_pages:	The number of pages that will be removed from the mapping
+ * @vma:	The vm area from which the mappings are removed
+ *
+ * The page range of the folio is defined by [page, page + nr_pages)
+ *
+ * The caller needs to hold the page table lock.
+ */
+void folio_remove_rmap_ptes(struct folio *folio, struct page *page,
+		int nr_pages, struct vm_area_struct *vma)
+{
+	__folio_remove_rmap(folio, page, nr_pages, vma, RMAP_LEVEL_PTE);
+}
+
+/**
+ * folio_remove_rmap_pmd - remove a PMD mapping from a page range of a folio
+ * @folio:	The folio to remove the mapping from
+ * @page:	The first page to remove
+ * @vma:	The vm area from which the mapping is removed
+ *
+ * The page range of the folio is defined by [page, page + HPAGE_PMD_NR)
+ *
+ * The caller needs to hold the page table lock.
+ */
+void folio_remove_rmap_pmd(struct folio *folio, struct page *page,
+		struct vm_area_struct *vma)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	__folio_remove_rmap(folio, page, HPAGE_PMD_NR, vma, RMAP_LEVEL_PMD);
+#else
+	WARN_ON_ONCE(true);
+#endif
+}
+
 /*
  * @arg: enum ttu_flags will be passed to this argument
  */
-- 
cgit v1.2.3


From 4d8f7418e8ba36036c8486d92d9591c368ab9b85 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Wed, 20 Dec 2023 23:44:56 +0100
Subject: mm/rmap: remove page_remove_rmap()

All callers are gone, let's remove it and some leftover traces.

Link: https://lkml.kernel.org/r/20231220224504.646757-33-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Yin Fengwei <fengwei.yin@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/rmap.h |  4 +---
 mm/filemap.c         | 10 +++++-----
 mm/internal.h        |  2 +-
 mm/memory-failure.c  |  4 ++--
 mm/rmap.c            | 23 ++---------------------
 5 files changed, 11 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 57e045093f04..fef369e37039 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -241,8 +241,6 @@ void folio_add_file_rmap_ptes(struct folio *, struct page *, int nr_pages,
 	folio_add_file_rmap_ptes(folio, page, 1, vma)
 void folio_add_file_rmap_pmd(struct folio *, struct page *,
 		struct vm_area_struct *);
-void page_remove_rmap(struct page *, struct vm_area_struct *,
-		bool compound);
 void folio_remove_rmap_ptes(struct folio *, struct page *, int nr_pages,
 		struct vm_area_struct *);
 #define folio_remove_rmap_pte(folio, page, vma) \
@@ -389,7 +387,7 @@ dup:
  *
  * This is similar to page_try_dup_anon_rmap(), however, not used during fork()
  * to duplicate a mapping, but instead to prepare for KSM or temporarily
- * unmapping a page (swap, migration) via page_remove_rmap().
+ * unmapping a page (swap, migration) via folio_remove_rmap_*().
  *
  * Marking the page shared can only fail if the page may be pinned; device
  * private pages cannot get pinned and consequently this function cannot fail.
diff --git a/mm/filemap.c b/mm/filemap.c
index 67ba56ecdd32..c8dafe70d4cc 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -113,11 +113,11 @@
  *    ->i_pages lock		(try_to_unmap_one)
  *    ->lruvec->lru_lock	(follow_page->mark_page_accessed)
  *    ->lruvec->lru_lock	(check_pte_range->isolate_lru_page)
- *    ->private_lock		(page_remove_rmap->set_page_dirty)
- *    ->i_pages lock		(page_remove_rmap->set_page_dirty)
- *    bdi.wb->list_lock		(page_remove_rmap->set_page_dirty)
- *    ->inode->i_lock		(page_remove_rmap->set_page_dirty)
- *    ->memcg->move_lock	(page_remove_rmap->folio_memcg_lock)
+ *    ->private_lock		(folio_remove_rmap_pte->set_page_dirty)
+ *    ->i_pages lock		(folio_remove_rmap_pte->set_page_dirty)
+ *    bdi.wb->list_lock		(folio_remove_rmap_pte->set_page_dirty)
+ *    ->inode->i_lock		(folio_remove_rmap_pte->set_page_dirty)
+ *    ->memcg->move_lock	(folio_remove_rmap_pte->folio_memcg_lock)
  *    bdi.wb->list_lock		(zap_pte_range->set_page_dirty)
  *    ->inode->i_lock		(zap_pte_range->set_page_dirty)
  *    ->private_lock		(zap_pte_range->block_dirty_folio)
diff --git a/mm/internal.h b/mm/internal.h
index 222e63b2dea4..a94355e70bd7 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -651,7 +651,7 @@ folio_within_vma(struct folio *folio, struct vm_area_struct *vma)
  * under page table lock for the pte/pmd being added or removed.
  *
  * mlock is usually called at the end of page_add_*_rmap(), munlock at
- * the end of page_remove_rmap(); but new anon folios are managed by
+ * the end of folio_remove_rmap_*(); but new anon folios are managed by
  * folio_add_lru_vma() calling mlock_new_folio().
  */
 void mlock_folio(struct folio *folio);
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 5a23da5eb8c1..a0d9b4ac7d54 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -2315,8 +2315,8 @@ try_again:
 	 * We use page flags to determine what action should be taken, but
 	 * the flags can be modified by the error containment action.  One
 	 * example is an mlocked page, where PG_mlocked is cleared by
-	 * page_remove_rmap() in try_to_unmap_one(). So to determine page status
-	 * correctly, we save a copy of the page flags at this time.
+	 * folio_remove_rmap_*() in try_to_unmap_one(). So to determine page
+	 * status correctly, we save a copy of the page flags at this time.
 	 */
 	page_flags = p->flags;
 
diff --git a/mm/rmap.c b/mm/rmap.c
index a3ec2be484cf..3ee254a99622 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -470,7 +470,7 @@ void __init anon_vma_init(void)
 /*
  * Getting a lock on a stable anon_vma from a page off the LRU is tricky!
  *
- * Since there is no serialization what so ever against page_remove_rmap()
+ * Since there is no serialization what so ever against folio_remove_rmap_*()
  * the best this function can do is return a refcount increased anon_vma
  * that might have been relevant to this page.
  *
@@ -487,7 +487,7 @@ void __init anon_vma_init(void)
  * [ something equivalent to page_mapped_in_vma() ].
  *
  * Since anon_vma's slab is SLAB_TYPESAFE_BY_RCU and we know from
- * page_remove_rmap() that the anon_vma pointer from page->mapping is valid
+ * folio_remove_rmap_*() that the anon_vma pointer from page->mapping is valid
  * if there is a mapcount, we can dereference the anon_vma after observing
  * those.
  *
@@ -1498,25 +1498,6 @@ void folio_add_file_rmap_pmd(struct folio *folio, struct page *page,
 #endif
 }
 
-/**
- * page_remove_rmap - take down pte mapping from a page
- * @page:	page to remove mapping from
- * @vma:	the vm area from which the mapping is removed
- * @compound:	uncharge the page as compound or small page
- *
- * The caller needs to hold the pte lock.
- */
-void page_remove_rmap(struct page *page, struct vm_area_struct *vma,
-		bool compound)
-{
-	struct folio *folio = page_folio(page);
-
-	if (likely(!compound))
-		folio_remove_rmap_pte(folio, page, vma);
-	else
-		folio_remove_rmap_pmd(folio, page, vma);
-}
-
 static __always_inline void __folio_remove_rmap(struct folio *folio,
 		struct page *page, int nr_pages, struct vm_area_struct *vma,
 		enum rmap_level level)
-- 
cgit v1.2.3


From d8ef5e311d7bfde54b60ab45026f206eff31b2d2 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Wed, 20 Dec 2023 23:44:57 +0100
Subject: mm/rmap: convert page_dup_file_rmap() to
 folio_dup_file_rmap_[pte|ptes|pmd]()

Let's convert page_dup_file_rmap() like the other rmap functions.  As
there is only a single caller, convert that single caller right away and
remove page_dup_file_rmap().

Add folio_dup_file_rmap_ptes() right away, we want to perform rmap baching
during fork() soon.

Link: https://lkml.kernel.org/r/20231220224504.646757-34-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Yin Fengwei <fengwei.yin@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/rmap.h | 59 +++++++++++++++++++++++++++++++++++++++++++++++-----
 mm/memory.c          |  2 +-
 2 files changed, 55 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index fef369e37039..7607f862e795 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -308,6 +308,60 @@ static inline void hugetlb_remove_rmap(struct folio *folio)
 	atomic_dec(&folio->_entire_mapcount);
 }
 
+static __always_inline void __folio_dup_file_rmap(struct folio *folio,
+		struct page *page, int nr_pages, enum rmap_level level)
+{
+	__folio_rmap_sanity_checks(folio, page, nr_pages, level);
+
+	switch (level) {
+	case RMAP_LEVEL_PTE:
+		do {
+			atomic_inc(&page->_mapcount);
+		} while (page++, --nr_pages > 0);
+		break;
+	case RMAP_LEVEL_PMD:
+		atomic_inc(&folio->_entire_mapcount);
+		break;
+	}
+}
+
+/**
+ * folio_dup_file_rmap_ptes - duplicate PTE mappings of a page range of a folio
+ * @folio:	The folio to duplicate the mappings of
+ * @page:	The first page to duplicate the mappings of
+ * @nr_pages:	The number of pages of which the mapping will be duplicated
+ *
+ * The page range of the folio is defined by [page, page + nr_pages)
+ *
+ * The caller needs to hold the page table lock.
+ */
+static inline void folio_dup_file_rmap_ptes(struct folio *folio,
+		struct page *page, int nr_pages)
+{
+	__folio_dup_file_rmap(folio, page, nr_pages, RMAP_LEVEL_PTE);
+}
+#define folio_dup_file_rmap_pte(folio, page) \
+	folio_dup_file_rmap_ptes(folio, page, 1)
+
+/**
+ * folio_dup_file_rmap_pmd - duplicate a PMD mapping of a page range of a folio
+ * @folio:	The folio to duplicate the mapping of
+ * @page:	The first page to duplicate the mapping of
+ *
+ * The page range of the folio is defined by [page, page + HPAGE_PMD_NR)
+ *
+ * The caller needs to hold the page table lock.
+ */
+static inline void folio_dup_file_rmap_pmd(struct folio *folio,
+		struct page *page)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	__folio_dup_file_rmap(folio, page, HPAGE_PMD_NR, RMAP_LEVEL_PTE);
+#else
+	WARN_ON_ONCE(true);
+#endif
+}
+
 static inline void __page_dup_rmap(struct page *page, bool compound)
 {
 	VM_WARN_ON(folio_test_hugetlb(page_folio(page)));
@@ -322,11 +376,6 @@ static inline void __page_dup_rmap(struct page *page, bool compound)
 	}
 }
 
-static inline void page_dup_file_rmap(struct page *page, bool compound)
-{
-	__page_dup_rmap(page, compound);
-}
-
 /**
  * page_try_dup_anon_rmap - try duplicating a mapping of an already mapped
  *			    anonymous page
diff --git a/mm/memory.c b/mm/memory.c
index e52c6e97444a..fdc87bf15545 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -965,7 +965,7 @@ copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
 		rss[MM_ANONPAGES]++;
 	} else if (page) {
 		folio_get(folio);
-		page_dup_file_rmap(page, false);
+		folio_dup_file_rmap_pte(folio, page);
 		rss[mm_counter_file(page)]++;
 	}
 
-- 
cgit v1.2.3


From 61d90309b7156d54c5d358cb5d8bf55b33d233d2 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Wed, 20 Dec 2023 23:44:58 +0100
Subject: mm/rmap: introduce folio_try_dup_anon_rmap_[pte|ptes|pmd]()

The last user of page_needs_cow_for_dma() and __page_dup_rmap() are gone,
remove them.

Add folio_try_dup_anon_rmap_ptes() right away, we want to perform rmap
baching during fork() soon.

Link: https://lkml.kernel.org/r/20231220224504.646757-35-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Yin Fengwei <fengwei.yin@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mm.h   |   6 ---
 include/linux/rmap.h | 150 ++++++++++++++++++++++++++++++++++++---------------
 2 files changed, 106 insertions(+), 50 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 75bba6102825..896c0079f64f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1975,12 +1975,6 @@ static inline bool folio_needs_cow_for_dma(struct vm_area_struct *vma,
 	return folio_maybe_dma_pinned(folio);
 }
 
-static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma,
-					  struct page *page)
-{
-	return folio_needs_cow_for_dma(vma, page_folio(page));
-}
-
 /**
  * is_zero_page - Query if a page is a zero page
  * @page: The page to query
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 7607f862e795..850aa74b6724 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -362,68 +362,130 @@ static inline void folio_dup_file_rmap_pmd(struct folio *folio,
 #endif
 }
 
-static inline void __page_dup_rmap(struct page *page, bool compound)
+static __always_inline int __folio_try_dup_anon_rmap(struct folio *folio,
+		struct page *page, int nr_pages, struct vm_area_struct *src_vma,
+		enum rmap_level level)
 {
-	VM_WARN_ON(folio_test_hugetlb(page_folio(page)));
+	bool maybe_pinned;
+	int i;
+
+	VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio);
+	__folio_rmap_sanity_checks(folio, page, nr_pages, level);
 
-	if (compound) {
-		struct folio *folio = (struct folio *)page;
+	/*
+	 * If this folio may have been pinned by the parent process,
+	 * don't allow to duplicate the mappings but instead require to e.g.,
+	 * copy the subpage immediately for the child so that we'll always
+	 * guarantee the pinned folio won't be randomly replaced in the
+	 * future on write faults.
+	 */
+	maybe_pinned = likely(!folio_is_device_private(folio)) &&
+		       unlikely(folio_needs_cow_for_dma(src_vma, folio));
 
-		VM_BUG_ON_PAGE(compound && !PageHead(page), page);
+	/*
+	 * No need to check+clear for already shared PTEs/PMDs of the
+	 * folio. But if any page is PageAnonExclusive, we must fallback to
+	 * copying if the folio maybe pinned.
+	 */
+	switch (level) {
+	case RMAP_LEVEL_PTE:
+		if (unlikely(maybe_pinned)) {
+			for (i = 0; i < nr_pages; i++)
+				if (PageAnonExclusive(page + i))
+					return -EBUSY;
+		}
+		do {
+			if (PageAnonExclusive(page))
+				ClearPageAnonExclusive(page);
+			atomic_inc(&page->_mapcount);
+		} while (page++, --nr_pages > 0);
+		break;
+	case RMAP_LEVEL_PMD:
+		if (PageAnonExclusive(page)) {
+			if (unlikely(maybe_pinned))
+				return -EBUSY;
+			ClearPageAnonExclusive(page);
+		}
 		atomic_inc(&folio->_entire_mapcount);
-	} else {
-		atomic_inc(&page->_mapcount);
+		break;
 	}
+	return 0;
 }
 
 /**
- * page_try_dup_anon_rmap - try duplicating a mapping of an already mapped
- *			    anonymous page
- * @page: the page to duplicate the mapping for
- * @compound: the page is mapped as compound or as a small page
- * @vma: the source vma
+ * folio_try_dup_anon_rmap_ptes - try duplicating PTE mappings of a page range
+ *				  of a folio
+ * @folio:	The folio to duplicate the mappings of
+ * @page:	The first page to duplicate the mappings of
+ * @nr_pages:	The number of pages of which the mapping will be duplicated
+ * @src_vma:	The vm area from which the mappings are duplicated
  *
- * The caller needs to hold the PT lock and the vma->vma_mm->write_protect_seq.
+ * The page range of the folio is defined by [page, page + nr_pages)
  *
- * Duplicating the mapping can only fail if the page may be pinned; device
- * private pages cannot get pinned and consequently this function cannot fail.
+ * The caller needs to hold the page table lock and the
+ * vma->vma_mm->write_protect_seq.
+ *
+ * Duplicating the mappings can only fail if the folio may be pinned; device
+ * private folios cannot get pinned and consequently this function cannot fail
+ * for them.
+ *
+ * If duplicating the mappings succeeded, the duplicated PTEs have to be R/O in
+ * the parent and the child. They must *not* be writable after this call
+ * succeeded.
+ *
+ * Returns 0 if duplicating the mappings succeeded. Returns -EBUSY otherwise.
+ */
+static inline int folio_try_dup_anon_rmap_ptes(struct folio *folio,
+		struct page *page, int nr_pages, struct vm_area_struct *src_vma)
+{
+	return __folio_try_dup_anon_rmap(folio, page, nr_pages, src_vma,
+					 RMAP_LEVEL_PTE);
+}
+#define folio_try_dup_anon_rmap_pte(folio, page, vma) \
+	folio_try_dup_anon_rmap_ptes(folio, page, 1, vma)
+
+/**
+ * folio_try_dup_anon_rmap_pmd - try duplicating a PMD mapping of a page range
+ *				 of a folio
+ * @folio:	The folio to duplicate the mapping of
+ * @page:	The first page to duplicate the mapping of
+ * @src_vma:	The vm area from which the mapping is duplicated
+ *
+ * The page range of the folio is defined by [page, page + HPAGE_PMD_NR)
  *
- * If duplicating the mapping succeeds, the page has to be mapped R/O into
- * the parent and the child. It must *not* get mapped writable after this call.
+ * The caller needs to hold the page table lock and the
+ * vma->vma_mm->write_protect_seq.
+ *
+ * Duplicating the mapping can only fail if the folio may be pinned; device
+ * private folios cannot get pinned and consequently this function cannot fail
+ * for them.
+ *
+ * If duplicating the mapping succeeds, the duplicated PMD has to be R/O in
+ * the parent and the child. They must *not* be writable after this call
+ * succeeded.
  *
  * Returns 0 if duplicating the mapping succeeded. Returns -EBUSY otherwise.
  */
+static inline int folio_try_dup_anon_rmap_pmd(struct folio *folio,
+		struct page *page, struct vm_area_struct *src_vma)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	return __folio_try_dup_anon_rmap(folio, page, HPAGE_PMD_NR, src_vma,
+					 RMAP_LEVEL_PMD);
+#else
+	WARN_ON_ONCE(true);
+	return -EBUSY;
+#endif
+}
+
 static inline int page_try_dup_anon_rmap(struct page *page, bool compound,
 					 struct vm_area_struct *vma)
 {
-	VM_BUG_ON_PAGE(!PageAnon(page), page);
-
-	/*
-	 * No need to check+clear for already shared pages, including KSM
-	 * pages.
-	 */
-	if (!PageAnonExclusive(page))
-		goto dup;
-
-	/*
-	 * If this page may have been pinned by the parent process,
-	 * don't allow to duplicate the mapping but instead require to e.g.,
-	 * copy the page immediately for the child so that we'll always
-	 * guarantee the pinned page won't be randomly replaced in the
-	 * future on write faults.
-	 */
-	if (likely(!is_device_private_page(page)) &&
-	    unlikely(page_needs_cow_for_dma(vma, page)))
-		return -EBUSY;
+	struct folio *folio = page_folio(page);
 
-	ClearPageAnonExclusive(page);
-	/*
-	 * It's okay to share the anon page between both processes, mapping
-	 * the page R/O into both processes.
-	 */
-dup:
-	__page_dup_rmap(page, compound);
-	return 0;
+	if (likely(!compound))
+		return folio_try_dup_anon_rmap_pte(folio, page, vma);
+	return folio_try_dup_anon_rmap_pmd(folio, page, vma);
 }
 
 /**
-- 
cgit v1.2.3


From a13d096471ec0ac5c6fc90fbcd57e8430024046a Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Wed, 20 Dec 2023 23:45:01 +0100
Subject: mm/rmap: remove page_try_dup_anon_rmap()

All users are gone, remove page_try_dup_anon_rmap() and any remaining
traces.

Link: https://lkml.kernel.org/r/20231220224504.646757-38-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Yin Fengwei <fengwei.yin@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/rmap.h | 16 +++-------------
 1 file changed, 3 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 850aa74b6724..0ad2ea2734e4 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -253,7 +253,7 @@ void hugetlb_add_anon_rmap(struct folio *, struct vm_area_struct *,
 void hugetlb_add_new_anon_rmap(struct folio *, struct vm_area_struct *,
 		unsigned long address);
 
-/* See page_try_dup_anon_rmap() */
+/* See folio_try_dup_anon_rmap_*() */
 static inline int hugetlb_try_dup_anon_rmap(struct folio *folio,
 		struct vm_area_struct *vma)
 {
@@ -478,16 +478,6 @@ static inline int folio_try_dup_anon_rmap_pmd(struct folio *folio,
 #endif
 }
 
-static inline int page_try_dup_anon_rmap(struct page *page, bool compound,
-					 struct vm_area_struct *vma)
-{
-	struct folio *folio = page_folio(page);
-
-	if (likely(!compound))
-		return folio_try_dup_anon_rmap_pte(folio, page, vma);
-	return folio_try_dup_anon_rmap_pmd(folio, page, vma);
-}
-
 /**
  * page_try_share_anon_rmap - try marking an exclusive anonymous page possibly
  *			      shared to prepare for KSM or temporary unmapping
@@ -496,8 +486,8 @@ static inline int page_try_dup_anon_rmap(struct page *page, bool compound,
  * The caller needs to hold the PT lock and has to have the page table entry
  * cleared/invalidated.
  *
- * This is similar to page_try_dup_anon_rmap(), however, not used during fork()
- * to duplicate a mapping, but instead to prepare for KSM or temporarily
+ * This is similar to folio_try_dup_anon_rmap_*(), however, not used during
+ * fork() to duplicate a mapping, but instead to prepare for KSM or temporarily
  * unmapping a page (swap, migration) via folio_remove_rmap_*().
  *
  * Marking the page shared can only fail if the page may be pinned; device
-- 
cgit v1.2.3


From e3b4b1374f87c71e9309efc6149f113cdd17af72 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Wed, 20 Dec 2023 23:45:02 +0100
Subject: mm: convert page_try_share_anon_rmap() to
 folio_try_share_anon_rmap_[pte|pmd]()

Let's convert it like we converted all the other rmap functions.  Don't
introduce folio_try_share_anon_rmap_ptes() for now, as we don't have a
user that wants rmap batching in sight.  Pretty easy to add later.

All users are easy to convert -- only ksm.c doesn't use folios yet but
that is left for future work -- so let's just do it in a single shot.

While at it, turn the BUG_ON into a WARN_ON_ONCE.

Note that page_try_share_anon_rmap() so far didn't care about pte/pmd
mappings (no compound parameter).  We're changing that so we can perform
better sanity checks and make the code actually more readable/consistent.
For example, __folio_rmap_sanity_checks() will make sure that a PMD range
actually falls completely into the folio.

Link: https://lkml.kernel.org/r/20231220224504.646757-39-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Yin Fengwei <fengwei.yin@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/rmap.h | 96 ++++++++++++++++++++++++++++++++++++++--------------
 mm/gup.c             |  2 +-
 mm/huge_memory.c     |  9 ++---
 mm/internal.h        |  4 +--
 mm/ksm.c             |  5 +--
 mm/migrate_device.c  |  2 +-
 mm/rmap.c            | 11 +++---
 7 files changed, 89 insertions(+), 40 deletions(-)

(limited to 'include')

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 0ad2ea2734e4..fd6fe16fa358 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -269,7 +269,7 @@ static inline int hugetlb_try_dup_anon_rmap(struct folio *folio,
 	return 0;
 }
 
-/* See page_try_share_anon_rmap() */
+/* See folio_try_share_anon_rmap_*() */
 static inline int hugetlb_try_share_anon_rmap(struct folio *folio)
 {
 	VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio);
@@ -478,31 +478,15 @@ static inline int folio_try_dup_anon_rmap_pmd(struct folio *folio,
 #endif
 }
 
-/**
- * page_try_share_anon_rmap - try marking an exclusive anonymous page possibly
- *			      shared to prepare for KSM or temporary unmapping
- * @page: the exclusive anonymous page to try marking possibly shared
- *
- * The caller needs to hold the PT lock and has to have the page table entry
- * cleared/invalidated.
- *
- * This is similar to folio_try_dup_anon_rmap_*(), however, not used during
- * fork() to duplicate a mapping, but instead to prepare for KSM or temporarily
- * unmapping a page (swap, migration) via folio_remove_rmap_*().
- *
- * Marking the page shared can only fail if the page may be pinned; device
- * private pages cannot get pinned and consequently this function cannot fail.
- *
- * Returns 0 if marking the page possibly shared succeeded. Returns -EBUSY
- * otherwise.
- */
-static inline int page_try_share_anon_rmap(struct page *page)
+static __always_inline int __folio_try_share_anon_rmap(struct folio *folio,
+		struct page *page, int nr_pages, enum rmap_level level)
 {
-	VM_WARN_ON(folio_test_hugetlb(page_folio(page)));
-	VM_BUG_ON_PAGE(!PageAnon(page) || !PageAnonExclusive(page), page);
+	VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio);
+	VM_WARN_ON_FOLIO(!PageAnonExclusive(page), folio);
+	__folio_rmap_sanity_checks(folio, page, nr_pages, level);
 
-	/* device private pages cannot get pinned via GUP. */
-	if (unlikely(is_device_private_page(page))) {
+	/* device private folios cannot get pinned via GUP. */
+	if (unlikely(folio_is_device_private(folio))) {
 		ClearPageAnonExclusive(page);
 		return 0;
 	}
@@ -553,7 +537,7 @@ static inline int page_try_share_anon_rmap(struct page *page)
 	if (IS_ENABLED(CONFIG_HAVE_FAST_GUP))
 		smp_mb();
 
-	if (unlikely(page_maybe_dma_pinned(page)))
+	if (unlikely(folio_maybe_dma_pinned(folio)))
 		return -EBUSY;
 	ClearPageAnonExclusive(page);
 
@@ -566,6 +550,68 @@ static inline int page_try_share_anon_rmap(struct page *page)
 	return 0;
 }
 
+/**
+ * folio_try_share_anon_rmap_pte - try marking an exclusive anonymous page
+ *				   mapped by a PTE possibly shared to prepare
+ *				   for KSM or temporary unmapping
+ * @folio:	The folio to share a mapping of
+ * @page:	The mapped exclusive page
+ *
+ * The caller needs to hold the page table lock and has to have the page table
+ * entries cleared/invalidated.
+ *
+ * This is similar to folio_try_dup_anon_rmap_pte(), however, not used during
+ * fork() to duplicate mappings, but instead to prepare for KSM or temporarily
+ * unmapping parts of a folio (swap, migration) via folio_remove_rmap_pte().
+ *
+ * Marking the mapped page shared can only fail if the folio maybe pinned;
+ * device private folios cannot get pinned and consequently this function cannot
+ * fail.
+ *
+ * Returns 0 if marking the mapped page possibly shared succeeded. Returns
+ * -EBUSY otherwise.
+ */
+static inline int folio_try_share_anon_rmap_pte(struct folio *folio,
+		struct page *page)
+{
+	return __folio_try_share_anon_rmap(folio, page, 1, RMAP_LEVEL_PTE);
+}
+
+/**
+ * folio_try_share_anon_rmap_pmd - try marking an exclusive anonymous page
+ *				   range mapped by a PMD possibly shared to
+ *				   prepare for temporary unmapping
+ * @folio:	The folio to share the mapping of
+ * @page:	The first page to share the mapping of
+ *
+ * The page range of the folio is defined by [page, page + HPAGE_PMD_NR)
+ *
+ * The caller needs to hold the page table lock and has to have the page table
+ * entries cleared/invalidated.
+ *
+ * This is similar to folio_try_dup_anon_rmap_pmd(), however, not used during
+ * fork() to duplicate a mapping, but instead to prepare for temporarily
+ * unmapping parts of a folio (swap, migration) via folio_remove_rmap_pmd().
+ *
+ * Marking the mapped pages shared can only fail if the folio maybe pinned;
+ * device private folios cannot get pinned and consequently this function cannot
+ * fail.
+ *
+ * Returns 0 if marking the mapped pages possibly shared succeeded. Returns
+ * -EBUSY otherwise.
+ */
+static inline int folio_try_share_anon_rmap_pmd(struct folio *folio,
+		struct page *page)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	return __folio_try_share_anon_rmap(folio, page, HPAGE_PMD_NR,
+					   RMAP_LEVEL_PMD);
+#else
+	WARN_ON_ONCE(true);
+	return -EBUSY;
+#endif
+}
+
 /*
  * Called from mm/vmscan.c to handle paging out
  */
diff --git a/mm/gup.c b/mm/gup.c
index 0a5f0e91bfec..df83182ec72d 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -177,7 +177,7 @@ struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags)
 	/*
 	 * Adjust the pincount before re-checking the PTE for changes.
 	 * This is essentially a smp_mb() and is paired with a memory
-	 * barrier in page_try_share_anon_rmap().
+	 * barrier in folio_try_share_anon_rmap_*().
 	 */
 	smp_mb__after_atomic();
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index de623b942b6e..1a588e29d287 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2523,10 +2523,11 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		 * In case we cannot clear PageAnonExclusive(), split the PMD
 		 * only and let try_to_migrate_one() fail later.
 		 *
-		 * See page_try_share_anon_rmap(): invalidate PMD first.
+		 * See folio_try_share_anon_rmap_pmd(): invalidate PMD first.
 		 */
 		anon_exclusive = PageAnonExclusive(page);
-		if (freeze && anon_exclusive && page_try_share_anon_rmap(page))
+		if (freeze && anon_exclusive &&
+		    folio_try_share_anon_rmap_pmd(folio, page))
 			freeze = false;
 		if (!freeze) {
 			rmap_t rmap_flags = RMAP_NONE;
@@ -3554,9 +3555,9 @@ int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
 	flush_cache_range(vma, address, address + HPAGE_PMD_SIZE);
 	pmdval = pmdp_invalidate(vma, address, pvmw->pmd);
 
-	/* See page_try_share_anon_rmap(): invalidate PMD first. */
+	/* See folio_try_share_anon_rmap_pmd(): invalidate PMD first. */
 	anon_exclusive = folio_test_anon(folio) && PageAnonExclusive(page);
-	if (anon_exclusive && page_try_share_anon_rmap(page)) {
+	if (anon_exclusive && folio_try_share_anon_rmap_pmd(folio, page)) {
 		set_pmd_at(mm, address, pvmw->pmd, pmdval);
 		return -EBUSY;
 	}
diff --git a/mm/internal.h b/mm/internal.h
index a94355e70bd7..29589bc3f046 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1047,7 +1047,7 @@ enum {
  * * Ordinary GUP: Using the PT lock
  * * GUP-fast and fork(): mm->write_protect_seq
  * * GUP-fast and KSM or temporary unmapping (swap, migration): see
- *    page_try_share_anon_rmap()
+ *    folio_try_share_anon_rmap_*()
  *
  * Must be called with the (sub)page that's actually referenced via the
  * page table entry, which might not necessarily be the head page for a
@@ -1090,7 +1090,7 @@ static inline bool gup_must_unshare(struct vm_area_struct *vma,
 		return is_cow_mapping(vma->vm_flags);
 	}
 
-	/* Paired with a memory barrier in page_try_share_anon_rmap(). */
+	/* Paired with a memory barrier in folio_try_share_anon_rmap_*(). */
 	if (IS_ENABLED(CONFIG_HAVE_FAST_GUP))
 		smp_rmb();
 
diff --git a/mm/ksm.c b/mm/ksm.c
index 716e2f87dd79..8c001819cf10 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -1331,8 +1331,9 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page,
 			goto out_unlock;
 		}
 
-		/* See page_try_share_anon_rmap(): clear PTE first. */
-		if (anon_exclusive && page_try_share_anon_rmap(page)) {
+		/* See folio_try_share_anon_rmap_pte(): clear PTE first. */
+		if (anon_exclusive &&
+		    folio_try_share_anon_rmap_pte(page_folio(page), page)) {
 			set_pte_at(mm, pvmw.address, pvmw.pte, entry);
 			goto out_unlock;
 		}
diff --git a/mm/migrate_device.c b/mm/migrate_device.c
index 39b7754480c6..b6c27c76e1a0 100644
--- a/mm/migrate_device.c
+++ b/mm/migrate_device.c
@@ -202,7 +202,7 @@ again:
 			if (anon_exclusive) {
 				pte = ptep_clear_flush(vma, addr, ptep);
 
-				if (page_try_share_anon_rmap(page)) {
+				if (folio_try_share_anon_rmap_pte(folio, page)) {
 					set_pte_at(mm, addr, ptep, pte);
 					folio_unlock(folio);
 					folio_put(folio);
diff --git a/mm/rmap.c b/mm/rmap.c
index 3ee254a99622..6209e65985a2 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1866,9 +1866,9 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 				break;
 			}
 
-			/* See page_try_share_anon_rmap(): clear PTE first. */
+			/* See folio_try_share_anon_rmap(): clear PTE first. */
 			if (anon_exclusive &&
-			    page_try_share_anon_rmap(subpage)) {
+			    folio_try_share_anon_rmap_pte(folio, subpage)) {
 				swap_free(entry);
 				set_pte_at(mm, address, pvmw.pte, pteval);
 				ret = false;
@@ -2142,7 +2142,8 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 			pte_t swp_pte;
 
 			if (anon_exclusive)
-				BUG_ON(page_try_share_anon_rmap(subpage));
+				WARN_ON_ONCE(folio_try_share_anon_rmap_pte(folio,
+									   subpage));
 
 			/*
 			 * Store the pfn of the page in a special migration
@@ -2213,7 +2214,7 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 			VM_BUG_ON_PAGE(pte_write(pteval) && folio_test_anon(folio) &&
 				       !anon_exclusive, subpage);
 
-			/* See page_try_share_anon_rmap(): clear PTE first. */
+			/* See folio_try_share_anon_rmap_pte(): clear PTE first. */
 			if (folio_test_hugetlb(folio)) {
 				if (anon_exclusive &&
 				    hugetlb_try_share_anon_rmap(folio)) {
@@ -2224,7 +2225,7 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 					break;
 				}
 			} else if (anon_exclusive &&
-				   page_try_share_anon_rmap(subpage)) {
+				   folio_try_share_anon_rmap_pte(folio, subpage)) {
 				set_pte_at(mm, address, pvmw.pte, pteval);
 				ret = false;
 				page_vma_mapped_walk_done(&pvmw);
-- 
cgit v1.2.3


From 90ca22513ed5d7cf546c7c8d35a03ec2a2f5c87e Mon Sep 17 00:00:00 2001
From: Mathis Marion <mathis.marion@silabs.com>
Date: Tue, 19 Dec 2023 14:11:54 +0100
Subject: lib: crc_ccitt_false() is identical to crc_itu_t()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

crc_ccitt_false() was introduced in commit 0d85adb5fbd33 ("lib/crc-ccitt:
Add CCITT-FALSE CRC16 variant"), but it is redundant with crc_itu_t().
Since the latter is more used, it is the one being kept.

Link: https://lkml.kernel.org/r/20231219131154.748577-1-Mathis.Marion@silabs.com
Signed-off-by: Mathis Marion <mathis.marion@silabs.com>
Cc: Andrey Smirnov <andrew.smirnov@gmail.com>
Cc: Andrey Vostrikov <andrey.vostrikov@cogentembedded.com>
Cc: Jérôme Pouiller <jerome.pouiller@silabs.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 .../driver-api/surface_aggregator/ssh.rst          |  2 +-
 drivers/mfd/Kconfig                                |  2 +-
 drivers/mfd/rave-sp.c                              |  4 +-
 drivers/platform/surface/aggregator/Kconfig        |  2 +-
 include/linux/crc-ccitt.h                          |  7 ---
 include/linux/surface_aggregator/serial_hub.h      |  4 +-
 lib/crc-ccitt.c                                    | 55 ----------------------
 7 files changed, 7 insertions(+), 69 deletions(-)

(limited to 'include')

diff --git a/Documentation/driver-api/surface_aggregator/ssh.rst b/Documentation/driver-api/surface_aggregator/ssh.rst
index b955b673838b..58a757319931 100644
--- a/Documentation/driver-api/surface_aggregator/ssh.rst
+++ b/Documentation/driver-api/surface_aggregator/ssh.rst
@@ -39,7 +39,7 @@ Note that the standard disclaimer for this subsystem also applies to this
 document: All of this has been reverse-engineered and may thus be erroneous
 and/or incomplete.
 
-All CRCs used in the following are two-byte ``crc_ccitt_false(0xffff, ...)``.
+All CRCs used in the following are two-byte ``crc_itu_t(0xffff, ...)``.
 All multi-byte values are little-endian, there is no implicit padding between
 values.
 
diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index 90ce58fd629e..925c19ee513b 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -2255,7 +2255,7 @@ config MFD_VEXPRESS_SYSREG
 config RAVE_SP_CORE
 	tristate "RAVE SP MCU core driver"
 	depends on SERIAL_DEV_BUS
-	select CRC_CCITT
+	select CRC_ITU_T
 	help
 	  Select this to get support for the Supervisory Processor
 	  device found on several devices in RAVE line of hardware.
diff --git a/drivers/mfd/rave-sp.c b/drivers/mfd/rave-sp.c
index da50eba10014..f62422740de2 100644
--- a/drivers/mfd/rave-sp.c
+++ b/drivers/mfd/rave-sp.c
@@ -9,7 +9,7 @@
  */
 
 #include <linux/atomic.h>
-#include <linux/crc-ccitt.h>
+#include <linux/crc-itu-t.h>
 #include <linux/delay.h>
 #include <linux/export.h>
 #include <linux/init.h>
@@ -251,7 +251,7 @@ static void csum_8b2c(const u8 *buf, size_t size, u8 *crc)
 
 static void csum_ccitt(const u8 *buf, size_t size, u8 *crc)
 {
-	const u16 calculated = crc_ccitt_false(0xffff, buf, size);
+	const u16 calculated = crc_itu_t(0xffff, buf, size);
 
 	/*
 	 * While the rest of the wire protocol is little-endian,
diff --git a/drivers/platform/surface/aggregator/Kconfig b/drivers/platform/surface/aggregator/Kconfig
index 88afc38ffdc5..957c216c180c 100644
--- a/drivers/platform/surface/aggregator/Kconfig
+++ b/drivers/platform/surface/aggregator/Kconfig
@@ -5,7 +5,7 @@ menuconfig SURFACE_AGGREGATOR
 	tristate "Microsoft Surface System Aggregator Module Subsystem and Drivers"
 	depends on SERIAL_DEV_BUS
 	depends on ACPI && !RISCV
-	select CRC_CCITT
+	select CRC_ITU_T
 	help
 	  The Surface System Aggregator Module (Surface SAM or SSAM) is an
 	  embedded controller (EC) found on 5th- and later-generation Microsoft
diff --git a/include/linux/crc-ccitt.h b/include/linux/crc-ccitt.h
index 72c92c396bb8..cd4f420231ba 100644
--- a/include/linux/crc-ccitt.h
+++ b/include/linux/crc-ccitt.h
@@ -5,19 +5,12 @@
 #include <linux/types.h>
 
 extern u16 const crc_ccitt_table[256];
-extern u16 const crc_ccitt_false_table[256];
 
 extern u16 crc_ccitt(u16 crc, const u8 *buffer, size_t len);
-extern u16 crc_ccitt_false(u16 crc, const u8 *buffer, size_t len);
 
 static inline u16 crc_ccitt_byte(u16 crc, const u8 c)
 {
 	return (crc >> 8) ^ crc_ccitt_table[(crc ^ c) & 0xff];
 }
 
-static inline u16 crc_ccitt_false_byte(u16 crc, const u8 c)
-{
-    return (crc << 8) ^ crc_ccitt_false_table[(crc >> 8) ^ c];
-}
-
 #endif /* _LINUX_CRC_CCITT_H */
diff --git a/include/linux/surface_aggregator/serial_hub.h b/include/linux/surface_aggregator/serial_hub.h
index 5c4ae1a26183..d8dbef6b7fc2 100644
--- a/include/linux/surface_aggregator/serial_hub.h
+++ b/include/linux/surface_aggregator/serial_hub.h
@@ -12,7 +12,7 @@
 #ifndef _LINUX_SURFACE_AGGREGATOR_SERIAL_HUB_H
 #define _LINUX_SURFACE_AGGREGATOR_SERIAL_HUB_H
 
-#include <linux/crc-ccitt.h>
+#include <linux/crc-itu-t.h>
 #include <linux/kref.h>
 #include <linux/ktime.h>
 #include <linux/list.h>
@@ -188,7 +188,7 @@ static_assert(sizeof(struct ssh_command) == 8);
  */
 static inline u16 ssh_crc(const u8 *buf, size_t len)
 {
-	return crc_ccitt_false(0xffff, buf, len);
+	return crc_itu_t(0xffff, buf, len);
 }
 
 /*
diff --git a/lib/crc-ccitt.c b/lib/crc-ccitt.c
index d1a7d29d2ac9..9cddf35d3b66 100644
--- a/lib/crc-ccitt.c
+++ b/lib/crc-ccitt.c
@@ -49,46 +49,6 @@ u16 const crc_ccitt_table[256] = {
 };
 EXPORT_SYMBOL(crc_ccitt_table);
 
-/*
- * Similar table to calculate CRC16 variant known as CRC-CCITT-FALSE
- * Reflected bits order, does not augment final value.
- */
-u16 const crc_ccitt_false_table[256] = {
-    0x0000, 0x1021, 0x2042, 0x3063, 0x4084, 0x50A5, 0x60C6, 0x70E7,
-    0x8108, 0x9129, 0xA14A, 0xB16B, 0xC18C, 0xD1AD, 0xE1CE, 0xF1EF,
-    0x1231, 0x0210, 0x3273, 0x2252, 0x52B5, 0x4294, 0x72F7, 0x62D6,
-    0x9339, 0x8318, 0xB37B, 0xA35A, 0xD3BD, 0xC39C, 0xF3FF, 0xE3DE,
-    0x2462, 0x3443, 0x0420, 0x1401, 0x64E6, 0x74C7, 0x44A4, 0x5485,
-    0xA56A, 0xB54B, 0x8528, 0x9509, 0xE5EE, 0xF5CF, 0xC5AC, 0xD58D,
-    0x3653, 0x2672, 0x1611, 0x0630, 0x76D7, 0x66F6, 0x5695, 0x46B4,
-    0xB75B, 0xA77A, 0x9719, 0x8738, 0xF7DF, 0xE7FE, 0xD79D, 0xC7BC,
-    0x48C4, 0x58E5, 0x6886, 0x78A7, 0x0840, 0x1861, 0x2802, 0x3823,
-    0xC9CC, 0xD9ED, 0xE98E, 0xF9AF, 0x8948, 0x9969, 0xA90A, 0xB92B,
-    0x5AF5, 0x4AD4, 0x7AB7, 0x6A96, 0x1A71, 0x0A50, 0x3A33, 0x2A12,
-    0xDBFD, 0xCBDC, 0xFBBF, 0xEB9E, 0x9B79, 0x8B58, 0xBB3B, 0xAB1A,
-    0x6CA6, 0x7C87, 0x4CE4, 0x5CC5, 0x2C22, 0x3C03, 0x0C60, 0x1C41,
-    0xEDAE, 0xFD8F, 0xCDEC, 0xDDCD, 0xAD2A, 0xBD0B, 0x8D68, 0x9D49,
-    0x7E97, 0x6EB6, 0x5ED5, 0x4EF4, 0x3E13, 0x2E32, 0x1E51, 0x0E70,
-    0xFF9F, 0xEFBE, 0xDFDD, 0xCFFC, 0xBF1B, 0xAF3A, 0x9F59, 0x8F78,
-    0x9188, 0x81A9, 0xB1CA, 0xA1EB, 0xD10C, 0xC12D, 0xF14E, 0xE16F,
-    0x1080, 0x00A1, 0x30C2, 0x20E3, 0x5004, 0x4025, 0x7046, 0x6067,
-    0x83B9, 0x9398, 0xA3FB, 0xB3DA, 0xC33D, 0xD31C, 0xE37F, 0xF35E,
-    0x02B1, 0x1290, 0x22F3, 0x32D2, 0x4235, 0x5214, 0x6277, 0x7256,
-    0xB5EA, 0xA5CB, 0x95A8, 0x8589, 0xF56E, 0xE54F, 0xD52C, 0xC50D,
-    0x34E2, 0x24C3, 0x14A0, 0x0481, 0x7466, 0x6447, 0x5424, 0x4405,
-    0xA7DB, 0xB7FA, 0x8799, 0x97B8, 0xE75F, 0xF77E, 0xC71D, 0xD73C,
-    0x26D3, 0x36F2, 0x0691, 0x16B0, 0x6657, 0x7676, 0x4615, 0x5634,
-    0xD94C, 0xC96D, 0xF90E, 0xE92F, 0x99C8, 0x89E9, 0xB98A, 0xA9AB,
-    0x5844, 0x4865, 0x7806, 0x6827, 0x18C0, 0x08E1, 0x3882, 0x28A3,
-    0xCB7D, 0xDB5C, 0xEB3F, 0xFB1E, 0x8BF9, 0x9BD8, 0xABBB, 0xBB9A,
-    0x4A75, 0x5A54, 0x6A37, 0x7A16, 0x0AF1, 0x1AD0, 0x2AB3, 0x3A92,
-    0xFD2E, 0xED0F, 0xDD6C, 0xCD4D, 0xBDAA, 0xAD8B, 0x9DE8, 0x8DC9,
-    0x7C26, 0x6C07, 0x5C64, 0x4C45, 0x3CA2, 0x2C83, 0x1CE0, 0x0CC1,
-    0xEF1F, 0xFF3E, 0xCF5D, 0xDF7C, 0xAF9B, 0xBFBA, 0x8FD9, 0x9FF8,
-    0x6E17, 0x7E36, 0x4E55, 0x5E74, 0x2E93, 0x3EB2, 0x0ED1, 0x1EF0
-};
-EXPORT_SYMBOL(crc_ccitt_false_table);
-
 /**
  *	crc_ccitt - recompute the CRC (CRC-CCITT variant) for the data
  *	buffer
@@ -104,20 +64,5 @@ u16 crc_ccitt(u16 crc, u8 const *buffer, size_t len)
 }
 EXPORT_SYMBOL(crc_ccitt);
 
-/**
- *	crc_ccitt_false - recompute the CRC (CRC-CCITT-FALSE variant)
- *	for the data buffer
- *	@crc: previous CRC value
- *	@buffer: data pointer
- *	@len: number of bytes in the buffer
- */
-u16 crc_ccitt_false(u16 crc, u8 const *buffer, size_t len)
-{
-	while (len--)
-		crc = crc_ccitt_false_byte(crc, *buffer++);
-	return crc;
-}
-EXPORT_SYMBOL(crc_ccitt_false);
-
 MODULE_DESCRIPTION("CRC-CCITT calculations");
 MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From 29166371ef6780429e4cb84f1827fafbdd4005ab Mon Sep 17 00:00:00 2001
From: Youling Tang <tangyouling@kylinos.cn>
Date: Wed, 27 Dec 2023 07:46:25 +0800
Subject: kdump: remove redundant DEFAULT_CRASH_KERNEL_LOW_SIZE

Remove duplicate definitions, no functional changes.

Link: https://lkml.kernel.org/r/MW4PR84MB3145459ADC7EB38BBB36955B8198A@MW4PR84MB3145.NAMPRD84.PROD.OUTLOOK.COM
Signed-off-by: Youling Tang <tangyouling@kylinos.cn>
Reported-by: Huacai Chen <chenhuacai@loongson.cn>
Acked-by: Baoquan He <bhe@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/crash_core.h | 6 ------
 1 file changed, 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h
index 5126a4fecb44..9eaeaafe0cad 100644
--- a/include/linux/crash_core.h
+++ b/include/linux/crash_core.h
@@ -87,12 +87,6 @@ Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type,
 			  void *data, size_t data_len);
 void final_note(Elf_Word *buf);
 
-#ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION
-#ifndef DEFAULT_CRASH_KERNEL_LOW_SIZE
-#define DEFAULT_CRASH_KERNEL_LOW_SIZE  (128UL << 20)
-#endif
-#endif
-
 int __init parse_crashkernel(char *cmdline, unsigned long long system_ram,
 		unsigned long long *crash_size, unsigned long long *crash_base,
 		unsigned long long *low_size, bool *high);
-- 
cgit v1.2.3


From 501a06fe8e4c185bbda371b8cedbdf1b23a633d8 Mon Sep 17 00:00:00 2001
From: Nhat Pham <nphamcs@gmail.com>
Date: Thu, 7 Dec 2023 11:24:06 -0800
Subject: zswap: memcontrol: implement zswap writeback disabling

During our experiment with zswap, we sometimes observe swap IOs due to
occasional zswap store failures and writebacks-to-swap.  These swapping
IOs prevent many users who cannot tolerate swapping from adopting zswap to
save memory and improve performance where possible.

This patch adds the option to disable this behavior entirely: do not
writeback to backing swapping device when a zswap store attempt fail, and
do not write pages in the zswap pool back to the backing swap device (both
when the pool is full, and when the new zswap shrinker is called).

This new behavior can be opted-in/out on a per-cgroup basis via a new
cgroup file.  By default, writebacks to swap device is enabled, which is
the previous behavior.  Initially, writeback is enabled for the root
cgroup, and a newly created cgroup will inherit the current setting of its
parent.

Note that this is subtly different from setting memory.swap.max to 0, as
it still allows for pages to be stored in the zswap pool (which itself
consumes swap space in its current form).

This patch should be applied on top of the zswap shrinker series:

https://lore.kernel.org/linux-mm/20231130194023.4102148-1-nphamcs@gmail.com/

as it also disables the zswap shrinker, a major source of zswap
writebacks.

For the most part, this feature is motivated by internal parties who
have already established their opinions regarding swapping - the
workloads that are highly sensitive to IO, and especially those who are
using servers with really slow disk performance (for instance, massive
but slow HDDs).  For these folks, it's impossible to convince them to
even entertain zswap if swapping also comes as a packaged deal.
Writeback disabling is quite a useful feature in these situations - on
a mixed workloads deployment, they can disable writeback for the more
IO-sensitive workloads, and enable writeback for other background
workloads.

For instance, on a server with HDD, I allocate memories and populate
them with random values (so that zswap store will always fail), and
specify memory.high low enough to trigger reclaim.  The time it takes
to allocate the memories and just read through it a couple of times
(doing silly things like computing the values' average etc.):

zswap.writeback disabled:
real 0m30.537s
user 0m23.687s
sys 0m6.637s
0 pages swapped in
0 pages swapped out

zswap.writeback enabled:
real 0m45.061s
user 0m24.310s
sys 0m8.892s
712686 pages swapped in
461093 pages swapped out

(the last two lines are from vmstat -s).

[nphamcs@gmail.com: add a comment about recurring zswap store failures leading to reclaim inefficiency]
  Link: https://lkml.kernel.org/r/20231221005725.3446672-1-nphamcs@gmail.com
Link: https://lkml.kernel.org/r/20231207192406.3809579-1-nphamcs@gmail.com
Signed-off-by: Nhat Pham <nphamcs@gmail.com>
Suggested-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Yosry Ahmed <yosryahmed@google.com>
Acked-by: Chris Li <chrisl@kernel.org>
Cc: Dan Streetman <ddstreet@ieee.org>
Cc: David Heidelberg <david@ixit.cz>
Cc: Domenico Cerasuolo <cerasuolodomenico@gmail.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Seth Jennings <sjenning@redhat.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vitaly Wool <vitaly.wool@konsulko.com>
Cc: Zefan Li <lizefan.x@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 Documentation/admin-guide/cgroup-v2.rst | 15 +++++++++++++
 Documentation/admin-guide/mm/zswap.rst  | 10 +++++++++
 include/linux/memcontrol.h              | 12 +++++++++++
 include/linux/zswap.h                   |  7 ++++++
 mm/memcontrol.c                         | 38 +++++++++++++++++++++++++++++++++
 mm/page_io.c                            |  5 +++++
 mm/shmem.c                              |  3 +--
 mm/zswap.c                              | 13 +++++++++--
 8 files changed, 99 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 3f85254f3cef..5ec7dd753cd1 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1679,6 +1679,21 @@ PAGE_SIZE multiple when read back.
 	limit, it will refuse to take any more stores before existing
 	entries fault back in or are written out to disk.
 
+  memory.zswap.writeback
+	A read-write single value file. The default value is "1". The
+	initial value of the root cgroup is 1, and when a new cgroup is
+	created, it inherits the current value of its parent.
+
+	When this is set to 0, all swapping attempts to swapping devices
+	are disabled. This included both zswap writebacks, and swapping due
+	to zswap store failures. If the zswap store failures are recurring
+	(for e.g if the pages are incompressible), users can observe
+	reclaim inefficiency after disabling writeback (because the same
+	pages might be rejected again and again).
+
+	Note that this is subtly different from setting memory.swap.max to
+	0, as it still allows for pages to be written to the zswap pool.
+
   memory.pressure
 	A read-only nested-keyed file.
 
diff --git a/Documentation/admin-guide/mm/zswap.rst b/Documentation/admin-guide/mm/zswap.rst
index 62fc244ec702..b42132969e31 100644
--- a/Documentation/admin-guide/mm/zswap.rst
+++ b/Documentation/admin-guide/mm/zswap.rst
@@ -153,6 +153,16 @@ attribute, e. g.::
 
 Setting this parameter to 100 will disable the hysteresis.
 
+Some users cannot tolerate the swapping that comes with zswap store failures
+and zswap writebacks. Swapping can be disabled entirely (without disabling
+zswap itself) on a cgroup-basis as follows:
+
+	echo 0 > /sys/fs/cgroup/<cgroup-name>/memory.zswap.writeback
+
+Note that if the store failures are recurring (for e.g if the pages are
+incompressible), users can observe reclaim inefficiency after disabling
+writeback (because the same pages might be rejected again and again).
+
 When there is a sizable amount of cold memory residing in the zswap pool, it
 can be advantageous to proactively write these cold pages to swap and reclaim
 the memory for other use cases. By default, the zswap shrinker is disabled.
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 43b77363ab8e..5de775e6cdd9 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -219,6 +219,12 @@ struct mem_cgroup {
 
 #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
 	unsigned long zswap_max;
+
+	/*
+	 * Prevent pages from this memcg from being written back from zswap to
+	 * swap, and from being swapped out on zswap store failures.
+	 */
+	bool zswap_writeback;
 #endif
 
 	unsigned long soft_limit;
@@ -1941,6 +1947,7 @@ static inline void count_objcg_event(struct obj_cgroup *objcg,
 bool obj_cgroup_may_zswap(struct obj_cgroup *objcg);
 void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, size_t size);
 void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size);
+bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg);
 #else
 static inline bool obj_cgroup_may_zswap(struct obj_cgroup *objcg)
 {
@@ -1954,6 +1961,11 @@ static inline void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg,
 					     size_t size)
 {
 }
+static inline bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg)
+{
+	/* if zswap is disabled, do not block pages going to the swapping device */
+	return true;
+}
 #endif
 
 #endif /* _LINUX_MEMCONTROL_H */
diff --git a/include/linux/zswap.h b/include/linux/zswap.h
index e88572d4c720..0b709f5bc65f 100644
--- a/include/linux/zswap.h
+++ b/include/linux/zswap.h
@@ -35,6 +35,7 @@ void zswap_swapoff(int type);
 void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg);
 void zswap_lruvec_state_init(struct lruvec *lruvec);
 void zswap_folio_swapin(struct folio *folio);
+bool is_zswap_enabled(void);
 #else
 
 struct zswap_lruvec_state {};
@@ -55,6 +56,12 @@ static inline void zswap_swapoff(int type) {}
 static inline void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg) {}
 static inline void zswap_lruvec_state_init(struct lruvec *lruvec) {}
 static inline void zswap_folio_swapin(struct folio *folio) {}
+
+static inline bool is_zswap_enabled(void)
+{
+	return false;
+}
+
 #endif
 
 #endif /* _LINUX_ZSWAP_H */
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index b08b9cd4a3a8..3ca691fb5b49 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5538,6 +5538,8 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 	WRITE_ONCE(memcg->soft_limit, PAGE_COUNTER_MAX);
 #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
 	memcg->zswap_max = PAGE_COUNTER_MAX;
+	WRITE_ONCE(memcg->zswap_writeback,
+		!parent || READ_ONCE(parent->zswap_writeback));
 #endif
 	page_counter_set_high(&memcg->swap, PAGE_COUNTER_MAX);
 	if (parent) {
@@ -8166,6 +8168,12 @@ void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size)
 	rcu_read_unlock();
 }
 
+bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg)
+{
+	/* if zswap is disabled, do not block pages going to the swapping device */
+	return !is_zswap_enabled() || !memcg || READ_ONCE(memcg->zswap_writeback);
+}
+
 static u64 zswap_current_read(struct cgroup_subsys_state *css,
 			      struct cftype *cft)
 {
@@ -8198,6 +8206,31 @@ static ssize_t zswap_max_write(struct kernfs_open_file *of,
 	return nbytes;
 }
 
+static int zswap_writeback_show(struct seq_file *m, void *v)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
+
+	seq_printf(m, "%d\n", READ_ONCE(memcg->zswap_writeback));
+	return 0;
+}
+
+static ssize_t zswap_writeback_write(struct kernfs_open_file *of,
+				char *buf, size_t nbytes, loff_t off)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
+	int zswap_writeback;
+	ssize_t parse_ret = kstrtoint(strstrip(buf), 0, &zswap_writeback);
+
+	if (parse_ret)
+		return parse_ret;
+
+	if (zswap_writeback != 0 && zswap_writeback != 1)
+		return -EINVAL;
+
+	WRITE_ONCE(memcg->zswap_writeback, zswap_writeback);
+	return nbytes;
+}
+
 static struct cftype zswap_files[] = {
 	{
 		.name = "zswap.current",
@@ -8210,6 +8243,11 @@ static struct cftype zswap_files[] = {
 		.seq_show = zswap_max_show,
 		.write = zswap_max_write,
 	},
+	{
+		.name = "zswap.writeback",
+		.seq_show = zswap_writeback_show,
+		.write = zswap_writeback_write,
+	},
 	{ }	/* terminate */
 };
 #endif /* CONFIG_MEMCG_KMEM && CONFIG_ZSWAP */
diff --git a/mm/page_io.c b/mm/page_io.c
index 09c6a4f316f3..ae2b49055e43 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -201,6 +201,11 @@ int swap_writepage(struct page *page, struct writeback_control *wbc)
 		folio_end_writeback(folio);
 		return 0;
 	}
+	if (!mem_cgroup_zswap_writeback_enabled(folio_memcg(folio))) {
+		folio_mark_dirty(folio);
+		return AOP_WRITEPAGE_ACTIVATE;
+	}
+
 	__swap_writepage(folio, wbc);
 	return 0;
 }
diff --git a/mm/shmem.c b/mm/shmem.c
index a4d388973021..928aa2304932 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1514,8 +1514,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 
 		mutex_unlock(&shmem_swaplist_mutex);
 		BUG_ON(folio_mapped(folio));
-		swap_writepage(&folio->page, wbc);
-		return 0;
+		return swap_writepage(&folio->page, wbc);
 	}
 
 	mutex_unlock(&shmem_swaplist_mutex);
diff --git a/mm/zswap.c b/mm/zswap.c
index f760801a3ea8..ca25b676048e 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -153,6 +153,11 @@ static bool zswap_shrinker_enabled = IS_ENABLED(
 		CONFIG_ZSWAP_SHRINKER_DEFAULT_ON);
 module_param_named(shrinker_enabled, zswap_shrinker_enabled, bool, 0644);
 
+bool is_zswap_enabled(void)
+{
+	return zswap_enabled;
+}
+
 /*********************************
 * data structures
 **********************************/
@@ -596,7 +601,8 @@ static unsigned long zswap_shrinker_scan(struct shrinker *shrinker,
 	struct zswap_pool *pool = shrinker->private_data;
 	bool encountered_page_in_swapcache = false;
 
-	if (!zswap_shrinker_enabled) {
+	if (!zswap_shrinker_enabled ||
+			!mem_cgroup_zswap_writeback_enabled(sc->memcg)) {
 		sc->nr_scanned = 0;
 		return SHRINK_STOP;
 	}
@@ -637,7 +643,7 @@ static unsigned long zswap_shrinker_count(struct shrinker *shrinker,
 	struct lruvec *lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(sc->nid));
 	unsigned long nr_backing, nr_stored, nr_freeable, nr_protected;
 
-	if (!zswap_shrinker_enabled)
+	if (!zswap_shrinker_enabled || !mem_cgroup_zswap_writeback_enabled(memcg))
 		return 0;
 
 #ifdef CONFIG_MEMCG_KMEM
@@ -923,6 +929,9 @@ static int shrink_memcg(struct mem_cgroup *memcg)
 	struct zswap_pool *pool;
 	int nid, shrunk = 0;
 
+	if (!mem_cgroup_zswap_writeback_enabled(memcg))
+		return -EINVAL;
+
 	/*
 	 * Skip zombies because their LRUs are reparented and we would be
 	 * reclaiming from the parent instead of the dead memcg.
-- 
cgit v1.2.3


From 66e82d219924f6112509f7e8f8e687fcc81a16e3 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 19 Dec 2023 14:34:46 +0100
Subject: ALSA: mark all struct bus_type as const

Now that the driver core can properly handle constant struct bus_type,
move all of the sound subsystem struct bus_type structures as const,
placing them into read-only memory which can not be modified at runtime.

Note, this fixes a duplicate definition of ac97_bus_type, which somehow
was declared extern in a .h file, and then static as a prototype in a .c
file, and then properly later on in the same .c file.  Amazing that no
compiler warning ever showed up for this.

Cc: Jaroslav Kysela <perex@perex.cz>
Cc: Takashi Iwai <tiwai@suse.com>
Cc: Dawei Li <set_pte_at@outlook.com>
Cc: Yu Liao <liaoyu15@huawei.com>
Cc: "Rafael J. Wysocki" <rafael@kernel.org>
Cc: Hans de Goede <hdegoede@redhat.com>
Cc: linux-sound@vger.kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/2023121945-immersion-budget-d0aa@gregkh
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/ac97_codec.h | 2 +-
 include/sound/hdaudio.h    | 2 +-
 sound/ac97/bus.c           | 2 --
 sound/ac97_bus.c           | 2 +-
 sound/hda/hda_bus_type.c   | 2 +-
 5 files changed, 4 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/sound/ac97_codec.h b/include/sound/ac97_codec.h
index c495c6d5fbe0..4bd3be3a3192 100644
--- a/include/sound/ac97_codec.h
+++ b/include/sound/ac97_codec.h
@@ -410,7 +410,7 @@ int snd_ac97_pcm_close(struct ac97_pcm *pcm);
 int snd_ac97_pcm_double_rate_rules(struct snd_pcm_runtime *runtime);
 
 /* ad hoc AC97 device driver access */
-extern struct bus_type ac97_bus_type;
+extern const struct bus_type ac97_bus_type;
 
 /* AC97 platform_data adding function */
 static inline void snd_ac97_dev_add_pdata(struct snd_ac97 *ac97, void *data)
diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h
index 62a3cd154ff2..a73d7f34f4e5 100644
--- a/include/sound/hdaudio.h
+++ b/include/sound/hdaudio.h
@@ -33,7 +33,7 @@ struct hda_device_id;
 /*
  * exported bus type
  */
-extern struct bus_type snd_hda_bus_type;
+extern const struct bus_type snd_hda_bus_type;
 
 /*
  * generic arrays
diff --git a/sound/ac97/bus.c b/sound/ac97/bus.c
index 3173e9d98927..1dc7965eb14b 100644
--- a/sound/ac97/bus.c
+++ b/sound/ac97/bus.c
@@ -28,8 +28,6 @@ static DEFINE_MUTEX(ac97_controllers_mutex);
 static DEFINE_IDR(ac97_adapter_idr);
 static LIST_HEAD(ac97_controllers);
 
-static struct bus_type ac97_bus_type;
-
 static inline struct ac97_controller*
 to_ac97_controller(struct device *ac97_adapter)
 {
diff --git a/sound/ac97_bus.c b/sound/ac97_bus.c
index c7aee8c42c55..7ea274c55900 100644
--- a/sound/ac97_bus.c
+++ b/sound/ac97_bus.c
@@ -75,7 +75,7 @@ int snd_ac97_reset(struct snd_ac97 *ac97, bool try_warm, unsigned int id,
 }
 EXPORT_SYMBOL_GPL(snd_ac97_reset);
 
-struct bus_type ac97_bus_type = {
+const struct bus_type ac97_bus_type = {
 	.name		= "ac97",
 };
 
diff --git a/sound/hda/hda_bus_type.c b/sound/hda/hda_bus_type.c
index 4cd94178df9f..cce2c30511a2 100644
--- a/sound/hda/hda_bus_type.c
+++ b/sound/hda/hda_bus_type.c
@@ -76,7 +76,7 @@ static int hda_uevent(const struct device *dev, struct kobj_uevent_env *env)
 	return 0;
 }
 
-struct bus_type snd_hda_bus_type = {
+const struct bus_type snd_hda_bus_type = {
 	.name = "hdaudio",
 	.match = hda_bus_match,
 	.uevent = hda_uevent,
-- 
cgit v1.2.3


From 7c223098212957a1ecd8768e8e747ae2cf88e880 Mon Sep 17 00:00:00 2001
From: David Laight <David.Laight@ACULAB.COM>
Date: Fri, 29 Dec 2023 20:53:49 +0000
Subject: locking/osq_lock: Move the definition of optimistic_spin_node into
 osq_lock.c

struct optimistic_spin_node is private to the implementation.
Move it into the C file to ensure nothing is accessing it.

Signed-off-by: David Laight <david.laight@aculab.com>
Acked-by: Waiman Long <longman@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/osq_lock.h  | 5 -----
 kernel/locking/osq_lock.c | 7 +++++++
 2 files changed, 7 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/osq_lock.h b/include/linux/osq_lock.h
index 5581dbd3bd34..ea8fb31379e3 100644
--- a/include/linux/osq_lock.h
+++ b/include/linux/osq_lock.h
@@ -6,11 +6,6 @@
  * An MCS like lock especially tailored for optimistic spinning for sleeping
  * lock implementations (mutex, rwsem, etc).
  */
-struct optimistic_spin_node {
-	struct optimistic_spin_node *next, *prev;
-	int locked; /* 1 if lock acquired */
-	int cpu; /* encoded CPU # + 1 value */
-};
 
 struct optimistic_spin_queue {
 	/*
diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c
index d5610ad52b92..d414eef4bec6 100644
--- a/kernel/locking/osq_lock.c
+++ b/kernel/locking/osq_lock.c
@@ -11,6 +11,13 @@
  * called from interrupt context and we have preemption disabled while
  * spinning.
  */
+
+struct optimistic_spin_node {
+	struct optimistic_spin_node *next, *prev;
+	int locked; /* 1 if lock acquired */
+	int cpu; /* encoded CPU # + 1 value */
+};
+
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct optimistic_spin_node, osq_node);
 
 /*
-- 
cgit v1.2.3


From cff9c565e65f3622e8dc1dcc21c1520a083dff35 Mon Sep 17 00:00:00 2001
From: Luiz Angelo Daros de Luca <luizluca@gmail.com>
Date: Wed, 20 Dec 2023 01:52:29 -0300
Subject: net: mdio: get/put device node during (un)registration

The __of_mdiobus_register() function was storing the device node in
dev.of_node without increasing its reference count. It implicitly relied
on the caller to maintain the allocated node until the mdiobus was
unregistered.

Now, __of_mdiobus_register() will acquire the node before assigning it,
and of_mdiobus_unregister_callback() will be called at the end of
mdio_unregister().

Drivers can now release the node immediately after MDIO registration.
Some of them are already doing that even before this patch.

Signed-off-by: Luiz Angelo Daros de Luca <luizluca@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/mdio/of_mdio.c | 12 +++++++++++-
 drivers/net/phy/mdio_bus.c |  3 +++
 include/linux/phy.h        |  3 +++
 3 files changed, 17 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/net/mdio/of_mdio.c b/drivers/net/mdio/of_mdio.c
index 64ebcb6d235c..9b6cab6154e0 100644
--- a/drivers/net/mdio/of_mdio.c
+++ b/drivers/net/mdio/of_mdio.c
@@ -139,6 +139,11 @@ bool of_mdiobus_child_is_phy(struct device_node *child)
 }
 EXPORT_SYMBOL(of_mdiobus_child_is_phy);
 
+static void __of_mdiobus_unregister_callback(struct mii_bus *mdio)
+{
+	of_node_put(mdio->dev.of_node);
+}
+
 /**
  * __of_mdiobus_register - Register mii_bus and create PHYs from the device tree
  * @mdio: pointer to mii_bus structure
@@ -166,6 +171,8 @@ int __of_mdiobus_register(struct mii_bus *mdio, struct device_node *np,
 	 * the device tree are populated after the bus has been registered */
 	mdio->phy_mask = ~0;
 
+	mdio->__unregister_callback = __of_mdiobus_unregister_callback;
+	of_node_get(np);
 	device_set_node(&mdio->dev, of_fwnode_handle(np));
 
 	/* Get bus level PHY reset GPIO details */
@@ -177,7 +184,7 @@ int __of_mdiobus_register(struct mii_bus *mdio, struct device_node *np,
 	/* Register the MDIO bus */
 	rc = __mdiobus_register(mdio, owner);
 	if (rc)
-		return rc;
+		goto put_node;
 
 	/* Loop over the child nodes and register a phy_device for each phy */
 	for_each_available_child_of_node(np, child) {
@@ -237,6 +244,9 @@ int __of_mdiobus_register(struct mii_bus *mdio, struct device_node *np,
 unregister:
 	of_node_put(child);
 	mdiobus_unregister(mdio);
+
+put_node:
+	of_node_put(np);
 	return rc;
 }
 EXPORT_SYMBOL(__of_mdiobus_register);
diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index 6cf73c15635b..4a30757c4ff8 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -787,6 +787,9 @@ void mdiobus_unregister(struct mii_bus *bus)
 		gpiod_set_value_cansleep(bus->reset_gpiod, 1);
 
 	device_del(&bus->dev);
+
+	if (bus->__unregister_callback)
+		bus->__unregister_callback(bus);
 }
 EXPORT_SYMBOL(mdiobus_unregister);
 
diff --git a/include/linux/phy.h b/include/linux/phy.h
index e9e85d347587..ede891776d8b 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -434,6 +434,9 @@ struct mii_bus {
 
 	/** @shared: shared state across different PHYs */
 	struct phy_package_shared *shared[PHY_MAX_ADDR];
+
+	/** @__unregister_callback: called at the last step of unregistration */
+	void (*__unregister_callback)(struct mii_bus *bus);
 };
 #define to_mii_bus(d) container_of(d, struct mii_bus, dev)
 
-- 
cgit v1.2.3


From 92f091cdddace38e57ad570663b058a38b4d8bed Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 30 Oct 2023 11:43:24 +0000
Subject: afs: Dispatch fileserver probes in priority order

When probing all the addresses for a fileserver, dispatch them in order of
descending priority to try and get back highest priority one first.

Also add a tracepoint to show the transmission and completion of the
probes.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
---
 fs/afs/fs_probe.c          | 25 +++++++++++++++++++++++--
 include/trace/events/afs.h | 33 +++++++++++++++++++++++++++++++++
 2 files changed, 56 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/fs/afs/fs_probe.c b/fs/afs/fs_probe.c
index 8008d3ecabab..c5702698b18b 100644
--- a/fs/afs/fs_probe.c
+++ b/fs/afs/fs_probe.c
@@ -102,7 +102,7 @@ void afs_fileserver_probe_result(struct afs_call *call)
 	struct afs_address *addr = &alist->addrs[call->probe_index];
 	struct afs_server *server = call->server;
 	unsigned int index = call->probe_index;
-	unsigned int rtt_us = 0, cap0;
+	unsigned int rtt_us = -1, cap0;
 	int ret = call->error;
 
 	_enter("%pU,%u", &server->uuid, index);
@@ -182,6 +182,7 @@ responded:
 out:
 	spin_unlock(&server->probe_lock);
 
+	trace_afs_fs_probe(server, false, alist, index, call->error, call->abort_code, rtt_us);
 	_debug("probe %pU [%u] %pISpc rtt=%d ret=%d",
 	       &server->uuid, index, rxrpc_kernel_remote_addr(alist->addrs[index].peer),
 	       rtt_us, ret);
@@ -207,6 +208,8 @@ void afs_fs_probe_fileserver(struct afs_net *net, struct afs_server *server,
 	afs_get_addrlist(alist, afs_alist_trace_get_probe);
 	read_unlock(&server->fs_lock);
 
+	afs_get_address_preferences(net, alist);
+
 	server->probed_at = jiffies;
 	atomic_set(&server->probe_outstanding, all ? alist->nr_addrs : 1);
 	memset(&server->probe, 0, sizeof(server->probe));
@@ -217,10 +220,28 @@ void afs_fs_probe_fileserver(struct afs_net *net, struct afs_server *server,
 		all = true;
 
 	if (all) {
-		for (index = 0; index < alist->nr_addrs; index++)
+		unsigned long unprobed = (1UL << alist->nr_addrs) - 1;
+		unsigned int i;
+		int best_prio;
+
+		while (unprobed) {
+			best_prio = -1;
+			index = 0;
+			for (i = 0; i < alist->nr_addrs; i++) {
+				if (test_bit(i, &unprobed) &&
+				    alist->addrs[i].prio > best_prio) {
+					index = i;
+					best_prio = alist->addrs[i].prio;
+				}
+			}
+			__clear_bit(index, &unprobed);
+
+			trace_afs_fs_probe(server, true, alist, index, 0, 0, 0);
 			if (!afs_fs_get_capabilities(net, server, alist, index, key))
 				afs_fs_probe_not_done(net, server, alist, index);
+		}
 	} else {
+		trace_afs_fs_probe(server, true, alist, index, 0, 0, 0);
 		if (!afs_fs_get_capabilities(net, server, alist, index, key))
 			afs_fs_probe_not_done(net, server, alist, index);
 	}
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index 0f68d67f52c8..81eb87fbcfa7 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -1387,6 +1387,39 @@ TRACE_EVENT(afs_alist,
 		      __entry->ref)
 	    );
 
+TRACE_EVENT(afs_fs_probe,
+	    TP_PROTO(struct afs_server *server, bool tx, struct afs_addr_list *alist,
+		     unsigned int addr_index, int error, s32 abort_code, unsigned int rtt_us),
+
+	    TP_ARGS(server, tx, alist, addr_index, error, abort_code, rtt_us),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,		server)
+		    __field(bool,			tx)
+		    __field(u16,			addr_index)
+		    __field(short,			error)
+		    __field(s32,			abort_code)
+		    __field(unsigned int,		rtt_us)
+		    __field_struct(struct sockaddr_rxrpc, srx)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->server = server->debug_id;
+		    __entry->tx = tx;
+		    __entry->addr_index = addr_index;
+		    __entry->error = error;
+		    __entry->abort_code = abort_code;
+		    __entry->rtt_us = rtt_us;
+		    memcpy(&__entry->srx, rxrpc_kernel_remote_srx(alist->addrs[addr_index].peer),
+			   sizeof(__entry->srx));
+			   ),
+
+	    TP_printk("s=%08x %s ax=%u e=%d ac=%d rtt=%d %pISpc",
+		      __entry->server, __entry->tx ? "tx" : "rx", __entry->addr_index,
+		      __entry->error, __entry->abort_code, __entry->rtt_us,
+		      &__entry->srx.transport)
+	    );
+
 #endif /* _TRACE_AFS_H */
 
 /* This part must be outside protection */
-- 
cgit v1.2.3


From e6a7d7f71b17e0a44e2155bdad47eae7b5368503 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 30 Oct 2023 11:53:16 +0000
Subject: afs: Dispatch vlserver probes in priority order

When probing all the addresses for a volume location server, dispatch them
in order of descending priority to try and get back highest priority one
first.

Also add a tracepoint to show the transmission and completion of the
probes.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
---
 fs/afs/internal.h          |  1 +
 fs/afs/vl_list.c           |  2 ++
 fs/afs/vl_probe.c          | 20 ++++++++++++++++++--
 include/trace/events/afs.h | 34 ++++++++++++++++++++++++++++++++++
 4 files changed, 55 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 9a1e151e77e7..88db04220773 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -447,6 +447,7 @@ struct afs_vlserver {
 	rwlock_t		lock;		/* Lock on addresses */
 	refcount_t		ref;
 	unsigned int		rtt;		/* Server's current RTT in uS */
+	unsigned int		debug_id;
 
 	/* Probe state */
 	wait_queue_head_t	probe_wq;
diff --git a/fs/afs/vl_list.c b/fs/afs/vl_list.c
index 5c4cd71caccf..9b1c20daac53 100644
--- a/fs/afs/vl_list.c
+++ b/fs/afs/vl_list.c
@@ -13,6 +13,7 @@ struct afs_vlserver *afs_alloc_vlserver(const char *name, size_t name_len,
 					unsigned short port)
 {
 	struct afs_vlserver *vlserver;
+	static atomic_t debug_ids;
 
 	vlserver = kzalloc(struct_size(vlserver, name, name_len + 1),
 			   GFP_KERNEL);
@@ -21,6 +22,7 @@ struct afs_vlserver *afs_alloc_vlserver(const char *name, size_t name_len,
 		rwlock_init(&vlserver->lock);
 		init_waitqueue_head(&vlserver->probe_wq);
 		spin_lock_init(&vlserver->probe_lock);
+		vlserver->debug_id = atomic_inc_return(&debug_ids);
 		vlserver->rtt = UINT_MAX;
 		vlserver->name_len = name_len;
 		vlserver->service_id = VL_SERVICE;
diff --git a/fs/afs/vl_probe.c b/fs/afs/vl_probe.c
index f868ae5d40e5..b128dc3d8af7 100644
--- a/fs/afs/vl_probe.c
+++ b/fs/afs/vl_probe.c
@@ -131,6 +131,7 @@ responded:
 out:
 	spin_unlock(&server->probe_lock);
 
+	trace_afs_vl_probe(server, false, alist, index, call->error, call->abort_code, rtt_us);
 	_debug("probe [%u][%u] %pISpc rtt=%d ret=%d",
 	       server_index, index, rxrpc_kernel_remote_addr(addr->peer),
 	       rtt_us, ret);
@@ -150,8 +151,10 @@ static bool afs_do_probe_vlserver(struct afs_net *net,
 {
 	struct afs_addr_list *alist;
 	struct afs_call *call;
-	unsigned int index;
+	unsigned long unprobed;
+	unsigned int index, i;
 	bool in_progress = false;
+	int best_prio;
 
 	_enter("%s", server->name);
 
@@ -165,7 +168,20 @@ static bool afs_do_probe_vlserver(struct afs_net *net,
 	memset(&server->probe, 0, sizeof(server->probe));
 	server->probe.rtt = UINT_MAX;
 
-	for (index = 0; index < alist->nr_addrs; index++) {
+	unprobed = (1UL << alist->nr_addrs) - 1;
+	while (unprobed) {
+		best_prio = -1;
+		index = 0;
+		for (i = 0; i < alist->nr_addrs; i++) {
+			if (test_bit(i, &unprobed) &&
+			    alist->addrs[i].prio > best_prio) {
+				index = i;
+				best_prio = alist->addrs[i].prio;
+			}
+		}
+		__clear_bit(index, &unprobed);
+
+		trace_afs_vl_probe(server, true, alist, index, 0, 0, 0);
 		call = afs_vl_get_capabilities(net, alist, index, key, server,
 					       server_index);
 		if (!IS_ERR(call)) {
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index 81eb87fbcfa7..f1815b3dafb0 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -1420,6 +1420,40 @@ TRACE_EVENT(afs_fs_probe,
 		      &__entry->srx.transport)
 	    );
 
+TRACE_EVENT(afs_vl_probe,
+	    TP_PROTO(struct afs_vlserver *server, bool tx, struct afs_addr_list *alist,
+		     unsigned int addr_index, int error, s32 abort_code, unsigned int rtt_us),
+
+	    TP_ARGS(server, tx, alist, addr_index, error, abort_code, rtt_us),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,		server)
+		    __field(bool,			tx)
+		    __field(unsigned short,		flags)
+		    __field(u16,			addr_index)
+		    __field(short,			error)
+		    __field(s32,			abort_code)
+		    __field(unsigned int,		rtt_us)
+		    __field_struct(struct sockaddr_rxrpc, srx)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->server = server->debug_id;
+		    __entry->tx = tx;
+		    __entry->addr_index = addr_index;
+		    __entry->error = error;
+		    __entry->abort_code = abort_code;
+		    __entry->rtt_us = rtt_us;
+		    memcpy(&__entry->srx, rxrpc_kernel_remote_srx(alist->addrs[addr_index].peer),
+			   sizeof(__entry->srx));
+			   ),
+
+	    TP_printk("vl=%08x %s ax=%u e=%d ac=%d rtt=%d %pISpc",
+		      __entry->server, __entry->tx ? "tx" : "rx", __entry->addr_index,
+		      __entry->error, __entry->abort_code, __entry->rtt_us,
+		      &__entry->srx.transport)
+	    );
+
 #endif /* _TRACE_AFS_H */
 
 /* This part must be outside protection */
-- 
cgit v1.2.3


From f49b594df3ebca53c91f4d6448680463f10aa479 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 31 Oct 2023 16:30:37 +0000
Subject: afs: Keep a record of the current fileserver endpoint state

Keep a record of the current fileserver endpoint state, including the probe
state, and replace it when a new probe is started rather than just
squelching the old state and overwriting it.  Clearance of the old state
can cause a race if there's another thread also currently trying to
communicate with that server.

It appears that this race might be the culprit for some occasions where
kafs complains about invalid data in the RPC reply because the rotation
algorithm fell all the way through without actually issuing an RPC call and
the error return got filled in from the probe state (which has a zero error
recorded).  Whatever happens to be in the caller's reply buffer is then
taken as the response.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
---
 fs/afs/fs_operation.c      |  19 ++--
 fs/afs/fs_probe.c          | 235 +++++++++++++++++++++++++++------------------
 fs/afs/fsclient.c          |   8 +-
 fs/afs/internal.h          |  66 +++++++++----
 fs/afs/proc.c              |  21 ++--
 fs/afs/rotate.c            |  80 ++++++++-------
 fs/afs/server.c            |  69 ++++++++-----
 fs/afs/vl_alias.c          |   4 +-
 fs/afs/vl_probe.c          |   2 +-
 fs/afs/vlclient.c          |   4 +-
 include/trace/events/afs.h |  69 ++++++++++---
 11 files changed, 366 insertions(+), 211 deletions(-)

(limited to 'include')

diff --git a/fs/afs/fs_operation.c b/fs/afs/fs_operation.c
index e760e11d5bcb..8c6d827f999d 100644
--- a/fs/afs/fs_operation.c
+++ b/fs/afs/fs_operation.c
@@ -228,6 +228,7 @@ void afs_wait_for_operation(struct afs_operation *op)
  */
 int afs_put_operation(struct afs_operation *op)
 {
+	struct afs_endpoint_state *estate = op->estate;
 	struct afs_addr_list *alist;
 	int i, ret = afs_op_error(op);
 
@@ -251,14 +252,16 @@ int afs_put_operation(struct afs_operation *op)
 		kfree(op->more_files);
 	}
 
-	alist = op->alist;
-	if (alist) {
-		if (op->call_responded &&
-		    op->addr_index != alist->preferred &&
-		    test_bit(alist->preferred, &op->addr_tried))
-			WRITE_ONCE(alist->preferred, op->addr_index);
-		afs_put_addrlist(alist, afs_alist_trace_put_operation);
-		op->alist = NULL;
+	if (estate) {
+		alist = estate->addresses;
+		if (alist) {
+			if (op->call_responded &&
+			    op->addr_index != alist->preferred &&
+			    test_bit(alist->preferred, &op->addr_tried))
+				WRITE_ONCE(alist->preferred, op->addr_index);
+		}
+		afs_put_endpoint_state(estate, afs_estate_trace_put_operation);
+		op->estate = NULL;
 	}
 
 	afs_put_serverlist(op->net, op->server_list);
diff --git a/fs/afs/fs_probe.c b/fs/afs/fs_probe.c
index c5702698b18b..a669aee033c5 100644
--- a/fs/afs/fs_probe.c
+++ b/fs/afs/fs_probe.c
@@ -15,6 +15,42 @@
 static unsigned int afs_fs_probe_fast_poll_interval = 30 * HZ;
 static unsigned int afs_fs_probe_slow_poll_interval = 5 * 60 * HZ;
 
+struct afs_endpoint_state *afs_get_endpoint_state(struct afs_endpoint_state *estate,
+						  enum afs_estate_trace where)
+{
+	if (estate) {
+		int r;
+
+		__refcount_inc(&estate->ref, &r);
+		trace_afs_estate(estate->server_id, estate->probe_seq, r, where);
+	}
+	return estate;
+}
+
+static void afs_endpoint_state_rcu(struct rcu_head *rcu)
+{
+	struct afs_endpoint_state *estate = container_of(rcu, struct afs_endpoint_state, rcu);
+
+	trace_afs_estate(estate->server_id, estate->probe_seq, refcount_read(&estate->ref),
+			 afs_estate_trace_free);
+	afs_put_addrlist(estate->addresses, afs_alist_trace_put_estate);
+	kfree(estate);
+}
+
+void afs_put_endpoint_state(struct afs_endpoint_state *estate, enum afs_estate_trace where)
+{
+	if (estate) {
+		unsigned int server_id = estate->server_id, probe_seq = estate->probe_seq;
+		bool dead;
+		int r;
+
+		dead = __refcount_dec_and_test(&estate->ref, &r);
+		trace_afs_estate(server_id, probe_seq, r, where);
+		if (dead)
+			call_rcu(&estate->rcu, afs_endpoint_state_rcu);
+	}
+}
+
 /*
  * Start the probe polling timer.  We have to supply it with an inc on the
  * outstanding server count.
@@ -38,9 +74,10 @@ static void afs_schedule_fs_probe(struct afs_net *net,
 /*
  * Handle the completion of a set of probes.
  */
-static void afs_finished_fs_probe(struct afs_net *net, struct afs_server *server)
+static void afs_finished_fs_probe(struct afs_net *net, struct afs_server *server,
+				  struct afs_endpoint_state *estate)
 {
-	bool responded = server->probe.responded;
+	bool responded = estate->responded;
 
 	write_seqlock(&net->fs_lock);
 	if (responded) {
@@ -50,6 +87,7 @@ static void afs_finished_fs_probe(struct afs_net *net, struct afs_server *server
 		clear_bit(AFS_SERVER_FL_RESPONDING, &server->flags);
 		list_add_tail(&server->probe_link, &net->fs_probe_fast);
 	}
+
 	write_sequnlock(&net->fs_lock);
 
 	afs_schedule_fs_probe(net, server, !responded);
@@ -58,12 +96,13 @@ static void afs_finished_fs_probe(struct afs_net *net, struct afs_server *server
 /*
  * Handle the completion of a probe.
  */
-static void afs_done_one_fs_probe(struct afs_net *net, struct afs_server *server)
+static void afs_done_one_fs_probe(struct afs_net *net, struct afs_server *server,
+				  struct afs_endpoint_state *estate)
 {
 	_enter("");
 
-	if (atomic_dec_and_test(&server->probe_outstanding))
-		afs_finished_fs_probe(net, server);
+	if (atomic_dec_and_test(&estate->nr_probing))
+		afs_finished_fs_probe(net, server, estate);
 
 	wake_up_all(&server->probe_wq);
 }
@@ -74,7 +113,7 @@ static void afs_done_one_fs_probe(struct afs_net *net, struct afs_server *server
  */
 static void afs_fs_probe_not_done(struct afs_net *net,
 				  struct afs_server *server,
-				  struct afs_addr_list *alist,
+				  struct afs_endpoint_state *estate,
 				  int index)
 {
 	_enter("");
@@ -82,14 +121,14 @@ static void afs_fs_probe_not_done(struct afs_net *net,
 	trace_afs_io_error(0, -ENOMEM, afs_io_error_fs_probe_fail);
 	spin_lock(&server->probe_lock);
 
-	server->probe.local_failure = true;
-	if (server->probe.error == 0)
-		server->probe.error = -ENOMEM;
+	estate->local_failure = true;
+	if (estate->error == 0)
+		estate->error = -ENOMEM;
 
-	set_bit(index, &alist->probe_failed);
+	set_bit(index, &estate->failed_set);
 
 	spin_unlock(&server->probe_lock);
-	return afs_done_one_fs_probe(net, server);
+	return afs_done_one_fs_probe(net, server, estate);
 }
 
 /*
@@ -98,7 +137,8 @@ static void afs_fs_probe_not_done(struct afs_net *net,
  */
 void afs_fileserver_probe_result(struct afs_call *call)
 {
-	struct afs_addr_list *alist = call->probe_alist;
+	struct afs_endpoint_state *estate = call->probe;
+	struct afs_addr_list *alist = estate->addresses;
 	struct afs_address *addr = &alist->addrs[call->probe_index];
 	struct afs_server *server = call->server;
 	unsigned int index = call->probe_index;
@@ -113,18 +153,18 @@ void afs_fileserver_probe_result(struct afs_call *call)
 
 	switch (ret) {
 	case 0:
-		server->probe.error = 0;
+		estate->error = 0;
 		goto responded;
 	case -ECONNABORTED:
-		if (!server->probe.responded) {
-			server->probe.abort_code = call->abort_code;
-			server->probe.error = ret;
+		if (!estate->responded) {
+			estate->abort_code = call->abort_code;
+			estate->error = ret;
 		}
 		goto responded;
 	case -ENOMEM:
 	case -ENONET:
-		clear_bit(index, &alist->responded);
-		server->probe.local_failure = true;
+		clear_bit(index, &estate->responsive_set);
+		estate->local_failure = true;
 		trace_afs_io_error(call->debug_id, ret, afs_io_error_fs_probe_fail);
 		goto out;
 	case -ECONNRESET: /* Responded, but call expired. */
@@ -137,28 +177,28 @@ void afs_fileserver_probe_result(struct afs_call *call)
 	case -ETIMEDOUT:
 	case -ETIME:
 	default:
-		clear_bit(index, &alist->responded);
-		set_bit(index, &alist->probe_failed);
-		if (!server->probe.responded &&
-		    (server->probe.error == 0 ||
-		     server->probe.error == -ETIMEDOUT ||
-		     server->probe.error == -ETIME))
-			server->probe.error = ret;
+		clear_bit(index, &estate->responsive_set);
+		set_bit(index, &estate->failed_set);
+		if (!estate->responded &&
+		    (estate->error == 0 ||
+		     estate->error == -ETIMEDOUT ||
+		     estate->error == -ETIME))
+			estate->error = ret;
 		trace_afs_io_error(call->debug_id, ret, afs_io_error_fs_probe_fail);
 		goto out;
 	}
 
 responded:
-	clear_bit(index, &alist->probe_failed);
+	clear_bit(index, &estate->failed_set);
 
 	if (call->service_id == YFS_FS_SERVICE) {
-		server->probe.is_yfs = true;
+		estate->is_yfs = true;
 		set_bit(AFS_SERVER_FL_IS_YFS, &server->flags);
 		server->service_id = call->service_id;
 	} else {
-		server->probe.not_yfs = true;
-		if (!server->probe.is_yfs) {
-			clear_bit(AFS_SERVER_FL_IS_YFS, &server->flags);
+		estate->not_yfs = true;
+		if (!estate->is_yfs) {
+			estate->is_yfs = false;
 			server->service_id = call->service_id;
 		}
 		cap0 = ntohl(call->tmp);
@@ -169,84 +209,90 @@ responded:
 	}
 
 	rtt_us = rxrpc_kernel_get_srtt(addr->peer);
-	if (rtt_us < server->probe.rtt) {
-		server->probe.rtt = rtt_us;
+	if (rtt_us < estate->rtt) {
+		estate->rtt = rtt_us;
 		server->rtt = rtt_us;
 		alist->preferred = index;
 	}
 
 	smp_wmb(); /* Set rtt before responded. */
-	server->probe.responded = true;
-	set_bit(index, &alist->responded);
+	estate->responded = true;
+	set_bit(index, &estate->responsive_set);
 	set_bit(AFS_SERVER_FL_RESPONDING, &server->flags);
 out:
 	spin_unlock(&server->probe_lock);
 
-	trace_afs_fs_probe(server, false, alist, index, call->error, call->abort_code, rtt_us);
-	_debug("probe %pU [%u] %pISpc rtt=%d ret=%d",
-	       &server->uuid, index, rxrpc_kernel_remote_addr(alist->addrs[index].peer),
+	trace_afs_fs_probe(server, false, estate, index, call->error, call->abort_code, rtt_us);
+	_debug("probe[%x] %pU [%u] %pISpc rtt=%d ret=%d",
+	       estate->probe_seq, &server->uuid, index,
+	       rxrpc_kernel_remote_addr(alist->addrs[index].peer),
 	       rtt_us, ret);
 
-	return afs_done_one_fs_probe(call->net, server);
+	return afs_done_one_fs_probe(call->net, server, estate);
 }
 
 /*
- * Probe one or all of a fileserver's addresses to find out the best route and
- * to query its capabilities.
+ * Probe all of a fileserver's addresses to find out the best route and to
+ * query its capabilities.
  */
 void afs_fs_probe_fileserver(struct afs_net *net, struct afs_server *server,
-			     struct key *key, bool all)
+			     struct afs_addr_list *new_alist, struct key *key)
 {
+	struct afs_endpoint_state *estate, *old;
 	struct afs_addr_list *alist;
-	unsigned int index;
+	unsigned long unprobed;
 
 	_enter("%pU", &server->uuid);
 
-	read_lock(&server->fs_lock);
-	alist = rcu_dereference_protected(server->addresses,
-					  lockdep_is_held(&server->fs_lock));
-	afs_get_addrlist(alist, afs_alist_trace_get_probe);
-	read_unlock(&server->fs_lock);
+	estate = kzalloc(sizeof(*estate), GFP_KERNEL);
+	if (!estate)
+		return;
+
+	refcount_set(&estate->ref, 1);
+	estate->server_id = server->debug_id;
+	estate->rtt = UINT_MAX;
+
+	write_lock(&server->fs_lock);
+
+	old = rcu_dereference_protected(server->endpoint_state,
+					lockdep_is_held(&server->fs_lock));
+	estate->responsive_set = old->responsive_set;
+	estate->addresses = afs_get_addrlist(new_alist ?: old->addresses,
+					     afs_alist_trace_get_estate);
+	alist = estate->addresses;
+	estate->probe_seq = ++server->probe_counter;
+	atomic_set(&estate->nr_probing, alist->nr_addrs);
+
+	rcu_assign_pointer(server->endpoint_state, estate);
+	old->superseded = true;
+	write_unlock(&server->fs_lock);
+
+	trace_afs_estate(estate->server_id, estate->probe_seq, refcount_read(&estate->ref),
+			 afs_estate_trace_alloc_probe);
 
 	afs_get_address_preferences(net, alist);
 
 	server->probed_at = jiffies;
-	atomic_set(&server->probe_outstanding, all ? alist->nr_addrs : 1);
-	memset(&server->probe, 0, sizeof(server->probe));
-	server->probe.rtt = UINT_MAX;
-
-	index = alist->preferred;
-	if (index < 0 || index >= alist->nr_addrs)
-		all = true;
-
-	if (all) {
-		unsigned long unprobed = (1UL << alist->nr_addrs) - 1;
-		unsigned int i;
-		int best_prio;
-
-		while (unprobed) {
-			best_prio = -1;
-			index = 0;
-			for (i = 0; i < alist->nr_addrs; i++) {
-				if (test_bit(i, &unprobed) &&
-				    alist->addrs[i].prio > best_prio) {
-					index = i;
-					best_prio = alist->addrs[i].prio;
-				}
+	unprobed = (1UL << alist->nr_addrs) - 1;
+	while (unprobed) {
+		unsigned int index = 0, i;
+		int best_prio = -1;
+
+		for (i = 0; i < alist->nr_addrs; i++) {
+			if (test_bit(i, &unprobed) &&
+			    alist->addrs[i].prio > best_prio) {
+				index = i;
+				best_prio = alist->addrs[i].prio;
 			}
-			__clear_bit(index, &unprobed);
-
-			trace_afs_fs_probe(server, true, alist, index, 0, 0, 0);
-			if (!afs_fs_get_capabilities(net, server, alist, index, key))
-				afs_fs_probe_not_done(net, server, alist, index);
 		}
-	} else {
-		trace_afs_fs_probe(server, true, alist, index, 0, 0, 0);
-		if (!afs_fs_get_capabilities(net, server, alist, index, key))
-			afs_fs_probe_not_done(net, server, alist, index);
+		__clear_bit(index, &unprobed);
+
+		trace_afs_fs_probe(server, true, estate, index, 0, 0, 0);
+		if (!afs_fs_get_capabilities(net, server, estate, index, key))
+			afs_fs_probe_not_done(net, server, estate, index);
 	}
 
-	afs_put_addrlist(alist, afs_alist_trace_put_probe);
+	afs_put_endpoint_state(old, afs_estate_trace_put_probe);
 }
 
 /*
@@ -254,6 +300,7 @@ void afs_fs_probe_fileserver(struct afs_net *net, struct afs_server *server,
  */
 int afs_wait_for_fs_probes(struct afs_server_list *slist, unsigned long untried)
 {
+	struct afs_endpoint_state *estate;
 	struct wait_queue_entry *waits;
 	struct afs_server *server;
 	unsigned int rtt = UINT_MAX, rtt_s;
@@ -263,15 +310,18 @@ int afs_wait_for_fs_probes(struct afs_server_list *slist, unsigned long untried)
 	_enter("%u,%lx", slist->nr_servers, untried);
 
 	/* Only wait for servers that have a probe outstanding. */
+	rcu_read_lock();
 	for (i = 0; i < slist->nr_servers; i++) {
 		if (test_bit(i, &untried)) {
 			server = slist->servers[i].server;
-			if (!atomic_read(&server->probe_outstanding))
+			estate = rcu_dereference(server->endpoint_state);
+			if (!atomic_read(&estate->nr_probing))
 				__clear_bit(i, &untried);
-			if (server->probe.responded)
+			if (estate->responded)
 				have_responders = true;
 		}
 	}
+	rcu_read_unlock();
 	if (have_responders || !untried)
 		return 0;
 
@@ -294,9 +344,9 @@ int afs_wait_for_fs_probes(struct afs_server_list *slist, unsigned long untried)
 		for (i = 0; i < slist->nr_servers; i++) {
 			if (test_bit(i, &untried)) {
 				server = slist->servers[i].server;
-				if (server->probe.responded)
+				if (estate->responded)
 					goto stop;
-				if (atomic_read(&server->probe_outstanding))
+				if (atomic_read(&estate->nr_probing))
 					still_probing = true;
 			}
 		}
@@ -348,7 +398,7 @@ void afs_fs_probe_timer(struct timer_list *timer)
 /*
  * Dispatch a probe to a server.
  */
-static void afs_dispatch_fs_probe(struct afs_net *net, struct afs_server *server, bool all)
+static void afs_dispatch_fs_probe(struct afs_net *net, struct afs_server *server)
 	__releases(&net->fs_lock)
 {
 	struct key *key = NULL;
@@ -361,7 +411,7 @@ static void afs_dispatch_fs_probe(struct afs_net *net, struct afs_server *server
 	afs_get_server(server, afs_server_trace_get_probe);
 	write_sequnlock(&net->fs_lock);
 
-	afs_fs_probe_fileserver(net, server, key, all);
+	afs_fs_probe_fileserver(net, server, NULL, key);
 	afs_put_server(net, server, afs_server_trace_put_probe);
 }
 
@@ -373,7 +423,7 @@ void afs_probe_fileserver(struct afs_net *net, struct afs_server *server)
 {
 	write_seqlock(&net->fs_lock);
 	if (!list_empty(&server->probe_link))
-		return afs_dispatch_fs_probe(net, server, true);
+		return afs_dispatch_fs_probe(net, server);
 	write_sequnlock(&net->fs_lock);
 }
 
@@ -433,7 +483,7 @@ again:
 		_debug("probe %pU", &server->uuid);
 
 	if (server && (first_pass || !need_resched())) {
-		afs_dispatch_fs_probe(net, server, server == fast);
+		afs_dispatch_fs_probe(net, server);
 		first_pass = false;
 		goto again;
 	}
@@ -457,12 +507,13 @@ again:
 /*
  * Wait for a probe on a particular fileserver to complete for 2s.
  */
-int afs_wait_for_one_fs_probe(struct afs_server *server, bool is_intr)
+int afs_wait_for_one_fs_probe(struct afs_server *server, struct afs_endpoint_state *estate,
+			      bool is_intr)
 {
 	struct wait_queue_entry wait;
 	unsigned long timo = 2 * HZ;
 
-	if (atomic_read(&server->probe_outstanding) == 0)
+	if (atomic_read(&estate->nr_probing) == 0)
 		goto dont_wait;
 
 	init_wait_entry(&wait, 0);
@@ -470,8 +521,8 @@ int afs_wait_for_one_fs_probe(struct afs_server *server, bool is_intr)
 		prepare_to_wait_event(&server->probe_wq, &wait,
 				      is_intr ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE);
 		if (timo == 0 ||
-		    server->probe.responded ||
-		    atomic_read(&server->probe_outstanding) == 0 ||
+		    estate->responded ||
+		    atomic_read(&estate->nr_probing) == 0 ||
 		    (is_intr && signal_pending(current)))
 			break;
 		timo = schedule_timeout(timo);
@@ -480,7 +531,7 @@ int afs_wait_for_one_fs_probe(struct afs_server *server, bool is_intr)
 	finish_wait(&server->probe_wq, &wait);
 
 dont_wait:
-	if (server->probe.responded)
+	if (estate->responded)
 		return 0;
 	if (is_intr && signal_pending(current))
 		return -ERESTARTSYS;
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index 4f98b43b0dde..f1f879ba9cf7 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -1697,7 +1697,7 @@ static int afs_deliver_fs_get_capabilities(struct afs_call *call)
 
 static void afs_fs_get_capabilities_destructor(struct afs_call *call)
 {
-	afs_put_addrlist(call->probe_alist, afs_alist_trace_put_getcaps);
+	afs_put_endpoint_state(call->probe, afs_estate_trace_put_getcaps);
 	afs_flat_call_destructor(call);
 }
 
@@ -1719,7 +1719,7 @@ static const struct afs_call_type afs_RXFSGetCapabilities = {
  * ->done() - otherwise we return false to indicate we didn't even try.
  */
 bool afs_fs_get_capabilities(struct afs_net *net, struct afs_server *server,
-			     struct afs_addr_list *alist, unsigned int addr_index,
+			     struct afs_endpoint_state *estate, unsigned int addr_index,
 			     struct key *key)
 {
 	struct afs_call *call;
@@ -1733,8 +1733,8 @@ bool afs_fs_get_capabilities(struct afs_net *net, struct afs_server *server,
 
 	call->key	= key;
 	call->server	= afs_use_server(server, afs_server_trace_get_caps);
-	call->peer	= rxrpc_kernel_get_peer(alist->addrs[addr_index].peer);
-	call->probe_alist = afs_get_addrlist(alist, afs_alist_trace_get_getcaps);
+	call->peer	= rxrpc_kernel_get_peer(estate->addresses->addrs[addr_index].peer);
+	call->probe	= afs_get_endpoint_state(estate, afs_estate_trace_get_getcaps);
 	call->probe_index = addr_index;
 	call->service_id = server->service_id;
 	call->upgrade	= true;
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 88db04220773..4d42f84a8da4 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -33,6 +33,7 @@
 struct pagevec;
 struct afs_call;
 struct afs_vnode;
+struct afs_server_probe;
 
 /*
  * Partial file-locking emulation mode.  (The problem being that AFS3 only
@@ -146,14 +147,13 @@ struct afs_call {
 	};
 	void			*buffer;	/* reply receive buffer */
 	union {
-		struct {
-			struct afs_addr_list	*probe_alist;
-			unsigned char		probe_index;	/* Address in ->probe_alist */
-		};
+		struct afs_endpoint_state *probe;
+		struct afs_addr_list	*vl_probe;
 		struct afs_addr_list	*ret_alist;
 		struct afs_vldb_entry	*ret_vldb;
 		char			*ret_str;
 	};
+	unsigned char		probe_index;	/* Address in ->probe_alist */
 	struct afs_operation	*op;
 	unsigned int		server_index;
 	refcount_t		ref;
@@ -520,6 +520,32 @@ struct afs_vldb_entry {
 	u8			name[AFS_MAXVOLNAME + 1]; /* NUL-padded volume name */
 };
 
+/*
+ * Fileserver endpoint state.  The records the addresses of a fileserver's
+ * endpoints and the state and result of a round of probing on them.  This
+ * allows the rotation algorithm to access those results without them being
+ * erased by a subsequent round of probing.
+ */
+struct afs_endpoint_state {
+	struct rcu_head		rcu;
+	struct afs_addr_list	*addresses;	/* The addresses being probed */
+	unsigned long		responsive_set;	/* Bitset of responsive endpoints */
+	unsigned long		failed_set;	/* Bitset of endpoints we failed to probe */
+	refcount_t		ref;
+	unsigned int		server_id;	/* Debug ID of server */
+	unsigned int		probe_seq;	/* Probe sequence (from server::probe_counter) */
+
+	atomic_t		nr_probing;	/* Number of outstanding probes */
+	unsigned int		rtt;		/* Best RTT in uS (or UINT_MAX) */
+	s32			abort_code;
+	short			error;
+	bool			responded:1;
+	bool			is_yfs:1;
+	bool			not_yfs:1;
+	bool			local_failure:1;
+	bool			superseded:1;	/* Set if has been superseded */
+};
+
 /*
  * Record of fileserver with which we're actively communicating.
  */
@@ -530,7 +556,6 @@ struct afs_server {
 		struct afs_uuid	_uuid;
 	};
 
-	struct afs_addr_list	__rcu *addresses;
 	struct afs_cell		*cell;		/* Cell to which belongs (pins ref) */
 	struct rb_node		uuid_rb;	/* Link in net->fs_servers */
 	struct afs_server __rcu	*uuid_next;	/* Next server with same UUID */
@@ -568,19 +593,11 @@ struct afs_server {
 	unsigned		cb_s_break;	/* Break-everything counter. */
 
 	/* Probe state */
+	struct afs_endpoint_state __rcu *endpoint_state; /* Latest endpoint/probe state */
 	unsigned long		probed_at;	/* Time last probe was dispatched (jiffies) */
 	wait_queue_head_t	probe_wq;
-	atomic_t		probe_outstanding;
+	unsigned int		probe_counter;	/* Number of probes issued */
 	spinlock_t		probe_lock;
-	struct {
-		unsigned int	rtt;		/* Best RTT in uS (or UINT_MAX) */
-		u32		abort_code;
-		short		error;
-		bool		responded:1;
-		bool		is_yfs:1;
-		bool		not_yfs:1;
-		bool		local_failure:1;
-	} probe;
 };
 
 /*
@@ -883,7 +900,7 @@ struct afs_operation {
 	/* Fileserver iteration state */
 	struct afs_server_list	*server_list;	/* Current server list (pins ref) */
 	struct afs_server	*server;	/* Server we're using (ref pinned by server_list) */
-	struct afs_addr_list	*alist;		/* Current address list (pins ref) */
+	struct afs_endpoint_state *estate;	/* Current endpoint state (pins ref) */
 	struct afs_call		*call;
 	unsigned long		untried_servers; /* Bitmask of untried servers */
 	unsigned long		addr_tried;	/* Tried addresses */
@@ -1153,7 +1170,7 @@ extern void afs_fs_release_lock(struct afs_operation *);
 int afs_fs_give_up_all_callbacks(struct afs_net *net, struct afs_server *server,
 				 struct afs_address *addr, struct key *key);
 bool afs_fs_get_capabilities(struct afs_net *net, struct afs_server *server,
-			     struct afs_addr_list *alist, unsigned int addr_index,
+			     struct afs_endpoint_state *estate, unsigned int addr_index,
 			     struct key *key);
 extern void afs_fs_inline_bulk_status(struct afs_operation *);
 
@@ -1190,12 +1207,17 @@ static inline void afs_op_set_fid(struct afs_operation *op, unsigned int n,
 /*
  * fs_probe.c
  */
+struct afs_endpoint_state *afs_get_endpoint_state(struct afs_endpoint_state *estate,
+						  enum afs_estate_trace where);
+void afs_put_endpoint_state(struct afs_endpoint_state *estate, enum afs_estate_trace where);
 extern void afs_fileserver_probe_result(struct afs_call *);
-extern void afs_fs_probe_fileserver(struct afs_net *, struct afs_server *, struct key *, bool);
+void afs_fs_probe_fileserver(struct afs_net *net, struct afs_server *server,
+			     struct afs_addr_list *new_addrs, struct key *key);
 extern int afs_wait_for_fs_probes(struct afs_server_list *, unsigned long);
 extern void afs_probe_fileserver(struct afs_net *, struct afs_server *);
 extern void afs_fs_probe_dispatcher(struct work_struct *);
-extern int afs_wait_for_one_fs_probe(struct afs_server *, bool);
+int afs_wait_for_one_fs_probe(struct afs_server *server, struct afs_endpoint_state *estate,
+			      bool is_intr);
 extern void afs_fs_probe_cleanup(struct afs_net *);
 
 /*
@@ -1348,12 +1370,14 @@ extern int afs_protocol_error(struct afs_call *, enum afs_eproto_cause);
 static inline void afs_make_op_call(struct afs_operation *op, struct afs_call *call,
 				    gfp_t gfp)
 {
+	struct afs_addr_list *alist = op->estate->addresses;
+
 	op->call	= call;
 	op->type	= call->type;
 	call->op	= op;
 	call->key	= op->key;
 	call->intr	= !(op->flags & AFS_OPERATION_UNINTR);
-	call->peer	= rxrpc_kernel_get_peer(op->alist->addrs[op->addr_index].peer);
+	call->peer	= rxrpc_kernel_get_peer(alist->addrs[op->addr_index].peer);
 	call->service_id = op->server->service_id;
 	afs_make_call(call, gfp);
 }
@@ -1476,7 +1500,7 @@ extern void afs_manage_servers(struct work_struct *);
 extern void afs_servers_timer(struct timer_list *);
 extern void afs_fs_probe_timer(struct timer_list *);
 extern void __net_exit afs_purge_servers(struct afs_net *);
-extern bool afs_check_server_record(struct afs_operation *, struct afs_server *);
+bool afs_check_server_record(struct afs_operation *op, struct afs_server *server, struct key *key);
 
 static inline void afs_inc_servers_outstanding(struct afs_net *net)
 {
diff --git a/fs/afs/proc.c b/fs/afs/proc.c
index 944eb51e75a1..a138022d8e0d 100644
--- a/fs/afs/proc.c
+++ b/fs/afs/proc.c
@@ -424,8 +424,9 @@ static const struct seq_operations afs_proc_cell_vlservers_ops = {
  */
 static int afs_proc_servers_show(struct seq_file *m, void *v)
 {
-	struct afs_server *server;
+	struct afs_endpoint_state *estate;
 	struct afs_addr_list *alist;
+	struct afs_server *server;
 	unsigned long failed;
 	int i;
 
@@ -435,7 +436,8 @@ static int afs_proc_servers_show(struct seq_file *m, void *v)
 	}
 
 	server = list_entry(v, struct afs_server, proc_link);
-	alist = rcu_dereference(server->addresses);
+	estate = rcu_dereference(server->endpoint_state);
+	alist = estate->addresses;
 	seq_printf(m, "%pU %3d %3d %s\n",
 		   &server->uuid,
 		   refcount_read(&server->ref),
@@ -443,13 +445,14 @@ static int afs_proc_servers_show(struct seq_file *m, void *v)
 		   server->cell->name);
 	seq_printf(m, "  - info: fl=%lx rtt=%u brk=%x\n",
 		   server->flags, server->rtt, server->cb_s_break);
-	seq_printf(m, "  - probe: last=%d out=%d\n",
-		   (int)(jiffies - server->probed_at) / HZ,
-		   atomic_read(&server->probe_outstanding));
-	failed = alist->probe_failed;
-	seq_printf(m, "  - ALIST v=%u rsp=%lx f=%lx ap=%u\n",
-		   alist->version, alist->responded, alist->probe_failed,
-		   alist->addr_pref_version);
+	seq_printf(m, "  - probe: last=%d\n",
+		   (int)(jiffies - server->probed_at) / HZ);
+	failed = estate->failed_set;
+	seq_printf(m, "  - ESTATE pq=%x np=%u rsp=%lx f=%lx\n",
+		   estate->probe_seq, atomic_read(&estate->nr_probing),
+		   estate->responsive_set, estate->failed_set);
+	seq_printf(m, "  - ALIST v=%u ap=%u\n",
+		   alist->version, alist->addr_pref_version);
 	for (i = 0; i < alist->nr_addrs; i++) {
 		const struct afs_address *addr = &alist->addrs[i];
 
diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c
index 5423ac80f4e0..e8635f60b97d 100644
--- a/fs/afs/rotate.c
+++ b/fs/afs/rotate.c
@@ -109,10 +109,11 @@ static bool afs_sleep_and_retry(struct afs_operation *op)
  */
 bool afs_select_fileserver(struct afs_operation *op)
 {
-	struct afs_addr_list *alist = op->alist;
+	struct afs_endpoint_state *estate = op->estate;
+	struct afs_addr_list *alist;
 	struct afs_server *server;
 	struct afs_vnode *vnode = op->file[0].vnode;
-	unsigned long set;
+	unsigned long set, failed;
 	unsigned int rtt;
 	s32 abort_code = op->call_abort_code;
 	int error = op->call_error, addr_index, i;
@@ -133,7 +134,7 @@ bool afs_select_fileserver(struct afs_operation *op)
 	if (op->nr_iterations == 0)
 		goto start;
 
-	WRITE_ONCE(alist->addrs[op->addr_index].last_error, error);
+	WRITE_ONCE(estate->addresses->addrs[op->addr_index].last_error, error);
 
 	/* Evaluate the result of the previous operation, if there was one. */
 	switch (op->call_error) {
@@ -401,14 +402,14 @@ bool afs_select_fileserver(struct afs_operation *op)
 
 restart_from_beginning:
 	_debug("restart");
-	afs_put_addrlist(alist, afs_alist_trace_put_restart_rotate);
-	alist = op->alist = NULL;
+	afs_put_endpoint_state(estate, afs_estate_trace_put_restart_rotate);
+	estate = op->estate = NULL;
 	op->server = NULL;
 	afs_put_serverlist(op->net, op->server_list);
 	op->server_list = NULL;
 start:
 	_debug("start");
-	ASSERTCMP(alist, ==, NULL);
+	ASSERTCMP(estate, ==, NULL);
 	/* See if we need to do an update of the volume record.  Note that the
 	 * volume may have moved or even have been deleted.
 	 */
@@ -425,7 +426,7 @@ start:
 
 pick_server:
 	_debug("pick [%lx]", op->untried_servers);
-	ASSERTCMP(alist, ==, NULL);
+	ASSERTCMP(estate, ==, NULL);
 
 	error = afs_wait_for_fs_probes(op->server_list, op->untried_servers);
 	if (error < 0) {
@@ -452,9 +453,9 @@ pick_server:
 		if (!test_bit(i, &op->untried_servers) ||
 		    !test_bit(AFS_SERVER_FL_RESPONDING, &s->flags))
 			continue;
-		if (s->probe.rtt <= rtt) {
+		if (s->rtt <= rtt) {
 			op->server_index = i;
-			rtt = s->probe.rtt;
+			rtt = s->rtt;
 		}
 	}
 
@@ -469,10 +470,10 @@ selected_server:
 	 * check it, create a callback intercept, find its address list and
 	 * probe its capabilities before we use it.
 	 */
-	ASSERTCMP(alist, ==, NULL);
+	ASSERTCMP(estate, ==, NULL);
 	server = op->server_list->servers[op->server_index].server;
 
-	if (!afs_check_server_record(op, server))
+	if (!afs_check_server_record(op, server, op->key))
 		goto failed;
 
 	_debug("USING SERVER: %pU", &server->uuid);
@@ -488,9 +489,9 @@ selected_server:
 	}
 
 	read_lock(&server->fs_lock);
-	alist = rcu_dereference_protected(server->addresses,
-					  lockdep_is_held(&server->fs_lock));
-	op->alist = afs_get_addrlist(alist, afs_alist_trace_get_fsrotate_set);
+	estate = rcu_dereference_protected(server->endpoint_state,
+					   lockdep_is_held(&server->fs_lock));
+	op->estate = afs_get_endpoint_state(estate, afs_estate_trace_get_fsrotate_set);
 	read_unlock(&server->fs_lock);
 
 retry_server:
@@ -501,18 +502,20 @@ iterate_address:
 	/* Iterate over the current server's address list to try and find an
 	 * address on which it will respond to us.
 	 */
-	set = READ_ONCE(alist->responded);
-	set &= ~(READ_ONCE(alist->probe_failed) | op->addr_tried);
+	set = READ_ONCE(estate->responsive_set);
+	failed = READ_ONCE(estate->failed_set);
+	_debug("iterate ES=%x rs=%lx fs=%lx", estate->probe_seq, set, failed);
+	set &= ~(failed | op->addr_tried);
 	if (!set)
 		goto out_of_addresses;
 
+	alist = estate->addresses;
 	addr_index = READ_ONCE(alist->preferred);
 	if (!test_bit(addr_index, &set))
 		addr_index = __ffs(set);
 
 	op->addr_index = addr_index;
 	set_bit(addr_index, &op->addr_tried);
-	op->alist = alist;
 
 	op->call_responded = false;
 	_debug("address [%u] %u/%u %pISp",
@@ -527,8 +530,8 @@ out_of_addresses:
 	 */
 	afs_probe_fileserver(op->net, op->server);
 	if (op->flags & AFS_OPERATION_RETRY_SERVER) {
-		error = afs_wait_for_one_fs_probe(
-			op->server, !(op->flags & AFS_OPERATION_UNINTR));
+		error = afs_wait_for_one_fs_probe(op->server, estate,
+						  !(op->flags & AFS_OPERATION_UNINTR));
 		switch (error) {
 		case 0:
 			op->flags &= ~AFS_OPERATION_RETRY_SERVER;
@@ -544,13 +547,14 @@ out_of_addresses:
 
 next_server:
 	_debug("next");
-	ASSERT(alist);
+	ASSERT(estate);
+	alist = estate->addresses;
 	if (op->call_responded &&
 	    op->addr_index != READ_ONCE(alist->preferred) &&
 	    test_bit(alist->preferred, &op->addr_tried))
 		WRITE_ONCE(alist->preferred, op->addr_index);
-	afs_put_addrlist(alist, afs_alist_trace_put_next_server);
-	alist = op->alist = NULL;
+	afs_put_endpoint_state(estate, afs_estate_trace_put_next_server);
+	estate = op->estate = NULL;
 	goto pick_server;
 
 no_more_servers:
@@ -560,23 +564,28 @@ no_more_servers:
 	if (op->flags & AFS_OPERATION_VBUSY)
 		goto restart_from_beginning;
 
+	rcu_read_lock();
 	for (i = 0; i < op->server_list->nr_servers; i++) {
+		struct afs_endpoint_state *estate;
 		struct afs_server *s = op->server_list->servers[i].server;
 
-		error = READ_ONCE(s->probe.error);
+		estate = rcu_dereference(s->endpoint_state);
+		error = READ_ONCE(estate->error);
 		if (error < 0)
-			afs_op_accumulate_error(op, error, s->probe.abort_code);
+			afs_op_accumulate_error(op, error, estate->abort_code);
 	}
+	rcu_read_unlock();
 
 failed:
 	op->flags |= AFS_OPERATION_STOP;
-	if (alist) {
+	if (estate) {
+		alist = estate->addresses;
 		if (op->call_responded &&
 		    op->addr_index != READ_ONCE(alist->preferred) &&
 		    test_bit(alist->preferred, &op->addr_tried))
 			WRITE_ONCE(alist->preferred, op->addr_index);
-		afs_put_addrlist(alist, afs_alist_trace_put_op_failed);
-		op->alist = NULL;
+		afs_put_endpoint_state(estate, afs_estate_trace_put_op_failed);
+		op->estate = NULL;
 	}
 	_leave(" = f [failed %d]", afs_op_error(op));
 	return false;
@@ -607,27 +616,30 @@ void afs_dump_edestaddrreq(const struct afs_operation *op)
 
 	if (op->server_list) {
 		const struct afs_server_list *sl = op->server_list;
+
 		pr_notice("FC: SL nr=%u pr=%u vnov=%hx\n",
 			  sl->nr_servers, sl->preferred, sl->vnovol_mask);
 		for (i = 0; i < sl->nr_servers; i++) {
 			const struct afs_server *s = sl->servers[i].server;
+			const struct afs_endpoint_state *e =
+				rcu_dereference(s->endpoint_state);
+			const struct afs_addr_list *a = e->addresses;
+
 			pr_notice("FC: server fl=%lx av=%u %pU\n",
 				  s->flags, s->addr_version, &s->uuid);
-			if (s->addresses) {
-				const struct afs_addr_list *a =
-					rcu_dereference(s->addresses);
+			pr_notice("FC:  - pq=%x R=%lx F=%lx\n",
+				  e->probe_seq, e->responsive_set, e->failed_set);
+			if (a) {
 				pr_notice("FC:  - av=%u nr=%u/%u/%u pr=%u\n",
 					  a->version,
 					  a->nr_ipv4, a->nr_addrs, a->max_addrs,
 					  a->preferred);
-				pr_notice("FC:  - R=%lx F=%lx\n",
-					  a->responded, a->probe_failed);
-				if (a == op->alist)
+				if (a == e->addresses)
 					pr_notice("FC:  - current\n");
 			}
 		}
 	}
 
-	pr_notice("AC: t=%lx ax=%u\n", op->addr_tried, op->addr_index);
+	pr_notice("AC: t=%lx ax=%d\n", op->addr_tried, op->addr_index);
 	rcu_read_unlock();
 }
diff --git a/fs/afs/server.c b/fs/afs/server.c
index 62d453365689..281625c71aff 100644
--- a/fs/afs/server.c
+++ b/fs/afs/server.c
@@ -23,6 +23,7 @@ static void __afs_put_server(struct afs_net *, struct afs_server *);
  */
 struct afs_server *afs_find_server(struct afs_net *net, const struct rxrpc_peer *peer)
 {
+	const struct afs_endpoint_state *estate;
 	const struct afs_addr_list *alist;
 	struct afs_server *server = NULL;
 	unsigned int i;
@@ -38,7 +39,8 @@ struct afs_server *afs_find_server(struct afs_net *net, const struct rxrpc_peer
 		read_seqbegin_or_lock(&net->fs_addr_lock, &seq);
 
 		hlist_for_each_entry_rcu(server, &net->fs_addresses6, addr6_link) {
-			alist = rcu_dereference(server->addresses);
+			estate = rcu_dereference(server->endpoint_state);
+			alist = estate->addresses;
 			for (i = 0; i < alist->nr_addrs; i++)
 				if (alist->addrs[i].peer == peer)
 					goto found;
@@ -111,6 +113,7 @@ struct afs_server *afs_find_server_by_uuid(struct afs_net *net, const uuid_t *uu
 static struct afs_server *afs_install_server(struct afs_cell *cell,
 					     struct afs_server *candidate)
 {
+	const struct afs_endpoint_state *estate;
 	const struct afs_addr_list *alist;
 	struct afs_server *server, *next;
 	struct afs_net *net = cell->net;
@@ -162,8 +165,9 @@ static struct afs_server *afs_install_server(struct afs_cell *cell,
 
 added_dup:
 	write_seqlock(&net->fs_addr_lock);
-	alist = rcu_dereference_protected(server->addresses,
-					  lockdep_is_held(&net->fs_addr_lock.lock));
+	estate = rcu_dereference_protected(server->endpoint_state,
+					   lockdep_is_held(&net->fs_addr_lock.lock));
+	alist = estate->addresses;
 
 	/* Secondly, if the server has any IPv4 and/or IPv6 addresses, install
 	 * it in the IPv4 and/or IPv6 reverse-map lists.
@@ -193,6 +197,7 @@ static struct afs_server *afs_alloc_server(struct afs_cell *cell,
 					   const uuid_t *uuid,
 					   struct afs_addr_list *alist)
 {
+	struct afs_endpoint_state *estate;
 	struct afs_server *server;
 	struct afs_net *net = cell->net;
 
@@ -202,10 +207,13 @@ static struct afs_server *afs_alloc_server(struct afs_cell *cell,
 	if (!server)
 		goto enomem;
 
+	estate = kzalloc(sizeof(struct afs_endpoint_state), GFP_KERNEL);
+	if (!estate)
+		goto enomem_server;
+
 	refcount_set(&server->ref, 1);
 	atomic_set(&server->active, 1);
 	server->debug_id = atomic_inc_return(&afs_server_debug_id);
-	RCU_INIT_POINTER(server->addresses, alist);
 	server->addr_version = alist->version;
 	server->uuid = *uuid;
 	rwlock_init(&server->fs_lock);
@@ -217,11 +225,23 @@ static struct afs_server *afs_alloc_server(struct afs_cell *cell,
 	server->rtt = UINT_MAX;
 	server->service_id = FS_SERVICE;
 
+	server->probe_counter = 1;
+	server->probed_at = jiffies - LONG_MAX / 2;
+	refcount_set(&estate->ref, 1);
+	estate->addresses = alist;
+	estate->server_id = server->debug_id;
+	estate->probe_seq = 1;
+	rcu_assign_pointer(server->endpoint_state, estate);
+
 	afs_inc_servers_outstanding(net);
 	trace_afs_server(server->debug_id, 1, 1, afs_server_trace_alloc);
+	trace_afs_estate(estate->server_id, estate->probe_seq, refcount_read(&estate->ref),
+			 afs_estate_trace_alloc_server);
 	_leave(" = %p", server);
 	return server;
 
+enomem_server:
+	kfree(server);
 enomem:
 	_leave(" = NULL [nomem]");
 	return NULL;
@@ -289,7 +309,7 @@ struct afs_server *afs_lookup_server(struct afs_cell *cell, struct key *key,
 		 * on the fileserver.  This will make sure the repeat-probing
 		 * service is started.
 		 */
-		afs_fs_probe_fileserver(cell->net, server, key, true);
+		afs_fs_probe_fileserver(cell->net, server, alist, key);
 	}
 
 	return server;
@@ -422,8 +442,8 @@ static void afs_server_rcu(struct rcu_head *rcu)
 
 	trace_afs_server(server->debug_id, refcount_read(&server->ref),
 			 atomic_read(&server->active), afs_server_trace_free);
-	afs_put_addrlist(rcu_access_pointer(server->addresses),
-			 afs_alist_trace_put_server);
+	afs_put_endpoint_state(rcu_access_pointer(server->endpoint_state),
+			       afs_estate_trace_put_server);
 	kfree(server);
 }
 
@@ -435,7 +455,8 @@ static void __afs_put_server(struct afs_net *net, struct afs_server *server)
 
 static void afs_give_up_callbacks(struct afs_net *net, struct afs_server *server)
 {
-	struct afs_addr_list *alist = rcu_access_pointer(server->addresses);
+	struct afs_endpoint_state *estate = rcu_access_pointer(server->endpoint_state);
+	struct afs_addr_list *alist = estate->addresses;
 
 	afs_fs_give_up_all_callbacks(net, server, &alist->addrs[alist->preferred], NULL);
 }
@@ -607,9 +628,12 @@ void afs_purge_servers(struct afs_net *net)
  * Get an update for a server's address list.
  */
 static noinline bool afs_update_server_record(struct afs_operation *op,
-					      struct afs_server *server)
+					      struct afs_server *server,
+					      struct key *key)
 {
-	struct afs_addr_list *alist, *discard;
+	struct afs_endpoint_state *estate;
+	struct afs_addr_list *alist;
+	bool has_addrs;
 
 	_enter("");
 
@@ -619,10 +643,15 @@ static noinline bool afs_update_server_record(struct afs_operation *op,
 
 	alist = afs_vl_lookup_addrs(op->volume->cell, op->key, &server->uuid);
 	if (IS_ERR(alist)) {
+		rcu_read_lock();
+		estate = rcu_dereference(server->endpoint_state);
+		has_addrs = estate->addresses;
+		rcu_read_unlock();
+
 		if ((PTR_ERR(alist) == -ERESTARTSYS ||
 		     PTR_ERR(alist) == -EINTR) &&
 		    (op->flags & AFS_OPERATION_UNINTR) &&
-		    server->addresses) {
+		    has_addrs) {
 			_leave(" = t [intr]");
 			return true;
 		}
@@ -631,17 +660,10 @@ static noinline bool afs_update_server_record(struct afs_operation *op,
 		return false;
 	}
 
-	discard = alist;
-	if (server->addr_version != alist->version) {
-		write_lock(&server->fs_lock);
-		discard = rcu_dereference_protected(server->addresses,
-						    lockdep_is_held(&server->fs_lock));
-		rcu_assign_pointer(server->addresses, alist);
-		server->addr_version = alist->version;
-		write_unlock(&server->fs_lock);
-	}
+	if (server->addr_version != alist->version)
+		afs_fs_probe_fileserver(op->net, server, alist, key);
 
-	afs_put_addrlist(discard, afs_alist_trace_put_server_update);
+	afs_put_addrlist(alist, afs_alist_trace_put_server_update);
 	_leave(" = t");
 	return true;
 }
@@ -649,7 +671,8 @@ static noinline bool afs_update_server_record(struct afs_operation *op,
 /*
  * See if a server's address list needs updating.
  */
-bool afs_check_server_record(struct afs_operation *op, struct afs_server *server)
+bool afs_check_server_record(struct afs_operation *op, struct afs_server *server,
+			     struct key *key)
 {
 	bool success;
 	int ret, retries = 0;
@@ -669,7 +692,7 @@ retry:
 update:
 	if (!test_and_set_bit_lock(AFS_SERVER_FL_UPDATING, &server->flags)) {
 		clear_bit(AFS_SERVER_FL_NEEDS_UPDATE, &server->flags);
-		success = afs_update_server_record(op, server);
+		success = afs_update_server_record(op, server, key);
 		clear_bit_unlock(AFS_SERVER_FL_UPDATING, &server->flags);
 		wake_up_bit(&server->flags, AFS_SERVER_FL_UPDATING);
 		_leave(" = %d", success);
diff --git a/fs/afs/vl_alias.c b/fs/afs/vl_alias.c
index 89cadd9a69e1..43788d0c18e8 100644
--- a/fs/afs/vl_alias.c
+++ b/fs/afs/vl_alias.c
@@ -41,8 +41,8 @@ static int afs_compare_fs_alists(const struct afs_server *server_a,
 	const struct afs_addr_list *la, *lb;
 	int a = 0, b = 0, addr_matches = 0;
 
-	la = rcu_dereference(server_a->addresses);
-	lb = rcu_dereference(server_b->addresses);
+	la = rcu_dereference(server_a->endpoint_state)->addresses;
+	lb = rcu_dereference(server_b->endpoint_state)->addresses;
 
 	while (a < la->nr_addrs && b < lb->nr_addrs) {
 		unsigned long pa = (unsigned long)la->addrs[a].peer;
diff --git a/fs/afs/vl_probe.c b/fs/afs/vl_probe.c
index b128dc3d8af7..3d2e0c925460 100644
--- a/fs/afs/vl_probe.c
+++ b/fs/afs/vl_probe.c
@@ -46,7 +46,7 @@ static void afs_done_one_vl_probe(struct afs_vlserver *server, bool wake_up)
  */
 void afs_vlserver_probe_result(struct afs_call *call)
 {
-	struct afs_addr_list *alist = call->probe_alist;
+	struct afs_addr_list *alist = call->vl_probe;
 	struct afs_vlserver *server = call->vlserver;
 	struct afs_address *addr = &alist->addrs[call->probe_index];
 	unsigned int server_index = call->server_index;
diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c
index 39a0b7614d05..cef02a265edc 100644
--- a/fs/afs/vlclient.c
+++ b/fs/afs/vlclient.c
@@ -371,7 +371,7 @@ static int afs_deliver_vl_get_capabilities(struct afs_call *call)
 
 static void afs_destroy_vl_get_capabilities(struct afs_call *call)
 {
-	afs_put_addrlist(call->probe_alist, afs_alist_trace_put_vlgetcaps);
+	afs_put_addrlist(call->vl_probe, afs_alist_trace_put_vlgetcaps);
 	afs_put_vlserver(call->net, call->vlserver);
 	afs_flat_call_destructor(call);
 }
@@ -414,7 +414,7 @@ struct afs_call *afs_vl_get_capabilities(struct afs_net *net,
 	call->vlserver = afs_get_vlserver(server);
 	call->server_index = server_index;
 	call->peer = rxrpc_kernel_get_peer(alist->addrs[addr_index].peer);
-	call->probe_alist = afs_get_addrlist(alist, afs_alist_trace_get_vlgetcaps);
+	call->vl_probe = afs_get_addrlist(alist, afs_alist_trace_get_vlgetcaps);
 	call->probe_index = addr_index;
 	call->service_id = server->service_id;
 	call->upgrade = true;
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index f1815b3dafb0..cf2fa4fddd5b 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -204,22 +204,14 @@ enum yfs_cm_operation {
 
 #define afs_alist_traces \
 	EM(afs_alist_trace_alloc,		"ALLOC     ") \
-	EM(afs_alist_trace_get_getcaps,		"GET getcap") \
-	EM(afs_alist_trace_get_fsrotate_set,	"GET fs-rot") \
-	EM(afs_alist_trace_get_probe,		"GET probe ") \
+	EM(afs_alist_trace_get_estate,		"GET estate") \
 	EM(afs_alist_trace_get_vlgetcaps,	"GET vgtcap") \
 	EM(afs_alist_trace_get_vlprobe,		"GET vprobe") \
 	EM(afs_alist_trace_get_vlrotate_set,	"GET vl-rot") \
+	EM(afs_alist_trace_put_estate,		"PUT estate") \
 	EM(afs_alist_trace_put_getaddru,	"PUT GtAdrU") \
-	EM(afs_alist_trace_put_getcaps,		"PUT getcap") \
-	EM(afs_alist_trace_put_next_server,	"PUT nx-srv") \
-	EM(afs_alist_trace_put_op_failed,	"PUT op-fai") \
-	EM(afs_alist_trace_put_operation,	"PUT op    ") \
 	EM(afs_alist_trace_put_parse_empty,	"PUT p-empt") \
 	EM(afs_alist_trace_put_parse_error,	"PUT p-err ") \
-	EM(afs_alist_trace_put_probe,		"PUT probe ") \
-	EM(afs_alist_trace_put_restart_rotate,	"PUT rstrot") \
-	EM(afs_alist_trace_put_server,		"PUT server") \
 	EM(afs_alist_trace_put_server_dup,	"PUT sv-dup") \
 	EM(afs_alist_trace_put_server_oom,	"PUT sv-oom") \
 	EM(afs_alist_trace_put_server_update,	"PUT sv-upd") \
@@ -233,6 +225,20 @@ enum yfs_cm_operation {
 	EM(afs_alist_trace_put_vlserver_old,	"PUT vs-old") \
 	E_(afs_alist_trace_free,		"FREE      ")
 
+#define afs_estate_traces \
+	EM(afs_estate_trace_alloc_probe,	"ALLOC prob") \
+	EM(afs_estate_trace_alloc_server,	"ALLOC srvr") \
+	EM(afs_estate_trace_get_fsrotate_set,	"GET fs-rot") \
+	EM(afs_estate_trace_get_getcaps,	"GET getcap") \
+	EM(afs_estate_trace_put_getcaps,	"PUT getcap") \
+	EM(afs_estate_trace_put_next_server,	"PUT nx-srv") \
+	EM(afs_estate_trace_put_op_failed,	"PUT op-fai") \
+	EM(afs_estate_trace_put_operation,	"PUT op    ") \
+	EM(afs_estate_trace_put_probe,		"PUT probe ") \
+	EM(afs_estate_trace_put_restart_rotate,	"PUT rstrot") \
+	EM(afs_estate_trace_put_server,		"PUT server") \
+	E_(afs_estate_trace_free,		"FREE      ")
+
 #define afs_fs_operations \
 	EM(afs_FS_FetchData,			"FS.FetchData") \
 	EM(afs_FS_FetchStatus,			"FS.FetchStatus") \
@@ -458,6 +464,7 @@ enum afs_cell_trace		{ afs_cell_traces } __mode(byte);
 enum afs_edit_dir_op		{ afs_edit_dir_ops } __mode(byte);
 enum afs_edit_dir_reason	{ afs_edit_dir_reasons } __mode(byte);
 enum afs_eproto_cause		{ afs_eproto_causes } __mode(byte);
+enum afs_estate_trace		{ afs_estate_traces } __mode(byte);
 enum afs_file_error		{ afs_file_errors } __mode(byte);
 enum afs_flock_event		{ afs_flock_events } __mode(byte);
 enum afs_flock_operation	{ afs_flock_operations } __mode(byte);
@@ -486,6 +493,7 @@ yfs_cm_operations;
 afs_edit_dir_ops;
 afs_edit_dir_reasons;
 afs_eproto_causes;
+afs_estate_traces;
 afs_io_errors;
 afs_file_errors;
 afs_flock_types;
@@ -1387,14 +1395,43 @@ TRACE_EVENT(afs_alist,
 		      __entry->ref)
 	    );
 
+TRACE_EVENT(afs_estate,
+	    TP_PROTO(unsigned int server_debug_id, unsigned int estate_debug_id,
+		     int ref, enum afs_estate_trace reason),
+
+	    TP_ARGS(server_debug_id, estate_debug_id, ref, reason),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,		server)
+		    __field(unsigned int,		estate)
+		    __field(int,			ref)
+		    __field(int,			active)
+		    __field(int,			reason)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->server = server_debug_id;
+		    __entry->estate = estate_debug_id;
+		    __entry->ref = ref;
+		    __entry->reason = reason;
+			   ),
+
+	    TP_printk("ES=%08x[%x] %s r=%d",
+		      __entry->server,
+		      __entry->estate,
+		      __print_symbolic(__entry->reason, afs_estate_traces),
+		      __entry->ref)
+	    );
+
 TRACE_EVENT(afs_fs_probe,
-	    TP_PROTO(struct afs_server *server, bool tx, struct afs_addr_list *alist,
+	    TP_PROTO(struct afs_server *server, bool tx, struct afs_endpoint_state *estate,
 		     unsigned int addr_index, int error, s32 abort_code, unsigned int rtt_us),
 
-	    TP_ARGS(server, tx, alist, addr_index, error, abort_code, rtt_us),
+	    TP_ARGS(server, tx, estate, addr_index, error, abort_code, rtt_us),
 
 	    TP_STRUCT__entry(
 		    __field(unsigned int,		server)
+		    __field(unsigned int,		estate)
 		    __field(bool,			tx)
 		    __field(u16,			addr_index)
 		    __field(short,			error)
@@ -1404,7 +1441,9 @@ TRACE_EVENT(afs_fs_probe,
 			     ),
 
 	    TP_fast_assign(
+		    struct afs_addr_list *alist = estate->addresses;
 		    __entry->server = server->debug_id;
+		    __entry->estate = estate->probe_seq;
 		    __entry->tx = tx;
 		    __entry->addr_index = addr_index;
 		    __entry->error = error;
@@ -1414,9 +1453,9 @@ TRACE_EVENT(afs_fs_probe,
 			   sizeof(__entry->srx));
 			   ),
 
-	    TP_printk("s=%08x %s ax=%u e=%d ac=%d rtt=%d %pISpc",
-		      __entry->server, __entry->tx ? "tx" : "rx", __entry->addr_index,
-		      __entry->error, __entry->abort_code, __entry->rtt_us,
+	    TP_printk("s=%08x %s pq=%x ax=%u e=%d ac=%d rtt=%d %pISpc",
+		      __entry->server, __entry->tx ? "tx" : "rx", __entry->estate,
+		      __entry->addr_index, __entry->error, __entry->abort_code, __entry->rtt_us,
 		      &__entry->srx.transport)
 	    );
 
-- 
cgit v1.2.3


From 32222f09782f1894fcfc37f6505ca676a6f4d1d6 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 7 Nov 2023 17:59:33 +0000
Subject: afs: Apply server breaks to mmap'd files in the call processor

Apply server breaks to mmap'd files that are being used from that server
from the call processor work function rather than punting it off to a
workqueue.  The work item, afs_server_init_callback(), then bumps each
individual inode off to its own work item introducing a potentially lengthy
delay.  This reduces that delay at the cost of extending the amount of time
we delay replying to the CB.InitCallBack3 notification RPC from the server.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
---
 fs/afs/callback.c          | 33 +++++++++++++++++++--------------
 fs/afs/cell.c              |  2 +-
 fs/afs/internal.h          |  4 +---
 fs/afs/server.c            |  2 --
 fs/afs/server_list.c       | 22 +++++++++++-----------
 include/trace/events/afs.h |  2 ++
 6 files changed, 34 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/fs/afs/callback.c b/fs/afs/callback.c
index 90f9b2a46ff4..f67e88076761 100644
--- a/fs/afs/callback.c
+++ b/fs/afs/callback.c
@@ -33,9 +33,8 @@ void afs_invalidate_mmap_work(struct work_struct *work)
 	unmap_mapping_pages(vnode->netfs.inode.i_mapping, 0, 0, false);
 }
 
-void afs_server_init_callback_work(struct work_struct *work)
+static void afs_server_init_callback(struct afs_server *server)
 {
-	struct afs_server *server = container_of(work, struct afs_server, initcb_work);
 	struct afs_vnode *vnode;
 	struct afs_cell *cell = server->cell;
 
@@ -57,15 +56,19 @@ void afs_server_init_callback_work(struct work_struct *work)
  */
 void afs_init_callback_state(struct afs_server *server)
 {
-	rcu_read_lock();
+	struct afs_cell *cell = server->cell;
+
+	down_read(&cell->vs_lock);
+
 	do {
 		server->cb_s_break++;
 		atomic_inc(&server->cell->fs_s_break);
 		if (!list_empty(&server->cell->fs_open_mmaps))
-			queue_work(system_unbound_wq, &server->initcb_work);
+			afs_server_init_callback(server);
 
 	} while ((server = rcu_dereference(server->uuid_next)));
-	rcu_read_unlock();
+
+	up_read(&cell->vs_lock);
 }
 
 /*
@@ -112,7 +115,7 @@ static struct afs_volume *afs_lookup_volume_rcu(struct afs_cell *cell,
 	struct rb_node *p;
 	int seq = 1;
 
-	do {
+	for (;;) {
 		/* Unfortunately, rbtree walking doesn't give reliable results
 		 * under just the RCU read lock, so we have to check for
 		 * changes.
@@ -133,7 +136,12 @@ static struct afs_volume *afs_lookup_volume_rcu(struct afs_cell *cell,
 			volume = NULL;
 		}
 
-	} while (need_seqretry(&cell->volume_lock, seq));
+		if (volume && afs_try_get_volume(volume, afs_volume_trace_get_callback))
+			break;
+		if (!need_seqretry(&cell->volume_lock, seq))
+			break;
+		seq |= 1; /* Want a lock next time */
+	}
 
 	done_seqretry(&cell->volume_lock, seq);
 	return volume;
@@ -188,12 +196,11 @@ static void afs_break_some_callbacks(struct afs_server *server,
 	afs_volid_t vid = cbb->fid.vid;
 	size_t i;
 
+	rcu_read_lock();
 	volume = afs_lookup_volume_rcu(server->cell, vid);
-
 	/* TODO: Find all matching volumes if we couldn't match the server and
 	 * break them anyway.
 	 */
-
 	for (i = *_count; i > 0; cbb++, i--) {
 		if (cbb->fid.vid == vid) {
 			_debug("- Fid { vl=%08llx n=%llu u=%u }",
@@ -207,6 +214,9 @@ static void afs_break_some_callbacks(struct afs_server *server,
 			*residue++ = *cbb;
 		}
 	}
+
+	rcu_read_unlock();
+	afs_put_volume(volume, afs_volume_trace_put_callback);
 }
 
 /*
@@ -219,11 +229,6 @@ void afs_break_callbacks(struct afs_server *server, size_t count,
 
 	ASSERT(server != NULL);
 
-	rcu_read_lock();
-
 	while (count > 0)
 		afs_break_some_callbacks(server, callbacks, &count);
-
-	rcu_read_unlock();
-	return;
 }
diff --git a/fs/afs/cell.c b/fs/afs/cell.c
index 55ee194e31ff..e4b6a80763d7 100644
--- a/fs/afs/cell.c
+++ b/fs/afs/cell.c
@@ -161,7 +161,7 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net,
 	refcount_set(&cell->ref, 1);
 	atomic_set(&cell->active, 0);
 	INIT_WORK(&cell->manager, afs_manage_cell_work);
-	spin_lock_init(&cell->vs_lock);
+	init_rwsem(&cell->vs_lock);
 	cell->volumes = RB_ROOT;
 	INIT_HLIST_HEAD(&cell->proc_volumes);
 	seqlock_init(&cell->volume_lock);
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 4a3d946b1d2a..5ae4ca999d65 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -414,7 +414,7 @@ struct afs_cell {
 	unsigned int		debug_id;
 
 	/* The volumes belonging to this cell */
-	spinlock_t		vs_lock;	/* Lock for server->volumes */
+	struct rw_semaphore	vs_lock;	/* Lock for server->volumes */
 	struct rb_root		volumes;	/* Tree of volumes on this server */
 	struct hlist_head	proc_volumes;	/* procfs volume list */
 	seqlock_t		volume_lock;	/* For volumes */
@@ -566,7 +566,6 @@ struct afs_server {
 	struct hlist_node	addr6_link;	/* Link in net->fs_addresses6 */
 	struct hlist_node	proc_link;	/* Link in net->fs_proc */
 	struct list_head	volumes;	/* RCU list of afs_server_entry objects */
-	struct work_struct	initcb_work;	/* Work for CB.InitCallBackState* */
 	struct afs_server	*gc_next;	/* Next server in manager's list */
 	time64_t		unuse_time;	/* Time at which last unused */
 	unsigned long		flags;
@@ -1041,7 +1040,6 @@ void afs_get_address_preferences(struct afs_net *net, struct afs_addr_list *alis
  * callback.c
  */
 extern void afs_invalidate_mmap_work(struct work_struct *);
-extern void afs_server_init_callback_work(struct work_struct *work);
 extern void afs_init_callback_state(struct afs_server *);
 extern void __afs_break_callback(struct afs_vnode *, enum afs_cb_break_reason);
 extern void afs_break_callback(struct afs_vnode *, enum afs_cb_break_reason);
diff --git a/fs/afs/server.c b/fs/afs/server.c
index db2f66b11b40..e169121f603e 100644
--- a/fs/afs/server.c
+++ b/fs/afs/server.c
@@ -218,7 +218,6 @@ static struct afs_server *afs_alloc_server(struct afs_cell *cell,
 	server->uuid = *uuid;
 	rwlock_init(&server->fs_lock);
 	INIT_LIST_HEAD(&server->volumes);
-	INIT_WORK(&server->initcb_work, afs_server_init_callback_work);
 	init_waitqueue_head(&server->probe_wq);
 	INIT_LIST_HEAD(&server->probe_link);
 	spin_lock_init(&server->probe_lock);
@@ -470,7 +469,6 @@ static void afs_destroy_server(struct afs_net *net, struct afs_server *server)
 	if (test_bit(AFS_SERVER_FL_MAY_HAVE_CB, &server->flags))
 		afs_give_up_callbacks(net, server);
 
-	flush_work(&server->initcb_work);
 	afs_put_server(net, server, afs_server_trace_destroy);
 }
 
diff --git a/fs/afs/server_list.c b/fs/afs/server_list.c
index 4d6369477f54..cfd900eb09ed 100644
--- a/fs/afs/server_list.c
+++ b/fs/afs/server_list.c
@@ -136,7 +136,7 @@ void afs_attach_volume_to_servers(struct afs_volume *volume, struct afs_server_l
 	struct list_head *p;
 	unsigned int i;
 
-	spin_lock(&volume->cell->vs_lock);
+	down_write(&volume->cell->vs_lock);
 
 	for (i = 0; i < slist->nr_servers; i++) {
 		se = &slist->servers[i];
@@ -147,11 +147,11 @@ void afs_attach_volume_to_servers(struct afs_volume *volume, struct afs_server_l
 			if (volume->vid <= pe->volume->vid)
 				break;
 		}
-		list_add_tail_rcu(&se->slink, p);
+		list_add_tail(&se->slink, p);
 	}
 
 	slist->attached = true;
-	spin_unlock(&volume->cell->vs_lock);
+	up_write(&volume->cell->vs_lock);
 }
 
 /*
@@ -164,7 +164,7 @@ void afs_reattach_volume_to_servers(struct afs_volume *volume, struct afs_server
 {
 	unsigned int n = 0, o = 0;
 
-	spin_lock(&volume->cell->vs_lock);
+	down_write(&volume->cell->vs_lock);
 
 	while (n < new->nr_servers || o < old->nr_servers) {
 		struct afs_server_entry *pn = n < new->nr_servers ? &new->servers[n] : NULL;
@@ -174,7 +174,7 @@ void afs_reattach_volume_to_servers(struct afs_volume *volume, struct afs_server
 		int diff;
 
 		if (pn && po && pn->server == po->server) {
-			list_replace_rcu(&po->slink, &pn->slink);
+			list_replace(&po->slink, &pn->slink);
 			n++;
 			o++;
 			continue;
@@ -192,15 +192,15 @@ void afs_reattach_volume_to_servers(struct afs_volume *volume, struct afs_server
 				if (volume->vid <= s->volume->vid)
 					break;
 			}
-			list_add_tail_rcu(&pn->slink, p);
+			list_add_tail(&pn->slink, p);
 			n++;
 		} else {
-			list_del_rcu(&po->slink);
+			list_del(&po->slink);
 			o++;
 		}
 	}
 
-	spin_unlock(&volume->cell->vs_lock);
+	up_write(&volume->cell->vs_lock);
 }
 
 /*
@@ -213,11 +213,11 @@ void afs_detach_volume_from_servers(struct afs_volume *volume, struct afs_server
 	if (!slist->attached)
 		return;
 
-	spin_lock(&volume->cell->vs_lock);
+	down_write(&volume->cell->vs_lock);
 
 	for (i = 0; i < slist->nr_servers; i++)
-		list_del_rcu(&slist->servers[i].slink);
+		list_del(&slist->servers[i].slink);
 
 	slist->attached = false;
-	spin_unlock(&volume->cell->vs_lock);
+	up_write(&volume->cell->vs_lock);
 }
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index cf2fa4fddd5b..63ab23876be8 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -151,9 +151,11 @@ enum yfs_cm_operation {
 	EM(afs_volume_trace_alloc,		"ALLOC         ") \
 	EM(afs_volume_trace_free,		"FREE          ") \
 	EM(afs_volume_trace_get_alloc_sbi,	"GET sbi-alloc ") \
+	EM(afs_volume_trace_get_callback,	"GET callback  ") \
 	EM(afs_volume_trace_get_cell_insert,	"GET cell-insrt") \
 	EM(afs_volume_trace_get_new_op,		"GET op-new    ") \
 	EM(afs_volume_trace_get_query_alias,	"GET cell-alias") \
+	EM(afs_volume_trace_put_callback,	"PUT callback  ") \
 	EM(afs_volume_trace_put_cell_dup,	"PUT cell-dup  ") \
 	EM(afs_volume_trace_put_cell_root,	"PUT cell-root ") \
 	EM(afs_volume_trace_put_destroy_sbi,	"PUT sbi-destry") \
-- 
cgit v1.2.3


From 16069e1349a0c5535e189f9dc5d937bfd7631a06 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Sun, 5 Nov 2023 16:11:07 +0000
Subject: afs: Parse the VolSync record in the reply of a number of RPC ops

A number of fileserver RPC operations return a VolSync record as part of
their reply that gives some information about the state of the volume being
accessed, including:

 (1) A volume Creation timestamp.  For an RW volume, this is the time at
     which the volume was created; if it changes, the RW volume was
     presumably restored from a backup and all cached data should be
     scrubbed as Data Version numbers could regress on the files in the
     volume.

     For an RO volume, this is the time it was last snapshotted from the RW
     volume.  It is expected to advance each time this happens; if it
     regresses, cached data should be scrubbed.

 (2) A volume Update timestamp (Auristor only).  For an RW volume, this is
     updated any time any change is made to a volume or its contents.  If
     it regresses, all cached data must be scrubbed.

     For an RO volume, this is a copy of the RW volume's Update timestamp
     at the point of snapshotting.  It can be used as a version number when
     checking to see if a callback on a RO volume was due to a snapshot.
     If it regresses, all cached data must be scrubbed.

but this is currently not made use of by the in-kernel afs filesystem.

Make the afs filesystem use this by:

 (1) Add an update time field to the afs_volsync struct and use a value of
     TIME64_MIN in both that and the creation time to indicate that they
     are unset.

 (2) Add creation and update time fields to the afs_volume struct and use
     this to track the two timestamps.

 (3) Add a volsync_lock mutex to the afs_volume struct to control
     modification access for when we detect a change in these values.

 (3) Add a 'pre-op volsync' struct to the afs_operation struct to record
     the state of the volume tracking before the op.

 (4) Add a new counter, cb_scrub, to the afs_volume struct to count events
     that require all data to be scrubbed.  A copy is placed in the
     afs_vnode struct (inode) and if they no longer match, a scrub takes
     place.

 (5) When the result of an operation is being parsed, parse the VolSync
     data too, if it is provided.  Note that the two timestamps are handled
     separately, since they don't work in quite the same way.

     - If the afs_volume tracking is unset, just set it and do nothing
       else.

     - If the result timestamps are the same as the ones in afs_volume, do
       nothing.

     - If the timestamps regress, increment cb_scrub if not already done
       so.

     - If the creation timestamp on a RW volume changes, increment cb_scrub
       if not already done so.

     - If the creation timestamp on a RO volume advances, update the server
       list and see if the current server has been excluded, if so reissue
       the op.  Once over half of the replication sites have been updated,
       increment cb_ro_snapshot to indicate updates may be required and
       switch over to excluding unupdated replication sites.

     - If the creation timestamp on a Backup volume advances, just
       increment cb_ro_snapshot to trigger updates.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
---
 fs/afs/afs.h               |   3 +-
 fs/afs/callback.c          |   7 +-
 fs/afs/fs_operation.c      |  14 ++--
 fs/afs/fsclient.c          |   5 +-
 fs/afs/inode.c             |   2 +-
 fs/afs/internal.h          |  16 +++-
 fs/afs/rotate.c            |   4 +-
 fs/afs/validation.c        | 199 ++++++++++++++++++++++++++++++++++++++++++++-
 fs/afs/volume.c            |   3 +
 fs/afs/yfsclient.c         |   5 +-
 include/trace/events/afs.h |  30 ++++++-
 11 files changed, 268 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/fs/afs/afs.h b/fs/afs/afs.h
index 81815724db6c..b488072aee87 100644
--- a/fs/afs/afs.h
+++ b/fs/afs/afs.h
@@ -165,7 +165,8 @@ struct afs_status_cb {
  * AFS volume synchronisation information
  */
 struct afs_volsync {
-	time64_t		creation;	/* volume creation time */
+	time64_t		creation;	/* Volume creation time (or TIME64_MIN) */
+	time64_t		update;		/* Volume update time (or TIME64_MIN) */
 };
 
 /*
diff --git a/fs/afs/callback.c b/fs/afs/callback.c
index f67e88076761..8ddc99c9c16b 100644
--- a/fs/afs/callback.c
+++ b/fs/afs/callback.c
@@ -81,7 +81,7 @@ void __afs_break_callback(struct afs_vnode *vnode, enum afs_cb_break_reason reas
 	clear_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags);
 	if (test_and_clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) {
 		vnode->cb_break++;
-		vnode->cb_v_break = vnode->volume->cb_v_break;
+		vnode->cb_v_break = atomic_read(&vnode->volume->cb_v_break);
 		afs_clear_permits(vnode);
 
 		if (vnode->lock_state == AFS_VNODE_LOCK_WAITING_FOR_CB)
@@ -159,12 +159,13 @@ static void afs_break_one_callback(struct afs_volume *volume,
 	struct super_block *sb;
 	struct afs_vnode *vnode;
 	struct inode *inode;
+	unsigned int cb_v_break;
 
 	if (fid->vnode == 0 && fid->unique == 0) {
 		/* The callback break applies to an entire volume. */
 		write_lock(&volume->cb_v_break_lock);
-		volume->cb_v_break++;
-		trace_afs_cb_break(fid, volume->cb_v_break,
+		cb_v_break = atomic_inc_return(&volume->cb_v_break);
+		trace_afs_cb_break(fid, cb_v_break,
 				   afs_cb_break_for_volume_callback, false);
 		write_unlock(&volume->cb_v_break_lock);
 		return;
diff --git a/fs/afs/fs_operation.c b/fs/afs/fs_operation.c
index 10137681aa7d..99d1e649e929 100644
--- a/fs/afs/fs_operation.c
+++ b/fs/afs/fs_operation.c
@@ -35,11 +35,13 @@ struct afs_operation *afs_alloc_operation(struct key *key, struct afs_volume *vo
 		key_get(key);
 	}
 
-	op->key		= key;
-	op->volume	= afs_get_volume(volume, afs_volume_trace_get_new_op);
-	op->net		= volume->cell->net;
-	op->cb_v_break	= volume->cb_v_break;
-	op->debug_id	= atomic_inc_return(&afs_operation_debug_counter);
+	op->key			= key;
+	op->volume		= afs_get_volume(volume, afs_volume_trace_get_new_op);
+	op->net			= volume->cell->net;
+	op->cb_v_break		= atomic_read(&volume->cb_v_break);
+	op->pre_volsync.creation = volume->creation_time;
+	op->pre_volsync.update	= volume->update_time;
+	op->debug_id		= atomic_inc_return(&afs_operation_debug_counter);
 	op->nr_iterations = -1;
 	afs_op_set_error(op, -EDESTADDRREQ);
 
@@ -147,7 +149,7 @@ bool afs_begin_vnode_operation(struct afs_operation *op)
 
 	afs_prepare_vnode(op, &op->file[0], 0);
 	afs_prepare_vnode(op, &op->file[1], 1);
-	op->cb_v_break = op->volume->cb_v_break;
+	op->cb_v_break = atomic_read(&op->volume->cb_v_break);
 	_leave(" = true");
 	return true;
 }
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index f1f879ba9cf7..80f7d9e796e3 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -1870,7 +1870,10 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call)
 			return ret;
 
 		bp = call->buffer;
-		xdr_decode_AFSVolSync(&bp, &op->volsync);
+		/* Unfortunately, prior to OpenAFS-1.6, volsync here is filled
+		 * with rubbish.
+		 */
+		xdr_decode_AFSVolSync(&bp, NULL);
 
 		call->unmarshall++;
 		fallthrough;
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 102e7c37d33c..df3d37577b5b 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -542,7 +542,7 @@ struct inode *afs_root_iget(struct super_block *sb, struct key *key)
 	BUG_ON(!(inode->i_state & I_NEW));
 
 	vnode = AFS_FS_I(inode);
-	vnode->cb_v_break = as->volume->cb_v_break,
+	vnode->cb_v_break = atomic_read(&as->volume->cb_v_break),
 	afs_set_netfs_context(vnode);
 
 	op = afs_alloc_operation(key, as->volume);
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 3d90415c2527..4b730cbcf63e 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -662,7 +662,15 @@ struct afs_volume {
 	rwlock_t		servers_lock;	/* Lock for ->servers */
 	unsigned int		servers_seq;	/* Incremented each time ->servers changes */
 
-	unsigned		cb_v_break;	/* Break-everything counter. */
+	/* RO release tracking */
+	struct mutex		volsync_lock;	/* Time/state evaluation lock */
+	time64_t		creation_time;	/* Volume creation time (or TIME64_MIN) */
+	time64_t		update_time;	/* Volume update time (or TIME64_MIN) */
+
+	/* Callback management */
+	atomic_t		cb_ro_snapshot;	/* RO volume update-from-snapshot counter */
+	atomic_t		cb_v_break;	/* Volume-break event counter. */
+	atomic_t		cb_scrub;	/* Scrub-all-data event counter. */
 	rwlock_t		cb_v_break_lock;
 
 	afs_voltype_t		type;		/* type of volume */
@@ -856,7 +864,8 @@ struct afs_operation {
 	struct afs_volume	*volume;	/* Volume being accessed */
 	struct afs_vnode_param	file[2];
 	struct afs_vnode_param	*more_files;
-	struct afs_volsync	volsync;
+	struct afs_volsync	pre_volsync;	/* Volsync before op */
+	struct afs_volsync	volsync;	/* Volsync returned by op */
 	struct dentry		*dentry;	/* Dentry to be altered */
 	struct dentry		*dentry_2;	/* Second dentry to be altered */
 	struct timespec64	mtime;		/* Modification time to record */
@@ -1063,7 +1072,7 @@ static inline unsigned int afs_calc_vnode_cb_break(struct afs_vnode *vnode)
 static inline bool afs_cb_is_broken(unsigned int cb_break,
 				    const struct afs_vnode *vnode)
 {
-	return cb_break != (vnode->cb_break + vnode->volume->cb_v_break);
+	return cb_break != (vnode->cb_break + atomic_read(&vnode->volume->cb_v_break));
 }
 
 /*
@@ -1555,6 +1564,7 @@ extern void afs_fs_exit(void);
 /*
  * validation.c
  */
+int afs_update_volume_state(struct afs_operation *op);
 bool afs_check_validity(struct afs_vnode *vnode);
 bool afs_pagecache_valid(struct afs_vnode *vnode);
 int afs_validate(struct afs_vnode *vnode, struct key *key);
diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c
index 3ab85a907a1d..5c50c9aa1f87 100644
--- a/fs/afs/rotate.c
+++ b/fs/afs/rotate.c
@@ -486,7 +486,7 @@ selected_server:
 		vnode->cb_server = server;
 		vnode->cb_s_break = server->cb_s_break;
 		vnode->cb_fs_s_break = atomic_read(&server->cell->fs_s_break);
-		vnode->cb_v_break = vnode->volume->cb_v_break;
+		vnode->cb_v_break = atomic_read(&vnode->volume->cb_v_break);
 		clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags);
 	}
 
@@ -519,6 +519,8 @@ iterate_address:
 	op->addr_index = addr_index;
 	set_bit(addr_index, &op->addr_tried);
 
+	op->volsync.creation = TIME64_MIN;
+	op->volsync.update = TIME64_MIN;
 	op->call_responded = false;
 	_debug("address [%u] %u/%u %pISp",
 	       op->server_index, addr_index, alist->nr_addrs,
diff --git a/fs/afs/validation.c b/fs/afs/validation.c
index 18ba2c5e8ead..6aadd5e075e4 100644
--- a/fs/afs/validation.c
+++ b/fs/afs/validation.c
@@ -10,6 +10,201 @@
 #include <linux/sched.h>
 #include "internal.h"
 
+/*
+ * See if the server we've just talked to is currently excluded.
+ */
+static bool __afs_is_server_excluded(struct afs_operation *op, struct afs_volume *volume)
+{
+	const struct afs_server_entry *se;
+	const struct afs_server_list *slist;
+	bool is_excluded = true;
+	int i;
+
+	rcu_read_lock();
+
+	slist = rcu_dereference(volume->servers);
+	for (i = 0; i < slist->nr_servers; i++) {
+		se = &slist->servers[i];
+		if (op->server == se->server) {
+			is_excluded = test_bit(AFS_SE_EXCLUDED, &se->flags);
+			break;
+		}
+	}
+
+	rcu_read_unlock();
+	return is_excluded;
+}
+
+/*
+ * Update the volume's server list when the creation time changes and see if
+ * the server we've just talked to is currently excluded.
+ */
+static int afs_is_server_excluded(struct afs_operation *op, struct afs_volume *volume)
+{
+	int ret;
+
+	if (__afs_is_server_excluded(op, volume))
+		return 1;
+
+	set_bit(AFS_VOLUME_NEEDS_UPDATE, &volume->flags);
+	ret = afs_check_volume_status(op->volume, op);
+	if (ret < 0)
+		return ret;
+
+	return __afs_is_server_excluded(op, volume);
+}
+
+/*
+ * Handle a change to the volume creation time in the VolSync record.
+ */
+static int afs_update_volume_creation_time(struct afs_operation *op, struct afs_volume *volume)
+{
+	unsigned int snap;
+	time64_t cur = volume->creation_time;
+	time64_t old = op->pre_volsync.creation;
+	time64_t new = op->volsync.creation;
+	int ret;
+
+	_enter("%llx,%llx,%llx->%llx", volume->vid, cur, old, new);
+
+	if (cur == TIME64_MIN) {
+		volume->creation_time = new;
+		return 0;
+	}
+
+	if (new == cur)
+		return 0;
+
+	/* Try to advance the creation timestamp from what we had before the
+	 * operation to what we got back from the server.  This should
+	 * hopefully ensure that in a race between multiple operations only one
+	 * of them will do this.
+	 */
+	if (cur != old)
+		return 0;
+
+	/* If the creation time changes in an unexpected way, we need to scrub
+	 * our caches.  For a RW vol, this will only change if the volume is
+	 * restored from a backup; for a RO/Backup vol, this will advance when
+	 * the volume is updated to a new snapshot (eg. "vos release").
+	 */
+	if (volume->type == AFSVL_RWVOL)
+		goto regressed;
+	if (volume->type == AFSVL_BACKVOL) {
+		if (new < old)
+			goto regressed;
+		goto advance;
+	}
+
+	/* We have an RO volume, we need to query the VL server and look at the
+	 * server flags to see if RW->RO replication is in progress.
+	 */
+	ret = afs_is_server_excluded(op, volume);
+	if (ret < 0)
+		return ret;
+	if (ret > 0) {
+		snap = atomic_read(&volume->cb_ro_snapshot);
+		trace_afs_cb_v_break(volume->vid, snap, afs_cb_break_volume_excluded);
+		return ret;
+	}
+
+advance:
+	snap = atomic_inc_return(&volume->cb_ro_snapshot);
+	trace_afs_cb_v_break(volume->vid, snap, afs_cb_break_for_vos_release);
+	volume->creation_time = new;
+	return 0;
+
+regressed:
+	atomic_inc(&volume->cb_scrub);
+	trace_afs_cb_v_break(volume->vid, 0, afs_cb_break_for_creation_regress);
+	volume->creation_time = new;
+	return 0;
+}
+
+/*
+ * Handle a change to the volume update time in the VolSync record.
+ */
+static void afs_update_volume_update_time(struct afs_operation *op, struct afs_volume *volume)
+{
+	enum afs_cb_break_reason reason = afs_cb_break_no_break;
+	time64_t cur = volume->update_time;
+	time64_t old = op->pre_volsync.update;
+	time64_t new = op->volsync.update;
+
+	_enter("%llx,%llx,%llx->%llx", volume->vid, cur, old, new);
+
+	if (cur == TIME64_MIN) {
+		volume->update_time = new;
+		return;
+	}
+
+	if (new == cur)
+		return;
+
+	/* If the volume update time changes in an unexpected way, we need to
+	 * scrub our caches.  For a RW vol, this will advance on every
+	 * modification op; for a RO/Backup vol, this will advance when the
+	 * volume is updated to a new snapshot (eg. "vos release").
+	 */
+	if (new < old)
+		reason = afs_cb_break_for_update_regress;
+
+	/* Try to advance the update timestamp from what we had before the
+	 * operation to what we got back from the server.  This should
+	 * hopefully ensure that in a race between multiple operations only one
+	 * of them will do this.
+	 */
+	if (cur == old) {
+		if (reason == afs_cb_break_for_update_regress) {
+			atomic_inc(&volume->cb_scrub);
+			trace_afs_cb_v_break(volume->vid, 0, reason);
+		}
+		volume->update_time = new;
+	}
+}
+
+static int afs_update_volume_times(struct afs_operation *op, struct afs_volume *volume)
+{
+	int ret = 0;
+
+	if (likely(op->volsync.creation == volume->creation_time &&
+		   op->volsync.update == volume->update_time))
+		return 0;
+
+	mutex_lock(&volume->volsync_lock);
+	if (op->volsync.creation != volume->creation_time) {
+		ret = afs_update_volume_creation_time(op, volume);
+		if (ret < 0)
+			goto out;
+	}
+	if (op->volsync.update != volume->update_time)
+		afs_update_volume_update_time(op, volume);
+out:
+	mutex_unlock(&volume->volsync_lock);
+	return ret;
+}
+
+/*
+ * Update the state of a volume.  Returns 1 to redo the operation from the start.
+ */
+int afs_update_volume_state(struct afs_operation *op)
+{
+	struct afs_volume *volume = op->volume;
+	int ret;
+
+	_enter("%llx", op->volume->vid);
+
+	if (op->volsync.creation != TIME64_MIN || op->volsync.update != TIME64_MIN) {
+		ret = afs_update_volume_times(op, volume);
+		if (ret != 0) {
+			_leave(" = %d", ret);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
 /*
  * mark the data attached to an inode as obsolete due to a write on the server
  * - might also want to ditch all the outstanding writes and dirty pages
@@ -74,7 +269,7 @@ bool afs_check_validity(struct afs_vnode *vnode)
 		cb_break = vnode->cb_break;
 
 		if (test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) {
-			if (vnode->cb_v_break != vnode->volume->cb_v_break)
+			if (vnode->cb_v_break != atomic_read(&vnode->volume->cb_v_break))
 				need_clear = afs_cb_break_for_v_break;
 			else if (!afs_check_server_good(vnode))
 				need_clear = afs_cb_break_for_s_reinit;
@@ -95,7 +290,7 @@ bool afs_check_validity(struct afs_vnode *vnode)
 
 	write_seqlock(&vnode->cb_lock);
 	if (need_clear == afs_cb_break_no_promise)
-		vnode->cb_v_break = vnode->volume->cb_v_break;
+		vnode->cb_v_break = atomic_read(&vnode->volume->cb_v_break);
 	else if (cb_break == vnode->cb_break)
 		__afs_break_callback(vnode, need_clear);
 	else
diff --git a/fs/afs/volume.c b/fs/afs/volume.c
index 4982fce25057..41ab1d3ff3ea 100644
--- a/fs/afs/volume.c
+++ b/fs/afs/volume.c
@@ -90,11 +90,14 @@ static struct afs_volume *afs_alloc_volume(struct afs_fs_context *params,
 	volume->type		= params->type;
 	volume->type_force	= params->force;
 	volume->name_len	= vldb->name_len;
+	volume->creation_time	= TIME64_MIN;
+	volume->update_time	= TIME64_MIN;
 
 	refcount_set(&volume->ref, 1);
 	INIT_HLIST_NODE(&volume->proc_link);
 	INIT_WORK(&volume->destructor, afs_destroy_volume);
 	rwlock_init(&volume->servers_lock);
+	mutex_init(&volume->volsync_lock);
 	rwlock_init(&volume->cb_v_break_lock);
 	memcpy(volume->name, vldb->name, vldb->name_len + 1);
 
diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c
index 11571cca86c1..2d6943f05ea5 100644
--- a/fs/afs/yfsclient.c
+++ b/fs/afs/yfsclient.c
@@ -245,12 +245,15 @@ static void xdr_decode_YFSVolSync(const __be32 **_bp,
 				  struct afs_volsync *volsync)
 {
 	struct yfs_xdr_YFSVolSync *x = (void *)*_bp;
-	u64 creation;
+	u64 creation, update;
 
 	if (volsync) {
 		creation = xdr_to_u64(x->vol_creation_date);
 		do_div(creation, 10 * 1000 * 1000);
 		volsync->creation = creation;
+		update = xdr_to_u64(x->vol_update_date);
+		do_div(update, 10 * 1000 * 1000);
+		volsync->update = update;
 	}
 
 	*_bp += xdr_size(x);
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index 63ab23876be8..bbe8dcab4b32 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -440,13 +440,17 @@ enum yfs_cm_operation {
 	EM(afs_cb_break_no_break,		"no-break")		\
 	EM(afs_cb_break_no_promise,		"no-promise")		\
 	EM(afs_cb_break_for_callback,		"break-cb")		\
+	EM(afs_cb_break_for_creation_regress,	"creation-regress")	\
 	EM(afs_cb_break_for_deleted,		"break-del")		\
 	EM(afs_cb_break_for_lapsed,		"break-lapsed")		\
 	EM(afs_cb_break_for_s_reinit,		"s-reinit")		\
 	EM(afs_cb_break_for_unlink,		"break-unlink")		\
+	EM(afs_cb_break_for_update_regress,	"update-regress")	\
 	EM(afs_cb_break_for_v_break,		"break-v")		\
 	EM(afs_cb_break_for_volume_callback,	"break-v-cb")		\
-	E_(afs_cb_break_for_zap,		"break-zap")
+	EM(afs_cb_break_for_vos_release,	"break-vos-release")	\
+	EM(afs_cb_break_for_zap,		"break-zap")		\
+	E_(afs_cb_break_volume_excluded,	"vol-excluded")
 
 /*
  * Generate enums for tracing information.
@@ -1249,6 +1253,30 @@ TRACE_EVENT(afs_get_tree,
 		      __entry->cell, __entry->volume, __entry->vid)
 	    );
 
+TRACE_EVENT(afs_cb_v_break,
+	    TP_PROTO(afs_volid_t vid, unsigned int cb_v_break,
+		     enum afs_cb_break_reason reason),
+
+	    TP_ARGS(vid, cb_v_break, reason),
+
+	    TP_STRUCT__entry(
+		    __field(afs_volid_t,		vid)
+		    __field(unsigned int,		cb_v_break)
+		    __field(enum afs_cb_break_reason,	reason)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->vid	= vid;
+		    __entry->cb_v_break	= cb_v_break;
+		    __entry->reason	= reason;
+			   ),
+
+	    TP_printk("%llx vb=%x %s",
+		      __entry->vid,
+		      __entry->cb_v_break,
+		      __print_symbolic(__entry->reason, afs_cb_break_reasons))
+	    );
+
 TRACE_EVENT(afs_cb_break,
 	    TP_PROTO(struct afs_fid *fid, unsigned int cb_break,
 		     enum afs_cb_break_reason reason, bool skipped),
-- 
cgit v1.2.3


From 453924de6212ac159f946b75c6b59918e2e30944 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 8 Nov 2023 13:57:42 +0000
Subject: afs: Overhaul invalidation handling to better support RO volumes

Overhaul the third party-induced invalidation handling, making use of the
previously added volume-level event counters (cb_scrub and cb_ro_snapshot)
that are now being parsed out of the VolSync record returned by the
fileserver in many of its replies.

This allows better handling of RO (and Backup) volumes.  Since these are
snapshot of a RW volume that are updated atomically simultantanously across
all servers that host them, they only require a single callback promise for
the entire volume.  The currently upstream code assumes that RO volumes
operate in the same manner as RW volumes, and that each file has its own
individual callback - which means that it does a status fetch for *every*
file in a RO volume, whether or not the volume got "released" (volume
callback breaks can occur for other reasons too, such as the volumeserver
taking ownership of a volume from a fileserver).

To this end, make the following changes:

 (1) Change the meaning of the volume's cb_v_break counter so that it is
     now a hint that we need to issue a status fetch to work out the state
     of a volume.  cb_v_break is incremented by volume break callbacks and
     by server initialisation callbacks.

 (2) Add a second counter, cb_v_check, to the afs_volume struct such that
     if this differs from cb_v_break, we need to do a check.  When the
     check is complete, cb_v_check is advanced to what cb_v_break was at
     the start of the status fetch.

 (3) Move the list of mmap'd vnodes to the volume and trigger removal of
     PTEs that map to files on a volume break rather than on a server
     break.

 (4) When a server reinitialisation callback comes in, use the
     server-to-volume reverse mapping added in a preceding patch to iterate
     over all the volumes using that server and clear the volume callback
     promises for that server and the general volume promise as a whole to
     trigger reanalysis.

 (5) Replace the AFS_VNODE_CB_PROMISED flag with an AFS_NO_CB_PROMISE
     (TIME64_MIN) value in the cb_expires_at field, reducing the number of
     checks we need to make.

 (6) Change afs_check_validity() to quickly see if various event counters
     have been incremented or if the vnode or volume callback promise is
     due to expire/has expired without making any changes to the state.
     That is now left to afs_validate() as this may get more complicated in
     future as we may have to examine server records too.

 (7) Overhaul afs_validate() so that it does a single status fetch if we
     need to check the state of either the vnode or the volume - and do so
     under appropriate locking.  The function does the following steps:

     (A) If the vnode/volume is no longer seen as valid, then we take the
     vnode validation lock and, if the volume promise has expired, the
     volume check lock also.  The latter prevents redundant checks being
     made to find out if a new version of the volume got released.

     (B) If a previous RPC call found that the volsync changed unexpectedly
     or that a RO volume was updated, then we unmap all PTEs pointing to
     the file to stop mmap being used for access.

     (C) If the vnode is still seen to be of uncertain validity, then we
     perform an FS.FetchStatus RPC op to jointly update the volume status
     and the vnode status.  This assessment is done as part of parsing the
     reply:

	If the RO volume creation timestamp advances, cb_ro_snapshot is
	incremented; if either the creation or update timestamps changes in
	an unexpected way, the cb_scrub counter is incremented

	If the Data Version returned doesn't match the copy we have
	locally, then we ask for the pagecache to be zapped.  This takes
	care of handling RO update.

     (D) If cb_scrub differs between volume and vnode, the vnode's
     pagecache is zapped and the vnode's cb_scrub is updated unless the
     file is marked as having been deleted.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
---
 fs/afs/callback.c          | 122 +++++++++++-------
 fs/afs/cell.c              |   2 -
 fs/afs/dir.c               |  10 +-
 fs/afs/file.c              |  13 +-
 fs/afs/fs_operation.c      |   3 +-
 fs/afs/inode.c             |  21 ++--
 fs/afs/internal.h          |  34 ++---
 fs/afs/proc.c              |   4 +-
 fs/afs/rotate.c            |  24 +++-
 fs/afs/server_list.c       |   2 +
 fs/afs/validation.c        | 305 +++++++++++++++++++++++++++++----------------
 fs/afs/volume.c            |   3 +
 include/trace/events/afs.h |   4 -
 13 files changed, 344 insertions(+), 203 deletions(-)

(limited to 'include')

diff --git a/fs/afs/callback.c b/fs/afs/callback.c
index 8ddc99c9c16b..99b2c8172021 100644
--- a/fs/afs/callback.c
+++ b/fs/afs/callback.c
@@ -33,21 +33,20 @@ void afs_invalidate_mmap_work(struct work_struct *work)
 	unmap_mapping_pages(vnode->netfs.inode.i_mapping, 0, 0, false);
 }
 
-static void afs_server_init_callback(struct afs_server *server)
+static void afs_volume_init_callback(struct afs_volume *volume)
 {
 	struct afs_vnode *vnode;
-	struct afs_cell *cell = server->cell;
 
-	down_read(&cell->fs_open_mmaps_lock);
+	down_read(&volume->open_mmaps_lock);
 
-	list_for_each_entry(vnode, &cell->fs_open_mmaps, cb_mmap_link) {
-		if (vnode->cb_server == server) {
-			clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags);
+	list_for_each_entry(vnode, &volume->open_mmaps, cb_mmap_link) {
+		if (vnode->cb_v_check != atomic_read(&volume->cb_v_break)) {
+			atomic64_set(&vnode->cb_expires_at, AFS_NO_CB_PROMISE);
 			queue_work(system_unbound_wq, &vnode->cb_work);
 		}
 	}
 
-	up_read(&cell->fs_open_mmaps_lock);
+	up_read(&volume->open_mmaps_lock);
 }
 
 /*
@@ -56,19 +55,20 @@ static void afs_server_init_callback(struct afs_server *server)
  */
 void afs_init_callback_state(struct afs_server *server)
 {
-	struct afs_cell *cell = server->cell;
+	struct afs_server_entry *se;
 
-	down_read(&cell->vs_lock);
+	down_read(&server->cell->vs_lock);
 
-	do {
-		server->cb_s_break++;
-		atomic_inc(&server->cell->fs_s_break);
-		if (!list_empty(&server->cell->fs_open_mmaps))
-			afs_server_init_callback(server);
-
-	} while ((server = rcu_dereference(server->uuid_next)));
+	list_for_each_entry(se, &server->volumes, slink) {
+		se->cb_expires_at = AFS_NO_CB_PROMISE;
+		se->volume->cb_expires_at = AFS_NO_CB_PROMISE;
+		trace_afs_cb_v_break(se->volume->vid, atomic_read(&se->volume->cb_v_break),
+				     afs_cb_break_for_s_reinit);
+		if (!list_empty(&se->volume->open_mmaps))
+			afs_volume_init_callback(se->volume);
+	}
 
-	up_read(&cell->vs_lock);
+	up_read(&server->cell->vs_lock);
 }
 
 /*
@@ -79,9 +79,9 @@ void __afs_break_callback(struct afs_vnode *vnode, enum afs_cb_break_reason reas
 	_enter("");
 
 	clear_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags);
-	if (test_and_clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) {
+	if (atomic64_xchg(&vnode->cb_expires_at, AFS_NO_CB_PROMISE) != AFS_NO_CB_PROMISE) {
 		vnode->cb_break++;
-		vnode->cb_v_break = atomic_read(&vnode->volume->cb_v_break);
+		vnode->cb_v_check = atomic_read(&vnode->volume->cb_v_break);
 		afs_clear_permits(vnode);
 
 		if (vnode->lock_state == AFS_VNODE_LOCK_WAITING_FOR_CB)
@@ -147,29 +147,51 @@ static struct afs_volume *afs_lookup_volume_rcu(struct afs_cell *cell,
 	return volume;
 }
 
+/*
+ * Allow the fileserver to break callbacks at the volume-level.  This is
+ * typically done when, for example, a R/W volume is snapshotted to a R/O
+ * volume (the only way to change an R/O volume).  It may also, however, happen
+ * when a volserver takes control of a volume (offlining it, moving it, etc.).
+ *
+ * Every file in that volume will need to be reevaluated.
+ */
+static void afs_break_volume_callback(struct afs_server *server,
+				      struct afs_volume *volume)
+	__releases(RCU)
+{
+	struct afs_server_list *slist = rcu_dereference(volume->servers);
+	unsigned int i, cb_v_break;
+
+	write_lock(&volume->cb_v_break_lock);
+
+	for (i = 0; i < slist->nr_servers; i++)
+		if (slist->servers[i].server == server)
+			slist->servers[i].cb_expires_at = AFS_NO_CB_PROMISE;
+	volume->cb_expires_at = AFS_NO_CB_PROMISE;
+
+	cb_v_break = atomic_inc_return_release(&volume->cb_v_break);
+	trace_afs_cb_v_break(volume->vid, cb_v_break, afs_cb_break_for_volume_callback);
+
+	write_unlock(&volume->cb_v_break_lock);
+	rcu_read_unlock();
+
+	if (!list_empty(&volume->open_mmaps))
+		afs_volume_init_callback(volume);
+}
+
 /*
  * allow the fileserver to explicitly break one callback
  * - happens when
  *   - the backing file is changed
  *   - a lock is released
  */
-static void afs_break_one_callback(struct afs_volume *volume,
+static void afs_break_one_callback(struct afs_server *server,
+				   struct afs_volume *volume,
 				   struct afs_fid *fid)
 {
 	struct super_block *sb;
 	struct afs_vnode *vnode;
 	struct inode *inode;
-	unsigned int cb_v_break;
-
-	if (fid->vnode == 0 && fid->unique == 0) {
-		/* The callback break applies to an entire volume. */
-		write_lock(&volume->cb_v_break_lock);
-		cb_v_break = atomic_inc_return(&volume->cb_v_break);
-		trace_afs_cb_break(fid, cb_v_break,
-				   afs_cb_break_for_volume_callback, false);
-		write_unlock(&volume->cb_v_break_lock);
-		return;
-	}
 
 	/* See if we can find a matching inode - even an I_NEW inode needs to
 	 * be marked as it can have its callback broken before we finish
@@ -199,24 +221,32 @@ static void afs_break_some_callbacks(struct afs_server *server,
 
 	rcu_read_lock();
 	volume = afs_lookup_volume_rcu(server->cell, vid);
-	/* TODO: Find all matching volumes if we couldn't match the server and
-	 * break them anyway.
-	 */
-	for (i = *_count; i > 0; cbb++, i--) {
-		if (cbb->fid.vid == vid) {
-			_debug("- Fid { vl=%08llx n=%llu u=%u }",
-			       cbb->fid.vid,
-			       cbb->fid.vnode,
-			       cbb->fid.unique);
-			--*_count;
-			if (volume)
-				afs_break_one_callback(volume, &cbb->fid);
-		} else {
-			*residue++ = *cbb;
+	if (cbb->fid.vnode == 0 && cbb->fid.unique == 0) {
+		afs_break_volume_callback(server, volume);
+		*_count -= 1;
+		if (*_count)
+			memmove(cbb, cbb + 1, sizeof(*cbb) * *_count);
+	} else {
+		/* TODO: Find all matching volumes if we couldn't match the server and
+		 * break them anyway.
+		 */
+
+		for (i = *_count; i > 0; cbb++, i--) {
+			if (cbb->fid.vid == vid) {
+				_debug("- Fid { vl=%08llx n=%llu u=%u }",
+				       cbb->fid.vid,
+				       cbb->fid.vnode,
+				       cbb->fid.unique);
+				--*_count;
+				if (volume)
+					afs_break_one_callback(server, volume, &cbb->fid);
+			} else {
+				*residue++ = *cbb;
+			}
 		}
+		rcu_read_unlock();
 	}
 
-	rcu_read_unlock();
 	afs_put_volume(volume, afs_volume_trace_put_callback);
 }
 
diff --git a/fs/afs/cell.c b/fs/afs/cell.c
index e4b6a80763d7..caa09875f520 100644
--- a/fs/afs/cell.c
+++ b/fs/afs/cell.c
@@ -167,8 +167,6 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net,
 	seqlock_init(&cell->volume_lock);
 	cell->fs_servers = RB_ROOT;
 	seqlock_init(&cell->fs_lock);
-	INIT_LIST_HEAD(&cell->fs_open_mmaps);
-	init_rwsem(&cell->fs_open_mmaps_lock);
 	rwlock_init(&cell->vl_servers_lock);
 	cell->flags = (1 << AFS_CELL_FL_CHECK_ALIAS);
 
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index e232f713ece1..c14533ef108f 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -1118,7 +1118,12 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
 	dir = AFS_FS_I(d_inode(parent));
 
 	/* validate the parent directory */
-	afs_validate(dir, key);
+	ret = afs_validate(dir, key);
+	if (ret == -ERESTARTSYS) {
+		dput(parent);
+		key_put(key);
+		return ret;
+	}
 
 	if (test_bit(AFS_VNODE_DELETED, &dir->flags)) {
 		_debug("%pd: parent dir deleted", dentry);
@@ -1260,6 +1265,7 @@ void afs_check_for_remote_deletion(struct afs_operation *op)
 	switch (afs_op_abort_code(op)) {
 	case VNOVNODE:
 		set_bit(AFS_VNODE_DELETED, &vnode->flags);
+		clear_nlink(&vnode->netfs.inode);
 		afs_break_callback(vnode, afs_cb_break_for_deleted);
 	}
 }
@@ -1375,7 +1381,7 @@ static void afs_dir_remove_subdir(struct dentry *dentry)
 
 		clear_nlink(&vnode->netfs.inode);
 		set_bit(AFS_VNODE_DELETED, &vnode->flags);
-		clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags);
+		atomic64_set(&vnode->cb_expires_at, AFS_NO_CB_PROMISE);
 		clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags);
 	}
 }
diff --git a/fs/afs/file.c b/fs/afs/file.c
index 8f9b42427569..30914e0d9cb2 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -514,13 +514,12 @@ static bool afs_release_folio(struct folio *folio, gfp_t gfp)
 static void afs_add_open_mmap(struct afs_vnode *vnode)
 {
 	if (atomic_inc_return(&vnode->cb_nr_mmap) == 1) {
-		down_write(&vnode->volume->cell->fs_open_mmaps_lock);
+		down_write(&vnode->volume->open_mmaps_lock);
 
 		if (list_empty(&vnode->cb_mmap_link))
-			list_add_tail(&vnode->cb_mmap_link,
-				      &vnode->volume->cell->fs_open_mmaps);
+			list_add_tail(&vnode->cb_mmap_link, &vnode->volume->open_mmaps);
 
-		up_write(&vnode->volume->cell->fs_open_mmaps_lock);
+		up_write(&vnode->volume->open_mmaps_lock);
 	}
 }
 
@@ -529,12 +528,12 @@ static void afs_drop_open_mmap(struct afs_vnode *vnode)
 	if (!atomic_dec_and_test(&vnode->cb_nr_mmap))
 		return;
 
-	down_write(&vnode->volume->cell->fs_open_mmaps_lock);
+	down_write(&vnode->volume->open_mmaps_lock);
 
 	if (atomic_read(&vnode->cb_nr_mmap) == 0)
 		list_del_init(&vnode->cb_mmap_link);
 
-	up_write(&vnode->volume->cell->fs_open_mmaps_lock);
+	up_write(&vnode->volume->open_mmaps_lock);
 	flush_work(&vnode->cb_work);
 }
 
@@ -570,7 +569,7 @@ static vm_fault_t afs_vm_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pg
 {
 	struct afs_vnode *vnode = AFS_FS_I(file_inode(vmf->vma->vm_file));
 
-	if (afs_pagecache_valid(vnode))
+	if (afs_check_validity(vnode))
 		return filemap_map_pages(vmf, start_pgoff, end_pgoff);
 	return 0;
 }
diff --git a/fs/afs/fs_operation.c b/fs/afs/fs_operation.c
index 99d1e649e929..cecc44af6a5f 100644
--- a/fs/afs/fs_operation.c
+++ b/fs/afs/fs_operation.c
@@ -42,7 +42,7 @@ struct afs_operation *afs_alloc_operation(struct key *key, struct afs_volume *vo
 	op->pre_volsync.creation = volume->creation_time;
 	op->pre_volsync.update	= volume->update_time;
 	op->debug_id		= atomic_inc_return(&afs_operation_debug_counter);
-	op->nr_iterations = -1;
+	op->nr_iterations	= -1;
 	afs_op_set_error(op, -EDESTADDRREQ);
 
 	_leave(" = [op=%08x]", op->debug_id);
@@ -184,7 +184,6 @@ void afs_wait_for_operation(struct afs_operation *op)
 		op->call_responded = false;
 		op->call_error = 0;
 		op->call_abort_code = 0;
-		op->cb_s_break = op->server->cb_s_break;
 		if (test_bit(AFS_SERVER_FL_IS_YFS, &op->server->flags) &&
 		    op->ops->issue_yfs_rpc)
 			op->ops->issue_yfs_rpc(op);
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index df3d37577b5b..4f04f6f33f46 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -85,8 +85,7 @@ static int afs_inode_init_from_status(struct afs_operation *op,
 
 	write_seqlock(&vnode->cb_lock);
 
-	vnode->cb_v_break = op->cb_v_break;
-	vnode->cb_s_break = op->cb_s_break;
+	vnode->cb_v_check = op->cb_v_break;
 	vnode->status = *status;
 
 	t = status->mtime_client;
@@ -146,11 +145,10 @@ static int afs_inode_init_from_status(struct afs_operation *op,
 	if (!vp->scb.have_cb) {
 		/* it's a symlink we just created (the fileserver
 		 * didn't give us a callback) */
-		vnode->cb_expires_at = ktime_get_real_seconds();
+		atomic64_set(&vnode->cb_expires_at, AFS_NO_CB_PROMISE);
 	} else {
-		vnode->cb_expires_at = vp->scb.callback.expires_at;
 		vnode->cb_server = op->server;
-		set_bit(AFS_VNODE_CB_PROMISED, &vnode->flags);
+		atomic64_set(&vnode->cb_expires_at, vp->scb.callback.expires_at);
 	}
 
 	write_sequnlock(&vnode->cb_lock);
@@ -214,7 +212,8 @@ static void afs_apply_status(struct afs_operation *op,
 	vnode->status = *status;
 
 	if (vp->dv_before + vp->dv_delta != status->data_version) {
-		if (test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags))
+		if (vnode->cb_ro_snapshot == atomic_read(&vnode->volume->cb_ro_snapshot) &&
+		    atomic64_read(&vnode->cb_expires_at) != AFS_NO_CB_PROMISE)
 			pr_warn("kAFS: vnode modified {%llx:%llu} %llx->%llx %s (op=%x)\n",
 				vnode->fid.vid, vnode->fid.vnode,
 				(unsigned long long)vp->dv_before + vp->dv_delta,
@@ -268,9 +267,9 @@ static void afs_apply_callback(struct afs_operation *op,
 	struct afs_vnode *vnode = vp->vnode;
 
 	if (!afs_cb_is_broken(vp->cb_break_before, vnode)) {
-		vnode->cb_expires_at	= cb->expires_at;
-		vnode->cb_server	= op->server;
-		set_bit(AFS_VNODE_CB_PROMISED, &vnode->flags);
+		if (op->volume->type == AFSVL_RWVOL)
+			vnode->cb_server = op->server;
+		atomic64_set(&vnode->cb_expires_at, cb->expires_at);
 	}
 }
 
@@ -542,7 +541,7 @@ struct inode *afs_root_iget(struct super_block *sb, struct key *key)
 	BUG_ON(!(inode->i_state & I_NEW));
 
 	vnode = AFS_FS_I(inode);
-	vnode->cb_v_break = atomic_read(&as->volume->cb_v_break),
+	vnode->cb_v_check = atomic_read(&as->volume->cb_v_break),
 	afs_set_netfs_context(vnode);
 
 	op = afs_alloc_operation(key, as->volume);
@@ -587,7 +586,7 @@ int afs_getattr(struct mnt_idmap *idmap, const struct path *path,
 
 	if (vnode->volume &&
 	    !(query_flags & AT_STATX_DONT_SYNC) &&
-	    !test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) {
+	    atomic64_read(&vnode->cb_expires_at) == AFS_NO_CB_PROMISE) {
 		key = afs_request_key(vnode->volume->cell);
 		if (IS_ERR(key))
 			return PTR_ERR(key);
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 4b730cbcf63e..6d0cd886b548 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -422,9 +422,6 @@ struct afs_cell {
 	/* Active fileserver interaction state. */
 	struct rb_root		fs_servers;	/* afs_server (by server UUID) */
 	seqlock_t		fs_lock;	/* For fs_servers  */
-	struct rw_semaphore	fs_open_mmaps_lock;
-	struct list_head	fs_open_mmaps;	/* List of vnodes that are mmapped */
-	atomic_t		fs_s_break;	/* Counter of CB.InitCallBackState messages */
 
 	/* VL server list. */
 	rwlock_t		vl_servers_lock; /* Lock on vl_servers */
@@ -591,9 +588,6 @@ struct afs_server {
 	/* file service access */
 	rwlock_t		fs_lock;	/* access lock */
 
-	/* callback promise management */
-	unsigned		cb_s_break;	/* Break-everything counter. */
-
 	/* Probe state */
 	struct afs_endpoint_state __rcu *endpoint_state; /* Latest endpoint/probe state */
 	unsigned long		probed_at;	/* Time last probe was dispatched (jiffies) */
@@ -615,6 +609,7 @@ struct afs_server_entry {
 	struct afs_server	*server;
 	struct afs_volume	*volume;
 	struct list_head	slink;		/* Link in server->volumes */
+	time64_t		cb_expires_at;	/* Time at which volume-level callback expires */
 	unsigned long		flags;
 #define AFS_SE_EXCLUDED		0		/* Set if server is to be excluded in rotation */
 };
@@ -668,10 +663,15 @@ struct afs_volume {
 	time64_t		update_time;	/* Volume update time (or TIME64_MIN) */
 
 	/* Callback management */
+	struct mutex		cb_check_lock;	/* Lock to control race to check after v_break */
+	time64_t		cb_expires_at;	/* Earliest volume callback expiry time */
 	atomic_t		cb_ro_snapshot;	/* RO volume update-from-snapshot counter */
 	atomic_t		cb_v_break;	/* Volume-break event counter. */
+	atomic_t		cb_v_check;	/* Volume-break has-been-checked counter. */
 	atomic_t		cb_scrub;	/* Scrub-all-data event counter. */
 	rwlock_t		cb_v_break_lock;
+	struct rw_semaphore	open_mmaps_lock;
+	struct list_head	open_mmaps;	/* List of vnodes that are mmapped */
 
 	afs_voltype_t		type;		/* type of volume */
 	char			type_force;	/* force volume type (suppress R/O -> R/W) */
@@ -710,7 +710,6 @@ struct afs_vnode {
 	spinlock_t		wb_lock;	/* lock for wb_keys */
 	spinlock_t		lock;		/* waitqueue/flags lock */
 	unsigned long		flags;
-#define AFS_VNODE_CB_PROMISED	0		/* Set if vnode has a callback promise */
 #define AFS_VNODE_UNSET		1		/* set if vnode attributes not yet set */
 #define AFS_VNODE_DIR_VALID	2		/* Set if dir contents are valid */
 #define AFS_VNODE_ZAP_DATA	3		/* set if vnode's data should be invalidated */
@@ -736,13 +735,14 @@ struct afs_vnode {
 	struct list_head	cb_mmap_link;	/* Link in cell->fs_open_mmaps */
 	void			*cb_server;	/* Server with callback/filelock */
 	atomic_t		cb_nr_mmap;	/* Number of mmaps */
-	unsigned int		cb_fs_s_break;	/* Mass server break counter (cell->fs_s_break) */
-	unsigned int		cb_s_break;	/* Mass break counter on ->server */
-	unsigned int		cb_v_break;	/* Mass break counter on ->volume */
+	unsigned int		cb_ro_snapshot;	/* RO volume release counter on ->volume */
+	unsigned int		cb_scrub;	/* Scrub counter on ->volume */
 	unsigned int		cb_break;	/* Break counter on vnode */
+	unsigned int		cb_v_check;	/* Break check counter on ->volume */
 	seqlock_t		cb_lock;	/* Lock for ->cb_server, ->status, ->cb_*break */
 
-	time64_t		cb_expires_at;	/* time at which callback expires */
+	atomic64_t		cb_expires_at;	/* time at which callback expires */
+#define AFS_NO_CB_PROMISE TIME64_MIN
 };
 
 static inline struct fscache_cookie *afs_vnode_cache(struct afs_vnode *vnode)
@@ -839,7 +839,7 @@ struct afs_vnode_param {
 	struct afs_fid		fid;		/* Fid to access */
 	struct afs_status_cb	scb;		/* Returned status and callback promise */
 	afs_dataversion_t	dv_before;	/* Data version before the call */
-	unsigned int		cb_break_before; /* cb_break + cb_s_break before the call */
+	unsigned int		cb_break_before; /* cb_break before the call */
 	u8			dv_delta;	/* Expected change in data version */
 	bool			put_vnode:1;	/* T if we have a ref on the vnode */
 	bool			need_io_lock:1;	/* T if we need the I/O lock on this */
@@ -875,7 +875,6 @@ struct afs_operation {
 	unsigned int		debug_id;
 
 	unsigned int		cb_v_break;	/* Volume break counter before op */
-	unsigned int		cb_s_break;	/* Server break counter before op */
 
 	union {
 		struct {
@@ -1066,13 +1065,15 @@ extern void afs_break_callbacks(struct afs_server *, size_t, struct afs_callback
 
 static inline unsigned int afs_calc_vnode_cb_break(struct afs_vnode *vnode)
 {
-	return vnode->cb_break + vnode->cb_v_break;
+	return vnode->cb_break + vnode->cb_ro_snapshot + vnode->cb_scrub;
 }
 
 static inline bool afs_cb_is_broken(unsigned int cb_break,
 				    const struct afs_vnode *vnode)
 {
-	return cb_break != (vnode->cb_break + atomic_read(&vnode->volume->cb_v_break));
+	return cb_break != (vnode->cb_break +
+			    atomic_read(&vnode->volume->cb_ro_snapshot) +
+			    atomic_read(&vnode->volume->cb_scrub));
 }
 
 /*
@@ -1564,9 +1565,8 @@ extern void afs_fs_exit(void);
 /*
  * validation.c
  */
+bool afs_check_validity(const struct afs_vnode *vnode);
 int afs_update_volume_state(struct afs_operation *op);
-bool afs_check_validity(struct afs_vnode *vnode);
-bool afs_pagecache_valid(struct afs_vnode *vnode);
 int afs_validate(struct afs_vnode *vnode, struct key *key);
 
 /*
diff --git a/fs/afs/proc.c b/fs/afs/proc.c
index a138022d8e0d..3bd02571f30d 100644
--- a/fs/afs/proc.c
+++ b/fs/afs/proc.c
@@ -443,8 +443,8 @@ static int afs_proc_servers_show(struct seq_file *m, void *v)
 		   refcount_read(&server->ref),
 		   atomic_read(&server->active),
 		   server->cell->name);
-	seq_printf(m, "  - info: fl=%lx rtt=%u brk=%x\n",
-		   server->flags, server->rtt, server->cb_s_break);
+	seq_printf(m, "  - info: fl=%lx rtt=%u\n",
+		   server->flags, server->rtt);
 	seq_printf(m, "  - probe: last=%d\n",
 		   (int)(jiffies - server->probed_at) / HZ);
 	failed = estate->failed_set;
diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c
index 5c50c9aa1f87..a8554b4d91b8 100644
--- a/fs/afs/rotate.c
+++ b/fs/afs/rotate.c
@@ -59,7 +59,7 @@ static bool afs_start_fs_iteration(struct afs_operation *op,
 		write_seqlock(&vnode->cb_lock);
 		ASSERTCMP(cb_server, ==, vnode->cb_server);
 		vnode->cb_server = NULL;
-		if (test_and_clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags))
+		if (atomic64_xchg(&vnode->cb_expires_at, AFS_NO_CB_PROMISE) != AFS_NO_CB_PROMISE)
 			vnode->cb_break++;
 		write_sequnlock(&vnode->cb_lock);
 	}
@@ -140,6 +140,22 @@ bool afs_select_fileserver(struct afs_operation *op)
 	switch (op->call_error) {
 	case 0:
 		op->cumul_error.responded = true;
+
+		/* We succeeded, but we may need to redo the op from another
+		 * server if we're looking at a set of RO volumes where some of
+		 * the servers have not yet been brought up to date lest we
+		 * regress the data.  We only switch to the new version once
+		 * >=50% of the servers are updated.
+		 */
+		error = afs_update_volume_state(op);
+		if (error != 0) {
+			if (error == 1) {
+				afs_sleep_and_retry(op);
+				goto restart_from_beginning;
+			}
+			afs_op_set_error(op, error);
+			goto failed;
+		}
 		fallthrough;
 	default:
 		/* Success or local failure.  Stop. */
@@ -484,10 +500,8 @@ selected_server:
 	op->server = server;
 	if (vnode->cb_server != server) {
 		vnode->cb_server = server;
-		vnode->cb_s_break = server->cb_s_break;
-		vnode->cb_fs_s_break = atomic_read(&server->cell->fs_s_break);
-		vnode->cb_v_break = atomic_read(&vnode->volume->cb_v_break);
-		clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags);
+		vnode->cb_v_check = atomic_read(&vnode->volume->cb_v_break);
+		atomic64_set(&vnode->cb_expires_at, AFS_NO_CB_PROMISE);
 	}
 
 	read_lock(&server->fs_lock);
diff --git a/fs/afs/server_list.c b/fs/afs/server_list.c
index fb0f4afcb304..ac4a7afff45e 100644
--- a/fs/afs/server_list.c
+++ b/fs/afs/server_list.c
@@ -110,6 +110,7 @@ struct afs_server_list *afs_alloc_server_list(struct afs_volume *volume,
 		slist->servers[j].server = server;
 		slist->servers[j].volume = volume;
 		slist->servers[j].flags = se_flags;
+		slist->servers[j].cb_expires_at = AFS_NO_CB_PROMISE;
 		slist->nr_servers++;
 	}
 
@@ -210,6 +211,7 @@ void afs_reattach_volume_to_servers(struct afs_volume *volume, struct afs_server
 		int diff;
 
 		if (pn && po && pn->server == po->server) {
+			pn->cb_expires_at = po->cb_expires_at;
 			list_replace(&po->slink, &pn->slink);
 			n++;
 			o++;
diff --git a/fs/afs/validation.c b/fs/afs/validation.c
index 6aadd5e075e4..46b37f2cce7d 100644
--- a/fs/afs/validation.c
+++ b/fs/afs/validation.c
@@ -10,6 +10,131 @@
 #include <linux/sched.h>
 #include "internal.h"
 
+/*
+ * Data validation is managed through a number of mechanisms from the server:
+ *
+ *  (1) On first contact with a server (such as if it has just been rebooted),
+ *      the server sends us a CB.InitCallBackState* request.
+ *
+ *  (2) On a RW volume, in response to certain vnode (inode)-accessing RPC
+ *      calls, the server maintains a time-limited per-vnode promise that it
+ *      will send us a CB.CallBack request if a third party alters the vnodes
+ *      accessed.
+ *
+ *      Note that a vnode-level callbacks may also be sent for other reasons,
+ *      such as filelock release.
+ *
+ *  (3) On a RO (or Backup) volume, in response to certain vnode-accessing RPC
+ *      calls, each server maintains a time-limited per-volume promise that it
+ *      will send us a CB.CallBack request if the RO volume is updated to a
+ *      snapshot of the RW volume ("vos release").  This is an atomic event
+ *      that cuts over all instances of the RO volume across multiple servers
+ *      simultaneously.
+ *
+ *	Note that a volume-level callbacks may also be sent for other reasons,
+ *	such as the volumeserver taking over control of the volume from the
+ *	fileserver.
+ *
+ *	Note also that each server maintains an independent time limit on an
+ *	independent callback.
+ *
+ *  (4) Certain RPC calls include a volume information record "VolSync" in
+ *      their reply.  This contains a creation date for the volume that should
+ *      remain unchanged for a RW volume (but will be changed if the volume is
+ *      restored from backup) or will be bumped to the time of snapshotting
+ *      when a RO volume is released.
+ *
+ * In order to track this events, the following are provided:
+ *
+ *	->cb_v_break.  A counter of events that might mean that the contents of
+ *	a volume have been altered since we last checked a vnode.
+ *
+ *	->cb_v_check.  A counter of the number of events that we've sent a
+ *	query to the server for.  Everything's up to date if this equals
+ *	cb_v_break.
+ *
+ *	->cb_scrub.  A counter of the number of regression events for which we
+ *	have to completely wipe the cache.
+ *
+ *	->cb_ro_snapshot.  A counter of the number of times that we've
+ *      recognised that a RO volume has been updated.
+ *
+ *	->cb_break.  A counter of events that might mean that the contents of a
+ *      vnode have been altered.
+ *
+ *	->cb_expires_at.  The time at which the callback promise expires or
+ *      AFS_NO_CB_PROMISE if we have no promise.
+ *
+ * The way we manage things is:
+ *
+ *  (1) When a volume-level CB.CallBack occurs, we increment ->cb_v_break on
+ *      the volume and reset ->cb_expires_at (ie. set AFS_NO_CB_PROMISE) on the
+ *      volume and volume's server record.
+ *
+ *  (2) When a CB.InitCallBackState occurs, we treat this as a volume-level
+ *	callback break on all the volumes that have been using that volume
+ *	(ie. increment ->cb_v_break and reset ->cb_expires_at).
+ *
+ *  (3) When a vnode-level CB.CallBack occurs, we increment ->cb_break on the
+ *	vnode and reset its ->cb_expires_at.  If the vnode is mmapped, we also
+ *	dispatch a work item to unmap all PTEs to the vnode's pagecache to
+ *	force reentry to the filesystem for revalidation.
+ *
+ *  (4) When entering the filesystem, we call afs_validate() to check the
+ *	validity of a vnode.  This first checks to see if ->cb_v_check and
+ *	->cb_v_break match, and if they don't, we lock volume->cb_check_lock
+ *	exclusively and perform an FS.FetchStatus on the vnode.
+ *
+ *	After checking the volume, we check the vnode.  If there's a mismatch
+ *	between the volume counters and the vnode's mirrors of those counters,
+ *	we lock vnode->validate_lock and issue an FS.FetchStatus on the vnode.
+ *
+ *  (5) When the reply from FS.FetchStatus arrives, the VolSync record is
+ *      parsed:
+ *
+ *	(A) If the Creation timestamp has changed on a RW volume or regressed
+ *	    on a RO volume, we try to increment ->cb_scrub; if it advances on a
+ *	    RO volume, we assume "vos release" happened and try to increment
+ *	    ->cb_ro_snapshot.
+ *
+ *      (B) If the Update timestamp has regressed, we try to increment
+ *	    ->cb_scrub.
+ *
+ *      Note that in both of these cases, we only do the increment if we can
+ *      cmpxchg the value of the timestamp from the value we noted before the
+ *      op.  This tries to prevent parallel ops from fighting one another.
+ *
+ *	volume->cb_v_check is then set to ->cb_v_break.
+ *
+ *  (6) The AFSCallBack record included in the FS.FetchStatus reply is also
+ *	parsed and used to set the promise in ->cb_expires_at for the vnode,
+ *	the volume and the volume's server record.
+ *
+ *  (7) If ->cb_scrub is seen to have advanced, we invalidate the pagecache for
+ *      the vnode.
+ */
+
+/*
+ * Check the validity of a vnode/inode and its parent volume.
+ */
+bool afs_check_validity(const struct afs_vnode *vnode)
+{
+	const struct afs_volume *volume = vnode->volume;
+	time64_t deadline = ktime_get_real_seconds() + 10;
+
+	if (atomic_read(&volume->cb_v_check) != atomic_read(&volume->cb_v_break) ||
+	    atomic64_read(&vnode->cb_expires_at)  <= deadline ||
+	    volume->cb_expires_at <= deadline ||
+	    vnode->cb_ro_snapshot != atomic_read(&volume->cb_ro_snapshot) ||
+	    vnode->cb_scrub	  != atomic_read(&volume->cb_scrub) ||
+	    test_bit(AFS_VNODE_ZAP_DATA, &vnode->flags)) {
+		_debug("inval");
+		return false;
+	}
+
+	return true;
+}
+
 /*
  * See if the server we've just talked to is currently excluded.
  */
@@ -185,11 +310,17 @@ out:
 }
 
 /*
- * Update the state of a volume.  Returns 1 to redo the operation from the start.
+ * Update the state of a volume, including recording the expiration time of the
+ * callback promise.  Returns 1 to redo the operation from the start.
  */
 int afs_update_volume_state(struct afs_operation *op)
 {
+	struct afs_server_list *slist = op->server_list;
+	struct afs_server_entry *se = &slist->servers[op->server_index];
+	struct afs_callback *cb = &op->file[0].scb.callback;
 	struct afs_volume *volume = op->volume;
+	unsigned int cb_v_break = atomic_read(&volume->cb_v_break);
+	unsigned int cb_v_check = atomic_read(&volume->cb_v_check);
 	int ret;
 
 	_enter("%llx", op->volume->vid);
@@ -202,6 +333,18 @@ int afs_update_volume_state(struct afs_operation *op)
 		}
 	}
 
+	if (op->cb_v_break == cb_v_break &&
+	    (op->file[0].scb.have_cb || op->file[1].scb.have_cb)) {
+		time64_t expires_at = cb->expires_at;
+
+		if (!op->file[0].scb.have_cb)
+			expires_at = op->file[1].scb.callback.expires_at;
+
+		se->cb_expires_at = expires_at;
+		volume->cb_expires_at = expires_at;
+	}
+	if (cb_v_check < op->cb_v_break)
+		atomic_cmpxchg(&volume->cb_v_check, cb_v_check, op->cb_v_break);
 	return 0;
 }
 
@@ -224,99 +367,6 @@ static void afs_zap_data(struct afs_vnode *vnode)
 		invalidate_inode_pages2(vnode->netfs.inode.i_mapping);
 }
 
-/*
- * Check to see if we have a server currently serving this volume and that it
- * hasn't been reinitialised or dropped from the list.
- */
-static bool afs_check_server_good(struct afs_vnode *vnode)
-{
-	struct afs_server_list *slist;
-	struct afs_server *server;
-	bool good;
-	int i;
-
-	if (vnode->cb_fs_s_break == atomic_read(&vnode->volume->cell->fs_s_break))
-		return true;
-
-	rcu_read_lock();
-
-	slist = rcu_dereference(vnode->volume->servers);
-	for (i = 0; i < slist->nr_servers; i++) {
-		server = slist->servers[i].server;
-		if (server == vnode->cb_server) {
-			good = (vnode->cb_s_break == server->cb_s_break);
-			rcu_read_unlock();
-			return good;
-		}
-	}
-
-	rcu_read_unlock();
-	return false;
-}
-
-/*
- * Check the validity of a vnode/inode.
- */
-bool afs_check_validity(struct afs_vnode *vnode)
-{
-	enum afs_cb_break_reason need_clear = afs_cb_break_no_break;
-	time64_t now = ktime_get_real_seconds();
-	unsigned int cb_break;
-	int seq;
-
-	do {
-		seq = read_seqbegin(&vnode->cb_lock);
-		cb_break = vnode->cb_break;
-
-		if (test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) {
-			if (vnode->cb_v_break != atomic_read(&vnode->volume->cb_v_break))
-				need_clear = afs_cb_break_for_v_break;
-			else if (!afs_check_server_good(vnode))
-				need_clear = afs_cb_break_for_s_reinit;
-			else if (test_bit(AFS_VNODE_ZAP_DATA, &vnode->flags))
-				need_clear = afs_cb_break_for_zap;
-			else if (vnode->cb_expires_at - 10 <= now)
-				need_clear = afs_cb_break_for_lapsed;
-		} else if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) {
-			;
-		} else {
-			need_clear = afs_cb_break_no_promise;
-		}
-
-	} while (read_seqretry(&vnode->cb_lock, seq));
-
-	if (need_clear == afs_cb_break_no_break)
-		return true;
-
-	write_seqlock(&vnode->cb_lock);
-	if (need_clear == afs_cb_break_no_promise)
-		vnode->cb_v_break = atomic_read(&vnode->volume->cb_v_break);
-	else if (cb_break == vnode->cb_break)
-		__afs_break_callback(vnode, need_clear);
-	else
-		trace_afs_cb_miss(&vnode->fid, need_clear);
-	write_sequnlock(&vnode->cb_lock);
-	return false;
-}
-
-/*
- * Returns true if the pagecache is still valid.  Does not sleep.
- */
-bool afs_pagecache_valid(struct afs_vnode *vnode)
-{
-	if (unlikely(test_bit(AFS_VNODE_DELETED, &vnode->flags))) {
-		if (vnode->netfs.inode.i_nlink)
-			clear_nlink(&vnode->netfs.inode);
-		return true;
-	}
-
-	if (test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags) &&
-	    afs_check_validity(vnode))
-		return true;
-
-	return false;
-}
-
 /*
  * validate a vnode/inode
  * - there are several things we need to check
@@ -328,23 +378,48 @@ bool afs_pagecache_valid(struct afs_vnode *vnode)
  */
 int afs_validate(struct afs_vnode *vnode, struct key *key)
 {
+	struct afs_volume *volume = vnode->volume;
+	unsigned int cb_ro_snapshot, cb_scrub;
+	time64_t deadline = ktime_get_real_seconds() + 10;
+	bool zap = false, locked_vol = false;
 	int ret;
 
 	_enter("{v={%llx:%llu} fl=%lx},%x",
 	       vnode->fid.vid, vnode->fid.vnode, vnode->flags,
 	       key_serial(key));
 
-	if (afs_pagecache_valid(vnode))
-		goto valid;
+	if (afs_check_validity(vnode))
+		return 0;
 
-	down_write(&vnode->validate_lock);
+	ret = down_write_killable(&vnode->validate_lock);
+	if (ret < 0)
+		goto error;
+
+	/* Validate a volume after the v_break has changed or the volume
+	 * callback expired.  We only want to do this once per volume per
+	 * v_break change.  The actual work will be done when parsing the
+	 * status fetch reply.
+	 */
+	if (volume->cb_expires_at <= deadline ||
+	    atomic_read(&volume->cb_v_check) != atomic_read(&volume->cb_v_break)) {
+		ret = mutex_lock_interruptible(&volume->cb_check_lock);
+		if (ret < 0)
+			goto error_unlock;
+		locked_vol = true;
+	}
 
-	/* if the promise has expired, we need to check the server again to get
-	 * a new promise - note that if the (parent) directory's metadata was
-	 * changed then the security may be different and we may no longer have
-	 * access */
-	if (!test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) {
-		_debug("not promised");
+	cb_ro_snapshot = atomic_read(&volume->cb_ro_snapshot);
+	cb_scrub = atomic_read(&volume->cb_scrub);
+	if (vnode->cb_ro_snapshot != cb_ro_snapshot ||
+	    vnode->cb_scrub	  != cb_scrub)
+		unmap_mapping_pages(vnode->netfs.inode.i_mapping, 0, 0, false);
+
+	if (vnode->cb_ro_snapshot != cb_ro_snapshot ||
+	    vnode->cb_scrub	  != cb_scrub ||
+	    volume->cb_expires_at <= deadline ||
+	    atomic_read(&volume->cb_v_check) != atomic_read(&volume->cb_v_break) ||
+	    atomic64_read(&vnode->cb_expires_at) <= deadline
+	    ) {
 		ret = afs_fetch_status(vnode, key, false, NULL);
 		if (ret < 0) {
 			if (ret == -ENOENT) {
@@ -353,9 +428,26 @@ int afs_validate(struct afs_vnode *vnode, struct key *key)
 			}
 			goto error_unlock;
 		}
+
 		_debug("new promise [fl=%lx]", vnode->flags);
 	}
 
+	/* We can drop the volume lock now as. */
+	if (locked_vol) {
+		mutex_unlock(&volume->cb_check_lock);
+		locked_vol = false;
+	}
+
+	cb_ro_snapshot = atomic_read(&volume->cb_ro_snapshot);
+	cb_scrub = atomic_read(&volume->cb_scrub);
+	_debug("vnode inval %x==%x %x==%x",
+	       vnode->cb_ro_snapshot, cb_ro_snapshot,
+	       vnode->cb_scrub, cb_scrub);
+	if (vnode->cb_scrub != cb_scrub)
+		zap = true;
+	vnode->cb_ro_snapshot = cb_ro_snapshot;
+	vnode->cb_scrub = cb_scrub;
+
 	if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) {
 		_debug("file already deleted");
 		ret = -ESTALE;
@@ -364,15 +456,18 @@ int afs_validate(struct afs_vnode *vnode, struct key *key)
 
 	/* if the vnode's data version number changed then its contents are
 	 * different */
-	if (test_and_clear_bit(AFS_VNODE_ZAP_DATA, &vnode->flags))
+	zap |= test_and_clear_bit(AFS_VNODE_ZAP_DATA, &vnode->flags);
+	if (zap)
 		afs_zap_data(vnode);
 	up_write(&vnode->validate_lock);
-valid:
 	_leave(" = 0");
 	return 0;
 
 error_unlock:
+	if (locked_vol)
+		mutex_unlock(&volume->cb_check_lock);
 	up_write(&vnode->validate_lock);
+error:
 	_leave(" = %d", ret);
 	return ret;
 }
diff --git a/fs/afs/volume.c b/fs/afs/volume.c
index 41ab1d3ff3ea..cc207dca1b21 100644
--- a/fs/afs/volume.c
+++ b/fs/afs/volume.c
@@ -98,7 +98,10 @@ static struct afs_volume *afs_alloc_volume(struct afs_fs_context *params,
 	INIT_WORK(&volume->destructor, afs_destroy_volume);
 	rwlock_init(&volume->servers_lock);
 	mutex_init(&volume->volsync_lock);
+	mutex_init(&volume->cb_check_lock);
 	rwlock_init(&volume->cb_v_break_lock);
+	INIT_LIST_HEAD(&volume->open_mmaps);
+	init_rwsem(&volume->open_mmaps_lock);
 	memcpy(volume->name, vldb->name, vldb->name_len + 1);
 
 	for (i = 0; i < AFS_MAXTYPES; i++)
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index bbe8dcab4b32..2df7d0fd3f21 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -438,18 +438,14 @@ enum yfs_cm_operation {
 
 #define afs_cb_break_reasons						\
 	EM(afs_cb_break_no_break,		"no-break")		\
-	EM(afs_cb_break_no_promise,		"no-promise")		\
 	EM(afs_cb_break_for_callback,		"break-cb")		\
 	EM(afs_cb_break_for_creation_regress,	"creation-regress")	\
 	EM(afs_cb_break_for_deleted,		"break-del")		\
-	EM(afs_cb_break_for_lapsed,		"break-lapsed")		\
 	EM(afs_cb_break_for_s_reinit,		"s-reinit")		\
 	EM(afs_cb_break_for_unlink,		"break-unlink")		\
 	EM(afs_cb_break_for_update_regress,	"update-regress")	\
-	EM(afs_cb_break_for_v_break,		"break-v")		\
 	EM(afs_cb_break_for_volume_callback,	"break-v-cb")		\
 	EM(afs_cb_break_for_vos_release,	"break-vos-release")	\
-	EM(afs_cb_break_for_zap,		"break-zap")		\
 	E_(afs_cb_break_volume_excluded,	"vol-excluded")
 
 /*
-- 
cgit v1.2.3


From 495f2ae9e3552c30f7b83be3d142a932885d506e Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 18 Oct 2023 09:24:01 +0100
Subject: afs: Fix fileserver rotation

Fix the fileserver rotation so that it doesn't use RTT as the basis for
deciding which server and address to use as this doesn't necessarily give a
good indication of the best path.  Instead, use the configurable preference
list in conjunction with whatever probes have succeeded at the time of
looking.

To this end, make the following changes:

 (1) Keep an array of "server states" to track what addresses we've tried
     on each server and move the waitqueue entries there that we'll need
     for probing.

 (2) Each afs_server_state struct is made to pin the corresponding server's
     endpoint state rather than the afs_operation struct carrying a pin on
     the server we're currently looking at.

 (3) Drop the server list preference; we now always rescan the server list.

 (4) afs_wait_for_probes() now uses the server state list to guide it in
     what it waits for (and to provide the waitqueue entries) and returns
     an indication of whether we'd got a response, run out of responsive
     addresses or the endpoint state had been superseded and we need to
     restart the iteration.

 (5) Call afs_get_address_preferences*() occasionally to refresh the
     preference values.

 (6) When picking a server, scan the addresses of the servers for which we
     have as-yet untested communications, looking for the highest priority
     one and use that instead of trying all the addresses for a particular
     server in ascending-RTT order.

 (7) When a Busy or Offline state is seen across all available servers, do
     a short sleep.

 (8) If we detect that we accessed a future RO volume version whilst it is
     undergoing replication, reissue the op against the older version until
     at least half of the servers are replicated.

 (9) Whilst RO replication is ongoing, increase the frequency of Volume
     Location server checks for that volume to every ten minutes instead of
     hourly.

Also add a tracepoint to track progress through the rotation algorithm.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
---
 fs/afs/fs_operation.c      |   8 +-
 fs/afs/fs_probe.c          | 103 ++++++++++----------------
 fs/afs/internal.h          |  23 +++++-
 fs/afs/rotate.c            | 178 +++++++++++++++++++++++++++++++++------------
 fs/afs/server_list.c       |  14 +---
 fs/afs/volume.c            |   6 +-
 include/trace/events/afs.h |  81 ++++++++++++++++++---
 7 files changed, 267 insertions(+), 146 deletions(-)

(limited to 'include')

diff --git a/fs/afs/fs_operation.c b/fs/afs/fs_operation.c
index cecc44af6a5f..3546b087e791 100644
--- a/fs/afs/fs_operation.c
+++ b/fs/afs/fs_operation.c
@@ -229,7 +229,6 @@ void afs_wait_for_operation(struct afs_operation *op)
  */
 int afs_put_operation(struct afs_operation *op)
 {
-	struct afs_endpoint_state *estate = op->estate;
 	struct afs_addr_list *alist;
 	int i, ret = afs_op_error(op);
 
@@ -253,18 +252,17 @@ int afs_put_operation(struct afs_operation *op)
 		kfree(op->more_files);
 	}
 
-	if (estate) {
-		alist = estate->addresses;
+	if (op->estate) {
+		alist = op->estate->addresses;
 		if (alist) {
 			if (op->call_responded &&
 			    op->addr_index != alist->preferred &&
 			    test_bit(alist->preferred, &op->addr_tried))
 				WRITE_ONCE(alist->preferred, op->addr_index);
 		}
-		afs_put_endpoint_state(estate, afs_estate_trace_put_operation);
-		op->estate = NULL;
 	}
 
+	afs_clear_server_states(op);
 	afs_put_serverlist(op->net, op->server_list);
 	afs_put_volume(op->volume, afs_volume_trace_put_put_op);
 	key_put(op->key);
diff --git a/fs/afs/fs_probe.c b/fs/afs/fs_probe.c
index c00d38b98a67..580de4adaaf6 100644
--- a/fs/afs/fs_probe.c
+++ b/fs/afs/fs_probe.c
@@ -296,58 +296,48 @@ void afs_fs_probe_fileserver(struct afs_net *net, struct afs_server *server,
 }
 
 /*
- * Wait for the first as-yet untried fileserver to respond.
+ * Wait for the first as-yet untried fileserver to respond, for the probe state
+ * to be superseded or for all probes to finish.
  */
-int afs_wait_for_fs_probes(struct afs_server_list *slist, unsigned long untried)
+int afs_wait_for_fs_probes(struct afs_operation *op, struct afs_server_state *states, bool intr)
 {
 	struct afs_endpoint_state *estate;
-	struct wait_queue_entry *waits;
-	struct afs_server *server;
-	unsigned int rtt = UINT_MAX, rtt_s;
-	bool have_responders = false;
-	int pref = -1, i;
+	struct afs_server_list *slist = op->server_list;
+	bool still_probing = true;
+	int ret = 0, i;
 
-	_enter("%u,%lx", slist->nr_servers, untried);
+	_enter("%u", slist->nr_servers);
 
-	/* Only wait for servers that have a probe outstanding. */
-	rcu_read_lock();
 	for (i = 0; i < slist->nr_servers; i++) {
-		if (test_bit(i, &untried)) {
-			server = slist->servers[i].server;
-			estate = rcu_dereference(server->endpoint_state);
-			if (!atomic_read(&estate->nr_probing))
-				__clear_bit(i, &untried);
-			if (test_bit(AFS_ESTATE_RESPONDED, &estate->flags))
-				have_responders = true;
-		}
+		estate = states[i].endpoint_state;
+		if (test_bit(AFS_ESTATE_SUPERSEDED, &estate->flags))
+			return 2;
+		if (atomic_read(&estate->nr_probing))
+			still_probing = true;
+		if (estate->responsive_set & states[i].untried_addrs)
+			return 1;
 	}
-	rcu_read_unlock();
-	if (have_responders || !untried)
+	if (!still_probing)
 		return 0;
 
-	waits = kmalloc(array_size(slist->nr_servers, sizeof(*waits)), GFP_KERNEL);
-	if (!waits)
-		return -ENOMEM;
-
-	for (i = 0; i < slist->nr_servers; i++) {
-		if (test_bit(i, &untried)) {
-			server = slist->servers[i].server;
-			init_waitqueue_entry(&waits[i], current);
-			add_wait_queue(&server->probe_wq, &waits[i]);
-		}
-	}
+	for (i = 0; i < slist->nr_servers; i++)
+		add_wait_queue(&slist->servers[i].server->probe_wq, &states[i].probe_waiter);
 
 	for (;;) {
-		bool still_probing = false;
+		still_probing = false;
 
-		set_current_state(TASK_INTERRUPTIBLE);
+		set_current_state(intr ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE);
 		for (i = 0; i < slist->nr_servers; i++) {
-			if (test_bit(i, &untried)) {
-				server = slist->servers[i].server;
-				if (test_bit(AFS_ESTATE_RESPONDED, &estate->flags))
-					goto stop;
-				if (atomic_read(&estate->nr_probing))
-					still_probing = true;
+			estate = states[i].endpoint_state;
+			if (test_bit(AFS_ESTATE_SUPERSEDED, &estate->flags)) {
+				ret = 2;
+				goto stop;
+			}
+			if (atomic_read(&estate->nr_probing))
+				still_probing = true;
+			if (estate->responsive_set & states[i].untried_addrs) {
+				ret = 1;
+				goto stop;
 			}
 		}
 
@@ -359,28 +349,12 @@ int afs_wait_for_fs_probes(struct afs_server_list *slist, unsigned long untried)
 stop:
 	set_current_state(TASK_RUNNING);
 
-	for (i = 0; i < slist->nr_servers; i++) {
-		if (test_bit(i, &untried)) {
-			server = slist->servers[i].server;
-			rtt_s = READ_ONCE(server->rtt);
-			if (test_bit(AFS_SERVER_FL_RESPONDING, &server->flags) &&
-			    rtt_s < rtt) {
-				pref = i;
-				rtt = rtt_s;
-			}
-
-			remove_wait_queue(&server->probe_wq, &waits[i]);
-		}
-	}
-
-	kfree(waits);
-
-	if (pref == -1 && signal_pending(current))
-		return -ERESTARTSYS;
+	for (i = 0; i < slist->nr_servers; i++)
+		remove_wait_queue(&slist->servers[i].server->probe_wq, &states[i].probe_waiter);
 
-	if (pref >= 0)
-		slist->preferred = pref;
-	return 0;
+	if (!ret && signal_pending(current))
+		ret = -ERESTARTSYS;
+	return ret;
 }
 
 /*
@@ -508,7 +482,7 @@ again:
  * Wait for a probe on a particular fileserver to complete for 2s.
  */
 int afs_wait_for_one_fs_probe(struct afs_server *server, struct afs_endpoint_state *estate,
-			      bool is_intr)
+			      unsigned long exclude, bool is_intr)
 {
 	struct wait_queue_entry wait;
 	unsigned long timo = 2 * HZ;
@@ -521,7 +495,8 @@ int afs_wait_for_one_fs_probe(struct afs_server *server, struct afs_endpoint_sta
 		prepare_to_wait_event(&server->probe_wq, &wait,
 				      is_intr ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE);
 		if (timo == 0 ||
-		    test_bit(AFS_ESTATE_RESPONDED, &estate->flags) ||
+		    test_bit(AFS_ESTATE_SUPERSEDED, &estate->flags) ||
+		    (estate->responsive_set & ~exclude) ||
 		    atomic_read(&estate->nr_probing) == 0 ||
 		    (is_intr && signal_pending(current)))
 			break;
@@ -531,7 +506,9 @@ int afs_wait_for_one_fs_probe(struct afs_server *server, struct afs_endpoint_sta
 	finish_wait(&server->probe_wq, &wait);
 
 dont_wait:
-	if (test_bit(AFS_ESTATE_RESPONDED, &estate->flags))
+	if (estate->responsive_set & ~exclude)
+		return 1;
+	if (test_bit(AFS_ESTATE_SUPERSEDED, &estate->flags))
 		return 0;
 	if (is_intr && signal_pending(current))
 		return -ERESTARTSYS;
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 6d0cd886b548..e3e373c1fecf 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -620,7 +620,6 @@ struct afs_server_list {
 	bool			attached;	/* T if attached to servers */
 	enum afs_ro_replicating	ro_replicating;	/* RW->RO update (probably) in progress */
 	unsigned char		nr_servers;
-	unsigned char		preferred;	/* Preferred server */
 	unsigned short		vnovol_mask;	/* Servers to be skipped due to VNOVOL */
 	unsigned int		seq;		/* Set to ->servers_seq when installed */
 	rwlock_t		lock;
@@ -821,6 +820,20 @@ struct afs_vl_cursor {
 	bool			call_responded;	/* T if the current address responded */
 };
 
+/*
+ * Fileserver state tracking for an operation.  An array of these is kept,
+ * indexed by server index.
+ */
+struct afs_server_state {
+	/* Tracking of fileserver probe state.  Other operations may interfere
+	 * by probing a fileserver when accessing other volumes.
+	 */
+	unsigned int		probe_seq;
+	unsigned long		untried_addrs;	/* Addresses we haven't tried yet */
+	struct wait_queue_entry	probe_waiter;
+	struct afs_endpoint_state *endpoint_state; /* Endpoint state being monitored */
+};
+
 /*
  * Fileserver operation methods.
  */
@@ -921,7 +934,8 @@ struct afs_operation {
 	/* Fileserver iteration state */
 	struct afs_server_list	*server_list;	/* Current server list (pins ref) */
 	struct afs_server	*server;	/* Server we're using (ref pinned by server_list) */
-	struct afs_endpoint_state *estate;	/* Current endpoint state (pins ref) */
+	struct afs_endpoint_state *estate;	/* Current endpoint state (doesn't pin ref) */
+	struct afs_server_state	*server_states;	/* States of the servers involved */
 	struct afs_call		*call;
 	unsigned long		untried_servers; /* Bitmask of untried servers */
 	unsigned long		addr_tried;	/* Tried addresses */
@@ -1235,11 +1249,11 @@ void afs_put_endpoint_state(struct afs_endpoint_state *estate, enum afs_estate_t
 extern void afs_fileserver_probe_result(struct afs_call *);
 void afs_fs_probe_fileserver(struct afs_net *net, struct afs_server *server,
 			     struct afs_addr_list *new_addrs, struct key *key);
-extern int afs_wait_for_fs_probes(struct afs_server_list *, unsigned long);
+int afs_wait_for_fs_probes(struct afs_operation *op, struct afs_server_state *states, bool intr);
 extern void afs_probe_fileserver(struct afs_net *, struct afs_server *);
 extern void afs_fs_probe_dispatcher(struct work_struct *);
 int afs_wait_for_one_fs_probe(struct afs_server *server, struct afs_endpoint_state *estate,
-			      bool is_intr);
+			      unsigned long exclude, bool is_intr);
 extern void afs_fs_probe_cleanup(struct afs_net *);
 
 /*
@@ -1363,6 +1377,7 @@ static inline void afs_put_sysnames(struct afs_sysnames *sysnames) {}
 /*
  * rotate.c
  */
+void afs_clear_server_states(struct afs_operation *op);
 extern bool afs_select_fileserver(struct afs_operation *);
 extern void afs_dump_edestaddrreq(const struct afs_operation *);
 
diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c
index a8554b4d91b8..ef7fe70777be 100644
--- a/fs/afs/rotate.c
+++ b/fs/afs/rotate.c
@@ -15,6 +15,18 @@
 #include "afs_fs.h"
 #include "protocol_uae.h"
 
+void afs_clear_server_states(struct afs_operation *op)
+{
+	unsigned int i;
+
+	if (op->server_states) {
+		for (i = 0; i < op->server_list->nr_servers; i++)
+			afs_put_endpoint_state(op->server_states[i].endpoint_state,
+					       afs_estate_trace_put_server_state);
+		kfree(op->server_states);
+	}
+}
+
 /*
  * Begin iteration through a server list, starting with the vnode's last used
  * server if possible, or the last recorded good server if not.
@@ -26,14 +38,41 @@ static bool afs_start_fs_iteration(struct afs_operation *op,
 	void *cb_server;
 	int i;
 
+	trace_afs_rotate(op, afs_rotate_trace_start, 0);
+
 	read_lock(&op->volume->servers_lock);
 	op->server_list = afs_get_serverlist(
 		rcu_dereference_protected(op->volume->servers,
 					  lockdep_is_held(&op->volume->servers_lock)));
 	read_unlock(&op->volume->servers_lock);
 
+	op->server_states = kcalloc(op->server_list->nr_servers, sizeof(op->server_states[0]),
+				    GFP_KERNEL);
+	if (!op->server_states) {
+		afs_op_nomem(op);
+		trace_afs_rotate(op, afs_rotate_trace_nomem, 0);
+		return false;
+	}
+
+	rcu_read_lock();
+	for (i = 0; i < op->server_list->nr_servers; i++) {
+		struct afs_endpoint_state *estate;
+		struct afs_server_state *s = &op->server_states[i];
+
+		server = op->server_list->servers[i].server;
+		estate = rcu_dereference(server->endpoint_state);
+		s->endpoint_state = afs_get_endpoint_state(estate,
+							   afs_estate_trace_get_server_state);
+		s->probe_seq = estate->probe_seq;
+		s->untried_addrs = (1UL << estate->addresses->nr_addrs) - 1;
+		init_waitqueue_entry(&s->probe_waiter, current);
+		afs_get_address_preferences(op->net, estate->addresses);
+	}
+	rcu_read_unlock();
+
+
 	op->untried_servers = (1UL << op->server_list->nr_servers) - 1;
-	op->server_index = READ_ONCE(op->server_list->preferred);
+	op->server_index = -1;
 
 	cb_server = vnode->cb_server;
 	if (cb_server) {
@@ -52,6 +91,7 @@ static bool afs_start_fs_iteration(struct afs_operation *op,
 		 */
 		if (op->flags & AFS_OPERATION_CUR_ONLY) {
 			afs_op_set_error(op, -ESTALE);
+			trace_afs_rotate(op, afs_rotate_trace_stale_lock, 0);
 			return false;
 		}
 
@@ -90,6 +130,7 @@ static void afs_busy(struct afs_volume *volume, u32 abort_code)
  */
 static bool afs_sleep_and_retry(struct afs_operation *op)
 {
+	trace_afs_rotate(op, afs_rotate_trace_busy_sleep, 0);
 	if (!(op->flags & AFS_OPERATION_UNINTR)) {
 		msleep_interruptible(1000);
 		if (signal_pending(current)) {
@@ -109,14 +150,13 @@ static bool afs_sleep_and_retry(struct afs_operation *op)
  */
 bool afs_select_fileserver(struct afs_operation *op)
 {
-	struct afs_endpoint_state *estate = op->estate;
 	struct afs_addr_list *alist;
 	struct afs_server *server;
 	struct afs_vnode *vnode = op->file[0].vnode;
 	unsigned long set, failed;
-	unsigned int rtt;
 	s32 abort_code = op->call_abort_code;
-	int error = op->call_error, addr_index, i;
+	int best_prio = 0;
+	int error = op->call_error, addr_index, i, j;
 
 	op->nr_iterations++;
 
@@ -127,6 +167,7 @@ bool afs_select_fileserver(struct afs_operation *op)
 	       error, abort_code);
 
 	if (op->flags & AFS_OPERATION_STOP) {
+		trace_afs_rotate(op, afs_rotate_trace_stopped, 0);
 		_leave(" = f [stopped]");
 		return false;
 	}
@@ -134,7 +175,8 @@ bool afs_select_fileserver(struct afs_operation *op)
 	if (op->nr_iterations == 0)
 		goto start;
 
-	WRITE_ONCE(estate->addresses->addrs[op->addr_index].last_error, error);
+	WRITE_ONCE(op->estate->addresses->addrs[op->addr_index].last_error, error);
+	trace_afs_rotate(op, afs_rotate_trace_iter, op->call_error);
 
 	/* Evaluate the result of the previous operation, if there was one. */
 	switch (op->call_error) {
@@ -161,6 +203,7 @@ bool afs_select_fileserver(struct afs_operation *op)
 		/* Success or local failure.  Stop. */
 		afs_op_set_error(op, error);
 		op->flags |= AFS_OPERATION_STOP;
+		trace_afs_rotate(op, afs_rotate_trace_stop, error);
 		_leave(" = f [okay/local %d]", error);
 		return false;
 
@@ -173,6 +216,7 @@ bool afs_select_fileserver(struct afs_operation *op)
 		 * errors instead.  IBM AFS and OpenAFS fileservers, however, do leak
 		 * these abort codes.
 		 */
+		trace_afs_rotate(op, afs_rotate_trace_aborted, abort_code);
 		op->cumul_error.responded = true;
 		switch (abort_code) {
 		case VNOVOL:
@@ -278,10 +322,6 @@ bool afs_select_fileserver(struct afs_operation *op)
 				afs_op_set_error(op, -EADV);
 				goto failed;
 			}
-			if (op->flags & AFS_OPERATION_CUR_ONLY) {
-				afs_op_set_error(op, -ESTALE);
-				goto failed;
-			}
 			goto busy;
 
 		case VRESTARTING: /* The fileserver is either shutting down or starting up. */
@@ -417,19 +457,22 @@ bool afs_select_fileserver(struct afs_operation *op)
 	}
 
 restart_from_beginning:
+	trace_afs_rotate(op, afs_rotate_trace_restart, 0);
 	_debug("restart");
-	afs_put_endpoint_state(estate, afs_estate_trace_put_restart_rotate);
-	estate = op->estate = NULL;
+	op->estate = NULL;
 	op->server = NULL;
+	afs_clear_server_states(op);
+	op->server_states = NULL;
 	afs_put_serverlist(op->net, op->server_list);
 	op->server_list = NULL;
 start:
 	_debug("start");
-	ASSERTCMP(estate, ==, NULL);
+	ASSERTCMP(op->estate, ==, NULL);
 	/* See if we need to do an update of the volume record.  Note that the
 	 * volume may have moved or even have been deleted.
 	 */
 	error = afs_check_volume_status(op->volume, op);
+	trace_afs_rotate(op, afs_rotate_trace_check_vol_status, error);
 	if (error < 0) {
 		afs_op_set_error(op, error);
 		goto failed;
@@ -442,16 +485,29 @@ start:
 
 pick_server:
 	_debug("pick [%lx]", op->untried_servers);
-	ASSERTCMP(estate, ==, NULL);
+	ASSERTCMP(op->estate, ==, NULL);
 
-	error = afs_wait_for_fs_probes(op->server_list, op->untried_servers);
-	if (error < 0) {
+	error = afs_wait_for_fs_probes(op, op->server_states,
+				       !(op->flags & AFS_OPERATION_UNINTR));
+	switch (error) {
+	case 0: /* No untried responsive servers and no outstanding probes */
+		trace_afs_rotate(op, afs_rotate_trace_probe_none, 0);
+		goto no_more_servers;
+	case 1: /* Got a response */
+		trace_afs_rotate(op, afs_rotate_trace_probe_response, 0);
+		break;
+	case 2: /* Probe data superseded */
+		trace_afs_rotate(op, afs_rotate_trace_probe_superseded, 0);
+		goto restart_from_beginning;
+	default:
+		trace_afs_rotate(op, afs_rotate_trace_probe_error, error);
 		afs_op_set_error(op, error);
 		goto failed;
 	}
 
-	/* Pick the untried server with the lowest RTT.  If we have outstanding
-	 * callbacks, we stick with the server we're already using if we can.
+	/* Pick the untried server with the highest priority untried endpoint.
+	 * If we have outstanding callbacks, we stick with the server we're
+	 * already using if we can.
 	 */
 	if (op->server) {
 		_debug("server %u", op->server_index);
@@ -461,34 +517,47 @@ pick_server:
 		_debug("no server");
 	}
 
+	rcu_read_lock();
 	op->server_index = -1;
-	rtt = UINT_MAX;
+	best_prio = -1;
 	for (i = 0; i < op->server_list->nr_servers; i++) {
+		struct afs_endpoint_state *es;
 		struct afs_server_entry *se = &op->server_list->servers[i];
+		struct afs_addr_list *sal;
 		struct afs_server *s = se->server;
 
 		if (!test_bit(i, &op->untried_servers) ||
 		    test_bit(AFS_SE_EXCLUDED, &se->flags) ||
 		    !test_bit(AFS_SERVER_FL_RESPONDING, &s->flags))
 			continue;
-		if (s->rtt <= rtt) {
-			op->server_index = i;
-			rtt = s->rtt;
+		es = op->server_states->endpoint_state;
+		sal = es->addresses;
+
+		afs_get_address_preferences_rcu(op->net, sal);
+		for (j = 0; j < sal->nr_addrs; j++) {
+			if (!sal->addrs[j].peer)
+				continue;
+			if (sal->addrs[j].prio > best_prio) {
+				op->server_index = i;
+				best_prio = sal->addrs[j].prio;
+			}
 		}
 	}
+	rcu_read_unlock();
 
 	if (op->server_index == -1)
 		goto no_more_servers;
 
 selected_server:
-	_debug("use %d", op->server_index);
+	trace_afs_rotate(op, afs_rotate_trace_selected_server, best_prio);
+	_debug("use %d prio %u", op->server_index, best_prio);
 	__clear_bit(op->server_index, &op->untried_servers);
 
 	/* We're starting on a different fileserver from the list.  We need to
 	 * check it, create a callback intercept, find its address list and
 	 * probe its capabilities before we use it.
 	 */
-	ASSERTCMP(estate, ==, NULL);
+	ASSERTCMP(op->estate, ==, NULL);
 	server = op->server_list->servers[op->server_index].server;
 
 	if (!afs_check_server_record(op, server, op->key))
@@ -504,12 +573,6 @@ selected_server:
 		atomic64_set(&vnode->cb_expires_at, AFS_NO_CB_PROMISE);
 	}
 
-	read_lock(&server->fs_lock);
-	estate = rcu_dereference_protected(server->endpoint_state,
-					   lockdep_is_held(&server->fs_lock));
-	op->estate = afs_get_endpoint_state(estate, afs_estate_trace_get_fsrotate_set);
-	read_unlock(&server->fs_lock);
-
 retry_server:
 	op->addr_tried = 0;
 	op->addr_index = -1;
@@ -518,14 +581,23 @@ iterate_address:
 	/* Iterate over the current server's address list to try and find an
 	 * address on which it will respond to us.
 	 */
-	set = READ_ONCE(estate->responsive_set);
-	failed = READ_ONCE(estate->failed_set);
-	_debug("iterate ES=%x rs=%lx fs=%lx", estate->probe_seq, set, failed);
+	op->estate = op->server_states[op->server_index].endpoint_state;
+	set = READ_ONCE(op->estate->responsive_set);
+	failed = READ_ONCE(op->estate->failed_set);
+	_debug("iterate ES=%x rs=%lx fs=%lx", op->estate->probe_seq, set, failed);
 	set &= ~(failed | op->addr_tried);
+	trace_afs_rotate(op, afs_rotate_trace_iterate_addr, set);
 	if (!set)
-		goto out_of_addresses;
+		goto wait_for_more_probe_results;
+
+	alist = op->estate->addresses;
+	for (i = 0; i < alist->nr_addrs; i++) {
+		if (alist->addrs[i].prio > best_prio) {
+			addr_index = i;
+			best_prio = alist->addrs[i].prio;
+		}
+	}
 
-	alist = estate->addresses;
 	addr_index = READ_ONCE(alist->preferred);
 	if (!test_bit(addr_index, &set))
 		addr_index = __ffs(set);
@@ -542,17 +614,24 @@ iterate_address:
 	_leave(" = t");
 	return true;
 
-out_of_addresses:
+wait_for_more_probe_results:
+	error = afs_wait_for_one_fs_probe(op->server, op->estate, op->addr_tried,
+					  !(op->flags & AFS_OPERATION_UNINTR));
+	if (!error)
+		goto iterate_address;
+
 	/* We've now had a failure to respond on all of a server's addresses -
 	 * immediately probe them again and consider retrying the server.
 	 */
+	trace_afs_rotate(op, afs_rotate_trace_probe_fileserver, 0);
 	afs_probe_fileserver(op->net, op->server);
 	if (op->flags & AFS_OPERATION_RETRY_SERVER) {
-		error = afs_wait_for_one_fs_probe(op->server, estate,
+		error = afs_wait_for_one_fs_probe(op->server, op->estate, op->addr_tried,
 						  !(op->flags & AFS_OPERATION_UNINTR));
 		switch (error) {
 		case 0:
 			op->flags &= ~AFS_OPERATION_RETRY_SERVER;
+			trace_afs_rotate(op, afs_rotate_trace_retry_server, 0);
 			goto retry_server;
 		case -ERESTARTSYS:
 			afs_op_set_error(op, error);
@@ -564,30 +643,33 @@ out_of_addresses:
 	}
 
 next_server:
+	trace_afs_rotate(op, afs_rotate_trace_next_server, 0);
 	_debug("next");
-	ASSERT(estate);
-	alist = estate->addresses;
+	ASSERT(op->estate);
+	alist = op->estate->addresses;
 	if (op->call_responded &&
 	    op->addr_index != READ_ONCE(alist->preferred) &&
 	    test_bit(alist->preferred, &op->addr_tried))
 		WRITE_ONCE(alist->preferred, op->addr_index);
-	afs_put_endpoint_state(estate, afs_estate_trace_put_next_server);
-	estate = op->estate = NULL;
+	op->estate = NULL;
 	goto pick_server;
 
 no_more_servers:
 	/* That's all the servers poked to no good effect.  Try again if some
 	 * of them were busy.
 	 */
-	if (op->flags & AFS_OPERATION_VBUSY)
+	trace_afs_rotate(op, afs_rotate_trace_no_more_servers, 0);
+	if (op->flags & AFS_OPERATION_VBUSY) {
+		afs_sleep_and_retry(op);
+		op->flags &= ~AFS_OPERATION_VBUSY;
 		goto restart_from_beginning;
+	}
 
 	rcu_read_lock();
 	for (i = 0; i < op->server_list->nr_servers; i++) {
 		struct afs_endpoint_state *estate;
-		struct afs_server *s = op->server_list->servers[i].server;
 
-		estate = rcu_dereference(s->endpoint_state);
+		estate = op->server_states->endpoint_state;
 		error = READ_ONCE(estate->error);
 		if (error < 0)
 			afs_op_accumulate_error(op, error, estate->abort_code);
@@ -595,14 +677,14 @@ no_more_servers:
 	rcu_read_unlock();
 
 failed:
+	trace_afs_rotate(op, afs_rotate_trace_failed, 0);
 	op->flags |= AFS_OPERATION_STOP;
-	if (estate) {
-		alist = estate->addresses;
+	if (op->estate) {
+		alist = op->estate->addresses;
 		if (op->call_responded &&
 		    op->addr_index != READ_ONCE(alist->preferred) &&
 		    test_bit(alist->preferred, &op->addr_tried))
 			WRITE_ONCE(alist->preferred, op->addr_index);
-		afs_put_endpoint_state(estate, afs_estate_trace_put_op_failed);
 		op->estate = NULL;
 	}
 	_leave(" = f [failed %d]", afs_op_error(op));
@@ -635,8 +717,8 @@ void afs_dump_edestaddrreq(const struct afs_operation *op)
 	if (op->server_list) {
 		const struct afs_server_list *sl = op->server_list;
 
-		pr_notice("FC: SL nr=%u pr=%u vnov=%hx\n",
-			  sl->nr_servers, sl->preferred, sl->vnovol_mask);
+		pr_notice("FC: SL nr=%u vnov=%hx\n",
+			  sl->nr_servers, sl->vnovol_mask);
 		for (i = 0; i < sl->nr_servers; i++) {
 			const struct afs_server *s = sl->servers[i].server;
 			const struct afs_endpoint_state *e =
diff --git a/fs/afs/server_list.c b/fs/afs/server_list.c
index ac4a7afff45e..7e7e567a7f8a 100644
--- a/fs/afs/server_list.c
+++ b/fs/afs/server_list.c
@@ -134,8 +134,7 @@ bool afs_annotate_server_list(struct afs_server_list *new,
 			      struct afs_server_list *old)
 {
 	unsigned long mask = 1UL << AFS_SE_EXCLUDED;
-	struct afs_server *cur;
-	int i, j;
+	int i;
 
 	if (old->nr_servers != new->nr_servers ||
 	    old->ro_replicating != new->ro_replicating)
@@ -148,18 +147,7 @@ bool afs_annotate_server_list(struct afs_server_list *new,
 			goto changed;
 	}
 	return false;
-
 changed:
-	/* Maintain the same preferred server as before if possible. */
-	cur = old->servers[old->preferred].server;
-	for (j = 0; j < new->nr_servers; j++) {
-		if (new->servers[j].server == cur) {
-			if (!test_bit(AFS_SE_EXCLUDED, &new->servers[j].flags))
-				new->preferred = j;
-			break;
-		}
-	}
-
 	return true;
 }
 
diff --git a/fs/afs/volume.c b/fs/afs/volume.c
index cc207dca1b21..020ecd45e476 100644
--- a/fs/afs/volume.c
+++ b/fs/afs/volume.c
@@ -397,7 +397,11 @@ static int afs_update_volume_status(struct afs_volume *volume, struct key *key)
 		discard = old;
 	}
 
-	volume->update_at = ktime_get_real_seconds() + afs_volume_record_life;
+	/* Check more often if replication is ongoing. */
+	if (new->ro_replicating)
+		volume->update_at = ktime_get_real_seconds() + 10 * 60;
+	else
+		volume->update_at = ktime_get_real_seconds() + afs_volume_record_life;
 	write_unlock(&volume->servers_lock);
 
 	if (discard == old)
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index 2df7d0fd3f21..b2e0847eca47 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -230,15 +230,12 @@ enum yfs_cm_operation {
 #define afs_estate_traces \
 	EM(afs_estate_trace_alloc_probe,	"ALLOC prob") \
 	EM(afs_estate_trace_alloc_server,	"ALLOC srvr") \
-	EM(afs_estate_trace_get_fsrotate_set,	"GET fs-rot") \
+	EM(afs_estate_trace_get_server_state,	"GET srv-st") \
 	EM(afs_estate_trace_get_getcaps,	"GET getcap") \
 	EM(afs_estate_trace_put_getcaps,	"PUT getcap") \
-	EM(afs_estate_trace_put_next_server,	"PUT nx-srv") \
-	EM(afs_estate_trace_put_op_failed,	"PUT op-fai") \
-	EM(afs_estate_trace_put_operation,	"PUT op    ") \
 	EM(afs_estate_trace_put_probe,		"PUT probe ") \
-	EM(afs_estate_trace_put_restart_rotate,	"PUT rstrot") \
 	EM(afs_estate_trace_put_server,		"PUT server") \
+	EM(afs_estate_trace_put_server_state,	"PUT srv-st") \
 	E_(afs_estate_trace_free,		"FREE      ")
 
 #define afs_fs_operations \
@@ -448,6 +445,29 @@ enum yfs_cm_operation {
 	EM(afs_cb_break_for_vos_release,	"break-vos-release")	\
 	E_(afs_cb_break_volume_excluded,	"vol-excluded")
 
+#define afs_rotate_traces						\
+	EM(afs_rotate_trace_aborted,		"Abortd")		\
+	EM(afs_rotate_trace_busy_sleep,		"BsySlp")		\
+	EM(afs_rotate_trace_check_vol_status,	"VolStt")		\
+	EM(afs_rotate_trace_failed,		"Failed")		\
+	EM(afs_rotate_trace_iter,		"Iter  ")		\
+	EM(afs_rotate_trace_iterate_addr,	"ItAddr")		\
+	EM(afs_rotate_trace_next_server,	"NextSv")		\
+	EM(afs_rotate_trace_no_more_servers,	"NoMore")		\
+	EM(afs_rotate_trace_nomem,		"Nomem ")		\
+	EM(afs_rotate_trace_probe_error,	"PrbErr")		\
+	EM(afs_rotate_trace_probe_fileserver,	"PrbFsv")		\
+	EM(afs_rotate_trace_probe_none,		"PrbNon")		\
+	EM(afs_rotate_trace_probe_response,	"PrbRsp")		\
+	EM(afs_rotate_trace_probe_superseded,	"PrbSup")		\
+	EM(afs_rotate_trace_restart,		"Rstart")		\
+	EM(afs_rotate_trace_retry_server,	"RtrySv")		\
+	EM(afs_rotate_trace_selected_server,	"SlctSv")		\
+	EM(afs_rotate_trace_stale_lock,		"StlLck")		\
+	EM(afs_rotate_trace_start,		"Start ")		\
+	EM(afs_rotate_trace_stop,		"Stop  ")		\
+	E_(afs_rotate_trace_stopped,		"Stoppd")
+
 /*
  * Generate enums for tracing information.
  */
@@ -471,6 +491,7 @@ enum afs_file_error		{ afs_file_errors } __mode(byte);
 enum afs_flock_event		{ afs_flock_events } __mode(byte);
 enum afs_flock_operation	{ afs_flock_operations } __mode(byte);
 enum afs_io_error		{ afs_io_errors } __mode(byte);
+enum afs_rotate_trace		{ afs_rotate_traces } __mode(byte);
 enum afs_server_trace		{ afs_server_traces } __mode(byte);
 enum afs_volume_trace		{ afs_volume_traces } __mode(byte);
 
@@ -486,21 +507,22 @@ enum afs_volume_trace		{ afs_volume_traces } __mode(byte);
 
 afs_alist_traces;
 afs_call_traces;
-afs_server_traces;
+afs_cb_break_reasons;
 afs_cell_traces;
-afs_fs_operations;
-afs_vl_operations;
 afs_cm_operations;
-yfs_cm_operations;
 afs_edit_dir_ops;
 afs_edit_dir_reasons;
 afs_eproto_causes;
 afs_estate_traces;
-afs_io_errors;
 afs_file_errors;
-afs_flock_types;
 afs_flock_operations;
-afs_cb_break_reasons;
+afs_flock_types;
+afs_fs_operations;
+afs_io_errors;
+afs_rotate_traces;
+afs_server_traces;
+afs_vl_operations;
+yfs_cm_operations;
 
 /*
  * Now redefine the EM() and E_() macros to map the enums to the strings that
@@ -1519,6 +1541,41 @@ TRACE_EVENT(afs_vl_probe,
 		      &__entry->srx.transport)
 	    );
 
+TRACE_EVENT(afs_rotate,
+	    TP_PROTO(struct afs_operation *op, enum afs_rotate_trace reason, unsigned int extra),
+
+	    TP_ARGS(op, reason, extra),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,		op)
+		    __field(unsigned int,		flags)
+		    __field(unsigned int,		extra)
+		    __field(unsigned short,		iteration)
+		    __field(short,			server_index)
+		    __field(short,			addr_index)
+		    __field(enum afs_rotate_trace,	reason)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->op = op->debug_id;
+		    __entry->flags = op->flags;
+		    __entry->iteration = op->nr_iterations;
+		    __entry->server_index = op->server_index;
+		    __entry->addr_index = op->addr_index;
+		    __entry->reason = reason;
+		    __entry->extra = extra;
+			   ),
+
+	    TP_printk("OP=%08x it=%02x %s fl=%x sx=%d ax=%d ext=%d",
+		      __entry->op,
+		      __entry->iteration,
+		      __print_symbolic(__entry->reason, afs_rotate_traces),
+		      __entry->flags,
+		      __entry->server_index,
+		      __entry->addr_index,
+		      __entry->extra)
+	    );
+
 #endif /* _TRACE_AFS_H */
 
 /* This part must be outside protection */
-- 
cgit v1.2.3


From abcbd3bfbbfe97a8912d0c929d4aa18f50d9bc52 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 17 Nov 2023 09:20:28 +0000
Subject: afs: trace: Log afs_make_call(), including server address

Add a tracepoint to log calls to afs_make_call(), including the destination
server address.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
---
 fs/afs/fsclient.c          | 22 ++++++++++++++++++++++
 fs/afs/internal.h          |  1 +
 fs/afs/rxrpc.c             |  2 ++
 fs/afs/yfsclient.c         | 20 ++++++++++++++++++++
 include/trace/events/afs.h | 36 ++++++++++++++++++++++++++++++++++++
 5 files changed, 81 insertions(+)

(limited to 'include')

diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index 80f7d9e796e3..79cd30775b7a 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -290,6 +290,7 @@ void afs_fs_fetch_status(struct afs_operation *op)
 	bp[2] = htonl(vp->fid.vnode);
 	bp[3] = htonl(vp->fid.unique);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -442,6 +443,7 @@ static void afs_fs_fetch_data64(struct afs_operation *op)
 	bp[6] = 0;
 	bp[7] = htonl(lower_32_bits(req->len));
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -476,6 +478,7 @@ void afs_fs_fetch_data(struct afs_operation *op)
 	bp[4] = htonl(lower_32_bits(req->pos));
 	bp[5] = htonl(lower_32_bits(req->len));
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -559,6 +562,7 @@ void afs_fs_create_file(struct afs_operation *op)
 	*bp++ = htonl(op->create.mode & S_IALLUGO); /* unix mode */
 	*bp++ = 0; /* segment size */
 
+	call->fid = dvp->fid;
 	trace_afs_make_fs_call1(call, &dvp->fid, name);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -612,6 +616,7 @@ void afs_fs_make_dir(struct afs_operation *op)
 	*bp++ = htonl(op->create.mode & S_IALLUGO); /* unix mode */
 	*bp++ = 0; /* segment size */
 
+	call->fid = dvp->fid;
 	trace_afs_make_fs_call1(call, &dvp->fid, name);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -685,6 +690,7 @@ void afs_fs_remove_file(struct afs_operation *op)
 		bp = (void *) bp + padsz;
 	}
 
+	call->fid = dvp->fid;
 	trace_afs_make_fs_call1(call, &dvp->fid, name);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -732,6 +738,7 @@ void afs_fs_remove_dir(struct afs_operation *op)
 		bp = (void *) bp + padsz;
 	}
 
+	call->fid = dvp->fid;
 	trace_afs_make_fs_call1(call, &dvp->fid, name);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -812,6 +819,7 @@ void afs_fs_link(struct afs_operation *op)
 	*bp++ = htonl(vp->fid.vnode);
 	*bp++ = htonl(vp->fid.unique);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call1(call, &vp->fid, name);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -907,6 +915,7 @@ void afs_fs_symlink(struct afs_operation *op)
 	*bp++ = htonl(S_IRWXUGO); /* unix mode */
 	*bp++ = 0; /* segment size */
 
+	call->fid = dvp->fid;
 	trace_afs_make_fs_call1(call, &dvp->fid, name);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1003,6 +1012,7 @@ void afs_fs_rename(struct afs_operation *op)
 		bp = (void *) bp + n_padsz;
 	}
 
+	call->fid = orig_dvp->fid;
 	trace_afs_make_fs_call2(call, &orig_dvp->fid, orig_name, new_name);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1090,6 +1100,7 @@ static void afs_fs_store_data64(struct afs_operation *op)
 	*bp++ = htonl(upper_32_bits(op->store.i_size));
 	*bp++ = htonl(lower_32_bits(op->store.i_size));
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1140,6 +1151,7 @@ void afs_fs_store_data(struct afs_operation *op)
 	*bp++ = htonl(lower_32_bits(op->store.size));
 	*bp++ = htonl(lower_32_bits(op->store.i_size));
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1206,6 +1218,7 @@ static void afs_fs_setattr_size64(struct afs_operation *op)
 	*bp++ = htonl(upper_32_bits(attr->ia_size));	/* new file length */
 	*bp++ = htonl(lower_32_bits(attr->ia_size));
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1247,6 +1260,7 @@ static void afs_fs_setattr_size(struct afs_operation *op)
 	*bp++ = 0;				/* size of write */
 	*bp++ = htonl(attr->ia_size);		/* new file length */
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1283,6 +1297,7 @@ void afs_fs_setattr(struct afs_operation *op)
 
 	xdr_encode_AFS_StoreStatus(&bp, op->setattr.attr);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1446,6 +1461,7 @@ void afs_fs_get_volume_status(struct afs_operation *op)
 	bp[0] = htonl(FSGETVOLUMESTATUS);
 	bp[1] = htonl(vp->fid.vid);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1528,6 +1544,7 @@ void afs_fs_set_lock(struct afs_operation *op)
 	*bp++ = htonl(vp->fid.unique);
 	*bp++ = htonl(op->lock.type);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_calli(call, &vp->fid, op->lock.type);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1554,6 +1571,7 @@ void afs_fs_extend_lock(struct afs_operation *op)
 	*bp++ = htonl(vp->fid.vnode);
 	*bp++ = htonl(vp->fid.unique);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1580,6 +1598,7 @@ void afs_fs_release_lock(struct afs_operation *op)
 	*bp++ = htonl(vp->fid.vnode);
 	*bp++ = htonl(vp->fid.unique);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1948,6 +1967,7 @@ void afs_fs_inline_bulk_status(struct afs_operation *op)
 		*bp++ = htonl(op->more_files[i].fid.unique);
 	}
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -2053,6 +2073,7 @@ void afs_fs_fetch_acl(struct afs_operation *op)
 	bp[2] = htonl(vp->fid.vnode);
 	bp[3] = htonl(vp->fid.unique);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_KERNEL);
 }
@@ -2098,6 +2119,7 @@ void afs_fs_store_acl(struct afs_operation *op)
 	if (acl->size != size)
 		memset((void *)&bp[5] + acl->size, 0, size - acl->size);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_KERNEL);
 }
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index a6a4fc417dba..e33ace259cc6 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -153,6 +153,7 @@ struct afs_call {
 		struct afs_vldb_entry	*ret_vldb;
 		char			*ret_str;
 	};
+	struct afs_fid		fid;		/* Primary vnode ID (or all zeroes) */
 	unsigned char		probe_index;	/* Address in ->probe_alist */
 	struct afs_operation	*op;
 	unsigned int		server_index;
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index 81013bc8bbfd..c453428f3c8b 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -313,6 +313,8 @@ void afs_make_call(struct afs_call *call, gfp_t gfp)
 	       call, call->type->name, key_serial(call->key),
 	       atomic_read(&call->net->nr_outstanding_calls));
 
+	trace_afs_make_call(call);
+
 	/* Work out the length we're going to transmit.  This is awkward for
 	 * calls such as FS.StoreData where there's an extra injection of data
 	 * after the initial fixed part.
diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c
index 2d6943f05ea5..f521e66d3bf6 100644
--- a/fs/afs/yfsclient.c
+++ b/fs/afs/yfsclient.c
@@ -493,6 +493,7 @@ void yfs_fs_fetch_data(struct afs_operation *op)
 	bp = xdr_encode_u64(bp, req->len);
 	yfs_check_req(call, bp);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -575,6 +576,7 @@ void yfs_fs_create_file(struct afs_operation *op)
 	bp = xdr_encode_u32(bp, yfs_LockNone); /* ViceLockType */
 	yfs_check_req(call, bp);
 
+	call->fid = dvp->fid;
 	trace_afs_make_fs_call1(call, &dvp->fid, name);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -623,6 +625,7 @@ void yfs_fs_make_dir(struct afs_operation *op)
 	bp = xdr_encode_YFSStoreStatus(bp, &op->create.mode, &op->mtime);
 	yfs_check_req(call, bp);
 
+	call->fid = dvp->fid;
 	trace_afs_make_fs_call1(call, &dvp->fid, name);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -707,6 +710,7 @@ void yfs_fs_remove_file2(struct afs_operation *op)
 	bp = xdr_encode_name(bp, name);
 	yfs_check_req(call, bp);
 
+	call->fid = dvp->fid;
 	trace_afs_make_fs_call1(call, &dvp->fid, name);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -776,6 +780,7 @@ void yfs_fs_remove_file(struct afs_operation *op)
 	bp = xdr_encode_name(bp, name);
 	yfs_check_req(call, bp);
 
+	call->fid = dvp->fid;
 	trace_afs_make_fs_call1(call, &dvp->fid, name);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -817,6 +822,7 @@ void yfs_fs_remove_dir(struct afs_operation *op)
 	bp = xdr_encode_name(bp, name);
 	yfs_check_req(call, bp);
 
+	call->fid = dvp->fid;
 	trace_afs_make_fs_call1(call, &dvp->fid, name);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -890,6 +896,7 @@ void yfs_fs_link(struct afs_operation *op)
 	bp = xdr_encode_YFSFid(bp, &vp->fid);
 	yfs_check_req(call, bp);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call1(call, &vp->fid, name);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -971,6 +978,7 @@ void yfs_fs_symlink(struct afs_operation *op)
 	bp = xdr_encode_YFSStoreStatus(bp, &mode, &op->mtime);
 	yfs_check_req(call, bp);
 
+	call->fid = dvp->fid;
 	trace_afs_make_fs_call1(call, &dvp->fid, name);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1050,6 +1058,7 @@ void yfs_fs_rename(struct afs_operation *op)
 	bp = xdr_encode_name(bp, new_name);
 	yfs_check_req(call, bp);
 
+	call->fid = orig_dvp->fid;
 	trace_afs_make_fs_call2(call, &orig_dvp->fid, orig_name, new_name);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1105,6 +1114,7 @@ void yfs_fs_store_data(struct afs_operation *op)
 	bp = xdr_encode_u64(bp, op->store.i_size);
 	yfs_check_req(call, bp);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1161,6 +1171,7 @@ static void yfs_fs_setattr_size(struct afs_operation *op)
 	bp = xdr_encode_u64(bp, attr->ia_size);	/* new file length */
 	yfs_check_req(call, bp);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1199,6 +1210,7 @@ void yfs_fs_setattr(struct afs_operation *op)
 	bp = xdr_encode_YFS_StoreStatus(bp, attr);
 	yfs_check_req(call, bp);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1369,6 +1381,7 @@ void yfs_fs_get_volume_status(struct afs_operation *op)
 	bp = xdr_encode_u64(bp, vp->fid.vid);
 	yfs_check_req(call, bp);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1433,6 +1446,7 @@ void yfs_fs_set_lock(struct afs_operation *op)
 	bp = xdr_encode_u32(bp, op->lock.type);
 	yfs_check_req(call, bp);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_calli(call, &vp->fid, op->lock.type);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1463,6 +1477,7 @@ void yfs_fs_extend_lock(struct afs_operation *op)
 	bp = xdr_encode_YFSFid(bp, &vp->fid);
 	yfs_check_req(call, bp);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1493,6 +1508,7 @@ void yfs_fs_release_lock(struct afs_operation *op)
 	bp = xdr_encode_YFSFid(bp, &vp->fid);
 	yfs_check_req(call, bp);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1559,6 +1575,7 @@ void yfs_fs_fetch_status(struct afs_operation *op)
 	bp = xdr_encode_YFSFid(bp, &vp->fid);
 	yfs_check_req(call, bp);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1739,6 +1756,7 @@ void yfs_fs_inline_bulk_status(struct afs_operation *op)
 		bp = xdr_encode_YFSFid(bp, &op->more_files[i].fid);
 	yfs_check_req(call, bp);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_NOFS);
 }
@@ -1901,6 +1919,7 @@ void yfs_fs_fetch_opaque_acl(struct afs_operation *op)
 	bp = xdr_encode_YFSFid(bp, &vp->fid);
 	yfs_check_req(call, bp);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_KERNEL);
 }
@@ -1951,6 +1970,7 @@ void yfs_fs_store_opaque_acl2(struct afs_operation *op)
 	bp += size / sizeof(__be32);
 	yfs_check_req(call, bp);
 
+	call->fid = vp->fid;
 	trace_afs_make_fs_call(call, &vp->fid);
 	afs_make_op_call(op, call, GFP_KERNEL);
 }
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index b2e0847eca47..5194b7e6dc8d 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -1576,6 +1576,42 @@ TRACE_EVENT(afs_rotate,
 		      __entry->extra)
 	    );
 
+TRACE_EVENT(afs_make_call,
+	    TP_PROTO(struct afs_call *call),
+
+	    TP_ARGS(call),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,		call)
+		    __field(bool,			is_vl)
+		    __field(enum afs_fs_operation,	op)
+		    __field_struct(struct afs_fid,	fid)
+		    __field_struct(struct sockaddr_rxrpc, srx)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->call = call->debug_id;
+		    __entry->op = call->operation_ID;
+		    __entry->fid = call->fid;
+		    memcpy(&__entry->srx, rxrpc_kernel_remote_srx(call->peer),
+			   sizeof(__entry->srx));
+		    __entry->srx.srx_service = call->service_id;
+		    __entry->is_vl = (__entry->srx.srx_service == VL_SERVICE ||
+				      __entry->srx.srx_service == YFS_VL_SERVICE);
+			   ),
+
+	    TP_printk("c=%08x %pISpc+%u %s %llx:%llx:%x",
+		      __entry->call,
+		      &__entry->srx.transport,
+		      __entry->srx.srx_service,
+		      __entry->is_vl ?
+		      __print_symbolic(__entry->op, afs_vl_operations) :
+		      __print_symbolic(__entry->op, afs_fs_operations),
+		      __entry->fid.vid,
+		      __entry->fid.vnode,
+		      __entry->fid.unique)
+	    );
+
 #endif /* _TRACE_AFS_H */
 
 /* This part must be outside protection */
-- 
cgit v1.2.3


From 02018c544ef113e980a2349eba89003d6f399d22 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Thu, 21 Dec 2023 19:00:34 +0100
Subject: net: phy: Introduce ethernet link topology representation

Link topologies containing multiple network PHYs attached to the same
net_device can be found when using a PHY as a media converter for use
with an SFP connector, on which an SFP transceiver containing a PHY can
be used.

With the current model, the transceiver's PHY can't be used for
operations such as cable testing, timestamping, macsec offload, etc.

The reason being that most of the logic for these configuration, coming
from either ethtool netlink or ioctls tend to use netdev->phydev, which
in multi-phy systems will reference the PHY closest to the MAC.

Introduce a numbering scheme allowing to enumerate PHY devices that
belong to any netdev, which can in turn allow userspace to take more
precise decisions with regard to each PHY's configuration.

The numbering is maintained per-netdev, in a phy_device_list.
The numbering works similarly to a netdevice's ifindex, with
identifiers that are only recycled once INT_MAX has been reached.

This prevents races that could occur between PHY listing and SFP
transceiver removal/insertion.

The identifiers are assigned at phy_attach time, as the numbering
depends on the netdevice the phy is attached to.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS                            |  2 +
 drivers/net/phy/Makefile               |  2 +-
 drivers/net/phy/phy_device.c           |  7 ++++
 drivers/net/phy/phy_link_topology.c    | 66 +++++++++++++++++++++++++++++++++
 include/linux/netdevice.h              |  4 +-
 include/linux/phy.h                    |  4 ++
 include/linux/phy_link_topology.h      | 67 ++++++++++++++++++++++++++++++++++
 include/linux/phy_link_topology_core.h | 19 ++++++++++
 include/uapi/linux/ethtool.h           | 16 ++++++++
 net/core/dev.c                         |  3 ++
 10 files changed, 188 insertions(+), 2 deletions(-)
 create mode 100644 drivers/net/phy/phy_link_topology.c
 create mode 100644 include/linux/phy_link_topology.h
 create mode 100644 include/linux/phy_link_topology_core.h

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index 2b916990d7f0..79ac49b113dc 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7871,6 +7871,8 @@ F:	include/linux/mii.h
 F:	include/linux/of_net.h
 F:	include/linux/phy.h
 F:	include/linux/phy_fixed.h
+F:	include/linux/phy_link_topology.h
+F:	include/linux/phy_link_topology_core.h
 F:	include/linux/phylib_stubs.h
 F:	include/linux/platform_data/mdio-bcm-unimac.h
 F:	include/linux/platform_data/mdio-gpio.h
diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile
index 6097afd44392..f218954fd7a8 100644
--- a/drivers/net/phy/Makefile
+++ b/drivers/net/phy/Makefile
@@ -2,7 +2,7 @@
 # Makefile for Linux PHY drivers
 
 libphy-y			:= phy.o phy-c45.o phy-core.o phy_device.o \
-				   linkmode.o
+				   linkmode.o phy_link_topology.o
 mdio-bus-y			+= mdio_bus.o mdio_device.o
 
 ifdef CONFIG_MDIO_DEVICE
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 3611ea64875e..ab8ae976a2f8 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -29,6 +29,7 @@
 #include <linux/phy.h>
 #include <linux/phylib_stubs.h>
 #include <linux/phy_led_triggers.h>
+#include <linux/phy_link_topology.h>
 #include <linux/pse-pd/pse.h>
 #include <linux/property.h>
 #include <linux/rtnetlink.h>
@@ -1491,6 +1492,11 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
 
 		if (phydev->sfp_bus_attached)
 			dev->sfp_bus = phydev->sfp_bus;
+
+		err = phy_link_topo_add_phy(&dev->link_topo, phydev,
+					    PHY_UPSTREAM_MAC, dev);
+		if (err)
+			goto error;
 	}
 
 	/* Some Ethernet drivers try to connect to a PHY device before
@@ -1820,6 +1826,7 @@ void phy_detach(struct phy_device *phydev)
 	if (dev) {
 		phydev->attached_dev->phydev = NULL;
 		phydev->attached_dev = NULL;
+		phy_link_topo_del_phy(&dev->link_topo, phydev);
 	}
 	phydev->phylink = NULL;
 
diff --git a/drivers/net/phy/phy_link_topology.c b/drivers/net/phy/phy_link_topology.c
new file mode 100644
index 000000000000..34e7e08fbfc3
--- /dev/null
+++ b/drivers/net/phy/phy_link_topology.c
@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Infrastructure to handle all PHY devices connected to a given netdev,
+ * either directly or indirectly attached.
+ *
+ * Copyright (c) 2023 Maxime Chevallier<maxime.chevallier@bootlin.com>
+ */
+
+#include <linux/phy_link_topology.h>
+#include <linux/netdevice.h>
+#include <linux/phy.h>
+#include <linux/rtnetlink.h>
+#include <linux/xarray.h>
+
+int phy_link_topo_add_phy(struct phy_link_topology *topo,
+			  struct phy_device *phy,
+			  enum phy_upstream upt, void *upstream)
+{
+	struct phy_device_node *pdn;
+	int ret;
+
+	pdn = kzalloc(sizeof(*pdn), GFP_KERNEL);
+	if (!pdn)
+		return -ENOMEM;
+
+	pdn->phy = phy;
+	switch (upt) {
+	case PHY_UPSTREAM_MAC:
+		pdn->upstream.netdev = (struct net_device *)upstream;
+		if (phy_on_sfp(phy))
+			pdn->parent_sfp_bus = pdn->upstream.netdev->sfp_bus;
+		break;
+	case PHY_UPSTREAM_PHY:
+		pdn->upstream.phydev = (struct phy_device *)upstream;
+		if (phy_on_sfp(phy))
+			pdn->parent_sfp_bus = pdn->upstream.phydev->sfp_bus;
+		break;
+	default:
+		ret = -EINVAL;
+		goto err;
+	}
+	pdn->upstream_type = upt;
+
+	ret = xa_alloc_cyclic(&topo->phys, &phy->phyindex, pdn, xa_limit_32b,
+			      &topo->next_phy_index, GFP_KERNEL);
+	if (ret)
+		goto err;
+
+	return 0;
+
+err:
+	kfree(pdn);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(phy_link_topo_add_phy);
+
+void phy_link_topo_del_phy(struct phy_link_topology *topo,
+			   struct phy_device *phy)
+{
+	struct phy_device_node *pdn = xa_erase(&topo->phys, phy->phyindex);
+
+	phy->phyindex = 0;
+
+	kfree(pdn);
+}
+EXPORT_SYMBOL_GPL(phy_link_topo_del_phy);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 75c7725e5e4f..5baa5517f533 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -40,7 +40,6 @@
 #include <net/dcbnl.h>
 #endif
 #include <net/netprio_cgroup.h>
-
 #include <linux/netdev_features.h>
 #include <linux/neighbour.h>
 #include <uapi/linux/netdevice.h>
@@ -52,6 +51,7 @@
 #include <net/net_trackers.h>
 #include <net/net_debug.h>
 #include <net/dropreason-core.h>
+#include <linux/phy_link_topology_core.h>
 
 struct netpoll_info;
 struct device;
@@ -2047,6 +2047,7 @@ enum netdev_stat_type {
  *	@fcoe_ddp_xid:	Max exchange id for FCoE LRO by ddp
  *
  *	@priomap:	XXX: need comments on this one
+ *	@link_topo:	Physical link topology tracking attached PHYs
  *	@phydev:	Physical device may attach itself
  *			for hardware timestamping
  *	@sfp_bus:	attached &struct sfp_bus structure.
@@ -2441,6 +2442,7 @@ struct net_device {
 #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO)
 	struct netprio_map __rcu *priomap;
 #endif
+	struct phy_link_topology	link_topo;
 	struct phy_device	*phydev;
 	struct sfp_bus		*sfp_bus;
 	struct lock_class_key	*qdisc_tx_busylock;
diff --git a/include/linux/phy.h b/include/linux/phy.h
index ede891776d8b..ea9416797b89 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -547,6 +547,9 @@ struct macsec_ops;
  * @drv: Pointer to the driver for this PHY instance
  * @devlink: Create a link between phy dev and mac dev, if the external phy
  *           used by current mac interface is managed by another mac interface.
+ * @phyindex: Unique id across the phy's parent tree of phys to address the PHY
+ *	      from userspace, similar to ifindex. A zero index means the PHY
+ *	      wasn't assigned an id yet.
  * @phy_id: UID for this device found during discovery
  * @c45_ids: 802.3-c45 Device Identifiers if is_c45.
  * @is_c45:  Set to true if this PHY uses clause 45 addressing.
@@ -646,6 +649,7 @@ struct phy_device {
 
 	struct device_link *devlink;
 
+	u32 phyindex;
 	u32 phy_id;
 
 	struct phy_c45_device_ids c45_ids;
diff --git a/include/linux/phy_link_topology.h b/include/linux/phy_link_topology.h
new file mode 100644
index 000000000000..91902263ec0e
--- /dev/null
+++ b/include/linux/phy_link_topology.h
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * PHY device list allow maintaining a list of PHY devices that are
+ * part of a netdevice's link topology. PHYs can for example be chained,
+ * as is the case when using a PHY that exposes an SFP module, on which an
+ * SFP transceiver that embeds a PHY is connected.
+ *
+ * This list can then be used by userspace to leverage individual PHY
+ * capabilities.
+ */
+#ifndef __PHY_LINK_TOPOLOGY_H
+#define __PHY_LINK_TOPOLOGY_H
+
+#include <linux/ethtool.h>
+#include <linux/phy_link_topology_core.h>
+
+struct xarray;
+struct phy_device;
+struct net_device;
+struct sfp_bus;
+
+struct phy_device_node {
+	enum phy_upstream upstream_type;
+
+	union {
+		struct net_device	*netdev;
+		struct phy_device	*phydev;
+	} upstream;
+
+	struct sfp_bus *parent_sfp_bus;
+
+	struct phy_device *phy;
+};
+
+static inline struct phy_device *
+phy_link_topo_get_phy(struct phy_link_topology *topo, u32 phyindex)
+{
+	struct phy_device_node *pdn = xa_load(&topo->phys, phyindex);
+
+	if (pdn)
+		return pdn->phy;
+
+	return NULL;
+}
+
+#if IS_ENABLED(CONFIG_PHYLIB)
+int phy_link_topo_add_phy(struct phy_link_topology *topo,
+			  struct phy_device *phy,
+			  enum phy_upstream upt, void *upstream);
+
+void phy_link_topo_del_phy(struct phy_link_topology *lt, struct phy_device *phy);
+
+#else
+static inline int phy_link_topo_add_phy(struct phy_link_topology *topo,
+					struct phy_device *phy,
+					enum phy_upstream upt, void *upstream)
+{
+	return 0;
+}
+
+static inline void phy_link_topo_del_phy(struct phy_link_topology *topo,
+					 struct phy_device *phy)
+{
+}
+#endif
+
+#endif /* __PHY_LINK_TOPOLOGY_H */
diff --git a/include/linux/phy_link_topology_core.h b/include/linux/phy_link_topology_core.h
new file mode 100644
index 000000000000..78c75f909489
--- /dev/null
+++ b/include/linux/phy_link_topology_core.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PHY_LINK_TOPOLOGY_CORE_H
+#define __PHY_LINK_TOPOLOGY_CORE_H
+
+struct xarray;
+
+struct phy_link_topology {
+	struct xarray phys;
+
+	u32 next_phy_index;
+};
+
+static inline void phy_link_topo_init(struct phy_link_topology *topo)
+{
+	xa_init_flags(&topo->phys, XA_FLAGS_ALLOC1);
+	topo->next_phy_index = 1;
+}
+
+#endif /* __PHY_LINK_TOPOLOGY_CORE_H */
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 85c412c23ab5..60801df9d8c0 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -2219,4 +2219,20 @@ struct ethtool_link_settings {
 	 * __u32 map_lp_advertising[link_mode_masks_nwords];
 	 */
 };
+
+/**
+ * enum phy_upstream - Represents the upstream component a given PHY device
+ * is connected to, as in what is on the other end of the MII bus. Most PHYs
+ * will be attached to an Ethernet MAC controller, but in some cases, there's
+ * an intermediate PHY used as a media-converter, which will driver another
+ * MII interface as its output.
+ * @PHY_UPSTREAM_MAC: Upstream component is a MAC (a switch port,
+ *		      or ethernet controller)
+ * @PHY_UPSTREAM_PHY: Upstream component is a PHY (likely a media converter)
+ */
+enum phy_upstream {
+	PHY_UPSTREAM_MAC,
+	PHY_UPSTREAM_PHY,
+};
+
 #endif /* _UAPI_LINUX_ETHTOOL_H */
diff --git a/net/core/dev.c b/net/core/dev.c
index f9d4b550ef4b..df04cbf77551 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -153,6 +153,7 @@
 #include <linux/prandom.h>
 #include <linux/once_lite.h>
 #include <net/netdev_rx_queue.h>
+#include <linux/phy_link_topology_core.h>
 
 #include "dev.h"
 #include "net-sysfs.h"
@@ -10875,6 +10876,8 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 #ifdef CONFIG_NET_SCHED
 	hash_init(dev->qdisc_hash);
 #endif
+	phy_link_topo_init(&dev->link_topo);
+
 	dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM;
 	setup(dev);
 
-- 
cgit v1.2.3


From 9c5625f559ad6fe9f6f733c11475bf470e637d34 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Thu, 21 Dec 2023 19:00:35 +0100
Subject: net: sfp: pass the phy_device when disconnecting an sfp module's PHY

Pass the phy_device as a parameter to the sfp upstream .disconnect_phy
operation. This is preparatory work to help track phy devices across
a net_device's link.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 8 ++++++++
 drivers/net/phy/phylink.c    | 3 ++-
 drivers/net/phy/sfp-bus.c    | 4 ++--
 include/linux/sfp.h          | 2 +-
 4 files changed, 13 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index ab8ae976a2f8..711629c49c11 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -266,6 +266,14 @@ static void phy_mdio_device_remove(struct mdio_device *mdiodev)
 
 static struct phy_driver genphy_driver;
 
+static struct phy_link_topology *phy_get_link_topology(struct phy_device *phydev)
+{
+	if (phydev->attached_dev)
+		return &phydev->attached_dev->link_topo;
+
+	return NULL;
+}
+
 static LIST_HEAD(phy_fixup_list);
 static DEFINE_MUTEX(phy_fixup_lock);
 
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 298dfd6982a5..3d25a4a6212b 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -3319,7 +3319,8 @@ static int phylink_sfp_connect_phy(void *upstream, struct phy_device *phy)
 	return ret;
 }
 
-static void phylink_sfp_disconnect_phy(void *upstream)
+static void phylink_sfp_disconnect_phy(void *upstream,
+				       struct phy_device *phydev)
 {
 	phylink_disconnect_phy(upstream);
 }
diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c
index 6fa679b36290..3a86c41e1235 100644
--- a/drivers/net/phy/sfp-bus.c
+++ b/drivers/net/phy/sfp-bus.c
@@ -486,7 +486,7 @@ static void sfp_unregister_bus(struct sfp_bus *bus)
 			bus->socket_ops->stop(bus->sfp);
 		bus->socket_ops->detach(bus->sfp);
 		if (bus->phydev && ops && ops->disconnect_phy)
-			ops->disconnect_phy(bus->upstream);
+			ops->disconnect_phy(bus->upstream, bus->phydev);
 	}
 	bus->registered = false;
 }
@@ -742,7 +742,7 @@ void sfp_remove_phy(struct sfp_bus *bus)
 	const struct sfp_upstream_ops *ops = sfp_get_upstream_ops(bus);
 
 	if (ops && ops->disconnect_phy)
-		ops->disconnect_phy(bus->upstream);
+		ops->disconnect_phy(bus->upstream, bus->phydev);
 	bus->phydev = NULL;
 }
 EXPORT_SYMBOL_GPL(sfp_remove_phy);
diff --git a/include/linux/sfp.h b/include/linux/sfp.h
index 9346cd44814d..0573e53b0c11 100644
--- a/include/linux/sfp.h
+++ b/include/linux/sfp.h
@@ -544,7 +544,7 @@ struct sfp_upstream_ops {
 	void (*link_down)(void *priv);
 	void (*link_up)(void *priv);
 	int (*connect_phy)(void *priv, struct phy_device *);
-	void (*disconnect_phy)(void *priv);
+	void (*disconnect_phy)(void *priv, struct phy_device *);
 };
 
 #if IS_ENABLED(CONFIG_SFP)
-- 
cgit v1.2.3


From 034fcc210349b873ece7356905be5c6ca11eef2a Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Thu, 21 Dec 2023 19:00:36 +0100
Subject: net: phy: add helpers to handle sfp phy connect/disconnect

There are a few PHY drivers that can handle SFP modules through their
sfp_upstream_ops. Introduce Phylib helpers to keep track of connected
SFP PHYs in a netdevice's namespace, by adding the SFP PHY to the
upstream PHY's netdev's namespace.

By doing so, these SFP PHYs can be enumerated and exposed to users,
which will be able to use their capabilities.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/at803x.c          |  2 ++
 drivers/net/phy/marvell-88x2222.c |  2 ++
 drivers/net/phy/marvell.c         |  2 ++
 drivers/net/phy/marvell10g.c      |  2 ++
 drivers/net/phy/phy_device.c      | 40 +++++++++++++++++++++++++++++++++++++++
 include/linux/phy.h               |  2 ++
 6 files changed, 50 insertions(+)

(limited to 'include')

diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c
index 19cfbf36fe80..aaf6c654aaed 100644
--- a/drivers/net/phy/at803x.c
+++ b/drivers/net/phy/at803x.c
@@ -1452,6 +1452,8 @@ static const struct sfp_upstream_ops at8031_sfp_ops = {
 	.attach = phy_sfp_attach,
 	.detach = phy_sfp_detach,
 	.module_insert = at8031_sfp_insert,
+	.connect_phy = phy_sfp_connect_phy,
+	.disconnect_phy = phy_sfp_disconnect_phy,
 };
 
 static int at8031_parse_dt(struct phy_device *phydev)
diff --git a/drivers/net/phy/marvell-88x2222.c b/drivers/net/phy/marvell-88x2222.c
index e3aa30dad2e6..3f77bbc7e04f 100644
--- a/drivers/net/phy/marvell-88x2222.c
+++ b/drivers/net/phy/marvell-88x2222.c
@@ -555,6 +555,8 @@ static const struct sfp_upstream_ops sfp_phy_ops = {
 	.link_down = mv2222_sfp_link_down,
 	.attach = phy_sfp_attach,
 	.detach = phy_sfp_detach,
+	.connect_phy = phy_sfp_connect_phy,
+	.disconnect_phy = phy_sfp_disconnect_phy,
 };
 
 static int mv2222_probe(struct phy_device *phydev)
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index eba652a4c1d8..674e29bce2cc 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -3254,6 +3254,8 @@ static const struct sfp_upstream_ops m88e1510_sfp_ops = {
 	.module_remove = m88e1510_sfp_remove,
 	.attach = phy_sfp_attach,
 	.detach = phy_sfp_detach,
+	.connect_phy = phy_sfp_connect_phy,
+	.disconnect_phy = phy_sfp_disconnect_phy,
 };
 
 static int m88e1510_probe(struct phy_device *phydev)
diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c
index ad43e280930c..6642eb642d4b 100644
--- a/drivers/net/phy/marvell10g.c
+++ b/drivers/net/phy/marvell10g.c
@@ -503,6 +503,8 @@ static int mv3310_sfp_insert(void *upstream, const struct sfp_eeprom_id *id)
 static const struct sfp_upstream_ops mv3310_sfp_ops = {
 	.attach = phy_sfp_attach,
 	.detach = phy_sfp_detach,
+	.connect_phy = phy_sfp_connect_phy,
+	.disconnect_phy = phy_sfp_disconnect_phy,
 	.module_insert = mv3310_sfp_insert,
 };
 
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 711629c49c11..1e595762afea 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1363,6 +1363,46 @@ phy_standalone_show(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR_RO(phy_standalone);
 
+/**
+ * phy_sfp_connect_phy - Connect the SFP module's PHY to the upstream PHY
+ * @upstream: pointer to the upstream phy device
+ * @phy: pointer to the SFP module's phy device
+ *
+ * This helper allows keeping track of PHY devices on the link. It adds the
+ * SFP module's phy to the phy namespace of the upstream phy
+ */
+int phy_sfp_connect_phy(void *upstream, struct phy_device *phy)
+{
+	struct phy_device *phydev = upstream;
+	struct phy_link_topology *topo = phy_get_link_topology(phydev);
+
+	if (topo)
+		return phy_link_topo_add_phy(topo, phy, PHY_UPSTREAM_PHY, phydev);
+
+	return 0;
+}
+EXPORT_SYMBOL(phy_sfp_connect_phy);
+
+/**
+ * phy_sfp_disconnect_phy - Disconnect the SFP module's PHY from the upstream PHY
+ * @upstream: pointer to the upstream phy device
+ * @phy: pointer to the SFP module's phy device
+ *
+ * This helper allows keeping track of PHY devices on the link. It removes the
+ * SFP module's phy to the phy namespace of the upstream phy. As the module phy
+ * will be destroyed, re-inserting the same module will add a new phy with a
+ * new index.
+ */
+void phy_sfp_disconnect_phy(void *upstream, struct phy_device *phy)
+{
+	struct phy_device *phydev = upstream;
+	struct phy_link_topology *topo = phy_get_link_topology(phydev);
+
+	if (topo)
+		phy_link_topo_del_phy(topo, phy);
+}
+EXPORT_SYMBOL(phy_sfp_disconnect_phy);
+
 /**
  * phy_sfp_attach - attach the SFP bus to the PHY upstream network device
  * @upstream: pointer to the phy device
diff --git a/include/linux/phy.h b/include/linux/phy.h
index ea9416797b89..ac22b8e28a85 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1729,6 +1729,8 @@ int phy_suspend(struct phy_device *phydev);
 int phy_resume(struct phy_device *phydev);
 int __phy_resume(struct phy_device *phydev);
 int phy_loopback(struct phy_device *phydev, bool enable);
+int phy_sfp_connect_phy(void *upstream, struct phy_device *phy);
+void phy_sfp_disconnect_phy(void *upstream, struct phy_device *phy);
 void phy_sfp_attach(void *upstream, struct sfp_bus *bus);
 void phy_sfp_detach(void *upstream, struct sfp_bus *bus);
 int phy_sfp_probe(struct phy_device *phydev,
-- 
cgit v1.2.3


From dedd702a35793ab462fce4c737eeba0badf9718e Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Thu, 21 Dec 2023 19:00:37 +0100
Subject: net: sfp: Add helper to return the SFP bus name

Knowing the bus name is helpful when we want to expose the link topology
to userspace, add a helper to return the SFP bus name.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/sfp-bus.c | 11 +++++++++++
 include/linux/sfp.h       |  6 ++++++
 2 files changed, 17 insertions(+)

(limited to 'include')

diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c
index 3a86c41e1235..fb1c102714b5 100644
--- a/drivers/net/phy/sfp-bus.c
+++ b/drivers/net/phy/sfp-bus.c
@@ -859,3 +859,14 @@ void sfp_unregister_socket(struct sfp_bus *bus)
 	sfp_bus_put(bus);
 }
 EXPORT_SYMBOL_GPL(sfp_unregister_socket);
+
+const char *sfp_get_name(struct sfp_bus *bus)
+{
+	ASSERT_RTNL();
+
+	if (bus->sfp_dev)
+		return dev_name(bus->sfp_dev);
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(sfp_get_name);
diff --git a/include/linux/sfp.h b/include/linux/sfp.h
index 0573e53b0c11..55c0ab17c9e2 100644
--- a/include/linux/sfp.h
+++ b/include/linux/sfp.h
@@ -570,6 +570,7 @@ struct sfp_bus *sfp_bus_find_fwnode(const struct fwnode_handle *fwnode);
 int sfp_bus_add_upstream(struct sfp_bus *bus, void *upstream,
 			 const struct sfp_upstream_ops *ops);
 void sfp_bus_del_upstream(struct sfp_bus *bus);
+const char *sfp_get_name(struct sfp_bus *bus);
 #else
 static inline int sfp_parse_port(struct sfp_bus *bus,
 				 const struct sfp_eeprom_id *id,
@@ -648,6 +649,11 @@ static inline int sfp_bus_add_upstream(struct sfp_bus *bus, void *upstream,
 static inline void sfp_bus_del_upstream(struct sfp_bus *bus)
 {
 }
+
+static inline const char *sfp_get_name(struct sfp_bus *bus)
+{
+	return NULL;
+}
 #endif
 
 #endif
-- 
cgit v1.2.3


From 2ab0edb505faa9ac90dee1732571390f074e8113 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Thu, 21 Dec 2023 19:00:38 +0100
Subject: net: ethtool: Allow passing a phy index for some commands

Some netlink commands are target towards ethernet PHYs, to control some
of their features. As there's several such commands, add the ability to
pass a PHY index in the ethnl request, which will populate the generic
ethnl_req_info with the relevant phydev when the command targets a PHY.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ethtool-netlink.rst |  7 +++++++
 include/uapi/linux/ethtool_netlink.h         |  1 +
 net/ethtool/netlink.c                        | 24 ++++++++++++++++++++++++
 net/ethtool/netlink.h                        |  7 +++++--
 4 files changed, 37 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst
index d583d9abf2f8..3ca6c21e74af 100644
--- a/Documentation/networking/ethtool-netlink.rst
+++ b/Documentation/networking/ethtool-netlink.rst
@@ -57,6 +57,7 @@ Structure of this header is
   ``ETHTOOL_A_HEADER_DEV_INDEX``  u32     device ifindex
   ``ETHTOOL_A_HEADER_DEV_NAME``   string  device name
   ``ETHTOOL_A_HEADER_FLAGS``      u32     flags common for all requests
+  ``ETHTOOL_A_HEADER_PHY_INDEX``  u32     phy device index
   ==============================  ======  =============================
 
 ``ETHTOOL_A_HEADER_DEV_INDEX`` and ``ETHTOOL_A_HEADER_DEV_NAME`` identify the
@@ -81,6 +82,12 @@ the behaviour is backward compatible, i.e. requests from old clients not aware
 of the flag should be interpreted the way the client expects. A client must
 not set flags it does not understand.
 
+``ETHTOOL_A_HEADER_PHY_INDEX`` identify the ethernet PHY the message relates to.
+As there are numerous commands that are related to PHY configuration, and because
+we can have more than one PHY on the link, the PHY index can be passed in the
+request for the commands that needs it. It is however not mandatory, and if it
+is not passed for commands that target a PHY, the net_device.phydev pointer
+is used, as a fallback that keeps the legacy behaviour.
 
 Bit sets
 ========
diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h
index 3f89074aa06c..422e8cfdd98c 100644
--- a/include/uapi/linux/ethtool_netlink.h
+++ b/include/uapi/linux/ethtool_netlink.h
@@ -133,6 +133,7 @@ enum {
 	ETHTOOL_A_HEADER_DEV_INDEX,		/* u32 */
 	ETHTOOL_A_HEADER_DEV_NAME,		/* string */
 	ETHTOOL_A_HEADER_FLAGS,			/* u32 - ETHTOOL_FLAG_* */
+	ETHTOOL_A_HEADER_PHY_INDEX,		/* u32 */
 
 	/* add new constants above here */
 	__ETHTOOL_A_HEADER_CNT,
diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index fe3553f60bf3..1c26766ce996 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -4,6 +4,7 @@
 #include <linux/ethtool_netlink.h>
 #include <linux/pm_runtime.h>
 #include "netlink.h"
+#include <linux/phy_link_topology.h>
 
 static struct genl_family ethtool_genl_family;
 
@@ -20,6 +21,7 @@ const struct nla_policy ethnl_header_policy[] = {
 					    .len = ALTIFNAMSIZ - 1 },
 	[ETHTOOL_A_HEADER_FLAGS]	= NLA_POLICY_MASK(NLA_U32,
 							  ETHTOOL_FLAGS_BASIC),
+	[ETHTOOL_A_HEADER_PHY_INDEX]		= NLA_POLICY_MIN(NLA_U32, 1),
 };
 
 const struct nla_policy ethnl_header_policy_stats[] = {
@@ -28,6 +30,7 @@ const struct nla_policy ethnl_header_policy_stats[] = {
 					    .len = ALTIFNAMSIZ - 1 },
 	[ETHTOOL_A_HEADER_FLAGS]	= NLA_POLICY_MASK(NLA_U32,
 							  ETHTOOL_FLAGS_STATS),
+	[ETHTOOL_A_HEADER_PHY_INDEX]		= NLA_POLICY_MIN(NLA_U32, 1),
 };
 
 int ethnl_ops_begin(struct net_device *dev)
@@ -91,6 +94,7 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info,
 {
 	struct nlattr *tb[ARRAY_SIZE(ethnl_header_policy)];
 	const struct nlattr *devname_attr;
+	struct phy_device *phydev = NULL;
 	struct net_device *dev = NULL;
 	u32 flags = 0;
 	int ret;
@@ -145,6 +149,26 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info,
 		return -EINVAL;
 	}
 
+	if (dev) {
+		if (tb[ETHTOOL_A_HEADER_PHY_INDEX]) {
+			u32 phy_index = nla_get_u32(tb[ETHTOOL_A_HEADER_PHY_INDEX]);
+
+			phydev = phy_link_topo_get_phy(&dev->link_topo,
+						       phy_index);
+			if (!phydev) {
+				NL_SET_ERR_MSG_ATTR(extack, header,
+						    "no phy matches phy index");
+				return -EINVAL;
+			}
+		} else {
+			/* If we need a PHY but no phy index is specified, fallback
+			 * to dev->phydev
+			 */
+			phydev = dev->phydev;
+		}
+	}
+
+	req_info->phydev = phydev;
 	req_info->dev = dev;
 	req_info->flags = flags;
 	return 0;
diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h
index 9a333a8d04c1..def84e2def9e 100644
--- a/net/ethtool/netlink.h
+++ b/net/ethtool/netlink.h
@@ -250,6 +250,7 @@ static inline unsigned int ethnl_reply_header_size(void)
  * @dev:   network device the request is for (may be null)
  * @dev_tracker: refcount tracker for @dev reference
  * @flags: request flags common for all request types
+ * @phydev: phy_device connected to @dev this request is for (may be null)
  *
  * This is a common base for request specific structures holding data from
  * parsed userspace request. These always embed struct ethnl_req_info at
@@ -259,6 +260,7 @@ struct ethnl_req_info {
 	struct net_device	*dev;
 	netdevice_tracker	dev_tracker;
 	u32			flags;
+	struct phy_device	*phydev;
 };
 
 static inline void ethnl_parse_header_dev_put(struct ethnl_req_info *req_info)
@@ -395,9 +397,10 @@ extern const struct ethnl_request_ops ethnl_rss_request_ops;
 extern const struct ethnl_request_ops ethnl_plca_cfg_request_ops;
 extern const struct ethnl_request_ops ethnl_plca_status_request_ops;
 extern const struct ethnl_request_ops ethnl_mm_request_ops;
+extern const struct ethnl_request_ops ethnl_phy_request_ops;
 
-extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1];
-extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1];
+extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_PHY_INDEX + 1];
+extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_PHY_INDEX + 1];
 extern const struct nla_policy ethnl_strset_get_policy[ETHTOOL_A_STRSET_COUNTS_ONLY + 1];
 extern const struct nla_policy ethnl_linkinfo_get_policy[ETHTOOL_A_LINKINFO_HEADER + 1];
 extern const struct nla_policy ethnl_linkinfo_set_policy[ETHTOOL_A_LINKINFO_TP_MDIX_CTRL + 1];
-- 
cgit v1.2.3


From 63d5eaf35ac36cad00cfb3809d794ef0078c822b Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Thu, 21 Dec 2023 19:00:40 +0100
Subject: net: ethtool: Introduce a command to list PHYs on an interface

As we have the ability to track the PHYs connected to a net_device
through the link_topology, we can expose this list to userspace. This
allows userspace to use these identifiers for phy-specific commands and
take the decision of which PHY to target by knowing the link topology.

Add PHY_GET and PHY_DUMP, which can be a filtered DUMP operation to list
devices on only one interface.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ethtool-netlink.rst |  44 ++++
 include/uapi/linux/ethtool_netlink.h         |  29 +++
 net/ethtool/Makefile                         |   2 +-
 net/ethtool/netlink.c                        |   9 +
 net/ethtool/netlink.h                        |   5 +
 net/ethtool/phy.c                            | 306 +++++++++++++++++++++++++++
 6 files changed, 394 insertions(+), 1 deletion(-)
 create mode 100644 net/ethtool/phy.c

(limited to 'include')

diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst
index 3ca6c21e74af..97ff787a7dd8 100644
--- a/Documentation/networking/ethtool-netlink.rst
+++ b/Documentation/networking/ethtool-netlink.rst
@@ -2011,6 +2011,49 @@ The attributes are propagated to the driver through the following structure:
 .. kernel-doc:: include/linux/ethtool.h
     :identifiers: ethtool_mm_cfg
 
+PHY_GET
+=======
+
+Retrieve information about a given Ethernet PHY sitting on the link. As there
+can be more than one PHY, the DUMP operation can be used to list the PHYs
+present on a given interface, by passing an interface index or name in
+the dump request
+
+Request contents:
+
+  ====================================  ======  ==========================
+  ``ETHTOOL_A_PHY_HEADER``              nested  request header
+  ====================================  ======  ==========================
+
+Kernel response contents:
+
+  ===================================== ======  ==========================
+  ``ETHTOOL_A_PHY_HEADER``              nested  request header
+  ``ETHTOOL_A_PHY_INDEX``               u32     the phy's unique index, that can
+                                                be used for phy-specific requests
+  ``ETHTOOL_A_PHY_DRVNAME``             string  the phy driver name
+  ``ETHTOOL_A_PHY_NAME``                string  the phy device name
+  ``ETHTOOL_A_PHY_UPSTREAM_TYPE``       u32     the type of device this phy is
+                                                connected to
+  ``ETHTOOL_A_PHY_UPSTREAM_PHY``        nested  if the phy is connected to another
+                                                phy, this nest contains info on
+                                                that connection
+  ``ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME`` string  if the phy controls an sfp bus,
+                                                the name of the sfp bus
+  ``ETHTOOL_A_PHY_ID``                  u32     the phy id if the phy is C22
+  ===================================== ======  ==========================
+
+When ``ETHTOOL_A_PHY_UPSTREAM_TYPE`` is PHY_UPSTREAM_PHY, the PHY's parent is
+another PHY. Information on the parent PHY will be set in the
+``ETHTOOL_A_PHY_UPSTREAM_PHY`` nest, which has the following structure :
+
+  =================================== ======  ==========================
+  ``ETHTOOL_A_PHY_UPSTREAM_INDEX``    u32     the PHY index of the upstream PHY
+  ``ETHTOOL_A_PHY_UPSTREAM_SFP_NAME`` string  if this PHY is connected to it's
+                                                parent PHY through an SFP bus, the
+                                                name of this sfp bus
+  =================================== ======  ==========================
+
 Request translation
 ===================
 
@@ -2117,4 +2160,5 @@ are netlink only.
   n/a                                 ``ETHTOOL_MSG_PLCA_GET_STATUS``
   n/a                                 ``ETHTOOL_MSG_MM_GET``
   n/a                                 ``ETHTOOL_MSG_MM_SET``
+  n/a                                 ``ETHTOOL_MSG_PHY_GET``
   =================================== =====================================
diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h
index 422e8cfdd98c..00cd7ad16709 100644
--- a/include/uapi/linux/ethtool_netlink.h
+++ b/include/uapi/linux/ethtool_netlink.h
@@ -57,6 +57,7 @@ enum {
 	ETHTOOL_MSG_PLCA_GET_STATUS,
 	ETHTOOL_MSG_MM_GET,
 	ETHTOOL_MSG_MM_SET,
+	ETHTOOL_MSG_PHY_GET,
 
 	/* add new constants above here */
 	__ETHTOOL_MSG_USER_CNT,
@@ -109,6 +110,8 @@ enum {
 	ETHTOOL_MSG_PLCA_NTF,
 	ETHTOOL_MSG_MM_GET_REPLY,
 	ETHTOOL_MSG_MM_NTF,
+	ETHTOOL_MSG_PHY_GET_REPLY,
+	ETHTOOL_MSG_PHY_NTF,
 
 	/* add new constants above here */
 	__ETHTOOL_MSG_KERNEL_CNT,
@@ -977,6 +980,32 @@ enum {
 	ETHTOOL_A_MM_MAX = (__ETHTOOL_A_MM_CNT - 1)
 };
 
+enum {
+	ETHTOOL_A_PHY_UPSTREAM_UNSPEC,
+	ETHTOOL_A_PHY_UPSTREAM_INDEX,			/* u32 */
+	ETHTOOL_A_PHY_UPSTREAM_SFP_NAME,		/* string */
+
+	/* add new constants above here */
+	__ETHTOOL_A_PHY_UPSTREAM_CNT,
+	ETHTOOL_A_PHY_UPSTREAM_MAX = (__ETHTOOL_A_PHY_UPSTREAM_CNT - 1)
+};
+
+enum {
+	ETHTOOL_A_PHY_UNSPEC,
+	ETHTOOL_A_PHY_HEADER,			/* nest - _A_HEADER_* */
+	ETHTOOL_A_PHY_INDEX,			/* u32 */
+	ETHTOOL_A_PHY_DRVNAME,			/* string */
+	ETHTOOL_A_PHY_NAME,			/* string */
+	ETHTOOL_A_PHY_UPSTREAM_TYPE,		/* u8 */
+	ETHTOOL_A_PHY_UPSTREAM,			/* nest - _A_PHY_UPSTREAM_* */
+	ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME,	/* string */
+	ETHTOOL_A_PHY_ID,			/* u32 */
+
+	/* add new constants above here */
+	__ETHTOOL_A_PHY_CNT,
+	ETHTOOL_A_PHY_MAX = (__ETHTOOL_A_PHY_CNT - 1)
+};
+
 /* generic netlink info */
 #define ETHTOOL_GENL_NAME "ethtool"
 #define ETHTOOL_GENL_VERSION 1
diff --git a/net/ethtool/Makefile b/net/ethtool/Makefile
index 504f954a1b28..0ccd0e9afd3f 100644
--- a/net/ethtool/Makefile
+++ b/net/ethtool/Makefile
@@ -8,4 +8,4 @@ ethtool_nl-y	:= netlink.o bitset.o strset.o linkinfo.o linkmodes.o rss.o \
 		   linkstate.o debug.o wol.o features.o privflags.o rings.o \
 		   channels.o coalesce.o pause.o eee.o tsinfo.o cabletest.o \
 		   tunnels.o fec.o eeprom.o stats.o phc_vclocks.o mm.o \
-		   module.o pse-pd.o plca.o mm.o
+		   module.o pse-pd.o plca.o mm.o phy.o
diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index 1c26766ce996..92b0dd8ca046 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -1153,6 +1153,15 @@ static const struct genl_ops ethtool_genl_ops[] = {
 		.policy = ethnl_mm_set_policy,
 		.maxattr = ARRAY_SIZE(ethnl_mm_set_policy) - 1,
 	},
+	{
+		.cmd	= ETHTOOL_MSG_PHY_GET,
+		.doit	= ethnl_phy_doit,
+		.start	= ethnl_phy_start,
+		.dumpit	= ethnl_phy_dumpit,
+		.done	= ethnl_phy_done,
+		.policy = ethnl_phy_get_policy,
+		.maxattr = ARRAY_SIZE(ethnl_phy_get_policy) - 1,
+	},
 };
 
 static const struct genl_multicast_group ethtool_nl_mcgrps[] = {
diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h
index def84e2def9e..5e6a43e35a09 100644
--- a/net/ethtool/netlink.h
+++ b/net/ethtool/netlink.h
@@ -444,6 +444,7 @@ extern const struct nla_policy ethnl_plca_set_cfg_policy[ETHTOOL_A_PLCA_MAX + 1]
 extern const struct nla_policy ethnl_plca_get_status_policy[ETHTOOL_A_PLCA_HEADER + 1];
 extern const struct nla_policy ethnl_mm_get_policy[ETHTOOL_A_MM_HEADER + 1];
 extern const struct nla_policy ethnl_mm_set_policy[ETHTOOL_A_MM_MAX + 1];
+extern const struct nla_policy ethnl_phy_get_policy[ETHTOOL_A_PHY_HEADER + 1];
 
 int ethnl_set_features(struct sk_buff *skb, struct genl_info *info);
 int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info);
@@ -451,6 +452,10 @@ int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info);
 int ethnl_tunnel_info_doit(struct sk_buff *skb, struct genl_info *info);
 int ethnl_tunnel_info_start(struct netlink_callback *cb);
 int ethnl_tunnel_info_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
+int ethnl_phy_start(struct netlink_callback *cb);
+int ethnl_phy_doit(struct sk_buff *skb, struct genl_info *info);
+int ethnl_phy_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
+int ethnl_phy_done(struct netlink_callback *cb);
 
 extern const char stats_std_names[__ETHTOOL_STATS_CNT][ETH_GSTRING_LEN];
 extern const char stats_eth_phy_names[__ETHTOOL_A_STATS_ETH_PHY_CNT][ETH_GSTRING_LEN];
diff --git a/net/ethtool/phy.c b/net/ethtool/phy.c
new file mode 100644
index 000000000000..5add2840aaeb
--- /dev/null
+++ b/net/ethtool/phy.c
@@ -0,0 +1,306 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2023 Bootlin
+ *
+ */
+#include "common.h"
+#include "netlink.h"
+
+#include <linux/phy.h>
+#include <linux/phy_link_topology.h>
+#include <linux/sfp.h>
+
+struct phy_req_info {
+	struct ethnl_req_info		base;
+	struct phy_device_node		pdn;
+};
+
+#define PHY_REQINFO(__req_base) \
+	container_of(__req_base, struct phy_req_info, base)
+
+const struct nla_policy ethnl_phy_get_policy[ETHTOOL_A_PHY_HEADER + 1] = {
+	[ETHTOOL_A_PHY_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy),
+};
+
+/* Caller holds rtnl */
+static ssize_t
+ethnl_phy_reply_size(const struct ethnl_req_info *req_base,
+		     struct netlink_ext_ack *extack)
+{
+	struct phy_link_topology *topo;
+	struct phy_device_node *pdn;
+	struct phy_device *phydev;
+	unsigned long index;
+	size_t size;
+
+	ASSERT_RTNL();
+
+	topo = &req_base->dev->link_topo;
+
+	size = nla_total_size(0);
+
+	xa_for_each(&topo->phys, index, pdn) {
+		phydev = pdn->phy;
+
+		/* ETHTOOL_A_PHY_INDEX */
+		size += nla_total_size(sizeof(u32));
+
+		/* ETHTOOL_A_DRVNAME */
+		size += nla_total_size(strlen(phydev->drv->name) + 1);
+
+		/* ETHTOOL_A_NAME */
+		size += nla_total_size(strlen(dev_name(&phydev->mdio.dev)) + 1);
+
+		/* ETHTOOL_A_PHY_UPSTREAM_TYPE */
+		size += nla_total_size(sizeof(u8));
+
+		/* ETHTOOL_A_PHY_ID */
+		size += nla_total_size(sizeof(u32));
+
+		if (phy_on_sfp(phydev)) {
+			const char *upstream_sfp_name = sfp_get_name(pdn->parent_sfp_bus);
+
+			/* ETHTOOL_A_PHY_UPSTREAM_SFP_NAME */
+			if (upstream_sfp_name)
+				size += nla_total_size(strlen(upstream_sfp_name) + 1);
+
+			/* ETHTOOL_A_PHY_UPSTREAM_INDEX */
+			size += nla_total_size(sizeof(u32));
+		}
+
+		/* ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME */
+		if (phydev->sfp_bus) {
+			const char *sfp_name = sfp_get_name(phydev->sfp_bus);
+
+			if (sfp_name)
+				size += nla_total_size(strlen(sfp_name) + 1);
+		}
+	}
+
+	return size;
+}
+
+static int
+ethnl_phy_fill_reply(const struct ethnl_req_info *req_base, struct sk_buff *skb)
+{
+	struct phy_req_info *req_info = PHY_REQINFO(req_base);
+	struct phy_device_node *pdn = &req_info->pdn;
+	struct phy_device *phydev = pdn->phy;
+	enum phy_upstream ptype;
+	struct nlattr *nest;
+
+	ptype = pdn->upstream_type;
+
+	if (nla_put_u32(skb, ETHTOOL_A_PHY_INDEX, phydev->phyindex) ||
+	    nla_put_string(skb, ETHTOOL_A_PHY_DRVNAME, phydev->drv->name) ||
+	    nla_put_string(skb, ETHTOOL_A_PHY_NAME, dev_name(&phydev->mdio.dev)) ||
+	    nla_put_u8(skb, ETHTOOL_A_PHY_UPSTREAM_TYPE, ptype) ||
+	    nla_put_u32(skb, ETHTOOL_A_PHY_ID, phydev->phy_id))
+		return -EMSGSIZE;
+
+	if (ptype == PHY_UPSTREAM_PHY) {
+		struct phy_device *upstream = pdn->upstream.phydev;
+		const char *sfp_upstream_name;
+
+		nest = nla_nest_start(skb, ETHTOOL_A_PHY_UPSTREAM);
+		if (!nest)
+			return -EMSGSIZE;
+
+		/* Parent index */
+		if (nla_put_u32(skb, ETHTOOL_A_PHY_UPSTREAM_INDEX, upstream->phyindex))
+			return -EMSGSIZE;
+
+		if (pdn->parent_sfp_bus) {
+			sfp_upstream_name = sfp_get_name(pdn->parent_sfp_bus);
+			if (sfp_upstream_name && nla_put_string(skb,
+								ETHTOOL_A_PHY_UPSTREAM_SFP_NAME,
+								sfp_upstream_name))
+				return -EMSGSIZE;
+		}
+
+		nla_nest_end(skb, nest);
+	}
+
+	if (phydev->sfp_bus) {
+		const char *sfp_name = sfp_get_name(phydev->sfp_bus);
+
+		if (sfp_name &&
+		    nla_put_string(skb, ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME,
+				   sfp_name))
+			return -EMSGSIZE;
+	}
+
+	return 0;
+}
+
+static int ethnl_phy_parse_request(struct ethnl_req_info *req_base,
+				   struct nlattr **tb)
+{
+	struct phy_link_topology *topo = &req_base->dev->link_topo;
+	struct phy_req_info *req_info = PHY_REQINFO(req_base);
+	struct phy_device_node *pdn;
+
+	if (!req_base->phydev)
+		return 0;
+
+	pdn = xa_load(&topo->phys, req_base->phydev->phyindex);
+	memcpy(&req_info->pdn, pdn, sizeof(*pdn));
+
+	return 0;
+}
+
+int ethnl_phy_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct phy_req_info req_info = {};
+	struct nlattr **tb = info->attrs;
+	struct sk_buff *rskb;
+	void *reply_payload;
+	int reply_len;
+	int ret;
+
+	ret = ethnl_parse_header_dev_get(&req_info.base,
+					 tb[ETHTOOL_A_PHY_HEADER],
+					 genl_info_net(info), info->extack,
+					 true);
+	if (ret < 0)
+		return ret;
+
+	rtnl_lock();
+
+	ret = ethnl_phy_parse_request(&req_info.base, tb);
+	if (ret < 0)
+		goto err_unlock_rtnl;
+
+	/* No PHY, return early */
+	if (!req_info.pdn.phy)
+		goto err_unlock_rtnl;
+
+	ret = ethnl_phy_reply_size(&req_info.base, info->extack);
+	if (ret < 0)
+		goto err_unlock_rtnl;
+	reply_len = ret + ethnl_reply_header_size();
+
+	rskb = ethnl_reply_init(reply_len, req_info.base.dev,
+				ETHTOOL_MSG_PHY_GET_REPLY,
+				ETHTOOL_A_PHY_HEADER,
+				info, &reply_payload);
+	if (!rskb) {
+		ret = -ENOMEM;
+		goto err_unlock_rtnl;
+	}
+
+	ret = ethnl_phy_fill_reply(&req_info.base, rskb);
+	if (ret)
+		goto err_free_msg;
+
+	rtnl_unlock();
+	ethnl_parse_header_dev_put(&req_info.base);
+	genlmsg_end(rskb, reply_payload);
+
+	return genlmsg_reply(rskb, info);
+
+err_free_msg:
+	nlmsg_free(rskb);
+err_unlock_rtnl:
+	rtnl_unlock();
+	ethnl_parse_header_dev_put(&req_info.base);
+	return ret;
+}
+
+struct ethnl_phy_dump_ctx {
+	struct phy_req_info	*phy_req_info;
+};
+
+int ethnl_phy_start(struct netlink_callback *cb)
+{
+	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
+	struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx;
+	struct nlattr **tb = info->info.attrs;
+	int ret;
+
+	BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx));
+
+	ctx->phy_req_info = kzalloc(sizeof(*ctx->phy_req_info), GFP_KERNEL);
+	if (!ctx->phy_req_info)
+		return -ENOMEM;
+
+	ret = ethnl_parse_header_dev_get(&ctx->phy_req_info->base,
+					 tb[ETHTOOL_A_PHY_HEADER],
+					 sock_net(cb->skb->sk), cb->extack,
+					 false);
+	return ret;
+}
+
+int ethnl_phy_done(struct netlink_callback *cb)
+{
+	struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx;
+
+	kfree(ctx->phy_req_info);
+
+	return 0;
+}
+
+static int ethnl_phy_dump_one_dev(struct sk_buff *skb, struct net_device *dev,
+				  struct netlink_callback *cb)
+{
+	struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx;
+	struct phy_req_info *pri = ctx->phy_req_info;
+	struct phy_device_node *pdn;
+	unsigned long index = 1;
+	int ret = 0;
+	void *ehdr;
+
+	pri->base.dev = dev;
+
+	xa_for_each(&dev->link_topo.phys, index, pdn) {
+		ehdr = ethnl_dump_put(skb, cb,
+				      ETHTOOL_MSG_PHY_GET_REPLY);
+		if (!ehdr) {
+			ret = -EMSGSIZE;
+			break;
+		}
+
+		ret = ethnl_fill_reply_header(skb, dev,
+					      ETHTOOL_A_PHY_HEADER);
+		if (ret < 0) {
+			genlmsg_cancel(skb, ehdr);
+			break;
+		}
+
+		memcpy(&pri->pdn, pdn, sizeof(*pdn));
+		ret = ethnl_phy_fill_reply(&pri->base, skb);
+
+		genlmsg_end(skb, ehdr);
+	}
+
+	return ret;
+}
+
+int ethnl_phy_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx;
+	struct net *net = sock_net(skb->sk);
+	unsigned long ifindex = 1;
+	struct net_device *dev;
+	int ret = 0;
+
+	rtnl_lock();
+
+	if (ctx->phy_req_info->base.dev) {
+		ret = ethnl_phy_dump_one_dev(skb, ctx->phy_req_info->base.dev, cb);
+		ethnl_parse_header_dev_put(&ctx->phy_req_info->base);
+		ctx->phy_req_info->base.dev = NULL;
+	} else {
+		for_each_netdev_dump(net, dev, ifindex) {
+			ret = ethnl_phy_dump_one_dev(skb, dev, cb);
+			if (ret)
+				break;
+		}
+	}
+	rtnl_unlock();
+
+	if (ret == -EMSGSIZE && skb->len)
+		return skb->len;
+	return ret;
+}
+
-- 
cgit v1.2.3


From 5a0e241003b80247de59727c945bc94c848f893d Mon Sep 17 00:00:00 2001
From: Fabio Estevam <festevam@denx.de>
Date: Wed, 29 Nov 2023 09:43:28 -0300
Subject: thermal/core: Prepare for introduction of thermal reboot

Add some helper functions to make it easier introducing the support
for thermal reboot.

No functional change.

Signed-off-by: Fabio Estevam <festevam@denx.de>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Link: https://lore.kernel.org/r/20231129124330.519423-2-festevam@gmail.com
---
 drivers/thermal/thermal_core.c | 14 ++++++++++----
 include/linux/reboot.h         |  7 ++++++-
 kernel/reboot.c                |  8 ++++----
 3 files changed, 20 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 5e5fcbd81dda..859f62e9d779 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -311,18 +311,24 @@ static void handle_non_critical_trips(struct thermal_zone_device *tz,
 		       def_governor->throttle(tz, trip);
 }
 
-void thermal_zone_device_critical(struct thermal_zone_device *tz)
+static void thermal_zone_device_halt(struct thermal_zone_device *tz, bool shutdown)
 {
 	/*
 	 * poweroff_delay_ms must be a carefully profiled positive value.
 	 * Its a must for forced_emergency_poweroff_work to be scheduled.
 	 */
 	int poweroff_delay_ms = CONFIG_THERMAL_EMERGENCY_POWEROFF_DELAY_MS;
+	const char *msg = "Temperature too high";
+
+	dev_emerg(&tz->device, "%s: critical temperature reached\n", tz->type);
 
-	dev_emerg(&tz->device, "%s: critical temperature reached, "
-		  "shutting down\n", tz->type);
+	if (shutdown)
+		hw_protection_shutdown(msg, poweroff_delay_ms);
+}
 
-	hw_protection_shutdown("Temperature too high", poweroff_delay_ms);
+void thermal_zone_device_critical(struct thermal_zone_device *tz)
+{
+	thermal_zone_device_halt(tz, true);
 }
 EXPORT_SYMBOL(thermal_zone_device_critical);
 
diff --git a/include/linux/reboot.h b/include/linux/reboot.h
index c4cc3b89ced1..4586c663884e 100644
--- a/include/linux/reboot.h
+++ b/include/linux/reboot.h
@@ -177,7 +177,12 @@ void ctrl_alt_del(void);
 
 extern void orderly_poweroff(bool force);
 extern void orderly_reboot(void);
-void hw_protection_shutdown(const char *reason, int ms_until_forced);
+void __hw_protection_shutdown(const char *reason, int ms_until_forced, bool shutdown);
+
+static inline void hw_protection_shutdown(const char *reason, int ms_until_forced)
+{
+	__hw_protection_shutdown(reason, ms_until_forced, true);
+}
 
 /*
  * Emergency restart, callable from an interrupt handler.
diff --git a/kernel/reboot.c b/kernel/reboot.c
index 395a0ea3c7a8..b236c4c06bb3 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -957,7 +957,7 @@ static void hw_failure_emergency_poweroff(int poweroff_delay_ms)
 }
 
 /**
- * hw_protection_shutdown - Trigger an emergency system poweroff
+ * __hw_protection_shutdown - Trigger an emergency system poweroff
  *
  * @reason:		Reason of emergency shutdown to be printed.
  * @ms_until_forced:	Time to wait for orderly shutdown before tiggering a
@@ -971,7 +971,7 @@ static void hw_failure_emergency_poweroff(int poweroff_delay_ms)
  * if the previous request has given a large timeout for forced shutdown.
  * Can be called from any context.
  */
-void hw_protection_shutdown(const char *reason, int ms_until_forced)
+void __hw_protection_shutdown(const char *reason, int ms_until_forced, bool shutdown)
 {
 	static atomic_t allow_proceed = ATOMIC_INIT(1);
 
@@ -986,9 +986,9 @@ void hw_protection_shutdown(const char *reason, int ms_until_forced)
 	 * orderly_poweroff failure
 	 */
 	hw_failure_emergency_poweroff(ms_until_forced);
-	orderly_poweroff(true);
+	if (shutdown)
+		orderly_poweroff(true);
 }
-EXPORT_SYMBOL_GPL(hw_protection_shutdown);
 
 static int __init reboot_setup(char *str)
 {
-- 
cgit v1.2.3


From 79fa723ba84c2b1b3124c72df8a3b07b851a5477 Mon Sep 17 00:00:00 2001
From: Fabio Estevam <festevam@denx.de>
Date: Wed, 29 Nov 2023 09:43:29 -0300
Subject: reboot: Introduce thermal_zone_device_critical_reboot()

Introduce thermal_zone_device_critical_reboot() to trigger an
emergency reboot.

It is a counterpart of thermal_zone_device_critical() with the
difference that it will force a reboot instead of shutdown.

The motivation for doing this is to allow the thermal subystem
to trigger a reboot when the temperature reaches the critical
temperature.

Signed-off-by: Fabio Estevam <festevam@denx.de>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Link: https://lore.kernel.org/r/20231129124330.519423-3-festevam@gmail.com
---
 drivers/thermal/thermal_core.c |  7 +++++++
 drivers/thermal/thermal_core.h |  1 +
 include/linux/reboot.h         |  5 +++++
 kernel/reboot.c                | 28 +++++++++++++++++-----------
 4 files changed, 30 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 859f62e9d779..0d761afb7cbc 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -324,6 +324,8 @@ static void thermal_zone_device_halt(struct thermal_zone_device *tz, bool shutdo
 
 	if (shutdown)
 		hw_protection_shutdown(msg, poweroff_delay_ms);
+	else
+		hw_protection_reboot(msg, poweroff_delay_ms);
 }
 
 void thermal_zone_device_critical(struct thermal_zone_device *tz)
@@ -332,6 +334,11 @@ void thermal_zone_device_critical(struct thermal_zone_device *tz)
 }
 EXPORT_SYMBOL(thermal_zone_device_critical);
 
+void thermal_zone_device_critical_reboot(struct thermal_zone_device *tz)
+{
+	thermal_zone_device_halt(tz, false);
+}
+
 static void handle_critical_trips(struct thermal_zone_device *tz,
 				  const struct thermal_trip *trip)
 {
diff --git a/drivers/thermal/thermal_core.h b/drivers/thermal/thermal_core.h
index fe2917a74054..b5e6743bd157 100644
--- a/drivers/thermal/thermal_core.h
+++ b/drivers/thermal/thermal_core.h
@@ -114,6 +114,7 @@ int thermal_zone_device_set_policy(struct thermal_zone_device *, char *);
 int thermal_build_list_of_policies(char *buf);
 void __thermal_zone_device_update(struct thermal_zone_device *tz,
 				  enum thermal_notify_event event);
+void thermal_zone_device_critical_reboot(struct thermal_zone_device *tz);
 
 /* Helpers */
 #define for_each_trip(__tz, __trip)	\
diff --git a/include/linux/reboot.h b/include/linux/reboot.h
index 4586c663884e..abcdde4df697 100644
--- a/include/linux/reboot.h
+++ b/include/linux/reboot.h
@@ -179,6 +179,11 @@ extern void orderly_poweroff(bool force);
 extern void orderly_reboot(void);
 void __hw_protection_shutdown(const char *reason, int ms_until_forced, bool shutdown);
 
+static inline void hw_protection_reboot(const char *reason, int ms_until_forced)
+{
+	__hw_protection_shutdown(reason, ms_until_forced, false);
+}
+
 static inline void hw_protection_shutdown(const char *reason, int ms_until_forced)
 {
 	__hw_protection_shutdown(reason, ms_until_forced, true);
diff --git a/kernel/reboot.c b/kernel/reboot.c
index b236c4c06bb3..35d5e0b67993 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -957,19 +957,22 @@ static void hw_failure_emergency_poweroff(int poweroff_delay_ms)
 }
 
 /**
- * __hw_protection_shutdown - Trigger an emergency system poweroff
+ * __hw_protection_shutdown - Trigger an emergency system shutdown or reboot
  *
- * @reason:		Reason of emergency shutdown to be printed.
- * @ms_until_forced:	Time to wait for orderly shutdown before tiggering a
- *			forced shudown. Negative value disables the forced
- *			shutdown.
+ * @reason:		Reason of emergency shutdown or reboot to be printed.
+ * @ms_until_forced:	Time to wait for orderly shutdown or reboot before
+ *			triggering it. Negative value disables the forced
+ *			shutdown or reboot.
+ * @shutdown:		If true, indicates that a shutdown will happen
+ *			after the critical tempeature is reached.
+ *			If false, indicates that a reboot will happen
+ *			after the critical tempeature is reached.
  *
- * Initiate an emergency system shutdown in order to protect hardware from
- * further damage. Usage examples include a thermal protection or a voltage or
- * current regulator failures.
- * NOTE: The request is ignored if protection shutdown is already pending even
- * if the previous request has given a large timeout for forced shutdown.
- * Can be called from any context.
+ * Initiate an emergency system shutdown or reboot in order to protect
+ * hardware from further damage. Usage examples include a thermal protection.
+ * NOTE: The request is ignored if protection shutdown or reboot is already
+ * pending even if the previous request has given a large timeout for forced
+ * shutdown/reboot.
  */
 void __hw_protection_shutdown(const char *reason, int ms_until_forced, bool shutdown)
 {
@@ -988,7 +991,10 @@ void __hw_protection_shutdown(const char *reason, int ms_until_forced, bool shut
 	hw_failure_emergency_poweroff(ms_until_forced);
 	if (shutdown)
 		orderly_poweroff(true);
+	else
+		orderly_reboot();
 }
+EXPORT_SYMBOL_GPL(__hw_protection_shutdown);
 
 static int __init reboot_setup(char *str)
 {
-- 
cgit v1.2.3


From 37d158d0b05144f696323ae5bbfe1e137f7c06d3 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Wed, 20 Dec 2023 08:38:46 +0100
Subject: HID: make hid_bus_type const

Now that the driver core can properly handle constant struct bus_type,
move the hid_bus_type variable to be a constant structure as well,
placing it into read-only memory which can not be modified at runtime.

Cc: Jiri Kosina <jikos@kernel.org>
Cc: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Cc: linux-input@vger.kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-core.c | 2 +-
 include/linux/hid.h    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index e0181218ad85..de7a477d6665 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -2749,7 +2749,7 @@ static int hid_uevent(const struct device *dev, struct kobj_uevent_env *env)
 	return 0;
 }
 
-struct bus_type hid_bus_type = {
+const struct bus_type hid_bus_type = {
 	.name		= "hid",
 	.dev_groups	= hid_dev_groups,
 	.drv_groups	= hid_drv_groups,
diff --git a/include/linux/hid.h b/include/linux/hid.h
index bf43f3ff6664..7c26db874ff0 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -912,7 +912,7 @@ extern bool hid_ignore(struct hid_device *);
 extern int hid_add_device(struct hid_device *);
 extern void hid_destroy_device(struct hid_device *);
 
-extern struct bus_type hid_bus_type;
+extern const struct bus_type hid_bus_type;
 
 extern int __must_check __hid_register_driver(struct hid_driver *,
 		struct module *, const char *mod_name);
-- 
cgit v1.2.3


From 9b0a3839e8d29663cd9ee2c43d38b06c3b91619e Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Wed, 20 Dec 2023 08:38:48 +0100
Subject: HID: bpf: make bus_type const in struct hid_bpf_ops

The struct bus_type pointer in hid_bpf_ops just passes the pointer to
the driver core, and the driver core can handle, and expects, a constant
pointer, so also make the pointer constant in hid_bpf_ops.

Part of the process of moving all usages of struct bus_type to be
constant to move them all to read-only memory.

Cc: Jiri Kosina <jikos@kernel.org>
Cc: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Cc: linux-input@vger.kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 include/linux/hid_bpf.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/hid_bpf.h b/include/linux/hid_bpf.h
index e9afb61e6ee0..840cd254172d 100644
--- a/include/linux/hid_bpf.h
+++ b/include/linux/hid_bpf.h
@@ -115,7 +115,7 @@ struct hid_bpf_ops {
 				  size_t len, enum hid_report_type rtype,
 				  enum hid_class_request reqtype);
 	struct module *owner;
-	struct bus_type *bus_type;
+	const struct bus_type *bus_type;
 };
 
 extern struct hid_bpf_ops *hid_bpf_ops;
-- 
cgit v1.2.3


From 200a6b3af05918ddb18832fa4d5a8f15c9dd99e0 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sat, 30 Dec 2023 21:48:56 -0800
Subject: drm/gpuvm: fix all kernel-doc warnings in include/drm/drm_gpuvm.h

Update kernel-doc comments in <drm/drm_gpuvm.h> to correct all
kernel-doc warnings:

drm_gpuvm.h:148: warning: Excess struct member 'addr' description in 'drm_gpuva'
drm_gpuvm.h:148: warning: Excess struct member 'offset' description in 'drm_gpuva'
drm_gpuvm.h:148: warning: Excess struct member 'obj' description in 'drm_gpuva'
drm_gpuvm.h:148: warning: Excess struct member 'entry' description in 'drm_gpuva'
drm_gpuvm.h:148: warning: Excess struct member '__subtree_last' description in 'drm_gpuva'
drm_gpuvm.h:192: warning: No description found for return value of 'drm_gpuva_invalidated'
drm_gpuvm.h:331: warning: Excess struct member 'tree' description in 'drm_gpuvm'
drm_gpuvm.h:331: warning: Excess struct member 'list' description in 'drm_gpuvm'
drm_gpuvm.h:331: warning: Excess struct member 'list' description in 'drm_gpuvm'
drm_gpuvm.h:331: warning: Excess struct member 'local_list' description in 'drm_gpuvm'
drm_gpuvm.h:331: warning: Excess struct member 'lock' description in 'drm_gpuvm'
drm_gpuvm.h:331: warning: Excess struct member 'list' description in 'drm_gpuvm'
drm_gpuvm.h:331: warning: Excess struct member 'local_list' description in 'drm_gpuvm'
drm_gpuvm.h:331: warning: Excess struct member 'lock' description in 'drm_gpuvm'
drm_gpuvm.h:352: warning: No description found for return value of 'drm_gpuvm_get'
drm_gpuvm.h:545: warning: Excess struct member 'fn' description in 'drm_gpuvm_exec'
drm_gpuvm.h:545: warning: Excess struct member 'priv' description in 'drm_gpuvm_exec'
drm_gpuvm.h:597: warning: missing initial short description on line:
 * drm_gpuvm_exec_resv_add_fence()
drm_gpuvm.h:616: warning: missing initial short description on line:
 * drm_gpuvm_exec_validate()
drm_gpuvm.h:623: warning: No description found for return value of 'drm_gpuvm_exec_validate'
drm_gpuvm.h:698: warning: Excess struct member 'gpuva' description in 'drm_gpuvm_bo'
drm_gpuvm.h:698: warning: Excess struct member 'entry' description in 'drm_gpuvm_bo'
drm_gpuvm.h:698: warning: Excess struct member 'gem' description in 'drm_gpuvm_bo'
drm_gpuvm.h:698: warning: Excess struct member 'evict' description in 'drm_gpuvm_bo'
drm_gpuvm.h:726: warning: No description found for return value of 'drm_gpuvm_bo_get'
drm_gpuvm.h:738: warning: missing initial short description on line:
 * drm_gpuvm_bo_gem_evict()
drm_gpuvm.h:740: warning: missing initial short description on line:
 * drm_gpuvm_bo_gem_evict()
drm_gpuvm.h:698: warning: Excess struct member 'evict' description in 'drm_gpuvm_bo'
drm_gpuvm.h:844: warning: Excess struct member 'addr' description in 'drm_gpuva_op_map'
drm_gpuvm.h:844: warning: Excess struct member 'range' description in 'drm_gpuva_op_map'
drm_gpuvm.h:844: warning: Excess struct member 'offset' description in 'drm_gpuva_op_map'
drm_gpuvm.h:844: warning: Excess struct member 'obj' description in 'drm_gpuva_op_map'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Maxime Ripard <mripard@kernel.org>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Cc: David Airlie <airlied@gmail.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: dri-devel@lists.freedesktop.org
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Vegard Nossum <vegard.nossum@oracle.com>
Signed-off-by: Maxime Ripard <mripard@kernel.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20231231054856.31786-1-rdunlap@infradead.org
---
 include/drm/drm_gpuvm.h | 80 +++++++++++++++++++++++++++----------------------
 1 file changed, 45 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/include/drm/drm_gpuvm.h b/include/drm/drm_gpuvm.h
index 6258849382e1..f3fdb810989a 100644
--- a/include/drm/drm_gpuvm.h
+++ b/include/drm/drm_gpuvm.h
@@ -92,7 +92,7 @@ struct drm_gpuva {
 	 */
 	struct {
 		/**
-		 * @addr: the start address
+		 * @va.addr: the start address
 		 */
 		u64 addr;
 
@@ -107,17 +107,17 @@ struct drm_gpuva {
 	 */
 	struct {
 		/**
-		 * @offset: the offset within the &drm_gem_object
+		 * @gem.offset: the offset within the &drm_gem_object
 		 */
 		u64 offset;
 
 		/**
-		 * @obj: the mapped &drm_gem_object
+		 * @gem.obj: the mapped &drm_gem_object
 		 */
 		struct drm_gem_object *obj;
 
 		/**
-		 * @entry: the &list_head to attach this object to a &drm_gpuvm_bo
+		 * @gem.entry: the &list_head to attach this object to a &drm_gpuvm_bo
 		 */
 		struct list_head entry;
 	} gem;
@@ -127,12 +127,12 @@ struct drm_gpuva {
 	 */
 	struct {
 		/**
-		 * @rb: the rb-tree node
+		 * @rb.node: the rb-tree node
 		 */
 		struct rb_node node;
 
 		/**
-		 * @entry: The &list_head to additionally connect &drm_gpuvas
+		 * @rb.entry: The &list_head to additionally connect &drm_gpuvas
 		 * in the same order they appear in the interval tree. This is
 		 * useful to keep iterating &drm_gpuvas from a start node found
 		 * through the rb-tree while doing modifications on the rb-tree
@@ -141,7 +141,7 @@ struct drm_gpuva {
 		struct list_head entry;
 
 		/**
-		 * @__subtree_last: needed by the interval tree, holding last-in-subtree
+		 * @rb.__subtree_last: needed by the interval tree, holding last-in-subtree
 		 */
 		u64 __subtree_last;
 	} rb;
@@ -187,6 +187,8 @@ static inline void drm_gpuva_invalidate(struct drm_gpuva *va, bool invalidate)
  * drm_gpuva_invalidated() - indicates whether the backing BO of this &drm_gpuva
  * is invalidated
  * @va: the &drm_gpuva to check
+ *
+ * Returns: %true if the GPU VA is invalidated, %false otherwise
  */
 static inline bool drm_gpuva_invalidated(struct drm_gpuva *va)
 {
@@ -252,12 +254,12 @@ struct drm_gpuvm {
 	 */
 	struct {
 		/**
-		 * @tree: the rb-tree to track GPU VA mappings
+		 * @rb.tree: the rb-tree to track GPU VA mappings
 		 */
 		struct rb_root_cached tree;
 
 		/**
-		 * @list: the &list_head to track GPU VA mappings
+		 * @rb.list: the &list_head to track GPU VA mappings
 		 */
 		struct list_head list;
 	} rb;
@@ -290,19 +292,19 @@ struct drm_gpuvm {
 	 */
 	struct {
 		/**
-		 * @list: &list_head storing &drm_gpuvm_bos serving as
+		 * @extobj.list: &list_head storing &drm_gpuvm_bos serving as
 		 * external object
 		 */
 		struct list_head list;
 
 		/**
-		 * @local_list: pointer to the local list temporarily storing
-		 * entries from the external object list
+		 * @extobj.local_list: pointer to the local list temporarily
+		 * storing entries from the external object list
 		 */
 		struct list_head *local_list;
 
 		/**
-		 * @lock: spinlock to protect the extobj list
+		 * @extobj.lock: spinlock to protect the extobj list
 		 */
 		spinlock_t lock;
 	} extobj;
@@ -312,19 +314,19 @@ struct drm_gpuvm {
 	 */
 	struct {
 		/**
-		 * @list: &list_head storing &drm_gpuvm_bos currently being
-		 * evicted
+		 * @evict.list: &list_head storing &drm_gpuvm_bos currently
+		 * being evicted
 		 */
 		struct list_head list;
 
 		/**
-		 * @local_list: pointer to the local list temporarily storing
-		 * entries from the evicted object list
+		 * @evict.local_list: pointer to the local list temporarily
+		 * storing entries from the evicted object list
 		 */
 		struct list_head *local_list;
 
 		/**
-		 * @lock: spinlock to protect the evict list
+		 * @evict.lock: spinlock to protect the evict list
 		 */
 		spinlock_t lock;
 	} evict;
@@ -344,6 +346,8 @@ void drm_gpuvm_init(struct drm_gpuvm *gpuvm, const char *name,
  *
  * This function acquires an additional reference to @gpuvm. It is illegal to
  * call this without already holding a reference. No locks required.
+ *
+ * Returns: the &struct drm_gpuvm pointer
  */
 static inline struct drm_gpuvm *
 drm_gpuvm_get(struct drm_gpuvm *gpuvm)
@@ -533,12 +537,13 @@ struct drm_gpuvm_exec {
 	 */
 	struct {
 		/**
-		 * @fn: The driver callback to lock additional &drm_gem_objects.
+		 * @extra.fn: The driver callback to lock additional
+		 * &drm_gem_objects.
 		 */
 		int (*fn)(struct drm_gpuvm_exec *vm_exec);
 
 		/**
-		 * @priv: driver private data for the @fn callback
+		 * @extra.priv: driver private data for the @fn callback
 		 */
 		void *priv;
 	} extra;
@@ -589,7 +594,7 @@ void drm_gpuvm_resv_add_fence(struct drm_gpuvm *gpuvm,
 			      enum dma_resv_usage extobj_usage);
 
 /**
- * drm_gpuvm_exec_resv_add_fence()
+ * drm_gpuvm_exec_resv_add_fence() - add fence to private and all extobj
  * @vm_exec: the &drm_gpuvm_exec wrapper
  * @fence: fence to add
  * @private_usage: private dma-resv usage
@@ -608,10 +613,12 @@ drm_gpuvm_exec_resv_add_fence(struct drm_gpuvm_exec *vm_exec,
 }
 
 /**
- * drm_gpuvm_exec_validate()
+ * drm_gpuvm_exec_validate() - validate all BOs marked as evicted
  * @vm_exec: the &drm_gpuvm_exec wrapper
  *
  * See drm_gpuvm_validate().
+ *
+ * Returns: 0 on success, negative error code on failure.
  */
 static inline int
 drm_gpuvm_exec_validate(struct drm_gpuvm_exec *vm_exec)
@@ -664,7 +671,7 @@ struct drm_gpuvm_bo {
 	 */
 	struct {
 		/**
-		 * @gpuva: The list of linked &drm_gpuvas.
+		 * @list.gpuva: The list of linked &drm_gpuvas.
 		 *
 		 * It is safe to access entries from this list as long as the
 		 * GEM's gpuva lock is held. See also struct drm_gem_object.
@@ -672,25 +679,25 @@ struct drm_gpuvm_bo {
 		struct list_head gpuva;
 
 		/**
-		 * @entry: Structure containing all &list_heads serving as
+		 * @list.entry: Structure containing all &list_heads serving as
 		 * entry.
 		 */
 		struct {
 			/**
-			 * @gem: List entry to attach to the &drm_gem_objects
-			 * gpuva list.
+			 * @list.entry.gem: List entry to attach to the
+			 * &drm_gem_objects gpuva list.
 			 */
 			struct list_head gem;
 
 			/**
-			 * @evict: List entry to attach to the &drm_gpuvms
-			 * extobj list.
+			 * @list.entry.evict: List entry to attach to the
+			 * &drm_gpuvms extobj list.
 			 */
 			struct list_head extobj;
 
 			/**
-			 * @evict: List entry to attach to the &drm_gpuvms evict
-			 * list.
+			 * @list.entry.evict: List entry to attach to the
+			 * &drm_gpuvms evict list.
 			 */
 			struct list_head evict;
 		} entry;
@@ -713,6 +720,8 @@ drm_gpuvm_bo_obtain_prealloc(struct drm_gpuvm_bo *vm_bo);
  *
  * This function acquires an additional reference to @vm_bo. It is illegal to
  * call this without already holding a reference. No locks required.
+ *
+ * Returns: the &struct vm_bo pointer
  */
 static inline struct drm_gpuvm_bo *
 drm_gpuvm_bo_get(struct drm_gpuvm_bo *vm_bo)
@@ -730,7 +739,8 @@ drm_gpuvm_bo_find(struct drm_gpuvm *gpuvm,
 void drm_gpuvm_bo_evict(struct drm_gpuvm_bo *vm_bo, bool evict);
 
 /**
- * drm_gpuvm_bo_gem_evict()
+ * drm_gpuvm_bo_gem_evict() - add/remove all &drm_gpuvm_bo's in the list
+ * to/from the &drm_gpuvms evicted list
  * @obj: the &drm_gem_object
  * @evict: indicates whether @obj is evicted
  *
@@ -817,12 +827,12 @@ struct drm_gpuva_op_map {
 	 */
 	struct {
 		/**
-		 * @addr: the base address of the new mapping
+		 * @va.addr: the base address of the new mapping
 		 */
 		u64 addr;
 
 		/**
-		 * @range: the range of the new mapping
+		 * @va.range: the range of the new mapping
 		 */
 		u64 range;
 	} va;
@@ -832,12 +842,12 @@ struct drm_gpuva_op_map {
 	 */
 	struct {
 		/**
-		 * @offset: the offset within the &drm_gem_object
+		 * @gem.offset: the offset within the &drm_gem_object
 		 */
 		u64 offset;
 
 		/**
-		 * @obj: the &drm_gem_object to map
+		 * @gem.obj: the &drm_gem_object to map
 		 */
 		struct drm_gem_object *obj;
 	} gem;
-- 
cgit v1.2.3


From 87d8f1ee1d4070571095859d310f6951440f288c Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sat, 23 Dec 2023 11:43:19 -0800
Subject: platform/x86: wmi: linux/wmi.h: fix Excess kernel-doc description
 warning
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Remove the "private:" comment to prevent the kernel-doc warning:

include/linux/wmi.h:27: warning: Excess struct member 'setable' description in 'wmi_device'

Either a struct member is documented (via kernel-doc) or it's private,
but not both.

Fixes: b4cc979588ee ("platform/x86: wmi: Add kernel doc comments")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Armin Wolf <W_Armin@gmx.de>
Cc: Hans de Goede <hdegoede@redhat.com>
Cc: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Cc: platform-driver-x86@vger.kernel.org
Reviewed-by: Armin Wolf <W_Armin@gmx.de>
Link: https://lore.kernel.org/r/20231223194321.23084-1-rdunlap@infradead.org
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 include/linux/wmi.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/wmi.h b/include/linux/wmi.h
index 50f7f1e4fd4f..686291b87852 100644
--- a/include/linux/wmi.h
+++ b/include/linux/wmi.h
@@ -21,8 +21,6 @@
  */
 struct wmi_device {
 	struct device dev;
-
-	/* private: used by the WMI driver core */
 	bool setable;
 };
 
-- 
cgit v1.2.3


From 993498e537af9260e697219ce41b41b22b6199cc Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 21 Dec 2023 14:07:47 +0000
Subject: net-device: move gso_partial_features to net_device_read_tx

dev->gso_partial_features is read from tx fast path for GSO packets.

Move it to appropriate section to avoid a cache line miss.

Fixes: 43a71cd66b9c ("net-device: reorganize net_device fast path variables")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Coco Li <lixiaoyan@google.com>
Cc: David Ahern <dsahern@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/net_cachelines/net_device.rst | 2 +-
 include/linux/netdevice.h                              | 2 +-
 net/core/dev.c                                         | 3 ++-
 3 files changed, 4 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/Documentation/networking/net_cachelines/net_device.rst b/Documentation/networking/net_cachelines/net_device.rst
index 6cab1b797739..2dd8d8f20da2 100644
--- a/Documentation/networking/net_cachelines/net_device.rst
+++ b/Documentation/networking/net_cachelines/net_device.rst
@@ -38,7 +38,7 @@ netdev_features_t                   wanted_features
 netdev_features_t                   vlan_features                                                   
 netdev_features_t                   hw_enc_features         -                   -                   netif_skb_features
 netdev_features_t                   mpls_features                                                   
-netdev_features_t                   gso_partial_features                                            
+netdev_features_t                   gso_partial_features    read_mostly                             gso_features_check
 unsigned_int                        min_mtu                                                         
 unsigned_int                        max_mtu                                                         
 unsigned_short                      type                                                            
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5baa5517f533..d59db9adcc96 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2115,6 +2115,7 @@ struct net_device {
 	const struct net_device_ops *netdev_ops;
 	const struct header_ops *header_ops;
 	struct netdev_queue	*_tx;
+	netdev_features_t	gso_partial_features;
 	unsigned int		real_num_tx_queues;
 	unsigned int		gso_max_size;
 	unsigned int		gso_ipv4_max_size;
@@ -2211,7 +2212,6 @@ struct net_device {
 	netdev_features_t	vlan_features;
 	netdev_features_t	hw_enc_features;
 	netdev_features_t	mpls_features;
-	netdev_features_t	gso_partial_features;
 
 	unsigned int		min_mtu;
 	unsigned int		max_mtu;
diff --git a/net/core/dev.c b/net/core/dev.c
index df04cbf77551..31588a50b757 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -11629,6 +11629,7 @@ static void __init net_dev_struct_check(void)
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_max_size);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_ipv4_max_size);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_max_segs);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_partial_features);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, num_tc);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, mtu);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, needed_headroom);
@@ -11642,7 +11643,7 @@ static void __init net_dev_struct_check(void)
 #ifdef CONFIG_NET_XGRESS
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, tcx_egress);
 #endif
-	CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_tx, 152);
+	CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_tx, 160);
 
 	/* TXRX read-mostly hotpath */
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, flags);
-- 
cgit v1.2.3


From ba24ea129126362e7139fed4e13701ca5b71ac0b Mon Sep 17 00:00:00 2001
From: Jamal Hadi Salim <jhs@mojatatu.com>
Date: Thu, 21 Dec 2023 16:31:03 -0500
Subject: net/sched: Retire ipt action

The tc ipt action was intended to run all netfilter/iptables target.
Unfortunately it has not benefitted over the years from proper updates when
netfilter changes, and for that reason it has remained rudimentary.
Pinging a bunch of people that i was aware were using this indicates that
removing it wont affect them.
Retire it to reduce maintenance efforts. Buh-bye.

Reviewed-by: Victor Noguiera <victor@mojatatu.com>
Reviewed-by: Pedro Tammela <pctammela@mojatatu.com>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tc_act/tc_ipt.h               |  17 --
 include/net/tc_wrapper.h                  |   4 -
 include/uapi/linux/pkt_cls.h              |   4 +-
 include/uapi/linux/tc_act/tc_ipt.h        |  20 --
 net/sched/Makefile                        |   1 -
 net/sched/act_ipt.c                       | 464 ------------------------------
 tools/testing/selftests/tc-testing/config |   1 -
 tools/testing/selftests/tc-testing/tdc.sh |   1 -
 8 files changed, 2 insertions(+), 510 deletions(-)
 delete mode 100644 include/net/tc_act/tc_ipt.h
 delete mode 100644 include/uapi/linux/tc_act/tc_ipt.h
 delete mode 100644 net/sched/act_ipt.c

(limited to 'include')

diff --git a/include/net/tc_act/tc_ipt.h b/include/net/tc_act/tc_ipt.h
deleted file mode 100644
index 4225fcb1c6ba..000000000000
--- a/include/net/tc_act/tc_ipt.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __NET_TC_IPT_H
-#define __NET_TC_IPT_H
-
-#include <net/act_api.h>
-
-struct xt_entry_target;
-
-struct tcf_ipt {
-	struct tc_action	common;
-	u32			tcfi_hook;
-	char			*tcfi_tname;
-	struct xt_entry_target	*tcfi_t;
-};
-#define to_ipt(a) ((struct tcf_ipt *)a)
-
-#endif /* __NET_TC_IPT_H */
diff --git a/include/net/tc_wrapper.h b/include/net/tc_wrapper.h
index a6d481b5bcbc..a608546bcefc 100644
--- a/include/net/tc_wrapper.h
+++ b/include/net/tc_wrapper.h
@@ -117,10 +117,6 @@ static inline int tc_act(struct sk_buff *skb, const struct tc_action *a,
 	if (a->ops->act == tcf_ife_act)
 		return tcf_ife_act(skb, a, res);
 #endif
-#if IS_BUILTIN(CONFIG_NET_ACT_IPT)
-	if (a->ops->act == tcf_ipt_act)
-		return tcf_ipt_act(skb, a, res);
-#endif
 #if IS_BUILTIN(CONFIG_NET_ACT_SIMP)
 	if (a->ops->act == tcf_simp_act)
 		return tcf_simp_act(skb, a, res);
diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index c7082cc60d21..2fec9b51d28d 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -99,7 +99,7 @@ enum {
  * versions.
  */
 #define TCA_ACT_GACT 5
-#define TCA_ACT_IPT 6
+#define TCA_ACT_IPT 6 /* obsoleted, can be reused */
 #define TCA_ACT_PEDIT 7
 #define TCA_ACT_MIRRED 8
 #define TCA_ACT_NAT 9
@@ -120,7 +120,7 @@ enum tca_id {
 	TCA_ID_UNSPEC = 0,
 	TCA_ID_POLICE = 1,
 	TCA_ID_GACT = TCA_ACT_GACT,
-	TCA_ID_IPT = TCA_ACT_IPT,
+	TCA_ID_IPT = TCA_ACT_IPT, /* Obsoleted, can be reused */
 	TCA_ID_PEDIT = TCA_ACT_PEDIT,
 	TCA_ID_MIRRED = TCA_ACT_MIRRED,
 	TCA_ID_NAT = TCA_ACT_NAT,
diff --git a/include/uapi/linux/tc_act/tc_ipt.h b/include/uapi/linux/tc_act/tc_ipt.h
deleted file mode 100644
index c48d7da6750d..000000000000
--- a/include/uapi/linux/tc_act/tc_ipt.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef __LINUX_TC_IPT_H
-#define __LINUX_TC_IPT_H
-
-#include <linux/pkt_cls.h>
-
-enum {
-	TCA_IPT_UNSPEC,
-	TCA_IPT_TABLE,
-	TCA_IPT_HOOK,
-	TCA_IPT_INDEX,
-	TCA_IPT_CNT,
-	TCA_IPT_TM,
-	TCA_IPT_TARG,
-	TCA_IPT_PAD,
-	__TCA_IPT_MAX
-};
-#define TCA_IPT_MAX (__TCA_IPT_MAX - 1)
-                                                                                
-#endif
diff --git a/net/sched/Makefile b/net/sched/Makefile
index b5fd49641d91..82c3f78ca486 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -13,7 +13,6 @@ obj-$(CONFIG_NET_ACT_POLICE)	+= act_police.o
 obj-$(CONFIG_NET_ACT_GACT)	+= act_gact.o
 obj-$(CONFIG_NET_ACT_MIRRED)	+= act_mirred.o
 obj-$(CONFIG_NET_ACT_SAMPLE)	+= act_sample.o
-obj-$(CONFIG_NET_ACT_IPT)	+= act_ipt.o
 obj-$(CONFIG_NET_ACT_NAT)	+= act_nat.o
 obj-$(CONFIG_NET_ACT_PEDIT)	+= act_pedit.o
 obj-$(CONFIG_NET_ACT_SIMP)	+= act_simple.o
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
deleted file mode 100644
index 598d6e299152..000000000000
--- a/net/sched/act_ipt.c
+++ /dev/null
@@ -1,464 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * net/sched/act_ipt.c		iptables target interface
- *
- *TODO: Add other tables. For now we only support the ipv4 table targets
- *
- * Copyright:	Jamal Hadi Salim (2002-13)
- */
-
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/errno.h>
-#include <linux/skbuff.h>
-#include <linux/rtnetlink.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/slab.h>
-#include <net/netlink.h>
-#include <net/pkt_sched.h>
-#include <linux/tc_act/tc_ipt.h>
-#include <net/tc_act/tc_ipt.h>
-#include <net/tc_wrapper.h>
-#include <net/ip.h>
-
-#include <linux/netfilter_ipv4/ip_tables.h>
-
-
-static struct tc_action_ops act_ipt_ops;
-static struct tc_action_ops act_xt_ops;
-
-static int ipt_init_target(struct net *net, struct xt_entry_target *t,
-			   char *table, unsigned int hook)
-{
-	struct xt_tgchk_param par;
-	struct xt_target *target;
-	struct ipt_entry e = {};
-	int ret = 0;
-
-	target = xt_request_find_target(AF_INET, t->u.user.name,
-					t->u.user.revision);
-	if (IS_ERR(target))
-		return PTR_ERR(target);
-
-	t->u.kernel.target = target;
-	memset(&par, 0, sizeof(par));
-	par.net       = net;
-	par.table     = table;
-	par.entryinfo = &e;
-	par.target    = target;
-	par.targinfo  = t->data;
-	par.hook_mask = 1 << hook;
-	par.family    = NFPROTO_IPV4;
-
-	ret = xt_check_target(&par, t->u.target_size - sizeof(*t), 0, false);
-	if (ret < 0) {
-		module_put(t->u.kernel.target->me);
-		return ret;
-	}
-	return 0;
-}
-
-static void ipt_destroy_target(struct xt_entry_target *t, struct net *net)
-{
-	struct xt_tgdtor_param par = {
-		.target   = t->u.kernel.target,
-		.targinfo = t->data,
-		.family   = NFPROTO_IPV4,
-		.net      = net,
-	};
-	if (par.target->destroy != NULL)
-		par.target->destroy(&par);
-	module_put(par.target->me);
-}
-
-static void tcf_ipt_release(struct tc_action *a)
-{
-	struct tcf_ipt *ipt = to_ipt(a);
-
-	if (ipt->tcfi_t) {
-		ipt_destroy_target(ipt->tcfi_t, a->idrinfo->net);
-		kfree(ipt->tcfi_t);
-	}
-	kfree(ipt->tcfi_tname);
-}
-
-static const struct nla_policy ipt_policy[TCA_IPT_MAX + 1] = {
-	[TCA_IPT_TABLE]	= { .type = NLA_STRING, .len = IFNAMSIZ },
-	[TCA_IPT_HOOK]	= NLA_POLICY_RANGE(NLA_U32, NF_INET_PRE_ROUTING,
-					   NF_INET_NUMHOOKS),
-	[TCA_IPT_INDEX]	= { .type = NLA_U32 },
-	[TCA_IPT_TARG]	= { .len = sizeof(struct xt_entry_target) },
-};
-
-static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla,
-			  struct nlattr *est, struct tc_action **a,
-			  const struct tc_action_ops *ops,
-			  struct tcf_proto *tp, u32 flags)
-{
-	struct tc_action_net *tn = net_generic(net, id);
-	bool bind = flags & TCA_ACT_FLAGS_BIND;
-	struct nlattr *tb[TCA_IPT_MAX + 1];
-	struct tcf_ipt *ipt;
-	struct xt_entry_target *td, *t;
-	char *tname;
-	bool exists = false;
-	int ret = 0, err;
-	u32 hook = 0;
-	u32 index = 0;
-
-	if (nla == NULL)
-		return -EINVAL;
-
-	err = nla_parse_nested_deprecated(tb, TCA_IPT_MAX, nla, ipt_policy,
-					  NULL);
-	if (err < 0)
-		return err;
-
-	if (tb[TCA_IPT_INDEX] != NULL)
-		index = nla_get_u32(tb[TCA_IPT_INDEX]);
-
-	err = tcf_idr_check_alloc(tn, &index, a, bind);
-	if (err < 0)
-		return err;
-	exists = err;
-	if (exists && bind)
-		return 0;
-
-	if (tb[TCA_IPT_HOOK] == NULL || tb[TCA_IPT_TARG] == NULL) {
-		if (exists)
-			tcf_idr_release(*a, bind);
-		else
-			tcf_idr_cleanup(tn, index);
-		return -EINVAL;
-	}
-
-	td = (struct xt_entry_target *)nla_data(tb[TCA_IPT_TARG]);
-	if (nla_len(tb[TCA_IPT_TARG]) != td->u.target_size) {
-		if (exists)
-			tcf_idr_release(*a, bind);
-		else
-			tcf_idr_cleanup(tn, index);
-		return -EINVAL;
-	}
-
-	if (!exists) {
-		ret = tcf_idr_create(tn, index, est, a, ops, bind,
-				     false, flags);
-		if (ret) {
-			tcf_idr_cleanup(tn, index);
-			return ret;
-		}
-		ret = ACT_P_CREATED;
-	} else {
-		if (bind)/* dont override defaults */
-			return 0;
-
-		if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
-			tcf_idr_release(*a, bind);
-			return -EEXIST;
-		}
-	}
-
-	err = -EINVAL;
-	hook = nla_get_u32(tb[TCA_IPT_HOOK]);
-	switch (hook) {
-	case NF_INET_PRE_ROUTING:
-		break;
-	case NF_INET_POST_ROUTING:
-		break;
-	default:
-		goto err1;
-	}
-
-	if (tb[TCA_IPT_TABLE]) {
-		/* mangle only for now */
-		if (nla_strcmp(tb[TCA_IPT_TABLE], "mangle"))
-			goto err1;
-	}
-
-	tname = kstrdup("mangle", GFP_KERNEL);
-	if (unlikely(!tname))
-		goto err1;
-
-	t = kmemdup(td, td->u.target_size, GFP_KERNEL);
-	if (unlikely(!t))
-		goto err2;
-
-	err = ipt_init_target(net, t, tname, hook);
-	if (err < 0)
-		goto err3;
-
-	ipt = to_ipt(*a);
-
-	spin_lock_bh(&ipt->tcf_lock);
-	if (ret != ACT_P_CREATED) {
-		ipt_destroy_target(ipt->tcfi_t, net);
-		kfree(ipt->tcfi_tname);
-		kfree(ipt->tcfi_t);
-	}
-	ipt->tcfi_tname = tname;
-	ipt->tcfi_t     = t;
-	ipt->tcfi_hook  = hook;
-	spin_unlock_bh(&ipt->tcf_lock);
-	return ret;
-
-err3:
-	kfree(t);
-err2:
-	kfree(tname);
-err1:
-	tcf_idr_release(*a, bind);
-	return err;
-}
-
-static int tcf_ipt_init(struct net *net, struct nlattr *nla,
-			struct nlattr *est, struct tc_action **a,
-			struct tcf_proto *tp,
-			u32 flags, struct netlink_ext_ack *extack)
-{
-	return __tcf_ipt_init(net, act_ipt_ops.net_id, nla, est,
-			      a, &act_ipt_ops, tp, flags);
-}
-
-static int tcf_xt_init(struct net *net, struct nlattr *nla,
-		       struct nlattr *est, struct tc_action **a,
-		       struct tcf_proto *tp,
-		       u32 flags, struct netlink_ext_ack *extack)
-{
-	return __tcf_ipt_init(net, act_xt_ops.net_id, nla, est,
-			      a, &act_xt_ops, tp, flags);
-}
-
-static bool tcf_ipt_act_check(struct sk_buff *skb)
-{
-	const struct iphdr *iph;
-	unsigned int nhoff, len;
-
-	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
-		return false;
-
-	nhoff = skb_network_offset(skb);
-	iph = ip_hdr(skb);
-	if (iph->ihl < 5 || iph->version != 4)
-		return false;
-
-	len = skb_ip_totlen(skb);
-	if (skb->len < nhoff + len || len < (iph->ihl * 4u))
-		return false;
-
-	return pskb_may_pull(skb, iph->ihl * 4u);
-}
-
-TC_INDIRECT_SCOPE int tcf_ipt_act(struct sk_buff *skb,
-				  const struct tc_action *a,
-				  struct tcf_result *res)
-{
-	char saved_cb[sizeof_field(struct sk_buff, cb)];
-	int ret = 0, result = 0;
-	struct tcf_ipt *ipt = to_ipt(a);
-	struct xt_action_param par;
-	struct nf_hook_state state = {
-		.net	= dev_net(skb->dev),
-		.in	= skb->dev,
-		.hook	= ipt->tcfi_hook,
-		.pf	= NFPROTO_IPV4,
-	};
-
-	if (skb_protocol(skb, false) != htons(ETH_P_IP))
-		return TC_ACT_UNSPEC;
-
-	if (skb_unclone(skb, GFP_ATOMIC))
-		return TC_ACT_UNSPEC;
-
-	if (!tcf_ipt_act_check(skb))
-		return TC_ACT_UNSPEC;
-
-	if (state.hook == NF_INET_POST_ROUTING) {
-		if (!skb_dst(skb))
-			return TC_ACT_UNSPEC;
-
-		state.out = skb->dev;
-	}
-
-	memcpy(saved_cb, skb->cb, sizeof(saved_cb));
-
-	spin_lock(&ipt->tcf_lock);
-
-	tcf_lastuse_update(&ipt->tcf_tm);
-	bstats_update(&ipt->tcf_bstats, skb);
-
-	/* yes, we have to worry about both in and out dev
-	 * worry later - danger - this API seems to have changed
-	 * from earlier kernels
-	 */
-	par.state    = &state;
-	par.target   = ipt->tcfi_t->u.kernel.target;
-	par.targinfo = ipt->tcfi_t->data;
-
-	memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
-
-	ret = par.target->target(skb, &par);
-
-	switch (ret) {
-	case NF_ACCEPT:
-		result = TC_ACT_OK;
-		break;
-	case NF_DROP:
-		result = TC_ACT_SHOT;
-		ipt->tcf_qstats.drops++;
-		break;
-	case XT_CONTINUE:
-		result = TC_ACT_PIPE;
-		break;
-	default:
-		net_notice_ratelimited("tc filter: Bogus netfilter code %d assume ACCEPT\n",
-				       ret);
-		result = TC_ACT_OK;
-		break;
-	}
-	spin_unlock(&ipt->tcf_lock);
-
-	memcpy(skb->cb, saved_cb, sizeof(skb->cb));
-
-	return result;
-
-}
-
-static int tcf_ipt_dump(struct sk_buff *skb, struct tc_action *a, int bind,
-			int ref)
-{
-	unsigned char *b = skb_tail_pointer(skb);
-	struct tcf_ipt *ipt = to_ipt(a);
-	struct xt_entry_target *t;
-	struct tcf_t tm;
-	struct tc_cnt c;
-
-	/* for simple targets kernel size == user size
-	 * user name = target name
-	 * for foolproof you need to not assume this
-	 */
-
-	spin_lock_bh(&ipt->tcf_lock);
-	t = kmemdup(ipt->tcfi_t, ipt->tcfi_t->u.user.target_size, GFP_ATOMIC);
-	if (unlikely(!t))
-		goto nla_put_failure;
-
-	c.bindcnt = atomic_read(&ipt->tcf_bindcnt) - bind;
-	c.refcnt = refcount_read(&ipt->tcf_refcnt) - ref;
-	strcpy(t->u.user.name, ipt->tcfi_t->u.kernel.target->name);
-
-	if (nla_put(skb, TCA_IPT_TARG, ipt->tcfi_t->u.user.target_size, t) ||
-	    nla_put_u32(skb, TCA_IPT_INDEX, ipt->tcf_index) ||
-	    nla_put_u32(skb, TCA_IPT_HOOK, ipt->tcfi_hook) ||
-	    nla_put(skb, TCA_IPT_CNT, sizeof(struct tc_cnt), &c) ||
-	    nla_put_string(skb, TCA_IPT_TABLE, ipt->tcfi_tname))
-		goto nla_put_failure;
-
-	tcf_tm_dump(&tm, &ipt->tcf_tm);
-	if (nla_put_64bit(skb, TCA_IPT_TM, sizeof(tm), &tm, TCA_IPT_PAD))
-		goto nla_put_failure;
-
-	spin_unlock_bh(&ipt->tcf_lock);
-	kfree(t);
-	return skb->len;
-
-nla_put_failure:
-	spin_unlock_bh(&ipt->tcf_lock);
-	nlmsg_trim(skb, b);
-	kfree(t);
-	return -1;
-}
-
-static struct tc_action_ops act_ipt_ops = {
-	.kind		=	"ipt",
-	.id		=	TCA_ID_IPT,
-	.owner		=	THIS_MODULE,
-	.act		=	tcf_ipt_act,
-	.dump		=	tcf_ipt_dump,
-	.cleanup	=	tcf_ipt_release,
-	.init		=	tcf_ipt_init,
-	.size		=	sizeof(struct tcf_ipt),
-};
-
-static __net_init int ipt_init_net(struct net *net)
-{
-	struct tc_action_net *tn = net_generic(net, act_ipt_ops.net_id);
-
-	return tc_action_net_init(net, tn, &act_ipt_ops);
-}
-
-static void __net_exit ipt_exit_net(struct list_head *net_list)
-{
-	tc_action_net_exit(net_list, act_ipt_ops.net_id);
-}
-
-static struct pernet_operations ipt_net_ops = {
-	.init = ipt_init_net,
-	.exit_batch = ipt_exit_net,
-	.id   = &act_ipt_ops.net_id,
-	.size = sizeof(struct tc_action_net),
-};
-
-static struct tc_action_ops act_xt_ops = {
-	.kind		=	"xt",
-	.id		=	TCA_ID_XT,
-	.owner		=	THIS_MODULE,
-	.act		=	tcf_ipt_act,
-	.dump		=	tcf_ipt_dump,
-	.cleanup	=	tcf_ipt_release,
-	.init		=	tcf_xt_init,
-	.size		=	sizeof(struct tcf_ipt),
-};
-
-static __net_init int xt_init_net(struct net *net)
-{
-	struct tc_action_net *tn = net_generic(net, act_xt_ops.net_id);
-
-	return tc_action_net_init(net, tn, &act_xt_ops);
-}
-
-static void __net_exit xt_exit_net(struct list_head *net_list)
-{
-	tc_action_net_exit(net_list, act_xt_ops.net_id);
-}
-
-static struct pernet_operations xt_net_ops = {
-	.init = xt_init_net,
-	.exit_batch = xt_exit_net,
-	.id   = &act_xt_ops.net_id,
-	.size = sizeof(struct tc_action_net),
-};
-
-MODULE_AUTHOR("Jamal Hadi Salim(2002-13)");
-MODULE_DESCRIPTION("Iptables target actions");
-MODULE_LICENSE("GPL");
-MODULE_ALIAS("act_xt");
-
-static int __init ipt_init_module(void)
-{
-	int ret1, ret2;
-
-	ret1 = tcf_register_action(&act_xt_ops, &xt_net_ops);
-	if (ret1 < 0)
-		pr_err("Failed to load xt action\n");
-
-	ret2 = tcf_register_action(&act_ipt_ops, &ipt_net_ops);
-	if (ret2 < 0)
-		pr_err("Failed to load ipt action\n");
-
-	if (ret1 < 0 && ret2 < 0) {
-		return ret1;
-	} else
-		return 0;
-}
-
-static void __exit ipt_cleanup_module(void)
-{
-	tcf_unregister_action(&act_ipt_ops, &ipt_net_ops);
-	tcf_unregister_action(&act_xt_ops, &xt_net_ops);
-}
-
-module_init(ipt_init_module);
-module_exit(ipt_cleanup_module);
diff --git a/tools/testing/selftests/tc-testing/config b/tools/testing/selftests/tc-testing/config
index 012aa33b341b..c60acba951c2 100644
--- a/tools/testing/selftests/tc-testing/config
+++ b/tools/testing/selftests/tc-testing/config
@@ -82,7 +82,6 @@ CONFIG_NET_ACT_GACT=m
 CONFIG_GACT_PROB=y
 CONFIG_NET_ACT_MIRRED=m
 CONFIG_NET_ACT_SAMPLE=m
-CONFIG_NET_ACT_IPT=m
 CONFIG_NET_ACT_NAT=m
 CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_ACT_SIMP=m
diff --git a/tools/testing/selftests/tc-testing/tdc.sh b/tools/testing/selftests/tc-testing/tdc.sh
index 407fa53822a0..c53ede8b730d 100755
--- a/tools/testing/selftests/tc-testing/tdc.sh
+++ b/tools/testing/selftests/tc-testing/tdc.sh
@@ -20,7 +20,6 @@ try_modprobe act_ct
 try_modprobe act_ctinfo
 try_modprobe act_gact
 try_modprobe act_gate
-try_modprobe act_ipt
 try_modprobe act_mirred
 try_modprobe act_mpls
 try_modprobe act_nat
-- 
cgit v1.2.3


From 059d37b718d38d26087121c754691df77acfc66b Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 22 Dec 2023 21:06:13 -0800
Subject: net: phy: linux/phy.h: fix Excess kernel-doc description warning

Remove the @phy_timer: line to prevent the kernel-doc warning:

include/linux/phy.h:768: warning: Excess struct member 'phy_timer' description in 'phy_device'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: Heiner Kallweit <hkallweit1@gmail.com>
Cc: Russell King <linux@armlinux.org.uk>
Cc: netdev@vger.kernel.org
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/phy.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/phy.h b/include/linux/phy.h
index 3cc52826f18e..bd285950972c 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -568,7 +568,6 @@ struct macsec_ops;
  *      - Bits [31:24] are reserved for defining generic
  *        PHY driver behavior.
  * @irq: IRQ number of the PHY's interrupt (-1 if none)
- * @phy_timer: The timer for handling the state machine
  * @phylink: Pointer to phylink instance for this PHY
  * @sfp_bus_attached: Flag indicating whether the SFP bus has been attached
  * @sfp_bus: SFP bus attached to this PHY's fiber port
-- 
cgit v1.2.3


From 41bc3e8fc1f728085da0ca6dbc1bef4a2ddb543c Mon Sep 17 00:00:00 2001
From: Jamal Hadi Salim <jhs@mojatatu.com>
Date: Sat, 23 Dec 2023 09:01:50 -0500
Subject: net/sched: Remove uapi support for rsvp classifier

commit 265b4da82dbf ("net/sched: Retire rsvp classifier") retired the TC RSVP
classifier.
Remove UAPI for it. Iproute2 will sync by equally removing it from user space.

Reviewed-by: Victor Nogueira <victor@mojatatu.com>
Reviewed-by: Pedro Tammela <pctammela@mojatatu.com>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/pkt_cls.h       | 31 -------------------------------
 tools/include/uapi/linux/pkt_cls.h | 31 -------------------------------
 2 files changed, 62 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index 2fec9b51d28d..fe922b61b99e 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -280,37 +280,6 @@ struct tc_u32_pcnt {
 
 #define TC_U32_MAXDEPTH 8
 
-
-/* RSVP filter */
-
-enum {
-	TCA_RSVP_UNSPEC,
-	TCA_RSVP_CLASSID,
-	TCA_RSVP_DST,
-	TCA_RSVP_SRC,
-	TCA_RSVP_PINFO,
-	TCA_RSVP_POLICE,
-	TCA_RSVP_ACT,
-	__TCA_RSVP_MAX
-};
-
-#define TCA_RSVP_MAX (__TCA_RSVP_MAX - 1 )
-
-struct tc_rsvp_gpi {
-	__u32	key;
-	__u32	mask;
-	int	offset;
-};
-
-struct tc_rsvp_pinfo {
-	struct tc_rsvp_gpi dpi;
-	struct tc_rsvp_gpi spi;
-	__u8	protocol;
-	__u8	tunnelid;
-	__u8	tunnelhdr;
-	__u8	pad;
-};
-
 /* ROUTE filter */
 
 enum {
diff --git a/tools/include/uapi/linux/pkt_cls.h b/tools/include/uapi/linux/pkt_cls.h
index 3faee0199a9b..82eccb6a4994 100644
--- a/tools/include/uapi/linux/pkt_cls.h
+++ b/tools/include/uapi/linux/pkt_cls.h
@@ -204,37 +204,6 @@ struct tc_u32_pcnt {
 
 #define TC_U32_MAXDEPTH 8
 
-
-/* RSVP filter */
-
-enum {
-	TCA_RSVP_UNSPEC,
-	TCA_RSVP_CLASSID,
-	TCA_RSVP_DST,
-	TCA_RSVP_SRC,
-	TCA_RSVP_PINFO,
-	TCA_RSVP_POLICE,
-	TCA_RSVP_ACT,
-	__TCA_RSVP_MAX
-};
-
-#define TCA_RSVP_MAX (__TCA_RSVP_MAX - 1 )
-
-struct tc_rsvp_gpi {
-	__u32	key;
-	__u32	mask;
-	int	offset;
-};
-
-struct tc_rsvp_pinfo {
-	struct tc_rsvp_gpi dpi;
-	struct tc_rsvp_gpi spi;
-	__u8	protocol;
-	__u8	tunnelid;
-	__u8	tunnelhdr;
-	__u8	pad;
-};
-
 /* ROUTE filter */
 
 enum {
-- 
cgit v1.2.3


From 82b2545ed9a465e4c470d2dbbb461522f767c56f Mon Sep 17 00:00:00 2001
From: Jamal Hadi Salim <jhs@mojatatu.com>
Date: Sat, 23 Dec 2023 09:01:51 -0500
Subject: net/sched: Remove uapi support for tcindex classifier

commit 8c710f75256b ("net/sched: Retire tcindex classifier") retired the TC
tcindex classifier.
Remove UAPI for it.  Iproute2 will sync by equally removing it from user space.

Reviewed-by: Victor Nogueira <victor@mojatatu.com>
Reviewed-by: Pedro Tammela <pctammela@mojatatu.com>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/pkt_cls.h       | 16 ----------------
 tools/include/uapi/linux/pkt_cls.h | 16 ----------------
 2 files changed, 32 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index fe922b61b99e..ea277039f89d 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -310,22 +310,6 @@ enum {
 
 #define TCA_FW_MAX (__TCA_FW_MAX - 1)
 
-/* TC index filter */
-
-enum {
-	TCA_TCINDEX_UNSPEC,
-	TCA_TCINDEX_HASH,
-	TCA_TCINDEX_MASK,
-	TCA_TCINDEX_SHIFT,
-	TCA_TCINDEX_FALL_THROUGH,
-	TCA_TCINDEX_CLASSID,
-	TCA_TCINDEX_POLICE,
-	TCA_TCINDEX_ACT,
-	__TCA_TCINDEX_MAX
-};
-
-#define TCA_TCINDEX_MAX     (__TCA_TCINDEX_MAX - 1)
-
 /* Flow filter */
 
 enum {
diff --git a/tools/include/uapi/linux/pkt_cls.h b/tools/include/uapi/linux/pkt_cls.h
index 82eccb6a4994..bd4b227ab4ba 100644
--- a/tools/include/uapi/linux/pkt_cls.h
+++ b/tools/include/uapi/linux/pkt_cls.h
@@ -234,22 +234,6 @@ enum {
 
 #define TCA_FW_MAX (__TCA_FW_MAX - 1)
 
-/* TC index filter */
-
-enum {
-	TCA_TCINDEX_UNSPEC,
-	TCA_TCINDEX_HASH,
-	TCA_TCINDEX_MASK,
-	TCA_TCINDEX_SHIFT,
-	TCA_TCINDEX_FALL_THROUGH,
-	TCA_TCINDEX_CLASSID,
-	TCA_TCINDEX_POLICE,
-	TCA_TCINDEX_ACT,
-	__TCA_TCINDEX_MAX
-};
-
-#define TCA_TCINDEX_MAX     (__TCA_TCINDEX_MAX - 1)
-
 /* Flow filter */
 
 enum {
-- 
cgit v1.2.3


From fe3b739a5472968d8d349522b6816bc4db82bc0f Mon Sep 17 00:00:00 2001
From: Jamal Hadi Salim <jhs@mojatatu.com>
Date: Sat, 23 Dec 2023 09:01:52 -0500
Subject: net/sched: Remove uapi support for dsmark qdisc

Commit bbe77c14ee61 ("net/sched: Retire dsmark qdisc") retired the dsmark
classifier. Remove UAPI support for it.
Iproute2 will sync by equally removing it from user space.

Reviewed-by: Victor Nogueira <victor@mojatatu.com>
Reviewed-by: Pedro Tammela <pctammela@mojatatu.com>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/pkt_sched.h       | 14 --------------
 tools/include/uapi/linux/pkt_sched.h | 14 --------------
 2 files changed, 28 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index f762a10bfb78..1e3a2b9ddf7e 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -557,20 +557,6 @@ enum {
 
 #define TCA_CBQ_MAX	(__TCA_CBQ_MAX - 1)
 
-/* dsmark section */
-
-enum {
-	TCA_DSMARK_UNSPEC,
-	TCA_DSMARK_INDICES,
-	TCA_DSMARK_DEFAULT_INDEX,
-	TCA_DSMARK_SET_TC_INDEX,
-	TCA_DSMARK_MASK,
-	TCA_DSMARK_VALUE,
-	__TCA_DSMARK_MAX,
-};
-
-#define TCA_DSMARK_MAX (__TCA_DSMARK_MAX - 1)
-
 /* ATM  section */
 
 enum {
diff --git a/tools/include/uapi/linux/pkt_sched.h b/tools/include/uapi/linux/pkt_sched.h
index 5c903abc9fa5..0f164f1458fd 100644
--- a/tools/include/uapi/linux/pkt_sched.h
+++ b/tools/include/uapi/linux/pkt_sched.h
@@ -537,20 +537,6 @@ enum {
 
 #define TCA_CBQ_MAX	(__TCA_CBQ_MAX - 1)
 
-/* dsmark section */
-
-enum {
-	TCA_DSMARK_UNSPEC,
-	TCA_DSMARK_INDICES,
-	TCA_DSMARK_DEFAULT_INDEX,
-	TCA_DSMARK_SET_TC_INDEX,
-	TCA_DSMARK_MASK,
-	TCA_DSMARK_VALUE,
-	__TCA_DSMARK_MAX,
-};
-
-#define TCA_DSMARK_MAX (__TCA_DSMARK_MAX - 1)
-
 /* ATM  section */
 
 enum {
-- 
cgit v1.2.3


From 26cc8714fc7f79a806c3d7ffa215b984c384ab4d Mon Sep 17 00:00:00 2001
From: Jamal Hadi Salim <jhs@mojatatu.com>
Date: Sat, 23 Dec 2023 09:01:53 -0500
Subject: net/sched: Remove uapi support for ATM qdisc

Commit fb38306ceb9e ("net/sched: Retire ATM qdisc") retired the ATM qdisc.
Remove UAPI for it. Iproute2 will sync by equally removing it from user space.

Reviewed-by: Victor Nogueira <victor@mojatatu.com>
Reviewed-by: Pedro Tammela <pctammela@mojatatu.com>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/pkt_sched.h       | 15 ---------------
 tools/include/uapi/linux/pkt_sched.h | 15 ---------------
 2 files changed, 30 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index 1e3a2b9ddf7e..28f08acdad52 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -557,21 +557,6 @@ enum {
 
 #define TCA_CBQ_MAX	(__TCA_CBQ_MAX - 1)
 
-/* ATM  section */
-
-enum {
-	TCA_ATM_UNSPEC,
-	TCA_ATM_FD,		/* file/socket descriptor */
-	TCA_ATM_PTR,		/* pointer to descriptor - later */
-	TCA_ATM_HDR,		/* LL header */
-	TCA_ATM_EXCESS,		/* excess traffic class (0 for CLP)  */
-	TCA_ATM_ADDR,		/* PVC address (for output only) */
-	TCA_ATM_STATE,		/* VC state (ATM_VS_*; for output only) */
-	__TCA_ATM_MAX,
-};
-
-#define TCA_ATM_MAX	(__TCA_ATM_MAX - 1)
-
 /* Network emulator */
 
 enum {
diff --git a/tools/include/uapi/linux/pkt_sched.h b/tools/include/uapi/linux/pkt_sched.h
index 0f164f1458fd..fc695429bc59 100644
--- a/tools/include/uapi/linux/pkt_sched.h
+++ b/tools/include/uapi/linux/pkt_sched.h
@@ -537,21 +537,6 @@ enum {
 
 #define TCA_CBQ_MAX	(__TCA_CBQ_MAX - 1)
 
-/* ATM  section */
-
-enum {
-	TCA_ATM_UNSPEC,
-	TCA_ATM_FD,		/* file/socket descriptor */
-	TCA_ATM_PTR,		/* pointer to descriptor - later */
-	TCA_ATM_HDR,		/* LL header */
-	TCA_ATM_EXCESS,		/* excess traffic class (0 for CLP)  */
-	TCA_ATM_ADDR,		/* PVC address (for output only) */
-	TCA_ATM_STATE,		/* VC state (ATM_VS_*; for output only) */
-	__TCA_ATM_MAX,
-};
-
-#define TCA_ATM_MAX	(__TCA_ATM_MAX - 1)
-
 /* Network emulator */
 
 enum {
-- 
cgit v1.2.3


From 33241dca486264193ed68167c8eeae1fb197f3df Mon Sep 17 00:00:00 2001
From: Jamal Hadi Salim <jhs@mojatatu.com>
Date: Sat, 23 Dec 2023 09:01:54 -0500
Subject: net/sched: Remove uapi support for CBQ qdisc

Commit 051d44209842 ("net/sched: Retire CBQ qdisc") retired the CBQ qdisc.
Remove UAPI for it. Iproute2 will sync by equally removing it from user space.

Reviewed-by: Victor Nogueira <victor@mojatatu.com>
Reviewed-by: Pedro Tammela <pctammela@mojatatu.com>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/pkt_sched.h       | 80 ------------------------------------
 tools/include/uapi/linux/pkt_sched.h | 80 ------------------------------------
 2 files changed, 160 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index 28f08acdad52..a3cd0c2dc995 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -477,86 +477,6 @@ enum {
 
 #define TCA_HFSC_MAX (__TCA_HFSC_MAX - 1)
 
-
-/* CBQ section */
-
-#define TC_CBQ_MAXPRIO		8
-#define TC_CBQ_MAXLEVEL		8
-#define TC_CBQ_DEF_EWMA		5
-
-struct tc_cbq_lssopt {
-	unsigned char	change;
-	unsigned char	flags;
-#define TCF_CBQ_LSS_BOUNDED	1
-#define TCF_CBQ_LSS_ISOLATED	2
-	unsigned char  	ewma_log;
-	unsigned char  	level;
-#define TCF_CBQ_LSS_FLAGS	1
-#define TCF_CBQ_LSS_EWMA	2
-#define TCF_CBQ_LSS_MAXIDLE	4
-#define TCF_CBQ_LSS_MINIDLE	8
-#define TCF_CBQ_LSS_OFFTIME	0x10
-#define TCF_CBQ_LSS_AVPKT	0x20
-	__u32		maxidle;
-	__u32		minidle;
-	__u32		offtime;
-	__u32		avpkt;
-};
-
-struct tc_cbq_wrropt {
-	unsigned char	flags;
-	unsigned char	priority;
-	unsigned char	cpriority;
-	unsigned char	__reserved;
-	__u32		allot;
-	__u32		weight;
-};
-
-struct tc_cbq_ovl {
-	unsigned char	strategy;
-#define	TC_CBQ_OVL_CLASSIC	0
-#define	TC_CBQ_OVL_DELAY	1
-#define	TC_CBQ_OVL_LOWPRIO	2
-#define	TC_CBQ_OVL_DROP		3
-#define	TC_CBQ_OVL_RCLASSIC	4
-	unsigned char	priority2;
-	__u16		pad;
-	__u32		penalty;
-};
-
-struct tc_cbq_police {
-	unsigned char	police;
-	unsigned char	__res1;
-	unsigned short	__res2;
-};
-
-struct tc_cbq_fopt {
-	__u32		split;
-	__u32		defmap;
-	__u32		defchange;
-};
-
-struct tc_cbq_xstats {
-	__u32		borrows;
-	__u32		overactions;
-	__s32		avgidle;
-	__s32		undertime;
-};
-
-enum {
-	TCA_CBQ_UNSPEC,
-	TCA_CBQ_LSSOPT,
-	TCA_CBQ_WRROPT,
-	TCA_CBQ_FOPT,
-	TCA_CBQ_OVL_STRATEGY,
-	TCA_CBQ_RATE,
-	TCA_CBQ_RTAB,
-	TCA_CBQ_POLICE,
-	__TCA_CBQ_MAX,
-};
-
-#define TCA_CBQ_MAX	(__TCA_CBQ_MAX - 1)
-
 /* Network emulator */
 
 enum {
diff --git a/tools/include/uapi/linux/pkt_sched.h b/tools/include/uapi/linux/pkt_sched.h
index fc695429bc59..587481a19433 100644
--- a/tools/include/uapi/linux/pkt_sched.h
+++ b/tools/include/uapi/linux/pkt_sched.h
@@ -457,86 +457,6 @@ enum {
 
 #define TCA_HFSC_MAX (__TCA_HFSC_MAX - 1)
 
-
-/* CBQ section */
-
-#define TC_CBQ_MAXPRIO		8
-#define TC_CBQ_MAXLEVEL		8
-#define TC_CBQ_DEF_EWMA		5
-
-struct tc_cbq_lssopt {
-	unsigned char	change;
-	unsigned char	flags;
-#define TCF_CBQ_LSS_BOUNDED	1
-#define TCF_CBQ_LSS_ISOLATED	2
-	unsigned char  	ewma_log;
-	unsigned char  	level;
-#define TCF_CBQ_LSS_FLAGS	1
-#define TCF_CBQ_LSS_EWMA	2
-#define TCF_CBQ_LSS_MAXIDLE	4
-#define TCF_CBQ_LSS_MINIDLE	8
-#define TCF_CBQ_LSS_OFFTIME	0x10
-#define TCF_CBQ_LSS_AVPKT	0x20
-	__u32		maxidle;
-	__u32		minidle;
-	__u32		offtime;
-	__u32		avpkt;
-};
-
-struct tc_cbq_wrropt {
-	unsigned char	flags;
-	unsigned char	priority;
-	unsigned char	cpriority;
-	unsigned char	__reserved;
-	__u32		allot;
-	__u32		weight;
-};
-
-struct tc_cbq_ovl {
-	unsigned char	strategy;
-#define	TC_CBQ_OVL_CLASSIC	0
-#define	TC_CBQ_OVL_DELAY	1
-#define	TC_CBQ_OVL_LOWPRIO	2
-#define	TC_CBQ_OVL_DROP		3
-#define	TC_CBQ_OVL_RCLASSIC	4
-	unsigned char	priority2;
-	__u16		pad;
-	__u32		penalty;
-};
-
-struct tc_cbq_police {
-	unsigned char	police;
-	unsigned char	__res1;
-	unsigned short	__res2;
-};
-
-struct tc_cbq_fopt {
-	__u32		split;
-	__u32		defmap;
-	__u32		defchange;
-};
-
-struct tc_cbq_xstats {
-	__u32		borrows;
-	__u32		overactions;
-	__s32		avgidle;
-	__s32		undertime;
-};
-
-enum {
-	TCA_CBQ_UNSPEC,
-	TCA_CBQ_LSSOPT,
-	TCA_CBQ_WRROPT,
-	TCA_CBQ_FOPT,
-	TCA_CBQ_OVL_STRATEGY,
-	TCA_CBQ_RATE,
-	TCA_CBQ_RTAB,
-	TCA_CBQ_POLICE,
-	__TCA_CBQ_MAX,
-};
-
-#define TCA_CBQ_MAX	(__TCA_CBQ_MAX - 1)
-
 /* Network emulator */
 
 enum {
-- 
cgit v1.2.3


From 76f5f55c45b906710c9565a7e68c8d782c46b394 Mon Sep 17 00:00:00 2001
From: Gergo Koteles <soyer@irl.hu>
Date: Sat, 30 Dec 2023 01:09:42 +0100
Subject: ALSA: hda/tas2781: add ptrs to calibration functions

Make calibration functions configurable to support different calibration
data storage modes.

Signed-off-by: Gergo Koteles <soyer@irl.hu>
Link: https://lore.kernel.org/r/5859c77ffef752b8a9784713b412d815d7e2688c.1703891777.git.soyer@irl.hu
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/tas2781.h           |  5 +++++
 sound/pci/hda/tas2781_hda_i2c.c   | 25 +++++++++++--------------
 sound/soc/codecs/tas2781-comlib.c | 15 +++++++++++++++
 3 files changed, 31 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/sound/tas2781.h b/include/sound/tas2781.h
index a6c808b22318..e17ceab4fead 100644
--- a/include/sound/tas2781.h
+++ b/include/sound/tas2781.h
@@ -131,6 +131,9 @@ struct tasdevice_priv {
 		const struct firmware *fmw, int offset);
 	int (*tasdevice_load_block)(struct tasdevice_priv *tas_priv,
 		struct tasdev_blk *block);
+
+	int (*save_calibration)(struct tasdevice_priv *tas_priv);
+	void (*apply_calibration)(struct tasdevice_priv *tas_priv);
 };
 
 void tas2781_reset(struct tasdevice_priv *tas_dev);
@@ -139,6 +142,8 @@ int tascodec_init(struct tasdevice_priv *tas_priv, void *codec,
 struct tasdevice_priv *tasdevice_kzalloc(struct i2c_client *i2c);
 int tasdevice_init(struct tasdevice_priv *tas_priv);
 void tasdevice_remove(struct tasdevice_priv *tas_priv);
+int tasdevice_save_calibration(struct tasdevice_priv *tas_priv);
+void tasdevice_apply_calibration(struct tasdevice_priv *tas_priv);
 int tasdevice_dev_read(struct tasdevice_priv *tas_priv,
 	unsigned short chn, unsigned int reg, unsigned int *value);
 int tasdevice_dev_write(struct tasdevice_priv *tas_priv,
diff --git a/sound/pci/hda/tas2781_hda_i2c.c b/sound/pci/hda/tas2781_hda_i2c.c
index c8523df4105f..4b639120c981 100644
--- a/sound/pci/hda/tas2781_hda_i2c.c
+++ b/sound/pci/hda/tas2781_hda_i2c.c
@@ -479,7 +479,7 @@ static int tas2781_save_calibration(struct tasdevice_priv *tas_priv)
 		dev_dbg(tas_priv->dev, "%4ld-%2d-%2d, %2d:%2d:%2d\n",
 			tm->tm_year, tm->tm_mon, tm->tm_mday,
 			tm->tm_hour, tm->tm_min, tm->tm_sec);
-		tas2781_apply_calib(tas_priv);
+		tasdevice_apply_calibration(tas_priv);
 	} else
 		tas_priv->cali_data.total_sz = 0;
 
@@ -582,7 +582,7 @@ static void tasdev_fw_ready(const struct firmware *fmw, void *context)
 	/* If calibrated data occurs error, dsp will still works with default
 	 * calibrated data inside algo.
 	 */
-	tas2781_save_calibration(tas_priv);
+	tasdevice_save_calibration(tas_priv);
 
 	tasdevice_tuning_switch(tas_hda->priv, 0);
 
@@ -685,10 +685,6 @@ static int tas2781_hda_i2c_probe(struct i2c_client *clt)
 	const char *device_name;
 	int ret;
 
-	if (strstr(dev_name(&clt->dev), "TIAS2781"))
-		device_name = "TIAS2781";
-	else
-		return -ENODEV;
 
 	tas_hda = devm_kzalloc(&clt->dev, sizeof(*tas_hda), GFP_KERNEL);
 	if (!tas_hda)
@@ -701,6 +697,13 @@ static int tas2781_hda_i2c_probe(struct i2c_client *clt)
 	if (!tas_hda->priv)
 		return -ENOMEM;
 
+	if (strstr(dev_name(&clt->dev), "TIAS2781")) {
+		device_name = "TIAS2781";
+		tas_hda->priv->save_calibration = tas2781_save_calibration;
+		tas_hda->priv->apply_calibration = tas2781_apply_calib;
+	} else
+		return -ENODEV;
+
 	tas_hda->priv->irq_info.irq = clt->irq;
 	ret = tas2781_read_acpi(tas_hda->priv, device_name);
 	if (ret)
@@ -767,8 +770,6 @@ static int tas2781_runtime_suspend(struct device *dev)
 static int tas2781_runtime_resume(struct device *dev)
 {
 	struct tas2781_hda *tas_hda = dev_get_drvdata(dev);
-	unsigned long calib_data_sz =
-		tas_hda->priv->ndev * TASDEVICE_SPEAKER_CALIBRATION_SIZE;
 
 	dev_dbg(tas_hda->dev, "Runtime Resume\n");
 
@@ -779,8 +780,7 @@ static int tas2781_runtime_resume(struct device *dev)
 	/* If calibrated data occurs error, dsp will still works with default
 	 * calibrated data inside algo.
 	 */
-	if (tas_hda->priv->cali_data.total_sz > calib_data_sz)
-		tas2781_apply_calib(tas_hda->priv);
+	tasdevice_apply_calibration(tas_hda->priv);
 
 	mutex_unlock(&tas_hda->priv->codec_lock);
 
@@ -811,8 +811,6 @@ static int tas2781_system_suspend(struct device *dev)
 static int tas2781_system_resume(struct device *dev)
 {
 	struct tas2781_hda *tas_hda = dev_get_drvdata(dev);
-	unsigned long calib_data_sz =
-		tas_hda->priv->ndev * TASDEVICE_SPEAKER_CALIBRATION_SIZE;
 	int i, ret;
 
 	dev_info(tas_hda->priv->dev, "System Resume\n");
@@ -834,8 +832,7 @@ static int tas2781_system_resume(struct device *dev)
 	/* If calibrated data occurs error, dsp will still work with default
 	 * calibrated data inside algo.
 	 */
-	if (tas_hda->priv->cali_data.total_sz > calib_data_sz)
-		tas2781_apply_calib(tas_hda->priv);
+	tasdevice_apply_calibration(tas_hda->priv);
 	mutex_unlock(&tas_hda->priv->codec_lock);
 
 	return 0;
diff --git a/sound/soc/codecs/tas2781-comlib.c b/sound/soc/codecs/tas2781-comlib.c
index 00e35169ae49..b7e56ceb1acf 100644
--- a/sound/soc/codecs/tas2781-comlib.c
+++ b/sound/soc/codecs/tas2781-comlib.c
@@ -412,6 +412,21 @@ void tasdevice_remove(struct tasdevice_priv *tas_priv)
 }
 EXPORT_SYMBOL_GPL(tasdevice_remove);
 
+int tasdevice_save_calibration(struct tasdevice_priv *tas_priv)
+{
+	if (tas_priv->save_calibration)
+		return tas_priv->save_calibration(tas_priv);
+	return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(tasdevice_save_calibration);
+
+void tasdevice_apply_calibration(struct tasdevice_priv *tas_priv)
+{
+	if (tas_priv->apply_calibration && tas_priv->cali_data.total_sz)
+		tas_priv->apply_calibration(tas_priv);
+}
+EXPORT_SYMBOL_GPL(tasdevice_apply_calibration);
+
 static int tasdevice_clamp(int val, int max, unsigned int invert)
 {
 	if (val > max)
-- 
cgit v1.2.3


From c021ca729fe870d25a4798491c383c89b3091650 Mon Sep 17 00:00:00 2001
From: Gergo Koteles <soyer@irl.hu>
Date: Sat, 30 Dec 2023 01:09:43 +0100
Subject: ALSA: hda/tas2781: add configurable global i2c address

Make the global i2c address configurable to support compatible amplifiers
with different global i2c address.

Signed-off-by: Gergo Koteles <soyer@irl.hu>
Link: https://lore.kernel.org/r/a252f1efeed5049f027f01e699c9e10e1e05bf9e.1703891777.git.soyer@irl.hu
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/tas2781.h         | 2 ++
 sound/pci/hda/tas2781_hda_i2c.c | 3 ++-
 2 files changed, 4 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/sound/tas2781.h b/include/sound/tas2781.h
index e17ceab4fead..dde9f8120d4c 100644
--- a/include/sound/tas2781.h
+++ b/include/sound/tas2781.h
@@ -121,6 +121,8 @@ struct tasdevice_priv {
 	bool force_fwload_status;
 	bool playback_started;
 	bool isacpi;
+	unsigned int global_addr;
+
 	int (*fw_parse_variable_header)(struct tasdevice_priv *tas_priv,
 		const struct firmware *fmw, int offset);
 	int (*fw_parse_program_data)(struct tasdevice_priv *tas_priv,
diff --git a/sound/pci/hda/tas2781_hda_i2c.c b/sound/pci/hda/tas2781_hda_i2c.c
index 4b639120c981..503be3fbce56 100644
--- a/sound/pci/hda/tas2781_hda_i2c.c
+++ b/sound/pci/hda/tas2781_hda_i2c.c
@@ -81,7 +81,7 @@ static int tas2781_get_i2c_res(struct acpi_resource *ares, void *data)
 
 	if (i2c_acpi_get_i2c_resource(ares, &sb)) {
 		if (tas_priv->ndev < TASDEVICE_MAX_CHANNELS &&
-			sb->slave_address != TAS2781_GLOBAL_ADDR) {
+			sb->slave_address != tas_priv->global_addr) {
 			tas_priv->tasdevice[tas_priv->ndev].dev_addr =
 				(unsigned int)sb->slave_address;
 			tas_priv->ndev++;
@@ -701,6 +701,7 @@ static int tas2781_hda_i2c_probe(struct i2c_client *clt)
 		device_name = "TIAS2781";
 		tas_hda->priv->save_calibration = tas2781_save_calibration;
 		tas_hda->priv->apply_calibration = tas2781_apply_calib;
+		tas_hda->priv->global_addr = TAS2781_GLOBAL_ADDR;
 	} else
 		return -ENODEV;
 
-- 
cgit v1.2.3


From c3ca4458cc2f719b1652abaa8d2fbf7f3d4311cb Mon Sep 17 00:00:00 2001
From: Gergo Koteles <soyer@irl.hu>
Date: Sat, 30 Dec 2023 01:09:44 +0100
Subject: ALSA: hda/tas2781: add TAS2563 support for 14ARB7

The INT8866 belongs to the Lenovo Yoga 7 Gen 7 AMD 14ARB7
laptop. It has two TAS2563 amplifier. Add the PNP ID
and calibration functions to handle them.

ACPI excerpt:

Scope (_SB.I2CD)
{
    Device (TAS)
    {
        Name (_HID, "INT8866")  // _HID: Hardware ID
        Name (_UID, Zero)  // _UID: Unique ID
        Method (_CRS, 0, NotSerialized)  // _CRS: Current Resource Settings
        {
            Name (RBUF, ResourceTemplate ()
            {
                I2cSerialBusV2 (0x004C, ControllerInitiated, 0x00061A80,
                    AddressingMode7Bit, "\\_SB.I2CD",
                    0x00, ResourceConsumer, , Exclusive,
                    )
                I2cSerialBusV2 (0x004D, ControllerInitiated, 0x00061A80,
                    AddressingMode7Bit, "\\_SB.I2CD",
                    0x00, ResourceConsumer, , Exclusive,
                    )
                GpioInt (Edge, ActiveLow, SharedAndWake, PullNone, 0x0000,
                    "\\_SB.GPIO", 0x00, ResourceConsumer, ,
                    )
                    {   // Pin list
                        0x0020
                    }
             })
             Return (RBUF) /* \_SB_.I2CD.TAS_._CRS.RBUF */
        }

        Method (_STA, 0, NotSerialized)  // _STA: Status
        {
            Return (0x0F)
        }
    }
}

Signed-off-by: Gergo Koteles <soyer@irl.hu>
Link: https://lore.kernel.org/r/3b8d4c602e1a46922f53bc9afc8b705d55aa4872.1703891777.git.soyer@irl.hu
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/tas2781.h         |  1 +
 sound/pci/hda/tas2781_hda_i2c.c | 87 +++++++++++++++++++++++++++++++++++++++++
 2 files changed, 88 insertions(+)

(limited to 'include')

diff --git a/include/sound/tas2781.h b/include/sound/tas2781.h
index dde9f8120d4c..0a86ab8d47b9 100644
--- a/include/sound/tas2781.h
+++ b/include/sound/tas2781.h
@@ -22,6 +22,7 @@
 #define TAS2781_DRV_VER			1
 #define SMARTAMP_MODULE_NAME		"tas2781"
 #define TAS2781_GLOBAL_ADDR	0x40
+#define TAS2563_GLOBAL_ADDR	0x48
 #define TASDEVICE_RATES			(SNDRV_PCM_RATE_44100 |\
 	SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_96000 |\
 	SNDRV_PCM_RATE_88200)
diff --git a/sound/pci/hda/tas2781_hda_i2c.c b/sound/pci/hda/tas2781_hda_i2c.c
index 503be3fbce56..4805cf0b6480 100644
--- a/sound/pci/hda/tas2781_hda_i2c.c
+++ b/sound/pci/hda/tas2781_hda_i2c.c
@@ -65,6 +65,24 @@ enum calib_data {
 	CALIB_MAX
 };
 
+#define TAS2563_MAX_CHANNELS	4
+
+#define TAS2563_CAL_POWER	TASDEVICE_REG(0, 0x0d, 0x3c)
+#define TAS2563_CAL_R0		TASDEVICE_REG(0, 0x0f, 0x34)
+#define TAS2563_CAL_INVR0	TASDEVICE_REG(0, 0x0f, 0x40)
+#define TAS2563_CAL_R0_LOW	TASDEVICE_REG(0, 0x0f, 0x48)
+#define TAS2563_CAL_TLIM	TASDEVICE_REG(0, 0x10, 0x14)
+#define TAS2563_CAL_N		5
+#define TAS2563_CAL_DATA_SIZE	4
+#define TAS2563_CAL_CH_SIZE	20
+#define TAS2563_CAL_ARRAY_SIZE	80
+
+static unsigned int cal_regs[TAS2563_CAL_N] = {
+	TAS2563_CAL_POWER, TAS2563_CAL_R0, TAS2563_CAL_INVR0,
+	TAS2563_CAL_R0_LOW, TAS2563_CAL_TLIM,
+};
+
+
 struct tas2781_hda {
 	struct device *dev;
 	struct tasdevice_priv *priv;
@@ -404,6 +422,69 @@ static const struct snd_kcontrol_new tas2781_dsp_conf_ctrl = {
 	.put = tasdevice_config_put,
 };
 
+static void tas2563_apply_calib(struct tasdevice_priv *tas_priv)
+{
+	unsigned int data;
+	int offset = 0;
+	int ret;
+
+	for (int i = 0; i < tas_priv->ndev; i++) {
+		for (int j = 0; j < TAS2563_CAL_N; ++j) {
+			data = cpu_to_be32(
+				*(uint32_t *)&tas_priv->cali_data.data[offset]);
+			ret = tasdevice_dev_bulk_write(tas_priv, i, cal_regs[j],
+				(unsigned char *)&data, TAS2563_CAL_DATA_SIZE);
+			if (ret)
+				dev_err(tas_priv->dev,
+					"Error writing calib regs\n");
+			offset += TAS2563_CAL_DATA_SIZE;
+		}
+	}
+}
+
+static int tas2563_save_calibration(struct tasdevice_priv *tas_priv)
+{
+	static efi_guid_t efi_guid = EFI_GUID(0x1f52d2a1, 0xbb3a, 0x457d, 0xbc,
+		0x09, 0x43, 0xa3, 0xf4, 0x31, 0x0a, 0x92);
+
+	static efi_char16_t *efi_vars[TAS2563_MAX_CHANNELS][TAS2563_CAL_N] = {
+		{ L"Power_1", L"R0_1", L"InvR0_1", L"R0_Low_1", L"TLim_1" },
+		{ L"Power_2", L"R0_2", L"InvR0_2", L"R0_Low_2", L"TLim_2" },
+		{ L"Power_3", L"R0_3", L"InvR0_3", L"R0_Low_3", L"TLim_3" },
+		{ L"Power_4", L"R0_4", L"InvR0_4", L"R0_Low_4", L"TLim_4" },
+	};
+
+	unsigned long max_size = TAS2563_CAL_DATA_SIZE;
+	unsigned int offset = 0;
+	efi_status_t status;
+	unsigned int attr;
+
+	tas_priv->cali_data.data = devm_kzalloc(tas_priv->dev,
+			TAS2563_CAL_ARRAY_SIZE, GFP_KERNEL);
+	if (!tas_priv->cali_data.data)
+		return -ENOMEM;
+
+	for (int i = 0; i < tas_priv->ndev; ++i) {
+		for (int j = 0; j < TAS2563_CAL_N; ++j) {
+			status = efi.get_variable(efi_vars[i][j],
+				&efi_guid, &attr, &max_size,
+				&tas_priv->cali_data.data[offset]);
+			if (status != EFI_SUCCESS ||
+				max_size != TAS2563_CAL_DATA_SIZE) {
+				dev_warn(tas_priv->dev,
+				"Calibration data read failed %ld\n", status);
+				return -EINVAL;
+			}
+			offset += TAS2563_CAL_DATA_SIZE;
+		}
+	}
+
+	tas_priv->cali_data.total_sz = offset;
+	tasdevice_apply_calibration(tas_priv);
+
+	return 0;
+}
+
 static void tas2781_apply_calib(struct tasdevice_priv *tas_priv)
 {
 	static const unsigned char page_array[CALIB_MAX] = {
@@ -702,6 +783,11 @@ static int tas2781_hda_i2c_probe(struct i2c_client *clt)
 		tas_hda->priv->save_calibration = tas2781_save_calibration;
 		tas_hda->priv->apply_calibration = tas2781_apply_calib;
 		tas_hda->priv->global_addr = TAS2781_GLOBAL_ADDR;
+	} else if (strstr(dev_name(&clt->dev), "INT8866")) {
+		device_name = "INT8866";
+		tas_hda->priv->save_calibration = tas2563_save_calibration;
+		tas_hda->priv->apply_calibration = tas2563_apply_calib;
+		tas_hda->priv->global_addr = TAS2563_GLOBAL_ADDR;
 	} else
 		return -ENODEV;
 
@@ -851,6 +937,7 @@ static const struct i2c_device_id tas2781_hda_i2c_id[] = {
 
 static const struct acpi_device_id tas2781_acpi_hda_match[] = {
 	{"TIAS2781", 0 },
+	{"INT8866", 0 },
 	{}
 };
 MODULE_DEVICE_TABLE(acpi, tas2781_acpi_hda_match);
-- 
cgit v1.2.3


From e4df56ad0bf3506c5189abb9be83f3bea05a4c4f Mon Sep 17 00:00:00 2001
From: Lin Gui <lin.gui@mediatek.com>
Date: Tue, 19 Dec 2023 07:05:32 +0800
Subject: mmc: core: Add wp_grp_size sysfs node

The eMMC card can be set into write-protected mode to prevent data from
being accidentally modified or deleted. Wp_grp_size (Write Protect Group
Size) refers to an attribute of the eMMC card, used to manage write
protection and is the CSD register [36:32] of the eMMC device. Wp_grp_size
(Write Protect Group Size) indicates how many eMMC blocks are contained in
each write protection group on the eMMC card.

To allow userspace easy access of the CSD register bits, let's add sysfs
node "wp_grp_size".

Signed-off-by: Lin Gui <lin.gui@mediatek.com>
Signed-off-by: Bo Ye <bo.ye@mediatek.com>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Link: https://lore.kernel.org/r/20231218230532.82427-1-bo.ye@mediatek.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/core/mmc.c   | 16 +++++++++++++++-
 include/linux/mmc/card.h |  2 ++
 2 files changed, 17 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 7b996db570c9..adf7b70cf1b6 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -136,6 +136,17 @@ static void mmc_set_erase_size(struct mmc_card *card)
 	mmc_init_erase(card);
 }
 
+
+static void mmc_set_wp_grp_size(struct mmc_card *card)
+{
+	if (card->ext_csd.erase_group_def & 1)
+		card->wp_grp_size = card->ext_csd.hc_erase_size *
+			card->ext_csd.raw_hc_erase_gap_size;
+	else
+		card->wp_grp_size = card->csd.erase_size *
+			(card->csd.wp_grp_size + 1);
+}
+
 /*
  * Given a 128-bit response, decode to our card CSD structure.
  */
@@ -186,6 +197,7 @@ static int mmc_decode_csd(struct mmc_card *card)
 		b = UNSTUFF_BITS(resp, 37, 5);
 		csd->erase_size = (a + 1) * (b + 1);
 		csd->erase_size <<= csd->write_blkbits - 9;
+		csd->wp_grp_size = UNSTUFF_BITS(resp, 32, 5);
 	}
 
 	return 0;
@@ -785,6 +797,7 @@ MMC_DEV_ATTR(csd, "%08x%08x%08x%08x\n", card->raw_csd[0], card->raw_csd[1],
 MMC_DEV_ATTR(date, "%02d/%04d\n", card->cid.month, card->cid.year);
 MMC_DEV_ATTR(erase_size, "%u\n", card->erase_size << 9);
 MMC_DEV_ATTR(preferred_erase_size, "%u\n", card->pref_erase << 9);
+MMC_DEV_ATTR(wp_grp_size, "%u\n", card->wp_grp_size << 9);
 MMC_DEV_ATTR(ffu_capable, "%d\n", card->ext_csd.ffu_capable);
 MMC_DEV_ATTR(hwrev, "0x%x\n", card->cid.hwrev);
 MMC_DEV_ATTR(manfid, "0x%06x\n", card->cid.manfid);
@@ -845,6 +858,7 @@ static struct attribute *mmc_std_attrs[] = {
 	&dev_attr_date.attr,
 	&dev_attr_erase_size.attr,
 	&dev_attr_preferred_erase_size.attr,
+	&dev_attr_wp_grp_size.attr,
 	&dev_attr_fwrev.attr,
 	&dev_attr_ffu_capable.attr,
 	&dev_attr_hwrev.attr,
@@ -1759,7 +1773,7 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr,
 			mmc_set_erase_size(card);
 		}
 	}
-
+	mmc_set_wp_grp_size(card);
 	/*
 	 * Ensure eMMC user default partition is enabled
 	 */
diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h
index 47eeb122524c..f34407cc2788 100644
--- a/include/linux/mmc/card.h
+++ b/include/linux/mmc/card.h
@@ -32,6 +32,7 @@ struct mmc_csd {
 	unsigned int		r2w_factor;
 	unsigned int		max_dtr;
 	unsigned int		erase_size;		/* In sectors */
+	unsigned int		wp_grp_size;
 	unsigned int		read_blkbits;
 	unsigned int		write_blkbits;
 	unsigned int		capacity;
@@ -303,6 +304,7 @@ struct mmc_card {
 	unsigned int		eg_boundary;	/* don't cross erase-group boundaries */
 	unsigned int		erase_arg;	/* erase / trim / discard */
  	u8			erased_byte;	/* value of erased bytes */
+	unsigned int		wp_grp_size;	/* write group size in sectors */
 
 	u32			raw_cid[4];	/* raw card CID */
 	u32			raw_csd[4];	/* raw card CSD */
-- 
cgit v1.2.3


From 3e64db35bc37edbe9e37aaa987df92cde12ddb6c Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 2 Jan 2024 14:23:34 -0800
Subject: Revert "net: mdio: get/put device node during (un)registration"

This reverts commit cff9c565e65f3622e8dc1dcc21c1520a083dff35.

Revert based on feedback from Russell.

Link: https://lore.kernel.org/all/ZZPtUIRerqTI2%2Fyh@shell.armlinux.org.uk/
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/mdio/of_mdio.c | 12 +-----------
 drivers/net/phy/mdio_bus.c |  3 ---
 include/linux/phy.h        |  3 ---
 3 files changed, 1 insertion(+), 17 deletions(-)

(limited to 'include')

diff --git a/drivers/net/mdio/of_mdio.c b/drivers/net/mdio/of_mdio.c
index 9b6cab6154e0..64ebcb6d235c 100644
--- a/drivers/net/mdio/of_mdio.c
+++ b/drivers/net/mdio/of_mdio.c
@@ -139,11 +139,6 @@ bool of_mdiobus_child_is_phy(struct device_node *child)
 }
 EXPORT_SYMBOL(of_mdiobus_child_is_phy);
 
-static void __of_mdiobus_unregister_callback(struct mii_bus *mdio)
-{
-	of_node_put(mdio->dev.of_node);
-}
-
 /**
  * __of_mdiobus_register - Register mii_bus and create PHYs from the device tree
  * @mdio: pointer to mii_bus structure
@@ -171,8 +166,6 @@ int __of_mdiobus_register(struct mii_bus *mdio, struct device_node *np,
 	 * the device tree are populated after the bus has been registered */
 	mdio->phy_mask = ~0;
 
-	mdio->__unregister_callback = __of_mdiobus_unregister_callback;
-	of_node_get(np);
 	device_set_node(&mdio->dev, of_fwnode_handle(np));
 
 	/* Get bus level PHY reset GPIO details */
@@ -184,7 +177,7 @@ int __of_mdiobus_register(struct mii_bus *mdio, struct device_node *np,
 	/* Register the MDIO bus */
 	rc = __mdiobus_register(mdio, owner);
 	if (rc)
-		goto put_node;
+		return rc;
 
 	/* Loop over the child nodes and register a phy_device for each phy */
 	for_each_available_child_of_node(np, child) {
@@ -244,9 +237,6 @@ int __of_mdiobus_register(struct mii_bus *mdio, struct device_node *np,
 unregister:
 	of_node_put(child);
 	mdiobus_unregister(mdio);
-
-put_node:
-	of_node_put(np);
 	return rc;
 }
 EXPORT_SYMBOL(__of_mdiobus_register);
diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index 4a30757c4ff8..6cf73c15635b 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -787,9 +787,6 @@ void mdiobus_unregister(struct mii_bus *bus)
 		gpiod_set_value_cansleep(bus->reset_gpiod, 1);
 
 	device_del(&bus->dev);
-
-	if (bus->__unregister_callback)
-		bus->__unregister_callback(bus);
 }
 EXPORT_SYMBOL(mdiobus_unregister);
 
diff --git a/include/linux/phy.h b/include/linux/phy.h
index ac22b8e28a85..6cb9d843aee9 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -434,9 +434,6 @@ struct mii_bus {
 
 	/** @shared: shared state across different PHYs */
 	struct phy_package_shared *shared[PHY_MAX_ADDR];
-
-	/** @__unregister_callback: called at the last step of unregistration */
-	void (*__unregister_callback)(struct mii_bus *bus);
 };
 #define to_mii_bus(d) container_of(d, struct mii_bus, dev)
 
-- 
cgit v1.2.3


From db02e176f597a14eb696141ffa008c2429453a15 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Wed, 6 Dec 2023 16:42:31 -0600
Subject: PCI/AER: Use explicit register sizes for struct members

aer_irq() reads the AER Root Error Status and Error Source Identification
(PCI_ERR_ROOT_STATUS and PCI_ERR_ROOT_ERR_SRC) registers directly into
struct aer_err_source.  Both registers are 32 bits, so declare the members
explicitly as "u32" instead of "unsigned int".

Similarly, aer_get_device_error_info() reads the AER Header Log
(PCI_ERR_HEADER_LOG) registers, which are also 32 bits, into struct
aer_header_log_regs.  Declare those members as "u32" as well.

No functional changes intended.

Link: https://lore.kernel.org/r/20231206224231.732765-4-helgaas@kernel.org
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/pci/pcie/aer.c | 4 ++--
 include/linux/aer.h    | 8 ++++----
 2 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index 412b00bdf918..05fc30bb5134 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -41,8 +41,8 @@
 #define AER_MAX_TYPEOF_UNCOR_ERRS	27	/* as per PCI_ERR_UNCOR_STATUS*/
 
 struct aer_err_source {
-	unsigned int status;
-	unsigned int id;
+	u32 status;			/* PCI_ERR_ROOT_STATUS */
+	u32 id;				/* PCI_ERR_ROOT_ERR_SRC */
 };
 
 struct aer_rpc {
diff --git a/include/linux/aer.h b/include/linux/aer.h
index f6ea2f57d808..ae0fae70d4bd 100644
--- a/include/linux/aer.h
+++ b/include/linux/aer.h
@@ -19,10 +19,10 @@
 struct pci_dev;
 
 struct aer_header_log_regs {
-	unsigned int dw0;
-	unsigned int dw1;
-	unsigned int dw2;
-	unsigned int dw3;
+	u32 dw0;
+	u32 dw1;
+	u32 dw2;
+	u32 dw3;
 };
 
 struct aer_capability_regs {
-- 
cgit v1.2.3


From 8dc4c410006531ddad981ca9578f83cb93860819 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Tue, 19 Dec 2023 13:02:05 +0200
Subject: xsk: make struct xsk_cb_desc available outside CONFIG_XDP_SOCKETS

The ice driver fails to build when CONFIG_XDP_SOCKETS is disabled.

drivers/net/ethernet/intel/ice/ice_base.c:533:21: error:
variable has incomplete type 'struct xsk_cb_desc'
        struct xsk_cb_desc desc = {};
                           ^
include/net/xsk_buff_pool.h:15:8: note:
forward declaration of 'struct xsk_cb_desc'
struct xsk_cb_desc;
       ^

Fixes: d68d707dcbbf ("ice: Support XDP hints in AF_XDP ZC mode")
Closes: https://lore.kernel.org/netdev/8b76dad3-8847-475b-aa17-613c9c978f7a@infradead.org/
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Acked-by: Larysa Zaremba <larysa.zaremba@intel.com>
Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Tested-by: Randy Dunlap <rdunlap@infradead.org> # build-tested
Link: https://lore.kernel.org/r/20231219110205.1289506-1-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/xdp_sock_drv.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index b62bb8525a5f..526c1e7f505e 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -12,14 +12,14 @@
 #define XDP_UMEM_MIN_CHUNK_SHIFT 11
 #define XDP_UMEM_MIN_CHUNK_SIZE (1 << XDP_UMEM_MIN_CHUNK_SHIFT)
 
-#ifdef CONFIG_XDP_SOCKETS
-
 struct xsk_cb_desc {
 	void *src;
 	u8 off;
 	u8 bytes;
 };
 
+#ifdef CONFIG_XDP_SOCKETS
+
 void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries);
 bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc);
 u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 max);
-- 
cgit v1.2.3


From 0dd415d155050f5c1cf360b97f905d42d44f33ed Mon Sep 17 00:00:00 2001
From: Ahmed Zaki <ahmed.zaki@intel.com>
Date: Thu, 21 Dec 2023 11:42:35 -0700
Subject: net: ethtool: add a NO_CHANGE uAPI for new RXFH's input_xfrm

Add a NO_CHANGE uAPI value for the new RXFH/RSS input_xfrm uAPI field.
This needed so that user-space can set other RSS values (hkey or indir
table) without affecting input_xfrm.

Should have been part of [1].

Link: https://lore.kernel.org/netdev/20231213003321.605376-1-ahmed.zaki@intel.com/ [1]
Fixes: 13e59344fb9d ("net: ethtool: add support for symmetric-xor RSS hash")
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
Link: https://lore.kernel.org/r/20231221184235.9192-3-ahmed.zaki@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/uapi/linux/ethtool.h | 1 +
 net/ethtool/ioctl.c          | 6 ++++--
 2 files changed, 5 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 60801df9d8c0..01ba529dbb6d 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -2002,6 +2002,7 @@ static inline int ethtool_validate_duplex(__u8 duplex)
  * be exploited to reduce the RSS queue spread.
  */
 #define	RXH_XFRM_SYM_XOR	(1 << 0)
+#define	RXH_XFRM_NO_CHANGE	0xff
 
 /* L2-L4 network traffic flow types */
 #define	TCP_V4_FLOW	0x01	/* hash or spec (tcp_ip4_spec) */
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 9adc240b8f0e..4c4f46dfc251 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -1304,14 +1304,16 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 		return -EOPNOTSUPP;
 
 	/* If either indir, hash key or function is valid, proceed further.
-	 * Must request at least one change: indir size, hash key or function.
+	 * Must request at least one change: indir size, hash key, function
+	 * or input transformation.
 	 */
 	if ((rxfh.indir_size &&
 	     rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE &&
 	     rxfh.indir_size != dev_indir_size) ||
 	    (rxfh.key_size && (rxfh.key_size != dev_key_size)) ||
 	    (rxfh.indir_size == ETH_RXFH_INDIR_NO_CHANGE &&
-	     rxfh.key_size == 0 && rxfh.hfunc == ETH_RSS_HASH_NO_CHANGE))
+	     rxfh.key_size == 0 && rxfh.hfunc == ETH_RSS_HASH_NO_CHANGE &&
+	     rxfh.input_xfrm == RXH_XFRM_NO_CHANGE))
 		return -EINVAL;
 
 	if (rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE)
-- 
cgit v1.2.3


From 7d4b5d7a37bdd63a5a3371b988744b060d5bb86f Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Wed, 27 Dec 2023 21:38:23 +0100
Subject: async: Introduce async_schedule_dev_nocall()

In preparation for subsequent changes, introduce a specialized variant
of async_schedule_dev() that will not invoke the argument function
synchronously when it cannot be scheduled for asynchronous execution.

The new function, async_schedule_dev_nocall(), will be used for fixing
possible deadlocks in the system-wide power management core code.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com> for the series.
Tested-by: Youngmin Nam <youngmin.nam@samsung.com>
Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 include/linux/async.h |  2 ++
 kernel/async.c        | 29 +++++++++++++++++++++++++++++
 2 files changed, 31 insertions(+)

(limited to 'include')

diff --git a/include/linux/async.h b/include/linux/async.h
index cce4ad31e8fc..33c9ff4afb49 100644
--- a/include/linux/async.h
+++ b/include/linux/async.h
@@ -90,6 +90,8 @@ async_schedule_dev(async_func_t func, struct device *dev)
 	return async_schedule_node(func, dev, dev_to_node(dev));
 }
 
+bool async_schedule_dev_nocall(async_func_t func, struct device *dev);
+
 /**
  * async_schedule_dev_domain - A device specific version of async_schedule_domain
  * @func: function to execute asynchronously
diff --git a/kernel/async.c b/kernel/async.c
index cffe6b4cff9f..673bba6bdf3a 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -243,6 +243,35 @@ async_cookie_t async_schedule_node(async_func_t func, void *data, int node)
 }
 EXPORT_SYMBOL_GPL(async_schedule_node);
 
+/**
+ * async_schedule_dev_nocall - A simplified variant of async_schedule_dev()
+ * @func: function to execute asynchronously
+ * @dev: device argument to be passed to function
+ *
+ * @dev is used as both the argument for the function and to provide NUMA
+ * context for where to run the function.
+ *
+ * If the asynchronous execution of @func is scheduled successfully, return
+ * true. Otherwise, do nothing and return false, unlike async_schedule_dev()
+ * that will run the function synchronously then.
+ */
+bool async_schedule_dev_nocall(async_func_t func, struct device *dev)
+{
+	struct async_entry *entry;
+
+	entry = kzalloc(sizeof(struct async_entry), GFP_KERNEL);
+
+	/* Give up if there is no memory or too much work. */
+	if (!entry || atomic_read(&entry_count) > MAX_WORK) {
+		kfree(entry);
+		return false;
+	}
+
+	__async_schedule_node_domain(func, dev, dev_to_node(dev),
+				     &async_dfl_domain, entry);
+	return true;
+}
+
 /**
  * async_synchronize_full - synchronize all asynchronous function calls
  *
-- 
cgit v1.2.3


From 3b82024c5ba93e7a0db2d0b9635ca6b28338efd7 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Thu, 28 Dec 2023 13:04:41 +0530
Subject: OPP: Move dev_pm_opp_icc_bw to internal opp.h

It isn't used by any driver or API, privatize it.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
---
 drivers/opp/opp.h      | 12 ++++++++++++
 include/linux/pm_opp.h | 12 ------------
 2 files changed, 12 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/drivers/opp/opp.h b/drivers/opp/opp.h
index 23dcb2fbf8c3..558c9ac6a6fa 100644
--- a/drivers/opp/opp.h
+++ b/drivers/opp/opp.h
@@ -50,6 +50,18 @@ struct opp_config_data {
 	unsigned int flags;
 };
 
+/**
+ * struct dev_pm_opp_icc_bw - Interconnect bandwidth values
+ * @avg:	Average bandwidth corresponding to this OPP (in icc units)
+ * @peak:	Peak bandwidth corresponding to this OPP (in icc units)
+ *
+ * This structure stores the bandwidth values for a single interconnect path.
+ */
+struct dev_pm_opp_icc_bw {
+	u32 avg;
+	u32 peak;
+};
+
 /*
  * Internal data structure organization with the OPP layer library is as
  * follows:
diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h
index 74768c47d790..76dcb7f37bcd 100644
--- a/include/linux/pm_opp.h
+++ b/include/linux/pm_opp.h
@@ -45,18 +45,6 @@ struct dev_pm_opp_supply {
 	unsigned long u_watt;
 };
 
-/**
- * struct dev_pm_opp_icc_bw - Interconnect bandwidth values
- * @avg:	Average bandwidth corresponding to this OPP (in icc units)
- * @peak:	Peak bandwidth corresponding to this OPP (in icc units)
- *
- * This structure stores the bandwidth values for a single interconnect path.
- */
-struct dev_pm_opp_icc_bw {
-	u32 avg;
-	u32 peak;
-};
-
 typedef int (*config_regulators_t)(struct device *dev,
 			struct dev_pm_opp *old_opp, struct dev_pm_opp *new_opp,
 			struct regulator **regulators, unsigned int count);
-- 
cgit v1.2.3


From a15f2d48c6f84ae0dd2000288592c79d5d1acd0e Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 19 Dec 2023 16:47:41 +0100
Subject: nubus: Make nubus_bus_type static and constant

Now that the driver core can properly handle constant struct bus_type,
move the nubus_bus_type variable to be a constant structure as well,
placing it into read-only memory which can not be modified at runtime.

It's also never used outside of drivers/nubus/bus.c so make it static
and don't export it as no one is using it.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Finn Thain <fthain@linux-m68k.org>
Reviewed-by: Geert Uytterhoeven <geert@linux-m68k.org>
Link: https://lore.kernel.org/r/2023121940-enlarged-editor-c9a8@gregkh
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
---
 drivers/nubus/bus.c   | 3 +--
 include/linux/nubus.h | 2 --
 2 files changed, 1 insertion(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/nubus/bus.c b/drivers/nubus/bus.c
index 72921e4f35f6..12df4d88970c 100644
--- a/drivers/nubus/bus.c
+++ b/drivers/nubus/bus.c
@@ -32,12 +32,11 @@ static void nubus_device_remove(struct device *dev)
 		ndrv->remove(to_nubus_board(dev));
 }
 
-struct bus_type nubus_bus_type = {
+static const struct bus_type nubus_bus_type = {
 	.name		= "nubus",
 	.probe		= nubus_device_probe,
 	.remove		= nubus_device_remove,
 };
-EXPORT_SYMBOL(nubus_bus_type);
 
 int nubus_driver_register(struct nubus_driver *ndrv)
 {
diff --git a/include/linux/nubus.h b/include/linux/nubus.h
index bdcd85e622d8..4d103ac8f5c7 100644
--- a/include/linux/nubus.h
+++ b/include/linux/nubus.h
@@ -89,8 +89,6 @@ struct nubus_driver {
 	void (*remove)(struct nubus_board *board);
 };
 
-extern struct bus_type nubus_bus_type;
-
 /* Generic NuBus interface functions, modelled after the PCI interface */
 #ifdef CONFIG_PROC_FS
 extern bool nubus_populate_procfs;
-- 
cgit v1.2.3


From 292010ee509443a1383bb079a4fa80515aa89a7f Mon Sep 17 00:00:00 2001
From: Benjamin Berg <benjamin.berg@intel.com>
Date: Wed, 20 Dec 2023 16:19:47 +0100
Subject: kunit: add parameter generation macro using description from array

The existing KUNIT_ARRAY_PARAM macro requires a separate function to
get the description. However, in a lot of cases the description can
just be copied directly from the array. Add a second macro that
avoids having to write a static function just for a single strscpy.

Signed-off-by: Benjamin Berg <benjamin.berg@intel.com>
Reviewed-by: David Gow <davidgow@google.com>
Link: https://msgid.link/20231220151952.415232-2-benjamin@sipsolutions.net
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 Documentation/dev-tools/kunit/usage.rst | 12 ++++--------
 include/kunit/test.h                    | 19 +++++++++++++++++++
 2 files changed, 23 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/Documentation/dev-tools/kunit/usage.rst b/Documentation/dev-tools/kunit/usage.rst
index c27e1646ecd9..b959e5befcbe 100644
--- a/Documentation/dev-tools/kunit/usage.rst
+++ b/Documentation/dev-tools/kunit/usage.rst
@@ -566,13 +566,9 @@ By reusing the same ``cases`` array from above, we can write the test as a
 		},
 	};
 
-	// Need a helper function to generate a name for each test case.
-	static void case_to_desc(const struct sha1_test_case *t, char *desc)
-	{
-		strcpy(desc, t->str);
-	}
-	// Creates `sha1_gen_params()` to iterate over `cases`.
-	KUNIT_ARRAY_PARAM(sha1, cases, case_to_desc);
+	// Creates `sha1_gen_params()` to iterate over `cases` while using
+	// the struct member `str` for the case description.
+	KUNIT_ARRAY_PARAM_DESC(sha1, cases, str);
 
 	// Looks no different from a normal test.
 	static void sha1_test(struct kunit *test)
@@ -588,7 +584,7 @@ By reusing the same ``cases`` array from above, we can write the test as a
 	}
 
 	// Instead of KUNIT_CASE, we use KUNIT_CASE_PARAM and pass in the
-	// function declared by KUNIT_ARRAY_PARAM.
+	// function declared by KUNIT_ARRAY_PARAM or KUNIT_ARRAY_PARAM_DESC.
 	static struct kunit_case sha1_test_cases[] = {
 		KUNIT_CASE_PARAM(sha1_test, sha1_gen_params),
 		{}
diff --git a/include/kunit/test.h b/include/kunit/test.h
index 20ed9f9275c9..2dfa851e1f88 100644
--- a/include/kunit/test.h
+++ b/include/kunit/test.h
@@ -1514,6 +1514,25 @@ do {									       \
 		return NULL;									\
 	}
 
+/**
+ * KUNIT_ARRAY_PARAM_DESC() - Define test parameter generator from an array.
+ * @name:  prefix for the test parameter generator function.
+ * @array: array of test parameters.
+ * @desc_member: structure member from array element to use as description
+ *
+ * Define function @name_gen_params which uses @array to generate parameters.
+ */
+#define KUNIT_ARRAY_PARAM_DESC(name, array, desc_member)					\
+	static const void *name##_gen_params(const void *prev, char *desc)			\
+	{											\
+		typeof((array)[0]) *__next = prev ? ((typeof(__next)) prev) + 1 : (array);	\
+		if (__next - (array) < ARRAY_SIZE((array))) {					\
+			strscpy(desc, __next->desc_member, KUNIT_PARAM_DESC_SIZE);		\
+			return __next;								\
+		}										\
+		return NULL;									\
+	}
+
 // TODO(dlatypov@google.com): consider eventually migrating users to explicitly
 // include resource.h themselves if they need it.
 #include <kunit/resource.h>
-- 
cgit v1.2.3


From b3231d353a51ddfb6ef7d17877d029790190f746 Mon Sep 17 00:00:00 2001
From: Benjamin Berg <benjamin.berg@intel.com>
Date: Wed, 20 Dec 2023 16:19:48 +0100
Subject: kunit: add a convenience allocation wrapper for SKBs

Add a simple convenience helper to allocate and zero fill an SKB for the
use by a kunit test. Also provide a way to free it again in case that
may be desirable.

This simply mirrors the kunit_kmalloc API.

Signed-off-by: Benjamin Berg <benjamin.berg@intel.com>
Reviewed-by: David Gow <davidgow@google.com>
Link: https://msgid.link/20231220151952.415232-3-benjamin@sipsolutions.net
[adjust file description as discussed]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/kunit/skbuff.h | 56 ++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 56 insertions(+)
 create mode 100644 include/kunit/skbuff.h

(limited to 'include')

diff --git a/include/kunit/skbuff.h b/include/kunit/skbuff.h
new file mode 100644
index 000000000000..44d12370939a
--- /dev/null
+++ b/include/kunit/skbuff.h
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * KUnit resource management helpers for SKBs (skbuff).
+ *
+ * Copyright (C) 2023 Intel Corporation
+ */
+
+#ifndef _KUNIT_SKBUFF_H
+#define _KUNIT_SKBUFF_H
+
+#include <kunit/resource.h>
+#include <linux/skbuff.h>
+
+static void kunit_action_kfree_skb(void *p)
+{
+	kfree_skb((struct sk_buff *)p);
+}
+
+/**
+ * kunit_zalloc_skb() - Allocate and initialize a resource managed skb.
+ * @test: The test case to which the skb belongs
+ * @len: size to allocate
+ *
+ * Allocate a new struct sk_buff with GFP_KERNEL, zero fill the give length
+ * and add it as a resource to the kunit test for automatic cleanup.
+ *
+ * Returns: newly allocated SKB, or %NULL on error
+ */
+static inline struct sk_buff *kunit_zalloc_skb(struct kunit *test, int len,
+					       gfp_t gfp)
+{
+	struct sk_buff *res = alloc_skb(len, GFP_KERNEL);
+
+	if (!res || skb_pad(res, len))
+		return NULL;
+
+	if (kunit_add_action_or_reset(test, kunit_action_kfree_skb, res))
+		return NULL;
+
+	return res;
+}
+
+/**
+ * kunit_kfree_skb() - Like kfree_skb except for allocations managed by KUnit.
+ * @test: The test case to which the resource belongs.
+ * @skb: The SKB to free.
+ */
+static inline void kunit_kfree_skb(struct kunit *test, struct sk_buff *skb)
+{
+	if (!skb)
+		return;
+
+	kunit_release_action(test, kunit_action_kfree_skb, (void *)skb);
+}
+
+#endif /* _KUNIT_SKBUFF_H */
-- 
cgit v1.2.3


From fcbac39b7d5e776bed058281af5d3248b94f1282 Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Thu, 21 Dec 2023 10:38:56 +0000
Subject: kunit: Allow passing function pointer to kunit_activate_static_stub()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Swap the arguments to typecheck_fn() in kunit_activate_static_stub()
so that real_fn_addr can be either the function itself or a pointer
to that function.

This is useful to simplify redirecting static functions in a module.
Having to pass the actual function meant that it must be exported
from the module. Either making the 'static' and EXPORT_SYMBOL*()
conditional (which makes the code messy), or change it to always
exported (which increases the export namespace and prevents the
compiler inlining a trivial stub function in non-test builds).

With the original definition of kunit_activate_static_stub() the
address of real_fn_addr was passed to typecheck_fn() as the type to
be passed. This meant that if real_fn_addr was a pointer-to-function
it would resolve to a ** instead of a *, giving an error like this:

   error: initialization of ‘int (**)(int)’ from incompatible pointer
   type ‘int (*)(int)’ [-Werror=incompatible-pointer-types]
   kunit_activate_static_stub(test, add_one_fn_ptr, subtract_one);
      |                             ^~~~~~~~~~~~
   ./include/linux/typecheck.h:21:25: note: in definition of macro
   ‘typecheck_fn’
   21 | ({ typeof(type) __tmp = function; \

Swapping the arguments to typecheck_fn makes it take the type of a
pointer to the replacement function. Either a function or a pointer
to function can be assigned to that. For example:

static int some_function(int x)
{
    /* whatever */
}

int (* some_function_ptr)(int) = some_function;

static int replacement(int x)
{
    /* whatever */
}

Then:
  kunit_activate_static_stub(test, some_function, replacement);
yields:
  typecheck_fn(typeof(&replacement), some_function);

and:
  kunit_activate_static_stub(test, some_function_ptr, replacement);
yields:
  typecheck_fn(typeof(&replacement), some_function_ptr);

The two typecheck_fn() then resolve to:

  int (*__tmp)(int) = some_function;
and
  int (*__tmp)(int) = some_function_ptr;

Both of these are valid. In the first case the compiler inserts
an implicit '&' to take the address of the supplied function, and
in the second case the RHS is already a pointer to the same type.

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Reviewed-by: Rae Moar <rmoar@google.com>
Reviewed-by: David Gow <davidgow@google.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 include/kunit/static_stub.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/kunit/static_stub.h b/include/kunit/static_stub.h
index 85315c80b303..bf940322dfc0 100644
--- a/include/kunit/static_stub.h
+++ b/include/kunit/static_stub.h
@@ -93,7 +93,7 @@ void __kunit_activate_static_stub(struct kunit *test,
  * The redirection can be disabled again with kunit_deactivate_static_stub().
  */
 #define kunit_activate_static_stub(test, real_fn_addr, replacement_addr) do {	\
-	typecheck_fn(typeof(&real_fn_addr), replacement_addr);			\
+	typecheck_fn(typeof(&replacement_addr), real_fn_addr);			\
 	__kunit_activate_static_stub(test, real_fn_addr, replacement_addr);	\
 } while (0)
 
-- 
cgit v1.2.3


From 2ad28ce9b98f8b22feaecc0966c706a8ef59cbf0 Mon Sep 17 00:00:00 2001
From: Max Gurtovoy <mgurtovoy@nvidia.com>
Date: Mon, 1 Jan 2024 12:35:27 +0200
Subject: nvme: remove unused definition

There is no users for NVMF_AUTH_HASH_LEN macro.

Reviewed-by: Israel Rukshin <israelr@nvidia.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 include/linux/nvme.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 44325c068b6a..462c21e0e417 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -20,7 +20,6 @@
 #define NVMF_TRSVCID_SIZE	32
 #define NVMF_TRADDR_SIZE	256
 #define NVMF_TSAS_SIZE		256
-#define NVMF_AUTH_HASH_LEN	64
 
 #define NVME_DISC_SUBSYS_NAME	"nqn.2014-08.org.nvmexpress.discovery"
 
-- 
cgit v1.2.3


From 7ece381aa72d430ee117958abb5bb23e21d72f1d Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Wed, 20 Dec 2023 15:52:56 +0000
Subject: kunit: Protect string comparisons against NULL

Add NULL checks to KUNIT_BINARY_STR_ASSERTION() so that it will fail
cleanly if either pointer is NULL, instead of causing a NULL pointer
dereference in the strcmp().

A test failure could be that a string is unexpectedly NULL. This could
be trapped by KUNIT_ASSERT_NOT_NULL() but that would terminate the test
at that point. It's preferable that the KUNIT_EXPECT_STR*() macros can
handle NULL pointers as a failure.

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Reviewed-by: David Gow <davidgow@google.com>
Reviewed-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 include/kunit/test.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/kunit/test.h b/include/kunit/test.h
index b163b9984b33..c2ce379c329b 100644
--- a/include/kunit/test.h
+++ b/include/kunit/test.h
@@ -758,7 +758,7 @@ do {									       \
 		.right_text = #right,					       \
 	};								       \
 									       \
-	if (likely(strcmp(__left, __right) op 0))			       \
+	if (likely((__left) && (__right) && (strcmp(__left, __right) op 0)))   \
 		break;							       \
 									       \
 									       \
-- 
cgit v1.2.3


From 5a72f0711151b5ccdd14e22ff5f2ba3605483a95 Mon Sep 17 00:00:00 2001
From: Inochi Amaoto <inochiama@outlook.com>
Date: Mon, 18 Dec 2023 12:04:03 +0800
Subject: dt-bindings: clock: sophgo: Add clock controller of CV1800 series SoC

Add definition for the clock controller of the CV1800 series SoC.

For CV181X, it has a clock that CV180X does not have. To avoid misuse,
also add a compatible string to identify CV181X series SoC.

Signed-off-by: Inochi Amaoto <inochiama@outlook.com>
Link: https://github.com/milkv-duo/duo-files/blob/main/hardware/CV1800B/CV1800B-CV1801B-Preliminary-Datasheet-full-en.pdf
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/IA1PR20MB49535E448097F6FFC1218C39BB90A@IA1PR20MB4953.namprd20.prod.outlook.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 .../bindings/clock/sophgo,cv1800-clk.yaml          |  46 ++++++
 include/dt-bindings/clock/sophgo,cv1800.h          | 176 +++++++++++++++++++++
 2 files changed, 222 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/clock/sophgo,cv1800-clk.yaml
 create mode 100644 include/dt-bindings/clock/sophgo,cv1800.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/clock/sophgo,cv1800-clk.yaml b/Documentation/devicetree/bindings/clock/sophgo,cv1800-clk.yaml
new file mode 100644
index 000000000000..c1dc24673c0d
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/sophgo,cv1800-clk.yaml
@@ -0,0 +1,46 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/sophgo,cv1800-clk.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Sophgo CV1800 Series Clock Controller
+
+maintainers:
+  - Inochi Amaoto <inochiama@outlook.com>
+
+properties:
+  compatible:
+    enum:
+      - sophgo,cv1800-clk
+      - sophgo,cv1810-clk
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  "#clock-cells":
+    const: 1
+    description:
+      See <dt-bindings/clock/sophgo,cv1800.h> for valid indices.
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - "#clock-cells"
+
+additionalProperties: false
+
+examples:
+  - |
+    clock-controller@3002000 {
+        compatible = "sophgo,cv1800-clk";
+        reg = <0x03002000 0x1000>;
+        clocks = <&osc>;
+        #clock-cells = <1>;
+    };
+
+...
diff --git a/include/dt-bindings/clock/sophgo,cv1800.h b/include/dt-bindings/clock/sophgo,cv1800.h
new file mode 100644
index 000000000000..cfbeca25a650
--- /dev/null
+++ b/include/dt-bindings/clock/sophgo,cv1800.h
@@ -0,0 +1,176 @@
+/* SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause */
+/*
+ * Copyright (C) 2023 Sophgo Ltd.
+ */
+
+#ifndef __DT_BINDINGS_SOPHGO_CV1800_CLK_H__
+#define __DT_BINDINGS_SOPHGO_CV1800_CLK_H__
+
+#define CLK_MPLL			0
+#define CLK_TPLL			1
+#define CLK_FPLL			2
+#define CLK_MIPIMPLL			3
+#define CLK_A0PLL			4
+#define CLK_DISPPLL			5
+#define CLK_CAM0PLL			6
+#define CLK_CAM1PLL			7
+
+#define CLK_MIPIMPLL_D3			8
+#define CLK_CAM0PLL_D2			9
+#define CLK_CAM0PLL_D3			10
+
+#define CLK_TPU				11
+#define CLK_TPU_FAB			12
+#define CLK_AHB_ROM			13
+#define CLK_DDR_AXI_REG			14
+#define CLK_RTC_25M			15
+#define CLK_SRC_RTC_SYS_0		16
+#define CLK_TEMPSEN			17
+#define CLK_SARADC			18
+#define CLK_EFUSE			19
+#define CLK_APB_EFUSE			20
+#define CLK_DEBUG			21
+#define CLK_AP_DEBUG			22
+#define CLK_XTAL_MISC			23
+#define CLK_AXI4_EMMC			24
+#define CLK_EMMC			25
+#define CLK_EMMC_100K			26
+#define CLK_AXI4_SD0			27
+#define CLK_SD0				28
+#define CLK_SD0_100K			29
+#define CLK_AXI4_SD1			30
+#define CLK_SD1				31
+#define CLK_SD1_100K			32
+#define CLK_SPI_NAND			33
+#define CLK_ETH0_500M			34
+#define CLK_AXI4_ETH0			35
+#define CLK_ETH1_500M			36
+#define CLK_AXI4_ETH1			37
+#define CLK_APB_GPIO			38
+#define CLK_APB_GPIO_INTR		39
+#define CLK_GPIO_DB			40
+#define CLK_AHB_SF			41
+#define CLK_AHB_SF1			42
+#define CLK_A24M			43
+#define CLK_AUDSRC			44
+#define CLK_APB_AUDSRC			45
+#define CLK_SDMA_AXI			46
+#define CLK_SDMA_AUD0			47
+#define CLK_SDMA_AUD1			48
+#define CLK_SDMA_AUD2			49
+#define CLK_SDMA_AUD3			50
+#define CLK_I2C				51
+#define CLK_APB_I2C			52
+#define CLK_APB_I2C0			53
+#define CLK_APB_I2C1			54
+#define CLK_APB_I2C2			55
+#define CLK_APB_I2C3			56
+#define CLK_APB_I2C4			57
+#define CLK_APB_WDT			58
+#define CLK_PWM_SRC			59
+#define CLK_PWM				60
+#define CLK_SPI				61
+#define CLK_APB_SPI0			62
+#define CLK_APB_SPI1			63
+#define CLK_APB_SPI2			64
+#define CLK_APB_SPI3			65
+#define CLK_1M				66
+#define CLK_CAM0_200			67
+#define CLK_PM				68
+#define CLK_TIMER0			69
+#define CLK_TIMER1			70
+#define CLK_TIMER2			71
+#define CLK_TIMER3			72
+#define CLK_TIMER4			73
+#define CLK_TIMER5			74
+#define CLK_TIMER6			75
+#define CLK_TIMER7			76
+#define CLK_UART0			77
+#define CLK_APB_UART0			78
+#define CLK_UART1			79
+#define CLK_APB_UART1			80
+#define CLK_UART2			81
+#define CLK_APB_UART2			82
+#define CLK_UART3			83
+#define CLK_APB_UART3			84
+#define CLK_UART4			85
+#define CLK_APB_UART4			86
+#define CLK_APB_I2S0			87
+#define CLK_APB_I2S1			88
+#define CLK_APB_I2S2			89
+#define CLK_APB_I2S3			90
+#define CLK_AXI4_USB			91
+#define CLK_APB_USB			92
+#define CLK_USB_125M			93
+#define CLK_USB_33K			94
+#define CLK_USB_12M			95
+#define CLK_AXI4			96
+#define CLK_AXI6			97
+#define CLK_DSI_ESC			98
+#define CLK_AXI_VIP			99
+#define CLK_SRC_VIP_SYS_0		100
+#define CLK_SRC_VIP_SYS_1		101
+#define CLK_SRC_VIP_SYS_2		102
+#define CLK_SRC_VIP_SYS_3		103
+#define CLK_SRC_VIP_SYS_4		104
+#define CLK_CSI_BE_VIP			105
+#define CLK_CSI_MAC0_VIP		106
+#define CLK_CSI_MAC1_VIP		107
+#define CLK_CSI_MAC2_VIP		108
+#define CLK_CSI0_RX_VIP			109
+#define CLK_CSI1_RX_VIP			110
+#define CLK_ISP_TOP_VIP			111
+#define CLK_IMG_D_VIP			112
+#define CLK_IMG_V_VIP			113
+#define CLK_SC_TOP_VIP			114
+#define CLK_SC_D_VIP			115
+#define CLK_SC_V1_VIP			116
+#define CLK_SC_V2_VIP			117
+#define CLK_SC_V3_VIP			118
+#define CLK_DWA_VIP			119
+#define CLK_BT_VIP			120
+#define CLK_DISP_VIP			121
+#define CLK_DSI_MAC_VIP			122
+#define CLK_LVDS0_VIP			123
+#define CLK_LVDS1_VIP			124
+#define CLK_PAD_VI_VIP			125
+#define CLK_PAD_VI1_VIP			126
+#define CLK_PAD_VI2_VIP			127
+#define CLK_CFG_REG_VIP			128
+#define CLK_VIP_IP0			129
+#define CLK_VIP_IP1			130
+#define CLK_VIP_IP2			131
+#define CLK_VIP_IP3			132
+#define CLK_IVE_VIP			133
+#define CLK_RAW_VIP			134
+#define CLK_OSDC_VIP			135
+#define CLK_CAM0_VIP			136
+#define CLK_AXI_VIDEO_CODEC		137
+#define CLK_VC_SRC0			138
+#define CLK_VC_SRC1			139
+#define CLK_VC_SRC2			140
+#define CLK_H264C			141
+#define CLK_APB_H264C			142
+#define CLK_H265C			143
+#define CLK_APB_H265C			144
+#define CLK_JPEG			145
+#define CLK_APB_JPEG			146
+#define CLK_CAM0			147
+#define CLK_CAM1			148
+#define CLK_WGN				149
+#define CLK_WGN0			150
+#define CLK_WGN1			151
+#define CLK_WGN2			152
+#define CLK_KEYSCAN			153
+#define CLK_CFG_REG_VC			154
+#define CLK_C906_0			155
+#define CLK_C906_1			156
+#define CLK_A53				157
+#define CLK_CPU_AXI0			158
+#define CLK_CPU_GIC			159
+#define CLK_XTAL_AP			160
+
+// Only for CV181x
+#define CLK_DISP_SRC_VIP		161
+
+#endif /* __DT_BINDINGS_SOPHGO_CV1800_CLK_H__ */
-- 
cgit v1.2.3


From 8187e001de156e99ef95366ffd10d627ed090826 Mon Sep 17 00:00:00 2001
From: Sam Shih <sam.shih@mediatek.com>
Date: Sun, 17 Dec 2023 21:49:33 +0000
Subject: dt-bindings: clock: mediatek: add MT7988 clock IDs

Add MT7988 clock dt-bindings for topckgen, apmixedsys, infracfg,
ethernet and xfipll subsystem clocks.

Signed-off-by: Sam Shih <sam.shih@mediatek.com>
Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Link: https://lore.kernel.org/r/27f99db432e9ccc804cc5b6501d7d17d72cae879.1702849494.git.daniel@makrotopia.org
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 include/dt-bindings/clock/mediatek,mt7988-clk.h | 280 ++++++++++++++++++++++++
 1 file changed, 280 insertions(+)
 create mode 100644 include/dt-bindings/clock/mediatek,mt7988-clk.h

(limited to 'include')

diff --git a/include/dt-bindings/clock/mediatek,mt7988-clk.h b/include/dt-bindings/clock/mediatek,mt7988-clk.h
new file mode 100644
index 000000000000..63376e40f14d
--- /dev/null
+++ b/include/dt-bindings/clock/mediatek,mt7988-clk.h
@@ -0,0 +1,280 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/*
+ * Copyright (c) 2023 MediaTek Inc.
+ * Author: Sam Shih <sam.shih@mediatek.com>
+ * Author: Xiufeng Li <Xiufeng.Li@mediatek.com>
+ */
+
+#ifndef _DT_BINDINGS_CLK_MT7988_H
+#define _DT_BINDINGS_CLK_MT7988_H
+
+/* APMIXEDSYS */
+
+#define CLK_APMIXED_NETSYSPLL			0
+#define CLK_APMIXED_MPLL			1
+#define CLK_APMIXED_MMPLL			2
+#define CLK_APMIXED_APLL2			3
+#define CLK_APMIXED_NET1PLL			4
+#define CLK_APMIXED_NET2PLL			5
+#define CLK_APMIXED_WEDMCUPLL			6
+#define CLK_APMIXED_SGMPLL			7
+#define CLK_APMIXED_ARM_B			8
+#define CLK_APMIXED_CCIPLL2_B			9
+#define CLK_APMIXED_USXGMIIPLL			10
+#define CLK_APMIXED_MSDCPLL			11
+
+/* TOPCKGEN */
+
+#define CLK_TOP_XTAL				0
+#define CLK_TOP_XTAL_D2				1
+#define CLK_TOP_RTC_32K				2
+#define CLK_TOP_RTC_32P7K			3
+#define CLK_TOP_MPLL_D2				4
+#define CLK_TOP_MPLL_D3_D2			5
+#define CLK_TOP_MPLL_D4				6
+#define CLK_TOP_MPLL_D8				7
+#define CLK_TOP_MPLL_D8_D2			8
+#define CLK_TOP_MMPLL_D2			9
+#define CLK_TOP_MMPLL_D3_D5			10
+#define CLK_TOP_MMPLL_D4			11
+#define CLK_TOP_MMPLL_D6_D2			12
+#define CLK_TOP_MMPLL_D8			13
+#define CLK_TOP_APLL2_D4			14
+#define CLK_TOP_NET1PLL_D4			15
+#define CLK_TOP_NET1PLL_D5			16
+#define CLK_TOP_NET1PLL_D5_D2			17
+#define CLK_TOP_NET1PLL_D5_D4			18
+#define CLK_TOP_NET1PLL_D8			19
+#define CLK_TOP_NET1PLL_D8_D2			20
+#define CLK_TOP_NET1PLL_D8_D4			21
+#define CLK_TOP_NET1PLL_D8_D8			22
+#define CLK_TOP_NET1PLL_D8_D16			23
+#define CLK_TOP_NET2PLL_D2			24
+#define CLK_TOP_NET2PLL_D4			25
+#define CLK_TOP_NET2PLL_D4_D4			26
+#define CLK_TOP_NET2PLL_D4_D8			27
+#define CLK_TOP_NET2PLL_D6			28
+#define CLK_TOP_NET2PLL_D8			29
+#define CLK_TOP_NETSYS_SEL			30
+#define CLK_TOP_NETSYS_500M_SEL			31
+#define CLK_TOP_NETSYS_2X_SEL			32
+#define CLK_TOP_NETSYS_GSW_SEL			33
+#define CLK_TOP_ETH_GMII_SEL			34
+#define CLK_TOP_NETSYS_MCU_SEL			35
+#define CLK_TOP_NETSYS_PAO_2X_SEL		36
+#define CLK_TOP_EIP197_SEL			37
+#define CLK_TOP_AXI_INFRA_SEL			38
+#define CLK_TOP_UART_SEL			39
+#define CLK_TOP_EMMC_250M_SEL			40
+#define CLK_TOP_EMMC_400M_SEL			41
+#define CLK_TOP_SPI_SEL				42
+#define CLK_TOP_SPIM_MST_SEL			43
+#define CLK_TOP_NFI1X_SEL			44
+#define CLK_TOP_SPINFI_SEL			45
+#define CLK_TOP_PWM_SEL				46
+#define CLK_TOP_I2C_SEL				47
+#define CLK_TOP_PCIE_MBIST_250M_SEL		48
+#define CLK_TOP_PEXTP_TL_SEL			49
+#define CLK_TOP_PEXTP_TL_P1_SEL			50
+#define CLK_TOP_PEXTP_TL_P2_SEL			51
+#define CLK_TOP_PEXTP_TL_P3_SEL			52
+#define CLK_TOP_USB_SYS_SEL			53
+#define CLK_TOP_USB_SYS_P1_SEL			54
+#define CLK_TOP_USB_XHCI_SEL			55
+#define CLK_TOP_USB_XHCI_P1_SEL			56
+#define CLK_TOP_USB_FRMCNT_SEL			57
+#define CLK_TOP_USB_FRMCNT_P1_SEL		58
+#define CLK_TOP_AUD_SEL				59
+#define CLK_TOP_A1SYS_SEL			60
+#define CLK_TOP_AUD_L_SEL			61
+#define CLK_TOP_A_TUNER_SEL			62
+#define CLK_TOP_SSPXTP_SEL			63
+#define CLK_TOP_USB_PHY_SEL			64
+#define CLK_TOP_USXGMII_SBUS_0_SEL		65
+#define CLK_TOP_USXGMII_SBUS_1_SEL		66
+#define CLK_TOP_SGM_0_SEL			67
+#define CLK_TOP_SGM_SBUS_0_SEL			68
+#define CLK_TOP_SGM_1_SEL			69
+#define CLK_TOP_SGM_SBUS_1_SEL			70
+#define CLK_TOP_XFI_PHY_0_XTAL_SEL		71
+#define CLK_TOP_XFI_PHY_1_XTAL_SEL		72
+#define CLK_TOP_SYSAXI_SEL			73
+#define CLK_TOP_SYSAPB_SEL			74
+#define CLK_TOP_ETH_REFCK_50M_SEL		75
+#define CLK_TOP_ETH_SYS_200M_SEL		76
+#define CLK_TOP_ETH_SYS_SEL			77
+#define CLK_TOP_ETH_XGMII_SEL			78
+#define CLK_TOP_BUS_TOPS_SEL			79
+#define CLK_TOP_NPU_TOPS_SEL			80
+#define CLK_TOP_DRAMC_SEL			81
+#define CLK_TOP_DRAMC_MD32_SEL			82
+#define CLK_TOP_INFRA_F26M_SEL			83
+#define CLK_TOP_PEXTP_P0_SEL			84
+#define CLK_TOP_PEXTP_P1_SEL			85
+#define CLK_TOP_PEXTP_P2_SEL			86
+#define CLK_TOP_PEXTP_P3_SEL			87
+#define CLK_TOP_DA_XTP_GLB_P0_SEL		88
+#define CLK_TOP_DA_XTP_GLB_P1_SEL		89
+#define CLK_TOP_DA_XTP_GLB_P2_SEL		90
+#define CLK_TOP_DA_XTP_GLB_P3_SEL		91
+#define CLK_TOP_CKM_SEL				92
+#define CLK_TOP_DA_SEL				93
+#define CLK_TOP_PEXTP_SEL			94
+#define CLK_TOP_TOPS_P2_26M_SEL			95
+#define CLK_TOP_MCUSYS_BACKUP_625M_SEL		96
+#define CLK_TOP_NETSYS_SYNC_250M_SEL		97
+#define CLK_TOP_MACSEC_SEL			98
+#define CLK_TOP_NETSYS_TOPS_400M_SEL		99
+#define CLK_TOP_NETSYS_PPEFB_250M_SEL		100
+#define CLK_TOP_NETSYS_WARP_SEL			101
+#define CLK_TOP_ETH_MII_SEL			102
+#define CLK_TOP_NPU_SEL				103
+#define CLK_TOP_AUD_I2S_M			104
+
+/* MCUSYS */
+
+#define CLK_MCU_BUS_DIV_SEL			0
+#define CLK_MCU_ARM_DIV_SEL			1
+
+/* INFRACFG_AO */
+
+#define CLK_INFRA_MUX_UART0_SEL			0
+#define CLK_INFRA_MUX_UART1_SEL			1
+#define CLK_INFRA_MUX_UART2_SEL			2
+#define CLK_INFRA_MUX_SPI0_SEL			3
+#define CLK_INFRA_MUX_SPI1_SEL			4
+#define CLK_INFRA_MUX_SPI2_SEL			5
+#define CLK_INFRA_PWM_SEL			6
+#define CLK_INFRA_PWM_CK1_SEL			7
+#define CLK_INFRA_PWM_CK2_SEL			8
+#define CLK_INFRA_PWM_CK3_SEL			9
+#define CLK_INFRA_PWM_CK4_SEL			10
+#define CLK_INFRA_PWM_CK5_SEL			11
+#define CLK_INFRA_PWM_CK6_SEL			12
+#define CLK_INFRA_PWM_CK7_SEL			13
+#define CLK_INFRA_PWM_CK8_SEL			14
+#define CLK_INFRA_PCIE_GFMUX_TL_O_P0_SEL	15
+#define CLK_INFRA_PCIE_GFMUX_TL_O_P1_SEL	16
+#define CLK_INFRA_PCIE_GFMUX_TL_O_P2_SEL	17
+#define CLK_INFRA_PCIE_GFMUX_TL_O_P3_SEL	18
+
+/* INFRACFG */
+
+#define CLK_INFRA_PCIE_PERI_26M_CK_P0		19
+#define CLK_INFRA_PCIE_PERI_26M_CK_P1		20
+#define CLK_INFRA_PCIE_PERI_26M_CK_P2		21
+#define CLK_INFRA_PCIE_PERI_26M_CK_P3		22
+#define CLK_INFRA_66M_GPT_BCK			23
+#define CLK_INFRA_66M_PWM_HCK			24
+#define CLK_INFRA_66M_PWM_BCK			25
+#define CLK_INFRA_66M_PWM_CK1			26
+#define CLK_INFRA_66M_PWM_CK2			27
+#define CLK_INFRA_66M_PWM_CK3			28
+#define CLK_INFRA_66M_PWM_CK4			29
+#define CLK_INFRA_66M_PWM_CK5			30
+#define CLK_INFRA_66M_PWM_CK6			31
+#define CLK_INFRA_66M_PWM_CK7			32
+#define CLK_INFRA_66M_PWM_CK8			33
+#define CLK_INFRA_133M_CQDMA_BCK		34
+#define CLK_INFRA_66M_AUD_SLV_BCK		35
+#define CLK_INFRA_AUD_26M			36
+#define CLK_INFRA_AUD_L				37
+#define CLK_INFRA_AUD_AUD			38
+#define CLK_INFRA_AUD_EG2			39
+#define CLK_INFRA_DRAMC_F26M			40
+#define CLK_INFRA_133M_DBG_ACKM			41
+#define CLK_INFRA_66M_AP_DMA_BCK		42
+#define CLK_INFRA_66M_SEJ_BCK			43
+#define CLK_INFRA_PRE_CK_SEJ_F13M		44
+#define CLK_INFRA_26M_THERM_SYSTEM		45
+#define CLK_INFRA_I2C_BCK			46
+#define CLK_INFRA_52M_UART0_CK			47
+#define CLK_INFRA_52M_UART1_CK			48
+#define CLK_INFRA_52M_UART2_CK			49
+#define CLK_INFRA_NFI				50
+#define CLK_INFRA_SPINFI			51
+#define CLK_INFRA_66M_NFI_HCK			52
+#define CLK_INFRA_104M_SPI0			53
+#define CLK_INFRA_104M_SPI1			54
+#define CLK_INFRA_104M_SPI2_BCK			55
+#define CLK_INFRA_66M_SPI0_HCK			56
+#define CLK_INFRA_66M_SPI1_HCK			57
+#define CLK_INFRA_66M_SPI2_HCK			58
+#define CLK_INFRA_66M_FLASHIF_AXI		59
+#define CLK_INFRA_RTC				60
+#define CLK_INFRA_26M_ADC_BCK			61
+#define CLK_INFRA_RC_ADC			62
+#define CLK_INFRA_MSDC400			63
+#define CLK_INFRA_MSDC2_HCK			64
+#define CLK_INFRA_133M_MSDC_0_HCK		65
+#define CLK_INFRA_66M_MSDC_0_HCK		66
+#define CLK_INFRA_133M_CPUM_BCK			67
+#define CLK_INFRA_BIST2FPC			68
+#define CLK_INFRA_I2C_X16W_MCK_CK_P1		69
+#define CLK_INFRA_I2C_X16W_PCK_CK_P1		70
+#define CLK_INFRA_133M_USB_HCK			71
+#define CLK_INFRA_133M_USB_HCK_CK_P1		72
+#define CLK_INFRA_66M_USB_HCK			73
+#define CLK_INFRA_66M_USB_HCK_CK_P1		74
+#define CLK_INFRA_USB_SYS			75
+#define CLK_INFRA_USB_SYS_CK_P1			76
+#define CLK_INFRA_USB_REF			77
+#define CLK_INFRA_USB_CK_P1			78
+#define CLK_INFRA_USB_FRMCNT			79
+#define CLK_INFRA_USB_FRMCNT_CK_P1		80
+#define CLK_INFRA_USB_PIPE			81
+#define CLK_INFRA_USB_PIPE_CK_P1		82
+#define CLK_INFRA_USB_UTMI			83
+#define CLK_INFRA_USB_UTMI_CK_P1		84
+#define CLK_INFRA_USB_XHCI			85
+#define CLK_INFRA_USB_XHCI_CK_P1		86
+#define CLK_INFRA_PCIE_GFMUX_TL_P0		87
+#define CLK_INFRA_PCIE_GFMUX_TL_P1		88
+#define CLK_INFRA_PCIE_GFMUX_TL_P2		89
+#define CLK_INFRA_PCIE_GFMUX_TL_P3		90
+#define CLK_INFRA_PCIE_PIPE_P0			91
+#define CLK_INFRA_PCIE_PIPE_P1			92
+#define CLK_INFRA_PCIE_PIPE_P2			93
+#define CLK_INFRA_PCIE_PIPE_P3			94
+#define CLK_INFRA_133M_PCIE_CK_P0		95
+#define CLK_INFRA_133M_PCIE_CK_P1		96
+#define CLK_INFRA_133M_PCIE_CK_P2		97
+#define CLK_INFRA_133M_PCIE_CK_P3		98
+
+/* ETHDMA */
+
+#define CLK_ETHDMA_XGP1_EN			0
+#define CLK_ETHDMA_XGP2_EN			1
+#define CLK_ETHDMA_XGP3_EN			2
+#define CLK_ETHDMA_FE_EN			3
+#define CLK_ETHDMA_GP2_EN			4
+#define CLK_ETHDMA_GP1_EN			5
+#define CLK_ETHDMA_GP3_EN			6
+#define CLK_ETHDMA_ESW_EN			7
+#define CLK_ETHDMA_CRYPT0_EN			8
+#define CLK_ETHDMA_NR_CLK			9
+
+/* SGMIISYS_0 */
+
+#define CLK_SGM0_TX_EN				0
+#define CLK_SGM0_RX_EN				1
+#define CLK_SGMII0_NR_CLK			2
+
+/* SGMIISYS_1 */
+
+#define CLK_SGM1_TX_EN				0
+#define CLK_SGM1_RX_EN				1
+#define CLK_SGMII1_NR_CLK			2
+
+/* ETHWARP */
+
+#define CLK_ETHWARP_WOCPU2_EN			0
+#define CLK_ETHWARP_WOCPU1_EN			1
+#define CLK_ETHWARP_WOCPU0_EN			2
+#define CLK_ETHWARP_NR_CLK			3
+
+/* XFIPLL */
+#define CLK_XFIPLL_PLL				0
+#define CLK_XFIPLL_PLL_EN			1
+
+#endif /* _DT_BINDINGS_CLK_MT7988_H */
-- 
cgit v1.2.3


From 5cfa3beb7761cb84be77225902e018d9d3f9b973 Mon Sep 17 00:00:00 2001
From: Daniel Golle <daniel@makrotopia.org>
Date: Sun, 17 Dec 2023 21:49:45 +0000
Subject: dt-bindings: reset: mediatek: add MT7988 ethwarp reset IDs

Add reset ID for ethwarp subsystem allowing to reset the built-in
Ethernet switch of the MediaTek MT7988 SoC.

Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/0c14bbacf471683af67ffa7572bfa1d5c45a0b5d.1702849494.git.daniel@makrotopia.org
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 include/dt-bindings/reset/mediatek,mt7988-resets.h | 13 +++++++++++++
 1 file changed, 13 insertions(+)
 create mode 100644 include/dt-bindings/reset/mediatek,mt7988-resets.h

(limited to 'include')

diff --git a/include/dt-bindings/reset/mediatek,mt7988-resets.h b/include/dt-bindings/reset/mediatek,mt7988-resets.h
new file mode 100644
index 000000000000..493301971367
--- /dev/null
+++ b/include/dt-bindings/reset/mediatek,mt7988-resets.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/*
+ * Copyright (c) 2023 Daniel Golle <daniel@makrotopia.org>
+ * Author: Daniel Golle <daniel@makrotopia.org>
+ */
+
+#ifndef _DT_BINDINGS_RESET_CONTROLLER_MT7988
+#define _DT_BINDINGS_RESET_CONTROLLER_MT7988
+
+/* ETHWARP resets */
+#define MT7988_ETHWARP_RST_SWITCH		0
+
+#endif  /* _DT_BINDINGS_RESET_CONTROLLER_MT7988 */
-- 
cgit v1.2.3


From b4c1d4d9734cda4394da5b59ebf7d9ca3579561a Mon Sep 17 00:00:00 2001
From: Zhengchao Shao <shaozhengchao@huawei.com>
Date: Tue, 2 Jan 2024 15:15:19 +0800
Subject: fib: remove unnecessary input parameters in fib_default_rule_add

When fib_default_rule_add is invoked, the value of the input parameter
'flags' is always 0. Rules uses kzalloc to allocate memory, so 'flags' has
been initialized to 0. Therefore, remove the input parameter 'flags' in
fib_default_rule_add.

Signed-off-by: Zhengchao Shao <shaozhengchao@huawei.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20240102071519.3781384-1-shaozhengchao@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/fib_rules.h | 3 +--
 net/core/fib_rules.c    | 3 +--
 net/ipv4/fib_rules.c    | 6 +++---
 net/ipv4/ipmr.c         | 2 +-
 net/ipv6/fib6_rules.c   | 4 ++--
 net/ipv6/ip6mr.c        | 2 +-
 6 files changed, 9 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index 82da359bca03..d17855c52ef9 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -172,8 +172,7 @@ void fib_rules_unregister(struct fib_rules_ops *);
 
 int fib_rules_lookup(struct fib_rules_ops *, struct flowi *, int flags,
 		     struct fib_lookup_arg *);
-int fib_default_rule_add(struct fib_rules_ops *, u32 pref, u32 table,
-			 u32 flags);
+int fib_default_rule_add(struct fib_rules_ops *, u32 pref, u32 table);
 bool fib_rule_matchall(const struct fib_rule *rule);
 int fib_rules_dump(struct net *net, struct notifier_block *nb, int family,
 		   struct netlink_ext_ack *extack);
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 75282222e0b4..96622bfb838a 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -53,7 +53,7 @@ bool fib_rule_matchall(const struct fib_rule *rule)
 EXPORT_SYMBOL_GPL(fib_rule_matchall);
 
 int fib_default_rule_add(struct fib_rules_ops *ops,
-			 u32 pref, u32 table, u32 flags)
+			 u32 pref, u32 table)
 {
 	struct fib_rule *r;
 
@@ -65,7 +65,6 @@ int fib_default_rule_add(struct fib_rules_ops *ops,
 	r->action = FR_ACT_TO_TBL;
 	r->pref = pref;
 	r->table = table;
-	r->flags = flags;
 	r->proto = RTPROT_KERNEL;
 	r->fr_net = ops->fro_net;
 	r->uid_range = fib_kuid_range_unset;
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 513f475c6a53..5bdd1c016009 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -395,13 +395,13 @@ static int fib_default_rules_init(struct fib_rules_ops *ops)
 {
 	int err;
 
-	err = fib_default_rule_add(ops, 0, RT_TABLE_LOCAL, 0);
+	err = fib_default_rule_add(ops, 0, RT_TABLE_LOCAL);
 	if (err < 0)
 		return err;
-	err = fib_default_rule_add(ops, 0x7FFE, RT_TABLE_MAIN, 0);
+	err = fib_default_rule_add(ops, 0x7FFE, RT_TABLE_MAIN);
 	if (err < 0)
 		return err;
-	err = fib_default_rule_add(ops, 0x7FFF, RT_TABLE_DEFAULT, 0);
+	err = fib_default_rule_add(ops, 0x7FFF, RT_TABLE_DEFAULT);
 	if (err < 0)
 		return err;
 	return 0;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 0063a237253b..9d6f59531b3a 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -253,7 +253,7 @@ static int __net_init ipmr_rules_init(struct net *net)
 		goto err1;
 	}
 
-	err = fib_default_rule_add(ops, 0x7fff, RT_TABLE_DEFAULT, 0);
+	err = fib_default_rule_add(ops, 0x7fff, RT_TABLE_DEFAULT);
 	if (err < 0)
 		goto err2;
 
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index 7c2003833010..7523c4baef35 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -475,11 +475,11 @@ static int __net_init fib6_rules_net_init(struct net *net)
 	if (IS_ERR(ops))
 		return PTR_ERR(ops);
 
-	err = fib_default_rule_add(ops, 0, RT6_TABLE_LOCAL, 0);
+	err = fib_default_rule_add(ops, 0, RT6_TABLE_LOCAL);
 	if (err)
 		goto out_fib6_rules_ops;
 
-	err = fib_default_rule_add(ops, 0x7FFE, RT6_TABLE_MAIN, 0);
+	err = fib_default_rule_add(ops, 0x7FFE, RT6_TABLE_MAIN);
 	if (err)
 		goto out_fib6_rules_ops;
 
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 30ca064b76ef..9782c180fee6 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -242,7 +242,7 @@ static int __net_init ip6mr_rules_init(struct net *net)
 		goto err1;
 	}
 
-	err = fib_default_rule_add(ops, 0x7fff, RT6_TABLE_DFLT, 0);
+	err = fib_default_rule_add(ops, 0x7fff, RT6_TABLE_DFLT);
 	if (err < 0)
 		goto err2;
 
-- 
cgit v1.2.3


From 7865dfb1eb941ddd25802a9e13b6ff5f3f4dc02f Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Thu, 21 Dec 2023 15:23:24 -0800
Subject: bpf: sockmap, added comments describing update proto rules

Add a comment describing that the psock update proto callbback can be
called multiple times and this must be safe.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/r/20231221232327.43678-3-john.fastabend@gmail.com
---
 include/linux/skmsg.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index c953b8c0d2f4..888a4b217829 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -100,6 +100,11 @@ struct sk_psock {
 	void (*saved_close)(struct sock *sk, long timeout);
 	void (*saved_write_space)(struct sock *sk);
 	void (*saved_data_ready)(struct sock *sk);
+	/* psock_update_sk_prot may be called with restore=false many times
+	 * so the handler must be safe for this case. It will be called
+	 * exactly once with restore=true when the psock is being destroyed
+	 * and psock refcnt is zero, but before an RCU grace period.
+	 */
 	int  (*psock_update_sk_prot)(struct sock *sk, struct sk_psock *psock,
 				     bool restore);
 	struct proto			*sk_proto;
-- 
cgit v1.2.3


From d3d344a1ca69d8fb2413e29e6400f3ad58a05c06 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 2 Jan 2024 16:22:20 +0000
Subject: net-device: move xdp_prog to net_device_read_rx

xdp_prog is used in receive path, both from XDP enabled drivers
and from netif_elide_gro().

This patch also removes two 4-bytes holes.

Fixes: 43a71cd66b9c ("net-device: reorganize net_device fast path variables")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Coco Li <lixiaoyan@google.com>
Cc: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240102162220.750823-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/net_cachelines/net_device.rst | 2 +-
 include/linux/netdevice.h                              | 2 +-
 net/core/dev.c                                         | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/Documentation/networking/net_cachelines/net_device.rst b/Documentation/networking/net_cachelines/net_device.rst
index 2dd8d8f20da2..e75a53593bb9 100644
--- a/Documentation/networking/net_cachelines/net_device.rst
+++ b/Documentation/networking/net_cachelines/net_device.rst
@@ -96,7 +96,7 @@ unsigned_char*                      dev_addr
 struct_netdev_queue*                _rx                     read_mostly         -                   netdev_get_rx_queue(rx)
 unsigned_int                        num_rx_queues                                                   
 unsigned_int                        real_num_rx_queues      -                   read_mostly         get_rps_cpu
-struct_bpf_prog*                    xdp_prog                                                        
+struct_bpf_prog*                    xdp_prog                -                   read_mostly         netif_elide_gro()
 unsigned_long                       gro_flush_timeout       -                   read_mostly         napi_complete_done
 int                                 napi_defer_hard_irqs    -                   read_mostly         napi_complete_done
 unsigned_int                        gro_max_size            -                   read_mostly         skb_gro_receive
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d59db9adcc96..e265aa1f2169 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2150,6 +2150,7 @@ struct net_device {
 
 	/* RX read-mostly hotpath */
 	__cacheline_group_begin(net_device_read_rx);
+	struct bpf_prog __rcu	*xdp_prog;
 	struct list_head	ptype_specific;
 	int			ifindex;
 	unsigned int		real_num_rx_queues;
@@ -2325,7 +2326,6 @@ struct net_device {
 	const unsigned char	*dev_addr;
 
 	unsigned int		num_rx_queues;
-	struct bpf_prog __rcu	*xdp_prog;
 #define GRO_LEGACY_MAX_SIZE	65536u
 /* TCP minimal MSS is 8 (TCP_MIN_GSO_SIZE),
  * and shinfo->gso_segs is a 16bit field.
diff --git a/net/core/dev.c b/net/core/dev.c
index 31588a50b757..bc4ac49d4643 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -11670,7 +11670,7 @@ static void __init net_dev_struct_check(void)
 #ifdef CONFIG_NET_XGRESS
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, tcx_ingress);
 #endif
-	CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_rx, 96);
+	CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_rx, 104);
 }
 
 /*
-- 
cgit v1.2.3


From c2a67de9bb543394aee869d1c68b5fbcd8a89dcb Mon Sep 17 00:00:00 2001
From: Pedro Tammela <pctammela@mojatatu.com>
Date: Fri, 29 Dec 2023 10:26:41 -0300
Subject: net/sched: introduce ACT_P_BOUND return code

Bound actions always return '0' and as of today we rely on '0'
being returned in order to properly skip bound actions in
tcf_idr_insert_many. In order to further improve maintainability,
introduce the ACT_P_BOUND return code.

Actions are updated to return 'ACT_P_BOUND' instead of plain '0'.
tcf_idr_insert_many is then updated to check for 'ACT_P_BOUND'.

Signed-off-by: Pedro Tammela <pctammela@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://lore.kernel.org/r/20231229132642.1489088-1-pctammela@mojatatu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/act_api.h      | 1 +
 net/sched/act_api.c        | 2 +-
 net/sched/act_bpf.c        | 2 +-
 net/sched/act_connmark.c   | 2 +-
 net/sched/act_csum.c       | 4 ++--
 net/sched/act_ct.c         | 2 +-
 net/sched/act_ctinfo.c     | 2 +-
 net/sched/act_gact.c       | 2 +-
 net/sched/act_gate.c       | 2 +-
 net/sched/act_ife.c        | 2 +-
 net/sched/act_mirred.c     | 2 +-
 net/sched/act_mpls.c       | 2 +-
 net/sched/act_nat.c        | 2 +-
 net/sched/act_pedit.c      | 2 +-
 net/sched/act_police.c     | 2 +-
 net/sched/act_sample.c     | 2 +-
 net/sched/act_simple.c     | 2 +-
 net/sched/act_skbedit.c    | 2 +-
 net/sched/act_skbmod.c     | 2 +-
 net/sched/act_tunnel_key.c | 2 +-
 net/sched/act_vlan.c       | 2 +-
 21 files changed, 22 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/include/net/act_api.h b/include/net/act_api.h
index ea13e1e4a7c2..447985a45ef6 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -137,6 +137,7 @@ struct tc_action_ops {
 
 #ifdef CONFIG_NET_CLS_ACT
 
+#define ACT_P_BOUND 0
 #define ACT_P_CREATED 1
 #define ACT_P_DELETED 1
 
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index a44c097a880d..ef70d4771811 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -1313,7 +1313,7 @@ void tcf_idr_insert_many(struct tc_action *actions[], int init_res[])
 	tcf_act_for_each_action(i, a, actions) {
 		struct tcf_idrinfo *idrinfo;
 
-		if (init_res[i] == 0) /* Bound */
+		if (init_res[i] == ACT_P_BOUND)
 			continue;
 
 		idrinfo = a->idrinfo;
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index b0455fda7d0b..6cfee6658103 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -318,7 +318,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 	} else if (ret > 0) {
 		/* Don't override defaults. */
 		if (bind)
-			return 0;
+			return ACT_P_BOUND;
 
 		if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
 			tcf_idr_release(*act, bind);
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index 0d7aee8933c5..f8762756657d 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -146,7 +146,7 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla,
 	} else if (ret > 0) {
 		ci = to_connmark(*a);
 		if (bind) {
-			err = 0;
+			err = ACT_P_BOUND;
 			goto out_free;
 		}
 		if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 8ed285023a40..7f8b1f2f2ed9 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -77,8 +77,8 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla,
 		}
 		ret = ACT_P_CREATED;
 	} else if (err > 0) {
-		if (bind)/* dont override defaults */
-			return 0;
+		if (bind) /* dont override defaults */
+			return ACT_P_BOUND;
 		if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
 			tcf_idr_release(*a, bind);
 			return -EEXIST;
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index f69c47945175..c3e004b5b820 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -1349,7 +1349,7 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla,
 		res = ACT_P_CREATED;
 	} else {
 		if (bind)
-			return 0;
+			return ACT_P_BOUND;
 
 		if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
 			tcf_idr_release(*a, bind);
diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c
index 4d15b6a6169c..e620f9a84afe 100644
--- a/net/sched/act_ctinfo.c
+++ b/net/sched/act_ctinfo.c
@@ -221,7 +221,7 @@ static int tcf_ctinfo_init(struct net *net, struct nlattr *nla,
 		ret = ACT_P_CREATED;
 	} else if (err > 0) {
 		if (bind) /* don't override defaults */
-			return 0;
+			return ACT_P_BOUND;
 		if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
 			tcf_idr_release(*a, bind);
 			return -EEXIST;
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index 904ab3d457ef..4af3b7ec249f 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -108,7 +108,7 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla,
 		ret = ACT_P_CREATED;
 	} else if (err > 0) {
 		if (bind)/* dont override defaults */
-			return 0;
+			return ACT_P_BOUND;
 		if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
 			tcf_idr_release(*a, bind);
 			return -EEXIST;
diff --git a/net/sched/act_gate.c b/net/sched/act_gate.c
index 393b78729216..c681cd011afd 100644
--- a/net/sched/act_gate.c
+++ b/net/sched/act_gate.c
@@ -356,7 +356,7 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla,
 		return err;
 
 	if (err && bind)
-		return 0;
+		return ACT_P_BOUND;
 
 	if (!err) {
 		ret = tcf_idr_create_from_flags(tn, index, est, a,
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index bc7611b0744c..0e867d13beb5 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -548,7 +548,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	exists = err;
 	if (exists && bind) {
 		kfree(p);
-		return 0;
+		return ACT_P_BOUND;
 	}
 
 	if (!exists) {
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index d1f9794ca9b7..12386f590b0f 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -135,7 +135,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 		return err;
 	exists = err;
 	if (exists && bind)
-		return 0;
+		return ACT_P_BOUND;
 
 	if (tb[TCA_MIRRED_BLOCKID] && parm->ifindex) {
 		NL_SET_ERR_MSG_MOD(extack,
diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c
index 1010dc632874..34b8edb6cc77 100644
--- a/net/sched/act_mpls.c
+++ b/net/sched/act_mpls.c
@@ -195,7 +195,7 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla,
 		return err;
 	exists = err;
 	if (exists && bind)
-		return 0;
+		return ACT_P_BOUND;
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, index, est, a, &act_mpls_ops, bind,
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 4184af5abbf3..a180e724634e 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -69,7 +69,7 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
 		ret = ACT_P_CREATED;
 	} else if (err > 0) {
 		if (bind)
-			return 0;
+			return ACT_P_BOUND;
 		if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
 			tcf_idr_release(*a, bind);
 			return -EEXIST;
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 1ef8fcfa9997..2ef22969f274 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -202,7 +202,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 		ret = ACT_P_CREATED;
 	} else if (err > 0) {
 		if (bind)
-			return 0;
+			return ACT_P_BOUND;
 		if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
 			ret = -EEXIST;
 			goto out_release;
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index f3121c5a85e9..e119b4a3db9f 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -77,7 +77,7 @@ static int tcf_police_init(struct net *net, struct nlattr *nla,
 		return err;
 	exists = err;
 	if (exists && bind)
-		return 0;
+		return ACT_P_BOUND;
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, index, NULL, a,
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 4c670e7568dc..c5c61efe6db4 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -66,7 +66,7 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 		return err;
 	exists = err;
 	if (exists && bind)
-		return 0;
+		return ACT_P_BOUND;
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, index, est, a,
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 4b84514534f3..0a3e92888295 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -118,7 +118,7 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
 		return err;
 	exists = err;
 	if (exists && bind)
-		return 0;
+		return ACT_P_BOUND;
 
 	if (tb[TCA_DEF_DATA] == NULL) {
 		if (exists)
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index ce7008cf291c..754f78b35bb8 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -209,7 +209,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 		return err;
 	exists = err;
 	if (exists && bind)
-		return 0;
+		return ACT_P_BOUND;
 
 	if (!flags) {
 		if (exists)
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index dffa990a9629..bcb673ab0008 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -157,7 +157,7 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
 		return err;
 	exists = err;
 	if (exists && bind)
-		return 0;
+		return ACT_P_BOUND;
 
 	if (!lflags) {
 		if (exists)
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 0c8aa7e686ea..300b08aa8283 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -401,7 +401,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 		return err;
 	exists = err;
 	if (exists && bind)
-		return 0;
+		return ACT_P_BOUND;
 
 	switch (parm->t_action) {
 	case TCA_TUNNEL_KEY_ACT_RELEASE:
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 0251442f5f29..836183011a7c 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -151,7 +151,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 		return err;
 	exists = err;
 	if (exists && bind)
-		return 0;
+		return ACT_P_BOUND;
 
 	switch (parm->v_action) {
 	case TCA_VLAN_ACT_POP:
-- 
cgit v1.2.3


From 9fc8e802048ad150e8032c4f3dbf40112160cfe9 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Thu, 21 Dec 2023 19:17:39 -0800
Subject: bpf: Add objcg to bpf_mem_alloc

The objcg is a bpf_mem_alloc level property since all bpf_mem_cache's
are with the same objcg. This patch made such a property explicit.
The next patch will use this property to save and restore objcg
for percpu unit allocator.

Acked-by: Hou Tao <houtao1@huawei.com>
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20231222031739.1288590-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf_mem_alloc.h |  1 +
 kernel/bpf/memalloc.c         | 11 ++++++-----
 2 files changed, 7 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h
index bb1223b21308..acef8c808599 100644
--- a/include/linux/bpf_mem_alloc.h
+++ b/include/linux/bpf_mem_alloc.h
@@ -11,6 +11,7 @@ struct bpf_mem_caches;
 struct bpf_mem_alloc {
 	struct bpf_mem_caches __percpu *caches;
 	struct bpf_mem_cache __percpu *cache;
+	struct obj_cgroup *objcg;
 	bool percpu;
 	struct work_struct work;
 };
diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 288ec4a967d0..4a21050f0359 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -523,6 +523,7 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 		if (memcg_bpf_enabled())
 			objcg = get_obj_cgroup_from_current();
 #endif
+		ma->objcg = objcg;
 		for_each_possible_cpu(cpu) {
 			c = per_cpu_ptr(pc, cpu);
 			c->unit_size = unit_size;
@@ -542,6 +543,7 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 #ifdef CONFIG_MEMCG_KMEM
 	objcg = get_obj_cgroup_from_current();
 #endif
+	ma->objcg = objcg;
 	for_each_possible_cpu(cpu) {
 		cc = per_cpu_ptr(pcc, cpu);
 		for (i = 0; i < NUM_CACHES; i++) {
@@ -691,9 +693,8 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma)
 			rcu_in_progress += atomic_read(&c->call_rcu_ttrace_in_progress);
 			rcu_in_progress += atomic_read(&c->call_rcu_in_progress);
 		}
-		/* objcg is the same across cpus */
-		if (c->objcg)
-			obj_cgroup_put(c->objcg);
+		if (ma->objcg)
+			obj_cgroup_put(ma->objcg);
 		destroy_mem_alloc(ma, rcu_in_progress);
 	}
 	if (ma->caches) {
@@ -709,8 +710,8 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma)
 				rcu_in_progress += atomic_read(&c->call_rcu_in_progress);
 			}
 		}
-		if (c->objcg)
-			obj_cgroup_put(c->objcg);
+		if (ma->objcg)
+			obj_cgroup_put(ma->objcg);
 		destroy_mem_alloc(ma, rcu_in_progress);
 	}
 }
-- 
cgit v1.2.3


From c39aa3b289e9c10d0d246cd919b06809f13b72b8 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Thu, 21 Dec 2023 19:17:45 -0800
Subject: bpf: Allow per unit prefill for non-fix-size percpu memory allocator

Commit 41a5db8d8161 ("Add support for non-fix-size percpu mem allocation")
added support for non-fix-size percpu memory allocation.
Such allocation will allocate percpu memory for all buckets on all
cpus and the memory consumption is in the order to quadratic.
For example, let us say, 4 cpus, unit size 16 bytes, so each
cpu has 16 * 4 = 64 bytes, with 4 cpus, total will be 64 * 4 = 256 bytes.
Then let us say, 8 cpus with the same unit size, each cpu
has 16 * 8 = 128 bytes, with 8 cpus, total will be 128 * 8 = 1024 bytes.
So if the number of cpus doubles, the number of memory consumption
will be 4 times. So for a system with large number of cpus, the
memory consumption goes up quickly with quadratic order.
For example, for 4KB percpu allocation, 128 cpus. The total memory
consumption will 4KB * 128 * 128 = 64MB. Things will become
worse if the number of cpus is bigger (e.g., 512, 1024, etc.)

In Commit 41a5db8d8161, the non-fix-size percpu memory allocation is
done in boot time, so for system with large number of cpus, the initial
percpu memory consumption is very visible. For example, for 128 cpu
system, the total percpu memory allocation will be at least
(16 + 32 + 64 + 96 + 128 + 196 + 256 + 512 + 1024 + 2048 + 4096)
  * 128 * 128 = ~138MB.
which is pretty big. It will be even bigger for larger number of cpus.

Note that the current prefill also allocates 4 entries if the unit size
is less than 256. So on top of 138MB memory consumption, this will
add more consumption with
3 * (16 + 32 + 64 + 96 + 128 + 196 + 256) * 128 * 128 = ~38MB.
Next patch will try to reduce this memory consumption.

Later on, Commit 1fda5bb66ad8 ("bpf: Do not allocate percpu memory
at init stage") moved the non-fix-size percpu memory allocation
to bpf verificaiton stage. Once a particular bpf_percpu_obj_new()
is called by bpf program, the memory allocator will try to fill in
the cache with all sizes, causing the same amount of percpu memory
consumption as in the boot stage.

To reduce the initial percpu memory consumption for non-fix-size
percpu memory allocation, instead of filling the cache with all
supported allocation sizes, this patch intends to fill the cache
only for the requested size. As typically users will not use large
percpu data structure, this can save memory significantly.
For example, the allocation size is 64 bytes with 128 cpus.
Then total percpu memory amount will be 64 * 128 * 128 = 1MB,
much less than previous 138MB.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Acked-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/r/20231222031745.1289082-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf_mem_alloc.h |  7 ++++++
 kernel/bpf/memalloc.c         | 57 ++++++++++++++++++++++++++++++++++++++++++-
 kernel/bpf/verifier.c         | 37 +++++++++++++++++-----------
 3 files changed, 86 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h
index acef8c808599..aaf004d94322 100644
--- a/include/linux/bpf_mem_alloc.h
+++ b/include/linux/bpf_mem_alloc.h
@@ -22,8 +22,15 @@ struct bpf_mem_alloc {
  * 'size = 0' is for bpf_mem_alloc which manages many fixed-size objects.
  * Alloc and free are done with bpf_mem_{alloc,free}() and the size of
  * the returned object is given by the size argument of bpf_mem_alloc().
+ * If percpu equals true, error will be returned in order to avoid
+ * large memory consumption and the below bpf_mem_alloc_percpu_unit_init()
+ * should be used to do on-demand per-cpu allocation for each size.
  */
 int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu);
+/* Initialize a non-fix-size percpu memory allocator */
+int bpf_mem_alloc_percpu_init(struct bpf_mem_alloc *ma, struct obj_cgroup *objcg);
+/* The percpu allocation with a specific unit size. */
+int bpf_mem_alloc_percpu_unit_init(struct bpf_mem_alloc *ma, int size);
 void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma);
 
 /* kmalloc/kfree equivalent: */
diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 4a21050f0359..f71da07eb8a0 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -121,6 +121,8 @@ struct bpf_mem_caches {
 	struct bpf_mem_cache cache[NUM_CACHES];
 };
 
+static const u16 sizes[NUM_CACHES] = {96, 192, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096};
+
 static struct llist_node notrace *__llist_del_first(struct llist_head *head)
 {
 	struct llist_node *entry, *next;
@@ -499,12 +501,14 @@ static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
  */
 int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 {
-	static u16 sizes[NUM_CACHES] = {96, 192, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096};
 	struct bpf_mem_caches *cc, __percpu *pcc;
 	struct bpf_mem_cache *c, __percpu *pc;
 	struct obj_cgroup *objcg = NULL;
 	int cpu, i, unit_size, percpu_size = 0;
 
+	if (percpu && size == 0)
+		return -EINVAL;
+
 	/* room for llist_node and per-cpu pointer */
 	if (percpu)
 		percpu_size = LLIST_NODE_SZ + sizeof(void *);
@@ -524,6 +528,7 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 			objcg = get_obj_cgroup_from_current();
 #endif
 		ma->objcg = objcg;
+
 		for_each_possible_cpu(cpu) {
 			c = per_cpu_ptr(pc, cpu);
 			c->unit_size = unit_size;
@@ -562,6 +567,56 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 	return 0;
 }
 
+int bpf_mem_alloc_percpu_init(struct bpf_mem_alloc *ma, struct obj_cgroup *objcg)
+{
+	struct bpf_mem_caches __percpu *pcc;
+
+	pcc = __alloc_percpu_gfp(sizeof(struct bpf_mem_caches), 8, GFP_KERNEL);
+	if (!pcc)
+		return -ENOMEM;
+
+	ma->caches = pcc;
+	ma->objcg = objcg;
+	ma->percpu = true;
+	return 0;
+}
+
+int bpf_mem_alloc_percpu_unit_init(struct bpf_mem_alloc *ma, int size)
+{
+	struct bpf_mem_caches *cc, __percpu *pcc;
+	int cpu, i, unit_size, percpu_size;
+	struct obj_cgroup *objcg;
+	struct bpf_mem_cache *c;
+
+	i = bpf_mem_cache_idx(size);
+	if (i < 0)
+		return -EINVAL;
+
+	/* room for llist_node and per-cpu pointer */
+	percpu_size = LLIST_NODE_SZ + sizeof(void *);
+
+	unit_size = sizes[i];
+	objcg = ma->objcg;
+	pcc = ma->caches;
+
+	for_each_possible_cpu(cpu) {
+		cc = per_cpu_ptr(pcc, cpu);
+		c = &cc->cache[i];
+		if (cpu == 0 && c->unit_size)
+			break;
+
+		c->unit_size = unit_size;
+		c->objcg = objcg;
+		c->percpu_size = percpu_size;
+		c->tgt = c;
+
+		init_refill_work(c);
+		prefill_mem_cache(c, cpu);
+	}
+
+	return 0;
+}
+
 static void drain_mem_cache(struct bpf_mem_cache *c)
 {
 	bool percpu = !!c->percpu_size;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index d4e31f61de0e..e9699a2cfe4f 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -12139,20 +12139,6 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 				if (meta.func_id == special_kfunc_list[KF_bpf_obj_new_impl] && !bpf_global_ma_set)
 					return -ENOMEM;
 
-				if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) {
-					if (!bpf_global_percpu_ma_set) {
-						mutex_lock(&bpf_percpu_ma_lock);
-						if (!bpf_global_percpu_ma_set) {
-							err = bpf_mem_alloc_init(&bpf_global_percpu_ma, 0, true);
-							if (!err)
-								bpf_global_percpu_ma_set = true;
-						}
-						mutex_unlock(&bpf_percpu_ma_lock);
-						if (err)
-							return err;
-					}
-				}
-
 				if (((u64)(u32)meta.arg_constant.value) != meta.arg_constant.value) {
 					verbose(env, "local type ID argument must be in range [0, U32_MAX]\n");
 					return -EINVAL;
@@ -12173,6 +12159,29 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 					return -EINVAL;
 				}
 
+				if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) {
+					if (!bpf_global_percpu_ma_set) {
+						mutex_lock(&bpf_percpu_ma_lock);
+						if (!bpf_global_percpu_ma_set) {
+							/* Charge memory allocated with bpf_global_percpu_ma to
+							 * root memcg. The obj_cgroup for root memcg is NULL.
+							 */
+							err = bpf_mem_alloc_percpu_init(&bpf_global_percpu_ma, NULL);
+							if (!err)
+								bpf_global_percpu_ma_set = true;
+						}
+						mutex_unlock(&bpf_percpu_ma_lock);
+						if (err)
+							return err;
+					}
+
+					mutex_lock(&bpf_percpu_ma_lock);
+					err = bpf_mem_alloc_percpu_unit_init(&bpf_global_percpu_ma, ret_t->size);
+					mutex_unlock(&bpf_percpu_ma_lock);
+					if (err)
+						return err;
+				}
+
 				struct_meta = btf_find_struct_meta(ret_btf, ret_btf_id);
 				if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) {
 					if (!__btf_type_is_scalar_struct(env, ret_btf, ret_t, 0)) {
-- 
cgit v1.2.3


From 5e5401d6612ef599ad45785b941eebda7effc90f Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 4 Jan 2024 09:47:36 +0000
Subject: net: phylink: move phylink_pcs_neg_mode() into phylink.c

Move phylink_pcs_neg_mode() from the header file into the .c file since
nothing should be using it.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phylink.c | 66 +++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/phylink.h   | 66 -----------------------------------------------
 2 files changed, 66 insertions(+), 66 deletions(-)

(limited to 'include')

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 3d25a4a6212b..a816391add12 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -1074,6 +1074,72 @@ static void phylink_pcs_an_restart(struct phylink *pl)
 		pl->pcs->ops->pcs_an_restart(pl->pcs);
 }
 
+/**
+ * phylink_pcs_neg_mode() - helper to determine PCS inband mode
+ * @mode: one of %MLO_AN_FIXED, %MLO_AN_PHY, %MLO_AN_INBAND.
+ * @interface: interface mode to be used
+ * @advertising: adertisement ethtool link mode mask
+ *
+ * Determines the negotiation mode to be used by the PCS, and returns
+ * one of:
+ *
+ * - %PHYLINK_PCS_NEG_NONE: interface mode does not support inband
+ * - %PHYLINK_PCS_NEG_OUTBAND: an out of band mode (e.g. reading the PHY)
+ *   will be used.
+ * - %PHYLINK_PCS_NEG_INBAND_DISABLED: inband mode selected but autoneg
+ *   disabled
+ * - %PHYLINK_PCS_NEG_INBAND_ENABLED: inband mode selected and autoneg enabled
+ *
+ * Note: this is for cases where the PCS itself is involved in negotiation
+ * (e.g. Clause 37, SGMII and similar) not Clause 73.
+ */
+static unsigned int phylink_pcs_neg_mode(unsigned int mode,
+					 phy_interface_t interface,
+					 const unsigned long *advertising)
+{
+	unsigned int neg_mode;
+
+	switch (interface) {
+	case PHY_INTERFACE_MODE_SGMII:
+	case PHY_INTERFACE_MODE_QSGMII:
+	case PHY_INTERFACE_MODE_QUSGMII:
+	case PHY_INTERFACE_MODE_USXGMII:
+		/* These protocols are designed for use with a PHY which
+		 * communicates its negotiation result back to the MAC via
+		 * inband communication. Note: there exist PHYs that run
+		 * with SGMII but do not send the inband data.
+		 */
+		if (!phylink_autoneg_inband(mode))
+			neg_mode = PHYLINK_PCS_NEG_OUTBAND;
+		else
+			neg_mode = PHYLINK_PCS_NEG_INBAND_ENABLED;
+		break;
+
+	case PHY_INTERFACE_MODE_1000BASEX:
+	case PHY_INTERFACE_MODE_2500BASEX:
+		/* 1000base-X is designed for use media-side for Fibre
+		 * connections, and thus the Autoneg bit needs to be
+		 * taken into account. We also do this for 2500base-X
+		 * as well, but drivers may not support this, so may
+		 * need to override this.
+		 */
+		if (!phylink_autoneg_inband(mode))
+			neg_mode = PHYLINK_PCS_NEG_OUTBAND;
+		else if (linkmode_test_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
+					   advertising))
+			neg_mode = PHYLINK_PCS_NEG_INBAND_ENABLED;
+		else
+			neg_mode = PHYLINK_PCS_NEG_INBAND_DISABLED;
+		break;
+
+	default:
+		neg_mode = PHYLINK_PCS_NEG_NONE;
+		break;
+	}
+
+	return neg_mode;
+}
+
 static void phylink_major_config(struct phylink *pl, bool restart,
 				  const struct phylink_link_state *state)
 {
diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index 875439ab45de..d589f89c612c 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -98,72 +98,6 @@ static inline bool phylink_autoneg_inband(unsigned int mode)
 	return mode == MLO_AN_INBAND;
 }
 
-/**
- * phylink_pcs_neg_mode() - helper to determine PCS inband mode
- * @mode: one of %MLO_AN_FIXED, %MLO_AN_PHY, %MLO_AN_INBAND.
- * @interface: interface mode to be used
- * @advertising: adertisement ethtool link mode mask
- *
- * Determines the negotiation mode to be used by the PCS, and returns
- * one of:
- *
- * - %PHYLINK_PCS_NEG_NONE: interface mode does not support inband
- * - %PHYLINK_PCS_NEG_OUTBAND: an out of band mode (e.g. reading the PHY)
- *   will be used.
- * - %PHYLINK_PCS_NEG_INBAND_DISABLED: inband mode selected but autoneg
- *   disabled
- * - %PHYLINK_PCS_NEG_INBAND_ENABLED: inband mode selected and autoneg enabled
- *
- * Note: this is for cases where the PCS itself is involved in negotiation
- * (e.g. Clause 37, SGMII and similar) not Clause 73.
- */
-static inline unsigned int phylink_pcs_neg_mode(unsigned int mode,
-						phy_interface_t interface,
-						const unsigned long *advertising)
-{
-	unsigned int neg_mode;
-
-	switch (interface) {
-	case PHY_INTERFACE_MODE_SGMII:
-	case PHY_INTERFACE_MODE_QSGMII:
-	case PHY_INTERFACE_MODE_QUSGMII:
-	case PHY_INTERFACE_MODE_USXGMII:
-		/* These protocols are designed for use with a PHY which
-		 * communicates its negotiation result back to the MAC via
-		 * inband communication. Note: there exist PHYs that run
-		 * with SGMII but do not send the inband data.
-		 */
-		if (!phylink_autoneg_inband(mode))
-			neg_mode = PHYLINK_PCS_NEG_OUTBAND;
-		else
-			neg_mode = PHYLINK_PCS_NEG_INBAND_ENABLED;
-		break;
-
-	case PHY_INTERFACE_MODE_1000BASEX:
-	case PHY_INTERFACE_MODE_2500BASEX:
-		/* 1000base-X is designed for use media-side for Fibre
-		 * connections, and thus the Autoneg bit needs to be
-		 * taken into account. We also do this for 2500base-X
-		 * as well, but drivers may not support this, so may
-		 * need to override this.
-		 */
-		if (!phylink_autoneg_inband(mode))
-			neg_mode = PHYLINK_PCS_NEG_OUTBAND;
-		else if (linkmode_test_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
-					   advertising))
-			neg_mode = PHYLINK_PCS_NEG_INBAND_ENABLED;
-		else
-			neg_mode = PHYLINK_PCS_NEG_INBAND_DISABLED;
-		break;
-
-	default:
-		neg_mode = PHYLINK_PCS_NEG_NONE;
-		break;
-	}
-
-	return neg_mode;
-}
-
 /**
  * struct phylink_link_state - link state structure
  * @advertising: ethtool bitmask containing advertised link modes
-- 
cgit v1.2.3


From 040a82be54c09a72162a3db2f5cd2ba289c0f224 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 13 Oct 2023 12:26:31 +0100
Subject: netfs: Rearrange netfs_io_subrequest to put request pointer first

Rearrange the netfs_io_subrequest struct to put the netfs_io_request
pointer (rreq) first.  This then allows netfs_io_subrequest to be put in a
union with a pointer to a wrapper around netfs_io_request.  This will be
useful in the future for cifs and maybe ceph.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Steve French <sfrench@samba.org>
cc: Shyam Prasad N <nspmangalore@gmail.com>
cc: Rohith Surabattula <rohiths.msft@gmail.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cifs@vger.kernel.org
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 include/linux/netfs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 852956aa3c4b..d3bac60fcd6f 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -204,8 +204,8 @@ struct netfs_cache_resources {
  * the pages it points to can be relied on to exist for the duration.
  */
 struct netfs_io_subrequest {
-	struct work_struct	work;
 	struct netfs_io_request *rreq;		/* Supervising I/O request */
+	struct work_struct	work;
 	struct list_head	rreq_link;	/* Link in rreq->subrequests */
 	struct iov_iter		io_iter;	/* Iterator for this subrequest */
 	loff_t			start;		/* Where to start the I/O */
-- 
cgit v1.2.3


From 51088e5cc241178ccd6db2dd6d161dc8df32057d Mon Sep 17 00:00:00 2001
From: Naresh Solanki <naresh.solanki@9elements.com>
Date: Thu, 4 Jan 2024 15:43:15 +0530
Subject: uapi: regulator: Fix typo

Fix minor typo.

Signed-off-by: Naresh Solanki <naresh.solanki@9elements.com>
Link: https://msgid.link/r/20240104101315.521301-1-naresh.solanki@9elements.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/uapi/regulator/regulator.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/regulator/regulator.h b/include/uapi/regulator/regulator.h
index d2b5612198b6..71bf71a22e7f 100644
--- a/include/uapi/regulator/regulator.h
+++ b/include/uapi/regulator/regulator.h
@@ -52,7 +52,7 @@
 /*
  * Following notifications should be emitted only if detected condition
  * is such that the HW is likely to still be working but consumers should
- * take a recovery action to prevent problems esacalating into errors.
+ * take a recovery action to prevent problems escalating into errors.
  */
 #define REGULATOR_EVENT_UNDER_VOLTAGE_WARN	0x2000
 #define REGULATOR_EVENT_OVER_CURRENT_WARN	0x4000
-- 
cgit v1.2.3


From f36be9ce8146faabdbbf74ee0499edb2039c53a5 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 19 Dec 2023 14:13:10 +0100
Subject: EDAC: constantify the struct bus_type usage

In many places in the edac code, struct bus_type pointers are passed
around and then eventually sent to the driver core, which can handle a
constant pointer.  So constantify all of the edac usage of these as well
because the data in them is never modified by the edac code either.

Cc: Borislav Petkov <bp@alien8.de>
Cc: Tony Luck <tony.luck@intel.com>
Cc: James Morse <james.morse@arm.com>
Cc: Mauro Carvalho Chehab <mchehab@kernel.org>
Cc: Robert Richter <rric@kernel.org>
Cc:  <linux-edac@vger.kernel.org>
Link: https://lore.kernel.org/r/2023121909-tribute-punctuate-4b22@gregkh
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/edac/edac_device.h       | 2 +-
 drivers/edac/edac_device_sysfs.c | 2 +-
 drivers/edac/edac_module.c       | 4 ++--
 drivers/edac/edac_pci_sysfs.c    | 2 +-
 include/linux/edac.h             | 4 ++--
 5 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/edac/edac_device.h b/drivers/edac/edac_device.h
index 3f44e6b9d387..7db22a4c83ef 100644
--- a/drivers/edac/edac_device.h
+++ b/drivers/edac/edac_device.h
@@ -176,7 +176,7 @@ struct edac_device_ctl_info {
 	struct edac_dev_sysfs_attribute *sysfs_attributes;
 
 	/* pointer to main 'edac' subsys in sysfs */
-	struct bus_type *edac_subsys;
+	const struct bus_type *edac_subsys;
 
 	/* the internal state of this controller instance */
 	int op_state;
diff --git a/drivers/edac/edac_device_sysfs.c b/drivers/edac/edac_device_sysfs.c
index 010c26be5846..237a542e045a 100644
--- a/drivers/edac/edac_device_sysfs.c
+++ b/drivers/edac/edac_device_sysfs.c
@@ -229,7 +229,7 @@ static struct kobj_type ktype_device_ctrl = {
 int edac_device_register_sysfs_main_kobj(struct edac_device_ctl_info *edac_dev)
 {
 	struct device *dev_root;
-	struct bus_type *edac_subsys;
+	const struct bus_type *edac_subsys;
 	int err = -ENODEV;
 
 	edac_dbg(1, "\n");
diff --git a/drivers/edac/edac_module.c b/drivers/edac/edac_module.c
index 32a931d0cb71..1c9f62382666 100644
--- a/drivers/edac/edac_module.c
+++ b/drivers/edac/edac_module.c
@@ -67,7 +67,7 @@ char *edac_op_state_to_string(int opstate)
  * sysfs object: /sys/devices/system/edac
  *	need to export to other files
  */
-static struct bus_type edac_subsys = {
+static const struct bus_type edac_subsys = {
 	.name = "edac",
 	.dev_name = "edac",
 };
@@ -90,7 +90,7 @@ static void edac_subsys_exit(void)
 }
 
 /* return pointer to the 'edac' node in sysfs */
-struct bus_type *edac_get_sysfs_subsys(void)
+const struct bus_type *edac_get_sysfs_subsys(void)
 {
 	return &edac_subsys;
 }
diff --git a/drivers/edac/edac_pci_sysfs.c b/drivers/edac/edac_pci_sysfs.c
index 287cc51dbc86..e823e4da086a 100644
--- a/drivers/edac/edac_pci_sysfs.c
+++ b/drivers/edac/edac_pci_sysfs.c
@@ -338,7 +338,7 @@ static struct kobj_type ktype_edac_pci_main_kobj = {
 static int edac_pci_main_kobj_setup(void)
 {
 	int err = -ENODEV;
-	struct bus_type *edac_subsys;
+	const struct bus_type *edac_subsys;
 	struct device *dev_root;
 
 	edac_dbg(0, "\n");
diff --git a/include/linux/edac.h b/include/linux/edac.h
index fa4bda2a70f6..ccaf2ae0801d 100644
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -30,7 +30,7 @@ struct device;
 
 extern int edac_op_state;
 
-struct bus_type *edac_get_sysfs_subsys(void);
+const struct bus_type *edac_get_sysfs_subsys(void);
 
 static inline void opstate_init(void)
 {
@@ -492,7 +492,7 @@ struct edac_raw_error_desc {
  */
 struct mem_ctl_info {
 	struct device			dev;
-	struct bus_type			*bus;
+	const struct bus_type		*bus;
 
 	struct list_head link;	/* for global list of mem_ctl_info structs */
 
-- 
cgit v1.2.3


From db2292b01b799e926abfdbd6fafa1f27f0d0e457 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 19 Dec 2023 15:07:23 +0100
Subject: PM: clk: make pm_clk_add_notifier() take a const pointer

The driver core wants to work with const struct bus_type, so there's no
reason that pm_clk_add_notifier() should not also do the same thing,
considering that it just passes the pointer off to the driver core which
is expecting a const *.

Cc: Rafael J. Wysocki <rafael@kernel.org>
Link: https://lore.kernel.org/r/2023121922-triumph-exploit-f545@gregkh
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/power/clock_ops.c | 2 +-
 include/linux/pm_clock.h       | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c
index 4110c19c08dc..e18ba676cdf6 100644
--- a/drivers/base/power/clock_ops.c
+++ b/drivers/base/power/clock_ops.c
@@ -793,7 +793,7 @@ static int pm_clk_notify(struct notifier_block *nb,
  * the remaining members of @clknb should be populated prior to calling this
  * routine.
  */
-void pm_clk_add_notifier(struct bus_type *bus,
+void pm_clk_add_notifier(const struct bus_type *bus,
 				 struct pm_clk_notifier_block *clknb)
 {
 	if (!bus || !clknb)
diff --git a/include/linux/pm_clock.h b/include/linux/pm_clock.h
index ada3a0ab10bf..68669ce18720 100644
--- a/include/linux/pm_clock.h
+++ b/include/linux/pm_clock.h
@@ -91,10 +91,10 @@ static inline int devm_pm_clk_create(struct device *dev)
 #endif
 
 #ifdef CONFIG_HAVE_CLK
-extern void pm_clk_add_notifier(struct bus_type *bus,
+extern void pm_clk_add_notifier(const struct bus_type *bus,
 					struct pm_clk_notifier_block *clknb);
 #else
-static inline void pm_clk_add_notifier(struct bus_type *bus,
+static inline void pm_clk_add_notifier(const struct bus_type *bus,
 					struct pm_clk_notifier_block *clknb)
 {
 }
-- 
cgit v1.2.3


From e76933a9bfa9b7f28a387f2e13cb3e689adc200d Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 19 Dec 2023 15:06:19 +0100
Subject: maple: make maple_bus_type static and const

There is no need to export maple_bus_type as no one uses it outside of
maple.c, so make it static, AND make it const as it can be read-only as
no one modifies it.

Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: Rich Felker <dalias@libc.org>
Cc: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Cc: <linux-sh@vger.kernel.org>
Link: https://lore.kernel.org/r/2023121918-rejoicing-frostlike-d976@gregkh
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/sh/maple/maple.c | 4 ++--
 include/linux/maple.h    | 1 -
 2 files changed, 2 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/sh/maple/maple.c b/drivers/sh/maple/maple.c
index e05473c5c267..16018009a5a6 100644
--- a/drivers/sh/maple/maple.c
+++ b/drivers/sh/maple/maple.c
@@ -59,6 +59,7 @@ struct maple_device_specify {
 static bool checked[MAPLE_PORTS];
 static bool empty[MAPLE_PORTS];
 static struct maple_device *baseunits[MAPLE_PORTS];
+static const struct bus_type maple_bus_type;
 
 /**
  * maple_driver_register - register a maple driver
@@ -773,11 +774,10 @@ static struct maple_driver maple_unsupported_device = {
 /*
  * maple_bus_type - core maple bus structure
  */
-struct bus_type maple_bus_type = {
+static const struct bus_type maple_bus_type = {
 	.name = "maple",
 	.match = maple_match_bus_driver,
 };
-EXPORT_SYMBOL_GPL(maple_bus_type);
 
 static struct device maple_bus = {
 	.init_name = "maple",
diff --git a/include/linux/maple.h b/include/linux/maple.h
index 9b140272ee16..9aae44efcfd4 100644
--- a/include/linux/maple.h
+++ b/include/linux/maple.h
@@ -5,7 +5,6 @@
 #include <mach/maple.h>
 
 struct device;
-extern struct bus_type maple_bus_type;
 
 /* Maple Bus command and response codes */
 enum maple_code {
-- 
cgit v1.2.3


From 86438841e48f6361f0a6a04805b7d7813738761f Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 19 Dec 2023 14:41:42 +0100
Subject: dma-debug: make dma_debug_add_bus take a const pointer

The driver core now can handle a const struct bus_type pointer, and the
dma_debug_add_bus() call just passes on the pointer give to it to the
driver core, so make this pointer const as well to allow everyone to use
read-only struct bus_type pointers going forward.

Cc: Christoph Hellwig <hch@lst.de>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc:  <iommu@lists.linux.dev>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/2023121941-dejected-nugget-681e@gregkh
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/dma-map-ops.h | 4 ++--
 kernel/dma/debug.c          | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index f2fc203fb8a1..e401f824a007 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -443,10 +443,10 @@ static inline void arch_teardown_dma_ops(struct device *dev)
 #endif /* CONFIG_ARCH_HAS_TEARDOWN_DMA_OPS */
 
 #ifdef CONFIG_DMA_API_DEBUG
-void dma_debug_add_bus(struct bus_type *bus);
+void dma_debug_add_bus(const struct bus_type *bus);
 void debug_dma_dump_mappings(struct device *dev);
 #else
-static inline void dma_debug_add_bus(struct bus_type *bus)
+static inline void dma_debug_add_bus(const struct bus_type *bus)
 {
 }
 static inline void debug_dma_dump_mappings(struct device *dev)
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index 3de494375b7b..1a5c86dd87d5 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -876,7 +876,7 @@ static int dma_debug_device_change(struct notifier_block *nb, unsigned long acti
 	return 0;
 }
 
-void dma_debug_add_bus(struct bus_type *bus)
+void dma_debug_add_bus(const struct bus_type *bus)
 {
 	struct notifier_block *nb;
 
-- 
cgit v1.2.3


From b5b0774d53bb81bddbf8c609b3f183d4af6e91da Mon Sep 17 00:00:00 2001
From: Basavaraj Natikar <Basavaraj.Natikar@amd.com>
Date: Wed, 20 Dec 2023 12:30:41 +0530
Subject: HID: amd_sfh: Add a new interface for exporting HPD data

AMDSFH has information about the User presence information via the Human
Presence Detection (HPD) sensor which is part of the AMD sensor fusion hub.

Add a new interface to export this information, where other drivers like
PMF can use this information to enhance user experiences.

Link: https://lore.kernel.org/all/ad064333-48a4-4cfa-9428-69e8a7c44667@redhat.com/
Co-developed-by: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Signed-off-by: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Signed-off-by: Basavaraj Natikar <Basavaraj.Natikar@amd.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/amd-sfh-hid/amd_sfh_common.h           |  5 +++
 drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c      | 14 +++++++
 drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_interface.c | 37 +++++++++++++++++
 drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_interface.h |  1 +
 include/linux/amd-pmf-io.h                         | 46 ++++++++++++++++++++++
 5 files changed, 103 insertions(+)
 create mode 100644 include/linux/amd-pmf-io.h

(limited to 'include')

diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_common.h b/drivers/hid/amd-sfh-hid/amd_sfh_common.h
index 2643bb14fee2..cd57037bf217 100644
--- a/drivers/hid/amd-sfh-hid/amd_sfh_common.h
+++ b/drivers/hid/amd-sfh-hid/amd_sfh_common.h
@@ -37,6 +37,10 @@ struct amd_mp2_sensor_info {
 	dma_addr_t dma_address;
 };
 
+struct sfh_dev_status {
+	bool is_hpd_present;
+};
+
 struct amd_mp2_dev {
 	struct pci_dev *pdev;
 	struct amdtp_cl_data *cl_data;
@@ -47,6 +51,7 @@ struct amd_mp2_dev {
 	struct amd_input_data in_data;
 	/* mp2 active control status */
 	u32 mp2_acs;
+	struct sfh_dev_status dev_en;
 };
 
 struct amd_mp2_ops {
diff --git a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c
index e9c6413af24a..0351b0fd394a 100644
--- a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c
+++ b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c
@@ -73,6 +73,12 @@ static int amd_sfh_hid_client_deinit(struct amd_mp2_dev *privdata)
 	int i, status;
 
 	for (i = 0; i < cl_data->num_hid_devices; i++) {
+		switch (cl_data->sensor_idx[i]) {
+		case HPD_IDX:
+			privdata->dev_en.is_hpd_present = false;
+			break;
+		}
+
 		if (cl_data->sensor_sts[i] == SENSOR_ENABLED) {
 			privdata->mp2_ops->stop(privdata, cl_data->sensor_idx[i]);
 			status = amd_sfh_wait_for_response
@@ -178,6 +184,11 @@ static int amd_sfh1_1_hid_client_init(struct amd_mp2_dev *privdata)
 			rc = amdtp_hid_probe(i, cl_data);
 			if (rc)
 				goto cleanup;
+			switch (cl_data->sensor_idx[i]) {
+			case HPD_IDX:
+				privdata->dev_en.is_hpd_present = true;
+				break;
+			}
 		}
 		dev_dbg(dev, "sid 0x%x (%s) status 0x%x\n",
 			cl_data->sensor_idx[i], get_sensor_name(cl_data->sensor_idx[i]),
@@ -259,6 +270,7 @@ static void amd_mp2_pci_remove(void *privdata)
 {
 	struct amd_mp2_dev *mp2 = privdata;
 
+	sfh_deinit_emp2();
 	amd_sfh_hid_client_deinit(privdata);
 	mp2->mp2_ops->stop_all(mp2);
 	pci_intx(mp2->pdev, false);
@@ -311,12 +323,14 @@ int amd_sfh1_1_init(struct amd_mp2_dev *mp2)
 
 	rc = amd_sfh_irq_init(mp2);
 	if (rc) {
+		sfh_deinit_emp2();
 		dev_err(dev, "amd_sfh_irq_init failed\n");
 		return rc;
 	}
 
 	rc = amd_sfh1_1_hid_client_init(mp2);
 	if (rc) {
+		sfh_deinit_emp2();
 		dev_err(dev, "amd_sfh1_1_hid_client_init failed\n");
 		return rc;
 	}
diff --git a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_interface.c b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_interface.c
index 4f81ef2d4f56..197b828fc6a0 100644
--- a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_interface.c
+++ b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_interface.c
@@ -7,11 +7,14 @@
  *
  * Author: Basavaraj Natikar <Basavaraj.Natikar@amd.com>
  */
+#include <linux/amd-pmf-io.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
 #include <linux/iopoll.h>
 
 #include "amd_sfh_interface.h"
 
+static struct amd_mp2_dev *emp2;
+
 static int amd_sfh_wait_response(struct amd_mp2_dev *mp2, u8 sid, u32 cmd_id)
 {
 	struct sfh_cmd_response cmd_resp;
@@ -73,7 +76,41 @@ static struct amd_mp2_ops amd_sfh_ops = {
 	.response = amd_sfh_wait_response,
 };
 
+void sfh_deinit_emp2(void)
+{
+	emp2 = NULL;
+}
+
 void sfh_interface_init(struct amd_mp2_dev *mp2)
 {
 	mp2->mp2_ops = &amd_sfh_ops;
+	emp2 = mp2;
+}
+
+static int amd_sfh_hpd_info(u8 *user_present)
+{
+	struct hpd_status hpdstatus;
+
+	if (!user_present)
+		return -EINVAL;
+
+	if (!emp2 || !emp2->dev_en.is_hpd_present)
+		return -ENODEV;
+
+	hpdstatus.val = readl(emp2->mmio + AMD_C2P_MSG(4));
+	*user_present = hpdstatus.shpd.presence;
+
+	return 0;
+}
+
+int amd_get_sfh_info(struct amd_sfh_info *sfh_info, enum sfh_message_type op)
+{
+	if (sfh_info) {
+		switch (op) {
+		case MT_HPD:
+			return amd_sfh_hpd_info(&sfh_info->user_present);
+		}
+	}
+	return -EINVAL;
 }
+EXPORT_SYMBOL_GPL(amd_get_sfh_info);
diff --git a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_interface.h b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_interface.h
index 75267b0fec70..2c211d28764d 100644
--- a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_interface.h
+++ b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_interface.h
@@ -165,6 +165,7 @@ struct hpd_status {
 };
 
 void sfh_interface_init(struct amd_mp2_dev *mp2);
+void sfh_deinit_emp2(void);
 void amd_sfh1_1_set_desc_ops(struct amd_mp2_ops *mp2_ops);
 int amd_sfh_float_to_int(u32 flt32_val);
 #endif
diff --git a/include/linux/amd-pmf-io.h b/include/linux/amd-pmf-io.h
new file mode 100644
index 000000000000..5b6d29d36922
--- /dev/null
+++ b/include/linux/amd-pmf-io.h
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * AMD Platform Management Framework Interface
+ *
+ * Copyright (c) 2023, Advanced Micro Devices, Inc.
+ * All Rights Reserved.
+ *
+ * Authors: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
+ *          Basavaraj Natikar <Basavaraj.Natikar@amd.com>
+ */
+
+#ifndef AMD_PMF_IO_H
+#define AMD_PMF_IO_H
+
+#include <linux/types.h>
+
+/**
+ * enum sfh_message_type - Query the SFH message type
+ * @MT_HPD: Message ID to know the Human presence info from MP2 FW
+ */
+enum sfh_message_type {
+	MT_HPD,
+};
+
+/**
+ * enum sfh_hpd_info - Query the Human presence information
+ * @SFH_NOT_DETECTED: Check the HPD connection information from MP2 FW
+ * @SFH_USER_PRESENT: Check if the user is present from HPD sensor
+ * @SFH_USER_AWAY: Check if the user is away from HPD sensor
+ */
+enum sfh_hpd_info {
+	SFH_NOT_DETECTED,
+	SFH_USER_PRESENT,
+	SFH_USER_AWAY,
+};
+
+/**
+ * struct amd_sfh_info - get HPD sensor info from MP2 FW
+ * @user_present: Populates the user presence information
+ */
+struct amd_sfh_info {
+	u8 user_present;
+};
+
+int amd_get_sfh_info(struct amd_sfh_info *sfh_info, enum sfh_message_type op);
+#endif
-- 
cgit v1.2.3


From 584f35a3647d42980af495fc0bc5c51eb174aa35 Mon Sep 17 00:00:00 2001
From: Basavaraj Natikar <Basavaraj.Natikar@amd.com>
Date: Wed, 20 Dec 2023 12:30:42 +0530
Subject: HID: amd_sfh: Add a new interface for exporting ALS data

AMDSFH has information about the Ambient light via the Ambient
Light Sensor (ALS) which is part of the AMD sensor fusion hub.

Add a new interface to export this information, where other drivers like
PMF can use this information to enhance user experiences.

Link: https://lore.kernel.org/all/ad064333-48a4-4cfa-9428-69e8a7c44667@redhat.com/
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Co-developed-by: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Signed-off-by: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Signed-off-by: Basavaraj Natikar <Basavaraj.Natikar@amd.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/amd-sfh-hid/amd_sfh_common.h           |  1 +
 drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c      |  6 ++++++
 drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_interface.c | 22 ++++++++++++++++++++++
 include/linux/amd-pmf-io.h                         |  4 ++++
 4 files changed, 33 insertions(+)

(limited to 'include')

diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_common.h b/drivers/hid/amd-sfh-hid/amd_sfh_common.h
index cd57037bf217..a1950bc6e6ce 100644
--- a/drivers/hid/amd-sfh-hid/amd_sfh_common.h
+++ b/drivers/hid/amd-sfh-hid/amd_sfh_common.h
@@ -39,6 +39,7 @@ struct amd_mp2_sensor_info {
 
 struct sfh_dev_status {
 	bool is_hpd_present;
+	bool is_als_present;
 };
 
 struct amd_mp2_dev {
diff --git a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c
index 0351b0fd394a..9dbe6f4cb294 100644
--- a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c
+++ b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c
@@ -77,6 +77,9 @@ static int amd_sfh_hid_client_deinit(struct amd_mp2_dev *privdata)
 		case HPD_IDX:
 			privdata->dev_en.is_hpd_present = false;
 			break;
+		case ALS_IDX:
+			privdata->dev_en.is_als_present = false;
+			break;
 		}
 
 		if (cl_data->sensor_sts[i] == SENSOR_ENABLED) {
@@ -188,6 +191,9 @@ static int amd_sfh1_1_hid_client_init(struct amd_mp2_dev *privdata)
 			case HPD_IDX:
 				privdata->dev_en.is_hpd_present = true;
 				break;
+			case ALS_IDX:
+				privdata->dev_en.is_als_present = true;
+				break;
 			}
 		}
 		dev_dbg(dev, "sid 0x%x (%s) status 0x%x\n",
diff --git a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_interface.c b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_interface.c
index 197b828fc6a0..ae36312bc236 100644
--- a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_interface.c
+++ b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_interface.c
@@ -103,12 +103,34 @@ static int amd_sfh_hpd_info(u8 *user_present)
 	return 0;
 }
 
+static int amd_sfh_als_info(u32 *ambient_light)
+{
+	struct sfh_als_data als_data;
+	void __iomem *sensoraddr;
+
+	if (!ambient_light)
+		return -EINVAL;
+
+	if (!emp2 || !emp2->dev_en.is_als_present)
+		return -ENODEV;
+
+	sensoraddr = emp2->vsbase +
+		(ALS_IDX * SENSOR_DATA_MEM_SIZE_DEFAULT) +
+		OFFSET_SENSOR_DATA_DEFAULT;
+	memcpy_fromio(&als_data, sensoraddr, sizeof(struct sfh_als_data));
+	*ambient_light = amd_sfh_float_to_int(als_data.lux);
+
+	return 0;
+}
+
 int amd_get_sfh_info(struct amd_sfh_info *sfh_info, enum sfh_message_type op)
 {
 	if (sfh_info) {
 		switch (op) {
 		case MT_HPD:
 			return amd_sfh_hpd_info(&sfh_info->user_present);
+		case MT_ALS:
+			return amd_sfh_als_info(&sfh_info->ambient_light);
 		}
 	}
 	return -EINVAL;
diff --git a/include/linux/amd-pmf-io.h b/include/linux/amd-pmf-io.h
index 5b6d29d36922..b4f818205216 100644
--- a/include/linux/amd-pmf-io.h
+++ b/include/linux/amd-pmf-io.h
@@ -17,9 +17,11 @@
 /**
  * enum sfh_message_type - Query the SFH message type
  * @MT_HPD: Message ID to know the Human presence info from MP2 FW
+ * @MT_ALS: Message ID to know the Ambient light info from MP2 FW
  */
 enum sfh_message_type {
 	MT_HPD,
+	MT_ALS,
 };
 
 /**
@@ -36,9 +38,11 @@ enum sfh_hpd_info {
 
 /**
  * struct amd_sfh_info - get HPD sensor info from MP2 FW
+ * @ambient_light: Populates the ambient light information
  * @user_present: Populates the user presence information
  */
 struct amd_sfh_info {
+	u32 ambient_light;
 	u8 user_present;
 };
 
-- 
cgit v1.2.3


From 398aa9a7e77cf23c2a6f882ddd3dcd96f21771dc Mon Sep 17 00:00:00 2001
From: Manan Aurora <maurora@google.com>
Date: Tue, 31 Oct 2023 03:46:41 +0000
Subject: usb: dwc3: Support EBC feature of DWC_usb31

Support configuration and use of bulk endpoints in the so-called EBC
mode described in the DBC_usb31 databook (appendix E)

Added a bit fifo_mode to usb_ep to indicate to the UDC driver that a
specific endpoint is to operate in the EBC (or equivalent) mode when
enabled

Added macros for bits 15 and 14 of DEPCFG parameter 1 to indicate EBC
mode and write back behaviour. These bits will be set to 1 when
configuring an EBC endpoint as described in the programming guide

Signed-off-by: Manan Aurora <maurora@google.com>
Link: https://lore.kernel.org/r/20231031034641.660606-1-maurora@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/core.h    | 1 +
 drivers/usb/dwc3/gadget.c  | 6 ++++++
 drivers/usb/dwc3/gadget.h  | 2 ++
 include/linux/usb/gadget.h | 1 +
 4 files changed, 10 insertions(+)

(limited to 'include')

diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index e120611a5174..e3eea965e57b 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -376,6 +376,7 @@
 /* Global HWPARAMS4 Register */
 #define DWC3_GHWPARAMS4_HIBER_SCRATCHBUFS(n)	(((n) & (0x0f << 13)) >> 13)
 #define DWC3_MAX_HIBER_SCRATCHBUFS		15
+#define DWC3_EXT_BUFF_CONTROL		BIT(21)
 
 /* Global HWPARAMS6 Register */
 #define DWC3_GHWPARAMS6_BCSUPPORT		BIT(14)
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 88d8d589f014..c15e965ea95a 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -673,6 +673,12 @@ static int dwc3_gadget_set_ep_config(struct dwc3_ep *dep, unsigned int action)
 		params.param1 |= DWC3_DEPCFG_BINTERVAL_M1(bInterval_m1);
 	}
 
+	if (dep->endpoint.fifo_mode) {
+		if (!(dwc->hwparams.hwparams4 & DWC3_EXT_BUFF_CONTROL))
+			return -EINVAL;
+		params.param1 |= DWC3_DEPCFG_EBC_HWO_NOWB | DWC3_DEPCFG_USE_EBC;
+	}
+
 	return dwc3_send_gadget_ep_cmd(dep, DWC3_DEPCMD_SETEPCONFIG, &params);
 }
 
diff --git a/drivers/usb/dwc3/gadget.h b/drivers/usb/dwc3/gadget.h
index 55a56cf67d73..fd7a4e94397e 100644
--- a/drivers/usb/dwc3/gadget.h
+++ b/drivers/usb/dwc3/gadget.h
@@ -26,6 +26,8 @@ struct dwc3;
 #define DWC3_DEPCFG_XFER_NOT_READY_EN	BIT(10)
 #define DWC3_DEPCFG_FIFO_ERROR_EN	BIT(11)
 #define DWC3_DEPCFG_STREAM_EVENT_EN	BIT(13)
+#define DWC3_DEPCFG_EBC_HWO_NOWB	BIT(14)
+#define DWC3_DEPCFG_USE_EBC		BIT(15)
 #define DWC3_DEPCFG_BINTERVAL_M1(n)	(((n) & 0xff) << 16)
 #define DWC3_DEPCFG_STREAM_CAPABLE	BIT(24)
 #define DWC3_DEPCFG_EP_NUMBER(n)	(((n) & 0x1f) << 25)
diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h
index 6532beb587b1..a771ccc038ac 100644
--- a/include/linux/usb/gadget.h
+++ b/include/linux/usb/gadget.h
@@ -236,6 +236,7 @@ struct usb_ep {
 	unsigned		max_streams:16;
 	unsigned		mult:2;
 	unsigned		maxburst:5;
+	unsigned		fifo_mode:1;
 	u8			address;
 	const struct usb_endpoint_descriptor	*desc;
 	const struct usb_ss_ep_comp_descriptor	*comp_desc;
-- 
cgit v1.2.3


From 49a78b05d5ca1e23fd737747a8757b8bdc319b30 Mon Sep 17 00:00:00 2001
From: Yajun Deng <yajun.deng@linux.dev>
Date: Thu, 4 Jan 2024 11:28:22 +0800
Subject: USB: core: Use device_driver directly in struct usb_driver and
 usb_device_driver

There is usbdrv_wrap in struct usb_driver and usb_device_driver, it
contains device_driver and for_devices. for_devices is used to
distinguish between device drivers and interface drivers.

Like the is_usb_device(), it tests the type of the device. We can test
that if the probe of device_driver is equal to usb_probe_device in
is_usb_device_driver(), and then the struct usbdrv_wrap is no longer
needed.

Clean up struct usbdrv_wrap, use device_driver directly in struct
usb_driver and usb_device_driver. This makes the code cleaner.

Signed-off-by: Yajun Deng <yajun.deng@linux.dev>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Link: https://lore.kernel.org/r/20240104032822.1896596-1-yajun.deng@linux.dev
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bluetooth/btusb.c                          |  6 +--
 drivers/net/can/usb/peak_usb/pcan_usb_core.c       |  2 +-
 .../net/wireless/broadcom/brcm80211/brcmfmac/usb.c |  2 +-
 drivers/net/wireless/marvell/mwifiex/usb.c         |  2 +-
 drivers/usb/core/driver.c                          | 59 ++++++++++++----------
 drivers/usb/core/usb.c                             |  2 +-
 drivers/usb/core/usb.h                             |  8 +--
 drivers/usb/misc/onboard_usb_hub.c                 |  2 +-
 drivers/usb/serial/bus.c                           |  2 +-
 drivers/usb/serial/usb-serial.c                    |  2 +-
 drivers/usb/storage/uas.c                          |  2 +-
 drivers/usb/usbip/stub_main.c                      |  8 +--
 include/linux/usb.h                                | 24 +++------
 13 files changed, 53 insertions(+), 68 deletions(-)

(limited to 'include')

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index b8e9de887b5d..02b3b1825403 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -4790,10 +4790,8 @@ static struct usb_driver btusb_driver = {
 	.disable_hub_initiated_lpm = 1,
 
 #ifdef CONFIG_DEV_COREDUMP
-	.drvwrap = {
-		.driver = {
-			.coredump = btusb_coredump,
-		},
+	.driver = {
+		.coredump = btusb_coredump,
 	},
 #endif
 };
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
index 24ad9f593a77..1efa39e134f4 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
@@ -1143,7 +1143,7 @@ static void __exit peak_usb_exit(void)
 	int err;
 
 	/* last chance do send any synchronous commands here */
-	err = driver_for_each_device(&peak_usb_driver.drvwrap.driver, NULL,
+	err = driver_for_each_device(&peak_usb_driver.driver, NULL,
 				     NULL, peak_usb_do_device_exit);
 	if (err)
 		pr_err("%s: failed to stop all can devices (err %d)\n",
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c
index 2178675ae1a4..0ccf735316c2 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c
@@ -1581,7 +1581,7 @@ static int brcmf_usb_reset_device(struct device *dev, void *notused)
 
 void brcmf_usb_exit(void)
 {
-	struct device_driver *drv = &brcmf_usbdrvr.drvwrap.driver;
+	struct device_driver *drv = &brcmf_usbdrvr.driver;
 	int ret;
 
 	brcmf_dbg(USB, "Enter\n");
diff --git a/drivers/net/wireless/marvell/mwifiex/usb.c b/drivers/net/wireless/marvell/mwifiex/usb.c
index d3ab9572e711..515e6db410f2 100644
--- a/drivers/net/wireless/marvell/mwifiex/usb.c
+++ b/drivers/net/wireless/marvell/mwifiex/usb.c
@@ -687,7 +687,7 @@ static struct usb_driver mwifiex_usb_driver = {
 	.suspend = mwifiex_usb_suspend,
 	.resume = mwifiex_usb_resume,
 	.soft_unbind = 1,
-	.drvwrap.driver = {
+	.driver = {
 		.coredump = mwifiex_usb_coredump,
 	},
 };
diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c
index 1dc0c0413043..e01b1913d02b 100644
--- a/drivers/usb/core/driver.c
+++ b/drivers/usb/core/driver.c
@@ -189,13 +189,13 @@ static int usb_create_newid_files(struct usb_driver *usb_drv)
 		goto exit;
 
 	if (usb_drv->probe != NULL) {
-		error = driver_create_file(&usb_drv->drvwrap.driver,
+		error = driver_create_file(&usb_drv->driver,
 					   &driver_attr_new_id);
 		if (error == 0) {
-			error = driver_create_file(&usb_drv->drvwrap.driver,
+			error = driver_create_file(&usb_drv->driver,
 					&driver_attr_remove_id);
 			if (error)
-				driver_remove_file(&usb_drv->drvwrap.driver,
+				driver_remove_file(&usb_drv->driver,
 						&driver_attr_new_id);
 		}
 	}
@@ -209,9 +209,9 @@ static void usb_remove_newid_files(struct usb_driver *usb_drv)
 		return;
 
 	if (usb_drv->probe != NULL) {
-		driver_remove_file(&usb_drv->drvwrap.driver,
+		driver_remove_file(&usb_drv->driver,
 				&driver_attr_remove_id);
-		driver_remove_file(&usb_drv->drvwrap.driver,
+		driver_remove_file(&usb_drv->driver,
 				   &driver_attr_new_id);
 	}
 }
@@ -552,7 +552,7 @@ int usb_driver_claim_interface(struct usb_driver *driver,
 	if (!iface->authorized)
 		return -ENODEV;
 
-	dev->driver = &driver->drvwrap.driver;
+	dev->driver = &driver->driver;
 	usb_set_intfdata(iface, data);
 	iface->needs_binding = 0;
 
@@ -615,7 +615,7 @@ void usb_driver_release_interface(struct usb_driver *driver,
 	struct device *dev = &iface->dev;
 
 	/* this should never happen, don't release something that's not ours */
-	if (!dev->driver || dev->driver != &driver->drvwrap.driver)
+	if (!dev->driver || dev->driver != &driver->driver)
 		return;
 
 	/* don't release from within disconnect() */
@@ -950,7 +950,7 @@ static int __usb_bus_reprobe_drivers(struct device *dev, void *data)
 	int ret;
 
 	/* Don't reprobe if current driver isn't usb_generic_driver */
-	if (dev->driver != &usb_generic_driver.drvwrap.driver)
+	if (dev->driver != &usb_generic_driver.driver)
 		return 0;
 
 	udev = to_usb_device(dev);
@@ -964,6 +964,11 @@ static int __usb_bus_reprobe_drivers(struct device *dev, void *data)
 	return 0;
 }
 
+bool is_usb_device_driver(const struct device_driver *drv)
+{
+	return drv->probe == usb_probe_device;
+}
+
 /**
  * usb_register_device_driver - register a USB device (not interface) driver
  * @new_udriver: USB operations for the device driver
@@ -983,15 +988,14 @@ int usb_register_device_driver(struct usb_device_driver *new_udriver,
 	if (usb_disabled())
 		return -ENODEV;
 
-	new_udriver->drvwrap.for_devices = 1;
-	new_udriver->drvwrap.driver.name = new_udriver->name;
-	new_udriver->drvwrap.driver.bus = &usb_bus_type;
-	new_udriver->drvwrap.driver.probe = usb_probe_device;
-	new_udriver->drvwrap.driver.remove = usb_unbind_device;
-	new_udriver->drvwrap.driver.owner = owner;
-	new_udriver->drvwrap.driver.dev_groups = new_udriver->dev_groups;
+	new_udriver->driver.name = new_udriver->name;
+	new_udriver->driver.bus = &usb_bus_type;
+	new_udriver->driver.probe = usb_probe_device;
+	new_udriver->driver.remove = usb_unbind_device;
+	new_udriver->driver.owner = owner;
+	new_udriver->driver.dev_groups = new_udriver->dev_groups;
 
-	retval = driver_register(&new_udriver->drvwrap.driver);
+	retval = driver_register(&new_udriver->driver);
 
 	if (!retval) {
 		pr_info("%s: registered new device driver %s\n",
@@ -1023,7 +1027,7 @@ void usb_deregister_device_driver(struct usb_device_driver *udriver)
 	pr_info("%s: deregistering device driver %s\n",
 			usbcore_name, udriver->name);
 
-	driver_unregister(&udriver->drvwrap.driver);
+	driver_unregister(&udriver->driver);
 }
 EXPORT_SYMBOL_GPL(usb_deregister_device_driver);
 
@@ -1051,18 +1055,17 @@ int usb_register_driver(struct usb_driver *new_driver, struct module *owner,
 	if (usb_disabled())
 		return -ENODEV;
 
-	new_driver->drvwrap.for_devices = 0;
-	new_driver->drvwrap.driver.name = new_driver->name;
-	new_driver->drvwrap.driver.bus = &usb_bus_type;
-	new_driver->drvwrap.driver.probe = usb_probe_interface;
-	new_driver->drvwrap.driver.remove = usb_unbind_interface;
-	new_driver->drvwrap.driver.owner = owner;
-	new_driver->drvwrap.driver.mod_name = mod_name;
-	new_driver->drvwrap.driver.dev_groups = new_driver->dev_groups;
+	new_driver->driver.name = new_driver->name;
+	new_driver->driver.bus = &usb_bus_type;
+	new_driver->driver.probe = usb_probe_interface;
+	new_driver->driver.remove = usb_unbind_interface;
+	new_driver->driver.owner = owner;
+	new_driver->driver.mod_name = mod_name;
+	new_driver->driver.dev_groups = new_driver->dev_groups;
 	spin_lock_init(&new_driver->dynids.lock);
 	INIT_LIST_HEAD(&new_driver->dynids.list);
 
-	retval = driver_register(&new_driver->drvwrap.driver);
+	retval = driver_register(&new_driver->driver);
 	if (retval)
 		goto out;
 
@@ -1077,7 +1080,7 @@ out:
 	return retval;
 
 out_newid:
-	driver_unregister(&new_driver->drvwrap.driver);
+	driver_unregister(&new_driver->driver);
 
 	pr_err("%s: error %d registering interface driver %s\n",
 		usbcore_name, retval, new_driver->name);
@@ -1102,7 +1105,7 @@ void usb_deregister(struct usb_driver *driver)
 			usbcore_name, driver->name);
 
 	usb_remove_newid_files(driver);
-	driver_unregister(&driver->drvwrap.driver);
+	driver_unregister(&driver->driver);
 	usb_free_dynids(driver);
 }
 EXPORT_SYMBOL_GPL(usb_deregister);
diff --git a/drivers/usb/core/usb.c b/drivers/usb/core/usb.c
index 2a938cf47ccd..dc8d9228a5e7 100644
--- a/drivers/usb/core/usb.c
+++ b/drivers/usb/core/usb.c
@@ -431,7 +431,7 @@ struct usb_interface *usb_find_interface(struct usb_driver *drv, int minor)
 	struct device *dev;
 
 	argb.minor = minor;
-	argb.drv = &drv->drvwrap.driver;
+	argb.drv = &drv->driver;
 
 	dev = bus_find_device(&usb_bus_type, NULL, &argb, __find_interface);
 
diff --git a/drivers/usb/core/usb.h b/drivers/usb/core/usb.h
index 60363153fc3f..bfecb50773b6 100644
--- a/drivers/usb/core/usb.h
+++ b/drivers/usb/core/usb.h
@@ -175,13 +175,7 @@ static inline int is_root_hub(struct usb_device *udev)
 	return (udev->parent == NULL);
 }
 
-/* Do the same for device drivers and interface drivers. */
-
-static inline int is_usb_device_driver(struct device_driver *drv)
-{
-	return container_of(drv, struct usbdrv_wrap, driver)->
-			for_devices;
-}
+extern bool is_usb_device_driver(const struct device_driver *drv);
 
 /* for labeling diagnostics */
 extern const char *usbcore_name;
diff --git a/drivers/usb/misc/onboard_usb_hub.c b/drivers/usb/misc/onboard_usb_hub.c
index c09fb6bd7d7d..0dd2b032c90b 100644
--- a/drivers/usb/misc/onboard_usb_hub.c
+++ b/drivers/usb/misc/onboard_usb_hub.c
@@ -244,7 +244,7 @@ static void onboard_hub_attach_usb_driver(struct work_struct *work)
 {
 	int err;
 
-	err = driver_attach(&onboard_hub_usbdev_driver.drvwrap.driver);
+	err = driver_attach(&onboard_hub_usbdev_driver.driver);
 	if (err)
 		pr_err("Failed to attach USB driver: %pe\n", ERR_PTR(err));
 }
diff --git a/drivers/usb/serial/bus.c b/drivers/usb/serial/bus.c
index 3eb8dc3a1a8f..6c812d01b37d 100644
--- a/drivers/usb/serial/bus.c
+++ b/drivers/usb/serial/bus.c
@@ -113,7 +113,7 @@ static ssize_t new_id_store(struct device_driver *driver,
 	if (retval >= 0 && usb_drv->usb_driver != NULL)
 		retval = usb_store_new_id(&usb_drv->usb_driver->dynids,
 					  usb_drv->usb_driver->id_table,
-					  &usb_drv->usb_driver->drvwrap.driver,
+					  &usb_drv->usb_driver->driver,
 					  buf, count);
 	return retval;
 }
diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c
index 17b09f03ef84..f1e91eb7f8a4 100644
--- a/drivers/usb/serial/usb-serial.c
+++ b/drivers/usb/serial/usb-serial.c
@@ -1521,7 +1521,7 @@ int usb_serial_register_drivers(struct usb_serial_driver *const serial_drivers[]
 
 	/* Now set udriver's id_table and look for matches */
 	udriver->id_table = id_table;
-	rc = driver_attach(&udriver->drvwrap.driver);
+	rc = driver_attach(&udriver->driver);
 	return 0;
 
 err_deregister_drivers:
diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c
index 696bb0b23599..9707f53cfda9 100644
--- a/drivers/usb/storage/uas.c
+++ b/drivers/usb/storage/uas.c
@@ -1246,7 +1246,7 @@ static struct usb_driver uas_driver = {
 	.suspend = uas_suspend,
 	.resume = uas_resume,
 	.reset_resume = uas_reset_resume,
-	.drvwrap.driver.shutdown = uas_shutdown,
+	.driver.shutdown = uas_shutdown,
 	.id_table = uas_usb_ids,
 };
 
diff --git a/drivers/usb/usbip/stub_main.c b/drivers/usb/usbip/stub_main.c
index 0a6624d37929..79110a69d697 100644
--- a/drivers/usb/usbip/stub_main.c
+++ b/drivers/usb/usbip/stub_main.c
@@ -377,14 +377,14 @@ static int __init usbip_host_init(void)
 		goto err_usb_register;
 	}
 
-	ret = driver_create_file(&stub_driver.drvwrap.driver,
+	ret = driver_create_file(&stub_driver.driver,
 				 &driver_attr_match_busid);
 	if (ret) {
 		pr_err("driver_create_file failed\n");
 		goto err_create_file;
 	}
 
-	ret = driver_create_file(&stub_driver.drvwrap.driver,
+	ret = driver_create_file(&stub_driver.driver,
 				 &driver_attr_rebind);
 	if (ret) {
 		pr_err("driver_create_file failed\n");
@@ -402,10 +402,10 @@ err_usb_register:
 
 static void __exit usbip_host_exit(void)
 {
-	driver_remove_file(&stub_driver.drvwrap.driver,
+	driver_remove_file(&stub_driver.driver,
 			   &driver_attr_match_busid);
 
-	driver_remove_file(&stub_driver.drvwrap.driver,
+	driver_remove_file(&stub_driver.driver,
 			   &driver_attr_rebind);
 
 	/*
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 07556341ba2b..9e52179872a5 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -1143,16 +1143,6 @@ extern ssize_t usb_store_new_id(struct usb_dynids *dynids,
 
 extern ssize_t usb_show_dynids(struct usb_dynids *dynids, char *buf);
 
-/**
- * struct usbdrv_wrap - wrapper for driver-model structure
- * @driver: The driver-model core driver structure.
- * @for_devices: Non-zero for device drivers, 0 for interface drivers.
- */
-struct usbdrv_wrap {
-	struct device_driver driver;
-	int for_devices;
-};
-
 /**
  * struct usb_driver - identifies USB interface driver to usbcore
  * @name: The driver name should be unique among USB drivers,
@@ -1193,7 +1183,7 @@ struct usbdrv_wrap {
  *	is bound to the driver.
  * @dynids: used internally to hold the list of dynamically added device
  *	ids for this driver.
- * @drvwrap: Driver-model core structure wrapper.
+ * @driver: The driver-model core driver structure.
  * @no_dynamic_id: if set to 1, the USB core will not allow dynamic ids to be
  *	added to this driver by preventing the sysfs file from being created.
  * @supports_autosuspend: if set to 0, the USB core will not allow autosuspend
@@ -1241,13 +1231,13 @@ struct usb_driver {
 	const struct attribute_group **dev_groups;
 
 	struct usb_dynids dynids;
-	struct usbdrv_wrap drvwrap;
+	struct device_driver driver;
 	unsigned int no_dynamic_id:1;
 	unsigned int supports_autosuspend:1;
 	unsigned int disable_hub_initiated_lpm:1;
 	unsigned int soft_unbind:1;
 };
-#define	to_usb_driver(d) container_of(d, struct usb_driver, drvwrap.driver)
+#define	to_usb_driver(d) container_of(d, struct usb_driver, driver)
 
 /**
  * struct usb_device_driver - identifies USB device driver to usbcore
@@ -1268,7 +1258,7 @@ struct usb_driver {
  *	on to call the normal usb_choose_configuration().
  * @dev_groups: Attributes attached to the device that will be created once it
  *	is bound to the driver.
- * @drvwrap: Driver-model core structure wrapper.
+ * @driver: The driver-model core driver structure.
  * @id_table: used with @match() to select better matching driver at
  * 	probe() time.
  * @supports_autosuspend: if set to 0, the USB core will not allow autosuspend
@@ -1277,7 +1267,7 @@ struct usb_driver {
  *	resume and suspend functions will be called in addition to the driver's
  *	own, so this part of the setup does not need to be replicated.
  *
- * USB drivers must provide all the fields listed above except drvwrap,
+ * USB drivers must provide all the fields listed above except driver,
  * match, and id_table.
  */
 struct usb_device_driver {
@@ -1293,13 +1283,13 @@ struct usb_device_driver {
 	int (*choose_configuration) (struct usb_device *udev);
 
 	const struct attribute_group **dev_groups;
-	struct usbdrv_wrap drvwrap;
+	struct device_driver driver;
 	const struct usb_device_id *id_table;
 	unsigned int supports_autosuspend:1;
 	unsigned int generic_subclass:1;
 };
 #define	to_usb_device_driver(d) container_of(d, struct usb_device_driver, \
-		drvwrap.driver)
+		driver)
 
 /**
  * struct usb_class_driver - identifies a USB driver that wants to use the USB major number
-- 
cgit v1.2.3


From cb86a3383aa7b9bb891daca691e596f6bfe52d82 Mon Sep 17 00:00:00 2001
From: Vamshi Gajjela <vamshigajjela@google.com>
Date: Thu, 9 Nov 2023 12:04:16 +0530
Subject: serial: core: Update uart_poll_timeout() function to return unsigned
 long

The function uart_fifo_timeout() returns an unsigned long value, which
is the number of jiffies. Therefore, change the variable timeout in the
function uart_poll_timeout() from int to unsigned long.
Change the return type of the function uart_poll_timeout() from int to
unsigned long to be consistent with the type of timeout values.

Signed-off-by: Vamshi Gajjela <vamshigajjela@google.com>
Link: https://lore.kernel.org/r/20231109063417.3971005-2-vamshigajjela@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/serial_core.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index 89f7b6c63598..536b2581d3e2 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -852,9 +852,9 @@ static inline unsigned long uart_fifo_timeout(struct uart_port *port)
 }
 
 /* Base timer interval for polling */
-static inline int uart_poll_timeout(struct uart_port *port)
+static inline unsigned long uart_poll_timeout(struct uart_port *port)
 {
-	int timeout = uart_fifo_timeout(port);
+	unsigned long timeout = uart_fifo_timeout(port);
 
 	return timeout > 6 ? (timeout / 2 - 2) : 1;
 }
-- 
cgit v1.2.3


From 76ac8e29855b06331d77a1d237a28ce97ac67a38 Mon Sep 17 00:00:00 2001
From: Crescent CY Hsieh <crescentcy.hsieh@moxa.com>
Date: Fri, 1 Dec 2023 15:15:53 +0800
Subject: tty: serial: Cleanup the bit shift with macro

This patch replaces the bit shift code with "_BITUL()" macro inside
"serial_rs485" struct.

Signed-off-by: Crescent CY Hsieh <crescentcy.hsieh@moxa.com>
Link: https://lore.kernel.org/r/20231201071554.258607-2-crescentcy.hsieh@moxa.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/uapi/linux/serial.h | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/serial.h b/include/uapi/linux/serial.h
index 53bc1af67a41..6c75ebdd7797 100644
--- a/include/uapi/linux/serial.h
+++ b/include/uapi/linux/serial.h
@@ -11,6 +11,7 @@
 #ifndef _UAPI_LINUX_SERIAL_H
 #define _UAPI_LINUX_SERIAL_H
 
+#include <linux/const.h>
 #include <linux/types.h>
 
 #include <linux/tty_flags.h>
@@ -140,14 +141,14 @@ struct serial_icounter_struct {
  */
 struct serial_rs485 {
 	__u32	flags;
-#define SER_RS485_ENABLED		(1 << 0)
-#define SER_RS485_RTS_ON_SEND		(1 << 1)
-#define SER_RS485_RTS_AFTER_SEND	(1 << 2)
-#define SER_RS485_RX_DURING_TX		(1 << 4)
-#define SER_RS485_TERMINATE_BUS		(1 << 5)
-#define SER_RS485_ADDRB			(1 << 6)
-#define SER_RS485_ADDR_RECV		(1 << 7)
-#define SER_RS485_ADDR_DEST		(1 << 8)
+#define SER_RS485_ENABLED		_BITUL(0)
+#define SER_RS485_RTS_ON_SEND		_BITUL(1)
+#define SER_RS485_RTS_AFTER_SEND	_BITUL(2)
+#define SER_RS485_RX_DURING_TX		_BITUL(3)
+#define SER_RS485_TERMINATE_BUS		_BITUL(4)
+#define SER_RS485_ADDRB			_BITUL(5)
+#define SER_RS485_ADDR_RECV		_BITUL(6)
+#define SER_RS485_ADDR_DEST		_BITUL(7)
 
 	__u32	delay_rts_before_send;
 	__u32	delay_rts_after_send;
-- 
cgit v1.2.3


From 6056f20f27e99fb67582f299468328505f130e36 Mon Sep 17 00:00:00 2001
From: Crescent CY Hsieh <crescentcy.hsieh@moxa.com>
Date: Fri, 1 Dec 2023 15:15:54 +0800
Subject: tty: serial: Add RS422 flag to struct serial_rs485

Add "SER_RS485_MODE_RS422" flag to struct serial_rs485, so that serial
port can switch interface into RS422 if supported by using ioctl command
"TIOCSRS485".

By treating RS422 as a mode of RS485, which means while enabling RS422
there are two flags need to be set (SER_RS485_ENABLED and
SER_RS485_MODE_RS422), it would make things much easier. For example
some places that checks for "SER_RS485_ENABLED" won't need to be rewritten.

Signed-off-by: Crescent CY Hsieh <crescentcy.hsieh@moxa.com>
Link: https://lore.kernel.org/r/20231201071554.258607-3-crescentcy.hsieh@moxa.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/serial_core.c | 6 ++++++
 include/uapi/linux/serial.h      | 2 ++
 2 files changed, 8 insertions(+)

(limited to 'include')

diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 1147fb1b39f2..d35371c076b2 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -1370,6 +1370,12 @@ static void uart_sanitize_serial_rs485(struct uart_port *port, struct serial_rs4
 		return;
 	}
 
+	/* Clear other RS485 flags but SER_RS485_TERMINATE_BUS and return if enabling RS422 */
+	if (rs485->flags & SER_RS485_MODE_RS422) {
+		rs485->flags &= (SER_RS485_ENABLED | SER_RS485_MODE_RS422 | SER_RS485_TERMINATE_BUS);
+		return;
+	}
+
 	/* Pick sane settings if the user hasn't */
 	if ((supported_flags & (SER_RS485_RTS_ON_SEND|SER_RS485_RTS_AFTER_SEND)) &&
 	    !(rs485->flags & SER_RS485_RTS_ON_SEND) ==
diff --git a/include/uapi/linux/serial.h b/include/uapi/linux/serial.h
index 6c75ebdd7797..9086367db043 100644
--- a/include/uapi/linux/serial.h
+++ b/include/uapi/linux/serial.h
@@ -138,6 +138,7 @@ struct serial_icounter_struct {
  * * %SER_RS485_ADDRB		- Enable RS485 addressing mode.
  * * %SER_RS485_ADDR_RECV - Receive address filter (enables @addr_recv). Requires %SER_RS485_ADDRB.
  * * %SER_RS485_ADDR_DEST - Destination address (enables @addr_dest). Requires %SER_RS485_ADDRB.
+ * * %SER_RS485_MODE_RS422	- Enable RS422. Requires %SER_RS485_ENABLED.
  */
 struct serial_rs485 {
 	__u32	flags;
@@ -149,6 +150,7 @@ struct serial_rs485 {
 #define SER_RS485_ADDRB			_BITUL(5)
 #define SER_RS485_ADDR_RECV		_BITUL(6)
 #define SER_RS485_ADDR_DEST		_BITUL(7)
+#define SER_RS485_MODE_RS422		_BITUL(8)
 
 	__u32	delay_rts_before_send;
 	__u32	delay_rts_after_send;
-- 
cgit v1.2.3


From 5f1e77b2285b47c216b44e513071549cf006a309 Mon Sep 17 00:00:00 2001
From: Anna Schumaker <Anna.Schumaker@Netapp.com>
Date: Thu, 30 Nov 2023 13:30:15 -0500
Subject: SUNRPC: Remove unused function rpc_clnt_xprt_switch_put()

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/linux/sunrpc/clnt.h | 1 -
 net/sunrpc/clnt.c           | 8 --------
 2 files changed, 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index e9d4377d03c6..5e9d1469c6fa 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -252,7 +252,6 @@ void		rpc_clnt_probe_trunked_xprts(struct rpc_clnt *,
 
 const char *rpc_proc_name(const struct rpc_task *task);
 
-void rpc_clnt_xprt_switch_put(struct rpc_clnt *);
 void rpc_clnt_xprt_switch_add_xprt(struct rpc_clnt *, struct rpc_xprt *);
 void rpc_clnt_xprt_switch_remove_xprt(struct rpc_clnt *, struct rpc_xprt *);
 bool rpc_clnt_xprt_switch_has_addr(struct rpc_clnt *clnt,
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 4aa838543f79..8df944444e9b 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -3247,14 +3247,6 @@ rpc_set_connect_timeout(struct rpc_clnt *clnt,
 }
 EXPORT_SYMBOL_GPL(rpc_set_connect_timeout);
 
-void rpc_clnt_xprt_switch_put(struct rpc_clnt *clnt)
-{
-	rcu_read_lock();
-	xprt_switch_put(rcu_dereference(clnt->cl_xpi.xpi_xpswitch));
-	rcu_read_unlock();
-}
-EXPORT_SYMBOL_GPL(rpc_clnt_xprt_switch_put);
-
 void rpc_clnt_xprt_set_online(struct rpc_clnt *clnt, struct rpc_xprt *xprt)
 {
 	struct rpc_xprt_switch *xps;
-- 
cgit v1.2.3


From 12fc0a963128b54b82e98b9909f463e784b90b07 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Fri, 15 Dec 2023 20:47:07 +0000
Subject: nfs: Remove writepage

NFS already has writepages and migrate_folio, so it does not need to
implement writepage.  The writepage operation is deprecated as it leads
to worse performance under high memory pressure due to folios being
written out in LRU order rather than sequentially within a file.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/file.c          |  1 -
 fs/nfs/write.c         | 11 -----------
 include/linux/nfs_fs.h |  1 -
 3 files changed, 13 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 3f9768810427..e437de2a5ad4 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -558,7 +558,6 @@ const struct address_space_operations nfs_file_aops = {
 	.read_folio = nfs_read_folio,
 	.readahead = nfs_readahead,
 	.dirty_folio = filemap_dirty_folio,
-	.writepage = nfs_writepage,
 	.writepages = nfs_writepages,
 	.write_begin = nfs_write_begin,
 	.write_end = nfs_write_end,
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index b664caea8b4e..0b4fdad511d9 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -680,17 +680,6 @@ static int nfs_writepage_locked(struct folio *folio,
 	return err;
 }
 
-int nfs_writepage(struct page *page, struct writeback_control *wbc)
-{
-	struct folio *folio = page_folio(page);
-	int ret;
-
-	ret = nfs_writepage_locked(folio, wbc);
-	if (ret != AOP_WRITEPAGE_ACTIVATE)
-		unlock_page(page);
-	return ret;
-}
-
 static int nfs_writepages_callback(struct folio *folio,
 				   struct writeback_control *wbc, void *data)
 {
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 279262057a92..f5ce7b101146 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -595,7 +595,6 @@ extern void nfs_complete_unlink(struct dentry *dentry, struct inode *);
  * linux/fs/nfs/write.c
  */
 extern int  nfs_congestion_kb;
-extern int  nfs_writepage(struct page *page, struct writeback_control *wbc);
 extern int  nfs_writepages(struct address_space *, struct writeback_control *);
 extern int  nfs_flush_incompatible(struct file *file, struct folio *folio);
 extern int  nfs_update_folio(struct file *file, struct folio *folio,
-- 
cgit v1.2.3


From 401df0d4f4098ecc9c5278da2f50756d62e5b37d Mon Sep 17 00:00:00 2001
From: Rafał Miłecki <rafal@milecki.pl>
Date: Tue, 19 Dec 2023 13:01:03 +0100
Subject: nvmem: layouts: refactor .add_cells() callback arguments
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Simply pass whole "struct nvmem_layout" instead of single variables.
There is nothing in "struct nvmem_layout" that we have to hide from
layout drivers. They also access it during .probe() and .remove().

Thanks to this change:

1. API gets more consistent
   All layouts drivers callbacks get the same argument

2. Layouts get correct device
   Before this change NVMEM core code was passing NVMEM device instead
   of layout device. That resulted in:
   * Confusing prints
   * Calling devm_*() helpers on wrong device
   * Helpers like of_device_get_match_data() dereferencing NULLs

3. It gets possible to get match data
   First of all nvmem_layout_get_match_data() requires passing "struct
   nvmem_layout" which .add_cells() callback didn't have before this. It
   doesn't matter much as it's rather useless now anyway (and will be
   dropped).
   What's more important however is that of_device_get_match_data() can
   be used now thanks to owning a proper device pointer.

Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Michael Walle <michael@walle.cc>
Link: https://lore.kernel.org/r/20231219120104.3422-1-zajec5@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/nvmem/core.c             | 2 +-
 drivers/nvmem/layouts/onie-tlv.c | 4 +++-
 drivers/nvmem/layouts/sl28vpd.c  | 4 +++-
 include/linux/nvmem-provider.h   | 2 +-
 4 files changed, 8 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index ba559e81f77f..441d132ebb61 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -854,7 +854,7 @@ int nvmem_layout_register(struct nvmem_layout *layout)
 		return -EINVAL;
 
 	/* Populate the cells */
-	ret = layout->add_cells(&layout->nvmem->dev, layout->nvmem);
+	ret = layout->add_cells(layout);
 	if (ret)
 		return ret;
 
diff --git a/drivers/nvmem/layouts/onie-tlv.c b/drivers/nvmem/layouts/onie-tlv.c
index b24cc5dcc6ee..9d2ad5f2dc10 100644
--- a/drivers/nvmem/layouts/onie-tlv.c
+++ b/drivers/nvmem/layouts/onie-tlv.c
@@ -182,8 +182,10 @@ static bool onie_tlv_crc_is_valid(struct device *dev, size_t table_len, u8 *tabl
 	return true;
 }
 
-static int onie_tlv_parse_table(struct device *dev, struct nvmem_device *nvmem)
+static int onie_tlv_parse_table(struct nvmem_layout *layout)
 {
+	struct nvmem_device *nvmem = layout->nvmem;
+	struct device *dev = &layout->dev;
 	struct onie_tlv_hdr hdr;
 	size_t table_len, data_len, hdr_len;
 	u8 *table, *data;
diff --git a/drivers/nvmem/layouts/sl28vpd.c b/drivers/nvmem/layouts/sl28vpd.c
index b8ffae646cc2..53fa50f17dca 100644
--- a/drivers/nvmem/layouts/sl28vpd.c
+++ b/drivers/nvmem/layouts/sl28vpd.c
@@ -80,8 +80,10 @@ static int sl28vpd_v1_check_crc(struct device *dev, struct nvmem_device *nvmem)
 	return 0;
 }
 
-static int sl28vpd_add_cells(struct device *dev, struct nvmem_device *nvmem)
+static int sl28vpd_add_cells(struct nvmem_layout *layout)
 {
+	struct nvmem_device *nvmem = layout->nvmem;
+	struct device *dev = &layout->dev;
 	const struct nvmem_cell_info *pinfo;
 	struct nvmem_cell_info info = {0};
 	struct device_node *layout_np;
diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h
index 6fe65b35ea97..81a67642ac55 100644
--- a/include/linux/nvmem-provider.h
+++ b/include/linux/nvmem-provider.h
@@ -173,7 +173,7 @@ struct nvmem_cell_table {
 struct nvmem_layout {
 	struct device dev;
 	struct nvmem_device *nvmem;
-	int (*add_cells)(struct device *dev, struct nvmem_device *nvmem);
+	int (*add_cells)(struct nvmem_layout *layout);
 };
 
 struct nvmem_layout_driver {
-- 
cgit v1.2.3


From 43f60e3fb62edc7bd8891de8779fb422f4ae23ae Mon Sep 17 00:00:00 2001
From: Rafał Miłecki <rafal@milecki.pl>
Date: Tue, 19 Dec 2023 13:01:04 +0100
Subject: nvmem: drop nvmem_layout_get_match_data()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Thanks for layouts refactoring we now have "struct device" associated
with layout. Also its OF pointer points directly to the "nvmem-layout"
DT node.

All it takes to get match data is a generic of_device_get_match_data().

Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Michael Walle <michael@walle.cc>
Link: https://lore.kernel.org/r/20231219120104.3422-2-zajec5@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/nvmem/core.c           | 13 -------------
 include/linux/nvmem-provider.h | 10 ----------
 2 files changed, 23 deletions(-)

(limited to 'include')

diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index 441d132ebb61..4ed54076346d 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -876,19 +876,6 @@ void nvmem_layout_unregister(struct nvmem_layout *layout)
 }
 EXPORT_SYMBOL_GPL(nvmem_layout_unregister);
 
-const void *nvmem_layout_get_match_data(struct nvmem_device *nvmem,
-					struct nvmem_layout *layout)
-{
-	struct device_node __maybe_unused *layout_np;
-	const struct of_device_id *match;
-
-	layout_np = of_nvmem_layout_get_container(nvmem);
-	match = of_match_node(layout->dev.driver->of_match_table, layout_np);
-
-	return match ? match->data : NULL;
-}
-EXPORT_SYMBOL_GPL(nvmem_layout_get_match_data);
-
 /**
  * nvmem_register() - Register a nvmem device for given nvmem_config.
  * Also creates a binary entry in /sys/bus/nvmem/devices/dev-name/nvmem
diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h
index 81a67642ac55..f0ba0e03218f 100644
--- a/include/linux/nvmem-provider.h
+++ b/include/linux/nvmem-provider.h
@@ -205,9 +205,6 @@ void nvmem_layout_driver_unregister(struct nvmem_layout_driver *drv);
 	module_driver(__nvmem_layout_driver, nvmem_layout_driver_register, \
 		      nvmem_layout_driver_unregister)
 
-const void *nvmem_layout_get_match_data(struct nvmem_device *nvmem,
-					struct nvmem_layout *layout);
-
 #else
 
 static inline struct nvmem_device *nvmem_register(const struct nvmem_config *c)
@@ -238,13 +235,6 @@ static inline int nvmem_layout_register(struct nvmem_layout *layout)
 
 static inline void nvmem_layout_unregister(struct nvmem_layout *layout) {}
 
-static inline const void *
-nvmem_layout_get_match_data(struct nvmem_device *nvmem,
-			    struct nvmem_layout *layout)
-{
-	return NULL;
-}
-
 #endif /* CONFIG_NVMEM */
 
 #if IS_ENABLED(CONFIG_NVMEM) && IS_ENABLED(CONFIG_OF)
-- 
cgit v1.2.3


From 33cf42e68efc8ff529a7eee08a4f0ba8c8d0a207 Mon Sep 17 00:00:00 2001
From: Rafał Miłecki <rafal@milecki.pl>
Date: Thu, 21 Dec 2023 18:34:17 +0100
Subject: nvmem: core: add nvmem_dev_size() helper
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This is required by layouts that need to read whole NVMEM content. It's
especially useful for NVMEM devices without hardcoded layout (like
U-Boot environment data block).

Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/r/20231221173421.13737-2-zajec5@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/nvmem/core.c           | 13 +++++++++++++
 include/linux/nvmem-consumer.h |  1 +
 2 files changed, 14 insertions(+)

(limited to 'include')

diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index 4ed54076346d..980123fb4dde 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -2163,6 +2163,19 @@ const char *nvmem_dev_name(struct nvmem_device *nvmem)
 }
 EXPORT_SYMBOL_GPL(nvmem_dev_name);
 
+/**
+ * nvmem_dev_size() - Get the size of a given nvmem device.
+ *
+ * @nvmem: nvmem device.
+ *
+ * Return: size of the nvmem device.
+ */
+size_t nvmem_dev_size(struct nvmem_device *nvmem)
+{
+	return nvmem->size;
+}
+EXPORT_SYMBOL_GPL(nvmem_dev_size);
+
 static int __init nvmem_init(void)
 {
 	int ret;
diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h
index 2d306fa13b1a..34c0e58dfa26 100644
--- a/include/linux/nvmem-consumer.h
+++ b/include/linux/nvmem-consumer.h
@@ -81,6 +81,7 @@ int nvmem_device_cell_write(struct nvmem_device *nvmem,
 			    struct nvmem_cell_info *info, void *buf);
 
 const char *nvmem_dev_name(struct nvmem_device *nvmem);
+size_t nvmem_dev_size(struct nvmem_device *nvmem);
 
 void nvmem_add_cell_lookups(struct nvmem_cell_lookup *entries,
 			    size_t nentries);
-- 
cgit v1.2.3


From aeda33ab8160c7a2e24ba4f44492ad1e974ddc7d Mon Sep 17 00:00:00 2001
From: Abhijit Gangurde <abhijit.gangurde@amd.com>
Date: Fri, 22 Dec 2023 12:16:26 +0530
Subject: cdx: create sysfs bin files for cdx resources

Resource binary file contains the content of the memory regions.
These resources<x> devices can be used to mmap the MMIO regions in
the user-space.

Co-developed-by: Puneet Gupta <puneet.gupta@amd.com>
Signed-off-by: Puneet Gupta <puneet.gupta@amd.com>
Signed-off-by: Abhijit Gangurde <abhijit.gangurde@amd.com>
Link: https://lore.kernel.org/r/20231222064627.2828960-1-abhijit.gangurde@amd.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/ABI/testing/sysfs-bus-cdx |   7 ++
 drivers/cdx/cdx.c                       | 118 +++++++++++++++++++++++++++++++-
 include/linux/cdx/cdx_bus.h             |  10 +++
 3 files changed, 134 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/Documentation/ABI/testing/sysfs-bus-cdx b/Documentation/ABI/testing/sysfs-bus-cdx
index 8c067ff99e54..e84277531414 100644
--- a/Documentation/ABI/testing/sysfs-bus-cdx
+++ b/Documentation/ABI/testing/sysfs-bus-cdx
@@ -98,6 +98,13 @@ Description:
 
 		  # echo 1 > /sys/bus/cdx/devices/.../remove
 
+What:		/sys/bus/cdx/devices/.../resource<N>
+Date:		July 2023
+Contact:	puneet.gupta@amd.com
+Description:
+		The resource binary file contains the content of the memory
+		regions. These files can be m'maped from userspace.
+
 What:		/sys/bus/cdx/devices/.../modalias
 Date:		July 2023
 Contact:	nipun.gupta@amd.com
diff --git a/drivers/cdx/cdx.c b/drivers/cdx/cdx.c
index d84d153078d7..2ec1846ff063 100644
--- a/drivers/cdx/cdx.c
+++ b/drivers/cdx/cdx.c
@@ -80,6 +80,8 @@ static DEFINE_MUTEX(cdx_controller_lock);
 
 static char *compat_node_name = "xlnx,versal-net-cdx";
 
+static void cdx_destroy_res_attr(struct cdx_device *cdx_dev, int num);
+
 /**
  * cdx_dev_reset - Reset a CDX device
  * @dev: CDX device
@@ -148,6 +150,7 @@ static int cdx_unregister_device(struct device *dev,
 		if (cdx_dev->enabled && cdx->ops->bus_disable)
 			cdx->ops->bus_disable(cdx, cdx_dev->bus_num);
 	} else {
+		cdx_destroy_res_attr(cdx_dev, MAX_CDX_DEV_RESOURCES);
 		kfree(cdx_dev->driver_override);
 		cdx_dev->driver_override = NULL;
 	}
@@ -643,11 +646,105 @@ static void cdx_device_release(struct device *dev)
 	kfree(cdx_dev);
 }
 
+static const struct vm_operations_struct cdx_phys_vm_ops = {
+#ifdef CONFIG_HAVE_IOREMAP_PROT
+	.access = generic_access_phys,
+#endif
+};
+
+/**
+ * cdx_mmap_resource - map a CDX resource into user memory space
+ * @fp: File pointer. Not used in this function, but required where
+ *      this API is registered as a callback.
+ * @kobj: kobject for mapping
+ * @attr: struct bin_attribute for the file being mapped
+ * @vma: struct vm_area_struct passed into the mmap
+ *
+ * Use the regular CDX mapping routines to map a CDX resource into userspace.
+ *
+ * Return: true on success, false otherwise.
+ */
+static int cdx_mmap_resource(struct file *fp, struct kobject *kobj,
+			     struct bin_attribute *attr,
+			     struct vm_area_struct *vma)
+{
+	struct cdx_device *cdx_dev = to_cdx_device(kobj_to_dev(kobj));
+	int num = (unsigned long)attr->private;
+	struct resource *res;
+	unsigned long size;
+
+	res = &cdx_dev->res[num];
+	if (iomem_is_exclusive(res->start))
+		return -EINVAL;
+
+	/* Make sure the caller is mapping a valid resource for this device */
+	size = ((cdx_resource_len(cdx_dev, num) - 1) >> PAGE_SHIFT) + 1;
+	if (vma->vm_pgoff + vma_pages(vma) > size)
+		return -EINVAL;
+
+	/*
+	 * Map memory region and vm->vm_pgoff is expected to be an
+	 * offset within that region.
+	 */
+	vma->vm_page_prot = pgprot_device(vma->vm_page_prot);
+	vma->vm_pgoff += (cdx_resource_start(cdx_dev, num) >> PAGE_SHIFT);
+	vma->vm_ops = &cdx_phys_vm_ops;
+	return io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
+				  vma->vm_end - vma->vm_start,
+				  vma->vm_page_prot);
+}
+
+static void cdx_destroy_res_attr(struct cdx_device *cdx_dev, int num)
+{
+	int i;
+
+	/* removing the bin attributes */
+	for (i = 0; i < num; i++) {
+		struct bin_attribute *res_attr;
+
+		res_attr = cdx_dev->res_attr[i];
+		if (res_attr) {
+			sysfs_remove_bin_file(&cdx_dev->dev.kobj, res_attr);
+			kfree(res_attr);
+		}
+	}
+}
+
+#define CDX_RES_ATTR_NAME_LEN	10
+static int cdx_create_res_attr(struct cdx_device *cdx_dev, int num)
+{
+	struct bin_attribute *res_attr;
+	char *res_attr_name;
+	int ret;
+
+	res_attr = kzalloc(sizeof(*res_attr) + CDX_RES_ATTR_NAME_LEN, GFP_ATOMIC);
+	if (!res_attr)
+		return -ENOMEM;
+
+	res_attr_name = (char *)(res_attr + 1);
+
+	sysfs_bin_attr_init(res_attr);
+
+	cdx_dev->res_attr[num] = res_attr;
+	sprintf(res_attr_name, "resource%d", num);
+
+	res_attr->mmap = cdx_mmap_resource;
+	res_attr->attr.name = res_attr_name;
+	res_attr->attr.mode = 0600;
+	res_attr->size = cdx_resource_len(cdx_dev, num);
+	res_attr->private = (void *)(unsigned long)num;
+	ret = sysfs_create_bin_file(&cdx_dev->dev.kobj, res_attr);
+	if (ret)
+		kfree(res_attr);
+
+	return ret;
+}
+
 int cdx_device_add(struct cdx_dev_params *dev_params)
 {
 	struct cdx_controller *cdx = dev_params->cdx;
 	struct cdx_device *cdx_dev;
-	int ret;
+	int ret, i;
 
 	cdx_dev = kzalloc(sizeof(*cdx_dev), GFP_KERNEL);
 	if (!cdx_dev)
@@ -690,7 +787,26 @@ int cdx_device_add(struct cdx_dev_params *dev_params)
 		goto fail;
 	}
 
+	/* Create resource<N> attributes */
+	for (i = 0; i < MAX_CDX_DEV_RESOURCES; i++) {
+		if (cdx_resource_flags(cdx_dev, i) & IORESOURCE_MEM) {
+			/* skip empty resources */
+			if (!cdx_resource_len(cdx_dev, i))
+				continue;
+
+			ret = cdx_create_res_attr(cdx_dev, i);
+			if (ret != 0) {
+				dev_err(&cdx_dev->dev,
+					"cdx device resource<%d> file creation failed: %d", i, ret);
+				goto resource_create_fail;
+			}
+		}
+	}
+
 	return 0;
+resource_create_fail:
+	cdx_destroy_res_attr(cdx_dev, i);
+	device_del(&cdx_dev->dev);
 fail:
 	/*
 	 * Do not free cdx_dev here as it would be freed in
diff --git a/include/linux/cdx/cdx_bus.h b/include/linux/cdx/cdx_bus.h
index 94ad2c9017c9..fab9e62c7e7d 100644
--- a/include/linux/cdx/cdx_bus.h
+++ b/include/linux/cdx/cdx_bus.h
@@ -135,6 +135,7 @@ struct cdx_device {
 	u8 bus_num;
 	u8 dev_num;
 	struct resource res[MAX_CDX_DEV_RESOURCES];
+	struct bin_attribute *res_attr[MAX_CDX_DEV_RESOURCES];
 	u8 res_count;
 	u64 dma_mask;
 	u16 flags;
@@ -147,6 +148,15 @@ struct cdx_device {
 #define to_cdx_device(_dev) \
 	container_of(_dev, struct cdx_device, dev)
 
+#define cdx_resource_start(dev, num)	((dev)->res[(num)].start)
+#define cdx_resource_end(dev, num)	((dev)->res[(num)].end)
+#define cdx_resource_flags(dev, num)	((dev)->res[(num)].flags)
+#define cdx_resource_len(dev, num) \
+	((cdx_resource_start((dev), (num)) == 0 &&	\
+	  cdx_resource_end((dev), (num)) ==		\
+	  cdx_resource_start((dev), (num))) ? 0 :	\
+	 (cdx_resource_end((dev), (num)) -		\
+	  cdx_resource_start((dev), (num)) + 1))
 /**
  * struct cdx_driver - CDX device driver
  * @driver: Generic device driver
-- 
cgit v1.2.3


From cf60af04edfe51fca488246c9959904adb2750fa Mon Sep 17 00:00:00 2001
From: Abhijit Gangurde <abhijit.gangurde@amd.com>
Date: Fri, 22 Dec 2023 12:16:27 +0530
Subject: cdx: Create resource debugfs file for cdx device

resource debugfs file contains host addresses of CDX device resources.
Each line of the resource file describe type of resource, a region
with start-end and flag fields.

Signed-off-by: Abhijit Gangurde <abhijit.gangurde@amd.com>
Link: https://lore.kernel.org/r/20231222064627.2828960-2-abhijit.gangurde@amd.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/cdx/cdx.c           | 39 ++++++++++++++++++++++++++++++++++++++-
 include/linux/cdx/cdx_bus.h |  2 ++
 2 files changed, 40 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/cdx/cdx.c b/drivers/cdx/cdx.c
index 2ec1846ff063..c0fca63c7434 100644
--- a/drivers/cdx/cdx.c
+++ b/drivers/cdx/cdx.c
@@ -67,6 +67,7 @@
 #include <linux/cdx/cdx_bus.h>
 #include <linux/iommu.h>
 #include <linux/dma-map-ops.h>
+#include <linux/debugfs.h>
 #include "cdx.h"
 
 /* Default DMA mask for devices on a CDX bus */
@@ -77,6 +78,8 @@
 static DEFINE_IDA(cdx_controller_ida);
 /* Lock to protect controller ops */
 static DEFINE_MUTEX(cdx_controller_lock);
+/* Debugfs dir for cdx bus */
+static struct dentry *cdx_debugfs_dir;
 
 static char *compat_node_name = "xlnx,versal-net-cdx";
 
@@ -151,6 +154,7 @@ static int cdx_unregister_device(struct device *dev,
 			cdx->ops->bus_disable(cdx, cdx_dev->bus_num);
 	} else {
 		cdx_destroy_res_attr(cdx_dev, MAX_CDX_DEV_RESOURCES);
+		debugfs_remove_recursive(cdx_dev->debugfs_dir);
 		kfree(cdx_dev->driver_override);
 		cdx_dev->driver_override = NULL;
 	}
@@ -554,6 +558,31 @@ static const struct attribute_group *cdx_dev_groups[] = {
 	NULL,
 };
 
+static int cdx_debug_resource_show(struct seq_file *s, void *data)
+{
+	struct cdx_device *cdx_dev = s->private;
+	int i;
+
+	for (i = 0; i < MAX_CDX_DEV_RESOURCES; i++) {
+		struct resource *res =  &cdx_dev->res[i];
+
+		seq_printf(s, "%pr\n", res);
+	}
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(cdx_debug_resource);
+
+static void cdx_device_debugfs_init(struct cdx_device *cdx_dev)
+{
+	cdx_dev->debugfs_dir = debugfs_create_dir(dev_name(&cdx_dev->dev), cdx_debugfs_dir);
+	if (IS_ERR(cdx_dev->debugfs_dir))
+		return;
+
+	debugfs_create_file("resource", 0444, cdx_dev->debugfs_dir, cdx_dev,
+			    &cdx_debug_resource_fops);
+}
+
 static ssize_t rescan_store(const struct bus_type *bus,
 			    const char *buf, size_t count)
 {
@@ -803,6 +832,8 @@ int cdx_device_add(struct cdx_dev_params *dev_params)
 		}
 	}
 
+	cdx_device_debugfs_init(cdx_dev);
+
 	return 0;
 resource_create_fail:
 	cdx_destroy_res_attr(cdx_dev, i);
@@ -907,6 +938,12 @@ EXPORT_SYMBOL_NS_GPL(cdx_unregister_controller, CDX_BUS_CONTROLLER);
 
 static int __init cdx_bus_init(void)
 {
-	return bus_register(&cdx_bus_type);
+	int ret;
+
+	ret = bus_register(&cdx_bus_type);
+	if (!ret)
+		cdx_debugfs_dir = debugfs_create_dir(cdx_bus_type.name, NULL);
+
+	return ret;
 }
 postcore_initcall(cdx_bus_init);
diff --git a/include/linux/cdx/cdx_bus.h b/include/linux/cdx/cdx_bus.h
index fab9e62c7e7d..6355a36a3f81 100644
--- a/include/linux/cdx/cdx_bus.h
+++ b/include/linux/cdx/cdx_bus.h
@@ -113,6 +113,7 @@ struct cdx_controller {
  * @dev_num: Device number for this device
  * @res: array of MMIO region entries
  * @res_attr: resource binary attribute
+ * @debugfs_dir: debugfs directory for this device
  * @res_count: number of valid MMIO regions
  * @dma_mask: Default DMA mask
  * @flags: CDX device flags
@@ -136,6 +137,7 @@ struct cdx_device {
 	u8 dev_num;
 	struct resource res[MAX_CDX_DEV_RESOURCES];
 	struct bin_attribute *res_attr[MAX_CDX_DEV_RESOURCES];
+	struct dentry *debugfs_dir;
 	u8 res_count;
 	u64 dma_mask;
 	u16 flags;
-- 
cgit v1.2.3


From a87e55bfa25c195b3aaa25369175905ba9527fff Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 19 Dec 2023 15:26:38 +0100
Subject: moxtet: remove unused moxtet_type declaration
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For some reason, moxtet_type was defined in moxtet.h, but never actually
used.  Looks like a left-over from the original commit that was
exporting the moxtet bus type, but that wasn't needed, and it was a
different variable name, so no one noticed this one dangling around.

Cc: Marek Behún <kabel@kernel.org>
Link: https://lore.kernel.org/r/2023121937-pants-heroics-17c1@gregkh
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/moxtet.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/moxtet.h b/include/linux/moxtet.h
index 79184948fab4..ac577699edfd 100644
--- a/include/linux/moxtet.h
+++ b/include/linux/moxtet.h
@@ -35,8 +35,6 @@ enum turris_mox_module_id {
 
 #define MOXTET_NIRQS	16
 
-extern struct bus_type moxtet_type;
-
 struct moxtet {
 	struct device			*dev;
 	struct mutex			lock;
-- 
cgit v1.2.3


From e1be24b2e1190a7662462e8e398189ac795339cd Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 19 Dec 2023 18:18:58 +0100
Subject: platform/surface: aggregator: make ssam_bus_type constant and static
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Now that the driver core can properly handle constant struct bus_type,
move the ssam_bus_type variable to be a constant structure as well,
placing it into read-only memory which can not be modified at runtime.

It's also never used outside of
drivers/platform/surface/aggregator/bus.c so make it static and don't
export it as no one is using it.

Cc: Maximilian Luz <luzmaximilian@gmail.com>
Cc: Hans de Goede <hdegoede@redhat.com>
Cc: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Cc:  <platform-driver-x86@vger.kernel.org>
Reviewed-by: Maximilian Luz <luzmaximilian@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/2023121957-tapered-upswing-8326@gregkh
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/platform/surface/aggregator/bus.c | 5 +++--
 include/linux/surface_aggregator/device.h | 1 -
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/platform/surface/aggregator/bus.c b/drivers/platform/surface/aggregator/bus.c
index 42ccd7f1c9b9..118caa651bec 100644
--- a/drivers/platform/surface/aggregator/bus.c
+++ b/drivers/platform/surface/aggregator/bus.c
@@ -35,6 +35,8 @@ static struct attribute *ssam_device_attrs[] = {
 };
 ATTRIBUTE_GROUPS(ssam_device);
 
+static const struct bus_type ssam_bus_type;
+
 static int ssam_device_uevent(const struct device *dev, struct kobj_uevent_env *env)
 {
 	const struct ssam_device *sdev = to_ssam_device(dev);
@@ -329,13 +331,12 @@ static void ssam_bus_remove(struct device *dev)
 		sdrv->remove(to_ssam_device(dev));
 }
 
-struct bus_type ssam_bus_type = {
+static const struct bus_type ssam_bus_type = {
 	.name   = "surface_aggregator",
 	.match  = ssam_bus_match,
 	.probe  = ssam_bus_probe,
 	.remove = ssam_bus_remove,
 };
-EXPORT_SYMBOL_GPL(ssam_bus_type);
 
 /**
  * __ssam_device_driver_register() - Register a SSAM client device driver.
diff --git a/include/linux/surface_aggregator/device.h b/include/linux/surface_aggregator/device.h
index 42b249b4c24b..8cd8c38cf3f3 100644
--- a/include/linux/surface_aggregator/device.h
+++ b/include/linux/surface_aggregator/device.h
@@ -193,7 +193,6 @@ struct ssam_device_driver {
 
 #ifdef CONFIG_SURFACE_AGGREGATOR_BUS
 
-extern struct bus_type ssam_bus_type;
 extern const struct device_type ssam_device_type;
 
 /**
-- 
cgit v1.2.3


From 0c4b2255b7afbcc80f4efcc8f67425162f49c263 Mon Sep 17 00:00:00 2001
From: Jay Buddhabhatti <jay.buddhabhatti@amd.com>
Date: Mon, 18 Dec 2023 21:50:24 -0800
Subject: firmware: xilinx: Export function to use in other module

Export zynqmp_pm_get_family_info() to access and find family information
in other module.

Signed-off-by: Jay Buddhabhatti <jay.buddhabhatti@amd.com>
Link: https://lore.kernel.org/r/20231219055025.27570-2-jay.buddhabhatti@amd.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/xilinx/zynqmp.c     | 3 ++-
 include/linux/firmware/xlnx-zynqmp.h | 6 ++++++
 2 files changed, 8 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c
index 73cae6ef83ec..79789f0563f6 100644
--- a/drivers/firmware/xilinx/zynqmp.c
+++ b/drivers/firmware/xilinx/zynqmp.c
@@ -463,7 +463,7 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_get_chipid);
  *
  * Return: Returns status, either success or error+reason
  */
-static int zynqmp_pm_get_family_info(u32 *family, u32 *subfamily)
+int zynqmp_pm_get_family_info(u32 *family, u32 *subfamily)
 {
 	u32 ret_payload[PAYLOAD_ARG_CNT];
 	u32 idcode;
@@ -488,6 +488,7 @@ static int zynqmp_pm_get_family_info(u32 *family, u32 *subfamily)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(zynqmp_pm_get_family_info);
 
 /**
  * zynqmp_pm_get_trustzone_version() - Get secure trustzone firmware version
diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h
index 1478f691cc10..06f4e6eaf13e 100644
--- a/include/linux/firmware/xlnx-zynqmp.h
+++ b/include/linux/firmware/xlnx-zynqmp.h
@@ -524,6 +524,7 @@ int zynqmp_pm_invoke_fn(u32 pm_api_id, u32 *ret_payload, u32 num_args, ...);
 #if IS_REACHABLE(CONFIG_ZYNQMP_FIRMWARE)
 int zynqmp_pm_get_api_version(u32 *version);
 int zynqmp_pm_get_chipid(u32 *idcode, u32 *version);
+int zynqmp_pm_get_family_info(u32 *family, u32 *subfamily);
 int zynqmp_pm_query_data(struct zynqmp_pm_query_data qdata, u32 *out);
 int zynqmp_pm_clock_enable(u32 clock_id);
 int zynqmp_pm_clock_disable(u32 clock_id);
@@ -602,6 +603,11 @@ static inline int zynqmp_pm_get_chipid(u32 *idcode, u32 *version)
 	return -ENODEV;
 }
 
+static inline int zynqmp_pm_get_family_info(u32 *family, u32 *subfamily)
+{
+	return -ENODEV;
+}
+
 static inline int zynqmp_pm_query_data(struct zynqmp_pm_query_data qdata,
 				       u32 *out)
 {
-- 
cgit v1.2.3


From 97d62760e441af9ed393e127a46172f9534b5808 Mon Sep 17 00:00:00 2001
From: Jay Buddhabhatti <jay.buddhabhatti@amd.com>
Date: Mon, 18 Dec 2023 21:50:25 -0800
Subject: drivers: soc: xilinx: add check for platform

Some error event IDs for Versal and Versal NET are different.
Both the platforms should access their respective error event
IDs so use sub_family_code to check for platform and check
error IDs for respective platforms. The family code is passed
via platform data to avoid platform detection again.
Platform data is setup when even driver is registered.

Signed-off-by: Jay Buddhabhatti <jay.buddhabhatti@amd.com>
Link: https://lore.kernel.org/r/20231219055025.27570-3-jay.buddhabhatti@amd.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/edac/versal_edac.c              |  4 ++--
 drivers/soc/xilinx/xlnx_event_manager.c | 25 ++++++++++++++++++++-----
 include/linux/firmware/xlnx-zynqmp.h    | 16 ++++++++++++----
 3 files changed, 34 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/edac/versal_edac.c b/drivers/edac/versal_edac.c
index 87e730dfefa0..116ed9b375de 100644
--- a/drivers/edac/versal_edac.c
+++ b/drivers/edac/versal_edac.c
@@ -1005,7 +1005,7 @@ static int mc_probe(struct platform_device *pdev)
 		goto free_edac_mc;
 	}
 
-	rc = xlnx_register_event(PM_NOTIFY_CB, EVENT_ERROR_PMC_ERR1,
+	rc = xlnx_register_event(PM_NOTIFY_CB, VERSAL_EVENT_ERROR_PMC_ERR1,
 				 XPM_EVENT_ERROR_MASK_DDRMC_CR | XPM_EVENT_ERROR_MASK_DDRMC_NCR |
 				 XPM_EVENT_ERROR_MASK_NOC_CR | XPM_EVENT_ERROR_MASK_NOC_NCR,
 				 false, err_callback, mci);
@@ -1042,7 +1042,7 @@ static int mc_remove(struct platform_device *pdev)
 	debugfs_remove_recursive(priv->debugfs);
 #endif
 
-	xlnx_unregister_event(PM_NOTIFY_CB, EVENT_ERROR_PMC_ERR1,
+	xlnx_unregister_event(PM_NOTIFY_CB, VERSAL_EVENT_ERROR_PMC_ERR1,
 			      XPM_EVENT_ERROR_MASK_DDRMC_CR |
 			      XPM_EVENT_ERROR_MASK_NOC_CR |
 			      XPM_EVENT_ERROR_MASK_NOC_NCR |
diff --git a/drivers/soc/xilinx/xlnx_event_manager.c b/drivers/soc/xilinx/xlnx_event_manager.c
index 27a8d89a0a09..2ce4c8e01f57 100644
--- a/drivers/soc/xilinx/xlnx_event_manager.c
+++ b/drivers/soc/xilinx/xlnx_event_manager.c
@@ -77,11 +77,26 @@ struct registered_event_data {
 
 static bool xlnx_is_error_event(const u32 node_id)
 {
-	if (node_id == EVENT_ERROR_PMC_ERR1 ||
-	    node_id == EVENT_ERROR_PMC_ERR2 ||
-	    node_id == EVENT_ERROR_PSM_ERR1 ||
-	    node_id == EVENT_ERROR_PSM_ERR2)
-		return true;
+	u32 pm_family_code, pm_sub_family_code;
+
+	zynqmp_pm_get_family_info(&pm_family_code, &pm_sub_family_code);
+
+	if (pm_sub_family_code == VERSAL_SUB_FAMILY_CODE) {
+		if (node_id == VERSAL_EVENT_ERROR_PMC_ERR1 ||
+		    node_id == VERSAL_EVENT_ERROR_PMC_ERR2 ||
+		    node_id == VERSAL_EVENT_ERROR_PSM_ERR1 ||
+		    node_id == VERSAL_EVENT_ERROR_PSM_ERR2)
+			return true;
+	} else {
+		if (node_id == VERSAL_NET_EVENT_ERROR_PMC_ERR1 ||
+		    node_id == VERSAL_NET_EVENT_ERROR_PMC_ERR2 ||
+		    node_id == VERSAL_NET_EVENT_ERROR_PMC_ERR3 ||
+		    node_id == VERSAL_NET_EVENT_ERROR_PSM_ERR1 ||
+		    node_id == VERSAL_NET_EVENT_ERROR_PSM_ERR2 ||
+		    node_id == VERSAL_NET_EVENT_ERROR_PSM_ERR3 ||
+		    node_id == VERSAL_NET_EVENT_ERROR_PSM_ERR4)
+			return true;
+	}
 
 	return false;
 }
diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h
index 06f4e6eaf13e..9a7e52739251 100644
--- a/include/linux/firmware/xlnx-zynqmp.h
+++ b/include/linux/firmware/xlnx-zynqmp.h
@@ -95,10 +95,18 @@
 /*
  * Node IDs for the Error Events.
  */
-#define EVENT_ERROR_PMC_ERR1	(0x28100000U)
-#define EVENT_ERROR_PMC_ERR2	(0x28104000U)
-#define EVENT_ERROR_PSM_ERR1	(0x28108000U)
-#define EVENT_ERROR_PSM_ERR2	(0x2810C000U)
+#define VERSAL_EVENT_ERROR_PMC_ERR1	(0x28100000U)
+#define VERSAL_EVENT_ERROR_PMC_ERR2	(0x28104000U)
+#define VERSAL_EVENT_ERROR_PSM_ERR1	(0x28108000U)
+#define VERSAL_EVENT_ERROR_PSM_ERR2	(0x2810C000U)
+
+#define VERSAL_NET_EVENT_ERROR_PMC_ERR1	(0x28100000U)
+#define VERSAL_NET_EVENT_ERROR_PMC_ERR2	(0x28104000U)
+#define VERSAL_NET_EVENT_ERROR_PMC_ERR3	(0x28108000U)
+#define VERSAL_NET_EVENT_ERROR_PSM_ERR1	(0x2810C000U)
+#define VERSAL_NET_EVENT_ERROR_PSM_ERR2	(0x28110000U)
+#define VERSAL_NET_EVENT_ERROR_PSM_ERR3	(0x28114000U)
+#define VERSAL_NET_EVENT_ERROR_PSM_ERR4	(0x28118000U)
 
 /* ZynqMP SD tap delay tuning */
 #define SD_ITAPDLY	0xFF180314
-- 
cgit v1.2.3


From 4c8530dc7d7da4abe97d65e8e038ce9852491369 Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <dima@arista.com>
Date: Thu, 4 Jan 2024 13:42:39 +0000
Subject: net/tcp: Only produce AO/MD5 logs if there are any keys

User won't care about inproper hash options in the TCP header if they
don't use neither TCP-AO nor TCP-MD5. Yet, those logs can add up in
syslog, while not being a real concern to the host admin:
> kernel: TCP: TCP segment has incorrect auth options set for XX.20.239.12.54681->XX.XX.90.103.80 [S]

Keep silent and avoid logging when there aren't any keys in the system.

Side-note: I also defined static_branch_tcp_*() helpers to avoid more
ifdeffery, going to remove more ifdeffery further with their help.

Reported-by: Christian Kujau <lists@nerdbynature.de>
Closes: https://lore.kernel.org/all/f6b59324-1417-566f-a976-ff2402718a8d@nerdbynature.de/
Signed-off-by: Dmitry Safonov <dima@arista.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Fixes: 2717b5adea9e ("net/tcp: Add tcp_hash_fail() ratelimited logs")
Link: https://lore.kernel.org/r/20240104-tcp_hash_fail-logs-v1-1-ff3e1f6f9e72@arista.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/tcp.h    |  2 --
 include/net/tcp_ao.h | 26 +++++++++++++++++++++++---
 2 files changed, 23 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 144ba48bb07b..87f0e6c2e1f2 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1788,8 +1788,6 @@ struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk,
 					 const struct sock *addr_sk);
 
 #ifdef CONFIG_TCP_MD5SIG
-#include <linux/jump_label.h>
-extern struct static_key_false_deferred tcp_md5_needed;
 struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index,
 					   const union tcp_md5_addr *addr,
 					   int family, bool any_l3index);
diff --git a/include/net/tcp_ao.h b/include/net/tcp_ao.h
index 647781080613..b04afced4cc9 100644
--- a/include/net/tcp_ao.h
+++ b/include/net/tcp_ao.h
@@ -127,12 +127,35 @@ struct tcp_ao_info {
 	struct rcu_head		rcu;
 };
 
+#ifdef CONFIG_TCP_MD5SIG
+#include <linux/jump_label.h>
+extern struct static_key_false_deferred tcp_md5_needed;
+#define static_branch_tcp_md5()	static_branch_unlikely(&tcp_md5_needed.key)
+#else
+#define static_branch_tcp_md5()	false
+#endif
+#ifdef CONFIG_TCP_AO
+/* TCP-AO structures and functions */
+#include <linux/jump_label.h>
+extern struct static_key_false_deferred tcp_ao_needed;
+#define static_branch_tcp_ao()	static_branch_unlikely(&tcp_ao_needed.key)
+#else
+#define static_branch_tcp_ao()	false
+#endif
+
+static inline bool tcp_hash_should_produce_warnings(void)
+{
+	return static_branch_tcp_md5() || static_branch_tcp_ao();
+}
+
 #define tcp_hash_fail(msg, family, skb, fmt, ...)			\
 do {									\
 	const struct tcphdr *th = tcp_hdr(skb);				\
 	char hdr_flags[6];						\
 	char *f = hdr_flags;						\
 									\
+	if (!tcp_hash_should_produce_warnings())			\
+		break;							\
 	if (th->fin)							\
 		*f++ = 'F';						\
 	if (th->syn)							\
@@ -159,9 +182,6 @@ do {									\
 
 #ifdef CONFIG_TCP_AO
 /* TCP-AO structures and functions */
-#include <linux/jump_label.h>
-extern struct static_key_false_deferred tcp_ao_needed;
-
 struct tcp4_ao_context {
 	__be32		saddr;
 	__be32		daddr;
-- 
cgit v1.2.3


From 98e20e5e13d2811898921f999288be7151a11954 Mon Sep 17 00:00:00 2001
From: Quentin Deslandes <qde@naccy.de>
Date: Tue, 26 Dec 2023 14:07:42 +0100
Subject: bpfilter: remove bpfilter

bpfilter was supposed to convert iptables filtering rules into
BPF programs on the fly, from the kernel, through a usermode
helper. The base code for the UMH was introduced in 2018, and
couple of attempts (2, 3) tried to introduce the BPF program
generate features but were abandoned.

bpfilter now sits in a kernel tree unused and unusable, occasionally
causing confusion amongst Linux users (4, 5).

As bpfilter is now developed in a dedicated repository on GitHub (6),
it was suggested a couple of times this year (LSFMM/BPF 2023,
LPC 2023) to remove the deprecated kernel part of the project. This
is the purpose of this patch.

[1]: https://lore.kernel.org/lkml/20180522022230.2492505-1-ast@kernel.org/
[2]: https://lore.kernel.org/bpf/20210829183608.2297877-1-me@ubique.spb.ru/#t
[3]: https://lore.kernel.org/lkml/20221224000402.476079-1-qde@naccy.de/
[4]: https://dxuuu.xyz/bpfilter.html
[5]: https://github.com/linuxkit/linuxkit/pull/3904
[6]: https://github.com/facebook/bpfilter

Signed-off-by: Quentin Deslandes <qde@naccy.de>
Link: https://lore.kernel.org/r/20231226130745.465988-1-qde@naccy.de
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/loongarch/configs/loongson3_defconfig |   1 -
 include/linux/bpfilter.h                   |  24 -----
 include/uapi/linux/bpfilter.h              |  21 -----
 net/Kconfig                                |   2 -
 net/Makefile                               |   1 -
 net/bpfilter/.gitignore                    |   2 -
 net/bpfilter/Kconfig                       |  23 -----
 net/bpfilter/Makefile                      |  20 -----
 net/bpfilter/bpfilter_kern.c               | 136 -----------------------------
 net/bpfilter/bpfilter_umh_blob.S           |   7 --
 net/bpfilter/main.c                        |  64 --------------
 net/bpfilter/msgfmt.h                      |  17 ----
 net/ipv4/Makefile                          |   2 -
 net/ipv4/bpfilter/Makefile                 |   2 -
 net/ipv4/bpfilter/sockopt.c                |  71 ---------------
 net/ipv4/ip_sockglue.c                     |  12 ---
 tools/bpf/bpftool/feature.c                |   4 -
 tools/testing/selftests/bpf/config.aarch64 |   1 -
 tools/testing/selftests/bpf/config.s390x   |   1 -
 tools/testing/selftests/bpf/config.x86_64  |   1 -
 tools/testing/selftests/hid/config         |   1 -
 21 files changed, 413 deletions(-)
 delete mode 100644 include/linux/bpfilter.h
 delete mode 100644 include/uapi/linux/bpfilter.h
 delete mode 100644 net/bpfilter/.gitignore
 delete mode 100644 net/bpfilter/Kconfig
 delete mode 100644 net/bpfilter/Makefile
 delete mode 100644 net/bpfilter/bpfilter_kern.c
 delete mode 100644 net/bpfilter/bpfilter_umh_blob.S
 delete mode 100644 net/bpfilter/main.c
 delete mode 100644 net/bpfilter/msgfmt.h
 delete mode 100644 net/ipv4/bpfilter/Makefile
 delete mode 100644 net/ipv4/bpfilter/sockopt.c

(limited to 'include')

diff --git a/arch/loongarch/configs/loongson3_defconfig b/arch/loongarch/configs/loongson3_defconfig
index 9c333d133c30..60e331af9839 100644
--- a/arch/loongarch/configs/loongson3_defconfig
+++ b/arch/loongarch/configs/loongson3_defconfig
@@ -276,7 +276,6 @@ CONFIG_BRIDGE_EBT_T_NAT=m
 CONFIG_BRIDGE_EBT_ARP=m
 CONFIG_BRIDGE_EBT_IP=m
 CONFIG_BRIDGE_EBT_IP6=m
-CONFIG_BPFILTER=y
 CONFIG_IP_SCTP=m
 CONFIG_RDS=y
 CONFIG_L2TP=m
diff --git a/include/linux/bpfilter.h b/include/linux/bpfilter.h
deleted file mode 100644
index 736ded4905e0..000000000000
--- a/include/linux/bpfilter.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_BPFILTER_H
-#define _LINUX_BPFILTER_H
-
-#include <uapi/linux/bpfilter.h>
-#include <linux/usermode_driver.h>
-#include <linux/sockptr.h>
-
-struct sock;
-int bpfilter_ip_set_sockopt(struct sock *sk, int optname, sockptr_t optval,
-			    unsigned int optlen);
-int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval,
-			    int __user *optlen);
-
-struct bpfilter_umh_ops {
-	struct umd_info info;
-	/* since ip_getsockopt() can run in parallel, serialize access to umh */
-	struct mutex lock;
-	int (*sockopt)(struct sock *sk, int optname, sockptr_t optval,
-		       unsigned int optlen, bool is_set);
-	int (*start)(void);
-};
-extern struct bpfilter_umh_ops bpfilter_ops;
-#endif
diff --git a/include/uapi/linux/bpfilter.h b/include/uapi/linux/bpfilter.h
deleted file mode 100644
index cbc1f5813f50..000000000000
--- a/include/uapi/linux/bpfilter.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _UAPI_LINUX_BPFILTER_H
-#define _UAPI_LINUX_BPFILTER_H
-
-#include <linux/if.h>
-
-enum {
-	BPFILTER_IPT_SO_SET_REPLACE = 64,
-	BPFILTER_IPT_SO_SET_ADD_COUNTERS = 65,
-	BPFILTER_IPT_SET_MAX,
-};
-
-enum {
-	BPFILTER_IPT_SO_GET_INFO = 64,
-	BPFILTER_IPT_SO_GET_ENTRIES = 65,
-	BPFILTER_IPT_SO_GET_REVISION_MATCH = 66,
-	BPFILTER_IPT_SO_GET_REVISION_TARGET = 67,
-	BPFILTER_IPT_GET_MAX,
-};
-
-#endif /* _UAPI_LINUX_BPFILTER_H */
diff --git a/net/Kconfig b/net/Kconfig
index 3ec6bc98fa05..4adc47d0c9c2 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -233,8 +233,6 @@ source "net/bridge/netfilter/Kconfig"
 
 endif
 
-source "net/bpfilter/Kconfig"
-
 source "net/dccp/Kconfig"
 source "net/sctp/Kconfig"
 source "net/rds/Kconfig"
diff --git a/net/Makefile b/net/Makefile
index 4c4dc535453d..b06b5539e7a6 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -19,7 +19,6 @@ obj-$(CONFIG_TLS)		+= tls/
 obj-$(CONFIG_XFRM)		+= xfrm/
 obj-$(CONFIG_UNIX_SCM)		+= unix/
 obj-y				+= ipv6/
-obj-$(CONFIG_BPFILTER)		+= bpfilter/
 obj-$(CONFIG_PACKET)		+= packet/
 obj-$(CONFIG_NET_KEY)		+= key/
 obj-$(CONFIG_BRIDGE)		+= bridge/
diff --git a/net/bpfilter/.gitignore b/net/bpfilter/.gitignore
deleted file mode 100644
index f34e85ee8204..000000000000
--- a/net/bpfilter/.gitignore
+++ /dev/null
@@ -1,2 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-bpfilter_umh
diff --git a/net/bpfilter/Kconfig b/net/bpfilter/Kconfig
deleted file mode 100644
index 3d4a21462458..000000000000
--- a/net/bpfilter/Kconfig
+++ /dev/null
@@ -1,23 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-menuconfig BPFILTER
-	bool "BPF based packet filtering framework (BPFILTER)"
-	depends on BPF && INET
-	select USERMODE_DRIVER
-	help
-	  This builds experimental bpfilter framework that is aiming to
-	  provide netfilter compatible functionality via BPF
-
-if BPFILTER
-config BPFILTER_UMH
-	tristate "bpfilter kernel module with user mode helper"
-	depends on CC_CAN_LINK
-	depends on m || CC_CAN_LINK_STATIC
-	default m
-	help
-	  This builds bpfilter kernel module with embedded user mode helper
-
-	  Note: To compile this as built-in, your toolchain must support
-	  building static binaries, since rootfs isn't mounted at the time
-	  when __init functions are called and do_execv won't be able to find
-	  the elf interpreter.
-endif
diff --git a/net/bpfilter/Makefile b/net/bpfilter/Makefile
deleted file mode 100644
index cdac82b8c53a..000000000000
--- a/net/bpfilter/Makefile
+++ /dev/null
@@ -1,20 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-#
-# Makefile for the Linux BPFILTER layer.
-#
-
-userprogs := bpfilter_umh
-bpfilter_umh-objs := main.o
-userccflags += -I $(srctree)/tools/include/ -I $(srctree)/tools/include/uapi
-
-ifeq ($(CONFIG_BPFILTER_UMH), y)
-# builtin bpfilter_umh should be linked with -static
-# since rootfs isn't mounted at the time of __init
-# function is called and do_execv won't find elf interpreter
-userldflags += -static
-endif
-
-$(obj)/bpfilter_umh_blob.o: $(obj)/bpfilter_umh
-
-obj-$(CONFIG_BPFILTER_UMH) += bpfilter.o
-bpfilter-objs += bpfilter_kern.o bpfilter_umh_blob.o
diff --git a/net/bpfilter/bpfilter_kern.c b/net/bpfilter/bpfilter_kern.c
deleted file mode 100644
index 97e129e3f31c..000000000000
--- a/net/bpfilter/bpfilter_kern.c
+++ /dev/null
@@ -1,136 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/umh.h>
-#include <linux/bpfilter.h>
-#include <linux/sched.h>
-#include <linux/sched/signal.h>
-#include <linux/fs.h>
-#include <linux/file.h>
-#include "msgfmt.h"
-
-extern char bpfilter_umh_start;
-extern char bpfilter_umh_end;
-
-static void shutdown_umh(void)
-{
-	struct umd_info *info = &bpfilter_ops.info;
-	struct pid *tgid = info->tgid;
-
-	if (tgid) {
-		kill_pid(tgid, SIGKILL, 1);
-		wait_event(tgid->wait_pidfd, thread_group_exited(tgid));
-		umd_cleanup_helper(info);
-	}
-}
-
-static void __stop_umh(void)
-{
-	if (IS_ENABLED(CONFIG_INET))
-		shutdown_umh();
-}
-
-static int bpfilter_send_req(struct mbox_request *req)
-{
-	struct mbox_reply reply;
-	loff_t pos = 0;
-	ssize_t n;
-
-	if (!bpfilter_ops.info.tgid)
-		return -EFAULT;
-	pos = 0;
-	n = kernel_write(bpfilter_ops.info.pipe_to_umh, req, sizeof(*req),
-			   &pos);
-	if (n != sizeof(*req)) {
-		pr_err("write fail %zd\n", n);
-		goto stop;
-	}
-	pos = 0;
-	n = kernel_read(bpfilter_ops.info.pipe_from_umh, &reply, sizeof(reply),
-			&pos);
-	if (n != sizeof(reply)) {
-		pr_err("read fail %zd\n", n);
-		goto stop;
-	}
-	return reply.status;
-stop:
-	__stop_umh();
-	return -EFAULT;
-}
-
-static int bpfilter_process_sockopt(struct sock *sk, int optname,
-				    sockptr_t optval, unsigned int optlen,
-				    bool is_set)
-{
-	struct mbox_request req = {
-		.is_set		= is_set,
-		.pid		= current->pid,
-		.cmd		= optname,
-		.addr		= (uintptr_t)optval.user,
-		.len		= optlen,
-	};
-	if (sockptr_is_kernel(optval)) {
-		pr_err("kernel access not supported\n");
-		return -EFAULT;
-	}
-	return bpfilter_send_req(&req);
-}
-
-static int start_umh(void)
-{
-	struct mbox_request req = { .pid = current->pid };
-	int err;
-
-	/* fork usermode process */
-	err = fork_usermode_driver(&bpfilter_ops.info);
-	if (err)
-		return err;
-	pr_info("Loaded bpfilter_umh pid %d\n", pid_nr(bpfilter_ops.info.tgid));
-
-	/* health check that usermode process started correctly */
-	if (bpfilter_send_req(&req) != 0) {
-		shutdown_umh();
-		return -EFAULT;
-	}
-
-	return 0;
-}
-
-static int __init load_umh(void)
-{
-	int err;
-
-	err = umd_load_blob(&bpfilter_ops.info,
-			    &bpfilter_umh_start,
-			    &bpfilter_umh_end - &bpfilter_umh_start);
-	if (err)
-		return err;
-
-	mutex_lock(&bpfilter_ops.lock);
-	err = start_umh();
-	if (!err && IS_ENABLED(CONFIG_INET)) {
-		bpfilter_ops.sockopt = &bpfilter_process_sockopt;
-		bpfilter_ops.start = &start_umh;
-	}
-	mutex_unlock(&bpfilter_ops.lock);
-	if (err)
-		umd_unload_blob(&bpfilter_ops.info);
-	return err;
-}
-
-static void __exit fini_umh(void)
-{
-	mutex_lock(&bpfilter_ops.lock);
-	if (IS_ENABLED(CONFIG_INET)) {
-		shutdown_umh();
-		bpfilter_ops.start = NULL;
-		bpfilter_ops.sockopt = NULL;
-	}
-	mutex_unlock(&bpfilter_ops.lock);
-
-	umd_unload_blob(&bpfilter_ops.info);
-}
-module_init(load_umh);
-module_exit(fini_umh);
-MODULE_LICENSE("GPL");
diff --git a/net/bpfilter/bpfilter_umh_blob.S b/net/bpfilter/bpfilter_umh_blob.S
deleted file mode 100644
index 40311d10d2f2..000000000000
--- a/net/bpfilter/bpfilter_umh_blob.S
+++ /dev/null
@@ -1,7 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-	.section .init.rodata, "a"
-	.global bpfilter_umh_start
-bpfilter_umh_start:
-	.incbin "net/bpfilter/bpfilter_umh"
-	.global bpfilter_umh_end
-bpfilter_umh_end:
diff --git a/net/bpfilter/main.c b/net/bpfilter/main.c
deleted file mode 100644
index 291a92546246..000000000000
--- a/net/bpfilter/main.c
+++ /dev/null
@@ -1,64 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#define _GNU_SOURCE
-#include <sys/uio.h>
-#include <errno.h>
-#include <stdio.h>
-#include <sys/socket.h>
-#include <fcntl.h>
-#include <unistd.h>
-#include "../../include/uapi/linux/bpf.h"
-#include <asm/unistd.h>
-#include "msgfmt.h"
-
-FILE *debug_f;
-
-static int handle_get_cmd(struct mbox_request *cmd)
-{
-	switch (cmd->cmd) {
-	case 0:
-		return 0;
-	default:
-		break;
-	}
-	return -ENOPROTOOPT;
-}
-
-static int handle_set_cmd(struct mbox_request *cmd)
-{
-	return -ENOPROTOOPT;
-}
-
-static void loop(void)
-{
-	while (1) {
-		struct mbox_request req;
-		struct mbox_reply reply;
-		int n;
-
-		n = read(0, &req, sizeof(req));
-		if (n != sizeof(req)) {
-			fprintf(debug_f, "invalid request %d\n", n);
-			return;
-		}
-
-		reply.status = req.is_set ?
-			handle_set_cmd(&req) :
-			handle_get_cmd(&req);
-
-		n = write(1, &reply, sizeof(reply));
-		if (n != sizeof(reply)) {
-			fprintf(debug_f, "reply failed %d\n", n);
-			return;
-		}
-	}
-}
-
-int main(void)
-{
-	debug_f = fopen("/dev/kmsg", "w");
-	setvbuf(debug_f, 0, _IOLBF, 0);
-	fprintf(debug_f, "<5>Started bpfilter\n");
-	loop();
-	fclose(debug_f);
-	return 0;
-}
diff --git a/net/bpfilter/msgfmt.h b/net/bpfilter/msgfmt.h
deleted file mode 100644
index 98d121c62945..000000000000
--- a/net/bpfilter/msgfmt.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _NET_BPFILTER_MSGFMT_H
-#define _NET_BPFILTER_MSGFMT_H
-
-struct mbox_request {
-	__u64 addr;
-	__u32 len;
-	__u32 is_set;
-	__u32 cmd;
-	__u32 pid;
-};
-
-struct mbox_reply {
-	__u32 status;
-};
-
-#endif
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index e144a02a6a61..ec36d2ec059e 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -16,8 +16,6 @@ obj-y     := route.o inetpeer.o protocol.o \
 	     inet_fragment.o ping.o ip_tunnel_core.o gre_offload.o \
 	     metrics.o netlink.o nexthop.o udp_tunnel_stub.o
 
-obj-$(CONFIG_BPFILTER) += bpfilter/
-
 obj-$(CONFIG_NET_IP_TUNNEL) += ip_tunnel.o
 obj-$(CONFIG_SYSCTL) += sysctl_net_ipv4.o
 obj-$(CONFIG_PROC_FS) += proc.o
diff --git a/net/ipv4/bpfilter/Makefile b/net/ipv4/bpfilter/Makefile
deleted file mode 100644
index 00af5305e05a..000000000000
--- a/net/ipv4/bpfilter/Makefile
+++ /dev/null
@@ -1,2 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-obj-$(CONFIG_BPFILTER) += sockopt.o
diff --git a/net/ipv4/bpfilter/sockopt.c b/net/ipv4/bpfilter/sockopt.c
deleted file mode 100644
index 193bcc2acccc..000000000000
--- a/net/ipv4/bpfilter/sockopt.c
+++ /dev/null
@@ -1,71 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/uaccess.h>
-#include <linux/bpfilter.h>
-#include <uapi/linux/bpf.h>
-#include <linux/wait.h>
-#include <linux/kmod.h>
-#include <linux/fs.h>
-#include <linux/file.h>
-
-struct bpfilter_umh_ops bpfilter_ops;
-EXPORT_SYMBOL_GPL(bpfilter_ops);
-
-static int bpfilter_mbox_request(struct sock *sk, int optname, sockptr_t optval,
-				 unsigned int optlen, bool is_set)
-{
-	int err;
-	mutex_lock(&bpfilter_ops.lock);
-	if (!bpfilter_ops.sockopt) {
-		mutex_unlock(&bpfilter_ops.lock);
-		request_module("bpfilter");
-		mutex_lock(&bpfilter_ops.lock);
-
-		if (!bpfilter_ops.sockopt) {
-			err = -ENOPROTOOPT;
-			goto out;
-		}
-	}
-	if (bpfilter_ops.info.tgid &&
-	    thread_group_exited(bpfilter_ops.info.tgid))
-		umd_cleanup_helper(&bpfilter_ops.info);
-
-	if (!bpfilter_ops.info.tgid) {
-		err = bpfilter_ops.start();
-		if (err)
-			goto out;
-	}
-	err = bpfilter_ops.sockopt(sk, optname, optval, optlen, is_set);
-out:
-	mutex_unlock(&bpfilter_ops.lock);
-	return err;
-}
-
-int bpfilter_ip_set_sockopt(struct sock *sk, int optname, sockptr_t optval,
-			    unsigned int optlen)
-{
-	return bpfilter_mbox_request(sk, optname, optval, optlen, true);
-}
-
-int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval,
-			    int __user *optlen)
-{
-	int len;
-
-	if (get_user(len, optlen))
-		return -EFAULT;
-
-	return bpfilter_mbox_request(sk, optname, USER_SOCKPTR(optval), len,
-				     false);
-}
-
-static int __init bpfilter_sockopt_init(void)
-{
-	mutex_init(&bpfilter_ops.lock);
-	bpfilter_ops.info.tgid = NULL;
-	bpfilter_ops.info.driver_name = "bpfilter_umh";
-
-	return 0;
-}
-device_initcall(bpfilter_sockopt_init);
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 66247e8b429e..7aa9dc0e6760 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -47,8 +47,6 @@
 #include <linux/errqueue.h>
 #include <linux/uaccess.h>
 
-#include <linux/bpfilter.h>
-
 /*
  *	SOL_IP control messages.
  */
@@ -1411,11 +1409,6 @@ int ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
 		return -ENOPROTOOPT;
 
 	err = do_ip_setsockopt(sk, level, optname, optval, optlen);
-#if IS_ENABLED(CONFIG_BPFILTER_UMH)
-	if (optname >= BPFILTER_IPT_SO_SET_REPLACE &&
-	    optname < BPFILTER_IPT_SET_MAX)
-		err = bpfilter_ip_set_sockopt(sk, optname, optval, optlen);
-#endif
 #ifdef CONFIG_NETFILTER
 	/* we need to exclude all possible ENOPROTOOPTs except default case */
 	if (err == -ENOPROTOOPT && optname != IP_HDRINCL &&
@@ -1763,11 +1756,6 @@ int ip_getsockopt(struct sock *sk, int level,
 	err = do_ip_getsockopt(sk, level, optname,
 			       USER_SOCKPTR(optval), USER_SOCKPTR(optlen));
 
-#if IS_ENABLED(CONFIG_BPFILTER_UMH)
-	if (optname >= BPFILTER_IPT_SO_GET_INFO &&
-	    optname < BPFILTER_IPT_GET_MAX)
-		err = bpfilter_ip_get_sockopt(sk, optname, optval, optlen);
-#endif
 #ifdef CONFIG_NETFILTER
 	/* we need to exclude all possible ENOPROTOOPTs except default case */
 	if (err == -ENOPROTOOPT && optname != IP_PKTOPTIONS &&
diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c
index edda4fc2c4d0..708733b0ea06 100644
--- a/tools/bpf/bpftool/feature.c
+++ b/tools/bpf/bpftool/feature.c
@@ -426,10 +426,6 @@ static void probe_kernel_image_config(const char *define_prefix)
 		{ "CONFIG_BPF_STREAM_PARSER", },
 		/* xt_bpf module for passing BPF programs to netfilter  */
 		{ "CONFIG_NETFILTER_XT_MATCH_BPF", },
-		/* bpfilter back-end for iptables */
-		{ "CONFIG_BPFILTER", },
-		/* bpftilter module with "user mode helper" */
-		{ "CONFIG_BPFILTER_UMH", },
 
 		/* test_bpf module for BPF tests */
 		{ "CONFIG_TEST_BPF", },
diff --git a/tools/testing/selftests/bpf/config.aarch64 b/tools/testing/selftests/bpf/config.aarch64
index 29c8635c5722..3720b7611523 100644
--- a/tools/testing/selftests/bpf/config.aarch64
+++ b/tools/testing/selftests/bpf/config.aarch64
@@ -11,7 +11,6 @@ CONFIG_BLK_DEV_IO_TRACE=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_BONDING=y
-CONFIG_BPFILTER=y
 CONFIG_BPF_JIT_ALWAYS_ON=y
 CONFIG_BPF_JIT_DEFAULT_ON=y
 CONFIG_BPF_PRELOAD_UMD=y
diff --git a/tools/testing/selftests/bpf/config.s390x b/tools/testing/selftests/bpf/config.s390x
index e93330382849..706931a8c2c6 100644
--- a/tools/testing/selftests/bpf/config.s390x
+++ b/tools/testing/selftests/bpf/config.s390x
@@ -9,7 +9,6 @@ CONFIG_BPF_JIT_ALWAYS_ON=y
 CONFIG_BPF_JIT_DEFAULT_ON=y
 CONFIG_BPF_PRELOAD=y
 CONFIG_BPF_PRELOAD_UMD=y
-CONFIG_BPFILTER=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_CGROUP_DEVICE=y
 CONFIG_CGROUP_FREEZER=y
diff --git a/tools/testing/selftests/bpf/config.x86_64 b/tools/testing/selftests/bpf/config.x86_64
index b946088017f1..5680befae8c6 100644
--- a/tools/testing/selftests/bpf/config.x86_64
+++ b/tools/testing/selftests/bpf/config.x86_64
@@ -19,7 +19,6 @@ CONFIG_BOOTTIME_TRACING=y
 CONFIG_BPF_JIT_ALWAYS_ON=y
 CONFIG_BPF_PRELOAD=y
 CONFIG_BPF_PRELOAD_UMD=y
-CONFIG_BPFILTER=y
 CONFIG_BSD_DISKLABEL=y
 CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_CFS_BANDWIDTH=y
diff --git a/tools/testing/selftests/hid/config b/tools/testing/selftests/hid/config
index 4f425178b56f..1758b055f295 100644
--- a/tools/testing/selftests/hid/config
+++ b/tools/testing/selftests/hid/config
@@ -1,5 +1,4 @@
 CONFIG_BPF_EVENTS=y
-CONFIG_BPFILTER=y
 CONFIG_BPF_JIT_ALWAYS_ON=y
 CONFIG_BPF_JIT=y
 CONFIG_BPF_KPROBE_OVERRIDE=y
-- 
cgit v1.2.3


From 57331a59ac0d680f606403eb24edd3c35aecba31 Mon Sep 17 00:00:00 2001
From: Benjamin Coddington <bcodding@redhat.com>
Date: Thu, 4 Jan 2024 09:58:46 -0500
Subject: NFSv4.1: Use the nfs_client's rpc timeouts for backchannel

For backchannel requests that lookup the appropriate nfs_client, use the
state-management rpc_clnt's rpc_timeout parameters for the backchannel's
response.  When the nfs_client cannot be found, fall back to using the
xprt's default timeout parameters.

Signed-off-by: Benjamin Coddington <bcodding@redhat.com>
Tested-by: Chuck Lever <chuck.lever@oracle.com>
Tested-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/callback_xdr.c          |  5 +++++
 include/linux/sunrpc/bc_xprt.h |  3 ++-
 include/linux/sunrpc/sched.h   | 14 +++++++++++++-
 include/linux/sunrpc/svc.h     |  2 ++
 include/linux/sunrpc/xprt.h    | 11 -----------
 net/sunrpc/clnt.c              |  6 ++++--
 net/sunrpc/svc.c               | 11 ++++++++++-
 net/sunrpc/xprt.c              | 12 +++++++++---
 8 files changed, 45 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index 321af81c456e..9369488f2ed4 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -967,6 +967,11 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp)
 		nops--;
 	}
 
+	if (svc_is_backchannel(rqstp) && cps.clp) {
+		rqstp->bc_to_initval = cps.clp->cl_rpcclient->cl_timeout->to_initval;
+		rqstp->bc_to_retries = cps.clp->cl_rpcclient->cl_timeout->to_retries;
+	}
+
 	*hdr_res.status = status;
 	*hdr_res.nops = htonl(nops);
 	nfs4_cb_free_slot(&cps);
diff --git a/include/linux/sunrpc/bc_xprt.h b/include/linux/sunrpc/bc_xprt.h
index db30a159f9d5..f22bf915dcf6 100644
--- a/include/linux/sunrpc/bc_xprt.h
+++ b/include/linux/sunrpc/bc_xprt.h
@@ -20,7 +20,8 @@
 #ifdef CONFIG_SUNRPC_BACKCHANNEL
 struct rpc_rqst *xprt_lookup_bc_request(struct rpc_xprt *xprt, __be32 xid);
 void xprt_complete_bc_request(struct rpc_rqst *req, uint32_t copied);
-void xprt_init_bc_request(struct rpc_rqst *req, struct rpc_task *task);
+void xprt_init_bc_request(struct rpc_rqst *req, struct rpc_task *task,
+		const struct rpc_timeout *to);
 void xprt_free_bc_request(struct rpc_rqst *req);
 int xprt_setup_backchannel(struct rpc_xprt *, unsigned int min_reqs);
 void xprt_destroy_backchannel(struct rpc_xprt *, unsigned int max_reqs);
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index 8ada7dc802d3..2d61987b3545 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -37,6 +37,17 @@ struct rpc_wait {
 	struct list_head	timer_list;	/* Timer list */
 };
 
+/*
+ * This describes a timeout strategy
+ */
+struct rpc_timeout {
+	unsigned long		to_initval,		/* initial timeout */
+				to_maxval,		/* max timeout */
+				to_increment;		/* if !exponential */
+	unsigned int		to_retries;		/* max # of retries */
+	unsigned char		to_exponential;
+};
+
 /*
  * This is the RPC task struct
  */
@@ -205,7 +216,8 @@ struct rpc_wait_queue {
  */
 struct rpc_task *rpc_new_task(const struct rpc_task_setup *);
 struct rpc_task *rpc_run_task(const struct rpc_task_setup *);
-struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req);
+struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req,
+		struct rpc_timeout *timeout);
 void		rpc_put_task(struct rpc_task *);
 void		rpc_put_task_async(struct rpc_task *);
 bool		rpc_task_set_rpc_status(struct rpc_task *task, int rpc_status);
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index b10f987509cc..3331a1c2b47e 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -250,6 +250,8 @@ struct svc_rqst {
 	struct net		*rq_bc_net;	/* pointer to backchannel's
 						 * net namespace
 						 */
+	unsigned long	bc_to_initval;
+	unsigned int	bc_to_retries;
 	void **			rq_lease_breaker; /* The v4 client breaking a lease */
 	unsigned int		rq_status_counter; /* RPC processing counter */
 };
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index f85d3a0daca2..464f6a9492ab 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -30,17 +30,6 @@
 #define RPC_MAXCWND(xprt)	((xprt)->max_reqs << RPC_CWNDSHIFT)
 #define RPCXPRT_CONGESTED(xprt) ((xprt)->cong >= (xprt)->cwnd)
 
-/*
- * This describes a timeout strategy
- */
-struct rpc_timeout {
-	unsigned long		to_initval,		/* initial timeout */
-				to_maxval,		/* max timeout */
-				to_increment;		/* if !exponential */
-	unsigned int		to_retries;		/* max # of retries */
-	unsigned char		to_exponential;
-};
-
 enum rpc_display_format_t {
 	RPC_DISPLAY_ADDR = 0,
 	RPC_DISPLAY_PORT,
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 0b2c4b5484f5..19437b15ffc7 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1311,8 +1311,10 @@ static void call_bc_encode(struct rpc_task *task);
  * rpc_run_bc_task - Allocate a new RPC task for backchannel use, then run
  * rpc_execute against it
  * @req: RPC request
+ * @timeout: timeout values to use for this task
  */
-struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req)
+struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req,
+		struct rpc_timeout *timeout)
 {
 	struct rpc_task *task;
 	struct rpc_task_setup task_setup_data = {
@@ -1331,7 +1333,7 @@ struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req)
 		return task;
 	}
 
-	xprt_init_bc_request(req, task);
+	xprt_init_bc_request(req, task, timeout);
 
 	task->tk_action = call_bc_encode;
 	atomic_inc(&task->tk_count);
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 3f2ea7a0496f..3f714d33624b 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1557,6 +1557,7 @@ void svc_process_bc(struct rpc_rqst *req, struct svc_rqst *rqstp)
 {
 	struct rpc_task *task;
 	int proc_error;
+	struct rpc_timeout timeout;
 
 	/* Build the svc_rqst used by the common processing routine */
 	rqstp->rq_xid = req->rq_xid;
@@ -1602,8 +1603,16 @@ void svc_process_bc(struct rpc_rqst *req, struct svc_rqst *rqstp)
 		return;
 	}
 	/* Finally, send the reply synchronously */
+	if (rqstp->bc_to_initval > 0) {
+		timeout.to_initval = rqstp->bc_to_initval;
+		timeout.to_retries = rqstp->bc_to_initval;
+	} else {
+		timeout.to_initval = req->rq_xprt->timeout->to_initval;
+		timeout.to_initval = req->rq_xprt->timeout->to_retries;
+	}
 	memcpy(&req->rq_snd_buf, &rqstp->rq_res, sizeof(req->rq_snd_buf));
-	task = rpc_run_bc_task(req);
+	task = rpc_run_bc_task(req, &timeout);
+
 	if (IS_ERR(task))
 		return;
 
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 6cc9ffac962d..af13fdfa6672 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -1986,7 +1986,8 @@ void xprt_release(struct rpc_task *task)
 
 #ifdef CONFIG_SUNRPC_BACKCHANNEL
 void
-xprt_init_bc_request(struct rpc_rqst *req, struct rpc_task *task)
+xprt_init_bc_request(struct rpc_rqst *req, struct rpc_task *task,
+		const struct rpc_timeout *to)
 {
 	struct xdr_buf *xbufp = &req->rq_snd_buf;
 
@@ -1999,8 +2000,13 @@ xprt_init_bc_request(struct rpc_rqst *req, struct rpc_task *task)
 	 */
 	xbufp->len = xbufp->head[0].iov_len + xbufp->page_len +
 		xbufp->tail[0].iov_len;
-
-	xprt_init_majortimeo(task, req, req->rq_xprt->timeout);
+	/*
+	 * Backchannel Replies are sent with !RPC_TASK_SOFT and
+	 * RPC_TASK_NO_RETRANS_TIMEOUT. The major timeout setting
+	 * affects only how long each Reply waits to be sent when
+	 * a transport connection cannot be established.
+	 */
+	xprt_init_majortimeo(task, req, to);
 }
 #endif
 
-- 
cgit v1.2.3


From fe1eb24bd5ade085914248c527044e942f75e06a Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 4 Jan 2024 16:04:35 -0800
Subject: Revert "Introduce PHY listing and link_topology tracking"

This reverts commit 32bb4515e34469975abc936deb0a116c4a445817.
This reverts commit d078d480639a4f3b5fc2d56247afa38e0956483a.
This reverts commit fcc4b105caa4b844bf043375bf799c20a9c99db1.
This reverts commit 345237dbc1bdbb274c9fb9ec38976261ff4a40b8.
This reverts commit 7db69ec9cfb8b4ab50420262631fb2d1908b25bf.
This reverts commit 95132a018f00f5dad38bdcfd4180d1af955d46f6.
This reverts commit 63d5eaf35ac36cad00cfb3809d794ef0078c822b.
This reverts commit c29451aefcb42359905d18678de38e52eccb3bb5.
This reverts commit 2ab0edb505faa9ac90dee1732571390f074e8113.
This reverts commit dedd702a35793ab462fce4c737eeba0badf9718e.
This reverts commit 034fcc210349b873ece7356905be5c6ca11eef2a.
This reverts commit 9c5625f559ad6fe9f6f733c11475bf470e637d34.
This reverts commit 02018c544ef113e980a2349eba89003d6f399d22.

Looks like we need more time for reviews, and incremental
changes will be hard to make sense of. So revert.

Link: https://lore.kernel.org/all/ZZP6FV5sXEf+xd58@shell.armlinux.org.uk/
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/ethtool.yaml       |  68 ------
 Documentation/networking/ethtool-netlink.rst   |  51 -----
 Documentation/networking/index.rst             |   1 -
 Documentation/networking/phy-link-topology.rst | 121 ----------
 MAINTAINERS                                    |   2 -
 drivers/net/phy/Makefile                       |   2 +-
 drivers/net/phy/at803x.c                       |   2 -
 drivers/net/phy/marvell-88x2222.c              |   2 -
 drivers/net/phy/marvell.c                      |   2 -
 drivers/net/phy/marvell10g.c                   |   2 -
 drivers/net/phy/phy_device.c                   |  55 -----
 drivers/net/phy/phy_link_topology.c            |  66 ------
 drivers/net/phy/phylink.c                      |   3 +-
 drivers/net/phy/sfp-bus.c                      |  15 +-
 include/linux/netdevice.h                      |   4 +-
 include/linux/phy.h                            |   6 -
 include/linux/phy_link_topology.h              |  67 ------
 include/linux/phy_link_topology_core.h         |  19 --
 include/linux/sfp.h                            |   8 +-
 include/uapi/linux/ethtool.h                   |  16 --
 include/uapi/linux/ethtool_netlink.h           |  30 ---
 net/core/dev.c                                 |   3 -
 net/ethtool/Makefile                           |   2 +-
 net/ethtool/cabletest.c                        |  12 +-
 net/ethtool/netlink.c                          |  33 ---
 net/ethtool/netlink.h                          |  12 +-
 net/ethtool/phy.c                              | 306 -------------------------
 net/ethtool/plca.c                             |  13 +-
 net/ethtool/pse-pd.c                           |   9 +-
 net/ethtool/strset.c                           |  15 +-
 30 files changed, 35 insertions(+), 912 deletions(-)
 delete mode 100644 Documentation/networking/phy-link-topology.rst
 delete mode 100644 drivers/net/phy/phy_link_topology.c
 delete mode 100644 include/linux/phy_link_topology.h
 delete mode 100644 include/linux/phy_link_topology_core.h
 delete mode 100644 net/ethtool/phy.c

(limited to 'include')

diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml
index 7f6fb1f61dd4..197208f419dc 100644
--- a/Documentation/netlink/specs/ethtool.yaml
+++ b/Documentation/netlink/specs/ethtool.yaml
@@ -16,11 +16,6 @@ definitions:
     name: stringset
     type: enum
     entries: []
-  -
-    name: phy-upstream-type
-    enum-name:
-    type: enum
-    entries: [ mac, phy ]
 
 attribute-sets:
   -
@@ -35,9 +30,6 @@ attribute-sets:
       -
         name: flags
         type: u32
-      -
-        name: phy-index
-        type: u32
 
   -
     name: bitset-bit
@@ -950,45 +942,6 @@ attribute-sets:
       -
         name: burst-tmr
         type: u32
-  -
-    name: phy-upstream
-    attributes:
-      -
-        name: index
-        type: u32
-      -
-        name: sfp-name
-        type: string
-  -
-    name: phy
-    attributes:
-      -
-        name: header
-        type: nest
-        nested-attributes: header
-      -
-        name: index
-        type: u32
-      -
-        name: drvname
-        type: string
-      -
-        name: name
-        type: string
-      -
-        name: upstream-type
-        type: u8
-        enum: phy-upstream-type
-      -
-        name: upstream
-        type: nest
-        nested-attributes: phy-upstream
-      -
-        name: downstream-sfp-name
-        type: string
-      -
-        name: id
-        type: u32
 
 operations:
   enum-model: directional
@@ -1740,24 +1693,3 @@ operations:
       name: mm-ntf
       doc: Notification for change in MAC Merge configuration.
       notify: mm-get
-    -
-      name: phy-get
-      doc: Get PHY devices attached to an interface
-
-      attribute-set: phy
-
-      do: &phy-get-op
-        request:
-          attributes:
-            - header
-        reply:
-          attributes:
-            - header
-            - index
-            - drvname
-            - name
-            - upstream-type
-            - upstream
-            - downstream-sfp-name
-            - id
-      dump: *phy-get-op
diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst
index 97ff787a7dd8..d583d9abf2f8 100644
--- a/Documentation/networking/ethtool-netlink.rst
+++ b/Documentation/networking/ethtool-netlink.rst
@@ -57,7 +57,6 @@ Structure of this header is
   ``ETHTOOL_A_HEADER_DEV_INDEX``  u32     device ifindex
   ``ETHTOOL_A_HEADER_DEV_NAME``   string  device name
   ``ETHTOOL_A_HEADER_FLAGS``      u32     flags common for all requests
-  ``ETHTOOL_A_HEADER_PHY_INDEX``  u32     phy device index
   ==============================  ======  =============================
 
 ``ETHTOOL_A_HEADER_DEV_INDEX`` and ``ETHTOOL_A_HEADER_DEV_NAME`` identify the
@@ -82,12 +81,6 @@ the behaviour is backward compatible, i.e. requests from old clients not aware
 of the flag should be interpreted the way the client expects. A client must
 not set flags it does not understand.
 
-``ETHTOOL_A_HEADER_PHY_INDEX`` identify the ethernet PHY the message relates to.
-As there are numerous commands that are related to PHY configuration, and because
-we can have more than one PHY on the link, the PHY index can be passed in the
-request for the commands that needs it. It is however not mandatory, and if it
-is not passed for commands that target a PHY, the net_device.phydev pointer
-is used, as a fallback that keeps the legacy behaviour.
 
 Bit sets
 ========
@@ -2011,49 +2004,6 @@ The attributes are propagated to the driver through the following structure:
 .. kernel-doc:: include/linux/ethtool.h
     :identifiers: ethtool_mm_cfg
 
-PHY_GET
-=======
-
-Retrieve information about a given Ethernet PHY sitting on the link. As there
-can be more than one PHY, the DUMP operation can be used to list the PHYs
-present on a given interface, by passing an interface index or name in
-the dump request
-
-Request contents:
-
-  ====================================  ======  ==========================
-  ``ETHTOOL_A_PHY_HEADER``              nested  request header
-  ====================================  ======  ==========================
-
-Kernel response contents:
-
-  ===================================== ======  ==========================
-  ``ETHTOOL_A_PHY_HEADER``              nested  request header
-  ``ETHTOOL_A_PHY_INDEX``               u32     the phy's unique index, that can
-                                                be used for phy-specific requests
-  ``ETHTOOL_A_PHY_DRVNAME``             string  the phy driver name
-  ``ETHTOOL_A_PHY_NAME``                string  the phy device name
-  ``ETHTOOL_A_PHY_UPSTREAM_TYPE``       u32     the type of device this phy is
-                                                connected to
-  ``ETHTOOL_A_PHY_UPSTREAM_PHY``        nested  if the phy is connected to another
-                                                phy, this nest contains info on
-                                                that connection
-  ``ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME`` string  if the phy controls an sfp bus,
-                                                the name of the sfp bus
-  ``ETHTOOL_A_PHY_ID``                  u32     the phy id if the phy is C22
-  ===================================== ======  ==========================
-
-When ``ETHTOOL_A_PHY_UPSTREAM_TYPE`` is PHY_UPSTREAM_PHY, the PHY's parent is
-another PHY. Information on the parent PHY will be set in the
-``ETHTOOL_A_PHY_UPSTREAM_PHY`` nest, which has the following structure :
-
-  =================================== ======  ==========================
-  ``ETHTOOL_A_PHY_UPSTREAM_INDEX``    u32     the PHY index of the upstream PHY
-  ``ETHTOOL_A_PHY_UPSTREAM_SFP_NAME`` string  if this PHY is connected to it's
-                                                parent PHY through an SFP bus, the
-                                                name of this sfp bus
-  =================================== ======  ==========================
-
 Request translation
 ===================
 
@@ -2160,5 +2110,4 @@ are netlink only.
   n/a                                 ``ETHTOOL_MSG_PLCA_GET_STATUS``
   n/a                                 ``ETHTOOL_MSG_MM_GET``
   n/a                                 ``ETHTOOL_MSG_MM_SET``
-  n/a                                 ``ETHTOOL_MSG_PHY_GET``
   =================================== =====================================
diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst
index a2c45a75a4a6..69f3d6dcd9fd 100644
--- a/Documentation/networking/index.rst
+++ b/Documentation/networking/index.rst
@@ -88,7 +88,6 @@ Contents:
    operstates
    packet_mmap
    phonet
-   phy-link-topology
    pktgen
    plip
    ppp_generic
diff --git a/Documentation/networking/phy-link-topology.rst b/Documentation/networking/phy-link-topology.rst
deleted file mode 100644
index 1fd8e904ef4b..000000000000
--- a/Documentation/networking/phy-link-topology.rst
+++ /dev/null
@@ -1,121 +0,0 @@
-.. SPDX-License-Identifier: GPL-2.0
-
-=================
-PHY link topology
-=================
-
-Overview
-========
-
-The PHY link topology representation in the networking stack aims at representing
-the hardware layout for any given Ethernet link.
-
-An Ethernet Interface from userspace's point of view is nothing but a
-:c:type:`struct net_device <net_device>`, which exposes configuration options
-through the legacy ioctls and the ethool netlink commands. The base assumption
-when designing these configuration channels were that the link looked
-something like this ::
-
-  +-----------------------+        +----------+      +--------------+
-  | Ethernet Controller / |        | Ethernet |      | Connector /  |
-  |       MAC             | ------ |   PHY    | ---- |    Port      | ---... to LP
-  +-----------------------+        +----------+      +--------------+
-  struct net_device               struct phy_device
-
-Commands that needs to configure the PHY will go through the net_device.phydev
-field to reach the PHY and perform the relevant configuration.
-
-This assumption falls apart in more complex topologies that can arise when,
-for example, using SFP transceivers (although that's not the only specific case).
-
-Here, we have 2 basic scenarios. Either the MAC is able to output a serialized
-interface, that can directly be fed to an SFP cage, such as SGMII, 1000BaseX,
-10GBaseR, etc.
-
-The link topology then looks like this (when an SFP module is inserted) ::
-
-  +-----+  SGMII  +------------+
-  | MAC | ------- | SFP Module |
-  +-----+         +------------+
-
-Knowing that some modules embed a PHY, the actual link is more like ::
-
-  +-----+  SGMII   +--------------+
-  | MAC | -------- | PHY (on SFP) |
-  +-----+          +--------------+
-
-In this case, the SFP PHY is handled by phylib, and registered by phylink through
-its SFP upstream ops.
-
-Now some Ethernet controllers aren't able to output a serialized interface, so
-we can't directly connect them to an SFP cage. However, some PHYs can be used
-as media-converters, to translate the non-serialized MAC MII interface to a
-serialized MII interface fed to the SFP ::
-
-  +-----+  RGMII  +-----------------------+  SGMII  +--------------+
-  | MAC | ------- | PHY (media converter) | ------- | PHY (on SFP) |
-  +-----+         +-----------------------+         +--------------+
-
-This is where the model of having a single net_device.phydev pointer shows its
-limitations, as we now have 2 PHYs on the link.
-
-The phy_link topology framework aims at providing a way to keep track of every
-PHY on the link, for use by both kernel drivers and subsystems, but also to
-report the topology to userspace, allowing to target individual PHYs in configuration
-commands.
-
-API
-===
-
-The :c:type:`struct phy_link_topology <phy_link_topology>` is a per-netdevice
-resource, that gets initialized at netdevice creation. Once it's initialized,
-it is then possible to register PHYs to the topology through :
-
-:c:func:`phy_link_topo_add_phy`
-
-Besides registering the PHY to the topology, this call will also assign a unique
-index to the PHY, which can then be reported to userspace to refer to this PHY
-(akin to the ifindex). This index is a u32, ranging from 1 to U32_MAX. The value
-0 is reserved to indicate the PHY doesn't belong to any topology yet.
-
-The PHY can then be removed from the topology through
-
-:c:func:`phy_link_topo_del_phy`
-
-These function are already hooked into the phylib subsystem, so all PHYs that
-are linked to a net_device through :c:func:`phy_attach_direct` will automatically
-join the netdev's topology.
-
-PHYs that are on a SFP module will also be automatically registered IF the SFP
-upstream is phylink (so, no media-converter).
-
-PHY drivers that can be used as SFP upstream need to call :c:func:`phy_sfp_attach_phy`
-and :c:func:`phy_sfp_detach_phy`, which can be used as a
-.attach_phy / .detach_phy implementation for the
-:c:type:`struct sfp_upstream_ops <sfp_upstream_ops>`.
-
-UAPI
-====
-
-There exist a set of netlink commands to query the link topology from userspace,
-see ``Documentation/networking/ethtool-netlink.rst``.
-
-The whole point of having a topology representation is to assign the phyindex
-field in :c:type:`struct phy_device <phy_device>`. This index is reported to
-userspace using the ``ETHTOOL_MSG_PHY_GET`` ethtnl command. Performing a DUMP operation
-will result in all PHYs from all net_device being listed. The DUMP command
-accepts either a ``ETHTOOL_A_HEADER_DEV_INDEX`` or ``ETHTOOL_A_HEADER_DEV_NAME``
-to be passed in the request to filter the DUMP to a single net_device.
-
-The retrieved index can then be passed as a request parameter using the
-``ETHTOOL_A_HEADER_PHY_INDEX`` field in the following ethnl commands :
-
-* ``ETHTOOL_MSG_STRSET_GET`` to get the stats string set from a given PHY
-* ``ETHTOOL_MSG_CABLE_TEST_ACT`` and ``ETHTOOL_MSG_CABLE_TEST_ACT``, to perform
-  cable testing on a given PHY on the link (most likely the outermost PHY)
-* ``ETHTOOL_MSG_PSE_SET`` and ``ETHTOOL_MSG_PSE_GET`` for PHY-controlled PoE and PSE settings
-* ``ETHTOOL_MSG_PLCA_GET_CFG``, ``ETHTOOL_MSG_PLCA_SET_CFG`` and ``ETHTOOL_MSG_PLCA_GET_STATUS``
-  to set the PLCA (Physical Layer Collision Avoidance) parameters
-
-Note that the PHY index can be passed to other requests, which will silently
-ignore it if present and irrelevant.
diff --git a/MAINTAINERS b/MAINTAINERS
index 79ac49b113dc..2b916990d7f0 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7871,8 +7871,6 @@ F:	include/linux/mii.h
 F:	include/linux/of_net.h
 F:	include/linux/phy.h
 F:	include/linux/phy_fixed.h
-F:	include/linux/phy_link_topology.h
-F:	include/linux/phy_link_topology_core.h
 F:	include/linux/phylib_stubs.h
 F:	include/linux/platform_data/mdio-bcm-unimac.h
 F:	include/linux/platform_data/mdio-gpio.h
diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile
index f218954fd7a8..6097afd44392 100644
--- a/drivers/net/phy/Makefile
+++ b/drivers/net/phy/Makefile
@@ -2,7 +2,7 @@
 # Makefile for Linux PHY drivers
 
 libphy-y			:= phy.o phy-c45.o phy-core.o phy_device.o \
-				   linkmode.o phy_link_topology.o
+				   linkmode.o
 mdio-bus-y			+= mdio_bus.o mdio_device.o
 
 ifdef CONFIG_MDIO_DEVICE
diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c
index aaf6c654aaed..19cfbf36fe80 100644
--- a/drivers/net/phy/at803x.c
+++ b/drivers/net/phy/at803x.c
@@ -1452,8 +1452,6 @@ static const struct sfp_upstream_ops at8031_sfp_ops = {
 	.attach = phy_sfp_attach,
 	.detach = phy_sfp_detach,
 	.module_insert = at8031_sfp_insert,
-	.connect_phy = phy_sfp_connect_phy,
-	.disconnect_phy = phy_sfp_disconnect_phy,
 };
 
 static int at8031_parse_dt(struct phy_device *phydev)
diff --git a/drivers/net/phy/marvell-88x2222.c b/drivers/net/phy/marvell-88x2222.c
index 3f77bbc7e04f..e3aa30dad2e6 100644
--- a/drivers/net/phy/marvell-88x2222.c
+++ b/drivers/net/phy/marvell-88x2222.c
@@ -555,8 +555,6 @@ static const struct sfp_upstream_ops sfp_phy_ops = {
 	.link_down = mv2222_sfp_link_down,
 	.attach = phy_sfp_attach,
 	.detach = phy_sfp_detach,
-	.connect_phy = phy_sfp_connect_phy,
-	.disconnect_phy = phy_sfp_disconnect_phy,
 };
 
 static int mv2222_probe(struct phy_device *phydev)
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index 674e29bce2cc..eba652a4c1d8 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -3254,8 +3254,6 @@ static const struct sfp_upstream_ops m88e1510_sfp_ops = {
 	.module_remove = m88e1510_sfp_remove,
 	.attach = phy_sfp_attach,
 	.detach = phy_sfp_detach,
-	.connect_phy = phy_sfp_connect_phy,
-	.disconnect_phy = phy_sfp_disconnect_phy,
 };
 
 static int m88e1510_probe(struct phy_device *phydev)
diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c
index 6642eb642d4b..ad43e280930c 100644
--- a/drivers/net/phy/marvell10g.c
+++ b/drivers/net/phy/marvell10g.c
@@ -503,8 +503,6 @@ static int mv3310_sfp_insert(void *upstream, const struct sfp_eeprom_id *id)
 static const struct sfp_upstream_ops mv3310_sfp_ops = {
 	.attach = phy_sfp_attach,
 	.detach = phy_sfp_detach,
-	.connect_phy = phy_sfp_connect_phy,
-	.disconnect_phy = phy_sfp_disconnect_phy,
 	.module_insert = mv3310_sfp_insert,
 };
 
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 1e595762afea..3611ea64875e 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -29,7 +29,6 @@
 #include <linux/phy.h>
 #include <linux/phylib_stubs.h>
 #include <linux/phy_led_triggers.h>
-#include <linux/phy_link_topology.h>
 #include <linux/pse-pd/pse.h>
 #include <linux/property.h>
 #include <linux/rtnetlink.h>
@@ -266,14 +265,6 @@ static void phy_mdio_device_remove(struct mdio_device *mdiodev)
 
 static struct phy_driver genphy_driver;
 
-static struct phy_link_topology *phy_get_link_topology(struct phy_device *phydev)
-{
-	if (phydev->attached_dev)
-		return &phydev->attached_dev->link_topo;
-
-	return NULL;
-}
-
 static LIST_HEAD(phy_fixup_list);
 static DEFINE_MUTEX(phy_fixup_lock);
 
@@ -1363,46 +1354,6 @@ phy_standalone_show(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR_RO(phy_standalone);
 
-/**
- * phy_sfp_connect_phy - Connect the SFP module's PHY to the upstream PHY
- * @upstream: pointer to the upstream phy device
- * @phy: pointer to the SFP module's phy device
- *
- * This helper allows keeping track of PHY devices on the link. It adds the
- * SFP module's phy to the phy namespace of the upstream phy
- */
-int phy_sfp_connect_phy(void *upstream, struct phy_device *phy)
-{
-	struct phy_device *phydev = upstream;
-	struct phy_link_topology *topo = phy_get_link_topology(phydev);
-
-	if (topo)
-		return phy_link_topo_add_phy(topo, phy, PHY_UPSTREAM_PHY, phydev);
-
-	return 0;
-}
-EXPORT_SYMBOL(phy_sfp_connect_phy);
-
-/**
- * phy_sfp_disconnect_phy - Disconnect the SFP module's PHY from the upstream PHY
- * @upstream: pointer to the upstream phy device
- * @phy: pointer to the SFP module's phy device
- *
- * This helper allows keeping track of PHY devices on the link. It removes the
- * SFP module's phy to the phy namespace of the upstream phy. As the module phy
- * will be destroyed, re-inserting the same module will add a new phy with a
- * new index.
- */
-void phy_sfp_disconnect_phy(void *upstream, struct phy_device *phy)
-{
-	struct phy_device *phydev = upstream;
-	struct phy_link_topology *topo = phy_get_link_topology(phydev);
-
-	if (topo)
-		phy_link_topo_del_phy(topo, phy);
-}
-EXPORT_SYMBOL(phy_sfp_disconnect_phy);
-
 /**
  * phy_sfp_attach - attach the SFP bus to the PHY upstream network device
  * @upstream: pointer to the phy device
@@ -1540,11 +1491,6 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
 
 		if (phydev->sfp_bus_attached)
 			dev->sfp_bus = phydev->sfp_bus;
-
-		err = phy_link_topo_add_phy(&dev->link_topo, phydev,
-					    PHY_UPSTREAM_MAC, dev);
-		if (err)
-			goto error;
 	}
 
 	/* Some Ethernet drivers try to connect to a PHY device before
@@ -1874,7 +1820,6 @@ void phy_detach(struct phy_device *phydev)
 	if (dev) {
 		phydev->attached_dev->phydev = NULL;
 		phydev->attached_dev = NULL;
-		phy_link_topo_del_phy(&dev->link_topo, phydev);
 	}
 	phydev->phylink = NULL;
 
diff --git a/drivers/net/phy/phy_link_topology.c b/drivers/net/phy/phy_link_topology.c
deleted file mode 100644
index 34e7e08fbfc3..000000000000
--- a/drivers/net/phy/phy_link_topology.c
+++ /dev/null
@@ -1,66 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0+
-/*
- * Infrastructure to handle all PHY devices connected to a given netdev,
- * either directly or indirectly attached.
- *
- * Copyright (c) 2023 Maxime Chevallier<maxime.chevallier@bootlin.com>
- */
-
-#include <linux/phy_link_topology.h>
-#include <linux/netdevice.h>
-#include <linux/phy.h>
-#include <linux/rtnetlink.h>
-#include <linux/xarray.h>
-
-int phy_link_topo_add_phy(struct phy_link_topology *topo,
-			  struct phy_device *phy,
-			  enum phy_upstream upt, void *upstream)
-{
-	struct phy_device_node *pdn;
-	int ret;
-
-	pdn = kzalloc(sizeof(*pdn), GFP_KERNEL);
-	if (!pdn)
-		return -ENOMEM;
-
-	pdn->phy = phy;
-	switch (upt) {
-	case PHY_UPSTREAM_MAC:
-		pdn->upstream.netdev = (struct net_device *)upstream;
-		if (phy_on_sfp(phy))
-			pdn->parent_sfp_bus = pdn->upstream.netdev->sfp_bus;
-		break;
-	case PHY_UPSTREAM_PHY:
-		pdn->upstream.phydev = (struct phy_device *)upstream;
-		if (phy_on_sfp(phy))
-			pdn->parent_sfp_bus = pdn->upstream.phydev->sfp_bus;
-		break;
-	default:
-		ret = -EINVAL;
-		goto err;
-	}
-	pdn->upstream_type = upt;
-
-	ret = xa_alloc_cyclic(&topo->phys, &phy->phyindex, pdn, xa_limit_32b,
-			      &topo->next_phy_index, GFP_KERNEL);
-	if (ret)
-		goto err;
-
-	return 0;
-
-err:
-	kfree(pdn);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(phy_link_topo_add_phy);
-
-void phy_link_topo_del_phy(struct phy_link_topology *topo,
-			   struct phy_device *phy)
-{
-	struct phy_device_node *pdn = xa_erase(&topo->phys, phy->phyindex);
-
-	phy->phyindex = 0;
-
-	kfree(pdn);
-}
-EXPORT_SYMBOL_GPL(phy_link_topo_del_phy);
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index a816391add12..ed0b4ccaa6a6 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -3385,8 +3385,7 @@ static int phylink_sfp_connect_phy(void *upstream, struct phy_device *phy)
 	return ret;
 }
 
-static void phylink_sfp_disconnect_phy(void *upstream,
-				       struct phy_device *phydev)
+static void phylink_sfp_disconnect_phy(void *upstream)
 {
 	phylink_disconnect_phy(upstream);
 }
diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c
index fb1c102714b5..6fa679b36290 100644
--- a/drivers/net/phy/sfp-bus.c
+++ b/drivers/net/phy/sfp-bus.c
@@ -486,7 +486,7 @@ static void sfp_unregister_bus(struct sfp_bus *bus)
 			bus->socket_ops->stop(bus->sfp);
 		bus->socket_ops->detach(bus->sfp);
 		if (bus->phydev && ops && ops->disconnect_phy)
-			ops->disconnect_phy(bus->upstream, bus->phydev);
+			ops->disconnect_phy(bus->upstream);
 	}
 	bus->registered = false;
 }
@@ -742,7 +742,7 @@ void sfp_remove_phy(struct sfp_bus *bus)
 	const struct sfp_upstream_ops *ops = sfp_get_upstream_ops(bus);
 
 	if (ops && ops->disconnect_phy)
-		ops->disconnect_phy(bus->upstream, bus->phydev);
+		ops->disconnect_phy(bus->upstream);
 	bus->phydev = NULL;
 }
 EXPORT_SYMBOL_GPL(sfp_remove_phy);
@@ -859,14 +859,3 @@ void sfp_unregister_socket(struct sfp_bus *bus)
 	sfp_bus_put(bus);
 }
 EXPORT_SYMBOL_GPL(sfp_unregister_socket);
-
-const char *sfp_get_name(struct sfp_bus *bus)
-{
-	ASSERT_RTNL();
-
-	if (bus->sfp_dev)
-		return dev_name(bus->sfp_dev);
-
-	return NULL;
-}
-EXPORT_SYMBOL_GPL(sfp_get_name);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index e265aa1f2169..118c40258d07 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -40,6 +40,7 @@
 #include <net/dcbnl.h>
 #endif
 #include <net/netprio_cgroup.h>
+
 #include <linux/netdev_features.h>
 #include <linux/neighbour.h>
 #include <uapi/linux/netdevice.h>
@@ -51,7 +52,6 @@
 #include <net/net_trackers.h>
 #include <net/net_debug.h>
 #include <net/dropreason-core.h>
-#include <linux/phy_link_topology_core.h>
 
 struct netpoll_info;
 struct device;
@@ -2047,7 +2047,6 @@ enum netdev_stat_type {
  *	@fcoe_ddp_xid:	Max exchange id for FCoE LRO by ddp
  *
  *	@priomap:	XXX: need comments on this one
- *	@link_topo:	Physical link topology tracking attached PHYs
  *	@phydev:	Physical device may attach itself
  *			for hardware timestamping
  *	@sfp_bus:	attached &struct sfp_bus structure.
@@ -2442,7 +2441,6 @@ struct net_device {
 #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO)
 	struct netprio_map __rcu *priomap;
 #endif
-	struct phy_link_topology	link_topo;
 	struct phy_device	*phydev;
 	struct sfp_bus		*sfp_bus;
 	struct lock_class_key	*qdisc_tx_busylock;
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 6cb9d843aee9..e9e85d347587 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -544,9 +544,6 @@ struct macsec_ops;
  * @drv: Pointer to the driver for this PHY instance
  * @devlink: Create a link between phy dev and mac dev, if the external phy
  *           used by current mac interface is managed by another mac interface.
- * @phyindex: Unique id across the phy's parent tree of phys to address the PHY
- *	      from userspace, similar to ifindex. A zero index means the PHY
- *	      wasn't assigned an id yet.
  * @phy_id: UID for this device found during discovery
  * @c45_ids: 802.3-c45 Device Identifiers if is_c45.
  * @is_c45:  Set to true if this PHY uses clause 45 addressing.
@@ -646,7 +643,6 @@ struct phy_device {
 
 	struct device_link *devlink;
 
-	u32 phyindex;
 	u32 phy_id;
 
 	struct phy_c45_device_ids c45_ids;
@@ -1726,8 +1722,6 @@ int phy_suspend(struct phy_device *phydev);
 int phy_resume(struct phy_device *phydev);
 int __phy_resume(struct phy_device *phydev);
 int phy_loopback(struct phy_device *phydev, bool enable);
-int phy_sfp_connect_phy(void *upstream, struct phy_device *phy);
-void phy_sfp_disconnect_phy(void *upstream, struct phy_device *phy);
 void phy_sfp_attach(void *upstream, struct sfp_bus *bus);
 void phy_sfp_detach(void *upstream, struct sfp_bus *bus);
 int phy_sfp_probe(struct phy_device *phydev,
diff --git a/include/linux/phy_link_topology.h b/include/linux/phy_link_topology.h
deleted file mode 100644
index 91902263ec0e..000000000000
--- a/include/linux/phy_link_topology.h
+++ /dev/null
@@ -1,67 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * PHY device list allow maintaining a list of PHY devices that are
- * part of a netdevice's link topology. PHYs can for example be chained,
- * as is the case when using a PHY that exposes an SFP module, on which an
- * SFP transceiver that embeds a PHY is connected.
- *
- * This list can then be used by userspace to leverage individual PHY
- * capabilities.
- */
-#ifndef __PHY_LINK_TOPOLOGY_H
-#define __PHY_LINK_TOPOLOGY_H
-
-#include <linux/ethtool.h>
-#include <linux/phy_link_topology_core.h>
-
-struct xarray;
-struct phy_device;
-struct net_device;
-struct sfp_bus;
-
-struct phy_device_node {
-	enum phy_upstream upstream_type;
-
-	union {
-		struct net_device	*netdev;
-		struct phy_device	*phydev;
-	} upstream;
-
-	struct sfp_bus *parent_sfp_bus;
-
-	struct phy_device *phy;
-};
-
-static inline struct phy_device *
-phy_link_topo_get_phy(struct phy_link_topology *topo, u32 phyindex)
-{
-	struct phy_device_node *pdn = xa_load(&topo->phys, phyindex);
-
-	if (pdn)
-		return pdn->phy;
-
-	return NULL;
-}
-
-#if IS_ENABLED(CONFIG_PHYLIB)
-int phy_link_topo_add_phy(struct phy_link_topology *topo,
-			  struct phy_device *phy,
-			  enum phy_upstream upt, void *upstream);
-
-void phy_link_topo_del_phy(struct phy_link_topology *lt, struct phy_device *phy);
-
-#else
-static inline int phy_link_topo_add_phy(struct phy_link_topology *topo,
-					struct phy_device *phy,
-					enum phy_upstream upt, void *upstream)
-{
-	return 0;
-}
-
-static inline void phy_link_topo_del_phy(struct phy_link_topology *topo,
-					 struct phy_device *phy)
-{
-}
-#endif
-
-#endif /* __PHY_LINK_TOPOLOGY_H */
diff --git a/include/linux/phy_link_topology_core.h b/include/linux/phy_link_topology_core.h
deleted file mode 100644
index 78c75f909489..000000000000
--- a/include/linux/phy_link_topology_core.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __PHY_LINK_TOPOLOGY_CORE_H
-#define __PHY_LINK_TOPOLOGY_CORE_H
-
-struct xarray;
-
-struct phy_link_topology {
-	struct xarray phys;
-
-	u32 next_phy_index;
-};
-
-static inline void phy_link_topo_init(struct phy_link_topology *topo)
-{
-	xa_init_flags(&topo->phys, XA_FLAGS_ALLOC1);
-	topo->next_phy_index = 1;
-}
-
-#endif /* __PHY_LINK_TOPOLOGY_CORE_H */
diff --git a/include/linux/sfp.h b/include/linux/sfp.h
index 55c0ab17c9e2..9346cd44814d 100644
--- a/include/linux/sfp.h
+++ b/include/linux/sfp.h
@@ -544,7 +544,7 @@ struct sfp_upstream_ops {
 	void (*link_down)(void *priv);
 	void (*link_up)(void *priv);
 	int (*connect_phy)(void *priv, struct phy_device *);
-	void (*disconnect_phy)(void *priv, struct phy_device *);
+	void (*disconnect_phy)(void *priv);
 };
 
 #if IS_ENABLED(CONFIG_SFP)
@@ -570,7 +570,6 @@ struct sfp_bus *sfp_bus_find_fwnode(const struct fwnode_handle *fwnode);
 int sfp_bus_add_upstream(struct sfp_bus *bus, void *upstream,
 			 const struct sfp_upstream_ops *ops);
 void sfp_bus_del_upstream(struct sfp_bus *bus);
-const char *sfp_get_name(struct sfp_bus *bus);
 #else
 static inline int sfp_parse_port(struct sfp_bus *bus,
 				 const struct sfp_eeprom_id *id,
@@ -649,11 +648,6 @@ static inline int sfp_bus_add_upstream(struct sfp_bus *bus, void *upstream,
 static inline void sfp_bus_del_upstream(struct sfp_bus *bus)
 {
 }
-
-static inline const char *sfp_get_name(struct sfp_bus *bus)
-{
-	return NULL;
-}
 #endif
 
 #endif
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 01ba529dbb6d..06ef6b78b7de 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -2220,20 +2220,4 @@ struct ethtool_link_settings {
 	 * __u32 map_lp_advertising[link_mode_masks_nwords];
 	 */
 };
-
-/**
- * enum phy_upstream - Represents the upstream component a given PHY device
- * is connected to, as in what is on the other end of the MII bus. Most PHYs
- * will be attached to an Ethernet MAC controller, but in some cases, there's
- * an intermediate PHY used as a media-converter, which will driver another
- * MII interface as its output.
- * @PHY_UPSTREAM_MAC: Upstream component is a MAC (a switch port,
- *		      or ethernet controller)
- * @PHY_UPSTREAM_PHY: Upstream component is a PHY (likely a media converter)
- */
-enum phy_upstream {
-	PHY_UPSTREAM_MAC,
-	PHY_UPSTREAM_PHY,
-};
-
 #endif /* _UAPI_LINUX_ETHTOOL_H */
diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h
index 00cd7ad16709..3f89074aa06c 100644
--- a/include/uapi/linux/ethtool_netlink.h
+++ b/include/uapi/linux/ethtool_netlink.h
@@ -57,7 +57,6 @@ enum {
 	ETHTOOL_MSG_PLCA_GET_STATUS,
 	ETHTOOL_MSG_MM_GET,
 	ETHTOOL_MSG_MM_SET,
-	ETHTOOL_MSG_PHY_GET,
 
 	/* add new constants above here */
 	__ETHTOOL_MSG_USER_CNT,
@@ -110,8 +109,6 @@ enum {
 	ETHTOOL_MSG_PLCA_NTF,
 	ETHTOOL_MSG_MM_GET_REPLY,
 	ETHTOOL_MSG_MM_NTF,
-	ETHTOOL_MSG_PHY_GET_REPLY,
-	ETHTOOL_MSG_PHY_NTF,
 
 	/* add new constants above here */
 	__ETHTOOL_MSG_KERNEL_CNT,
@@ -136,7 +133,6 @@ enum {
 	ETHTOOL_A_HEADER_DEV_INDEX,		/* u32 */
 	ETHTOOL_A_HEADER_DEV_NAME,		/* string */
 	ETHTOOL_A_HEADER_FLAGS,			/* u32 - ETHTOOL_FLAG_* */
-	ETHTOOL_A_HEADER_PHY_INDEX,		/* u32 */
 
 	/* add new constants above here */
 	__ETHTOOL_A_HEADER_CNT,
@@ -980,32 +976,6 @@ enum {
 	ETHTOOL_A_MM_MAX = (__ETHTOOL_A_MM_CNT - 1)
 };
 
-enum {
-	ETHTOOL_A_PHY_UPSTREAM_UNSPEC,
-	ETHTOOL_A_PHY_UPSTREAM_INDEX,			/* u32 */
-	ETHTOOL_A_PHY_UPSTREAM_SFP_NAME,		/* string */
-
-	/* add new constants above here */
-	__ETHTOOL_A_PHY_UPSTREAM_CNT,
-	ETHTOOL_A_PHY_UPSTREAM_MAX = (__ETHTOOL_A_PHY_UPSTREAM_CNT - 1)
-};
-
-enum {
-	ETHTOOL_A_PHY_UNSPEC,
-	ETHTOOL_A_PHY_HEADER,			/* nest - _A_HEADER_* */
-	ETHTOOL_A_PHY_INDEX,			/* u32 */
-	ETHTOOL_A_PHY_DRVNAME,			/* string */
-	ETHTOOL_A_PHY_NAME,			/* string */
-	ETHTOOL_A_PHY_UPSTREAM_TYPE,		/* u8 */
-	ETHTOOL_A_PHY_UPSTREAM,			/* nest - _A_PHY_UPSTREAM_* */
-	ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME,	/* string */
-	ETHTOOL_A_PHY_ID,			/* u32 */
-
-	/* add new constants above here */
-	__ETHTOOL_A_PHY_CNT,
-	ETHTOOL_A_PHY_MAX = (__ETHTOOL_A_PHY_CNT - 1)
-};
-
 /* generic netlink info */
 #define ETHTOOL_GENL_NAME "ethtool"
 #define ETHTOOL_GENL_VERSION 1
diff --git a/net/core/dev.c b/net/core/dev.c
index bc4ac49d4643..f01a9b858347 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -153,7 +153,6 @@
 #include <linux/prandom.h>
 #include <linux/once_lite.h>
 #include <net/netdev_rx_queue.h>
-#include <linux/phy_link_topology_core.h>
 
 #include "dev.h"
 #include "net-sysfs.h"
@@ -10876,8 +10875,6 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 #ifdef CONFIG_NET_SCHED
 	hash_init(dev->qdisc_hash);
 #endif
-	phy_link_topo_init(&dev->link_topo);
-
 	dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM;
 	setup(dev);
 
diff --git a/net/ethtool/Makefile b/net/ethtool/Makefile
index 0ccd0e9afd3f..504f954a1b28 100644
--- a/net/ethtool/Makefile
+++ b/net/ethtool/Makefile
@@ -8,4 +8,4 @@ ethtool_nl-y	:= netlink.o bitset.o strset.o linkinfo.o linkmodes.o rss.o \
 		   linkstate.o debug.o wol.o features.o privflags.o rings.o \
 		   channels.o coalesce.o pause.o eee.o tsinfo.o cabletest.o \
 		   tunnels.o fec.o eeprom.o stats.o phc_vclocks.o mm.o \
-		   module.o pse-pd.o plca.o mm.o phy.o
+		   module.o pse-pd.o plca.o mm.o
diff --git a/net/ethtool/cabletest.c b/net/ethtool/cabletest.c
index 6b00d0800f23..06a151165c31 100644
--- a/net/ethtool/cabletest.c
+++ b/net/ethtool/cabletest.c
@@ -69,7 +69,7 @@ int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info)
 		return ret;
 
 	dev = req_info.dev;
-	if (!req_info.phydev) {
+	if (!dev->phydev) {
 		ret = -EOPNOTSUPP;
 		goto out_dev_put;
 	}
@@ -85,12 +85,12 @@ int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info)
 	if (ret < 0)
 		goto out_rtnl;
 
-	ret = ops->start_cable_test(req_info.phydev, info->extack);
+	ret = ops->start_cable_test(dev->phydev, info->extack);
 
 	ethnl_ops_complete(dev);
 
 	if (!ret)
-		ethnl_cable_test_started(req_info.phydev,
+		ethnl_cable_test_started(dev->phydev,
 					 ETHTOOL_MSG_CABLE_TEST_NTF);
 
 out_rtnl:
@@ -321,7 +321,7 @@ int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info)
 		return ret;
 
 	dev = req_info.dev;
-	if (!req_info.phydev) {
+	if (!dev->phydev) {
 		ret = -EOPNOTSUPP;
 		goto out_dev_put;
 	}
@@ -342,12 +342,12 @@ int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info)
 	if (ret < 0)
 		goto out_rtnl;
 
-	ret = ops->start_cable_test_tdr(req_info.phydev, info->extack, &cfg);
+	ret = ops->start_cable_test_tdr(dev->phydev, info->extack, &cfg);
 
 	ethnl_ops_complete(dev);
 
 	if (!ret)
-		ethnl_cable_test_started(req_info.phydev,
+		ethnl_cable_test_started(dev->phydev,
 					 ETHTOOL_MSG_CABLE_TEST_TDR_NTF);
 
 out_rtnl:
diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index 92b0dd8ca046..fe3553f60bf3 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -4,7 +4,6 @@
 #include <linux/ethtool_netlink.h>
 #include <linux/pm_runtime.h>
 #include "netlink.h"
-#include <linux/phy_link_topology.h>
 
 static struct genl_family ethtool_genl_family;
 
@@ -21,7 +20,6 @@ const struct nla_policy ethnl_header_policy[] = {
 					    .len = ALTIFNAMSIZ - 1 },
 	[ETHTOOL_A_HEADER_FLAGS]	= NLA_POLICY_MASK(NLA_U32,
 							  ETHTOOL_FLAGS_BASIC),
-	[ETHTOOL_A_HEADER_PHY_INDEX]		= NLA_POLICY_MIN(NLA_U32, 1),
 };
 
 const struct nla_policy ethnl_header_policy_stats[] = {
@@ -30,7 +28,6 @@ const struct nla_policy ethnl_header_policy_stats[] = {
 					    .len = ALTIFNAMSIZ - 1 },
 	[ETHTOOL_A_HEADER_FLAGS]	= NLA_POLICY_MASK(NLA_U32,
 							  ETHTOOL_FLAGS_STATS),
-	[ETHTOOL_A_HEADER_PHY_INDEX]		= NLA_POLICY_MIN(NLA_U32, 1),
 };
 
 int ethnl_ops_begin(struct net_device *dev)
@@ -94,7 +91,6 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info,
 {
 	struct nlattr *tb[ARRAY_SIZE(ethnl_header_policy)];
 	const struct nlattr *devname_attr;
-	struct phy_device *phydev = NULL;
 	struct net_device *dev = NULL;
 	u32 flags = 0;
 	int ret;
@@ -149,26 +145,6 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info,
 		return -EINVAL;
 	}
 
-	if (dev) {
-		if (tb[ETHTOOL_A_HEADER_PHY_INDEX]) {
-			u32 phy_index = nla_get_u32(tb[ETHTOOL_A_HEADER_PHY_INDEX]);
-
-			phydev = phy_link_topo_get_phy(&dev->link_topo,
-						       phy_index);
-			if (!phydev) {
-				NL_SET_ERR_MSG_ATTR(extack, header,
-						    "no phy matches phy index");
-				return -EINVAL;
-			}
-		} else {
-			/* If we need a PHY but no phy index is specified, fallback
-			 * to dev->phydev
-			 */
-			phydev = dev->phydev;
-		}
-	}
-
-	req_info->phydev = phydev;
 	req_info->dev = dev;
 	req_info->flags = flags;
 	return 0;
@@ -1153,15 +1129,6 @@ static const struct genl_ops ethtool_genl_ops[] = {
 		.policy = ethnl_mm_set_policy,
 		.maxattr = ARRAY_SIZE(ethnl_mm_set_policy) - 1,
 	},
-	{
-		.cmd	= ETHTOOL_MSG_PHY_GET,
-		.doit	= ethnl_phy_doit,
-		.start	= ethnl_phy_start,
-		.dumpit	= ethnl_phy_dumpit,
-		.done	= ethnl_phy_done,
-		.policy = ethnl_phy_get_policy,
-		.maxattr = ARRAY_SIZE(ethnl_phy_get_policy) - 1,
-	},
 };
 
 static const struct genl_multicast_group ethtool_nl_mcgrps[] = {
diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h
index 5e6a43e35a09..9a333a8d04c1 100644
--- a/net/ethtool/netlink.h
+++ b/net/ethtool/netlink.h
@@ -250,7 +250,6 @@ static inline unsigned int ethnl_reply_header_size(void)
  * @dev:   network device the request is for (may be null)
  * @dev_tracker: refcount tracker for @dev reference
  * @flags: request flags common for all request types
- * @phydev: phy_device connected to @dev this request is for (may be null)
  *
  * This is a common base for request specific structures holding data from
  * parsed userspace request. These always embed struct ethnl_req_info at
@@ -260,7 +259,6 @@ struct ethnl_req_info {
 	struct net_device	*dev;
 	netdevice_tracker	dev_tracker;
 	u32			flags;
-	struct phy_device	*phydev;
 };
 
 static inline void ethnl_parse_header_dev_put(struct ethnl_req_info *req_info)
@@ -397,10 +395,9 @@ extern const struct ethnl_request_ops ethnl_rss_request_ops;
 extern const struct ethnl_request_ops ethnl_plca_cfg_request_ops;
 extern const struct ethnl_request_ops ethnl_plca_status_request_ops;
 extern const struct ethnl_request_ops ethnl_mm_request_ops;
-extern const struct ethnl_request_ops ethnl_phy_request_ops;
 
-extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_PHY_INDEX + 1];
-extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_PHY_INDEX + 1];
+extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1];
+extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1];
 extern const struct nla_policy ethnl_strset_get_policy[ETHTOOL_A_STRSET_COUNTS_ONLY + 1];
 extern const struct nla_policy ethnl_linkinfo_get_policy[ETHTOOL_A_LINKINFO_HEADER + 1];
 extern const struct nla_policy ethnl_linkinfo_set_policy[ETHTOOL_A_LINKINFO_TP_MDIX_CTRL + 1];
@@ -444,7 +441,6 @@ extern const struct nla_policy ethnl_plca_set_cfg_policy[ETHTOOL_A_PLCA_MAX + 1]
 extern const struct nla_policy ethnl_plca_get_status_policy[ETHTOOL_A_PLCA_HEADER + 1];
 extern const struct nla_policy ethnl_mm_get_policy[ETHTOOL_A_MM_HEADER + 1];
 extern const struct nla_policy ethnl_mm_set_policy[ETHTOOL_A_MM_MAX + 1];
-extern const struct nla_policy ethnl_phy_get_policy[ETHTOOL_A_PHY_HEADER + 1];
 
 int ethnl_set_features(struct sk_buff *skb, struct genl_info *info);
 int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info);
@@ -452,10 +448,6 @@ int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info);
 int ethnl_tunnel_info_doit(struct sk_buff *skb, struct genl_info *info);
 int ethnl_tunnel_info_start(struct netlink_callback *cb);
 int ethnl_tunnel_info_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
-int ethnl_phy_start(struct netlink_callback *cb);
-int ethnl_phy_doit(struct sk_buff *skb, struct genl_info *info);
-int ethnl_phy_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
-int ethnl_phy_done(struct netlink_callback *cb);
 
 extern const char stats_std_names[__ETHTOOL_STATS_CNT][ETH_GSTRING_LEN];
 extern const char stats_eth_phy_names[__ETHTOOL_A_STATS_ETH_PHY_CNT][ETH_GSTRING_LEN];
diff --git a/net/ethtool/phy.c b/net/ethtool/phy.c
deleted file mode 100644
index 5add2840aaeb..000000000000
--- a/net/ethtool/phy.c
+++ /dev/null
@@ -1,306 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright 2023 Bootlin
- *
- */
-#include "common.h"
-#include "netlink.h"
-
-#include <linux/phy.h>
-#include <linux/phy_link_topology.h>
-#include <linux/sfp.h>
-
-struct phy_req_info {
-	struct ethnl_req_info		base;
-	struct phy_device_node		pdn;
-};
-
-#define PHY_REQINFO(__req_base) \
-	container_of(__req_base, struct phy_req_info, base)
-
-const struct nla_policy ethnl_phy_get_policy[ETHTOOL_A_PHY_HEADER + 1] = {
-	[ETHTOOL_A_PHY_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy),
-};
-
-/* Caller holds rtnl */
-static ssize_t
-ethnl_phy_reply_size(const struct ethnl_req_info *req_base,
-		     struct netlink_ext_ack *extack)
-{
-	struct phy_link_topology *topo;
-	struct phy_device_node *pdn;
-	struct phy_device *phydev;
-	unsigned long index;
-	size_t size;
-
-	ASSERT_RTNL();
-
-	topo = &req_base->dev->link_topo;
-
-	size = nla_total_size(0);
-
-	xa_for_each(&topo->phys, index, pdn) {
-		phydev = pdn->phy;
-
-		/* ETHTOOL_A_PHY_INDEX */
-		size += nla_total_size(sizeof(u32));
-
-		/* ETHTOOL_A_DRVNAME */
-		size += nla_total_size(strlen(phydev->drv->name) + 1);
-
-		/* ETHTOOL_A_NAME */
-		size += nla_total_size(strlen(dev_name(&phydev->mdio.dev)) + 1);
-
-		/* ETHTOOL_A_PHY_UPSTREAM_TYPE */
-		size += nla_total_size(sizeof(u8));
-
-		/* ETHTOOL_A_PHY_ID */
-		size += nla_total_size(sizeof(u32));
-
-		if (phy_on_sfp(phydev)) {
-			const char *upstream_sfp_name = sfp_get_name(pdn->parent_sfp_bus);
-
-			/* ETHTOOL_A_PHY_UPSTREAM_SFP_NAME */
-			if (upstream_sfp_name)
-				size += nla_total_size(strlen(upstream_sfp_name) + 1);
-
-			/* ETHTOOL_A_PHY_UPSTREAM_INDEX */
-			size += nla_total_size(sizeof(u32));
-		}
-
-		/* ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME */
-		if (phydev->sfp_bus) {
-			const char *sfp_name = sfp_get_name(phydev->sfp_bus);
-
-			if (sfp_name)
-				size += nla_total_size(strlen(sfp_name) + 1);
-		}
-	}
-
-	return size;
-}
-
-static int
-ethnl_phy_fill_reply(const struct ethnl_req_info *req_base, struct sk_buff *skb)
-{
-	struct phy_req_info *req_info = PHY_REQINFO(req_base);
-	struct phy_device_node *pdn = &req_info->pdn;
-	struct phy_device *phydev = pdn->phy;
-	enum phy_upstream ptype;
-	struct nlattr *nest;
-
-	ptype = pdn->upstream_type;
-
-	if (nla_put_u32(skb, ETHTOOL_A_PHY_INDEX, phydev->phyindex) ||
-	    nla_put_string(skb, ETHTOOL_A_PHY_DRVNAME, phydev->drv->name) ||
-	    nla_put_string(skb, ETHTOOL_A_PHY_NAME, dev_name(&phydev->mdio.dev)) ||
-	    nla_put_u8(skb, ETHTOOL_A_PHY_UPSTREAM_TYPE, ptype) ||
-	    nla_put_u32(skb, ETHTOOL_A_PHY_ID, phydev->phy_id))
-		return -EMSGSIZE;
-
-	if (ptype == PHY_UPSTREAM_PHY) {
-		struct phy_device *upstream = pdn->upstream.phydev;
-		const char *sfp_upstream_name;
-
-		nest = nla_nest_start(skb, ETHTOOL_A_PHY_UPSTREAM);
-		if (!nest)
-			return -EMSGSIZE;
-
-		/* Parent index */
-		if (nla_put_u32(skb, ETHTOOL_A_PHY_UPSTREAM_INDEX, upstream->phyindex))
-			return -EMSGSIZE;
-
-		if (pdn->parent_sfp_bus) {
-			sfp_upstream_name = sfp_get_name(pdn->parent_sfp_bus);
-			if (sfp_upstream_name && nla_put_string(skb,
-								ETHTOOL_A_PHY_UPSTREAM_SFP_NAME,
-								sfp_upstream_name))
-				return -EMSGSIZE;
-		}
-
-		nla_nest_end(skb, nest);
-	}
-
-	if (phydev->sfp_bus) {
-		const char *sfp_name = sfp_get_name(phydev->sfp_bus);
-
-		if (sfp_name &&
-		    nla_put_string(skb, ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME,
-				   sfp_name))
-			return -EMSGSIZE;
-	}
-
-	return 0;
-}
-
-static int ethnl_phy_parse_request(struct ethnl_req_info *req_base,
-				   struct nlattr **tb)
-{
-	struct phy_link_topology *topo = &req_base->dev->link_topo;
-	struct phy_req_info *req_info = PHY_REQINFO(req_base);
-	struct phy_device_node *pdn;
-
-	if (!req_base->phydev)
-		return 0;
-
-	pdn = xa_load(&topo->phys, req_base->phydev->phyindex);
-	memcpy(&req_info->pdn, pdn, sizeof(*pdn));
-
-	return 0;
-}
-
-int ethnl_phy_doit(struct sk_buff *skb, struct genl_info *info)
-{
-	struct phy_req_info req_info = {};
-	struct nlattr **tb = info->attrs;
-	struct sk_buff *rskb;
-	void *reply_payload;
-	int reply_len;
-	int ret;
-
-	ret = ethnl_parse_header_dev_get(&req_info.base,
-					 tb[ETHTOOL_A_PHY_HEADER],
-					 genl_info_net(info), info->extack,
-					 true);
-	if (ret < 0)
-		return ret;
-
-	rtnl_lock();
-
-	ret = ethnl_phy_parse_request(&req_info.base, tb);
-	if (ret < 0)
-		goto err_unlock_rtnl;
-
-	/* No PHY, return early */
-	if (!req_info.pdn.phy)
-		goto err_unlock_rtnl;
-
-	ret = ethnl_phy_reply_size(&req_info.base, info->extack);
-	if (ret < 0)
-		goto err_unlock_rtnl;
-	reply_len = ret + ethnl_reply_header_size();
-
-	rskb = ethnl_reply_init(reply_len, req_info.base.dev,
-				ETHTOOL_MSG_PHY_GET_REPLY,
-				ETHTOOL_A_PHY_HEADER,
-				info, &reply_payload);
-	if (!rskb) {
-		ret = -ENOMEM;
-		goto err_unlock_rtnl;
-	}
-
-	ret = ethnl_phy_fill_reply(&req_info.base, rskb);
-	if (ret)
-		goto err_free_msg;
-
-	rtnl_unlock();
-	ethnl_parse_header_dev_put(&req_info.base);
-	genlmsg_end(rskb, reply_payload);
-
-	return genlmsg_reply(rskb, info);
-
-err_free_msg:
-	nlmsg_free(rskb);
-err_unlock_rtnl:
-	rtnl_unlock();
-	ethnl_parse_header_dev_put(&req_info.base);
-	return ret;
-}
-
-struct ethnl_phy_dump_ctx {
-	struct phy_req_info	*phy_req_info;
-};
-
-int ethnl_phy_start(struct netlink_callback *cb)
-{
-	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
-	struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx;
-	struct nlattr **tb = info->info.attrs;
-	int ret;
-
-	BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx));
-
-	ctx->phy_req_info = kzalloc(sizeof(*ctx->phy_req_info), GFP_KERNEL);
-	if (!ctx->phy_req_info)
-		return -ENOMEM;
-
-	ret = ethnl_parse_header_dev_get(&ctx->phy_req_info->base,
-					 tb[ETHTOOL_A_PHY_HEADER],
-					 sock_net(cb->skb->sk), cb->extack,
-					 false);
-	return ret;
-}
-
-int ethnl_phy_done(struct netlink_callback *cb)
-{
-	struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx;
-
-	kfree(ctx->phy_req_info);
-
-	return 0;
-}
-
-static int ethnl_phy_dump_one_dev(struct sk_buff *skb, struct net_device *dev,
-				  struct netlink_callback *cb)
-{
-	struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx;
-	struct phy_req_info *pri = ctx->phy_req_info;
-	struct phy_device_node *pdn;
-	unsigned long index = 1;
-	int ret = 0;
-	void *ehdr;
-
-	pri->base.dev = dev;
-
-	xa_for_each(&dev->link_topo.phys, index, pdn) {
-		ehdr = ethnl_dump_put(skb, cb,
-				      ETHTOOL_MSG_PHY_GET_REPLY);
-		if (!ehdr) {
-			ret = -EMSGSIZE;
-			break;
-		}
-
-		ret = ethnl_fill_reply_header(skb, dev,
-					      ETHTOOL_A_PHY_HEADER);
-		if (ret < 0) {
-			genlmsg_cancel(skb, ehdr);
-			break;
-		}
-
-		memcpy(&pri->pdn, pdn, sizeof(*pdn));
-		ret = ethnl_phy_fill_reply(&pri->base, skb);
-
-		genlmsg_end(skb, ehdr);
-	}
-
-	return ret;
-}
-
-int ethnl_phy_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
-{
-	struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx;
-	struct net *net = sock_net(skb->sk);
-	unsigned long ifindex = 1;
-	struct net_device *dev;
-	int ret = 0;
-
-	rtnl_lock();
-
-	if (ctx->phy_req_info->base.dev) {
-		ret = ethnl_phy_dump_one_dev(skb, ctx->phy_req_info->base.dev, cb);
-		ethnl_parse_header_dev_put(&ctx->phy_req_info->base);
-		ctx->phy_req_info->base.dev = NULL;
-	} else {
-		for_each_netdev_dump(net, dev, ifindex) {
-			ret = ethnl_phy_dump_one_dev(skb, dev, cb);
-			if (ret)
-				break;
-		}
-	}
-	rtnl_unlock();
-
-	if (ret == -EMSGSIZE && skb->len)
-		return skb->len;
-	return ret;
-}
-
diff --git a/net/ethtool/plca.c b/net/ethtool/plca.c
index 2b3e419f4dc2..b1e2e3b5027f 100644
--- a/net/ethtool/plca.c
+++ b/net/ethtool/plca.c
@@ -61,7 +61,7 @@ static int plca_get_cfg_prepare_data(const struct ethnl_req_info *req_base,
 	int ret;
 
 	// check that the PHY device is available and connected
-	if (!req_base->phydev) {
+	if (!dev->phydev) {
 		ret = -EOPNOTSUPP;
 		goto out;
 	}
@@ -80,7 +80,7 @@ static int plca_get_cfg_prepare_data(const struct ethnl_req_info *req_base,
 	memset(&data->plca_cfg, 0xff,
 	       sizeof_field(struct plca_reply_data, plca_cfg));
 
-	ret = ops->get_plca_cfg(req_base->phydev, &data->plca_cfg);
+	ret = ops->get_plca_cfg(dev->phydev, &data->plca_cfg);
 	ethnl_ops_complete(dev);
 
 out:
@@ -141,6 +141,7 @@ const struct nla_policy ethnl_plca_set_cfg_policy[] = {
 static int
 ethnl_set_plca(struct ethnl_req_info *req_info, struct genl_info *info)
 {
+	struct net_device *dev = req_info->dev;
 	const struct ethtool_phy_ops *ops;
 	struct nlattr **tb = info->attrs;
 	struct phy_plca_cfg plca_cfg;
@@ -148,7 +149,7 @@ ethnl_set_plca(struct ethnl_req_info *req_info, struct genl_info *info)
 	int ret;
 
 	// check that the PHY device is available and connected
-	if (!req_info->phydev)
+	if (!dev->phydev)
 		return -EOPNOTSUPP;
 
 	ops = ethtool_phy_ops;
@@ -167,7 +168,7 @@ ethnl_set_plca(struct ethnl_req_info *req_info, struct genl_info *info)
 	if (!mod)
 		return 0;
 
-	ret = ops->set_plca_cfg(req_info->phydev, &plca_cfg, info->extack);
+	ret = ops->set_plca_cfg(dev->phydev, &plca_cfg, info->extack);
 	return ret < 0 ? ret : 1;
 }
 
@@ -203,7 +204,7 @@ static int plca_get_status_prepare_data(const struct ethnl_req_info *req_base,
 	int ret;
 
 	// check that the PHY device is available and connected
-	if (!req_base->phydev) {
+	if (!dev->phydev) {
 		ret = -EOPNOTSUPP;
 		goto out;
 	}
@@ -222,7 +223,7 @@ static int plca_get_status_prepare_data(const struct ethnl_req_info *req_base,
 	memset(&data->plca_st, 0xff,
 	       sizeof_field(struct plca_reply_data, plca_st));
 
-	ret = ops->get_plca_status(req_base->phydev, &data->plca_st);
+	ret = ops->get_plca_status(dev->phydev, &data->plca_st);
 	ethnl_ops_complete(dev);
 out:
 	return ret;
diff --git a/net/ethtool/pse-pd.c b/net/ethtool/pse-pd.c
index 4a1c8d37bd3d..cc478af77111 100644
--- a/net/ethtool/pse-pd.c
+++ b/net/ethtool/pse-pd.c
@@ -31,10 +31,12 @@ const struct nla_policy ethnl_pse_get_policy[ETHTOOL_A_PSE_HEADER + 1] = {
 	[ETHTOOL_A_PSE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy),
 };
 
-static int pse_get_pse_attributes(struct phy_device *phydev,
+static int pse_get_pse_attributes(struct net_device *dev,
 				  struct netlink_ext_ack *extack,
 				  struct pse_reply_data *data)
 {
+	struct phy_device *phydev = dev->phydev;
+
 	if (!phydev) {
 		NL_SET_ERR_MSG(extack, "No PHY is attached");
 		return -EOPNOTSUPP;
@@ -62,7 +64,7 @@ static int pse_prepare_data(const struct ethnl_req_info *req_base,
 	if (ret < 0)
 		return ret;
 
-	ret = pse_get_pse_attributes(req_base->phydev, info->extack, data);
+	ret = pse_get_pse_attributes(dev, info->extack, data);
 
 	ethnl_ops_complete(dev);
 
@@ -122,6 +124,7 @@ ethnl_set_pse_validate(struct ethnl_req_info *req_info, struct genl_info *info)
 static int
 ethnl_set_pse(struct ethnl_req_info *req_info, struct genl_info *info)
 {
+	struct net_device *dev = req_info->dev;
 	struct pse_control_config config = {};
 	struct nlattr **tb = info->attrs;
 	struct phy_device *phydev;
@@ -129,7 +132,7 @@ ethnl_set_pse(struct ethnl_req_info *req_info, struct genl_info *info)
 	/* this values are already validated by the ethnl_pse_set_policy */
 	config.admin_cotrol = nla_get_u32(tb[ETHTOOL_A_PODL_PSE_ADMIN_CONTROL]);
 
-	phydev = req_info->phydev;
+	phydev = dev->phydev;
 	if (!phydev) {
 		NL_SET_ERR_MSG(info->extack, "No PHY is attached");
 		return -EOPNOTSUPP;
diff --git a/net/ethtool/strset.c b/net/ethtool/strset.c
index 70c00631c51f..c678b484a079 100644
--- a/net/ethtool/strset.c
+++ b/net/ethtool/strset.c
@@ -233,18 +233,17 @@ static void strset_cleanup_data(struct ethnl_reply_data *reply_base)
 }
 
 static int strset_prepare_set(struct strset_info *info, struct net_device *dev,
-			      struct phy_device *phydev, unsigned int id,
-			      bool counts_only)
+			      unsigned int id, bool counts_only)
 {
 	const struct ethtool_phy_ops *phy_ops = ethtool_phy_ops;
 	const struct ethtool_ops *ops = dev->ethtool_ops;
 	void *strings;
 	int count, ret;
 
-	if (id == ETH_SS_PHY_STATS && phydev &&
+	if (id == ETH_SS_PHY_STATS && dev->phydev &&
 	    !ops->get_ethtool_phy_stats && phy_ops &&
 	    phy_ops->get_sset_count)
-		ret = phy_ops->get_sset_count(phydev);
+		ret = phy_ops->get_sset_count(dev->phydev);
 	else if (ops->get_sset_count && ops->get_strings)
 		ret = ops->get_sset_count(dev, id);
 	else
@@ -259,10 +258,10 @@ static int strset_prepare_set(struct strset_info *info, struct net_device *dev,
 		strings = kcalloc(count, ETH_GSTRING_LEN, GFP_KERNEL);
 		if (!strings)
 			return -ENOMEM;
-		if (id == ETH_SS_PHY_STATS && phydev &&
+		if (id == ETH_SS_PHY_STATS && dev->phydev &&
 		    !ops->get_ethtool_phy_stats && phy_ops &&
 		    phy_ops->get_strings)
-			phy_ops->get_strings(phydev, strings);
+			phy_ops->get_strings(dev->phydev, strings);
 		else
 			ops->get_strings(dev, id, strings);
 		info->strings = strings;
@@ -306,8 +305,8 @@ static int strset_prepare_data(const struct ethnl_req_info *req_base,
 		    !data->sets[i].per_dev)
 			continue;
 
-		ret = strset_prepare_set(&data->sets[i], dev, req_base->phydev,
-					 i, req_info->counts_only);
+		ret = strset_prepare_set(&data->sets[i], dev, i,
+					 req_info->counts_only);
 		if (ret < 0)
 			goto err_ops;
 	}
-- 
cgit v1.2.3


From 19bfcdf9498aa968ea293417fbbc39e523527ca8 Mon Sep 17 00:00:00 2001
From: Dmitrii Dolgov <9erthalion6@gmail.com>
Date: Wed, 3 Jan 2024 20:05:44 +0100
Subject: bpf: Relax tracing prog recursive attach rules

Currently, it's not allowed to attach an fentry/fexit prog to another
one fentry/fexit. At the same time it's not uncommon to see a tracing
program with lots of logic in use, and the attachment limitation
prevents usage of fentry/fexit for performance analysis (e.g. with
"bpftool prog profile" command) in this case. An example could be
falcosecurity libs project that uses tp_btf tracing programs.

Following the corresponding discussion [1], the reason for that is to
avoid tracing progs call cycles without introducing more complex
solutions. But currently it seems impossible to load and attach tracing
programs in a way that will form such a cycle. The limitation is coming
from the fact that attach_prog_fd is specified at the prog load (thus
making it impossible to attach to a program loaded after it in this
way), as well as tracing progs not implementing link_detach.

Replace "no same type" requirement with verification that no more than
one level of attachment nesting is allowed. In this way only one
fentry/fexit program could be attached to another fentry/fexit to cover
profiling use case, and still no cycle could be formed. To implement,
add a new field into bpf_prog_aux to track nested attachment for tracing
programs.

[1]: https://lore.kernel.org/bpf/20191108064039.2041889-16-ast@kernel.org/

Acked-by: Jiri Olsa <olsajiri@gmail.com>
Acked-by: Song Liu <song@kernel.org>
Signed-off-by: Dmitrii Dolgov <9erthalion6@gmail.com>
Link: https://lore.kernel.org/r/20240103190559.14750-2-9erthalion6@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h   |  1 +
 kernel/bpf/syscall.c  | 23 ++++++++++++++++++++++-
 kernel/bpf/verifier.c | 39 +++++++++++++++++++++++++--------------
 3 files changed, 48 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 7671530d6e4e..e30100597d0a 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1449,6 +1449,7 @@ struct bpf_prog_aux {
 	bool dev_bound; /* Program is bound to the netdev. */
 	bool offload_requested; /* Program is bound and offloaded to the netdev. */
 	bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */
+	bool attach_tracing_prog; /* true if tracing another tracing program */
 	bool func_proto_unreliable;
 	bool sleepable;
 	bool tail_call_reachable;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 1bf9805ee185..d15f9998bc20 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2738,6 +2738,22 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
 			goto free_prog_sec;
 	}
 
+	/*
+	 * Bookkeeping for managing the program attachment chain.
+	 *
+	 * It might be tempting to set attach_tracing_prog flag at the attachment
+	 * time, but this will not prevent from loading bunch of tracing prog
+	 * first, then attach them one to another.
+	 *
+	 * The flag attach_tracing_prog is set for the whole program lifecycle, and
+	 * doesn't have to be cleared in bpf_tracing_link_release, since tracing
+	 * programs cannot change attachment target.
+	 */
+	if (type == BPF_PROG_TYPE_TRACING && dst_prog &&
+	    dst_prog->type == BPF_PROG_TYPE_TRACING) {
+		prog->aux->attach_tracing_prog = true;
+	}
+
 	/* find program type: socket_filter vs tracing_filter */
 	err = find_prog_type(type, prog);
 	if (err < 0)
@@ -3171,7 +3187,12 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog,
 	}
 
 	if (tgt_prog_fd) {
-		/* For now we only allow new targets for BPF_PROG_TYPE_EXT */
+		/*
+		 * For now we only allow new targets for BPF_PROG_TYPE_EXT. If this
+		 * part would be changed to implement the same for
+		 * BPF_PROG_TYPE_TRACING, do not forget to update the way how
+		 * attach_tracing_prog flag is set.
+		 */
 		if (prog->type != BPF_PROG_TYPE_EXT) {
 			err = -EINVAL;
 			goto out_put_prog;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index d5f4ff1eb235..adbf330d364b 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -20317,6 +20317,7 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
 			    struct bpf_attach_target_info *tgt_info)
 {
 	bool prog_extension = prog->type == BPF_PROG_TYPE_EXT;
+	bool prog_tracing = prog->type == BPF_PROG_TYPE_TRACING;
 	const char prefix[] = "btf_trace_";
 	int ret = 0, subprog = -1, i;
 	const struct btf_type *t;
@@ -20387,10 +20388,21 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
 			bpf_log(log, "Can attach to only JITed progs\n");
 			return -EINVAL;
 		}
-		if (tgt_prog->type == prog->type) {
-			/* Cannot fentry/fexit another fentry/fexit program.
-			 * Cannot attach program extension to another extension.
-			 * It's ok to attach fentry/fexit to extension program.
+		if (prog_tracing) {
+			if (aux->attach_tracing_prog) {
+				/*
+				 * Target program is an fentry/fexit which is already attached
+				 * to another tracing program. More levels of nesting
+				 * attachment are not allowed.
+				 */
+				bpf_log(log, "Cannot nest tracing program attach more than once\n");
+				return -EINVAL;
+			}
+		} else if (tgt_prog->type == prog->type) {
+			/*
+			 * To avoid potential call chain cycles, prevent attaching of a
+			 * program extension to another extension. It's ok to attach
+			 * fentry/fexit to extension program.
 			 */
 			bpf_log(log, "Cannot recursively attach\n");
 			return -EINVAL;
@@ -20403,16 +20415,15 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
 			 * except fentry/fexit. The reason is the following.
 			 * The fentry/fexit programs are used for performance
 			 * analysis, stats and can be attached to any program
-			 * type except themselves. When extension program is
-			 * replacing XDP function it is necessary to allow
-			 * performance analysis of all functions. Both original
-			 * XDP program and its program extension. Hence
-			 * attaching fentry/fexit to BPF_PROG_TYPE_EXT is
-			 * allowed. If extending of fentry/fexit was allowed it
-			 * would be possible to create long call chain
-			 * fentry->extension->fentry->extension beyond
-			 * reasonable stack size. Hence extending fentry is not
-			 * allowed.
+			 * type. When extension program is replacing XDP function
+			 * it is necessary to allow performance analysis of all
+			 * functions. Both original XDP program and its program
+			 * extension. Hence attaching fentry/fexit to
+			 * BPF_PROG_TYPE_EXT is allowed. If extending of
+			 * fentry/fexit was allowed it would be possible to create
+			 * long call chain fentry->extension->fentry->extension
+			 * beyond reasonable stack size. Hence extending fentry
+			 * is not allowed.
 			 */
 			bpf_log(log, "Cannot extend fentry/fexit\n");
 			return -EINVAL;
-- 
cgit v1.2.3


From 990b6b5b13b7993b7f44740c0add3119d407ccbf Mon Sep 17 00:00:00 2001
From: Zhihao Cheng <chengzhihao1@huawei.com>
Date: Wed, 13 Dec 2023 09:32:20 +0800
Subject: jbd2: add errseq to detect client fs's bdev writeback error

Add errseq in journal, so that JBD2 can detect whether metadata is
successfully written to fs bdev. This patch adds detection in recovery
process to replace original solution(using local variable wb_err).

Signed-off-by: Zhihao Cheng <chengzhihao1@huawei.com>
Suggested-by: Jan Kara <jack@suse.cz>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20231213013224.2100050-2-chengzhihao1@huawei.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/jbd2/journal.c    |  1 +
 fs/jbd2/recovery.c   |  7 +------
 include/linux/jbd2.h | 26 ++++++++++++++++++++++++++
 3 files changed, 28 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 206cb53ef2b0..559938a82379 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1534,6 +1534,7 @@ static journal_t *journal_init_common(struct block_device *bdev,
 	journal->j_fs_dev = fs_dev;
 	journal->j_blk_offset = start;
 	journal->j_total_len = len;
+	jbd2_init_fs_dev_write_error(journal);
 
 	err = journal_load_superblock(journal);
 	if (err)
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 01f744cb97a4..1f7664984d6e 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -289,8 +289,6 @@ int jbd2_journal_recover(journal_t *journal)
 	journal_superblock_t *	sb;
 
 	struct recovery_info	info;
-	errseq_t		wb_err;
-	struct address_space	*mapping;
 
 	memset(&info, 0, sizeof(info));
 	sb = journal->j_superblock;
@@ -308,9 +306,6 @@ int jbd2_journal_recover(journal_t *journal)
 		return 0;
 	}
 
-	wb_err = 0;
-	mapping = journal->j_fs_dev->bd_inode->i_mapping;
-	errseq_check_and_advance(&mapping->wb_err, &wb_err);
 	err = do_one_pass(journal, &info, PASS_SCAN);
 	if (!err)
 		err = do_one_pass(journal, &info, PASS_REVOKE);
@@ -334,7 +329,7 @@ int jbd2_journal_recover(journal_t *journal)
 	err2 = sync_blockdev(journal->j_fs_dev);
 	if (!err)
 		err = err2;
-	err2 = errseq_check_and_advance(&mapping->wb_err, &wb_err);
+	err2 = jbd2_check_fs_dev_write_error(journal);
 	if (!err)
 		err = err2;
 	/* Make sure all replayed data is on permanent storage */
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index beb30719ee16..cea1aa70ae36 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -998,6 +998,13 @@ struct journal_s
 	 */
 	struct block_device	*j_fs_dev;
 
+	/**
+	 * @j_fs_dev_wb_err:
+	 *
+	 * Records the errseq of the client fs's backing block device.
+	 */
+	errseq_t		j_fs_dev_wb_err;
+
 	/**
 	 * @j_total_len: Total maximum capacity of the journal region on disk.
 	 */
@@ -1698,6 +1705,25 @@ static inline void jbd2_journal_abort_handle(handle_t *handle)
 	handle->h_aborted = 1;
 }
 
+static inline void jbd2_init_fs_dev_write_error(journal_t *journal)
+{
+	struct address_space *mapping = journal->j_fs_dev->bd_inode->i_mapping;
+
+	/*
+	 * Save the original wb_err value of client fs's bdev mapping which
+	 * could be used to detect the client fs's metadata async write error.
+	 */
+	errseq_check_and_advance(&mapping->wb_err, &journal->j_fs_dev_wb_err);
+}
+
+static inline int jbd2_check_fs_dev_write_error(journal_t *journal)
+{
+	struct address_space *mapping = journal->j_fs_dev->bd_inode->i_mapping;
+
+	return errseq_check(&mapping->wb_err,
+			    READ_ONCE(journal->j_fs_dev_wb_err));
+}
+
 #endif /* __KERNEL__   */
 
 /* Comparison functions for transaction IDs: perform comparisons using
-- 
cgit v1.2.3


From 8a4fd33d879fb303b207f06ea6340d73f698c4ed Mon Sep 17 00:00:00 2001
From: Zhihao Cheng <chengzhihao1@huawei.com>
Date: Wed, 13 Dec 2023 09:32:22 +0800
Subject: jbd2: remove unused 'JBD2_CHECKPOINT_IO_ERROR' and 'j_atomic_flags'

Since 'JBD2_CHECKPOINT_IO_ERROR' and j_atomic_flags' are not useful
anymore after fs dev's errseq is imported into jbd2, just remove them.

Signed-off-by: Zhihao Cheng <chengzhihao1@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20231213013224.2100050-4-chengzhihao1@huawei.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/jbd2/checkpoint.c | 11 -----------
 include/linux/jbd2.h | 11 -----------
 2 files changed, 22 deletions(-)

(limited to 'include')

diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 118699fff2f9..1c97e64c4784 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -556,7 +556,6 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh)
 	struct transaction_chp_stats_s *stats;
 	transaction_t *transaction;
 	journal_t *journal;
-	struct buffer_head *bh = jh2bh(jh);
 
 	JBUFFER_TRACE(jh, "entry");
 
@@ -569,16 +568,6 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh)
 
 	JBUFFER_TRACE(jh, "removing from transaction");
 
-	/*
-	 * If we have failed to write the buffer out to disk, the filesystem
-	 * may become inconsistent. We cannot abort the journal here since
-	 * we hold j_list_lock and we have to be careful about races with
-	 * jbd2_journal_destroy(). So mark the writeback IO error in the
-	 * journal here and we abort the journal later from a better context.
-	 */
-	if (buffer_write_io_error(bh))
-		set_bit(JBD2_CHECKPOINT_IO_ERROR, &journal->j_atomic_flags);
-
 	__buffer_unlink(jh);
 	jh->b_cp_transaction = NULL;
 	percpu_counter_dec(&journal->j_checkpoint_jh_count);
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index cea1aa70ae36..971f3e826e15 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -755,11 +755,6 @@ struct journal_s
 	 */
 	unsigned long		j_flags;
 
-	/**
-	 * @j_atomic_flags: Atomic journaling state flags.
-	 */
-	unsigned long		j_atomic_flags;
-
 	/**
 	 * @j_errno:
 	 *
@@ -1406,12 +1401,6 @@ JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit,	FAST_COMMIT)
 #define JBD2_JOURNAL_FLUSH_VALID	(JBD2_JOURNAL_FLUSH_DISCARD | \
 					JBD2_JOURNAL_FLUSH_ZEROOUT)
 
-/*
- * Journal atomic flag definitions
- */
-#define JBD2_CHECKPOINT_IO_ERROR	0x001	/* Detect io error while writing
-						 * buffer back to disk */
-
 /*
  * Function declarations for the journaling transaction and buffer
  * management
-- 
cgit v1.2.3


From c2e64baac4f36f7e0365218c7523bb9ba4639250 Mon Sep 17 00:00:00 2001
From: Thierry Reding <thierry.reding@gmail.com>
Date: Thu, 21 Dec 2023 11:08:02 +0100
Subject: pwm: Add pwm_apply_state() compatibility stub
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In order to make the transition to the new pwm_apply_might_sleep() a bit
smoother, add a compatibility stub. This will prevent new calls to the
old function introduced via other subsystems from breaking builds. Once
the next merge window has closed we can take another stab at removing
the stub.

Reviewed-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 include/linux/pwm.h | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index 5dd665d8c909..2a5e1154652e 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -537,6 +537,13 @@ static inline void pwm_apply_args(struct pwm_device *pwm)
 	pwm_apply_might_sleep(pwm, &state);
 }
 
+/* only for backwards-compatibility, new code should not use this */
+static inline int pwm_apply_state(struct pwm_device *pwm,
+				  const struct pwm_state *state)
+{
+	return pwm_apply_might_sleep(pwm, state);
+}
+
 struct pwm_lookup {
 	struct list_head list;
 	const char *provider;
-- 
cgit v1.2.3


From d73f444d06fb8a42a5c0623453f3ea1fe9880229 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 22 Dec 2023 21:06:20 -0800
Subject: pwm: linux/pwm.h: fix Excess kernel-doc description warning
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Remove the @pwm: line to prevent the kernel-doc warning:

include/linux/pwm.h:87: warning: Excess struct member 'pwm' description in 'pwm_device'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Thierry Reding <thierry.reding@gmail.com>
Cc: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Cc:  <linux-pwm@vger.kernel.org>
Fixes: f3e25e68ceb2 ("pwm: Drop unused member "pwm" from struct pwm_device")
Reviewed-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 include/linux/pwm.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index 2a5e1154652e..fcc2c4496f73 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -69,7 +69,6 @@ struct pwm_state {
  * @label: name of the PWM device
  * @flags: flags associated with the PWM device
  * @hwpwm: per-chip relative index of the PWM device
- * @pwm: global index of the PWM device
  * @chip: PWM chip providing this PWM device
  * @args: PWM arguments
  * @state: last applied state
-- 
cgit v1.2.3


From e9aa44736cb75e901d76ee59d80db1ae79d516f1 Mon Sep 17 00:00:00 2001
From: Shenghao Ding <shenghao-ding@ti.com>
Date: Thu, 4 Jan 2024 22:57:18 +0800
Subject: ASoC: tas2781: Add tas2563 into header file for DSP mode

Move tas2563 from tas2562 header file to tas2781 header file to unbind
tas2563 from tas2562 driver code and bind it to tas2781 driver code,
because tas2563 only work in bypass-DSP mode with tas2562 driver. In
order to enable DSP mode for tas2563, it has been moved to tas2781
driver. As to the hardware part, such as register setting and DSP
firmware, all these are stored in the binary firmware. What tas2781
drivder does is to parse the firmware and download it to the chip,
then power on the chip. So, tas2781 driver can be resued as tas2563
driver. Only attention will be paid to downloading corresponding firmware.

Signed-off-by: Shenghao Ding <shenghao-ding@ti.com>
Link: https://msgid.link/r/20240104145721.1398-3-shenghao-ding@ti.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/tas2781.h | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/sound/tas2781.h b/include/sound/tas2781.h
index a6c808b22318..813cf9446a58 100644
--- a/include/sound/tas2781.h
+++ b/include/sound/tas2781.h
@@ -1,13 +1,13 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 //
-// ALSA SoC Texas Instruments TAS2781 Audio Smart Amplifier
+// ALSA SoC Texas Instruments TAS2563/TAS2781 Audio Smart Amplifier
 //
 // Copyright (C) 2022 - 2023 Texas Instruments Incorporated
 // https://www.ti.com
 //
-// The TAS2781 driver implements a flexible and configurable
+// The TAS2563/TAS2781 driver implements a flexible and configurable
 // algo coefficient setting for one, two, or even multiple
-// TAS2781 chips.
+// TAS2563/TAS2781 chips.
 //
 // Author: Shenghao Ding <shenghao-ding@ti.com>
 // Author: Kevin Lu <kevin-lu@ti.com>
@@ -59,7 +59,8 @@
 #define TASDEVICE_CMD_FIELD_W		0x4
 
 enum audio_device {
-	TAS2781	= 0,
+	TAS2563,
+	TAS2781,
 };
 
 enum device_catlog_id {
-- 
cgit v1.2.3


From 92a714d727ec9e7ccfcc7432d348aba730145914 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 4 Jan 2024 15:52:11 +0000
Subject: netfs: Fix interaction between write-streaming and cachefiles culling

An issue can occur between write-streaming (storing dirty data in partial
non-uptodate pages) and a cachefiles object being culled to make space.
The problem occurs because the cache object is only marked in use while
there are files open using it.  Once it has been released, it can be culled
and the cookie marked disabled.

At this point, a streaming write is permitted to occur (if the cache is
active, we require pages to be prefetched and cached), but the cache can
become active again before this gets flushed out - and then two effects can
occur:

 (1) The cache may be asked to write out a region that's less than its DIO
     block size (assumed by cachefiles to be PAGE_SIZE) - and this causes
     one of two debugging statements to be emitted.

 (2) netfs_how_to_modify() gets confused because it sees a page that isn't
     allowed to be non-uptodate being uptodate and tries to prefetch it -
     leading to a warning that PG_fscache is set twice.

Fix this by the following means:

 (1) Add a netfs_inode flag to disallow write-streaming to an inode and set
     it if we ever do local caching of that inode.  It remains set for the
     lifetime of that inode - even if the cookie becomes disabled.

 (2) If the no-write-streaming flag is set, then make netfs_how_to_modify()
     always want to prefetch instead.

 (3) If netfs_how_to_modify() decides it wants to prefetch a folio, but
     that folio has write-streamed data in it, then it requires the folio
     be flushed first.

 (4) Export a counter of the number of times we wanted to prefetch a
     non-uptodate page, but found it had write-streamed data in it.

 (5) Export a counter of the number of times we cancelled a write to the
     cache because it didn't DIO align and remove the debug statements.

Reported-by: Marc Dionne <marc.dionne@auristor.com>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-erofs@lists.ozlabs.org
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/cachefiles/io.c            | 12 ++++++------
 fs/netfs/buffered_write.c     | 24 ++++++++++++++++++++----
 fs/netfs/fscache_stats.c      |  9 ++++++---
 fs/netfs/internal.h           |  1 +
 fs/netfs/stats.c              |  6 ++++--
 include/linux/fscache-cache.h |  3 +++
 include/linux/netfs.h         |  1 +
 7 files changed, 41 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c
index 7529b40bc95a..3eec26967437 100644
--- a/fs/cachefiles/io.c
+++ b/fs/cachefiles/io.c
@@ -528,12 +528,12 @@ int __cachefiles_prepare_write(struct cachefiles_object *object,
 
 	/* Round to DIO size */
 	start = round_down(*_start, PAGE_SIZE);
-	if (start != *_start) {
-		kleave(" = -ENOBUFS [down]");
-		return -ENOBUFS;
-	}
-	if (*_len > upper_len) {
-		kleave(" = -ENOBUFS [up]");
+	if (start != *_start || *_len > upper_len) {
+		/* Probably asked to cache a streaming write written into the
+		 * pagecache when the cookie was temporarily out of service to
+		 * culling.
+		 */
+		fscache_count_dio_misfit();
 		return -ENOBUFS;
 	}
 
diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index 08f28800232c..6cd8f7422e9a 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -80,10 +80,19 @@ static enum netfs_how_to_modify netfs_how_to_modify(struct netfs_inode *ctx,
 		return NETFS_WHOLE_FOLIO_MODIFY;
 
 	if (file->f_mode & FMODE_READ)
-		return NETFS_JUST_PREFETCH;
-
-	if (netfs_is_cache_enabled(ctx))
-		return NETFS_JUST_PREFETCH;
+		goto no_write_streaming;
+	if (test_bit(NETFS_ICTX_NO_WRITE_STREAMING, &ctx->flags))
+		goto no_write_streaming;
+
+	if (netfs_is_cache_enabled(ctx)) {
+		/* We don't want to get a streaming write on a file that loses
+		 * caching service temporarily because the backing store got
+		 * culled.
+		 */
+		if (!test_bit(NETFS_ICTX_NO_WRITE_STREAMING, &ctx->flags))
+			set_bit(NETFS_ICTX_NO_WRITE_STREAMING, &ctx->flags);
+		goto no_write_streaming;
+	}
 
 	if (!finfo)
 		return NETFS_STREAMING_WRITE;
@@ -95,6 +104,13 @@ static enum netfs_how_to_modify netfs_how_to_modify(struct netfs_inode *ctx,
 	if (offset == finfo->dirty_offset + finfo->dirty_len)
 		return NETFS_STREAMING_WRITE_CONT;
 	return NETFS_FLUSH_CONTENT;
+
+no_write_streaming:
+	if (finfo) {
+		netfs_stat(&netfs_n_wh_wstream_conflict);
+		return NETFS_FLUSH_CONTENT;
+	}
+	return NETFS_JUST_PREFETCH;
 }
 
 /*
diff --git a/fs/netfs/fscache_stats.c b/fs/netfs/fscache_stats.c
index aad812ead398..add21abdf713 100644
--- a/fs/netfs/fscache_stats.c
+++ b/fs/netfs/fscache_stats.c
@@ -48,13 +48,15 @@ atomic_t fscache_n_no_create_space;
 EXPORT_SYMBOL(fscache_n_no_create_space);
 atomic_t fscache_n_culled;
 EXPORT_SYMBOL(fscache_n_culled);
+atomic_t fscache_n_dio_misfit;
+EXPORT_SYMBOL(fscache_n_dio_misfit);
 
 /*
  * display the general statistics
  */
 int fscache_stats_show(struct seq_file *m)
 {
-	seq_puts(m, "FS-Cache statistics\n");
+	seq_puts(m, "-- FS-Cache statistics --\n");
 	seq_printf(m, "Cookies: n=%d v=%d vcol=%u voom=%u\n",
 		   atomic_read(&fscache_n_cookies),
 		   atomic_read(&fscache_n_volumes),
@@ -93,8 +95,9 @@ int fscache_stats_show(struct seq_file *m)
 		   atomic_read(&fscache_n_no_create_space),
 		   atomic_read(&fscache_n_culled));
 
-	seq_printf(m, "IO     : rd=%u wr=%u\n",
+	seq_printf(m, "IO     : rd=%u wr=%u mis=%u\n",
 		   atomic_read(&fscache_n_read),
-		   atomic_read(&fscache_n_write));
+		   atomic_read(&fscache_n_write),
+		   atomic_read(&fscache_n_dio_misfit));
 	return 0;
 }
diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index 3f9620d0fa63..ec7045d24400 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -123,6 +123,7 @@ extern atomic_t netfs_n_rh_write_begin;
 extern atomic_t netfs_n_rh_write_done;
 extern atomic_t netfs_n_rh_write_failed;
 extern atomic_t netfs_n_rh_write_zskip;
+extern atomic_t netfs_n_wh_wstream_conflict;
 extern atomic_t netfs_n_wh_upload;
 extern atomic_t netfs_n_wh_upload_done;
 extern atomic_t netfs_n_wh_upload_failed;
diff --git a/fs/netfs/stats.c b/fs/netfs/stats.c
index 42db36528d92..deeba9f9dcf5 100644
--- a/fs/netfs/stats.c
+++ b/fs/netfs/stats.c
@@ -29,6 +29,7 @@ atomic_t netfs_n_rh_write_begin;
 atomic_t netfs_n_rh_write_done;
 atomic_t netfs_n_rh_write_failed;
 atomic_t netfs_n_rh_write_zskip;
+atomic_t netfs_n_wh_wstream_conflict;
 atomic_t netfs_n_wh_upload;
 atomic_t netfs_n_wh_upload_done;
 atomic_t netfs_n_wh_upload_failed;
@@ -66,9 +67,10 @@ int netfs_stats_show(struct seq_file *m, void *v)
 		   atomic_read(&netfs_n_wh_write),
 		   atomic_read(&netfs_n_wh_write_done),
 		   atomic_read(&netfs_n_wh_write_failed));
-	seq_printf(m, "Netfs  : rr=%u sr=%u\n",
+	seq_printf(m, "Netfs  : rr=%u sr=%u wsc=%u\n",
 		   atomic_read(&netfs_n_rh_rreq),
-		   atomic_read(&netfs_n_rh_sreq));
+		   atomic_read(&netfs_n_rh_sreq),
+		   atomic_read(&netfs_n_wh_wstream_conflict));
 	return fscache_stats_show(m);
 }
 EXPORT_SYMBOL(netfs_stats_show);
diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h
index a174cedf4d90..bdf7f3eddf0a 100644
--- a/include/linux/fscache-cache.h
+++ b/include/linux/fscache-cache.h
@@ -189,17 +189,20 @@ extern atomic_t fscache_n_write;
 extern atomic_t fscache_n_no_write_space;
 extern atomic_t fscache_n_no_create_space;
 extern atomic_t fscache_n_culled;
+extern atomic_t fscache_n_dio_misfit;
 #define fscache_count_read() atomic_inc(&fscache_n_read)
 #define fscache_count_write() atomic_inc(&fscache_n_write)
 #define fscache_count_no_write_space() atomic_inc(&fscache_n_no_write_space)
 #define fscache_count_no_create_space() atomic_inc(&fscache_n_no_create_space)
 #define fscache_count_culled() atomic_inc(&fscache_n_culled)
+#define fscache_count_dio_misfit() atomic_inc(&fscache_n_dio_misfit)
 #else
 #define fscache_count_read() do {} while(0)
 #define fscache_count_write() do {} while(0)
 #define fscache_count_no_write_space() do {} while(0)
 #define fscache_count_no_create_space() do {} while(0)
 #define fscache_count_culled() do {} while(0)
+#define fscache_count_dio_misfit() do {} while(0)
 #endif
 
 #endif /* _LINUX_FSCACHE_CACHE_H */
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index d3bac60fcd6f..100cbb261269 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -142,6 +142,7 @@ struct netfs_inode {
 #define NETFS_ICTX_ODIRECT	0		/* The file has DIO in progress */
 #define NETFS_ICTX_UNBUFFERED	1		/* I/O should not use the pagecache */
 #define NETFS_ICTX_WRITETHROUGH	2		/* Write-through caching */
+#define NETFS_ICTX_NO_WRITE_STREAMING	3	/* Don't engage in write-streaming */
 };
 
 /*
-- 
cgit v1.2.3


From 8a6286c1804e2c7144aef3154a0357c4b496e10b Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Wed, 3 Jan 2024 14:28:36 +0100
Subject: dpll: expose fractional frequency offset value to user

Add a new netlink attribute to expose fractional frequency offset value
for a pin. Add an op to get the value from the driver.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Acked-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Acked-by: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Link: https://lore.kernel.org/r/20240103132838.1501801-2-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/dpll.yaml | 11 +++++++++++
 drivers/dpll/dpll_netlink.c           | 24 ++++++++++++++++++++++++
 include/linux/dpll.h                  |  3 +++
 include/uapi/linux/dpll.h             |  1 +
 4 files changed, 39 insertions(+)

(limited to 'include')

diff --git a/Documentation/netlink/specs/dpll.yaml b/Documentation/netlink/specs/dpll.yaml
index cf8abe1c0550..b14aed18065f 100644
--- a/Documentation/netlink/specs/dpll.yaml
+++ b/Documentation/netlink/specs/dpll.yaml
@@ -296,6 +296,16 @@ attribute-sets:
       -
         name: phase-offset
         type: s64
+      -
+        name: fractional-frequency-offset
+        type: sint
+        doc: |
+          The FFO (Fractional Frequency Offset) between the RX and TX
+          symbol rate on the media associated with the pin:
+          (rx_frequency-tx_frequency)/rx_frequency
+          Value is in PPM (parts per million).
+          This may be implemented for example for pin of type
+          PIN_TYPE_SYNCE_ETH_PORT.
   -
     name: pin-parent-device
     subset-of: pin
@@ -460,6 +470,7 @@ operations:
             - phase-adjust-min
             - phase-adjust-max
             - phase-adjust
+            - fractional-frequency-offset
 
       dump:
         pre: dpll-lock-dumpit
diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c
index 21c627e9401a..3370dbddb86b 100644
--- a/drivers/dpll/dpll_netlink.c
+++ b/drivers/dpll/dpll_netlink.c
@@ -263,6 +263,27 @@ dpll_msg_add_phase_offset(struct sk_buff *msg, struct dpll_pin *pin,
 	return 0;
 }
 
+static int dpll_msg_add_ffo(struct sk_buff *msg, struct dpll_pin *pin,
+			    struct dpll_pin_ref *ref,
+			    struct netlink_ext_ack *extack)
+{
+	const struct dpll_pin_ops *ops = dpll_pin_ops(ref);
+	struct dpll_device *dpll = ref->dpll;
+	s64 ffo;
+	int ret;
+
+	if (!ops->ffo_get)
+		return 0;
+	ret = ops->ffo_get(pin, dpll_pin_on_dpll_priv(dpll, pin),
+			   dpll, dpll_priv(dpll), &ffo, extack);
+	if (ret) {
+		if (ret == -ENODATA)
+			return 0;
+		return ret;
+	}
+	return nla_put_sint(msg, DPLL_A_PIN_FRACTIONAL_FREQUENCY_OFFSET, ffo);
+}
+
 static int
 dpll_msg_add_pin_freq(struct sk_buff *msg, struct dpll_pin *pin,
 		      struct dpll_pin_ref *ref, struct netlink_ext_ack *extack)
@@ -440,6 +461,9 @@ dpll_cmd_pin_get_one(struct sk_buff *msg, struct dpll_pin *pin,
 			prop->phase_range.max))
 		return -EMSGSIZE;
 	ret = dpll_msg_add_pin_phase_adjust(msg, pin, ref, extack);
+	if (ret)
+		return ret;
+	ret = dpll_msg_add_ffo(msg, pin, ref, extack);
 	if (ret)
 		return ret;
 	if (xa_empty(&pin->parent_refs))
diff --git a/include/linux/dpll.h b/include/linux/dpll.h
index b1a5f9ca8ee5..9cf896ea1d41 100644
--- a/include/linux/dpll.h
+++ b/include/linux/dpll.h
@@ -77,6 +77,9 @@ struct dpll_pin_ops {
 				const struct dpll_device *dpll, void *dpll_priv,
 				const s32 phase_adjust,
 				struct netlink_ext_ack *extack);
+	int (*ffo_get)(const struct dpll_pin *pin, void *pin_priv,
+		       const struct dpll_device *dpll, void *dpll_priv,
+		       s64 *ffo, struct netlink_ext_ack *extack);
 };
 
 struct dpll_pin_frequency {
diff --git a/include/uapi/linux/dpll.h b/include/uapi/linux/dpll.h
index 715a491d2727..b4e947f9bfbc 100644
--- a/include/uapi/linux/dpll.h
+++ b/include/uapi/linux/dpll.h
@@ -179,6 +179,7 @@ enum dpll_a_pin {
 	DPLL_A_PIN_PHASE_ADJUST_MAX,
 	DPLL_A_PIN_PHASE_ADJUST,
 	DPLL_A_PIN_PHASE_OFFSET,
+	DPLL_A_PIN_FRACTIONAL_FREQUENCY_OFFSET,
 
 	__DPLL_A_PIN_MAX,
 	DPLL_A_PIN_MAX = (__DPLL_A_PIN_MAX - 1)
-- 
cgit v1.2.3


From 9c5938694cd0e9e00bdfb7e60900673263daf4d5 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Fri, 5 Jan 2024 16:57:29 +0100
Subject: mm/rmap: silence VM_WARN_ON_FOLIO() in __folio_rmap_sanity_checks()

Unfortunately, vm_insert_page() and friends and up passing
driver-allocated folios into folio_add_file_rmap_pte() using
insert_page_into_pte_locked().

While these driver-allocated folios can be compound pages (large folios),
they are not proper "rmappable" folios.

In these VM_MIXEDMAP VMAs, there isn't really the concept of a reverse
mapping, so long-term, we should clean that up and not call into rmap
code.

For the time being, document how we can end up in rmap code with large
folios that are not marked rmappable.

Link: https://lkml.kernel.org/r/793c5cee-d5fc-4eb1-86a2-39e05686233d@redhat.com
Fixes: 68f0320824fa ("mm/rmap: convert folio_add_file_rmap_range() into folio_add_file_rmap_[pte|ptes|pmd]()")
Reported-by: syzbot+50ef73537bbc393a25bb@syzkaller.appspotmail.com
Closes: https://lkml.kernel.org/r/000000000000014174060e09316e@google.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Yin Fengwei <fengwei.yin@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/rmap.h | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index fd6fe16fa358..b7944a833668 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -199,8 +199,15 @@ static inline void __folio_rmap_sanity_checks(struct folio *folio,
 {
 	/* hugetlb folios are handled separately. */
 	VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio);
-	VM_WARN_ON_FOLIO(folio_test_large(folio) &&
-			 !folio_test_large_rmappable(folio), folio);
+
+	/*
+	 * TODO: we get driver-allocated folios that have nothing to do with
+	 * the rmap using vm_insert_page(); therefore, we cannot assume that
+	 * folio_test_large_rmappable() holds for large folios. We should
+	 * handle any desired mapcount+stats accounting for these folios in
+	 * VM_MIXEDMAP VMAs separately, and then sanity-check here that
+	 * we really only get rmappable folios.
+	 */
 
 	VM_WARN_ON_ONCE(nr_pages <= 0);
 	VM_WARN_ON_FOLIO(page_folio(page) != folio, folio);
-- 
cgit v1.2.3


From 71ce1ab54a505736786d9c5921e6c2718c7ec535 Mon Sep 17 00:00:00 2001
From: Kinsey Ho <kinseyho@google.com>
Date: Wed, 27 Dec 2023 14:12:01 +0000
Subject: mm/mglru: add CONFIG_ARCH_HAS_HW_PTE_YOUNG

Patch series "mm/mglru: Kconfig cleanup", v4.

This series is the result of the following discussion:
https://lore.kernel.org/47066176-bd93-55dd-c2fa-002299d9e034@linux.ibm.com/

It mainly avoids building the code that walks page tables on CPUs that
use it, i.e., those don't support hardware accessed bit. Specifically,
it introduces a new Kconfig to guard some of functions added by
commit bd74fdaea146 ("mm: multi-gen LRU: support page table walks")
on CPUs like POWER9, on which the series was tested.


This patch (of 5):

Some architectures are able to set the accessed bit in PTEs when PTEs
are used as part of linear address translations.

Add CONFIG_ARCH_HAS_HW_PTE_YOUNG for such architectures to be able to
override arch_has_hw_pte_young().

Link: https://lkml.kernel.org/r/20231227141205.2200125-1-kinseyho@google.com
Link: https://lkml.kernel.org/r/20231227141205.2200125-2-kinseyho@google.com
Signed-off-by: Kinsey Ho <kinseyho@google.com>
Co-developed-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Tested-by: Donet Tom <donettom@linux.vnet.ibm.com>
Acked-by: Yu Zhao <yuzhao@google.com>
Cc: kernel test robot <lkp@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/Kconfig                   | 8 ++++++++
 arch/arm64/Kconfig             | 1 +
 arch/x86/Kconfig               | 1 +
 arch/x86/include/asm/pgtable.h | 6 ------
 include/linux/pgtable.h        | 2 +-
 5 files changed, 11 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/arch/Kconfig b/arch/Kconfig
index f4b210ab0612..8c8901f80586 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -1470,6 +1470,14 @@ config DYNAMIC_SIGFRAME
 config HAVE_ARCH_NODE_DEV_GROUP
 	bool
 
+config ARCH_HAS_HW_PTE_YOUNG
+	bool
+	help
+	  Architectures that select this option are capable of setting the
+	  accessed bit in PTE entries when using them as part of linear address
+	  translations. Architectures that require runtime check should select
+	  this option and override arch_has_hw_pte_young().
+
 config ARCH_HAS_NONLEAF_PMD_YOUNG
 	bool
 	help
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 7b071a00425d..12d611f3da5d 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -36,6 +36,7 @@ config ARM64
 	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
 	select ARCH_HAS_PTE_DEVMAP
 	select ARCH_HAS_PTE_SPECIAL
+	select ARCH_HAS_HW_PTE_YOUNG
 	select ARCH_HAS_SETUP_DMA_OPS
 	select ARCH_HAS_SET_DIRECT_MAP
 	select ARCH_HAS_SET_MEMORY
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 1566748f16c4..04941a1ffc0a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -88,6 +88,7 @@ config X86
 	select ARCH_HAS_PMEM_API		if X86_64
 	select ARCH_HAS_PTE_DEVMAP		if X86_64
 	select ARCH_HAS_PTE_SPECIAL
+	select ARCH_HAS_HW_PTE_YOUNG
 	select ARCH_HAS_NONLEAF_PMD_YOUNG	if PGTABLE_LEVELS > 2
 	select ARCH_HAS_UACCESS_FLUSHCACHE	if X86_64
 	select ARCH_HAS_COPY_MC			if X86_64
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 57bab91bbf50..08b5cb22d9a6 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -1679,12 +1679,6 @@ static inline bool arch_has_pfn_modify_check(void)
 	return boot_cpu_has_bug(X86_BUG_L1TF);
 }
 
-#define arch_has_hw_pte_young arch_has_hw_pte_young
-static inline bool arch_has_hw_pte_young(void)
-{
-	return true;
-}
-
 #define arch_check_zapped_pte arch_check_zapped_pte
 void arch_check_zapped_pte(struct vm_area_struct *vma, pte_t pte);
 
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index af7639c3b0a3..9ecc20fa6269 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -375,7 +375,7 @@ static inline bool arch_has_hw_nonleaf_pmd_young(void)
  */
 static inline bool arch_has_hw_pte_young(void)
 {
-	return false;
+	return IS_ENABLED(CONFIG_ARCH_HAS_HW_PTE_YOUNG);
 }
 #endif
 
-- 
cgit v1.2.3


From 61dd3f246b3adaabff3241c586f2210ac91b05a4 Mon Sep 17 00:00:00 2001
From: Kinsey Ho <kinseyho@google.com>
Date: Wed, 27 Dec 2023 14:12:02 +0000
Subject: mm/mglru: add CONFIG_LRU_GEN_WALKS_MMU

Add CONFIG_LRU_GEN_WALKS_MMU such that if disabled, the code that
walks page tables to promote pages into the youngest generation will
not be built.

Also improves code readability by adding two helper functions
get_mm_state() and get_next_mm().

Link: https://lkml.kernel.org/r/20231227141205.2200125-3-kinseyho@google.com
Signed-off-by: Kinsey Ho <kinseyho@google.com>
Co-developed-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Tested-by: Donet Tom <donettom@linux.vnet.ibm.com>
Acked-by: Yu Zhao <yuzhao@google.com>
Cc: kernel test robot <lkp@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/memcontrol.h |   2 +-
 include/linux/mm_types.h   |  12 ++-
 include/linux/mmzone.h     |   2 +
 kernel/fork.c              |   2 +-
 mm/Kconfig                 |   4 +
 mm/vmscan.c                | 192 +++++++++++++++++++++++++++++----------------
 6 files changed, 139 insertions(+), 75 deletions(-)

(limited to 'include')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 5de775e6cdd9..20ff87f8e001 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -330,7 +330,7 @@ struct mem_cgroup {
 	struct deferred_split deferred_split_queue;
 #endif
 
-#ifdef CONFIG_LRU_GEN
+#ifdef CONFIG_LRU_GEN_WALKS_MMU
 	/* per-memcg mm_struct list */
 	struct lru_gen_mm_list mm_list;
 #endif
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index a66534c78c4d..552fa2d11c57 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -958,7 +958,7 @@ struct mm_struct {
 		 */
 		unsigned long ksm_zero_pages;
 #endif /* CONFIG_KSM */
-#ifdef CONFIG_LRU_GEN
+#ifdef CONFIG_LRU_GEN_WALKS_MMU
 		struct {
 			/* this mm_struct is on lru_gen_mm_list */
 			struct list_head list;
@@ -973,7 +973,7 @@ struct mm_struct {
 			struct mem_cgroup *memcg;
 #endif
 		} lru_gen;
-#endif /* CONFIG_LRU_GEN */
+#endif /* CONFIG_LRU_GEN_WALKS_MMU */
 	} __randomize_layout;
 
 	/*
@@ -1011,6 +1011,10 @@ struct lru_gen_mm_list {
 	spinlock_t lock;
 };
 
+#endif /* CONFIG_LRU_GEN */
+
+#ifdef CONFIG_LRU_GEN_WALKS_MMU
+
 void lru_gen_add_mm(struct mm_struct *mm);
 void lru_gen_del_mm(struct mm_struct *mm);
 #ifdef CONFIG_MEMCG
@@ -1036,7 +1040,7 @@ static inline void lru_gen_use_mm(struct mm_struct *mm)
 	WRITE_ONCE(mm->lru_gen.bitmap, -1);
 }
 
-#else /* !CONFIG_LRU_GEN */
+#else /* !CONFIG_LRU_GEN_WALKS_MMU */
 
 static inline void lru_gen_add_mm(struct mm_struct *mm)
 {
@@ -1060,7 +1064,7 @@ static inline void lru_gen_use_mm(struct mm_struct *mm)
 {
 }
 
-#endif /* CONFIG_LRU_GEN */
+#endif /* CONFIG_LRU_GEN_WALKS_MMU */
 
 struct vma_iterator {
 	struct ma_state mas;
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 2efd3be484fd..bc3f63ec4291 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -640,9 +640,11 @@ struct lruvec {
 #ifdef CONFIG_LRU_GEN
 	/* evictable pages divided into generations */
 	struct lru_gen_folio		lrugen;
+#ifdef CONFIG_LRU_GEN_WALKS_MMU
 	/* to concurrently iterate lru_gen_mm_list */
 	struct lru_gen_mm_state		mm_state;
 #endif
+#endif /* CONFIG_LRU_GEN */
 #ifdef CONFIG_MEMCG
 	struct pglist_data *pgdat;
 #endif
diff --git a/kernel/fork.c b/kernel/fork.c
index 93924392a5c3..56cf276432c8 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2946,7 +2946,7 @@ pid_t kernel_clone(struct kernel_clone_args *args)
 		get_task_struct(p);
 	}
 
-	if (IS_ENABLED(CONFIG_LRU_GEN) && !(clone_flags & CLONE_VM)) {
+	if (IS_ENABLED(CONFIG_LRU_GEN_WALKS_MMU) && !(clone_flags & CLONE_VM)) {
 		/* lock the task to synchronize with memcg migration */
 		task_lock(p);
 		lru_gen_add_mm(p->mm);
diff --git a/mm/Kconfig b/mm/Kconfig
index b072664b889a..79d563d8f9e0 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -1274,6 +1274,10 @@ config LRU_GEN_STATS
 	  from evicted generations for debugging purpose.
 
 	  This option has a per-memcg and per-node memory overhead.
+
+config LRU_GEN_WALKS_MMU
+	def_bool y
+	depends on LRU_GEN && ARCH_HAS_HW_PTE_YOUNG
 # }
 
 config ARCH_SUPPORTS_PER_VMA_LOCK
diff --git a/mm/vmscan.c b/mm/vmscan.c
index b4ca3563bcf4..aa7ea09ffb4c 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2671,13 +2671,14 @@ static void get_item_key(void *item, int *key)
 	key[1] = hash >> BLOOM_FILTER_SHIFT;
 }
 
-static bool test_bloom_filter(struct lruvec *lruvec, unsigned long seq, void *item)
+static bool test_bloom_filter(struct lru_gen_mm_state *mm_state, unsigned long seq,
+			      void *item)
 {
 	int key[2];
 	unsigned long *filter;
 	int gen = filter_gen_from_seq(seq);
 
-	filter = READ_ONCE(lruvec->mm_state.filters[gen]);
+	filter = READ_ONCE(mm_state->filters[gen]);
 	if (!filter)
 		return true;
 
@@ -2686,13 +2687,14 @@ static bool test_bloom_filter(struct lruvec *lruvec, unsigned long seq, void *it
 	return test_bit(key[0], filter) && test_bit(key[1], filter);
 }
 
-static void update_bloom_filter(struct lruvec *lruvec, unsigned long seq, void *item)
+static void update_bloom_filter(struct lru_gen_mm_state *mm_state, unsigned long seq,
+				void *item)
 {
 	int key[2];
 	unsigned long *filter;
 	int gen = filter_gen_from_seq(seq);
 
-	filter = READ_ONCE(lruvec->mm_state.filters[gen]);
+	filter = READ_ONCE(mm_state->filters[gen]);
 	if (!filter)
 		return;
 
@@ -2704,12 +2706,12 @@ static void update_bloom_filter(struct lruvec *lruvec, unsigned long seq, void *
 		set_bit(key[1], filter);
 }
 
-static void reset_bloom_filter(struct lruvec *lruvec, unsigned long seq)
+static void reset_bloom_filter(struct lru_gen_mm_state *mm_state, unsigned long seq)
 {
 	unsigned long *filter;
 	int gen = filter_gen_from_seq(seq);
 
-	filter = lruvec->mm_state.filters[gen];
+	filter = mm_state->filters[gen];
 	if (filter) {
 		bitmap_clear(filter, 0, BIT(BLOOM_FILTER_SHIFT));
 		return;
@@ -2717,13 +2719,15 @@ static void reset_bloom_filter(struct lruvec *lruvec, unsigned long seq)
 
 	filter = bitmap_zalloc(BIT(BLOOM_FILTER_SHIFT),
 			       __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN);
-	WRITE_ONCE(lruvec->mm_state.filters[gen], filter);
+	WRITE_ONCE(mm_state->filters[gen], filter);
 }
 
 /******************************************************************************
  *                          mm_struct list
  ******************************************************************************/
 
+#ifdef CONFIG_LRU_GEN_WALKS_MMU
+
 static struct lru_gen_mm_list *get_mm_list(struct mem_cgroup *memcg)
 {
 	static struct lru_gen_mm_list mm_list = {
@@ -2740,6 +2744,29 @@ static struct lru_gen_mm_list *get_mm_list(struct mem_cgroup *memcg)
 	return &mm_list;
 }
 
+static struct lru_gen_mm_state *get_mm_state(struct lruvec *lruvec)
+{
+	return &lruvec->mm_state;
+}
+
+static struct mm_struct *get_next_mm(struct lru_gen_mm_walk *walk)
+{
+	int key;
+	struct mm_struct *mm;
+	struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec);
+	struct lru_gen_mm_state *mm_state = get_mm_state(walk->lruvec);
+
+	mm = list_entry(mm_state->head, struct mm_struct, lru_gen.list);
+	key = pgdat->node_id % BITS_PER_TYPE(mm->lru_gen.bitmap);
+
+	if (!walk->force_scan && !test_bit(key, &mm->lru_gen.bitmap))
+		return NULL;
+
+	clear_bit(key, &mm->lru_gen.bitmap);
+
+	return mmget_not_zero(mm) ? mm : NULL;
+}
+
 void lru_gen_add_mm(struct mm_struct *mm)
 {
 	int nid;
@@ -2755,10 +2782,11 @@ void lru_gen_add_mm(struct mm_struct *mm)
 
 	for_each_node_state(nid, N_MEMORY) {
 		struct lruvec *lruvec = get_lruvec(memcg, nid);
+		struct lru_gen_mm_state *mm_state = get_mm_state(lruvec);
 
 		/* the first addition since the last iteration */
-		if (lruvec->mm_state.tail == &mm_list->fifo)
-			lruvec->mm_state.tail = &mm->lru_gen.list;
+		if (mm_state->tail == &mm_list->fifo)
+			mm_state->tail = &mm->lru_gen.list;
 	}
 
 	list_add_tail(&mm->lru_gen.list, &mm_list->fifo);
@@ -2784,14 +2812,15 @@ void lru_gen_del_mm(struct mm_struct *mm)
 
 	for_each_node(nid) {
 		struct lruvec *lruvec = get_lruvec(memcg, nid);
+		struct lru_gen_mm_state *mm_state = get_mm_state(lruvec);
 
 		/* where the current iteration continues after */
-		if (lruvec->mm_state.head == &mm->lru_gen.list)
-			lruvec->mm_state.head = lruvec->mm_state.head->prev;
+		if (mm_state->head == &mm->lru_gen.list)
+			mm_state->head = mm_state->head->prev;
 
 		/* where the last iteration ended before */
-		if (lruvec->mm_state.tail == &mm->lru_gen.list)
-			lruvec->mm_state.tail = lruvec->mm_state.tail->next;
+		if (mm_state->tail == &mm->lru_gen.list)
+			mm_state->tail = mm_state->tail->next;
 	}
 
 	list_del_init(&mm->lru_gen.list);
@@ -2834,10 +2863,30 @@ void lru_gen_migrate_mm(struct mm_struct *mm)
 }
 #endif
 
+#else /* !CONFIG_LRU_GEN_WALKS_MMU */
+
+static struct lru_gen_mm_list *get_mm_list(struct mem_cgroup *memcg)
+{
+	return NULL;
+}
+
+static struct lru_gen_mm_state *get_mm_state(struct lruvec *lruvec)
+{
+	return NULL;
+}
+
+static struct mm_struct *get_next_mm(struct lru_gen_mm_walk *walk)
+{
+	return NULL;
+}
+
+#endif
+
 static void reset_mm_stats(struct lruvec *lruvec, struct lru_gen_mm_walk *walk, bool last)
 {
 	int i;
 	int hist;
+	struct lru_gen_mm_state *mm_state = get_mm_state(lruvec);
 
 	lockdep_assert_held(&get_mm_list(lruvec_memcg(lruvec))->lock);
 
@@ -2845,44 +2894,20 @@ static void reset_mm_stats(struct lruvec *lruvec, struct lru_gen_mm_walk *walk,
 		hist = lru_hist_from_seq(walk->max_seq);
 
 		for (i = 0; i < NR_MM_STATS; i++) {
-			WRITE_ONCE(lruvec->mm_state.stats[hist][i],
-				   lruvec->mm_state.stats[hist][i] + walk->mm_stats[i]);
+			WRITE_ONCE(mm_state->stats[hist][i],
+				   mm_state->stats[hist][i] + walk->mm_stats[i]);
 			walk->mm_stats[i] = 0;
 		}
 	}
 
 	if (NR_HIST_GENS > 1 && last) {
-		hist = lru_hist_from_seq(lruvec->mm_state.seq + 1);
+		hist = lru_hist_from_seq(mm_state->seq + 1);
 
 		for (i = 0; i < NR_MM_STATS; i++)
-			WRITE_ONCE(lruvec->mm_state.stats[hist][i], 0);
+			WRITE_ONCE(mm_state->stats[hist][i], 0);
 	}
 }
 
-static bool should_skip_mm(struct mm_struct *mm, struct lru_gen_mm_walk *walk)
-{
-	int type;
-	unsigned long size = 0;
-	struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec);
-	int key = pgdat->node_id % BITS_PER_TYPE(mm->lru_gen.bitmap);
-
-	if (!walk->force_scan && !test_bit(key, &mm->lru_gen.bitmap))
-		return true;
-
-	clear_bit(key, &mm->lru_gen.bitmap);
-
-	for (type = !walk->can_swap; type < ANON_AND_FILE; type++) {
-		size += type ? get_mm_counter(mm, MM_FILEPAGES) :
-			       get_mm_counter(mm, MM_ANONPAGES) +
-			       get_mm_counter(mm, MM_SHMEMPAGES);
-	}
-
-	if (size < MIN_LRU_BATCH)
-		return true;
-
-	return !mmget_not_zero(mm);
-}
-
 static bool iterate_mm_list(struct lruvec *lruvec, struct lru_gen_mm_walk *walk,
 			    struct mm_struct **iter)
 {
@@ -2891,7 +2916,7 @@ static bool iterate_mm_list(struct lruvec *lruvec, struct lru_gen_mm_walk *walk,
 	struct mm_struct *mm = NULL;
 	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
 	struct lru_gen_mm_list *mm_list = get_mm_list(memcg);
-	struct lru_gen_mm_state *mm_state = &lruvec->mm_state;
+	struct lru_gen_mm_state *mm_state = get_mm_state(lruvec);
 
 	/*
 	 * mm_state->seq is incremented after each iteration of mm_list. There
@@ -2929,11 +2954,7 @@ static bool iterate_mm_list(struct lruvec *lruvec, struct lru_gen_mm_walk *walk,
 			mm_state->tail = mm_state->head->next;
 			walk->force_scan = true;
 		}
-
-		mm = list_entry(mm_state->head, struct mm_struct, lru_gen.list);
-		if (should_skip_mm(mm, walk))
-			mm = NULL;
-	} while (!mm);
+	} while (!(mm = get_next_mm(walk)));
 done:
 	if (*iter || last)
 		reset_mm_stats(lruvec, walk, last);
@@ -2941,7 +2962,7 @@ done:
 	spin_unlock(&mm_list->lock);
 
 	if (mm && first)
-		reset_bloom_filter(lruvec, walk->max_seq + 1);
+		reset_bloom_filter(mm_state, walk->max_seq + 1);
 
 	if (*iter)
 		mmput_async(*iter);
@@ -2956,7 +2977,7 @@ static bool iterate_mm_list_nowalk(struct lruvec *lruvec, unsigned long max_seq)
 	bool success = false;
 	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
 	struct lru_gen_mm_list *mm_list = get_mm_list(memcg);
-	struct lru_gen_mm_state *mm_state = &lruvec->mm_state;
+	struct lru_gen_mm_state *mm_state = get_mm_state(lruvec);
 
 	spin_lock(&mm_list->lock);
 
@@ -3469,6 +3490,7 @@ static void walk_pmd_range(pud_t *pud, unsigned long start, unsigned long end,
 	DECLARE_BITMAP(bitmap, MIN_LRU_BATCH);
 	unsigned long first = -1;
 	struct lru_gen_mm_walk *walk = args->private;
+	struct lru_gen_mm_state *mm_state = get_mm_state(walk->lruvec);
 
 	VM_WARN_ON_ONCE(pud_leaf(*pud));
 
@@ -3520,7 +3542,7 @@ restart:
 			walk_pmd_range_locked(pud, addr, vma, args, bitmap, &first);
 		}
 
-		if (!walk->force_scan && !test_bloom_filter(walk->lruvec, walk->max_seq, pmd + i))
+		if (!walk->force_scan && !test_bloom_filter(mm_state, walk->max_seq, pmd + i))
 			continue;
 
 		walk->mm_stats[MM_NONLEAF_FOUND]++;
@@ -3531,7 +3553,7 @@ restart:
 		walk->mm_stats[MM_NONLEAF_ADDED]++;
 
 		/* carry over to the next generation */
-		update_bloom_filter(walk->lruvec, walk->max_seq + 1, pmd + i);
+		update_bloom_filter(mm_state, walk->max_seq + 1, pmd + i);
 	}
 
 	walk_pmd_range_locked(pud, -1, vma, args, bitmap, &first);
@@ -3738,16 +3760,25 @@ next:
 	return success;
 }
 
-static void inc_max_seq(struct lruvec *lruvec, bool can_swap, bool force_scan)
+static bool inc_max_seq(struct lruvec *lruvec, unsigned long max_seq,
+			bool can_swap, bool force_scan)
 {
+	bool success;
 	int prev, next;
 	int type, zone;
 	struct lru_gen_folio *lrugen = &lruvec->lrugen;
 restart:
+	if (max_seq < READ_ONCE(lrugen->max_seq))
+		return false;
+
 	spin_lock_irq(&lruvec->lru_lock);
 
 	VM_WARN_ON_ONCE(!seq_is_valid(lruvec));
 
+	success = max_seq == lrugen->max_seq;
+	if (!success)
+		goto unlock;
+
 	for (type = ANON_AND_FILE - 1; type >= 0; type--) {
 		if (get_nr_gens(lruvec, type) != MAX_NR_GENS)
 			continue;
@@ -3791,8 +3822,10 @@ restart:
 	WRITE_ONCE(lrugen->timestamps[next], jiffies);
 	/* make sure preceding modifications appear */
 	smp_store_release(&lrugen->max_seq, lrugen->max_seq + 1);
-
+unlock:
 	spin_unlock_irq(&lruvec->lru_lock);
+
+	return success;
 }
 
 static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long max_seq,
@@ -3802,14 +3835,16 @@ static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long max_seq,
 	struct lru_gen_mm_walk *walk;
 	struct mm_struct *mm = NULL;
 	struct lru_gen_folio *lrugen = &lruvec->lrugen;
+	struct lru_gen_mm_state *mm_state = get_mm_state(lruvec);
 
 	VM_WARN_ON_ONCE(max_seq > READ_ONCE(lrugen->max_seq));
 
+	if (!mm_state)
+		return inc_max_seq(lruvec, max_seq, can_swap, force_scan);
+
 	/* see the comment in iterate_mm_list() */
-	if (max_seq <= READ_ONCE(lruvec->mm_state.seq)) {
-		success = false;
-		goto done;
-	}
+	if (max_seq <= READ_ONCE(mm_state->seq))
+		return false;
 
 	/*
 	 * If the hardware doesn't automatically set the accessed bit, fallback
@@ -3839,8 +3874,10 @@ static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long max_seq,
 			walk_mm(lruvec, mm, walk);
 	} while (mm);
 done:
-	if (success)
-		inc_max_seq(lruvec, can_swap, force_scan);
+	if (success) {
+		success = inc_max_seq(lruvec, max_seq, can_swap, force_scan);
+		WARN_ON_ONCE(!success);
+	}
 
 	return success;
 }
@@ -3964,6 +4001,7 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 	struct mem_cgroup *memcg = folio_memcg(folio);
 	struct pglist_data *pgdat = folio_pgdat(folio);
 	struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
+	struct lru_gen_mm_state *mm_state = get_mm_state(lruvec);
 	DEFINE_MAX_SEQ(lruvec);
 	int old_gen, new_gen = lru_gen_from_seq(max_seq);
 
@@ -4042,8 +4080,8 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 	mem_cgroup_unlock_pages();
 
 	/* feedback from rmap walkers to page table walkers */
-	if (suitable_to_scan(i, young))
-		update_bloom_filter(lruvec, max_seq, pvmw->pmd);
+	if (mm_state && suitable_to_scan(i, young))
+		update_bloom_filter(mm_state, max_seq, pvmw->pmd);
 }
 
 /******************************************************************************
@@ -5219,6 +5257,7 @@ static void lru_gen_seq_show_full(struct seq_file *m, struct lruvec *lruvec,
 	int type, tier;
 	int hist = lru_hist_from_seq(seq);
 	struct lru_gen_folio *lrugen = &lruvec->lrugen;
+	struct lru_gen_mm_state *mm_state = get_mm_state(lruvec);
 
 	for (tier = 0; tier < MAX_NR_TIERS; tier++) {
 		seq_printf(m, "            %10d", tier);
@@ -5244,6 +5283,9 @@ static void lru_gen_seq_show_full(struct seq_file *m, struct lruvec *lruvec,
 		seq_putc(m, '\n');
 	}
 
+	if (!mm_state)
+		return;
+
 	seq_puts(m, "                      ");
 	for (i = 0; i < NR_MM_STATS; i++) {
 		const char *s = "      ";
@@ -5251,10 +5293,10 @@ static void lru_gen_seq_show_full(struct seq_file *m, struct lruvec *lruvec,
 
 		if (seq == max_seq && NR_HIST_GENS == 1) {
 			s = "LOYNFA";
-			n = READ_ONCE(lruvec->mm_state.stats[hist][i]);
+			n = READ_ONCE(mm_state->stats[hist][i]);
 		} else if (seq != max_seq && NR_HIST_GENS > 1) {
 			s = "loynfa";
-			n = READ_ONCE(lruvec->mm_state.stats[hist][i]);
+			n = READ_ONCE(mm_state->stats[hist][i]);
 		}
 
 		seq_printf(m, " %10lu%c", n, s[i]);
@@ -5523,6 +5565,7 @@ void lru_gen_init_lruvec(struct lruvec *lruvec)
 	int i;
 	int gen, type, zone;
 	struct lru_gen_folio *lrugen = &lruvec->lrugen;
+	struct lru_gen_mm_state *mm_state = get_mm_state(lruvec);
 
 	lrugen->max_seq = MIN_NR_GENS + 1;
 	lrugen->enabled = lru_gen_enabled();
@@ -5533,7 +5576,8 @@ void lru_gen_init_lruvec(struct lruvec *lruvec)
 	for_each_gen_type_zone(gen, type, zone)
 		INIT_LIST_HEAD(&lrugen->folios[gen][type][zone]);
 
-	lruvec->mm_state.seq = MIN_NR_GENS;
+	if (mm_state)
+		mm_state->seq = MIN_NR_GENS;
 }
 
 #ifdef CONFIG_MEMCG
@@ -5552,28 +5596,38 @@ void lru_gen_init_pgdat(struct pglist_data *pgdat)
 
 void lru_gen_init_memcg(struct mem_cgroup *memcg)
 {
-	INIT_LIST_HEAD(&memcg->mm_list.fifo);
-	spin_lock_init(&memcg->mm_list.lock);
+	struct lru_gen_mm_list *mm_list = get_mm_list(memcg);
+
+	if (!mm_list)
+		return;
+
+	INIT_LIST_HEAD(&mm_list->fifo);
+	spin_lock_init(&mm_list->lock);
 }
 
 void lru_gen_exit_memcg(struct mem_cgroup *memcg)
 {
 	int i;
 	int nid;
+	struct lru_gen_mm_list *mm_list = get_mm_list(memcg);
 
-	VM_WARN_ON_ONCE(!list_empty(&memcg->mm_list.fifo));
+	VM_WARN_ON_ONCE(mm_list && !list_empty(&mm_list->fifo));
 
 	for_each_node(nid) {
 		struct lruvec *lruvec = get_lruvec(memcg, nid);
+		struct lru_gen_mm_state *mm_state = get_mm_state(lruvec);
 
 		VM_WARN_ON_ONCE(memchr_inv(lruvec->lrugen.nr_pages, 0,
 					   sizeof(lruvec->lrugen.nr_pages)));
 
 		lruvec->lrugen.list.next = LIST_POISON1;
 
+		if (!mm_state)
+			continue;
+
 		for (i = 0; i < NR_BLOOM_FILTERS; i++) {
-			bitmap_free(lruvec->mm_state.filters[i]);
-			lruvec->mm_state.filters[i] = NULL;
+			bitmap_free(mm_state->filters[i]);
+			mm_state->filters[i] = NULL;
 		}
 	}
 }
-- 
cgit v1.2.3


From 745b13e647cd119e70d16b57698e12b7c86ca264 Mon Sep 17 00:00:00 2001
From: Kinsey Ho <kinseyho@google.com>
Date: Wed, 27 Dec 2023 14:12:03 +0000
Subject: mm/mglru: remove CONFIG_MEMCG

Remove CONFIG_MEMCG in a refactoring to improve code readability at
the cost of a few bytes in struct lru_gen_folio per node when
CONFIG_MEMCG=n.

Link: https://lkml.kernel.org/r/20231227141205.2200125-4-kinseyho@google.com
Signed-off-by: Kinsey Ho <kinseyho@google.com>
Co-developed-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Tested-by: Donet Tom <donettom@linux.vnet.ibm.com>
Acked-by: Yu Zhao <yuzhao@google.com>
Cc: kernel test robot <lkp@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mm_types.h |  4 ---
 include/linux/mmzone.h   | 26 ++-----------------
 mm/vmscan.c              | 67 +++++++++++++++---------------------------------
 3 files changed, 23 insertions(+), 74 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 552fa2d11c57..55b7121809ff 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -1017,9 +1017,7 @@ struct lru_gen_mm_list {
 
 void lru_gen_add_mm(struct mm_struct *mm);
 void lru_gen_del_mm(struct mm_struct *mm);
-#ifdef CONFIG_MEMCG
 void lru_gen_migrate_mm(struct mm_struct *mm);
-#endif
 
 static inline void lru_gen_init_mm(struct mm_struct *mm)
 {
@@ -1050,11 +1048,9 @@ static inline void lru_gen_del_mm(struct mm_struct *mm)
 {
 }
 
-#ifdef CONFIG_MEMCG
 static inline void lru_gen_migrate_mm(struct mm_struct *mm)
 {
 }
-#endif
 
 static inline void lru_gen_init_mm(struct mm_struct *mm)
 {
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index bc3f63ec4291..28665e1b8475 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -440,14 +440,12 @@ struct lru_gen_folio {
 	atomic_long_t refaulted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS];
 	/* whether the multi-gen LRU is enabled */
 	bool enabled;
-#ifdef CONFIG_MEMCG
 	/* the memcg generation this lru_gen_folio belongs to */
 	u8 gen;
 	/* the list segment this lru_gen_folio belongs to */
 	u8 seg;
 	/* per-node lru_gen_folio list for global reclaim */
 	struct hlist_nulls_node list;
-#endif
 };
 
 enum {
@@ -493,11 +491,6 @@ struct lru_gen_mm_walk {
 	bool force_scan;
 };
 
-void lru_gen_init_lruvec(struct lruvec *lruvec);
-void lru_gen_look_around(struct page_vma_mapped_walk *pvmw);
-
-#ifdef CONFIG_MEMCG
-
 /*
  * For each node, memcgs are divided into two generations: the old and the
  * young. For each generation, memcgs are randomly sharded into multiple bins
@@ -555,6 +548,8 @@ struct lru_gen_memcg {
 };
 
 void lru_gen_init_pgdat(struct pglist_data *pgdat);
+void lru_gen_init_lruvec(struct lruvec *lruvec);
+void lru_gen_look_around(struct page_vma_mapped_walk *pvmw);
 
 void lru_gen_init_memcg(struct mem_cgroup *memcg);
 void lru_gen_exit_memcg(struct mem_cgroup *memcg);
@@ -563,19 +558,6 @@ void lru_gen_offline_memcg(struct mem_cgroup *memcg);
 void lru_gen_release_memcg(struct mem_cgroup *memcg);
 void lru_gen_soft_reclaim(struct mem_cgroup *memcg, int nid);
 
-#else /* !CONFIG_MEMCG */
-
-#define MEMCG_NR_GENS	1
-
-struct lru_gen_memcg {
-};
-
-static inline void lru_gen_init_pgdat(struct pglist_data *pgdat)
-{
-}
-
-#endif /* CONFIG_MEMCG */
-
 #else /* !CONFIG_LRU_GEN */
 
 static inline void lru_gen_init_pgdat(struct pglist_data *pgdat)
@@ -590,8 +572,6 @@ static inline void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 {
 }
 
-#ifdef CONFIG_MEMCG
-
 static inline void lru_gen_init_memcg(struct mem_cgroup *memcg)
 {
 }
@@ -616,8 +596,6 @@ static inline void lru_gen_soft_reclaim(struct mem_cgroup *memcg, int nid)
 {
 }
 
-#endif /* CONFIG_MEMCG */
-
 #endif /* CONFIG_LRU_GEN */
 
 struct lruvec {
diff --git a/mm/vmscan.c b/mm/vmscan.c
index aa7ea09ffb4c..351a0b5043c0 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4097,13 +4097,6 @@ enum {
 	MEMCG_LRU_YOUNG,
 };
 
-#ifdef CONFIG_MEMCG
-
-static int lru_gen_memcg_seg(struct lruvec *lruvec)
-{
-	return READ_ONCE(lruvec->lrugen.seg);
-}
-
 static void lru_gen_rotate_memcg(struct lruvec *lruvec, int op)
 {
 	int seg;
@@ -4150,6 +4143,8 @@ static void lru_gen_rotate_memcg(struct lruvec *lruvec, int op)
 	spin_unlock_irqrestore(&pgdat->memcg_lru.lock, flags);
 }
 
+#ifdef CONFIG_MEMCG
+
 void lru_gen_online_memcg(struct mem_cgroup *memcg)
 {
 	int gen;
@@ -4217,18 +4212,11 @@ void lru_gen_soft_reclaim(struct mem_cgroup *memcg, int nid)
 	struct lruvec *lruvec = get_lruvec(memcg, nid);
 
 	/* see the comment on MEMCG_NR_GENS */
-	if (lru_gen_memcg_seg(lruvec) != MEMCG_LRU_HEAD)
+	if (READ_ONCE(lruvec->lrugen.seg) != MEMCG_LRU_HEAD)
 		lru_gen_rotate_memcg(lruvec, MEMCG_LRU_HEAD);
 }
 
-#else /* !CONFIG_MEMCG */
-
-static int lru_gen_memcg_seg(struct lruvec *lruvec)
-{
-	return 0;
-}
-
-#endif
+#endif /* CONFIG_MEMCG */
 
 /******************************************************************************
  *                          the eviction
@@ -4776,7 +4764,7 @@ static int shrink_one(struct lruvec *lruvec, struct scan_control *sc)
 
 	if (mem_cgroup_below_low(NULL, memcg)) {
 		/* see the comment on MEMCG_NR_GENS */
-		if (lru_gen_memcg_seg(lruvec) != MEMCG_LRU_TAIL)
+		if (READ_ONCE(lruvec->lrugen.seg) != MEMCG_LRU_TAIL)
 			return MEMCG_LRU_TAIL;
 
 		memcg_memory_event(memcg, MEMCG_LOW);
@@ -4799,12 +4787,10 @@ static int shrink_one(struct lruvec *lruvec, struct scan_control *sc)
 		return 0;
 
 	/* one retry if offlined or too small */
-	return lru_gen_memcg_seg(lruvec) != MEMCG_LRU_TAIL ?
+	return READ_ONCE(lruvec->lrugen.seg) != MEMCG_LRU_TAIL ?
 	       MEMCG_LRU_TAIL : MEMCG_LRU_YOUNG;
 }
 
-#ifdef CONFIG_MEMCG
-
 static void shrink_many(struct pglist_data *pgdat, struct scan_control *sc)
 {
 	int op;
@@ -4896,20 +4882,6 @@ static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc
 	blk_finish_plug(&plug);
 }
 
-#else /* !CONFIG_MEMCG */
-
-static void shrink_many(struct pglist_data *pgdat, struct scan_control *sc)
-{
-	BUILD_BUG();
-}
-
-static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
-{
-	BUILD_BUG();
-}
-
-#endif
-
 static void set_initial_priority(struct pglist_data *pgdat, struct scan_control *sc)
 {
 	int priority;
@@ -5560,6 +5532,18 @@ static const struct file_operations lru_gen_ro_fops = {
  *                          initialization
  ******************************************************************************/
 
+void lru_gen_init_pgdat(struct pglist_data *pgdat)
+{
+	int i, j;
+
+	spin_lock_init(&pgdat->memcg_lru.lock);
+
+	for (i = 0; i < MEMCG_NR_GENS; i++) {
+		for (j = 0; j < MEMCG_NR_BINS; j++)
+			INIT_HLIST_NULLS_HEAD(&pgdat->memcg_lru.fifo[i][j], i);
+	}
+}
+
 void lru_gen_init_lruvec(struct lruvec *lruvec)
 {
 	int i;
@@ -5582,18 +5566,6 @@ void lru_gen_init_lruvec(struct lruvec *lruvec)
 
 #ifdef CONFIG_MEMCG
 
-void lru_gen_init_pgdat(struct pglist_data *pgdat)
-{
-	int i, j;
-
-	spin_lock_init(&pgdat->memcg_lru.lock);
-
-	for (i = 0; i < MEMCG_NR_GENS; i++) {
-		for (j = 0; j < MEMCG_NR_BINS; j++)
-			INIT_HLIST_NULLS_HEAD(&pgdat->memcg_lru.fifo[i][j], i);
-	}
-}
-
 void lru_gen_init_memcg(struct mem_cgroup *memcg)
 {
 	struct lru_gen_mm_list *mm_list = get_mm_list(memcg);
@@ -5653,14 +5625,17 @@ late_initcall(init_lru_gen);
 
 static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
 {
+	BUILD_BUG();
 }
 
 static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 {
+	BUILD_BUG();
 }
 
 static void lru_gen_shrink_node(struct pglist_data *pgdat, struct scan_control *sc)
 {
+	BUILD_BUG();
 }
 
 #endif /* CONFIG_LRU_GEN */
-- 
cgit v1.2.3


From 533c67e6358406727145efae32882c4dc355d6c5 Mon Sep 17 00:00:00 2001
From: Kinsey Ho <kinseyho@google.com>
Date: Wed, 27 Dec 2023 14:12:04 +0000
Subject: mm/mglru: add dummy pmd_dirty()

Add dummy pmd_dirty() for architectures that don't provide it.
This is similar to commit 6617da8fb565 ("mm: add dummy pmd_young()
for architectures not having it").

Link: https://lkml.kernel.org/r/20231227141205.2200125-5-kinseyho@google.com
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202312210606.1Etqz3M4-lkp@intel.com/
Closes: https://lore.kernel.org/oe-kbuild-all/202312210042.xQEiqlEh-lkp@intel.com/
Signed-off-by: Kinsey Ho <kinseyho@google.com>
Suggested-by: Yu Zhao <yuzhao@google.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Donet Tom <donettom@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/loongarch/include/asm/pgtable.h | 1 +
 arch/mips/include/asm/pgtable.h      | 1 +
 arch/riscv/include/asm/pgtable.h     | 1 +
 arch/s390/include/asm/pgtable.h      | 1 +
 arch/sparc/include/asm/pgtable_64.h  | 1 +
 arch/x86/include/asm/pgtable.h       | 1 +
 include/linux/pgtable.h              | 7 +++++++
 7 files changed, 13 insertions(+)

(limited to 'include')

diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h
index 29d9b12298bc..8b5df1bbf9e9 100644
--- a/arch/loongarch/include/asm/pgtable.h
+++ b/arch/loongarch/include/asm/pgtable.h
@@ -523,6 +523,7 @@ static inline pmd_t pmd_wrprotect(pmd_t pmd)
 	return pmd;
 }
 
+#define pmd_dirty pmd_dirty
 static inline int pmd_dirty(pmd_t pmd)
 {
 	return !!(pmd_val(pmd) & (_PAGE_DIRTY | _PAGE_MODIFIED));
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index 430b208c0130..e27a4c83c548 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -655,6 +655,7 @@ static inline pmd_t pmd_mkwrite_novma(pmd_t pmd)
 	return pmd;
 }
 
+#define pmd_dirty pmd_dirty
 static inline int pmd_dirty(pmd_t pmd)
 {
 	return !!(pmd_val(pmd) & _PAGE_MODIFIED);
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index ab00235b018f..7b4287f36054 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -673,6 +673,7 @@ static inline int pmd_write(pmd_t pmd)
 	return pte_write(pmd_pte(pmd));
 }
 
+#define pmd_dirty pmd_dirty
 static inline int pmd_dirty(pmd_t pmd)
 {
 	return pte_dirty(pmd_pte(pmd));
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 601e87fa8a9a..1299b56e43f6 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -770,6 +770,7 @@ static inline int pud_write(pud_t pud)
 	return (pud_val(pud) & _REGION3_ENTRY_WRITE) != 0;
 }
 
+#define pmd_dirty pmd_dirty
 static inline int pmd_dirty(pmd_t pmd)
 {
 	return (pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY) != 0;
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 5e41033bf4ca..a8c871b7d786 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -706,6 +706,7 @@ static inline unsigned long pmd_write(pmd_t pmd)
 #define pud_write(pud)	pte_write(__pte(pud_val(pud)))
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define pmd_dirty pmd_dirty
 static inline unsigned long pmd_dirty(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 08b5cb22d9a6..9d077bca6a10 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -141,6 +141,7 @@ static inline int pte_young(pte_t pte)
 	return pte_flags(pte) & _PAGE_ACCESSED;
 }
 
+#define pmd_dirty pmd_dirty
 static inline bool pmd_dirty(pmd_t pmd)
 {
 	return pmd_flags(pmd) & _PAGE_DIRTY_BITS;
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 9ecc20fa6269..466cf477551a 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -184,6 +184,13 @@ static inline int pmd_young(pmd_t pmd)
 }
 #endif
 
+#ifndef pmd_dirty
+static inline int pmd_dirty(pmd_t pmd)
+{
+	return 0;
+}
+#endif
+
 /*
  * A facility to provide lazy MMU batching.  This allows PTE updates and
  * page invalidations to be delayed until a call to leave lazy MMU mode
-- 
cgit v1.2.3


From e435ca87882167dda78776ce4bd6eb2094eb864b Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 28 Dec 2023 08:57:43 +0000
Subject: mm: remove inc/dec lruvec page state functions

Patch series "Remove some lruvec page accounting functions", v2.

Some functions are now unused; remove them.  Make
__mod_lruvec_page_state() unused and then remove it.


This patch (of 6):

All callers of these have been converted to their folio equivalents.

Link: https://lkml.kernel.org/r/20231228085748.1083901-1-willy@infradead.org
Link: https://lkml.kernel.org/r/20231228085748.1083901-2-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/vmstat.h | 24 ------------------------
 1 file changed, 24 deletions(-)

(limited to 'include')

diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index fed855bae6d8..147ae73e0ee7 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -597,18 +597,6 @@ static inline void mod_lruvec_page_state(struct page *page,
 
 #endif /* CONFIG_MEMCG */
 
-static inline void __inc_lruvec_page_state(struct page *page,
-					   enum node_stat_item idx)
-{
-	__mod_lruvec_page_state(page, idx, 1);
-}
-
-static inline void __dec_lruvec_page_state(struct page *page,
-					   enum node_stat_item idx)
-{
-	__mod_lruvec_page_state(page, idx, -1);
-}
-
 static inline void __lruvec_stat_mod_folio(struct folio *folio,
 					   enum node_stat_item idx, int val)
 {
@@ -627,18 +615,6 @@ static inline void __lruvec_stat_sub_folio(struct folio *folio,
 	__lruvec_stat_mod_folio(folio, idx, -folio_nr_pages(folio));
 }
 
-static inline void inc_lruvec_page_state(struct page *page,
-					 enum node_stat_item idx)
-{
-	mod_lruvec_page_state(page, idx, 1);
-}
-
-static inline void dec_lruvec_page_state(struct page *page,
-					 enum node_stat_item idx)
-{
-	mod_lruvec_page_state(page, idx, -1);
-}
-
 static inline void lruvec_stat_mod_folio(struct folio *folio,
 					 enum node_stat_item idx, int val)
 {
-- 
cgit v1.2.3


From c701123bd68bf1cc3bc167b4f597cb1f4995c39c Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 28 Dec 2023 08:57:48 +0000
Subject: mm/memcontrol: remove __mod_lruvec_page_state()

There are no more callers of __mod_lruvec_page_state(), so convert the
implementation to __lruvec_stat_mod_folio(), removing two calls to
compound_head() (one explicit, one hidden inside page_memcg()).

Link: https://lkml.kernel.org/r/20231228085748.1083901-7-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Acked-by: Shakeel Butt <shakeelb@google.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/vmstat.h | 36 ++++++++++++++++++------------------
 mm/memcontrol.c        |  9 ++++-----
 2 files changed, 22 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 147ae73e0ee7..343906a98d6e 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -556,19 +556,25 @@ static inline void mod_lruvec_state(struct lruvec *lruvec,
 	local_irq_restore(flags);
 }
 
-void __mod_lruvec_page_state(struct page *page,
+void __lruvec_stat_mod_folio(struct folio *folio,
 			     enum node_stat_item idx, int val);
 
-static inline void mod_lruvec_page_state(struct page *page,
+static inline void lruvec_stat_mod_folio(struct folio *folio,
 					 enum node_stat_item idx, int val)
 {
 	unsigned long flags;
 
 	local_irq_save(flags);
-	__mod_lruvec_page_state(page, idx, val);
+	__lruvec_stat_mod_folio(folio, idx, val);
 	local_irq_restore(flags);
 }
 
+static inline void mod_lruvec_page_state(struct page *page,
+					 enum node_stat_item idx, int val)
+{
+	lruvec_stat_mod_folio(page_folio(page), idx, val);
+}
+
 #else
 
 static inline void __mod_lruvec_state(struct lruvec *lruvec,
@@ -583,10 +589,16 @@ static inline void mod_lruvec_state(struct lruvec *lruvec,
 	mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
 }
 
-static inline void __mod_lruvec_page_state(struct page *page,
-					   enum node_stat_item idx, int val)
+static inline void __lruvec_stat_mod_folio(struct folio *folio,
+					 enum node_stat_item idx, int val)
 {
-	__mod_node_page_state(page_pgdat(page), idx, val);
+	__mod_node_page_state(folio_pgdat(folio), idx, val);
+}
+
+static inline void lruvec_stat_mod_folio(struct folio *folio,
+					 enum node_stat_item idx, int val)
+{
+	mod_node_page_state(folio_pgdat(folio), idx, val);
 }
 
 static inline void mod_lruvec_page_state(struct page *page,
@@ -597,12 +609,6 @@ static inline void mod_lruvec_page_state(struct page *page,
 
 #endif /* CONFIG_MEMCG */
 
-static inline void __lruvec_stat_mod_folio(struct folio *folio,
-					   enum node_stat_item idx, int val)
-{
-	__mod_lruvec_page_state(&folio->page, idx, val);
-}
-
 static inline void __lruvec_stat_add_folio(struct folio *folio,
 					   enum node_stat_item idx)
 {
@@ -615,12 +621,6 @@ static inline void __lruvec_stat_sub_folio(struct folio *folio,
 	__lruvec_stat_mod_folio(folio, idx, -folio_nr_pages(folio));
 }
 
-static inline void lruvec_stat_mod_folio(struct folio *folio,
-					 enum node_stat_item idx, int val)
-{
-	mod_lruvec_page_state(&folio->page, idx, val);
-}
-
 static inline void lruvec_stat_add_folio(struct folio *folio,
 					 enum node_stat_item idx)
 {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 3ca691fb5b49..0082cef6e1fd 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -890,16 +890,15 @@ void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 		__mod_memcg_lruvec_state(lruvec, idx, val);
 }
 
-void __mod_lruvec_page_state(struct page *page, enum node_stat_item idx,
+void __lruvec_stat_mod_folio(struct folio *folio, enum node_stat_item idx,
 			     int val)
 {
-	struct page *head = compound_head(page); /* rmap on tail pages */
 	struct mem_cgroup *memcg;
-	pg_data_t *pgdat = page_pgdat(page);
+	pg_data_t *pgdat = folio_pgdat(folio);
 	struct lruvec *lruvec;
 
 	rcu_read_lock();
-	memcg = page_memcg(head);
+	memcg = folio_memcg(folio);
 	/* Untracked pages have no memcg, no lruvec. Update only the node */
 	if (!memcg) {
 		rcu_read_unlock();
@@ -911,7 +910,7 @@ void __mod_lruvec_page_state(struct page *page, enum node_stat_item idx,
 	__mod_lruvec_state(lruvec, idx, val);
 	rcu_read_unlock();
 }
-EXPORT_SYMBOL(__mod_lruvec_page_state);
+EXPORT_SYMBOL(__lruvec_stat_mod_folio);
 
 void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val)
 {
-- 
cgit v1.2.3


From b805ab3c6935d14654ccc28f16ffce7a13c2c528 Mon Sep 17 00:00:00 2001
From: Li Zhijian <lizhijian@fujitsu.com>
Date: Fri, 29 Dec 2023 10:26:51 +0800
Subject: mm/vmstat: move pgdemote_* out of CONFIG_NUMA_BALANCING

Demotion can work well without CONFIG_NUMA_BALANCING.  But the commit
23e9f0138963 ("mm/vmstat: move pgdemote_* to per-node stats") wrongly hid
it behind CONFIG_NUMA_BALANCING.

Fix it by moving them out of CONFIG_NUMA_BALANCING.

Link: https://lkml.kernel.org/r/20231229022651.3229174-1-lizhijian@fujitsu.com
Fixes: 23e9f0138963 ("mm/vmstat: move pgdemote_* to per-node stats")
Signed-off-by: Li Zhijian <lizhijian@fujitsu.com>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "Rafael J. Wysocki" <rafael@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mmzone.h | 2 +-
 mm/vmscan.c            | 5 +----
 mm/vmstat.c            | 2 +-
 3 files changed, 3 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 28665e1b8475..c18c53353b50 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -207,11 +207,11 @@ enum node_stat_item {
 #ifdef CONFIG_NUMA_BALANCING
 	PGPROMOTE_SUCCESS,	/* promote successfully */
 	PGPROMOTE_CANDIDATE,	/* candidate pages to promote */
+#endif
 	/* PGDEMOTE_*: pages demoted */
 	PGDEMOTE_KSWAPD,
 	PGDEMOTE_DIRECT,
 	PGDEMOTE_KHUGEPAGED,
-#endif
 	NR_VM_NODE_STAT_ITEMS
 };
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index ceba905e5630..600ed3cbf7cb 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -409,12 +409,10 @@ void drop_slab(void)
 
 static int reclaimer_offset(void)
 {
-#ifdef CONFIG_NUMA_BALANCING
 	BUILD_BUG_ON(PGSTEAL_DIRECT - PGSTEAL_KSWAPD !=
 			PGDEMOTE_DIRECT - PGDEMOTE_KSWAPD);
 	BUILD_BUG_ON(PGSTEAL_KHUGEPAGED - PGSTEAL_KSWAPD !=
 			PGDEMOTE_KHUGEPAGED - PGDEMOTE_KSWAPD);
-#endif
 	BUILD_BUG_ON(PGSTEAL_DIRECT - PGSTEAL_KSWAPD !=
 			PGSCAN_DIRECT - PGSCAN_KSWAPD);
 	BUILD_BUG_ON(PGSTEAL_KHUGEPAGED - PGSTEAL_KSWAPD !=
@@ -978,10 +976,9 @@ static unsigned int demote_folio_list(struct list_head *demote_folios,
 	migrate_pages(demote_folios, alloc_demote_folio, NULL,
 		      (unsigned long)&mtc, MIGRATE_ASYNC, MR_DEMOTION,
 		      &nr_succeeded);
-#ifdef CONFIG_NUMA_BALANCING
+
 	mod_node_page_state(pgdat, PGDEMOTE_KSWAPD + reclaimer_offset(),
 			    nr_succeeded);
-#endif
 
 	return nr_succeeded;
 }
diff --git a/mm/vmstat.c b/mm/vmstat.c
index cfd8d8256f8e..1437ca2f28c5 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1248,10 +1248,10 @@ const char * const vmstat_text[] = {
 #ifdef CONFIG_NUMA_BALANCING
 	"pgpromote_success",
 	"pgpromote_candidate",
+#endif
 	"pgdemote_kswapd",
 	"pgdemote_direct",
 	"pgdemote_khugepaged",
-#endif
 
 	/* enum writeback_stat_item counters */
 	"nr_dirty_threshold",
-- 
cgit v1.2.3


From d93cca2f3109f88c94a32d3322ec8b2854a9c339 Mon Sep 17 00:00:00 2001
From: David McKay <david.mckay@codasip.com>
Date: Thu, 4 Jan 2024 09:40:10 +0000
Subject: asm-generic: Fix 32 bit __generic_cmpxchg_local

Commit 656e9007ef58 ("asm-generic: avoid __generic_cmpxchg_local
warnings") introduced a typo that means the code is incorrect for 32 bit
values. It will work fine for postive numbers, but will fail for
negative numbers on a system where longs are 64 bit.

Fixes: 656e9007ef58 ("asm-generic: avoid __generic_cmpxchg_local warnings")
Signed-off-by: David McKay <david.mckay@codasip.com>
Signed-off-by: Stuart Menefy <stuart.menefy@codasip.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 include/asm-generic/cmpxchg-local.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/asm-generic/cmpxchg-local.h b/include/asm-generic/cmpxchg-local.h
index 3df9f59a544e..f27d66fdc00a 100644
--- a/include/asm-generic/cmpxchg-local.h
+++ b/include/asm-generic/cmpxchg-local.h
@@ -34,7 +34,7 @@ static inline unsigned long __generic_cmpxchg_local(volatile void *ptr,
 			*(u16 *)ptr = (new & 0xffffu);
 		break;
 	case 4: prev = *(u32 *)ptr;
-		if (prev == (old & 0xffffffffffu))
+		if (prev == (old & 0xffffffffu))
 			*(u32 *)ptr = (new & 0xffffffffu);
 		break;
 	case 8: prev = *(u64 *)ptr;
-- 
cgit v1.2.3


From 26a1a86dd093a10d0653429bf013dae6e95dccbf Mon Sep 17 00:00:00 2001
From: Ira Weiny <ira.weiny@intel.com>
Date: Wed, 20 Dec 2023 16:17:29 -0800
Subject: cxl/events: Promote CXL event structures to a core header

UEFI code can process CXL events through CPER records.  Those records
use almost the same format as the CXL events.

Lift the CXL event structures to a core header to be shared in later
patches.

[jic123: drop "CXL rev 3.0" mention]

Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Link: https://lore.kernel.org/r/20231220-cxl-cper-v5-2-1bb8a4ca2c7a@intel.com
[djbw: add F: entry to maintainers for include/linux/cxl-event.h]
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 MAINTAINERS               |  1 +
 drivers/cxl/cxlmem.h      | 90 +-------------------------------------------
 include/linux/cxl-event.h | 95 +++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 97 insertions(+), 89 deletions(-)
 create mode 100644 include/linux/cxl-event.h

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index 7cef2d2ef8d7..04f6c52d0a8f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5245,6 +5245,7 @@ M:	Dan Williams <dan.j.williams@intel.com>
 L:	linux-cxl@vger.kernel.org
 S:	Maintained
 F:	drivers/cxl/
+F:	include/linux/cxl-event.h
 F:	include/uapi/linux/cxl_mem.h
 F:	tools/testing/cxl/
 
diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h
index a2fcbca253f3..f0e7ebb84f02 100644
--- a/drivers/cxl/cxlmem.h
+++ b/drivers/cxl/cxlmem.h
@@ -6,6 +6,7 @@
 #include <linux/cdev.h>
 #include <linux/uuid.h>
 #include <linux/rcuwait.h>
+#include <linux/cxl-event.h>
 #include "cxl.h"
 
 /* CXL 2.0 8.2.8.5.1.1 Memory Device Status Register */
@@ -579,27 +580,6 @@ struct cxl_mbox_identify {
 	u8 qos_telemetry_caps;
 } __packed;
 
-/*
- * Common Event Record Format
- * CXL rev 3.0 section 8.2.9.2.1; Table 8-42
- */
-struct cxl_event_record_hdr {
-	uuid_t id;
-	u8 length;
-	u8 flags[3];
-	__le16 handle;
-	__le16 related_handle;
-	__le64 timestamp;
-	u8 maint_op_class;
-	u8 reserved[15];
-} __packed;
-
-#define CXL_EVENT_RECORD_DATA_LENGTH 0x50
-struct cxl_event_record_raw {
-	struct cxl_event_record_hdr hdr;
-	u8 data[CXL_EVENT_RECORD_DATA_LENGTH];
-} __packed;
-
 /*
  * Get Event Records output payload
  * CXL rev 3.0 section 8.2.9.2.2; Table 8-50
@@ -641,74 +621,6 @@ struct cxl_mbox_clear_event_payload {
 } __packed;
 #define CXL_CLEAR_EVENT_MAX_HANDLES U8_MAX
 
-/*
- * General Media Event Record
- * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
- */
-#define CXL_EVENT_GEN_MED_COMP_ID_SIZE	0x10
-struct cxl_event_gen_media {
-	struct cxl_event_record_hdr hdr;
-	__le64 phys_addr;
-	u8 descriptor;
-	u8 type;
-	u8 transaction_type;
-	u8 validity_flags[2];
-	u8 channel;
-	u8 rank;
-	u8 device[3];
-	u8 component_id[CXL_EVENT_GEN_MED_COMP_ID_SIZE];
-	u8 reserved[46];
-} __packed;
-
-/*
- * DRAM Event Record - DER
- * CXL rev 3.0 section 8.2.9.2.1.2; Table 3-44
- */
-#define CXL_EVENT_DER_CORRECTION_MASK_SIZE	0x20
-struct cxl_event_dram {
-	struct cxl_event_record_hdr hdr;
-	__le64 phys_addr;
-	u8 descriptor;
-	u8 type;
-	u8 transaction_type;
-	u8 validity_flags[2];
-	u8 channel;
-	u8 rank;
-	u8 nibble_mask[3];
-	u8 bank_group;
-	u8 bank;
-	u8 row[3];
-	u8 column[2];
-	u8 correction_mask[CXL_EVENT_DER_CORRECTION_MASK_SIZE];
-	u8 reserved[0x17];
-} __packed;
-
-/*
- * Get Health Info Record
- * CXL rev 3.0 section 8.2.9.8.3.1; Table 8-100
- */
-struct cxl_get_health_info {
-	u8 health_status;
-	u8 media_status;
-	u8 add_status;
-	u8 life_used;
-	u8 device_temp[2];
-	u8 dirty_shutdown_cnt[4];
-	u8 cor_vol_err_cnt[4];
-	u8 cor_per_err_cnt[4];
-} __packed;
-
-/*
- * Memory Module Event Record
- * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45
- */
-struct cxl_event_mem_module {
-	struct cxl_event_record_hdr hdr;
-	u8 event_type;
-	struct cxl_get_health_info info;
-	u8 reserved[0x3d];
-} __packed;
-
 struct cxl_mbox_get_partition_info {
 	__le64 active_volatile_cap;
 	__le64 active_persistent_cap;
diff --git a/include/linux/cxl-event.h b/include/linux/cxl-event.h
new file mode 100644
index 000000000000..0fc068123f8e
--- /dev/null
+++ b/include/linux/cxl-event.h
@@ -0,0 +1,95 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2023 Intel Corporation. */
+#ifndef _LINUX_CXL_EVENT_H
+#define _LINUX_CXL_EVENT_H
+
+/*
+ * Common Event Record Format
+ * CXL rev 3.0 section 8.2.9.2.1; Table 8-42
+ */
+struct cxl_event_record_hdr {
+	uuid_t id;
+	u8 length;
+	u8 flags[3];
+	__le16 handle;
+	__le16 related_handle;
+	__le64 timestamp;
+	u8 maint_op_class;
+	u8 reserved[15];
+} __packed;
+
+#define CXL_EVENT_RECORD_DATA_LENGTH 0x50
+struct cxl_event_record_raw {
+	struct cxl_event_record_hdr hdr;
+	u8 data[CXL_EVENT_RECORD_DATA_LENGTH];
+} __packed;
+
+/*
+ * General Media Event Record
+ * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
+ */
+#define CXL_EVENT_GEN_MED_COMP_ID_SIZE	0x10
+struct cxl_event_gen_media {
+	struct cxl_event_record_hdr hdr;
+	__le64 phys_addr;
+	u8 descriptor;
+	u8 type;
+	u8 transaction_type;
+	u8 validity_flags[2];
+	u8 channel;
+	u8 rank;
+	u8 device[3];
+	u8 component_id[CXL_EVENT_GEN_MED_COMP_ID_SIZE];
+	u8 reserved[46];
+} __packed;
+
+/*
+ * DRAM Event Record - DER
+ * CXL rev 3.0 section 8.2.9.2.1.2; Table 3-44
+ */
+#define CXL_EVENT_DER_CORRECTION_MASK_SIZE	0x20
+struct cxl_event_dram {
+	struct cxl_event_record_hdr hdr;
+	__le64 phys_addr;
+	u8 descriptor;
+	u8 type;
+	u8 transaction_type;
+	u8 validity_flags[2];
+	u8 channel;
+	u8 rank;
+	u8 nibble_mask[3];
+	u8 bank_group;
+	u8 bank;
+	u8 row[3];
+	u8 column[2];
+	u8 correction_mask[CXL_EVENT_DER_CORRECTION_MASK_SIZE];
+	u8 reserved[0x17];
+} __packed;
+
+/*
+ * Get Health Info Record
+ * CXL rev 3.0 section 8.2.9.8.3.1; Table 8-100
+ */
+struct cxl_get_health_info {
+	u8 health_status;
+	u8 media_status;
+	u8 add_status;
+	u8 life_used;
+	u8 device_temp[2];
+	u8 dirty_shutdown_cnt[4];
+	u8 cor_vol_err_cnt[4];
+	u8 cor_per_err_cnt[4];
+} __packed;
+
+/*
+ * Memory Module Event Record
+ * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45
+ */
+struct cxl_event_mem_module {
+	struct cxl_event_record_hdr hdr;
+	u8 event_type;
+	struct cxl_get_health_info info;
+	u8 reserved[0x3d];
+} __packed;
+
+#endif /* _LINUX_CXL_EVENT_H */
-- 
cgit v1.2.3


From 2307157c85096026043ba11f9ad8393c31515c45 Mon Sep 17 00:00:00 2001
From: Michael Margolin <mrgolin@amazon.com>
Date: Thu, 4 Jan 2024 09:51:55 +0000
Subject: RDMA/efa: Add EFA query MR support

Add EFA driver uapi definitions and register a new query MR method that
currently returns the physical interconnects the device is using to
reach the MR. Update admin definitions and efa-abi accordingly.

Reviewed-by: Anas Mousa <anasmous@amazon.com>
Reviewed-by: Firas Jahjah <firasj@amazon.com>
Signed-off-by: Michael Margolin <mrgolin@amazon.com>
Link: https://lore.kernel.org/r/20240104095155.10676-1-mrgolin@amazon.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/efa/efa.h                 | 12 ++++-
 drivers/infiniband/hw/efa/efa_admin_cmds_defs.h | 33 +++++++++++-
 drivers/infiniband/hw/efa/efa_com_cmd.c         | 11 +++-
 drivers/infiniband/hw/efa/efa_com_cmd.h         | 12 ++++-
 drivers/infiniband/hw/efa/efa_main.c            |  7 ++-
 drivers/infiniband/hw/efa/efa_verbs.c           | 71 ++++++++++++++++++++++++-
 include/uapi/rdma/efa-abi.h                     | 21 +++++++-
 7 files changed, 160 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/efa/efa.h b/drivers/infiniband/hw/efa/efa.h
index 7352a1f5d811..e2bdec32ae80 100644
--- a/drivers/infiniband/hw/efa/efa.h
+++ b/drivers/infiniband/hw/efa/efa.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause */
 /*
- * Copyright 2018-2021 Amazon.com, Inc. or its affiliates. All rights reserved.
+ * Copyright 2018-2024 Amazon.com, Inc. or its affiliates. All rights reserved.
  */
 
 #ifndef _EFA_H_
@@ -80,9 +80,19 @@ struct efa_pd {
 	u16 pdn;
 };
 
+struct efa_mr_interconnect_info {
+	u16 recv_ic_id;
+	u16 rdma_read_ic_id;
+	u16 rdma_recv_ic_id;
+	u8 recv_ic_id_valid : 1;
+	u8 rdma_read_ic_id_valid : 1;
+	u8 rdma_recv_ic_id_valid : 1;
+};
+
 struct efa_mr {
 	struct ib_mr ibmr;
 	struct ib_umem *umem;
+	struct efa_mr_interconnect_info ic_info;
 };
 
 struct efa_cq {
diff --git a/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h b/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h
index 9c65bd27bae0..7377c8a9f4d5 100644
--- a/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h
+++ b/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause */
 /*
- * Copyright 2018-2023 Amazon.com, Inc. or its affiliates. All rights reserved.
+ * Copyright 2018-2024 Amazon.com, Inc. or its affiliates. All rights reserved.
  */
 
 #ifndef _EFA_ADMIN_CMDS_H_
@@ -415,6 +415,32 @@ struct efa_admin_reg_mr_resp {
 	 * memory region
 	 */
 	u32 r_key;
+
+	/*
+	 * Mask indicating which fields have valid values
+	 * 0 : recv_ic_id
+	 * 1 : rdma_read_ic_id
+	 * 2 : rdma_recv_ic_id
+	 */
+	u8 validity;
+
+	/*
+	 * Physical interconnect used by the device to reach the MR for receive
+	 * operation
+	 */
+	u8 recv_ic_id;
+
+	/*
+	 * Physical interconnect used by the device to reach the MR for RDMA
+	 * read operation
+	 */
+	u8 rdma_read_ic_id;
+
+	/*
+	 * Physical interconnect used by the device to reach the MR for RDMA
+	 * write receive
+	 */
+	u8 rdma_recv_ic_id;
 };
 
 struct efa_admin_dereg_mr_cmd {
@@ -999,6 +1025,11 @@ struct efa_admin_host_info {
 #define EFA_ADMIN_REG_MR_CMD_REMOTE_WRITE_ENABLE_MASK       BIT(1)
 #define EFA_ADMIN_REG_MR_CMD_REMOTE_READ_ENABLE_MASK        BIT(2)
 
+/* reg_mr_resp */
+#define EFA_ADMIN_REG_MR_RESP_RECV_IC_ID_MASK               BIT(0)
+#define EFA_ADMIN_REG_MR_RESP_RDMA_READ_IC_ID_MASK          BIT(1)
+#define EFA_ADMIN_REG_MR_RESP_RDMA_RECV_IC_ID_MASK          BIT(2)
+
 /* create_cq_cmd */
 #define EFA_ADMIN_CREATE_CQ_CMD_INTERRUPT_MODE_ENABLED_MASK BIT(5)
 #define EFA_ADMIN_CREATE_CQ_CMD_VIRT_MASK                   BIT(6)
diff --git a/drivers/infiniband/hw/efa/efa_com_cmd.c b/drivers/infiniband/hw/efa/efa_com_cmd.c
index 576811885d59..d3398c7b0bd0 100644
--- a/drivers/infiniband/hw/efa/efa_com_cmd.c
+++ b/drivers/infiniband/hw/efa/efa_com_cmd.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause
 /*
- * Copyright 2018-2023 Amazon.com, Inc. or its affiliates. All rights reserved.
+ * Copyright 2018-2024 Amazon.com, Inc. or its affiliates. All rights reserved.
  */
 
 #include "efa_com.h"
@@ -270,6 +270,15 @@ int efa_com_register_mr(struct efa_com_dev *edev,
 
 	result->l_key = cmd_completion.l_key;
 	result->r_key = cmd_completion.r_key;
+	result->ic_info.recv_ic_id = cmd_completion.recv_ic_id;
+	result->ic_info.rdma_read_ic_id = cmd_completion.rdma_read_ic_id;
+	result->ic_info.rdma_recv_ic_id = cmd_completion.rdma_recv_ic_id;
+	result->ic_info.recv_ic_id_valid = EFA_GET(&cmd_completion.validity,
+						   EFA_ADMIN_REG_MR_RESP_RECV_IC_ID);
+	result->ic_info.rdma_read_ic_id_valid = EFA_GET(&cmd_completion.validity,
+							EFA_ADMIN_REG_MR_RESP_RDMA_READ_IC_ID);
+	result->ic_info.rdma_recv_ic_id_valid = EFA_GET(&cmd_completion.validity,
+							EFA_ADMIN_REG_MR_RESP_RDMA_RECV_IC_ID);
 
 	return 0;
 }
diff --git a/drivers/infiniband/hw/efa/efa_com_cmd.h b/drivers/infiniband/hw/efa/efa_com_cmd.h
index fc97f37bb39b..720a99ba0f7d 100644
--- a/drivers/infiniband/hw/efa/efa_com_cmd.h
+++ b/drivers/infiniband/hw/efa/efa_com_cmd.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause */
 /*
- * Copyright 2018-2023 Amazon.com, Inc. or its affiliates. All rights reserved.
+ * Copyright 2018-2024 Amazon.com, Inc. or its affiliates. All rights reserved.
  */
 
 #ifndef _EFA_COM_CMD_H_
@@ -199,6 +199,15 @@ struct efa_com_reg_mr_params {
 	u8 indirect;
 };
 
+struct efa_com_mr_interconnect_info {
+	u16 recv_ic_id;
+	u16 rdma_read_ic_id;
+	u16 rdma_recv_ic_id;
+	u8 recv_ic_id_valid : 1;
+	u8 rdma_read_ic_id_valid : 1;
+	u8 rdma_recv_ic_id_valid : 1;
+};
+
 struct efa_com_reg_mr_result {
 	/*
 	 * To be used in conjunction with local buffers references in SQ and
@@ -210,6 +219,7 @@ struct efa_com_reg_mr_result {
 	 * accessed memory region
 	 */
 	u32 r_key;
+	struct efa_com_mr_interconnect_info ic_info;
 };
 
 struct efa_com_dereg_mr_params {
diff --git a/drivers/infiniband/hw/efa/efa_main.c b/drivers/infiniband/hw/efa/efa_main.c
index 15ee92081118..7b1910a86216 100644
--- a/drivers/infiniband/hw/efa/efa_main.c
+++ b/drivers/infiniband/hw/efa/efa_main.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause
 /*
- * Copyright 2018-2022 Amazon.com, Inc. or its affiliates. All rights reserved.
+ * Copyright 2018-2024 Amazon.com, Inc. or its affiliates. All rights reserved.
  */
 
 #include <linux/module.h>
@@ -9,6 +9,7 @@
 #include <linux/version.h>
 
 #include <rdma/ib_user_verbs.h>
+#include <rdma/uverbs_ioctl.h>
 
 #include "efa.h"
 
@@ -36,6 +37,8 @@ MODULE_DEVICE_TABLE(pci, efa_pci_tbl);
 	(BIT(EFA_ADMIN_FATAL_ERROR) | BIT(EFA_ADMIN_WARNING) | \
 	 BIT(EFA_ADMIN_NOTIFICATION) | BIT(EFA_ADMIN_KEEP_ALIVE))
 
+extern const struct uapi_definition efa_uapi_defs[];
+
 /* This handler will called for unknown event group or unimplemented handlers */
 static void unimplemented_aenq_handler(void *data,
 				       struct efa_admin_aenq_entry *aenq_e)
@@ -432,6 +435,8 @@ static int efa_ib_device_add(struct efa_dev *dev)
 
 	ib_set_device_ops(&dev->ibdev, &efa_dev_ops);
 
+	dev->ibdev.driver_def = efa_uapi_defs;
+
 	err = ib_register_device(&dev->ibdev, "efa_%d", &pdev->dev);
 	if (err)
 		goto err_destroy_eqs;
diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c
index 0f8ca99d0827..2f412db2edcd 100644
--- a/drivers/infiniband/hw/efa/efa_verbs.c
+++ b/drivers/infiniband/hw/efa/efa_verbs.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
 /*
- * Copyright 2018-2023 Amazon.com, Inc. or its affiliates. All rights reserved.
+ * Copyright 2018-2024 Amazon.com, Inc. or its affiliates. All rights reserved.
  */
 
 #include <linux/dma-buf.h>
@@ -13,6 +13,9 @@
 #include <rdma/ib_user_verbs.h>
 #include <rdma/ib_verbs.h>
 #include <rdma/uverbs_ioctl.h>
+#define UVERBS_MODULE_NAME efa_ib
+#include <rdma/uverbs_named_ioctl.h>
+#include <rdma/ib_user_ioctl_cmds.h>
 
 #include "efa.h"
 #include "efa_io_defs.h"
@@ -1653,6 +1656,12 @@ static int efa_register_mr(struct ib_pd *ibpd, struct efa_mr *mr, u64 start,
 	mr->ibmr.lkey = result.l_key;
 	mr->ibmr.rkey = result.r_key;
 	mr->ibmr.length = length;
+	mr->ic_info.recv_ic_id = result.ic_info.recv_ic_id;
+	mr->ic_info.rdma_read_ic_id = result.ic_info.rdma_read_ic_id;
+	mr->ic_info.rdma_recv_ic_id = result.ic_info.rdma_recv_ic_id;
+	mr->ic_info.recv_ic_id_valid = result.ic_info.recv_ic_id_valid;
+	mr->ic_info.rdma_read_ic_id_valid = result.ic_info.rdma_read_ic_id_valid;
+	mr->ic_info.rdma_recv_ic_id_valid = result.ic_info.rdma_recv_ic_id_valid;
 	ibdev_dbg(&dev->ibdev, "Registered mr[%d]\n", mr->ibmr.lkey);
 
 	return 0;
@@ -1735,6 +1744,39 @@ err_out:
 	return ERR_PTR(err);
 }
 
+static int UVERBS_HANDLER(EFA_IB_METHOD_MR_QUERY)(struct uverbs_attr_bundle *attrs)
+{
+	struct ib_mr *ibmr = uverbs_attr_get_obj(attrs, EFA_IB_ATTR_QUERY_MR_HANDLE);
+	struct efa_mr *mr = to_emr(ibmr);
+	u16 ic_id_validity = 0;
+	int ret;
+
+	ret = uverbs_copy_to(attrs, EFA_IB_ATTR_QUERY_MR_RESP_RECV_IC_ID,
+			     &mr->ic_info.recv_ic_id, sizeof(mr->ic_info.recv_ic_id));
+	if (ret)
+		return ret;
+
+	ret = uverbs_copy_to(attrs, EFA_IB_ATTR_QUERY_MR_RESP_RDMA_READ_IC_ID,
+			     &mr->ic_info.rdma_read_ic_id, sizeof(mr->ic_info.rdma_read_ic_id));
+	if (ret)
+		return ret;
+
+	ret = uverbs_copy_to(attrs, EFA_IB_ATTR_QUERY_MR_RESP_RDMA_RECV_IC_ID,
+			     &mr->ic_info.rdma_recv_ic_id, sizeof(mr->ic_info.rdma_recv_ic_id));
+	if (ret)
+		return ret;
+
+	if (mr->ic_info.recv_ic_id_valid)
+		ic_id_validity |= EFA_QUERY_MR_VALIDITY_RECV_IC_ID;
+	if (mr->ic_info.rdma_read_ic_id_valid)
+		ic_id_validity |= EFA_QUERY_MR_VALIDITY_RDMA_READ_IC_ID;
+	if (mr->ic_info.rdma_recv_ic_id_valid)
+		ic_id_validity |= EFA_QUERY_MR_VALIDITY_RDMA_RECV_IC_ID;
+
+	return uverbs_copy_to(attrs, EFA_IB_ATTR_QUERY_MR_RESP_IC_ID_VALIDITY,
+			      &ic_id_validity, sizeof(ic_id_validity));
+}
+
 int efa_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata)
 {
 	struct efa_dev *dev = to_edev(ibmr->device);
@@ -2157,3 +2199,30 @@ enum rdma_link_layer efa_port_link_layer(struct ib_device *ibdev,
 	return IB_LINK_LAYER_UNSPECIFIED;
 }
 
+DECLARE_UVERBS_NAMED_METHOD(EFA_IB_METHOD_MR_QUERY,
+			    UVERBS_ATTR_IDR(EFA_IB_ATTR_QUERY_MR_HANDLE,
+					    UVERBS_OBJECT_MR,
+					    UVERBS_ACCESS_READ,
+					    UA_MANDATORY),
+			    UVERBS_ATTR_PTR_OUT(EFA_IB_ATTR_QUERY_MR_RESP_IC_ID_VALIDITY,
+						UVERBS_ATTR_TYPE(u16),
+						UA_MANDATORY),
+			    UVERBS_ATTR_PTR_OUT(EFA_IB_ATTR_QUERY_MR_RESP_RECV_IC_ID,
+						UVERBS_ATTR_TYPE(u16),
+						UA_MANDATORY),
+			    UVERBS_ATTR_PTR_OUT(EFA_IB_ATTR_QUERY_MR_RESP_RDMA_READ_IC_ID,
+						UVERBS_ATTR_TYPE(u16),
+						UA_MANDATORY),
+			    UVERBS_ATTR_PTR_OUT(EFA_IB_ATTR_QUERY_MR_RESP_RDMA_RECV_IC_ID,
+						UVERBS_ATTR_TYPE(u16),
+						UA_MANDATORY));
+
+ADD_UVERBS_METHODS(efa_mr,
+		   UVERBS_OBJECT_MR,
+		   &UVERBS_METHOD(EFA_IB_METHOD_MR_QUERY));
+
+const struct uapi_definition efa_uapi_defs[] = {
+	UAPI_DEF_CHAIN_OBJ_TREE(UVERBS_OBJECT_MR,
+				&efa_mr),
+	{},
+};
diff --git a/include/uapi/rdma/efa-abi.h b/include/uapi/rdma/efa-abi.h
index d94c32f28804..701e2d567e41 100644
--- a/include/uapi/rdma/efa-abi.h
+++ b/include/uapi/rdma/efa-abi.h
@@ -1,12 +1,13 @@
 /* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */
 /*
- * Copyright 2018-2023 Amazon.com, Inc. or its affiliates. All rights reserved.
+ * Copyright 2018-2024 Amazon.com, Inc. or its affiliates. All rights reserved.
  */
 
 #ifndef EFA_ABI_USER_H
 #define EFA_ABI_USER_H
 
 #include <linux/types.h>
+#include <rdma/ib_user_ioctl_cmds.h>
 
 /*
  * Increment this value if any changes that break userspace ABI
@@ -134,4 +135,22 @@ struct efa_ibv_ex_query_device_resp {
 	__u32 device_caps;
 };
 
+enum {
+	EFA_QUERY_MR_VALIDITY_RECV_IC_ID = 1 << 0,
+	EFA_QUERY_MR_VALIDITY_RDMA_READ_IC_ID = 1 << 1,
+	EFA_QUERY_MR_VALIDITY_RDMA_RECV_IC_ID = 1 << 2,
+};
+
+enum efa_query_mr_attrs {
+	EFA_IB_ATTR_QUERY_MR_HANDLE = (1U << UVERBS_ID_NS_SHIFT),
+	EFA_IB_ATTR_QUERY_MR_RESP_IC_ID_VALIDITY,
+	EFA_IB_ATTR_QUERY_MR_RESP_RECV_IC_ID,
+	EFA_IB_ATTR_QUERY_MR_RESP_RDMA_READ_IC_ID,
+	EFA_IB_ATTR_QUERY_MR_RESP_RDMA_RECV_IC_ID,
+};
+
+enum efa_mr_methods {
+	EFA_IB_METHOD_MR_QUERY = (1U << UVERBS_ID_NS_SHIFT),
+};
+
 #endif /* EFA_ABI_USER_H */
-- 
cgit v1.2.3


From 405cd9fc6f44f7a54505019bea60de83f1c58365 Mon Sep 17 00:00:00 2001
From: Pedro Tammela <pctammela@mojatatu.com>
Date: Thu, 4 Jan 2024 21:38:10 -0300
Subject: net/sched: simplify tc_action_load_ops parameters

Instead of using two bools derived from a flags passed as arguments to
the parent function of tc_action_load_ops, just pass the flags itself
to tc_action_load_ops to simplify its parameters.

Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Pedro Tammela <pctammela@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/act_api.h |  3 +--
 net/sched/act_api.c   | 10 +++++-----
 net/sched/cls_api.c   |  5 ++---
 3 files changed, 8 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/net/act_api.h b/include/net/act_api.h
index 447985a45ef6..e1e5e72b901e 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -208,8 +208,7 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
 		    struct nlattr *est,
 		    struct tc_action *actions[], int init_res[], size_t *attr_size,
 		    u32 flags, u32 fl_flags, struct netlink_ext_ack *extack);
-struct tc_action_ops *tc_action_load_ops(struct nlattr *nla, bool police,
-					 bool rtnl_held,
+struct tc_action_ops *tc_action_load_ops(struct nlattr *nla, u32 flags,
 					 struct netlink_ext_ack *extack);
 struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 				    struct nlattr *nla, struct nlattr *est,
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index ef70d4771811..3e30d7260493 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -1324,10 +1324,10 @@ void tcf_idr_insert_many(struct tc_action *actions[], int init_res[])
 	}
 }
 
-struct tc_action_ops *tc_action_load_ops(struct nlattr *nla, bool police,
-					 bool rtnl_held,
+struct tc_action_ops *tc_action_load_ops(struct nlattr *nla, u32 flags,
 					 struct netlink_ext_ack *extack)
 {
+	bool police = flags & TCA_ACT_FLAGS_POLICE;
 	struct nlattr *tb[TCA_ACT_MAX + 1];
 	struct tc_action_ops *a_o;
 	char act_name[IFNAMSIZ];
@@ -1359,6 +1359,8 @@ struct tc_action_ops *tc_action_load_ops(struct nlattr *nla, bool police,
 	a_o = tc_lookup_action_n(act_name);
 	if (a_o == NULL) {
 #ifdef CONFIG_MODULES
+		bool rtnl_held = !(flags & TCA_ACT_FLAGS_NO_RTNL);
+
 		if (rtnl_held)
 			rtnl_unlock();
 		request_module("act_%s", act_name);
@@ -1475,9 +1477,7 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
 	for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) {
 		struct tc_action_ops *a_o;
 
-		a_o = tc_action_load_ops(tb[i], flags & TCA_ACT_FLAGS_POLICE,
-					 !(flags & TCA_ACT_FLAGS_NO_RTNL),
-					 extack);
+		a_o = tc_action_load_ops(tb[i], flags, extack);
 		if (IS_ERR(a_o)) {
 			err = PTR_ERR(a_o);
 			goto err_mod;
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 253b26f2eddd..e3236a3169c3 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -3314,12 +3314,11 @@ int tcf_exts_validate_ex(struct net *net, struct tcf_proto *tp, struct nlattr **
 		if (exts->police && tb[exts->police]) {
 			struct tc_action_ops *a_o;
 
-			a_o = tc_action_load_ops(tb[exts->police], true,
-						 !(flags & TCA_ACT_FLAGS_NO_RTNL),
+			flags |= TCA_ACT_FLAGS_POLICE | TCA_ACT_FLAGS_BIND;
+			a_o = tc_action_load_ops(tb[exts->police], flags,
 						 extack);
 			if (IS_ERR(a_o))
 				return PTR_ERR(a_o);
-			flags |= TCA_ACT_FLAGS_POLICE | TCA_ACT_FLAGS_BIND;
 			act = tcf_action_init_1(net, tp, tb[exts->police],
 						rate_tlv, a_o, init_res, flags,
 						extack);
-- 
cgit v1.2.3


From 477bd4beb93bf9ace9bda71f1437b191befa9cf4 Mon Sep 17 00:00:00 2001
From: Swee Leong Ching <leong.ching.swee@intel.com>
Date: Fri, 5 Jan 2024 15:09:23 +0800
Subject: net: stmmac: Make MSI interrupt routine generic

There is no support for per DMA channel interrupt for non-MSI platform,
where the MAC's per channel interrupt hooks up to interrupt controller(GIC)
through shared peripheral interrupt(SPI) to handle interrupt from TX/RX
transmit channel.

This patch generalize the existing MSI ISR to also support non-MSI
platform.

Signed-off-by: Teoh Ji Sheng <ji.sheng.teoh@intel.com>
Signed-off-by: Swee Leong Ching <leong.ching.swee@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c  |  4 +--
 .../net/ethernet/stmicro/stmmac/dwmac-socfpga.c    |  3 +++
 drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c   |  2 +-
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c  | 30 +++++++++++-----------
 include/linux/stmmac.h                             |  4 +--
 5 files changed, 23 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index 60283543ffc8..f0ec69af96c9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -952,7 +952,7 @@ static int stmmac_config_single_msi(struct pci_dev *pdev,
 
 	res->irq = pci_irq_vector(pdev, 0);
 	res->wol_irq = res->irq;
-	plat->flags &= ~STMMAC_FLAG_MULTI_MSI_EN;
+	plat->flags &= ~STMMAC_FLAG_MULTI_IRQ_EN;
 	dev_info(&pdev->dev, "%s: Single IRQ enablement successful\n",
 		 __func__);
 
@@ -1004,7 +1004,7 @@ static int stmmac_config_multi_msi(struct pci_dev *pdev,
 	if (plat->msi_sfty_ue_vec < STMMAC_MSI_VEC_MAX)
 		res->sfty_ue_irq = pci_irq_vector(pdev, plat->msi_sfty_ue_vec);
 
-	plat->flags |= STMMAC_FLAG_MULTI_MSI_EN;
+	plat->flags |= STMMAC_FLAG_MULTI_IRQ_EN;
 	dev_info(&pdev->dev, "%s: multi MSI enablement successful\n", __func__);
 
 	return 0;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
index ba2ce776bd4d..cf43fb3c6cc5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
@@ -427,6 +427,9 @@ static int socfpga_dwmac_probe(struct platform_device *pdev)
 	plat_dat->bsp_priv = dwmac;
 	plat_dat->fix_mac_speed = socfpga_dwmac_fix_mac_speed;
 
+	if (stmmac_res.rx_irq[0] > 0 && stmmac_res.tx_irq[0] > 0)
+		plat_dat->flags |= STMMAC_FLAG_MULTI_IRQ_EN;
+
 	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
 	if (ret)
 		return ret;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
index 84d3a8551b03..5f649106ffcd 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
@@ -175,7 +175,7 @@ static void dwmac4_dma_init(void __iomem *ioaddr,
 
 	value = readl(ioaddr + DMA_BUS_MODE);
 
-	if (dma_cfg->multi_msi_en) {
+	if (dma_cfg->multi_irq_en) {
 		value &= ~DMA_BUS_MODE_INTM_MASK;
 		value |= (DMA_BUS_MODE_INTM_MODE1 << DMA_BUS_MODE_INTM_SHIFT);
 	}
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 47de466e432c..57873b879b33 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -129,8 +129,8 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id);
 /* For MSI interrupts handling */
 static irqreturn_t stmmac_mac_interrupt(int irq, void *dev_id);
 static irqreturn_t stmmac_safety_interrupt(int irq, void *dev_id);
-static irqreturn_t stmmac_msi_intr_tx(int irq, void *data);
-static irqreturn_t stmmac_msi_intr_rx(int irq, void *data);
+static irqreturn_t stmmac_dma_tx_interrupt(int irq, void *data);
+static irqreturn_t stmmac_dma_rx_interrupt(int irq, void *data);
 static void stmmac_reset_rx_queue(struct stmmac_priv *priv, u32 queue);
 static void stmmac_reset_tx_queue(struct stmmac_priv *priv, u32 queue);
 static void stmmac_reset_queues_param(struct stmmac_priv *priv);
@@ -3602,7 +3602,7 @@ static void stmmac_free_irq(struct net_device *dev,
 	}
 }
 
-static int stmmac_request_irq_multi_msi(struct net_device *dev)
+static int stmmac_request_irq_multi(struct net_device *dev)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
 	enum request_irq_err irq_err;
@@ -3697,7 +3697,7 @@ static int stmmac_request_irq_multi_msi(struct net_device *dev)
 		}
 	}
 
-	/* Request Rx MSI irq */
+	/* Request Rx irq */
 	for (i = 0; i < priv->plat->rx_queues_to_use; i++) {
 		if (i >= MTL_MAX_RX_QUEUES)
 			break;
@@ -3707,11 +3707,11 @@ static int stmmac_request_irq_multi_msi(struct net_device *dev)
 		int_name = priv->int_name_rx_irq[i];
 		sprintf(int_name, "%s:%s-%d", dev->name, "rx", i);
 		ret = request_irq(priv->rx_irq[i],
-				  stmmac_msi_intr_rx,
+				  stmmac_dma_rx_interrupt,
 				  0, int_name, &priv->dma_conf.rx_queue[i]);
 		if (unlikely(ret < 0)) {
 			netdev_err(priv->dev,
-				   "%s: alloc rx-%d  MSI %d (error: %d)\n",
+				   "%s: alloc rx-%d  dma rx_irq %d (error: %d)\n",
 				   __func__, i, priv->rx_irq[i], ret);
 			irq_err = REQ_IRQ_ERR_RX;
 			irq_idx = i;
@@ -3722,7 +3722,7 @@ static int stmmac_request_irq_multi_msi(struct net_device *dev)
 		irq_set_affinity_hint(priv->rx_irq[i], &cpu_mask);
 	}
 
-	/* Request Tx MSI irq */
+	/* Request Tx irq */
 	for (i = 0; i < priv->plat->tx_queues_to_use; i++) {
 		if (i >= MTL_MAX_TX_QUEUES)
 			break;
@@ -3732,11 +3732,11 @@ static int stmmac_request_irq_multi_msi(struct net_device *dev)
 		int_name = priv->int_name_tx_irq[i];
 		sprintf(int_name, "%s:%s-%d", dev->name, "tx", i);
 		ret = request_irq(priv->tx_irq[i],
-				  stmmac_msi_intr_tx,
+				  stmmac_dma_tx_interrupt,
 				  0, int_name, &priv->dma_conf.tx_queue[i]);
 		if (unlikely(ret < 0)) {
 			netdev_err(priv->dev,
-				   "%s: alloc tx-%d  MSI %d (error: %d)\n",
+				   "%s: alloc tx-%d  dma tx_irq %d (error: %d)\n",
 				   __func__, i, priv->tx_irq[i], ret);
 			irq_err = REQ_IRQ_ERR_TX;
 			irq_idx = i;
@@ -3811,8 +3811,8 @@ static int stmmac_request_irq(struct net_device *dev)
 	int ret;
 
 	/* Request the IRQ lines */
-	if (priv->plat->flags & STMMAC_FLAG_MULTI_MSI_EN)
-		ret = stmmac_request_irq_multi_msi(dev);
+	if (priv->plat->flags & STMMAC_FLAG_MULTI_IRQ_EN)
+		ret = stmmac_request_irq_multi(dev);
 	else
 		ret = stmmac_request_irq_single(dev);
 
@@ -6075,7 +6075,7 @@ static irqreturn_t stmmac_safety_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static irqreturn_t stmmac_msi_intr_tx(int irq, void *data)
+static irqreturn_t stmmac_dma_tx_interrupt(int irq, void *data)
 {
 	struct stmmac_tx_queue *tx_q = (struct stmmac_tx_queue *)data;
 	struct stmmac_dma_conf *dma_conf;
@@ -6107,7 +6107,7 @@ static irqreturn_t stmmac_msi_intr_tx(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static irqreturn_t stmmac_msi_intr_rx(int irq, void *data)
+static irqreturn_t stmmac_dma_rx_interrupt(int irq, void *data)
 {
 	struct stmmac_rx_queue *rx_q = (struct stmmac_rx_queue *)data;
 	struct stmmac_dma_conf *dma_conf;
@@ -7456,8 +7456,8 @@ int stmmac_dvr_probe(struct device *device,
 	priv->plat = plat_dat;
 	priv->ioaddr = res->addr;
 	priv->dev->base_addr = (unsigned long)res->addr;
-	priv->plat->dma_cfg->multi_msi_en =
-		(priv->plat->flags & STMMAC_FLAG_MULTI_MSI_EN);
+	priv->plat->dma_cfg->multi_irq_en =
+		(priv->plat->flags & STMMAC_FLAG_MULTI_IRQ_EN);
 
 	priv->dev->irq = res->irq;
 	priv->wol_irq = res->wol_irq;
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index dee5ad6e48c5..b950e6f9761d 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -98,7 +98,7 @@ struct stmmac_dma_cfg {
 	int mixed_burst;
 	bool aal;
 	bool eame;
-	bool multi_msi_en;
+	bool multi_irq_en;
 	bool dche;
 };
 
@@ -215,7 +215,7 @@ struct dwmac4_addrs {
 #define STMMAC_FLAG_TSO_EN			BIT(4)
 #define STMMAC_FLAG_SERDES_UP_AFTER_PHY_LINKUP	BIT(5)
 #define STMMAC_FLAG_VLAN_FAIL_Q_EN		BIT(6)
-#define STMMAC_FLAG_MULTI_MSI_EN		BIT(7)
+#define STMMAC_FLAG_MULTI_IRQ_EN		BIT(7)
 #define STMMAC_FLAG_EXT_SNAPSHOT_EN		BIT(8)
 #define STMMAC_FLAG_INT_SNAPSHOT_EN		BIT(9)
 #define STMMAC_FLAG_RX_CLK_RUNS_IN_LPI		BIT(10)
-- 
cgit v1.2.3


From deb704281f076097b0347116a82edeba96697db1 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Fri, 17 Nov 2023 17:14:27 -0500
Subject: SUNRPC: Add a server-side API for retrieving an RPC's pseudoflavor

NFSD will use this new API to determine whether nfsd_splice_read is
safe to use. This avoids the need to add a dependency to NFSD for
CONFIG_SUNRPC_GSS.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/svcauth.h    |  7 ++++++-
 net/sunrpc/auth_gss/svcauth_gss.c |  6 ++++++
 net/sunrpc/svcauth.c              | 16 ++++++++++++++++
 3 files changed, 28 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/svcauth.h b/include/linux/sunrpc/svcauth.h
index 6f90203edbf8..61c455f1e1f5 100644
--- a/include/linux/sunrpc/svcauth.h
+++ b/include/linux/sunrpc/svcauth.h
@@ -131,8 +131,11 @@ enum svc_auth_status {
  *   This call releases a domain.
  *
  * set_client()
- *   Givens a pending request (struct svc_rqst), finds and assigns
+ *   Given a pending request (struct svc_rqst), finds and assigns
  *   an appropriate 'auth_domain' as the client.
+ *
+ * pseudoflavor()
+ *   Returns RPC_AUTH pseudoflavor in use by @rqstp.
  */
 struct auth_ops {
 	char *	name;
@@ -143,11 +146,13 @@ struct auth_ops {
 	int			(*release)(struct svc_rqst *rqstp);
 	void			(*domain_release)(struct auth_domain *dom);
 	enum svc_auth_status	(*set_client)(struct svc_rqst *rqstp);
+	rpc_authflavor_t	(*pseudoflavor)(struct svc_rqst *rqstp);
 };
 
 struct svc_xprt;
 
 extern enum svc_auth_status svc_authenticate(struct svc_rqst *rqstp);
+extern rpc_authflavor_t svc_auth_flavor(struct svc_rqst *rqstp);
 extern int	svc_authorise(struct svc_rqst *rqstp);
 extern enum svc_auth_status svc_set_client(struct svc_rqst *rqstp);
 extern int	svc_auth_register(rpc_authflavor_t flavor, struct auth_ops *aops);
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index 18734e70c5dd..104d9a320142 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -2014,6 +2014,11 @@ svcauth_gss_domain_release(struct auth_domain *dom)
 	call_rcu(&dom->rcu_head, svcauth_gss_domain_release_rcu);
 }
 
+static rpc_authflavor_t svcauth_gss_pseudoflavor(struct svc_rqst *rqstp)
+{
+	return svcauth_gss_flavor(rqstp->rq_gssclient);
+}
+
 static struct auth_ops svcauthops_gss = {
 	.name		= "rpcsec_gss",
 	.owner		= THIS_MODULE,
@@ -2022,6 +2027,7 @@ static struct auth_ops svcauthops_gss = {
 	.release	= svcauth_gss_release,
 	.domain_release = svcauth_gss_domain_release,
 	.set_client	= svcauth_gss_set_client,
+	.pseudoflavor	= svcauth_gss_pseudoflavor,
 };
 
 static int rsi_cache_create_net(struct net *net)
diff --git a/net/sunrpc/svcauth.c b/net/sunrpc/svcauth.c
index aa4429d0b810..1619211f0960 100644
--- a/net/sunrpc/svcauth.c
+++ b/net/sunrpc/svcauth.c
@@ -160,6 +160,22 @@ svc_auth_unregister(rpc_authflavor_t flavor)
 }
 EXPORT_SYMBOL_GPL(svc_auth_unregister);
 
+/**
+ * svc_auth_flavor - return RPC transaction's RPC_AUTH flavor
+ * @rqstp: RPC transaction context
+ *
+ * Returns an RPC flavor or GSS pseudoflavor.
+ */
+rpc_authflavor_t svc_auth_flavor(struct svc_rqst *rqstp)
+{
+	struct auth_ops *aops = rqstp->rq_authop;
+
+	if (!aops->pseudoflavor)
+		return aops->flavour;
+	return aops->pseudoflavor(rqstp);
+}
+EXPORT_SYMBOL_GPL(svc_auth_flavor);
+
 /**************************************************
  * 'auth_domains' are stored in a hash table indexed by name.
  * When the last reference to an 'auth_domain' is dropped,
-- 
cgit v1.2.3


From 3587b5c75376fd0b6ca8c4a8de54954e410f4e0e Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Fri, 17 Nov 2023 17:14:46 -0500
Subject: SUNRPC: Remove RQ_SPLICE_OK

This flag is no longer used.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/svc.h        |  2 --
 include/trace/events/sunrpc.h     |  1 -
 net/sunrpc/auth_gss/svcauth_gss.c | 10 ----------
 net/sunrpc/svc.c                  |  2 --
 4 files changed, 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index b10f987509cc..544fcfe07479 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -260,8 +260,6 @@ enum {
 	RQ_LOCAL,		/* local request */
 	RQ_USEDEFERRAL,		/* use deferral */
 	RQ_DROPME,		/* drop current reply */
-	RQ_SPLICE_OK,		/* turned off in gss privacy to prevent
-				 * encrypting page cache pages */
 	RQ_VICTIM,		/* Have agreed to shut down */
 	RQ_DATA,		/* request has data */
 };
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 337c90787fb1..cdd3a45e6003 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -1675,7 +1675,6 @@ DEFINE_SVCXDRBUF_EVENT(sendto);
 	svc_rqst_flag(LOCAL)						\
 	svc_rqst_flag(USEDEFERRAL)					\
 	svc_rqst_flag(DROPME)						\
-	svc_rqst_flag(SPLICE_OK)					\
 	svc_rqst_flag(VICTIM)						\
 	svc_rqst_flag_end(DATA)
 
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index 104d9a320142..24de94184700 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -866,14 +866,6 @@ svcauth_gss_unwrap_integ(struct svc_rqst *rqstp, u32 seq, struct gss_ctx *ctx)
 	struct xdr_buf databody_integ;
 	struct xdr_netobj checksum;
 
-	/* NFS READ normally uses splice to send data in-place. However
-	 * the data in cache can change after the reply's MIC is computed
-	 * but before the RPC reply is sent. To prevent the client from
-	 * rejecting the server-computed MIC in this somewhat rare case,
-	 * do not use splice with the GSS integrity service.
-	 */
-	clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
-
 	/* Did we already verify the signature on the original pass through? */
 	if (rqstp->rq_deferred)
 		return 0;
@@ -948,8 +940,6 @@ svcauth_gss_unwrap_priv(struct svc_rqst *rqstp, u32 seq, struct gss_ctx *ctx)
 	struct xdr_buf *buf = xdr->buf;
 	unsigned int saved_len;
 
-	clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
-
 	if (xdr_stream_decode_u32(xdr, &len) < 0)
 		goto unwrap_failed;
 	if (rqstp->rq_deferred) {
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 3f2ea7a0496f..fa4e23fa0e09 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1305,8 +1305,6 @@ svc_process_common(struct svc_rqst *rqstp)
 	int			rc;
 	__be32			*p;
 
-	/* Will be turned off by GSS integrity and privacy services */
-	set_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
 	/* Will be turned off only when NFSv4 Sessions are used */
 	set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
 	clear_bit(RQ_DROPME, &rqstp->rq_flags);
-- 
cgit v1.2.3


From 52e89100754b2e888cb63bf2d19e65d809497cd6 Mon Sep 17 00:00:00 2001
From: ChenXiaoSong <chenxiaosong@kylinos.cn>
Date: Sat, 2 Dec 2023 21:07:25 +0000
Subject: NFSv4, NFSD: move enum nfs_cb_opnum4 to include/linux/nfs4.h

Callback operations enum is defined in client and server, move it to
common header file.

Signed-off-by: ChenXiaoSong <chenxiaosong@kylinos.cn>
Acked-by: Anna Schumaker <Anna.Schumaker@netapp.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfs/callback.h      | 19 -------------------
 fs/nfsd/nfs4callback.c | 26 +-------------------------
 include/linux/nfs4.h   | 22 ++++++++++++++++++++++
 3 files changed, 23 insertions(+), 44 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h
index ccd4f245cae2..0279b78b5fc9 100644
--- a/fs/nfs/callback.h
+++ b/fs/nfs/callback.h
@@ -19,25 +19,6 @@ enum nfs4_callback_procnum {
 	CB_COMPOUND = 1,
 };
 
-enum nfs4_callback_opnum {
-	OP_CB_GETATTR = 3,
-	OP_CB_RECALL  = 4,
-/* Callback operations new to NFSv4.1 */
-	OP_CB_LAYOUTRECALL  = 5,
-	OP_CB_NOTIFY        = 6,
-	OP_CB_PUSH_DELEG    = 7,
-	OP_CB_RECALL_ANY    = 8,
-	OP_CB_RECALLABLE_OBJ_AVAIL = 9,
-	OP_CB_RECALL_SLOT   = 10,
-	OP_CB_SEQUENCE      = 11,
-	OP_CB_WANTS_CANCELLED = 12,
-	OP_CB_NOTIFY_LOCK   = 13,
-	OP_CB_NOTIFY_DEVICEID = 14,
-/* Callback operations new to NFSv4.2 */
-	OP_CB_OFFLOAD = 15,
-	OP_CB_ILLEGAL = 10044,
-};
-
 struct nfs4_slot;
 struct cb_process_state {
 	__be32			drc_status;
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 4039ffcf90ba..926c29879c6a 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -31,6 +31,7 @@
  *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 
+#include <linux/nfs4.h>
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/xprt.h>
 #include <linux/sunrpc/svc_xprt.h>
@@ -87,31 +88,6 @@ static void encode_bitmap4(struct xdr_stream *xdr, const __u32 *bitmap,
 	WARN_ON_ONCE(xdr_stream_encode_uint32_array(xdr, bitmap, len) < 0);
 }
 
-/*
- *	nfs_cb_opnum4
- *
- *	enum nfs_cb_opnum4 {
- *		OP_CB_GETATTR		= 3,
- *		  ...
- *	};
- */
-enum nfs_cb_opnum4 {
-	OP_CB_GETATTR			= 3,
-	OP_CB_RECALL			= 4,
-	OP_CB_LAYOUTRECALL		= 5,
-	OP_CB_NOTIFY			= 6,
-	OP_CB_PUSH_DELEG		= 7,
-	OP_CB_RECALL_ANY		= 8,
-	OP_CB_RECALLABLE_OBJ_AVAIL	= 9,
-	OP_CB_RECALL_SLOT		= 10,
-	OP_CB_SEQUENCE			= 11,
-	OP_CB_WANTS_CANCELLED		= 12,
-	OP_CB_NOTIFY_LOCK		= 13,
-	OP_CB_NOTIFY_DEVICEID		= 14,
-	OP_CB_OFFLOAD			= 15,
-	OP_CB_ILLEGAL			= 10044
-};
-
 static void encode_nfs_cb_opnum4(struct xdr_stream *xdr, enum nfs_cb_opnum4 op)
 {
 	__be32 *p;
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index c11c4db34639..ef8d2d618d5b 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -869,4 +869,26 @@ enum {
 	RCA4_TYPE_MASK_OTHER_LAYOUT_MAX	= 15,
 };
 
+enum nfs_cb_opnum4 {
+	OP_CB_GETATTR = 3,
+	OP_CB_RECALL  = 4,
+
+	/* Callback operations new to NFSv4.1 */
+	OP_CB_LAYOUTRECALL  = 5,
+	OP_CB_NOTIFY        = 6,
+	OP_CB_PUSH_DELEG    = 7,
+	OP_CB_RECALL_ANY    = 8,
+	OP_CB_RECALLABLE_OBJ_AVAIL = 9,
+	OP_CB_RECALL_SLOT   = 10,
+	OP_CB_SEQUENCE      = 11,
+	OP_CB_WANTS_CANCELLED = 12,
+	OP_CB_NOTIFY_LOCK   = 13,
+	OP_CB_NOTIFY_DEVICEID = 14,
+
+	/* Callback operations new to NFSv4.2 */
+	OP_CB_OFFLOAD = 15,
+
+	OP_CB_ILLEGAL = 10044,
+};
+
 #endif
-- 
cgit v1.2.3


From b541dd554bc0442f7ff8c6cab6c5460c044913c8 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Tue, 21 Nov 2023 11:40:13 -0500
Subject: svcrdma: Eliminate allocation of recv_ctxt objects in backchannel

The svc_rdma_recv_ctxt free list uses a lockless list to avoid the
need for a spin lock in the fast path. llist_del_first(), which is
used by svc_rdma_recv_ctxt_get(), requires serialization, however,
when there are multiple list producers that are unserialized.

I mistakenly thought there was only one caller of
svc_rdma_recv_ctxt_get() (svc_rdma_refresh_recvs()), thus explicit
serialization would not be necessary. But there is another caller:
svc_rdma_bc_sendto(), and these two are not serialized against each
other. I haven't seen ill effects that I could directly ascribe to
a lack of serialization. It's just an observation based on code
audit.

When DMA-mapping before sending a Reply, the passed-in struct
svc_rdma_recv_ctxt is used only for its write and reply PCLs. These
are currently always empty in the backchannel case. So, instead of
passing a full svc_rdma_recv_ctxt object to
svc_rdma_map_reply_msg(), let's pass in just the Write and Reply
PCLs.

This change makes it unnecessary for the backchannel to acquire a
dummy svc_rdma_recv_ctxt object when sending an RPC Call. The need
for svc_rdma_recv_ctxt free list serialization is now completely
avoided.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/svc_rdma.h            |  3 ++-
 net/sunrpc/xprtrdma/svc_rdma_backchannel.c | 11 ++++-------
 net/sunrpc/xprtrdma/svc_rdma_sendto.c      | 31 ++++++++++++++++--------------
 3 files changed, 23 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index a5ee0af2a310..4ac32895a058 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -200,7 +200,8 @@ extern int svc_rdma_send(struct svcxprt_rdma *rdma,
 			 struct svc_rdma_send_ctxt *ctxt);
 extern int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
 				  struct svc_rdma_send_ctxt *sctxt,
-				  const struct svc_rdma_recv_ctxt *rctxt,
+				  const struct svc_rdma_pcl *write_pcl,
+				  const struct svc_rdma_pcl *reply_pcl,
 				  const struct xdr_buf *xdr);
 extern void svc_rdma_send_error_msg(struct svcxprt_rdma *rdma,
 				    struct svc_rdma_send_ctxt *sctxt,
diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
index 7420a2c990c7..c9be6778643b 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
@@ -76,15 +76,12 @@ static int svc_rdma_bc_sendto(struct svcxprt_rdma *rdma,
 			      struct rpc_rqst *rqst,
 			      struct svc_rdma_send_ctxt *sctxt)
 {
-	struct svc_rdma_recv_ctxt *rctxt;
+	struct svc_rdma_pcl empty_pcl;
 	int ret;
 
-	rctxt = svc_rdma_recv_ctxt_get(rdma);
-	if (!rctxt)
-		return -EIO;
-
-	ret = svc_rdma_map_reply_msg(rdma, sctxt, rctxt, &rqst->rq_snd_buf);
-	svc_rdma_recv_ctxt_put(rdma, rctxt);
+	pcl_init(&empty_pcl);
+	ret = svc_rdma_map_reply_msg(rdma, sctxt, &empty_pcl, &empty_pcl,
+				     &rqst->rq_snd_buf);
 	if (ret < 0)
 		return -EIO;
 
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index c6644cca52c5..45735f74eb86 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -653,7 +653,7 @@ static int svc_rdma_xb_count_sges(const struct xdr_buf *xdr,
  * svc_rdma_pull_up_needed - Determine whether to use pull-up
  * @rdma: controlling transport
  * @sctxt: send_ctxt for the Send WR
- * @rctxt: Write and Reply chunks provided by client
+ * @write_pcl: Write chunk list provided by client
  * @xdr: xdr_buf containing RPC message to transmit
  *
  * Returns:
@@ -662,7 +662,7 @@ static int svc_rdma_xb_count_sges(const struct xdr_buf *xdr,
  */
 static bool svc_rdma_pull_up_needed(const struct svcxprt_rdma *rdma,
 				    const struct svc_rdma_send_ctxt *sctxt,
-				    const struct svc_rdma_recv_ctxt *rctxt,
+				    const struct svc_rdma_pcl *write_pcl,
 				    const struct xdr_buf *xdr)
 {
 	/* Resources needed for the transport header */
@@ -672,7 +672,7 @@ static bool svc_rdma_pull_up_needed(const struct svcxprt_rdma *rdma,
 	};
 	int ret;
 
-	ret = pcl_process_nonpayloads(&rctxt->rc_write_pcl, xdr,
+	ret = pcl_process_nonpayloads(write_pcl, xdr,
 				      svc_rdma_xb_count_sges, &args);
 	if (ret < 0)
 		return false;
@@ -728,7 +728,7 @@ static int svc_rdma_xb_linearize(const struct xdr_buf *xdr,
  * svc_rdma_pull_up_reply_msg - Copy Reply into a single buffer
  * @rdma: controlling transport
  * @sctxt: send_ctxt for the Send WR; xprt hdr is already prepared
- * @rctxt: Write and Reply chunks provided by client
+ * @write_pcl: Write chunk list provided by client
  * @xdr: prepared xdr_buf containing RPC message
  *
  * The device is not capable of sending the reply directly.
@@ -743,7 +743,7 @@ static int svc_rdma_xb_linearize(const struct xdr_buf *xdr,
  */
 static int svc_rdma_pull_up_reply_msg(const struct svcxprt_rdma *rdma,
 				      struct svc_rdma_send_ctxt *sctxt,
-				      const struct svc_rdma_recv_ctxt *rctxt,
+				      const struct svc_rdma_pcl *write_pcl,
 				      const struct xdr_buf *xdr)
 {
 	struct svc_rdma_pullup_data args = {
@@ -751,7 +751,7 @@ static int svc_rdma_pull_up_reply_msg(const struct svcxprt_rdma *rdma,
 	};
 	int ret;
 
-	ret = pcl_process_nonpayloads(&rctxt->rc_write_pcl, xdr,
+	ret = pcl_process_nonpayloads(write_pcl, xdr,
 				      svc_rdma_xb_linearize, &args);
 	if (ret < 0)
 		return ret;
@@ -764,7 +764,8 @@ static int svc_rdma_pull_up_reply_msg(const struct svcxprt_rdma *rdma,
 /* svc_rdma_map_reply_msg - DMA map the buffer holding RPC message
  * @rdma: controlling transport
  * @sctxt: send_ctxt for the Send WR
- * @rctxt: Write and Reply chunks provided by client
+ * @write_pcl: Write chunk list provided by client
+ * @reply_pcl: Reply chunk provided by client
  * @xdr: prepared xdr_buf containing RPC message
  *
  * Returns:
@@ -776,7 +777,8 @@ static int svc_rdma_pull_up_reply_msg(const struct svcxprt_rdma *rdma,
  */
 int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
 			   struct svc_rdma_send_ctxt *sctxt,
-			   const struct svc_rdma_recv_ctxt *rctxt,
+			   const struct svc_rdma_pcl *write_pcl,
+			   const struct svc_rdma_pcl *reply_pcl,
 			   const struct xdr_buf *xdr)
 {
 	struct svc_rdma_map_data args = {
@@ -789,18 +791,18 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
 	sctxt->sc_sges[0].length = sctxt->sc_hdrbuf.len;
 
 	/* If there is a Reply chunk, nothing follows the transport
-	 * header, and we're done here.
+	 * header, so there is nothing to map.
 	 */
-	if (!pcl_is_empty(&rctxt->rc_reply_pcl))
+	if (!pcl_is_empty(reply_pcl))
 		return 0;
 
 	/* For pull-up, svc_rdma_send() will sync the transport header.
 	 * No additional DMA mapping is necessary.
 	 */
-	if (svc_rdma_pull_up_needed(rdma, sctxt, rctxt, xdr))
-		return svc_rdma_pull_up_reply_msg(rdma, sctxt, rctxt, xdr);
+	if (svc_rdma_pull_up_needed(rdma, sctxt, write_pcl, xdr))
+		return svc_rdma_pull_up_reply_msg(rdma, sctxt, write_pcl, xdr);
 
-	return pcl_process_nonpayloads(&rctxt->rc_write_pcl, xdr,
+	return pcl_process_nonpayloads(write_pcl, xdr,
 				       svc_rdma_xb_dma_map, &args);
 }
 
@@ -848,7 +850,8 @@ static int svc_rdma_send_reply_msg(struct svcxprt_rdma *rdma,
 {
 	int ret;
 
-	ret = svc_rdma_map_reply_msg(rdma, sctxt, rctxt, &rqstp->rq_res);
+	ret = svc_rdma_map_reply_msg(rdma, sctxt, &rctxt->rc_write_pcl,
+				     &rctxt->rc_reply_pcl, &rqstp->rq_res);
 	if (ret < 0)
 		return ret;
 
-- 
cgit v1.2.3


From 9c7e1a06588ee6962afe0dfe5a398e1d23212005 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Tue, 21 Nov 2023 11:40:26 -0500
Subject: svcrdma: Add a utility workqueue to svcrdma

To handle work in the background, set up an UNBOUND workqueue for
svcrdma. Subsequent patches will make use of it.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/svc_rdma.h          |  1 +
 net/sunrpc/xprtrdma/svc_rdma.c           | 32 ++++++++++++++++++++++++--------
 net/sunrpc/xprtrdma/svc_rdma_transport.c |  1 +
 3 files changed, 26 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 4ac32895a058..e18c94e816b3 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -65,6 +65,7 @@ extern unsigned int svcrdma_ord;
 extern unsigned int svcrdma_max_requests;
 extern unsigned int svcrdma_max_bc_requests;
 extern unsigned int svcrdma_max_req_size;
+extern struct workqueue_struct *svcrdma_wq;
 
 extern struct percpu_counter svcrdma_stat_read;
 extern struct percpu_counter svcrdma_stat_recv;
diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c
index f0d5eeed4c88..f86970733eb0 100644
--- a/net/sunrpc/xprtrdma/svc_rdma.c
+++ b/net/sunrpc/xprtrdma/svc_rdma.c
@@ -256,28 +256,44 @@ out_err:
 	return rc;
 }
 
+struct workqueue_struct *svcrdma_wq;
+
 void svc_rdma_cleanup(void)
 {
-	dprintk("SVCRDMA Module Removed, deregister RPC RDMA transport\n");
 	svc_unreg_xprt_class(&svc_rdma_class);
 	svc_rdma_proc_cleanup();
+	if (svcrdma_wq) {
+		struct workqueue_struct *wq = svcrdma_wq;
+
+		svcrdma_wq = NULL;
+		destroy_workqueue(wq);
+	}
+
+	dprintk("SVCRDMA Module Removed, deregister RPC RDMA transport\n");
 }
 
 int svc_rdma_init(void)
 {
+	struct workqueue_struct *wq;
 	int rc;
 
-	dprintk("SVCRDMA Module Init, register RPC RDMA transport\n");
-	dprintk("\tsvcrdma_ord      : %d\n", svcrdma_ord);
-	dprintk("\tmax_requests     : %u\n", svcrdma_max_requests);
-	dprintk("\tmax_bc_requests  : %u\n", svcrdma_max_bc_requests);
-	dprintk("\tmax_inline       : %d\n", svcrdma_max_req_size);
+	wq = alloc_workqueue("svcrdma", WQ_UNBOUND, 0);
+	if (!wq)
+		return -ENOMEM;
 
 	rc = svc_rdma_proc_init();
-	if (rc)
+	if (rc) {
+		destroy_workqueue(wq);
 		return rc;
+	}
 
-	/* Register RDMA with the SVC transport switch */
+	svcrdma_wq = wq;
 	svc_reg_xprt_class(&svc_rdma_class);
+
+	dprintk("SVCRDMA Module Init, register RPC RDMA transport\n");
+	dprintk("\tsvcrdma_ord      : %d\n", svcrdma_ord);
+	dprintk("\tmax_requests     : %u\n", svcrdma_max_requests);
+	dprintk("\tmax_bc_requests  : %u\n", svcrdma_max_bc_requests);
+	dprintk("\tmax_inline       : %d\n", svcrdma_max_req_size);
 	return 0;
 }
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 2abd895046ee..c046916df007 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -547,6 +547,7 @@ static void __svc_rdma_free(struct work_struct *work)
 	/* This blocks until the Completion Queues are empty */
 	if (rdma->sc_qp && !IS_ERR(rdma->sc_qp))
 		ib_drain_qp(rdma->sc_qp);
+	flush_workqueue(svcrdma_wq);
 
 	svc_rdma_flush_recv_queues(rdma);
 
-- 
cgit v1.2.3


From ae225fe27b931de89b6b1e1bbe6de4de23000850 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Tue, 21 Nov 2023 11:40:33 -0500
Subject: svcrdma: Add an async version of svc_rdma_send_ctxt_put()

DMA unmapping can take quite some time, so it should not be handled
in a single-threaded completion handler. Defer releasing send_ctxts
to the recently-added workqueue.

With this patch, DMA unmapping can be handled in parallel, and it
does not cause head-of-queue blocking of Send completions.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/svc_rdma.h       |  2 ++
 net/sunrpc/xprtrdma/svc_rdma_sendto.c | 34 +++++++++++++++++++++++++---------
 2 files changed, 27 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index e18c94e816b3..ab250017b99f 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -152,7 +152,9 @@ struct svc_rdma_recv_ctxt {
 struct svc_rdma_send_ctxt {
 	struct llist_node	sc_node;
 	struct rpc_rdma_cid	sc_cid;
+	struct work_struct	sc_work;
 
+	struct svcxprt_rdma	*sc_rdma;
 	struct ib_send_wr	sc_send_wr;
 	struct ib_cqe		sc_cqe;
 	struct xdr_buf		sc_hdrbuf;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 45735f74eb86..22c39ba923d2 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -143,6 +143,7 @@ svc_rdma_send_ctxt_alloc(struct svcxprt_rdma *rdma)
 
 	svc_rdma_send_cid_init(rdma, &ctxt->sc_cid);
 
+	ctxt->sc_rdma = rdma;
 	ctxt->sc_send_wr.next = NULL;
 	ctxt->sc_send_wr.wr_cqe = &ctxt->sc_cqe;
 	ctxt->sc_send_wr.sg_list = ctxt->sc_sges;
@@ -223,15 +224,8 @@ out_empty:
 	goto out;
 }
 
-/**
- * svc_rdma_send_ctxt_put - Return send_ctxt to free list
- * @rdma: controlling svcxprt_rdma
- * @ctxt: object to return to the free list
- *
- * Pages left in sc_pages are DMA unmapped and released.
- */
-void svc_rdma_send_ctxt_put(struct svcxprt_rdma *rdma,
-			    struct svc_rdma_send_ctxt *ctxt)
+static void svc_rdma_send_ctxt_release(struct svcxprt_rdma *rdma,
+				       struct svc_rdma_send_ctxt *ctxt)
 {
 	struct ib_device *device = rdma->sc_cm_id->device;
 	unsigned int i;
@@ -255,6 +249,28 @@ void svc_rdma_send_ctxt_put(struct svcxprt_rdma *rdma,
 	llist_add(&ctxt->sc_node, &rdma->sc_send_ctxts);
 }
 
+static void svc_rdma_send_ctxt_put_async(struct work_struct *work)
+{
+	struct svc_rdma_send_ctxt *ctxt;
+
+	ctxt = container_of(work, struct svc_rdma_send_ctxt, sc_work);
+	svc_rdma_send_ctxt_release(ctxt->sc_rdma, ctxt);
+}
+
+/**
+ * svc_rdma_send_ctxt_put - Return send_ctxt to free list
+ * @rdma: controlling svcxprt_rdma
+ * @ctxt: object to return to the free list
+ *
+ * Pages left in sc_pages are DMA unmapped and released.
+ */
+void svc_rdma_send_ctxt_put(struct svcxprt_rdma *rdma,
+			    struct svc_rdma_send_ctxt *ctxt)
+{
+	INIT_WORK(&ctxt->sc_work, svc_rdma_send_ctxt_put_async);
+	queue_work(svcrdma_wq, &ctxt->sc_work);
+}
+
 /**
  * svc_rdma_wake_send_waiters - manage Send Queue accounting
  * @rdma: controlling transport
-- 
cgit v1.2.3


From be2acb104880dbd5582c898d000cab5f38750bb9 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Mon, 27 Nov 2023 11:33:30 -0500
Subject: rpcrdma: Introduce a simple cid tracepoint class

De-duplicate some code, making it easier to add new tracepoints that
report only a completion ID.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/trace/events/rpcrdma.h          | 93 +++++++++------------------------
 net/sunrpc/xprtrdma/svc_rdma_recvfrom.c |  2 +-
 net/sunrpc/xprtrdma/svc_rdma_rw.c       |  2 +-
 net/sunrpc/xprtrdma/svc_rdma_sendto.c   |  2 +-
 net/sunrpc/xprtrdma/verbs.c             |  2 +-
 5 files changed, 30 insertions(+), 71 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index 718df1d9b834..b3445e07c151 100644
--- a/include/trace/events/rpcrdma.h
+++ b/include/trace/events/rpcrdma.h
@@ -22,47 +22,37 @@
  ** Event classes
  **/
 
-DECLARE_EVENT_CLASS(rpcrdma_completion_class,
+DECLARE_EVENT_CLASS(rpcrdma_simple_cid_class,
 	TP_PROTO(
-		const struct ib_wc *wc,
 		const struct rpc_rdma_cid *cid
 	),
 
-	TP_ARGS(wc, cid),
+	TP_ARGS(cid),
 
 	TP_STRUCT__entry(
 		__field(u32, cq_id)
 		__field(int, completion_id)
-		__field(unsigned long, status)
-		__field(unsigned int, vendor_err)
 	),
 
 	TP_fast_assign(
 		__entry->cq_id = cid->ci_queue_id;
 		__entry->completion_id = cid->ci_completion_id;
-		__entry->status = wc->status;
-		if (wc->status)
-			__entry->vendor_err = wc->vendor_err;
-		else
-			__entry->vendor_err = 0;
 	),
 
-	TP_printk("cq.id=%u cid=%d status=%s (%lu/0x%x)",
-		__entry->cq_id, __entry->completion_id,
-		rdma_show_wc_status(__entry->status),
-		__entry->status, __entry->vendor_err
+	TP_printk("cq.id=%d cid=%d",
+		__entry->cq_id, __entry->completion_id
 	)
 );
 
-#define DEFINE_COMPLETION_EVENT(name)					\
-		DEFINE_EVENT(rpcrdma_completion_class, name,		\
+#define DEFINE_SIMPLE_CID_EVENT(name)					\
+		DEFINE_EVENT(rpcrdma_simple_cid_class, name,		\
 				TP_PROTO(				\
-					const struct ib_wc *wc,		\
 					const struct rpc_rdma_cid *cid	\
 				),					\
-				TP_ARGS(wc, cid))
+				TP_ARGS(cid)				\
+		)
 
-DECLARE_EVENT_CLASS(rpcrdma_send_completion_class,
+DECLARE_EVENT_CLASS(rpcrdma_completion_class,
 	TP_PROTO(
 		const struct ib_wc *wc,
 		const struct rpc_rdma_cid *cid
@@ -73,20 +63,29 @@ DECLARE_EVENT_CLASS(rpcrdma_send_completion_class,
 	TP_STRUCT__entry(
 		__field(u32, cq_id)
 		__field(int, completion_id)
+		__field(unsigned long, status)
+		__field(unsigned int, vendor_err)
 	),
 
 	TP_fast_assign(
 		__entry->cq_id = cid->ci_queue_id;
 		__entry->completion_id = cid->ci_completion_id;
+		__entry->status = wc->status;
+		if (wc->status)
+			__entry->vendor_err = wc->vendor_err;
+		else
+			__entry->vendor_err = 0;
 	),
 
-	TP_printk("cq.id=%u cid=%d",
-		__entry->cq_id, __entry->completion_id
+	TP_printk("cq.id=%u cid=%d status=%s (%lu/0x%x)",
+		__entry->cq_id, __entry->completion_id,
+		rdma_show_wc_status(__entry->status),
+		__entry->status, __entry->vendor_err
 	)
 );
 
-#define DEFINE_SEND_COMPLETION_EVENT(name)				\
-		DEFINE_EVENT(rpcrdma_send_completion_class, name,	\
+#define DEFINE_COMPLETION_EVENT(name)					\
+		DEFINE_EVENT(rpcrdma_completion_class, name,		\
 				TP_PROTO(				\
 					const struct ib_wc *wc,		\
 					const struct rpc_rdma_cid *cid	\
@@ -978,27 +977,7 @@ TRACE_EVENT(xprtrdma_post_send_err,
 	)
 );
 
-TRACE_EVENT(xprtrdma_post_recv,
-	TP_PROTO(
-		const struct rpcrdma_rep *rep
-	),
-
-	TP_ARGS(rep),
-
-	TP_STRUCT__entry(
-		__field(u32, cq_id)
-		__field(int, completion_id)
-	),
-
-	TP_fast_assign(
-		__entry->cq_id = rep->rr_cid.ci_queue_id;
-		__entry->completion_id = rep->rr_cid.ci_completion_id;
-	),
-
-	TP_printk("cq.id=%d cid=%d",
-		__entry->cq_id, __entry->completion_id
-	)
-);
+DEFINE_SIMPLE_CID_EVENT(xprtrdma_post_recv);
 
 TRACE_EVENT(xprtrdma_post_recvs,
 	TP_PROTO(
@@ -2020,31 +1999,11 @@ TRACE_EVENT(svcrdma_post_send,
 	)
 );
 
-DEFINE_SEND_COMPLETION_EVENT(svcrdma_wc_send);
+DEFINE_SIMPLE_CID_EVENT(svcrdma_wc_send);
 DEFINE_SEND_FLUSH_EVENT(svcrdma_wc_send_flush);
 DEFINE_SEND_FLUSH_EVENT(svcrdma_wc_send_err);
 
-TRACE_EVENT(svcrdma_post_recv,
-	TP_PROTO(
-		const struct svc_rdma_recv_ctxt *ctxt
-	),
-
-	TP_ARGS(ctxt),
-
-	TP_STRUCT__entry(
-		__field(u32, cq_id)
-		__field(int, completion_id)
-	),
-
-	TP_fast_assign(
-		__entry->cq_id = ctxt->rc_cid.ci_queue_id;
-		__entry->completion_id = ctxt->rc_cid.ci_completion_id;
-	),
-
-	TP_printk("cq.id=%d cid=%d",
-		__entry->cq_id, __entry->completion_id
-	)
-);
+DEFINE_SIMPLE_CID_EVENT(svcrdma_post_recv);
 
 DEFINE_RECEIVE_SUCCESS_EVENT(svcrdma_wc_recv);
 DEFINE_RECEIVE_FLUSH_EVENT(svcrdma_wc_recv_flush);
@@ -2153,7 +2112,7 @@ TRACE_EVENT(svcrdma_wc_read,
 DEFINE_SEND_FLUSH_EVENT(svcrdma_wc_read_flush);
 DEFINE_SEND_FLUSH_EVENT(svcrdma_wc_read_err);
 
-DEFINE_SEND_COMPLETION_EVENT(svcrdma_wc_write);
+DEFINE_SIMPLE_CID_EVENT(svcrdma_wc_write);
 DEFINE_SEND_FLUSH_EVENT(svcrdma_wc_write_flush);
 DEFINE_SEND_FLUSH_EVENT(svcrdma_wc_write_err);
 
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index c8c1c534070b..72374033bb2b 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -264,7 +264,7 @@ static bool svc_rdma_refresh_recvs(struct svcxprt_rdma *rdma,
 		if (!ctxt)
 			break;
 
-		trace_svcrdma_post_recv(ctxt);
+		trace_svcrdma_post_recv(&ctxt->rc_cid);
 		ctxt->rc_recv_wr.next = recv_chain;
 		recv_chain = &ctxt->rc_recv_wr;
 		rdma->sc_pending_recvs++;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c
index de1ec3220aab..db2a4bd2f7ad 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_rw.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c
@@ -282,7 +282,7 @@ static void svc_rdma_write_done(struct ib_cq *cq, struct ib_wc *wc)
 
 	switch (wc->status) {
 	case IB_WC_SUCCESS:
-		trace_svcrdma_wc_write(wc, &cc->cc_cid);
+		trace_svcrdma_wc_write(&cc->cc_cid);
 		break;
 	case IB_WC_WR_FLUSH_ERR:
 		trace_svcrdma_wc_write_flush(wc, &cc->cc_cid);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 09f5d0570bc9..31b711deab5e 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -305,7 +305,7 @@ static void svc_rdma_wc_send(struct ib_cq *cq, struct ib_wc *wc)
 	if (unlikely(wc->status != IB_WC_SUCCESS))
 		goto flushed;
 
-	trace_svcrdma_wc_send(wc, &ctxt->sc_cid);
+	trace_svcrdma_wc_send(&ctxt->sc_cid);
 	svc_rdma_send_ctxt_put(rdma, ctxt);
 	return;
 
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 28c0771c4e8c..4f8d7efa469f 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -1364,7 +1364,7 @@ void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed, bool temp)
 		}
 
 		rep->rr_cid.ci_queue_id = ep->re_attr.recv_cq->res.id;
-		trace_xprtrdma_post_recv(rep);
+		trace_xprtrdma_post_recv(&rep->rr_cid);
 		rep->rr_recv_wr.next = wr;
 		wr = &rep->rr_recv_wr;
 		--needed;
-- 
cgit v1.2.3


From ad3656bd84e0a91d4505095a0df7fbb6a8e0796a Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Mon, 27 Nov 2023 11:33:37 -0500
Subject: svcrdma: SQ error tracepoints should report completion IDs

Update the Send Queue's error flow tracepoints to report the
completion ID of the waiting or failing context. This ties the
wait/failure to a particular operation or request, which is a little
more useful than knowing only the transport that is about to close.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/trace/events/rpcrdma.h        | 49 +++++++++++++++++++++--------------
 net/sunrpc/xprtrdma/svc_rdma_rw.c     |  6 ++---
 net/sunrpc/xprtrdma/svc_rdma_sendto.c |  6 ++---
 3 files changed, 35 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index b3445e07c151..f1c2022d39ca 100644
--- a/include/trace/events/rpcrdma.h
+++ b/include/trace/events/rpcrdma.h
@@ -2143,65 +2143,74 @@ TRACE_EVENT(svcrdma_qp_error,
 	)
 );
 
-DECLARE_EVENT_CLASS(svcrdma_sendqueue_event,
+DECLARE_EVENT_CLASS(svcrdma_sendqueue_class,
 	TP_PROTO(
-		const struct svcxprt_rdma *rdma
+		const struct svcxprt_rdma *rdma,
+		const struct rpc_rdma_cid *cid
 	),
 
-	TP_ARGS(rdma),
+	TP_ARGS(rdma, cid),
 
 	TP_STRUCT__entry(
+		__field(u32, cq_id)
+		__field(int, completion_id)
 		__field(int, avail)
 		__field(int, depth)
-		__string(addr, rdma->sc_xprt.xpt_remotebuf)
 	),
 
 	TP_fast_assign(
+		__entry->cq_id = cid->ci_queue_id;
+		__entry->completion_id = cid->ci_completion_id;
 		__entry->avail = atomic_read(&rdma->sc_sq_avail);
 		__entry->depth = rdma->sc_sq_depth;
-		__assign_str(addr, rdma->sc_xprt.xpt_remotebuf);
 	),
 
-	TP_printk("addr=%s sc_sq_avail=%d/%d",
-		__get_str(addr), __entry->avail, __entry->depth
+	TP_printk("cq.id=%u cid=%d sc_sq_avail=%d/%d",
+		__entry->cq_id, __entry->completion_id,
+		__entry->avail, __entry->depth
 	)
 );
 
 #define DEFINE_SQ_EVENT(name)						\
-		DEFINE_EVENT(svcrdma_sendqueue_event, svcrdma_sq_##name,\
-				TP_PROTO(				\
-					const struct svcxprt_rdma *rdma \
-				),					\
-				TP_ARGS(rdma))
+		DEFINE_EVENT(svcrdma_sendqueue_class, name,		\
+			TP_PROTO(					\
+				const struct svcxprt_rdma *rdma,	\
+				const struct rpc_rdma_cid *cid		\
+			),						\
+			TP_ARGS(rdma, cid)				\
+		)
 
-DEFINE_SQ_EVENT(full);
-DEFINE_SQ_EVENT(retry);
+DEFINE_SQ_EVENT(svcrdma_sq_full);
+DEFINE_SQ_EVENT(svcrdma_sq_retry);
 
 TRACE_EVENT(svcrdma_sq_post_err,
 	TP_PROTO(
 		const struct svcxprt_rdma *rdma,
+		const struct rpc_rdma_cid *cid,
 		int status
 	),
 
-	TP_ARGS(rdma, status),
+	TP_ARGS(rdma, cid, status),
 
 	TP_STRUCT__entry(
+		__field(u32, cq_id)
+		__field(int, completion_id)
 		__field(int, avail)
 		__field(int, depth)
 		__field(int, status)
-		__string(addr, rdma->sc_xprt.xpt_remotebuf)
 	),
 
 	TP_fast_assign(
+		__entry->cq_id = cid->ci_queue_id;
+		__entry->completion_id = cid->ci_completion_id;
 		__entry->avail = atomic_read(&rdma->sc_sq_avail);
 		__entry->depth = rdma->sc_sq_depth;
 		__entry->status = status;
-		__assign_str(addr, rdma->sc_xprt.xpt_remotebuf);
 	),
 
-	TP_printk("addr=%s sc_sq_avail=%d/%d status=%d",
-		__get_str(addr), __entry->avail, __entry->depth,
-		__entry->status
+	TP_printk("cq.id=%u cid=%d sc_sq_avail=%d/%d status=%d",
+		__entry->cq_id, __entry->completion_id,
+		__entry->avail, __entry->depth, __entry->status
 	)
 );
 
diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c
index db2a4bd2f7ad..b06e49cc55fb 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_rw.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c
@@ -406,14 +406,14 @@ static int svc_rdma_post_chunk_ctxt(struct svc_rdma_chunk_ctxt *cc)
 		}
 
 		percpu_counter_inc(&svcrdma_stat_sq_starve);
-		trace_svcrdma_sq_full(rdma);
+		trace_svcrdma_sq_full(rdma, &cc->cc_cid);
 		atomic_add(cc->cc_sqecount, &rdma->sc_sq_avail);
 		wait_event(rdma->sc_send_wait,
 			   atomic_read(&rdma->sc_sq_avail) > cc->cc_sqecount);
-		trace_svcrdma_sq_retry(rdma);
+		trace_svcrdma_sq_retry(rdma, &cc->cc_cid);
 	} while (1);
 
-	trace_svcrdma_sq_post_err(rdma, ret);
+	trace_svcrdma_sq_post_err(rdma, &cc->cc_cid, ret);
 	svc_xprt_deferred_close(&rdma->sc_xprt);
 
 	/* If even one was posted, there will be a completion. */
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 31b711deab5e..2ee691c45b85 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -343,13 +343,13 @@ int svc_rdma_send(struct svcxprt_rdma *rdma, struct svc_rdma_send_ctxt *ctxt)
 	while (1) {
 		if ((atomic_dec_return(&rdma->sc_sq_avail) < 0)) {
 			percpu_counter_inc(&svcrdma_stat_sq_starve);
-			trace_svcrdma_sq_full(rdma);
+			trace_svcrdma_sq_full(rdma, &ctxt->sc_cid);
 			atomic_inc(&rdma->sc_sq_avail);
 			wait_event(rdma->sc_send_wait,
 				   atomic_read(&rdma->sc_sq_avail) > 1);
 			if (test_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags))
 				return -ENOTCONN;
-			trace_svcrdma_sq_retry(rdma);
+			trace_svcrdma_sq_retry(rdma, &ctxt->sc_cid);
 			continue;
 		}
 
@@ -360,7 +360,7 @@ int svc_rdma_send(struct svcxprt_rdma *rdma, struct svc_rdma_send_ctxt *ctxt)
 		return 0;
 	}
 
-	trace_svcrdma_sq_post_err(rdma, ret);
+	trace_svcrdma_sq_post_err(rdma, &ctxt->sc_cid, ret);
 	svc_xprt_deferred_close(&rdma->sc_xprt);
 	wake_up(&rdma->sc_send_wait);
 	return ret;
-- 
cgit v1.2.3


From 848760a9e701cfab93a71374c1727491b0bc321e Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Mon, 27 Nov 2023 11:33:43 -0500
Subject: svcrdma: DMA error tracepoints should report completion IDs

Update the DMA error flow tracepoints to report the completion ID of
the failing context. This ties the wait/failure to a particular
operation or request, which is more useful than knowing only the
failing transport.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/trace/events/rpcrdma.h    | 74 +++++++++++++++++++--------------------
 net/sunrpc/xprtrdma/svc_rdma_rw.c |  9 ++---
 2 files changed, 42 insertions(+), 41 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index f1c2022d39ca..bba758e5fb1d 100644
--- a/include/trace/events/rpcrdma.h
+++ b/include/trace/events/rpcrdma.h
@@ -1805,33 +1805,37 @@ DEFINE_SVC_DMA_EVENT(dma_unmap_page);
 TRACE_EVENT(svcrdma_dma_map_rw_err,
 	TP_PROTO(
 		const struct svcxprt_rdma *rdma,
+		u64 offset,
+		u32 handle,
 		unsigned int nents,
 		int status
 	),
 
-	TP_ARGS(rdma, nents, status),
+	TP_ARGS(rdma, offset, handle, nents, status),
 
 	TP_STRUCT__entry(
-		__field(int, status)
+		__field(u32, cq_id)
+		__field(u32, handle)
+		__field(u64, offset)
 		__field(unsigned int, nents)
-		__string(device, rdma->sc_cm_id->device->name)
-		__string(addr, rdma->sc_xprt.xpt_remotebuf)
+		__field(int, status)
 	),
 
 	TP_fast_assign(
-		__entry->status = status;
+		__entry->cq_id = rdma->sc_sq_cq->res.id;
+		__entry->handle = handle;
+		__entry->offset = offset;
 		__entry->nents = nents;
-		__assign_str(device, rdma->sc_cm_id->device->name);
-		__assign_str(addr, rdma->sc_xprt.xpt_remotebuf);
+		__entry->status = status;
 	),
 
-	TP_printk("addr=%s device=%s nents=%u status=%d",
-		__get_str(addr), __get_str(device), __entry->nents,
-		__entry->status
+	TP_printk("cq.id=%u 0x%016llx:0x%08x nents=%u status=%d",
+		__entry->cq_id, (unsigned long long)__entry->offset,
+		__entry->handle, __entry->nents, __entry->status
 	)
 );
 
-TRACE_EVENT(svcrdma_no_rwctx_err,
+TRACE_EVENT(svcrdma_rwctx_empty,
 	TP_PROTO(
 		const struct svcxprt_rdma *rdma,
 		unsigned int num_sges
@@ -1840,79 +1844,75 @@ TRACE_EVENT(svcrdma_no_rwctx_err,
 	TP_ARGS(rdma, num_sges),
 
 	TP_STRUCT__entry(
+		__field(u32, cq_id)
 		__field(unsigned int, num_sges)
-		__string(device, rdma->sc_cm_id->device->name)
-		__string(addr, rdma->sc_xprt.xpt_remotebuf)
 	),
 
 	TP_fast_assign(
+		__entry->cq_id = rdma->sc_sq_cq->res.id;
 		__entry->num_sges = num_sges;
-		__assign_str(device, rdma->sc_cm_id->device->name);
-		__assign_str(addr, rdma->sc_xprt.xpt_remotebuf);
 	),
 
-	TP_printk("addr=%s device=%s num_sges=%d",
-		__get_str(addr), __get_str(device), __entry->num_sges
+	TP_printk("cq.id=%u num_sges=%d",
+		__entry->cq_id, __entry->num_sges
 	)
 );
 
 TRACE_EVENT(svcrdma_page_overrun_err,
 	TP_PROTO(
-		const struct svcxprt_rdma *rdma,
-		const struct svc_rqst *rqst,
+		const struct rpc_rdma_cid *cid,
 		unsigned int pageno
 	),
 
-	TP_ARGS(rdma, rqst, pageno),
+	TP_ARGS(cid, pageno),
 
 	TP_STRUCT__entry(
+		__field(u32, cq_id)
+		__field(int, completion_id)
 		__field(unsigned int, pageno)
-		__field(u32, xid)
-		__string(device, rdma->sc_cm_id->device->name)
-		__string(addr, rdma->sc_xprt.xpt_remotebuf)
 	),
 
 	TP_fast_assign(
+		__entry->cq_id = cid->ci_queue_id;
+		__entry->completion_id = cid->ci_completion_id;
 		__entry->pageno = pageno;
-		__entry->xid = __be32_to_cpu(rqst->rq_xid);
-		__assign_str(device, rdma->sc_cm_id->device->name);
-		__assign_str(addr, rdma->sc_xprt.xpt_remotebuf);
 	),
 
-	TP_printk("addr=%s device=%s xid=0x%08x pageno=%u", __get_str(addr),
-		__get_str(device), __entry->xid, __entry->pageno
+	TP_printk("cq.id=%u cid=%d pageno=%u",
+		__entry->cq_id, __entry->completion_id,
+		__entry->pageno
 	)
 );
 
 TRACE_EVENT(svcrdma_small_wrch_err,
 	TP_PROTO(
-		const struct svcxprt_rdma *rdma,
+		const struct rpc_rdma_cid *cid,
 		unsigned int remaining,
 		unsigned int seg_no,
 		unsigned int num_segs
 	),
 
-	TP_ARGS(rdma, remaining, seg_no, num_segs),
+	TP_ARGS(cid, remaining, seg_no, num_segs),
 
 	TP_STRUCT__entry(
+		__field(u32, cq_id)
+		__field(int, completion_id)
 		__field(unsigned int, remaining)
 		__field(unsigned int, seg_no)
 		__field(unsigned int, num_segs)
-		__string(device, rdma->sc_cm_id->device->name)
-		__string(addr, rdma->sc_xprt.xpt_remotebuf)
 	),
 
 	TP_fast_assign(
+		__entry->cq_id = cid->ci_queue_id;
+		__entry->completion_id = cid->ci_completion_id;
 		__entry->remaining = remaining;
 		__entry->seg_no = seg_no;
 		__entry->num_segs = num_segs;
-		__assign_str(device, rdma->sc_cm_id->device->name);
-		__assign_str(addr, rdma->sc_xprt.xpt_remotebuf);
 	),
 
-	TP_printk("addr=%s device=%s remaining=%u seg_no=%u num_segs=%u",
-		__get_str(addr), __get_str(device), __entry->remaining,
-		__entry->seg_no, __entry->num_segs
+	TP_printk("cq.id=%u cid=%d remaining=%u seg_no=%u num_segs=%u",
+		__entry->cq_id, __entry->completion_id,
+		__entry->remaining, __entry->seg_no, __entry->num_segs
 	)
 );
 
diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c
index b06e49cc55fb..c06676714417 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_rw.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c
@@ -80,7 +80,7 @@ svc_rdma_get_rw_ctxt(struct svcxprt_rdma *rdma, unsigned int sges)
 out_free:
 	kfree(ctxt);
 out_noctx:
-	trace_svcrdma_no_rwctx_err(rdma, sges);
+	trace_svcrdma_rwctx_empty(rdma, sges);
 	return NULL;
 }
 
@@ -135,8 +135,9 @@ static int svc_rdma_rw_ctx_init(struct svcxprt_rdma *rdma,
 			       ctxt->rw_sg_table.sgl, ctxt->rw_nents,
 			       0, offset, handle, direction);
 	if (unlikely(ret < 0)) {
+		trace_svcrdma_dma_map_rw_err(rdma, offset, handle,
+					     ctxt->rw_nents, ret);
 		svc_rdma_put_rw_ctxt(rdma, ctxt);
-		trace_svcrdma_dma_map_rw_err(rdma, ctxt->rw_nents, ret);
 	}
 	return ret;
 }
@@ -526,7 +527,7 @@ svc_rdma_build_writes(struct svc_rdma_write_info *info,
 	return 0;
 
 out_overflow:
-	trace_svcrdma_small_wrch_err(rdma, remaining, info->wi_seg_no,
+	trace_svcrdma_small_wrch_err(&cc->cc_cid, remaining, info->wi_seg_no,
 				     info->wi_chunk->ch_segcount);
 	return -E2BIG;
 }
@@ -766,7 +767,7 @@ static int svc_rdma_build_read_segment(struct svc_rdma_read_info *info,
 	return 0;
 
 out_overrun:
-	trace_svcrdma_page_overrun_err(cc->cc_rdma, rqstp, info->ri_pageno);
+	trace_svcrdma_page_overrun_err(&cc->cc_cid, info->ri_pageno);
 	return -EINVAL;
 }
 
-- 
cgit v1.2.3


From 2dd6e29a3ea86ce51404589fd99597cd4dd0cd41 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Mon, 27 Nov 2023 11:33:50 -0500
Subject: svcrdma: Update some svcrdma DMA-related tracepoints

A send/recv_ctxt already records transport-related information
in the cq.id, thus there is no need to record the IP addresses of
the transport endpoints.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/trace/events/rpcrdma.h        | 21 +++++++++++----------
 net/sunrpc/xprtrdma/svc_rdma_sendto.c | 10 +++++-----
 2 files changed, 16 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index bba758e5fb1d..9a3fc6eb09a8 100644
--- a/include/trace/events/rpcrdma.h
+++ b/include/trace/events/rpcrdma.h
@@ -1762,29 +1762,29 @@ DEFINE_ERROR_EVENT(chunk);
 
 DECLARE_EVENT_CLASS(svcrdma_dma_map_class,
 	TP_PROTO(
-		const struct svcxprt_rdma *rdma,
+		const struct rpc_rdma_cid *cid,
 		u64 dma_addr,
 		u32 length
 	),
 
-	TP_ARGS(rdma, dma_addr, length),
+	TP_ARGS(cid, dma_addr, length),
 
 	TP_STRUCT__entry(
+		__field(u32, cq_id)
+		__field(int, completion_id)
 		__field(u64, dma_addr)
 		__field(u32, length)
-		__string(device, rdma->sc_cm_id->device->name)
-		__string(addr, rdma->sc_xprt.xpt_remotebuf)
 	),
 
 	TP_fast_assign(
+		__entry->cq_id = cid->ci_queue_id;
+		__entry->completion_id = cid->ci_completion_id;
 		__entry->dma_addr = dma_addr;
 		__entry->length = length;
-		__assign_str(device, rdma->sc_cm_id->device->name);
-		__assign_str(addr, rdma->sc_xprt.xpt_remotebuf);
 	),
 
-	TP_printk("addr=%s device=%s dma_addr=%llu length=%u",
-		__get_str(addr), __get_str(device),
+	TP_printk("cq.id=%u cid=%d dma_addr=%llu length=%u",
+		__entry->cq_id, __entry->completion_id,
 		__entry->dma_addr, __entry->length
 	)
 );
@@ -1792,11 +1792,12 @@ DECLARE_EVENT_CLASS(svcrdma_dma_map_class,
 #define DEFINE_SVC_DMA_EVENT(name)					\
 		DEFINE_EVENT(svcrdma_dma_map_class, svcrdma_##name,	\
 				TP_PROTO(				\
-					const struct svcxprt_rdma *rdma,\
+					const struct rpc_rdma_cid *cid, \
 					u64 dma_addr,			\
 					u32 length			\
 				),					\
-				TP_ARGS(rdma, dma_addr, length))
+				TP_ARGS(cid, dma_addr, length)		\
+		)
 
 DEFINE_SVC_DMA_EVENT(dma_map_page);
 DEFINE_SVC_DMA_EVENT(dma_map_err);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 2ee691c45b85..9571ed4a74d4 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -237,13 +237,13 @@ static void svc_rdma_send_ctxt_release(struct svcxprt_rdma *rdma,
 	 * remains mapped until @ctxt is destroyed.
 	 */
 	for (i = 1; i < ctxt->sc_send_wr.num_sge; i++) {
+		trace_svcrdma_dma_unmap_page(&ctxt->sc_cid,
+					     ctxt->sc_sges[i].addr,
+					     ctxt->sc_sges[i].length);
 		ib_dma_unmap_page(device,
 				  ctxt->sc_sges[i].addr,
 				  ctxt->sc_sges[i].length,
 				  DMA_TO_DEVICE);
-		trace_svcrdma_dma_unmap_page(rdma,
-					     ctxt->sc_sges[i].addr,
-					     ctxt->sc_sges[i].length);
 	}
 
 	llist_add(&ctxt->sc_node, &rdma->sc_send_ctxts);
@@ -550,14 +550,14 @@ static int svc_rdma_page_dma_map(void *data, struct page *page,
 	if (ib_dma_mapping_error(dev, dma_addr))
 		goto out_maperr;
 
-	trace_svcrdma_dma_map_page(rdma, dma_addr, len);
+	trace_svcrdma_dma_map_page(&ctxt->sc_cid, dma_addr, len);
 	ctxt->sc_sges[ctxt->sc_cur_sge_no].addr = dma_addr;
 	ctxt->sc_sges[ctxt->sc_cur_sge_no].length = len;
 	ctxt->sc_send_wr.num_sge++;
 	return 0;
 
 out_maperr:
-	trace_svcrdma_dma_map_err(rdma, dma_addr, len);
+	trace_svcrdma_dma_map_err(&ctxt->sc_cid, dma_addr, len);
 	return -EIO;
 }
 
-- 
cgit v1.2.3


From 6a04a4349330c5476adf465159a7f49411091bbe Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Mon, 4 Dec 2023 09:57:09 -0500
Subject: svcrdma: Move struct svc_rdma_chunk_ctxt to svc_rdma.h

Prepare for nestling these into the send and recv ctxts so they
no longer have to be allocated dynamically.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/svc_rdma.h   | 15 +++++++++++++++
 net/sunrpc/xprtrdma/svc_rdma_rw.c | 18 ------------------
 2 files changed, 15 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index ab250017b99f..50c4f18a9b7f 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -127,6 +127,21 @@ enum {
 
 #define RPCSVC_MAXPAYLOAD_RDMA	RPCSVC_MAXPAYLOAD
 
+/*
+ * A chunk context tracks all I/O for moving one Read or Write
+ * chunk. This is a set of rdma_rw's that handle data movement
+ * for all segments of one chunk.
+ */
+struct svc_rdma_chunk_ctxt {
+	struct rpc_rdma_cid	cc_cid;
+	struct ib_cqe		cc_cqe;
+	struct list_head	cc_rwctxts;
+	ktime_t			cc_posttime;
+	int			cc_sqecount;
+	enum ib_wc_status	cc_status;
+	struct completion	cc_done;
+};
+
 struct svc_rdma_recv_ctxt {
 	struct llist_node	rc_node;
 	struct list_head	rc_list;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c
index cfa5973c9277..1de56e9fea91 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_rw.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c
@@ -146,24 +146,6 @@ static int svc_rdma_rw_ctx_init(struct svcxprt_rdma *rdma,
 	return ret;
 }
 
-/* A chunk context tracks all I/O for moving one Read or Write
- * chunk. This is a set of rdma_rw's that handle data movement
- * for all segments of one chunk.
- *
- * These are small, acquired with a single allocator call, and
- * no more than one is needed per chunk. They are allocated on
- * demand, and not cached.
- */
-struct svc_rdma_chunk_ctxt {
-	struct rpc_rdma_cid	cc_cid;
-	struct ib_cqe		cc_cqe;
-	struct list_head	cc_rwctxts;
-	ktime_t			cc_posttime;
-	int			cc_sqecount;
-	enum ib_wc_status	cc_status;
-	struct completion	cc_done;
-};
-
 static void svc_rdma_cc_cid_init(struct svcxprt_rdma *rdma,
 				 struct rpc_rdma_cid *cid)
 {
-- 
cgit v1.2.3


From b1818412d06fc03605d02dbdd4a7c53dc9e2d5ba Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Mon, 4 Dec 2023 09:57:16 -0500
Subject: svcrdma: Start moving fields out of struct svc_rdma_read_info

Since the request's svc_rdma_recv_ctxt will stay around for the
duration of the RDMA Read operation, the contents of struct
svc_rdma_read_info can reside in the request's svc_rdma_recv_ctxt
rather than being allocated separately. This will eventually save a
call to kmalloc() in a hot path.

Start this clean-up by moving the Read chunk's svc_rdma_chunk_ctxt.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/svc_rdma.h   |  4 +++
 net/sunrpc/xprtrdma/svc_rdma_rw.c | 57 ++++++++++++++++++---------------------
 2 files changed, 30 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 50c4f18a9b7f..6c7501ae4e29 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -156,6 +156,10 @@ struct svc_rdma_recv_ctxt {
 	u32			rc_inv_rkey;
 	__be32			rc_msgtype;
 
+	/* State for pulling a Read chunk */
+	unsigned int		rc_readbytes;
+	struct svc_rdma_chunk_ctxt	rc_cc;
+
 	struct svc_rdma_pcl	rc_call_pcl;
 
 	struct svc_rdma_pcl	rc_read_pcl;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c
index 1de56e9fea91..a27b8f338ae5 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_rw.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c
@@ -294,9 +294,6 @@ struct svc_rdma_read_info {
 	struct svc_rdma_recv_ctxt	*ri_readctxt;
 	unsigned int			ri_pageno;
 	unsigned int			ri_pageoff;
-	unsigned int			ri_totalbytes;
-
-	struct svc_rdma_chunk_ctxt	ri_cc;
 };
 
 static struct svc_rdma_read_info *
@@ -304,20 +301,13 @@ svc_rdma_read_info_alloc(struct svcxprt_rdma *rdma)
 {
 	struct svc_rdma_read_info *info;
 
-	info = kmalloc_node(sizeof(*info), GFP_KERNEL,
+	return kmalloc_node(sizeof(*info), GFP_KERNEL,
 			    ibdev_to_node(rdma->sc_cm_id->device));
-	if (!info)
-		return info;
-
-	svc_rdma_cc_init(rdma, &info->ri_cc);
-	info->ri_cc.cc_cqe.done = svc_rdma_wc_read_done;
-	return info;
 }
 
 static void svc_rdma_read_info_free(struct svcxprt_rdma *rdma,
 				    struct svc_rdma_read_info *info)
 {
-	svc_rdma_cc_release(rdma, &info->ri_cc, DMA_FROM_DEVICE);
 	kfree(info);
 }
 
@@ -333,12 +323,12 @@ static void svc_rdma_wc_read_done(struct ib_cq *cq, struct ib_wc *wc)
 	struct ib_cqe *cqe = wc->wr_cqe;
 	struct svc_rdma_chunk_ctxt *cc =
 			container_of(cqe, struct svc_rdma_chunk_ctxt, cc_cqe);
-	struct svc_rdma_read_info *info;
+	struct svc_rdma_recv_ctxt *ctxt;
 
 	switch (wc->status) {
 	case IB_WC_SUCCESS:
-		info = container_of(cc, struct svc_rdma_read_info, ri_cc);
-		trace_svcrdma_wc_read(wc, &cc->cc_cid, info->ri_totalbytes,
+		ctxt = container_of(cc, struct svc_rdma_recv_ctxt, rc_cc);
+		trace_svcrdma_wc_read(wc, &cc->cc_cid, ctxt->rc_readbytes,
 				      cc->cc_posttime);
 		break;
 	case IB_WC_WR_FLUSH_ERR:
@@ -708,7 +698,7 @@ static int svc_rdma_build_read_segment(struct svcxprt_rdma *rdma,
 				       const struct svc_rdma_segment *segment)
 {
 	struct svc_rdma_recv_ctxt *head = info->ri_readctxt;
-	struct svc_rdma_chunk_ctxt *cc = &info->ri_cc;
+	struct svc_rdma_chunk_ctxt *cc = &head->rc_cc;
 	struct svc_rqst *rqstp = info->ri_rqst;
 	unsigned int sge_no, seg_len, len;
 	struct svc_rdma_rw_ctxt *ctxt;
@@ -778,6 +768,7 @@ static int svc_rdma_build_read_chunk(struct svcxprt_rdma *rdma,
 				     struct svc_rdma_read_info *info,
 				     const struct svc_rdma_chunk *chunk)
 {
+	struct svc_rdma_recv_ctxt *head = info->ri_readctxt;
 	const struct svc_rdma_segment *segment;
 	int ret;
 
@@ -786,7 +777,7 @@ static int svc_rdma_build_read_chunk(struct svcxprt_rdma *rdma,
 		ret = svc_rdma_build_read_segment(rdma, info, segment);
 		if (ret < 0)
 			break;
-		info->ri_totalbytes += segment->rs_length;
+		head->rc_readbytes += segment->rs_length;
 	}
 	return ret;
 }
@@ -828,7 +819,7 @@ static int svc_rdma_copy_inline_range(struct svc_rdma_read_info *info,
 		dst = page_address(rqstp->rq_pages[info->ri_pageno]);
 		memcpy(dst + info->ri_pageno, src + offset, page_len);
 
-		info->ri_totalbytes += page_len;
+		head->rc_readbytes += page_len;
 		info->ri_pageoff += page_len;
 		if (info->ri_pageoff == PAGE_SIZE) {
 			info->ri_pageno++;
@@ -883,7 +874,7 @@ static noinline int svc_rdma_read_multiple_chunks(struct svcxprt_rdma *rdma,
 			break;
 
 		start += length;
-		length = next->ch_position - info->ri_totalbytes;
+		length = next->ch_position - head->rc_readbytes;
 		ret = svc_rdma_copy_inline_range(info, start, length);
 		if (ret < 0)
 			return ret;
@@ -895,13 +886,13 @@ static noinline int svc_rdma_read_multiple_chunks(struct svcxprt_rdma *rdma,
 	if (ret < 0)
 		return ret;
 
-	buf->len += info->ri_totalbytes;
-	buf->buflen += info->ri_totalbytes;
+	buf->len += head->rc_readbytes;
+	buf->buflen += head->rc_readbytes;
 
 	buf->head[0].iov_base = page_address(info->ri_rqst->rq_pages[0]);
-	buf->head[0].iov_len = min_t(size_t, PAGE_SIZE, info->ri_totalbytes);
+	buf->head[0].iov_len = min_t(size_t, PAGE_SIZE, head->rc_readbytes);
 	buf->pages = &info->ri_rqst->rq_pages[1];
-	buf->page_len = info->ri_totalbytes - buf->head[0].iov_len;
+	buf->page_len = head->rc_readbytes - buf->head[0].iov_len;
 	return 0;
 }
 
@@ -985,6 +976,7 @@ static int svc_rdma_read_chunk_range(struct svcxprt_rdma *rdma,
 				     const struct svc_rdma_chunk *chunk,
 				     unsigned int offset, unsigned int length)
 {
+	struct svc_rdma_recv_ctxt *head = info->ri_readctxt;
 	const struct svc_rdma_segment *segment;
 	int ret;
 
@@ -1005,7 +997,7 @@ static int svc_rdma_read_chunk_range(struct svcxprt_rdma *rdma,
 		if (ret < 0)
 			break;
 
-		info->ri_totalbytes += dummy.rs_length;
+		head->rc_readbytes += dummy.rs_length;
 		length -= dummy.rs_length;
 		offset = 0;
 	}
@@ -1055,7 +1047,7 @@ static int svc_rdma_read_call_chunk(struct svcxprt_rdma *rdma,
 			break;
 
 		start += length;
-		length = next->ch_position - info->ri_totalbytes;
+		length = next->ch_position - head->rc_readbytes;
 		ret = svc_rdma_read_chunk_range(rdma, info, call_chunk,
 						start, length);
 		if (ret < 0)
@@ -1089,6 +1081,7 @@ static int svc_rdma_read_call_chunk(struct svcxprt_rdma *rdma,
 static noinline int svc_rdma_read_special(struct svcxprt_rdma *rdma,
 					  struct svc_rdma_read_info *info)
 {
+	struct svc_rdma_recv_ctxt *head = info->ri_readctxt;
 	struct xdr_buf *buf = &info->ri_rqst->rq_arg;
 	int ret;
 
@@ -1096,13 +1089,13 @@ static noinline int svc_rdma_read_special(struct svcxprt_rdma *rdma,
 	if (ret < 0)
 		goto out;
 
-	buf->len += info->ri_totalbytes;
-	buf->buflen += info->ri_totalbytes;
+	buf->len += head->rc_readbytes;
+	buf->buflen += head->rc_readbytes;
 
 	buf->head[0].iov_base = page_address(info->ri_rqst->rq_pages[0]);
-	buf->head[0].iov_len = min_t(size_t, PAGE_SIZE, info->ri_totalbytes);
+	buf->head[0].iov_len = min_t(size_t, PAGE_SIZE, head->rc_readbytes);
 	buf->pages = &info->ri_rqst->rq_pages[1];
-	buf->page_len = info->ri_totalbytes - buf->head[0].iov_len;
+	buf->page_len = head->rc_readbytes - buf->head[0].iov_len;
 
 out:
 	return ret;
@@ -1135,19 +1128,20 @@ int svc_rdma_process_read_list(struct svcxprt_rdma *rdma,
 			       struct svc_rqst *rqstp,
 			       struct svc_rdma_recv_ctxt *head)
 {
+	struct svc_rdma_chunk_ctxt *cc = &head->rc_cc;
 	struct svc_rdma_read_info *info;
-	struct svc_rdma_chunk_ctxt *cc;
 	int ret;
 
 	info = svc_rdma_read_info_alloc(rdma);
 	if (!info)
 		return -ENOMEM;
-	cc = &info->ri_cc;
 	info->ri_rqst = rqstp;
 	info->ri_readctxt = head;
 	info->ri_pageno = 0;
 	info->ri_pageoff = 0;
-	info->ri_totalbytes = 0;
+	svc_rdma_cc_init(rdma, cc);
+	cc->cc_cqe.done = svc_rdma_wc_read_done;
+	head->rc_readbytes = 0;
 
 	if (pcl_is_empty(&head->rc_call_pcl)) {
 		if (head->rc_read_pcl.cl_count == 1)
@@ -1178,6 +1172,7 @@ int svc_rdma_process_read_list(struct svcxprt_rdma *rdma,
 	head->rc_page_count = 0;
 
 out_err:
+	svc_rdma_cc_release(rdma, cc, DMA_FROM_DEVICE);
 	svc_rdma_read_info_free(rdma, info);
 	return ret;
 }
-- 
cgit v1.2.3


From 8e122582680c6f8acd686a5a2af9c0e46fe90f2d Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Mon, 4 Dec 2023 09:57:22 -0500
Subject: svcrdma: Move svc_rdma_read_info::ri_pageno to struct
 svc_rdma_recv_ctxt

Further clean up: move the page index field into svc_rdma_recv_ctxt.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/svc_rdma.h   |  1 +
 net/sunrpc/xprtrdma/svc_rdma_rw.c | 21 +++++++++------------
 2 files changed, 10 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 6c7501ae4e29..0ea66f73bec2 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -157,6 +157,7 @@ struct svc_rdma_recv_ctxt {
 	__be32			rc_msgtype;
 
 	/* State for pulling a Read chunk */
+	unsigned int		rc_curpage;
 	unsigned int		rc_readbytes;
 	struct svc_rdma_chunk_ctxt	rc_cc;
 
diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c
index a27b8f338ae5..487acb192558 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_rw.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c
@@ -292,7 +292,6 @@ static void svc_rdma_write_done(struct ib_cq *cq, struct ib_wc *wc)
 struct svc_rdma_read_info {
 	struct svc_rqst			*ri_rqst;
 	struct svc_rdma_recv_ctxt	*ri_readctxt;
-	unsigned int			ri_pageno;
 	unsigned int			ri_pageoff;
 };
 
@@ -720,20 +719,18 @@ static int svc_rdma_build_read_segment(struct svcxprt_rdma *rdma,
 		if (!info->ri_pageoff)
 			head->rc_page_count++;
 
-		sg_set_page(sg, rqstp->rq_pages[info->ri_pageno],
+		sg_set_page(sg, rqstp->rq_pages[head->rc_curpage],
 			    seg_len, info->ri_pageoff);
 		sg = sg_next(sg);
 
 		info->ri_pageoff += seg_len;
 		if (info->ri_pageoff == PAGE_SIZE) {
-			info->ri_pageno++;
+			head->rc_curpage++;
 			info->ri_pageoff = 0;
 		}
 		len -= seg_len;
 
-		/* Safety check */
-		if (len &&
-		    &rqstp->rq_pages[info->ri_pageno + 1] > rqstp->rq_page_end)
+		if (len && ((head->rc_curpage + 1) > ARRAY_SIZE(rqstp->rq_pages)))
 			goto out_overrun;
 	}
 
@@ -748,7 +745,7 @@ static int svc_rdma_build_read_segment(struct svcxprt_rdma *rdma,
 	return 0;
 
 out_overrun:
-	trace_svcrdma_page_overrun_err(&cc->cc_cid, info->ri_pageno);
+	trace_svcrdma_page_overrun_err(&cc->cc_cid, head->rc_curpage);
 	return -EINVAL;
 }
 
@@ -790,7 +787,7 @@ static int svc_rdma_build_read_chunk(struct svcxprt_rdma *rdma,
  *
  * Take a page at a time from rqstp->rq_pages and copy the inline
  * content from the Receive buffer into that page. Update
- * info->ri_pageno and info->ri_pageoff so that the next RDMA Read
+ * head->rc_curpage and info->ri_pageoff so that the next RDMA Read
  * result will land contiguously with the copied content.
  *
  * Return values:
@@ -816,13 +813,13 @@ static int svc_rdma_copy_inline_range(struct svc_rdma_read_info *info,
 		if (!info->ri_pageoff)
 			head->rc_page_count++;
 
-		dst = page_address(rqstp->rq_pages[info->ri_pageno]);
-		memcpy(dst + info->ri_pageno, src + offset, page_len);
+		dst = page_address(rqstp->rq_pages[head->rc_curpage]);
+		memcpy(dst + head->rc_curpage, src + offset, page_len);
 
 		head->rc_readbytes += page_len;
 		info->ri_pageoff += page_len;
 		if (info->ri_pageoff == PAGE_SIZE) {
-			info->ri_pageno++;
+			head->rc_curpage++;
 			info->ri_pageoff = 0;
 		}
 		remaining -= page_len;
@@ -1137,10 +1134,10 @@ int svc_rdma_process_read_list(struct svcxprt_rdma *rdma,
 		return -ENOMEM;
 	info->ri_rqst = rqstp;
 	info->ri_readctxt = head;
-	info->ri_pageno = 0;
 	info->ri_pageoff = 0;
 	svc_rdma_cc_init(rdma, cc);
 	cc->cc_cqe.done = svc_rdma_wc_read_done;
+	head->rc_curpage = 0;
 	head->rc_readbytes = 0;
 
 	if (pcl_is_empty(&head->rc_call_pcl)) {
-- 
cgit v1.2.3


From 919f6e790ab6cca772fa60c6006162c0a7ebbfc5 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Mon, 4 Dec 2023 09:57:28 -0500
Subject: svcrdma: Move read_info::ri_pageoff into struct svc_rdma_recv_ctxt

Further clean up: move the starting byte offset field into
svc_rdma_recv_ctxt.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/svc_rdma.h   |  1 +
 net/sunrpc/xprtrdma/svc_rdma_rw.c | 31 +++++++++++++++----------------
 2 files changed, 16 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 0ea66f73bec2..44a14eaf8c40 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -157,6 +157,7 @@ struct svc_rdma_recv_ctxt {
 	__be32			rc_msgtype;
 
 	/* State for pulling a Read chunk */
+	unsigned int		rc_pageoff;
 	unsigned int		rc_curpage;
 	unsigned int		rc_readbytes;
 	struct svc_rdma_chunk_ctxt	rc_cc;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c
index 487acb192558..dbced8970779 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_rw.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c
@@ -292,7 +292,6 @@ static void svc_rdma_write_done(struct ib_cq *cq, struct ib_wc *wc)
 struct svc_rdma_read_info {
 	struct svc_rqst			*ri_rqst;
 	struct svc_rdma_recv_ctxt	*ri_readctxt;
-	unsigned int			ri_pageoff;
 };
 
 static struct svc_rdma_read_info *
@@ -705,7 +704,7 @@ static int svc_rdma_build_read_segment(struct svcxprt_rdma *rdma,
 	int ret;
 
 	len = segment->rs_length;
-	sge_no = PAGE_ALIGN(info->ri_pageoff + len) >> PAGE_SHIFT;
+	sge_no = PAGE_ALIGN(head->rc_pageoff + len) >> PAGE_SHIFT;
 	ctxt = svc_rdma_get_rw_ctxt(rdma, sge_no);
 	if (!ctxt)
 		return -ENOMEM;
@@ -714,19 +713,19 @@ static int svc_rdma_build_read_segment(struct svcxprt_rdma *rdma,
 	sg = ctxt->rw_sg_table.sgl;
 	for (sge_no = 0; sge_no < ctxt->rw_nents; sge_no++) {
 		seg_len = min_t(unsigned int, len,
-				PAGE_SIZE - info->ri_pageoff);
+				PAGE_SIZE - head->rc_pageoff);
 
-		if (!info->ri_pageoff)
+		if (!head->rc_pageoff)
 			head->rc_page_count++;
 
 		sg_set_page(sg, rqstp->rq_pages[head->rc_curpage],
-			    seg_len, info->ri_pageoff);
+			    seg_len, head->rc_pageoff);
 		sg = sg_next(sg);
 
-		info->ri_pageoff += seg_len;
-		if (info->ri_pageoff == PAGE_SIZE) {
+		head->rc_pageoff += seg_len;
+		if (head->rc_pageoff == PAGE_SIZE) {
 			head->rc_curpage++;
-			info->ri_pageoff = 0;
+			head->rc_pageoff = 0;
 		}
 		len -= seg_len;
 
@@ -787,7 +786,7 @@ static int svc_rdma_build_read_chunk(struct svcxprt_rdma *rdma,
  *
  * Take a page at a time from rqstp->rq_pages and copy the inline
  * content from the Receive buffer into that page. Update
- * head->rc_curpage and info->ri_pageoff so that the next RDMA Read
+ * head->rc_curpage and head->rc_pageoff so that the next RDMA Read
  * result will land contiguously with the copied content.
  *
  * Return values:
@@ -803,24 +802,24 @@ static int svc_rdma_copy_inline_range(struct svc_rdma_read_info *info,
 	struct svc_rqst *rqstp = info->ri_rqst;
 	unsigned int page_no, numpages;
 
-	numpages = PAGE_ALIGN(info->ri_pageoff + remaining) >> PAGE_SHIFT;
+	numpages = PAGE_ALIGN(head->rc_pageoff + remaining) >> PAGE_SHIFT;
 	for (page_no = 0; page_no < numpages; page_no++) {
 		unsigned int page_len;
 
 		page_len = min_t(unsigned int, remaining,
-				 PAGE_SIZE - info->ri_pageoff);
+				 PAGE_SIZE - head->rc_pageoff);
 
-		if (!info->ri_pageoff)
+		if (!head->rc_pageoff)
 			head->rc_page_count++;
 
 		dst = page_address(rqstp->rq_pages[head->rc_curpage]);
 		memcpy(dst + head->rc_curpage, src + offset, page_len);
 
 		head->rc_readbytes += page_len;
-		info->ri_pageoff += page_len;
-		if (info->ri_pageoff == PAGE_SIZE) {
+		head->rc_pageoff += page_len;
+		if (head->rc_pageoff == PAGE_SIZE) {
 			head->rc_curpage++;
-			info->ri_pageoff = 0;
+			head->rc_pageoff = 0;
 		}
 		remaining -= page_len;
 		offset += page_len;
@@ -1134,9 +1133,9 @@ int svc_rdma_process_read_list(struct svcxprt_rdma *rdma,
 		return -ENOMEM;
 	info->ri_rqst = rqstp;
 	info->ri_readctxt = head;
-	info->ri_pageoff = 0;
 	svc_rdma_cc_init(rdma, cc);
 	cc->cc_cqe.done = svc_rdma_wc_read_done;
+	head->rc_pageoff = 0;
 	head->rc_curpage = 0;
 	head->rc_readbytes = 0;
 
-- 
cgit v1.2.3


From fc20f19b4df4a46d1003d15d84148a117e8bdf5d Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Mon, 4 Dec 2023 09:57:35 -0500
Subject: svcrdma: Update synopsis of svc_rdma_build_read_segment()

Since the RDMA Read I/O state is now contained in the recv_ctxt,
svc_rdma_build_read_segment() can use the recv_ctxt to derive that
information rather than the other way around. This removes one usage
of the ri_readctxt field, enabling its removal in a subsequent
patch.

At the same time, the use of ri_rqst can similarly be replaced with
a passed-in function parameter.

Start with build_read_segment() because it is a common utility
function at the bottom of the Read chunk path.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/svc_rdma.h   |  7 +++++++
 net/sunrpc/xprtrdma/svc_rdma_rw.c | 17 +++++++++--------
 2 files changed, 16 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 44a14eaf8c40..f03f9909fb97 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -116,6 +116,13 @@ struct svcxprt_rdma {
 /* sc_flags */
 #define RDMAXPRT_CONN_PENDING	3
 
+static inline struct svcxprt_rdma *svc_rdma_rqst_rdma(struct svc_rqst *rqstp)
+{
+	struct svc_xprt *xprt = rqstp->rq_xprt;
+
+	return container_of(xprt, struct svcxprt_rdma, sc_xprt);
+}
+
 /*
  * Default connection parameters
  */
diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c
index dbced8970779..c2d0e4bb454e 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_rw.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c
@@ -681,8 +681,8 @@ out_err:
 
 /**
  * svc_rdma_build_read_segment - Build RDMA Read WQEs to pull one RDMA segment
- * @rdma: controlling transport
- * @info: context for ongoing I/O
+ * @rqstp: RPC transaction context
+ * @head: context for ongoing I/O
  * @segment: co-ordinates of remote memory to be read
  *
  * Returns:
@@ -691,13 +691,12 @@ out_err:
  *   %-ENOMEM: allocating a local resources failed
  *   %-EIO: a DMA mapping error occurred
  */
-static int svc_rdma_build_read_segment(struct svcxprt_rdma *rdma,
-				       struct svc_rdma_read_info *info,
+static int svc_rdma_build_read_segment(struct svc_rqst *rqstp,
+				       struct svc_rdma_recv_ctxt *head,
 				       const struct svc_rdma_segment *segment)
 {
-	struct svc_rdma_recv_ctxt *head = info->ri_readctxt;
+	struct svcxprt_rdma *rdma = svc_rdma_rqst_rdma(rqstp);
 	struct svc_rdma_chunk_ctxt *cc = &head->rc_cc;
-	struct svc_rqst *rqstp = info->ri_rqst;
 	unsigned int sge_no, seg_len, len;
 	struct svc_rdma_rw_ctxt *ctxt;
 	struct scatterlist *sg;
@@ -770,7 +769,8 @@ static int svc_rdma_build_read_chunk(struct svcxprt_rdma *rdma,
 
 	ret = -EINVAL;
 	pcl_for_each_segment(segment, chunk) {
-		ret = svc_rdma_build_read_segment(rdma, info, segment);
+		ret = svc_rdma_build_read_segment(info->ri_rqst,
+						  info->ri_readctxt, segment);
 		if (ret < 0)
 			break;
 		head->rc_readbytes += segment->rs_length;
@@ -989,7 +989,8 @@ static int svc_rdma_read_chunk_range(struct svcxprt_rdma *rdma,
 		dummy.rs_length = min_t(u32, length, segment->rs_length) - offset;
 		dummy.rs_offset = segment->rs_offset + offset;
 
-		ret = svc_rdma_build_read_segment(rdma, info, &dummy);
+		ret = svc_rdma_build_read_segment(info->ri_rqst,
+						  info->ri_readctxt, &dummy);
 		if (ret < 0)
 			break;
 
-- 
cgit v1.2.3


From 018f34051bc9f4908336b3fe9e52931bb8410ced Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Mon, 4 Dec 2023 09:58:33 -0500
Subject: svcrdma: Move the svc_rdma_cc_init() call

Now that the chunk_ctxt for Reads is no longer dynamically allocated
it can be initialized once for the life of the object that contains
it (struct svc_rdma_recv_ctxt).

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/svc_rdma.h         |  2 ++
 net/sunrpc/xprtrdma/svc_rdma_recvfrom.c |  1 +
 net/sunrpc/xprtrdma/svc_rdma_rw.c       | 11 ++++++++---
 3 files changed, 11 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index f03f9909fb97..051fefde8d51 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -211,6 +211,8 @@ extern int svc_rdma_recvfrom(struct svc_rqst *);
 
 /* svc_rdma_rw.c */
 extern void svc_rdma_destroy_rw_ctxts(struct svcxprt_rdma *rdma);
+extern void svc_rdma_cc_init(struct svcxprt_rdma *rdma,
+			     struct svc_rdma_chunk_ctxt *cc);
 extern int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma,
 				     const struct svc_rdma_chunk *chunk,
 				     const struct xdr_buf *xdr);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 72374033bb2b..392a91dc8a99 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -156,6 +156,7 @@ svc_rdma_recv_ctxt_alloc(struct svcxprt_rdma *rdma)
 	ctxt->rc_recv_sge.length = rdma->sc_max_req_size;
 	ctxt->rc_recv_sge.lkey = rdma->sc_pd->local_dma_lkey;
 	ctxt->rc_recv_buf = buffer;
+	svc_rdma_cc_init(rdma, &ctxt->rc_cc);
 	return ctxt;
 
 fail2:
diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c
index 0ccb21f1089e..4d2db06ccfd2 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_rw.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c
@@ -153,8 +153,13 @@ static void svc_rdma_cc_cid_init(struct svcxprt_rdma *rdma,
 	cid->ci_completion_id = atomic_inc_return(&rdma->sc_completion_ids);
 }
 
-static void svc_rdma_cc_init(struct svcxprt_rdma *rdma,
-			     struct svc_rdma_chunk_ctxt *cc)
+/**
+ * svc_rdma_cc_init - Initialize an svc_rdma_chunk_ctxt
+ * @rdma: controlling transport instance
+ * @cc: svc_rdma_chunk_ctxt to be initialized
+ */
+void svc_rdma_cc_init(struct svcxprt_rdma *rdma,
+		      struct svc_rdma_chunk_ctxt *cc)
 {
 	svc_rdma_cc_cid_init(rdma, &cc->cc_cid);
 
@@ -1101,8 +1106,8 @@ int svc_rdma_process_read_list(struct svcxprt_rdma *rdma,
 	struct svc_rdma_chunk_ctxt *cc = &head->rc_cc;
 	int ret;
 
-	svc_rdma_cc_init(rdma, cc);
 	cc->cc_cqe.done = svc_rdma_wc_read_done;
+	cc->cc_sqecount = 0;
 	head->rc_pageoff = 0;
 	head->rc_curpage = 0;
 	head->rc_readbytes = 0;
-- 
cgit v1.2.3


From 28ee0ec8948ac235327a1f5472fc032b308284a3 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Mon, 11 Dec 2023 10:24:08 -0500
Subject: svcrdma: De-duplicate completion ID initialization helpers

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/svc_rdma.h         | 24 ++++++++++++++++++++++++
 net/sunrpc/xprtrdma/svc_rdma_recvfrom.c |  7 -------
 net/sunrpc/xprtrdma/svc_rdma_rw.c       |  9 +--------
 net/sunrpc/xprtrdma/svc_rdma_sendto.c   |  7 -------
 4 files changed, 25 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 051fefde8d51..46f2ce9f810b 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -134,6 +134,30 @@ enum {
 
 #define RPCSVC_MAXPAYLOAD_RDMA	RPCSVC_MAXPAYLOAD
 
+/**
+ * svc_rdma_send_cid_init - Initialize a Receive Queue completion ID
+ * @rdma: controlling transport
+ * @cid: completion ID to initialize
+ */
+static inline void svc_rdma_recv_cid_init(struct svcxprt_rdma *rdma,
+					  struct rpc_rdma_cid *cid)
+{
+	cid->ci_queue_id = rdma->sc_rq_cq->res.id;
+	cid->ci_completion_id = atomic_inc_return(&rdma->sc_completion_ids);
+}
+
+/**
+ * svc_rdma_send_cid_init - Initialize a Send Queue completion ID
+ * @rdma: controlling transport
+ * @cid: completion ID to initialize
+ */
+static inline void svc_rdma_send_cid_init(struct svcxprt_rdma *rdma,
+					  struct rpc_rdma_cid *cid)
+{
+	cid->ci_queue_id = rdma->sc_sq_cq->res.id;
+	cid->ci_completion_id = atomic_inc_return(&rdma->sc_completion_ids);
+}
+
 /*
  * A chunk context tracks all I/O for moving one Read or Write
  * chunk. This is a set of rdma_rw's that handle data movement
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 392a91dc8a99..ac6351e292c5 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -115,13 +115,6 @@ svc_rdma_next_recv_ctxt(struct list_head *list)
 					rc_list);
 }
 
-static void svc_rdma_recv_cid_init(struct svcxprt_rdma *rdma,
-				   struct rpc_rdma_cid *cid)
-{
-	cid->ci_queue_id = rdma->sc_rq_cq->res.id;
-	cid->ci_completion_id = atomic_inc_return(&rdma->sc_completion_ids);
-}
-
 static struct svc_rdma_recv_ctxt *
 svc_rdma_recv_ctxt_alloc(struct svcxprt_rdma *rdma)
 {
diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c
index 4d2db06ccfd2..eab71f3867fa 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_rw.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c
@@ -146,13 +146,6 @@ static int svc_rdma_rw_ctx_init(struct svcxprt_rdma *rdma,
 	return ret;
 }
 
-static void svc_rdma_cc_cid_init(struct svcxprt_rdma *rdma,
-				 struct rpc_rdma_cid *cid)
-{
-	cid->ci_queue_id = rdma->sc_sq_cq->res.id;
-	cid->ci_completion_id = atomic_inc_return(&rdma->sc_completion_ids);
-}
-
 /**
  * svc_rdma_cc_init - Initialize an svc_rdma_chunk_ctxt
  * @rdma: controlling transport instance
@@ -161,7 +154,7 @@ static void svc_rdma_cc_cid_init(struct svcxprt_rdma *rdma,
 void svc_rdma_cc_init(struct svcxprt_rdma *rdma,
 		      struct svc_rdma_chunk_ctxt *cc)
 {
-	svc_rdma_cc_cid_init(rdma, &cc->cc_cid);
+	svc_rdma_send_cid_init(rdma, &cc->cc_cid);
 
 	INIT_LIST_HEAD(&cc->cc_rwctxts);
 	cc->cc_sqecount = 0;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 9571ed4a74d4..c9585e469ca8 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -113,13 +113,6 @@
 
 static void svc_rdma_wc_send(struct ib_cq *cq, struct ib_wc *wc);
 
-static void svc_rdma_send_cid_init(struct svcxprt_rdma *rdma,
-				   struct rpc_rdma_cid *cid)
-{
-	cid->ci_queue_id = rdma->sc_sq_cq->res.id;
-	cid->ci_completion_id = atomic_inc_return(&rdma->sc_completion_ids);
-}
-
 static struct svc_rdma_send_ctxt *
 svc_rdma_send_ctxt_alloc(struct svcxprt_rdma *rdma)
 {
-- 
cgit v1.2.3


From 4d9d69db898d05bd063548eee65d16a020676fec Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Mon, 18 Dec 2023 17:31:48 -0500
Subject: svcrdma: Add back svc_rdma_recv_ctxt::rc_pages

Having an nfsd thread waiting for an RDMA Read completion is
problematic if the Read responder (the client) stops responding. We
need to go back to handling RDMA Reads by allowing the nfsd thread
to return to the svc scheduler, then waking a second thread finish
the RPC message once the Read completion fires.

To start with, restore the rc_pages field so that RDMA Read pages
can be managed across calls to svc_rdma_recvfrom().

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/svc_rdma.h         | 4 +++-
 net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 5 +++++
 net/sunrpc/xprtrdma/svc_rdma_rw.c       | 4 +++-
 3 files changed, 11 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 46f2ce9f810b..0f2d7f68ef5d 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -183,7 +183,6 @@ struct svc_rdma_recv_ctxt {
 	void			*rc_recv_buf;
 	struct xdr_stream	rc_stream;
 	u32			rc_byte_len;
-	unsigned int		rc_page_count;
 	u32			rc_inv_rkey;
 	__be32			rc_msgtype;
 
@@ -199,6 +198,9 @@ struct svc_rdma_recv_ctxt {
 	struct svc_rdma_chunk	*rc_cur_result_payload;
 	struct svc_rdma_pcl	rc_write_pcl;
 	struct svc_rdma_pcl	rc_reply_pcl;
+
+	unsigned int		rc_page_count;
+	struct page		*rc_pages[RPCSVC_MAXPAGES];
 };
 
 struct svc_rdma_send_ctxt {
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 38f01652dc6d..e363cb1bdbc4 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -214,6 +214,11 @@ struct svc_rdma_recv_ctxt *svc_rdma_recv_ctxt_get(struct svcxprt_rdma *rdma)
 void svc_rdma_recv_ctxt_put(struct svcxprt_rdma *rdma,
 			    struct svc_rdma_recv_ctxt *ctxt)
 {
+	/* @rc_page_count is normally zero here, but error flows
+	 * can leave pages in @rc_pages.
+	 */
+	release_pages(ctxt->rc_pages, ctxt->rc_page_count);
+
 	pcl_free(&ctxt->rc_call_pcl);
 	pcl_free(&ctxt->rc_read_pcl);
 	pcl_free(&ctxt->rc_write_pcl);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c
index ff54bb268b7d..28a34718dee5 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_rw.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c
@@ -1131,7 +1131,9 @@ int svc_rdma_process_read_list(struct svcxprt_rdma *rdma,
 	rqstp->rq_respages = &rqstp->rq_pages[head->rc_page_count];
 	rqstp->rq_next_page = rqstp->rq_respages + 1;
 
-	/* Ensure svc_rdma_recv_ctxt_put() does not try to release pages */
+	/* Ensure svc_rdma_recv_ctxt_put() does not release pages
+	 * left in @rc_pages while I/O proceeds.
+	 */
 	head->rc_page_count = 0;
 
 out_err:
-- 
cgit v1.2.3


From a937693a82fd2211c5e52b638959d1486a77d16a Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Mon, 18 Dec 2023 17:31:54 -0500
Subject: svcrdma: Add back svcxprt_rdma::sc_read_complete_q

Having an nfsd thread waiting for an RDMA Read completion is
problematic if the Read responder (ie, the client) stops responding.
We need to go back to handling RDMA Reads by allowing the nfsd
thread to return to the svc scheduler, then waking a second thread
finish the RPC message once the Read completion fires.

As a next step, add a list_head upon which completed Reads are queued.
A subsequent patch will make use of this queue.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/svc_rdma.h          |  1 +
 net/sunrpc/xprtrdma/svc_rdma_recvfrom.c  | 37 +++++++++++++++++++++++++++++++-
 net/sunrpc/xprtrdma/svc_rdma_transport.c |  1 +
 3 files changed, 38 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 0f2d7f68ef5d..c98d29e51b9c 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -98,6 +98,7 @@ struct svcxprt_rdma {
 	u32		     sc_pending_recvs;
 	u32		     sc_recv_batch;
 	struct list_head     sc_rq_dto_q;
+	struct list_head     sc_read_complete_q;
 	spinlock_t	     sc_rq_dto_lock;
 	struct ib_qp         *sc_qp;
 	struct ib_cq         *sc_rq_cq;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index e363cb1bdbc4..2de947183a7a 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -382,6 +382,10 @@ void svc_rdma_flush_recv_queues(struct svcxprt_rdma *rdma)
 {
 	struct svc_rdma_recv_ctxt *ctxt;
 
+	while ((ctxt = svc_rdma_next_recv_ctxt(&rdma->sc_read_complete_q))) {
+		list_del(&ctxt->rc_list);
+		svc_rdma_recv_ctxt_put(rdma, ctxt);
+	}
 	while ((ctxt = svc_rdma_next_recv_ctxt(&rdma->sc_rq_dto_q))) {
 		list_del(&ctxt->rc_list);
 		svc_rdma_recv_ctxt_put(rdma, ctxt);
@@ -763,6 +767,30 @@ static bool svc_rdma_is_reverse_direction_reply(struct svc_xprt *xprt,
 	return true;
 }
 
+static noinline void svc_rdma_read_complete(struct svc_rqst *rqstp,
+					    struct svc_rdma_recv_ctxt *ctxt)
+{
+	int i;
+
+	/* Transfer the Read chunk pages into @rqstp.rq_pages, replacing
+	 * the rq_pages that were already allocated for this rqstp.
+	 */
+	release_pages(rqstp->rq_respages, ctxt->rc_page_count);
+	for (i = 0; i < ctxt->rc_page_count; i++)
+		rqstp->rq_pages[i] = ctxt->rc_pages[i];
+
+	/* Update @rqstp's result send buffer to start after the
+	 * last page in the RDMA Read payload.
+	 */
+	rqstp->rq_respages = &rqstp->rq_pages[ctxt->rc_page_count];
+	rqstp->rq_next_page = rqstp->rq_respages + 1;
+
+	/* Prevent svc_rdma_recv_ctxt_put() from releasing the
+	 * pages in ctxt::rc_pages a second time.
+	 */
+	ctxt->rc_page_count = 0;
+}
+
 /**
  * svc_rdma_recvfrom - Receive an RPC call
  * @rqstp: request structure into which to receive an RPC Call
@@ -807,8 +835,14 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 
 	rqstp->rq_xprt_ctxt = NULL;
 
-	ctxt = NULL;
 	spin_lock(&rdma_xprt->sc_rq_dto_lock);
+	ctxt = svc_rdma_next_recv_ctxt(&rdma_xprt->sc_read_complete_q);
+	if (ctxt) {
+		list_del(&ctxt->rc_list);
+		spin_unlock_bh(&rdma_xprt->sc_rq_dto_lock);
+		svc_rdma_read_complete(rqstp, ctxt);
+		goto complete;
+	}
 	ctxt = svc_rdma_next_recv_ctxt(&rdma_xprt->sc_rq_dto_q);
 	if (ctxt)
 		list_del(&ctxt->rc_list);
@@ -846,6 +880,7 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 			goto out_readfail;
 	}
 
+complete:
 	rqstp->rq_xprt_ctxt = ctxt;
 	rqstp->rq_prot = IPPROTO_MAX;
 	svc_xprt_copy_addrs(rqstp, xprt);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 8127c711fa3b..4f27325ace4a 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -137,6 +137,7 @@ static struct svcxprt_rdma *svc_rdma_create_xprt(struct svc_serv *serv,
 	svc_xprt_init(net, &svc_rdma_class, &cma_xprt->sc_xprt, serv);
 	INIT_LIST_HEAD(&cma_xprt->sc_accept_q);
 	INIT_LIST_HEAD(&cma_xprt->sc_rq_dto_q);
+	INIT_LIST_HEAD(&cma_xprt->sc_read_complete_q);
 	init_llist_head(&cma_xprt->sc_send_ctxts);
 	init_llist_head(&cma_xprt->sc_recv_ctxts);
 	init_llist_head(&cma_xprt->sc_rw_ctxts);
-- 
cgit v1.2.3


From ecba85e951c178e3fe7cea04eebf1035e8168f93 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Mon, 18 Dec 2023 17:32:01 -0500
Subject: svcrdma: Copy construction of svc_rqst::rq_arg to
 rdma_read_complete()

Once a set of RDMA Reads are complete, the Read completion handler
will poke the transport to trigger a second call to
svc_rdma_recvfrom(). recvfrom() will then merge the RDMA Read
payloads with the previously received RPC header to form a completed
RPC Call message.

The new code is copied from the svc_rdma_process_read_list() path.
A subsequent patch will make use of this code and remove the code
that this was copied from (svc_rdma_rw.c).

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/trace/events/rpcrdma.h          |  1 +
 net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 93 ++++++++++++++++++++++++++++++++-
 2 files changed, 93 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index 9a3fc6eb09a8..110c1475c527 100644
--- a/include/trace/events/rpcrdma.h
+++ b/include/trace/events/rpcrdma.h
@@ -2112,6 +2112,7 @@ TRACE_EVENT(svcrdma_wc_read,
 
 DEFINE_SEND_FLUSH_EVENT(svcrdma_wc_read_flush);
 DEFINE_SEND_FLUSH_EVENT(svcrdma_wc_read_err);
+DEFINE_SIMPLE_CID_EVENT(svcrdma_read_finished);
 
 DEFINE_SIMPLE_CID_EVENT(svcrdma_wc_write);
 DEFINE_SEND_FLUSH_EVENT(svcrdma_wc_write_flush);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 2de947183a7a..034bdd02f925 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -767,10 +767,86 @@ static bool svc_rdma_is_reverse_direction_reply(struct svc_xprt *xprt,
 	return true;
 }
 
+/* Finish constructing the RPC Call message in rqstp::rq_arg.
+ *
+ * The incoming RPC/RDMA message is an RDMA_MSG type message
+ * with a single Read chunk (only the upper layer data payload
+ * was conveyed via RDMA Read).
+ */
+static void svc_rdma_read_complete_one(struct svc_rqst *rqstp,
+				       struct svc_rdma_recv_ctxt *ctxt)
+{
+	struct svc_rdma_chunk *chunk = pcl_first_chunk(&ctxt->rc_read_pcl);
+	struct xdr_buf *buf = &rqstp->rq_arg;
+	unsigned int length;
+
+	/* Split the Receive buffer between the head and tail
+	 * buffers at Read chunk's position. XDR roundup of the
+	 * chunk is not included in either the pagelist or in
+	 * the tail.
+	 */
+	buf->tail[0].iov_base = buf->head[0].iov_base + chunk->ch_position;
+	buf->tail[0].iov_len = buf->head[0].iov_len - chunk->ch_position;
+	buf->head[0].iov_len = chunk->ch_position;
+
+	/* Read chunk may need XDR roundup (see RFC 8166, s. 3.4.5.2).
+	 *
+	 * If the client already rounded up the chunk length, the
+	 * length does not change. Otherwise, the length of the page
+	 * list is increased to include XDR round-up.
+	 *
+	 * Currently these chunks always start at page offset 0,
+	 * thus the rounded-up length never crosses a page boundary.
+	 */
+	buf->pages = &rqstp->rq_pages[0];
+	length = xdr_align_size(chunk->ch_length);
+	buf->page_len = length;
+	buf->len += length;
+	buf->buflen += length;
+}
+
+/* Finish constructing the RPC Call message in rqstp::rq_arg.
+ *
+ * The incoming RPC/RDMA message is an RDMA_MSG type message
+ * with payload in multiple Read chunks and no PZRC.
+ */
+static void svc_rdma_read_complete_multiple(struct svc_rqst *rqstp,
+					    struct svc_rdma_recv_ctxt *ctxt)
+{
+	struct xdr_buf *buf = &rqstp->rq_arg;
+
+	buf->len += ctxt->rc_readbytes;
+	buf->buflen += ctxt->rc_readbytes;
+
+	buf->head[0].iov_base = page_address(rqstp->rq_pages[0]);
+	buf->head[0].iov_len = min_t(size_t, PAGE_SIZE, ctxt->rc_readbytes);
+	buf->pages = &rqstp->rq_pages[1];
+	buf->page_len = ctxt->rc_readbytes - buf->head[0].iov_len;
+}
+
+/* Finish constructing the RPC Call message in rqstp::rq_arg.
+ *
+ * The incoming RPC/RDMA message is an RDMA_NOMSG type message
+ * (the RPC message body was conveyed via RDMA Read).
+ */
+static void svc_rdma_read_complete_pzrc(struct svc_rqst *rqstp,
+					struct svc_rdma_recv_ctxt *ctxt)
+{
+	struct xdr_buf *buf = &rqstp->rq_arg;
+
+	buf->len += ctxt->rc_readbytes;
+	buf->buflen += ctxt->rc_readbytes;
+
+	buf->head[0].iov_base = page_address(rqstp->rq_pages[0]);
+	buf->head[0].iov_len = min_t(size_t, PAGE_SIZE, ctxt->rc_readbytes);
+	buf->pages = &rqstp->rq_pages[1];
+	buf->page_len = ctxt->rc_readbytes - buf->head[0].iov_len;
+}
+
 static noinline void svc_rdma_read_complete(struct svc_rqst *rqstp,
 					    struct svc_rdma_recv_ctxt *ctxt)
 {
-	int i;
+	unsigned int i;
 
 	/* Transfer the Read chunk pages into @rqstp.rq_pages, replacing
 	 * the rq_pages that were already allocated for this rqstp.
@@ -789,6 +865,21 @@ static noinline void svc_rdma_read_complete(struct svc_rqst *rqstp,
 	 * pages in ctxt::rc_pages a second time.
 	 */
 	ctxt->rc_page_count = 0;
+
+	/* Finish constructing the RPC Call message. The exact
+	 * procedure for that depends on what kind of RPC/RDMA
+	 * chunks were provided by the client.
+	 */
+	if (pcl_is_empty(&ctxt->rc_call_pcl)) {
+		if (ctxt->rc_read_pcl.cl_count == 1)
+			svc_rdma_read_complete_one(rqstp, ctxt);
+		else
+			svc_rdma_read_complete_multiple(rqstp, ctxt);
+	} else {
+		svc_rdma_read_complete_pzrc(rqstp, ctxt);
+	}
+
+	trace_svcrdma_read_finished(&ctxt->rc_cid);
 }
 
 /**
-- 
cgit v1.2.3


From d3dba534100d4e9eb7a5204be97cd6f9ada2066e Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Mon, 18 Dec 2023 17:32:07 -0500
Subject: svcrdma: Implement multi-stage Read completion again

Having an nfsd thread waiting for an RDMA Read completion is
problematic if the Read responder (ie, the client) stops responding.
We need to go back to handling RDMA Reads by getting the svc scheduler
to call svc_rdma_recvfrom() a second time to finish building an RPC
message after a Read completion.

This is the final patch, and makes several changes that have to
happen concurrently:

1. svc_rdma_process_read_list no longer waits for a completion, but
   simply builds and posts the Read WRs.

2. svc_rdma_read_done() now queues a completed Read on
   sc_read_complete_q for later processing rather than calling
   complete().

3. The completed RPC message is no longer built in the
   svc_rdma_process_read_list() path. Finishing the message is now
   done in svc_rdma_recvfrom() when it notices work on the
   sc_read_complete_q. The "finish building this RPC message" code
   is removed from the svc_rdma_process_read_list() path.

This arrangement avoids the need for an nfsd thread to wait for an
RDMA Read non-interruptibly without a timeout. It's basically the
same code structure that Tom Tucker used for Read chunks along with
some clean-up and modernization.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/svc_rdma.h         |   6 +-
 net/sunrpc/xprtrdma/svc_rdma_recvfrom.c |  36 +++++---
 net/sunrpc/xprtrdma/svc_rdma_rw.c       | 151 +++++++++++---------------------
 3 files changed, 80 insertions(+), 113 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index c98d29e51b9c..e7595ae62fe2 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -170,8 +170,6 @@ struct svc_rdma_chunk_ctxt {
 	struct list_head	cc_rwctxts;
 	ktime_t			cc_posttime;
 	int			cc_sqecount;
-	enum ib_wc_status	cc_status;
-	struct completion	cc_done;
 };
 
 struct svc_rdma_recv_ctxt {
@@ -191,6 +189,7 @@ struct svc_rdma_recv_ctxt {
 	unsigned int		rc_pageoff;
 	unsigned int		rc_curpage;
 	unsigned int		rc_readbytes;
+	struct xdr_buf		rc_saved_arg;
 	struct svc_rdma_chunk_ctxt	rc_cc;
 
 	struct svc_rdma_pcl	rc_call_pcl;
@@ -240,6 +239,9 @@ extern int svc_rdma_recvfrom(struct svc_rqst *);
 extern void svc_rdma_destroy_rw_ctxts(struct svcxprt_rdma *rdma);
 extern void svc_rdma_cc_init(struct svcxprt_rdma *rdma,
 			     struct svc_rdma_chunk_ctxt *cc);
+extern void svc_rdma_cc_release(struct svcxprt_rdma *rdma,
+				struct svc_rdma_chunk_ctxt *cc,
+				enum dma_data_direction dir);
 extern int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma,
 				     const struct svc_rdma_chunk *chunk,
 				     const struct xdr_buf *xdr);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 034bdd02f925..d72953f29258 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -214,6 +214,8 @@ struct svc_rdma_recv_ctxt *svc_rdma_recv_ctxt_get(struct svcxprt_rdma *rdma)
 void svc_rdma_recv_ctxt_put(struct svcxprt_rdma *rdma,
 			    struct svc_rdma_recv_ctxt *ctxt)
 {
+	svc_rdma_cc_release(rdma, &ctxt->rc_cc, DMA_FROM_DEVICE);
+
 	/* @rc_page_count is normally zero here, but error flows
 	 * can leave pages in @rc_pages.
 	 */
@@ -870,6 +872,7 @@ static noinline void svc_rdma_read_complete(struct svc_rqst *rqstp,
 	 * procedure for that depends on what kind of RPC/RDMA
 	 * chunks were provided by the client.
 	 */
+	rqstp->rq_arg = ctxt->rc_saved_arg;
 	if (pcl_is_empty(&ctxt->rc_call_pcl)) {
 		if (ctxt->rc_read_pcl.cl_count == 1)
 			svc_rdma_read_complete_one(rqstp, ctxt);
@@ -930,7 +933,8 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 	ctxt = svc_rdma_next_recv_ctxt(&rdma_xprt->sc_read_complete_q);
 	if (ctxt) {
 		list_del(&ctxt->rc_list);
-		spin_unlock_bh(&rdma_xprt->sc_rq_dto_lock);
+		spin_unlock(&rdma_xprt->sc_rq_dto_lock);
+		svc_xprt_received(xprt);
 		svc_rdma_read_complete(rqstp, ctxt);
 		goto complete;
 	}
@@ -965,11 +969,8 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 	svc_rdma_get_inv_rkey(rdma_xprt, ctxt);
 
 	if (!pcl_is_empty(&ctxt->rc_read_pcl) ||
-	    !pcl_is_empty(&ctxt->rc_call_pcl)) {
-		ret = svc_rdma_process_read_list(rdma_xprt, rqstp, ctxt);
-		if (ret < 0)
-			goto out_readfail;
-	}
+	    !pcl_is_empty(&ctxt->rc_call_pcl))
+		goto out_readlist;
 
 complete:
 	rqstp->rq_xprt_ctxt = ctxt;
@@ -983,12 +984,23 @@ out_err:
 	svc_rdma_recv_ctxt_put(rdma_xprt, ctxt);
 	return 0;
 
-out_readfail:
-	if (ret == -EINVAL)
-		svc_rdma_send_error(rdma_xprt, ctxt, ret);
-	svc_rdma_recv_ctxt_put(rdma_xprt, ctxt);
-	svc_xprt_deferred_close(xprt);
-	return -ENOTCONN;
+out_readlist:
+	/* This @rqstp is about to be recycled. Save the work
+	 * already done constructing the Call message in rq_arg
+	 * so it can be restored when the RDMA Reads have
+	 * completed.
+	 */
+	ctxt->rc_saved_arg = rqstp->rq_arg;
+
+	ret = svc_rdma_process_read_list(rdma_xprt, rqstp, ctxt);
+	if (ret < 0) {
+		if (ret == -EINVAL)
+			svc_rdma_send_error(rdma_xprt, ctxt, ret);
+		svc_rdma_recv_ctxt_put(rdma_xprt, ctxt);
+		svc_xprt_deferred_close(xprt);
+		return ret;
+	}
+	return 0;
 
 out_backchannel:
 	svc_rdma_handle_bc_reply(rqstp, ctxt);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c
index 28a34718dee5..c00fcce61d1e 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_rw.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c
@@ -163,14 +163,15 @@ void svc_rdma_cc_init(struct svcxprt_rdma *rdma,
 	cc->cc_sqecount = 0;
 }
 
-/*
- * The consumed rw_ctx's are cleaned and placed on a local llist so
- * that only one atomic llist operation is needed to put them all
- * back on the free list.
+/**
+ * svc_rdma_cc_release - Release resources held by a svc_rdma_chunk_ctxt
+ * @rdma: controlling transport instance
+ * @cc: svc_rdma_chunk_ctxt to be released
+ * @dir: DMA direction
  */
-static void svc_rdma_cc_release(struct svcxprt_rdma *rdma,
-				struct svc_rdma_chunk_ctxt *cc,
-				enum dma_data_direction dir)
+void svc_rdma_cc_release(struct svcxprt_rdma *rdma,
+			 struct svc_rdma_chunk_ctxt *cc,
+			 enum dma_data_direction dir)
 {
 	struct llist_node *first, *last;
 	struct svc_rdma_rw_ctxt *ctxt;
@@ -300,12 +301,21 @@ static void svc_rdma_wc_read_done(struct ib_cq *cq, struct ib_wc *wc)
 			container_of(cqe, struct svc_rdma_chunk_ctxt, cc_cqe);
 	struct svc_rdma_recv_ctxt *ctxt;
 
+	svc_rdma_wake_send_waiters(rdma, cc->cc_sqecount);
+
+	ctxt = container_of(cc, struct svc_rdma_recv_ctxt, rc_cc);
 	switch (wc->status) {
 	case IB_WC_SUCCESS:
-		ctxt = container_of(cc, struct svc_rdma_recv_ctxt, rc_cc);
 		trace_svcrdma_wc_read(wc, &cc->cc_cid, ctxt->rc_readbytes,
 				      cc->cc_posttime);
-		break;
+
+		spin_lock(&rdma->sc_rq_dto_lock);
+		list_add_tail(&ctxt->rc_list, &rdma->sc_read_complete_q);
+		/* the unlock pairs with the smp_rmb in svc_xprt_ready */
+		set_bit(XPT_DATA, &rdma->sc_xprt.xpt_flags);
+		spin_unlock(&rdma->sc_rq_dto_lock);
+		svc_xprt_enqueue(&rdma->sc_xprt);
+		return;
 	case IB_WC_WR_FLUSH_ERR:
 		trace_svcrdma_wc_read_flush(wc, &cc->cc_cid);
 		break;
@@ -313,10 +323,13 @@ static void svc_rdma_wc_read_done(struct ib_cq *cq, struct ib_wc *wc)
 		trace_svcrdma_wc_read_err(wc, &cc->cc_cid);
 	}
 
-	svc_rdma_wake_send_waiters(rdma, cc->cc_sqecount);
-	cc->cc_status = wc->status;
-	complete(&cc->cc_done);
-	return;
+	/* The RDMA Read has flushed, so the incoming RPC message
+	 * cannot be constructed and must be dropped. Signal the
+	 * loss to the client by closing the connection.
+	 */
+	svc_rdma_cc_release(rdma, cc, DMA_FROM_DEVICE);
+	svc_rdma_recv_ctxt_put(rdma, ctxt);
+	svc_xprt_deferred_close(&rdma->sc_xprt);
 }
 
 /*
@@ -823,7 +836,6 @@ svc_rdma_read_multiple_chunks(struct svc_rqst *rqstp,
 			      struct svc_rdma_recv_ctxt *head)
 {
 	const struct svc_rdma_pcl *pcl = &head->rc_read_pcl;
-	struct xdr_buf *buf = &rqstp->rq_arg;
 	struct svc_rdma_chunk *chunk, *next;
 	unsigned int start, length;
 	int ret;
@@ -853,18 +865,7 @@ svc_rdma_read_multiple_chunks(struct svc_rqst *rqstp,
 
 	start += length;
 	length = head->rc_byte_len - start;
-	ret = svc_rdma_copy_inline_range(rqstp, head, start, length);
-	if (ret < 0)
-		return ret;
-
-	buf->len += head->rc_readbytes;
-	buf->buflen += head->rc_readbytes;
-
-	buf->head[0].iov_base = page_address(rqstp->rq_pages[0]);
-	buf->head[0].iov_len = min_t(size_t, PAGE_SIZE, head->rc_readbytes);
-	buf->pages = &rqstp->rq_pages[1];
-	buf->page_len = head->rc_readbytes - buf->head[0].iov_len;
-	return 0;
+	return svc_rdma_copy_inline_range(rqstp, head, start, length);
 }
 
 /**
@@ -888,42 +889,8 @@ svc_rdma_read_multiple_chunks(struct svc_rqst *rqstp,
 static int svc_rdma_read_data_item(struct svc_rqst *rqstp,
 				   struct svc_rdma_recv_ctxt *head)
 {
-	struct xdr_buf *buf = &rqstp->rq_arg;
-	struct svc_rdma_chunk *chunk;
-	unsigned int length;
-	int ret;
-
-	chunk = pcl_first_chunk(&head->rc_read_pcl);
-	ret = svc_rdma_build_read_chunk(rqstp, head, chunk);
-	if (ret < 0)
-		goto out;
-
-	/* Split the Receive buffer between the head and tail
-	 * buffers at Read chunk's position. XDR roundup of the
-	 * chunk is not included in either the pagelist or in
-	 * the tail.
-	 */
-	buf->tail[0].iov_base = buf->head[0].iov_base + chunk->ch_position;
-	buf->tail[0].iov_len = buf->head[0].iov_len - chunk->ch_position;
-	buf->head[0].iov_len = chunk->ch_position;
-
-	/* Read chunk may need XDR roundup (see RFC 8166, s. 3.4.5.2).
-	 *
-	 * If the client already rounded up the chunk length, the
-	 * length does not change. Otherwise, the length of the page
-	 * list is increased to include XDR round-up.
-	 *
-	 * Currently these chunks always start at page offset 0,
-	 * thus the rounded-up length never crosses a page boundary.
-	 */
-	buf->pages = &rqstp->rq_pages[0];
-	length = xdr_align_size(chunk->ch_length);
-	buf->page_len = length;
-	buf->len += length;
-	buf->buflen += length;
-
-out:
-	return ret;
+	return svc_rdma_build_read_chunk(rqstp, head,
+					 pcl_first_chunk(&head->rc_read_pcl));
 }
 
 /**
@@ -1051,23 +1018,28 @@ static int svc_rdma_read_call_chunk(struct svc_rqst *rqstp,
 static noinline int svc_rdma_read_special(struct svc_rqst *rqstp,
 					  struct svc_rdma_recv_ctxt *head)
 {
-	struct xdr_buf *buf = &rqstp->rq_arg;
-	int ret;
-
-	ret = svc_rdma_read_call_chunk(rqstp, head);
-	if (ret < 0)
-		goto out;
-
-	buf->len += head->rc_readbytes;
-	buf->buflen += head->rc_readbytes;
+	return svc_rdma_read_call_chunk(rqstp, head);
+}
 
-	buf->head[0].iov_base = page_address(rqstp->rq_pages[0]);
-	buf->head[0].iov_len = min_t(size_t, PAGE_SIZE, head->rc_readbytes);
-	buf->pages = &rqstp->rq_pages[1];
-	buf->page_len = head->rc_readbytes - buf->head[0].iov_len;
+/* Pages under I/O have been copied to head->rc_pages. Ensure that
+ * svc_xprt_release() does not put them when svc_rdma_recvfrom()
+ * returns. This has to be done after all Read WRs are constructed
+ * to properly handle a page that happens to be part of I/O on behalf
+ * of two different RDMA segments.
+ *
+ * Note: if the subsequent post_send fails, these pages have already
+ * been moved to head->rc_pages and thus will be cleaned up by
+ * svc_rdma_recv_ctxt_put().
+ */
+static void svc_rdma_clear_rqst_pages(struct svc_rqst *rqstp,
+				      struct svc_rdma_recv_ctxt *head)
+{
+	unsigned int i;
 
-out:
-	return ret;
+	for (i = 0; i < head->rc_page_count; i++) {
+		head->rc_pages[i] = rqstp->rq_pages[i];
+		rqstp->rq_pages[i] = NULL;
+	}
 }
 
 /**
@@ -1113,30 +1085,11 @@ int svc_rdma_process_read_list(struct svcxprt_rdma *rdma,
 			ret = svc_rdma_read_multiple_chunks(rqstp, head);
 	} else
 		ret = svc_rdma_read_special(rqstp, head);
+	svc_rdma_clear_rqst_pages(rqstp, head);
 	if (ret < 0)
-		goto out_err;
+		return ret;
 
 	trace_svcrdma_post_read_chunk(&cc->cc_cid, cc->cc_sqecount);
-	init_completion(&cc->cc_done);
 	ret = svc_rdma_post_chunk_ctxt(rdma, cc);
-	if (ret < 0)
-		goto out_err;
-
-	ret = 1;
-	wait_for_completion(&cc->cc_done);
-	if (cc->cc_status != IB_WC_SUCCESS)
-		ret = -EIO;
-
-	/* rq_respages starts after the last arg page */
-	rqstp->rq_respages = &rqstp->rq_pages[head->rc_page_count];
-	rqstp->rq_next_page = rqstp->rq_respages + 1;
-
-	/* Ensure svc_rdma_recv_ctxt_put() does not release pages
-	 * left in @rc_pages while I/O proceeds.
-	 */
-	head->rc_page_count = 0;
-
-out_err:
-	svc_rdma_cc_release(rdma, cc, DMA_FROM_DEVICE);
-	return ret;
+	return ret < 0 ? ret : 1;
 }
-- 
cgit v1.2.3


From 7b207ccd983350a5dedd132b57c666186dd02a7c Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.de>
Date: Fri, 15 Dec 2023 11:56:32 +1100
Subject: svc: don't hold reference for poolstats, only mutex.

A future patch will remove refcounting on svc_serv as it is of little
use.
It is currently used to keep the svc around while the pool_stats file is
open.
Change this to get the pointer, protected by the mutex, only in
seq_start, and the release the mutex in seq_stop.
This means that if the nfsd server is stopped and restarted while the
pool_stats file it open, then some pool stats info could be from the
first instance and some from the second.  This might appear odd, but is
unlikely to be a problem in practice.

Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/netns.h            |  4 +++-
 fs/nfsd/nfsctl.c           |  2 +-
 fs/nfsd/nfssvc.c           | 24 ++----------------------
 include/linux/sunrpc/svc.h |  8 +++++++-
 net/sunrpc/svc_xprt.c      | 32 +++++++++++++++++++++++---------
 5 files changed, 36 insertions(+), 34 deletions(-)

(limited to 'include')

diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
index ab303a8b77d5..16dbef245dbb 100644
--- a/fs/nfsd/netns.h
+++ b/fs/nfsd/netns.h
@@ -123,7 +123,9 @@ struct nfsd_net {
 	u32 clientid_counter;
 	u32 clverifier_counter;
 
-	struct svc_serv *nfsd_serv;
+	struct svc_info nfsd_info;
+#define nfsd_serv nfsd_info.serv
+
 	/* When a listening socket is added to nfsd, keep_active is set
 	 * and this justifies a reference on nfsd_serv.  This stops
 	 * nfsd_serv from being freed.  When the number of threads is
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 6a3b385703cc..46a001e81b55 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -183,7 +183,7 @@ static const struct file_operations pool_stats_operations = {
 	.open		= nfsd_pool_stats_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
-	.release	= nfsd_pool_stats_release,
+	.release	= seq_release,
 };
 
 DEFINE_SHOW_ATTRIBUTE(nfsd_reply_cache_stats);
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index ee835bf9ee42..365968737923 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -684,6 +684,7 @@ int nfsd_create_serv(struct net *net)
 		return error;
 	}
 	spin_lock(&nfsd_notifier_lock);
+	nn->nfsd_info.mutex = &nfsd_mutex;
 	nn->nfsd_serv = serv;
 	spin_unlock(&nfsd_notifier_lock);
 
@@ -1082,28 +1083,7 @@ bool nfssvc_encode_voidres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
 
 int nfsd_pool_stats_open(struct inode *inode, struct file *file)
 {
-	int ret;
 	struct nfsd_net *nn = net_generic(inode->i_sb->s_fs_info, nfsd_net_id);
 
-	mutex_lock(&nfsd_mutex);
-	if (nn->nfsd_serv == NULL) {
-		mutex_unlock(&nfsd_mutex);
-		return -ENODEV;
-	}
-	svc_get(nn->nfsd_serv);
-	ret = svc_pool_stats_open(nn->nfsd_serv, file);
-	mutex_unlock(&nfsd_mutex);
-	return ret;
-}
-
-int nfsd_pool_stats_release(struct inode *inode, struct file *file)
-{
-	struct seq_file *seq = file->private_data;
-	struct svc_serv *serv = seq->private;
-	int ret = seq_release(inode, file);
-
-	mutex_lock(&nfsd_mutex);
-	svc_put(serv);
-	mutex_unlock(&nfsd_mutex);
-	return ret;
+	return svc_pool_stats_open(&nn->nfsd_info, file);
 }
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 544fcfe07479..3bea2840272d 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -97,6 +97,12 @@ struct svc_serv {
 #endif /* CONFIG_SUNRPC_BACKCHANNEL */
 };
 
+/* This is used by pool_stats to find and lock an svc */
+struct svc_info {
+	struct svc_serv		*serv;
+	struct mutex		*mutex;
+};
+
 /**
  * svc_get() - increment reference count on a SUNRPC serv
  * @serv:  the svc_serv to have count incremented
@@ -431,7 +437,7 @@ void		   svc_exit_thread(struct svc_rqst *);
 struct svc_serv *  svc_create_pooled(struct svc_program *, unsigned int,
 				     int (*threadfn)(void *data));
 int		   svc_set_num_threads(struct svc_serv *, struct svc_pool *, int);
-int		   svc_pool_stats_open(struct svc_serv *serv, struct file *file);
+int		   svc_pool_stats_open(struct svc_info *si, struct file *file);
 void		   svc_process(struct svc_rqst *rqstp);
 void		   svc_process_bc(struct rpc_rqst *req, struct svc_rqst *rqstp);
 int		   svc_register(const struct svc_serv *, struct net *, const int,
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 1b71055fc391..b4a85a227bd7 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -1362,29 +1362,36 @@ int svc_xprt_names(struct svc_serv *serv, char *buf, const int buflen)
 }
 EXPORT_SYMBOL_GPL(svc_xprt_names);
 
-
 /*----------------------------------------------------------------------------*/
 
 static void *svc_pool_stats_start(struct seq_file *m, loff_t *pos)
 {
 	unsigned int pidx = (unsigned int)*pos;
-	struct svc_serv *serv = m->private;
+	struct svc_info *si = m->private;
 
 	dprintk("svc_pool_stats_start, *pidx=%u\n", pidx);
 
+	mutex_lock(si->mutex);
+
 	if (!pidx)
 		return SEQ_START_TOKEN;
-	return (pidx > serv->sv_nrpools ? NULL : &serv->sv_pools[pidx-1]);
+	if (!si->serv)
+		return NULL;
+	return pidx > si->serv->sv_nrpools ? NULL
+		: &si->serv->sv_pools[pidx - 1];
 }
 
 static void *svc_pool_stats_next(struct seq_file *m, void *p, loff_t *pos)
 {
 	struct svc_pool *pool = p;
-	struct svc_serv *serv = m->private;
+	struct svc_info *si = m->private;
+	struct svc_serv *serv = si->serv;
 
 	dprintk("svc_pool_stats_next, *pos=%llu\n", *pos);
 
-	if (p == SEQ_START_TOKEN) {
+	if (!serv) {
+		pool = NULL;
+	} else if (p == SEQ_START_TOKEN) {
 		pool = &serv->sv_pools[0];
 	} else {
 		unsigned int pidx = (pool - &serv->sv_pools[0]);
@@ -1399,6 +1406,9 @@ static void *svc_pool_stats_next(struct seq_file *m, void *p, loff_t *pos)
 
 static void svc_pool_stats_stop(struct seq_file *m, void *p)
 {
+	struct svc_info *si = m->private;
+
+	mutex_unlock(si->mutex);
 }
 
 static int svc_pool_stats_show(struct seq_file *m, void *p)
@@ -1426,14 +1436,18 @@ static const struct seq_operations svc_pool_stats_seq_ops = {
 	.show	= svc_pool_stats_show,
 };
 
-int svc_pool_stats_open(struct svc_serv *serv, struct file *file)
+int svc_pool_stats_open(struct svc_info *info, struct file *file)
 {
+	struct seq_file *seq;
 	int err;
 
 	err = seq_open(file, &svc_pool_stats_seq_ops);
-	if (!err)
-		((struct seq_file *) file->private_data)->private = serv;
-	return err;
+	if (err)
+		return err;
+	seq = file->private_data;
+	seq->private = info;
+
+	return 0;
 }
 EXPORT_SYMBOL(svc_pool_stats_open);
 
-- 
cgit v1.2.3


From 1e3577a4521ef33199eea05ce7b9099825848c49 Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.de>
Date: Fri, 15 Dec 2023 11:56:34 +1100
Subject: SUNRPC: discard sv_refcnt, and svc_get/svc_put

sv_refcnt is no longer useful.
lockd and nfs-cb only ever have the svc active when there are a non-zero
number of threads, so sv_refcnt mirrors sv_nrthreads.

nfsd also keeps the svc active between when a socket is added and when
the first thread is started, but we don't really need a refcount for
that.  We can simply not destroy the svc while there are any permanent
sockets attached.

So remove sv_refcnt and the get/put functions.
Instead of a final call to svc_put(), call svc_destroy() instead.
This is changed to also store NULL in the passed-in pointer to make it
easier to avoid use-after-free situations.

Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/lockd/svc.c             | 10 ++++------
 fs/nfs/callback.c          | 13 ++++++-------
 fs/nfsd/netns.h            |  7 -------
 fs/nfsd/nfsctl.c           | 13 ++-----------
 fs/nfsd/nfssvc.c           | 26 ++++----------------------
 include/linux/sunrpc/svc.h | 27 +--------------------------
 net/sunrpc/svc.c           | 13 ++++---------
 7 files changed, 21 insertions(+), 88 deletions(-)

(limited to 'include')

diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index 81be07c1d3d1..0d6cb3fdc0e1 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -345,10 +345,10 @@ static int lockd_get(void)
 
 	serv->sv_maxconn = nlm_max_connections;
 	error = svc_set_num_threads(serv, NULL, 1);
-	/* The thread now holds the only reference */
-	svc_put(serv);
-	if (error < 0)
+	if (error < 0) {
+		svc_destroy(&serv);
 		return error;
+	}
 
 	nlmsvc_serv = serv;
 	register_inetaddr_notifier(&lockd_inetaddr_notifier);
@@ -372,11 +372,9 @@ static void lockd_put(void)
 	unregister_inet6addr_notifier(&lockd_inet6addr_notifier);
 #endif
 
-	svc_get(nlmsvc_serv);
 	svc_set_num_threads(nlmsvc_serv, NULL, 0);
-	svc_put(nlmsvc_serv);
 	timer_delete_sync(&nlmsvc_retry);
-	nlmsvc_serv = NULL;
+	svc_destroy(&nlmsvc_serv);
 	dprintk("lockd_down: service destroyed\n");
 }
 
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index 4ffa1f469e90..760d27dd7225 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -187,7 +187,7 @@ static struct svc_serv *nfs_callback_create_svc(int minorversion)
 	 * Check whether we're already up and running.
 	 */
 	if (cb_info->serv)
-		return svc_get(cb_info->serv);
+		return cb_info->serv;
 
 	/*
 	 * Sanity check: if there's no task,
@@ -245,9 +245,10 @@ int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt)
 
 	cb_info->users++;
 err_net:
-	if (!cb_info->users)
-		cb_info->serv = NULL;
-	svc_put(serv);
+	if (!cb_info->users) {
+		svc_set_num_threads(cb_info->serv, NULL, 0);
+		svc_destroy(&cb_info->serv);
+	}
 err_create:
 	mutex_unlock(&nfs_callback_mutex);
 	return ret;
@@ -271,11 +272,9 @@ void nfs_callback_down(int minorversion, struct net *net)
 	nfs_callback_down_net(minorversion, serv, net);
 	cb_info->users--;
 	if (cb_info->users == 0) {
-		svc_get(serv);
 		svc_set_num_threads(serv, NULL, 0);
-		svc_put(serv);
 		dprintk("nfs_callback_down: service destroyed\n");
-		cb_info->serv = NULL;
+		svc_destroy(&cb_info->serv);
 	}
 	mutex_unlock(&nfs_callback_mutex);
 }
diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
index 16dbef245dbb..74b4360779a1 100644
--- a/fs/nfsd/netns.h
+++ b/fs/nfsd/netns.h
@@ -126,13 +126,6 @@ struct nfsd_net {
 	struct svc_info nfsd_info;
 #define nfsd_serv nfsd_info.serv
 
-	/* When a listening socket is added to nfsd, keep_active is set
-	 * and this justifies a reference on nfsd_serv.  This stops
-	 * nfsd_serv from being freed.  When the number of threads is
-	 * set, keep_active is cleared and the reference is dropped.  So
-	 * when the last thread exits, the service will be destroyed.
-	 */
-	int keep_active;
 
 	/*
 	 * clientid and stateid data for construction of net unique COPY
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 46a001e81b55..5c2fae98d98a 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -711,12 +711,8 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred
 	serv = nn->nfsd_serv;
 	err = svc_addsock(serv, net, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred);
 
-	if (err < 0 && !serv->sv_nrthreads && !nn->keep_active)
+	if (!serv->sv_nrthreads && list_empty(&nn->nfsd_serv->sv_permsocks))
 		nfsd_last_thread(net);
-	else if (err >= 0 && !serv->sv_nrthreads && !xchg(&nn->keep_active, 1))
-		svc_get(serv);
-
-	svc_put(serv);
 	return err;
 }
 
@@ -754,10 +750,6 @@ static ssize_t __write_ports_addxprt(char *buf, struct net *net, const struct cr
 	if (err < 0 && err != -EAFNOSUPPORT)
 		goto out_close;
 
-	if (!serv->sv_nrthreads && !xchg(&nn->keep_active, 1))
-		svc_get(serv);
-
-	svc_put(serv);
 	return 0;
 out_close:
 	xprt = svc_find_xprt(serv, transport, net, PF_INET, port);
@@ -766,10 +758,9 @@ out_close:
 		svc_xprt_put(xprt);
 	}
 out_err:
-	if (!serv->sv_nrthreads && !nn->keep_active)
+	if (!serv->sv_nrthreads && list_empty(&nn->nfsd_serv->sv_permsocks))
 		nfsd_last_thread(net);
 
-	svc_put(serv);
 	return err;
 }
 
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 365968737923..1a295c409343 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -59,15 +59,6 @@ static __be32			nfsd_init_request(struct svc_rqst *,
  * nfsd_mutex protects nn->nfsd_serv -- both the pointer itself and some members
  * of the svc_serv struct such as ->sv_temp_socks and ->sv_permsocks.
  *
- * If (out side the lock) nn->nfsd_serv is non-NULL, then it must point to a
- * properly initialised 'struct svc_serv' with ->sv_nrthreads > 0 (unless
- * nn->keep_active is set).  That number of nfsd threads must
- * exist and each must be listed in ->sp_all_threads in some entry of
- * ->sv_pools[].
- *
- * Each active thread holds a counted reference on nn->nfsd_serv, as does
- * the nn->keep_active flag and various transient calls to svc_get().
- *
  * Finally, the nfsd_mutex also protects some of the global variables that are
  * accessed when nfsd starts and that are settable via the write_* routines in
  * nfsctl.c. In particular:
@@ -572,6 +563,7 @@ void nfsd_last_thread(struct net *net)
 
 	nfsd_shutdown_net(net);
 	nfsd_export_flush(net);
+	svc_destroy(&serv);
 }
 
 void nfsd_reset_versions(struct nfsd_net *nn)
@@ -646,11 +638,9 @@ void nfsd_shutdown_threads(struct net *net)
 		return;
 	}
 
-	svc_get(serv);
 	/* Kill outstanding nfsd threads */
 	svc_set_num_threads(serv, NULL, 0);
 	nfsd_last_thread(net);
-	svc_put(serv);
 	mutex_unlock(&nfsd_mutex);
 }
 
@@ -666,10 +656,9 @@ int nfsd_create_serv(struct net *net)
 	struct svc_serv *serv;
 
 	WARN_ON(!mutex_is_locked(&nfsd_mutex));
-	if (nn->nfsd_serv) {
-		svc_get(nn->nfsd_serv);
+	if (nn->nfsd_serv)
 		return 0;
-	}
+
 	if (nfsd_max_blksize == 0)
 		nfsd_max_blksize = nfsd_get_default_max_blksize();
 	nfsd_reset_versions(nn);
@@ -680,7 +669,7 @@ int nfsd_create_serv(struct net *net)
 	serv->sv_maxconn = nn->max_connections;
 	error = svc_bind(serv, net);
 	if (error < 0) {
-		svc_put(serv);
+		svc_destroy(&serv);
 		return error;
 	}
 	spin_lock(&nfsd_notifier_lock);
@@ -764,7 +753,6 @@ int nfsd_set_nrthreads(int n, int *nthreads, struct net *net)
 		nthreads[0] = 1;
 
 	/* apply the new numbers */
-	svc_get(nn->nfsd_serv);
 	for (i = 0; i < n; i++) {
 		err = svc_set_num_threads(nn->nfsd_serv,
 					  &nn->nfsd_serv->sv_pools[i],
@@ -772,7 +760,6 @@ int nfsd_set_nrthreads(int n, int *nthreads, struct net *net)
 		if (err)
 			break;
 	}
-	svc_put(nn->nfsd_serv);
 	return err;
 }
 
@@ -814,13 +801,8 @@ nfsd_svc(int nrservs, struct net *net, const struct cred *cred)
 		goto out_put;
 	error = serv->sv_nrthreads;
 out_put:
-	/* Threads now hold service active */
-	if (xchg(&nn->keep_active, 0))
-		svc_put(serv);
-
 	if (serv->sv_nrthreads == 0)
 		nfsd_last_thread(net);
-	svc_put(serv);
 out:
 	mutex_unlock(&nfsd_mutex);
 	return error;
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 3bea2840272d..8d7888234e9e 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -69,7 +69,6 @@ struct svc_serv {
 	struct svc_program *	sv_program;	/* RPC program */
 	struct svc_stat *	sv_stats;	/* RPC statistics */
 	spinlock_t		sv_lock;
-	struct kref		sv_refcnt;
 	unsigned int		sv_nrthreads;	/* # of server threads */
 	unsigned int		sv_maxconn;	/* max connections allowed or
 						 * '0' causing max to be based
@@ -103,31 +102,7 @@ struct svc_info {
 	struct mutex		*mutex;
 };
 
-/**
- * svc_get() - increment reference count on a SUNRPC serv
- * @serv:  the svc_serv to have count incremented
- *
- * Returns: the svc_serv that was passed in.
- */
-static inline struct svc_serv *svc_get(struct svc_serv *serv)
-{
-	kref_get(&serv->sv_refcnt);
-	return serv;
-}
-
-void svc_destroy(struct kref *);
-
-/**
- * svc_put - decrement reference count on a SUNRPC serv
- * @serv:  the svc_serv to have count decremented
- *
- * When the reference count reaches zero, svc_destroy()
- * is called to clean up and free the serv.
- */
-static inline void svc_put(struct svc_serv *serv)
-{
-	kref_put(&serv->sv_refcnt, svc_destroy);
-}
+void svc_destroy(struct svc_serv **svcp);
 
 /*
  * Maximum payload size supported by a kernel RPC server.
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index fa4e23fa0e09..eb5856e1351d 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -463,7 +463,6 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools,
 		return NULL;
 	serv->sv_name      = prog->pg_name;
 	serv->sv_program   = prog;
-	kref_init(&serv->sv_refcnt);
 	serv->sv_stats     = prog->pg_stats;
 	if (bufsize > RPCSVC_MAXPAYLOAD)
 		bufsize = RPCSVC_MAXPAYLOAD;
@@ -564,11 +563,13 @@ EXPORT_SYMBOL_GPL(svc_create_pooled);
  * protect sv_permsocks and sv_tempsocks.
  */
 void
-svc_destroy(struct kref *ref)
+svc_destroy(struct svc_serv **servp)
 {
-	struct svc_serv *serv = container_of(ref, struct svc_serv, sv_refcnt);
+	struct svc_serv *serv = *servp;
 	unsigned int i;
 
+	*servp = NULL;
+
 	dprintk("svc: svc_destroy(%s)\n", serv->sv_program->pg_name);
 	timer_shutdown_sync(&serv->sv_temptimer);
 
@@ -675,7 +676,6 @@ svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node)
 	if (!rqstp)
 		return ERR_PTR(-ENOMEM);
 
-	svc_get(serv);
 	spin_lock_bh(&serv->sv_lock);
 	serv->sv_nrthreads += 1;
 	spin_unlock_bh(&serv->sv_lock);
@@ -935,11 +935,6 @@ svc_exit_thread(struct svc_rqst *rqstp)
 
 	svc_rqst_free(rqstp);
 
-	svc_put(serv);
-	/* That svc_put() cannot be the last, because the thread
-	 * waiting for SP_VICTIM_REMAINS to clear must hold
-	 * a reference. So it is still safe to access pool.
-	 */
 	clear_and_wake_up_bit(SP_VICTIM_REMAINS, &pool->sp_flags);
 }
 EXPORT_SYMBOL_GPL(svc_exit_thread);
-- 
cgit v1.2.3


From 317bacf960a4879af22d12175f47d284930b3273 Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Fri, 1 Dec 2023 17:25:27 -0500
Subject: i3c: master: add enable(disable) hot join in sys entry

Add hotjoin entry in sys file system allow user enable/disable hotjoin
feature.

Add (*enable(disable)_hotjoin)() to i3c_master_controller_ops.
Add api i3c_master_enable(disable)_hotjoin();

Signed-off-by: Frank Li <Frank.Li@nxp.com>
Link: https://lore.kernel.org/r/20231201222532.2431484-2-Frank.Li@nxp.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master.c       | 83 ++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/i3c/master.h |  5 +++
 2 files changed, 88 insertions(+)

(limited to 'include')

diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c
index 8b729ebae2a6..3afa530c5e32 100644
--- a/drivers/i3c/master.c
+++ b/drivers/i3c/master.c
@@ -557,6 +557,88 @@ static ssize_t i2c_scl_frequency_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(i2c_scl_frequency);
 
+static int i3c_set_hotjoin(struct i3c_master_controller *master, bool enable)
+{
+	int ret;
+
+	if (!master || !master->ops)
+		return -EINVAL;
+
+	if (!master->ops->enable_hotjoin || !master->ops->disable_hotjoin)
+		return -EINVAL;
+
+	i3c_bus_normaluse_lock(&master->bus);
+
+	if (enable)
+		ret = master->ops->enable_hotjoin(master);
+	else
+		ret = master->ops->disable_hotjoin(master);
+
+	master->hotjoin = enable;
+
+	i3c_bus_normaluse_unlock(&master->bus);
+
+	return ret;
+}
+
+static ssize_t hotjoin_store(struct device *dev, struct device_attribute *attr,
+			     const char *buf, size_t count)
+{
+	struct i3c_bus *i3cbus = dev_to_i3cbus(dev);
+	int ret;
+	bool res;
+
+	if (!i3cbus->cur_master)
+		return -EINVAL;
+
+	if (kstrtobool(buf, &res))
+		return -EINVAL;
+
+	ret = i3c_set_hotjoin(i3cbus->cur_master->common.master, res);
+	if (ret)
+		return ret;
+
+	return count;
+}
+
+/*
+ * i3c_master_enable_hotjoin - Enable hotjoin
+ * @master: I3C master object
+ *
+ * Return: a 0 in case of success, an negative error code otherwise.
+ */
+int i3c_master_enable_hotjoin(struct i3c_master_controller *master)
+{
+	return i3c_set_hotjoin(master, true);
+}
+EXPORT_SYMBOL_GPL(i3c_master_enable_hotjoin);
+
+/*
+ * i3c_master_disable_hotjoin - Disable hotjoin
+ * @master: I3C master object
+ *
+ * Return: a 0 in case of success, an negative error code otherwise.
+ */
+int i3c_master_disable_hotjoin(struct i3c_master_controller *master)
+{
+	return i3c_set_hotjoin(master, false);
+}
+EXPORT_SYMBOL_GPL(i3c_master_disable_hotjoin);
+
+static ssize_t hotjoin_show(struct device *dev, struct device_attribute *da, char *buf)
+{
+	struct i3c_bus *i3cbus = dev_to_i3cbus(dev);
+	ssize_t ret;
+
+	i3c_bus_normaluse_lock(i3cbus);
+	ret = sysfs_emit(buf, "%d\n", i3cbus->cur_master->common.master->hotjoin);
+	i3c_bus_normaluse_unlock(i3cbus);
+
+	return ret;
+}
+
+static DEVICE_ATTR_RW(hotjoin);
+
 static struct attribute *i3c_masterdev_attrs[] = {
 	&dev_attr_mode.attr,
 	&dev_attr_current_master.attr,
@@ -567,6 +649,7 @@ static struct attribute *i3c_masterdev_attrs[] = {
 	&dev_attr_pid.attr,
 	&dev_attr_dynamic_address.attr,
 	&dev_attr_hdrcap.attr,
+	&dev_attr_hotjoin.attr,
 	NULL,
 };
 ATTRIBUTE_GROUPS(i3c_masterdev);
diff --git a/include/linux/i3c/master.h b/include/linux/i3c/master.h
index 24c1863b86e2..3b5bd8e3257c 100644
--- a/include/linux/i3c/master.h
+++ b/include/linux/i3c/master.h
@@ -460,6 +460,8 @@ struct i3c_master_controller_ops {
 	int (*disable_ibi)(struct i3c_dev_desc *dev);
 	void (*recycle_ibi_slot)(struct i3c_dev_desc *dev,
 				 struct i3c_ibi_slot *slot);
+	int (*enable_hotjoin)(struct i3c_master_controller *master);
+	int (*disable_hotjoin)(struct i3c_master_controller *master);
 };
 
 /**
@@ -495,6 +497,7 @@ struct i3c_master_controller {
 	const struct i3c_master_controller_ops *ops;
 	unsigned int secondary : 1;
 	unsigned int init_done : 1;
+	unsigned int hotjoin: 1;
 	struct {
 		struct list_head i3c;
 		struct list_head i2c;
@@ -551,6 +554,8 @@ int i3c_master_register(struct i3c_master_controller *master,
 			const struct i3c_master_controller_ops *ops,
 			bool secondary);
 void i3c_master_unregister(struct i3c_master_controller *master);
+int i3c_master_enable_hotjoin(struct i3c_master_controller *master);
+int i3c_master_disable_hotjoin(struct i3c_master_controller *master);
 
 /**
  * i3c_dev_get_master_data() - get master private data attached to an I3C
-- 
cgit v1.2.3


From e5e3df06ac98d15cfb10bb5c12356709365e91b2 Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Fri, 1 Dec 2023 17:25:29 -0500
Subject: i3c: add actual_len in i3c_priv_xfer
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In MIPI I3C Specification:

"Ninth Bit of SDR Target Returned (Read) Data as End-of-Data: In I2C, the
ninth Data bit from Target to Controller is an ACK by the Controller. By
contrast, in I3C this bit allows the Target to end a Read, and allows the
Controller to Abort a Read. In SDR terms, the ninth bit of Read data is
referred to as the T-Bit (for ‘Transition’)"

I3C allow devices early terminate data transfer. So need "actual_len" field
to indicate how much get by i3c_priv_xfer.

Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Frank Li <Frank.Li@nxp.com>
Link: https://lore.kernel.org/r/20231201222532.2431484-4-Frank.Li@nxp.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 include/linux/i3c/device.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/i3c/device.h b/include/linux/i3c/device.h
index 84ed77c04940..e119f11948ef 100644
--- a/include/linux/i3c/device.h
+++ b/include/linux/i3c/device.h
@@ -54,6 +54,7 @@ enum i3c_hdr_mode {
  * struct i3c_priv_xfer - I3C SDR private transfer
  * @rnw: encodes the transfer direction. true for a read, false for a write
  * @len: transfer length in bytes of the transfer
+ * @actual_len: actual length in bytes are transferred by the controller
  * @data: input/output buffer
  * @data.in: input buffer. Must point to a DMA-able buffer
  * @data.out: output buffer. Must point to a DMA-able buffer
@@ -62,6 +63,7 @@ enum i3c_hdr_mode {
 struct i3c_priv_xfer {
 	u8 rnw;
 	u16 len;
+	u16 actual_len;
 	union {
 		void *in;
 		const void *out;
-- 
cgit v1.2.3


From 18e5794879905a788e06fb2bc40b6f5b58eae5c2 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 22 Dec 2023 21:05:42 -0800
Subject: i3c: master: fix Excess kernel-doc description warning

Remove the @boardinfo: line to prevent the kernel-doc warning:

include/linux/i3c/master.h:98: warning: Excess struct member 'boardinfo' description in 'i2c_dev_desc'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Alexandre Belloni <alexandre.belloni@bootlin.com>
Cc:  <linux-i3c@lists.infradead.org>
Link: https://lore.kernel.org/r/20231223050542.13930-1-rdunlap@infradead.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 include/linux/i3c/master.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/i3c/master.h b/include/linux/i3c/master.h
index 3b5bd8e3257c..1ecd73b17ff5 100644
--- a/include/linux/i3c/master.h
+++ b/include/linux/i3c/master.h
@@ -76,7 +76,6 @@ struct i2c_dev_boardinfo {
 /**
  * struct i2c_dev_desc - I2C device descriptor
  * @common: common part of the I2C device descriptor
- * @boardinfo: pointer to the boardinfo attached to this I2C device
  * @dev: I2C device object registered to the I2C framework
  * @addr: I2C device address
  * @lvr: LVR (Legacy Virtual Register) needed by the I3C core to know about
-- 
cgit v1.2.3


From 10416a3578ba5f76d0b161d2d36a1d8a4c46a69d Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 19 Dec 2023 15:59:32 +0100
Subject: firewire: make fw_bus_type const

Now that the driver core can properly handle constant struct bus_type,
move the fw_bus_type variable to be a constant structure as well,
placing it into read-only memory which can not be modified at runtime.

Cc: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Cc: linux1394-devel@lists.sourceforge.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/2023121931-skydiver-dodgy-d1bd@gregkh
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
---
 drivers/firewire/core-device.c | 2 +-
 include/linux/firewire.h       | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/firewire/core-device.c b/drivers/firewire/core-device.c
index 2828e9573e90..7ca8e31dadb5 100644
--- a/drivers/firewire/core-device.c
+++ b/drivers/firewire/core-device.c
@@ -219,7 +219,7 @@ static int fw_unit_uevent(const struct device *dev, struct kobj_uevent_env *env)
 	return 0;
 }
 
-struct bus_type fw_bus_type = {
+const struct bus_type fw_bus_type = {
 	.name = "firewire",
 	.match = fw_unit_match,
 	.probe = fw_unit_probe,
diff --git a/include/linux/firewire.h b/include/linux/firewire.h
index bd3fc75d4f14..dd9f2d765e68 100644
--- a/include/linux/firewire.h
+++ b/include/linux/firewire.h
@@ -75,7 +75,7 @@ void fw_csr_iterator_init(struct fw_csr_iterator *ci, const u32 *p);
 int fw_csr_iterator_next(struct fw_csr_iterator *ci, int *key, int *value);
 int fw_csr_string(const u32 *directory, int key, char *buf, size_t size);
 
-extern struct bus_type fw_bus_type;
+extern const struct bus_type fw_bus_type;
 
 struct fw_card_driver;
 struct fw_node;
-- 
cgit v1.2.3


From e9ee910218ffd420454b52a052d6f1087354905b Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Sun, 7 Jan 2024 17:11:38 -0800
Subject: Revert "net: stmmac: Enable Per DMA Channel interrupt"

Revert "net: stmmac: Use interrupt mode INTM=1 for per channel irq"
This reverts commit 36af9f25ddfd311da82628f194c794786467cb12.
Revert "net: stmmac: Add support for TX/RX channel interrupt"
This reverts commit 9072e03d32088137a435ddf3aa95fd6e038d69d8.
Revert "net: stmmac: Make MSI interrupt routine generic"
This reverts commit 477bd4beb93bf9ace9bda71f1437b191befa9cf4.
Revert "dt-bindings: net: snps,dwmac: per channel irq"
This reverts commit 67d47c8ada0f8795bfcdb85cc8f2ad3ce556674b.

Device tree bindings need to be reviewed.

Link: https://lore.kernel.org/all/2df9fe3e-7971-4aa2-89a9-0e085b3b00d7@linaro.org/
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../devicetree/bindings/net/snps,dwmac.yaml        | 24 +++++-----------
 drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c  |  4 +--
 .../net/ethernet/stmicro/stmmac/dwmac-socfpga.c    |  3 --
 drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c   |  2 +-
 drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h     |  3 --
 drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c | 32 +++++++++-------------
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c  | 30 ++++++++++----------
 .../net/ethernet/stmicro/stmmac/stmmac_platform.c  | 28 -------------------
 include/linux/stmmac.h                             |  4 +--
 9 files changed, 40 insertions(+), 90 deletions(-)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/net/snps,dwmac.yaml b/Documentation/devicetree/bindings/net/snps,dwmac.yaml
index e72dded824f4..5c2769dc689a 100644
--- a/Documentation/devicetree/bindings/net/snps,dwmac.yaml
+++ b/Documentation/devicetree/bindings/net/snps,dwmac.yaml
@@ -103,27 +103,17 @@ properties:
 
   interrupts:
     minItems: 1
-    maxItems: 19
+    items:
+      - description: Combined signal for various interrupt events
+      - description: The interrupt to manage the remote wake-up packet detection
+      - description: The interrupt that occurs when Rx exits the LPI state
 
   interrupt-names:
     minItems: 1
-    maxItems: 19
     items:
-      oneOf:
-        - description: Combined signal for various interrupt events
-          const: macirq
-        - description: The interrupt to manage the remote wake-up packet detection
-          const: eth_wake_irq
-        - description: The interrupt that occurs when Rx exits the LPI state
-          const: eth_lpi
-        - description: DMA Tx per-channel interrupt
-          pattern: '^dma_tx[0-7]?$'
-        - description: DMA Rx per-channel interrupt
-          pattern: '^dma_rx[0-7]?$'
-
-    allOf:
-      - contains:
-          const: macirq
+      - const: macirq
+      - enum: [eth_wake_irq, eth_lpi]
+      - const: eth_lpi
 
   clocks:
     minItems: 1
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index f0ec69af96c9..60283543ffc8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -952,7 +952,7 @@ static int stmmac_config_single_msi(struct pci_dev *pdev,
 
 	res->irq = pci_irq_vector(pdev, 0);
 	res->wol_irq = res->irq;
-	plat->flags &= ~STMMAC_FLAG_MULTI_IRQ_EN;
+	plat->flags &= ~STMMAC_FLAG_MULTI_MSI_EN;
 	dev_info(&pdev->dev, "%s: Single IRQ enablement successful\n",
 		 __func__);
 
@@ -1004,7 +1004,7 @@ static int stmmac_config_multi_msi(struct pci_dev *pdev,
 	if (plat->msi_sfty_ue_vec < STMMAC_MSI_VEC_MAX)
 		res->sfty_ue_irq = pci_irq_vector(pdev, plat->msi_sfty_ue_vec);
 
-	plat->flags |= STMMAC_FLAG_MULTI_IRQ_EN;
+	plat->flags |= STMMAC_FLAG_MULTI_MSI_EN;
 	dev_info(&pdev->dev, "%s: multi MSI enablement successful\n", __func__);
 
 	return 0;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
index cf43fb3c6cc5..ba2ce776bd4d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
@@ -427,9 +427,6 @@ static int socfpga_dwmac_probe(struct platform_device *pdev)
 	plat_dat->bsp_priv = dwmac;
 	plat_dat->fix_mac_speed = socfpga_dwmac_fix_mac_speed;
 
-	if (stmmac_res.rx_irq[0] > 0 && stmmac_res.tx_irq[0] > 0)
-		plat_dat->flags |= STMMAC_FLAG_MULTI_IRQ_EN;
-
 	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
 	if (ret)
 		return ret;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
index 5f649106ffcd..84d3a8551b03 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
@@ -175,7 +175,7 @@ static void dwmac4_dma_init(void __iomem *ioaddr,
 
 	value = readl(ioaddr + DMA_BUS_MODE);
 
-	if (dma_cfg->multi_irq_en) {
+	if (dma_cfg->multi_msi_en) {
 		value &= ~DMA_BUS_MODE_INTM_MASK;
 		value |= (DMA_BUS_MODE_INTM_MODE1 << DMA_BUS_MODE_INTM_SHIFT);
 	}
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
index 04bf731cb7ea..207ff1799f2c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
@@ -346,9 +346,6 @@
 /* DMA Registers */
 #define XGMAC_DMA_MODE			0x00003000
 #define XGMAC_SWR			BIT(0)
-#define XGMAC_DMA_MODE_INTM_MASK	GENMASK(13, 12)
-#define XGMAC_DMA_MODE_INTM_SHIFT	12
-#define XGMAC_DMA_MODE_INTM_MODE1	0x1
 #define XGMAC_DMA_SYSBUS_MODE		0x00003004
 #define XGMAC_WR_OSR_LMT		GENMASK(29, 24)
 #define XGMAC_WR_OSR_LMT_SHIFT		24
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
index dcb9f094415d..3cde695fec91 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
@@ -31,13 +31,6 @@ static void dwxgmac2_dma_init(void __iomem *ioaddr,
 		value |= XGMAC_EAME;
 
 	writel(value, ioaddr + XGMAC_DMA_SYSBUS_MODE);
-
-	if (dma_cfg->multi_irq_en) {
-		value = readl(ioaddr + XGMAC_DMA_MODE);
-		value &= ~XGMAC_DMA_MODE_INTM_MASK;
-		value |= (XGMAC_DMA_MODE_INTM_MODE1 << XGMAC_DMA_MODE_INTM_SHIFT);
-		writel(value, ioaddr + XGMAC_DMA_MODE);
-	}
 }
 
 static void dwxgmac2_dma_init_chan(struct stmmac_priv *priv,
@@ -372,18 +365,19 @@ static int dwxgmac2_dma_interrupt(struct stmmac_priv *priv,
 	}
 
 	/* TX/RX NORMAL interrupts */
-	if (likely(intr_status & XGMAC_RI)) {
-		u64_stats_update_begin(&rxq_stats->syncp);
-		rxq_stats->rx_normal_irq_n++;
-		u64_stats_update_end(&rxq_stats->syncp);
-		ret |= handle_rx;
-	}
-
-	if (likely(intr_status & (XGMAC_TI | XGMAC_TBU))) {
-		u64_stats_update_begin(&txq_stats->syncp);
-		txq_stats->tx_normal_irq_n++;
-		u64_stats_update_end(&txq_stats->syncp);
-		ret |= handle_tx;
+	if (likely(intr_status & XGMAC_NIS)) {
+		if (likely(intr_status & XGMAC_RI)) {
+			u64_stats_update_begin(&rxq_stats->syncp);
+			rxq_stats->rx_normal_irq_n++;
+			u64_stats_update_end(&rxq_stats->syncp);
+			ret |= handle_rx;
+		}
+		if (likely(intr_status & (XGMAC_TI | XGMAC_TBU))) {
+			u64_stats_update_begin(&txq_stats->syncp);
+			txq_stats->tx_normal_irq_n++;
+			u64_stats_update_end(&txq_stats->syncp);
+			ret |= handle_tx;
+		}
 	}
 
 	/* Clear interrupts */
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 57873b879b33..47de466e432c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -129,8 +129,8 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id);
 /* For MSI interrupts handling */
 static irqreturn_t stmmac_mac_interrupt(int irq, void *dev_id);
 static irqreturn_t stmmac_safety_interrupt(int irq, void *dev_id);
-static irqreturn_t stmmac_dma_tx_interrupt(int irq, void *data);
-static irqreturn_t stmmac_dma_rx_interrupt(int irq, void *data);
+static irqreturn_t stmmac_msi_intr_tx(int irq, void *data);
+static irqreturn_t stmmac_msi_intr_rx(int irq, void *data);
 static void stmmac_reset_rx_queue(struct stmmac_priv *priv, u32 queue);
 static void stmmac_reset_tx_queue(struct stmmac_priv *priv, u32 queue);
 static void stmmac_reset_queues_param(struct stmmac_priv *priv);
@@ -3602,7 +3602,7 @@ static void stmmac_free_irq(struct net_device *dev,
 	}
 }
 
-static int stmmac_request_irq_multi(struct net_device *dev)
+static int stmmac_request_irq_multi_msi(struct net_device *dev)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
 	enum request_irq_err irq_err;
@@ -3697,7 +3697,7 @@ static int stmmac_request_irq_multi(struct net_device *dev)
 		}
 	}
 
-	/* Request Rx irq */
+	/* Request Rx MSI irq */
 	for (i = 0; i < priv->plat->rx_queues_to_use; i++) {
 		if (i >= MTL_MAX_RX_QUEUES)
 			break;
@@ -3707,11 +3707,11 @@ static int stmmac_request_irq_multi(struct net_device *dev)
 		int_name = priv->int_name_rx_irq[i];
 		sprintf(int_name, "%s:%s-%d", dev->name, "rx", i);
 		ret = request_irq(priv->rx_irq[i],
-				  stmmac_dma_rx_interrupt,
+				  stmmac_msi_intr_rx,
 				  0, int_name, &priv->dma_conf.rx_queue[i]);
 		if (unlikely(ret < 0)) {
 			netdev_err(priv->dev,
-				   "%s: alloc rx-%d  dma rx_irq %d (error: %d)\n",
+				   "%s: alloc rx-%d  MSI %d (error: %d)\n",
 				   __func__, i, priv->rx_irq[i], ret);
 			irq_err = REQ_IRQ_ERR_RX;
 			irq_idx = i;
@@ -3722,7 +3722,7 @@ static int stmmac_request_irq_multi(struct net_device *dev)
 		irq_set_affinity_hint(priv->rx_irq[i], &cpu_mask);
 	}
 
-	/* Request Tx irq */
+	/* Request Tx MSI irq */
 	for (i = 0; i < priv->plat->tx_queues_to_use; i++) {
 		if (i >= MTL_MAX_TX_QUEUES)
 			break;
@@ -3732,11 +3732,11 @@ static int stmmac_request_irq_multi(struct net_device *dev)
 		int_name = priv->int_name_tx_irq[i];
 		sprintf(int_name, "%s:%s-%d", dev->name, "tx", i);
 		ret = request_irq(priv->tx_irq[i],
-				  stmmac_dma_tx_interrupt,
+				  stmmac_msi_intr_tx,
 				  0, int_name, &priv->dma_conf.tx_queue[i]);
 		if (unlikely(ret < 0)) {
 			netdev_err(priv->dev,
-				   "%s: alloc tx-%d  dma tx_irq %d (error: %d)\n",
+				   "%s: alloc tx-%d  MSI %d (error: %d)\n",
 				   __func__, i, priv->tx_irq[i], ret);
 			irq_err = REQ_IRQ_ERR_TX;
 			irq_idx = i;
@@ -3811,8 +3811,8 @@ static int stmmac_request_irq(struct net_device *dev)
 	int ret;
 
 	/* Request the IRQ lines */
-	if (priv->plat->flags & STMMAC_FLAG_MULTI_IRQ_EN)
-		ret = stmmac_request_irq_multi(dev);
+	if (priv->plat->flags & STMMAC_FLAG_MULTI_MSI_EN)
+		ret = stmmac_request_irq_multi_msi(dev);
 	else
 		ret = stmmac_request_irq_single(dev);
 
@@ -6075,7 +6075,7 @@ static irqreturn_t stmmac_safety_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static irqreturn_t stmmac_dma_tx_interrupt(int irq, void *data)
+static irqreturn_t stmmac_msi_intr_tx(int irq, void *data)
 {
 	struct stmmac_tx_queue *tx_q = (struct stmmac_tx_queue *)data;
 	struct stmmac_dma_conf *dma_conf;
@@ -6107,7 +6107,7 @@ static irqreturn_t stmmac_dma_tx_interrupt(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static irqreturn_t stmmac_dma_rx_interrupt(int irq, void *data)
+static irqreturn_t stmmac_msi_intr_rx(int irq, void *data)
 {
 	struct stmmac_rx_queue *rx_q = (struct stmmac_rx_queue *)data;
 	struct stmmac_dma_conf *dma_conf;
@@ -7456,8 +7456,8 @@ int stmmac_dvr_probe(struct device *device,
 	priv->plat = plat_dat;
 	priv->ioaddr = res->addr;
 	priv->dev->base_addr = (unsigned long)res->addr;
-	priv->plat->dma_cfg->multi_irq_en =
-		(priv->plat->flags & STMMAC_FLAG_MULTI_IRQ_EN);
+	priv->plat->dma_cfg->multi_msi_en =
+		(priv->plat->flags & STMMAC_FLAG_MULTI_MSI_EN);
 
 	priv->dev->irq = res->irq;
 	priv->wol_irq = res->wol_irq;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index ae6859153e98..70eadc83ca68 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -710,10 +710,6 @@ EXPORT_SYMBOL_GPL(devm_stmmac_probe_config_dt);
 int stmmac_get_platform_resources(struct platform_device *pdev,
 				  struct stmmac_resources *stmmac_res)
 {
-	char irq_name[9];
-	int i;
-	int irq;
-
 	memset(stmmac_res, 0, sizeof(*stmmac_res));
 
 	/* Get IRQ information early to have an ability to ask for deferred
@@ -747,30 +743,6 @@ int stmmac_get_platform_resources(struct platform_device *pdev,
 		dev_info(&pdev->dev, "IRQ eth_lpi not found\n");
 	}
 
-	/* For RX Channel */
-	for (i = 0; i < MTL_MAX_RX_QUEUES; i++) {
-		snprintf(irq_name, sizeof(irq_name), "dma_rx%i", i);
-		irq = platform_get_irq_byname_optional(pdev, irq_name);
-		if (irq == -EPROBE_DEFER)
-			return irq;
-		else if (irq < 0)
-			break;
-
-		stmmac_res->rx_irq[i] = irq;
-	}
-
-	/* For TX Channel */
-	for (i = 0; i < MTL_MAX_TX_QUEUES; i++) {
-		snprintf(irq_name, sizeof(irq_name), "dma_tx%i", i);
-		irq = platform_get_irq_byname_optional(pdev, irq_name);
-		if (irq == -EPROBE_DEFER)
-			return irq;
-		else if (irq < 0)
-			break;
-
-		stmmac_res->tx_irq[i] = irq;
-	}
-
 	stmmac_res->addr = devm_platform_ioremap_resource(pdev, 0);
 
 	return PTR_ERR_OR_ZERO(stmmac_res->addr);
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index b950e6f9761d..dee5ad6e48c5 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -98,7 +98,7 @@ struct stmmac_dma_cfg {
 	int mixed_burst;
 	bool aal;
 	bool eame;
-	bool multi_irq_en;
+	bool multi_msi_en;
 	bool dche;
 };
 
@@ -215,7 +215,7 @@ struct dwmac4_addrs {
 #define STMMAC_FLAG_TSO_EN			BIT(4)
 #define STMMAC_FLAG_SERDES_UP_AFTER_PHY_LINKUP	BIT(5)
 #define STMMAC_FLAG_VLAN_FAIL_Q_EN		BIT(6)
-#define STMMAC_FLAG_MULTI_IRQ_EN		BIT(7)
+#define STMMAC_FLAG_MULTI_MSI_EN		BIT(7)
 #define STMMAC_FLAG_EXT_SNAPSHOT_EN		BIT(8)
 #define STMMAC_FLAG_INT_SNAPSHOT_EN		BIT(9)
 #define STMMAC_FLAG_RX_CLK_RUNS_IN_LPI		BIT(10)
-- 
cgit v1.2.3


From 3fbf61207c66ff7ac9b60ab76d4bfd239f97e973 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Sun, 7 Jan 2024 17:14:51 -0800
Subject: Revert "mlx5 updates 2023-12-20"

Revert "net/mlx5: Implement management PF Ethernet profile"
This reverts commit 22c4640698a1d47606b5a4264a584e8046641784.
Revert "net/mlx5: Enable SD feature"
This reverts commit c88c49ac9c18fb7c3fa431126de1d8f8f555e912.
Revert "net/mlx5e: Block TLS device offload on combined SD netdev"
This reverts commit 83a59ce0057b7753d7fbece194b89622c663b2a6.
Revert "net/mlx5e: Support per-mdev queue counter"
This reverts commit d72baceb92539a178d2610b0e9ceb75706a75b55.
Revert "net/mlx5e: Support cross-vhca RSS"
This reverts commit c73a3ab8fa6e93a783bd563938d7cf00d62d5d34.
Revert "net/mlx5e: Let channels be SD-aware"
This reverts commit e4f9686bdee7b4dd89e0ed63cd03606e4bda4ced.
Revert "net/mlx5e: Create EN core HW resources for all secondary devices"
This reverts commit c4fb94aa822d6c9d05fc3c5aee35c7e339061dc1.
Revert "net/mlx5e: Create single netdev per SD group"
This reverts commit e2578b4f983cfcd47837bbe3bcdbf5920e50b2ad.
Revert "net/mlx5: SD, Add informative prints in kernel log"
This reverts commit c82d360325112ccc512fc11a3b68cdcdf04a1478.
Revert "net/mlx5: SD, Implement steering for primary and secondaries"
This reverts commit 605fcce33b2d1beb0139b6e5913fa0b2062116b2.
Revert "net/mlx5: SD, Implement devcom communication and primary election"
This reverts commit a45af9a96740873db9a4b5bb493ce2ad81ccb4d5.
Revert "net/mlx5: SD, Implement basic query and instantiation"
This reverts commit 63b9ce944c0e26c44c42cdd5095c2e9851c1a8ff.
Revert "net/mlx5: SD, Introduce SD lib"
This reverts commit 4a04a31f49320d078b8078e1da4b0e2faca5dfa3.
Revert "net/mlx5: Fix query of sd_group field"
This reverts commit e04984a37398b3f4f5a79c993b94c6b1224184cc.
Revert "net/mlx5e: Use the correct lag ports number when creating TISes"
This reverts commit a7e7b40c4bc115dbf2a2bb453d7bbb2e0ea99703.

There are some unanswered questions on the list, and we don't
have any docs. Given the lack of replies so far and the fact
that v6.8 merge window has started - let's revert this and
revisit for v6.9.

Link: https://lore.kernel.org/all/20231221005721.186607-1-saeed@kernel.org/
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/Makefile   |   2 +-
 drivers/net/ethernet/mellanox/mlx5/core/dev.c      |   3 -
 drivers/net/ethernet/mellanox/mlx5/core/ecpf.c     |   6 -
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |  15 +-
 .../net/ethernet/mellanox/mlx5/core/en/channels.c  |  10 +-
 .../net/ethernet/mellanox/mlx5/core/en/channels.h  |   6 +-
 .../net/ethernet/mellanox/mlx5/core/en/mgmt_pf.c   | 268 ------------
 .../ethernet/mellanox/mlx5/core/en/monitor_stats.c |  48 +-
 .../net/ethernet/mellanox/mlx5/core/en/params.c    |   9 +-
 .../net/ethernet/mellanox/mlx5/core/en/params.h    |   3 +
 drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c   |  12 +-
 drivers/net/ethernet/mellanox/mlx5/core/en/qos.c   |   8 +-
 .../ethernet/mellanox/mlx5/core/en/reporter_rx.c   |   4 +-
 .../ethernet/mellanox/mlx5/core/en/reporter_tx.c   |   3 +-
 drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c   | 123 +-----
 drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h   |   9 +-
 drivers/net/ethernet/mellanox/mlx5/core/en/rss.c   |  17 +-
 drivers/net/ethernet/mellanox/mlx5/core/en/rss.h   |   4 +-
 .../net/ethernet/mellanox/mlx5/core/en/rx_res.c    |  62 +--
 .../net/ethernet/mellanox/mlx5/core/en/rx_res.h    |   1 -
 drivers/net/ethernet/mellanox/mlx5/core/en/trap.c  |  11 +-
 .../net/ethernet/mellanox/mlx5/core/en/xsk/pool.c  |   6 +-
 .../net/ethernet/mellanox/mlx5/core/en/xsk/setup.c |   8 +-
 .../ethernet/mellanox/mlx5/core/en_accel/ktls.c    |   2 +-
 .../ethernet/mellanox/mlx5/core/en_accel/ktls.h    |   4 +-
 .../ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c |   6 +-
 .../net/ethernet/mellanox/mlx5/core/en_common.c    |  21 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  | 200 ++-------
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.c |  39 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c    |   4 +-
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c  |   2 +-
 .../net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c  |   2 +-
 .../net/ethernet/mellanox/mlx5/core/lib/devcom.h   |   1 -
 drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h |  12 -
 drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c   | 487 ---------------------
 drivers/net/ethernet/mellanox/mlx5/core/lib/sd.h   |  38 --
 drivers/net/ethernet/mellanox/mlx5/core/vport.c    |  21 -
 include/linux/mlx5/driver.h                        |  10 -
 include/linux/mlx5/mlx5_ifc.h                      |  24 +-
 include/linux/mlx5/vport.h                         |   1 -
 40 files changed, 192 insertions(+), 1320 deletions(-)
 delete mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/mgmt_pf.c
 delete mode 100644 drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c
 delete mode 100644 drivers/net/ethernet/mellanox/mlx5/core/lib/sd.h

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index f36232dead1a..c44870b175f9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -29,7 +29,7 @@ mlx5_core-$(CONFIG_MLX5_CORE_EN) += en/rqt.o en/tir.o en/rss.o en/rx_res.o \
 		en/reporter_tx.o en/reporter_rx.o en/params.o en/xsk/pool.o \
 		en/xsk/setup.o en/xsk/rx.o en/xsk/tx.o en/devlink.o en/ptp.o \
 		en/qos.o en/htb.o en/trap.o en/fs_tt_redirect.o en/selq.o \
-		en/mgmt_pf.o lib/crypto.o lib/sd.o
+		lib/crypto.o
 
 #
 # Netdev extra
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
index aa1b471e13fa..cf0477f53dc4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
@@ -190,9 +190,6 @@ bool mlx5_rdma_supported(struct mlx5_core_dev *dev)
 	if (is_mp_supported(dev))
 		return false;
 
-	if (mlx5_core_is_mgmt_pf(dev))
-		return false;
-
 	return true;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c
index aa397e3ebe6d..d000236ddbac 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c
@@ -75,9 +75,6 @@ int mlx5_ec_init(struct mlx5_core_dev *dev)
 	if (!mlx5_core_is_ecpf(dev))
 		return 0;
 
-	if (mlx5_core_is_mgmt_pf(dev))
-		return 0;
-
 	return mlx5_host_pf_init(dev);
 }
 
@@ -88,9 +85,6 @@ void mlx5_ec_cleanup(struct mlx5_core_dev *dev)
 	if (!mlx5_core_is_ecpf(dev))
 		return;
 
-	if (mlx5_core_is_mgmt_pf(dev))
-		return;
-
 	mlx5_host_pf_cleanup(dev);
 
 	err = mlx5_wait_for_pages(dev, &dev->priv.page_counters[MLX5_HOST_PF]);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 922b63c25154..0bfe1ca8a364 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -60,10 +60,8 @@
 #include "lib/clock.h"
 #include "en/rx_res.h"
 #include "en/selq.h"
-#include "lib/sd.h"
 
 extern const struct net_device_ops mlx5e_netdev_ops;
-extern const struct net_device_ops mlx5e_mgmt_netdev_ops;
 struct page_pool;
 
 #define MLX5E_METADATA_ETHER_TYPE (0x8CE4)
@@ -793,8 +791,6 @@ struct mlx5e_channel {
 	struct hwtstamp_config    *tstamp;
 	DECLARE_BITMAP(state, MLX5E_CHANNEL_NUM_STATES);
 	int                        ix;
-	int                        vec_ix;
-	int                        sd_ix;
 	int                        cpu;
 	/* Sync between icosq recovery and XSK enable/disable. */
 	struct mutex               icosq_recovery_lock;
@@ -918,7 +914,7 @@ struct mlx5e_priv {
 	bool                       tx_ptp_opened;
 	bool                       rx_ptp_opened;
 	struct hwtstamp_config     tstamp;
-	u16                        q_counter[MLX5_SD_MAX_GROUP_SZ];
+	u16                        q_counter;
 	u16                        drop_rq_q_counter;
 	struct notifier_block      events_nb;
 	struct notifier_block      blocking_events_nb;
@@ -1033,12 +1029,12 @@ struct mlx5e_xsk_param;
 
 struct mlx5e_rq_param;
 int mlx5e_open_rq(struct mlx5e_params *params, struct mlx5e_rq_param *param,
-		  struct mlx5e_xsk_param *xsk, int node, u16 q_counter,
+		  struct mlx5e_xsk_param *xsk, int node,
 		  struct mlx5e_rq *rq);
 #define MLX5E_RQ_WQES_TIMEOUT 20000 /* msecs */
 int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time);
 void mlx5e_close_rq(struct mlx5e_rq *rq);
-int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param, u16 q_counter);
+int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param);
 void mlx5e_destroy_rq(struct mlx5e_rq *rq);
 
 struct mlx5e_sq_param;
@@ -1126,10 +1122,9 @@ static inline bool mlx5_tx_swp_supported(struct mlx5_core_dev *mdev)
 }
 
 extern const struct ethtool_ops mlx5e_ethtool_ops;
-extern const struct mlx5e_profile mlx5e_mgmt_pf_nic_profile;
 
 int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, u32 *mkey);
-int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev, bool create_tises);
+int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev);
 void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev);
 int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb,
 		       bool enable_mc_lb);
@@ -1232,8 +1227,6 @@ netdev_features_t mlx5e_features_check(struct sk_buff *skb,
 				       struct net_device *netdev,
 				       netdev_features_t features);
 int mlx5e_set_features(struct net_device *netdev, netdev_features_t features);
-void mlx5e_nic_set_rx_mode(struct mlx5e_priv *priv);
-
 #ifdef CONFIG_MLX5_ESWITCH
 int mlx5e_set_vf_mac(struct net_device *dev, int vf, u8 *mac);
 int mlx5e_set_vf_rate(struct net_device *dev, int vf, int min_tx_rate, int max_tx_rate);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/channels.c b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.c
index 874a1016623c..48581ea3adcb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/channels.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.c
@@ -23,26 +23,20 @@ bool mlx5e_channels_is_xsk(struct mlx5e_channels *chs, unsigned int ix)
 	return test_bit(MLX5E_CHANNEL_STATE_XSK, c->state);
 }
 
-void mlx5e_channels_get_regular_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn,
-				    u32 *vhca_id)
+void mlx5e_channels_get_regular_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn)
 {
 	struct mlx5e_channel *c = mlx5e_channels_get(chs, ix);
 
 	*rqn = c->rq.rqn;
-	if (vhca_id)
-		*vhca_id = MLX5_CAP_GEN(c->mdev, vhca_id);
 }
 
-void mlx5e_channels_get_xsk_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn,
-				u32 *vhca_id)
+void mlx5e_channels_get_xsk_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn)
 {
 	struct mlx5e_channel *c = mlx5e_channels_get(chs, ix);
 
 	WARN_ON_ONCE(!test_bit(MLX5E_CHANNEL_STATE_XSK, c->state));
 
 	*rqn = c->xskrq.rqn;
-	if (vhca_id)
-		*vhca_id = MLX5_CAP_GEN(c->mdev, vhca_id);
 }
 
 bool mlx5e_channels_get_ptp_rqn(struct mlx5e_channels *chs, u32 *rqn)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/channels.h b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.h
index 6715aa9383b9..637ca90daaa8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/channels.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.h
@@ -10,10 +10,8 @@ struct mlx5e_channels;
 
 unsigned int mlx5e_channels_get_num(struct mlx5e_channels *chs);
 bool mlx5e_channels_is_xsk(struct mlx5e_channels *chs, unsigned int ix);
-void mlx5e_channels_get_regular_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn,
-				    u32 *vhca_id);
-void mlx5e_channels_get_xsk_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn,
-				u32 *vhca_id);
+void mlx5e_channels_get_regular_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn);
+void mlx5e_channels_get_xsk_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn);
 bool mlx5e_channels_get_ptp_rqn(struct mlx5e_channels *chs, u32 *rqn);
 
 #endif /* __MLX5_EN_CHANNELS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/mgmt_pf.c b/drivers/net/ethernet/mellanox/mlx5/core/en/mgmt_pf.c
deleted file mode 100644
index 77b5805895b9..000000000000
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/mgmt_pf.c
+++ /dev/null
@@ -1,268 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
-// Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
-
-#include <linux/kernel.h>
-#include "en/params.h"
-#include "en/health.h"
-#include "lib/eq.h"
-#include "en/dcbnl.h"
-#include "en_accel/ipsec.h"
-#include "en_accel/en_accel.h"
-#include "en/trap.h"
-#include "en/monitor_stats.h"
-#include "en/hv_vhca_stats.h"
-#include "en_rep.h"
-#include "en.h"
-
-static int mgmt_pf_async_event(struct notifier_block *nb, unsigned long event, void *data)
-{
-	struct mlx5e_priv *priv = container_of(nb, struct mlx5e_priv, events_nb);
-	struct mlx5_eqe   *eqe = data;
-
-	if (event != MLX5_EVENT_TYPE_PORT_CHANGE)
-		return NOTIFY_DONE;
-
-	switch (eqe->sub_type) {
-	case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
-	case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
-		queue_work(priv->wq, &priv->update_carrier_work);
-		break;
-	default:
-		return NOTIFY_DONE;
-	}
-
-	return NOTIFY_OK;
-}
-
-static void mlx5e_mgmt_pf_enable_async_events(struct mlx5e_priv *priv)
-{
-	priv->events_nb.notifier_call = mgmt_pf_async_event;
-	mlx5_notifier_register(priv->mdev, &priv->events_nb);
-}
-
-static void mlx5e_disable_mgmt_pf_async_events(struct mlx5e_priv *priv)
-{
-	mlx5_notifier_unregister(priv->mdev, &priv->events_nb);
-}
-
-static void mlx5e_modify_mgmt_pf_admin_state(struct mlx5_core_dev *mdev,
-					     enum mlx5_port_status state)
-{
-	struct mlx5_eswitch *esw = mdev->priv.eswitch;
-	int vport_admin_state;
-
-	mlx5_set_port_admin_status(mdev, state);
-
-	if (state == MLX5_PORT_UP)
-		vport_admin_state = MLX5_VPORT_ADMIN_STATE_AUTO;
-	else
-		vport_admin_state = MLX5_VPORT_ADMIN_STATE_DOWN;
-
-	mlx5_eswitch_set_vport_state(esw, MLX5_VPORT_UPLINK, vport_admin_state);
-}
-
-static void mlx5e_build_mgmt_pf_nic_params(struct mlx5e_priv *priv, u16 mtu)
-{
-	struct mlx5e_params *params = &priv->channels.params;
-	struct mlx5_core_dev *mdev = priv->mdev;
-	u8 rx_cq_period_mode;
-
-	params->sw_mtu = mtu;
-	params->hard_mtu = MLX5E_ETH_HARD_MTU;
-	params->num_channels = 1;
-
-	/* SQ */
-	params->log_sq_size = is_kdump_kernel() ?
-		MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE :
-		MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE;
-	MLX5E_SET_PFLAG(params, MLX5E_PFLAG_SKB_TX_MPWQE, mlx5e_tx_mpwqe_supported(mdev));
-
-	MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_NO_CSUM_COMPLETE, false);
-
-	/* RQ */
-	mlx5e_build_rq_params(mdev, params);
-
-	/* CQ moderation params */
-	rx_cq_period_mode = MLX5_CAP_GEN(mdev, cq_period_start_from_cqe) ?
-			MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
-			MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
-	params->rx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
-	params->tx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
-	mlx5e_set_rx_cq_mode_params(params, rx_cq_period_mode);
-	mlx5e_set_tx_cq_mode_params(params, MLX5_CQ_PERIOD_MODE_START_FROM_EQE);
-
-	/* TX inline */
-	mlx5_query_min_inline(mdev, &params->tx_min_inline_mode);
-}
-
-static int mlx5e_mgmt_pf_init(struct mlx5_core_dev *mdev,
-			      struct net_device *netdev)
-{
-	struct mlx5e_priv *priv = netdev_priv(netdev);
-	struct mlx5e_flow_steering *fs;
-	int err;
-
-	mlx5e_build_mgmt_pf_nic_params(priv, netdev->mtu);
-
-	mlx5e_timestamp_init(priv);
-
-	fs = mlx5e_fs_init(priv->profile, mdev,
-			   !test_bit(MLX5E_STATE_DESTROYING, &priv->state),
-			   priv->dfs_root);
-	if (!fs) {
-		err = -ENOMEM;
-		mlx5_core_err(mdev, "FS initialization failed, %d\n", err);
-		return err;
-	}
-	priv->fs = fs;
-
-	mlx5e_health_create_reporters(priv);
-
-	return 0;
-}
-
-static void mlx5e_mgmt_pf_cleanup(struct mlx5e_priv *priv)
-{
-	mlx5e_health_destroy_reporters(priv);
-	mlx5e_fs_cleanup(priv->fs);
-	priv->fs = NULL;
-}
-
-static int mlx5e_mgmt_pf_init_rx(struct mlx5e_priv *priv)
-{
-	struct mlx5_core_dev *mdev = priv->mdev;
-	int err;
-
-	priv->rx_res = mlx5e_rx_res_create(mdev, 0, priv->max_nch, priv->drop_rq.rqn,
-					   &priv->channels.params.packet_merge,
-					   priv->channels.params.num_channels);
-	if (!priv->rx_res)
-		return -ENOMEM;
-
-	mlx5e_create_q_counters(priv);
-
-	err = mlx5e_open_drop_rq(priv, &priv->drop_rq);
-	if (err) {
-		mlx5_core_err(mdev, "open drop rq failed, %d\n", err);
-		goto err_destroy_q_counters;
-	}
-
-	err = mlx5e_create_flow_steering(priv->fs, priv->rx_res, priv->profile,
-					 priv->netdev);
-	if (err) {
-		mlx5_core_warn(mdev, "create flow steering failed, %d\n", err);
-		goto err_destroy_rx_res;
-	}
-
-	return 0;
-
-err_destroy_rx_res:
-	mlx5e_rx_res_destroy(priv->rx_res);
-	priv->rx_res = NULL;
-	mlx5e_close_drop_rq(&priv->drop_rq);
-err_destroy_q_counters:
-	mlx5e_destroy_q_counters(priv);
-	return err;
-}
-
-static void mlx5e_mgmt_pf_cleanup_rx(struct mlx5e_priv *priv)
-{
-	mlx5e_destroy_flow_steering(priv->fs, !!(priv->netdev->hw_features & NETIF_F_NTUPLE),
-				    priv->profile);
-	mlx5e_rx_res_destroy(priv->rx_res);
-	priv->rx_res = NULL;
-	mlx5e_close_drop_rq(&priv->drop_rq);
-	mlx5e_destroy_q_counters(priv);
-}
-
-static int mlx5e_mgmt_pf_init_tx(struct mlx5e_priv *priv)
-{
-	return 0;
-}
-
-static void mlx5e_mgmt_pf_cleanup_tx(struct mlx5e_priv *priv)
-{
-}
-
-static void mlx5e_mgmt_pf_enable(struct mlx5e_priv *priv)
-{
-	struct net_device *netdev = priv->netdev;
-	struct mlx5_core_dev *mdev = priv->mdev;
-
-	mlx5e_fs_init_l2_addr(priv->fs, netdev);
-
-	/* Marking the link as currently not needed by the Driver */
-	if (!netif_running(netdev))
-		mlx5e_modify_mgmt_pf_admin_state(mdev, MLX5_PORT_DOWN);
-
-	mlx5e_set_netdev_mtu_boundaries(priv);
-	mlx5e_set_dev_port_mtu(priv);
-
-	mlx5e_mgmt_pf_enable_async_events(priv);
-	if (mlx5e_monitor_counter_supported(priv))
-		mlx5e_monitor_counter_init(priv);
-
-	mlx5e_hv_vhca_stats_create(priv);
-	if (netdev->reg_state != NETREG_REGISTERED)
-		return;
-	mlx5e_dcbnl_init_app(priv);
-
-	mlx5e_nic_set_rx_mode(priv);
-
-	rtnl_lock();
-	if (netif_running(netdev))
-		mlx5e_open(netdev);
-	udp_tunnel_nic_reset_ntf(priv->netdev);
-	netif_device_attach(netdev);
-	rtnl_unlock();
-}
-
-static void mlx5e_mgmt_pf_disable(struct mlx5e_priv *priv)
-{
-	if (priv->netdev->reg_state == NETREG_REGISTERED)
-		mlx5e_dcbnl_delete_app(priv);
-
-	rtnl_lock();
-	if (netif_running(priv->netdev))
-		mlx5e_close(priv->netdev);
-	netif_device_detach(priv->netdev);
-	rtnl_unlock();
-
-	mlx5e_nic_set_rx_mode(priv);
-
-	mlx5e_hv_vhca_stats_destroy(priv);
-	if (mlx5e_monitor_counter_supported(priv))
-		mlx5e_monitor_counter_cleanup(priv);
-
-	mlx5e_disable_mgmt_pf_async_events(priv);
-	mlx5e_ipsec_cleanup(priv);
-}
-
-static int mlx5e_mgmt_pf_update_rx(struct mlx5e_priv *priv)
-{
-	return mlx5e_refresh_tirs(priv, false, false);
-}
-
-static int mlx5e_mgmt_pf_max_nch_limit(struct mlx5_core_dev *mdev)
-{
-	return 1;
-}
-
-const struct mlx5e_profile mlx5e_mgmt_pf_nic_profile = {
-	.init		   = mlx5e_mgmt_pf_init,
-	.cleanup	   = mlx5e_mgmt_pf_cleanup,
-	.init_rx	   = mlx5e_mgmt_pf_init_rx,
-	.cleanup_rx	   = mlx5e_mgmt_pf_cleanup_rx,
-	.init_tx	   = mlx5e_mgmt_pf_init_tx,
-	.cleanup_tx	   = mlx5e_mgmt_pf_cleanup_tx,
-	.enable		   = mlx5e_mgmt_pf_enable,
-	.disable	   = mlx5e_mgmt_pf_disable,
-	.update_rx	   = mlx5e_mgmt_pf_update_rx,
-	.update_stats	   = mlx5e_stats_update_ndo_stats,
-	.update_carrier	   = mlx5e_update_carrier,
-	.rx_handlers       = &mlx5e_rx_handlers_nic,
-	.max_tc		   = 1,
-	.max_nch_limit	   = mlx5e_mgmt_pf_max_nch_limit,
-	.stats_grps	   = mlx5e_nic_stats_grps,
-	.stats_grps_num	   = mlx5e_nic_stats_grps_num
-};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c
index e2d8d2754be0..40c8df111754 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c
@@ -20,8 +20,10 @@
 #define NUM_REQ_PPCNT_COUNTER_S1 MLX5_CMD_SET_MONITOR_NUM_PPCNT_COUNTER_SET1
 #define NUM_REQ_Q_COUNTERS_S1    MLX5_CMD_SET_MONITOR_NUM_Q_COUNTERS_SET1
 
-static int mlx5e_monitor_counter_cap(struct mlx5_core_dev *mdev)
+int mlx5e_monitor_counter_supported(struct mlx5e_priv *priv)
 {
+	struct mlx5_core_dev *mdev = priv->mdev;
+
 	if (!MLX5_CAP_GEN(mdev, max_num_of_monitor_counters))
 		return false;
 	if (MLX5_CAP_PCAM_REG(mdev, ppcnt) &&
@@ -34,38 +36,24 @@ static int mlx5e_monitor_counter_cap(struct mlx5_core_dev *mdev)
 	return true;
 }
 
-int mlx5e_monitor_counter_supported(struct mlx5e_priv *priv)
-{
-	struct mlx5_core_dev *pos;
-	int i;
-
-	mlx5_sd_for_each_dev(i, priv->mdev, pos)
-		if (!mlx5e_monitor_counter_cap(pos))
-			return false;
-	return true;
-}
-
-static void mlx5e_monitor_counter_arm(struct mlx5_core_dev *mdev)
+static void mlx5e_monitor_counter_arm(struct mlx5e_priv *priv)
 {
 	u32 in[MLX5_ST_SZ_DW(arm_monitor_counter_in)] = {};
 
 	MLX5_SET(arm_monitor_counter_in, in, opcode,
 		 MLX5_CMD_OP_ARM_MONITOR_COUNTER);
-	mlx5_cmd_exec_in(mdev, arm_monitor_counter, in);
+	mlx5_cmd_exec_in(priv->mdev, arm_monitor_counter, in);
 }
 
 static void mlx5e_monitor_counters_work(struct work_struct *work)
 {
 	struct mlx5e_priv *priv = container_of(work, struct mlx5e_priv,
 					       monitor_counters_work);
-	struct mlx5_core_dev *pos;
-	int i;
 
 	mutex_lock(&priv->state_lock);
 	mlx5e_stats_update_ndo_stats(priv);
 	mutex_unlock(&priv->state_lock);
-	mlx5_sd_for_each_dev(i, priv->mdev, pos)
-		mlx5e_monitor_counter_arm(pos);
+	mlx5e_monitor_counter_arm(priv);
 }
 
 static int mlx5e_monitor_event_handler(struct notifier_block *nb,
@@ -109,13 +97,15 @@ static int fill_monitor_counter_q_counter_set1(int cnt, int q_counter, u32 *in)
 }
 
 /* check if mlx5e_monitor_counter_supported before calling this function*/
-static void mlx5e_set_monitor_counter(struct mlx5_core_dev *mdev, int q_counter)
+static void mlx5e_set_monitor_counter(struct mlx5e_priv *priv)
 {
+	struct mlx5_core_dev *mdev = priv->mdev;
 	int max_num_of_counters = MLX5_CAP_GEN(mdev, max_num_of_monitor_counters);
 	int num_q_counters      = MLX5_CAP_GEN(mdev, num_q_monitor_counters);
 	int num_ppcnt_counters  = !MLX5_CAP_PCAM_REG(mdev, ppcnt) ? 0 :
 				  MLX5_CAP_GEN(mdev, num_ppcnt_monitor_counters);
 	u32 in[MLX5_ST_SZ_DW(set_monitor_counter_in)] = {};
+	int q_counter = priv->q_counter;
 	int cnt	= 0;
 
 	if (num_ppcnt_counters  >=  NUM_REQ_PPCNT_COUNTER_S1 &&
@@ -137,17 +127,13 @@ static void mlx5e_set_monitor_counter(struct mlx5_core_dev *mdev, int q_counter)
 /* check if mlx5e_monitor_counter_supported before calling this function*/
 void mlx5e_monitor_counter_init(struct mlx5e_priv *priv)
 {
-	struct mlx5_core_dev *pos;
-	int i;
-
 	INIT_WORK(&priv->monitor_counters_work, mlx5e_monitor_counters_work);
 	MLX5_NB_INIT(&priv->monitor_counters_nb, mlx5e_monitor_event_handler,
 		     MONITOR_COUNTER);
-	mlx5_sd_for_each_dev(i, priv->mdev, pos) {
-		mlx5_eq_notifier_register(pos, &priv->monitor_counters_nb);
-		mlx5e_set_monitor_counter(pos, priv->q_counter[i]);
-		mlx5e_monitor_counter_arm(pos);
-	}
+	mlx5_eq_notifier_register(priv->mdev, &priv->monitor_counters_nb);
+
+	mlx5e_set_monitor_counter(priv);
+	mlx5e_monitor_counter_arm(priv);
 	queue_work(priv->wq, &priv->update_stats_work);
 }
 
@@ -155,15 +141,11 @@ void mlx5e_monitor_counter_init(struct mlx5e_priv *priv)
 void mlx5e_monitor_counter_cleanup(struct mlx5e_priv *priv)
 {
 	u32 in[MLX5_ST_SZ_DW(set_monitor_counter_in)] = {};
-	struct mlx5_core_dev *pos;
-	int i;
 
 	MLX5_SET(set_monitor_counter_in, in, opcode,
 		 MLX5_CMD_OP_SET_MONITOR_COUNTER);
 
-	mlx5_sd_for_each_dev(i, priv->mdev, pos) {
-		mlx5_cmd_exec_in(pos, set_monitor_counter, in);
-		mlx5_eq_notifier_unregister(pos, &priv->monitor_counters_nb);
-	}
+	mlx5_cmd_exec_in(priv->mdev, set_monitor_counter, in);
+	mlx5_eq_notifier_unregister(priv->mdev, &priv->monitor_counters_nb);
 	cancel_work_sync(&priv->monitor_counters_work);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
index fb10bb166fbb..284253b79266 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
@@ -674,7 +674,7 @@ void mlx5e_build_create_cq_param(struct mlx5e_create_cq_param *ccp, struct mlx5e
 		.napi = &c->napi,
 		.ch_stats = c->stats,
 		.node = cpu_to_node(c->cpu),
-		.ix = c->vec_ix,
+		.ix = c->ix,
 	};
 }
 
@@ -945,6 +945,7 @@ static u8 rq_end_pad_mode(struct mlx5_core_dev *mdev, struct mlx5e_params *param
 int mlx5e_build_rq_param(struct mlx5_core_dev *mdev,
 			 struct mlx5e_params *params,
 			 struct mlx5e_xsk_param *xsk,
+			 u16 q_counter,
 			 struct mlx5e_rq_param *param)
 {
 	void *rqc = param->rqc;
@@ -1006,6 +1007,7 @@ int mlx5e_build_rq_param(struct mlx5_core_dev *mdev,
 	MLX5_SET(wq, wq, log_wq_stride,
 		 mlx5e_get_rqwq_log_stride(params->rq_wq_type, ndsegs));
 	MLX5_SET(wq, wq, pd,               mdev->mlx5e_res.hw_objs.pdn);
+	MLX5_SET(rqc, rqc, counter_set_id, q_counter);
 	MLX5_SET(rqc, rqc, vsd,            params->vlan_strip_disable);
 	MLX5_SET(rqc, rqc, scatter_fcs,    params->scatter_fcs_en);
 
@@ -1016,6 +1018,7 @@ int mlx5e_build_rq_param(struct mlx5_core_dev *mdev,
 }
 
 void mlx5e_build_drop_rq_param(struct mlx5_core_dev *mdev,
+			       u16 q_counter,
 			       struct mlx5e_rq_param *param)
 {
 	void *rqc = param->rqc;
@@ -1024,6 +1027,7 @@ void mlx5e_build_drop_rq_param(struct mlx5_core_dev *mdev,
 	MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_CYCLIC);
 	MLX5_SET(wq, wq, log_wq_stride,
 		 mlx5e_get_rqwq_log_stride(MLX5_WQ_TYPE_CYCLIC, 1));
+	MLX5_SET(rqc, rqc, counter_set_id, q_counter);
 
 	param->wq.buf_numa_node = dev_to_node(mlx5_core_dma_dev(mdev));
 }
@@ -1288,12 +1292,13 @@ void mlx5e_build_xdpsq_param(struct mlx5_core_dev *mdev,
 
 int mlx5e_build_channel_param(struct mlx5_core_dev *mdev,
 			      struct mlx5e_params *params,
+			      u16 q_counter,
 			      struct mlx5e_channel_param *cparam)
 {
 	u8 icosq_log_wq_sz, async_icosq_log_wq_sz;
 	int err;
 
-	err = mlx5e_build_rq_param(mdev, params, NULL, &cparam->rq);
+	err = mlx5e_build_rq_param(mdev, params, NULL, q_counter, &cparam->rq);
 	if (err)
 		return err;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
index 9a781f18b57f..6800949dafbc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
@@ -130,8 +130,10 @@ void mlx5e_build_create_cq_param(struct mlx5e_create_cq_param *ccp, struct mlx5e
 int mlx5e_build_rq_param(struct mlx5_core_dev *mdev,
 			 struct mlx5e_params *params,
 			 struct mlx5e_xsk_param *xsk,
+			 u16 q_counter,
 			 struct mlx5e_rq_param *param);
 void mlx5e_build_drop_rq_param(struct mlx5_core_dev *mdev,
+			       u16 q_counter,
 			       struct mlx5e_rq_param *param);
 void mlx5e_build_sq_param_common(struct mlx5_core_dev *mdev,
 				 struct mlx5e_sq_param *param);
@@ -147,6 +149,7 @@ void mlx5e_build_xdpsq_param(struct mlx5_core_dev *mdev,
 			     struct mlx5e_sq_param *param);
 int mlx5e_build_channel_param(struct mlx5_core_dev *mdev,
 			      struct mlx5e_params *params,
+			      u16 q_counter,
 			      struct mlx5e_channel_param *cparam);
 
 u16 mlx5e_calc_sq_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *params);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
index cafb41895f94..c206cc0a8483 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
@@ -646,6 +646,7 @@ static void mlx5e_ptp_build_sq_param(struct mlx5_core_dev *mdev,
 
 static void mlx5e_ptp_build_rq_param(struct mlx5_core_dev *mdev,
 				     struct net_device *netdev,
+				     u16 q_counter,
 				     struct mlx5e_ptp_params *ptp_params)
 {
 	struct mlx5e_rq_param *rq_params = &ptp_params->rq_param;
@@ -654,7 +655,7 @@ static void mlx5e_ptp_build_rq_param(struct mlx5_core_dev *mdev,
 	params->rq_wq_type = MLX5_WQ_TYPE_CYCLIC;
 	mlx5e_init_rq_type_params(mdev, params);
 	params->sw_mtu = netdev->max_mtu;
-	mlx5e_build_rq_param(mdev, params, NULL, rq_params);
+	mlx5e_build_rq_param(mdev, params, NULL, q_counter, rq_params);
 }
 
 static void mlx5e_ptp_build_params(struct mlx5e_ptp *c,
@@ -680,7 +681,7 @@ static void mlx5e_ptp_build_params(struct mlx5e_ptp *c,
 	/* RQ */
 	if (test_bit(MLX5E_PTP_STATE_RX, c->state)) {
 		params->vlan_strip_disable = orig->vlan_strip_disable;
-		mlx5e_ptp_build_rq_param(c->mdev, c->netdev, cparams);
+		mlx5e_ptp_build_rq_param(c->mdev, c->netdev, c->priv->q_counter, cparams);
 	}
 }
 
@@ -713,16 +714,13 @@ static int mlx5e_ptp_open_rq(struct mlx5e_ptp *c, struct mlx5e_params *params,
 			     struct mlx5e_rq_param *rq_param)
 {
 	int node = dev_to_node(c->mdev->device);
-	int err, sd_ix;
-	u16 q_counter;
+	int err;
 
 	err = mlx5e_init_ptp_rq(c, params, &c->rq);
 	if (err)
 		return err;
 
-	sd_ix = mlx5_sd_ch_ix_get_dev_ix(c->mdev, MLX5E_PTP_CHANNEL_IX);
-	q_counter = c->priv->q_counter[sd_ix];
-	return mlx5e_open_rq(params, rq_param, NULL, node, q_counter, &c->rq);
+	return mlx5e_open_rq(params, rq_param, NULL, node, &c->rq);
 }
 
 static int mlx5e_ptp_open_queues(struct mlx5e_ptp *c,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c
index e87e26f2c669..34adf8c3f81a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c
@@ -122,8 +122,8 @@ int mlx5e_open_qos_sq(struct mlx5e_priv *priv, struct mlx5e_channels *chs,
 
 	memset(&param_sq, 0, sizeof(param_sq));
 	memset(&param_cq, 0, sizeof(param_cq));
-	mlx5e_build_sq_param(c->mdev, params, &param_sq);
-	mlx5e_build_tx_cq_param(c->mdev, params, &param_cq);
+	mlx5e_build_sq_param(priv->mdev, params, &param_sq);
+	mlx5e_build_tx_cq_param(priv->mdev, params, &param_cq);
 	err = mlx5e_open_cq(c->mdev, params->tx_cq_moderation, &param_cq, &ccp, &sq->cq);
 	if (err)
 		goto err_free_sq;
@@ -176,7 +176,7 @@ int mlx5e_activate_qos_sq(void *data, u16 node_qid, u32 hw_id)
 	 */
 	smp_wmb();
 
-	qos_dbg(sq->mdev, "Activate QoS SQ qid %u\n", node_qid);
+	qos_dbg(priv->mdev, "Activate QoS SQ qid %u\n", node_qid);
 	mlx5e_activate_txqsq(sq);
 
 	return 0;
@@ -190,7 +190,7 @@ void mlx5e_deactivate_qos_sq(struct mlx5e_priv *priv, u16 qid)
 	if (!sq) /* Handle the case when the SQ failed to open. */
 		return;
 
-	qos_dbg(sq->mdev, "Deactivate QoS SQ qid %u\n", qid);
+	qos_dbg(priv->mdev, "Deactivate QoS SQ qid %u\n", qid);
 	mlx5e_deactivate_txqsq(sq);
 
 	priv->txq2sq[mlx5e_qid_from_qos(&priv->channels, qid)] = NULL;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
index 25d751eba99b..4358798d6ce1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
@@ -294,8 +294,8 @@ static void mlx5e_rx_reporter_diagnose_generic_rq(struct mlx5e_rq *rq,
 
 	params = &priv->channels.params;
 	rq_sz = mlx5e_rqwq_get_size(rq);
-	real_time =  mlx5_is_real_time_rq(rq->mdev);
-	rq_stride = BIT(mlx5e_mpwqe_get_log_stride_size(rq->mdev, params, NULL));
+	real_time =  mlx5_is_real_time_rq(priv->mdev);
+	rq_stride = BIT(mlx5e_mpwqe_get_log_stride_size(priv->mdev, params, NULL));
 
 	mlx5e_health_fmsg_named_obj_nest_start(fmsg, "RQ");
 	devlink_fmsg_u8_pair_put(fmsg, "type", params->rq_wq_type);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index 0ab9db319530..6b44ddce14e9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -219,6 +219,7 @@ mlx5e_tx_reporter_build_diagnose_output_sq_common(struct devlink_fmsg *fmsg,
 						  struct mlx5e_txqsq *sq, int tc)
 {
 	bool stopped = netif_xmit_stopped(sq->txq);
+	struct mlx5e_priv *priv = sq->priv;
 	u8 state;
 	int err;
 
@@ -226,7 +227,7 @@ mlx5e_tx_reporter_build_diagnose_output_sq_common(struct devlink_fmsg *fmsg,
 	devlink_fmsg_u32_pair_put(fmsg, "txq ix", sq->txq_ix);
 	devlink_fmsg_u32_pair_put(fmsg, "sqn", sq->sqn);
 
-	err = mlx5_core_query_sq_state(sq->mdev, sq->sqn, &state);
+	err = mlx5_core_query_sq_state(priv->mdev, sq->sqn, &state);
 	if (!err)
 		devlink_fmsg_u8_pair_put(fmsg, "HW state", state);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c
index bcafb4bf9415..7b8ff7a71003 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c
@@ -4,33 +4,6 @@
 #include "rqt.h"
 #include <linux/mlx5/transobj.h>
 
-static bool verify_num_vhca_ids(struct mlx5_core_dev *mdev, u32 *vhca_ids,
-				unsigned int size)
-{
-	unsigned int max_num_vhca_id = MLX5_CAP_GEN_2(mdev, max_rqt_vhca_id);
-	int i;
-
-	/* Verify that all vhca_ids are in range [0, max_num_vhca_ids - 1] */
-	for (i = 0; i < size; i++)
-		if (vhca_ids[i] >= max_num_vhca_id)
-			return false;
-	return true;
-}
-
-static bool rqt_verify_vhca_ids(struct mlx5_core_dev *mdev, u32 *vhca_ids,
-				unsigned int size)
-{
-	if (!vhca_ids)
-		return true;
-
-	if (!MLX5_CAP_GEN(mdev, cross_vhca_rqt))
-		return false;
-	if (!verify_num_vhca_ids(mdev, vhca_ids, size))
-		return false;
-
-	return true;
-}
-
 void mlx5e_rss_params_indir_init_uniform(struct mlx5e_rss_params_indir *indir,
 					 unsigned int num_channels)
 {
@@ -40,38 +13,19 @@ void mlx5e_rss_params_indir_init_uniform(struct mlx5e_rss_params_indir *indir,
 		indir->table[i] = i % num_channels;
 }
 
-static void fill_rqn_list(void *rqtc, u32 *rqns, u32 *vhca_ids, unsigned int size)
-{
-	unsigned int i;
-
-	if (vhca_ids) {
-		MLX5_SET(rqtc, rqtc, rq_vhca_id_format, 1);
-		for (i = 0; i < size; i++) {
-			MLX5_SET(rqtc, rqtc, rq_vhca[i].rq_num, rqns[i]);
-			MLX5_SET(rqtc, rqtc, rq_vhca[i].rq_vhca_id, vhca_ids[i]);
-		}
-	} else {
-		for (i = 0; i < size; i++)
-			MLX5_SET(rqtc, rqtc, rq_num[i], rqns[i]);
-	}
-}
 static int mlx5e_rqt_init(struct mlx5e_rqt *rqt, struct mlx5_core_dev *mdev,
-			  u16 max_size, u32 *init_rqns, u32 *init_vhca_ids, u16 init_size)
+			  u16 max_size, u32 *init_rqns, u16 init_size)
 {
-	int entry_sz;
 	void *rqtc;
 	int inlen;
 	int err;
 	u32 *in;
-
-	if (!rqt_verify_vhca_ids(mdev, init_vhca_ids, init_size))
-		return -EOPNOTSUPP;
+	int i;
 
 	rqt->mdev = mdev;
 	rqt->size = max_size;
 
-	entry_sz = init_vhca_ids ? MLX5_ST_SZ_BYTES(rq_vhca) : MLX5_ST_SZ_BYTES(rq_num);
-	inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + entry_sz * init_size;
+	inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + sizeof(u32) * init_size;
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if (!in)
 		return -ENOMEM;
@@ -79,9 +33,10 @@ static int mlx5e_rqt_init(struct mlx5e_rqt *rqt, struct mlx5_core_dev *mdev,
 	rqtc = MLX5_ADDR_OF(create_rqt_in, in, rqt_context);
 
 	MLX5_SET(rqtc, rqtc, rqt_max_size, rqt->size);
-	MLX5_SET(rqtc, rqtc, rqt_actual_size, init_size);
 
-	fill_rqn_list(rqtc, init_rqns, init_vhca_ids, init_size);
+	MLX5_SET(rqtc, rqtc, rqt_actual_size, init_size);
+	for (i = 0; i < init_size; i++)
+		MLX5_SET(rqtc, rqtc, rq_num[i], init_rqns[i]);
 
 	err = mlx5_core_create_rqt(rqt->mdev, in, inlen, &rqt->rqtn);
 
@@ -94,7 +49,7 @@ int mlx5e_rqt_init_direct(struct mlx5e_rqt *rqt, struct mlx5_core_dev *mdev,
 {
 	u16 max_size = indir_enabled ? indir_table_size : 1;
 
-	return mlx5e_rqt_init(rqt, mdev, max_size, &init_rqn, NULL, 1);
+	return mlx5e_rqt_init(rqt, mdev, max_size, &init_rqn, 1);
 }
 
 static int mlx5e_bits_invert(unsigned long a, int size)
@@ -108,8 +63,7 @@ static int mlx5e_bits_invert(unsigned long a, int size)
 	return inv;
 }
 
-static int mlx5e_calc_indir_rqns(u32 *rss_rqns, u32 *rqns, u32 *rss_vhca_ids, u32 *vhca_ids,
-				 unsigned int num_rqns,
+static int mlx5e_calc_indir_rqns(u32 *rss_rqns, u32 *rqns, unsigned int num_rqns,
 				 u8 hfunc, struct mlx5e_rss_params_indir *indir)
 {
 	unsigned int i;
@@ -128,42 +82,30 @@ static int mlx5e_calc_indir_rqns(u32 *rss_rqns, u32 *rqns, u32 *rss_vhca_ids, u3
 			 */
 			return -EINVAL;
 		rss_rqns[i] = rqns[ix];
-		if (vhca_ids)
-			rss_vhca_ids[i] = vhca_ids[ix];
 	}
 
 	return 0;
 }
 
 int mlx5e_rqt_init_indir(struct mlx5e_rqt *rqt, struct mlx5_core_dev *mdev,
-			 u32 *rqns, u32 *vhca_ids, unsigned int num_rqns,
+			 u32 *rqns, unsigned int num_rqns,
 			 u8 hfunc, struct mlx5e_rss_params_indir *indir)
 {
-	u32 *rss_rqns, *rss_vhca_ids = NULL;
+	u32 *rss_rqns;
 	int err;
 
 	rss_rqns = kvmalloc_array(indir->actual_table_size, sizeof(*rss_rqns), GFP_KERNEL);
 	if (!rss_rqns)
 		return -ENOMEM;
 
-	if (vhca_ids) {
-		rss_vhca_ids = kvmalloc_array(indir->actual_table_size, sizeof(*rss_vhca_ids),
-					      GFP_KERNEL);
-		if (!rss_vhca_ids) {
-			kvfree(rss_rqns);
-			return -ENOMEM;
-		}
-	}
-
-	err = mlx5e_calc_indir_rqns(rss_rqns, rqns, rss_vhca_ids, vhca_ids, num_rqns, hfunc, indir);
+	err = mlx5e_calc_indir_rqns(rss_rqns, rqns, num_rqns, hfunc, indir);
 	if (err)
 		goto out;
 
-	err = mlx5e_rqt_init(rqt, mdev, indir->max_table_size, rss_rqns, rss_vhca_ids,
+	err = mlx5e_rqt_init(rqt, mdev, indir->max_table_size, rss_rqns,
 			     indir->actual_table_size);
 
 out:
-	kvfree(rss_vhca_ids);
 	kvfree(rss_rqns);
 	return err;
 }
@@ -184,20 +126,15 @@ void mlx5e_rqt_destroy(struct mlx5e_rqt *rqt)
 	mlx5_core_destroy_rqt(rqt->mdev, rqt->rqtn);
 }
 
-static int mlx5e_rqt_redirect(struct mlx5e_rqt *rqt, u32 *rqns, u32 *vhca_ids,
-			      unsigned int size)
+static int mlx5e_rqt_redirect(struct mlx5e_rqt *rqt, u32 *rqns, unsigned int size)
 {
-	int entry_sz;
+	unsigned int i;
 	void *rqtc;
 	int inlen;
 	u32 *in;
 	int err;
 
-	if (!rqt_verify_vhca_ids(rqt->mdev, vhca_ids, size))
-		return -EINVAL;
-
-	entry_sz = vhca_ids ? MLX5_ST_SZ_BYTES(rq_vhca) : MLX5_ST_SZ_BYTES(rq_num);
-	inlen = MLX5_ST_SZ_BYTES(modify_rqt_in) + entry_sz * size;
+	inlen = MLX5_ST_SZ_BYTES(modify_rqt_in) + sizeof(u32) * size;
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if (!in)
 		return -ENOMEM;
@@ -206,8 +143,8 @@ static int mlx5e_rqt_redirect(struct mlx5e_rqt *rqt, u32 *rqns, u32 *vhca_ids,
 
 	MLX5_SET(modify_rqt_in, in, bitmask.rqn_list, 1);
 	MLX5_SET(rqtc, rqtc, rqt_actual_size, size);
-
-	fill_rqn_list(rqtc, rqns, vhca_ids, size);
+	for (i = 0; i < size; i++)
+		MLX5_SET(rqtc, rqtc, rq_num[i], rqns[i]);
 
 	err = mlx5_core_modify_rqt(rqt->mdev, rqt->rqtn, in, inlen);
 
@@ -215,21 +152,17 @@ static int mlx5e_rqt_redirect(struct mlx5e_rqt *rqt, u32 *rqns, u32 *vhca_ids,
 	return err;
 }
 
-int mlx5e_rqt_redirect_direct(struct mlx5e_rqt *rqt, u32 rqn, u32 *vhca_id)
+int mlx5e_rqt_redirect_direct(struct mlx5e_rqt *rqt, u32 rqn)
 {
-	return mlx5e_rqt_redirect(rqt, &rqn, vhca_id, 1);
+	return mlx5e_rqt_redirect(rqt, &rqn, 1);
 }
 
-int mlx5e_rqt_redirect_indir(struct mlx5e_rqt *rqt, u32 *rqns, u32 *vhca_ids,
-			     unsigned int num_rqns,
+int mlx5e_rqt_redirect_indir(struct mlx5e_rqt *rqt, u32 *rqns, unsigned int num_rqns,
 			     u8 hfunc, struct mlx5e_rss_params_indir *indir)
 {
-	u32 *rss_rqns, *rss_vhca_ids = NULL;
+	u32 *rss_rqns;
 	int err;
 
-	if (!rqt_verify_vhca_ids(rqt->mdev, vhca_ids, num_rqns))
-		return -EINVAL;
-
 	if (WARN_ON(rqt->size != indir->max_table_size))
 		return -EINVAL;
 
@@ -237,23 +170,13 @@ int mlx5e_rqt_redirect_indir(struct mlx5e_rqt *rqt, u32 *rqns, u32 *vhca_ids,
 	if (!rss_rqns)
 		return -ENOMEM;
 
-	if (vhca_ids) {
-		rss_vhca_ids = kvmalloc_array(indir->actual_table_size, sizeof(*rss_vhca_ids),
-					      GFP_KERNEL);
-		if (!rss_vhca_ids) {
-			kvfree(rss_rqns);
-			return -ENOMEM;
-		}
-	}
-
-	err = mlx5e_calc_indir_rqns(rss_rqns, rqns, rss_vhca_ids, vhca_ids, num_rqns, hfunc, indir);
+	err = mlx5e_calc_indir_rqns(rss_rqns, rqns, num_rqns, hfunc, indir);
 	if (err)
 		goto out;
 
-	err = mlx5e_rqt_redirect(rqt, rss_rqns, rss_vhca_ids, indir->actual_table_size);
+	err = mlx5e_rqt_redirect(rqt, rss_rqns, indir->actual_table_size);
 
 out:
-	kvfree(rss_vhca_ids);
 	kvfree(rss_rqns);
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h
index e0bc30308c77..77fba3ebd18d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h
@@ -20,7 +20,7 @@ void mlx5e_rss_params_indir_init_uniform(struct mlx5e_rss_params_indir *indir,
 					 unsigned int num_channels);
 
 struct mlx5e_rqt {
-	struct mlx5_core_dev *mdev; /* primary */
+	struct mlx5_core_dev *mdev;
 	u32 rqtn;
 	u16 size;
 };
@@ -28,7 +28,7 @@ struct mlx5e_rqt {
 int mlx5e_rqt_init_direct(struct mlx5e_rqt *rqt, struct mlx5_core_dev *mdev,
 			  bool indir_enabled, u32 init_rqn, u32 indir_table_size);
 int mlx5e_rqt_init_indir(struct mlx5e_rqt *rqt, struct mlx5_core_dev *mdev,
-			 u32 *rqns, u32 *vhca_ids, unsigned int num_rqns,
+			 u32 *rqns, unsigned int num_rqns,
 			 u8 hfunc, struct mlx5e_rss_params_indir *indir);
 void mlx5e_rqt_destroy(struct mlx5e_rqt *rqt);
 
@@ -38,9 +38,8 @@ static inline u32 mlx5e_rqt_get_rqtn(struct mlx5e_rqt *rqt)
 }
 
 u32 mlx5e_rqt_size(struct mlx5_core_dev *mdev, unsigned int num_channels);
-int mlx5e_rqt_redirect_direct(struct mlx5e_rqt *rqt, u32 rqn, u32 *vhca_id);
-int mlx5e_rqt_redirect_indir(struct mlx5e_rqt *rqt, u32 *rqns, u32 *vhca_ids,
-			     unsigned int num_rqns,
+int mlx5e_rqt_redirect_direct(struct mlx5e_rqt *rqt, u32 rqn);
+int mlx5e_rqt_redirect_indir(struct mlx5e_rqt *rqt, u32 *rqns, unsigned int num_rqns,
 			     u8 hfunc, struct mlx5e_rss_params_indir *indir);
 
 #endif /* __MLX5_EN_RQT_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c
index 5f742f896600..c1545a2e8d6d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c
@@ -74,7 +74,7 @@ struct mlx5e_rss {
 	struct mlx5e_tir *tir[MLX5E_NUM_INDIR_TIRS];
 	struct mlx5e_tir *inner_tir[MLX5E_NUM_INDIR_TIRS];
 	struct mlx5e_rqt rqt;
-	struct mlx5_core_dev *mdev; /* primary */
+	struct mlx5_core_dev *mdev;
 	u32 drop_rqn;
 	bool inner_ft_support;
 	bool enabled;
@@ -473,22 +473,21 @@ int mlx5e_rss_obtain_tirn(struct mlx5e_rss *rss,
 	return 0;
 }
 
-static int mlx5e_rss_apply(struct mlx5e_rss *rss, u32 *rqns, u32 *vhca_ids, unsigned int num_rqns)
+static int mlx5e_rss_apply(struct mlx5e_rss *rss, u32 *rqns, unsigned int num_rqns)
 {
 	int err;
 
-	err = mlx5e_rqt_redirect_indir(&rss->rqt, rqns, vhca_ids, num_rqns, rss->hash.hfunc,
-				       &rss->indir);
+	err = mlx5e_rqt_redirect_indir(&rss->rqt, rqns, num_rqns, rss->hash.hfunc, &rss->indir);
 	if (err)
 		mlx5e_rss_warn(rss->mdev, "Failed to redirect RQT %#x to channels: err = %d\n",
 			       mlx5e_rqt_get_rqtn(&rss->rqt), err);
 	return err;
 }
 
-void mlx5e_rss_enable(struct mlx5e_rss *rss, u32 *rqns, u32 *vhca_ids, unsigned int num_rqns)
+void mlx5e_rss_enable(struct mlx5e_rss *rss, u32 *rqns, unsigned int num_rqns)
 {
 	rss->enabled = true;
-	mlx5e_rss_apply(rss, rqns, vhca_ids, num_rqns);
+	mlx5e_rss_apply(rss, rqns, num_rqns);
 }
 
 void mlx5e_rss_disable(struct mlx5e_rss *rss)
@@ -496,7 +495,7 @@ void mlx5e_rss_disable(struct mlx5e_rss *rss)
 	int err;
 
 	rss->enabled = false;
-	err = mlx5e_rqt_redirect_direct(&rss->rqt, rss->drop_rqn, NULL);
+	err = mlx5e_rqt_redirect_direct(&rss->rqt, rss->drop_rqn);
 	if (err)
 		mlx5e_rss_warn(rss->mdev, "Failed to redirect RQT %#x to drop RQ %#x: err = %d\n",
 			       mlx5e_rqt_get_rqtn(&rss->rqt), rss->drop_rqn, err);
@@ -569,7 +568,7 @@ int mlx5e_rss_get_rxfh(struct mlx5e_rss *rss, u32 *indir, u8 *key, u8 *hfunc)
 
 int mlx5e_rss_set_rxfh(struct mlx5e_rss *rss, const u32 *indir,
 		       const u8 *key, const u8 *hfunc,
-		       u32 *rqns, u32 *vhca_ids, unsigned int num_rqns)
+		       u32 *rqns, unsigned int num_rqns)
 {
 	bool changed_indir = false;
 	bool changed_hash = false;
@@ -609,7 +608,7 @@ int mlx5e_rss_set_rxfh(struct mlx5e_rss *rss, const u32 *indir,
 	}
 
 	if (changed_indir && rss->enabled) {
-		err = mlx5e_rss_apply(rss, rqns, vhca_ids, num_rqns);
+		err = mlx5e_rss_apply(rss, rqns, num_rqns);
 		if (err) {
 			mlx5e_rss_copy(rss, old_rss);
 			goto out;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h
index d0df98963c8d..d1d0bc350e92 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h
@@ -39,7 +39,7 @@ int mlx5e_rss_obtain_tirn(struct mlx5e_rss *rss,
 			  const struct mlx5e_packet_merge_param *init_pkt_merge_param,
 			  bool inner, u32 *tirn);
 
-void mlx5e_rss_enable(struct mlx5e_rss *rss, u32 *rqns, u32 *vhca_ids, unsigned int num_rqns);
+void mlx5e_rss_enable(struct mlx5e_rss *rss, u32 *rqns, unsigned int num_rqns);
 void mlx5e_rss_disable(struct mlx5e_rss *rss);
 
 int mlx5e_rss_packet_merge_set_param(struct mlx5e_rss *rss,
@@ -47,7 +47,7 @@ int mlx5e_rss_packet_merge_set_param(struct mlx5e_rss *rss,
 int mlx5e_rss_get_rxfh(struct mlx5e_rss *rss, u32 *indir, u8 *key, u8 *hfunc);
 int mlx5e_rss_set_rxfh(struct mlx5e_rss *rss, const u32 *indir,
 		       const u8 *key, const u8 *hfunc,
-		       u32 *rqns, u32 *vhca_ids, unsigned int num_rqns);
+		       u32 *rqns, unsigned int num_rqns);
 struct mlx5e_rss_params_hash mlx5e_rss_get_hash(struct mlx5e_rss *rss);
 u8 mlx5e_rss_get_hash_fields(struct mlx5e_rss *rss, enum mlx5_traffic_types tt);
 int mlx5e_rss_set_hash_fields(struct mlx5e_rss *rss, enum mlx5_traffic_types tt,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
index a86eade9a9e0..b23e224e3763 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
@@ -8,7 +8,7 @@
 #define MLX5E_MAX_NUM_RSS 16
 
 struct mlx5e_rx_res {
-	struct mlx5_core_dev *mdev; /* primary */
+	struct mlx5_core_dev *mdev;
 	enum mlx5e_rx_res_features features;
 	unsigned int max_nch;
 	u32 drop_rqn;
@@ -19,7 +19,6 @@ struct mlx5e_rx_res {
 	struct mlx5e_rss *rss[MLX5E_MAX_NUM_RSS];
 	bool rss_active;
 	u32 *rss_rqns;
-	u32 *rss_vhca_ids;
 	unsigned int rss_nch;
 
 	struct {
@@ -35,13 +34,6 @@ struct mlx5e_rx_res {
 
 /* API for rx_res_rss_* */
 
-static u32 *get_vhca_ids(struct mlx5e_rx_res *res, int offset)
-{
-	bool multi_vhca = res->features & MLX5E_RX_RES_FEATURE_MULTI_VHCA;
-
-	return multi_vhca ? res->rss_vhca_ids + offset : NULL;
-}
-
 void mlx5e_rx_res_rss_update_num_channels(struct mlx5e_rx_res *res, u32 nch)
 {
 	int i;
@@ -93,11 +85,8 @@ int mlx5e_rx_res_rss_init(struct mlx5e_rx_res *res, u32 *rss_idx, unsigned int i
 		return PTR_ERR(rss);
 
 	mlx5e_rss_set_indir_uniform(rss, init_nch);
-	if (res->rss_active) {
-		u32 *vhca_ids = get_vhca_ids(res, 0);
-
-		mlx5e_rss_enable(rss, res->rss_rqns, vhca_ids, res->rss_nch);
-	}
+	if (res->rss_active)
+		mlx5e_rss_enable(rss, res->rss_rqns, res->rss_nch);
 
 	res->rss[i] = rss;
 	*rss_idx = i;
@@ -164,12 +153,10 @@ static void mlx5e_rx_res_rss_enable(struct mlx5e_rx_res *res)
 
 	for (i = 0; i < MLX5E_MAX_NUM_RSS; i++) {
 		struct mlx5e_rss *rss = res->rss[i];
-		u32 *vhca_ids;
 
 		if (!rss)
 			continue;
-		vhca_ids = get_vhca_ids(res, 0);
-		mlx5e_rss_enable(rss, res->rss_rqns, vhca_ids, res->rss_nch);
+		mlx5e_rss_enable(rss, res->rss_rqns, res->rss_nch);
 	}
 }
 
@@ -213,7 +200,6 @@ int mlx5e_rx_res_rss_get_rxfh(struct mlx5e_rx_res *res, u32 rss_idx,
 int mlx5e_rx_res_rss_set_rxfh(struct mlx5e_rx_res *res, u32 rss_idx,
 			      const u32 *indir, const u8 *key, const u8 *hfunc)
 {
-	u32 *vhca_ids = get_vhca_ids(res, 0);
 	struct mlx5e_rss *rss;
 
 	if (rss_idx >= MLX5E_MAX_NUM_RSS)
@@ -223,8 +209,7 @@ int mlx5e_rx_res_rss_set_rxfh(struct mlx5e_rx_res *res, u32 rss_idx,
 	if (!rss)
 		return -ENOENT;
 
-	return mlx5e_rss_set_rxfh(rss, indir, key, hfunc, res->rss_rqns, vhca_ids,
-				  res->rss_nch);
+	return mlx5e_rss_set_rxfh(rss, indir, key, hfunc, res->rss_rqns, res->rss_nch);
 }
 
 int mlx5e_rx_res_rss_get_hash_fields(struct mlx5e_rx_res *res, u32 rss_idx,
@@ -295,13 +280,11 @@ struct mlx5e_rss *mlx5e_rx_res_rss_get(struct mlx5e_rx_res *res, u32 rss_idx)
 
 static void mlx5e_rx_res_free(struct mlx5e_rx_res *res)
 {
-	kvfree(res->rss_vhca_ids);
 	kvfree(res->rss_rqns);
 	kvfree(res);
 }
 
-static struct mlx5e_rx_res *mlx5e_rx_res_alloc(struct mlx5_core_dev *mdev, unsigned int max_nch,
-					       bool multi_vhca)
+static struct mlx5e_rx_res *mlx5e_rx_res_alloc(struct mlx5_core_dev *mdev, unsigned int max_nch)
 {
 	struct mlx5e_rx_res *rx_res;
 
@@ -315,15 +298,6 @@ static struct mlx5e_rx_res *mlx5e_rx_res_alloc(struct mlx5_core_dev *mdev, unsig
 		return NULL;
 	}
 
-	if (multi_vhca) {
-		rx_res->rss_vhca_ids = kvcalloc(max_nch, sizeof(*rx_res->rss_vhca_ids), GFP_KERNEL);
-		if (!rx_res->rss_vhca_ids) {
-			kvfree(rx_res->rss_rqns);
-			kvfree(rx_res);
-			return NULL;
-		}
-	}
-
 	return rx_res;
 }
 
@@ -450,11 +424,10 @@ mlx5e_rx_res_create(struct mlx5_core_dev *mdev, enum mlx5e_rx_res_features featu
 		    const struct mlx5e_packet_merge_param *init_pkt_merge_param,
 		    unsigned int init_nch)
 {
-	bool multi_vhca = features & MLX5E_RX_RES_FEATURE_MULTI_VHCA;
 	struct mlx5e_rx_res *res;
 	int err;
 
-	res = mlx5e_rx_res_alloc(mdev, max_nch, multi_vhca);
+	res = mlx5e_rx_res_alloc(mdev, max_nch);
 	if (!res)
 		return ERR_PTR(-ENOMEM);
 
@@ -531,11 +504,10 @@ static void mlx5e_rx_res_channel_activate_direct(struct mlx5e_rx_res *res,
 						 struct mlx5e_channels *chs,
 						 unsigned int ix)
 {
-	u32 *vhca_id = get_vhca_ids(res, ix);
 	u32 rqn = res->rss_rqns[ix];
 	int err;
 
-	err = mlx5e_rqt_redirect_direct(&res->channels[ix].direct_rqt, rqn, vhca_id);
+	err = mlx5e_rqt_redirect_direct(&res->channels[ix].direct_rqt, rqn);
 	if (err)
 		mlx5_core_warn(res->mdev, "Failed to redirect direct RQT %#x to RQ %#x (channel %u): err = %d\n",
 			       mlx5e_rqt_get_rqtn(&res->channels[ix].direct_rqt),
@@ -547,7 +519,7 @@ static void mlx5e_rx_res_channel_deactivate_direct(struct mlx5e_rx_res *res,
 {
 	int err;
 
-	err = mlx5e_rqt_redirect_direct(&res->channels[ix].direct_rqt, res->drop_rqn, NULL);
+	err = mlx5e_rqt_redirect_direct(&res->channels[ix].direct_rqt, res->drop_rqn);
 	if (err)
 		mlx5_core_warn(res->mdev, "Failed to redirect direct RQT %#x to drop RQ %#x (channel %u): err = %d\n",
 			       mlx5e_rqt_get_rqtn(&res->channels[ix].direct_rqt),
@@ -562,12 +534,10 @@ void mlx5e_rx_res_channels_activate(struct mlx5e_rx_res *res, struct mlx5e_chann
 	nch = mlx5e_channels_get_num(chs);
 
 	for (ix = 0; ix < chs->num; ix++) {
-		u32 *vhca_id = get_vhca_ids(res, ix);
-
 		if (mlx5e_channels_is_xsk(chs, ix))
-			mlx5e_channels_get_xsk_rqn(chs, ix, &res->rss_rqns[ix], vhca_id);
+			mlx5e_channels_get_xsk_rqn(chs, ix, &res->rss_rqns[ix]);
 		else
-			mlx5e_channels_get_regular_rqn(chs, ix, &res->rss_rqns[ix], vhca_id);
+			mlx5e_channels_get_regular_rqn(chs, ix, &res->rss_rqns[ix]);
 	}
 	res->rss_nch = chs->num;
 
@@ -584,7 +554,7 @@ void mlx5e_rx_res_channels_activate(struct mlx5e_rx_res *res, struct mlx5e_chann
 		if (!mlx5e_channels_get_ptp_rqn(chs, &rqn))
 			rqn = res->drop_rqn;
 
-		err = mlx5e_rqt_redirect_direct(&res->ptp.rqt, rqn, NULL);
+		err = mlx5e_rqt_redirect_direct(&res->ptp.rqt, rqn);
 		if (err)
 			mlx5_core_warn(res->mdev, "Failed to redirect direct RQT %#x to RQ %#x (PTP): err = %d\n",
 				       mlx5e_rqt_get_rqtn(&res->ptp.rqt),
@@ -603,7 +573,7 @@ void mlx5e_rx_res_channels_deactivate(struct mlx5e_rx_res *res)
 		mlx5e_rx_res_channel_deactivate_direct(res, ix);
 
 	if (res->features & MLX5E_RX_RES_FEATURE_PTP) {
-		err = mlx5e_rqt_redirect_direct(&res->ptp.rqt, res->drop_rqn, NULL);
+		err = mlx5e_rqt_redirect_direct(&res->ptp.rqt, res->drop_rqn);
 		if (err)
 			mlx5_core_warn(res->mdev, "Failed to redirect direct RQT %#x to drop RQ %#x (PTP): err = %d\n",
 				       mlx5e_rqt_get_rqtn(&res->ptp.rqt),
@@ -614,12 +584,10 @@ void mlx5e_rx_res_channels_deactivate(struct mlx5e_rx_res *res)
 void mlx5e_rx_res_xsk_update(struct mlx5e_rx_res *res, struct mlx5e_channels *chs,
 			     unsigned int ix, bool xsk)
 {
-	u32 *vhca_id = get_vhca_ids(res, ix);
-
 	if (xsk)
-		mlx5e_channels_get_xsk_rqn(chs, ix, &res->rss_rqns[ix], vhca_id);
+		mlx5e_channels_get_xsk_rqn(chs, ix, &res->rss_rqns[ix]);
 	else
-		mlx5e_channels_get_regular_rqn(chs, ix, &res->rss_rqns[ix], vhca_id);
+		mlx5e_channels_get_regular_rqn(chs, ix, &res->rss_rqns[ix]);
 
 	mlx5e_rx_res_rss_enable(res);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h
index 7b1a9f0f1874..82aaba8a82b3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h
@@ -18,7 +18,6 @@ struct mlx5e_rss_params_hash;
 enum mlx5e_rx_res_features {
 	MLX5E_RX_RES_FEATURE_INNER_FT = BIT(0),
 	MLX5E_RX_RES_FEATURE_PTP = BIT(1),
-	MLX5E_RX_RES_FEATURE_MULTI_VHCA = BIT(2),
 };
 
 /* Setup */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
index 53ca16cb9c41..ac458a8d10e0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
@@ -63,12 +63,10 @@ static int mlx5e_open_trap_rq(struct mlx5e_priv *priv, struct mlx5e_trap *t)
 	struct mlx5e_create_cq_param ccp = {};
 	struct dim_cq_moder trap_moder = {};
 	struct mlx5e_rq *rq = &t->rq;
-	u16 q_counter;
 	int node;
 	int err;
 
 	node = dev_to_node(mdev->device);
-	q_counter = priv->q_counter[0];
 
 	ccp.netdev   = priv->netdev;
 	ccp.wq       = priv->wq;
@@ -81,7 +79,7 @@ static int mlx5e_open_trap_rq(struct mlx5e_priv *priv, struct mlx5e_trap *t)
 		return err;
 
 	mlx5e_init_trap_rq(t, &t->params, rq);
-	err = mlx5e_open_rq(&t->params, rq_param, NULL, node, q_counter, rq);
+	err = mlx5e_open_rq(&t->params, rq_param, NULL, node, rq);
 	if (err)
 		goto err_destroy_cq;
 
@@ -118,14 +116,15 @@ static int mlx5e_create_trap_direct_rq_tir(struct mlx5_core_dev *mdev, struct ml
 }
 
 static void mlx5e_build_trap_params(struct mlx5_core_dev *mdev,
-				    int max_mtu, struct mlx5e_trap *t)
+				    int max_mtu, u16 q_counter,
+				    struct mlx5e_trap *t)
 {
 	struct mlx5e_params *params = &t->params;
 
 	params->rq_wq_type = MLX5_WQ_TYPE_CYCLIC;
 	mlx5e_init_rq_type_params(mdev, params);
 	params->sw_mtu = max_mtu;
-	mlx5e_build_rq_param(mdev, params, NULL, &t->rq_param);
+	mlx5e_build_rq_param(mdev, params, NULL, q_counter, &t->rq_param);
 }
 
 static struct mlx5e_trap *mlx5e_open_trap(struct mlx5e_priv *priv)
@@ -139,7 +138,7 @@ static struct mlx5e_trap *mlx5e_open_trap(struct mlx5e_priv *priv)
 	if (!t)
 		return ERR_PTR(-ENOMEM);
 
-	mlx5e_build_trap_params(priv->mdev, netdev->max_mtu, t);
+	mlx5e_build_trap_params(priv->mdev, netdev->max_mtu, priv->q_counter, t);
 
 	t->priv     = priv;
 	t->mdev     = priv->mdev;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c
index db776e515b6a..ebada0c5af3c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c
@@ -6,10 +6,10 @@
 #include "setup.h"
 #include "en/params.h"
 
-static int mlx5e_xsk_map_pool(struct mlx5_core_dev *mdev,
+static int mlx5e_xsk_map_pool(struct mlx5e_priv *priv,
 			      struct xsk_buff_pool *pool)
 {
-	struct device *dev = mlx5_core_dma_dev(mdev);
+	struct device *dev = mlx5_core_dma_dev(priv->mdev);
 
 	return xsk_pool_dma_map(pool, dev, DMA_ATTR_SKIP_CPU_SYNC);
 }
@@ -89,7 +89,7 @@ static int mlx5e_xsk_enable_locked(struct mlx5e_priv *priv,
 	if (unlikely(!mlx5e_xsk_is_pool_sane(pool)))
 		return -EINVAL;
 
-	err = mlx5e_xsk_map_pool(mlx5_sd_ch_ix_get_dev(priv->mdev, ix), pool);
+	err = mlx5e_xsk_map_pool(priv, pool);
 	if (unlikely(err))
 		return err;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
index 06592b9f0424..82e6abbc1734 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
@@ -49,9 +49,10 @@ bool mlx5e_validate_xsk_param(struct mlx5e_params *params,
 static void mlx5e_build_xsk_cparam(struct mlx5_core_dev *mdev,
 				   struct mlx5e_params *params,
 				   struct mlx5e_xsk_param *xsk,
+				   u16 q_counter,
 				   struct mlx5e_channel_param *cparam)
 {
-	mlx5e_build_rq_param(mdev, params, xsk, &cparam->rq);
+	mlx5e_build_rq_param(mdev, params, xsk, q_counter, &cparam->rq);
 	mlx5e_build_xdpsq_param(mdev, params, xsk, &cparam->xdp_sq);
 }
 
@@ -92,7 +93,6 @@ static int mlx5e_open_xsk_rq(struct mlx5e_channel *c, struct mlx5e_params *param
 			     struct mlx5e_rq_param *rq_params, struct xsk_buff_pool *pool,
 			     struct mlx5e_xsk_param *xsk)
 {
-	u16 q_counter = c->priv->q_counter[c->sd_ix];
 	struct mlx5e_rq *xskrq = &c->xskrq;
 	int err;
 
@@ -100,7 +100,7 @@ static int mlx5e_open_xsk_rq(struct mlx5e_channel *c, struct mlx5e_params *param
 	if (err)
 		return err;
 
-	err = mlx5e_open_rq(params, rq_params, xsk, cpu_to_node(c->cpu), q_counter, xskrq);
+	err = mlx5e_open_rq(params, rq_params, xsk, cpu_to_node(c->cpu), xskrq);
 	if (err)
 		return err;
 
@@ -125,7 +125,7 @@ int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params,
 	if (!cparam)
 		return -ENOMEM;
 
-	mlx5e_build_xsk_cparam(priv->mdev, params, xsk, cparam);
+	mlx5e_build_xsk_cparam(priv->mdev, params, xsk, priv->q_counter, cparam);
 
 	err = mlx5e_open_cq(c->mdev, params->rx_cq_moderation, &cparam->rq.cqp, &ccp,
 			    &c->xskrq.cq);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c
index e3e57c849436..984fa04bd331 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c
@@ -96,7 +96,7 @@ bool mlx5e_is_ktls_rx(struct mlx5_core_dev *mdev)
 {
 	u8 max_sq_wqebbs = mlx5e_get_max_sq_wqebbs(mdev);
 
-	if (is_kdump_kernel() || !MLX5_CAP_GEN(mdev, tls_rx) || mlx5_get_sd(mdev))
+	if (is_kdump_kernel() || !MLX5_CAP_GEN(mdev, tls_rx))
 		return false;
 
 	/* Check the possibility to post the required ICOSQ WQEs. */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
index adc6d8ea0960..f11075e67658 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
@@ -11,7 +11,6 @@
 
 #ifdef CONFIG_MLX5_EN_TLS
 #include "lib/crypto.h"
-#include "lib/mlx5.h"
 
 struct mlx5_crypto_dek *mlx5_ktls_create_key(struct mlx5_crypto_dek_pool *dek_pool,
 					     struct tls_crypto_info *crypto_info);
@@ -62,8 +61,7 @@ void mlx5e_ktls_rx_resync_destroy_resp_list(struct mlx5e_ktls_resync_resp *resp_
 
 static inline bool mlx5e_is_ktls_tx(struct mlx5_core_dev *mdev)
 {
-	return !is_kdump_kernel() && MLX5_CAP_GEN(mdev, tls_tx) &&
-		!mlx5_get_sd(mdev);
+	return !is_kdump_kernel() && MLX5_CAP_GEN(mdev, tls_tx);
 }
 
 bool mlx5e_is_ktls_rx(struct mlx5_core_dev *mdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
index 65ccb33edafb..9b597cb24598 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
@@ -267,7 +267,7 @@ resync_post_get_progress_params(struct mlx5e_icosq *sq,
 		goto err_out;
 	}
 
-	pdev = mlx5_core_dma_dev(sq->channel->mdev);
+	pdev = mlx5_core_dma_dev(sq->channel->priv->mdev);
 	buf->dma_addr = dma_map_single(pdev, &buf->progress,
 				       PROGRESS_PARAMS_PADDED_SIZE, DMA_FROM_DEVICE);
 	if (unlikely(dma_mapping_error(pdev, buf->dma_addr))) {
@@ -425,12 +425,14 @@ void mlx5e_ktls_handle_get_psv_completion(struct mlx5e_icosq_wqe_info *wi,
 {
 	struct mlx5e_ktls_rx_resync_buf *buf = wi->tls_get_params.buf;
 	struct mlx5e_ktls_offload_context_rx *priv_rx;
+	struct mlx5e_ktls_rx_resync_ctx *resync;
 	u8 tracker_state, auth_state, *ctx;
 	struct device *dev;
 	u32 hw_seq;
 
 	priv_rx = buf->priv_rx;
-	dev = mlx5_core_dma_dev(sq->channel->mdev);
+	resync = &priv_rx->resync;
+	dev = mlx5_core_dma_dev(resync->priv->mdev);
 	if (unlikely(test_bit(MLX5E_PRIV_RX_FLAG_DELETING, priv_rx->flags)))
 		goto out;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
index 6ed3a32b7e22..67f546683e85 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
@@ -95,7 +95,7 @@ static void mlx5e_destroy_tises(struct mlx5_core_dev *mdev, u32 tisn[MLX5_MAX_PO
 {
 	int tc, i;
 
-	for (i = 0; i < mlx5e_get_num_lag_ports(mdev); i++)
+	for (i = 0; i < MLX5_MAX_PORTS; i++)
 		for (tc = 0; tc < MLX5_MAX_NUM_TC; tc++)
 			mlx5e_destroy_tis(mdev, tisn[i][tc]);
 }
@@ -110,7 +110,7 @@ static int mlx5e_create_tises(struct mlx5_core_dev *mdev, u32 tisn[MLX5_MAX_PORT
 	int tc, i;
 	int err;
 
-	for (i = 0; i < mlx5e_get_num_lag_ports(mdev); i++) {
+	for (i = 0; i < MLX5_MAX_PORTS; i++) {
 		for (tc = 0; tc < MLX5_MAX_NUM_TC; tc++) {
 			u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {};
 			void *tisc;
@@ -140,7 +140,7 @@ err_close_tises:
 	return err;
 }
 
-int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev, bool create_tises)
+int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev)
 {
 	struct mlx5e_hw_objs *res = &mdev->mlx5e_res.hw_objs;
 	int err;
@@ -169,15 +169,11 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev, bool create_tises)
 		goto err_destroy_mkey;
 	}
 
-	if (create_tises) {
-		err = mlx5e_create_tises(mdev, res->tisn);
-		if (err) {
-			mlx5_core_err(mdev, "alloc tises failed, %d\n", err);
-			goto err_destroy_bfreg;
-		}
-		res->tisn_valid = true;
+	err = mlx5e_create_tises(mdev, res->tisn);
+	if (err) {
+		mlx5_core_err(mdev, "alloc tises failed, %d\n", err);
+		goto err_destroy_bfreg;
 	}
-
 	INIT_LIST_HEAD(&res->td.tirs_list);
 	mutex_init(&res->td.list_lock);
 
@@ -207,8 +203,7 @@ void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev)
 
 	mlx5_crypto_dek_cleanup(mdev->mlx5e_res.dek_priv);
 	mdev->mlx5e_res.dek_priv = NULL;
-	if (res->tisn_valid)
-		mlx5e_destroy_tises(mdev, res->tisn);
+	mlx5e_destroy_tises(mdev, res->tisn);
 	mlx5_free_bfreg(mdev, &res->bfreg);
 	mlx5_core_destroy_mkey(mdev, res->mkey);
 	mlx5_core_dealloc_transport_domain(mdev, res->td.tdn);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 40626b6108fb..b5f1c4ca38ba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -70,7 +70,6 @@
 #include "qos.h"
 #include "en/trap.h"
 #include "lib/devcom.h"
-#include "lib/sd.h"
 
 bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev, u8 page_shift,
 					    enum mlx5e_mpwrq_umr_mode umr_mode)
@@ -1025,7 +1024,7 @@ static void mlx5e_free_rq(struct mlx5e_rq *rq)
 	mlx5_wq_destroy(&rq->wq_ctrl);
 }
 
-int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param, u16 q_counter)
+int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param)
 {
 	struct mlx5_core_dev *mdev = rq->mdev;
 	u8 ts_format;
@@ -1052,7 +1051,6 @@ int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param, u16 q_cou
 	MLX5_SET(rqc,  rqc, cqn,		rq->cq.mcq.cqn);
 	MLX5_SET(rqc,  rqc, state,		MLX5_RQC_STATE_RST);
 	MLX5_SET(rqc,  rqc, ts_format,		ts_format);
-	MLX5_SET(rqc,  rqc, counter_set_id,     q_counter);
 	MLX5_SET(wq,   wq,  log_wq_pg_sz,	rq->wq_ctrl.buf.page_shift -
 						MLX5_ADAPTER_PAGE_SHIFT);
 	MLX5_SET64(wq, wq,  dbr_addr,		rq->wq_ctrl.db.dma);
@@ -1276,7 +1274,7 @@ void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
 }
 
 int mlx5e_open_rq(struct mlx5e_params *params, struct mlx5e_rq_param *param,
-		  struct mlx5e_xsk_param *xsk, int node, u16 q_counter,
+		  struct mlx5e_xsk_param *xsk, int node,
 		  struct mlx5e_rq *rq)
 {
 	struct mlx5_core_dev *mdev = rq->mdev;
@@ -1289,7 +1287,7 @@ int mlx5e_open_rq(struct mlx5e_params *params, struct mlx5e_rq_param *param,
 	if (err)
 		return err;
 
-	err = mlx5e_create_rq(rq, param, q_counter);
+	err = mlx5e_create_rq(rq, param);
 	if (err)
 		goto err_free_rq;
 
@@ -2335,14 +2333,13 @@ static int mlx5e_set_tx_maxrate(struct net_device *dev, int index, u32 rate)
 static int mlx5e_open_rxq_rq(struct mlx5e_channel *c, struct mlx5e_params *params,
 			     struct mlx5e_rq_param *rq_params)
 {
-	u16 q_counter = c->priv->q_counter[c->sd_ix];
 	int err;
 
 	err = mlx5e_init_rxq_rq(c, params, rq_params->xdp_frag_size, &c->rq);
 	if (err)
 		return err;
 
-	return mlx5e_open_rq(params, rq_params, NULL, cpu_to_node(c->cpu), q_counter, &c->rq);
+	return mlx5e_open_rq(params, rq_params, NULL, cpu_to_node(c->cpu), &c->rq);
 }
 
 static int mlx5e_open_queues(struct mlx5e_channel *c,
@@ -2529,20 +2526,14 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 			      struct xsk_buff_pool *xsk_pool,
 			      struct mlx5e_channel **cp)
 {
+	int cpu = mlx5_comp_vector_get_cpu(priv->mdev, ix);
 	struct net_device *netdev = priv->netdev;
-	struct mlx5_core_dev *mdev;
 	struct mlx5e_xsk_param xsk;
 	struct mlx5e_channel *c;
 	unsigned int irq;
-	int vec_ix;
-	int cpu;
 	int err;
 
-	mdev = mlx5_sd_ch_ix_get_dev(priv->mdev, ix);
-	vec_ix = mlx5_sd_ch_ix_get_vec_ix(mdev, ix);
-	cpu = mlx5_comp_vector_get_cpu(mdev, vec_ix);
-
-	err = mlx5_comp_irqn_get(mdev, vec_ix, &irq);
+	err = mlx5_comp_irqn_get(priv->mdev, ix, &irq);
 	if (err)
 		return err;
 
@@ -2555,20 +2546,18 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 		return -ENOMEM;
 
 	c->priv     = priv;
-	c->mdev     = mdev;
+	c->mdev     = priv->mdev;
 	c->tstamp   = &priv->tstamp;
 	c->ix       = ix;
-	c->vec_ix   = vec_ix;
-	c->sd_ix    = mlx5_sd_ch_ix_get_dev_ix(mdev, ix);
 	c->cpu      = cpu;
-	c->pdev     = mlx5_core_dma_dev(mdev);
+	c->pdev     = mlx5_core_dma_dev(priv->mdev);
 	c->netdev   = priv->netdev;
-	c->mkey_be  = cpu_to_be32(mdev->mlx5e_res.hw_objs.mkey);
+	c->mkey_be  = cpu_to_be32(priv->mdev->mlx5e_res.hw_objs.mkey);
 	c->num_tc   = mlx5e_get_dcb_num_tc(params);
 	c->xdp      = !!params->xdp_prog;
 	c->stats    = &priv->channel_stats[ix]->ch;
 	c->aff_mask = irq_get_effective_affinity_mask(irq);
-	c->lag_port = mlx5e_enumerate_lag_port(mdev, ix);
+	c->lag_port = mlx5e_enumerate_lag_port(priv->mdev, ix);
 
 	netif_napi_add(netdev, &c->napi, mlx5e_napi_poll);
 
@@ -2658,7 +2647,7 @@ int mlx5e_open_channels(struct mlx5e_priv *priv,
 	if (!chs->c || !cparam)
 		goto err_free;
 
-	err = mlx5e_build_channel_param(priv->mdev, &chs->params, cparam);
+	err = mlx5e_build_channel_param(priv->mdev, &chs->params, priv->q_counter, cparam);
 	if (err)
 		goto err_free;
 
@@ -2946,18 +2935,15 @@ static MLX5E_DEFINE_PREACTIVATE_WRAPPER_CTX(mlx5e_update_netdev_queues);
 static void mlx5e_set_default_xps_cpumasks(struct mlx5e_priv *priv,
 					   struct mlx5e_params *params)
 {
-	int ix;
+	struct mlx5_core_dev *mdev = priv->mdev;
+	int num_comp_vectors, ix, irq;
 
-	for (ix = 0; ix < params->num_channels; ix++) {
-		int num_comp_vectors, irq, vec_ix;
-		struct mlx5_core_dev *mdev;
+	num_comp_vectors = mlx5_comp_vectors_max(mdev);
 
-		mdev = mlx5_sd_ch_ix_get_dev(priv->mdev, ix);
-		num_comp_vectors = mlx5_comp_vectors_max(mdev);
+	for (ix = 0; ix < params->num_channels; ix++) {
 		cpumask_clear(priv->scratchpad.cpumask);
-		vec_ix = mlx5_sd_ch_ix_get_vec_ix(mdev, ix);
 
-		for (irq = vec_ix; irq < num_comp_vectors; irq += params->num_channels) {
+		for (irq = ix; irq < num_comp_vectors; irq += params->num_channels) {
 			int cpu = mlx5_comp_vector_get_cpu(mdev, irq);
 
 			cpumask_set_cpu(cpu, priv->scratchpad.cpumask);
@@ -3349,7 +3335,7 @@ int mlx5e_open_drop_rq(struct mlx5e_priv *priv,
 	struct mlx5e_cq *cq = &drop_rq->cq;
 	int err;
 
-	mlx5e_build_drop_rq_param(mdev, &rq_param);
+	mlx5e_build_drop_rq_param(mdev, priv->drop_rq_q_counter, &rq_param);
 
 	err = mlx5e_alloc_drop_cq(priv, cq, &cq_param);
 	if (err)
@@ -3363,7 +3349,7 @@ int mlx5e_open_drop_rq(struct mlx5e_priv *priv,
 	if (err)
 		goto err_destroy_cq;
 
-	err = mlx5e_create_rq(drop_rq, &rq_param, priv->drop_rq_q_counter);
+	err = mlx5e_create_rq(drop_rq, &rq_param);
 	if (err)
 		goto err_free_rq;
 
@@ -3799,7 +3785,7 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	stats->tx_errors = stats->tx_aborted_errors + stats->tx_carrier_errors;
 }
 
-void mlx5e_nic_set_rx_mode(struct mlx5e_priv *priv)
+static void mlx5e_nic_set_rx_mode(struct mlx5e_priv *priv)
 {
 	if (mlx5e_is_uplink_rep(priv))
 		return; /* no rx mode for uplink rep */
@@ -5004,15 +4990,6 @@ const struct net_device_ops mlx5e_netdev_ops = {
 #endif
 };
 
-const struct net_device_ops mlx5e_mgmt_netdev_ops = {
-	.ndo_open		= mlx5e_open,
-	.ndo_stop		= mlx5e_close,
-	.ndo_start_xmit		= mlx5e_xmit,
-	.ndo_get_stats64	= mlx5e_get_stats,
-	.ndo_change_mtu		= mlx5e_change_nic_mtu,
-	.ndo_set_rx_mode	= mlx5e_set_rx_mode,
-};
-
 static u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout)
 {
 	int i;
@@ -5152,11 +5129,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 
 	SET_NETDEV_DEV(netdev, mdev->device);
 
-	if (mlx5_core_is_mgmt_pf(mdev))
-		netdev->netdev_ops = &mlx5e_mgmt_netdev_ops;
-	else
-		netdev->netdev_ops = &mlx5e_netdev_ops;
-
+	netdev->netdev_ops = &mlx5e_netdev_ops;
 	netdev->xdp_metadata_ops = &mlx5e_xdp_metadata_ops;
 	netdev->xsk_tx_metadata_ops = &mlx5e_xsk_tx_metadata_ops;
 
@@ -5291,17 +5264,13 @@ void mlx5e_create_q_counters(struct mlx5e_priv *priv)
 	u32 out[MLX5_ST_SZ_DW(alloc_q_counter_out)] = {};
 	u32 in[MLX5_ST_SZ_DW(alloc_q_counter_in)] = {};
 	struct mlx5_core_dev *mdev = priv->mdev;
-	struct mlx5_core_dev *pos;
-	int err, i;
+	int err;
 
 	MLX5_SET(alloc_q_counter_in, in, opcode, MLX5_CMD_OP_ALLOC_Q_COUNTER);
-
-	mlx5_sd_for_each_dev(i, mdev, pos) {
-		err = mlx5_cmd_exec_inout(pos, alloc_q_counter, in, out);
-		if (!err)
-			priv->q_counter[i] =
-				MLX5_GET(alloc_q_counter_out, out, counter_set_id);
-	}
+	err = mlx5_cmd_exec_inout(mdev, alloc_q_counter, in, out);
+	if (!err)
+		priv->q_counter =
+			MLX5_GET(alloc_q_counter_out, out, counter_set_id);
 
 	err = mlx5_cmd_exec_inout(mdev, alloc_q_counter, in, out);
 	if (!err)
@@ -5312,17 +5281,13 @@ void mlx5e_create_q_counters(struct mlx5e_priv *priv)
 void mlx5e_destroy_q_counters(struct mlx5e_priv *priv)
 {
 	u32 in[MLX5_ST_SZ_DW(dealloc_q_counter_in)] = {};
-	struct mlx5_core_dev *pos;
-	int i;
 
 	MLX5_SET(dealloc_q_counter_in, in, opcode,
 		 MLX5_CMD_OP_DEALLOC_Q_COUNTER);
-	mlx5_sd_for_each_dev(i, priv->mdev, pos) {
-		if (priv->q_counter[i]) {
-			MLX5_SET(dealloc_q_counter_in, in, counter_set_id,
-				 priv->q_counter[i]);
-			mlx5_cmd_exec_in(pos, dealloc_q_counter, in);
-		}
+	if (priv->q_counter) {
+		MLX5_SET(dealloc_q_counter_in, in, counter_set_id,
+			 priv->q_counter);
+		mlx5_cmd_exec_in(priv->mdev, dealloc_q_counter, in);
 	}
 
 	if (priv->drop_rq_q_counter) {
@@ -5406,8 +5371,6 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv)
 	features = MLX5E_RX_RES_FEATURE_PTP;
 	if (mlx5_tunnel_inner_ft_supported(mdev))
 		features |= MLX5E_RX_RES_FEATURE_INNER_FT;
-	if (mlx5_get_sd(priv->mdev))
-		features |= MLX5E_RX_RES_FEATURE_MULTI_VHCA;
 
 	priv->rx_res = mlx5e_rx_res_create(priv->mdev, features, priv->max_nch, priv->drop_rq.rqn,
 					   &priv->channels.params.packet_merge,
@@ -6017,52 +5980,28 @@ void mlx5e_destroy_netdev(struct mlx5e_priv *priv)
 	free_netdev(netdev);
 }
 
-static int _mlx5e_resume(struct auxiliary_device *adev)
+static int mlx5e_resume(struct auxiliary_device *adev)
 {
 	struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev);
 	struct mlx5e_dev *mlx5e_dev = auxiliary_get_drvdata(adev);
 	struct mlx5e_priv *priv = mlx5e_dev->priv;
 	struct net_device *netdev = priv->netdev;
 	struct mlx5_core_dev *mdev = edev->mdev;
-	struct mlx5_core_dev *pos, *to;
-	int err, i;
+	int err;
 
 	if (netif_device_present(netdev))
 		return 0;
 
-	mlx5_sd_for_each_dev(i, mdev, pos) {
-		err = mlx5e_create_mdev_resources(pos, true);
-		if (err)
-			goto err_destroy_mdev_res;
-	}
-
-	err = mlx5e_attach_netdev(priv);
+	err = mlx5e_create_mdev_resources(mdev);
 	if (err)
-		goto err_destroy_mdev_res;
-
-	return 0;
-
-err_destroy_mdev_res:
-	to = pos;
-	mlx5_sd_for_each_dev_to(i, mdev, to, pos)
-		mlx5e_destroy_mdev_resources(pos);
-	return err;
-}
-
-static int mlx5e_resume(struct auxiliary_device *adev)
-{
-	struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev);
-	struct mlx5_core_dev *mdev = edev->mdev;
-	struct auxiliary_device *actual_adev;
-	int err;
+		return err;
 
-	err = mlx5_sd_init(mdev);
-	if (err)
+	err = mlx5e_attach_netdev(priv);
+	if (err) {
+		mlx5e_destroy_mdev_resources(mdev);
 		return err;
+	}
 
-	actual_adev = mlx5_sd_get_adev(mdev, adev, edev->idx);
-	if (actual_adev)
-		return _mlx5e_resume(actual_adev);
 	return 0;
 }
 
@@ -6072,53 +6011,33 @@ static int _mlx5e_suspend(struct auxiliary_device *adev)
 	struct mlx5e_priv *priv = mlx5e_dev->priv;
 	struct net_device *netdev = priv->netdev;
 	struct mlx5_core_dev *mdev = priv->mdev;
-	struct mlx5_core_dev *pos;
-	int i;
 
 	if (!netif_device_present(netdev)) {
 		if (test_bit(MLX5E_STATE_DESTROYING, &priv->state))
-			mlx5_sd_for_each_dev(i, mdev, pos)
-				mlx5e_destroy_mdev_resources(pos);
+			mlx5e_destroy_mdev_resources(mdev);
 		return -ENODEV;
 	}
 
 	mlx5e_detach_netdev(priv);
-	mlx5_sd_for_each_dev(i, mdev, pos)
-		mlx5e_destroy_mdev_resources(pos);
-
+	mlx5e_destroy_mdev_resources(mdev);
 	return 0;
 }
 
 static int mlx5e_suspend(struct auxiliary_device *adev, pm_message_t state)
 {
-	struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev);
-	struct mlx5_core_dev *mdev = edev->mdev;
-	struct auxiliary_device *actual_adev;
-	int err = 0;
-
-	actual_adev = mlx5_sd_get_adev(mdev, adev, edev->idx);
-	if (actual_adev)
-		err = _mlx5e_suspend(actual_adev);
-
-	mlx5_sd_cleanup(mdev);
-	return err;
+	return _mlx5e_suspend(adev);
 }
 
 static int _mlx5e_probe(struct auxiliary_device *adev)
 {
 	struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev);
+	const struct mlx5e_profile *profile = &mlx5e_nic_profile;
 	struct mlx5_core_dev *mdev = edev->mdev;
-	const struct mlx5e_profile *profile;
 	struct mlx5e_dev *mlx5e_dev;
 	struct net_device *netdev;
 	struct mlx5e_priv *priv;
 	int err;
 
-	if (mlx5_core_is_mgmt_pf(mdev))
-		profile = &mlx5e_mgmt_pf_nic_profile;
-	else
-		profile = &mlx5e_nic_profile;
-
 	mlx5e_dev = mlx5e_create_devlink(&adev->dev, mdev);
 	if (IS_ERR(mlx5e_dev))
 		return PTR_ERR(mlx5e_dev);
@@ -6152,9 +6071,9 @@ static int _mlx5e_probe(struct auxiliary_device *adev)
 		goto err_destroy_netdev;
 	}
 
-	err = _mlx5e_resume(adev);
+	err = mlx5e_resume(adev);
 	if (err) {
-		mlx5_core_err(mdev, "_mlx5e_resume failed, %d\n", err);
+		mlx5_core_err(mdev, "mlx5e_resume failed, %d\n", err);
 		goto err_profile_cleanup;
 	}
 
@@ -6185,29 +6104,15 @@ err_devlink_unregister:
 static int mlx5e_probe(struct auxiliary_device *adev,
 		       const struct auxiliary_device_id *id)
 {
-	struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev);
-	struct mlx5_core_dev *mdev = edev->mdev;
-	struct auxiliary_device *actual_adev;
-	int err;
-
-	err = mlx5_sd_init(mdev);
-	if (err)
-		return err;
-
-	actual_adev = mlx5_sd_get_adev(mdev, adev, edev->idx);
-	if (actual_adev)
-		return _mlx5e_probe(actual_adev);
-	return 0;
+	return _mlx5e_probe(adev);
 }
 
-static void _mlx5e_remove(struct auxiliary_device *adev)
+static void mlx5e_remove(struct auxiliary_device *adev)
 {
-	struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev);
 	struct mlx5e_dev *mlx5e_dev = auxiliary_get_drvdata(adev);
 	struct mlx5e_priv *priv = mlx5e_dev->priv;
-	struct mlx5_core_dev *mdev = edev->mdev;
 
-	mlx5_core_uplink_netdev_set(mdev, NULL);
+	mlx5_core_uplink_netdev_set(priv->mdev, NULL);
 	mlx5e_dcbnl_delete_app(priv);
 	unregister_netdev(priv->netdev);
 	_mlx5e_suspend(adev);
@@ -6217,19 +6122,6 @@ static void _mlx5e_remove(struct auxiliary_device *adev)
 	mlx5e_destroy_devlink(mlx5e_dev);
 }
 
-static void mlx5e_remove(struct auxiliary_device *adev)
-{
-	struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev);
-	struct mlx5_core_dev *mdev = edev->mdev;
-	struct auxiliary_device *actual_adev;
-
-	actual_adev = mlx5_sd_get_adev(mdev, adev, edev->idx);
-	if (actual_adev)
-		_mlx5e_remove(actual_adev);
-
-	mlx5_sd_cleanup(mdev);
-}
-
 static const struct auxiliary_device_id mlx5e_id_table[] = {
 	{ .name = MLX5_ADEV_NAME ".eth", },
 	{},
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index f3d0898bdbc6..4b96ad657145 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -561,23 +561,11 @@ static const struct counter_desc drop_rq_stats_desc[] = {
 #define NUM_Q_COUNTERS			ARRAY_SIZE(q_stats_desc)
 #define NUM_DROP_RQ_COUNTERS		ARRAY_SIZE(drop_rq_stats_desc)
 
-static bool q_counter_any(struct mlx5e_priv *priv)
-{
-	struct mlx5_core_dev *pos;
-	int i;
-
-	mlx5_sd_for_each_dev(i, priv->mdev, pos)
-		if (priv->q_counter[i++])
-			return true;
-
-	return false;
-}
-
 static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(qcnt)
 {
 	int num_stats = 0;
 
-	if (q_counter_any(priv))
+	if (priv->q_counter)
 		num_stats += NUM_Q_COUNTERS;
 
 	if (priv->drop_rq_q_counter)
@@ -590,7 +578,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(qcnt)
 {
 	int i;
 
-	for (i = 0; i < NUM_Q_COUNTERS && q_counter_any(priv); i++)
+	for (i = 0; i < NUM_Q_COUNTERS && priv->q_counter; i++)
 		strcpy(data + (idx++) * ETH_GSTRING_LEN,
 		       q_stats_desc[i].format);
 
@@ -605,7 +593,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(qcnt)
 {
 	int i;
 
-	for (i = 0; i < NUM_Q_COUNTERS && q_counter_any(priv); i++)
+	for (i = 0; i < NUM_Q_COUNTERS && priv->q_counter; i++)
 		data[idx++] = MLX5E_READ_CTR32_CPU(&priv->stats.qcnt,
 						   q_stats_desc, i);
 	for (i = 0; i < NUM_DROP_RQ_COUNTERS && priv->drop_rq_q_counter; i++)
@@ -619,23 +607,18 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(qcnt)
 	struct mlx5e_qcounter_stats *qcnt = &priv->stats.qcnt;
 	u32 out[MLX5_ST_SZ_DW(query_q_counter_out)] = {};
 	u32 in[MLX5_ST_SZ_DW(query_q_counter_in)] = {};
-	struct mlx5_core_dev *pos;
-	u32 rx_out_of_buffer = 0;
-	int ret, i;
+	int ret;
 
 	MLX5_SET(query_q_counter_in, in, opcode, MLX5_CMD_OP_QUERY_Q_COUNTER);
 
-	mlx5_sd_for_each_dev(i, priv->mdev, pos) {
-		if (priv->q_counter[i]) {
-			MLX5_SET(query_q_counter_in, in, counter_set_id,
-				 priv->q_counter[i]);
-			ret = mlx5_cmd_exec_inout(pos, query_q_counter, in, out);
-			if (!ret)
-				rx_out_of_buffer += MLX5_GET(query_q_counter_out,
-							     out, out_of_buffer);
-		}
+	if (priv->q_counter) {
+		MLX5_SET(query_q_counter_in, in, counter_set_id,
+			 priv->q_counter);
+		ret = mlx5_cmd_exec_inout(priv->mdev, query_q_counter, in, out);
+		if (!ret)
+			qcnt->rx_out_of_buffer = MLX5_GET(query_q_counter_out,
+							  out, out_of_buffer);
 	}
-	qcnt->rx_out_of_buffer = rx_out_of_buffer;
 
 	if (priv->drop_rq_q_counter) {
 		MLX5_SET(query_q_counter_in, in, counter_set_id,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index b8ceb972df9e..30932c9c9a8f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -766,7 +766,7 @@ static int mlx5e_hairpin_create_indirect_rqt(struct mlx5e_hairpin *hp)
 		return err;
 
 	mlx5e_rss_params_indir_init_uniform(&indir, hp->num_channels);
-	err = mlx5e_rqt_init_indir(&hp->indir_rqt, mdev, hp->pair->rqn, NULL, hp->num_channels,
+	err = mlx5e_rqt_init_indir(&hp->indir_rqt, mdev, hp->pair->rqn, hp->num_channels,
 				   mlx5e_rx_res_get_current_hash(priv->rx_res).hfunc,
 				   &indir);
 
@@ -1169,7 +1169,7 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv,
 			MLX5_CAP_GEN(priv->mdev, log_min_hairpin_wq_data_sz),
 			MLX5_CAP_GEN(priv->mdev, log_max_hairpin_wq_data_sz));
 
-	params.q_counter = priv->q_counter[0];
+	params.q_counter = priv->q_counter;
 	err = devl_param_driverinit_value_get(
 		devlink, MLX5_DEVLINK_PARAM_ID_HAIRPIN_NUM_QUEUES, &val);
 	if (err) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 3bf419d06d53..3047d7015c52 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1665,7 +1665,7 @@ int mlx5_esw_sf_max_hpf_functions(struct mlx5_core_dev *dev, u16 *max_sfs, u16 *
 	void *hca_caps;
 	int err;
 
-	if (!mlx5_core_is_ecpf(dev) || mlx5_core_is_mgmt_pf(dev)) {
+	if (!mlx5_core_is_ecpf(dev)) {
 		*max_sfs = 0;
 		return 0;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index d77be1b4dd9c..58845121954c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -783,7 +783,7 @@ static int mlx5_rdma_setup_rn(struct ib_device *ibdev, u32 port_num,
 		}
 
 		/* This should only be called once per mdev */
-		err = mlx5e_create_mdev_resources(mdev, false);
+		err = mlx5e_create_mdev_resources(mdev);
 		if (err)
 			goto destroy_ht;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h
index d58032dd0df7..ec32b686f586 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h
@@ -10,7 +10,6 @@ enum mlx5_devcom_component {
 	MLX5_DEVCOM_ESW_OFFLOADS,
 	MLX5_DEVCOM_MPV,
 	MLX5_DEVCOM_HCA_PORTS,
-	MLX5_DEVCOM_SD_GROUP,
 	MLX5_DEVCOM_NUM_COMPONENTS,
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
index 37d5f445598c..2b5826a785c4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
@@ -54,16 +54,4 @@ static inline struct net_device *mlx5_uplink_netdev_get(struct mlx5_core_dev *md
 {
 	return mdev->mlx5e_res.uplink_netdev;
 }
-
-struct mlx5_sd;
-
-static inline struct mlx5_sd *mlx5_get_sd(struct mlx5_core_dev *dev)
-{
-	return dev->sd;
-}
-
-static inline void mlx5_set_sd(struct mlx5_core_dev *dev, struct mlx5_sd *sd)
-{
-	dev->sd = sd;
-}
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c
deleted file mode 100644
index f68942277c62..000000000000
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c
+++ /dev/null
@@ -1,487 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
-/* Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
-
-#include "lib/sd.h"
-#include "mlx5_core.h"
-#include "lib/mlx5.h"
-#include "fs_cmd.h"
-#include <linux/mlx5/vport.h>
-
-#define sd_info(__dev, format, ...) \
-	dev_info((__dev)->device, "Socket-Direct: " format, ##__VA_ARGS__)
-#define sd_warn(__dev, format, ...) \
-	dev_warn((__dev)->device, "Socket-Direct: " format, ##__VA_ARGS__)
-
-struct mlx5_sd {
-	u32 group_id;
-	u8 host_buses;
-	struct mlx5_devcom_comp_dev *devcom;
-	bool primary;
-	union {
-		struct { /* primary */
-			struct mlx5_core_dev *secondaries[MLX5_SD_MAX_GROUP_SZ - 1];
-			struct mlx5_flow_table *tx_ft;
-		};
-		struct { /* secondary */
-			struct mlx5_core_dev *primary_dev;
-			u32 alias_obj_id;
-		};
-	};
-};
-
-static int mlx5_sd_get_host_buses(struct mlx5_core_dev *dev)
-{
-	struct mlx5_sd *sd = mlx5_get_sd(dev);
-
-	if (!sd)
-		return 1;
-
-	return sd->host_buses;
-}
-
-static struct mlx5_core_dev *mlx5_sd_get_primary(struct mlx5_core_dev *dev)
-{
-	struct mlx5_sd *sd = mlx5_get_sd(dev);
-
-	if (!sd)
-		return dev;
-
-	return sd->primary ? dev : sd->primary_dev;
-}
-
-struct mlx5_core_dev *
-mlx5_sd_primary_get_peer(struct mlx5_core_dev *primary, int idx)
-{
-	struct mlx5_sd *sd;
-
-	if (idx == 0)
-		return primary;
-
-	if (idx >= mlx5_sd_get_host_buses(primary))
-		return NULL;
-
-	sd = mlx5_get_sd(primary);
-	return sd->secondaries[idx - 1];
-}
-
-int mlx5_sd_ch_ix_get_dev_ix(struct mlx5_core_dev *dev, int ch_ix)
-{
-	return ch_ix % mlx5_sd_get_host_buses(dev);
-}
-
-int mlx5_sd_ch_ix_get_vec_ix(struct mlx5_core_dev *dev, int ch_ix)
-{
-	return ch_ix / mlx5_sd_get_host_buses(dev);
-}
-
-struct mlx5_core_dev *mlx5_sd_ch_ix_get_dev(struct mlx5_core_dev *primary, int ch_ix)
-{
-	int mdev_idx = mlx5_sd_ch_ix_get_dev_ix(primary, ch_ix);
-
-	return mlx5_sd_primary_get_peer(primary, mdev_idx);
-}
-
-static bool ft_create_alias_supported(struct mlx5_core_dev *dev)
-{
-	u64 obj_allowed = MLX5_CAP_GEN_2_64(dev, allowed_object_for_other_vhca_access);
-	u32 obj_supp = MLX5_CAP_GEN_2(dev, cross_vhca_object_to_object_supported);
-
-	if (!(obj_supp &
-	    MLX5_CROSS_VHCA_OBJ_TO_OBJ_SUPPORTED_LOCAL_FLOW_TABLE_ROOT_TO_REMOTE_FLOW_TABLE))
-		return false;
-
-	if (!(obj_allowed & MLX5_ALLOWED_OBJ_FOR_OTHER_VHCA_ACCESS_FLOW_TABLE))
-		return false;
-
-	return true;
-}
-
-static bool mlx5_sd_is_supported(struct mlx5_core_dev *dev, u8 host_buses)
-{
-	/* Feature is currently implemented for PFs only */
-	if (!mlx5_core_is_pf(dev))
-		return false;
-
-	/* Honor the SW implementation limit */
-	if (host_buses > MLX5_SD_MAX_GROUP_SZ)
-		return false;
-
-	/* Disconnect secondaries from the network */
-	if (!MLX5_CAP_GEN(dev, eswitch_manager))
-		return false;
-	if (!MLX5_CAP_GEN(dev, silent_mode))
-		return false;
-
-	/* RX steering from primary to secondaries */
-	if (!MLX5_CAP_GEN(dev, cross_vhca_rqt))
-		return false;
-	if (host_buses > MLX5_CAP_GEN_2(dev, max_rqt_vhca_id))
-		return false;
-
-	/* TX steering from secondaries to primary */
-	if (!ft_create_alias_supported(dev))
-		return false;
-	if (!MLX5_CAP_FLOWTABLE_NIC_TX(dev, reset_root_to_default))
-		return false;
-
-	return true;
-}
-
-static int mlx5_query_sd(struct mlx5_core_dev *dev, bool *sdm,
-			 u8 *host_buses, u8 *sd_group)
-{
-	u32 out[MLX5_ST_SZ_DW(mpir_reg)];
-	int err;
-
-	err = mlx5_query_mpir_reg(dev, out);
-	if (err)
-		return err;
-
-	err = mlx5_query_nic_vport_sd_group(dev, sd_group);
-	if (err)
-		return err;
-
-	*sdm = MLX5_GET(mpir_reg, out, sdm);
-	*host_buses = MLX5_GET(mpir_reg, out, host_buses);
-
-	return 0;
-}
-
-static u32 mlx5_sd_group_id(struct mlx5_core_dev *dev, u8 sd_group)
-{
-	return (u32)((MLX5_CAP_GEN(dev, native_port_num) << 8) | sd_group);
-}
-
-static int sd_init(struct mlx5_core_dev *dev)
-{
-	u8 host_buses, sd_group;
-	struct mlx5_sd *sd;
-	u32 group_id;
-	bool sdm;
-	int err;
-
-	err = mlx5_query_sd(dev, &sdm, &host_buses, &sd_group);
-	if (err)
-		return err;
-
-	if (!sdm)
-		return 0;
-
-	if (!sd_group)
-		return 0;
-
-	group_id = mlx5_sd_group_id(dev, sd_group);
-
-	if (!mlx5_sd_is_supported(dev, host_buses)) {
-		sd_warn(dev, "can't support requested netdev combining for group id 0x%x), skipping\n",
-			group_id);
-		return 0;
-	}
-
-	sd = kzalloc(sizeof(*sd), GFP_KERNEL);
-	if (!sd)
-		return -ENOMEM;
-
-	sd->host_buses = host_buses;
-	sd->group_id = group_id;
-
-	mlx5_set_sd(dev, sd);
-
-	return 0;
-}
-
-static void sd_cleanup(struct mlx5_core_dev *dev)
-{
-	struct mlx5_sd *sd = mlx5_get_sd(dev);
-
-	mlx5_set_sd(dev, NULL);
-	kfree(sd);
-}
-
-static int sd_register(struct mlx5_core_dev *dev)
-{
-	struct mlx5_devcom_comp_dev *devcom, *pos;
-	struct mlx5_core_dev *peer, *primary;
-	struct mlx5_sd *sd, *primary_sd;
-	int err, i;
-
-	sd = mlx5_get_sd(dev);
-	devcom = mlx5_devcom_register_component(dev->priv.devc, MLX5_DEVCOM_SD_GROUP,
-						sd->group_id, NULL, dev);
-	if (!devcom)
-		return -ENOMEM;
-
-	sd->devcom = devcom;
-
-	if (mlx5_devcom_comp_get_size(devcom) != sd->host_buses)
-		return 0;
-
-	mlx5_devcom_comp_lock(devcom);
-	mlx5_devcom_comp_set_ready(devcom, true);
-	mlx5_devcom_comp_unlock(devcom);
-
-	if (!mlx5_devcom_for_each_peer_begin(devcom)) {
-		err = -ENODEV;
-		goto err_devcom_unreg;
-	}
-
-	primary = dev;
-	mlx5_devcom_for_each_peer_entry(devcom, peer, pos)
-		if (peer->pdev->bus->number < primary->pdev->bus->number)
-			primary = peer;
-
-	primary_sd = mlx5_get_sd(primary);
-	primary_sd->primary = true;
-	i = 0;
-	/* loop the secondaries */
-	mlx5_devcom_for_each_peer_entry(primary_sd->devcom, peer, pos) {
-		struct mlx5_sd *peer_sd = mlx5_get_sd(peer);
-
-		primary_sd->secondaries[i++] = peer;
-		peer_sd->primary = false;
-		peer_sd->primary_dev = primary;
-	}
-
-	mlx5_devcom_for_each_peer_end(devcom);
-	return 0;
-
-err_devcom_unreg:
-	mlx5_devcom_comp_lock(sd->devcom);
-	mlx5_devcom_comp_set_ready(sd->devcom, false);
-	mlx5_devcom_comp_unlock(sd->devcom);
-	mlx5_devcom_unregister_component(sd->devcom);
-	return err;
-}
-
-static void sd_unregister(struct mlx5_core_dev *dev)
-{
-	struct mlx5_sd *sd = mlx5_get_sd(dev);
-
-	mlx5_devcom_comp_lock(sd->devcom);
-	mlx5_devcom_comp_set_ready(sd->devcom, false);
-	mlx5_devcom_comp_unlock(sd->devcom);
-	mlx5_devcom_unregister_component(sd->devcom);
-}
-
-static int sd_cmd_set_primary(struct mlx5_core_dev *primary, u8 *alias_key)
-{
-	struct mlx5_cmd_allow_other_vhca_access_attr allow_attr = {};
-	struct mlx5_sd *sd = mlx5_get_sd(primary);
-	struct mlx5_flow_table_attr ft_attr = {};
-	struct mlx5_flow_namespace *nic_ns;
-	struct mlx5_flow_table *ft;
-	int err;
-
-	nic_ns = mlx5_get_flow_namespace(primary, MLX5_FLOW_NAMESPACE_EGRESS);
-	if (!nic_ns)
-		return -EOPNOTSUPP;
-
-	ft = mlx5_create_flow_table(nic_ns, &ft_attr);
-	if (IS_ERR(ft)) {
-		err = PTR_ERR(ft);
-		return err;
-	}
-	sd->tx_ft = ft;
-	memcpy(allow_attr.access_key, alias_key, ACCESS_KEY_LEN);
-	allow_attr.obj_type = MLX5_GENERAL_OBJECT_TYPES_FLOW_TABLE_ALIAS;
-	allow_attr.obj_id = (ft->type << FT_ID_FT_TYPE_OFFSET) | ft->id;
-
-	err = mlx5_cmd_allow_other_vhca_access(primary, &allow_attr);
-	if (err) {
-		mlx5_core_err(primary, "Failed to allow other vhca access err=%d\n",
-			      err);
-		mlx5_destroy_flow_table(ft);
-		return err;
-	}
-
-	return 0;
-}
-
-static void sd_cmd_unset_primary(struct mlx5_core_dev *primary)
-{
-	struct mlx5_sd *sd = mlx5_get_sd(primary);
-
-	mlx5_destroy_flow_table(sd->tx_ft);
-}
-
-static int sd_secondary_create_alias_ft(struct mlx5_core_dev *secondary,
-					struct mlx5_core_dev *primary,
-					struct mlx5_flow_table *ft,
-					u32 *obj_id, u8 *alias_key)
-{
-	u32 aliased_object_id = (ft->type << FT_ID_FT_TYPE_OFFSET) | ft->id;
-	u16 vhca_id_to_be_accessed = MLX5_CAP_GEN(primary, vhca_id);
-	struct mlx5_cmd_alias_obj_create_attr alias_attr = {};
-	int ret;
-
-	memcpy(alias_attr.access_key, alias_key, ACCESS_KEY_LEN);
-	alias_attr.obj_id = aliased_object_id;
-	alias_attr.obj_type = MLX5_GENERAL_OBJECT_TYPES_FLOW_TABLE_ALIAS;
-	alias_attr.vhca_id = vhca_id_to_be_accessed;
-	ret = mlx5_cmd_alias_obj_create(secondary, &alias_attr, obj_id);
-	if (ret) {
-		mlx5_core_err(secondary, "Failed to create alias object err=%d\n",
-			      ret);
-		return ret;
-	}
-
-	return 0;
-}
-
-static void sd_secondary_destroy_alias_ft(struct mlx5_core_dev *secondary)
-{
-	struct mlx5_sd *sd = mlx5_get_sd(secondary);
-
-	mlx5_cmd_alias_obj_destroy(secondary, sd->alias_obj_id,
-				   MLX5_GENERAL_OBJECT_TYPES_FLOW_TABLE_ALIAS);
-}
-
-static int sd_cmd_set_secondary(struct mlx5_core_dev *secondary,
-				struct mlx5_core_dev *primary,
-				u8 *alias_key)
-{
-	struct mlx5_sd *primary_sd = mlx5_get_sd(primary);
-	struct mlx5_sd *sd = mlx5_get_sd(secondary);
-	int err;
-
-	err = mlx5_fs_cmd_set_l2table_entry_silent(secondary, 1);
-	if (err)
-		return err;
-
-	err = sd_secondary_create_alias_ft(secondary, primary, primary_sd->tx_ft,
-					   &sd->alias_obj_id, alias_key);
-	if (err)
-		goto err_unset_silent;
-
-	err = mlx5_fs_cmd_set_tx_flow_table_root(secondary, sd->alias_obj_id, false);
-	if (err)
-		goto err_destroy_alias_ft;
-
-	return 0;
-
-err_destroy_alias_ft:
-	sd_secondary_destroy_alias_ft(secondary);
-err_unset_silent:
-	mlx5_fs_cmd_set_l2table_entry_silent(secondary, 0);
-	return err;
-}
-
-static void sd_cmd_unset_secondary(struct mlx5_core_dev *secondary)
-{
-	mlx5_fs_cmd_set_tx_flow_table_root(secondary, 0, true);
-	sd_secondary_destroy_alias_ft(secondary);
-	mlx5_fs_cmd_set_l2table_entry_silent(secondary, 0);
-}
-
-static void sd_print_group(struct mlx5_core_dev *primary)
-{
-	struct mlx5_sd *sd = mlx5_get_sd(primary);
-	struct mlx5_core_dev *pos;
-	int i;
-
-	sd_info(primary, "group id %#x, primary %s, vhca %u\n",
-		sd->group_id, pci_name(primary->pdev),
-		MLX5_CAP_GEN(primary, vhca_id));
-	mlx5_sd_for_each_secondary(i, primary, pos)
-		sd_info(primary, "group id %#x, secondary#%d %s, vhca %u\n",
-			sd->group_id, i - 1, pci_name(pos->pdev),
-			MLX5_CAP_GEN(pos, vhca_id));
-}
-
-int mlx5_sd_init(struct mlx5_core_dev *dev)
-{
-	struct mlx5_core_dev *primary, *pos, *to;
-	struct mlx5_sd *sd = mlx5_get_sd(dev);
-	u8 alias_key[ACCESS_KEY_LEN];
-	int err, i;
-
-	err = sd_init(dev);
-	if (err)
-		return err;
-
-	sd = mlx5_get_sd(dev);
-	if (!sd)
-		return 0;
-
-	err = sd_register(dev);
-	if (err)
-		goto err_sd_cleanup;
-
-	if (!mlx5_devcom_comp_is_ready(sd->devcom))
-		return 0;
-
-	primary = mlx5_sd_get_primary(dev);
-
-	for (i = 0; i < ACCESS_KEY_LEN; i++)
-		alias_key[i] = get_random_u8();
-
-	err = sd_cmd_set_primary(primary, alias_key);
-	if (err)
-		goto err_sd_unregister;
-
-	mlx5_sd_for_each_secondary(i, primary, pos) {
-		err = sd_cmd_set_secondary(pos, primary, alias_key);
-		if (err)
-			goto err_unset_secondaries;
-	}
-
-	sd_info(primary, "group id %#x, size %d, combined\n",
-		sd->group_id, mlx5_devcom_comp_get_size(sd->devcom));
-	sd_print_group(primary);
-
-	return 0;
-
-err_unset_secondaries:
-	to = pos;
-	mlx5_sd_for_each_secondary_to(i, primary, to, pos)
-		sd_cmd_unset_secondary(pos);
-	sd_cmd_unset_primary(primary);
-err_sd_unregister:
-	sd_unregister(dev);
-err_sd_cleanup:
-	sd_cleanup(dev);
-	return err;
-}
-
-void mlx5_sd_cleanup(struct mlx5_core_dev *dev)
-{
-	struct mlx5_sd *sd = mlx5_get_sd(dev);
-	struct mlx5_core_dev *primary, *pos;
-	int i;
-
-	if (!sd)
-		return;
-
-	if (!mlx5_devcom_comp_is_ready(sd->devcom))
-		goto out;
-
-	primary = mlx5_sd_get_primary(dev);
-	mlx5_sd_for_each_secondary(i, primary, pos)
-		sd_cmd_unset_secondary(pos);
-	sd_cmd_unset_primary(primary);
-
-	sd_info(primary, "group id %#x, uncombined\n", sd->group_id);
-out:
-	sd_unregister(dev);
-	sd_cleanup(dev);
-}
-
-struct auxiliary_device *mlx5_sd_get_adev(struct mlx5_core_dev *dev,
-					  struct auxiliary_device *adev,
-					  int idx)
-{
-	struct mlx5_sd *sd = mlx5_get_sd(dev);
-	struct mlx5_core_dev *primary;
-
-	if (!sd)
-		return adev;
-
-	if (!mlx5_devcom_comp_is_ready(sd->devcom))
-		return NULL;
-
-	primary = mlx5_sd_get_primary(dev);
-	if (dev == primary)
-		return adev;
-
-	return &primary->priv.adev[idx]->adev;
-}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.h
deleted file mode 100644
index 137efaf9aabc..000000000000
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.h
+++ /dev/null
@@ -1,38 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
-/* Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
-
-#ifndef __MLX5_LIB_SD_H__
-#define __MLX5_LIB_SD_H__
-
-#define MLX5_SD_MAX_GROUP_SZ 2
-
-struct mlx5_sd;
-
-struct mlx5_core_dev *mlx5_sd_primary_get_peer(struct mlx5_core_dev *primary, int idx);
-int mlx5_sd_ch_ix_get_dev_ix(struct mlx5_core_dev *dev, int ch_ix);
-int mlx5_sd_ch_ix_get_vec_ix(struct mlx5_core_dev *dev, int ch_ix);
-struct mlx5_core_dev *mlx5_sd_ch_ix_get_dev(struct mlx5_core_dev *primary, int ch_ix);
-struct auxiliary_device *mlx5_sd_get_adev(struct mlx5_core_dev *dev,
-					  struct auxiliary_device *adev,
-					  int idx);
-
-int mlx5_sd_init(struct mlx5_core_dev *dev);
-void mlx5_sd_cleanup(struct mlx5_core_dev *dev);
-
-#define mlx5_sd_for_each_dev_from_to(i, primary, ix_from, to, pos)	\
-	for (i = ix_from;							\
-	     (pos = mlx5_sd_primary_get_peer(primary, i)) && pos != (to); i++)
-
-#define mlx5_sd_for_each_dev(i, primary, pos)				\
-	mlx5_sd_for_each_dev_from_to(i, primary, 0, NULL, pos)
-
-#define mlx5_sd_for_each_dev_to(i, primary, to, pos)			\
-	mlx5_sd_for_each_dev_from_to(i, primary, 0, to, pos)
-
-#define mlx5_sd_for_each_secondary(i, primary, pos)			\
-	mlx5_sd_for_each_dev_from_to(i, primary, 1, NULL, pos)
-
-#define mlx5_sd_for_each_secondary_to(i, primary, to, pos)		\
-	mlx5_sd_for_each_dev_from_to(i, primary, 1, to, pos)
-
-#endif /* __MLX5_LIB_SD_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index 1005bb6935b6..21753f327868 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -440,27 +440,6 @@ out:
 }
 EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_system_image_guid);
 
-int mlx5_query_nic_vport_sd_group(struct mlx5_core_dev *mdev, u8 *sd_group)
-{
-	int outlen = MLX5_ST_SZ_BYTES(query_nic_vport_context_out);
-	u32 *out;
-	int err;
-
-	out = kvzalloc(outlen, GFP_KERNEL);
-	if (!out)
-		return -ENOMEM;
-
-	err = mlx5_query_nic_vport_context(mdev, 0, out);
-	if (err)
-		goto out;
-
-	*sd_group = MLX5_GET(query_nic_vport_context_out, out,
-			     nic_vport_context.sd_group);
-out:
-	kvfree(out);
-	return err;
-}
-
 int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid)
 {
 	u32 *out;
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 2bba88c67f58..7ee5b79ff3d6 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -681,7 +681,6 @@ struct mlx5e_resources {
 		struct mlx5_sq_bfreg       bfreg;
 #define MLX5_MAX_NUM_TC 8
 		u32                        tisn[MLX5_MAX_PORTS][MLX5_MAX_NUM_TC];
-		bool			   tisn_valid;
 	} hw_objs;
 	struct net_device *uplink_netdev;
 	struct mutex uplink_netdev_lock;
@@ -822,7 +821,6 @@ struct mlx5_core_dev {
 	struct blocking_notifier_head macsec_nh;
 #endif
 	u64 num_ipsec_offloads;
-	struct mlx5_sd          *sd;
 };
 
 struct mlx5_db {
@@ -1224,14 +1222,6 @@ static inline bool mlx5_core_is_ecpf(const struct mlx5_core_dev *dev)
 	return dev->caps.embedded_cpu;
 }
 
-static inline bool mlx5_core_is_mgmt_pf(const struct mlx5_core_dev *dev)
-{
-	if (!MLX5_CAP_GEN_2(dev, local_mng_port_valid))
-		return false;
-
-	return MLX5_CAP_GEN_2(dev, local_mng_port);
-}
-
 static inline bool
 mlx5_core_is_ecpf_esw_manager(const struct mlx5_core_dev *dev)
 {
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 586569209254..fee20fc010c2 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1954,10 +1954,8 @@ enum {
 struct mlx5_ifc_cmd_hca_cap_2_bits {
 	u8	   reserved_at_0[0x80];
 
-	u8	   migratable[0x1];
-	u8	   reserved_at_81[0x19];
-	u8	   local_mng_port[0x1];
-	u8	   reserved_at_9b[0x5];
+	u8         migratable[0x1];
+	u8         reserved_at_81[0x1f];
 
 	u8	   max_reformat_insert_size[0x8];
 	u8	   max_reformat_insert_offset[0x8];
@@ -1975,13 +1973,7 @@ struct mlx5_ifc_cmd_hca_cap_2_bits {
 
 	u8	   allowed_object_for_other_vhca_access[0x40];
 
-	u8	   reserved_at_140[0x20];
-
-	u8	   reserved_at_160[0xa];
-	u8	   local_mng_port_valid[0x1];
-	u8	   reserved_at_16b[0x15];
-
-	u8	   reserved_at_180[0x20];
+	u8	   reserved_at_140[0x60];
 
 	u8	   flow_table_type_2_type[0x8];
 	u8	   reserved_at_1a8[0x3];
@@ -4038,13 +4030,8 @@ struct mlx5_ifc_nic_vport_context_bits {
 	u8	   affiliation_criteria[0x4];
 	u8	   affiliated_vhca_id[0x10];
 
-	u8	   reserved_at_60[0xa0];
+	u8	   reserved_at_60[0xd0];
 
-	u8	   reserved_at_100[0x1];
-	u8         sd_group[0x3];
-	u8	   reserved_at_104[0x1c];
-
-	u8	   reserved_at_120[0x10];
 	u8         mtu[0x10];
 
 	u8         system_image_guid[0x40];
@@ -10129,7 +10116,8 @@ struct mlx5_ifc_mpir_reg_bits {
 	u8         reserved_at_20[0x20];
 
 	u8         local_port[0x8];
-	u8         reserved_at_28[0x18];
+	u8         reserved_at_28[0x15];
+	u8         sd_group[0x3];
 
 	u8         reserved_at_60[0x20];
 };
diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h
index c36cc6d82926..fbb9bf447889 100644
--- a/include/linux/mlx5/vport.h
+++ b/include/linux/mlx5/vport.h
@@ -72,7 +72,6 @@ int mlx5_query_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 *mtu);
 int mlx5_modify_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 mtu);
 int mlx5_query_nic_vport_system_image_guid(struct mlx5_core_dev *mdev,
 					   u64 *system_image_guid);
-int mlx5_query_nic_vport_sd_group(struct mlx5_core_dev *mdev, u8 *sd_group);
 int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid);
 int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev,
 				    u16 vport, u64 node_guid);
-- 
cgit v1.2.3


From 4e33b071bb8e8415fb9847249ffcf300fa7d8cac Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 28 Dec 2023 07:51:41 +0000
Subject: block: remove disk_clear_zoned

disk_clear_zoned is unused now that the last warts of the host-aware
model support in sd are gone.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Link: https://lore.kernel.org/r/20231228075141.362560-3-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-zoned.c      | 21 ---------------------
 include/linux/blkdev.h |  1 -
 2 files changed, 22 deletions(-)

(limited to 'include')

diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index c59d44ee6b23..623879d875a4 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -615,24 +615,3 @@ int blk_revalidate_disk_zones(struct gendisk *disk,
 	return ret;
 }
 EXPORT_SYMBOL_GPL(blk_revalidate_disk_zones);
-
-void disk_clear_zoned(struct gendisk *disk)
-{
-	struct request_queue *q = disk->queue;
-
-	blk_mq_freeze_queue(q);
-
-	q->limits.zoned = false;
-	disk_free_zone_bitmaps(disk);
-	blk_queue_flag_clear(QUEUE_FLAG_ZONE_RESETALL, q);
-	q->required_elevator_features &= ~ELEVATOR_F_ZBD_SEQ_WRITE;
-	disk->nr_zones = 0;
-	disk->max_open_zones = 0;
-	disk->max_active_zones = 0;
-	q->limits.chunk_sectors = 0;
-	q->limits.zone_write_granularity = 0;
-	q->limits.max_zone_append_sectors = 0;
-
-	blk_mq_unfreeze_queue(q);
-}
-EXPORT_SYMBOL_GPL(disk_clear_zoned);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 94701a63ad8a..e1e705aef51e 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -318,7 +318,6 @@ typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx,
 			       void *data);
 
 void disk_set_zoned(struct gendisk *disk);
-void disk_clear_zoned(struct gendisk *disk);
 
 #define BLK_ALL_ZONES  ((unsigned int)-1)
 int blkdev_report_zones(struct block_device *bdev, sector_t sector,
-- 
cgit v1.2.3


From 1ab33c03145d0f6c345823fc2da935d9a1a9e9fc Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Sun, 7 Jan 2024 22:16:45 -0800
Subject: asm-generic: make sparse happy with odd-sized put_unaligned_*()

__put_unaligned_be24() and friends use implicit casts to convert
larger-sized data to bytes, which trips sparse truncation warnings when
the argument is a constant:

    CC [M]  drivers/input/touchscreen/hynitron_cstxxx.o
    CHECK   drivers/input/touchscreen/hynitron_cstxxx.c
  drivers/input/touchscreen/hynitron_cstxxx.c: note: in included file (through arch/x86/include/generated/asm/unaligned.h):
  include/asm-generic/unaligned.h:119:16: warning: cast truncates bits from constant value (aa01a0 becomes a0)
  include/asm-generic/unaligned.h:120:20: warning: cast truncates bits from constant value (aa01 becomes 1)
  include/asm-generic/unaligned.h:119:16: warning: cast truncates bits from constant value (ab00d0 becomes d0)
  include/asm-generic/unaligned.h:120:20: warning: cast truncates bits from constant value (ab00 becomes 0)

To avoid this let's mask off upper bits explicitly, the resulting code
should be exactly the same, but it will keep sparse happy.

Reported-by: kernel test robot <lkp@intel.com>
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Closes: https://lore.kernel.org/oe-kbuild-all/202401070147.gqwVulOn-lkp@intel.com/
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/asm-generic/unaligned.h | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/asm-generic/unaligned.h b/include/asm-generic/unaligned.h
index 699650f81970..a84c64e5f11e 100644
--- a/include/asm-generic/unaligned.h
+++ b/include/asm-generic/unaligned.h
@@ -104,9 +104,9 @@ static inline u32 get_unaligned_le24(const void *p)
 
 static inline void __put_unaligned_be24(const u32 val, u8 *p)
 {
-	*p++ = val >> 16;
-	*p++ = val >> 8;
-	*p++ = val;
+	*p++ = (val >> 16) & 0xff;
+	*p++ = (val >> 8) & 0xff;
+	*p++ = val & 0xff;
 }
 
 static inline void put_unaligned_be24(const u32 val, void *p)
@@ -116,9 +116,9 @@ static inline void put_unaligned_be24(const u32 val, void *p)
 
 static inline void __put_unaligned_le24(const u32 val, u8 *p)
 {
-	*p++ = val;
-	*p++ = val >> 8;
-	*p++ = val >> 16;
+	*p++ = val & 0xff;
+	*p++ = (val >> 8) & 0xff;
+	*p++ = (val >> 16) & 0xff;
 }
 
 static inline void put_unaligned_le24(const u32 val, void *p)
@@ -128,12 +128,12 @@ static inline void put_unaligned_le24(const u32 val, void *p)
 
 static inline void __put_unaligned_be48(const u64 val, u8 *p)
 {
-	*p++ = val >> 40;
-	*p++ = val >> 32;
-	*p++ = val >> 24;
-	*p++ = val >> 16;
-	*p++ = val >> 8;
-	*p++ = val;
+	*p++ = (val >> 40) & 0xff;
+	*p++ = (val >> 32) & 0xff;
+	*p++ = (val >> 24) & 0xff;
+	*p++ = (val >> 16) & 0xff;
+	*p++ = (val >> 8) & 0xff;
+	*p++ = val & 0xff;
 }
 
 static inline void put_unaligned_be48(const u64 val, void *p)
-- 
cgit v1.2.3


From 3b7cb745473aec7255d66e3854abaa9c3f46f952 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Mon, 8 Jan 2024 11:50:16 -0700
Subject: block: move __get_task_ioprio() into header file

We call this once per IO, which can be millions of times per second.
Since nobody really uses io priorities, or at least it isn't very
common, this is all wasted time and can amount to as much as 3% of
the total kernel time.

Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/ioprio.c         | 26 --------------------------
 include/linux/ioprio.h | 25 ++++++++++++++++++++++++-
 2 files changed, 24 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/block/ioprio.c b/block/ioprio.c
index b5a942519a79..73301a261429 100644
--- a/block/ioprio.c
+++ b/block/ioprio.c
@@ -139,32 +139,6 @@ out:
 	return ret;
 }
 
-/*
- * If the task has set an I/O priority, use that. Otherwise, return
- * the default I/O priority.
- *
- * Expected to be called for current task or with task_lock() held to keep
- * io_context stable.
- */
-int __get_task_ioprio(struct task_struct *p)
-{
-	struct io_context *ioc = p->io_context;
-	int prio;
-
-	if (p != current)
-		lockdep_assert_held(&p->alloc_lock);
-	if (ioc)
-		prio = ioc->ioprio;
-	else
-		prio = IOPRIO_DEFAULT;
-
-	if (IOPRIO_PRIO_CLASS(prio) == IOPRIO_CLASS_NONE)
-		prio = IOPRIO_PRIO_VALUE(task_nice_ioclass(p),
-					 task_nice_ioprio(p));
-	return prio;
-}
-EXPORT_SYMBOL_GPL(__get_task_ioprio);
-
 static int get_task_ioprio(struct task_struct *p)
 {
 	int ret;
diff --git a/include/linux/ioprio.h b/include/linux/ioprio.h
index 7578d4f6a969..d6a9b5b7ed16 100644
--- a/include/linux/ioprio.h
+++ b/include/linux/ioprio.h
@@ -47,7 +47,30 @@ static inline int task_nice_ioclass(struct task_struct *task)
 }
 
 #ifdef CONFIG_BLOCK
-int __get_task_ioprio(struct task_struct *p);
+/*
+ * If the task has set an I/O priority, use that. Otherwise, return
+ * the default I/O priority.
+ *
+ * Expected to be called for current task or with task_lock() held to keep
+ * io_context stable.
+ */
+static inline int __get_task_ioprio(struct task_struct *p)
+{
+	struct io_context *ioc = p->io_context;
+	int prio;
+
+	if (p != current)
+		lockdep_assert_held(&p->alloc_lock);
+	if (ioc)
+		prio = ioc->ioprio;
+	else
+		prio = IOPRIO_DEFAULT;
+
+	if (IOPRIO_PRIO_CLASS(prio) == IOPRIO_CLASS_NONE)
+		prio = IOPRIO_PRIO_VALUE(task_nice_ioclass(p),
+					 task_nice_ioprio(p));
+	return prio;
+}
 #else
 static inline int __get_task_ioprio(struct task_struct *p)
 {
-- 
cgit v1.2.3


From 53889bcaf536b3abedeaf104019877cee37dd08b Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Mon, 8 Jan 2024 11:51:57 -0700
Subject: block: make __get_task_ioprio() easier to read

We don't need to do any gymnastics if we don't have an io_context
assigned at all, so just return early with our default priority.

Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/ioprio.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/ioprio.h b/include/linux/ioprio.h
index d6a9b5b7ed16..db1249cd9692 100644
--- a/include/linux/ioprio.h
+++ b/include/linux/ioprio.h
@@ -59,13 +59,13 @@ static inline int __get_task_ioprio(struct task_struct *p)
 	struct io_context *ioc = p->io_context;
 	int prio;
 
+	if (!ioc)
+		return IOPRIO_DEFAULT;
+
 	if (p != current)
 		lockdep_assert_held(&p->alloc_lock);
-	if (ioc)
-		prio = ioc->ioprio;
-	else
-		prio = IOPRIO_DEFAULT;
 
+	prio = ioc->ioprio;
 	if (IOPRIO_PRIO_CLASS(prio) == IOPRIO_CLASS_NONE)
 		prio = IOPRIO_PRIO_VALUE(task_nice_ioclass(p),
 					 task_nice_ioprio(p));
-- 
cgit v1.2.3


From fd37721803c6e73619108f76ad2e12a9aa5fafaf Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Thu, 28 Dec 2023 17:47:03 +0300
Subject: mm, treewide: introduce NR_PAGE_ORDERS

NR_PAGE_ORDERS defines the number of page orders supported by the page
allocator, ranging from 0 to MAX_ORDER, MAX_ORDER + 1 in total.

NR_PAGE_ORDERS assists in defining arrays of page orders and allows for
more natural iteration over them.

[kirill.shutemov@linux.intel.com: fixup for kerneldoc warning]
  Link: https://lkml.kernel.org/r/20240101111512.7empzyifq7kxtzk3@box
Link: https://lkml.kernel.org/r/20231228144704.14033-1-kirill.shutemov@linux.intel.com
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 Documentation/admin-guide/kdump/vmcoreinfo.rst |  6 +++---
 arch/arm64/kvm/hyp/include/nvhe/gfp.h          |  2 +-
 arch/sparc/kernel/traps_64.c                   |  2 +-
 drivers/gpu/drm/ttm/tests/ttm_device_test.c    |  2 +-
 drivers/gpu/drm/ttm/ttm_pool.c                 | 20 ++++++++++----------
 include/drm/ttm/ttm_pool.h                     |  2 +-
 include/linux/mmzone.h                         |  6 ++++--
 kernel/crash_core.c                            |  2 +-
 lib/test_meminit.c                             |  2 +-
 mm/compaction.c                                |  2 +-
 mm/kmsan/init.c                                |  2 +-
 mm/page_alloc.c                                | 13 ++++++-------
 mm/page_reporting.c                            |  2 +-
 mm/show_mem.c                                  |  8 ++++----
 mm/vmstat.c                                    | 12 ++++++------
 15 files changed, 42 insertions(+), 41 deletions(-)

(limited to 'include')

diff --git a/Documentation/admin-guide/kdump/vmcoreinfo.rst b/Documentation/admin-guide/kdump/vmcoreinfo.rst
index 78e4d2e7ba14..3f8769e46b07 100644
--- a/Documentation/admin-guide/kdump/vmcoreinfo.rst
+++ b/Documentation/admin-guide/kdump/vmcoreinfo.rst
@@ -172,7 +172,7 @@ variables.
 Offset of the free_list's member. This value is used to compute the number
 of free pages.
 
-Each zone has a free_area structure array called free_area[MAX_ORDER + 1].
+Each zone has a free_area structure array called free_area[NR_PAGE_ORDERS].
 The free_list represents a linked list of free page blocks.
 
 (list_head, next|prev)
@@ -189,8 +189,8 @@ Offsets of the vmap_area's members. They carry vmalloc-specific
 information. Makedumpfile gets the start address of the vmalloc region
 from this.
 
-(zone.free_area, MAX_ORDER + 1)
--------------------------------
+(zone.free_area, NR_PAGE_ORDERS)
+--------------------------------
 
 Free areas descriptor. User-space tools use this value to iterate the
 free_area ranges. MAX_ORDER is used by the zone buddy allocator.
diff --git a/arch/arm64/kvm/hyp/include/nvhe/gfp.h b/arch/arm64/kvm/hyp/include/nvhe/gfp.h
index fe5472a184a3..97c527ef53c2 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/gfp.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/gfp.h
@@ -16,7 +16,7 @@ struct hyp_pool {
 	 * API at EL2.
 	 */
 	hyp_spinlock_t lock;
-	struct list_head free_area[MAX_ORDER + 1];
+	struct list_head free_area[NR_PAGE_ORDERS];
 	phys_addr_t range_start;
 	phys_addr_t range_end;
 	unsigned short max_order;
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index 08ffd17d5ec3..523a6e5ee925 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -897,7 +897,7 @@ void __init cheetah_ecache_flush_init(void)
 
 	/* Now allocate error trap reporting scoreboard. */
 	sz = NR_CPUS * (2 * sizeof(struct cheetah_err_info));
-	for (order = 0; order <= MAX_ORDER; order++) {
+	for (order = 0; order < NR_PAGE_ORDERS; order++) {
 		if ((PAGE_SIZE << order) >= sz)
 			break;
 	}
diff --git a/drivers/gpu/drm/ttm/tests/ttm_device_test.c b/drivers/gpu/drm/ttm/tests/ttm_device_test.c
index b1b423b68cdf..19eaff22e6ae 100644
--- a/drivers/gpu/drm/ttm/tests/ttm_device_test.c
+++ b/drivers/gpu/drm/ttm/tests/ttm_device_test.c
@@ -175,7 +175,7 @@ static void ttm_device_init_pools(struct kunit *test)
 
 	if (params->pools_init_expected) {
 		for (int i = 0; i < TTM_NUM_CACHING_TYPES; ++i) {
-			for (int j = 0; j <= MAX_ORDER; ++j) {
+			for (int j = 0; j < NR_PAGE_ORDERS; ++j) {
 				pt = pool->caching[i].orders[j];
 				KUNIT_EXPECT_PTR_EQ(test, pt.pool, pool);
 				KUNIT_EXPECT_EQ(test, pt.caching, i);
diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c
index fe610a3cace0..d183bb97c526 100644
--- a/drivers/gpu/drm/ttm/ttm_pool.c
+++ b/drivers/gpu/drm/ttm/ttm_pool.c
@@ -65,11 +65,11 @@ module_param(page_pool_size, ulong, 0644);
 
 static atomic_long_t allocated_pages;
 
-static struct ttm_pool_type global_write_combined[MAX_ORDER + 1];
-static struct ttm_pool_type global_uncached[MAX_ORDER + 1];
+static struct ttm_pool_type global_write_combined[NR_PAGE_ORDERS];
+static struct ttm_pool_type global_uncached[NR_PAGE_ORDERS];
 
-static struct ttm_pool_type global_dma32_write_combined[MAX_ORDER + 1];
-static struct ttm_pool_type global_dma32_uncached[MAX_ORDER + 1];
+static struct ttm_pool_type global_dma32_write_combined[NR_PAGE_ORDERS];
+static struct ttm_pool_type global_dma32_uncached[NR_PAGE_ORDERS];
 
 static spinlock_t shrinker_lock;
 static struct list_head shrinker_list;
@@ -568,7 +568,7 @@ void ttm_pool_init(struct ttm_pool *pool, struct device *dev,
 
 	if (use_dma_alloc || nid != NUMA_NO_NODE) {
 		for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i)
-			for (j = 0; j <= MAX_ORDER; ++j)
+			for (j = 0; j < NR_PAGE_ORDERS; ++j)
 				ttm_pool_type_init(&pool->caching[i].orders[j],
 						   pool, i, j);
 	}
@@ -601,7 +601,7 @@ void ttm_pool_fini(struct ttm_pool *pool)
 
 	if (pool->use_dma_alloc || pool->nid != NUMA_NO_NODE) {
 		for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i)
-			for (j = 0; j <= MAX_ORDER; ++j)
+			for (j = 0; j < NR_PAGE_ORDERS; ++j)
 				ttm_pool_type_fini(&pool->caching[i].orders[j]);
 	}
 
@@ -656,7 +656,7 @@ static void ttm_pool_debugfs_header(struct seq_file *m)
 	unsigned int i;
 
 	seq_puts(m, "\t ");
-	for (i = 0; i <= MAX_ORDER; ++i)
+	for (i = 0; i < NR_PAGE_ORDERS; ++i)
 		seq_printf(m, " ---%2u---", i);
 	seq_puts(m, "\n");
 }
@@ -667,7 +667,7 @@ static void ttm_pool_debugfs_orders(struct ttm_pool_type *pt,
 {
 	unsigned int i;
 
-	for (i = 0; i <= MAX_ORDER; ++i)
+	for (i = 0; i < NR_PAGE_ORDERS; ++i)
 		seq_printf(m, " %8u", ttm_pool_type_count(&pt[i]));
 	seq_puts(m, "\n");
 }
@@ -776,7 +776,7 @@ int ttm_pool_mgr_init(unsigned long num_pages)
 	spin_lock_init(&shrinker_lock);
 	INIT_LIST_HEAD(&shrinker_list);
 
-	for (i = 0; i <= MAX_ORDER; ++i) {
+	for (i = 0; i < NR_PAGE_ORDERS; ++i) {
 		ttm_pool_type_init(&global_write_combined[i], NULL,
 				   ttm_write_combined, i);
 		ttm_pool_type_init(&global_uncached[i], NULL, ttm_uncached, i);
@@ -816,7 +816,7 @@ void ttm_pool_mgr_fini(void)
 {
 	unsigned int i;
 
-	for (i = 0; i <= MAX_ORDER; ++i) {
+	for (i = 0; i < NR_PAGE_ORDERS; ++i) {
 		ttm_pool_type_fini(&global_write_combined[i]);
 		ttm_pool_type_fini(&global_uncached[i]);
 
diff --git a/include/drm/ttm/ttm_pool.h b/include/drm/ttm/ttm_pool.h
index 30a347e5aa11..4490d43c63e3 100644
--- a/include/drm/ttm/ttm_pool.h
+++ b/include/drm/ttm/ttm_pool.h
@@ -74,7 +74,7 @@ struct ttm_pool {
 	bool use_dma32;
 
 	struct {
-		struct ttm_pool_type orders[MAX_ORDER + 1];
+		struct ttm_pool_type orders[NR_PAGE_ORDERS];
 	} caching[TTM_NUM_CACHING_TYPES];
 };
 
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index c18c53353b50..1ea7636dfb76 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -35,6 +35,8 @@
 
 #define IS_MAX_ORDER_ALIGNED(pfn) IS_ALIGNED(pfn, MAX_ORDER_NR_PAGES)
 
+#define NR_PAGE_ORDERS (MAX_ORDER + 1)
+
 /*
  * PAGE_ALLOC_COSTLY_ORDER is the order at which allocations are deemed
  * costly to service.  That is between allocation orders which should
@@ -96,7 +98,7 @@ static inline bool migratetype_is_mergeable(int mt)
 }
 
 #define for_each_migratetype_order(order, type) \
-	for (order = 0; order <= MAX_ORDER; order++) \
+	for (order = 0; order < NR_PAGE_ORDERS; order++) \
 		for (type = 0; type < MIGRATE_TYPES; type++)
 
 extern int page_group_by_mobility_disabled;
@@ -933,7 +935,7 @@ struct zone {
 	CACHELINE_PADDING(_pad1_);
 
 	/* free areas of different sizes */
-	struct free_area	free_area[MAX_ORDER + 1];
+	struct free_area	free_area[NR_PAGE_ORDERS];
 
 #ifdef CONFIG_UNACCEPTED_MEMORY
 	/* Pages to be accepted. All pages on the list are MAX_ORDER */
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index d4313b53837e..56cf4ad7abbb 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -802,7 +802,7 @@ static int __init crash_save_vmcoreinfo_init(void)
 	VMCOREINFO_OFFSET(list_head, prev);
 	VMCOREINFO_OFFSET(vmap_area, va_start);
 	VMCOREINFO_OFFSET(vmap_area, list);
-	VMCOREINFO_LENGTH(zone.free_area, MAX_ORDER + 1);
+	VMCOREINFO_LENGTH(zone.free_area, NR_PAGE_ORDERS);
 	log_buf_vmcoreinfo_setup();
 	VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES);
 	VMCOREINFO_NUMBER(NR_FREE_PAGES);
diff --git a/lib/test_meminit.c b/lib/test_meminit.c
index 0ae35223d773..0dc173849a54 100644
--- a/lib/test_meminit.c
+++ b/lib/test_meminit.c
@@ -93,7 +93,7 @@ static int __init test_pages(int *total_failures)
 	int failures = 0, num_tests = 0;
 	int i;
 
-	for (i = 0; i <= MAX_ORDER; i++)
+	for (i = 0; i < NR_PAGE_ORDERS; i++)
 		num_tests += do_alloc_pages_order(i, &failures);
 
 	REPORT_FAILURES_IN_FN();
diff --git a/mm/compaction.c b/mm/compaction.c
index de15a2ef0af5..24f8eb4d6260 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -2229,7 +2229,7 @@ static enum compact_result __compact_finished(struct compact_control *cc)
 
 	/* Direct compactor: Is a suitable page free? */
 	ret = COMPACT_NO_SUITABLE_PAGE;
-	for (order = cc->order; order <= MAX_ORDER; order++) {
+	for (order = cc->order; order < NR_PAGE_ORDERS; order++) {
 		struct free_area *area = &cc->zone->free_area[order];
 		bool can_steal;
 
diff --git a/mm/kmsan/init.c b/mm/kmsan/init.c
index ffedf4dbc49d..103e2e88ea03 100644
--- a/mm/kmsan/init.c
+++ b/mm/kmsan/init.c
@@ -96,7 +96,7 @@ void __init kmsan_init_shadow(void)
 struct metadata_page_pair {
 	struct page *shadow, *origin;
 };
-static struct metadata_page_pair held_back[MAX_ORDER + 1] __initdata;
+static struct metadata_page_pair held_back[NR_PAGE_ORDERS] __initdata;
 
 /*
  * Eager metadata allocation. When the memblock allocator is freeing pages to
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 5526797b7f96..ccecf6158ae4 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1560,7 +1560,7 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
 	struct page *page;
 
 	/* Find a page of the appropriate size in the preferred list */
-	for (current_order = order; current_order <= MAX_ORDER; ++current_order) {
+	for (current_order = order; current_order < NR_PAGE_ORDERS; ++current_order) {
 		area = &(zone->free_area[current_order]);
 		page = get_page_from_free_area(area, migratetype);
 		if (!page)
@@ -1934,7 +1934,7 @@ static bool unreserve_highatomic_pageblock(const struct alloc_context *ac,
 			continue;
 
 		spin_lock_irqsave(&zone->lock, flags);
-		for (order = 0; order <= MAX_ORDER; order++) {
+		for (order = 0; order < NR_PAGE_ORDERS; order++) {
 			struct free_area *area = &(zone->free_area[order]);
 
 			page = get_page_from_free_area(area, MIGRATE_HIGHATOMIC);
@@ -2044,8 +2044,7 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype,
 	return false;
 
 find_smallest:
-	for (current_order = order; current_order <= MAX_ORDER;
-							current_order++) {
+	for (current_order = order; current_order < NR_PAGE_ORDERS; current_order++) {
 		area = &(zone->free_area[current_order]);
 		fallback_mt = find_suitable_fallback(area, current_order,
 				start_migratetype, false, &can_steal);
@@ -3000,7 +2999,7 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
 		return true;
 
 	/* For a high-order request, check at least one suitable page is free */
-	for (o = order; o <= MAX_ORDER; o++) {
+	for (o = order; o < NR_PAGE_ORDERS; o++) {
 		struct free_area *area = &z->free_area[o];
 		int mt;
 
@@ -6628,7 +6627,7 @@ bool is_free_buddy_page(struct page *page)
 	unsigned long pfn = page_to_pfn(page);
 	unsigned int order;
 
-	for (order = 0; order <= MAX_ORDER; order++) {
+	for (order = 0; order < NR_PAGE_ORDERS; order++) {
 		struct page *page_head = page - (pfn & ((1 << order) - 1));
 
 		if (PageBuddy(page_head) &&
@@ -6683,7 +6682,7 @@ bool take_page_off_buddy(struct page *page)
 	bool ret = false;
 
 	spin_lock_irqsave(&zone->lock, flags);
-	for (order = 0; order <= MAX_ORDER; order++) {
+	for (order = 0; order < NR_PAGE_ORDERS; order++) {
 		struct page *page_head = page - (pfn & ((1 << order) - 1));
 		int page_order = buddy_order(page_head);
 
diff --git a/mm/page_reporting.c b/mm/page_reporting.c
index b021f482a4cb..66369cc5279b 100644
--- a/mm/page_reporting.c
+++ b/mm/page_reporting.c
@@ -276,7 +276,7 @@ page_reporting_process_zone(struct page_reporting_dev_info *prdev,
 		return err;
 
 	/* Process each free list starting from lowest order/mt */
-	for (order = page_reporting_order; order <= MAX_ORDER; order++) {
+	for (order = page_reporting_order; order < NR_PAGE_ORDERS; order++) {
 		for (mt = 0; mt < MIGRATE_TYPES; mt++) {
 			/* We do not pull pages from the isolate free list */
 			if (is_migrate_isolate(mt))
diff --git a/mm/show_mem.c b/mm/show_mem.c
index ba0808d6917f..8dcfafbd283c 100644
--- a/mm/show_mem.c
+++ b/mm/show_mem.c
@@ -352,8 +352,8 @@ static void show_free_areas(unsigned int filter, nodemask_t *nodemask, int max_z
 
 	for_each_populated_zone(zone) {
 		unsigned int order;
-		unsigned long nr[MAX_ORDER + 1], flags, total = 0;
-		unsigned char types[MAX_ORDER + 1];
+		unsigned long nr[NR_PAGE_ORDERS], flags, total = 0;
+		unsigned char types[NR_PAGE_ORDERS];
 
 		if (zone_idx(zone) > max_zone_idx)
 			continue;
@@ -363,7 +363,7 @@ static void show_free_areas(unsigned int filter, nodemask_t *nodemask, int max_z
 		printk(KERN_CONT "%s: ", zone->name);
 
 		spin_lock_irqsave(&zone->lock, flags);
-		for (order = 0; order <= MAX_ORDER; order++) {
+		for (order = 0; order < NR_PAGE_ORDERS; order++) {
 			struct free_area *area = &zone->free_area[order];
 			int type;
 
@@ -377,7 +377,7 @@ static void show_free_areas(unsigned int filter, nodemask_t *nodemask, int max_z
 			}
 		}
 		spin_unlock_irqrestore(&zone->lock, flags);
-		for (order = 0; order <= MAX_ORDER; order++) {
+		for (order = 0; order < NR_PAGE_ORDERS; order++) {
 			printk(KERN_CONT "%lu*%lukB ",
 			       nr[order], K(1UL) << order);
 			if (nr[order])
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 1437ca2f28c5..03ead31c46a0 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1059,7 +1059,7 @@ static void fill_contig_page_info(struct zone *zone,
 	info->free_blocks_total = 0;
 	info->free_blocks_suitable = 0;
 
-	for (order = 0; order <= MAX_ORDER; order++) {
+	for (order = 0; order < NR_PAGE_ORDERS; order++) {
 		unsigned long blocks;
 
 		/*
@@ -1476,7 +1476,7 @@ static void frag_show_print(struct seq_file *m, pg_data_t *pgdat,
 	int order;
 
 	seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name);
-	for (order = 0; order <= MAX_ORDER; ++order)
+	for (order = 0; order < NR_PAGE_ORDERS; ++order)
 		/*
 		 * Access to nr_free is lockless as nr_free is used only for
 		 * printing purposes. Use data_race to avoid KCSAN warning.
@@ -1505,7 +1505,7 @@ static void pagetypeinfo_showfree_print(struct seq_file *m,
 					pgdat->node_id,
 					zone->name,
 					migratetype_names[mtype]);
-		for (order = 0; order <= MAX_ORDER; ++order) {
+		for (order = 0; order < NR_PAGE_ORDERS; ++order) {
 			unsigned long freecount = 0;
 			struct free_area *area;
 			struct list_head *curr;
@@ -1545,7 +1545,7 @@ static void pagetypeinfo_showfree(struct seq_file *m, void *arg)
 
 	/* Print header */
 	seq_printf(m, "%-43s ", "Free pages count per migrate type at order");
-	for (order = 0; order <= MAX_ORDER; ++order)
+	for (order = 0; order < NR_PAGE_ORDERS; ++order)
 		seq_printf(m, "%6d ", order);
 	seq_putc(m, '\n');
 
@@ -2181,7 +2181,7 @@ static void unusable_show_print(struct seq_file *m,
 	seq_printf(m, "Node %d, zone %8s ",
 				pgdat->node_id,
 				zone->name);
-	for (order = 0; order <= MAX_ORDER; ++order) {
+	for (order = 0; order < NR_PAGE_ORDERS; ++order) {
 		fill_contig_page_info(zone, order, &info);
 		index = unusable_free_index(order, &info);
 		seq_printf(m, "%d.%03d ", index / 1000, index % 1000);
@@ -2233,7 +2233,7 @@ static void extfrag_show_print(struct seq_file *m,
 	seq_printf(m, "Node %d, zone %8s ",
 				pgdat->node_id,
 				zone->name);
-	for (order = 0; order <= MAX_ORDER; ++order) {
+	for (order = 0; order < NR_PAGE_ORDERS; ++order) {
 		fill_contig_page_info(zone, order, &info);
 		index = __fragmentation_index(order, &info);
 		seq_printf(m, "%2d.%03d ", index / 1000, index % 1000);
-- 
cgit v1.2.3


From 5e0a760b44417f7cadd79de2204d6247109558a0 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Thu, 28 Dec 2023 17:47:04 +0300
Subject: mm, treewide: rename MAX_ORDER to MAX_PAGE_ORDER

commit 23baf831a32c ("mm, treewide: redefine MAX_ORDER sanely") has
changed the definition of MAX_ORDER to be inclusive.  This has caused
issues with code that was not yet upstream and depended on the previous
definition.

To draw attention to the altered meaning of the define, rename MAX_ORDER
to MAX_PAGE_ORDER.

Link: https://lkml.kernel.org/r/20231228144704.14033-2-kirill.shutemov@linux.intel.com
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 Documentation/admin-guide/kdump/vmcoreinfo.rst  |  2 +-
 Documentation/admin-guide/kernel-parameters.txt | 24 ++++++++++++------------
 Documentation/networking/packet_mmap.rst        | 14 +++++++-------
 arch/arm/Kconfig                                |  2 +-
 arch/arm64/Kconfig                              | 20 ++++++++++----------
 arch/arm64/include/asm/sparsemem.h              |  2 +-
 arch/arm64/kvm/hyp/nvhe/page_alloc.c            |  3 ++-
 arch/arm64/mm/hugetlbpage.c                     |  2 +-
 arch/m68k/Kconfig.cpu                           |  2 +-
 arch/nios2/Kconfig                              |  2 +-
 arch/powerpc/Kconfig                            |  2 +-
 arch/powerpc/mm/book3s64/iommu_api.c            |  2 +-
 arch/powerpc/mm/hugetlbpage.c                   |  2 +-
 arch/powerpc/platforms/powernv/pci-ioda.c       |  2 +-
 arch/sh/mm/Kconfig                              |  2 +-
 arch/sparc/Kconfig                              |  2 +-
 arch/sparc/kernel/pci_sun4v.c                   |  2 +-
 arch/sparc/mm/tsb.c                             |  4 ++--
 arch/um/kernel/um_arch.c                        |  4 ++--
 arch/xtensa/Kconfig                             |  2 +-
 drivers/accel/qaic/qaic_data.c                  |  2 +-
 drivers/base/regmap/regmap-debugfs.c            |  8 ++++----
 drivers/block/floppy.c                          |  2 +-
 drivers/crypto/ccp/sev-dev.c                    |  2 +-
 drivers/crypto/hisilicon/sgl.c                  |  6 +++---
 drivers/gpu/drm/i915/gem/i915_gem_internal.c    |  2 +-
 drivers/gpu/drm/i915/gem/selftests/huge_pages.c |  2 +-
 drivers/gpu/drm/ttm/tests/ttm_pool_test.c       |  8 ++++----
 drivers/gpu/drm/ttm/ttm_pool.c                  |  2 +-
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h     |  2 +-
 drivers/iommu/dma-iommu.c                       |  2 +-
 drivers/irqchip/irq-gic-v3-its.c                |  4 ++--
 drivers/md/dm-bufio.c                           |  2 +-
 drivers/md/dm-crypt.c                           |  2 +-
 drivers/md/dm-flakey.c                          |  2 +-
 drivers/misc/genwqe/card_dev.c                  |  2 +-
 drivers/misc/genwqe/card_utils.c                |  4 ++--
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c |  2 +-
 drivers/net/ethernet/ibm/ibmvnic.h              |  4 ++--
 drivers/video/fbdev/hyperv_fb.c                 |  6 +++---
 drivers/video/fbdev/vermilion/vermilion.c       |  2 +-
 drivers/virtio/virtio_balloon.c                 |  2 +-
 drivers/virtio/virtio_mem.c                     |  8 ++++----
 fs/ramfs/file-nommu.c                           |  2 +-
 include/linux/hugetlb.h                         |  2 +-
 include/linux/mmzone.h                          | 14 +++++++-------
 include/linux/pageblock-flags.h                 |  4 ++--
 include/linux/slab.h                            |  4 ++--
 kernel/dma/pool.c                               |  6 +++---
 kernel/dma/swiotlb.c                            |  4 ++--
 kernel/events/ring_buffer.c                     | 10 +++++-----
 mm/Kconfig                                      |  6 +++---
 mm/compaction.c                                 |  4 ++--
 mm/debug_page_alloc.c                           |  2 +-
 mm/debug_vm_pgtable.c                           |  4 ++--
 mm/huge_memory.c                                |  2 +-
 mm/hugetlb.c                                    |  4 ++--
 mm/internal.h                                   |  2 +-
 mm/kmsan/init.c                                 |  6 +++---
 mm/memblock.c                                   |  7 ++++---
 mm/memory_hotplug.c                             |  9 +++++----
 mm/mm_init.c                                    | 22 +++++++++++-----------
 mm/page_alloc.c                                 | 24 ++++++++++++------------
 mm/page_isolation.c                             | 17 +++++++++--------
 mm/page_owner.c                                 |  6 +++---
 mm/page_reporting.c                             |  4 ++--
 mm/shuffle.h                                    |  2 +-
 mm/slab.c                                       |  2 +-
 mm/slub.c                                       |  4 ++--
 mm/vmscan.c                                     |  2 +-
 mm/vmstat.c                                     |  2 +-
 net/smc/smc_ib.c                                |  2 +-
 security/integrity/ima/ima_crypto.c             |  2 +-
 tools/perf/Documentation/perf-intel-pt.txt      |  2 +-
 tools/testing/memblock/linux/mmzone.h           |  6 +++---
 tools/testing/selftests/mm/thuge-gen.c          |  3 ++-
 76 files changed, 186 insertions(+), 181 deletions(-)

(limited to 'include')

diff --git a/Documentation/admin-guide/kdump/vmcoreinfo.rst b/Documentation/admin-guide/kdump/vmcoreinfo.rst
index 3f8769e46b07..bced9e4b6e08 100644
--- a/Documentation/admin-guide/kdump/vmcoreinfo.rst
+++ b/Documentation/admin-guide/kdump/vmcoreinfo.rst
@@ -193,7 +193,7 @@ from this.
 --------------------------------
 
 Free areas descriptor. User-space tools use this value to iterate the
-free_area ranges. MAX_ORDER is used by the zone buddy allocator.
+free_area ranges. NR_PAGE_ORDERS is used by the zone buddy allocator.
 
 prb
 ---
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 65731b060e3f..8a01b8112f0b 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -970,17 +970,17 @@
 			buddy allocator. Bigger value increase the probability
 			of catching random memory corruption, but reduce the
 			amount of memory for normal system use. The maximum
-			possible value is MAX_ORDER/2.  Setting this parameter
-			to 1 or 2 should be enough to identify most random
-			memory corruption problems caused by bugs in kernel or
-			driver code when a CPU writes to (or reads from) a
-			random memory location. Note that there exists a class
-			of memory corruptions problems caused by buggy H/W or
-			F/W or by drivers badly programming DMA (basically when
-			memory is written at bus level and the CPU MMU is
-			bypassed) which are not detectable by
-			CONFIG_DEBUG_PAGEALLOC, hence this option will not help
-			tracking down these problems.
+			possible value is MAX_PAGE_ORDER/2.  Setting this
+			parameter to 1 or 2 should be enough to identify most
+			random memory corruption problems caused by bugs in
+			kernel or driver code when a CPU writes to (or reads
+			from) a random memory location. Note that there exists
+			a class of memory corruptions problems caused by buggy
+			H/W or F/W or by drivers badly programming DMA
+			(basically when memory is written at bus level and the
+			CPU MMU is bypassed) which are not detectable by
+			CONFIG_DEBUG_PAGEALLOC, hence this option will not
+			help tracking down these problems.
 
 	debug_pagealloc=
 			[KNL] When CONFIG_DEBUG_PAGEALLOC is set, this parameter
@@ -4136,7 +4136,7 @@
 			[KNL] Minimal page reporting order
 			Format: <integer>
 			Adjust the minimal page reporting order. The page
-			reporting is disabled when it exceeds MAX_ORDER.
+			reporting is disabled when it exceeds MAX_PAGE_ORDER.
 
 	panic=		[KNL] Kernel behaviour on panic: delay <timeout>
 			timeout > 0: seconds before rebooting
diff --git a/Documentation/networking/packet_mmap.rst b/Documentation/networking/packet_mmap.rst
index 30a3be3c48f3..dca15d15feaf 100644
--- a/Documentation/networking/packet_mmap.rst
+++ b/Documentation/networking/packet_mmap.rst
@@ -263,20 +263,20 @@ the name indicates, this function allocates pages of memory, and the second
 argument is "order" or a power of two number of pages, that is
 (for PAGE_SIZE == 4096) order=0 ==> 4096 bytes, order=1 ==> 8192 bytes,
 order=2 ==> 16384 bytes, etc. The maximum size of a
-region allocated by __get_free_pages is determined by the MAX_ORDER macro. More
-precisely the limit can be calculated as::
+region allocated by __get_free_pages is determined by the MAX_PAGE_ORDER macro.
+More precisely the limit can be calculated as::
 
-   PAGE_SIZE << MAX_ORDER
+   PAGE_SIZE << MAX_PAGE_ORDER
 
    In a i386 architecture PAGE_SIZE is 4096 bytes
-   In a 2.4/i386 kernel MAX_ORDER is 10
-   In a 2.6/i386 kernel MAX_ORDER is 11
+   In a 2.4/i386 kernel MAX_PAGE_ORDER is 10
+   In a 2.6/i386 kernel MAX_PAGE_ORDER is 11
 
 So get_free_pages can allocate as much as 4MB or 8MB in a 2.4/2.6 kernel
 respectively, with an i386 architecture.
 
 User space programs can include /usr/include/sys/user.h and
-/usr/include/linux/mmzone.h to get PAGE_SIZE MAX_ORDER declarations.
+/usr/include/linux/mmzone.h to get PAGE_SIZE MAX_PAGE_ORDER declarations.
 
 The pagesize can also be determined dynamically with the getpagesize (2)
 system call.
@@ -324,7 +324,7 @@ Definitions:
 		(see /proc/slabinfo)
 <pointer size>  depends on the architecture -- ``sizeof(void *)``
 <page size>     depends on the architecture -- PAGE_SIZE or getpagesize (2)
-<max-order>     is the value defined with MAX_ORDER
+<max-order>     is the value defined with MAX_PAGE_ORDER
 <frame size>    it's an upper bound of frame's capture size (more on this later)
 ==============  ================================================================
 
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index f8567e95f98b..b2ab8db63c4b 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1362,7 +1362,7 @@ config ARCH_FORCE_MAX_ORDER
 	default "10"
 	help
 	  The kernel page allocator limits the size of maximal physically
-	  contiguous allocations. The limit is called MAX_ORDER and it
+	  contiguous allocations. The limit is called MAX_PAGE_ORDER and it
 	  defines the maximal power of two of number of pages that can be
 	  allocated as a single contiguous block. This option allows
 	  overriding the default setting when ability to allocate very
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 12d611f3da5d..442539fd06fe 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1520,15 +1520,15 @@ config XEN
 
 # include/linux/mmzone.h requires the following to be true:
 #
-#   MAX_ORDER + PAGE_SHIFT <= SECTION_SIZE_BITS
+#   MAX_PAGE_ORDER + PAGE_SHIFT <= SECTION_SIZE_BITS
 #
-# so the maximum value of MAX_ORDER is SECTION_SIZE_BITS - PAGE_SHIFT:
+# so the maximum value of MAX_PAGE_ORDER is SECTION_SIZE_BITS - PAGE_SHIFT:
 #
-#     | SECTION_SIZE_BITS |  PAGE_SHIFT  |  max MAX_ORDER  |  default MAX_ORDER |
-# ----+-------------------+--------------+-----------------+--------------------+
-# 4K  |       27          |      12      |       15        |         10         |
-# 16K |       27          |      14      |       13        |         11         |
-# 64K |       29          |      16      |       13        |         13         |
+#     | SECTION_SIZE_BITS |  PAGE_SHIFT  |  max MAX_PAGE_ORDER  |  default MAX_PAGE_ORDER |
+# ----+-------------------+--------------+----------------------+-------------------------+
+# 4K  |       27          |      12      |       15             |         10              |
+# 16K |       27          |      14      |       13             |         11              |
+# 64K |       29          |      16      |       13             |         13              |
 config ARCH_FORCE_MAX_ORDER
 	int
 	default "13" if ARM64_64K_PAGES
@@ -1536,16 +1536,16 @@ config ARCH_FORCE_MAX_ORDER
 	default "10"
 	help
 	  The kernel page allocator limits the size of maximal physically
-	  contiguous allocations. The limit is called MAX_ORDER and it
+	  contiguous allocations. The limit is called MAX_PAGE_ORDER and it
 	  defines the maximal power of two of number of pages that can be
 	  allocated as a single contiguous block. This option allows
 	  overriding the default setting when ability to allocate very
 	  large blocks of physically contiguous memory is required.
 
 	  The maximal size of allocation cannot exceed the size of the
-	  section, so the value of MAX_ORDER should satisfy
+	  section, so the value of MAX_PAGE_ORDER should satisfy
 
-	    MAX_ORDER + PAGE_SHIFT <= SECTION_SIZE_BITS
+	    MAX_PAGE_ORDER + PAGE_SHIFT <= SECTION_SIZE_BITS
 
 	  Don't change if unsure.
 
diff --git a/arch/arm64/include/asm/sparsemem.h b/arch/arm64/include/asm/sparsemem.h
index 5f5437621029..8a8acc220371 100644
--- a/arch/arm64/include/asm/sparsemem.h
+++ b/arch/arm64/include/asm/sparsemem.h
@@ -10,7 +10,7 @@
 /*
  * Section size must be at least 512MB for 64K base
  * page size config. Otherwise it will be less than
- * MAX_ORDER and the build process will fail.
+ * MAX_PAGE_ORDER and the build process will fail.
  */
 #ifdef CONFIG_ARM64_64K_PAGES
 #define SECTION_SIZE_BITS 29
diff --git a/arch/arm64/kvm/hyp/nvhe/page_alloc.c b/arch/arm64/kvm/hyp/nvhe/page_alloc.c
index b1e392186a0f..e691290d3765 100644
--- a/arch/arm64/kvm/hyp/nvhe/page_alloc.c
+++ b/arch/arm64/kvm/hyp/nvhe/page_alloc.c
@@ -228,7 +228,8 @@ int hyp_pool_init(struct hyp_pool *pool, u64 pfn, unsigned int nr_pages,
 	int i;
 
 	hyp_spin_lock_init(&pool->lock);
-	pool->max_order = min(MAX_ORDER, get_order(nr_pages << PAGE_SHIFT));
+	pool->max_order = min(MAX_PAGE_ORDER,
+			      get_order(nr_pages << PAGE_SHIFT));
 	for (i = 0; i <= pool->max_order; i++)
 		INIT_LIST_HEAD(&pool->free_area[i]);
 	pool->range_start = phys;
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index f5aae342632c..8116ac599f80 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -51,7 +51,7 @@ void __init arm64_hugetlb_cma_reserve(void)
 	 * page allocator. Just warn if there is any change
 	 * breaking this assumption.
 	 */
-	WARN_ON(order <= MAX_ORDER);
+	WARN_ON(order <= MAX_PAGE_ORDER);
 	hugetlb_cma_reserve(order);
 }
 #endif /* CONFIG_CMA */
diff --git a/arch/m68k/Kconfig.cpu b/arch/m68k/Kconfig.cpu
index ad69b466a08b..9dcf245c9cbf 100644
--- a/arch/m68k/Kconfig.cpu
+++ b/arch/m68k/Kconfig.cpu
@@ -402,7 +402,7 @@ config ARCH_FORCE_MAX_ORDER
 	default "10"
 	help
 	  The kernel page allocator limits the size of maximal physically
-	  contiguous allocations. The limit is called MAX_ORDER and it
+	  contiguous allocations. The limit is called MAX_PAGE_ORDER and it
 	  defines the maximal power of two of number of pages that can be
 	  allocated as a single contiguous block. This option allows
 	  overriding the default setting when ability to allocate very
diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig
index d54464021a61..58d9565dc2c7 100644
--- a/arch/nios2/Kconfig
+++ b/arch/nios2/Kconfig
@@ -50,7 +50,7 @@ config ARCH_FORCE_MAX_ORDER
 	default "10"
 	help
 	  The kernel page allocator limits the size of maximal physically
-	  contiguous allocations. The limit is called MAX_ORDER and it
+	  contiguous allocations. The limit is called MAX_PAGE_ORDER and it
 	  defines the maximal power of two of number of pages that can be
 	  allocated as a single contiguous block. This option allows
 	  overriding the default setting when ability to allocate very
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 1f11a62809f2..52d7e3fad553 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -915,7 +915,7 @@ config ARCH_FORCE_MAX_ORDER
 	default "10"
 	help
 	  The kernel page allocator limits the size of maximal physically
-	  contiguous allocations. The limit is called MAX_ORDER and it
+	  contiguous allocations. The limit is called MAX_PAGE_ORDER and it
 	  defines the maximal power of two of number of pages that can be
 	  allocated as a single contiguous block. This option allows
 	  overriding the default setting when ability to allocate very
diff --git a/arch/powerpc/mm/book3s64/iommu_api.c b/arch/powerpc/mm/book3s64/iommu_api.c
index d19fb1f3007d..c0e8d597e4cb 100644
--- a/arch/powerpc/mm/book3s64/iommu_api.c
+++ b/arch/powerpc/mm/book3s64/iommu_api.c
@@ -97,7 +97,7 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
 	}
 
 	mmap_read_lock(mm);
-	chunk = (1UL << (PAGE_SHIFT + MAX_ORDER)) /
+	chunk = (1UL << (PAGE_SHIFT + MAX_PAGE_ORDER)) /
 			sizeof(struct vm_area_struct *);
 	chunk = min(chunk, entries);
 	for (entry = 0; entry < entries; entry += chunk) {
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index f7c683b672c1..0a540b37aab6 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -615,7 +615,7 @@ void __init gigantic_hugetlb_cma_reserve(void)
 		order = mmu_psize_to_shift(MMU_PAGE_16G) - PAGE_SHIFT;
 
 	if (order) {
-		VM_WARN_ON(order <= MAX_ORDER);
+		VM_WARN_ON(order <= MAX_PAGE_ORDER);
 		hugetlb_cma_reserve(order);
 	}
 }
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 28fac4770073..23f5b5093ec1 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1389,7 +1389,7 @@ static long pnv_pci_ioda2_setup_default_config(struct pnv_ioda_pe *pe)
 	 * DMA window can be larger than available memory, which will
 	 * cause errors later.
 	 */
-	const u64 maxblock = 1UL << (PAGE_SHIFT + MAX_ORDER);
+	const u64 maxblock = 1UL << (PAGE_SHIFT + MAX_PAGE_ORDER);
 
 	/*
 	 * We create the default window as big as we can. The constraint is
diff --git a/arch/sh/mm/Kconfig b/arch/sh/mm/Kconfig
index 511c17aede4a..455311d9a5e9 100644
--- a/arch/sh/mm/Kconfig
+++ b/arch/sh/mm/Kconfig
@@ -26,7 +26,7 @@ config ARCH_FORCE_MAX_ORDER
 	default "10"
 	help
 	  The kernel page allocator limits the size of maximal physically
-	  contiguous allocations. The limit is called MAX_ORDER and it
+	  contiguous allocations. The limit is called MAX_PAGE:_ORDER and it
 	  defines the maximal power of two of number of pages that can be
 	  allocated as a single contiguous block. This option allows
 	  overriding the default setting when ability to allocate very
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 49849790e66d..204c43cb3d43 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -277,7 +277,7 @@ config ARCH_FORCE_MAX_ORDER
 	default "12"
 	help
 	  The kernel page allocator limits the size of maximal physically
-	  contiguous allocations. The limit is called MAX_ORDER and it
+	  contiguous allocations. The limit is called MAX_PAGE_ORDER and it
 	  defines the maximal power of two of number of pages that can be
 	  allocated as a single contiguous block. This option allows
 	  overriding the default setting when ability to allocate very
diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c
index c80b0a21d709..083e5f05a7f0 100644
--- a/arch/sparc/kernel/pci_sun4v.c
+++ b/arch/sparc/kernel/pci_sun4v.c
@@ -194,7 +194,7 @@ static void *dma_4v_alloc_coherent(struct device *dev, size_t size,
 
 	size = IO_PAGE_ALIGN(size);
 	order = get_order(size);
-	if (unlikely(order > MAX_ORDER))
+	if (unlikely(order > MAX_PAGE_ORDER))
 		return NULL;
 
 	npages = size >> IO_PAGE_SHIFT;
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index 5e2931a18409..6acd8a4c1e2a 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -402,8 +402,8 @@ void tsb_grow(struct mm_struct *mm, unsigned long tsb_index, unsigned long rss)
 	unsigned long new_rss_limit;
 	gfp_t gfp_flags;
 
-	if (max_tsb_size > PAGE_SIZE << MAX_ORDER)
-		max_tsb_size = PAGE_SIZE << MAX_ORDER;
+	if (max_tsb_size > PAGE_SIZE << MAX_PAGE_ORDER)
+		max_tsb_size = PAGE_SIZE << MAX_PAGE_ORDER;
 
 	new_cache_index = 0;
 	for (new_size = 8192; new_size < max_tsb_size; new_size <<= 1UL) {
diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index b1bfed0c8528..7a9820797eae 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -373,10 +373,10 @@ int __init linux_main(int argc, char **argv)
 	max_physmem = TASK_SIZE - uml_physmem - iomem_size - MIN_VMALLOC;
 
 	/*
-	 * Zones have to begin on a 1 << MAX_ORDER page boundary,
+	 * Zones have to begin on a 1 << MAX_PAGE_ORDER page boundary,
 	 * so this makes sure that's true for highmem
 	 */
-	max_physmem &= ~((1 << (PAGE_SHIFT + MAX_ORDER)) - 1);
+	max_physmem &= ~((1 << (PAGE_SHIFT + MAX_PAGE_ORDER)) - 1);
 	if (physmem_size + iomem_size > max_physmem) {
 		highmem = physmem_size + iomem_size - max_physmem;
 		physmem_size -= highmem;
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index 7d792077e5fd..e031eaf36c99 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -793,7 +793,7 @@ config ARCH_FORCE_MAX_ORDER
 	default "10"
 	help
 	  The kernel page allocator limits the size of maximal physically
-	  contiguous allocations. The limit is called MAX_ORDER and it
+	  contiguous allocations. The limit is called MAX_PAGE_ORDER and it
 	  defines the maximal power of two of number of pages that can be
 	  allocated as a single contiguous block. This option allows
 	  overriding the default setting when ability to allocate very
diff --git a/drivers/accel/qaic/qaic_data.c b/drivers/accel/qaic/qaic_data.c
index 4a8e43a7a6a4..aaeb2c9c071a 100644
--- a/drivers/accel/qaic/qaic_data.c
+++ b/drivers/accel/qaic/qaic_data.c
@@ -451,7 +451,7 @@ static int create_sgt(struct qaic_device *qdev, struct sg_table **sgt_out, u64 s
 		 * later
 		 */
 		buf_extra = (PAGE_SIZE - size % PAGE_SIZE) % PAGE_SIZE;
-		max_order = min(MAX_ORDER - 1, get_order(size));
+		max_order = min(MAX_PAGE_ORDER - 1, get_order(size));
 	} else {
 		/* allocate a single page for book keeping */
 		nr_pages = 1;
diff --git a/drivers/base/regmap/regmap-debugfs.c b/drivers/base/regmap/regmap-debugfs.c
index bdd80b73c3e6..fb84cda92a75 100644
--- a/drivers/base/regmap/regmap-debugfs.c
+++ b/drivers/base/regmap/regmap-debugfs.c
@@ -226,8 +226,8 @@ static ssize_t regmap_read_debugfs(struct regmap *map, unsigned int from,
 	if (*ppos < 0 || !count)
 		return -EINVAL;
 
-	if (count > (PAGE_SIZE << MAX_ORDER))
-		count = PAGE_SIZE << MAX_ORDER;
+	if (count > (PAGE_SIZE << MAX_PAGE_ORDER))
+		count = PAGE_SIZE << MAX_PAGE_ORDER;
 
 	buf = kmalloc(count, GFP_KERNEL);
 	if (!buf)
@@ -373,8 +373,8 @@ static ssize_t regmap_reg_ranges_read_file(struct file *file,
 	if (*ppos < 0 || !count)
 		return -EINVAL;
 
-	if (count > (PAGE_SIZE << MAX_ORDER))
-		count = PAGE_SIZE << MAX_ORDER;
+	if (count > (PAGE_SIZE << MAX_PAGE_ORDER))
+		count = PAGE_SIZE << MAX_PAGE_ORDER;
 
 	buf = kmalloc(count, GFP_KERNEL);
 	if (!buf)
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 11114a5d9e5c..d0e41d52d6a9 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -3079,7 +3079,7 @@ static void raw_cmd_free(struct floppy_raw_cmd **ptr)
 	}
 }
 
-#define MAX_LEN (1UL << MAX_ORDER << PAGE_SHIFT)
+#define MAX_LEN (1UL << MAX_PAGE_ORDER << PAGE_SHIFT)
 
 static int raw_cmd_copyin(int cmd, void __user *param,
 				 struct floppy_raw_cmd **rcmd)
diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c
index fcaccd0b5a65..e4d3f45242f6 100644
--- a/drivers/crypto/ccp/sev-dev.c
+++ b/drivers/crypto/ccp/sev-dev.c
@@ -906,7 +906,7 @@ static int sev_ioctl_do_get_id2(struct sev_issue_cmd *argp)
 		/*
 		 * The length of the ID shouldn't be assumed by software since
 		 * it may change in the future.  The allocation size is limited
-		 * to 1 << (PAGE_SHIFT + MAX_ORDER) by the page allocator.
+		 * to 1 << (PAGE_SHIFT + MAX_PAGE_ORDER) by the page allocator.
 		 * If the allocation fails, simply return ENOMEM rather than
 		 * warning in the kernel log.
 		 */
diff --git a/drivers/crypto/hisilicon/sgl.c b/drivers/crypto/hisilicon/sgl.c
index 3df7a256e919..5c1012d7ffa9 100644
--- a/drivers/crypto/hisilicon/sgl.c
+++ b/drivers/crypto/hisilicon/sgl.c
@@ -70,11 +70,11 @@ struct hisi_acc_sgl_pool *hisi_acc_create_sgl_pool(struct device *dev,
 			 HISI_ACC_SGL_ALIGN_SIZE);
 
 	/*
-	 * the pool may allocate a block of memory of size PAGE_SIZE * 2^MAX_ORDER,
+	 * the pool may allocate a block of memory of size PAGE_SIZE * 2^MAX_PAGE_ORDER,
 	 * block size may exceed 2^31 on ia64, so the max of block size is 2^31
 	 */
-	block_size = 1 << (PAGE_SHIFT + MAX_ORDER < 32 ?
-			   PAGE_SHIFT + MAX_ORDER : 31);
+	block_size = 1 << (PAGE_SHIFT + MAX_PAGE_ORDER < 32 ?
+			   PAGE_SHIFT + MAX_PAGE_ORDER : 31);
 	sgl_num_per_block = block_size / sgl_size;
 	block_num = count / sgl_num_per_block;
 	remain_sgl = count % sgl_num_per_block;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_internal.c b/drivers/gpu/drm/i915/gem/i915_gem_internal.c
index 6bc26b4b06b8..ea7561ae6e13 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_internal.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_internal.c
@@ -36,7 +36,7 @@ static int i915_gem_object_get_pages_internal(struct drm_i915_gem_object *obj)
 	struct sg_table *st;
 	struct scatterlist *sg;
 	unsigned int npages; /* restricted by sg_alloc_table */
-	int max_order = MAX_ORDER;
+	int max_order = MAX_PAGE_ORDER;
 	unsigned int max_segment;
 	gfp_t gfp;
 
diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
index 6b9f6cf50bf6..84c50c4c4af7 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
@@ -115,7 +115,7 @@ static int get_huge_pages(struct drm_i915_gem_object *obj)
 		do {
 			struct page *page;
 
-			GEM_BUG_ON(order > MAX_ORDER);
+			GEM_BUG_ON(order > MAX_PAGE_ORDER);
 			page = alloc_pages(GFP | __GFP_ZERO, order);
 			if (!page)
 				goto err;
diff --git a/drivers/gpu/drm/ttm/tests/ttm_pool_test.c b/drivers/gpu/drm/ttm/tests/ttm_pool_test.c
index 2d9cae8cd984..cceaa18d4e46 100644
--- a/drivers/gpu/drm/ttm/tests/ttm_pool_test.c
+++ b/drivers/gpu/drm/ttm/tests/ttm_pool_test.c
@@ -109,7 +109,7 @@ static const struct ttm_pool_test_case ttm_pool_basic_cases[] = {
 	},
 	{
 		.description = "Above the allocation limit",
-		.order = MAX_ORDER + 1,
+		.order = MAX_PAGE_ORDER + 1,
 	},
 	{
 		.description = "One page, with coherent DMA mappings enabled",
@@ -118,7 +118,7 @@ static const struct ttm_pool_test_case ttm_pool_basic_cases[] = {
 	},
 	{
 		.description = "Above the allocation limit, with coherent DMA mappings enabled",
-		.order = MAX_ORDER + 1,
+		.order = MAX_PAGE_ORDER + 1,
 		.use_dma_alloc = true,
 	},
 };
@@ -165,7 +165,7 @@ static void ttm_pool_alloc_basic(struct kunit *test)
 	fst_page = tt->pages[0];
 	last_page = tt->pages[tt->num_pages - 1];
 
-	if (params->order <= MAX_ORDER) {
+	if (params->order <= MAX_PAGE_ORDER) {
 		if (params->use_dma_alloc) {
 			KUNIT_ASSERT_NOT_NULL(test, (void *)fst_page->private);
 			KUNIT_ASSERT_NOT_NULL(test, (void *)last_page->private);
@@ -182,7 +182,7 @@ static void ttm_pool_alloc_basic(struct kunit *test)
 			 * order 0 blocks
 			 */
 			KUNIT_ASSERT_EQ(test, fst_page->private,
-					min_t(unsigned int, MAX_ORDER,
+					min_t(unsigned int, MAX_PAGE_ORDER,
 					      params->order));
 			KUNIT_ASSERT_EQ(test, last_page->private, 0);
 		}
diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c
index d183bb97c526..b62f420a9f96 100644
--- a/drivers/gpu/drm/ttm/ttm_pool.c
+++ b/drivers/gpu/drm/ttm/ttm_pool.c
@@ -447,7 +447,7 @@ int ttm_pool_alloc(struct ttm_pool *pool, struct ttm_tt *tt,
 	else
 		gfp_flags |= GFP_HIGHUSER;
 
-	for (order = min_t(unsigned int, MAX_ORDER, __fls(num_pages));
+	for (order = min_t(unsigned int, MAX_PAGE_ORDER, __fls(num_pages));
 	     num_pages;
 	     order = min_t(unsigned int, order, __fls(num_pages))) {
 		struct ttm_pool_type *pt;
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
index 961205ba86d2..925ac6a47bce 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -188,7 +188,7 @@
 #ifdef CONFIG_CMA_ALIGNMENT
 #define Q_MAX_SZ_SHIFT			(PAGE_SHIFT + CONFIG_CMA_ALIGNMENT)
 #else
-#define Q_MAX_SZ_SHIFT			(PAGE_SHIFT + MAX_ORDER)
+#define Q_MAX_SZ_SHIFT			(PAGE_SHIFT + MAX_PAGE_ORDER)
 #endif
 
 /*
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 85163a83df2f..e59f50e11ea8 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -884,7 +884,7 @@ static struct page **__iommu_dma_alloc_pages(struct device *dev,
 	struct page **pages;
 	unsigned int i = 0, nid = dev_to_node(dev);
 
-	order_mask &= GENMASK(MAX_ORDER, 0);
+	order_mask &= GENMASK(MAX_PAGE_ORDER, 0);
 	if (!order_mask)
 		return NULL;
 
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 9a7a74239eab..d097001c1e3e 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -2465,8 +2465,8 @@ static bool its_parse_indirect_baser(struct its_node *its,
 	 * feature is not supported by hardware.
 	 */
 	new_order = max_t(u32, get_order(esz << ids), new_order);
-	if (new_order > MAX_ORDER) {
-		new_order = MAX_ORDER;
+	if (new_order > MAX_PAGE_ORDER) {
+		new_order = MAX_PAGE_ORDER;
 		ids = ilog2(PAGE_ORDER_TO_SIZE(new_order) / (int)esz);
 		pr_warn("ITS@%pa: %s Table too large, reduce ids %llu->%u\n",
 			&its->phys_base, its_base_type_string[type],
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index f03d7dba270c..13c65b7e1ed6 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -1170,7 +1170,7 @@ static void __cache_size_refresh(void)
  * If the allocation may fail we use __get_free_pages. Memory fragmentation
  * won't have a fatal effect here, but it just causes flushes of some other
  * buffers and more I/O will be performed. Don't use __get_free_pages if it
- * always fails (i.e. order > MAX_ORDER).
+ * always fails (i.e. order > MAX_PAGE_ORDER).
  *
  * If the allocation shouldn't fail we use __vmalloc. This is only for the
  * initial reserve allocation, so there's no risk of wasting all vmalloc
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 2ae8560b6a14..855b482cbff1 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1673,7 +1673,7 @@ static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned int size)
 	unsigned int nr_iovecs = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	gfp_t gfp_mask = GFP_NOWAIT | __GFP_HIGHMEM;
 	unsigned int remaining_size;
-	unsigned int order = MAX_ORDER;
+	unsigned int order = MAX_PAGE_ORDER;
 
 retry:
 	if (unlikely(gfp_mask & __GFP_DIRECT_RECLAIM))
diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c
index f57fb821528d..7916ed9f10e8 100644
--- a/drivers/md/dm-flakey.c
+++ b/drivers/md/dm-flakey.c
@@ -434,7 +434,7 @@ static struct bio *clone_bio(struct dm_target *ti, struct flakey_c *fc, struct b
 
 	remaining_size = size;
 
-	order = MAX_ORDER;
+	order = MAX_PAGE_ORDER;
 	while (remaining_size) {
 		struct page *pages;
 		unsigned size_to_add, to_copy;
diff --git a/drivers/misc/genwqe/card_dev.c b/drivers/misc/genwqe/card_dev.c
index 55fc5b80e649..4441aca2280a 100644
--- a/drivers/misc/genwqe/card_dev.c
+++ b/drivers/misc/genwqe/card_dev.c
@@ -443,7 +443,7 @@ static int genwqe_mmap(struct file *filp, struct vm_area_struct *vma)
 	if (vsize == 0)
 		return -EINVAL;
 
-	if (get_order(vsize) > MAX_ORDER)
+	if (get_order(vsize) > MAX_PAGE_ORDER)
 		return -ENOMEM;
 
 	dma_map = kzalloc(sizeof(struct dma_mapping), GFP_KERNEL);
diff --git a/drivers/misc/genwqe/card_utils.c b/drivers/misc/genwqe/card_utils.c
index 1c798d6b2dfb..a2c4a9b4f871 100644
--- a/drivers/misc/genwqe/card_utils.c
+++ b/drivers/misc/genwqe/card_utils.c
@@ -210,7 +210,7 @@ u32 genwqe_crc32(u8 *buff, size_t len, u32 init)
 void *__genwqe_alloc_consistent(struct genwqe_dev *cd, size_t size,
 			       dma_addr_t *dma_handle)
 {
-	if (get_order(size) > MAX_ORDER)
+	if (get_order(size) > MAX_PAGE_ORDER)
 		return NULL;
 
 	return dma_alloc_coherent(&cd->pci_dev->dev, size, dma_handle,
@@ -308,7 +308,7 @@ int genwqe_alloc_sync_sgl(struct genwqe_dev *cd, struct genwqe_sgl *sgl,
 	sgl->write = write;
 	sgl->sgl_size = genwqe_sgl_size(sgl->nr_pages);
 
-	if (get_order(sgl->sgl_size) > MAX_ORDER) {
+	if (get_order(sgl->sgl_size) > MAX_PAGE_ORDER) {
 		dev_err(&pci_dev->dev,
 			"[%s] err: too much memory requested!\n", __func__);
 		return ret;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index b618797a7e8d..f1695c889d3a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -1041,7 +1041,7 @@ static void hns3_init_tx_spare_buffer(struct hns3_enet_ring *ring)
 		return;
 
 	order = get_order(alloc_size);
-	if (order > MAX_ORDER) {
+	if (order > MAX_PAGE_ORDER) {
 		if (net_ratelimit())
 			dev_warn(ring_to_dev(ring), "failed to allocate tx spare buffer, exceed to max order\n");
 		return;
diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h
index 4e18b4cefa97..94ac36b1408b 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.h
+++ b/drivers/net/ethernet/ibm/ibmvnic.h
@@ -48,7 +48,7 @@
  * of 4096 jumbo frames (MTU=9000) we will need about 9K*4K = 36MB plus
  * some padding.
  *
- * But the size of a single DMA region is limited by MAX_ORDER in the
+ * But the size of a single DMA region is limited by MAX_PAGE_ORDER in the
  * kernel (about 16MB currently).  To support say 4K Jumbo frames, we
  * use a set of LTBs (struct ltb_set) per pool.
  *
@@ -75,7 +75,7 @@
  * pool for the 4MB. Thus the 16 Rx and Tx queues require 32 * 5 = 160
  * plus 16 for the TSO pools for a total of 176 LTB mappings per VNIC.
  */
-#define IBMVNIC_ONE_LTB_MAX	((u32)((1 << MAX_ORDER) * PAGE_SIZE))
+#define IBMVNIC_ONE_LTB_MAX	((u32)((1 << MAX_PAGE_ORDER) * PAGE_SIZE))
 #define IBMVNIC_ONE_LTB_SIZE	min((u32)(8 << 20), IBMVNIC_ONE_LTB_MAX)
 #define IBMVNIC_LTB_SET_SIZE	(38 << 20)
 
diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c
index a80939fe2ee6..6a29d2594b91 100644
--- a/drivers/video/fbdev/hyperv_fb.c
+++ b/drivers/video/fbdev/hyperv_fb.c
@@ -927,8 +927,8 @@ static phys_addr_t hvfb_get_phymem(struct hv_device *hdev,
 	if (request_size == 0)
 		return -1;
 
-	if (order <= MAX_ORDER) {
-		/* Call alloc_pages if the size is less than 2^MAX_ORDER */
+	if (order <= MAX_PAGE_ORDER) {
+		/* Call alloc_pages if the size is less than 2^MAX_PAGE_ORDER */
 		page = alloc_pages(GFP_KERNEL | __GFP_ZERO, order);
 		if (!page)
 			return -1;
@@ -958,7 +958,7 @@ static void hvfb_release_phymem(struct hv_device *hdev,
 {
 	unsigned int order = get_order(size);
 
-	if (order <= MAX_ORDER)
+	if (order <= MAX_PAGE_ORDER)
 		__free_pages(pfn_to_page(paddr >> PAGE_SHIFT), order);
 	else
 		dma_free_coherent(&hdev->device,
diff --git a/drivers/video/fbdev/vermilion/vermilion.c b/drivers/video/fbdev/vermilion/vermilion.c
index 840ead69654b..a32e5b2924c9 100644
--- a/drivers/video/fbdev/vermilion/vermilion.c
+++ b/drivers/video/fbdev/vermilion/vermilion.c
@@ -197,7 +197,7 @@ static int vmlfb_alloc_vram(struct vml_info *vinfo,
 		va = &vinfo->vram[i];
 		order = 0;
 
-		while (requested > (PAGE_SIZE << order) && order <= MAX_ORDER)
+		while (requested > (PAGE_SIZE << order) && order <= MAX_PAGE_ORDER)
 			order++;
 
 		err = vmlfb_alloc_vram_area(va, order, 0);
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 1fe93e93f5bc..59cdc0292dce 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -33,7 +33,7 @@
 #define VIRTIO_BALLOON_FREE_PAGE_ALLOC_FLAG (__GFP_NORETRY | __GFP_NOWARN | \
 					     __GFP_NOMEMALLOC)
 /* The order of free page blocks to report to host */
-#define VIRTIO_BALLOON_HINT_BLOCK_ORDER MAX_ORDER
+#define VIRTIO_BALLOON_HINT_BLOCK_ORDER MAX_PAGE_ORDER
 /* The size of a free page block in bytes */
 #define VIRTIO_BALLOON_HINT_BLOCK_BYTES \
 	(1 << (VIRTIO_BALLOON_HINT_BLOCK_ORDER + PAGE_SHIFT))
diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c
index fa5226c198cc..8e3223294442 100644
--- a/drivers/virtio/virtio_mem.c
+++ b/drivers/virtio/virtio_mem.c
@@ -1154,13 +1154,13 @@ static void virtio_mem_clear_fake_offline(unsigned long pfn,
  */
 static void virtio_mem_fake_online(unsigned long pfn, unsigned long nr_pages)
 {
-	unsigned long order = MAX_ORDER;
+	unsigned long order = MAX_PAGE_ORDER;
 	unsigned long i;
 
 	/*
 	 * We might get called for ranges that don't cover properly aligned
-	 * MAX_ORDER pages; however, we can only online properly aligned
-	 * pages with an order of MAX_ORDER at maximum.
+	 * MAX_PAGE_ORDER pages; however, we can only online properly aligned
+	 * pages with an order of MAX_PAGE_ORDER at maximum.
 	 */
 	while (!IS_ALIGNED(pfn | nr_pages, 1 << order))
 		order--;
@@ -1280,7 +1280,7 @@ static void virtio_mem_online_page(struct virtio_mem *vm,
 	bool do_online;
 
 	/*
-	 * We can get called with any order up to MAX_ORDER. If our subblock
+	 * We can get called with any order up to MAX_PAGE_ORDER. If our subblock
 	 * size is smaller than that and we have a mixture of plugged and
 	 * unplugged subblocks within such a page, we have to process in
 	 * smaller granularity. In that case we'll adjust the order exactly once
diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c
index efb1b4c1a0a4..7a6d980e614d 100644
--- a/fs/ramfs/file-nommu.c
+++ b/fs/ramfs/file-nommu.c
@@ -70,7 +70,7 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize)
 
 	/* make various checks */
 	order = get_order(newsize);
-	if (unlikely(order > MAX_ORDER))
+	if (unlikely(order > MAX_PAGE_ORDER))
 		return -EFBIG;
 
 	ret = inode_newsize_ok(inode, newsize);
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 236ec7b63c54..c1ee640d87b1 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -829,7 +829,7 @@ static inline unsigned huge_page_shift(struct hstate *h)
 
 static inline bool hstate_is_gigantic(struct hstate *h)
 {
-	return huge_page_order(h) > MAX_ORDER;
+	return huge_page_order(h) > MAX_PAGE_ORDER;
 }
 
 static inline unsigned int pages_per_huge_page(const struct hstate *h)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 1ea7636dfb76..4ed33b127821 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -27,15 +27,15 @@
 
 /* Free memory management - zoned buddy allocator.  */
 #ifndef CONFIG_ARCH_FORCE_MAX_ORDER
-#define MAX_ORDER 10
+#define MAX_PAGE_ORDER 10
 #else
-#define MAX_ORDER CONFIG_ARCH_FORCE_MAX_ORDER
+#define MAX_PAGE_ORDER CONFIG_ARCH_FORCE_MAX_ORDER
 #endif
-#define MAX_ORDER_NR_PAGES (1 << MAX_ORDER)
+#define MAX_ORDER_NR_PAGES (1 << MAX_PAGE_ORDER)
 
 #define IS_MAX_ORDER_ALIGNED(pfn) IS_ALIGNED(pfn, MAX_ORDER_NR_PAGES)
 
-#define NR_PAGE_ORDERS (MAX_ORDER + 1)
+#define NR_PAGE_ORDERS (MAX_PAGE_ORDER + 1)
 
 /*
  * PAGE_ALLOC_COSTLY_ORDER is the order at which allocations are deemed
@@ -938,7 +938,7 @@ struct zone {
 	struct free_area	free_area[NR_PAGE_ORDERS];
 
 #ifdef CONFIG_UNACCEPTED_MEMORY
-	/* Pages to be accepted. All pages on the list are MAX_ORDER */
+	/* Pages to be accepted. All pages on the list are MAX_PAGE_ORDER */
 	struct list_head	unaccepted_pages;
 #endif
 
@@ -1748,8 +1748,8 @@ static inline bool movable_only_nodes(nodemask_t *nodes)
 #define SECTION_BLOCKFLAGS_BITS \
 	((1UL << (PFN_SECTION_SHIFT - pageblock_order)) * NR_PAGEBLOCK_BITS)
 
-#if (MAX_ORDER + PAGE_SHIFT) > SECTION_SIZE_BITS
-#error Allocator MAX_ORDER exceeds SECTION_SIZE
+#if (MAX_PAGE_ORDER + PAGE_SHIFT) > SECTION_SIZE_BITS
+#error Allocator MAX_PAGE_ORDER exceeds SECTION_SIZE
 #endif
 
 static inline unsigned long pfn_to_section_nr(unsigned long pfn)
diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h
index e83c4c095041..3f2409b968ec 100644
--- a/include/linux/pageblock-flags.h
+++ b/include/linux/pageblock-flags.h
@@ -41,14 +41,14 @@ extern unsigned int pageblock_order;
  * Huge pages are a constant size, but don't exceed the maximum allocation
  * granularity.
  */
-#define pageblock_order		min_t(unsigned int, HUGETLB_PAGE_ORDER, MAX_ORDER)
+#define pageblock_order		min_t(unsigned int, HUGETLB_PAGE_ORDER, MAX_PAGE_ORDER)
 
 #endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */
 
 #else /* CONFIG_HUGETLB_PAGE */
 
 /* If huge pages are not used, group by MAX_ORDER_NR_PAGES */
-#define pageblock_order		MAX_ORDER
+#define pageblock_order		MAX_PAGE_ORDER
 
 #endif /* CONFIG_HUGETLB_PAGE */
 
diff --git a/include/linux/slab.h b/include/linux/slab.h
index d6d6ffeeb9a2..d63823e518c0 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -308,7 +308,7 @@ static inline unsigned int arch_slab_minalign(void)
  * (PAGE_SIZE*2).  Larger requests are passed to the page allocator.
  */
 #define KMALLOC_SHIFT_HIGH	(PAGE_SHIFT + 1)
-#define KMALLOC_SHIFT_MAX	(MAX_ORDER + PAGE_SHIFT)
+#define KMALLOC_SHIFT_MAX	(MAX_PAGE_ORDER + PAGE_SHIFT)
 #ifndef KMALLOC_SHIFT_LOW
 #define KMALLOC_SHIFT_LOW	5
 #endif
@@ -316,7 +316,7 @@ static inline unsigned int arch_slab_minalign(void)
 
 #ifdef CONFIG_SLUB
 #define KMALLOC_SHIFT_HIGH	(PAGE_SHIFT + 1)
-#define KMALLOC_SHIFT_MAX	(MAX_ORDER + PAGE_SHIFT)
+#define KMALLOC_SHIFT_MAX	(MAX_PAGE_ORDER + PAGE_SHIFT)
 #ifndef KMALLOC_SHIFT_LOW
 #define KMALLOC_SHIFT_LOW	3
 #endif
diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c
index b481c48a31a6..d10613eb0f63 100644
--- a/kernel/dma/pool.c
+++ b/kernel/dma/pool.c
@@ -84,8 +84,8 @@ static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size,
 	void *addr;
 	int ret = -ENOMEM;
 
-	/* Cannot allocate larger than MAX_ORDER */
-	order = min(get_order(pool_size), MAX_ORDER);
+	/* Cannot allocate larger than MAX_PAGE_ORDER */
+	order = min(get_order(pool_size), MAX_PAGE_ORDER);
 
 	do {
 		pool_size = 1 << (PAGE_SHIFT + order);
@@ -190,7 +190,7 @@ static int __init dma_atomic_pool_init(void)
 
 	/*
 	 * If coherent_pool was not used on the command line, default the pool
-	 * sizes to 128KB per 1GB of memory, min 128KB, max MAX_ORDER.
+	 * sizes to 128KB per 1GB of memory, min 128KB, max MAX_PAGE_ORDER.
 	 */
 	if (!atomic_pool_size) {
 		unsigned long pages = totalram_pages() / (SZ_1G / SZ_128K);
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 33d942615be5..176078bf2215 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -686,8 +686,8 @@ static struct io_tlb_pool *swiotlb_alloc_pool(struct device *dev,
 	size_t pool_size;
 	size_t tlb_size;
 
-	if (nslabs > SLABS_PER_PAGE << MAX_ORDER) {
-		nslabs = SLABS_PER_PAGE << MAX_ORDER;
+	if (nslabs > SLABS_PER_PAGE << MAX_PAGE_ORDER) {
+		nslabs = SLABS_PER_PAGE << MAX_PAGE_ORDER;
 		nareas = limit_nareas(nareas, nslabs);
 	}
 
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index e8d82c2f07d0..60ed43d1c29e 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -610,8 +610,8 @@ static struct page *rb_alloc_aux_page(int node, int order)
 {
 	struct page *page;
 
-	if (order > MAX_ORDER)
-		order = MAX_ORDER;
+	if (order > MAX_PAGE_ORDER)
+		order = MAX_PAGE_ORDER;
 
 	do {
 		page = alloc_pages_node(node, PERF_AUX_GFP, order);
@@ -702,9 +702,9 @@ int rb_alloc_aux(struct perf_buffer *rb, struct perf_event *event,
 
 	/*
 	 * kcalloc_node() is unable to allocate buffer if the size is larger
-	 * than: PAGE_SIZE << MAX_ORDER; directly bail out in this case.
+	 * than: PAGE_SIZE << MAX_PAGE_ORDER; directly bail out in this case.
 	 */
-	if (get_order((unsigned long)nr_pages * sizeof(void *)) > MAX_ORDER)
+	if (get_order((unsigned long)nr_pages * sizeof(void *)) > MAX_PAGE_ORDER)
 		return -ENOMEM;
 	rb->aux_pages = kcalloc_node(nr_pages, sizeof(void *), GFP_KERNEL,
 				     node);
@@ -821,7 +821,7 @@ struct perf_buffer *rb_alloc(int nr_pages, long watermark, int cpu, int flags)
 	size = sizeof(struct perf_buffer);
 	size += nr_pages * sizeof(void *);
 
-	if (order_base_2(size) > PAGE_SHIFT+MAX_ORDER)
+	if (order_base_2(size) > PAGE_SHIFT+MAX_PAGE_ORDER)
 		goto fail;
 
 	node = (cpu == -1) ? cpu : cpu_to_node(cpu);
diff --git a/mm/Kconfig b/mm/Kconfig
index 79d563d8f9e0..cb9d470f0bf7 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -381,7 +381,7 @@ config SHUFFLE_PAGE_ALLOCATOR
 	  the presence of a memory-side-cache. There are also incidental
 	  security benefits as it reduces the predictability of page
 	  allocations to compliment SLAB_FREELIST_RANDOM, but the
-	  default granularity of shuffling on the MAX_ORDER i.e, 10th
+	  default granularity of shuffling on the MAX_PAGE_ORDER i.e, 10th
 	  order of pages is selected based on cache utilization benefits
 	  on x86.
 
@@ -713,8 +713,8 @@ config HUGETLB_PAGE_SIZE_VARIABLE
 	  HUGETLB_PAGE_ORDER when there are multiple HugeTLB page sizes available
 	  on a platform.
 
-	  Note that the pageblock_order cannot exceed MAX_ORDER and will be
-	  clamped down to MAX_ORDER.
+	  Note that the pageblock_order cannot exceed MAX_PAGE_ORDER and will be
+	  clamped down to MAX_PAGE_ORDER.
 
 config CONTIG_ALLOC
 	def_bool (MEMORY_ISOLATION && COMPACTION) || CMA
diff --git a/mm/compaction.c b/mm/compaction.c
index 24f8eb4d6260..27ada42924d5 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -999,7 +999,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 			 * a valid page order. Consider only values in the
 			 * valid order range to prevent low_pfn overflow.
 			 */
-			if (freepage_order > 0 && freepage_order <= MAX_ORDER) {
+			if (freepage_order > 0 && freepage_order <= MAX_PAGE_ORDER) {
 				low_pfn += (1UL << freepage_order) - 1;
 				nr_scanned += (1UL << freepage_order) - 1;
 			}
@@ -1017,7 +1017,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		if (PageCompound(page) && !cc->alloc_contig) {
 			const unsigned int order = compound_order(page);
 
-			if (likely(order <= MAX_ORDER)) {
+			if (likely(order <= MAX_PAGE_ORDER)) {
 				low_pfn += (1UL << order) - 1;
 				nr_scanned += (1UL << order) - 1;
 			}
diff --git a/mm/debug_page_alloc.c b/mm/debug_page_alloc.c
index f9d145730fd1..6755f0c9d4a3 100644
--- a/mm/debug_page_alloc.c
+++ b/mm/debug_page_alloc.c
@@ -22,7 +22,7 @@ static int __init debug_guardpage_minorder_setup(char *buf)
 {
 	unsigned long res;
 
-	if (kstrtoul(buf, 10, &res) < 0 ||  res > MAX_ORDER / 2) {
+	if (kstrtoul(buf, 10, &res) < 0 ||  res > MAX_PAGE_ORDER / 2) {
 		pr_err("Bad debug_guardpage_minorder value\n");
 		return 0;
 	}
diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c
index e651500e597a..5662e29fe253 100644
--- a/mm/debug_vm_pgtable.c
+++ b/mm/debug_vm_pgtable.c
@@ -1091,7 +1091,7 @@ debug_vm_pgtable_alloc_huge_page(struct pgtable_debug_args *args, int order)
 	struct page *page = NULL;
 
 #ifdef CONFIG_CONTIG_ALLOC
-	if (order > MAX_ORDER) {
+	if (order > MAX_PAGE_ORDER) {
 		page = alloc_contig_pages((1 << order), GFP_KERNEL,
 					  first_online_node, NULL);
 		if (page) {
@@ -1101,7 +1101,7 @@ debug_vm_pgtable_alloc_huge_page(struct pgtable_debug_args *args, int order)
 	}
 #endif
 
-	if (order <= MAX_ORDER)
+	if (order <= MAX_PAGE_ORDER)
 		page = alloc_pages(GFP_KERNEL, order);
 
 	return page;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 1a588e29d287..b9a7a57691d7 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -682,7 +682,7 @@ static int __init hugepage_init(void)
 	/*
 	 * hugepages can't be allocated by the buddy allocator
 	 */
-	MAYBE_BUILD_BUG_ON(HPAGE_PMD_ORDER > MAX_ORDER);
+	MAYBE_BUILD_BUG_ON(HPAGE_PMD_ORDER > MAX_PAGE_ORDER);
 	/*
 	 * we use page->mapping and page->index in second tail page
 	 * as list_head: assuming THP order >= 2
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 378e460a6ab4..0d262784ce60 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3410,7 +3410,7 @@ static void __init prep_and_add_bootmem_folios(struct hstate *h,
 
 /*
  * Put bootmem huge pages into the standard lists after mem_map is up.
- * Note: This only applies to gigantic (order > MAX_ORDER) pages.
+ * Note: This only applies to gigantic (order > MAX_PAGE_ORDER) pages.
  */
 static void __init gather_bootmem_prealloc(void)
 {
@@ -4790,7 +4790,7 @@ static int __init default_hugepagesz_setup(char *s)
 	 * The number of default huge pages (for this size) could have been
 	 * specified as the first hugetlb parameter: hugepages=X.  If so,
 	 * then default_hstate_max_huge_pages is set.  If the default huge
-	 * page size is gigantic (> MAX_ORDER), then the pages must be
+	 * page size is gigantic (> MAX_PAGE_ORDER), then the pages must be
 	 * allocated here from bootmem allocator.
 	 */
 	if (default_hstate_max_huge_pages) {
diff --git a/mm/internal.h b/mm/internal.h
index ac40c3d00336..f309a010d50f 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -335,7 +335,7 @@ static inline bool page_is_buddy(struct page *page, struct page *buddy,
  * satisfies the following equation:
  *     P = B & ~(1 << O)
  *
- * Assumption: *_mem_map is contiguous at least up to MAX_ORDER
+ * Assumption: *_mem_map is contiguous at least up to MAX_PAGE_ORDER
  */
 static inline unsigned long
 __find_buddy_pfn(unsigned long page_pfn, unsigned int order)
diff --git a/mm/kmsan/init.c b/mm/kmsan/init.c
index 103e2e88ea03..3ac3b8921d36 100644
--- a/mm/kmsan/init.c
+++ b/mm/kmsan/init.c
@@ -141,7 +141,7 @@ struct smallstack {
 
 static struct smallstack collect = {
 	.index = 0,
-	.order = MAX_ORDER,
+	.order = MAX_PAGE_ORDER,
 };
 
 static void smallstack_push(struct smallstack *stack, struct page *pages)
@@ -211,8 +211,8 @@ static void kmsan_memblock_discard(void)
 	 *    order=N-1,
 	 *  - repeat.
 	 */
-	collect.order = MAX_ORDER;
-	for (int i = MAX_ORDER; i >= 0; i--) {
+	collect.order = MAX_PAGE_ORDER;
+	for (int i = MAX_PAGE_ORDER; i >= 0; i--) {
 		if (held_back[i].shadow)
 			smallstack_push(&collect, held_back[i].shadow);
 		if (held_back[i].origin)
diff --git a/mm/memblock.c b/mm/memblock.c
index 4a62f7774b65..8c194d8afeec 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -2113,12 +2113,13 @@ static void __init __free_pages_memory(unsigned long start, unsigned long end)
 		 * Free the pages in the largest chunks alignment allows.
 		 *
 		 * __ffs() behaviour is undefined for 0. start == 0 is
-		 * MAX_ORDER-aligned, set order to MAX_ORDER for the case.
+		 * MAX_PAGE_ORDER-aligned, set order to MAX_PAGE_ORDER for
+		 * the case.
 		 */
 		if (start)
-			order = min_t(int, MAX_ORDER, __ffs(start));
+			order = min_t(int, MAX_PAGE_ORDER, __ffs(start));
 		else
-			order = MAX_ORDER;
+			order = MAX_PAGE_ORDER;
 
 		while (start + (1UL << order) > end)
 			order--;
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 926e1cfb10e9..b3c0ff52bb72 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -645,7 +645,7 @@ static void online_pages_range(unsigned long start_pfn, unsigned long nr_pages)
 	unsigned long pfn;
 
 	/*
-	 * Online the pages in MAX_ORDER aligned chunks. The callback might
+	 * Online the pages in MAX_PAGE_ORDER aligned chunks. The callback might
 	 * decide to not expose all pages to the buddy (e.g., expose them
 	 * later). We account all pages as being online and belonging to this
 	 * zone ("present").
@@ -660,12 +660,13 @@ static void online_pages_range(unsigned long start_pfn, unsigned long nr_pages)
 		 * Free to online pages in the largest chunks alignment allows.
 		 *
 		 * __ffs() behaviour is undefined for 0. start == 0 is
-		 * MAX_ORDER-aligned, Set order to MAX_ORDER for the case.
+		 * MAX_PAGE_ORDER-aligned, Set order to MAX_PAGE_ORDER for
+		 * the case.
 		 */
 		if (pfn)
-			order = min_t(int, MAX_ORDER, __ffs(pfn));
+			order = min_t(int, MAX_PAGE_ORDER, __ffs(pfn));
 		else
-			order = MAX_ORDER;
+			order = MAX_PAGE_ORDER;
 
 		(*online_page_callback)(pfn_to_page(pfn), order);
 		pfn += (1UL << order);
diff --git a/mm/mm_init.c b/mm/mm_init.c
index 2830eef2b16c..89dc29f1e6c6 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -1455,7 +1455,7 @@ static inline void setup_usemap(struct zone *zone) {}
 /* Initialise the number of pages represented by NR_PAGEBLOCK_BITS */
 void __init set_pageblock_order(void)
 {
-	unsigned int order = MAX_ORDER;
+	unsigned int order = MAX_PAGE_ORDER;
 
 	/* Check that pageblock_nr_pages has not already been setup */
 	if (pageblock_order)
@@ -1638,7 +1638,7 @@ static void __init alloc_node_mem_map(struct pglist_data *pgdat)
 	start = pgdat->node_start_pfn & ~(MAX_ORDER_NR_PAGES - 1);
 	offset = pgdat->node_start_pfn - start;
 	/*
-	 * The zone's endpoints aren't required to be MAX_ORDER
+		 * The zone's endpoints aren't required to be MAX_PAGE_ORDER
 	 * aligned but the node_mem_map endpoints must be in order
 	 * for the buddy allocator to function correctly.
 	 */
@@ -1964,11 +1964,11 @@ static void __init deferred_free_range(unsigned long pfn,
 	if (nr_pages == MAX_ORDER_NR_PAGES && IS_MAX_ORDER_ALIGNED(pfn)) {
 		for (i = 0; i < nr_pages; i += pageblock_nr_pages)
 			set_pageblock_migratetype(page + i, MIGRATE_MOVABLE);
-		__free_pages_core(page, MAX_ORDER);
+		__free_pages_core(page, MAX_PAGE_ORDER);
 		return;
 	}
 
-	/* Accept chunks smaller than MAX_ORDER upfront */
+	/* Accept chunks smaller than MAX_PAGE_ORDER upfront */
 	accept_memory(PFN_PHYS(pfn), PFN_PHYS(pfn + nr_pages));
 
 	for (i = 0; i < nr_pages; i++, page++, pfn++) {
@@ -1991,8 +1991,8 @@ static inline void __init pgdat_init_report_one_done(void)
 /*
  * Returns true if page needs to be initialized or freed to buddy allocator.
  *
- * We check if a current MAX_ORDER block is valid by only checking the validity
- * of the head pfn.
+ * We check if a current MAX_PAGE_ORDER block is valid by only checking the
+ * validity of the head pfn.
  */
 static inline bool __init deferred_pfn_valid(unsigned long pfn)
 {
@@ -2149,8 +2149,8 @@ deferred_init_memmap_chunk(unsigned long start_pfn, unsigned long end_pfn,
 	deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn, start_pfn);
 
 	/*
-	 * Initialize and free pages in MAX_ORDER sized increments so that we
-	 * can avoid introducing any issues with the buddy allocator.
+	 * Initialize and free pages in MAX_PAGE_ORDER sized increments so that
+	 * we can avoid introducing any issues with the buddy allocator.
 	 */
 	while (spfn < end_pfn) {
 		deferred_init_maxorder(&i, zone, &spfn, &epfn);
@@ -2291,7 +2291,7 @@ bool __init deferred_grow_zone(struct zone *zone, unsigned int order)
 	}
 
 	/*
-	 * Initialize and free pages in MAX_ORDER sized increments so
+	 * Initialize and free pages in MAX_PAGE_ORDER sized increments so
 	 * that we can avoid introducing any issues with the buddy
 	 * allocator.
 	 */
@@ -2509,7 +2509,7 @@ void *__init alloc_large_system_hash(const char *tablename,
 			else
 				table = memblock_alloc_raw(size,
 							   SMP_CACHE_BYTES);
-		} else if (get_order(size) > MAX_ORDER || hashdist) {
+		} else if (get_order(size) > MAX_PAGE_ORDER || hashdist) {
 			table = vmalloc_huge(size, gfp_flags);
 			virt = true;
 			if (table)
@@ -2756,7 +2756,7 @@ void __init mm_core_init(void)
 
 	/*
 	 * page_ext requires contiguous pages,
-	 * bigger than MAX_ORDER unless SPARSEMEM.
+	 * bigger than MAX_PAGE_ORDER unless SPARSEMEM.
 	 */
 	page_ext_init_flatmem();
 	mem_debugging_and_hardening_init();
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ccecf6158ae4..a01baf0454f8 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -727,7 +727,7 @@ buddy_merge_likely(unsigned long pfn, unsigned long buddy_pfn,
 	unsigned long higher_page_pfn;
 	struct page *higher_page;
 
-	if (order >= MAX_ORDER - 1)
+	if (order >= MAX_PAGE_ORDER - 1)
 		return false;
 
 	higher_page_pfn = buddy_pfn & pfn;
@@ -782,7 +782,7 @@ static inline void __free_one_page(struct page *page,
 	VM_BUG_ON_PAGE(pfn & ((1 << order) - 1), page);
 	VM_BUG_ON_PAGE(bad_range(zone, page), page);
 
-	while (order < MAX_ORDER) {
+	while (order < MAX_PAGE_ORDER) {
 		if (compaction_capture(capc, page, order, migratetype)) {
 			__mod_zone_freepage_state(zone, -(1 << order),
 								migratetype);
@@ -1297,7 +1297,7 @@ void __free_pages_core(struct page *page, unsigned int order)
 	atomic_long_add(nr_pages, &page_zone(page)->managed_pages);
 
 	if (page_contains_unaccepted(page, order)) {
-		if (order == MAX_ORDER && __free_unaccepted(page))
+		if (order == MAX_PAGE_ORDER && __free_unaccepted(page))
 			return;
 
 		accept_page(page, order);
@@ -1327,7 +1327,7 @@ void __free_pages_core(struct page *page, unsigned int order)
  *
  * Note: the function may return non-NULL struct page even for a page block
  * which contains a memory hole (i.e. there is no physical memory for a subset
- * of the pfn range). For example, if the pageblock order is MAX_ORDER, which
+ * of the pfn range). For example, if the pageblock order is MAX_PAGE_ORDER, which
  * will fall into 2 sub-sections, and the end pfn of the pageblock may be hole
  * even though the start pfn is online and valid. This should be safe most of
  * the time because struct pages are still initialized via init_unavailable_range()
@@ -2018,7 +2018,7 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype,
 	 * approximates finding the pageblock with the most free pages, which
 	 * would be too costly to do exactly.
 	 */
-	for (current_order = MAX_ORDER; current_order >= min_order;
+	for (current_order = MAX_PAGE_ORDER; current_order >= min_order;
 				--current_order) {
 		area = &(zone->free_area[current_order]);
 		fallback_mt = find_suitable_fallback(area, current_order,
@@ -2056,7 +2056,7 @@ find_smallest:
 	 * This should not happen - we already found a suitable fallback
 	 * when looking for the largest page.
 	 */
-	VM_BUG_ON(current_order > MAX_ORDER);
+	VM_BUG_ON(current_order > MAX_PAGE_ORDER);
 
 do_steal:
 	page = get_page_from_free_area(area, fallback_mt);
@@ -4533,7 +4533,7 @@ struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid,
 	 * There are several places where we assume that the order value is sane
 	 * so bail out early if the request is out of bound.
 	 */
-	if (WARN_ON_ONCE_GFP(order > MAX_ORDER, gfp))
+	if (WARN_ON_ONCE_GFP(order > MAX_PAGE_ORDER, gfp))
 		return NULL;
 
 	gfp &= gfp_allowed_mask;
@@ -4815,7 +4815,7 @@ static void *make_alloc_exact(unsigned long addr, unsigned int order,
  * minimum number of pages to satisfy the request.  alloc_pages() can only
  * allocate memory in power-of-two pages.
  *
- * This function is also limited by MAX_ORDER.
+ * This function is also limited by MAX_PAGE_ORDER.
  *
  * Memory allocated by this function must be released by free_pages_exact().
  *
@@ -6373,7 +6373,7 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 	order = 0;
 	outer_start = start;
 	while (!PageBuddy(pfn_to_page(outer_start))) {
-		if (++order > MAX_ORDER) {
+		if (++order > MAX_PAGE_ORDER) {
 			outer_start = start;
 			break;
 		}
@@ -6635,7 +6635,7 @@ bool is_free_buddy_page(struct page *page)
 			break;
 	}
 
-	return order <= MAX_ORDER;
+	return order <= MAX_PAGE_ORDER;
 }
 EXPORT_SYMBOL(is_free_buddy_page);
 
@@ -6807,9 +6807,9 @@ static bool try_to_accept_memory_one(struct zone *zone)
 	__mod_zone_page_state(zone, NR_UNACCEPTED, -MAX_ORDER_NR_PAGES);
 	spin_unlock_irqrestore(&zone->lock, flags);
 
-	accept_page(page, MAX_ORDER);
+	accept_page(page, MAX_PAGE_ORDER);
 
-	__free_pages_ok(page, MAX_ORDER, FPI_TO_TAIL);
+	__free_pages_ok(page, MAX_PAGE_ORDER, FPI_TO_TAIL);
 
 	if (last)
 		static_branch_dec(&zones_with_unaccepted_pages);
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index bcf99ba747a0..cd0ea3668253 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -226,7 +226,7 @@ static void unset_migratetype_isolate(struct page *page, int migratetype)
 	 */
 	if (PageBuddy(page)) {
 		order = buddy_order(page);
-		if (order >= pageblock_order && order < MAX_ORDER) {
+		if (order >= pageblock_order && order < MAX_PAGE_ORDER) {
 			buddy = find_buddy_page_pfn(page, page_to_pfn(page),
 						    order, NULL);
 			if (buddy && !is_migrate_isolate_page(buddy)) {
@@ -290,11 +290,12 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages)
  *			isolate_single_pageblock()
  * @migratetype:	migrate type to set in error recovery.
  *
- * Free and in-use pages can be as big as MAX_ORDER and contain more than one
+ * Free and in-use pages can be as big as MAX_PAGE_ORDER and contain more than one
  * pageblock. When not all pageblocks within a page are isolated at the same
  * time, free page accounting can go wrong. For example, in the case of
- * MAX_ORDER = pageblock_order + 1, a MAX_ORDER page has two pagelbocks.
- * [         MAX_ORDER           ]
+ * MAX_PAGE_ORDER = pageblock_order + 1, a MAX_PAGE_ORDER page has two
+ * pagelbocks.
+ * [      MAX_PAGE_ORDER         ]
  * [  pageblock0  |  pageblock1  ]
  * When either pageblock is isolated, if it is a free page, the page is not
  * split into separate migratetype lists, which is supposed to; if it is an
@@ -451,7 +452,7 @@ static int isolate_single_pageblock(unsigned long boundary_pfn, int flags,
 				 * the free page to the right migratetype list.
 				 *
 				 * head_pfn is not used here as a hugetlb page order
-				 * can be bigger than MAX_ORDER, but after it is
+				 * can be bigger than MAX_PAGE_ORDER, but after it is
 				 * freed, the free page order is not. Use pfn within
 				 * the range to find the head of the free page.
 				 */
@@ -459,7 +460,7 @@ static int isolate_single_pageblock(unsigned long boundary_pfn, int flags,
 				outer_pfn = pfn;
 				while (!PageBuddy(pfn_to_page(outer_pfn))) {
 					/* stop if we cannot find the free page */
-					if (++order > MAX_ORDER)
+					if (++order > MAX_PAGE_ORDER)
 						goto failed;
 					outer_pfn &= ~0UL << order;
 				}
@@ -660,8 +661,8 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn,
 	int ret;
 
 	/*
-	 * Note: pageblock_nr_pages != MAX_ORDER. Then, chunks of free pages
-	 * are not aligned to pageblock_nr_pages.
+	 * Note: pageblock_nr_pages != MAX_PAGE_ORDER. Then, chunks of free
+	 * pages are not aligned to pageblock_nr_pages.
 	 * Then we just check migratetype first.
 	 */
 	for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) {
diff --git a/mm/page_owner.c b/mm/page_owner.c
index 040dbf26a986..5634e5d890f8 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -320,7 +320,7 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m,
 				unsigned long freepage_order;
 
 				freepage_order = buddy_order_unsafe(page);
-				if (freepage_order <= MAX_ORDER)
+				if (freepage_order <= MAX_PAGE_ORDER)
 					pfn += (1UL << freepage_order) - 1;
 				continue;
 			}
@@ -555,7 +555,7 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 		if (PageBuddy(page)) {
 			unsigned long freepage_order = buddy_order_unsafe(page);
 
-			if (freepage_order <= MAX_ORDER)
+			if (freepage_order <= MAX_PAGE_ORDER)
 				pfn += (1UL << freepage_order) - 1;
 			continue;
 		}
@@ -663,7 +663,7 @@ static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone)
 			if (PageBuddy(page)) {
 				unsigned long order = buddy_order_unsafe(page);
 
-				if (order > 0 && order <= MAX_ORDER)
+				if (order > 0 && order <= MAX_PAGE_ORDER)
 					pfn += (1UL << order) - 1;
 				continue;
 			}
diff --git a/mm/page_reporting.c b/mm/page_reporting.c
index 66369cc5279b..e4c428e61d8c 100644
--- a/mm/page_reporting.c
+++ b/mm/page_reporting.c
@@ -20,7 +20,7 @@ static int page_order_update_notify(const char *val, const struct kernel_param *
 	 * If param is set beyond this limit, order is set to default
 	 * pageblock_order value
 	 */
-	return  param_set_uint_minmax(val, kp, 0, MAX_ORDER);
+	return  param_set_uint_minmax(val, kp, 0, MAX_PAGE_ORDER);
 }
 
 static const struct kernel_param_ops page_reporting_param_ops = {
@@ -370,7 +370,7 @@ int page_reporting_register(struct page_reporting_dev_info *prdev)
 	 */
 
 	if (page_reporting_order == -1) {
-		if (prdev->order > 0 && prdev->order <= MAX_ORDER)
+		if (prdev->order > 0 && prdev->order <= MAX_PAGE_ORDER)
 			page_reporting_order = prdev->order;
 		else
 			page_reporting_order = pageblock_order;
diff --git a/mm/shuffle.h b/mm/shuffle.h
index a6bdf54f96f1..61bbcddeeee6 100644
--- a/mm/shuffle.h
+++ b/mm/shuffle.h
@@ -4,7 +4,7 @@
 #define _MM_SHUFFLE_H
 #include <linux/jump_label.h>
 
-#define SHUFFLE_ORDER MAX_ORDER
+#define SHUFFLE_ORDER MAX_PAGE_ORDER
 
 #ifdef CONFIG_SHUFFLE_PAGE_ALLOCATOR
 DECLARE_STATIC_KEY_FALSE(page_alloc_shuffle_key);
diff --git a/mm/slab.c b/mm/slab.c
index 773c79e153f3..073cae923d56 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -465,7 +465,7 @@ static int __init slab_max_order_setup(char *str)
 {
 	get_option(&str, &slab_max_order);
 	slab_max_order = slab_max_order < 0 ? 0 :
-				min(slab_max_order, MAX_ORDER);
+				min(slab_max_order, MAX_PAGE_ORDER);
 	slab_max_order_set = true;
 
 	return 1;
diff --git a/mm/slub.c b/mm/slub.c
index a5420be89c8c..ba162e661e2e 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -4194,7 +4194,7 @@ static inline int calculate_order(unsigned int size)
 	 * Doh this slab cannot be placed using slub_max_order.
 	 */
 	order = get_order(size);
-	if (order <= MAX_ORDER)
+	if (order <= MAX_PAGE_ORDER)
 		return order;
 	return -ENOSYS;
 }
@@ -4722,7 +4722,7 @@ __setup("slub_min_order=", setup_slub_min_order);
 static int __init setup_slub_max_order(char *str)
 {
 	get_option(&str, (int *)&slub_max_order);
-	slub_max_order = min_t(unsigned int, slub_max_order, MAX_ORDER);
+	slub_max_order = min_t(unsigned int, slub_max_order, MAX_PAGE_ORDER);
 
 	if (slub_min_order > slub_max_order)
 		slub_min_order = slub_max_order;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 600ed3cbf7cb..68f0abbb8e59 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -6415,7 +6415,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 	 * scan_control uses s8 fields for order, priority, and reclaim_idx.
 	 * Confirm they are large enough for max values.
 	 */
-	BUILD_BUG_ON(MAX_ORDER >= S8_MAX);
+	BUILD_BUG_ON(MAX_PAGE_ORDER >= S8_MAX);
 	BUILD_BUG_ON(DEF_PRIORITY > S8_MAX);
 	BUILD_BUG_ON(MAX_NR_ZONES > S8_MAX);
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 03ead31c46a0..db79935e4a54 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1092,7 +1092,7 @@ static int __fragmentation_index(unsigned int order, struct contig_page_info *in
 {
 	unsigned long requested = 1UL << order;
 
-	if (WARN_ON_ONCE(order > MAX_ORDER))
+	if (WARN_ON_ONCE(order > MAX_PAGE_ORDER))
 		return 0;
 
 	if (!info->free_blocks_total)
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index 89981dbe46c9..97704a9e84c7 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -844,7 +844,7 @@ long smc_ib_setup_per_ibdev(struct smc_ib_device *smcibdev)
 		goto out;
 	/* the calculated number of cq entries fits to mlx5 cq allocation */
 	cqe_size_order = cache_line_size() == 128 ? 7 : 6;
-	smc_order = MAX_ORDER - cqe_size_order;
+	smc_order = MAX_PAGE_ORDER - cqe_size_order;
 	if (SMC_MAX_CQE + 2 > (0x00000001 << smc_order) * PAGE_SIZE)
 		cqattr.cqe = (0x00000001 << smc_order) * PAGE_SIZE - 2;
 	smcibdev->roce_cq_send = ib_create_cq(smcibdev->ibdev,
diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c
index 51ad29940f05..f3738b2c8bcd 100644
--- a/security/integrity/ima/ima_crypto.c
+++ b/security/integrity/ima/ima_crypto.c
@@ -38,7 +38,7 @@ static int param_set_bufsize(const char *val, const struct kernel_param *kp)
 
 	size = memparse(val, NULL);
 	order = get_order(size);
-	if (order > MAX_ORDER)
+	if (order > MAX_PAGE_ORDER)
 		return -EINVAL;
 	ima_maxorder = order;
 	ima_bufsize = PAGE_SIZE << order;
diff --git a/tools/perf/Documentation/perf-intel-pt.txt b/tools/perf/Documentation/perf-intel-pt.txt
index 4c90cc176f81..2109690b0d5f 100644
--- a/tools/perf/Documentation/perf-intel-pt.txt
+++ b/tools/perf/Documentation/perf-intel-pt.txt
@@ -683,7 +683,7 @@ Buffer handling
 ~~~~~~~~~~~~~~~
 
 There may be buffer limitations (i.e. single ToPa entry) which means that actual
-buffer sizes are limited to powers of 2 up to 4MiB (MAX_ORDER).  In order to
+buffer sizes are limited to powers of 2 up to 4MiB (MAX_PAGE_ORDER).  In order to
 provide other sizes, and in particular an arbitrarily large size, multiple
 buffers are logically concatenated.  However an interrupt must be used to switch
 between buffers.  That has two potential problems:
diff --git a/tools/testing/memblock/linux/mmzone.h b/tools/testing/memblock/linux/mmzone.h
index 134f8eab0768..71546e15bdd3 100644
--- a/tools/testing/memblock/linux/mmzone.h
+++ b/tools/testing/memblock/linux/mmzone.h
@@ -17,10 +17,10 @@ enum zone_type {
 };
 
 #define MAX_NR_ZONES __MAX_NR_ZONES
-#define MAX_ORDER 10
-#define MAX_ORDER_NR_PAGES (1 << MAX_ORDER)
+#define MAX_PAGE_ORDER 10
+#define MAX_ORDER_NR_PAGES (1 << MAX_PAGE_ORDER)
 
-#define pageblock_order		MAX_ORDER
+#define pageblock_order		MAX_PAGE_ORDER
 #define pageblock_nr_pages	BIT(pageblock_order)
 #define pageblock_align(pfn)	ALIGN((pfn), pageblock_nr_pages)
 #define pageblock_start_pfn(pfn)	ALIGN_DOWN((pfn), pageblock_nr_pages)
diff --git a/tools/testing/selftests/mm/thuge-gen.c b/tools/testing/selftests/mm/thuge-gen.c
index 16ed4dfa7359..622987f12c89 100644
--- a/tools/testing/selftests/mm/thuge-gen.c
+++ b/tools/testing/selftests/mm/thuge-gen.c
@@ -3,7 +3,8 @@
 
    Before running this huge pages for each huge page size must have been
    reserved.
-   For large pages beyond MAX_ORDER (like 1GB on x86) boot options must be used.
+   For large pages beyond MAX_PAGE_ORDER (like 1GB on x86) boot options must
+   be used.
    Also shmmax must be increased.
    And you need to run as root to work around some weird permissions in shm.
    And nothing using huge pages should run in parallel.
-- 
cgit v1.2.3


From 125c0a646a257fd58de223f2c3e1fe8a99085644 Mon Sep 17 00:00:00 2001
From: Juergen Gross <jgross@suse.com>
Date: Tue, 5 Dec 2023 12:51:21 +0100
Subject: xen: update PV-device interface headers

Update the Xen PV-device interface headers in order to avoid undefined
behavior with flexible arrays being defined with one array element.

Reported-by: Pry Mar <pryorm09@gmail.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Acked-by: Stefano Stabellini <sstabellini@kernel.org>
Link: https://lore.kernel.org/r/20231205115121.11627-1-jgross@suse.com
Signed-off-by: Juergen Gross <jgross@suse.com>
---
 include/xen/interface/io/displif.h | 2 +-
 include/xen/interface/io/ring.h    | 2 +-
 include/xen/interface/io/sndif.h   | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/xen/interface/io/displif.h b/include/xen/interface/io/displif.h
index 18417b017869..60e42d3b760e 100644
--- a/include/xen/interface/io/displif.h
+++ b/include/xen/interface/io/displif.h
@@ -537,7 +537,7 @@ struct xendispl_dbuf_create_req {
 
 struct xendispl_page_directory {
 	grant_ref_t gref_dir_next_page;
-	grant_ref_t gref[1]; /* Variable length */
+	grant_ref_t gref[];
 };
 
 /*
diff --git a/include/xen/interface/io/ring.h b/include/xen/interface/io/ring.h
index ba4c4274b714..4fef1efcdcab 100644
--- a/include/xen/interface/io/ring.h
+++ b/include/xen/interface/io/ring.h
@@ -95,7 +95,7 @@ struct __name##_sring {                                                 \
     RING_IDX req_prod, req_event;                                       \
     RING_IDX rsp_prod, rsp_event;                                       \
     uint8_t __pad[48];                                                  \
-    union __name##_sring_entry ring[1]; /* variable-length */           \
+    union __name##_sring_entry ring[];                                  \
 };                                                                      \
                                                                         \
 /* "Front" end's private variables */                                   \
diff --git a/include/xen/interface/io/sndif.h b/include/xen/interface/io/sndif.h
index 445657cdb1de..b818517588b5 100644
--- a/include/xen/interface/io/sndif.h
+++ b/include/xen/interface/io/sndif.h
@@ -659,7 +659,7 @@ struct xensnd_open_req {
 
 struct xensnd_page_directory {
 	grant_ref_t gref_dir_next_page;
-	grant_ref_t gref[1]; /* Variable length */
+	grant_ref_t gref[];
 };
 
 /*
-- 
cgit v1.2.3


From 2fb7e4dd35c52933b18ff127bf92d703c8e2e897 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Fri, 5 Jan 2024 13:51:21 +0100
Subject: PNP: make pnp_bus_type const

Now that the driver core can properly handle constant struct bus_type,
move the pnp_bus_type variable to be a constant structure as well,
placing it into read-only memory which can not be modified at runtime.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/pnp/driver.c | 2 +-
 include/linux/pnp.h  | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/pnp/driver.c b/drivers/pnp/driver.c
index 46c534f6b1c9..0a5d0d8befa8 100644
--- a/drivers/pnp/driver.c
+++ b/drivers/pnp/driver.c
@@ -256,7 +256,7 @@ static const struct dev_pm_ops pnp_bus_dev_pm_ops = {
 	.restore = pnp_bus_resume,
 };
 
-struct bus_type pnp_bus_type = {
+const struct bus_type pnp_bus_type = {
 	.name    = "pnp",
 	.match   = pnp_bus_match,
 	.probe   = pnp_device_probe,
diff --git a/include/linux/pnp.h b/include/linux/pnp.h
index 267fb8a4fb6e..ddbe7c3ca4ce 100644
--- a/include/linux/pnp.h
+++ b/include/linux/pnp.h
@@ -435,7 +435,7 @@ struct pnp_protocol {
 #define protocol_for_each_dev(protocol, dev)	\
 	list_for_each_entry(dev, &(protocol)->devices, protocol_list)
 
-extern struct bus_type pnp_bus_type;
+extern const struct bus_type pnp_bus_type;
 
 #if defined(CONFIG_PNP)
 
-- 
cgit v1.2.3


From cb1210a7c03c55f9fb7496bd44155c6a024fe458 Mon Sep 17 00:00:00 2001
From: Lorenzo Pieralisi <lpieralisi@kernel.org>
Date: Wed, 27 Dec 2023 12:00:36 +0100
Subject: ACPICA: MADT: Add GICC online capable bit handling

ACPICA commit 16f0befdeddf25756f317907798192bbaa417e5e

Implement code to handle the GICC online capable bit management
added into ACPI v6.5.

Link: https://github.com/acpica/acpica/commit/16f0befd
Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/actbl2.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h
index 3751ae69432f..2b4dd2c3348f 100644
--- a/include/acpi/actbl2.h
+++ b/include/acpi/actbl2.h
@@ -1046,6 +1046,7 @@ struct acpi_madt_generic_interrupt {
 /* ACPI_MADT_ENABLED                    (1)      Processor is usable if set */
 #define ACPI_MADT_PERFORMANCE_IRQ_MODE  (1<<1)	/* 01: Performance Interrupt Mode */
 #define ACPI_MADT_VGIC_IRQ_MODE         (1<<2)	/* 02: VGIC Maintenance Interrupt mode */
+#define ACPI_MADT_GICC_ONLINE_CAPABLE   (1<<3)	/* 03: Processor is online capable  */
 
 /* 12: Generic Distributor (ACPI 5.0 + ACPI 6.0 changes) */
 
-- 
cgit v1.2.3


From 3be8fb1bc6fc10b6c8e79052126fa5a423698fd1 Mon Sep 17 00:00:00 2001
From: Lorenzo Pieralisi <lpieralisi@kernel.org>
Date: Wed, 27 Dec 2023 12:00:37 +0100
Subject: ACPICA: MADT: Add new MADT GICC/GICR/ITS non-coherent flags handling

ACPICA commit c5d2010744b1bf7efba0bd04a8a9c200ef8fb610

Add new flags and related fields to the MADT GICC/GICR/ITS
structures according to the code first ECR:

https://bugzilla.tianocore.org/show_bug.cgi?id=4557

Update the MADT template to the latest MADT revision.

Link: https://github.com/acpica/acpica/commit/c5d20107
Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/actbl2.h | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h
index 2b4dd2c3348f..9775384d61c6 100644
--- a/include/acpi/actbl2.h
+++ b/include/acpi/actbl2.h
@@ -1047,6 +1047,7 @@ struct acpi_madt_generic_interrupt {
 #define ACPI_MADT_PERFORMANCE_IRQ_MODE  (1<<1)	/* 01: Performance Interrupt Mode */
 #define ACPI_MADT_VGIC_IRQ_MODE         (1<<2)	/* 02: VGIC Maintenance Interrupt mode */
 #define ACPI_MADT_GICC_ONLINE_CAPABLE   (1<<3)	/* 03: Processor is online capable  */
+#define ACPI_MADT_GICC_NON_COHERENT     (1<<4)	/* 04: GIC redistributor is not coherent */
 
 /* 12: Generic Distributor (ACPI 5.0 + ACPI 6.0 changes) */
 
@@ -1091,21 +1092,27 @@ struct acpi_madt_generic_msi_frame {
 
 struct acpi_madt_generic_redistributor {
 	struct acpi_subtable_header header;
-	u16 reserved;		/* reserved - must be zero */
+	u8 flags;
+	u8 reserved;		/* reserved - must be zero */
 	u64 base_address;
 	u32 length;
 };
 
+#define ACPI_MADT_GICR_NON_COHERENT     (1)
+
 /* 15: Generic Translator (ACPI 6.0) */
 
 struct acpi_madt_generic_translator {
 	struct acpi_subtable_header header;
-	u16 reserved;		/* reserved - must be zero */
+	u8 flags;
+	u8 reserved;		/* reserved - must be zero */
 	u32 translation_id;
 	u64 base_address;
 	u32 reserved2;
 };
 
+#define ACPI_MADT_ITS_NON_COHERENT      (1)
+
 /* 16: Multiprocessor wakeup (ACPI 6.4) */
 
 struct acpi_madt_multiproc_wakeup {
-- 
cgit v1.2.3


From 6eade110754c085cee9e46f4d87d2c3ea4e59e8c Mon Sep 17 00:00:00 2001
From: Ira Weiny <ira.weiny@intel.com>
Date: Wed, 20 Dec 2023 16:17:32 -0800
Subject: cxl/events: Separate UUID from event structures

The UEFI CXL CPER structure does not include the UUID.  Now that the
UUID is passed separately to the trace event there is no need to have
the UUID in those structures.

Move UUID from the event record header to the raw structures.  Adjust
cxl-test to Create dummy structures for creating test records.

Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Link: https://lore.kernel.org/r/20231220-cxl-cper-v5-5-1bb8a4ca2c7a@intel.com
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/core/mbox.c      |   2 +-
 include/linux/cxl-event.h    |   6 +-
 tools/testing/cxl/test/mem.c | 129 +++++++++++++++++++++++++------------------
 3 files changed, 81 insertions(+), 56 deletions(-)

(limited to 'include')

diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
index 5f3681de10de..4c5161896826 100644
--- a/drivers/cxl/core/mbox.c
+++ b/drivers/cxl/core/mbox.c
@@ -840,7 +840,7 @@ static void cxl_event_trace_record(const struct cxl_memdev *cxlmd,
 				   enum cxl_event_log_type type,
 				   struct cxl_event_record_raw *record)
 {
-	uuid_t *id = &record->hdr.id;
+	uuid_t *id = &record->id;
 
 	if (uuid_equal(id, &CXL_EVENT_GEN_MEDIA_UUID)) {
 		struct cxl_event_gen_media *rec =
diff --git a/include/linux/cxl-event.h b/include/linux/cxl-event.h
index 0fc068123f8e..3d9b5954d0c1 100644
--- a/include/linux/cxl-event.h
+++ b/include/linux/cxl-event.h
@@ -8,7 +8,6 @@
  * CXL rev 3.0 section 8.2.9.2.1; Table 8-42
  */
 struct cxl_event_record_hdr {
-	uuid_t id;
 	u8 length;
 	u8 flags[3];
 	__le16 handle;
@@ -18,8 +17,13 @@ struct cxl_event_record_hdr {
 	u8 reserved[15];
 } __packed;
 
+/*
+ * Common Event Record Format
+ * CXL rev 3.0 section 8.2.9.2.1; Table 8-42
+ */
 #define CXL_EVENT_RECORD_DATA_LENGTH 0x50
 struct cxl_event_record_raw {
+	uuid_t id;
 	struct cxl_event_record_hdr hdr;
 	u8 data[CXL_EVENT_RECORD_DATA_LENGTH];
 } __packed;
diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c
index 5a95b04b329a..9cc2b8ce1efd 100644
--- a/tools/testing/cxl/test/mem.c
+++ b/tools/testing/cxl/test/mem.c
@@ -337,9 +337,9 @@ static void cxl_mock_event_trigger(struct device *dev)
 }
 
 struct cxl_event_record_raw maint_needed = {
+	.id = UUID_INIT(0xBA5EBA11, 0xABCD, 0xEFEB,
+			0xa5, 0x5a, 0xa5, 0x5a, 0xa5, 0xa5, 0x5a, 0xa5),
 	.hdr = {
-		.id = UUID_INIT(0xBA5EBA11, 0xABCD, 0xEFEB,
-				0xa5, 0x5a, 0xa5, 0x5a, 0xa5, 0xa5, 0x5a, 0xa5),
 		.length = sizeof(struct cxl_event_record_raw),
 		.flags[0] = CXL_EVENT_RECORD_FLAG_MAINT_NEEDED,
 		/* .handle = Set dynamically */
@@ -349,9 +349,9 @@ struct cxl_event_record_raw maint_needed = {
 };
 
 struct cxl_event_record_raw hardware_replace = {
+	.id = UUID_INIT(0xABCDEFEB, 0xBA11, 0xBA5E,
+			0xa5, 0x5a, 0xa5, 0x5a, 0xa5, 0xa5, 0x5a, 0xa5),
 	.hdr = {
-		.id = UUID_INIT(0xABCDEFEB, 0xBA11, 0xBA5E,
-				0xa5, 0x5a, 0xa5, 0x5a, 0xa5, 0xa5, 0x5a, 0xa5),
 		.length = sizeof(struct cxl_event_record_raw),
 		.flags[0] = CXL_EVENT_RECORD_FLAG_HW_REPLACE,
 		/* .handle = Set dynamically */
@@ -360,61 +360,82 @@ struct cxl_event_record_raw hardware_replace = {
 	.data = { 0xDE, 0xAD, 0xBE, 0xEF },
 };
 
-struct cxl_event_gen_media gen_media = {
-	.hdr = {
-		.id = CXL_EVENT_GEN_MEDIA_UUID,
-		.length = sizeof(struct cxl_event_gen_media),
-		.flags[0] = CXL_EVENT_RECORD_FLAG_PERMANENT,
-		/* .handle = Set dynamically */
-		.related_handle = cpu_to_le16(0),
+struct cxl_test_gen_media {
+	uuid_t id;
+	struct cxl_event_gen_media rec;
+} __packed;
+
+struct cxl_test_gen_media gen_media = {
+	.id = CXL_EVENT_GEN_MEDIA_UUID,
+	.rec = {
+		.hdr = {
+			.length = sizeof(struct cxl_test_gen_media),
+			.flags[0] = CXL_EVENT_RECORD_FLAG_PERMANENT,
+			/* .handle = Set dynamically */
+			.related_handle = cpu_to_le16(0),
+		},
+		.phys_addr = cpu_to_le64(0x2000),
+		.descriptor = CXL_GMER_EVT_DESC_UNCORECTABLE_EVENT,
+		.type = CXL_GMER_MEM_EVT_TYPE_DATA_PATH_ERROR,
+		.transaction_type = CXL_GMER_TRANS_HOST_WRITE,
+		/* .validity_flags = <set below> */
+		.channel = 1,
+		.rank = 30
 	},
-	.phys_addr = cpu_to_le64(0x2000),
-	.descriptor = CXL_GMER_EVT_DESC_UNCORECTABLE_EVENT,
-	.type = CXL_GMER_MEM_EVT_TYPE_DATA_PATH_ERROR,
-	.transaction_type = CXL_GMER_TRANS_HOST_WRITE,
-	/* .validity_flags = <set below> */
-	.channel = 1,
-	.rank = 30
 };
 
-struct cxl_event_dram dram = {
-	.hdr = {
-		.id = CXL_EVENT_DRAM_UUID,
-		.length = sizeof(struct cxl_event_dram),
-		.flags[0] = CXL_EVENT_RECORD_FLAG_PERF_DEGRADED,
-		/* .handle = Set dynamically */
-		.related_handle = cpu_to_le16(0),
+struct cxl_test_dram {
+	uuid_t id;
+	struct cxl_event_dram rec;
+} __packed;
+
+struct cxl_test_dram dram = {
+	.id = CXL_EVENT_DRAM_UUID,
+	.rec = {
+		.hdr = {
+			.length = sizeof(struct cxl_test_dram),
+			.flags[0] = CXL_EVENT_RECORD_FLAG_PERF_DEGRADED,
+			/* .handle = Set dynamically */
+			.related_handle = cpu_to_le16(0),
+		},
+		.phys_addr = cpu_to_le64(0x8000),
+		.descriptor = CXL_GMER_EVT_DESC_THRESHOLD_EVENT,
+		.type = CXL_GMER_MEM_EVT_TYPE_INV_ADDR,
+		.transaction_type = CXL_GMER_TRANS_INTERNAL_MEDIA_SCRUB,
+		/* .validity_flags = <set below> */
+		.channel = 1,
+		.bank_group = 5,
+		.bank = 2,
+		.column = {0xDE, 0xAD},
 	},
-	.phys_addr = cpu_to_le64(0x8000),
-	.descriptor = CXL_GMER_EVT_DESC_THRESHOLD_EVENT,
-	.type = CXL_GMER_MEM_EVT_TYPE_INV_ADDR,
-	.transaction_type = CXL_GMER_TRANS_INTERNAL_MEDIA_SCRUB,
-	/* .validity_flags = <set below> */
-	.channel = 1,
-	.bank_group = 5,
-	.bank = 2,
-	.column = {0xDE, 0xAD},
 };
 
-struct cxl_event_mem_module mem_module = {
-	.hdr = {
-		.id = CXL_EVENT_MEM_MODULE_UUID,
-		.length = sizeof(struct cxl_event_mem_module),
-		/* .handle = Set dynamically */
-		.related_handle = cpu_to_le16(0),
+struct cxl_test_mem_module {
+	uuid_t id;
+	struct cxl_event_mem_module rec;
+} __packed;
+
+struct cxl_test_mem_module mem_module = {
+	.id = CXL_EVENT_MEM_MODULE_UUID,
+	.rec = {
+		.hdr = {
+			.length = sizeof(struct cxl_test_mem_module),
+			/* .handle = Set dynamically */
+			.related_handle = cpu_to_le16(0),
+		},
+		.event_type = CXL_MMER_TEMP_CHANGE,
+		.info = {
+			.health_status = CXL_DHI_HS_PERFORMANCE_DEGRADED,
+			.media_status = CXL_DHI_MS_ALL_DATA_LOST,
+			.add_status = (CXL_DHI_AS_CRITICAL << 2) |
+				      (CXL_DHI_AS_WARNING << 4) |
+				      (CXL_DHI_AS_WARNING << 5),
+			.device_temp = { 0xDE, 0xAD},
+			.dirty_shutdown_cnt = { 0xde, 0xad, 0xbe, 0xef },
+			.cor_vol_err_cnt = { 0xde, 0xad, 0xbe, 0xef },
+			.cor_per_err_cnt = { 0xde, 0xad, 0xbe, 0xef },
+		}
 	},
-	.event_type = CXL_MMER_TEMP_CHANGE,
-	.info = {
-		.health_status = CXL_DHI_HS_PERFORMANCE_DEGRADED,
-		.media_status = CXL_DHI_MS_ALL_DATA_LOST,
-		.add_status = (CXL_DHI_AS_CRITICAL << 2) |
-			      (CXL_DHI_AS_WARNING << 4) |
-			      (CXL_DHI_AS_WARNING << 5),
-		.device_temp = { 0xDE, 0xAD},
-		.dirty_shutdown_cnt = { 0xde, 0xad, 0xbe, 0xef },
-		.cor_vol_err_cnt = { 0xde, 0xad, 0xbe, 0xef },
-		.cor_per_err_cnt = { 0xde, 0xad, 0xbe, 0xef },
-	}
 };
 
 static int mock_set_timestamp(struct cxl_dev_state *cxlds,
@@ -436,11 +457,11 @@ static int mock_set_timestamp(struct cxl_dev_state *cxlds,
 static void cxl_mock_add_event_logs(struct mock_event_store *mes)
 {
 	put_unaligned_le16(CXL_GMER_VALID_CHANNEL | CXL_GMER_VALID_RANK,
-			   &gen_media.validity_flags);
+			   &gen_media.rec.validity_flags);
 
 	put_unaligned_le16(CXL_DER_VALID_CHANNEL | CXL_DER_VALID_BANK_GROUP |
 			   CXL_DER_VALID_BANK | CXL_DER_VALID_COLUMN,
-			   &dram.validity_flags);
+			   &dram.rec.validity_flags);
 
 	mes_add_event(mes, CXL_EVENT_TYPE_INFO, &maint_needed);
 	mes_add_event(mes, CXL_EVENT_TYPE_INFO,
-- 
cgit v1.2.3


From f9c683386f5bc0364615138ce2b14be50848dbcf Mon Sep 17 00:00:00 2001
From: Ira Weiny <ira.weiny@intel.com>
Date: Wed, 20 Dec 2023 16:17:33 -0800
Subject: cxl/events: Create a CXL event union

The CXL CPER and event log records share everything but a UUID/GUID in
their structures.

Define a cxl_event union without the UUID/GUID to be shared between the
CPER and event log record formats.  Adjust the code to use this union.

Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Link: https://lore.kernel.org/r/20231220-cxl-cper-v5-6-1bb8a4ca2c7a@intel.com
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/core/mbox.c      | 32 +++++++++++++-------------------
 drivers/cxl/core/trace.h     |  8 ++++----
 include/linux/cxl-event.h    | 23 +++++++++++++++++------
 tools/testing/cxl/test/mem.c | 31 ++++++++++++++++++-------------
 4 files changed, 52 insertions(+), 42 deletions(-)

(limited to 'include')

diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
index 4c5161896826..06957696247b 100644
--- a/drivers/cxl/core/mbox.c
+++ b/drivers/cxl/core/mbox.c
@@ -840,26 +840,17 @@ static void cxl_event_trace_record(const struct cxl_memdev *cxlmd,
 				   enum cxl_event_log_type type,
 				   struct cxl_event_record_raw *record)
 {
+	union cxl_event *evt = &record->event;
 	uuid_t *id = &record->id;
 
-	if (uuid_equal(id, &CXL_EVENT_GEN_MEDIA_UUID)) {
-		struct cxl_event_gen_media *rec =
-				(struct cxl_event_gen_media *)record;
-
-		trace_cxl_general_media(cxlmd, type, rec);
-	} else if (uuid_equal(id, &CXL_EVENT_DRAM_UUID)) {
-		struct cxl_event_dram *rec = (struct cxl_event_dram *)record;
-
-		trace_cxl_dram(cxlmd, type, rec);
-	} else if (uuid_equal(id, &CXL_EVENT_MEM_MODULE_UUID)) {
-		struct cxl_event_mem_module *rec =
-				(struct cxl_event_mem_module *)record;
-
-		trace_cxl_memory_module(cxlmd, type, rec);
-	} else {
-		/* For unknown record types print just the header */
-		trace_cxl_generic_event(cxlmd, type, id, record);
-	}
+	if (uuid_equal(id, &CXL_EVENT_GEN_MEDIA_UUID))
+		trace_cxl_general_media(cxlmd, type, &evt->gen_media);
+	else if (uuid_equal(id, &CXL_EVENT_DRAM_UUID))
+		trace_cxl_dram(cxlmd, type, &evt->dram);
+	else if (uuid_equal(id, &CXL_EVENT_MEM_MODULE_UUID))
+		trace_cxl_memory_module(cxlmd, type, &evt->mem_module);
+	else
+		trace_cxl_generic_event(cxlmd, type, id, &evt->generic);
 }
 
 static int cxl_clear_event_record(struct cxl_memdev_state *mds,
@@ -902,7 +893,10 @@ static int cxl_clear_event_record(struct cxl_memdev_state *mds,
 	 */
 	i = 0;
 	for (cnt = 0; cnt < total; cnt++) {
-		payload->handles[i++] = get_pl->records[cnt].hdr.handle;
+		struct cxl_event_record_raw *raw = &get_pl->records[cnt];
+		struct cxl_event_generic *gen = &raw->event.generic;
+
+		payload->handles[i++] = gen->hdr.handle;
 		dev_dbg(mds->cxlds.dev, "Event log '%d': Clearing %u\n", log,
 			le16_to_cpu(payload->handles[i]));
 
diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h
index 312cfa9e0004..89445435303a 100644
--- a/drivers/cxl/core/trace.h
+++ b/drivers/cxl/core/trace.h
@@ -225,9 +225,9 @@ TRACE_EVENT(cxl_overflow,
 TRACE_EVENT(cxl_generic_event,
 
 	TP_PROTO(const struct cxl_memdev *cxlmd, enum cxl_event_log_type log,
-		 const uuid_t *uuid, struct cxl_event_record_raw *rec),
+		 const uuid_t *uuid, struct cxl_event_generic *gen_rec),
 
-	TP_ARGS(cxlmd, log, uuid, rec),
+	TP_ARGS(cxlmd, log, uuid, gen_rec),
 
 	TP_STRUCT__entry(
 		CXL_EVT_TP_entry
@@ -235,9 +235,9 @@ TRACE_EVENT(cxl_generic_event,
 	),
 
 	TP_fast_assign(
-		CXL_EVT_TP_fast_assign(cxlmd, log, rec->hdr);
+		CXL_EVT_TP_fast_assign(cxlmd, log, gen_rec->hdr);
 		memcpy(&__entry->hdr_uuid, uuid, sizeof(uuid_t));
-		memcpy(__entry->data, &rec->data, CXL_EVENT_RECORD_DATA_LENGTH);
+		memcpy(__entry->data, gen_rec->data, CXL_EVENT_RECORD_DATA_LENGTH);
 	),
 
 	CXL_EVT_TP_printk("%s",
diff --git a/include/linux/cxl-event.h b/include/linux/cxl-event.h
index 3d9b5954d0c1..4d6c05f535f8 100644
--- a/include/linux/cxl-event.h
+++ b/include/linux/cxl-event.h
@@ -17,13 +17,8 @@ struct cxl_event_record_hdr {
 	u8 reserved[15];
 } __packed;
 
-/*
- * Common Event Record Format
- * CXL rev 3.0 section 8.2.9.2.1; Table 8-42
- */
 #define CXL_EVENT_RECORD_DATA_LENGTH 0x50
-struct cxl_event_record_raw {
-	uuid_t id;
+struct cxl_event_generic {
 	struct cxl_event_record_hdr hdr;
 	u8 data[CXL_EVENT_RECORD_DATA_LENGTH];
 } __packed;
@@ -96,4 +91,20 @@ struct cxl_event_mem_module {
 	u8 reserved[0x3d];
 } __packed;
 
+union cxl_event {
+	struct cxl_event_generic generic;
+	struct cxl_event_gen_media gen_media;
+	struct cxl_event_dram dram;
+	struct cxl_event_mem_module mem_module;
+} __packed;
+
+/*
+ * Common Event Record Format; in event logs
+ * CXL rev 3.0 section 8.2.9.2.1; Table 8-42
+ */
+struct cxl_event_record_raw {
+	uuid_t id;
+	union cxl_event event;
+} __packed;
+
 #endif /* _LINUX_CXL_EVENT_H */
diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c
index 9cc2b8ce1efd..35ee41e435ab 100644
--- a/tools/testing/cxl/test/mem.c
+++ b/tools/testing/cxl/test/mem.c
@@ -251,7 +251,8 @@ static int mock_get_event(struct device *dev, struct cxl_mbox_cmd *cmd)
 	for (i = 0; i < CXL_TEST_EVENT_CNT && !event_log_empty(log); i++) {
 		memcpy(&pl->records[i], event_get_current(log),
 		       sizeof(pl->records[i]));
-		pl->records[i].hdr.handle = event_get_cur_event_handle(log);
+		pl->records[i].event.generic.hdr.handle =
+				event_get_cur_event_handle(log);
 		log->cur_idx++;
 	}
 
@@ -339,25 +340,29 @@ static void cxl_mock_event_trigger(struct device *dev)
 struct cxl_event_record_raw maint_needed = {
 	.id = UUID_INIT(0xBA5EBA11, 0xABCD, 0xEFEB,
 			0xa5, 0x5a, 0xa5, 0x5a, 0xa5, 0xa5, 0x5a, 0xa5),
-	.hdr = {
-		.length = sizeof(struct cxl_event_record_raw),
-		.flags[0] = CXL_EVENT_RECORD_FLAG_MAINT_NEEDED,
-		/* .handle = Set dynamically */
-		.related_handle = cpu_to_le16(0xa5b6),
+	.event.generic = {
+		.hdr = {
+			.length = sizeof(struct cxl_event_record_raw),
+			.flags[0] = CXL_EVENT_RECORD_FLAG_MAINT_NEEDED,
+			/* .handle = Set dynamically */
+			.related_handle = cpu_to_le16(0xa5b6),
+		},
+		.data = { 0xDE, 0xAD, 0xBE, 0xEF },
 	},
-	.data = { 0xDE, 0xAD, 0xBE, 0xEF },
 };
 
 struct cxl_event_record_raw hardware_replace = {
 	.id = UUID_INIT(0xABCDEFEB, 0xBA11, 0xBA5E,
 			0xa5, 0x5a, 0xa5, 0x5a, 0xa5, 0xa5, 0x5a, 0xa5),
-	.hdr = {
-		.length = sizeof(struct cxl_event_record_raw),
-		.flags[0] = CXL_EVENT_RECORD_FLAG_HW_REPLACE,
-		/* .handle = Set dynamically */
-		.related_handle = cpu_to_le16(0xb6a5),
+	.event.generic = {
+		.hdr = {
+			.length = sizeof(struct cxl_event_record_raw),
+			.flags[0] = CXL_EVENT_RECORD_FLAG_HW_REPLACE,
+			/* .handle = Set dynamically */
+			.related_handle = cpu_to_le16(0xb6a5),
+		},
+		.data = { 0xDE, 0xAD, 0xBE, 0xEF },
 	},
-	.data = { 0xDE, 0xAD, 0xBE, 0xEF },
 };
 
 struct cxl_test_gen_media {
-- 
cgit v1.2.3


From 671a794c33c6e048ca5cedd5ad6af44d52d5d7e5 Mon Sep 17 00:00:00 2001
From: Ira Weiny <ira.weiny@intel.com>
Date: Wed, 20 Dec 2023 16:17:34 -0800
Subject: acpi/ghes: Process CXL Component Events

BIOS can configure memory devices as firmware first.  This will send CXL
events to the firmware instead of the OS.  The firmware can then send
these events to the OS via UEFI.

UEFI v2.10 section N.2.14 defines a Common Platform Error Record (CPER)
format for CXL Component Events.  The format is mostly the same as the
CXL Common Event Record Format.  The difference is the use of a GUID in
the Section Type rather than a UUID as part of the event itself.

Add GHES support to detect CXL CPER records and call a registered
callback with the event.

A notifier chain was considered for the callback but the complexity did
not justify the use case as only the CXL subsystem requires this event.
Enforce that only one callback can be registered at any time.

Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Rafael J. Wysocki <rafael@kernel.org>
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Link: https://lore.kernel.org/r/20231220-cxl-cper-v5-7-1bb8a4ca2c7a@intel.com
[djbw: fixup checkpatch errors]
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/acpi/apei/ghes.c  | 89 +++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/cxl-event.h | 50 ++++++++++++++++++++++++++
 2 files changed, 139 insertions(+)

(limited to 'include')

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 63ad0541db38..56a5d2ef9e0a 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -26,6 +26,7 @@
 #include <linux/interrupt.h>
 #include <linux/timer.h>
 #include <linux/cper.h>
+#include <linux/cxl-event.h>
 #include <linux/platform_device.h>
 #include <linux/mutex.h>
 #include <linux/ratelimit.h>
@@ -657,6 +658,78 @@ static void ghes_defer_non_standard_event(struct acpi_hest_generic_data *gdata,
 	schedule_work(&entry->work);
 }
 
+/*
+ * Only a single callback can be registered for CXL CPER events.
+ */
+static DECLARE_RWSEM(cxl_cper_rw_sem);
+static cxl_cper_callback cper_callback;
+
+/* CXL Event record UUIDs are formatted as GUIDs and reported in section type */
+
+/*
+ * General Media Event Record
+ * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
+ */
+#define CPER_SEC_CXL_GEN_MEDIA_GUID					\
+	GUID_INIT(0xfbcd0a77, 0xc260, 0x417f,				\
+		  0x85, 0xa9, 0x08, 0x8b, 0x16, 0x21, 0xeb, 0xa6)
+
+/*
+ * DRAM Event Record
+ * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44
+ */
+#define CPER_SEC_CXL_DRAM_GUID						\
+	GUID_INIT(0x601dcbb3, 0x9c06, 0x4eab,				\
+		  0xb8, 0xaf, 0x4e, 0x9b, 0xfb, 0x5c, 0x96, 0x24)
+
+/*
+ * Memory Module Event Record
+ * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45
+ */
+#define CPER_SEC_CXL_MEM_MODULE_GUID					\
+	GUID_INIT(0xfe927475, 0xdd59, 0x4339,				\
+		  0xa5, 0x86, 0x79, 0xba, 0xb1, 0x13, 0xb7, 0x74)
+
+static void cxl_cper_post_event(enum cxl_event_type event_type,
+				struct cxl_cper_event_rec *rec)
+{
+	if (rec->hdr.length <= sizeof(rec->hdr) ||
+	    rec->hdr.length > sizeof(*rec)) {
+		pr_err(FW_WARN "CXL CPER Invalid section length (%u)\n",
+		       rec->hdr.length);
+		return;
+	}
+
+	if (!(rec->hdr.validation_bits & CPER_CXL_COMP_EVENT_LOG_VALID)) {
+		pr_err(FW_WARN "CXL CPER invalid event\n");
+		return;
+	}
+
+	guard(rwsem_read)(&cxl_cper_rw_sem);
+	if (cper_callback)
+		cper_callback(event_type, rec);
+}
+
+int cxl_cper_register_callback(cxl_cper_callback callback)
+{
+	guard(rwsem_write)(&cxl_cper_rw_sem);
+	if (cper_callback)
+		return -EINVAL;
+	cper_callback = callback;
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cper_register_callback, CXL);
+
+int cxl_cper_unregister_callback(cxl_cper_callback callback)
+{
+	guard(rwsem_write)(&cxl_cper_rw_sem);
+	if (callback != cper_callback)
+		return -EINVAL;
+	cper_callback = NULL;
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cper_unregister_callback, CXL);
+
 static bool ghes_do_proc(struct ghes *ghes,
 			 const struct acpi_hest_generic_status *estatus)
 {
@@ -690,6 +763,22 @@ static bool ghes_do_proc(struct ghes *ghes,
 		}
 		else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) {
 			queued = ghes_handle_arm_hw_error(gdata, sev);
+		} else if (guid_equal(sec_type, &CPER_SEC_CXL_GEN_MEDIA_GUID)) {
+			struct cxl_cper_event_rec *rec =
+				acpi_hest_get_payload(gdata);
+
+			cxl_cper_post_event(CXL_CPER_EVENT_GEN_MEDIA, rec);
+		} else if (guid_equal(sec_type, &CPER_SEC_CXL_DRAM_GUID)) {
+			struct cxl_cper_event_rec *rec =
+				acpi_hest_get_payload(gdata);
+
+			cxl_cper_post_event(CXL_CPER_EVENT_DRAM, rec);
+		} else if (guid_equal(sec_type,
+				      &CPER_SEC_CXL_MEM_MODULE_GUID)) {
+			struct cxl_cper_event_rec *rec =
+				acpi_hest_get_payload(gdata);
+
+			cxl_cper_post_event(CXL_CPER_EVENT_MEM_MODULE, rec);
 		} else {
 			void *err = acpi_hest_get_payload(gdata);
 
diff --git a/include/linux/cxl-event.h b/include/linux/cxl-event.h
index 4d6c05f535f8..95841750a383 100644
--- a/include/linux/cxl-event.h
+++ b/include/linux/cxl-event.h
@@ -107,4 +107,54 @@ struct cxl_event_record_raw {
 	union cxl_event event;
 } __packed;
 
+enum cxl_event_type {
+	CXL_CPER_EVENT_GEN_MEDIA,
+	CXL_CPER_EVENT_DRAM,
+	CXL_CPER_EVENT_MEM_MODULE,
+};
+
+#define CPER_CXL_DEVICE_ID_VALID		BIT(0)
+#define CPER_CXL_DEVICE_SN_VALID		BIT(1)
+#define CPER_CXL_COMP_EVENT_LOG_VALID		BIT(2)
+struct cxl_cper_event_rec {
+	struct {
+		u32 length;
+		u64 validation_bits;
+		struct cper_cxl_event_devid {
+			u16 vendor_id;
+			u16 device_id;
+			u8 func_num;
+			u8 device_num;
+			u8 bus_num;
+			u16 segment_num;
+			u16 slot_num; /* bits 2:0 reserved */
+			u8 reserved;
+		} __packed device_id;
+		struct cper_cxl_event_sn {
+			u32 lower_dw;
+			u32 upper_dw;
+		} __packed dev_serial_num;
+	} __packed hdr;
+
+	union cxl_event event;
+} __packed;
+
+typedef void (*cxl_cper_callback)(enum cxl_event_type type,
+				  struct cxl_cper_event_rec *rec);
+
+#ifdef CONFIG_ACPI_APEI_GHES
+int cxl_cper_register_callback(cxl_cper_callback callback);
+int cxl_cper_unregister_callback(cxl_cper_callback callback);
+#else
+static inline int cxl_cper_register_callback(cxl_cper_callback callback)
+{
+	return 0;
+}
+
+static inline int cxl_cper_unregister_callback(cxl_cper_callback callback)
+{
+	return 0;
+}
+#endif
+
 #endif /* _LINUX_CXL_EVENT_H */
-- 
cgit v1.2.3


From ced085ef369af7a2b6da962ec2fbd01339f60693 Mon Sep 17 00:00:00 2001
From: Ira Weiny <ira.weiny@intel.com>
Date: Wed, 20 Dec 2023 16:17:35 -0800
Subject: PCI: Introduce cleanup helpers for device reference counts and locks

The "goto error" pattern is notorious for introducing subtle resource
leaks. Use the new cleanup.h helpers for PCI device reference counts and
locks.

Similar to the new put_device() and device_lock() cleanup helpers,
__free(put_device) and guard(device), define the same for PCI devices,
__free(pci_dev_put) and guard(pci_dev).  These helpers eliminate the
need for "goto free;" and "goto unlock;" patterns. For example, A
'struct pci_dev *' instance declared as:

    struct pci_dev *pdev __free(pci_dev_put) = NULL;

...will automatically call pci_dev_put() if @pdev is non-NULL when @pdev
goes out of scope (automatic variable scope). If a function wants to
invoke pci_dev_put() on error, but return @pdev on success, it can do:

    return no_free_ptr(pdev);

...or:

    return_ptr(pdev);

For potential cleanup opportunity there are 587 open-coded calls to
pci_dev_put() in the kernel with 65 instances within 10 lines of a goto
statement with the CXL driver threatening to add another one.

The guard() helper holds the associated lock for the remainder of the
current scope in which it was invoked. So, for example:

    func(...)
    {
        if (...) {
            ...
            guard(pci_dev); /* pci_dev_lock() invoked here */
            ...
        } /* <- implied pci_dev_unlock() triggered here */
    }

There are 15 invocations of pci_dev_unlock() in the kernel with 5
instances within 10 lines of a goto statement. Again, the CXL driver is
threatening to add another.

Introduce these helpers to preclude the addition of new more error prone
goto put; / goto unlock; sequences. For now, these helpers are used in
drivers/cxl/pci.c to allow ACPI error reports to be fed back into the
CXL driver associated with the PCI device identified in the report.

Cc: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Link: https://lore.kernel.org/r/20231220-cxl-cper-v5-8-1bb8a4ca2c7a@intel.com
[djbw: rewrite changelog]
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 include/linux/pci.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/pci.h b/include/linux/pci.h
index dea043bc1e38..0d23d2e0eb1a 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1170,6 +1170,7 @@ int pci_get_interrupt_pin(struct pci_dev *dev, struct pci_dev **bridge);
 u8 pci_common_swizzle(struct pci_dev *dev, u8 *pinp);
 struct pci_dev *pci_dev_get(struct pci_dev *dev);
 void pci_dev_put(struct pci_dev *dev);
+DEFINE_FREE(pci_dev_put, struct pci_dev *, if (_T) pci_dev_put(_T))
 void pci_remove_bus(struct pci_bus *b);
 void pci_stop_and_remove_bus_device(struct pci_dev *dev);
 void pci_stop_and_remove_bus_device_locked(struct pci_dev *dev);
@@ -1874,6 +1875,7 @@ void pci_cfg_access_unlock(struct pci_dev *dev);
 void pci_dev_lock(struct pci_dev *dev);
 int pci_dev_trylock(struct pci_dev *dev);
 void pci_dev_unlock(struct pci_dev *dev);
+DEFINE_GUARD(pci_dev, struct pci_dev *, pci_dev_lock(_T), pci_dev_unlock(_T))
 
 /*
  * PCI domain support.  Sometimes called PCI segment (eg by ACPI),
-- 
cgit v1.2.3


From dc97f6344f205b0dfa144e1b3e16d6dc05383d57 Mon Sep 17 00:00:00 2001
From: Ira Weiny <ira.weiny@intel.com>
Date: Wed, 20 Dec 2023 16:17:36 -0800
Subject: cxl/pci: Register for and process CPER events

If the firmware has configured CXL event support to be firmware first
the OS can process those events through CPER records.  The CXL layer has
unique DPA to HPA knowledge and standard event trace parsing in place.

CPER records contain Bus, Device, Function information which can be used
to identify the PCI device which is sending the event.

Change the PCI driver registration to include registration of a CXL
CPER callback to process events through the trace subsystem.

Use new scoped based management to simplify the handling of the PCI
device object.

Tested-by: Smita-Koralahalli <Smita.KoralahalliChannabasappa@amd.com>
Reviewed-by: Smita-Koralahalli <Smita.KoralahalliChannabasappa@amd.com>
Link: https://lore.kernel.org/r/20231220-cxl-cper-v5-9-1bb8a4ca2c7a@intel.com
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
[djbw: use new pci_dev guard, flip init order]
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/core/mbox.c   | 40 ++++++++++++++++++++++----------
 drivers/cxl/cxlmem.h      |  4 ++++
 drivers/cxl/pci.c         | 58 ++++++++++++++++++++++++++++++++++++++++++++++-
 include/linux/cxl-event.h |  1 +
 4 files changed, 90 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
index 06957696247b..23021920aace 100644
--- a/drivers/cxl/core/mbox.c
+++ b/drivers/cxl/core/mbox.c
@@ -836,21 +836,37 @@ out:
 }
 EXPORT_SYMBOL_NS_GPL(cxl_enumerate_cmds, CXL);
 
-static void cxl_event_trace_record(const struct cxl_memdev *cxlmd,
-				   enum cxl_event_log_type type,
-				   struct cxl_event_record_raw *record)
+void cxl_event_trace_record(const struct cxl_memdev *cxlmd,
+			    enum cxl_event_log_type type,
+			    enum cxl_event_type event_type,
+			    const uuid_t *uuid, union cxl_event *evt)
 {
-	union cxl_event *evt = &record->event;
-	uuid_t *id = &record->id;
-
-	if (uuid_equal(id, &CXL_EVENT_GEN_MEDIA_UUID))
+	if (event_type == CXL_CPER_EVENT_GEN_MEDIA)
 		trace_cxl_general_media(cxlmd, type, &evt->gen_media);
-	else if (uuid_equal(id, &CXL_EVENT_DRAM_UUID))
+	else if (event_type == CXL_CPER_EVENT_DRAM)
 		trace_cxl_dram(cxlmd, type, &evt->dram);
-	else if (uuid_equal(id, &CXL_EVENT_MEM_MODULE_UUID))
+	else if (event_type == CXL_CPER_EVENT_MEM_MODULE)
 		trace_cxl_memory_module(cxlmd, type, &evt->mem_module);
 	else
-		trace_cxl_generic_event(cxlmd, type, id, &evt->generic);
+		trace_cxl_generic_event(cxlmd, type, uuid, &evt->generic);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_event_trace_record, CXL);
+
+static void __cxl_event_trace_record(const struct cxl_memdev *cxlmd,
+				     enum cxl_event_log_type type,
+				     struct cxl_event_record_raw *record)
+{
+	enum cxl_event_type ev_type = CXL_CPER_EVENT_GENERIC;
+	const uuid_t *uuid = &record->id;
+
+	if (uuid_equal(uuid, &CXL_EVENT_GEN_MEDIA_UUID))
+		ev_type = CXL_CPER_EVENT_GEN_MEDIA;
+	else if (uuid_equal(uuid, &CXL_EVENT_DRAM_UUID))
+		ev_type = CXL_CPER_EVENT_DRAM;
+	else if (uuid_equal(uuid, &CXL_EVENT_MEM_MODULE_UUID))
+		ev_type = CXL_CPER_EVENT_MEM_MODULE;
+
+	cxl_event_trace_record(cxlmd, type, ev_type, uuid, &record->event);
 }
 
 static int cxl_clear_event_record(struct cxl_memdev_state *mds,
@@ -961,8 +977,8 @@ static void cxl_mem_get_records_log(struct cxl_memdev_state *mds,
 			break;
 
 		for (i = 0; i < nr_rec; i++)
-			cxl_event_trace_record(cxlmd, type,
-					       &payload->records[i]);
+			__cxl_event_trace_record(cxlmd, type,
+						 &payload->records[i]);
 
 		if (payload->flags & CXL_GET_EVENT_FLAG_OVERFLOW)
 			trace_cxl_overflow(cxlmd, type, payload);
diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h
index 27575513ec68..3c201324a3b3 100644
--- a/drivers/cxl/cxlmem.h
+++ b/drivers/cxl/cxlmem.h
@@ -802,6 +802,10 @@ void set_exclusive_cxl_commands(struct cxl_memdev_state *mds,
 void clear_exclusive_cxl_commands(struct cxl_memdev_state *mds,
 				  unsigned long *cmds);
 void cxl_mem_get_event_records(struct cxl_memdev_state *mds, u32 status);
+void cxl_event_trace_record(const struct cxl_memdev *cxlmd,
+			    enum cxl_event_log_type type,
+			    enum cxl_event_type event_type,
+			    const uuid_t *uuid, union cxl_event *evt);
 int cxl_set_timestamp(struct cxl_memdev_state *mds);
 int cxl_poison_state_init(struct cxl_memdev_state *mds);
 int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len,
diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c
index 0155fb66b580..4fd1f207c84e 100644
--- a/drivers/cxl/pci.c
+++ b/drivers/cxl/pci.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /* Copyright(c) 2020 Intel Corporation. All rights reserved. */
+#include <asm-generic/unaligned.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
 #include <linux/moduleparam.h>
 #include <linux/module.h>
@@ -969,6 +970,61 @@ static struct pci_driver cxl_pci_driver = {
 	},
 };
 
+#define CXL_EVENT_HDR_FLAGS_REC_SEVERITY GENMASK(1, 0)
+static void cxl_cper_event_call(enum cxl_event_type ev_type,
+				struct cxl_cper_event_rec *rec)
+{
+	struct cper_cxl_event_devid *device_id = &rec->hdr.device_id;
+	struct pci_dev *pdev __free(pci_dev_put) = NULL;
+	enum cxl_event_log_type log_type;
+	struct cxl_dev_state *cxlds;
+	unsigned int devfn;
+	u32 hdr_flags;
+
+	devfn = PCI_DEVFN(device_id->device_num, device_id->func_num);
+	pdev = pci_get_domain_bus_and_slot(device_id->segment_num,
+					   device_id->bus_num, devfn);
+	if (!pdev)
+		return;
+
+	guard(pci_dev)(pdev);
+	if (pdev->driver != &cxl_pci_driver)
+		return;
+
+	cxlds = pci_get_drvdata(pdev);
+	if (!cxlds)
+		return;
+
+	/* Fabricate a log type */
+	hdr_flags = get_unaligned_le24(rec->event.generic.hdr.flags);
+	log_type = FIELD_GET(CXL_EVENT_HDR_FLAGS_REC_SEVERITY, hdr_flags);
+
+	cxl_event_trace_record(cxlds->cxlmd, log_type, ev_type,
+			       &uuid_null, &rec->event);
+}
+
+static int __init cxl_pci_driver_init(void)
+{
+	int rc;
+
+	rc = cxl_cper_register_callback(cxl_cper_event_call);
+	if (rc)
+		return rc;
+
+	rc = pci_register_driver(&cxl_pci_driver);
+	if (rc)
+		cxl_cper_unregister_callback(cxl_cper_event_call);
+
+	return rc;
+}
+
+static void __exit cxl_pci_driver_exit(void)
+{
+	pci_unregister_driver(&cxl_pci_driver);
+	cxl_cper_unregister_callback(cxl_cper_event_call);
+}
+
+module_init(cxl_pci_driver_init);
+module_exit(cxl_pci_driver_exit);
 MODULE_LICENSE("GPL v2");
-module_pci_driver(cxl_pci_driver);
 MODULE_IMPORT_NS(CXL);
diff --git a/include/linux/cxl-event.h b/include/linux/cxl-event.h
index 95841750a383..91125eca4c8a 100644
--- a/include/linux/cxl-event.h
+++ b/include/linux/cxl-event.h
@@ -108,6 +108,7 @@ struct cxl_event_record_raw {
 } __packed;
 
 enum cxl_event_type {
+	CXL_CPER_EVENT_GENERIC,
 	CXL_CPER_EVENT_GEN_MEDIA,
 	CXL_CPER_EVENT_DRAM,
 	CXL_CPER_EVENT_MEM_MODULE,
-- 
cgit v1.2.3


From 35967bdcff325f4572b21b0d0005318da7e03f53 Mon Sep 17 00:00:00 2001
From: Changyuan Lyu <changyuanl@google.com>
Date: Wed, 20 Dec 2023 12:49:06 -0800
Subject: virtio_pmem: support feature SHMEM_REGION

This patch adds the support for feature VIRTIO_PMEM_F_SHMEM_REGION
(virtio spec v1.2 section 5.19.5.2 [1]).

During feature negotiation, if VIRTIO_PMEM_F_SHMEM_REGION is offered
by the device, the driver looks for a shared memory region of id 0.
If it is found, this feature is understood. Otherwise, this feature
bit is cleared.

During probe, if VIRTIO_PMEM_F_SHMEM_REGION has been negotiated,
virtio pmem ignores the `start` and `size` fields in device config
and uses the physical address range of shared memory region 0.

[1] https://docs.oasis-open.org/virtio/virtio/v1.2/csd01/virtio-v1.2-csd01.html#x1-6480002

Signed-off-by: Changyuan Lyu <changyuanl@google.com>
Message-Id: <20231220204906.566922-1-changyuanl@google.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
---
 drivers/nvdimm/virtio_pmem.c     | 36 ++++++++++++++++++++++++++++++++----
 include/uapi/linux/virtio_pmem.h |  7 +++++++
 2 files changed, 39 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/nvdimm/virtio_pmem.c b/drivers/nvdimm/virtio_pmem.c
index a92eb172f0e7..4ceced5cefcf 100644
--- a/drivers/nvdimm/virtio_pmem.c
+++ b/drivers/nvdimm/virtio_pmem.c
@@ -29,12 +29,27 @@ static int init_vq(struct virtio_pmem *vpmem)
 	return 0;
 };
 
+static int virtio_pmem_validate(struct virtio_device *vdev)
+{
+	struct virtio_shm_region shm_reg;
+
+	if (virtio_has_feature(vdev, VIRTIO_PMEM_F_SHMEM_REGION) &&
+		!virtio_get_shm_region(vdev, &shm_reg, (u8)VIRTIO_PMEM_SHMEM_REGION_ID)
+	) {
+		dev_notice(&vdev->dev, "failed to get shared memory region %d\n",
+				VIRTIO_PMEM_SHMEM_REGION_ID);
+		__virtio_clear_bit(vdev, VIRTIO_PMEM_F_SHMEM_REGION);
+	}
+	return 0;
+}
+
 static int virtio_pmem_probe(struct virtio_device *vdev)
 {
 	struct nd_region_desc ndr_desc = {};
 	struct nd_region *nd_region;
 	struct virtio_pmem *vpmem;
 	struct resource res;
+	struct virtio_shm_region shm_reg;
 	int err = 0;
 
 	if (!vdev->config->get) {
@@ -57,10 +72,16 @@ static int virtio_pmem_probe(struct virtio_device *vdev)
 		goto out_err;
 	}
 
-	virtio_cread_le(vpmem->vdev, struct virtio_pmem_config,
-			start, &vpmem->start);
-	virtio_cread_le(vpmem->vdev, struct virtio_pmem_config,
-			size, &vpmem->size);
+	if (virtio_has_feature(vdev, VIRTIO_PMEM_F_SHMEM_REGION)) {
+		virtio_get_shm_region(vdev, &shm_reg, (u8)VIRTIO_PMEM_SHMEM_REGION_ID);
+		vpmem->start = shm_reg.addr;
+		vpmem->size = shm_reg.len;
+	} else {
+		virtio_cread_le(vpmem->vdev, struct virtio_pmem_config,
+				start, &vpmem->start);
+		virtio_cread_le(vpmem->vdev, struct virtio_pmem_config,
+				size, &vpmem->size);
+	}
 
 	res.start = vpmem->start;
 	res.end   = vpmem->start + vpmem->size - 1;
@@ -122,10 +143,17 @@ static void virtio_pmem_remove(struct virtio_device *vdev)
 	virtio_reset_device(vdev);
 }
 
+static unsigned int features[] = {
+	VIRTIO_PMEM_F_SHMEM_REGION,
+};
+
 static struct virtio_driver virtio_pmem_driver = {
+	.feature_table		= features,
+	.feature_table_size	= ARRAY_SIZE(features),
 	.driver.name		= KBUILD_MODNAME,
 	.driver.owner		= THIS_MODULE,
 	.id_table		= id_table,
+	.validate		= virtio_pmem_validate,
 	.probe			= virtio_pmem_probe,
 	.remove			= virtio_pmem_remove,
 };
diff --git a/include/uapi/linux/virtio_pmem.h b/include/uapi/linux/virtio_pmem.h
index d676b3620383..ede4f3564977 100644
--- a/include/uapi/linux/virtio_pmem.h
+++ b/include/uapi/linux/virtio_pmem.h
@@ -14,6 +14,13 @@
 #include <linux/virtio_ids.h>
 #include <linux/virtio_config.h>
 
+/* Feature bits */
+/* guest physical address range will be indicated as shared memory region 0 */
+#define VIRTIO_PMEM_F_SHMEM_REGION 0
+
+/* shmid of the shared memory region corresponding to the pmem */
+#define VIRTIO_PMEM_SHMEM_REGION_ID 0
+
 struct virtio_pmem_config {
 	__le64 start;
 	__le64 size;
-- 
cgit v1.2.3


From ef067191f73cce3ee192e991ce486d95524655d5 Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Mon, 25 Dec 2023 17:11:56 +0200
Subject: vdpa/mlx5: Expose resumable vq capability
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Necessary for checking if resumable vqs are supported by the hardware.
Actual support will be added in a downstream patch.

Reviewed-by: Gal Pressman <gal@nvidia.com>
Acked-by: Eugenio Pérez <eperezma@redhat.com>
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Message-Id: <20231225151203.152687-2-dtatulea@nvidia.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 include/linux/mlx5/mlx5_ifc.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 6f3631425f38..9eaceaf6bcb0 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1236,7 +1236,8 @@ struct mlx5_ifc_virtio_emulation_cap_bits {
 
 	u8	   reserved_at_c0[0x13];
 	u8         desc_group_mkey_supported[0x1];
-	u8         reserved_at_d4[0xc];
+	u8         freeze_to_rdy_supported[0x1];
+	u8         reserved_at_d5[0xb];
 
 	u8         reserved_at_e0[0x20];
 
-- 
cgit v1.2.3


From 9b23417825df470e4c9e98e7ed4b2c37465bfa1e Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Mon, 25 Dec 2023 17:11:59 +0200
Subject: vdpa/mlx5: Mark vq addrs for modification in hw vq

Addresses get set by .set_vq_address. hw vq addresses will be updated on
next modify_virtqueue.

Reviewed-by: Gal Pressman <gal@nvidia.com>
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Message-Id: <20231225151203.152687-5-dtatulea@nvidia.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vdpa/mlx5/net/mlx5_vnet.c  | 9 +++++++++
 include/linux/mlx5/mlx5_ifc_vdpa.h | 1 +
 2 files changed, 10 insertions(+)

(limited to 'include')

diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index f8f088cced50..80e066de0866 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -1209,6 +1209,7 @@ static int modify_virtqueue(struct mlx5_vdpa_net *ndev,
 	bool state_change = false;
 	void *obj_context;
 	void *cmd_hdr;
+	void *vq_ctx;
 	void *in;
 	int err;
 
@@ -1230,6 +1231,7 @@ static int modify_virtqueue(struct mlx5_vdpa_net *ndev,
 	MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, uid, ndev->mvdev.res.uid);
 
 	obj_context = MLX5_ADDR_OF(modify_virtio_net_q_in, in, obj_context);
+	vq_ctx = MLX5_ADDR_OF(virtio_net_q_object, obj_context, virtio_q_context);
 
 	if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_STATE) {
 		if (!is_valid_state_change(mvq->fw_state, state, is_resumable(ndev))) {
@@ -1241,6 +1243,12 @@ static int modify_virtqueue(struct mlx5_vdpa_net *ndev,
 		state_change = true;
 	}
 
+	if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_ADDRS) {
+		MLX5_SET64(virtio_q, vq_ctx, desc_addr, mvq->desc_addr);
+		MLX5_SET64(virtio_q, vq_ctx, used_addr, mvq->device_addr);
+		MLX5_SET64(virtio_q, vq_ctx, available_addr, mvq->driver_addr);
+	}
+
 	MLX5_SET64(virtio_net_q_object, obj_context, modify_field_select, mvq->modified_fields);
 	err = mlx5_cmd_exec(ndev->mvdev.mdev, in, inlen, out, sizeof(out));
 	if (err)
@@ -2202,6 +2210,7 @@ static int mlx5_vdpa_set_vq_address(struct vdpa_device *vdev, u16 idx, u64 desc_
 	mvq->desc_addr = desc_area;
 	mvq->device_addr = device_area;
 	mvq->driver_addr = driver_area;
+	mvq->modified_fields |= MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_ADDRS;
 	return 0;
 }
 
diff --git a/include/linux/mlx5/mlx5_ifc_vdpa.h b/include/linux/mlx5/mlx5_ifc_vdpa.h
index b86d51a855f6..9594ac405740 100644
--- a/include/linux/mlx5/mlx5_ifc_vdpa.h
+++ b/include/linux/mlx5/mlx5_ifc_vdpa.h
@@ -145,6 +145,7 @@ enum {
 	MLX5_VIRTQ_MODIFY_MASK_STATE                    = (u64)1 << 0,
 	MLX5_VIRTQ_MODIFY_MASK_DIRTY_BITMAP_PARAMS      = (u64)1 << 3,
 	MLX5_VIRTQ_MODIFY_MASK_DIRTY_BITMAP_DUMP_ENABLE = (u64)1 << 4,
+	MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_ADDRS           = (u64)1 << 6,
 	MLX5_VIRTQ_MODIFY_MASK_DESC_GROUP_MKEY          = (u64)1 << 14,
 };
 
-- 
cgit v1.2.3


From 60c43b3f6b4eb5a3d672952a0d65991f414ea258 Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Mon, 25 Dec 2023 17:12:00 +0200
Subject: vdpa/mlx5: Mark vq state for modification in hw vq

.set_vq_state will set the indices and mark the fields to be modified in
the hw vq.

Advertise that the device supports changing the vq state when the device
is in DRIVER_OK state and suspended.

Reviewed-by: Gal Pressman <gal@nvidia.com>
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Message-Id: <20231225151203.152687-6-dtatulea@nvidia.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vdpa/mlx5/net/mlx5_vnet.c  | 8 ++++++++
 include/linux/mlx5/mlx5_ifc_vdpa.h | 2 ++
 2 files changed, 10 insertions(+)

(limited to 'include')

diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 80e066de0866..d6c8506cec8f 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -1249,6 +1249,12 @@ static int modify_virtqueue(struct mlx5_vdpa_net *ndev,
 		MLX5_SET64(virtio_q, vq_ctx, available_addr, mvq->driver_addr);
 	}
 
+	if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_AVAIL_IDX)
+		MLX5_SET(virtio_net_q_object, obj_context, hw_available_index, mvq->avail_idx);
+
+	if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_USED_IDX)
+		MLX5_SET(virtio_net_q_object, obj_context, hw_used_index, mvq->used_idx);
+
 	MLX5_SET64(virtio_net_q_object, obj_context, modify_field_select, mvq->modified_fields);
 	err = mlx5_cmd_exec(ndev->mvdev.mdev, in, inlen, out, sizeof(out));
 	if (err)
@@ -2328,6 +2334,8 @@ static int mlx5_vdpa_set_vq_state(struct vdpa_device *vdev, u16 idx,
 
 	mvq->used_idx = state->split.avail_index;
 	mvq->avail_idx = state->split.avail_index;
+	mvq->modified_fields |= MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_AVAIL_IDX |
+				MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_USED_IDX;
 	return 0;
 }
 
diff --git a/include/linux/mlx5/mlx5_ifc_vdpa.h b/include/linux/mlx5/mlx5_ifc_vdpa.h
index 9594ac405740..32e712106e68 100644
--- a/include/linux/mlx5/mlx5_ifc_vdpa.h
+++ b/include/linux/mlx5/mlx5_ifc_vdpa.h
@@ -146,6 +146,8 @@ enum {
 	MLX5_VIRTQ_MODIFY_MASK_DIRTY_BITMAP_PARAMS      = (u64)1 << 3,
 	MLX5_VIRTQ_MODIFY_MASK_DIRTY_BITMAP_DUMP_ENABLE = (u64)1 << 4,
 	MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_ADDRS           = (u64)1 << 6,
+	MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_AVAIL_IDX       = (u64)1 << 7,
+	MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_USED_IDX        = (u64)1 << 8,
 	MLX5_VIRTQ_MODIFY_MASK_DESC_GROUP_MKEY          = (u64)1 << 14,
 };
 
-- 
cgit v1.2.3


From f756dd3e2a4c704c0ab5ecb143ab71f1249af497 Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Mon, 25 Dec 2023 17:12:01 +0200
Subject: vdpa/mlx5: Use vq suspend/resume during .set_map
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Instead of tearing down and setting up vq resources, use vq
suspend/resume during .set_map to speed things up a bit.

The vq mr is updated with the new mapping while the vqs are suspended.

If the device doesn't support resumable vqs, do the old teardown and
setup dance.

Reviewed-by: Gal Pressman <gal@nvidia.com>
Acked-by: Eugenio Pérez <eperezma@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Message-Id: <20231225151203.152687-7-dtatulea@nvidia.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vdpa/mlx5/net/mlx5_vnet.c  | 46 +++++++++++++++++++++++++++++++-------
 include/linux/mlx5/mlx5_ifc_vdpa.h |  1 +
 2 files changed, 39 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index d6c8506cec8f..6a21223d97a8 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -1206,6 +1206,7 @@ static int modify_virtqueue(struct mlx5_vdpa_net *ndev,
 {
 	int inlen = MLX5_ST_SZ_BYTES(modify_virtio_net_q_in);
 	u32 out[MLX5_ST_SZ_DW(modify_virtio_net_q_out)] = {};
+	struct mlx5_vdpa_dev *mvdev = &ndev->mvdev;
 	bool state_change = false;
 	void *obj_context;
 	void *cmd_hdr;
@@ -1255,6 +1256,24 @@ static int modify_virtqueue(struct mlx5_vdpa_net *ndev,
 	if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_USED_IDX)
 		MLX5_SET(virtio_net_q_object, obj_context, hw_used_index, mvq->used_idx);
 
+	if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_MKEY) {
+		struct mlx5_vdpa_mr *mr = mvdev->mr[mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP]];
+
+		if (mr)
+			MLX5_SET(virtio_q, vq_ctx, virtio_q_mkey, mr->mkey);
+		else
+			mvq->modified_fields &= ~MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_MKEY;
+	}
+
+	if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_DESC_GROUP_MKEY) {
+		struct mlx5_vdpa_mr *mr = mvdev->mr[mvdev->group2asid[MLX5_VDPA_DATAVQ_DESC_GROUP]];
+
+		if (mr && MLX5_CAP_DEV_VDPA_EMULATION(mvdev->mdev, desc_group_mkey_supported))
+			MLX5_SET(virtio_q, vq_ctx, desc_group_mkey, mr->mkey);
+		else
+			mvq->modified_fields &= ~MLX5_VIRTQ_MODIFY_MASK_DESC_GROUP_MKEY;
+	}
+
 	MLX5_SET64(virtio_net_q_object, obj_context, modify_field_select, mvq->modified_fields);
 	err = mlx5_cmd_exec(ndev->mvdev.mdev, in, inlen, out, sizeof(out));
 	if (err)
@@ -2784,24 +2803,35 @@ static int mlx5_vdpa_change_map(struct mlx5_vdpa_dev *mvdev,
 				unsigned int asid)
 {
 	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
+	bool teardown = !is_resumable(ndev);
 	int err;
 
 	suspend_vqs(ndev);
-	err = save_channels_info(ndev);
-	if (err)
-		return err;
+	if (teardown) {
+		err = save_channels_info(ndev);
+		if (err)
+			return err;
 
-	teardown_driver(ndev);
+		teardown_driver(ndev);
+	}
 
 	mlx5_vdpa_update_mr(mvdev, new_mr, asid);
 
+	for (int i = 0; i < ndev->cur_num_vqs; i++)
+		ndev->vqs[i].modified_fields |= MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_MKEY |
+						MLX5_VIRTQ_MODIFY_MASK_DESC_GROUP_MKEY;
+
 	if (!(mvdev->status & VIRTIO_CONFIG_S_DRIVER_OK) || mvdev->suspended)
 		return 0;
 
-	restore_channels_info(ndev);
-	err = setup_driver(mvdev);
-	if (err)
-		return err;
+	if (teardown) {
+		restore_channels_info(ndev);
+		err = setup_driver(mvdev);
+		if (err)
+			return err;
+	}
+
+	resume_vqs(ndev);
 
 	return 0;
 }
diff --git a/include/linux/mlx5/mlx5_ifc_vdpa.h b/include/linux/mlx5/mlx5_ifc_vdpa.h
index 32e712106e68..40371c916cf9 100644
--- a/include/linux/mlx5/mlx5_ifc_vdpa.h
+++ b/include/linux/mlx5/mlx5_ifc_vdpa.h
@@ -148,6 +148,7 @@ enum {
 	MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_ADDRS           = (u64)1 << 6,
 	MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_AVAIL_IDX       = (u64)1 << 7,
 	MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_USED_IDX        = (u64)1 << 8,
+	MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_MKEY            = (u64)1 << 11,
 	MLX5_VIRTQ_MODIFY_MASK_DESC_GROUP_MKEY          = (u64)1 << 14,
 };
 
-- 
cgit v1.2.3


From 3e999770ac1c7c31a70685dd5b88e89473509e9c Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Tue, 9 Jan 2024 17:59:22 +0100
Subject: PM: sleep: Restore asynchronous device resume optimization

Before commit 7839d0078e0d ("PM: sleep: Fix possible deadlocks in core
system-wide PM code"), the resume of devices that were allowed to resume
asynchronously was scheduled before starting the resume of the other
devices, so the former did not have to wait for the latter unless
functional dependencies were present.

Commit 7839d0078e0d removed that optimization in order to address a
correctness issue, but it can be restored with the help of a new device
power management flag, so do that now.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
---
 drivers/base/power/main.c | 117 +++++++++++++++++++++++++---------------------
 include/linux/pm.h        |   1 +
 2 files changed, 65 insertions(+), 53 deletions(-)

(limited to 'include')

diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 9c5a5f4dba5a..fadcd0379dc2 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -579,7 +579,7 @@ bool dev_pm_skip_resume(struct device *dev)
 }
 
 /**
- * __device_resume_noirq - Execute a "noirq resume" callback for given device.
+ * device_resume_noirq - Execute a "noirq resume" callback for given device.
  * @dev: Device to handle.
  * @state: PM transition of the system being carried out.
  * @async: If true, the device is being resumed asynchronously.
@@ -587,7 +587,7 @@ bool dev_pm_skip_resume(struct device *dev)
  * The driver of @dev will not receive interrupts while this function is being
  * executed.
  */
-static void __device_resume_noirq(struct device *dev, pm_message_t state, bool async)
+static void device_resume_noirq(struct device *dev, pm_message_t state, bool async)
 {
 	pm_callback_t callback = NULL;
 	const char *info = NULL;
@@ -674,16 +674,22 @@ static bool dpm_async_fn(struct device *dev, async_func_t func)
 {
 	reinit_completion(&dev->power.completion);
 
-	if (!is_async(dev))
-		return false;
-
-	get_device(dev);
+	if (is_async(dev)) {
+		dev->power.async_in_progress = true;
 
-	if (async_schedule_dev_nocall(func, dev))
-		return true;
+		get_device(dev);
 
-	put_device(dev);
+		if (async_schedule_dev_nocall(func, dev))
+			return true;
 
+		put_device(dev);
+	}
+	/*
+	 * Because async_schedule_dev_nocall() above has returned false or it
+	 * has not been called at all, func() is not running and it is safe to
+	 * update the async_in_progress flag without extra synchronization.
+	 */
+	dev->power.async_in_progress = false;
 	return false;
 }
 
@@ -691,18 +697,10 @@ static void async_resume_noirq(void *data, async_cookie_t cookie)
 {
 	struct device *dev = data;
 
-	__device_resume_noirq(dev, pm_transition, true);
+	device_resume_noirq(dev, pm_transition, true);
 	put_device(dev);
 }
 
-static void device_resume_noirq(struct device *dev)
-{
-	if (dpm_async_fn(dev, async_resume_noirq))
-		return;
-
-	__device_resume_noirq(dev, pm_transition, false);
-}
-
 static void dpm_noirq_resume_devices(pm_message_t state)
 {
 	struct device *dev;
@@ -712,18 +710,28 @@ static void dpm_noirq_resume_devices(pm_message_t state)
 	mutex_lock(&dpm_list_mtx);
 	pm_transition = state;
 
+	/*
+	 * Trigger the resume of "async" devices upfront so they don't have to
+	 * wait for the "non-async" ones they don't depend on.
+	 */
+	list_for_each_entry(dev, &dpm_noirq_list, power.entry)
+		dpm_async_fn(dev, async_resume_noirq);
+
 	while (!list_empty(&dpm_noirq_list)) {
 		dev = to_device(dpm_noirq_list.next);
-		get_device(dev);
 		list_move_tail(&dev->power.entry, &dpm_late_early_list);
 
-		mutex_unlock(&dpm_list_mtx);
+		if (!dev->power.async_in_progress) {
+			get_device(dev);
 
-		device_resume_noirq(dev);
+			mutex_unlock(&dpm_list_mtx);
 
-		put_device(dev);
+			device_resume_noirq(dev, state, false);
 
-		mutex_lock(&dpm_list_mtx);
+			put_device(dev);
+
+			mutex_lock(&dpm_list_mtx);
+		}
 	}
 	mutex_unlock(&dpm_list_mtx);
 	async_synchronize_full();
@@ -747,14 +755,14 @@ void dpm_resume_noirq(pm_message_t state)
 }
 
 /**
- * __device_resume_early - Execute an "early resume" callback for given device.
+ * device_resume_early - Execute an "early resume" callback for given device.
  * @dev: Device to handle.
  * @state: PM transition of the system being carried out.
  * @async: If true, the device is being resumed asynchronously.
  *
  * Runtime PM is disabled for @dev while this function is being executed.
  */
-static void __device_resume_early(struct device *dev, pm_message_t state, bool async)
+static void device_resume_early(struct device *dev, pm_message_t state, bool async)
 {
 	pm_callback_t callback = NULL;
 	const char *info = NULL;
@@ -820,18 +828,10 @@ static void async_resume_early(void *data, async_cookie_t cookie)
 {
 	struct device *dev = data;
 
-	__device_resume_early(dev, pm_transition, true);
+	device_resume_early(dev, pm_transition, true);
 	put_device(dev);
 }
 
-static void device_resume_early(struct device *dev)
-{
-	if (dpm_async_fn(dev, async_resume_early))
-		return;
-
-	__device_resume_early(dev, pm_transition, false);
-}
-
 /**
  * dpm_resume_early - Execute "early resume" callbacks for all devices.
  * @state: PM transition of the system being carried out.
@@ -845,18 +845,28 @@ void dpm_resume_early(pm_message_t state)
 	mutex_lock(&dpm_list_mtx);
 	pm_transition = state;
 
+	/*
+	 * Trigger the resume of "async" devices upfront so they don't have to
+	 * wait for the "non-async" ones they don't depend on.
+	 */
+	list_for_each_entry(dev, &dpm_late_early_list, power.entry)
+		dpm_async_fn(dev, async_resume_early);
+
 	while (!list_empty(&dpm_late_early_list)) {
 		dev = to_device(dpm_late_early_list.next);
-		get_device(dev);
 		list_move_tail(&dev->power.entry, &dpm_suspended_list);
 
-		mutex_unlock(&dpm_list_mtx);
+		if (!dev->power.async_in_progress) {
+			get_device(dev);
 
-		device_resume_early(dev);
+			mutex_unlock(&dpm_list_mtx);
 
-		put_device(dev);
+			device_resume_early(dev, state, false);
 
-		mutex_lock(&dpm_list_mtx);
+			put_device(dev);
+
+			mutex_lock(&dpm_list_mtx);
+		}
 	}
 	mutex_unlock(&dpm_list_mtx);
 	async_synchronize_full();
@@ -876,12 +886,12 @@ void dpm_resume_start(pm_message_t state)
 EXPORT_SYMBOL_GPL(dpm_resume_start);
 
 /**
- * __device_resume - Execute "resume" callbacks for given device.
+ * device_resume - Execute "resume" callbacks for given device.
  * @dev: Device to handle.
  * @state: PM transition of the system being carried out.
  * @async: If true, the device is being resumed asynchronously.
  */
-static void __device_resume(struct device *dev, pm_message_t state, bool async)
+static void device_resume(struct device *dev, pm_message_t state, bool async)
 {
 	pm_callback_t callback = NULL;
 	const char *info = NULL;
@@ -975,18 +985,10 @@ static void async_resume(void *data, async_cookie_t cookie)
 {
 	struct device *dev = data;
 
-	__device_resume(dev, pm_transition, true);
+	device_resume(dev, pm_transition, true);
 	put_device(dev);
 }
 
-static void device_resume(struct device *dev)
-{
-	if (dpm_async_fn(dev, async_resume))
-		return;
-
-	__device_resume(dev, pm_transition, false);
-}
-
 /**
  * dpm_resume - Execute "resume" callbacks for non-sysdev devices.
  * @state: PM transition of the system being carried out.
@@ -1006,16 +1008,25 @@ void dpm_resume(pm_message_t state)
 	pm_transition = state;
 	async_error = 0;
 
+	/*
+	 * Trigger the resume of "async" devices upfront so they don't have to
+	 * wait for the "non-async" ones they don't depend on.
+	 */
+	list_for_each_entry(dev, &dpm_suspended_list, power.entry)
+		dpm_async_fn(dev, async_resume);
+
 	while (!list_empty(&dpm_suspended_list)) {
 		dev = to_device(dpm_suspended_list.next);
 
 		get_device(dev);
 
-		mutex_unlock(&dpm_list_mtx);
+		if (!dev->power.async_in_progress) {
+			mutex_unlock(&dpm_list_mtx);
 
-		device_resume(dev);
+			device_resume(dev, state, false);
 
-		mutex_lock(&dpm_list_mtx);
+			mutex_lock(&dpm_list_mtx);
+		}
 
 		if (!list_empty(&dev->power.entry))
 			list_move_tail(&dev->power.entry, &dpm_prepared_list);
diff --git a/include/linux/pm.h b/include/linux/pm.h
index 92a4f69de0e8..a2f3e53a8196 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -681,6 +681,7 @@ struct dev_pm_info {
 	bool			wakeup_path:1;
 	bool			syscore:1;
 	bool			no_pm_callbacks:1;	/* Owned by the PM core */
+	bool			async_in_progress:1;	/* Owned by the PM core */
 	unsigned int		must_resume:1;	/* Owned by the PM core */
 	unsigned int		may_skip_resume:1;	/* Set by subsystems */
 #else
-- 
cgit v1.2.3


From f35b88b66fbb5c90298ce3aa483b8a2cf1f39ad0 Mon Sep 17 00:00:00 2001
From: Lu Baolu <baolu.lu@linux.intel.com>
Date: Wed, 10 Jan 2024 20:10:08 -0800
Subject: iommu: Add cache_invalidate_user op

The updates of the PTEs in the nested page table will be propagated to the
hardware caches.

Add a new domain op cache_invalidate_user() for the userspace to flush the
hardware caches for a nested domain through iommufd. No wrapper for it, as
it's only supposed to be used by iommufd. Then, pass in invalidation
requests in form of a user data array containing a number of invalidation
data entries.

Link: https://lore.kernel.org/r/20240111041015.47920-2-yi.l.liu@intel.com
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Yi Liu <yi.l.liu@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 include/linux/iommu.h | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

(limited to 'include')

diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 6291aa7b079b..93c0d12dd047 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -284,6 +284,23 @@ struct iommu_user_data {
 	size_t len;
 };
 
+/**
+ * struct iommu_user_data_array - iommu driver specific user space data array
+ * @type: The data type of all the entries in the user buffer array
+ * @uptr: Pointer to the user buffer array
+ * @entry_len: The fixed-width length of an entry in the array, in bytes
+ * @entry_num: The number of total entries in the array
+ *
+ * The user buffer includes an array of requests with format defined in
+ * include/uapi/linux/iommufd.h
+ */
+struct iommu_user_data_array {
+	unsigned int type;
+	void __user *uptr;
+	size_t entry_len;
+	u32 entry_num;
+};
+
 /**
  * __iommu_copy_struct_from_user - Copy iommu driver specific user space data
  * @dst_data: Pointer to an iommu driver specific user data that is defined in
@@ -440,6 +457,13 @@ struct iommu_ops {
  * @iotlb_sync_map: Sync mappings created recently using @map to the hardware
  * @iotlb_sync: Flush all queued ranges from the hardware TLBs and empty flush
  *            queue
+ * @cache_invalidate_user: Flush hardware cache for user space IO page table.
+ *                         The @domain must be IOMMU_DOMAIN_NESTED. The @array
+ *                         passes in the cache invalidation requests, in form
+ *                         of a driver data structure. The driver must update
+ *                         array->entry_num to report the number of handled
+ *                         invalidation requests. The driver data structure
+ *                         must be defined in include/uapi/linux/iommufd.h
  * @iova_to_phys: translate iova to physical address
  * @enforce_cache_coherency: Prevent any kind of DMA from bypassing IOMMU_CACHE,
  *                           including no-snoop TLPs on PCIe or other platform
@@ -465,6 +489,8 @@ struct iommu_domain_ops {
 			      size_t size);
 	void (*iotlb_sync)(struct iommu_domain *domain,
 			   struct iommu_iotlb_gather *iotlb_gather);
+	int (*cache_invalidate_user)(struct iommu_domain *domain,
+				     struct iommu_user_data_array *array);
 
 	phys_addr_t (*iova_to_phys)(struct iommu_domain *domain,
 				    dma_addr_t iova);
-- 
cgit v1.2.3


From 8c6eabae3807e048b9f17733af5e20500fbf858c Mon Sep 17 00:00:00 2001
From: Yi Liu <yi.l.liu@intel.com>
Date: Wed, 10 Jan 2024 20:10:09 -0800
Subject: iommufd: Add IOMMU_HWPT_INVALIDATE

In nested translation, the stage-1 page table is user-managed but cached
by the IOMMU hardware, so an update on present page table entries in the
stage-1 page table should be followed with a cache invalidation.

Add an IOMMU_HWPT_INVALIDATE ioctl to support such a cache invalidation.
It takes hwpt_id to specify the iommu_domain, and a multi-entry array to
support multiple invalidation data in one ioctl.

enum iommu_hwpt_invalidate_data_type is defined to tag the data type of
the entries in the multi-entry array.

Link: https://lore.kernel.org/r/20240111041015.47920-3-yi.l.liu@intel.com
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Co-developed-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Yi Liu <yi.l.liu@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/iommu/iommufd/hw_pagetable.c    | 41 +++++++++++++++++++++++++++++++
 drivers/iommu/iommufd/iommufd_private.h | 10 ++++++++
 drivers/iommu/iommufd/main.c            |  3 +++
 include/uapi/linux/iommufd.h            | 43 +++++++++++++++++++++++++++++++++
 4 files changed, 97 insertions(+)

(limited to 'include')

diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c
index cbb5df0a6c32..4e8711f19f72 100644
--- a/drivers/iommu/iommufd/hw_pagetable.c
+++ b/drivers/iommu/iommufd/hw_pagetable.c
@@ -371,3 +371,44 @@ int iommufd_hwpt_get_dirty_bitmap(struct iommufd_ucmd *ucmd)
 	iommufd_put_object(ucmd->ictx, &hwpt_paging->common.obj);
 	return rc;
 }
+
+int iommufd_hwpt_invalidate(struct iommufd_ucmd *ucmd)
+{
+	struct iommu_hwpt_invalidate *cmd = ucmd->cmd;
+	struct iommu_user_data_array data_array = {
+		.type = cmd->data_type,
+		.uptr = u64_to_user_ptr(cmd->data_uptr),
+		.entry_len = cmd->entry_len,
+		.entry_num = cmd->entry_num,
+	};
+	struct iommufd_hw_pagetable *hwpt;
+	u32 done_num = 0;
+	int rc;
+
+	if (cmd->__reserved) {
+		rc = -EOPNOTSUPP;
+		goto out;
+	}
+
+	if (cmd->entry_num && (!cmd->data_uptr || !cmd->entry_len)) {
+		rc = -EINVAL;
+		goto out;
+	}
+
+	hwpt = iommufd_get_hwpt_nested(ucmd, cmd->hwpt_id);
+	if (IS_ERR(hwpt)) {
+		rc = PTR_ERR(hwpt);
+		goto out;
+	}
+
+	rc = hwpt->domain->ops->cache_invalidate_user(hwpt->domain,
+						      &data_array);
+	done_num = data_array.entry_num;
+
+	iommufd_put_object(ucmd->ictx, &hwpt->obj);
+out:
+	cmd->entry_num = done_num;
+	if (iommufd_ucmd_respond(ucmd, sizeof(*cmd)))
+		return -EFAULT;
+	return rc;
+}
diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h
index abae041e256f..991f864d1f9b 100644
--- a/drivers/iommu/iommufd/iommufd_private.h
+++ b/drivers/iommu/iommufd/iommufd_private.h
@@ -328,6 +328,15 @@ iommufd_get_hwpt_paging(struct iommufd_ucmd *ucmd, u32 id)
 					       IOMMUFD_OBJ_HWPT_PAGING),
 			    struct iommufd_hwpt_paging, common.obj);
 }
+
+static inline struct iommufd_hw_pagetable *
+iommufd_get_hwpt_nested(struct iommufd_ucmd *ucmd, u32 id)
+{
+	return container_of(iommufd_get_object(ucmd->ictx, id,
+					       IOMMUFD_OBJ_HWPT_NESTED),
+			    struct iommufd_hw_pagetable, obj);
+}
+
 int iommufd_hwpt_set_dirty_tracking(struct iommufd_ucmd *ucmd);
 int iommufd_hwpt_get_dirty_bitmap(struct iommufd_ucmd *ucmd);
 
@@ -345,6 +354,7 @@ void iommufd_hwpt_paging_abort(struct iommufd_object *obj);
 void iommufd_hwpt_nested_destroy(struct iommufd_object *obj);
 void iommufd_hwpt_nested_abort(struct iommufd_object *obj);
 int iommufd_hwpt_alloc(struct iommufd_ucmd *ucmd);
+int iommufd_hwpt_invalidate(struct iommufd_ucmd *ucmd);
 
 static inline void iommufd_hw_pagetable_put(struct iommufd_ctx *ictx,
 					    struct iommufd_hw_pagetable *hwpt)
diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c
index c9091e46d208..39b32932c61e 100644
--- a/drivers/iommu/iommufd/main.c
+++ b/drivers/iommu/iommufd/main.c
@@ -322,6 +322,7 @@ union ucmd_buffer {
 	struct iommu_hw_info info;
 	struct iommu_hwpt_alloc hwpt;
 	struct iommu_hwpt_get_dirty_bitmap get_dirty_bitmap;
+	struct iommu_hwpt_invalidate cache;
 	struct iommu_hwpt_set_dirty_tracking set_dirty_tracking;
 	struct iommu_ioas_alloc alloc;
 	struct iommu_ioas_allow_iovas allow_iovas;
@@ -360,6 +361,8 @@ static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = {
 		 __reserved),
 	IOCTL_OP(IOMMU_HWPT_GET_DIRTY_BITMAP, iommufd_hwpt_get_dirty_bitmap,
 		 struct iommu_hwpt_get_dirty_bitmap, data),
+	IOCTL_OP(IOMMU_HWPT_INVALIDATE, iommufd_hwpt_invalidate,
+		 struct iommu_hwpt_invalidate, __reserved),
 	IOCTL_OP(IOMMU_HWPT_SET_DIRTY_TRACKING, iommufd_hwpt_set_dirty_tracking,
 		 struct iommu_hwpt_set_dirty_tracking, __reserved),
 	IOCTL_OP(IOMMU_IOAS_ALLOC, iommufd_ioas_alloc_ioctl,
diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h
index 0b2bc6252e2c..824560c50ec6 100644
--- a/include/uapi/linux/iommufd.h
+++ b/include/uapi/linux/iommufd.h
@@ -49,6 +49,7 @@ enum {
 	IOMMUFD_CMD_GET_HW_INFO,
 	IOMMUFD_CMD_HWPT_SET_DIRTY_TRACKING,
 	IOMMUFD_CMD_HWPT_GET_DIRTY_BITMAP,
+	IOMMUFD_CMD_HWPT_INVALIDATE,
 };
 
 /**
@@ -613,4 +614,46 @@ struct iommu_hwpt_get_dirty_bitmap {
 #define IOMMU_HWPT_GET_DIRTY_BITMAP _IO(IOMMUFD_TYPE, \
 					IOMMUFD_CMD_HWPT_GET_DIRTY_BITMAP)
 
+/**
+ * enum iommu_hwpt_invalidate_data_type - IOMMU HWPT Cache Invalidation
+ *                                        Data Type
+ * @IOMMU_HWPT_INVALIDATE_DATA_VTD_S1: Invalidation data for VTD_S1
+ */
+enum iommu_hwpt_invalidate_data_type {
+	IOMMU_HWPT_INVALIDATE_DATA_VTD_S1,
+};
+
+/**
+ * struct iommu_hwpt_invalidate - ioctl(IOMMU_HWPT_INVALIDATE)
+ * @size: sizeof(struct iommu_hwpt_invalidate)
+ * @hwpt_id: ID of a nested HWPT for cache invalidation
+ * @data_uptr: User pointer to an array of driver-specific cache invalidation
+ *             data.
+ * @data_type: One of enum iommu_hwpt_invalidate_data_type, defining the data
+ *             type of all the entries in the invalidation request array. It
+ *             should be a type supported by the hwpt pointed by @hwpt_id.
+ * @entry_len: Length (in bytes) of a request entry in the request array
+ * @entry_num: Input the number of cache invalidation requests in the array.
+ *             Output the number of requests successfully handled by kernel.
+ * @__reserved: Must be 0.
+ *
+ * Invalidate the iommu cache for user-managed page table. Modifications on a
+ * user-managed page table should be followed by this operation to sync cache.
+ * Each ioctl can support one or more cache invalidation requests in the array
+ * that has a total size of @entry_len * @entry_num.
+ *
+ * An empty invalidation request array by setting @entry_num==0 is allowed, and
+ * @entry_len and @data_uptr would be ignored in this case. This can be used to
+ * check if the given @data_type is supported or not by kernel.
+ */
+struct iommu_hwpt_invalidate {
+	__u32 size;
+	__u32 hwpt_id;
+	__aligned_u64 data_uptr;
+	__u32 data_type;
+	__u32 entry_len;
+	__u32 entry_num;
+	__u32 __reserved;
+};
+#define IOMMU_HWPT_INVALIDATE _IO(IOMMUFD_TYPE, IOMMUFD_CMD_HWPT_INVALIDATE)
 #endif
-- 
cgit v1.2.3


From 77785117f9c73fd71a440a5ac86dd80752967adc Mon Sep 17 00:00:00 2001
From: Nicolin Chen <nicolinc@nvidia.com>
Date: Wed, 10 Jan 2024 20:10:10 -0800
Subject: iommu: Add iommu_copy_struct_from_user_array helper

Wrap up the data pointer/num sanity and __iommu_copy_struct_from_user()
call for iommu drivers to copy driver specific data at a specific location
in the struct iommu_user_data_array.

And expect it to be used in cache_invalidate_user ops for example.

Link: https://lore.kernel.org/r/20240111041015.47920-4-yi.l.liu@intel.com
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Co-developed-by: Yi Liu <yi.l.liu@intel.com>
Signed-off-by: Yi Liu <yi.l.liu@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 include/linux/iommu.h | 51 +++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 51 insertions(+)

(limited to 'include')

diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 93c0d12dd047..9dbadf74a3a1 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -341,6 +341,57 @@ static inline int __iommu_copy_struct_from_user(
 				      sizeof(*kdst),                      \
 				      offsetofend(typeof(*kdst), min_last))
 
+/**
+ * __iommu_copy_struct_from_user_array - Copy iommu driver specific user space
+ *                                       data from an iommu_user_data_array
+ * @dst_data: Pointer to an iommu driver specific user data that is defined in
+ *            include/uapi/linux/iommufd.h
+ * @src_array: Pointer to a struct iommu_user_data_array for a user space array
+ * @data_type: The data type of the @dst_data. Must match with @src_array.type
+ * @index: Index to the location in the array to copy user data from
+ * @data_len: Length of current user data structure, i.e. sizeof(struct _dst)
+ * @min_len: Initial length of user data structure for backward compatibility.
+ *           This should be offsetofend using the last member in the user data
+ *           struct that was initially added to include/uapi/linux/iommufd.h
+ */
+static inline int __iommu_copy_struct_from_user_array(
+	void *dst_data, const struct iommu_user_data_array *src_array,
+	unsigned int data_type, unsigned int index, size_t data_len,
+	size_t min_len)
+{
+	struct iommu_user_data src_data;
+
+	if (WARN_ON(!src_array || index >= src_array->entry_num))
+		return -EINVAL;
+	if (!src_array->entry_num)
+		return -EINVAL;
+	src_data.uptr = src_array->uptr + src_array->entry_len * index;
+	src_data.len = src_array->entry_len;
+	src_data.type = src_array->type;
+
+	return __iommu_copy_struct_from_user(dst_data, &src_data, data_type,
+					     data_len, min_len);
+}
+
+/**
+ * iommu_copy_struct_from_user_array - Copy iommu driver specific user space
+ *                                     data from an iommu_user_data_array
+ * @kdst: Pointer to an iommu driver specific user data that is defined in
+ *        include/uapi/linux/iommufd.h
+ * @user_array: Pointer to a struct iommu_user_data_array for a user space
+ *              array
+ * @data_type: The data type of the @kdst. Must match with @user_array->type
+ * @index: Index to the location in the array to copy user data from
+ * @min_last: The last member of the data structure @kdst points in the
+ *            initial version.
+ * Return 0 for success, otherwise -error.
+ */
+#define iommu_copy_struct_from_user_array(kdst, user_array, data_type, index, \
+					  min_last)                           \
+	__iommu_copy_struct_from_user_array(                                  \
+		kdst, user_array, data_type, index, sizeof(*(kdst)),          \
+		offsetofend(typeof(*(kdst)), min_last))
+
 /**
  * struct iommu_ops - iommu ops and capabilities
  * @capable: check capability
-- 
cgit v1.2.3


From 393a5778b72a7b551493d0fd3fbe0282154058fe Mon Sep 17 00:00:00 2001
From: Yi Liu <yi.l.liu@intel.com>
Date: Wed, 10 Jan 2024 20:10:14 -0800
Subject: iommufd: Add data structure for Intel VT-d stage-1 cache invalidation

This adds the data structure invalidating caches for the nested domain
allocated with IOMMU_HWPT_DATA_VTD_S1 type.

Link: https://lore.kernel.org/r/20240111041015.47920-8-yi.l.liu@intel.com
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Yi Liu <yi.l.liu@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 include/uapi/linux/iommufd.h | 36 ++++++++++++++++++++++++++++++++++++
 1 file changed, 36 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h
index 824560c50ec6..1dfeaa2e649e 100644
--- a/include/uapi/linux/iommufd.h
+++ b/include/uapi/linux/iommufd.h
@@ -623,6 +623,42 @@ enum iommu_hwpt_invalidate_data_type {
 	IOMMU_HWPT_INVALIDATE_DATA_VTD_S1,
 };
 
+/**
+ * enum iommu_hwpt_vtd_s1_invalidate_flags - Flags for Intel VT-d
+ *                                           stage-1 cache invalidation
+ * @IOMMU_VTD_INV_FLAGS_LEAF: Indicates whether the invalidation applies
+ *                            to all-levels page structure cache or just
+ *                            the leaf PTE cache.
+ */
+enum iommu_hwpt_vtd_s1_invalidate_flags {
+	IOMMU_VTD_INV_FLAGS_LEAF = 1 << 0,
+};
+
+/**
+ * struct iommu_hwpt_vtd_s1_invalidate - Intel VT-d cache invalidation
+ *                                       (IOMMU_HWPT_INVALIDATE_DATA_VTD_S1)
+ * @addr: The start address of the range to be invalidated. It needs to
+ *        be 4KB aligned.
+ * @npages: Number of contiguous 4K pages to be invalidated.
+ * @flags: Combination of enum iommu_hwpt_vtd_s1_invalidate_flags
+ * @__reserved: Must be 0
+ *
+ * The Intel VT-d specific invalidation data for user-managed stage-1 cache
+ * invalidation in nested translation. Userspace uses this structure to
+ * tell the impacted cache scope after modifying the stage-1 page table.
+ *
+ * Invalidating all the caches related to the page table by setting @addr
+ * to be 0 and @npages to be U64_MAX.
+ *
+ * The device TLB will be invalidated automatically if ATS is enabled.
+ */
+struct iommu_hwpt_vtd_s1_invalidate {
+	__aligned_u64 addr;
+	__aligned_u64 npages;
+	__u32 flags;
+	__u32 __reserved;
+};
+
 /**
  * struct iommu_hwpt_invalidate - ioctl(IOMMU_HWPT_INVALIDATE)
  * @size: sizeof(struct iommu_hwpt_invalidate)
-- 
cgit v1.2.3


From dee56ccb468a832074397fdbf22bbd9bf6d710aa Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Tue, 12 Dec 2023 15:18:02 +0100
Subject: fbdev: amba-clcd: Delete the old CLCD driver

We have managed to ascertain that all users of the old FBDEV
code that are out of tree are now gone.

The new DRM driver can be found in drivers/gpu/drm/pl111/.

The remaining out of tree user was the ARM FVP emulation
platform, running Android. Thanks to changes in Android
versions 13 and 14, Android can now use the DRM driver when
being emulated under FVP. Some final patches are being put
in place to make it fully featured.

This is essentially a revert of the partial revert in
commit 112c35237c72 ("Partially revert "video: fbdev: amba-clcd: Retire elder CLCD driver"")

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 MAINTAINERS                     |   5 -
 drivers/video/fbdev/Kconfig     |  18 -
 drivers/video/fbdev/Makefile    |   1 -
 drivers/video/fbdev/amba-clcd.c | 984 ----------------------------------------
 include/linux/amba/clcd-regs.h  |  87 ----
 include/linux/amba/clcd.h       | 290 ------------
 6 files changed, 1385 deletions(-)
 delete mode 100644 drivers/video/fbdev/amba-clcd.c
 delete mode 100644 include/linux/amba/clcd-regs.h
 delete mode 100644 include/linux/amba/clcd.h

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index cc92b10a4cad..d3054a00c8e3 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1684,11 +1684,6 @@ S:	Odd Fixes
 F:	drivers/amba/
 F:	include/linux/amba/bus.h
 
-ARM PRIMECELL CLCD PL110 DRIVER
-M:	Russell King <linux@armlinux.org.uk>
-S:	Odd Fixes
-F:	drivers/video/fbdev/amba-clcd.*
-
 ARM PRIMECELL KMI PL050 DRIVER
 M:	Russell King <linux@armlinux.org.uk>
 S:	Odd Fixes
diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig
index b65f20006bd7..3cdd2d50f59b 100644
--- a/drivers/video/fbdev/Kconfig
+++ b/drivers/video/fbdev/Kconfig
@@ -116,24 +116,6 @@ config FB_PM2_FIFO_DISCONNECT
 	help
 	  Support the Permedia2 FIFO disconnect feature.
 
-config FB_ARMCLCD
-	tristate "ARM PrimeCell PL110 support"
-	depends on ARM || ARM64 || COMPILE_TEST
-	depends on FB && ARM_AMBA && HAS_IOMEM
-	select FB_IOMEM_HELPERS
-	select FB_MODE_HELPERS if OF
-	select VIDEOMODE_HELPERS if OF
-	select BACKLIGHT_CLASS_DEVICE if OF
-	help
-	  This framebuffer device driver is for the ARM PrimeCell PL110
-	  Colour LCD controller.  ARM PrimeCells provide the building
-	  blocks for System on a Chip devices.
-
-	  If you want to compile this as a module (=code which can be
-	  inserted into and removed from the running kernel), say M
-	  here and read <file:Documentation/kbuild/modules.rst>.  The module
-	  will be called amba-clcd.
-
 config FB_ACORN
 	bool "Acorn VIDC support"
 	depends on (FB = y) && ARM && ARCH_ACORN
diff --git a/drivers/video/fbdev/Makefile b/drivers/video/fbdev/Makefile
index 7cf7b0af1465..3eecd51267fa 100644
--- a/drivers/video/fbdev/Makefile
+++ b/drivers/video/fbdev/Makefile
@@ -74,7 +74,6 @@ obj-$(CONFIG_FB_HIT)              += hitfb.o
 obj-$(CONFIG_FB_ATMEL)		  += atmel_lcdfb.o
 obj-$(CONFIG_FB_PVR2)             += pvr2fb.o
 obj-$(CONFIG_FB_VOODOO1)          += sstfb.o
-obj-$(CONFIG_FB_ARMCLCD)	  += amba-clcd.o
 obj-$(CONFIG_FB_GOLDFISH)         += goldfishfb.o
 obj-$(CONFIG_FB_68328)            += 68328fb.o
 obj-$(CONFIG_FB_GBE)              += gbefb.o
diff --git a/drivers/video/fbdev/amba-clcd.c b/drivers/video/fbdev/amba-clcd.c
deleted file mode 100644
index 0399db369e70..000000000000
--- a/drivers/video/fbdev/amba-clcd.c
+++ /dev/null
@@ -1,984 +0,0 @@
-/*
- *  linux/drivers/video/amba-clcd.c
- *
- * Copyright (C) 2001 ARM Limited, by David A Rusling
- * Updated to 2.5, Deep Blue Solutions Ltd.
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file COPYING in the main directory of this archive
- * for more details.
- *
- *  ARM PrimeCell PL110 Color LCD Controller
- */
-#include <linux/amba/bus.h>
-#include <linux/amba/clcd.h>
-#include <linux/backlight.h>
-#include <linux/clk.h>
-#include <linux/delay.h>
-#include <linux/dma-mapping.h>
-#include <linux/fb.h>
-#include <linux/init.h>
-#include <linux/ioport.h>
-#include <linux/list.h>
-#include <linux/mm.h>
-#include <linux/module.h>
-#include <linux/of_address.h>
-#include <linux/of_graph.h>
-#include <linux/slab.h>
-#include <linux/string.h>
-#include <video/display_timing.h>
-#include <video/of_display_timing.h>
-#include <video/videomode.h>
-
-#define to_clcd(info)	container_of(info, struct clcd_fb, fb)
-
-/* This is limited to 16 characters when displayed by X startup */
-static const char *clcd_name = "CLCD FB";
-
-static inline void clcdfb_set_start(struct clcd_fb *fb)
-{
-	unsigned long ustart = fb->fb.fix.smem_start;
-	unsigned long lstart;
-
-	ustart += fb->fb.var.yoffset * fb->fb.fix.line_length;
-	lstart = ustart + fb->fb.var.yres * fb->fb.fix.line_length / 2;
-
-	writel(ustart, fb->regs + CLCD_UBAS);
-	writel(lstart, fb->regs + CLCD_LBAS);
-}
-
-static void clcdfb_disable(struct clcd_fb *fb)
-{
-	u32 val;
-
-	if (fb->board->disable)
-		fb->board->disable(fb);
-
-	if (fb->panel->backlight) {
-		fb->panel->backlight->props.power = FB_BLANK_POWERDOWN;
-		backlight_update_status(fb->panel->backlight);
-	}
-
-	val = readl(fb->regs + fb->off_cntl);
-	if (val & CNTL_LCDPWR) {
-		val &= ~CNTL_LCDPWR;
-		writel(val, fb->regs + fb->off_cntl);
-
-		msleep(20);
-	}
-	if (val & CNTL_LCDEN) {
-		val &= ~CNTL_LCDEN;
-		writel(val, fb->regs + fb->off_cntl);
-	}
-
-	/*
-	 * Disable CLCD clock source.
-	 */
-	if (fb->clk_enabled) {
-		fb->clk_enabled = false;
-		clk_disable(fb->clk);
-	}
-}
-
-static void clcdfb_enable(struct clcd_fb *fb, u32 cntl)
-{
-	/*
-	 * Enable the CLCD clock source.
-	 */
-	if (!fb->clk_enabled) {
-		fb->clk_enabled = true;
-		clk_enable(fb->clk);
-	}
-
-	/*
-	 * Bring up by first enabling..
-	 */
-	cntl |= CNTL_LCDEN;
-	writel(cntl, fb->regs + fb->off_cntl);
-
-	msleep(20);
-
-	/*
-	 * and now apply power.
-	 */
-	cntl |= CNTL_LCDPWR;
-	writel(cntl, fb->regs + fb->off_cntl);
-
-	/*
-	 * Turn on backlight
-	 */
-	if (fb->panel->backlight) {
-		fb->panel->backlight->props.power = FB_BLANK_UNBLANK;
-		backlight_update_status(fb->panel->backlight);
-	}
-
-	/*
-	 * finally, enable the interface.
-	 */
-	if (fb->board->enable)
-		fb->board->enable(fb);
-}
-
-static int
-clcdfb_set_bitfields(struct clcd_fb *fb, struct fb_var_screeninfo *var)
-{
-	u32 caps;
-	int ret = 0;
-
-	if (fb->panel->caps && fb->board->caps)
-		caps = fb->panel->caps & fb->board->caps;
-	else {
-		/* Old way of specifying what can be used */
-		caps = fb->panel->cntl & CNTL_BGR ?
-			CLCD_CAP_BGR : CLCD_CAP_RGB;
-		/* But mask out 444 modes as they weren't supported */
-		caps &= ~CLCD_CAP_444;
-	}
-
-	/* Only TFT panels can do RGB888/BGR888 */
-	if (!(fb->panel->cntl & CNTL_LCDTFT))
-		caps &= ~CLCD_CAP_888;
-
-	memset(&var->transp, 0, sizeof(var->transp));
-
-	var->red.msb_right = 0;
-	var->green.msb_right = 0;
-	var->blue.msb_right = 0;
-
-	switch (var->bits_per_pixel) {
-	case 1:
-	case 2:
-	case 4:
-	case 8:
-		/* If we can't do 5551, reject */
-		caps &= CLCD_CAP_5551;
-		if (!caps) {
-			ret = -EINVAL;
-			break;
-		}
-
-		var->red.length		= var->bits_per_pixel;
-		var->red.offset		= 0;
-		var->green.length	= var->bits_per_pixel;
-		var->green.offset	= 0;
-		var->blue.length	= var->bits_per_pixel;
-		var->blue.offset	= 0;
-		break;
-
-	case 16:
-		/* If we can't do 444, 5551 or 565, reject */
-		if (!(caps & (CLCD_CAP_444 | CLCD_CAP_5551 | CLCD_CAP_565))) {
-			ret = -EINVAL;
-			break;
-		}
-
-		/*
-		 * Green length can be 4, 5 or 6 depending whether
-		 * we're operating in 444, 5551 or 565 mode.
-		 */
-		if (var->green.length == 4 && caps & CLCD_CAP_444)
-			caps &= CLCD_CAP_444;
-		if (var->green.length == 5 && caps & CLCD_CAP_5551)
-			caps &= CLCD_CAP_5551;
-		else if (var->green.length == 6 && caps & CLCD_CAP_565)
-			caps &= CLCD_CAP_565;
-		else {
-			/*
-			 * PL110 officially only supports RGB555,
-			 * but may be wired up to allow RGB565.
-			 */
-			if (caps & CLCD_CAP_565) {
-				var->green.length = 6;
-				caps &= CLCD_CAP_565;
-			} else if (caps & CLCD_CAP_5551) {
-				var->green.length = 5;
-				caps &= CLCD_CAP_5551;
-			} else {
-				var->green.length = 4;
-				caps &= CLCD_CAP_444;
-			}
-		}
-
-		if (var->green.length >= 5) {
-			var->red.length = 5;
-			var->blue.length = 5;
-		} else {
-			var->red.length = 4;
-			var->blue.length = 4;
-		}
-		break;
-	case 32:
-		/* If we can't do 888, reject */
-		caps &= CLCD_CAP_888;
-		if (!caps) {
-			ret = -EINVAL;
-			break;
-		}
-
-		var->red.length = 8;
-		var->green.length = 8;
-		var->blue.length = 8;
-		break;
-	default:
-		ret = -EINVAL;
-		break;
-	}
-
-	/*
-	 * >= 16bpp displays have separate colour component bitfields
-	 * encoded in the pixel data.  Calculate their position from
-	 * the bitfield length defined above.
-	 */
-	if (ret == 0 && var->bits_per_pixel >= 16) {
-		bool bgr, rgb;
-
-		bgr = caps & CLCD_CAP_BGR && var->blue.offset == 0;
-		rgb = caps & CLCD_CAP_RGB && var->red.offset == 0;
-
-		if (!bgr && !rgb)
-			/*
-			 * The requested format was not possible, try just
-			 * our capabilities.  One of BGR or RGB must be
-			 * supported.
-			 */
-			bgr = caps & CLCD_CAP_BGR;
-
-		if (bgr) {
-			var->blue.offset = 0;
-			var->green.offset = var->blue.offset + var->blue.length;
-			var->red.offset = var->green.offset + var->green.length;
-		} else {
-			var->red.offset = 0;
-			var->green.offset = var->red.offset + var->red.length;
-			var->blue.offset = var->green.offset + var->green.length;
-		}
-	}
-
-	return ret;
-}
-
-static int clcdfb_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
-{
-	struct clcd_fb *fb = to_clcd(info);
-	int ret = -EINVAL;
-
-	if (fb->board->check)
-		ret = fb->board->check(fb, var);
-
-	if (ret == 0 &&
-	    var->xres_virtual * var->bits_per_pixel / 8 *
-	    var->yres_virtual > fb->fb.fix.smem_len)
-		ret = -EINVAL;
-
-	if (ret == 0)
-		ret = clcdfb_set_bitfields(fb, var);
-
-	return ret;
-}
-
-static int clcdfb_set_par(struct fb_info *info)
-{
-	struct clcd_fb *fb = to_clcd(info);
-	struct clcd_regs regs;
-
-	fb->fb.fix.line_length = fb->fb.var.xres_virtual *
-				 fb->fb.var.bits_per_pixel / 8;
-
-	if (fb->fb.var.bits_per_pixel <= 8)
-		fb->fb.fix.visual = FB_VISUAL_PSEUDOCOLOR;
-	else
-		fb->fb.fix.visual = FB_VISUAL_TRUECOLOR;
-
-	fb->board->decode(fb, &regs);
-
-	clcdfb_disable(fb);
-
-	writel(regs.tim0, fb->regs + CLCD_TIM0);
-	writel(regs.tim1, fb->regs + CLCD_TIM1);
-	writel(regs.tim2, fb->regs + CLCD_TIM2);
-	writel(regs.tim3, fb->regs + CLCD_TIM3);
-
-	clcdfb_set_start(fb);
-
-	clk_set_rate(fb->clk, (1000000000 / regs.pixclock) * 1000);
-
-	fb->clcd_cntl = regs.cntl;
-
-	clcdfb_enable(fb, regs.cntl);
-
-#ifdef DEBUG
-	printk(KERN_INFO
-	       "CLCD: Registers set to\n"
-	       "  %08x %08x %08x %08x\n"
-	       "  %08x %08x %08x %08x\n",
-		readl(fb->regs + CLCD_TIM0), readl(fb->regs + CLCD_TIM1),
-		readl(fb->regs + CLCD_TIM2), readl(fb->regs + CLCD_TIM3),
-		readl(fb->regs + CLCD_UBAS), readl(fb->regs + CLCD_LBAS),
-		readl(fb->regs + fb->off_ienb), readl(fb->regs + fb->off_cntl));
-#endif
-
-	return 0;
-}
-
-static inline u32 convert_bitfield(int val, struct fb_bitfield *bf)
-{
-	unsigned int mask = (1 << bf->length) - 1;
-
-	return (val >> (16 - bf->length) & mask) << bf->offset;
-}
-
-/*
- *  Set a single color register. The values supplied have a 16 bit
- *  magnitude.  Return != 0 for invalid regno.
- */
-static int
-clcdfb_setcolreg(unsigned int regno, unsigned int red, unsigned int green,
-		 unsigned int blue, unsigned int transp, struct fb_info *info)
-{
-	struct clcd_fb *fb = to_clcd(info);
-
-	if (regno < 16)
-		fb->cmap[regno] = convert_bitfield(transp, &fb->fb.var.transp) |
-				  convert_bitfield(blue, &fb->fb.var.blue) |
-				  convert_bitfield(green, &fb->fb.var.green) |
-				  convert_bitfield(red, &fb->fb.var.red);
-
-	if (fb->fb.fix.visual == FB_VISUAL_PSEUDOCOLOR && regno < 256) {
-		int hw_reg = CLCD_PALETTE + ((regno * 2) & ~3);
-		u32 val, mask, newval;
-
-		newval  = (red >> 11)  & 0x001f;
-		newval |= (green >> 6) & 0x03e0;
-		newval |= (blue >> 1)  & 0x7c00;
-
-		/*
-		 * 3.2.11: if we're configured for big endian
-		 * byte order, the palette entries are swapped.
-		 */
-		if (fb->clcd_cntl & CNTL_BEBO)
-			regno ^= 1;
-
-		if (regno & 1) {
-			newval <<= 16;
-			mask = 0x0000ffff;
-		} else {
-			mask = 0xffff0000;
-		}
-
-		val = readl(fb->regs + hw_reg) & mask;
-		writel(val | newval, fb->regs + hw_reg);
-	}
-
-	return regno > 255;
-}
-
-/*
- *  Blank the screen if blank_mode != 0, else unblank. If blank == NULL
- *  then the caller blanks by setting the CLUT (Color Look Up Table) to all
- *  black. Return 0 if blanking succeeded, != 0 if un-/blanking failed due
- *  to e.g. a video mode which doesn't support it. Implements VESA suspend
- *  and powerdown modes on hardware that supports disabling hsync/vsync:
- *    blank_mode == 2: suspend vsync
- *    blank_mode == 3: suspend hsync
- *    blank_mode == 4: powerdown
- */
-static int clcdfb_blank(int blank_mode, struct fb_info *info)
-{
-	struct clcd_fb *fb = to_clcd(info);
-
-	if (blank_mode != 0) {
-		clcdfb_disable(fb);
-	} else {
-		clcdfb_enable(fb, fb->clcd_cntl);
-	}
-	return 0;
-}
-
-static int clcdfb_mmap(struct fb_info *info,
-		       struct vm_area_struct *vma)
-{
-	struct clcd_fb *fb = to_clcd(info);
-	unsigned long len, off = vma->vm_pgoff << PAGE_SHIFT;
-	int ret = -EINVAL;
-
-	len = info->fix.smem_len;
-
-	if (off <= len && vma->vm_end - vma->vm_start <= len - off &&
-	    fb->board->mmap)
-		ret = fb->board->mmap(fb, vma);
-
-	return ret;
-}
-
-static const struct fb_ops clcdfb_ops = {
-	.owner		= THIS_MODULE,
-	__FB_DEFAULT_IOMEM_OPS_RDWR,
-	.fb_check_var	= clcdfb_check_var,
-	.fb_set_par	= clcdfb_set_par,
-	.fb_setcolreg	= clcdfb_setcolreg,
-	.fb_blank	= clcdfb_blank,
-	__FB_DEFAULT_IOMEM_OPS_DRAW,
-	.fb_mmap	= clcdfb_mmap,
-};
-
-static int clcdfb_register(struct clcd_fb *fb)
-{
-	int ret;
-
-	/*
-	 * ARM PL111 always has IENB at 0x1c; it's only PL110
-	 * which is reversed on some platforms.
-	 */
-	if (amba_manf(fb->dev) == 0x41 && amba_part(fb->dev) == 0x111) {
-		fb->off_ienb = CLCD_PL111_IENB;
-		fb->off_cntl = CLCD_PL111_CNTL;
-	} else {
-		fb->off_ienb = CLCD_PL110_IENB;
-		fb->off_cntl = CLCD_PL110_CNTL;
-	}
-
-	fb->clk = clk_get(&fb->dev->dev, NULL);
-	if (IS_ERR(fb->clk)) {
-		ret = PTR_ERR(fb->clk);
-		goto out;
-	}
-
-	ret = clk_prepare(fb->clk);
-	if (ret)
-		goto free_clk;
-
-	fb->fb.device		= &fb->dev->dev;
-
-	fb->fb.fix.mmio_start	= fb->dev->res.start;
-	fb->fb.fix.mmio_len	= resource_size(&fb->dev->res);
-
-	fb->regs = ioremap(fb->fb.fix.mmio_start, fb->fb.fix.mmio_len);
-	if (!fb->regs) {
-		printk(KERN_ERR "CLCD: unable to remap registers\n");
-		ret = -ENOMEM;
-		goto clk_unprep;
-	}
-
-	fb->fb.fbops		= &clcdfb_ops;
-	fb->fb.pseudo_palette	= fb->cmap;
-
-	strncpy(fb->fb.fix.id, clcd_name, sizeof(fb->fb.fix.id));
-	fb->fb.fix.type		= FB_TYPE_PACKED_PIXELS;
-	fb->fb.fix.type_aux	= 0;
-	fb->fb.fix.xpanstep	= 0;
-	fb->fb.fix.ypanstep	= 0;
-	fb->fb.fix.ywrapstep	= 0;
-	fb->fb.fix.accel	= FB_ACCEL_NONE;
-
-	fb->fb.var.xres		= fb->panel->mode.xres;
-	fb->fb.var.yres		= fb->panel->mode.yres;
-	fb->fb.var.xres_virtual	= fb->panel->mode.xres;
-	fb->fb.var.yres_virtual	= fb->panel->mode.yres;
-	fb->fb.var.bits_per_pixel = fb->panel->bpp;
-	fb->fb.var.grayscale	= fb->panel->grayscale;
-	fb->fb.var.pixclock	= fb->panel->mode.pixclock;
-	fb->fb.var.left_margin	= fb->panel->mode.left_margin;
-	fb->fb.var.right_margin	= fb->panel->mode.right_margin;
-	fb->fb.var.upper_margin	= fb->panel->mode.upper_margin;
-	fb->fb.var.lower_margin	= fb->panel->mode.lower_margin;
-	fb->fb.var.hsync_len	= fb->panel->mode.hsync_len;
-	fb->fb.var.vsync_len	= fb->panel->mode.vsync_len;
-	fb->fb.var.sync		= fb->panel->mode.sync;
-	fb->fb.var.vmode	= fb->panel->mode.vmode;
-	fb->fb.var.activate	= FB_ACTIVATE_NOW;
-	fb->fb.var.nonstd	= 0;
-	fb->fb.var.height	= fb->panel->height;
-	fb->fb.var.width	= fb->panel->width;
-	fb->fb.var.accel_flags	= 0;
-
-	fb->fb.monspecs.hfmin	= 0;
-	fb->fb.monspecs.hfmax   = 100000;
-	fb->fb.monspecs.vfmin	= 0;
-	fb->fb.monspecs.vfmax	= 400;
-	fb->fb.monspecs.dclkmin = 1000000;
-	fb->fb.monspecs.dclkmax	= 100000000;
-
-	/*
-	 * Make sure that the bitfields are set appropriately.
-	 */
-	clcdfb_set_bitfields(fb, &fb->fb.var);
-
-	/*
-	 * Allocate colourmap.
-	 */
-	ret = fb_alloc_cmap(&fb->fb.cmap, 256, 0);
-	if (ret)
-		goto unmap;
-
-	/*
-	 * Ensure interrupts are disabled.
-	 */
-	writel(0, fb->regs + fb->off_ienb);
-
-	fb_set_var(&fb->fb, &fb->fb.var);
-
-	dev_info(&fb->dev->dev, "%s hardware, %s display\n",
-	         fb->board->name, fb->panel->mode.name);
-
-	ret = register_framebuffer(&fb->fb);
-	if (ret == 0)
-		goto out;
-
-	printk(KERN_ERR "CLCD: cannot register framebuffer (%d)\n", ret);
-
-	fb_dealloc_cmap(&fb->fb.cmap);
- unmap:
-	iounmap(fb->regs);
- clk_unprep:
-	clk_unprepare(fb->clk);
- free_clk:
-	clk_put(fb->clk);
- out:
-	return ret;
-}
-
-#ifdef CONFIG_OF
-static int clcdfb_of_get_dpi_panel_mode(struct device_node *node,
-		struct clcd_panel *clcd_panel)
-{
-	int err;
-	struct display_timing timing;
-	struct videomode video;
-
-	err = of_get_display_timing(node, "panel-timing", &timing);
-	if (err) {
-		pr_err("%pOF: problems parsing panel-timing (%d)\n", node, err);
-		return err;
-	}
-
-	videomode_from_timing(&timing, &video);
-
-	err = fb_videomode_from_videomode(&video, &clcd_panel->mode);
-	if (err)
-		return err;
-
-	/* Set up some inversion flags */
-	if (timing.flags & DISPLAY_FLAGS_PIXDATA_NEGEDGE)
-		clcd_panel->tim2 |= TIM2_IPC;
-	else if (!(timing.flags & DISPLAY_FLAGS_PIXDATA_POSEDGE))
-		/*
-		 * To preserve backwards compatibility, the IPC (inverted
-		 * pixel clock) flag needs to be set on any display that
-		 * doesn't explicitly specify that the pixel clock is
-		 * active on the negative or positive edge.
-		 */
-		clcd_panel->tim2 |= TIM2_IPC;
-
-	if (timing.flags & DISPLAY_FLAGS_HSYNC_LOW)
-		clcd_panel->tim2 |= TIM2_IHS;
-
-	if (timing.flags & DISPLAY_FLAGS_VSYNC_LOW)
-		clcd_panel->tim2 |= TIM2_IVS;
-
-	if (timing.flags & DISPLAY_FLAGS_DE_LOW)
-		clcd_panel->tim2 |= TIM2_IOE;
-
-	return 0;
-}
-
-static int clcdfb_snprintf_mode(char *buf, int size, struct fb_videomode *mode)
-{
-	return snprintf(buf, size, "%ux%u@%u", mode->xres, mode->yres,
-			mode->refresh);
-}
-
-static int clcdfb_of_get_backlight(struct device *dev,
-				   struct clcd_panel *clcd_panel)
-{
-	struct backlight_device *backlight;
-
-	/* Look up the optional backlight device */
-	backlight = devm_of_find_backlight(dev);
-	if (IS_ERR(backlight))
-		return PTR_ERR(backlight);
-
-	clcd_panel->backlight = backlight;
-	return 0;
-}
-
-static int clcdfb_of_get_mode(struct device *dev, struct device_node *panel,
-			      struct clcd_panel *clcd_panel)
-{
-	int err;
-	struct fb_videomode *mode;
-	char *name;
-	int len;
-
-	/* Only directly connected DPI panels supported for now */
-	if (of_device_is_compatible(panel, "panel-dpi"))
-		err = clcdfb_of_get_dpi_panel_mode(panel, clcd_panel);
-	else
-		err = -ENOENT;
-	if (err)
-		return err;
-	mode = &clcd_panel->mode;
-
-	len = clcdfb_snprintf_mode(NULL, 0, mode);
-	name = devm_kzalloc(dev, len + 1, GFP_KERNEL);
-	if (!name)
-		return -ENOMEM;
-
-	clcdfb_snprintf_mode(name, len + 1, mode);
-	mode->name = name;
-
-	return 0;
-}
-
-static int clcdfb_of_init_tft_panel(struct clcd_fb *fb, u32 r0, u32 g0, u32 b0)
-{
-	static struct {
-		unsigned int part;
-		u32 r0, g0, b0;
-		u32 caps;
-	} panels[] = {
-		{ 0x110, 1,  7, 13, CLCD_CAP_5551 },
-		{ 0x110, 0,  8, 16, CLCD_CAP_888 },
-		{ 0x110, 16, 8, 0,  CLCD_CAP_888 },
-		{ 0x111, 4, 14, 20, CLCD_CAP_444 },
-		{ 0x111, 3, 11, 19, CLCD_CAP_444 | CLCD_CAP_5551 },
-		{ 0x111, 3, 10, 19, CLCD_CAP_444 | CLCD_CAP_5551 |
-				    CLCD_CAP_565 },
-		{ 0x111, 0,  8, 16, CLCD_CAP_444 | CLCD_CAP_5551 |
-				    CLCD_CAP_565 | CLCD_CAP_888 },
-	};
-	int i;
-
-	/* Bypass pixel clock divider */
-	fb->panel->tim2 |= TIM2_BCD;
-
-	/* TFT display, vert. comp. interrupt at the start of the back porch */
-	fb->panel->cntl |= CNTL_LCDTFT | CNTL_LCDVCOMP(1);
-
-	fb->panel->caps = 0;
-
-	/* Match the setup with known variants */
-	for (i = 0; i < ARRAY_SIZE(panels) && !fb->panel->caps; i++) {
-		if (amba_part(fb->dev) != panels[i].part)
-			continue;
-		if (g0 != panels[i].g0)
-			continue;
-		if (r0 == panels[i].r0 && b0 == panels[i].b0)
-			fb->panel->caps = panels[i].caps;
-	}
-
-	/*
-	 * If we actually physically connected the R lines to B and
-	 * vice versa
-	 */
-	if (r0 != 0 && b0 == 0)
-		fb->panel->bgr_connection = true;
-
-	return fb->panel->caps ? 0 : -EINVAL;
-}
-
-static int clcdfb_of_init_display(struct clcd_fb *fb)
-{
-	struct device_node *endpoint, *panel;
-	int err;
-	unsigned int bpp;
-	u32 max_bandwidth;
-	u32 tft_r0b0g0[3];
-
-	fb->panel = devm_kzalloc(&fb->dev->dev, sizeof(*fb->panel), GFP_KERNEL);
-	if (!fb->panel)
-		return -ENOMEM;
-
-	/*
-	 * Fetch the panel endpoint.
-	 */
-	endpoint = of_graph_get_next_endpoint(fb->dev->dev.of_node, NULL);
-	if (!endpoint)
-		return -ENODEV;
-
-	panel = of_graph_get_remote_port_parent(endpoint);
-	if (!panel) {
-		err = -ENODEV;
-		goto out_endpoint_put;
-	}
-
-	err = clcdfb_of_get_backlight(&fb->dev->dev, fb->panel);
-	if (err)
-		goto out_panel_put;
-
-	err = clcdfb_of_get_mode(&fb->dev->dev, panel, fb->panel);
-	if (err)
-		goto out_panel_put;
-
-	err = of_property_read_u32(fb->dev->dev.of_node, "max-memory-bandwidth",
-			&max_bandwidth);
-	if (!err) {
-		/*
-		 * max_bandwidth is in bytes per second and pixclock in
-		 * pico-seconds, so the maximum allowed bits per pixel is
-		 *   8 * max_bandwidth / (PICOS2KHZ(pixclock) * 1000)
-		 * Rearrange this calculation to avoid overflow and then ensure
-		 * result is a valid format.
-		 */
-		bpp = max_bandwidth / (1000 / 8)
-			/ PICOS2KHZ(fb->panel->mode.pixclock);
-		bpp = rounddown_pow_of_two(bpp);
-		if (bpp > 32)
-			bpp = 32;
-	} else
-		bpp = 32;
-	fb->panel->bpp = bpp;
-
-#ifdef CONFIG_CPU_BIG_ENDIAN
-	fb->panel->cntl |= CNTL_BEBO;
-#endif
-	fb->panel->width = -1;
-	fb->panel->height = -1;
-
-	if (of_property_read_u32_array(endpoint,
-			"arm,pl11x,tft-r0g0b0-pads",
-			tft_r0b0g0, ARRAY_SIZE(tft_r0b0g0)) != 0) {
-		err = -ENOENT;
-		goto out_panel_put;
-	}
-
-	of_node_put(panel);
-	of_node_put(endpoint);
-
-	return clcdfb_of_init_tft_panel(fb, tft_r0b0g0[0],
-					tft_r0b0g0[1],  tft_r0b0g0[2]);
-out_panel_put:
-	of_node_put(panel);
-out_endpoint_put:
-	of_node_put(endpoint);
-	return err;
-}
-
-static int clcdfb_of_vram_setup(struct clcd_fb *fb)
-{
-	int err;
-	struct device_node *memory;
-	u64 size;
-
-	err = clcdfb_of_init_display(fb);
-	if (err)
-		return err;
-
-	memory = of_parse_phandle(fb->dev->dev.of_node, "memory-region", 0);
-	if (!memory)
-		return -ENODEV;
-
-	fb->fb.screen_base = of_iomap(memory, 0);
-	if (!fb->fb.screen_base) {
-		of_node_put(memory);
-		return -ENOMEM;
-	}
-
-	fb->fb.fix.smem_start = of_translate_address(memory,
-			of_get_address(memory, 0, &size, NULL));
-	fb->fb.fix.smem_len = size;
-	of_node_put(memory);
-
-	return 0;
-}
-
-static int clcdfb_of_vram_mmap(struct clcd_fb *fb, struct vm_area_struct *vma)
-{
-	unsigned long off, user_size, kernel_size;
-
-
-	off = vma->vm_pgoff << PAGE_SHIFT;
-	user_size = vma->vm_end - vma->vm_start;
-	kernel_size = fb->fb.fix.smem_len;
-
-	if (off >= kernel_size || user_size > (kernel_size - off))
-		return -ENXIO;
-
-	return remap_pfn_range(vma, vma->vm_start,
-			__phys_to_pfn(fb->fb.fix.smem_start) + vma->vm_pgoff,
-			user_size,
-			pgprot_writecombine(vma->vm_page_prot));
-}
-
-static void clcdfb_of_vram_remove(struct clcd_fb *fb)
-{
-	iounmap(fb->fb.screen_base);
-}
-
-static int clcdfb_of_dma_setup(struct clcd_fb *fb)
-{
-	unsigned long framesize;
-	dma_addr_t dma;
-	int err;
-
-	err = clcdfb_of_init_display(fb);
-	if (err)
-		return err;
-
-	framesize = PAGE_ALIGN(fb->panel->mode.xres * fb->panel->mode.yres *
-			fb->panel->bpp / 8);
-	fb->fb.screen_base = dma_alloc_coherent(&fb->dev->dev, framesize,
-			&dma, GFP_KERNEL);
-	if (!fb->fb.screen_base)
-		return -ENOMEM;
-
-	fb->fb.fix.smem_start = dma;
-	fb->fb.fix.smem_len = framesize;
-
-	return 0;
-}
-
-static int clcdfb_of_dma_mmap(struct clcd_fb *fb, struct vm_area_struct *vma)
-{
-	return dma_mmap_wc(&fb->dev->dev, vma, fb->fb.screen_base,
-			   fb->fb.fix.smem_start, fb->fb.fix.smem_len);
-}
-
-static void clcdfb_of_dma_remove(struct clcd_fb *fb)
-{
-	dma_free_coherent(&fb->dev->dev, fb->fb.fix.smem_len,
-			fb->fb.screen_base, fb->fb.fix.smem_start);
-}
-
-static struct clcd_board *clcdfb_of_get_board(struct amba_device *dev)
-{
-	struct clcd_board *board = devm_kzalloc(&dev->dev, sizeof(*board),
-			GFP_KERNEL);
-	struct device_node *node = dev->dev.of_node;
-
-	if (!board)
-		return NULL;
-
-	board->name = of_node_full_name(node);
-	board->caps = CLCD_CAP_ALL;
-	board->check = clcdfb_check;
-	board->decode = clcdfb_decode;
-	if (of_property_present(node, "memory-region")) {
-		board->setup = clcdfb_of_vram_setup;
-		board->mmap = clcdfb_of_vram_mmap;
-		board->remove = clcdfb_of_vram_remove;
-	} else {
-		board->setup = clcdfb_of_dma_setup;
-		board->mmap = clcdfb_of_dma_mmap;
-		board->remove = clcdfb_of_dma_remove;
-	}
-
-	return board;
-}
-#else
-static struct clcd_board *clcdfb_of_get_board(struct amba_device *dev)
-{
-	return NULL;
-}
-#endif
-
-static int clcdfb_probe(struct amba_device *dev, const struct amba_id *id)
-{
-	struct clcd_board *board = dev_get_platdata(&dev->dev);
-	struct clcd_fb *fb;
-	int ret;
-
-	if (!board)
-		board = clcdfb_of_get_board(dev);
-
-	if (!board)
-		return -EINVAL;
-
-	ret = dma_set_mask_and_coherent(&dev->dev, DMA_BIT_MASK(32));
-	if (ret)
-		goto out;
-
-	ret = amba_request_regions(dev, NULL);
-	if (ret) {
-		printk(KERN_ERR "CLCD: unable to reserve regs region\n");
-		goto out;
-	}
-
-	fb = kzalloc(sizeof(*fb), GFP_KERNEL);
-	if (!fb) {
-		ret = -ENOMEM;
-		goto free_region;
-	}
-
-	fb->dev = dev;
-	fb->board = board;
-
-	dev_info(&fb->dev->dev, "PL%03x designer %02x rev%u at 0x%08llx\n",
-		amba_part(dev), amba_manf(dev), amba_rev(dev),
-		(unsigned long long)dev->res.start);
-
-	ret = fb->board->setup(fb);
-	if (ret)
-		goto free_fb;
-
-	ret = clcdfb_register(fb);
-	if (ret == 0) {
-		amba_set_drvdata(dev, fb);
-		goto out;
-	}
-
-	fb->board->remove(fb);
- free_fb:
-	kfree(fb);
- free_region:
-	amba_release_regions(dev);
- out:
-	return ret;
-}
-
-static void clcdfb_remove(struct amba_device *dev)
-{
-	struct clcd_fb *fb = amba_get_drvdata(dev);
-
-	clcdfb_disable(fb);
-	unregister_framebuffer(&fb->fb);
-	if (fb->fb.cmap.len)
-		fb_dealloc_cmap(&fb->fb.cmap);
-	iounmap(fb->regs);
-	clk_unprepare(fb->clk);
-	clk_put(fb->clk);
-
-	fb->board->remove(fb);
-
-	kfree(fb);
-
-	amba_release_regions(dev);
-}
-
-static const struct amba_id clcdfb_id_table[] = {
-	{
-		.id	= 0x00041110,
-		.mask	= 0x000ffffe,
-	},
-	{ 0, 0 },
-};
-
-MODULE_DEVICE_TABLE(amba, clcdfb_id_table);
-
-static struct amba_driver clcd_driver = {
-	.drv 		= {
-		.name	= "clcd-pl11x",
-	},
-	.probe		= clcdfb_probe,
-	.remove		= clcdfb_remove,
-	.id_table	= clcdfb_id_table,
-};
-
-static int __init amba_clcdfb_init(void)
-{
-	if (fb_get_options("ambafb", NULL))
-		return -ENODEV;
-
-	return amba_driver_register(&clcd_driver);
-}
-
-module_init(amba_clcdfb_init);
-
-static void __exit amba_clcdfb_exit(void)
-{
-	amba_driver_unregister(&clcd_driver);
-}
-
-module_exit(amba_clcdfb_exit);
-
-MODULE_DESCRIPTION("ARM PrimeCell PL110 CLCD core driver");
-MODULE_LICENSE("GPL");
diff --git a/include/linux/amba/clcd-regs.h b/include/linux/amba/clcd-regs.h
deleted file mode 100644
index 421b0fa90d6a..000000000000
--- a/include/linux/amba/clcd-regs.h
+++ /dev/null
@@ -1,87 +0,0 @@
-/*
- * David A Rusling
- *
- * Copyright (C) 2001 ARM Limited
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file COPYING in the main directory of this archive
- * for more details.
- */
-
-#ifndef AMBA_CLCD_REGS_H
-#define AMBA_CLCD_REGS_H
-
-/*
- * CLCD Controller Internal Register addresses
- */
-#define CLCD_TIM0		0x00000000
-#define CLCD_TIM1 		0x00000004
-#define CLCD_TIM2 		0x00000008
-#define CLCD_TIM3 		0x0000000c
-#define CLCD_UBAS 		0x00000010
-#define CLCD_LBAS 		0x00000014
-
-#define CLCD_PL110_IENB		0x00000018
-#define CLCD_PL110_CNTL		0x0000001c
-#define CLCD_PL110_STAT		0x00000020
-#define CLCD_PL110_INTR 	0x00000024
-#define CLCD_PL110_UCUR		0x00000028
-#define CLCD_PL110_LCUR		0x0000002C
-
-#define CLCD_PL111_CNTL		0x00000018
-#define CLCD_PL111_IENB		0x0000001c
-#define CLCD_PL111_RIS		0x00000020
-#define CLCD_PL111_MIS		0x00000024
-#define CLCD_PL111_ICR		0x00000028
-#define CLCD_PL111_UCUR		0x0000002c
-#define CLCD_PL111_LCUR		0x00000030
-
-#define CLCD_PALL 		0x00000200
-#define CLCD_PALETTE		0x00000200
-
-#define TIM2_PCD_LO_MASK	GENMASK(4, 0)
-#define TIM2_PCD_LO_BITS	5
-#define TIM2_CLKSEL		(1 << 5)
-#define TIM2_ACB_MASK		GENMASK(10, 6)
-#define TIM2_IVS		(1 << 11)
-#define TIM2_IHS		(1 << 12)
-#define TIM2_IPC		(1 << 13)
-#define TIM2_IOE		(1 << 14)
-#define TIM2_BCD		(1 << 26)
-#define TIM2_PCD_HI_MASK	GENMASK(31, 27)
-#define TIM2_PCD_HI_BITS	5
-#define TIM2_PCD_HI_SHIFT	27
-
-#define CNTL_LCDEN		(1 << 0)
-#define CNTL_LCDBPP1		(0 << 1)
-#define CNTL_LCDBPP2		(1 << 1)
-#define CNTL_LCDBPP4		(2 << 1)
-#define CNTL_LCDBPP8		(3 << 1)
-#define CNTL_LCDBPP16		(4 << 1)
-#define CNTL_LCDBPP16_565	(6 << 1)
-#define CNTL_LCDBPP16_444	(7 << 1)
-#define CNTL_LCDBPP24		(5 << 1)
-#define CNTL_LCDBW		(1 << 4)
-#define CNTL_LCDTFT		(1 << 5)
-#define CNTL_LCDMONO8		(1 << 6)
-#define CNTL_LCDDUAL		(1 << 7)
-#define CNTL_BGR		(1 << 8)
-#define CNTL_BEBO		(1 << 9)
-#define CNTL_BEPO		(1 << 10)
-#define CNTL_LCDPWR		(1 << 11)
-#define CNTL_LCDVCOMP(x)	((x) << 12)
-#define CNTL_LDMAFIFOTIME	(1 << 15)
-#define CNTL_WATERMARK		(1 << 16)
-
-/* ST Microelectronics variant bits */
-#define CNTL_ST_1XBPP_444	0x0
-#define CNTL_ST_1XBPP_5551	(1 << 17)
-#define CNTL_ST_1XBPP_565	(1 << 18)
-#define CNTL_ST_CDWID_12	0x0
-#define CNTL_ST_CDWID_16	(1 << 19)
-#define CNTL_ST_CDWID_18	(1 << 20)
-#define CNTL_ST_CDWID_24	((1 << 19)|(1 << 20))
-#define CNTL_ST_CEAEN		(1 << 21)
-#define CNTL_ST_LCDBPP24_PACKED	(6 << 1)
-
-#endif /* AMBA_CLCD_REGS_H */
diff --git a/include/linux/amba/clcd.h b/include/linux/amba/clcd.h
deleted file mode 100644
index b6e0cbeaf533..000000000000
--- a/include/linux/amba/clcd.h
+++ /dev/null
@@ -1,290 +0,0 @@
-/*
- * linux/include/asm-arm/hardware/amba_clcd.h -- Integrator LCD panel.
- *
- * David A Rusling
- *
- * Copyright (C) 2001 ARM Limited
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file COPYING in the main directory of this archive
- * for more details.
- */
-#include <linux/fb.h>
-#include <linux/amba/clcd-regs.h>
-
-enum {
-	/* individual formats */
-	CLCD_CAP_RGB444		= (1 << 0),
-	CLCD_CAP_RGB5551	= (1 << 1),
-	CLCD_CAP_RGB565		= (1 << 2),
-	CLCD_CAP_RGB888		= (1 << 3),
-	CLCD_CAP_BGR444		= (1 << 4),
-	CLCD_CAP_BGR5551	= (1 << 5),
-	CLCD_CAP_BGR565		= (1 << 6),
-	CLCD_CAP_BGR888		= (1 << 7),
-
-	/* connection layouts */
-	CLCD_CAP_444		= CLCD_CAP_RGB444 | CLCD_CAP_BGR444,
-	CLCD_CAP_5551		= CLCD_CAP_RGB5551 | CLCD_CAP_BGR5551,
-	CLCD_CAP_565		= CLCD_CAP_RGB565 | CLCD_CAP_BGR565,
-	CLCD_CAP_888		= CLCD_CAP_RGB888 | CLCD_CAP_BGR888,
-
-	/* red/blue ordering */
-	CLCD_CAP_RGB		= CLCD_CAP_RGB444 | CLCD_CAP_RGB5551 |
-				  CLCD_CAP_RGB565 | CLCD_CAP_RGB888,
-	CLCD_CAP_BGR		= CLCD_CAP_BGR444 | CLCD_CAP_BGR5551 |
-				  CLCD_CAP_BGR565 | CLCD_CAP_BGR888,
-
-	CLCD_CAP_ALL		= CLCD_CAP_BGR | CLCD_CAP_RGB,
-};
-
-struct backlight_device;
-
-struct clcd_panel {
-	struct fb_videomode	mode;
-	signed short		width;	/* width in mm */
-	signed short		height;	/* height in mm */
-	u32			tim2;
-	u32			tim3;
-	u32			cntl;
-	u32			caps;
-	unsigned int		bpp:8,
-				fixedtimings:1,
-				grayscale:1;
-	unsigned int		connector;
-	struct backlight_device	*backlight;
-	/*
-	 * If the B/R lines are switched between the CLCD
-	 * and the panel we need to know this and not try to
-	 * compensate with the BGR bit in the control register.
-	 */
-	bool			bgr_connection;
-};
-
-struct clcd_regs {
-	u32			tim0;
-	u32			tim1;
-	u32			tim2;
-	u32			tim3;
-	u32			cntl;
-	unsigned long		pixclock;
-};
-
-struct clcd_fb;
-
-/*
- * the board-type specific routines
- */
-struct clcd_board {
-	const char *name;
-
-	/*
-	 * Optional.  Hardware capability flags.
-	 */
-	u32	caps;
-
-	/*
-	 * Optional.  Check whether the var structure is acceptable
-	 * for this display.
-	 */
-	int	(*check)(struct clcd_fb *fb, struct fb_var_screeninfo *var);
-
-	/*
-	 * Compulsory.  Decode fb->fb.var into regs->*.  In the case of
-	 * fixed timing, set regs->* to the register values required.
-	 */
-	void	(*decode)(struct clcd_fb *fb, struct clcd_regs *regs);
-
-	/*
-	 * Optional.  Disable any extra display hardware.
-	 */
-	void	(*disable)(struct clcd_fb *);
-
-	/*
-	 * Optional.  Enable any extra display hardware.
-	 */
-	void	(*enable)(struct clcd_fb *);
-
-	/*
-	 * Setup platform specific parts of CLCD driver
-	 */
-	int	(*setup)(struct clcd_fb *);
-
-	/*
-	 * mmap the framebuffer memory
-	 */
-	int	(*mmap)(struct clcd_fb *, struct vm_area_struct *);
-
-	/*
-	 * Remove platform specific parts of CLCD driver
-	 */
-	void	(*remove)(struct clcd_fb *);
-};
-
-struct amba_device;
-struct clk;
-
-/* this data structure describes each frame buffer device we find */
-struct clcd_fb {
-	struct fb_info		fb;
-	struct amba_device	*dev;
-	struct clk		*clk;
-	struct clcd_panel	*panel;
-	struct clcd_board	*board;
-	void			*board_data;
-	void __iomem		*regs;
-	u16			off_ienb;
-	u16			off_cntl;
-	u32			clcd_cntl;
-	u32			cmap[16];
-	bool			clk_enabled;
-};
-
-static inline void clcdfb_decode(struct clcd_fb *fb, struct clcd_regs *regs)
-{
-	struct fb_var_screeninfo *var = &fb->fb.var;
-	u32 val, cpl;
-
-	/*
-	 * Program the CLCD controller registers and start the CLCD
-	 */
-	val = ((var->xres / 16) - 1) << 2;
-	val |= (var->hsync_len - 1) << 8;
-	val |= (var->right_margin - 1) << 16;
-	val |= (var->left_margin - 1) << 24;
-	regs->tim0 = val;
-
-	val = var->yres;
-	if (fb->panel->cntl & CNTL_LCDDUAL)
-		val /= 2;
-	val -= 1;
-	val |= (var->vsync_len - 1) << 10;
-	val |= var->lower_margin << 16;
-	val |= var->upper_margin << 24;
-	regs->tim1 = val;
-
-	val = fb->panel->tim2;
-	val |= var->sync & FB_SYNC_HOR_HIGH_ACT  ? 0 : TIM2_IHS;
-	val |= var->sync & FB_SYNC_VERT_HIGH_ACT ? 0 : TIM2_IVS;
-
-	cpl = var->xres_virtual;
-	if (fb->panel->cntl & CNTL_LCDTFT)	  /* TFT */
-		/* / 1 */;
-	else if (!var->grayscale)		  /* STN color */
-		cpl = cpl * 8 / 3;
-	else if (fb->panel->cntl & CNTL_LCDMONO8) /* STN monochrome, 8bit */
-		cpl /= 8;
-	else					  /* STN monochrome, 4bit */
-		cpl /= 4;
-
-	regs->tim2 = val | ((cpl - 1) << 16);
-
-	regs->tim3 = fb->panel->tim3;
-
-	val = fb->panel->cntl;
-	if (var->grayscale)
-		val |= CNTL_LCDBW;
-
-	if (fb->panel->caps && fb->board->caps && var->bits_per_pixel >= 16) {
-		/*
-		 * if board and panel supply capabilities, we can support
-		 * changing BGR/RGB depending on supplied parameters. Here
-		 * we switch to what the framebuffer is providing if need
-		 * be, so if the framebuffer is BGR but the display connection
-		 * is RGB (first case) we switch it around. Vice versa mutatis
-		 * mutandis if the framebuffer is RGB but the display connection
-		 * is BGR, we flip it around.
-		 */
-		if (var->red.offset == 0)
-			val &= ~CNTL_BGR;
-		else
-			val |= CNTL_BGR;
-		if (fb->panel->bgr_connection)
-			val ^= CNTL_BGR;
-	}
-
-	switch (var->bits_per_pixel) {
-	case 1:
-		val |= CNTL_LCDBPP1;
-		break;
-	case 2:
-		val |= CNTL_LCDBPP2;
-		break;
-	case 4:
-		val |= CNTL_LCDBPP4;
-		break;
-	case 8:
-		val |= CNTL_LCDBPP8;
-		break;
-	case 16:
-		/*
-		 * PL110 cannot choose between 5551 and 565 modes in its
-		 * control register.  It is possible to use 565 with
-		 * custom external wiring.
-		 */
-		if (amba_part(fb->dev) == 0x110 ||
-		    var->green.length == 5)
-			val |= CNTL_LCDBPP16;
-		else if (var->green.length == 6)
-			val |= CNTL_LCDBPP16_565;
-		else
-			val |= CNTL_LCDBPP16_444;
-		break;
-	case 32:
-		val |= CNTL_LCDBPP24;
-		break;
-	}
-
-	regs->cntl = val;
-	regs->pixclock = var->pixclock;
-}
-
-static inline int clcdfb_check(struct clcd_fb *fb, struct fb_var_screeninfo *var)
-{
-	var->xres_virtual = var->xres = (var->xres + 15) & ~15;
-	var->yres_virtual = var->yres = (var->yres + 1) & ~1;
-
-#define CHECK(e,l,h) (var->e < l || var->e > h)
-	if (CHECK(right_margin, (5+1), 256) ||	/* back porch */
-	    CHECK(left_margin, (5+1), 256) ||	/* front porch */
-	    CHECK(hsync_len, (5+1), 256) ||
-	    var->xres > 4096 ||
-	    var->lower_margin > 255 ||		/* back porch */
-	    var->upper_margin > 255 ||		/* front porch */
-	    var->vsync_len > 32 ||
-	    var->yres > 1024)
-		return -EINVAL;
-#undef CHECK
-
-	/* single panel mode: PCD = max(PCD, 1) */
-	/* dual panel mode: PCD = max(PCD, 5) */
-
-	/*
-	 * You can't change the grayscale setting, and
-	 * we can only do non-interlaced video.
-	 */
-	if (var->grayscale != fb->fb.var.grayscale ||
-	    (var->vmode & FB_VMODE_MASK) != FB_VMODE_NONINTERLACED)
-		return -EINVAL;
-
-#define CHECK(e) (var->e != fb->fb.var.e)
-	if (fb->panel->fixedtimings &&
-	    (CHECK(xres)		||
-	     CHECK(yres)		||
-	     CHECK(bits_per_pixel)	||
-	     CHECK(pixclock)		||
-	     CHECK(left_margin)		||
-	     CHECK(right_margin)	||
-	     CHECK(upper_margin)	||
-	     CHECK(lower_margin)	||
-	     CHECK(hsync_len)		||
-	     CHECK(vsync_len)		||
-	     CHECK(sync)))
-		return -EINVAL;
-#undef CHECK
-
-	var->nonstd = 0;
-	var->accel_flags = 0;
-
-	return 0;
-}
-- 
cgit v1.2.3


From 12b8de566fa9ec428e724f955735fd1ca278ca4c Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Wed, 20 Dec 2023 14:22:54 +0100
Subject: video/sticore: Store ROM device in STI struct

Store the ROM's parent device in each STI struct, so we can associate
the STI framebuffer with a device.

The new field will eventually replace the fbdev subsystem's info field,
which the function fb_is_primary_device() currently requires to detect
the firmware's output. By using the device instead of the framebuffer
info, a later patch can generalize the helper for use in non-fbdev code.

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 drivers/video/sticore.c | 5 +++++
 include/video/sticore.h | 4 ++++
 2 files changed, 9 insertions(+)

(limited to 'include')

diff --git a/drivers/video/sticore.c b/drivers/video/sticore.c
index c3765ad6eedf..7115b325817f 100644
--- a/drivers/video/sticore.c
+++ b/drivers/video/sticore.c
@@ -1041,6 +1041,9 @@ static int __init sticore_pa_init(struct parisc_device *dev)
 
 	print_pa_hwpath(dev, sti->pa_path);
 	sticore_check_for_default_sti(sti, sti->pa_path);
+
+	sti->dev = &dev->dev;
+
 	return 0;
 }
 
@@ -1084,6 +1087,8 @@ static int sticore_pci_init(struct pci_dev *pd, const struct pci_device_id *ent)
 		pr_warn("Unable to handle STI device '%s'\n", pci_name(pd));
 		return -ENODEV;
 	}
+
+	sti->dev = &pd->dev;
 #endif /* CONFIG_PCI */
 
 	return 0;
diff --git a/include/video/sticore.h b/include/video/sticore.h
index 012b5b46ad7d..9d993e22805d 100644
--- a/include/video/sticore.h
+++ b/include/video/sticore.h
@@ -2,6 +2,7 @@
 #ifndef STICORE_H
 #define STICORE_H
 
+struct device;
 struct fb_info;
 
 /* generic STI structures & functions */
@@ -370,6 +371,9 @@ struct sti_struct {
 	/* pointer to the fb_info where this STI device is used */
 	struct fb_info *info;
 
+	/* pointer to the parent device */
+	struct device *dev;
+
 	/* pointer to all internal data */
 	struct sti_all_data *sti_data;
 
-- 
cgit v1.2.3


From e2e0b838a1849f92612a8305c09aaf31bf824350 Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Wed, 20 Dec 2023 14:22:57 +0100
Subject: video/sticore: Remove info field from STI struct

The info field in struct sti_struct was used to detect the default
display device. That test is now done with the respective Linux device
and the info field is unused. Remove it.

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 drivers/video/fbdev/stifb.c | 3 ---
 include/video/sticore.h     | 4 ----
 2 files changed, 7 deletions(-)

(limited to 'include')

diff --git a/drivers/video/fbdev/stifb.c b/drivers/video/fbdev/stifb.c
index 36e6bcab83aa..2de0e675fd15 100644
--- a/drivers/video/fbdev/stifb.c
+++ b/drivers/video/fbdev/stifb.c
@@ -1389,7 +1389,6 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref)
 	}
 
 	/* save for primary gfx device detection & unregister_framebuffer() */
-	sti->info = info;
 	if (register_framebuffer(fb->info) < 0)
 		goto out_err4;
 
@@ -1417,7 +1416,6 @@ out_err1:
 	iounmap(info->screen_base);
 out_err0:
 	framebuffer_release(info);
-	sti->info = NULL;
 	return -ENXIO;
 }
 
@@ -1496,7 +1494,6 @@ stifb_cleanup(void)
 		        framebuffer_release(info);
 			dev_set_drvdata(sti->dev, NULL);
 		}
-		sti->info = NULL;
 	}
 }
 
diff --git a/include/video/sticore.h b/include/video/sticore.h
index 9d993e22805d..823666af1871 100644
--- a/include/video/sticore.h
+++ b/include/video/sticore.h
@@ -3,7 +3,6 @@
 #define STICORE_H
 
 struct device;
-struct fb_info;
 
 /* generic STI structures & functions */
 
@@ -368,9 +367,6 @@ struct sti_struct {
 	/* PCI data structures (pg. 17ff from sti.pdf) */
 	u8 rm_entry[16]; /* pci region mapper array == pci config space offset */
 
-	/* pointer to the fb_info where this STI device is used */
-	struct fb_info *info;
-
 	/* pointer to the parent device */
 	struct device *dev;
 
-- 
cgit v1.2.3


From 7ea26f9460c6c76b1d6e36f39fce34b16cb88300 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Tue, 9 Jan 2024 20:22:45 +0200
Subject: fsnotify: compile out fsnotify permission hooks if
 !FANOTIFY_ACCESS_PERMISSIONS

The depency of FANOTIFY_ACCESS_PERMISSIONS on SECURITY made sure that
the fsnotify permission hooks were never called when SECURITY was
disabled.

Moving the fsnotify permission hook out of the secutiy hook broke that
optimisation.

Reported-and-tested-by: Jens Axboe <axboe@kernel.dk>
Closes: https://lore.kernel.org/linux-fsdevel/53682ece-f0e7-48de-9a1c-879ee34b0449@kernel.dk/
Fixes: d9e5d31084b0 ("fsnotify: optionally pass access range in file permission hooks")
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Link: https://lore.kernel.org/r/20240109182245.38884-1-amir73il@gmail.com
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/fsnotify.h | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

(limited to 'include')

diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index 11e6434b8e71..8300a5286988 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -100,6 +100,7 @@ static inline int fsnotify_file(struct file *file, __u32 mask)
 	return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH);
 }
 
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
 /*
  * fsnotify_file_area_perm - permission hook before access to file range
  */
@@ -145,6 +146,24 @@ static inline int fsnotify_open_perm(struct file *file)
 	return fsnotify_file(file, FS_OPEN_PERM);
 }
 
+#else
+static inline int fsnotify_file_area_perm(struct file *file, int perm_mask,
+					  const loff_t *ppos, size_t count)
+{
+	return 0;
+}
+
+static inline int fsnotify_file_perm(struct file *file, int perm_mask)
+{
+	return 0;
+}
+
+static inline int fsnotify_open_perm(struct file *file)
+{
+	return 0;
+}
+#endif
+
 /*
  * fsnotify_link_count - inode's link count changed
  */
-- 
cgit v1.2.3


From 755113d7678681a137c330f7997ceb680adb644e Mon Sep 17 00:00:00 2001
From: Daniel Lezcano <daniel.lezcano@linaro.org>
Date: Tue, 9 Jan 2024 10:41:11 +0100
Subject: thermal/debugfs: Add thermal cooling device debugfs information

The thermal framework does not have any debug information except a
sysfs stat which is a bit controversial. This one allocates big chunks
of memory for every cooling devices with a high number of states and
could represent on some systems in production several megabytes of
memory for just a portion of it. As the sysfs is limited to a page
size, the output is not exploitable with large data array and gets
truncated.

The patch provides the same information than sysfs except the
transitions are dynamically allocated, thus they won't show more
events than the ones which actually occurred. There is no longer a
size limitation and it opens the field for more debugging information
where the debugfs is designed for, not sysfs.

The thermal debugfs directory structure tries to stay consistent with
the sysfs one but in a very simplified way:

thermal/
 -- cooling_devices
    |-- 0
    |   |-- clear
    |   |-- time_in_state_ms
    |   |-- total_trans
    |   `-- trans_table
    |-- 1
    |   |-- clear
    |   |-- time_in_state_ms
    |   |-- total_trans
    |   `-- trans_table
    |-- 2
    |   |-- clear
    |   |-- time_in_state_ms
    |   |-- total_trans
    |   `-- trans_table
    |-- 3
    |   |-- clear
    |   |-- time_in_state_ms
    |   |-- total_trans
    |   `-- trans_table
    `-- 4
        |-- clear
        |-- time_in_state_ms
        |-- total_trans
        `-- trans_table

The content of the files in the cooling devices directory is the same
as the sysfs one except for the trans_table which has the following
format:

Transition	Hits
1->0      	246
0->1      	246
2->1      	632
1->2      	632
3->2      	98
2->3      	98

Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
[ rjw: White space fixups, rebase ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/thermal/Kconfig           |   7 +
 drivers/thermal/Makefile          |   2 +
 drivers/thermal/thermal_core.c    |   6 +
 drivers/thermal/thermal_core.h    |   1 +
 drivers/thermal/thermal_debugfs.c | 446 ++++++++++++++++++++++++++++++++++++++
 drivers/thermal/thermal_debugfs.h |  14 ++
 drivers/thermal/thermal_helpers.c |  20 +-
 include/linux/thermal.h           |   7 +
 8 files changed, 497 insertions(+), 6 deletions(-)
 create mode 100644 drivers/thermal/thermal_debugfs.c
 create mode 100644 drivers/thermal/thermal_debugfs.h

(limited to 'include')

diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index c81a00fbca7d..3ff7add3fb7c 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -33,6 +33,13 @@ config THERMAL_STATISTICS
 
 	  If in doubt, say N.
 
+config THERMAL_DEBUGFS
+	bool "Thermal subsystem debug support"
+	depends on DEBUG_FS
+	help
+	  Say Y to allow the thermal subsystem to collect diagnostic
+	  information that can be accessed via debugfs.
+
 config THERMAL_EMERGENCY_POWEROFF_DELAY_MS
 	int "Emergency poweroff delay in milli-seconds"
 	default 0
diff --git a/drivers/thermal/Makefile b/drivers/thermal/Makefile
index c934cab309ae..0f65ae86a9c6 100644
--- a/drivers/thermal/Makefile
+++ b/drivers/thermal/Makefile
@@ -10,6 +10,8 @@ thermal_sys-y			+= thermal_trip.o thermal_helpers.o
 # netlink interface to manage the thermal framework
 thermal_sys-$(CONFIG_THERMAL_NETLINK)		+= thermal_netlink.o
 
+thermal_sys-$(CONFIG_THERMAL_DEBUGFS)	+= thermal_debugfs.o
+
 # interface to/from other layers providing sensors
 thermal_sys-$(CONFIG_THERMAL_HWMON)		+= thermal_hwmon.o
 thermal_sys-$(CONFIG_THERMAL_OF)		+= thermal_of.o
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index c0b012e075f3..5d9cc422d7ba 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -960,6 +960,8 @@ __thermal_cooling_device_register(struct device_node *np,
 
 	mutex_unlock(&thermal_list_lock);
 
+	thermal_debug_cdev_add(cdev);
+
 	return cdev;
 
 out_cooling_dev:
@@ -1166,6 +1168,8 @@ void thermal_cooling_device_unregister(struct thermal_cooling_device *cdev)
 	if (!cdev)
 		return;
 
+	thermal_debug_cdev_remove(cdev);
+
 	mutex_lock(&thermal_list_lock);
 
 	if (!thermal_cooling_device_present(cdev)) {
@@ -1629,6 +1633,8 @@ static int __init thermal_init(void)
 {
 	int result;
 
+	thermal_debug_init();
+
 	result = thermal_netlink_init();
 	if (result)
 		goto error;
diff --git a/drivers/thermal/thermal_core.h b/drivers/thermal/thermal_core.h
index 4e023d54fd27..e9c099ecdd0f 100644
--- a/drivers/thermal/thermal_core.h
+++ b/drivers/thermal/thermal_core.h
@@ -13,6 +13,7 @@
 #include <linux/thermal.h>
 
 #include "thermal_netlink.h"
+#include "thermal_debugfs.h"
 
 /* Default Thermal Governor */
 #if defined(CONFIG_THERMAL_DEFAULT_GOV_STEP_WISE)
diff --git a/drivers/thermal/thermal_debugfs.c b/drivers/thermal/thermal_debugfs.c
new file mode 100644
index 000000000000..b18bdde47847
--- /dev/null
+++ b/drivers/thermal/thermal_debugfs.c
@@ -0,0 +1,446 @@
+
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2023 Linaro Limited
+ *
+ * Author: Daniel Lezcano <daniel.lezcano@linaro.org>
+ *
+ * Thermal subsystem debug support
+ */
+#include <linux/debugfs.h>
+#include <linux/ktime.h>
+#include <linux/list.h>
+#include <linux/minmax.h>
+#include <linux/mutex.h>
+#include <linux/thermal.h>
+
+static struct dentry *d_root;
+static struct dentry *d_cdev;
+
+/*
+ * Length of the string containing the thermal zone id or the cooling
+ * device id, including the ending nul character. We can reasonably
+ * assume there won't be more than 256 thermal zones as the maximum
+ * observed today is around 32.
+ */
+#define IDSLENGTH 4
+
+/*
+ * The cooling device transition list is stored in a hash table where
+ * the size is CDEVSTATS_HASH_SIZE. The majority of cooling devices
+ * have dozen of states but some can have much more, so a hash table
+ * is more adequate in this case, because the cost of browsing the entire
+ * list when storing the transitions may not be negligible.
+ */
+#define CDEVSTATS_HASH_SIZE 16
+
+/**
+ * struct cdev_debugfs - per cooling device statistics structure
+ * A cooling device can have a high number of states. Showing the
+ * transitions on a matrix based representation can be overkill given
+ * most of the transitions won't happen and we end up with a matrix
+ * filled with zero. Instead, we show the transitions which actually
+ * happened.
+ *
+ * Every transition updates the current_state and the timestamp. The
+ * transitions and the durations are stored in lists.
+ *
+ * @total: the number of transitions for this cooling device
+ * @current_state: the current cooling device state
+ * @timestamp: the state change timestamp
+ * @transitions: an array of lists containing the state transitions
+ * @durations: an array of lists containing the residencies of each state
+ */
+struct cdev_debugfs {
+	u32 total;
+	int current_state;
+	ktime_t timestamp;
+	struct list_head transitions[CDEVSTATS_HASH_SIZE];
+	struct list_head durations[CDEVSTATS_HASH_SIZE];
+};
+
+/**
+ * struct cdev_value - Common structure for cooling device entry
+ *
+ * The following common structure allows to store the information
+ * related to the transitions and to the state residencies. They are
+ * identified with a id which is associated to a value. It is used as
+ * nodes for the "transitions" and "durations" above.
+ *
+ * @node: node to insert the structure in a list
+ * @id: identifier of the value which can be a state or a transition
+ * @residency: a ktime_t representing a state residency duration
+ * @count: a number of occurrences
+ */
+struct cdev_record {
+	struct list_head node;
+	int id;
+	union {
+                ktime_t residency;
+                u64 count;
+        };
+};
+
+/**
+ * struct thermal_debugfs - High level structure for a thermal object in debugfs
+ *
+ * The thermal_debugfs structure is the common structure used by the
+ * cooling device to compute the statistics.
+ *
+ * @d_top: top directory of the thermal object directory
+ * @lock: per object lock to protect the internals
+ *
+ * @cdev: a cooling device debug structure
+ */
+struct thermal_debugfs {
+	struct dentry *d_top;
+	struct mutex lock;
+	union {
+		struct cdev_debugfs cdev_dbg;
+	};
+};
+
+void thermal_debug_init(void)
+{
+	d_root = debugfs_create_dir("thermal", NULL);
+	if (!d_root)
+		return;
+
+	d_cdev = debugfs_create_dir("cooling_devices", d_root);
+}
+
+static struct thermal_debugfs *thermal_debugfs_add_id(struct dentry *d, int id)
+{
+	struct thermal_debugfs *thermal_dbg;
+	char ids[IDSLENGTH];
+
+	thermal_dbg = kzalloc(sizeof(*thermal_dbg), GFP_KERNEL);
+	if (!thermal_dbg)
+		return NULL;
+
+	mutex_init(&thermal_dbg->lock);
+
+	snprintf(ids, IDSLENGTH, "%d", id);
+
+	thermal_dbg->d_top = debugfs_create_dir(ids, d);
+	if (!thermal_dbg->d_top) {
+		kfree(thermal_dbg);
+		return NULL;
+	}
+
+	return thermal_dbg;
+}
+
+static void thermal_debugfs_remove_id(struct thermal_debugfs *thermal_dbg)
+{
+	if (!thermal_dbg)
+		return;
+
+	debugfs_remove(thermal_dbg->d_top);
+
+	kfree(thermal_dbg);
+}
+
+static struct cdev_record *
+thermal_debugfs_cdev_record_alloc(struct thermal_debugfs *thermal_dbg,
+				  struct list_head *lists, int id)
+{
+	struct cdev_record *cdev_record;
+
+	cdev_record = kzalloc(sizeof(*cdev_record), GFP_KERNEL);
+	if (!cdev_record)
+		return NULL;
+
+	cdev_record->id = id;
+	INIT_LIST_HEAD(&cdev_record->node);
+	list_add_tail(&cdev_record->node,
+		      &lists[cdev_record->id % CDEVSTATS_HASH_SIZE]);
+
+	return cdev_record;
+}
+
+static struct cdev_record *
+thermal_debugfs_cdev_record_find(struct thermal_debugfs *thermal_dbg,
+				 struct list_head *lists, int id)
+{
+	struct cdev_record *entry;
+
+	list_for_each_entry(entry, &lists[id % CDEVSTATS_HASH_SIZE], node)
+		if (entry->id == id)
+			return entry;
+
+	return NULL;
+}
+
+static struct cdev_record *
+thermal_debugfs_cdev_record_get(struct thermal_debugfs *thermal_dbg,
+				struct list_head *lists, int id)
+{
+	struct cdev_record *cdev_record;
+
+	cdev_record = thermal_debugfs_cdev_record_find(thermal_dbg, lists, id);
+	if (cdev_record)
+		return cdev_record;
+
+	return thermal_debugfs_cdev_record_alloc(thermal_dbg, lists, id);
+}
+
+static void thermal_debugfs_cdev_clear(struct cdev_debugfs *cdev_dbg)
+{
+	int i;
+	struct cdev_record *entry, *tmp;
+
+	for (i = 0; i < CDEVSTATS_HASH_SIZE; i++) {
+
+		list_for_each_entry_safe(entry, tmp,
+					 &cdev_dbg->transitions[i], node) {
+			list_del(&entry->node);
+			kfree(entry);
+		}
+
+		list_for_each_entry_safe(entry, tmp,
+					 &cdev_dbg->durations[i], node) {
+			list_del(&entry->node);
+			kfree(entry);
+		}
+	}
+
+	cdev_dbg->total = 0;
+}
+
+static void *cdev_seq_start(struct seq_file *s, loff_t *pos)
+{
+	struct thermal_debugfs *thermal_dbg = s->private;
+
+	mutex_lock(&thermal_dbg->lock);
+
+	return (*pos < CDEVSTATS_HASH_SIZE) ? pos : NULL;
+}
+
+static void *cdev_seq_next(struct seq_file *s, void *v, loff_t *pos)
+{
+	(*pos)++;
+
+	return (*pos < CDEVSTATS_HASH_SIZE) ? pos : NULL;
+}
+
+static void cdev_seq_stop(struct seq_file *s, void *v)
+{
+	struct thermal_debugfs *thermal_dbg = s->private;
+
+	mutex_unlock(&thermal_dbg->lock);
+}
+
+static int cdev_tt_seq_show(struct seq_file *s, void *v)
+{
+	struct thermal_debugfs *thermal_dbg = s->private;
+	struct cdev_debugfs *cdev_dbg = &thermal_dbg->cdev_dbg;
+	struct list_head *transitions = cdev_dbg->transitions;
+	struct cdev_record *entry;
+	int i = *(loff_t *)v;
+
+	if (!i)
+		seq_puts(s, "Transition\tOccurences\n");
+
+	list_for_each_entry(entry, &transitions[i], node) {
+		/*
+		 * Assuming maximum cdev states is 1024, the longer
+		 * string for a transition would be "1024->1024\0"
+		 */
+		char buffer[11];
+
+		snprintf(buffer, ARRAY_SIZE(buffer), "%d->%d",
+			 entry->id >> 16, entry->id & 0xFFFF);
+
+		seq_printf(s, "%-10s\t%-10llu\n", buffer, entry->count);
+	}
+
+	return 0;
+}
+
+static const struct seq_operations tt_sops = {
+	.start = cdev_seq_start,
+	.next = cdev_seq_next,
+	.stop = cdev_seq_stop,
+	.show = cdev_tt_seq_show,
+};
+
+DEFINE_SEQ_ATTRIBUTE(tt);
+
+static int cdev_dt_seq_show(struct seq_file *s, void *v)
+{
+	struct thermal_debugfs *thermal_dbg = s->private;
+	struct cdev_debugfs *cdev_dbg = &thermal_dbg->cdev_dbg;
+	struct list_head *durations = cdev_dbg->durations;
+	struct cdev_record *entry;
+	int i = *(loff_t *)v;
+
+	if (!i)
+		seq_puts(s, "State\tResidency\n");
+
+	list_for_each_entry(entry, &durations[i], node) {
+		s64 duration = ktime_to_ms(entry->residency);
+
+		if (entry->id == cdev_dbg->current_state)
+			duration += ktime_ms_delta(ktime_get(),
+						   cdev_dbg->timestamp);
+
+		seq_printf(s, "%-5d\t%-10llu\n", entry->id, duration);
+	}
+
+	return 0;
+}
+
+static const struct seq_operations dt_sops = {
+	.start = cdev_seq_start,
+	.next = cdev_seq_next,
+	.stop = cdev_seq_stop,
+	.show = cdev_dt_seq_show,
+};
+
+DEFINE_SEQ_ATTRIBUTE(dt);
+
+static int cdev_clear_set(void *data, u64 val)
+{
+	struct thermal_debugfs *thermal_dbg = data;
+
+	if (!val)
+		return -EINVAL;
+
+	mutex_lock(&thermal_dbg->lock);
+
+	thermal_debugfs_cdev_clear(&thermal_dbg->cdev_dbg);
+
+	mutex_unlock(&thermal_dbg->lock);
+
+	return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(cdev_clear_fops, NULL, cdev_clear_set, "%llu\n");
+
+/**
+ * thermal_debug_cdev_state_update - Update a cooling device state change
+ *
+ * Computes a transition and the duration of the previous state residency.
+ *
+ * @cdev : a pointer to a cooling device
+ * @new_state: an integer corresponding to the new cooling device state
+ */
+void thermal_debug_cdev_state_update(const struct thermal_cooling_device *cdev,
+				     int new_state)
+{
+	struct thermal_debugfs *thermal_dbg = cdev->debugfs;
+	struct cdev_debugfs *cdev_dbg;
+	struct cdev_record *cdev_record;
+	int transition, old_state;
+
+	if (!thermal_dbg || (thermal_dbg->cdev_dbg.current_state == new_state))
+		return;
+
+	mutex_lock(&thermal_dbg->lock);
+
+	cdev_dbg = &thermal_dbg->cdev_dbg;
+
+	old_state = cdev_dbg->current_state;
+
+	/*
+	 * Get the old state information in the durations list. If
+	 * this one does not exist, a new allocated one will be
+	 * returned. Recompute the total duration in the old state and
+	 * get a new timestamp for the new state.
+	 */
+	cdev_record = thermal_debugfs_cdev_record_get(thermal_dbg,
+						      cdev_dbg->durations,
+						      old_state);
+	if (cdev_record) {
+		ktime_t now = ktime_get();
+		ktime_t delta = ktime_sub(now, cdev_dbg->timestamp);
+		cdev_record->residency = ktime_add(cdev_record->residency, delta);
+		cdev_dbg->timestamp = now;
+	}
+
+	cdev_dbg->current_state = new_state;
+	transition = (old_state << 16) | new_state;
+
+	/*
+	 * Get the transition in the transitions list. If this one
+	 * does not exist, a new allocated one will be returned.
+	 * Increment the occurrence of this transition which is stored
+	 * in the value field.
+	 */
+	cdev_record = thermal_debugfs_cdev_record_get(thermal_dbg,
+						      cdev_dbg->transitions,
+						      transition);
+	if (cdev_record)
+		cdev_record->count++;
+
+	cdev_dbg->total++;
+
+	mutex_unlock(&thermal_dbg->lock);
+}
+
+/**
+ * thermal_debug_cdev_add - Add a cooling device debugfs entry
+ *
+ * Allocates a cooling device object for debug, initializes the
+ * statistics and create the entries in sysfs.
+ * @cdev: a pointer to a cooling device
+ */
+void thermal_debug_cdev_add(struct thermal_cooling_device *cdev)
+{
+	struct thermal_debugfs *thermal_dbg;
+	struct cdev_debugfs *cdev_dbg;
+	int i;
+
+	thermal_dbg = thermal_debugfs_add_id(d_cdev, cdev->id);
+	if (!thermal_dbg)
+		return;
+
+	cdev_dbg = &thermal_dbg->cdev_dbg;
+
+	for (i = 0; i < CDEVSTATS_HASH_SIZE; i++) {
+		INIT_LIST_HEAD(&cdev_dbg->transitions[i]);
+		INIT_LIST_HEAD(&cdev_dbg->durations[i]);
+	}
+
+	cdev_dbg->current_state = 0;
+	cdev_dbg->timestamp = ktime_get();
+
+	debugfs_create_file("trans_table", 0400, thermal_dbg->d_top,
+			    thermal_dbg, &tt_fops);
+
+	debugfs_create_file("time_in_state_ms", 0400, thermal_dbg->d_top,
+			    thermal_dbg, &dt_fops);
+
+	debugfs_create_file("clear", 0200, thermal_dbg->d_top,
+			    thermal_dbg, &cdev_clear_fops);
+
+	debugfs_create_u32("total_trans", 0400, thermal_dbg->d_top,
+			   &cdev_dbg->total);
+
+	cdev->debugfs = thermal_dbg;
+}
+
+/**
+ * thermal_debug_cdev_remove - Remove a cooling device debugfs entry
+ *
+ * Frees the statistics memory data and remove the debugfs entry
+ *
+ * @cdev: a pointer to a cooling device
+ */
+void thermal_debug_cdev_remove(struct thermal_cooling_device *cdev)
+{
+	struct thermal_debugfs *thermal_dbg = cdev->debugfs;
+
+	if (!thermal_dbg)
+		return;
+
+	mutex_lock(&thermal_dbg->lock);
+
+	thermal_debugfs_cdev_clear(&thermal_dbg->cdev_dbg);
+	cdev->debugfs = NULL;
+
+	mutex_unlock(&thermal_dbg->lock);
+
+	thermal_debugfs_remove_id(thermal_dbg);
+}
diff --git a/drivers/thermal/thermal_debugfs.h b/drivers/thermal/thermal_debugfs.h
new file mode 100644
index 000000000000..341499388448
--- /dev/null
+++ b/drivers/thermal/thermal_debugfs.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifdef CONFIG_THERMAL_DEBUGFS
+void thermal_debug_init(void);
+void thermal_debug_cdev_add(struct thermal_cooling_device *cdev);
+void thermal_debug_cdev_remove(struct thermal_cooling_device *cdev);
+void thermal_debug_cdev_state_update(const struct thermal_cooling_device *cdev, int state);
+#else
+static inline void thermal_debug_init(void) {}
+static inline void thermal_debug_cdev_add(struct thermal_cooling_device *cdev) {}
+static inline void thermal_debug_cdev_remove(struct thermal_cooling_device *cdev) {}
+static inline void thermal_debug_cdev_state_update(const struct thermal_cooling_device *cdev,
+						   int state) {}
+#endif /* CONFIG_THERMAL_DEBUGFS */
diff --git a/drivers/thermal/thermal_helpers.c b/drivers/thermal/thermal_helpers.c
index c3982e0f0075..8f85581693e7 100644
--- a/drivers/thermal/thermal_helpers.c
+++ b/drivers/thermal/thermal_helpers.c
@@ -146,14 +146,22 @@ unlock:
 }
 EXPORT_SYMBOL_GPL(thermal_zone_get_temp);
 
-static void thermal_cdev_set_cur_state(struct thermal_cooling_device *cdev,
-				       int target)
+static int thermal_cdev_set_cur_state(struct thermal_cooling_device *cdev, int state)
 {
-	if (cdev->ops->set_cur_state(cdev, target))
-		return;
+	int ret;
+
+	/*
+	 * No check is needed for the ops->set_cur_state as the
+	 * registering function checked the ops are correctly set
+	 */
+	ret = cdev->ops->set_cur_state(cdev, state);
+	if (!ret) {
+		thermal_notify_cdev_state_update(cdev->id, state);
+		thermal_cooling_device_stats_update(cdev, state);
+		thermal_debug_cdev_state_update(cdev, state);
+	}
 
-	thermal_notify_cdev_state_update(cdev->id, target);
-	thermal_cooling_device_stats_update(cdev, target);
+	return ret;
 }
 
 void __thermal_cdev_update(struct thermal_cooling_device *cdev)
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 9d0427da32af..7defea8fa223 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -32,6 +32,7 @@
 struct thermal_zone_device;
 struct thermal_cooling_device;
 struct thermal_instance;
+struct thermal_debugfs;
 struct thermal_attr;
 
 enum thermal_trend {
@@ -113,6 +114,9 @@ struct thermal_cooling_device {
 	struct mutex lock; /* protect thermal_instances list */
 	struct list_head thermal_instances;
 	struct list_head node;
+#ifdef CONFIG_THERMAL_DEBUGFS
+	struct thermal_debugfs *debugfs;
+#endif
 };
 
 /**
@@ -189,6 +193,9 @@ struct thermal_zone_device {
 	struct list_head node;
 	struct delayed_work poll_queue;
 	enum thermal_notify_event notify_event;
+#ifdef CONFIG_THERMAL_DEBUGFS
+	struct thermal_debugfs *debugfs;
+#endif
 	bool suspended;
 };
 
-- 
cgit v1.2.3


From 57a427c81c322c5f0cdfe7c46cdee553d18b1ec6 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Fri, 5 Jan 2024 14:45:11 +0100
Subject: thermal: core: Use kstrdup_const() during cooling device registration

Some *thermal_cooling_device_register() calls pass a string literal as
the 'type' parameter, so kstrdup_const() can be used instead of
kstrdup() to avoid a memory allocation in such cases.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
[ rjw: Subject and changelog edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/thermal/thermal_core.c | 6 +++---
 include/linux/thermal.h        | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index abf4c2390b19..dfaa6341694a 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -845,7 +845,7 @@ static void thermal_release(struct device *dev)
 			    sizeof("cooling_device") - 1)) {
 		cdev = to_cooling_device(dev);
 		thermal_cooling_device_destroy_sysfs(cdev);
-		kfree(cdev->type);
+		kfree_const(cdev->type);
 		ida_free(&thermal_cdev_ida, cdev->id);
 		kfree(cdev);
 	}
@@ -917,7 +917,7 @@ __thermal_cooling_device_register(struct device_node *np,
 	cdev->id = ret;
 	id = ret;
 
-	cdev->type = kstrdup(type ? type : "", GFP_KERNEL);
+	cdev->type = kstrdup_const(type ? type : "", GFP_KERNEL);
 	if (!cdev->type) {
 		ret = -ENOMEM;
 		goto out_ida_remove;
@@ -970,7 +970,7 @@ __thermal_cooling_device_register(struct device_node *np,
 out_cooling_dev:
 	thermal_cooling_device_destroy_sysfs(cdev);
 out_cdev_type:
-	kfree(cdev->type);
+	kfree_const(cdev->type);
 out_ida_remove:
 	ida_free(&thermal_cdev_ida, id);
 out_kfree_cdev:
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 7defea8fa223..3227335fb447 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -103,7 +103,7 @@ struct thermal_cooling_device_ops {
 
 struct thermal_cooling_device {
 	int id;
-	char *type;
+	const char *type;
 	unsigned long max_state;
 	struct device device;
 	struct device_node *np;
-- 
cgit v1.2.3


From ba5afb9a84df2e6b26a1b6389b98849cd16ea757 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Fri, 12 Jan 2024 09:09:14 +0100
Subject: fs: rework listmount() implementation

Linus pointed out that there's error handling and naming issues in the
that we should rewrite:

* Perform the access checks for the buffer before actually doing any
  work instead of doing it during the iteration.
* Rename the arguments to listmount() and do_listmount() to clarify what
  the arguments are used for.
* Get rid of the pointless ctr variable and overflow checking.
* Get rid of the pointless speculation check.

Link: https://lore.kernel.org/r/CAHk-=wjh6Cypo8WC-McXgSzCaou3UXccxB+7PVeSuGR8AjCphg@mail.gmail.com
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/namespace.c           | 50 +++++++++++++++++++++++++++---------------------
 include/linux/syscalls.h |  2 +-
 2 files changed, 29 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/fs/namespace.c b/fs/namespace.c
index ef1fd6829814..437f60e96d40 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -5042,13 +5042,12 @@ static struct mount *listmnt_next(struct mount *curr)
 	return node_to_mount(rb_next(&curr->mnt_node));
 }
 
-static ssize_t do_listmount(struct mount *first, struct path *orig, u64 mnt_id,
-			    u64 __user *buf, size_t bufsize,
-			    const struct path *root)
+static ssize_t do_listmount(struct mount *first, struct path *orig,
+			    u64 mnt_parent_id, u64 __user *mnt_ids,
+			    size_t nr_mnt_ids, const struct path *root)
 {
 	struct mount *r;
-	ssize_t ctr;
-	int err;
+	ssize_t ret;
 
 	/*
 	 * Don't trigger audit denials. We just want to determine what
@@ -5058,50 +5057,57 @@ static ssize_t do_listmount(struct mount *first, struct path *orig, u64 mnt_id,
 	    !ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 
-	err = security_sb_statfs(orig->dentry);
-	if (err)
-		return err;
+	ret = security_sb_statfs(orig->dentry);
+	if (ret)
+		return ret;
 
-	for (ctr = 0, r = first; r && ctr < bufsize; r = listmnt_next(r)) {
-		if (r->mnt_id_unique == mnt_id)
+	for (ret = 0, r = first; r && nr_mnt_ids; r = listmnt_next(r)) {
+		if (r->mnt_id_unique == mnt_parent_id)
 			continue;
 		if (!is_path_reachable(r, r->mnt.mnt_root, orig))
 			continue;
-		ctr = array_index_nospec(ctr, bufsize);
-		if (put_user(r->mnt_id_unique, buf + ctr))
+		if (put_user(r->mnt_id_unique, mnt_ids))
 			return -EFAULT;
-		if (check_add_overflow(ctr, 1, &ctr))
-			return -ERANGE;
+		mnt_ids++;
+		nr_mnt_ids--;
+		ret++;
 	}
-	return ctr;
+	return ret;
 }
 
-SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req,
-		u64 __user *, buf, size_t, bufsize, unsigned int, flags)
+SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req, u64 __user *,
+		mnt_ids, size_t, nr_mnt_ids, unsigned int, flags)
 {
 	struct mnt_namespace *ns = current->nsproxy->mnt_ns;
 	struct mnt_id_req kreq;
 	struct mount *first;
 	struct path root, orig;
-	u64 mnt_id, last_mnt_id;
+	u64 mnt_parent_id, last_mnt_id;
+	const size_t maxcount = (size_t)-1 >> 3;
 	ssize_t ret;
 
 	if (flags)
 		return -EINVAL;
 
+	if (unlikely(nr_mnt_ids > maxcount))
+		return -EFAULT;
+
+	if (!access_ok(mnt_ids, nr_mnt_ids * sizeof(*mnt_ids)))
+		return -EFAULT;
+
 	ret = copy_mnt_id_req(req, &kreq);
 	if (ret)
 		return ret;
-	mnt_id = kreq.mnt_id;
+	mnt_parent_id = kreq.mnt_id;
 	last_mnt_id = kreq.param;
 
 	down_read(&namespace_sem);
 	get_fs_root(current->fs, &root);
-	if (mnt_id == LSMT_ROOT) {
+	if (mnt_parent_id == LSMT_ROOT) {
 		orig = root;
 	} else {
 		ret = -ENOENT;
-		orig.mnt  = lookup_mnt_in_ns(mnt_id, ns);
+		orig.mnt = lookup_mnt_in_ns(mnt_parent_id, ns);
 		if (!orig.mnt)
 			goto err;
 		orig.dentry = orig.mnt->mnt_root;
@@ -5111,7 +5117,7 @@ SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req,
 	else
 		first = mnt_find_id_at(ns, last_mnt_id + 1);
 
-	ret = do_listmount(first, &orig, mnt_id, buf, bufsize, &root);
+	ret = do_listmount(first, &orig, mnt_parent_id, mnt_ids, nr_mnt_ids, &root);
 err:
 	path_put(&root);
 	up_read(&namespace_sem);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 5c0dbef55792..cdba4d0c6d4a 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -414,7 +414,7 @@ asmlinkage long sys_statmount(const struct mnt_id_req __user *req,
 			      struct statmount __user *buf, size_t bufsize,
 			      unsigned int flags);
 asmlinkage long sys_listmount(const struct mnt_id_req __user *req,
-			      u64 __user *buf, size_t bufsize,
+			      u64 __user *mnt_ids, size_t nr_mnt_ids,
 			      unsigned int flags);
 asmlinkage long sys_truncate(const char __user *path, long length);
 asmlinkage long sys_ftruncate(unsigned int fd, unsigned long length);
-- 
cgit v1.2.3


From 9181d6f8a2bb32d158de66a84164fac05e3ddd18 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 12 Jan 2024 12:28:16 +0000
Subject: net: add more sanity check in virtio_net_hdr_to_skb()

syzbot/KMSAN reports access to uninitialized data from gso_features_check() [1]

The repro use af_packet, injecting a gso packet and hdrlen == 0.

We could fix the issue making gso_features_check() more careful
while dealing with NETIF_F_TSO_MANGLEID in fast path.

Or we can make sure virtio_net_hdr_to_skb() pulls minimal network and
transport headers as intended.

Note that for GSO packets coming from untrusted sources, SKB_GSO_DODGY
bit forces a proper header validation (and pull) before the packet can
hit any device ndo_start_xmit(), thus we do not need a precise disection
at virtio_net_hdr_to_skb() stage.

[1]
BUG: KMSAN: uninit-value in skb_gso_segment include/net/gso.h:83 [inline]
BUG: KMSAN: uninit-value in validate_xmit_skb+0x10f2/0x1930 net/core/dev.c:3629
 skb_gso_segment include/net/gso.h:83 [inline]
 validate_xmit_skb+0x10f2/0x1930 net/core/dev.c:3629
 __dev_queue_xmit+0x1eac/0x5130 net/core/dev.c:4341
 dev_queue_xmit include/linux/netdevice.h:3134 [inline]
 packet_xmit+0x9c/0x6b0 net/packet/af_packet.c:276
 packet_snd net/packet/af_packet.c:3087 [inline]
 packet_sendmsg+0x8b1d/0x9f30 net/packet/af_packet.c:3119
 sock_sendmsg_nosec net/socket.c:730 [inline]
 __sock_sendmsg net/socket.c:745 [inline]
 ____sys_sendmsg+0x9c2/0xd60 net/socket.c:2584
 ___sys_sendmsg+0x28d/0x3c0 net/socket.c:2638
 __sys_sendmsg net/socket.c:2667 [inline]
 __do_sys_sendmsg net/socket.c:2676 [inline]
 __se_sys_sendmsg net/socket.c:2674 [inline]
 __x64_sys_sendmsg+0x307/0x490 net/socket.c:2674
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0x44/0x110 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x63/0x6b

Uninit was created at:
 slab_post_alloc_hook+0x129/0xa70 mm/slab.h:768
 slab_alloc_node mm/slub.c:3478 [inline]
 kmem_cache_alloc_node+0x5e9/0xb10 mm/slub.c:3523
 kmalloc_reserve+0x13d/0x4a0 net/core/skbuff.c:560
 __alloc_skb+0x318/0x740 net/core/skbuff.c:651
 alloc_skb include/linux/skbuff.h:1286 [inline]
 alloc_skb_with_frags+0xc8/0xbd0 net/core/skbuff.c:6334
 sock_alloc_send_pskb+0xa80/0xbf0 net/core/sock.c:2780
 packet_alloc_skb net/packet/af_packet.c:2936 [inline]
 packet_snd net/packet/af_packet.c:3030 [inline]
 packet_sendmsg+0x70e8/0x9f30 net/packet/af_packet.c:3119
 sock_sendmsg_nosec net/socket.c:730 [inline]
 __sock_sendmsg net/socket.c:745 [inline]
 ____sys_sendmsg+0x9c2/0xd60 net/socket.c:2584
 ___sys_sendmsg+0x28d/0x3c0 net/socket.c:2638
 __sys_sendmsg net/socket.c:2667 [inline]
 __do_sys_sendmsg net/socket.c:2676 [inline]
 __se_sys_sendmsg net/socket.c:2674 [inline]
 __x64_sys_sendmsg+0x307/0x490 net/socket.c:2674
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0x44/0x110 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x63/0x6b

CPU: 0 PID: 5025 Comm: syz-executor279 Not tainted 6.7.0-rc7-syzkaller-00003-gfbafc3e621c3 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 11/17/2023

Reported-by: syzbot+7f4d0ea3df4d4fa9a65f@syzkaller.appspotmail.com
Link: https://lore.kernel.org/netdev/0000000000005abd7b060eb160cd@google.com/
Fixes: 9274124f023b ("net: stricter validation of untrusted gso packets")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/virtio_net.h | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 27cc1d464321..4dfa9b69ca8d 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -3,6 +3,8 @@
 #define _LINUX_VIRTIO_NET_H
 
 #include <linux/if_vlan.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
 #include <linux/udp.h>
 #include <uapi/linux/tcp.h>
 #include <uapi/linux/virtio_net.h>
@@ -49,6 +51,7 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 					const struct virtio_net_hdr *hdr,
 					bool little_endian)
 {
+	unsigned int nh_min_len = sizeof(struct iphdr);
 	unsigned int gso_type = 0;
 	unsigned int thlen = 0;
 	unsigned int p_off = 0;
@@ -65,6 +68,7 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 			gso_type = SKB_GSO_TCPV6;
 			ip_proto = IPPROTO_TCP;
 			thlen = sizeof(struct tcphdr);
+			nh_min_len = sizeof(struct ipv6hdr);
 			break;
 		case VIRTIO_NET_HDR_GSO_UDP:
 			gso_type = SKB_GSO_UDP;
@@ -100,7 +104,8 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 		if (!skb_partial_csum_set(skb, start, off))
 			return -EINVAL;
 
-		p_off = skb_transport_offset(skb) + thlen;
+		nh_min_len = max_t(u32, nh_min_len, skb_transport_offset(skb));
+		p_off = nh_min_len + thlen;
 		if (!pskb_may_pull(skb, p_off))
 			return -EINVAL;
 	} else {
@@ -140,7 +145,7 @@ retry:
 
 			skb_set_transport_header(skb, keys.control.thoff);
 		} else if (gso_type) {
-			p_off = thlen;
+			p_off = nh_min_len + thlen;
 			if (!pskb_may_pull(skb, p_off))
 				return -EINVAL;
 		}
-- 
cgit v1.2.3


From 894d7508316e7ad722df597d68b4b1797a9eee11 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Fri, 12 Jan 2024 17:13:14 +0100
Subject: net: netdev_queue: netdev_txq_completed_mb(): fix wake condition

netif_txq_try_stop() uses "get_desc >= start_thrs" as the check for
the call to netif_tx_start_queue().

Use ">=" i netdev_txq_completed_mb(), too.

Fixes: c91c46de6bbc ("net: provide macros for commonly copied lockless queue stop/wake code")
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netdev_queues.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h
index d68b0a483431..8b8ed4e13d74 100644
--- a/include/net/netdev_queues.h
+++ b/include/net/netdev_queues.h
@@ -128,7 +128,7 @@ netdev_txq_completed_mb(struct netdev_queue *dev_queue,
 		netdev_txq_completed_mb(txq, pkts, bytes);		\
 									\
 		_res = -1;						\
-		if (pkts && likely(get_desc > start_thrs)) {		\
+		if (pkts && likely(get_desc >= start_thrs)) {		\
 			_res = 1;					\
 			if (unlikely(netif_tx_queue_stopped(txq)) &&	\
 			    !(down_cond)) {				\
-- 
cgit v1.2.3


From 34d946b723b53488ab39d8ac540ddf9db255317a Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Tue, 9 Jan 2024 00:25:48 -0500
Subject: i3c: master: fix kernel-doc check warning

Fix warning found by
	'scripts/kernel-doc -v -none include/linux/i3c/master.h'

include/linux/i3c/master.h:457: warning: Function parameter or member 'enable_hotjoin' not described in 'i3c_master_controller_ops'
include/linux/i3c/master.h:457: warning: Function parameter or member 'disable_hotjoin' not described in 'i3c_master_controller_ops'
include/linux/i3c/master.h:499: warning: Function parameter or member 'hotjoin' not described in 'i3c_master_controller'

Signed-off-by: Frank Li <Frank.Li@nxp.com>
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/r/20240109052548.2128133-1-Frank.Li@nxp.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 include/linux/i3c/master.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/linux/i3c/master.h b/include/linux/i3c/master.h
index 1ecd73b17ff5..0ca27dd86956 100644
--- a/include/linux/i3c/master.h
+++ b/include/linux/i3c/master.h
@@ -433,6 +433,8 @@ struct i3c_bus {
  *		      for a future IBI
  *		      This method is mandatory only if ->request_ibi is not
  *		      NULL.
+ * @enable_hotjoin: enable hot join event detect.
+ * @disable_hotjoin: disable hot join event detect.
  */
 struct i3c_master_controller_ops {
 	int (*bus_init)(struct i3c_master_controller *master);
@@ -474,6 +476,7 @@ struct i3c_master_controller_ops {
  * @ops: master operations. See &struct i3c_master_controller_ops
  * @secondary: true if the master is a secondary master
  * @init_done: true when the bus initialization is done
+ * @hotjoin: true if the master support hotjoin
  * @boardinfo.i3c: list of I3C  boardinfo objects
  * @boardinfo.i2c: list of I2C boardinfo objects
  * @boardinfo: board-level information attached to devices connected on the bus
-- 
cgit v1.2.3


From aaefabc4a5f7ae48682c4d2d5d10faaf95c08eb9 Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Tue, 7 Nov 2023 10:44:41 +0800
Subject: ceph: try to allocate a smaller extent map for sparse read

In fscrypt case and for a smaller read length we can predict the
max count of the extent map. And for small read length use cases
this could save some memories.

[ idryomov: squash into a single patch to avoid build break, drop
  redundant variable in ceph_alloc_sparse_ext_map() ]

Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/addr.c                  |  4 +++-
 fs/ceph/file.c                  |  8 ++++++--
 fs/ceph/super.h                 | 14 ++++++++++++++
 include/linux/ceph/osd_client.h |  7 +++++--
 4 files changed, 28 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 85be3bf18cdf..a5caafc1859e 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -357,6 +357,7 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 	u64 len = subreq->len;
 	bool sparse = IS_ENCRYPTED(inode) || ceph_test_mount_opt(fsc, SPARSEREAD);
 	u64 off = subreq->start;
+	int extent_cnt;
 
 	if (ceph_inode_is_shutdown(inode)) {
 		err = -EIO;
@@ -379,7 +380,8 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 	}
 
 	if (sparse) {
-		err = ceph_alloc_sparse_ext_map(&req->r_ops[0]);
+		extent_cnt = __ceph_sparse_read_ext_count(inode, len);
+		err = ceph_alloc_sparse_ext_map(&req->r_ops[0], extent_cnt);
 		if (err)
 			goto out;
 	}
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 3b5aae29e944..4dde0da10079 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1028,6 +1028,7 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 		struct ceph_osd_req_op *op;
 		u64 read_off = off;
 		u64 read_len = len;
+		int extent_cnt;
 
 		/* determine new offset/length if encrypted */
 		ceph_fscrypt_adjust_off_and_len(inode, &read_off, &read_len);
@@ -1067,7 +1068,8 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos,
 
 		op = &req->r_ops[0];
 		if (sparse) {
-			ret = ceph_alloc_sparse_ext_map(op);
+			extent_cnt = __ceph_sparse_read_ext_count(inode, read_len);
+			ret = ceph_alloc_sparse_ext_map(op, extent_cnt);
 			if (ret) {
 				ceph_osdc_put_request(req);
 				break;
@@ -1464,6 +1466,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 		ssize_t len;
 		struct ceph_osd_req_op *op;
 		int readop = sparse ? CEPH_OSD_OP_SPARSE_READ : CEPH_OSD_OP_READ;
+		int extent_cnt;
 
 		if (write)
 			size = min_t(u64, size, fsc->mount_options->wsize);
@@ -1527,7 +1530,8 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 		osd_req_op_extent_osd_data_bvecs(req, 0, bvecs, num_pages, len);
 		op = &req->r_ops[0];
 		if (sparse) {
-			ret = ceph_alloc_sparse_ext_map(op);
+			extent_cnt = __ceph_sparse_read_ext_count(inode, size);
+			ret = ceph_alloc_sparse_ext_map(op, extent_cnt);
 			if (ret) {
 				ceph_osdc_put_request(req);
 				break;
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index fe0f64a0acb2..b06e2bc86221 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -3,6 +3,7 @@
 #define _FS_CEPH_SUPER_H
 
 #include <linux/ceph/ceph_debug.h>
+#include <linux/ceph/osd_client.h>
 
 #include <asm/unaligned.h>
 #include <linux/backing-dev.h>
@@ -1407,6 +1408,19 @@ static inline void __ceph_update_quota(struct ceph_inode_info *ci,
 		ceph_adjust_quota_realms_count(&ci->netfs.inode, has_quota);
 }
 
+static inline int __ceph_sparse_read_ext_count(struct inode *inode, u64 len)
+{
+	int cnt = 0;
+
+	if (IS_ENCRYPTED(inode)) {
+		cnt = len >> CEPH_FSCRYPT_BLOCK_SHIFT;
+		if (cnt > CEPH_SPARSE_EXT_ARRAY_INITIAL)
+			cnt = 0;
+	}
+
+	return cnt;
+}
+
 extern void ceph_handle_quota(struct ceph_mds_client *mdsc,
 			      struct ceph_mds_session *session,
 			      struct ceph_msg *msg);
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index b8610e9d2471..fa018d5864e7 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -572,9 +572,12 @@ int __ceph_alloc_sparse_ext_map(struct ceph_osd_req_op *op, int cnt);
  */
 #define CEPH_SPARSE_EXT_ARRAY_INITIAL  16
 
-static inline int ceph_alloc_sparse_ext_map(struct ceph_osd_req_op *op)
+static inline int ceph_alloc_sparse_ext_map(struct ceph_osd_req_op *op, int cnt)
 {
-	return __ceph_alloc_sparse_ext_map(op, CEPH_SPARSE_EXT_ARRAY_INITIAL);
+	if (!cnt)
+		cnt = CEPH_SPARSE_EXT_ARRAY_INITIAL;
+
+	return __ceph_alloc_sparse_ext_map(op, cnt);
 }
 
 extern void ceph_osdc_get_request(struct ceph_osd_request *req);
-- 
cgit v1.2.3


From 832b371097eb928d077c827b8f117bf5b99d35c0 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Mon, 15 Jan 2024 16:05:26 +0100
Subject: gpiolib: Fix scope-based gpio_device refcounting

Commit 9e4555d1e54a ("gpiolib: add support for scope-based management to
gpio_device") sought to add scope-based gpio_device refcounting, but
erroneously forgot a negation of IS_ERR_OR_NULL().

As a result, gpio_device_put() is not called if the gpio_device pointer
is valid (meaning the ref is leaked), but only called if the pointer is
NULL or an ERR_PTR().

While at it drop a superfluous trailing semicolon.

Fixes: 9e4555d1e54a ("gpiolib: add support for scope-based management to gpio_device")
Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 include/linux/gpio/driver.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index e846bd4e7559..9a5c6c76e653 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -635,7 +635,7 @@ struct gpio_device *gpio_device_get(struct gpio_device *gdev);
 void gpio_device_put(struct gpio_device *gdev);
 
 DEFINE_FREE(gpio_device_put, struct gpio_device *,
-	    if (IS_ERR_OR_NULL(_T)) gpio_device_put(_T));
+	    if (!IS_ERR_OR_NULL(_T)) gpio_device_put(_T))
 
 struct device *gpio_device_to_device(struct gpio_device *gdev);
 
-- 
cgit v1.2.3


From 2db6b72c989763e30fab83b186e9263fece26bc6 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Wed, 6 Dec 2023 12:17:51 -0600
Subject: PCI: Fix kernel-doc issues

Fix kernel-doc issues reported by
"find include -name \*pci\* | xargs scripts/kernel-doc -none":

  include/linux/pci.h:731: warning: Function parameter or member 'pdev' not described in 'pci_is_vga'
  include/linux/pci-epc.h:154: warning: Function parameter or member 'list_lock' not described in 'pci_epc'
  include/linux/pci-epf.h:83: warning: expecting prototype for struct pci_epf_event_ops. Prototype was for struct pci_epc_event_ops instead

Link: https://lore.kernel.org/r/20240111162850.2177655-1-helgaas@kernel.org
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Acked-by: Sui Jingfeng <suijingfeng@loongson.cn>
---
 include/linux/pci-epc.h | 2 +-
 include/linux/pci-epf.h | 2 +-
 include/linux/pci.h     | 1 +
 3 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h
index 5cb694031072..bfe41b03b70c 100644
--- a/include/linux/pci-epc.h
+++ b/include/linux/pci-epc.h
@@ -122,7 +122,7 @@ struct pci_epc_mem {
  * struct pci_epc - represents the PCI EPC device
  * @dev: PCI EPC device
  * @pci_epf: list of endpoint functions present in this EPC device
- * list_lock: Mutex for protecting pci_epf list
+ * @list_lock: Mutex for protecting pci_epf list
  * @ops: function pointers for performing endpoint operations
  * @windows: array of address space of the endpoint controller
  * @mem: first window of the endpoint controller, which corresponds to
diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h
index 3f44b6aec477..92d0b71d33d7 100644
--- a/include/linux/pci-epf.h
+++ b/include/linux/pci-epf.h
@@ -68,7 +68,7 @@ struct pci_epf_ops {
 };
 
 /**
- * struct pci_epf_event_ops - Callbacks for capturing the EPC events
+ * struct pci_epc_event_ops - Callbacks for capturing the EPC events
  * @core_init: Callback for the EPC initialization complete event
  * @link_up: Callback for the EPC link up event
  * @link_down: Callback for the EPC link down event
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 1a89dc66f89a..eb45087d7e00 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -715,6 +715,7 @@ static inline bool pci_is_bridge(struct pci_dev *dev)
 
 /**
  * pci_is_vga - check if the PCI device is a VGA device
+ * @pdev: PCI device
  *
  * The PCI Code and ID Assignment spec, r1.15, secs 1.4 and 1.1, define
  * VGA Base Class and Sub-Classes:
-- 
cgit v1.2.3


From 5f4c01f1e3c7b0c8d1e5dd6f080531de7aa5e47b Mon Sep 17 00:00:00 2001
From: Leonardo Bras <leobras@redhat.com>
Date: Mon, 15 Jan 2024 17:19:34 -0300
Subject: spinlock: Fix failing build for PREEMPT_RT

Since 1d71b30e1f85 ("sched.h: Move (spin|rwlock)_needbreak() to
spinlock.h") build fails for PREEMPT_RT, since there is no definition
available of either spin_needbreak() and rwlock_needbreak().

Since it was moved on the mentioned commit, it was placed inside a
!PREEMPT_RT part of the code, making it out of reach for an RT kernel.

Fix this by moving code it a few lines down so it can be reached by an
RT build, where it can also make use of the *_is_contended() definition
added by the spinlock_rt.h.

Fixes: d1d71b30e1f85 ("sched.h: Move (spin|rwlock)_needbreak() to
spinlock.h")
Signed-off-by: Leonardo Bras <leobras@redhat.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Acked-by: Waiman Long <longman@redhat.com>
---
 include/linux/spinlock.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 0c71f06454d9..b5c59fdad160 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -449,6 +449,12 @@ static __always_inline int spin_is_contended(spinlock_t *lock)
 	return raw_spin_is_contended(&lock->rlock);
 }
 
+#define assert_spin_locked(lock)	assert_raw_spin_locked(&(lock)->rlock)
+
+#else  /* !CONFIG_PREEMPT_RT */
+# include <linux/spinlock_rt.h>
+#endif /* CONFIG_PREEMPT_RT */
+
 /*
  * Does a critical section need to be broken due to another
  * task waiting?: (technically does not depend on CONFIG_PREEMPTION,
@@ -480,12 +486,6 @@ static inline int rwlock_needbreak(rwlock_t *lock)
 #endif
 }
 
-#define assert_spin_locked(lock)	assert_raw_spin_locked(&(lock)->rlock)
-
-#else  /* !CONFIG_PREEMPT_RT */
-# include <linux/spinlock_rt.h>
-#endif /* CONFIG_PREEMPT_RT */
-
 /*
  * Pull the atomic_t declaration:
  * (asm-mips/atomic.h needs above definitions)
-- 
cgit v1.2.3


From 7bed6f3d08b7af27b7015da8dc3acf2b9c1f21d7 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Tue, 16 Jan 2024 21:29:59 +0000
Subject: block: Fix iterating over an empty bio with bio_for_each_folio_all

If the bio contains no data, bio_first_folio() calls page_folio() on a
NULL pointer and oopses.  Move the test that we've reached the end of
the bio from bio_next_folio() to bio_first_folio().

Reported-by: syzbot+8b23309d5788a79d3eea@syzkaller.appspotmail.com
Reported-by: syzbot+004c1e0fced2b4bc3dcc@syzkaller.appspotmail.com
Fixes: 640d1930bef4 ("block: Add bio_for_each_folio_all()")
Cc: stable@vger.kernel.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Link: https://lore.kernel.org/r/20240116212959.3413014-1-willy@infradead.org
[axboe: add unlikely() to error case]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/bio.h | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/bio.h b/include/linux/bio.h
index ec4db73e5f4e..875d792bffff 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -286,6 +286,11 @@ static inline void bio_first_folio(struct folio_iter *fi, struct bio *bio,
 {
 	struct bio_vec *bvec = bio_first_bvec_all(bio) + i;
 
+	if (unlikely(i >= bio->bi_vcnt)) {
+		fi->folio = NULL;
+		return;
+	}
+
 	fi->folio = page_folio(bvec->bv_page);
 	fi->offset = bvec->bv_offset +
 			PAGE_SIZE * (bvec->bv_page - &fi->folio->page);
@@ -303,10 +308,8 @@ static inline void bio_next_folio(struct folio_iter *fi, struct bio *bio)
 		fi->offset = 0;
 		fi->length = min(folio_size(fi->folio), fi->_seg_count);
 		fi->_next = folio_next(fi->folio);
-	} else if (fi->_i + 1 < bio->bi_vcnt) {
-		bio_first_folio(fi, bio, fi->_i + 1);
 	} else {
-		fi->folio = NULL;
+		bio_first_folio(fi, bio, fi->_i + 1);
 	}
 }
 
-- 
cgit v1.2.3


From a54e72197037d2c9bfcd70dddaac8c8ccb5b41ba Mon Sep 17 00:00:00 2001
From: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Date: Thu, 11 Jan 2024 23:06:39 +0800
Subject: netfilter: propagate net to nf_bridge_get_physindev

This is a preparation patch for replacing physindev with physinif on
nf_bridge_info structure. We will use dev_get_by_index_rcu to resolve
device, when needed, and it requires net to be available.

Signed-off-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter_bridge.h           |  2 +-
 net/ipv4/netfilter/nf_reject_ipv4.c        |  2 +-
 net/ipv6/netfilter/nf_reject_ipv6.c        |  2 +-
 net/netfilter/ipset/ip_set_hash_netiface.c |  8 ++++----
 net/netfilter/nf_log_syslog.c              | 13 +++++++------
 net/netfilter/nf_queue.c                   |  2 +-
 net/netfilter/xt_physdev.c                 |  2 +-
 7 files changed, 16 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h
index f980edfdd278..e927b9a15a55 100644
--- a/include/linux/netfilter_bridge.h
+++ b/include/linux/netfilter_bridge.h
@@ -56,7 +56,7 @@ static inline int nf_bridge_get_physoutif(const struct sk_buff *skb)
 }
 
 static inline struct net_device *
-nf_bridge_get_physindev(const struct sk_buff *skb)
+nf_bridge_get_physindev(const struct sk_buff *skb, struct net *net)
 {
 	const struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 
diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c
index f01b038fc1cd..86e7d390671a 100644
--- a/net/ipv4/netfilter/nf_reject_ipv4.c
+++ b/net/ipv4/netfilter/nf_reject_ipv4.c
@@ -289,7 +289,7 @@ void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb,
 	 * build the eth header using the original destination's MAC as the
 	 * source, and send the RST packet directly.
 	 */
-	br_indev = nf_bridge_get_physindev(oldskb);
+	br_indev = nf_bridge_get_physindev(oldskb, net);
 	if (br_indev) {
 		struct ethhdr *oeth = eth_hdr(oldskb);
 
diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c
index d45bc54b7ea5..27b2164f4c43 100644
--- a/net/ipv6/netfilter/nf_reject_ipv6.c
+++ b/net/ipv6/netfilter/nf_reject_ipv6.c
@@ -354,7 +354,7 @@ void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb,
 	 * build the eth header using the original destination's MAC as the
 	 * source, and send the RST packet directly.
 	 */
-	br_indev = nf_bridge_get_physindev(oldskb);
+	br_indev = nf_bridge_get_physindev(oldskb, net);
 	if (br_indev) {
 		struct ethhdr *oeth = eth_hdr(oldskb);
 
diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c
index 95aeb31c60e0..30a655e5c4fd 100644
--- a/net/netfilter/ipset/ip_set_hash_netiface.c
+++ b/net/netfilter/ipset/ip_set_hash_netiface.c
@@ -138,9 +138,9 @@ hash_netiface4_data_next(struct hash_netiface4_elem *next,
 #include "ip_set_hash_gen.h"
 
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-static const char *get_physindev_name(const struct sk_buff *skb)
+static const char *get_physindev_name(const struct sk_buff *skb, struct net *net)
 {
-	struct net_device *dev = nf_bridge_get_physindev(skb);
+	struct net_device *dev = nf_bridge_get_physindev(skb, net);
 
 	return dev ? dev->name : NULL;
 }
@@ -177,7 +177,7 @@ hash_netiface4_kadt(struct ip_set *set, const struct sk_buff *skb,
 
 	if (opt->cmdflags & IPSET_FLAG_PHYSDEV) {
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-		const char *eiface = SRCDIR ? get_physindev_name(skb) :
+		const char *eiface = SRCDIR ? get_physindev_name(skb, xt_net(par)) :
 					      get_physoutdev_name(skb);
 
 		if (!eiface)
@@ -395,7 +395,7 @@ hash_netiface6_kadt(struct ip_set *set, const struct sk_buff *skb,
 
 	if (opt->cmdflags & IPSET_FLAG_PHYSDEV) {
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-		const char *eiface = SRCDIR ? get_physindev_name(skb) :
+		const char *eiface = SRCDIR ? get_physindev_name(skb, xt_net(par)) :
 					      get_physoutdev_name(skb);
 
 		if (!eiface)
diff --git a/net/netfilter/nf_log_syslog.c b/net/netfilter/nf_log_syslog.c
index c66689ad2b49..58402226045e 100644
--- a/net/netfilter/nf_log_syslog.c
+++ b/net/netfilter/nf_log_syslog.c
@@ -111,7 +111,8 @@ nf_log_dump_packet_common(struct nf_log_buf *m, u8 pf,
 			  unsigned int hooknum, const struct sk_buff *skb,
 			  const struct net_device *in,
 			  const struct net_device *out,
-			  const struct nf_loginfo *loginfo, const char *prefix)
+			  const struct nf_loginfo *loginfo, const char *prefix,
+			  struct net *net)
 {
 	const struct net_device *physoutdev __maybe_unused;
 	const struct net_device *physindev __maybe_unused;
@@ -121,7 +122,7 @@ nf_log_dump_packet_common(struct nf_log_buf *m, u8 pf,
 			in ? in->name : "",
 			out ? out->name : "");
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-	physindev = nf_bridge_get_physindev(skb);
+	physindev = nf_bridge_get_physindev(skb, net);
 	if (physindev && in != physindev)
 		nf_log_buf_add(m, "PHYSIN=%s ", physindev->name);
 	physoutdev = nf_bridge_get_physoutdev(skb);
@@ -148,7 +149,7 @@ static void nf_log_arp_packet(struct net *net, u_int8_t pf,
 		loginfo = &default_loginfo;
 
 	nf_log_dump_packet_common(m, pf, hooknum, skb, in, out, loginfo,
-				  prefix);
+				  prefix, net);
 	dump_arp_packet(m, loginfo, skb, skb_network_offset(skb));
 
 	nf_log_buf_close(m);
@@ -845,7 +846,7 @@ static void nf_log_ip_packet(struct net *net, u_int8_t pf,
 		loginfo = &default_loginfo;
 
 	nf_log_dump_packet_common(m, pf, hooknum, skb, in,
-				  out, loginfo, prefix);
+				  out, loginfo, prefix, net);
 
 	if (in)
 		dump_mac_header(m, loginfo, skb);
@@ -880,7 +881,7 @@ static void nf_log_ip6_packet(struct net *net, u_int8_t pf,
 		loginfo = &default_loginfo;
 
 	nf_log_dump_packet_common(m, pf, hooknum, skb, in, out,
-				  loginfo, prefix);
+				  loginfo, prefix, net);
 
 	if (in)
 		dump_mac_header(m, loginfo, skb);
@@ -916,7 +917,7 @@ static void nf_log_unknown_packet(struct net *net, u_int8_t pf,
 		loginfo = &default_loginfo;
 
 	nf_log_dump_packet_common(m, pf, hooknum, skb, in, out, loginfo,
-				  prefix);
+				  prefix, net);
 
 	dump_mac_header(m, loginfo, skb);
 
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index 3dfcb3ac5cb4..e2f334f70281 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -84,7 +84,7 @@ static void __nf_queue_entry_init_physdevs(struct nf_queue_entry *entry)
 	const struct sk_buff *skb = entry->skb;
 
 	if (nf_bridge_info_exists(skb)) {
-		entry->physin = nf_bridge_get_physindev(skb);
+		entry->physin = nf_bridge_get_physindev(skb, entry->state.net);
 		entry->physout = nf_bridge_get_physoutdev(skb);
 	} else {
 		entry->physin = NULL;
diff --git a/net/netfilter/xt_physdev.c b/net/netfilter/xt_physdev.c
index ec6ed6fda96c..343e65f377d4 100644
--- a/net/netfilter/xt_physdev.c
+++ b/net/netfilter/xt_physdev.c
@@ -59,7 +59,7 @@ physdev_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	    (!!outdev ^ !(info->invert & XT_PHYSDEV_OP_BRIDGED)))
 		return false;
 
-	physdev = nf_bridge_get_physindev(skb);
+	physdev = nf_bridge_get_physindev(skb, xt_net(par));
 	indev = physdev ? physdev->name : NULL;
 
 	if ((info->bitmask & XT_PHYSDEV_OP_ISIN &&
-- 
cgit v1.2.3


From 9874808878d9eed407e3977fd11fee49de1e1d86 Mon Sep 17 00:00:00 2001
From: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Date: Thu, 11 Jan 2024 23:06:40 +0800
Subject: netfilter: bridge: replace physindev with physinif in nf_bridge_info

An skb can be added to a neigh->arp_queue while waiting for an arp
reply. Where original skb's skb->dev can be different to neigh's
neigh->dev. For instance in case of bridging dnated skb from one veth to
another, the skb would be added to a neigh->arp_queue of the bridge.

As skb->dev can be reset back to nf_bridge->physindev and used, and as
there is no explicit mechanism that prevents this physindev from been
freed under us (for instance neigh_flush_dev doesn't cleanup skbs from
different device's neigh queue) we can crash on e.g. this stack:

arp_process
  neigh_update
    skb = __skb_dequeue(&neigh->arp_queue)
      neigh_resolve_output(..., skb)
        ...
          br_nf_dev_xmit
            br_nf_pre_routing_finish_bridge_slow
              skb->dev = nf_bridge->physindev
              br_handle_frame_finish

Let's use plain ifindex instead of net_device link. To peek into the
original net_device we will use dev_get_by_index_rcu(). Thus either we
get device and are safe to use it or we don't get it and drop skb.

Fixes: c4e70a87d975 ("netfilter: bridge: rename br_netfilter.c to br_netfilter_hooks.c")
Suggested-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter_bridge.h    |  4 ++--
 include/linux/skbuff.h              |  2 +-
 net/bridge/br_netfilter_hooks.c     | 42 ++++++++++++++++++++++++++++++-------
 net/bridge/br_netfilter_ipv6.c      | 14 +++++++++----
 net/ipv4/netfilter/nf_reject_ipv4.c |  9 +++++---
 net/ipv6/netfilter/nf_reject_ipv6.c | 11 +++++++---
 6 files changed, 61 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h
index e927b9a15a55..743475ca7e9d 100644
--- a/include/linux/netfilter_bridge.h
+++ b/include/linux/netfilter_bridge.h
@@ -42,7 +42,7 @@ static inline int nf_bridge_get_physinif(const struct sk_buff *skb)
 	if (!nf_bridge)
 		return 0;
 
-	return nf_bridge->physindev ? nf_bridge->physindev->ifindex : 0;
+	return nf_bridge->physinif;
 }
 
 static inline int nf_bridge_get_physoutif(const struct sk_buff *skb)
@@ -60,7 +60,7 @@ nf_bridge_get_physindev(const struct sk_buff *skb, struct net *net)
 {
 	const struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 
-	return nf_bridge ? nf_bridge->physindev : NULL;
+	return nf_bridge ? dev_get_by_index_rcu(net, nf_bridge->physinif) : NULL;
 }
 
 static inline struct net_device *
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index a5ae952454c8..2dde34c29203 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -295,7 +295,7 @@ struct nf_bridge_info {
 	u8			bridged_dnat:1;
 	u8			sabotage_in_done:1;
 	__u16			frag_max_size;
-	struct net_device	*physindev;
+	int			physinif;
 
 	/* always valid & non-NULL from FORWARD on, for physdev match */
 	struct net_device	*physoutdev;
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 6adcb45bca75..ed1720890757 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -279,8 +279,17 @@ int br_nf_pre_routing_finish_bridge(struct net *net, struct sock *sk, struct sk_
 
 		if ((READ_ONCE(neigh->nud_state) & NUD_CONNECTED) &&
 		    READ_ONCE(neigh->hh.hh_len)) {
+			struct net_device *br_indev;
+
+			br_indev = nf_bridge_get_physindev(skb, net);
+			if (!br_indev) {
+				neigh_release(neigh);
+				goto free_skb;
+			}
+
 			neigh_hh_bridge(&neigh->hh, skb);
-			skb->dev = nf_bridge->physindev;
+			skb->dev = br_indev;
+
 			ret = br_handle_frame_finish(net, sk, skb);
 		} else {
 			/* the neighbour function below overwrites the complete
@@ -352,12 +361,18 @@ br_nf_ipv4_daddr_was_changed(const struct sk_buff *skb,
  */
 static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
-	struct net_device *dev = skb->dev;
+	struct net_device *dev = skb->dev, *br_indev;
 	struct iphdr *iph = ip_hdr(skb);
 	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 	struct rtable *rt;
 	int err;
 
+	br_indev = nf_bridge_get_physindev(skb, net);
+	if (!br_indev) {
+		kfree_skb(skb);
+		return 0;
+	}
+
 	nf_bridge->frag_max_size = IPCB(skb)->frag_max_size;
 
 	if (nf_bridge->pkt_otherhost) {
@@ -397,7 +412,7 @@ free_skb:
 		} else {
 			if (skb_dst(skb)->dev == dev) {
 bridged_dnat:
-				skb->dev = nf_bridge->physindev;
+				skb->dev = br_indev;
 				nf_bridge_update_protocol(skb);
 				nf_bridge_push_encap_header(skb);
 				br_nf_hook_thresh(NF_BR_PRE_ROUTING,
@@ -410,7 +425,7 @@ bridged_dnat:
 			skb->pkt_type = PACKET_HOST;
 		}
 	} else {
-		rt = bridge_parent_rtable(nf_bridge->physindev);
+		rt = bridge_parent_rtable(br_indev);
 		if (!rt) {
 			kfree_skb(skb);
 			return 0;
@@ -419,7 +434,7 @@ bridged_dnat:
 		skb_dst_set_noref(skb, &rt->dst);
 	}
 
-	skb->dev = nf_bridge->physindev;
+	skb->dev = br_indev;
 	nf_bridge_update_protocol(skb);
 	nf_bridge_push_encap_header(skb);
 	br_nf_hook_thresh(NF_BR_PRE_ROUTING, net, sk, skb, skb->dev, NULL,
@@ -456,7 +471,7 @@ struct net_device *setup_pre_routing(struct sk_buff *skb, const struct net *net)
 	}
 
 	nf_bridge->in_prerouting = 1;
-	nf_bridge->physindev = skb->dev;
+	nf_bridge->physinif = skb->dev->ifindex;
 	skb->dev = brnf_get_logical_dev(skb, skb->dev, net);
 
 	if (skb->protocol == htons(ETH_P_8021Q))
@@ -553,7 +568,11 @@ static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff
 		if (skb->protocol == htons(ETH_P_IPV6))
 			nf_bridge->frag_max_size = IP6CB(skb)->frag_max_size;
 
-		in = nf_bridge->physindev;
+		in = nf_bridge_get_physindev(skb, net);
+		if (!in) {
+			kfree_skb(skb);
+			return 0;
+		}
 		if (nf_bridge->pkt_otherhost) {
 			skb->pkt_type = PACKET_OTHERHOST;
 			nf_bridge->pkt_otherhost = false;
@@ -899,6 +918,13 @@ static unsigned int ip_sabotage_in(void *priv,
 static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb)
 {
 	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
+	struct net_device *br_indev;
+
+	br_indev = nf_bridge_get_physindev(skb, dev_net(skb->dev));
+	if (!br_indev) {
+		kfree_skb(skb);
+		return;
+	}
 
 	skb_pull(skb, ETH_HLEN);
 	nf_bridge->bridged_dnat = 0;
@@ -908,7 +934,7 @@ static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb)
 	skb_copy_to_linear_data_offset(skb, -(ETH_HLEN - ETH_ALEN),
 				       nf_bridge->neigh_header,
 				       ETH_HLEN - ETH_ALEN);
-	skb->dev = nf_bridge->physindev;
+	skb->dev = br_indev;
 
 	nf_bridge->physoutdev = NULL;
 	br_handle_frame_finish(dev_net(skb->dev), NULL, skb);
diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c
index 2e24a743f917..e0421eaa3abc 100644
--- a/net/bridge/br_netfilter_ipv6.c
+++ b/net/bridge/br_netfilter_ipv6.c
@@ -102,9 +102,15 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc
 {
 	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 	struct rtable *rt;
-	struct net_device *dev = skb->dev;
+	struct net_device *dev = skb->dev, *br_indev;
 	const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops();
 
+	br_indev = nf_bridge_get_physindev(skb, net);
+	if (!br_indev) {
+		kfree_skb(skb);
+		return 0;
+	}
+
 	nf_bridge->frag_max_size = IP6CB(skb)->frag_max_size;
 
 	if (nf_bridge->pkt_otherhost) {
@@ -122,7 +128,7 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc
 		}
 
 		if (skb_dst(skb)->dev == dev) {
-			skb->dev = nf_bridge->physindev;
+			skb->dev = br_indev;
 			nf_bridge_update_protocol(skb);
 			nf_bridge_push_encap_header(skb);
 			br_nf_hook_thresh(NF_BR_PRE_ROUTING,
@@ -133,7 +139,7 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc
 		ether_addr_copy(eth_hdr(skb)->h_dest, dev->dev_addr);
 		skb->pkt_type = PACKET_HOST;
 	} else {
-		rt = bridge_parent_rtable(nf_bridge->physindev);
+		rt = bridge_parent_rtable(br_indev);
 		if (!rt) {
 			kfree_skb(skb);
 			return 0;
@@ -142,7 +148,7 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc
 		skb_dst_set_noref(skb, &rt->dst);
 	}
 
-	skb->dev = nf_bridge->physindev;
+	skb->dev = br_indev;
 	nf_bridge_update_protocol(skb);
 	nf_bridge_push_encap_header(skb);
 	br_nf_hook_thresh(NF_BR_PRE_ROUTING, net, sk, skb,
diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c
index 86e7d390671a..04504b2b51df 100644
--- a/net/ipv4/netfilter/nf_reject_ipv4.c
+++ b/net/ipv4/netfilter/nf_reject_ipv4.c
@@ -239,7 +239,6 @@ static int nf_reject_fill_skb_dst(struct sk_buff *skb_in)
 void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb,
 		   int hook)
 {
-	struct net_device *br_indev __maybe_unused;
 	struct sk_buff *nskb;
 	struct iphdr *niph;
 	const struct tcphdr *oth;
@@ -289,9 +288,13 @@ void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb,
 	 * build the eth header using the original destination's MAC as the
 	 * source, and send the RST packet directly.
 	 */
-	br_indev = nf_bridge_get_physindev(oldskb, net);
-	if (br_indev) {
+	if (nf_bridge_info_exists(oldskb)) {
 		struct ethhdr *oeth = eth_hdr(oldskb);
+		struct net_device *br_indev;
+
+		br_indev = nf_bridge_get_physindev(oldskb, net);
+		if (!br_indev)
+			goto free_nskb;
 
 		nskb->dev = br_indev;
 		niph->tot_len = htons(nskb->len);
diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c
index 27b2164f4c43..196dd4ecb5e2 100644
--- a/net/ipv6/netfilter/nf_reject_ipv6.c
+++ b/net/ipv6/netfilter/nf_reject_ipv6.c
@@ -278,7 +278,6 @@ static int nf_reject6_fill_skb_dst(struct sk_buff *skb_in)
 void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb,
 		    int hook)
 {
-	struct net_device *br_indev __maybe_unused;
 	struct sk_buff *nskb;
 	struct tcphdr _otcph;
 	const struct tcphdr *otcph;
@@ -354,9 +353,15 @@ void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb,
 	 * build the eth header using the original destination's MAC as the
 	 * source, and send the RST packet directly.
 	 */
-	br_indev = nf_bridge_get_physindev(oldskb, net);
-	if (br_indev) {
+	if (nf_bridge_info_exists(oldskb)) {
 		struct ethhdr *oeth = eth_hdr(oldskb);
+		struct net_device *br_indev;
+
+		br_indev = nf_bridge_get_physindev(oldskb, net);
+		if (!br_indev) {
+			kfree_skb(nskb);
+			return;
+		}
 
 		nskb->dev = br_indev;
 		nskb->protocol = htons(ETH_P_IPV6);
-- 
cgit v1.2.3


From 49e60333d743ae32db3bdde2f93bc818482dd741 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Wed, 17 Jan 2024 12:36:09 -0800
Subject: blk-mq: Remove the hctx 'run' debugfs attribute

Nobody uses the debugfs hctx 'run' attribute. Hence remove this
attribute and also the code that updates the corresponding member
variable.

Suggested-by: Jens Axboe <axboe@kernel.dk>
Cc: Gabriel Ryan <gabe@cs.columbia.edu>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20240117203609.4122520-1-bvanassche@acm.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq-debugfs.c | 18 ------------------
 block/blk-mq-sched.c   |  2 --
 include/linux/blk-mq.h |  3 ---
 3 files changed, 23 deletions(-)

(limited to 'include')

diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 5cbeb9344f2f..94668e72ab09 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -479,23 +479,6 @@ out:
 	return res;
 }
 
-static int hctx_run_show(void *data, struct seq_file *m)
-{
-	struct blk_mq_hw_ctx *hctx = data;
-
-	seq_printf(m, "%lu\n", hctx->run);
-	return 0;
-}
-
-static ssize_t hctx_run_write(void *data, const char __user *buf, size_t count,
-			      loff_t *ppos)
-{
-	struct blk_mq_hw_ctx *hctx = data;
-
-	hctx->run = 0;
-	return count;
-}
-
 static int hctx_active_show(void *data, struct seq_file *m)
 {
 	struct blk_mq_hw_ctx *hctx = data;
@@ -624,7 +607,6 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_attrs[] = {
 	{"tags_bitmap", 0400, hctx_tags_bitmap_show},
 	{"sched_tags", 0400, hctx_sched_tags_show},
 	{"sched_tags_bitmap", 0400, hctx_sched_tags_bitmap_show},
-	{"run", 0600, hctx_run_show, hctx_run_write},
 	{"active", 0400, hctx_active_show},
 	{"dispatch_busy", 0400, hctx_dispatch_busy_show},
 	{"type", 0400, hctx_type_show},
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 67c95f31b15b..451a2c1f1f32 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -324,8 +324,6 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 	if (unlikely(blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q)))
 		return;
 
-	hctx->run++;
-
 	/*
 	 * A return of -EAGAIN is an indication that hctx->dispatch is not
 	 * empty and we must run again in order to avoid starving flushes.
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index a676e116085f..7a8150a5f051 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -391,9 +391,6 @@ struct blk_mq_hw_ctx {
 	 */
 	struct blk_mq_tags	*sched_tags;
 
-	/** @run: Number of dispatched requests. */
-	unsigned long		run;
-
 	/** @numa_node: NUMA node the storage adapter has been connected to. */
 	unsigned int		numa_node;
 	/** @queue_num: Index of this hardware queue. */
-- 
cgit v1.2.3


From 1e7196fa5b0312a6a3e49e7c1300e145afcba96b Mon Sep 17 00:00:00 2001
From: Charlie Jenkins <charlie@rivosinc.com>
Date: Mon, 8 Jan 2024 15:57:02 -0800
Subject: asm-generic: Improve csum_fold

This csum_fold implementation introduced into arch/arc by Vineet Gupta
is better than the default implementation on at least arc, x86, and
riscv. Using GCC trunk and compiling non-inlined version, this
implementation has 41.6667%, 25% fewer instructions on riscv64, x86-64
respectively with -O3 optimization. Most implmentations override this
default in asm, but this should be more performant than all of those
other implementations except for arm which has barrel shifting and
sparc32 which has a carry flag.

Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
Reviewed-by: David Laight <david.laight@aculab.com>
Link: https://lore.kernel.org/r/20240108-optimize_checksum-v15-1-1c50de5f2167@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 include/asm-generic/checksum.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/asm-generic/checksum.h b/include/asm-generic/checksum.h
index 43e18db89c14..ad928cce268b 100644
--- a/include/asm-generic/checksum.h
+++ b/include/asm-generic/checksum.h
@@ -2,6 +2,8 @@
 #ifndef __ASM_GENERIC_CHECKSUM_H
 #define __ASM_GENERIC_CHECKSUM_H
 
+#include <linux/bitops.h>
+
 /*
  * computes the checksum of a memory block at buff, length len,
  * and adds in "sum" (32-bit)
@@ -31,9 +33,7 @@ extern __sum16 ip_fast_csum(const void *iph, unsigned int ihl);
 static inline __sum16 csum_fold(__wsum csum)
 {
 	u32 sum = (__force u32)csum;
-	sum = (sum & 0xffff) + (sum >> 16);
-	sum = (sum & 0xffff) + (sum >> 16);
-	return (__force __sum16)~sum;
+	return (__force __sum16)((~sum - ror32(sum, 16)) >> 16);
 }
 #endif
 
-- 
cgit v1.2.3


From 66967a32d3b16ed447e76fed4d946bab52e43d86 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Wed, 17 Jan 2024 19:31:40 -0800
Subject: bpf: extract bpf_ctx_convert_map logic and make it more reusable

Refactor btf_get_prog_ctx_type() a bit to allow reuse of
bpf_ctx_convert_map logic in more than one places. Simplify interface by
returning btf_type instead of btf_member (field reference in BTF).

To do the above we need to touch and start untangling
btf_translate_to_vmlinux() implementation. We do the bare minimum to
not regress anything for btf_translate_to_vmlinux(), but its
implementation is very questionable for what it claims to be doing.
Mapping kfunc argument types to kernel corresponding types conceptually
is quite different from recognizing program context types. Fixing this
is out of scope for this change though.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20240118033143.3384355-3-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/btf.h |  2 +-
 kernel/bpf/btf.c    | 71 +++++++++++++++++++++++++++++++++--------------------
 2 files changed, 46 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/include/linux/btf.h b/include/linux/btf.h
index 59d404e22814..cf5c6ff48981 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -512,7 +512,7 @@ s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id);
 int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_cnt,
 				struct module *owner);
 struct btf_struct_meta *btf_find_struct_meta(const struct btf *btf, u32 btf_id);
-const struct btf_member *
+const struct btf_type *
 btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf,
 		      const struct btf_type *t, enum bpf_prog_type prog_type,
 		      int arg);
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 51e8b4bee0c8..10ac9efc662d 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -5615,21 +5615,46 @@ static u8 bpf_ctx_convert_map[] = {
 #undef BPF_MAP_TYPE
 #undef BPF_LINK_TYPE
 
-const struct btf_member *
-btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf,
-		      const struct btf_type *t, enum bpf_prog_type prog_type,
-		      int arg)
+static const struct btf_type *find_canonical_prog_ctx_type(enum bpf_prog_type prog_type)
 {
 	const struct btf_type *conv_struct;
-	const struct btf_type *ctx_struct;
 	const struct btf_member *ctx_type;
-	const char *tname, *ctx_tname;
 
 	conv_struct = bpf_ctx_convert.t;
-	if (!conv_struct) {
-		bpf_log(log, "btf_vmlinux is malformed\n");
+	if (!conv_struct)
 		return NULL;
-	}
+	/* prog_type is valid bpf program type. No need for bounds check. */
+	ctx_type = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2;
+	/* ctx_type is a pointer to prog_ctx_type in vmlinux.
+	 * Like 'struct __sk_buff'
+	 */
+	return btf_type_by_id(btf_vmlinux, ctx_type->type);
+}
+
+static int find_kern_ctx_type_id(enum bpf_prog_type prog_type)
+{
+	const struct btf_type *conv_struct;
+	const struct btf_member *ctx_type;
+
+	conv_struct = bpf_ctx_convert.t;
+	if (!conv_struct)
+		return -EFAULT;
+	/* prog_type is valid bpf program type. No need for bounds check. */
+	ctx_type = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2 + 1;
+	/* ctx_type is a pointer to prog_ctx_type in vmlinux.
+	 * Like 'struct sk_buff'
+	 */
+	return ctx_type->type;
+}
+
+const struct btf_type *
+btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf,
+		      const struct btf_type *t, enum bpf_prog_type prog_type,
+		      int arg)
+{
+	const struct btf_type *ctx_type;
+	const char *tname, *ctx_tname;
+
 	t = btf_type_by_id(btf, t->type);
 	while (btf_type_is_modifier(t))
 		t = btf_type_by_id(btf, t->type);
@@ -5646,17 +5671,15 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf,
 		bpf_log(log, "arg#%d struct doesn't have a name\n", arg);
 		return NULL;
 	}
-	/* prog_type is valid bpf program type. No need for bounds check. */
-	ctx_type = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2;
-	/* ctx_struct is a pointer to prog_ctx_type in vmlinux.
-	 * Like 'struct __sk_buff'
-	 */
-	ctx_struct = btf_type_by_id(btf_vmlinux, ctx_type->type);
-	if (!ctx_struct)
+
+	ctx_type = find_canonical_prog_ctx_type(prog_type);
+	if (!ctx_type) {
+		bpf_log(log, "btf_vmlinux is malformed\n");
 		/* should not happen */
 		return NULL;
+	}
 again:
-	ctx_tname = btf_name_by_offset(btf_vmlinux, ctx_struct->name_off);
+	ctx_tname = btf_name_by_offset(btf_vmlinux, ctx_type->name_off);
 	if (!ctx_tname) {
 		/* should not happen */
 		bpf_log(log, "Please fix kernel include/linux/bpf_types.h\n");
@@ -5677,10 +5700,10 @@ again:
 		/* bpf_user_pt_regs_t is a typedef, so resolve it to
 		 * underlying struct and check name again
 		 */
-		if (!btf_type_is_modifier(ctx_struct))
+		if (!btf_type_is_modifier(ctx_type))
 			return NULL;
-		while (btf_type_is_modifier(ctx_struct))
-			ctx_struct = btf_type_by_id(btf_vmlinux, ctx_struct->type);
+		while (btf_type_is_modifier(ctx_type))
+			ctx_type = btf_type_by_id(btf_vmlinux, ctx_type->type);
 		goto again;
 	}
 	return ctx_type;
@@ -5692,13 +5715,9 @@ static int btf_translate_to_vmlinux(struct bpf_verifier_log *log,
 				     enum bpf_prog_type prog_type,
 				     int arg)
 {
-	const struct btf_member *prog_ctx_type, *kern_ctx_type;
-
-	prog_ctx_type = btf_get_prog_ctx_type(log, btf, t, prog_type, arg);
-	if (!prog_ctx_type)
+	if (!btf_get_prog_ctx_type(log, btf, t, prog_type, arg))
 		return -ENOENT;
-	kern_ctx_type = prog_ctx_type + 1;
-	return kern_ctx_type->type;
+	return find_kern_ctx_type_id(prog_type);
 }
 
 int get_kern_ctx_btf_id(struct bpf_verifier_log *log, enum bpf_prog_type prog_type)
-- 
cgit v1.2.3


From 7a8e9cdf9405819105ae7405cd91e482bf574b01 Mon Sep 17 00:00:00 2001
From: Nathan Lynch <nathanl@linux.ibm.com>
Date: Tue, 16 Jan 2024 08:09:25 -0600
Subject: seq_buf: Make DECLARE_SEQ_BUF() usable
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Using the address operator on the array doesn't work:

./include/linux/seq_buf.h:27:27: error: initialization of ‘char *’
  from incompatible pointer type ‘char (*)[128]’
  [-Werror=incompatible-pointer-types]
   27 |                 .buffer = &__ ## NAME ## _buffer,       \
      |                           ^

Apart from fixing that, we can improve DECLARE_SEQ_BUF() by using a
compound literal to define the buffer array without attaching a name
to it. This makes the macro a single statement, allowing constructs
such as:

  static DECLARE_SEQ_BUF(my_seq_buf, MYSB_SIZE);

to work as intended.

Link: https://lkml.kernel.org/r/20240116-declare-seq-buf-fix-v1-1-915db4692f32@linux.ibm.com

Cc: stable@vger.kernel.org
Acked-by: Kees Cook <keescook@chromium.org>
Fixes: dcc4e5728eea ("seq_buf: Introduce DECLARE_SEQ_BUF and seq_buf_str()")
Signed-off-by: Nathan Lynch <nathanl@linux.ibm.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/seq_buf.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h
index 5fb1f12c33f9..c44f4b47b945 100644
--- a/include/linux/seq_buf.h
+++ b/include/linux/seq_buf.h
@@ -22,9 +22,8 @@ struct seq_buf {
 };
 
 #define DECLARE_SEQ_BUF(NAME, SIZE)			\
-	char __ ## NAME ## _buffer[SIZE] = "";		\
 	struct seq_buf NAME = {				\
-		.buffer = &__ ## NAME ## _buffer,	\
+		.buffer = (char[SIZE]) { 0 },		\
 		.size = SIZE,				\
 	}
 
-- 
cgit v1.2.3


From b60db383e2ba64a18e49b6bef3be1ab18aa159f1 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 23 Nov 2023 10:40:40 +0100
Subject: include/linux/i2c.h: remove I2C_CLASS_DDC support

After removal of the legacy EEPROM driver and I2C_CLASS_DDC support in
olpc_dcon there's no i2c client driver left supporting I2C_CLASS_DDC.
Class-based device auto-detection is a legacy mechanism and shouldn't
be used in new code. So we can remove this class completely now.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 include/linux/i2c.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index 0dae9db27538..d029aade338f 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -850,7 +850,6 @@ static inline void i2c_mark_adapter_resumed(struct i2c_adapter *adap)
 
 /* i2c adapter classes (bitmask) */
 #define I2C_CLASS_HWMON		(1<<0)	/* lm_sensors, ... */
-#define I2C_CLASS_DDC		(1<<3)	/* DDC bus on graphics adapters */
 #define I2C_CLASS_SPD		(1<<7)	/* Memory modules */
 /* Warn users that the adapter doesn't support classes anymore */
 #define I2C_CLASS_DEPRECATED	(1<<8)
-- 
cgit v1.2.3


From 73febd775bdbdb98c81255ff85773ac410ded5c4 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Sun, 12 Nov 2023 17:54:41 -0500
Subject: i2c: create debugfs entry per adapter

Two drivers already implement custom debugfs handling for their
i2c_adapter and more will come. So, let the core create a debugfs
directory per adapter and pass that to drivers for their debugfs files.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/i2c-core-base.c | 11 +++++++++++
 include/linux/i2c.h         |  2 ++
 2 files changed, 13 insertions(+)

(limited to 'include')

diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c
index eac90a3cf61a..f6c828bbd166 100644
--- a/drivers/i2c/i2c-core-base.c
+++ b/drivers/i2c/i2c-core-base.c
@@ -16,6 +16,7 @@
 #include <linux/acpi.h>
 #include <linux/clk/clk-conf.h>
 #include <linux/completion.h>
+#include <linux/debugfs.h>
 #include <linux/delay.h>
 #include <linux/err.h>
 #include <linux/errno.h>
@@ -67,6 +68,8 @@ static int i2c_detect(struct i2c_adapter *adapter, struct i2c_driver *driver);
 static DEFINE_STATIC_KEY_FALSE(i2c_trace_msg_key);
 static bool is_registered;
 
+static struct dentry *i2c_debugfs_root;
+
 int i2c_transfer_trace_reg(void)
 {
 	static_branch_inc(&i2c_trace_msg_key);
@@ -1524,6 +1527,8 @@ static int i2c_register_adapter(struct i2c_adapter *adap)
 		goto out_list;
 	}
 
+	adap->debugfs = debugfs_create_dir(dev_name(&adap->dev), i2c_debugfs_root);
+
 	res = i2c_setup_smbus_alert(adap);
 	if (res)
 		goto out_reg;
@@ -1563,6 +1568,7 @@ static int i2c_register_adapter(struct i2c_adapter *adap)
 	return 0;
 
 out_reg:
+	debugfs_remove_recursive(adap->debugfs);
 	init_completion(&adap->dev_released);
 	device_unregister(&adap->dev);
 	wait_for_completion(&adap->dev_released);
@@ -1764,6 +1770,8 @@ void i2c_del_adapter(struct i2c_adapter *adap)
 
 	i2c_host_notify_irq_teardown(adap);
 
+	debugfs_remove_recursive(adap->debugfs);
+
 	/* wait until all references to the device are gone
 	 *
 	 * FIXME: This is old code and should ideally be replaced by an
@@ -2061,6 +2069,8 @@ static int __init i2c_init(void)
 
 	is_registered = true;
 
+	i2c_debugfs_root = debugfs_create_dir("i2c", NULL);
+
 #ifdef CONFIG_I2C_COMPAT
 	i2c_adapter_compat_class = class_compat_register("i2c-adapter");
 	if (!i2c_adapter_compat_class) {
@@ -2099,6 +2109,7 @@ static void __exit i2c_exit(void)
 #ifdef CONFIG_I2C_COMPAT
 	class_compat_unregister(i2c_adapter_compat_class);
 #endif
+	debugfs_remove_recursive(i2c_debugfs_root);
 	bus_unregister(&i2c_bus_type);
 	tracepoint_synchronize_unregister();
 }
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index d029aade338f..e01fb1097868 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -746,6 +746,8 @@ struct i2c_adapter {
 
 	struct irq_domain *host_notify_domain;
 	struct regulator *bus_regulator;
+
+	struct dentry *debugfs;
 };
 #define to_i2c_adapter(d) container_of(d, struct i2c_adapter, dev)
 
-- 
cgit v1.2.3


From 94959c0e796e41128483588d133b9a7003b409f9 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 19 Dec 2023 16:22:43 +0100
Subject: i2c: make i2c_bus_type const

Now that the driver core can properly handle constant struct bus_type,
move the i2c_bus_type variable to be a constant structure as well, placing
it into read-only memory which can not be modified at runtime.

Note, the sound/soc/rockchip/rk3399_gru_sound.c also needed tweaking as
it decided to save off a pointer to a bus type for internal stuff, and
it was using the i2c_bus_type as well.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/i2c-core-base.c           | 2 +-
 include/linux/i2c.h                   | 2 +-
 sound/soc/rockchip/rk3399_gru_sound.c | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c
index f6c828bbd166..3bd48d4b6318 100644
--- a/drivers/i2c/i2c-core-base.c
+++ b/drivers/i2c/i2c-core-base.c
@@ -692,7 +692,7 @@ static struct attribute *i2c_dev_attrs[] = {
 };
 ATTRIBUTE_GROUPS(i2c_dev);
 
-struct bus_type i2c_bus_type = {
+const struct bus_type i2c_bus_type = {
 	.name		= "i2c",
 	.match		= i2c_device_match,
 	.probe		= i2c_device_probe,
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index e01fb1097868..652ecb7abeda 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -23,7 +23,7 @@
 #include <linux/swab.h>		/* for swab16 */
 #include <uapi/linux/i2c.h>
 
-extern struct bus_type i2c_bus_type;
+extern const struct bus_type i2c_bus_type;
 extern struct device_type i2c_adapter_type;
 extern struct device_type i2c_client_type;
 
diff --git a/sound/soc/rockchip/rk3399_gru_sound.c b/sound/soc/rockchip/rk3399_gru_sound.c
index 1a504ebd3a0e..6c89c7331229 100644
--- a/sound/soc/rockchip/rk3399_gru_sound.c
+++ b/sound/soc/rockchip/rk3399_gru_sound.c
@@ -446,7 +446,7 @@ static const struct rockchip_sound_route rockchip_routes[] = {
 
 struct dailink_match_data {
 	const char *compatible;
-	struct bus_type *bus_type;
+	const struct bus_type *bus_type;
 };
 
 static const struct dailink_match_data dailink_match[] = {
-- 
cgit v1.2.3


From a8355235dbd571b32c750ee756dd6dac216d18f2 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Wed, 8 Nov 2023 07:38:07 +0100
Subject: i2c: mux: reg: Remove class-based device auto-detection support

Legacy class-based device auto-detection shouldn't be used in new code.
Therefore remove support in i2c-mux-reg as long as we don't have a
user of this feature yet.

Link: https://lore.kernel.org/linux-i2c/a22978a4-88e4-46f4-b71c-032b22321599@gmail.com/
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/muxes/i2c-mux-reg.c           | 4 +---
 include/linux/platform_data/i2c-mux-reg.h | 2 --
 2 files changed, 1 insertion(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/i2c/muxes/i2c-mux-reg.c b/drivers/i2c/muxes/i2c-mux-reg.c
index 9efc1ed01577..8489971babd3 100644
--- a/drivers/i2c/muxes/i2c-mux-reg.c
+++ b/drivers/i2c/muxes/i2c-mux-reg.c
@@ -159,7 +159,6 @@ static int i2c_mux_reg_probe(struct platform_device *pdev)
 	struct regmux *mux;
 	struct i2c_adapter *parent;
 	struct resource *res;
-	unsigned int class;
 	int i, ret, nr;
 
 	mux = devm_kzalloc(&pdev->dev, sizeof(*mux), GFP_KERNEL);
@@ -213,9 +212,8 @@ static int i2c_mux_reg_probe(struct platform_device *pdev)
 
 	for (i = 0; i < mux->data.n_values; i++) {
 		nr = mux->data.base_nr ? (mux->data.base_nr + i) : 0;
-		class = mux->data.classes ? mux->data.classes[i] : 0;
 
-		ret = i2c_mux_add_adapter(muxc, nr, mux->data.values[i], class);
+		ret = i2c_mux_add_adapter(muxc, nr, mux->data.values[i], 0);
 		if (ret)
 			goto err_del_mux_adapters;
 	}
diff --git a/include/linux/platform_data/i2c-mux-reg.h b/include/linux/platform_data/i2c-mux-reg.h
index 2543c2a1c9ae..e2e895768311 100644
--- a/include/linux/platform_data/i2c-mux-reg.h
+++ b/include/linux/platform_data/i2c-mux-reg.h
@@ -17,7 +17,6 @@
  * @n_values: Number of multiplexer channels
  * @little_endian: Indicating if the register is in little endian
  * @write_only: Reading the register is not allowed by hardware
- * @classes: Optional I2C auto-detection classes
  * @idle: Value to write to mux when idle
  * @idle_in_use: indicate if idle value is in use
  * @reg: Virtual address of the register to switch channel
@@ -30,7 +29,6 @@ struct i2c_mux_reg_platform_data {
 	int n_values;
 	bool little_endian;
 	bool write_only;
-	const unsigned int *classes;
 	u32 idle;
 	bool idle_in_use;
 	void __iomem *reg;
-- 
cgit v1.2.3


From ef175b29a242fea98f467f008237484b03c94834 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Fri, 15 Jan 2021 15:24:59 -0600
Subject: of: Stop circularly including of_device.h and of_platform.h

The DT of_device.h and of_platform.h headers date back to the separate
of_platform_bus_type before it was merged into the regular platform bus.
As part of that merge prepping Arm DT support 13 years ago, they
"temporarily" include each other. The headers also include
platform_device.h and of.h. The result was lots of drivers relied on
these implicit includes.

Now the entire tree has been fixed over the last couple of cycles to
explicitly include the necessary headers instead of relying on
of_device.h and/or of_platform.h implicit includes, so the implicit and
circular includes can finally be removed.

Signed-off-by: Rob Herring <robh@kernel.org>
---
 include/linux/of_device.h   | 5 +----
 include/linux/of_platform.h | 4 ++--
 2 files changed, 3 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/of_device.h b/include/linux/of_device.h
index a72661e47faa..9042bca5bb84 100644
--- a/include/linux/of_device.h
+++ b/include/linux/of_device.h
@@ -2,10 +2,7 @@
 #ifndef _LINUX_OF_DEVICE_H
 #define _LINUX_OF_DEVICE_H
 
-#include <linux/platform_device.h>
-#include <linux/of_platform.h> /* temporary until merge */
-
-#include <linux/of.h>
+#include <linux/device/driver.h>
 
 struct device;
 struct of_device_id;
diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h
index fadfea575485..a2ff1ad48f7f 100644
--- a/include/linux/of_platform.h
+++ b/include/linux/of_platform.h
@@ -7,11 +7,11 @@
  */
 
 #include <linux/mod_devicetable.h>
-#include <linux/of_device.h>
-#include <linux/platform_device.h>
 
 struct device;
+struct device_node;
 struct of_device_id;
+struct platform_device;
 
 /**
  * struct of_dev_auxdata - lookup table entry for device names & platform_data
-- 
cgit v1.2.3


From d26270061ae66b915138af7cd73ca6f8b85e6b44 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Thu, 18 Jan 2024 12:31:55 -0800
Subject: string: Remove strlcpy()

With all the users of strlcpy() removed[1] from the kernel, remove the
API, self-tests, and other references. Leave mentions in Documentation
(about its deprecation), and in checkpatch.pl (to help migrate host-only
tools/ usage). Long live strscpy().

Link: https://github.com/KSPP/linux/issues/89 [1]
Cc: Azeem Shaikh <azeemshaikh38@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Whitcroft <apw@canonical.com>
Cc: Joe Perches <joe@perches.com>
Cc: Dwaipayan Ray <dwaipayanray1@gmail.com>
Cc: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Cc: linux-hardening@vger.kernel.org
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 include/linux/fortify-string.h                | 51 ---------------------------
 include/linux/string.h                        |  3 --
 lib/nlattr.c                                  |  2 +-
 lib/string.c                                  | 15 --------
 lib/test_fortify/write_overflow-strlcpy-src.c |  5 ---
 lib/test_fortify/write_overflow-strlcpy.c     |  5 ---
 6 files changed, 1 insertion(+), 80 deletions(-)
 delete mode 100644 lib/test_fortify/write_overflow-strlcpy-src.c
 delete mode 100644 lib/test_fortify/write_overflow-strlcpy.c

(limited to 'include')

diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h
index 79ef6ac4c021..89a6888f2f9e 100644
--- a/include/linux/fortify-string.h
+++ b/include/linux/fortify-string.h
@@ -214,51 +214,6 @@ __kernel_size_t __fortify_strlen(const char * const POS p)
 	return ret;
 }
 
-/* Defined after fortified strlen() to reuse it. */
-extern size_t __real_strlcpy(char *, const char *, size_t) __RENAME(strlcpy);
-/**
- * strlcpy - Copy a string into another string buffer
- *
- * @p: pointer to destination of copy
- * @q: pointer to NUL-terminated source string to copy
- * @size: maximum number of bytes to write at @p
- *
- * If strlen(@q) >= @size, the copy of @q will be truncated at
- * @size - 1 bytes. @p will always be NUL-terminated.
- *
- * Do not use this function. While FORTIFY_SOURCE tries to avoid
- * over-reads when calculating strlen(@q), it is still possible.
- * Prefer strscpy(), though note its different return values for
- * detecting truncation.
- *
- * Returns total number of bytes written to @p, including terminating NUL.
- *
- */
-__FORTIFY_INLINE size_t strlcpy(char * const POS p, const char * const POS q, size_t size)
-{
-	const size_t p_size = __member_size(p);
-	const size_t q_size = __member_size(q);
-	size_t q_len;	/* Full count of source string length. */
-	size_t len;	/* Count of characters going into destination. */
-
-	if (p_size == SIZE_MAX && q_size == SIZE_MAX)
-		return __real_strlcpy(p, q, size);
-	q_len = strlen(q);
-	len = (q_len >= size) ? size - 1 : q_len;
-	if (__builtin_constant_p(size) && __builtin_constant_p(q_len) && size) {
-		/* Write size is always larger than destination. */
-		if (len >= p_size)
-			__write_overflow();
-	}
-	if (size) {
-		if (len >= p_size)
-			fortify_panic(__func__);
-		__underlying_memcpy(p, q, len);
-		p[len] = '\0';
-	}
-	return q_len;
-}
-
 /* Defined after fortified strnlen() to reuse it. */
 extern ssize_t __real_strscpy(char *, const char *, size_t) __RENAME(strscpy);
 /**
@@ -272,12 +227,6 @@ extern ssize_t __real_strscpy(char *, const char *, size_t) __RENAME(strscpy);
  * @p buffer. The behavior is undefined if the string buffers overlap. The
  * destination @p buffer is always NUL terminated, unless it's zero-sized.
  *
- * Preferred to strlcpy() since the API doesn't require reading memory
- * from the source @q string beyond the specified @size bytes, and since
- * the return value is easier to error-check than strlcpy()'s.
- * In addition, the implementation is robust to the string changing out
- * from underneath it, unlike the current strlcpy() implementation.
- *
  * Preferred to strncpy() since it always returns a valid string, and
  * doesn't unnecessarily force the tail of the destination buffer to be
  * zero padded. If padding is desired please use strscpy_pad().
diff --git a/include/linux/string.h b/include/linux/string.h
index ce137830a0b9..ab148d8dbfc1 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -66,9 +66,6 @@ extern char * strcpy(char *,const char *);
 #ifndef __HAVE_ARCH_STRNCPY
 extern char * strncpy(char *,const char *, __kernel_size_t);
 #endif
-#ifndef __HAVE_ARCH_STRLCPY
-size_t strlcpy(char *, const char *, size_t);
-#endif
 #ifndef __HAVE_ARCH_STRSCPY
 ssize_t strscpy(char *, const char *, size_t);
 #endif
diff --git a/lib/nlattr.c b/lib/nlattr.c
index dc15e7888fc1..ed2ab43e1b22 100644
--- a/lib/nlattr.c
+++ b/lib/nlattr.c
@@ -758,7 +758,7 @@ EXPORT_SYMBOL(nla_find);
  * @dstsize: Size of destination buffer.
  *
  * Copies at most dstsize - 1 bytes into the destination buffer.
- * Unlike strlcpy the destination buffer is always padded out.
+ * Unlike strscpy() the destination buffer is always padded out.
  *
  * Return:
  * * srclen - Returns @nla length (not including the trailing %NUL).
diff --git a/lib/string.c b/lib/string.c
index be26623953d2..6891d15ce991 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -103,21 +103,6 @@ char *strncpy(char *dest, const char *src, size_t count)
 EXPORT_SYMBOL(strncpy);
 #endif
 
-#ifndef __HAVE_ARCH_STRLCPY
-size_t strlcpy(char *dest, const char *src, size_t size)
-{
-	size_t ret = strlen(src);
-
-	if (size) {
-		size_t len = (ret >= size) ? size - 1 : ret;
-		__builtin_memcpy(dest, src, len);
-		dest[len] = '\0';
-	}
-	return ret;
-}
-EXPORT_SYMBOL(strlcpy);
-#endif
-
 #ifndef __HAVE_ARCH_STRSCPY
 ssize_t strscpy(char *dest, const char *src, size_t count)
 {
diff --git a/lib/test_fortify/write_overflow-strlcpy-src.c b/lib/test_fortify/write_overflow-strlcpy-src.c
deleted file mode 100644
index 91bf83ebd34a..000000000000
--- a/lib/test_fortify/write_overflow-strlcpy-src.c
+++ /dev/null
@@ -1,5 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-#define TEST	\
-	strlcpy(small, large_src, sizeof(small) + 1)
-
-#include "test_fortify.h"
diff --git a/lib/test_fortify/write_overflow-strlcpy.c b/lib/test_fortify/write_overflow-strlcpy.c
deleted file mode 100644
index 1883db7c0cd6..000000000000
--- a/lib/test_fortify/write_overflow-strlcpy.c
+++ /dev/null
@@ -1,5 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-#define TEST	\
-	strlcpy(instance.buf, large_src, sizeof(instance.buf) + 1)
-
-#include "test_fortify.h"
-- 
cgit v1.2.3